Global seed set to 42
['p_np'] False
2 1
iupac_vocab_size: 1491
training... 1491

  0%|          | 0/469 [00:00<?, ?it/s]Some weights of the model checkpoint at checkpoints/iupac were not used when initializing GPT2ForSequenceClassification: ['lm_head.weight']
- This IS expected if you are initializing GPT2ForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing GPT2ForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
GPU available: True, used: True
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]

  | Name        | Type                          | Params
--------------------------------------------------------------
0 | transformer | GPT2ForSequenceClassification | 7.1 M 
--------------------------------------------------------------
75.9 K    Trainable params
7.0 M     Non-trainable params
7.1 M     Total params
28.416    Total estimated model params size (MB)

Validation sanity check: 0it [00:00, ?it/s]
Validation sanity check:   0%|          | 0/2 [00:00<?, ?it/s]
Validation sanity check:  50%|█████     | 1/2 [00:02<00:02,  2.29s/it]
                                                                      Global seed set to 42


Training: 0it [00:00, ?it/s]
Training:   0%|          | 0/938 [00:00<?, ?it/s]
Epoch 0:   0%|          | 0/938 [00:00<?, ?it/s] 
Epoch 0:   0%|          | 1/938 [00:00<01:31, 10.19it/s, loss=3.7, v_num=5]
Epoch 0:   0%|          | 2/938 [00:00<01:14, 12.52it/s, loss=3.7, v_num=5]
Epoch 0:   0%|          | 2/938 [00:00<01:14, 12.49it/s, loss=3.36, v_num=5]
Epoch 0:   0%|          | 3/938 [00:00<01:10, 13.29it/s, loss=3.4, v_num=5] 
Epoch 0:   0%|          | 4/938 [00:00<01:09, 13.41it/s, loss=3.4, v_num=5]
Epoch 0:   0%|          | 4/938 [00:00<01:09, 13.40it/s, loss=3.39, v_num=5]
Epoch 0:   1%|          | 5/938 [00:00<01:03, 14.60it/s, loss=3.42, v_num=5]
Epoch 0:   1%|          | 6/938 [00:00<01:04, 14.42it/s, loss=3.42, v_num=5]
Epoch 0:   1%|          | 6/938 [00:00<01:04, 14.41it/s, loss=3.35, v_num=5]
Epoch 0:   1%|          | 7/938 [00:00<01:03, 14.68it/s, loss=3.37, v_num=5]
Epoch 0:   1%|          | 8/938 [00:00<01:00, 15.35it/s, loss=3.37, v_num=5]
Epoch 0:   1%|          | 8/938 [00:00<01:00, 15.34it/s, loss=3.37, v_num=5]
Epoch 0:   1%|          | 9/938 [00:00<00:59, 15.53it/s, loss=3.34, v_num=5]
Epoch 0:   1%|          | 10/938 [00:00<01:00, 15.31it/s, loss=3.34, v_num=5]
Epoch 0:   1%|          | 10/938 [00:00<01:00, 15.30it/s, loss=3.31, v_num=5]
Epoch 0:   1%|          | 11/938 [00:00<00:59, 15.51it/s, loss=3.33, v_num=5]
Epoch 0:   1%|▏         | 12/938 [00:00<00:59, 15.53it/s, loss=3.33, v_num=5]
Epoch 0:   1%|▏         | 12/938 [00:00<00:59, 15.52it/s, loss=3.31, v_num=5]
Epoch 0:   1%|▏         | 13/938 [00:00<00:58, 15.69it/s, loss=3.31, v_num=5]
Epoch 0:   1%|▏         | 14/938 [00:00<00:58, 15.83it/s, loss=3.31, v_num=5]
Epoch 0:   1%|▏         | 14/938 [00:00<00:58, 15.83it/s, loss=3.3, v_num=5] 
Epoch 0:   2%|▏         | 15/938 [00:00<00:58, 15.65it/s, loss=3.28, v_num=5]
Epoch 0:   2%|▏         | 16/938 [00:01<00:58, 15.80it/s, loss=3.28, v_num=5]
Epoch 0:   2%|▏         | 16/938 [00:01<00:58, 15.80it/s, loss=3.25, v_num=5]
Epoch 0:   2%|▏         | 17/938 [00:01<00:57, 15.90it/s, loss=3.24, v_num=5]
Epoch 0:   2%|▏         | 18/938 [00:01<00:57, 16.00it/s, loss=3.24, v_num=5]
Epoch 0:   2%|▏         | 18/938 [00:01<00:57, 15.99it/s, loss=3.23, v_num=5]
Epoch 0:   2%|▏         | 19/938 [00:01<00:57, 15.94it/s, loss=3.2, v_num=5] 
Epoch 0:   2%|▏         | 20/938 [00:01<00:57, 15.87it/s, loss=3.2, v_num=5]
Epoch 0:   2%|▏         | 20/938 [00:01<00:57, 15.87it/s, loss=3.17, v_num=5]
Epoch 0:   2%|▏         | 21/938 [00:01<00:57, 15.94it/s, loss=3.13, v_num=5]
Epoch 0:   2%|▏         | 22/938 [00:01<00:56, 16.17it/s, loss=3.13, v_num=5]
Epoch 0:   2%|▏         | 22/938 [00:01<00:56, 16.16it/s, loss=3.09, v_num=5]
Epoch 0:   2%|▏         | 23/938 [00:01<00:56, 16.18it/s, loss=3.03, v_num=5]
Epoch 0:   3%|▎         | 24/938 [00:01<00:56, 16.16it/s, loss=3.03, v_num=5]
Epoch 0:   3%|▎         | 24/938 [00:01<00:56, 16.15it/s, loss=2.98, v_num=5]
Epoch 0:   3%|▎         | 25/938 [00:01<00:55, 16.30it/s, loss=2.91, v_num=5]
Epoch 0:   3%|▎         | 26/938 [00:01<00:56, 16.28it/s, loss=2.91, v_num=5]
Epoch 0:   3%|▎         | 26/938 [00:01<00:56, 16.28it/s, loss=2.86, v_num=5]
Epoch 0:   3%|▎         | 27/938 [00:01<00:56, 16.17it/s, loss=2.77, v_num=5]
Epoch 0:   3%|▎         | 28/938 [00:01<00:56, 16.16it/s, loss=2.77, v_num=5]
Epoch 0:   3%|▎         | 28/938 [00:01<00:56, 16.15it/s, loss=2.7, v_num=5] 
Epoch 0:   3%|▎         | 29/938 [00:01<00:56, 16.03it/s, loss=2.65, v_num=5]
Epoch 0:   3%|▎         | 30/938 [00:01<00:56, 16.12it/s, loss=2.65, v_num=5]
Epoch 0:   3%|▎         | 30/938 [00:01<00:56, 16.11it/s, loss=2.57, v_num=5]
Epoch 0:   3%|▎         | 31/938 [00:01<00:56, 16.06it/s, loss=2.49, v_num=5]
Epoch 0:   3%|▎         | 32/938 [00:01<00:56, 16.01it/s, loss=2.49, v_num=5]
Epoch 0:   3%|▎         | 32/938 [00:01<00:56, 16.01it/s, loss=2.43, v_num=5]
Epoch 0:   4%|▎         | 33/938 [00:02<00:56, 16.03it/s, loss=2.33, v_num=5]
Epoch 0:   4%|▎         | 34/938 [00:02<00:56, 16.01it/s, loss=2.33, v_num=5]
Epoch 0:   4%|▎         | 34/938 [00:02<00:56, 16.01it/s, loss=2.27, v_num=5]
Epoch 0:   4%|▎         | 35/938 [00:02<00:56, 16.04it/s, loss=2.22, v_num=5]
Epoch 0:   4%|▍         | 36/938 [00:02<00:56, 16.01it/s, loss=2.22, v_num=5]
Epoch 0:   4%|▍         | 36/938 [00:02<00:56, 16.01it/s, loss=2.16, v_num=5]
Epoch 0:   4%|▍         | 37/938 [00:02<00:56, 15.86it/s, loss=2.1, v_num=5] 
Epoch 0:   4%|▍         | 38/938 [00:02<00:56, 15.91it/s, loss=2.1, v_num=5]
Epoch 0:   4%|▍         | 38/938 [00:02<00:56, 15.90it/s, loss=2.01, v_num=5]
Epoch 0:   4%|▍         | 39/938 [00:02<00:56, 15.94it/s, loss=1.95, v_num=5]
Epoch 0:   4%|▍         | 40/938 [00:02<00:56, 15.93it/s, loss=1.95, v_num=5]
Epoch 0:   4%|▍         | 40/938 [00:02<00:56, 15.93it/s, loss=1.92, v_num=5]
Epoch 0:   4%|▍         | 41/938 [00:02<00:56, 15.96it/s, loss=1.87, v_num=5]
Epoch 0:   4%|▍         | 42/938 [00:02<00:56, 15.96it/s, loss=1.87, v_num=5]
Epoch 0:   4%|▍         | 42/938 [00:02<00:56, 15.96it/s, loss=1.83, v_num=5]
Epoch 0:   5%|▍         | 43/938 [00:02<00:56, 15.94it/s, loss=1.81, v_num=5]
Epoch 0:   5%|▍         | 44/938 [00:02<00:56, 15.90it/s, loss=1.81, v_num=5]
Epoch 0:   5%|▍         | 44/938 [00:02<00:56, 15.90it/s, loss=1.77, v_num=5]
Epoch 0:   5%|▍         | 45/938 [00:02<00:56, 15.83it/s, loss=1.75, v_num=5]
Epoch 0:   5%|▍         | 46/938 [00:02<00:56, 15.86it/s, loss=1.75, v_num=5]
Epoch 0:   5%|▍         | 46/938 [00:02<00:56, 15.86it/s, loss=1.73, v_num=5]
Epoch 0:   5%|▌         | 47/938 [00:02<00:56, 15.86it/s, loss=1.76, v_num=5]
Epoch 0:   5%|▌         | 48/938 [00:03<00:56, 15.84it/s, loss=1.76, v_num=5]
Epoch 0:   5%|▌         | 48/938 [00:03<00:56, 15.84it/s, loss=1.73, v_num=5]
Epoch 0:   5%|▌         | 49/938 [00:03<00:56, 15.85it/s, loss=1.72, v_num=5]
Epoch 0:   5%|▌         | 50/938 [00:03<00:56, 15.82it/s, loss=1.72, v_num=5]
Epoch 0:   5%|▌         | 50/938 [00:03<00:56, 15.82it/s, loss=1.75, v_num=5]
Epoch 0:   5%|▌         | 51/938 [00:03<00:55, 15.84it/s, loss=1.74, v_num=5]
Epoch 0:   6%|▌         | 52/938 [00:03<00:55, 15.84it/s, loss=1.74, v_num=5]
Epoch 0:   6%|▌         | 52/938 [00:03<00:55, 15.84it/s, loss=1.73, v_num=5]
Epoch 0:   6%|▌         | 53/938 [00:03<00:56, 15.79it/s, loss=1.75, v_num=5]
Epoch 0:   6%|▌         | 54/938 [00:03<00:55, 15.86it/s, loss=1.75, v_num=5]
Epoch 0:   6%|▌         | 54/938 [00:03<00:55, 15.86it/s, loss=1.73, v_num=5]
Epoch 0:   6%|▌         | 55/938 [00:03<00:55, 15.88it/s, loss=1.71, v_num=5]
Epoch 0:   6%|▌         | 56/938 [00:03<00:55, 15.85it/s, loss=1.71, v_num=5]
Epoch 0:   6%|▌         | 56/938 [00:03<00:55, 15.85it/s, loss=1.72, v_num=5]
Epoch 0:   6%|▌         | 57/938 [00:03<00:55, 15.88it/s, loss=1.72, v_num=5]
Epoch 0:   6%|▌         | 58/938 [00:03<00:55, 15.89it/s, loss=1.72, v_num=5]
Epoch 0:   6%|▌         | 58/938 [00:03<00:55, 15.89it/s, loss=1.74, v_num=5]
Epoch 0:   6%|▋         | 59/938 [00:03<00:55, 15.92it/s, loss=1.75, v_num=5]
Epoch 0:   6%|▋         | 60/938 [00:03<00:55, 15.95it/s, loss=1.75, v_num=5]
Epoch 0:   6%|▋         | 60/938 [00:03<00:55, 15.95it/s, loss=1.73, v_num=5]
Epoch 0:   7%|▋         | 61/938 [00:03<00:54, 15.96it/s, loss=1.73, v_num=5]
Epoch 0:   7%|▋         | 62/938 [00:03<00:54, 15.95it/s, loss=1.73, v_num=5]
Epoch 0:   7%|▋         | 62/938 [00:03<00:54, 15.95it/s, loss=1.73, v_num=5]
Epoch 0:   7%|▋         | 63/938 [00:03<00:54, 15.95it/s, loss=1.73, v_num=5]
Epoch 0:   7%|▋         | 64/938 [00:04<00:55, 15.83it/s, loss=1.73, v_num=5]
Epoch 0:   7%|▋         | 64/938 [00:04<00:55, 15.83it/s, loss=1.74, v_num=5]
Epoch 0:   7%|▋         | 65/938 [00:04<00:55, 15.87it/s, loss=1.74, v_num=5]
Epoch 0:   7%|▋         | 66/938 [00:04<00:55, 15.74it/s, loss=1.74, v_num=5]
Epoch 0:   7%|▋         | 66/938 [00:04<00:55, 15.74it/s, loss=1.74, v_num=5]
Epoch 0:   7%|▋         | 67/938 [00:04<00:55, 15.73it/s, loss=1.71, v_num=5]
Epoch 0:   7%|▋         | 68/938 [00:04<00:55, 15.73it/s, loss=1.71, v_num=5]
Epoch 0:   7%|▋         | 68/938 [00:04<00:55, 15.72it/s, loss=1.72, v_num=5]
Epoch 0:   7%|▋         | 69/938 [00:04<00:55, 15.74it/s, loss=1.71, v_num=5]
Epoch 0:   7%|▋         | 70/938 [00:04<00:54, 15.79it/s, loss=1.71, v_num=5]
Epoch 0:   7%|▋         | 70/938 [00:04<00:54, 15.79it/s, loss=1.69, v_num=5]
Epoch 0:   8%|▊         | 71/938 [00:04<00:54, 15.80it/s, loss=1.7, v_num=5] 
Epoch 0:   8%|▊         | 72/938 [00:04<00:54, 15.75it/s, loss=1.7, v_num=5]
Epoch 0:   8%|▊         | 72/938 [00:04<00:54, 15.75it/s, loss=1.7, v_num=5]
Epoch 0:   8%|▊         | 73/938 [00:04<00:54, 15.76it/s, loss=1.71, v_num=5]
Epoch 0:   8%|▊         | 74/938 [00:04<00:54, 15.72it/s, loss=1.71, v_num=5]
Epoch 0:   8%|▊         | 74/938 [00:04<00:54, 15.72it/s, loss=1.71, v_num=5]
Epoch 0:   8%|▊         | 75/938 [00:04<00:54, 15.75it/s, loss=1.72, v_num=5]
Epoch 0:   8%|▊         | 76/938 [00:04<00:54, 15.74it/s, loss=1.72, v_num=5]
Epoch 0:   8%|▊         | 76/938 [00:04<00:54, 15.74it/s, loss=1.7, v_num=5] 
Epoch 0:   8%|▊         | 77/938 [00:04<00:54, 15.73it/s, loss=1.69, v_num=5]
Epoch 0:   8%|▊         | 78/938 [00:04<00:54, 15.73it/s, loss=1.69, v_num=5]
Epoch 0:   8%|▊         | 78/938 [00:04<00:54, 15.72it/s, loss=1.69, v_num=5]
Epoch 0:   8%|▊         | 79/938 [00:05<00:54, 15.69it/s, loss=1.67, v_num=5]
Epoch 0:   9%|▊         | 80/938 [00:05<00:54, 15.71it/s, loss=1.67, v_num=5]
Epoch 0:   9%|▊         | 80/938 [00:05<00:54, 15.71it/s, loss=1.67, v_num=5]
Epoch 0:   9%|▊         | 81/938 [00:05<00:54, 15.72it/s, loss=1.68, v_num=5]
Epoch 0:   9%|▊         | 82/938 [00:05<00:54, 15.74it/s, loss=1.68, v_num=5]
Epoch 0:   9%|▊         | 82/938 [00:05<00:54, 15.73it/s, loss=1.66, v_num=5]
Epoch 0:   9%|▉         | 83/938 [00:05<00:54, 15.73it/s, loss=1.66, v_num=5]
Epoch 0:   9%|▉         | 84/938 [00:05<00:54, 15.75it/s, loss=1.66, v_num=5]
Epoch 0:   9%|▉         | 84/938 [00:05<00:54, 15.75it/s, loss=1.64, v_num=5]
Epoch 0:   9%|▉         | 85/938 [00:05<00:54, 15.76it/s, loss=1.64, v_num=5]
Epoch 0:   9%|▉         | 86/938 [00:05<00:53, 15.82it/s, loss=1.64, v_num=5]
Epoch 0:   9%|▉         | 86/938 [00:05<00:53, 15.81it/s, loss=1.66, v_num=5]
Epoch 0:   9%|▉         | 87/938 [00:05<00:53, 15.82it/s, loss=1.66, v_num=5]
Epoch 0:   9%|▉         | 88/938 [00:05<00:53, 15.84it/s, loss=1.66, v_num=5]
Epoch 0:   9%|▉         | 88/938 [00:05<00:53, 15.84it/s, loss=1.66, v_num=5]
Epoch 0:   9%|▉         | 89/938 [00:05<00:53, 15.88it/s, loss=1.67, v_num=5]
Epoch 0:  10%|▉         | 90/938 [00:05<00:53, 15.87it/s, loss=1.67, v_num=5]
Epoch 0:  10%|▉         | 90/938 [00:05<00:53, 15.87it/s, loss=1.68, v_num=5]
Epoch 0:  10%|▉         | 91/938 [00:05<00:53, 15.84it/s, loss=1.66, v_num=5]
Epoch 0:  10%|▉         | 92/938 [00:05<00:53, 15.86it/s, loss=1.66, v_num=5]
Epoch 0:  10%|▉         | 92/938 [00:05<00:53, 15.86it/s, loss=1.65, v_num=5]
Epoch 0:  10%|▉         | 93/938 [00:05<00:53, 15.83it/s, loss=1.64, v_num=5]
Epoch 0:  10%|█         | 94/938 [00:05<00:53, 15.85it/s, loss=1.64, v_num=5]
Epoch 0:  10%|█         | 94/938 [00:05<00:53, 15.85it/s, loss=1.66, v_num=5]
Epoch 0:  10%|█         | 95/938 [00:05<00:53, 15.83it/s, loss=1.65, v_num=5]
Epoch 0:  10%|█         | 96/938 [00:06<00:53, 15.85it/s, loss=1.65, v_num=5]
Epoch 0:  10%|█         | 96/938 [00:06<00:53, 15.84it/s, loss=1.66, v_num=5]
Epoch 0:  10%|█         | 97/938 [00:06<00:53, 15.86it/s, loss=1.67, v_num=5]
Epoch 0:  10%|█         | 98/938 [00:06<00:53, 15.85it/s, loss=1.67, v_num=5]
Epoch 0:  10%|█         | 98/938 [00:06<00:53, 15.85it/s, loss=1.66, v_num=5]
Epoch 0:  11%|█         | 99/938 [00:06<00:52, 15.84it/s, loss=1.68, v_num=5]
Epoch 0:  11%|█         | 100/938 [00:06<00:52, 15.88it/s, loss=1.68, v_num=5]
Epoch 0:  11%|█         | 100/938 [00:06<00:52, 15.88it/s, loss=1.68, v_num=5]
Epoch 0:  11%|█         | 101/938 [00:06<00:52, 15.85it/s, loss=1.67, v_num=5]
Epoch 0:  11%|█         | 102/938 [00:06<00:52, 15.85it/s, loss=1.67, v_num=5]
Epoch 0:  11%|█         | 102/938 [00:06<00:52, 15.85it/s, loss=1.68, v_num=5]
Epoch 0:  11%|█         | 103/938 [00:06<00:52, 15.88it/s, loss=1.68, v_num=5]
Epoch 0:  11%|█         | 104/938 [00:06<00:52, 15.89it/s, loss=1.68, v_num=5]
Epoch 0:  11%|█         | 104/938 [00:06<00:52, 15.89it/s, loss=1.68, v_num=5]
Epoch 0:  11%|█         | 105/938 [00:06<00:52, 15.87it/s, loss=1.67, v_num=5]
Epoch 0:  11%|█▏        | 106/938 [00:06<00:52, 15.86it/s, loss=1.67, v_num=5]
Epoch 0:  11%|█▏        | 106/938 [00:06<00:52, 15.86it/s, loss=1.67, v_num=5]
Epoch 0:  11%|█▏        | 107/938 [00:06<00:52, 15.85it/s, loss=1.66, v_num=5]
Epoch 0:  12%|█▏        | 108/938 [00:06<00:52, 15.85it/s, loss=1.66, v_num=5]
Epoch 0:  12%|█▏        | 108/938 [00:06<00:52, 15.85it/s, loss=1.66, v_num=5]
Epoch 0:  12%|█▏        | 109/938 [00:06<00:52, 15.86it/s, loss=1.65, v_num=5]
Epoch 0:  12%|█▏        | 110/938 [00:06<00:52, 15.88it/s, loss=1.65, v_num=5]
Epoch 0:  12%|█▏        | 110/938 [00:06<00:52, 15.88it/s, loss=1.64, v_num=5]
Epoch 0:  12%|█▏        | 111/938 [00:06<00:52, 15.90it/s, loss=1.65, v_num=5]
Epoch 0:  12%|█▏        | 112/938 [00:07<00:51, 15.89it/s, loss=1.65, v_num=5]
Epoch 0:  12%|█▏        | 112/938 [00:07<00:51, 15.89it/s, loss=1.65, v_num=5]
Epoch 0:  12%|█▏        | 113/938 [00:07<00:51, 15.88it/s, loss=1.65, v_num=5]
Epoch 0:  12%|█▏        | 114/938 [00:07<00:51, 15.90it/s, loss=1.65, v_num=5]
Epoch 0:  12%|█▏        | 114/938 [00:07<00:51, 15.90it/s, loss=1.64, v_num=5]
Epoch 0:  12%|█▏        | 115/938 [00:07<00:51, 15.85it/s, loss=1.63, v_num=5]
Epoch 0:  12%|█▏        | 116/938 [00:07<00:51, 15.85it/s, loss=1.63, v_num=5]
Epoch 0:  12%|█▏        | 116/938 [00:07<00:51, 15.85it/s, loss=1.63, v_num=5]
Epoch 0:  12%|█▏        | 117/938 [00:07<00:51, 15.84it/s, loss=1.61, v_num=5]
Epoch 0:  13%|█▎        | 118/938 [00:07<00:51, 15.86it/s, loss=1.61, v_num=5]
Epoch 0:  13%|█▎        | 118/938 [00:07<00:51, 15.86it/s, loss=1.61, v_num=5]
Epoch 0:  13%|█▎        | 119/938 [00:07<00:51, 15.87it/s, loss=1.61, v_num=5]
Epoch 0:  13%|█▎        | 120/938 [00:07<00:51, 15.88it/s, loss=1.61, v_num=5]
Epoch 0:  13%|█▎        | 120/938 [00:07<00:51, 15.88it/s, loss=1.61, v_num=5]
Epoch 0:  13%|█▎        | 121/938 [00:07<00:51, 15.89it/s, loss=1.63, v_num=5]
Epoch 0:  13%|█▎        | 122/938 [00:07<00:51, 15.89it/s, loss=1.63, v_num=5]
Epoch 0:  13%|█▎        | 122/938 [00:07<00:51, 15.89it/s, loss=1.61, v_num=5]
Epoch 0:  13%|█▎        | 123/938 [00:07<00:51, 15.89it/s, loss=1.6, v_num=5] 
Epoch 0:  13%|█▎        | 124/938 [00:07<00:51, 15.88it/s, loss=1.6, v_num=5]
Epoch 0:  13%|█▎        | 124/938 [00:07<00:51, 15.88it/s, loss=1.58, v_num=5]
Epoch 0:  13%|█▎        | 125/938 [00:07<00:51, 15.89it/s, loss=1.58, v_num=5]
Epoch 0:  13%|█▎        | 126/938 [00:07<00:51, 15.89it/s, loss=1.58, v_num=5]
Epoch 0:  13%|█▎        | 126/938 [00:07<00:51, 15.89it/s, loss=1.57, v_num=5]
Epoch 0:  14%|█▎        | 127/938 [00:07<00:51, 15.90it/s, loss=1.56, v_num=5]
Epoch 0:  14%|█▎        | 128/938 [00:08<00:50, 15.91it/s, loss=1.56, v_num=5]
Epoch 0:  14%|█▎        | 128/938 [00:08<00:50, 15.91it/s, loss=1.56, v_num=5]
Epoch 0:  14%|█▍        | 129/938 [00:08<00:50, 15.92it/s, loss=1.54, v_num=5]
Epoch 0:  14%|█▍        | 130/938 [00:08<00:50, 15.93it/s, loss=1.54, v_num=5]
Epoch 0:  14%|█▍        | 130/938 [00:08<00:50, 15.93it/s, loss=1.53, v_num=5]
Epoch 0:  14%|█▍        | 131/938 [00:08<00:50, 15.94it/s, loss=1.52, v_num=5]
Epoch 0:  14%|█▍        | 132/938 [00:08<00:50, 15.92it/s, loss=1.52, v_num=5]
Epoch 0:  14%|█▍        | 132/938 [00:08<00:50, 15.92it/s, loss=1.52, v_num=5]
Epoch 0:  14%|█▍        | 133/938 [00:08<00:50, 15.93it/s, loss=1.51, v_num=5]
Epoch 0:  14%|█▍        | 134/938 [00:08<00:50, 15.92it/s, loss=1.51, v_num=5]
Epoch 0:  14%|█▍        | 134/938 [00:08<00:50, 15.92it/s, loss=1.5, v_num=5] 
Epoch 0:  14%|█▍        | 135/938 [00:08<00:50, 15.91it/s, loss=1.5, v_num=5]
Epoch 0:  14%|█▍        | 136/938 [00:08<00:50, 15.92it/s, loss=1.5, v_num=5]
Epoch 0:  14%|█▍        | 136/938 [00:08<00:50, 15.92it/s, loss=1.48, v_num=5]
Epoch 0:  15%|█▍        | 137/938 [00:08<00:50, 15.91it/s, loss=1.47, v_num=5]
Epoch 0:  15%|█▍        | 138/938 [00:08<00:50, 15.92it/s, loss=1.47, v_num=5]
Epoch 0:  15%|█▍        | 138/938 [00:08<00:50, 15.92it/s, loss=1.46, v_num=5]
Epoch 0:  15%|█▍        | 139/938 [00:08<00:50, 15.93it/s, loss=1.45, v_num=5]
Epoch 0:  15%|█▍        | 140/938 [00:08<00:50, 15.92it/s, loss=1.45, v_num=5]
Epoch 0:  15%|█▍        | 140/938 [00:08<00:50, 15.92it/s, loss=1.43, v_num=5]
Epoch 0:  15%|█▌        | 141/938 [00:08<00:50, 15.93it/s, loss=1.4, v_num=5] 
Epoch 0:  15%|█▌        | 142/938 [00:08<00:49, 15.97it/s, loss=1.4, v_num=5]
Epoch 0:  15%|█▌        | 142/938 [00:08<00:49, 15.97it/s, loss=1.39, v_num=5]
Epoch 0:  15%|█▌        | 143/938 [00:08<00:49, 15.97it/s, loss=1.37, v_num=5]
Epoch 0:  15%|█▌        | 144/938 [00:09<00:49, 15.97it/s, loss=1.37, v_num=5]
Epoch 0:  15%|█▌        | 144/938 [00:09<00:49, 15.97it/s, loss=1.36, v_num=5]
Epoch 0:  15%|█▌        | 145/938 [00:09<00:49, 15.99it/s, loss=1.34, v_num=5]
Epoch 0:  16%|█▌        | 146/938 [00:09<00:49, 15.99it/s, loss=1.34, v_num=5]
Epoch 0:  16%|█▌        | 146/938 [00:09<00:49, 15.99it/s, loss=1.31, v_num=5]
Epoch 0:  16%|█▌        | 147/938 [00:09<00:49, 15.99it/s, loss=1.3, v_num=5] 
Epoch 0:  16%|█▌        | 148/938 [00:09<00:49, 15.93it/s, loss=1.3, v_num=5]
Epoch 0:  16%|█▌        | 148/938 [00:09<00:49, 15.93it/s, loss=1.27, v_num=5]
Epoch 0:  16%|█▌        | 149/938 [00:09<00:49, 15.92it/s, loss=1.28, v_num=5]
Epoch 0:  16%|█▌        | 150/938 [00:09<00:49, 15.93it/s, loss=1.28, v_num=5]
Epoch 0:  16%|█▌        | 150/938 [00:09<00:49, 15.93it/s, loss=1.27, v_num=5]
Epoch 0:  16%|█▌        | 151/938 [00:09<00:49, 15.93it/s, loss=1.24, v_num=5]
Epoch 0:  16%|█▌        | 152/938 [00:09<00:49, 15.92it/s, loss=1.24, v_num=5]
Epoch 0:  16%|█▌        | 152/938 [00:09<00:49, 15.92it/s, loss=1.21, v_num=5]
Epoch 0:  16%|█▋        | 153/938 [00:09<00:49, 15.95it/s, loss=1.19, v_num=5]
Epoch 0:  16%|█▋        | 154/938 [00:09<00:49, 15.95it/s, loss=1.19, v_num=5]
Epoch 0:  16%|█▋        | 154/938 [00:09<00:49, 15.95it/s, loss=1.19, v_num=5]
Epoch 0:  17%|█▋        | 155/938 [00:09<00:49, 15.95it/s, loss=1.17, v_num=5]
Epoch 0:  17%|█▋        | 156/938 [00:09<00:48, 15.96it/s, loss=1.17, v_num=5]
Epoch 0:  17%|█▋        | 156/938 [00:09<00:48, 15.96it/s, loss=1.15, v_num=5]
Epoch 0:  17%|█▋        | 157/938 [00:09<00:48, 15.94it/s, loss=1.14, v_num=5]
Epoch 0:  17%|█▋        | 158/938 [00:09<00:48, 15.94it/s, loss=1.14, v_num=5]
Epoch 0:  17%|█▋        | 158/938 [00:09<00:48, 15.94it/s, loss=1.14, v_num=5]
Epoch 0:  17%|█▋        | 159/938 [00:09<00:48, 15.94it/s, loss=1.12, v_num=5]
Epoch 0:  17%|█▋        | 160/938 [00:10<00:48, 15.94it/s, loss=1.12, v_num=5]
Epoch 0:  17%|█▋        | 160/938 [00:10<00:48, 15.94it/s, loss=1.11, v_num=5]
Epoch 0:  17%|█▋        | 161/938 [00:10<00:48, 15.94it/s, loss=1.11, v_num=5]
Epoch 0:  17%|█▋        | 162/938 [00:10<00:48, 15.92it/s, loss=1.11, v_num=5]
Epoch 0:  17%|█▋        | 162/938 [00:10<00:48, 15.92it/s, loss=1.1, v_num=5] 
Epoch 0:  17%|█▋        | 163/938 [00:10<00:48, 15.91it/s, loss=1.1, v_num=5]
Epoch 0:  17%|█▋        | 164/938 [00:10<00:48, 15.91it/s, loss=1.1, v_num=5]
Epoch 0:  17%|█▋        | 164/938 [00:10<00:48, 15.91it/s, loss=1.1, v_num=5]
Epoch 0:  18%|█▊        | 165/938 [00:10<00:48, 15.91it/s, loss=1.09, v_num=5]
Epoch 0:  18%|█▊        | 166/938 [00:10<00:48, 15.91it/s, loss=1.09, v_num=5]
Epoch 0:  18%|█▊        | 166/938 [00:10<00:48, 15.91it/s, loss=1.1, v_num=5] 
Epoch 0:  18%|█▊        | 167/938 [00:10<00:48, 15.91it/s, loss=1.09, v_num=5]
Epoch 0:  18%|█▊        | 168/938 [00:10<00:48, 15.91it/s, loss=1.09, v_num=5]
Epoch 0:  18%|█▊        | 168/938 [00:10<00:48, 15.91it/s, loss=1.1, v_num=5] 
Epoch 0:  18%|█▊        | 169/938 [00:10<00:48, 15.93it/s, loss=1.09, v_num=5]
Epoch 0:  18%|█▊        | 170/938 [00:10<00:48, 15.92it/s, loss=1.09, v_num=5]
Epoch 0:  18%|█▊        | 170/938 [00:10<00:48, 15.92it/s, loss=1.08, v_num=5]
Epoch 0:  18%|█▊        | 171/938 [00:10<00:48, 15.92it/s, loss=1.08, v_num=5]
Epoch 0:  18%|█▊        | 172/938 [00:10<00:48, 15.92it/s, loss=1.08, v_num=5]
Epoch 0:  18%|█▊        | 172/938 [00:10<00:48, 15.92it/s, loss=1.08, v_num=5]
Epoch 0:  18%|█▊        | 173/938 [00:10<00:48, 15.92it/s, loss=1.07, v_num=5]
Epoch 0:  19%|█▊        | 174/938 [00:10<00:47, 15.92it/s, loss=1.07, v_num=5]
Epoch 0:  19%|█▊        | 174/938 [00:10<00:47, 15.92it/s, loss=1.05, v_num=5]
Epoch 0:  19%|█▊        | 175/938 [00:10<00:47, 15.91it/s, loss=1.05, v_num=5]
Epoch 0:  19%|█▉        | 176/938 [00:11<00:47, 15.89it/s, loss=1.05, v_num=5]
Epoch 0:  19%|█▉        | 176/938 [00:11<00:47, 15.89it/s, loss=1.05, v_num=5]
Epoch 0:  19%|█▉        | 177/938 [00:11<00:47, 15.90it/s, loss=1.06, v_num=5]
Epoch 0:  19%|█▉        | 178/938 [00:11<00:47, 15.90it/s, loss=1.06, v_num=5]
Epoch 0:  19%|█▉        | 178/938 [00:11<00:47, 15.90it/s, loss=1.05, v_num=5]
Epoch 0:  19%|█▉        | 179/938 [00:11<00:47, 15.91it/s, loss=1.04, v_num=5]
Epoch 0:  19%|█▉        | 180/938 [00:11<00:47, 15.93it/s, loss=1.04, v_num=5]
Epoch 0:  19%|█▉        | 180/938 [00:11<00:47, 15.93it/s, loss=1.04, v_num=5]
Epoch 0:  19%|█▉        | 181/938 [00:11<00:47, 15.93it/s, loss=1.03, v_num=5]
Epoch 0:  19%|█▉        | 182/938 [00:11<00:47, 15.92it/s, loss=1.03, v_num=5]
Epoch 0:  19%|█▉        | 182/938 [00:11<00:47, 15.92it/s, loss=1.04, v_num=5]
Epoch 0:  20%|█▉        | 183/938 [00:11<00:47, 15.93it/s, loss=1.03, v_num=5]
Epoch 0:  20%|█▉        | 184/938 [00:11<00:47, 15.93it/s, loss=1.03, v_num=5]
Epoch 0:  20%|█▉        | 184/938 [00:11<00:47, 15.93it/s, loss=1.04, v_num=5]
Epoch 0:  20%|█▉        | 185/938 [00:11<00:47, 15.94it/s, loss=1.04, v_num=5]
Epoch 0:  20%|█▉        | 186/938 [00:11<00:47, 15.94it/s, loss=1.04, v_num=5]
Epoch 0:  20%|█▉        | 186/938 [00:11<00:47, 15.94it/s, loss=1.03, v_num=5]
Epoch 0:  20%|█▉        | 187/938 [00:11<00:47, 15.94it/s, loss=1.03, v_num=5]
Epoch 0:  20%|██        | 188/938 [00:11<00:47, 15.93it/s, loss=1.03, v_num=5]
Epoch 0:  20%|██        | 188/938 [00:11<00:47, 15.93it/s, loss=1, v_num=5]   
Epoch 0:  20%|██        | 189/938 [00:11<00:46, 15.94it/s, loss=0.994, v_num=5]
Epoch 0:  20%|██        | 190/938 [00:11<00:46, 15.93it/s, loss=0.994, v_num=5]
Epoch 0:  20%|██        | 190/938 [00:11<00:46, 15.93it/s, loss=0.996, v_num=5]
Epoch 0:  20%|██        | 191/938 [00:11<00:46, 15.95it/s, loss=1.01, v_num=5] 
Epoch 0:  20%|██        | 192/938 [00:12<00:46, 15.94it/s, loss=1.01, v_num=5]
Epoch 0:  20%|██        | 192/938 [00:12<00:46, 15.94it/s, loss=1.01, v_num=5]
Epoch 0:  21%|██        | 193/938 [00:12<00:46, 15.94it/s, loss=1, v_num=5]   
Epoch 0:  21%|██        | 194/938 [00:12<00:46, 15.96it/s, loss=1, v_num=5]
Epoch 0:  21%|██        | 194/938 [00:12<00:46, 15.96it/s, loss=1, v_num=5]
Epoch 0:  21%|██        | 195/938 [00:12<00:46, 15.96it/s, loss=1.01, v_num=5]
Epoch 0:  21%|██        | 196/938 [00:12<00:46, 15.96it/s, loss=1.01, v_num=5]
Epoch 0:  21%|██        | 196/938 [00:12<00:46, 15.96it/s, loss=1.02, v_num=5]
Epoch 0:  21%|██        | 197/938 [00:12<00:46, 15.98it/s, loss=1.02, v_num=5]
Epoch 0:  21%|██        | 198/938 [00:12<00:46, 15.98it/s, loss=1.02, v_num=5]
Epoch 0:  21%|██        | 198/938 [00:12<00:46, 15.98it/s, loss=1.02, v_num=5]
Epoch 0:  21%|██        | 199/938 [00:12<00:46, 15.97it/s, loss=1.02, v_num=5]
Epoch 0:  21%|██▏       | 200/938 [00:12<00:46, 15.97it/s, loss=1.02, v_num=5]
Epoch 0:  21%|██▏       | 200/938 [00:12<00:46, 15.97it/s, loss=1.03, v_num=5]
Epoch 0:  21%|██▏       | 201/938 [00:12<00:46, 15.94it/s, loss=1.04, v_num=5]
Epoch 0:  22%|██▏       | 202/938 [00:12<00:46, 15.93it/s, loss=1.04, v_num=5]
Epoch 0:  22%|██▏       | 202/938 [00:12<00:46, 15.93it/s, loss=1.03, v_num=5]
Epoch 0:  22%|██▏       | 203/938 [00:12<00:46, 15.93it/s, loss=1.03, v_num=5]
Epoch 0:  22%|██▏       | 204/938 [00:12<00:46, 15.94it/s, loss=1.03, v_num=5]
Epoch 0:  22%|██▏       | 204/938 [00:12<00:46, 15.93it/s, loss=1.03, v_num=5]
Epoch 0:  22%|██▏       | 205/938 [00:12<00:45, 15.95it/s, loss=1.02, v_num=5]
Epoch 0:  22%|██▏       | 206/938 [00:12<00:45, 15.95it/s, loss=1.02, v_num=5]
Epoch 0:  22%|██▏       | 206/938 [00:12<00:45, 15.95it/s, loss=1.01, v_num=5]
Epoch 0:  22%|██▏       | 207/938 [00:12<00:45, 15.95it/s, loss=1.03, v_num=5]
Epoch 0:  22%|██▏       | 208/938 [00:13<00:45, 15.97it/s, loss=1.03, v_num=5]
Epoch 0:  22%|██▏       | 208/938 [00:13<00:45, 15.97it/s, loss=1.05, v_num=5]
Epoch 0:  22%|██▏       | 209/938 [00:13<00:45, 15.96it/s, loss=1.05, v_num=5]
Epoch 0:  22%|██▏       | 210/938 [00:13<00:45, 15.96it/s, loss=1.05, v_num=5]
Epoch 0:  22%|██▏       | 210/938 [00:13<00:45, 15.96it/s, loss=1.05, v_num=5]
Epoch 0:  22%|██▏       | 211/938 [00:13<00:45, 15.95it/s, loss=1.04, v_num=5]
Epoch 0:  23%|██▎       | 212/938 [00:13<00:45, 15.89it/s, loss=1.04, v_num=5]
Epoch 0:  23%|██▎       | 212/938 [00:13<00:45, 15.89it/s, loss=1.04, v_num=5]
Epoch 0:  23%|██▎       | 213/938 [00:13<00:45, 15.89it/s, loss=1.06, v_num=5]
Epoch 0:  23%|██▎       | 214/938 [00:13<00:45, 15.88it/s, loss=1.06, v_num=5]
Epoch 0:  23%|██▎       | 214/938 [00:13<00:45, 15.88it/s, loss=1.07, v_num=5]
Epoch 0:  23%|██▎       | 215/938 [00:13<00:45, 15.87it/s, loss=1.07, v_num=5]
Epoch 0:  23%|██▎       | 216/938 [00:13<00:45, 15.86it/s, loss=1.07, v_num=5]
Epoch 0:  23%|██▎       | 216/938 [00:13<00:45, 15.86it/s, loss=1.07, v_num=5]
Epoch 0:  23%|██▎       | 217/938 [00:13<00:45, 15.85it/s, loss=1.08, v_num=5]
Epoch 0:  23%|██▎       | 218/938 [00:13<00:45, 15.86it/s, loss=1.08, v_num=5]
Epoch 0:  23%|██▎       | 218/938 [00:13<00:45, 15.86it/s, loss=1.06, v_num=5]
Epoch 0:  23%|██▎       | 219/938 [00:13<00:45, 15.86it/s, loss=1.05, v_num=5]
Epoch 0:  23%|██▎       | 220/938 [00:13<00:45, 15.87it/s, loss=1.05, v_num=5]
Epoch 0:  23%|██▎       | 220/938 [00:13<00:45, 15.87it/s, loss=1.03, v_num=5]
Epoch 0:  24%|██▎       | 221/938 [00:13<00:45, 15.87it/s, loss=1.02, v_num=5]
Epoch 0:  24%|██▎       | 222/938 [00:13<00:45, 15.87it/s, loss=1.02, v_num=5]
Epoch 0:  24%|██▎       | 222/938 [00:13<00:45, 15.87it/s, loss=1.02, v_num=5]
Epoch 0:  24%|██▍       | 223/938 [00:14<00:45, 15.88it/s, loss=1.02, v_num=5]
Epoch 0:  24%|██▍       | 224/938 [00:14<00:44, 15.89it/s, loss=1.02, v_num=5]
Epoch 0:  24%|██▍       | 224/938 [00:14<00:44, 15.89it/s, loss=1.01, v_num=5]
Epoch 0:  24%|██▍       | 225/938 [00:14<00:44, 15.89it/s, loss=1.03, v_num=5]
Epoch 0:  24%|██▍       | 226/938 [00:14<00:44, 15.90it/s, loss=1.03, v_num=5]
Epoch 0:  24%|██▍       | 226/938 [00:14<00:44, 15.90it/s, loss=1.04, v_num=5]
Epoch 0:  24%|██▍       | 227/938 [00:14<00:44, 15.90it/s, loss=1.03, v_num=5]
Epoch 0:  24%|██▍       | 228/938 [00:14<00:44, 15.91it/s, loss=1.03, v_num=5]
Epoch 0:  24%|██▍       | 228/938 [00:14<00:44, 15.91it/s, loss=1.01, v_num=5]
Epoch 0:  24%|██▍       | 229/938 [00:14<00:44, 15.92it/s, loss=1.01, v_num=5]
Epoch 0:  25%|██▍       | 230/938 [00:14<00:44, 15.92it/s, loss=1.01, v_num=5]
Epoch 0:  25%|██▍       | 230/938 [00:14<00:44, 15.92it/s, loss=1.01, v_num=5]
Epoch 0:  25%|██▍       | 231/938 [00:14<00:44, 15.93it/s, loss=1.02, v_num=5]
Epoch 0:  25%|██▍       | 232/938 [00:14<00:44, 15.94it/s, loss=1.02, v_num=5]
Epoch 0:  25%|██▍       | 232/938 [00:14<00:44, 15.94it/s, loss=1, v_num=5]   
Epoch 0:  25%|██▍       | 233/938 [00:14<00:44, 15.94it/s, loss=0.997, v_num=5]
Epoch 0:  25%|██▍       | 234/938 [00:14<00:44, 15.94it/s, loss=0.997, v_num=5]
Epoch 0:  25%|██▍       | 234/938 [00:14<00:44, 15.94it/s, loss=0.995, v_num=5]
Epoch 0:  25%|██▌       | 235/938 [00:14<00:44, 15.96it/s, loss=0.979, v_num=5]
Epoch 0:  25%|██▌       | 236/938 [00:14<00:43, 15.97it/s, loss=0.972, v_num=5]
Epoch 0:  25%|██▌       | 237/938 [00:14<00:43, 15.97it/s, loss=0.972, v_num=5]
Epoch 0:  25%|██▌       | 237/938 [00:14<00:43, 15.97it/s, loss=0.962, v_num=5]
Epoch 0:  25%|██▌       | 238/938 [00:14<00:43, 15.98it/s, loss=0.952, v_num=5]
Epoch 0:  25%|██▌       | 239/938 [00:14<00:43, 15.98it/s, loss=0.953, v_num=5]
Epoch 0:  26%|██▌       | 240/938 [00:15<00:43, 15.98it/s, loss=0.953, v_num=5]
Epoch 0:  26%|██▌       | 240/938 [00:15<00:43, 15.98it/s, loss=0.964, v_num=5]
Epoch 0:  26%|██▌       | 241/938 [00:15<00:43, 16.00it/s, loss=0.959, v_num=5]
Epoch 0:  26%|██▌       | 242/938 [00:15<00:43, 16.01it/s, loss=0.958, v_num=5]
Epoch 0:  26%|██▌       | 243/938 [00:15<00:43, 16.01it/s, loss=0.958, v_num=5]
Epoch 0:  26%|██▌       | 243/938 [00:15<00:43, 16.01it/s, loss=0.954, v_num=5]
Epoch 0:  26%|██▌       | 244/938 [00:15<00:43, 16.02it/s, loss=0.95, v_num=5] 
Epoch 0:  26%|██▌       | 245/938 [00:15<00:43, 16.03it/s, loss=0.95, v_num=5]
Epoch 0:  26%|██▌       | 246/938 [00:15<00:43, 16.03it/s, loss=0.95, v_num=5]
Epoch 0:  26%|██▌       | 246/938 [00:15<00:43, 16.03it/s, loss=0.937, v_num=5]
Epoch 0:  26%|██▋       | 247/938 [00:15<00:43, 16.04it/s, loss=0.94, v_num=5] 
Epoch 0:  26%|██▋       | 248/938 [00:15<00:43, 16.04it/s, loss=0.947, v_num=5]
Epoch 0:  27%|██▋       | 249/938 [00:15<00:42, 16.04it/s, loss=0.947, v_num=5]
Epoch 0:  27%|██▋       | 249/938 [00:15<00:42, 16.04it/s, loss=0.945, v_num=5]
Epoch 0:  27%|██▋       | 250/938 [00:15<00:42, 16.05it/s, loss=0.951, v_num=5]
Epoch 0:  27%|██▋       | 251/938 [00:15<00:42, 16.04it/s, loss=0.938, v_num=5]
Epoch 0:  27%|██▋       | 252/938 [00:15<00:42, 16.03it/s, loss=0.938, v_num=5]
Epoch 0:  27%|██▋       | 252/938 [00:15<00:42, 16.03it/s, loss=0.934, v_num=5]
Epoch 0:  27%|██▋       | 253/938 [00:15<00:42, 16.03it/s, loss=0.947, v_num=5]
Epoch 0:  27%|██▋       | 254/938 [00:15<00:42, 16.03it/s, loss=0.943, v_num=5]
Epoch 0:  27%|██▋       | 255/938 [00:15<00:42, 16.03it/s, loss=0.943, v_num=5]
Epoch 0:  27%|██▋       | 255/938 [00:15<00:42, 16.03it/s, loss=0.956, v_num=5]
Epoch 0:  27%|██▋       | 256/938 [00:15<00:42, 16.03it/s, loss=0.954, v_num=5]
Epoch 0:  27%|██▋       | 257/938 [00:16<00:42, 16.03it/s, loss=0.947, v_num=5]
Epoch 0:  28%|██▊       | 258/938 [00:16<00:42, 16.04it/s, loss=0.947, v_num=5]
Epoch 0:  28%|██▊       | 258/938 [00:16<00:42, 16.04it/s, loss=0.955, v_num=5]
Epoch 0:  28%|██▊       | 259/938 [00:16<00:42, 16.04it/s, loss=0.969, v_num=5]
Epoch 0:  28%|██▊       | 260/938 [00:16<00:42, 16.05it/s, loss=0.973, v_num=5]
Epoch 0:  28%|██▊       | 261/938 [00:16<00:42, 16.06it/s, loss=0.973, v_num=5]
Epoch 0:  28%|██▊       | 261/938 [00:16<00:42, 16.05it/s, loss=0.985, v_num=5]
Epoch 0:  28%|██▊       | 262/938 [00:16<00:42, 16.06it/s, loss=0.988, v_num=5]
Epoch 0:  28%|██▊       | 263/938 [00:16<00:42, 16.05it/s, loss=0.989, v_num=5]
Epoch 0:  28%|██▊       | 264/938 [00:16<00:42, 16.04it/s, loss=0.989, v_num=5]
Epoch 0:  28%|██▊       | 264/938 [00:16<00:42, 16.04it/s, loss=0.992, v_num=5]
Epoch 0:  28%|██▊       | 265/938 [00:16<00:41, 16.04it/s, loss=0.976, v_num=5]
Epoch 0:  28%|██▊       | 266/938 [00:16<00:41, 16.02it/s, loss=0.984, v_num=5]
Epoch 0:  28%|██▊       | 267/938 [00:16<00:41, 16.01it/s, loss=0.984, v_num=5]
Epoch 0:  28%|██▊       | 267/938 [00:16<00:41, 16.00it/s, loss=0.989, v_num=5]
Epoch 0:  29%|██▊       | 268/938 [00:16<00:41, 16.00it/s, loss=0.976, v_num=5]
Epoch 0:  29%|██▊       | 269/938 [00:16<00:41, 15.96it/s, loss=0.977, v_num=5]
Epoch 0:  29%|██▉       | 270/938 [00:16<00:41, 15.97it/s, loss=0.977, v_num=5]
Epoch 0:  29%|██▉       | 270/938 [00:16<00:41, 15.97it/s, loss=0.979, v_num=5]
Epoch 0:  29%|██▉       | 271/938 [00:16<00:41, 15.96it/s, loss=0.973, v_num=5]
Epoch 0:  29%|██▉       | 272/938 [00:17<00:41, 15.96it/s, loss=0.979, v_num=5]
Epoch 0:  29%|██▉       | 273/938 [00:17<00:41, 15.96it/s, loss=0.979, v_num=5]
Epoch 0:  29%|██▉       | 273/938 [00:17<00:41, 15.96it/s, loss=0.958, v_num=5]
Epoch 0:  29%|██▉       | 274/938 [00:17<00:41, 15.93it/s, loss=0.954, v_num=5]
Epoch 0:  29%|██▉       | 275/938 [00:17<00:41, 15.91it/s, loss=0.947, v_num=5]
Epoch 0:  29%|██▉       | 276/938 [00:17<00:41, 15.92it/s, loss=0.947, v_num=5]
Epoch 0:  29%|██▉       | 276/938 [00:17<00:41, 15.92it/s, loss=0.945, v_num=5]
Epoch 0:  30%|██▉       | 277/938 [00:17<00:41, 15.91it/s, loss=0.939, v_num=5]
Epoch 0:  30%|██▉       | 278/938 [00:17<00:41, 15.92it/s, loss=0.942, v_num=5]
Epoch 0:  30%|██▉       | 279/938 [00:17<00:41, 15.93it/s, loss=0.942, v_num=5]
Epoch 0:  30%|██▉       | 279/938 [00:17<00:41, 15.93it/s, loss=0.934, v_num=5]
Epoch 0:  30%|██▉       | 280/938 [00:17<00:41, 15.93it/s, loss=0.931, v_num=5]
Epoch 0:  30%|██▉       | 281/938 [00:17<00:41, 15.93it/s, loss=0.924, v_num=5]
Epoch 0:  30%|███       | 282/938 [00:17<00:41, 15.94it/s, loss=0.924, v_num=5]
Epoch 0:  30%|███       | 282/938 [00:17<00:41, 15.94it/s, loss=0.921, v_num=5]
Epoch 0:  30%|███       | 283/938 [00:17<00:41, 15.94it/s, loss=0.918, v_num=5]
Epoch 0:  30%|███       | 284/938 [00:17<00:41, 15.95it/s, loss=0.918, v_num=5]
Epoch 0:  30%|███       | 285/938 [00:17<00:40, 15.94it/s, loss=0.918, v_num=5]
Epoch 0:  30%|███       | 285/938 [00:17<00:40, 15.94it/s, loss=0.92, v_num=5] 
Epoch 0:  30%|███       | 286/938 [00:17<00:40, 15.94it/s, loss=0.913, v_num=5]
Epoch 0:  31%|███       | 287/938 [00:18<00:40, 15.93it/s, loss=0.907, v_num=5]
Epoch 0:  31%|███       | 288/938 [00:18<00:40, 15.91it/s, loss=0.907, v_num=5]
Epoch 0:  31%|███       | 288/938 [00:18<00:40, 15.91it/s, loss=0.904, v_num=5]
Epoch 0:  31%|███       | 289/938 [00:18<00:40, 15.91it/s, loss=0.889, v_num=5]
Epoch 0:  31%|███       | 290/938 [00:18<00:40, 15.91it/s, loss=0.882, v_num=5]
Epoch 0:  31%|███       | 291/938 [00:18<00:40, 15.91it/s, loss=0.882, v_num=5]
Epoch 0:  31%|███       | 291/938 [00:18<00:40, 15.91it/s, loss=0.885, v_num=5]
Epoch 0:  31%|███       | 292/938 [00:18<00:40, 15.91it/s, loss=0.873, v_num=5]
Epoch 0:  31%|███       | 293/938 [00:18<00:40, 15.92it/s, loss=0.873, v_num=5]
Epoch 0:  31%|███▏      | 294/938 [00:18<00:40, 15.92it/s, loss=0.873, v_num=5]
Epoch 0:  31%|███▏      | 294/938 [00:18<00:40, 15.92it/s, loss=0.873, v_num=5]
Epoch 0:  31%|███▏      | 295/938 [00:18<00:40, 15.92it/s, loss=0.867, v_num=5]
Epoch 0:  32%|███▏      | 296/938 [00:18<00:40, 15.92it/s, loss=0.864, v_num=5]
Epoch 0:  32%|███▏      | 297/938 [00:18<00:40, 15.91it/s, loss=0.864, v_num=5]
Epoch 0:  32%|███▏      | 297/938 [00:18<00:40, 15.91it/s, loss=0.871, v_num=5]
Epoch 0:  32%|███▏      | 298/938 [00:18<00:40, 15.91it/s, loss=0.87, v_num=5] 
Epoch 0:  32%|███▏      | 299/938 [00:18<00:40, 15.91it/s, loss=0.866, v_num=5]
Epoch 0:  32%|███▏      | 300/938 [00:18<00:40, 15.90it/s, loss=0.866, v_num=5]
Epoch 0:  32%|███▏      | 300/938 [00:18<00:40, 15.90it/s, loss=0.866, v_num=5]
Epoch 0:  32%|███▏      | 301/938 [00:18<00:40, 15.90it/s, loss=0.864, v_num=5]
Epoch 0:  32%|███▏      | 302/938 [00:18<00:39, 15.90it/s, loss=0.855, v_num=5]
Epoch 0:  32%|███▏      | 303/938 [00:19<00:39, 15.90it/s, loss=0.855, v_num=5]
Epoch 0:  32%|███▏      | 303/938 [00:19<00:39, 15.90it/s, loss=0.856, v_num=5]
Epoch 0:  32%|███▏      | 304/938 [00:19<00:39, 15.89it/s, loss=0.858, v_num=5]
Epoch 0:  33%|███▎      | 305/938 [00:19<00:39, 15.89it/s, loss=0.857, v_num=5]
Epoch 0:  33%|███▎      | 306/938 [00:19<00:39, 15.89it/s, loss=0.857, v_num=5]
Epoch 0:  33%|███▎      | 306/938 [00:19<00:39, 15.88it/s, loss=0.862, v_num=5]
Epoch 0:  33%|███▎      | 307/938 [00:19<00:39, 15.89it/s, loss=0.854, v_num=5]
Epoch 0:  33%|███▎      | 308/938 [00:19<00:39, 15.89it/s, loss=0.859, v_num=5]
Epoch 0:  33%|███▎      | 309/938 [00:19<00:39, 15.89it/s, loss=0.859, v_num=5]
Epoch 0:  33%|███▎      | 309/938 [00:19<00:39, 15.89it/s, loss=0.86, v_num=5] 
Epoch 0:  33%|███▎      | 310/938 [00:19<00:39, 15.89it/s, loss=0.865, v_num=5]
Epoch 0:  33%|███▎      | 311/938 [00:19<00:39, 15.88it/s, loss=0.869, v_num=5]
Epoch 0:  33%|███▎      | 312/938 [00:19<00:39, 15.88it/s, loss=0.869, v_num=5]
Epoch 0:  33%|███▎      | 312/938 [00:19<00:39, 15.88it/s, loss=0.883, v_num=5]
Epoch 0:  33%|███▎      | 313/938 [00:19<00:39, 15.88it/s, loss=0.882, v_num=5]
Epoch 0:  33%|███▎      | 314/938 [00:19<00:39, 15.88it/s, loss=0.88, v_num=5] 
Epoch 0:  34%|███▎      | 315/938 [00:19<00:39, 15.88it/s, loss=0.88, v_num=5]
Epoch 0:  34%|███▎      | 315/938 [00:19<00:39, 15.88it/s, loss=0.874, v_num=5]
Epoch 0:  34%|███▎      | 316/938 [00:19<00:39, 15.88it/s, loss=0.873, v_num=5]
Epoch 0:  34%|███▍      | 317/938 [00:19<00:39, 15.88it/s, loss=0.872, v_num=5]
Epoch 0:  34%|███▍      | 318/938 [00:20<00:39, 15.89it/s, loss=0.872, v_num=5]
Epoch 0:  34%|███▍      | 318/938 [00:20<00:39, 15.89it/s, loss=0.863, v_num=5]
Epoch 0:  34%|███▍      | 319/938 [00:20<00:38, 15.89it/s, loss=0.861, v_num=5]
Epoch 0:  34%|███▍      | 320/938 [00:20<00:38, 15.89it/s, loss=0.856, v_num=5]
Epoch 0:  34%|███▍      | 321/938 [00:20<00:38, 15.89it/s, loss=0.856, v_num=5]
Epoch 0:  34%|███▍      | 321/938 [00:20<00:38, 15.89it/s, loss=0.868, v_num=5]
Epoch 0:  34%|███▍      | 322/938 [00:20<00:38, 15.88it/s, loss=0.876, v_num=5]
Epoch 0:  34%|███▍      | 323/938 [00:20<00:38, 15.89it/s, loss=0.873, v_num=5]
Epoch 0:  35%|███▍      | 324/938 [00:20<00:38, 15.89it/s, loss=0.873, v_num=5]
Epoch 0:  35%|███▍      | 324/938 [00:20<00:38, 15.89it/s, loss=0.87, v_num=5] 
Epoch 0:  35%|███▍      | 325/938 [00:20<00:38, 15.90it/s, loss=0.87, v_num=5]
Epoch 0:  35%|███▍      | 326/938 [00:20<00:38, 15.91it/s, loss=0.875, v_num=5]
Epoch 0:  35%|███▍      | 327/938 [00:20<00:38, 15.91it/s, loss=0.875, v_num=5]
Epoch 0:  35%|███▍      | 327/938 [00:20<00:38, 15.91it/s, loss=0.89, v_num=5] 
Epoch 0:  35%|███▍      | 328/938 [00:20<00:38, 15.91it/s, loss=0.895, v_num=5]
Epoch 0:  35%|███▌      | 329/938 [00:20<00:38, 15.91it/s, loss=0.897, v_num=5]
Epoch 0:  35%|███▌      | 330/938 [00:20<00:38, 15.90it/s, loss=0.897, v_num=5]
Epoch 0:  35%|███▌      | 330/938 [00:20<00:38, 15.90it/s, loss=0.889, v_num=5]
Epoch 0:  35%|███▌      | 331/938 [00:20<00:38, 15.90it/s, loss=0.89, v_num=5] 
Epoch 0:  35%|███▌      | 332/938 [00:20<00:38, 15.90it/s, loss=0.878, v_num=5]
Epoch 0:  36%|███▌      | 333/938 [00:20<00:38, 15.89it/s, loss=0.878, v_num=5]
Epoch 0:  36%|███▌      | 333/938 [00:20<00:38, 15.89it/s, loss=0.887, v_num=5]
Epoch 0:  36%|███▌      | 334/938 [00:21<00:37, 15.90it/s, loss=0.892, v_num=5]
Epoch 0:  36%|███▌      | 335/938 [00:21<00:37, 15.90it/s, loss=0.895, v_num=5]
Epoch 0:  36%|███▌      | 336/938 [00:21<00:37, 15.90it/s, loss=0.895, v_num=5]
Epoch 0:  36%|███▌      | 336/938 [00:21<00:37, 15.90it/s, loss=0.894, v_num=5]
Epoch 0:  36%|███▌      | 337/938 [00:21<00:37, 15.91it/s, loss=0.889, v_num=5]
Epoch 0:  36%|███▌      | 338/938 [00:21<00:37, 15.91it/s, loss=0.883, v_num=5]
Epoch 0:  36%|███▌      | 339/938 [00:21<00:37, 15.92it/s, loss=0.883, v_num=5]
Epoch 0:  36%|███▌      | 339/938 [00:21<00:37, 15.92it/s, loss=0.879, v_num=5]
Epoch 0:  36%|███▌      | 340/938 [00:21<00:37, 15.93it/s, loss=0.879, v_num=5]
Epoch 0:  36%|███▋      | 341/938 [00:21<00:37, 15.93it/s, loss=0.867, v_num=5]
Epoch 0:  36%|███▋      | 342/938 [00:21<00:37, 15.93it/s, loss=0.867, v_num=5]
Epoch 0:  36%|███▋      | 342/938 [00:21<00:37, 15.93it/s, loss=0.863, v_num=5]
Epoch 0:  37%|███▋      | 343/938 [00:21<00:37, 15.94it/s, loss=0.868, v_num=5]
Epoch 0:  37%|███▋      | 344/938 [00:21<00:37, 15.94it/s, loss=0.872, v_num=5]
Epoch 0:  37%|███▋      | 345/938 [00:21<00:37, 15.94it/s, loss=0.872, v_num=5]
Epoch 0:  37%|███▋      | 345/938 [00:21<00:37, 15.94it/s, loss=0.875, v_num=5]
Epoch 0:  37%|███▋      | 346/938 [00:21<00:37, 15.94it/s, loss=0.865, v_num=5]
Epoch 0:  37%|███▋      | 347/938 [00:21<00:37, 15.94it/s, loss=0.859, v_num=5]
Epoch 0:  37%|███▋      | 348/938 [00:21<00:37, 15.94it/s, loss=0.859, v_num=5]
Epoch 0:  37%|███▋      | 348/938 [00:21<00:37, 15.94it/s, loss=0.853, v_num=5]
Epoch 0:  37%|███▋      | 349/938 [00:21<00:36, 15.94it/s, loss=0.854, v_num=5]
Epoch 0:  37%|███▋      | 350/938 [00:21<00:36, 15.94it/s, loss=0.86, v_num=5] 
Epoch 0:  37%|███▋      | 351/938 [00:22<00:36, 15.94it/s, loss=0.86, v_num=5]
Epoch 0:  37%|███▋      | 351/938 [00:22<00:36, 15.94it/s, loss=0.846, v_num=5]
Epoch 0:  38%|███▊      | 352/938 [00:22<00:36, 15.95it/s, loss=0.843, v_num=5]
Epoch 0:  38%|███▊      | 353/938 [00:22<00:36, 15.94it/s, loss=0.833, v_num=5]
Epoch 0:  38%|███▊      | 354/938 [00:22<00:36, 15.94it/s, loss=0.833, v_num=5]
Epoch 0:  38%|███▊      | 354/938 [00:22<00:36, 15.94it/s, loss=0.846, v_num=5]
Epoch 0:  38%|███▊      | 355/938 [00:22<00:36, 15.94it/s, loss=0.844, v_num=5]
Epoch 0:  38%|███▊      | 356/938 [00:22<00:36, 15.93it/s, loss=0.85, v_num=5] 
Epoch 0:  38%|███▊      | 357/938 [00:22<00:36, 15.94it/s, loss=0.85, v_num=5]
Epoch 0:  38%|███▊      | 357/938 [00:22<00:36, 15.94it/s, loss=0.855, v_num=5]
Epoch 0:  38%|███▊      | 358/938 [00:22<00:36, 15.93it/s, loss=0.872, v_num=5]
Epoch 0:  38%|███▊      | 359/938 [00:22<00:36, 15.93it/s, loss=0.884, v_num=5]
Epoch 0:  38%|███▊      | 360/938 [00:22<00:36, 15.93it/s, loss=0.884, v_num=5]
Epoch 0:  38%|███▊      | 360/938 [00:22<00:36, 15.93it/s, loss=0.89, v_num=5] 
Epoch 0:  38%|███▊      | 361/938 [00:22<00:36, 15.93it/s, loss=0.903, v_num=5]
Epoch 0:  39%|███▊      | 362/938 [00:22<00:36, 15.94it/s, loss=0.892, v_num=5]
Epoch 0:  39%|███▊      | 363/938 [00:22<00:36, 15.95it/s, loss=0.892, v_num=5]
Epoch 0:  39%|███▊      | 363/938 [00:22<00:36, 15.95it/s, loss=0.885, v_num=5]
Epoch 0:  39%|███▉      | 364/938 [00:22<00:36, 15.94it/s, loss=0.886, v_num=5]
Epoch 0:  39%|███▉      | 365/938 [00:22<00:35, 15.95it/s, loss=0.889, v_num=5]
Epoch 0:  39%|███▉      | 366/938 [00:22<00:35, 15.95it/s, loss=0.889, v_num=5]
Epoch 0:  39%|███▉      | 366/938 [00:22<00:35, 15.95it/s, loss=0.894, v_num=5]
Epoch 0:  39%|███▉      | 367/938 [00:23<00:35, 15.95it/s, loss=0.888, v_num=5]
Epoch 0:  39%|███▉      | 368/938 [00:23<00:35, 15.96it/s, loss=0.882, v_num=5]
Epoch 0:  39%|███▉      | 369/938 [00:23<00:35, 15.96it/s, loss=0.882, v_num=5]
Epoch 0:  39%|███▉      | 369/938 [00:23<00:35, 15.96it/s, loss=0.883, v_num=5]
Epoch 0:  39%|███▉      | 370/938 [00:23<00:35, 15.96it/s, loss=0.889, v_num=5]
Epoch 0:  40%|███▉      | 371/938 [00:23<00:35, 15.96it/s, loss=0.911, v_num=5]
Epoch 0:  40%|███▉      | 372/938 [00:23<00:35, 15.95it/s, loss=0.911, v_num=5]
Epoch 0:  40%|███▉      | 372/938 [00:23<00:35, 15.95it/s, loss=0.914, v_num=5]
Epoch 0:  40%|███▉      | 373/938 [00:23<00:35, 15.95it/s, loss=0.925, v_num=5]
Epoch 0:  40%|███▉      | 374/938 [00:23<00:35, 15.95it/s, loss=0.911, v_num=5]
Epoch 0:  40%|███▉      | 375/938 [00:23<00:35, 15.95it/s, loss=0.911, v_num=5]
Epoch 0:  40%|███▉      | 375/938 [00:23<00:35, 15.95it/s, loss=0.918, v_num=5]
Epoch 0:  40%|████      | 376/938 [00:23<00:35, 15.95it/s, loss=0.916, v_num=5]
Epoch 0:  40%|████      | 377/938 [00:23<00:35, 15.95it/s, loss=0.914, v_num=5]
Epoch 0:  40%|████      | 378/938 [00:23<00:35, 15.94it/s, loss=0.914, v_num=5]
Epoch 0:  40%|████      | 378/938 [00:23<00:35, 15.94it/s, loss=0.901, v_num=5]
Epoch 0:  40%|████      | 379/938 [00:23<00:35, 15.94it/s, loss=0.896, v_num=5]
Epoch 0:  41%|████      | 380/938 [00:23<00:35, 15.94it/s, loss=0.891, v_num=5]
Epoch 0:  41%|████      | 381/938 [00:23<00:34, 15.95it/s, loss=0.891, v_num=5]
Epoch 0:  41%|████      | 381/938 [00:23<00:34, 15.95it/s, loss=0.871, v_num=5]
Epoch 0:  41%|████      | 382/938 [00:23<00:34, 15.94it/s, loss=0.884, v_num=5]
Epoch 0:  41%|████      | 383/938 [00:24<00:34, 15.93it/s, loss=0.885, v_num=5]
Epoch 0:  41%|████      | 384/938 [00:24<00:34, 15.94it/s, loss=0.885, v_num=5]
Epoch 0:  41%|████      | 384/938 [00:24<00:34, 15.94it/s, loss=0.884, v_num=5]
Epoch 0:  41%|████      | 385/938 [00:24<00:34, 15.94it/s, loss=0.875, v_num=5]
Epoch 0:  41%|████      | 386/938 [00:24<00:34, 15.94it/s, loss=0.87, v_num=5] 
Epoch 0:  41%|████▏     | 387/938 [00:24<00:34, 15.95it/s, loss=0.87, v_num=5]
Epoch 0:  41%|████▏     | 387/938 [00:24<00:34, 15.95it/s, loss=0.869, v_num=5]
Epoch 0:  41%|████▏     | 388/938 [00:24<00:34, 15.94it/s, loss=0.879, v_num=5]
Epoch 0:  41%|████▏     | 389/938 [00:24<00:34, 15.95it/s, loss=0.877, v_num=5]
Epoch 0:  42%|████▏     | 390/938 [00:24<00:34, 15.94it/s, loss=0.877, v_num=5]
Epoch 0:  42%|████▏     | 390/938 [00:24<00:34, 15.94it/s, loss=0.87, v_num=5] 
Epoch 0:  42%|████▏     | 391/938 [00:24<00:34, 15.94it/s, loss=0.855, v_num=5]
Epoch 0:  42%|████▏     | 392/938 [00:24<00:34, 15.93it/s, loss=0.857, v_num=5]
Epoch 0:  42%|████▏     | 393/938 [00:24<00:34, 15.93it/s, loss=0.857, v_num=5]
Epoch 0:  42%|████▏     | 393/938 [00:24<00:34, 15.93it/s, loss=0.843, v_num=5]
Epoch 0:  42%|████▏     | 394/938 [00:24<00:34, 15.94it/s, loss=0.842, v_num=5]
Epoch 0:  42%|████▏     | 395/938 [00:24<00:34, 15.94it/s, loss=0.852, v_num=5]
Epoch 0:  42%|████▏     | 396/938 [00:24<00:33, 15.94it/s, loss=0.852, v_num=5]
Epoch 0:  42%|████▏     | 396/938 [00:24<00:33, 15.94it/s, loss=0.841, v_num=5]
Epoch 0:  42%|████▏     | 397/938 [00:24<00:33, 15.94it/s, loss=0.835, v_num=5]
Epoch 0:  42%|████▏     | 398/938 [00:24<00:33, 15.94it/s, loss=0.857, v_num=5]
Epoch 0:  43%|████▎     | 399/938 [00:25<00:33, 15.95it/s, loss=0.857, v_num=5]
Epoch 0:  43%|████▎     | 399/938 [00:25<00:33, 15.95it/s, loss=0.858, v_num=5]
Epoch 0:  43%|████▎     | 400/938 [00:25<00:33, 15.95it/s, loss=0.865, v_num=5]
Epoch 0:  43%|████▎     | 401/938 [00:25<00:33, 15.95it/s, loss=0.87, v_num=5] 
Epoch 0:  43%|████▎     | 402/938 [00:25<00:33, 15.95it/s, loss=0.87, v_num=5]
Epoch 0:  43%|████▎     | 402/938 [00:25<00:33, 15.95it/s, loss=0.861, v_num=5]
Epoch 0:  43%|████▎     | 403/938 [00:25<00:33, 15.95it/s, loss=0.868, v_num=5]
Epoch 0:  43%|████▎     | 404/938 [00:25<00:33, 15.95it/s, loss=0.867, v_num=5]
Epoch 0:  43%|████▎     | 405/938 [00:25<00:33, 15.95it/s, loss=0.867, v_num=5]
Epoch 0:  43%|████▎     | 405/938 [00:25<00:33, 15.95it/s, loss=0.863, v_num=5]
Epoch 0:  43%|████▎     | 406/938 [00:25<00:33, 15.95it/s, loss=0.861, v_num=5]
Epoch 0:  43%|████▎     | 407/938 [00:25<00:33, 15.95it/s, loss=0.859, v_num=5]
Epoch 0:  43%|████▎     | 408/938 [00:25<00:33, 15.95it/s, loss=0.859, v_num=5]
Epoch 0:  43%|████▎     | 408/938 [00:25<00:33, 15.95it/s, loss=0.846, v_num=5]
Epoch 0:  44%|████▎     | 409/938 [00:25<00:33, 15.95it/s, loss=0.836, v_num=5]
Epoch 0:  44%|████▎     | 410/938 [00:25<00:33, 15.95it/s, loss=0.831, v_num=5]
Epoch 0:  44%|████▍     | 411/938 [00:25<00:33, 15.96it/s, loss=0.831, v_num=5]
Epoch 0:  44%|████▍     | 411/938 [00:25<00:33, 15.96it/s, loss=0.832, v_num=5]
Epoch 0:  44%|████▍     | 412/938 [00:25<00:32, 15.96it/s, loss=0.825, v_num=5]
Epoch 0:  44%|████▍     | 413/938 [00:25<00:32, 15.96it/s, loss=0.822, v_num=5]
Epoch 0:  44%|████▍     | 414/938 [00:25<00:32, 15.96it/s, loss=0.822, v_num=5]
Epoch 0:  44%|████▍     | 414/938 [00:25<00:32, 15.96it/s, loss=0.819, v_num=5]
Epoch 0:  44%|████▍     | 415/938 [00:26<00:32, 15.95it/s, loss=0.803, v_num=5]
Epoch 0:  44%|████▍     | 416/938 [00:26<00:32, 15.95it/s, loss=0.807, v_num=5]
Epoch 0:  44%|████▍     | 417/938 [00:26<00:32, 15.96it/s, loss=0.807, v_num=5]
Epoch 0:  44%|████▍     | 417/938 [00:26<00:32, 15.96it/s, loss=0.809, v_num=5]
Epoch 0:  45%|████▍     | 418/938 [00:26<00:32, 15.95it/s, loss=0.784, v_num=5]
Epoch 0:  45%|████▍     | 419/938 [00:26<00:32, 15.95it/s, loss=0.785, v_num=5]
Epoch 0:  45%|████▍     | 420/938 [00:26<00:32, 15.95it/s, loss=0.785, v_num=5]
Epoch 0:  45%|████▍     | 420/938 [00:26<00:32, 15.95it/s, loss=0.765, v_num=5]
Epoch 0:  45%|████▍     | 421/938 [00:26<00:32, 15.95it/s, loss=0.758, v_num=5]
Epoch 0:  45%|████▍     | 422/938 [00:26<00:32, 15.95it/s, loss=0.758, v_num=5]
Epoch 0:  45%|████▌     | 423/938 [00:26<00:32, 15.96it/s, loss=0.758, v_num=5]
Epoch 0:  45%|████▌     | 423/938 [00:26<00:32, 15.96it/s, loss=0.76, v_num=5] 
Epoch 0:  45%|████▌     | 424/938 [00:26<00:32, 15.96it/s, loss=0.764, v_num=5]
Epoch 0:  45%|████▌     | 425/938 [00:26<00:32, 15.96it/s, loss=0.779, v_num=5]
Epoch 0:  45%|████▌     | 426/938 [00:26<00:32, 15.96it/s, loss=0.779, v_num=5]
Epoch 0:  45%|████▌     | 426/938 [00:26<00:32, 15.96it/s, loss=0.773, v_num=5]
Epoch 0:  46%|████▌     | 427/938 [00:26<00:32, 15.96it/s, loss=0.79, v_num=5] 
Epoch 0:  46%|████▌     | 428/938 [00:26<00:31, 15.96it/s, loss=0.793, v_num=5]
Epoch 0:  46%|████▌     | 429/938 [00:26<00:31, 15.96it/s, loss=0.793, v_num=5]
Epoch 0:  46%|████▌     | 429/938 [00:26<00:31, 15.96it/s, loss=0.803, v_num=5]
Epoch 0:  46%|████▌     | 430/938 [00:26<00:31, 15.97it/s, loss=0.8, v_num=5]  
Epoch 0:  46%|████▌     | 431/938 [00:26<00:31, 15.97it/s, loss=0.791, v_num=5]
Epoch 0:  46%|████▌     | 432/938 [00:27<00:31, 15.97it/s, loss=0.791, v_num=5]
Epoch 0:  46%|████▌     | 432/938 [00:27<00:31, 15.96it/s, loss=0.798, v_num=5]
Epoch 0:  46%|████▌     | 433/938 [00:27<00:31, 15.97it/s, loss=0.798, v_num=5]
Epoch 0:  46%|████▋     | 434/938 [00:27<00:31, 15.95it/s, loss=0.794, v_num=5]
Epoch 0:  46%|████▋     | 435/938 [00:27<00:31, 15.95it/s, loss=0.794, v_num=5]
Epoch 0:  46%|████▋     | 435/938 [00:27<00:31, 15.95it/s, loss=0.791, v_num=5]
Epoch 0:  46%|████▋     | 436/938 [00:27<00:31, 15.95it/s, loss=0.792, v_num=5]
Epoch 0:  47%|████▋     | 437/938 [00:27<00:31, 15.95it/s, loss=0.796, v_num=5]
Epoch 0:  47%|████▋     | 438/938 [00:27<00:31, 15.95it/s, loss=0.796, v_num=5]
Epoch 0:  47%|████▋     | 438/938 [00:27<00:31, 15.95it/s, loss=0.797, v_num=5]
Epoch 0:  47%|████▋     | 439/938 [00:27<00:31, 15.92it/s, loss=0.802, v_num=5]
Epoch 0:  47%|████▋     | 440/938 [00:27<00:31, 15.91it/s, loss=0.808, v_num=5]
Epoch 0:  47%|████▋     | 441/938 [00:27<00:31, 15.91it/s, loss=0.808, v_num=5]
Epoch 0:  47%|████▋     | 441/938 [00:27<00:31, 15.91it/s, loss=0.811, v_num=5]
Epoch 0:  47%|████▋     | 442/938 [00:27<00:31, 15.91it/s, loss=0.814, v_num=5]
Epoch 0:  47%|████▋     | 443/938 [00:27<00:31, 15.92it/s, loss=0.804, v_num=5]
Epoch 0:  47%|████▋     | 444/938 [00:27<00:31, 15.92it/s, loss=0.804, v_num=5]
Epoch 0:  47%|████▋     | 444/938 [00:27<00:31, 15.92it/s, loss=0.795, v_num=5]
Epoch 0:  47%|████▋     | 445/938 [00:27<00:30, 15.91it/s, loss=0.783, v_num=5]
Epoch 0:  48%|████▊     | 446/938 [00:28<00:30, 15.92it/s, loss=0.791, v_num=5]
Epoch 0:  48%|████▊     | 447/938 [00:28<00:30, 15.92it/s, loss=0.791, v_num=5]
Epoch 0:  48%|████▊     | 447/938 [00:28<00:30, 15.92it/s, loss=0.78, v_num=5] 
Epoch 0:  48%|████▊     | 448/938 [00:28<00:30, 15.92it/s, loss=0.78, v_num=5]
Epoch 0:  48%|████▊     | 449/938 [00:28<00:30, 15.92it/s, loss=0.77, v_num=5]
Epoch 0:  48%|████▊     | 450/938 [00:28<00:30, 15.91it/s, loss=0.77, v_num=5]
Epoch 0:  48%|████▊     | 450/938 [00:28<00:30, 15.91it/s, loss=0.77, v_num=5]
Epoch 0:  48%|████▊     | 451/938 [00:28<00:30, 15.91it/s, loss=0.777, v_num=5]
Epoch 0:  48%|████▊     | 452/938 [00:28<00:30, 15.92it/s, loss=0.775, v_num=5]
Epoch 0:  48%|████▊     | 453/938 [00:28<00:30, 15.92it/s, loss=0.775, v_num=5]
Epoch 0:  48%|████▊     | 453/938 [00:28<00:30, 15.92it/s, loss=0.775, v_num=5]
Epoch 0:  48%|████▊     | 454/938 [00:28<00:30, 15.92it/s, loss=0.774, v_num=5]
Epoch 0:  49%|████▊     | 455/938 [00:28<00:30, 15.92it/s, loss=0.782, v_num=5]
Epoch 0:  49%|████▊     | 456/938 [00:28<00:30, 15.92it/s, loss=0.782, v_num=5]
Epoch 0:  49%|████▊     | 456/938 [00:28<00:30, 15.92it/s, loss=0.788, v_num=5]
Epoch 0:  49%|████▊     | 457/938 [00:28<00:30, 15.92it/s, loss=0.784, v_num=5]
Epoch 0:  49%|████▉     | 458/938 [00:28<00:30, 15.93it/s, loss=0.79, v_num=5] 
Epoch 0:  49%|████▉     | 459/938 [00:28<00:30, 15.93it/s, loss=0.79, v_num=5]
Epoch 0:  49%|████▉     | 459/938 [00:28<00:30, 15.93it/s, loss=0.789, v_num=5]
Epoch 0:  49%|████▉     | 460/938 [00:28<00:30, 15.93it/s, loss=0.79, v_num=5] 
Epoch 0:  49%|████▉     | 461/938 [00:28<00:29, 15.91it/s, loss=0.792, v_num=5]
Epoch 0:  49%|████▉     | 462/938 [00:29<00:29, 15.91it/s, loss=0.792, v_num=5]
Epoch 0:  49%|████▉     | 462/938 [00:29<00:29, 15.91it/s, loss=0.796, v_num=5]
Epoch 0:  49%|████▉     | 463/938 [00:29<00:29, 15.92it/s, loss=0.802, v_num=5]
Epoch 0:  49%|████▉     | 464/938 [00:29<00:29, 15.92it/s, loss=0.799, v_num=5]
Epoch 0:  50%|████▉     | 465/938 [00:29<00:29, 15.92it/s, loss=0.799, v_num=5]
Epoch 0:  50%|████▉     | 465/938 [00:29<00:29, 15.92it/s, loss=0.796, v_num=5]
Epoch 0:  50%|████▉     | 466/938 [00:29<00:29, 15.92it/s, loss=0.788, v_num=5]
Epoch 0:  50%|████▉     | 467/938 [00:29<00:29, 15.92it/s, loss=0.79, v_num=5] 
Epoch 0:  50%|████▉     | 468/938 [00:29<00:29, 15.91it/s, loss=0.79, v_num=5]
Epoch 0:  50%|████▉     | 468/938 [00:29<00:29, 15.91it/s, loss=0.792, v_num=5]
Epoch 0:  50%|█████     | 469/938 [00:29<00:29, 15.93it/s, loss=0.8, v_num=5]  

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]
Epoch 0:  50%|█████     | 471/938 [00:29<00:29, 15.95it/s, loss=0.8, v_num=5]

Validating:   0%|          | 2/469 [00:00<00:24, 19.22it/s]
Epoch 0:  51%|█████     | 474/938 [00:29<00:29, 15.99it/s, loss=0.8, v_num=5]

Validating:   1%|          | 5/469 [00:00<00:19, 23.44it/s]
Epoch 0:  51%|█████     | 477/938 [00:29<00:28, 16.04it/s, loss=0.8, v_num=5]

Validating:   2%|▏         | 8/469 [00:00<00:18, 25.45it/s]
Epoch 0:  51%|█████     | 480/938 [00:29<00:28, 16.08it/s, loss=0.8, v_num=5]

Validating:   2%|▏         | 11/469 [00:00<00:17, 26.22it/s]
Epoch 0:  51%|█████▏    | 483/938 [00:29<00:28, 16.12it/s, loss=0.8, v_num=5]

Validating:   3%|▎         | 14/469 [00:00<00:16, 27.04it/s]
Epoch 0:  52%|█████▏    | 486/938 [00:30<00:27, 16.15it/s, loss=0.8, v_num=5]

Validating:   4%|▎         | 17/469 [00:00<00:17, 25.54it/s]
Epoch 0:  52%|█████▏    | 489/938 [00:30<00:27, 16.19it/s, loss=0.8, v_num=5]

Validating:   4%|▍         | 20/469 [00:00<00:17, 26.26it/s]
Epoch 0:  52%|█████▏    | 492/938 [00:30<00:27, 16.24it/s, loss=0.8, v_num=5]

Validating:   5%|▍         | 23/469 [00:00<00:16, 26.65it/s]
Epoch 0:  53%|█████▎    | 495/938 [00:30<00:27, 16.28it/s, loss=0.8, v_num=5]

Validating:   6%|▌         | 26/469 [00:00<00:16, 26.92it/s]
Epoch 0:  53%|█████▎    | 498/938 [00:30<00:26, 16.32it/s, loss=0.8, v_num=5]

Validating:   6%|▌         | 29/469 [00:01<00:16, 27.39it/s]
Epoch 0:  54%|█████▎    | 502/938 [00:30<00:26, 16.38it/s, loss=0.8, v_num=5]

Validating:   7%|▋         | 33/469 [00:01<00:15, 27.97it/s]

Validating:   8%|▊         | 36/469 [00:01<00:15, 27.46it/s]
Epoch 0:  54%|█████▍    | 506/938 [00:30<00:26, 16.43it/s, loss=0.8, v_num=5]

Validating:   8%|▊         | 39/469 [00:01<00:15, 27.56it/s]
Epoch 0:  54%|█████▍    | 510/938 [00:30<00:25, 16.48it/s, loss=0.8, v_num=5]

Validating:   9%|▉         | 42/469 [00:01<00:15, 27.20it/s]
Epoch 0:  55%|█████▍    | 514/938 [00:31<00:25, 16.53it/s, loss=0.8, v_num=5]

Validating:  10%|▉         | 45/469 [00:01<00:15, 27.28it/s]

Validating:  10%|█         | 48/469 [00:01<00:15, 26.94it/s]
Epoch 0:  55%|█████▌    | 518/938 [00:31<00:25, 16.58it/s, loss=0.8, v_num=5]

Validating:  11%|█         | 51/469 [00:01<00:15, 27.03it/s]
Epoch 0:  56%|█████▌    | 522/938 [00:31<00:25, 16.62it/s, loss=0.8, v_num=5]

Validating:  12%|█▏        | 54/469 [00:02<00:15, 26.88it/s]
Epoch 0:  56%|█████▌    | 526/938 [00:31<00:24, 16.67it/s, loss=0.8, v_num=5]

Validating:  12%|█▏        | 57/469 [00:02<00:15, 26.75it/s]

Validating:  13%|█▎        | 60/469 [00:02<00:15, 26.64it/s]
Epoch 0:  57%|█████▋    | 530/938 [00:31<00:24, 16.72it/s, loss=0.8, v_num=5]

Validating:  13%|█▎        | 63/469 [00:02<00:14, 27.13it/s]
Epoch 0:  57%|█████▋    | 534/938 [00:31<00:24, 16.77it/s, loss=0.8, v_num=5]

Validating:  14%|█▍        | 66/469 [00:02<00:14, 27.27it/s]
Epoch 0:  57%|█████▋    | 538/938 [00:31<00:23, 16.81it/s, loss=0.8, v_num=5]

Validating:  15%|█▍        | 69/469 [00:02<00:15, 26.12it/s]

Validating:  15%|█▌        | 72/469 [00:02<00:14, 27.06it/s]
Epoch 0:  58%|█████▊    | 542/938 [00:32<00:23, 16.86it/s, loss=0.8, v_num=5]

Validating:  16%|█▌        | 75/469 [00:02<00:14, 27.35it/s]
Epoch 0:  58%|█████▊    | 546/938 [00:32<00:23, 16.91it/s, loss=0.8, v_num=5]

Validating:  17%|█▋        | 78/469 [00:02<00:14, 26.50it/s]
Epoch 0:  59%|█████▊    | 550/938 [00:32<00:22, 16.95it/s, loss=0.8, v_num=5]

Validating:  17%|█▋        | 81/469 [00:03<00:14, 26.84it/s]

Validating:  18%|█▊        | 84/469 [00:03<00:14, 27.45it/s]
Epoch 0:  59%|█████▉    | 554/938 [00:32<00:22, 17.00it/s, loss=0.8, v_num=5]

Validating:  19%|█▊        | 87/469 [00:03<00:13, 27.32it/s]
Epoch 0:  59%|█████▉    | 558/938 [00:32<00:22, 17.04it/s, loss=0.8, v_num=5]

Validating:  19%|█▉        | 90/469 [00:03<00:14, 26.66it/s]
Epoch 0:  60%|█████▉    | 562/938 [00:32<00:22, 17.08it/s, loss=0.8, v_num=5]

Validating:  20%|█▉        | 93/469 [00:03<00:14, 25.72it/s]

Validating:  20%|██        | 96/469 [00:03<00:13, 26.87it/s]
Epoch 0:  60%|██████    | 566/938 [00:33<00:21, 17.13it/s, loss=0.8, v_num=5]

Validating:  21%|██        | 99/469 [00:03<00:13, 27.12it/s]
Epoch 0:  61%|██████    | 570/938 [00:33<00:21, 17.18it/s, loss=0.8, v_num=5]

Validating:  22%|██▏       | 102/469 [00:03<00:13, 27.29it/s]
Epoch 0:  61%|██████    | 574/938 [00:33<00:21, 17.22it/s, loss=0.8, v_num=5]

Validating:  22%|██▏       | 105/469 [00:03<00:13, 27.50it/s]

Validating:  23%|██▎       | 108/469 [00:04<00:13, 26.80it/s]
Epoch 0:  62%|██████▏   | 578/938 [00:33<00:20, 17.26it/s, loss=0.8, v_num=5]

Validating:  24%|██▎       | 111/469 [00:04<00:13, 27.17it/s]
Epoch 0:  62%|██████▏   | 582/938 [00:33<00:20, 17.30it/s, loss=0.8, v_num=5]

Validating:  24%|██▍       | 114/469 [00:04<00:13, 26.19it/s]
Epoch 0:  62%|██████▏   | 586/938 [00:33<00:20, 17.35it/s, loss=0.8, v_num=5]

Validating:  25%|██▍       | 117/469 [00:04<00:13, 27.05it/s]

Validating:  26%|██▌       | 120/469 [00:04<00:13, 25.94it/s]
Epoch 0:  63%|██████▎   | 590/938 [00:33<00:20, 17.38it/s, loss=0.8, v_num=5]

Validating:  26%|██▌       | 123/469 [00:04<00:13, 26.00it/s]
Epoch 0:  63%|██████▎   | 594/938 [00:34<00:19, 17.42it/s, loss=0.8, v_num=5]

Validating:  27%|██▋       | 126/469 [00:04<00:13, 26.09it/s]
Epoch 0:  64%|██████▍   | 598/938 [00:34<00:19, 17.46it/s, loss=0.8, v_num=5]

Validating:  28%|██▊       | 129/469 [00:04<00:12, 27.06it/s]

Validating:  28%|██▊       | 132/469 [00:04<00:12, 27.70it/s]
Epoch 0:  64%|██████▍   | 602/938 [00:34<00:19, 17.51it/s, loss=0.8, v_num=5]

Validating:  29%|██▉       | 136/469 [00:05<00:11, 28.43it/s]
Epoch 0:  65%|██████▍   | 606/938 [00:34<00:18, 17.56it/s, loss=0.8, v_num=5]

Validating:  30%|██▉       | 139/469 [00:05<00:11, 28.16it/s]
Epoch 0:  65%|██████▌   | 610/938 [00:34<00:18, 17.60it/s, loss=0.8, v_num=5]

Validating:  30%|███       | 142/469 [00:05<00:11, 28.27it/s]
Epoch 0:  65%|██████▌   | 614/938 [00:34<00:18, 17.64it/s, loss=0.8, v_num=5]

Validating:  31%|███       | 145/469 [00:05<00:11, 27.44it/s]

Validating:  32%|███▏      | 148/469 [00:05<00:11, 27.93it/s]
Epoch 0:  66%|██████▌   | 618/938 [00:34<00:18, 17.69it/s, loss=0.8, v_num=5]

Validating:  32%|███▏      | 151/469 [00:05<00:11, 27.54it/s]
Epoch 0:  66%|██████▋   | 622/938 [00:35<00:17, 17.73it/s, loss=0.8, v_num=5]

Validating:  33%|███▎      | 154/469 [00:05<00:11, 27.82it/s]
Epoch 0:  67%|██████▋   | 626/938 [00:35<00:17, 17.77it/s, loss=0.8, v_num=5]

Validating:  33%|███▎      | 157/469 [00:05<00:11, 27.98it/s]

Validating:  34%|███▍      | 160/469 [00:05<00:11, 27.60it/s]
Epoch 0:  67%|██████▋   | 630/938 [00:35<00:17, 17.81it/s, loss=0.8, v_num=5]

Validating:  35%|███▍      | 163/469 [00:06<00:11, 26.78it/s]
Epoch 0:  68%|██████▊   | 634/938 [00:35<00:17, 17.84it/s, loss=0.8, v_num=5]

Validating:  35%|███▌      | 166/469 [00:06<00:11, 27.24it/s]
Epoch 0:  68%|██████▊   | 638/938 [00:35<00:16, 17.88it/s, loss=0.8, v_num=5]

Validating:  36%|███▌      | 169/469 [00:06<00:10, 27.55it/s]

Validating:  37%|███▋      | 172/469 [00:06<00:10, 27.42it/s]
Epoch 0:  68%|██████▊   | 642/938 [00:35<00:16, 17.92it/s, loss=0.8, v_num=5]

Validating:  37%|███▋      | 175/469 [00:06<00:10, 27.07it/s]
Epoch 0:  69%|██████▉   | 646/938 [00:35<00:16, 17.96it/s, loss=0.8, v_num=5]

Validating:  38%|███▊      | 178/469 [00:06<00:10, 27.35it/s]
Epoch 0:  69%|██████▉   | 650/938 [00:36<00:16, 18.00it/s, loss=0.8, v_num=5]

Validating:  39%|███▊      | 181/469 [00:06<00:10, 27.20it/s]

Validating:  39%|███▉      | 184/469 [00:06<00:10, 27.62it/s]
Epoch 0:  70%|██████▉   | 654/938 [00:36<00:15, 18.04it/s, loss=0.8, v_num=5]

Validating:  40%|███▉      | 187/469 [00:06<00:10, 27.89it/s]
Epoch 0:  70%|███████   | 658/938 [00:36<00:15, 18.08it/s, loss=0.8, v_num=5]

Validating:  41%|████      | 190/469 [00:07<00:09, 28.02it/s]
Epoch 0:  71%|███████   | 662/938 [00:36<00:15, 18.12it/s, loss=0.8, v_num=5]

Validating:  41%|████      | 193/469 [00:07<00:09, 28.47it/s]

Validating:  42%|████▏     | 196/469 [00:07<00:09, 28.44it/s]
Epoch 0:  71%|███████   | 666/938 [00:36<00:14, 18.16it/s, loss=0.8, v_num=5]

Validating:  42%|████▏     | 199/469 [00:07<00:09, 28.26it/s]
Epoch 0:  71%|███████▏  | 670/938 [00:36<00:14, 18.19it/s, loss=0.8, v_num=5]

Validating:  43%|████▎     | 202/469 [00:07<00:09, 27.63it/s]
Epoch 0:  72%|███████▏  | 674/938 [00:36<00:14, 18.23it/s, loss=0.8, v_num=5]

Validating:  44%|████▎     | 205/469 [00:07<00:09, 27.46it/s]

Validating:  44%|████▍     | 208/469 [00:07<00:09, 27.73it/s]
Epoch 0:  72%|███████▏  | 678/938 [00:37<00:14, 18.27it/s, loss=0.8, v_num=5]

Validating:  45%|████▍     | 211/469 [00:07<00:09, 28.10it/s]
Epoch 0:  73%|███████▎  | 682/938 [00:37<00:13, 18.31it/s, loss=0.8, v_num=5]

Validating:  46%|████▌     | 214/469 [00:07<00:08, 28.55it/s]
Epoch 0:  73%|███████▎  | 686/938 [00:37<00:13, 18.35it/s, loss=0.8, v_num=5]

Validating:  46%|████▋     | 217/469 [00:07<00:08, 28.62it/s]

Validating:  47%|████▋     | 220/469 [00:08<00:08, 29.00it/s]
Epoch 0:  74%|███████▎  | 690/938 [00:37<00:13, 18.39it/s, loss=0.8, v_num=5]

Validating:  48%|████▊     | 223/469 [00:08<00:08, 28.63it/s]
Epoch 0:  74%|███████▍  | 694/938 [00:37<00:13, 18.42it/s, loss=0.8, v_num=5]

Validating:  48%|████▊     | 226/469 [00:08<00:08, 28.25it/s]
Epoch 0:  74%|███████▍  | 698/938 [00:37<00:13, 18.46it/s, loss=0.8, v_num=5]

Validating:  49%|████▉     | 229/469 [00:08<00:08, 28.04it/s]

Validating:  49%|████▉     | 232/469 [00:08<00:08, 27.90it/s]
Epoch 0:  75%|███████▍  | 702/938 [00:37<00:12, 18.49it/s, loss=0.8, v_num=5]

Validating:  50%|█████     | 235/469 [00:08<00:08, 27.34it/s]
Epoch 0:  75%|███████▌  | 706/938 [00:38<00:12, 18.52it/s, loss=0.8, v_num=5]

Validating:  51%|█████     | 238/469 [00:08<00:08, 27.45it/s]
Epoch 0:  76%|███████▌  | 710/938 [00:38<00:12, 18.56it/s, loss=0.8, v_num=5]

Validating:  51%|█████▏    | 241/469 [00:08<00:08, 27.35it/s]

Validating:  52%|█████▏    | 244/469 [00:08<00:08, 27.88it/s]
Epoch 0:  76%|███████▌  | 714/938 [00:38<00:12, 18.60it/s, loss=0.8, v_num=5]

Validating:  53%|█████▎    | 247/469 [00:09<00:08, 27.26it/s]
Epoch 0:  77%|███████▋  | 718/938 [00:38<00:11, 18.63it/s, loss=0.8, v_num=5]

Validating:  53%|█████▎    | 250/469 [00:09<00:07, 27.90it/s]
Epoch 0:  77%|███████▋  | 722/938 [00:38<00:11, 18.66it/s, loss=0.8, v_num=5]

Validating:  54%|█████▍    | 253/469 [00:09<00:07, 27.55it/s]

Validating:  55%|█████▍    | 256/469 [00:09<00:07, 26.90it/s]
Epoch 0:  77%|███████▋  | 726/938 [00:38<00:11, 18.69it/s, loss=0.8, v_num=5]

Validating:  55%|█████▌    | 259/469 [00:09<00:07, 27.57it/s]
Epoch 0:  78%|███████▊  | 730/938 [00:38<00:11, 18.73it/s, loss=0.8, v_num=5]

Validating:  56%|█████▌    | 262/469 [00:09<00:07, 28.04it/s]
Epoch 0:  78%|███████▊  | 734/938 [00:39<00:10, 18.76it/s, loss=0.8, v_num=5]

Validating:  57%|█████▋    | 265/469 [00:09<00:07, 28.04it/s]

Validating:  57%|█████▋    | 268/469 [00:09<00:07, 28.13it/s]
Epoch 0:  79%|███████▊  | 738/938 [00:39<00:10, 18.80it/s, loss=0.8, v_num=5]

Validating:  58%|█████▊    | 271/469 [00:09<00:06, 28.62it/s]
Epoch 0:  79%|███████▉  | 742/938 [00:39<00:10, 18.83it/s, loss=0.8, v_num=5]

Validating:  58%|█████▊    | 274/469 [00:10<00:06, 28.21it/s]
Epoch 0:  80%|███████▉  | 746/938 [00:39<00:10, 18.86it/s, loss=0.8, v_num=5]

Validating:  59%|█████▉    | 277/469 [00:10<00:07, 27.25it/s]

Validating:  60%|█████▉    | 280/469 [00:10<00:06, 27.52it/s]
Epoch 0:  80%|███████▉  | 750/938 [00:39<00:09, 18.89it/s, loss=0.8, v_num=5]

Validating:  60%|██████    | 283/469 [00:10<00:06, 27.04it/s]
Epoch 0:  80%|████████  | 754/938 [00:39<00:09, 18.92it/s, loss=0.8, v_num=5]

Validating:  61%|██████    | 286/469 [00:10<00:06, 27.09it/s]
Epoch 0:  81%|████████  | 758/938 [00:39<00:09, 18.95it/s, loss=0.8, v_num=5]

Validating:  62%|██████▏   | 289/469 [00:10<00:06, 27.66it/s]

Validating:  62%|██████▏   | 292/469 [00:10<00:06, 27.44it/s]
Epoch 0:  81%|████████  | 762/938 [00:40<00:09, 18.98it/s, loss=0.8, v_num=5]

Validating:  63%|██████▎   | 295/469 [00:10<00:06, 27.08it/s]
Epoch 0:  82%|████████▏ | 766/938 [00:40<00:09, 19.01it/s, loss=0.8, v_num=5]

Validating:  64%|██████▎   | 298/469 [00:10<00:06, 26.46it/s]
Epoch 0:  82%|████████▏ | 770/938 [00:40<00:08, 19.04it/s, loss=0.8, v_num=5]

Validating:  64%|██████▍   | 301/469 [00:11<00:06, 26.67it/s]

Validating:  65%|██████▍   | 304/469 [00:11<00:06, 27.27it/s]
Epoch 0:  83%|████████▎ | 774/938 [00:40<00:08, 19.07it/s, loss=0.8, v_num=5]

Validating:  65%|██████▌   | 307/469 [00:11<00:06, 26.85it/s]
Epoch 0:  83%|████████▎ | 778/938 [00:40<00:08, 19.10it/s, loss=0.8, v_num=5]

Validating:  66%|██████▌   | 310/469 [00:11<00:05, 26.84it/s]
Epoch 0:  83%|████████▎ | 782/938 [00:40<00:08, 19.12it/s, loss=0.8, v_num=5]

Validating:  67%|██████▋   | 313/469 [00:11<00:05, 26.47it/s]

Validating:  67%|██████▋   | 316/469 [00:11<00:05, 27.27it/s]
Epoch 0:  84%|████████▍ | 786/938 [00:41<00:07, 19.16it/s, loss=0.8, v_num=5]

Validating:  68%|██████▊   | 319/469 [00:11<00:05, 27.78it/s]
Epoch 0:  84%|████████▍ | 790/938 [00:41<00:07, 19.19it/s, loss=0.8, v_num=5]

Validating:  69%|██████▉   | 323/469 [00:11<00:05, 28.81it/s]
Epoch 0:  85%|████████▍ | 794/938 [00:41<00:07, 19.22it/s, loss=0.8, v_num=5]

Validating:  70%|██████▉   | 326/469 [00:11<00:05, 28.00it/s]
Epoch 0:  85%|████████▌ | 798/938 [00:41<00:07, 19.25it/s, loss=0.8, v_num=5]

Validating:  70%|███████   | 329/469 [00:12<00:05, 27.76it/s]

Validating:  71%|███████   | 332/469 [00:12<00:05, 25.92it/s]
Epoch 0:  86%|████████▌ | 802/938 [00:41<00:07, 19.27it/s, loss=0.8, v_num=5]

Validating:  71%|███████▏  | 335/469 [00:12<00:05, 26.61it/s]
Epoch 0:  86%|████████▌ | 806/938 [00:41<00:06, 19.30it/s, loss=0.8, v_num=5]

Validating:  72%|███████▏  | 338/469 [00:12<00:04, 26.93it/s]
Epoch 0:  86%|████████▋ | 810/938 [00:41<00:06, 19.33it/s, loss=0.8, v_num=5]

Validating:  73%|███████▎  | 341/469 [00:12<00:04, 27.33it/s]

Validating:  73%|███████▎  | 344/469 [00:12<00:04, 27.81it/s]
Epoch 0:  87%|████████▋ | 814/938 [00:42<00:06, 19.36it/s, loss=0.8, v_num=5]

Validating:  74%|███████▍  | 347/469 [00:12<00:04, 26.96it/s]
Epoch 0:  87%|████████▋ | 818/938 [00:42<00:06, 19.38it/s, loss=0.8, v_num=5]

Validating:  75%|███████▍  | 350/469 [00:12<00:04, 27.08it/s]
Epoch 0:  88%|████████▊ | 822/938 [00:42<00:05, 19.41it/s, loss=0.8, v_num=5]

Validating:  75%|███████▌  | 353/469 [00:12<00:04, 26.99it/s]

Validating:  76%|███████▌  | 356/469 [00:13<00:04, 26.99it/s]
Epoch 0:  88%|████████▊ | 826/938 [00:42<00:05, 19.43it/s, loss=0.8, v_num=5]

Validating:  77%|███████▋  | 359/469 [00:13<00:04, 27.09it/s]
Epoch 0:  88%|████████▊ | 830/938 [00:42<00:05, 19.46it/s, loss=0.8, v_num=5]

Validating:  77%|███████▋  | 362/469 [00:13<00:04, 26.72it/s]
Epoch 0:  89%|████████▉ | 834/938 [00:42<00:05, 19.49it/s, loss=0.8, v_num=5]

Validating:  78%|███████▊  | 365/469 [00:13<00:03, 26.84it/s]

Validating:  78%|███████▊  | 368/469 [00:13<00:03, 27.44it/s]
Epoch 0:  89%|████████▉ | 838/938 [00:42<00:05, 19.52it/s, loss=0.8, v_num=5]

Validating:  79%|███████▉  | 371/469 [00:13<00:03, 28.14it/s]
Epoch 0:  90%|████████▉ | 842/938 [00:43<00:04, 19.55it/s, loss=0.8, v_num=5]

Validating:  80%|███████▉  | 374/469 [00:13<00:03, 28.40it/s]
Epoch 0:  90%|█████████ | 846/938 [00:43<00:04, 19.57it/s, loss=0.8, v_num=5]

Validating:  80%|████████  | 377/469 [00:13<00:03, 28.06it/s]

Validating:  81%|████████  | 380/469 [00:13<00:03, 27.21it/s]
Epoch 0:  91%|█████████ | 850/938 [00:43<00:04, 19.60it/s, loss=0.8, v_num=5]

Validating:  82%|████████▏ | 383/469 [00:14<00:03, 27.75it/s]
Epoch 0:  91%|█████████ | 854/938 [00:43<00:04, 19.63it/s, loss=0.8, v_num=5]

Validating:  83%|████████▎ | 387/469 [00:14<00:02, 28.57it/s]
Epoch 0:  91%|█████████▏| 858/938 [00:43<00:04, 19.66it/s, loss=0.8, v_num=5]

Validating:  83%|████████▎ | 390/469 [00:14<00:02, 27.78it/s]
Epoch 0:  92%|█████████▏| 862/938 [00:43<00:03, 19.68it/s, loss=0.8, v_num=5]

Validating:  84%|████████▍ | 393/469 [00:14<00:02, 27.92it/s]

Validating:  84%|████████▍ | 396/469 [00:14<00:02, 27.67it/s]
Epoch 0:  92%|█████████▏| 866/938 [00:43<00:03, 19.71it/s, loss=0.8, v_num=5]

Validating:  85%|████████▌ | 400/469 [00:14<00:02, 28.64it/s]
Epoch 0:  93%|█████████▎| 870/938 [00:44<00:03, 19.74it/s, loss=0.8, v_num=5]

Validating:  86%|████████▌ | 403/469 [00:14<00:02, 28.77it/s]
Epoch 0:  93%|█████████▎| 874/938 [00:44<00:03, 19.77it/s, loss=0.8, v_num=5]

Validating:  87%|████████▋ | 406/469 [00:14<00:02, 27.85it/s]
Epoch 0:  94%|█████████▎| 878/938 [00:44<00:03, 19.79it/s, loss=0.8, v_num=5]

Validating:  87%|████████▋ | 409/469 [00:14<00:02, 27.25it/s]

Validating:  88%|████████▊ | 412/469 [00:15<00:02, 27.19it/s]
Epoch 0:  94%|█████████▍| 882/938 [00:44<00:02, 19.81it/s, loss=0.8, v_num=5]

Validating:  89%|████████▊ | 416/469 [00:15<00:01, 28.50it/s]
Epoch 0:  94%|█████████▍| 886/938 [00:44<00:02, 19.84it/s, loss=0.8, v_num=5]

Validating:  89%|████████▉ | 419/469 [00:15<00:01, 28.29it/s]
Epoch 0:  95%|█████████▍| 890/938 [00:44<00:02, 19.87it/s, loss=0.8, v_num=5]

Validating:  90%|████████▉ | 422/469 [00:15<00:01, 28.55it/s]
Epoch 0:  95%|█████████▌| 894/938 [00:44<00:02, 19.88it/s, loss=0.8, v_num=5]

Validating:  91%|█████████ | 425/469 [00:15<00:01, 26.17it/s]

Validating:  91%|█████████▏| 428/469 [00:15<00:01, 24.97it/s]
Epoch 0:  96%|█████████▌| 898/938 [00:45<00:02, 19.90it/s, loss=0.8, v_num=5]

Validating:  92%|█████████▏| 431/469 [00:15<00:01, 25.51it/s]
Epoch 0:  96%|█████████▌| 902/938 [00:45<00:01, 19.92it/s, loss=0.8, v_num=5]

Validating:  93%|█████████▎| 434/469 [00:15<00:01, 25.90it/s]
Epoch 0:  97%|█████████▋| 906/938 [00:45<00:01, 19.95it/s, loss=0.8, v_num=5]

Validating:  93%|█████████▎| 437/469 [00:16<00:01, 26.57it/s]

Validating:  94%|█████████▍| 440/469 [00:16<00:01, 26.80it/s]
Epoch 0:  97%|█████████▋| 910/938 [00:45<00:01, 19.97it/s, loss=0.8, v_num=5]

Validating:  95%|█████████▍| 444/469 [00:16<00:00, 27.98it/s]
Epoch 0:  97%|█████████▋| 914/938 [00:45<00:01, 20.00it/s, loss=0.8, v_num=5]

Validating:  95%|█████████▌| 447/469 [00:16<00:00, 28.02it/s]
Epoch 0:  98%|█████████▊| 918/938 [00:45<00:00, 20.02it/s, loss=0.8, v_num=5]

Validating:  96%|█████████▌| 450/469 [00:16<00:00, 27.64it/s]
Epoch 0:  98%|█████████▊| 922/938 [00:45<00:00, 20.05it/s, loss=0.8, v_num=5]

Validating:  97%|█████████▋| 453/469 [00:16<00:00, 27.37it/s]

Validating:  97%|█████████▋| 456/469 [00:16<00:00, 26.85it/s]
Epoch 0:  99%|█████████▊| 926/938 [00:46<00:00, 20.07it/s, loss=0.8, v_num=5]

Validating:  98%|█████████▊| 459/469 [00:16<00:00, 27.11it/s]
Epoch 0:  99%|█████████▉| 930/938 [00:46<00:00, 20.09it/s, loss=0.8, v_num=5]

Validating:  99%|█████████▊| 462/469 [00:16<00:00, 27.11it/s]
Epoch 0: 100%|█████████▉| 934/938 [00:46<00:00, 20.11it/s, loss=0.8, v_num=5]

Validating:  99%|█████████▉| 465/469 [00:17<00:00, 26.07it/s]

Validating: 100%|█████████▉| 468/469 [00:17<00:00, 27.11it/s]
Epoch 0: 100%|██████████| 938/938 [00:46<00:00, 20.13it/s, loss=0.8, v_num=5]
Epoch 0: 100%|██████████| 938/938 [00:46<00:00, 20.12it/s, loss=0.8, v_num=5, val_rmse=0.691]

                                                             
Epoch 0: 100%|██████████| 938/938 [00:46<00:00, 20.11it/s, loss=0.8, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 0:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.8, v_num=5, val_rmse=0.691, train_rmse=1.210]          
Epoch 1:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.8, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   0%|          | 1/938 [00:00<01:06, 14.04it/s, loss=0.803, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   0%|          | 2/938 [00:00<01:00, 15.47it/s, loss=0.806, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   0%|          | 3/938 [00:00<00:59, 15.59it/s, loss=0.802, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   0%|          | 4/938 [00:00<01:01, 15.25it/s, loss=0.802, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   0%|          | 4/938 [00:00<01:01, 15.21it/s, loss=0.805, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   1%|          | 5/938 [00:00<00:59, 15.57it/s, loss=0.808, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   1%|          | 6/938 [00:00<00:58, 15.82it/s, loss=0.803, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   1%|          | 7/938 [00:00<01:00, 15.41it/s, loss=0.793, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   1%|          | 8/938 [00:00<01:00, 15.37it/s, loss=0.793, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   1%|          | 8/938 [00:00<01:00, 15.35it/s, loss=0.801, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   1%|          | 9/938 [00:00<00:59, 15.67it/s, loss=0.802, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   1%|          | 10/938 [00:00<00:59, 15.61it/s, loss=0.812, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   1%|          | 11/938 [00:00<00:58, 15.74it/s, loss=0.814, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   1%|▏         | 12/938 [00:00<00:57, 16.00it/s, loss=0.814, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   1%|▏         | 12/938 [00:00<00:57, 15.99it/s, loss=0.814, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   1%|▏         | 13/938 [00:00<00:57, 16.10it/s, loss=0.809, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   1%|▏         | 14/938 [00:00<00:57, 16.08it/s, loss=0.805, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   2%|▏         | 15/938 [00:00<00:57, 16.15it/s, loss=0.799, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   2%|▏         | 16/938 [00:00<00:56, 16.23it/s, loss=0.799, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   2%|▏         | 16/938 [00:00<00:56, 16.22it/s, loss=0.808, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   2%|▏         | 17/938 [00:01<00:56, 16.29it/s, loss=0.806, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   2%|▏         | 18/938 [00:01<00:56, 16.26it/s, loss=0.798, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   2%|▏         | 19/938 [00:01<00:56, 16.21it/s, loss=0.8, v_num=5, val_rmse=0.691, train_rmse=1.210]  
Epoch 1:   2%|▏         | 20/938 [00:01<00:56, 16.26it/s, loss=0.8, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   2%|▏         | 20/938 [00:01<00:56, 16.25it/s, loss=0.802, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   2%|▏         | 21/938 [00:01<00:56, 16.18it/s, loss=0.802, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   2%|▏         | 22/938 [00:01<00:56, 16.21it/s, loss=0.796, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   2%|▏         | 23/938 [00:01<00:58, 15.68it/s, loss=0.795, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   3%|▎         | 24/938 [00:01<00:58, 15.68it/s, loss=0.795, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   3%|▎         | 24/938 [00:01<00:58, 15.67it/s, loss=0.806, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   3%|▎         | 25/938 [00:01<00:58, 15.73it/s, loss=0.806, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   3%|▎         | 26/938 [00:01<00:58, 15.67it/s, loss=0.805, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   3%|▎         | 27/938 [00:01<00:58, 15.59it/s, loss=0.812, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   3%|▎         | 28/938 [00:01<00:58, 15.65it/s, loss=0.812, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   3%|▎         | 28/938 [00:01<00:58, 15.64it/s, loss=0.808, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   3%|▎         | 29/938 [00:01<00:58, 15.61it/s, loss=0.809, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   3%|▎         | 30/938 [00:01<00:58, 15.65it/s, loss=0.786, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   3%|▎         | 31/938 [00:01<00:58, 15.60it/s, loss=0.78, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:   3%|▎         | 32/938 [00:02<00:58, 15.57it/s, loss=0.78, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   3%|▎         | 32/938 [00:02<00:58, 15.57it/s, loss=0.77, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   4%|▎         | 33/938 [00:02<00:57, 15.67it/s, loss=0.769, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   4%|▎         | 34/938 [00:02<00:57, 15.70it/s, loss=0.763, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   4%|▎         | 35/938 [00:02<00:57, 15.63it/s, loss=0.772, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   4%|▍         | 36/938 [00:02<00:57, 15.73it/s, loss=0.772, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   4%|▍         | 36/938 [00:02<00:57, 15.73it/s, loss=0.767, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   4%|▍         | 37/938 [00:02<00:57, 15.76it/s, loss=0.77, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:   4%|▍         | 38/938 [00:02<00:57, 15.79it/s, loss=0.772, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   4%|▍         | 39/938 [00:02<00:56, 15.79it/s, loss=0.775, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   4%|▍         | 40/938 [00:02<00:56, 15.76it/s, loss=0.775, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   4%|▍         | 40/938 [00:02<00:56, 15.76it/s, loss=0.772, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   4%|▍         | 41/938 [00:02<00:56, 15.79it/s, loss=0.775, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   4%|▍         | 42/938 [00:02<00:56, 15.78it/s, loss=0.772, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   5%|▍         | 43/938 [00:02<00:56, 15.76it/s, loss=0.771, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   5%|▍         | 44/938 [00:02<00:56, 15.80it/s, loss=0.771, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   5%|▍         | 44/938 [00:02<00:56, 15.79it/s, loss=0.773, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   5%|▍         | 45/938 [00:02<00:56, 15.82it/s, loss=0.773, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   5%|▍         | 46/938 [00:02<00:56, 15.79it/s, loss=0.769, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   5%|▌         | 47/938 [00:02<00:56, 15.85it/s, loss=0.767, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   5%|▌         | 48/938 [00:03<00:56, 15.83it/s, loss=0.767, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   5%|▌         | 48/938 [00:03<00:56, 15.83it/s, loss=0.757, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   5%|▌         | 49/938 [00:03<00:56, 15.86it/s, loss=0.749, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   5%|▌         | 50/938 [00:03<00:55, 15.93it/s, loss=0.751, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   5%|▌         | 51/938 [00:03<00:55, 15.91it/s, loss=0.754, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   6%|▌         | 52/938 [00:03<00:55, 15.86it/s, loss=0.754, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   6%|▌         | 52/938 [00:03<00:55, 15.86it/s, loss=0.757, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   6%|▌         | 53/938 [00:03<00:55, 15.88it/s, loss=0.763, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   6%|▌         | 54/938 [00:03<00:55, 15.85it/s, loss=0.761, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   6%|▌         | 55/938 [00:03<00:55, 15.83it/s, loss=0.759, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   6%|▌         | 56/938 [00:03<00:55, 15.85it/s, loss=0.759, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   6%|▌         | 56/938 [00:03<00:55, 15.84it/s, loss=0.752, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   6%|▌         | 57/938 [00:03<00:55, 15.83it/s, loss=0.749, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   6%|▌         | 58/938 [00:03<00:55, 15.88it/s, loss=0.75, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:   6%|▋         | 59/938 [00:03<00:55, 15.89it/s, loss=0.745, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   6%|▋         | 60/938 [00:03<00:55, 15.90it/s, loss=0.745, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   6%|▋         | 60/938 [00:03<00:55, 15.90it/s, loss=0.746, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   7%|▋         | 61/938 [00:03<00:55, 15.94it/s, loss=0.74, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:   7%|▋         | 62/938 [00:03<00:55, 15.91it/s, loss=0.76, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   7%|▋         | 63/938 [00:03<00:54, 15.93it/s, loss=0.771, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   7%|▋         | 64/938 [00:04<00:54, 15.94it/s, loss=0.771, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   7%|▋         | 64/938 [00:04<00:54, 15.94it/s, loss=0.763, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   7%|▋         | 65/938 [00:04<00:54, 15.89it/s, loss=0.762, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   7%|▋         | 66/938 [00:04<00:54, 15.89it/s, loss=0.763, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   7%|▋         | 67/938 [00:04<00:54, 15.90it/s, loss=0.756, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   7%|▋         | 68/938 [00:04<00:54, 15.84it/s, loss=0.756, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   7%|▋         | 68/938 [00:04<00:54, 15.84it/s, loss=0.755, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   7%|▋         | 69/938 [00:04<00:54, 15.88it/s, loss=0.755, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   7%|▋         | 70/938 [00:04<00:54, 15.89it/s, loss=0.751, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   8%|▊         | 71/938 [00:04<00:54, 15.88it/s, loss=0.752, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   8%|▊         | 72/938 [00:04<00:54, 15.83it/s, loss=0.752, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   8%|▊         | 72/938 [00:04<00:54, 15.83it/s, loss=0.76, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:   8%|▊         | 73/938 [00:04<00:54, 15.84it/s, loss=0.755, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   8%|▊         | 74/938 [00:04<00:54, 15.85it/s, loss=0.764, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   8%|▊         | 75/938 [00:04<00:54, 15.87it/s, loss=0.766, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   8%|▊         | 76/938 [00:04<00:54, 15.88it/s, loss=0.766, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   8%|▊         | 76/938 [00:04<00:54, 15.88it/s, loss=0.767, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   8%|▊         | 77/938 [00:04<00:54, 15.91it/s, loss=0.77, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:   8%|▊         | 78/938 [00:04<00:54, 15.88it/s, loss=0.779, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   8%|▊         | 79/938 [00:04<00:54, 15.89it/s, loss=0.78, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:   9%|▊         | 80/938 [00:05<00:53, 15.91it/s, loss=0.78, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   9%|▊         | 80/938 [00:05<00:53, 15.91it/s, loss=0.773, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   9%|▊         | 81/938 [00:05<00:53, 15.87it/s, loss=0.766, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   9%|▊         | 82/938 [00:05<00:53, 15.90it/s, loss=0.752, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   9%|▉         | 83/938 [00:05<00:53, 15.89it/s, loss=0.741, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   9%|▉         | 84/938 [00:05<00:53, 15.90it/s, loss=0.741, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   9%|▉         | 84/938 [00:05<00:53, 15.90it/s, loss=0.742, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   9%|▉         | 85/938 [00:05<00:53, 15.95it/s, loss=0.744, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   9%|▉         | 86/938 [00:05<00:53, 15.94it/s, loss=0.749, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   9%|▉         | 87/938 [00:05<00:53, 15.94it/s, loss=0.75, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:   9%|▉         | 88/938 [00:05<00:53, 15.96it/s, loss=0.75, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   9%|▉         | 88/938 [00:05<00:53, 15.96it/s, loss=0.755, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:   9%|▉         | 89/938 [00:05<00:53, 15.97it/s, loss=0.764, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  10%|▉         | 90/938 [00:05<00:53, 15.94it/s, loss=0.774, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  10%|▉         | 91/938 [00:05<00:53, 15.95it/s, loss=0.767, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  10%|▉         | 92/938 [00:05<00:53, 15.95it/s, loss=0.767, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  10%|▉         | 92/938 [00:05<00:53, 15.95it/s, loss=0.76, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  10%|▉         | 93/938 [00:05<00:52, 15.96it/s, loss=0.762, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  10%|█         | 94/938 [00:05<00:52, 15.93it/s, loss=0.762, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  10%|█         | 95/938 [00:05<00:52, 15.92it/s, loss=0.763, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  10%|█         | 96/938 [00:06<00:52, 15.95it/s, loss=0.763, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  10%|█         | 96/938 [00:06<00:52, 15.95it/s, loss=0.77, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  10%|█         | 97/938 [00:06<00:52, 15.95it/s, loss=0.774, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  10%|█         | 98/938 [00:06<00:52, 15.94it/s, loss=0.764, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  11%|█         | 99/938 [00:06<00:52, 15.96it/s, loss=0.762, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  11%|█         | 100/938 [00:06<00:52, 15.95it/s, loss=0.762, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  11%|█         | 100/938 [00:06<00:52, 15.95it/s, loss=0.761, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  11%|█         | 101/938 [00:06<00:52, 15.96it/s, loss=0.77, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  11%|█         | 102/938 [00:06<00:52, 15.97it/s, loss=0.765, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  11%|█         | 103/938 [00:06<00:52, 15.95it/s, loss=0.763, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  11%|█         | 104/938 [00:06<00:52, 15.92it/s, loss=0.763, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  11%|█         | 104/938 [00:06<00:52, 15.91it/s, loss=0.761, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  11%|█         | 105/938 [00:06<00:52, 15.95it/s, loss=0.758, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  11%|█▏        | 106/938 [00:06<00:52, 15.96it/s, loss=0.751, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  11%|█▏        | 107/938 [00:06<00:52, 15.97it/s, loss=0.762, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  12%|█▏        | 108/938 [00:06<00:51, 15.99it/s, loss=0.762, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  12%|█▏        | 108/938 [00:06<00:51, 15.99it/s, loss=0.758, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  12%|█▏        | 109/938 [00:06<00:51, 15.99it/s, loss=0.754, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  12%|█▏        | 110/938 [00:06<00:51, 15.99it/s, loss=0.744, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  12%|█▏        | 111/938 [00:06<00:51, 16.01it/s, loss=0.753, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  12%|█▏        | 112/938 [00:07<00:51, 16.00it/s, loss=0.753, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  12%|█▏        | 112/938 [00:07<00:51, 16.00it/s, loss=0.761, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  12%|█▏        | 113/938 [00:07<00:51, 16.00it/s, loss=0.761, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  12%|█▏        | 114/938 [00:07<00:51, 15.95it/s, loss=0.765, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  12%|█▏        | 115/938 [00:07<00:51, 15.88it/s, loss=0.763, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  12%|█▏        | 116/938 [00:07<00:51, 15.89it/s, loss=0.763, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  12%|█▏        | 116/938 [00:07<00:51, 15.88it/s, loss=0.763, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  12%|█▏        | 117/938 [00:07<00:51, 15.87it/s, loss=0.765, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  13%|█▎        | 118/938 [00:07<00:51, 15.84it/s, loss=0.757, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  13%|█▎        | 119/938 [00:07<00:51, 15.84it/s, loss=0.759, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  13%|█▎        | 120/938 [00:07<00:51, 15.85it/s, loss=0.759, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  13%|█▎        | 120/938 [00:07<00:51, 15.85it/s, loss=0.761, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  13%|█▎        | 121/938 [00:07<00:51, 15.82it/s, loss=0.751, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  13%|█▎        | 122/938 [00:07<00:51, 15.83it/s, loss=0.761, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  13%|█▎        | 123/938 [00:07<00:51, 15.82it/s, loss=0.769, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  13%|█▎        | 124/938 [00:07<00:51, 15.79it/s, loss=0.769, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  13%|█▎        | 124/938 [00:07<00:51, 15.79it/s, loss=0.768, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  13%|█▎        | 125/938 [00:07<00:51, 15.80it/s, loss=0.766, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  13%|█▎        | 126/938 [00:07<00:51, 15.81it/s, loss=0.765, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  14%|█▎        | 127/938 [00:08<00:51, 15.81it/s, loss=0.766, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  14%|█▎        | 128/938 [00:08<00:51, 15.81it/s, loss=0.766, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  14%|█▎        | 128/938 [00:08<00:51, 15.81it/s, loss=0.767, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  14%|█▍        | 129/938 [00:08<00:51, 15.80it/s, loss=0.766, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  14%|█▍        | 130/938 [00:08<00:51, 15.80it/s, loss=0.77, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  14%|█▍        | 131/938 [00:08<00:51, 15.80it/s, loss=0.774, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  14%|█▍        | 132/938 [00:08<00:51, 15.77it/s, loss=0.774, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  14%|█▍        | 132/938 [00:08<00:51, 15.77it/s, loss=0.772, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  14%|█▍        | 133/938 [00:08<00:50, 15.79it/s, loss=0.769, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  14%|█▍        | 134/938 [00:08<00:50, 15.79it/s, loss=0.757, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  14%|█▍        | 135/938 [00:08<00:50, 15.79it/s, loss=0.751, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  14%|█▍        | 136/938 [00:08<00:50, 15.80it/s, loss=0.751, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  14%|█▍        | 136/938 [00:08<00:50, 15.80it/s, loss=0.749, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  15%|█▍        | 137/938 [00:08<00:50, 15.79it/s, loss=0.751, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  15%|█▍        | 138/938 [00:08<00:50, 15.78it/s, loss=0.752, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  15%|█▍        | 139/938 [00:08<00:50, 15.81it/s, loss=0.749, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  15%|█▍        | 140/938 [00:08<00:50, 15.80it/s, loss=0.749, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  15%|█▍        | 140/938 [00:08<00:50, 15.80it/s, loss=0.761, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  15%|█▌        | 141/938 [00:08<00:50, 15.79it/s, loss=0.762, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  15%|█▌        | 142/938 [00:08<00:50, 15.80it/s, loss=0.756, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  15%|█▌        | 143/938 [00:09<00:50, 15.81it/s, loss=0.754, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  15%|█▌        | 144/938 [00:09<00:50, 15.82it/s, loss=0.754, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  15%|█▌        | 144/938 [00:09<00:50, 15.82it/s, loss=0.768, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  15%|█▌        | 145/938 [00:09<00:50, 15.83it/s, loss=0.772, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  16%|█▌        | 146/938 [00:09<00:50, 15.82it/s, loss=0.774, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  16%|█▌        | 147/938 [00:09<00:49, 15.83it/s, loss=0.766, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  16%|█▌        | 148/938 [00:09<00:49, 15.83it/s, loss=0.766, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  16%|█▌        | 148/938 [00:09<00:49, 15.83it/s, loss=0.768, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  16%|█▌        | 149/938 [00:09<00:50, 15.78it/s, loss=0.763, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  16%|█▌        | 150/938 [00:09<00:49, 15.77it/s, loss=0.762, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  16%|█▌        | 151/938 [00:09<00:49, 15.76it/s, loss=0.76, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  16%|█▌        | 152/938 [00:09<00:49, 15.75it/s, loss=0.76, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  16%|█▌        | 152/938 [00:09<00:49, 15.75it/s, loss=0.756, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  16%|█▋        | 153/938 [00:09<00:49, 15.73it/s, loss=0.754, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  16%|█▋        | 154/938 [00:09<00:49, 15.74it/s, loss=0.756, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  17%|█▋        | 155/938 [00:09<00:49, 15.74it/s, loss=0.759, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  17%|█▋        | 156/938 [00:09<00:49, 15.75it/s, loss=0.759, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  17%|█▋        | 156/938 [00:09<00:49, 15.75it/s, loss=0.758, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  17%|█▋        | 157/938 [00:09<00:49, 15.75it/s, loss=0.752, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  17%|█▋        | 158/938 [00:10<00:49, 15.75it/s, loss=0.763, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  17%|█▋        | 159/938 [00:10<00:49, 15.74it/s, loss=0.764, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  17%|█▋        | 160/938 [00:10<00:49, 15.73it/s, loss=0.764, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  17%|█▋        | 160/938 [00:10<00:49, 15.73it/s, loss=0.755, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  17%|█▋        | 161/938 [00:10<00:49, 15.72it/s, loss=0.76, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  17%|█▋        | 162/938 [00:10<00:49, 15.74it/s, loss=0.768, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  17%|█▋        | 163/938 [00:10<00:49, 15.75it/s, loss=0.758, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  17%|█▋        | 164/938 [00:10<00:49, 15.76it/s, loss=0.758, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  17%|█▋        | 164/938 [00:10<00:49, 15.76it/s, loss=0.737, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  18%|█▊        | 165/938 [00:10<00:49, 15.76it/s, loss=0.742, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  18%|█▊        | 166/938 [00:10<00:49, 15.73it/s, loss=0.742, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  18%|█▊        | 167/938 [00:10<00:49, 15.72it/s, loss=0.733, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  18%|█▊        | 168/938 [00:10<00:48, 15.73it/s, loss=0.733, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  18%|█▊        | 168/938 [00:10<00:48, 15.73it/s, loss=0.731, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  18%|█▊        | 169/938 [00:10<00:48, 15.72it/s, loss=0.739, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  18%|█▊        | 170/938 [00:10<00:48, 15.71it/s, loss=0.747, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  18%|█▊        | 171/938 [00:10<00:48, 15.70it/s, loss=0.743, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  18%|█▊        | 172/938 [00:10<00:48, 15.69it/s, loss=0.743, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  18%|█▊        | 172/938 [00:10<00:48, 15.69it/s, loss=0.74, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  18%|█▊        | 173/938 [00:11<00:48, 15.64it/s, loss=0.743, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  19%|█▊        | 174/938 [00:11<00:48, 15.62it/s, loss=0.75, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  19%|█▊        | 175/938 [00:11<00:48, 15.63it/s, loss=0.748, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  19%|█▉        | 176/938 [00:11<00:48, 15.63it/s, loss=0.748, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  19%|█▉        | 176/938 [00:11<00:48, 15.63it/s, loss=0.75, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  19%|█▉        | 177/938 [00:11<00:48, 15.64it/s, loss=0.753, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  19%|█▉        | 178/938 [00:11<00:48, 15.63it/s, loss=0.748, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  19%|█▉        | 179/938 [00:11<00:48, 15.63it/s, loss=0.749, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  19%|█▉        | 180/938 [00:11<00:48, 15.63it/s, loss=0.749, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  19%|█▉        | 180/938 [00:11<00:48, 15.63it/s, loss=0.762, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  19%|█▉        | 181/938 [00:11<00:48, 15.64it/s, loss=0.76, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  19%|█▉        | 182/938 [00:11<00:48, 15.63it/s, loss=0.76, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  20%|█▉        | 183/938 [00:11<00:48, 15.63it/s, loss=0.762, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  20%|█▉        | 184/938 [00:11<00:48, 15.64it/s, loss=0.762, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  20%|█▉        | 184/938 [00:11<00:48, 15.64it/s, loss=0.774, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  20%|█▉        | 185/938 [00:11<00:48, 15.63it/s, loss=0.769, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  20%|█▉        | 186/938 [00:11<00:48, 15.64it/s, loss=0.773, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  20%|█▉        | 187/938 [00:11<00:48, 15.64it/s, loss=0.781, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  20%|██        | 188/938 [00:12<00:47, 15.63it/s, loss=0.781, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  20%|██        | 188/938 [00:12<00:47, 15.63it/s, loss=0.784, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  20%|██        | 189/938 [00:12<00:47, 15.64it/s, loss=0.787, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  20%|██        | 190/938 [00:12<00:47, 15.64it/s, loss=0.785, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  20%|██        | 191/938 [00:12<00:47, 15.64it/s, loss=0.789, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  20%|██        | 192/938 [00:12<00:47, 15.62it/s, loss=0.789, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  20%|██        | 192/938 [00:12<00:47, 15.62it/s, loss=0.795, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  21%|██        | 193/938 [00:12<00:47, 15.63it/s, loss=0.806, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  21%|██        | 194/938 [00:12<00:47, 15.63it/s, loss=0.791, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  21%|██        | 195/938 [00:12<00:47, 15.64it/s, loss=0.793, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  21%|██        | 196/938 [00:12<00:47, 15.64it/s, loss=0.793, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  21%|██        | 196/938 [00:12<00:47, 15.64it/s, loss=0.792, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  21%|██        | 197/938 [00:12<00:47, 15.64it/s, loss=0.79, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  21%|██        | 198/938 [00:12<00:47, 15.62it/s, loss=0.785, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  21%|██        | 199/938 [00:12<00:47, 15.63it/s, loss=0.781, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  21%|██▏       | 200/938 [00:12<00:47, 15.57it/s, loss=0.781, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  21%|██▏       | 200/938 [00:12<00:47, 15.57it/s, loss=0.768, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  21%|██▏       | 201/938 [00:12<00:47, 15.58it/s, loss=0.778, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  22%|██▏       | 202/938 [00:12<00:47, 15.55it/s, loss=0.771, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  22%|██▏       | 203/938 [00:13<00:47, 15.52it/s, loss=0.774, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  22%|██▏       | 204/938 [00:13<00:47, 15.52it/s, loss=0.774, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  22%|██▏       | 204/938 [00:13<00:47, 15.52it/s, loss=0.767, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  22%|██▏       | 205/938 [00:13<00:47, 15.53it/s, loss=0.768, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  22%|██▏       | 206/938 [00:13<00:47, 15.53it/s, loss=0.768, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  22%|██▏       | 207/938 [00:13<00:47, 15.52it/s, loss=0.772, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  22%|██▏       | 208/938 [00:13<00:47, 15.50it/s, loss=0.772, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  22%|██▏       | 208/938 [00:13<00:47, 15.50it/s, loss=0.763, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  22%|██▏       | 209/938 [00:13<00:47, 15.48it/s, loss=0.757, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  22%|██▏       | 210/938 [00:13<00:47, 15.45it/s, loss=0.756, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  22%|██▏       | 211/938 [00:13<00:47, 15.43it/s, loss=0.751, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  23%|██▎       | 212/938 [00:13<00:47, 15.42it/s, loss=0.751, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  23%|██▎       | 212/938 [00:13<00:47, 15.42it/s, loss=0.752, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  23%|██▎       | 213/938 [00:13<00:47, 15.42it/s, loss=0.737, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  23%|██▎       | 214/938 [00:13<00:46, 15.43it/s, loss=0.748, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  23%|██▎       | 215/938 [00:13<00:46, 15.43it/s, loss=0.753, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  23%|██▎       | 216/938 [00:14<00:46, 15.42it/s, loss=0.753, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  23%|██▎       | 216/938 [00:14<00:46, 15.42it/s, loss=0.744, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  23%|██▎       | 217/938 [00:14<00:46, 15.41it/s, loss=0.739, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  23%|██▎       | 218/938 [00:14<00:46, 15.41it/s, loss=0.741, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  23%|██▎       | 219/938 [00:14<00:46, 15.39it/s, loss=0.737, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  23%|██▎       | 220/938 [00:14<00:46, 15.38it/s, loss=0.737, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  23%|██▎       | 220/938 [00:14<00:46, 15.38it/s, loss=0.74, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  24%|██▎       | 221/938 [00:14<00:46, 15.37it/s, loss=0.729, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  24%|██▎       | 222/938 [00:14<00:46, 15.36it/s, loss=0.721, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  24%|██▍       | 223/938 [00:14<00:46, 15.35it/s, loss=0.722, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  24%|██▍       | 224/938 [00:14<00:46, 15.36it/s, loss=0.722, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  24%|██▍       | 224/938 [00:14<00:46, 15.36it/s, loss=0.724, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  24%|██▍       | 225/938 [00:14<00:46, 15.36it/s, loss=0.716, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  24%|██▍       | 226/938 [00:14<00:46, 15.35it/s, loss=0.715, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  24%|██▍       | 227/938 [00:14<00:46, 15.35it/s, loss=0.708, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  24%|██▍       | 228/938 [00:14<00:46, 15.35it/s, loss=0.708, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  24%|██▍       | 228/938 [00:14<00:46, 15.35it/s, loss=0.718, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  24%|██▍       | 229/938 [00:14<00:46, 15.34it/s, loss=0.712, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  25%|██▍       | 230/938 [00:15<00:46, 15.32it/s, loss=0.703, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  25%|██▍       | 231/938 [00:15<00:46, 15.26it/s, loss=0.703, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  25%|██▍       | 232/938 [00:15<00:46, 15.27it/s, loss=0.703, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  25%|██▍       | 232/938 [00:15<00:46, 15.27it/s, loss=0.699, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  25%|██▍       | 233/938 [00:15<00:46, 15.26it/s, loss=0.701, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  25%|██▍       | 234/938 [00:15<00:46, 15.25it/s, loss=0.696, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  25%|██▌       | 235/938 [00:15<00:46, 15.25it/s, loss=0.713, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  25%|██▌       | 236/938 [00:15<00:46, 15.23it/s, loss=0.713, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  25%|██▌       | 236/938 [00:15<00:46, 15.23it/s, loss=0.72, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  25%|██▌       | 237/938 [00:15<00:46, 15.22it/s, loss=0.721, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  25%|██▌       | 238/938 [00:15<00:46, 15.21it/s, loss=0.723, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  25%|██▌       | 239/938 [00:15<00:45, 15.21it/s, loss=0.739, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  26%|██▌       | 240/938 [00:15<00:45, 15.18it/s, loss=0.739, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  26%|██▌       | 240/938 [00:15<00:45, 15.18it/s, loss=0.739, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  26%|██▌       | 241/938 [00:15<00:45, 15.17it/s, loss=0.741, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  26%|██▌       | 242/938 [00:15<00:45, 15.14it/s, loss=0.746, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  26%|██▌       | 243/938 [00:16<00:45, 15.14it/s, loss=0.75, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  26%|██▌       | 244/938 [00:16<00:45, 15.13it/s, loss=0.75, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  26%|██▌       | 244/938 [00:16<00:45, 15.13it/s, loss=0.746, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  26%|██▌       | 245/938 [00:16<00:45, 15.14it/s, loss=0.766, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  26%|██▌       | 246/938 [00:16<00:45, 15.14it/s, loss=0.767, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  26%|██▋       | 247/938 [00:16<00:45, 15.14it/s, loss=0.768, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  26%|██▋       | 248/938 [00:16<00:45, 15.13it/s, loss=0.768, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  26%|██▋       | 248/938 [00:16<00:45, 15.13it/s, loss=0.764, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  27%|██▋       | 249/938 [00:16<00:45, 15.15it/s, loss=0.776, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  27%|██▋       | 250/938 [00:16<00:45, 15.12it/s, loss=0.782, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  27%|██▋       | 251/938 [00:16<00:45, 15.12it/s, loss=0.787, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  27%|██▋       | 252/938 [00:16<00:45, 15.11it/s, loss=0.787, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  27%|██▋       | 252/938 [00:16<00:45, 15.11it/s, loss=0.802, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  27%|██▋       | 253/938 [00:16<00:45, 15.12it/s, loss=0.804, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  27%|██▋       | 254/938 [00:16<00:45, 15.12it/s, loss=0.8, v_num=5, val_rmse=0.691, train_rmse=1.210]  
Epoch 1:  27%|██▋       | 255/938 [00:16<00:45, 15.13it/s, loss=0.773, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  27%|██▋       | 256/938 [00:16<00:45, 15.12it/s, loss=0.773, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  27%|██▋       | 256/938 [00:16<00:45, 15.12it/s, loss=0.776, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  27%|██▋       | 257/938 [00:16<00:45, 15.12it/s, loss=0.779, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  28%|██▊       | 258/938 [00:17<00:44, 15.11it/s, loss=0.782, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  28%|██▊       | 259/938 [00:17<00:44, 15.11it/s, loss=0.762, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  28%|██▊       | 260/938 [00:17<00:44, 15.11it/s, loss=0.762, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  28%|██▊       | 260/938 [00:17<00:44, 15.11it/s, loss=0.754, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  28%|██▊       | 261/938 [00:17<00:44, 15.12it/s, loss=0.769, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  28%|██▊       | 262/938 [00:17<00:44, 15.12it/s, loss=0.763, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  28%|██▊       | 263/938 [00:17<00:44, 15.12it/s, loss=0.765, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  28%|██▊       | 264/938 [00:17<00:44, 15.13it/s, loss=0.765, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  28%|██▊       | 264/938 [00:17<00:44, 15.13it/s, loss=0.767, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  28%|██▊       | 265/938 [00:17<00:44, 15.14it/s, loss=0.758, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  28%|██▊       | 266/938 [00:17<00:44, 15.14it/s, loss=0.76, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  28%|██▊       | 267/938 [00:17<00:44, 15.15it/s, loss=0.76, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  29%|██▊       | 268/938 [00:17<00:44, 15.15it/s, loss=0.76, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  29%|██▊       | 268/938 [00:17<00:44, 15.15it/s, loss=0.76, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  29%|██▊       | 269/938 [00:17<00:44, 15.15it/s, loss=0.741, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  29%|██▉       | 270/938 [00:17<00:44, 15.16it/s, loss=0.737, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  29%|██▉       | 271/938 [00:17<00:43, 15.16it/s, loss=0.726, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  29%|██▉       | 272/938 [00:17<00:43, 15.17it/s, loss=0.726, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  29%|██▉       | 272/938 [00:17<00:43, 15.17it/s, loss=0.711, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  29%|██▉       | 273/938 [00:17<00:43, 15.17it/s, loss=0.713, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  29%|██▉       | 274/938 [00:18<00:43, 15.17it/s, loss=0.715, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  29%|██▉       | 275/938 [00:18<00:43, 15.18it/s, loss=0.72, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  29%|██▉       | 276/938 [00:18<00:43, 15.18it/s, loss=0.72, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  29%|██▉       | 276/938 [00:18<00:43, 15.18it/s, loss=0.711, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  30%|██▉       | 277/938 [00:18<00:43, 15.17it/s, loss=0.708, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  30%|██▉       | 278/938 [00:18<00:43, 15.18it/s, loss=0.702, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  30%|██▉       | 279/938 [00:18<00:43, 15.17it/s, loss=0.718, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  30%|██▉       | 280/938 [00:18<00:43, 15.17it/s, loss=0.718, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  30%|██▉       | 280/938 [00:18<00:43, 15.17it/s, loss=0.724, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  30%|██▉       | 281/938 [00:18<00:43, 15.17it/s, loss=0.713, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  30%|███       | 282/938 [00:18<00:43, 15.17it/s, loss=0.717, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  30%|███       | 283/938 [00:18<00:43, 15.19it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  30%|███       | 284/938 [00:18<00:43, 15.18it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  30%|███       | 284/938 [00:18<00:43, 15.18it/s, loss=0.714, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  30%|███       | 285/938 [00:18<00:43, 15.18it/s, loss=0.716, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  30%|███       | 286/938 [00:18<00:42, 15.18it/s, loss=0.715, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  31%|███       | 287/938 [00:18<00:42, 15.18it/s, loss=0.715, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  31%|███       | 288/938 [00:18<00:42, 15.17it/s, loss=0.715, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  31%|███       | 288/938 [00:18<00:42, 15.17it/s, loss=0.719, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  31%|███       | 289/938 [00:19<00:42, 15.17it/s, loss=0.735, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  31%|███       | 290/938 [00:19<00:42, 15.17it/s, loss=0.735, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  31%|███       | 291/938 [00:19<00:42, 15.16it/s, loss=0.738, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  31%|███       | 292/938 [00:19<00:42, 15.17it/s, loss=0.738, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  31%|███       | 292/938 [00:19<00:42, 15.17it/s, loss=0.733, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  31%|███       | 293/938 [00:19<00:42, 15.17it/s, loss=0.723, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  31%|███▏      | 294/938 [00:19<00:42, 15.17it/s, loss=0.726, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  31%|███▏      | 295/938 [00:19<00:42, 15.17it/s, loss=0.728, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  32%|███▏      | 296/938 [00:19<00:42, 15.19it/s, loss=0.728, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  32%|███▏      | 296/938 [00:19<00:42, 15.19it/s, loss=0.729, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  32%|███▏      | 297/938 [00:19<00:42, 15.19it/s, loss=0.732, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  32%|███▏      | 298/938 [00:19<00:42, 15.19it/s, loss=0.74, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  32%|███▏      | 299/938 [00:19<00:42, 15.21it/s, loss=0.724, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  32%|███▏      | 300/938 [00:19<00:41, 15.22it/s, loss=0.724, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  32%|███▏      | 300/938 [00:19<00:41, 15.22it/s, loss=0.724, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  32%|███▏      | 301/938 [00:19<00:41, 15.22it/s, loss=0.726, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  32%|███▏      | 302/938 [00:19<00:41, 15.22it/s, loss=0.718, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  32%|███▏      | 303/938 [00:19<00:41, 15.22it/s, loss=0.726, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  32%|███▏      | 304/938 [00:19<00:41, 15.20it/s, loss=0.726, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  32%|███▏      | 304/938 [00:19<00:41, 15.20it/s, loss=0.723, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  33%|███▎      | 305/938 [00:20<00:41, 15.20it/s, loss=0.72, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  33%|███▎      | 306/938 [00:20<00:41, 15.21it/s, loss=0.715, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  33%|███▎      | 307/938 [00:20<00:41, 15.22it/s, loss=0.715, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  33%|███▎      | 308/938 [00:20<00:41, 15.22it/s, loss=0.715, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  33%|███▎      | 308/938 [00:20<00:41, 15.22it/s, loss=0.707, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  33%|███▎      | 309/938 [00:20<00:41, 15.22it/s, loss=0.699, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  33%|███▎      | 310/938 [00:20<00:41, 15.23it/s, loss=0.698, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  33%|███▎      | 311/938 [00:20<00:41, 15.24it/s, loss=0.699, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  33%|███▎      | 312/938 [00:20<00:41, 15.24it/s, loss=0.699, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  33%|███▎      | 312/938 [00:20<00:41, 15.24it/s, loss=0.705, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  33%|███▎      | 313/938 [00:20<00:40, 15.25it/s, loss=0.711, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  33%|███▎      | 314/938 [00:20<00:40, 15.25it/s, loss=0.716, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  34%|███▎      | 315/938 [00:20<00:40, 15.25it/s, loss=0.724, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  34%|███▎      | 316/938 [00:20<00:40, 15.24it/s, loss=0.724, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  34%|███▎      | 316/938 [00:20<00:40, 15.24it/s, loss=0.724, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  34%|███▍      | 317/938 [00:20<00:40, 15.24it/s, loss=0.719, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  34%|███▍      | 318/938 [00:20<00:40, 15.24it/s, loss=0.719, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  34%|███▍      | 319/938 [00:20<00:40, 15.25it/s, loss=0.729, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  34%|███▍      | 320/938 [00:20<00:40, 15.25it/s, loss=0.729, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  34%|███▍      | 320/938 [00:20<00:40, 15.24it/s, loss=0.732, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  34%|███▍      | 321/938 [00:21<00:40, 15.26it/s, loss=0.74, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  34%|███▍      | 322/938 [00:21<00:40, 15.26it/s, loss=0.748, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  34%|███▍      | 323/938 [00:21<00:40, 15.27it/s, loss=0.742, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  35%|███▍      | 324/938 [00:21<00:40, 15.28it/s, loss=0.742, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  35%|███▍      | 324/938 [00:21<00:40, 15.28it/s, loss=0.739, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  35%|███▍      | 325/938 [00:21<00:40, 15.29it/s, loss=0.743, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  35%|███▍      | 326/938 [00:21<00:40, 15.29it/s, loss=0.74, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  35%|███▍      | 327/938 [00:21<00:39, 15.30it/s, loss=0.742, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  35%|███▍      | 328/938 [00:21<00:39, 15.30it/s, loss=0.742, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  35%|███▍      | 328/938 [00:21<00:39, 15.30it/s, loss=0.743, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  35%|███▌      | 329/938 [00:21<00:39, 15.30it/s, loss=0.748, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  35%|███▌      | 330/938 [00:21<00:39, 15.31it/s, loss=0.748, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  35%|███▌      | 331/938 [00:21<00:39, 15.31it/s, loss=0.766, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  35%|███▌      | 332/938 [00:21<00:39, 15.32it/s, loss=0.766, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  35%|███▌      | 332/938 [00:21<00:39, 15.32it/s, loss=0.77, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  36%|███▌      | 333/938 [00:21<00:39, 15.33it/s, loss=0.772, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  36%|███▌      | 334/938 [00:21<00:39, 15.33it/s, loss=0.766, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  36%|███▌      | 335/938 [00:21<00:39, 15.33it/s, loss=0.755, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  36%|███▌      | 336/938 [00:21<00:39, 15.34it/s, loss=0.755, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  36%|███▌      | 336/938 [00:21<00:39, 15.34it/s, loss=0.761, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  36%|███▌      | 337/938 [00:21<00:39, 15.34it/s, loss=0.765, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  36%|███▌      | 338/938 [00:22<00:39, 15.34it/s, loss=0.758, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  36%|███▌      | 339/938 [00:22<00:39, 15.34it/s, loss=0.761, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  36%|███▌      | 340/938 [00:22<00:38, 15.35it/s, loss=0.761, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  36%|███▌      | 340/938 [00:22<00:38, 15.35it/s, loss=0.752, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  36%|███▋      | 341/938 [00:22<00:38, 15.36it/s, loss=0.739, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  36%|███▋      | 342/938 [00:22<00:38, 15.36it/s, loss=0.738, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  37%|███▋      | 343/938 [00:22<00:38, 15.36it/s, loss=0.741, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  37%|███▋      | 344/938 [00:22<00:38, 15.37it/s, loss=0.741, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  37%|███▋      | 344/938 [00:22<00:38, 15.37it/s, loss=0.746, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  37%|███▋      | 345/938 [00:22<00:38, 15.37it/s, loss=0.735, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  37%|███▋      | 346/938 [00:22<00:38, 15.37it/s, loss=0.741, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  37%|███▋      | 347/938 [00:22<00:38, 15.38it/s, loss=0.74, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  37%|███▋      | 348/938 [00:22<00:38, 15.38it/s, loss=0.74, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  37%|███▋      | 348/938 [00:22<00:38, 15.38it/s, loss=0.744, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  37%|███▋      | 349/938 [00:22<00:38, 15.38it/s, loss=0.742, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  37%|███▋      | 350/938 [00:22<00:38, 15.38it/s, loss=0.742, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  37%|███▋      | 351/938 [00:22<00:38, 15.38it/s, loss=0.728, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  38%|███▊      | 352/938 [00:22<00:38, 15.39it/s, loss=0.728, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  38%|███▊      | 352/938 [00:22<00:38, 15.39it/s, loss=0.721, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  38%|███▊      | 353/938 [00:22<00:37, 15.40it/s, loss=0.716, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  38%|███▊      | 354/938 [00:22<00:37, 15.39it/s, loss=0.714, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  38%|███▊      | 355/938 [00:23<00:37, 15.40it/s, loss=0.717, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  38%|███▊      | 356/938 [00:23<00:37, 15.40it/s, loss=0.717, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  38%|███▊      | 356/938 [00:23<00:37, 15.40it/s, loss=0.712, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  38%|███▊      | 357/938 [00:23<00:37, 15.40it/s, loss=0.711, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  38%|███▊      | 358/938 [00:23<00:37, 15.39it/s, loss=0.708, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  38%|███▊      | 359/938 [00:23<00:37, 15.40it/s, loss=0.7, v_num=5, val_rmse=0.691, train_rmse=1.210]  
Epoch 1:  38%|███▊      | 360/938 [00:23<00:37, 15.39it/s, loss=0.7, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  38%|███▊      | 360/938 [00:23<00:37, 15.39it/s, loss=0.708, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  38%|███▊      | 361/938 [00:23<00:37, 15.39it/s, loss=0.708, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  39%|███▊      | 362/938 [00:23<00:37, 15.40it/s, loss=0.714, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  39%|███▊      | 363/938 [00:23<00:37, 15.39it/s, loss=0.712, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  39%|███▉      | 364/938 [00:23<00:37, 15.39it/s, loss=0.712, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  39%|███▉      | 364/938 [00:23<00:37, 15.39it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  39%|███▉      | 365/938 [00:23<00:37, 15.40it/s, loss=0.717, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  39%|███▉      | 366/938 [00:23<00:37, 15.40it/s, loss=0.721, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  39%|███▉      | 367/938 [00:23<00:37, 15.40it/s, loss=0.714, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  39%|███▉      | 368/938 [00:23<00:36, 15.41it/s, loss=0.714, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  39%|███▉      | 368/938 [00:23<00:36, 15.41it/s, loss=0.721, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  39%|███▉      | 369/938 [00:23<00:36, 15.42it/s, loss=0.715, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  39%|███▉      | 370/938 [00:23<00:36, 15.42it/s, loss=0.724, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  40%|███▉      | 371/938 [00:24<00:36, 15.43it/s, loss=0.724, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  40%|███▉      | 372/938 [00:24<00:36, 15.42it/s, loss=0.724, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  40%|███▉      | 372/938 [00:24<00:36, 15.42it/s, loss=0.728, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  40%|███▉      | 373/938 [00:24<00:36, 15.42it/s, loss=0.733, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  40%|███▉      | 374/938 [00:24<00:36, 15.43it/s, loss=0.73, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  40%|███▉      | 375/938 [00:24<00:36, 15.43it/s, loss=0.727, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  40%|████      | 376/938 [00:24<00:36, 15.43it/s, loss=0.727, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  40%|████      | 376/938 [00:24<00:36, 15.43it/s, loss=0.723, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  40%|████      | 377/938 [00:24<00:36, 15.43it/s, loss=0.715, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  40%|████      | 378/938 [00:24<00:36, 15.43it/s, loss=0.718, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  40%|████      | 379/938 [00:24<00:36, 15.43it/s, loss=0.723, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  41%|████      | 380/938 [00:24<00:36, 15.43it/s, loss=0.723, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  41%|████      | 380/938 [00:24<00:36, 15.43it/s, loss=0.729, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  41%|████      | 381/938 [00:24<00:36, 15.43it/s, loss=0.724, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  41%|████      | 382/938 [00:24<00:36, 15.43it/s, loss=0.722, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  41%|████      | 383/938 [00:24<00:35, 15.43it/s, loss=0.712, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  41%|████      | 384/938 [00:24<00:35, 15.43it/s, loss=0.712, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  41%|████      | 384/938 [00:24<00:35, 15.43it/s, loss=0.704, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  41%|████      | 385/938 [00:24<00:35, 15.44it/s, loss=0.702, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  41%|████      | 386/938 [00:25<00:35, 15.44it/s, loss=0.703, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  41%|████▏     | 387/938 [00:25<00:35, 15.45it/s, loss=0.707, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  41%|████▏     | 388/938 [00:25<00:35, 15.45it/s, loss=0.707, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  41%|████▏     | 388/938 [00:25<00:35, 15.45it/s, loss=0.702, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  41%|████▏     | 389/938 [00:25<00:35, 15.45it/s, loss=0.705, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  42%|████▏     | 390/938 [00:25<00:35, 15.46it/s, loss=0.699, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  42%|████▏     | 391/938 [00:25<00:35, 15.45it/s, loss=0.694, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  42%|████▏     | 392/938 [00:25<00:35, 15.46it/s, loss=0.694, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  42%|████▏     | 392/938 [00:25<00:35, 15.46it/s, loss=0.688, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  42%|████▏     | 393/938 [00:25<00:35, 15.45it/s, loss=0.684, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  42%|████▏     | 394/938 [00:25<00:35, 15.46it/s, loss=0.694, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  42%|████▏     | 395/938 [00:25<00:35, 15.46it/s, loss=0.699, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  42%|████▏     | 396/938 [00:25<00:35, 15.45it/s, loss=0.699, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  42%|████▏     | 396/938 [00:25<00:35, 15.45it/s, loss=0.699, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  42%|████▏     | 397/938 [00:25<00:35, 15.45it/s, loss=0.705, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  42%|████▏     | 398/938 [00:25<00:34, 15.45it/s, loss=0.702, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  43%|████▎     | 399/938 [00:25<00:34, 15.45it/s, loss=0.695, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  43%|████▎     | 400/938 [00:25<00:34, 15.45it/s, loss=0.695, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  43%|████▎     | 400/938 [00:25<00:34, 15.45it/s, loss=0.685, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  43%|████▎     | 401/938 [00:25<00:34, 15.45it/s, loss=0.688, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  43%|████▎     | 402/938 [00:26<00:34, 15.45it/s, loss=0.686, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  43%|████▎     | 403/938 [00:26<00:34, 15.45it/s, loss=0.693, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  43%|████▎     | 404/938 [00:26<00:34, 15.45it/s, loss=0.693, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  43%|████▎     | 404/938 [00:26<00:34, 15.45it/s, loss=0.696, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  43%|████▎     | 405/938 [00:26<00:34, 15.45it/s, loss=0.704, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  43%|████▎     | 406/938 [00:26<00:34, 15.45it/s, loss=0.698, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  43%|████▎     | 407/938 [00:26<00:34, 15.45it/s, loss=0.702, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  43%|████▎     | 408/938 [00:26<00:34, 15.45it/s, loss=0.702, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  43%|████▎     | 408/938 [00:26<00:34, 15.45it/s, loss=0.701, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  44%|████▎     | 409/938 [00:26<00:34, 15.44it/s, loss=0.702, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  44%|████▎     | 410/938 [00:26<00:34, 15.44it/s, loss=0.699, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  44%|████▍     | 411/938 [00:26<00:34, 15.45it/s, loss=0.701, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  44%|████▍     | 412/938 [00:26<00:34, 15.44it/s, loss=0.701, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  44%|████▍     | 412/938 [00:26<00:34, 15.44it/s, loss=0.707, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  44%|████▍     | 413/938 [00:26<00:33, 15.45it/s, loss=0.724, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  44%|████▍     | 414/938 [00:26<00:33, 15.45it/s, loss=0.721, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  44%|████▍     | 415/938 [00:26<00:33, 15.45it/s, loss=0.72, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  44%|████▍     | 416/938 [00:26<00:33, 15.45it/s, loss=0.72, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  44%|████▍     | 416/938 [00:26<00:33, 15.45it/s, loss=0.723, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  44%|████▍     | 417/938 [00:26<00:33, 15.45it/s, loss=0.731, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  45%|████▍     | 418/938 [00:27<00:33, 15.45it/s, loss=0.737, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  45%|████▍     | 419/938 [00:27<00:33, 15.45it/s, loss=0.746, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  45%|████▍     | 420/938 [00:27<00:33, 15.45it/s, loss=0.746, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  45%|████▍     | 420/938 [00:27<00:33, 15.45it/s, loss=0.749, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  45%|████▍     | 421/938 [00:27<00:33, 15.46it/s, loss=0.745, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  45%|████▍     | 422/938 [00:27<00:33, 15.45it/s, loss=0.745, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  45%|████▌     | 423/938 [00:27<00:33, 15.46it/s, loss=0.745, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  45%|████▌     | 424/938 [00:27<00:33, 15.46it/s, loss=0.745, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  45%|████▌     | 424/938 [00:27<00:33, 15.45it/s, loss=0.742, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  45%|████▌     | 425/938 [00:27<00:33, 15.45it/s, loss=0.73, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  45%|████▌     | 426/938 [00:27<00:33, 15.45it/s, loss=0.728, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  46%|████▌     | 427/938 [00:27<00:33, 15.44it/s, loss=0.725, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  46%|████▌     | 428/938 [00:27<00:33, 15.44it/s, loss=0.725, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  46%|████▌     | 428/938 [00:27<00:33, 15.44it/s, loss=0.724, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  46%|████▌     | 429/938 [00:27<00:32, 15.44it/s, loss=0.718, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  46%|████▌     | 430/938 [00:27<00:32, 15.44it/s, loss=0.715, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  46%|████▌     | 431/938 [00:27<00:32, 15.45it/s, loss=0.718, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  46%|████▌     | 432/938 [00:27<00:32, 15.44it/s, loss=0.718, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  46%|████▌     | 432/938 [00:27<00:32, 15.44it/s, loss=0.714, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  46%|████▌     | 433/938 [00:28<00:32, 15.44it/s, loss=0.699, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  46%|████▋     | 434/938 [00:28<00:32, 15.45it/s, loss=0.696, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  46%|████▋     | 435/938 [00:28<00:32, 15.45it/s, loss=0.695, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  46%|████▋     | 436/938 [00:28<00:32, 15.45it/s, loss=0.695, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  46%|████▋     | 436/938 [00:28<00:32, 15.45it/s, loss=0.691, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  47%|████▋     | 437/938 [00:28<00:32, 15.45it/s, loss=0.686, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  47%|████▋     | 438/938 [00:28<00:32, 15.45it/s, loss=0.688, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  47%|████▋     | 439/938 [00:28<00:32, 15.46it/s, loss=0.685, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  47%|████▋     | 440/938 [00:28<00:32, 15.45it/s, loss=0.685, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  47%|████▋     | 440/938 [00:28<00:32, 15.45it/s, loss=0.68, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  47%|████▋     | 441/938 [00:28<00:32, 15.46it/s, loss=0.691, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  47%|████▋     | 442/938 [00:28<00:32, 15.47it/s, loss=0.687, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  47%|████▋     | 443/938 [00:28<00:32, 15.43it/s, loss=0.687, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  47%|████▋     | 444/938 [00:28<00:32, 15.44it/s, loss=0.687, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  47%|████▋     | 444/938 [00:28<00:32, 15.44it/s, loss=0.692, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  47%|████▋     | 445/938 [00:28<00:31, 15.44it/s, loss=0.697, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  48%|████▊     | 446/938 [00:28<00:31, 15.43it/s, loss=0.7, v_num=5, val_rmse=0.691, train_rmse=1.210]  
Epoch 1:  48%|████▊     | 447/938 [00:28<00:31, 15.44it/s, loss=0.703, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  48%|████▊     | 448/938 [00:29<00:31, 15.44it/s, loss=0.703, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  48%|████▊     | 448/938 [00:29<00:31, 15.44it/s, loss=0.7, v_num=5, val_rmse=0.691, train_rmse=1.210]  
Epoch 1:  48%|████▊     | 449/938 [00:29<00:31, 15.44it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  48%|████▊     | 450/938 [00:29<00:31, 15.44it/s, loss=0.721, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  48%|████▊     | 451/938 [00:29<00:31, 15.45it/s, loss=0.716, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  48%|████▊     | 452/938 [00:29<00:31, 15.44it/s, loss=0.716, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  48%|████▊     | 452/938 [00:29<00:31, 15.44it/s, loss=0.72, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  48%|████▊     | 453/938 [00:29<00:31, 15.44it/s, loss=0.718, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  48%|████▊     | 454/938 [00:29<00:31, 15.44it/s, loss=0.724, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  49%|████▊     | 455/938 [00:29<00:31, 15.45it/s, loss=0.721, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  49%|████▊     | 456/938 [00:29<00:31, 15.45it/s, loss=0.721, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  49%|████▊     | 456/938 [00:29<00:31, 15.45it/s, loss=0.721, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  49%|████▊     | 457/938 [00:29<00:31, 15.45it/s, loss=0.713, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  49%|████▉     | 458/938 [00:29<00:31, 15.45it/s, loss=0.708, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  49%|████▉     | 459/938 [00:29<00:31, 15.45it/s, loss=0.708, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  49%|████▉     | 460/938 [00:29<00:30, 15.45it/s, loss=0.708, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  49%|████▉     | 460/938 [00:29<00:30, 15.45it/s, loss=0.714, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  49%|████▉     | 461/938 [00:29<00:30, 15.45it/s, loss=0.711, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  49%|████▉     | 462/938 [00:29<00:30, 15.45it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  49%|████▉     | 463/938 [00:29<00:30, 15.45it/s, loss=0.705, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  49%|████▉     | 464/938 [00:30<00:30, 15.46it/s, loss=0.705, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  49%|████▉     | 464/938 [00:30<00:30, 15.45it/s, loss=0.707, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  50%|████▉     | 465/938 [00:30<00:30, 15.45it/s, loss=0.707, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  50%|████▉     | 466/938 [00:30<00:30, 15.45it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210] 
Epoch 1:  50%|████▉     | 467/938 [00:30<00:30, 15.44it/s, loss=0.713, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  50%|████▉     | 468/938 [00:30<00:30, 15.45it/s, loss=0.713, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  50%|████▉     | 468/938 [00:30<00:30, 15.45it/s, loss=0.716, v_num=5, val_rmse=0.691, train_rmse=1.210]
Epoch 1:  50%|█████     | 469/938 [00:30<00:30, 15.46it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210] 

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]
Epoch 1:  50%|█████     | 472/938 [00:30<00:30, 15.51it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:   1%|          | 3/469 [00:00<00:19, 24.14it/s]

Validating:   1%|▏         | 6/469 [00:00<00:17, 25.98it/s]
Epoch 1:  51%|█████     | 476/938 [00:30<00:29, 15.57it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:   2%|▏         | 9/469 [00:00<00:17, 26.67it/s]
Epoch 1:  51%|█████     | 480/938 [00:30<00:29, 15.63it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:   3%|▎         | 12/469 [00:00<00:16, 26.97it/s]
Epoch 1:  52%|█████▏    | 484/938 [00:30<00:28, 15.68it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:   3%|▎         | 15/469 [00:00<00:17, 26.35it/s]

Validating:   4%|▍         | 18/469 [00:00<00:16, 26.60it/s]
Epoch 1:  52%|█████▏    | 488/938 [00:31<00:28, 15.73it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:   4%|▍         | 21/469 [00:00<00:16, 27.15it/s]
Epoch 1:  52%|█████▏    | 492/938 [00:31<00:28, 15.79it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:   5%|▌         | 24/469 [00:00<00:16, 27.03it/s]
Epoch 1:  53%|█████▎    | 496/938 [00:31<00:27, 15.84it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:   6%|▌         | 27/469 [00:01<00:16, 26.53it/s]

Validating:   6%|▋         | 30/469 [00:01<00:16, 26.37it/s]
Epoch 1:  53%|█████▎    | 500/938 [00:31<00:27, 15.89it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:   7%|▋         | 33/469 [00:01<00:16, 26.88it/s]
Epoch 1:  54%|█████▎    | 504/938 [00:31<00:27, 15.94it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:   8%|▊         | 36/469 [00:01<00:16, 26.91it/s]
Epoch 1:  54%|█████▍    | 508/938 [00:31<00:26, 16.00it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:   8%|▊         | 39/469 [00:01<00:16, 26.76it/s]
Epoch 1:  55%|█████▍    | 512/938 [00:31<00:26, 16.05it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:   9%|▉         | 43/469 [00:01<00:15, 28.00it/s]

Validating:  10%|▉         | 46/469 [00:01<00:15, 27.99it/s]
Epoch 1:  55%|█████▌    | 516/938 [00:32<00:26, 16.11it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  10%|█         | 49/469 [00:01<00:15, 27.46it/s]
Epoch 1:  55%|█████▌    | 520/938 [00:32<00:25, 16.16it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  11%|█         | 52/469 [00:01<00:15, 27.50it/s]
Epoch 1:  56%|█████▌    | 524/938 [00:32<00:25, 16.21it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  12%|█▏        | 55/469 [00:02<00:15, 27.20it/s]

Validating:  12%|█▏        | 58/469 [00:02<00:15, 26.01it/s]
Epoch 1:  56%|█████▋    | 528/938 [00:32<00:25, 16.25it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  13%|█▎        | 61/469 [00:02<00:15, 25.84it/s]
Epoch 1:  57%|█████▋    | 532/938 [00:32<00:24, 16.29it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  14%|█▍        | 65/469 [00:02<00:15, 26.54it/s]
Epoch 1:  57%|█████▋    | 536/938 [00:32<00:24, 16.34it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  14%|█▍        | 68/469 [00:02<00:14, 27.10it/s]
Epoch 1:  58%|█████▊    | 540/938 [00:32<00:24, 16.40it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  15%|█▌        | 71/469 [00:02<00:14, 27.14it/s]

Validating:  16%|█▌        | 74/469 [00:02<00:15, 25.29it/s]
Epoch 1:  58%|█████▊    | 544/938 [00:33<00:23, 16.43it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  17%|█▋        | 78/469 [00:02<00:14, 26.63it/s]
Epoch 1:  58%|█████▊    | 548/938 [00:33<00:23, 16.48it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  17%|█▋        | 81/469 [00:03<00:15, 25.48it/s]
Epoch 1:  59%|█████▉    | 552/938 [00:33<00:23, 16.52it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  18%|█▊        | 84/469 [00:03<00:14, 26.27it/s]
Epoch 1:  59%|█████▉    | 556/938 [00:33<00:23, 16.57it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  19%|█▊        | 87/469 [00:03<00:14, 27.02it/s]

Validating:  19%|█▉        | 90/469 [00:03<00:13, 27.12it/s]
Epoch 1:  60%|█████▉    | 560/938 [00:33<00:22, 16.62it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  20%|█▉        | 93/469 [00:03<00:13, 27.39it/s]
Epoch 1:  60%|██████    | 564/938 [00:33<00:22, 16.67it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  21%|██        | 97/469 [00:03<00:12, 28.75it/s]
Epoch 1:  61%|██████    | 568/938 [00:33<00:22, 16.72it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  21%|██▏       | 100/469 [00:03<00:13, 27.90it/s]
Epoch 1:  61%|██████    | 572/938 [00:34<00:21, 16.77it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  22%|██▏       | 103/469 [00:03<00:13, 27.77it/s]

Validating:  23%|██▎       | 106/469 [00:03<00:12, 28.31it/s]
Epoch 1:  61%|██████▏   | 576/938 [00:34<00:21, 16.81it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  23%|██▎       | 109/469 [00:04<00:12, 28.48it/s]
Epoch 1:  62%|██████▏   | 580/938 [00:34<00:21, 16.86it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  24%|██▍       | 112/469 [00:04<00:12, 28.61it/s]
Epoch 1:  62%|██████▏   | 584/938 [00:34<00:20, 16.91it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  25%|██▍       | 115/469 [00:04<00:12, 28.67it/s]

Validating:  25%|██▌       | 118/469 [00:04<00:12, 28.23it/s]
Epoch 1:  63%|██████▎   | 588/938 [00:34<00:20, 16.95it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  26%|██▌       | 121/469 [00:04<00:12, 28.20it/s]
Epoch 1:  63%|██████▎   | 592/938 [00:34<00:20, 17.00it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  26%|██▋       | 124/469 [00:04<00:12, 27.82it/s]
Epoch 1:  64%|██████▎   | 596/938 [00:34<00:20, 17.04it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  27%|██▋       | 127/469 [00:04<00:12, 27.91it/s]

Validating:  28%|██▊       | 130/469 [00:04<00:12, 27.91it/s]
Epoch 1:  64%|██████▍   | 600/938 [00:35<00:19, 17.09it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  28%|██▊       | 133/469 [00:04<00:12, 27.76it/s]
Epoch 1:  64%|██████▍   | 604/938 [00:35<00:19, 17.13it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  29%|██▉       | 137/469 [00:05<00:11, 28.31it/s]
Epoch 1:  65%|██████▍   | 608/938 [00:35<00:19, 17.18it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  30%|██▉       | 140/469 [00:05<00:11, 27.54it/s]
Epoch 1:  65%|██████▌   | 612/938 [00:35<00:18, 17.22it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  30%|███       | 143/469 [00:05<00:11, 27.33it/s]

Validating:  31%|███       | 146/469 [00:05<00:11, 27.13it/s]
Epoch 1:  66%|██████▌   | 616/938 [00:35<00:18, 17.26it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  32%|███▏      | 149/469 [00:05<00:11, 27.62it/s]
Epoch 1:  66%|██████▌   | 620/938 [00:35<00:18, 17.29it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  32%|███▏      | 152/469 [00:05<00:12, 26.36it/s]
Epoch 1:  67%|██████▋   | 624/938 [00:35<00:18, 17.33it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  33%|███▎      | 155/469 [00:05<00:11, 26.31it/s]

Validating:  34%|███▎      | 158/469 [00:05<00:11, 27.06it/s]
Epoch 1:  67%|██████▋   | 628/938 [00:36<00:17, 17.37it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  35%|███▍      | 162/469 [00:05<00:10, 28.27it/s]
Epoch 1:  67%|██████▋   | 632/938 [00:36<00:17, 17.42it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  35%|███▌      | 165/469 [00:06<00:10, 27.79it/s]
Epoch 1:  68%|██████▊   | 636/938 [00:36<00:17, 17.46it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  36%|███▌      | 168/469 [00:06<00:10, 27.83it/s]
Epoch 1:  68%|██████▊   | 640/938 [00:36<00:17, 17.50it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  36%|███▋      | 171/469 [00:06<00:10, 27.66it/s]

Validating:  37%|███▋      | 174/469 [00:06<00:11, 26.79it/s]
Epoch 1:  69%|██████▊   | 644/938 [00:36<00:16, 17.53it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  38%|███▊      | 177/469 [00:06<00:10, 26.73it/s]
Epoch 1:  69%|██████▉   | 648/938 [00:36<00:16, 17.57it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  38%|███▊      | 180/469 [00:06<00:10, 26.98it/s]
Epoch 1:  70%|██████▉   | 652/938 [00:37<00:16, 17.61it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  39%|███▉      | 183/469 [00:06<00:10, 27.30it/s]

Validating:  40%|███▉      | 186/469 [00:06<00:10, 27.23it/s]
Epoch 1:  70%|██████▉   | 656/938 [00:37<00:15, 17.65it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  40%|████      | 189/469 [00:06<00:10, 26.87it/s]
Epoch 1:  70%|███████   | 660/938 [00:37<00:15, 17.68it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  41%|████      | 192/469 [00:07<00:10, 26.09it/s]
Epoch 1:  71%|███████   | 664/938 [00:37<00:15, 17.72it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  42%|████▏     | 195/469 [00:07<00:10, 26.52it/s]

Validating:  42%|████▏     | 198/469 [00:07<00:10, 26.76it/s]
Epoch 1:  71%|███████   | 668/938 [00:37<00:15, 17.75it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  43%|████▎     | 201/469 [00:07<00:09, 27.39it/s]
Epoch 1:  72%|███████▏  | 672/938 [00:37<00:14, 17.80it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  43%|████▎     | 204/469 [00:07<00:09, 27.38it/s]
Epoch 1:  72%|███████▏  | 676/938 [00:37<00:14, 17.83it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  44%|████▍     | 207/469 [00:07<00:09, 27.53it/s]
Epoch 1:  72%|███████▏  | 680/938 [00:38<00:14, 17.88it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  45%|████▍     | 211/469 [00:07<00:08, 28.82it/s]

Validating:  46%|████▌     | 214/469 [00:07<00:09, 27.83it/s]
Epoch 1:  73%|███████▎  | 684/938 [00:38<00:14, 17.91it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  46%|████▋     | 217/469 [00:07<00:08, 28.02it/s]
Epoch 1:  73%|███████▎  | 688/938 [00:38<00:13, 17.95it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  47%|████▋     | 220/469 [00:08<00:08, 28.10it/s]
Epoch 1:  74%|███████▍  | 692/938 [00:38<00:13, 17.99it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  48%|████▊     | 223/469 [00:08<00:08, 28.21it/s]

Validating:  48%|████▊     | 226/469 [00:08<00:08, 27.84it/s]
Epoch 1:  74%|███████▍  | 696/938 [00:38<00:13, 18.02it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  49%|████▉     | 229/469 [00:08<00:08, 28.07it/s]
Epoch 1:  75%|███████▍  | 700/938 [00:38<00:13, 18.07it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  49%|████▉     | 232/469 [00:08<00:08, 28.46it/s]
Epoch 1:  75%|███████▌  | 704/938 [00:38<00:12, 18.10it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  50%|█████     | 235/469 [00:08<00:08, 27.94it/s]

Validating:  51%|█████     | 238/469 [00:08<00:08, 27.87it/s]
Epoch 1:  75%|███████▌  | 708/938 [00:39<00:12, 18.13it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  51%|█████▏    | 241/469 [00:08<00:08, 27.78it/s]
Epoch 1:  76%|███████▌  | 712/938 [00:39<00:12, 18.17it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  52%|█████▏    | 244/469 [00:08<00:08, 26.68it/s]
Epoch 1:  76%|███████▋  | 716/938 [00:39<00:12, 18.20it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  53%|█████▎    | 247/469 [00:09<00:08, 27.05it/s]
Epoch 1:  77%|███████▋  | 720/938 [00:39<00:11, 18.24it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  54%|█████▎    | 251/469 [00:09<00:07, 27.86it/s]

Validating:  54%|█████▍    | 254/469 [00:09<00:07, 27.39it/s]
Epoch 1:  77%|███████▋  | 724/938 [00:39<00:11, 18.27it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  55%|█████▍    | 257/469 [00:09<00:07, 26.68it/s]
Epoch 1:  78%|███████▊  | 728/938 [00:39<00:11, 18.30it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  55%|█████▌    | 260/469 [00:09<00:07, 26.86it/s]
Epoch 1:  78%|███████▊  | 732/938 [00:39<00:11, 18.33it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  56%|█████▌    | 263/469 [00:09<00:07, 27.24it/s]

Validating:  57%|█████▋    | 266/469 [00:09<00:07, 25.78it/s]
Epoch 1:  78%|███████▊  | 736/938 [00:40<00:11, 18.35it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  57%|█████▋    | 269/469 [00:09<00:07, 25.01it/s]
Epoch 1:  79%|███████▉  | 740/938 [00:40<00:10, 18.38it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  58%|█████▊    | 272/469 [00:10<00:07, 25.09it/s]
Epoch 1:  79%|███████▉  | 744/938 [00:40<00:10, 18.41it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  59%|█████▊    | 275/469 [00:10<00:07, 25.72it/s]

Validating:  59%|█████▉    | 278/469 [00:10<00:07, 25.39it/s]
Epoch 1:  80%|███████▉  | 748/938 [00:40<00:10, 18.43it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  60%|█████▉    | 281/469 [00:10<00:07, 25.64it/s]
Epoch 1:  80%|████████  | 752/938 [00:40<00:10, 18.46it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  61%|██████    | 284/469 [00:10<00:07, 26.31it/s]
Epoch 1:  81%|████████  | 756/938 [00:40<00:09, 18.50it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  61%|██████    | 287/469 [00:10<00:06, 26.29it/s]

Validating:  62%|██████▏   | 290/469 [00:10<00:06, 27.29it/s]
Epoch 1:  81%|████████  | 760/938 [00:41<00:09, 18.53it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  62%|██████▏   | 293/469 [00:10<00:06, 27.30it/s]
Epoch 1:  81%|████████▏ | 764/938 [00:41<00:09, 18.56it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  63%|██████▎   | 296/469 [00:10<00:06, 27.50it/s]
Epoch 1:  82%|████████▏ | 768/938 [00:41<00:09, 18.59it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  64%|██████▍   | 299/469 [00:11<00:06, 27.86it/s]

Validating:  64%|██████▍   | 302/469 [00:11<00:05, 28.34it/s]
Epoch 1:  82%|████████▏ | 772/938 [00:41<00:08, 18.63it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  65%|██████▌   | 305/469 [00:11<00:05, 28.29it/s]
Epoch 1:  83%|████████▎ | 776/938 [00:41<00:08, 18.66it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  66%|██████▌   | 308/469 [00:11<00:05, 27.26it/s]
Epoch 1:  83%|████████▎ | 780/938 [00:41<00:08, 18.69it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  66%|██████▋   | 311/469 [00:11<00:05, 27.38it/s]
Epoch 1:  84%|████████▎ | 784/938 [00:41<00:08, 18.72it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  67%|██████▋   | 315/469 [00:11<00:05, 28.06it/s]

Validating:  68%|██████▊   | 318/469 [00:11<00:05, 28.26it/s]
Epoch 1:  84%|████████▍ | 788/938 [00:42<00:07, 18.76it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  68%|██████▊   | 321/469 [00:11<00:05, 27.18it/s]
Epoch 1:  84%|████████▍ | 792/938 [00:42<00:07, 18.78it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  69%|██████▉   | 324/469 [00:11<00:05, 27.50it/s]
Epoch 1:  85%|████████▍ | 796/938 [00:42<00:07, 18.81it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  70%|██████▉   | 327/469 [00:12<00:05, 27.63it/s]

Validating:  70%|███████   | 330/469 [00:12<00:04, 28.20it/s]
Epoch 1:  85%|████████▌ | 800/938 [00:42<00:07, 18.85it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  71%|███████   | 333/469 [00:12<00:04, 28.60it/s]
Epoch 1:  86%|████████▌ | 804/938 [00:42<00:07, 18.88it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  72%|███████▏  | 336/469 [00:12<00:04, 27.99it/s]
Epoch 1:  86%|████████▌ | 808/938 [00:42<00:06, 18.91it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  72%|███████▏  | 339/469 [00:12<00:04, 27.43it/s]

Validating:  73%|███████▎  | 342/469 [00:12<00:04, 27.23it/s]
Epoch 1:  87%|████████▋ | 812/938 [00:42<00:06, 18.93it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  74%|███████▎  | 345/469 [00:12<00:04, 27.41it/s]
Epoch 1:  87%|████████▋ | 816/938 [00:43<00:06, 18.96it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  74%|███████▍  | 348/469 [00:12<00:04, 26.85it/s]
Epoch 1:  87%|████████▋ | 820/938 [00:43<00:06, 18.99it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  75%|███████▍  | 351/469 [00:12<00:04, 26.89it/s]

Validating:  75%|███████▌  | 354/469 [00:13<00:04, 26.69it/s]
Epoch 1:  88%|████████▊ | 824/938 [00:43<00:05, 19.01it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  76%|███████▌  | 357/469 [00:13<00:04, 26.85it/s]
Epoch 1:  88%|████████▊ | 828/938 [00:43<00:05, 19.04it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  77%|███████▋  | 360/469 [00:13<00:04, 26.89it/s]
Epoch 1:  89%|████████▊ | 832/938 [00:43<00:05, 19.06it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  77%|███████▋  | 363/469 [00:13<00:04, 26.38it/s]

Validating:  78%|███████▊  | 366/469 [00:13<00:03, 27.17it/s]
Epoch 1:  89%|████████▉ | 836/938 [00:43<00:05, 19.09it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  79%|███████▊  | 369/469 [00:13<00:03, 27.27it/s]
Epoch 1:  90%|████████▉ | 840/938 [00:43<00:05, 19.12it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  79%|███████▉  | 372/469 [00:13<00:03, 27.70it/s]
Epoch 1:  90%|████████▉ | 844/938 [00:44<00:04, 19.16it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  80%|███████▉  | 375/469 [00:13<00:03, 27.43it/s]

Validating:  81%|████████  | 378/469 [00:13<00:03, 27.93it/s]
Epoch 1:  90%|█████████ | 848/938 [00:44<00:04, 19.18it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  81%|████████▏ | 382/469 [00:14<00:03, 28.57it/s]
Epoch 1:  91%|█████████ | 852/938 [00:44<00:04, 19.21it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  82%|████████▏ | 385/469 [00:14<00:02, 28.29it/s]
Epoch 1:  91%|█████████▏| 856/938 [00:44<00:04, 19.24it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  83%|████████▎ | 388/469 [00:14<00:02, 28.15it/s]
Epoch 1:  92%|█████████▏| 860/938 [00:44<00:04, 19.27it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  83%|████████▎ | 391/469 [00:14<00:02, 27.82it/s]

Validating:  84%|████████▍ | 394/469 [00:14<00:02, 27.75it/s]
Epoch 1:  92%|█████████▏| 864/938 [00:44<00:03, 19.29it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  85%|████████▍ | 397/469 [00:14<00:02, 27.49it/s]
Epoch 1:  93%|█████████▎| 868/938 [00:44<00:03, 19.32it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  85%|████████▌ | 400/469 [00:14<00:02, 27.68it/s]
Epoch 1:  93%|█████████▎| 872/938 [00:45<00:03, 19.35it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  86%|████████▌ | 403/469 [00:14<00:02, 27.99it/s]

Validating:  87%|████████▋ | 406/469 [00:14<00:02, 27.45it/s]
Epoch 1:  93%|█████████▎| 876/938 [00:45<00:03, 19.37it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  87%|████████▋ | 409/469 [00:14<00:02, 27.44it/s]
Epoch 1:  94%|█████████▍| 880/938 [00:45<00:02, 19.40it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  88%|████████▊ | 412/469 [00:15<00:02, 27.96it/s]
Epoch 1:  94%|█████████▍| 884/938 [00:45<00:02, 19.43it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  88%|████████▊ | 415/469 [00:15<00:01, 27.99it/s]

Validating:  89%|████████▉ | 418/469 [00:15<00:01, 27.89it/s]
Epoch 1:  95%|█████████▍| 888/938 [00:45<00:02, 19.45it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  90%|████████▉ | 421/469 [00:15<00:01, 27.42it/s]
Epoch 1:  95%|█████████▌| 892/938 [00:45<00:02, 19.48it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  91%|█████████ | 425/469 [00:15<00:01, 28.24it/s]
Epoch 1:  96%|█████████▌| 896/938 [00:45<00:02, 19.51it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  91%|█████████▏| 428/469 [00:15<00:01, 27.53it/s]
Epoch 1:  96%|█████████▌| 900/938 [00:46<00:01, 19.53it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  92%|█████████▏| 431/469 [00:15<00:01, 27.28it/s]

Validating:  93%|█████████▎| 434/469 [00:15<00:01, 26.13it/s]
Epoch 1:  96%|█████████▋| 904/938 [00:46<00:01, 19.55it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  93%|█████████▎| 437/469 [00:16<00:01, 26.33it/s]
Epoch 1:  97%|█████████▋| 908/938 [00:46<00:01, 19.57it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  94%|█████████▍| 440/469 [00:16<00:01, 26.42it/s]
Epoch 1:  97%|█████████▋| 912/938 [00:46<00:01, 19.59it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  94%|█████████▍| 443/469 [00:16<00:00, 26.47it/s]

Validating:  95%|█████████▌| 446/469 [00:16<00:00, 27.00it/s]
Epoch 1:  98%|█████████▊| 916/938 [00:46<00:01, 19.62it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  96%|█████████▌| 449/469 [00:16<00:00, 27.61it/s]
Epoch 1:  98%|█████████▊| 920/938 [00:46<00:00, 19.65it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  96%|█████████▋| 452/469 [00:16<00:00, 27.98it/s]
Epoch 1:  99%|█████████▊| 924/938 [00:46<00:00, 19.67it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  97%|█████████▋| 455/469 [00:16<00:00, 27.37it/s]

Validating:  98%|█████████▊| 458/469 [00:16<00:00, 27.15it/s]
Epoch 1:  99%|█████████▉| 928/938 [00:47<00:00, 19.69it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  98%|█████████▊| 461/469 [00:16<00:00, 27.55it/s]
Epoch 1:  99%|█████████▉| 932/938 [00:47<00:00, 19.72it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating:  99%|█████████▉| 464/469 [00:17<00:00, 27.49it/s]
Epoch 1: 100%|█████████▉| 936/938 [00:47<00:00, 19.74it/s, loss=0.71, v_num=5, val_rmse=0.691, train_rmse=1.210]

Validating: 100%|█████████▉| 467/469 [00:17<00:00, 27.68it/s]
Epoch 1: 100%|██████████| 938/938 [00:47<00:00, 19.74it/s, loss=0.71, v_num=5, val_rmse=0.561, train_rmse=1.210]

                                                             
Epoch 1: 100%|██████████| 938/938 [00:47<00:00, 19.74it/s, loss=0.71, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 1:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.71, v_num=5, val_rmse=0.561, train_rmse=0.743]          
Epoch 2:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.71, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   0%|          | 1/938 [00:00<01:05, 14.24it/s, loss=0.706, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   0%|          | 2/938 [00:00<01:00, 15.56it/s, loss=0.71, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:   0%|          | 3/938 [00:00<00:58, 15.93it/s, loss=0.703, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   0%|          | 4/938 [00:00<00:56, 16.44it/s, loss=0.703, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   0%|          | 4/938 [00:00<00:56, 16.41it/s, loss=0.703, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   1%|          | 5/938 [00:00<00:55, 16.75it/s, loss=0.697, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   1%|          | 6/938 [00:00<00:56, 16.51it/s, loss=0.704, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   1%|          | 7/938 [00:00<00:55, 16.84it/s, loss=0.705, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   1%|          | 8/938 [00:00<00:59, 15.71it/s, loss=0.705, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   1%|          | 8/938 [00:00<00:59, 15.70it/s, loss=0.712, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   1%|          | 9/938 [00:00<00:59, 15.73it/s, loss=0.714, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   1%|          | 10/938 [00:00<00:58, 15.87it/s, loss=0.708, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   1%|          | 11/938 [00:00<00:58, 15.95it/s, loss=0.707, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   1%|▏         | 12/938 [00:00<00:57, 16.04it/s, loss=0.707, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   1%|▏         | 12/938 [00:00<00:57, 16.04it/s, loss=0.703, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   1%|▏         | 13/938 [00:00<00:58, 15.94it/s, loss=0.703, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   1%|▏         | 14/938 [00:00<01:01, 15.13it/s, loss=0.711, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   2%|▏         | 15/938 [00:00<01:00, 15.27it/s, loss=0.708, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   2%|▏         | 16/938 [00:01<01:00, 15.20it/s, loss=0.708, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   2%|▏         | 16/938 [00:01<01:00, 15.19it/s, loss=0.705, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   2%|▏         | 17/938 [00:01<01:00, 15.27it/s, loss=0.697, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   2%|▏         | 18/938 [00:01<00:59, 15.39it/s, loss=0.689, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   2%|▏         | 19/938 [00:01<00:59, 15.43it/s, loss=0.687, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   2%|▏         | 20/938 [00:01<00:59, 15.50it/s, loss=0.687, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   2%|▏         | 20/938 [00:01<00:59, 15.49it/s, loss=0.686, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   2%|▏         | 21/938 [00:01<00:59, 15.48it/s, loss=0.682, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   2%|▏         | 22/938 [00:01<00:58, 15.60it/s, loss=0.677, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   2%|▏         | 23/938 [00:01<00:57, 15.78it/s, loss=0.681, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   3%|▎         | 24/938 [00:01<00:58, 15.72it/s, loss=0.681, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   3%|▎         | 24/938 [00:01<00:58, 15.72it/s, loss=0.686, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   3%|▎         | 25/938 [00:01<00:57, 15.79it/s, loss=0.696, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   3%|▎         | 26/938 [00:01<00:57, 15.89it/s, loss=0.692, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   3%|▎         | 27/938 [00:01<00:57, 15.86it/s, loss=0.693, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   3%|▎         | 28/938 [00:01<00:57, 15.89it/s, loss=0.693, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   3%|▎         | 28/938 [00:01<00:57, 15.89it/s, loss=0.689, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   3%|▎         | 29/938 [00:01<00:56, 15.95it/s, loss=0.691, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   3%|▎         | 30/938 [00:01<00:57, 15.90it/s, loss=0.695, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   3%|▎         | 31/938 [00:01<00:56, 15.95it/s, loss=0.696, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   3%|▎         | 32/938 [00:02<00:57, 15.85it/s, loss=0.696, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   3%|▎         | 32/938 [00:02<00:57, 15.84it/s, loss=0.696, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   4%|▎         | 33/938 [00:02<00:57, 15.80it/s, loss=0.695, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   4%|▎         | 34/938 [00:02<00:56, 15.89it/s, loss=0.698, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   4%|▎         | 35/938 [00:02<00:57, 15.79it/s, loss=0.697, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   4%|▍         | 36/938 [00:02<00:57, 15.67it/s, loss=0.697, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   4%|▍         | 36/938 [00:02<00:57, 15.67it/s, loss=0.699, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   4%|▍         | 37/938 [00:02<00:57, 15.63it/s, loss=0.7, v_num=5, val_rmse=0.561, train_rmse=0.743]  
Epoch 2:   4%|▍         | 38/938 [00:02<00:57, 15.60it/s, loss=0.704, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   4%|▍         | 39/938 [00:02<00:57, 15.63it/s, loss=0.702, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   4%|▍         | 40/938 [00:02<00:57, 15.59it/s, loss=0.702, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   4%|▍         | 40/938 [00:02<00:57, 15.59it/s, loss=0.702, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   4%|▍         | 41/938 [00:02<00:57, 15.61it/s, loss=0.699, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   4%|▍         | 42/938 [00:02<00:57, 15.61it/s, loss=0.703, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   5%|▍         | 43/938 [00:02<00:57, 15.58it/s, loss=0.699, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   5%|▍         | 44/938 [00:02<00:57, 15.63it/s, loss=0.699, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   5%|▍         | 44/938 [00:02<00:57, 15.63it/s, loss=0.688, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   5%|▍         | 45/938 [00:02<00:57, 15.61it/s, loss=0.675, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   5%|▍         | 46/938 [00:02<00:57, 15.62it/s, loss=0.672, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   5%|▌         | 47/938 [00:02<00:56, 15.68it/s, loss=0.673, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   5%|▌         | 48/938 [00:03<00:56, 15.67it/s, loss=0.673, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   5%|▌         | 48/938 [00:03<00:56, 15.67it/s, loss=0.669, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   5%|▌         | 49/938 [00:03<00:56, 15.62it/s, loss=0.669, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   5%|▌         | 50/938 [00:03<00:56, 15.65it/s, loss=0.68, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:   5%|▌         | 51/938 [00:03<00:56, 15.67it/s, loss=0.68, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   6%|▌         | 52/938 [00:03<00:56, 15.68it/s, loss=0.68, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   6%|▌         | 52/938 [00:03<00:56, 15.68it/s, loss=0.68, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   6%|▌         | 53/938 [00:03<00:56, 15.66it/s, loss=0.692, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   6%|▌         | 54/938 [00:03<00:56, 15.68it/s, loss=0.679, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   6%|▌         | 55/938 [00:03<00:56, 15.75it/s, loss=0.683, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   6%|▌         | 56/938 [00:03<00:56, 15.71it/s, loss=0.683, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   6%|▌         | 56/938 [00:03<00:56, 15.71it/s, loss=0.682, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   6%|▌         | 57/938 [00:03<00:56, 15.70it/s, loss=0.681, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   6%|▌         | 58/938 [00:03<00:55, 15.72it/s, loss=0.675, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   6%|▋         | 59/938 [00:03<00:55, 15.75it/s, loss=0.676, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   6%|▋         | 60/938 [00:03<00:55, 15.70it/s, loss=0.676, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   6%|▋         | 60/938 [00:03<00:55, 15.69it/s, loss=0.683, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   7%|▋         | 61/938 [00:03<00:56, 15.65it/s, loss=0.687, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   7%|▋         | 62/938 [00:03<00:56, 15.63it/s, loss=0.687, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   7%|▋         | 63/938 [00:04<00:55, 15.66it/s, loss=0.696, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   7%|▋         | 64/938 [00:04<00:55, 15.64it/s, loss=0.696, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   7%|▋         | 64/938 [00:04<00:55, 15.64it/s, loss=0.703, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   7%|▋         | 65/938 [00:04<00:55, 15.63it/s, loss=0.706, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   7%|▋         | 66/938 [00:04<00:55, 15.63it/s, loss=0.704, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   7%|▋         | 67/938 [00:04<00:55, 15.60it/s, loss=0.71, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:   7%|▋         | 68/938 [00:04<00:55, 15.59it/s, loss=0.71, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   7%|▋         | 68/938 [00:04<00:55, 15.59it/s, loss=0.717, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   7%|▋         | 69/938 [00:04<00:55, 15.58it/s, loss=0.715, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   7%|▋         | 70/938 [00:04<00:55, 15.58it/s, loss=0.701, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   8%|▊         | 71/938 [00:04<00:55, 15.57it/s, loss=0.696, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   8%|▊         | 72/938 [00:04<00:55, 15.59it/s, loss=0.696, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   8%|▊         | 72/938 [00:04<00:55, 15.59it/s, loss=0.697, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   8%|▊         | 73/938 [00:04<00:55, 15.63it/s, loss=0.701, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   8%|▊         | 74/938 [00:04<00:55, 15.64it/s, loss=0.707, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   8%|▊         | 75/938 [00:04<00:55, 15.64it/s, loss=0.703, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   8%|▊         | 76/938 [00:04<00:54, 15.67it/s, loss=0.703, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   8%|▊         | 76/938 [00:04<00:54, 15.67it/s, loss=0.702, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   8%|▊         | 77/938 [00:04<00:54, 15.70it/s, loss=0.71, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:   8%|▊         | 78/938 [00:04<00:54, 15.71it/s, loss=0.707, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   8%|▊         | 79/938 [00:05<00:54, 15.72it/s, loss=0.702, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   9%|▊         | 80/938 [00:05<00:54, 15.70it/s, loss=0.702, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   9%|▊         | 80/938 [00:05<00:54, 15.70it/s, loss=0.697, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   9%|▊         | 81/938 [00:05<00:54, 15.69it/s, loss=0.698, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   9%|▊         | 82/938 [00:05<00:54, 15.68it/s, loss=0.705, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   9%|▉         | 83/938 [00:05<00:54, 15.67it/s, loss=0.714, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   9%|▉         | 84/938 [00:05<00:54, 15.66it/s, loss=0.714, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   9%|▉         | 84/938 [00:05<00:54, 15.66it/s, loss=0.715, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   9%|▉         | 85/938 [00:05<00:54, 15.69it/s, loss=0.717, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   9%|▉         | 86/938 [00:05<00:54, 15.66it/s, loss=0.719, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   9%|▉         | 87/938 [00:05<00:54, 15.67it/s, loss=0.713, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   9%|▉         | 88/938 [00:05<00:54, 15.65it/s, loss=0.713, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   9%|▉         | 88/938 [00:05<00:54, 15.64it/s, loss=0.705, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:   9%|▉         | 89/938 [00:05<00:54, 15.58it/s, loss=0.7, v_num=5, val_rmse=0.561, train_rmse=0.743]  
Epoch 2:  10%|▉         | 90/938 [00:05<00:54, 15.57it/s, loss=0.705, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  10%|▉         | 91/938 [00:05<00:54, 15.58it/s, loss=0.705, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  10%|▉         | 92/938 [00:05<00:54, 15.58it/s, loss=0.705, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  10%|▉         | 92/938 [00:05<00:54, 15.57it/s, loss=0.71, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  10%|▉         | 93/938 [00:05<00:54, 15.61it/s, loss=0.696, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  10%|█         | 94/938 [00:06<00:54, 15.60it/s, loss=0.69, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  10%|█         | 95/938 [00:06<00:54, 15.58it/s, loss=0.689, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  10%|█         | 96/938 [00:06<00:53, 15.59it/s, loss=0.689, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  10%|█         | 96/938 [00:06<00:54, 15.59it/s, loss=0.683, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  10%|█         | 97/938 [00:06<00:53, 15.58it/s, loss=0.68, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  10%|█         | 98/938 [00:06<00:53, 15.58it/s, loss=0.693, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  11%|█         | 99/938 [00:06<00:53, 15.58it/s, loss=0.697, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  11%|█         | 100/938 [00:06<00:53, 15.57it/s, loss=0.697, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  11%|█         | 100/938 [00:06<00:53, 15.56it/s, loss=0.693, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  11%|█         | 101/938 [00:06<00:53, 15.56it/s, loss=0.691, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  11%|█         | 102/938 [00:06<00:53, 15.57it/s, loss=0.684, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  11%|█         | 103/938 [00:06<00:53, 15.58it/s, loss=0.668, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  11%|█         | 104/938 [00:06<00:53, 15.58it/s, loss=0.668, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  11%|█         | 104/938 [00:06<00:53, 15.58it/s, loss=0.671, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  11%|█         | 105/938 [00:06<00:53, 15.57it/s, loss=0.666, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  11%|█▏        | 106/938 [00:06<00:53, 15.58it/s, loss=0.669, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  11%|█▏        | 107/938 [00:06<00:53, 15.59it/s, loss=0.671, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  12%|█▏        | 108/938 [00:06<00:53, 15.58it/s, loss=0.671, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  12%|█▏        | 108/938 [00:06<00:53, 15.58it/s, loss=0.681, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  12%|█▏        | 109/938 [00:06<00:53, 15.58it/s, loss=0.687, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  12%|█▏        | 110/938 [00:07<00:53, 15.58it/s, loss=0.687, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  12%|█▏        | 111/938 [00:07<00:53, 15.56it/s, loss=0.69, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  12%|█▏        | 112/938 [00:07<00:53, 15.55it/s, loss=0.69, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  12%|█▏        | 112/938 [00:07<00:53, 15.55it/s, loss=0.68, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  12%|█▏        | 113/938 [00:07<00:53, 15.53it/s, loss=0.678, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  12%|█▏        | 114/938 [00:07<00:53, 15.52it/s, loss=0.674, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  12%|█▏        | 115/938 [00:07<00:53, 15.52it/s, loss=0.683, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  12%|█▏        | 116/938 [00:07<00:53, 15.51it/s, loss=0.683, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  12%|█▏        | 116/938 [00:07<00:53, 15.51it/s, loss=0.689, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  12%|█▏        | 117/938 [00:07<00:52, 15.50it/s, loss=0.681, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  13%|█▎        | 118/938 [00:07<00:52, 15.50it/s, loss=0.672, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  13%|█▎        | 119/938 [00:07<00:52, 15.47it/s, loss=0.668, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  13%|█▎        | 120/938 [00:07<00:52, 15.46it/s, loss=0.668, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  13%|█▎        | 120/938 [00:07<00:52, 15.46it/s, loss=0.672, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  13%|█▎        | 121/938 [00:07<00:52, 15.48it/s, loss=0.669, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  13%|█▎        | 122/938 [00:07<00:52, 15.46it/s, loss=0.667, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  13%|█▎        | 123/938 [00:07<00:52, 15.45it/s, loss=0.668, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  13%|█▎        | 124/938 [00:08<00:52, 15.43it/s, loss=0.668, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  13%|█▎        | 124/938 [00:08<00:52, 15.43it/s, loss=0.667, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  13%|█▎        | 125/938 [00:08<00:52, 15.43it/s, loss=0.673, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  13%|█▎        | 126/938 [00:08<00:52, 15.44it/s, loss=0.673, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  14%|█▎        | 127/938 [00:08<00:52, 15.42it/s, loss=0.669, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  14%|█▎        | 128/938 [00:08<00:52, 15.42it/s, loss=0.669, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  14%|█▎        | 128/938 [00:08<00:52, 15.42it/s, loss=0.661, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  14%|█▍        | 129/938 [00:08<00:52, 15.45it/s, loss=0.657, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  14%|█▍        | 130/938 [00:08<00:52, 15.44it/s, loss=0.651, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  14%|█▍        | 131/938 [00:08<00:52, 15.43it/s, loss=0.646, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  14%|█▍        | 132/938 [00:08<00:52, 15.40it/s, loss=0.646, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  14%|█▍        | 132/938 [00:08<00:52, 15.40it/s, loss=0.652, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  14%|█▍        | 133/938 [00:08<00:52, 15.39it/s, loss=0.662, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  14%|█▍        | 134/938 [00:08<00:52, 15.39it/s, loss=0.669, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  14%|█▍        | 135/938 [00:08<00:52, 15.39it/s, loss=0.662, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  14%|█▍        | 136/938 [00:08<00:52, 15.40it/s, loss=0.662, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  14%|█▍        | 136/938 [00:08<00:52, 15.40it/s, loss=0.661, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  15%|█▍        | 137/938 [00:08<00:52, 15.40it/s, loss=0.671, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  15%|█▍        | 138/938 [00:08<00:51, 15.39it/s, loss=0.678, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  15%|█▍        | 139/938 [00:09<00:51, 15.39it/s, loss=0.675, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  15%|█▍        | 140/938 [00:09<00:51, 15.40it/s, loss=0.675, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  15%|█▍        | 140/938 [00:09<00:51, 15.40it/s, loss=0.676, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  15%|█▌        | 141/938 [00:09<00:51, 15.41it/s, loss=0.684, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  15%|█▌        | 142/938 [00:09<00:51, 15.41it/s, loss=0.682, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  15%|█▌        | 143/938 [00:09<00:51, 15.43it/s, loss=0.684, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  15%|█▌        | 144/938 [00:09<00:51, 15.43it/s, loss=0.684, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  15%|█▌        | 144/938 [00:09<00:51, 15.43it/s, loss=0.673, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  15%|█▌        | 145/938 [00:09<00:51, 15.38it/s, loss=0.675, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  16%|█▌        | 146/938 [00:09<00:51, 15.33it/s, loss=0.675, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  16%|█▌        | 147/938 [00:09<00:51, 15.32it/s, loss=0.677, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  16%|█▌        | 148/938 [00:09<00:51, 15.29it/s, loss=0.677, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  16%|█▌        | 148/938 [00:09<00:51, 15.29it/s, loss=0.687, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  16%|█▌        | 149/938 [00:09<00:51, 15.29it/s, loss=0.689, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  16%|█▌        | 150/938 [00:09<00:51, 15.29it/s, loss=0.689, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  16%|█▌        | 151/938 [00:09<00:51, 15.29it/s, loss=0.688, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  16%|█▌        | 152/938 [00:09<00:51, 15.28it/s, loss=0.688, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  16%|█▌        | 152/938 [00:09<00:51, 15.28it/s, loss=0.683, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  16%|█▋        | 153/938 [00:09<00:51, 15.31it/s, loss=0.678, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  16%|█▋        | 154/938 [00:10<00:51, 15.27it/s, loss=0.687, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  17%|█▋        | 155/938 [00:10<00:51, 15.27it/s, loss=0.679, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  17%|█▋        | 156/938 [00:10<00:51, 15.28it/s, loss=0.679, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  17%|█▋        | 156/938 [00:10<00:51, 15.28it/s, loss=0.676, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  17%|█▋        | 157/938 [00:10<00:51, 15.27it/s, loss=0.671, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  17%|█▋        | 158/938 [00:10<00:51, 15.27it/s, loss=0.666, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  17%|█▋        | 159/938 [00:10<00:50, 15.28it/s, loss=0.675, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  17%|█▋        | 160/938 [00:10<00:50, 15.29it/s, loss=0.675, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  17%|█▋        | 160/938 [00:10<00:50, 15.29it/s, loss=0.671, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  17%|█▋        | 161/938 [00:10<00:50, 15.30it/s, loss=0.662, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  17%|█▋        | 162/938 [00:10<00:50, 15.31it/s, loss=0.666, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  17%|█▋        | 163/938 [00:10<00:50, 15.30it/s, loss=0.676, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  17%|█▋        | 164/938 [00:10<00:50, 15.32it/s, loss=0.676, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  17%|█▋        | 164/938 [00:10<00:50, 15.32it/s, loss=0.688, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  18%|█▊        | 165/938 [00:10<00:50, 15.32it/s, loss=0.691, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  18%|█▊        | 166/938 [00:10<00:50, 15.33it/s, loss=0.691, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  18%|█▊        | 167/938 [00:10<00:50, 15.33it/s, loss=0.69, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  18%|█▊        | 168/938 [00:10<00:50, 15.34it/s, loss=0.69, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  18%|█▊        | 168/938 [00:10<00:50, 15.34it/s, loss=0.685, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  18%|█▊        | 169/938 [00:11<00:50, 15.35it/s, loss=0.691, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  18%|█▊        | 170/938 [00:11<00:50, 15.33it/s, loss=0.69, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  18%|█▊        | 171/938 [00:11<00:50, 15.32it/s, loss=0.701, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  18%|█▊        | 172/938 [00:11<00:50, 15.32it/s, loss=0.701, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  18%|█▊        | 172/938 [00:11<00:50, 15.31it/s, loss=0.707, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  18%|█▊        | 173/938 [00:11<00:49, 15.32it/s, loss=0.706, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  19%|█▊        | 174/938 [00:11<00:49, 15.32it/s, loss=0.691, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  19%|█▊        | 175/938 [00:11<00:49, 15.33it/s, loss=0.706, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  19%|█▉        | 176/938 [00:11<00:49, 15.32it/s, loss=0.706, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  19%|█▉        | 176/938 [00:11<00:49, 15.32it/s, loss=0.707, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  19%|█▉        | 177/938 [00:11<00:49, 15.31it/s, loss=0.709, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  19%|█▉        | 178/938 [00:11<00:49, 15.29it/s, loss=0.715, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  19%|█▉        | 179/938 [00:11<00:49, 15.29it/s, loss=0.717, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  19%|█▉        | 180/938 [00:11<00:49, 15.29it/s, loss=0.717, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  19%|█▉        | 180/938 [00:11<00:49, 15.29it/s, loss=0.724, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  19%|█▉        | 181/938 [00:11<00:49, 15.30it/s, loss=0.726, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  19%|█▉        | 182/938 [00:11<00:49, 15.30it/s, loss=0.721, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  20%|█▉        | 183/938 [00:11<00:49, 15.31it/s, loss=0.716, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  20%|█▉        | 184/938 [00:12<00:49, 15.31it/s, loss=0.716, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  20%|█▉        | 184/938 [00:12<00:49, 15.31it/s, loss=0.709, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  20%|█▉        | 185/938 [00:12<00:49, 15.29it/s, loss=0.708, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  20%|█▉        | 186/938 [00:12<00:49, 15.29it/s, loss=0.707, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  20%|█▉        | 187/938 [00:12<00:49, 15.27it/s, loss=0.701, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  20%|██        | 188/938 [00:12<00:49, 15.26it/s, loss=0.701, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  20%|██        | 188/938 [00:12<00:49, 15.26it/s, loss=0.702, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  20%|██        | 189/938 [00:12<00:49, 15.28it/s, loss=0.696, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  20%|██        | 190/938 [00:12<00:48, 15.28it/s, loss=0.693, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  20%|██        | 191/938 [00:12<00:48, 15.26it/s, loss=0.682, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  20%|██        | 192/938 [00:12<00:48, 15.25it/s, loss=0.682, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  20%|██        | 192/938 [00:12<00:48, 15.25it/s, loss=0.683, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  21%|██        | 193/938 [00:12<00:48, 15.24it/s, loss=0.679, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  21%|██        | 194/938 [00:12<00:48, 15.24it/s, loss=0.685, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  21%|██        | 195/938 [00:12<00:48, 15.23it/s, loss=0.677, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  21%|██        | 196/938 [00:12<00:48, 15.14it/s, loss=0.677, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  21%|██        | 196/938 [00:12<00:48, 15.14it/s, loss=0.678, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  21%|██        | 197/938 [00:13<00:48, 15.14it/s, loss=0.681, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  21%|██        | 198/938 [00:13<00:48, 15.14it/s, loss=0.671, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  21%|██        | 199/938 [00:13<00:48, 15.13it/s, loss=0.666, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  21%|██▏       | 200/938 [00:13<00:48, 15.13it/s, loss=0.666, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  21%|██▏       | 200/938 [00:13<00:48, 15.13it/s, loss=0.662, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  21%|██▏       | 201/938 [00:13<00:48, 15.14it/s, loss=0.668, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  22%|██▏       | 202/938 [00:13<00:48, 15.13it/s, loss=0.663, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  22%|██▏       | 203/938 [00:13<00:48, 15.12it/s, loss=0.662, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  22%|██▏       | 204/938 [00:13<00:48, 15.12it/s, loss=0.662, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  22%|██▏       | 204/938 [00:13<00:48, 15.12it/s, loss=0.667, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  22%|██▏       | 205/938 [00:13<00:48, 15.10it/s, loss=0.66, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  22%|██▏       | 206/938 [00:13<00:48, 15.10it/s, loss=0.656, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  22%|██▏       | 207/938 [00:13<00:48, 15.09it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  22%|██▏       | 208/938 [00:13<00:48, 15.09it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  22%|██▏       | 208/938 [00:13<00:48, 15.09it/s, loss=0.658, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  22%|██▏       | 209/938 [00:13<00:48, 15.09it/s, loss=0.657, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  22%|██▏       | 210/938 [00:13<00:48, 15.09it/s, loss=0.666, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  22%|██▏       | 211/938 [00:13<00:48, 15.09it/s, loss=0.672, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  23%|██▎       | 212/938 [00:14<00:48, 15.09it/s, loss=0.672, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  23%|██▎       | 212/938 [00:14<00:48, 15.09it/s, loss=0.673, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  23%|██▎       | 213/938 [00:14<00:48, 15.08it/s, loss=0.671, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  23%|██▎       | 214/938 [00:14<00:48, 15.08it/s, loss=0.675, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  23%|██▎       | 215/938 [00:14<00:48, 15.06it/s, loss=0.67, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  23%|██▎       | 216/938 [00:14<00:47, 15.07it/s, loss=0.67, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  23%|██▎       | 216/938 [00:14<00:47, 15.07it/s, loss=0.672, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  23%|██▎       | 217/938 [00:14<00:47, 15.07it/s, loss=0.661, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  23%|██▎       | 218/938 [00:14<00:47, 15.07it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  23%|██▎       | 219/938 [00:14<00:47, 15.06it/s, loss=0.667, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  23%|██▎       | 220/938 [00:14<00:47, 15.07it/s, loss=0.667, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  23%|██▎       | 220/938 [00:14<00:47, 15.06it/s, loss=0.669, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  24%|██▎       | 221/938 [00:14<00:47, 15.06it/s, loss=0.664, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  24%|██▎       | 222/938 [00:14<00:47, 15.05it/s, loss=0.671, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  24%|██▍       | 223/938 [00:14<00:47, 15.05it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  24%|██▍       | 224/938 [00:14<00:47, 15.03it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  24%|██▍       | 224/938 [00:14<00:47, 15.03it/s, loss=0.66, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  24%|██▍       | 225/938 [00:14<00:47, 15.04it/s, loss=0.656, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  24%|██▍       | 226/938 [00:15<00:47, 15.04it/s, loss=0.662, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  24%|██▍       | 227/938 [00:15<00:47, 15.04it/s, loss=0.65, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  24%|██▍       | 228/938 [00:15<00:47, 15.04it/s, loss=0.65, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  24%|██▍       | 228/938 [00:15<00:47, 15.04it/s, loss=0.662, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  24%|██▍       | 229/938 [00:15<00:47, 15.04it/s, loss=0.666, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  25%|██▍       | 230/938 [00:15<00:47, 15.04it/s, loss=0.667, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  25%|██▍       | 231/938 [00:15<00:47, 15.02it/s, loss=0.66, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  25%|██▍       | 232/938 [00:15<00:46, 15.02it/s, loss=0.66, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  25%|██▍       | 232/938 [00:15<00:46, 15.02it/s, loss=0.651, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  25%|██▍       | 233/938 [00:15<00:46, 15.02it/s, loss=0.66, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  25%|██▍       | 234/938 [00:15<00:46, 15.02it/s, loss=0.663, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  25%|██▌       | 235/938 [00:15<00:46, 15.02it/s, loss=0.671, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  25%|██▌       | 236/938 [00:15<00:46, 15.02it/s, loss=0.671, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  25%|██▌       | 236/938 [00:15<00:46, 15.02it/s, loss=0.671, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  25%|██▌       | 237/938 [00:15<00:46, 15.02it/s, loss=0.679, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  25%|██▌       | 238/938 [00:15<00:46, 15.01it/s, loss=0.682, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  25%|██▌       | 239/938 [00:15<00:46, 14.99it/s, loss=0.684, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  26%|██▌       | 240/938 [00:16<00:46, 14.97it/s, loss=0.684, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  26%|██▌       | 240/938 [00:16<00:46, 14.97it/s, loss=0.684, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  26%|██▌       | 241/938 [00:16<00:46, 14.97it/s, loss=0.69, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  26%|██▌       | 242/938 [00:16<00:46, 14.97it/s, loss=0.691, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  26%|██▌       | 243/938 [00:16<00:46, 14.97it/s, loss=0.688, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  26%|██▌       | 244/938 [00:16<00:46, 14.97it/s, loss=0.688, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  26%|██▌       | 244/938 [00:16<00:46, 14.97it/s, loss=0.695, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  26%|██▌       | 245/938 [00:16<00:46, 14.96it/s, loss=0.696, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  26%|██▌       | 246/938 [00:16<00:46, 14.95it/s, loss=0.692, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  26%|██▋       | 247/938 [00:16<00:46, 14.95it/s, loss=0.694, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  26%|██▋       | 248/938 [00:16<00:46, 14.94it/s, loss=0.694, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  26%|██▋       | 248/938 [00:16<00:46, 14.94it/s, loss=0.686, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  27%|██▋       | 249/938 [00:16<00:46, 14.94it/s, loss=0.681, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  27%|██▋       | 250/938 [00:16<00:46, 14.93it/s, loss=0.67, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  27%|██▋       | 251/938 [00:16<00:46, 14.92it/s, loss=0.678, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  27%|██▋       | 252/938 [00:16<00:45, 14.92it/s, loss=0.678, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  27%|██▋       | 252/938 [00:16<00:45, 14.92it/s, loss=0.681, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  27%|██▋       | 253/938 [00:16<00:45, 14.91it/s, loss=0.67, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  27%|██▋       | 254/938 [00:17<00:45, 14.90it/s, loss=0.662, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  27%|██▋       | 255/938 [00:17<00:45, 14.90it/s, loss=0.663, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  27%|██▋       | 256/938 [00:17<00:45, 14.91it/s, loss=0.663, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  27%|██▋       | 256/938 [00:17<00:45, 14.91it/s, loss=0.654, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  27%|██▋       | 257/938 [00:17<00:45, 14.89it/s, loss=0.647, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  28%|██▊       | 258/938 [00:17<00:45, 14.90it/s, loss=0.64, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  28%|██▊       | 259/938 [00:17<00:45, 14.89it/s, loss=0.633, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  28%|██▊       | 260/938 [00:17<00:45, 14.89it/s, loss=0.633, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  28%|██▊       | 260/938 [00:17<00:45, 14.89it/s, loss=0.628, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  28%|██▊       | 261/938 [00:17<00:45, 14.88it/s, loss=0.621, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  28%|██▊       | 262/938 [00:17<00:45, 14.87it/s, loss=0.618, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  28%|██▊       | 263/938 [00:17<00:45, 14.87it/s, loss=0.618, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  28%|██▊       | 264/938 [00:17<00:45, 14.87it/s, loss=0.618, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  28%|██▊       | 264/938 [00:17<00:45, 14.87it/s, loss=0.609, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  28%|██▊       | 265/938 [00:17<00:45, 14.87it/s, loss=0.611, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  28%|██▊       | 266/938 [00:17<00:45, 14.87it/s, loss=0.61, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  28%|██▊       | 267/938 [00:18<00:45, 14.82it/s, loss=0.613, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  29%|██▊       | 268/938 [00:18<00:45, 14.83it/s, loss=0.613, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  29%|██▊       | 268/938 [00:18<00:45, 14.83it/s, loss=0.616, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  29%|██▊       | 269/938 [00:18<00:45, 14.83it/s, loss=0.618, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  29%|██▉       | 270/938 [00:18<00:45, 14.82it/s, loss=0.628, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  29%|██▉       | 271/938 [00:18<00:44, 14.83it/s, loss=0.621, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  29%|██▉       | 272/938 [00:18<00:44, 14.82it/s, loss=0.621, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  29%|██▉       | 272/938 [00:18<00:44, 14.82it/s, loss=0.622, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  29%|██▉       | 273/938 [00:18<00:44, 14.82it/s, loss=0.627, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  29%|██▉       | 274/938 [00:18<00:44, 14.82it/s, loss=0.631, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  29%|██▉       | 275/938 [00:18<00:44, 14.81it/s, loss=0.632, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  29%|██▉       | 276/938 [00:18<00:44, 14.82it/s, loss=0.632, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  29%|██▉       | 276/938 [00:18<00:44, 14.81it/s, loss=0.638, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  30%|██▉       | 277/938 [00:18<00:44, 14.81it/s, loss=0.645, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  30%|██▉       | 278/938 [00:18<00:44, 14.81it/s, loss=0.65, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  30%|██▉       | 279/938 [00:18<00:44, 14.80it/s, loss=0.648, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  30%|██▉       | 280/938 [00:18<00:44, 14.81it/s, loss=0.648, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  30%|██▉       | 280/938 [00:18<00:44, 14.81it/s, loss=0.649, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  30%|██▉       | 281/938 [00:18<00:44, 14.81it/s, loss=0.653, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  30%|███       | 282/938 [00:19<00:44, 14.80it/s, loss=0.659, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  30%|███       | 283/938 [00:19<00:44, 14.80it/s, loss=0.659, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  30%|███       | 284/938 [00:19<00:44, 14.81it/s, loss=0.659, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  30%|███       | 284/938 [00:19<00:44, 14.81it/s, loss=0.663, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  30%|███       | 285/938 [00:19<00:44, 14.80it/s, loss=0.663, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  30%|███       | 286/938 [00:19<00:44, 14.80it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  31%|███       | 287/938 [00:19<00:43, 14.80it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  31%|███       | 288/938 [00:19<00:43, 14.80it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  31%|███       | 288/938 [00:19<00:43, 14.80it/s, loss=0.668, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  31%|███       | 289/938 [00:19<00:43, 14.80it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  31%|███       | 290/938 [00:19<00:43, 14.80it/s, loss=0.666, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  31%|███       | 291/938 [00:19<00:43, 14.80it/s, loss=0.675, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  31%|███       | 292/938 [00:19<00:43, 14.80it/s, loss=0.675, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  31%|███       | 292/938 [00:19<00:43, 14.80it/s, loss=0.68, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  31%|███       | 293/938 [00:19<00:43, 14.79it/s, loss=0.687, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  31%|███▏      | 294/938 [00:19<00:43, 14.78it/s, loss=0.681, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  31%|███▏      | 295/938 [00:19<00:43, 14.77it/s, loss=0.682, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  32%|███▏      | 296/938 [00:20<00:43, 14.77it/s, loss=0.682, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  32%|███▏      | 296/938 [00:20<00:43, 14.77it/s, loss=0.683, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  32%|███▏      | 297/938 [00:20<00:43, 14.77it/s, loss=0.687, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  32%|███▏      | 298/938 [00:20<00:43, 14.75it/s, loss=0.689, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  32%|███▏      | 299/938 [00:20<00:43, 14.77it/s, loss=0.693, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  32%|███▏      | 300/938 [00:20<00:43, 14.77it/s, loss=0.693, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  32%|███▏      | 300/938 [00:20<00:43, 14.77it/s, loss=0.689, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  32%|███▏      | 301/938 [00:20<00:43, 14.77it/s, loss=0.688, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  32%|███▏      | 302/938 [00:20<00:43, 14.77it/s, loss=0.686, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  32%|███▏      | 303/938 [00:20<00:43, 14.76it/s, loss=0.683, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  32%|███▏      | 304/938 [00:20<00:42, 14.76it/s, loss=0.683, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  32%|███▏      | 304/938 [00:20<00:42, 14.76it/s, loss=0.685, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  33%|███▎      | 305/938 [00:20<00:42, 14.75it/s, loss=0.687, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  33%|███▎      | 306/938 [00:20<00:42, 14.75it/s, loss=0.685, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  33%|███▎      | 307/938 [00:20<00:42, 14.75it/s, loss=0.683, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  33%|███▎      | 308/938 [00:20<00:42, 14.75it/s, loss=0.683, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  33%|███▎      | 308/938 [00:20<00:42, 14.75it/s, loss=0.681, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  33%|███▎      | 309/938 [00:20<00:42, 14.75it/s, loss=0.685, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  33%|███▎      | 310/938 [00:21<00:42, 14.75it/s, loss=0.682, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  33%|███▎      | 311/938 [00:21<00:42, 14.75it/s, loss=0.675, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  33%|███▎      | 312/938 [00:21<00:42, 14.76it/s, loss=0.675, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  33%|███▎      | 312/938 [00:21<00:42, 14.76it/s, loss=0.672, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  33%|███▎      | 313/938 [00:21<00:42, 14.76it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  33%|███▎      | 314/938 [00:21<00:42, 14.76it/s, loss=0.669, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  34%|███▎      | 315/938 [00:21<00:42, 14.77it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  34%|███▎      | 316/938 [00:21<00:42, 14.76it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  34%|███▎      | 316/938 [00:21<00:42, 14.76it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  34%|███▍      | 317/938 [00:21<00:42, 14.76it/s, loss=0.655, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  34%|███▍      | 318/938 [00:21<00:42, 14.76it/s, loss=0.656, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  34%|███▍      | 319/938 [00:21<00:41, 14.75it/s, loss=0.651, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  34%|███▍      | 320/938 [00:21<00:41, 14.75it/s, loss=0.651, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  34%|███▍      | 320/938 [00:21<00:41, 14.75it/s, loss=0.653, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  34%|███▍      | 321/938 [00:21<00:41, 14.75it/s, loss=0.654, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  34%|███▍      | 322/938 [00:21<00:41, 14.76it/s, loss=0.647, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  34%|███▍      | 323/938 [00:21<00:41, 14.74it/s, loss=0.65, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  35%|███▍      | 324/938 [00:21<00:41, 14.74it/s, loss=0.65, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  35%|███▍      | 324/938 [00:21<00:41, 14.74it/s, loss=0.648, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  35%|███▍      | 325/938 [00:22<00:41, 14.74it/s, loss=0.642, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  35%|███▍      | 326/938 [00:22<00:41, 14.73it/s, loss=0.645, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  35%|███▍      | 327/938 [00:22<00:41, 14.73it/s, loss=0.646, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  35%|███▍      | 328/938 [00:22<00:41, 14.73it/s, loss=0.646, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  35%|███▍      | 328/938 [00:22<00:41, 14.73it/s, loss=0.651, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  35%|███▌      | 329/938 [00:22<00:41, 14.74it/s, loss=0.652, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  35%|███▌      | 330/938 [00:22<00:41, 14.72it/s, loss=0.646, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  35%|███▌      | 331/938 [00:22<00:41, 14.72it/s, loss=0.642, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  35%|███▌      | 332/938 [00:22<00:41, 14.71it/s, loss=0.642, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  35%|███▌      | 332/938 [00:22<00:41, 14.71it/s, loss=0.642, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  36%|███▌      | 333/938 [00:22<00:41, 14.71it/s, loss=0.648, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  36%|███▌      | 334/938 [00:22<00:41, 14.70it/s, loss=0.65, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  36%|███▌      | 335/938 [00:22<00:41, 14.69it/s, loss=0.655, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  36%|███▌      | 336/938 [00:22<00:40, 14.69it/s, loss=0.655, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  36%|███▌      | 336/938 [00:22<00:40, 14.69it/s, loss=0.656, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  36%|███▌      | 337/938 [00:22<00:40, 14.69it/s, loss=0.661, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  36%|███▌      | 338/938 [00:23<00:40, 14.69it/s, loss=0.657, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  36%|███▌      | 339/938 [00:23<00:40, 14.70it/s, loss=0.663, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  36%|███▌      | 340/938 [00:23<00:40, 14.68it/s, loss=0.663, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  36%|███▌      | 340/938 [00:23<00:40, 14.68it/s, loss=0.668, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  36%|███▋      | 341/938 [00:23<00:40, 14.67it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  36%|███▋      | 342/938 [00:23<00:40, 14.67it/s, loss=0.676, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  37%|███▋      | 343/938 [00:23<00:40, 14.66it/s, loss=0.678, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  37%|███▋      | 344/938 [00:23<00:40, 14.64it/s, loss=0.678, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  37%|███▋      | 344/938 [00:23<00:40, 14.64it/s, loss=0.679, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  37%|███▋      | 345/938 [00:23<00:40, 14.65it/s, loss=0.683, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  37%|███▋      | 346/938 [00:23<00:40, 14.65it/s, loss=0.69, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  37%|███▋      | 347/938 [00:23<00:40, 14.65it/s, loss=0.697, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  37%|███▋      | 348/938 [00:23<00:40, 14.65it/s, loss=0.697, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  37%|███▋      | 348/938 [00:23<00:40, 14.65it/s, loss=0.688, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  37%|███▋      | 349/938 [00:23<00:40, 14.65it/s, loss=0.678, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  37%|███▋      | 350/938 [00:23<00:40, 14.64it/s, loss=0.68, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  37%|███▋      | 351/938 [00:23<00:40, 14.63it/s, loss=0.679, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  38%|███▊      | 352/938 [00:24<00:40, 14.63it/s, loss=0.679, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  38%|███▊      | 352/938 [00:24<00:40, 14.63it/s, loss=0.678, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  38%|███▊      | 353/938 [00:24<00:39, 14.64it/s, loss=0.674, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  38%|███▊      | 354/938 [00:24<00:39, 14.63it/s, loss=0.669, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  38%|███▊      | 355/938 [00:24<00:39, 14.63it/s, loss=0.662, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  38%|███▊      | 356/938 [00:24<00:39, 14.63it/s, loss=0.662, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  38%|███▊      | 356/938 [00:24<00:39, 14.63it/s, loss=0.659, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  38%|███▊      | 357/938 [00:24<00:39, 14.63it/s, loss=0.663, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  38%|███▊      | 358/938 [00:24<00:39, 14.63it/s, loss=0.66, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  38%|███▊      | 359/938 [00:24<00:39, 14.63it/s, loss=0.676, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  38%|███▊      | 360/938 [00:24<00:39, 14.63it/s, loss=0.676, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  38%|███▊      | 360/938 [00:24<00:39, 14.63it/s, loss=0.671, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  38%|███▊      | 361/938 [00:24<00:39, 14.64it/s, loss=0.673, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  39%|███▊      | 362/938 [00:24<00:39, 14.63it/s, loss=0.662, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  39%|███▊      | 363/938 [00:24<00:39, 14.62it/s, loss=0.661, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  39%|███▉      | 364/938 [00:24<00:39, 14.61it/s, loss=0.661, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  39%|███▉      | 364/938 [00:24<00:39, 14.61it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  39%|███▉      | 365/938 [00:25<00:39, 14.59it/s, loss=0.668, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  39%|███▉      | 366/938 [00:25<00:39, 14.60it/s, loss=0.657, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  39%|███▉      | 367/938 [00:25<00:39, 14.59it/s, loss=0.649, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  39%|███▉      | 368/938 [00:25<00:39, 14.59it/s, loss=0.649, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  39%|███▉      | 368/938 [00:25<00:39, 14.59it/s, loss=0.655, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  39%|███▉      | 369/938 [00:25<00:39, 14.58it/s, loss=0.671, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  39%|███▉      | 370/938 [00:25<00:38, 14.58it/s, loss=0.675, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  40%|███▉      | 371/938 [00:25<00:38, 14.59it/s, loss=0.679, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  40%|███▉      | 372/938 [00:25<00:38, 14.59it/s, loss=0.679, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  40%|███▉      | 372/938 [00:25<00:38, 14.59it/s, loss=0.684, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  40%|███▉      | 373/938 [00:25<00:38, 14.59it/s, loss=0.675, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  40%|███▉      | 374/938 [00:25<00:38, 14.58it/s, loss=0.679, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  40%|███▉      | 375/938 [00:25<00:38, 14.57it/s, loss=0.682, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  40%|████      | 376/938 [00:25<00:38, 14.57it/s, loss=0.682, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  40%|████      | 376/938 [00:25<00:38, 14.57it/s, loss=0.684, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  40%|████      | 377/938 [00:25<00:38, 14.57it/s, loss=0.677, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  40%|████      | 378/938 [00:25<00:38, 14.57it/s, loss=0.674, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  40%|████      | 379/938 [00:26<00:38, 14.56it/s, loss=0.661, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  41%|████      | 380/938 [00:26<00:38, 14.56it/s, loss=0.661, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  41%|████      | 380/938 [00:26<00:38, 14.56it/s, loss=0.664, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  41%|████      | 381/938 [00:26<00:38, 14.56it/s, loss=0.66, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  41%|████      | 382/938 [00:26<00:38, 14.56it/s, loss=0.66, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  41%|████      | 383/938 [00:26<00:38, 14.57it/s, loss=0.661, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  41%|████      | 384/938 [00:26<00:38, 14.56it/s, loss=0.661, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  41%|████      | 384/938 [00:26<00:38, 14.56it/s, loss=0.655, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  41%|████      | 385/938 [00:26<00:37, 14.57it/s, loss=0.651, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  41%|████      | 386/938 [00:26<00:37, 14.56it/s, loss=0.659, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  41%|████▏     | 387/938 [00:26<00:37, 14.56it/s, loss=0.661, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  41%|████▏     | 388/938 [00:26<00:37, 14.57it/s, loss=0.661, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  41%|████▏     | 388/938 [00:26<00:37, 14.57it/s, loss=0.658, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  41%|████▏     | 389/938 [00:26<00:37, 14.57it/s, loss=0.651, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  42%|████▏     | 390/938 [00:26<00:37, 14.56it/s, loss=0.648, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  42%|████▏     | 391/938 [00:26<00:37, 14.56it/s, loss=0.65, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  42%|████▏     | 392/938 [00:26<00:37, 14.55it/s, loss=0.65, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  42%|████▏     | 392/938 [00:26<00:37, 14.55it/s, loss=0.646, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  42%|████▏     | 393/938 [00:26<00:37, 14.56it/s, loss=0.654, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  42%|████▏     | 394/938 [00:27<00:37, 14.56it/s, loss=0.656, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  42%|████▏     | 395/938 [00:27<00:37, 14.56it/s, loss=0.651, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  42%|████▏     | 396/938 [00:27<00:37, 14.56it/s, loss=0.651, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  42%|████▏     | 396/938 [00:27<00:37, 14.56it/s, loss=0.657, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  42%|████▏     | 397/938 [00:27<00:37, 14.55it/s, loss=0.661, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  42%|████▏     | 398/938 [00:27<00:37, 14.55it/s, loss=0.663, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  43%|████▎     | 399/938 [00:27<00:37, 14.56it/s, loss=0.659, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  43%|████▎     | 400/938 [00:27<00:36, 14.56it/s, loss=0.659, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  43%|████▎     | 400/938 [00:27<00:36, 14.56it/s, loss=0.658, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  43%|████▎     | 401/938 [00:27<00:36, 14.57it/s, loss=0.661, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  43%|████▎     | 402/938 [00:27<00:36, 14.57it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  43%|████▎     | 403/938 [00:27<00:36, 14.57it/s, loss=0.661, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  43%|████▎     | 404/938 [00:27<00:36, 14.57it/s, loss=0.661, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  43%|████▎     | 404/938 [00:27<00:36, 14.56it/s, loss=0.664, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  43%|████▎     | 405/938 [00:27<00:36, 14.57it/s, loss=0.669, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  43%|████▎     | 406/938 [00:27<00:36, 14.56it/s, loss=0.67, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  43%|████▎     | 407/938 [00:27<00:36, 14.57it/s, loss=0.67, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  43%|████▎     | 408/938 [00:27<00:36, 14.57it/s, loss=0.67, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  43%|████▎     | 408/938 [00:27<00:36, 14.57it/s, loss=0.66, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  44%|████▎     | 409/938 [00:28<00:36, 14.58it/s, loss=0.66, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  44%|████▎     | 410/938 [00:28<00:36, 14.58it/s, loss=0.658, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  44%|████▍     | 411/938 [00:28<00:36, 14.57it/s, loss=0.657, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  44%|████▍     | 412/938 [00:28<00:36, 14.57it/s, loss=0.657, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  44%|████▍     | 412/938 [00:28<00:36, 14.57it/s, loss=0.655, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  44%|████▍     | 413/938 [00:28<00:36, 14.57it/s, loss=0.661, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  44%|████▍     | 414/938 [00:28<00:35, 14.58it/s, loss=0.657, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  44%|████▍     | 415/938 [00:28<00:35, 14.57it/s, loss=0.658, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  44%|████▍     | 416/938 [00:28<00:35, 14.58it/s, loss=0.658, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  44%|████▍     | 416/938 [00:28<00:35, 14.58it/s, loss=0.648, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  44%|████▍     | 417/938 [00:28<00:35, 14.57it/s, loss=0.648, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  45%|████▍     | 418/938 [00:28<00:35, 14.57it/s, loss=0.649, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  45%|████▍     | 419/938 [00:28<00:35, 14.56it/s, loss=0.653, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  45%|████▍     | 420/938 [00:28<00:35, 14.57it/s, loss=0.653, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  45%|████▍     | 420/938 [00:28<00:35, 14.57it/s, loss=0.652, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  45%|████▍     | 421/938 [00:28<00:35, 14.57it/s, loss=0.66, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  45%|████▍     | 422/938 [00:28<00:35, 14.58it/s, loss=0.66, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  45%|████▌     | 423/938 [00:29<00:35, 14.58it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  45%|████▌     | 424/938 [00:29<00:35, 14.58it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  45%|████▌     | 424/938 [00:29<00:35, 14.58it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  45%|████▌     | 425/938 [00:29<00:35, 14.57it/s, loss=0.654, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  45%|████▌     | 426/938 [00:29<00:35, 14.56it/s, loss=0.65, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  46%|████▌     | 427/938 [00:29<00:35, 14.56it/s, loss=0.65, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  46%|████▌     | 428/938 [00:29<00:35, 14.56it/s, loss=0.65, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  46%|████▌     | 428/938 [00:29<00:35, 14.56it/s, loss=0.659, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  46%|████▌     | 429/938 [00:29<00:34, 14.56it/s, loss=0.656, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  46%|████▌     | 430/938 [00:29<00:34, 14.56it/s, loss=0.661, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  46%|████▌     | 431/938 [00:29<00:34, 14.57it/s, loss=0.66, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  46%|████▌     | 432/938 [00:29<00:34, 14.57it/s, loss=0.66, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  46%|████▌     | 432/938 [00:29<00:34, 14.57it/s, loss=0.662, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  46%|████▌     | 433/938 [00:29<00:34, 14.57it/s, loss=0.659, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  46%|████▋     | 434/938 [00:29<00:34, 14.58it/s, loss=0.666, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  46%|████▋     | 435/938 [00:29<00:34, 14.58it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  46%|████▋     | 436/938 [00:29<00:34, 14.55it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  46%|████▋     | 436/938 [00:29<00:34, 14.55it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  47%|████▋     | 437/938 [00:30<00:34, 14.54it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  47%|████▋     | 438/938 [00:30<00:34, 14.54it/s, loss=0.658, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  47%|████▋     | 439/938 [00:30<00:34, 14.55it/s, loss=0.658, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  47%|████▋     | 440/938 [00:30<00:34, 14.55it/s, loss=0.658, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  47%|████▋     | 440/938 [00:30<00:34, 14.55it/s, loss=0.662, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  47%|████▋     | 441/938 [00:30<00:34, 14.55it/s, loss=0.648, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  47%|████▋     | 442/938 [00:30<00:34, 14.54it/s, loss=0.649, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  47%|████▋     | 443/938 [00:30<00:34, 14.54it/s, loss=0.647, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  47%|████▋     | 444/938 [00:30<00:34, 14.53it/s, loss=0.647, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  47%|████▋     | 444/938 [00:30<00:34, 14.53it/s, loss=0.639, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  47%|████▋     | 445/938 [00:30<00:33, 14.53it/s, loss=0.65, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  48%|████▊     | 446/938 [00:30<00:33, 14.54it/s, loss=0.657, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  48%|████▊     | 447/938 [00:30<00:33, 14.53it/s, loss=0.669, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  48%|████▊     | 448/938 [00:30<00:33, 14.53it/s, loss=0.669, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  48%|████▊     | 448/938 [00:30<00:33, 14.53it/s, loss=0.671, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  48%|████▊     | 449/938 [00:30<00:33, 14.54it/s, loss=0.669, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  48%|████▊     | 450/938 [00:30<00:33, 14.54it/s, loss=0.666, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  48%|████▊     | 451/938 [00:31<00:33, 14.52it/s, loss=0.671, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  48%|████▊     | 452/938 [00:31<00:33, 14.53it/s, loss=0.671, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  48%|████▊     | 452/938 [00:31<00:33, 14.53it/s, loss=0.678, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  48%|████▊     | 453/938 [00:31<00:33, 14.52it/s, loss=0.675, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  48%|████▊     | 454/938 [00:31<00:33, 14.52it/s, loss=0.669, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  49%|████▊     | 455/938 [00:31<00:33, 14.52it/s, loss=0.673, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  49%|████▊     | 456/938 [00:31<00:33, 14.52it/s, loss=0.673, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  49%|████▊     | 456/938 [00:31<00:33, 14.52it/s, loss=0.675, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  49%|████▊     | 457/938 [00:31<00:33, 14.52it/s, loss=0.681, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  49%|████▉     | 458/938 [00:31<00:33, 14.52it/s, loss=0.686, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  49%|████▉     | 459/938 [00:31<00:33, 14.51it/s, loss=0.684, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  49%|████▉     | 460/938 [00:31<00:32, 14.50it/s, loss=0.684, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  49%|████▉     | 460/938 [00:31<00:32, 14.50it/s, loss=0.682, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  49%|████▉     | 461/938 [00:31<00:32, 14.50it/s, loss=0.69, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  49%|████▉     | 462/938 [00:31<00:32, 14.49it/s, loss=0.691, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  49%|████▉     | 463/938 [00:31<00:32, 14.49it/s, loss=0.69, v_num=5, val_rmse=0.561, train_rmse=0.743] 
Epoch 2:  49%|████▉     | 464/938 [00:32<00:32, 14.49it/s, loss=0.69, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  49%|████▉     | 464/938 [00:32<00:32, 14.49it/s, loss=0.696, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  50%|████▉     | 465/938 [00:32<00:32, 14.48it/s, loss=0.686, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  50%|████▉     | 466/938 [00:32<00:32, 14.48it/s, loss=0.673, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  50%|████▉     | 467/938 [00:32<00:32, 14.48it/s, loss=0.662, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  50%|████▉     | 468/938 [00:32<00:32, 14.49it/s, loss=0.662, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  50%|████▉     | 468/938 [00:32<00:32, 14.49it/s, loss=0.656, v_num=5, val_rmse=0.561, train_rmse=0.743]
Epoch 2:  50%|█████     | 469/938 [00:32<00:32, 14.51it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]
Epoch 2:  50%|█████     | 472/938 [00:32<00:32, 14.56it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:   1%|          | 3/469 [00:00<00:19, 23.38it/s]

Validating:   1%|▏         | 6/469 [00:00<00:19, 23.53it/s]
Epoch 2:  51%|█████     | 476/938 [00:32<00:31, 14.61it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:   2%|▏         | 9/469 [00:00<00:19, 24.15it/s]
Epoch 2:  51%|█████     | 480/938 [00:32<00:31, 14.66it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:   3%|▎         | 12/469 [00:00<00:18, 25.01it/s]
Epoch 2:  52%|█████▏    | 484/938 [00:32<00:30, 14.71it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:   3%|▎         | 15/469 [00:00<00:19, 23.89it/s]

Validating:   4%|▍         | 18/469 [00:00<00:18, 24.20it/s]
Epoch 2:  52%|█████▏    | 488/938 [00:33<00:30, 14.75it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:   4%|▍         | 21/469 [00:00<00:18, 24.41it/s]
Epoch 2:  52%|█████▏    | 492/938 [00:33<00:30, 14.80it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:   5%|▌         | 24/469 [00:00<00:18, 24.19it/s]
Epoch 2:  53%|█████▎    | 496/938 [00:33<00:29, 14.85it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:   6%|▌         | 27/469 [00:01<00:17, 24.87it/s]

Validating:   6%|▋         | 30/469 [00:01<00:17, 25.43it/s]
Epoch 2:  53%|█████▎    | 500/938 [00:33<00:29, 14.90it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:   7%|▋         | 33/469 [00:01<00:17, 25.47it/s]
Epoch 2:  54%|█████▎    | 504/938 [00:33<00:29, 14.96it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:   8%|▊         | 36/469 [00:01<00:16, 26.25it/s]
Epoch 2:  54%|█████▍    | 508/938 [00:33<00:28, 15.01it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:   8%|▊         | 39/469 [00:01<00:16, 26.01it/s]

Validating:   9%|▉         | 42/469 [00:01<00:17, 25.00it/s]
Epoch 2:  55%|█████▍    | 512/938 [00:34<00:28, 15.05it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  10%|▉         | 45/469 [00:01<00:18, 22.98it/s]
Epoch 2:  55%|█████▌    | 516/938 [00:34<00:27, 15.08it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  10%|█         | 48/469 [00:01<00:17, 23.94it/s]
Epoch 2:  55%|█████▌    | 520/938 [00:34<00:27, 15.14it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  11%|█         | 51/469 [00:02<00:16, 24.95it/s]

Validating:  12%|█▏        | 54/469 [00:02<00:16, 24.67it/s]
Epoch 2:  56%|█████▌    | 524/938 [00:34<00:27, 15.18it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  12%|█▏        | 57/469 [00:02<00:16, 24.25it/s]
Epoch 2:  56%|█████▋    | 528/938 [00:34<00:26, 15.22it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  13%|█▎        | 60/469 [00:02<00:16, 24.76it/s]
Epoch 2:  57%|█████▋    | 532/938 [00:34<00:26, 15.27it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  13%|█▎        | 63/469 [00:02<00:16, 25.27it/s]

Validating:  14%|█▍        | 66/469 [00:02<00:16, 24.02it/s]
Epoch 2:  57%|█████▋    | 536/938 [00:35<00:26, 15.31it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  15%|█▍        | 69/469 [00:02<00:16, 24.98it/s]
Epoch 2:  58%|█████▊    | 540/938 [00:35<00:25, 15.35it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  15%|█▌        | 72/469 [00:02<00:15, 25.17it/s]
Epoch 2:  58%|█████▊    | 544/938 [00:35<00:25, 15.40it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  16%|█▌        | 75/469 [00:03<00:15, 25.41it/s]

Validating:  17%|█▋        | 78/469 [00:03<00:15, 24.66it/s]
Epoch 2:  58%|█████▊    | 548/938 [00:35<00:25, 15.44it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  17%|█▋        | 81/469 [00:03<00:16, 24.18it/s]
Epoch 2:  59%|█████▉    | 552/938 [00:35<00:24, 15.48it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  18%|█▊        | 84/469 [00:03<00:15, 24.28it/s]
Epoch 2:  59%|█████▉    | 556/938 [00:35<00:24, 15.53it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  19%|█▊        | 87/469 [00:03<00:15, 24.62it/s]

Validating:  19%|█▉        | 90/469 [00:03<00:15, 24.02it/s]
Epoch 2:  60%|█████▉    | 560/938 [00:35<00:24, 15.56it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  20%|█▉        | 93/469 [00:03<00:15, 24.47it/s]
Epoch 2:  60%|██████    | 564/938 [00:36<00:23, 15.60it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  20%|██        | 96/469 [00:03<00:15, 24.87it/s]
Epoch 2:  61%|██████    | 568/938 [00:36<00:23, 15.64it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  21%|██        | 99/469 [00:04<00:15, 24.22it/s]

Validating:  22%|██▏       | 102/469 [00:04<00:15, 24.35it/s]
Epoch 2:  61%|██████    | 572/938 [00:36<00:23, 15.68it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  22%|██▏       | 105/469 [00:04<00:15, 24.03it/s]
Epoch 2:  61%|██████▏   | 576/938 [00:36<00:23, 15.72it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  23%|██▎       | 108/469 [00:04<00:14, 24.61it/s]
Epoch 2:  62%|██████▏   | 580/938 [00:36<00:22, 15.76it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  24%|██▎       | 111/469 [00:04<00:14, 25.43it/s]

Validating:  24%|██▍       | 114/469 [00:04<00:15, 22.35it/s]
Epoch 2:  62%|██████▏   | 584/938 [00:36<00:22, 15.78it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  25%|██▍       | 117/469 [00:04<00:15, 22.97it/s]
Epoch 2:  63%|██████▎   | 588/938 [00:37<00:22, 15.82it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  26%|██▌       | 120/469 [00:04<00:14, 23.44it/s]
Epoch 2:  63%|██████▎   | 592/938 [00:37<00:21, 15.86it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  26%|██▌       | 123/469 [00:05<00:14, 23.85it/s]

Validating:  27%|██▋       | 126/469 [00:05<00:14, 24.15it/s]
Epoch 2:  64%|██████▎   | 596/938 [00:37<00:21, 15.90it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  28%|██▊       | 129/469 [00:05<00:13, 24.61it/s]
Epoch 2:  64%|██████▍   | 600/938 [00:37<00:21, 15.94it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  28%|██▊       | 132/469 [00:05<00:13, 24.86it/s]
Epoch 2:  64%|██████▍   | 604/938 [00:37<00:20, 15.98it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  29%|██▉       | 135/469 [00:05<00:13, 25.57it/s]

Validating:  29%|██▉       | 138/469 [00:05<00:13, 23.94it/s]
Epoch 2:  65%|██████▍   | 608/938 [00:37<00:20, 16.01it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  30%|███       | 141/469 [00:05<00:13, 24.59it/s]
Epoch 2:  65%|██████▌   | 612/938 [00:38<00:20, 16.05it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  31%|███       | 144/469 [00:05<00:13, 24.48it/s]
Epoch 2:  66%|██████▌   | 616/938 [00:38<00:20, 16.09it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  31%|███▏      | 147/469 [00:05<00:12, 25.02it/s]

Validating:  32%|███▏      | 150/469 [00:06<00:12, 25.43it/s]
Epoch 2:  66%|██████▌   | 620/938 [00:38<00:19, 16.13it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  33%|███▎      | 153/469 [00:06<00:12, 25.10it/s]
Epoch 2:  67%|██████▋   | 624/938 [00:38<00:19, 16.16it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  33%|███▎      | 156/469 [00:06<00:12, 25.05it/s]
Epoch 2:  67%|██████▋   | 628/938 [00:38<00:19, 16.20it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  34%|███▍      | 159/469 [00:06<00:12, 25.19it/s]

Validating:  35%|███▍      | 162/469 [00:06<00:12, 25.55it/s]
Epoch 2:  67%|██████▋   | 632/938 [00:38<00:18, 16.24it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  35%|███▌      | 165/469 [00:06<00:12, 24.83it/s]
Epoch 2:  68%|██████▊   | 636/938 [00:39<00:18, 16.27it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  36%|███▌      | 168/469 [00:06<00:12, 23.29it/s]
Epoch 2:  68%|██████▊   | 640/938 [00:39<00:18, 16.30it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  36%|███▋      | 171/469 [00:06<00:12, 23.91it/s]

Validating:  37%|███▋      | 174/469 [00:07<00:11, 24.61it/s]
Epoch 2:  69%|██████▊   | 644/938 [00:39<00:17, 16.34it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  38%|███▊      | 177/469 [00:07<00:11, 24.81it/s]
Epoch 2:  69%|██████▉   | 648/938 [00:39<00:17, 16.37it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  38%|███▊      | 180/469 [00:07<00:12, 24.02it/s]
Epoch 2:  70%|██████▉   | 652/938 [00:39<00:17, 16.39it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  39%|███▉      | 183/469 [00:07<00:12, 23.48it/s]

Validating:  40%|███▉      | 186/469 [00:07<00:11, 24.17it/s]
Epoch 2:  70%|██████▉   | 656/938 [00:39<00:17, 16.43it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  40%|████      | 189/469 [00:07<00:11, 24.31it/s]
Epoch 2:  70%|███████   | 660/938 [00:40<00:16, 16.47it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  41%|████      | 192/469 [00:07<00:10, 25.54it/s]
Epoch 2:  71%|███████   | 664/938 [00:40<00:16, 16.50it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  42%|████▏     | 195/469 [00:07<00:10, 25.75it/s]

Validating:  42%|████▏     | 198/469 [00:08<00:10, 25.26it/s]
Epoch 2:  71%|███████   | 668/938 [00:40<00:16, 16.54it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  43%|████▎     | 201/469 [00:08<00:10, 26.03it/s]
Epoch 2:  72%|███████▏  | 672/938 [00:40<00:16, 16.58it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  43%|████▎     | 204/469 [00:08<00:10, 24.94it/s]
Epoch 2:  72%|███████▏  | 676/938 [00:40<00:15, 16.60it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  44%|████▍     | 207/469 [00:08<00:10, 24.62it/s]

Validating:  45%|████▍     | 210/469 [00:08<00:10, 25.69it/s]
Epoch 2:  72%|███████▏  | 680/938 [00:40<00:15, 16.64it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  45%|████▌     | 213/469 [00:08<00:10, 25.35it/s]
Epoch 2:  73%|███████▎  | 684/938 [00:41<00:15, 16.68it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  46%|████▌     | 216/469 [00:08<00:09, 25.41it/s]
Epoch 2:  73%|███████▎  | 688/938 [00:41<00:14, 16.71it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  47%|████▋     | 219/469 [00:08<00:09, 25.70it/s]

Validating:  47%|████▋     | 222/469 [00:09<00:10, 24.16it/s]
Epoch 2:  74%|███████▍  | 692/938 [00:41<00:14, 16.73it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  48%|████▊     | 225/469 [00:09<00:10, 22.71it/s]
Epoch 2:  74%|███████▍  | 696/938 [00:41<00:14, 16.76it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  49%|████▊     | 228/469 [00:09<00:10, 23.57it/s]
Epoch 2:  75%|███████▍  | 700/938 [00:41<00:14, 16.79it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  49%|████▉     | 231/469 [00:09<00:09, 24.25it/s]

Validating:  50%|████▉     | 234/469 [00:09<00:09, 23.55it/s]
Epoch 2:  75%|███████▌  | 704/938 [00:41<00:13, 16.81it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  51%|█████     | 237/469 [00:09<00:09, 24.26it/s]
Epoch 2:  75%|███████▌  | 708/938 [00:42<00:13, 16.84it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  51%|█████     | 240/469 [00:09<00:09, 24.36it/s]
Epoch 2:  76%|███████▌  | 712/938 [00:42<00:13, 16.87it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  52%|█████▏    | 243/469 [00:09<00:09, 23.93it/s]

Validating:  52%|█████▏    | 246/469 [00:10<00:09, 24.55it/s]
Epoch 2:  76%|███████▋  | 716/938 [00:42<00:13, 16.91it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  53%|█████▎    | 249/469 [00:10<00:08, 24.81it/s]
Epoch 2:  77%|███████▋  | 720/938 [00:42<00:12, 16.94it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  54%|█████▎    | 252/469 [00:10<00:08, 25.31it/s]
Epoch 2:  77%|███████▋  | 724/938 [00:42<00:12, 16.97it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  54%|█████▍    | 255/469 [00:10<00:08, 25.08it/s]

Validating:  55%|█████▌    | 258/469 [00:10<00:08, 25.04it/s]
Epoch 2:  78%|███████▊  | 728/938 [00:42<00:12, 17.00it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  56%|█████▌    | 261/469 [00:10<00:08, 23.96it/s]
Epoch 2:  78%|███████▊  | 732/938 [00:42<00:12, 17.02it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  56%|█████▋    | 264/469 [00:10<00:08, 24.59it/s]
Epoch 2:  78%|███████▊  | 736/938 [00:43<00:11, 17.05it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  57%|█████▋    | 267/469 [00:10<00:08, 24.14it/s]

Validating:  58%|█████▊    | 270/469 [00:11<00:08, 23.56it/s]
Epoch 2:  79%|███████▉  | 740/938 [00:43<00:11, 17.07it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  58%|█████▊    | 273/469 [00:11<00:08, 24.03it/s]
Epoch 2:  79%|███████▉  | 744/938 [00:43<00:11, 17.11it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  59%|█████▉    | 276/469 [00:11<00:07, 25.20it/s]
Epoch 2:  80%|███████▉  | 748/938 [00:43<00:11, 17.14it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  59%|█████▉    | 279/469 [00:11<00:07, 25.38it/s]

Validating:  60%|██████    | 282/469 [00:11<00:07, 25.27it/s]
Epoch 2:  80%|████████  | 752/938 [00:43<00:10, 17.17it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  61%|██████    | 285/469 [00:11<00:07, 25.05it/s]
Epoch 2:  81%|████████  | 756/938 [00:43<00:10, 17.20it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  61%|██████▏   | 288/469 [00:11<00:07, 25.07it/s]
Epoch 2:  81%|████████  | 760/938 [00:44<00:10, 17.22it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  62%|██████▏   | 291/469 [00:11<00:07, 24.70it/s]

Validating:  63%|██████▎   | 294/469 [00:11<00:06, 25.23it/s]
Epoch 2:  81%|████████▏ | 764/938 [00:44<00:10, 17.25it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  63%|██████▎   | 297/469 [00:12<00:06, 25.57it/s]
Epoch 2:  82%|████████▏ | 768/938 [00:44<00:09, 17.28it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  64%|██████▍   | 300/469 [00:12<00:06, 24.65it/s]
Epoch 2:  82%|████████▏ | 772/938 [00:44<00:09, 17.30it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  65%|██████▍   | 303/469 [00:12<00:07, 22.77it/s]

Validating:  65%|██████▌   | 306/469 [00:12<00:06, 23.30it/s]
Epoch 2:  83%|████████▎ | 776/938 [00:44<00:09, 17.32it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  66%|██████▌   | 309/469 [00:12<00:06, 23.72it/s]
Epoch 2:  83%|████████▎ | 780/938 [00:44<00:09, 17.35it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  67%|██████▋   | 312/469 [00:12<00:06, 24.39it/s]
Epoch 2:  84%|████████▎ | 784/938 [00:45<00:08, 17.37it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  67%|██████▋   | 315/469 [00:12<00:06, 24.15it/s]

Validating:  68%|██████▊   | 318/469 [00:12<00:06, 24.11it/s]
Epoch 2:  84%|████████▍ | 788/938 [00:45<00:08, 17.40it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  68%|██████▊   | 321/469 [00:13<00:06, 24.37it/s]
Epoch 2:  84%|████████▍ | 792/938 [00:45<00:08, 17.42it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  69%|██████▉   | 324/469 [00:13<00:05, 24.37it/s]
Epoch 2:  85%|████████▍ | 796/938 [00:45<00:08, 17.45it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  70%|██████▉   | 327/469 [00:13<00:05, 24.72it/s]

Validating:  70%|███████   | 330/469 [00:13<00:05, 25.32it/s]
Epoch 2:  85%|████████▌ | 800/938 [00:45<00:07, 17.48it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  71%|███████   | 333/469 [00:13<00:05, 25.52it/s]
Epoch 2:  86%|████████▌ | 804/938 [00:45<00:07, 17.51it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  72%|███████▏  | 336/469 [00:13<00:05, 25.18it/s]
Epoch 2:  86%|████████▌ | 808/938 [00:46<00:07, 17.54it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  72%|███████▏  | 340/469 [00:13<00:04, 26.96it/s]
Epoch 2:  87%|████████▋ | 812/938 [00:46<00:07, 17.58it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  73%|███████▎  | 343/469 [00:13<00:04, 27.10it/s]

Validating:  74%|███████▍  | 346/469 [00:14<00:04, 25.91it/s]
Epoch 2:  87%|████████▋ | 816/938 [00:46<00:06, 17.60it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  74%|███████▍  | 349/469 [00:14<00:04, 26.29it/s]
Epoch 2:  87%|████████▋ | 820/938 [00:46<00:06, 17.63it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  75%|███████▌  | 352/469 [00:14<00:04, 25.85it/s]
Epoch 2:  88%|████████▊ | 824/938 [00:46<00:06, 17.65it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  76%|███████▌  | 355/469 [00:14<00:04, 25.24it/s]

Validating:  76%|███████▋  | 358/469 [00:14<00:04, 25.20it/s]
Epoch 2:  88%|████████▊ | 828/938 [00:46<00:06, 17.67it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  77%|███████▋  | 361/469 [00:14<00:04, 25.58it/s]
Epoch 2:  89%|████████▊ | 832/938 [00:47<00:05, 17.70it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  78%|███████▊  | 364/469 [00:14<00:04, 26.16it/s]
Epoch 2:  89%|████████▉ | 836/938 [00:47<00:05, 17.73it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  78%|███████▊  | 367/469 [00:14<00:04, 25.01it/s]

Validating:  79%|███████▉  | 370/469 [00:15<00:04, 24.45it/s]
Epoch 2:  90%|████████▉ | 840/938 [00:47<00:05, 17.75it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  80%|███████▉  | 373/469 [00:15<00:03, 25.06it/s]
Epoch 2:  90%|████████▉ | 844/938 [00:47<00:05, 17.77it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  80%|████████  | 376/469 [00:15<00:03, 25.07it/s]
Epoch 2:  90%|█████████ | 848/938 [00:47<00:05, 17.80it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  81%|████████  | 379/469 [00:15<00:03, 24.84it/s]

Validating:  81%|████████▏ | 382/469 [00:15<00:03, 24.76it/s]
Epoch 2:  91%|█████████ | 852/938 [00:47<00:04, 17.82it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  82%|████████▏ | 385/469 [00:15<00:03, 24.65it/s]
Epoch 2:  91%|█████████▏| 856/938 [00:47<00:04, 17.85it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  83%|████████▎ | 388/469 [00:15<00:03, 25.18it/s]
Epoch 2:  92%|█████████▏| 860/938 [00:48<00:04, 17.87it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  83%|████████▎ | 391/469 [00:15<00:03, 25.04it/s]

Validating:  84%|████████▍ | 394/469 [00:15<00:03, 24.94it/s]
Epoch 2:  92%|█████████▏| 864/938 [00:48<00:04, 17.89it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  85%|████████▍ | 397/469 [00:16<00:02, 24.65it/s]
Epoch 2:  93%|█████████▎| 868/938 [00:48<00:03, 17.92it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  85%|████████▌ | 400/469 [00:16<00:02, 25.26it/s]
Epoch 2:  93%|█████████▎| 872/938 [00:48<00:03, 17.94it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  86%|████████▌ | 403/469 [00:16<00:02, 25.65it/s]

Validating:  87%|████████▋ | 406/469 [00:16<00:02, 25.95it/s]
Epoch 2:  93%|█████████▎| 876/938 [00:48<00:03, 17.97it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  87%|████████▋ | 409/469 [00:16<00:02, 26.59it/s]
Epoch 2:  94%|█████████▍| 880/938 [00:48<00:03, 18.00it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  88%|████████▊ | 412/469 [00:16<00:02, 26.55it/s]
Epoch 2:  94%|█████████▍| 884/938 [00:49<00:02, 18.02it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  88%|████████▊ | 415/469 [00:16<00:02, 25.40it/s]

Validating:  89%|████████▉ | 418/469 [00:16<00:02, 23.96it/s]
Epoch 2:  95%|█████████▍| 888/938 [00:49<00:02, 18.03it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  90%|████████▉ | 421/469 [00:17<00:02, 22.81it/s]
Epoch 2:  95%|█████████▌| 892/938 [00:49<00:02, 18.04it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  90%|█████████ | 424/469 [00:17<00:02, 21.95it/s]
Epoch 2:  96%|█████████▌| 896/938 [00:49<00:02, 18.06it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  91%|█████████ | 427/469 [00:17<00:01, 23.08it/s]

Validating:  92%|█████████▏| 430/469 [00:17<00:01, 23.60it/s]
Epoch 2:  96%|█████████▌| 900/938 [00:49<00:02, 18.08it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  92%|█████████▏| 433/469 [00:17<00:01, 24.20it/s]
Epoch 2:  96%|█████████▋| 904/938 [00:49<00:01, 18.11it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  93%|█████████▎| 436/469 [00:17<00:01, 24.28it/s]
Epoch 2:  97%|█████████▋| 908/938 [00:50<00:01, 18.13it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  94%|█████████▎| 439/469 [00:17<00:01, 23.92it/s]

Validating:  94%|█████████▍| 442/469 [00:17<00:01, 24.87it/s]
Epoch 2:  97%|█████████▋| 912/938 [00:50<00:01, 18.15it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  95%|█████████▍| 445/469 [00:18<00:00, 24.06it/s]
Epoch 2:  98%|█████████▊| 916/938 [00:50<00:01, 18.17it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  96%|█████████▌| 448/469 [00:18<00:00, 24.85it/s]
Epoch 2:  98%|█████████▊| 920/938 [00:50<00:00, 18.19it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  96%|█████████▌| 451/469 [00:18<00:00, 25.00it/s]

Validating:  97%|█████████▋| 454/469 [00:18<00:00, 24.92it/s]
Epoch 2:  99%|█████████▊| 924/938 [00:50<00:00, 18.21it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  97%|█████████▋| 457/469 [00:18<00:00, 24.62it/s]
Epoch 2:  99%|█████████▉| 928/938 [00:50<00:00, 18.23it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  98%|█████████▊| 460/469 [00:18<00:00, 25.06it/s]
Epoch 2:  99%|█████████▉| 932/938 [00:51<00:00, 18.25it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating:  99%|█████████▊| 463/469 [00:18<00:00, 24.73it/s]

Validating:  99%|█████████▉| 466/469 [00:18<00:00, 24.64it/s]
Epoch 2: 100%|█████████▉| 936/938 [00:51<00:00, 18.27it/s, loss=0.665, v_num=5, val_rmse=0.561, train_rmse=0.743]

Validating: 100%|██████████| 469/469 [00:18<00:00, 25.95it/s]
Epoch 2: 100%|██████████| 938/938 [00:51<00:00, 18.27it/s, loss=0.665, v_num=5, val_rmse=0.531, train_rmse=0.743]

                                                             
Epoch 2: 100%|██████████| 938/938 [00:51<00:00, 18.26it/s, loss=0.665, v_num=5, val_rmse=0.531, train_rmse=0.673]
Epoch 2: 100%|██████████| 938/938 [00:51<00:00, 18.23it/s, loss=0.665, v_num=5, val_rmse=0.531, train_rmse=0.673]LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]


Testing: 0it [00:00, ?it/s]
Testing:   0%|          | 2/469 [00:00<00:23, 19.76it/s]
Testing:   1%|          | 5/469 [00:00<00:19, 23.35it/s]
Testing:   2%|▏         | 8/469 [00:00<00:18, 24.44it/s]
Testing:   2%|▏         | 11/469 [00:00<00:18, 24.37it/s]
Testing:   3%|▎         | 14/469 [00:00<00:18, 25.26it/s]
Testing:   4%|▎         | 17/469 [00:00<00:19, 23.60it/s]
Testing:   4%|▍         | 20/469 [00:00<00:18, 24.60it/s]
Testing:   5%|▍         | 23/469 [00:00<00:18, 24.43it/s]
Testing:   6%|▌         | 26/469 [00:01<00:17, 24.89it/s]
Testing:   6%|▌         | 29/469 [00:01<00:17, 24.93it/s]
Testing:   7%|▋         | 32/469 [00:01<00:17, 24.54it/s]
Testing:   7%|▋         | 35/469 [00:01<00:16, 25.74it/s]
Testing:   8%|▊         | 38/469 [00:01<00:16, 25.64it/s]
Testing:   9%|▊         | 41/469 [00:01<00:16, 26.24it/s]
Testing:   9%|▉         | 44/469 [00:01<00:16, 26.11it/s]
Testing:  10%|█         | 47/469 [00:01<00:16, 25.23it/s]
Testing:  11%|█         | 50/469 [00:02<00:16, 25.14it/s]
Testing:  11%|█▏        | 53/469 [00:02<00:16, 24.88it/s]
Testing:  12%|█▏        | 56/469 [00:02<00:17, 23.06it/s]
Testing:  13%|█▎        | 59/469 [00:02<00:17, 23.17it/s]
Testing:  13%|█▎        | 62/469 [00:02<00:16, 24.38it/s]
Testing:  14%|█▍        | 65/469 [00:02<00:16, 24.58it/s]
Testing:  14%|█▍        | 68/469 [00:02<00:15, 25.30it/s]
Testing:  15%|█▌        | 71/469 [00:02<00:15, 26.01it/s]
Testing:  16%|█▌        | 74/469 [00:02<00:15, 26.12it/s]
Testing:  16%|█▋        | 77/469 [00:03<00:14, 26.20it/s]
Testing:  17%|█▋        | 80/469 [00:03<00:14, 26.41it/s]
Testing:  18%|█▊        | 83/469 [00:03<00:14, 26.90it/s]
Testing:  18%|█▊        | 86/469 [00:03<00:15, 24.96it/s]
Testing:  19%|█▉        | 89/469 [00:03<00:15, 24.65it/s]
Testing:  20%|█▉        | 92/469 [00:03<00:15, 24.75it/s]
Testing:  20%|██        | 95/469 [00:03<00:14, 25.11it/s]
Testing:  21%|██        | 98/469 [00:03<00:14, 25.10it/s]
Testing:  22%|██▏       | 101/469 [00:04<00:14, 25.01it/s]
Testing:  22%|██▏       | 104/469 [00:04<00:15, 24.32it/s]
Testing:  23%|██▎       | 107/469 [00:04<00:14, 24.74it/s]
Testing:  23%|██▎       | 110/469 [00:04<00:14, 25.07it/s]
Testing:  24%|██▍       | 113/469 [00:04<00:14, 23.82it/s]
Testing:  25%|██▍       | 116/469 [00:04<00:14, 23.59it/s]
Testing:  25%|██▌       | 119/469 [00:04<00:14, 23.68it/s]
Testing:  26%|██▌       | 122/469 [00:04<00:14, 23.95it/s]
Testing:  27%|██▋       | 125/469 [00:05<00:13, 24.75it/s]
Testing:  27%|██▋       | 128/469 [00:05<00:13, 25.53it/s]
Testing:  28%|██▊       | 131/469 [00:05<00:13, 25.72it/s]
Testing:  29%|██▊       | 134/469 [00:05<00:13, 25.23it/s]
Testing:  29%|██▉       | 137/469 [00:05<00:12, 25.80it/s]
Testing:  30%|██▉       | 140/469 [00:05<00:12, 25.96it/s]
Testing:  30%|███       | 143/469 [00:05<00:12, 26.24it/s]
Testing:  31%|███       | 146/469 [00:05<00:12, 26.44it/s]
Testing:  32%|███▏      | 149/469 [00:05<00:12, 26.16it/s]
Testing:  32%|███▏      | 152/469 [00:06<00:11, 26.61it/s]
Testing:  33%|███▎      | 155/469 [00:06<00:11, 26.96it/s]
Testing:  34%|███▎      | 158/469 [00:06<00:11, 27.06it/s]
Testing:  34%|███▍      | 161/469 [00:06<00:12, 25.66it/s]
Testing:  35%|███▍      | 164/469 [00:06<00:11, 26.64it/s]
Testing:  36%|███▌      | 167/469 [00:06<00:11, 25.64it/s]
Testing:  36%|███▌      | 170/469 [00:06<00:11, 25.67it/s]
Testing:  37%|███▋      | 173/469 [00:06<00:11, 25.65it/s]
Testing:  38%|███▊      | 176/469 [00:06<00:11, 25.55it/s]
Testing:  38%|███▊      | 179/469 [00:07<00:11, 25.25it/s]
Testing:  39%|███▉      | 182/469 [00:07<00:11, 25.50it/s]
Testing:  39%|███▉      | 185/469 [00:07<00:10, 26.32it/s]
Testing:  40%|████      | 188/469 [00:07<00:10, 26.86it/s]
Testing:  41%|████      | 191/469 [00:07<00:10, 26.37it/s]
Testing:  41%|████▏     | 194/469 [00:07<00:10, 26.94it/s]
Testing:  42%|████▏     | 197/469 [00:07<00:10, 26.71it/s]
Testing:  43%|████▎     | 200/469 [00:07<00:09, 26.99it/s]
Testing:  43%|████▎     | 203/469 [00:08<00:10, 24.36it/s]
Testing:  44%|████▍     | 206/469 [00:08<00:10, 24.28it/s]
Testing:  45%|████▍     | 209/469 [00:08<00:10, 23.85it/s]
Testing:  45%|████▌     | 212/469 [00:08<00:10, 24.27it/s]
Testing:  46%|████▌     | 215/469 [00:08<00:10, 25.23it/s]
Testing:  46%|████▋     | 218/469 [00:08<00:09, 25.79it/s]
Testing:  47%|████▋     | 221/469 [00:08<00:09, 25.83it/s]
Testing:  48%|████▊     | 224/469 [00:08<00:10, 24.22it/s]
Testing:  48%|████▊     | 227/469 [00:08<00:09, 25.38it/s]
Testing:  49%|████▉     | 230/469 [00:09<00:09, 24.93it/s]
Testing:  50%|████▉     | 233/469 [00:09<00:09, 25.62it/s]
Testing:  50%|█████     | 236/469 [00:09<00:09, 25.66it/s]
Testing:  51%|█████     | 239/469 [00:09<00:09, 25.06it/s]
Testing:  52%|█████▏    | 242/469 [00:09<00:09, 24.62it/s]
Testing:  52%|█████▏    | 245/469 [00:09<00:08, 24.92it/s]
Testing:  53%|█████▎    | 248/469 [00:09<00:08, 24.75it/s]
Testing:  54%|█████▎    | 251/469 [00:09<00:08, 24.98it/s]
Testing:  54%|█████▍    | 254/469 [00:10<00:08, 24.83it/s]
Testing:  55%|█████▍    | 257/469 [00:10<00:08, 23.74it/s]
Testing:  55%|█████▌    | 260/469 [00:10<00:09, 22.35it/s]
Testing:  56%|█████▌    | 263/469 [00:10<00:08, 23.21it/s]
Testing:  57%|█████▋    | 266/469 [00:10<00:08, 23.68it/s]
Testing:  57%|█████▋    | 269/469 [00:10<00:08, 23.77it/s]
Testing:  58%|█████▊    | 272/469 [00:10<00:08, 24.18it/s]
Testing:  59%|█████▊    | 275/469 [00:10<00:07, 25.44it/s]
Testing:  59%|█████▉    | 278/469 [00:11<00:07, 25.62it/s]
Testing:  60%|█████▉    | 281/469 [00:11<00:07, 24.93it/s]
Testing:  61%|██████    | 284/469 [00:11<00:07, 25.37it/s]
Testing:  61%|██████    | 287/469 [00:11<00:07, 25.11it/s]
Testing:  62%|██████▏   | 290/469 [00:11<00:07, 25.07it/s]
Testing:  62%|██████▏   | 293/469 [00:11<00:07, 24.58it/s]
Testing:  63%|██████▎   | 296/469 [00:11<00:06, 25.52it/s]
Testing:  64%|██████▍   | 299/469 [00:11<00:06, 25.72it/s]
Testing:  64%|██████▍   | 302/469 [00:12<00:06, 26.54it/s]
Testing:  65%|██████▌   | 305/469 [00:12<00:06, 25.97it/s]
Testing:  66%|██████▌   | 308/469 [00:12<00:06, 25.32it/s]
Testing:  66%|██████▋   | 311/469 [00:12<00:06, 25.55it/s]
Testing:  67%|██████▋   | 314/469 [00:12<00:06, 25.20it/s]
Testing:  68%|██████▊   | 317/469 [00:12<00:06, 25.05it/s]
Testing:  68%|██████▊   | 320/469 [00:12<00:05, 25.27it/s]
Testing:  69%|██████▉   | 323/469 [00:12<00:05, 24.49it/s]
Testing:  70%|██████▉   | 326/469 [00:12<00:05, 24.80it/s]
Testing:  70%|███████   | 329/469 [00:13<00:05, 24.29it/s]
Testing:  71%|███████   | 332/469 [00:13<00:05, 24.87it/s]
Testing:  71%|███████▏  | 335/469 [00:13<00:05, 24.99it/s]
Testing:  72%|███████▏  | 338/469 [00:13<00:05, 24.48it/s]
Testing:  73%|███████▎  | 341/469 [00:13<00:05, 24.91it/s]
Testing:  73%|███████▎  | 344/469 [00:13<00:04, 25.63it/s]
Testing:  74%|███████▍  | 347/469 [00:13<00:04, 25.20it/s]
Testing:  75%|███████▍  | 350/469 [00:13<00:04, 24.79it/s]
Testing:  75%|███████▌  | 353/469 [00:14<00:04, 25.28it/s]
Testing:  76%|███████▌  | 356/469 [00:14<00:04, 25.23it/s]
Testing:  77%|███████▋  | 359/469 [00:14<00:04, 24.86it/s]
Testing:  77%|███████▋  | 362/469 [00:14<00:04, 24.93it/s]
Testing:  78%|███████▊  | 365/469 [00:14<00:04, 25.41it/s]
Testing:  78%|███████▊  | 368/469 [00:14<00:03, 25.41it/s]
Testing:  79%|███████▉  | 371/469 [00:14<00:03, 25.38it/s]
Testing:  80%|███████▉  | 374/469 [00:14<00:03, 25.05it/s]
Testing:  80%|████████  | 377/469 [00:15<00:03, 24.46it/s]
Testing:  81%|████████  | 380/469 [00:15<00:03, 24.40it/s]
Testing:  82%|████████▏ | 383/469 [00:15<00:03, 24.80it/s]
Testing:  82%|████████▏ | 386/469 [00:15<00:03, 25.09it/s]
Testing:  83%|████████▎ | 389/469 [00:15<00:03, 24.91it/s]
Testing:  84%|████████▎ | 392/469 [00:15<00:03, 25.06it/s]
Testing:  84%|████████▍ | 395/469 [00:15<00:02, 25.38it/s]
Testing:  85%|████████▍ | 398/469 [00:15<00:02, 25.25it/s]
Testing:  86%|████████▌ | 401/469 [00:15<00:02, 25.49it/s]
Testing:  86%|████████▌ | 404/469 [00:16<00:02, 26.31it/s]
Testing:  87%|████████▋ | 407/469 [00:16<00:02, 25.49it/s]
Testing:  87%|████████▋ | 410/469 [00:16<00:02, 26.38it/s]
Testing:  88%|████████▊ | 413/469 [00:16<00:02, 26.09it/s]
Testing:  89%|████████▊ | 416/469 [00:16<00:02, 25.97it/s]
Testing:  89%|████████▉ | 419/469 [00:16<00:01, 26.32it/s]
Testing:  90%|████████▉ | 422/469 [00:16<00:01, 25.63it/s]
Testing:  91%|█████████ | 425/469 [00:16<00:01, 25.79it/s]
Testing:  91%|█████████▏| 428/469 [00:17<00:01, 25.46it/s]
Testing:  92%|█████████▏| 431/469 [00:17<00:01, 26.02it/s]
Testing:  93%|█████████▎| 434/469 [00:17<00:01, 26.47it/s]
Testing:  93%|█████████▎| 437/469 [00:17<00:01, 27.03it/s]
Testing:  94%|█████████▍| 440/469 [00:17<00:01, 26.43it/s]
Testing:  94%|█████████▍| 443/469 [00:17<00:01, 25.25it/s]
Testing:  95%|█████████▌| 446/469 [00:17<00:00, 24.98it/s]
Testing:  96%|█████████▌| 449/469 [00:17<00:00, 24.92it/s]
Testing:  96%|█████████▋| 452/469 [00:17<00:00, 24.20it/s]
Testing:  97%|█████████▋| 455/469 [00:18<00:00, 23.50it/s]
Testing:  98%|█████████▊| 458/469 [00:18<00:00, 24.09it/s]
Testing:  98%|█████████▊| 461/469 [00:18<00:00, 23.47it/s]
Testing:  99%|█████████▉| 464/469 [00:18<00:00, 24.62it/s]
Testing: 100%|█████████▉| 467/469 [00:18<00:00, 25.50it/s]--------------------------------------------------------------------------------
DATALOADER:0 TEST RESULTS
{'test_rmse': 0.5313125848770142}
--------------------------------------------------------------------------------

Testing: 100%|██████████| 469/469 [00:18<00:00, 25.17it/s]
  0%|          | 0/469 [02:50<?, ?it/s]
Global seed set to 43

['p_np'] False
2 1
iupac_vocab_size: 1491
training... 1491

  0%|          | 0/469 [00:00<?, ?it/s]Some weights of the model checkpoint at checkpoints/iupac were not used when initializing GPT2ForSequenceClassification: ['lm_head.weight']
- This IS expected if you are initializing GPT2ForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing GPT2ForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
GPU available: True, used: True
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]

  | Name        | Type                          | Params
--------------------------------------------------------------
0 | transformer | GPT2ForSequenceClassification | 7.1 M 
--------------------------------------------------------------
75.9 K    Trainable params
7.0 M     Non-trainable params
7.1 M     Total params
28.416    Total estimated model params size (MB)

Validation sanity check: 0it [00:00, ?it/s]
Validation sanity check:   0%|          | 0/2 [00:00<?, ?it/s]
Validation sanity check: 100%|██████████| 2/2 [00:00<00:00, 19.33it/s]
                                                                      Global seed set to 43


Training: 0it [00:00, ?it/s]
Training:   0%|          | 0/938 [00:00<?, ?it/s]
Epoch 0:   0%|          | 0/938 [00:00<?, ?it/s] 
Epoch 0:   0%|          | 1/938 [00:00<01:27, 10.67it/s, loss=3.34, v_num=8]
Epoch 0:   0%|          | 2/938 [00:00<01:19, 11.79it/s, loss=3.34, v_num=8]
Epoch 0:   0%|          | 2/938 [00:00<01:19, 11.76it/s, loss=3.4, v_num=8] 
Epoch 0:   0%|          | 3/938 [00:00<01:10, 13.18it/s, loss=3.45, v_num=8]
Epoch 0:   0%|          | 4/938 [00:00<01:08, 13.59it/s, loss=3.45, v_num=8]
Epoch 0:   0%|          | 4/938 [00:00<01:08, 13.57it/s, loss=3.5, v_num=8] 
Epoch 0:   1%|          | 5/938 [00:00<01:07, 13.92it/s, loss=3.48, v_num=8]
Epoch 0:   1%|          | 6/938 [00:00<01:06, 14.07it/s, loss=3.48, v_num=8]
Epoch 0:   1%|          | 6/938 [00:00<01:06, 14.06it/s, loss=3.48, v_num=8]
Epoch 0:   1%|          | 7/938 [00:00<01:04, 14.40it/s, loss=3.46, v_num=8]
Epoch 0:   1%|          | 8/938 [00:00<01:04, 14.38it/s, loss=3.46, v_num=8]
Epoch 0:   1%|          | 8/938 [00:00<01:04, 14.37it/s, loss=3.48, v_num=8]
Epoch 0:   1%|          | 9/938 [00:00<01:05, 14.20it/s, loss=3.5, v_num=8] 
Epoch 0:   1%|          | 10/938 [00:00<01:06, 14.02it/s, loss=3.5, v_num=8]
Epoch 0:   1%|          | 10/938 [00:00<01:06, 14.01it/s, loss=3.51, v_num=8]
Epoch 0:   1%|          | 11/938 [00:00<01:06, 13.88it/s, loss=3.49, v_num=8]
Epoch 0:   1%|▏         | 12/938 [00:00<01:06, 13.98it/s, loss=3.49, v_num=8]
Epoch 0:   1%|▏         | 12/938 [00:00<01:06, 13.97it/s, loss=3.49, v_num=8]
Epoch 0:   1%|▏         | 13/938 [00:00<01:05, 14.20it/s, loss=3.5, v_num=8] 
Epoch 0:   1%|▏         | 14/938 [00:00<01:04, 14.39it/s, loss=3.5, v_num=8]
Epoch 0:   1%|▏         | 14/938 [00:00<01:04, 14.38it/s, loss=3.47, v_num=8]
Epoch 0:   2%|▏         | 15/938 [00:01<01:03, 14.56it/s, loss=3.47, v_num=8]
Epoch 0:   2%|▏         | 16/938 [00:01<01:03, 14.56it/s, loss=3.47, v_num=8]
Epoch 0:   2%|▏         | 16/938 [00:01<01:03, 14.56it/s, loss=3.46, v_num=8]
Epoch 0:   2%|▏         | 17/938 [00:01<01:03, 14.53it/s, loss=3.46, v_num=8]
Epoch 0:   2%|▏         | 18/938 [00:01<01:03, 14.57it/s, loss=3.46, v_num=8]
Epoch 0:   2%|▏         | 18/938 [00:01<01:03, 14.56it/s, loss=3.42, v_num=8]
Epoch 0:   2%|▏         | 19/938 [00:01<01:02, 14.59it/s, loss=3.39, v_num=8]
Epoch 0:   2%|▏         | 20/938 [00:01<01:02, 14.70it/s, loss=3.39, v_num=8]
Epoch 0:   2%|▏         | 20/938 [00:01<01:02, 14.70it/s, loss=3.35, v_num=8]
Epoch 0:   2%|▏         | 21/938 [00:01<01:02, 14.72it/s, loss=3.34, v_num=8]
Epoch 0:   2%|▏         | 22/938 [00:01<01:02, 14.72it/s, loss=3.34, v_num=8]
Epoch 0:   2%|▏         | 22/938 [00:01<01:02, 14.72it/s, loss=3.3, v_num=8] 
Epoch 0:   2%|▏         | 23/938 [00:01<01:02, 14.74it/s, loss=3.26, v_num=8]
Epoch 0:   3%|▎         | 24/938 [00:01<01:02, 14.58it/s, loss=3.26, v_num=8]
Epoch 0:   3%|▎         | 24/938 [00:01<01:02, 14.58it/s, loss=3.22, v_num=8]
Epoch 0:   3%|▎         | 25/938 [00:01<01:02, 14.52it/s, loss=3.17, v_num=8]
Epoch 0:   3%|▎         | 26/938 [00:01<01:02, 14.68it/s, loss=3.17, v_num=8]
Epoch 0:   3%|▎         | 26/938 [00:01<01:02, 14.68it/s, loss=3.12, v_num=8]
Epoch 0:   3%|▎         | 27/938 [00:01<01:02, 14.55it/s, loss=3.08, v_num=8]
Epoch 0:   3%|▎         | 28/938 [00:01<01:02, 14.55it/s, loss=3.08, v_num=8]
Epoch 0:   3%|▎         | 28/938 [00:01<01:02, 14.55it/s, loss=3, v_num=8]   
Epoch 0:   3%|▎         | 29/938 [00:01<01:02, 14.57it/s, loss=2.93, v_num=8]
Epoch 0:   3%|▎         | 30/938 [00:02<01:02, 14.58it/s, loss=2.93, v_num=8]
Epoch 0:   3%|▎         | 30/938 [00:02<01:02, 14.58it/s, loss=2.87, v_num=8]
Epoch 0:   3%|▎         | 31/938 [00:02<01:01, 14.63it/s, loss=2.81, v_num=8]
Epoch 0:   3%|▎         | 32/938 [00:02<01:02, 14.59it/s, loss=2.81, v_num=8]
Epoch 0:   3%|▎         | 32/938 [00:02<01:02, 14.59it/s, loss=2.75, v_num=8]
Epoch 0:   4%|▎         | 33/938 [00:02<01:02, 14.44it/s, loss=2.67, v_num=8]
Epoch 0:   4%|▎         | 34/938 [00:02<01:02, 14.38it/s, loss=2.67, v_num=8]
Epoch 0:   4%|▎         | 34/938 [00:02<01:02, 14.38it/s, loss=2.6, v_num=8] 
Epoch 0:   4%|▎         | 35/938 [00:02<01:02, 14.44it/s, loss=2.51, v_num=8]
Epoch 0:   4%|▍         | 36/938 [00:02<01:02, 14.38it/s, loss=2.51, v_num=8]
Epoch 0:   4%|▍         | 36/938 [00:02<01:02, 14.38it/s, loss=2.43, v_num=8]
Epoch 0:   4%|▍         | 37/938 [00:02<01:02, 14.32it/s, loss=2.35, v_num=8]
Epoch 0:   4%|▍         | 38/938 [00:02<01:02, 14.32it/s, loss=2.35, v_num=8]
Epoch 0:   4%|▍         | 38/938 [00:02<01:02, 14.32it/s, loss=2.29, v_num=8]
Epoch 0:   4%|▍         | 39/938 [00:02<01:02, 14.32it/s, loss=2.23, v_num=8]
Epoch 0:   4%|▍         | 40/938 [00:02<01:02, 14.32it/s, loss=2.23, v_num=8]
Epoch 0:   4%|▍         | 40/938 [00:02<01:02, 14.32it/s, loss=2.18, v_num=8]
Epoch 0:   4%|▍         | 41/938 [00:02<01:02, 14.36it/s, loss=2.1, v_num=8] 
Epoch 0:   4%|▍         | 42/938 [00:02<01:02, 14.30it/s, loss=2.1, v_num=8]
Epoch 0:   4%|▍         | 42/938 [00:02<01:02, 14.29it/s, loss=2.06, v_num=8]
Epoch 0:   5%|▍         | 43/938 [00:02<01:02, 14.35it/s, loss=2, v_num=8]   
Epoch 0:   5%|▍         | 44/938 [00:03<01:02, 14.35it/s, loss=2, v_num=8]
Epoch 0:   5%|▍         | 44/938 [00:03<01:02, 14.34it/s, loss=1.96, v_num=8]
Epoch 0:   5%|▍         | 45/938 [00:03<01:01, 14.42it/s, loss=1.92, v_num=8]
Epoch 0:   5%|▍         | 46/938 [00:03<01:01, 14.41it/s, loss=1.92, v_num=8]
Epoch 0:   5%|▍         | 46/938 [00:03<01:01, 14.41it/s, loss=1.88, v_num=8]
Epoch 0:   5%|▌         | 47/938 [00:03<01:01, 14.40it/s, loss=1.86, v_num=8]
Epoch 0:   5%|▌         | 48/938 [00:03<01:01, 14.45it/s, loss=1.86, v_num=8]
Epoch 0:   5%|▌         | 48/938 [00:03<01:01, 14.45it/s, loss=1.84, v_num=8]
Epoch 0:   5%|▌         | 49/938 [00:03<01:01, 14.42it/s, loss=1.81, v_num=8]
Epoch 0:   5%|▌         | 50/938 [00:03<01:01, 14.40it/s, loss=1.81, v_num=8]
Epoch 0:   5%|▌         | 50/938 [00:03<01:01, 14.40it/s, loss=1.77, v_num=8]
Epoch 0:   5%|▌         | 51/938 [00:03<01:01, 14.43it/s, loss=1.74, v_num=8]
Epoch 0:   6%|▌         | 52/938 [00:03<01:01, 14.43it/s, loss=1.74, v_num=8]
Epoch 0:   6%|▌         | 52/938 [00:03<01:01, 14.42it/s, loss=1.71, v_num=8]
Epoch 0:   6%|▌         | 53/938 [00:03<01:01, 14.35it/s, loss=1.71, v_num=8]
Epoch 0:   6%|▌         | 54/938 [00:03<01:01, 14.38it/s, loss=1.71, v_num=8]
Epoch 0:   6%|▌         | 54/938 [00:03<01:01, 14.38it/s, loss=1.7, v_num=8] 
Epoch 0:   6%|▌         | 55/938 [00:03<01:01, 14.34it/s, loss=1.7, v_num=8]
Epoch 0:   6%|▌         | 56/938 [00:03<01:01, 14.34it/s, loss=1.7, v_num=8]
Epoch 0:   6%|▌         | 56/938 [00:03<01:01, 14.34it/s, loss=1.69, v_num=8]
Epoch 0:   6%|▌         | 57/938 [00:03<01:01, 14.29it/s, loss=1.69, v_num=8]
Epoch 0:   6%|▌         | 58/938 [00:04<01:01, 14.27it/s, loss=1.69, v_num=8]
Epoch 0:   6%|▌         | 58/938 [00:04<01:01, 14.27it/s, loss=1.71, v_num=8]
Epoch 0:   6%|▋         | 59/938 [00:04<01:01, 14.29it/s, loss=1.71, v_num=8]
Epoch 0:   6%|▋         | 60/938 [00:04<01:01, 14.30it/s, loss=1.71, v_num=8]
Epoch 0:   6%|▋         | 60/938 [00:04<01:01, 14.30it/s, loss=1.71, v_num=8]
Epoch 0:   7%|▋         | 61/938 [00:04<01:01, 14.33it/s, loss=1.72, v_num=8]
Epoch 0:   7%|▋         | 62/938 [00:04<01:01, 14.34it/s, loss=1.72, v_num=8]
Epoch 0:   7%|▋         | 62/938 [00:04<01:01, 14.34it/s, loss=1.72, v_num=8]
Epoch 0:   7%|▋         | 63/938 [00:04<01:01, 14.32it/s, loss=1.72, v_num=8]
Epoch 0:   7%|▋         | 64/938 [00:04<01:01, 14.26it/s, loss=1.72, v_num=8]
Epoch 0:   7%|▋         | 64/938 [00:04<01:01, 14.26it/s, loss=1.7, v_num=8] 
Epoch 0:   7%|▋         | 65/938 [00:04<01:01, 14.26it/s, loss=1.69, v_num=8]
Epoch 0:   7%|▋         | 66/938 [00:04<01:01, 14.22it/s, loss=1.69, v_num=8]
Epoch 0:   7%|▋         | 66/938 [00:04<01:01, 14.21it/s, loss=1.69, v_num=8]
Epoch 0:   7%|▋         | 67/938 [00:04<01:01, 14.18it/s, loss=1.68, v_num=8]
Epoch 0:   7%|▋         | 68/938 [00:04<01:01, 14.21it/s, loss=1.68, v_num=8]
Epoch 0:   7%|▋         | 68/938 [00:04<01:01, 14.21it/s, loss=1.68, v_num=8]
Epoch 0:   7%|▋         | 69/938 [00:04<01:01, 14.20it/s, loss=1.69, v_num=8]
Epoch 0:   7%|▋         | 70/938 [00:04<01:01, 14.20it/s, loss=1.69, v_num=8]
Epoch 0:   7%|▋         | 70/938 [00:04<01:01, 14.20it/s, loss=1.69, v_num=8]
Epoch 0:   8%|▊         | 71/938 [00:05<01:01, 14.17it/s, loss=1.7, v_num=8] 
Epoch 0:   8%|▊         | 72/938 [00:05<01:01, 14.16it/s, loss=1.7, v_num=8]
Epoch 0:   8%|▊         | 72/938 [00:05<01:01, 14.16it/s, loss=1.72, v_num=8]
Epoch 0:   8%|▊         | 73/938 [00:05<01:01, 14.13it/s, loss=1.71, v_num=8]
Epoch 0:   8%|▊         | 74/938 [00:05<01:01, 14.16it/s, loss=1.71, v_num=8]
Epoch 0:   8%|▊         | 74/938 [00:05<01:01, 14.16it/s, loss=1.72, v_num=8]
Epoch 0:   8%|▊         | 75/938 [00:05<01:01, 14.14it/s, loss=1.71, v_num=8]
Epoch 0:   8%|▊         | 76/938 [00:05<01:00, 14.14it/s, loss=1.71, v_num=8]
Epoch 0:   8%|▊         | 76/938 [00:05<01:00, 14.14it/s, loss=1.75, v_num=8]
Epoch 0:   8%|▊         | 77/938 [00:05<01:00, 14.14it/s, loss=1.75, v_num=8]
Epoch 0:   8%|▊         | 78/938 [00:05<01:01, 14.08it/s, loss=1.75, v_num=8]
Epoch 0:   8%|▊         | 78/938 [00:05<01:01, 14.08it/s, loss=1.74, v_num=8]
Epoch 0:   8%|▊         | 79/938 [00:05<01:00, 14.12it/s, loss=1.74, v_num=8]
Epoch 0:   9%|▊         | 80/938 [00:05<01:00, 14.11it/s, loss=1.74, v_num=8]
Epoch 0:   9%|▊         | 80/938 [00:05<01:00, 14.11it/s, loss=1.73, v_num=8]
Epoch 0:   9%|▊         | 81/938 [00:05<01:00, 14.12it/s, loss=1.72, v_num=8]
Epoch 0:   9%|▊         | 82/938 [00:05<01:00, 14.17it/s, loss=1.72, v_num=8]
Epoch 0:   9%|▊         | 82/938 [00:05<01:00, 14.17it/s, loss=1.71, v_num=8]
Epoch 0:   9%|▉         | 83/938 [00:05<01:00, 14.13it/s, loss=1.72, v_num=8]
Epoch 0:   9%|▉         | 84/938 [00:05<01:00, 14.10it/s, loss=1.72, v_num=8]
Epoch 0:   9%|▉         | 84/938 [00:05<01:00, 14.10it/s, loss=1.73, v_num=8]
Epoch 0:   9%|▉         | 85/938 [00:06<01:00, 14.14it/s, loss=1.72, v_num=8]
Epoch 0:   9%|▉         | 86/938 [00:06<01:00, 14.17it/s, loss=1.72, v_num=8]
Epoch 0:   9%|▉         | 86/938 [00:06<01:00, 14.17it/s, loss=1.72, v_num=8]
Epoch 0:   9%|▉         | 87/938 [00:06<01:00, 14.16it/s, loss=1.72, v_num=8]
Epoch 0:   9%|▉         | 88/938 [00:06<00:59, 14.17it/s, loss=1.72, v_num=8]
Epoch 0:   9%|▉         | 88/938 [00:06<00:59, 14.17it/s, loss=1.71, v_num=8]
Epoch 0:   9%|▉         | 89/938 [00:06<00:59, 14.17it/s, loss=1.72, v_num=8]
Epoch 0:  10%|▉         | 90/938 [00:06<00:59, 14.18it/s, loss=1.72, v_num=8]
Epoch 0:  10%|▉         | 90/938 [00:06<00:59, 14.18it/s, loss=1.72, v_num=8]
Epoch 0:  10%|▉         | 91/938 [00:06<00:59, 14.16it/s, loss=1.71, v_num=8]
Epoch 0:  10%|▉         | 92/938 [00:06<00:59, 14.17it/s, loss=1.71, v_num=8]
Epoch 0:  10%|▉         | 92/938 [00:06<00:59, 14.16it/s, loss=1.7, v_num=8] 
Epoch 0:  10%|▉         | 93/938 [00:06<00:59, 14.18it/s, loss=1.71, v_num=8]
Epoch 0:  10%|█         | 94/938 [00:06<00:59, 14.18it/s, loss=1.71, v_num=8]
Epoch 0:  10%|█         | 94/938 [00:06<00:59, 14.18it/s, loss=1.73, v_num=8]
Epoch 0:  10%|█         | 95/938 [00:06<00:59, 14.22it/s, loss=1.73, v_num=8]
Epoch 0:  10%|█         | 96/938 [00:06<00:59, 14.20it/s, loss=1.73, v_num=8]
Epoch 0:  10%|█         | 96/938 [00:06<00:59, 14.20it/s, loss=1.69, v_num=8]
Epoch 0:  10%|█         | 97/938 [00:06<00:59, 14.22it/s, loss=1.68, v_num=8]
Epoch 0:  10%|█         | 98/938 [00:06<00:58, 14.25it/s, loss=1.68, v_num=8]
Epoch 0:  10%|█         | 98/938 [00:06<00:58, 14.25it/s, loss=1.67, v_num=8]
Epoch 0:  11%|█         | 99/938 [00:06<00:58, 14.26it/s, loss=1.65, v_num=8]
Epoch 0:  11%|█         | 100/938 [00:07<00:58, 14.28it/s, loss=1.65, v_num=8]
Epoch 0:  11%|█         | 100/938 [00:07<00:58, 14.28it/s, loss=1.66, v_num=8]
Epoch 0:  11%|█         | 101/938 [00:07<00:58, 14.28it/s, loss=1.68, v_num=8]
Epoch 0:  11%|█         | 102/938 [00:07<00:58, 14.29it/s, loss=1.68, v_num=8]
Epoch 0:  11%|█         | 102/938 [00:07<00:58, 14.29it/s, loss=1.68, v_num=8]
Epoch 0:  11%|█         | 103/938 [00:07<00:58, 14.26it/s, loss=1.68, v_num=8]
Epoch 0:  11%|█         | 104/938 [00:07<00:58, 14.25it/s, loss=1.68, v_num=8]
Epoch 0:  11%|█         | 104/938 [00:07<00:58, 14.25it/s, loss=1.69, v_num=8]
Epoch 0:  11%|█         | 105/938 [00:07<00:58, 14.20it/s, loss=1.7, v_num=8] 
Epoch 0:  11%|█▏        | 106/938 [00:07<00:58, 14.21it/s, loss=1.7, v_num=8]
Epoch 0:  11%|█▏        | 106/938 [00:07<00:58, 14.21it/s, loss=1.71, v_num=8]
Epoch 0:  11%|█▏        | 107/938 [00:07<00:58, 14.21it/s, loss=1.69, v_num=8]
Epoch 0:  12%|█▏        | 108/938 [00:07<00:58, 14.21it/s, loss=1.69, v_num=8]
Epoch 0:  12%|█▏        | 108/938 [00:07<00:58, 14.21it/s, loss=1.71, v_num=8]
Epoch 0:  12%|█▏        | 109/938 [00:07<00:58, 14.18it/s, loss=1.71, v_num=8]
Epoch 0:  12%|█▏        | 110/938 [00:07<00:58, 14.21it/s, loss=1.71, v_num=8]
Epoch 0:  12%|█▏        | 110/938 [00:07<00:58, 14.21it/s, loss=1.69, v_num=8]
Epoch 0:  12%|█▏        | 111/938 [00:07<00:58, 14.20it/s, loss=1.68, v_num=8]
Epoch 0:  12%|█▏        | 112/938 [00:07<00:58, 14.18it/s, loss=1.68, v_num=8]
Epoch 0:  12%|█▏        | 112/938 [00:07<00:58, 14.18it/s, loss=1.69, v_num=8]
Epoch 0:  12%|█▏        | 113/938 [00:07<00:58, 14.20it/s, loss=1.69, v_num=8]
Epoch 0:  12%|█▏        | 114/938 [00:08<00:58, 14.20it/s, loss=1.69, v_num=8]
Epoch 0:  12%|█▏        | 114/938 [00:08<00:58, 14.20it/s, loss=1.67, v_num=8]
Epoch 0:  12%|█▏        | 115/938 [00:08<00:57, 14.21it/s, loss=1.65, v_num=8]
Epoch 0:  12%|█▏        | 116/938 [00:08<00:57, 14.21it/s, loss=1.65, v_num=8]
Epoch 0:  12%|█▏        | 116/938 [00:08<00:57, 14.21it/s, loss=1.66, v_num=8]
Epoch 0:  12%|█▏        | 117/938 [00:08<00:57, 14.19it/s, loss=1.66, v_num=8]
Epoch 0:  13%|█▎        | 118/938 [00:08<00:57, 14.21it/s, loss=1.66, v_num=8]
Epoch 0:  13%|█▎        | 118/938 [00:08<00:57, 14.21it/s, loss=1.67, v_num=8]
Epoch 0:  13%|█▎        | 119/938 [00:08<00:57, 14.19it/s, loss=1.67, v_num=8]
Epoch 0:  13%|█▎        | 120/938 [00:08<00:57, 14.22it/s, loss=1.67, v_num=8]
Epoch 0:  13%|█▎        | 120/938 [00:08<00:57, 14.22it/s, loss=1.69, v_num=8]
Epoch 0:  13%|█▎        | 121/938 [00:08<00:57, 14.21it/s, loss=1.69, v_num=8]
Epoch 0:  13%|█▎        | 122/938 [00:08<00:57, 14.21it/s, loss=1.69, v_num=8]
Epoch 0:  13%|█▎        | 122/938 [00:08<00:57, 14.21it/s, loss=1.67, v_num=8]
Epoch 0:  13%|█▎        | 123/938 [00:08<00:57, 14.20it/s, loss=1.68, v_num=8]
Epoch 0:  13%|█▎        | 124/938 [00:08<00:57, 14.19it/s, loss=1.68, v_num=8]
Epoch 0:  13%|█▎        | 124/938 [00:08<00:57, 14.19it/s, loss=1.67, v_num=8]
Epoch 0:  13%|█▎        | 125/938 [00:08<00:57, 14.19it/s, loss=1.67, v_num=8]
Epoch 0:  13%|█▎        | 126/938 [00:08<00:57, 14.18it/s, loss=1.67, v_num=8]
Epoch 0:  13%|█▎        | 126/938 [00:08<00:57, 14.18it/s, loss=1.67, v_num=8]
Epoch 0:  14%|█▎        | 127/938 [00:08<00:57, 14.19it/s, loss=1.65, v_num=8]
Epoch 0:  14%|█▎        | 128/938 [00:09<00:57, 14.19it/s, loss=1.65, v_num=8]
Epoch 0:  14%|█▎        | 128/938 [00:09<00:57, 14.19it/s, loss=1.65, v_num=8]
Epoch 0:  14%|█▍        | 129/938 [00:09<00:56, 14.21it/s, loss=1.63, v_num=8]
Epoch 0:  14%|█▍        | 130/938 [00:09<00:56, 14.21it/s, loss=1.63, v_num=8]
Epoch 0:  14%|█▍        | 130/938 [00:09<00:56, 14.21it/s, loss=1.65, v_num=8]
Epoch 0:  14%|█▍        | 131/938 [00:09<00:56, 14.22it/s, loss=1.66, v_num=8]
Epoch 0:  14%|█▍        | 132/938 [00:09<00:56, 14.21it/s, loss=1.66, v_num=8]
Epoch 0:  14%|█▍        | 132/938 [00:09<00:56, 14.21it/s, loss=1.64, v_num=8]
Epoch 0:  14%|█▍        | 133/938 [00:09<00:56, 14.21it/s, loss=1.62, v_num=8]
Epoch 0:  14%|█▍        | 134/938 [00:09<00:56, 14.22it/s, loss=1.62, v_num=8]
Epoch 0:  14%|█▍        | 134/938 [00:09<00:56, 14.22it/s, loss=1.59, v_num=8]
Epoch 0:  14%|█▍        | 135/938 [00:09<00:56, 14.24it/s, loss=1.58, v_num=8]
Epoch 0:  14%|█▍        | 136/938 [00:09<00:56, 14.25it/s, loss=1.58, v_num=8]
Epoch 0:  14%|█▍        | 136/938 [00:09<00:56, 14.25it/s, loss=1.58, v_num=8]
Epoch 0:  15%|█▍        | 137/938 [00:09<00:56, 14.25it/s, loss=1.54, v_num=8]
Epoch 0:  15%|█▍        | 138/938 [00:09<00:56, 14.26it/s, loss=1.54, v_num=8]
Epoch 0:  15%|█▍        | 138/938 [00:09<00:56, 14.26it/s, loss=1.55, v_num=8]
Epoch 0:  15%|█▍        | 139/938 [00:09<00:55, 14.29it/s, loss=1.53, v_num=8]
Epoch 0:  15%|█▍        | 140/938 [00:09<00:55, 14.29it/s, loss=1.53, v_num=8]
Epoch 0:  15%|█▍        | 140/938 [00:09<00:55, 14.29it/s, loss=1.5, v_num=8] 
Epoch 0:  15%|█▌        | 141/938 [00:09<00:55, 14.31it/s, loss=1.46, v_num=8]
Epoch 0:  15%|█▌        | 142/938 [00:09<00:55, 14.31it/s, loss=1.46, v_num=8]
Epoch 0:  15%|█▌        | 142/938 [00:09<00:55, 14.31it/s, loss=1.45, v_num=8]
Epoch 0:  15%|█▌        | 143/938 [00:09<00:55, 14.31it/s, loss=1.42, v_num=8]
Epoch 0:  15%|█▌        | 144/938 [00:10<00:55, 14.33it/s, loss=1.42, v_num=8]
Epoch 0:  15%|█▌        | 144/938 [00:10<00:55, 14.32it/s, loss=1.39, v_num=8]
Epoch 0:  15%|█▌        | 145/938 [00:10<00:55, 14.34it/s, loss=1.37, v_num=8]
Epoch 0:  16%|█▌        | 146/938 [00:10<00:55, 14.34it/s, loss=1.37, v_num=8]
Epoch 0:  16%|█▌        | 146/938 [00:10<00:55, 14.34it/s, loss=1.35, v_num=8]
Epoch 0:  16%|█▌        | 147/938 [00:10<00:55, 14.33it/s, loss=1.34, v_num=8]
Epoch 0:  16%|█▌        | 148/938 [00:10<00:55, 14.35it/s, loss=1.34, v_num=8]
Epoch 0:  16%|█▌        | 148/938 [00:10<00:55, 14.35it/s, loss=1.29, v_num=8]
Epoch 0:  16%|█▌        | 149/938 [00:10<00:54, 14.35it/s, loss=1.27, v_num=8]
Epoch 0:  16%|█▌        | 150/938 [00:10<00:54, 14.37it/s, loss=1.27, v_num=8]
Epoch 0:  16%|█▌        | 150/938 [00:10<00:54, 14.37it/s, loss=1.24, v_num=8]
Epoch 0:  16%|█▌        | 151/938 [00:10<00:54, 14.37it/s, loss=1.22, v_num=8]
Epoch 0:  16%|█▌        | 152/938 [00:10<00:54, 14.37it/s, loss=1.22, v_num=8]
Epoch 0:  16%|█▌        | 152/938 [00:10<00:54, 14.37it/s, loss=1.21, v_num=8]
Epoch 0:  16%|█▋        | 153/938 [00:10<00:54, 14.37it/s, loss=1.2, v_num=8] 
Epoch 0:  16%|█▋        | 154/938 [00:10<00:54, 14.37it/s, loss=1.2, v_num=8]
Epoch 0:  16%|█▋        | 154/938 [00:10<00:54, 14.37it/s, loss=1.2, v_num=8]
Epoch 0:  17%|█▋        | 155/938 [00:10<00:54, 14.35it/s, loss=1.21, v_num=8]
Epoch 0:  17%|█▋        | 156/938 [00:10<00:54, 14.36it/s, loss=1.21, v_num=8]
Epoch 0:  17%|█▋        | 156/938 [00:10<00:54, 14.36it/s, loss=1.19, v_num=8]
Epoch 0:  17%|█▋        | 157/938 [00:10<00:54, 14.36it/s, loss=1.19, v_num=8]
Epoch 0:  17%|█▋        | 158/938 [00:11<00:54, 14.36it/s, loss=1.19, v_num=8]
Epoch 0:  17%|█▋        | 158/938 [00:11<00:54, 14.36it/s, loss=1.16, v_num=8]
Epoch 0:  17%|█▋        | 159/938 [00:11<00:54, 14.35it/s, loss=1.16, v_num=8]
Epoch 0:  17%|█▋        | 160/938 [00:11<00:54, 14.36it/s, loss=1.16, v_num=8]
Epoch 0:  17%|█▋        | 160/938 [00:11<00:54, 14.36it/s, loss=1.15, v_num=8]
Epoch 0:  17%|█▋        | 161/938 [00:11<00:54, 14.37it/s, loss=1.16, v_num=8]
Epoch 0:  17%|█▋        | 162/938 [00:11<00:53, 14.38it/s, loss=1.16, v_num=8]
Epoch 0:  17%|█▋        | 162/938 [00:11<00:53, 14.38it/s, loss=1.14, v_num=8]
Epoch 0:  17%|█▋        | 163/938 [00:11<00:53, 14.38it/s, loss=1.13, v_num=8]
Epoch 0:  17%|█▋        | 164/938 [00:11<00:53, 14.39it/s, loss=1.13, v_num=8]
Epoch 0:  17%|█▋        | 164/938 [00:11<00:53, 14.39it/s, loss=1.13, v_num=8]
Epoch 0:  18%|█▊        | 165/938 [00:11<00:53, 14.39it/s, loss=1.12, v_num=8]
Epoch 0:  18%|█▊        | 166/938 [00:11<00:53, 14.40it/s, loss=1.12, v_num=8]
Epoch 0:  18%|█▊        | 166/938 [00:11<00:53, 14.39it/s, loss=1.12, v_num=8]
Epoch 0:  18%|█▊        | 167/938 [00:11<00:53, 14.40it/s, loss=1.1, v_num=8] 
Epoch 0:  18%|█▊        | 168/938 [00:11<00:53, 14.40it/s, loss=1.1, v_num=8]
Epoch 0:  18%|█▊        | 168/938 [00:11<00:53, 14.40it/s, loss=1.12, v_num=8]
Epoch 0:  18%|█▊        | 169/938 [00:11<00:53, 14.41it/s, loss=1.12, v_num=8]
Epoch 0:  18%|█▊        | 170/938 [00:11<00:53, 14.41it/s, loss=1.12, v_num=8]
Epoch 0:  18%|█▊        | 170/938 [00:11<00:53, 14.41it/s, loss=1.12, v_num=8]
Epoch 0:  18%|█▊        | 171/938 [00:11<00:53, 14.42it/s, loss=1.1, v_num=8] 
Epoch 0:  18%|█▊        | 172/938 [00:11<00:53, 14.43it/s, loss=1.1, v_num=8]
Epoch 0:  18%|█▊        | 172/938 [00:11<00:53, 14.43it/s, loss=1.1, v_num=8]
Epoch 0:  18%|█▊        | 173/938 [00:11<00:53, 14.42it/s, loss=1.09, v_num=8]
Epoch 0:  19%|█▊        | 174/938 [00:12<00:52, 14.42it/s, loss=1.09, v_num=8]
Epoch 0:  19%|█▊        | 174/938 [00:12<00:52, 14.42it/s, loss=1.07, v_num=8]
Epoch 0:  19%|█▊        | 175/938 [00:12<00:52, 14.41it/s, loss=1.07, v_num=8]
Epoch 0:  19%|█▉        | 176/938 [00:12<00:52, 14.41it/s, loss=1.07, v_num=8]
Epoch 0:  19%|█▉        | 176/938 [00:12<00:52, 14.41it/s, loss=1.07, v_num=8]
Epoch 0:  19%|█▉        | 177/938 [00:12<00:52, 14.41it/s, loss=1.06, v_num=8]
Epoch 0:  19%|█▉        | 178/938 [00:12<00:52, 14.42it/s, loss=1.06, v_num=8]
Epoch 0:  19%|█▉        | 178/938 [00:12<00:52, 14.42it/s, loss=1.06, v_num=8]
Epoch 0:  19%|█▉        | 179/938 [00:12<00:52, 14.41it/s, loss=1.07, v_num=8]
Epoch 0:  19%|█▉        | 180/938 [00:12<00:52, 14.39it/s, loss=1.07, v_num=8]
Epoch 0:  19%|█▉        | 180/938 [00:12<00:52, 14.39it/s, loss=1.06, v_num=8]
Epoch 0:  19%|█▉        | 181/938 [00:12<00:52, 14.38it/s, loss=1.05, v_num=8]
Epoch 0:  19%|█▉        | 182/938 [00:12<00:52, 14.39it/s, loss=1.05, v_num=8]
Epoch 0:  19%|█▉        | 182/938 [00:12<00:52, 14.39it/s, loss=1.05, v_num=8]
Epoch 0:  20%|█▉        | 183/938 [00:12<00:52, 14.39it/s, loss=1.05, v_num=8]
Epoch 0:  20%|█▉        | 184/938 [00:12<00:52, 14.37it/s, loss=1.05, v_num=8]
Epoch 0:  20%|█▉        | 184/938 [00:12<00:52, 14.37it/s, loss=1.05, v_num=8]
Epoch 0:  20%|█▉        | 185/938 [00:12<00:52, 14.37it/s, loss=1.07, v_num=8]
Epoch 0:  20%|█▉        | 186/938 [00:12<00:52, 14.39it/s, loss=1.07, v_num=8]
Epoch 0:  20%|█▉        | 186/938 [00:12<00:52, 14.39it/s, loss=1.05, v_num=8]
Epoch 0:  20%|█▉        | 187/938 [00:13<00:52, 14.36it/s, loss=1.06, v_num=8]
Epoch 0:  20%|██        | 188/938 [00:13<00:52, 14.31it/s, loss=1.06, v_num=8]
Epoch 0:  20%|██        | 188/938 [00:13<00:52, 14.31it/s, loss=1.06, v_num=8]
Epoch 0:  20%|██        | 189/938 [00:13<00:52, 14.31it/s, loss=1.04, v_num=8]
Epoch 0:  20%|██        | 190/938 [00:13<00:52, 14.31it/s, loss=1.04, v_num=8]
Epoch 0:  20%|██        | 190/938 [00:13<00:52, 14.31it/s, loss=1.03, v_num=8]
Epoch 0:  20%|██        | 191/938 [00:13<00:52, 14.31it/s, loss=1.02, v_num=8]
Epoch 0:  20%|██        | 192/938 [00:13<00:52, 14.30it/s, loss=1.02, v_num=8]
Epoch 0:  20%|██        | 192/938 [00:13<00:52, 14.30it/s, loss=1.02, v_num=8]
Epoch 0:  21%|██        | 193/938 [00:13<00:52, 14.31it/s, loss=1, v_num=8]   
Epoch 0:  21%|██        | 194/938 [00:13<00:51, 14.33it/s, loss=1, v_num=8]
Epoch 0:  21%|██        | 194/938 [00:13<00:51, 14.33it/s, loss=1.01, v_num=8]
Epoch 0:  21%|██        | 195/938 [00:13<00:51, 14.33it/s, loss=1.01, v_num=8]
Epoch 0:  21%|██        | 196/938 [00:13<00:51, 14.32it/s, loss=1.01, v_num=8]
Epoch 0:  21%|██        | 196/938 [00:13<00:51, 14.32it/s, loss=1.01, v_num=8]
Epoch 0:  21%|██        | 197/938 [00:13<00:51, 14.34it/s, loss=1.01, v_num=8]
Epoch 0:  21%|██        | 198/938 [00:13<00:51, 14.34it/s, loss=1.01, v_num=8]
Epoch 0:  21%|██        | 198/938 [00:13<00:51, 14.34it/s, loss=1.01, v_num=8]
Epoch 0:  21%|██        | 199/938 [00:13<00:51, 14.35it/s, loss=0.999, v_num=8]
Epoch 0:  21%|██▏       | 200/938 [00:13<00:51, 14.34it/s, loss=0.999, v_num=8]
Epoch 0:  21%|██▏       | 200/938 [00:13<00:51, 14.34it/s, loss=0.993, v_num=8]
Epoch 0:  21%|██▏       | 201/938 [00:14<00:51, 14.31it/s, loss=0.994, v_num=8]
Epoch 0:  22%|██▏       | 202/938 [00:14<00:51, 14.30it/s, loss=0.994, v_num=8]
Epoch 0:  22%|██▏       | 202/938 [00:14<00:51, 14.30it/s, loss=1.01, v_num=8] 
Epoch 0:  22%|██▏       | 203/938 [00:14<00:51, 14.29it/s, loss=1.01, v_num=8]
Epoch 0:  22%|██▏       | 204/938 [00:14<00:51, 14.30it/s, loss=1.01, v_num=8]
Epoch 0:  22%|██▏       | 204/938 [00:14<00:51, 14.30it/s, loss=1, v_num=8]   
Epoch 0:  22%|██▏       | 205/938 [00:14<00:51, 14.30it/s, loss=0.986, v_num=8]
Epoch 0:  22%|██▏       | 206/938 [00:14<00:51, 14.30it/s, loss=0.986, v_num=8]
Epoch 0:  22%|██▏       | 206/938 [00:14<00:51, 14.30it/s, loss=0.988, v_num=8]
Epoch 0:  22%|██▏       | 207/938 [00:14<00:51, 14.29it/s, loss=0.991, v_num=8]
Epoch 0:  22%|██▏       | 208/938 [00:14<00:51, 14.30it/s, loss=0.991, v_num=8]
Epoch 0:  22%|██▏       | 208/938 [00:14<00:51, 14.29it/s, loss=0.987, v_num=8]
Epoch 0:  22%|██▏       | 209/938 [00:14<00:50, 14.30it/s, loss=0.989, v_num=8]
Epoch 0:  22%|██▏       | 210/938 [00:14<00:50, 14.29it/s, loss=0.989, v_num=8]
Epoch 0:  22%|██▏       | 210/938 [00:14<00:50, 14.29it/s, loss=0.986, v_num=8]
Epoch 0:  22%|██▏       | 211/938 [00:14<00:50, 14.31it/s, loss=0.99, v_num=8] 
Epoch 0:  23%|██▎       | 212/938 [00:14<00:50, 14.30it/s, loss=0.99, v_num=8]
Epoch 0:  23%|██▎       | 212/938 [00:14<00:50, 14.30it/s, loss=0.995, v_num=8]
Epoch 0:  23%|██▎       | 213/938 [00:14<00:50, 14.31it/s, loss=0.999, v_num=8]
Epoch 0:  23%|██▎       | 214/938 [00:14<00:50, 14.32it/s, loss=0.999, v_num=8]
Epoch 0:  23%|██▎       | 214/938 [00:14<00:50, 14.32it/s, loss=0.991, v_num=8]
Epoch 0:  23%|██▎       | 215/938 [00:15<00:50, 14.32it/s, loss=0.978, v_num=8]
Epoch 0:  23%|██▎       | 216/938 [00:15<00:50, 14.33it/s, loss=0.978, v_num=8]
Epoch 0:  23%|██▎       | 216/938 [00:15<00:50, 14.33it/s, loss=0.974, v_num=8]
Epoch 0:  23%|██▎       | 217/938 [00:15<00:50, 14.34it/s, loss=0.962, v_num=8]
Epoch 0:  23%|██▎       | 218/938 [00:15<00:50, 14.34it/s, loss=0.962, v_num=8]
Epoch 0:  23%|██▎       | 218/938 [00:15<00:50, 14.34it/s, loss=0.957, v_num=8]
Epoch 0:  23%|██▎       | 219/938 [00:15<00:50, 14.35it/s, loss=0.961, v_num=8]
Epoch 0:  23%|██▎       | 220/938 [00:15<00:50, 14.35it/s, loss=0.961, v_num=8]
Epoch 0:  23%|██▎       | 220/938 [00:15<00:50, 14.35it/s, loss=0.961, v_num=8]
Epoch 0:  24%|██▎       | 221/938 [00:15<00:49, 14.35it/s, loss=0.949, v_num=8]
Epoch 0:  24%|██▎       | 222/938 [00:15<00:49, 14.36it/s, loss=0.949, v_num=8]
Epoch 0:  24%|██▎       | 222/938 [00:15<00:49, 14.35it/s, loss=0.941, v_num=8]
Epoch 0:  24%|██▍       | 223/938 [00:15<00:49, 14.35it/s, loss=0.94, v_num=8] 
Epoch 0:  24%|██▍       | 224/938 [00:15<00:49, 14.34it/s, loss=0.94, v_num=8]
Epoch 0:  24%|██▍       | 224/938 [00:15<00:49, 14.34it/s, loss=0.936, v_num=8]
Epoch 0:  24%|██▍       | 225/938 [00:15<00:49, 14.34it/s, loss=0.929, v_num=8]
Epoch 0:  24%|██▍       | 226/938 [00:15<00:49, 14.33it/s, loss=0.929, v_num=8]
Epoch 0:  24%|██▍       | 226/938 [00:15<00:49, 14.33it/s, loss=0.935, v_num=8]
Epoch 0:  24%|██▍       | 227/938 [00:15<00:49, 14.34it/s, loss=0.918, v_num=8]
Epoch 0:  24%|██▍       | 228/938 [00:15<00:49, 14.35it/s, loss=0.918, v_num=8]
Epoch 0:  24%|██▍       | 228/938 [00:15<00:49, 14.35it/s, loss=0.922, v_num=8]
Epoch 0:  24%|██▍       | 229/938 [00:15<00:49, 14.36it/s, loss=0.935, v_num=8]
Epoch 0:  25%|██▍       | 230/938 [00:16<00:49, 14.35it/s, loss=0.935, v_num=8]
Epoch 0:  25%|██▍       | 230/938 [00:16<00:49, 14.35it/s, loss=0.932, v_num=8]
Epoch 0:  25%|██▍       | 231/938 [00:16<00:49, 14.35it/s, loss=0.927, v_num=8]
Epoch 0:  25%|██▍       | 232/938 [00:16<00:49, 14.35it/s, loss=0.927, v_num=8]
Epoch 0:  25%|██▍       | 232/938 [00:16<00:49, 14.35it/s, loss=0.927, v_num=8]
Epoch 0:  25%|██▍       | 233/938 [00:16<00:49, 14.34it/s, loss=0.934, v_num=8]
Epoch 0:  25%|██▍       | 234/938 [00:16<00:49, 14.35it/s, loss=0.934, v_num=8]
Epoch 0:  25%|██▍       | 234/938 [00:16<00:49, 14.35it/s, loss=0.938, v_num=8]
Epoch 0:  25%|██▌       | 235/938 [00:16<00:48, 14.35it/s, loss=0.938, v_num=8]
Epoch 0:  25%|██▌       | 236/938 [00:16<00:48, 14.36it/s, loss=0.938, v_num=8]
Epoch 0:  25%|██▌       | 236/938 [00:16<00:48, 14.36it/s, loss=0.941, v_num=8]
Epoch 0:  25%|██▌       | 237/938 [00:16<00:48, 14.35it/s, loss=0.935, v_num=8]
Epoch 0:  25%|██▌       | 238/938 [00:16<00:48, 14.36it/s, loss=0.935, v_num=8]
Epoch 0:  25%|██▌       | 238/938 [00:16<00:48, 14.36it/s, loss=0.939, v_num=8]
Epoch 0:  25%|██▌       | 239/938 [00:16<00:48, 14.37it/s, loss=0.932, v_num=8]
Epoch 0:  26%|██▌       | 240/938 [00:16<00:48, 14.38it/s, loss=0.932, v_num=8]
Epoch 0:  26%|██▌       | 240/938 [00:16<00:48, 14.38it/s, loss=0.934, v_num=8]
Epoch 0:  26%|██▌       | 241/938 [00:16<00:48, 14.37it/s, loss=0.945, v_num=8]
Epoch 0:  26%|██▌       | 242/938 [00:16<00:48, 14.37it/s, loss=0.945, v_num=8]
Epoch 0:  26%|██▌       | 242/938 [00:16<00:48, 14.37it/s, loss=0.937, v_num=8]
Epoch 0:  26%|██▌       | 243/938 [00:16<00:48, 14.38it/s, loss=0.935, v_num=8]
Epoch 0:  26%|██▌       | 244/938 [00:16<00:48, 14.37it/s, loss=0.935, v_num=8]
Epoch 0:  26%|██▌       | 244/938 [00:16<00:48, 14.37it/s, loss=0.937, v_num=8]
Epoch 0:  26%|██▌       | 245/938 [00:17<00:48, 14.37it/s, loss=0.942, v_num=8]
Epoch 0:  26%|██▌       | 246/938 [00:17<00:48, 14.37it/s, loss=0.942, v_num=8]
Epoch 0:  26%|██▌       | 246/938 [00:17<00:48, 14.37it/s, loss=0.93, v_num=8] 
Epoch 0:  26%|██▋       | 247/938 [00:17<00:48, 14.37it/s, loss=0.937, v_num=8]
Epoch 0:  26%|██▋       | 248/938 [00:17<00:47, 14.38it/s, loss=0.937, v_num=8]
Epoch 0:  26%|██▋       | 248/938 [00:17<00:48, 14.37it/s, loss=0.932, v_num=8]
Epoch 0:  27%|██▋       | 249/938 [00:17<00:47, 14.38it/s, loss=0.91, v_num=8] 
Epoch 0:  27%|██▋       | 250/938 [00:17<00:47, 14.38it/s, loss=0.91, v_num=8]
Epoch 0:  27%|██▋       | 250/938 [00:17<00:47, 14.38it/s, loss=0.918, v_num=8]
Epoch 0:  27%|██▋       | 251/938 [00:17<00:47, 14.37it/s, loss=0.93, v_num=8] 
Epoch 0:  27%|██▋       | 252/938 [00:17<00:47, 14.38it/s, loss=0.93, v_num=8]
Epoch 0:  27%|██▋       | 252/938 [00:17<00:47, 14.37it/s, loss=0.923, v_num=8]
Epoch 0:  27%|██▋       | 253/938 [00:17<00:47, 14.38it/s, loss=0.917, v_num=8]
Epoch 0:  27%|██▋       | 254/938 [00:17<00:47, 14.38it/s, loss=0.917, v_num=8]
Epoch 0:  27%|██▋       | 254/938 [00:17<00:47, 14.38it/s, loss=0.912, v_num=8]
Epoch 0:  27%|██▋       | 255/938 [00:17<00:47, 14.39it/s, loss=0.914, v_num=8]
Epoch 0:  27%|██▋       | 256/938 [00:17<00:47, 14.39it/s, loss=0.914, v_num=8]
Epoch 0:  27%|██▋       | 256/938 [00:17<00:47, 14.39it/s, loss=0.908, v_num=8]
Epoch 0:  27%|██▋       | 257/938 [00:17<00:47, 14.39it/s, loss=0.916, v_num=8]
Epoch 0:  28%|██▊       | 258/938 [00:17<00:47, 14.39it/s, loss=0.916, v_num=8]
Epoch 0:  28%|██▊       | 258/938 [00:17<00:47, 14.39it/s, loss=0.917, v_num=8]
Epoch 0:  28%|██▊       | 259/938 [00:18<00:47, 14.39it/s, loss=0.922, v_num=8]
Epoch 0:  28%|██▊       | 260/938 [00:18<00:47, 14.38it/s, loss=0.922, v_num=8]
Epoch 0:  28%|██▊       | 260/938 [00:18<00:47, 14.38it/s, loss=0.921, v_num=8]
Epoch 0:  28%|██▊       | 261/938 [00:18<00:47, 14.38it/s, loss=0.917, v_num=8]
Epoch 0:  28%|██▊       | 262/938 [00:18<00:46, 14.39it/s, loss=0.917, v_num=8]
Epoch 0:  28%|██▊       | 262/938 [00:18<00:46, 14.39it/s, loss=0.912, v_num=8]
Epoch 0:  28%|██▊       | 263/938 [00:18<00:46, 14.39it/s, loss=0.911, v_num=8]
Epoch 0:  28%|██▊       | 264/938 [00:18<00:46, 14.37it/s, loss=0.911, v_num=8]
Epoch 0:  28%|██▊       | 264/938 [00:18<00:46, 14.37it/s, loss=0.899, v_num=8]
Epoch 0:  28%|██▊       | 265/938 [00:18<00:46, 14.38it/s, loss=0.901, v_num=8]
Epoch 0:  28%|██▊       | 266/938 [00:18<00:46, 14.38it/s, loss=0.901, v_num=8]
Epoch 0:  28%|██▊       | 266/938 [00:18<00:46, 14.38it/s, loss=0.899, v_num=8]
Epoch 0:  28%|██▊       | 267/938 [00:18<00:46, 14.38it/s, loss=0.899, v_num=8]
Epoch 0:  29%|██▊       | 268/938 [00:18<00:46, 14.39it/s, loss=0.899, v_num=8]
Epoch 0:  29%|██▊       | 268/938 [00:18<00:46, 14.39it/s, loss=0.898, v_num=8]
Epoch 0:  29%|██▊       | 269/938 [00:18<00:46, 14.37it/s, loss=0.906, v_num=8]
Epoch 0:  29%|██▉       | 270/938 [00:18<00:46, 14.38it/s, loss=0.906, v_num=8]
Epoch 0:  29%|██▉       | 270/938 [00:18<00:46, 14.38it/s, loss=0.906, v_num=8]
Epoch 0:  29%|██▉       | 271/938 [00:18<00:46, 14.39it/s, loss=0.887, v_num=8]
Epoch 0:  29%|██▉       | 272/938 [00:18<00:46, 14.37it/s, loss=0.887, v_num=8]
Epoch 0:  29%|██▉       | 272/938 [00:18<00:46, 14.37it/s, loss=0.889, v_num=8]
Epoch 0:  29%|██▉       | 273/938 [00:18<00:46, 14.38it/s, loss=0.876, v_num=8]
Epoch 0:  29%|██▉       | 274/938 [00:19<00:46, 14.39it/s, loss=0.876, v_num=8]
Epoch 0:  29%|██▉       | 274/938 [00:19<00:46, 14.39it/s, loss=0.881, v_num=8]
Epoch 0:  29%|██▉       | 275/938 [00:19<00:46, 14.40it/s, loss=0.882, v_num=8]
Epoch 0:  29%|██▉       | 276/938 [00:19<00:45, 14.40it/s, loss=0.882, v_num=8]
Epoch 0:  29%|██▉       | 276/938 [00:19<00:45, 14.40it/s, loss=0.887, v_num=8]
Epoch 0:  30%|██▉       | 277/938 [00:19<00:45, 14.40it/s, loss=0.886, v_num=8]
Epoch 0:  30%|██▉       | 278/938 [00:19<00:45, 14.39it/s, loss=0.886, v_num=8]
Epoch 0:  30%|██▉       | 278/938 [00:19<00:45, 14.39it/s, loss=0.879, v_num=8]
Epoch 0:  30%|██▉       | 279/938 [00:19<00:45, 14.39it/s, loss=0.875, v_num=8]
Epoch 0:  30%|██▉       | 280/938 [00:19<00:45, 14.40it/s, loss=0.875, v_num=8]
Epoch 0:  30%|██▉       | 280/938 [00:19<00:45, 14.40it/s, loss=0.879, v_num=8]
Epoch 0:  30%|██▉       | 281/938 [00:19<00:45, 14.39it/s, loss=0.885, v_num=8]
Epoch 0:  30%|███       | 282/938 [00:19<00:45, 14.39it/s, loss=0.885, v_num=8]
Epoch 0:  30%|███       | 282/938 [00:19<00:45, 14.39it/s, loss=0.887, v_num=8]
Epoch 0:  30%|███       | 283/938 [00:19<00:45, 14.40it/s, loss=0.888, v_num=8]
Epoch 0:  30%|███       | 284/938 [00:19<00:45, 14.40it/s, loss=0.888, v_num=8]
Epoch 0:  30%|███       | 284/938 [00:19<00:45, 14.40it/s, loss=0.899, v_num=8]
Epoch 0:  30%|███       | 285/938 [00:19<00:45, 14.39it/s, loss=0.9, v_num=8]  
Epoch 0:  30%|███       | 286/938 [00:19<00:45, 14.40it/s, loss=0.9, v_num=8]
Epoch 0:  30%|███       | 286/938 [00:19<00:45, 14.40it/s, loss=0.902, v_num=8]
Epoch 0:  31%|███       | 287/938 [00:19<00:45, 14.41it/s, loss=0.897, v_num=8]
Epoch 0:  31%|███       | 288/938 [00:19<00:45, 14.41it/s, loss=0.897, v_num=8]
Epoch 0:  31%|███       | 288/938 [00:19<00:45, 14.41it/s, loss=0.895, v_num=8]
Epoch 0:  31%|███       | 289/938 [00:20<00:45, 14.41it/s, loss=0.895, v_num=8]
Epoch 0:  31%|███       | 290/938 [00:20<00:44, 14.41it/s, loss=0.895, v_num=8]
Epoch 0:  31%|███       | 290/938 [00:20<00:44, 14.41it/s, loss=0.891, v_num=8]
Epoch 0:  31%|███       | 291/938 [00:20<00:44, 14.41it/s, loss=0.893, v_num=8]
Epoch 0:  31%|███       | 292/938 [00:20<00:44, 14.42it/s, loss=0.893, v_num=8]
Epoch 0:  31%|███       | 292/938 [00:20<00:44, 14.41it/s, loss=0.885, v_num=8]
Epoch 0:  31%|███       | 293/938 [00:20<00:44, 14.41it/s, loss=0.896, v_num=8]
Epoch 0:  31%|███▏      | 294/938 [00:20<00:44, 14.41it/s, loss=0.896, v_num=8]
Epoch 0:  31%|███▏      | 294/938 [00:20<00:44, 14.41it/s, loss=0.89, v_num=8] 
Epoch 0:  31%|███▏      | 295/938 [00:20<00:44, 14.40it/s, loss=0.888, v_num=8]
Epoch 0:  32%|███▏      | 296/938 [00:20<00:44, 14.41it/s, loss=0.888, v_num=8]
Epoch 0:  32%|███▏      | 296/938 [00:20<00:44, 14.41it/s, loss=0.889, v_num=8]
Epoch 0:  32%|███▏      | 297/938 [00:20<00:44, 14.41it/s, loss=0.884, v_num=8]
Epoch 0:  32%|███▏      | 298/938 [00:20<00:44, 14.42it/s, loss=0.884, v_num=8]
Epoch 0:  32%|███▏      | 298/938 [00:20<00:44, 14.42it/s, loss=0.885, v_num=8]
Epoch 0:  32%|███▏      | 299/938 [00:20<00:44, 14.42it/s, loss=0.885, v_num=8]
Epoch 0:  32%|███▏      | 300/938 [00:20<00:44, 14.42it/s, loss=0.885, v_num=8]
Epoch 0:  32%|███▏      | 300/938 [00:20<00:44, 14.42it/s, loss=0.875, v_num=8]
Epoch 0:  32%|███▏      | 301/938 [00:20<00:44, 14.43it/s, loss=0.867, v_num=8]
Epoch 0:  32%|███▏      | 302/938 [00:20<00:44, 14.42it/s, loss=0.867, v_num=8]
Epoch 0:  32%|███▏      | 302/938 [00:20<00:44, 14.42it/s, loss=0.877, v_num=8]
Epoch 0:  32%|███▏      | 303/938 [00:21<00:44, 14.43it/s, loss=0.874, v_num=8]
Epoch 0:  32%|███▏      | 304/938 [00:21<00:43, 14.44it/s, loss=0.874, v_num=8]
Epoch 0:  32%|███▏      | 304/938 [00:21<00:43, 14.44it/s, loss=0.861, v_num=8]
Epoch 0:  33%|███▎      | 305/938 [00:21<00:43, 14.44it/s, loss=0.864, v_num=8]
Epoch 0:  33%|███▎      | 306/938 [00:21<00:43, 14.44it/s, loss=0.864, v_num=8]
Epoch 0:  33%|███▎      | 306/938 [00:21<00:43, 14.44it/s, loss=0.878, v_num=8]
Epoch 0:  33%|███▎      | 307/938 [00:21<00:43, 14.44it/s, loss=0.892, v_num=8]
Epoch 0:  33%|███▎      | 308/938 [00:21<00:43, 14.39it/s, loss=0.892, v_num=8]
Epoch 0:  33%|███▎      | 308/938 [00:21<00:43, 14.39it/s, loss=0.89, v_num=8] 
Epoch 0:  33%|███▎      | 309/938 [00:21<00:43, 14.39it/s, loss=0.883, v_num=8]
Epoch 0:  33%|███▎      | 310/938 [00:21<00:43, 14.41it/s, loss=0.883, v_num=8]
Epoch 0:  33%|███▎      | 310/938 [00:21<00:43, 14.41it/s, loss=0.888, v_num=8]
Epoch 0:  33%|███▎      | 311/938 [00:21<00:43, 14.41it/s, loss=0.887, v_num=8]
Epoch 0:  33%|███▎      | 312/938 [00:21<00:43, 14.41it/s, loss=0.887, v_num=8]
Epoch 0:  33%|███▎      | 312/938 [00:21<00:43, 14.41it/s, loss=0.89, v_num=8] 
Epoch 0:  33%|███▎      | 313/938 [00:21<00:43, 14.42it/s, loss=0.889, v_num=8]
Epoch 0:  33%|███▎      | 314/938 [00:21<00:43, 14.42it/s, loss=0.889, v_num=8]
Epoch 0:  33%|███▎      | 314/938 [00:21<00:43, 14.42it/s, loss=0.884, v_num=8]
Epoch 0:  34%|███▎      | 315/938 [00:21<00:43, 14.42it/s, loss=0.878, v_num=8]
Epoch 0:  34%|███▎      | 316/938 [00:21<00:43, 14.43it/s, loss=0.878, v_num=8]
Epoch 0:  34%|███▎      | 316/938 [00:21<00:43, 14.43it/s, loss=0.869, v_num=8]
Epoch 0:  34%|███▍      | 317/938 [00:22<00:43, 14.40it/s, loss=0.881, v_num=8]
Epoch 0:  34%|███▍      | 318/938 [00:22<00:43, 14.40it/s, loss=0.881, v_num=8]
Epoch 0:  34%|███▍      | 318/938 [00:22<00:43, 14.40it/s, loss=0.888, v_num=8]
Epoch 0:  34%|███▍      | 319/938 [00:22<00:42, 14.41it/s, loss=0.886, v_num=8]
Epoch 0:  34%|███▍      | 320/938 [00:22<00:42, 14.41it/s, loss=0.886, v_num=8]
Epoch 0:  34%|███▍      | 320/938 [00:22<00:42, 14.41it/s, loss=0.902, v_num=8]
Epoch 0:  34%|███▍      | 321/938 [00:22<00:42, 14.41it/s, loss=0.912, v_num=8]
Epoch 0:  34%|███▍      | 322/938 [00:22<00:42, 14.40it/s, loss=0.912, v_num=8]
Epoch 0:  34%|███▍      | 322/938 [00:22<00:42, 14.40it/s, loss=0.909, v_num=8]
Epoch 0:  34%|███▍      | 323/938 [00:22<00:42, 14.39it/s, loss=0.911, v_num=8]
Epoch 0:  35%|███▍      | 324/938 [00:22<00:42, 14.39it/s, loss=0.911, v_num=8]
Epoch 0:  35%|███▍      | 324/938 [00:22<00:42, 14.39it/s, loss=0.913, v_num=8]
Epoch 0:  35%|███▍      | 325/938 [00:22<00:42, 14.40it/s, loss=0.918, v_num=8]
Epoch 0:  35%|███▍      | 326/938 [00:22<00:42, 14.39it/s, loss=0.918, v_num=8]
Epoch 0:  35%|███▍      | 326/938 [00:22<00:42, 14.39it/s, loss=0.909, v_num=8]
Epoch 0:  35%|███▍      | 327/938 [00:22<00:42, 14.39it/s, loss=0.904, v_num=8]
Epoch 0:  35%|███▍      | 328/938 [00:22<00:42, 14.39it/s, loss=0.904, v_num=8]
Epoch 0:  35%|███▍      | 328/938 [00:22<00:42, 14.39it/s, loss=0.904, v_num=8]
Epoch 0:  35%|███▌      | 329/938 [00:22<00:42, 14.40it/s, loss=0.912, v_num=8]
Epoch 0:  35%|███▌      | 330/938 [00:22<00:42, 14.40it/s, loss=0.912, v_num=8]
Epoch 0:  35%|███▌      | 330/938 [00:22<00:42, 14.40it/s, loss=0.907, v_num=8]
Epoch 0:  35%|███▌      | 331/938 [00:22<00:42, 14.40it/s, loss=0.911, v_num=8]
Epoch 0:  35%|███▌      | 332/938 [00:23<00:42, 14.40it/s, loss=0.911, v_num=8]
Epoch 0:  35%|███▌      | 332/938 [00:23<00:42, 14.40it/s, loss=0.911, v_num=8]
Epoch 0:  36%|███▌      | 333/938 [00:23<00:42, 14.40it/s, loss=0.911, v_num=8]
Epoch 0:  36%|███▌      | 334/938 [00:23<00:42, 14.37it/s, loss=0.911, v_num=8]
Epoch 0:  36%|███▌      | 334/938 [00:23<00:42, 14.37it/s, loss=0.914, v_num=8]
Epoch 0:  36%|███▌      | 335/938 [00:23<00:41, 14.37it/s, loss=0.919, v_num=8]
Epoch 0:  36%|███▌      | 336/938 [00:23<00:41, 14.38it/s, loss=0.919, v_num=8]
Epoch 0:  36%|███▌      | 336/938 [00:23<00:41, 14.38it/s, loss=0.92, v_num=8] 
Epoch 0:  36%|███▌      | 337/938 [00:23<00:41, 14.39it/s, loss=0.91, v_num=8]
Epoch 0:  36%|███▌      | 338/938 [00:23<00:41, 14.39it/s, loss=0.91, v_num=8]
Epoch 0:  36%|███▌      | 338/938 [00:23<00:41, 14.39it/s, loss=0.91, v_num=8]
Epoch 0:  36%|███▌      | 339/938 [00:23<00:41, 14.40it/s, loss=0.905, v_num=8]
Epoch 0:  36%|███▌      | 340/938 [00:23<00:41, 14.40it/s, loss=0.905, v_num=8]
Epoch 0:  36%|███▌      | 340/938 [00:23<00:41, 14.40it/s, loss=0.888, v_num=8]
Epoch 0:  36%|███▋      | 341/938 [00:23<00:41, 14.40it/s, loss=0.878, v_num=8]
Epoch 0:  36%|███▋      | 342/938 [00:23<00:41, 14.40it/s, loss=0.878, v_num=8]
Epoch 0:  36%|███▋      | 342/938 [00:23<00:41, 14.40it/s, loss=0.872, v_num=8]
Epoch 0:  37%|███▋      | 343/938 [00:23<00:41, 14.38it/s, loss=0.862, v_num=8]
Epoch 0:  37%|███▋      | 344/938 [00:23<00:41, 14.38it/s, loss=0.862, v_num=8]
Epoch 0:  37%|███▋      | 344/938 [00:23<00:41, 14.38it/s, loss=0.875, v_num=8]
Epoch 0:  37%|███▋      | 345/938 [00:23<00:41, 14.39it/s, loss=0.865, v_num=8]
Epoch 0:  37%|███▋      | 346/938 [00:24<00:41, 14.39it/s, loss=0.865, v_num=8]
Epoch 0:  37%|███▋      | 346/938 [00:24<00:41, 14.39it/s, loss=0.863, v_num=8]
Epoch 0:  37%|███▋      | 347/938 [00:24<00:41, 14.39it/s, loss=0.852, v_num=8]
Epoch 0:  37%|███▋      | 348/938 [00:24<00:40, 14.40it/s, loss=0.852, v_num=8]
Epoch 0:  37%|███▋      | 348/938 [00:24<00:40, 14.40it/s, loss=0.856, v_num=8]
Epoch 0:  37%|███▋      | 349/938 [00:24<00:40, 14.39it/s, loss=0.851, v_num=8]
Epoch 0:  37%|███▋      | 350/938 [00:24<00:40, 14.39it/s, loss=0.851, v_num=8]
Epoch 0:  37%|███▋      | 350/938 [00:24<00:40, 14.39it/s, loss=0.86, v_num=8] 
Epoch 0:  37%|███▋      | 351/938 [00:24<00:40, 14.40it/s, loss=0.866, v_num=8]
Epoch 0:  38%|███▊      | 352/938 [00:24<00:40, 14.40it/s, loss=0.866, v_num=8]
Epoch 0:  38%|███▊      | 352/938 [00:24<00:40, 14.40it/s, loss=0.865, v_num=8]
Epoch 0:  38%|███▊      | 353/938 [00:24<00:40, 14.40it/s, loss=0.863, v_num=8]
Epoch 0:  38%|███▊      | 354/938 [00:24<00:40, 14.40it/s, loss=0.863, v_num=8]
Epoch 0:  38%|███▊      | 354/938 [00:24<00:40, 14.40it/s, loss=0.868, v_num=8]
Epoch 0:  38%|███▊      | 355/938 [00:24<00:40, 14.40it/s, loss=0.863, v_num=8]
Epoch 0:  38%|███▊      | 356/938 [00:24<00:40, 14.39it/s, loss=0.863, v_num=8]
Epoch 0:  38%|███▊      | 356/938 [00:24<00:40, 14.39it/s, loss=0.854, v_num=8]
Epoch 0:  38%|███▊      | 357/938 [00:24<00:40, 14.38it/s, loss=0.862, v_num=8]
Epoch 0:  38%|███▊      | 358/938 [00:24<00:40, 14.39it/s, loss=0.862, v_num=8]
Epoch 0:  38%|███▊      | 358/938 [00:24<00:40, 14.39it/s, loss=0.852, v_num=8]
Epoch 0:  38%|███▊      | 359/938 [00:24<00:40, 14.39it/s, loss=0.865, v_num=8]
Epoch 0:  38%|███▊      | 360/938 [00:25<00:40, 14.39it/s, loss=0.865, v_num=8]
Epoch 0:  38%|███▊      | 360/938 [00:25<00:40, 14.39it/s, loss=0.864, v_num=8]
Epoch 0:  38%|███▊      | 361/938 [00:25<00:40, 14.39it/s, loss=0.867, v_num=8]
Epoch 0:  39%|███▊      | 362/938 [00:25<00:40, 14.39it/s, loss=0.867, v_num=8]
Epoch 0:  39%|███▊      | 362/938 [00:25<00:40, 14.39it/s, loss=0.865, v_num=8]
Epoch 0:  39%|███▊      | 363/938 [00:25<00:39, 14.39it/s, loss=0.869, v_num=8]
Epoch 0:  39%|███▉      | 364/938 [00:25<00:39, 14.39it/s, loss=0.869, v_num=8]
Epoch 0:  39%|███▉      | 364/938 [00:25<00:39, 14.39it/s, loss=0.871, v_num=8]
Epoch 0:  39%|███▉      | 365/938 [00:25<00:39, 14.39it/s, loss=0.872, v_num=8]
Epoch 0:  39%|███▉      | 366/938 [00:25<00:39, 14.39it/s, loss=0.872, v_num=8]
Epoch 0:  39%|███▉      | 366/938 [00:25<00:39, 14.39it/s, loss=0.881, v_num=8]
Epoch 0:  39%|███▉      | 367/938 [00:25<00:39, 14.39it/s, loss=0.892, v_num=8]
Epoch 0:  39%|███▉      | 368/938 [00:25<00:39, 14.39it/s, loss=0.892, v_num=8]
Epoch 0:  39%|███▉      | 368/938 [00:25<00:39, 14.39it/s, loss=0.882, v_num=8]
Epoch 0:  39%|███▉      | 369/938 [00:25<00:39, 14.39it/s, loss=0.885, v_num=8]
Epoch 0:  39%|███▉      | 370/938 [00:25<00:39, 14.39it/s, loss=0.885, v_num=8]
Epoch 0:  39%|███▉      | 370/938 [00:25<00:39, 14.39it/s, loss=0.875, v_num=8]
Epoch 0:  40%|███▉      | 371/938 [00:25<00:39, 14.37it/s, loss=0.865, v_num=8]
Epoch 0:  40%|███▉      | 372/938 [00:25<00:39, 14.38it/s, loss=0.865, v_num=8]
Epoch 0:  40%|███▉      | 372/938 [00:25<00:39, 14.38it/s, loss=0.872, v_num=8]
Epoch 0:  40%|███▉      | 373/938 [00:25<00:39, 14.39it/s, loss=0.871, v_num=8]
Epoch 0:  40%|███▉      | 374/938 [00:25<00:39, 14.39it/s, loss=0.871, v_num=8]
Epoch 0:  40%|███▉      | 374/938 [00:25<00:39, 14.39it/s, loss=0.861, v_num=8]
Epoch 0:  40%|███▉      | 375/938 [00:26<00:39, 14.39it/s, loss=0.865, v_num=8]
Epoch 0:  40%|████      | 376/938 [00:26<00:39, 14.39it/s, loss=0.865, v_num=8]
Epoch 0:  40%|████      | 376/938 [00:26<00:39, 14.39it/s, loss=0.877, v_num=8]
Epoch 0:  40%|████      | 377/938 [00:26<00:38, 14.39it/s, loss=0.868, v_num=8]
Epoch 0:  40%|████      | 378/938 [00:26<00:38, 14.40it/s, loss=0.868, v_num=8]
Epoch 0:  40%|████      | 378/938 [00:26<00:38, 14.40it/s, loss=0.865, v_num=8]
Epoch 0:  40%|████      | 379/938 [00:26<00:38, 14.40it/s, loss=0.852, v_num=8]
Epoch 0:  41%|████      | 380/938 [00:26<00:38, 14.40it/s, loss=0.852, v_num=8]
Epoch 0:  41%|████      | 380/938 [00:26<00:38, 14.40it/s, loss=0.857, v_num=8]
Epoch 0:  41%|████      | 381/938 [00:26<00:38, 14.40it/s, loss=0.854, v_num=8]
Epoch 0:  41%|████      | 382/938 [00:26<00:38, 14.40it/s, loss=0.854, v_num=8]
Epoch 0:  41%|████      | 382/938 [00:26<00:38, 14.40it/s, loss=0.85, v_num=8] 
Epoch 0:  41%|████      | 383/938 [00:26<00:38, 14.40it/s, loss=0.848, v_num=8]
Epoch 0:  41%|████      | 384/938 [00:26<00:38, 14.40it/s, loss=0.848, v_num=8]
Epoch 0:  41%|████      | 384/938 [00:26<00:38, 14.40it/s, loss=0.834, v_num=8]
Epoch 0:  41%|████      | 385/938 [00:26<00:38, 14.40it/s, loss=0.829, v_num=8]
Epoch 0:  41%|████      | 386/938 [00:26<00:38, 14.40it/s, loss=0.829, v_num=8]
Epoch 0:  41%|████      | 386/938 [00:26<00:38, 14.40it/s, loss=0.814, v_num=8]
Epoch 0:  41%|████▏     | 387/938 [00:26<00:38, 14.41it/s, loss=0.813, v_num=8]
Epoch 0:  41%|████▏     | 388/938 [00:26<00:38, 14.41it/s, loss=0.813, v_num=8]
Epoch 0:  41%|████▏     | 388/938 [00:26<00:38, 14.41it/s, loss=0.815, v_num=8]
Epoch 0:  41%|████▏     | 389/938 [00:27<00:38, 14.40it/s, loss=0.81, v_num=8] 
Epoch 0:  42%|████▏     | 390/938 [00:27<00:38, 14.41it/s, loss=0.81, v_num=8]
Epoch 0:  42%|████▏     | 390/938 [00:27<00:38, 14.41it/s, loss=0.811, v_num=8]
Epoch 0:  42%|████▏     | 391/938 [00:27<00:37, 14.41it/s, loss=0.809, v_num=8]
Epoch 0:  42%|████▏     | 392/938 [00:27<00:37, 14.41it/s, loss=0.809, v_num=8]
Epoch 0:  42%|████▏     | 392/938 [00:27<00:37, 14.41it/s, loss=0.802, v_num=8]
Epoch 0:  42%|████▏     | 393/938 [00:27<00:37, 14.42it/s, loss=0.797, v_num=8]
Epoch 0:  42%|████▏     | 394/938 [00:27<00:37, 14.42it/s, loss=0.797, v_num=8]
Epoch 0:  42%|████▏     | 394/938 [00:27<00:37, 14.42it/s, loss=0.801, v_num=8]
Epoch 0:  42%|████▏     | 395/938 [00:27<00:37, 14.43it/s, loss=0.804, v_num=8]
Epoch 0:  42%|████▏     | 396/938 [00:27<00:37, 14.43it/s, loss=0.804, v_num=8]
Epoch 0:  42%|████▏     | 396/938 [00:27<00:37, 14.43it/s, loss=0.799, v_num=8]
Epoch 0:  42%|████▏     | 397/938 [00:27<00:37, 14.43it/s, loss=0.819, v_num=8]
Epoch 0:  42%|████▏     | 398/938 [00:27<00:37, 14.43it/s, loss=0.819, v_num=8]
Epoch 0:  42%|████▏     | 398/938 [00:27<00:37, 14.43it/s, loss=0.821, v_num=8]
Epoch 0:  43%|████▎     | 399/938 [00:27<00:37, 14.43it/s, loss=0.828, v_num=8]
Epoch 0:  43%|████▎     | 400/938 [00:27<00:37, 14.43it/s, loss=0.828, v_num=8]
Epoch 0:  43%|████▎     | 400/938 [00:27<00:37, 14.43it/s, loss=0.823, v_num=8]
Epoch 0:  43%|████▎     | 401/938 [00:27<00:37, 14.43it/s, loss=0.826, v_num=8]
Epoch 0:  43%|████▎     | 402/938 [00:27<00:37, 14.44it/s, loss=0.826, v_num=8]
Epoch 0:  43%|████▎     | 402/938 [00:27<00:37, 14.44it/s, loss=0.827, v_num=8]
Epoch 0:  43%|████▎     | 403/938 [00:27<00:37, 14.43it/s, loss=0.824, v_num=8]
Epoch 0:  43%|████▎     | 404/938 [00:27<00:36, 14.43it/s, loss=0.824, v_num=8]
Epoch 0:  43%|████▎     | 404/938 [00:27<00:36, 14.43it/s, loss=0.831, v_num=8]
Epoch 0:  43%|████▎     | 405/938 [00:28<00:36, 14.43it/s, loss=0.831, v_num=8]
Epoch 0:  43%|████▎     | 406/938 [00:28<00:36, 14.44it/s, loss=0.831, v_num=8]
Epoch 0:  43%|████▎     | 406/938 [00:28<00:36, 14.44it/s, loss=0.833, v_num=8]
Epoch 0:  43%|████▎     | 407/938 [00:28<00:36, 14.44it/s, loss=0.819, v_num=8]
Epoch 0:  43%|████▎     | 408/938 [00:28<00:36, 14.40it/s, loss=0.819, v_num=8]
Epoch 0:  43%|████▎     | 408/938 [00:28<00:36, 14.40it/s, loss=0.819, v_num=8]
Epoch 0:  44%|████▎     | 409/938 [00:28<00:36, 14.41it/s, loss=0.816, v_num=8]
Epoch 0:  44%|████▎     | 410/938 [00:28<00:36, 14.41it/s, loss=0.816, v_num=8]
Epoch 0:  44%|████▎     | 410/938 [00:28<00:36, 14.41it/s, loss=0.822, v_num=8]
Epoch 0:  44%|████▍     | 411/938 [00:28<00:36, 14.41it/s, loss=0.844, v_num=8]
Epoch 0:  44%|████▍     | 412/938 [00:28<00:36, 14.41it/s, loss=0.844, v_num=8]
Epoch 0:  44%|████▍     | 412/938 [00:28<00:36, 14.41it/s, loss=0.851, v_num=8]
Epoch 0:  44%|████▍     | 413/938 [00:28<00:36, 14.42it/s, loss=0.867, v_num=8]
Epoch 0:  44%|████▍     | 414/938 [00:28<00:36, 14.41it/s, loss=0.867, v_num=8]
Epoch 0:  44%|████▍     | 414/938 [00:28<00:36, 14.41it/s, loss=0.881, v_num=8]
Epoch 0:  44%|████▍     | 415/938 [00:28<00:36, 14.42it/s, loss=0.879, v_num=8]
Epoch 0:  44%|████▍     | 416/938 [00:28<00:36, 14.42it/s, loss=0.879, v_num=8]
Epoch 0:  44%|████▍     | 416/938 [00:28<00:36, 14.42it/s, loss=0.886, v_num=8]
Epoch 0:  44%|████▍     | 417/938 [00:28<00:36, 14.43it/s, loss=0.856, v_num=8]
Epoch 0:  45%|████▍     | 418/938 [00:28<00:36, 14.43it/s, loss=0.856, v_num=8]
Epoch 0:  45%|████▍     | 418/938 [00:28<00:36, 14.43it/s, loss=0.854, v_num=8]
Epoch 0:  45%|████▍     | 419/938 [00:29<00:35, 14.43it/s, loss=0.85, v_num=8] 
Epoch 0:  45%|████▍     | 420/938 [00:29<00:35, 14.43it/s, loss=0.85, v_num=8]
Epoch 0:  45%|████▍     | 420/938 [00:29<00:35, 14.43it/s, loss=0.853, v_num=8]
Epoch 0:  45%|████▍     | 421/938 [00:29<00:35, 14.43it/s, loss=0.846, v_num=8]
Epoch 0:  45%|████▍     | 422/938 [00:29<00:35, 14.43it/s, loss=0.846, v_num=8]
Epoch 0:  45%|████▍     | 422/938 [00:29<00:35, 14.43it/s, loss=0.85, v_num=8] 
Epoch 0:  45%|████▌     | 423/938 [00:29<00:35, 14.43it/s, loss=0.846, v_num=8]
Epoch 0:  45%|████▌     | 424/938 [00:29<00:35, 14.43it/s, loss=0.846, v_num=8]
Epoch 0:  45%|████▌     | 424/938 [00:29<00:35, 14.43it/s, loss=0.84, v_num=8] 
Epoch 0:  45%|████▌     | 425/938 [00:29<00:35, 14.44it/s, loss=0.844, v_num=8]
Epoch 0:  45%|████▌     | 426/938 [00:29<00:35, 14.44it/s, loss=0.844, v_num=8]
Epoch 0:  45%|████▌     | 426/938 [00:29<00:35, 14.44it/s, loss=0.856, v_num=8]
Epoch 0:  46%|████▌     | 427/938 [00:29<00:35, 14.44it/s, loss=0.859, v_num=8]
Epoch 0:  46%|████▌     | 428/938 [00:29<00:35, 14.45it/s, loss=0.859, v_num=8]
Epoch 0:  46%|████▌     | 428/938 [00:29<00:35, 14.45it/s, loss=0.852, v_num=8]
Epoch 0:  46%|████▌     | 429/938 [00:29<00:35, 14.44it/s, loss=0.851, v_num=8]
Epoch 0:  46%|████▌     | 430/938 [00:29<00:35, 14.44it/s, loss=0.851, v_num=8]
Epoch 0:  46%|████▌     | 430/938 [00:29<00:35, 14.44it/s, loss=0.846, v_num=8]
Epoch 0:  46%|████▌     | 431/938 [00:29<00:35, 14.45it/s, loss=0.831, v_num=8]
Epoch 0:  46%|████▌     | 432/938 [00:29<00:35, 14.44it/s, loss=0.831, v_num=8]
Epoch 0:  46%|████▌     | 432/938 [00:29<00:35, 14.44it/s, loss=0.826, v_num=8]
Epoch 0:  46%|████▌     | 433/938 [00:29<00:34, 14.44it/s, loss=0.806, v_num=8]
Epoch 0:  46%|████▋     | 434/938 [00:30<00:34, 14.44it/s, loss=0.806, v_num=8]
Epoch 0:  46%|████▋     | 434/938 [00:30<00:34, 14.44it/s, loss=0.796, v_num=8]
Epoch 0:  46%|████▋     | 435/938 [00:30<00:34, 14.44it/s, loss=0.787, v_num=8]
Epoch 0:  46%|████▋     | 436/938 [00:30<00:34, 14.44it/s, loss=0.787, v_num=8]
Epoch 0:  46%|████▋     | 436/938 [00:30<00:34, 14.44it/s, loss=0.78, v_num=8] 
Epoch 0:  47%|████▋     | 437/938 [00:30<00:34, 14.45it/s, loss=0.788, v_num=8]
Epoch 0:  47%|████▋     | 438/938 [00:30<00:34, 14.45it/s, loss=0.788, v_num=8]
Epoch 0:  47%|████▋     | 438/938 [00:30<00:34, 14.45it/s, loss=0.787, v_num=8]
Epoch 0:  47%|████▋     | 439/938 [00:30<00:34, 14.45it/s, loss=0.791, v_num=8]
Epoch 0:  47%|████▋     | 440/938 [00:30<00:34, 14.45it/s, loss=0.791, v_num=8]
Epoch 0:  47%|████▋     | 440/938 [00:30<00:34, 14.45it/s, loss=0.806, v_num=8]
Epoch 0:  47%|████▋     | 441/938 [00:30<00:34, 14.45it/s, loss=0.81, v_num=8] 
Epoch 0:  47%|████▋     | 442/938 [00:30<00:34, 14.45it/s, loss=0.81, v_num=8]
Epoch 0:  47%|████▋     | 442/938 [00:30<00:34, 14.45it/s, loss=0.809, v_num=8]
Epoch 0:  47%|████▋     | 443/938 [00:30<00:34, 14.45it/s, loss=0.817, v_num=8]
Epoch 0:  47%|████▋     | 444/938 [00:30<00:34, 14.45it/s, loss=0.817, v_num=8]
Epoch 0:  47%|████▋     | 444/938 [00:30<00:34, 14.45it/s, loss=0.818, v_num=8]
Epoch 0:  47%|████▋     | 445/938 [00:30<00:34, 14.46it/s, loss=0.806, v_num=8]
Epoch 0:  48%|████▊     | 446/938 [00:30<00:34, 14.45it/s, loss=0.806, v_num=8]
Epoch 0:  48%|████▊     | 446/938 [00:30<00:34, 14.45it/s, loss=0.798, v_num=8]
Epoch 0:  48%|████▊     | 447/938 [00:30<00:33, 14.45it/s, loss=0.798, v_num=8]
Epoch 0:  48%|████▊     | 448/938 [00:30<00:33, 14.46it/s, loss=0.798, v_num=8]
Epoch 0:  48%|████▊     | 448/938 [00:30<00:33, 14.45it/s, loss=0.802, v_num=8]
Epoch 0:  48%|████▊     | 449/938 [00:31<00:33, 14.45it/s, loss=0.811, v_num=8]
Epoch 0:  48%|████▊     | 450/938 [00:31<00:33, 14.45it/s, loss=0.811, v_num=8]
Epoch 0:  48%|████▊     | 450/938 [00:31<00:33, 14.45it/s, loss=0.805, v_num=8]
Epoch 0:  48%|████▊     | 451/938 [00:31<00:33, 14.45it/s, loss=0.804, v_num=8]
Epoch 0:  48%|████▊     | 452/938 [00:31<00:33, 14.45it/s, loss=0.804, v_num=8]
Epoch 0:  48%|████▊     | 452/938 [00:31<00:33, 14.45it/s, loss=0.8, v_num=8]  
Epoch 0:  48%|████▊     | 453/938 [00:31<00:33, 14.46it/s, loss=0.81, v_num=8]
Epoch 0:  48%|████▊     | 454/938 [00:31<00:33, 14.44it/s, loss=0.81, v_num=8]
Epoch 0:  48%|████▊     | 454/938 [00:31<00:33, 14.44it/s, loss=0.808, v_num=8]
Epoch 0:  49%|████▊     | 455/938 [00:31<00:33, 14.44it/s, loss=0.81, v_num=8] 
Epoch 0:  49%|████▊     | 456/938 [00:31<00:33, 14.44it/s, loss=0.81, v_num=8]
Epoch 0:  49%|████▊     | 456/938 [00:31<00:33, 14.44it/s, loss=0.812, v_num=8]
Epoch 0:  49%|████▊     | 457/938 [00:31<00:33, 14.44it/s, loss=0.808, v_num=8]
Epoch 0:  49%|████▉     | 458/938 [00:31<00:33, 14.44it/s, loss=0.808, v_num=8]
Epoch 0:  49%|████▉     | 458/938 [00:31<00:33, 14.44it/s, loss=0.813, v_num=8]
Epoch 0:  49%|████▉     | 459/938 [00:31<00:33, 14.44it/s, loss=0.805, v_num=8]
Epoch 0:  49%|████▉     | 460/938 [00:31<00:33, 14.45it/s, loss=0.805, v_num=8]
Epoch 0:  49%|████▉     | 460/938 [00:31<00:33, 14.45it/s, loss=0.789, v_num=8]
Epoch 0:  49%|████▉     | 461/938 [00:31<00:33, 14.45it/s, loss=0.784, v_num=8]
Epoch 0:  49%|████▉     | 462/938 [00:31<00:32, 14.45it/s, loss=0.784, v_num=8]
Epoch 0:  49%|████▉     | 462/938 [00:31<00:32, 14.45it/s, loss=0.78, v_num=8] 
Epoch 0:  49%|████▉     | 463/938 [00:32<00:32, 14.45it/s, loss=0.77, v_num=8]
Epoch 0:  49%|████▉     | 464/938 [00:32<00:32, 14.45it/s, loss=0.77, v_num=8]
Epoch 0:  49%|████▉     | 464/938 [00:32<00:32, 14.45it/s, loss=0.767, v_num=8]
Epoch 0:  50%|████▉     | 465/938 [00:32<00:32, 14.45it/s, loss=0.778, v_num=8]
Epoch 0:  50%|████▉     | 466/938 [00:32<00:32, 14.45it/s, loss=0.778, v_num=8]
Epoch 0:  50%|████▉     | 466/938 [00:32<00:32, 14.45it/s, loss=0.776, v_num=8]
Epoch 0:  50%|████▉     | 467/938 [00:32<00:32, 14.46it/s, loss=0.781, v_num=8]
Epoch 0:  50%|████▉     | 468/938 [00:32<00:32, 14.46it/s, loss=0.781, v_num=8]
Epoch 0:  50%|████▉     | 468/938 [00:32<00:32, 14.46it/s, loss=0.788, v_num=8]
Epoch 0:  50%|█████     | 469/938 [00:32<00:32, 14.47it/s, loss=0.784, v_num=8]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]
Epoch 0:  50%|█████     | 471/938 [00:32<00:32, 14.50it/s, loss=0.784, v_num=8]

Validating:   1%|          | 3/469 [00:00<00:19, 24.26it/s]
Epoch 0:  51%|█████     | 474/938 [00:32<00:31, 14.55it/s, loss=0.784, v_num=8]

Validating:   1%|▏         | 6/469 [00:00<00:19, 24.12it/s]
Epoch 0:  51%|█████     | 477/938 [00:32<00:31, 14.59it/s, loss=0.784, v_num=8]

Validating:   2%|▏         | 9/469 [00:00<00:18, 25.43it/s]
Epoch 0:  51%|█████     | 480/938 [00:32<00:31, 14.63it/s, loss=0.784, v_num=8]

Validating:   3%|▎         | 12/469 [00:00<00:17, 25.85it/s]
Epoch 0:  51%|█████▏    | 483/938 [00:32<00:31, 14.67it/s, loss=0.784, v_num=8]

Validating:   3%|▎         | 15/469 [00:00<00:17, 26.33it/s]
Epoch 0:  52%|█████▏    | 486/938 [00:33<00:30, 14.71it/s, loss=0.784, v_num=8]

Validating:   4%|▍         | 18/469 [00:00<00:17, 25.65it/s]
Epoch 0:  52%|█████▏    | 489/938 [00:33<00:30, 14.75it/s, loss=0.784, v_num=8]

Validating:   4%|▍         | 21/469 [00:00<00:16, 26.61it/s]
Epoch 0:  52%|█████▏    | 492/938 [00:33<00:30, 14.79it/s, loss=0.784, v_num=8]

Validating:   5%|▌         | 24/469 [00:00<00:16, 26.52it/s]
Epoch 0:  53%|█████▎    | 495/938 [00:33<00:29, 14.83it/s, loss=0.784, v_num=8]

Validating:   6%|▌         | 27/469 [00:01<00:16, 26.73it/s]
Epoch 0:  53%|█████▎    | 498/938 [00:33<00:29, 14.87it/s, loss=0.784, v_num=8]

Validating:   6%|▋         | 30/469 [00:01<00:16, 26.55it/s]
Epoch 0:  53%|█████▎    | 501/938 [00:33<00:29, 14.91it/s, loss=0.784, v_num=8]

Validating:   7%|▋         | 33/469 [00:01<00:16, 25.84it/s]
Epoch 0:  54%|█████▎    | 504/938 [00:33<00:29, 14.94it/s, loss=0.784, v_num=8]

Validating:   8%|▊         | 36/469 [00:01<00:17, 25.34it/s]
Epoch 0:  54%|█████▍    | 507/938 [00:33<00:28, 14.97it/s, loss=0.784, v_num=8]

Validating:   8%|▊         | 39/469 [00:01<00:17, 24.24it/s]
Epoch 0:  54%|█████▍    | 510/938 [00:33<00:28, 15.00it/s, loss=0.784, v_num=8]

Validating:   9%|▉         | 42/469 [00:01<00:17, 24.25it/s]
Epoch 0:  55%|█████▍    | 513/938 [00:34<00:28, 15.03it/s, loss=0.784, v_num=8]

Validating:  10%|▉         | 45/469 [00:01<00:17, 24.70it/s]
Epoch 0:  55%|█████▌    | 516/938 [00:34<00:27, 15.08it/s, loss=0.784, v_num=8]

Validating:  10%|█         | 48/469 [00:01<00:16, 25.71it/s]
Epoch 0:  55%|█████▌    | 519/938 [00:34<00:27, 15.12it/s, loss=0.784, v_num=8]

Validating:  11%|█         | 51/469 [00:01<00:15, 26.20it/s]
Epoch 0:  56%|█████▌    | 522/938 [00:34<00:27, 15.15it/s, loss=0.784, v_num=8]

Validating:  12%|█▏        | 54/469 [00:02<00:15, 26.61it/s]
Epoch 0:  56%|█████▌    | 525/938 [00:34<00:27, 15.20it/s, loss=0.784, v_num=8]

Validating:  12%|█▏        | 57/469 [00:02<00:15, 26.12it/s]
Epoch 0:  56%|█████▋    | 528/938 [00:34<00:26, 15.23it/s, loss=0.784, v_num=8]

Validating:  13%|█▎        | 60/469 [00:02<00:15, 26.39it/s]
Epoch 0:  57%|█████▋    | 531/938 [00:34<00:26, 15.27it/s, loss=0.784, v_num=8]

Validating:  13%|█▎        | 63/469 [00:02<00:15, 25.56it/s]
Epoch 0:  57%|█████▋    | 534/938 [00:34<00:26, 15.30it/s, loss=0.784, v_num=8]

Validating:  14%|█▍        | 66/469 [00:02<00:15, 25.54it/s]
Epoch 0:  57%|█████▋    | 537/938 [00:35<00:26, 15.33it/s, loss=0.784, v_num=8]

Validating:  15%|█▍        | 69/469 [00:02<00:15, 25.29it/s]
Epoch 0:  58%|█████▊    | 540/938 [00:35<00:25, 15.37it/s, loss=0.784, v_num=8]

Validating:  15%|█▌        | 72/469 [00:02<00:15, 25.98it/s]
Epoch 0:  58%|█████▊    | 543/938 [00:35<00:25, 15.40it/s, loss=0.784, v_num=8]

Validating:  16%|█▌        | 75/469 [00:02<00:14, 26.51it/s]
Epoch 0:  58%|█████▊    | 546/938 [00:35<00:25, 15.44it/s, loss=0.784, v_num=8]

Validating:  17%|█▋        | 78/469 [00:03<00:14, 26.62it/s]
Epoch 0:  59%|█████▊    | 549/938 [00:35<00:25, 15.48it/s, loss=0.784, v_num=8]

Validating:  17%|█▋        | 81/469 [00:03<00:14, 27.34it/s]
Epoch 0:  59%|█████▉    | 552/938 [00:35<00:24, 15.52it/s, loss=0.784, v_num=8]

Validating:  18%|█▊        | 84/469 [00:03<00:14, 25.69it/s]
Epoch 0:  59%|█████▉    | 555/938 [00:35<00:24, 15.54it/s, loss=0.784, v_num=8]

Validating:  19%|█▊        | 87/469 [00:03<00:14, 25.47it/s]
Epoch 0:  59%|█████▉    | 558/938 [00:35<00:24, 15.57it/s, loss=0.784, v_num=8]

Validating:  19%|█▉        | 90/469 [00:03<00:15, 24.82it/s]
Epoch 0:  60%|█████▉    | 561/938 [00:35<00:24, 15.61it/s, loss=0.784, v_num=8]

Validating:  20%|█▉        | 93/469 [00:03<00:14, 25.94it/s]
Epoch 0:  60%|██████    | 564/938 [00:36<00:23, 15.64it/s, loss=0.784, v_num=8]

Validating:  20%|██        | 96/469 [00:03<00:14, 26.42it/s]
Epoch 0:  60%|██████    | 567/938 [00:36<00:23, 15.68it/s, loss=0.784, v_num=8]

Validating:  21%|██        | 99/469 [00:03<00:14, 26.25it/s]
Epoch 0:  61%|██████    | 570/938 [00:36<00:23, 15.71it/s, loss=0.784, v_num=8]

Validating:  22%|██▏       | 102/469 [00:03<00:14, 25.61it/s]
Epoch 0:  61%|██████    | 573/938 [00:36<00:23, 15.74it/s, loss=0.784, v_num=8]

Validating:  22%|██▏       | 105/469 [00:04<00:13, 26.37it/s]
Epoch 0:  61%|██████▏   | 576/938 [00:36<00:22, 15.77it/s, loss=0.784, v_num=8]

Validating:  23%|██▎       | 108/469 [00:04<00:13, 25.98it/s]
Epoch 0:  62%|██████▏   | 579/938 [00:36<00:22, 15.80it/s, loss=0.784, v_num=8]

Validating:  24%|██▎       | 111/469 [00:04<00:13, 25.80it/s]
Epoch 0:  62%|██████▏   | 582/938 [00:36<00:22, 15.84it/s, loss=0.784, v_num=8]

Validating:  24%|██▍       | 114/469 [00:04<00:13, 25.83it/s]
Epoch 0:  62%|██████▏   | 585/938 [00:36<00:22, 15.87it/s, loss=0.784, v_num=8]

Validating:  25%|██▍       | 117/469 [00:04<00:13, 25.72it/s]
Epoch 0:  63%|██████▎   | 588/938 [00:36<00:22, 15.90it/s, loss=0.784, v_num=8]

Validating:  26%|██▌       | 120/469 [00:04<00:13, 25.51it/s]
Epoch 0:  63%|██████▎   | 591/938 [00:37<00:21, 15.93it/s, loss=0.784, v_num=8]

Validating:  26%|██▌       | 123/469 [00:04<00:13, 25.63it/s]
Epoch 0:  63%|██████▎   | 594/938 [00:37<00:21, 15.96it/s, loss=0.784, v_num=8]

Validating:  27%|██▋       | 126/469 [00:04<00:13, 25.71it/s]
Epoch 0:  64%|██████▎   | 597/938 [00:37<00:21, 15.99it/s, loss=0.784, v_num=8]

Validating:  28%|██▊       | 129/469 [00:04<00:12, 26.65it/s]
Epoch 0:  64%|██████▍   | 600/938 [00:37<00:21, 16.03it/s, loss=0.784, v_num=8]

Validating:  28%|██▊       | 132/469 [00:05<00:12, 26.05it/s]
Epoch 0:  64%|██████▍   | 603/938 [00:37<00:20, 16.05it/s, loss=0.784, v_num=8]

Validating:  29%|██▉       | 135/469 [00:05<00:13, 25.54it/s]
Epoch 0:  65%|██████▍   | 606/938 [00:37<00:20, 16.08it/s, loss=0.784, v_num=8]

Validating:  29%|██▉       | 138/469 [00:05<00:12, 25.55it/s]
Epoch 0:  65%|██████▍   | 609/938 [00:37<00:20, 16.11it/s, loss=0.784, v_num=8]

Validating:  30%|███       | 141/469 [00:05<00:12, 26.09it/s]
Epoch 0:  65%|██████▌   | 612/938 [00:37<00:20, 16.15it/s, loss=0.784, v_num=8]

Validating:  31%|███       | 144/469 [00:05<00:12, 26.25it/s]
Epoch 0:  66%|██████▌   | 615/938 [00:38<00:19, 16.18it/s, loss=0.784, v_num=8]

Validating:  31%|███▏      | 147/469 [00:05<00:12, 26.47it/s]
Epoch 0:  66%|██████▌   | 618/938 [00:38<00:19, 16.21it/s, loss=0.784, v_num=8]

Validating:  32%|███▏      | 150/469 [00:05<00:12, 26.34it/s]
Epoch 0:  66%|██████▌   | 621/938 [00:38<00:19, 16.24it/s, loss=0.784, v_num=8]

Validating:  33%|███▎      | 153/469 [00:05<00:12, 26.30it/s]
Epoch 0:  67%|██████▋   | 624/938 [00:38<00:19, 16.27it/s, loss=0.784, v_num=8]

Validating:  33%|███▎      | 156/469 [00:06<00:11, 26.27it/s]
Epoch 0:  67%|██████▋   | 627/938 [00:38<00:19, 16.30it/s, loss=0.784, v_num=8]

Validating:  34%|███▍      | 159/469 [00:06<00:11, 26.94it/s]
Epoch 0:  67%|██████▋   | 630/938 [00:38<00:18, 16.33it/s, loss=0.784, v_num=8]

Validating:  35%|███▍      | 162/469 [00:06<00:11, 26.44it/s]
Epoch 0:  67%|██████▋   | 633/938 [00:38<00:18, 16.36it/s, loss=0.784, v_num=8]

Validating:  35%|███▌      | 165/469 [00:06<00:11, 27.14it/s]
Epoch 0:  68%|██████▊   | 636/938 [00:38<00:18, 16.39it/s, loss=0.784, v_num=8]

Validating:  36%|███▌      | 168/469 [00:06<00:11, 27.31it/s]
Epoch 0:  68%|██████▊   | 639/938 [00:38<00:18, 16.42it/s, loss=0.784, v_num=8]

Validating:  36%|███▋      | 171/469 [00:06<00:11, 26.70it/s]
Epoch 0:  68%|██████▊   | 642/938 [00:39<00:18, 16.44it/s, loss=0.784, v_num=8]

Validating:  37%|███▋      | 174/469 [00:06<00:12, 24.51it/s]
Epoch 0:  69%|██████▉   | 645/938 [00:39<00:17, 16.46it/s, loss=0.784, v_num=8]

Validating:  38%|███▊      | 177/469 [00:06<00:11, 25.05it/s]
Epoch 0:  69%|██████▉   | 648/938 [00:39<00:17, 16.49it/s, loss=0.784, v_num=8]

Validating:  38%|███▊      | 180/469 [00:06<00:11, 25.53it/s]
Epoch 0:  69%|██████▉   | 651/938 [00:39<00:17, 16.52it/s, loss=0.784, v_num=8]

Validating:  39%|███▉      | 183/469 [00:07<00:10, 26.42it/s]
Epoch 0:  70%|██████▉   | 654/938 [00:39<00:17, 16.55it/s, loss=0.784, v_num=8]

Validating:  40%|███▉      | 186/469 [00:07<00:11, 25.45it/s]
Epoch 0:  70%|███████   | 657/938 [00:39<00:16, 16.57it/s, loss=0.784, v_num=8]

Validating:  40%|████      | 189/469 [00:07<00:11, 24.55it/s]
Epoch 0:  70%|███████   | 660/938 [00:39<00:16, 16.59it/s, loss=0.784, v_num=8]

Validating:  41%|████      | 192/469 [00:07<00:11, 24.93it/s]
Epoch 0:  71%|███████   | 663/938 [00:39<00:16, 16.62it/s, loss=0.784, v_num=8]

Validating:  42%|████▏     | 195/469 [00:07<00:10, 25.51it/s]
Epoch 0:  71%|███████   | 666/938 [00:39<00:16, 16.65it/s, loss=0.784, v_num=8]

Validating:  42%|████▏     | 198/469 [00:07<00:10, 25.82it/s]
Epoch 0:  71%|███████▏  | 669/938 [00:40<00:16, 16.68it/s, loss=0.784, v_num=8]

Validating:  43%|████▎     | 201/469 [00:07<00:10, 25.36it/s]
Epoch 0:  72%|███████▏  | 672/938 [00:40<00:15, 16.70it/s, loss=0.784, v_num=8]

Validating:  43%|████▎     | 204/469 [00:07<00:10, 25.55it/s]
Epoch 0:  72%|███████▏  | 675/938 [00:40<00:15, 16.73it/s, loss=0.784, v_num=8]

Validating:  44%|████▍     | 207/469 [00:07<00:09, 26.37it/s]
Epoch 0:  72%|███████▏  | 678/938 [00:40<00:15, 16.76it/s, loss=0.784, v_num=8]

Validating:  45%|████▍     | 210/469 [00:08<00:10, 25.59it/s]
Epoch 0:  73%|███████▎  | 681/938 [00:40<00:15, 16.78it/s, loss=0.784, v_num=8]

Validating:  45%|████▌     | 213/469 [00:08<00:10, 24.71it/s]
Epoch 0:  73%|███████▎  | 684/938 [00:40<00:15, 16.80it/s, loss=0.784, v_num=8]

Validating:  46%|████▌     | 216/469 [00:08<00:10, 24.89it/s]
Epoch 0:  73%|███████▎  | 687/938 [00:40<00:14, 16.83it/s, loss=0.784, v_num=8]

Validating:  47%|████▋     | 219/469 [00:08<00:09, 25.56it/s]
Epoch 0:  74%|███████▎  | 690/938 [00:40<00:14, 16.85it/s, loss=0.784, v_num=8]

Validating:  47%|████▋     | 222/469 [00:08<00:09, 25.80it/s]
Epoch 0:  74%|███████▍  | 693/938 [00:41<00:14, 16.88it/s, loss=0.784, v_num=8]

Validating:  48%|████▊     | 225/469 [00:08<00:09, 26.14it/s]
Epoch 0:  74%|███████▍  | 696/938 [00:41<00:14, 16.91it/s, loss=0.784, v_num=8]

Validating:  49%|████▊     | 228/469 [00:08<00:09, 26.03it/s]
Epoch 0:  75%|███████▍  | 699/938 [00:41<00:14, 16.93it/s, loss=0.784, v_num=8]

Validating:  49%|████▉     | 231/469 [00:08<00:09, 26.31it/s]
Epoch 0:  75%|███████▍  | 702/938 [00:41<00:13, 16.96it/s, loss=0.784, v_num=8]

Validating:  50%|████▉     | 234/469 [00:09<00:08, 26.59it/s]
Epoch 0:  75%|███████▌  | 705/938 [00:41<00:13, 16.99it/s, loss=0.784, v_num=8]

Validating:  51%|█████     | 237/469 [00:09<00:08, 26.42it/s]
Epoch 0:  75%|███████▌  | 708/938 [00:41<00:13, 17.02it/s, loss=0.784, v_num=8]

Validating:  51%|█████     | 240/469 [00:09<00:08, 26.82it/s]
Epoch 0:  76%|███████▌  | 711/938 [00:41<00:13, 17.04it/s, loss=0.784, v_num=8]

Validating:  52%|█████▏    | 243/469 [00:09<00:08, 26.97it/s]
Epoch 0:  76%|███████▌  | 714/938 [00:41<00:13, 17.06it/s, loss=0.784, v_num=8]

Validating:  52%|█████▏    | 246/469 [00:09<00:09, 24.69it/s]
Epoch 0:  76%|███████▋  | 717/938 [00:41<00:12, 17.08it/s, loss=0.784, v_num=8]

Validating:  53%|█████▎    | 249/469 [00:09<00:08, 24.48it/s]
Epoch 0:  77%|███████▋  | 720/938 [00:42<00:12, 17.10it/s, loss=0.784, v_num=8]

Validating:  54%|█████▎    | 252/469 [00:09<00:09, 24.01it/s]
Epoch 0:  77%|███████▋  | 723/938 [00:42<00:12, 17.12it/s, loss=0.784, v_num=8]

Validating:  54%|█████▍    | 255/469 [00:09<00:09, 23.68it/s]
Epoch 0:  77%|███████▋  | 726/938 [00:42<00:12, 17.14it/s, loss=0.784, v_num=8]

Validating:  55%|█████▌    | 258/469 [00:10<00:09, 22.06it/s]
Epoch 0:  78%|███████▊  | 729/938 [00:42<00:12, 17.15it/s, loss=0.784, v_num=8]

Validating:  56%|█████▌    | 261/469 [00:10<00:09, 22.69it/s]
Epoch 0:  78%|███████▊  | 732/938 [00:42<00:12, 17.17it/s, loss=0.784, v_num=8]

Validating:  56%|█████▋    | 264/469 [00:10<00:08, 24.48it/s]
Epoch 0:  78%|███████▊  | 735/938 [00:42<00:11, 17.19it/s, loss=0.784, v_num=8]

Validating:  57%|█████▋    | 267/469 [00:10<00:08, 24.68it/s]
Epoch 0:  79%|███████▊  | 738/938 [00:42<00:11, 17.22it/s, loss=0.784, v_num=8]

Validating:  58%|█████▊    | 270/469 [00:10<00:07, 25.85it/s]
Epoch 0:  79%|███████▉  | 742/938 [00:43<00:11, 17.25it/s, loss=0.784, v_num=8]

Validating:  58%|█████▊    | 273/469 [00:10<00:07, 26.06it/s]

Validating:  59%|█████▉    | 276/469 [00:10<00:07, 26.58it/s]
Epoch 0:  80%|███████▉  | 746/938 [00:43<00:11, 17.29it/s, loss=0.784, v_num=8]

Validating:  59%|█████▉    | 279/469 [00:10<00:07, 24.65it/s]
Epoch 0:  80%|███████▉  | 750/938 [00:43<00:10, 17.31it/s, loss=0.784, v_num=8]

Validating:  60%|██████    | 282/469 [00:10<00:07, 24.59it/s]
Epoch 0:  80%|████████  | 754/938 [00:43<00:10, 17.34it/s, loss=0.784, v_num=8]

Validating:  61%|██████    | 285/469 [00:11<00:07, 25.10it/s]

Validating:  61%|██████▏   | 288/469 [00:11<00:07, 24.75it/s]
Epoch 0:  81%|████████  | 758/938 [00:43<00:10, 17.36it/s, loss=0.784, v_num=8]

Validating:  62%|██████▏   | 291/469 [00:11<00:07, 24.88it/s]
Epoch 0:  81%|████████  | 762/938 [00:43<00:10, 17.39it/s, loss=0.784, v_num=8]

Validating:  63%|██████▎   | 294/469 [00:11<00:07, 24.91it/s]
Epoch 0:  82%|████████▏ | 766/938 [00:43<00:09, 17.42it/s, loss=0.784, v_num=8]

Validating:  63%|██████▎   | 297/469 [00:11<00:06, 26.00it/s]

Validating:  64%|██████▍   | 300/469 [00:11<00:06, 26.01it/s]
Epoch 0:  82%|████████▏ | 770/938 [00:44<00:09, 17.46it/s, loss=0.784, v_num=8]

Validating:  65%|██████▍   | 303/469 [00:11<00:06, 26.36it/s]
Epoch 0:  83%|████████▎ | 774/938 [00:44<00:09, 17.49it/s, loss=0.784, v_num=8]

Validating:  65%|██████▌   | 306/469 [00:11<00:06, 26.39it/s]
Epoch 0:  83%|████████▎ | 778/938 [00:44<00:09, 17.52it/s, loss=0.784, v_num=8]

Validating:  66%|██████▌   | 309/469 [00:12<00:05, 26.82it/s]

Validating:  67%|██████▋   | 312/469 [00:12<00:05, 26.31it/s]
Epoch 0:  83%|████████▎ | 782/938 [00:44<00:08, 17.55it/s, loss=0.784, v_num=8]

Validating:  67%|██████▋   | 315/469 [00:12<00:06, 24.57it/s]
Epoch 0:  84%|████████▍ | 786/938 [00:44<00:08, 17.57it/s, loss=0.784, v_num=8]

Validating:  68%|██████▊   | 318/469 [00:12<00:06, 25.13it/s]
Epoch 0:  84%|████████▍ | 790/938 [00:44<00:08, 17.60it/s, loss=0.784, v_num=8]

Validating:  68%|██████▊   | 321/469 [00:12<00:05, 25.31it/s]

Validating:  69%|██████▉   | 324/469 [00:12<00:05, 26.39it/s]
Epoch 0:  85%|████████▍ | 794/938 [00:45<00:08, 17.63it/s, loss=0.784, v_num=8]

Validating:  70%|██████▉   | 327/469 [00:12<00:05, 26.21it/s]
Epoch 0:  85%|████████▌ | 798/938 [00:45<00:07, 17.66it/s, loss=0.784, v_num=8]

Validating:  70%|███████   | 330/469 [00:12<00:05, 26.38it/s]
Epoch 0:  86%|████████▌ | 802/938 [00:45<00:07, 17.69it/s, loss=0.784, v_num=8]

Validating:  71%|███████   | 333/469 [00:12<00:05, 26.61it/s]

Validating:  72%|███████▏  | 336/469 [00:13<00:05, 26.27it/s]
Epoch 0:  86%|████████▌ | 806/938 [00:45<00:07, 17.72it/s, loss=0.784, v_num=8]

Validating:  72%|███████▏  | 339/469 [00:13<00:04, 26.65it/s]
Epoch 0:  86%|████████▋ | 810/938 [00:45<00:07, 17.75it/s, loss=0.784, v_num=8]

Validating:  73%|███████▎  | 342/469 [00:13<00:04, 25.98it/s]
Epoch 0:  87%|████████▋ | 814/938 [00:45<00:06, 17.77it/s, loss=0.784, v_num=8]

Validating:  74%|███████▎  | 345/469 [00:13<00:04, 25.55it/s]

Validating:  74%|███████▍  | 348/469 [00:13<00:04, 25.22it/s]
Epoch 0:  87%|████████▋ | 818/938 [00:45<00:06, 17.80it/s, loss=0.784, v_num=8]

Validating:  75%|███████▍  | 351/469 [00:13<00:04, 25.98it/s]
Epoch 0:  88%|████████▊ | 822/938 [00:46<00:06, 17.83it/s, loss=0.784, v_num=8]

Validating:  75%|███████▌  | 354/469 [00:13<00:04, 26.42it/s]
Epoch 0:  88%|████████▊ | 826/938 [00:46<00:06, 17.85it/s, loss=0.784, v_num=8]

Validating:  76%|███████▌  | 357/469 [00:13<00:04, 26.11it/s]

Validating:  77%|███████▋  | 360/469 [00:13<00:04, 26.17it/s]
Epoch 0:  88%|████████▊ | 830/938 [00:46<00:06, 17.88it/s, loss=0.784, v_num=8]

Validating:  77%|███████▋  | 363/469 [00:14<00:04, 25.60it/s]
Epoch 0:  89%|████████▉ | 834/938 [00:46<00:05, 17.91it/s, loss=0.784, v_num=8]

Validating:  78%|███████▊  | 366/469 [00:14<00:03, 26.03it/s]
Epoch 0:  89%|████████▉ | 838/938 [00:46<00:05, 17.93it/s, loss=0.784, v_num=8]

Validating:  79%|███████▊  | 369/469 [00:14<00:03, 26.07it/s]

Validating:  79%|███████▉  | 372/469 [00:14<00:03, 25.57it/s]
Epoch 0:  90%|████████▉ | 842/938 [00:46<00:05, 17.96it/s, loss=0.784, v_num=8]

Validating:  80%|███████▉  | 375/469 [00:14<00:03, 25.60it/s]
Epoch 0:  90%|█████████ | 846/938 [00:47<00:05, 17.99it/s, loss=0.784, v_num=8]

Validating:  81%|████████  | 378/469 [00:14<00:03, 26.53it/s]
Epoch 0:  91%|█████████ | 850/938 [00:47<00:04, 18.02it/s, loss=0.784, v_num=8]

Validating:  81%|████████  | 381/469 [00:14<00:03, 26.64it/s]

Validating:  82%|████████▏ | 384/469 [00:14<00:03, 26.53it/s]
Epoch 0:  91%|█████████ | 854/938 [00:47<00:04, 18.04it/s, loss=0.784, v_num=8]

Validating:  83%|████████▎ | 387/469 [00:15<00:03, 26.29it/s]
Epoch 0:  91%|█████████▏| 858/938 [00:47<00:04, 18.07it/s, loss=0.784, v_num=8]

Validating:  83%|████████▎ | 390/469 [00:15<00:02, 26.45it/s]
Epoch 0:  92%|█████████▏| 862/938 [00:47<00:04, 18.08it/s, loss=0.784, v_num=8]

Validating:  84%|████████▍ | 393/469 [00:15<00:03, 24.35it/s]

Validating:  84%|████████▍ | 396/469 [00:15<00:02, 24.86it/s]
Epoch 0:  92%|█████████▏| 866/938 [00:47<00:03, 18.11it/s, loss=0.784, v_num=8]

Validating:  85%|████████▌ | 399/469 [00:15<00:02, 25.10it/s]
Epoch 0:  93%|█████████▎| 870/938 [00:47<00:03, 18.14it/s, loss=0.784, v_num=8]

Validating:  86%|████████▌ | 402/469 [00:15<00:02, 25.48it/s]
Epoch 0:  93%|█████████▎| 874/938 [00:48<00:03, 18.16it/s, loss=0.784, v_num=8]

Validating:  86%|████████▋ | 405/469 [00:15<00:02, 26.13it/s]

Validating:  87%|████████▋ | 408/469 [00:15<00:02, 25.69it/s]
Epoch 0:  94%|█████████▎| 878/938 [00:48<00:03, 18.19it/s, loss=0.784, v_num=8]

Validating:  88%|████████▊ | 411/469 [00:15<00:02, 24.99it/s]
Epoch 0:  94%|█████████▍| 882/938 [00:48<00:03, 18.21it/s, loss=0.784, v_num=8]

Validating:  88%|████████▊ | 414/469 [00:16<00:02, 25.41it/s]
Epoch 0:  94%|█████████▍| 886/938 [00:48<00:02, 18.23it/s, loss=0.784, v_num=8]

Validating:  89%|████████▉ | 417/469 [00:16<00:02, 25.55it/s]

Validating:  90%|████████▉ | 420/469 [00:16<00:01, 26.25it/s]
Epoch 0:  95%|█████████▍| 890/938 [00:48<00:02, 18.26it/s, loss=0.784, v_num=8]

Validating:  90%|█████████ | 423/469 [00:16<00:01, 26.12it/s]
Epoch 0:  95%|█████████▌| 894/938 [00:48<00:02, 18.28it/s, loss=0.784, v_num=8]

Validating:  91%|█████████ | 426/469 [00:16<00:01, 25.74it/s]
Epoch 0:  96%|█████████▌| 898/938 [00:49<00:02, 18.30it/s, loss=0.784, v_num=8]

Validating:  91%|█████████▏| 429/469 [00:16<00:01, 25.79it/s]

Validating:  92%|█████████▏| 432/469 [00:16<00:01, 25.62it/s]
Epoch 0:  96%|█████████▌| 902/938 [00:49<00:01, 18.33it/s, loss=0.784, v_num=8]

Validating:  93%|█████████▎| 435/469 [00:16<00:01, 25.81it/s]
Epoch 0:  97%|█████████▋| 906/938 [00:49<00:01, 18.35it/s, loss=0.784, v_num=8]

Validating:  93%|█████████▎| 438/469 [00:17<00:01, 26.77it/s]
Epoch 0:  97%|█████████▋| 910/938 [00:49<00:01, 18.38it/s, loss=0.784, v_num=8]

Validating:  94%|█████████▍| 441/469 [00:17<00:01, 26.37it/s]

Validating:  95%|█████████▍| 444/469 [00:17<00:00, 26.16it/s]
Epoch 0:  97%|█████████▋| 914/938 [00:49<00:01, 18.40it/s, loss=0.784, v_num=8]

Validating:  96%|█████████▌| 448/469 [00:17<00:00, 27.37it/s]
Epoch 0:  98%|█████████▊| 918/938 [00:49<00:01, 18.43it/s, loss=0.784, v_num=8]

Validating:  96%|█████████▌| 451/469 [00:17<00:00, 26.92it/s]
Epoch 0:  98%|█████████▊| 922/938 [00:49<00:00, 18.46it/s, loss=0.784, v_num=8]

Validating:  97%|█████████▋| 454/469 [00:17<00:00, 26.72it/s]
Epoch 0:  99%|█████████▊| 926/938 [00:50<00:00, 18.48it/s, loss=0.784, v_num=8]

Validating:  97%|█████████▋| 457/469 [00:17<00:00, 27.30it/s]

Validating:  98%|█████████▊| 460/469 [00:17<00:00, 27.71it/s]
Epoch 0:  99%|█████████▉| 930/938 [00:50<00:00, 18.51it/s, loss=0.784, v_num=8]

Validating:  99%|█████████▊| 463/469 [00:17<00:00, 26.82it/s]
Epoch 0: 100%|█████████▉| 934/938 [00:50<00:00, 18.53it/s, loss=0.784, v_num=8]

Validating:  99%|█████████▉| 466/469 [00:18<00:00, 26.28it/s]
Epoch 0: 100%|██████████| 938/938 [00:50<00:00, 18.55it/s, loss=0.784, v_num=8]
Epoch 0: 100%|██████████| 938/938 [00:50<00:00, 18.54it/s, loss=0.784, v_num=8, val_rmse=0.637]

                                                             
Epoch 0: 100%|██████████| 938/938 [00:50<00:00, 18.53it/s, loss=0.784, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 0:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.784, v_num=8, val_rmse=0.637, train_rmse=1.230]          
Epoch 1:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.784, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   0%|          | 1/938 [00:00<01:16, 12.25it/s, loss=0.775, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   0%|          | 2/938 [00:00<01:10, 13.23it/s, loss=0.77, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:   0%|          | 3/938 [00:00<01:11, 13.16it/s, loss=0.777, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   0%|          | 4/938 [00:00<01:08, 13.59it/s, loss=0.777, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   0%|          | 4/938 [00:00<01:08, 13.57it/s, loss=0.77, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:   1%|          | 5/938 [00:00<01:06, 14.10it/s, loss=0.772, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   1%|          | 6/938 [00:00<01:06, 13.97it/s, loss=0.77, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:   1%|          | 7/938 [00:00<01:04, 14.43it/s, loss=0.772, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   1%|          | 8/938 [00:00<01:04, 14.48it/s, loss=0.772, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   1%|          | 8/938 [00:00<01:04, 14.46it/s, loss=0.779, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   1%|          | 9/938 [00:00<01:03, 14.55it/s, loss=0.775, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   1%|          | 10/938 [00:00<01:03, 14.72it/s, loss=0.774, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   1%|          | 11/938 [00:00<01:03, 14.70it/s, loss=0.77, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:   1%|▏         | 12/938 [00:00<01:02, 14.79it/s, loss=0.77, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   1%|▏         | 12/938 [00:00<01:02, 14.78it/s, loss=0.78, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   1%|▏         | 13/938 [00:00<01:01, 14.92it/s, loss=0.784, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   1%|▏         | 14/938 [00:00<01:01, 14.91it/s, loss=0.784, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   2%|▏         | 15/938 [00:01<01:02, 14.69it/s, loss=0.79, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:   2%|▏         | 16/938 [00:01<01:02, 14.78it/s, loss=0.79, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   2%|▏         | 16/938 [00:01<01:02, 14.78it/s, loss=0.78, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   2%|▏         | 17/938 [00:01<01:02, 14.69it/s, loss=0.773, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   2%|▏         | 18/938 [00:01<01:02, 14.63it/s, loss=0.774, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   2%|▏         | 19/938 [00:01<01:02, 14.81it/s, loss=0.764, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   2%|▏         | 20/938 [00:01<01:02, 14.78it/s, loss=0.764, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   2%|▏         | 20/938 [00:01<01:02, 14.78it/s, loss=0.767, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   2%|▏         | 21/938 [00:01<01:02, 14.79it/s, loss=0.78, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:   2%|▏         | 22/938 [00:01<01:02, 14.73it/s, loss=0.784, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   2%|▏         | 23/938 [00:01<01:01, 14.76it/s, loss=0.774, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   3%|▎         | 24/938 [00:01<01:01, 14.82it/s, loss=0.774, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   3%|▎         | 24/938 [00:01<01:01, 14.82it/s, loss=0.781, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   3%|▎         | 25/938 [00:01<01:01, 14.89it/s, loss=0.783, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   3%|▎         | 26/938 [00:01<01:01, 14.73it/s, loss=0.785, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   3%|▎         | 27/938 [00:01<01:02, 14.47it/s, loss=0.779, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   3%|▎         | 28/938 [00:01<01:02, 14.49it/s, loss=0.779, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   3%|▎         | 28/938 [00:01<01:02, 14.48it/s, loss=0.778, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   3%|▎         | 29/938 [00:02<01:02, 14.50it/s, loss=0.771, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   3%|▎         | 30/938 [00:02<01:02, 14.58it/s, loss=0.775, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   3%|▎         | 31/938 [00:02<01:02, 14.55it/s, loss=0.774, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   3%|▎         | 32/938 [00:02<01:01, 14.62it/s, loss=0.774, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   3%|▎         | 32/938 [00:02<01:01, 14.62it/s, loss=0.761, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   4%|▎         | 33/938 [00:02<01:02, 14.60it/s, loss=0.757, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   4%|▎         | 34/938 [00:02<01:01, 14.62it/s, loss=0.764, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   4%|▎         | 35/938 [00:02<01:01, 14.62it/s, loss=0.758, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   4%|▍         | 36/938 [00:02<01:01, 14.61it/s, loss=0.758, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   4%|▍         | 36/938 [00:02<01:01, 14.61it/s, loss=0.762, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   4%|▍         | 37/938 [00:02<01:01, 14.70it/s, loss=0.773, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   4%|▍         | 38/938 [00:02<01:01, 14.68it/s, loss=0.776, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   4%|▍         | 39/938 [00:02<01:01, 14.68it/s, loss=0.782, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   4%|▍         | 40/938 [00:02<01:00, 14.74it/s, loss=0.782, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   4%|▍         | 40/938 [00:02<01:00, 14.74it/s, loss=0.78, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:   4%|▍         | 41/938 [00:02<01:00, 14.77it/s, loss=0.771, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   4%|▍         | 42/938 [00:02<01:00, 14.75it/s, loss=0.771, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   5%|▍         | 43/938 [00:02<01:00, 14.81it/s, loss=0.776, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   5%|▍         | 44/938 [00:02<01:00, 14.77it/s, loss=0.776, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   5%|▍         | 44/938 [00:02<01:00, 14.77it/s, loss=0.77, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:   5%|▍         | 45/938 [00:03<01:00, 14.78it/s, loss=0.773, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   5%|▍         | 46/938 [00:03<01:00, 14.82it/s, loss=0.774, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   5%|▌         | 47/938 [00:03<01:00, 14.80it/s, loss=0.777, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   5%|▌         | 48/938 [00:03<00:59, 14.83it/s, loss=0.777, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   5%|▌         | 48/938 [00:03<01:00, 14.83it/s, loss=0.779, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   5%|▌         | 49/938 [00:03<01:00, 14.81it/s, loss=0.784, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   5%|▌         | 50/938 [00:03<00:59, 14.84it/s, loss=0.782, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   5%|▌         | 51/938 [00:03<00:59, 14.86it/s, loss=0.787, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   6%|▌         | 52/938 [00:03<00:59, 14.88it/s, loss=0.787, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   6%|▌         | 52/938 [00:03<00:59, 14.88it/s, loss=0.791, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   6%|▌         | 53/938 [00:03<00:59, 14.89it/s, loss=0.788, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   6%|▌         | 54/938 [00:03<00:59, 14.83it/s, loss=0.787, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   6%|▌         | 55/938 [00:03<00:59, 14.87it/s, loss=0.792, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   6%|▌         | 56/938 [00:03<00:59, 14.87it/s, loss=0.792, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   6%|▌         | 56/938 [00:03<00:59, 14.86it/s, loss=0.801, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   6%|▌         | 57/938 [00:03<00:59, 14.82it/s, loss=0.799, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   6%|▌         | 58/938 [00:03<00:59, 14.85it/s, loss=0.789, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   6%|▋         | 59/938 [00:03<00:59, 14.85it/s, loss=0.785, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   6%|▋         | 60/938 [00:04<00:59, 14.87it/s, loss=0.785, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   6%|▋         | 60/938 [00:04<00:59, 14.86it/s, loss=0.788, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   7%|▋         | 61/938 [00:04<00:58, 14.88it/s, loss=0.795, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   7%|▋         | 62/938 [00:04<00:58, 14.86it/s, loss=0.797, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   7%|▋         | 63/938 [00:04<00:58, 14.88it/s, loss=0.798, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   7%|▋         | 64/938 [00:04<00:58, 14.89it/s, loss=0.798, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   7%|▋         | 64/938 [00:04<00:58, 14.89it/s, loss=0.797, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   7%|▋         | 65/938 [00:04<00:58, 14.87it/s, loss=0.788, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   7%|▋         | 66/938 [00:04<00:58, 14.88it/s, loss=0.788, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   7%|▋         | 67/938 [00:04<00:58, 14.89it/s, loss=0.792, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   7%|▋         | 68/938 [00:04<00:58, 14.88it/s, loss=0.792, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   7%|▋         | 68/938 [00:04<00:58, 14.87it/s, loss=0.781, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   7%|▋         | 69/938 [00:04<00:58, 14.87it/s, loss=0.788, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   7%|▋         | 70/938 [00:04<00:58, 14.86it/s, loss=0.778, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   8%|▊         | 71/938 [00:04<00:58, 14.86it/s, loss=0.782, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   8%|▊         | 72/938 [00:04<00:58, 14.76it/s, loss=0.782, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   8%|▊         | 72/938 [00:04<00:58, 14.76it/s, loss=0.785, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   8%|▊         | 73/938 [00:04<00:58, 14.73it/s, loss=0.785, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   8%|▊         | 74/938 [00:05<00:58, 14.74it/s, loss=0.789, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   8%|▊         | 75/938 [00:05<00:58, 14.73it/s, loss=0.79, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:   8%|▊         | 76/938 [00:05<00:58, 14.72it/s, loss=0.79, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   8%|▊         | 76/938 [00:05<00:58, 14.71it/s, loss=0.778, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   8%|▊         | 77/938 [00:05<00:58, 14.71it/s, loss=0.775, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   8%|▊         | 78/938 [00:05<00:58, 14.72it/s, loss=0.776, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   8%|▊         | 79/938 [00:05<00:58, 14.68it/s, loss=0.782, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   9%|▊         | 80/938 [00:05<00:58, 14.61it/s, loss=0.782, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   9%|▊         | 80/938 [00:05<00:58, 14.61it/s, loss=0.782, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   9%|▊         | 81/938 [00:05<00:58, 14.66it/s, loss=0.775, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   9%|▊         | 82/938 [00:05<00:58, 14.69it/s, loss=0.767, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   9%|▉         | 83/938 [00:05<00:58, 14.68it/s, loss=0.769, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   9%|▉         | 84/938 [00:05<00:58, 14.68it/s, loss=0.769, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   9%|▉         | 84/938 [00:05<00:58, 14.68it/s, loss=0.781, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   9%|▉         | 85/938 [00:05<00:58, 14.60it/s, loss=0.787, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   9%|▉         | 86/938 [00:05<00:58, 14.60it/s, loss=0.792, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   9%|▉         | 87/938 [00:05<00:58, 14.60it/s, loss=0.784, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   9%|▉         | 88/938 [00:06<00:58, 14.59it/s, loss=0.784, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   9%|▉         | 88/938 [00:06<00:58, 14.59it/s, loss=0.793, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:   9%|▉         | 89/938 [00:06<00:58, 14.56it/s, loss=0.78, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  10%|▉         | 90/938 [00:06<00:58, 14.59it/s, loss=0.789, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  10%|▉         | 91/938 [00:06<00:58, 14.57it/s, loss=0.787, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  10%|▉         | 92/938 [00:06<00:58, 14.57it/s, loss=0.787, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  10%|▉         | 92/938 [00:06<00:58, 14.57it/s, loss=0.786, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  10%|▉         | 93/938 [00:06<00:57, 14.57it/s, loss=0.786, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  10%|█         | 94/938 [00:06<00:57, 14.59it/s, loss=0.773, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  10%|█         | 95/938 [00:06<00:57, 14.59it/s, loss=0.766, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  10%|█         | 96/938 [00:06<00:57, 14.61it/s, loss=0.766, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  10%|█         | 96/938 [00:06<00:57, 14.61it/s, loss=0.772, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  10%|█         | 97/938 [00:06<00:57, 14.60it/s, loss=0.767, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  10%|█         | 98/938 [00:06<00:57, 14.61it/s, loss=0.76, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  11%|█         | 99/938 [00:06<00:57, 14.62it/s, loss=0.752, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  11%|█         | 100/938 [00:06<00:57, 14.58it/s, loss=0.752, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  11%|█         | 100/938 [00:06<00:57, 14.58it/s, loss=0.748, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  11%|█         | 101/938 [00:06<00:57, 14.56it/s, loss=0.746, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  11%|█         | 102/938 [00:06<00:57, 14.59it/s, loss=0.746, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  11%|█         | 103/938 [00:07<00:57, 14.58it/s, loss=0.751, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  11%|█         | 104/938 [00:07<00:57, 14.59it/s, loss=0.751, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  11%|█         | 104/938 [00:07<00:57, 14.59it/s, loss=0.745, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  11%|█         | 105/938 [00:07<00:57, 14.55it/s, loss=0.735, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  11%|█▏        | 106/938 [00:07<00:57, 14.54it/s, loss=0.729, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  11%|█▏        | 107/938 [00:07<00:57, 14.55it/s, loss=0.734, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  12%|█▏        | 108/938 [00:07<00:57, 14.53it/s, loss=0.734, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  12%|█▏        | 108/938 [00:07<00:57, 14.53it/s, loss=0.737, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  12%|█▏        | 109/938 [00:07<00:57, 14.51it/s, loss=0.737, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  12%|█▏        | 110/938 [00:07<00:57, 14.52it/s, loss=0.742, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  12%|█▏        | 111/938 [00:07<00:56, 14.53it/s, loss=0.732, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  12%|█▏        | 112/938 [00:07<00:56, 14.51it/s, loss=0.732, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  12%|█▏        | 112/938 [00:07<00:56, 14.51it/s, loss=0.727, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  12%|█▏        | 113/938 [00:07<00:56, 14.52it/s, loss=0.728, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  12%|█▏        | 114/938 [00:07<00:56, 14.50it/s, loss=0.741, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  12%|█▏        | 115/938 [00:07<00:56, 14.50it/s, loss=0.735, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  12%|█▏        | 116/938 [00:07<00:56, 14.50it/s, loss=0.735, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  12%|█▏        | 116/938 [00:07<00:56, 14.50it/s, loss=0.738, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  12%|█▏        | 117/938 [00:08<00:56, 14.50it/s, loss=0.739, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  13%|█▎        | 118/938 [00:08<00:56, 14.48it/s, loss=0.755, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  13%|█▎        | 119/938 [00:08<00:56, 14.48it/s, loss=0.757, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  13%|█▎        | 120/938 [00:08<00:56, 14.50it/s, loss=0.757, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  13%|█▎        | 120/938 [00:08<00:56, 14.50it/s, loss=0.752, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  13%|█▎        | 121/938 [00:08<00:56, 14.48it/s, loss=0.756, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  13%|█▎        | 122/938 [00:08<00:56, 14.50it/s, loss=0.758, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  13%|█▎        | 123/938 [00:08<00:56, 14.50it/s, loss=0.755, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  13%|█▎        | 124/938 [00:08<00:56, 14.50it/s, loss=0.755, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  13%|█▎        | 124/938 [00:08<00:56, 14.50it/s, loss=0.754, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  13%|█▎        | 125/938 [00:08<00:56, 14.51it/s, loss=0.771, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  13%|█▎        | 126/938 [00:08<00:55, 14.51it/s, loss=0.77, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  14%|█▎        | 127/938 [00:08<00:55, 14.50it/s, loss=0.77, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  14%|█▎        | 128/938 [00:08<00:55, 14.49it/s, loss=0.77, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  14%|█▎        | 128/938 [00:08<00:55, 14.49it/s, loss=0.767, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  14%|█▍        | 129/938 [00:08<00:55, 14.50it/s, loss=0.773, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  14%|█▍        | 130/938 [00:08<00:55, 14.49it/s, loss=0.769, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  14%|█▍        | 131/938 [00:09<00:55, 14.50it/s, loss=0.773, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  14%|█▍        | 132/938 [00:09<00:55, 14.50it/s, loss=0.773, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  14%|█▍        | 132/938 [00:09<00:55, 14.50it/s, loss=0.77, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  14%|█▍        | 133/938 [00:09<00:55, 14.49it/s, loss=0.769, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  14%|█▍        | 134/938 [00:09<00:55, 14.47it/s, loss=0.771, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  14%|█▍        | 135/938 [00:09<00:55, 14.48it/s, loss=0.78, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  14%|█▍        | 136/938 [00:09<00:55, 14.48it/s, loss=0.78, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  14%|█▍        | 136/938 [00:09<00:55, 14.48it/s, loss=0.778, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  15%|█▍        | 137/938 [00:09<00:55, 14.47it/s, loss=0.784, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  15%|█▍        | 138/938 [00:09<00:55, 14.46it/s, loss=0.767, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  15%|█▍        | 139/938 [00:09<00:55, 14.46it/s, loss=0.774, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  15%|█▍        | 140/938 [00:09<00:55, 14.46it/s, loss=0.774, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  15%|█▍        | 140/938 [00:09<00:55, 14.46it/s, loss=0.776, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  15%|█▌        | 141/938 [00:09<00:55, 14.45it/s, loss=0.779, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  15%|█▌        | 142/938 [00:09<00:55, 14.45it/s, loss=0.77, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  15%|█▌        | 143/938 [00:09<00:54, 14.46it/s, loss=0.762, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  15%|█▌        | 144/938 [00:09<00:54, 14.45it/s, loss=0.762, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  15%|█▌        | 144/938 [00:09<00:54, 14.45it/s, loss=0.769, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  15%|█▌        | 145/938 [00:10<00:54, 14.44it/s, loss=0.748, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  16%|█▌        | 146/938 [00:10<00:55, 14.38it/s, loss=0.748, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  16%|█▌        | 147/938 [00:10<00:54, 14.39it/s, loss=0.75, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  16%|█▌        | 148/938 [00:10<00:54, 14.39it/s, loss=0.75, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  16%|█▌        | 148/938 [00:10<00:54, 14.39it/s, loss=0.739, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  16%|█▌        | 149/938 [00:10<00:54, 14.40it/s, loss=0.741, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  16%|█▌        | 150/938 [00:10<00:54, 14.34it/s, loss=0.746, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  16%|█▌        | 151/938 [00:10<00:54, 14.34it/s, loss=0.756, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  16%|█▌        | 152/938 [00:10<00:54, 14.31it/s, loss=0.756, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  16%|█▌        | 152/938 [00:10<00:54, 14.31it/s, loss=0.764, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  16%|█▋        | 153/938 [00:10<00:54, 14.29it/s, loss=0.757, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  16%|█▋        | 154/938 [00:10<00:54, 14.31it/s, loss=0.753, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  17%|█▋        | 155/938 [00:10<00:54, 14.31it/s, loss=0.752, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  17%|█▋        | 156/938 [00:10<00:54, 14.32it/s, loss=0.752, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  17%|█▋        | 156/938 [00:10<00:54, 14.32it/s, loss=0.751, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  17%|█▋        | 157/938 [00:10<00:54, 14.33it/s, loss=0.746, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  17%|█▋        | 158/938 [00:11<00:54, 14.33it/s, loss=0.747, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  17%|█▋        | 159/938 [00:11<00:54, 14.33it/s, loss=0.749, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  17%|█▋        | 160/938 [00:11<00:54, 14.34it/s, loss=0.749, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  17%|█▋        | 160/938 [00:11<00:54, 14.34it/s, loss=0.743, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  17%|█▋        | 161/938 [00:11<00:54, 14.35it/s, loss=0.753, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  17%|█▋        | 162/938 [00:11<00:54, 14.35it/s, loss=0.768, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  17%|█▋        | 163/938 [00:11<00:53, 14.35it/s, loss=0.774, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  17%|█▋        | 164/938 [00:11<00:53, 14.36it/s, loss=0.774, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  17%|█▋        | 164/938 [00:11<00:53, 14.35it/s, loss=0.767, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  18%|█▊        | 165/938 [00:11<00:53, 14.36it/s, loss=0.771, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  18%|█▊        | 166/938 [00:11<00:53, 14.37it/s, loss=0.772, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  18%|█▊        | 167/938 [00:11<00:53, 14.36it/s, loss=0.768, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  18%|█▊        | 168/938 [00:11<00:53, 14.37it/s, loss=0.768, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  18%|█▊        | 168/938 [00:11<00:53, 14.37it/s, loss=0.773, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  18%|█▊        | 169/938 [00:11<00:53, 14.38it/s, loss=0.773, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  18%|█▊        | 170/938 [00:11<00:53, 14.37it/s, loss=0.765, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  18%|█▊        | 171/938 [00:11<00:53, 14.36it/s, loss=0.749, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  18%|█▊        | 172/938 [00:11<00:53, 14.37it/s, loss=0.749, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  18%|█▊        | 172/938 [00:11<00:53, 14.37it/s, loss=0.744, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  18%|█▊        | 173/938 [00:12<00:53, 14.37it/s, loss=0.752, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  19%|█▊        | 174/938 [00:12<00:53, 14.38it/s, loss=0.749, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  19%|█▊        | 175/938 [00:12<00:53, 14.39it/s, loss=0.746, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  19%|█▉        | 176/938 [00:12<00:52, 14.39it/s, loss=0.746, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  19%|█▉        | 176/938 [00:12<00:52, 14.39it/s, loss=0.742, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  19%|█▉        | 177/938 [00:12<00:52, 14.39it/s, loss=0.743, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  19%|█▉        | 178/938 [00:12<00:52, 14.39it/s, loss=0.741, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  19%|█▉        | 179/938 [00:12<00:52, 14.40it/s, loss=0.734, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  19%|█▉        | 180/938 [00:12<00:52, 14.41it/s, loss=0.734, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  19%|█▉        | 180/938 [00:12<00:52, 14.41it/s, loss=0.738, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  19%|█▉        | 181/938 [00:12<00:52, 14.42it/s, loss=0.721, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  19%|█▉        | 182/938 [00:12<00:52, 14.42it/s, loss=0.717, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  20%|█▉        | 183/938 [00:12<00:52, 14.43it/s, loss=0.712, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  20%|█▉        | 184/938 [00:12<00:52, 14.43it/s, loss=0.712, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  20%|█▉        | 184/938 [00:12<00:52, 14.43it/s, loss=0.705, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  20%|█▉        | 185/938 [00:12<00:52, 14.43it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  20%|█▉        | 186/938 [00:12<00:52, 14.42it/s, loss=0.715, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  20%|█▉        | 187/938 [00:12<00:52, 14.43it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  20%|██        | 188/938 [00:13<00:51, 14.43it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  20%|██        | 188/938 [00:13<00:51, 14.43it/s, loss=0.706, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  20%|██        | 189/938 [00:13<00:51, 14.43it/s, loss=0.717, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  20%|██        | 190/938 [00:13<00:51, 14.45it/s, loss=0.725, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  20%|██        | 191/938 [00:13<00:51, 14.47it/s, loss=0.733, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  20%|██        | 192/938 [00:13<00:51, 14.47it/s, loss=0.733, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  20%|██        | 192/938 [00:13<00:51, 14.47it/s, loss=0.73, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  21%|██        | 193/938 [00:13<00:51, 14.46it/s, loss=0.731, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  21%|██        | 194/938 [00:13<00:51, 14.48it/s, loss=0.727, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  21%|██        | 195/938 [00:13<00:51, 14.47it/s, loss=0.732, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  21%|██        | 196/938 [00:13<00:51, 14.48it/s, loss=0.732, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  21%|██        | 196/938 [00:13<00:51, 14.48it/s, loss=0.736, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  21%|██        | 197/938 [00:13<00:51, 14.48it/s, loss=0.743, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  21%|██        | 198/938 [00:13<00:51, 14.49it/s, loss=0.746, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  21%|██        | 199/938 [00:13<00:51, 14.49it/s, loss=0.753, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  21%|██▏       | 200/938 [00:13<00:50, 14.48it/s, loss=0.753, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  21%|██▏       | 200/938 [00:13<00:50, 14.48it/s, loss=0.755, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  21%|██▏       | 201/938 [00:13<00:50, 14.46it/s, loss=0.768, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  22%|██▏       | 202/938 [00:13<00:50, 14.46it/s, loss=0.764, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  22%|██▏       | 203/938 [00:14<00:50, 14.45it/s, loss=0.768, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  22%|██▏       | 204/938 [00:14<00:50, 14.46it/s, loss=0.768, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  22%|██▏       | 204/938 [00:14<00:50, 14.46it/s, loss=0.768, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  22%|██▏       | 205/938 [00:14<00:50, 14.46it/s, loss=0.774, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  22%|██▏       | 206/938 [00:14<00:50, 14.46it/s, loss=0.766, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  22%|██▏       | 207/938 [00:14<00:50, 14.47it/s, loss=0.764, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  22%|██▏       | 208/938 [00:14<00:50, 14.45it/s, loss=0.764, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  22%|██▏       | 208/938 [00:14<00:50, 14.45it/s, loss=0.777, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  22%|██▏       | 209/938 [00:14<00:50, 14.45it/s, loss=0.769, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  22%|██▏       | 210/938 [00:14<00:50, 14.45it/s, loss=0.76, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  22%|██▏       | 211/938 [00:14<00:50, 14.45it/s, loss=0.76, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  23%|██▎       | 212/938 [00:14<00:50, 14.44it/s, loss=0.76, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  23%|██▎       | 212/938 [00:14<00:50, 14.44it/s, loss=0.76, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  23%|██▎       | 213/938 [00:14<00:50, 14.43it/s, loss=0.765, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  23%|██▎       | 214/938 [00:14<00:50, 14.43it/s, loss=0.768, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  23%|██▎       | 215/938 [00:14<00:50, 14.44it/s, loss=0.762, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  23%|██▎       | 216/938 [00:14<00:49, 14.44it/s, loss=0.762, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  23%|██▎       | 216/938 [00:14<00:50, 14.44it/s, loss=0.764, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  23%|██▎       | 217/938 [00:15<00:49, 14.43it/s, loss=0.758, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  23%|██▎       | 218/938 [00:15<00:49, 14.43it/s, loss=0.762, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  23%|██▎       | 219/938 [00:15<00:49, 14.43it/s, loss=0.755, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  23%|██▎       | 220/938 [00:15<00:49, 14.44it/s, loss=0.755, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  23%|██▎       | 220/938 [00:15<00:49, 14.43it/s, loss=0.756, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  24%|██▎       | 221/938 [00:15<00:49, 14.45it/s, loss=0.747, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  24%|██▎       | 222/938 [00:15<00:49, 14.46it/s, loss=0.745, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  24%|██▍       | 223/938 [00:15<00:49, 14.47it/s, loss=0.739, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  24%|██▍       | 224/938 [00:15<00:49, 14.48it/s, loss=0.739, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  24%|██▍       | 224/938 [00:15<00:49, 14.47it/s, loss=0.738, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  24%|██▍       | 225/938 [00:15<00:49, 14.46it/s, loss=0.733, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  24%|██▍       | 226/938 [00:15<00:49, 14.47it/s, loss=0.733, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  24%|██▍       | 227/938 [00:15<00:49, 14.47it/s, loss=0.735, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  24%|██▍       | 228/938 [00:15<00:49, 14.47it/s, loss=0.735, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  24%|██▍       | 228/938 [00:15<00:49, 14.47it/s, loss=0.731, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  24%|██▍       | 229/938 [00:15<00:48, 14.47it/s, loss=0.725, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  25%|██▍       | 230/938 [00:15<00:48, 14.48it/s, loss=0.731, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  25%|██▍       | 231/938 [00:15<00:48, 14.45it/s, loss=0.729, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  25%|██▍       | 232/938 [00:16<00:48, 14.47it/s, loss=0.729, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  25%|██▍       | 232/938 [00:16<00:48, 14.47it/s, loss=0.728, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  25%|██▍       | 233/938 [00:16<00:48, 14.48it/s, loss=0.717, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  25%|██▍       | 234/938 [00:16<00:48, 14.45it/s, loss=0.72, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  25%|██▌       | 235/938 [00:16<00:48, 14.45it/s, loss=0.725, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  25%|██▌       | 236/938 [00:16<00:48, 14.44it/s, loss=0.725, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  25%|██▌       | 236/938 [00:16<00:48, 14.44it/s, loss=0.722, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  25%|██▌       | 237/938 [00:16<00:48, 14.43it/s, loss=0.72, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  25%|██▌       | 238/938 [00:16<00:48, 14.43it/s, loss=0.721, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  25%|██▌       | 239/938 [00:16<00:48, 14.42it/s, loss=0.731, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  26%|██▌       | 240/938 [00:16<00:48, 14.40it/s, loss=0.731, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  26%|██▌       | 240/938 [00:16<00:48, 14.40it/s, loss=0.739, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  26%|██▌       | 241/938 [00:16<00:48, 14.39it/s, loss=0.741, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  26%|██▌       | 242/938 [00:16<00:48, 14.39it/s, loss=0.744, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  26%|██▌       | 243/938 [00:16<00:48, 14.39it/s, loss=0.74, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  26%|██▌       | 244/938 [00:16<00:48, 14.40it/s, loss=0.74, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  26%|██▌       | 244/938 [00:16<00:48, 14.40it/s, loss=0.736, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  26%|██▌       | 245/938 [00:17<00:48, 14.39it/s, loss=0.735, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  26%|██▌       | 246/938 [00:17<00:48, 14.40it/s, loss=0.742, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  26%|██▋       | 247/938 [00:17<00:47, 14.41it/s, loss=0.747, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  26%|██▋       | 248/938 [00:17<00:47, 14.42it/s, loss=0.747, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  26%|██▋       | 248/938 [00:17<00:47, 14.42it/s, loss=0.75, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  27%|██▋       | 249/938 [00:17<00:47, 14.42it/s, loss=0.751, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  27%|██▋       | 250/938 [00:17<00:47, 14.41it/s, loss=0.739, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  27%|██▋       | 251/938 [00:17<00:47, 14.41it/s, loss=0.743, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  27%|██▋       | 252/938 [00:17<00:47, 14.40it/s, loss=0.743, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  27%|██▋       | 252/938 [00:17<00:47, 14.40it/s, loss=0.753, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  27%|██▋       | 253/938 [00:17<00:47, 14.40it/s, loss=0.755, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  27%|██▋       | 254/938 [00:17<00:47, 14.40it/s, loss=0.748, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  27%|██▋       | 255/938 [00:17<00:47, 14.39it/s, loss=0.743, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  27%|██▋       | 256/938 [00:17<00:47, 14.39it/s, loss=0.743, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  27%|██▋       | 256/938 [00:17<00:47, 14.39it/s, loss=0.745, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  27%|██▋       | 257/938 [00:17<00:47, 14.39it/s, loss=0.753, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  28%|██▊       | 258/938 [00:17<00:47, 14.37it/s, loss=0.752, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  28%|██▊       | 259/938 [00:18<00:47, 14.37it/s, loss=0.744, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  28%|██▊       | 260/938 [00:18<00:47, 14.36it/s, loss=0.744, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  28%|██▊       | 260/938 [00:18<00:47, 14.36it/s, loss=0.727, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  28%|██▊       | 261/938 [00:18<00:47, 14.37it/s, loss=0.734, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  28%|██▊       | 262/938 [00:18<00:47, 14.37it/s, loss=0.739, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  28%|██▊       | 263/938 [00:18<00:46, 14.38it/s, loss=0.748, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  28%|██▊       | 264/938 [00:18<00:46, 14.39it/s, loss=0.748, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  28%|██▊       | 264/938 [00:18<00:46, 14.38it/s, loss=0.759, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  28%|██▊       | 265/938 [00:18<00:46, 14.39it/s, loss=0.761, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  28%|██▊       | 266/938 [00:18<00:46, 14.40it/s, loss=0.757, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  28%|██▊       | 267/938 [00:18<00:46, 14.39it/s, loss=0.761, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  29%|██▊       | 268/938 [00:18<00:46, 14.40it/s, loss=0.761, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  29%|██▊       | 268/938 [00:18<00:46, 14.40it/s, loss=0.763, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  29%|██▊       | 269/938 [00:18<00:46, 14.39it/s, loss=0.767, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  29%|██▉       | 270/938 [00:18<00:46, 14.38it/s, loss=0.778, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  29%|██▉       | 271/938 [00:18<00:46, 14.38it/s, loss=0.775, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  29%|██▉       | 272/938 [00:18<00:46, 14.39it/s, loss=0.775, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  29%|██▉       | 272/938 [00:18<00:46, 14.39it/s, loss=0.781, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  29%|██▉       | 273/938 [00:18<00:46, 14.38it/s, loss=0.787, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  29%|██▉       | 274/938 [00:19<00:46, 14.37it/s, loss=0.799, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  29%|██▉       | 275/938 [00:19<00:46, 14.38it/s, loss=0.81, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  29%|██▉       | 276/938 [00:19<00:46, 14.38it/s, loss=0.81, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  29%|██▉       | 276/938 [00:19<00:46, 14.38it/s, loss=0.811, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  30%|██▉       | 277/938 [00:19<00:45, 14.38it/s, loss=0.798, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  30%|██▉       | 278/938 [00:19<00:45, 14.37it/s, loss=0.8, v_num=8, val_rmse=0.637, train_rmse=1.230]  
Epoch 1:  30%|██▉       | 279/938 [00:19<00:45, 14.36it/s, loss=0.805, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  30%|██▉       | 280/938 [00:19<00:45, 14.36it/s, loss=0.805, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  30%|██▉       | 280/938 [00:19<00:45, 14.36it/s, loss=0.825, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  30%|██▉       | 281/938 [00:19<00:45, 14.33it/s, loss=0.829, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  30%|███       | 282/938 [00:19<00:45, 14.34it/s, loss=0.826, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  30%|███       | 283/938 [00:19<00:45, 14.33it/s, loss=0.827, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  30%|███       | 284/938 [00:19<00:45, 14.33it/s, loss=0.827, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  30%|███       | 284/938 [00:19<00:45, 14.33it/s, loss=0.819, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  30%|███       | 285/938 [00:19<00:45, 14.33it/s, loss=0.814, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  30%|███       | 286/938 [00:19<00:45, 14.33it/s, loss=0.818, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  31%|███       | 287/938 [00:20<00:45, 14.33it/s, loss=0.819, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  31%|███       | 288/938 [00:20<00:45, 14.33it/s, loss=0.819, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  31%|███       | 288/938 [00:20<00:45, 14.33it/s, loss=0.81, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  31%|███       | 289/938 [00:20<00:45, 14.33it/s, loss=0.803, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  31%|███       | 290/938 [00:20<00:45, 14.33it/s, loss=0.805, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  31%|███       | 291/938 [00:20<00:45, 14.32it/s, loss=0.812, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  31%|███       | 292/938 [00:20<00:45, 14.30it/s, loss=0.812, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  31%|███       | 292/938 [00:20<00:45, 14.30it/s, loss=0.797, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  31%|███       | 293/938 [00:20<00:45, 14.30it/s, loss=0.797, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  31%|███▏      | 294/938 [00:20<00:45, 14.30it/s, loss=0.786, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  31%|███▏      | 295/938 [00:20<00:45, 14.29it/s, loss=0.772, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  32%|███▏      | 296/938 [00:20<00:44, 14.30it/s, loss=0.772, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  32%|███▏      | 296/938 [00:20<00:44, 14.29it/s, loss=0.762, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  32%|███▏      | 297/938 [00:20<00:44, 14.29it/s, loss=0.762, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  32%|███▏      | 298/938 [00:20<00:44, 14.28it/s, loss=0.756, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  32%|███▏      | 299/938 [00:20<00:44, 14.28it/s, loss=0.748, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  32%|███▏      | 300/938 [00:21<00:44, 14.28it/s, loss=0.748, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  32%|███▏      | 300/938 [00:21<00:44, 14.28it/s, loss=0.738, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  32%|███▏      | 301/938 [00:21<00:44, 14.27it/s, loss=0.726, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  32%|███▏      | 302/938 [00:21<00:44, 14.27it/s, loss=0.72, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  32%|███▏      | 303/938 [00:21<00:44, 14.26it/s, loss=0.714, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  32%|███▏      | 304/938 [00:21<00:44, 14.27it/s, loss=0.714, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  32%|███▏      | 304/938 [00:21<00:44, 14.27it/s, loss=0.725, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  33%|███▎      | 305/938 [00:21<00:44, 14.27it/s, loss=0.728, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  33%|███▎      | 306/938 [00:21<00:44, 14.27it/s, loss=0.726, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  33%|███▎      | 307/938 [00:21<00:44, 14.27it/s, loss=0.716, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  33%|███▎      | 308/938 [00:21<00:44, 14.27it/s, loss=0.716, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  33%|███▎      | 308/938 [00:21<00:44, 14.27it/s, loss=0.717, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  33%|███▎      | 309/938 [00:21<00:44, 14.26it/s, loss=0.724, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  33%|███▎      | 310/938 [00:21<00:44, 14.27it/s, loss=0.716, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  33%|███▎      | 311/938 [00:21<00:43, 14.27it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  33%|███▎      | 312/938 [00:21<00:43, 14.28it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  33%|███▎      | 312/938 [00:21<00:43, 14.28it/s, loss=0.714, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  33%|███▎      | 313/938 [00:21<00:43, 14.27it/s, loss=0.711, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  33%|███▎      | 314/938 [00:22<00:43, 14.27it/s, loss=0.712, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  34%|███▎      | 315/938 [00:22<00:43, 14.28it/s, loss=0.723, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  34%|███▎      | 316/938 [00:22<00:43, 14.26it/s, loss=0.723, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  34%|███▎      | 316/938 [00:22<00:43, 14.26it/s, loss=0.731, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  34%|███▍      | 317/938 [00:22<00:43, 14.25it/s, loss=0.734, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  34%|███▍      | 318/938 [00:22<00:43, 14.26it/s, loss=0.738, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  34%|███▍      | 319/938 [00:22<00:43, 14.26it/s, loss=0.736, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  34%|███▍      | 320/938 [00:22<00:43, 14.25it/s, loss=0.736, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  34%|███▍      | 320/938 [00:22<00:43, 14.25it/s, loss=0.736, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  34%|███▍      | 321/938 [00:22<00:43, 14.26it/s, loss=0.734, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  34%|███▍      | 322/938 [00:22<00:43, 14.26it/s, loss=0.732, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  34%|███▍      | 323/938 [00:22<00:43, 14.26it/s, loss=0.726, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  35%|███▍      | 324/938 [00:22<00:43, 14.26it/s, loss=0.726, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  35%|███▍      | 324/938 [00:22<00:43, 14.26it/s, loss=0.712, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  35%|███▍      | 325/938 [00:22<00:43, 14.23it/s, loss=0.712, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  35%|███▍      | 326/938 [00:22<00:43, 14.23it/s, loss=0.711, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  35%|███▍      | 327/938 [00:22<00:42, 14.24it/s, loss=0.724, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  35%|███▍      | 328/938 [00:23<00:42, 14.23it/s, loss=0.724, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  35%|███▍      | 328/938 [00:23<00:42, 14.23it/s, loss=0.725, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  35%|███▌      | 329/938 [00:23<00:42, 14.23it/s, loss=0.721, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  35%|███▌      | 330/938 [00:23<00:42, 14.23it/s, loss=0.72, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  35%|███▌      | 331/938 [00:23<00:42, 14.23it/s, loss=0.712, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  35%|███▌      | 332/938 [00:23<00:42, 14.22it/s, loss=0.712, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  35%|███▌      | 332/938 [00:23<00:42, 14.22it/s, loss=0.718, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  36%|███▌      | 333/938 [00:23<00:42, 14.22it/s, loss=0.726, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  36%|███▌      | 334/938 [00:23<00:42, 14.22it/s, loss=0.723, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  36%|███▌      | 335/938 [00:23<00:42, 14.23it/s, loss=0.713, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  36%|███▌      | 336/938 [00:23<00:42, 14.22it/s, loss=0.713, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  36%|███▌      | 336/938 [00:23<00:42, 14.22it/s, loss=0.705, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  36%|███▌      | 337/938 [00:23<00:42, 14.20it/s, loss=0.701, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  36%|███▌      | 338/938 [00:23<00:42, 14.21it/s, loss=0.7, v_num=8, val_rmse=0.637, train_rmse=1.230]  
Epoch 1:  36%|███▌      | 339/938 [00:23<00:42, 14.20it/s, loss=0.703, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  36%|███▌      | 340/938 [00:23<00:42, 14.17it/s, loss=0.703, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  36%|███▌      | 340/938 [00:23<00:42, 14.17it/s, loss=0.693, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  36%|███▋      | 341/938 [00:24<00:42, 14.18it/s, loss=0.698, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  36%|███▋      | 342/938 [00:24<00:42, 14.19it/s, loss=0.703, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  37%|███▋      | 343/938 [00:24<00:41, 14.19it/s, loss=0.714, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  37%|███▋      | 344/938 [00:24<00:41, 14.20it/s, loss=0.714, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  37%|███▋      | 344/938 [00:24<00:41, 14.20it/s, loss=0.726, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  37%|███▋      | 345/938 [00:24<00:41, 14.19it/s, loss=0.722, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  37%|███▋      | 346/938 [00:24<00:41, 14.19it/s, loss=0.724, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  37%|███▋      | 347/938 [00:24<00:41, 14.20it/s, loss=0.707, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  37%|███▋      | 348/938 [00:24<00:41, 14.20it/s, loss=0.707, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  37%|███▋      | 348/938 [00:24<00:41, 14.20it/s, loss=0.709, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  37%|███▋      | 349/938 [00:24<00:41, 14.20it/s, loss=0.703, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  37%|███▋      | 350/938 [00:24<00:41, 14.20it/s, loss=0.713, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  37%|███▋      | 351/938 [00:24<00:41, 14.20it/s, loss=0.721, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  38%|███▊      | 352/938 [00:24<00:41, 14.20it/s, loss=0.721, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  38%|███▊      | 352/938 [00:24<00:41, 14.20it/s, loss=0.733, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  38%|███▊      | 353/938 [00:24<00:41, 14.20it/s, loss=0.718, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  38%|███▊      | 354/938 [00:24<00:41, 14.20it/s, loss=0.715, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  38%|███▊      | 355/938 [00:24<00:41, 14.21it/s, loss=0.712, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  38%|███▊      | 356/938 [00:25<00:40, 14.21it/s, loss=0.712, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  38%|███▊      | 356/938 [00:25<00:40, 14.21it/s, loss=0.722, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  38%|███▊      | 357/938 [00:25<00:40, 14.21it/s, loss=0.727, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  38%|███▊      | 358/938 [00:25<00:40, 14.21it/s, loss=0.723, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  38%|███▊      | 359/938 [00:25<00:40, 14.21it/s, loss=0.727, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  38%|███▊      | 360/938 [00:25<00:40, 14.20it/s, loss=0.727, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  38%|███▊      | 360/938 [00:25<00:40, 14.20it/s, loss=0.737, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  38%|███▊      | 361/938 [00:25<00:40, 14.21it/s, loss=0.731, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  39%|███▊      | 362/938 [00:25<00:40, 14.21it/s, loss=0.727, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  39%|███▊      | 363/938 [00:25<00:40, 14.21it/s, loss=0.717, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  39%|███▉      | 364/938 [00:25<00:40, 14.20it/s, loss=0.717, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  39%|███▉      | 364/938 [00:25<00:40, 14.20it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  39%|███▉      | 365/938 [00:25<00:40, 14.21it/s, loss=0.714, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  39%|███▉      | 366/938 [00:25<00:40, 14.21it/s, loss=0.704, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  39%|███▉      | 367/938 [00:25<00:40, 14.21it/s, loss=0.706, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  39%|███▉      | 368/938 [00:25<00:40, 14.21it/s, loss=0.706, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  39%|███▉      | 368/938 [00:25<00:40, 14.21it/s, loss=0.703, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  39%|███▉      | 369/938 [00:25<00:40, 14.21it/s, loss=0.709, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  39%|███▉      | 370/938 [00:26<00:39, 14.21it/s, loss=0.699, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  40%|███▉      | 371/938 [00:26<00:39, 14.21it/s, loss=0.696, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  40%|███▉      | 372/938 [00:26<00:39, 14.22it/s, loss=0.696, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  40%|███▉      | 372/938 [00:26<00:39, 14.22it/s, loss=0.678, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  40%|███▉      | 373/938 [00:26<00:39, 14.22it/s, loss=0.678, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  40%|███▉      | 374/938 [00:26<00:39, 14.23it/s, loss=0.677, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  40%|███▉      | 375/938 [00:26<00:39, 14.22it/s, loss=0.685, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  40%|████      | 376/938 [00:26<00:39, 14.23it/s, loss=0.685, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  40%|████      | 376/938 [00:26<00:39, 14.23it/s, loss=0.681, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  40%|████      | 377/938 [00:26<00:39, 14.23it/s, loss=0.683, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  40%|████      | 378/938 [00:26<00:39, 14.23it/s, loss=0.685, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  40%|████      | 379/938 [00:26<00:39, 14.23it/s, loss=0.683, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  41%|████      | 380/938 [00:26<00:39, 14.23it/s, loss=0.683, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  41%|████      | 380/938 [00:26<00:39, 14.23it/s, loss=0.678, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  41%|████      | 381/938 [00:26<00:39, 14.23it/s, loss=0.68, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  41%|████      | 382/938 [00:26<00:39, 14.23it/s, loss=0.684, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  41%|████      | 383/938 [00:26<00:39, 14.23it/s, loss=0.688, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  41%|████      | 384/938 [00:26<00:38, 14.23it/s, loss=0.688, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  41%|████      | 384/938 [00:26<00:38, 14.23it/s, loss=0.69, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  41%|████      | 385/938 [00:27<00:38, 14.23it/s, loss=0.691, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  41%|████      | 386/938 [00:27<00:38, 14.22it/s, loss=0.698, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  41%|████▏     | 387/938 [00:27<00:38, 14.22it/s, loss=0.693, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  41%|████▏     | 388/938 [00:27<00:38, 14.22it/s, loss=0.693, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  41%|████▏     | 388/938 [00:27<00:38, 14.22it/s, loss=0.688, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  41%|████▏     | 389/938 [00:27<00:38, 14.22it/s, loss=0.682, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  42%|████▏     | 390/938 [00:27<00:38, 14.21it/s, loss=0.681, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  42%|████▏     | 391/938 [00:27<00:38, 14.21it/s, loss=0.675, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  42%|████▏     | 392/938 [00:27<00:38, 14.22it/s, loss=0.675, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  42%|████▏     | 392/938 [00:27<00:38, 14.22it/s, loss=0.671, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  42%|████▏     | 393/938 [00:27<00:38, 14.22it/s, loss=0.672, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  42%|████▏     | 394/938 [00:27<00:38, 14.22it/s, loss=0.679, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  42%|████▏     | 395/938 [00:27<00:38, 14.22it/s, loss=0.679, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  42%|████▏     | 396/938 [00:27<00:38, 14.22it/s, loss=0.679, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  42%|████▏     | 396/938 [00:27<00:38, 14.22it/s, loss=0.68, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  42%|████▏     | 397/938 [00:27<00:38, 14.22it/s, loss=0.684, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  42%|████▏     | 398/938 [00:27<00:37, 14.22it/s, loss=0.691, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  43%|████▎     | 399/938 [00:28<00:37, 14.22it/s, loss=0.689, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  43%|████▎     | 400/938 [00:28<00:37, 14.21it/s, loss=0.689, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  43%|████▎     | 400/938 [00:28<00:37, 14.21it/s, loss=0.698, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  43%|████▎     | 401/938 [00:28<00:37, 14.20it/s, loss=0.696, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  43%|████▎     | 402/938 [00:28<00:37, 14.20it/s, loss=0.684, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  43%|████▎     | 403/938 [00:28<00:37, 14.20it/s, loss=0.686, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  43%|████▎     | 404/938 [00:28<00:37, 14.20it/s, loss=0.686, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  43%|████▎     | 404/938 [00:28<00:37, 14.20it/s, loss=0.679, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  43%|████▎     | 405/938 [00:28<00:37, 14.19it/s, loss=0.679, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  43%|████▎     | 406/938 [00:28<00:37, 14.19it/s, loss=0.682, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  43%|████▎     | 407/938 [00:28<00:37, 14.18it/s, loss=0.692, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  43%|████▎     | 408/938 [00:28<00:37, 14.18it/s, loss=0.692, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  43%|████▎     | 408/938 [00:28<00:37, 14.18it/s, loss=0.701, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  44%|████▎     | 409/938 [00:28<00:37, 14.19it/s, loss=0.702, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  44%|████▎     | 410/938 [00:28<00:37, 14.19it/s, loss=0.701, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  44%|████▍     | 411/938 [00:28<00:37, 14.20it/s, loss=0.705, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  44%|████▍     | 412/938 [00:29<00:37, 14.20it/s, loss=0.705, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  44%|████▍     | 412/938 [00:29<00:37, 14.20it/s, loss=0.713, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  44%|████▍     | 413/938 [00:29<00:36, 14.20it/s, loss=0.713, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  44%|████▍     | 414/938 [00:29<00:36, 14.21it/s, loss=0.712, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  44%|████▍     | 415/938 [00:29<00:36, 14.21it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  44%|████▍     | 416/938 [00:29<00:36, 14.20it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  44%|████▍     | 416/938 [00:29<00:36, 14.20it/s, loss=0.703, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  44%|████▍     | 417/938 [00:29<00:36, 14.20it/s, loss=0.691, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  45%|████▍     | 418/938 [00:29<00:36, 14.20it/s, loss=0.677, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  45%|████▍     | 419/938 [00:29<00:36, 14.20it/s, loss=0.679, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  45%|████▍     | 420/938 [00:29<00:36, 14.20it/s, loss=0.679, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  45%|████▍     | 420/938 [00:29<00:36, 14.20it/s, loss=0.669, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  45%|████▍     | 421/938 [00:29<00:36, 14.19it/s, loss=0.67, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  45%|████▍     | 422/938 [00:29<00:36, 14.19it/s, loss=0.673, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  45%|████▌     | 423/938 [00:29<00:36, 14.19it/s, loss=0.672, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  45%|████▌     | 424/938 [00:29<00:36, 14.19it/s, loss=0.672, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  45%|████▌     | 424/938 [00:29<00:36, 14.19it/s, loss=0.675, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  45%|████▌     | 425/938 [00:29<00:36, 14.20it/s, loss=0.672, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  45%|████▌     | 426/938 [00:30<00:36, 14.18it/s, loss=0.663, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  46%|████▌     | 427/938 [00:30<00:36, 14.19it/s, loss=0.66, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  46%|████▌     | 428/938 [00:30<00:35, 14.18it/s, loss=0.66, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  46%|████▌     | 428/938 [00:30<00:35, 14.18it/s, loss=0.652, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  46%|████▌     | 429/938 [00:30<00:35, 14.18it/s, loss=0.652, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  46%|████▌     | 430/938 [00:30<00:35, 14.17it/s, loss=0.655, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  46%|████▌     | 431/938 [00:30<00:35, 14.18it/s, loss=0.66, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  46%|████▌     | 432/938 [00:30<00:35, 14.17it/s, loss=0.66, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  46%|████▌     | 432/938 [00:30<00:35, 14.17it/s, loss=0.658, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  46%|████▌     | 433/938 [00:30<00:35, 14.17it/s, loss=0.663, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  46%|████▋     | 434/938 [00:30<00:35, 14.17it/s, loss=0.662, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  46%|████▋     | 435/938 [00:30<00:35, 14.17it/s, loss=0.662, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  46%|████▋     | 436/938 [00:30<00:35, 14.17it/s, loss=0.662, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  46%|████▋     | 436/938 [00:30<00:35, 14.17it/s, loss=0.666, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  47%|████▋     | 437/938 [00:30<00:35, 14.16it/s, loss=0.675, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  47%|████▋     | 438/938 [00:30<00:35, 14.17it/s, loss=0.692, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  47%|████▋     | 439/938 [00:30<00:35, 14.16it/s, loss=0.689, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  47%|████▋     | 440/938 [00:31<00:35, 14.16it/s, loss=0.689, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  47%|████▋     | 440/938 [00:31<00:35, 14.16it/s, loss=0.691, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  47%|████▋     | 441/938 [00:31<00:35, 14.16it/s, loss=0.684, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  47%|████▋     | 442/938 [00:31<00:35, 14.15it/s, loss=0.688, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  47%|████▋     | 443/938 [00:31<00:34, 14.16it/s, loss=0.684, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  47%|████▋     | 444/938 [00:31<00:34, 14.15it/s, loss=0.684, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  47%|████▋     | 444/938 [00:31<00:34, 14.15it/s, loss=0.687, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  47%|████▋     | 445/938 [00:31<00:34, 14.16it/s, loss=0.684, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  48%|████▊     | 446/938 [00:31<00:34, 14.16it/s, loss=0.687, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  48%|████▊     | 447/938 [00:31<00:34, 14.16it/s, loss=0.686, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  48%|████▊     | 448/938 [00:31<00:34, 14.17it/s, loss=0.686, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  48%|████▊     | 448/938 [00:31<00:34, 14.17it/s, loss=0.69, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  48%|████▊     | 449/938 [00:31<00:34, 14.17it/s, loss=0.69, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  48%|████▊     | 450/938 [00:31<00:34, 14.17it/s, loss=0.697, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  48%|████▊     | 451/938 [00:31<00:34, 14.18it/s, loss=0.697, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  48%|████▊     | 452/938 [00:31<00:34, 14.19it/s, loss=0.697, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  48%|████▊     | 452/938 [00:31<00:34, 14.19it/s, loss=0.69, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  48%|████▊     | 453/938 [00:31<00:34, 14.19it/s, loss=0.688, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  48%|████▊     | 454/938 [00:32<00:34, 14.19it/s, loss=0.701, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  49%|████▊     | 455/938 [00:32<00:34, 14.19it/s, loss=0.694, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  49%|████▊     | 456/938 [00:32<00:33, 14.19it/s, loss=0.694, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  49%|████▊     | 456/938 [00:32<00:33, 14.19it/s, loss=0.694, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  49%|████▊     | 457/938 [00:32<00:33, 14.19it/s, loss=0.689, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  49%|████▉     | 458/938 [00:32<00:33, 14.19it/s, loss=0.686, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  49%|████▉     | 459/938 [00:32<00:33, 14.19it/s, loss=0.691, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  49%|████▉     | 460/938 [00:32<00:33, 14.19it/s, loss=0.691, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  49%|████▉     | 460/938 [00:32<00:33, 14.19it/s, loss=0.687, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  49%|████▉     | 461/938 [00:32<00:33, 14.19it/s, loss=0.694, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  49%|████▉     | 462/938 [00:32<00:33, 14.19it/s, loss=0.694, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  49%|████▉     | 463/938 [00:32<00:33, 14.19it/s, loss=0.704, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  49%|████▉     | 464/938 [00:32<00:33, 14.19it/s, loss=0.704, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  49%|████▉     | 464/938 [00:32<00:33, 14.19it/s, loss=0.705, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  50%|████▉     | 465/938 [00:32<00:33, 14.18it/s, loss=0.712, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  50%|████▉     | 466/938 [00:32<00:33, 14.19it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230] 
Epoch 1:  50%|████▉     | 467/938 [00:32<00:33, 14.19it/s, loss=0.712, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  50%|████▉     | 468/938 [00:32<00:33, 14.18it/s, loss=0.712, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  50%|████▉     | 468/938 [00:32<00:33, 14.18it/s, loss=0.708, v_num=8, val_rmse=0.637, train_rmse=1.230]
Epoch 1:  50%|█████     | 469/938 [00:33<00:33, 14.20it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230] 

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]
Epoch 1:  50%|█████     | 472/938 [00:33<00:32, 14.25it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:   1%|          | 3/469 [00:00<00:21, 21.75it/s]

Validating:   1%|▏         | 6/469 [00:00<00:21, 21.87it/s]
Epoch 1:  51%|█████     | 476/938 [00:33<00:32, 14.29it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:   2%|▏         | 9/469 [00:00<00:20, 22.67it/s]
Epoch 1:  51%|█████     | 480/938 [00:33<00:31, 14.34it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:   3%|▎         | 12/469 [00:00<00:20, 22.84it/s]
Epoch 1:  52%|█████▏    | 484/938 [00:33<00:31, 14.39it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:   3%|▎         | 15/469 [00:00<00:18, 24.04it/s]

Validating:   4%|▍         | 18/469 [00:00<00:18, 24.06it/s]
Epoch 1:  52%|█████▏    | 488/938 [00:33<00:31, 14.44it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:   4%|▍         | 21/469 [00:00<00:19, 23.51it/s]
Epoch 1:  52%|█████▏    | 492/938 [00:33<00:30, 14.48it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:   5%|▌         | 24/469 [00:01<00:18, 24.29it/s]
Epoch 1:  53%|█████▎    | 496/938 [00:34<00:30, 14.54it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:   6%|▌         | 27/469 [00:01<00:17, 25.04it/s]

Validating:   6%|▋         | 30/469 [00:01<00:17, 25.40it/s]
Epoch 1:  53%|█████▎    | 500/938 [00:34<00:30, 14.59it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:   7%|▋         | 33/469 [00:01<00:17, 25.32it/s]
Epoch 1:  54%|█████▎    | 504/938 [00:34<00:29, 14.64it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:   8%|▊         | 36/469 [00:01<00:16, 25.73it/s]
Epoch 1:  54%|█████▍    | 508/938 [00:34<00:29, 14.69it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:   8%|▊         | 39/469 [00:01<00:16, 25.79it/s]

Validating:   9%|▉         | 42/469 [00:01<00:17, 24.92it/s]
Epoch 1:  55%|█████▍    | 512/938 [00:34<00:28, 14.73it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  10%|▉         | 45/469 [00:01<00:17, 24.40it/s]
Epoch 1:  55%|█████▌    | 516/938 [00:34<00:28, 14.78it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  10%|█         | 48/469 [00:01<00:16, 25.63it/s]
Epoch 1:  55%|█████▌    | 520/938 [00:35<00:28, 14.84it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  11%|█         | 51/469 [00:02<00:16, 25.62it/s]

Validating:  12%|█▏        | 54/469 [00:02<00:16, 25.91it/s]
Epoch 1:  56%|█████▌    | 524/938 [00:35<00:27, 14.88it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  12%|█▏        | 57/469 [00:02<00:17, 23.97it/s]
Epoch 1:  56%|█████▋    | 528/938 [00:35<00:27, 14.91it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  13%|█▎        | 60/469 [00:02<00:16, 24.42it/s]
Epoch 1:  57%|█████▋    | 532/938 [00:35<00:27, 14.96it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  13%|█▎        | 63/469 [00:02<00:16, 25.09it/s]

Validating:  14%|█▍        | 66/469 [00:02<00:15, 25.21it/s]
Epoch 1:  57%|█████▋    | 536/938 [00:35<00:26, 15.01it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  15%|█▍        | 69/469 [00:02<00:15, 25.45it/s]
Epoch 1:  58%|█████▊    | 540/938 [00:35<00:26, 15.06it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  15%|█▌        | 72/469 [00:02<00:16, 24.76it/s]
Epoch 1:  58%|█████▊    | 544/938 [00:36<00:26, 15.10it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  16%|█▌        | 75/469 [00:03<00:15, 25.40it/s]

Validating:  17%|█▋        | 78/469 [00:03<00:15, 25.04it/s]
Epoch 1:  58%|█████▊    | 548/938 [00:36<00:25, 15.14it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  17%|█▋        | 81/469 [00:03<00:15, 24.56it/s]
Epoch 1:  59%|█████▉    | 552/938 [00:36<00:25, 15.19it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  18%|█▊        | 84/469 [00:03<00:16, 23.75it/s]
Epoch 1:  59%|█████▉    | 556/938 [00:36<00:25, 15.21it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  19%|█▊        | 87/469 [00:03<00:16, 22.77it/s]

Validating:  19%|█▉        | 90/469 [00:03<00:15, 24.05it/s]
Epoch 1:  60%|█████▉    | 560/938 [00:36<00:24, 15.26it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  20%|█▉        | 93/469 [00:03<00:15, 24.76it/s]
Epoch 1:  60%|██████    | 564/938 [00:36<00:24, 15.30it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  20%|██        | 96/469 [00:03<00:15, 24.75it/s]
Epoch 1:  61%|██████    | 568/938 [00:37<00:24, 15.35it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  21%|██        | 99/469 [00:04<00:14, 25.41it/s]

Validating:  22%|██▏       | 102/469 [00:04<00:14, 25.09it/s]
Epoch 1:  61%|██████    | 572/938 [00:37<00:23, 15.39it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  22%|██▏       | 105/469 [00:04<00:14, 25.28it/s]
Epoch 1:  61%|██████▏   | 576/938 [00:37<00:23, 15.43it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  23%|██▎       | 108/469 [00:04<00:14, 24.96it/s]
Epoch 1:  62%|██████▏   | 580/938 [00:37<00:23, 15.47it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  24%|██▎       | 111/469 [00:04<00:14, 25.10it/s]

Validating:  24%|██▍       | 114/469 [00:04<00:13, 25.63it/s]
Epoch 1:  62%|██████▏   | 584/938 [00:37<00:22, 15.52it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  25%|██▍       | 117/469 [00:04<00:13, 25.68it/s]
Epoch 1:  63%|██████▎   | 588/938 [00:37<00:22, 15.56it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  26%|██▌       | 120/469 [00:04<00:13, 25.88it/s]
Epoch 1:  63%|██████▎   | 592/938 [00:37<00:22, 15.61it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  26%|██▌       | 123/469 [00:04<00:12, 26.84it/s]

Validating:  27%|██▋       | 126/469 [00:05<00:12, 26.98it/s]
Epoch 1:  64%|██████▎   | 596/938 [00:38<00:21, 15.65it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  28%|██▊       | 129/469 [00:05<00:12, 26.93it/s]
Epoch 1:  64%|██████▍   | 600/938 [00:38<00:21, 15.69it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  28%|██▊       | 132/469 [00:05<00:12, 27.05it/s]
Epoch 1:  64%|██████▍   | 604/938 [00:38<00:21, 15.73it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  29%|██▉       | 135/469 [00:05<00:12, 26.15it/s]

Validating:  29%|██▉       | 138/469 [00:05<00:12, 26.32it/s]
Epoch 1:  65%|██████▍   | 608/938 [00:38<00:20, 15.78it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  30%|███       | 141/469 [00:05<00:13, 24.55it/s]
Epoch 1:  65%|██████▌   | 612/938 [00:38<00:20, 15.80it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  31%|███       | 144/469 [00:05<00:13, 24.05it/s]
Epoch 1:  66%|██████▌   | 616/938 [00:38<00:20, 15.84it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  31%|███▏      | 147/469 [00:05<00:13, 24.65it/s]

Validating:  32%|███▏      | 150/469 [00:06<00:13, 24.26it/s]
Epoch 1:  66%|██████▌   | 620/938 [00:39<00:20, 15.88it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  33%|███▎      | 153/469 [00:06<00:12, 24.69it/s]
Epoch 1:  67%|██████▋   | 624/938 [00:39<00:19, 15.92it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  33%|███▎      | 156/469 [00:06<00:12, 25.20it/s]
Epoch 1:  67%|██████▋   | 628/938 [00:39<00:19, 15.95it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  34%|███▍      | 159/469 [00:06<00:12, 24.23it/s]

Validating:  35%|███▍      | 162/469 [00:06<00:12, 24.46it/s]
Epoch 1:  67%|██████▋   | 632/938 [00:39<00:19, 15.98it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  35%|███▌      | 165/469 [00:06<00:12, 24.29it/s]
Epoch 1:  68%|██████▊   | 636/938 [00:39<00:18, 16.02it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  36%|███▌      | 168/469 [00:06<00:11, 25.14it/s]
Epoch 1:  68%|██████▊   | 640/938 [00:39<00:18, 16.06it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  36%|███▋      | 171/469 [00:06<00:11, 25.17it/s]

Validating:  37%|███▋      | 174/469 [00:06<00:11, 25.17it/s]
Epoch 1:  69%|██████▊   | 644/938 [00:40<00:18, 16.10it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  38%|███▊      | 177/469 [00:07<00:11, 25.79it/s]
Epoch 1:  69%|██████▉   | 648/938 [00:40<00:17, 16.13it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  38%|███▊      | 180/469 [00:07<00:11, 25.56it/s]
Epoch 1:  70%|██████▉   | 652/938 [00:40<00:17, 16.17it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  39%|███▉      | 183/469 [00:07<00:11, 25.16it/s]

Validating:  40%|███▉      | 186/469 [00:07<00:11, 24.32it/s]
Epoch 1:  70%|██████▉   | 656/938 [00:40<00:17, 16.20it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  40%|████      | 189/469 [00:07<00:11, 24.74it/s]
Epoch 1:  70%|███████   | 660/938 [00:40<00:17, 16.23it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  41%|████      | 192/469 [00:07<00:11, 24.49it/s]
Epoch 1:  71%|███████   | 664/938 [00:40<00:16, 16.27it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  42%|████▏     | 195/469 [00:07<00:10, 25.08it/s]

Validating:  42%|████▏     | 198/469 [00:07<00:10, 24.84it/s]
Epoch 1:  71%|███████   | 668/938 [00:40<00:16, 16.30it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  43%|████▎     | 201/469 [00:08<00:10, 24.51it/s]
Epoch 1:  72%|███████▏  | 672/938 [00:41<00:16, 16.33it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  43%|████▎     | 204/469 [00:08<00:10, 24.67it/s]
Epoch 1:  72%|███████▏  | 676/938 [00:41<00:16, 16.37it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  44%|████▍     | 207/469 [00:08<00:10, 25.71it/s]

Validating:  45%|████▍     | 210/469 [00:08<00:10, 25.74it/s]
Epoch 1:  72%|███████▏  | 680/938 [00:41<00:15, 16.41it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  45%|████▌     | 213/469 [00:08<00:10, 25.51it/s]
Epoch 1:  73%|███████▎  | 684/938 [00:41<00:15, 16.44it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  46%|████▌     | 216/469 [00:08<00:10, 25.06it/s]
Epoch 1:  73%|███████▎  | 688/938 [00:41<00:15, 16.47it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  47%|████▋     | 219/469 [00:08<00:10, 24.42it/s]

Validating:  47%|████▋     | 222/469 [00:08<00:09, 24.90it/s]
Epoch 1:  74%|███████▍  | 692/938 [00:41<00:14, 16.50it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  48%|████▊     | 225/469 [00:09<00:09, 24.92it/s]
Epoch 1:  74%|███████▍  | 696/938 [00:42<00:14, 16.53it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  49%|████▊     | 228/469 [00:09<00:10, 23.76it/s]
Epoch 1:  75%|███████▍  | 700/938 [00:42<00:14, 16.56it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  49%|████▉     | 231/469 [00:09<00:09, 24.57it/s]

Validating:  50%|████▉     | 234/469 [00:09<00:09, 25.31it/s]
Epoch 1:  75%|███████▌  | 704/938 [00:42<00:14, 16.60it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  51%|█████     | 237/469 [00:09<00:09, 25.39it/s]
Epoch 1:  75%|███████▌  | 708/938 [00:42<00:13, 16.63it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  51%|█████     | 240/469 [00:09<00:09, 25.23it/s]
Epoch 1:  76%|███████▌  | 712/938 [00:42<00:13, 16.66it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  52%|█████▏    | 243/469 [00:09<00:09, 24.75it/s]

Validating:  52%|█████▏    | 246/469 [00:09<00:08, 24.78it/s]
Epoch 1:  76%|███████▋  | 716/938 [00:42<00:13, 16.69it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  53%|█████▎    | 249/469 [00:09<00:08, 25.50it/s]
Epoch 1:  77%|███████▋  | 720/938 [00:43<00:13, 16.73it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  54%|█████▎    | 252/469 [00:10<00:08, 25.45it/s]
Epoch 1:  77%|███████▋  | 724/938 [00:43<00:12, 16.75it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  54%|█████▍    | 255/469 [00:10<00:08, 25.19it/s]

Validating:  55%|█████▌    | 258/469 [00:10<00:08, 24.65it/s]
Epoch 1:  78%|███████▊  | 728/938 [00:43<00:12, 16.78it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  56%|█████▌    | 261/469 [00:10<00:08, 24.59it/s]
Epoch 1:  78%|███████▊  | 732/938 [00:43<00:12, 16.81it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  56%|█████▋    | 264/469 [00:10<00:08, 24.46it/s]
Epoch 1:  78%|███████▊  | 736/938 [00:43<00:11, 16.84it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  57%|█████▋    | 267/469 [00:10<00:08, 24.49it/s]

Validating:  58%|█████▊    | 270/469 [00:10<00:07, 25.25it/s]
Epoch 1:  79%|███████▉  | 740/938 [00:43<00:11, 16.87it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  58%|█████▊    | 273/469 [00:10<00:07, 25.01it/s]
Epoch 1:  79%|███████▉  | 744/938 [00:44<00:11, 16.90it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  59%|█████▉    | 276/469 [00:11<00:07, 25.31it/s]
Epoch 1:  80%|███████▉  | 748/938 [00:44<00:11, 16.93it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  59%|█████▉    | 279/469 [00:11<00:07, 25.46it/s]

Validating:  60%|██████    | 282/469 [00:11<00:07, 25.78it/s]
Epoch 1:  80%|████████  | 752/938 [00:44<00:10, 16.97it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  61%|██████    | 285/469 [00:11<00:07, 25.68it/s]
Epoch 1:  81%|████████  | 756/938 [00:44<00:10, 17.00it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  61%|██████▏   | 288/469 [00:11<00:07, 25.53it/s]
Epoch 1:  81%|████████  | 760/938 [00:44<00:10, 17.02it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  62%|██████▏   | 291/469 [00:11<00:07, 25.38it/s]

Validating:  63%|██████▎   | 294/469 [00:11<00:06, 25.78it/s]
Epoch 1:  81%|████████▏ | 764/938 [00:44<00:10, 17.06it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  63%|██████▎   | 297/469 [00:11<00:06, 24.86it/s]
Epoch 1:  82%|████████▏ | 768/938 [00:44<00:09, 17.08it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  64%|██████▍   | 300/469 [00:12<00:06, 25.22it/s]
Epoch 1:  82%|████████▏ | 772/938 [00:45<00:09, 17.11it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  65%|██████▍   | 303/469 [00:12<00:06, 25.22it/s]

Validating:  65%|██████▌   | 306/469 [00:12<00:06, 25.50it/s]
Epoch 1:  83%|████████▎ | 776/938 [00:45<00:09, 17.14it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  66%|██████▌   | 309/469 [00:12<00:06, 24.75it/s]
Epoch 1:  83%|████████▎ | 780/938 [00:45<00:09, 17.17it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  67%|██████▋   | 312/469 [00:12<00:06, 24.57it/s]
Epoch 1:  84%|████████▎ | 784/938 [00:45<00:08, 17.19it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  67%|██████▋   | 315/469 [00:12<00:05, 25.73it/s]

Validating:  68%|██████▊   | 318/469 [00:12<00:05, 25.39it/s]
Epoch 1:  84%|████████▍ | 788/938 [00:45<00:08, 17.22it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  68%|██████▊   | 321/469 [00:12<00:05, 25.91it/s]
Epoch 1:  84%|████████▍ | 792/938 [00:45<00:08, 17.25it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  69%|██████▉   | 324/469 [00:12<00:05, 25.39it/s]
Epoch 1:  85%|████████▍ | 796/938 [00:46<00:08, 17.28it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  70%|██████▉   | 327/469 [00:13<00:05, 25.04it/s]

Validating:  70%|███████   | 330/469 [00:13<00:05, 24.19it/s]
Epoch 1:  85%|████████▌ | 800/938 [00:46<00:07, 17.30it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  71%|███████   | 333/469 [00:13<00:05, 24.48it/s]
Epoch 1:  86%|████████▌ | 804/938 [00:46<00:07, 17.33it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  72%|███████▏  | 336/469 [00:13<00:05, 24.95it/s]
Epoch 1:  86%|████████▌ | 808/938 [00:46<00:07, 17.36it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  72%|███████▏  | 339/469 [00:13<00:05, 24.07it/s]

Validating:  73%|███████▎  | 342/469 [00:13<00:05, 24.44it/s]
Epoch 1:  87%|████████▋ | 812/938 [00:46<00:07, 17.38it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  74%|███████▎  | 345/469 [00:13<00:05, 24.49it/s]
Epoch 1:  87%|████████▋ | 816/938 [00:46<00:07, 17.40it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  74%|███████▍  | 348/469 [00:13<00:04, 25.79it/s]
Epoch 1:  87%|████████▋ | 820/938 [00:47<00:06, 17.43it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  75%|███████▍  | 351/469 [00:14<00:04, 25.53it/s]

Validating:  75%|███████▌  | 354/469 [00:14<00:04, 25.39it/s]
Epoch 1:  88%|████████▊ | 824/938 [00:47<00:06, 17.46it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  76%|███████▌  | 357/469 [00:14<00:04, 25.22it/s]
Epoch 1:  88%|████████▊ | 828/938 [00:47<00:06, 17.48it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  77%|███████▋  | 360/469 [00:14<00:04, 25.26it/s]
Epoch 1:  89%|████████▊ | 832/938 [00:47<00:06, 17.51it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  77%|███████▋  | 363/469 [00:14<00:04, 25.33it/s]

Validating:  78%|███████▊  | 366/469 [00:14<00:03, 26.10it/s]
Epoch 1:  89%|████████▉ | 836/938 [00:47<00:05, 17.54it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  79%|███████▊  | 369/469 [00:14<00:03, 26.06it/s]
Epoch 1:  90%|████████▉ | 840/938 [00:47<00:05, 17.57it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  79%|███████▉  | 372/469 [00:14<00:03, 25.90it/s]
Epoch 1:  90%|████████▉ | 844/938 [00:47<00:05, 17.60it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  80%|███████▉  | 375/469 [00:14<00:03, 26.51it/s]

Validating:  81%|████████  | 378/469 [00:15<00:03, 25.88it/s]
Epoch 1:  90%|█████████ | 848/938 [00:48<00:05, 17.62it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  81%|████████  | 381/469 [00:15<00:03, 25.03it/s]
Epoch 1:  91%|█████████ | 852/938 [00:48<00:04, 17.65it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  82%|████████▏ | 384/469 [00:15<00:03, 24.10it/s]
Epoch 1:  91%|█████████▏| 856/938 [00:48<00:04, 17.66it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  83%|████████▎ | 387/469 [00:15<00:03, 24.80it/s]

Validating:  83%|████████▎ | 390/469 [00:15<00:03, 24.24it/s]
Epoch 1:  92%|█████████▏| 860/938 [00:48<00:04, 17.69it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  84%|████████▍ | 393/469 [00:15<00:03, 24.16it/s]
Epoch 1:  92%|█████████▏| 864/938 [00:48<00:04, 17.71it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  84%|████████▍ | 396/469 [00:15<00:03, 24.00it/s]
Epoch 1:  93%|█████████▎| 868/938 [00:48<00:03, 17.73it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  85%|████████▌ | 399/469 [00:15<00:02, 24.73it/s]

Validating:  86%|████████▌ | 402/469 [00:16<00:02, 25.50it/s]
Epoch 1:  93%|█████████▎| 872/938 [00:49<00:03, 17.76it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  86%|████████▋ | 405/469 [00:16<00:02, 24.18it/s]
Epoch 1:  93%|█████████▎| 876/938 [00:49<00:03, 17.78it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  87%|████████▋ | 408/469 [00:16<00:02, 25.20it/s]
Epoch 1:  94%|█████████▍| 880/938 [00:49<00:03, 17.81it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  88%|████████▊ | 411/469 [00:16<00:02, 25.83it/s]

Validating:  88%|████████▊ | 414/469 [00:16<00:02, 25.86it/s]
Epoch 1:  94%|█████████▍| 884/938 [00:49<00:03, 17.83it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  89%|████████▉ | 417/469 [00:16<00:02, 25.64it/s]
Epoch 1:  95%|█████████▍| 888/938 [00:49<00:02, 17.85it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  90%|████████▉ | 420/469 [00:16<00:01, 25.16it/s]
Epoch 1:  95%|█████████▌| 892/938 [00:49<00:02, 17.87it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  90%|█████████ | 423/469 [00:16<00:01, 24.69it/s]

Validating:  91%|█████████ | 426/469 [00:17<00:01, 24.62it/s]
Epoch 1:  96%|█████████▌| 896/938 [00:50<00:02, 17.90it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  91%|█████████▏| 429/469 [00:17<00:01, 25.22it/s]
Epoch 1:  96%|█████████▌| 900/938 [00:50<00:02, 17.92it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  92%|█████████▏| 432/469 [00:17<00:01, 24.43it/s]
Epoch 1:  96%|█████████▋| 904/938 [00:50<00:01, 17.94it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  93%|█████████▎| 435/469 [00:17<00:01, 24.71it/s]

Validating:  93%|█████████▎| 438/469 [00:17<00:01, 25.41it/s]
Epoch 1:  97%|█████████▋| 908/938 [00:50<00:01, 17.97it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  94%|█████████▍| 441/469 [00:17<00:01, 26.47it/s]
Epoch 1:  97%|█████████▋| 912/938 [00:50<00:01, 18.00it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  95%|█████████▍| 444/469 [00:17<00:00, 26.93it/s]
Epoch 1:  98%|█████████▊| 916/938 [00:50<00:01, 18.02it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  95%|█████████▌| 447/469 [00:17<00:00, 25.47it/s]

Validating:  96%|█████████▌| 450/469 [00:17<00:00, 25.16it/s]
Epoch 1:  98%|█████████▊| 920/938 [00:51<00:00, 18.04it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  97%|█████████▋| 453/469 [00:18<00:00, 24.59it/s]
Epoch 1:  99%|█████████▊| 924/938 [00:51<00:00, 18.05it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  97%|█████████▋| 456/469 [00:18<00:00, 24.59it/s]
Epoch 1:  99%|█████████▉| 928/938 [00:51<00:00, 18.08it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  98%|█████████▊| 459/469 [00:18<00:00, 24.74it/s]

Validating:  99%|█████████▊| 462/469 [00:18<00:00, 25.04it/s]
Epoch 1:  99%|█████████▉| 932/938 [00:51<00:00, 18.10it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating:  99%|█████████▉| 465/469 [00:18<00:00, 23.80it/s]
Epoch 1: 100%|█████████▉| 936/938 [00:51<00:00, 18.12it/s, loss=0.71, v_num=8, val_rmse=0.637, train_rmse=1.230]

Validating: 100%|█████████▉| 468/469 [00:18<00:00, 23.80it/s]
Epoch 1: 100%|██████████| 938/938 [00:51<00:00, 18.11it/s, loss=0.71, v_num=8, val_rmse=0.561, train_rmse=1.230]

                                                             
Epoch 1: 100%|██████████| 938/938 [00:51<00:00, 18.10it/s, loss=0.71, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 1:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.71, v_num=8, val_rmse=0.561, train_rmse=0.739]          
Epoch 2:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.71, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   0%|          | 1/938 [00:00<01:23, 11.23it/s, loss=0.7, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   0%|          | 2/938 [00:00<01:07, 13.80it/s, loss=0.698, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   0%|          | 3/938 [00:00<01:08, 13.56it/s, loss=0.702, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   0%|          | 4/938 [00:00<01:05, 14.18it/s, loss=0.702, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   0%|          | 4/938 [00:00<01:05, 14.16it/s, loss=0.699, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   1%|          | 5/938 [00:00<01:06, 14.05it/s, loss=0.688, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   1%|          | 6/938 [00:00<01:04, 14.45it/s, loss=0.694, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   1%|          | 7/938 [00:00<01:02, 14.83it/s, loss=0.693, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   1%|          | 8/938 [00:00<01:02, 14.87it/s, loss=0.693, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   1%|          | 8/938 [00:00<01:02, 14.85it/s, loss=0.693, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   1%|          | 9/938 [00:00<01:01, 15.05it/s, loss=0.687, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   1%|          | 10/938 [00:00<01:02, 14.84it/s, loss=0.69, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   1%|          | 11/938 [00:00<01:03, 14.54it/s, loss=0.692, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   1%|▏         | 12/938 [00:00<01:05, 14.22it/s, loss=0.692, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   1%|▏         | 12/938 [00:00<01:05, 14.21it/s, loss=0.69, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:   1%|▏         | 13/938 [00:00<01:04, 14.33it/s, loss=0.689, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   1%|▏         | 14/938 [00:00<01:05, 14.11it/s, loss=0.678, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   2%|▏         | 15/938 [00:01<01:04, 14.24it/s, loss=0.676, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   2%|▏         | 16/938 [00:01<01:03, 14.42it/s, loss=0.676, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   2%|▏         | 16/938 [00:01<01:03, 14.41it/s, loss=0.672, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   2%|▏         | 17/938 [00:01<01:04, 14.25it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   2%|▏         | 18/938 [00:01<01:04, 14.16it/s, loss=0.669, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   2%|▏         | 19/938 [00:01<01:04, 14.14it/s, loss=0.669, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   2%|▏         | 20/938 [00:01<01:04, 14.22it/s, loss=0.669, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   2%|▏         | 20/938 [00:01<01:04, 14.22it/s, loss=0.665, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   2%|▏         | 21/938 [00:01<01:05, 14.07it/s, loss=0.667, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   2%|▏         | 22/938 [00:01<01:04, 14.13it/s, loss=0.669, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   2%|▏         | 23/938 [00:01<01:04, 14.14it/s, loss=0.667, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   3%|▎         | 24/938 [00:01<01:04, 14.15it/s, loss=0.667, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   3%|▎         | 24/938 [00:01<01:04, 14.14it/s, loss=0.67, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:   3%|▎         | 25/938 [00:01<01:04, 14.15it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   3%|▎         | 26/938 [00:01<01:04, 14.15it/s, loss=0.681, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   3%|▎         | 27/938 [00:01<01:04, 14.11it/s, loss=0.682, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   3%|▎         | 28/938 [00:01<01:04, 14.03it/s, loss=0.682, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   3%|▎         | 28/938 [00:01<01:04, 14.02it/s, loss=0.684, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   3%|▎         | 29/938 [00:02<01:05, 13.93it/s, loss=0.684, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   3%|▎         | 30/938 [00:02<01:05, 13.97it/s, loss=0.682, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   3%|▎         | 31/938 [00:02<01:05, 13.92it/s, loss=0.686, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   3%|▎         | 32/938 [00:02<01:04, 13.94it/s, loss=0.686, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   3%|▎         | 32/938 [00:02<01:04, 13.94it/s, loss=0.694, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   4%|▎         | 33/938 [00:02<01:04, 14.05it/s, loss=0.692, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   4%|▎         | 34/938 [00:02<01:04, 14.04it/s, loss=0.701, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   4%|▎         | 35/938 [00:02<01:04, 14.10it/s, loss=0.7, v_num=8, val_rmse=0.561, train_rmse=0.739]  
Epoch 2:   4%|▍         | 36/938 [00:02<01:04, 14.02it/s, loss=0.7, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   4%|▍         | 36/938 [00:02<01:04, 14.01it/s, loss=0.702, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   4%|▍         | 37/938 [00:02<01:04, 14.02it/s, loss=0.699, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   4%|▍         | 38/938 [00:02<01:04, 13.89it/s, loss=0.703, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   4%|▍         | 39/938 [00:02<01:04, 13.94it/s, loss=0.698, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   4%|▍         | 40/938 [00:02<01:04, 13.89it/s, loss=0.698, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   4%|▍         | 40/938 [00:02<01:04, 13.89it/s, loss=0.695, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   4%|▍         | 41/938 [00:02<01:04, 13.87it/s, loss=0.693, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   4%|▍         | 42/938 [00:03<01:04, 13.89it/s, loss=0.689, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   5%|▍         | 43/938 [00:03<01:04, 13.87it/s, loss=0.691, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   5%|▍         | 44/938 [00:03<01:04, 13.91it/s, loss=0.691, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   5%|▍         | 44/938 [00:03<01:04, 13.91it/s, loss=0.682, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   5%|▍         | 45/938 [00:03<01:04, 13.93it/s, loss=0.688, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   5%|▍         | 46/938 [00:03<01:03, 13.98it/s, loss=0.678, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   5%|▌         | 47/938 [00:03<01:03, 14.00it/s, loss=0.676, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   5%|▌         | 48/938 [00:03<01:03, 14.03it/s, loss=0.676, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   5%|▌         | 48/938 [00:03<01:03, 14.03it/s, loss=0.68, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:   5%|▌         | 49/938 [00:03<01:03, 14.08it/s, loss=0.681, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   5%|▌         | 50/938 [00:03<01:03, 14.09it/s, loss=0.67, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:   5%|▌         | 51/938 [00:03<01:02, 14.13it/s, loss=0.666, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   6%|▌         | 52/938 [00:03<01:02, 14.07it/s, loss=0.666, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   6%|▌         | 52/938 [00:03<01:02, 14.07it/s, loss=0.658, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   6%|▌         | 53/938 [00:03<01:03, 14.04it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   6%|▌         | 54/938 [00:03<01:02, 14.04it/s, loss=0.66, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:   6%|▌         | 55/938 [00:03<01:02, 14.04it/s, loss=0.653, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   6%|▌         | 56/938 [00:03<01:02, 14.04it/s, loss=0.653, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   6%|▌         | 56/938 [00:03<01:02, 14.04it/s, loss=0.649, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   6%|▌         | 57/938 [00:04<01:02, 14.05it/s, loss=0.655, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   6%|▌         | 58/938 [00:04<01:02, 14.06it/s, loss=0.655, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   6%|▋         | 59/938 [00:04<01:02, 14.15it/s, loss=0.659, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   6%|▋         | 60/938 [00:04<01:02, 14.13it/s, loss=0.659, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   6%|▋         | 60/938 [00:04<01:02, 14.12it/s, loss=0.665, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   7%|▋         | 61/938 [00:04<01:02, 14.13it/s, loss=0.665, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   7%|▋         | 62/938 [00:04<01:01, 14.19it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   7%|▋         | 63/938 [00:04<01:01, 14.20it/s, loss=0.668, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   7%|▋         | 64/938 [00:04<01:01, 14.23it/s, loss=0.668, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   7%|▋         | 64/938 [00:04<01:01, 14.23it/s, loss=0.669, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   7%|▋         | 65/938 [00:04<01:01, 14.24it/s, loss=0.659, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   7%|▋         | 66/938 [00:04<01:01, 14.25it/s, loss=0.66, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:   7%|▋         | 67/938 [00:04<01:00, 14.28it/s, loss=0.663, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   7%|▋         | 68/938 [00:04<01:00, 14.29it/s, loss=0.663, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   7%|▋         | 68/938 [00:04<01:00, 14.29it/s, loss=0.661, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   7%|▋         | 69/938 [00:04<01:00, 14.34it/s, loss=0.659, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   7%|▋         | 70/938 [00:04<01:00, 14.30it/s, loss=0.659, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   8%|▊         | 71/938 [00:04<01:00, 14.29it/s, loss=0.658, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   8%|▊         | 72/938 [00:05<01:00, 14.32it/s, loss=0.658, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   8%|▊         | 72/938 [00:05<01:00, 14.31it/s, loss=0.658, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   8%|▊         | 73/938 [00:05<01:00, 14.27it/s, loss=0.658, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   8%|▊         | 74/938 [00:05<01:00, 14.28it/s, loss=0.654, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   8%|▊         | 75/938 [00:05<01:00, 14.30it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   8%|▊         | 76/938 [00:05<01:00, 14.29it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   8%|▊         | 76/938 [00:05<01:00, 14.29it/s, loss=0.663, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   8%|▊         | 77/938 [00:05<01:00, 14.27it/s, loss=0.663, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   8%|▊         | 78/938 [00:05<01:00, 14.31it/s, loss=0.668, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   8%|▊         | 79/938 [00:05<01:00, 14.28it/s, loss=0.666, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   9%|▊         | 80/938 [00:05<01:00, 14.29it/s, loss=0.666, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   9%|▊         | 80/938 [00:05<01:00, 14.29it/s, loss=0.667, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   9%|▊         | 81/938 [00:05<01:00, 14.28it/s, loss=0.67, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:   9%|▊         | 82/938 [00:05<00:59, 14.30it/s, loss=0.66, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   9%|▉         | 83/938 [00:05<00:59, 14.31it/s, loss=0.67, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   9%|▉         | 84/938 [00:05<00:59, 14.29it/s, loss=0.67, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   9%|▉         | 84/938 [00:05<00:59, 14.29it/s, loss=0.682, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   9%|▉         | 85/938 [00:05<01:00, 14.20it/s, loss=0.683, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   9%|▉         | 86/938 [00:06<01:00, 14.20it/s, loss=0.674, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   9%|▉         | 87/938 [00:06<01:00, 14.18it/s, loss=0.672, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   9%|▉         | 88/938 [00:06<00:59, 14.19it/s, loss=0.672, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   9%|▉         | 88/938 [00:06<00:59, 14.19it/s, loss=0.679, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:   9%|▉         | 89/938 [00:06<00:59, 14.21it/s, loss=0.684, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  10%|▉         | 90/938 [00:06<00:59, 14.18it/s, loss=0.696, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  10%|▉         | 91/938 [00:06<00:59, 14.17it/s, loss=0.708, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  10%|▉         | 92/938 [00:06<00:59, 14.17it/s, loss=0.708, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  10%|▉         | 92/938 [00:06<00:59, 14.17it/s, loss=0.709, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  10%|▉         | 93/938 [00:06<00:59, 14.19it/s, loss=0.717, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  10%|█         | 94/938 [00:06<00:59, 14.18it/s, loss=0.719, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  10%|█         | 95/938 [00:06<00:59, 14.17it/s, loss=0.715, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  10%|█         | 96/938 [00:06<00:59, 14.14it/s, loss=0.715, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  10%|█         | 96/938 [00:06<00:59, 14.14it/s, loss=0.713, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  10%|█         | 97/938 [00:06<00:59, 14.15it/s, loss=0.714, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  10%|█         | 98/938 [00:06<00:59, 14.16it/s, loss=0.705, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  11%|█         | 99/938 [00:06<00:59, 14.14it/s, loss=0.708, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  11%|█         | 100/938 [00:07<00:59, 14.12it/s, loss=0.708, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  11%|█         | 100/938 [00:07<00:59, 14.12it/s, loss=0.703, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  11%|█         | 101/938 [00:07<00:59, 14.13it/s, loss=0.708, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  11%|█         | 102/938 [00:07<00:59, 14.15it/s, loss=0.709, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  11%|█         | 103/938 [00:07<00:58, 14.15it/s, loss=0.708, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  11%|█         | 104/938 [00:07<00:58, 14.16it/s, loss=0.708, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  11%|█         | 104/938 [00:07<00:58, 14.16it/s, loss=0.693, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  11%|█         | 105/938 [00:07<00:58, 14.16it/s, loss=0.698, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  11%|█▏        | 106/938 [00:07<00:58, 14.19it/s, loss=0.704, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  11%|█▏        | 107/938 [00:07<00:58, 14.18it/s, loss=0.698, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  12%|█▏        | 108/938 [00:07<00:58, 14.17it/s, loss=0.698, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  12%|█▏        | 108/938 [00:07<00:58, 14.17it/s, loss=0.693, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  12%|█▏        | 109/938 [00:07<00:58, 14.21it/s, loss=0.685, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  12%|█▏        | 110/938 [00:07<00:58, 14.19it/s, loss=0.676, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  12%|█▏        | 111/938 [00:07<00:58, 14.21it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  12%|█▏        | 112/938 [00:07<00:58, 14.22it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  12%|█▏        | 112/938 [00:07<00:58, 14.22it/s, loss=0.657, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  12%|█▏        | 113/938 [00:07<00:58, 14.22it/s, loss=0.655, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  12%|█▏        | 114/938 [00:08<00:57, 14.21it/s, loss=0.663, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  12%|█▏        | 115/938 [00:08<00:57, 14.21it/s, loss=0.664, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  12%|█▏        | 116/938 [00:08<00:57, 14.21it/s, loss=0.664, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  12%|█▏        | 116/938 [00:08<00:57, 14.21it/s, loss=0.667, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  12%|█▏        | 117/938 [00:08<00:57, 14.20it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  13%|█▎        | 118/938 [00:08<00:57, 14.20it/s, loss=0.664, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  13%|█▎        | 119/938 [00:08<00:57, 14.17it/s, loss=0.668, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  13%|█▎        | 120/938 [00:08<00:57, 14.17it/s, loss=0.668, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  13%|█▎        | 120/938 [00:08<00:57, 14.17it/s, loss=0.678, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  13%|█▎        | 121/938 [00:08<00:57, 14.15it/s, loss=0.666, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  13%|█▎        | 122/938 [00:08<00:57, 14.11it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  13%|█▎        | 123/938 [00:08<00:57, 14.10it/s, loss=0.663, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  13%|█▎        | 124/938 [00:08<00:57, 14.07it/s, loss=0.663, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  13%|█▎        | 124/938 [00:08<00:57, 14.06it/s, loss=0.667, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  13%|█▎        | 125/938 [00:08<00:57, 14.04it/s, loss=0.666, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  13%|█▎        | 126/938 [00:08<00:57, 14.05it/s, loss=0.666, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  14%|█▎        | 127/938 [00:09<00:57, 14.08it/s, loss=0.67, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:  14%|█▎        | 128/938 [00:09<00:57, 14.07it/s, loss=0.67, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  14%|█▎        | 128/938 [00:09<00:57, 14.07it/s, loss=0.661, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  14%|█▍        | 129/938 [00:09<00:57, 14.08it/s, loss=0.656, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  14%|█▍        | 130/938 [00:09<00:57, 14.08it/s, loss=0.655, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  14%|█▍        | 131/938 [00:09<00:57, 14.08it/s, loss=0.657, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  14%|█▍        | 132/938 [00:09<00:57, 14.10it/s, loss=0.657, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  14%|█▍        | 132/938 [00:09<00:57, 14.10it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  14%|█▍        | 133/938 [00:09<00:57, 14.08it/s, loss=0.654, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  14%|█▍        | 134/938 [00:09<00:57, 14.09it/s, loss=0.644, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  14%|█▍        | 135/938 [00:09<00:56, 14.09it/s, loss=0.644, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  14%|█▍        | 136/938 [00:09<00:56, 14.08it/s, loss=0.644, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  14%|█▍        | 136/938 [00:09<00:56, 14.08it/s, loss=0.647, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  15%|█▍        | 137/938 [00:09<00:56, 14.07it/s, loss=0.653, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  15%|█▍        | 138/938 [00:09<00:56, 14.08it/s, loss=0.651, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  15%|█▍        | 139/938 [00:09<00:56, 14.07it/s, loss=0.657, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  15%|█▍        | 140/938 [00:09<00:56, 14.10it/s, loss=0.657, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  15%|█▍        | 140/938 [00:09<00:56, 14.10it/s, loss=0.655, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  15%|█▌        | 141/938 [00:10<00:56, 14.01it/s, loss=0.663, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  15%|█▌        | 142/938 [00:10<00:56, 14.02it/s, loss=0.661, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  15%|█▌        | 143/938 [00:10<00:56, 14.02it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  15%|█▌        | 144/938 [00:10<00:56, 14.02it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  15%|█▌        | 144/938 [00:10<00:56, 14.02it/s, loss=0.664, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  15%|█▌        | 145/938 [00:10<00:56, 14.01it/s, loss=0.655, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  16%|█▌        | 146/938 [00:10<00:56, 14.01it/s, loss=0.663, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  16%|█▌        | 147/938 [00:10<00:56, 14.03it/s, loss=0.668, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  16%|█▌        | 148/938 [00:10<00:56, 14.02it/s, loss=0.668, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  16%|█▌        | 148/938 [00:10<00:56, 14.02it/s, loss=0.674, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  16%|█▌        | 149/938 [00:10<00:56, 14.03it/s, loss=0.676, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  16%|█▌        | 150/938 [00:10<00:56, 14.04it/s, loss=0.681, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  16%|█▌        | 151/938 [00:10<00:56, 14.04it/s, loss=0.682, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  16%|█▌        | 152/938 [00:10<00:55, 14.06it/s, loss=0.682, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  16%|█▌        | 152/938 [00:10<00:55, 14.06it/s, loss=0.683, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  16%|█▋        | 153/938 [00:10<00:55, 14.06it/s, loss=0.689, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  16%|█▋        | 154/938 [00:10<00:55, 14.07it/s, loss=0.689, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  17%|█▋        | 155/938 [00:11<00:55, 14.07it/s, loss=0.688, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  17%|█▋        | 156/938 [00:11<00:55, 14.06it/s, loss=0.688, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  17%|█▋        | 156/938 [00:11<00:55, 14.06it/s, loss=0.686, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  17%|█▋        | 157/938 [00:11<00:55, 14.05it/s, loss=0.688, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  17%|█▋        | 158/938 [00:11<00:55, 14.07it/s, loss=0.685, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  17%|█▋        | 159/938 [00:11<00:55, 14.06it/s, loss=0.674, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  17%|█▋        | 160/938 [00:11<00:55, 14.07it/s, loss=0.674, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  17%|█▋        | 160/938 [00:11<00:55, 14.07it/s, loss=0.672, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  17%|█▋        | 161/938 [00:11<00:55, 14.07it/s, loss=0.67, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:  17%|█▋        | 162/938 [00:11<00:55, 14.04it/s, loss=0.673, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  17%|█▋        | 163/938 [00:11<00:55, 14.06it/s, loss=0.684, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  17%|█▋        | 164/938 [00:11<00:54, 14.07it/s, loss=0.684, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  17%|█▋        | 164/938 [00:11<00:55, 14.07it/s, loss=0.682, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  18%|█▊        | 165/938 [00:11<00:54, 14.07it/s, loss=0.688, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  18%|█▊        | 166/938 [00:11<00:54, 14.07it/s, loss=0.677, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  18%|█▊        | 167/938 [00:11<00:54, 14.06it/s, loss=0.672, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  18%|█▊        | 168/938 [00:11<00:54, 14.06it/s, loss=0.672, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  18%|█▊        | 168/938 [00:11<00:54, 14.06it/s, loss=0.681, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  18%|█▊        | 169/938 [00:12<00:54, 14.06it/s, loss=0.685, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  18%|█▊        | 170/938 [00:12<00:54, 14.07it/s, loss=0.677, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  18%|█▊        | 171/938 [00:12<00:54, 14.09it/s, loss=0.682, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  18%|█▊        | 172/938 [00:12<00:54, 14.08it/s, loss=0.682, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  18%|█▊        | 172/938 [00:12<00:54, 14.08it/s, loss=0.683, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  18%|█▊        | 173/938 [00:12<00:54, 14.06it/s, loss=0.681, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  19%|█▊        | 174/938 [00:12<00:54, 14.08it/s, loss=0.685, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  19%|█▊        | 175/938 [00:12<00:54, 14.08it/s, loss=0.69, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:  19%|█▉        | 176/938 [00:12<00:54, 14.07it/s, loss=0.69, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  19%|█▉        | 176/938 [00:12<00:54, 14.07it/s, loss=0.685, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  19%|█▉        | 177/938 [00:12<00:54, 14.09it/s, loss=0.675, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  19%|█▉        | 178/938 [00:12<00:53, 14.09it/s, loss=0.678, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  19%|█▉        | 179/938 [00:12<00:53, 14.09it/s, loss=0.682, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  19%|█▉        | 180/938 [00:12<00:53, 14.10it/s, loss=0.682, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  19%|█▉        | 180/938 [00:12<00:53, 14.10it/s, loss=0.68, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:  19%|█▉        | 181/938 [00:12<00:53, 14.11it/s, loss=0.68, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  19%|█▉        | 182/938 [00:12<00:53, 14.10it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  20%|█▉        | 183/938 [00:12<00:53, 14.10it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  20%|█▉        | 184/938 [00:13<00:53, 14.11it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  20%|█▉        | 184/938 [00:13<00:53, 14.11it/s, loss=0.665, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  20%|█▉        | 185/938 [00:13<00:53, 14.12it/s, loss=0.664, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  20%|█▉        | 186/938 [00:13<00:53, 14.12it/s, loss=0.665, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  20%|█▉        | 187/938 [00:13<00:53, 14.13it/s, loss=0.665, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  20%|██        | 188/938 [00:13<00:53, 14.15it/s, loss=0.665, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  20%|██        | 188/938 [00:13<00:53, 14.14it/s, loss=0.657, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  20%|██        | 189/938 [00:13<00:52, 14.14it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  20%|██        | 190/938 [00:13<00:52, 14.14it/s, loss=0.666, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  20%|██        | 191/938 [00:13<00:52, 14.12it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  20%|██        | 192/938 [00:13<00:52, 14.13it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  20%|██        | 192/938 [00:13<00:52, 14.13it/s, loss=0.666, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  21%|██        | 193/938 [00:13<00:52, 14.12it/s, loss=0.659, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  21%|██        | 194/938 [00:13<00:52, 14.12it/s, loss=0.652, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  21%|██        | 195/938 [00:13<00:52, 14.13it/s, loss=0.649, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  21%|██        | 196/938 [00:13<00:52, 14.13it/s, loss=0.649, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  21%|██        | 196/938 [00:13<00:52, 14.13it/s, loss=0.651, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  21%|██        | 197/938 [00:13<00:52, 14.13it/s, loss=0.656, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  21%|██        | 198/938 [00:14<00:52, 14.09it/s, loss=0.655, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  21%|██        | 199/938 [00:14<00:52, 14.09it/s, loss=0.656, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  21%|██▏       | 200/938 [00:14<00:52, 14.09it/s, loss=0.656, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  21%|██▏       | 200/938 [00:14<00:52, 14.09it/s, loss=0.666, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  21%|██▏       | 201/938 [00:14<00:52, 14.09it/s, loss=0.664, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  22%|██▏       | 202/938 [00:14<00:52, 14.08it/s, loss=0.675, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  22%|██▏       | 203/938 [00:14<00:52, 14.08it/s, loss=0.673, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  22%|██▏       | 204/938 [00:14<00:52, 14.08it/s, loss=0.673, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  22%|██▏       | 204/938 [00:14<00:52, 14.08it/s, loss=0.676, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  22%|██▏       | 205/938 [00:14<00:52, 14.09it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  22%|██▏       | 206/938 [00:14<00:51, 14.09it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  22%|██▏       | 207/938 [00:14<00:51, 14.09it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  22%|██▏       | 208/938 [00:14<00:51, 14.10it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  22%|██▏       | 208/938 [00:14<00:51, 14.10it/s, loss=0.669, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  22%|██▏       | 209/938 [00:14<00:51, 14.12it/s, loss=0.673, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  22%|██▏       | 210/938 [00:14<00:51, 14.12it/s, loss=0.675, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  22%|██▏       | 211/938 [00:14<00:51, 14.12it/s, loss=0.677, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  23%|██▎       | 212/938 [00:15<00:51, 14.12it/s, loss=0.677, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  23%|██▎       | 212/938 [00:15<00:51, 14.12it/s, loss=0.676, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  23%|██▎       | 213/938 [00:15<00:51, 14.11it/s, loss=0.679, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  23%|██▎       | 214/938 [00:15<00:51, 14.10it/s, loss=0.679, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  23%|██▎       | 215/938 [00:15<00:51, 14.12it/s, loss=0.677, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  23%|██▎       | 216/938 [00:15<00:51, 14.11it/s, loss=0.677, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  23%|██▎       | 216/938 [00:15<00:51, 14.11it/s, loss=0.684, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  23%|██▎       | 217/938 [00:15<00:51, 14.11it/s, loss=0.683, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  23%|██▎       | 218/938 [00:15<00:51, 14.09it/s, loss=0.683, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  23%|██▎       | 219/938 [00:15<00:51, 14.03it/s, loss=0.678, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  23%|██▎       | 220/938 [00:15<00:51, 14.04it/s, loss=0.678, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  23%|██▎       | 220/938 [00:15<00:51, 14.04it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  24%|██▎       | 221/938 [00:15<00:51, 14.05it/s, loss=0.668, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  24%|██▎       | 222/938 [00:15<00:50, 14.06it/s, loss=0.661, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  24%|██▍       | 223/938 [00:15<00:50, 14.02it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  24%|██▍       | 224/938 [00:15<00:50, 14.02it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  24%|██▍       | 224/938 [00:15<00:50, 14.02it/s, loss=0.661, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  24%|██▍       | 225/938 [00:16<00:50, 14.01it/s, loss=0.667, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  24%|██▍       | 226/938 [00:16<00:50, 14.01it/s, loss=0.678, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  24%|██▍       | 227/938 [00:16<00:50, 14.02it/s, loss=0.674, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  24%|██▍       | 228/938 [00:16<00:50, 14.02it/s, loss=0.674, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  24%|██▍       | 228/938 [00:16<00:50, 14.02it/s, loss=0.678, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  24%|██▍       | 229/938 [00:16<00:50, 14.03it/s, loss=0.667, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  25%|██▍       | 230/938 [00:16<00:50, 14.04it/s, loss=0.673, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  25%|██▍       | 231/938 [00:16<00:50, 14.04it/s, loss=0.677, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  25%|██▍       | 232/938 [00:16<00:50, 14.04it/s, loss=0.677, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  25%|██▍       | 232/938 [00:16<00:50, 14.04it/s, loss=0.672, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  25%|██▍       | 233/938 [00:16<00:50, 14.05it/s, loss=0.674, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  25%|██▍       | 234/938 [00:16<00:50, 14.04it/s, loss=0.678, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  25%|██▌       | 235/938 [00:16<00:50, 14.05it/s, loss=0.691, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  25%|██▌       | 236/938 [00:16<00:49, 14.05it/s, loss=0.691, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  25%|██▌       | 236/938 [00:16<00:49, 14.04it/s, loss=0.683, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  25%|██▌       | 237/938 [00:16<00:49, 14.05it/s, loss=0.685, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  25%|██▌       | 238/938 [00:16<00:49, 14.03it/s, loss=0.678, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  25%|██▌       | 239/938 [00:17<00:49, 14.04it/s, loss=0.677, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  26%|██▌       | 240/938 [00:17<00:49, 14.03it/s, loss=0.677, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  26%|██▌       | 240/938 [00:17<00:49, 14.03it/s, loss=0.684, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  26%|██▌       | 241/938 [00:17<00:49, 14.03it/s, loss=0.687, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  26%|██▌       | 242/938 [00:17<00:49, 14.04it/s, loss=0.685, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  26%|██▌       | 243/938 [00:17<00:49, 14.04it/s, loss=0.688, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  26%|██▌       | 244/938 [00:17<00:49, 14.05it/s, loss=0.688, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  26%|██▌       | 244/938 [00:17<00:49, 14.05it/s, loss=0.686, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  26%|██▌       | 245/938 [00:17<00:49, 14.03it/s, loss=0.69, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:  26%|██▌       | 246/938 [00:17<00:49, 14.03it/s, loss=0.682, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  26%|██▋       | 247/938 [00:17<00:49, 14.04it/s, loss=0.694, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  26%|██▋       | 248/938 [00:17<00:49, 14.04it/s, loss=0.694, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  26%|██▋       | 248/938 [00:17<00:49, 14.04it/s, loss=0.687, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  27%|██▋       | 249/938 [00:17<00:49, 14.05it/s, loss=0.688, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  27%|██▋       | 250/938 [00:17<00:48, 14.05it/s, loss=0.681, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  27%|██▋       | 251/938 [00:17<00:48, 14.05it/s, loss=0.679, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  27%|██▋       | 252/938 [00:17<00:48, 14.06it/s, loss=0.679, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  27%|██▋       | 252/938 [00:17<00:48, 14.06it/s, loss=0.685, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  27%|██▋       | 253/938 [00:17<00:48, 14.06it/s, loss=0.682, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  27%|██▋       | 254/938 [00:18<00:48, 14.07it/s, loss=0.687, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  27%|██▋       | 255/938 [00:18<00:48, 14.07it/s, loss=0.673, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  27%|██▋       | 256/938 [00:18<00:48, 14.07it/s, loss=0.673, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  27%|██▋       | 256/938 [00:18<00:48, 14.07it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  27%|██▋       | 257/938 [00:18<00:48, 14.06it/s, loss=0.67, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:  28%|██▊       | 258/938 [00:18<00:48, 14.07it/s, loss=0.673, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  28%|██▊       | 259/938 [00:18<00:48, 14.07it/s, loss=0.678, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  28%|██▊       | 260/938 [00:18<00:48, 14.08it/s, loss=0.678, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  28%|██▊       | 260/938 [00:18<00:48, 14.08it/s, loss=0.667, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  28%|██▊       | 261/938 [00:18<00:48, 14.07it/s, loss=0.668, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  28%|██▊       | 262/938 [00:18<00:48, 14.07it/s, loss=0.675, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  28%|██▊       | 263/938 [00:18<00:47, 14.07it/s, loss=0.672, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  28%|██▊       | 264/938 [00:18<00:47, 14.07it/s, loss=0.672, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  28%|██▊       | 264/938 [00:18<00:47, 14.07it/s, loss=0.68, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:  28%|██▊       | 265/938 [00:18<00:47, 14.06it/s, loss=0.682, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  28%|██▊       | 266/938 [00:18<00:47, 14.06it/s, loss=0.679, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  28%|██▊       | 267/938 [00:18<00:47, 14.07it/s, loss=0.674, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  29%|██▊       | 268/938 [00:19<00:47, 14.07it/s, loss=0.674, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  29%|██▊       | 268/938 [00:19<00:47, 14.07it/s, loss=0.68, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:  29%|██▊       | 269/938 [00:19<00:47, 14.08it/s, loss=0.684, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  29%|██▉       | 270/938 [00:19<00:47, 14.07it/s, loss=0.682, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  29%|██▉       | 271/938 [00:19<00:47, 14.08it/s, loss=0.675, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  29%|██▉       | 272/938 [00:19<00:47, 14.08it/s, loss=0.675, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  29%|██▉       | 272/938 [00:19<00:47, 14.08it/s, loss=0.67, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:  29%|██▉       | 273/938 [00:19<00:47, 14.08it/s, loss=0.674, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  29%|██▉       | 274/938 [00:19<00:47, 14.10it/s, loss=0.669, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  29%|██▉       | 275/938 [00:19<00:47, 14.09it/s, loss=0.67, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:  29%|██▉       | 276/938 [00:19<00:46, 14.10it/s, loss=0.67, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  29%|██▉       | 276/938 [00:19<00:46, 14.09it/s, loss=0.672, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  30%|██▉       | 277/938 [00:19<00:46, 14.11it/s, loss=0.667, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  30%|██▉       | 278/938 [00:19<00:46, 14.11it/s, loss=0.675, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  30%|██▉       | 279/938 [00:19<00:46, 14.11it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  30%|██▉       | 280/938 [00:19<00:46, 14.10it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  30%|██▉       | 280/938 [00:19<00:46, 14.10it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  30%|██▉       | 281/938 [00:19<00:46, 14.09it/s, loss=0.677, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  30%|███       | 282/938 [00:20<00:46, 14.09it/s, loss=0.672, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  30%|███       | 283/938 [00:20<00:46, 14.10it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  30%|███       | 284/938 [00:20<00:46, 14.10it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  30%|███       | 284/938 [00:20<00:46, 14.10it/s, loss=0.661, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  30%|███       | 285/938 [00:20<00:46, 14.11it/s, loss=0.66, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:  30%|███       | 286/938 [00:20<00:46, 14.10it/s, loss=0.67, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  31%|███       | 287/938 [00:20<00:46, 14.10it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  31%|███       | 288/938 [00:20<00:46, 14.11it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  31%|███       | 288/938 [00:20<00:46, 14.11it/s, loss=0.674, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  31%|███       | 289/938 [00:20<00:46, 14.10it/s, loss=0.67, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:  31%|███       | 290/938 [00:20<00:45, 14.10it/s, loss=0.666, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  31%|███       | 291/938 [00:20<00:45, 14.10it/s, loss=0.669, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  31%|███       | 292/938 [00:20<00:45, 14.10it/s, loss=0.669, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  31%|███       | 292/938 [00:20<00:45, 14.10it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  31%|███       | 293/938 [00:20<00:45, 14.09it/s, loss=0.669, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  31%|███▏      | 294/938 [00:20<00:45, 14.10it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  31%|███▏      | 295/938 [00:20<00:45, 14.09it/s, loss=0.678, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  32%|███▏      | 296/938 [00:20<00:45, 14.10it/s, loss=0.678, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  32%|███▏      | 296/938 [00:20<00:45, 14.10it/s, loss=0.674, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  32%|███▏      | 297/938 [00:21<00:45, 14.10it/s, loss=0.676, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  32%|███▏      | 298/938 [00:21<00:45, 14.11it/s, loss=0.668, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  32%|███▏      | 299/938 [00:21<00:45, 14.12it/s, loss=0.679, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  32%|███▏      | 300/938 [00:21<00:45, 14.12it/s, loss=0.679, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  32%|███▏      | 300/938 [00:21<00:45, 14.12it/s, loss=0.677, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  32%|███▏      | 301/938 [00:21<00:45, 14.08it/s, loss=0.674, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  32%|███▏      | 302/938 [00:21<00:45, 14.08it/s, loss=0.677, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  32%|███▏      | 303/938 [00:21<00:45, 14.08it/s, loss=0.673, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  32%|███▏      | 304/938 [00:21<00:45, 14.07it/s, loss=0.673, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  32%|███▏      | 304/938 [00:21<00:45, 14.07it/s, loss=0.669, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  33%|███▎      | 305/938 [00:21<00:44, 14.07it/s, loss=0.669, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  33%|███▎      | 306/938 [00:21<00:44, 14.07it/s, loss=0.665, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  33%|███▎      | 307/938 [00:21<00:44, 14.06it/s, loss=0.663, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  33%|███▎      | 308/938 [00:21<00:44, 14.07it/s, loss=0.663, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  33%|███▎      | 308/938 [00:21<00:44, 14.07it/s, loss=0.654, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  33%|███▎      | 309/938 [00:21<00:44, 14.07it/s, loss=0.659, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  33%|███▎      | 310/938 [00:22<00:44, 14.07it/s, loss=0.665, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  33%|███▎      | 311/938 [00:22<00:44, 14.08it/s, loss=0.666, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  33%|███▎      | 312/938 [00:22<00:44, 14.06it/s, loss=0.666, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  33%|███▎      | 312/938 [00:22<00:44, 14.06it/s, loss=0.664, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  33%|███▎      | 313/938 [00:22<00:44, 14.07it/s, loss=0.661, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  33%|███▎      | 314/938 [00:22<00:44, 14.06it/s, loss=0.655, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  34%|███▎      | 315/938 [00:22<00:44, 14.05it/s, loss=0.646, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  34%|███▎      | 316/938 [00:22<00:44, 14.05it/s, loss=0.646, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  34%|███▎      | 316/938 [00:22<00:44, 14.05it/s, loss=0.658, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  34%|███▍      | 317/938 [00:22<00:44, 14.05it/s, loss=0.657, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  34%|███▍      | 318/938 [00:22<00:44, 14.04it/s, loss=0.661, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  34%|███▍      | 319/938 [00:22<00:44, 14.04it/s, loss=0.651, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  34%|███▍      | 320/938 [00:22<00:44, 14.04it/s, loss=0.651, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  34%|███▍      | 320/938 [00:22<00:44, 14.04it/s, loss=0.654, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  34%|███▍      | 321/938 [00:22<00:43, 14.04it/s, loss=0.655, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  34%|███▍      | 322/938 [00:22<00:43, 14.05it/s, loss=0.649, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  34%|███▍      | 323/938 [00:22<00:43, 14.05it/s, loss=0.658, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  35%|███▍      | 324/938 [00:23<00:43, 14.04it/s, loss=0.658, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  35%|███▍      | 324/938 [00:23<00:43, 14.04it/s, loss=0.667, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  35%|███▍      | 325/938 [00:23<00:43, 14.03it/s, loss=0.665, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  35%|███▍      | 326/938 [00:23<00:43, 14.02it/s, loss=0.664, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  35%|███▍      | 327/938 [00:23<00:43, 14.03it/s, loss=0.665, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  35%|███▍      | 328/938 [00:23<00:43, 14.03it/s, loss=0.665, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  35%|███▍      | 328/938 [00:23<00:43, 14.03it/s, loss=0.676, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  35%|███▌      | 329/938 [00:23<00:43, 14.03it/s, loss=0.676, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  35%|███▌      | 330/938 [00:23<00:43, 14.03it/s, loss=0.681, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  35%|███▌      | 331/938 [00:23<00:43, 14.03it/s, loss=0.677, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  35%|███▌      | 332/938 [00:23<00:43, 14.03it/s, loss=0.677, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  35%|███▌      | 332/938 [00:23<00:43, 14.03it/s, loss=0.677, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  36%|███▌      | 333/938 [00:23<00:43, 14.04it/s, loss=0.675, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  36%|███▌      | 334/938 [00:23<00:43, 14.03it/s, loss=0.679, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  36%|███▌      | 335/938 [00:23<00:42, 14.04it/s, loss=0.678, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  36%|███▌      | 336/938 [00:23<00:42, 14.03it/s, loss=0.678, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  36%|███▌      | 336/938 [00:23<00:42, 14.03it/s, loss=0.673, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  36%|███▌      | 337/938 [00:24<00:42, 14.04it/s, loss=0.672, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  36%|███▌      | 338/938 [00:24<00:42, 14.04it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  36%|███▌      | 339/938 [00:24<00:42, 14.04it/s, loss=0.682, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  36%|███▌      | 340/938 [00:24<00:42, 14.04it/s, loss=0.682, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  36%|███▌      | 340/938 [00:24<00:42, 14.04it/s, loss=0.675, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  36%|███▋      | 341/938 [00:24<00:42, 14.04it/s, loss=0.669, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  36%|███▋      | 342/938 [00:24<00:42, 14.04it/s, loss=0.676, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  37%|███▋      | 343/938 [00:24<00:42, 14.05it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  37%|███▋      | 344/938 [00:24<00:42, 14.05it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  37%|███▋      | 344/938 [00:24<00:42, 14.05it/s, loss=0.663, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  37%|███▋      | 345/938 [00:24<00:42, 14.04it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  37%|███▋      | 346/938 [00:24<00:42, 14.04it/s, loss=0.656, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  37%|███▋      | 347/938 [00:24<00:42, 14.05it/s, loss=0.66, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:  37%|███▋      | 348/938 [00:24<00:41, 14.05it/s, loss=0.66, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  37%|███▋      | 348/938 [00:24<00:41, 14.05it/s, loss=0.654, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  37%|███▋      | 349/938 [00:24<00:41, 14.05it/s, loss=0.657, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  37%|███▋      | 350/938 [00:24<00:41, 14.05it/s, loss=0.653, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  37%|███▋      | 351/938 [00:24<00:41, 14.04it/s, loss=0.658, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  38%|███▊      | 352/938 [00:25<00:41, 14.05it/s, loss=0.658, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  38%|███▊      | 352/938 [00:25<00:41, 14.05it/s, loss=0.658, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  38%|███▊      | 353/938 [00:25<00:41, 14.06it/s, loss=0.658, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  38%|███▊      | 354/938 [00:25<00:41, 14.06it/s, loss=0.669, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  38%|███▊      | 355/938 [00:25<00:41, 14.06it/s, loss=0.674, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  38%|███▊      | 356/938 [00:25<00:41, 14.06it/s, loss=0.674, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  38%|███▊      | 356/938 [00:25<00:41, 14.06it/s, loss=0.673, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  38%|███▊      | 357/938 [00:25<00:41, 14.05it/s, loss=0.683, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  38%|███▊      | 358/938 [00:25<00:41, 14.06it/s, loss=0.691, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  38%|███▊      | 359/938 [00:25<00:41, 14.06it/s, loss=0.691, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  38%|███▊      | 360/938 [00:25<00:41, 14.06it/s, loss=0.691, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  38%|███▊      | 360/938 [00:25<00:41, 14.06it/s, loss=0.688, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  38%|███▊      | 361/938 [00:25<00:41, 14.05it/s, loss=0.696, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  39%|███▊      | 362/938 [00:25<00:40, 14.06it/s, loss=0.693, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  39%|███▊      | 363/938 [00:25<00:40, 14.06it/s, loss=0.701, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  39%|███▉      | 364/938 [00:25<00:40, 14.04it/s, loss=0.701, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  39%|███▉      | 364/938 [00:25<00:40, 14.04it/s, loss=0.712, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  39%|███▉      | 365/938 [00:25<00:40, 14.05it/s, loss=0.703, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  39%|███▉      | 366/938 [00:26<00:40, 14.05it/s, loss=0.706, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  39%|███▉      | 367/938 [00:26<00:40, 14.05it/s, loss=0.7, v_num=8, val_rmse=0.561, train_rmse=0.739]  
Epoch 2:  39%|███▉      | 368/938 [00:26<00:40, 14.04it/s, loss=0.7, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  39%|███▉      | 368/938 [00:26<00:40, 14.04it/s, loss=0.695, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  39%|███▉      | 369/938 [00:26<00:40, 14.05it/s, loss=0.684, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  39%|███▉      | 370/938 [00:26<00:40, 14.04it/s, loss=0.678, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  40%|███▉      | 371/938 [00:26<00:40, 14.05it/s, loss=0.674, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  40%|███▉      | 372/938 [00:26<00:40, 14.04it/s, loss=0.674, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  40%|███▉      | 372/938 [00:26<00:40, 14.04it/s, loss=0.67, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:  40%|███▉      | 373/938 [00:26<00:40, 14.05it/s, loss=0.674, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  40%|███▉      | 374/938 [00:26<00:40, 14.04it/s, loss=0.667, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  40%|███▉      | 375/938 [00:26<00:40, 14.04it/s, loss=0.664, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  40%|████      | 376/938 [00:26<00:40, 14.04it/s, loss=0.664, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  40%|████      | 376/938 [00:26<00:40, 14.04it/s, loss=0.666, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  40%|████      | 377/938 [00:26<00:39, 14.04it/s, loss=0.663, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  40%|████      | 378/938 [00:26<00:39, 14.03it/s, loss=0.657, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  40%|████      | 379/938 [00:26<00:39, 14.04it/s, loss=0.659, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  41%|████      | 380/938 [00:27<00:39, 14.04it/s, loss=0.659, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  41%|████      | 380/938 [00:27<00:39, 14.04it/s, loss=0.652, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  41%|████      | 381/938 [00:27<00:39, 14.04it/s, loss=0.649, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  41%|████      | 382/938 [00:27<00:39, 14.04it/s, loss=0.65, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:  41%|████      | 383/938 [00:27<00:39, 14.04it/s, loss=0.647, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  41%|████      | 384/938 [00:27<00:39, 14.04it/s, loss=0.647, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  41%|████      | 384/938 [00:27<00:39, 14.04it/s, loss=0.641, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  41%|████      | 385/938 [00:27<00:39, 14.03it/s, loss=0.65, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:  41%|████      | 386/938 [00:27<00:39, 14.03it/s, loss=0.659, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  41%|████▏     | 387/938 [00:27<00:39, 14.04it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  41%|████▏     | 388/938 [00:27<00:39, 14.04it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  41%|████▏     | 388/938 [00:27<00:39, 14.04it/s, loss=0.663, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  41%|████▏     | 389/938 [00:27<00:39, 14.04it/s, loss=0.667, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  42%|████▏     | 390/938 [00:27<00:39, 14.04it/s, loss=0.669, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  42%|████▏     | 391/938 [00:27<00:38, 14.04it/s, loss=0.674, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  42%|████▏     | 392/938 [00:27<00:38, 14.03it/s, loss=0.674, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  42%|████▏     | 392/938 [00:27<00:38, 14.03it/s, loss=0.675, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  42%|████▏     | 393/938 [00:27<00:38, 14.04it/s, loss=0.666, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  42%|████▏     | 394/938 [00:28<00:38, 14.04it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  42%|████▏     | 395/938 [00:28<00:38, 14.04it/s, loss=0.664, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  42%|████▏     | 396/938 [00:28<00:38, 14.04it/s, loss=0.664, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  42%|████▏     | 396/938 [00:28<00:38, 14.03it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  42%|████▏     | 397/938 [00:28<00:38, 14.04it/s, loss=0.667, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  42%|████▏     | 398/938 [00:28<00:38, 14.04it/s, loss=0.667, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  43%|████▎     | 399/938 [00:28<00:38, 14.04it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  43%|████▎     | 400/938 [00:28<00:38, 14.04it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  43%|████▎     | 400/938 [00:28<00:38, 14.04it/s, loss=0.667, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  43%|████▎     | 401/938 [00:28<00:38, 14.03it/s, loss=0.663, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  43%|████▎     | 402/938 [00:28<00:38, 14.04it/s, loss=0.659, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  43%|████▎     | 403/938 [00:28<00:38, 14.04it/s, loss=0.654, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  43%|████▎     | 404/938 [00:28<00:38, 14.04it/s, loss=0.654, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  43%|████▎     | 404/938 [00:28<00:38, 14.04it/s, loss=0.664, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  43%|████▎     | 405/938 [00:28<00:37, 14.04it/s, loss=0.661, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  43%|████▎     | 406/938 [00:28<00:37, 14.05it/s, loss=0.648, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  43%|████▎     | 407/938 [00:28<00:37, 14.05it/s, loss=0.643, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  43%|████▎     | 408/938 [00:29<00:37, 14.04it/s, loss=0.643, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  43%|████▎     | 408/938 [00:29<00:37, 14.04it/s, loss=0.649, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  44%|████▎     | 409/938 [00:29<00:37, 14.05it/s, loss=0.647, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  44%|████▎     | 410/938 [00:29<00:37, 14.05it/s, loss=0.651, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  44%|████▍     | 411/938 [00:29<00:37, 14.05it/s, loss=0.641, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  44%|████▍     | 412/938 [00:29<00:37, 14.06it/s, loss=0.641, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  44%|████▍     | 412/938 [00:29<00:37, 14.06it/s, loss=0.648, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  44%|████▍     | 413/938 [00:29<00:37, 14.05it/s, loss=0.656, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  44%|████▍     | 414/938 [00:29<00:37, 14.05it/s, loss=0.652, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  44%|████▍     | 415/938 [00:29<00:37, 14.06it/s, loss=0.657, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  44%|████▍     | 416/938 [00:29<00:37, 14.05it/s, loss=0.657, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  44%|████▍     | 416/938 [00:29<00:37, 14.05it/s, loss=0.643, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  44%|████▍     | 417/938 [00:29<00:37, 14.04it/s, loss=0.647, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  45%|████▍     | 418/938 [00:29<00:37, 14.04it/s, loss=0.657, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  45%|████▍     | 419/938 [00:29<00:36, 14.04it/s, loss=0.658, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  45%|████▍     | 420/938 [00:29<00:36, 14.04it/s, loss=0.658, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  45%|████▍     | 420/938 [00:29<00:36, 14.04it/s, loss=0.664, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  45%|████▍     | 421/938 [00:29<00:36, 14.04it/s, loss=0.658, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  45%|████▍     | 422/938 [00:30<00:36, 14.05it/s, loss=0.665, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  45%|████▌     | 423/938 [00:30<00:36, 14.05it/s, loss=0.665, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  45%|████▌     | 424/938 [00:30<00:36, 14.05it/s, loss=0.665, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  45%|████▌     | 424/938 [00:30<00:36, 14.05it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  45%|████▌     | 425/938 [00:30<00:36, 14.04it/s, loss=0.66, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:  45%|████▌     | 426/938 [00:30<00:36, 14.03it/s, loss=0.67, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  46%|████▌     | 427/938 [00:30<00:36, 14.02it/s, loss=0.668, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  46%|████▌     | 428/938 [00:30<00:36, 14.03it/s, loss=0.668, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  46%|████▌     | 428/938 [00:30<00:36, 14.03it/s, loss=0.672, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  46%|████▌     | 429/938 [00:30<00:36, 14.03it/s, loss=0.677, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  46%|████▌     | 430/938 [00:30<00:36, 14.03it/s, loss=0.678, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  46%|████▌     | 431/938 [00:30<00:36, 14.02it/s, loss=0.681, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  46%|████▌     | 432/938 [00:30<00:36, 14.02it/s, loss=0.681, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  46%|████▌     | 432/938 [00:30<00:36, 14.02it/s, loss=0.676, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  46%|████▌     | 433/938 [00:30<00:36, 14.02it/s, loss=0.677, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  46%|████▋     | 434/938 [00:30<00:35, 14.02it/s, loss=0.676, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  46%|████▋     | 435/938 [00:31<00:35, 14.02it/s, loss=0.674, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  46%|████▋     | 436/938 [00:31<00:35, 14.02it/s, loss=0.674, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  46%|████▋     | 436/938 [00:31<00:35, 14.02it/s, loss=0.678, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  47%|████▋     | 437/938 [00:31<00:35, 14.02it/s, loss=0.67, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:  47%|████▋     | 438/938 [00:31<00:35, 14.01it/s, loss=0.667, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  47%|████▋     | 439/938 [00:31<00:35, 14.01it/s, loss=0.667, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  47%|████▋     | 440/938 [00:31<00:35, 14.01it/s, loss=0.667, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  47%|████▋     | 440/938 [00:31<00:35, 14.01it/s, loss=0.678, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  47%|████▋     | 441/938 [00:31<00:35, 14.02it/s, loss=0.682, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  47%|████▋     | 442/938 [00:31<00:35, 14.02it/s, loss=0.677, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  47%|████▋     | 443/938 [00:31<00:35, 14.02it/s, loss=0.676, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  47%|████▋     | 444/938 [00:31<00:35, 14.02it/s, loss=0.676, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  47%|████▋     | 444/938 [00:31<00:35, 14.02it/s, loss=0.669, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  47%|████▋     | 445/938 [00:31<00:35, 14.03it/s, loss=0.674, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  48%|████▊     | 446/938 [00:31<00:35, 14.03it/s, loss=0.665, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  48%|████▊     | 447/938 [00:31<00:35, 14.03it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  48%|████▊     | 448/938 [00:31<00:34, 14.03it/s, loss=0.671, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  48%|████▊     | 448/938 [00:31<00:34, 14.02it/s, loss=0.662, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  48%|████▊     | 449/938 [00:32<00:34, 14.03it/s, loss=0.654, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  48%|████▊     | 450/938 [00:32<00:34, 14.03it/s, loss=0.648, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  48%|████▊     | 451/938 [00:32<00:34, 14.03it/s, loss=0.647, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  48%|████▊     | 452/938 [00:32<00:34, 14.03it/s, loss=0.647, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  48%|████▊     | 452/938 [00:32<00:34, 14.03it/s, loss=0.64, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:  48%|████▊     | 453/938 [00:32<00:34, 14.03it/s, loss=0.638, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  48%|████▊     | 454/938 [00:32<00:34, 14.03it/s, loss=0.65, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:  49%|████▊     | 455/938 [00:32<00:34, 14.04it/s, loss=0.643, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  49%|████▊     | 456/938 [00:32<00:34, 14.04it/s, loss=0.643, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  49%|████▊     | 456/938 [00:32<00:34, 14.04it/s, loss=0.648, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  49%|████▊     | 457/938 [00:32<00:34, 14.04it/s, loss=0.649, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  49%|████▉     | 458/938 [00:32<00:34, 14.04it/s, loss=0.643, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  49%|████▉     | 459/938 [00:32<00:34, 14.04it/s, loss=0.64, v_num=8, val_rmse=0.561, train_rmse=0.739] 
Epoch 2:  49%|████▉     | 460/938 [00:32<00:34, 14.04it/s, loss=0.64, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  49%|████▉     | 460/938 [00:32<00:34, 14.04it/s, loss=0.623, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  49%|████▉     | 461/938 [00:32<00:33, 14.05it/s, loss=0.625, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  49%|████▉     | 462/938 [00:32<00:33, 14.05it/s, loss=0.628, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  49%|████▉     | 463/938 [00:32<00:33, 14.04it/s, loss=0.631, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  49%|████▉     | 464/938 [00:33<00:33, 14.04it/s, loss=0.631, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  49%|████▉     | 464/938 [00:33<00:33, 14.04it/s, loss=0.629, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  50%|████▉     | 465/938 [00:33<00:33, 14.05it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  50%|████▉     | 466/938 [00:33<00:33, 14.05it/s, loss=0.623, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  50%|████▉     | 467/938 [00:33<00:33, 14.05it/s, loss=0.623, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  50%|████▉     | 468/938 [00:33<00:33, 14.06it/s, loss=0.623, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  50%|████▉     | 468/938 [00:33<00:33, 14.06it/s, loss=0.621, v_num=8, val_rmse=0.561, train_rmse=0.739]
Epoch 2:  50%|█████     | 469/938 [00:33<00:33, 14.06it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]

Validating:   0%|          | 2/469 [00:00<00:26, 17.79it/s]
Epoch 2:  50%|█████     | 472/938 [00:33<00:33, 14.11it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:   1%|          | 5/469 [00:00<00:19, 24.40it/s]
Epoch 2:  51%|█████     | 476/938 [00:33<00:32, 14.17it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:   2%|▏         | 8/469 [00:00<00:17, 26.02it/s]
Epoch 2:  51%|█████     | 480/938 [00:33<00:32, 14.22it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:   2%|▏         | 11/469 [00:00<00:17, 26.48it/s]

Validating:   3%|▎         | 14/469 [00:00<00:16, 27.19it/s]
Epoch 2:  52%|█████▏    | 484/938 [00:33<00:31, 14.28it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:   4%|▎         | 17/469 [00:00<00:16, 27.20it/s]
Epoch 2:  52%|█████▏    | 488/938 [00:34<00:31, 14.34it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:   4%|▍         | 20/469 [00:00<00:17, 26.32it/s]
Epoch 2:  52%|█████▏    | 492/938 [00:34<00:30, 14.39it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:   5%|▍         | 23/469 [00:00<00:16, 26.88it/s]

Validating:   6%|▌         | 26/469 [00:00<00:16, 26.65it/s]
Epoch 2:  53%|█████▎    | 496/938 [00:34<00:30, 14.44it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:   6%|▌         | 29/469 [00:01<00:16, 26.52it/s]
Epoch 2:  53%|█████▎    | 500/938 [00:34<00:30, 14.50it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:   7%|▋         | 32/469 [00:01<00:17, 24.81it/s]
Epoch 2:  54%|█████▎    | 504/938 [00:34<00:29, 14.54it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:   7%|▋         | 35/469 [00:01<00:16, 25.81it/s]

Validating:   8%|▊         | 38/469 [00:01<00:16, 25.39it/s]
Epoch 2:  54%|█████▍    | 508/938 [00:34<00:29, 14.59it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:   9%|▊         | 41/469 [00:01<00:16, 25.60it/s]
Epoch 2:  55%|█████▍    | 512/938 [00:34<00:29, 14.64it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:   9%|▉         | 44/469 [00:01<00:16, 25.49it/s]
Epoch 2:  55%|█████▌    | 516/938 [00:35<00:28, 14.69it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  10%|█         | 48/469 [00:01<00:15, 26.74it/s]
Epoch 2:  55%|█████▌    | 520/938 [00:35<00:28, 14.74it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  11%|█         | 51/469 [00:01<00:15, 26.80it/s]

Validating:  12%|█▏        | 54/469 [00:02<00:15, 26.61it/s]
Epoch 2:  56%|█████▌    | 524/938 [00:35<00:27, 14.80it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  12%|█▏        | 57/469 [00:02<00:15, 26.71it/s]
Epoch 2:  56%|█████▋    | 528/938 [00:35<00:27, 14.85it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  13%|█▎        | 60/469 [00:02<00:15, 26.98it/s]
Epoch 2:  57%|█████▋    | 532/938 [00:35<00:27, 14.90it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  13%|█▎        | 63/469 [00:02<00:15, 26.84it/s]

Validating:  14%|█▍        | 66/469 [00:02<00:15, 26.12it/s]
Epoch 2:  57%|█████▋    | 536/938 [00:35<00:26, 14.94it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  15%|█▍        | 69/469 [00:02<00:15, 26.20it/s]
Epoch 2:  58%|█████▊    | 540/938 [00:36<00:26, 14.99it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  15%|█▌        | 72/469 [00:02<00:14, 26.60it/s]
Epoch 2:  58%|█████▊    | 544/938 [00:36<00:26, 15.04it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  16%|█▌        | 75/469 [00:02<00:14, 26.35it/s]

Validating:  17%|█▋        | 78/469 [00:02<00:14, 26.65it/s]
Epoch 2:  58%|█████▊    | 548/938 [00:36<00:25, 15.09it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  17%|█▋        | 81/469 [00:03<00:14, 26.15it/s]
Epoch 2:  59%|█████▉    | 552/938 [00:36<00:25, 15.13it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  18%|█▊        | 84/469 [00:03<00:14, 26.32it/s]
Epoch 2:  59%|█████▉    | 556/938 [00:36<00:25, 15.18it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  19%|█▊        | 87/469 [00:03<00:14, 26.57it/s]

Validating:  19%|█▉        | 90/469 [00:03<00:14, 25.61it/s]
Epoch 2:  60%|█████▉    | 560/938 [00:36<00:24, 15.22it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  20%|█▉        | 93/469 [00:03<00:14, 26.35it/s]
Epoch 2:  60%|██████    | 564/938 [00:36<00:24, 15.27it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  20%|██        | 96/469 [00:03<00:14, 25.94it/s]
Epoch 2:  61%|██████    | 568/938 [00:37<00:24, 15.31it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  21%|██        | 99/469 [00:03<00:14, 26.27it/s]

Validating:  22%|██▏       | 102/469 [00:03<00:15, 23.97it/s]
Epoch 2:  61%|██████    | 572/938 [00:37<00:23, 15.34it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  22%|██▏       | 105/469 [00:04<00:15, 23.62it/s]
Epoch 2:  61%|██████▏   | 576/938 [00:37<00:23, 15.38it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  23%|██▎       | 108/469 [00:04<00:14, 24.90it/s]
Epoch 2:  62%|██████▏   | 580/938 [00:37<00:23, 15.43it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  24%|██▎       | 111/469 [00:04<00:14, 25.44it/s]

Validating:  24%|██▍       | 114/469 [00:04<00:13, 26.15it/s]
Epoch 2:  62%|██████▏   | 584/938 [00:37<00:22, 15.48it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  25%|██▍       | 117/469 [00:04<00:13, 25.93it/s]
Epoch 2:  63%|██████▎   | 588/938 [00:37<00:22, 15.52it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  26%|██▌       | 120/469 [00:04<00:13, 25.14it/s]
Epoch 2:  63%|██████▎   | 592/938 [00:38<00:22, 15.56it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  26%|██▌       | 123/469 [00:04<00:13, 26.07it/s]

Validating:  27%|██▋       | 126/469 [00:04<00:13, 25.36it/s]
Epoch 2:  64%|██████▎   | 596/938 [00:38<00:21, 15.60it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  28%|██▊       | 129/469 [00:04<00:13, 25.89it/s]
Epoch 2:  64%|██████▍   | 600/938 [00:38<00:21, 15.64it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  28%|██▊       | 132/469 [00:05<00:12, 26.35it/s]
Epoch 2:  64%|██████▍   | 604/938 [00:38<00:21, 15.69it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  29%|██▉       | 135/469 [00:05<00:13, 25.61it/s]

Validating:  29%|██▉       | 138/469 [00:05<00:12, 25.78it/s]
Epoch 2:  65%|██████▍   | 608/938 [00:38<00:20, 15.72it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  30%|███       | 141/469 [00:05<00:12, 25.81it/s]
Epoch 2:  65%|██████▌   | 612/938 [00:38<00:20, 15.76it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  31%|███       | 144/469 [00:05<00:12, 26.07it/s]
Epoch 2:  66%|██████▌   | 616/938 [00:38<00:20, 15.81it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  31%|███▏      | 147/469 [00:05<00:12, 25.82it/s]

Validating:  32%|███▏      | 150/469 [00:05<00:12, 25.46it/s]
Epoch 2:  66%|██████▌   | 620/938 [00:39<00:20, 15.84it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  33%|███▎      | 153/469 [00:05<00:12, 26.02it/s]
Epoch 2:  67%|██████▋   | 624/938 [00:39<00:19, 15.88it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  33%|███▎      | 156/469 [00:06<00:12, 25.76it/s]
Epoch 2:  67%|██████▋   | 628/938 [00:39<00:19, 15.92it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  34%|███▍      | 159/469 [00:06<00:12, 25.59it/s]

Validating:  35%|███▍      | 162/469 [00:06<00:11, 26.55it/s]
Epoch 2:  67%|██████▋   | 632/938 [00:39<00:19, 15.96it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  35%|███▌      | 165/469 [00:06<00:11, 25.96it/s]
Epoch 2:  68%|██████▊   | 636/938 [00:39<00:18, 16.00it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  36%|███▌      | 168/469 [00:06<00:11, 25.88it/s]
Epoch 2:  68%|██████▊   | 640/938 [00:39<00:18, 16.04it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  36%|███▋      | 171/469 [00:06<00:11, 25.61it/s]

Validating:  37%|███▋      | 174/469 [00:06<00:11, 25.68it/s]
Epoch 2:  69%|██████▊   | 644/938 [00:40<00:18, 16.07it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  38%|███▊      | 177/469 [00:06<00:11, 26.19it/s]
Epoch 2:  69%|██████▉   | 648/938 [00:40<00:17, 16.12it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  38%|███▊      | 180/469 [00:06<00:11, 26.10it/s]
Epoch 2:  70%|██████▉   | 652/938 [00:40<00:17, 16.15it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  39%|███▉      | 183/469 [00:07<00:11, 25.79it/s]

Validating:  40%|███▉      | 186/469 [00:07<00:10, 25.94it/s]
Epoch 2:  70%|██████▉   | 656/938 [00:40<00:17, 16.19it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  40%|████      | 189/469 [00:07<00:10, 26.68it/s]
Epoch 2:  70%|███████   | 660/938 [00:40<00:17, 16.23it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  41%|████      | 192/469 [00:07<00:10, 27.01it/s]
Epoch 2:  71%|███████   | 664/938 [00:40<00:16, 16.27it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  42%|████▏     | 195/469 [00:07<00:10, 26.98it/s]

Validating:  42%|████▏     | 198/469 [00:07<00:09, 27.55it/s]
Epoch 2:  71%|███████   | 668/938 [00:40<00:16, 16.31it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  43%|████▎     | 201/469 [00:07<00:09, 27.03it/s]
Epoch 2:  72%|███████▏  | 672/938 [00:41<00:16, 16.35it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  43%|████▎     | 204/469 [00:07<00:09, 27.23it/s]
Epoch 2:  72%|███████▏  | 676/938 [00:41<00:15, 16.39it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  44%|████▍     | 207/469 [00:07<00:09, 26.49it/s]

Validating:  45%|████▍     | 210/469 [00:08<00:09, 27.30it/s]
Epoch 2:  72%|███████▏  | 680/938 [00:41<00:15, 16.43it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  45%|████▌     | 213/469 [00:08<00:09, 26.96it/s]
Epoch 2:  73%|███████▎  | 684/938 [00:41<00:15, 16.46it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  46%|████▌     | 216/469 [00:08<00:09, 25.77it/s]
Epoch 2:  73%|███████▎  | 688/938 [00:41<00:15, 16.50it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  47%|████▋     | 219/469 [00:08<00:09, 26.06it/s]

Validating:  47%|████▋     | 222/469 [00:08<00:09, 26.23it/s]
Epoch 2:  74%|███████▍  | 692/938 [00:41<00:14, 16.53it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  48%|████▊     | 225/469 [00:08<00:09, 26.56it/s]
Epoch 2:  74%|███████▍  | 696/938 [00:42<00:14, 16.57it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  49%|████▊     | 228/469 [00:08<00:09, 26.47it/s]
Epoch 2:  75%|███████▍  | 700/938 [00:42<00:14, 16.60it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  49%|████▉     | 231/469 [00:08<00:08, 26.97it/s]

Validating:  50%|████▉     | 234/469 [00:08<00:08, 26.69it/s]
Epoch 2:  75%|███████▌  | 704/938 [00:42<00:14, 16.64it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  51%|█████     | 237/469 [00:09<00:08, 27.15it/s]
Epoch 2:  75%|███████▌  | 708/938 [00:42<00:13, 16.68it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  51%|█████     | 240/469 [00:09<00:08, 26.66it/s]
Epoch 2:  76%|███████▌  | 712/938 [00:42<00:13, 16.71it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  52%|█████▏    | 243/469 [00:09<00:08, 26.94it/s]

Validating:  52%|█████▏    | 246/469 [00:09<00:08, 26.88it/s]
Epoch 2:  76%|███████▋  | 716/938 [00:42<00:13, 16.75it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  53%|█████▎    | 249/469 [00:09<00:08, 27.21it/s]
Epoch 2:  77%|███████▋  | 720/938 [00:42<00:12, 16.79it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  54%|█████▎    | 252/469 [00:09<00:07, 27.54it/s]
Epoch 2:  77%|███████▋  | 724/938 [00:43<00:12, 16.82it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  54%|█████▍    | 255/469 [00:09<00:07, 26.94it/s]

Validating:  55%|█████▌    | 258/469 [00:09<00:07, 27.40it/s]
Epoch 2:  78%|███████▊  | 728/938 [00:43<00:12, 16.86it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  56%|█████▌    | 261/469 [00:09<00:07, 26.62it/s]
Epoch 2:  78%|███████▊  | 732/938 [00:43<00:12, 16.89it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  56%|█████▋    | 264/469 [00:10<00:07, 26.90it/s]
Epoch 2:  78%|███████▊  | 736/938 [00:43<00:11, 16.92it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  57%|█████▋    | 267/469 [00:10<00:07, 26.13it/s]

Validating:  58%|█████▊    | 270/469 [00:10<00:07, 26.11it/s]
Epoch 2:  79%|███████▉  | 740/938 [00:43<00:11, 16.95it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  58%|█████▊    | 273/469 [00:10<00:07, 26.73it/s]
Epoch 2:  79%|███████▉  | 744/938 [00:43<00:11, 16.99it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  59%|█████▉    | 276/469 [00:10<00:07, 26.68it/s]
Epoch 2:  80%|███████▉  | 748/938 [00:43<00:11, 17.02it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  59%|█████▉    | 279/469 [00:10<00:07, 25.76it/s]

Validating:  60%|██████    | 282/469 [00:10<00:06, 26.73it/s]
Epoch 2:  80%|████████  | 752/938 [00:44<00:10, 17.05it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  61%|██████    | 285/469 [00:10<00:06, 26.79it/s]
Epoch 2:  81%|████████  | 756/938 [00:44<00:10, 17.08it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  61%|██████▏   | 288/469 [00:10<00:06, 27.20it/s]
Epoch 2:  81%|████████  | 760/938 [00:44<00:10, 17.12it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  62%|██████▏   | 291/469 [00:11<00:06, 27.06it/s]

Validating:  63%|██████▎   | 294/469 [00:11<00:06, 27.83it/s]
Epoch 2:  81%|████████▏ | 764/938 [00:44<00:10, 17.16it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  63%|██████▎   | 297/469 [00:11<00:06, 27.60it/s]
Epoch 2:  82%|████████▏ | 768/938 [00:44<00:09, 17.19it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  64%|██████▍   | 300/469 [00:11<00:06, 27.22it/s]
Epoch 2:  82%|████████▏ | 772/938 [00:44<00:09, 17.22it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  65%|██████▍   | 303/469 [00:11<00:06, 27.65it/s]

Validating:  65%|██████▌   | 306/469 [00:11<00:05, 27.50it/s]
Epoch 2:  83%|████████▎ | 776/938 [00:44<00:09, 17.26it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  66%|██████▌   | 309/469 [00:11<00:05, 27.25it/s]
Epoch 2:  83%|████████▎ | 780/938 [00:45<00:09, 17.29it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  67%|██████▋   | 312/469 [00:11<00:05, 26.87it/s]
Epoch 2:  84%|████████▎ | 784/938 [00:45<00:08, 17.31it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  67%|██████▋   | 315/469 [00:11<00:05, 26.87it/s]

Validating:  68%|██████▊   | 318/469 [00:12<00:05, 26.78it/s]
Epoch 2:  84%|████████▍ | 788/938 [00:45<00:08, 17.35it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  68%|██████▊   | 321/469 [00:12<00:05, 26.91it/s]
Epoch 2:  84%|████████▍ | 792/938 [00:45<00:08, 17.38it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  69%|██████▉   | 324/469 [00:12<00:05, 27.41it/s]
Epoch 2:  85%|████████▍ | 796/938 [00:45<00:08, 17.41it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  70%|██████▉   | 327/469 [00:12<00:05, 27.92it/s]

Validating:  70%|███████   | 330/469 [00:12<00:05, 27.46it/s]
Epoch 2:  85%|████████▌ | 800/938 [00:45<00:07, 17.45it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  71%|███████   | 333/469 [00:12<00:05, 27.08it/s]
Epoch 2:  86%|████████▌ | 804/938 [00:46<00:07, 17.47it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  72%|███████▏  | 336/469 [00:12<00:05, 25.58it/s]
Epoch 2:  86%|████████▌ | 808/938 [00:46<00:07, 17.50it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  72%|███████▏  | 340/469 [00:12<00:04, 26.98it/s]
Epoch 2:  87%|████████▋ | 812/938 [00:46<00:07, 17.53it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  73%|███████▎  | 343/469 [00:13<00:04, 26.10it/s]

Validating:  74%|███████▍  | 346/469 [00:13<00:04, 25.13it/s]
Epoch 2:  87%|████████▋ | 816/938 [00:46<00:06, 17.55it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  74%|███████▍  | 349/469 [00:13<00:04, 25.04it/s]
Epoch 2:  87%|████████▋ | 820/938 [00:46<00:06, 17.58it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  75%|███████▌  | 352/469 [00:13<00:04, 24.26it/s]
Epoch 2:  88%|████████▊ | 824/938 [00:46<00:06, 17.60it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  76%|███████▌  | 355/469 [00:13<00:04, 24.86it/s]

Validating:  76%|███████▋  | 358/469 [00:13<00:04, 24.71it/s]
Epoch 2:  88%|████████▊ | 828/938 [00:46<00:06, 17.62it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  77%|███████▋  | 361/469 [00:13<00:04, 24.14it/s]
Epoch 2:  89%|████████▊ | 832/938 [00:47<00:06, 17.65it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  78%|███████▊  | 364/469 [00:13<00:04, 24.74it/s]
Epoch 2:  89%|████████▉ | 836/938 [00:47<00:05, 17.67it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  78%|███████▊  | 367/469 [00:13<00:04, 25.11it/s]

Validating:  79%|███████▉  | 370/469 [00:14<00:03, 24.90it/s]
Epoch 2:  90%|████████▉ | 840/938 [00:47<00:05, 17.70it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  80%|███████▉  | 373/469 [00:14<00:03, 25.44it/s]
Epoch 2:  90%|████████▉ | 844/938 [00:47<00:05, 17.72it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  80%|████████  | 376/469 [00:14<00:03, 24.29it/s]
Epoch 2:  90%|█████████ | 848/938 [00:47<00:05, 17.74it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  81%|████████  | 379/469 [00:14<00:03, 23.94it/s]

Validating:  81%|████████▏ | 382/469 [00:14<00:03, 24.10it/s]
Epoch 2:  91%|█████████ | 852/938 [00:47<00:04, 17.76it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  82%|████████▏ | 385/469 [00:14<00:03, 24.87it/s]
Epoch 2:  91%|█████████▏| 856/938 [00:48<00:04, 17.79it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  83%|████████▎ | 388/469 [00:14<00:03, 25.35it/s]
Epoch 2:  92%|█████████▏| 860/938 [00:48<00:04, 17.82it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  83%|████████▎ | 391/469 [00:14<00:02, 26.20it/s]

Validating:  84%|████████▍ | 394/469 [00:15<00:02, 25.68it/s]
Epoch 2:  92%|█████████▏| 864/938 [00:48<00:04, 17.84it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  85%|████████▍ | 398/469 [00:15<00:02, 27.21it/s]
Epoch 2:  93%|█████████▎| 868/938 [00:48<00:03, 17.88it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  86%|████████▌ | 401/469 [00:15<00:02, 26.68it/s]
Epoch 2:  93%|█████████▎| 872/938 [00:48<00:03, 17.91it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  86%|████████▌ | 404/469 [00:15<00:02, 25.38it/s]
Epoch 2:  93%|█████████▎| 876/938 [00:48<00:03, 17.93it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  87%|████████▋ | 407/469 [00:15<00:02, 26.54it/s]

Validating:  87%|████████▋ | 410/469 [00:15<00:02, 26.70it/s]
Epoch 2:  94%|█████████▍| 880/938 [00:49<00:03, 17.95it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  88%|████████▊ | 413/469 [00:15<00:02, 26.81it/s]
Epoch 2:  94%|█████████▍| 884/938 [00:49<00:03, 17.98it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  89%|████████▊ | 416/469 [00:15<00:01, 27.33it/s]
Epoch 2:  95%|█████████▍| 888/938 [00:49<00:02, 18.01it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  89%|████████▉ | 419/469 [00:15<00:01, 27.26it/s]

Validating:  90%|████████▉ | 422/469 [00:16<00:01, 27.51it/s]
Epoch 2:  95%|█████████▌| 892/938 [00:49<00:02, 18.04it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  91%|█████████ | 425/469 [00:16<00:01, 26.67it/s]
Epoch 2:  96%|█████████▌| 896/938 [00:49<00:02, 18.06it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  91%|█████████▏| 428/469 [00:16<00:01, 26.63it/s]
Epoch 2:  96%|█████████▌| 900/938 [00:49<00:02, 18.09it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  92%|█████████▏| 431/469 [00:16<00:01, 26.57it/s]

Validating:  93%|█████████▎| 434/469 [00:16<00:01, 26.68it/s]
Epoch 2:  96%|█████████▋| 904/938 [00:49<00:01, 18.12it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  93%|█████████▎| 437/469 [00:16<00:01, 25.60it/s]
Epoch 2:  97%|█████████▋| 908/938 [00:50<00:01, 18.14it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  94%|█████████▍| 440/469 [00:16<00:01, 26.23it/s]
Epoch 2:  97%|█████████▋| 912/938 [00:50<00:01, 18.16it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  94%|█████████▍| 443/469 [00:16<00:00, 26.58it/s]

Validating:  95%|█████████▌| 446/469 [00:17<00:00, 26.61it/s]
Epoch 2:  98%|█████████▊| 916/938 [00:50<00:01, 18.19it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  96%|█████████▌| 449/469 [00:17<00:00, 26.65it/s]
Epoch 2:  98%|█████████▊| 920/938 [00:50<00:00, 18.21it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  96%|█████████▋| 452/469 [00:17<00:00, 26.48it/s]
Epoch 2:  99%|█████████▊| 924/938 [00:50<00:00, 18.24it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  97%|█████████▋| 455/469 [00:17<00:00, 27.08it/s]

Validating:  98%|█████████▊| 458/469 [00:17<00:00, 27.08it/s]
Epoch 2:  99%|█████████▉| 928/938 [00:50<00:00, 18.27it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  98%|█████████▊| 461/469 [00:17<00:00, 27.19it/s]
Epoch 2:  99%|█████████▉| 932/938 [00:50<00:00, 18.29it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating:  99%|█████████▉| 464/469 [00:17<00:00, 26.32it/s]
Epoch 2: 100%|█████████▉| 936/938 [00:51<00:00, 18.31it/s, loss=0.624, v_num=8, val_rmse=0.561, train_rmse=0.739]

Validating: 100%|█████████▉| 467/469 [00:17<00:00, 26.71it/s]
Epoch 2: 100%|██████████| 938/938 [00:51<00:00, 18.32it/s, loss=0.624, v_num=8, val_rmse=0.517, train_rmse=0.739]

                                                             
Epoch 2: 100%|██████████| 938/938 [00:51<00:00, 18.31it/s, loss=0.624, v_num=8, val_rmse=0.517, train_rmse=0.669]
Epoch 2: 100%|██████████| 938/938 [00:51<00:00, 18.28it/s, loss=0.624, v_num=8, val_rmse=0.517, train_rmse=0.669]LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]


Testing: 0it [00:00, ?it/s]
Testing:   1%|          | 3/469 [00:00<00:20, 22.24it/s]
Testing:   1%|▏         | 6/469 [00:00<00:18, 24.97it/s]
Testing:   2%|▏         | 9/469 [00:00<00:18, 25.38it/s]
Testing:   3%|▎         | 12/469 [00:00<00:17, 25.91it/s]
Testing:   3%|▎         | 15/469 [00:00<00:17, 26.10it/s]
Testing:   4%|▍         | 18/469 [00:00<00:17, 26.41it/s]
Testing:   4%|▍         | 21/469 [00:00<00:16, 27.00it/s]
Testing:   5%|▌         | 24/469 [00:00<00:16, 26.62it/s]
Testing:   6%|▌         | 27/469 [00:01<00:16, 26.50it/s]
Testing:   6%|▋         | 30/469 [00:01<00:17, 25.67it/s]
Testing:   7%|▋         | 33/469 [00:01<00:17, 25.41it/s]
Testing:   8%|▊         | 36/469 [00:01<00:16, 26.16it/s]
Testing:   8%|▊         | 39/469 [00:01<00:16, 26.49it/s]
Testing:   9%|▉         | 42/469 [00:01<00:15, 27.18it/s]
Testing:  10%|▉         | 45/469 [00:01<00:15, 26.68it/s]
Testing:  10%|█         | 48/469 [00:01<00:17, 24.24it/s]
Testing:  11%|█         | 51/469 [00:01<00:16, 24.70it/s]
Testing:  12%|█▏        | 54/469 [00:02<00:16, 25.62it/s]
Testing:  12%|█▏        | 57/469 [00:02<00:15, 25.96it/s]
Testing:  13%|█▎        | 60/469 [00:02<00:16, 25.41it/s]
Testing:  13%|█▎        | 63/469 [00:02<00:15, 26.34it/s]
Testing:  14%|█▍        | 66/469 [00:02<00:15, 26.23it/s]
Testing:  15%|█▍        | 69/469 [00:02<00:15, 26.45it/s]
Testing:  15%|█▌        | 72/469 [00:02<00:14, 26.68it/s]
Testing:  16%|█▌        | 75/469 [00:02<00:14, 27.18it/s]
Testing:  17%|█▋        | 78/469 [00:02<00:14, 27.58it/s]
Testing:  17%|█▋        | 81/469 [00:03<00:14, 26.80it/s]
Testing:  18%|█▊        | 84/469 [00:03<00:14, 26.28it/s]
Testing:  19%|█▊        | 87/469 [00:03<00:14, 26.43it/s]
Testing:  19%|█▉        | 90/469 [00:03<00:15, 24.14it/s]
Testing:  20%|█▉        | 93/469 [00:03<00:15, 24.97it/s]
Testing:  20%|██        | 96/469 [00:03<00:14, 25.06it/s]
Testing:  21%|██        | 99/469 [00:03<00:14, 25.65it/s]
Testing:  22%|██▏       | 102/469 [00:03<00:14, 25.64it/s]
Testing:  22%|██▏       | 105/469 [00:04<00:13, 26.23it/s]
Testing:  23%|██▎       | 108/469 [00:04<00:14, 24.61it/s]
Testing:  24%|██▎       | 111/469 [00:04<00:14, 24.77it/s]
Testing:  24%|██▍       | 114/469 [00:04<00:14, 24.59it/s]
Testing:  25%|██▍       | 117/469 [00:04<00:14, 24.86it/s]
Testing:  26%|██▌       | 121/469 [00:04<00:13, 26.34it/s]
Testing:  26%|██▋       | 124/469 [00:04<00:13, 26.09it/s]
Testing:  27%|██▋       | 127/469 [00:04<00:12, 27.02it/s]
Testing:  28%|██▊       | 130/469 [00:05<00:12, 27.57it/s]
Testing:  28%|██▊       | 133/469 [00:05<00:12, 27.38it/s]
Testing:  29%|██▉       | 136/469 [00:05<00:12, 26.79it/s]
Testing:  30%|██▉       | 139/469 [00:05<00:12, 26.64it/s]
Testing:  30%|███       | 142/469 [00:05<00:12, 26.17it/s]
Testing:  31%|███       | 145/469 [00:05<00:12, 25.82it/s]
Testing:  32%|███▏      | 148/469 [00:05<00:12, 25.62it/s]
Testing:  32%|███▏      | 151/469 [00:05<00:11, 26.60it/s]
Testing:  33%|███▎      | 154/469 [00:05<00:11, 26.64it/s]
Testing:  33%|███▎      | 157/469 [00:06<00:12, 25.29it/s]
Testing:  34%|███▍      | 160/469 [00:06<00:13, 23.33it/s]
Testing:  35%|███▍      | 163/469 [00:06<00:12, 23.69it/s]
Testing:  35%|███▌      | 166/469 [00:06<00:12, 25.01it/s]
Testing:  36%|███▌      | 169/469 [00:06<00:11, 25.19it/s]
Testing:  37%|███▋      | 172/469 [00:06<00:11, 25.22it/s]
Testing:  37%|███▋      | 175/469 [00:06<00:11, 25.23it/s]
Testing:  38%|███▊      | 178/469 [00:06<00:11, 25.41it/s]
Testing:  39%|███▊      | 181/469 [00:07<00:11, 25.55it/s]
Testing:  39%|███▉      | 184/469 [00:07<00:10, 26.05it/s]
Testing:  40%|███▉      | 187/469 [00:07<00:10, 26.19it/s]
Testing:  41%|████      | 190/469 [00:07<00:10, 25.91it/s]
Testing:  41%|████      | 193/469 [00:07<00:10, 25.47it/s]
Testing:  42%|████▏     | 197/469 [00:07<00:10, 26.46it/s]
Testing:  43%|████▎     | 200/469 [00:07<00:10, 26.56it/s]
Testing:  43%|████▎     | 203/469 [00:07<00:10, 26.43it/s]
Testing:  44%|████▍     | 206/469 [00:07<00:10, 25.23it/s]
Testing:  45%|████▍     | 209/469 [00:08<00:09, 26.07it/s]
Testing:  45%|████▌     | 212/469 [00:08<00:09, 26.09it/s]
Testing:  46%|████▌     | 215/469 [00:08<00:09, 26.82it/s]
Testing:  46%|████▋     | 218/469 [00:08<00:09, 26.64it/s]
Testing:  47%|████▋     | 221/469 [00:08<00:09, 26.82it/s]
Testing:  48%|████▊     | 224/469 [00:08<00:09, 26.36it/s]
Testing:  48%|████▊     | 227/469 [00:08<00:09, 26.13it/s]
Testing:  49%|████▉     | 230/469 [00:08<00:09, 25.53it/s]
Testing:  50%|████▉     | 233/469 [00:09<00:09, 25.29it/s]
Testing:  50%|█████     | 236/469 [00:09<00:09, 24.63it/s]
Testing:  51%|█████     | 239/469 [00:09<00:09, 25.20it/s]
Testing:  52%|█████▏    | 242/469 [00:09<00:09, 25.12it/s]
Testing:  52%|█████▏    | 245/469 [00:09<00:08, 25.86it/s]
Testing:  53%|█████▎    | 248/469 [00:09<00:08, 25.60it/s]
Testing:  54%|█████▎    | 251/469 [00:09<00:08, 26.17it/s]
Testing:  54%|█████▍    | 254/469 [00:09<00:08, 25.49it/s]
Testing:  55%|█████▍    | 257/469 [00:09<00:08, 24.39it/s]
Testing:  55%|█████▌    | 260/469 [00:10<00:08, 24.49it/s]
Testing:  56%|█████▋    | 264/469 [00:10<00:07, 26.50it/s]
Testing:  57%|█████▋    | 267/469 [00:10<00:07, 26.57it/s]
Testing:  58%|█████▊    | 270/469 [00:10<00:07, 26.73it/s]
Testing:  58%|█████▊    | 273/469 [00:10<00:07, 26.62it/s]
Testing:  59%|█████▉    | 276/469 [00:10<00:08, 23.97it/s]
Testing:  59%|█████▉    | 279/469 [00:10<00:07, 23.92it/s]
Testing:  60%|██████    | 282/469 [00:10<00:08, 23.25it/s]
Testing:  61%|██████    | 285/469 [00:11<00:07, 23.11it/s]
Testing:  61%|██████▏   | 288/469 [00:11<00:07, 23.20it/s]
Testing:  62%|██████▏   | 291/469 [00:11<00:07, 24.18it/s]
Testing:  63%|██████▎   | 294/469 [00:11<00:06, 25.03it/s]
Testing:  63%|██████▎   | 297/469 [00:11<00:07, 23.51it/s]
Testing:  64%|██████▍   | 300/469 [00:11<00:07, 23.90it/s]
Testing:  65%|██████▍   | 303/469 [00:11<00:06, 24.17it/s]
Testing:  65%|██████▌   | 306/469 [00:11<00:06, 24.73it/s]
Testing:  66%|██████▌   | 309/469 [00:12<00:06, 23.75it/s]
Testing:  67%|██████▋   | 312/469 [00:12<00:06, 24.73it/s]
Testing:  67%|██████▋   | 315/469 [00:12<00:06, 25.20it/s]
Testing:  68%|██████▊   | 318/469 [00:12<00:06, 24.11it/s]
Testing:  68%|██████▊   | 321/469 [00:12<00:06, 24.49it/s]
Testing:  69%|██████▉   | 324/469 [00:12<00:05, 24.98it/s]
Testing:  70%|██████▉   | 327/469 [00:12<00:05, 25.23it/s]
Testing:  70%|███████   | 330/469 [00:12<00:05, 25.88it/s]
Testing:  71%|███████   | 333/469 [00:13<00:05, 26.86it/s]
Testing:  72%|███████▏  | 336/469 [00:13<00:05, 25.49it/s]
Testing:  72%|███████▏  | 339/469 [00:13<00:05, 24.34it/s]
Testing:  73%|███████▎  | 343/469 [00:13<00:04, 25.97it/s]
Testing:  74%|███████▍  | 346/469 [00:13<00:04, 25.42it/s]
Testing:  74%|███████▍  | 349/469 [00:13<00:04, 26.31it/s]
Testing:  75%|███████▌  | 352/469 [00:13<00:04, 26.34it/s]
Testing:  76%|███████▌  | 355/469 [00:13<00:04, 26.52it/s]
Testing:  76%|███████▋  | 358/469 [00:13<00:04, 26.30it/s]
Testing:  77%|███████▋  | 361/469 [00:14<00:04, 24.96it/s]
Testing:  78%|███████▊  | 364/469 [00:14<00:04, 25.73it/s]
Testing:  78%|███████▊  | 367/469 [00:14<00:03, 26.49it/s]
Testing:  79%|███████▉  | 370/469 [00:14<00:03, 25.54it/s]
Testing:  80%|███████▉  | 373/469 [00:14<00:03, 25.23it/s]
Testing:  80%|████████  | 376/469 [00:14<00:03, 25.81it/s]
Testing:  81%|████████  | 379/469 [00:14<00:03, 25.50it/s]
Testing:  81%|████████▏ | 382/469 [00:14<00:03, 22.35it/s]
Testing:  82%|████████▏ | 385/469 [00:15<00:03, 22.78it/s]
Testing:  83%|████████▎ | 388/469 [00:15<00:03, 23.63it/s]
Testing:  83%|████████▎ | 391/469 [00:15<00:03, 24.63it/s]
Testing:  84%|████████▍ | 394/469 [00:15<00:03, 24.94it/s]
Testing:  85%|████████▍ | 397/469 [00:15<00:02, 24.91it/s]
Testing:  85%|████████▌ | 400/469 [00:15<00:02, 25.05it/s]
Testing:  86%|████████▌ | 403/469 [00:15<00:02, 24.92it/s]
Testing:  87%|████████▋ | 406/469 [00:15<00:02, 25.89it/s]
Testing:  87%|████████▋ | 409/469 [00:16<00:02, 26.42it/s]
Testing:  88%|████████▊ | 412/469 [00:16<00:02, 26.33it/s]
Testing:  88%|████████▊ | 415/469 [00:16<00:02, 26.97it/s]
Testing:  89%|████████▉ | 418/469 [00:16<00:01, 25.89it/s]
Testing:  90%|████████▉ | 421/469 [00:16<00:01, 25.90it/s]
Testing:  90%|█████████ | 424/469 [00:16<00:01, 25.98it/s]
Testing:  91%|█████████ | 427/469 [00:16<00:01, 25.80it/s]
Testing:  92%|█████████▏| 430/469 [00:16<00:01, 26.28it/s]
Testing:  92%|█████████▏| 433/469 [00:16<00:01, 26.57it/s]
Testing:  93%|█████████▎| 436/469 [00:17<00:01, 27.27it/s]
Testing:  94%|█████████▎| 439/469 [00:17<00:01, 27.22it/s]
Testing:  94%|█████████▍| 442/469 [00:17<00:01, 26.79it/s]
Testing:  95%|█████████▍| 445/469 [00:17<00:00, 26.80it/s]
Testing:  96%|█████████▌| 448/469 [00:17<00:00, 26.22it/s]
Testing:  96%|█████████▌| 451/469 [00:17<00:00, 26.76it/s]
Testing:  97%|█████████▋| 454/469 [00:17<00:00, 26.92it/s]
Testing:  97%|█████████▋| 457/469 [00:17<00:00, 26.60it/s]
Testing:  98%|█████████▊| 460/469 [00:17<00:00, 24.63it/s]
Testing:  99%|█████████▊| 463/469 [00:18<00:00, 24.30it/s]
Testing:  99%|█████████▉| 466/469 [00:18<00:00, 24.91it/s]--------------------------------------------------------------------------------
DATALOADER:0 TEST RESULTS
{'test_rmse': 0.5170217752456665}
--------------------------------------------------------------------------------

Testing: 100%|██████████| 469/469 [00:18<00:00, 25.58it/s]
  0%|          | 0/469 [02:53<?, ?it/s]
Global seed set to 44

['p_np'] False
2 1
iupac_vocab_size: 1491
training... 1491

  0%|          | 0/469 [00:00<?, ?it/s]Some weights of the model checkpoint at checkpoints/iupac were not used when initializing GPT2ForSequenceClassification: ['lm_head.weight']
- This IS expected if you are initializing GPT2ForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing GPT2ForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
GPU available: True, used: True
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]

  | Name        | Type                          | Params
--------------------------------------------------------------
0 | transformer | GPT2ForSequenceClassification | 7.1 M 
--------------------------------------------------------------
75.9 K    Trainable params
7.0 M     Non-trainable params
7.1 M     Total params
28.416    Total estimated model params size (MB)

Validation sanity check: 0it [00:00, ?it/s]
Validation sanity check:   0%|          | 0/2 [00:00<?, ?it/s]
                                                              Global seed set to 44


Training: 0it [00:00, ?it/s]
Training:   0%|          | 0/938 [00:00<?, ?it/s]
Epoch 0:   0%|          | 0/938 [00:00<?, ?it/s] 
Epoch 0:   0%|          | 1/938 [00:00<01:30, 10.38it/s, loss=3.74, v_num=9]
Epoch 0:   0%|          | 2/938 [00:00<01:09, 13.40it/s, loss=3.74, v_num=9]
Epoch 0:   0%|          | 2/938 [00:00<01:10, 13.37it/s, loss=3.54, v_num=9]
Epoch 0:   0%|          | 3/938 [00:00<01:27, 10.74it/s, loss=3.58, v_num=9]
Epoch 0:   0%|          | 4/938 [00:00<01:19, 11.76it/s, loss=3.58, v_num=9]
Epoch 0:   0%|          | 4/938 [00:00<01:19, 11.74it/s, loss=3.61, v_num=9]
Epoch 0:   1%|          | 5/938 [00:00<01:16, 12.21it/s, loss=3.59, v_num=9]
Epoch 0:   1%|          | 6/938 [00:00<01:15, 12.40it/s, loss=3.59, v_num=9]
Epoch 0:   1%|          | 6/938 [00:00<01:15, 12.39it/s, loss=3.54, v_num=9]
Epoch 0:   1%|          | 7/938 [00:00<01:11, 12.96it/s, loss=3.53, v_num=9]
Epoch 0:   1%|          | 8/938 [00:00<01:14, 12.55it/s, loss=3.53, v_num=9]
Epoch 0:   1%|          | 8/938 [00:00<01:14, 12.54it/s, loss=3.52, v_num=9]
Epoch 0:   1%|          | 9/938 [00:00<01:12, 12.79it/s, loss=3.52, v_num=9]
Epoch 0:   1%|          | 10/938 [00:00<01:10, 13.24it/s, loss=3.52, v_num=9]
Epoch 0:   1%|          | 10/938 [00:00<01:10, 13.23it/s, loss=3.54, v_num=9]
Epoch 0:   1%|          | 11/938 [00:00<01:09, 13.36it/s, loss=3.53, v_num=9]
Epoch 0:   1%|▏         | 12/938 [00:00<01:08, 13.48it/s, loss=3.53, v_num=9]
Epoch 0:   1%|▏         | 12/938 [00:00<01:08, 13.47it/s, loss=3.52, v_num=9]
Epoch 0:   1%|▏         | 13/938 [00:00<01:07, 13.66it/s, loss=3.49, v_num=9]
Epoch 0:   1%|▏         | 14/938 [00:01<01:06, 13.86it/s, loss=3.49, v_num=9]
Epoch 0:   1%|▏         | 14/938 [00:01<01:06, 13.85it/s, loss=3.48, v_num=9]
Epoch 0:   2%|▏         | 15/938 [00:01<01:06, 13.89it/s, loss=3.49, v_num=9]
Epoch 0:   2%|▏         | 16/938 [00:01<01:06, 13.94it/s, loss=3.49, v_num=9]
Epoch 0:   2%|▏         | 16/938 [00:01<01:06, 13.94it/s, loss=3.47, v_num=9]
Epoch 0:   2%|▏         | 17/938 [00:01<01:05, 14.03it/s, loss=3.46, v_num=9]
Epoch 0:   2%|▏         | 18/938 [00:01<01:05, 14.07it/s, loss=3.46, v_num=9]
Epoch 0:   2%|▏         | 18/938 [00:01<01:05, 14.07it/s, loss=3.44, v_num=9]
Epoch 0:   2%|▏         | 19/938 [00:01<01:04, 14.14it/s, loss=3.43, v_num=9]
Epoch 0:   2%|▏         | 20/938 [00:01<01:04, 14.18it/s, loss=3.43, v_num=9]
Epoch 0:   2%|▏         | 20/938 [00:01<01:04, 14.18it/s, loss=3.4, v_num=9] 
Epoch 0:   2%|▏         | 21/938 [00:01<01:04, 14.29it/s, loss=3.35, v_num=9]
Epoch 0:   2%|▏         | 22/938 [00:01<01:03, 14.40it/s, loss=3.35, v_num=9]
Epoch 0:   2%|▏         | 22/938 [00:01<01:03, 14.40it/s, loss=3.31, v_num=9]
Epoch 0:   2%|▏         | 23/938 [00:01<01:03, 14.32it/s, loss=3.27, v_num=9]
Epoch 0:   3%|▎         | 24/938 [00:01<01:04, 14.27it/s, loss=3.27, v_num=9]
Epoch 0:   3%|▎         | 24/938 [00:01<01:04, 14.27it/s, loss=3.2, v_num=9] 
Epoch 0:   3%|▎         | 25/938 [00:01<01:03, 14.31it/s, loss=3.14, v_num=9]
Epoch 0:   3%|▎         | 26/938 [00:01<01:03, 14.27it/s, loss=3.14, v_num=9]
Epoch 0:   3%|▎         | 26/938 [00:01<01:03, 14.27it/s, loss=3.11, v_num=9]
Epoch 0:   3%|▎         | 27/938 [00:01<01:03, 14.30it/s, loss=3.07, v_num=9]
Epoch 0:   3%|▎         | 28/938 [00:01<01:03, 14.35it/s, loss=3.07, v_num=9]
Epoch 0:   3%|▎         | 28/938 [00:01<01:03, 14.34it/s, loss=3.03, v_num=9]
Epoch 0:   3%|▎         | 29/938 [00:02<01:03, 14.33it/s, loss=2.96, v_num=9]
Epoch 0:   3%|▎         | 30/938 [00:02<01:02, 14.42it/s, loss=2.96, v_num=9]
Epoch 0:   3%|▎         | 30/938 [00:02<01:02, 14.42it/s, loss=2.9, v_num=9] 
Epoch 0:   3%|▎         | 31/938 [00:02<01:02, 14.40it/s, loss=2.84, v_num=9]
Epoch 0:   3%|▎         | 32/938 [00:02<01:02, 14.43it/s, loss=2.84, v_num=9]
Epoch 0:   3%|▎         | 32/938 [00:02<01:02, 14.43it/s, loss=2.78, v_num=9]
Epoch 0:   4%|▎         | 33/938 [00:02<01:02, 14.50it/s, loss=2.71, v_num=9]
Epoch 0:   4%|▎         | 34/938 [00:02<01:02, 14.40it/s, loss=2.71, v_num=9]
Epoch 0:   4%|▎         | 34/938 [00:02<01:02, 14.40it/s, loss=2.63, v_num=9]
Epoch 0:   4%|▎         | 35/938 [00:02<01:02, 14.36it/s, loss=2.55, v_num=9]
Epoch 0:   4%|▍         | 36/938 [00:02<01:02, 14.41it/s, loss=2.55, v_num=9]
Epoch 0:   4%|▍         | 36/938 [00:02<01:02, 14.41it/s, loss=2.5, v_num=9] 
Epoch 0:   4%|▍         | 37/938 [00:02<01:02, 14.36it/s, loss=2.42, v_num=9]
Epoch 0:   4%|▍         | 38/938 [00:02<01:02, 14.36it/s, loss=2.42, v_num=9]
Epoch 0:   4%|▍         | 38/938 [00:02<01:02, 14.36it/s, loss=2.34, v_num=9]
Epoch 0:   4%|▍         | 39/938 [00:02<01:02, 14.32it/s, loss=2.27, v_num=9]
Epoch 0:   4%|▍         | 40/938 [00:02<01:02, 14.34it/s, loss=2.27, v_num=9]
Epoch 0:   4%|▍         | 40/938 [00:02<01:02, 14.33it/s, loss=2.22, v_num=9]
Epoch 0:   4%|▍         | 41/938 [00:02<01:02, 14.32it/s, loss=2.17, v_num=9]
Epoch 0:   4%|▍         | 42/938 [00:02<01:02, 14.34it/s, loss=2.17, v_num=9]
Epoch 0:   4%|▍         | 42/938 [00:02<01:02, 14.34it/s, loss=2.12, v_num=9]
Epoch 0:   5%|▍         | 43/938 [00:02<01:02, 14.36it/s, loss=2.06, v_num=9]
Epoch 0:   5%|▍         | 44/938 [00:03<01:02, 14.32it/s, loss=2.06, v_num=9]
Epoch 0:   5%|▍         | 44/938 [00:03<01:02, 14.31it/s, loss=2.04, v_num=9]
Epoch 0:   5%|▍         | 45/938 [00:03<01:02, 14.33it/s, loss=2, v_num=9]   
Epoch 0:   5%|▍         | 46/938 [00:03<01:02, 14.33it/s, loss=2, v_num=9]
Epoch 0:   5%|▍         | 46/938 [00:03<01:02, 14.33it/s, loss=1.96, v_num=9]
Epoch 0:   5%|▌         | 47/938 [00:03<01:02, 14.34it/s, loss=1.9, v_num=9] 
Epoch 0:   5%|▌         | 48/938 [00:03<01:02, 14.31it/s, loss=1.9, v_num=9]
Epoch 0:   5%|▌         | 48/938 [00:03<01:02, 14.30it/s, loss=1.85, v_num=9]
Epoch 0:   5%|▌         | 49/938 [00:03<01:02, 14.33it/s, loss=1.81, v_num=9]
Epoch 0:   5%|▌         | 50/938 [00:03<01:02, 14.29it/s, loss=1.81, v_num=9]
Epoch 0:   5%|▌         | 50/938 [00:03<01:02, 14.29it/s, loss=1.77, v_num=9]
Epoch 0:   5%|▌         | 51/938 [00:03<01:02, 14.29it/s, loss=1.73, v_num=9]
Epoch 0:   6%|▌         | 52/938 [00:03<01:01, 14.31it/s, loss=1.73, v_num=9]
Epoch 0:   6%|▌         | 52/938 [00:03<01:01, 14.31it/s, loss=1.7, v_num=9] 
Epoch 0:   6%|▌         | 53/938 [00:03<01:01, 14.30it/s, loss=1.69, v_num=9]
Epoch 0:   6%|▌         | 54/938 [00:03<01:01, 14.35it/s, loss=1.69, v_num=9]
Epoch 0:   6%|▌         | 54/938 [00:03<01:01, 14.35it/s, loss=1.7, v_num=9] 
Epoch 0:   6%|▌         | 55/938 [00:03<01:01, 14.33it/s, loss=1.68, v_num=9]
Epoch 0:   6%|▌         | 56/938 [00:03<01:01, 14.29it/s, loss=1.68, v_num=9]
Epoch 0:   6%|▌         | 56/938 [00:03<01:01, 14.29it/s, loss=1.66, v_num=9]
Epoch 0:   6%|▌         | 57/938 [00:03<01:01, 14.26it/s, loss=1.65, v_num=9]
Epoch 0:   6%|▌         | 58/938 [00:04<01:01, 14.30it/s, loss=1.65, v_num=9]
Epoch 0:   6%|▌         | 58/938 [00:04<01:01, 14.30it/s, loss=1.65, v_num=9]
Epoch 0:   6%|▋         | 59/938 [00:04<01:01, 14.27it/s, loss=1.64, v_num=9]
Epoch 0:   6%|▋         | 60/938 [00:04<01:01, 14.29it/s, loss=1.64, v_num=9]
Epoch 0:   6%|▋         | 60/938 [00:04<01:01, 14.29it/s, loss=1.63, v_num=9]
Epoch 0:   7%|▋         | 61/938 [00:04<01:01, 14.28it/s, loss=1.61, v_num=9]
Epoch 0:   7%|▋         | 62/938 [00:04<01:01, 14.28it/s, loss=1.61, v_num=9]
Epoch 0:   7%|▋         | 62/938 [00:04<01:01, 14.28it/s, loss=1.62, v_num=9]
Epoch 0:   7%|▋         | 63/938 [00:04<01:01, 14.31it/s, loss=1.62, v_num=9]
Epoch 0:   7%|▋         | 64/938 [00:04<01:01, 14.32it/s, loss=1.62, v_num=9]
Epoch 0:   7%|▋         | 64/938 [00:04<01:01, 14.32it/s, loss=1.62, v_num=9]
Epoch 0:   7%|▋         | 65/938 [00:04<01:01, 14.29it/s, loss=1.63, v_num=9]
Epoch 0:   7%|▋         | 66/938 [00:04<01:00, 14.33it/s, loss=1.63, v_num=9]
Epoch 0:   7%|▋         | 66/938 [00:04<01:00, 14.32it/s, loss=1.62, v_num=9]
Epoch 0:   7%|▋         | 67/938 [00:04<01:00, 14.32it/s, loss=1.64, v_num=9]
Epoch 0:   7%|▋         | 68/938 [00:04<01:00, 14.33it/s, loss=1.64, v_num=9]
Epoch 0:   7%|▋         | 68/938 [00:04<01:00, 14.32it/s, loss=1.65, v_num=9]
Epoch 0:   7%|▋         | 69/938 [00:04<01:00, 14.31it/s, loss=1.65, v_num=9]
Epoch 0:   7%|▋         | 70/938 [00:04<01:00, 14.32it/s, loss=1.65, v_num=9]
Epoch 0:   7%|▋         | 70/938 [00:04<01:00, 14.32it/s, loss=1.66, v_num=9]
Epoch 0:   8%|▊         | 71/938 [00:04<01:00, 14.33it/s, loss=1.67, v_num=9]
Epoch 0:   8%|▊         | 72/938 [00:05<01:00, 14.36it/s, loss=1.67, v_num=9]
Epoch 0:   8%|▊         | 72/938 [00:05<01:00, 14.36it/s, loss=1.67, v_num=9]
Epoch 0:   8%|▊         | 73/938 [00:05<01:00, 14.40it/s, loss=1.67, v_num=9]
Epoch 0:   8%|▊         | 74/938 [00:05<00:59, 14.43it/s, loss=1.67, v_num=9]
Epoch 0:   8%|▊         | 74/938 [00:05<00:59, 14.43it/s, loss=1.64, v_num=9]
Epoch 0:   8%|▊         | 75/938 [00:05<00:59, 14.44it/s, loss=1.65, v_num=9]
Epoch 0:   8%|▊         | 76/938 [00:05<00:59, 14.46it/s, loss=1.65, v_num=9]
Epoch 0:   8%|▊         | 76/938 [00:05<00:59, 14.46it/s, loss=1.65, v_num=9]
Epoch 0:   8%|▊         | 77/938 [00:05<00:59, 14.45it/s, loss=1.67, v_num=9]
Epoch 0:   8%|▊         | 78/938 [00:05<00:59, 14.45it/s, loss=1.67, v_num=9]
Epoch 0:   8%|▊         | 78/938 [00:05<00:59, 14.45it/s, loss=1.67, v_num=9]
Epoch 0:   8%|▊         | 79/938 [00:05<00:59, 14.41it/s, loss=1.67, v_num=9]
Epoch 0:   9%|▊         | 80/938 [00:05<00:59, 14.42it/s, loss=1.67, v_num=9]
Epoch 0:   9%|▊         | 80/938 [00:05<00:59, 14.42it/s, loss=1.67, v_num=9]
Epoch 0:   9%|▊         | 81/938 [00:05<00:59, 14.42it/s, loss=1.67, v_num=9]
Epoch 0:   9%|▊         | 82/938 [00:05<00:59, 14.29it/s, loss=1.67, v_num=9]
Epoch 0:   9%|▊         | 82/938 [00:05<00:59, 14.29it/s, loss=1.66, v_num=9]
Epoch 0:   9%|▉         | 83/938 [00:05<01:00, 14.25it/s, loss=1.66, v_num=9]
Epoch 0:   9%|▉         | 84/938 [00:05<00:59, 14.26it/s, loss=1.66, v_num=9]
Epoch 0:   9%|▉         | 84/938 [00:05<00:59, 14.26it/s, loss=1.66, v_num=9]
Epoch 0:   9%|▉         | 85/938 [00:05<00:59, 14.27it/s, loss=1.67, v_num=9]
Epoch 0:   9%|▉         | 86/938 [00:06<00:59, 14.27it/s, loss=1.67, v_num=9]
Epoch 0:   9%|▉         | 86/938 [00:06<00:59, 14.27it/s, loss=1.65, v_num=9]
Epoch 0:   9%|▉         | 87/938 [00:06<00:59, 14.28it/s, loss=1.66, v_num=9]
Epoch 0:   9%|▉         | 88/938 [00:06<00:59, 14.25it/s, loss=1.66, v_num=9]
Epoch 0:   9%|▉         | 88/938 [00:06<00:59, 14.25it/s, loss=1.66, v_num=9]
Epoch 0:   9%|▉         | 89/938 [00:06<00:59, 14.27it/s, loss=1.68, v_num=9]
Epoch 0:  10%|▉         | 90/938 [00:06<00:59, 14.30it/s, loss=1.68, v_num=9]
Epoch 0:  10%|▉         | 90/938 [00:06<00:59, 14.29it/s, loss=1.68, v_num=9]
Epoch 0:  10%|▉         | 91/938 [00:06<00:59, 14.30it/s, loss=1.68, v_num=9]
Epoch 0:  10%|▉         | 92/938 [00:06<00:59, 14.33it/s, loss=1.68, v_num=9]
Epoch 0:  10%|▉         | 92/938 [00:06<00:59, 14.33it/s, loss=1.68, v_num=9]
Epoch 0:  10%|▉         | 93/938 [00:06<00:59, 14.32it/s, loss=1.68, v_num=9]
Epoch 0:  10%|█         | 94/938 [00:06<00:58, 14.33it/s, loss=1.68, v_num=9]
Epoch 0:  10%|█         | 94/938 [00:06<00:58, 14.33it/s, loss=1.69, v_num=9]
Epoch 0:  10%|█         | 95/938 [00:06<00:58, 14.30it/s, loss=1.68, v_num=9]
Epoch 0:  10%|█         | 96/938 [00:06<00:58, 14.34it/s, loss=1.68, v_num=9]
Epoch 0:  10%|█         | 96/938 [00:06<00:58, 14.34it/s, loss=1.68, v_num=9]
Epoch 0:  10%|█         | 97/938 [00:06<00:58, 14.34it/s, loss=1.67, v_num=9]
Epoch 0:  10%|█         | 98/938 [00:06<00:58, 14.36it/s, loss=1.67, v_num=9]
Epoch 0:  10%|█         | 98/938 [00:06<00:58, 14.36it/s, loss=1.68, v_num=9]
Epoch 0:  11%|█         | 99/938 [00:06<00:58, 14.36it/s, loss=1.67, v_num=9]
Epoch 0:  11%|█         | 100/938 [00:06<00:58, 14.37it/s, loss=1.67, v_num=9]
Epoch 0:  11%|█         | 100/938 [00:06<00:58, 14.37it/s, loss=1.68, v_num=9]
Epoch 0:  11%|█         | 101/938 [00:07<00:58, 14.36it/s, loss=1.69, v_num=9]
Epoch 0:  11%|█         | 102/938 [00:07<00:58, 14.35it/s, loss=1.69, v_num=9]
Epoch 0:  11%|█         | 102/938 [00:07<00:58, 14.35it/s, loss=1.69, v_num=9]
Epoch 0:  11%|█         | 103/938 [00:07<00:58, 14.37it/s, loss=1.69, v_num=9]
Epoch 0:  11%|█         | 104/938 [00:07<00:58, 14.36it/s, loss=1.69, v_num=9]
Epoch 0:  11%|█         | 104/938 [00:07<00:58, 14.36it/s, loss=1.68, v_num=9]
Epoch 0:  11%|█         | 105/938 [00:07<00:57, 14.37it/s, loss=1.67, v_num=9]
Epoch 0:  11%|█▏        | 106/938 [00:07<00:57, 14.37it/s, loss=1.67, v_num=9]
Epoch 0:  11%|█▏        | 106/938 [00:07<00:57, 14.37it/s, loss=1.68, v_num=9]
Epoch 0:  11%|█▏        | 107/938 [00:07<00:57, 14.37it/s, loss=1.66, v_num=9]
Epoch 0:  12%|█▏        | 108/938 [00:07<00:57, 14.38it/s, loss=1.66, v_num=9]
Epoch 0:  12%|█▏        | 108/938 [00:07<00:57, 14.38it/s, loss=1.64, v_num=9]
Epoch 0:  12%|█▏        | 109/938 [00:07<00:58, 14.28it/s, loss=1.64, v_num=9]
Epoch 0:  12%|█▏        | 110/938 [00:07<00:58, 14.26it/s, loss=1.64, v_num=9]
Epoch 0:  12%|█▏        | 110/938 [00:07<00:58, 14.26it/s, loss=1.66, v_num=9]
Epoch 0:  12%|█▏        | 111/938 [00:07<00:57, 14.27it/s, loss=1.65, v_num=9]
Epoch 0:  12%|█▏        | 112/938 [00:07<00:57, 14.28it/s, loss=1.65, v_num=9]
Epoch 0:  12%|█▏        | 112/938 [00:07<00:57, 14.28it/s, loss=1.64, v_num=9]
Epoch 0:  12%|█▏        | 113/938 [00:07<00:57, 14.28it/s, loss=1.63, v_num=9]
Epoch 0:  12%|█▏        | 114/938 [00:07<00:57, 14.28it/s, loss=1.63, v_num=9]
Epoch 0:  12%|█▏        | 114/938 [00:07<00:57, 14.28it/s, loss=1.63, v_num=9]
Epoch 0:  12%|█▏        | 115/938 [00:08<00:57, 14.24it/s, loss=1.64, v_num=9]
Epoch 0:  12%|█▏        | 116/938 [00:08<00:57, 14.25it/s, loss=1.64, v_num=9]
Epoch 0:  12%|█▏        | 116/938 [00:08<00:57, 14.25it/s, loss=1.64, v_num=9]
Epoch 0:  12%|█▏        | 117/938 [00:08<00:57, 14.24it/s, loss=1.62, v_num=9]
Epoch 0:  13%|█▎        | 118/938 [00:08<00:57, 14.24it/s, loss=1.62, v_num=9]
Epoch 0:  13%|█▎        | 118/938 [00:08<00:57, 14.24it/s, loss=1.64, v_num=9]
Epoch 0:  13%|█▎        | 119/938 [00:08<00:57, 14.26it/s, loss=1.64, v_num=9]
Epoch 0:  13%|█▎        | 120/938 [00:08<00:57, 14.19it/s, loss=1.64, v_num=9]
Epoch 0:  13%|█▎        | 120/938 [00:08<00:57, 14.19it/s, loss=1.63, v_num=9]
Epoch 0:  13%|█▎        | 121/938 [00:08<00:57, 14.20it/s, loss=1.61, v_num=9]
Epoch 0:  13%|█▎        | 122/938 [00:08<00:57, 14.22it/s, loss=1.61, v_num=9]
Epoch 0:  13%|█▎        | 122/938 [00:08<00:57, 14.21it/s, loss=1.62, v_num=9]
Epoch 0:  13%|█▎        | 123/938 [00:08<00:57, 14.23it/s, loss=1.62, v_num=9]
Epoch 0:  13%|█▎        | 124/938 [00:08<00:57, 14.18it/s, loss=1.62, v_num=9]
Epoch 0:  13%|█▎        | 124/938 [00:08<00:57, 14.17it/s, loss=1.62, v_num=9]
Epoch 0:  13%|█▎        | 125/938 [00:08<00:57, 14.19it/s, loss=1.61, v_num=9]
Epoch 0:  13%|█▎        | 126/938 [00:08<00:57, 14.21it/s, loss=1.61, v_num=9]
Epoch 0:  13%|█▎        | 126/938 [00:08<00:57, 14.21it/s, loss=1.6, v_num=9] 
Epoch 0:  14%|█▎        | 127/938 [00:08<00:57, 14.22it/s, loss=1.56, v_num=9]
Epoch 0:  14%|█▎        | 128/938 [00:08<00:56, 14.24it/s, loss=1.56, v_num=9]
Epoch 0:  14%|█▎        | 128/938 [00:08<00:56, 14.24it/s, loss=1.57, v_num=9]
Epoch 0:  14%|█▍        | 129/938 [00:09<00:56, 14.25it/s, loss=1.57, v_num=9]
Epoch 0:  14%|█▍        | 130/938 [00:09<00:56, 14.24it/s, loss=1.57, v_num=9]
Epoch 0:  14%|█▍        | 130/938 [00:09<00:56, 14.24it/s, loss=1.55, v_num=9]
Epoch 0:  14%|█▍        | 131/938 [00:09<00:56, 14.26it/s, loss=1.54, v_num=9]
Epoch 0:  14%|█▍        | 132/938 [00:09<00:56, 14.27it/s, loss=1.54, v_num=9]
Epoch 0:  14%|█▍        | 132/938 [00:09<00:56, 14.27it/s, loss=1.53, v_num=9]
Epoch 0:  14%|█▍        | 133/938 [00:09<00:56, 14.28it/s, loss=1.52, v_num=9]
Epoch 0:  14%|█▍        | 134/938 [00:09<00:56, 14.29it/s, loss=1.52, v_num=9]
Epoch 0:  14%|█▍        | 134/938 [00:09<00:56, 14.29it/s, loss=1.53, v_num=9]
Epoch 0:  14%|█▍        | 135/938 [00:09<00:56, 14.29it/s, loss=1.5, v_num=9] 
Epoch 0:  14%|█▍        | 136/938 [00:09<00:56, 14.30it/s, loss=1.5, v_num=9]
Epoch 0:  14%|█▍        | 136/938 [00:09<00:56, 14.30it/s, loss=1.49, v_num=9]
Epoch 0:  15%|█▍        | 137/938 [00:09<00:56, 14.29it/s, loss=1.48, v_num=9]
Epoch 0:  15%|█▍        | 138/938 [00:09<00:55, 14.30it/s, loss=1.48, v_num=9]
Epoch 0:  15%|█▍        | 138/938 [00:09<00:55, 14.30it/s, loss=1.46, v_num=9]
Epoch 0:  15%|█▍        | 139/938 [00:09<00:55, 14.31it/s, loss=1.45, v_num=9]
Epoch 0:  15%|█▍        | 140/938 [00:09<00:55, 14.29it/s, loss=1.45, v_num=9]
Epoch 0:  15%|█▍        | 140/938 [00:09<00:55, 14.29it/s, loss=1.45, v_num=9]
Epoch 0:  15%|█▌        | 141/938 [00:09<00:55, 14.24it/s, loss=1.44, v_num=9]
Epoch 0:  15%|█▌        | 142/938 [00:09<00:55, 14.22it/s, loss=1.44, v_num=9]
Epoch 0:  15%|█▌        | 142/938 [00:09<00:55, 14.22it/s, loss=1.4, v_num=9] 
Epoch 0:  15%|█▌        | 143/938 [00:10<00:55, 14.26it/s, loss=1.39, v_num=9]
Epoch 0:  15%|█▌        | 144/938 [00:10<00:55, 14.25it/s, loss=1.39, v_num=9]
Epoch 0:  15%|█▌        | 144/938 [00:10<00:55, 14.25it/s, loss=1.36, v_num=9]
Epoch 0:  15%|█▌        | 145/938 [00:10<00:55, 14.27it/s, loss=1.36, v_num=9]
Epoch 0:  16%|█▌        | 146/938 [00:10<00:55, 14.28it/s, loss=1.36, v_num=9]
Epoch 0:  16%|█▌        | 146/938 [00:10<00:55, 14.28it/s, loss=1.35, v_num=9]
Epoch 0:  16%|█▌        | 147/938 [00:10<00:55, 14.28it/s, loss=1.36, v_num=9]
Epoch 0:  16%|█▌        | 148/938 [00:10<00:55, 14.27it/s, loss=1.36, v_num=9]
Epoch 0:  16%|█▌        | 148/938 [00:10<00:55, 14.27it/s, loss=1.35, v_num=9]
Epoch 0:  16%|█▌        | 149/938 [00:10<00:55, 14.30it/s, loss=1.32, v_num=9]
Epoch 0:  16%|█▌        | 150/938 [00:10<00:55, 14.30it/s, loss=1.32, v_num=9]
Epoch 0:  16%|█▌        | 150/938 [00:10<00:55, 14.30it/s, loss=1.32, v_num=9]
Epoch 0:  16%|█▌        | 151/938 [00:10<00:54, 14.32it/s, loss=1.29, v_num=9]
Epoch 0:  16%|█▌        | 152/938 [00:10<00:54, 14.32it/s, loss=1.29, v_num=9]
Epoch 0:  16%|█▌        | 152/938 [00:10<00:54, 14.32it/s, loss=1.28, v_num=9]
Epoch 0:  16%|█▋        | 153/938 [00:10<00:54, 14.34it/s, loss=1.27, v_num=9]
Epoch 0:  16%|█▋        | 154/938 [00:10<00:54, 14.34it/s, loss=1.27, v_num=9]
Epoch 0:  16%|█▋        | 154/938 [00:10<00:54, 14.34it/s, loss=1.25, v_num=9]
Epoch 0:  17%|█▋        | 155/938 [00:10<00:54, 14.36it/s, loss=1.23, v_num=9]
Epoch 0:  17%|█▋        | 156/938 [00:10<00:54, 14.37it/s, loss=1.23, v_num=9]
Epoch 0:  17%|█▋        | 156/938 [00:10<00:54, 14.37it/s, loss=1.22, v_num=9]
Epoch 0:  17%|█▋        | 157/938 [00:10<00:54, 14.38it/s, loss=1.22, v_num=9]
Epoch 0:  17%|█▋        | 158/938 [00:10<00:54, 14.38it/s, loss=1.22, v_num=9]
Epoch 0:  17%|█▋        | 158/938 [00:10<00:54, 14.38it/s, loss=1.21, v_num=9]
Epoch 0:  17%|█▋        | 159/938 [00:11<00:54, 14.41it/s, loss=1.2, v_num=9] 
Epoch 0:  17%|█▋        | 160/938 [00:11<00:54, 14.40it/s, loss=1.2, v_num=9]
Epoch 0:  17%|█▋        | 160/938 [00:11<00:54, 14.40it/s, loss=1.19, v_num=9]
Epoch 0:  17%|█▋        | 161/938 [00:11<00:53, 14.41it/s, loss=1.17, v_num=9]
Epoch 0:  17%|█▋        | 162/938 [00:11<00:53, 14.40it/s, loss=1.17, v_num=9]
Epoch 0:  17%|█▋        | 162/938 [00:11<00:53, 14.40it/s, loss=1.17, v_num=9]
Epoch 0:  17%|█▋        | 163/938 [00:11<00:53, 14.40it/s, loss=1.17, v_num=9]
Epoch 0:  17%|█▋        | 164/938 [00:11<00:53, 14.40it/s, loss=1.17, v_num=9]
Epoch 0:  17%|█▋        | 164/938 [00:11<00:53, 14.40it/s, loss=1.18, v_num=9]
Epoch 0:  18%|█▊        | 165/938 [00:11<00:53, 14.40it/s, loss=1.16, v_num=9]
Epoch 0:  18%|█▊        | 166/938 [00:11<00:53, 14.40it/s, loss=1.16, v_num=9]
Epoch 0:  18%|█▊        | 166/938 [00:11<00:53, 14.40it/s, loss=1.18, v_num=9]
Epoch 0:  18%|█▊        | 167/938 [00:11<00:53, 14.42it/s, loss=1.17, v_num=9]
Epoch 0:  18%|█▊        | 168/938 [00:11<00:53, 14.39it/s, loss=1.17, v_num=9]
Epoch 0:  18%|█▊        | 168/938 [00:11<00:53, 14.39it/s, loss=1.16, v_num=9]
Epoch 0:  18%|█▊        | 169/938 [00:11<00:53, 14.38it/s, loss=1.15, v_num=9]
Epoch 0:  18%|█▊        | 170/938 [00:11<00:53, 14.38it/s, loss=1.15, v_num=9]
Epoch 0:  18%|█▊        | 170/938 [00:11<00:53, 14.38it/s, loss=1.14, v_num=9]
Epoch 0:  18%|█▊        | 171/938 [00:11<00:53, 14.38it/s, loss=1.15, v_num=9]
Epoch 0:  18%|█▊        | 172/938 [00:11<00:53, 14.39it/s, loss=1.15, v_num=9]
Epoch 0:  18%|█▊        | 172/938 [00:11<00:53, 14.39it/s, loss=1.14, v_num=9]
Epoch 0:  18%|█▊        | 173/938 [00:12<00:53, 14.40it/s, loss=1.13, v_num=9]
Epoch 0:  19%|█▊        | 174/938 [00:12<00:53, 14.41it/s, loss=1.13, v_num=9]
Epoch 0:  19%|█▊        | 174/938 [00:12<00:53, 14.41it/s, loss=1.12, v_num=9]
Epoch 0:  19%|█▊        | 175/938 [00:12<00:52, 14.40it/s, loss=1.12, v_num=9]
Epoch 0:  19%|█▉        | 176/938 [00:12<00:52, 14.40it/s, loss=1.12, v_num=9]
Epoch 0:  19%|█▉        | 176/938 [00:12<00:52, 14.40it/s, loss=1.12, v_num=9]
Epoch 0:  19%|█▉        | 177/938 [00:12<00:52, 14.39it/s, loss=1.13, v_num=9]
Epoch 0:  19%|█▉        | 178/938 [00:12<00:52, 14.37it/s, loss=1.13, v_num=9]
Epoch 0:  19%|█▉        | 178/938 [00:12<00:52, 14.37it/s, loss=1.13, v_num=9]
Epoch 0:  19%|█▉        | 179/938 [00:12<00:52, 14.38it/s, loss=1.12, v_num=9]
Epoch 0:  19%|█▉        | 180/938 [00:12<00:52, 14.39it/s, loss=1.12, v_num=9]
Epoch 0:  19%|█▉        | 180/938 [00:12<00:52, 14.39it/s, loss=1.12, v_num=9]
Epoch 0:  19%|█▉        | 181/938 [00:12<00:52, 14.40it/s, loss=1.14, v_num=9]
Epoch 0:  19%|█▉        | 182/938 [00:12<00:52, 14.40it/s, loss=1.14, v_num=9]
Epoch 0:  19%|█▉        | 182/938 [00:12<00:52, 14.40it/s, loss=1.14, v_num=9]
Epoch 0:  20%|█▉        | 183/938 [00:12<00:52, 14.41it/s, loss=1.14, v_num=9]
Epoch 0:  20%|█▉        | 184/938 [00:12<00:52, 14.41it/s, loss=1.14, v_num=9]
Epoch 0:  20%|█▉        | 184/938 [00:12<00:52, 14.41it/s, loss=1.12, v_num=9]
Epoch 0:  20%|█▉        | 185/938 [00:12<00:52, 14.42it/s, loss=1.11, v_num=9]
Epoch 0:  20%|█▉        | 186/938 [00:12<00:52, 14.41it/s, loss=1.11, v_num=9]
Epoch 0:  20%|█▉        | 186/938 [00:12<00:52, 14.41it/s, loss=1.1, v_num=9] 
Epoch 0:  20%|█▉        | 187/938 [00:12<00:52, 14.42it/s, loss=1.09, v_num=9]
Epoch 0:  20%|██        | 188/938 [00:13<00:51, 14.43it/s, loss=1.09, v_num=9]
Epoch 0:  20%|██        | 188/938 [00:13<00:51, 14.43it/s, loss=1.08, v_num=9]
Epoch 0:  20%|██        | 189/938 [00:13<00:51, 14.44it/s, loss=1.06, v_num=9]
Epoch 0:  20%|██        | 190/938 [00:13<00:51, 14.43it/s, loss=1.06, v_num=9]
Epoch 0:  20%|██        | 190/938 [00:13<00:51, 14.43it/s, loss=1.05, v_num=9]
Epoch 0:  20%|██        | 191/938 [00:13<00:51, 14.43it/s, loss=1.05, v_num=9]
Epoch 0:  20%|██        | 192/938 [00:13<00:51, 14.44it/s, loss=1.05, v_num=9]
Epoch 0:  20%|██        | 192/938 [00:13<00:51, 14.44it/s, loss=1.06, v_num=9]
Epoch 0:  21%|██        | 193/938 [00:13<00:51, 14.45it/s, loss=1.07, v_num=9]
Epoch 0:  21%|██        | 194/938 [00:13<00:51, 14.44it/s, loss=1.07, v_num=9]
Epoch 0:  21%|██        | 194/938 [00:13<00:51, 14.44it/s, loss=1.07, v_num=9]
Epoch 0:  21%|██        | 195/938 [00:13<00:51, 14.43it/s, loss=1.08, v_num=9]
Epoch 0:  21%|██        | 196/938 [00:13<00:51, 14.43it/s, loss=1.08, v_num=9]
Epoch 0:  21%|██        | 196/938 [00:13<00:51, 14.43it/s, loss=1.07, v_num=9]
Epoch 0:  21%|██        | 197/938 [00:13<00:51, 14.43it/s, loss=1.05, v_num=9]
Epoch 0:  21%|██        | 198/938 [00:13<00:51, 14.43it/s, loss=1.05, v_num=9]
Epoch 0:  21%|██        | 198/938 [00:13<00:51, 14.43it/s, loss=1.05, v_num=9]
Epoch 0:  21%|██        | 199/938 [00:13<00:51, 14.41it/s, loss=1.05, v_num=9]
Epoch 0:  21%|██▏       | 200/938 [00:13<00:51, 14.41it/s, loss=1.05, v_num=9]
Epoch 0:  21%|██▏       | 200/938 [00:13<00:51, 14.41it/s, loss=1.03, v_num=9]
Epoch 0:  21%|██▏       | 201/938 [00:13<00:51, 14.42it/s, loss=1, v_num=9]   
Epoch 0:  22%|██▏       | 202/938 [00:14<00:51, 14.42it/s, loss=1, v_num=9]
Epoch 0:  22%|██▏       | 202/938 [00:14<00:51, 14.42it/s, loss=1, v_num=9]
Epoch 0:  22%|██▏       | 203/938 [00:14<00:50, 14.43it/s, loss=0.989, v_num=9]
Epoch 0:  22%|██▏       | 204/938 [00:14<00:50, 14.44it/s, loss=0.989, v_num=9]
Epoch 0:  22%|██▏       | 204/938 [00:14<00:50, 14.44it/s, loss=0.996, v_num=9]
Epoch 0:  22%|██▏       | 205/938 [00:14<00:50, 14.44it/s, loss=1, v_num=9]    
Epoch 0:  22%|██▏       | 206/938 [00:14<00:50, 14.44it/s, loss=1, v_num=9]
Epoch 0:  22%|██▏       | 206/938 [00:14<00:50, 14.44it/s, loss=0.996, v_num=9]
Epoch 0:  22%|██▏       | 207/938 [00:14<00:50, 14.45it/s, loss=0.995, v_num=9]
Epoch 0:  22%|██▏       | 208/938 [00:14<00:50, 14.45it/s, loss=0.995, v_num=9]
Epoch 0:  22%|██▏       | 208/938 [00:14<00:50, 14.44it/s, loss=0.994, v_num=9]
Epoch 0:  22%|██▏       | 209/938 [00:14<00:50, 14.44it/s, loss=1.01, v_num=9] 
Epoch 0:  22%|██▏       | 210/938 [00:14<00:50, 14.44it/s, loss=1.01, v_num=9]
Epoch 0:  22%|██▏       | 210/938 [00:14<00:50, 14.44it/s, loss=1.02, v_num=9]
Epoch 0:  22%|██▏       | 211/938 [00:14<00:50, 14.44it/s, loss=1.01, v_num=9]
Epoch 0:  23%|██▎       | 212/938 [00:14<00:50, 14.43it/s, loss=1.01, v_num=9]
Epoch 0:  23%|██▎       | 212/938 [00:14<00:50, 14.43it/s, loss=1.01, v_num=9]
Epoch 0:  23%|██▎       | 213/938 [00:14<00:50, 14.44it/s, loss=1, v_num=9]   
Epoch 0:  23%|██▎       | 214/938 [00:14<00:50, 14.42it/s, loss=1, v_num=9]
Epoch 0:  23%|██▎       | 214/938 [00:14<00:50, 14.42it/s, loss=1.01, v_num=9]
Epoch 0:  23%|██▎       | 215/938 [00:14<00:50, 14.42it/s, loss=1, v_num=9]   
Epoch 0:  23%|██▎       | 216/938 [00:14<00:50, 14.42it/s, loss=1, v_num=9]
Epoch 0:  23%|██▎       | 216/938 [00:14<00:50, 14.42it/s, loss=1, v_num=9]
Epoch 0:  23%|██▎       | 217/938 [00:15<00:50, 14.41it/s, loss=1.01, v_num=9]
Epoch 0:  23%|██▎       | 218/938 [00:15<00:49, 14.41it/s, loss=1.01, v_num=9]
Epoch 0:  23%|██▎       | 218/938 [00:15<00:49, 14.41it/s, loss=1, v_num=9]   
Epoch 0:  23%|██▎       | 219/938 [00:15<00:49, 14.42it/s, loss=0.995, v_num=9]
Epoch 0:  23%|██▎       | 220/938 [00:15<00:49, 14.43it/s, loss=0.995, v_num=9]
Epoch 0:  23%|██▎       | 220/938 [00:15<00:49, 14.43it/s, loss=1, v_num=9]    
Epoch 0:  24%|██▎       | 221/938 [00:15<00:49, 14.44it/s, loss=1.01, v_num=9]
Epoch 0:  24%|██▎       | 222/938 [00:15<00:49, 14.44it/s, loss=1.01, v_num=9]
Epoch 0:  24%|██▎       | 222/938 [00:15<00:49, 14.44it/s, loss=1.01, v_num=9]
Epoch 0:  24%|██▍       | 223/938 [00:15<00:49, 14.43it/s, loss=1, v_num=9]   
Epoch 0:  24%|██▍       | 224/938 [00:15<00:49, 14.42it/s, loss=1, v_num=9]
Epoch 0:  24%|██▍       | 224/938 [00:15<00:49, 14.42it/s, loss=0.987, v_num=9]
Epoch 0:  24%|██▍       | 225/938 [00:15<00:49, 14.40it/s, loss=0.984, v_num=9]
Epoch 0:  24%|██▍       | 226/938 [00:15<00:49, 14.41it/s, loss=0.984, v_num=9]
Epoch 0:  24%|██▍       | 226/938 [00:15<00:49, 14.41it/s, loss=0.99, v_num=9] 
Epoch 0:  24%|██▍       | 227/938 [00:15<00:49, 14.40it/s, loss=1, v_num=9]   
Epoch 0:  24%|██▍       | 228/938 [00:15<00:49, 14.41it/s, loss=1, v_num=9]
Epoch 0:  24%|██▍       | 228/938 [00:15<00:49, 14.41it/s, loss=1, v_num=9]
Epoch 0:  24%|██▍       | 229/938 [00:15<00:49, 14.41it/s, loss=0.988, v_num=9]
Epoch 0:  25%|██▍       | 230/938 [00:15<00:49, 14.42it/s, loss=0.988, v_num=9]
Epoch 0:  25%|██▍       | 230/938 [00:15<00:49, 14.42it/s, loss=0.983, v_num=9]
Epoch 0:  25%|██▍       | 231/938 [00:16<00:49, 14.39it/s, loss=0.984, v_num=9]
Epoch 0:  25%|██▍       | 232/938 [00:16<00:49, 14.39it/s, loss=0.984, v_num=9]
Epoch 0:  25%|██▍       | 232/938 [00:16<00:49, 14.39it/s, loss=0.983, v_num=9]
Epoch 0:  25%|██▍       | 233/938 [00:16<00:48, 14.39it/s, loss=0.981, v_num=9]
Epoch 0:  25%|██▍       | 234/938 [00:16<00:48, 14.39it/s, loss=0.981, v_num=9]
Epoch 0:  25%|██▍       | 234/938 [00:16<00:48, 14.39it/s, loss=0.978, v_num=9]
Epoch 0:  25%|██▌       | 235/938 [00:16<00:48, 14.39it/s, loss=0.987, v_num=9]
Epoch 0:  25%|██▌       | 236/938 [00:16<00:48, 14.40it/s, loss=0.987, v_num=9]
Epoch 0:  25%|██▌       | 236/938 [00:16<00:48, 14.39it/s, loss=0.985, v_num=9]
Epoch 0:  25%|██▌       | 237/938 [00:16<00:48, 14.39it/s, loss=0.97, v_num=9] 
Epoch 0:  25%|██▌       | 238/938 [00:16<00:48, 14.38it/s, loss=0.97, v_num=9]
Epoch 0:  25%|██▌       | 238/938 [00:16<00:48, 14.38it/s, loss=0.972, v_num=9]
Epoch 0:  25%|██▌       | 239/938 [00:16<00:48, 14.38it/s, loss=0.98, v_num=9] 
Epoch 0:  26%|██▌       | 240/938 [00:16<00:48, 14.38it/s, loss=0.98, v_num=9]
Epoch 0:  26%|██▌       | 240/938 [00:16<00:48, 14.38it/s, loss=0.983, v_num=9]
Epoch 0:  26%|██▌       | 241/938 [00:16<00:48, 14.37it/s, loss=0.97, v_num=9] 
Epoch 0:  26%|██▌       | 242/938 [00:16<00:48, 14.37it/s, loss=0.97, v_num=9]
Epoch 0:  26%|██▌       | 242/938 [00:16<00:48, 14.37it/s, loss=0.962, v_num=9]
Epoch 0:  26%|██▌       | 243/938 [00:16<00:48, 14.36it/s, loss=0.971, v_num=9]
Epoch 0:  26%|██▌       | 244/938 [00:16<00:48, 14.36it/s, loss=0.971, v_num=9]
Epoch 0:  26%|██▌       | 244/938 [00:16<00:48, 14.36it/s, loss=0.974, v_num=9]
Epoch 0:  26%|██▌       | 245/938 [00:17<00:48, 14.34it/s, loss=0.974, v_num=9]
Epoch 0:  26%|██▌       | 246/938 [00:17<00:48, 14.36it/s, loss=0.974, v_num=9]
Epoch 0:  26%|██▌       | 246/938 [00:17<00:48, 14.36it/s, loss=0.961, v_num=9]
Epoch 0:  26%|██▋       | 247/938 [00:17<00:48, 14.35it/s, loss=0.957, v_num=9]
Epoch 0:  26%|██▋       | 248/938 [00:17<00:48, 14.35it/s, loss=0.957, v_num=9]
Epoch 0:  26%|██▋       | 248/938 [00:17<00:48, 14.35it/s, loss=0.943, v_num=9]
Epoch 0:  27%|██▋       | 249/938 [00:17<00:47, 14.36it/s, loss=0.959, v_num=9]
Epoch 0:  27%|██▋       | 250/938 [00:17<00:47, 14.36it/s, loss=0.959, v_num=9]
Epoch 0:  27%|██▋       | 250/938 [00:17<00:47, 14.36it/s, loss=0.942, v_num=9]
Epoch 0:  27%|██▋       | 251/938 [00:17<00:47, 14.38it/s, loss=0.934, v_num=9]
Epoch 0:  27%|██▋       | 252/938 [00:17<00:47, 14.37it/s, loss=0.934, v_num=9]
Epoch 0:  27%|██▋       | 252/938 [00:17<00:47, 14.37it/s, loss=0.925, v_num=9]
Epoch 0:  27%|██▋       | 253/938 [00:17<00:47, 14.38it/s, loss=0.921, v_num=9]
Epoch 0:  27%|██▋       | 254/938 [00:17<00:47, 14.39it/s, loss=0.921, v_num=9]
Epoch 0:  27%|██▋       | 254/938 [00:17<00:47, 14.39it/s, loss=0.913, v_num=9]
Epoch 0:  27%|██▋       | 255/938 [00:17<00:47, 14.37it/s, loss=0.916, v_num=9]
Epoch 0:  27%|██▋       | 256/938 [00:17<00:47, 14.38it/s, loss=0.916, v_num=9]
Epoch 0:  27%|██▋       | 256/938 [00:17<00:47, 14.38it/s, loss=0.912, v_num=9]
Epoch 0:  27%|██▋       | 257/938 [00:17<00:47, 14.37it/s, loss=0.911, v_num=9]
Epoch 0:  28%|██▊       | 258/938 [00:17<00:47, 14.38it/s, loss=0.911, v_num=9]
Epoch 0:  28%|██▊       | 258/938 [00:17<00:47, 14.37it/s, loss=0.917, v_num=9]
Epoch 0:  28%|██▊       | 259/938 [00:18<00:47, 14.38it/s, loss=0.913, v_num=9]
Epoch 0:  28%|██▊       | 260/938 [00:18<00:47, 14.38it/s, loss=0.913, v_num=9]
Epoch 0:  28%|██▊       | 260/938 [00:18<00:47, 14.38it/s, loss=0.91, v_num=9] 
Epoch 0:  28%|██▊       | 261/938 [00:18<00:47, 14.38it/s, loss=0.927, v_num=9]
Epoch 0:  28%|██▊       | 262/938 [00:18<00:46, 14.39it/s, loss=0.927, v_num=9]
Epoch 0:  28%|██▊       | 262/938 [00:18<00:46, 14.39it/s, loss=0.938, v_num=9]
Epoch 0:  28%|██▊       | 263/938 [00:18<00:46, 14.38it/s, loss=0.947, v_num=9]
Epoch 0:  28%|██▊       | 264/938 [00:18<00:46, 14.39it/s, loss=0.947, v_num=9]
Epoch 0:  28%|██▊       | 264/938 [00:18<00:46, 14.39it/s, loss=0.947, v_num=9]
Epoch 0:  28%|██▊       | 265/938 [00:18<00:46, 14.39it/s, loss=0.933, v_num=9]
Epoch 0:  28%|██▊       | 266/938 [00:18<00:46, 14.39it/s, loss=0.933, v_num=9]
Epoch 0:  28%|██▊       | 266/938 [00:18<00:46, 14.39it/s, loss=0.94, v_num=9] 
Epoch 0:  28%|██▊       | 267/938 [00:18<00:46, 14.40it/s, loss=0.948, v_num=9]
Epoch 0:  29%|██▊       | 268/938 [00:18<00:46, 14.39it/s, loss=0.948, v_num=9]
Epoch 0:  29%|██▊       | 268/938 [00:18<00:46, 14.39it/s, loss=0.942, v_num=9]
Epoch 0:  29%|██▊       | 269/938 [00:18<00:46, 14.39it/s, loss=0.932, v_num=9]
Epoch 0:  29%|██▉       | 270/938 [00:18<00:46, 14.40it/s, loss=0.932, v_num=9]
Epoch 0:  29%|██▉       | 270/938 [00:18<00:46, 14.40it/s, loss=0.944, v_num=9]
Epoch 0:  29%|██▉       | 271/938 [00:18<00:46, 14.41it/s, loss=0.94, v_num=9] 
Epoch 0:  29%|██▉       | 272/938 [00:18<00:46, 14.42it/s, loss=0.94, v_num=9]
Epoch 0:  29%|██▉       | 272/938 [00:18<00:46, 14.42it/s, loss=0.923, v_num=9]
Epoch 0:  29%|██▉       | 273/938 [00:18<00:46, 14.41it/s, loss=0.923, v_num=9]
Epoch 0:  29%|██▉       | 274/938 [00:19<00:46, 14.42it/s, loss=0.923, v_num=9]
Epoch 0:  29%|██▉       | 274/938 [00:19<00:46, 14.42it/s, loss=0.926, v_num=9]
Epoch 0:  29%|██▉       | 275/938 [00:19<00:46, 14.41it/s, loss=0.913, v_num=9]
Epoch 0:  29%|██▉       | 276/938 [00:19<00:45, 14.41it/s, loss=0.913, v_num=9]
Epoch 0:  29%|██▉       | 276/938 [00:19<00:45, 14.41it/s, loss=0.923, v_num=9]
Epoch 0:  30%|██▉       | 277/938 [00:19<00:45, 14.42it/s, loss=0.935, v_num=9]
Epoch 0:  30%|██▉       | 278/938 [00:19<00:45, 14.41it/s, loss=0.935, v_num=9]
Epoch 0:  30%|██▉       | 278/938 [00:19<00:45, 14.40it/s, loss=0.925, v_num=9]
Epoch 0:  30%|██▉       | 279/938 [00:19<00:45, 14.41it/s, loss=0.913, v_num=9]
Epoch 0:  30%|██▉       | 280/938 [00:19<00:45, 14.41it/s, loss=0.913, v_num=9]
Epoch 0:  30%|██▉       | 280/938 [00:19<00:45, 14.41it/s, loss=0.907, v_num=9]
Epoch 0:  30%|██▉       | 281/938 [00:19<00:45, 14.41it/s, loss=0.894, v_num=9]
Epoch 0:  30%|███       | 282/938 [00:19<00:45, 14.41it/s, loss=0.894, v_num=9]
Epoch 0:  30%|███       | 282/938 [00:19<00:45, 14.41it/s, loss=0.88, v_num=9] 
Epoch 0:  30%|███       | 283/938 [00:19<00:45, 14.42it/s, loss=0.865, v_num=9]
Epoch 0:  30%|███       | 284/938 [00:19<00:45, 14.41it/s, loss=0.865, v_num=9]
Epoch 0:  30%|███       | 284/938 [00:19<00:45, 14.41it/s, loss=0.874, v_num=9]
Epoch 0:  30%|███       | 285/938 [00:19<00:45, 14.42it/s, loss=0.881, v_num=9]
Epoch 0:  30%|███       | 286/938 [00:19<00:45, 14.42it/s, loss=0.881, v_num=9]
Epoch 0:  30%|███       | 286/938 [00:19<00:45, 14.42it/s, loss=0.878, v_num=9]
Epoch 0:  31%|███       | 287/938 [00:19<00:45, 14.42it/s, loss=0.864, v_num=9]
Epoch 0:  31%|███       | 288/938 [00:19<00:45, 14.43it/s, loss=0.864, v_num=9]
Epoch 0:  31%|███       | 288/938 [00:19<00:45, 14.43it/s, loss=0.866, v_num=9]
Epoch 0:  31%|███       | 289/938 [00:20<00:44, 14.42it/s, loss=0.88, v_num=9] 
Epoch 0:  31%|███       | 290/938 [00:20<00:44, 14.43it/s, loss=0.88, v_num=9]
Epoch 0:  31%|███       | 290/938 [00:20<00:44, 14.43it/s, loss=0.883, v_num=9]
Epoch 0:  31%|███       | 291/938 [00:20<00:44, 14.43it/s, loss=0.892, v_num=9]
Epoch 0:  31%|███       | 292/938 [00:20<00:44, 14.42it/s, loss=0.892, v_num=9]
Epoch 0:  31%|███       | 292/938 [00:20<00:44, 14.42it/s, loss=0.91, v_num=9] 
Epoch 0:  31%|███       | 293/938 [00:20<00:44, 14.43it/s, loss=0.913, v_num=9]
Epoch 0:  31%|███▏      | 294/938 [00:20<00:44, 14.43it/s, loss=0.913, v_num=9]
Epoch 0:  31%|███▏      | 294/938 [00:20<00:44, 14.43it/s, loss=0.906, v_num=9]
Epoch 0:  31%|███▏      | 295/938 [00:20<00:44, 14.44it/s, loss=0.895, v_num=9]
Epoch 0:  32%|███▏      | 296/938 [00:20<00:44, 14.43it/s, loss=0.895, v_num=9]
Epoch 0:  32%|███▏      | 296/938 [00:20<00:44, 14.43it/s, loss=0.891, v_num=9]
Epoch 0:  32%|███▏      | 297/938 [00:20<00:44, 14.43it/s, loss=0.893, v_num=9]
Epoch 0:  32%|███▏      | 298/938 [00:20<00:44, 14.42it/s, loss=0.893, v_num=9]
Epoch 0:  32%|███▏      | 298/938 [00:20<00:44, 14.42it/s, loss=0.885, v_num=9]
Epoch 0:  32%|███▏      | 299/938 [00:20<00:44, 14.42it/s, loss=0.894, v_num=9]
Epoch 0:  32%|███▏      | 300/938 [00:20<00:44, 14.42it/s, loss=0.894, v_num=9]
Epoch 0:  32%|███▏      | 300/938 [00:20<00:44, 14.42it/s, loss=0.9, v_num=9]  
Epoch 0:  32%|███▏      | 301/938 [00:20<00:44, 14.42it/s, loss=0.895, v_num=9]
Epoch 0:  32%|███▏      | 302/938 [00:20<00:44, 14.43it/s, loss=0.895, v_num=9]
Epoch 0:  32%|███▏      | 302/938 [00:20<00:44, 14.43it/s, loss=0.899, v_num=9]
Epoch 0:  32%|███▏      | 303/938 [00:21<00:44, 14.42it/s, loss=0.907, v_num=9]
Epoch 0:  32%|███▏      | 304/938 [00:21<00:43, 14.43it/s, loss=0.907, v_num=9]
Epoch 0:  32%|███▏      | 304/938 [00:21<00:43, 14.43it/s, loss=0.904, v_num=9]
Epoch 0:  33%|███▎      | 305/938 [00:21<00:43, 14.43it/s, loss=0.91, v_num=9] 
Epoch 0:  33%|███▎      | 306/938 [00:21<00:43, 14.45it/s, loss=0.91, v_num=9]
Epoch 0:  33%|███▎      | 306/938 [00:21<00:43, 14.45it/s, loss=0.914, v_num=9]
Epoch 0:  33%|███▎      | 307/938 [00:21<00:43, 14.44it/s, loss=0.918, v_num=9]
Epoch 0:  33%|███▎      | 308/938 [00:21<00:43, 14.45it/s, loss=0.918, v_num=9]
Epoch 0:  33%|███▎      | 308/938 [00:21<00:43, 14.45it/s, loss=0.92, v_num=9] 
Epoch 0:  33%|███▎      | 309/938 [00:21<00:43, 14.44it/s, loss=0.908, v_num=9]
Epoch 0:  33%|███▎      | 310/938 [00:21<00:43, 14.44it/s, loss=0.908, v_num=9]
Epoch 0:  33%|███▎      | 310/938 [00:21<00:43, 14.44it/s, loss=0.903, v_num=9]
Epoch 0:  33%|███▎      | 311/938 [00:21<00:43, 14.43it/s, loss=0.905, v_num=9]
Epoch 0:  33%|███▎      | 312/938 [00:21<00:43, 14.43it/s, loss=0.905, v_num=9]
Epoch 0:  33%|███▎      | 312/938 [00:21<00:43, 14.43it/s, loss=0.902, v_num=9]
Epoch 0:  33%|███▎      | 313/938 [00:21<00:43, 14.42it/s, loss=0.907, v_num=9]
Epoch 0:  33%|███▎      | 314/938 [00:21<00:43, 14.42it/s, loss=0.907, v_num=9]
Epoch 0:  33%|███▎      | 314/938 [00:21<00:43, 14.42it/s, loss=0.909, v_num=9]
Epoch 0:  34%|███▎      | 315/938 [00:21<00:43, 14.43it/s, loss=0.933, v_num=9]
Epoch 0:  34%|███▎      | 316/938 [00:21<00:43, 14.43it/s, loss=0.933, v_num=9]
Epoch 0:  34%|███▎      | 316/938 [00:21<00:43, 14.43it/s, loss=0.93, v_num=9] 
Epoch 0:  34%|███▍      | 317/938 [00:21<00:43, 14.43it/s, loss=0.913, v_num=9]
Epoch 0:  34%|███▍      | 318/938 [00:22<00:42, 14.43it/s, loss=0.913, v_num=9]
Epoch 0:  34%|███▍      | 318/938 [00:22<00:42, 14.43it/s, loss=0.913, v_num=9]
Epoch 0:  34%|███▍      | 319/938 [00:22<00:42, 14.44it/s, loss=0.911, v_num=9]
Epoch 0:  34%|███▍      | 320/938 [00:22<00:42, 14.44it/s, loss=0.911, v_num=9]
Epoch 0:  34%|███▍      | 320/938 [00:22<00:42, 14.44it/s, loss=0.905, v_num=9]
Epoch 0:  34%|███▍      | 321/938 [00:22<00:42, 14.44it/s, loss=0.898, v_num=9]
Epoch 0:  34%|███▍      | 322/938 [00:22<00:42, 14.44it/s, loss=0.898, v_num=9]
Epoch 0:  34%|███▍      | 322/938 [00:22<00:42, 14.44it/s, loss=0.896, v_num=9]
Epoch 0:  34%|███▍      | 323/938 [00:22<00:42, 14.44it/s, loss=0.896, v_num=9]
Epoch 0:  35%|███▍      | 324/938 [00:22<00:42, 14.44it/s, loss=0.896, v_num=9]
Epoch 0:  35%|███▍      | 324/938 [00:22<00:42, 14.44it/s, loss=0.886, v_num=9]
Epoch 0:  35%|███▍      | 325/938 [00:22<00:42, 14.44it/s, loss=0.882, v_num=9]
Epoch 0:  35%|███▍      | 326/938 [00:22<00:42, 14.44it/s, loss=0.882, v_num=9]
Epoch 0:  35%|███▍      | 326/938 [00:22<00:42, 14.44it/s, loss=0.877, v_num=9]
Epoch 0:  35%|███▍      | 327/938 [00:22<00:42, 14.44it/s, loss=0.87, v_num=9] 
Epoch 0:  35%|███▍      | 328/938 [00:22<00:42, 14.44it/s, loss=0.87, v_num=9]
Epoch 0:  35%|███▍      | 328/938 [00:22<00:42, 14.44it/s, loss=0.882, v_num=9]
Epoch 0:  35%|███▌      | 329/938 [00:22<00:42, 14.44it/s, loss=0.874, v_num=9]
Epoch 0:  35%|███▌      | 330/938 [00:22<00:42, 14.43it/s, loss=0.874, v_num=9]
Epoch 0:  35%|███▌      | 330/938 [00:22<00:42, 14.43it/s, loss=0.86, v_num=9] 
Epoch 0:  35%|███▌      | 331/938 [00:22<00:42, 14.43it/s, loss=0.845, v_num=9]
Epoch 0:  35%|███▌      | 332/938 [00:23<00:42, 14.43it/s, loss=0.845, v_num=9]
Epoch 0:  35%|███▌      | 332/938 [00:23<00:42, 14.43it/s, loss=0.839, v_num=9]
Epoch 0:  36%|███▌      | 333/938 [00:23<00:41, 14.43it/s, loss=0.841, v_num=9]
Epoch 0:  36%|███▌      | 334/938 [00:23<00:41, 14.42it/s, loss=0.841, v_num=9]
Epoch 0:  36%|███▌      | 334/938 [00:23<00:41, 14.42it/s, loss=0.848, v_num=9]
Epoch 0:  36%|███▌      | 335/938 [00:23<00:41, 14.41it/s, loss=0.831, v_num=9]
Epoch 0:  36%|███▌      | 336/938 [00:23<00:41, 14.41it/s, loss=0.831, v_num=9]
Epoch 0:  36%|███▌      | 336/938 [00:23<00:41, 14.41it/s, loss=0.825, v_num=9]
Epoch 0:  36%|███▌      | 337/938 [00:23<00:41, 14.40it/s, loss=0.836, v_num=9]
Epoch 0:  36%|███▌      | 338/938 [00:23<00:41, 14.40it/s, loss=0.836, v_num=9]
Epoch 0:  36%|███▌      | 338/938 [00:23<00:41, 14.40it/s, loss=0.84, v_num=9] 
Epoch 0:  36%|███▌      | 339/938 [00:23<00:41, 14.39it/s, loss=0.836, v_num=9]
Epoch 0:  36%|███▌      | 340/938 [00:23<00:41, 14.39it/s, loss=0.836, v_num=9]
Epoch 0:  36%|███▌      | 340/938 [00:23<00:41, 14.39it/s, loss=0.839, v_num=9]
Epoch 0:  36%|███▋      | 341/938 [00:23<00:41, 14.39it/s, loss=0.86, v_num=9] 
Epoch 0:  36%|███▋      | 342/938 [00:23<00:41, 14.40it/s, loss=0.86, v_num=9]
Epoch 0:  36%|███▋      | 342/938 [00:23<00:41, 14.40it/s, loss=0.857, v_num=9]
Epoch 0:  37%|███▋      | 343/938 [00:23<00:41, 14.40it/s, loss=0.853, v_num=9]
Epoch 0:  37%|███▋      | 344/938 [00:23<00:41, 14.39it/s, loss=0.853, v_num=9]
Epoch 0:  37%|███▋      | 344/938 [00:23<00:41, 14.39it/s, loss=0.855, v_num=9]
Epoch 0:  37%|███▋      | 345/938 [00:23<00:41, 14.40it/s, loss=0.855, v_num=9]
Epoch 0:  37%|███▋      | 346/938 [00:24<00:41, 14.39it/s, loss=0.855, v_num=9]
Epoch 0:  37%|███▋      | 346/938 [00:24<00:41, 14.39it/s, loss=0.864, v_num=9]
Epoch 0:  37%|███▋      | 347/938 [00:24<00:41, 14.40it/s, loss=0.865, v_num=9]
Epoch 0:  37%|███▋      | 348/938 [00:24<00:40, 14.40it/s, loss=0.865, v_num=9]
Epoch 0:  37%|███▋      | 348/938 [00:24<00:40, 14.40it/s, loss=0.856, v_num=9]
Epoch 0:  37%|███▋      | 349/938 [00:24<00:40, 14.41it/s, loss=0.854, v_num=9]
Epoch 0:  37%|███▋      | 350/938 [00:24<00:40, 14.40it/s, loss=0.854, v_num=9]
Epoch 0:  37%|███▋      | 350/938 [00:24<00:40, 14.40it/s, loss=0.871, v_num=9]
Epoch 0:  37%|███▋      | 351/938 [00:24<00:40, 14.40it/s, loss=0.866, v_num=9]
Epoch 0:  38%|███▊      | 352/938 [00:24<00:40, 14.40it/s, loss=0.866, v_num=9]
Epoch 0:  38%|███▊      | 352/938 [00:24<00:40, 14.40it/s, loss=0.865, v_num=9]
Epoch 0:  38%|███▊      | 353/938 [00:24<00:40, 14.40it/s, loss=0.864, v_num=9]
Epoch 0:  38%|███▊      | 354/938 [00:24<00:40, 14.41it/s, loss=0.864, v_num=9]
Epoch 0:  38%|███▊      | 354/938 [00:24<00:40, 14.41it/s, loss=0.862, v_num=9]
Epoch 0:  38%|███▊      | 355/938 [00:24<00:40, 14.38it/s, loss=0.86, v_num=9] 
Epoch 0:  38%|███▊      | 356/938 [00:24<00:40, 14.37it/s, loss=0.86, v_num=9]
Epoch 0:  38%|███▊      | 356/938 [00:24<00:40, 14.37it/s, loss=0.863, v_num=9]
Epoch 0:  38%|███▊      | 357/938 [00:24<00:40, 14.38it/s, loss=0.86, v_num=9] 
Epoch 0:  38%|███▊      | 358/938 [00:24<00:40, 14.38it/s, loss=0.86, v_num=9]
Epoch 0:  38%|███▊      | 358/938 [00:24<00:40, 14.38it/s, loss=0.86, v_num=9]
Epoch 0:  38%|███▊      | 359/938 [00:24<00:40, 14.39it/s, loss=0.859, v_num=9]
Epoch 0:  38%|███▊      | 360/938 [00:25<00:40, 14.39it/s, loss=0.859, v_num=9]
Epoch 0:  38%|███▊      | 360/938 [00:25<00:40, 14.39it/s, loss=0.855, v_num=9]
Epoch 0:  38%|███▊      | 361/938 [00:25<00:40, 14.39it/s, loss=0.849, v_num=9]
Epoch 0:  39%|███▊      | 362/938 [00:25<00:40, 14.38it/s, loss=0.849, v_num=9]
Epoch 0:  39%|███▊      | 362/938 [00:25<00:40, 14.38it/s, loss=0.859, v_num=9]
Epoch 0:  39%|███▊      | 363/938 [00:25<00:40, 14.37it/s, loss=0.855, v_num=9]
Epoch 0:  39%|███▉      | 364/938 [00:25<00:39, 14.37it/s, loss=0.855, v_num=9]
Epoch 0:  39%|███▉      | 364/938 [00:25<00:39, 14.37it/s, loss=0.855, v_num=9]
Epoch 0:  39%|███▉      | 365/938 [00:25<00:39, 14.37it/s, loss=0.857, v_num=9]
Epoch 0:  39%|███▉      | 366/938 [00:25<00:39, 14.37it/s, loss=0.857, v_num=9]
Epoch 0:  39%|███▉      | 366/938 [00:25<00:39, 14.37it/s, loss=0.842, v_num=9]
Epoch 0:  39%|███▉      | 367/938 [00:25<00:39, 14.37it/s, loss=0.846, v_num=9]
Epoch 0:  39%|███▉      | 368/938 [00:25<00:39, 14.37it/s, loss=0.846, v_num=9]
Epoch 0:  39%|███▉      | 368/938 [00:25<00:39, 14.37it/s, loss=0.848, v_num=9]
Epoch 0:  39%|███▉      | 369/938 [00:25<00:39, 14.37it/s, loss=0.849, v_num=9]
Epoch 0:  39%|███▉      | 370/938 [00:25<00:39, 14.38it/s, loss=0.849, v_num=9]
Epoch 0:  39%|███▉      | 370/938 [00:25<00:39, 14.38it/s, loss=0.848, v_num=9]
Epoch 0:  40%|███▉      | 371/938 [00:25<00:39, 14.38it/s, loss=0.866, v_num=9]
Epoch 0:  40%|███▉      | 372/938 [00:25<00:39, 14.37it/s, loss=0.866, v_num=9]
Epoch 0:  40%|███▉      | 372/938 [00:25<00:39, 14.37it/s, loss=0.868, v_num=9]
Epoch 0:  40%|███▉      | 373/938 [00:25<00:39, 14.37it/s, loss=0.858, v_num=9]
Epoch 0:  40%|███▉      | 374/938 [00:26<00:39, 14.37it/s, loss=0.858, v_num=9]
Epoch 0:  40%|███▉      | 374/938 [00:26<00:39, 14.37it/s, loss=0.851, v_num=9]
Epoch 0:  40%|███▉      | 375/938 [00:26<00:39, 14.37it/s, loss=0.861, v_num=9]
Epoch 0:  40%|████      | 376/938 [00:26<00:39, 14.37it/s, loss=0.861, v_num=9]
Epoch 0:  40%|████      | 376/938 [00:26<00:39, 14.37it/s, loss=0.857, v_num=9]
Epoch 0:  40%|████      | 377/938 [00:26<00:39, 14.37it/s, loss=0.856, v_num=9]
Epoch 0:  40%|████      | 378/938 [00:26<00:38, 14.38it/s, loss=0.856, v_num=9]
Epoch 0:  40%|████      | 378/938 [00:26<00:38, 14.38it/s, loss=0.853, v_num=9]
Epoch 0:  40%|████      | 379/938 [00:26<00:38, 14.38it/s, loss=0.859, v_num=9]
Epoch 0:  41%|████      | 380/938 [00:26<00:38, 14.39it/s, loss=0.859, v_num=9]
Epoch 0:  41%|████      | 380/938 [00:26<00:38, 14.39it/s, loss=0.859, v_num=9]
Epoch 0:  41%|████      | 381/938 [00:26<00:38, 14.39it/s, loss=0.842, v_num=9]
Epoch 0:  41%|████      | 382/938 [00:26<00:38, 14.38it/s, loss=0.842, v_num=9]
Epoch 0:  41%|████      | 382/938 [00:26<00:38, 14.38it/s, loss=0.841, v_num=9]
Epoch 0:  41%|████      | 383/938 [00:26<00:38, 14.38it/s, loss=0.844, v_num=9]
Epoch 0:  41%|████      | 384/938 [00:26<00:38, 14.38it/s, loss=0.844, v_num=9]
Epoch 0:  41%|████      | 384/938 [00:26<00:38, 14.38it/s, loss=0.842, v_num=9]
Epoch 0:  41%|████      | 385/938 [00:26<00:38, 14.37it/s, loss=0.844, v_num=9]
Epoch 0:  41%|████      | 386/938 [00:26<00:38, 14.38it/s, loss=0.844, v_num=9]
Epoch 0:  41%|████      | 386/938 [00:26<00:38, 14.38it/s, loss=0.853, v_num=9]
Epoch 0:  41%|████▏     | 387/938 [00:26<00:38, 14.38it/s, loss=0.851, v_num=9]
Epoch 0:  41%|████▏     | 388/938 [00:26<00:38, 14.39it/s, loss=0.851, v_num=9]
Epoch 0:  41%|████▏     | 388/938 [00:26<00:38, 14.39it/s, loss=0.858, v_num=9]
Epoch 0:  41%|████▏     | 389/938 [00:27<00:38, 14.40it/s, loss=0.853, v_num=9]
Epoch 0:  42%|████▏     | 390/938 [00:27<00:38, 14.40it/s, loss=0.853, v_num=9]
Epoch 0:  42%|████▏     | 390/938 [00:27<00:38, 14.40it/s, loss=0.849, v_num=9]
Epoch 0:  42%|████▏     | 391/938 [00:27<00:37, 14.40it/s, loss=0.841, v_num=9]
Epoch 0:  42%|████▏     | 392/938 [00:27<00:37, 14.40it/s, loss=0.841, v_num=9]
Epoch 0:  42%|████▏     | 392/938 [00:27<00:37, 14.40it/s, loss=0.836, v_num=9]
Epoch 0:  42%|████▏     | 393/938 [00:27<00:37, 14.40it/s, loss=0.835, v_num=9]
Epoch 0:  42%|████▏     | 394/938 [00:27<00:37, 14.40it/s, loss=0.835, v_num=9]
Epoch 0:  42%|████▏     | 394/938 [00:27<00:37, 14.40it/s, loss=0.836, v_num=9]
Epoch 0:  42%|████▏     | 395/938 [00:27<00:37, 14.41it/s, loss=0.828, v_num=9]
Epoch 0:  42%|████▏     | 396/938 [00:27<00:37, 14.41it/s, loss=0.828, v_num=9]
Epoch 0:  42%|████▏     | 396/938 [00:27<00:37, 14.41it/s, loss=0.829, v_num=9]
Epoch 0:  42%|████▏     | 397/938 [00:27<00:37, 14.41it/s, loss=0.829, v_num=9]
Epoch 0:  42%|████▏     | 398/938 [00:27<00:37, 14.41it/s, loss=0.829, v_num=9]
Epoch 0:  42%|████▏     | 398/938 [00:27<00:37, 14.41it/s, loss=0.826, v_num=9]
Epoch 0:  43%|████▎     | 399/938 [00:27<00:37, 14.41it/s, loss=0.823, v_num=9]
Epoch 0:  43%|████▎     | 400/938 [00:27<00:37, 14.40it/s, loss=0.823, v_num=9]
Epoch 0:  43%|████▎     | 400/938 [00:27<00:37, 14.40it/s, loss=0.83, v_num=9] 
Epoch 0:  43%|████▎     | 401/938 [00:27<00:37, 14.41it/s, loss=0.841, v_num=9]
Epoch 0:  43%|████▎     | 402/938 [00:27<00:37, 14.41it/s, loss=0.841, v_num=9]
Epoch 0:  43%|████▎     | 402/938 [00:27<00:37, 14.41it/s, loss=0.828, v_num=9]
Epoch 0:  43%|████▎     | 403/938 [00:27<00:37, 14.41it/s, loss=0.828, v_num=9]
Epoch 0:  43%|████▎     | 404/938 [00:28<00:37, 14.42it/s, loss=0.828, v_num=9]
Epoch 0:  43%|████▎     | 404/938 [00:28<00:37, 14.42it/s, loss=0.822, v_num=9]
Epoch 0:  43%|████▎     | 405/938 [00:28<00:36, 14.42it/s, loss=0.832, v_num=9]
Epoch 0:  43%|████▎     | 406/938 [00:28<00:36, 14.43it/s, loss=0.832, v_num=9]
Epoch 0:  43%|████▎     | 406/938 [00:28<00:36, 14.43it/s, loss=0.825, v_num=9]
Epoch 0:  43%|████▎     | 407/938 [00:28<00:36, 14.42it/s, loss=0.827, v_num=9]
Epoch 0:  43%|████▎     | 408/938 [00:28<00:36, 14.42it/s, loss=0.827, v_num=9]
Epoch 0:  43%|████▎     | 408/938 [00:28<00:36, 14.42it/s, loss=0.823, v_num=9]
Epoch 0:  44%|████▎     | 409/938 [00:28<00:36, 14.42it/s, loss=0.827, v_num=9]
Epoch 0:  44%|████▎     | 410/938 [00:28<00:36, 14.42it/s, loss=0.827, v_num=9]
Epoch 0:  44%|████▎     | 410/938 [00:28<00:36, 14.42it/s, loss=0.83, v_num=9] 
Epoch 0:  44%|████▍     | 411/938 [00:28<00:36, 14.43it/s, loss=0.826, v_num=9]
Epoch 0:  44%|████▍     | 412/938 [00:28<00:36, 14.42it/s, loss=0.826, v_num=9]
Epoch 0:  44%|████▍     | 412/938 [00:28<00:36, 14.42it/s, loss=0.832, v_num=9]
Epoch 0:  44%|████▍     | 413/938 [00:28<00:36, 14.42it/s, loss=0.837, v_num=9]
Epoch 0:  44%|████▍     | 414/938 [00:28<00:36, 14.42it/s, loss=0.837, v_num=9]
Epoch 0:  44%|████▍     | 414/938 [00:28<00:36, 14.42it/s, loss=0.839, v_num=9]
Epoch 0:  44%|████▍     | 415/938 [00:28<00:36, 14.43it/s, loss=0.844, v_num=9]
Epoch 0:  44%|████▍     | 416/938 [00:28<00:36, 14.43it/s, loss=0.844, v_num=9]
Epoch 0:  44%|████▍     | 416/938 [00:28<00:36, 14.43it/s, loss=0.846, v_num=9]
Epoch 0:  44%|████▍     | 417/938 [00:28<00:36, 14.43it/s, loss=0.843, v_num=9]
Epoch 0:  45%|████▍     | 418/938 [00:28<00:36, 14.43it/s, loss=0.843, v_num=9]
Epoch 0:  45%|████▍     | 418/938 [00:28<00:36, 14.43it/s, loss=0.838, v_num=9]
Epoch 0:  45%|████▍     | 419/938 [00:29<00:35, 14.43it/s, loss=0.834, v_num=9]
Epoch 0:  45%|████▍     | 420/938 [00:29<00:35, 14.44it/s, loss=0.834, v_num=9]
Epoch 0:  45%|████▍     | 420/938 [00:29<00:35, 14.44it/s, loss=0.841, v_num=9]
Epoch 0:  45%|████▍     | 421/938 [00:29<00:35, 14.44it/s, loss=0.839, v_num=9]
Epoch 0:  45%|████▍     | 422/938 [00:29<00:35, 14.43it/s, loss=0.839, v_num=9]
Epoch 0:  45%|████▍     | 422/938 [00:29<00:35, 14.43it/s, loss=0.847, v_num=9]
Epoch 0:  45%|████▌     | 423/938 [00:29<00:35, 14.42it/s, loss=0.844, v_num=9]
Epoch 0:  45%|████▌     | 424/938 [00:29<00:35, 14.41it/s, loss=0.844, v_num=9]
Epoch 0:  45%|████▌     | 424/938 [00:29<00:35, 14.41it/s, loss=0.853, v_num=9]
Epoch 0:  45%|████▌     | 425/938 [00:29<00:35, 14.41it/s, loss=0.842, v_num=9]
Epoch 0:  45%|████▌     | 426/938 [00:29<00:35, 14.40it/s, loss=0.842, v_num=9]
Epoch 0:  45%|████▌     | 426/938 [00:29<00:35, 14.40it/s, loss=0.844, v_num=9]
Epoch 0:  46%|████▌     | 427/938 [00:29<00:35, 14.40it/s, loss=0.844, v_num=9]
Epoch 0:  46%|████▌     | 428/938 [00:29<00:35, 14.40it/s, loss=0.844, v_num=9]
Epoch 0:  46%|████▌     | 428/938 [00:29<00:35, 14.40it/s, loss=0.832, v_num=9]
Epoch 0:  46%|████▌     | 429/938 [00:29<00:35, 14.40it/s, loss=0.838, v_num=9]
Epoch 0:  46%|████▌     | 430/938 [00:29<00:35, 14.40it/s, loss=0.838, v_num=9]
Epoch 0:  46%|████▌     | 430/938 [00:29<00:35, 14.40it/s, loss=0.837, v_num=9]
Epoch 0:  46%|████▌     | 431/938 [00:29<00:35, 14.40it/s, loss=0.84, v_num=9] 
Epoch 0:  46%|████▌     | 432/938 [00:30<00:35, 14.40it/s, loss=0.84, v_num=9]
Epoch 0:  46%|████▌     | 432/938 [00:30<00:35, 14.40it/s, loss=0.846, v_num=9]
Epoch 0:  46%|████▌     | 433/938 [00:30<00:35, 14.39it/s, loss=0.84, v_num=9] 
Epoch 0:  46%|████▋     | 434/938 [00:30<00:35, 14.39it/s, loss=0.84, v_num=9]
Epoch 0:  46%|████▋     | 434/938 [00:30<00:35, 14.39it/s, loss=0.837, v_num=9]
Epoch 0:  46%|████▋     | 435/938 [00:30<00:34, 14.39it/s, loss=0.831, v_num=9]
Epoch 0:  46%|████▋     | 436/938 [00:30<00:34, 14.38it/s, loss=0.831, v_num=9]
Epoch 0:  46%|████▋     | 436/938 [00:30<00:34, 14.38it/s, loss=0.829, v_num=9]
Epoch 0:  47%|████▋     | 437/938 [00:30<00:34, 14.38it/s, loss=0.831, v_num=9]
Epoch 0:  47%|████▋     | 438/938 [00:30<00:34, 14.39it/s, loss=0.831, v_num=9]
Epoch 0:  47%|████▋     | 438/938 [00:30<00:34, 14.39it/s, loss=0.84, v_num=9] 
Epoch 0:  47%|████▋     | 439/938 [00:30<00:34, 14.38it/s, loss=0.848, v_num=9]
Epoch 0:  47%|████▋     | 440/938 [00:30<00:34, 14.38it/s, loss=0.848, v_num=9]
Epoch 0:  47%|████▋     | 440/938 [00:30<00:34, 14.38it/s, loss=0.839, v_num=9]
Epoch 0:  47%|████▋     | 441/938 [00:30<00:34, 14.38it/s, loss=0.835, v_num=9]
Epoch 0:  47%|████▋     | 442/938 [00:30<00:34, 14.38it/s, loss=0.835, v_num=9]
Epoch 0:  47%|████▋     | 442/938 [00:30<00:34, 14.38it/s, loss=0.835, v_num=9]
Epoch 0:  47%|████▋     | 443/938 [00:30<00:34, 14.39it/s, loss=0.838, v_num=9]
Epoch 0:  47%|████▋     | 444/938 [00:30<00:34, 14.38it/s, loss=0.838, v_num=9]
Epoch 0:  47%|████▋     | 444/938 [00:30<00:34, 14.38it/s, loss=0.831, v_num=9]
Epoch 0:  47%|████▋     | 445/938 [00:30<00:34, 14.39it/s, loss=0.819, v_num=9]
Epoch 0:  48%|████▊     | 446/938 [00:30<00:34, 14.39it/s, loss=0.819, v_num=9]
Epoch 0:  48%|████▊     | 446/938 [00:30<00:34, 14.39it/s, loss=0.809, v_num=9]
Epoch 0:  48%|████▊     | 447/938 [00:31<00:34, 14.39it/s, loss=0.797, v_num=9]
Epoch 0:  48%|████▊     | 448/938 [00:31<00:34, 14.38it/s, loss=0.797, v_num=9]
Epoch 0:  48%|████▊     | 448/938 [00:31<00:34, 14.38it/s, loss=0.797, v_num=9]
Epoch 0:  48%|████▊     | 449/938 [00:31<00:33, 14.38it/s, loss=0.788, v_num=9]
Epoch 0:  48%|████▊     | 450/938 [00:31<00:33, 14.38it/s, loss=0.788, v_num=9]
Epoch 0:  48%|████▊     | 450/938 [00:31<00:33, 14.38it/s, loss=0.786, v_num=9]
Epoch 0:  48%|████▊     | 451/938 [00:31<00:33, 14.39it/s, loss=0.781, v_num=9]
Epoch 0:  48%|████▊     | 452/938 [00:31<00:33, 14.39it/s, loss=0.781, v_num=9]
Epoch 0:  48%|████▊     | 452/938 [00:31<00:33, 14.38it/s, loss=0.768, v_num=9]
Epoch 0:  48%|████▊     | 453/938 [00:31<00:33, 14.38it/s, loss=0.769, v_num=9]
Epoch 0:  48%|████▊     | 454/938 [00:31<00:33, 14.39it/s, loss=0.769, v_num=9]
Epoch 0:  48%|████▊     | 454/938 [00:31<00:33, 14.39it/s, loss=0.774, v_num=9]
Epoch 0:  49%|████▊     | 455/938 [00:31<00:33, 14.39it/s, loss=0.781, v_num=9]
Epoch 0:  49%|████▊     | 456/938 [00:31<00:33, 14.39it/s, loss=0.781, v_num=9]
Epoch 0:  49%|████▊     | 456/938 [00:31<00:33, 14.39it/s, loss=0.789, v_num=9]
Epoch 0:  49%|████▊     | 457/938 [00:31<00:33, 14.39it/s, loss=0.792, v_num=9]
Epoch 0:  49%|████▉     | 458/938 [00:31<00:33, 14.40it/s, loss=0.792, v_num=9]
Epoch 0:  49%|████▉     | 458/938 [00:31<00:33, 14.40it/s, loss=0.802, v_num=9]
Epoch 0:  49%|████▉     | 459/938 [00:31<00:33, 14.40it/s, loss=0.797, v_num=9]
Epoch 0:  49%|████▉     | 460/938 [00:31<00:33, 14.40it/s, loss=0.797, v_num=9]
Epoch 0:  49%|████▉     | 460/938 [00:31<00:33, 14.40it/s, loss=0.789, v_num=9]
Epoch 0:  49%|████▉     | 461/938 [00:32<00:33, 14.40it/s, loss=0.795, v_num=9]
Epoch 0:  49%|████▉     | 462/938 [00:32<00:33, 14.40it/s, loss=0.795, v_num=9]
Epoch 0:  49%|████▉     | 462/938 [00:32<00:33, 14.40it/s, loss=0.796, v_num=9]
Epoch 0:  49%|████▉     | 463/938 [00:32<00:33, 14.39it/s, loss=0.797, v_num=9]
Epoch 0:  49%|████▉     | 464/938 [00:32<00:32, 14.40it/s, loss=0.797, v_num=9]
Epoch 0:  49%|████▉     | 464/938 [00:32<00:32, 14.40it/s, loss=0.799, v_num=9]
Epoch 0:  50%|████▉     | 465/938 [00:32<00:32, 14.40it/s, loss=0.808, v_num=9]
Epoch 0:  50%|████▉     | 466/938 [00:32<00:32, 14.41it/s, loss=0.808, v_num=9]
Epoch 0:  50%|████▉     | 466/938 [00:32<00:32, 14.41it/s, loss=0.822, v_num=9]
Epoch 0:  50%|████▉     | 467/938 [00:32<00:32, 14.40it/s, loss=0.83, v_num=9] 
Epoch 0:  50%|████▉     | 468/938 [00:32<00:32, 14.40it/s, loss=0.83, v_num=9]
Epoch 0:  50%|████▉     | 468/938 [00:32<00:32, 14.40it/s, loss=0.835, v_num=9]
Epoch 0:  50%|█████     | 469/938 [00:32<00:32, 14.41it/s, loss=0.84, v_num=9] 

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]
Epoch 0:  50%|█████     | 471/938 [00:32<00:32, 14.45it/s, loss=0.84, v_num=9]

Validating:   0%|          | 2/469 [00:00<00:24, 19.21it/s]
Epoch 0:  51%|█████     | 474/938 [00:32<00:32, 14.48it/s, loss=0.84, v_num=9]

Validating:   1%|          | 5/469 [00:00<00:22, 20.71it/s]
Epoch 0:  51%|█████     | 477/938 [00:32<00:31, 14.52it/s, loss=0.84, v_num=9]

Validating:   2%|▏         | 8/469 [00:00<00:19, 23.17it/s]
Epoch 0:  51%|█████     | 480/938 [00:33<00:31, 14.54it/s, loss=0.84, v_num=9]

Validating:   2%|▏         | 11/469 [00:00<00:20, 22.22it/s]
Epoch 0:  51%|█████▏    | 483/938 [00:33<00:31, 14.59it/s, loss=0.84, v_num=9]

Validating:   3%|▎         | 14/469 [00:00<00:18, 24.24it/s]
Epoch 0:  52%|█████▏    | 486/938 [00:33<00:30, 14.63it/s, loss=0.84, v_num=9]

Validating:   4%|▎         | 17/469 [00:00<00:18, 25.07it/s]
Epoch 0:  52%|█████▏    | 489/938 [00:33<00:30, 14.67it/s, loss=0.84, v_num=9]

Validating:   4%|▍         | 20/469 [00:00<00:17, 25.95it/s]
Epoch 0:  52%|█████▏    | 492/938 [00:33<00:30, 14.71it/s, loss=0.84, v_num=9]

Validating:   5%|▍         | 23/469 [00:00<00:16, 26.28it/s]
Epoch 0:  53%|█████▎    | 495/938 [00:33<00:30, 14.75it/s, loss=0.84, v_num=9]

Validating:   6%|▌         | 26/469 [00:01<00:17, 25.79it/s]
Epoch 0:  53%|█████▎    | 498/938 [00:33<00:29, 14.79it/s, loss=0.84, v_num=9]

Validating:   6%|▌         | 29/469 [00:01<00:17, 25.69it/s]
Epoch 0:  53%|█████▎    | 501/938 [00:33<00:29, 14.83it/s, loss=0.84, v_num=9]

Validating:   7%|▋         | 32/469 [00:01<00:16, 26.05it/s]
Epoch 0:  54%|█████▎    | 504/938 [00:33<00:29, 14.87it/s, loss=0.84, v_num=9]

Validating:   7%|▋         | 35/469 [00:01<00:16, 26.55it/s]
Epoch 0:  54%|█████▍    | 507/938 [00:34<00:28, 14.90it/s, loss=0.84, v_num=9]

Validating:   8%|▊         | 38/469 [00:01<00:16, 25.93it/s]
Epoch 0:  54%|█████▍    | 510/938 [00:34<00:28, 14.94it/s, loss=0.84, v_num=9]

Validating:   9%|▊         | 41/469 [00:01<00:16, 25.94it/s]
Epoch 0:  55%|█████▍    | 513/938 [00:34<00:28, 14.98it/s, loss=0.84, v_num=9]

Validating:   9%|▉         | 44/469 [00:01<00:16, 25.64it/s]
Epoch 0:  55%|█████▌    | 516/938 [00:34<00:28, 15.01it/s, loss=0.84, v_num=9]

Validating:  10%|█         | 47/469 [00:01<00:16, 25.53it/s]
Epoch 0:  55%|█████▌    | 519/938 [00:34<00:27, 15.05it/s, loss=0.84, v_num=9]

Validating:  11%|█         | 50/469 [00:01<00:16, 24.85it/s]
Epoch 0:  56%|█████▌    | 522/938 [00:34<00:27, 15.08it/s, loss=0.84, v_num=9]

Validating:  11%|█▏        | 53/469 [00:02<00:16, 25.16it/s]
Epoch 0:  56%|█████▌    | 525/938 [00:34<00:27, 15.11it/s, loss=0.84, v_num=9]

Validating:  12%|█▏        | 56/469 [00:02<00:16, 24.62it/s]
Epoch 0:  56%|█████▋    | 528/938 [00:34<00:27, 15.15it/s, loss=0.84, v_num=9]

Validating:  13%|█▎        | 59/469 [00:02<00:16, 24.89it/s]
Epoch 0:  57%|█████▋    | 531/938 [00:34<00:26, 15.18it/s, loss=0.84, v_num=9]

Validating:  13%|█▎        | 62/469 [00:02<00:16, 25.32it/s]
Epoch 0:  57%|█████▋    | 534/938 [00:35<00:26, 15.21it/s, loss=0.84, v_num=9]

Validating:  14%|█▍        | 65/469 [00:02<00:16, 25.13it/s]
Epoch 0:  57%|█████▋    | 537/938 [00:35<00:26, 15.24it/s, loss=0.84, v_num=9]

Validating:  14%|█▍        | 68/469 [00:02<00:16, 24.80it/s]
Epoch 0:  58%|█████▊    | 540/938 [00:35<00:26, 15.28it/s, loss=0.84, v_num=9]

Validating:  15%|█▌        | 71/469 [00:02<00:15, 25.62it/s]
Epoch 0:  58%|█████▊    | 543/938 [00:35<00:25, 15.32it/s, loss=0.84, v_num=9]

Validating:  16%|█▌        | 74/469 [00:02<00:14, 26.44it/s]
Epoch 0:  58%|█████▊    | 546/938 [00:35<00:25, 15.36it/s, loss=0.84, v_num=9]

Validating:  16%|█▋        | 77/469 [00:03<00:14, 26.51it/s]
Epoch 0:  59%|█████▊    | 549/938 [00:35<00:25, 15.39it/s, loss=0.84, v_num=9]

Validating:  17%|█▋        | 80/469 [00:03<00:15, 25.83it/s]
Epoch 0:  59%|█████▉    | 552/938 [00:35<00:25, 15.43it/s, loss=0.84, v_num=9]

Validating:  18%|█▊        | 83/469 [00:03<00:14, 26.09it/s]
Epoch 0:  59%|█████▉    | 555/938 [00:35<00:24, 15.45it/s, loss=0.84, v_num=9]

Validating:  18%|█▊        | 86/469 [00:03<00:15, 25.36it/s]
Epoch 0:  59%|█████▉    | 558/938 [00:36<00:24, 15.49it/s, loss=0.84, v_num=9]

Validating:  19%|█▉        | 89/469 [00:03<00:14, 25.45it/s]
Epoch 0:  60%|█████▉    | 561/938 [00:36<00:24, 15.52it/s, loss=0.84, v_num=9]

Validating:  20%|█▉        | 92/469 [00:03<00:14, 25.31it/s]
Epoch 0:  60%|██████    | 564/938 [00:36<00:24, 15.56it/s, loss=0.84, v_num=9]

Validating:  20%|██        | 95/469 [00:03<00:14, 25.98it/s]
Epoch 0:  60%|██████    | 567/938 [00:36<00:23, 15.58it/s, loss=0.84, v_num=9]

Validating:  21%|██        | 98/469 [00:03<00:14, 25.21it/s]
Epoch 0:  61%|██████    | 570/938 [00:36<00:23, 15.61it/s, loss=0.84, v_num=9]

Validating:  22%|██▏       | 101/469 [00:04<00:14, 24.58it/s]
Epoch 0:  61%|██████    | 573/938 [00:36<00:23, 15.64it/s, loss=0.84, v_num=9]

Validating:  22%|██▏       | 104/469 [00:04<00:15, 24.16it/s]
Epoch 0:  61%|██████▏   | 576/938 [00:36<00:23, 15.67it/s, loss=0.84, v_num=9]

Validating:  23%|██▎       | 107/469 [00:04<00:14, 24.38it/s]
Epoch 0:  62%|██████▏   | 579/938 [00:36<00:22, 15.70it/s, loss=0.84, v_num=9]

Validating:  23%|██▎       | 110/469 [00:04<00:14, 24.77it/s]
Epoch 0:  62%|██████▏   | 582/938 [00:36<00:22, 15.73it/s, loss=0.84, v_num=9]

Validating:  24%|██▍       | 113/469 [00:04<00:14, 25.01it/s]
Epoch 0:  62%|██████▏   | 585/938 [00:37<00:22, 15.77it/s, loss=0.84, v_num=9]

Validating:  25%|██▍       | 116/469 [00:04<00:14, 25.10it/s]
Epoch 0:  63%|██████▎   | 588/938 [00:37<00:22, 15.79it/s, loss=0.84, v_num=9]

Validating:  25%|██▌       | 119/469 [00:04<00:14, 24.73it/s]
Epoch 0:  63%|██████▎   | 591/938 [00:37<00:21, 15.82it/s, loss=0.84, v_num=9]

Validating:  26%|██▌       | 122/469 [00:04<00:13, 25.07it/s]
Epoch 0:  63%|██████▎   | 594/938 [00:37<00:21, 15.85it/s, loss=0.84, v_num=9]

Validating:  27%|██▋       | 125/469 [00:04<00:13, 25.43it/s]
Epoch 0:  64%|██████▎   | 597/938 [00:37<00:21, 15.88it/s, loss=0.84, v_num=9]

Validating:  27%|██▋       | 128/469 [00:05<00:13, 25.50it/s]
Epoch 0:  64%|██████▍   | 600/938 [00:37<00:21, 15.92it/s, loss=0.84, v_num=9]

Validating:  28%|██▊       | 131/469 [00:05<00:13, 25.47it/s]
Epoch 0:  64%|██████▍   | 603/938 [00:37<00:21, 15.94it/s, loss=0.84, v_num=9]

Validating:  29%|██▊       | 134/469 [00:05<00:13, 25.64it/s]
Epoch 0:  65%|██████▍   | 606/938 [00:37<00:20, 15.98it/s, loss=0.84, v_num=9]

Validating:  29%|██▉       | 137/469 [00:05<00:12, 25.97it/s]
Epoch 0:  65%|██████▍   | 609/938 [00:38<00:20, 16.01it/s, loss=0.84, v_num=9]

Validating:  30%|██▉       | 140/469 [00:05<00:12, 26.07it/s]
Epoch 0:  65%|██████▌   | 612/938 [00:38<00:20, 16.03it/s, loss=0.84, v_num=9]

Validating:  30%|███       | 143/469 [00:05<00:13, 25.05it/s]
Epoch 0:  66%|██████▌   | 616/938 [00:38<00:20, 16.08it/s, loss=0.84, v_num=9]

Validating:  31%|███▏      | 147/469 [00:05<00:12, 26.15it/s]

Validating:  32%|███▏      | 150/469 [00:05<00:11, 26.79it/s]
Epoch 0:  66%|██████▌   | 620/938 [00:38<00:19, 16.12it/s, loss=0.84, v_num=9]

Validating:  33%|███▎      | 153/469 [00:06<00:11, 27.04it/s]
Epoch 0:  67%|██████▋   | 624/938 [00:38<00:19, 16.16it/s, loss=0.84, v_num=9]

Validating:  33%|███▎      | 156/469 [00:06<00:11, 26.97it/s]
Epoch 0:  67%|██████▋   | 628/938 [00:38<00:19, 16.20it/s, loss=0.84, v_num=9]

Validating:  34%|███▍      | 159/469 [00:06<00:11, 26.03it/s]

Validating:  35%|███▍      | 162/469 [00:06<00:12, 25.44it/s]
Epoch 0:  67%|██████▋   | 632/938 [00:38<00:18, 16.23it/s, loss=0.84, v_num=9]

Validating:  35%|███▌      | 165/469 [00:06<00:12, 25.23it/s]
Epoch 0:  68%|██████▊   | 636/938 [00:39<00:18, 16.27it/s, loss=0.84, v_num=9]

Validating:  36%|███▌      | 168/469 [00:06<00:12, 24.83it/s]
Epoch 0:  68%|██████▊   | 640/938 [00:39<00:18, 16.30it/s, loss=0.84, v_num=9]

Validating:  36%|███▋      | 171/469 [00:06<00:12, 24.68it/s]

Validating:  37%|███▋      | 174/469 [00:06<00:12, 23.83it/s]
Epoch 0:  69%|██████▊   | 644/938 [00:39<00:18, 16.33it/s, loss=0.84, v_num=9]

Validating:  38%|███▊      | 177/469 [00:07<00:12, 23.19it/s]
Epoch 0:  69%|██████▉   | 648/938 [00:39<00:17, 16.36it/s, loss=0.84, v_num=9]

Validating:  38%|███▊      | 180/469 [00:07<00:12, 23.87it/s]
Epoch 0:  70%|██████▉   | 652/938 [00:39<00:17, 16.39it/s, loss=0.84, v_num=9]

Validating:  39%|███▉      | 183/469 [00:07<00:12, 23.68it/s]

Validating:  40%|███▉      | 186/469 [00:07<00:11, 24.18it/s]
Epoch 0:  70%|██████▉   | 656/938 [00:39<00:17, 16.43it/s, loss=0.84, v_num=9]

Validating:  40%|████      | 189/469 [00:07<00:11, 24.39it/s]
Epoch 0:  70%|███████   | 660/938 [00:40<00:16, 16.46it/s, loss=0.84, v_num=9]

Validating:  41%|████      | 192/469 [00:07<00:11, 23.79it/s]
Epoch 0:  71%|███████   | 664/938 [00:40<00:16, 16.49it/s, loss=0.84, v_num=9]

Validating:  42%|████▏     | 195/469 [00:07<00:11, 24.25it/s]

Validating:  42%|████▏     | 198/469 [00:07<00:11, 24.29it/s]
Epoch 0:  71%|███████   | 668/938 [00:40<00:16, 16.52it/s, loss=0.84, v_num=9]

Validating:  43%|████▎     | 201/469 [00:08<00:11, 23.92it/s]
Epoch 0:  72%|███████▏  | 672/938 [00:40<00:16, 16.55it/s, loss=0.84, v_num=9]

Validating:  43%|████▎     | 204/469 [00:08<00:10, 24.11it/s]
Epoch 0:  72%|███████▏  | 676/938 [00:40<00:15, 16.59it/s, loss=0.84, v_num=9]

Validating:  44%|████▍     | 207/469 [00:08<00:10, 24.79it/s]
Epoch 0:  72%|███████▏  | 680/938 [00:40<00:15, 16.63it/s, loss=0.84, v_num=9]

Validating:  45%|████▍     | 211/469 [00:08<00:09, 25.93it/s]

Validating:  46%|████▌     | 214/469 [00:08<00:09, 25.67it/s]
Epoch 0:  73%|███████▎  | 684/938 [00:41<00:15, 16.66it/s, loss=0.84, v_num=9]

Validating:  46%|████▋     | 217/469 [00:08<00:09, 25.38it/s]
Epoch 0:  73%|███████▎  | 688/938 [00:41<00:14, 16.69it/s, loss=0.84, v_num=9]

Validating:  47%|████▋     | 220/469 [00:08<00:09, 26.40it/s]
Epoch 0:  74%|███████▍  | 692/938 [00:41<00:14, 16.73it/s, loss=0.84, v_num=9]

Validating:  48%|████▊     | 223/469 [00:08<00:09, 25.83it/s]

Validating:  48%|████▊     | 226/469 [00:08<00:09, 25.76it/s]
Epoch 0:  74%|███████▍  | 696/938 [00:41<00:14, 16.76it/s, loss=0.84, v_num=9]

Validating:  49%|████▉     | 229/469 [00:09<00:09, 25.62it/s]
Epoch 0:  75%|███████▍  | 700/938 [00:41<00:14, 16.80it/s, loss=0.84, v_num=9]

Validating:  49%|████▉     | 232/469 [00:09<00:09, 25.76it/s]
Epoch 0:  75%|███████▌  | 704/938 [00:41<00:13, 16.83it/s, loss=0.84, v_num=9]

Validating:  50%|█████     | 235/469 [00:09<00:08, 26.50it/s]

Validating:  51%|█████     | 238/469 [00:09<00:09, 24.54it/s]
Epoch 0:  75%|███████▌  | 708/938 [00:42<00:13, 16.85it/s, loss=0.84, v_num=9]

Validating:  51%|█████▏    | 241/469 [00:09<00:09, 25.29it/s]
Epoch 0:  76%|███████▌  | 712/938 [00:42<00:13, 16.89it/s, loss=0.84, v_num=9]

Validating:  52%|█████▏    | 244/469 [00:09<00:08, 25.60it/s]
Epoch 0:  76%|███████▋  | 716/938 [00:42<00:13, 16.92it/s, loss=0.84, v_num=9]

Validating:  53%|█████▎    | 247/469 [00:09<00:08, 26.10it/s]

Validating:  53%|█████▎    | 250/469 [00:09<00:08, 26.29it/s]
Epoch 0:  77%|███████▋  | 720/938 [00:42<00:12, 16.96it/s, loss=0.84, v_num=9]

Validating:  54%|█████▍    | 253/469 [00:10<00:08, 25.85it/s]
Epoch 0:  77%|███████▋  | 724/938 [00:42<00:12, 16.99it/s, loss=0.84, v_num=9]

Validating:  55%|█████▍    | 256/469 [00:10<00:08, 25.73it/s]
Epoch 0:  78%|███████▊  | 728/938 [00:42<00:12, 17.02it/s, loss=0.84, v_num=9]

Validating:  55%|█████▌    | 259/469 [00:10<00:08, 24.87it/s]

Validating:  56%|█████▌    | 262/469 [00:10<00:08, 24.80it/s]
Epoch 0:  78%|███████▊  | 732/938 [00:42<00:12, 17.05it/s, loss=0.84, v_num=9]

Validating:  57%|█████▋    | 265/469 [00:10<00:08, 24.98it/s]
Epoch 0:  78%|███████▊  | 736/938 [00:43<00:11, 17.08it/s, loss=0.84, v_num=9]

Validating:  57%|█████▋    | 268/469 [00:10<00:08, 24.73it/s]
Epoch 0:  79%|███████▉  | 740/938 [00:43<00:11, 17.11it/s, loss=0.84, v_num=9]

Validating:  58%|█████▊    | 271/469 [00:10<00:07, 24.89it/s]

Validating:  58%|█████▊    | 274/469 [00:10<00:07, 25.65it/s]
Epoch 0:  79%|███████▉  | 744/938 [00:43<00:11, 17.14it/s, loss=0.84, v_num=9]

Validating:  59%|█████▉    | 277/469 [00:10<00:07, 25.62it/s]
Epoch 0:  80%|███████▉  | 748/938 [00:43<00:11, 17.17it/s, loss=0.84, v_num=9]

Validating:  60%|█████▉    | 280/469 [00:11<00:07, 25.69it/s]
Epoch 0:  80%|████████  | 752/938 [00:43<00:10, 17.20it/s, loss=0.84, v_num=9]

Validating:  60%|██████    | 283/469 [00:11<00:07, 26.20it/s]

Validating:  61%|██████    | 286/469 [00:11<00:06, 26.51it/s]
Epoch 0:  81%|████████  | 756/938 [00:43<00:10, 17.24it/s, loss=0.84, v_num=9]

Validating:  62%|██████▏   | 289/469 [00:11<00:07, 23.98it/s]
Epoch 0:  81%|████████  | 760/938 [00:44<00:10, 17.25it/s, loss=0.84, v_num=9]

Validating:  62%|██████▏   | 292/469 [00:11<00:07, 25.28it/s]
Epoch 0:  81%|████████▏ | 764/938 [00:44<00:10, 17.28it/s, loss=0.84, v_num=9]

Validating:  63%|██████▎   | 295/469 [00:11<00:07, 24.76it/s]

Validating:  64%|██████▎   | 298/469 [00:11<00:06, 25.26it/s]
Epoch 0:  82%|████████▏ | 768/938 [00:44<00:09, 17.31it/s, loss=0.84, v_num=9]

Validating:  64%|██████▍   | 301/469 [00:11<00:06, 25.05it/s]
Epoch 0:  82%|████████▏ | 772/938 [00:44<00:09, 17.34it/s, loss=0.84, v_num=9]

Validating:  65%|██████▍   | 304/469 [00:12<00:06, 24.90it/s]
Epoch 0:  83%|████████▎ | 776/938 [00:44<00:09, 17.37it/s, loss=0.84, v_num=9]

Validating:  65%|██████▌   | 307/469 [00:12<00:06, 25.10it/s]

Validating:  66%|██████▌   | 310/469 [00:12<00:06, 25.35it/s]
Epoch 0:  83%|████████▎ | 780/938 [00:44<00:09, 17.40it/s, loss=0.84, v_num=9]

Validating:  67%|██████▋   | 313/469 [00:12<00:06, 25.10it/s]
Epoch 0:  84%|████████▎ | 784/938 [00:45<00:08, 17.42it/s, loss=0.84, v_num=9]

Validating:  67%|██████▋   | 316/469 [00:12<00:06, 24.86it/s]
Epoch 0:  84%|████████▍ | 788/938 [00:45<00:08, 17.45it/s, loss=0.84, v_num=9]

Validating:  68%|██████▊   | 319/469 [00:12<00:05, 25.34it/s]

Validating:  69%|██████▊   | 322/469 [00:12<00:05, 25.59it/s]
Epoch 0:  84%|████████▍ | 792/938 [00:45<00:08, 17.48it/s, loss=0.84, v_num=9]

Validating:  69%|██████▉   | 325/469 [00:12<00:05, 26.15it/s]
Epoch 0:  85%|████████▍ | 796/938 [00:45<00:08, 17.51it/s, loss=0.84, v_num=9]

Validating:  70%|██████▉   | 328/469 [00:13<00:05, 25.55it/s]
Epoch 0:  85%|████████▌ | 800/938 [00:45<00:07, 17.53it/s, loss=0.84, v_num=9]

Validating:  71%|███████   | 331/469 [00:13<00:05, 24.86it/s]

Validating:  71%|███████   | 334/469 [00:13<00:05, 24.77it/s]
Epoch 0:  86%|████████▌ | 804/938 [00:45<00:07, 17.56it/s, loss=0.84, v_num=9]

Validating:  72%|███████▏  | 337/469 [00:13<00:05, 23.66it/s]
Epoch 0:  86%|████████▌ | 808/938 [00:45<00:07, 17.58it/s, loss=0.84, v_num=9]

Validating:  72%|███████▏  | 340/469 [00:13<00:05, 24.09it/s]
Epoch 0:  87%|████████▋ | 812/938 [00:46<00:07, 17.61it/s, loss=0.84, v_num=9]

Validating:  73%|███████▎  | 343/469 [00:13<00:04, 25.47it/s]

Validating:  74%|███████▍  | 346/469 [00:13<00:04, 26.00it/s]
Epoch 0:  87%|████████▋ | 816/938 [00:46<00:06, 17.64it/s, loss=0.84, v_num=9]

Validating:  74%|███████▍  | 349/469 [00:13<00:04, 26.21it/s]
Epoch 0:  87%|████████▋ | 820/938 [00:46<00:06, 17.67it/s, loss=0.84, v_num=9]

Validating:  75%|███████▌  | 352/469 [00:13<00:04, 26.52it/s]
Epoch 0:  88%|████████▊ | 824/938 [00:46<00:06, 17.69it/s, loss=0.84, v_num=9]

Validating:  76%|███████▌  | 355/469 [00:14<00:04, 25.91it/s]

Validating:  76%|███████▋  | 358/469 [00:14<00:04, 26.20it/s]
Epoch 0:  88%|████████▊ | 828/938 [00:46<00:06, 17.72it/s, loss=0.84, v_num=9]

Validating:  77%|███████▋  | 361/469 [00:14<00:04, 25.61it/s]
Epoch 0:  89%|████████▊ | 832/938 [00:46<00:05, 17.75it/s, loss=0.84, v_num=9]

Validating:  78%|███████▊  | 364/469 [00:14<00:04, 26.16it/s]
Epoch 0:  89%|████████▉ | 836/938 [00:47<00:05, 17.77it/s, loss=0.84, v_num=9]

Validating:  78%|███████▊  | 367/469 [00:14<00:03, 25.97it/s]

Validating:  79%|███████▉  | 370/469 [00:14<00:03, 25.14it/s]
Epoch 0:  90%|████████▉ | 840/938 [00:47<00:05, 17.80it/s, loss=0.84, v_num=9]

Validating:  80%|███████▉  | 373/469 [00:14<00:03, 26.03it/s]
Epoch 0:  90%|████████▉ | 844/938 [00:47<00:05, 17.83it/s, loss=0.84, v_num=9]

Validating:  80%|████████  | 376/469 [00:14<00:03, 26.05it/s]
Epoch 0:  90%|█████████ | 848/938 [00:47<00:05, 17.86it/s, loss=0.84, v_num=9]

Validating:  81%|████████  | 379/469 [00:14<00:03, 26.79it/s]

Validating:  81%|████████▏ | 382/469 [00:15<00:03, 26.16it/s]
Epoch 0:  91%|█████████ | 852/938 [00:47<00:04, 17.88it/s, loss=0.84, v_num=9]

Validating:  82%|████████▏ | 385/469 [00:15<00:03, 26.50it/s]
Epoch 0:  91%|█████████▏| 856/938 [00:47<00:04, 17.91it/s, loss=0.84, v_num=9]

Validating:  83%|████████▎ | 388/469 [00:15<00:03, 25.40it/s]
Epoch 0:  92%|█████████▏| 860/938 [00:47<00:04, 17.93it/s, loss=0.84, v_num=9]

Validating:  83%|████████▎ | 391/469 [00:15<00:03, 24.99it/s]

Validating:  84%|████████▍ | 394/469 [00:15<00:02, 25.39it/s]
Epoch 0:  92%|█████████▏| 864/938 [00:48<00:04, 17.95it/s, loss=0.84, v_num=9]

Validating:  85%|████████▍ | 397/469 [00:15<00:02, 25.67it/s]
Epoch 0:  93%|█████████▎| 868/938 [00:48<00:03, 17.98it/s, loss=0.84, v_num=9]

Validating:  85%|████████▌ | 400/469 [00:15<00:02, 26.07it/s]
Epoch 0:  93%|█████████▎| 872/938 [00:48<00:03, 18.00it/s, loss=0.84, v_num=9]

Validating:  86%|████████▌ | 403/469 [00:15<00:02, 25.58it/s]

Validating:  87%|████████▋ | 406/469 [00:16<00:02, 26.25it/s]
Epoch 0:  93%|█████████▎| 876/938 [00:48<00:03, 18.03it/s, loss=0.84, v_num=9]

Validating:  87%|████████▋ | 409/469 [00:16<00:02, 26.14it/s]
Epoch 0:  94%|█████████▍| 880/938 [00:48<00:03, 18.06it/s, loss=0.84, v_num=9]

Validating:  88%|████████▊ | 412/469 [00:16<00:02, 25.92it/s]
Epoch 0:  94%|█████████▍| 884/938 [00:48<00:02, 18.08it/s, loss=0.84, v_num=9]

Validating:  88%|████████▊ | 415/469 [00:16<00:02, 25.37it/s]

Validating:  89%|████████▉ | 418/469 [00:16<00:02, 24.78it/s]
Epoch 0:  95%|█████████▍| 888/938 [00:49<00:02, 18.10it/s, loss=0.84, v_num=9]

Validating:  90%|████████▉ | 421/469 [00:16<00:01, 24.84it/s]
Epoch 0:  95%|█████████▌| 892/938 [00:49<00:02, 18.12it/s, loss=0.84, v_num=9]

Validating:  90%|█████████ | 424/469 [00:16<00:01, 25.94it/s]
Epoch 0:  96%|█████████▌| 896/938 [00:49<00:02, 18.15it/s, loss=0.84, v_num=9]

Validating:  91%|█████████ | 427/469 [00:16<00:01, 26.49it/s]

Validating:  92%|█████████▏| 430/469 [00:16<00:01, 26.53it/s]
Epoch 0:  96%|█████████▌| 900/938 [00:49<00:02, 18.18it/s, loss=0.84, v_num=9]

Validating:  92%|█████████▏| 433/469 [00:17<00:01, 25.66it/s]
Epoch 0:  96%|█████████▋| 904/938 [00:49<00:01, 18.20it/s, loss=0.84, v_num=9]

Validating:  93%|█████████▎| 436/469 [00:17<00:01, 26.12it/s]
Epoch 0:  97%|█████████▋| 908/938 [00:49<00:01, 18.21it/s, loss=0.84, v_num=9]

Validating:  94%|█████████▎| 439/469 [00:17<00:01, 23.43it/s]

Validating:  94%|█████████▍| 442/469 [00:17<00:01, 24.23it/s]
Epoch 0:  97%|█████████▋| 912/938 [00:50<00:01, 18.23it/s, loss=0.84, v_num=9]

Validating:  95%|█████████▍| 445/469 [00:17<00:01, 23.94it/s]
Epoch 0:  98%|█████████▊| 916/938 [00:50<00:01, 18.25it/s, loss=0.84, v_num=9]

Validating:  96%|█████████▌| 448/469 [00:17<00:00, 23.25it/s]
Epoch 0:  98%|█████████▊| 920/938 [00:50<00:00, 18.27it/s, loss=0.84, v_num=9]

Validating:  96%|█████████▌| 451/469 [00:17<00:00, 23.66it/s]

Validating:  97%|█████████▋| 454/469 [00:17<00:00, 24.49it/s]
Epoch 0:  99%|█████████▊| 924/938 [00:50<00:00, 18.29it/s, loss=0.84, v_num=9]

Validating:  97%|█████████▋| 457/469 [00:18<00:00, 24.97it/s]
Epoch 0:  99%|█████████▉| 928/938 [00:50<00:00, 18.31it/s, loss=0.84, v_num=9]

Validating:  98%|█████████▊| 460/469 [00:18<00:00, 24.45it/s]
Epoch 0:  99%|█████████▉| 932/938 [00:50<00:00, 18.33it/s, loss=0.84, v_num=9]

Validating:  99%|█████████▊| 463/469 [00:18<00:00, 24.44it/s]

Validating:  99%|█████████▉| 466/469 [00:18<00:00, 24.29it/s]
Epoch 0: 100%|█████████▉| 936/938 [00:51<00:00, 18.35it/s, loss=0.84, v_num=9]
Epoch 0: 100%|██████████| 938/938 [00:51<00:00, 18.35it/s, loss=0.84, v_num=9, val_rmse=0.772]

                                                             
Epoch 0: 100%|██████████| 938/938 [00:51<00:00, 18.34it/s, loss=0.84, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 0:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.84, v_num=9, val_rmse=0.772, train_rmse=1.230]          
Epoch 1:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.84, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   0%|          | 1/938 [00:00<01:35,  9.81it/s, loss=0.844, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   0%|          | 2/938 [00:00<01:31, 10.23it/s, loss=0.853, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   0%|          | 3/938 [00:00<01:20, 11.59it/s, loss=0.865, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   0%|          | 4/938 [00:00<01:14, 12.50it/s, loss=0.865, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   0%|          | 4/938 [00:00<01:14, 12.49it/s, loss=0.863, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   1%|          | 5/938 [00:00<01:12, 12.86it/s, loss=0.854, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   1%|          | 6/938 [00:00<01:09, 13.47it/s, loss=0.847, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   1%|          | 7/938 [00:00<01:10, 13.13it/s, loss=0.849, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   1%|          | 8/938 [00:00<01:10, 13.28it/s, loss=0.849, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   1%|          | 8/938 [00:00<01:10, 13.27it/s, loss=0.85, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:   1%|          | 9/938 [00:00<01:10, 13.21it/s, loss=0.834, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   1%|          | 10/938 [00:00<01:09, 13.37it/s, loss=0.83, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   1%|          | 11/938 [00:00<01:11, 12.91it/s, loss=0.84, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   1%|▏         | 12/938 [00:00<01:10, 13.19it/s, loss=0.84, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   1%|▏         | 12/938 [00:00<01:10, 13.18it/s, loss=0.837, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   1%|▏         | 13/938 [00:00<01:10, 13.10it/s, loss=0.824, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   1%|▏         | 14/938 [00:01<01:10, 13.18it/s, loss=0.829, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   2%|▏         | 15/938 [00:01<01:10, 13.12it/s, loss=0.837, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   2%|▏         | 16/938 [00:01<01:10, 13.13it/s, loss=0.837, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   2%|▏         | 16/938 [00:01<01:10, 13.12it/s, loss=0.837, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   2%|▏         | 17/938 [00:01<01:09, 13.19it/s, loss=0.826, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   2%|▏         | 18/938 [00:01<01:09, 13.26it/s, loss=0.831, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   2%|▏         | 19/938 [00:01<01:08, 13.33it/s, loss=0.832, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   2%|▏         | 20/938 [00:01<01:08, 13.48it/s, loss=0.832, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   2%|▏         | 20/938 [00:01<01:08, 13.48it/s, loss=0.828, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   2%|▏         | 21/938 [00:01<01:08, 13.45it/s, loss=0.823, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   2%|▏         | 22/938 [00:01<01:07, 13.52it/s, loss=0.831, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   2%|▏         | 23/938 [00:01<01:08, 13.30it/s, loss=0.821, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   3%|▎         | 24/938 [00:01<01:09, 13.19it/s, loss=0.821, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   3%|▎         | 24/938 [00:01<01:09, 13.18it/s, loss=0.821, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   3%|▎         | 25/938 [00:01<01:09, 13.08it/s, loss=0.83, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:   3%|▎         | 26/938 [00:01<01:09, 13.04it/s, loss=0.831, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   3%|▎         | 27/938 [00:02<01:10, 12.92it/s, loss=0.819, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   3%|▎         | 28/938 [00:02<01:09, 13.03it/s, loss=0.819, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   3%|▎         | 28/938 [00:02<01:09, 13.03it/s, loss=0.804, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   3%|▎         | 29/938 [00:02<01:09, 13.08it/s, loss=0.799, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   3%|▎         | 30/938 [00:02<01:09, 13.14it/s, loss=0.796, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   3%|▎         | 31/938 [00:02<01:09, 13.10it/s, loss=0.795, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   3%|▎         | 32/938 [00:02<01:08, 13.19it/s, loss=0.795, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   3%|▎         | 32/938 [00:02<01:08, 13.19it/s, loss=0.79, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:   4%|▎         | 33/938 [00:02<01:08, 13.22it/s, loss=0.795, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   4%|▎         | 34/938 [00:02<01:07, 13.31it/s, loss=0.794, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   4%|▎         | 35/938 [00:02<01:07, 13.33it/s, loss=0.791, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   4%|▍         | 36/938 [00:02<01:07, 13.36it/s, loss=0.791, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   4%|▍         | 36/938 [00:02<01:07, 13.36it/s, loss=0.792, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   4%|▍         | 37/938 [00:02<01:07, 13.43it/s, loss=0.793, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   4%|▍         | 38/938 [00:02<01:06, 13.44it/s, loss=0.784, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   4%|▍         | 39/938 [00:02<01:06, 13.43it/s, loss=0.785, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   4%|▍         | 40/938 [00:02<01:06, 13.46it/s, loss=0.785, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   4%|▍         | 40/938 [00:02<01:06, 13.46it/s, loss=0.788, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   4%|▍         | 41/938 [00:03<01:06, 13.51it/s, loss=0.788, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   4%|▍         | 42/938 [00:03<01:06, 13.48it/s, loss=0.774, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   5%|▍         | 43/938 [00:03<01:06, 13.48it/s, loss=0.778, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   5%|▍         | 44/938 [00:03<01:06, 13.51it/s, loss=0.778, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   5%|▍         | 44/938 [00:03<01:06, 13.51it/s, loss=0.781, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   5%|▍         | 45/938 [00:03<01:05, 13.54it/s, loss=0.775, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   5%|▍         | 46/938 [00:03<01:06, 13.46it/s, loss=0.767, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   5%|▌         | 47/938 [00:03<01:06, 13.49it/s, loss=0.766, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   5%|▌         | 48/938 [00:03<01:05, 13.49it/s, loss=0.766, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   5%|▌         | 48/938 [00:03<01:06, 13.48it/s, loss=0.785, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   5%|▌         | 49/938 [00:03<01:05, 13.49it/s, loss=0.792, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   5%|▌         | 50/938 [00:03<01:05, 13.52it/s, loss=0.799, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   5%|▌         | 51/938 [00:03<01:05, 13.55it/s, loss=0.796, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   6%|▌         | 52/938 [00:03<01:05, 13.56it/s, loss=0.796, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   6%|▌         | 52/938 [00:03<01:05, 13.56it/s, loss=0.8, v_num=9, val_rmse=0.772, train_rmse=1.230]  
Epoch 1:   6%|▌         | 53/938 [00:03<01:05, 13.51it/s, loss=0.807, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   6%|▌         | 54/938 [00:03<01:05, 13.53it/s, loss=0.807, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   6%|▌         | 55/938 [00:04<01:05, 13.51it/s, loss=0.81, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:   6%|▌         | 56/938 [00:04<01:05, 13.56it/s, loss=0.81, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   6%|▌         | 56/938 [00:04<01:05, 13.56it/s, loss=0.808, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   6%|▌         | 57/938 [00:04<01:04, 13.58it/s, loss=0.816, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   6%|▌         | 58/938 [00:04<01:04, 13.60it/s, loss=0.816, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   6%|▋         | 59/938 [00:04<01:04, 13.65it/s, loss=0.815, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   6%|▋         | 60/938 [00:04<01:04, 13.66it/s, loss=0.815, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   6%|▋         | 60/938 [00:04<01:04, 13.66it/s, loss=0.81, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:   7%|▋         | 61/938 [00:04<01:03, 13.74it/s, loss=0.806, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   7%|▋         | 62/938 [00:04<01:03, 13.75it/s, loss=0.804, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   7%|▋         | 63/938 [00:04<01:03, 13.75it/s, loss=0.803, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   7%|▋         | 64/938 [00:04<01:03, 13.78it/s, loss=0.803, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   7%|▋         | 64/938 [00:04<01:03, 13.78it/s, loss=0.798, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   7%|▋         | 65/938 [00:04<01:03, 13.77it/s, loss=0.798, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   7%|▋         | 66/938 [00:04<01:03, 13.79it/s, loss=0.821, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   7%|▋         | 67/938 [00:04<01:03, 13.78it/s, loss=0.823, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   7%|▋         | 68/938 [00:04<01:03, 13.76it/s, loss=0.823, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   7%|▋         | 68/938 [00:04<01:03, 13.76it/s, loss=0.814, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   7%|▋         | 69/938 [00:05<01:03, 13.78it/s, loss=0.818, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   7%|▋         | 70/938 [00:05<01:03, 13.75it/s, loss=0.813, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   8%|▊         | 71/938 [00:05<01:03, 13.71it/s, loss=0.81, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:   8%|▊         | 72/938 [00:05<01:03, 13.70it/s, loss=0.81, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   8%|▊         | 72/938 [00:05<01:03, 13.70it/s, loss=0.807, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   8%|▊         | 73/938 [00:05<01:03, 13.72it/s, loss=0.806, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   8%|▊         | 74/938 [00:05<01:03, 13.70it/s, loss=0.794, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   8%|▊         | 75/938 [00:05<01:02, 13.70it/s, loss=0.795, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   8%|▊         | 76/938 [00:05<01:02, 13.75it/s, loss=0.795, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   8%|▊         | 76/938 [00:05<01:02, 13.75it/s, loss=0.789, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   8%|▊         | 77/938 [00:05<01:02, 13.75it/s, loss=0.788, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   8%|▊         | 78/938 [00:05<01:02, 13.76it/s, loss=0.794, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   8%|▊         | 79/938 [00:05<01:02, 13.67it/s, loss=0.801, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   9%|▊         | 80/938 [00:05<01:02, 13.66it/s, loss=0.801, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   9%|▊         | 80/938 [00:05<01:02, 13.66it/s, loss=0.803, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   9%|▊         | 81/938 [00:05<01:02, 13.67it/s, loss=0.805, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   9%|▊         | 82/938 [00:05<01:02, 13.71it/s, loss=0.81, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:   9%|▉         | 83/938 [00:06<01:02, 13.68it/s, loss=0.806, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   9%|▉         | 84/938 [00:06<01:02, 13.68it/s, loss=0.806, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   9%|▉         | 84/938 [00:06<01:02, 13.68it/s, loss=0.813, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   9%|▉         | 85/938 [00:06<01:02, 13.59it/s, loss=0.821, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   9%|▉         | 86/938 [00:06<01:02, 13.62it/s, loss=0.809, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   9%|▉         | 87/938 [00:06<01:02, 13.63it/s, loss=0.814, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   9%|▉         | 88/938 [00:06<01:02, 13.66it/s, loss=0.814, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   9%|▉         | 88/938 [00:06<01:02, 13.66it/s, loss=0.811, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:   9%|▉         | 89/938 [00:06<01:02, 13.64it/s, loss=0.799, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  10%|▉         | 90/938 [00:06<01:02, 13.63it/s, loss=0.796, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  10%|▉         | 91/938 [00:06<01:02, 13.64it/s, loss=0.798, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  10%|▉         | 92/938 [00:06<01:02, 13.62it/s, loss=0.798, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  10%|▉         | 92/938 [00:06<01:02, 13.62it/s, loss=0.803, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  10%|▉         | 93/938 [00:06<01:01, 13.64it/s, loss=0.799, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  10%|█         | 94/938 [00:06<01:01, 13.64it/s, loss=0.806, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  10%|█         | 95/938 [00:06<01:01, 13.65it/s, loss=0.797, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  10%|█         | 96/938 [00:07<01:01, 13.66it/s, loss=0.797, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  10%|█         | 96/938 [00:07<01:01, 13.66it/s, loss=0.796, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  10%|█         | 97/938 [00:07<01:01, 13.69it/s, loss=0.791, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  10%|█         | 98/938 [00:07<01:01, 13.70it/s, loss=0.783, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  11%|█         | 99/938 [00:07<01:01, 13.73it/s, loss=0.777, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  11%|█         | 100/938 [00:07<01:01, 13.73it/s, loss=0.777, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  11%|█         | 100/938 [00:07<01:01, 13.73it/s, loss=0.79, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  11%|█         | 101/938 [00:07<01:00, 13.75it/s, loss=0.791, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  11%|█         | 102/938 [00:07<01:00, 13.73it/s, loss=0.785, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  11%|█         | 103/938 [00:07<01:00, 13.74it/s, loss=0.787, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  11%|█         | 104/938 [00:07<01:00, 13.72it/s, loss=0.787, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  11%|█         | 104/938 [00:07<01:00, 13.72it/s, loss=0.78, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  11%|█         | 105/938 [00:07<01:00, 13.74it/s, loss=0.778, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  11%|█▏        | 106/938 [00:07<01:00, 13.74it/s, loss=0.776, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  11%|█▏        | 107/938 [00:07<01:00, 13.74it/s, loss=0.78, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  12%|█▏        | 108/938 [00:07<01:00, 13.75it/s, loss=0.78, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  12%|█▏        | 108/938 [00:07<01:00, 13.75it/s, loss=0.78, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  12%|█▏        | 109/938 [00:07<01:00, 13.72it/s, loss=0.787, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  12%|█▏        | 110/938 [00:08<01:00, 13.73it/s, loss=0.807, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  12%|█▏        | 111/938 [00:08<01:00, 13.73it/s, loss=0.807, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  12%|█▏        | 112/938 [00:08<01:00, 13.72it/s, loss=0.807, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  12%|█▏        | 112/938 [00:08<01:00, 13.72it/s, loss=0.8, v_num=9, val_rmse=0.772, train_rmse=1.230]  
Epoch 1:  12%|█▏        | 113/938 [00:08<01:00, 13.73it/s, loss=0.799, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  12%|█▏        | 114/938 [00:08<01:00, 13.62it/s, loss=0.801, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  12%|█▏        | 115/938 [00:08<01:00, 13.63it/s, loss=0.792, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  12%|█▏        | 116/938 [00:08<01:00, 13.65it/s, loss=0.792, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  12%|█▏        | 116/938 [00:08<01:00, 13.65it/s, loss=0.794, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  12%|█▏        | 117/938 [00:08<01:00, 13.61it/s, loss=0.791, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  13%|█▎        | 118/938 [00:08<01:00, 13.60it/s, loss=0.794, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  13%|█▎        | 119/938 [00:08<01:00, 13.63it/s, loss=0.789, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  13%|█▎        | 120/938 [00:08<01:00, 13.62it/s, loss=0.789, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  13%|█▎        | 120/938 [00:08<01:00, 13.62it/s, loss=0.775, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  13%|█▎        | 121/938 [00:08<00:59, 13.62it/s, loss=0.78, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  13%|█▎        | 122/938 [00:08<00:59, 13.64it/s, loss=0.789, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  13%|█▎        | 123/938 [00:09<00:59, 13.62it/s, loss=0.786, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  13%|█▎        | 124/938 [00:09<00:59, 13.60it/s, loss=0.786, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  13%|█▎        | 124/938 [00:09<00:59, 13.60it/s, loss=0.781, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  13%|█▎        | 125/938 [00:09<00:59, 13.60it/s, loss=0.78, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  13%|█▎        | 126/938 [00:09<00:59, 13.63it/s, loss=0.777, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  14%|█▎        | 127/938 [00:09<00:59, 13.63it/s, loss=0.78, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  14%|█▎        | 128/938 [00:09<00:59, 13.64it/s, loss=0.78, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  14%|█▎        | 128/938 [00:09<00:59, 13.64it/s, loss=0.774, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  14%|█▍        | 129/938 [00:09<00:59, 13.65it/s, loss=0.776, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  14%|█▍        | 130/938 [00:09<00:59, 13.68it/s, loss=0.763, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  14%|█▍        | 131/938 [00:09<00:58, 13.69it/s, loss=0.774, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  14%|█▍        | 132/938 [00:09<00:58, 13.69it/s, loss=0.774, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  14%|█▍        | 132/938 [00:09<00:58, 13.68it/s, loss=0.792, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  14%|█▍        | 133/938 [00:09<00:58, 13.72it/s, loss=0.792, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  14%|█▍        | 134/938 [00:09<00:58, 13.69it/s, loss=0.776, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  14%|█▍        | 135/938 [00:09<00:58, 13.70it/s, loss=0.781, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  14%|█▍        | 136/938 [00:09<00:58, 13.71it/s, loss=0.781, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  14%|█▍        | 136/938 [00:09<00:58, 13.71it/s, loss=0.778, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  15%|█▍        | 137/938 [00:09<00:58, 13.73it/s, loss=0.79, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  15%|█▍        | 138/938 [00:10<00:58, 13.72it/s, loss=0.792, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  15%|█▍        | 139/938 [00:10<00:58, 13.72it/s, loss=0.795, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  15%|█▍        | 140/938 [00:10<00:58, 13.73it/s, loss=0.795, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  15%|█▍        | 140/938 [00:10<00:58, 13.73it/s, loss=0.803, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  15%|█▌        | 141/938 [00:10<00:58, 13.72it/s, loss=0.803, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  15%|█▌        | 142/938 [00:10<00:58, 13.72it/s, loss=0.812, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  15%|█▌        | 143/938 [00:10<00:57, 13.72it/s, loss=0.815, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  15%|█▌        | 144/938 [00:10<00:57, 13.72it/s, loss=0.815, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  15%|█▌        | 144/938 [00:10<00:57, 13.72it/s, loss=0.817, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  15%|█▌        | 145/938 [00:10<00:57, 13.72it/s, loss=0.81, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  16%|█▌        | 146/938 [00:10<00:57, 13.69it/s, loss=0.823, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  16%|█▌        | 147/938 [00:10<00:57, 13.68it/s, loss=0.81, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  16%|█▌        | 148/938 [00:10<00:57, 13.70it/s, loss=0.81, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  16%|█▌        | 148/938 [00:10<00:57, 13.70it/s, loss=0.815, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  16%|█▌        | 149/938 [00:10<00:57, 13.70it/s, loss=0.819, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  16%|█▌        | 150/938 [00:10<00:57, 13.67it/s, loss=0.817, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  16%|█▌        | 151/938 [00:11<00:57, 13.68it/s, loss=0.803, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  16%|█▌        | 152/938 [00:11<00:57, 13.70it/s, loss=0.803, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  16%|█▌        | 152/938 [00:11<00:57, 13.70it/s, loss=0.803, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  16%|█▋        | 153/938 [00:11<00:57, 13.70it/s, loss=0.805, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  16%|█▋        | 154/938 [00:11<00:57, 13.71it/s, loss=0.827, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  17%|█▋        | 155/938 [00:11<00:57, 13.71it/s, loss=0.842, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  17%|█▋        | 156/938 [00:11<00:57, 13.70it/s, loss=0.842, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  17%|█▋        | 156/938 [00:11<00:57, 13.70it/s, loss=0.845, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  17%|█▋        | 157/938 [00:11<00:57, 13.70it/s, loss=0.847, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  17%|█▋        | 158/938 [00:11<00:56, 13.71it/s, loss=0.852, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  17%|█▋        | 159/938 [00:11<00:56, 13.72it/s, loss=0.853, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  17%|█▋        | 160/938 [00:11<00:56, 13.71it/s, loss=0.853, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  17%|█▋        | 160/938 [00:11<00:56, 13.71it/s, loss=0.853, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  17%|█▋        | 161/938 [00:11<00:56, 13.71it/s, loss=0.842, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  17%|█▋        | 162/938 [00:11<00:56, 13.70it/s, loss=0.822, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  17%|█▋        | 163/938 [00:11<00:56, 13.70it/s, loss=0.832, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  17%|█▋        | 164/938 [00:11<00:56, 13.72it/s, loss=0.832, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  17%|█▋        | 164/938 [00:11<00:56, 13.72it/s, loss=0.831, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  18%|█▊        | 165/938 [00:12<00:56, 13.71it/s, loss=0.83, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  18%|█▊        | 166/938 [00:12<00:56, 13.71it/s, loss=0.816, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  18%|█▊        | 167/938 [00:12<00:56, 13.70it/s, loss=0.818, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  18%|█▊        | 168/938 [00:12<00:56, 13.71it/s, loss=0.818, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  18%|█▊        | 168/938 [00:12<00:56, 13.71it/s, loss=0.821, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  18%|█▊        | 169/938 [00:12<00:56, 13.70it/s, loss=0.81, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  18%|█▊        | 170/938 [00:12<00:56, 13.69it/s, loss=0.816, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  18%|█▊        | 171/938 [00:12<00:56, 13.69it/s, loss=0.822, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  18%|█▊        | 172/938 [00:12<00:55, 13.69it/s, loss=0.822, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  18%|█▊        | 172/938 [00:12<00:55, 13.69it/s, loss=0.818, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  18%|█▊        | 173/938 [00:12<00:55, 13.68it/s, loss=0.832, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  19%|█▊        | 174/938 [00:12<00:55, 13.69it/s, loss=0.819, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  19%|█▊        | 175/938 [00:12<00:55, 13.70it/s, loss=0.812, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  19%|█▉        | 176/938 [00:12<00:55, 13.71it/s, loss=0.812, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  19%|█▉        | 176/938 [00:12<00:55, 13.71it/s, loss=0.812, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  19%|█▉        | 177/938 [00:12<00:55, 13.71it/s, loss=0.814, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  19%|█▉        | 178/938 [00:12<00:55, 13.72it/s, loss=0.81, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  19%|█▉        | 179/938 [00:13<00:55, 13.71it/s, loss=0.809, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  19%|█▉        | 180/938 [00:13<00:55, 13.72it/s, loss=0.809, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  19%|█▉        | 180/938 [00:13<00:55, 13.72it/s, loss=0.804, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  19%|█▉        | 181/938 [00:13<00:55, 13.71it/s, loss=0.818, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  19%|█▉        | 182/938 [00:13<00:55, 13.70it/s, loss=0.828, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  20%|█▉        | 183/938 [00:13<00:55, 13.72it/s, loss=0.828, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  20%|█▉        | 184/938 [00:13<00:54, 13.71it/s, loss=0.828, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  20%|█▉        | 184/938 [00:13<00:54, 13.71it/s, loss=0.833, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  20%|█▉        | 185/938 [00:13<00:54, 13.72it/s, loss=0.831, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  20%|█▉        | 186/938 [00:13<00:54, 13.72it/s, loss=0.831, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  20%|█▉        | 187/938 [00:13<00:54, 13.71it/s, loss=0.842, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  20%|██        | 188/938 [00:13<00:54, 13.71it/s, loss=0.842, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  20%|██        | 188/938 [00:13<00:54, 13.71it/s, loss=0.843, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  20%|██        | 189/938 [00:13<00:54, 13.67it/s, loss=0.847, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  20%|██        | 190/938 [00:13<00:54, 13.67it/s, loss=0.843, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  20%|██        | 191/938 [00:13<00:54, 13.67it/s, loss=0.835, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  20%|██        | 192/938 [00:14<00:54, 13.68it/s, loss=0.835, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  20%|██        | 192/938 [00:14<00:54, 13.68it/s, loss=0.829, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  21%|██        | 193/938 [00:14<00:54, 13.68it/s, loss=0.815, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  21%|██        | 194/938 [00:14<00:54, 13.68it/s, loss=0.81, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  21%|██        | 195/938 [00:14<00:54, 13.68it/s, loss=0.816, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  21%|██        | 196/938 [00:14<00:54, 13.69it/s, loss=0.816, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  21%|██        | 196/938 [00:14<00:54, 13.68it/s, loss=0.819, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  21%|██        | 197/938 [00:14<00:54, 13.67it/s, loss=0.804, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  21%|██        | 198/938 [00:14<00:54, 13.68it/s, loss=0.797, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  21%|██        | 199/938 [00:14<00:53, 13.70it/s, loss=0.792, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  21%|██▏       | 200/938 [00:14<00:53, 13.69it/s, loss=0.792, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  21%|██▏       | 200/938 [00:14<00:53, 13.69it/s, loss=0.791, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  21%|██▏       | 201/938 [00:14<00:53, 13.70it/s, loss=0.781, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  22%|██▏       | 202/938 [00:14<00:53, 13.70it/s, loss=0.769, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  22%|██▏       | 203/938 [00:14<00:53, 13.70it/s, loss=0.762, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  22%|██▏       | 204/938 [00:14<00:53, 13.71it/s, loss=0.762, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  22%|██▏       | 204/938 [00:14<00:53, 13.71it/s, loss=0.762, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  22%|██▏       | 205/938 [00:14<00:53, 13.72it/s, loss=0.762, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  22%|██▏       | 206/938 [00:15<00:53, 13.73it/s, loss=0.768, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  22%|██▏       | 207/938 [00:15<00:53, 13.74it/s, loss=0.759, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  22%|██▏       | 208/938 [00:15<00:53, 13.74it/s, loss=0.759, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  22%|██▏       | 208/938 [00:15<00:53, 13.74it/s, loss=0.75, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  22%|██▏       | 209/938 [00:15<00:53, 13.74it/s, loss=0.742, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  22%|██▏       | 210/938 [00:15<00:53, 13.73it/s, loss=0.738, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  22%|██▏       | 211/938 [00:15<00:52, 13.74it/s, loss=0.742, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  23%|██▎       | 212/938 [00:15<00:52, 13.74it/s, loss=0.742, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  23%|██▎       | 212/938 [00:15<00:52, 13.74it/s, loss=0.739, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  23%|██▎       | 213/938 [00:15<00:52, 13.74it/s, loss=0.734, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  23%|██▎       | 214/938 [00:15<00:52, 13.74it/s, loss=0.732, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  23%|██▎       | 215/938 [00:15<00:52, 13.73it/s, loss=0.734, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  23%|██▎       | 216/938 [00:15<00:52, 13.73it/s, loss=0.734, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  23%|██▎       | 216/938 [00:15<00:52, 13.73it/s, loss=0.73, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  23%|██▎       | 217/938 [00:15<00:52, 13.72it/s, loss=0.733, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  23%|██▎       | 218/938 [00:15<00:52, 13.72it/s, loss=0.737, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  23%|██▎       | 219/938 [00:15<00:52, 13.71it/s, loss=0.749, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  23%|██▎       | 220/938 [00:16<00:52, 13.73it/s, loss=0.749, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  23%|██▎       | 220/938 [00:16<00:52, 13.73it/s, loss=0.752, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  24%|██▎       | 221/938 [00:16<00:52, 13.72it/s, loss=0.745, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  24%|██▎       | 222/938 [00:16<00:52, 13.72it/s, loss=0.758, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  24%|██▍       | 223/938 [00:16<00:52, 13.73it/s, loss=0.753, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  24%|██▍       | 224/938 [00:16<00:52, 13.73it/s, loss=0.753, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  24%|██▍       | 224/938 [00:16<00:52, 13.73it/s, loss=0.753, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  24%|██▍       | 225/938 [00:16<00:51, 13.74it/s, loss=0.759, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  24%|██▍       | 226/938 [00:16<00:51, 13.74it/s, loss=0.752, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  24%|██▍       | 227/938 [00:16<00:51, 13.75it/s, loss=0.746, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  24%|██▍       | 228/938 [00:16<00:51, 13.77it/s, loss=0.746, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  24%|██▍       | 228/938 [00:16<00:51, 13.77it/s, loss=0.755, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  24%|██▍       | 229/938 [00:16<00:51, 13.78it/s, loss=0.762, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  25%|██▍       | 230/938 [00:16<00:51, 13.79it/s, loss=0.759, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  25%|██▍       | 231/938 [00:16<00:51, 13.80it/s, loss=0.764, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  25%|██▍       | 232/938 [00:16<00:51, 13.80it/s, loss=0.764, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  25%|██▍       | 232/938 [00:16<00:51, 13.80it/s, loss=0.766, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  25%|██▍       | 233/938 [00:16<00:51, 13.80it/s, loss=0.767, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  25%|██▍       | 234/938 [00:16<00:51, 13.79it/s, loss=0.771, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  25%|██▌       | 235/938 [00:17<00:50, 13.81it/s, loss=0.762, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  25%|██▌       | 236/938 [00:17<00:50, 13.82it/s, loss=0.762, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  25%|██▌       | 236/938 [00:17<00:50, 13.82it/s, loss=0.761, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  25%|██▌       | 237/938 [00:17<00:50, 13.82it/s, loss=0.757, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  25%|██▌       | 238/938 [00:17<00:50, 13.83it/s, loss=0.753, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  25%|██▌       | 239/938 [00:17<00:50, 13.82it/s, loss=0.741, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  26%|██▌       | 240/938 [00:17<00:50, 13.82it/s, loss=0.741, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  26%|██▌       | 240/938 [00:17<00:50, 13.82it/s, loss=0.735, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  26%|██▌       | 241/938 [00:17<00:50, 13.81it/s, loss=0.741, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  26%|██▌       | 242/938 [00:17<00:50, 13.82it/s, loss=0.739, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  26%|██▌       | 243/938 [00:17<00:50, 13.81it/s, loss=0.736, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  26%|██▌       | 244/938 [00:17<00:50, 13.82it/s, loss=0.736, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  26%|██▌       | 244/938 [00:17<00:50, 13.82it/s, loss=0.736, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  26%|██▌       | 245/938 [00:17<00:50, 13.82it/s, loss=0.73, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  26%|██▌       | 246/938 [00:17<00:50, 13.83it/s, loss=0.728, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  26%|██▋       | 247/938 [00:17<00:49, 13.84it/s, loss=0.725, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  26%|██▋       | 248/938 [00:17<00:49, 13.85it/s, loss=0.725, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  26%|██▋       | 248/938 [00:17<00:49, 13.85it/s, loss=0.721, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  27%|██▋       | 249/938 [00:17<00:49, 13.85it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  27%|██▋       | 250/938 [00:18<00:49, 13.85it/s, loss=0.733, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  27%|██▋       | 251/938 [00:18<00:49, 13.85it/s, loss=0.728, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  27%|██▋       | 252/938 [00:18<00:49, 13.85it/s, loss=0.728, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  27%|██▋       | 252/938 [00:18<00:49, 13.85it/s, loss=0.722, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  27%|██▋       | 253/938 [00:18<00:49, 13.86it/s, loss=0.72, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  27%|██▋       | 254/938 [00:18<00:49, 13.85it/s, loss=0.721, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  27%|██▋       | 255/938 [00:18<00:49, 13.85it/s, loss=0.722, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  27%|██▋       | 256/938 [00:18<00:49, 13.85it/s, loss=0.722, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  27%|██▋       | 256/938 [00:18<00:49, 13.85it/s, loss=0.731, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  27%|██▋       | 257/938 [00:18<00:49, 13.85it/s, loss=0.73, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  28%|██▊       | 258/938 [00:18<00:49, 13.85it/s, loss=0.745, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  28%|██▊       | 259/938 [00:18<00:49, 13.85it/s, loss=0.741, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  28%|██▊       | 260/938 [00:18<00:48, 13.84it/s, loss=0.741, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  28%|██▊       | 260/938 [00:18<00:48, 13.84it/s, loss=0.751, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  28%|██▊       | 261/938 [00:18<00:48, 13.84it/s, loss=0.749, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  28%|██▊       | 262/938 [00:18<00:48, 13.85it/s, loss=0.735, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  28%|██▊       | 263/938 [00:18<00:48, 13.85it/s, loss=0.744, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  28%|██▊       | 264/938 [00:19<00:48, 13.85it/s, loss=0.744, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  28%|██▊       | 264/938 [00:19<00:48, 13.85it/s, loss=0.737, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  28%|██▊       | 265/938 [00:19<00:48, 13.84it/s, loss=0.746, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  28%|██▊       | 266/938 [00:19<00:48, 13.84it/s, loss=0.747, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  28%|██▊       | 267/938 [00:19<00:48, 13.83it/s, loss=0.75, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  29%|██▊       | 268/938 [00:19<00:48, 13.82it/s, loss=0.75, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  29%|██▊       | 268/938 [00:19<00:48, 13.82it/s, loss=0.746, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  29%|██▊       | 269/938 [00:19<00:48, 13.83it/s, loss=0.752, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  29%|██▉       | 270/938 [00:19<00:48, 13.83it/s, loss=0.74, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  29%|██▉       | 271/938 [00:19<00:48, 13.83it/s, loss=0.738, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  29%|██▉       | 272/938 [00:19<00:48, 13.83it/s, loss=0.738, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  29%|██▉       | 272/938 [00:19<00:48, 13.83it/s, loss=0.739, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  29%|██▉       | 273/938 [00:19<00:48, 13.82it/s, loss=0.742, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  29%|██▉       | 274/938 [00:19<00:48, 13.82it/s, loss=0.743, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  29%|██▉       | 275/938 [00:19<00:47, 13.82it/s, loss=0.736, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  29%|██▉       | 276/938 [00:19<00:47, 13.82it/s, loss=0.736, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  29%|██▉       | 276/938 [00:19<00:47, 13.82it/s, loss=0.727, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  30%|██▉       | 277/938 [00:20<00:47, 13.82it/s, loss=0.735, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  30%|██▉       | 278/938 [00:20<00:47, 13.81it/s, loss=0.717, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  30%|██▉       | 279/938 [00:20<00:47, 13.81it/s, loss=0.724, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  30%|██▉       | 280/938 [00:20<00:47, 13.82it/s, loss=0.724, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  30%|██▉       | 280/938 [00:20<00:47, 13.82it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  30%|██▉       | 281/938 [00:20<00:47, 13.81it/s, loss=0.716, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  30%|███       | 282/938 [00:20<00:47, 13.82it/s, loss=0.724, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  30%|███       | 283/938 [00:20<00:47, 13.81it/s, loss=0.734, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  30%|███       | 284/938 [00:20<00:47, 13.81it/s, loss=0.734, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  30%|███       | 284/938 [00:20<00:47, 13.81it/s, loss=0.74, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  30%|███       | 285/938 [00:20<00:47, 13.80it/s, loss=0.733, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  30%|███       | 286/938 [00:20<00:47, 13.81it/s, loss=0.736, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  31%|███       | 287/938 [00:20<00:47, 13.81it/s, loss=0.733, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  31%|███       | 288/938 [00:20<00:47, 13.81it/s, loss=0.733, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  31%|███       | 288/938 [00:20<00:47, 13.81it/s, loss=0.744, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  31%|███       | 289/938 [00:20<00:47, 13.80it/s, loss=0.742, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  31%|███       | 290/938 [00:21<00:46, 13.81it/s, loss=0.739, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  31%|███       | 291/938 [00:21<00:46, 13.81it/s, loss=0.741, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  31%|███       | 292/938 [00:21<00:46, 13.81it/s, loss=0.741, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  31%|███       | 292/938 [00:21<00:46, 13.81it/s, loss=0.746, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  31%|███       | 293/938 [00:21<00:46, 13.80it/s, loss=0.745, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  31%|███▏      | 294/938 [00:21<00:46, 13.80it/s, loss=0.753, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  31%|███▏      | 295/938 [00:21<00:46, 13.81it/s, loss=0.751, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  32%|███▏      | 296/938 [00:21<00:46, 13.81it/s, loss=0.751, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  32%|███▏      | 296/938 [00:21<00:46, 13.81it/s, loss=0.75, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  32%|███▏      | 297/938 [00:21<00:46, 13.81it/s, loss=0.746, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  32%|███▏      | 298/938 [00:21<00:46, 13.81it/s, loss=0.751, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  32%|███▏      | 299/938 [00:21<00:46, 13.82it/s, loss=0.749, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  32%|███▏      | 300/938 [00:21<00:46, 13.83it/s, loss=0.749, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  32%|███▏      | 300/938 [00:21<00:46, 13.83it/s, loss=0.753, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  32%|███▏      | 301/938 [00:21<00:46, 13.84it/s, loss=0.754, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  32%|███▏      | 302/938 [00:21<00:45, 13.84it/s, loss=0.755, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  32%|███▏      | 303/938 [00:21<00:45, 13.85it/s, loss=0.739, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  32%|███▏      | 304/938 [00:21<00:45, 13.85it/s, loss=0.739, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  32%|███▏      | 304/938 [00:21<00:45, 13.85it/s, loss=0.74, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  33%|███▎      | 305/938 [00:22<00:45, 13.85it/s, loss=0.743, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  33%|███▎      | 306/938 [00:22<00:45, 13.85it/s, loss=0.738, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  33%|███▎      | 307/938 [00:22<00:45, 13.85it/s, loss=0.742, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  33%|███▎      | 308/938 [00:22<00:45, 13.86it/s, loss=0.742, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  33%|███▎      | 308/938 [00:22<00:45, 13.85it/s, loss=0.734, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  33%|███▎      | 309/938 [00:22<00:45, 13.85it/s, loss=0.74, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  33%|███▎      | 310/938 [00:22<00:45, 13.86it/s, loss=0.743, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  33%|███▎      | 311/938 [00:22<00:45, 13.85it/s, loss=0.744, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  33%|███▎      | 312/938 [00:22<00:45, 13.85it/s, loss=0.744, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  33%|███▎      | 312/938 [00:22<00:45, 13.85it/s, loss=0.736, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  33%|███▎      | 313/938 [00:22<00:45, 13.86it/s, loss=0.733, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  33%|███▎      | 314/938 [00:22<00:45, 13.85it/s, loss=0.721, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  34%|███▎      | 315/938 [00:22<00:44, 13.86it/s, loss=0.726, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  34%|███▎      | 316/938 [00:22<00:44, 13.86it/s, loss=0.726, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  34%|███▎      | 316/938 [00:22<00:44, 13.86it/s, loss=0.738, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  34%|███▍      | 317/938 [00:22<00:44, 13.87it/s, loss=0.746, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  34%|███▍      | 318/938 [00:22<00:44, 13.86it/s, loss=0.75, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  34%|███▍      | 319/938 [00:23<00:44, 13.87it/s, loss=0.752, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  34%|███▍      | 320/938 [00:23<00:44, 13.87it/s, loss=0.752, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  34%|███▍      | 320/938 [00:23<00:44, 13.87it/s, loss=0.742, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  34%|███▍      | 321/938 [00:23<00:44, 13.87it/s, loss=0.746, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  34%|███▍      | 322/938 [00:23<00:44, 13.88it/s, loss=0.744, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  34%|███▍      | 323/938 [00:23<00:44, 13.88it/s, loss=0.744, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  35%|███▍      | 324/938 [00:23<00:44, 13.89it/s, loss=0.744, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  35%|███▍      | 324/938 [00:23<00:44, 13.89it/s, loss=0.749, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  35%|███▍      | 325/938 [00:23<00:44, 13.88it/s, loss=0.745, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  35%|███▍      | 326/938 [00:23<00:44, 13.89it/s, loss=0.742, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  35%|███▍      | 327/938 [00:23<00:43, 13.89it/s, loss=0.751, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  35%|███▍      | 328/938 [00:23<00:43, 13.90it/s, loss=0.751, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  35%|███▍      | 328/938 [00:23<00:43, 13.90it/s, loss=0.753, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  35%|███▌      | 329/938 [00:23<00:43, 13.89it/s, loss=0.74, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  35%|███▌      | 330/938 [00:23<00:43, 13.89it/s, loss=0.744, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  35%|███▌      | 331/938 [00:23<00:43, 13.89it/s, loss=0.744, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  35%|███▌      | 332/938 [00:23<00:43, 13.89it/s, loss=0.744, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  35%|███▌      | 332/938 [00:23<00:43, 13.89it/s, loss=0.744, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  36%|███▌      | 333/938 [00:23<00:43, 13.90it/s, loss=0.741, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  36%|███▌      | 334/938 [00:24<00:43, 13.89it/s, loss=0.738, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  36%|███▌      | 335/938 [00:24<00:43, 13.89it/s, loss=0.731, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  36%|███▌      | 336/938 [00:24<00:43, 13.89it/s, loss=0.731, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  36%|███▌      | 336/938 [00:24<00:43, 13.89it/s, loss=0.716, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  36%|███▌      | 337/938 [00:24<00:43, 13.90it/s, loss=0.71, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  36%|███▌      | 338/938 [00:24<00:43, 13.90it/s, loss=0.712, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  36%|███▌      | 339/938 [00:24<00:43, 13.90it/s, loss=0.709, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  36%|███▌      | 340/938 [00:24<00:43, 13.90it/s, loss=0.709, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  36%|███▌      | 340/938 [00:24<00:43, 13.90it/s, loss=0.712, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  36%|███▋      | 341/938 [00:24<00:42, 13.90it/s, loss=0.708, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  36%|███▋      | 342/938 [00:24<00:42, 13.91it/s, loss=0.706, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  37%|███▋      | 343/938 [00:24<00:42, 13.91it/s, loss=0.701, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  37%|███▋      | 344/938 [00:24<00:42, 13.92it/s, loss=0.701, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  37%|███▋      | 344/938 [00:24<00:42, 13.92it/s, loss=0.698, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  37%|███▋      | 345/938 [00:24<00:42, 13.92it/s, loss=0.708, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  37%|███▋      | 346/938 [00:24<00:42, 13.92it/s, loss=0.713, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  37%|███▋      | 347/938 [00:24<00:42, 13.92it/s, loss=0.699, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  37%|███▋      | 348/938 [00:24<00:42, 13.92it/s, loss=0.699, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  37%|███▋      | 348/938 [00:24<00:42, 13.92it/s, loss=0.696, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  37%|███▋      | 349/938 [00:25<00:42, 13.91it/s, loss=0.705, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  37%|███▋      | 350/938 [00:25<00:42, 13.90it/s, loss=0.7, v_num=9, val_rmse=0.772, train_rmse=1.230]  
Epoch 1:  37%|███▋      | 351/938 [00:25<00:42, 13.91it/s, loss=0.697, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  38%|███▊      | 352/938 [00:25<00:42, 13.91it/s, loss=0.697, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  38%|███▊      | 352/938 [00:25<00:42, 13.91it/s, loss=0.701, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  38%|███▊      | 353/938 [00:25<00:42, 13.91it/s, loss=0.709, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  38%|███▊      | 354/938 [00:25<00:41, 13.92it/s, loss=0.727, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  38%|███▊      | 355/938 [00:25<00:41, 13.91it/s, loss=0.743, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  38%|███▊      | 356/938 [00:25<00:41, 13.92it/s, loss=0.743, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  38%|███▊      | 356/938 [00:25<00:41, 13.92it/s, loss=0.744, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  38%|███▊      | 357/938 [00:25<00:41, 13.91it/s, loss=0.738, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  38%|███▊      | 358/938 [00:25<00:41, 13.91it/s, loss=0.733, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  38%|███▊      | 359/938 [00:25<00:41, 13.91it/s, loss=0.739, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  38%|███▊      | 360/938 [00:25<00:41, 13.91it/s, loss=0.739, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  38%|███▊      | 360/938 [00:25<00:41, 13.91it/s, loss=0.744, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  38%|███▊      | 361/938 [00:25<00:41, 13.91it/s, loss=0.742, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  39%|███▊      | 362/938 [00:26<00:41, 13.91it/s, loss=0.739, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  39%|███▊      | 363/938 [00:26<00:41, 13.91it/s, loss=0.743, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  39%|███▉      | 364/938 [00:26<00:41, 13.91it/s, loss=0.743, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  39%|███▉      | 364/938 [00:26<00:41, 13.91it/s, loss=0.743, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  39%|███▉      | 365/938 [00:26<00:41, 13.92it/s, loss=0.732, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  39%|███▉      | 366/938 [00:26<00:41, 13.92it/s, loss=0.735, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  39%|███▉      | 367/938 [00:26<00:40, 13.94it/s, loss=0.748, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  39%|███▉      | 368/938 [00:26<00:40, 13.94it/s, loss=0.748, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  39%|███▉      | 368/938 [00:26<00:40, 13.94it/s, loss=0.748, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  39%|███▉      | 369/938 [00:26<00:40, 13.94it/s, loss=0.744, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  39%|███▉      | 370/938 [00:26<00:40, 13.94it/s, loss=0.745, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  40%|███▉      | 371/938 [00:26<00:40, 13.94it/s, loss=0.741, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  40%|███▉      | 372/938 [00:26<00:40, 13.95it/s, loss=0.741, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  40%|███▉      | 372/938 [00:26<00:40, 13.95it/s, loss=0.741, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  40%|███▉      | 373/938 [00:26<00:40, 13.95it/s, loss=0.743, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  40%|███▉      | 374/938 [00:26<00:40, 13.94it/s, loss=0.727, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  40%|███▉      | 375/938 [00:26<00:40, 13.95it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  40%|████      | 376/938 [00:26<00:40, 13.95it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  40%|████      | 376/938 [00:26<00:40, 13.95it/s, loss=0.722, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  40%|████      | 377/938 [00:27<00:40, 13.95it/s, loss=0.728, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  40%|████      | 378/938 [00:27<00:40, 13.95it/s, loss=0.737, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  40%|████      | 379/938 [00:27<00:40, 13.95it/s, loss=0.741, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  41%|████      | 380/938 [00:27<00:40, 13.94it/s, loss=0.741, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  41%|████      | 380/938 [00:27<00:40, 13.94it/s, loss=0.754, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  41%|████      | 381/938 [00:27<00:39, 13.95it/s, loss=0.765, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  41%|████      | 382/938 [00:27<00:39, 13.95it/s, loss=0.77, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  41%|████      | 383/938 [00:27<00:39, 13.95it/s, loss=0.767, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  41%|████      | 384/938 [00:27<00:39, 13.95it/s, loss=0.767, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  41%|████      | 384/938 [00:27<00:39, 13.95it/s, loss=0.76, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  41%|████      | 385/938 [00:27<00:39, 13.95it/s, loss=0.76, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  41%|████      | 386/938 [00:27<00:39, 13.96it/s, loss=0.759, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  41%|████▏     | 387/938 [00:27<00:39, 13.96it/s, loss=0.756, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  41%|████▏     | 388/938 [00:27<00:39, 13.96it/s, loss=0.756, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  41%|████▏     | 388/938 [00:27<00:39, 13.96it/s, loss=0.759, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  41%|████▏     | 389/938 [00:27<00:39, 13.96it/s, loss=0.76, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  42%|████▏     | 390/938 [00:27<00:39, 13.96it/s, loss=0.762, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  42%|████▏     | 391/938 [00:28<00:39, 13.96it/s, loss=0.761, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  42%|████▏     | 392/938 [00:28<00:39, 13.96it/s, loss=0.761, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  42%|████▏     | 392/938 [00:28<00:39, 13.96it/s, loss=0.762, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  42%|████▏     | 393/938 [00:28<00:39, 13.96it/s, loss=0.764, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  42%|████▏     | 394/938 [00:28<00:38, 13.96it/s, loss=0.771, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  42%|████▏     | 395/938 [00:28<00:38, 13.96it/s, loss=0.769, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  42%|████▏     | 396/938 [00:28<00:38, 13.96it/s, loss=0.769, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  42%|████▏     | 396/938 [00:28<00:38, 13.96it/s, loss=0.771, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  42%|████▏     | 397/938 [00:28<00:38, 13.96it/s, loss=0.769, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  42%|████▏     | 398/938 [00:28<00:38, 13.97it/s, loss=0.76, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  43%|████▎     | 399/938 [00:28<00:38, 13.97it/s, loss=0.753, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  43%|████▎     | 400/938 [00:28<00:38, 13.98it/s, loss=0.753, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  43%|████▎     | 400/938 [00:28<00:38, 13.98it/s, loss=0.743, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  43%|████▎     | 401/938 [00:28<00:38, 13.98it/s, loss=0.742, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  43%|████▎     | 402/938 [00:28<00:38, 13.99it/s, loss=0.741, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  43%|████▎     | 403/938 [00:28<00:38, 13.98it/s, loss=0.739, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  43%|████▎     | 404/938 [00:28<00:38, 13.99it/s, loss=0.739, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  43%|████▎     | 404/938 [00:28<00:38, 13.99it/s, loss=0.741, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  43%|████▎     | 405/938 [00:28<00:38, 13.99it/s, loss=0.745, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  43%|████▎     | 406/938 [00:29<00:38, 13.99it/s, loss=0.748, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  43%|████▎     | 407/938 [00:29<00:37, 14.00it/s, loss=0.744, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  43%|████▎     | 408/938 [00:29<00:37, 13.99it/s, loss=0.744, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  43%|████▎     | 408/938 [00:29<00:37, 13.99it/s, loss=0.741, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  44%|████▎     | 409/938 [00:29<00:37, 14.00it/s, loss=0.743, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  44%|████▎     | 410/938 [00:29<00:37, 14.00it/s, loss=0.745, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  44%|████▍     | 411/938 [00:29<00:37, 14.00it/s, loss=0.746, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  44%|████▍     | 412/938 [00:29<00:37, 14.00it/s, loss=0.746, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  44%|████▍     | 412/938 [00:29<00:37, 14.00it/s, loss=0.748, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  44%|████▍     | 413/938 [00:29<00:37, 14.00it/s, loss=0.75, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  44%|████▍     | 414/938 [00:29<00:37, 14.00it/s, loss=0.747, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  44%|████▍     | 415/938 [00:29<00:37, 13.99it/s, loss=0.743, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  44%|████▍     | 416/938 [00:29<00:37, 13.99it/s, loss=0.743, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  44%|████▍     | 416/938 [00:29<00:37, 13.98it/s, loss=0.744, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  44%|████▍     | 417/938 [00:29<00:37, 13.99it/s, loss=0.738, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  45%|████▍     | 418/938 [00:29<00:37, 13.99it/s, loss=0.74, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  45%|████▍     | 419/938 [00:29<00:37, 13.98it/s, loss=0.737, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  45%|████▍     | 420/938 [00:30<00:37, 13.99it/s, loss=0.737, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  45%|████▍     | 420/938 [00:30<00:37, 13.99it/s, loss=0.733, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  45%|████▍     | 421/938 [00:30<00:36, 13.99it/s, loss=0.716, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  45%|████▍     | 422/938 [00:30<00:36, 14.00it/s, loss=0.725, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  45%|████▌     | 423/938 [00:30<00:36, 14.00it/s, loss=0.733, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  45%|████▌     | 424/938 [00:30<00:36, 14.00it/s, loss=0.733, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  45%|████▌     | 424/938 [00:30<00:36, 14.00it/s, loss=0.743, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  45%|████▌     | 425/938 [00:30<00:36, 14.00it/s, loss=0.737, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  45%|████▌     | 426/938 [00:30<00:36, 14.00it/s, loss=0.735, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  46%|████▌     | 427/938 [00:30<00:36, 14.00it/s, loss=0.731, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  46%|████▌     | 428/938 [00:30<00:36, 13.98it/s, loss=0.731, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  46%|████▌     | 428/938 [00:30<00:36, 13.98it/s, loss=0.724, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  46%|████▌     | 429/938 [00:30<00:36, 13.98it/s, loss=0.719, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  46%|████▌     | 430/938 [00:30<00:36, 13.96it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  46%|████▌     | 431/938 [00:30<00:36, 13.96it/s, loss=0.716, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  46%|████▌     | 432/938 [00:30<00:36, 13.96it/s, loss=0.716, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  46%|████▌     | 432/938 [00:30<00:36, 13.96it/s, loss=0.71, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  46%|████▌     | 433/938 [00:31<00:36, 13.96it/s, loss=0.706, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  46%|████▋     | 434/938 [00:31<00:36, 13.96it/s, loss=0.707, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  46%|████▋     | 435/938 [00:31<00:36, 13.97it/s, loss=0.708, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  46%|████▋     | 436/938 [00:31<00:35, 13.97it/s, loss=0.708, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  46%|████▋     | 436/938 [00:31<00:35, 13.97it/s, loss=0.706, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  47%|████▋     | 437/938 [00:31<00:35, 13.97it/s, loss=0.716, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  47%|████▋     | 438/938 [00:31<00:35, 13.97it/s, loss=0.713, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  47%|████▋     | 439/938 [00:31<00:35, 13.96it/s, loss=0.712, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  47%|████▋     | 440/938 [00:31<00:35, 13.96it/s, loss=0.712, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  47%|████▋     | 440/938 [00:31<00:35, 13.96it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  47%|████▋     | 441/938 [00:31<00:35, 13.96it/s, loss=0.721, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  47%|████▋     | 442/938 [00:31<00:35, 13.96it/s, loss=0.708, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  47%|████▋     | 443/938 [00:31<00:35, 13.96it/s, loss=0.705, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  47%|████▋     | 444/938 [00:31<00:35, 13.96it/s, loss=0.705, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  47%|████▋     | 444/938 [00:31<00:35, 13.96it/s, loss=0.697, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  47%|████▋     | 445/938 [00:31<00:35, 13.96it/s, loss=0.695, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  48%|████▊     | 446/938 [00:31<00:35, 13.97it/s, loss=0.694, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  48%|████▊     | 447/938 [00:31<00:35, 13.97it/s, loss=0.691, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  48%|████▊     | 448/938 [00:32<00:35, 13.97it/s, loss=0.691, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  48%|████▊     | 448/938 [00:32<00:35, 13.97it/s, loss=0.698, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  48%|████▊     | 449/938 [00:32<00:34, 13.98it/s, loss=0.71, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  48%|████▊     | 450/938 [00:32<00:34, 13.97it/s, loss=0.708, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  48%|████▊     | 451/938 [00:32<00:34, 13.98it/s, loss=0.716, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  48%|████▊     | 452/938 [00:32<00:34, 13.97it/s, loss=0.716, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  48%|████▊     | 452/938 [00:32<00:34, 13.97it/s, loss=0.72, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  48%|████▊     | 453/938 [00:32<00:34, 13.97it/s, loss=0.723, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  48%|████▊     | 454/938 [00:32<00:34, 13.98it/s, loss=0.73, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  49%|████▊     | 455/938 [00:32<00:34, 13.97it/s, loss=0.734, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  49%|████▊     | 456/938 [00:32<00:34, 13.96it/s, loss=0.734, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  49%|████▊     | 456/938 [00:32<00:34, 13.96it/s, loss=0.736, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  49%|████▊     | 457/938 [00:32<00:34, 13.96it/s, loss=0.721, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  49%|████▉     | 458/938 [00:32<00:34, 13.96it/s, loss=0.72, v_num=9, val_rmse=0.772, train_rmse=1.230] 
Epoch 1:  49%|████▉     | 459/938 [00:32<00:34, 13.97it/s, loss=0.72, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  49%|████▉     | 460/938 [00:32<00:34, 13.97it/s, loss=0.72, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  49%|████▉     | 460/938 [00:32<00:34, 13.97it/s, loss=0.723, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  49%|████▉     | 461/938 [00:33<00:34, 13.96it/s, loss=0.735, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  49%|████▉     | 462/938 [00:33<00:34, 13.97it/s, loss=0.736, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  49%|████▉     | 463/938 [00:33<00:34, 13.97it/s, loss=0.735, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  49%|████▉     | 464/938 [00:33<00:33, 13.97it/s, loss=0.735, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  49%|████▉     | 464/938 [00:33<00:33, 13.97it/s, loss=0.735, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  50%|████▉     | 465/938 [00:33<00:33, 13.97it/s, loss=0.737, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  50%|████▉     | 466/938 [00:33<00:33, 13.98it/s, loss=0.732, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  50%|████▉     | 467/938 [00:33<00:33, 13.98it/s, loss=0.739, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  50%|████▉     | 468/938 [00:33<00:33, 13.98it/s, loss=0.739, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  50%|████▉     | 468/938 [00:33<00:33, 13.98it/s, loss=0.734, v_num=9, val_rmse=0.772, train_rmse=1.230]
Epoch 1:  50%|█████     | 469/938 [00:33<00:33, 14.00it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]
Epoch 1:  50%|█████     | 472/938 [00:33<00:33, 14.05it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:   1%|          | 3/469 [00:00<00:19, 23.32it/s]

Validating:   1%|▏         | 6/469 [00:00<00:17, 26.00it/s]
Epoch 1:  51%|█████     | 476/938 [00:33<00:32, 14.11it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:   2%|▏         | 9/469 [00:00<00:18, 25.15it/s]
Epoch 1:  51%|█████     | 480/938 [00:33<00:32, 14.16it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:   3%|▎         | 12/469 [00:00<00:18, 25.13it/s]
Epoch 1:  52%|█████▏    | 484/938 [00:34<00:31, 14.21it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:   3%|▎         | 15/469 [00:00<00:17, 25.37it/s]

Validating:   4%|▍         | 18/469 [00:00<00:18, 24.71it/s]
Epoch 1:  52%|█████▏    | 488/938 [00:34<00:31, 14.26it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:   4%|▍         | 21/469 [00:00<00:17, 25.44it/s]
Epoch 1:  52%|█████▏    | 492/938 [00:34<00:31, 14.31it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:   5%|▌         | 24/469 [00:00<00:16, 26.24it/s]
Epoch 1:  53%|█████▎    | 496/938 [00:34<00:30, 14.36it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:   6%|▌         | 27/469 [00:01<00:17, 25.37it/s]

Validating:   6%|▋         | 30/469 [00:01<00:17, 25.56it/s]
Epoch 1:  53%|█████▎    | 500/938 [00:34<00:30, 14.41it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:   7%|▋         | 33/469 [00:01<00:17, 25.06it/s]
Epoch 1:  54%|█████▎    | 504/938 [00:34<00:30, 14.46it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:   8%|▊         | 36/469 [00:01<00:16, 25.58it/s]
Epoch 1:  54%|█████▍    | 508/938 [00:34<00:29, 14.52it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:   8%|▊         | 39/469 [00:01<00:16, 26.06it/s]

Validating:   9%|▉         | 42/469 [00:01<00:17, 25.12it/s]
Epoch 1:  55%|█████▍    | 512/938 [00:35<00:29, 14.56it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  10%|▉         | 45/469 [00:01<00:16, 25.62it/s]
Epoch 1:  55%|█████▌    | 516/938 [00:35<00:28, 14.61it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  10%|█         | 48/469 [00:01<00:16, 25.67it/s]
Epoch 1:  55%|█████▌    | 520/938 [00:35<00:28, 14.66it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  11%|█         | 51/469 [00:02<00:16, 25.01it/s]

Validating:  12%|█▏        | 54/469 [00:02<00:16, 24.90it/s]
Epoch 1:  56%|█████▌    | 524/938 [00:35<00:28, 14.70it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  12%|█▏        | 57/469 [00:02<00:16, 25.32it/s]
Epoch 1:  56%|█████▋    | 528/938 [00:35<00:27, 14.75it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  13%|█▎        | 60/469 [00:02<00:16, 25.55it/s]
Epoch 1:  57%|█████▋    | 532/938 [00:35<00:27, 14.80it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  13%|█▎        | 63/469 [00:02<00:16, 25.08it/s]

Validating:  14%|█▍        | 66/469 [00:02<00:15, 25.33it/s]
Epoch 1:  57%|█████▋    | 536/938 [00:36<00:27, 14.84it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  15%|█▍        | 69/469 [00:02<00:15, 26.23it/s]
Epoch 1:  58%|█████▊    | 540/938 [00:36<00:26, 14.89it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  15%|█▌        | 72/469 [00:02<00:16, 24.30it/s]
Epoch 1:  58%|█████▊    | 544/938 [00:36<00:26, 14.93it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  16%|█▌        | 75/469 [00:02<00:15, 24.91it/s]

Validating:  17%|█▋        | 78/469 [00:03<00:15, 24.85it/s]
Epoch 1:  58%|█████▊    | 548/938 [00:36<00:26, 14.97it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  17%|█▋        | 81/469 [00:03<00:15, 24.77it/s]
Epoch 1:  59%|█████▉    | 552/938 [00:36<00:25, 15.02it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  18%|█▊        | 84/469 [00:03<00:14, 25.79it/s]
Epoch 1:  59%|█████▉    | 556/938 [00:36<00:25, 15.07it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  19%|█▊        | 87/469 [00:03<00:14, 25.94it/s]

Validating:  19%|█▉        | 90/469 [00:03<00:14, 26.88it/s]
Epoch 1:  60%|█████▉    | 560/938 [00:37<00:25, 15.12it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  20%|█▉        | 93/469 [00:03<00:14, 26.18it/s]
Epoch 1:  60%|██████    | 564/938 [00:37<00:24, 15.16it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  20%|██        | 96/469 [00:03<00:14, 26.37it/s]
Epoch 1:  61%|██████    | 568/938 [00:37<00:24, 15.21it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  21%|██        | 99/469 [00:03<00:14, 25.74it/s]

Validating:  22%|██▏       | 102/469 [00:03<00:13, 26.39it/s]
Epoch 1:  61%|██████    | 572/938 [00:37<00:23, 15.25it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  22%|██▏       | 105/469 [00:04<00:14, 25.53it/s]
Epoch 1:  61%|██████▏   | 576/938 [00:37<00:23, 15.29it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  23%|██▎       | 108/469 [00:04<00:14, 25.68it/s]
Epoch 1:  62%|██████▏   | 580/938 [00:37<00:23, 15.34it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  24%|██▎       | 111/469 [00:04<00:13, 25.89it/s]

Validating:  24%|██▍       | 114/469 [00:04<00:13, 25.37it/s]
Epoch 1:  62%|██████▏   | 584/938 [00:37<00:23, 15.38it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  25%|██▍       | 117/469 [00:04<00:14, 24.63it/s]
Epoch 1:  63%|██████▎   | 588/938 [00:38<00:22, 15.41it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  26%|██▌       | 120/469 [00:04<00:13, 25.10it/s]
Epoch 1:  63%|██████▎   | 592/938 [00:38<00:22, 15.46it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  26%|██▌       | 123/469 [00:04<00:13, 24.77it/s]

Validating:  27%|██▋       | 126/469 [00:04<00:13, 24.54it/s]
Epoch 1:  64%|██████▎   | 596/938 [00:38<00:22, 15.49it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  28%|██▊       | 130/469 [00:05<00:13, 25.78it/s]
Epoch 1:  64%|██████▍   | 600/938 [00:38<00:21, 15.54it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  28%|██▊       | 133/469 [00:05<00:13, 25.84it/s]
Epoch 1:  64%|██████▍   | 604/938 [00:38<00:21, 15.58it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  29%|██▉       | 136/469 [00:05<00:12, 26.45it/s]
Epoch 1:  65%|██████▍   | 608/938 [00:38<00:21, 15.63it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  30%|██▉       | 139/469 [00:05<00:12, 26.75it/s]

Validating:  30%|███       | 142/469 [00:05<00:12, 26.83it/s]
Epoch 1:  65%|██████▌   | 612/938 [00:39<00:20, 15.67it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  31%|███       | 145/469 [00:05<00:12, 26.84it/s]
Epoch 1:  66%|██████▌   | 616/938 [00:39<00:20, 15.71it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  32%|███▏      | 148/469 [00:05<00:12, 24.87it/s]
Epoch 1:  66%|██████▌   | 620/938 [00:39<00:20, 15.74it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  32%|███▏      | 151/469 [00:05<00:13, 24.01it/s]

Validating:  33%|███▎      | 154/469 [00:06<00:12, 24.75it/s]
Epoch 1:  67%|██████▋   | 624/938 [00:39<00:19, 15.77it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  33%|███▎      | 157/469 [00:06<00:12, 25.35it/s]
Epoch 1:  67%|██████▋   | 628/938 [00:39<00:19, 15.81it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  34%|███▍      | 160/469 [00:06<00:12, 25.68it/s]
Epoch 1:  67%|██████▋   | 632/938 [00:39<00:19, 15.86it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  35%|███▍      | 163/469 [00:06<00:11, 26.39it/s]

Validating:  35%|███▌      | 166/469 [00:06<00:11, 26.84it/s]
Epoch 1:  68%|██████▊   | 636/938 [00:39<00:18, 15.90it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  36%|███▌      | 169/469 [00:06<00:11, 26.76it/s]
Epoch 1:  68%|██████▊   | 640/938 [00:40<00:18, 15.94it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  37%|███▋      | 172/469 [00:06<00:11, 26.85it/s]
Epoch 1:  69%|██████▊   | 644/938 [00:40<00:18, 15.98it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  37%|███▋      | 175/469 [00:06<00:10, 26.77it/s]

Validating:  38%|███▊      | 178/469 [00:06<00:11, 26.34it/s]
Epoch 1:  69%|██████▉   | 648/938 [00:40<00:18, 16.02it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  39%|███▊      | 181/469 [00:07<00:10, 26.46it/s]
Epoch 1:  70%|██████▉   | 652/938 [00:40<00:17, 16.06it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  39%|███▉      | 184/469 [00:07<00:10, 26.94it/s]
Epoch 1:  70%|██████▉   | 656/938 [00:40<00:17, 16.10it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  40%|███▉      | 187/469 [00:07<00:10, 26.49it/s]

Validating:  41%|████      | 190/469 [00:07<00:10, 26.74it/s]
Epoch 1:  70%|███████   | 660/938 [00:40<00:17, 16.14it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  41%|████      | 193/469 [00:07<00:10, 26.55it/s]
Epoch 1:  71%|███████   | 664/938 [00:41<00:16, 16.17it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  42%|████▏     | 196/469 [00:07<00:10, 26.03it/s]
Epoch 1:  71%|███████   | 668/938 [00:41<00:16, 16.21it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  42%|████▏     | 199/469 [00:07<00:10, 26.46it/s]

Validating:  43%|████▎     | 202/469 [00:07<00:09, 26.93it/s]
Epoch 1:  72%|███████▏  | 672/938 [00:41<00:16, 16.25it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  44%|████▎     | 205/469 [00:07<00:09, 27.00it/s]
Epoch 1:  72%|███████▏  | 676/938 [00:41<00:16, 16.29it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  44%|████▍     | 208/469 [00:08<00:09, 27.16it/s]
Epoch 1:  72%|███████▏  | 680/938 [00:41<00:15, 16.33it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  45%|████▍     | 211/469 [00:08<00:09, 27.21it/s]

Validating:  46%|████▌     | 214/469 [00:08<00:09, 26.49it/s]
Epoch 1:  73%|███████▎  | 684/938 [00:41<00:15, 16.36it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  46%|████▋     | 217/469 [00:08<00:09, 26.00it/s]
Epoch 1:  73%|███████▎  | 688/938 [00:41<00:15, 16.40it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  47%|████▋     | 220/469 [00:08<00:09, 26.18it/s]
Epoch 1:  74%|███████▍  | 692/938 [00:42<00:14, 16.43it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  48%|████▊     | 223/469 [00:08<00:09, 25.99it/s]

Validating:  48%|████▊     | 226/469 [00:08<00:09, 25.98it/s]
Epoch 1:  74%|███████▍  | 696/938 [00:42<00:14, 16.47it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  49%|████▉     | 229/469 [00:08<00:09, 25.80it/s]
Epoch 1:  75%|███████▍  | 700/938 [00:42<00:14, 16.50it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  49%|████▉     | 232/469 [00:08<00:09, 25.59it/s]
Epoch 1:  75%|███████▌  | 704/938 [00:42<00:14, 16.53it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  50%|█████     | 235/469 [00:09<00:09, 24.51it/s]

Validating:  51%|█████     | 238/469 [00:09<00:09, 23.63it/s]
Epoch 1:  75%|███████▌  | 708/938 [00:42<00:13, 16.55it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  51%|█████▏    | 241/469 [00:09<00:09, 23.84it/s]
Epoch 1:  76%|███████▌  | 712/938 [00:42<00:13, 16.58it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  52%|█████▏    | 244/469 [00:09<00:09, 24.09it/s]
Epoch 1:  76%|███████▋  | 716/938 [00:43<00:13, 16.61it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  53%|█████▎    | 247/469 [00:09<00:08, 24.71it/s]

Validating:  53%|█████▎    | 250/469 [00:09<00:09, 23.15it/s]
Epoch 1:  77%|███████▋  | 720/938 [00:43<00:13, 16.63it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  54%|█████▍    | 253/469 [00:09<00:09, 23.85it/s]
Epoch 1:  77%|███████▋  | 724/938 [00:43<00:12, 16.67it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  55%|█████▍    | 256/469 [00:10<00:08, 24.60it/s]
Epoch 1:  78%|███████▊  | 728/938 [00:43<00:12, 16.70it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  55%|█████▌    | 259/469 [00:10<00:08, 24.71it/s]

Validating:  56%|█████▌    | 262/469 [00:10<00:08, 24.98it/s]
Epoch 1:  78%|███████▊  | 732/938 [00:43<00:12, 16.73it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  57%|█████▋    | 265/469 [00:10<00:08, 25.35it/s]
Epoch 1:  78%|███████▊  | 736/938 [00:43<00:12, 16.76it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  57%|█████▋    | 268/469 [00:10<00:08, 25.01it/s]
Epoch 1:  79%|███████▉  | 740/938 [00:44<00:11, 16.80it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  58%|█████▊    | 271/469 [00:10<00:07, 25.53it/s]

Validating:  58%|█████▊    | 274/469 [00:10<00:07, 25.85it/s]
Epoch 1:  79%|███████▉  | 744/938 [00:44<00:11, 16.83it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  59%|█████▉    | 277/469 [00:10<00:07, 26.44it/s]
Epoch 1:  80%|███████▉  | 748/938 [00:44<00:11, 16.86it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  60%|█████▉    | 280/469 [00:10<00:07, 26.62it/s]
Epoch 1:  80%|████████  | 752/938 [00:44<00:11, 16.90it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  60%|██████    | 283/469 [00:11<00:07, 26.18it/s]

Validating:  61%|██████    | 286/469 [00:11<00:06, 26.76it/s]
Epoch 1:  81%|████████  | 756/938 [00:44<00:10, 16.93it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  62%|██████▏   | 290/469 [00:11<00:06, 27.96it/s]
Epoch 1:  81%|████████  | 760/938 [00:44<00:10, 16.97it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  62%|██████▏   | 293/469 [00:11<00:06, 27.79it/s]
Epoch 1:  81%|████████▏ | 764/938 [00:44<00:10, 17.00it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  63%|██████▎   | 296/469 [00:11<00:06, 27.32it/s]
Epoch 1:  82%|████████▏ | 768/938 [00:45<00:09, 17.03it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  64%|██████▍   | 299/469 [00:11<00:06, 27.68it/s]

Validating:  64%|██████▍   | 302/469 [00:11<00:06, 27.01it/s]
Epoch 1:  82%|████████▏ | 772/938 [00:45<00:09, 17.07it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  65%|██████▌   | 305/469 [00:11<00:05, 27.69it/s]
Epoch 1:  83%|████████▎ | 776/938 [00:45<00:09, 17.10it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  66%|██████▌   | 308/469 [00:11<00:05, 27.34it/s]
Epoch 1:  83%|████████▎ | 780/938 [00:45<00:09, 17.14it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  66%|██████▋   | 311/469 [00:12<00:05, 27.43it/s]

Validating:  67%|██████▋   | 314/469 [00:12<00:05, 27.27it/s]
Epoch 1:  84%|████████▎ | 784/938 [00:45<00:08, 17.17it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  68%|██████▊   | 317/469 [00:12<00:06, 24.63it/s]
Epoch 1:  84%|████████▍ | 788/938 [00:45<00:08, 17.18it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  68%|██████▊   | 320/469 [00:12<00:05, 24.98it/s]
Epoch 1:  84%|████████▍ | 792/938 [00:46<00:08, 17.21it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  69%|██████▉   | 323/469 [00:12<00:05, 24.74it/s]

Validating:  70%|██████▉   | 326/469 [00:12<00:05, 24.84it/s]
Epoch 1:  85%|████████▍ | 796/938 [00:46<00:08, 17.24it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  70%|███████   | 329/469 [00:12<00:05, 24.38it/s]
Epoch 1:  85%|████████▌ | 800/938 [00:46<00:07, 17.26it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  71%|███████   | 332/469 [00:12<00:05, 24.78it/s]
Epoch 1:  86%|████████▌ | 804/938 [00:46<00:07, 17.29it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  71%|███████▏  | 335/469 [00:13<00:05, 24.94it/s]

Validating:  72%|███████▏  | 338/469 [00:13<00:05, 25.24it/s]
Epoch 1:  86%|████████▌ | 808/938 [00:46<00:07, 17.32it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  73%|███████▎  | 341/469 [00:13<00:05, 24.84it/s]
Epoch 1:  87%|████████▋ | 812/938 [00:46<00:07, 17.34it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  73%|███████▎  | 344/469 [00:13<00:05, 24.36it/s]
Epoch 1:  87%|████████▋ | 816/938 [00:46<00:07, 17.37it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  74%|███████▍  | 347/469 [00:13<00:04, 24.60it/s]

Validating:  75%|███████▍  | 350/469 [00:13<00:04, 25.41it/s]
Epoch 1:  87%|████████▋ | 820/938 [00:47<00:06, 17.40it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  75%|███████▌  | 353/469 [00:13<00:04, 25.67it/s]
Epoch 1:  88%|████████▊ | 824/938 [00:47<00:06, 17.42it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  76%|███████▌  | 356/469 [00:13<00:04, 25.00it/s]
Epoch 1:  88%|████████▊ | 828/938 [00:47<00:06, 17.45it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  77%|███████▋  | 359/469 [00:13<00:04, 25.10it/s]

Validating:  77%|███████▋  | 362/469 [00:14<00:04, 25.70it/s]
Epoch 1:  89%|████████▊ | 832/938 [00:47<00:06, 17.48it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  78%|███████▊  | 365/469 [00:14<00:04, 25.65it/s]
Epoch 1:  89%|████████▉ | 836/938 [00:47<00:05, 17.50it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  78%|███████▊  | 368/469 [00:14<00:03, 25.59it/s]
Epoch 1:  90%|████████▉ | 840/938 [00:47<00:05, 17.53it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  79%|███████▉  | 371/469 [00:14<00:03, 26.34it/s]

Validating:  80%|███████▉  | 374/469 [00:14<00:03, 26.19it/s]
Epoch 1:  90%|████████▉ | 844/938 [00:48<00:05, 17.56it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  80%|████████  | 377/469 [00:14<00:03, 26.03it/s]
Epoch 1:  90%|█████████ | 848/938 [00:48<00:05, 17.59it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  81%|████████  | 380/469 [00:14<00:03, 26.83it/s]
Epoch 1:  91%|█████████ | 852/938 [00:48<00:04, 17.61it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  82%|████████▏ | 383/469 [00:14<00:03, 26.05it/s]

Validating:  82%|████████▏ | 386/469 [00:15<00:03, 26.34it/s]
Epoch 1:  91%|█████████▏| 856/938 [00:48<00:04, 17.64it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  83%|████████▎ | 389/469 [00:15<00:03, 25.92it/s]
Epoch 1:  92%|█████████▏| 860/938 [00:48<00:04, 17.66it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  84%|████████▎ | 392/469 [00:15<00:02, 26.02it/s]
Epoch 1:  92%|█████████▏| 864/938 [00:48<00:04, 17.69it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  84%|████████▍ | 395/469 [00:15<00:02, 26.35it/s]

Validating:  85%|████████▍ | 398/469 [00:15<00:02, 26.18it/s]
Epoch 1:  93%|█████████▎| 868/938 [00:48<00:03, 17.72it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  86%|████████▌ | 401/469 [00:15<00:02, 26.85it/s]
Epoch 1:  93%|█████████▎| 872/938 [00:49<00:03, 17.75it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  86%|████████▌ | 404/469 [00:15<00:02, 26.71it/s]
Epoch 1:  93%|█████████▎| 876/938 [00:49<00:03, 17.77it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  87%|████████▋ | 407/469 [00:15<00:02, 26.23it/s]

Validating:  87%|████████▋ | 410/469 [00:15<00:02, 25.14it/s]
Epoch 1:  94%|█████████▍| 880/938 [00:49<00:03, 17.79it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  88%|████████▊ | 413/469 [00:16<00:02, 26.03it/s]
Epoch 1:  94%|█████████▍| 884/938 [00:49<00:03, 17.82it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  89%|████████▊ | 416/469 [00:16<00:02, 26.28it/s]
Epoch 1:  95%|█████████▍| 888/938 [00:49<00:02, 17.85it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  89%|████████▉ | 419/469 [00:16<00:01, 25.99it/s]

Validating:  90%|████████▉ | 422/469 [00:16<00:01, 26.05it/s]
Epoch 1:  95%|█████████▌| 892/938 [00:49<00:02, 17.87it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  91%|█████████ | 425/469 [00:16<00:01, 25.64it/s]
Epoch 1:  96%|█████████▌| 896/938 [00:50<00:02, 17.90it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  91%|█████████▏| 428/469 [00:16<00:01, 25.85it/s]
Epoch 1:  96%|█████████▌| 900/938 [00:50<00:02, 17.92it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  92%|█████████▏| 431/469 [00:16<00:01, 26.43it/s]

Validating:  93%|█████████▎| 434/469 [00:16<00:01, 26.49it/s]
Epoch 1:  96%|█████████▋| 904/938 [00:50<00:01, 17.95it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  93%|█████████▎| 437/469 [00:16<00:01, 27.04it/s]
Epoch 1:  97%|█████████▋| 908/938 [00:50<00:01, 17.98it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  94%|█████████▍| 440/469 [00:17<00:01, 26.57it/s]
Epoch 1:  97%|█████████▋| 912/938 [00:50<00:01, 18.00it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  94%|█████████▍| 443/469 [00:17<00:01, 25.02it/s]

Validating:  95%|█████████▌| 446/469 [00:17<00:00, 25.87it/s]
Epoch 1:  98%|█████████▊| 916/938 [00:50<00:01, 18.02it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  96%|█████████▌| 449/469 [00:17<00:00, 25.48it/s]
Epoch 1:  98%|█████████▊| 920/938 [00:50<00:00, 18.05it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  96%|█████████▋| 452/469 [00:17<00:00, 26.44it/s]
Epoch 1:  99%|█████████▊| 924/938 [00:51<00:00, 18.07it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  97%|█████████▋| 455/469 [00:17<00:00, 26.26it/s]

Validating:  98%|█████████▊| 458/469 [00:17<00:00, 26.90it/s]
Epoch 1:  99%|█████████▉| 928/938 [00:51<00:00, 18.10it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  98%|█████████▊| 461/469 [00:17<00:00, 26.31it/s]
Epoch 1:  99%|█████████▉| 932/938 [00:51<00:00, 18.12it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating:  99%|█████████▉| 464/469 [00:17<00:00, 26.32it/s]
Epoch 1: 100%|█████████▉| 936/938 [00:51<00:00, 18.15it/s, loss=0.718, v_num=9, val_rmse=0.772, train_rmse=1.230]

Validating: 100%|█████████▉| 467/469 [00:18<00:00, 26.39it/s]
Epoch 1: 100%|██████████| 938/938 [00:51<00:00, 18.15it/s, loss=0.718, v_num=9, val_rmse=0.568, train_rmse=1.230]

                                                             
Epoch 1: 100%|██████████| 938/938 [00:51<00:00, 18.14it/s, loss=0.718, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 1:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.718, v_num=9, val_rmse=0.568, train_rmse=0.764]          
Epoch 2:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.718, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   0%|          | 1/938 [00:00<01:20, 11.65it/s, loss=0.722, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   0%|          | 2/938 [00:00<01:14, 12.57it/s, loss=0.717, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   0%|          | 3/938 [00:00<01:10, 13.31it/s, loss=0.711, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   0%|          | 4/938 [00:00<01:04, 14.56it/s, loss=0.711, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   0%|          | 4/938 [00:00<01:04, 14.53it/s, loss=0.699, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   1%|          | 5/938 [00:00<01:02, 14.96it/s, loss=0.684, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   1%|          | 6/938 [00:00<01:02, 14.86it/s, loss=0.68, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:   1%|          | 7/938 [00:00<01:02, 14.85it/s, loss=0.677, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   1%|          | 8/938 [00:00<01:02, 14.88it/s, loss=0.677, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   1%|          | 8/938 [00:00<01:02, 14.87it/s, loss=0.686, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   1%|          | 9/938 [00:00<01:03, 14.73it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   1%|          | 10/938 [00:00<01:02, 14.84it/s, loss=0.694, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   1%|          | 11/938 [00:00<01:04, 14.33it/s, loss=0.68, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:   1%|▏         | 12/938 [00:00<01:05, 14.15it/s, loss=0.68, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   1%|▏         | 12/938 [00:00<01:05, 14.14it/s, loss=0.665, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   1%|▏         | 13/938 [00:00<01:04, 14.37it/s, loss=0.674, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   1%|▏         | 14/938 [00:00<01:04, 14.42it/s, loss=0.685, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   2%|▏         | 15/938 [00:01<01:04, 14.37it/s, loss=0.685, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   2%|▏         | 16/938 [00:01<01:03, 14.56it/s, loss=0.685, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   2%|▏         | 16/938 [00:01<01:03, 14.56it/s, loss=0.685, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   2%|▏         | 17/938 [00:01<01:02, 14.70it/s, loss=0.686, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   2%|▏         | 18/938 [00:01<01:03, 14.57it/s, loss=0.681, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   2%|▏         | 19/938 [00:01<01:02, 14.66it/s, loss=0.686, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   2%|▏         | 20/938 [00:01<01:02, 14.61it/s, loss=0.686, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   2%|▏         | 20/938 [00:01<01:02, 14.60it/s, loss=0.696, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   2%|▏         | 21/938 [00:01<01:02, 14.71it/s, loss=0.695, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   2%|▏         | 22/938 [00:01<01:02, 14.76it/s, loss=0.698, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   2%|▏         | 23/938 [00:01<01:02, 14.73it/s, loss=0.703, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   3%|▎         | 24/938 [00:01<01:01, 14.74it/s, loss=0.703, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   3%|▎         | 24/938 [00:01<01:02, 14.74it/s, loss=0.706, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   3%|▎         | 25/938 [00:01<01:01, 14.80it/s, loss=0.719, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   3%|▎         | 26/938 [00:01<01:01, 14.86it/s, loss=0.72, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:   3%|▎         | 27/938 [00:01<01:01, 14.79it/s, loss=0.722, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   3%|▎         | 28/938 [00:01<01:01, 14.88it/s, loss=0.722, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   3%|▎         | 28/938 [00:01<01:01, 14.88it/s, loss=0.723, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   3%|▎         | 29/938 [00:01<01:00, 14.91it/s, loss=0.721, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   3%|▎         | 30/938 [00:02<01:00, 14.91it/s, loss=0.716, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   3%|▎         | 31/938 [00:02<01:01, 14.85it/s, loss=0.72, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:   3%|▎         | 32/938 [00:02<01:01, 14.72it/s, loss=0.72, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   3%|▎         | 32/938 [00:02<01:01, 14.72it/s, loss=0.734, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   4%|▎         | 33/938 [00:02<01:01, 14.67it/s, loss=0.723, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   4%|▎         | 34/938 [00:02<01:01, 14.69it/s, loss=0.718, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   4%|▎         | 35/938 [00:02<01:01, 14.57it/s, loss=0.72, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:   4%|▍         | 36/938 [00:02<01:01, 14.64it/s, loss=0.72, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   4%|▍         | 36/938 [00:02<01:01, 14.64it/s, loss=0.728, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   4%|▍         | 37/938 [00:02<01:01, 14.66it/s, loss=0.732, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   4%|▍         | 38/938 [00:02<01:01, 14.56it/s, loss=0.744, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   4%|▍         | 39/938 [00:02<01:02, 14.40it/s, loss=0.742, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   4%|▍         | 40/938 [00:02<01:02, 14.48it/s, loss=0.742, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   4%|▍         | 40/938 [00:02<01:02, 14.48it/s, loss=0.737, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   4%|▍         | 41/938 [00:02<01:02, 14.45it/s, loss=0.727, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   4%|▍         | 42/938 [00:02<01:01, 14.52it/s, loss=0.72, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:   5%|▍         | 43/938 [00:02<01:01, 14.52it/s, loss=0.711, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   5%|▍         | 44/938 [00:03<01:01, 14.57it/s, loss=0.711, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   5%|▍         | 44/938 [00:03<01:01, 14.56it/s, loss=0.716, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   5%|▍         | 45/938 [00:03<01:01, 14.57it/s, loss=0.707, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   5%|▍         | 46/938 [00:03<01:01, 14.60it/s, loss=0.714, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   5%|▌         | 47/938 [00:03<01:01, 14.59it/s, loss=0.711, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   5%|▌         | 48/938 [00:03<01:01, 14.59it/s, loss=0.711, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   5%|▌         | 48/938 [00:03<01:01, 14.59it/s, loss=0.711, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   5%|▌         | 49/938 [00:03<01:00, 14.62it/s, loss=0.711, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   5%|▌         | 50/938 [00:03<01:00, 14.65it/s, loss=0.713, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   5%|▌         | 51/938 [00:03<01:01, 14.51it/s, loss=0.715, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   6%|▌         | 52/938 [00:03<01:01, 14.51it/s, loss=0.715, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   6%|▌         | 52/938 [00:03<01:01, 14.50it/s, loss=0.705, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   6%|▌         | 53/938 [00:03<01:00, 14.54it/s, loss=0.702, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   6%|▌         | 54/938 [00:03<01:00, 14.52it/s, loss=0.7, v_num=9, val_rmse=0.568, train_rmse=0.764]  
Epoch 2:   6%|▌         | 55/938 [00:03<01:00, 14.52it/s, loss=0.696, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   6%|▌         | 56/938 [00:03<01:00, 14.54it/s, loss=0.696, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   6%|▌         | 56/938 [00:03<01:00, 14.54it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   6%|▌         | 57/938 [00:03<01:00, 14.49it/s, loss=0.683, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   6%|▌         | 58/938 [00:04<01:00, 14.48it/s, loss=0.68, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:   6%|▋         | 59/938 [00:04<01:00, 14.42it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   6%|▋         | 60/938 [00:04<01:00, 14.43it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   6%|▋         | 60/938 [00:04<01:00, 14.43it/s, loss=0.693, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   7%|▋         | 61/938 [00:04<01:00, 14.40it/s, loss=0.703, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   7%|▋         | 62/938 [00:04<01:00, 14.38it/s, loss=0.703, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   7%|▋         | 63/938 [00:04<01:00, 14.38it/s, loss=0.706, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   7%|▋         | 64/938 [00:04<01:00, 14.39it/s, loss=0.706, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   7%|▋         | 64/938 [00:04<01:00, 14.39it/s, loss=0.698, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   7%|▋         | 65/938 [00:04<01:00, 14.43it/s, loss=0.699, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   7%|▋         | 66/938 [00:04<01:00, 14.46it/s, loss=0.691, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   7%|▋         | 67/938 [00:04<01:00, 14.42it/s, loss=0.679, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   7%|▋         | 68/938 [00:04<01:00, 14.40it/s, loss=0.679, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   7%|▋         | 68/938 [00:04<01:00, 14.40it/s, loss=0.684, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   7%|▋         | 69/938 [00:04<01:00, 14.39it/s, loss=0.688, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   7%|▋         | 70/938 [00:04<01:00, 14.37it/s, loss=0.68, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:   8%|▊         | 71/938 [00:04<01:00, 14.35it/s, loss=0.674, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   8%|▊         | 72/938 [00:05<01:00, 14.37it/s, loss=0.674, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   8%|▊         | 72/938 [00:05<01:00, 14.37it/s, loss=0.69, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:   8%|▊         | 73/938 [00:05<01:00, 14.35it/s, loss=0.698, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   8%|▊         | 74/938 [00:05<01:00, 14.38it/s, loss=0.697, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   8%|▊         | 75/938 [00:05<01:00, 14.35it/s, loss=0.698, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   8%|▊         | 76/938 [00:05<01:00, 14.34it/s, loss=0.698, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   8%|▊         | 76/938 [00:05<01:00, 14.33it/s, loss=0.699, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   8%|▊         | 77/938 [00:05<00:59, 14.36it/s, loss=0.697, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   8%|▊         | 78/938 [00:05<00:59, 14.36it/s, loss=0.686, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   8%|▊         | 79/938 [00:05<00:59, 14.39it/s, loss=0.684, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   9%|▊         | 80/938 [00:05<00:59, 14.41it/s, loss=0.684, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   9%|▊         | 80/938 [00:05<00:59, 14.41it/s, loss=0.674, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   9%|▊         | 81/938 [00:05<00:59, 14.39it/s, loss=0.669, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   9%|▊         | 82/938 [00:05<00:59, 14.41it/s, loss=0.679, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   9%|▉         | 83/938 [00:05<00:59, 14.39it/s, loss=0.68, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:   9%|▉         | 84/938 [00:05<00:59, 14.42it/s, loss=0.68, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   9%|▉         | 84/938 [00:05<00:59, 14.42it/s, loss=0.687, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   9%|▉         | 85/938 [00:05<00:59, 14.39it/s, loss=0.69, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:   9%|▉         | 86/938 [00:05<00:59, 14.40it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   9%|▉         | 87/938 [00:06<00:59, 14.41it/s, loss=0.696, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   9%|▉         | 88/938 [00:06<00:58, 14.43it/s, loss=0.696, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   9%|▉         | 88/938 [00:06<00:58, 14.43it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:   9%|▉         | 89/938 [00:06<00:58, 14.42it/s, loss=0.679, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  10%|▉         | 90/938 [00:06<00:58, 14.43it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  10%|▉         | 91/938 [00:06<00:58, 14.44it/s, loss=0.688, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  10%|▉         | 92/938 [00:06<00:58, 14.42it/s, loss=0.688, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  10%|▉         | 92/938 [00:06<00:58, 14.42it/s, loss=0.676, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  10%|▉         | 93/938 [00:06<00:58, 14.45it/s, loss=0.678, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  10%|█         | 94/938 [00:06<00:58, 14.45it/s, loss=0.683, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  10%|█         | 95/938 [00:06<00:58, 14.46it/s, loss=0.692, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  10%|█         | 96/938 [00:06<00:58, 14.47it/s, loss=0.692, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  10%|█         | 96/938 [00:06<00:58, 14.47it/s, loss=0.698, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  10%|█         | 97/938 [00:06<00:58, 14.48it/s, loss=0.707, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  10%|█         | 98/938 [00:06<00:57, 14.49it/s, loss=0.708, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  11%|█         | 99/938 [00:06<00:57, 14.48it/s, loss=0.703, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  11%|█         | 100/938 [00:06<00:57, 14.50it/s, loss=0.703, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  11%|█         | 100/938 [00:06<00:57, 14.50it/s, loss=0.708, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  11%|█         | 101/938 [00:06<00:57, 14.50it/s, loss=0.711, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  11%|█         | 102/938 [00:07<00:57, 14.51it/s, loss=0.702, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  11%|█         | 103/938 [00:07<00:57, 14.48it/s, loss=0.709, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  11%|█         | 104/938 [00:07<00:57, 14.50it/s, loss=0.709, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  11%|█         | 104/938 [00:07<00:57, 14.50it/s, loss=0.703, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  11%|█         | 105/938 [00:07<00:57, 14.52it/s, loss=0.692, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  11%|█▏        | 106/938 [00:07<00:57, 14.48it/s, loss=0.693, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  11%|█▏        | 107/938 [00:07<00:57, 14.50it/s, loss=0.698, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  12%|█▏        | 108/938 [00:07<00:57, 14.51it/s, loss=0.698, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  12%|█▏        | 108/938 [00:07<00:57, 14.51it/s, loss=0.709, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  12%|█▏        | 109/938 [00:07<00:57, 14.51it/s, loss=0.713, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  12%|█▏        | 110/938 [00:07<00:57, 14.49it/s, loss=0.705, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  12%|█▏        | 111/938 [00:07<00:56, 14.51it/s, loss=0.71, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:  12%|█▏        | 112/938 [00:07<00:56, 14.52it/s, loss=0.71, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  12%|█▏        | 112/938 [00:07<00:56, 14.52it/s, loss=0.709, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  12%|█▏        | 113/938 [00:07<00:56, 14.53it/s, loss=0.712, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  12%|█▏        | 114/938 [00:07<00:56, 14.54it/s, loss=0.707, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  12%|█▏        | 115/938 [00:07<00:56, 14.53it/s, loss=0.707, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  12%|█▏        | 116/938 [00:07<00:56, 14.53it/s, loss=0.707, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  12%|█▏        | 116/938 [00:07<00:56, 14.53it/s, loss=0.705, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  12%|█▏        | 117/938 [00:08<00:56, 14.54it/s, loss=0.7, v_num=9, val_rmse=0.568, train_rmse=0.764]  
Epoch 2:  13%|█▎        | 118/938 [00:08<00:56, 14.56it/s, loss=0.706, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  13%|█▎        | 119/938 [00:08<00:56, 14.57it/s, loss=0.703, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  13%|█▎        | 120/938 [00:08<00:56, 14.58it/s, loss=0.703, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  13%|█▎        | 120/938 [00:08<00:56, 14.58it/s, loss=0.706, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  13%|█▎        | 121/938 [00:08<00:56, 14.57it/s, loss=0.703, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  13%|█▎        | 122/938 [00:08<00:56, 14.56it/s, loss=0.701, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  13%|█▎        | 123/938 [00:08<00:55, 14.57it/s, loss=0.693, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  13%|█▎        | 124/938 [00:08<00:55, 14.56it/s, loss=0.693, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  13%|█▎        | 124/938 [00:08<00:55, 14.56it/s, loss=0.695, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  13%|█▎        | 125/938 [00:08<00:55, 14.56it/s, loss=0.7, v_num=9, val_rmse=0.568, train_rmse=0.764]  
Epoch 2:  13%|█▎        | 126/938 [00:08<00:55, 14.56it/s, loss=0.699, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  14%|█▎        | 127/938 [00:08<00:55, 14.58it/s, loss=0.696, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  14%|█▎        | 128/938 [00:08<00:55, 14.49it/s, loss=0.696, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  14%|█▎        | 128/938 [00:08<00:55, 14.49it/s, loss=0.686, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  14%|█▍        | 129/938 [00:08<00:55, 14.50it/s, loss=0.693, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  14%|█▍        | 130/938 [00:08<00:55, 14.51it/s, loss=0.693, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  14%|█▍        | 131/938 [00:09<00:55, 14.49it/s, loss=0.691, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  14%|█▍        | 132/938 [00:09<00:55, 14.51it/s, loss=0.691, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  14%|█▍        | 132/938 [00:09<00:55, 14.51it/s, loss=0.686, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  14%|█▍        | 133/938 [00:09<00:55, 14.51it/s, loss=0.678, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  14%|█▍        | 134/938 [00:09<00:55, 14.53it/s, loss=0.675, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  14%|█▍        | 135/938 [00:09<00:55, 14.53it/s, loss=0.675, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  14%|█▍        | 136/938 [00:09<00:55, 14.54it/s, loss=0.675, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  14%|█▍        | 136/938 [00:09<00:55, 14.54it/s, loss=0.669, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  15%|█▍        | 137/938 [00:09<00:55, 14.54it/s, loss=0.666, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  15%|█▍        | 138/938 [00:09<00:54, 14.56it/s, loss=0.674, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  15%|█▍        | 139/938 [00:09<00:54, 14.56it/s, loss=0.675, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  15%|█▍        | 140/938 [00:09<00:54, 14.56it/s, loss=0.675, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  15%|█▍        | 140/938 [00:09<00:54, 14.56it/s, loss=0.669, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  15%|█▌        | 141/938 [00:09<00:54, 14.57it/s, loss=0.669, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  15%|█▌        | 142/938 [00:09<00:54, 14.56it/s, loss=0.677, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  15%|█▌        | 143/938 [00:09<00:54, 14.57it/s, loss=0.676, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  15%|█▌        | 144/938 [00:09<00:54, 14.56it/s, loss=0.676, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  15%|█▌        | 144/938 [00:09<00:54, 14.56it/s, loss=0.675, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  15%|█▌        | 145/938 [00:09<00:54, 14.58it/s, loss=0.673, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  16%|█▌        | 146/938 [00:10<00:54, 14.58it/s, loss=0.673, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  16%|█▌        | 147/938 [00:10<00:54, 14.60it/s, loss=0.672, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  16%|█▌        | 148/938 [00:10<00:54, 14.59it/s, loss=0.672, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  16%|█▌        | 148/938 [00:10<00:54, 14.59it/s, loss=0.68, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:  16%|█▌        | 149/938 [00:10<00:54, 14.61it/s, loss=0.691, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  16%|█▌        | 150/938 [00:10<00:53, 14.61it/s, loss=0.698, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  16%|█▌        | 151/938 [00:10<00:53, 14.60it/s, loss=0.704, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  16%|█▌        | 152/938 [00:10<00:53, 14.60it/s, loss=0.704, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  16%|█▌        | 152/938 [00:10<00:53, 14.60it/s, loss=0.712, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  16%|█▋        | 153/938 [00:10<00:53, 14.60it/s, loss=0.722, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  16%|█▋        | 154/938 [00:10<00:53, 14.57it/s, loss=0.72, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:  17%|█▋        | 155/938 [00:10<00:53, 14.58it/s, loss=0.711, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  17%|█▋        | 156/938 [00:10<00:53, 14.56it/s, loss=0.711, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  17%|█▋        | 156/938 [00:10<00:53, 14.56it/s, loss=0.706, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  17%|█▋        | 157/938 [00:10<00:53, 14.57it/s, loss=0.705, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  17%|█▋        | 158/938 [00:10<00:53, 14.58it/s, loss=0.693, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  17%|█▋        | 159/938 [00:10<00:53, 14.58it/s, loss=0.691, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  17%|█▋        | 160/938 [00:10<00:53, 14.58it/s, loss=0.691, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  17%|█▋        | 160/938 [00:10<00:53, 14.58it/s, loss=0.697, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  17%|█▋        | 161/938 [00:11<00:53, 14.59it/s, loss=0.697, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  17%|█▋        | 162/938 [00:11<00:53, 14.60it/s, loss=0.699, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  17%|█▋        | 163/938 [00:11<00:53, 14.60it/s, loss=0.702, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  17%|█▋        | 164/938 [00:11<00:52, 14.60it/s, loss=0.702, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  17%|█▋        | 164/938 [00:11<00:53, 14.60it/s, loss=0.709, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  18%|█▊        | 165/938 [00:11<00:52, 14.61it/s, loss=0.714, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  18%|█▊        | 166/938 [00:11<00:52, 14.61it/s, loss=0.71, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:  18%|█▊        | 167/938 [00:11<00:52, 14.62it/s, loss=0.719, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  18%|█▊        | 168/938 [00:11<00:52, 14.62it/s, loss=0.719, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  18%|█▊        | 168/938 [00:11<00:52, 14.62it/s, loss=0.713, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  18%|█▊        | 169/938 [00:11<00:52, 14.62it/s, loss=0.699, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  18%|█▊        | 170/938 [00:11<00:52, 14.60it/s, loss=0.694, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  18%|█▊        | 171/938 [00:11<00:52, 14.62it/s, loss=0.694, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  18%|█▊        | 172/938 [00:11<00:52, 14.61it/s, loss=0.694, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  18%|█▊        | 172/938 [00:11<00:52, 14.61it/s, loss=0.692, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  18%|█▊        | 173/938 [00:11<00:52, 14.63it/s, loss=0.684, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  19%|█▊        | 174/938 [00:11<00:52, 14.64it/s, loss=0.684, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  19%|█▊        | 175/938 [00:11<00:52, 14.63it/s, loss=0.676, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  19%|█▉        | 176/938 [00:12<00:52, 14.62it/s, loss=0.676, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  19%|█▉        | 176/938 [00:12<00:52, 14.62it/s, loss=0.686, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  19%|█▉        | 177/938 [00:12<00:52, 14.62it/s, loss=0.7, v_num=9, val_rmse=0.568, train_rmse=0.764]  
Epoch 2:  19%|█▉        | 178/938 [00:12<00:52, 14.61it/s, loss=0.706, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  19%|█▉        | 179/938 [00:12<00:51, 14.61it/s, loss=0.709, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  19%|█▉        | 180/938 [00:12<00:51, 14.63it/s, loss=0.709, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  19%|█▉        | 180/938 [00:12<00:51, 14.63it/s, loss=0.708, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  19%|█▉        | 181/938 [00:12<00:51, 14.63it/s, loss=0.712, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  19%|█▉        | 182/938 [00:12<00:51, 14.63it/s, loss=0.711, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  20%|█▉        | 183/938 [00:12<00:51, 14.64it/s, loss=0.713, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  20%|█▉        | 184/938 [00:12<00:51, 14.63it/s, loss=0.713, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  20%|█▉        | 184/938 [00:12<00:51, 14.63it/s, loss=0.712, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  20%|█▉        | 185/938 [00:12<00:51, 14.64it/s, loss=0.708, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  20%|█▉        | 186/938 [00:12<00:51, 14.62it/s, loss=0.711, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  20%|█▉        | 187/938 [00:12<00:51, 14.61it/s, loss=0.708, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  20%|██        | 188/938 [00:12<00:51, 14.61it/s, loss=0.708, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  20%|██        | 188/938 [00:12<00:51, 14.61it/s, loss=0.707, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  20%|██        | 189/938 [00:12<00:51, 14.62it/s, loss=0.703, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  20%|██        | 190/938 [00:12<00:51, 14.63it/s, loss=0.705, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  20%|██        | 191/938 [00:13<00:51, 14.62it/s, loss=0.706, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  20%|██        | 192/938 [00:13<00:50, 14.63it/s, loss=0.706, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  20%|██        | 192/938 [00:13<00:50, 14.63it/s, loss=0.706, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  21%|██        | 193/938 [00:13<00:50, 14.62it/s, loss=0.704, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  21%|██        | 194/938 [00:13<00:50, 14.63it/s, loss=0.718, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  21%|██        | 195/938 [00:13<00:50, 14.63it/s, loss=0.718, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  21%|██        | 196/938 [00:13<00:50, 14.63it/s, loss=0.718, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  21%|██        | 196/938 [00:13<00:50, 14.63it/s, loss=0.717, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  21%|██        | 197/938 [00:13<00:50, 14.64it/s, loss=0.703, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  21%|██        | 198/938 [00:13<00:50, 14.64it/s, loss=0.703, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  21%|██        | 199/938 [00:13<00:50, 14.64it/s, loss=0.702, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  21%|██▏       | 200/938 [00:13<00:50, 14.64it/s, loss=0.702, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  21%|██▏       | 200/938 [00:13<00:50, 14.64it/s, loss=0.706, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  21%|██▏       | 201/938 [00:13<00:50, 14.65it/s, loss=0.708, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  22%|██▏       | 202/938 [00:13<00:50, 14.59it/s, loss=0.702, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  22%|██▏       | 203/938 [00:13<00:50, 14.59it/s, loss=0.695, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  22%|██▏       | 204/938 [00:14<00:50, 14.57it/s, loss=0.695, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  22%|██▏       | 204/938 [00:14<00:50, 14.57it/s, loss=0.702, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  22%|██▏       | 205/938 [00:14<00:50, 14.57it/s, loss=0.703, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  22%|██▏       | 206/938 [00:14<00:50, 14.57it/s, loss=0.711, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  22%|██▏       | 207/938 [00:14<00:50, 14.56it/s, loss=0.706, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  22%|██▏       | 208/938 [00:14<00:50, 14.57it/s, loss=0.706, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  22%|██▏       | 208/938 [00:14<00:50, 14.57it/s, loss=0.712, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  22%|██▏       | 209/938 [00:14<00:50, 14.57it/s, loss=0.711, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  22%|██▏       | 210/938 [00:14<00:49, 14.56it/s, loss=0.705, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  22%|██▏       | 211/938 [00:14<00:49, 14.57it/s, loss=0.7, v_num=9, val_rmse=0.568, train_rmse=0.764]  
Epoch 2:  23%|██▎       | 212/938 [00:14<00:49, 14.56it/s, loss=0.7, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  23%|██▎       | 212/938 [00:14<00:49, 14.56it/s, loss=0.701, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  23%|██▎       | 213/938 [00:14<00:49, 14.55it/s, loss=0.701, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  23%|██▎       | 214/938 [00:14<00:49, 14.56it/s, loss=0.692, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  23%|██▎       | 215/938 [00:14<00:49, 14.55it/s, loss=0.698, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  23%|██▎       | 216/938 [00:14<00:49, 14.55it/s, loss=0.698, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  23%|██▎       | 216/938 [00:14<00:49, 14.55it/s, loss=0.697, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  23%|██▎       | 217/938 [00:14<00:49, 14.55it/s, loss=0.704, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  23%|██▎       | 218/938 [00:14<00:49, 14.55it/s, loss=0.7, v_num=9, val_rmse=0.568, train_rmse=0.764]  
Epoch 2:  23%|██▎       | 219/938 [00:15<00:49, 14.56it/s, loss=0.705, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  23%|██▎       | 220/938 [00:15<00:49, 14.55it/s, loss=0.705, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  23%|██▎       | 220/938 [00:15<00:49, 14.54it/s, loss=0.704, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  24%|██▎       | 221/938 [00:15<00:49, 14.54it/s, loss=0.701, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  24%|██▎       | 222/938 [00:15<00:49, 14.53it/s, loss=0.696, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  24%|██▍       | 223/938 [00:15<00:49, 14.54it/s, loss=0.702, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  24%|██▍       | 224/938 [00:15<00:49, 14.54it/s, loss=0.702, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  24%|██▍       | 224/938 [00:15<00:49, 14.54it/s, loss=0.694, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  24%|██▍       | 225/938 [00:15<00:49, 14.54it/s, loss=0.694, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  24%|██▍       | 226/938 [00:15<00:48, 14.55it/s, loss=0.687, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  24%|██▍       | 227/938 [00:15<00:48, 14.56it/s, loss=0.691, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  24%|██▍       | 228/938 [00:15<00:48, 14.56it/s, loss=0.691, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  24%|██▍       | 228/938 [00:15<00:48, 14.56it/s, loss=0.69, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:  24%|██▍       | 229/938 [00:15<00:48, 14.56it/s, loss=0.693, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  25%|██▍       | 230/938 [00:15<00:48, 14.55it/s, loss=0.692, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  25%|██▍       | 231/938 [00:15<00:48, 14.52it/s, loss=0.687, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  25%|██▍       | 232/938 [00:15<00:48, 14.53it/s, loss=0.687, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  25%|██▍       | 232/938 [00:15<00:48, 14.53it/s, loss=0.681, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  25%|██▍       | 233/938 [00:16<00:48, 14.54it/s, loss=0.688, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  25%|██▍       | 234/938 [00:16<00:48, 14.53it/s, loss=0.683, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  25%|██▌       | 235/938 [00:16<00:48, 14.53it/s, loss=0.681, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  25%|██▌       | 236/938 [00:16<00:48, 14.55it/s, loss=0.681, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  25%|██▌       | 236/938 [00:16<00:48, 14.55it/s, loss=0.681, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  25%|██▌       | 237/938 [00:16<00:48, 14.54it/s, loss=0.679, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  25%|██▌       | 238/938 [00:16<00:48, 14.53it/s, loss=0.683, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  25%|██▌       | 239/938 [00:16<00:48, 14.52it/s, loss=0.684, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  26%|██▌       | 240/938 [00:16<00:48, 14.53it/s, loss=0.684, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  26%|██▌       | 240/938 [00:16<00:48, 14.53it/s, loss=0.675, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  26%|██▌       | 241/938 [00:16<00:47, 14.53it/s, loss=0.677, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  26%|██▌       | 242/938 [00:16<00:47, 14.53it/s, loss=0.68, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:  26%|██▌       | 243/938 [00:16<00:47, 14.53it/s, loss=0.682, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  26%|██▌       | 244/938 [00:16<00:47, 14.53it/s, loss=0.682, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  26%|██▌       | 244/938 [00:16<00:47, 14.53it/s, loss=0.684, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  26%|██▌       | 245/938 [00:16<00:47, 14.53it/s, loss=0.684, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  26%|██▌       | 246/938 [00:16<00:47, 14.50it/s, loss=0.69, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:  26%|██▋       | 247/938 [00:17<00:47, 14.50it/s, loss=0.68, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  26%|██▋       | 248/938 [00:17<00:47, 14.51it/s, loss=0.68, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  26%|██▋       | 248/938 [00:17<00:47, 14.51it/s, loss=0.676, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  27%|██▋       | 249/938 [00:17<00:47, 14.51it/s, loss=0.675, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  27%|██▋       | 250/938 [00:17<00:47, 14.53it/s, loss=0.677, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  27%|██▋       | 251/938 [00:17<00:47, 14.52it/s, loss=0.693, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  27%|██▋       | 252/938 [00:17<00:47, 14.52it/s, loss=0.693, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  27%|██▋       | 252/938 [00:17<00:47, 14.52it/s, loss=0.698, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  27%|██▋       | 253/938 [00:17<00:47, 14.52it/s, loss=0.696, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  27%|██▋       | 254/938 [00:17<00:47, 14.53it/s, loss=0.702, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  27%|██▋       | 255/938 [00:17<00:47, 14.53it/s, loss=0.706, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  27%|██▋       | 256/938 [00:17<00:46, 14.54it/s, loss=0.706, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  27%|██▋       | 256/938 [00:17<00:46, 14.54it/s, loss=0.71, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:  27%|██▋       | 257/938 [00:17<00:47, 14.48it/s, loss=0.707, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  28%|██▊       | 258/938 [00:17<00:46, 14.48it/s, loss=0.705, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  28%|██▊       | 259/938 [00:17<00:46, 14.49it/s, loss=0.704, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  28%|██▊       | 260/938 [00:17<00:46, 14.49it/s, loss=0.704, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  28%|██▊       | 260/938 [00:17<00:46, 14.49it/s, loss=0.714, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  28%|██▊       | 261/938 [00:18<00:46, 14.49it/s, loss=0.711, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  28%|██▊       | 262/938 [00:18<00:46, 14.50it/s, loss=0.713, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  28%|██▊       | 263/938 [00:18<00:46, 14.49it/s, loss=0.717, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  28%|██▊       | 264/938 [00:18<00:46, 14.49it/s, loss=0.717, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  28%|██▊       | 264/938 [00:18<00:46, 14.49it/s, loss=0.711, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  28%|██▊       | 265/938 [00:18<00:46, 14.48it/s, loss=0.711, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  28%|██▊       | 266/938 [00:18<00:46, 14.48it/s, loss=0.709, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  28%|██▊       | 267/938 [00:18<00:46, 14.49it/s, loss=0.717, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  29%|██▊       | 268/938 [00:18<00:46, 14.49it/s, loss=0.717, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  29%|██▊       | 268/938 [00:18<00:46, 14.49it/s, loss=0.712, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  29%|██▊       | 269/938 [00:18<00:46, 14.49it/s, loss=0.716, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  29%|██▉       | 270/938 [00:18<00:46, 14.49it/s, loss=0.712, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  29%|██▉       | 271/938 [00:18<00:46, 14.49it/s, loss=0.701, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  29%|██▉       | 272/938 [00:18<00:45, 14.49it/s, loss=0.701, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  29%|██▉       | 272/938 [00:18<00:45, 14.49it/s, loss=0.703, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  29%|██▉       | 273/938 [00:18<00:45, 14.49it/s, loss=0.697, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  29%|██▉       | 274/938 [00:18<00:45, 14.49it/s, loss=0.692, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  29%|██▉       | 275/938 [00:18<00:45, 14.49it/s, loss=0.688, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  29%|██▉       | 276/938 [00:19<00:45, 14.48it/s, loss=0.688, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  29%|██▉       | 276/938 [00:19<00:45, 14.48it/s, loss=0.675, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  30%|██▉       | 277/938 [00:19<00:45, 14.48it/s, loss=0.672, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  30%|██▉       | 278/938 [00:19<00:45, 14.49it/s, loss=0.669, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  30%|██▉       | 279/938 [00:19<00:45, 14.49it/s, loss=0.659, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  30%|██▉       | 280/938 [00:19<00:45, 14.50it/s, loss=0.659, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  30%|██▉       | 280/938 [00:19<00:45, 14.50it/s, loss=0.65, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:  30%|██▉       | 281/938 [00:19<00:45, 14.50it/s, loss=0.645, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  30%|███       | 282/938 [00:19<00:45, 14.49it/s, loss=0.645, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  30%|███       | 283/938 [00:19<00:45, 14.50it/s, loss=0.641, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  30%|███       | 284/938 [00:19<00:45, 14.50it/s, loss=0.641, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  30%|███       | 284/938 [00:19<00:45, 14.50it/s, loss=0.646, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  30%|███       | 285/938 [00:19<00:45, 14.49it/s, loss=0.648, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  30%|███       | 286/938 [00:19<00:45, 14.49it/s, loss=0.647, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  31%|███       | 287/938 [00:19<00:44, 14.49it/s, loss=0.642, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  31%|███       | 288/938 [00:19<00:44, 14.50it/s, loss=0.642, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  31%|███       | 288/938 [00:19<00:44, 14.50it/s, loss=0.641, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  31%|███       | 289/938 [00:19<00:44, 14.50it/s, loss=0.637, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  31%|███       | 290/938 [00:19<00:44, 14.50it/s, loss=0.641, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  31%|███       | 291/938 [00:20<00:44, 14.50it/s, loss=0.639, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  31%|███       | 292/938 [00:20<00:44, 14.47it/s, loss=0.639, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  31%|███       | 292/938 [00:20<00:44, 14.47it/s, loss=0.636, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  31%|███       | 293/938 [00:20<00:44, 14.47it/s, loss=0.646, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  31%|███▏      | 294/938 [00:20<00:44, 14.48it/s, loss=0.638, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  31%|███▏      | 295/938 [00:20<00:44, 14.48it/s, loss=0.643, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  32%|███▏      | 296/938 [00:20<00:44, 14.49it/s, loss=0.643, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  32%|███▏      | 296/938 [00:20<00:44, 14.49it/s, loss=0.648, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  32%|███▏      | 297/938 [00:20<00:44, 14.49it/s, loss=0.654, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  32%|███▏      | 298/938 [00:20<00:44, 14.49it/s, loss=0.656, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  32%|███▏      | 299/938 [00:20<00:44, 14.51it/s, loss=0.66, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:  32%|███▏      | 300/938 [00:20<00:44, 14.50it/s, loss=0.66, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  32%|███▏      | 300/938 [00:20<00:44, 14.50it/s, loss=0.663, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  32%|███▏      | 301/938 [00:20<00:43, 14.50it/s, loss=0.675, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  32%|███▏      | 302/938 [00:20<00:43, 14.50it/s, loss=0.674, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  32%|███▏      | 303/938 [00:20<00:43, 14.49it/s, loss=0.669, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  32%|███▏      | 304/938 [00:20<00:43, 14.49it/s, loss=0.669, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  32%|███▏      | 304/938 [00:20<00:43, 14.49it/s, loss=0.67, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:  33%|███▎      | 305/938 [00:21<00:43, 14.50it/s, loss=0.669, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  33%|███▎      | 306/938 [00:21<00:43, 14.50it/s, loss=0.669, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  33%|███▎      | 307/938 [00:21<00:43, 14.51it/s, loss=0.675, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  33%|███▎      | 308/938 [00:21<00:43, 14.51it/s, loss=0.675, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  33%|███▎      | 308/938 [00:21<00:43, 14.51it/s, loss=0.692, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  33%|███▎      | 309/938 [00:21<00:43, 14.51it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  33%|███▎      | 310/938 [00:21<00:43, 14.51it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  33%|███▎      | 311/938 [00:21<00:43, 14.51it/s, loss=0.697, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  33%|███▎      | 312/938 [00:21<00:43, 14.50it/s, loss=0.697, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  33%|███▎      | 312/938 [00:21<00:43, 14.50it/s, loss=0.703, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  33%|███▎      | 313/938 [00:21<00:43, 14.50it/s, loss=0.698, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  33%|███▎      | 314/938 [00:21<00:43, 14.50it/s, loss=0.708, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  34%|███▎      | 315/938 [00:21<00:43, 14.48it/s, loss=0.719, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  34%|███▎      | 316/938 [00:21<00:42, 14.48it/s, loss=0.719, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  34%|███▎      | 316/938 [00:21<00:42, 14.48it/s, loss=0.718, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  34%|███▍      | 317/938 [00:21<00:42, 14.47it/s, loss=0.719, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  34%|███▍      | 318/938 [00:21<00:42, 14.47it/s, loss=0.729, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  34%|███▍      | 319/938 [00:22<00:42, 14.48it/s, loss=0.726, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  34%|███▍      | 320/938 [00:22<00:42, 14.47it/s, loss=0.726, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  34%|███▍      | 320/938 [00:22<00:42, 14.47it/s, loss=0.722, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  34%|███▍      | 321/938 [00:22<00:42, 14.48it/s, loss=0.722, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  34%|███▍      | 322/938 [00:22<00:42, 14.48it/s, loss=0.724, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  34%|███▍      | 323/938 [00:22<00:42, 14.47it/s, loss=0.736, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  35%|███▍      | 324/938 [00:22<00:42, 14.47it/s, loss=0.736, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  35%|███▍      | 324/938 [00:22<00:42, 14.47it/s, loss=0.733, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  35%|███▍      | 325/938 [00:22<00:42, 14.47it/s, loss=0.737, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  35%|███▍      | 326/938 [00:22<00:42, 14.47it/s, loss=0.731, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  35%|███▍      | 327/938 [00:22<00:42, 14.47it/s, loss=0.726, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  35%|███▍      | 328/938 [00:22<00:42, 14.48it/s, loss=0.726, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  35%|███▍      | 328/938 [00:22<00:42, 14.48it/s, loss=0.715, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  35%|███▌      | 329/938 [00:22<00:42, 14.46it/s, loss=0.718, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  35%|███▌      | 330/938 [00:22<00:42, 14.45it/s, loss=0.723, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  35%|███▌      | 331/938 [00:22<00:41, 14.46it/s, loss=0.72, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:  35%|███▌      | 332/938 [00:22<00:41, 14.45it/s, loss=0.72, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  35%|███▌      | 332/938 [00:22<00:41, 14.45it/s, loss=0.716, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  36%|███▌      | 333/938 [00:23<00:41, 14.45it/s, loss=0.71, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:  36%|███▌      | 334/938 [00:23<00:41, 14.45it/s, loss=0.706, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  36%|███▌      | 335/938 [00:23<00:41, 14.45it/s, loss=0.695, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  36%|███▌      | 336/938 [00:23<00:41, 14.45it/s, loss=0.695, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  36%|███▌      | 336/938 [00:23<00:41, 14.45it/s, loss=0.708, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  36%|███▌      | 337/938 [00:23<00:41, 14.44it/s, loss=0.709, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  36%|███▌      | 338/938 [00:23<00:41, 14.44it/s, loss=0.694, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  36%|███▌      | 339/938 [00:23<00:41, 14.44it/s, loss=0.698, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  36%|███▌      | 340/938 [00:23<00:41, 14.44it/s, loss=0.698, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  36%|███▌      | 340/938 [00:23<00:41, 14.44it/s, loss=0.706, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  36%|███▋      | 341/938 [00:23<00:41, 14.44it/s, loss=0.697, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  36%|███▋      | 342/938 [00:23<00:41, 14.44it/s, loss=0.694, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  37%|███▋      | 343/938 [00:23<00:41, 14.43it/s, loss=0.682, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  37%|███▋      | 344/938 [00:23<00:41, 14.43it/s, loss=0.682, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  37%|███▋      | 344/938 [00:23<00:41, 14.43it/s, loss=0.681, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  37%|███▋      | 345/938 [00:23<00:41, 14.44it/s, loss=0.68, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:  37%|███▋      | 346/938 [00:23<00:41, 14.43it/s, loss=0.699, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  37%|███▋      | 347/938 [00:24<00:40, 14.43it/s, loss=0.705, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  37%|███▋      | 348/938 [00:24<00:40, 14.43it/s, loss=0.705, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  37%|███▋      | 348/938 [00:24<00:40, 14.43it/s, loss=0.702, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  37%|███▋      | 349/938 [00:24<00:40, 14.43it/s, loss=0.699, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  37%|███▋      | 350/938 [00:24<00:40, 14.42it/s, loss=0.698, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  37%|███▋      | 351/938 [00:24<00:40, 14.41it/s, loss=0.699, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  38%|███▊      | 352/938 [00:24<00:40, 14.41it/s, loss=0.699, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  38%|███▊      | 352/938 [00:24<00:40, 14.41it/s, loss=0.701, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  38%|███▊      | 353/938 [00:24<00:40, 14.42it/s, loss=0.711, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  38%|███▊      | 354/938 [00:24<00:40, 14.42it/s, loss=0.707, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  38%|███▊      | 355/938 [00:24<00:40, 14.42it/s, loss=0.705, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  38%|███▊      | 356/938 [00:24<00:40, 14.42it/s, loss=0.705, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  38%|███▊      | 356/938 [00:24<00:40, 14.42it/s, loss=0.695, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  38%|███▊      | 357/938 [00:24<00:40, 14.41it/s, loss=0.691, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  38%|███▊      | 358/938 [00:24<00:40, 14.41it/s, loss=0.698, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  38%|███▊      | 359/938 [00:24<00:40, 14.40it/s, loss=0.701, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  38%|███▊      | 360/938 [00:25<00:40, 14.40it/s, loss=0.701, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  38%|███▊      | 360/938 [00:25<00:40, 14.40it/s, loss=0.696, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  38%|███▊      | 361/938 [00:25<00:40, 14.40it/s, loss=0.701, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  39%|███▊      | 362/938 [00:25<00:39, 14.40it/s, loss=0.704, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  39%|███▊      | 363/938 [00:25<00:39, 14.41it/s, loss=0.708, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  39%|███▉      | 364/938 [00:25<00:39, 14.41it/s, loss=0.708, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  39%|███▉      | 364/938 [00:25<00:39, 14.41it/s, loss=0.714, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  39%|███▉      | 365/938 [00:25<00:39, 14.41it/s, loss=0.716, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  39%|███▉      | 366/938 [00:25<00:39, 14.41it/s, loss=0.701, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  39%|███▉      | 367/938 [00:25<00:39, 14.42it/s, loss=0.696, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  39%|███▉      | 368/938 [00:25<00:39, 14.42it/s, loss=0.696, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  39%|███▉      | 368/938 [00:25<00:39, 14.42it/s, loss=0.698, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  39%|███▉      | 369/938 [00:25<00:39, 14.41it/s, loss=0.703, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  39%|███▉      | 370/938 [00:25<00:39, 14.42it/s, loss=0.697, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  40%|███▉      | 371/938 [00:25<00:39, 14.41it/s, loss=0.693, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  40%|███▉      | 372/938 [00:25<00:39, 14.41it/s, loss=0.693, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  40%|███▉      | 372/938 [00:25<00:39, 14.41it/s, loss=0.684, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  40%|███▉      | 373/938 [00:25<00:39, 14.40it/s, loss=0.683, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  40%|███▉      | 374/938 [00:25<00:39, 14.40it/s, loss=0.681, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  40%|███▉      | 375/938 [00:26<00:39, 14.40it/s, loss=0.681, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  40%|████      | 376/938 [00:26<00:39, 14.40it/s, loss=0.681, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  40%|████      | 376/938 [00:26<00:39, 14.39it/s, loss=0.685, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  40%|████      | 377/938 [00:26<00:38, 14.39it/s, loss=0.699, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  40%|████      | 378/938 [00:26<00:38, 14.40it/s, loss=0.694, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  40%|████      | 379/938 [00:26<00:38, 14.40it/s, loss=0.687, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  41%|████      | 380/938 [00:26<00:38, 14.40it/s, loss=0.687, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  41%|████      | 380/938 [00:26<00:38, 14.40it/s, loss=0.684, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  41%|████      | 381/938 [00:26<00:38, 14.40it/s, loss=0.68, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:  41%|████      | 382/938 [00:26<00:38, 14.40it/s, loss=0.675, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  41%|████      | 383/938 [00:26<00:38, 14.39it/s, loss=0.678, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  41%|████      | 384/938 [00:26<00:38, 14.39it/s, loss=0.678, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  41%|████      | 384/938 [00:26<00:38, 14.39it/s, loss=0.674, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  41%|████      | 385/938 [00:26<00:38, 14.39it/s, loss=0.674, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  41%|████      | 386/938 [00:26<00:38, 14.38it/s, loss=0.673, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  41%|████▏     | 387/938 [00:26<00:38, 14.38it/s, loss=0.672, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  41%|████▏     | 388/938 [00:26<00:38, 14.38it/s, loss=0.672, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  41%|████▏     | 388/938 [00:26<00:38, 14.38it/s, loss=0.677, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  41%|████▏     | 389/938 [00:27<00:38, 14.38it/s, loss=0.671, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  42%|████▏     | 390/938 [00:27<00:38, 14.38it/s, loss=0.688, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  42%|████▏     | 391/938 [00:27<00:38, 14.38it/s, loss=0.688, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  42%|████▏     | 392/938 [00:27<00:37, 14.39it/s, loss=0.688, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  42%|████▏     | 392/938 [00:27<00:37, 14.39it/s, loss=0.699, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  42%|████▏     | 393/938 [00:27<00:37, 14.39it/s, loss=0.69, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:  42%|████▏     | 394/938 [00:27<00:37, 14.40it/s, loss=0.695, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  42%|████▏     | 395/938 [00:27<00:37, 14.40it/s, loss=0.7, v_num=9, val_rmse=0.568, train_rmse=0.764]  
Epoch 2:  42%|████▏     | 396/938 [00:27<00:37, 14.39it/s, loss=0.7, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  42%|████▏     | 396/938 [00:27<00:37, 14.39it/s, loss=0.699, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  42%|████▏     | 397/938 [00:27<00:37, 14.40it/s, loss=0.682, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  42%|████▏     | 398/938 [00:27<00:37, 14.40it/s, loss=0.687, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  43%|████▎     | 399/938 [00:27<00:37, 14.40it/s, loss=0.69, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:  43%|████▎     | 400/938 [00:27<00:37, 14.40it/s, loss=0.69, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  43%|████▎     | 400/938 [00:27<00:37, 14.40it/s, loss=0.69, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  43%|████▎     | 401/938 [00:27<00:37, 14.41it/s, loss=0.694, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  43%|████▎     | 402/938 [00:27<00:37, 14.41it/s, loss=0.707, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  43%|████▎     | 403/938 [00:27<00:37, 14.41it/s, loss=0.701, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  43%|████▎     | 404/938 [00:28<00:37, 14.41it/s, loss=0.701, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  43%|████▎     | 404/938 [00:28<00:37, 14.41it/s, loss=0.708, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  43%|████▎     | 405/938 [00:28<00:36, 14.41it/s, loss=0.702, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  43%|████▎     | 406/938 [00:28<00:36, 14.40it/s, loss=0.709, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  43%|████▎     | 407/938 [00:28<00:36, 14.40it/s, loss=0.711, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  43%|████▎     | 408/938 [00:28<00:36, 14.40it/s, loss=0.711, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  43%|████▎     | 408/938 [00:28<00:36, 14.40it/s, loss=0.712, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  44%|████▎     | 409/938 [00:28<00:36, 14.40it/s, loss=0.716, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  44%|████▎     | 410/938 [00:28<00:36, 14.40it/s, loss=0.706, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  44%|████▍     | 411/938 [00:28<00:36, 14.40it/s, loss=0.709, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  44%|████▍     | 412/938 [00:28<00:36, 14.39it/s, loss=0.709, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  44%|████▍     | 412/938 [00:28<00:36, 14.38it/s, loss=0.705, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  44%|████▍     | 413/938 [00:28<00:36, 14.38it/s, loss=0.707, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  44%|████▍     | 414/938 [00:28<00:36, 14.38it/s, loss=0.701, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  44%|████▍     | 415/938 [00:28<00:36, 14.38it/s, loss=0.697, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  44%|████▍     | 416/938 [00:28<00:36, 14.38it/s, loss=0.697, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  44%|████▍     | 416/938 [00:28<00:36, 14.38it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  44%|████▍     | 417/938 [00:28<00:36, 14.38it/s, loss=0.686, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  45%|████▍     | 418/938 [00:29<00:36, 14.38it/s, loss=0.683, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  45%|████▍     | 419/938 [00:29<00:36, 14.37it/s, loss=0.681, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  45%|████▍     | 420/938 [00:29<00:36, 14.37it/s, loss=0.681, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  45%|████▍     | 420/938 [00:29<00:36, 14.37it/s, loss=0.678, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  45%|████▍     | 421/938 [00:29<00:35, 14.37it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  45%|████▍     | 422/938 [00:29<00:35, 14.38it/s, loss=0.678, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  45%|████▌     | 423/938 [00:29<00:35, 14.37it/s, loss=0.678, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  45%|████▌     | 424/938 [00:29<00:35, 14.38it/s, loss=0.678, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  45%|████▌     | 424/938 [00:29<00:35, 14.38it/s, loss=0.671, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  45%|████▌     | 425/938 [00:29<00:35, 14.37it/s, loss=0.674, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  45%|████▌     | 426/938 [00:29<00:35, 14.38it/s, loss=0.673, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  46%|████▌     | 427/938 [00:29<00:35, 14.38it/s, loss=0.674, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  46%|████▌     | 428/938 [00:29<00:35, 14.39it/s, loss=0.674, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  46%|████▌     | 428/938 [00:29<00:35, 14.39it/s, loss=0.662, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  46%|████▌     | 429/938 [00:29<00:35, 14.39it/s, loss=0.659, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  46%|████▌     | 430/938 [00:29<00:35, 14.39it/s, loss=0.658, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  46%|████▌     | 431/938 [00:29<00:35, 14.39it/s, loss=0.656, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  46%|████▌     | 432/938 [00:30<00:35, 14.39it/s, loss=0.656, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  46%|████▌     | 432/938 [00:30<00:35, 14.39it/s, loss=0.66, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:  46%|████▌     | 433/938 [00:30<00:35, 14.39it/s, loss=0.663, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  46%|████▋     | 434/938 [00:30<00:35, 14.38it/s, loss=0.669, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  46%|████▋     | 435/938 [00:30<00:34, 14.39it/s, loss=0.671, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  46%|████▋     | 436/938 [00:30<00:34, 14.39it/s, loss=0.671, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  46%|████▋     | 436/938 [00:30<00:34, 14.39it/s, loss=0.673, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  47%|████▋     | 437/938 [00:30<00:34, 14.38it/s, loss=0.678, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  47%|████▋     | 438/938 [00:30<00:34, 14.39it/s, loss=0.688, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  47%|████▋     | 439/938 [00:30<00:34, 14.39it/s, loss=0.687, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  47%|████▋     | 440/938 [00:30<00:34, 14.38it/s, loss=0.687, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  47%|████▋     | 440/938 [00:30<00:34, 14.38it/s, loss=0.699, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  47%|████▋     | 441/938 [00:30<00:34, 14.39it/s, loss=0.686, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  47%|████▋     | 442/938 [00:30<00:34, 14.38it/s, loss=0.685, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  47%|████▋     | 443/938 [00:30<00:34, 14.39it/s, loss=0.681, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  47%|████▋     | 444/938 [00:30<00:34, 14.39it/s, loss=0.681, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  47%|████▋     | 444/938 [00:30<00:34, 14.39it/s, loss=0.691, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  47%|████▋     | 445/938 [00:30<00:34, 14.39it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  48%|████▊     | 446/938 [00:30<00:34, 14.39it/s, loss=0.68, v_num=9, val_rmse=0.568, train_rmse=0.764] 
Epoch 2:  48%|████▊     | 447/938 [00:31<00:34, 14.40it/s, loss=0.682, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  48%|████▊     | 448/938 [00:31<00:34, 14.39it/s, loss=0.682, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  48%|████▊     | 448/938 [00:31<00:34, 14.39it/s, loss=0.697, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  48%|████▊     | 449/938 [00:31<00:33, 14.39it/s, loss=0.693, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  48%|████▊     | 450/938 [00:31<00:33, 14.39it/s, loss=0.694, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  48%|████▊     | 451/938 [00:31<00:33, 14.38it/s, loss=0.695, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  48%|████▊     | 452/938 [00:31<00:33, 14.39it/s, loss=0.695, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  48%|████▊     | 452/938 [00:31<00:33, 14.38it/s, loss=0.694, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  48%|████▊     | 453/938 [00:31<00:33, 14.39it/s, loss=0.693, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  48%|████▊     | 454/938 [00:31<00:33, 14.39it/s, loss=0.697, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  49%|████▊     | 455/938 [00:31<00:33, 14.38it/s, loss=0.702, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  49%|████▊     | 456/938 [00:31<00:33, 14.38it/s, loss=0.702, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  49%|████▊     | 456/938 [00:31<00:33, 14.38it/s, loss=0.705, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  49%|████▊     | 457/938 [00:31<00:33, 14.38it/s, loss=0.707, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  49%|████▉     | 458/938 [00:31<00:33, 14.38it/s, loss=0.696, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  49%|████▉     | 459/938 [00:31<00:33, 14.38it/s, loss=0.701, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  49%|████▉     | 460/938 [00:31<00:33, 14.38it/s, loss=0.701, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  49%|████▉     | 460/938 [00:31<00:33, 14.38it/s, loss=0.701, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  49%|████▉     | 461/938 [00:32<00:33, 14.38it/s, loss=0.703, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  49%|████▉     | 462/938 [00:32<00:33, 14.38it/s, loss=0.706, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  49%|████▉     | 463/938 [00:32<00:33, 14.39it/s, loss=0.713, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  49%|████▉     | 464/938 [00:32<00:32, 14.39it/s, loss=0.713, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  49%|████▉     | 464/938 [00:32<00:32, 14.39it/s, loss=0.701, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  50%|████▉     | 465/938 [00:32<00:32, 14.39it/s, loss=0.708, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  50%|████▉     | 466/938 [00:32<00:32, 14.39it/s, loss=0.707, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  50%|████▉     | 467/938 [00:32<00:32, 14.40it/s, loss=0.702, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  50%|████▉     | 468/938 [00:32<00:32, 14.40it/s, loss=0.702, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  50%|████▉     | 468/938 [00:32<00:32, 14.39it/s, loss=0.693, v_num=9, val_rmse=0.568, train_rmse=0.764]
Epoch 2:  50%|█████     | 469/938 [00:32<00:32, 14.40it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]
Epoch 2:  50%|█████     | 472/938 [00:32<00:32, 14.45it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:   1%|          | 3/469 [00:00<00:22, 20.65it/s]

Validating:   1%|▏         | 6/469 [00:00<00:19, 23.46it/s]
Epoch 2:  51%|█████     | 476/938 [00:32<00:31, 14.50it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:   2%|▏         | 9/469 [00:00<00:18, 25.27it/s]
Epoch 2:  51%|█████     | 480/938 [00:32<00:31, 14.56it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:   3%|▎         | 12/469 [00:00<00:17, 25.53it/s]
Epoch 2:  52%|█████▏    | 484/938 [00:33<00:31, 14.61it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:   3%|▎         | 15/469 [00:00<00:17, 26.32it/s]

Validating:   4%|▍         | 18/469 [00:00<00:17, 25.93it/s]
Epoch 2:  52%|█████▏    | 488/938 [00:33<00:30, 14.67it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:   4%|▍         | 21/469 [00:00<00:17, 25.97it/s]
Epoch 2:  52%|█████▏    | 492/938 [00:33<00:30, 14.72it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:   5%|▌         | 24/469 [00:00<00:16, 26.33it/s]
Epoch 2:  53%|█████▎    | 496/938 [00:33<00:29, 14.77it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:   6%|▌         | 27/469 [00:01<00:16, 26.10it/s]

Validating:   6%|▋         | 30/469 [00:01<00:17, 25.41it/s]
Epoch 2:  53%|█████▎    | 500/938 [00:33<00:29, 14.82it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:   7%|▋         | 33/469 [00:01<00:17, 24.51it/s]
Epoch 2:  54%|█████▎    | 504/938 [00:33<00:29, 14.86it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:   8%|▊         | 36/469 [00:01<00:16, 25.90it/s]
Epoch 2:  54%|█████▍    | 508/938 [00:34<00:28, 14.92it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:   8%|▊         | 39/469 [00:01<00:16, 25.61it/s]

Validating:   9%|▉         | 42/469 [00:01<00:16, 25.22it/s]
Epoch 2:  55%|█████▍    | 512/938 [00:34<00:28, 14.96it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  10%|▉         | 45/469 [00:01<00:16, 25.19it/s]
Epoch 2:  55%|█████▌    | 516/938 [00:34<00:28, 15.01it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  10%|█         | 48/469 [00:01<00:16, 24.99it/s]
Epoch 2:  55%|█████▌    | 520/938 [00:34<00:27, 15.05it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  11%|█         | 51/469 [00:02<00:16, 25.11it/s]

Validating:  12%|█▏        | 54/469 [00:02<00:15, 26.07it/s]
Epoch 2:  56%|█████▌    | 524/938 [00:34<00:27, 15.11it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  12%|█▏        | 57/469 [00:02<00:15, 26.26it/s]
Epoch 2:  56%|█████▋    | 528/938 [00:34<00:27, 15.16it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  13%|█▎        | 60/469 [00:02<00:16, 25.31it/s]
Epoch 2:  57%|█████▋    | 532/938 [00:35<00:26, 15.20it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  13%|█▎        | 63/469 [00:02<00:16, 24.67it/s]

Validating:  14%|█▍        | 66/469 [00:02<00:16, 24.88it/s]
Epoch 2:  57%|█████▋    | 536/938 [00:35<00:26, 15.24it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  15%|█▍        | 69/469 [00:02<00:15, 25.12it/s]
Epoch 2:  58%|█████▊    | 540/938 [00:35<00:26, 15.29it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  15%|█▌        | 72/469 [00:02<00:15, 25.28it/s]
Epoch 2:  58%|█████▊    | 544/938 [00:35<00:25, 15.34it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  16%|█▌        | 75/469 [00:02<00:15, 25.95it/s]

Validating:  17%|█▋        | 78/469 [00:03<00:15, 25.23it/s]
Epoch 2:  58%|█████▊    | 548/938 [00:35<00:25, 15.38it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  17%|█▋        | 81/469 [00:03<00:14, 26.26it/s]
Epoch 2:  59%|█████▉    | 552/938 [00:35<00:25, 15.43it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  18%|█▊        | 84/469 [00:03<00:14, 25.67it/s]
Epoch 2:  59%|█████▉    | 556/938 [00:35<00:24, 15.47it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  19%|█▊        | 87/469 [00:03<00:14, 25.70it/s]

Validating:  19%|█▉        | 90/469 [00:03<00:15, 23.71it/s]
Epoch 2:  60%|█████▉    | 560/938 [00:36<00:24, 15.50it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  20%|█▉        | 93/469 [00:03<00:15, 24.48it/s]
Epoch 2:  60%|██████    | 564/938 [00:36<00:24, 15.55it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  20%|██        | 96/469 [00:03<00:16, 23.21it/s]
Epoch 2:  61%|██████    | 568/938 [00:36<00:23, 15.58it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  21%|██        | 99/469 [00:03<00:15, 24.02it/s]

Validating:  22%|██▏       | 102/469 [00:04<00:14, 24.75it/s]
Epoch 2:  61%|██████    | 572/938 [00:36<00:23, 15.62it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  22%|██▏       | 105/469 [00:04<00:14, 25.01it/s]
Epoch 2:  61%|██████▏   | 576/938 [00:36<00:23, 15.66it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  23%|██▎       | 108/469 [00:04<00:14, 24.43it/s]
Epoch 2:  62%|██████▏   | 580/938 [00:36<00:22, 15.69it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  24%|██▎       | 111/469 [00:04<00:15, 23.65it/s]

Validating:  24%|██▍       | 114/469 [00:04<00:14, 24.30it/s]
Epoch 2:  62%|██████▏   | 584/938 [00:37<00:22, 15.73it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  25%|██▍       | 117/469 [00:04<00:14, 24.59it/s]
Epoch 2:  63%|██████▎   | 588/938 [00:37<00:22, 15.78it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  26%|██▌       | 120/469 [00:04<00:14, 23.93it/s]
Epoch 2:  63%|██████▎   | 592/938 [00:37<00:21, 15.81it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  26%|██▌       | 123/469 [00:04<00:14, 23.08it/s]

Validating:  27%|██▋       | 126/469 [00:05<00:14, 23.56it/s]
Epoch 2:  64%|██████▎   | 596/938 [00:37<00:21, 15.84it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  28%|██▊       | 129/469 [00:05<00:14, 23.31it/s]
Epoch 2:  64%|██████▍   | 600/938 [00:37<00:21, 15.87it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  28%|██▊       | 132/469 [00:05<00:15, 21.78it/s]
Epoch 2:  64%|██████▍   | 604/938 [00:38<00:21, 15.89it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  29%|██▉       | 135/469 [00:05<00:14, 22.49it/s]

Validating:  29%|██▉       | 138/469 [00:05<00:14, 22.24it/s]
Epoch 2:  65%|██████▍   | 608/938 [00:38<00:20, 15.92it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  30%|███       | 141/469 [00:05<00:14, 23.25it/s]
Epoch 2:  65%|██████▌   | 612/938 [00:38<00:20, 15.96it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  31%|███       | 144/469 [00:05<00:13, 24.04it/s]
Epoch 2:  66%|██████▌   | 616/938 [00:38<00:20, 16.00it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  31%|███▏      | 147/469 [00:05<00:13, 23.44it/s]

Validating:  32%|███▏      | 150/469 [00:06<00:13, 23.52it/s]
Epoch 2:  66%|██████▌   | 620/938 [00:38<00:19, 16.03it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  33%|███▎      | 153/469 [00:06<00:13, 22.71it/s]
Epoch 2:  67%|██████▋   | 624/938 [00:38<00:19, 16.05it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  33%|███▎      | 156/469 [00:06<00:14, 21.45it/s]
Epoch 2:  67%|██████▋   | 628/938 [00:39<00:19, 16.08it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  34%|███▍      | 159/469 [00:06<00:13, 22.52it/s]

Validating:  35%|███▍      | 162/469 [00:06<00:13, 23.31it/s]
Epoch 2:  67%|██████▋   | 632/938 [00:39<00:18, 16.12it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  35%|███▌      | 165/469 [00:06<00:13, 22.98it/s]
Epoch 2:  68%|██████▊   | 636/938 [00:39<00:18, 16.15it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  36%|███▌      | 168/469 [00:06<00:12, 23.87it/s]
Epoch 2:  68%|██████▊   | 640/938 [00:39<00:18, 16.18it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  36%|███▋      | 171/469 [00:07<00:12, 23.86it/s]

Validating:  37%|███▋      | 174/469 [00:07<00:11, 24.93it/s]
Epoch 2:  69%|██████▊   | 644/938 [00:39<00:18, 16.22it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  38%|███▊      | 177/469 [00:07<00:11, 24.43it/s]
Epoch 2:  69%|██████▉   | 648/938 [00:39<00:17, 16.25it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  38%|███▊      | 180/469 [00:07<00:12, 22.26it/s]
Epoch 2:  70%|██████▉   | 652/938 [00:40<00:17, 16.27it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  39%|███▉      | 183/469 [00:07<00:12, 22.96it/s]

Validating:  40%|███▉      | 186/469 [00:07<00:12, 23.47it/s]
Epoch 2:  70%|██████▉   | 656/938 [00:40<00:17, 16.31it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  40%|████      | 189/469 [00:07<00:11, 23.91it/s]
Epoch 2:  70%|███████   | 660/938 [00:40<00:17, 16.34it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  41%|████      | 192/469 [00:07<00:11, 24.13it/s]
Epoch 2:  71%|███████   | 664/938 [00:40<00:16, 16.37it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  42%|████▏     | 195/469 [00:08<00:11, 24.33it/s]

Validating:  42%|████▏     | 198/469 [00:08<00:11, 24.21it/s]
Epoch 2:  71%|███████   | 668/938 [00:40<00:16, 16.41it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  43%|████▎     | 201/469 [00:08<00:11, 23.69it/s]
Epoch 2:  72%|███████▏  | 672/938 [00:40<00:16, 16.44it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  43%|████▎     | 204/469 [00:08<00:10, 24.39it/s]
Epoch 2:  72%|███████▏  | 676/938 [00:41<00:15, 16.47it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  44%|████▍     | 207/469 [00:08<00:10, 24.48it/s]

Validating:  45%|████▍     | 210/469 [00:08<00:10, 24.51it/s]
Epoch 2:  72%|███████▏  | 680/938 [00:41<00:15, 16.50it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  45%|████▌     | 213/469 [00:08<00:10, 24.34it/s]
Epoch 2:  73%|███████▎  | 684/938 [00:41<00:15, 16.54it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  46%|████▌     | 216/469 [00:08<00:10, 24.13it/s]
Epoch 2:  73%|███████▎  | 688/938 [00:41<00:15, 16.56it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  47%|████▋     | 219/469 [00:09<00:10, 23.58it/s]

Validating:  47%|████▋     | 222/469 [00:09<00:11, 22.38it/s]
Epoch 2:  74%|███████▍  | 692/938 [00:41<00:14, 16.58it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  48%|████▊     | 225/469 [00:09<00:10, 22.84it/s]
Epoch 2:  74%|███████▍  | 696/938 [00:41<00:14, 16.61it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  49%|████▊     | 228/469 [00:09<00:10, 23.30it/s]
Epoch 2:  75%|███████▍  | 700/938 [00:42<00:14, 16.64it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  49%|████▉     | 231/469 [00:09<00:10, 23.78it/s]

Validating:  50%|████▉     | 234/469 [00:09<00:09, 24.07it/s]
Epoch 2:  75%|███████▌  | 704/938 [00:42<00:14, 16.67it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  51%|█████     | 237/469 [00:09<00:09, 24.16it/s]
Epoch 2:  75%|███████▌  | 708/938 [00:42<00:13, 16.70it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  51%|█████     | 240/469 [00:09<00:09, 23.60it/s]
Epoch 2:  76%|███████▌  | 712/938 [00:42<00:13, 16.73it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  52%|█████▏    | 243/469 [00:10<00:09, 24.10it/s]

Validating:  52%|█████▏    | 246/469 [00:10<00:09, 24.38it/s]
Epoch 2:  76%|███████▋  | 716/938 [00:42<00:13, 16.76it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  53%|█████▎    | 249/469 [00:10<00:08, 24.83it/s]
Epoch 2:  77%|███████▋  | 720/938 [00:42<00:12, 16.79it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  54%|█████▎    | 252/469 [00:10<00:08, 25.05it/s]
Epoch 2:  77%|███████▋  | 724/938 [00:43<00:12, 16.82it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  54%|█████▍    | 255/469 [00:10<00:08, 24.22it/s]

Validating:  55%|█████▌    | 258/469 [00:10<00:09, 23.38it/s]
Epoch 2:  78%|███████▊  | 728/938 [00:43<00:12, 16.84it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  56%|█████▌    | 261/469 [00:10<00:09, 22.00it/s]
Epoch 2:  78%|███████▊  | 732/938 [00:43<00:12, 16.85it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  56%|█████▋    | 264/469 [00:10<00:09, 20.66it/s]
Epoch 2:  78%|███████▊  | 736/938 [00:43<00:11, 16.87it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  57%|█████▋    | 267/469 [00:11<00:09, 21.37it/s]

Validating:  58%|█████▊    | 270/469 [00:11<00:09, 20.61it/s]
Epoch 2:  79%|███████▉  | 740/938 [00:43<00:11, 16.88it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  58%|█████▊    | 273/469 [00:11<00:09, 21.57it/s]
Epoch 2:  79%|███████▉  | 744/938 [00:44<00:11, 16.91it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  59%|█████▉    | 276/469 [00:11<00:08, 22.62it/s]
Epoch 2:  80%|███████▉  | 748/938 [00:44<00:11, 16.94it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  59%|█████▉    | 279/469 [00:11<00:07, 23.88it/s]

Validating:  60%|██████    | 282/469 [00:11<00:07, 24.85it/s]
Epoch 2:  80%|████████  | 752/938 [00:44<00:10, 16.98it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  61%|██████    | 285/469 [00:11<00:07, 24.49it/s]
Epoch 2:  81%|████████  | 756/938 [00:44<00:10, 17.00it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  61%|██████▏   | 288/469 [00:12<00:07, 23.58it/s]
Epoch 2:  81%|████████  | 760/938 [00:44<00:10, 17.02it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  62%|██████▏   | 291/469 [00:12<00:07, 23.55it/s]

Validating:  63%|██████▎   | 294/469 [00:12<00:07, 24.00it/s]
Epoch 2:  81%|████████▏ | 764/938 [00:44<00:10, 17.05it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  63%|██████▎   | 297/469 [00:12<00:06, 24.73it/s]
Epoch 2:  82%|████████▏ | 768/938 [00:44<00:09, 17.08it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  64%|██████▍   | 300/469 [00:12<00:06, 25.03it/s]
Epoch 2:  82%|████████▏ | 772/938 [00:45<00:09, 17.11it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  65%|██████▍   | 303/469 [00:12<00:06, 25.44it/s]

Validating:  65%|██████▌   | 306/469 [00:12<00:06, 26.06it/s]
Epoch 2:  83%|████████▎ | 776/938 [00:45<00:09, 17.14it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  66%|██████▌   | 309/469 [00:12<00:06, 26.03it/s]
Epoch 2:  83%|████████▎ | 780/938 [00:45<00:09, 17.17it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  67%|██████▋   | 312/469 [00:12<00:06, 25.46it/s]
Epoch 2:  84%|████████▎ | 784/938 [00:45<00:08, 17.20it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  67%|██████▋   | 315/469 [00:13<00:05, 25.68it/s]

Validating:  68%|██████▊   | 318/469 [00:13<00:05, 25.61it/s]
Epoch 2:  84%|████████▍ | 788/938 [00:45<00:08, 17.23it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  68%|██████▊   | 321/469 [00:13<00:05, 25.79it/s]
Epoch 2:  84%|████████▍ | 792/938 [00:45<00:08, 17.26it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  69%|██████▉   | 324/469 [00:13<00:05, 24.82it/s]
Epoch 2:  85%|████████▍ | 796/938 [00:46<00:08, 17.28it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  70%|██████▉   | 327/469 [00:13<00:05, 24.87it/s]

Validating:  70%|███████   | 330/469 [00:13<00:05, 25.28it/s]
Epoch 2:  85%|████████▌ | 800/938 [00:46<00:07, 17.31it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  71%|███████   | 333/469 [00:13<00:05, 25.06it/s]
Epoch 2:  86%|████████▌ | 804/938 [00:46<00:07, 17.34it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  72%|███████▏  | 336/469 [00:13<00:05, 25.22it/s]
Epoch 2:  86%|████████▌ | 808/938 [00:46<00:07, 17.37it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  72%|███████▏  | 339/469 [00:14<00:05, 25.41it/s]

Validating:  73%|███████▎  | 342/469 [00:14<00:05, 25.05it/s]
Epoch 2:  87%|████████▋ | 812/938 [00:46<00:07, 17.39it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  74%|███████▎  | 345/469 [00:14<00:04, 25.39it/s]
Epoch 2:  87%|████████▋ | 816/938 [00:46<00:07, 17.42it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  74%|███████▍  | 348/469 [00:14<00:04, 25.56it/s]
Epoch 2:  87%|████████▋ | 820/938 [00:47<00:06, 17.44it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  75%|███████▍  | 351/469 [00:14<00:04, 24.91it/s]

Validating:  75%|███████▌  | 354/469 [00:14<00:04, 25.08it/s]
Epoch 2:  88%|████████▊ | 824/938 [00:47<00:06, 17.47it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  76%|███████▌  | 357/469 [00:14<00:04, 25.94it/s]
Epoch 2:  88%|████████▊ | 828/938 [00:47<00:06, 17.50it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  77%|███████▋  | 360/469 [00:14<00:04, 26.39it/s]
Epoch 2:  89%|████████▊ | 832/938 [00:47<00:06, 17.53it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  77%|███████▋  | 363/469 [00:14<00:04, 26.11it/s]

Validating:  78%|███████▊  | 366/469 [00:15<00:04, 24.58it/s]
Epoch 2:  89%|████████▉ | 836/938 [00:47<00:05, 17.55it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  79%|███████▊  | 369/469 [00:15<00:04, 24.41it/s]
Epoch 2:  90%|████████▉ | 840/938 [00:47<00:05, 17.57it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  79%|███████▉  | 372/469 [00:15<00:03, 24.86it/s]
Epoch 2:  90%|████████▉ | 844/938 [00:47<00:05, 17.60it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  80%|███████▉  | 375/469 [00:15<00:03, 24.52it/s]

Validating:  81%|████████  | 378/469 [00:15<00:03, 25.35it/s]
Epoch 2:  90%|█████████ | 848/938 [00:48<00:05, 17.62it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  81%|████████  | 381/469 [00:15<00:03, 24.70it/s]
Epoch 2:  91%|█████████ | 852/938 [00:48<00:04, 17.64it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  82%|████████▏ | 384/469 [00:15<00:03, 23.94it/s]
Epoch 2:  91%|█████████▏| 856/938 [00:48<00:04, 17.67it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  83%|████████▎ | 387/469 [00:15<00:03, 25.09it/s]

Validating:  83%|████████▎ | 390/469 [00:16<00:03, 25.26it/s]
Epoch 2:  92%|█████████▏| 860/938 [00:48<00:04, 17.69it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  84%|████████▍ | 393/469 [00:16<00:03, 24.53it/s]
Epoch 2:  92%|█████████▏| 864/938 [00:48<00:04, 17.71it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  84%|████████▍ | 396/469 [00:16<00:03, 24.13it/s]
Epoch 2:  93%|█████████▎| 868/938 [00:48<00:03, 17.73it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  85%|████████▌ | 399/469 [00:16<00:02, 24.48it/s]

Validating:  86%|████████▌ | 402/469 [00:16<00:02, 25.66it/s]
Epoch 2:  93%|█████████▎| 872/938 [00:49<00:03, 17.77it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  86%|████████▋ | 405/469 [00:16<00:02, 24.35it/s]
Epoch 2:  93%|█████████▎| 876/938 [00:49<00:03, 17.78it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  87%|████████▋ | 408/469 [00:16<00:02, 23.97it/s]
Epoch 2:  94%|█████████▍| 880/938 [00:49<00:03, 17.80it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  88%|████████▊ | 411/469 [00:16<00:02, 24.75it/s]

Validating:  88%|████████▊ | 414/469 [00:17<00:02, 24.67it/s]
Epoch 2:  94%|█████████▍| 884/938 [00:49<00:03, 17.83it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  89%|████████▉ | 417/469 [00:17<00:02, 25.06it/s]
Epoch 2:  95%|█████████▍| 888/938 [00:49<00:02, 17.85it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  90%|████████▉ | 420/469 [00:17<00:01, 25.84it/s]
Epoch 2:  95%|█████████▌| 892/938 [00:49<00:02, 17.88it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  90%|█████████ | 423/469 [00:17<00:01, 25.10it/s]

Validating:  91%|█████████ | 426/469 [00:17<00:01, 24.22it/s]
Epoch 2:  96%|█████████▌| 896/938 [00:50<00:02, 17.89it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  91%|█████████▏| 429/469 [00:17<00:01, 24.30it/s]
Epoch 2:  96%|█████████▌| 900/938 [00:50<00:02, 17.92it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  92%|█████████▏| 432/469 [00:17<00:01, 24.37it/s]
Epoch 2:  96%|█████████▋| 904/938 [00:50<00:01, 17.94it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  93%|█████████▎| 435/469 [00:17<00:01, 24.49it/s]

Validating:  93%|█████████▎| 438/469 [00:17<00:01, 24.56it/s]
Epoch 2:  97%|█████████▋| 908/938 [00:50<00:01, 17.96it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  94%|█████████▍| 441/469 [00:18<00:01, 25.13it/s]
Epoch 2:  97%|█████████▋| 912/938 [00:50<00:01, 17.98it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  95%|█████████▍| 444/469 [00:18<00:01, 24.66it/s]
Epoch 2:  98%|█████████▊| 916/938 [00:50<00:01, 18.01it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  95%|█████████▌| 447/469 [00:18<00:00, 25.52it/s]

Validating:  96%|█████████▌| 450/469 [00:18<00:00, 26.13it/s]
Epoch 2:  98%|█████████▊| 920/938 [00:51<00:00, 18.03it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  97%|█████████▋| 453/469 [00:18<00:00, 25.69it/s]
Epoch 2:  99%|█████████▊| 924/938 [00:51<00:00, 18.05it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  97%|█████████▋| 456/469 [00:18<00:00, 25.44it/s]
Epoch 2:  99%|█████████▉| 928/938 [00:51<00:00, 18.08it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  98%|█████████▊| 459/469 [00:18<00:00, 25.86it/s]

Validating:  99%|█████████▊| 462/469 [00:18<00:00, 25.80it/s]
Epoch 2:  99%|█████████▉| 932/938 [00:51<00:00, 18.10it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating:  99%|█████████▉| 465/469 [00:19<00:00, 26.40it/s]
Epoch 2: 100%|█████████▉| 936/938 [00:51<00:00, 18.13it/s, loss=0.689, v_num=9, val_rmse=0.568, train_rmse=0.764]

Validating: 100%|█████████▉| 468/469 [00:19<00:00, 26.14it/s]
Epoch 2: 100%|██████████| 938/938 [00:51<00:00, 18.13it/s, loss=0.689, v_num=9, val_rmse=0.531, train_rmse=0.764]

                                                             
Epoch 2: 100%|██████████| 938/938 [00:51<00:00, 18.12it/s, loss=0.689, v_num=9, val_rmse=0.531, train_rmse=0.694]
Epoch 2: 100%|██████████| 938/938 [00:51<00:00, 18.08it/s, loss=0.689, v_num=9, val_rmse=0.531, train_rmse=0.694]LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]


Testing: 0it [00:00, ?it/s]
Testing:   0%|          | 2/469 [00:00<00:25, 18.34it/s]
Testing:   1%|          | 5/469 [00:00<00:19, 23.54it/s]
Testing:   2%|▏         | 8/469 [00:00<00:19, 23.85it/s]
Testing:   2%|▏         | 11/469 [00:00<00:19, 23.73it/s]
Testing:   3%|▎         | 14/469 [00:00<00:20, 22.55it/s]
Testing:   4%|▎         | 17/469 [00:00<00:19, 23.01it/s]
Testing:   4%|▍         | 20/469 [00:00<00:19, 22.47it/s]
Testing:   5%|▍         | 23/469 [00:01<00:19, 22.76it/s]
Testing:   6%|▌         | 26/469 [00:01<00:19, 23.04it/s]
Testing:   6%|▌         | 29/469 [00:01<00:18, 23.93it/s]
Testing:   7%|▋         | 32/469 [00:01<00:17, 24.82it/s]
Testing:   7%|▋         | 35/469 [00:01<00:17, 25.15it/s]
Testing:   8%|▊         | 38/469 [00:01<00:17, 25.05it/s]
Testing:   9%|▊         | 41/469 [00:01<00:17, 24.62it/s]
Testing:   9%|▉         | 44/469 [00:01<00:17, 24.67it/s]
Testing:  10%|█         | 47/469 [00:01<00:17, 24.40it/s]
Testing:  11%|█         | 50/469 [00:02<00:16, 24.83it/s]
Testing:  11%|█▏        | 53/469 [00:02<00:17, 24.47it/s]
Testing:  12%|█▏        | 56/469 [00:02<00:17, 24.05it/s]
Testing:  13%|█▎        | 59/469 [00:02<00:16, 24.79it/s]
Testing:  13%|█▎        | 62/469 [00:02<00:16, 25.22it/s]
Testing:  14%|█▍        | 65/469 [00:02<00:15, 25.75it/s]
Testing:  14%|█▍        | 68/469 [00:02<00:15, 25.14it/s]
Testing:  15%|█▌        | 71/469 [00:02<00:17, 23.05it/s]
Testing:  16%|█▌        | 74/469 [00:03<00:16, 23.52it/s]
Testing:  16%|█▋        | 77/469 [00:03<00:16, 23.91it/s]
Testing:  17%|█▋        | 80/469 [00:03<00:16, 23.85it/s]
Testing:  18%|█▊        | 83/469 [00:03<00:15, 24.40it/s]
Testing:  18%|█▊        | 86/469 [00:03<00:15, 25.11it/s]
Testing:  19%|█▉        | 89/469 [00:03<00:14, 25.35it/s]
Testing:  20%|█▉        | 92/469 [00:03<00:15, 24.66it/s]
Testing:  20%|██        | 95/469 [00:03<00:15, 24.28it/s]
Testing:  21%|██        | 98/469 [00:04<00:14, 25.27it/s]
Testing:  22%|██▏       | 101/469 [00:04<00:14, 25.09it/s]
Testing:  22%|██▏       | 104/469 [00:04<00:13, 26.27it/s]
Testing:  23%|██▎       | 107/469 [00:04<00:14, 25.74it/s]
Testing:  23%|██▎       | 110/469 [00:04<00:13, 26.11it/s]
Testing:  24%|██▍       | 113/469 [00:04<00:14, 24.16it/s]
Testing:  25%|██▍       | 116/469 [00:04<00:14, 24.03it/s]
Testing:  25%|██▌       | 119/469 [00:04<00:14, 23.93it/s]
Testing:  26%|██▌       | 122/469 [00:05<00:14, 24.14it/s]
Testing:  27%|██▋       | 125/469 [00:05<00:13, 24.67it/s]
Testing:  27%|██▋       | 128/469 [00:05<00:14, 24.28it/s]
Testing:  28%|██▊       | 131/469 [00:05<00:13, 24.33it/s]
Testing:  29%|██▊       | 134/469 [00:05<00:13, 24.83it/s]
Testing:  29%|██▉       | 137/469 [00:05<00:13, 25.17it/s]
Testing:  30%|██▉       | 140/469 [00:05<00:13, 25.17it/s]
Testing:  30%|███       | 143/469 [00:05<00:12, 25.17it/s]
Testing:  31%|███       | 146/469 [00:05<00:12, 25.24it/s]
Testing:  32%|███▏      | 149/469 [00:06<00:12, 24.83it/s]
Testing:  32%|███▏      | 152/469 [00:06<00:12, 25.05it/s]
Testing:  33%|███▎      | 155/469 [00:06<00:12, 25.26it/s]
Testing:  34%|███▎      | 158/469 [00:06<00:12, 25.07it/s]
Testing:  34%|███▍      | 161/469 [00:06<00:12, 25.40it/s]
Testing:  35%|███▍      | 164/469 [00:06<00:11, 25.47it/s]
Testing:  36%|███▌      | 167/469 [00:06<00:12, 24.59it/s]
Testing:  36%|███▌      | 170/469 [00:06<00:12, 24.61it/s]
Testing:  37%|███▋      | 173/469 [00:07<00:11, 25.07it/s]
Testing:  38%|███▊      | 176/469 [00:07<00:12, 23.80it/s]
Testing:  38%|███▊      | 179/469 [00:07<00:11, 24.98it/s]
Testing:  39%|███▉      | 182/469 [00:07<00:11, 25.11it/s]
Testing:  39%|███▉      | 185/469 [00:07<00:11, 25.12it/s]
Testing:  40%|████      | 188/469 [00:07<00:10, 26.02it/s]
Testing:  41%|████      | 191/469 [00:07<00:10, 25.94it/s]
Testing:  41%|████▏     | 194/469 [00:07<00:10, 25.00it/s]
Testing:  42%|████▏     | 197/469 [00:08<00:10, 24.93it/s]
Testing:  43%|████▎     | 200/469 [00:08<00:11, 24.13it/s]
Testing:  43%|████▎     | 203/469 [00:08<00:11, 22.73it/s]
Testing:  44%|████▍     | 206/469 [00:08<00:11, 22.91it/s]
Testing:  45%|████▍     | 209/469 [00:08<00:10, 24.05it/s]
Testing:  45%|████▌     | 212/469 [00:08<00:10, 24.35it/s]
Testing:  46%|████▌     | 215/469 [00:08<00:10, 24.87it/s]
Testing:  46%|████▋     | 218/469 [00:08<00:10, 24.28it/s]
Testing:  47%|████▋     | 221/469 [00:09<00:10, 24.37it/s]
Testing:  48%|████▊     | 224/469 [00:09<00:09, 25.06it/s]
Testing:  48%|████▊     | 227/469 [00:09<00:09, 25.64it/s]
Testing:  49%|████▉     | 230/469 [00:09<00:09, 26.29it/s]
Testing:  50%|████▉     | 233/469 [00:09<00:09, 25.10it/s]
Testing:  50%|█████     | 236/469 [00:09<00:09, 25.51it/s]
Testing:  51%|█████     | 239/469 [00:09<00:09, 25.43it/s]
Testing:  52%|█████▏    | 242/469 [00:09<00:08, 26.07it/s]
Testing:  52%|█████▏    | 245/469 [00:09<00:09, 24.83it/s]
Testing:  53%|█████▎    | 248/469 [00:10<00:08, 25.21it/s]
Testing:  54%|█████▎    | 251/469 [00:10<00:08, 25.26it/s]
Testing:  54%|█████▍    | 254/469 [00:10<00:08, 26.12it/s]
Testing:  55%|█████▍    | 257/469 [00:10<00:08, 25.42it/s]
Testing:  55%|█████▌    | 260/469 [00:10<00:08, 25.49it/s]
Testing:  56%|█████▌    | 263/469 [00:10<00:08, 25.62it/s]
Testing:  57%|█████▋    | 266/469 [00:10<00:07, 25.86it/s]
Testing:  57%|█████▋    | 269/469 [00:10<00:07, 26.47it/s]
Testing:  58%|█████▊    | 272/469 [00:10<00:07, 27.31it/s]
Testing:  59%|█████▊    | 275/469 [00:11<00:07, 26.46it/s]
Testing:  59%|█████▉    | 278/469 [00:11<00:07, 25.88it/s]
Testing:  60%|█████▉    | 281/469 [00:11<00:07, 26.47it/s]
Testing:  61%|██████    | 284/469 [00:11<00:07, 23.57it/s]
Testing:  61%|██████    | 287/469 [00:11<00:07, 23.74it/s]
Testing:  62%|██████▏   | 290/469 [00:11<00:07, 24.25it/s]
Testing:  62%|██████▏   | 293/469 [00:11<00:07, 24.41it/s]
Testing:  63%|██████▎   | 296/469 [00:11<00:07, 24.53it/s]
Testing:  64%|██████▍   | 299/469 [00:12<00:06, 24.71it/s]
Testing:  64%|██████▍   | 302/469 [00:12<00:06, 24.68it/s]
Testing:  65%|██████▌   | 305/469 [00:12<00:06, 25.30it/s]
Testing:  66%|██████▌   | 308/469 [00:12<00:06, 24.42it/s]
Testing:  66%|██████▋   | 311/469 [00:12<00:06, 23.99it/s]
Testing:  67%|██████▋   | 314/469 [00:12<00:06, 23.91it/s]
Testing:  68%|██████▊   | 317/469 [00:12<00:06, 24.29it/s]
Testing:  68%|██████▊   | 320/469 [00:12<00:05, 25.13it/s]
Testing:  69%|██████▉   | 323/469 [00:13<00:05, 24.81it/s]
Testing:  70%|██████▉   | 326/469 [00:13<00:05, 25.29it/s]
Testing:  70%|███████   | 329/469 [00:13<00:05, 25.40it/s]
Testing:  71%|███████   | 332/469 [00:13<00:05, 24.83it/s]
Testing:  71%|███████▏  | 335/469 [00:13<00:05, 24.81it/s]
Testing:  72%|███████▏  | 338/469 [00:13<00:05, 24.06it/s]
Testing:  73%|███████▎  | 341/469 [00:13<00:05, 23.35it/s]
Testing:  73%|███████▎  | 344/469 [00:13<00:05, 24.09it/s]
Testing:  74%|███████▍  | 347/469 [00:14<00:04, 24.79it/s]
Testing:  75%|███████▍  | 350/469 [00:14<00:04, 24.80it/s]
Testing:  75%|███████▌  | 353/469 [00:14<00:04, 24.63it/s]
Testing:  76%|███████▌  | 356/469 [00:14<00:04, 24.38it/s]
Testing:  77%|███████▋  | 359/469 [00:14<00:04, 24.11it/s]
Testing:  77%|███████▋  | 362/469 [00:14<00:04, 24.82it/s]
Testing:  78%|███████▊  | 365/469 [00:14<00:04, 25.18it/s]
Testing:  78%|███████▊  | 368/469 [00:14<00:04, 24.93it/s]
Testing:  79%|███████▉  | 371/469 [00:15<00:03, 24.94it/s]
Testing:  80%|███████▉  | 374/469 [00:15<00:03, 25.29it/s]
Testing:  80%|████████  | 377/469 [00:15<00:03, 24.66it/s]
Testing:  81%|████████  | 380/469 [00:15<00:03, 25.30it/s]
Testing:  82%|████████▏ | 383/469 [00:15<00:03, 25.44it/s]
Testing:  82%|████████▏ | 386/469 [00:15<00:03, 25.33it/s]
Testing:  83%|████████▎ | 389/469 [00:15<00:03, 25.80it/s]
Testing:  84%|████████▎ | 392/469 [00:15<00:03, 25.03it/s]
Testing:  84%|████████▍ | 395/469 [00:15<00:02, 25.25it/s]
Testing:  85%|████████▍ | 398/469 [00:16<00:02, 24.45it/s]
Testing:  86%|████████▌ | 401/469 [00:16<00:02, 24.11it/s]
Testing:  86%|████████▌ | 404/469 [00:16<00:02, 24.98it/s]
Testing:  87%|████████▋ | 407/469 [00:16<00:02, 25.43it/s]
Testing:  87%|████████▋ | 410/469 [00:16<00:02, 25.76it/s]
Testing:  88%|████████▊ | 413/469 [00:16<00:02, 24.51it/s]
Testing:  89%|████████▊ | 416/469 [00:16<00:02, 24.48it/s]
Testing:  89%|████████▉ | 419/469 [00:16<00:02, 24.68it/s]
Testing:  90%|████████▉ | 422/469 [00:17<00:01, 25.27it/s]
Testing:  91%|█████████ | 425/469 [00:17<00:01, 25.37it/s]
Testing:  91%|█████████▏| 428/469 [00:17<00:01, 25.17it/s]
Testing:  92%|█████████▏| 431/469 [00:17<00:01, 24.92it/s]
Testing:  93%|█████████▎| 434/469 [00:17<00:01, 25.05it/s]
Testing:  93%|█████████▎| 437/469 [00:17<00:01, 25.38it/s]
Testing:  94%|█████████▍| 440/469 [00:17<00:01, 26.07it/s]
Testing:  94%|█████████▍| 443/469 [00:17<00:00, 26.21it/s]
Testing:  95%|█████████▌| 446/469 [00:17<00:00, 25.10it/s]
Testing:  96%|█████████▌| 449/469 [00:18<00:00, 24.57it/s]
Testing:  96%|█████████▋| 452/469 [00:18<00:00, 24.99it/s]
Testing:  97%|█████████▋| 455/469 [00:18<00:00, 24.87it/s]
Testing:  98%|█████████▊| 458/469 [00:18<00:00, 24.79it/s]
Testing:  98%|█████████▊| 461/469 [00:18<00:00, 24.35it/s]
Testing:  99%|█████████▉| 464/469 [00:18<00:00, 24.69it/s]
Testing: 100%|█████████▉| 467/469 [00:18<00:00, 25.46it/s]--------------------------------------------------------------------------------
DATALOADER:0 TEST RESULTS
{'test_rmse': 0.5311928987503052}
--------------------------------------------------------------------------------

Testing: 100%|██████████| 469/469 [00:18<00:00, 24.81it/s]
  0%|          | 0/469 [02:54<?, ?it/s]
Global seed set to 45

['p_np'] False
2 1
iupac_vocab_size: 1491
training... 1491

  0%|          | 0/469 [00:00<?, ?it/s]Some weights of the model checkpoint at checkpoints/iupac were not used when initializing GPT2ForSequenceClassification: ['lm_head.weight']
- This IS expected if you are initializing GPT2ForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing GPT2ForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
GPU available: True, used: True
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]

  | Name        | Type                          | Params
--------------------------------------------------------------
0 | transformer | GPT2ForSequenceClassification | 7.1 M 
--------------------------------------------------------------
75.9 K    Trainable params
7.0 M     Non-trainable params
7.1 M     Total params
28.416    Total estimated model params size (MB)

Validation sanity check: 0it [00:00, ?it/s]
Validation sanity check:   0%|          | 0/2 [00:00<?, ?it/s]
                                                              Global seed set to 45


Training: 0it [00:00, ?it/s]
Training:   0%|          | 0/938 [00:00<?, ?it/s]
Epoch 0:   0%|          | 0/938 [00:00<?, ?it/s] 
Epoch 0:   0%|          | 1/938 [00:00<01:36,  9.67it/s]
Epoch 0:   0%|          | 1/938 [00:00<01:37,  9.62it/s, loss=3.41, v_num=10]
Epoch 0:   0%|          | 2/938 [00:00<01:17, 12.07it/s, loss=3.38, v_num=10]
Epoch 0:   0%|          | 3/938 [00:00<01:18, 11.92it/s, loss=3.38, v_num=10]
Epoch 0:   0%|          | 3/938 [00:00<01:18, 11.89it/s, loss=3.42, v_num=10]
Epoch 0:   0%|          | 4/938 [00:00<01:15, 12.32it/s, loss=3.41, v_num=10]
Epoch 0:   1%|          | 5/938 [00:00<01:14, 12.52it/s, loss=3.41, v_num=10]
Epoch 0:   1%|          | 5/938 [00:00<01:14, 12.50it/s, loss=3.38, v_num=10]
Epoch 0:   1%|          | 6/938 [00:00<01:11, 12.97it/s, loss=3.44, v_num=10]
Epoch 0:   1%|          | 7/938 [00:00<01:12, 12.80it/s, loss=3.44, v_num=10]
Epoch 0:   1%|          | 7/938 [00:00<01:12, 12.79it/s, loss=3.43, v_num=10]
Epoch 0:   1%|          | 8/938 [00:00<01:11, 12.96it/s, loss=3.5, v_num=10] 
Epoch 0:   1%|          | 9/938 [00:00<01:11, 12.97it/s, loss=3.5, v_num=10]
Epoch 0:   1%|          | 9/938 [00:00<01:11, 12.96it/s, loss=3.45, v_num=10]
Epoch 0:   1%|          | 10/938 [00:00<01:11, 12.95it/s, loss=3.45, v_num=10]
Epoch 0:   1%|          | 11/938 [00:00<01:10, 13.06it/s, loss=3.45, v_num=10]
Epoch 0:   1%|          | 11/938 [00:00<01:11, 13.05it/s, loss=3.43, v_num=10]
Epoch 0:   1%|▏         | 12/938 [00:00<01:11, 12.86it/s, loss=3.43, v_num=10]
Epoch 0:   1%|▏         | 13/938 [00:01<01:11, 12.90it/s, loss=3.43, v_num=10]
Epoch 0:   1%|▏         | 13/938 [00:01<01:11, 12.89it/s, loss=3.42, v_num=10]
Epoch 0:   1%|▏         | 14/938 [00:01<01:11, 13.01it/s, loss=3.42, v_num=10]
Epoch 0:   2%|▏         | 15/938 [00:01<01:10, 13.10it/s, loss=3.42, v_num=10]
Epoch 0:   2%|▏         | 15/938 [00:01<01:10, 13.10it/s, loss=3.39, v_num=10]
Epoch 0:   2%|▏         | 16/938 [00:01<01:09, 13.20it/s, loss=3.35, v_num=10]
Epoch 0:   2%|▏         | 17/938 [00:01<01:09, 13.24it/s, loss=3.35, v_num=10]
Epoch 0:   2%|▏         | 17/938 [00:01<01:09, 13.24it/s, loss=3.32, v_num=10]
Epoch 0:   2%|▏         | 18/938 [00:01<01:09, 13.19it/s, loss=3.3, v_num=10] 
Epoch 0:   2%|▏         | 19/938 [00:01<01:09, 13.26it/s, loss=3.3, v_num=10]
Epoch 0:   2%|▏         | 19/938 [00:01<01:09, 13.25it/s, loss=3.29, v_num=10]
Epoch 0:   2%|▏         | 20/938 [00:01<01:08, 13.31it/s, loss=3.28, v_num=10]
Epoch 0:   2%|▏         | 21/938 [00:01<01:09, 13.24it/s, loss=3.28, v_num=10]
Epoch 0:   2%|▏         | 21/938 [00:01<01:09, 13.23it/s, loss=3.24, v_num=10]
Epoch 0:   2%|▏         | 22/938 [00:01<01:08, 13.28it/s, loss=3.2, v_num=10] 
Epoch 0:   2%|▏         | 23/938 [00:01<01:08, 13.33it/s, loss=3.2, v_num=10]
Epoch 0:   2%|▏         | 23/938 [00:01<01:08, 13.32it/s, loss=3.15, v_num=10]
Epoch 0:   3%|▎         | 24/938 [00:01<01:08, 13.36it/s, loss=3.1, v_num=10] 
Epoch 0:   3%|▎         | 25/938 [00:01<01:07, 13.50it/s, loss=3.1, v_num=10]
Epoch 0:   3%|▎         | 25/938 [00:01<01:07, 13.50it/s, loss=3.05, v_num=10]
Epoch 0:   3%|▎         | 26/938 [00:01<01:07, 13.53it/s, loss=2.99, v_num=10]
Epoch 0:   3%|▎         | 27/938 [00:01<01:07, 13.54it/s, loss=2.99, v_num=10]
Epoch 0:   3%|▎         | 27/938 [00:01<01:07, 13.54it/s, loss=2.94, v_num=10]
Epoch 0:   3%|▎         | 28/938 [00:02<01:07, 13.57it/s, loss=2.83, v_num=10]
Epoch 0:   3%|▎         | 29/938 [00:02<01:07, 13.40it/s, loss=2.83, v_num=10]
Epoch 0:   3%|▎         | 29/938 [00:02<01:07, 13.40it/s, loss=2.79, v_num=10]
Epoch 0:   3%|▎         | 30/938 [00:02<01:07, 13.44it/s, loss=2.72, v_num=10]
Epoch 0:   3%|▎         | 31/938 [00:02<01:07, 13.43it/s, loss=2.72, v_num=10]
Epoch 0:   3%|▎         | 31/938 [00:02<01:07, 13.43it/s, loss=2.64, v_num=10]
Epoch 0:   3%|▎         | 32/938 [00:02<01:07, 13.50it/s, loss=2.56, v_num=10]
Epoch 0:   4%|▎         | 33/938 [00:02<01:07, 13.42it/s, loss=2.56, v_num=10]
Epoch 0:   4%|▎         | 33/938 [00:02<01:07, 13.41it/s, loss=2.47, v_num=10]
Epoch 0:   4%|▎         | 34/938 [00:02<01:07, 13.41it/s, loss=2.39, v_num=10]
Epoch 0:   4%|▎         | 35/938 [00:02<01:06, 13.49it/s, loss=2.39, v_num=10]
Epoch 0:   4%|▎         | 35/938 [00:02<01:06, 13.48it/s, loss=2.33, v_num=10]
Epoch 0:   4%|▍         | 36/938 [00:02<01:06, 13.47it/s, loss=2.26, v_num=10]
Epoch 0:   4%|▍         | 37/938 [00:02<01:07, 13.39it/s, loss=2.26, v_num=10]
Epoch 0:   4%|▍         | 37/938 [00:02<01:07, 13.39it/s, loss=2.2, v_num=10] 
Epoch 0:   4%|▍         | 38/938 [00:02<01:07, 13.42it/s, loss=2.13, v_num=10]
Epoch 0:   4%|▍         | 39/938 [00:02<01:06, 13.42it/s, loss=2.13, v_num=10]
Epoch 0:   4%|▍         | 39/938 [00:02<01:06, 13.42it/s, loss=2.07, v_num=10]
Epoch 0:   4%|▍         | 40/938 [00:02<01:06, 13.45it/s, loss=2.01, v_num=10]
Epoch 0:   4%|▍         | 41/938 [00:03<01:06, 13.47it/s, loss=2.01, v_num=10]
Epoch 0:   4%|▍         | 41/938 [00:03<01:06, 13.47it/s, loss=1.98, v_num=10]
Epoch 0:   4%|▍         | 42/938 [00:03<01:06, 13.46it/s, loss=1.94, v_num=10]
Epoch 0:   5%|▍         | 43/938 [00:03<01:06, 13.52it/s, loss=1.94, v_num=10]
Epoch 0:   5%|▍         | 43/938 [00:03<01:06, 13.52it/s, loss=1.89, v_num=10]
Epoch 0:   5%|▍         | 44/938 [00:03<01:06, 13.49it/s, loss=1.85, v_num=10]
Epoch 0:   5%|▍         | 45/938 [00:03<01:06, 13.47it/s, loss=1.85, v_num=10]
Epoch 0:   5%|▍         | 45/938 [00:03<01:06, 13.47it/s, loss=1.81, v_num=10]
Epoch 0:   5%|▍         | 46/938 [00:03<01:06, 13.48it/s, loss=1.76, v_num=10]
Epoch 0:   5%|▌         | 47/938 [00:03<01:06, 13.46it/s, loss=1.76, v_num=10]
Epoch 0:   5%|▌         | 47/938 [00:03<01:06, 13.46it/s, loss=1.73, v_num=10]
Epoch 0:   5%|▌         | 48/938 [00:03<01:06, 13.45it/s, loss=1.72, v_num=10]
Epoch 0:   5%|▌         | 49/938 [00:03<01:06, 13.40it/s, loss=1.72, v_num=10]
Epoch 0:   5%|▌         | 49/938 [00:03<01:06, 13.39it/s, loss=1.7, v_num=10] 
Epoch 0:   5%|▌         | 50/938 [00:03<01:06, 13.44it/s, loss=1.67, v_num=10]
Epoch 0:   5%|▌         | 51/938 [00:03<01:06, 13.44it/s, loss=1.67, v_num=10]
Epoch 0:   5%|▌         | 51/938 [00:03<01:06, 13.44it/s, loss=1.66, v_num=10]
Epoch 0:   6%|▌         | 52/938 [00:03<01:06, 13.41it/s, loss=1.65, v_num=10]
Epoch 0:   6%|▌         | 53/938 [00:03<01:06, 13.40it/s, loss=1.65, v_num=10]
Epoch 0:   6%|▌         | 53/938 [00:03<01:06, 13.40it/s, loss=1.66, v_num=10]
Epoch 0:   6%|▌         | 54/938 [00:04<01:06, 13.37it/s, loss=1.65, v_num=10]
Epoch 0:   6%|▌         | 55/938 [00:04<01:06, 13.38it/s, loss=1.65, v_num=10]
Epoch 0:   6%|▌         | 55/938 [00:04<01:06, 13.38it/s, loss=1.64, v_num=10]
Epoch 0:   6%|▌         | 56/938 [00:04<01:05, 13.42it/s, loss=1.65, v_num=10]
Epoch 0:   6%|▌         | 57/938 [00:04<01:05, 13.43it/s, loss=1.65, v_num=10]
Epoch 0:   6%|▌         | 57/938 [00:04<01:05, 13.43it/s, loss=1.65, v_num=10]
Epoch 0:   6%|▌         | 58/938 [00:04<01:05, 13.48it/s, loss=1.67, v_num=10]
Epoch 0:   6%|▋         | 59/938 [00:04<01:05, 13.50it/s, loss=1.67, v_num=10]
Epoch 0:   6%|▋         | 59/938 [00:04<01:05, 13.50it/s, loss=1.67, v_num=10]
Epoch 0:   6%|▋         | 60/938 [00:04<01:05, 13.47it/s, loss=1.66, v_num=10]
Epoch 0:   7%|▋         | 61/938 [00:04<01:04, 13.52it/s, loss=1.66, v_num=10]
Epoch 0:   7%|▋         | 61/938 [00:04<01:04, 13.52it/s, loss=1.64, v_num=10]
Epoch 0:   7%|▋         | 62/938 [00:04<01:04, 13.49it/s, loss=1.64, v_num=10]
Epoch 0:   7%|▋         | 63/938 [00:04<01:04, 13.50it/s, loss=1.64, v_num=10]
Epoch 0:   7%|▋         | 63/938 [00:04<01:04, 13.49it/s, loss=1.63, v_num=10]
Epoch 0:   7%|▋         | 64/938 [00:04<01:04, 13.47it/s, loss=1.64, v_num=10]
Epoch 0:   7%|▋         | 65/938 [00:04<01:04, 13.51it/s, loss=1.64, v_num=10]
Epoch 0:   7%|▋         | 65/938 [00:04<01:04, 13.50it/s, loss=1.67, v_num=10]
Epoch 0:   7%|▋         | 66/938 [00:04<01:04, 13.52it/s, loss=1.68, v_num=10]
Epoch 0:   7%|▋         | 67/938 [00:04<01:04, 13.53it/s, loss=1.68, v_num=10]
Epoch 0:   7%|▋         | 67/938 [00:04<01:04, 13.53it/s, loss=1.67, v_num=10]
Epoch 0:   7%|▋         | 68/938 [00:05<01:04, 13.53it/s, loss=1.68, v_num=10]
Epoch 0:   7%|▋         | 69/938 [00:05<01:04, 13.46it/s, loss=1.68, v_num=10]
Epoch 0:   7%|▋         | 69/938 [00:05<01:04, 13.46it/s, loss=1.67, v_num=10]
Epoch 0:   7%|▋         | 70/938 [00:05<01:04, 13.49it/s, loss=1.68, v_num=10]
Epoch 0:   8%|▊         | 71/938 [00:05<01:04, 13.44it/s, loss=1.68, v_num=10]
Epoch 0:   8%|▊         | 71/938 [00:05<01:04, 13.44it/s, loss=1.69, v_num=10]
Epoch 0:   8%|▊         | 72/938 [00:05<01:04, 13.47it/s, loss=1.7, v_num=10] 
Epoch 0:   8%|▊         | 73/938 [00:05<01:04, 13.49it/s, loss=1.7, v_num=10]
Epoch 0:   8%|▊         | 73/938 [00:05<01:04, 13.49it/s, loss=1.71, v_num=10]
Epoch 0:   8%|▊         | 74/938 [00:05<01:04, 13.47it/s, loss=1.7, v_num=10] 
Epoch 0:   8%|▊         | 75/938 [00:05<01:03, 13.50it/s, loss=1.7, v_num=10]
Epoch 0:   8%|▊         | 75/938 [00:05<01:03, 13.50it/s, loss=1.7, v_num=10]
Epoch 0:   8%|▊         | 76/938 [00:05<01:03, 13.48it/s, loss=1.71, v_num=10]
Epoch 0:   8%|▊         | 77/938 [00:05<01:03, 13.46it/s, loss=1.71, v_num=10]
Epoch 0:   8%|▊         | 77/938 [00:05<01:03, 13.46it/s, loss=1.73, v_num=10]
Epoch 0:   8%|▊         | 78/938 [00:05<01:04, 13.43it/s, loss=1.7, v_num=10] 
Epoch 0:   8%|▊         | 79/938 [00:05<01:03, 13.45it/s, loss=1.7, v_num=10]
Epoch 0:   8%|▊         | 79/938 [00:05<01:03, 13.45it/s, loss=1.7, v_num=10]
Epoch 0:   9%|▊         | 80/938 [00:05<01:03, 13.45it/s, loss=1.72, v_num=10]
Epoch 0:   9%|▊         | 81/938 [00:06<01:03, 13.46it/s, loss=1.72, v_num=10]
Epoch 0:   9%|▊         | 81/938 [00:06<01:03, 13.46it/s, loss=1.72, v_num=10]
Epoch 0:   9%|▊         | 82/938 [00:06<01:03, 13.47it/s, loss=1.72, v_num=10]
Epoch 0:   9%|▉         | 83/938 [00:06<01:03, 13.50it/s, loss=1.72, v_num=10]
Epoch 0:   9%|▉         | 83/938 [00:06<01:03, 13.50it/s, loss=1.74, v_num=10]
Epoch 0:   9%|▉         | 84/938 [00:06<01:03, 13.51it/s, loss=1.73, v_num=10]
Epoch 0:   9%|▉         | 85/938 [00:06<01:03, 13.52it/s, loss=1.73, v_num=10]
Epoch 0:   9%|▉         | 85/938 [00:06<01:03, 13.52it/s, loss=1.71, v_num=10]
Epoch 0:   9%|▉         | 86/938 [00:06<01:02, 13.55it/s, loss=1.71, v_num=10]
Epoch 0:   9%|▉         | 87/938 [00:06<01:02, 13.54it/s, loss=1.71, v_num=10]
Epoch 0:   9%|▉         | 87/938 [00:06<01:02, 13.54it/s, loss=1.71, v_num=10]
Epoch 0:   9%|▉         | 88/938 [00:06<01:02, 13.57it/s, loss=1.69, v_num=10]
Epoch 0:   9%|▉         | 89/938 [00:06<01:02, 13.58it/s, loss=1.69, v_num=10]
Epoch 0:   9%|▉         | 89/938 [00:06<01:02, 13.58it/s, loss=1.7, v_num=10] 
Epoch 0:  10%|▉         | 90/938 [00:06<01:02, 13.57it/s, loss=1.7, v_num=10]
Epoch 0:  10%|▉         | 91/938 [00:06<01:02, 13.59it/s, loss=1.7, v_num=10]
Epoch 0:  10%|▉         | 91/938 [00:06<01:02, 13.59it/s, loss=1.7, v_num=10]
Epoch 0:  10%|▉         | 92/938 [00:06<01:02, 13.53it/s, loss=1.7, v_num=10]
Epoch 0:  10%|▉         | 93/938 [00:06<01:02, 13.51it/s, loss=1.7, v_num=10]
Epoch 0:  10%|▉         | 93/938 [00:06<01:02, 13.51it/s, loss=1.69, v_num=10]
Epoch 0:  10%|█         | 94/938 [00:06<01:02, 13.48it/s, loss=1.71, v_num=10]
Epoch 0:  10%|█         | 95/938 [00:07<01:02, 13.48it/s, loss=1.71, v_num=10]
Epoch 0:  10%|█         | 95/938 [00:07<01:02, 13.48it/s, loss=1.7, v_num=10] 
Epoch 0:  10%|█         | 96/938 [00:07<01:02, 13.50it/s, loss=1.69, v_num=10]
Epoch 0:  10%|█         | 97/938 [00:07<01:02, 13.52it/s, loss=1.69, v_num=10]
Epoch 0:  10%|█         | 97/938 [00:07<01:02, 13.52it/s, loss=1.67, v_num=10]
Epoch 0:  10%|█         | 98/938 [00:07<01:02, 13.52it/s, loss=1.68, v_num=10]
Epoch 0:  11%|█         | 99/938 [00:07<01:02, 13.51it/s, loss=1.68, v_num=10]
Epoch 0:  11%|█         | 99/938 [00:07<01:02, 13.51it/s, loss=1.67, v_num=10]
Epoch 0:  11%|█         | 100/938 [00:07<01:01, 13.54it/s, loss=1.66, v_num=10]
Epoch 0:  11%|█         | 101/938 [00:07<01:01, 13.56it/s, loss=1.66, v_num=10]
Epoch 0:  11%|█         | 101/938 [00:07<01:01, 13.56it/s, loss=1.66, v_num=10]
Epoch 0:  11%|█         | 102/938 [00:07<01:01, 13.60it/s, loss=1.66, v_num=10]
Epoch 0:  11%|█         | 103/938 [00:07<01:01, 13.62it/s, loss=1.66, v_num=10]
Epoch 0:  11%|█         | 103/938 [00:07<01:01, 13.62it/s, loss=1.64, v_num=10]
Epoch 0:  11%|█         | 104/938 [00:07<01:01, 13.63it/s, loss=1.63, v_num=10]
Epoch 0:  11%|█         | 105/938 [00:07<01:01, 13.63it/s, loss=1.63, v_num=10]
Epoch 0:  11%|█         | 105/938 [00:07<01:01, 13.63it/s, loss=1.63, v_num=10]
Epoch 0:  11%|█▏        | 106/938 [00:07<01:00, 13.64it/s, loss=1.64, v_num=10]
Epoch 0:  11%|█▏        | 107/938 [00:07<01:00, 13.65it/s, loss=1.64, v_num=10]
Epoch 0:  11%|█▏        | 107/938 [00:07<01:00, 13.65it/s, loss=1.65, v_num=10]
Epoch 0:  12%|█▏        | 108/938 [00:07<01:00, 13.65it/s, loss=1.65, v_num=10]
Epoch 0:  12%|█▏        | 109/938 [00:07<01:00, 13.66it/s, loss=1.65, v_num=10]
Epoch 0:  12%|█▏        | 109/938 [00:07<01:00, 13.66it/s, loss=1.67, v_num=10]
Epoch 0:  12%|█▏        | 110/938 [00:08<01:00, 13.66it/s, loss=1.67, v_num=10]
Epoch 0:  12%|█▏        | 111/938 [00:08<01:00, 13.65it/s, loss=1.67, v_num=10]
Epoch 0:  12%|█▏        | 111/938 [00:08<01:00, 13.65it/s, loss=1.66, v_num=10]
Epoch 0:  12%|█▏        | 112/938 [00:08<01:00, 13.68it/s, loss=1.65, v_num=10]
Epoch 0:  12%|█▏        | 113/938 [00:08<01:00, 13.57it/s, loss=1.65, v_num=10]
Epoch 0:  12%|█▏        | 113/938 [00:08<01:00, 13.57it/s, loss=1.66, v_num=10]
Epoch 0:  12%|█▏        | 114/938 [00:08<01:00, 13.58it/s, loss=1.66, v_num=10]
Epoch 0:  12%|█▏        | 115/938 [00:08<01:00, 13.58it/s, loss=1.66, v_num=10]
Epoch 0:  12%|█▏        | 115/938 [00:08<01:00, 13.58it/s, loss=1.68, v_num=10]
Epoch 0:  12%|█▏        | 116/938 [00:08<01:00, 13.58it/s, loss=1.68, v_num=10]
Epoch 0:  12%|█▏        | 117/938 [00:08<01:00, 13.59it/s, loss=1.68, v_num=10]
Epoch 0:  12%|█▏        | 117/938 [00:08<01:00, 13.59it/s, loss=1.67, v_num=10]
Epoch 0:  13%|█▎        | 118/938 [00:08<01:00, 13.61it/s, loss=1.67, v_num=10]
Epoch 0:  13%|█▎        | 119/938 [00:08<01:00, 13.62it/s, loss=1.67, v_num=10]
Epoch 0:  13%|█▎        | 119/938 [00:08<01:00, 13.62it/s, loss=1.67, v_num=10]
Epoch 0:  13%|█▎        | 120/938 [00:08<00:59, 13.64it/s, loss=1.67, v_num=10]
Epoch 0:  13%|█▎        | 121/938 [00:08<01:00, 13.61it/s, loss=1.67, v_num=10]
Epoch 0:  13%|█▎        | 121/938 [00:08<01:00, 13.61it/s, loss=1.66, v_num=10]
Epoch 0:  13%|█▎        | 122/938 [00:08<00:59, 13.62it/s, loss=1.66, v_num=10]
Epoch 0:  13%|█▎        | 123/938 [00:09<00:59, 13.61it/s, loss=1.66, v_num=10]
Epoch 0:  13%|█▎        | 123/938 [00:09<00:59, 13.61it/s, loss=1.65, v_num=10]
Epoch 0:  13%|█▎        | 124/938 [00:09<00:59, 13.62it/s, loss=1.66, v_num=10]
Epoch 0:  13%|█▎        | 125/938 [00:09<00:59, 13.59it/s, loss=1.66, v_num=10]
Epoch 0:  13%|█▎        | 125/938 [00:09<00:59, 13.59it/s, loss=1.65, v_num=10]
Epoch 0:  13%|█▎        | 126/938 [00:09<00:59, 13.61it/s, loss=1.66, v_num=10]
Epoch 0:  14%|█▎        | 127/938 [00:09<00:59, 13.60it/s, loss=1.66, v_num=10]
Epoch 0:  14%|█▎        | 127/938 [00:09<00:59, 13.60it/s, loss=1.65, v_num=10]
Epoch 0:  14%|█▎        | 128/938 [00:09<00:59, 13.59it/s, loss=1.66, v_num=10]
Epoch 0:  14%|█▍        | 129/938 [00:09<00:59, 13.60it/s, loss=1.66, v_num=10]
Epoch 0:  14%|█▍        | 129/938 [00:09<00:59, 13.60it/s, loss=1.63, v_num=10]
Epoch 0:  14%|█▍        | 130/938 [00:09<00:59, 13.62it/s, loss=1.61, v_num=10]
Epoch 0:  14%|█▍        | 131/938 [00:09<00:59, 13.60it/s, loss=1.61, v_num=10]
Epoch 0:  14%|█▍        | 131/938 [00:09<00:59, 13.60it/s, loss=1.61, v_num=10]
Epoch 0:  14%|█▍        | 132/938 [00:09<00:59, 13.61it/s, loss=1.6, v_num=10] 
Epoch 0:  14%|█▍        | 133/938 [00:09<00:59, 13.60it/s, loss=1.6, v_num=10]
Epoch 0:  14%|█▍        | 133/938 [00:09<00:59, 13.60it/s, loss=1.58, v_num=10]
Epoch 0:  14%|█▍        | 134/938 [00:09<00:59, 13.60it/s, loss=1.55, v_num=10]
Epoch 0:  14%|█▍        | 135/938 [00:09<00:58, 13.63it/s, loss=1.55, v_num=10]
Epoch 0:  14%|█▍        | 135/938 [00:09<00:58, 13.63it/s, loss=1.53, v_num=10]
Epoch 0:  14%|█▍        | 136/938 [00:09<00:58, 13.62it/s, loss=1.53, v_num=10]
Epoch 0:  15%|█▍        | 137/938 [00:10<00:58, 13.62it/s, loss=1.53, v_num=10]
Epoch 0:  15%|█▍        | 137/938 [00:10<00:58, 13.62it/s, loss=1.52, v_num=10]
Epoch 0:  15%|█▍        | 138/938 [00:10<00:58, 13.61it/s, loss=1.49, v_num=10]
Epoch 0:  15%|█▍        | 139/938 [00:10<00:58, 13.62it/s, loss=1.49, v_num=10]
Epoch 0:  15%|█▍        | 139/938 [00:10<00:58, 13.62it/s, loss=1.47, v_num=10]
Epoch 0:  15%|█▍        | 140/938 [00:10<00:58, 13.61it/s, loss=1.44, v_num=10]
Epoch 0:  15%|█▌        | 141/938 [00:10<00:58, 13.63it/s, loss=1.44, v_num=10]
Epoch 0:  15%|█▌        | 141/938 [00:10<00:58, 13.63it/s, loss=1.42, v_num=10]
Epoch 0:  15%|█▌        | 142/938 [00:10<00:58, 13.63it/s, loss=1.41, v_num=10]
Epoch 0:  15%|█▌        | 143/938 [00:10<00:58, 13.65it/s, loss=1.41, v_num=10]
Epoch 0:  15%|█▌        | 143/938 [00:10<00:58, 13.65it/s, loss=1.4, v_num=10] 
Epoch 0:  15%|█▌        | 144/938 [00:10<00:58, 13.65it/s, loss=1.38, v_num=10]
Epoch 0:  15%|█▌        | 145/938 [00:10<00:58, 13.65it/s, loss=1.38, v_num=10]
Epoch 0:  15%|█▌        | 145/938 [00:10<00:58, 13.65it/s, loss=1.36, v_num=10]
Epoch 0:  16%|█▌        | 146/938 [00:10<00:58, 13.65it/s, loss=1.32, v_num=10]
Epoch 0:  16%|█▌        | 147/938 [00:10<00:57, 13.65it/s, loss=1.32, v_num=10]
Epoch 0:  16%|█▌        | 147/938 [00:10<00:57, 13.65it/s, loss=1.3, v_num=10] 
Epoch 0:  16%|█▌        | 148/938 [00:10<00:57, 13.64it/s, loss=1.28, v_num=10]
Epoch 0:  16%|█▌        | 149/938 [00:10<00:57, 13.66it/s, loss=1.28, v_num=10]
Epoch 0:  16%|█▌        | 149/938 [00:10<00:57, 13.66it/s, loss=1.27, v_num=10]
Epoch 0:  16%|█▌        | 150/938 [00:10<00:57, 13.66it/s, loss=1.27, v_num=10]
Epoch 0:  16%|█▌        | 151/938 [00:11<00:57, 13.67it/s, loss=1.27, v_num=10]
Epoch 0:  16%|█▌        | 151/938 [00:11<00:57, 13.67it/s, loss=1.25, v_num=10]
Epoch 0:  16%|█▌        | 152/938 [00:11<00:57, 13.66it/s, loss=1.24, v_num=10]
Epoch 0:  16%|█▋        | 153/938 [00:11<00:57, 13.66it/s, loss=1.24, v_num=10]
Epoch 0:  16%|█▋        | 153/938 [00:11<00:57, 13.66it/s, loss=1.23, v_num=10]
Epoch 0:  16%|█▋        | 154/938 [00:11<00:57, 13.65it/s, loss=1.23, v_num=10]
Epoch 0:  17%|█▋        | 155/938 [00:11<00:57, 13.67it/s, loss=1.23, v_num=10]
Epoch 0:  17%|█▋        | 155/938 [00:11<00:57, 13.67it/s, loss=1.21, v_num=10]
Epoch 0:  17%|█▋        | 156/938 [00:11<00:57, 13.65it/s, loss=1.18, v_num=10]
Epoch 0:  17%|█▋        | 157/938 [00:11<00:57, 13.65it/s, loss=1.18, v_num=10]
Epoch 0:  17%|█▋        | 157/938 [00:11<00:57, 13.65it/s, loss=1.16, v_num=10]
Epoch 0:  17%|█▋        | 158/938 [00:11<00:57, 13.64it/s, loss=1.16, v_num=10]
Epoch 0:  17%|█▋        | 159/938 [00:11<00:57, 13.66it/s, loss=1.16, v_num=10]
Epoch 0:  17%|█▋        | 159/938 [00:11<00:57, 13.66it/s, loss=1.15, v_num=10]
Epoch 0:  17%|█▋        | 160/938 [00:11<00:56, 13.67it/s, loss=1.14, v_num=10]
Epoch 0:  17%|█▋        | 161/938 [00:11<00:56, 13.68it/s, loss=1.14, v_num=10]
Epoch 0:  17%|█▋        | 161/938 [00:11<00:56, 13.68it/s, loss=1.15, v_num=10]
Epoch 0:  17%|█▋        | 162/938 [00:11<00:56, 13.68it/s, loss=1.14, v_num=10]
Epoch 0:  17%|█▋        | 163/938 [00:11<00:56, 13.68it/s, loss=1.14, v_num=10]
Epoch 0:  17%|█▋        | 163/938 [00:11<00:56, 13.68it/s, loss=1.14, v_num=10]
Epoch 0:  17%|█▋        | 164/938 [00:11<00:56, 13.69it/s, loss=1.14, v_num=10]
Epoch 0:  18%|█▊        | 165/938 [00:12<00:56, 13.70it/s, loss=1.14, v_num=10]
Epoch 0:  18%|█▊        | 165/938 [00:12<00:56, 13.70it/s, loss=1.13, v_num=10]
Epoch 0:  18%|█▊        | 166/938 [00:12<00:56, 13.71it/s, loss=1.13, v_num=10]
Epoch 0:  18%|█▊        | 167/938 [00:12<00:56, 13.70it/s, loss=1.13, v_num=10]
Epoch 0:  18%|█▊        | 167/938 [00:12<00:56, 13.70it/s, loss=1.14, v_num=10]
Epoch 0:  18%|█▊        | 168/938 [00:12<00:56, 13.71it/s, loss=1.13, v_num=10]
Epoch 0:  18%|█▊        | 169/938 [00:12<00:56, 13.72it/s, loss=1.13, v_num=10]
Epoch 0:  18%|█▊        | 169/938 [00:12<00:56, 13.72it/s, loss=1.12, v_num=10]
Epoch 0:  18%|█▊        | 170/938 [00:12<00:55, 13.72it/s, loss=1.11, v_num=10]
Epoch 0:  18%|█▊        | 171/938 [00:12<00:55, 13.73it/s, loss=1.11, v_num=10]
Epoch 0:  18%|█▊        | 171/938 [00:12<00:55, 13.73it/s, loss=1.1, v_num=10] 
Epoch 0:  18%|█▊        | 172/938 [00:12<00:55, 13.73it/s, loss=1.1, v_num=10]
Epoch 0:  18%|█▊        | 173/938 [00:12<00:55, 13.74it/s, loss=1.1, v_num=10]
Epoch 0:  18%|█▊        | 173/938 [00:12<00:55, 13.74it/s, loss=1.09, v_num=10]
Epoch 0:  19%|█▊        | 174/938 [00:12<00:55, 13.73it/s, loss=1.08, v_num=10]
Epoch 0:  19%|█▊        | 175/938 [00:12<00:55, 13.70it/s, loss=1.08, v_num=10]
Epoch 0:  19%|█▊        | 175/938 [00:12<00:55, 13.70it/s, loss=1.07, v_num=10]
Epoch 0:  19%|█▉        | 176/938 [00:12<00:55, 13.71it/s, loss=1.08, v_num=10]
Epoch 0:  19%|█▉        | 177/938 [00:12<00:55, 13.65it/s, loss=1.08, v_num=10]
Epoch 0:  19%|█▉        | 177/938 [00:12<00:55, 13.65it/s, loss=1.09, v_num=10]
Epoch 0:  19%|█▉        | 178/938 [00:13<00:55, 13.63it/s, loss=1.1, v_num=10] 
Epoch 0:  19%|█▉        | 179/938 [00:13<00:55, 13.62it/s, loss=1.1, v_num=10]
Epoch 0:  19%|█▉        | 179/938 [00:13<00:55, 13.62it/s, loss=1.11, v_num=10]
Epoch 0:  19%|█▉        | 180/938 [00:13<00:55, 13.59it/s, loss=1.12, v_num=10]
Epoch 0:  19%|█▉        | 181/938 [00:13<00:55, 13.60it/s, loss=1.12, v_num=10]
Epoch 0:  19%|█▉        | 181/938 [00:13<00:55, 13.60it/s, loss=1.1, v_num=10] 
Epoch 0:  19%|█▉        | 182/938 [00:13<00:55, 13.60it/s, loss=1.09, v_num=10]
Epoch 0:  20%|█▉        | 183/938 [00:13<00:55, 13.60it/s, loss=1.09, v_num=10]
Epoch 0:  20%|█▉        | 183/938 [00:13<00:55, 13.60it/s, loss=1.07, v_num=10]
Epoch 0:  20%|█▉        | 184/938 [00:13<00:55, 13.61it/s, loss=1.07, v_num=10]
Epoch 0:  20%|█▉        | 185/938 [00:13<00:55, 13.62it/s, loss=1.07, v_num=10]
Epoch 0:  20%|█▉        | 185/938 [00:13<00:55, 13.62it/s, loss=1.07, v_num=10]
Epoch 0:  20%|█▉        | 186/938 [00:13<00:55, 13.61it/s, loss=1.07, v_num=10]
Epoch 0:  20%|█▉        | 187/938 [00:13<00:55, 13.62it/s, loss=1.07, v_num=10]
Epoch 0:  20%|█▉        | 187/938 [00:13<00:55, 13.62it/s, loss=1.06, v_num=10]
Epoch 0:  20%|██        | 188/938 [00:13<00:55, 13.63it/s, loss=1.05, v_num=10]
Epoch 0:  20%|██        | 189/938 [00:13<00:54, 13.64it/s, loss=1.05, v_num=10]
Epoch 0:  20%|██        | 189/938 [00:13<00:54, 13.64it/s, loss=1.04, v_num=10]
Epoch 0:  20%|██        | 190/938 [00:13<00:54, 13.64it/s, loss=1.04, v_num=10]
Epoch 0:  20%|██        | 191/938 [00:14<00:54, 13.64it/s, loss=1.04, v_num=10]
Epoch 0:  20%|██        | 191/938 [00:14<00:54, 13.64it/s, loss=1.03, v_num=10]
Epoch 0:  20%|██        | 192/938 [00:14<00:54, 13.63it/s, loss=1.03, v_num=10]
Epoch 0:  21%|██        | 193/938 [00:14<00:54, 13.64it/s, loss=1.03, v_num=10]
Epoch 0:  21%|██        | 193/938 [00:14<00:54, 13.64it/s, loss=1.03, v_num=10]
Epoch 0:  21%|██        | 194/938 [00:14<00:54, 13.64it/s, loss=1.03, v_num=10]
Epoch 0:  21%|██        | 195/938 [00:14<00:54, 13.65it/s, loss=1.03, v_num=10]
Epoch 0:  21%|██        | 195/938 [00:14<00:54, 13.65it/s, loss=1.02, v_num=10]
Epoch 0:  21%|██        | 196/938 [00:14<00:54, 13.65it/s, loss=1.01, v_num=10]
Epoch 0:  21%|██        | 197/938 [00:14<00:54, 13.66it/s, loss=1.01, v_num=10]
Epoch 0:  21%|██        | 197/938 [00:14<00:54, 13.66it/s, loss=1.01, v_num=10]
Epoch 0:  21%|██        | 198/938 [00:14<00:54, 13.65it/s, loss=1, v_num=10]   
Epoch 0:  21%|██        | 199/938 [00:14<00:54, 13.66it/s, loss=1, v_num=10]
Epoch 0:  21%|██        | 199/938 [00:14<00:54, 13.66it/s, loss=0.982, v_num=10]
Epoch 0:  21%|██▏       | 200/938 [00:14<00:53, 13.67it/s, loss=0.965, v_num=10]
Epoch 0:  21%|██▏       | 201/938 [00:14<00:53, 13.68it/s, loss=0.965, v_num=10]
Epoch 0:  21%|██▏       | 201/938 [00:14<00:53, 13.68it/s, loss=0.959, v_num=10]
Epoch 0:  22%|██▏       | 202/938 [00:14<00:53, 13.68it/s, loss=0.962, v_num=10]
Epoch 0:  22%|██▏       | 203/938 [00:14<00:53, 13.68it/s, loss=0.962, v_num=10]
Epoch 0:  22%|██▏       | 203/938 [00:14<00:53, 13.68it/s, loss=0.961, v_num=10]
Epoch 0:  22%|██▏       | 204/938 [00:14<00:53, 13.66it/s, loss=0.96, v_num=10] 
Epoch 0:  22%|██▏       | 205/938 [00:14<00:53, 13.67it/s, loss=0.96, v_num=10]
Epoch 0:  22%|██▏       | 205/938 [00:14<00:53, 13.67it/s, loss=0.949, v_num=10]
Epoch 0:  22%|██▏       | 206/938 [00:15<00:53, 13.67it/s, loss=0.941, v_num=10]
Epoch 0:  22%|██▏       | 207/938 [00:15<00:53, 13.68it/s, loss=0.941, v_num=10]
Epoch 0:  22%|██▏       | 207/938 [00:15<00:53, 13.68it/s, loss=0.944, v_num=10]
Epoch 0:  22%|██▏       | 208/938 [00:15<00:53, 13.68it/s, loss=0.95, v_num=10] 
Epoch 0:  22%|██▏       | 209/938 [00:15<00:53, 13.68it/s, loss=0.95, v_num=10]
Epoch 0:  22%|██▏       | 209/938 [00:15<00:53, 13.68it/s, loss=0.95, v_num=10]
Epoch 0:  22%|██▏       | 210/938 [00:15<00:53, 13.68it/s, loss=0.941, v_num=10]
Epoch 0:  22%|██▏       | 211/938 [00:15<00:53, 13.69it/s, loss=0.941, v_num=10]
Epoch 0:  22%|██▏       | 211/938 [00:15<00:53, 13.69it/s, loss=0.942, v_num=10]
Epoch 0:  23%|██▎       | 212/938 [00:15<00:53, 13.68it/s, loss=0.945, v_num=10]
Epoch 0:  23%|██▎       | 213/938 [00:15<00:52, 13.70it/s, loss=0.945, v_num=10]
Epoch 0:  23%|██▎       | 213/938 [00:15<00:52, 13.70it/s, loss=0.927, v_num=10]
Epoch 0:  23%|██▎       | 214/938 [00:15<00:52, 13.69it/s, loss=0.911, v_num=10]
Epoch 0:  23%|██▎       | 215/938 [00:15<00:52, 13.69it/s, loss=0.911, v_num=10]
Epoch 0:  23%|██▎       | 215/938 [00:15<00:52, 13.69it/s, loss=0.907, v_num=10]
Epoch 0:  23%|██▎       | 216/938 [00:15<00:52, 13.66it/s, loss=0.914, v_num=10]
Epoch 0:  23%|██▎       | 217/938 [00:15<00:52, 13.66it/s, loss=0.914, v_num=10]
Epoch 0:  23%|██▎       | 217/938 [00:15<00:52, 13.66it/s, loss=0.902, v_num=10]
Epoch 0:  23%|██▎       | 218/938 [00:15<00:52, 13.66it/s, loss=0.899, v_num=10]
Epoch 0:  23%|██▎       | 219/938 [00:16<00:52, 13.67it/s, loss=0.899, v_num=10]
Epoch 0:  23%|██▎       | 219/938 [00:16<00:52, 13.67it/s, loss=0.912, v_num=10]
Epoch 0:  23%|██▎       | 220/938 [00:16<00:52, 13.67it/s, loss=0.913, v_num=10]
Epoch 0:  24%|██▎       | 221/938 [00:16<00:52, 13.68it/s, loss=0.913, v_num=10]
Epoch 0:  24%|██▎       | 221/938 [00:16<00:52, 13.67it/s, loss=0.922, v_num=10]
Epoch 0:  24%|██▎       | 222/938 [00:16<00:52, 13.69it/s, loss=0.918, v_num=10]
Epoch 0:  24%|██▍       | 223/938 [00:16<00:52, 13.68it/s, loss=0.918, v_num=10]
Epoch 0:  24%|██▍       | 223/938 [00:16<00:52, 13.68it/s, loss=0.927, v_num=10]
Epoch 0:  24%|██▍       | 224/938 [00:16<00:52, 13.69it/s, loss=0.922, v_num=10]
Epoch 0:  24%|██▍       | 225/938 [00:16<00:52, 13.69it/s, loss=0.922, v_num=10]
Epoch 0:  24%|██▍       | 225/938 [00:16<00:52, 13.69it/s, loss=0.921, v_num=10]
Epoch 0:  24%|██▍       | 226/938 [00:16<00:52, 13.67it/s, loss=0.912, v_num=10]
Epoch 0:  24%|██▍       | 227/938 [00:16<00:52, 13.66it/s, loss=0.912, v_num=10]
Epoch 0:  24%|██▍       | 227/938 [00:16<00:52, 13.66it/s, loss=0.899, v_num=10]
Epoch 0:  24%|██▍       | 228/938 [00:16<00:51, 13.66it/s, loss=0.898, v_num=10]
Epoch 0:  24%|██▍       | 229/938 [00:16<00:51, 13.66it/s, loss=0.898, v_num=10]
Epoch 0:  24%|██▍       | 229/938 [00:16<00:51, 13.66it/s, loss=0.897, v_num=10]
Epoch 0:  25%|██▍       | 230/938 [00:16<00:51, 13.66it/s, loss=0.896, v_num=10]
Epoch 0:  25%|██▍       | 231/938 [00:16<00:51, 13.66it/s, loss=0.896, v_num=10]
Epoch 0:  25%|██▍       | 231/938 [00:16<00:51, 13.66it/s, loss=0.887, v_num=10]
Epoch 0:  25%|██▍       | 232/938 [00:16<00:51, 13.65it/s, loss=0.886, v_num=10]
Epoch 0:  25%|██▍       | 233/938 [00:17<00:51, 13.65it/s, loss=0.886, v_num=10]
Epoch 0:  25%|██▍       | 233/938 [00:17<00:51, 13.65it/s, loss=0.898, v_num=10]
Epoch 0:  25%|██▍       | 234/938 [00:17<00:51, 13.65it/s, loss=0.897, v_num=10]
Epoch 0:  25%|██▌       | 235/938 [00:17<00:51, 13.65it/s, loss=0.897, v_num=10]
Epoch 0:  25%|██▌       | 235/938 [00:17<00:51, 13.65it/s, loss=0.898, v_num=10]
Epoch 0:  25%|██▌       | 236/938 [00:17<00:51, 13.65it/s, loss=0.906, v_num=10]
Epoch 0:  25%|██▌       | 237/938 [00:17<00:51, 13.65it/s, loss=0.906, v_num=10]
Epoch 0:  25%|██▌       | 237/938 [00:17<00:51, 13.65it/s, loss=0.908, v_num=10]
Epoch 0:  25%|██▌       | 238/938 [00:17<00:51, 13.66it/s, loss=0.913, v_num=10]
Epoch 0:  25%|██▌       | 239/938 [00:17<00:51, 13.66it/s, loss=0.913, v_num=10]
Epoch 0:  25%|██▌       | 239/938 [00:17<00:51, 13.66it/s, loss=0.909, v_num=10]
Epoch 0:  26%|██▌       | 240/938 [00:17<00:51, 13.67it/s, loss=0.909, v_num=10]
Epoch 0:  26%|██▌       | 241/938 [00:17<00:51, 13.67it/s, loss=0.909, v_num=10]
Epoch 0:  26%|██▌       | 241/938 [00:17<00:51, 13.67it/s, loss=0.908, v_num=10]
Epoch 0:  26%|██▌       | 242/938 [00:17<00:50, 13.68it/s, loss=0.91, v_num=10] 
Epoch 0:  26%|██▌       | 243/938 [00:17<00:50, 13.68it/s, loss=0.91, v_num=10]
Epoch 0:  26%|██▌       | 243/938 [00:17<00:50, 13.68it/s, loss=0.906, v_num=10]
Epoch 0:  26%|██▌       | 244/938 [00:17<00:50, 13.67it/s, loss=0.901, v_num=10]
Epoch 0:  26%|██▌       | 245/938 [00:17<00:50, 13.66it/s, loss=0.901, v_num=10]
Epoch 0:  26%|██▌       | 245/938 [00:17<00:50, 13.66it/s, loss=0.905, v_num=10]
Epoch 0:  26%|██▌       | 246/938 [00:17<00:50, 13.68it/s, loss=0.898, v_num=10]
Epoch 0:  26%|██▋       | 247/938 [00:18<00:50, 13.68it/s, loss=0.898, v_num=10]
Epoch 0:  26%|██▋       | 247/938 [00:18<00:50, 13.68it/s, loss=0.908, v_num=10]
Epoch 0:  26%|██▋       | 248/938 [00:18<00:50, 13.68it/s, loss=0.906, v_num=10]
Epoch 0:  27%|██▋       | 249/938 [00:18<00:50, 13.70it/s, loss=0.906, v_num=10]
Epoch 0:  27%|██▋       | 249/938 [00:18<00:50, 13.70it/s, loss=0.899, v_num=10]
Epoch 0:  27%|██▋       | 250/938 [00:18<00:50, 13.71it/s, loss=0.891, v_num=10]
Epoch 0:  27%|██▋       | 251/938 [00:18<00:50, 13.71it/s, loss=0.891, v_num=10]
Epoch 0:  27%|██▋       | 251/938 [00:18<00:50, 13.71it/s, loss=0.904, v_num=10]
Epoch 0:  27%|██▋       | 252/938 [00:18<00:50, 13.71it/s, loss=0.901, v_num=10]
Epoch 0:  27%|██▋       | 253/938 [00:18<00:50, 13.70it/s, loss=0.901, v_num=10]
Epoch 0:  27%|██▋       | 253/938 [00:18<00:50, 13.70it/s, loss=0.904, v_num=10]
Epoch 0:  27%|██▋       | 254/938 [00:18<00:50, 13.65it/s, loss=0.905, v_num=10]
Epoch 0:  27%|██▋       | 255/938 [00:18<00:50, 13.66it/s, loss=0.905, v_num=10]
Epoch 0:  27%|██▋       | 255/938 [00:18<00:50, 13.66it/s, loss=0.914, v_num=10]
Epoch 0:  27%|██▋       | 256/938 [00:18<00:49, 13.65it/s, loss=0.9, v_num=10]  
Epoch 0:  27%|██▋       | 257/938 [00:18<00:49, 13.65it/s, loss=0.9, v_num=10]
Epoch 0:  27%|██▋       | 257/938 [00:18<00:49, 13.65it/s, loss=0.897, v_num=10]
Epoch 0:  28%|██▊       | 258/938 [00:18<00:49, 13.65it/s, loss=0.886, v_num=10]
Epoch 0:  28%|██▊       | 259/938 [00:18<00:49, 13.66it/s, loss=0.886, v_num=10]
Epoch 0:  28%|██▊       | 259/938 [00:18<00:49, 13.66it/s, loss=0.886, v_num=10]
Epoch 0:  28%|██▊       | 260/938 [00:19<00:49, 13.67it/s, loss=0.884, v_num=10]
Epoch 0:  28%|██▊       | 261/938 [00:19<00:49, 13.67it/s, loss=0.884, v_num=10]
Epoch 0:  28%|██▊       | 261/938 [00:19<00:49, 13.67it/s, loss=0.885, v_num=10]
Epoch 0:  28%|██▊       | 262/938 [00:19<00:49, 13.67it/s, loss=0.887, v_num=10]
Epoch 0:  28%|██▊       | 263/938 [00:19<00:49, 13.68it/s, loss=0.887, v_num=10]
Epoch 0:  28%|██▊       | 263/938 [00:19<00:49, 13.68it/s, loss=0.903, v_num=10]
Epoch 0:  28%|██▊       | 264/938 [00:19<00:49, 13.67it/s, loss=0.913, v_num=10]
Epoch 0:  28%|██▊       | 265/938 [00:19<00:49, 13.67it/s, loss=0.913, v_num=10]
Epoch 0:  28%|██▊       | 265/938 [00:19<00:49, 13.67it/s, loss=0.912, v_num=10]
Epoch 0:  28%|██▊       | 266/938 [00:19<00:49, 13.68it/s, loss=0.915, v_num=10]
Epoch 0:  28%|██▊       | 267/938 [00:19<00:49, 13.67it/s, loss=0.915, v_num=10]
Epoch 0:  28%|██▊       | 267/938 [00:19<00:49, 13.67it/s, loss=0.913, v_num=10]
Epoch 0:  29%|██▊       | 268/938 [00:19<00:48, 13.67it/s, loss=0.905, v_num=10]
Epoch 0:  29%|██▊       | 269/938 [00:19<00:48, 13.68it/s, loss=0.905, v_num=10]
Epoch 0:  29%|██▊       | 269/938 [00:19<00:48, 13.68it/s, loss=0.909, v_num=10]
Epoch 0:  29%|██▉       | 270/938 [00:19<00:48, 13.68it/s, loss=0.911, v_num=10]
Epoch 0:  29%|██▉       | 271/938 [00:19<00:48, 13.69it/s, loss=0.911, v_num=10]
Epoch 0:  29%|██▉       | 271/938 [00:19<00:48, 13.69it/s, loss=0.907, v_num=10]
Epoch 0:  29%|██▉       | 272/938 [00:19<00:48, 13.69it/s, loss=0.903, v_num=10]
Epoch 0:  29%|██▉       | 273/938 [00:19<00:48, 13.70it/s, loss=0.903, v_num=10]
Epoch 0:  29%|██▉       | 273/938 [00:19<00:48, 13.70it/s, loss=0.896, v_num=10]
Epoch 0:  29%|██▉       | 274/938 [00:19<00:48, 13.71it/s, loss=0.893, v_num=10]
Epoch 0:  29%|██▉       | 275/938 [00:20<00:48, 13.70it/s, loss=0.893, v_num=10]
Epoch 0:  29%|██▉       | 275/938 [00:20<00:48, 13.70it/s, loss=0.882, v_num=10]
Epoch 0:  29%|██▉       | 276/938 [00:20<00:48, 13.70it/s, loss=0.877, v_num=10]
Epoch 0:  30%|██▉       | 277/938 [00:20<00:48, 13.68it/s, loss=0.877, v_num=10]
Epoch 0:  30%|██▉       | 277/938 [00:20<00:48, 13.68it/s, loss=0.89, v_num=10] 
Epoch 0:  30%|██▉       | 278/938 [00:20<00:48, 13.69it/s, loss=0.886, v_num=10]
Epoch 0:  30%|██▉       | 279/938 [00:20<00:48, 13.68it/s, loss=0.886, v_num=10]
Epoch 0:  30%|██▉       | 279/938 [00:20<00:48, 13.68it/s, loss=0.878, v_num=10]
Epoch 0:  30%|██▉       | 280/938 [00:20<00:48, 13.68it/s, loss=0.88, v_num=10] 
Epoch 0:  30%|██▉       | 281/938 [00:20<00:48, 13.67it/s, loss=0.88, v_num=10]
Epoch 0:  30%|██▉       | 281/938 [00:20<00:48, 13.67it/s, loss=0.875, v_num=10]
Epoch 0:  30%|███       | 282/938 [00:20<00:47, 13.67it/s, loss=0.882, v_num=10]
Epoch 0:  30%|███       | 283/938 [00:20<00:47, 13.66it/s, loss=0.882, v_num=10]
Epoch 0:  30%|███       | 283/938 [00:20<00:47, 13.66it/s, loss=0.858, v_num=10]
Epoch 0:  30%|███       | 284/938 [00:20<00:47, 13.66it/s, loss=0.857, v_num=10]
Epoch 0:  30%|███       | 285/938 [00:20<00:47, 13.66it/s, loss=0.857, v_num=10]
Epoch 0:  30%|███       | 285/938 [00:20<00:47, 13.66it/s, loss=0.852, v_num=10]
Epoch 0:  30%|███       | 286/938 [00:20<00:47, 13.65it/s, loss=0.845, v_num=10]
Epoch 0:  31%|███       | 287/938 [00:21<00:47, 13.65it/s, loss=0.845, v_num=10]
Epoch 0:  31%|███       | 287/938 [00:21<00:47, 13.65it/s, loss=0.838, v_num=10]
Epoch 0:  31%|███       | 288/938 [00:21<00:47, 13.66it/s, loss=0.843, v_num=10]
Epoch 0:  31%|███       | 289/938 [00:21<00:47, 13.66it/s, loss=0.843, v_num=10]
Epoch 0:  31%|███       | 289/938 [00:21<00:47, 13.66it/s, loss=0.835, v_num=10]
Epoch 0:  31%|███       | 290/938 [00:21<00:47, 13.66it/s, loss=0.84, v_num=10] 
Epoch 0:  31%|███       | 291/938 [00:21<00:47, 13.66it/s, loss=0.84, v_num=10]
Epoch 0:  31%|███       | 291/938 [00:21<00:47, 13.66it/s, loss=0.832, v_num=10]
Epoch 0:  31%|███       | 292/938 [00:21<00:47, 13.66it/s, loss=0.839, v_num=10]
Epoch 0:  31%|███       | 293/938 [00:21<00:47, 13.67it/s, loss=0.839, v_num=10]
Epoch 0:  31%|███       | 293/938 [00:21<00:47, 13.67it/s, loss=0.835, v_num=10]
Epoch 0:  31%|███▏      | 294/938 [00:21<00:47, 13.67it/s, loss=0.835, v_num=10]
Epoch 0:  31%|███▏      | 295/938 [00:21<00:47, 13.68it/s, loss=0.835, v_num=10]
Epoch 0:  31%|███▏      | 295/938 [00:21<00:47, 13.68it/s, loss=0.838, v_num=10]
Epoch 0:  32%|███▏      | 296/938 [00:21<00:46, 13.67it/s, loss=0.841, v_num=10]
Epoch 0:  32%|███▏      | 297/938 [00:21<00:46, 13.68it/s, loss=0.841, v_num=10]
Epoch 0:  32%|███▏      | 297/938 [00:21<00:46, 13.68it/s, loss=0.826, v_num=10]
Epoch 0:  32%|███▏      | 298/938 [00:21<00:46, 13.67it/s, loss=0.836, v_num=10]
Epoch 0:  32%|███▏      | 299/938 [00:21<00:46, 13.68it/s, loss=0.836, v_num=10]
Epoch 0:  32%|███▏      | 299/938 [00:21<00:46, 13.68it/s, loss=0.842, v_num=10]
Epoch 0:  32%|███▏      | 300/938 [00:21<00:46, 13.68it/s, loss=0.836, v_num=10]
Epoch 0:  32%|███▏      | 301/938 [00:22<00:46, 13.68it/s, loss=0.836, v_num=10]
Epoch 0:  32%|███▏      | 301/938 [00:22<00:46, 13.68it/s, loss=0.832, v_num=10]
Epoch 0:  32%|███▏      | 302/938 [00:22<00:46, 13.68it/s, loss=0.815, v_num=10]
Epoch 0:  32%|███▏      | 303/938 [00:22<00:46, 13.69it/s, loss=0.815, v_num=10]
Epoch 0:  32%|███▏      | 303/938 [00:22<00:46, 13.69it/s, loss=0.825, v_num=10]
Epoch 0:  32%|███▏      | 304/938 [00:22<00:46, 13.70it/s, loss=0.82, v_num=10] 
Epoch 0:  33%|███▎      | 305/938 [00:22<00:46, 13.69it/s, loss=0.82, v_num=10]
Epoch 0:  33%|███▎      | 305/938 [00:22<00:46, 13.69it/s, loss=0.812, v_num=10]
Epoch 0:  33%|███▎      | 306/938 [00:22<00:46, 13.70it/s, loss=0.825, v_num=10]
Epoch 0:  33%|███▎      | 307/938 [00:22<00:46, 13.69it/s, loss=0.825, v_num=10]
Epoch 0:  33%|███▎      | 307/938 [00:22<00:46, 13.69it/s, loss=0.827, v_num=10]
Epoch 0:  33%|███▎      | 308/938 [00:22<00:46, 13.69it/s, loss=0.82, v_num=10] 
Epoch 0:  33%|███▎      | 309/938 [00:22<00:45, 13.70it/s, loss=0.82, v_num=10]
Epoch 0:  33%|███▎      | 309/938 [00:22<00:45, 13.70it/s, loss=0.829, v_num=10]
Epoch 0:  33%|███▎      | 310/938 [00:22<00:45, 13.70it/s, loss=0.825, v_num=10]
Epoch 0:  33%|███▎      | 311/938 [00:22<00:45, 13.69it/s, loss=0.825, v_num=10]
Epoch 0:  33%|███▎      | 311/938 [00:22<00:45, 13.69it/s, loss=0.829, v_num=10]
Epoch 0:  33%|███▎      | 312/938 [00:22<00:45, 13.69it/s, loss=0.82, v_num=10] 
Epoch 0:  33%|███▎      | 313/938 [00:22<00:45, 13.70it/s, loss=0.82, v_num=10]
Epoch 0:  33%|███▎      | 313/938 [00:22<00:45, 13.69it/s, loss=0.817, v_num=10]
Epoch 0:  33%|███▎      | 314/938 [00:22<00:45, 13.69it/s, loss=0.819, v_num=10]
Epoch 0:  34%|███▎      | 315/938 [00:23<00:45, 13.69it/s, loss=0.819, v_num=10]
Epoch 0:  34%|███▎      | 315/938 [00:23<00:45, 13.69it/s, loss=0.809, v_num=10]
Epoch 0:  34%|███▎      | 316/938 [00:23<00:45, 13.68it/s, loss=0.803, v_num=10]
Epoch 0:  34%|███▍      | 317/938 [00:23<00:45, 13.69it/s, loss=0.803, v_num=10]
Epoch 0:  34%|███▍      | 317/938 [00:23<00:45, 13.69it/s, loss=0.802, v_num=10]
Epoch 0:  34%|███▍      | 318/938 [00:23<00:45, 13.68it/s, loss=0.792, v_num=10]
Epoch 0:  34%|███▍      | 319/938 [00:23<00:45, 13.69it/s, loss=0.792, v_num=10]
Epoch 0:  34%|███▍      | 319/938 [00:23<00:45, 13.69it/s, loss=0.786, v_num=10]
Epoch 0:  34%|███▍      | 320/938 [00:23<00:45, 13.69it/s, loss=0.8, v_num=10]  
Epoch 0:  34%|███▍      | 321/938 [00:23<00:45, 13.69it/s, loss=0.8, v_num=10]
Epoch 0:  34%|███▍      | 321/938 [00:23<00:45, 13.69it/s, loss=0.804, v_num=10]
Epoch 0:  34%|███▍      | 322/938 [00:23<00:45, 13.69it/s, loss=0.803, v_num=10]
Epoch 0:  34%|███▍      | 323/938 [00:23<00:44, 13.68it/s, loss=0.803, v_num=10]
Epoch 0:  34%|███▍      | 323/938 [00:23<00:44, 13.68it/s, loss=0.798, v_num=10]
Epoch 0:  35%|███▍      | 324/938 [00:23<00:44, 13.69it/s, loss=0.811, v_num=10]
Epoch 0:  35%|███▍      | 325/938 [00:23<00:44, 13.69it/s, loss=0.811, v_num=10]
Epoch 0:  35%|███▍      | 325/938 [00:23<00:44, 13.69it/s, loss=0.822, v_num=10]
Epoch 0:  35%|███▍      | 326/938 [00:23<00:44, 13.69it/s, loss=0.819, v_num=10]
Epoch 0:  35%|███▍      | 327/938 [00:23<00:44, 13.69it/s, loss=0.819, v_num=10]
Epoch 0:  35%|███▍      | 327/938 [00:23<00:44, 13.69it/s, loss=0.819, v_num=10]
Epoch 0:  35%|███▍      | 328/938 [00:23<00:44, 13.69it/s, loss=0.828, v_num=10]
Epoch 0:  35%|███▌      | 329/938 [00:24<00:44, 13.69it/s, loss=0.828, v_num=10]
Epoch 0:  35%|███▌      | 329/938 [00:24<00:44, 13.69it/s, loss=0.826, v_num=10]
Epoch 0:  35%|███▌      | 330/938 [00:24<00:44, 13.70it/s, loss=0.823, v_num=10]
Epoch 0:  35%|███▌      | 331/938 [00:24<00:44, 13.69it/s, loss=0.823, v_num=10]
Epoch 0:  35%|███▌      | 331/938 [00:24<00:44, 13.69it/s, loss=0.824, v_num=10]
Epoch 0:  35%|███▌      | 332/938 [00:24<00:44, 13.69it/s, loss=0.837, v_num=10]
Epoch 0:  36%|███▌      | 333/938 [00:24<00:44, 13.69it/s, loss=0.837, v_num=10]
Epoch 0:  36%|███▌      | 333/938 [00:24<00:44, 13.69it/s, loss=0.843, v_num=10]
Epoch 0:  36%|███▌      | 334/938 [00:24<00:44, 13.70it/s, loss=0.843, v_num=10]
Epoch 0:  36%|███▌      | 335/938 [00:24<00:44, 13.69it/s, loss=0.843, v_num=10]
Epoch 0:  36%|███▌      | 335/938 [00:24<00:44, 13.69it/s, loss=0.844, v_num=10]
Epoch 0:  36%|███▌      | 336/938 [00:24<00:43, 13.70it/s, loss=0.847, v_num=10]
Epoch 0:  36%|███▌      | 337/938 [00:24<00:43, 13.69it/s, loss=0.847, v_num=10]
Epoch 0:  36%|███▌      | 337/938 [00:24<00:43, 13.69it/s, loss=0.859, v_num=10]
Epoch 0:  36%|███▌      | 338/938 [00:24<00:43, 13.69it/s, loss=0.855, v_num=10]
Epoch 0:  36%|███▌      | 339/938 [00:24<00:43, 13.70it/s, loss=0.855, v_num=10]
Epoch 0:  36%|███▌      | 339/938 [00:24<00:43, 13.70it/s, loss=0.852, v_num=10]
Epoch 0:  36%|███▌      | 340/938 [00:24<00:43, 13.70it/s, loss=0.845, v_num=10]
Epoch 0:  36%|███▋      | 341/938 [00:24<00:43, 13.69it/s, loss=0.845, v_num=10]
Epoch 0:  36%|███▋      | 341/938 [00:24<00:43, 13.69it/s, loss=0.835, v_num=10]
Epoch 0:  36%|███▋      | 342/938 [00:24<00:43, 13.69it/s, loss=0.851, v_num=10]
Epoch 0:  37%|███▋      | 343/938 [00:25<00:43, 13.68it/s, loss=0.851, v_num=10]
Epoch 0:  37%|███▋      | 343/938 [00:25<00:43, 13.68it/s, loss=0.852, v_num=10]
Epoch 0:  37%|███▋      | 344/938 [00:25<00:43, 13.68it/s, loss=0.84, v_num=10] 
Epoch 0:  37%|███▋      | 345/938 [00:25<00:43, 13.68it/s, loss=0.84, v_num=10]
Epoch 0:  37%|███▋      | 345/938 [00:25<00:43, 13.68it/s, loss=0.837, v_num=10]
Epoch 0:  37%|███▋      | 346/938 [00:25<00:43, 13.69it/s, loss=0.833, v_num=10]
Epoch 0:  37%|███▋      | 347/938 [00:25<00:43, 13.69it/s, loss=0.833, v_num=10]
Epoch 0:  37%|███▋      | 347/938 [00:25<00:43, 13.69it/s, loss=0.832, v_num=10]
Epoch 0:  37%|███▋      | 348/938 [00:25<00:43, 13.69it/s, loss=0.827, v_num=10]
Epoch 0:  37%|███▋      | 349/938 [00:25<00:43, 13.69it/s, loss=0.827, v_num=10]
Epoch 0:  37%|███▋      | 349/938 [00:25<00:43, 13.69it/s, loss=0.823, v_num=10]
Epoch 0:  37%|███▋      | 350/938 [00:25<00:42, 13.68it/s, loss=0.824, v_num=10]
Epoch 0:  37%|███▋      | 351/938 [00:25<00:42, 13.68it/s, loss=0.824, v_num=10]
Epoch 0:  37%|███▋      | 351/938 [00:25<00:42, 13.68it/s, loss=0.82, v_num=10] 
Epoch 0:  38%|███▊      | 352/938 [00:25<00:42, 13.67it/s, loss=0.815, v_num=10]
Epoch 0:  38%|███▊      | 353/938 [00:25<00:42, 13.67it/s, loss=0.815, v_num=10]
Epoch 0:  38%|███▊      | 353/938 [00:25<00:42, 13.67it/s, loss=0.818, v_num=10]
Epoch 0:  38%|███▊      | 354/938 [00:25<00:42, 13.67it/s, loss=0.824, v_num=10]
Epoch 0:  38%|███▊      | 355/938 [00:25<00:42, 13.67it/s, loss=0.824, v_num=10]
Epoch 0:  38%|███▊      | 355/938 [00:25<00:42, 13.67it/s, loss=0.829, v_num=10]
Epoch 0:  38%|███▊      | 356/938 [00:26<00:42, 13.67it/s, loss=0.828, v_num=10]
Epoch 0:  38%|███▊      | 357/938 [00:26<00:42, 13.67it/s, loss=0.828, v_num=10]
Epoch 0:  38%|███▊      | 357/938 [00:26<00:42, 13.67it/s, loss=0.821, v_num=10]
Epoch 0:  38%|███▊      | 358/938 [00:26<00:42, 13.68it/s, loss=0.821, v_num=10]
Epoch 0:  38%|███▊      | 359/938 [00:26<00:42, 13.68it/s, loss=0.821, v_num=10]
Epoch 0:  38%|███▊      | 359/938 [00:26<00:42, 13.68it/s, loss=0.83, v_num=10] 
Epoch 0:  38%|███▊      | 360/938 [00:26<00:42, 13.68it/s, loss=0.83, v_num=10]
Epoch 0:  38%|███▊      | 361/938 [00:26<00:42, 13.69it/s, loss=0.83, v_num=10]
Epoch 0:  38%|███▊      | 361/938 [00:26<00:42, 13.68it/s, loss=0.838, v_num=10]
Epoch 0:  39%|███▊      | 362/938 [00:26<00:42, 13.68it/s, loss=0.83, v_num=10] 
Epoch 0:  39%|███▊      | 363/938 [00:26<00:42, 13.68it/s, loss=0.83, v_num=10]
Epoch 0:  39%|███▊      | 363/938 [00:26<00:42, 13.68it/s, loss=0.834, v_num=10]
Epoch 0:  39%|███▉      | 364/938 [00:26<00:41, 13.68it/s, loss=0.839, v_num=10]
Epoch 0:  39%|███▉      | 365/938 [00:26<00:41, 13.66it/s, loss=0.839, v_num=10]
Epoch 0:  39%|███▉      | 365/938 [00:26<00:41, 13.66it/s, loss=0.831, v_num=10]
Epoch 0:  39%|███▉      | 366/938 [00:26<00:41, 13.66it/s, loss=0.831, v_num=10]
Epoch 0:  39%|███▉      | 367/938 [00:26<00:41, 13.66it/s, loss=0.831, v_num=10]
Epoch 0:  39%|███▉      | 367/938 [00:26<00:41, 13.66it/s, loss=0.818, v_num=10]
Epoch 0:  39%|███▉      | 368/938 [00:26<00:41, 13.67it/s, loss=0.822, v_num=10]
Epoch 0:  39%|███▉      | 369/938 [00:26<00:41, 13.67it/s, loss=0.822, v_num=10]
Epoch 0:  39%|███▉      | 369/938 [00:26<00:41, 13.67it/s, loss=0.823, v_num=10]
Epoch 0:  39%|███▉      | 370/938 [00:27<00:41, 13.67it/s, loss=0.818, v_num=10]
Epoch 0:  40%|███▉      | 371/938 [00:27<00:41, 13.67it/s, loss=0.818, v_num=10]
Epoch 0:  40%|███▉      | 371/938 [00:27<00:41, 13.67it/s, loss=0.816, v_num=10]
Epoch 0:  40%|███▉      | 372/938 [00:27<00:41, 13.67it/s, loss=0.811, v_num=10]
Epoch 0:  40%|███▉      | 373/938 [00:27<00:41, 13.66it/s, loss=0.811, v_num=10]
Epoch 0:  40%|███▉      | 373/938 [00:27<00:41, 13.66it/s, loss=0.816, v_num=10]
Epoch 0:  40%|███▉      | 374/938 [00:27<00:41, 13.66it/s, loss=0.812, v_num=10]
Epoch 0:  40%|███▉      | 375/938 [00:27<00:41, 13.66it/s, loss=0.812, v_num=10]
Epoch 0:  40%|███▉      | 375/938 [00:27<00:41, 13.66it/s, loss=0.824, v_num=10]
Epoch 0:  40%|████      | 376/938 [00:27<00:41, 13.66it/s, loss=0.83, v_num=10] 
Epoch 0:  40%|████      | 377/938 [00:27<00:41, 13.65it/s, loss=0.83, v_num=10]
Epoch 0:  40%|████      | 377/938 [00:27<00:41, 13.65it/s, loss=0.818, v_num=10]
Epoch 0:  40%|████      | 378/938 [00:27<00:40, 13.66it/s, loss=0.827, v_num=10]
Epoch 0:  40%|████      | 379/938 [00:27<00:40, 13.66it/s, loss=0.827, v_num=10]
Epoch 0:  40%|████      | 379/938 [00:27<00:40, 13.66it/s, loss=0.826, v_num=10]
Epoch 0:  41%|████      | 380/938 [00:27<00:40, 13.66it/s, loss=0.831, v_num=10]
Epoch 0:  41%|████      | 381/938 [00:27<00:40, 13.66it/s, loss=0.831, v_num=10]
Epoch 0:  41%|████      | 381/938 [00:27<00:40, 13.66it/s, loss=0.821, v_num=10]
Epoch 0:  41%|████      | 382/938 [00:27<00:40, 13.65it/s, loss=0.81, v_num=10] 
Epoch 0:  41%|████      | 383/938 [00:28<00:40, 13.64it/s, loss=0.81, v_num=10]
Epoch 0:  41%|████      | 383/938 [00:28<00:40, 13.64it/s, loss=0.809, v_num=10]
Epoch 0:  41%|████      | 384/938 [00:28<00:40, 13.64it/s, loss=0.794, v_num=10]
Epoch 0:  41%|████      | 385/938 [00:28<00:40, 13.65it/s, loss=0.794, v_num=10]
Epoch 0:  41%|████      | 385/938 [00:28<00:40, 13.65it/s, loss=0.8, v_num=10]  
Epoch 0:  41%|████      | 386/938 [00:28<00:40, 13.66it/s, loss=0.807, v_num=10]
Epoch 0:  41%|████▏     | 387/938 [00:28<00:40, 13.67it/s, loss=0.807, v_num=10]
Epoch 0:  41%|████▏     | 387/938 [00:28<00:40, 13.67it/s, loss=0.82, v_num=10] 
Epoch 0:  41%|████▏     | 388/938 [00:28<00:40, 13.67it/s, loss=0.816, v_num=10]
Epoch 0:  41%|████▏     | 389/938 [00:28<00:40, 13.68it/s, loss=0.816, v_num=10]
Epoch 0:  41%|████▏     | 389/938 [00:28<00:40, 13.68it/s, loss=0.816, v_num=10]
Epoch 0:  42%|████▏     | 390/938 [00:28<00:40, 13.67it/s, loss=0.823, v_num=10]
Epoch 0:  42%|████▏     | 391/938 [00:28<00:40, 13.67it/s, loss=0.823, v_num=10]
Epoch 0:  42%|████▏     | 391/938 [00:28<00:40, 13.67it/s, loss=0.829, v_num=10]
Epoch 0:  42%|████▏     | 392/938 [00:28<00:39, 13.67it/s, loss=0.824, v_num=10]
Epoch 0:  42%|████▏     | 393/938 [00:28<00:39, 13.67it/s, loss=0.824, v_num=10]
Epoch 0:  42%|████▏     | 393/938 [00:28<00:39, 13.67it/s, loss=0.82, v_num=10] 
Epoch 0:  42%|████▏     | 394/938 [00:28<00:39, 13.66it/s, loss=0.825, v_num=10]
Epoch 0:  42%|████▏     | 395/938 [00:28<00:39, 13.66it/s, loss=0.825, v_num=10]
Epoch 0:  42%|████▏     | 395/938 [00:28<00:39, 13.66it/s, loss=0.821, v_num=10]
Epoch 0:  42%|████▏     | 396/938 [00:28<00:39, 13.66it/s, loss=0.823, v_num=10]
Epoch 0:  42%|████▏     | 397/938 [00:29<00:39, 13.66it/s, loss=0.823, v_num=10]
Epoch 0:  42%|████▏     | 397/938 [00:29<00:39, 13.66it/s, loss=0.834, v_num=10]
Epoch 0:  42%|████▏     | 398/938 [00:29<00:39, 13.66it/s, loss=0.832, v_num=10]
Epoch 0:  43%|████▎     | 399/938 [00:29<00:39, 13.67it/s, loss=0.832, v_num=10]
Epoch 0:  43%|████▎     | 399/938 [00:29<00:39, 13.67it/s, loss=0.84, v_num=10] 
Epoch 0:  43%|████▎     | 400/938 [00:29<00:39, 13.67it/s, loss=0.832, v_num=10]
Epoch 0:  43%|████▎     | 401/938 [00:29<00:39, 13.67it/s, loss=0.832, v_num=10]
Epoch 0:  43%|████▎     | 401/938 [00:29<00:39, 13.67it/s, loss=0.838, v_num=10]
Epoch 0:  43%|████▎     | 402/938 [00:29<00:39, 13.67it/s, loss=0.838, v_num=10]
Epoch 0:  43%|████▎     | 403/938 [00:29<00:39, 13.67it/s, loss=0.838, v_num=10]
Epoch 0:  43%|████▎     | 403/938 [00:29<00:39, 13.67it/s, loss=0.833, v_num=10]
Epoch 0:  43%|████▎     | 404/938 [00:29<00:39, 13.67it/s, loss=0.842, v_num=10]
Epoch 0:  43%|████▎     | 405/938 [00:29<00:38, 13.67it/s, loss=0.842, v_num=10]
Epoch 0:  43%|████▎     | 405/938 [00:29<00:38, 13.67it/s, loss=0.842, v_num=10]
Epoch 0:  43%|████▎     | 406/938 [00:29<00:38, 13.67it/s, loss=0.837, v_num=10]
Epoch 0:  43%|████▎     | 407/938 [00:29<00:38, 13.67it/s, loss=0.837, v_num=10]
Epoch 0:  43%|████▎     | 407/938 [00:29<00:38, 13.67it/s, loss=0.836, v_num=10]
Epoch 0:  43%|████▎     | 408/938 [00:29<00:38, 13.68it/s, loss=0.838, v_num=10]
Epoch 0:  44%|████▎     | 409/938 [00:29<00:38, 13.68it/s, loss=0.838, v_num=10]
Epoch 0:  44%|████▎     | 409/938 [00:29<00:38, 13.68it/s, loss=0.844, v_num=10]
Epoch 0:  44%|████▎     | 410/938 [00:29<00:38, 13.68it/s, loss=0.845, v_num=10]
Epoch 0:  44%|████▍     | 411/938 [00:30<00:38, 13.69it/s, loss=0.845, v_num=10]
Epoch 0:  44%|████▍     | 411/938 [00:30<00:38, 13.69it/s, loss=0.838, v_num=10]
Epoch 0:  44%|████▍     | 412/938 [00:30<00:38, 13.69it/s, loss=0.845, v_num=10]
Epoch 0:  44%|████▍     | 413/938 [00:30<00:38, 13.70it/s, loss=0.845, v_num=10]
Epoch 0:  44%|████▍     | 413/938 [00:30<00:38, 13.70it/s, loss=0.835, v_num=10]
Epoch 0:  44%|████▍     | 414/938 [00:30<00:38, 13.70it/s, loss=0.83, v_num=10] 
Epoch 0:  44%|████▍     | 415/938 [00:30<00:38, 13.70it/s, loss=0.83, v_num=10]
Epoch 0:  44%|████▍     | 415/938 [00:30<00:38, 13.70it/s, loss=0.822, v_num=10]
Epoch 0:  44%|████▍     | 416/938 [00:30<00:38, 13.70it/s, loss=0.813, v_num=10]
Epoch 0:  44%|████▍     | 417/938 [00:30<00:38, 13.70it/s, loss=0.813, v_num=10]
Epoch 0:  44%|████▍     | 417/938 [00:30<00:38, 13.70it/s, loss=0.808, v_num=10]
Epoch 0:  45%|████▍     | 418/938 [00:30<00:37, 13.71it/s, loss=0.798, v_num=10]
Epoch 0:  45%|████▍     | 419/938 [00:30<00:37, 13.71it/s, loss=0.798, v_num=10]
Epoch 0:  45%|████▍     | 419/938 [00:30<00:37, 13.71it/s, loss=0.787, v_num=10]
Epoch 0:  45%|████▍     | 420/938 [00:30<00:37, 13.69it/s, loss=0.79, v_num=10] 
Epoch 0:  45%|████▍     | 421/938 [00:30<00:37, 13.69it/s, loss=0.79, v_num=10]
Epoch 0:  45%|████▍     | 421/938 [00:30<00:37, 13.69it/s, loss=0.798, v_num=10]
Epoch 0:  45%|████▍     | 422/938 [00:30<00:37, 13.69it/s, loss=0.796, v_num=10]
Epoch 0:  45%|████▌     | 423/938 [00:30<00:37, 13.69it/s, loss=0.796, v_num=10]
Epoch 0:  45%|████▌     | 423/938 [00:30<00:37, 13.69it/s, loss=0.786, v_num=10]
Epoch 0:  45%|████▌     | 424/938 [00:30<00:37, 13.69it/s, loss=0.786, v_num=10]
Epoch 0:  45%|████▌     | 425/938 [00:31<00:37, 13.68it/s, loss=0.786, v_num=10]
Epoch 0:  45%|████▌     | 425/938 [00:31<00:37, 13.68it/s, loss=0.786, v_num=10]
Epoch 0:  45%|████▌     | 426/938 [00:31<00:37, 13.67it/s, loss=0.786, v_num=10]
Epoch 0:  46%|████▌     | 427/938 [00:31<00:37, 13.68it/s, loss=0.786, v_num=10]
Epoch 0:  46%|████▌     | 427/938 [00:31<00:37, 13.68it/s, loss=0.778, v_num=10]
Epoch 0:  46%|████▌     | 428/938 [00:31<00:37, 13.69it/s, loss=0.778, v_num=10]
Epoch 0:  46%|████▌     | 429/938 [00:31<00:37, 13.68it/s, loss=0.778, v_num=10]
Epoch 0:  46%|████▌     | 429/938 [00:31<00:37, 13.68it/s, loss=0.767, v_num=10]
Epoch 0:  46%|████▌     | 430/938 [00:31<00:37, 13.69it/s, loss=0.76, v_num=10] 
Epoch 0:  46%|████▌     | 431/938 [00:31<00:37, 13.68it/s, loss=0.76, v_num=10]
Epoch 0:  46%|████▌     | 431/938 [00:31<00:37, 13.68it/s, loss=0.766, v_num=10]
Epoch 0:  46%|████▌     | 432/938 [00:31<00:36, 13.69it/s, loss=0.759, v_num=10]
Epoch 0:  46%|████▌     | 433/938 [00:31<00:36, 13.69it/s, loss=0.759, v_num=10]
Epoch 0:  46%|████▌     | 433/938 [00:31<00:36, 13.69it/s, loss=0.761, v_num=10]
Epoch 0:  46%|████▋     | 434/938 [00:31<00:36, 13.68it/s, loss=0.758, v_num=10]
Epoch 0:  46%|████▋     | 435/938 [00:31<00:36, 13.69it/s, loss=0.758, v_num=10]
Epoch 0:  46%|████▋     | 435/938 [00:31<00:36, 13.69it/s, loss=0.755, v_num=10]
Epoch 0:  46%|████▋     | 436/938 [00:31<00:36, 13.68it/s, loss=0.765, v_num=10]
Epoch 0:  47%|████▋     | 437/938 [00:31<00:36, 13.69it/s, loss=0.765, v_num=10]
Epoch 0:  47%|████▋     | 437/938 [00:31<00:36, 13.69it/s, loss=0.761, v_num=10]
Epoch 0:  47%|████▋     | 438/938 [00:31<00:36, 13.69it/s, loss=0.769, v_num=10]
Epoch 0:  47%|████▋     | 439/938 [00:32<00:36, 13.69it/s, loss=0.769, v_num=10]
Epoch 0:  47%|████▋     | 439/938 [00:32<00:36, 13.69it/s, loss=0.766, v_num=10]
Epoch 0:  47%|████▋     | 440/938 [00:32<00:36, 13.69it/s, loss=0.759, v_num=10]
Epoch 0:  47%|████▋     | 441/938 [00:32<00:36, 13.70it/s, loss=0.759, v_num=10]
Epoch 0:  47%|████▋     | 441/938 [00:32<00:36, 13.70it/s, loss=0.752, v_num=10]
Epoch 0:  47%|████▋     | 442/938 [00:32<00:36, 13.69it/s, loss=0.756, v_num=10]
Epoch 0:  47%|████▋     | 443/938 [00:32<00:36, 13.69it/s, loss=0.756, v_num=10]
Epoch 0:  47%|████▋     | 443/938 [00:32<00:36, 13.69it/s, loss=0.77, v_num=10] 
Epoch 0:  47%|████▋     | 444/938 [00:32<00:36, 13.69it/s, loss=0.774, v_num=10]
Epoch 0:  47%|████▋     | 445/938 [00:32<00:36, 13.69it/s, loss=0.774, v_num=10]
Epoch 0:  47%|████▋     | 445/938 [00:32<00:36, 13.69it/s, loss=0.77, v_num=10] 
Epoch 0:  48%|████▊     | 446/938 [00:32<00:35, 13.69it/s, loss=0.77, v_num=10]
Epoch 0:  48%|████▊     | 447/938 [00:32<00:35, 13.68it/s, loss=0.77, v_num=10]
Epoch 0:  48%|████▊     | 447/938 [00:32<00:35, 13.68it/s, loss=0.774, v_num=10]
Epoch 0:  48%|████▊     | 448/938 [00:32<00:35, 13.68it/s, loss=0.772, v_num=10]
Epoch 0:  48%|████▊     | 449/938 [00:32<00:35, 13.67it/s, loss=0.772, v_num=10]
Epoch 0:  48%|████▊     | 449/938 [00:32<00:35, 13.67it/s, loss=0.773, v_num=10]
Epoch 0:  48%|████▊     | 450/938 [00:32<00:35, 13.67it/s, loss=0.773, v_num=10]
Epoch 0:  48%|████▊     | 451/938 [00:32<00:35, 13.67it/s, loss=0.773, v_num=10]
Epoch 0:  48%|████▊     | 451/938 [00:32<00:35, 13.67it/s, loss=0.768, v_num=10]
Epoch 0:  48%|████▊     | 452/938 [00:33<00:35, 13.67it/s, loss=0.778, v_num=10]
Epoch 0:  48%|████▊     | 453/938 [00:33<00:35, 13.67it/s, loss=0.778, v_num=10]
Epoch 0:  48%|████▊     | 453/938 [00:33<00:35, 13.67it/s, loss=0.784, v_num=10]
Epoch 0:  48%|████▊     | 454/938 [00:33<00:35, 13.66it/s, loss=0.791, v_num=10]
Epoch 0:  49%|████▊     | 455/938 [00:33<00:35, 13.67it/s, loss=0.791, v_num=10]
Epoch 0:  49%|████▊     | 455/938 [00:33<00:35, 13.67it/s, loss=0.793, v_num=10]
Epoch 0:  49%|████▊     | 456/938 [00:33<00:35, 13.67it/s, loss=0.791, v_num=10]
Epoch 0:  49%|████▊     | 457/938 [00:33<00:35, 13.67it/s, loss=0.791, v_num=10]
Epoch 0:  49%|████▊     | 457/938 [00:33<00:35, 13.67it/s, loss=0.797, v_num=10]
Epoch 0:  49%|████▉     | 458/938 [00:33<00:35, 13.67it/s, loss=0.801, v_num=10]
Epoch 0:  49%|████▉     | 459/938 [00:33<00:35, 13.67it/s, loss=0.801, v_num=10]
Epoch 0:  49%|████▉     | 459/938 [00:33<00:35, 13.67it/s, loss=0.81, v_num=10] 
Epoch 0:  49%|████▉     | 460/938 [00:33<00:34, 13.67it/s, loss=0.81, v_num=10]
Epoch 0:  49%|████▉     | 461/938 [00:33<00:34, 13.67it/s, loss=0.81, v_num=10]
Epoch 0:  49%|████▉     | 461/938 [00:33<00:34, 13.67it/s, loss=0.817, v_num=10]
Epoch 0:  49%|████▉     | 462/938 [00:33<00:34, 13.66it/s, loss=0.823, v_num=10]
Epoch 0:  49%|████▉     | 463/938 [00:33<00:34, 13.67it/s, loss=0.823, v_num=10]
Epoch 0:  49%|████▉     | 463/938 [00:33<00:34, 13.67it/s, loss=0.82, v_num=10] 
Epoch 0:  49%|████▉     | 464/938 [00:33<00:34, 13.67it/s, loss=0.815, v_num=10]
Epoch 0:  50%|████▉     | 465/938 [00:34<00:34, 13.67it/s, loss=0.815, v_num=10]
Epoch 0:  50%|████▉     | 465/938 [00:34<00:34, 13.67it/s, loss=0.815, v_num=10]
Epoch 0:  50%|████▉     | 466/938 [00:34<00:34, 13.67it/s, loss=0.805, v_num=10]
Epoch 0:  50%|████▉     | 467/938 [00:34<00:34, 13.67it/s, loss=0.805, v_num=10]
Epoch 0:  50%|████▉     | 467/938 [00:34<00:34, 13.67it/s, loss=0.81, v_num=10] 
Epoch 0:  50%|████▉     | 468/938 [00:34<00:34, 13.67it/s, loss=0.807, v_num=10]
Epoch 0:  50%|█████     | 469/938 [00:34<00:34, 13.69it/s, loss=0.807, v_num=10]
Epoch 0:  50%|█████     | 469/938 [00:34<00:34, 13.69it/s, loss=0.807, v_num=10]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]

Validating:   0%|          | 2/469 [00:00<00:25, 18.28it/s]
Epoch 0:  50%|█████     | 472/938 [00:34<00:33, 13.73it/s, loss=0.807, v_num=10]

Validating:   1%|          | 5/469 [00:00<00:20, 23.16it/s]
Epoch 0:  51%|█████     | 475/938 [00:34<00:33, 13.77it/s, loss=0.807, v_num=10]

Validating:   2%|▏         | 8/469 [00:00<00:18, 25.32it/s]
Epoch 0:  51%|█████     | 478/938 [00:34<00:33, 13.82it/s, loss=0.807, v_num=10]

Validating:   2%|▏         | 11/469 [00:00<00:17, 26.36it/s]
Epoch 0:  51%|█████▏    | 481/938 [00:34<00:32, 13.86it/s, loss=0.807, v_num=10]

Validating:   3%|▎         | 14/469 [00:00<00:18, 25.05it/s]
Epoch 0:  52%|█████▏    | 484/938 [00:34<00:32, 13.90it/s, loss=0.807, v_num=10]

Validating:   4%|▎         | 17/469 [00:00<00:17, 25.25it/s]
Epoch 0:  52%|█████▏    | 487/938 [00:34<00:32, 13.93it/s, loss=0.807, v_num=10]

Validating:   4%|▍         | 20/469 [00:00<00:17, 25.84it/s]
Epoch 0:  52%|█████▏    | 490/938 [00:35<00:32, 13.98it/s, loss=0.807, v_num=10]

Validating:   5%|▍         | 23/469 [00:00<00:17, 26.20it/s]
Epoch 0:  53%|█████▎    | 493/938 [00:35<00:31, 14.02it/s, loss=0.807, v_num=10]

Validating:   6%|▌         | 26/469 [00:01<00:16, 26.13it/s]
Epoch 0:  53%|█████▎    | 496/938 [00:35<00:31, 14.06it/s, loss=0.807, v_num=10]

Validating:   6%|▌         | 29/469 [00:01<00:16, 26.01it/s]
Epoch 0:  53%|█████▎    | 499/938 [00:35<00:31, 14.09it/s, loss=0.807, v_num=10]

Validating:   7%|▋         | 32/469 [00:01<00:16, 25.88it/s]
Epoch 0:  54%|█████▎    | 502/938 [00:35<00:30, 14.13it/s, loss=0.807, v_num=10]

Validating:   7%|▋         | 35/469 [00:01<00:16, 26.37it/s]
Epoch 0:  54%|█████▍    | 505/938 [00:35<00:30, 14.17it/s, loss=0.807, v_num=10]

Validating:   8%|▊         | 38/469 [00:01<00:16, 26.38it/s]
Epoch 0:  54%|█████▍    | 508/938 [00:35<00:30, 14.21it/s, loss=0.807, v_num=10]

Validating:   9%|▊         | 41/469 [00:01<00:15, 26.93it/s]
Epoch 0:  54%|█████▍    | 511/938 [00:35<00:29, 14.25it/s, loss=0.807, v_num=10]

Validating:   9%|▉         | 44/469 [00:01<00:16, 26.39it/s]
Epoch 0:  55%|█████▍    | 514/938 [00:35<00:29, 14.29it/s, loss=0.807, v_num=10]

Validating:  10%|█         | 47/469 [00:01<00:16, 25.80it/s]
Epoch 0:  55%|█████▌    | 517/938 [00:36<00:29, 14.33it/s, loss=0.807, v_num=10]

Validating:  11%|█         | 50/469 [00:01<00:16, 25.80it/s]
Epoch 0:  55%|█████▌    | 520/938 [00:36<00:29, 14.36it/s, loss=0.807, v_num=10]

Validating:  11%|█▏        | 53/469 [00:02<00:16, 25.56it/s]
Epoch 0:  56%|█████▌    | 523/938 [00:36<00:28, 14.40it/s, loss=0.807, v_num=10]

Validating:  12%|█▏        | 56/469 [00:02<00:15, 25.83it/s]
Epoch 0:  56%|█████▌    | 526/938 [00:36<00:28, 14.43it/s, loss=0.807, v_num=10]

Validating:  13%|█▎        | 59/469 [00:02<00:16, 25.42it/s]
Epoch 0:  56%|█████▋    | 529/938 [00:36<00:28, 14.47it/s, loss=0.807, v_num=10]

Validating:  13%|█▎        | 62/469 [00:02<00:15, 26.06it/s]
Epoch 0:  57%|█████▋    | 532/938 [00:36<00:27, 14.51it/s, loss=0.807, v_num=10]

Validating:  14%|█▍        | 65/469 [00:02<00:16, 24.34it/s]
Epoch 0:  57%|█████▋    | 535/938 [00:36<00:27, 14.53it/s, loss=0.807, v_num=10]

Validating:  14%|█▍        | 68/469 [00:02<00:16, 24.22it/s]
Epoch 0:  57%|█████▋    | 538/938 [00:36<00:27, 14.56it/s, loss=0.807, v_num=10]

Validating:  15%|█▌        | 71/469 [00:02<00:16, 23.75it/s]
Epoch 0:  58%|█████▊    | 541/938 [00:37<00:27, 14.59it/s, loss=0.807, v_num=10]

Validating:  16%|█▌        | 74/469 [00:02<00:16, 24.03it/s]
Epoch 0:  58%|█████▊    | 544/938 [00:37<00:26, 14.63it/s, loss=0.807, v_num=10]

Validating:  16%|█▋        | 77/469 [00:03<00:16, 24.42it/s]
Epoch 0:  58%|█████▊    | 547/938 [00:37<00:26, 14.66it/s, loss=0.807, v_num=10]

Validating:  17%|█▋        | 80/469 [00:03<00:15, 25.01it/s]
Epoch 0:  59%|█████▊    | 550/938 [00:37<00:26, 14.70it/s, loss=0.807, v_num=10]

Validating:  18%|█▊        | 83/469 [00:03<00:14, 26.28it/s]
Epoch 0:  59%|█████▉    | 553/938 [00:37<00:26, 14.74it/s, loss=0.807, v_num=10]

Validating:  18%|█▊        | 86/469 [00:03<00:14, 27.16it/s]
Epoch 0:  59%|█████▉    | 556/938 [00:37<00:25, 14.78it/s, loss=0.807, v_num=10]

Validating:  19%|█▉        | 89/469 [00:03<00:14, 26.62it/s]
Epoch 0:  60%|█████▉    | 559/938 [00:37<00:25, 14.81it/s, loss=0.807, v_num=10]

Validating:  20%|█▉        | 92/469 [00:03<00:14, 26.36it/s]
Epoch 0:  60%|█████▉    | 562/938 [00:37<00:25, 14.84it/s, loss=0.807, v_num=10]

Validating:  20%|██        | 95/469 [00:03<00:14, 26.32it/s]
Epoch 0:  60%|██████    | 565/938 [00:37<00:25, 14.88it/s, loss=0.807, v_num=10]

Validating:  21%|██        | 98/469 [00:03<00:14, 25.90it/s]
Epoch 0:  61%|██████    | 568/938 [00:38<00:24, 14.91it/s, loss=0.807, v_num=10]

Validating:  22%|██▏       | 101/469 [00:03<00:13, 26.36it/s]
Epoch 0:  61%|██████    | 571/938 [00:38<00:24, 14.95it/s, loss=0.807, v_num=10]

Validating:  22%|██▏       | 104/469 [00:04<00:13, 26.19it/s]
Epoch 0:  61%|██████    | 574/938 [00:38<00:24, 14.98it/s, loss=0.807, v_num=10]

Validating:  23%|██▎       | 107/469 [00:04<00:14, 25.55it/s]
Epoch 0:  62%|██████▏   | 577/938 [00:38<00:24, 15.01it/s, loss=0.807, v_num=10]

Validating:  23%|██▎       | 110/469 [00:04<00:14, 24.63it/s]
Epoch 0:  62%|██████▏   | 580/938 [00:38<00:23, 15.04it/s, loss=0.807, v_num=10]

Validating:  24%|██▍       | 113/469 [00:04<00:14, 25.22it/s]
Epoch 0:  62%|██████▏   | 583/938 [00:38<00:23, 15.07it/s, loss=0.807, v_num=10]

Validating:  25%|██▍       | 116/469 [00:04<00:14, 24.21it/s]
Epoch 0:  62%|██████▏   | 586/938 [00:38<00:23, 15.09it/s, loss=0.807, v_num=10]

Validating:  25%|██▌       | 119/469 [00:04<00:13, 25.46it/s]
Epoch 0:  63%|██████▎   | 589/938 [00:38<00:23, 15.13it/s, loss=0.807, v_num=10]

Validating:  26%|██▌       | 122/469 [00:04<00:13, 25.91it/s]
Epoch 0:  63%|██████▎   | 592/938 [00:39<00:22, 15.16it/s, loss=0.807, v_num=10]

Validating:  27%|██▋       | 125/469 [00:04<00:13, 26.34it/s]
Epoch 0:  63%|██████▎   | 595/938 [00:39<00:22, 15.20it/s, loss=0.807, v_num=10]

Validating:  27%|██▋       | 128/469 [00:05<00:13, 25.45it/s]
Epoch 0:  64%|██████▍   | 598/938 [00:39<00:22, 15.23it/s, loss=0.807, v_num=10]

Validating:  28%|██▊       | 131/469 [00:05<00:13, 25.11it/s]
Epoch 0:  64%|██████▍   | 601/938 [00:39<00:22, 15.25it/s, loss=0.807, v_num=10]

Validating:  29%|██▊       | 134/469 [00:05<00:12, 25.77it/s]
Epoch 0:  64%|██████▍   | 604/938 [00:39<00:21, 15.29it/s, loss=0.807, v_num=10]

Validating:  29%|██▉       | 137/469 [00:05<00:13, 25.33it/s]
Epoch 0:  65%|██████▍   | 607/938 [00:39<00:21, 15.32it/s, loss=0.807, v_num=10]

Validating:  30%|██▉       | 140/469 [00:05<00:13, 25.03it/s]
Epoch 0:  65%|██████▌   | 610/938 [00:39<00:21, 15.34it/s, loss=0.807, v_num=10]

Validating:  30%|███       | 143/469 [00:05<00:12, 25.18it/s]
Epoch 0:  65%|██████▌   | 613/938 [00:39<00:21, 15.37it/s, loss=0.807, v_num=10]

Validating:  31%|███       | 146/469 [00:05<00:12, 25.32it/s]
Epoch 0:  66%|██████▌   | 616/938 [00:39<00:20, 15.40it/s, loss=0.807, v_num=10]

Validating:  32%|███▏      | 149/469 [00:05<00:12, 25.47it/s]
Epoch 0:  66%|██████▌   | 619/938 [00:40<00:20, 15.43it/s, loss=0.807, v_num=10]

Validating:  32%|███▏      | 152/469 [00:05<00:12, 26.27it/s]
Epoch 0:  66%|██████▋   | 622/938 [00:40<00:20, 15.47it/s, loss=0.807, v_num=10]

Validating:  33%|███▎      | 155/469 [00:06<00:12, 25.62it/s]
Epoch 0:  67%|██████▋   | 625/938 [00:40<00:20, 15.50it/s, loss=0.807, v_num=10]

Validating:  34%|███▎      | 158/469 [00:06<00:12, 24.48it/s]
Epoch 0:  67%|██████▋   | 628/938 [00:40<00:19, 15.52it/s, loss=0.807, v_num=10]

Validating:  34%|███▍      | 161/469 [00:06<00:12, 24.15it/s]
Epoch 0:  67%|██████▋   | 631/938 [00:40<00:19, 15.54it/s, loss=0.807, v_num=10]

Validating:  35%|███▍      | 164/469 [00:06<00:12, 24.83it/s]
Epoch 0:  68%|██████▊   | 634/938 [00:40<00:19, 15.57it/s, loss=0.807, v_num=10]

Validating:  36%|███▌      | 167/469 [00:06<00:11, 25.45it/s]
Epoch 0:  68%|██████▊   | 637/938 [00:40<00:19, 15.60it/s, loss=0.807, v_num=10]

Validating:  36%|███▌      | 170/469 [00:06<00:11, 25.43it/s]
Epoch 0:  68%|██████▊   | 640/938 [00:40<00:19, 15.63it/s, loss=0.807, v_num=10]

Validating:  37%|███▋      | 173/469 [00:06<00:11, 25.66it/s]
Epoch 0:  69%|██████▊   | 643/938 [00:41<00:18, 15.66it/s, loss=0.807, v_num=10]

Validating:  38%|███▊      | 176/469 [00:06<00:11, 25.88it/s]
Epoch 0:  69%|██████▉   | 646/938 [00:41<00:18, 15.69it/s, loss=0.807, v_num=10]

Validating:  38%|███▊      | 179/469 [00:07<00:11, 26.25it/s]
Epoch 0:  69%|██████▉   | 649/938 [00:41<00:18, 15.72it/s, loss=0.807, v_num=10]

Validating:  39%|███▉      | 182/469 [00:07<00:11, 25.96it/s]
Epoch 0:  70%|██████▉   | 652/938 [00:41<00:18, 15.75it/s, loss=0.807, v_num=10]

Validating:  39%|███▉      | 185/469 [00:07<00:10, 26.28it/s]
Epoch 0:  70%|██████▉   | 655/938 [00:41<00:17, 15.78it/s, loss=0.807, v_num=10]

Validating:  40%|████      | 188/469 [00:07<00:10, 25.66it/s]
Epoch 0:  70%|███████   | 658/938 [00:41<00:17, 15.81it/s, loss=0.807, v_num=10]

Validating:  41%|████      | 191/469 [00:07<00:10, 25.32it/s]
Epoch 0:  70%|███████   | 661/938 [00:41<00:17, 15.83it/s, loss=0.807, v_num=10]

Validating:  41%|████▏     | 194/469 [00:07<00:10, 25.81it/s]
Epoch 0:  71%|███████   | 664/938 [00:41<00:17, 15.86it/s, loss=0.807, v_num=10]

Validating:  42%|████▏     | 197/469 [00:07<00:10, 26.22it/s]
Epoch 0:  71%|███████   | 667/938 [00:41<00:17, 15.89it/s, loss=0.807, v_num=10]

Validating:  43%|████▎     | 200/469 [00:07<00:10, 25.84it/s]
Epoch 0:  71%|███████▏  | 670/938 [00:42<00:16, 15.92it/s, loss=0.807, v_num=10]

Validating:  43%|████▎     | 204/469 [00:07<00:09, 27.07it/s]
Epoch 0:  72%|███████▏  | 674/938 [00:42<00:16, 15.96it/s, loss=0.807, v_num=10]

Validating:  44%|████▍     | 207/469 [00:08<00:09, 27.44it/s]
Epoch 0:  72%|███████▏  | 678/938 [00:42<00:16, 16.00it/s, loss=0.807, v_num=10]

Validating:  45%|████▍     | 210/469 [00:08<00:09, 27.10it/s]
Epoch 0:  73%|███████▎  | 682/938 [00:42<00:15, 16.04it/s, loss=0.807, v_num=10]

Validating:  45%|████▌     | 213/469 [00:08<00:09, 27.16it/s]

Validating:  46%|████▌     | 216/469 [00:08<00:09, 26.88it/s]
Epoch 0:  73%|███████▎  | 686/938 [00:42<00:15, 16.08it/s, loss=0.807, v_num=10]

Validating:  47%|████▋     | 219/469 [00:08<00:09, 26.64it/s]
Epoch 0:  74%|███████▎  | 690/938 [00:42<00:15, 16.11it/s, loss=0.807, v_num=10]

Validating:  47%|████▋     | 222/469 [00:08<00:09, 26.02it/s]
Epoch 0:  74%|███████▍  | 694/938 [00:42<00:15, 16.14it/s, loss=0.807, v_num=10]

Validating:  48%|████▊     | 225/469 [00:08<00:09, 25.61it/s]

Validating:  49%|████▊     | 228/469 [00:08<00:09, 25.78it/s]
Epoch 0:  74%|███████▍  | 698/938 [00:43<00:14, 16.18it/s, loss=0.807, v_num=10]

Validating:  49%|████▉     | 231/469 [00:08<00:09, 26.26it/s]
Epoch 0:  75%|███████▍  | 702/938 [00:43<00:14, 16.22it/s, loss=0.807, v_num=10]

Validating:  50%|████▉     | 234/469 [00:09<00:09, 25.81it/s]
Epoch 0:  75%|███████▌  | 706/938 [00:43<00:14, 16.25it/s, loss=0.807, v_num=10]

Validating:  51%|█████     | 237/469 [00:09<00:08, 26.65it/s]

Validating:  51%|█████     | 240/469 [00:09<00:08, 26.61it/s]
Epoch 0:  76%|███████▌  | 710/938 [00:43<00:13, 16.29it/s, loss=0.807, v_num=10]

Validating:  52%|█████▏    | 243/469 [00:09<00:08, 26.87it/s]
Epoch 0:  76%|███████▌  | 714/938 [00:43<00:13, 16.32it/s, loss=0.807, v_num=10]

Validating:  52%|█████▏    | 246/469 [00:09<00:08, 26.46it/s]
Epoch 0:  77%|███████▋  | 718/938 [00:43<00:13, 16.36it/s, loss=0.807, v_num=10]

Validating:  53%|█████▎    | 249/469 [00:09<00:08, 26.19it/s]

Validating:  54%|█████▎    | 252/469 [00:09<00:08, 26.87it/s]
Epoch 0:  77%|███████▋  | 722/938 [00:44<00:13, 16.39it/s, loss=0.807, v_num=10]

Validating:  54%|█████▍    | 255/469 [00:09<00:08, 25.31it/s]
Epoch 0:  77%|███████▋  | 726/938 [00:44<00:12, 16.42it/s, loss=0.807, v_num=10]

Validating:  55%|█████▌    | 258/469 [00:10<00:08, 25.60it/s]
Epoch 0:  78%|███████▊  | 730/938 [00:44<00:12, 16.45it/s, loss=0.807, v_num=10]

Validating:  56%|█████▌    | 261/469 [00:10<00:08, 25.22it/s]

Validating:  56%|█████▋    | 264/469 [00:10<00:07, 26.08it/s]
Epoch 0:  78%|███████▊  | 734/938 [00:44<00:12, 16.49it/s, loss=0.807, v_num=10]

Validating:  57%|█████▋    | 267/469 [00:10<00:08, 23.43it/s]
Epoch 0:  79%|███████▊  | 738/938 [00:44<00:12, 16.50it/s, loss=0.807, v_num=10]

Validating:  58%|█████▊    | 270/469 [00:10<00:08, 23.83it/s]
Epoch 0:  79%|███████▉  | 742/938 [00:44<00:11, 16.54it/s, loss=0.807, v_num=10]

Validating:  58%|█████▊    | 273/469 [00:10<00:07, 24.58it/s]

Validating:  59%|█████▉    | 276/469 [00:10<00:07, 25.35it/s]
Epoch 0:  80%|███████▉  | 746/938 [00:45<00:11, 16.57it/s, loss=0.807, v_num=10]

Validating:  59%|█████▉    | 279/469 [00:10<00:07, 25.69it/s]
Epoch 0:  80%|███████▉  | 750/938 [00:45<00:11, 16.60it/s, loss=0.807, v_num=10]

Validating:  60%|██████    | 282/469 [00:10<00:07, 25.97it/s]
Epoch 0:  80%|████████  | 754/938 [00:45<00:11, 16.64it/s, loss=0.807, v_num=10]

Validating:  61%|██████    | 285/469 [00:11<00:06, 26.42it/s]

Validating:  61%|██████▏   | 288/469 [00:11<00:06, 26.76it/s]
Epoch 0:  81%|████████  | 758/938 [00:45<00:10, 16.67it/s, loss=0.807, v_num=10]

Validating:  62%|██████▏   | 291/469 [00:11<00:06, 25.76it/s]
Epoch 0:  81%|████████  | 762/938 [00:45<00:10, 16.70it/s, loss=0.807, v_num=10]

Validating:  63%|██████▎   | 294/469 [00:11<00:06, 26.11it/s]
Epoch 0:  82%|████████▏ | 766/938 [00:45<00:10, 16.73it/s, loss=0.807, v_num=10]

Validating:  63%|██████▎   | 297/469 [00:11<00:06, 26.58it/s]

Validating:  64%|██████▍   | 300/469 [00:11<00:06, 26.61it/s]
Epoch 0:  82%|████████▏ | 770/938 [00:45<00:10, 16.77it/s, loss=0.807, v_num=10]

Validating:  65%|██████▍   | 303/469 [00:11<00:06, 25.91it/s]
Epoch 0:  83%|████████▎ | 774/938 [00:46<00:09, 16.80it/s, loss=0.807, v_num=10]

Validating:  65%|██████▌   | 306/469 [00:11<00:06, 26.30it/s]
Epoch 0:  83%|████████▎ | 778/938 [00:46<00:09, 16.83it/s, loss=0.807, v_num=10]

Validating:  66%|██████▌   | 309/469 [00:12<00:06, 25.99it/s]

Validating:  67%|██████▋   | 312/469 [00:12<00:05, 26.61it/s]
Epoch 0:  83%|████████▎ | 782/938 [00:46<00:09, 16.86it/s, loss=0.807, v_num=10]

Validating:  67%|██████▋   | 315/469 [00:12<00:05, 26.76it/s]
Epoch 0:  84%|████████▍ | 786/938 [00:46<00:08, 16.89it/s, loss=0.807, v_num=10]

Validating:  68%|██████▊   | 318/469 [00:12<00:05, 26.95it/s]
Epoch 0:  84%|████████▍ | 790/938 [00:46<00:08, 16.92it/s, loss=0.807, v_num=10]

Validating:  68%|██████▊   | 321/469 [00:12<00:05, 25.68it/s]

Validating:  69%|██████▉   | 324/469 [00:12<00:05, 25.37it/s]
Epoch 0:  85%|████████▍ | 794/938 [00:46<00:08, 16.95it/s, loss=0.807, v_num=10]

Validating:  70%|██████▉   | 327/469 [00:12<00:05, 25.52it/s]
Epoch 0:  85%|████████▌ | 798/938 [00:47<00:08, 16.97it/s, loss=0.807, v_num=10]

Validating:  70%|███████   | 330/469 [00:12<00:05, 24.21it/s]
Epoch 0:  86%|████████▌ | 802/938 [00:47<00:08, 17.00it/s, loss=0.807, v_num=10]

Validating:  71%|███████   | 333/469 [00:12<00:05, 25.14it/s]

Validating:  72%|███████▏  | 336/469 [00:13<00:05, 24.75it/s]
Epoch 0:  86%|████████▌ | 806/938 [00:47<00:07, 17.02it/s, loss=0.807, v_num=10]

Validating:  72%|███████▏  | 339/469 [00:13<00:05, 24.94it/s]
Epoch 0:  86%|████████▋ | 810/938 [00:47<00:07, 17.06it/s, loss=0.807, v_num=10]

Validating:  73%|███████▎  | 342/469 [00:13<00:04, 25.64it/s]
Epoch 0:  87%|████████▋ | 814/938 [00:47<00:07, 17.09it/s, loss=0.807, v_num=10]

Validating:  74%|███████▎  | 345/469 [00:13<00:04, 25.66it/s]

Validating:  74%|███████▍  | 348/469 [00:13<00:04, 26.04it/s]
Epoch 0:  87%|████████▋ | 818/938 [00:47<00:07, 17.11it/s, loss=0.807, v_num=10]

Validating:  75%|███████▍  | 351/469 [00:13<00:04, 26.73it/s]
Epoch 0:  88%|████████▊ | 822/938 [00:47<00:06, 17.15it/s, loss=0.807, v_num=10]

Validating:  75%|███████▌  | 354/469 [00:13<00:04, 26.62it/s]
Epoch 0:  88%|████████▊ | 826/938 [00:48<00:06, 17.18it/s, loss=0.807, v_num=10]

Validating:  76%|███████▌  | 357/469 [00:13<00:04, 26.78it/s]

Validating:  77%|███████▋  | 360/469 [00:13<00:04, 25.78it/s]
Epoch 0:  88%|████████▊ | 830/938 [00:48<00:06, 17.20it/s, loss=0.807, v_num=10]

Validating:  77%|███████▋  | 363/469 [00:14<00:04, 24.33it/s]
Epoch 0:  89%|████████▉ | 834/938 [00:48<00:06, 17.22it/s, loss=0.807, v_num=10]

Validating:  78%|███████▊  | 366/469 [00:14<00:04, 23.21it/s]
Epoch 0:  89%|████████▉ | 838/938 [00:48<00:05, 17.24it/s, loss=0.807, v_num=10]

Validating:  79%|███████▊  | 369/469 [00:14<00:04, 23.91it/s]

Validating:  79%|███████▉  | 372/469 [00:14<00:04, 23.72it/s]
Epoch 0:  90%|████████▉ | 842/938 [00:48<00:05, 17.26it/s, loss=0.807, v_num=10]

Validating:  80%|███████▉  | 375/469 [00:14<00:03, 24.37it/s]
Epoch 0:  90%|█████████ | 846/938 [00:48<00:05, 17.29it/s, loss=0.807, v_num=10]

Validating:  81%|████████  | 378/469 [00:14<00:03, 23.37it/s]
Epoch 0:  91%|█████████ | 850/938 [00:49<00:05, 17.31it/s, loss=0.807, v_num=10]

Validating:  81%|████████  | 381/469 [00:14<00:03, 24.63it/s]

Validating:  82%|████████▏ | 384/469 [00:14<00:03, 24.66it/s]
Epoch 0:  91%|█████████ | 854/938 [00:49<00:04, 17.33it/s, loss=0.807, v_num=10]

Validating:  83%|████████▎ | 387/469 [00:15<00:03, 25.14it/s]
Epoch 0:  91%|█████████▏| 858/938 [00:49<00:04, 17.36it/s, loss=0.807, v_num=10]

Validating:  83%|████████▎ | 390/469 [00:15<00:03, 24.47it/s]
Epoch 0:  92%|█████████▏| 862/938 [00:49<00:04, 17.38it/s, loss=0.807, v_num=10]

Validating:  84%|████████▍ | 393/469 [00:15<00:03, 24.30it/s]

Validating:  84%|████████▍ | 396/469 [00:15<00:02, 25.21it/s]
Epoch 0:  92%|█████████▏| 866/938 [00:49<00:04, 17.41it/s, loss=0.807, v_num=10]

Validating:  85%|████████▌ | 399/469 [00:15<00:02, 25.69it/s]
Epoch 0:  93%|█████████▎| 870/938 [00:49<00:03, 17.44it/s, loss=0.807, v_num=10]

Validating:  86%|████████▌ | 402/469 [00:15<00:02, 25.94it/s]
Epoch 0:  93%|█████████▎| 874/938 [00:50<00:03, 17.46it/s, loss=0.807, v_num=10]

Validating:  86%|████████▋ | 405/469 [00:15<00:02, 25.38it/s]

Validating:  87%|████████▋ | 408/469 [00:15<00:02, 25.81it/s]
Epoch 0:  94%|█████████▎| 878/938 [00:50<00:03, 17.49it/s, loss=0.807, v_num=10]

Validating:  88%|████████▊ | 411/469 [00:16<00:02, 26.29it/s]
Epoch 0:  94%|█████████▍| 882/938 [00:50<00:03, 17.52it/s, loss=0.807, v_num=10]

Validating:  88%|████████▊ | 414/469 [00:16<00:02, 25.97it/s]
Epoch 0:  94%|█████████▍| 886/938 [00:50<00:02, 17.54it/s, loss=0.807, v_num=10]

Validating:  89%|████████▉ | 417/469 [00:16<00:02, 25.74it/s]

Validating:  90%|████████▉ | 420/469 [00:16<00:01, 24.83it/s]
Epoch 0:  95%|█████████▍| 890/938 [00:50<00:02, 17.56it/s, loss=0.807, v_num=10]

Validating:  90%|█████████ | 423/469 [00:16<00:01, 24.02it/s]
Epoch 0:  95%|█████████▌| 894/938 [00:50<00:02, 17.58it/s, loss=0.807, v_num=10]

Validating:  91%|█████████ | 426/469 [00:16<00:01, 24.74it/s]
Epoch 0:  96%|█████████▌| 898/938 [00:51<00:02, 17.61it/s, loss=0.807, v_num=10]

Validating:  91%|█████████▏| 429/469 [00:16<00:01, 24.86it/s]

Validating:  92%|█████████▏| 432/469 [00:16<00:01, 25.44it/s]
Epoch 0:  96%|█████████▌| 902/938 [00:51<00:02, 17.63it/s, loss=0.807, v_num=10]

Validating:  93%|█████████▎| 435/469 [00:16<00:01, 26.46it/s]
Epoch 0:  97%|█████████▋| 906/938 [00:51<00:01, 17.66it/s, loss=0.807, v_num=10]

Validating:  93%|█████████▎| 438/469 [00:17<00:01, 25.96it/s]
Epoch 0:  97%|█████████▋| 910/938 [00:51<00:01, 17.69it/s, loss=0.807, v_num=10]

Validating:  94%|█████████▍| 441/469 [00:17<00:01, 25.78it/s]

Validating:  95%|█████████▍| 444/469 [00:17<00:00, 26.32it/s]
Epoch 0:  97%|█████████▋| 914/938 [00:51<00:01, 17.71it/s, loss=0.807, v_num=10]

Validating:  95%|█████████▌| 447/469 [00:17<00:00, 25.68it/s]
Epoch 0:  98%|█████████▊| 918/938 [00:51<00:01, 17.73it/s, loss=0.807, v_num=10]

Validating:  96%|█████████▌| 450/469 [00:17<00:00, 25.41it/s]
Epoch 0:  98%|█████████▊| 922/938 [00:51<00:00, 17.75it/s, loss=0.807, v_num=10]

Validating:  97%|█████████▋| 453/469 [00:17<00:00, 25.42it/s]

Validating:  97%|█████████▋| 456/469 [00:17<00:00, 25.61it/s]
Epoch 0:  99%|█████████▊| 926/938 [00:52<00:00, 17.78it/s, loss=0.807, v_num=10]

Validating:  98%|█████████▊| 459/469 [00:17<00:00, 25.85it/s]
Epoch 0:  99%|█████████▉| 930/938 [00:52<00:00, 17.80it/s, loss=0.807, v_num=10]

Validating:  99%|█████████▊| 462/469 [00:18<00:00, 24.53it/s]
Epoch 0: 100%|█████████▉| 934/938 [00:52<00:00, 17.82it/s, loss=0.807, v_num=10]

Validating:  99%|█████████▉| 465/469 [00:18<00:00, 24.01it/s]

Validating: 100%|█████████▉| 468/469 [00:18<00:00, 24.94it/s]
Epoch 0: 100%|██████████| 938/938 [00:52<00:00, 17.84it/s, loss=0.807, v_num=10]
Epoch 0: 100%|██████████| 938/938 [00:52<00:00, 17.83it/s, loss=0.807, v_num=10, val_rmse=0.659]

                                                             
Epoch 0: 100%|██████████| 938/938 [00:52<00:00, 17.82it/s, loss=0.807, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 0:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.807, v_num=10, val_rmse=0.659, train_rmse=1.190]          
Epoch 1:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.807, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   0%|          | 1/938 [00:00<01:26, 10.84it/s, loss=0.806, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   0%|          | 2/938 [00:00<01:18, 11.92it/s, loss=0.819, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   0%|          | 3/938 [00:00<01:15, 12.38it/s, loss=0.811, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   0%|          | 4/938 [00:00<01:10, 13.33it/s, loss=0.811, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   0%|          | 4/938 [00:00<01:10, 13.31it/s, loss=0.805, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   1%|          | 5/938 [00:00<01:09, 13.38it/s, loss=0.806, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   1%|          | 6/938 [00:00<01:08, 13.63it/s, loss=0.803, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   1%|          | 7/938 [00:00<01:06, 13.93it/s, loss=0.798, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   1%|          | 8/938 [00:00<01:05, 14.11it/s, loss=0.798, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   1%|          | 8/938 [00:00<01:05, 14.09it/s, loss=0.794, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   1%|          | 9/938 [00:00<01:05, 14.09it/s, loss=0.788, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   1%|          | 10/938 [00:00<01:05, 14.16it/s, loss=0.783, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   1%|          | 11/938 [00:00<01:05, 14.23it/s, loss=0.781, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   1%|▏         | 12/938 [00:00<01:05, 14.23it/s, loss=0.781, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   1%|▏         | 12/938 [00:00<01:05, 14.22it/s, loss=0.769, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   1%|▏         | 13/938 [00:00<01:04, 14.38it/s, loss=0.765, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   1%|▏         | 14/938 [00:00<01:03, 14.59it/s, loss=0.761, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   2%|▏         | 15/938 [00:01<01:03, 14.53it/s, loss=0.761, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   2%|▏         | 16/938 [00:01<01:03, 14.55it/s, loss=0.761, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   2%|▏         | 16/938 [00:01<01:03, 14.54it/s, loss=0.766, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   2%|▏         | 17/938 [00:01<01:03, 14.60it/s, loss=0.773, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   2%|▏         | 18/938 [00:01<01:03, 14.46it/s, loss=0.774, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   2%|▏         | 19/938 [00:01<01:04, 14.36it/s, loss=0.779, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   2%|▏         | 20/938 [00:01<01:04, 14.30it/s, loss=0.779, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   2%|▏         | 20/938 [00:01<01:04, 14.30it/s, loss=0.782, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   2%|▏         | 21/938 [00:01<01:04, 14.29it/s, loss=0.785, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   2%|▏         | 22/938 [00:01<01:03, 14.33it/s, loss=0.775, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   2%|▏         | 23/938 [00:01<01:03, 14.48it/s, loss=0.776, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   3%|▎         | 24/938 [00:01<01:03, 14.48it/s, loss=0.776, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   3%|▎         | 24/938 [00:01<01:03, 14.47it/s, loss=0.786, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   3%|▎         | 25/938 [00:01<01:03, 14.48it/s, loss=0.776, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   3%|▎         | 26/938 [00:01<01:03, 14.47it/s, loss=0.772, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   3%|▎         | 27/938 [00:01<01:03, 14.40it/s, loss=0.775, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   3%|▎         | 28/938 [00:01<01:03, 14.40it/s, loss=0.775, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   3%|▎         | 28/938 [00:01<01:03, 14.39it/s, loss=0.777, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   3%|▎         | 29/938 [00:02<01:02, 14.44it/s, loss=0.778, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   3%|▎         | 30/938 [00:02<01:03, 14.38it/s, loss=0.774, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   3%|▎         | 31/938 [00:02<01:02, 14.42it/s, loss=0.795, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   3%|▎         | 32/938 [00:02<01:02, 14.44it/s, loss=0.795, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   3%|▎         | 32/938 [00:02<01:02, 14.44it/s, loss=0.792, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   4%|▎         | 33/938 [00:02<01:02, 14.39it/s, loss=0.785, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   4%|▎         | 34/938 [00:02<01:03, 14.26it/s, loss=0.78, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:   4%|▎         | 35/938 [00:02<01:03, 14.32it/s, loss=0.775, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   4%|▍         | 36/938 [00:02<01:02, 14.33it/s, loss=0.775, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   4%|▍         | 36/938 [00:02<01:02, 14.33it/s, loss=0.777, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   4%|▍         | 37/938 [00:02<01:02, 14.37it/s, loss=0.769, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   4%|▍         | 38/938 [00:02<01:02, 14.36it/s, loss=0.76, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:   4%|▍         | 39/938 [00:02<01:02, 14.27it/s, loss=0.753, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   4%|▍         | 40/938 [00:02<01:03, 14.25it/s, loss=0.753, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   4%|▍         | 40/938 [00:02<01:03, 14.25it/s, loss=0.749, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   4%|▍         | 41/938 [00:02<01:02, 14.34it/s, loss=0.762, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   4%|▍         | 42/938 [00:02<01:02, 14.38it/s, loss=0.759, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   5%|▍         | 43/938 [00:02<01:02, 14.38it/s, loss=0.756, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   5%|▍         | 44/938 [00:03<01:01, 14.43it/s, loss=0.756, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   5%|▍         | 44/938 [00:03<01:01, 14.43it/s, loss=0.752, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   5%|▍         | 45/938 [00:03<01:01, 14.44it/s, loss=0.754, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   5%|▍         | 46/938 [00:03<01:01, 14.44it/s, loss=0.755, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   5%|▌         | 47/938 [00:03<01:01, 14.45it/s, loss=0.751, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   5%|▌         | 48/938 [00:03<01:01, 14.47it/s, loss=0.751, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   5%|▌         | 48/938 [00:03<01:01, 14.47it/s, loss=0.754, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   5%|▌         | 49/938 [00:03<01:01, 14.48it/s, loss=0.76, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:   5%|▌         | 50/938 [00:03<01:01, 14.49it/s, loss=0.758, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   5%|▌         | 51/938 [00:03<01:01, 14.38it/s, loss=0.743, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   6%|▌         | 52/938 [00:03<01:01, 14.37it/s, loss=0.743, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   6%|▌         | 52/938 [00:03<01:01, 14.37it/s, loss=0.751, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   6%|▌         | 53/938 [00:03<01:01, 14.43it/s, loss=0.759, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   6%|▌         | 54/938 [00:03<01:01, 14.44it/s, loss=0.762, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   6%|▌         | 55/938 [00:03<01:01, 14.47it/s, loss=0.757, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   6%|▌         | 56/938 [00:03<01:01, 14.44it/s, loss=0.757, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   6%|▌         | 56/938 [00:03<01:01, 14.43it/s, loss=0.757, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   6%|▌         | 57/938 [00:03<01:01, 14.41it/s, loss=0.772, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   6%|▌         | 58/938 [00:04<01:00, 14.44it/s, loss=0.77, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:   6%|▋         | 59/938 [00:04<01:00, 14.43it/s, loss=0.774, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   6%|▋         | 60/938 [00:04<01:00, 14.42it/s, loss=0.774, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   6%|▋         | 60/938 [00:04<01:00, 14.41it/s, loss=0.772, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   7%|▋         | 61/938 [00:04<01:00, 14.43it/s, loss=0.758, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   7%|▋         | 62/938 [00:04<01:00, 14.43it/s, loss=0.756, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   7%|▋         | 63/938 [00:04<01:00, 14.40it/s, loss=0.756, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   7%|▋         | 64/938 [00:04<01:00, 14.40it/s, loss=0.756, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   7%|▋         | 64/938 [00:04<01:00, 14.39it/s, loss=0.757, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   7%|▋         | 65/938 [00:04<01:00, 14.40it/s, loss=0.756, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   7%|▋         | 66/938 [00:04<01:00, 14.38it/s, loss=0.757, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   7%|▋         | 67/938 [00:04<01:00, 14.34it/s, loss=0.755, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   7%|▋         | 68/938 [00:04<01:00, 14.35it/s, loss=0.755, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   7%|▋         | 68/938 [00:04<01:00, 14.35it/s, loss=0.751, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   7%|▋         | 69/938 [00:04<01:00, 14.32it/s, loss=0.738, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   7%|▋         | 70/938 [00:04<01:00, 14.32it/s, loss=0.746, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   8%|▊         | 71/938 [00:04<01:00, 14.34it/s, loss=0.75, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:   8%|▊         | 72/938 [00:05<01:00, 14.33it/s, loss=0.75, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   8%|▊         | 72/938 [00:05<01:00, 14.33it/s, loss=0.741, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   8%|▊         | 73/938 [00:05<01:00, 14.33it/s, loss=0.734, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   8%|▊         | 74/938 [00:05<01:00, 14.31it/s, loss=0.741, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   8%|▊         | 75/938 [00:05<01:00, 14.27it/s, loss=0.747, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   8%|▊         | 76/938 [00:05<01:00, 14.28it/s, loss=0.747, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   8%|▊         | 76/938 [00:05<01:00, 14.28it/s, loss=0.738, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   8%|▊         | 77/938 [00:05<01:00, 14.25it/s, loss=0.725, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   8%|▊         | 78/938 [00:05<01:00, 14.24it/s, loss=0.733, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   8%|▊         | 79/938 [00:05<01:00, 14.25it/s, loss=0.731, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   9%|▊         | 80/938 [00:05<01:00, 14.19it/s, loss=0.731, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   9%|▊         | 80/938 [00:05<01:00, 14.19it/s, loss=0.739, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   9%|▊         | 81/938 [00:05<01:00, 14.20it/s, loss=0.748, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   9%|▊         | 82/938 [00:05<01:00, 14.20it/s, loss=0.754, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   9%|▉         | 83/938 [00:05<01:00, 14.21it/s, loss=0.755, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   9%|▉         | 84/938 [00:05<01:00, 14.20it/s, loss=0.755, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   9%|▉         | 84/938 [00:05<01:00, 14.20it/s, loss=0.751, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   9%|▉         | 85/938 [00:05<01:00, 14.20it/s, loss=0.755, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   9%|▉         | 86/938 [00:06<01:00, 14.19it/s, loss=0.753, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   9%|▉         | 87/938 [00:06<01:00, 14.07it/s, loss=0.756, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   9%|▉         | 88/938 [00:06<01:00, 14.06it/s, loss=0.756, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   9%|▉         | 88/938 [00:06<01:00, 14.06it/s, loss=0.757, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:   9%|▉         | 89/938 [00:06<01:00, 14.09it/s, loss=0.767, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  10%|▉         | 90/938 [00:06<01:00, 14.07it/s, loss=0.768, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  10%|▉         | 91/938 [00:06<01:00, 14.09it/s, loss=0.761, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  10%|▉         | 92/938 [00:06<01:00, 14.10it/s, loss=0.761, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  10%|▉         | 92/938 [00:06<01:00, 14.10it/s, loss=0.764, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  10%|▉         | 93/938 [00:06<00:59, 14.12it/s, loss=0.766, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  10%|█         | 94/938 [00:06<00:59, 14.15it/s, loss=0.771, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  10%|█         | 95/938 [00:06<00:59, 14.16it/s, loss=0.767, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  10%|█         | 96/938 [00:06<00:59, 14.16it/s, loss=0.767, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  10%|█         | 96/938 [00:06<00:59, 14.16it/s, loss=0.772, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  10%|█         | 97/938 [00:06<00:59, 14.15it/s, loss=0.784, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  10%|█         | 98/938 [00:06<00:59, 14.16it/s, loss=0.776, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  11%|█         | 99/938 [00:06<00:59, 14.15it/s, loss=0.786, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  11%|█         | 100/938 [00:07<00:59, 14.15it/s, loss=0.786, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  11%|█         | 100/938 [00:07<00:59, 14.15it/s, loss=0.784, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  11%|█         | 101/938 [00:07<00:59, 14.18it/s, loss=0.773, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  11%|█         | 102/938 [00:07<00:59, 14.17it/s, loss=0.766, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  11%|█         | 103/938 [00:07<00:58, 14.17it/s, loss=0.769, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  11%|█         | 104/938 [00:07<00:58, 14.19it/s, loss=0.769, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  11%|█         | 104/938 [00:07<00:58, 14.19it/s, loss=0.776, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  11%|█         | 105/938 [00:07<00:58, 14.21it/s, loss=0.768, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  11%|█▏        | 106/938 [00:07<00:58, 14.17it/s, loss=0.767, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  11%|█▏        | 107/938 [00:07<00:58, 14.21it/s, loss=0.76, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  12%|█▏        | 108/938 [00:07<00:58, 14.20it/s, loss=0.76, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  12%|█▏        | 108/938 [00:07<00:58, 14.20it/s, loss=0.756, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  12%|█▏        | 109/938 [00:07<00:58, 14.22it/s, loss=0.749, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  12%|█▏        | 110/938 [00:07<00:58, 14.23it/s, loss=0.742, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  12%|█▏        | 111/938 [00:07<00:58, 14.22it/s, loss=0.738, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  12%|█▏        | 112/938 [00:07<00:58, 14.21it/s, loss=0.738, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  12%|█▏        | 112/938 [00:07<00:58, 14.21it/s, loss=0.734, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  12%|█▏        | 113/938 [00:07<00:58, 14.20it/s, loss=0.736, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  12%|█▏        | 114/938 [00:08<00:58, 14.21it/s, loss=0.727, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  12%|█▏        | 115/938 [00:08<00:57, 14.20it/s, loss=0.722, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  12%|█▏        | 116/938 [00:08<00:57, 14.22it/s, loss=0.722, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  12%|█▏        | 116/938 [00:08<00:57, 14.22it/s, loss=0.718, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  12%|█▏        | 117/938 [00:08<00:57, 14.16it/s, loss=0.711, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  13%|█▎        | 118/938 [00:08<00:57, 14.14it/s, loss=0.721, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  13%|█▎        | 119/938 [00:08<00:57, 14.16it/s, loss=0.714, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  13%|█▎        | 120/938 [00:08<00:57, 14.15it/s, loss=0.714, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  13%|█▎        | 120/938 [00:08<00:57, 14.15it/s, loss=0.711, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  13%|█▎        | 121/938 [00:08<00:57, 14.16it/s, loss=0.712, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  13%|█▎        | 122/938 [00:08<00:57, 14.14it/s, loss=0.72, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  13%|█▎        | 123/938 [00:08<00:57, 14.15it/s, loss=0.721, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  13%|█▎        | 124/938 [00:08<00:57, 14.17it/s, loss=0.721, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  13%|█▎        | 124/938 [00:08<00:57, 14.17it/s, loss=0.713, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  13%|█▎        | 125/938 [00:08<00:57, 14.16it/s, loss=0.719, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  13%|█▎        | 126/938 [00:08<00:57, 14.17it/s, loss=0.724, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  14%|█▎        | 127/938 [00:08<00:57, 14.17it/s, loss=0.726, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  14%|█▎        | 128/938 [00:09<00:57, 14.19it/s, loss=0.726, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  14%|█▎        | 128/938 [00:09<00:57, 14.19it/s, loss=0.731, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  14%|█▍        | 129/938 [00:09<00:57, 14.18it/s, loss=0.73, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  14%|█▍        | 130/938 [00:09<00:56, 14.19it/s, loss=0.737, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  14%|█▍        | 131/938 [00:09<00:56, 14.20it/s, loss=0.734, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  14%|█▍        | 132/938 [00:09<00:56, 14.21it/s, loss=0.734, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  14%|█▍        | 132/938 [00:09<00:56, 14.21it/s, loss=0.744, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  14%|█▍        | 133/938 [00:09<00:56, 14.22it/s, loss=0.737, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  14%|█▍        | 134/938 [00:09<00:56, 14.22it/s, loss=0.736, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  14%|█▍        | 135/938 [00:09<00:56, 14.23it/s, loss=0.747, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  14%|█▍        | 136/938 [00:09<00:56, 14.25it/s, loss=0.747, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  14%|█▍        | 136/938 [00:09<00:56, 14.25it/s, loss=0.749, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  15%|█▍        | 137/938 [00:09<00:56, 14.26it/s, loss=0.746, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  15%|█▍        | 138/938 [00:09<00:56, 14.26it/s, loss=0.743, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  15%|█▍        | 139/938 [00:09<00:56, 14.26it/s, loss=0.74, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  15%|█▍        | 140/938 [00:09<00:56, 14.23it/s, loss=0.74, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  15%|█▍        | 140/938 [00:09<00:56, 14.23it/s, loss=0.742, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  15%|█▌        | 141/938 [00:09<00:56, 14.22it/s, loss=0.744, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  15%|█▌        | 142/938 [00:09<00:55, 14.24it/s, loss=0.737, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  15%|█▌        | 143/938 [00:10<00:55, 14.26it/s, loss=0.729, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  15%|█▌        | 144/938 [00:10<00:55, 14.27it/s, loss=0.729, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  15%|█▌        | 144/938 [00:10<00:55, 14.27it/s, loss=0.729, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  15%|█▌        | 145/938 [00:10<00:55, 14.29it/s, loss=0.727, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  16%|█▌        | 146/938 [00:10<00:55, 14.29it/s, loss=0.725, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  16%|█▌        | 147/938 [00:10<00:55, 14.21it/s, loss=0.73, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  16%|█▌        | 148/938 [00:10<00:55, 14.19it/s, loss=0.73, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  16%|█▌        | 148/938 [00:10<00:55, 14.19it/s, loss=0.742, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  16%|█▌        | 149/938 [00:10<00:55, 14.18it/s, loss=0.74, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  16%|█▌        | 150/938 [00:10<00:55, 14.20it/s, loss=0.732, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  16%|█▌        | 151/938 [00:10<00:55, 14.21it/s, loss=0.744, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  16%|█▌        | 152/938 [00:10<00:55, 14.22it/s, loss=0.744, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  16%|█▌        | 152/938 [00:10<00:55, 14.22it/s, loss=0.74, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  16%|█▋        | 153/938 [00:10<00:55, 14.23it/s, loss=0.744, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  16%|█▋        | 154/938 [00:10<00:55, 14.23it/s, loss=0.742, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  17%|█▋        | 155/938 [00:10<00:55, 14.23it/s, loss=0.742, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  17%|█▋        | 156/938 [00:10<00:54, 14.24it/s, loss=0.742, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  17%|█▋        | 156/938 [00:10<00:54, 14.24it/s, loss=0.745, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  17%|█▋        | 157/938 [00:11<00:54, 14.25it/s, loss=0.749, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  17%|█▋        | 158/938 [00:11<00:54, 14.25it/s, loss=0.741, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  17%|█▋        | 159/938 [00:11<00:54, 14.27it/s, loss=0.746, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  17%|█▋        | 160/938 [00:11<00:54, 14.26it/s, loss=0.746, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  17%|█▋        | 160/938 [00:11<00:54, 14.26it/s, loss=0.749, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  17%|█▋        | 161/938 [00:11<00:54, 14.27it/s, loss=0.748, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  17%|█▋        | 162/938 [00:11<00:54, 14.28it/s, loss=0.753, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  17%|█▋        | 163/938 [00:11<00:54, 14.28it/s, loss=0.762, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  17%|█▋        | 164/938 [00:11<00:54, 14.27it/s, loss=0.762, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  17%|█▋        | 164/938 [00:11<00:54, 14.27it/s, loss=0.765, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  18%|█▊        | 165/938 [00:11<00:54, 14.28it/s, loss=0.759, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  18%|█▊        | 166/938 [00:11<00:54, 14.28it/s, loss=0.761, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  18%|█▊        | 167/938 [00:11<00:53, 14.28it/s, loss=0.754, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  18%|█▊        | 168/938 [00:11<00:53, 14.29it/s, loss=0.754, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  18%|█▊        | 168/938 [00:11<00:53, 14.29it/s, loss=0.736, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  18%|█▊        | 169/938 [00:11<00:53, 14.28it/s, loss=0.742, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  18%|█▊        | 170/938 [00:11<00:53, 14.28it/s, loss=0.751, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  18%|█▊        | 171/938 [00:11<00:53, 14.28it/s, loss=0.747, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  18%|█▊        | 172/938 [00:12<00:53, 14.29it/s, loss=0.747, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  18%|█▊        | 172/938 [00:12<00:53, 14.29it/s, loss=0.745, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  18%|█▊        | 173/938 [00:12<00:53, 14.29it/s, loss=0.745, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  19%|█▊        | 174/938 [00:12<00:53, 14.28it/s, loss=0.742, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  19%|█▊        | 175/938 [00:12<00:53, 14.20it/s, loss=0.734, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  19%|█▉        | 176/938 [00:12<00:53, 14.21it/s, loss=0.734, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  19%|█▉        | 176/938 [00:12<00:53, 14.21it/s, loss=0.734, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  19%|█▉        | 177/938 [00:12<00:53, 14.20it/s, loss=0.735, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  19%|█▉        | 178/938 [00:12<00:53, 14.21it/s, loss=0.734, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  19%|█▉        | 179/938 [00:12<00:53, 14.23it/s, loss=0.724, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  19%|█▉        | 180/938 [00:12<00:53, 14.23it/s, loss=0.724, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  19%|█▉        | 180/938 [00:12<00:53, 14.23it/s, loss=0.72, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  19%|█▉        | 181/938 [00:12<00:53, 14.24it/s, loss=0.715, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  19%|█▉        | 182/938 [00:12<00:53, 14.23it/s, loss=0.714, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  20%|█▉        | 183/938 [00:12<00:53, 14.23it/s, loss=0.709, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  20%|█▉        | 184/938 [00:12<00:52, 14.23it/s, loss=0.709, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  20%|█▉        | 184/938 [00:12<00:52, 14.23it/s, loss=0.703, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  20%|█▉        | 185/938 [00:12<00:52, 14.24it/s, loss=0.703, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  20%|█▉        | 186/938 [00:13<00:52, 14.25it/s, loss=0.7, v_num=10, val_rmse=0.659, train_rmse=1.190]  
Epoch 1:  20%|█▉        | 187/938 [00:13<00:52, 14.25it/s, loss=0.7, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  20%|██        | 188/938 [00:13<00:52, 14.26it/s, loss=0.7, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  20%|██        | 188/938 [00:13<00:52, 14.26it/s, loss=0.706, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  20%|██        | 189/938 [00:13<00:52, 14.26it/s, loss=0.709, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  20%|██        | 190/938 [00:13<00:52, 14.26it/s, loss=0.703, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  20%|██        | 191/938 [00:13<00:53, 14.02it/s, loss=0.693, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  20%|██        | 192/938 [00:13<00:53, 14.03it/s, loss=0.693, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  20%|██        | 192/938 [00:13<00:53, 14.03it/s, loss=0.696, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  21%|██        | 193/938 [00:13<00:53, 14.03it/s, loss=0.698, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  21%|██        | 194/938 [00:13<00:53, 14.02it/s, loss=0.698, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  21%|██        | 195/938 [00:13<00:52, 14.04it/s, loss=0.711, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  21%|██        | 196/938 [00:13<00:52, 14.03it/s, loss=0.711, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  21%|██        | 196/938 [00:13<00:52, 14.03it/s, loss=0.712, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  21%|██        | 197/938 [00:14<00:52, 14.03it/s, loss=0.705, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  21%|██        | 198/938 [00:14<00:52, 14.02it/s, loss=0.714, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  21%|██        | 199/938 [00:14<00:52, 14.01it/s, loss=0.717, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  21%|██▏       | 200/938 [00:14<00:52, 14.03it/s, loss=0.717, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  21%|██▏       | 200/938 [00:14<00:52, 14.02it/s, loss=0.723, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  21%|██▏       | 201/938 [00:14<00:52, 14.04it/s, loss=0.723, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  22%|██▏       | 202/938 [00:14<00:52, 14.05it/s, loss=0.723, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  22%|██▏       | 203/938 [00:14<00:52, 14.06it/s, loss=0.729, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  22%|██▏       | 204/938 [00:14<00:52, 14.06it/s, loss=0.729, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  22%|██▏       | 204/938 [00:14<00:52, 14.06it/s, loss=0.736, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  22%|██▏       | 205/938 [00:14<00:52, 14.05it/s, loss=0.742, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  22%|██▏       | 206/938 [00:14<00:52, 14.07it/s, loss=0.743, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  22%|██▏       | 207/938 [00:14<00:52, 14.05it/s, loss=0.745, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  22%|██▏       | 208/938 [00:14<00:51, 14.05it/s, loss=0.745, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  22%|██▏       | 208/938 [00:14<00:51, 14.05it/s, loss=0.742, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  22%|██▏       | 209/938 [00:14<00:51, 14.07it/s, loss=0.742, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  22%|██▏       | 210/938 [00:14<00:51, 14.07it/s, loss=0.734, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  22%|██▏       | 211/938 [00:14<00:51, 14.07it/s, loss=0.744, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  23%|██▎       | 212/938 [00:15<00:51, 14.08it/s, loss=0.744, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  23%|██▎       | 212/938 [00:15<00:51, 14.08it/s, loss=0.741, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  23%|██▎       | 213/938 [00:15<00:51, 14.07it/s, loss=0.753, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  23%|██▎       | 214/938 [00:15<00:51, 14.08it/s, loss=0.749, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  23%|██▎       | 215/938 [00:15<00:51, 14.08it/s, loss=0.737, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  23%|██▎       | 216/938 [00:15<00:51, 14.09it/s, loss=0.737, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  23%|██▎       | 216/938 [00:15<00:51, 14.09it/s, loss=0.734, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  23%|██▎       | 217/938 [00:15<00:51, 14.07it/s, loss=0.74, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  23%|██▎       | 218/938 [00:15<00:51, 14.04it/s, loss=0.742, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  23%|██▎       | 219/938 [00:15<00:51, 14.04it/s, loss=0.747, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  23%|██▎       | 220/938 [00:15<00:51, 14.03it/s, loss=0.747, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  23%|██▎       | 220/938 [00:15<00:51, 14.03it/s, loss=0.736, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  24%|██▎       | 221/938 [00:15<00:51, 14.03it/s, loss=0.737, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  24%|██▎       | 222/938 [00:15<00:51, 14.04it/s, loss=0.731, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  24%|██▍       | 223/938 [00:15<00:50, 14.03it/s, loss=0.728, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  24%|██▍       | 224/938 [00:15<00:50, 14.03it/s, loss=0.728, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  24%|██▍       | 224/938 [00:15<00:50, 14.03it/s, loss=0.723, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  24%|██▍       | 225/938 [00:16<00:50, 14.04it/s, loss=0.717, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  24%|██▍       | 226/938 [00:16<00:50, 14.05it/s, loss=0.721, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  24%|██▍       | 227/938 [00:16<00:50, 14.06it/s, loss=0.722, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  24%|██▍       | 228/938 [00:16<00:50, 14.06it/s, loss=0.722, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  24%|██▍       | 228/938 [00:16<00:50, 14.06it/s, loss=0.718, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  24%|██▍       | 229/938 [00:16<00:50, 14.06it/s, loss=0.712, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  25%|██▍       | 230/938 [00:16<00:50, 14.05it/s, loss=0.724, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  25%|██▍       | 231/938 [00:16<00:50, 14.06it/s, loss=0.723, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  25%|██▍       | 232/938 [00:16<00:50, 14.07it/s, loss=0.723, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  25%|██▍       | 232/938 [00:16<00:50, 14.06it/s, loss=0.719, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  25%|██▍       | 233/938 [00:16<00:50, 14.04it/s, loss=0.714, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  25%|██▍       | 234/938 [00:16<00:50, 14.04it/s, loss=0.718, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  25%|██▌       | 235/938 [00:16<00:50, 14.05it/s, loss=0.725, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  25%|██▌       | 236/938 [00:16<00:50, 14.04it/s, loss=0.725, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  25%|██▌       | 236/938 [00:16<00:50, 14.04it/s, loss=0.73, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  25%|██▌       | 237/938 [00:16<00:49, 14.04it/s, loss=0.731, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  25%|██▌       | 238/938 [00:16<00:49, 14.04it/s, loss=0.721, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  25%|██▌       | 239/938 [00:17<00:49, 14.04it/s, loss=0.715, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  26%|██▌       | 240/938 [00:17<00:49, 14.03it/s, loss=0.715, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  26%|██▌       | 240/938 [00:17<00:49, 14.03it/s, loss=0.718, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  26%|██▌       | 241/938 [00:17<00:49, 14.02it/s, loss=0.722, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  26%|██▌       | 242/938 [00:17<00:49, 14.03it/s, loss=0.734, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  26%|██▌       | 243/938 [00:17<00:49, 14.04it/s, loss=0.734, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  26%|██▌       | 244/938 [00:17<00:49, 14.05it/s, loss=0.734, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  26%|██▌       | 244/938 [00:17<00:49, 14.05it/s, loss=0.734, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  26%|██▌       | 245/938 [00:17<00:49, 14.05it/s, loss=0.744, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  26%|██▌       | 246/938 [00:17<00:49, 14.06it/s, loss=0.741, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  26%|██▋       | 247/938 [00:17<00:49, 14.05it/s, loss=0.743, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  26%|██▋       | 248/938 [00:17<00:49, 14.06it/s, loss=0.743, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  26%|██▋       | 248/938 [00:17<00:49, 14.06it/s, loss=0.745, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  27%|██▋       | 249/938 [00:17<00:48, 14.07it/s, loss=0.743, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  27%|██▋       | 250/938 [00:17<00:48, 14.07it/s, loss=0.74, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  27%|██▋       | 251/938 [00:17<00:48, 14.08it/s, loss=0.739, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  27%|██▋       | 252/938 [00:17<00:48, 14.08it/s, loss=0.739, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  27%|██▋       | 252/938 [00:17<00:48, 14.08it/s, loss=0.749, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  27%|██▋       | 253/938 [00:17<00:48, 14.08it/s, loss=0.74, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  27%|██▋       | 254/938 [00:18<00:48, 14.08it/s, loss=0.739, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  27%|██▋       | 255/938 [00:18<00:48, 14.09it/s, loss=0.726, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  27%|██▋       | 256/938 [00:18<00:48, 14.08it/s, loss=0.726, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  27%|██▋       | 256/938 [00:18<00:48, 14.08it/s, loss=0.725, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  27%|██▋       | 257/938 [00:18<00:48, 14.09it/s, loss=0.72, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  28%|██▊       | 258/938 [00:18<00:48, 14.10it/s, loss=0.721, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  28%|██▊       | 259/938 [00:18<00:48, 14.08it/s, loss=0.726, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  28%|██▊       | 260/938 [00:18<00:48, 14.08it/s, loss=0.726, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  28%|██▊       | 260/938 [00:18<00:48, 14.08it/s, loss=0.724, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  28%|██▊       | 261/938 [00:18<00:48, 14.07it/s, loss=0.723, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  28%|██▊       | 262/938 [00:18<00:48, 14.07it/s, loss=0.718, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  28%|██▊       | 263/938 [00:18<00:47, 14.07it/s, loss=0.713, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  28%|██▊       | 264/938 [00:18<00:47, 14.06it/s, loss=0.713, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  28%|██▊       | 264/938 [00:18<00:47, 14.06it/s, loss=0.717, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  28%|██▊       | 265/938 [00:18<00:47, 14.04it/s, loss=0.714, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  28%|██▊       | 266/938 [00:18<00:47, 14.05it/s, loss=0.722, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  28%|██▊       | 267/938 [00:19<00:47, 14.05it/s, loss=0.727, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  29%|██▊       | 268/938 [00:19<00:47, 14.04it/s, loss=0.727, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  29%|██▊       | 268/938 [00:19<00:47, 14.04it/s, loss=0.731, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  29%|██▊       | 269/938 [00:19<00:47, 14.05it/s, loss=0.736, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  29%|██▉       | 270/938 [00:19<00:47, 14.04it/s, loss=0.734, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  29%|██▉       | 271/938 [00:19<00:47, 14.05it/s, loss=0.735, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  29%|██▉       | 272/938 [00:19<00:47, 14.05it/s, loss=0.735, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  29%|██▉       | 272/938 [00:19<00:47, 14.05it/s, loss=0.743, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  29%|██▉       | 273/938 [00:19<00:47, 14.05it/s, loss=0.742, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  29%|██▉       | 274/938 [00:19<00:47, 14.05it/s, loss=0.75, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  29%|██▉       | 275/938 [00:19<00:47, 14.05it/s, loss=0.761, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  29%|██▉       | 276/938 [00:19<00:47, 14.05it/s, loss=0.761, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  29%|██▉       | 276/938 [00:19<00:47, 14.05it/s, loss=0.76, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  30%|██▉       | 277/938 [00:19<00:47, 14.06it/s, loss=0.764, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  30%|██▉       | 278/938 [00:19<00:46, 14.06it/s, loss=0.77, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  30%|██▉       | 279/938 [00:19<00:46, 14.05it/s, loss=0.762, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  30%|██▉       | 280/938 [00:19<00:46, 14.07it/s, loss=0.762, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  30%|██▉       | 280/938 [00:19<00:46, 14.07it/s, loss=0.763, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  30%|██▉       | 281/938 [00:19<00:46, 14.06it/s, loss=0.766, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  30%|███       | 282/938 [00:20<00:46, 14.06it/s, loss=0.767, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  30%|███       | 283/938 [00:20<00:46, 14.07it/s, loss=0.765, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  30%|███       | 284/938 [00:20<00:46, 14.07it/s, loss=0.765, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  30%|███       | 284/938 [00:20<00:46, 14.07it/s, loss=0.757, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  30%|███       | 285/938 [00:20<00:46, 14.07it/s, loss=0.747, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  30%|███       | 286/938 [00:20<00:46, 14.09it/s, loss=0.741, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  31%|███       | 287/938 [00:20<00:46, 14.09it/s, loss=0.742, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  31%|███       | 288/938 [00:20<00:46, 14.10it/s, loss=0.742, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  31%|███       | 288/938 [00:20<00:46, 14.10it/s, loss=0.742, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  31%|███       | 289/938 [00:20<00:46, 14.10it/s, loss=0.737, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  31%|███       | 290/938 [00:20<00:45, 14.09it/s, loss=0.735, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  31%|███       | 291/938 [00:20<00:45, 14.09it/s, loss=0.731, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  31%|███       | 292/938 [00:20<00:45, 14.09it/s, loss=0.731, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  31%|███       | 292/938 [00:20<00:45, 14.09it/s, loss=0.724, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  31%|███       | 293/938 [00:20<00:45, 14.10it/s, loss=0.724, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  31%|███▏      | 294/938 [00:20<00:45, 14.11it/s, loss=0.72, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  31%|███▏      | 295/938 [00:20<00:45, 14.11it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  32%|███▏      | 296/938 [00:20<00:45, 14.10it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  32%|███▏      | 296/938 [00:20<00:45, 14.10it/s, loss=0.706, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  32%|███▏      | 297/938 [00:21<00:45, 14.10it/s, loss=0.7, v_num=10, val_rmse=0.659, train_rmse=1.190]  
Epoch 1:  32%|███▏      | 298/938 [00:21<00:45, 14.10it/s, loss=0.697, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  32%|███▏      | 299/938 [00:21<00:45, 14.10it/s, loss=0.696, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  32%|███▏      | 300/938 [00:21<00:45, 14.10it/s, loss=0.696, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  32%|███▏      | 300/938 [00:21<00:45, 14.10it/s, loss=0.696, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  32%|███▏      | 301/938 [00:21<00:45, 14.11it/s, loss=0.687, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  32%|███▏      | 302/938 [00:21<00:45, 14.12it/s, loss=0.683, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  32%|███▏      | 303/938 [00:21<00:44, 14.12it/s, loss=0.69, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  32%|███▏      | 304/938 [00:21<00:44, 14.13it/s, loss=0.69, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  32%|███▏      | 304/938 [00:21<00:44, 14.13it/s, loss=0.696, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  33%|███▎      | 305/938 [00:21<00:44, 14.10it/s, loss=0.698, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  33%|███▎      | 306/938 [00:21<00:44, 14.11it/s, loss=0.707, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  33%|███▎      | 307/938 [00:21<00:44, 14.10it/s, loss=0.695, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  33%|███▎      | 308/938 [00:21<00:44, 14.10it/s, loss=0.695, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  33%|███▎      | 308/938 [00:21<00:44, 14.10it/s, loss=0.687, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  33%|███▎      | 309/938 [00:21<00:44, 14.10it/s, loss=0.683, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  33%|███▎      | 310/938 [00:21<00:44, 14.10it/s, loss=0.679, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  33%|███▎      | 311/938 [00:22<00:44, 14.09it/s, loss=0.684, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  33%|███▎      | 312/938 [00:22<00:44, 14.10it/s, loss=0.684, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  33%|███▎      | 312/938 [00:22<00:44, 14.10it/s, loss=0.684, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  33%|███▎      | 313/938 [00:22<00:44, 14.10it/s, loss=0.679, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  33%|███▎      | 314/938 [00:22<00:44, 14.10it/s, loss=0.677, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  34%|███▎      | 315/938 [00:22<00:44, 14.11it/s, loss=0.7, v_num=10, val_rmse=0.659, train_rmse=1.190]  
Epoch 1:  34%|███▎      | 316/938 [00:22<00:44, 14.11it/s, loss=0.7, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  34%|███▎      | 316/938 [00:22<00:44, 14.11it/s, loss=0.696, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  34%|███▍      | 317/938 [00:22<00:44, 14.11it/s, loss=0.694, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  34%|███▍      | 318/938 [00:22<00:43, 14.12it/s, loss=0.703, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  34%|███▍      | 319/938 [00:22<00:43, 14.12it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  34%|███▍      | 320/938 [00:22<00:43, 14.12it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  34%|███▍      | 320/938 [00:22<00:43, 14.12it/s, loss=0.714, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  34%|███▍      | 321/938 [00:22<00:43, 14.12it/s, loss=0.716, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  34%|███▍      | 322/938 [00:22<00:43, 14.12it/s, loss=0.724, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  34%|███▍      | 323/938 [00:22<00:43, 14.11it/s, loss=0.72, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  35%|███▍      | 324/938 [00:22<00:43, 14.12it/s, loss=0.72, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  35%|███▍      | 324/938 [00:22<00:43, 14.12it/s, loss=0.724, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  35%|███▍      | 325/938 [00:23<00:43, 14.12it/s, loss=0.723, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  35%|███▍      | 326/938 [00:23<00:43, 14.13it/s, loss=0.705, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  35%|███▍      | 327/938 [00:23<00:43, 14.14it/s, loss=0.71, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  35%|███▍      | 328/938 [00:23<00:43, 14.14it/s, loss=0.71, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  35%|███▍      | 328/938 [00:23<00:43, 14.14it/s, loss=0.714, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  35%|███▌      | 329/938 [00:23<00:43, 14.14it/s, loss=0.718, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  35%|███▌      | 330/938 [00:23<00:42, 14.15it/s, loss=0.725, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  35%|███▌      | 331/938 [00:23<00:42, 14.14it/s, loss=0.719, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  35%|███▌      | 332/938 [00:23<00:42, 14.15it/s, loss=0.719, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  35%|███▌      | 332/938 [00:23<00:42, 14.15it/s, loss=0.718, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  36%|███▌      | 333/938 [00:23<00:42, 14.15it/s, loss=0.723, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  36%|███▌      | 334/938 [00:23<00:42, 14.15it/s, loss=0.722, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  36%|███▌      | 335/938 [00:23<00:42, 14.15it/s, loss=0.703, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  36%|███▌      | 336/938 [00:23<00:42, 14.16it/s, loss=0.703, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  36%|███▌      | 336/938 [00:23<00:42, 14.16it/s, loss=0.712, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  36%|███▌      | 337/938 [00:23<00:42, 14.15it/s, loss=0.724, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  36%|███▌      | 338/938 [00:23<00:42, 14.15it/s, loss=0.711, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  36%|███▌      | 339/938 [00:23<00:42, 14.16it/s, loss=0.719, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  36%|███▌      | 340/938 [00:24<00:42, 14.15it/s, loss=0.719, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  36%|███▌      | 340/938 [00:24<00:42, 14.15it/s, loss=0.711, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  36%|███▋      | 341/938 [00:24<00:42, 14.16it/s, loss=0.719, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  36%|███▋      | 342/938 [00:24<00:42, 14.17it/s, loss=0.713, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  37%|███▋      | 343/938 [00:24<00:41, 14.17it/s, loss=0.723, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  37%|███▋      | 344/938 [00:24<00:41, 14.18it/s, loss=0.723, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  37%|███▋      | 344/938 [00:24<00:41, 14.18it/s, loss=0.722, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  37%|███▋      | 345/938 [00:24<00:41, 14.18it/s, loss=0.724, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  37%|███▋      | 346/938 [00:24<00:41, 14.17it/s, loss=0.732, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  37%|███▋      | 347/938 [00:24<00:41, 14.17it/s, loss=0.724, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  37%|███▋      | 348/938 [00:24<00:41, 14.18it/s, loss=0.724, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  37%|███▋      | 348/938 [00:24<00:41, 14.18it/s, loss=0.738, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  37%|███▋      | 349/938 [00:24<00:41, 14.18it/s, loss=0.742, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  37%|███▋      | 350/938 [00:24<00:41, 14.18it/s, loss=0.75, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  37%|███▋      | 351/938 [00:24<00:41, 14.18it/s, loss=0.754, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  38%|███▊      | 352/938 [00:24<00:41, 14.18it/s, loss=0.754, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  38%|███▊      | 352/938 [00:24<00:41, 14.18it/s, loss=0.752, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  38%|███▊      | 353/938 [00:24<00:41, 14.19it/s, loss=0.745, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  38%|███▊      | 354/938 [00:24<00:41, 14.18it/s, loss=0.745, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  38%|███▊      | 355/938 [00:25<00:41, 14.18it/s, loss=0.761, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  38%|███▊      | 356/938 [00:25<00:41, 14.18it/s, loss=0.761, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  38%|███▊      | 356/938 [00:25<00:41, 14.18it/s, loss=0.758, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  38%|███▊      | 357/938 [00:25<00:40, 14.19it/s, loss=0.748, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  38%|███▊      | 358/938 [00:25<00:40, 14.19it/s, loss=0.751, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  38%|███▊      | 359/938 [00:25<00:40, 14.19it/s, loss=0.744, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  38%|███▊      | 360/938 [00:25<00:40, 14.20it/s, loss=0.744, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  38%|███▊      | 360/938 [00:25<00:40, 14.20it/s, loss=0.747, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  38%|███▊      | 361/938 [00:25<00:40, 14.19it/s, loss=0.741, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  39%|███▊      | 362/938 [00:25<00:40, 14.20it/s, loss=0.738, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  39%|███▊      | 363/938 [00:25<00:40, 14.20it/s, loss=0.73, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  39%|███▉      | 364/938 [00:25<00:40, 14.21it/s, loss=0.73, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  39%|███▉      | 364/938 [00:25<00:40, 14.21it/s, loss=0.725, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  39%|███▉      | 365/938 [00:25<00:40, 14.21it/s, loss=0.719, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  39%|███▉      | 366/938 [00:25<00:40, 14.21it/s, loss=0.718, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  39%|███▉      | 367/938 [00:25<00:40, 14.21it/s, loss=0.715, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  39%|███▉      | 368/938 [00:25<00:40, 14.21it/s, loss=0.715, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  39%|███▉      | 368/938 [00:25<00:40, 14.21it/s, loss=0.7, v_num=10, val_rmse=0.659, train_rmse=1.190]  
Epoch 1:  39%|███▉      | 369/938 [00:25<00:40, 14.21it/s, loss=0.694, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  39%|███▉      | 370/938 [00:26<00:39, 14.20it/s, loss=0.69, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  40%|███▉      | 371/938 [00:26<00:39, 14.19it/s, loss=0.684, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  40%|███▉      | 372/938 [00:26<00:39, 14.19it/s, loss=0.684, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  40%|███▉      | 372/938 [00:26<00:39, 14.19it/s, loss=0.69, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  40%|███▉      | 373/938 [00:26<00:39, 14.20it/s, loss=0.694, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  40%|███▉      | 374/938 [00:26<00:39, 14.19it/s, loss=0.694, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  40%|███▉      | 375/938 [00:26<00:39, 14.20it/s, loss=0.678, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  40%|████      | 376/938 [00:26<00:39, 14.20it/s, loss=0.678, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  40%|████      | 376/938 [00:26<00:39, 14.20it/s, loss=0.673, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  40%|████      | 377/938 [00:26<00:39, 14.21it/s, loss=0.666, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  40%|████      | 378/938 [00:26<00:39, 14.20it/s, loss=0.667, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  40%|████      | 379/938 [00:26<00:39, 14.20it/s, loss=0.676, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  41%|████      | 380/938 [00:26<00:39, 14.21it/s, loss=0.676, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  41%|████      | 380/938 [00:26<00:39, 14.21it/s, loss=0.671, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  41%|████      | 381/938 [00:26<00:39, 14.21it/s, loss=0.682, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  41%|████      | 382/938 [00:26<00:39, 14.21it/s, loss=0.675, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  41%|████      | 383/938 [00:26<00:39, 14.21it/s, loss=0.68, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  41%|████      | 384/938 [00:27<00:38, 14.21it/s, loss=0.68, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  41%|████      | 384/938 [00:27<00:38, 14.21it/s, loss=0.687, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  41%|████      | 385/938 [00:27<00:38, 14.21it/s, loss=0.696, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  41%|████      | 386/938 [00:27<00:38, 14.22it/s, loss=0.694, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  41%|████▏     | 387/938 [00:27<00:38, 14.22it/s, loss=0.706, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  41%|████▏     | 388/938 [00:27<00:38, 14.22it/s, loss=0.706, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  41%|████▏     | 388/938 [00:27<00:38, 14.22it/s, loss=0.71, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  41%|████▏     | 389/938 [00:27<00:38, 14.22it/s, loss=0.712, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  42%|████▏     | 390/938 [00:27<00:38, 14.22it/s, loss=0.704, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  42%|████▏     | 391/938 [00:27<00:38, 14.22it/s, loss=0.709, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  42%|████▏     | 392/938 [00:27<00:38, 14.23it/s, loss=0.709, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  42%|████▏     | 392/938 [00:27<00:38, 14.22it/s, loss=0.702, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  42%|████▏     | 393/938 [00:27<00:38, 14.23it/s, loss=0.709, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  42%|████▏     | 394/938 [00:27<00:38, 14.23it/s, loss=0.712, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  42%|████▏     | 395/938 [00:27<00:38, 14.23it/s, loss=0.719, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  42%|████▏     | 396/938 [00:27<00:38, 14.21it/s, loss=0.719, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  42%|████▏     | 396/938 [00:27<00:38, 14.21it/s, loss=0.72, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  42%|████▏     | 397/938 [00:27<00:38, 14.22it/s, loss=0.728, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  42%|████▏     | 398/938 [00:28<00:37, 14.21it/s, loss=0.73, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  43%|████▎     | 399/938 [00:28<00:37, 14.21it/s, loss=0.718, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  43%|████▎     | 400/938 [00:28<00:37, 14.21it/s, loss=0.718, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  43%|████▎     | 400/938 [00:28<00:37, 14.21it/s, loss=0.718, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  43%|████▎     | 401/938 [00:28<00:37, 14.21it/s, loss=0.71, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  43%|████▎     | 402/938 [00:28<00:37, 14.21it/s, loss=0.72, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  43%|████▎     | 403/938 [00:28<00:37, 14.21it/s, loss=0.711, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  43%|████▎     | 404/938 [00:28<00:37, 14.21it/s, loss=0.711, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  43%|████▎     | 404/938 [00:28<00:37, 14.21it/s, loss=0.705, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  43%|████▎     | 405/938 [00:28<00:37, 14.21it/s, loss=0.704, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  43%|████▎     | 406/938 [00:28<00:37, 14.21it/s, loss=0.706, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  43%|████▎     | 407/938 [00:28<00:37, 14.22it/s, loss=0.703, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  43%|████▎     | 408/938 [00:28<00:37, 14.21it/s, loss=0.703, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  43%|████▎     | 408/938 [00:28<00:37, 14.21it/s, loss=0.698, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  44%|████▎     | 409/938 [00:28<00:37, 14.22it/s, loss=0.694, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  44%|████▎     | 410/938 [00:28<00:37, 14.22it/s, loss=0.695, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  44%|████▍     | 411/938 [00:28<00:37, 14.22it/s, loss=0.695, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  44%|████▍     | 412/938 [00:28<00:36, 14.22it/s, loss=0.695, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  44%|████▍     | 412/938 [00:28<00:36, 14.22it/s, loss=0.694, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  44%|████▍     | 413/938 [00:29<00:36, 14.21it/s, loss=0.684, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  44%|████▍     | 414/938 [00:29<00:36, 14.21it/s, loss=0.688, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  44%|████▍     | 415/938 [00:29<00:36, 14.21it/s, loss=0.682, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  44%|████▍     | 416/938 [00:29<00:36, 14.21it/s, loss=0.682, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  44%|████▍     | 416/938 [00:29<00:36, 14.21it/s, loss=0.682, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  44%|████▍     | 417/938 [00:29<00:36, 14.21it/s, loss=0.688, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  45%|████▍     | 418/938 [00:29<00:36, 14.21it/s, loss=0.682, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  45%|████▍     | 419/938 [00:29<00:36, 14.21it/s, loss=0.688, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  45%|████▍     | 420/938 [00:29<00:36, 14.21it/s, loss=0.688, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  45%|████▍     | 420/938 [00:29<00:36, 14.21it/s, loss=0.688, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  45%|████▍     | 421/938 [00:29<00:36, 14.21it/s, loss=0.686, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  45%|████▍     | 422/938 [00:29<00:36, 14.21it/s, loss=0.686, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  45%|████▌     | 423/938 [00:29<00:36, 14.22it/s, loss=0.688, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  45%|████▌     | 424/938 [00:29<00:36, 14.22it/s, loss=0.688, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  45%|████▌     | 424/938 [00:29<00:36, 14.22it/s, loss=0.688, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  45%|████▌     | 425/938 [00:29<00:36, 14.22it/s, loss=0.686, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  45%|████▌     | 426/938 [00:29<00:36, 14.22it/s, loss=0.683, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  46%|████▌     | 427/938 [00:30<00:35, 14.22it/s, loss=0.688, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  46%|████▌     | 428/938 [00:30<00:35, 14.22it/s, loss=0.688, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  46%|████▌     | 428/938 [00:30<00:35, 14.22it/s, loss=0.693, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  46%|████▌     | 429/938 [00:30<00:35, 14.21it/s, loss=0.706, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  46%|████▌     | 430/938 [00:30<00:35, 14.21it/s, loss=0.714, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  46%|████▌     | 431/938 [00:30<00:35, 14.21it/s, loss=0.712, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  46%|████▌     | 432/938 [00:30<00:35, 14.22it/s, loss=0.712, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  46%|████▌     | 432/938 [00:30<00:35, 14.22it/s, loss=0.706, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  46%|████▌     | 433/938 [00:30<00:35, 14.23it/s, loss=0.71, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  46%|████▋     | 434/938 [00:30<00:35, 14.23it/s, loss=0.71, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  46%|████▋     | 435/938 [00:30<00:35, 14.23it/s, loss=0.722, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  46%|████▋     | 436/938 [00:30<00:35, 14.23it/s, loss=0.722, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  46%|████▋     | 436/938 [00:30<00:35, 14.23it/s, loss=0.722, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  47%|████▋     | 437/938 [00:30<00:35, 14.23it/s, loss=0.713, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  47%|████▋     | 438/938 [00:30<00:35, 14.24it/s, loss=0.713, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  47%|████▋     | 439/938 [00:30<00:35, 14.24it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  47%|████▋     | 440/938 [00:30<00:34, 14.24it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  47%|████▋     | 440/938 [00:30<00:34, 14.24it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  47%|████▋     | 441/938 [00:30<00:34, 14.24it/s, loss=0.705, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  47%|████▋     | 442/938 [00:31<00:34, 14.24it/s, loss=0.698, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  47%|████▋     | 443/938 [00:31<00:34, 14.23it/s, loss=0.7, v_num=10, val_rmse=0.659, train_rmse=1.190]  
Epoch 1:  47%|████▋     | 444/938 [00:31<00:34, 14.22it/s, loss=0.7, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  47%|████▋     | 444/938 [00:31<00:34, 14.22it/s, loss=0.695, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  47%|████▋     | 445/938 [00:31<00:34, 14.22it/s, loss=0.692, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  48%|████▊     | 446/938 [00:31<00:34, 14.22it/s, loss=0.7, v_num=10, val_rmse=0.659, train_rmse=1.190]  
Epoch 1:  48%|████▊     | 447/938 [00:31<00:34, 14.21it/s, loss=0.693, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  48%|████▊     | 448/938 [00:31<00:34, 14.20it/s, loss=0.693, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  48%|████▊     | 448/938 [00:31<00:34, 14.20it/s, loss=0.691, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  48%|████▊     | 449/938 [00:31<00:34, 14.20it/s, loss=0.679, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  48%|████▊     | 450/938 [00:31<00:34, 14.20it/s, loss=0.682, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  48%|████▊     | 451/938 [00:31<00:34, 14.20it/s, loss=0.68, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  48%|████▊     | 452/938 [00:31<00:34, 14.20it/s, loss=0.68, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  48%|████▊     | 452/938 [00:31<00:34, 14.20it/s, loss=0.681, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  48%|████▊     | 453/938 [00:31<00:34, 14.20it/s, loss=0.678, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  48%|████▊     | 454/938 [00:31<00:34, 14.20it/s, loss=0.673, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  49%|████▊     | 455/938 [00:32<00:34, 14.20it/s, loss=0.667, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  49%|████▊     | 456/938 [00:32<00:33, 14.19it/s, loss=0.667, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  49%|████▊     | 456/938 [00:32<00:33, 14.19it/s, loss=0.665, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  49%|████▊     | 457/938 [00:32<00:33, 14.20it/s, loss=0.664, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  49%|████▉     | 458/938 [00:32<00:33, 14.20it/s, loss=0.669, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  49%|████▉     | 459/938 [00:32<00:33, 14.19it/s, loss=0.676, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  49%|████▉     | 460/938 [00:32<00:33, 14.20it/s, loss=0.676, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  49%|████▉     | 460/938 [00:32<00:33, 14.20it/s, loss=0.679, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  49%|████▉     | 461/938 [00:32<00:33, 14.19it/s, loss=0.683, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  49%|████▉     | 462/938 [00:32<00:33, 14.20it/s, loss=0.69, v_num=10, val_rmse=0.659, train_rmse=1.190] 
Epoch 1:  49%|████▉     | 463/938 [00:32<00:33, 14.20it/s, loss=0.699, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  49%|████▉     | 464/938 [00:32<00:33, 14.20it/s, loss=0.699, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  49%|████▉     | 464/938 [00:32<00:33, 14.20it/s, loss=0.699, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  50%|████▉     | 465/938 [00:32<00:33, 14.20it/s, loss=0.707, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  50%|████▉     | 466/938 [00:32<00:33, 14.20it/s, loss=0.703, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  50%|████▉     | 467/938 [00:32<00:33, 14.20it/s, loss=0.704, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  50%|████▉     | 468/938 [00:32<00:33, 14.21it/s, loss=0.704, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  50%|████▉     | 468/938 [00:32<00:33, 14.21it/s, loss=0.707, v_num=10, val_rmse=0.659, train_rmse=1.190]
Epoch 1:  50%|█████     | 469/938 [00:32<00:32, 14.22it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]
Epoch 1:  50%|█████     | 472/938 [00:33<00:32, 14.27it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:   1%|          | 3/469 [00:00<00:22, 20.78it/s]

Validating:   1%|▏         | 6/469 [00:00<00:22, 21.00it/s]
Epoch 1:  51%|█████     | 476/938 [00:33<00:32, 14.31it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:   2%|▏         | 9/469 [00:00<00:20, 22.57it/s]
Epoch 1:  51%|█████     | 480/938 [00:33<00:31, 14.36it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:   3%|▎         | 12/469 [00:00<00:19, 23.58it/s]
Epoch 1:  52%|█████▏    | 484/938 [00:33<00:31, 14.41it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:   3%|▎         | 15/469 [00:00<00:19, 23.77it/s]

Validating:   4%|▍         | 18/469 [00:00<00:18, 24.48it/s]
Epoch 1:  52%|█████▏    | 488/938 [00:33<00:31, 14.46it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:   4%|▍         | 21/469 [00:00<00:17, 25.43it/s]
Epoch 1:  52%|█████▏    | 492/938 [00:33<00:30, 14.51it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:   5%|▌         | 24/469 [00:00<00:17, 25.48it/s]
Epoch 1:  53%|█████▎    | 496/938 [00:34<00:30, 14.57it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:   6%|▌         | 27/469 [00:01<00:17, 25.90it/s]

Validating:   6%|▋         | 30/469 [00:01<00:16, 26.34it/s]
Epoch 1:  53%|█████▎    | 500/938 [00:34<00:29, 14.62it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:   7%|▋         | 33/469 [00:01<00:16, 26.52it/s]
Epoch 1:  54%|█████▎    | 504/938 [00:34<00:29, 14.67it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:   8%|▊         | 36/469 [00:01<00:17, 24.84it/s]
Epoch 1:  54%|█████▍    | 508/938 [00:34<00:29, 14.72it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:   8%|▊         | 39/469 [00:01<00:16, 25.55it/s]

Validating:   9%|▉         | 42/469 [00:01<00:16, 25.84it/s]
Epoch 1:  55%|█████▍    | 512/938 [00:34<00:28, 14.77it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  10%|▉         | 45/469 [00:01<00:18, 23.47it/s]
Epoch 1:  55%|█████▌    | 516/938 [00:34<00:28, 14.79it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  10%|█         | 48/469 [00:01<00:18, 23.08it/s]
Epoch 1:  55%|█████▌    | 520/938 [00:35<00:28, 14.84it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  11%|█         | 51/469 [00:02<00:17, 23.95it/s]

Validating:  12%|█▏        | 54/469 [00:02<00:17, 24.06it/s]
Epoch 1:  56%|█████▌    | 524/938 [00:35<00:27, 14.89it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  12%|█▏        | 57/469 [00:02<00:17, 23.68it/s]
Epoch 1:  56%|█████▋    | 528/938 [00:35<00:27, 14.92it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  13%|█▎        | 60/469 [00:02<00:17, 23.19it/s]
Epoch 1:  57%|█████▋    | 532/938 [00:35<00:27, 14.97it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  13%|█▎        | 63/469 [00:02<00:16, 24.26it/s]

Validating:  14%|█▍        | 66/469 [00:02<00:16, 24.57it/s]
Epoch 1:  57%|█████▋    | 536/938 [00:35<00:26, 15.02it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  15%|█▍        | 69/469 [00:02<00:15, 25.48it/s]
Epoch 1:  58%|█████▊    | 540/938 [00:35<00:26, 15.06it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  15%|█▌        | 72/469 [00:02<00:15, 25.18it/s]
Epoch 1:  58%|█████▊    | 544/938 [00:36<00:26, 15.10it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  16%|█▌        | 75/469 [00:03<00:16, 24.50it/s]

Validating:  17%|█▋        | 78/469 [00:03<00:16, 24.19it/s]
Epoch 1:  58%|█████▊    | 548/938 [00:36<00:25, 15.15it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  17%|█▋        | 81/469 [00:03<00:16, 23.45it/s]
Epoch 1:  59%|█████▉    | 552/938 [00:36<00:25, 15.18it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  18%|█▊        | 84/469 [00:03<00:16, 24.01it/s]
Epoch 1:  59%|█████▉    | 556/938 [00:36<00:25, 15.23it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  19%|█▊        | 87/469 [00:03<00:15, 24.88it/s]

Validating:  19%|█▉        | 90/469 [00:03<00:14, 25.41it/s]
Epoch 1:  60%|█████▉    | 560/938 [00:36<00:24, 15.28it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  20%|█▉        | 93/469 [00:03<00:14, 25.94it/s]
Epoch 1:  60%|██████    | 564/938 [00:36<00:24, 15.32it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  20%|██        | 96/469 [00:03<00:14, 25.90it/s]
Epoch 1:  61%|██████    | 568/938 [00:36<00:24, 15.36it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  21%|██        | 99/469 [00:04<00:14, 25.52it/s]

Validating:  22%|██▏       | 102/469 [00:04<00:14, 25.45it/s]
Epoch 1:  61%|██████    | 572/938 [00:37<00:23, 15.41it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  22%|██▏       | 105/469 [00:04<00:14, 25.46it/s]
Epoch 1:  61%|██████▏   | 576/938 [00:37<00:23, 15.45it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  23%|██▎       | 108/469 [00:04<00:14, 24.22it/s]
Epoch 1:  62%|██████▏   | 580/938 [00:37<00:23, 15.49it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  24%|██▎       | 111/469 [00:04<00:14, 25.10it/s]

Validating:  24%|██▍       | 114/469 [00:04<00:13, 25.94it/s]
Epoch 1:  62%|██████▏   | 584/938 [00:37<00:22, 15.53it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  25%|██▍       | 117/469 [00:04<00:14, 24.42it/s]
Epoch 1:  63%|██████▎   | 588/938 [00:37<00:22, 15.56it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  26%|██▌       | 120/469 [00:04<00:14, 24.25it/s]
Epoch 1:  63%|██████▎   | 592/938 [00:37<00:22, 15.60it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  26%|██▌       | 123/469 [00:05<00:14, 23.57it/s]

Validating:  27%|██▋       | 126/469 [00:05<00:14, 24.44it/s]
Epoch 1:  64%|██████▎   | 596/938 [00:38<00:21, 15.64it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  28%|██▊       | 129/469 [00:05<00:13, 24.72it/s]
Epoch 1:  64%|██████▍   | 600/938 [00:38<00:21, 15.68it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  28%|██▊       | 132/469 [00:05<00:14, 23.89it/s]
Epoch 1:  64%|██████▍   | 604/938 [00:38<00:21, 15.71it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  29%|██▉       | 135/469 [00:05<00:14, 23.68it/s]

Validating:  29%|██▉       | 138/469 [00:05<00:13, 24.10it/s]
Epoch 1:  65%|██████▍   | 608/938 [00:38<00:20, 15.75it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  30%|███       | 141/469 [00:05<00:13, 23.54it/s]
Epoch 1:  65%|██████▌   | 612/938 [00:38<00:20, 15.77it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  31%|███       | 144/469 [00:05<00:14, 22.92it/s]
Epoch 1:  66%|██████▌   | 616/938 [00:38<00:20, 15.81it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  31%|███▏      | 147/469 [00:06<00:13, 23.81it/s]

Validating:  32%|███▏      | 150/469 [00:06<00:13, 24.38it/s]
Epoch 1:  66%|██████▌   | 620/938 [00:39<00:20, 15.85it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  33%|███▎      | 153/469 [00:06<00:12, 24.67it/s]
Epoch 1:  67%|██████▋   | 624/938 [00:39<00:19, 15.89it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  33%|███▎      | 156/469 [00:06<00:12, 24.57it/s]
Epoch 1:  67%|██████▋   | 628/938 [00:39<00:19, 15.92it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  34%|███▍      | 159/469 [00:06<00:12, 24.16it/s]

Validating:  35%|███▍      | 162/469 [00:06<00:12, 24.82it/s]
Epoch 1:  67%|██████▋   | 632/938 [00:39<00:19, 15.96it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  35%|███▌      | 165/469 [00:06<00:12, 24.62it/s]
Epoch 1:  68%|██████▊   | 636/938 [00:39<00:18, 15.99it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  36%|███▌      | 168/469 [00:06<00:11, 25.26it/s]
Epoch 1:  68%|██████▊   | 640/938 [00:39<00:18, 16.03it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  36%|███▋      | 171/469 [00:06<00:11, 25.45it/s]

Validating:  37%|███▋      | 174/469 [00:07<00:11, 24.88it/s]
Epoch 1:  69%|██████▊   | 644/938 [00:40<00:18, 16.07it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  38%|███▊      | 177/469 [00:07<00:11, 25.91it/s]
Epoch 1:  69%|██████▉   | 648/938 [00:40<00:18, 16.11it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  38%|███▊      | 180/469 [00:07<00:11, 26.00it/s]
Epoch 1:  70%|██████▉   | 652/938 [00:40<00:17, 16.15it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  39%|███▉      | 183/469 [00:07<00:11, 25.96it/s]

Validating:  40%|███▉      | 186/469 [00:07<00:11, 24.96it/s]
Epoch 1:  70%|██████▉   | 656/938 [00:40<00:17, 16.18it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  40%|████      | 189/469 [00:07<00:11, 24.26it/s]
Epoch 1:  70%|███████   | 660/938 [00:40<00:17, 16.21it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  41%|████      | 192/469 [00:07<00:11, 24.84it/s]
Epoch 1:  71%|███████   | 664/938 [00:40<00:16, 16.24it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  42%|████▏     | 195/469 [00:07<00:11, 24.38it/s]

Validating:  42%|████▏     | 198/469 [00:08<00:11, 24.41it/s]
Epoch 1:  71%|███████   | 668/938 [00:41<00:16, 16.28it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  43%|████▎     | 201/469 [00:08<00:10, 25.67it/s]
Epoch 1:  72%|███████▏  | 672/938 [00:41<00:16, 16.32it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  43%|████▎     | 204/469 [00:08<00:11, 23.54it/s]
Epoch 1:  72%|███████▏  | 676/938 [00:41<00:16, 16.33it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  44%|████▍     | 207/469 [00:08<00:11, 23.38it/s]

Validating:  45%|████▍     | 210/469 [00:08<00:10, 23.87it/s]
Epoch 1:  72%|███████▏  | 680/938 [00:41<00:15, 16.37it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  45%|████▌     | 213/469 [00:08<00:10, 24.65it/s]
Epoch 1:  73%|███████▎  | 684/938 [00:41<00:15, 16.40it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  46%|████▌     | 216/469 [00:08<00:09, 25.82it/s]
Epoch 1:  73%|███████▎  | 688/938 [00:41<00:15, 16.44it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  47%|████▋     | 219/469 [00:08<00:10, 24.74it/s]

Validating:  47%|████▋     | 222/469 [00:09<00:10, 24.50it/s]
Epoch 1:  74%|███████▍  | 692/938 [00:42<00:14, 16.47it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  48%|████▊     | 225/469 [00:09<00:09, 24.99it/s]
Epoch 1:  74%|███████▍  | 696/938 [00:42<00:14, 16.50it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  49%|████▊     | 228/469 [00:09<00:09, 24.85it/s]
Epoch 1:  75%|███████▍  | 700/938 [00:42<00:14, 16.53it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  49%|████▉     | 231/469 [00:09<00:09, 24.74it/s]

Validating:  50%|████▉     | 234/469 [00:09<00:09, 25.61it/s]
Epoch 1:  75%|███████▌  | 704/938 [00:42<00:14, 16.57it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  51%|█████     | 237/469 [00:09<00:09, 23.91it/s]
Epoch 1:  75%|███████▌  | 708/938 [00:42<00:13, 16.59it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  51%|█████     | 240/469 [00:09<00:09, 23.98it/s]
Epoch 1:  76%|███████▌  | 712/938 [00:42<00:13, 16.62it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  52%|█████▏    | 243/469 [00:09<00:09, 24.55it/s]

Validating:  52%|█████▏    | 246/469 [00:10<00:09, 23.57it/s]
Epoch 1:  76%|███████▋  | 716/938 [00:43<00:13, 16.65it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  53%|█████▎    | 249/469 [00:10<00:09, 24.25it/s]
Epoch 1:  77%|███████▋  | 720/938 [00:43<00:13, 16.68it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  54%|█████▎    | 252/469 [00:10<00:09, 24.09it/s]
Epoch 1:  77%|███████▋  | 724/938 [00:43<00:12, 16.71it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  54%|█████▍    | 255/469 [00:10<00:08, 24.69it/s]

Validating:  55%|█████▌    | 258/469 [00:10<00:08, 25.65it/s]
Epoch 1:  78%|███████▊  | 728/938 [00:43<00:12, 16.75it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  56%|█████▌    | 261/469 [00:10<00:07, 26.01it/s]
Epoch 1:  78%|███████▊  | 732/938 [00:43<00:12, 16.78it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  56%|█████▋    | 264/469 [00:10<00:08, 25.33it/s]
Epoch 1:  78%|███████▊  | 736/938 [00:43<00:12, 16.81it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  57%|█████▋    | 267/469 [00:10<00:07, 25.61it/s]

Validating:  58%|█████▊    | 270/469 [00:10<00:07, 25.21it/s]
Epoch 1:  79%|███████▉  | 740/938 [00:43<00:11, 16.84it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  58%|█████▊    | 273/469 [00:11<00:07, 25.37it/s]
Epoch 1:  79%|███████▉  | 744/938 [00:44<00:11, 16.87it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  59%|█████▉    | 276/469 [00:11<00:07, 25.26it/s]
Epoch 1:  80%|███████▉  | 748/938 [00:44<00:11, 16.90it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  59%|█████▉    | 279/469 [00:11<00:07, 25.22it/s]

Validating:  60%|██████    | 282/469 [00:11<00:07, 25.24it/s]
Epoch 1:  80%|████████  | 752/938 [00:44<00:10, 16.93it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  61%|██████    | 285/469 [00:11<00:07, 23.18it/s]
Epoch 1:  81%|████████  | 756/938 [00:44<00:10, 16.94it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  61%|██████▏   | 288/469 [00:11<00:07, 23.39it/s]
Epoch 1:  81%|████████  | 760/938 [00:44<00:10, 16.97it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  62%|██████▏   | 291/469 [00:11<00:07, 23.49it/s]

Validating:  63%|██████▎   | 294/469 [00:11<00:07, 23.08it/s]
Epoch 1:  81%|████████▏ | 764/938 [00:44<00:10, 16.99it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  63%|██████▎   | 297/469 [00:12<00:07, 23.78it/s]
Epoch 1:  82%|████████▏ | 768/938 [00:45<00:09, 17.02it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  64%|██████▍   | 300/469 [00:12<00:06, 24.33it/s]
Epoch 1:  82%|████████▏ | 772/938 [00:45<00:09, 17.05it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  65%|██████▍   | 303/469 [00:12<00:06, 25.12it/s]

Validating:  65%|██████▌   | 306/469 [00:12<00:06, 23.79it/s]
Epoch 1:  83%|████████▎ | 776/938 [00:45<00:09, 17.07it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  66%|██████▌   | 309/469 [00:12<00:06, 23.83it/s]
Epoch 1:  83%|████████▎ | 780/938 [00:45<00:09, 17.10it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  67%|██████▋   | 312/469 [00:12<00:06, 23.49it/s]
Epoch 1:  84%|████████▎ | 784/938 [00:45<00:08, 17.12it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  67%|██████▋   | 315/469 [00:12<00:06, 23.86it/s]

Validating:  68%|██████▊   | 318/469 [00:12<00:06, 24.19it/s]
Epoch 1:  84%|████████▍ | 788/938 [00:45<00:08, 17.15it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  68%|██████▊   | 321/469 [00:13<00:06, 22.54it/s]
Epoch 1:  84%|████████▍ | 792/938 [00:46<00:08, 17.16it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  69%|██████▉   | 324/469 [00:13<00:06, 22.88it/s]
Epoch 1:  85%|████████▍ | 796/938 [00:46<00:08, 17.19it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  70%|██████▉   | 327/469 [00:13<00:05, 23.78it/s]

Validating:  70%|███████   | 330/469 [00:13<00:05, 23.49it/s]
Epoch 1:  85%|████████▌ | 800/938 [00:46<00:08, 17.21it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  71%|███████   | 333/469 [00:13<00:05, 23.79it/s]
Epoch 1:  86%|████████▌ | 804/938 [00:46<00:07, 17.24it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  72%|███████▏  | 336/469 [00:13<00:05, 24.72it/s]
Epoch 1:  86%|████████▌ | 808/938 [00:46<00:07, 17.27it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  72%|███████▏  | 339/469 [00:13<00:05, 24.89it/s]

Validating:  73%|███████▎  | 342/469 [00:13<00:05, 25.33it/s]
Epoch 1:  87%|████████▋ | 812/938 [00:46<00:07, 17.30it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  74%|███████▎  | 345/469 [00:14<00:04, 25.23it/s]
Epoch 1:  87%|████████▋ | 816/938 [00:47<00:07, 17.32it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  74%|███████▍  | 348/469 [00:14<00:04, 24.81it/s]
Epoch 1:  87%|████████▋ | 820/938 [00:47<00:06, 17.35it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  75%|███████▍  | 351/469 [00:14<00:04, 25.10it/s]

Validating:  75%|███████▌  | 354/469 [00:14<00:04, 25.37it/s]
Epoch 1:  88%|████████▊ | 824/938 [00:47<00:06, 17.38it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  76%|███████▌  | 357/469 [00:14<00:04, 25.02it/s]
Epoch 1:  88%|████████▊ | 828/938 [00:47<00:06, 17.40it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  77%|███████▋  | 360/469 [00:14<00:04, 25.97it/s]
Epoch 1:  89%|████████▊ | 832/938 [00:47<00:06, 17.43it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  77%|███████▋  | 363/469 [00:14<00:04, 26.32it/s]

Validating:  78%|███████▊  | 366/469 [00:14<00:03, 26.52it/s]
Epoch 1:  89%|████████▉ | 836/938 [00:47<00:05, 17.46it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  79%|███████▊  | 369/469 [00:15<00:03, 26.07it/s]
Epoch 1:  90%|████████▉ | 840/938 [00:48<00:05, 17.49it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  79%|███████▉  | 372/469 [00:15<00:04, 23.62it/s]
Epoch 1:  90%|████████▉ | 844/938 [00:48<00:05, 17.50it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  80%|███████▉  | 375/469 [00:15<00:03, 24.08it/s]

Validating:  81%|████████  | 378/469 [00:15<00:03, 24.48it/s]
Epoch 1:  90%|█████████ | 848/938 [00:48<00:05, 17.53it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  81%|████████  | 381/469 [00:15<00:03, 25.30it/s]
Epoch 1:  91%|█████████ | 852/938 [00:48<00:04, 17.56it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  82%|████████▏ | 384/469 [00:15<00:03, 25.44it/s]
Epoch 1:  91%|█████████▏| 856/938 [00:48<00:04, 17.58it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  83%|████████▎ | 387/469 [00:15<00:03, 24.92it/s]

Validating:  83%|████████▎ | 390/469 [00:15<00:03, 24.73it/s]
Epoch 1:  92%|█████████▏| 860/938 [00:48<00:04, 17.60it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  84%|████████▍ | 393/469 [00:15<00:03, 24.60it/s]
Epoch 1:  92%|█████████▏| 864/938 [00:49<00:04, 17.62it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  84%|████████▍ | 396/469 [00:16<00:03, 23.98it/s]
Epoch 1:  93%|█████████▎| 868/938 [00:49<00:03, 17.65it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  85%|████████▌ | 399/469 [00:16<00:02, 24.07it/s]

Validating:  86%|████████▌ | 402/469 [00:16<00:02, 23.81it/s]
Epoch 1:  93%|█████████▎| 872/938 [00:49<00:03, 17.66it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  86%|████████▋ | 405/469 [00:16<00:02, 24.15it/s]
Epoch 1:  93%|█████████▎| 876/938 [00:49<00:03, 17.69it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  87%|████████▋ | 408/469 [00:16<00:02, 24.98it/s]
Epoch 1:  94%|█████████▍| 880/938 [00:49<00:03, 17.71it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  88%|████████▊ | 411/469 [00:16<00:02, 24.91it/s]

Validating:  88%|████████▊ | 414/469 [00:16<00:02, 25.78it/s]
Epoch 1:  94%|█████████▍| 884/938 [00:49<00:03, 17.74it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  89%|████████▉ | 417/469 [00:16<00:02, 25.36it/s]
Epoch 1:  95%|█████████▍| 888/938 [00:49<00:02, 17.77it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  90%|████████▉ | 420/469 [00:17<00:01, 24.82it/s]
Epoch 1:  95%|█████████▌| 892/938 [00:50<00:02, 17.78it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  90%|█████████ | 423/469 [00:17<00:01, 24.84it/s]

Validating:  91%|█████████ | 426/469 [00:17<00:01, 24.75it/s]
Epoch 1:  96%|█████████▌| 896/938 [00:50<00:02, 17.81it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  91%|█████████▏| 429/469 [00:17<00:01, 25.50it/s]
Epoch 1:  96%|█████████▌| 900/938 [00:50<00:02, 17.83it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  92%|█████████▏| 432/469 [00:17<00:01, 24.15it/s]
Epoch 1:  96%|█████████▋| 904/938 [00:50<00:01, 17.85it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  93%|█████████▎| 435/469 [00:17<00:01, 24.92it/s]

Validating:  93%|█████████▎| 438/469 [00:17<00:01, 24.09it/s]
Epoch 1:  97%|█████████▋| 908/938 [00:50<00:01, 17.87it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  94%|█████████▍| 441/469 [00:17<00:01, 23.80it/s]
Epoch 1:  97%|█████████▋| 912/938 [00:50<00:01, 17.89it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  95%|█████████▍| 444/469 [00:18<00:01, 24.02it/s]
Epoch 1:  98%|█████████▊| 916/938 [00:51<00:01, 17.91it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  95%|█████████▌| 447/469 [00:18<00:00, 23.95it/s]

Validating:  96%|█████████▌| 450/469 [00:18<00:00, 24.31it/s]
Epoch 1:  98%|█████████▊| 920/938 [00:51<00:01, 17.93it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  97%|█████████▋| 453/469 [00:18<00:00, 25.10it/s]
Epoch 1:  99%|█████████▊| 924/938 [00:51<00:00, 17.95it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  97%|█████████▋| 456/469 [00:18<00:00, 22.88it/s]
Epoch 1:  99%|█████████▉| 928/938 [00:51<00:00, 17.96it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  98%|█████████▊| 459/469 [00:18<00:00, 23.63it/s]

Validating:  99%|█████████▊| 462/469 [00:18<00:00, 24.35it/s]
Epoch 1:  99%|█████████▉| 932/938 [00:51<00:00, 17.99it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating:  99%|█████████▉| 465/469 [00:18<00:00, 23.61it/s]
Epoch 1: 100%|█████████▉| 936/938 [00:52<00:00, 18.00it/s, loss=0.708, v_num=10, val_rmse=0.659, train_rmse=1.190]

Validating: 100%|█████████▉| 468/469 [00:19<00:00, 22.98it/s]
Epoch 1: 100%|██████████| 938/938 [00:52<00:00, 18.00it/s, loss=0.708, v_num=10, val_rmse=0.554, train_rmse=1.190]

                                                             
Epoch 1: 100%|██████████| 938/938 [00:52<00:00, 17.99it/s, loss=0.708, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 1:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.708, v_num=10, val_rmse=0.554, train_rmse=0.728]          
Epoch 2:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.708, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   0%|          | 1/938 [00:00<01:30, 10.31it/s, loss=0.702, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   0%|          | 2/938 [00:00<01:18, 11.95it/s, loss=0.702, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   0%|          | 3/938 [00:00<01:13, 12.80it/s, loss=0.704, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   0%|          | 4/938 [00:00<01:08, 13.57it/s, loss=0.704, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   0%|          | 4/938 [00:00<01:08, 13.55it/s, loss=0.705, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   1%|          | 5/938 [00:00<01:07, 13.78it/s, loss=0.699, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   1%|          | 6/938 [00:00<01:04, 14.38it/s, loss=0.691, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   1%|          | 7/938 [00:00<01:04, 14.48it/s, loss=0.701, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   1%|          | 8/938 [00:00<01:04, 14.40it/s, loss=0.701, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   1%|          | 8/938 [00:00<01:04, 14.38it/s, loss=0.702, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   1%|          | 9/938 [00:00<01:04, 14.48it/s, loss=0.698, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   1%|          | 10/938 [00:00<01:04, 14.44it/s, loss=0.699, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   1%|          | 11/938 [00:00<01:04, 14.43it/s, loss=0.698, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   1%|▏         | 12/938 [00:00<01:04, 14.42it/s, loss=0.698, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   1%|▏         | 12/938 [00:00<01:04, 14.41it/s, loss=0.696, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   1%|▏         | 13/938 [00:00<01:05, 14.22it/s, loss=0.689, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   1%|▏         | 14/938 [00:00<01:04, 14.23it/s, loss=0.677, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   2%|▏         | 15/938 [00:01<01:04, 14.22it/s, loss=0.679, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   2%|▏         | 16/938 [00:01<01:05, 14.13it/s, loss=0.679, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   2%|▏         | 16/938 [00:01<01:05, 14.12it/s, loss=0.674, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   2%|▏         | 17/938 [00:01<01:04, 14.23it/s, loss=0.669, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   2%|▏         | 18/938 [00:01<01:05, 14.11it/s, loss=0.671, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   2%|▏         | 19/938 [00:01<01:05, 14.04it/s, loss=0.659, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   2%|▏         | 20/938 [00:01<01:05, 14.00it/s, loss=0.659, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   2%|▏         | 20/938 [00:01<01:05, 13.99it/s, loss=0.659, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   2%|▏         | 21/938 [00:01<01:04, 14.17it/s, loss=0.658, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   2%|▏         | 22/938 [00:01<01:05, 14.08it/s, loss=0.661, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   2%|▏         | 23/938 [00:01<01:04, 14.18it/s, loss=0.66, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:   3%|▎         | 24/938 [00:01<01:04, 14.17it/s, loss=0.66, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   3%|▎         | 24/938 [00:01<01:04, 14.17it/s, loss=0.669, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   3%|▎         | 25/938 [00:01<01:04, 14.21it/s, loss=0.672, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   3%|▎         | 26/938 [00:01<01:04, 14.22it/s, loss=0.675, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   3%|▎         | 27/938 [00:01<01:04, 14.02it/s, loss=0.67, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:   3%|▎         | 28/938 [00:01<01:04, 14.07it/s, loss=0.67, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   3%|▎         | 28/938 [00:01<01:04, 14.07it/s, loss=0.676, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   3%|▎         | 29/938 [00:02<01:05, 13.84it/s, loss=0.676, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   3%|▎         | 30/938 [00:02<01:05, 13.90it/s, loss=0.673, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   3%|▎         | 31/938 [00:02<01:05, 13.86it/s, loss=0.67, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:   3%|▎         | 32/938 [00:02<01:05, 13.92it/s, loss=0.67, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   3%|▎         | 32/938 [00:02<01:05, 13.92it/s, loss=0.674, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   4%|▎         | 33/938 [00:02<01:04, 13.94it/s, loss=0.675, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   4%|▎         | 34/938 [00:02<01:05, 13.89it/s, loss=0.677, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   4%|▎         | 35/938 [00:02<01:05, 13.86it/s, loss=0.675, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   4%|▍         | 36/938 [00:02<01:04, 13.92it/s, loss=0.675, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   4%|▍         | 36/938 [00:02<01:04, 13.92it/s, loss=0.68, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:   4%|▍         | 37/938 [00:02<01:04, 13.93it/s, loss=0.681, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   4%|▍         | 38/938 [00:02<01:04, 13.99it/s, loss=0.675, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   4%|▍         | 39/938 [00:02<01:04, 13.95it/s, loss=0.68, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:   4%|▍         | 40/938 [00:02<01:04, 14.01it/s, loss=0.68, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   4%|▍         | 40/938 [00:02<01:04, 14.01it/s, loss=0.68, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   4%|▍         | 41/938 [00:02<01:05, 13.67it/s, loss=0.68, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   4%|▍         | 42/938 [00:03<01:05, 13.74it/s, loss=0.675, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   5%|▍         | 43/938 [00:03<01:05, 13.68it/s, loss=0.674, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   5%|▍         | 44/938 [00:03<01:05, 13.73it/s, loss=0.674, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   5%|▍         | 44/938 [00:03<01:05, 13.72it/s, loss=0.659, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   5%|▍         | 45/938 [00:03<01:04, 13.77it/s, loss=0.671, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   5%|▍         | 46/938 [00:03<01:04, 13.78it/s, loss=0.674, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   5%|▌         | 47/938 [00:03<01:05, 13.59it/s, loss=0.672, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   5%|▌         | 48/938 [00:03<01:05, 13.52it/s, loss=0.672, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   5%|▌         | 48/938 [00:03<01:05, 13.51it/s, loss=0.66, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:   5%|▌         | 49/938 [00:03<01:05, 13.56it/s, loss=0.67, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   5%|▌         | 50/938 [00:03<01:05, 13.55it/s, loss=0.668, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   5%|▌         | 51/938 [00:03<01:05, 13.56it/s, loss=0.673, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   6%|▌         | 52/938 [00:03<01:05, 13.61it/s, loss=0.673, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   6%|▌         | 52/938 [00:03<01:05, 13.60it/s, loss=0.665, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   6%|▌         | 53/938 [00:03<01:05, 13.58it/s, loss=0.671, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   6%|▌         | 54/938 [00:03<01:04, 13.63it/s, loss=0.671, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   6%|▌         | 55/938 [00:04<01:04, 13.65it/s, loss=0.668, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   6%|▌         | 56/938 [00:04<01:04, 13.67it/s, loss=0.668, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   6%|▌         | 56/938 [00:04<01:04, 13.66it/s, loss=0.665, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   6%|▌         | 57/938 [00:04<01:04, 13.69it/s, loss=0.666, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   6%|▌         | 58/938 [00:04<01:04, 13.73it/s, loss=0.673, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   6%|▋         | 59/938 [00:04<01:03, 13.76it/s, loss=0.672, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   6%|▋         | 60/938 [00:04<01:03, 13.81it/s, loss=0.672, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   6%|▋         | 60/938 [00:04<01:03, 13.80it/s, loss=0.688, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   7%|▋         | 61/938 [00:04<01:03, 13.83it/s, loss=0.685, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   7%|▋         | 62/938 [00:04<01:03, 13.84it/s, loss=0.691, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   7%|▋         | 63/938 [00:04<01:03, 13.84it/s, loss=0.695, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   7%|▋         | 64/938 [00:04<01:03, 13.84it/s, loss=0.695, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   7%|▋         | 64/938 [00:04<01:03, 13.84it/s, loss=0.7, v_num=10, val_rmse=0.554, train_rmse=0.728]  
Epoch 2:   7%|▋         | 65/938 [00:04<01:02, 13.86it/s, loss=0.693, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   7%|▋         | 66/938 [00:04<01:02, 13.88it/s, loss=0.698, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   7%|▋         | 67/938 [00:04<01:02, 13.85it/s, loss=0.698, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   7%|▋         | 68/938 [00:04<01:02, 13.87it/s, loss=0.698, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   7%|▋         | 68/938 [00:04<01:02, 13.87it/s, loss=0.707, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   7%|▋         | 69/938 [00:04<01:02, 13.87it/s, loss=0.697, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   7%|▋         | 70/938 [00:05<01:02, 13.88it/s, loss=0.694, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   8%|▊         | 71/938 [00:05<01:02, 13.80it/s, loss=0.694, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   8%|▊         | 72/938 [00:05<01:02, 13.83it/s, loss=0.694, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   8%|▊         | 72/938 [00:05<01:02, 13.82it/s, loss=0.695, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   8%|▊         | 73/938 [00:05<01:02, 13.78it/s, loss=0.69, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:   8%|▊         | 74/938 [00:05<01:02, 13.81it/s, loss=0.69, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   8%|▊         | 75/938 [00:05<01:02, 13.81it/s, loss=0.698, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   8%|▊         | 76/938 [00:05<01:02, 13.79it/s, loss=0.698, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   8%|▊         | 76/938 [00:05<01:02, 13.79it/s, loss=0.7, v_num=10, val_rmse=0.554, train_rmse=0.728]  
Epoch 2:   8%|▊         | 77/938 [00:05<01:02, 13.75it/s, loss=0.696, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   8%|▊         | 78/938 [00:05<01:02, 13.72it/s, loss=0.686, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   8%|▊         | 79/938 [00:05<01:02, 13.73it/s, loss=0.693, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   9%|▊         | 80/938 [00:05<01:02, 13.72it/s, loss=0.693, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   9%|▊         | 80/938 [00:05<01:02, 13.72it/s, loss=0.679, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   9%|▊         | 81/938 [00:05<01:02, 13.75it/s, loss=0.677, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   9%|▊         | 82/938 [00:05<01:02, 13.74it/s, loss=0.669, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   9%|▉         | 83/938 [00:06<01:02, 13.64it/s, loss=0.668, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   9%|▉         | 84/938 [00:06<01:02, 13.61it/s, loss=0.668, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   9%|▉         | 84/938 [00:06<01:02, 13.60it/s, loss=0.674, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   9%|▉         | 85/938 [00:06<01:02, 13.62it/s, loss=0.674, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   9%|▉         | 86/938 [00:06<01:02, 13.65it/s, loss=0.669, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   9%|▉         | 87/938 [00:06<01:02, 13.64it/s, loss=0.663, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   9%|▉         | 88/938 [00:06<01:02, 13.64it/s, loss=0.663, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   9%|▉         | 88/938 [00:06<01:02, 13.64it/s, loss=0.659, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:   9%|▉         | 89/938 [00:06<01:02, 13.65it/s, loss=0.656, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  10%|▉         | 90/938 [00:06<01:02, 13.63it/s, loss=0.653, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  10%|▉         | 91/938 [00:06<01:02, 13.61it/s, loss=0.66, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  10%|▉         | 92/938 [00:06<01:02, 13.63it/s, loss=0.66, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  10%|▉         | 92/938 [00:06<01:02, 13.63it/s, loss=0.657, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  10%|▉         | 93/938 [00:06<01:01, 13.64it/s, loss=0.656, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  10%|█         | 94/938 [00:06<01:01, 13.63it/s, loss=0.654, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  10%|█         | 95/938 [00:06<01:01, 13.62it/s, loss=0.652, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  10%|█         | 96/938 [00:07<01:01, 13.60it/s, loss=0.652, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  10%|█         | 96/938 [00:07<01:01, 13.60it/s, loss=0.65, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  10%|█         | 97/938 [00:07<01:01, 13.57it/s, loss=0.652, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  10%|█         | 98/938 [00:07<01:01, 13.58it/s, loss=0.663, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  11%|█         | 99/938 [00:07<01:01, 13.59it/s, loss=0.658, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  11%|█         | 100/938 [00:07<01:01, 13.62it/s, loss=0.658, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  11%|█         | 100/938 [00:07<01:01, 13.62it/s, loss=0.657, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  11%|█         | 101/938 [00:07<01:01, 13.62it/s, loss=0.66, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  11%|█         | 102/938 [00:07<01:01, 13.63it/s, loss=0.671, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  11%|█         | 103/938 [00:07<01:01, 13.63it/s, loss=0.676, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  11%|█         | 104/938 [00:07<01:01, 13.64it/s, loss=0.676, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  11%|█         | 104/938 [00:07<01:01, 13.64it/s, loss=0.67, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  11%|█         | 105/938 [00:07<01:01, 13.65it/s, loss=0.665, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  11%|█▏        | 106/938 [00:07<01:01, 13.63it/s, loss=0.666, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  11%|█▏        | 107/938 [00:07<01:01, 13.60it/s, loss=0.664, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  12%|█▏        | 108/938 [00:07<01:01, 13.59it/s, loss=0.664, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  12%|█▏        | 108/938 [00:07<01:01, 13.59it/s, loss=0.664, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  12%|█▏        | 109/938 [00:08<01:00, 13.60it/s, loss=0.669, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  12%|█▏        | 110/938 [00:08<01:00, 13.60it/s, loss=0.679, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  12%|█▏        | 111/938 [00:08<01:00, 13.58it/s, loss=0.663, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  12%|█▏        | 112/938 [00:08<01:00, 13.61it/s, loss=0.663, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  12%|█▏        | 112/938 [00:08<01:00, 13.61it/s, loss=0.66, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  12%|█▏        | 113/938 [00:08<01:00, 13.60it/s, loss=0.665, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  12%|█▏        | 114/938 [00:08<01:00, 13.60it/s, loss=0.668, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  12%|█▏        | 115/938 [00:08<01:00, 13.61it/s, loss=0.672, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  12%|█▏        | 116/938 [00:08<01:00, 13.62it/s, loss=0.672, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  12%|█▏        | 116/938 [00:08<01:00, 13.61it/s, loss=0.677, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  12%|█▏        | 117/938 [00:08<01:00, 13.62it/s, loss=0.677, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  13%|█▎        | 118/938 [00:08<01:00, 13.62it/s, loss=0.673, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  13%|█▎        | 119/938 [00:08<01:00, 13.60it/s, loss=0.674, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  13%|█▎        | 120/938 [00:08<01:00, 13.60it/s, loss=0.674, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  13%|█▎        | 120/938 [00:08<01:00, 13.60it/s, loss=0.681, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  13%|█▎        | 121/938 [00:08<01:00, 13.60it/s, loss=0.681, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  13%|█▎        | 122/938 [00:08<00:59, 13.61it/s, loss=0.682, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  13%|█▎        | 123/938 [00:09<00:59, 13.63it/s, loss=0.68, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  13%|█▎        | 124/938 [00:09<00:59, 13.60it/s, loss=0.68, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  13%|█▎        | 124/938 [00:09<00:59, 13.60it/s, loss=0.673, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  13%|█▎        | 125/938 [00:09<00:59, 13.59it/s, loss=0.676, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  13%|█▎        | 126/938 [00:09<00:59, 13.59it/s, loss=0.668, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  14%|█▎        | 127/938 [00:09<00:59, 13.61it/s, loss=0.681, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  14%|█▎        | 128/938 [00:09<00:59, 13.58it/s, loss=0.681, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  14%|█▎        | 128/938 [00:09<00:59, 13.58it/s, loss=0.682, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  14%|█▍        | 129/938 [00:09<00:59, 13.59it/s, loss=0.682, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  14%|█▍        | 130/938 [00:09<00:59, 13.60it/s, loss=0.691, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  14%|█▍        | 131/938 [00:09<00:59, 13.61it/s, loss=0.693, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  14%|█▍        | 132/938 [00:09<00:59, 13.61it/s, loss=0.693, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  14%|█▍        | 132/938 [00:09<00:59, 13.61it/s, loss=0.697, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  14%|█▍        | 133/938 [00:09<00:59, 13.61it/s, loss=0.689, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  14%|█▍        | 134/938 [00:09<00:59, 13.61it/s, loss=0.685, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  14%|█▍        | 135/938 [00:09<00:58, 13.61it/s, loss=0.682, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  14%|█▍        | 136/938 [00:09<00:58, 13.62it/s, loss=0.682, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  14%|█▍        | 136/938 [00:09<00:58, 13.62it/s, loss=0.672, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  15%|█▍        | 137/938 [00:10<00:58, 13.62it/s, loss=0.673, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  15%|█▍        | 138/938 [00:10<00:58, 13.61it/s, loss=0.677, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  15%|█▍        | 139/938 [00:10<00:58, 13.60it/s, loss=0.671, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  15%|█▍        | 140/938 [00:10<00:58, 13.60it/s, loss=0.671, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  15%|█▍        | 140/938 [00:10<00:58, 13.59it/s, loss=0.66, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  15%|█▌        | 141/938 [00:10<00:58, 13.59it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  15%|█▌        | 142/938 [00:10<00:58, 13.58it/s, loss=0.654, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  15%|█▌        | 143/938 [00:10<00:58, 13.58it/s, loss=0.652, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  15%|█▌        | 144/938 [00:10<00:58, 13.60it/s, loss=0.652, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  15%|█▌        | 144/938 [00:10<00:58, 13.60it/s, loss=0.664, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  15%|█▌        | 145/938 [00:10<00:58, 13.61it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  16%|█▌        | 146/938 [00:10<00:58, 13.61it/s, loss=0.663, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  16%|█▌        | 147/938 [00:10<00:58, 13.62it/s, loss=0.66, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  16%|█▌        | 148/938 [00:10<00:57, 13.63it/s, loss=0.66, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  16%|█▌        | 148/938 [00:10<00:57, 13.63it/s, loss=0.657, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  16%|█▌        | 149/938 [00:10<00:57, 13.63it/s, loss=0.653, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  16%|█▌        | 150/938 [00:10<00:57, 13.64it/s, loss=0.638, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  16%|█▌        | 151/938 [00:11<00:57, 13.62it/s, loss=0.64, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  16%|█▌        | 152/938 [00:11<00:57, 13.62it/s, loss=0.64, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  16%|█▌        | 152/938 [00:11<00:57, 13.62it/s, loss=0.643, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  16%|█▋        | 153/938 [00:11<00:57, 13.63it/s, loss=0.651, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  16%|█▋        | 154/938 [00:11<00:57, 13.63it/s, loss=0.656, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  17%|█▋        | 155/938 [00:11<00:57, 13.62it/s, loss=0.66, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  17%|█▋        | 156/938 [00:11<00:57, 13.63it/s, loss=0.66, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  17%|█▋        | 156/938 [00:11<00:57, 13.63it/s, loss=0.663, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  17%|█▋        | 157/938 [00:11<00:57, 13.61it/s, loss=0.664, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  17%|█▋        | 158/938 [00:11<00:57, 13.62it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  17%|█▋        | 159/938 [00:11<00:57, 13.61it/s, loss=0.673, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  17%|█▋        | 160/938 [00:11<00:57, 13.61it/s, loss=0.673, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  17%|█▋        | 160/938 [00:11<00:57, 13.61it/s, loss=0.672, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  17%|█▋        | 161/938 [00:11<00:57, 13.62it/s, loss=0.671, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  17%|█▋        | 162/938 [00:11<00:56, 13.62it/s, loss=0.678, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  17%|█▋        | 163/938 [00:11<00:56, 13.62it/s, loss=0.679, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  17%|█▋        | 164/938 [00:12<00:56, 13.64it/s, loss=0.679, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  17%|█▋        | 164/938 [00:12<00:56, 13.64it/s, loss=0.678, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  18%|█▊        | 165/938 [00:12<00:56, 13.60it/s, loss=0.685, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  18%|█▊        | 166/938 [00:12<00:56, 13.62it/s, loss=0.695, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  18%|█▊        | 167/938 [00:12<00:56, 13.61it/s, loss=0.681, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  18%|█▊        | 168/938 [00:12<00:56, 13.62it/s, loss=0.681, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  18%|█▊        | 168/938 [00:12<00:56, 13.62it/s, loss=0.675, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  18%|█▊        | 169/938 [00:12<00:56, 13.64it/s, loss=0.681, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  18%|█▊        | 170/938 [00:12<00:56, 13.63it/s, loss=0.696, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  18%|█▊        | 171/938 [00:12<00:56, 13.63it/s, loss=0.698, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  18%|█▊        | 172/938 [00:12<00:56, 13.63it/s, loss=0.698, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  18%|█▊        | 172/938 [00:12<00:56, 13.63it/s, loss=0.691, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  18%|█▊        | 173/938 [00:12<00:56, 13.61it/s, loss=0.684, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  19%|█▊        | 174/938 [00:12<00:56, 13.62it/s, loss=0.679, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  19%|█▊        | 175/938 [00:12<00:56, 13.62it/s, loss=0.671, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  19%|█▉        | 176/938 [00:12<00:55, 13.62it/s, loss=0.671, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  19%|█▉        | 176/938 [00:12<00:55, 13.62it/s, loss=0.675, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  19%|█▉        | 177/938 [00:13<00:55, 13.61it/s, loss=0.673, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  19%|█▉        | 178/938 [00:13<00:55, 13.62it/s, loss=0.673, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  19%|█▉        | 179/938 [00:13<00:55, 13.62it/s, loss=0.668, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  19%|█▉        | 180/938 [00:13<00:55, 13.62it/s, loss=0.668, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  19%|█▉        | 180/938 [00:13<00:55, 13.62it/s, loss=0.675, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  19%|█▉        | 181/938 [00:13<00:55, 13.62it/s, loss=0.678, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  19%|█▉        | 182/938 [00:13<00:55, 13.62it/s, loss=0.669, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  20%|█▉        | 183/938 [00:13<00:55, 13.62it/s, loss=0.665, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  20%|█▉        | 184/938 [00:13<00:55, 13.63it/s, loss=0.665, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  20%|█▉        | 184/938 [00:13<00:55, 13.63it/s, loss=0.667, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  20%|█▉        | 185/938 [00:13<00:55, 13.62it/s, loss=0.656, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  20%|█▉        | 186/938 [00:13<00:55, 13.62it/s, loss=0.644, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  20%|█▉        | 187/938 [00:13<00:55, 13.64it/s, loss=0.655, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  20%|██        | 188/938 [00:13<00:55, 13.63it/s, loss=0.655, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  20%|██        | 188/938 [00:13<00:55, 13.63it/s, loss=0.668, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  20%|██        | 189/938 [00:13<00:54, 13.63it/s, loss=0.67, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  20%|██        | 190/938 [00:13<00:54, 13.63it/s, loss=0.664, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  20%|██        | 191/938 [00:14<00:54, 13.64it/s, loss=0.665, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  20%|██        | 192/938 [00:14<00:54, 13.64it/s, loss=0.665, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  20%|██        | 192/938 [00:14<00:54, 13.64it/s, loss=0.667, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  21%|██        | 193/938 [00:14<00:54, 13.65it/s, loss=0.665, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  21%|██        | 194/938 [00:14<00:54, 13.64it/s, loss=0.666, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  21%|██        | 195/938 [00:14<00:54, 13.64it/s, loss=0.67, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  21%|██        | 196/938 [00:14<00:54, 13.64it/s, loss=0.67, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  21%|██        | 196/938 [00:14<00:54, 13.64it/s, loss=0.668, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  21%|██        | 197/938 [00:14<00:54, 13.65it/s, loss=0.668, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  21%|██        | 198/938 [00:14<00:54, 13.66it/s, loss=0.661, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  21%|██        | 199/938 [00:14<00:54, 13.66it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  21%|██▏       | 200/938 [00:14<00:54, 13.65it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  21%|██▏       | 200/938 [00:14<00:54, 13.65it/s, loss=0.671, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  21%|██▏       | 201/938 [00:14<00:53, 13.66it/s, loss=0.669, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  22%|██▏       | 202/938 [00:14<00:53, 13.65it/s, loss=0.667, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  22%|██▏       | 203/938 [00:14<00:53, 13.65it/s, loss=0.665, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  22%|██▏       | 204/938 [00:14<00:53, 13.65it/s, loss=0.665, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  22%|██▏       | 204/938 [00:14<00:53, 13.65it/s, loss=0.667, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  22%|██▏       | 205/938 [00:15<00:53, 13.64it/s, loss=0.675, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  22%|██▏       | 206/938 [00:15<00:53, 13.64it/s, loss=0.682, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  22%|██▏       | 207/938 [00:15<00:53, 13.61it/s, loss=0.679, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  22%|██▏       | 208/938 [00:15<00:53, 13.62it/s, loss=0.679, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  22%|██▏       | 208/938 [00:15<00:53, 13.62it/s, loss=0.677, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  22%|██▏       | 209/938 [00:15<00:53, 13.62it/s, loss=0.675, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  22%|██▏       | 210/938 [00:15<00:53, 13.63it/s, loss=0.671, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  22%|██▏       | 211/938 [00:15<00:53, 13.63it/s, loss=0.668, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  23%|██▎       | 212/938 [00:15<00:53, 13.63it/s, loss=0.668, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  23%|██▎       | 212/938 [00:15<00:53, 13.62it/s, loss=0.673, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  23%|██▎       | 213/938 [00:15<00:53, 13.62it/s, loss=0.686, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  23%|██▎       | 214/938 [00:15<00:53, 13.63it/s, loss=0.679, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  23%|██▎       | 215/938 [00:15<00:53, 13.63it/s, loss=0.68, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  23%|██▎       | 216/938 [00:15<00:52, 13.64it/s, loss=0.68, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  23%|██▎       | 216/938 [00:15<00:52, 13.64it/s, loss=0.682, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  23%|██▎       | 217/938 [00:15<00:52, 13.64it/s, loss=0.681, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  23%|██▎       | 218/938 [00:15<00:52, 13.64it/s, loss=0.696, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  23%|██▎       | 219/938 [00:16<00:52, 13.65it/s, loss=0.69, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  23%|██▎       | 220/938 [00:16<00:52, 13.66it/s, loss=0.69, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  23%|██▎       | 220/938 [00:16<00:52, 13.66it/s, loss=0.678, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  24%|██▎       | 221/938 [00:16<00:52, 13.66it/s, loss=0.671, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  24%|██▎       | 222/938 [00:16<00:52, 13.66it/s, loss=0.676, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  24%|██▍       | 223/938 [00:16<00:52, 13.67it/s, loss=0.679, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  24%|██▍       | 224/938 [00:16<00:52, 13.68it/s, loss=0.679, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  24%|██▍       | 224/938 [00:16<00:52, 13.68it/s, loss=0.673, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  24%|██▍       | 225/938 [00:16<00:52, 13.67it/s, loss=0.681, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  24%|██▍       | 226/938 [00:16<00:52, 13.69it/s, loss=0.686, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  24%|██▍       | 227/938 [00:16<00:51, 13.68it/s, loss=0.693, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  24%|██▍       | 228/938 [00:16<00:51, 13.68it/s, loss=0.693, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  24%|██▍       | 228/938 [00:16<00:51, 13.68it/s, loss=0.697, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  24%|██▍       | 229/938 [00:16<00:51, 13.68it/s, loss=0.702, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  25%|██▍       | 230/938 [00:16<00:51, 13.67it/s, loss=0.709, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  25%|██▍       | 231/938 [00:16<00:51, 13.68it/s, loss=0.71, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  25%|██▍       | 232/938 [00:16<00:51, 13.68it/s, loss=0.71, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  25%|██▍       | 232/938 [00:16<00:51, 13.68it/s, loss=0.718, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  25%|██▍       | 233/938 [00:17<00:51, 13.68it/s, loss=0.707, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  25%|██▍       | 234/938 [00:17<00:51, 13.68it/s, loss=0.715, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  25%|██▌       | 235/938 [00:17<00:51, 13.70it/s, loss=0.717, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  25%|██▌       | 236/938 [00:17<00:51, 13.70it/s, loss=0.717, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  25%|██▌       | 236/938 [00:17<00:51, 13.70it/s, loss=0.715, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  25%|██▌       | 237/938 [00:17<00:51, 13.70it/s, loss=0.717, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  25%|██▌       | 238/938 [00:17<00:51, 13.70it/s, loss=0.711, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  25%|██▌       | 239/938 [00:17<00:51, 13.69it/s, loss=0.712, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  26%|██▌       | 240/938 [00:17<00:50, 13.69it/s, loss=0.712, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  26%|██▌       | 240/938 [00:17<00:50, 13.69it/s, loss=0.718, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  26%|██▌       | 241/938 [00:17<00:50, 13.69it/s, loss=0.721, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  26%|██▌       | 242/938 [00:17<00:50, 13.70it/s, loss=0.713, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  26%|██▌       | 243/938 [00:17<00:50, 13.70it/s, loss=0.709, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  26%|██▌       | 244/938 [00:17<00:50, 13.71it/s, loss=0.709, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  26%|██▌       | 244/938 [00:17<00:50, 13.71it/s, loss=0.708, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  26%|██▌       | 245/938 [00:17<00:50, 13.73it/s, loss=0.698, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  26%|██▌       | 246/938 [00:17<00:50, 13.73it/s, loss=0.691, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  26%|██▋       | 247/938 [00:17<00:50, 13.73it/s, loss=0.69, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  26%|██▋       | 248/938 [00:18<00:50, 13.73it/s, loss=0.69, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  26%|██▋       | 248/938 [00:18<00:50, 13.73it/s, loss=0.683, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  27%|██▋       | 249/938 [00:18<00:50, 13.73it/s, loss=0.671, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  27%|██▋       | 250/938 [00:18<00:50, 13.73it/s, loss=0.664, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  27%|██▋       | 251/938 [00:18<00:50, 13.72it/s, loss=0.664, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  27%|██▋       | 252/938 [00:18<00:49, 13.72it/s, loss=0.664, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  27%|██▋       | 252/938 [00:18<00:49, 13.72it/s, loss=0.65, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  27%|██▋       | 253/938 [00:18<00:49, 13.72it/s, loss=0.649, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  27%|██▋       | 254/938 [00:18<00:49, 13.73it/s, loss=0.641, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  27%|██▋       | 255/938 [00:18<00:49, 13.74it/s, loss=0.64, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  27%|██▋       | 256/938 [00:18<00:49, 13.74it/s, loss=0.64, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  27%|██▋       | 256/938 [00:18<00:49, 13.74it/s, loss=0.632, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  27%|██▋       | 257/938 [00:18<00:49, 13.74it/s, loss=0.636, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  28%|██▊       | 258/938 [00:18<00:49, 13.75it/s, loss=0.651, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  28%|██▊       | 259/938 [00:18<00:49, 13.75it/s, loss=0.655, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  28%|██▊       | 260/938 [00:18<00:49, 13.76it/s, loss=0.655, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  28%|██▊       | 260/938 [00:18<00:49, 13.76it/s, loss=0.656, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  28%|██▊       | 261/938 [00:18<00:49, 13.76it/s, loss=0.661, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  28%|██▊       | 262/938 [00:19<00:49, 13.77it/s, loss=0.674, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  28%|██▊       | 263/938 [00:19<00:49, 13.77it/s, loss=0.676, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  28%|██▊       | 264/938 [00:19<00:48, 13.77it/s, loss=0.676, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  28%|██▊       | 264/938 [00:19<00:48, 13.77it/s, loss=0.674, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  28%|██▊       | 265/938 [00:19<00:48, 13.76it/s, loss=0.682, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  28%|██▊       | 266/938 [00:19<00:48, 13.77it/s, loss=0.682, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  28%|██▊       | 267/938 [00:19<00:48, 13.77it/s, loss=0.68, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  29%|██▊       | 268/938 [00:19<00:48, 13.74it/s, loss=0.68, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  29%|██▊       | 268/938 [00:19<00:48, 13.74it/s, loss=0.674, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  29%|██▊       | 269/938 [00:19<00:48, 13.75it/s, loss=0.675, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  29%|██▉       | 270/938 [00:19<00:48, 13.75it/s, loss=0.68, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  29%|██▉       | 271/938 [00:19<00:48, 13.76it/s, loss=0.681, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  29%|██▉       | 272/938 [00:19<00:48, 13.76it/s, loss=0.681, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  29%|██▉       | 272/938 [00:19<00:48, 13.76it/s, loss=0.684, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  29%|██▉       | 273/938 [00:19<00:48, 13.76it/s, loss=0.703, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  29%|██▉       | 274/938 [00:19<00:48, 13.75it/s, loss=0.705, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  29%|██▉       | 275/938 [00:20<00:48, 13.75it/s, loss=0.707, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  29%|██▉       | 276/938 [00:20<00:48, 13.75it/s, loss=0.707, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  29%|██▉       | 276/938 [00:20<00:48, 13.75it/s, loss=0.714, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  30%|██▉       | 277/938 [00:20<00:48, 13.75it/s, loss=0.709, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  30%|██▉       | 278/938 [00:20<00:47, 13.75it/s, loss=0.696, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  30%|██▉       | 279/938 [00:20<00:47, 13.75it/s, loss=0.697, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  30%|██▉       | 280/938 [00:20<00:47, 13.74it/s, loss=0.697, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  30%|██▉       | 280/938 [00:20<00:47, 13.74it/s, loss=0.689, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  30%|██▉       | 281/938 [00:20<00:47, 13.74it/s, loss=0.687, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  30%|███       | 282/938 [00:20<00:47, 13.74it/s, loss=0.684, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  30%|███       | 283/938 [00:20<00:47, 13.73it/s, loss=0.688, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  30%|███       | 284/938 [00:20<00:47, 13.72it/s, loss=0.688, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  30%|███       | 284/938 [00:20<00:47, 13.72it/s, loss=0.691, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  30%|███       | 285/938 [00:20<00:47, 13.72it/s, loss=0.688, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  30%|███       | 286/938 [00:20<00:47, 13.72it/s, loss=0.688, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  31%|███       | 287/938 [00:20<00:47, 13.72it/s, loss=0.684, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  31%|███       | 288/938 [00:20<00:47, 13.72it/s, loss=0.684, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  31%|███       | 288/938 [00:20<00:47, 13.72it/s, loss=0.682, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  31%|███       | 289/938 [00:21<00:47, 13.71it/s, loss=0.68, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  31%|███       | 290/938 [00:21<00:47, 13.72it/s, loss=0.679, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  31%|███       | 291/938 [00:21<00:47, 13.71it/s, loss=0.671, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  31%|███       | 292/938 [00:21<00:47, 13.72it/s, loss=0.671, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  31%|███       | 292/938 [00:21<00:47, 13.72it/s, loss=0.665, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  31%|███       | 293/938 [00:21<00:47, 13.72it/s, loss=0.648, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  31%|███▏      | 294/938 [00:21<00:46, 13.72it/s, loss=0.655, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  31%|███▏      | 295/938 [00:21<00:46, 13.71it/s, loss=0.654, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  32%|███▏      | 296/938 [00:21<00:46, 13.73it/s, loss=0.654, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  32%|███▏      | 296/938 [00:21<00:46, 13.72it/s, loss=0.654, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  32%|███▏      | 297/938 [00:21<00:46, 13.72it/s, loss=0.654, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  32%|███▏      | 298/938 [00:21<00:46, 13.73it/s, loss=0.646, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  32%|███▏      | 299/938 [00:21<00:46, 13.73it/s, loss=0.646, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  32%|███▏      | 300/938 [00:21<00:46, 13.72it/s, loss=0.646, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  32%|███▏      | 300/938 [00:21<00:46, 13.72it/s, loss=0.656, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  32%|███▏      | 301/938 [00:21<00:46, 13.73it/s, loss=0.655, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  32%|███▏      | 302/938 [00:21<00:46, 13.73it/s, loss=0.656, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  32%|███▏      | 303/938 [00:22<00:46, 13.72it/s, loss=0.65, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  32%|███▏      | 304/938 [00:22<00:46, 13.73it/s, loss=0.65, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  32%|███▏      | 304/938 [00:22<00:46, 13.73it/s, loss=0.645, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  33%|███▎      | 305/938 [00:22<00:46, 13.74it/s, loss=0.643, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  33%|███▎      | 306/938 [00:22<00:46, 13.73it/s, loss=0.641, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  33%|███▎      | 307/938 [00:22<00:45, 13.74it/s, loss=0.641, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  33%|███▎      | 308/938 [00:22<00:45, 13.72it/s, loss=0.641, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  33%|███▎      | 308/938 [00:22<00:45, 13.72it/s, loss=0.642, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  33%|███▎      | 309/938 [00:22<00:45, 13.71it/s, loss=0.649, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  33%|███▎      | 310/938 [00:22<00:45, 13.72it/s, loss=0.649, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  33%|███▎      | 311/938 [00:22<00:45, 13.72it/s, loss=0.649, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  33%|███▎      | 312/938 [00:22<00:45, 13.72it/s, loss=0.649, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  33%|███▎      | 312/938 [00:22<00:45, 13.72it/s, loss=0.656, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  33%|███▎      | 313/938 [00:22<00:45, 13.73it/s, loss=0.658, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  33%|███▎      | 314/938 [00:22<00:45, 13.72it/s, loss=0.651, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  34%|███▎      | 315/938 [00:22<00:45, 13.72it/s, loss=0.649, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  34%|███▎      | 316/938 [00:23<00:45, 13.73it/s, loss=0.649, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  34%|███▎      | 316/938 [00:23<00:45, 13.73it/s, loss=0.643, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  34%|███▍      | 317/938 [00:23<00:45, 13.73it/s, loss=0.648, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  34%|███▍      | 318/938 [00:23<00:45, 13.74it/s, loss=0.649, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  34%|███▍      | 319/938 [00:23<00:45, 13.75it/s, loss=0.642, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  34%|███▍      | 320/938 [00:23<00:45, 13.72it/s, loss=0.642, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  34%|███▍      | 320/938 [00:23<00:45, 13.72it/s, loss=0.632, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  34%|███▍      | 321/938 [00:23<00:44, 13.73it/s, loss=0.632, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  34%|███▍      | 322/938 [00:23<00:44, 13.70it/s, loss=0.627, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  34%|███▍      | 323/938 [00:23<00:44, 13.70it/s, loss=0.628, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  35%|███▍      | 324/938 [00:23<00:44, 13.69it/s, loss=0.628, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  35%|███▍      | 324/938 [00:23<00:44, 13.69it/s, loss=0.631, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  35%|███▍      | 325/938 [00:23<00:44, 13.70it/s, loss=0.64, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  35%|███▍      | 326/938 [00:23<00:44, 13.70it/s, loss=0.645, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  35%|███▍      | 327/938 [00:23<00:44, 13.70it/s, loss=0.651, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  35%|███▍      | 328/938 [00:23<00:44, 13.70it/s, loss=0.651, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  35%|███▍      | 328/938 [00:23<00:44, 13.70it/s, loss=0.651, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  35%|███▌      | 329/938 [00:24<00:44, 13.70it/s, loss=0.653, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  35%|███▌      | 330/938 [00:24<00:44, 13.70it/s, loss=0.655, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  35%|███▌      | 331/938 [00:24<00:44, 13.70it/s, loss=0.664, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  35%|███▌      | 332/938 [00:24<00:44, 13.71it/s, loss=0.664, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  35%|███▌      | 332/938 [00:24<00:44, 13.71it/s, loss=0.661, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  36%|███▌      | 333/938 [00:24<00:44, 13.71it/s, loss=0.664, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  36%|███▌      | 334/938 [00:24<00:44, 13.70it/s, loss=0.661, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  36%|███▌      | 335/938 [00:24<00:43, 13.71it/s, loss=0.666, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  36%|███▌      | 336/938 [00:24<00:43, 13.71it/s, loss=0.666, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  36%|███▌      | 336/938 [00:24<00:43, 13.71it/s, loss=0.668, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  36%|███▌      | 337/938 [00:24<00:43, 13.71it/s, loss=0.66, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  36%|███▌      | 338/938 [00:24<00:43, 13.70it/s, loss=0.661, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  36%|███▌      | 339/938 [00:24<00:43, 13.70it/s, loss=0.668, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  36%|███▌      | 340/938 [00:24<00:43, 13.71it/s, loss=0.668, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  36%|███▌      | 340/938 [00:24<00:43, 13.71it/s, loss=0.67, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  36%|███▋      | 341/938 [00:24<00:43, 13.71it/s, loss=0.67, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  36%|███▋      | 342/938 [00:24<00:43, 13.70it/s, loss=0.674, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  37%|███▋      | 343/938 [00:25<00:43, 13.70it/s, loss=0.674, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  37%|███▋      | 344/938 [00:25<00:43, 13.71it/s, loss=0.674, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  37%|███▋      | 344/938 [00:25<00:43, 13.71it/s, loss=0.668, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  37%|███▋      | 345/938 [00:25<00:43, 13.70it/s, loss=0.656, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  37%|███▋      | 346/938 [00:25<00:43, 13.70it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  37%|███▋      | 347/938 [00:25<00:43, 13.70it/s, loss=0.658, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  37%|███▋      | 348/938 [00:25<00:43, 13.69it/s, loss=0.658, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  37%|███▋      | 348/938 [00:25<00:43, 13.69it/s, loss=0.68, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  37%|███▋      | 349/938 [00:25<00:43, 13.69it/s, loss=0.681, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  37%|███▋      | 350/938 [00:25<00:42, 13.68it/s, loss=0.678, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  37%|███▋      | 351/938 [00:25<00:42, 13.68it/s, loss=0.674, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  38%|███▊      | 352/938 [00:25<00:42, 13.68it/s, loss=0.674, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  38%|███▊      | 352/938 [00:25<00:42, 13.68it/s, loss=0.68, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  38%|███▊      | 353/938 [00:25<00:42, 13.68it/s, loss=0.683, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  38%|███▊      | 354/938 [00:25<00:42, 13.69it/s, loss=0.688, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  38%|███▊      | 355/938 [00:25<00:42, 13.69it/s, loss=0.682, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  38%|███▊      | 356/938 [00:26<00:42, 13.69it/s, loss=0.682, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  38%|███▊      | 356/938 [00:26<00:42, 13.69it/s, loss=0.686, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  38%|███▊      | 357/938 [00:26<00:42, 13.69it/s, loss=0.687, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  38%|███▊      | 358/938 [00:26<00:42, 13.69it/s, loss=0.691, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  38%|███▊      | 359/938 [00:26<00:42, 13.68it/s, loss=0.689, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  38%|███▊      | 360/938 [00:26<00:42, 13.68it/s, loss=0.689, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  38%|███▊      | 360/938 [00:26<00:42, 13.68it/s, loss=0.69, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  38%|███▊      | 361/938 [00:26<00:42, 13.68it/s, loss=0.687, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  39%|███▊      | 362/938 [00:26<00:42, 13.68it/s, loss=0.687, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  39%|███▊      | 363/938 [00:26<00:42, 13.68it/s, loss=0.69, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  39%|███▉      | 364/938 [00:26<00:41, 13.69it/s, loss=0.69, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  39%|███▉      | 364/938 [00:26<00:41, 13.69it/s, loss=0.697, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  39%|███▉      | 365/938 [00:26<00:41, 13.69it/s, loss=0.701, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  39%|███▉      | 366/938 [00:26<00:41, 13.68it/s, loss=0.689, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  39%|███▉      | 367/938 [00:26<00:41, 13.69it/s, loss=0.694, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  39%|███▉      | 368/938 [00:26<00:41, 13.68it/s, loss=0.694, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  39%|███▉      | 368/938 [00:26<00:41, 13.68it/s, loss=0.674, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  39%|███▉      | 369/938 [00:26<00:41, 13.69it/s, loss=0.669, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  39%|███▉      | 370/938 [00:27<00:41, 13.69it/s, loss=0.663, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  40%|███▉      | 371/938 [00:27<00:41, 13.69it/s, loss=0.665, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  40%|███▉      | 372/938 [00:27<00:41, 13.69it/s, loss=0.665, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  40%|███▉      | 372/938 [00:27<00:41, 13.69it/s, loss=0.661, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  40%|███▉      | 373/938 [00:27<00:41, 13.69it/s, loss=0.658, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  40%|███▉      | 374/938 [00:27<00:41, 13.68it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  40%|███▉      | 375/938 [00:27<00:41, 13.68it/s, loss=0.657, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  40%|████      | 376/938 [00:27<00:41, 13.68it/s, loss=0.657, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  40%|████      | 376/938 [00:27<00:41, 13.68it/s, loss=0.659, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  40%|████      | 377/938 [00:27<00:40, 13.68it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  40%|████      | 378/938 [00:27<00:40, 13.68it/s, loss=0.658, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  40%|████      | 379/938 [00:27<00:40, 13.67it/s, loss=0.658, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  41%|████      | 380/938 [00:27<00:40, 13.67it/s, loss=0.658, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  41%|████      | 380/938 [00:27<00:40, 13.67it/s, loss=0.655, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  41%|████      | 381/938 [00:27<00:40, 13.68it/s, loss=0.663, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  41%|████      | 382/938 [00:27<00:40, 13.67it/s, loss=0.663, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  41%|████      | 383/938 [00:27<00:40, 13.68it/s, loss=0.665, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  41%|████      | 384/938 [00:28<00:40, 13.68it/s, loss=0.665, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  41%|████      | 384/938 [00:28<00:40, 13.68it/s, loss=0.657, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  41%|████      | 385/938 [00:28<00:40, 13.68it/s, loss=0.655, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  41%|████      | 386/938 [00:28<00:40, 13.68it/s, loss=0.667, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  41%|████▏     | 387/938 [00:28<00:40, 13.68it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  41%|████▏     | 388/938 [00:28<00:40, 13.68it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  41%|████▏     | 388/938 [00:28<00:40, 13.68it/s, loss=0.672, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  41%|████▏     | 389/938 [00:28<00:40, 13.68it/s, loss=0.667, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  42%|████▏     | 390/938 [00:28<00:40, 13.68it/s, loss=0.674, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  42%|████▏     | 391/938 [00:28<00:39, 13.68it/s, loss=0.668, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  42%|████▏     | 392/938 [00:28<00:39, 13.69it/s, loss=0.668, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  42%|████▏     | 392/938 [00:28<00:39, 13.68it/s, loss=0.669, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  42%|████▏     | 393/938 [00:28<00:39, 13.68it/s, loss=0.663, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  42%|████▏     | 394/938 [00:28<00:39, 13.69it/s, loss=0.664, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  42%|████▏     | 395/938 [00:28<00:39, 13.68it/s, loss=0.668, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  42%|████▏     | 396/938 [00:28<00:39, 13.69it/s, loss=0.668, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  42%|████▏     | 396/938 [00:28<00:39, 13.69it/s, loss=0.67, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  42%|████▏     | 397/938 [00:29<00:39, 13.69it/s, loss=0.661, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  42%|████▏     | 398/938 [00:29<00:39, 13.69it/s, loss=0.664, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  43%|████▎     | 399/938 [00:29<00:39, 13.70it/s, loss=0.659, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  43%|████▎     | 400/938 [00:29<00:39, 13.69it/s, loss=0.659, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  43%|████▎     | 400/938 [00:29<00:39, 13.69it/s, loss=0.654, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  43%|████▎     | 401/938 [00:29<00:39, 13.69it/s, loss=0.647, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  43%|████▎     | 402/938 [00:29<00:39, 13.70it/s, loss=0.636, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  43%|████▎     | 403/938 [00:29<00:39, 13.70it/s, loss=0.636, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  43%|████▎     | 404/938 [00:29<00:38, 13.70it/s, loss=0.636, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  43%|████▎     | 404/938 [00:29<00:38, 13.70it/s, loss=0.644, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  43%|████▎     | 405/938 [00:29<00:38, 13.71it/s, loss=0.645, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  43%|████▎     | 406/938 [00:29<00:38, 13.71it/s, loss=0.634, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  43%|████▎     | 407/938 [00:29<00:38, 13.71it/s, loss=0.636, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  43%|████▎     | 408/938 [00:29<00:38, 13.71it/s, loss=0.636, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  43%|████▎     | 408/938 [00:29<00:38, 13.71it/s, loss=0.635, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  44%|████▎     | 409/938 [00:29<00:38, 13.71it/s, loss=0.641, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  44%|████▎     | 410/938 [00:29<00:38, 13.71it/s, loss=0.636, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  44%|████▍     | 411/938 [00:29<00:38, 13.71it/s, loss=0.648, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  44%|████▍     | 412/938 [00:30<00:38, 13.71it/s, loss=0.648, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  44%|████▍     | 412/938 [00:30<00:38, 13.71it/s, loss=0.645, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  44%|████▍     | 413/938 [00:30<00:38, 13.70it/s, loss=0.652, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  44%|████▍     | 414/938 [00:30<00:38, 13.70it/s, loss=0.648, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  44%|████▍     | 415/938 [00:30<00:38, 13.69it/s, loss=0.648, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  44%|████▍     | 416/938 [00:30<00:38, 13.68it/s, loss=0.648, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  44%|████▍     | 416/938 [00:30<00:38, 13.68it/s, loss=0.648, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  44%|████▍     | 417/938 [00:30<00:38, 13.67it/s, loss=0.654, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  45%|████▍     | 418/938 [00:30<00:38, 13.67it/s, loss=0.661, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  45%|████▍     | 419/938 [00:30<00:37, 13.67it/s, loss=0.665, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  45%|████▍     | 420/938 [00:30<00:37, 13.67it/s, loss=0.665, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  45%|████▍     | 420/938 [00:30<00:37, 13.67it/s, loss=0.672, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  45%|████▍     | 421/938 [00:30<00:37, 13.67it/s, loss=0.683, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  45%|████▍     | 422/938 [00:30<00:37, 13.68it/s, loss=0.688, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  45%|████▌     | 423/938 [00:30<00:37, 13.67it/s, loss=0.691, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  45%|████▌     | 424/938 [00:31<00:37, 13.67it/s, loss=0.691, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  45%|████▌     | 424/938 [00:31<00:37, 13.67it/s, loss=0.686, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  45%|████▌     | 425/938 [00:31<00:37, 13.67it/s, loss=0.679, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  45%|████▌     | 426/938 [00:31<00:37, 13.66it/s, loss=0.686, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  46%|████▌     | 427/938 [00:31<00:37, 13.66it/s, loss=0.684, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  46%|████▌     | 428/938 [00:31<00:37, 13.66it/s, loss=0.684, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  46%|████▌     | 428/938 [00:31<00:37, 13.66it/s, loss=0.676, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  46%|████▌     | 429/938 [00:31<00:37, 13.66it/s, loss=0.667, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  46%|████▌     | 430/938 [00:31<00:37, 13.66it/s, loss=0.674, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  46%|████▌     | 431/938 [00:31<00:37, 13.66it/s, loss=0.664, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  46%|████▌     | 432/938 [00:31<00:37, 13.66it/s, loss=0.664, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  46%|████▌     | 432/938 [00:31<00:37, 13.65it/s, loss=0.665, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  46%|████▌     | 433/938 [00:31<00:36, 13.65it/s, loss=0.661, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  46%|████▋     | 434/938 [00:31<00:36, 13.65it/s, loss=0.66, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  46%|████▋     | 435/938 [00:31<00:36, 13.65it/s, loss=0.657, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  46%|████▋     | 436/938 [00:31<00:36, 13.65it/s, loss=0.657, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  46%|████▋     | 436/938 [00:31<00:36, 13.65it/s, loss=0.652, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  47%|████▋     | 437/938 [00:32<00:36, 13.65it/s, loss=0.651, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  47%|████▋     | 438/938 [00:32<00:36, 13.64it/s, loss=0.644, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  47%|████▋     | 439/938 [00:32<00:36, 13.64it/s, loss=0.642, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  47%|████▋     | 440/938 [00:32<00:36, 13.64it/s, loss=0.642, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  47%|████▋     | 440/938 [00:32<00:36, 13.64it/s, loss=0.636, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  47%|████▋     | 441/938 [00:32<00:36, 13.64it/s, loss=0.627, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  47%|████▋     | 442/938 [00:32<00:36, 13.64it/s, loss=0.634, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  47%|████▋     | 443/938 [00:32<00:36, 13.64it/s, loss=0.636, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  47%|████▋     | 444/938 [00:32<00:36, 13.65it/s, loss=0.636, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  47%|████▋     | 444/938 [00:32<00:36, 13.65it/s, loss=0.638, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  47%|████▋     | 445/938 [00:32<00:36, 13.65it/s, loss=0.645, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  48%|████▊     | 446/938 [00:32<00:36, 13.65it/s, loss=0.641, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  48%|████▊     | 447/938 [00:32<00:35, 13.65it/s, loss=0.642, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  48%|████▊     | 448/938 [00:32<00:35, 13.65it/s, loss=0.642, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  48%|████▊     | 448/938 [00:32<00:35, 13.65it/s, loss=0.645, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  48%|████▊     | 449/938 [00:32<00:35, 13.65it/s, loss=0.648, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  48%|████▊     | 450/938 [00:32<00:35, 13.65it/s, loss=0.653, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  48%|████▊     | 451/938 [00:33<00:35, 13.65it/s, loss=0.653, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  48%|████▊     | 452/938 [00:33<00:35, 13.65it/s, loss=0.653, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  48%|████▊     | 452/938 [00:33<00:35, 13.65it/s, loss=0.659, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  48%|████▊     | 453/938 [00:33<00:35, 13.65it/s, loss=0.661, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  48%|████▊     | 454/938 [00:33<00:35, 13.66it/s, loss=0.66, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  49%|████▊     | 455/938 [00:33<00:35, 13.66it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  49%|████▊     | 456/938 [00:33<00:35, 13.67it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  49%|████▊     | 456/938 [00:33<00:35, 13.67it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  49%|████▊     | 457/938 [00:33<00:35, 13.67it/s, loss=0.657, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  49%|████▉     | 458/938 [00:33<00:35, 13.67it/s, loss=0.66, v_num=10, val_rmse=0.554, train_rmse=0.728] 
Epoch 2:  49%|████▉     | 459/938 [00:33<00:35, 13.67it/s, loss=0.653, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  49%|████▉     | 460/938 [00:33<00:34, 13.68it/s, loss=0.653, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  49%|████▉     | 460/938 [00:33<00:34, 13.68it/s, loss=0.657, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  49%|████▉     | 461/938 [00:33<00:34, 13.67it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  49%|████▉     | 462/938 [00:33<00:34, 13.68it/s, loss=0.661, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  49%|████▉     | 463/938 [00:33<00:34, 13.67it/s, loss=0.651, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  49%|████▉     | 464/938 [00:33<00:34, 13.68it/s, loss=0.651, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  49%|████▉     | 464/938 [00:33<00:34, 13.68it/s, loss=0.651, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  50%|████▉     | 465/938 [00:34<00:34, 13.66it/s, loss=0.649, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  50%|████▉     | 466/938 [00:34<00:34, 13.66it/s, loss=0.646, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  50%|████▉     | 467/938 [00:34<00:34, 13.67it/s, loss=0.645, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  50%|████▉     | 468/938 [00:34<00:34, 13.67it/s, loss=0.645, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  50%|████▉     | 468/938 [00:34<00:34, 13.67it/s, loss=0.653, v_num=10, val_rmse=0.554, train_rmse=0.728]
Epoch 2:  50%|█████     | 469/938 [00:34<00:34, 13.68it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]

Validating:   0%|          | 2/469 [00:00<00:24, 18.97it/s]
Epoch 2:  50%|█████     | 472/938 [00:34<00:33, 13.72it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:   1%|          | 5/469 [00:00<00:21, 21.26it/s]
Epoch 2:  51%|█████     | 476/938 [00:34<00:33, 13.77it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:   2%|▏         | 8/469 [00:00<00:20, 22.38it/s]
Epoch 2:  51%|█████     | 480/938 [00:34<00:33, 13.81it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:   2%|▏         | 11/469 [00:00<00:20, 22.54it/s]

Validating:   3%|▎         | 14/469 [00:00<00:19, 23.25it/s]
Epoch 2:  52%|█████▏    | 484/938 [00:34<00:32, 13.86it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:   4%|▎         | 17/469 [00:00<00:18, 24.06it/s]
Epoch 2:  52%|█████▏    | 488/938 [00:35<00:32, 13.92it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:   4%|▍         | 20/469 [00:00<00:17, 25.35it/s]
Epoch 2:  52%|█████▏    | 492/938 [00:35<00:31, 13.97it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:   5%|▍         | 23/469 [00:00<00:17, 24.99it/s]

Validating:   6%|▌         | 26/469 [00:01<00:17, 25.22it/s]
Epoch 2:  53%|█████▎    | 496/938 [00:35<00:31, 14.02it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:   6%|▌         | 29/469 [00:01<00:17, 25.77it/s]
Epoch 2:  53%|█████▎    | 500/938 [00:35<00:31, 14.08it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:   7%|▋         | 32/469 [00:01<00:17, 24.77it/s]
Epoch 2:  54%|█████▎    | 504/938 [00:35<00:30, 14.12it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:   7%|▋         | 35/469 [00:01<00:17, 25.35it/s]

Validating:   8%|▊         | 38/469 [00:01<00:17, 25.31it/s]
Epoch 2:  54%|█████▍    | 508/938 [00:35<00:30, 14.17it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:   9%|▊         | 41/469 [00:01<00:17, 24.98it/s]
Epoch 2:  55%|█████▍    | 512/938 [00:36<00:29, 14.22it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:   9%|▉         | 44/469 [00:01<00:16, 25.38it/s]
Epoch 2:  55%|█████▌    | 516/938 [00:36<00:29, 14.27it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  10%|█         | 47/469 [00:01<00:17, 24.03it/s]

Validating:  11%|█         | 50/469 [00:02<00:17, 24.10it/s]
Epoch 2:  55%|█████▌    | 520/938 [00:36<00:29, 14.31it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  11%|█▏        | 53/469 [00:02<00:16, 24.81it/s]
Epoch 2:  56%|█████▌    | 524/938 [00:36<00:28, 14.34it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  12%|█▏        | 56/469 [00:02<00:17, 23.41it/s]
Epoch 2:  56%|█████▋    | 528/938 [00:36<00:28, 14.39it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  13%|█▎        | 59/469 [00:02<00:16, 24.16it/s]

Validating:  13%|█▎        | 62/469 [00:02<00:16, 24.30it/s]
Epoch 2:  57%|█████▋    | 532/938 [00:36<00:28, 14.44it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  14%|█▍        | 65/469 [00:02<00:16, 25.06it/s]
Epoch 2:  57%|█████▋    | 536/938 [00:36<00:27, 14.49it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  14%|█▍        | 68/469 [00:02<00:16, 24.90it/s]
Epoch 2:  58%|█████▊    | 540/938 [00:37<00:27, 14.54it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  15%|█▌        | 71/469 [00:02<00:16, 24.85it/s]

Validating:  16%|█▌        | 74/469 [00:03<00:15, 25.14it/s]
Epoch 2:  58%|█████▊    | 544/938 [00:37<00:27, 14.58it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  16%|█▋        | 77/469 [00:03<00:15, 25.07it/s]
Epoch 2:  58%|█████▊    | 548/938 [00:37<00:26, 14.62it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  17%|█▋        | 80/469 [00:03<00:15, 24.79it/s]
Epoch 2:  59%|█████▉    | 552/938 [00:37<00:26, 14.67it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  18%|█▊        | 83/469 [00:03<00:15, 24.52it/s]

Validating:  18%|█▊        | 86/469 [00:03<00:15, 25.32it/s]
Epoch 2:  59%|█████▉    | 556/938 [00:37<00:25, 14.71it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  19%|█▉        | 89/469 [00:03<00:15, 23.88it/s]
Epoch 2:  60%|█████▉    | 560/938 [00:37<00:25, 14.75it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  20%|█▉        | 92/469 [00:03<00:15, 23.82it/s]
Epoch 2:  60%|██████    | 564/938 [00:38<00:25, 14.79it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  20%|██        | 95/469 [00:03<00:15, 24.37it/s]

Validating:  21%|██        | 98/469 [00:04<00:15, 24.04it/s]
Epoch 2:  61%|██████    | 568/938 [00:38<00:24, 14.83it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  22%|██▏       | 101/469 [00:04<00:15, 23.54it/s]
Epoch 2:  61%|██████    | 572/938 [00:38<00:24, 14.86it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  22%|██▏       | 104/469 [00:04<00:15, 23.96it/s]
Epoch 2:  61%|██████▏   | 576/938 [00:38<00:24, 14.91it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  23%|██▎       | 107/469 [00:04<00:14, 24.52it/s]

Validating:  23%|██▎       | 110/469 [00:04<00:14, 24.76it/s]
Epoch 2:  62%|██████▏   | 580/938 [00:38<00:23, 14.95it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  24%|██▍       | 113/469 [00:04<00:14, 24.76it/s]
Epoch 2:  62%|██████▏   | 584/938 [00:38<00:23, 14.99it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  25%|██▍       | 116/469 [00:04<00:14, 25.18it/s]
Epoch 2:  63%|██████▎   | 588/938 [00:39<00:23, 15.03it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  25%|██▌       | 119/469 [00:04<00:14, 24.37it/s]

Validating:  26%|██▌       | 122/469 [00:04<00:14, 24.33it/s]
Epoch 2:  63%|██████▎   | 592/938 [00:39<00:22, 15.07it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  27%|██▋       | 125/469 [00:05<00:14, 23.99it/s]
Epoch 2:  64%|██████▎   | 596/938 [00:39<00:22, 15.10it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  27%|██▋       | 128/469 [00:05<00:14, 23.69it/s]
Epoch 2:  64%|██████▍   | 600/938 [00:39<00:22, 15.15it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  28%|██▊       | 131/469 [00:05<00:13, 24.91it/s]

Validating:  29%|██▊       | 134/469 [00:05<00:13, 24.32it/s]
Epoch 2:  64%|██████▍   | 604/938 [00:39<00:21, 15.18it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  29%|██▉       | 137/469 [00:05<00:14, 23.36it/s]
Epoch 2:  65%|██████▍   | 608/938 [00:39<00:21, 15.21it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  30%|██▉       | 140/469 [00:05<00:13, 24.04it/s]
Epoch 2:  65%|██████▌   | 612/938 [00:40<00:21, 15.25it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  30%|███       | 143/469 [00:05<00:13, 24.21it/s]

Validating:  31%|███       | 146/469 [00:05<00:13, 24.80it/s]
Epoch 2:  66%|██████▌   | 616/938 [00:40<00:21, 15.30it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  32%|███▏      | 149/469 [00:06<00:12, 25.42it/s]
Epoch 2:  66%|██████▌   | 620/938 [00:40<00:20, 15.34it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  32%|███▏      | 152/469 [00:06<00:12, 25.03it/s]
Epoch 2:  67%|██████▋   | 624/938 [00:40<00:20, 15.37it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  33%|███▎      | 155/469 [00:06<00:12, 24.55it/s]

Validating:  34%|███▎      | 158/469 [00:06<00:12, 24.09it/s]
Epoch 2:  67%|██████▋   | 628/938 [00:40<00:20, 15.40it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  34%|███▍      | 161/469 [00:06<00:12, 24.36it/s]
Epoch 2:  67%|██████▋   | 632/938 [00:40<00:19, 15.44it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  35%|███▍      | 164/469 [00:06<00:12, 24.94it/s]
Epoch 2:  68%|██████▊   | 636/938 [00:41<00:19, 15.48it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  36%|███▌      | 167/469 [00:06<00:12, 24.44it/s]

Validating:  36%|███▌      | 170/469 [00:06<00:12, 24.14it/s]
Epoch 2:  68%|██████▊   | 640/938 [00:41<00:19, 15.51it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  37%|███▋      | 173/469 [00:07<00:11, 24.85it/s]
Epoch 2:  69%|██████▊   | 644/938 [00:41<00:18, 15.55it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  38%|███▊      | 176/469 [00:07<00:11, 24.91it/s]
Epoch 2:  69%|██████▉   | 648/938 [00:41<00:18, 15.59it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  38%|███▊      | 179/469 [00:07<00:11, 24.71it/s]

Validating:  39%|███▉      | 182/469 [00:07<00:11, 24.71it/s]
Epoch 2:  70%|██████▉   | 652/938 [00:41<00:18, 15.62it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  39%|███▉      | 185/469 [00:07<00:11, 24.41it/s]
Epoch 2:  70%|██████▉   | 656/938 [00:41<00:18, 15.65it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  40%|████      | 188/469 [00:07<00:12, 22.93it/s]
Epoch 2:  70%|███████   | 660/938 [00:42<00:17, 15.68it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  41%|████      | 191/469 [00:07<00:11, 23.22it/s]

Validating:  41%|████▏     | 194/469 [00:07<00:12, 22.53it/s]
Epoch 2:  71%|███████   | 664/938 [00:42<00:17, 15.71it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  42%|████▏     | 197/469 [00:08<00:11, 23.34it/s]
Epoch 2:  71%|███████   | 668/938 [00:42<00:17, 15.74it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  43%|████▎     | 200/469 [00:08<00:11, 24.11it/s]
Epoch 2:  72%|███████▏  | 672/938 [00:42<00:16, 15.78it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  43%|████▎     | 203/469 [00:08<00:11, 23.69it/s]

Validating:  44%|████▍     | 206/469 [00:08<00:10, 24.56it/s]
Epoch 2:  72%|███████▏  | 676/938 [00:42<00:16, 15.81it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  45%|████▍     | 209/469 [00:08<00:10, 25.35it/s]
Epoch 2:  72%|███████▏  | 680/938 [00:42<00:16, 15.85it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  45%|████▌     | 212/469 [00:08<00:10, 25.47it/s]
Epoch 2:  73%|███████▎  | 684/938 [00:43<00:15, 15.88it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  46%|████▌     | 215/469 [00:08<00:10, 25.11it/s]

Validating:  46%|████▋     | 218/469 [00:08<00:10, 23.92it/s]
Epoch 2:  73%|███████▎  | 688/938 [00:43<00:15, 15.91it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  47%|████▋     | 221/469 [00:09<00:10, 23.62it/s]
Epoch 2:  74%|███████▍  | 692/938 [00:43<00:15, 15.94it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  48%|████▊     | 224/469 [00:09<00:10, 22.84it/s]
Epoch 2:  74%|███████▍  | 696/938 [00:43<00:15, 15.96it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  48%|████▊     | 227/469 [00:09<00:10, 23.16it/s]

Validating:  49%|████▉     | 230/469 [00:09<00:10, 23.24it/s]
Epoch 2:  75%|███████▍  | 700/938 [00:43<00:14, 15.99it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  50%|████▉     | 233/469 [00:09<00:10, 22.74it/s]
Epoch 2:  75%|███████▌  | 704/938 [00:43<00:14, 16.02it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  50%|█████     | 236/469 [00:09<00:09, 23.38it/s]
Epoch 2:  75%|███████▌  | 708/938 [00:44<00:14, 16.06it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  51%|█████     | 239/469 [00:09<00:09, 23.86it/s]

Validating:  52%|█████▏    | 242/469 [00:09<00:09, 24.34it/s]
Epoch 2:  76%|███████▌  | 712/938 [00:44<00:14, 16.09it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  52%|█████▏    | 245/469 [00:10<00:09, 23.91it/s]
Epoch 2:  76%|███████▋  | 716/938 [00:44<00:13, 16.11it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  53%|█████▎    | 248/469 [00:10<00:09, 24.08it/s]
Epoch 2:  77%|███████▋  | 720/938 [00:44<00:13, 16.14it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  54%|█████▎    | 251/469 [00:10<00:09, 23.76it/s]

Validating:  54%|█████▍    | 254/469 [00:10<00:08, 24.26it/s]
Epoch 2:  77%|███████▋  | 724/938 [00:44<00:13, 16.17it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  55%|█████▍    | 257/469 [00:10<00:08, 24.22it/s]
Epoch 2:  78%|███████▊  | 728/938 [00:44<00:12, 16.20it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  55%|█████▌    | 260/469 [00:10<00:08, 24.18it/s]
Epoch 2:  78%|███████▊  | 732/938 [00:45<00:12, 16.23it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  56%|█████▌    | 263/469 [00:10<00:08, 24.86it/s]

Validating:  57%|█████▋    | 266/469 [00:10<00:08, 25.21it/s]
Epoch 2:  78%|███████▊  | 736/938 [00:45<00:12, 16.27it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  57%|█████▋    | 269/469 [00:11<00:07, 25.96it/s]
Epoch 2:  79%|███████▉  | 740/938 [00:45<00:12, 16.30it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  58%|█████▊    | 272/469 [00:11<00:07, 25.48it/s]
Epoch 2:  79%|███████▉  | 744/938 [00:45<00:11, 16.33it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  59%|█████▊    | 275/469 [00:11<00:07, 25.29it/s]

Validating:  59%|█████▉    | 278/469 [00:11<00:07, 25.22it/s]
Epoch 2:  80%|███████▉  | 748/938 [00:45<00:11, 16.36it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  60%|█████▉    | 281/469 [00:11<00:07, 25.48it/s]
Epoch 2:  80%|████████  | 752/938 [00:45<00:11, 16.40it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  61%|██████    | 284/469 [00:11<00:07, 25.17it/s]
Epoch 2:  81%|████████  | 756/938 [00:46<00:11, 16.42it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  61%|██████    | 287/469 [00:11<00:07, 24.68it/s]

Validating:  62%|██████▏   | 290/469 [00:11<00:07, 24.62it/s]
Epoch 2:  81%|████████  | 760/938 [00:46<00:10, 16.45it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  62%|██████▏   | 293/469 [00:12<00:07, 25.03it/s]
Epoch 2:  81%|████████▏ | 764/938 [00:46<00:10, 16.48it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  63%|██████▎   | 296/469 [00:12<00:06, 24.83it/s]
Epoch 2:  82%|████████▏ | 768/938 [00:46<00:10, 16.51it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  64%|██████▍   | 299/469 [00:12<00:06, 24.78it/s]

Validating:  64%|██████▍   | 302/469 [00:12<00:06, 24.02it/s]
Epoch 2:  82%|████████▏ | 772/938 [00:46<00:10, 16.53it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  65%|██████▌   | 305/469 [00:12<00:06, 23.78it/s]
Epoch 2:  83%|████████▎ | 776/938 [00:46<00:09, 16.56it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  66%|██████▌   | 308/469 [00:12<00:06, 24.74it/s]
Epoch 2:  83%|████████▎ | 780/938 [00:47<00:09, 16.59it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  66%|██████▋   | 311/469 [00:12<00:06, 24.50it/s]

Validating:  67%|██████▋   | 314/469 [00:12<00:06, 23.66it/s]
Epoch 2:  84%|████████▎ | 784/938 [00:47<00:09, 16.61it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  68%|██████▊   | 317/469 [00:13<00:06, 24.19it/s]
Epoch 2:  84%|████████▍ | 788/938 [00:47<00:09, 16.64it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  68%|██████▊   | 320/469 [00:13<00:06, 24.14it/s]
Epoch 2:  84%|████████▍ | 792/938 [00:47<00:08, 16.67it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  69%|██████▉   | 323/469 [00:13<00:05, 25.08it/s]

Validating:  70%|██████▉   | 326/469 [00:13<00:05, 25.71it/s]
Epoch 2:  85%|████████▍ | 796/938 [00:47<00:08, 16.70it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  70%|███████   | 329/469 [00:13<00:05, 25.79it/s]
Epoch 2:  85%|████████▌ | 800/938 [00:47<00:08, 16.73it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  71%|███████   | 332/469 [00:13<00:05, 25.70it/s]
Epoch 2:  86%|████████▌ | 804/938 [00:47<00:07, 16.76it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  71%|███████▏  | 335/469 [00:13<00:05, 26.13it/s]

Validating:  72%|███████▏  | 338/469 [00:13<00:05, 25.84it/s]
Epoch 2:  86%|████████▌ | 808/938 [00:48<00:07, 16.79it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  73%|███████▎  | 341/469 [00:13<00:05, 25.44it/s]
Epoch 2:  87%|████████▋ | 812/938 [00:48<00:07, 16.82it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  73%|███████▎  | 344/469 [00:14<00:04, 26.14it/s]
Epoch 2:  87%|████████▋ | 816/938 [00:48<00:07, 16.85it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  74%|███████▍  | 347/469 [00:14<00:04, 26.04it/s]

Validating:  75%|███████▍  | 350/469 [00:14<00:04, 25.67it/s]
Epoch 2:  87%|████████▋ | 820/938 [00:48<00:06, 16.88it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  75%|███████▌  | 353/469 [00:14<00:04, 25.23it/s]
Epoch 2:  88%|████████▊ | 824/938 [00:48<00:06, 16.91it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  76%|███████▌  | 356/469 [00:14<00:04, 25.38it/s]
Epoch 2:  88%|████████▊ | 828/938 [00:48<00:06, 16.93it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  77%|███████▋  | 359/469 [00:14<00:04, 25.87it/s]

Validating:  77%|███████▋  | 362/469 [00:14<00:04, 24.51it/s]
Epoch 2:  89%|████████▊ | 832/938 [00:49<00:06, 16.95it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  78%|███████▊  | 365/469 [00:14<00:04, 23.48it/s]
Epoch 2:  89%|████████▉ | 836/938 [00:49<00:06, 16.97it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  78%|███████▊  | 368/469 [00:15<00:04, 23.75it/s]
Epoch 2:  90%|████████▉ | 840/938 [00:49<00:05, 17.00it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  79%|███████▉  | 371/469 [00:15<00:04, 24.32it/s]

Validating:  80%|███████▉  | 374/469 [00:15<00:04, 23.21it/s]
Epoch 2:  90%|████████▉ | 844/938 [00:49<00:05, 17.02it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  80%|████████  | 377/469 [00:15<00:03, 24.00it/s]
Epoch 2:  90%|█████████ | 848/938 [00:49<00:05, 17.05it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  81%|████████  | 380/469 [00:15<00:03, 24.48it/s]
Epoch 2:  91%|█████████ | 852/938 [00:49<00:05, 17.07it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  82%|████████▏ | 383/469 [00:15<00:03, 24.15it/s]

Validating:  82%|████████▏ | 386/469 [00:15<00:03, 24.02it/s]
Epoch 2:  91%|█████████▏| 856/938 [00:50<00:04, 17.09it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  83%|████████▎ | 389/469 [00:15<00:03, 23.50it/s]
Epoch 2:  92%|█████████▏| 860/938 [00:50<00:04, 17.11it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  84%|████████▎ | 392/469 [00:16<00:03, 24.43it/s]
Epoch 2:  92%|█████████▏| 864/938 [00:50<00:04, 17.14it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  84%|████████▍ | 395/469 [00:16<00:03, 23.09it/s]

Validating:  85%|████████▍ | 398/469 [00:16<00:03, 23.33it/s]
Epoch 2:  93%|█████████▎| 868/938 [00:50<00:04, 17.15it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  86%|████████▌ | 401/469 [00:16<00:02, 23.66it/s]
Epoch 2:  93%|█████████▎| 872/938 [00:50<00:03, 17.18it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  86%|████████▌ | 404/469 [00:16<00:02, 24.02it/s]
Epoch 2:  93%|█████████▎| 876/938 [00:50<00:03, 17.21it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  87%|████████▋ | 407/469 [00:16<00:02, 24.70it/s]

Validating:  87%|████████▋ | 410/469 [00:16<00:02, 24.90it/s]
Epoch 2:  94%|█████████▍| 880/938 [00:51<00:03, 17.23it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  88%|████████▊ | 413/469 [00:16<00:02, 24.96it/s]
Epoch 2:  94%|█████████▍| 884/938 [00:51<00:03, 17.25it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  89%|████████▊ | 416/469 [00:17<00:02, 24.83it/s]
Epoch 2:  95%|█████████▍| 888/938 [00:51<00:02, 17.27it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  89%|████████▉ | 419/469 [00:17<00:02, 22.79it/s]

Validating:  90%|████████▉ | 422/469 [00:17<00:02, 23.47it/s]
Epoch 2:  95%|█████████▌| 892/938 [00:51<00:02, 17.29it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  91%|█████████ | 425/469 [00:17<00:01, 23.73it/s]
Epoch 2:  96%|█████████▌| 896/938 [00:51<00:02, 17.31it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  91%|█████████▏| 428/469 [00:17<00:01, 24.73it/s]
Epoch 2:  96%|█████████▌| 900/938 [00:51<00:02, 17.34it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  92%|█████████▏| 431/469 [00:17<00:01, 24.76it/s]

Validating:  93%|█████████▎| 434/469 [00:17<00:01, 23.92it/s]
Epoch 2:  96%|█████████▋| 904/938 [00:52<00:01, 17.36it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  93%|█████████▎| 437/469 [00:17<00:01, 24.37it/s]
Epoch 2:  97%|█████████▋| 908/938 [00:52<00:01, 17.38it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  94%|█████████▍| 440/469 [00:18<00:01, 24.60it/s]
Epoch 2:  97%|█████████▋| 912/938 [00:52<00:01, 17.40it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  94%|█████████▍| 443/469 [00:18<00:01, 24.77it/s]

Validating:  95%|█████████▌| 446/469 [00:18<00:00, 25.03it/s]
Epoch 2:  98%|█████████▊| 916/938 [00:52<00:01, 17.43it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  96%|█████████▌| 449/469 [00:18<00:00, 24.55it/s]
Epoch 2:  98%|█████████▊| 920/938 [00:52<00:01, 17.45it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  96%|█████████▋| 452/469 [00:18<00:00, 24.92it/s]
Epoch 2:  99%|█████████▊| 924/938 [00:52<00:00, 17.48it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  97%|█████████▋| 455/469 [00:18<00:00, 25.31it/s]

Validating:  98%|█████████▊| 458/469 [00:18<00:00, 25.57it/s]
Epoch 2:  99%|█████████▉| 928/938 [00:53<00:00, 17.50it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  98%|█████████▊| 461/469 [00:18<00:00, 25.63it/s]
Epoch 2:  99%|█████████▉| 932/938 [00:53<00:00, 17.53it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating:  99%|█████████▉| 464/469 [00:18<00:00, 25.64it/s]
Epoch 2: 100%|█████████▉| 936/938 [00:53<00:00, 17.55it/s, loss=0.662, v_num=10, val_rmse=0.554, train_rmse=0.728]

Validating: 100%|█████████▉| 467/469 [00:19<00:00, 26.21it/s]
Epoch 2: 100%|██████████| 938/938 [00:53<00:00, 17.55it/s, loss=0.662, v_num=10, val_rmse=0.525, train_rmse=0.728]

                                                             
Epoch 2: 100%|██████████| 938/938 [00:53<00:00, 17.55it/s, loss=0.662, v_num=10, val_rmse=0.525, train_rmse=0.669]
Epoch 2: 100%|██████████| 938/938 [00:53<00:00, 17.49it/s, loss=0.662, v_num=10, val_rmse=0.525, train_rmse=0.669]LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]


Testing: 0it [00:00, ?it/s]
Testing:   0%|          | 2/469 [00:00<00:25, 18.14it/s]
Testing:   1%|          | 5/469 [00:00<00:23, 19.51it/s]
Testing:   2%|▏         | 8/469 [00:00<00:20, 22.23it/s]
Testing:   2%|▏         | 11/469 [00:00<00:19, 23.05it/s]
Testing:   3%|▎         | 14/469 [00:00<00:20, 22.60it/s]
Testing:   4%|▎         | 17/469 [00:00<00:19, 23.64it/s]
Testing:   4%|▍         | 20/469 [00:00<00:19, 23.48it/s]
Testing:   5%|▍         | 23/469 [00:01<00:19, 23.27it/s]
Testing:   6%|▌         | 26/469 [00:01<00:19, 22.42it/s]
Testing:   6%|▌         | 29/469 [00:01<00:19, 22.13it/s]
Testing:   7%|▋         | 32/469 [00:01<00:19, 22.34it/s]
Testing:   7%|▋         | 35/469 [00:01<00:18, 23.53it/s]
Testing:   8%|▊         | 38/469 [00:01<00:17, 24.20it/s]
Testing:   9%|▊         | 41/469 [00:01<00:17, 24.78it/s]
Testing:   9%|▉         | 44/469 [00:01<00:17, 24.45it/s]
Testing:  10%|█         | 47/469 [00:02<00:17, 23.66it/s]
Testing:  11%|█         | 50/469 [00:02<00:17, 24.53it/s]
Testing:  11%|█▏        | 53/469 [00:02<00:17, 24.01it/s]
Testing:  12%|█▏        | 56/469 [00:02<00:17, 24.03it/s]
Testing:  13%|█▎        | 59/469 [00:02<00:17, 23.53it/s]
Testing:  13%|█▎        | 62/469 [00:02<00:17, 23.17it/s]
Testing:  14%|█▍        | 65/469 [00:02<00:17, 23.48it/s]
Testing:  14%|█▍        | 68/469 [00:02<00:16, 23.79it/s]
Testing:  15%|█▌        | 71/469 [00:03<00:16, 23.99it/s]
Testing:  16%|█▌        | 74/469 [00:03<00:16, 23.24it/s]
Testing:  16%|█▋        | 77/469 [00:03<00:16, 23.28it/s]
Testing:  17%|█▋        | 80/469 [00:03<00:16, 24.17it/s]
Testing:  18%|█▊        | 83/469 [00:03<00:16, 23.79it/s]
Testing:  18%|█▊        | 86/469 [00:03<00:15, 24.45it/s]
Testing:  19%|█▉        | 89/469 [00:03<00:15, 23.96it/s]
Testing:  20%|█▉        | 92/469 [00:03<00:15, 24.46it/s]
Testing:  20%|██        | 95/469 [00:04<00:14, 25.21it/s]
Testing:  21%|██        | 98/469 [00:04<00:15, 24.10it/s]
Testing:  22%|██▏       | 101/469 [00:04<00:15, 24.16it/s]
Testing:  22%|██▏       | 104/469 [00:04<00:14, 24.97it/s]
Testing:  23%|██▎       | 107/469 [00:04<00:14, 25.61it/s]
Testing:  23%|██▎       | 110/469 [00:04<00:14, 24.88it/s]
Testing:  24%|██▍       | 113/469 [00:04<00:14, 23.76it/s]
Testing:  25%|██▍       | 116/469 [00:04<00:15, 22.09it/s]
Testing:  25%|██▌       | 119/469 [00:05<00:15, 22.39it/s]
Testing:  26%|██▌       | 122/469 [00:05<00:15, 23.07it/s]
Testing:  27%|██▋       | 125/469 [00:05<00:14, 23.28it/s]
Testing:  27%|██▋       | 128/469 [00:05<00:14, 23.99it/s]
Testing:  28%|██▊       | 131/469 [00:05<00:13, 24.93it/s]
Testing:  29%|██▊       | 134/469 [00:05<00:13, 25.29it/s]
Testing:  29%|██▉       | 137/469 [00:05<00:13, 25.06it/s]
Testing:  30%|██▉       | 140/469 [00:05<00:12, 25.41it/s]
Testing:  30%|███       | 143/469 [00:05<00:12, 26.17it/s]
Testing:  31%|███       | 146/469 [00:06<00:12, 25.74it/s]
Testing:  32%|███▏      | 149/469 [00:06<00:12, 25.72it/s]
Testing:  32%|███▏      | 152/469 [00:06<00:12, 26.06it/s]
Testing:  33%|███▎      | 155/469 [00:06<00:11, 26.29it/s]
Testing:  34%|███▎      | 158/469 [00:06<00:12, 25.72it/s]
Testing:  34%|███▍      | 161/469 [00:06<00:11, 26.34it/s]
Testing:  35%|███▍      | 164/469 [00:06<00:11, 26.67it/s]
Testing:  36%|███▌      | 167/469 [00:06<00:11, 26.37it/s]
Testing:  36%|███▌      | 170/469 [00:07<00:11, 26.28it/s]
Testing:  37%|███▋      | 174/469 [00:07<00:10, 27.32it/s]
Testing:  38%|███▊      | 177/469 [00:07<00:10, 27.29it/s]
Testing:  38%|███▊      | 180/469 [00:07<00:10, 26.29it/s]
Testing:  39%|███▉      | 183/469 [00:07<00:10, 26.71it/s]
Testing:  40%|███▉      | 186/469 [00:07<00:11, 25.62it/s]
Testing:  40%|████      | 189/469 [00:07<00:10, 26.64it/s]
Testing:  41%|████      | 192/469 [00:07<00:10, 27.01it/s]
Testing:  42%|████▏     | 195/469 [00:07<00:10, 26.90it/s]
Testing:  42%|████▏     | 198/469 [00:08<00:10, 26.23it/s]
Testing:  43%|████▎     | 201/469 [00:08<00:10, 25.90it/s]
Testing:  43%|████▎     | 204/469 [00:08<00:10, 25.46it/s]
Testing:  44%|████▍     | 207/469 [00:08<00:09, 26.52it/s]
Testing:  45%|████▍     | 210/469 [00:08<00:09, 27.14it/s]
Testing:  45%|████▌     | 213/469 [00:08<00:09, 27.18it/s]
Testing:  46%|████▌     | 216/469 [00:08<00:09, 26.54it/s]
Testing:  47%|████▋     | 219/469 [00:08<00:09, 25.66it/s]
Testing:  47%|████▋     | 222/469 [00:09<00:09, 24.85it/s]
Testing:  48%|████▊     | 225/469 [00:09<00:09, 25.53it/s]
Testing:  49%|████▊     | 228/469 [00:09<00:09, 25.80it/s]
Testing:  49%|████▉     | 231/469 [00:09<00:09, 24.07it/s]
Testing:  50%|████▉     | 234/469 [00:09<00:09, 24.39it/s]
Testing:  51%|█████     | 238/469 [00:09<00:08, 25.92it/s]
Testing:  51%|█████▏    | 241/469 [00:09<00:08, 26.26it/s]
Testing:  52%|█████▏    | 244/469 [00:09<00:08, 25.64it/s]
Testing:  53%|█████▎    | 247/469 [00:09<00:08, 25.27it/s]
Testing:  53%|█████▎    | 250/469 [00:10<00:08, 24.40it/s]
Testing:  54%|█████▍    | 253/469 [00:10<00:08, 25.25it/s]
Testing:  55%|█████▍    | 256/469 [00:10<00:08, 25.48it/s]
Testing:  55%|█████▌    | 259/469 [00:10<00:08, 25.70it/s]
Testing:  56%|█████▌    | 262/469 [00:10<00:08, 25.56it/s]
Testing:  57%|█████▋    | 265/469 [00:10<00:08, 25.42it/s]
Testing:  57%|█████▋    | 269/469 [00:10<00:07, 26.24it/s]
Testing:  58%|█████▊    | 272/469 [00:10<00:07, 25.95it/s]
Testing:  59%|█████▊    | 275/469 [00:11<00:07, 25.95it/s]
Testing:  59%|█████▉    | 278/469 [00:11<00:07, 26.19it/s]
Testing:  60%|█████▉    | 281/469 [00:11<00:07, 26.42it/s]
Testing:  61%|██████    | 284/469 [00:11<00:07, 25.72it/s]
Testing:  61%|██████    | 287/469 [00:11<00:06, 26.62it/s]
Testing:  62%|██████▏   | 290/469 [00:11<00:06, 26.37it/s]
Testing:  62%|██████▏   | 293/469 [00:11<00:07, 24.64it/s]
Testing:  63%|██████▎   | 296/469 [00:11<00:06, 25.43it/s]
Testing:  64%|██████▍   | 299/469 [00:12<00:06, 25.34it/s]
Testing:  64%|██████▍   | 302/469 [00:12<00:06, 25.82it/s]
Testing:  65%|██████▌   | 305/469 [00:12<00:06, 25.98it/s]
Testing:  66%|██████▌   | 308/469 [00:12<00:06, 25.24it/s]
Testing:  66%|██████▋   | 311/469 [00:12<00:06, 25.10it/s]
Testing:  67%|██████▋   | 314/469 [00:12<00:06, 25.24it/s]
Testing:  68%|██████▊   | 317/469 [00:12<00:05, 25.40it/s]
Testing:  68%|██████▊   | 320/469 [00:12<00:05, 25.44it/s]
Testing:  69%|██████▉   | 323/469 [00:12<00:05, 25.53it/s]
Testing:  70%|██████▉   | 326/469 [00:13<00:05, 25.04it/s]
Testing:  70%|███████   | 329/469 [00:13<00:05, 25.18it/s]
Testing:  71%|███████   | 332/469 [00:13<00:05, 24.92it/s]
Testing:  71%|███████▏  | 335/469 [00:13<00:05, 25.19it/s]
Testing:  72%|███████▏  | 338/469 [00:13<00:05, 25.70it/s]
Testing:  73%|███████▎  | 341/469 [00:13<00:04, 26.05it/s]
Testing:  73%|███████▎  | 344/469 [00:13<00:04, 26.12it/s]
Testing:  74%|███████▍  | 347/469 [00:13<00:04, 25.36it/s]
Testing:  75%|███████▍  | 350/469 [00:14<00:04, 25.68it/s]
Testing:  75%|███████▌  | 353/469 [00:14<00:04, 25.87it/s]
Testing:  76%|███████▌  | 356/469 [00:14<00:04, 25.67it/s]
Testing:  77%|███████▋  | 359/469 [00:14<00:04, 26.33it/s]
Testing:  77%|███████▋  | 362/469 [00:14<00:03, 26.86it/s]
Testing:  78%|███████▊  | 365/469 [00:14<00:03, 26.74it/s]
Testing:  78%|███████▊  | 368/469 [00:14<00:03, 26.68it/s]
Testing:  79%|███████▉  | 371/469 [00:14<00:03, 26.65it/s]
Testing:  80%|███████▉  | 374/469 [00:14<00:03, 27.53it/s]
Testing:  80%|████████  | 377/469 [00:15<00:03, 26.46it/s]
Testing:  81%|████████  | 380/469 [00:15<00:03, 25.84it/s]
Testing:  82%|████████▏ | 383/469 [00:15<00:03, 26.19it/s]
Testing:  82%|████████▏ | 386/469 [00:15<00:03, 26.62it/s]
Testing:  83%|████████▎ | 389/469 [00:15<00:03, 26.10it/s]
Testing:  84%|████████▎ | 392/469 [00:15<00:03, 24.08it/s]
Testing:  84%|████████▍ | 395/469 [00:15<00:02, 24.67it/s]
Testing:  85%|████████▍ | 398/469 [00:15<00:02, 24.39it/s]
Testing:  86%|████████▌ | 401/469 [00:15<00:02, 24.06it/s]
Testing:  86%|████████▌ | 404/469 [00:16<00:02, 23.62it/s]
Testing:  87%|████████▋ | 407/469 [00:16<00:02, 24.57it/s]
Testing:  87%|████████▋ | 410/469 [00:16<00:02, 24.30it/s]
Testing:  88%|████████▊ | 413/469 [00:16<00:02, 24.59it/s]
Testing:  89%|████████▊ | 416/469 [00:16<00:02, 24.04it/s]
Testing:  89%|████████▉ | 419/469 [00:16<00:02, 23.79it/s]
Testing:  90%|████████▉ | 422/469 [00:16<00:01, 24.03it/s]
Testing:  91%|█████████ | 425/469 [00:16<00:01, 24.89it/s]
Testing:  91%|█████████▏| 428/469 [00:17<00:01, 24.87it/s]
Testing:  92%|█████████▏| 431/469 [00:17<00:01, 25.74it/s]
Testing:  93%|█████████▎| 434/469 [00:17<00:01, 26.62it/s]
Testing:  93%|█████████▎| 437/469 [00:17<00:01, 26.21it/s]
Testing:  94%|█████████▍| 440/469 [00:17<00:01, 26.33it/s]
Testing:  94%|█████████▍| 443/469 [00:17<00:00, 27.24it/s]
Testing:  95%|█████████▌| 446/469 [00:17<00:00, 27.37it/s]
Testing:  96%|█████████▌| 449/469 [00:17<00:00, 27.28it/s]
Testing:  96%|█████████▋| 452/469 [00:17<00:00, 26.25it/s]
Testing:  97%|█████████▋| 455/469 [00:18<00:00, 26.46it/s]
Testing:  98%|█████████▊| 458/469 [00:18<00:00, 25.91it/s]
Testing:  98%|█████████▊| 461/469 [00:18<00:00, 26.18it/s]
Testing:  99%|█████████▉| 464/469 [00:18<00:00, 25.51it/s]
Testing: 100%|█████████▉| 467/469 [00:18<00:00, 25.03it/s]--------------------------------------------------------------------------------
DATALOADER:0 TEST RESULTS
{'test_rmse': 0.5243797302246094}
--------------------------------------------------------------------------------

Testing: 100%|██████████| 469/469 [00:18<00:00, 25.16it/s]
  0%|          | 0/469 [02:58<?, ?it/s]
Global seed set to 46

['p_np'] False
2 1
iupac_vocab_size: 1491
training... 1491

  0%|          | 0/469 [00:00<?, ?it/s]Some weights of the model checkpoint at checkpoints/iupac were not used when initializing GPT2ForSequenceClassification: ['lm_head.weight']
- This IS expected if you are initializing GPT2ForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing GPT2ForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
GPU available: True, used: True
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]

  | Name        | Type                          | Params
--------------------------------------------------------------
0 | transformer | GPT2ForSequenceClassification | 7.1 M 
--------------------------------------------------------------
75.9 K    Trainable params
7.0 M     Non-trainable params
7.1 M     Total params
28.416    Total estimated model params size (MB)

Validation sanity check: 0it [00:00, ?it/s]
Validation sanity check:   0%|          | 0/2 [00:00<?, ?it/s]
Validation sanity check: 100%|██████████| 2/2 [00:00<00:00, 17.11it/s]
                                                                      Global seed set to 46


Training: 0it [00:00, ?it/s]
Training:   0%|          | 0/938 [00:00<?, ?it/s]
Epoch 0:   0%|          | 0/938 [00:00<?, ?it/s] 
Epoch 0:   0%|          | 1/938 [00:00<01:37,  9.61it/s]
Epoch 0:   0%|          | 1/938 [00:00<01:37,  9.58it/s, loss=3.71, v_num=11]
Epoch 0:   0%|          | 2/938 [00:00<01:24, 11.08it/s, loss=3.52, v_num=11]
Epoch 0:   0%|          | 3/938 [00:00<01:15, 12.33it/s, loss=3.52, v_num=11]
Epoch 0:   0%|          | 3/938 [00:00<01:15, 12.31it/s, loss=3.59, v_num=11]
Epoch 0:   0%|          | 4/938 [00:00<01:14, 12.57it/s, loss=3.64, v_num=11]
Epoch 0:   1%|          | 5/938 [00:00<01:12, 12.94it/s, loss=3.64, v_num=11]
Epoch 0:   1%|          | 5/938 [00:00<01:12, 12.92it/s, loss=3.68, v_num=11]
Epoch 0:   1%|          | 6/938 [00:00<01:09, 13.39it/s, loss=3.66, v_num=11]
Epoch 0:   1%|          | 7/938 [00:00<01:08, 13.61it/s, loss=3.66, v_num=11]
Epoch 0:   1%|          | 7/938 [00:00<01:08, 13.60it/s, loss=3.62, v_num=11]
Epoch 0:   1%|          | 8/938 [00:00<01:10, 13.27it/s, loss=3.6, v_num=11] 
Epoch 0:   1%|          | 9/938 [00:00<01:08, 13.50it/s, loss=3.6, v_num=11]
Epoch 0:   1%|          | 9/938 [00:00<01:08, 13.49it/s, loss=3.59, v_num=11]
Epoch 0:   1%|          | 10/938 [00:00<01:10, 13.13it/s, loss=3.56, v_num=11]
Epoch 0:   1%|          | 11/938 [00:00<01:09, 13.29it/s, loss=3.56, v_num=11]
Epoch 0:   1%|          | 11/938 [00:00<01:09, 13.28it/s, loss=3.53, v_num=11]
Epoch 0:   1%|▏         | 12/938 [00:00<01:07, 13.69it/s, loss=3.49, v_num=11]
Epoch 0:   1%|▏         | 13/938 [00:00<01:06, 13.84it/s, loss=3.49, v_num=11]
Epoch 0:   1%|▏         | 13/938 [00:00<01:06, 13.84it/s, loss=3.51, v_num=11]
Epoch 0:   1%|▏         | 14/938 [00:00<01:05, 14.02it/s, loss=3.48, v_num=11]
Epoch 0:   2%|▏         | 15/938 [00:01<01:05, 14.18it/s, loss=3.48, v_num=11]
Epoch 0:   2%|▏         | 15/938 [00:01<01:05, 14.18it/s, loss=3.47, v_num=11]
Epoch 0:   2%|▏         | 16/938 [00:01<01:05, 13.99it/s, loss=3.46, v_num=11]
Epoch 0:   2%|▏         | 17/938 [00:01<01:05, 14.03it/s, loss=3.46, v_num=11]
Epoch 0:   2%|▏         | 17/938 [00:01<01:05, 14.02it/s, loss=3.44, v_num=11]
Epoch 0:   2%|▏         | 18/938 [00:01<01:05, 14.05it/s, loss=3.41, v_num=11]
Epoch 0:   2%|▏         | 19/938 [00:01<01:05, 14.00it/s, loss=3.41, v_num=11]
Epoch 0:   2%|▏         | 19/938 [00:01<01:05, 14.00it/s, loss=3.41, v_num=11]
Epoch 0:   2%|▏         | 20/938 [00:01<01:05, 14.05it/s, loss=3.38, v_num=11]
Epoch 0:   2%|▏         | 21/938 [00:01<01:04, 14.17it/s, loss=3.38, v_num=11]
Epoch 0:   2%|▏         | 21/938 [00:01<01:04, 14.17it/s, loss=3.37, v_num=11]
Epoch 0:   2%|▏         | 22/938 [00:01<01:04, 14.19it/s, loss=3.34, v_num=11]
Epoch 0:   2%|▏         | 23/938 [00:01<01:04, 14.14it/s, loss=3.34, v_num=11]
Epoch 0:   2%|▏         | 23/938 [00:01<01:04, 14.13it/s, loss=3.3, v_num=11] 
Epoch 0:   3%|▎         | 24/938 [00:01<01:04, 14.25it/s, loss=3.26, v_num=11]
Epoch 0:   3%|▎         | 25/938 [00:01<01:04, 14.18it/s, loss=3.26, v_num=11]
Epoch 0:   3%|▎         | 25/938 [00:01<01:04, 14.18it/s, loss=3.19, v_num=11]
Epoch 0:   3%|▎         | 26/938 [00:01<01:04, 14.21it/s, loss=3.13, v_num=11]
Epoch 0:   3%|▎         | 27/938 [00:01<01:03, 14.28it/s, loss=3.13, v_num=11]
Epoch 0:   3%|▎         | 27/938 [00:01<01:03, 14.27it/s, loss=3.1, v_num=11] 
Epoch 0:   3%|▎         | 28/938 [00:01<01:03, 14.31it/s, loss=3.05, v_num=11]
Epoch 0:   3%|▎         | 29/938 [00:02<01:03, 14.29it/s, loss=3.05, v_num=11]
Epoch 0:   3%|▎         | 29/938 [00:02<01:03, 14.29it/s, loss=2.99, v_num=11]
Epoch 0:   3%|▎         | 30/938 [00:02<01:03, 14.41it/s, loss=2.95, v_num=11]
Epoch 0:   3%|▎         | 31/938 [00:02<01:03, 14.37it/s, loss=2.95, v_num=11]
Epoch 0:   3%|▎         | 31/938 [00:02<01:03, 14.36it/s, loss=2.91, v_num=11]
Epoch 0:   3%|▎         | 32/938 [00:02<01:02, 14.42it/s, loss=2.86, v_num=11]
Epoch 0:   4%|▎         | 33/938 [00:02<01:02, 14.50it/s, loss=2.86, v_num=11]
Epoch 0:   4%|▎         | 33/938 [00:02<01:02, 14.50it/s, loss=2.79, v_num=11]
Epoch 0:   4%|▎         | 34/938 [00:02<01:02, 14.47it/s, loss=2.74, v_num=11]
Epoch 0:   4%|▎         | 35/938 [00:02<01:02, 14.47it/s, loss=2.74, v_num=11]
Epoch 0:   4%|▎         | 35/938 [00:02<01:02, 14.47it/s, loss=2.67, v_num=11]
Epoch 0:   4%|▍         | 36/938 [00:02<01:02, 14.49it/s, loss=2.6, v_num=11] 
Epoch 0:   4%|▍         | 37/938 [00:02<01:02, 14.51it/s, loss=2.6, v_num=11]
Epoch 0:   4%|▍         | 37/938 [00:02<01:02, 14.51it/s, loss=2.53, v_num=11]
Epoch 0:   4%|▍         | 38/938 [00:02<01:01, 14.53it/s, loss=2.47, v_num=11]
Epoch 0:   4%|▍         | 39/938 [00:02<01:01, 14.52it/s, loss=2.47, v_num=11]
Epoch 0:   4%|▍         | 39/938 [00:02<01:01, 14.52it/s, loss=2.4, v_num=11] 
Epoch 0:   4%|▍         | 40/938 [00:02<01:01, 14.56it/s, loss=2.33, v_num=11]
Epoch 0:   4%|▍         | 41/938 [00:02<01:01, 14.61it/s, loss=2.33, v_num=11]
Epoch 0:   4%|▍         | 41/938 [00:02<01:01, 14.60it/s, loss=2.25, v_num=11]
Epoch 0:   4%|▍         | 42/938 [00:02<01:02, 14.39it/s, loss=2.19, v_num=11]
Epoch 0:   5%|▍         | 43/938 [00:02<01:02, 14.39it/s, loss=2.19, v_num=11]
Epoch 0:   5%|▍         | 43/938 [00:02<01:02, 14.39it/s, loss=2.12, v_num=11]
Epoch 0:   5%|▍         | 44/938 [00:03<01:02, 14.39it/s, loss=2.05, v_num=11]
Epoch 0:   5%|▍         | 45/938 [00:03<01:01, 14.46it/s, loss=2.05, v_num=11]
Epoch 0:   5%|▍         | 45/938 [00:03<01:01, 14.46it/s, loss=2.01, v_num=11]
Epoch 0:   5%|▍         | 46/938 [00:03<01:01, 14.43it/s, loss=1.99, v_num=11]
Epoch 0:   5%|▌         | 47/938 [00:03<01:01, 14.47it/s, loss=1.99, v_num=11]
Epoch 0:   5%|▌         | 47/938 [00:03<01:01, 14.47it/s, loss=1.95, v_num=11]
Epoch 0:   5%|▌         | 48/938 [00:03<01:01, 14.52it/s, loss=1.92, v_num=11]
Epoch 0:   5%|▌         | 49/938 [00:03<01:02, 14.23it/s, loss=1.92, v_num=11]
Epoch 0:   5%|▌         | 49/938 [00:03<01:02, 14.22it/s, loss=1.88, v_num=11]
Epoch 0:   5%|▌         | 50/938 [00:03<01:02, 14.21it/s, loss=1.85, v_num=11]
Epoch 0:   5%|▌         | 51/938 [00:03<01:02, 14.18it/s, loss=1.85, v_num=11]
Epoch 0:   5%|▌         | 51/938 [00:03<01:02, 14.18it/s, loss=1.81, v_num=11]
Epoch 0:   6%|▌         | 52/938 [00:03<01:02, 14.21it/s, loss=1.79, v_num=11]
Epoch 0:   6%|▌         | 53/938 [00:03<01:02, 14.22it/s, loss=1.79, v_num=11]
Epoch 0:   6%|▌         | 53/938 [00:03<01:02, 14.22it/s, loss=1.76, v_num=11]
Epoch 0:   6%|▌         | 54/938 [00:03<01:02, 14.24it/s, loss=1.75, v_num=11]
Epoch 0:   6%|▌         | 55/938 [00:03<01:01, 14.28it/s, loss=1.75, v_num=11]
Epoch 0:   6%|▌         | 55/938 [00:03<01:01, 14.28it/s, loss=1.74, v_num=11]
Epoch 0:   6%|▌         | 56/938 [00:03<01:01, 14.25it/s, loss=1.73, v_num=11]
Epoch 0:   6%|▌         | 57/938 [00:04<01:01, 14.24it/s, loss=1.73, v_num=11]
Epoch 0:   6%|▌         | 57/938 [00:04<01:01, 14.24it/s, loss=1.74, v_num=11]
Epoch 0:   6%|▌         | 58/938 [00:04<01:01, 14.24it/s, loss=1.74, v_num=11]
Epoch 0:   6%|▋         | 59/938 [00:04<01:01, 14.29it/s, loss=1.74, v_num=11]
Epoch 0:   6%|▋         | 59/938 [00:04<01:01, 14.29it/s, loss=1.71, v_num=11]
Epoch 0:   6%|▋         | 60/938 [00:04<01:01, 14.23it/s, loss=1.71, v_num=11]
Epoch 0:   7%|▋         | 61/938 [00:04<01:01, 14.23it/s, loss=1.71, v_num=11]
Epoch 0:   7%|▋         | 61/938 [00:04<01:01, 14.23it/s, loss=1.7, v_num=11] 
Epoch 0:   7%|▋         | 62/938 [00:04<01:01, 14.20it/s, loss=1.7, v_num=11]
Epoch 0:   7%|▋         | 63/938 [00:04<01:01, 14.20it/s, loss=1.7, v_num=11]
Epoch 0:   7%|▋         | 63/938 [00:04<01:01, 14.19it/s, loss=1.69, v_num=11]
Epoch 0:   7%|▋         | 64/938 [00:04<01:01, 14.22it/s, loss=1.7, v_num=11] 
Epoch 0:   7%|▋         | 65/938 [00:04<01:01, 14.26it/s, loss=1.7, v_num=11]
Epoch 0:   7%|▋         | 65/938 [00:04<01:01, 14.26it/s, loss=1.69, v_num=11]
Epoch 0:   7%|▋         | 66/938 [00:04<01:01, 14.29it/s, loss=1.68, v_num=11]
Epoch 0:   7%|▋         | 67/938 [00:04<01:01, 14.27it/s, loss=1.68, v_num=11]
Epoch 0:   7%|▋         | 67/938 [00:04<01:01, 14.26it/s, loss=1.66, v_num=11]
Epoch 0:   7%|▋         | 68/938 [00:04<01:00, 14.30it/s, loss=1.65, v_num=11]
Epoch 0:   7%|▋         | 69/938 [00:04<01:00, 14.28it/s, loss=1.65, v_num=11]
Epoch 0:   7%|▋         | 69/938 [00:04<01:00, 14.28it/s, loss=1.65, v_num=11]
Epoch 0:   7%|▋         | 70/938 [00:04<01:00, 14.30it/s, loss=1.64, v_num=11]
Epoch 0:   8%|▊         | 71/938 [00:04<01:00, 14.33it/s, loss=1.64, v_num=11]
Epoch 0:   8%|▊         | 71/938 [00:04<01:00, 14.33it/s, loss=1.64, v_num=11]
Epoch 0:   8%|▊         | 72/938 [00:05<01:00, 14.36it/s, loss=1.62, v_num=11]
Epoch 0:   8%|▊         | 73/938 [00:05<01:00, 14.35it/s, loss=1.62, v_num=11]
Epoch 0:   8%|▊         | 73/938 [00:05<01:00, 14.34it/s, loss=1.61, v_num=11]
Epoch 0:   8%|▊         | 74/938 [00:05<01:00, 14.36it/s, loss=1.61, v_num=11]
Epoch 0:   8%|▊         | 75/938 [00:05<01:00, 14.32it/s, loss=1.61, v_num=11]
Epoch 0:   8%|▊         | 75/938 [00:05<01:00, 14.32it/s, loss=1.61, v_num=11]
Epoch 0:   8%|▊         | 76/938 [00:05<01:00, 14.31it/s, loss=1.6, v_num=11] 
Epoch 0:   8%|▊         | 77/938 [00:05<01:00, 14.34it/s, loss=1.6, v_num=11]
Epoch 0:   8%|▊         | 77/938 [00:05<01:00, 14.34it/s, loss=1.6, v_num=11]
Epoch 0:   8%|▊         | 78/938 [00:05<00:59, 14.35it/s, loss=1.6, v_num=11]
Epoch 0:   8%|▊         | 79/938 [00:05<00:59, 14.35it/s, loss=1.6, v_num=11]
Epoch 0:   8%|▊         | 79/938 [00:05<00:59, 14.35it/s, loss=1.6, v_num=11]
Epoch 0:   9%|▊         | 80/938 [00:05<00:59, 14.40it/s, loss=1.61, v_num=11]
Epoch 0:   9%|▊         | 81/938 [00:05<00:59, 14.38it/s, loss=1.61, v_num=11]
Epoch 0:   9%|▊         | 81/938 [00:05<00:59, 14.37it/s, loss=1.61, v_num=11]
Epoch 0:   9%|▊         | 82/938 [00:05<00:59, 14.38it/s, loss=1.62, v_num=11]
Epoch 0:   9%|▉         | 83/938 [00:05<00:59, 14.39it/s, loss=1.62, v_num=11]
Epoch 0:   9%|▉         | 83/938 [00:05<00:59, 14.39it/s, loss=1.62, v_num=11]
Epoch 0:   9%|▉         | 84/938 [00:05<00:59, 14.39it/s, loss=1.61, v_num=11]
Epoch 0:   9%|▉         | 85/938 [00:05<00:59, 14.35it/s, loss=1.61, v_num=11]
Epoch 0:   9%|▉         | 85/938 [00:05<00:59, 14.35it/s, loss=1.63, v_num=11]
Epoch 0:   9%|▉         | 86/938 [00:05<00:59, 14.40it/s, loss=1.63, v_num=11]
Epoch 0:   9%|▉         | 87/938 [00:06<00:59, 14.42it/s, loss=1.63, v_num=11]
Epoch 0:   9%|▉         | 87/938 [00:06<00:59, 14.42it/s, loss=1.64, v_num=11]
Epoch 0:   9%|▉         | 88/938 [00:06<00:58, 14.44it/s, loss=1.64, v_num=11]
Epoch 0:   9%|▉         | 89/938 [00:06<00:58, 14.40it/s, loss=1.64, v_num=11]
Epoch 0:   9%|▉         | 89/938 [00:06<00:58, 14.40it/s, loss=1.64, v_num=11]
Epoch 0:  10%|▉         | 90/938 [00:06<00:58, 14.41it/s, loss=1.67, v_num=11]
Epoch 0:  10%|▉         | 91/938 [00:06<00:58, 14.40it/s, loss=1.67, v_num=11]
Epoch 0:  10%|▉         | 91/938 [00:06<00:58, 14.40it/s, loss=1.66, v_num=11]
Epoch 0:  10%|▉         | 92/938 [00:06<00:58, 14.41it/s, loss=1.66, v_num=11]
Epoch 0:  10%|▉         | 93/938 [00:06<00:58, 14.43it/s, loss=1.66, v_num=11]
Epoch 0:  10%|▉         | 93/938 [00:06<00:58, 14.43it/s, loss=1.65, v_num=11]
Epoch 0:  10%|█         | 94/938 [00:06<00:58, 14.44it/s, loss=1.64, v_num=11]
Epoch 0:  10%|█         | 95/938 [00:06<00:58, 14.42it/s, loss=1.64, v_num=11]
Epoch 0:  10%|█         | 95/938 [00:06<00:58, 14.42it/s, loss=1.64, v_num=11]
Epoch 0:  10%|█         | 96/938 [00:06<00:58, 14.42it/s, loss=1.66, v_num=11]
Epoch 0:  10%|█         | 97/938 [00:06<00:58, 14.42it/s, loss=1.66, v_num=11]
Epoch 0:  10%|█         | 97/938 [00:06<00:58, 14.42it/s, loss=1.65, v_num=11]
Epoch 0:  10%|█         | 98/938 [00:06<00:58, 14.37it/s, loss=1.65, v_num=11]
Epoch 0:  11%|█         | 99/938 [00:06<00:58, 14.35it/s, loss=1.65, v_num=11]
Epoch 0:  11%|█         | 99/938 [00:06<00:58, 14.35it/s, loss=1.67, v_num=11]
Epoch 0:  11%|█         | 100/938 [00:06<00:58, 14.37it/s, loss=1.66, v_num=11]
Epoch 0:  11%|█         | 101/938 [00:07<00:58, 14.38it/s, loss=1.66, v_num=11]
Epoch 0:  11%|█         | 101/938 [00:07<00:58, 14.38it/s, loss=1.67, v_num=11]
Epoch 0:  11%|█         | 102/938 [00:07<00:58, 14.39it/s, loss=1.66, v_num=11]
Epoch 0:  11%|█         | 103/938 [00:07<00:58, 14.38it/s, loss=1.66, v_num=11]
Epoch 0:  11%|█         | 103/938 [00:07<00:58, 14.38it/s, loss=1.67, v_num=11]
Epoch 0:  11%|█         | 104/938 [00:07<00:57, 14.41it/s, loss=1.67, v_num=11]
Epoch 0:  11%|█         | 105/938 [00:07<00:57, 14.41it/s, loss=1.67, v_num=11]
Epoch 0:  11%|█         | 105/938 [00:07<00:57, 14.41it/s, loss=1.65, v_num=11]
Epoch 0:  11%|█▏        | 106/938 [00:07<00:57, 14.41it/s, loss=1.66, v_num=11]
Epoch 0:  11%|█▏        | 107/938 [00:07<00:57, 14.38it/s, loss=1.66, v_num=11]
Epoch 0:  11%|█▏        | 107/938 [00:07<00:57, 14.38it/s, loss=1.65, v_num=11]
Epoch 0:  12%|█▏        | 108/938 [00:07<00:57, 14.36it/s, loss=1.65, v_num=11]
Epoch 0:  12%|█▏        | 109/938 [00:07<00:57, 14.37it/s, loss=1.65, v_num=11]
Epoch 0:  12%|█▏        | 109/938 [00:07<00:57, 14.37it/s, loss=1.64, v_num=11]
Epoch 0:  12%|█▏        | 110/938 [00:07<00:57, 14.34it/s, loss=1.64, v_num=11]
Epoch 0:  12%|█▏        | 111/938 [00:07<00:57, 14.35it/s, loss=1.64, v_num=11]
Epoch 0:  12%|█▏        | 111/938 [00:07<00:57, 14.34it/s, loss=1.64, v_num=11]
Epoch 0:  12%|█▏        | 112/938 [00:07<00:57, 14.36it/s, loss=1.66, v_num=11]
Epoch 0:  12%|█▏        | 113/938 [00:07<00:57, 14.38it/s, loss=1.66, v_num=11]
Epoch 0:  12%|█▏        | 113/938 [00:07<00:57, 14.38it/s, loss=1.66, v_num=11]
Epoch 0:  12%|█▏        | 114/938 [00:07<00:57, 14.35it/s, loss=1.67, v_num=11]
Epoch 0:  12%|█▏        | 115/938 [00:08<00:57, 14.37it/s, loss=1.67, v_num=11]
Epoch 0:  12%|█▏        | 115/938 [00:08<00:57, 14.37it/s, loss=1.66, v_num=11]
Epoch 0:  12%|█▏        | 116/938 [00:08<00:57, 14.39it/s, loss=1.65, v_num=11]
Epoch 0:  12%|█▏        | 117/938 [00:08<00:57, 14.40it/s, loss=1.65, v_num=11]
Epoch 0:  12%|█▏        | 117/938 [00:08<00:57, 14.40it/s, loss=1.62, v_num=11]
Epoch 0:  13%|█▎        | 118/938 [00:08<00:56, 14.41it/s, loss=1.61, v_num=11]
Epoch 0:  13%|█▎        | 119/938 [00:08<00:56, 14.38it/s, loss=1.61, v_num=11]
Epoch 0:  13%|█▎        | 119/938 [00:08<00:56, 14.38it/s, loss=1.59, v_num=11]
Epoch 0:  13%|█▎        | 120/938 [00:08<00:56, 14.38it/s, loss=1.59, v_num=11]
Epoch 0:  13%|█▎        | 121/938 [00:08<00:56, 14.40it/s, loss=1.59, v_num=11]
Epoch 0:  13%|█▎        | 121/938 [00:08<00:56, 14.40it/s, loss=1.57, v_num=11]
Epoch 0:  13%|█▎        | 122/938 [00:08<00:56, 14.41it/s, loss=1.56, v_num=11]
Epoch 0:  13%|█▎        | 123/938 [00:08<00:56, 14.42it/s, loss=1.56, v_num=11]
Epoch 0:  13%|█▎        | 123/938 [00:08<00:56, 14.41it/s, loss=1.56, v_num=11]
Epoch 0:  13%|█▎        | 124/938 [00:08<00:56, 14.43it/s, loss=1.54, v_num=11]
Epoch 0:  13%|█▎        | 125/938 [00:08<00:56, 14.44it/s, loss=1.54, v_num=11]
Epoch 0:  13%|█▎        | 125/938 [00:08<00:56, 14.44it/s, loss=1.52, v_num=11]
Epoch 0:  13%|█▎        | 126/938 [00:08<00:56, 14.45it/s, loss=1.5, v_num=11] 
Epoch 0:  14%|█▎        | 127/938 [00:08<00:56, 14.46it/s, loss=1.5, v_num=11]
Epoch 0:  14%|█▎        | 127/938 [00:08<00:56, 14.45it/s, loss=1.49, v_num=11]
Epoch 0:  14%|█▎        | 128/938 [00:08<00:56, 14.44it/s, loss=1.49, v_num=11]
Epoch 0:  14%|█▍        | 129/938 [00:08<00:56, 14.42it/s, loss=1.49, v_num=11]
Epoch 0:  14%|█▍        | 129/938 [00:08<00:56, 14.42it/s, loss=1.47, v_num=11]
Epoch 0:  14%|█▍        | 130/938 [00:09<00:56, 14.40it/s, loss=1.43, v_num=11]
Epoch 0:  14%|█▍        | 131/938 [00:09<00:56, 14.39it/s, loss=1.43, v_num=11]
Epoch 0:  14%|█▍        | 131/938 [00:09<00:56, 14.39it/s, loss=1.41, v_num=11]
Epoch 0:  14%|█▍        | 132/938 [00:09<00:56, 14.39it/s, loss=1.37, v_num=11]
Epoch 0:  14%|█▍        | 133/938 [00:09<00:56, 14.36it/s, loss=1.37, v_num=11]
Epoch 0:  14%|█▍        | 133/938 [00:09<00:56, 14.36it/s, loss=1.36, v_num=11]
Epoch 0:  14%|█▍        | 134/938 [00:09<00:55, 14.37it/s, loss=1.36, v_num=11]
Epoch 0:  14%|█▍        | 135/938 [00:09<00:55, 14.39it/s, loss=1.36, v_num=11]
Epoch 0:  14%|█▍        | 135/938 [00:09<00:55, 14.39it/s, loss=1.35, v_num=11]
Epoch 0:  14%|█▍        | 136/938 [00:09<00:55, 14.40it/s, loss=1.31, v_num=11]
Epoch 0:  15%|█▍        | 137/938 [00:09<00:55, 14.41it/s, loss=1.31, v_num=11]
Epoch 0:  15%|█▍        | 137/938 [00:09<00:55, 14.41it/s, loss=1.31, v_num=11]
Epoch 0:  15%|█▍        | 138/938 [00:09<00:55, 14.39it/s, loss=1.3, v_num=11] 
Epoch 0:  15%|█▍        | 139/938 [00:09<00:55, 14.40it/s, loss=1.3, v_num=11]
Epoch 0:  15%|█▍        | 139/938 [00:09<00:55, 14.40it/s, loss=1.29, v_num=11]
Epoch 0:  15%|█▍        | 140/938 [00:09<00:55, 14.40it/s, loss=1.27, v_num=11]
Epoch 0:  15%|█▌        | 141/938 [00:09<00:55, 14.41it/s, loss=1.27, v_num=11]
Epoch 0:  15%|█▌        | 141/938 [00:09<00:55, 14.41it/s, loss=1.25, v_num=11]
Epoch 0:  15%|█▌        | 142/938 [00:09<00:55, 14.42it/s, loss=1.23, v_num=11]
Epoch 0:  15%|█▌        | 143/938 [00:09<00:55, 14.43it/s, loss=1.23, v_num=11]
Epoch 0:  15%|█▌        | 143/938 [00:09<00:55, 14.43it/s, loss=1.22, v_num=11]
Epoch 0:  15%|█▌        | 144/938 [00:09<00:55, 14.42it/s, loss=1.21, v_num=11]
Epoch 0:  15%|█▌        | 145/938 [00:10<00:54, 14.43it/s, loss=1.21, v_num=11]
Epoch 0:  15%|█▌        | 145/938 [00:10<00:54, 14.43it/s, loss=1.21, v_num=11]
Epoch 0:  16%|█▌        | 146/938 [00:10<00:54, 14.40it/s, loss=1.19, v_num=11]
Epoch 0:  16%|█▌        | 147/938 [00:10<00:54, 14.42it/s, loss=1.19, v_num=11]
Epoch 0:  16%|█▌        | 147/938 [00:10<00:54, 14.42it/s, loss=1.18, v_num=11]
Epoch 0:  16%|█▌        | 148/938 [00:10<00:54, 14.39it/s, loss=1.16, v_num=11]
Epoch 0:  16%|█▌        | 149/938 [00:10<00:54, 14.38it/s, loss=1.16, v_num=11]
Epoch 0:  16%|█▌        | 149/938 [00:10<00:54, 14.38it/s, loss=1.17, v_num=11]
Epoch 0:  16%|█▌        | 150/938 [00:10<00:54, 14.39it/s, loss=1.18, v_num=11]
Epoch 0:  16%|█▌        | 151/938 [00:10<00:54, 14.39it/s, loss=1.18, v_num=11]
Epoch 0:  16%|█▌        | 151/938 [00:10<00:54, 14.39it/s, loss=1.19, v_num=11]
Epoch 0:  16%|█▌        | 152/938 [00:10<00:54, 14.35it/s, loss=1.19, v_num=11]
Epoch 0:  16%|█▋        | 153/938 [00:10<00:54, 14.32it/s, loss=1.19, v_num=11]
Epoch 0:  16%|█▋        | 153/938 [00:10<00:54, 14.32it/s, loss=1.18, v_num=11]
Epoch 0:  16%|█▋        | 154/938 [00:10<00:54, 14.33it/s, loss=1.17, v_num=11]
Epoch 0:  17%|█▋        | 155/938 [00:10<00:54, 14.34it/s, loss=1.17, v_num=11]
Epoch 0:  17%|█▋        | 155/938 [00:10<00:54, 14.34it/s, loss=1.16, v_num=11]
Epoch 0:  17%|█▋        | 156/938 [00:10<00:54, 14.33it/s, loss=1.15, v_num=11]
Epoch 0:  17%|█▋        | 157/938 [00:10<00:54, 14.33it/s, loss=1.15, v_num=11]
Epoch 0:  17%|█▋        | 157/938 [00:10<00:54, 14.33it/s, loss=1.14, v_num=11]
Epoch 0:  17%|█▋        | 158/938 [00:11<00:54, 14.34it/s, loss=1.12, v_num=11]
Epoch 0:  17%|█▋        | 159/938 [00:11<00:54, 14.35it/s, loss=1.12, v_num=11]
Epoch 0:  17%|█▋        | 159/938 [00:11<00:54, 14.35it/s, loss=1.11, v_num=11]
Epoch 0:  17%|█▋        | 160/938 [00:11<00:54, 14.33it/s, loss=1.12, v_num=11]
Epoch 0:  17%|█▋        | 161/938 [00:11<00:54, 14.34it/s, loss=1.12, v_num=11]
Epoch 0:  17%|█▋        | 161/938 [00:11<00:54, 14.34it/s, loss=1.12, v_num=11]
Epoch 0:  17%|█▋        | 162/938 [00:11<00:54, 14.34it/s, loss=1.13, v_num=11]
Epoch 0:  17%|█▋        | 163/938 [00:11<00:54, 14.34it/s, loss=1.13, v_num=11]
Epoch 0:  17%|█▋        | 163/938 [00:11<00:54, 14.34it/s, loss=1.12, v_num=11]
Epoch 0:  17%|█▋        | 164/938 [00:11<00:53, 14.35it/s, loss=1.12, v_num=11]
Epoch 0:  18%|█▊        | 165/938 [00:11<00:53, 14.36it/s, loss=1.12, v_num=11]
Epoch 0:  18%|█▊        | 165/938 [00:11<00:53, 14.36it/s, loss=1.13, v_num=11]
Epoch 0:  18%|█▊        | 166/938 [00:11<00:53, 14.34it/s, loss=1.12, v_num=11]
Epoch 0:  18%|█▊        | 167/938 [00:11<00:53, 14.34it/s, loss=1.12, v_num=11]
Epoch 0:  18%|█▊        | 167/938 [00:11<00:53, 14.34it/s, loss=1.12, v_num=11]
Epoch 0:  18%|█▊        | 168/938 [00:11<00:53, 14.34it/s, loss=1.13, v_num=11]
Epoch 0:  18%|█▊        | 169/938 [00:11<00:53, 14.36it/s, loss=1.13, v_num=11]
Epoch 0:  18%|█▊        | 169/938 [00:11<00:53, 14.36it/s, loss=1.11, v_num=11]
Epoch 0:  18%|█▊        | 170/938 [00:11<00:53, 14.36it/s, loss=1.09, v_num=11]
Epoch 0:  18%|█▊        | 171/938 [00:11<00:53, 14.36it/s, loss=1.09, v_num=11]
Epoch 0:  18%|█▊        | 171/938 [00:11<00:53, 14.36it/s, loss=1.08, v_num=11]
Epoch 0:  18%|█▊        | 172/938 [00:11<00:53, 14.36it/s, loss=1.08, v_num=11]
Epoch 0:  18%|█▊        | 173/938 [00:12<00:53, 14.37it/s, loss=1.08, v_num=11]
Epoch 0:  18%|█▊        | 173/938 [00:12<00:53, 14.37it/s, loss=1.08, v_num=11]
Epoch 0:  19%|█▊        | 174/938 [00:12<00:53, 14.36it/s, loss=1.07, v_num=11]
Epoch 0:  19%|█▊        | 175/938 [00:12<00:53, 14.37it/s, loss=1.07, v_num=11]
Epoch 0:  19%|█▊        | 175/938 [00:12<00:53, 14.37it/s, loss=1.08, v_num=11]
Epoch 0:  19%|█▉        | 176/938 [00:12<00:53, 14.37it/s, loss=1.08, v_num=11]
Epoch 0:  19%|█▉        | 177/938 [00:12<00:52, 14.37it/s, loss=1.08, v_num=11]
Epoch 0:  19%|█▉        | 177/938 [00:12<00:52, 14.37it/s, loss=1.09, v_num=11]
Epoch 0:  19%|█▉        | 178/938 [00:12<00:52, 14.36it/s, loss=1.1, v_num=11] 
Epoch 0:  19%|█▉        | 179/938 [00:12<00:52, 14.38it/s, loss=1.1, v_num=11]
Epoch 0:  19%|█▉        | 179/938 [00:12<00:52, 14.38it/s, loss=1.1, v_num=11]
Epoch 0:  19%|█▉        | 180/938 [00:12<00:52, 14.38it/s, loss=1.09, v_num=11]
Epoch 0:  19%|█▉        | 181/938 [00:12<00:52, 14.39it/s, loss=1.09, v_num=11]
Epoch 0:  19%|█▉        | 181/938 [00:12<00:52, 14.39it/s, loss=1.1, v_num=11] 
Epoch 0:  19%|█▉        | 182/938 [00:12<00:52, 14.40it/s, loss=1.09, v_num=11]
Epoch 0:  20%|█▉        | 183/938 [00:12<00:52, 14.42it/s, loss=1.09, v_num=11]
Epoch 0:  20%|█▉        | 183/938 [00:12<00:52, 14.41it/s, loss=1.09, v_num=11]
Epoch 0:  20%|█▉        | 184/938 [00:12<00:52, 14.40it/s, loss=1.09, v_num=11]
Epoch 0:  20%|█▉        | 185/938 [00:12<00:52, 14.42it/s, loss=1.09, v_num=11]
Epoch 0:  20%|█▉        | 185/938 [00:12<00:52, 14.42it/s, loss=1.07, v_num=11]
Epoch 0:  20%|█▉        | 186/938 [00:12<00:52, 14.42it/s, loss=1.06, v_num=11]
Epoch 0:  20%|█▉        | 187/938 [00:12<00:52, 14.42it/s, loss=1.06, v_num=11]
Epoch 0:  20%|█▉        | 187/938 [00:12<00:52, 14.42it/s, loss=1.05, v_num=11]
Epoch 0:  20%|██        | 188/938 [00:13<00:51, 14.42it/s, loss=1.04, v_num=11]
Epoch 0:  20%|██        | 189/938 [00:13<00:51, 14.42it/s, loss=1.04, v_num=11]
Epoch 0:  20%|██        | 189/938 [00:13<00:51, 14.42it/s, loss=1.02, v_num=11]
Epoch 0:  20%|██        | 190/938 [00:13<00:51, 14.41it/s, loss=1.03, v_num=11]
Epoch 0:  20%|██        | 191/938 [00:13<00:51, 14.43it/s, loss=1.03, v_num=11]
Epoch 0:  20%|██        | 191/938 [00:13<00:51, 14.43it/s, loss=1.02, v_num=11]
Epoch 0:  20%|██        | 192/938 [00:13<00:51, 14.42it/s, loss=1.01, v_num=11]
Epoch 0:  21%|██        | 193/938 [00:13<00:51, 14.43it/s, loss=1.01, v_num=11]
Epoch 0:  21%|██        | 193/938 [00:13<00:51, 14.43it/s, loss=1.01, v_num=11]
Epoch 0:  21%|██        | 194/938 [00:13<00:51, 14.44it/s, loss=1.02, v_num=11]
Epoch 0:  21%|██        | 195/938 [00:13<00:51, 14.43it/s, loss=1.02, v_num=11]
Epoch 0:  21%|██        | 195/938 [00:13<00:51, 14.43it/s, loss=1, v_num=11]   
Epoch 0:  21%|██        | 196/938 [00:13<00:51, 14.43it/s, loss=0.997, v_num=11]
Epoch 0:  21%|██        | 197/938 [00:13<00:51, 14.44it/s, loss=0.997, v_num=11]
Epoch 0:  21%|██        | 197/938 [00:13<00:51, 14.44it/s, loss=0.983, v_num=11]
Epoch 0:  21%|██        | 198/938 [00:13<00:51, 14.45it/s, loss=0.977, v_num=11]
Epoch 0:  21%|██        | 199/938 [00:13<00:51, 14.44it/s, loss=0.977, v_num=11]
Epoch 0:  21%|██        | 199/938 [00:13<00:51, 14.44it/s, loss=0.969, v_num=11]
Epoch 0:  21%|██▏       | 200/938 [00:13<00:51, 14.45it/s, loss=0.952, v_num=11]
Epoch 0:  21%|██▏       | 201/938 [00:13<00:51, 14.43it/s, loss=0.952, v_num=11]
Epoch 0:  21%|██▏       | 201/938 [00:13<00:51, 14.43it/s, loss=0.938, v_num=11]
Epoch 0:  22%|██▏       | 202/938 [00:13<00:50, 14.44it/s, loss=0.938, v_num=11]
Epoch 0:  22%|██▏       | 203/938 [00:14<00:50, 14.45it/s, loss=0.938, v_num=11]
Epoch 0:  22%|██▏       | 203/938 [00:14<00:50, 14.45it/s, loss=0.926, v_num=11]
Epoch 0:  22%|██▏       | 204/938 [00:14<00:50, 14.45it/s, loss=0.917, v_num=11]
Epoch 0:  22%|██▏       | 205/938 [00:14<00:50, 14.45it/s, loss=0.917, v_num=11]
Epoch 0:  22%|██▏       | 205/938 [00:14<00:50, 14.45it/s, loss=0.919, v_num=11]
Epoch 0:  22%|██▏       | 206/938 [00:14<00:50, 14.45it/s, loss=0.916, v_num=11]
Epoch 0:  22%|██▏       | 207/938 [00:14<00:50, 14.46it/s, loss=0.916, v_num=11]
Epoch 0:  22%|██▏       | 207/938 [00:14<00:50, 14.45it/s, loss=0.928, v_num=11]
Epoch 0:  22%|██▏       | 208/938 [00:14<00:50, 14.45it/s, loss=0.922, v_num=11]
Epoch 0:  22%|██▏       | 209/938 [00:14<00:50, 14.46it/s, loss=0.922, v_num=11]
Epoch 0:  22%|██▏       | 209/938 [00:14<00:50, 14.46it/s, loss=0.939, v_num=11]
Epoch 0:  22%|██▏       | 210/938 [00:14<00:50, 14.47it/s, loss=0.94, v_num=11] 
Epoch 0:  22%|██▏       | 211/938 [00:14<00:50, 14.47it/s, loss=0.94, v_num=11]
Epoch 0:  22%|██▏       | 211/938 [00:14<00:50, 14.47it/s, loss=0.936, v_num=11]
Epoch 0:  23%|██▎       | 212/938 [00:14<00:50, 14.47it/s, loss=0.936, v_num=11]
Epoch 0:  23%|██▎       | 213/938 [00:14<00:50, 14.46it/s, loss=0.936, v_num=11]
Epoch 0:  23%|██▎       | 213/938 [00:14<00:50, 14.46it/s, loss=0.933, v_num=11]
Epoch 0:  23%|██▎       | 214/938 [00:14<00:50, 14.46it/s, loss=0.92, v_num=11] 
Epoch 0:  23%|██▎       | 215/938 [00:14<00:50, 14.45it/s, loss=0.92, v_num=11]
Epoch 0:  23%|██▎       | 215/938 [00:14<00:50, 14.45it/s, loss=0.918, v_num=11]
Epoch 0:  23%|██▎       | 216/938 [00:14<00:49, 14.44it/s, loss=0.921, v_num=11]
Epoch 0:  23%|██▎       | 217/938 [00:15<00:49, 14.44it/s, loss=0.921, v_num=11]
Epoch 0:  23%|██▎       | 217/938 [00:15<00:49, 14.44it/s, loss=0.921, v_num=11]
Epoch 0:  23%|██▎       | 218/938 [00:15<00:49, 14.44it/s, loss=0.92, v_num=11] 
Epoch 0:  23%|██▎       | 219/938 [00:15<00:49, 14.43it/s, loss=0.92, v_num=11]
Epoch 0:  23%|██▎       | 219/938 [00:15<00:49, 14.43it/s, loss=0.915, v_num=11]
Epoch 0:  23%|██▎       | 220/938 [00:15<00:49, 14.43it/s, loss=0.922, v_num=11]
Epoch 0:  24%|██▎       | 221/938 [00:15<00:49, 14.42it/s, loss=0.922, v_num=11]
Epoch 0:  24%|██▎       | 221/938 [00:15<00:49, 14.42it/s, loss=0.926, v_num=11]
Epoch 0:  24%|██▎       | 222/938 [00:15<00:49, 14.43it/s, loss=0.932, v_num=11]
Epoch 0:  24%|██▍       | 223/938 [00:15<00:49, 14.43it/s, loss=0.932, v_num=11]
Epoch 0:  24%|██▍       | 223/938 [00:15<00:49, 14.43it/s, loss=0.932, v_num=11]
Epoch 0:  24%|██▍       | 224/938 [00:15<00:49, 14.44it/s, loss=0.941, v_num=11]
Epoch 0:  24%|██▍       | 225/938 [00:15<00:49, 14.42it/s, loss=0.941, v_num=11]
Epoch 0:  24%|██▍       | 225/938 [00:15<00:49, 14.42it/s, loss=0.943, v_num=11]
Epoch 0:  24%|██▍       | 226/938 [00:15<00:49, 14.44it/s, loss=0.941, v_num=11]
Epoch 0:  24%|██▍       | 227/938 [00:15<00:49, 14.43it/s, loss=0.941, v_num=11]
Epoch 0:  24%|██▍       | 227/938 [00:15<00:49, 14.43it/s, loss=0.929, v_num=11]
Epoch 0:  24%|██▍       | 228/938 [00:15<00:49, 14.43it/s, loss=0.928, v_num=11]
Epoch 0:  24%|██▍       | 229/938 [00:15<00:49, 14.44it/s, loss=0.928, v_num=11]
Epoch 0:  24%|██▍       | 229/938 [00:15<00:49, 14.43it/s, loss=0.929, v_num=11]
Epoch 0:  25%|██▍       | 230/938 [00:15<00:49, 14.44it/s, loss=0.914, v_num=11]
Epoch 0:  25%|██▍       | 231/938 [00:15<00:48, 14.44it/s, loss=0.914, v_num=11]
Epoch 0:  25%|██▍       | 231/938 [00:16<00:48, 14.44it/s, loss=0.918, v_num=11]
Epoch 0:  25%|██▍       | 232/938 [00:16<00:48, 14.45it/s, loss=0.907, v_num=11]
Epoch 0:  25%|██▍       | 233/938 [00:16<00:48, 14.45it/s, loss=0.907, v_num=11]
Epoch 0:  25%|██▍       | 233/938 [00:16<00:48, 14.44it/s, loss=0.914, v_num=11]
Epoch 0:  25%|██▍       | 234/938 [00:16<00:48, 14.42it/s, loss=0.911, v_num=11]
Epoch 0:  25%|██▌       | 235/938 [00:16<00:48, 14.44it/s, loss=0.911, v_num=11]
Epoch 0:  25%|██▌       | 235/938 [00:16<00:48, 14.44it/s, loss=0.913, v_num=11]
Epoch 0:  25%|██▌       | 236/938 [00:16<00:48, 14.44it/s, loss=0.907, v_num=11]
Epoch 0:  25%|██▌       | 237/938 [00:16<00:48, 14.44it/s, loss=0.907, v_num=11]
Epoch 0:  25%|██▌       | 237/938 [00:16<00:48, 14.44it/s, loss=0.897, v_num=11]
Epoch 0:  25%|██▌       | 238/938 [00:16<00:48, 14.45it/s, loss=0.901, v_num=11]
Epoch 0:  25%|██▌       | 239/938 [00:16<00:48, 14.44it/s, loss=0.901, v_num=11]
Epoch 0:  25%|██▌       | 239/938 [00:16<00:48, 14.44it/s, loss=0.905, v_num=11]
Epoch 0:  26%|██▌       | 240/938 [00:16<00:48, 14.42it/s, loss=0.91, v_num=11] 
Epoch 0:  26%|██▌       | 241/938 [00:16<00:48, 14.43it/s, loss=0.91, v_num=11]
Epoch 0:  26%|██▌       | 241/938 [00:16<00:48, 14.43it/s, loss=0.917, v_num=11]
Epoch 0:  26%|██▌       | 242/938 [00:16<00:48, 14.44it/s, loss=0.911, v_num=11]
Epoch 0:  26%|██▌       | 243/938 [00:16<00:48, 14.44it/s, loss=0.911, v_num=11]
Epoch 0:  26%|██▌       | 243/938 [00:16<00:48, 14.44it/s, loss=0.917, v_num=11]
Epoch 0:  26%|██▌       | 244/938 [00:16<00:48, 14.45it/s, loss=0.922, v_num=11]
Epoch 0:  26%|██▌       | 245/938 [00:16<00:47, 14.45it/s, loss=0.922, v_num=11]
Epoch 0:  26%|██▌       | 245/938 [00:16<00:47, 14.45it/s, loss=0.917, v_num=11]
Epoch 0:  26%|██▌       | 246/938 [00:17<00:47, 14.46it/s, loss=0.918, v_num=11]
Epoch 0:  26%|██▋       | 247/938 [00:17<00:47, 14.46it/s, loss=0.918, v_num=11]
Epoch 0:  26%|██▋       | 247/938 [00:17<00:47, 14.46it/s, loss=0.926, v_num=11]
Epoch 0:  26%|██▋       | 248/938 [00:17<00:47, 14.46it/s, loss=0.921, v_num=11]
Epoch 0:  27%|██▋       | 249/938 [00:17<00:47, 14.47it/s, loss=0.921, v_num=11]
Epoch 0:  27%|██▋       | 249/938 [00:17<00:47, 14.47it/s, loss=0.909, v_num=11]
Epoch 0:  27%|██▋       | 250/938 [00:17<00:47, 14.47it/s, loss=0.917, v_num=11]
Epoch 0:  27%|██▋       | 251/938 [00:17<00:47, 14.47it/s, loss=0.917, v_num=11]
Epoch 0:  27%|██▋       | 251/938 [00:17<00:47, 14.47it/s, loss=0.913, v_num=11]
Epoch 0:  27%|██▋       | 252/938 [00:17<00:47, 14.47it/s, loss=0.922, v_num=11]
Epoch 0:  27%|██▋       | 253/938 [00:17<00:47, 14.48it/s, loss=0.922, v_num=11]
Epoch 0:  27%|██▋       | 253/938 [00:17<00:47, 14.48it/s, loss=0.916, v_num=11]
Epoch 0:  27%|██▋       | 254/938 [00:17<00:47, 14.48it/s, loss=0.921, v_num=11]
Epoch 0:  27%|██▋       | 255/938 [00:17<00:47, 14.49it/s, loss=0.921, v_num=11]
Epoch 0:  27%|██▋       | 255/938 [00:17<00:47, 14.49it/s, loss=0.918, v_num=11]
Epoch 0:  27%|██▋       | 256/938 [00:17<00:47, 14.49it/s, loss=0.925, v_num=11]
Epoch 0:  27%|██▋       | 257/938 [00:17<00:47, 14.48it/s, loss=0.925, v_num=11]
Epoch 0:  27%|██▋       | 257/938 [00:17<00:47, 14.48it/s, loss=0.936, v_num=11]
Epoch 0:  28%|██▊       | 258/938 [00:17<00:46, 14.48it/s, loss=0.939, v_num=11]
Epoch 0:  28%|██▊       | 259/938 [00:17<00:46, 14.48it/s, loss=0.939, v_num=11]
Epoch 0:  28%|██▊       | 259/938 [00:17<00:46, 14.48it/s, loss=0.942, v_num=11]
Epoch 0:  28%|██▊       | 260/938 [00:17<00:46, 14.48it/s, loss=0.934, v_num=11]
Epoch 0:  28%|██▊       | 261/938 [00:18<00:46, 14.48it/s, loss=0.934, v_num=11]
Epoch 0:  28%|██▊       | 261/938 [00:18<00:46, 14.48it/s, loss=0.923, v_num=11]
Epoch 0:  28%|██▊       | 262/938 [00:18<00:46, 14.48it/s, loss=0.92, v_num=11] 
Epoch 0:  28%|██▊       | 263/938 [00:18<00:46, 14.48it/s, loss=0.92, v_num=11]
Epoch 0:  28%|██▊       | 263/938 [00:18<00:46, 14.48it/s, loss=0.915, v_num=11]
Epoch 0:  28%|██▊       | 264/938 [00:18<00:46, 14.48it/s, loss=0.901, v_num=11]
Epoch 0:  28%|██▊       | 265/938 [00:18<00:46, 14.44it/s, loss=0.901, v_num=11]
Epoch 0:  28%|██▊       | 265/938 [00:18<00:46, 14.44it/s, loss=0.902, v_num=11]
Epoch 0:  28%|██▊       | 266/938 [00:18<00:46, 14.43it/s, loss=0.9, v_num=11]  
Epoch 0:  28%|██▊       | 267/938 [00:18<00:46, 14.40it/s, loss=0.9, v_num=11]
Epoch 0:  28%|██▊       | 267/938 [00:18<00:46, 14.40it/s, loss=0.896, v_num=11]
Epoch 0:  29%|██▊       | 268/938 [00:18<00:46, 14.40it/s, loss=0.9, v_num=11]  
Epoch 0:  29%|██▊       | 269/938 [00:18<00:46, 14.39it/s, loss=0.9, v_num=11]
Epoch 0:  29%|██▊       | 269/938 [00:18<00:46, 14.39it/s, loss=0.898, v_num=11]
Epoch 0:  29%|██▉       | 270/938 [00:18<00:46, 14.38it/s, loss=0.888, v_num=11]
Epoch 0:  29%|██▉       | 271/938 [00:18<00:46, 14.38it/s, loss=0.888, v_num=11]
Epoch 0:  29%|██▉       | 271/938 [00:18<00:46, 14.38it/s, loss=0.885, v_num=11]
Epoch 0:  29%|██▉       | 272/938 [00:18<00:46, 14.37it/s, loss=0.878, v_num=11]
Epoch 0:  29%|██▉       | 273/938 [00:18<00:46, 14.37it/s, loss=0.878, v_num=11]
Epoch 0:  29%|██▉       | 273/938 [00:18<00:46, 14.37it/s, loss=0.873, v_num=11]
Epoch 0:  29%|██▉       | 274/938 [00:19<00:46, 14.37it/s, loss=0.873, v_num=11]
Epoch 0:  29%|██▉       | 275/938 [00:19<00:46, 14.38it/s, loss=0.873, v_num=11]
Epoch 0:  29%|██▉       | 275/938 [00:19<00:46, 14.38it/s, loss=0.866, v_num=11]
Epoch 0:  29%|██▉       | 276/938 [00:19<00:46, 14.38it/s, loss=0.865, v_num=11]
Epoch 0:  30%|██▉       | 277/938 [00:19<00:45, 14.38it/s, loss=0.865, v_num=11]
Epoch 0:  30%|██▉       | 277/938 [00:19<00:45, 14.38it/s, loss=0.863, v_num=11]
Epoch 0:  30%|██▉       | 278/938 [00:19<00:45, 14.38it/s, loss=0.861, v_num=11]
Epoch 0:  30%|██▉       | 279/938 [00:19<00:45, 14.38it/s, loss=0.861, v_num=11]
Epoch 0:  30%|██▉       | 279/938 [00:19<00:45, 14.38it/s, loss=0.859, v_num=11]
Epoch 0:  30%|██▉       | 280/938 [00:19<00:45, 14.39it/s, loss=0.875, v_num=11]
Epoch 0:  30%|██▉       | 281/938 [00:19<00:45, 14.39it/s, loss=0.875, v_num=11]
Epoch 0:  30%|██▉       | 281/938 [00:19<00:45, 14.39it/s, loss=0.876, v_num=11]
Epoch 0:  30%|███       | 282/938 [00:19<00:45, 14.39it/s, loss=0.873, v_num=11]
Epoch 0:  30%|███       | 283/938 [00:19<00:45, 14.37it/s, loss=0.873, v_num=11]
Epoch 0:  30%|███       | 283/938 [00:19<00:45, 14.37it/s, loss=0.869, v_num=11]
Epoch 0:  30%|███       | 284/938 [00:19<00:45, 14.36it/s, loss=0.879, v_num=11]
Epoch 0:  30%|███       | 285/938 [00:19<00:45, 14.36it/s, loss=0.879, v_num=11]
Epoch 0:  30%|███       | 285/938 [00:19<00:45, 14.36it/s, loss=0.876, v_num=11]
Epoch 0:  30%|███       | 286/938 [00:19<00:45, 14.37it/s, loss=0.894, v_num=11]
Epoch 0:  31%|███       | 287/938 [00:19<00:45, 14.37it/s, loss=0.894, v_num=11]
Epoch 0:  31%|███       | 287/938 [00:19<00:45, 14.37it/s, loss=0.889, v_num=11]
Epoch 0:  31%|███       | 288/938 [00:20<00:45, 14.37it/s, loss=0.89, v_num=11] 
Epoch 0:  31%|███       | 289/938 [00:20<00:45, 14.38it/s, loss=0.89, v_num=11]
Epoch 0:  31%|███       | 289/938 [00:20<00:45, 14.38it/s, loss=0.889, v_num=11]
Epoch 0:  31%|███       | 290/938 [00:20<00:45, 14.38it/s, loss=0.899, v_num=11]
Epoch 0:  31%|███       | 291/938 [00:20<00:45, 14.37it/s, loss=0.899, v_num=11]
Epoch 0:  31%|███       | 291/938 [00:20<00:45, 14.37it/s, loss=0.897, v_num=11]
Epoch 0:  31%|███       | 292/938 [00:20<00:44, 14.37it/s, loss=0.894, v_num=11]
Epoch 0:  31%|███       | 293/938 [00:20<00:44, 14.37it/s, loss=0.894, v_num=11]
Epoch 0:  31%|███       | 293/938 [00:20<00:44, 14.37it/s, loss=0.892, v_num=11]
Epoch 0:  31%|███▏      | 294/938 [00:20<00:44, 14.36it/s, loss=0.889, v_num=11]
Epoch 0:  31%|███▏      | 295/938 [00:20<00:44, 14.37it/s, loss=0.889, v_num=11]
Epoch 0:  31%|███▏      | 295/938 [00:20<00:44, 14.37it/s, loss=0.895, v_num=11]
Epoch 0:  32%|███▏      | 296/938 [00:20<00:44, 14.36it/s, loss=0.891, v_num=11]
Epoch 0:  32%|███▏      | 297/938 [00:20<00:44, 14.35it/s, loss=0.891, v_num=11]
Epoch 0:  32%|███▏      | 297/938 [00:20<00:44, 14.35it/s, loss=0.892, v_num=11]
Epoch 0:  32%|███▏      | 298/938 [00:20<00:44, 14.35it/s, loss=0.89, v_num=11] 
Epoch 0:  32%|███▏      | 299/938 [00:20<00:44, 14.34it/s, loss=0.89, v_num=11]
Epoch 0:  32%|███▏      | 299/938 [00:20<00:44, 14.34it/s, loss=0.892, v_num=11]
Epoch 0:  32%|███▏      | 300/938 [00:20<00:44, 14.34it/s, loss=0.877, v_num=11]
Epoch 0:  32%|███▏      | 301/938 [00:20<00:44, 14.34it/s, loss=0.877, v_num=11]
Epoch 0:  32%|███▏      | 301/938 [00:20<00:44, 14.34it/s, loss=0.882, v_num=11]
Epoch 0:  32%|███▏      | 302/938 [00:21<00:44, 14.34it/s, loss=0.881, v_num=11]
Epoch 0:  32%|███▏      | 303/938 [00:21<00:44, 14.35it/s, loss=0.881, v_num=11]
Epoch 0:  32%|███▏      | 303/938 [00:21<00:44, 14.35it/s, loss=0.884, v_num=11]
Epoch 0:  32%|███▏      | 304/938 [00:21<00:44, 14.35it/s, loss=0.87, v_num=11] 
Epoch 0:  33%|███▎      | 305/938 [00:21<00:44, 14.34it/s, loss=0.87, v_num=11]
Epoch 0:  33%|███▎      | 305/938 [00:21<00:44, 14.34it/s, loss=0.875, v_num=11]
Epoch 0:  33%|███▎      | 306/938 [00:21<00:44, 14.35it/s, loss=0.868, v_num=11]
Epoch 0:  33%|███▎      | 307/938 [00:21<00:43, 14.34it/s, loss=0.868, v_num=11]
Epoch 0:  33%|███▎      | 307/938 [00:21<00:43, 14.34it/s, loss=0.872, v_num=11]
Epoch 0:  33%|███▎      | 308/938 [00:21<00:43, 14.35it/s, loss=0.87, v_num=11] 
Epoch 0:  33%|███▎      | 309/938 [00:21<00:43, 14.36it/s, loss=0.87, v_num=11]
Epoch 0:  33%|███▎      | 309/938 [00:21<00:43, 14.36it/s, loss=0.869, v_num=11]
Epoch 0:  33%|███▎      | 310/938 [00:21<00:43, 14.36it/s, loss=0.864, v_num=11]
Epoch 0:  33%|███▎      | 311/938 [00:21<00:43, 14.35it/s, loss=0.864, v_num=11]
Epoch 0:  33%|███▎      | 311/938 [00:21<00:43, 14.35it/s, loss=0.86, v_num=11] 
Epoch 0:  33%|███▎      | 312/938 [00:21<00:43, 14.35it/s, loss=0.861, v_num=11]
Epoch 0:  33%|███▎      | 313/938 [00:21<00:43, 14.35it/s, loss=0.861, v_num=11]
Epoch 0:  33%|███▎      | 313/938 [00:21<00:43, 14.35it/s, loss=0.863, v_num=11]
Epoch 0:  33%|███▎      | 314/938 [00:21<00:43, 14.35it/s, loss=0.873, v_num=11]
Epoch 0:  34%|███▎      | 315/938 [00:21<00:43, 14.35it/s, loss=0.873, v_num=11]
Epoch 0:  34%|███▎      | 315/938 [00:21<00:43, 14.35it/s, loss=0.866, v_num=11]
Epoch 0:  34%|███▎      | 316/938 [00:22<00:43, 14.36it/s, loss=0.868, v_num=11]
Epoch 0:  34%|███▍      | 317/938 [00:22<00:43, 14.36it/s, loss=0.868, v_num=11]
Epoch 0:  34%|███▍      | 317/938 [00:22<00:43, 14.36it/s, loss=0.867, v_num=11]
Epoch 0:  34%|███▍      | 318/938 [00:22<00:43, 14.36it/s, loss=0.856, v_num=11]
Epoch 0:  34%|███▍      | 319/938 [00:22<00:43, 14.35it/s, loss=0.856, v_num=11]
Epoch 0:  34%|███▍      | 319/938 [00:22<00:43, 14.35it/s, loss=0.854, v_num=11]
Epoch 0:  34%|███▍      | 320/938 [00:22<00:43, 14.34it/s, loss=0.853, v_num=11]
Epoch 0:  34%|███▍      | 321/938 [00:22<00:43, 14.34it/s, loss=0.853, v_num=11]
Epoch 0:  34%|███▍      | 321/938 [00:22<00:43, 14.34it/s, loss=0.848, v_num=11]
Epoch 0:  34%|███▍      | 322/938 [00:22<00:42, 14.35it/s, loss=0.843, v_num=11]
Epoch 0:  34%|███▍      | 323/938 [00:22<00:42, 14.35it/s, loss=0.843, v_num=11]
Epoch 0:  34%|███▍      | 323/938 [00:22<00:42, 14.35it/s, loss=0.854, v_num=11]
Epoch 0:  35%|███▍      | 324/938 [00:22<00:42, 14.35it/s, loss=0.852, v_num=11]
Epoch 0:  35%|███▍      | 325/938 [00:22<00:42, 14.35it/s, loss=0.852, v_num=11]
Epoch 0:  35%|███▍      | 325/938 [00:22<00:42, 14.35it/s, loss=0.832, v_num=11]
Epoch 0:  35%|███▍      | 326/938 [00:22<00:42, 14.36it/s, loss=0.82, v_num=11] 
Epoch 0:  35%|███▍      | 327/938 [00:22<00:42, 14.36it/s, loss=0.82, v_num=11]
Epoch 0:  35%|███▍      | 327/938 [00:22<00:42, 14.36it/s, loss=0.816, v_num=11]
Epoch 0:  35%|███▍      | 328/938 [00:22<00:42, 14.35it/s, loss=0.807, v_num=11]
Epoch 0:  35%|███▌      | 329/938 [00:22<00:42, 14.35it/s, loss=0.807, v_num=11]
Epoch 0:  35%|███▌      | 329/938 [00:22<00:42, 14.35it/s, loss=0.81, v_num=11] 
Epoch 0:  35%|███▌      | 330/938 [00:22<00:42, 14.35it/s, loss=0.812, v_num=11]
Epoch 0:  35%|███▌      | 331/938 [00:23<00:42, 14.35it/s, loss=0.812, v_num=11]
Epoch 0:  35%|███▌      | 331/938 [00:23<00:42, 14.35it/s, loss=0.819, v_num=11]
Epoch 0:  35%|███▌      | 332/938 [00:23<00:42, 14.34it/s, loss=0.821, v_num=11]
Epoch 0:  36%|███▌      | 333/938 [00:23<00:42, 14.33it/s, loss=0.821, v_num=11]
Epoch 0:  36%|███▌      | 333/938 [00:23<00:42, 14.33it/s, loss=0.826, v_num=11]
Epoch 0:  36%|███▌      | 334/938 [00:23<00:42, 14.34it/s, loss=0.813, v_num=11]
Epoch 0:  36%|███▌      | 335/938 [00:23<00:42, 14.34it/s, loss=0.813, v_num=11]
Epoch 0:  36%|███▌      | 335/938 [00:23<00:42, 14.34it/s, loss=0.829, v_num=11]
Epoch 0:  36%|███▌      | 336/938 [00:23<00:41, 14.34it/s, loss=0.826, v_num=11]
Epoch 0:  36%|███▌      | 337/938 [00:23<00:41, 14.34it/s, loss=0.826, v_num=11]
Epoch 0:  36%|███▌      | 337/938 [00:23<00:41, 14.34it/s, loss=0.819, v_num=11]
Epoch 0:  36%|███▌      | 338/938 [00:23<00:41, 14.33it/s, loss=0.827, v_num=11]
Epoch 0:  36%|███▌      | 339/938 [00:23<00:41, 14.32it/s, loss=0.827, v_num=11]
Epoch 0:  36%|███▌      | 339/938 [00:23<00:41, 14.32it/s, loss=0.822, v_num=11]
Epoch 0:  36%|███▌      | 340/938 [00:23<00:41, 14.32it/s, loss=0.818, v_num=11]
Epoch 0:  36%|███▋      | 341/938 [00:23<00:41, 14.32it/s, loss=0.818, v_num=11]
Epoch 0:  36%|███▋      | 341/938 [00:23<00:41, 14.32it/s, loss=0.811, v_num=11]
Epoch 0:  36%|███▋      | 342/938 [00:23<00:41, 14.31it/s, loss=0.808, v_num=11]
Epoch 0:  37%|███▋      | 343/938 [00:23<00:41, 14.30it/s, loss=0.808, v_num=11]
Epoch 0:  37%|███▋      | 343/938 [00:23<00:41, 14.30it/s, loss=0.797, v_num=11]
Epoch 0:  37%|███▋      | 344/938 [00:24<00:41, 14.29it/s, loss=0.798, v_num=11]
Epoch 0:  37%|███▋      | 345/938 [00:24<00:41, 14.28it/s, loss=0.798, v_num=11]
Epoch 0:  37%|███▋      | 345/938 [00:24<00:41, 14.28it/s, loss=0.809, v_num=11]
Epoch 0:  37%|███▋      | 346/938 [00:24<00:41, 14.29it/s, loss=0.809, v_num=11]
Epoch 0:  37%|███▋      | 347/938 [00:24<00:41, 14.29it/s, loss=0.809, v_num=11]
Epoch 0:  37%|███▋      | 347/938 [00:24<00:41, 14.29it/s, loss=0.807, v_num=11]
Epoch 0:  37%|███▋      | 348/938 [00:24<00:41, 14.30it/s, loss=0.807, v_num=11]
Epoch 0:  37%|███▋      | 349/938 [00:24<00:41, 14.30it/s, loss=0.807, v_num=11]
Epoch 0:  37%|███▋      | 349/938 [00:24<00:41, 14.29it/s, loss=0.804, v_num=11]
Epoch 0:  37%|███▋      | 350/938 [00:24<00:41, 14.31it/s, loss=0.801, v_num=11]
Epoch 0:  37%|███▋      | 351/938 [00:24<00:41, 14.31it/s, loss=0.801, v_num=11]
Epoch 0:  37%|███▋      | 351/938 [00:24<00:41, 14.31it/s, loss=0.802, v_num=11]
Epoch 0:  38%|███▊      | 352/938 [00:24<00:40, 14.31it/s, loss=0.803, v_num=11]
Epoch 0:  38%|███▊      | 353/938 [00:24<00:40, 14.32it/s, loss=0.803, v_num=11]
Epoch 0:  38%|███▊      | 353/938 [00:24<00:40, 14.32it/s, loss=0.792, v_num=11]
Epoch 0:  38%|███▊      | 354/938 [00:24<00:40, 14.31it/s, loss=0.791, v_num=11]
Epoch 0:  38%|███▊      | 355/938 [00:24<00:40, 14.32it/s, loss=0.791, v_num=11]
Epoch 0:  38%|███▊      | 355/938 [00:24<00:40, 14.32it/s, loss=0.784, v_num=11]
Epoch 0:  38%|███▊      | 356/938 [00:24<00:40, 14.32it/s, loss=0.786, v_num=11]
Epoch 0:  38%|███▊      | 357/938 [00:24<00:40, 14.32it/s, loss=0.786, v_num=11]
Epoch 0:  38%|███▊      | 357/938 [00:24<00:40, 14.32it/s, loss=0.784, v_num=11]
Epoch 0:  38%|███▊      | 358/938 [00:25<00:40, 14.31it/s, loss=0.785, v_num=11]
Epoch 0:  38%|███▊      | 359/938 [00:25<00:40, 14.30it/s, loss=0.785, v_num=11]
Epoch 0:  38%|███▊      | 359/938 [00:25<00:40, 14.30it/s, loss=0.795, v_num=11]
Epoch 0:  38%|███▊      | 360/938 [00:25<00:40, 14.31it/s, loss=0.808, v_num=11]
Epoch 0:  38%|███▊      | 361/938 [00:25<00:40, 14.30it/s, loss=0.808, v_num=11]
Epoch 0:  38%|███▊      | 361/938 [00:25<00:40, 14.30it/s, loss=0.812, v_num=11]
Epoch 0:  39%|███▊      | 362/938 [00:25<00:40, 14.30it/s, loss=0.808, v_num=11]
Epoch 0:  39%|███▊      | 363/938 [00:25<00:40, 14.30it/s, loss=0.808, v_num=11]
Epoch 0:  39%|███▊      | 363/938 [00:25<00:40, 14.30it/s, loss=0.816, v_num=11]
Epoch 0:  39%|███▉      | 364/938 [00:25<00:40, 14.30it/s, loss=0.82, v_num=11] 
Epoch 0:  39%|███▉      | 365/938 [00:25<00:40, 14.30it/s, loss=0.82, v_num=11]
Epoch 0:  39%|███▉      | 365/938 [00:25<00:40, 14.30it/s, loss=0.823, v_num=11]
Epoch 0:  39%|███▉      | 366/938 [00:25<00:40, 14.30it/s, loss=0.827, v_num=11]
Epoch 0:  39%|███▉      | 367/938 [00:25<00:39, 14.30it/s, loss=0.827, v_num=11]
Epoch 0:  39%|███▉      | 367/938 [00:25<00:39, 14.30it/s, loss=0.826, v_num=11]
Epoch 0:  39%|███▉      | 368/938 [00:25<00:39, 14.30it/s, loss=0.83, v_num=11] 
Epoch 0:  39%|███▉      | 369/938 [00:25<00:39, 14.31it/s, loss=0.83, v_num=11]
Epoch 0:  39%|███▉      | 369/938 [00:25<00:39, 14.31it/s, loss=0.846, v_num=11]
Epoch 0:  39%|███▉      | 370/938 [00:25<00:39, 14.31it/s, loss=0.842, v_num=11]
Epoch 0:  40%|███▉      | 371/938 [00:25<00:39, 14.30it/s, loss=0.842, v_num=11]
Epoch 0:  40%|███▉      | 371/938 [00:25<00:39, 14.30it/s, loss=0.836, v_num=11]
Epoch 0:  40%|███▉      | 372/938 [00:26<00:39, 14.30it/s, loss=0.842, v_num=11]
Epoch 0:  40%|███▉      | 373/938 [00:26<00:39, 14.31it/s, loss=0.842, v_num=11]
Epoch 0:  40%|███▉      | 373/938 [00:26<00:39, 14.31it/s, loss=0.842, v_num=11]
Epoch 0:  40%|███▉      | 374/938 [00:26<00:39, 14.31it/s, loss=0.843, v_num=11]
Epoch 0:  40%|███▉      | 375/938 [00:26<00:39, 14.31it/s, loss=0.843, v_num=11]
Epoch 0:  40%|███▉      | 375/938 [00:26<00:39, 14.31it/s, loss=0.833, v_num=11]
Epoch 0:  40%|████      | 376/938 [00:26<00:39, 14.32it/s, loss=0.827, v_num=11]
Epoch 0:  40%|████      | 377/938 [00:26<00:39, 14.32it/s, loss=0.827, v_num=11]
Epoch 0:  40%|████      | 377/938 [00:26<00:39, 14.32it/s, loss=0.833, v_num=11]
Epoch 0:  40%|████      | 378/938 [00:26<00:39, 14.32it/s, loss=0.831, v_num=11]
Epoch 0:  40%|████      | 379/938 [00:26<00:39, 14.32it/s, loss=0.831, v_num=11]
Epoch 0:  40%|████      | 379/938 [00:26<00:39, 14.32it/s, loss=0.818, v_num=11]
Epoch 0:  41%|████      | 380/938 [00:26<00:38, 14.32it/s, loss=0.806, v_num=11]
Epoch 0:  41%|████      | 381/938 [00:26<00:38, 14.33it/s, loss=0.806, v_num=11]
Epoch 0:  41%|████      | 381/938 [00:26<00:38, 14.33it/s, loss=0.807, v_num=11]
Epoch 0:  41%|████      | 382/938 [00:26<00:38, 14.33it/s, loss=0.812, v_num=11]
Epoch 0:  41%|████      | 383/938 [00:26<00:38, 14.33it/s, loss=0.812, v_num=11]
Epoch 0:  41%|████      | 383/938 [00:26<00:38, 14.33it/s, loss=0.801, v_num=11]
Epoch 0:  41%|████      | 384/938 [00:26<00:38, 14.33it/s, loss=0.808, v_num=11]
Epoch 0:  41%|████      | 385/938 [00:26<00:38, 14.33it/s, loss=0.808, v_num=11]
Epoch 0:  41%|████      | 385/938 [00:26<00:38, 14.33it/s, loss=0.798, v_num=11]
Epoch 0:  41%|████      | 386/938 [00:26<00:38, 14.34it/s, loss=0.802, v_num=11]
Epoch 0:  41%|████▏     | 387/938 [00:26<00:38, 14.34it/s, loss=0.802, v_num=11]
Epoch 0:  41%|████▏     | 387/938 [00:26<00:38, 14.34it/s, loss=0.812, v_num=11]
Epoch 0:  41%|████▏     | 388/938 [00:27<00:38, 14.34it/s, loss=0.811, v_num=11]
Epoch 0:  41%|████▏     | 389/938 [00:27<00:38, 14.34it/s, loss=0.811, v_num=11]
Epoch 0:  41%|████▏     | 389/938 [00:27<00:38, 14.34it/s, loss=0.799, v_num=11]
Epoch 0:  42%|████▏     | 390/938 [00:27<00:38, 14.34it/s, loss=0.796, v_num=11]
Epoch 0:  42%|████▏     | 391/938 [00:27<00:38, 14.35it/s, loss=0.796, v_num=11]
Epoch 0:  42%|████▏     | 391/938 [00:27<00:38, 14.35it/s, loss=0.796, v_num=11]
Epoch 0:  42%|████▏     | 392/938 [00:27<00:38, 14.34it/s, loss=0.791, v_num=11]
Epoch 0:  42%|████▏     | 393/938 [00:27<00:37, 14.34it/s, loss=0.791, v_num=11]
Epoch 0:  42%|████▏     | 393/938 [00:27<00:37, 14.34it/s, loss=0.787, v_num=11]
Epoch 0:  42%|████▏     | 394/938 [00:27<00:37, 14.35it/s, loss=0.799, v_num=11]
Epoch 0:  42%|████▏     | 395/938 [00:27<00:37, 14.35it/s, loss=0.799, v_num=11]
Epoch 0:  42%|████▏     | 395/938 [00:27<00:37, 14.35it/s, loss=0.797, v_num=11]
Epoch 0:  42%|████▏     | 396/938 [00:27<00:37, 14.35it/s, loss=0.793, v_num=11]
Epoch 0:  42%|████▏     | 397/938 [00:27<00:37, 14.35it/s, loss=0.793, v_num=11]
Epoch 0:  42%|████▏     | 397/938 [00:27<00:37, 14.35it/s, loss=0.783, v_num=11]
Epoch 0:  42%|████▏     | 398/938 [00:27<00:37, 14.35it/s, loss=0.783, v_num=11]
Epoch 0:  43%|████▎     | 399/938 [00:27<00:37, 14.35it/s, loss=0.783, v_num=11]
Epoch 0:  43%|████▎     | 399/938 [00:27<00:37, 14.35it/s, loss=0.788, v_num=11]
Epoch 0:  43%|████▎     | 400/938 [00:27<00:37, 14.36it/s, loss=0.793, v_num=11]
Epoch 0:  43%|████▎     | 401/938 [00:27<00:37, 14.35it/s, loss=0.793, v_num=11]
Epoch 0:  43%|████▎     | 401/938 [00:27<00:37, 14.35it/s, loss=0.797, v_num=11]
Epoch 0:  43%|████▎     | 402/938 [00:28<00:37, 14.35it/s, loss=0.795, v_num=11]
Epoch 0:  43%|████▎     | 403/938 [00:28<00:37, 14.35it/s, loss=0.795, v_num=11]
Epoch 0:  43%|████▎     | 403/938 [00:28<00:37, 14.35it/s, loss=0.797, v_num=11]
Epoch 0:  43%|████▎     | 404/938 [00:28<00:37, 14.35it/s, loss=0.791, v_num=11]
Epoch 0:  43%|████▎     | 405/938 [00:28<00:37, 14.35it/s, loss=0.791, v_num=11]
Epoch 0:  43%|████▎     | 405/938 [00:28<00:37, 14.35it/s, loss=0.802, v_num=11]
Epoch 0:  43%|████▎     | 406/938 [00:28<00:37, 14.36it/s, loss=0.791, v_num=11]
Epoch 0:  43%|████▎     | 407/938 [00:28<00:36, 14.35it/s, loss=0.791, v_num=11]
Epoch 0:  43%|████▎     | 407/938 [00:28<00:36, 14.35it/s, loss=0.786, v_num=11]
Epoch 0:  43%|████▎     | 408/938 [00:28<00:36, 14.35it/s, loss=0.785, v_num=11]
Epoch 0:  44%|████▎     | 409/938 [00:28<00:36, 14.35it/s, loss=0.785, v_num=11]
Epoch 0:  44%|████▎     | 409/938 [00:28<00:36, 14.35it/s, loss=0.785, v_num=11]
Epoch 0:  44%|████▎     | 410/938 [00:28<00:36, 14.36it/s, loss=0.788, v_num=11]
Epoch 0:  44%|████▍     | 411/938 [00:28<00:36, 14.35it/s, loss=0.788, v_num=11]
Epoch 0:  44%|████▍     | 411/938 [00:28<00:36, 14.35it/s, loss=0.79, v_num=11] 
Epoch 0:  44%|████▍     | 412/938 [00:28<00:36, 14.36it/s, loss=0.793, v_num=11]
Epoch 0:  44%|████▍     | 413/938 [00:28<00:36, 14.36it/s, loss=0.793, v_num=11]
Epoch 0:  44%|████▍     | 413/938 [00:28<00:36, 14.36it/s, loss=0.806, v_num=11]
Epoch 0:  44%|████▍     | 414/938 [00:28<00:36, 14.36it/s, loss=0.792, v_num=11]
Epoch 0:  44%|████▍     | 415/938 [00:28<00:36, 14.36it/s, loss=0.792, v_num=11]
Epoch 0:  44%|████▍     | 415/938 [00:28<00:36, 14.36it/s, loss=0.791, v_num=11]
Epoch 0:  44%|████▍     | 416/938 [00:28<00:36, 14.36it/s, loss=0.796, v_num=11]
Epoch 0:  44%|████▍     | 417/938 [00:29<00:36, 14.36it/s, loss=0.796, v_num=11]
Epoch 0:  44%|████▍     | 417/938 [00:29<00:36, 14.36it/s, loss=0.802, v_num=11]
Epoch 0:  45%|████▍     | 418/938 [00:29<00:36, 14.36it/s, loss=0.797, v_num=11]
Epoch 0:  45%|████▍     | 419/938 [00:29<00:36, 14.36it/s, loss=0.797, v_num=11]
Epoch 0:  45%|████▍     | 419/938 [00:29<00:36, 14.36it/s, loss=0.805, v_num=11]
Epoch 0:  45%|████▍     | 420/938 [00:29<00:36, 14.36it/s, loss=0.798, v_num=11]
Epoch 0:  45%|████▍     | 421/938 [00:29<00:35, 14.36it/s, loss=0.798, v_num=11]
Epoch 0:  45%|████▍     | 421/938 [00:29<00:35, 14.36it/s, loss=0.791, v_num=11]
Epoch 0:  45%|████▍     | 422/938 [00:29<00:35, 14.36it/s, loss=0.797, v_num=11]
Epoch 0:  45%|████▌     | 423/938 [00:29<00:35, 14.36it/s, loss=0.797, v_num=11]
Epoch 0:  45%|████▌     | 423/938 [00:29<00:35, 14.36it/s, loss=0.79, v_num=11] 
Epoch 0:  45%|████▌     | 424/938 [00:29<00:35, 14.36it/s, loss=0.789, v_num=11]
Epoch 0:  45%|████▌     | 425/938 [00:29<00:35, 14.35it/s, loss=0.789, v_num=11]
Epoch 0:  45%|████▌     | 425/938 [00:29<00:35, 14.35it/s, loss=0.794, v_num=11]
Epoch 0:  45%|████▌     | 426/938 [00:29<00:35, 14.35it/s, loss=0.797, v_num=11]
Epoch 0:  46%|████▌     | 427/938 [00:29<00:35, 14.35it/s, loss=0.797, v_num=11]
Epoch 0:  46%|████▌     | 427/938 [00:29<00:35, 14.35it/s, loss=0.791, v_num=11]
Epoch 0:  46%|████▌     | 428/938 [00:29<00:35, 14.36it/s, loss=0.796, v_num=11]
Epoch 0:  46%|████▌     | 429/938 [00:29<00:35, 14.35it/s, loss=0.796, v_num=11]
Epoch 0:  46%|████▌     | 429/938 [00:29<00:35, 14.35it/s, loss=0.789, v_num=11]
Epoch 0:  46%|████▌     | 430/938 [00:29<00:35, 14.36it/s, loss=0.788, v_num=11]
Epoch 0:  46%|████▌     | 431/938 [00:30<00:35, 14.36it/s, loss=0.788, v_num=11]
Epoch 0:  46%|████▌     | 431/938 [00:30<00:35, 14.36it/s, loss=0.787, v_num=11]
Epoch 0:  46%|████▌     | 432/938 [00:30<00:35, 14.36it/s, loss=0.781, v_num=11]
Epoch 0:  46%|████▌     | 433/938 [00:30<00:35, 14.36it/s, loss=0.781, v_num=11]
Epoch 0:  46%|████▌     | 433/938 [00:30<00:35, 14.36it/s, loss=0.772, v_num=11]
Epoch 0:  46%|████▋     | 434/938 [00:30<00:35, 14.36it/s, loss=0.78, v_num=11] 
Epoch 0:  46%|████▋     | 435/938 [00:30<00:35, 14.36it/s, loss=0.78, v_num=11]
Epoch 0:  46%|████▋     | 435/938 [00:30<00:35, 14.36it/s, loss=0.786, v_num=11]
Epoch 0:  46%|████▋     | 436/938 [00:30<00:34, 14.37it/s, loss=0.778, v_num=11]
Epoch 0:  47%|████▋     | 437/938 [00:30<00:34, 14.37it/s, loss=0.778, v_num=11]
Epoch 0:  47%|████▋     | 437/938 [00:30<00:34, 14.36it/s, loss=0.774, v_num=11]
Epoch 0:  47%|████▋     | 438/938 [00:30<00:34, 14.37it/s, loss=0.773, v_num=11]
Epoch 0:  47%|████▋     | 439/938 [00:30<00:34, 14.37it/s, loss=0.773, v_num=11]
Epoch 0:  47%|████▋     | 439/938 [00:30<00:34, 14.37it/s, loss=0.762, v_num=11]
Epoch 0:  47%|████▋     | 440/938 [00:30<00:34, 14.37it/s, loss=0.764, v_num=11]
Epoch 0:  47%|████▋     | 441/938 [00:30<00:34, 14.37it/s, loss=0.764, v_num=11]
Epoch 0:  47%|████▋     | 441/938 [00:30<00:34, 14.37it/s, loss=0.773, v_num=11]
Epoch 0:  47%|████▋     | 442/938 [00:30<00:34, 14.37it/s, loss=0.775, v_num=11]
Epoch 0:  47%|████▋     | 443/938 [00:30<00:34, 14.37it/s, loss=0.775, v_num=11]
Epoch 0:  47%|████▋     | 443/938 [00:30<00:34, 14.37it/s, loss=0.783, v_num=11]
Epoch 0:  47%|████▋     | 444/938 [00:30<00:34, 14.37it/s, loss=0.781, v_num=11]
Epoch 0:  47%|████▋     | 445/938 [00:30<00:34, 14.37it/s, loss=0.781, v_num=11]
Epoch 0:  47%|████▋     | 445/938 [00:30<00:34, 14.37it/s, loss=0.77, v_num=11] 
Epoch 0:  48%|████▊     | 446/938 [00:31<00:34, 14.38it/s, loss=0.765, v_num=11]
Epoch 0:  48%|████▊     | 447/938 [00:31<00:34, 14.37it/s, loss=0.765, v_num=11]
Epoch 0:  48%|████▊     | 447/938 [00:31<00:34, 14.37it/s, loss=0.769, v_num=11]
Epoch 0:  48%|████▊     | 448/938 [00:31<00:34, 14.37it/s, loss=0.765, v_num=11]
Epoch 0:  48%|████▊     | 449/938 [00:31<00:34, 14.37it/s, loss=0.765, v_num=11]
Epoch 0:  48%|████▊     | 449/938 [00:31<00:34, 14.37it/s, loss=0.775, v_num=11]
Epoch 0:  48%|████▊     | 450/938 [00:31<00:33, 14.37it/s, loss=0.775, v_num=11]
Epoch 0:  48%|████▊     | 451/938 [00:31<00:33, 14.38it/s, loss=0.775, v_num=11]
Epoch 0:  48%|████▊     | 451/938 [00:31<00:33, 14.38it/s, loss=0.775, v_num=11]
Epoch 0:  48%|████▊     | 452/938 [00:31<00:33, 14.38it/s, loss=0.776, v_num=11]
Epoch 0:  48%|████▊     | 453/938 [00:31<00:33, 14.38it/s, loss=0.776, v_num=11]
Epoch 0:  48%|████▊     | 453/938 [00:31<00:33, 14.38it/s, loss=0.778, v_num=11]
Epoch 0:  48%|████▊     | 454/938 [00:31<00:33, 14.39it/s, loss=0.778, v_num=11]
Epoch 0:  49%|████▊     | 455/938 [00:31<00:33, 14.38it/s, loss=0.778, v_num=11]
Epoch 0:  49%|████▊     | 455/938 [00:31<00:33, 14.38it/s, loss=0.775, v_num=11]
Epoch 0:  49%|████▊     | 456/938 [00:31<00:33, 14.38it/s, loss=0.786, v_num=11]
Epoch 0:  49%|████▊     | 457/938 [00:31<00:33, 14.38it/s, loss=0.786, v_num=11]
Epoch 0:  49%|████▊     | 457/938 [00:31<00:33, 14.38it/s, loss=0.784, v_num=11]
Epoch 0:  49%|████▉     | 458/938 [00:31<00:33, 14.38it/s, loss=0.788, v_num=11]
Epoch 0:  49%|████▉     | 459/938 [00:31<00:33, 14.38it/s, loss=0.788, v_num=11]
Epoch 0:  49%|████▉     | 459/938 [00:31<00:33, 14.38it/s, loss=0.803, v_num=11]
Epoch 0:  49%|████▉     | 460/938 [00:31<00:33, 14.38it/s, loss=0.806, v_num=11]
Epoch 0:  49%|████▉     | 461/938 [00:32<00:33, 14.37it/s, loss=0.806, v_num=11]
Epoch 0:  49%|████▉     | 461/938 [00:32<00:33, 14.37it/s, loss=0.803, v_num=11]
Epoch 0:  49%|████▉     | 462/938 [00:32<00:33, 14.37it/s, loss=0.798, v_num=11]
Epoch 0:  49%|████▉     | 463/938 [00:32<00:33, 14.38it/s, loss=0.798, v_num=11]
Epoch 0:  49%|████▉     | 463/938 [00:32<00:33, 14.38it/s, loss=0.811, v_num=11]
Epoch 0:  49%|████▉     | 464/938 [00:32<00:32, 14.38it/s, loss=0.806, v_num=11]
Epoch 0:  50%|████▉     | 465/938 [00:32<00:32, 14.37it/s, loss=0.806, v_num=11]
Epoch 0:  50%|████▉     | 465/938 [00:32<00:32, 14.37it/s, loss=0.796, v_num=11]
Epoch 0:  50%|████▉     | 466/938 [00:32<00:32, 14.37it/s, loss=0.794, v_num=11]
Epoch 0:  50%|████▉     | 467/938 [00:32<00:32, 14.37it/s, loss=0.794, v_num=11]
Epoch 0:  50%|████▉     | 467/938 [00:32<00:32, 14.37it/s, loss=0.796, v_num=11]
Epoch 0:  50%|████▉     | 468/938 [00:32<00:32, 14.37it/s, loss=0.79, v_num=11] 
Epoch 0:  50%|█████     | 469/938 [00:32<00:32, 14.38it/s, loss=0.79, v_num=11]
Epoch 0:  50%|█████     | 469/938 [00:32<00:32, 14.38it/s, loss=0.782, v_num=11]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]

Validating:   0%|          | 2/469 [00:00<00:24, 18.69it/s]
Epoch 0:  50%|█████     | 472/938 [00:32<00:32, 14.43it/s, loss=0.782, v_num=11]

Validating:   1%|          | 5/469 [00:00<00:20, 22.23it/s]
Epoch 0:  51%|█████     | 475/938 [00:32<00:32, 14.46it/s, loss=0.782, v_num=11]

Validating:   2%|▏         | 8/469 [00:00<00:19, 23.07it/s]
Epoch 0:  51%|█████     | 478/938 [00:32<00:31, 14.50it/s, loss=0.782, v_num=11]

Validating:   2%|▏         | 11/469 [00:00<00:18, 24.48it/s]
Epoch 0:  51%|█████▏    | 481/938 [00:33<00:31, 14.54it/s, loss=0.782, v_num=11]

Validating:   3%|▎         | 14/469 [00:00<00:18, 24.75it/s]
Epoch 0:  52%|█████▏    | 484/938 [00:33<00:31, 14.58it/s, loss=0.782, v_num=11]

Validating:   4%|▎         | 17/469 [00:00<00:18, 24.10it/s]
Epoch 0:  52%|█████▏    | 487/938 [00:33<00:30, 14.61it/s, loss=0.782, v_num=11]

Validating:   4%|▍         | 20/469 [00:00<00:18, 24.05it/s]
Epoch 0:  52%|█████▏    | 490/938 [00:33<00:30, 14.65it/s, loss=0.782, v_num=11]

Validating:   5%|▍         | 23/469 [00:00<00:18, 24.63it/s]
Epoch 0:  53%|█████▎    | 493/938 [00:33<00:30, 14.69it/s, loss=0.782, v_num=11]

Validating:   6%|▌         | 26/469 [00:01<00:18, 24.27it/s]
Epoch 0:  53%|█████▎    | 496/938 [00:33<00:30, 14.72it/s, loss=0.782, v_num=11]

Validating:   6%|▌         | 29/469 [00:01<00:18, 23.98it/s]
Epoch 0:  53%|█████▎    | 499/938 [00:33<00:29, 14.75it/s, loss=0.782, v_num=11]

Validating:   7%|▋         | 32/469 [00:01<00:17, 24.81it/s]
Epoch 0:  54%|█████▎    | 502/938 [00:33<00:29, 14.79it/s, loss=0.782, v_num=11]

Validating:   7%|▋         | 35/469 [00:01<00:18, 23.04it/s]
Epoch 0:  54%|█████▍    | 505/938 [00:34<00:29, 14.82it/s, loss=0.782, v_num=11]

Validating:   8%|▊         | 38/469 [00:01<00:18, 23.05it/s]
Epoch 0:  54%|█████▍    | 508/938 [00:34<00:28, 14.85it/s, loss=0.782, v_num=11]

Validating:   9%|▊         | 41/469 [00:01<00:18, 23.67it/s]
Epoch 0:  54%|█████▍    | 511/938 [00:34<00:28, 14.88it/s, loss=0.782, v_num=11]

Validating:   9%|▉         | 44/469 [00:01<00:17, 24.21it/s]
Epoch 0:  55%|█████▍    | 514/938 [00:34<00:28, 14.92it/s, loss=0.782, v_num=11]

Validating:  10%|█         | 47/469 [00:01<00:17, 24.61it/s]
Epoch 0:  55%|█████▌    | 517/938 [00:34<00:28, 14.96it/s, loss=0.782, v_num=11]

Validating:  11%|█         | 50/469 [00:02<00:17, 24.28it/s]
Epoch 0:  55%|█████▌    | 520/938 [00:34<00:27, 14.99it/s, loss=0.782, v_num=11]

Validating:  11%|█▏        | 53/469 [00:02<00:17, 24.37it/s]
Epoch 0:  56%|█████▌    | 523/938 [00:34<00:27, 15.02it/s, loss=0.782, v_num=11]

Validating:  12%|█▏        | 56/469 [00:02<00:17, 23.64it/s]
Epoch 0:  56%|█████▌    | 526/938 [00:34<00:27, 15.05it/s, loss=0.782, v_num=11]

Validating:  13%|█▎        | 59/469 [00:02<00:17, 23.46it/s]
Epoch 0:  56%|█████▋    | 529/938 [00:35<00:27, 15.08it/s, loss=0.782, v_num=11]

Validating:  13%|█▎        | 62/469 [00:02<00:16, 24.40it/s]
Epoch 0:  57%|█████▋    | 532/938 [00:35<00:26, 15.11it/s, loss=0.782, v_num=11]

Validating:  14%|█▍        | 65/469 [00:02<00:17, 23.07it/s]
Epoch 0:  57%|█████▋    | 535/938 [00:35<00:26, 15.14it/s, loss=0.782, v_num=11]

Validating:  14%|█▍        | 68/469 [00:02<00:16, 24.21it/s]
Epoch 0:  57%|█████▋    | 538/938 [00:35<00:26, 15.17it/s, loss=0.782, v_num=11]

Validating:  15%|█▌        | 71/469 [00:02<00:16, 24.78it/s]
Epoch 0:  58%|█████▊    | 541/938 [00:35<00:26, 15.21it/s, loss=0.782, v_num=11]

Validating:  16%|█▌        | 74/469 [00:03<00:16, 24.47it/s]
Epoch 0:  58%|█████▊    | 544/938 [00:35<00:25, 15.24it/s, loss=0.782, v_num=11]

Validating:  16%|█▋        | 77/469 [00:03<00:15, 24.63it/s]
Epoch 0:  58%|█████▊    | 547/938 [00:35<00:25, 15.27it/s, loss=0.782, v_num=11]

Validating:  17%|█▋        | 80/469 [00:03<00:15, 25.17it/s]
Epoch 0:  59%|█████▊    | 550/938 [00:35<00:25, 15.31it/s, loss=0.782, v_num=11]

Validating:  18%|█▊        | 83/469 [00:03<00:15, 25.35it/s]
Epoch 0:  59%|█████▉    | 553/938 [00:36<00:25, 15.34it/s, loss=0.782, v_num=11]

Validating:  18%|█▊        | 86/469 [00:03<00:14, 25.67it/s]
Epoch 0:  59%|█████▉    | 556/938 [00:36<00:24, 15.38it/s, loss=0.782, v_num=11]

Validating:  19%|█▉        | 89/469 [00:03<00:14, 26.06it/s]
Epoch 0:  60%|█████▉    | 559/938 [00:36<00:24, 15.41it/s, loss=0.782, v_num=11]

Validating:  20%|█▉        | 92/469 [00:03<00:14, 26.75it/s]
Epoch 0:  60%|█████▉    | 562/938 [00:36<00:24, 15.45it/s, loss=0.782, v_num=11]

Validating:  20%|██        | 95/469 [00:03<00:14, 25.96it/s]
Epoch 0:  60%|██████    | 565/938 [00:36<00:24, 15.48it/s, loss=0.782, v_num=11]

Validating:  21%|██        | 98/469 [00:03<00:14, 26.35it/s]
Epoch 0:  61%|██████    | 568/938 [00:36<00:23, 15.52it/s, loss=0.782, v_num=11]

Validating:  22%|██▏       | 101/469 [00:04<00:14, 25.65it/s]
Epoch 0:  61%|██████    | 571/938 [00:36<00:23, 15.55it/s, loss=0.782, v_num=11]

Validating:  22%|██▏       | 104/469 [00:04<00:14, 24.75it/s]
Epoch 0:  61%|██████    | 574/938 [00:36<00:23, 15.57it/s, loss=0.782, v_num=11]

Validating:  23%|██▎       | 107/469 [00:04<00:14, 24.67it/s]
Epoch 0:  62%|██████▏   | 577/938 [00:36<00:23, 15.60it/s, loss=0.782, v_num=11]

Validating:  23%|██▎       | 110/469 [00:04<00:14, 24.05it/s]
Epoch 0:  62%|██████▏   | 580/938 [00:37<00:22, 15.63it/s, loss=0.782, v_num=11]

Validating:  24%|██▍       | 113/469 [00:04<00:15, 23.53it/s]
Epoch 0:  62%|██████▏   | 583/938 [00:37<00:22, 15.65it/s, loss=0.782, v_num=11]

Validating:  25%|██▍       | 116/469 [00:04<00:15, 23.30it/s]
Epoch 0:  62%|██████▏   | 586/938 [00:37<00:22, 15.68it/s, loss=0.782, v_num=11]

Validating:  25%|██▌       | 119/469 [00:04<00:14, 23.60it/s]
Epoch 0:  63%|██████▎   | 589/938 [00:37<00:22, 15.70it/s, loss=0.782, v_num=11]

Validating:  26%|██▌       | 122/469 [00:05<00:14, 23.22it/s]
Epoch 0:  63%|██████▎   | 592/938 [00:37<00:21, 15.73it/s, loss=0.782, v_num=11]

Validating:  27%|██▋       | 125/469 [00:05<00:14, 23.87it/s]
Epoch 0:  63%|██████▎   | 595/938 [00:37<00:21, 15.76it/s, loss=0.782, v_num=11]

Validating:  27%|██▋       | 128/469 [00:05<00:14, 23.65it/s]
Epoch 0:  64%|██████▍   | 598/938 [00:37<00:21, 15.78it/s, loss=0.782, v_num=11]

Validating:  28%|██▊       | 131/469 [00:05<00:14, 23.90it/s]
Epoch 0:  64%|██████▍   | 601/938 [00:38<00:21, 15.81it/s, loss=0.782, v_num=11]

Validating:  29%|██▊       | 134/469 [00:05<00:13, 24.60it/s]
Epoch 0:  64%|██████▍   | 604/938 [00:38<00:21, 15.84it/s, loss=0.782, v_num=11]

Validating:  29%|██▉       | 137/469 [00:05<00:14, 23.43it/s]
Epoch 0:  65%|██████▍   | 607/938 [00:38<00:20, 15.86it/s, loss=0.782, v_num=11]

Validating:  30%|██▉       | 140/469 [00:05<00:13, 24.54it/s]
Epoch 0:  65%|██████▌   | 610/938 [00:38<00:20, 15.90it/s, loss=0.782, v_num=11]

Validating:  30%|███       | 143/469 [00:05<00:12, 25.52it/s]
Epoch 0:  65%|██████▌   | 613/938 [00:38<00:20, 15.93it/s, loss=0.782, v_num=11]

Validating:  31%|███       | 146/469 [00:05<00:12, 25.89it/s]
Epoch 0:  66%|██████▌   | 616/938 [00:38<00:20, 15.96it/s, loss=0.782, v_num=11]

Validating:  32%|███▏      | 149/469 [00:06<00:12, 25.94it/s]
Epoch 0:  66%|██████▌   | 619/938 [00:38<00:19, 15.99it/s, loss=0.782, v_num=11]

Validating:  32%|███▏      | 152/469 [00:06<00:12, 26.10it/s]
Epoch 0:  66%|██████▋   | 622/938 [00:38<00:19, 16.02it/s, loss=0.782, v_num=11]

Validating:  33%|███▎      | 155/469 [00:06<00:12, 25.75it/s]
Epoch 0:  67%|██████▋   | 625/938 [00:38<00:19, 16.05it/s, loss=0.782, v_num=11]

Validating:  34%|███▎      | 158/469 [00:06<00:12, 24.79it/s]
Epoch 0:  67%|██████▋   | 628/938 [00:39<00:19, 16.07it/s, loss=0.782, v_num=11]

Validating:  34%|███▍      | 161/469 [00:06<00:12, 24.29it/s]
Epoch 0:  67%|██████▋   | 631/938 [00:39<00:19, 16.10it/s, loss=0.782, v_num=11]

Validating:  35%|███▍      | 164/469 [00:06<00:11, 25.60it/s]
Epoch 0:  68%|██████▊   | 634/938 [00:39<00:18, 16.13it/s, loss=0.782, v_num=11]

Validating:  36%|███▌      | 167/469 [00:06<00:11, 25.93it/s]
Epoch 0:  68%|██████▊   | 637/938 [00:39<00:18, 16.16it/s, loss=0.782, v_num=11]

Validating:  36%|███▌      | 170/469 [00:06<00:11, 25.32it/s]
Epoch 0:  68%|██████▊   | 640/938 [00:39<00:18, 16.19it/s, loss=0.782, v_num=11]

Validating:  37%|███▋      | 173/469 [00:07<00:11, 25.31it/s]
Epoch 0:  69%|██████▊   | 643/938 [00:39<00:18, 16.21it/s, loss=0.782, v_num=11]

Validating:  38%|███▊      | 176/469 [00:07<00:11, 24.91it/s]
Epoch 0:  69%|██████▉   | 646/938 [00:39<00:17, 16.24it/s, loss=0.782, v_num=11]

Validating:  38%|███▊      | 179/469 [00:07<00:11, 25.47it/s]
Epoch 0:  69%|██████▉   | 649/938 [00:39<00:17, 16.27it/s, loss=0.782, v_num=11]

Validating:  39%|███▉      | 182/469 [00:07<00:11, 25.79it/s]
Epoch 0:  70%|██████▉   | 652/938 [00:40<00:17, 16.30it/s, loss=0.782, v_num=11]

Validating:  39%|███▉      | 185/469 [00:07<00:11, 25.72it/s]
Epoch 0:  70%|██████▉   | 655/938 [00:40<00:17, 16.32it/s, loss=0.782, v_num=11]

Validating:  40%|████      | 188/469 [00:07<00:11, 23.43it/s]
Epoch 0:  70%|███████   | 658/938 [00:40<00:17, 16.34it/s, loss=0.782, v_num=11]

Validating:  41%|████      | 191/469 [00:07<00:11, 23.62it/s]
Epoch 0:  70%|███████   | 661/938 [00:40<00:16, 16.36it/s, loss=0.782, v_num=11]

Validating:  41%|████▏     | 194/469 [00:07<00:11, 24.48it/s]
Epoch 0:  71%|███████   | 664/938 [00:40<00:16, 16.39it/s, loss=0.782, v_num=11]

Validating:  42%|████▏     | 197/469 [00:08<00:11, 24.70it/s]
Epoch 0:  71%|███████   | 667/938 [00:40<00:16, 16.41it/s, loss=0.782, v_num=11]

Validating:  43%|████▎     | 200/469 [00:08<00:10, 24.83it/s]
Epoch 0:  71%|███████▏  | 670/938 [00:40<00:16, 16.44it/s, loss=0.782, v_num=11]

Validating:  43%|████▎     | 203/469 [00:08<00:11, 23.89it/s]
Epoch 0:  72%|███████▏  | 673/938 [00:40<00:16, 16.46it/s, loss=0.782, v_num=11]

Validating:  44%|████▍     | 206/469 [00:08<00:11, 23.63it/s]
Epoch 0:  72%|███████▏  | 676/938 [00:41<00:15, 16.48it/s, loss=0.782, v_num=11]

Validating:  45%|████▍     | 209/469 [00:08<00:11, 23.41it/s]
Epoch 0:  72%|███████▏  | 679/938 [00:41<00:15, 16.50it/s, loss=0.782, v_num=11]

Validating:  45%|████▌     | 212/469 [00:08<00:10, 24.66it/s]
Epoch 0:  73%|███████▎  | 682/938 [00:41<00:15, 16.53it/s, loss=0.782, v_num=11]

Validating:  46%|████▌     | 215/469 [00:08<00:10, 24.20it/s]
Epoch 0:  73%|███████▎  | 685/938 [00:41<00:15, 16.55it/s, loss=0.782, v_num=11]

Validating:  46%|████▋     | 218/469 [00:08<00:10, 23.51it/s]
Epoch 0:  73%|███████▎  | 688/938 [00:41<00:15, 16.57it/s, loss=0.782, v_num=11]

Validating:  47%|████▋     | 221/469 [00:09<00:10, 23.64it/s]
Epoch 0:  74%|███████▎  | 691/938 [00:41<00:14, 16.59it/s, loss=0.782, v_num=11]

Validating:  48%|████▊     | 224/469 [00:09<00:09, 24.81it/s]
Epoch 0:  74%|███████▍  | 694/938 [00:41<00:14, 16.62it/s, loss=0.782, v_num=11]

Validating:  48%|████▊     | 227/469 [00:09<00:09, 25.23it/s]
Epoch 0:  74%|███████▍  | 697/938 [00:41<00:14, 16.65it/s, loss=0.782, v_num=11]

Validating:  49%|████▉     | 230/469 [00:09<00:09, 25.50it/s]
Epoch 0:  75%|███████▍  | 700/938 [00:41<00:14, 16.67it/s, loss=0.782, v_num=11]

Validating:  50%|████▉     | 233/469 [00:09<00:09, 25.21it/s]
Epoch 0:  75%|███████▍  | 703/938 [00:42<00:14, 16.69it/s, loss=0.782, v_num=11]

Validating:  50%|█████     | 236/469 [00:09<00:09, 25.38it/s]
Epoch 0:  75%|███████▌  | 706/938 [00:42<00:13, 16.72it/s, loss=0.782, v_num=11]

Validating:  51%|█████     | 239/469 [00:09<00:09, 25.41it/s]
Epoch 0:  76%|███████▌  | 709/938 [00:42<00:13, 16.74it/s, loss=0.782, v_num=11]

Validating:  52%|█████▏    | 242/469 [00:09<00:09, 25.02it/s]
Epoch 0:  76%|███████▌  | 712/938 [00:42<00:13, 16.77it/s, loss=0.782, v_num=11]

Validating:  52%|█████▏    | 245/469 [00:09<00:09, 24.62it/s]
Epoch 0:  76%|███████▌  | 715/938 [00:42<00:13, 16.79it/s, loss=0.782, v_num=11]

Validating:  53%|█████▎    | 248/469 [00:10<00:09, 24.02it/s]
Epoch 0:  77%|███████▋  | 718/938 [00:42<00:13, 16.80it/s, loss=0.782, v_num=11]

Validating:  54%|█████▎    | 251/469 [00:10<00:08, 24.67it/s]
Epoch 0:  77%|███████▋  | 721/938 [00:42<00:12, 16.83it/s, loss=0.782, v_num=11]

Validating:  54%|█████▍    | 254/469 [00:10<00:08, 25.19it/s]
Epoch 0:  77%|███████▋  | 724/938 [00:42<00:12, 16.86it/s, loss=0.782, v_num=11]

Validating:  55%|█████▍    | 257/469 [00:10<00:08, 24.72it/s]
Epoch 0:  78%|███████▊  | 727/938 [00:43<00:12, 16.88it/s, loss=0.782, v_num=11]

Validating:  55%|█████▌    | 260/469 [00:10<00:08, 24.74it/s]
Epoch 0:  78%|███████▊  | 730/938 [00:43<00:12, 16.90it/s, loss=0.782, v_num=11]

Validating:  56%|█████▌    | 263/469 [00:10<00:07, 25.81it/s]
Epoch 0:  78%|███████▊  | 733/938 [00:43<00:12, 16.93it/s, loss=0.782, v_num=11]

Validating:  57%|█████▋    | 266/469 [00:10<00:08, 25.23it/s]
Epoch 0:  78%|███████▊  | 736/938 [00:43<00:11, 16.95it/s, loss=0.782, v_num=11]

Validating:  57%|█████▋    | 269/469 [00:10<00:08, 24.91it/s]
Epoch 0:  79%|███████▉  | 739/938 [00:43<00:11, 16.97it/s, loss=0.782, v_num=11]

Validating:  58%|█████▊    | 272/469 [00:11<00:07, 25.03it/s]
Epoch 0:  79%|███████▉  | 742/938 [00:43<00:11, 16.99it/s, loss=0.782, v_num=11]

Validating:  59%|█████▊    | 275/469 [00:11<00:07, 25.51it/s]
Epoch 0:  79%|███████▉  | 745/938 [00:43<00:11, 17.01it/s, loss=0.782, v_num=11]

Validating:  59%|█████▉    | 278/469 [00:11<00:07, 26.27it/s]
Epoch 0:  80%|███████▉  | 748/938 [00:43<00:11, 17.04it/s, loss=0.782, v_num=11]

Validating:  60%|█████▉    | 281/469 [00:11<00:07, 25.20it/s]
Epoch 0:  80%|████████  | 751/938 [00:44<00:10, 17.06it/s, loss=0.782, v_num=11]

Validating:  61%|██████    | 284/469 [00:11<00:07, 24.88it/s]
Epoch 0:  80%|████████  | 754/938 [00:44<00:10, 17.08it/s, loss=0.782, v_num=11]

Validating:  61%|██████    | 287/469 [00:11<00:07, 25.09it/s]
Epoch 0:  81%|████████  | 757/938 [00:44<00:10, 17.10it/s, loss=0.782, v_num=11]

Validating:  62%|██████▏   | 290/469 [00:11<00:07, 25.47it/s]
Epoch 0:  81%|████████  | 760/938 [00:44<00:10, 17.13it/s, loss=0.782, v_num=11]

Validating:  62%|██████▏   | 293/469 [00:11<00:07, 24.87it/s]
Epoch 0:  81%|████████▏ | 763/938 [00:44<00:10, 17.14it/s, loss=0.782, v_num=11]

Validating:  63%|██████▎   | 296/469 [00:12<00:07, 24.32it/s]
Epoch 0:  82%|████████▏ | 766/938 [00:44<00:10, 17.16it/s, loss=0.782, v_num=11]

Validating:  64%|██████▍   | 299/469 [00:12<00:06, 24.33it/s]
Epoch 0:  82%|████████▏ | 769/938 [00:44<00:09, 17.18it/s, loss=0.782, v_num=11]

Validating:  64%|██████▍   | 302/469 [00:12<00:06, 25.10it/s]
Epoch 0:  82%|████████▏ | 772/938 [00:44<00:09, 17.21it/s, loss=0.782, v_num=11]

Validating:  65%|██████▌   | 305/469 [00:12<00:06, 25.39it/s]
Epoch 0:  83%|████████▎ | 775/938 [00:44<00:09, 17.23it/s, loss=0.782, v_num=11]

Validating:  66%|██████▌   | 308/469 [00:12<00:06, 25.64it/s]
Epoch 0:  83%|████████▎ | 778/938 [00:45<00:09, 17.25it/s, loss=0.782, v_num=11]

Validating:  66%|██████▋   | 311/469 [00:12<00:06, 24.59it/s]
Epoch 0:  83%|████████▎ | 781/938 [00:45<00:09, 17.27it/s, loss=0.782, v_num=11]

Validating:  67%|██████▋   | 314/469 [00:12<00:06, 24.42it/s]
Epoch 0:  84%|████████▎ | 784/938 [00:45<00:08, 17.29it/s, loss=0.782, v_num=11]

Validating:  68%|██████▊   | 317/469 [00:12<00:06, 24.73it/s]
Epoch 0:  84%|████████▍ | 787/938 [00:45<00:08, 17.31it/s, loss=0.782, v_num=11]

Validating:  68%|██████▊   | 320/469 [00:13<00:06, 23.71it/s]
Epoch 0:  84%|████████▍ | 790/938 [00:45<00:08, 17.32it/s, loss=0.782, v_num=11]

Validating:  69%|██████▉   | 323/469 [00:13<00:06, 23.78it/s]
Epoch 0:  85%|████████▍ | 793/938 [00:45<00:08, 17.34it/s, loss=0.782, v_num=11]

Validating:  70%|██████▉   | 326/469 [00:13<00:05, 25.04it/s]
Epoch 0:  85%|████████▍ | 796/938 [00:45<00:08, 17.36it/s, loss=0.782, v_num=11]

Validating:  70%|███████   | 329/469 [00:13<00:05, 25.54it/s]
Epoch 0:  85%|████████▌ | 799/938 [00:45<00:07, 17.39it/s, loss=0.782, v_num=11]

Validating:  71%|███████   | 332/469 [00:13<00:05, 25.70it/s]
Epoch 0:  86%|████████▌ | 802/938 [00:46<00:07, 17.41it/s, loss=0.782, v_num=11]

Validating:  71%|███████▏  | 335/469 [00:13<00:05, 25.72it/s]
Epoch 0:  86%|████████▌ | 805/938 [00:46<00:07, 17.43it/s, loss=0.782, v_num=11]

Validating:  72%|███████▏  | 338/469 [00:13<00:05, 25.91it/s]
Epoch 0:  86%|████████▌ | 808/938 [00:46<00:07, 17.45it/s, loss=0.782, v_num=11]

Validating:  73%|███████▎  | 341/469 [00:13<00:04, 26.79it/s]
Epoch 0:  86%|████████▋ | 811/938 [00:46<00:07, 17.48it/s, loss=0.782, v_num=11]

Validating:  73%|███████▎  | 344/469 [00:13<00:04, 27.32it/s]
Epoch 0:  87%|████████▋ | 814/938 [00:46<00:07, 17.50it/s, loss=0.782, v_num=11]

Validating:  74%|███████▍  | 347/469 [00:14<00:04, 27.45it/s]
Epoch 0:  87%|████████▋ | 817/938 [00:46<00:06, 17.53it/s, loss=0.782, v_num=11]

Validating:  75%|███████▍  | 350/469 [00:14<00:04, 27.10it/s]
Epoch 0:  87%|████████▋ | 820/938 [00:46<00:06, 17.55it/s, loss=0.782, v_num=11]

Validating:  75%|███████▌  | 353/469 [00:14<00:04, 27.09it/s]
Epoch 0:  88%|████████▊ | 823/938 [00:46<00:06, 17.57it/s, loss=0.782, v_num=11]

Validating:  76%|███████▌  | 356/469 [00:14<00:04, 26.17it/s]
Epoch 0:  88%|████████▊ | 826/938 [00:46<00:06, 17.59it/s, loss=0.782, v_num=11]

Validating:  77%|███████▋  | 359/469 [00:14<00:04, 25.23it/s]
Epoch 0:  88%|████████▊ | 829/938 [00:47<00:06, 17.60it/s, loss=0.782, v_num=11]

Validating:  77%|███████▋  | 362/469 [00:14<00:04, 25.55it/s]
Epoch 0:  89%|████████▊ | 832/938 [00:47<00:06, 17.62it/s, loss=0.782, v_num=11]

Validating:  78%|███████▊  | 365/469 [00:14<00:04, 25.88it/s]
Epoch 0:  89%|████████▉ | 835/938 [00:47<00:05, 17.65it/s, loss=0.782, v_num=11]

Validating:  78%|███████▊  | 368/469 [00:14<00:03, 25.77it/s]
Epoch 0:  89%|████████▉ | 838/938 [00:47<00:05, 17.67it/s, loss=0.782, v_num=11]

Validating:  79%|███████▉  | 371/469 [00:14<00:03, 25.99it/s]
Epoch 0:  90%|████████▉ | 841/938 [00:47<00:05, 17.69it/s, loss=0.782, v_num=11]

Validating:  80%|███████▉  | 374/469 [00:15<00:03, 24.70it/s]
Epoch 0:  90%|████████▉ | 844/938 [00:47<00:05, 17.70it/s, loss=0.782, v_num=11]

Validating:  80%|████████  | 377/469 [00:15<00:03, 25.02it/s]
Epoch 0:  90%|█████████ | 847/938 [00:47<00:05, 17.72it/s, loss=0.782, v_num=11]

Validating:  81%|████████  | 380/469 [00:15<00:03, 25.86it/s]
Epoch 0:  91%|█████████ | 850/938 [00:47<00:04, 17.74it/s, loss=0.782, v_num=11]

Validating:  82%|████████▏ | 383/469 [00:15<00:03, 24.44it/s]
Epoch 0:  91%|█████████ | 853/938 [00:48<00:04, 17.75it/s, loss=0.782, v_num=11]

Validating:  82%|████████▏ | 386/469 [00:15<00:03, 24.60it/s]
Epoch 0:  91%|█████████▏| 856/938 [00:48<00:04, 17.77it/s, loss=0.782, v_num=11]

Validating:  83%|████████▎ | 389/469 [00:15<00:03, 24.27it/s]
Epoch 0:  92%|█████████▏| 859/938 [00:48<00:04, 17.79it/s, loss=0.782, v_num=11]

Validating:  84%|████████▎ | 392/469 [00:15<00:03, 25.08it/s]
Epoch 0:  92%|█████████▏| 862/938 [00:48<00:04, 17.81it/s, loss=0.782, v_num=11]

Validating:  84%|████████▍ | 395/469 [00:15<00:02, 24.88it/s]
Epoch 0:  92%|█████████▏| 865/938 [00:48<00:04, 17.82it/s, loss=0.782, v_num=11]

Validating:  85%|████████▍ | 398/469 [00:16<00:02, 25.63it/s]
Epoch 0:  93%|█████████▎| 868/938 [00:48<00:03, 17.85it/s, loss=0.782, v_num=11]

Validating:  86%|████████▌ | 401/469 [00:16<00:02, 25.58it/s]
Epoch 0:  93%|█████████▎| 871/938 [00:48<00:03, 17.87it/s, loss=0.782, v_num=11]

Validating:  86%|████████▌ | 404/469 [00:16<00:02, 25.03it/s]
Epoch 0:  93%|█████████▎| 874/938 [00:48<00:03, 17.88it/s, loss=0.782, v_num=11]

Validating:  87%|████████▋ | 407/469 [00:16<00:02, 25.67it/s]
Epoch 0:  93%|█████████▎| 877/938 [00:48<00:03, 17.90it/s, loss=0.782, v_num=11]

Validating:  87%|████████▋ | 410/469 [00:16<00:02, 26.01it/s]
Epoch 0:  94%|█████████▍| 880/938 [00:49<00:03, 17.92it/s, loss=0.782, v_num=11]

Validating:  88%|████████▊ | 413/469 [00:16<00:02, 25.88it/s]
Epoch 0:  94%|█████████▍| 883/938 [00:49<00:03, 17.94it/s, loss=0.782, v_num=11]

Validating:  89%|████████▊ | 416/469 [00:16<00:02, 25.08it/s]
Epoch 0:  94%|█████████▍| 886/938 [00:49<00:02, 17.95it/s, loss=0.782, v_num=11]

Validating:  89%|████████▉ | 419/469 [00:16<00:02, 24.98it/s]
Epoch 0:  95%|█████████▍| 889/938 [00:49<00:02, 17.97it/s, loss=0.782, v_num=11]

Validating:  90%|████████▉ | 422/469 [00:16<00:01, 24.83it/s]
Epoch 0:  95%|█████████▌| 892/938 [00:49<00:02, 17.99it/s, loss=0.782, v_num=11]

Validating:  91%|█████████ | 425/469 [00:17<00:01, 26.17it/s]
Epoch 0:  95%|█████████▌| 895/938 [00:49<00:02, 18.01it/s, loss=0.782, v_num=11]

Validating:  91%|█████████▏| 428/469 [00:17<00:01, 23.63it/s]
Epoch 0:  96%|█████████▌| 898/938 [00:49<00:02, 18.02it/s, loss=0.782, v_num=11]

Validating:  92%|█████████▏| 431/469 [00:17<00:01, 24.47it/s]
Epoch 0:  96%|█████████▌| 901/938 [00:49<00:02, 18.03it/s, loss=0.782, v_num=11]

Validating:  93%|█████████▎| 434/469 [00:17<00:01, 25.24it/s]
Epoch 0:  96%|█████████▋| 904/938 [00:50<00:01, 18.05it/s, loss=0.782, v_num=11]

Validating:  93%|█████████▎| 437/469 [00:17<00:01, 26.11it/s]
Epoch 0:  97%|█████████▋| 907/938 [00:50<00:01, 18.08it/s, loss=0.782, v_num=11]

Validating:  94%|█████████▍| 440/469 [00:17<00:01, 24.87it/s]
Epoch 0:  97%|█████████▋| 910/938 [00:50<00:01, 18.09it/s, loss=0.782, v_num=11]

Validating:  94%|█████████▍| 443/469 [00:17<00:01, 24.41it/s]
Epoch 0:  97%|█████████▋| 913/938 [00:50<00:01, 18.10it/s, loss=0.782, v_num=11]

Validating:  95%|█████████▌| 446/469 [00:17<00:00, 24.90it/s]
Epoch 0:  98%|█████████▊| 916/938 [00:50<00:01, 18.12it/s, loss=0.782, v_num=11]

Validating:  96%|█████████▌| 449/469 [00:18<00:00, 24.56it/s]
Epoch 0:  98%|█████████▊| 919/938 [00:50<00:01, 18.13it/s, loss=0.782, v_num=11]

Validating:  96%|█████████▋| 452/469 [00:18<00:00, 24.29it/s]
Epoch 0:  98%|█████████▊| 922/938 [00:50<00:00, 18.15it/s, loss=0.782, v_num=11]

Validating:  97%|█████████▋| 455/469 [00:18<00:00, 24.67it/s]
Epoch 0:  99%|█████████▊| 925/938 [00:50<00:00, 18.16it/s, loss=0.782, v_num=11]

Validating:  98%|█████████▊| 458/469 [00:18<00:00, 25.00it/s]
Epoch 0:  99%|█████████▉| 928/938 [00:51<00:00, 18.18it/s, loss=0.782, v_num=11]

Validating:  98%|█████████▊| 461/469 [00:18<00:00, 24.52it/s]
Epoch 0:  99%|█████████▉| 931/938 [00:51<00:00, 18.20it/s, loss=0.782, v_num=11]

Validating:  99%|█████████▉| 464/469 [00:18<00:00, 21.84it/s]
Epoch 0: 100%|█████████▉| 934/938 [00:51<00:00, 18.19it/s, loss=0.782, v_num=11]

Validating: 100%|█████████▉| 467/469 [00:18<00:00, 22.16it/s]
Epoch 0: 100%|█████████▉| 937/938 [00:51<00:00, 18.20it/s, loss=0.782, v_num=11]
Epoch 0: 100%|██████████| 938/938 [00:51<00:00, 18.20it/s, loss=0.782, v_num=11, val_rmse=0.618]

                                                             
Epoch 0: 100%|██████████| 938/938 [00:51<00:00, 18.19it/s, loss=0.782, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 0:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.782, v_num=11, val_rmse=0.618, train_rmse=1.190]          
Epoch 1:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.782, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   0%|          | 1/938 [00:00<01:15, 12.36it/s, loss=0.78, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   0%|          | 2/938 [00:00<01:16, 12.28it/s, loss=0.776, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   0%|          | 3/938 [00:00<01:10, 13.32it/s, loss=0.776, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   0%|          | 3/938 [00:00<01:10, 13.28it/s, loss=0.776, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   0%|          | 4/938 [00:00<01:04, 14.40it/s, loss=0.773, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   1%|          | 5/938 [00:00<01:04, 14.41it/s, loss=0.77, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:   1%|          | 6/938 [00:00<01:04, 14.55it/s, loss=0.77, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   1%|          | 6/938 [00:00<01:04, 14.52it/s, loss=0.77, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   1%|          | 7/938 [00:00<01:05, 14.20it/s, loss=0.766, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   1%|          | 8/938 [00:00<01:06, 14.09it/s, loss=0.766, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   1%|          | 9/938 [00:00<01:06, 14.01it/s, loss=0.766, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   1%|          | 9/938 [00:00<01:06, 14.00it/s, loss=0.762, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   1%|          | 10/938 [00:00<01:06, 13.88it/s, loss=0.749, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   1%|          | 11/938 [00:00<01:07, 13.81it/s, loss=0.756, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   1%|▏         | 12/938 [00:00<01:06, 13.97it/s, loss=0.756, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   1%|▏         | 12/938 [00:00<01:06, 13.96it/s, loss=0.754, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   1%|▏         | 13/938 [00:00<01:06, 13.87it/s, loss=0.755, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   1%|▏         | 14/938 [00:01<01:07, 13.67it/s, loss=0.746, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   2%|▏         | 15/938 [00:01<01:07, 13.75it/s, loss=0.746, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   2%|▏         | 15/938 [00:01<01:07, 13.74it/s, loss=0.75, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:   2%|▏         | 16/938 [00:01<01:06, 13.97it/s, loss=0.763, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   2%|▏         | 17/938 [00:01<01:05, 13.98it/s, loss=0.766, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   2%|▏         | 18/938 [00:01<01:06, 13.94it/s, loss=0.766, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   2%|▏         | 18/938 [00:01<01:06, 13.93it/s, loss=0.766, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   2%|▏         | 19/938 [00:01<01:05, 13.96it/s, loss=0.767, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   2%|▏         | 20/938 [00:01<01:05, 13.99it/s, loss=0.772, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   2%|▏         | 21/938 [00:01<01:06, 13.76it/s, loss=0.772, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   2%|▏         | 21/938 [00:01<01:06, 13.75it/s, loss=0.774, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   2%|▏         | 22/938 [00:01<01:06, 13.87it/s, loss=0.772, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   2%|▏         | 23/938 [00:01<01:05, 13.89it/s, loss=0.775, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   3%|▎         | 24/938 [00:01<01:05, 13.96it/s, loss=0.775, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   3%|▎         | 24/938 [00:01<01:05, 13.95it/s, loss=0.781, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   3%|▎         | 25/938 [00:01<01:05, 14.01it/s, loss=0.768, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   3%|▎         | 26/938 [00:01<01:04, 14.05it/s, loss=0.773, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   3%|▎         | 27/938 [00:01<01:04, 14.07it/s, loss=0.773, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   3%|▎         | 27/938 [00:01<01:04, 14.06it/s, loss=0.772, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   3%|▎         | 28/938 [00:01<01:04, 14.04it/s, loss=0.774, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   3%|▎         | 29/938 [00:02<01:04, 14.12it/s, loss=0.777, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   3%|▎         | 30/938 [00:02<01:05, 13.95it/s, loss=0.777, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   3%|▎         | 30/938 [00:02<01:05, 13.95it/s, loss=0.772, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   3%|▎         | 31/938 [00:02<01:05, 13.95it/s, loss=0.759, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   3%|▎         | 32/938 [00:02<01:05, 13.87it/s, loss=0.754, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   4%|▎         | 33/938 [00:02<01:05, 13.92it/s, loss=0.754, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   4%|▎         | 33/938 [00:02<01:05, 13.91it/s, loss=0.755, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   4%|▎         | 34/938 [00:02<01:05, 13.88it/s, loss=0.749, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   4%|▎         | 35/938 [00:02<01:04, 13.96it/s, loss=0.747, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   4%|▍         | 36/938 [00:02<01:04, 14.00it/s, loss=0.747, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   4%|▍         | 36/938 [00:02<01:04, 14.00it/s, loss=0.742, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   4%|▍         | 37/938 [00:02<01:04, 14.03it/s, loss=0.757, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   4%|▍         | 38/938 [00:02<01:03, 14.08it/s, loss=0.749, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   4%|▍         | 39/938 [00:02<01:03, 14.10it/s, loss=0.749, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   4%|▍         | 39/938 [00:02<01:03, 14.10it/s, loss=0.749, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   4%|▍         | 40/938 [00:02<01:03, 14.15it/s, loss=0.746, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   4%|▍         | 41/938 [00:02<01:03, 14.14it/s, loss=0.739, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   4%|▍         | 42/938 [00:02<01:03, 14.13it/s, loss=0.739, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   4%|▍         | 42/938 [00:02<01:03, 14.13it/s, loss=0.748, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   5%|▍         | 43/938 [00:03<01:03, 14.12it/s, loss=0.738, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   5%|▍         | 44/938 [00:03<01:03, 14.16it/s, loss=0.737, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   5%|▍         | 45/938 [00:03<01:03, 14.16it/s, loss=0.737, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   5%|▍         | 45/938 [00:03<01:03, 14.16it/s, loss=0.744, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   5%|▍         | 46/938 [00:03<01:02, 14.16it/s, loss=0.741, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   5%|▌         | 47/938 [00:03<01:03, 14.12it/s, loss=0.748, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   5%|▌         | 48/938 [00:03<01:03, 14.10it/s, loss=0.748, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   5%|▌         | 48/938 [00:03<01:03, 14.09it/s, loss=0.748, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   5%|▌         | 49/938 [00:03<01:02, 14.12it/s, loss=0.747, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   5%|▌         | 50/938 [00:03<01:02, 14.10it/s, loss=0.756, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   5%|▌         | 51/938 [00:03<01:02, 14.11it/s, loss=0.756, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   5%|▌         | 51/938 [00:03<01:02, 14.11it/s, loss=0.769, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   6%|▌         | 52/938 [00:03<01:02, 14.13it/s, loss=0.776, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   6%|▌         | 53/938 [00:03<01:02, 14.18it/s, loss=0.772, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   6%|▌         | 54/938 [00:03<01:02, 14.13it/s, loss=0.772, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   6%|▌         | 54/938 [00:03<01:02, 14.13it/s, loss=0.773, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   6%|▌         | 55/938 [00:03<01:02, 14.11it/s, loss=0.779, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   6%|▌         | 56/938 [00:03<01:02, 14.11it/s, loss=0.781, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   6%|▌         | 57/938 [00:04<01:02, 14.04it/s, loss=0.781, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   6%|▌         | 57/938 [00:04<01:02, 14.03it/s, loss=0.773, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   6%|▌         | 58/938 [00:04<01:02, 14.04it/s, loss=0.773, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   6%|▋         | 59/938 [00:04<01:02, 14.03it/s, loss=0.77, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:   6%|▋         | 60/938 [00:04<01:02, 14.07it/s, loss=0.77, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   6%|▋         | 60/938 [00:04<01:02, 14.07it/s, loss=0.779, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   7%|▋         | 61/938 [00:04<01:02, 14.06it/s, loss=0.787, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   7%|▋         | 62/938 [00:04<01:02, 14.06it/s, loss=0.782, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   7%|▋         | 63/938 [00:04<01:02, 14.01it/s, loss=0.782, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   7%|▋         | 63/938 [00:04<01:02, 14.01it/s, loss=0.778, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   7%|▋         | 64/938 [00:04<01:02, 14.01it/s, loss=0.775, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   7%|▋         | 65/938 [00:04<01:02, 14.05it/s, loss=0.792, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   7%|▋         | 66/938 [00:04<01:02, 14.06it/s, loss=0.792, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   7%|▋         | 66/938 [00:04<01:02, 14.06it/s, loss=0.794, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   7%|▋         | 67/938 [00:04<01:01, 14.06it/s, loss=0.793, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   7%|▋         | 68/938 [00:04<01:01, 14.06it/s, loss=0.794, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   7%|▋         | 69/938 [00:04<01:01, 14.05it/s, loss=0.794, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   7%|▋         | 69/938 [00:04<01:01, 14.04it/s, loss=0.79, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:   7%|▋         | 70/938 [00:04<01:01, 14.00it/s, loss=0.783, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   8%|▊         | 71/938 [00:05<01:01, 13.99it/s, loss=0.783, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   8%|▊         | 72/938 [00:05<01:01, 13.98it/s, loss=0.783, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   8%|▊         | 72/938 [00:05<01:01, 13.98it/s, loss=0.788, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   8%|▊         | 73/938 [00:05<01:01, 13.96it/s, loss=0.788, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   8%|▊         | 74/938 [00:05<01:01, 14.01it/s, loss=0.782, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   8%|▊         | 75/938 [00:05<01:01, 14.00it/s, loss=0.782, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   8%|▊         | 75/938 [00:05<01:01, 14.00it/s, loss=0.787, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   8%|▊         | 76/938 [00:05<01:01, 13.99it/s, loss=0.793, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   8%|▊         | 77/938 [00:05<01:01, 13.97it/s, loss=0.785, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   8%|▊         | 78/938 [00:05<01:01, 13.96it/s, loss=0.785, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   8%|▊         | 78/938 [00:05<01:01, 13.96it/s, loss=0.794, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   8%|▊         | 79/938 [00:05<01:01, 13.96it/s, loss=0.813, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   9%|▊         | 80/938 [00:05<01:01, 13.97it/s, loss=0.804, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   9%|▊         | 81/938 [00:05<01:01, 13.97it/s, loss=0.804, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   9%|▊         | 81/938 [00:05<01:01, 13.97it/s, loss=0.808, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   9%|▊         | 82/938 [00:05<01:01, 13.96it/s, loss=0.808, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   9%|▉         | 83/938 [00:05<01:01, 13.97it/s, loss=0.814, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   9%|▉         | 84/938 [00:06<01:01, 13.96it/s, loss=0.814, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   9%|▉         | 84/938 [00:06<01:01, 13.96it/s, loss=0.811, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   9%|▉         | 85/938 [00:06<01:01, 13.97it/s, loss=0.79, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:   9%|▉         | 86/938 [00:06<01:01, 13.96it/s, loss=0.793, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   9%|▉         | 87/938 [00:06<01:01, 13.93it/s, loss=0.793, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   9%|▉         | 87/938 [00:06<01:01, 13.93it/s, loss=0.785, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   9%|▉         | 88/938 [00:06<01:01, 13.93it/s, loss=0.791, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:   9%|▉         | 89/938 [00:06<01:01, 13.82it/s, loss=0.794, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  10%|▉         | 90/938 [00:06<01:01, 13.83it/s, loss=0.794, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  10%|▉         | 90/938 [00:06<01:01, 13.83it/s, loss=0.795, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  10%|▉         | 91/938 [00:06<01:01, 13.83it/s, loss=0.785, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  10%|▉         | 92/938 [00:06<01:01, 13.86it/s, loss=0.781, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  10%|▉         | 93/938 [00:06<01:01, 13.84it/s, loss=0.781, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  10%|▉         | 93/938 [00:06<01:01, 13.84it/s, loss=0.78, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  10%|█         | 94/938 [00:06<01:00, 13.86it/s, loss=0.783, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  10%|█         | 95/938 [00:06<01:00, 13.88it/s, loss=0.772, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  10%|█         | 96/938 [00:06<01:00, 13.87it/s, loss=0.772, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  10%|█         | 96/938 [00:06<01:00, 13.87it/s, loss=0.762, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  10%|█         | 97/938 [00:07<01:00, 13.84it/s, loss=0.768, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  10%|█         | 98/938 [00:07<01:00, 13.87it/s, loss=0.764, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  11%|█         | 99/938 [00:07<01:00, 13.87it/s, loss=0.764, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  11%|█         | 99/938 [00:07<01:00, 13.87it/s, loss=0.744, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  11%|█         | 100/938 [00:07<01:00, 13.86it/s, loss=0.747, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  11%|█         | 101/938 [00:07<01:00, 13.89it/s, loss=0.745, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  11%|█         | 102/938 [00:07<01:00, 13.88it/s, loss=0.745, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  11%|█         | 102/938 [00:07<01:00, 13.87it/s, loss=0.749, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  11%|█         | 103/938 [00:07<01:00, 13.87it/s, loss=0.758, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  11%|█         | 104/938 [00:07<01:00, 13.87it/s, loss=0.751, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  11%|█         | 105/938 [00:07<00:59, 13.89it/s, loss=0.751, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  11%|█         | 105/938 [00:07<00:59, 13.88it/s, loss=0.761, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  11%|█▏        | 106/938 [00:07<01:00, 13.81it/s, loss=0.759, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  11%|█▏        | 107/938 [00:07<01:00, 13.85it/s, loss=0.763, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  12%|█▏        | 108/938 [00:07<01:00, 13.83it/s, loss=0.763, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  12%|█▏        | 108/938 [00:07<01:00, 13.83it/s, loss=0.757, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  12%|█▏        | 109/938 [00:07<00:59, 13.85it/s, loss=0.754, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  12%|█▏        | 110/938 [00:07<00:59, 13.86it/s, loss=0.749, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  12%|█▏        | 111/938 [00:08<00:59, 13.85it/s, loss=0.749, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  12%|█▏        | 111/938 [00:08<00:59, 13.85it/s, loss=0.748, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  12%|█▏        | 112/938 [00:08<00:59, 13.86it/s, loss=0.738, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  12%|█▏        | 113/938 [00:08<00:59, 13.84it/s, loss=0.736, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  12%|█▏        | 114/938 [00:08<00:59, 13.83it/s, loss=0.736, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  12%|█▏        | 114/938 [00:08<00:59, 13.83it/s, loss=0.736, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  12%|█▏        | 115/938 [00:08<00:59, 13.83it/s, loss=0.732, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  12%|█▏        | 116/938 [00:08<00:59, 13.85it/s, loss=0.728, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  12%|█▏        | 117/938 [00:08<00:59, 13.83it/s, loss=0.728, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  12%|█▏        | 117/938 [00:08<00:59, 13.83it/s, loss=0.728, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  13%|█▎        | 118/938 [00:08<00:59, 13.82it/s, loss=0.732, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  13%|█▎        | 119/938 [00:08<00:59, 13.83it/s, loss=0.738, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  13%|█▎        | 120/938 [00:08<00:59, 13.79it/s, loss=0.738, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  13%|█▎        | 120/938 [00:08<00:59, 13.79it/s, loss=0.741, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  13%|█▎        | 121/938 [00:08<00:59, 13.80it/s, loss=0.751, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  13%|█▎        | 122/938 [00:08<00:59, 13.81it/s, loss=0.75, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  13%|█▎        | 123/938 [00:08<00:59, 13.80it/s, loss=0.75, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  13%|█▎        | 123/938 [00:08<00:59, 13.80it/s, loss=0.75, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  13%|█▎        | 124/938 [00:09<00:59, 13.77it/s, loss=0.759, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  13%|█▎        | 125/938 [00:09<00:59, 13.76it/s, loss=0.753, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  13%|█▎        | 126/938 [00:09<00:59, 13.74it/s, loss=0.753, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  13%|█▎        | 126/938 [00:09<00:59, 13.74it/s, loss=0.754, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  14%|█▎        | 127/938 [00:09<00:58, 13.76it/s, loss=0.756, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  14%|█▎        | 128/938 [00:09<00:58, 13.76it/s, loss=0.764, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  14%|█▍        | 129/938 [00:09<00:58, 13.75it/s, loss=0.764, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  14%|█▍        | 129/938 [00:09<00:58, 13.75it/s, loss=0.768, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  14%|█▍        | 130/938 [00:09<00:58, 13.77it/s, loss=0.778, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  14%|█▍        | 131/938 [00:09<00:58, 13.78it/s, loss=0.788, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  14%|█▍        | 132/938 [00:09<00:58, 13.79it/s, loss=0.788, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  14%|█▍        | 132/938 [00:09<00:58, 13.79it/s, loss=0.796, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  14%|█▍        | 133/938 [00:09<00:58, 13.78it/s, loss=0.807, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  14%|█▍        | 134/938 [00:09<00:58, 13.77it/s, loss=0.814, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  14%|█▍        | 135/938 [00:09<00:58, 13.78it/s, loss=0.814, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  14%|█▍        | 135/938 [00:09<00:58, 13.78it/s, loss=0.817, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  14%|█▍        | 136/938 [00:09<00:58, 13.76it/s, loss=0.825, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  15%|█▍        | 137/938 [00:09<00:58, 13.75it/s, loss=0.825, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  15%|█▍        | 138/938 [00:10<00:58, 13.77it/s, loss=0.825, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  15%|█▍        | 138/938 [00:10<00:58, 13.76it/s, loss=0.829, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  15%|█▍        | 139/938 [00:10<00:58, 13.74it/s, loss=0.825, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  15%|█▍        | 140/938 [00:10<00:57, 13.76it/s, loss=0.817, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  15%|█▌        | 141/938 [00:10<00:57, 13.76it/s, loss=0.817, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  15%|█▌        | 141/938 [00:10<00:57, 13.76it/s, loss=0.798, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  15%|█▌        | 142/938 [00:10<00:57, 13.76it/s, loss=0.798, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  15%|█▌        | 143/938 [00:10<00:57, 13.78it/s, loss=0.786, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  15%|█▌        | 144/938 [00:10<00:57, 13.78it/s, loss=0.786, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  15%|█▌        | 144/938 [00:10<00:57, 13.78it/s, loss=0.783, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  15%|█▌        | 145/938 [00:10<00:57, 13.80it/s, loss=0.781, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  16%|█▌        | 146/938 [00:10<00:57, 13.79it/s, loss=0.775, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  16%|█▌        | 147/938 [00:10<00:57, 13.78it/s, loss=0.775, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  16%|█▌        | 147/938 [00:10<00:57, 13.78it/s, loss=0.768, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  16%|█▌        | 148/938 [00:10<00:57, 13.77it/s, loss=0.757, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  16%|█▌        | 149/938 [00:10<00:57, 13.76it/s, loss=0.766, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  16%|█▌        | 150/938 [00:10<00:57, 13.78it/s, loss=0.766, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  16%|█▌        | 150/938 [00:10<00:57, 13.78it/s, loss=0.763, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  16%|█▌        | 151/938 [00:10<00:57, 13.81it/s, loss=0.758, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  16%|█▌        | 152/938 [00:10<00:56, 13.82it/s, loss=0.744, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  16%|█▋        | 153/938 [00:11<00:56, 13.83it/s, loss=0.744, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  16%|█▋        | 153/938 [00:11<00:56, 13.83it/s, loss=0.741, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  16%|█▋        | 154/938 [00:11<00:56, 13.82it/s, loss=0.736, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  17%|█▋        | 155/938 [00:11<00:56, 13.81it/s, loss=0.735, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  17%|█▋        | 156/938 [00:11<00:56, 13.81it/s, loss=0.735, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  17%|█▋        | 156/938 [00:11<00:56, 13.81it/s, loss=0.736, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  17%|█▋        | 157/938 [00:11<00:56, 13.83it/s, loss=0.731, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  17%|█▋        | 158/938 [00:11<00:56, 13.85it/s, loss=0.719, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  17%|█▋        | 159/938 [00:11<00:56, 13.87it/s, loss=0.719, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  17%|█▋        | 159/938 [00:11<00:56, 13.87it/s, loss=0.716, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  17%|█▋        | 160/938 [00:11<00:56, 13.88it/s, loss=0.717, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  17%|█▋        | 161/938 [00:11<00:56, 13.86it/s, loss=0.718, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  17%|█▋        | 162/938 [00:11<00:55, 13.86it/s, loss=0.718, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  17%|█▋        | 162/938 [00:11<00:55, 13.86it/s, loss=0.725, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  17%|█▋        | 163/938 [00:11<00:55, 13.85it/s, loss=0.725, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  17%|█▋        | 164/938 [00:11<00:56, 13.81it/s, loss=0.722, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  18%|█▊        | 165/938 [00:11<00:55, 13.81it/s, loss=0.722, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  18%|█▊        | 165/938 [00:11<00:55, 13.81it/s, loss=0.725, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  18%|█▊        | 166/938 [00:12<00:55, 13.81it/s, loss=0.73, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  18%|█▊        | 167/938 [00:12<00:55, 13.82it/s, loss=0.734, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  18%|█▊        | 168/938 [00:12<00:55, 13.83it/s, loss=0.734, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  18%|█▊        | 168/938 [00:12<00:55, 13.83it/s, loss=0.739, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  18%|█▊        | 169/938 [00:12<00:55, 13.83it/s, loss=0.73, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  18%|█▊        | 170/938 [00:12<00:55, 13.82it/s, loss=0.736, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  18%|█▊        | 171/938 [00:12<00:55, 13.82it/s, loss=0.736, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  18%|█▊        | 171/938 [00:12<00:55, 13.82it/s, loss=0.734, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  18%|█▊        | 172/938 [00:12<00:55, 13.82it/s, loss=0.746, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  18%|█▊        | 173/938 [00:12<00:55, 13.77it/s, loss=0.749, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  19%|█▊        | 174/938 [00:12<00:55, 13.75it/s, loss=0.749, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  19%|█▊        | 174/938 [00:12<00:55, 13.75it/s, loss=0.748, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  19%|█▊        | 175/938 [00:12<00:55, 13.75it/s, loss=0.747, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  19%|█▉        | 176/938 [00:12<00:55, 13.74it/s, loss=0.747, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  19%|█▉        | 177/938 [00:12<00:55, 13.74it/s, loss=0.747, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  19%|█▉        | 177/938 [00:12<00:55, 13.74it/s, loss=0.752, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  19%|█▉        | 178/938 [00:12<00:55, 13.75it/s, loss=0.755, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  19%|█▉        | 179/938 [00:13<00:55, 13.76it/s, loss=0.754, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  19%|█▉        | 180/938 [00:13<00:55, 13.76it/s, loss=0.754, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  19%|█▉        | 180/938 [00:13<00:55, 13.76it/s, loss=0.748, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  19%|█▉        | 181/938 [00:13<00:55, 13.74it/s, loss=0.746, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  19%|█▉        | 182/938 [00:13<00:55, 13.74it/s, loss=0.733, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  20%|█▉        | 183/938 [00:13<00:54, 13.74it/s, loss=0.733, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  20%|█▉        | 183/938 [00:13<00:54, 13.74it/s, loss=0.742, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  20%|█▉        | 184/938 [00:13<00:54, 13.73it/s, loss=0.749, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  20%|█▉        | 185/938 [00:13<00:54, 13.73it/s, loss=0.745, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  20%|█▉        | 186/938 [00:13<00:54, 13.72it/s, loss=0.745, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  20%|█▉        | 186/938 [00:13<00:54, 13.72it/s, loss=0.743, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  20%|█▉        | 187/938 [00:13<00:54, 13.73it/s, loss=0.743, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  20%|██        | 188/938 [00:13<00:54, 13.71it/s, loss=0.745, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  20%|██        | 189/938 [00:13<00:54, 13.70it/s, loss=0.745, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  20%|██        | 189/938 [00:13<00:54, 13.70it/s, loss=0.749, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  20%|██        | 190/938 [00:13<00:54, 13.69it/s, loss=0.743, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  20%|██        | 191/938 [00:13<00:54, 13.69it/s, loss=0.75, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  20%|██        | 192/938 [00:14<00:54, 13.69it/s, loss=0.75, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  20%|██        | 192/938 [00:14<00:54, 13.69it/s, loss=0.74, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  21%|██        | 193/938 [00:14<00:54, 13.69it/s, loss=0.73, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  21%|██        | 194/938 [00:14<00:54, 13.70it/s, loss=0.738, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  21%|██        | 195/938 [00:14<00:54, 13.70it/s, loss=0.738, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  21%|██        | 195/938 [00:14<00:54, 13.70it/s, loss=0.74, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  21%|██        | 196/938 [00:14<00:54, 13.71it/s, loss=0.735, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  21%|██        | 197/938 [00:14<00:54, 13.70it/s, loss=0.73, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  21%|██        | 198/938 [00:14<00:54, 13.70it/s, loss=0.73, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  21%|██        | 198/938 [00:14<00:54, 13.70it/s, loss=0.73, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  21%|██        | 199/938 [00:14<00:54, 13.68it/s, loss=0.742, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  21%|██▏       | 200/938 [00:14<00:53, 13.69it/s, loss=0.752, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  21%|██▏       | 201/938 [00:14<00:53, 13.67it/s, loss=0.752, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  21%|██▏       | 201/938 [00:14<00:53, 13.67it/s, loss=0.766, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  22%|██▏       | 202/938 [00:14<00:53, 13.68it/s, loss=0.763, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  22%|██▏       | 203/938 [00:14<00:53, 13.68it/s, loss=0.756, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  22%|██▏       | 204/938 [00:14<00:53, 13.69it/s, loss=0.756, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  22%|██▏       | 204/938 [00:14<00:53, 13.69it/s, loss=0.752, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  22%|██▏       | 205/938 [00:14<00:53, 13.70it/s, loss=0.756, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  22%|██▏       | 206/938 [00:15<00:53, 13.69it/s, loss=0.753, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  22%|██▏       | 207/938 [00:15<00:53, 13.69it/s, loss=0.753, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  22%|██▏       | 207/938 [00:15<00:53, 13.69it/s, loss=0.753, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  22%|██▏       | 208/938 [00:15<00:53, 13.70it/s, loss=0.743, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  22%|██▏       | 209/938 [00:15<00:53, 13.69it/s, loss=0.74, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  22%|██▏       | 210/938 [00:15<00:53, 13.70it/s, loss=0.74, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  22%|██▏       | 210/938 [00:15<00:53, 13.70it/s, loss=0.733, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  22%|██▏       | 211/938 [00:15<00:53, 13.69it/s, loss=0.726, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  23%|██▎       | 212/938 [00:15<00:53, 13.70it/s, loss=0.724, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  23%|██▎       | 213/938 [00:15<00:52, 13.70it/s, loss=0.724, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  23%|██▎       | 213/938 [00:15<00:52, 13.70it/s, loss=0.725, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  23%|██▎       | 214/938 [00:15<00:52, 13.71it/s, loss=0.717, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  23%|██▎       | 215/938 [00:15<00:52, 13.70it/s, loss=0.713, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  23%|██▎       | 216/938 [00:15<00:52, 13.71it/s, loss=0.713, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  23%|██▎       | 216/938 [00:15<00:52, 13.71it/s, loss=0.715, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  23%|██▎       | 217/938 [00:15<00:52, 13.72it/s, loss=0.726, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  23%|██▎       | 218/938 [00:15<00:52, 13.72it/s, loss=0.724, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  23%|██▎       | 219/938 [00:15<00:52, 13.72it/s, loss=0.724, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  23%|██▎       | 219/938 [00:15<00:52, 13.72it/s, loss=0.72, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  23%|██▎       | 220/938 [00:16<00:52, 13.71it/s, loss=0.72, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  24%|██▎       | 221/938 [00:16<00:52, 13.71it/s, loss=0.712, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  24%|██▎       | 222/938 [00:16<00:52, 13.71it/s, loss=0.712, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  24%|██▎       | 222/938 [00:16<00:52, 13.71it/s, loss=0.713, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  24%|██▍       | 223/938 [00:16<00:52, 13.72it/s, loss=0.712, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  24%|██▍       | 224/938 [00:16<00:52, 13.71it/s, loss=0.72, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  24%|██▍       | 225/938 [00:16<00:51, 13.72it/s, loss=0.72, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  24%|██▍       | 225/938 [00:16<00:51, 13.72it/s, loss=0.715, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  24%|██▍       | 226/938 [00:16<00:51, 13.73it/s, loss=0.713, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  24%|██▍       | 227/938 [00:16<00:51, 13.72it/s, loss=0.71, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  24%|██▍       | 228/938 [00:16<00:51, 13.73it/s, loss=0.71, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  24%|██▍       | 228/938 [00:16<00:51, 13.73it/s, loss=0.724, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  24%|██▍       | 229/938 [00:16<00:51, 13.74it/s, loss=0.72, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  25%|██▍       | 230/938 [00:16<00:51, 13.74it/s, loss=0.722, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  25%|██▍       | 231/938 [00:16<00:51, 13.74it/s, loss=0.722, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  25%|██▍       | 231/938 [00:16<00:51, 13.74it/s, loss=0.716, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  25%|██▍       | 232/938 [00:16<00:51, 13.74it/s, loss=0.721, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  25%|██▍       | 233/938 [00:16<00:51, 13.75it/s, loss=0.725, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  25%|██▍       | 234/938 [00:17<00:51, 13.74it/s, loss=0.725, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  25%|██▍       | 234/938 [00:17<00:51, 13.74it/s, loss=0.73, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  25%|██▌       | 235/938 [00:17<00:51, 13.74it/s, loss=0.733, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  25%|██▌       | 236/938 [00:17<00:51, 13.74it/s, loss=0.735, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  25%|██▌       | 237/938 [00:17<00:51, 13.75it/s, loss=0.735, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  25%|██▌       | 237/938 [00:17<00:51, 13.74it/s, loss=0.727, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  25%|██▌       | 238/938 [00:17<00:50, 13.74it/s, loss=0.728, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  25%|██▌       | 239/938 [00:17<00:50, 13.74it/s, loss=0.73, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  26%|██▌       | 240/938 [00:17<00:50, 13.75it/s, loss=0.73, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  26%|██▌       | 240/938 [00:17<00:50, 13.75it/s, loss=0.724, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  26%|██▌       | 241/938 [00:17<00:50, 13.75it/s, loss=0.725, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  26%|██▌       | 242/938 [00:17<00:50, 13.76it/s, loss=0.721, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  26%|██▌       | 243/938 [00:17<00:50, 13.76it/s, loss=0.721, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  26%|██▌       | 243/938 [00:17<00:50, 13.75it/s, loss=0.727, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  26%|██▌       | 244/938 [00:17<00:50, 13.76it/s, loss=0.722, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  26%|██▌       | 245/938 [00:17<00:50, 13.76it/s, loss=0.726, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  26%|██▌       | 246/938 [00:17<00:50, 13.77it/s, loss=0.726, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  26%|██▌       | 246/938 [00:17<00:50, 13.77it/s, loss=0.731, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  26%|██▋       | 247/938 [00:17<00:50, 13.76it/s, loss=0.727, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  26%|██▋       | 248/938 [00:18<00:50, 13.76it/s, loss=0.718, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  27%|██▋       | 249/938 [00:18<00:50, 13.74it/s, loss=0.718, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  27%|██▋       | 249/938 [00:18<00:50, 13.73it/s, loss=0.713, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  27%|██▋       | 250/938 [00:18<00:50, 13.73it/s, loss=0.716, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  27%|██▋       | 251/938 [00:18<00:50, 13.72it/s, loss=0.72, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  27%|██▋       | 252/938 [00:18<00:49, 13.72it/s, loss=0.72, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  27%|██▋       | 252/938 [00:18<00:49, 13.72it/s, loss=0.718, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  27%|██▋       | 253/938 [00:18<00:49, 13.73it/s, loss=0.711, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  27%|██▋       | 254/938 [00:18<00:49, 13.73it/s, loss=0.71, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  27%|██▋       | 255/938 [00:18<00:49, 13.73it/s, loss=0.71, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  27%|██▋       | 255/938 [00:18<00:49, 13.73it/s, loss=0.702, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  27%|██▋       | 256/938 [00:18<00:49, 13.74it/s, loss=0.699, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  27%|██▋       | 257/938 [00:18<00:49, 13.74it/s, loss=0.689, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  28%|██▊       | 258/938 [00:18<00:49, 13.75it/s, loss=0.689, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  28%|██▊       | 258/938 [00:18<00:49, 13.75it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  28%|██▊       | 259/938 [00:18<00:49, 13.75it/s, loss=0.684, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  28%|██▊       | 260/938 [00:18<00:49, 13.75it/s, loss=0.679, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  28%|██▊       | 261/938 [00:19<00:49, 13.74it/s, loss=0.679, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  28%|██▊       | 261/938 [00:19<00:49, 13.73it/s, loss=0.676, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  28%|██▊       | 262/938 [00:19<00:49, 13.74it/s, loss=0.683, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  28%|██▊       | 263/938 [00:19<00:49, 13.73it/s, loss=0.681, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  28%|██▊       | 264/938 [00:19<00:49, 13.74it/s, loss=0.681, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  28%|██▊       | 264/938 [00:19<00:49, 13.74it/s, loss=0.669, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  28%|██▊       | 265/938 [00:19<00:48, 13.74it/s, loss=0.669, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  28%|██▊       | 266/938 [00:19<00:48, 13.73it/s, loss=0.663, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  28%|██▊       | 267/938 [00:19<00:48, 13.74it/s, loss=0.663, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  28%|██▊       | 267/938 [00:19<00:48, 13.74it/s, loss=0.667, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  29%|██▊       | 268/938 [00:19<00:48, 13.74it/s, loss=0.668, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  29%|██▊       | 269/938 [00:19<00:48, 13.74it/s, loss=0.669, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  29%|██▉       | 270/938 [00:19<00:48, 13.74it/s, loss=0.669, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  29%|██▉       | 270/938 [00:19<00:48, 13.74it/s, loss=0.668, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  29%|██▉       | 271/938 [00:19<00:48, 13.74it/s, loss=0.67, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  29%|██▉       | 272/938 [00:19<00:48, 13.73it/s, loss=0.67, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  29%|██▉       | 273/938 [00:19<00:48, 13.73it/s, loss=0.67, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  29%|██▉       | 273/938 [00:19<00:48, 13.73it/s, loss=0.678, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  29%|██▉       | 274/938 [00:19<00:48, 13.73it/s, loss=0.682, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  29%|██▉       | 275/938 [00:20<00:48, 13.74it/s, loss=0.687, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  29%|██▉       | 276/938 [00:20<00:48, 13.74it/s, loss=0.687, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  29%|██▉       | 276/938 [00:20<00:48, 13.74it/s, loss=0.685, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  30%|██▉       | 277/938 [00:20<00:48, 13.74it/s, loss=0.692, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  30%|██▉       | 278/938 [00:20<00:48, 13.74it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  30%|██▉       | 279/938 [00:20<00:47, 13.73it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  30%|██▉       | 279/938 [00:20<00:47, 13.73it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  30%|██▉       | 280/938 [00:20<00:47, 13.73it/s, loss=0.688, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  30%|██▉       | 281/938 [00:20<00:47, 13.74it/s, loss=0.693, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  30%|███       | 282/938 [00:20<00:47, 13.73it/s, loss=0.693, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  30%|███       | 282/938 [00:20<00:47, 13.73it/s, loss=0.689, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  30%|███       | 283/938 [00:20<00:47, 13.73it/s, loss=0.688, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  30%|███       | 284/938 [00:20<00:47, 13.73it/s, loss=0.693, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  30%|███       | 285/938 [00:20<00:47, 13.72it/s, loss=0.693, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  30%|███       | 285/938 [00:20<00:47, 13.72it/s, loss=0.689, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  30%|███       | 286/938 [00:20<00:47, 13.73it/s, loss=0.684, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  31%|███       | 287/938 [00:20<00:47, 13.73it/s, loss=0.684, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  31%|███       | 288/938 [00:20<00:47, 13.72it/s, loss=0.684, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  31%|███       | 288/938 [00:20<00:47, 13.72it/s, loss=0.682, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  31%|███       | 289/938 [00:21<00:47, 13.72it/s, loss=0.685, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  31%|███       | 290/938 [00:21<00:47, 13.72it/s, loss=0.678, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  31%|███       | 291/938 [00:21<00:47, 13.72it/s, loss=0.678, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  31%|███       | 291/938 [00:21<00:47, 13.72it/s, loss=0.677, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  31%|███       | 292/938 [00:21<00:47, 13.73it/s, loss=0.682, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  31%|███       | 293/938 [00:21<00:46, 13.73it/s, loss=0.691, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  31%|███▏      | 294/938 [00:21<00:46, 13.73it/s, loss=0.691, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  31%|███▏      | 294/938 [00:21<00:46, 13.73it/s, loss=0.686, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  31%|███▏      | 295/938 [00:21<00:46, 13.73it/s, loss=0.683, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  32%|███▏      | 296/938 [00:21<00:46, 13.73it/s, loss=0.685, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  32%|███▏      | 297/938 [00:21<00:46, 13.73it/s, loss=0.685, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  32%|███▏      | 297/938 [00:21<00:46, 13.73it/s, loss=0.688, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  32%|███▏      | 298/938 [00:21<00:46, 13.74it/s, loss=0.692, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  32%|███▏      | 299/938 [00:21<00:46, 13.73it/s, loss=0.697, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  32%|███▏      | 300/938 [00:21<00:46, 13.73it/s, loss=0.697, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  32%|███▏      | 300/938 [00:21<00:46, 13.73it/s, loss=0.704, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  32%|███▏      | 301/938 [00:21<00:46, 13.73it/s, loss=0.708, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  32%|███▏      | 302/938 [00:21<00:46, 13.74it/s, loss=0.709, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  32%|███▏      | 303/938 [00:22<00:46, 13.73it/s, loss=0.709, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  32%|███▏      | 303/938 [00:22<00:46, 13.73it/s, loss=0.712, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  32%|███▏      | 304/938 [00:22<00:46, 13.74it/s, loss=0.712, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  33%|███▎      | 305/938 [00:22<00:46, 13.71it/s, loss=0.716, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  33%|███▎      | 306/938 [00:22<00:46, 13.71it/s, loss=0.716, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  33%|███▎      | 306/938 [00:22<00:46, 13.71it/s, loss=0.724, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  33%|███▎      | 307/938 [00:22<00:45, 13.72it/s, loss=0.727, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  33%|███▎      | 308/938 [00:22<00:45, 13.72it/s, loss=0.732, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  33%|███▎      | 309/938 [00:22<00:45, 13.72it/s, loss=0.732, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  33%|███▎      | 309/938 [00:22<00:45, 13.71it/s, loss=0.726, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  33%|███▎      | 310/938 [00:22<00:45, 13.72it/s, loss=0.732, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  33%|███▎      | 311/938 [00:22<00:45, 13.72it/s, loss=0.725, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  33%|███▎      | 312/938 [00:22<00:45, 13.72it/s, loss=0.725, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  33%|███▎      | 312/938 [00:22<00:45, 13.72it/s, loss=0.717, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  33%|███▎      | 313/938 [00:22<00:45, 13.73it/s, loss=0.704, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  33%|███▎      | 314/938 [00:22<00:45, 13.73it/s, loss=0.707, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  34%|███▎      | 315/938 [00:22<00:45, 13.73it/s, loss=0.707, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  34%|███▎      | 315/938 [00:22<00:45, 13.73it/s, loss=0.709, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  34%|███▎      | 316/938 [00:23<00:45, 13.73it/s, loss=0.705, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  34%|███▍      | 317/938 [00:23<00:45, 13.72it/s, loss=0.703, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  34%|███▍      | 318/938 [00:23<00:45, 13.72it/s, loss=0.703, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  34%|███▍      | 318/938 [00:23<00:45, 13.72it/s, loss=0.705, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  34%|███▍      | 319/938 [00:23<00:45, 13.73it/s, loss=0.702, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  34%|███▍      | 320/938 [00:23<00:45, 13.73it/s, loss=0.697, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  34%|███▍      | 321/938 [00:23<00:44, 13.73it/s, loss=0.697, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  34%|███▍      | 321/938 [00:23<00:44, 13.73it/s, loss=0.704, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  34%|███▍      | 322/938 [00:23<00:44, 13.72it/s, loss=0.702, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  34%|███▍      | 323/938 [00:23<00:44, 13.72it/s, loss=0.694, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  35%|███▍      | 324/938 [00:23<00:44, 13.72it/s, loss=0.694, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  35%|███▍      | 324/938 [00:23<00:44, 13.72it/s, loss=0.708, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  35%|███▍      | 325/938 [00:23<00:44, 13.72it/s, loss=0.706, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  35%|███▍      | 326/938 [00:23<00:44, 13.73it/s, loss=0.703, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  35%|███▍      | 327/938 [00:23<00:44, 13.73it/s, loss=0.703, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  35%|███▍      | 327/938 [00:23<00:44, 13.73it/s, loss=0.7, v_num=11, val_rmse=0.618, train_rmse=1.190]  
Epoch 1:  35%|███▍      | 328/938 [00:23<00:44, 13.73it/s, loss=0.699, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  35%|███▌      | 329/938 [00:23<00:44, 13.72it/s, loss=0.702, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  35%|███▌      | 330/938 [00:24<00:44, 13.71it/s, loss=0.702, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  35%|███▌      | 330/938 [00:24<00:44, 13.71it/s, loss=0.7, v_num=11, val_rmse=0.618, train_rmse=1.190]  
Epoch 1:  35%|███▌      | 331/938 [00:24<00:44, 13.72it/s, loss=0.707, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  35%|███▌      | 332/938 [00:24<00:44, 13.71it/s, loss=0.708, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  36%|███▌      | 333/938 [00:24<00:44, 13.71it/s, loss=0.708, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  36%|███▌      | 333/938 [00:24<00:44, 13.71it/s, loss=0.709, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  36%|███▌      | 334/938 [00:24<00:44, 13.72it/s, loss=0.699, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  36%|███▌      | 335/938 [00:24<00:43, 13.71it/s, loss=0.696, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  36%|███▌      | 336/938 [00:24<00:43, 13.72it/s, loss=0.696, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  36%|███▌      | 336/938 [00:24<00:43, 13.72it/s, loss=0.698, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  36%|███▌      | 337/938 [00:24<00:43, 13.72it/s, loss=0.697, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  36%|███▌      | 338/938 [00:24<00:43, 13.72it/s, loss=0.684, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  36%|███▌      | 339/938 [00:24<00:43, 13.72it/s, loss=0.684, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  36%|███▌      | 339/938 [00:24<00:43, 13.72it/s, loss=0.686, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  36%|███▌      | 340/938 [00:24<00:43, 13.72it/s, loss=0.694, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  36%|███▋      | 341/938 [00:24<00:43, 13.72it/s, loss=0.678, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  36%|███▋      | 342/938 [00:24<00:43, 13.72it/s, loss=0.678, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  36%|███▋      | 342/938 [00:24<00:43, 13.72it/s, loss=0.676, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  37%|███▋      | 343/938 [00:25<00:43, 13.71it/s, loss=0.678, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  37%|███▋      | 344/938 [00:25<00:43, 13.71it/s, loss=0.662, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  37%|███▋      | 345/938 [00:25<00:43, 13.72it/s, loss=0.662, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  37%|███▋      | 345/938 [00:25<00:43, 13.72it/s, loss=0.661, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  37%|███▋      | 346/938 [00:25<00:43, 13.72it/s, loss=0.661, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  37%|███▋      | 347/938 [00:25<00:43, 13.71it/s, loss=0.654, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  37%|███▋      | 348/938 [00:25<00:43, 13.72it/s, loss=0.654, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  37%|███▋      | 348/938 [00:25<00:43, 13.72it/s, loss=0.662, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  37%|███▋      | 349/938 [00:25<00:42, 13.71it/s, loss=0.672, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  37%|███▋      | 350/938 [00:25<00:42, 13.71it/s, loss=0.675, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  37%|███▋      | 351/938 [00:25<00:42, 13.70it/s, loss=0.675, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  37%|███▋      | 351/938 [00:25<00:42, 13.70it/s, loss=0.676, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  38%|███▊      | 352/938 [00:25<00:42, 13.69it/s, loss=0.683, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  38%|███▊      | 353/938 [00:25<00:42, 13.69it/s, loss=0.683, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  38%|███▊      | 354/938 [00:25<00:42, 13.69it/s, loss=0.683, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  38%|███▊      | 354/938 [00:25<00:42, 13.69it/s, loss=0.682, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  38%|███▊      | 355/938 [00:25<00:42, 13.68it/s, loss=0.684, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  38%|███▊      | 356/938 [00:26<00:42, 13.68it/s, loss=0.693, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  38%|███▊      | 357/938 [00:26<00:42, 13.69it/s, loss=0.693, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  38%|███▊      | 357/938 [00:26<00:42, 13.69it/s, loss=0.692, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  38%|███▊      | 358/938 [00:26<00:42, 13.69it/s, loss=0.697, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  38%|███▊      | 359/938 [00:26<00:42, 13.69it/s, loss=0.694, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  38%|███▊      | 360/938 [00:26<00:42, 13.70it/s, loss=0.694, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  38%|███▊      | 360/938 [00:26<00:42, 13.70it/s, loss=0.688, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  38%|███▊      | 361/938 [00:26<00:42, 13.69it/s, loss=0.684, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  39%|███▊      | 362/938 [00:26<00:42, 13.69it/s, loss=0.692, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  39%|███▊      | 363/938 [00:26<00:41, 13.69it/s, loss=0.692, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  39%|███▊      | 363/938 [00:26<00:41, 13.69it/s, loss=0.695, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  39%|███▉      | 364/938 [00:26<00:41, 13.69it/s, loss=0.699, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  39%|███▉      | 365/938 [00:26<00:41, 13.69it/s, loss=0.705, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  39%|███▉      | 366/938 [00:26<00:41, 13.70it/s, loss=0.705, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  39%|███▉      | 366/938 [00:26<00:41, 13.70it/s, loss=0.703, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  39%|███▉      | 367/938 [00:26<00:41, 13.71it/s, loss=0.71, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  39%|███▉      | 368/938 [00:26<00:41, 13.70it/s, loss=0.706, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  39%|███▉      | 369/938 [00:26<00:41, 13.70it/s, loss=0.706, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  39%|███▉      | 369/938 [00:26<00:41, 13.70it/s, loss=0.705, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  39%|███▉      | 370/938 [00:27<00:41, 13.70it/s, loss=0.699, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  40%|███▉      | 371/938 [00:27<00:41, 13.70it/s, loss=0.703, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  40%|███▉      | 372/938 [00:27<00:41, 13.70it/s, loss=0.703, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  40%|███▉      | 372/938 [00:27<00:41, 13.70it/s, loss=0.697, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  40%|███▉      | 373/938 [00:27<00:41, 13.71it/s, loss=0.694, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  40%|███▉      | 374/938 [00:27<00:41, 13.71it/s, loss=0.701, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  40%|███▉      | 375/938 [00:27<00:41, 13.70it/s, loss=0.701, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  40%|███▉      | 375/938 [00:27<00:41, 13.70it/s, loss=0.697, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  40%|████      | 376/938 [00:27<00:40, 13.71it/s, loss=0.687, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  40%|████      | 377/938 [00:27<00:40, 13.70it/s, loss=0.689, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  40%|████      | 378/938 [00:27<00:40, 13.70it/s, loss=0.689, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  40%|████      | 378/938 [00:27<00:40, 13.70it/s, loss=0.693, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  40%|████      | 379/938 [00:27<00:40, 13.70it/s, loss=0.697, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  41%|████      | 380/938 [00:27<00:40, 13.71it/s, loss=0.697, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  41%|████      | 381/938 [00:27<00:40, 13.71it/s, loss=0.697, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  41%|████      | 381/938 [00:27<00:40, 13.71it/s, loss=0.699, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  41%|████      | 382/938 [00:27<00:40, 13.71it/s, loss=0.701, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  41%|████      | 383/938 [00:27<00:40, 13.72it/s, loss=0.696, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  41%|████      | 384/938 [00:27<00:40, 13.72it/s, loss=0.696, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  41%|████      | 384/938 [00:27<00:40, 13.72it/s, loss=0.702, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  41%|████      | 385/938 [00:28<00:40, 13.72it/s, loss=0.696, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  41%|████      | 386/938 [00:28<00:40, 13.72it/s, loss=0.713, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  41%|████▏     | 387/938 [00:28<00:40, 13.72it/s, loss=0.713, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  41%|████▏     | 387/938 [00:28<00:40, 13.72it/s, loss=0.712, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  41%|████▏     | 388/938 [00:28<00:40, 13.72it/s, loss=0.712, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  41%|████▏     | 389/938 [00:28<00:40, 13.72it/s, loss=0.706, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  42%|████▏     | 390/938 [00:28<00:39, 13.71it/s, loss=0.706, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  42%|████▏     | 390/938 [00:28<00:39, 13.71it/s, loss=0.717, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  42%|████▏     | 391/938 [00:28<00:39, 13.71it/s, loss=0.713, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  42%|████▏     | 392/938 [00:28<00:39, 13.71it/s, loss=0.718, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  42%|████▏     | 393/938 [00:28<00:39, 13.71it/s, loss=0.718, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  42%|████▏     | 393/938 [00:28<00:39, 13.71it/s, loss=0.716, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  42%|████▏     | 394/938 [00:28<00:39, 13.69it/s, loss=0.714, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  42%|████▏     | 395/938 [00:28<00:39, 13.70it/s, loss=0.728, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  42%|████▏     | 396/938 [00:28<00:39, 13.70it/s, loss=0.728, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  42%|████▏     | 396/938 [00:28<00:39, 13.70it/s, loss=0.735, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  42%|████▏     | 397/938 [00:28<00:39, 13.70it/s, loss=0.741, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  42%|████▏     | 398/938 [00:29<00:39, 13.70it/s, loss=0.74, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  43%|████▎     | 399/938 [00:29<00:39, 13.70it/s, loss=0.74, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  43%|████▎     | 399/938 [00:29<00:39, 13.70it/s, loss=0.742, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  43%|████▎     | 400/938 [00:29<00:39, 13.71it/s, loss=0.739, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  43%|████▎     | 401/938 [00:29<00:39, 13.71it/s, loss=0.745, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  43%|████▎     | 402/938 [00:29<00:39, 13.71it/s, loss=0.745, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  43%|████▎     | 402/938 [00:29<00:39, 13.71it/s, loss=0.738, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  43%|████▎     | 403/938 [00:29<00:39, 13.71it/s, loss=0.746, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  43%|████▎     | 404/938 [00:29<00:38, 13.71it/s, loss=0.738, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  43%|████▎     | 405/938 [00:29<00:38, 13.71it/s, loss=0.738, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  43%|████▎     | 405/938 [00:29<00:38, 13.71it/s, loss=0.735, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  43%|████▎     | 406/938 [00:29<00:38, 13.71it/s, loss=0.722, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  43%|████▎     | 407/938 [00:29<00:38, 13.72it/s, loss=0.722, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  43%|████▎     | 408/938 [00:29<00:38, 13.72it/s, loss=0.722, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  43%|████▎     | 408/938 [00:29<00:38, 13.72it/s, loss=0.711, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  44%|████▎     | 409/938 [00:29<00:38, 13.72it/s, loss=0.714, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  44%|████▎     | 410/938 [00:29<00:38, 13.72it/s, loss=0.702, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  44%|████▍     | 411/938 [00:29<00:38, 13.72it/s, loss=0.702, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  44%|████▍     | 411/938 [00:29<00:38, 13.72it/s, loss=0.695, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  44%|████▍     | 412/938 [00:30<00:38, 13.73it/s, loss=0.686, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  44%|████▍     | 413/938 [00:30<00:38, 13.73it/s, loss=0.688, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  44%|████▍     | 414/938 [00:30<00:38, 13.73it/s, loss=0.688, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  44%|████▍     | 414/938 [00:30<00:38, 13.73it/s, loss=0.685, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  44%|████▍     | 415/938 [00:30<00:38, 13.73it/s, loss=0.672, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  44%|████▍     | 416/938 [00:30<00:38, 13.74it/s, loss=0.666, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  44%|████▍     | 417/938 [00:30<00:37, 13.73it/s, loss=0.666, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  44%|████▍     | 417/938 [00:30<00:37, 13.73it/s, loss=0.656, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  45%|████▍     | 418/938 [00:30<00:37, 13.73it/s, loss=0.65, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  45%|████▍     | 419/938 [00:30<00:37, 13.73it/s, loss=0.643, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  45%|████▍     | 420/938 [00:30<00:37, 13.73it/s, loss=0.643, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  45%|████▍     | 420/938 [00:30<00:37, 13.73it/s, loss=0.648, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  45%|████▍     | 421/938 [00:30<00:37, 13.73it/s, loss=0.645, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  45%|████▍     | 422/938 [00:30<00:37, 13.72it/s, loss=0.65, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  45%|████▌     | 423/938 [00:30<00:37, 13.73it/s, loss=0.65, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  45%|████▌     | 423/938 [00:30<00:37, 13.73it/s, loss=0.65, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  45%|████▌     | 424/938 [00:30<00:37, 13.72it/s, loss=0.65, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  45%|████▌     | 425/938 [00:30<00:37, 13.72it/s, loss=0.652, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  45%|████▌     | 426/938 [00:31<00:37, 13.72it/s, loss=0.652, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  45%|████▌     | 426/938 [00:31<00:37, 13.72it/s, loss=0.657, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  46%|████▌     | 427/938 [00:31<00:37, 13.72it/s, loss=0.663, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  46%|████▌     | 428/938 [00:31<00:37, 13.72it/s, loss=0.666, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  46%|████▌     | 429/938 [00:31<00:37, 13.72it/s, loss=0.666, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  46%|████▌     | 429/938 [00:31<00:37, 13.72it/s, loss=0.657, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  46%|████▌     | 430/938 [00:31<00:37, 13.72it/s, loss=0.665, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  46%|████▌     | 431/938 [00:31<00:36, 13.73it/s, loss=0.67, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  46%|████▌     | 432/938 [00:31<00:36, 13.73it/s, loss=0.67, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  46%|████▌     | 432/938 [00:31<00:36, 13.73it/s, loss=0.671, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  46%|████▌     | 433/938 [00:31<00:36, 13.73it/s, loss=0.676, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  46%|████▋     | 434/938 [00:31<00:36, 13.73it/s, loss=0.682, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  46%|████▋     | 435/938 [00:31<00:36, 13.72it/s, loss=0.682, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  46%|████▋     | 435/938 [00:31<00:36, 13.72it/s, loss=0.687, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  46%|████▋     | 436/938 [00:31<00:36, 13.73it/s, loss=0.686, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  47%|████▋     | 437/938 [00:31<00:36, 13.73it/s, loss=0.702, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  47%|████▋     | 438/938 [00:31<00:36, 13.73it/s, loss=0.702, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  47%|████▋     | 438/938 [00:31<00:36, 13.73it/s, loss=0.715, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  47%|████▋     | 439/938 [00:31<00:36, 13.73it/s, loss=0.728, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  47%|████▋     | 440/938 [00:32<00:36, 13.73it/s, loss=0.731, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  47%|████▋     | 441/938 [00:32<00:36, 13.73it/s, loss=0.731, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  47%|████▋     | 441/938 [00:32<00:36, 13.73it/s, loss=0.734, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  47%|████▋     | 442/938 [00:32<00:36, 13.73it/s, loss=0.726, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  47%|████▋     | 443/938 [00:32<00:36, 13.73it/s, loss=0.719, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  47%|████▋     | 444/938 [00:32<00:35, 13.73it/s, loss=0.719, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  47%|████▋     | 444/938 [00:32<00:35, 13.73it/s, loss=0.72, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  47%|████▋     | 445/938 [00:32<00:35, 13.73it/s, loss=0.72, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  48%|████▊     | 446/938 [00:32<00:35, 13.74it/s, loss=0.721, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  48%|████▊     | 447/938 [00:32<00:35, 13.74it/s, loss=0.721, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  48%|████▊     | 447/938 [00:32<00:35, 13.74it/s, loss=0.718, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  48%|████▊     | 448/938 [00:32<00:35, 13.75it/s, loss=0.715, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  48%|████▊     | 449/938 [00:32<00:35, 13.75it/s, loss=0.719, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  48%|████▊     | 450/938 [00:32<00:35, 13.75it/s, loss=0.719, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  48%|████▊     | 450/938 [00:32<00:35, 13.75it/s, loss=0.705, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  48%|████▊     | 451/938 [00:32<00:35, 13.75it/s, loss=0.708, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  48%|████▊     | 452/938 [00:32<00:35, 13.75it/s, loss=0.713, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  48%|████▊     | 453/938 [00:32<00:35, 13.75it/s, loss=0.713, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  48%|████▊     | 453/938 [00:32<00:35, 13.75it/s, loss=0.712, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  48%|████▊     | 454/938 [00:33<00:35, 13.75it/s, loss=0.71, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  49%|████▊     | 455/938 [00:33<00:35, 13.74it/s, loss=0.711, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  49%|████▊     | 456/938 [00:33<00:35, 13.75it/s, loss=0.711, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  49%|████▊     | 456/938 [00:33<00:35, 13.75it/s, loss=0.709, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  49%|████▊     | 457/938 [00:33<00:34, 13.75it/s, loss=0.7, v_num=11, val_rmse=0.618, train_rmse=1.190]  
Epoch 1:  49%|████▉     | 458/938 [00:33<00:34, 13.73it/s, loss=0.689, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  49%|████▉     | 459/938 [00:33<00:34, 13.73it/s, loss=0.689, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  49%|████▉     | 459/938 [00:33<00:34, 13.73it/s, loss=0.674, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  49%|████▉     | 460/938 [00:33<00:34, 13.72it/s, loss=0.679, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  49%|████▉     | 461/938 [00:33<00:34, 13.71it/s, loss=0.676, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  49%|████▉     | 462/938 [00:33<00:34, 13.71it/s, loss=0.676, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  49%|████▉     | 462/938 [00:33<00:34, 13.71it/s, loss=0.686, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  49%|████▉     | 463/938 [00:33<00:34, 13.71it/s, loss=0.691, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  49%|████▉     | 464/938 [00:33<00:34, 13.71it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190] 
Epoch 1:  50%|████▉     | 465/938 [00:33<00:34, 13.71it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  50%|████▉     | 465/938 [00:33<00:34, 13.71it/s, loss=0.689, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  50%|████▉     | 466/938 [00:33<00:34, 13.71it/s, loss=0.687, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  50%|████▉     | 467/938 [00:34<00:34, 13.71it/s, loss=0.675, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  50%|████▉     | 468/938 [00:34<00:34, 13.71it/s, loss=0.675, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  50%|████▉     | 468/938 [00:34<00:34, 13.71it/s, loss=0.686, v_num=11, val_rmse=0.618, train_rmse=1.190]
Epoch 1:  50%|█████     | 469/938 [00:34<00:34, 13.72it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190] 

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]
Epoch 1:  50%|█████     | 471/938 [00:34<00:33, 13.76it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:   1%|          | 3/469 [00:00<00:20, 23.00it/s]
Epoch 1:  51%|█████     | 474/938 [00:34<00:33, 13.80it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:   1%|▏         | 6/469 [00:00<00:19, 23.23it/s]
Epoch 1:  51%|█████     | 477/938 [00:34<00:33, 13.84it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:   2%|▏         | 9/469 [00:00<00:18, 24.75it/s]
Epoch 1:  51%|█████     | 480/938 [00:34<00:32, 13.88it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:   3%|▎         | 12/469 [00:00<00:17, 25.56it/s]
Epoch 1:  51%|█████▏    | 483/938 [00:34<00:32, 13.92it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:   3%|▎         | 15/469 [00:00<00:18, 25.11it/s]
Epoch 1:  52%|█████▏    | 486/938 [00:34<00:32, 13.95it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:   4%|▍         | 18/469 [00:00<00:17, 25.17it/s]
Epoch 1:  52%|█████▏    | 489/938 [00:34<00:32, 13.99it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:   4%|▍         | 21/469 [00:00<00:19, 22.81it/s]
Epoch 1:  52%|█████▏    | 492/938 [00:35<00:31, 14.02it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:   5%|▌         | 24/469 [00:00<00:18, 23.66it/s]
Epoch 1:  53%|█████▎    | 495/938 [00:35<00:31, 14.06it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:   6%|▌         | 27/469 [00:01<00:18, 23.70it/s]
Epoch 1:  53%|█████▎    | 498/938 [00:35<00:31, 14.09it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:   6%|▋         | 30/469 [00:01<00:18, 24.36it/s]
Epoch 1:  53%|█████▎    | 501/938 [00:35<00:30, 14.13it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:   7%|▋         | 33/469 [00:01<00:17, 24.88it/s]
Epoch 1:  54%|█████▎    | 504/938 [00:35<00:30, 14.16it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:   8%|▊         | 36/469 [00:01<00:17, 24.20it/s]
Epoch 1:  54%|█████▍    | 507/938 [00:35<00:30, 14.20it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:   8%|▊         | 39/469 [00:01<00:18, 23.83it/s]
Epoch 1:  54%|█████▍    | 510/938 [00:35<00:30, 14.23it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:   9%|▉         | 42/469 [00:01<00:18, 23.36it/s]
Epoch 1:  55%|█████▍    | 513/938 [00:35<00:29, 14.26it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  10%|▉         | 45/469 [00:01<00:18, 23.35it/s]
Epoch 1:  55%|█████▌    | 516/938 [00:36<00:29, 14.30it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  10%|█         | 48/469 [00:01<00:17, 24.32it/s]
Epoch 1:  55%|█████▌    | 519/938 [00:36<00:29, 14.33it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  11%|█         | 51/469 [00:02<00:16, 24.98it/s]
Epoch 1:  56%|█████▌    | 522/938 [00:36<00:28, 14.36it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  12%|█▏        | 54/469 [00:02<00:17, 24.20it/s]
Epoch 1:  56%|█████▌    | 525/938 [00:36<00:28, 14.40it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  12%|█▏        | 57/469 [00:02<00:17, 23.86it/s]
Epoch 1:  56%|█████▋    | 528/938 [00:36<00:28, 14.43it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  13%|█▎        | 60/469 [00:02<00:17, 23.73it/s]
Epoch 1:  57%|█████▋    | 531/938 [00:36<00:28, 14.47it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  13%|█▎        | 63/469 [00:02<00:16, 24.92it/s]
Epoch 1:  57%|█████▋    | 534/938 [00:36<00:27, 14.51it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  14%|█▍        | 66/469 [00:02<00:16, 24.74it/s]
Epoch 1:  57%|█████▋    | 537/938 [00:36<00:27, 14.54it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  15%|█▍        | 69/469 [00:02<00:16, 24.42it/s]
Epoch 1:  58%|█████▊    | 540/938 [00:37<00:27, 14.57it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  15%|█▌        | 72/469 [00:02<00:16, 24.05it/s]
Epoch 1:  58%|█████▊    | 543/938 [00:37<00:27, 14.60it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  16%|█▌        | 75/469 [00:03<00:16, 23.83it/s]
Epoch 1:  58%|█████▊    | 546/938 [00:37<00:26, 14.61it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  17%|█▋        | 78/469 [00:03<00:18, 21.41it/s]
Epoch 1:  59%|█████▊    | 549/938 [00:37<00:26, 14.64it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  17%|█▋        | 81/469 [00:03<00:17, 22.42it/s]
Epoch 1:  59%|█████▉    | 552/938 [00:37<00:26, 14.67it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  18%|█▊        | 84/469 [00:03<00:17, 22.43it/s]
Epoch 1:  59%|█████▉    | 555/938 [00:37<00:26, 14.70it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  19%|█▊        | 87/469 [00:03<00:16, 22.61it/s]
Epoch 1:  59%|█████▉    | 558/938 [00:37<00:25, 14.73it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  19%|█▉        | 90/469 [00:03<00:16, 22.55it/s]
Epoch 1:  60%|█████▉    | 561/938 [00:38<00:25, 14.76it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  20%|█▉        | 93/469 [00:03<00:16, 23.46it/s]
Epoch 1:  60%|██████    | 564/938 [00:38<00:25, 14.79it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  20%|██        | 96/469 [00:04<00:16, 22.89it/s]
Epoch 1:  60%|██████    | 567/938 [00:38<00:25, 14.81it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  21%|██        | 99/469 [00:04<00:16, 22.09it/s]
Epoch 1:  61%|██████    | 570/938 [00:38<00:24, 14.84it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  22%|██▏       | 102/469 [00:04<00:15, 23.12it/s]
Epoch 1:  61%|██████    | 573/938 [00:38<00:24, 14.87it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  22%|██▏       | 105/469 [00:04<00:15, 23.11it/s]
Epoch 1:  61%|██████▏   | 576/938 [00:38<00:24, 14.89it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  23%|██▎       | 108/469 [00:04<00:15, 22.62it/s]
Epoch 1:  62%|██████▏   | 579/938 [00:38<00:24, 14.92it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  24%|██▎       | 111/469 [00:04<00:15, 22.72it/s]
Epoch 1:  62%|██████▏   | 582/938 [00:38<00:23, 14.95it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  24%|██▍       | 114/469 [00:04<00:15, 23.59it/s]
Epoch 1:  62%|██████▏   | 585/938 [00:39<00:23, 14.98it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  25%|██▍       | 117/469 [00:04<00:15, 23.13it/s]
Epoch 1:  63%|██████▎   | 588/938 [00:39<00:23, 15.00it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  26%|██▌       | 120/469 [00:05<00:16, 21.27it/s]
Epoch 1:  63%|██████▎   | 591/938 [00:39<00:23, 15.02it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  26%|██▌       | 123/469 [00:05<00:15, 22.19it/s]
Epoch 1:  63%|██████▎   | 594/938 [00:39<00:22, 15.05it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  27%|██▋       | 126/469 [00:05<00:15, 22.37it/s]
Epoch 1:  64%|██████▎   | 597/938 [00:39<00:22, 15.08it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  28%|██▊       | 129/469 [00:05<00:14, 23.21it/s]
Epoch 1:  64%|██████▍   | 600/938 [00:39<00:22, 15.11it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  28%|██▊       | 132/469 [00:05<00:13, 24.30it/s]
Epoch 1:  64%|██████▍   | 603/938 [00:39<00:22, 15.14it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  29%|██▉       | 135/469 [00:05<00:13, 24.58it/s]
Epoch 1:  65%|██████▍   | 606/938 [00:39<00:21, 15.17it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  29%|██▉       | 138/469 [00:05<00:13, 24.28it/s]
Epoch 1:  65%|██████▍   | 609/938 [00:40<00:21, 15.19it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  30%|███       | 141/469 [00:05<00:13, 24.29it/s]
Epoch 1:  65%|██████▌   | 612/938 [00:40<00:21, 15.22it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  31%|███       | 144/469 [00:06<00:13, 24.81it/s]
Epoch 1:  66%|██████▌   | 615/938 [00:40<00:21, 15.26it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  31%|███▏      | 147/469 [00:06<00:12, 24.85it/s]
Epoch 1:  66%|██████▌   | 618/938 [00:40<00:20, 15.28it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  32%|███▏      | 150/469 [00:06<00:12, 24.71it/s]
Epoch 1:  66%|██████▌   | 621/938 [00:40<00:20, 15.31it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  33%|███▎      | 153/469 [00:06<00:12, 25.59it/s]
Epoch 1:  67%|██████▋   | 624/938 [00:40<00:20, 15.34it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  33%|███▎      | 156/469 [00:06<00:12, 25.48it/s]
Epoch 1:  67%|██████▋   | 627/938 [00:40<00:20, 15.37it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  34%|███▍      | 159/469 [00:06<00:12, 24.45it/s]
Epoch 1:  67%|██████▋   | 630/938 [00:40<00:20, 15.39it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  35%|███▍      | 162/469 [00:06<00:12, 23.92it/s]
Epoch 1:  67%|██████▋   | 633/938 [00:41<00:19, 15.42it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  35%|███▌      | 165/469 [00:06<00:12, 23.81it/s]
Epoch 1:  68%|██████▊   | 636/938 [00:41<00:19, 15.44it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  36%|███▌      | 168/469 [00:07<00:12, 23.47it/s]
Epoch 1:  68%|██████▊   | 639/938 [00:41<00:19, 15.47it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  36%|███▋      | 171/469 [00:07<00:13, 22.74it/s]
Epoch 1:  68%|██████▊   | 642/938 [00:41<00:19, 15.49it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  37%|███▋      | 174/469 [00:07<00:12, 23.94it/s]
Epoch 1:  69%|██████▉   | 645/938 [00:41<00:18, 15.52it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  38%|███▊      | 177/469 [00:07<00:12, 23.85it/s]
Epoch 1:  69%|██████▉   | 648/938 [00:41<00:18, 15.54it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  38%|███▊      | 180/469 [00:07<00:11, 24.26it/s]
Epoch 1:  69%|██████▉   | 651/938 [00:41<00:18, 15.57it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  39%|███▉      | 183/469 [00:07<00:11, 25.01it/s]
Epoch 1:  70%|██████▉   | 654/938 [00:41<00:18, 15.60it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  40%|███▉      | 186/469 [00:07<00:11, 25.12it/s]
Epoch 1:  70%|███████   | 657/938 [00:42<00:17, 15.63it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  40%|████      | 189/469 [00:07<00:10, 25.56it/s]
Epoch 1:  70%|███████   | 660/938 [00:42<00:17, 15.66it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  41%|████      | 192/469 [00:08<00:10, 25.43it/s]
Epoch 1:  71%|███████   | 663/938 [00:42<00:17, 15.68it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  42%|████▏     | 195/469 [00:08<00:10, 25.75it/s]
Epoch 1:  71%|███████   | 666/938 [00:42<00:17, 15.71it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  42%|████▏     | 198/469 [00:08<00:10, 25.21it/s]
Epoch 1:  71%|███████▏  | 669/938 [00:42<00:17, 15.74it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  43%|████▎     | 201/469 [00:08<00:10, 25.71it/s]
Epoch 1:  72%|███████▏  | 672/938 [00:42<00:16, 15.77it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  43%|████▎     | 204/469 [00:08<00:10, 26.10it/s]
Epoch 1:  72%|███████▏  | 675/938 [00:42<00:16, 15.79it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  44%|████▍     | 207/469 [00:08<00:10, 25.24it/s]
Epoch 1:  72%|███████▏  | 678/938 [00:42<00:16, 15.82it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  45%|████▍     | 210/469 [00:08<00:10, 25.10it/s]
Epoch 1:  73%|███████▎  | 681/938 [00:43<00:16, 15.83it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  45%|████▌     | 213/469 [00:08<00:10, 23.84it/s]
Epoch 1:  73%|███████▎  | 684/938 [00:43<00:16, 15.86it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  46%|████▌     | 216/469 [00:09<00:10, 24.41it/s]
Epoch 1:  73%|███████▎  | 687/938 [00:43<00:15, 15.89it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  47%|████▋     | 219/469 [00:09<00:10, 24.01it/s]
Epoch 1:  74%|███████▎  | 690/938 [00:43<00:15, 15.91it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  47%|████▋     | 222/469 [00:09<00:10, 23.91it/s]
Epoch 1:  74%|███████▍  | 693/938 [00:43<00:15, 15.94it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  48%|████▊     | 225/469 [00:09<00:09, 24.64it/s]
Epoch 1:  74%|███████▍  | 696/938 [00:43<00:15, 15.96it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  49%|████▊     | 228/469 [00:09<00:10, 24.07it/s]
Epoch 1:  75%|███████▍  | 699/938 [00:43<00:14, 15.98it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  49%|████▉     | 231/469 [00:09<00:09, 24.37it/s]
Epoch 1:  75%|███████▍  | 702/938 [00:43<00:14, 16.00it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  50%|████▉     | 234/469 [00:09<00:09, 24.19it/s]
Epoch 1:  75%|███████▌  | 705/938 [00:43<00:14, 16.03it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  51%|█████     | 237/469 [00:09<00:09, 23.75it/s]
Epoch 1:  75%|███████▌  | 708/938 [00:44<00:14, 16.05it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  51%|█████     | 240/469 [00:10<00:09, 23.54it/s]
Epoch 1:  76%|███████▌  | 711/938 [00:44<00:14, 16.07it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  52%|█████▏    | 243/469 [00:10<00:09, 24.15it/s]
Epoch 1:  76%|███████▌  | 714/938 [00:44<00:13, 16.10it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  52%|█████▏    | 246/469 [00:10<00:09, 24.38it/s]
Epoch 1:  76%|███████▋  | 717/938 [00:44<00:13, 16.12it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  53%|█████▎    | 249/469 [00:10<00:08, 24.64it/s]
Epoch 1:  77%|███████▋  | 720/938 [00:44<00:13, 16.14it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  54%|█████▎    | 252/469 [00:10<00:08, 24.98it/s]
Epoch 1:  77%|███████▋  | 723/938 [00:44<00:13, 16.16it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  54%|█████▍    | 255/469 [00:10<00:09, 21.83it/s]
Epoch 1:  77%|███████▋  | 726/938 [00:44<00:13, 16.17it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  55%|█████▌    | 258/469 [00:10<00:09, 22.75it/s]
Epoch 1:  78%|███████▊  | 729/938 [00:45<00:12, 16.19it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  56%|█████▌    | 261/469 [00:10<00:09, 23.05it/s]
Epoch 1:  78%|███████▊  | 732/938 [00:45<00:12, 16.22it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  56%|█████▋    | 264/469 [00:11<00:08, 23.96it/s]
Epoch 1:  78%|███████▊  | 735/938 [00:45<00:12, 16.24it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  57%|█████▋    | 267/469 [00:11<00:08, 23.69it/s]
Epoch 1:  79%|███████▊  | 738/938 [00:45<00:12, 16.26it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  58%|█████▊    | 270/469 [00:11<00:08, 23.25it/s]
Epoch 1:  79%|███████▉  | 741/938 [00:45<00:12, 16.28it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  58%|█████▊    | 273/469 [00:11<00:08, 23.46it/s]
Epoch 1:  79%|███████▉  | 744/938 [00:45<00:11, 16.30it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  59%|█████▉    | 276/469 [00:11<00:08, 23.63it/s]
Epoch 1:  80%|███████▉  | 747/938 [00:45<00:11, 16.32it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  59%|█████▉    | 279/469 [00:11<00:08, 23.64it/s]
Epoch 1:  80%|███████▉  | 750/938 [00:45<00:11, 16.34it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  60%|██████    | 282/469 [00:11<00:07, 24.76it/s]
Epoch 1:  80%|████████  | 753/938 [00:45<00:11, 16.37it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  61%|██████    | 285/469 [00:11<00:07, 25.60it/s]
Epoch 1:  81%|████████  | 756/938 [00:46<00:11, 16.40it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  61%|██████▏   | 288/469 [00:12<00:06, 26.08it/s]
Epoch 1:  81%|████████  | 759/938 [00:46<00:10, 16.42it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  62%|██████▏   | 291/469 [00:12<00:07, 25.42it/s]
Epoch 1:  81%|████████  | 762/938 [00:46<00:10, 16.44it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  63%|██████▎   | 294/469 [00:12<00:07, 24.86it/s]
Epoch 1:  82%|████████▏ | 765/938 [00:46<00:10, 16.46it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  63%|██████▎   | 297/469 [00:12<00:06, 25.01it/s]
Epoch 1:  82%|████████▏ | 768/938 [00:46<00:10, 16.48it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  64%|██████▍   | 300/469 [00:12<00:06, 24.60it/s]
Epoch 1:  82%|████████▏ | 771/938 [00:46<00:10, 16.49it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  65%|██████▍   | 303/469 [00:12<00:07, 22.93it/s]
Epoch 1:  83%|████████▎ | 774/938 [00:46<00:09, 16.51it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  65%|██████▌   | 306/469 [00:12<00:06, 23.29it/s]
Epoch 1:  83%|████████▎ | 777/938 [00:46<00:09, 16.54it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  66%|██████▌   | 309/469 [00:12<00:06, 24.86it/s]
Epoch 1:  83%|████████▎ | 780/938 [00:47<00:09, 16.56it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  67%|██████▋   | 312/469 [00:12<00:06, 25.24it/s]
Epoch 1:  83%|████████▎ | 783/938 [00:47<00:09, 16.59it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  67%|██████▋   | 315/469 [00:13<00:05, 25.70it/s]
Epoch 1:  84%|████████▍ | 786/938 [00:47<00:09, 16.61it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  68%|██████▊   | 318/469 [00:13<00:06, 25.16it/s]
Epoch 1:  84%|████████▍ | 789/938 [00:47<00:08, 16.63it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  68%|██████▊   | 321/469 [00:13<00:05, 25.61it/s]
Epoch 1:  84%|████████▍ | 792/938 [00:47<00:08, 16.66it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  69%|██████▉   | 324/469 [00:13<00:05, 25.35it/s]
Epoch 1:  85%|████████▍ | 795/938 [00:47<00:08, 16.68it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  70%|██████▉   | 327/469 [00:13<00:05, 25.84it/s]
Epoch 1:  85%|████████▌ | 798/938 [00:47<00:08, 16.70it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  70%|███████   | 330/469 [00:13<00:05, 25.42it/s]
Epoch 1:  85%|████████▌ | 801/938 [00:47<00:08, 16.72it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  71%|███████   | 333/469 [00:13<00:05, 25.79it/s]
Epoch 1:  86%|████████▌ | 804/938 [00:48<00:08, 16.74it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  72%|███████▏  | 336/469 [00:13<00:05, 23.54it/s]
Epoch 1:  86%|████████▌ | 807/938 [00:48<00:07, 16.75it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  72%|███████▏  | 339/469 [00:14<00:05, 23.65it/s]
Epoch 1:  86%|████████▋ | 810/938 [00:48<00:07, 16.77it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  73%|███████▎  | 342/469 [00:14<00:05, 23.83it/s]
Epoch 1:  87%|████████▋ | 813/938 [00:48<00:07, 16.79it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  74%|███████▎  | 345/469 [00:14<00:05, 24.26it/s]
Epoch 1:  87%|████████▋ | 816/938 [00:48<00:07, 16.81it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  74%|███████▍  | 348/469 [00:14<00:04, 24.49it/s]
Epoch 1:  87%|████████▋ | 819/938 [00:48<00:07, 16.83it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  75%|███████▍  | 351/469 [00:14<00:04, 23.96it/s]
Epoch 1:  88%|████████▊ | 822/938 [00:48<00:06, 16.84it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  75%|███████▌  | 354/469 [00:14<00:04, 24.49it/s]
Epoch 1:  88%|████████▊ | 825/938 [00:48<00:06, 16.86it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  76%|███████▌  | 357/469 [00:14<00:04, 24.31it/s]
Epoch 1:  88%|████████▊ | 828/938 [00:49<00:06, 16.88it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  77%|███████▋  | 360/469 [00:14<00:04, 24.81it/s]
Epoch 1:  89%|████████▊ | 831/938 [00:49<00:06, 16.91it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  77%|███████▋  | 363/469 [00:15<00:04, 24.25it/s]
Epoch 1:  89%|████████▉ | 834/938 [00:49<00:06, 16.92it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  78%|███████▊  | 366/469 [00:15<00:04, 24.54it/s]
Epoch 1:  89%|████████▉ | 837/938 [00:49<00:05, 16.94it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  79%|███████▊  | 369/469 [00:15<00:04, 24.46it/s]
Epoch 1:  90%|████████▉ | 840/938 [00:49<00:05, 16.96it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  79%|███████▉  | 372/469 [00:15<00:03, 25.13it/s]
Epoch 1:  90%|████████▉ | 843/938 [00:49<00:05, 16.98it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  80%|███████▉  | 375/469 [00:15<00:03, 25.46it/s]
Epoch 1:  90%|█████████ | 846/938 [00:49<00:05, 17.01it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  81%|████████  | 378/469 [00:15<00:03, 25.66it/s]
Epoch 1:  91%|█████████ | 849/938 [00:49<00:05, 17.02it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  81%|████████  | 381/469 [00:15<00:03, 25.98it/s]
Epoch 1:  91%|█████████ | 852/938 [00:49<00:05, 17.05it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  82%|████████▏ | 384/469 [00:15<00:03, 25.61it/s]
Epoch 1:  91%|█████████ | 855/938 [00:50<00:04, 17.07it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  83%|████████▎ | 387/469 [00:15<00:03, 26.13it/s]
Epoch 1:  91%|█████████▏| 858/938 [00:50<00:04, 17.09it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  83%|████████▎ | 390/469 [00:16<00:02, 26.51it/s]
Epoch 1:  92%|█████████▏| 861/938 [00:50<00:04, 17.11it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  84%|████████▍ | 393/469 [00:16<00:02, 25.96it/s]
Epoch 1:  92%|█████████▏| 864/938 [00:50<00:04, 17.13it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  84%|████████▍ | 396/469 [00:16<00:02, 25.40it/s]
Epoch 1:  92%|█████████▏| 867/938 [00:50<00:04, 17.15it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  85%|████████▌ | 399/469 [00:16<00:02, 25.43it/s]
Epoch 1:  93%|█████████▎| 870/938 [00:50<00:03, 17.17it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  86%|████████▌ | 402/469 [00:16<00:02, 24.37it/s]
Epoch 1:  93%|█████████▎| 873/938 [00:50<00:03, 17.18it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  86%|████████▋ | 405/469 [00:16<00:02, 24.70it/s]
Epoch 1:  93%|█████████▎| 876/938 [00:50<00:03, 17.20it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  87%|████████▋ | 408/469 [00:16<00:02, 24.71it/s]
Epoch 1:  94%|█████████▎| 879/938 [00:51<00:03, 17.22it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  88%|████████▊ | 411/469 [00:16<00:02, 25.30it/s]
Epoch 1:  94%|█████████▍| 882/938 [00:51<00:03, 17.24it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  88%|████████▊ | 414/469 [00:17<00:02, 25.49it/s]
Epoch 1:  94%|█████████▍| 885/938 [00:51<00:03, 17.26it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  89%|████████▉ | 417/469 [00:17<00:02, 25.15it/s]
Epoch 1:  95%|█████████▍| 888/938 [00:51<00:02, 17.28it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  90%|████████▉ | 420/469 [00:17<00:01, 25.98it/s]
Epoch 1:  95%|█████████▍| 891/938 [00:51<00:02, 17.30it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  90%|█████████ | 423/469 [00:17<00:01, 26.23it/s]
Epoch 1:  95%|█████████▌| 894/938 [00:51<00:02, 17.32it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  91%|█████████ | 426/469 [00:17<00:01, 26.42it/s]
Epoch 1:  96%|█████████▌| 897/938 [00:51<00:02, 17.34it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  91%|█████████▏| 429/469 [00:17<00:01, 26.59it/s]
Epoch 1:  96%|█████████▌| 900/938 [00:51<00:02, 17.36it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  92%|█████████▏| 432/469 [00:17<00:01, 26.05it/s]
Epoch 1:  96%|█████████▋| 903/938 [00:51<00:02, 17.38it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  93%|█████████▎| 435/469 [00:17<00:01, 26.55it/s]
Epoch 1:  97%|█████████▋| 906/938 [00:52<00:01, 17.40it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  93%|█████████▎| 438/469 [00:17<00:01, 25.70it/s]
Epoch 1:  97%|█████████▋| 909/938 [00:52<00:01, 17.41it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  94%|█████████▍| 441/469 [00:18<00:01, 25.88it/s]
Epoch 1:  97%|█████████▋| 912/938 [00:52<00:01, 17.43it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  95%|█████████▍| 444/469 [00:18<00:00, 25.06it/s]
Epoch 1:  98%|█████████▊| 915/938 [00:52<00:01, 17.44it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  95%|█████████▌| 447/469 [00:18<00:00, 24.25it/s]
Epoch 1:  98%|█████████▊| 918/938 [00:52<00:01, 17.46it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  96%|█████████▌| 450/469 [00:18<00:00, 24.21it/s]
Epoch 1:  98%|█████████▊| 921/938 [00:52<00:00, 17.47it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  97%|█████████▋| 453/469 [00:18<00:00, 24.88it/s]
Epoch 1:  99%|█████████▊| 924/938 [00:52<00:00, 17.49it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  97%|█████████▋| 456/469 [00:18<00:00, 24.86it/s]
Epoch 1:  99%|█████████▉| 927/938 [00:52<00:00, 17.51it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  98%|█████████▊| 459/469 [00:18<00:00, 24.63it/s]
Epoch 1:  99%|█████████▉| 930/938 [00:53<00:00, 17.52it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  99%|█████████▊| 462/469 [00:18<00:00, 24.12it/s]
Epoch 1:  99%|█████████▉| 933/938 [00:53<00:00, 17.54it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating:  99%|█████████▉| 465/469 [00:19<00:00, 24.82it/s]
Epoch 1: 100%|█████████▉| 936/938 [00:53<00:00, 17.56it/s, loss=0.69, v_num=11, val_rmse=0.618, train_rmse=1.190]

Validating: 100%|█████████▉| 468/469 [00:19<00:00, 25.84it/s]
Epoch 1: 100%|██████████| 938/938 [00:53<00:00, 17.57it/s, loss=0.69, v_num=11, val_rmse=0.554, train_rmse=1.190]

                                                             
Epoch 1: 100%|██████████| 938/938 [00:53<00:00, 17.56it/s, loss=0.69, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 1:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.69, v_num=11, val_rmse=0.554, train_rmse=0.726]          
Epoch 2:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.69, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   0%|          | 1/938 [00:00<01:14, 12.51it/s, loss=0.699, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   0%|          | 2/938 [00:00<01:07, 13.78it/s, loss=0.697, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   0%|          | 3/938 [00:00<01:02, 14.89it/s, loss=0.697, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   0%|          | 3/938 [00:00<01:02, 14.85it/s, loss=0.698, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   0%|          | 4/938 [00:00<01:08, 13.54it/s, loss=0.699, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   1%|          | 5/938 [00:00<01:06, 14.01it/s, loss=0.702, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   1%|          | 6/938 [00:00<01:05, 14.32it/s, loss=0.702, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   1%|          | 6/938 [00:00<01:05, 14.30it/s, loss=0.699, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   1%|          | 7/938 [00:00<01:06, 14.07it/s, loss=0.705, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   1%|          | 8/938 [00:00<01:05, 14.30it/s, loss=0.709, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   1%|          | 9/938 [00:00<01:04, 14.33it/s, loss=0.709, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   1%|          | 9/938 [00:00<01:04, 14.31it/s, loss=0.706, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   1%|          | 10/938 [00:00<01:06, 13.90it/s, loss=0.706, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   1%|          | 11/938 [00:00<01:07, 13.77it/s, loss=0.692, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   1%|▏         | 12/938 [00:00<01:06, 13.87it/s, loss=0.692, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   1%|▏         | 12/938 [00:00<01:06, 13.86it/s, loss=0.694, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   1%|▏         | 13/938 [00:00<01:06, 13.97it/s, loss=0.696, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   1%|▏         | 14/938 [00:01<01:06, 13.99it/s, loss=0.696, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   2%|▏         | 15/938 [00:01<01:06, 13.91it/s, loss=0.696, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   2%|▏         | 15/938 [00:01<01:06, 13.90it/s, loss=0.693, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   2%|▏         | 16/938 [00:01<01:06, 13.87it/s, loss=0.704, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   2%|▏         | 17/938 [00:01<01:05, 13.98it/s, loss=0.705, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   2%|▏         | 18/938 [00:01<01:05, 14.08it/s, loss=0.705, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   2%|▏         | 18/938 [00:01<01:05, 14.07it/s, loss=0.71, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:   2%|▏         | 19/938 [00:01<01:05, 14.09it/s, loss=0.699, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   2%|▏         | 20/938 [00:01<01:04, 14.15it/s, loss=0.703, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   2%|▏         | 21/938 [00:01<01:04, 14.13it/s, loss=0.703, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   2%|▏         | 21/938 [00:01<01:04, 14.13it/s, loss=0.71, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:   2%|▏         | 22/938 [00:01<01:05, 14.03it/s, loss=0.712, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   2%|▏         | 23/938 [00:01<01:04, 14.20it/s, loss=0.713, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   3%|▎         | 24/938 [00:01<01:04, 14.11it/s, loss=0.713, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   3%|▎         | 24/938 [00:01<01:04, 14.11it/s, loss=0.706, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   3%|▎         | 25/938 [00:01<01:04, 14.17it/s, loss=0.704, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   3%|▎         | 26/938 [00:01<01:04, 14.21it/s, loss=0.709, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   3%|▎         | 27/938 [00:01<01:03, 14.28it/s, loss=0.709, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   3%|▎         | 27/938 [00:01<01:03, 14.27it/s, loss=0.711, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   3%|▎         | 28/938 [00:01<01:03, 14.28it/s, loss=0.719, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   3%|▎         | 29/938 [00:02<01:03, 14.35it/s, loss=0.728, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   3%|▎         | 30/938 [00:02<01:03, 14.39it/s, loss=0.728, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   3%|▎         | 30/938 [00:02<01:03, 14.39it/s, loss=0.735, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   3%|▎         | 31/938 [00:02<01:02, 14.43it/s, loss=0.748, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   3%|▎         | 32/938 [00:02<01:02, 14.44it/s, loss=0.75, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:   4%|▎         | 33/938 [00:02<01:02, 14.44it/s, loss=0.75, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   4%|▎         | 33/938 [00:02<01:02, 14.44it/s, loss=0.741, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   4%|▎         | 34/938 [00:02<01:02, 14.41it/s, loss=0.739, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   4%|▎         | 35/938 [00:02<01:02, 14.42it/s, loss=0.749, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   4%|▍         | 36/938 [00:02<01:02, 14.36it/s, loss=0.749, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   4%|▍         | 36/938 [00:02<01:02, 14.36it/s, loss=0.735, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   4%|▍         | 37/938 [00:02<01:02, 14.31it/s, loss=0.739, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   4%|▍         | 38/938 [00:02<01:02, 14.38it/s, loss=0.745, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   4%|▍         | 39/938 [00:02<01:02, 14.40it/s, loss=0.745, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   4%|▍         | 39/938 [00:02<01:02, 14.40it/s, loss=0.754, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   4%|▍         | 40/938 [00:02<01:02, 14.43it/s, loss=0.75, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:   4%|▍         | 41/938 [00:02<01:02, 14.44it/s, loss=0.753, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   4%|▍         | 42/938 [00:02<01:02, 14.45it/s, loss=0.753, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   4%|▍         | 42/938 [00:02<01:02, 14.45it/s, loss=0.749, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   5%|▍         | 43/938 [00:02<01:01, 14.45it/s, loss=0.744, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   5%|▍         | 44/938 [00:03<01:01, 14.46it/s, loss=0.75, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:   5%|▍         | 45/938 [00:03<01:01, 14.47it/s, loss=0.75, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   5%|▍         | 45/938 [00:03<01:01, 14.47it/s, loss=0.747, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   5%|▍         | 46/938 [00:03<01:01, 14.48it/s, loss=0.749, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   5%|▌         | 47/938 [00:03<01:01, 14.49it/s, loss=0.743, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   5%|▌         | 48/938 [00:03<01:01, 14.46it/s, loss=0.743, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   5%|▌         | 48/938 [00:03<01:01, 14.45it/s, loss=0.726, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   5%|▌         | 49/938 [00:03<01:01, 14.49it/s, loss=0.718, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   5%|▌         | 50/938 [00:03<01:01, 14.51it/s, loss=0.717, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   5%|▌         | 51/938 [00:03<01:01, 14.40it/s, loss=0.717, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   5%|▌         | 51/938 [00:03<01:01, 14.39it/s, loss=0.707, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   6%|▌         | 52/938 [00:03<01:01, 14.39it/s, loss=0.708, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   6%|▌         | 53/938 [00:03<01:01, 14.39it/s, loss=0.711, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   6%|▌         | 54/938 [00:03<01:01, 14.39it/s, loss=0.711, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   6%|▌         | 54/938 [00:03<01:01, 14.39it/s, loss=0.711, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   6%|▌         | 55/938 [00:03<01:01, 14.34it/s, loss=0.706, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   6%|▌         | 56/938 [00:03<01:01, 14.33it/s, loss=0.706, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   6%|▌         | 57/938 [00:03<01:01, 14.32it/s, loss=0.706, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   6%|▌         | 57/938 [00:03<01:01, 14.31it/s, loss=0.691, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   6%|▌         | 58/938 [00:04<01:01, 14.32it/s, loss=0.689, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   6%|▋         | 59/938 [00:04<01:01, 14.32it/s, loss=0.685, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   6%|▋         | 60/938 [00:04<01:01, 14.31it/s, loss=0.685, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   6%|▋         | 60/938 [00:04<01:01, 14.30it/s, loss=0.68, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:   7%|▋         | 61/938 [00:04<01:01, 14.32it/s, loss=0.677, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   7%|▋         | 62/938 [00:04<01:01, 14.31it/s, loss=0.672, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   7%|▋         | 63/938 [00:04<01:01, 14.33it/s, loss=0.672, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   7%|▋         | 63/938 [00:04<01:01, 14.32it/s, loss=0.674, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   7%|▋         | 64/938 [00:04<01:00, 14.34it/s, loss=0.675, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   7%|▋         | 65/938 [00:04<01:00, 14.32it/s, loss=0.681, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   7%|▋         | 66/938 [00:04<01:00, 14.32it/s, loss=0.681, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   7%|▋         | 66/938 [00:04<01:00, 14.32it/s, loss=0.676, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   7%|▋         | 67/938 [00:04<01:00, 14.33it/s, loss=0.677, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   7%|▋         | 68/938 [00:04<01:01, 14.25it/s, loss=0.678, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   7%|▋         | 69/938 [00:04<01:01, 14.19it/s, loss=0.678, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   7%|▋         | 69/938 [00:04<01:01, 14.18it/s, loss=0.685, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   7%|▋         | 70/938 [00:04<01:01, 14.15it/s, loss=0.681, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   8%|▊         | 71/938 [00:05<01:01, 14.16it/s, loss=0.678, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   8%|▊         | 72/938 [00:05<01:01, 14.19it/s, loss=0.678, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   8%|▊         | 72/938 [00:05<01:01, 14.19it/s, loss=0.668, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   8%|▊         | 73/938 [00:05<01:00, 14.19it/s, loss=0.673, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   8%|▊         | 74/938 [00:05<01:00, 14.18it/s, loss=0.673, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   8%|▊         | 75/938 [00:05<01:00, 14.22it/s, loss=0.673, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   8%|▊         | 75/938 [00:05<01:00, 14.22it/s, loss=0.67, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:   8%|▊         | 76/938 [00:05<01:00, 14.21it/s, loss=0.677, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   8%|▊         | 77/938 [00:05<01:00, 14.23it/s, loss=0.679, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   8%|▊         | 78/938 [00:05<01:00, 14.26it/s, loss=0.679, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   8%|▊         | 78/938 [00:05<01:00, 14.26it/s, loss=0.674, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   8%|▊         | 79/938 [00:05<01:00, 14.26it/s, loss=0.673, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   9%|▊         | 80/938 [00:05<01:00, 14.23it/s, loss=0.684, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   9%|▊         | 81/938 [00:05<01:00, 14.26it/s, loss=0.684, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   9%|▊         | 81/938 [00:05<01:00, 14.26it/s, loss=0.678, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   9%|▊         | 82/938 [00:05<01:00, 14.24it/s, loss=0.686, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   9%|▉         | 83/938 [00:05<01:00, 14.24it/s, loss=0.685, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   9%|▉         | 84/938 [00:05<00:59, 14.26it/s, loss=0.685, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   9%|▉         | 84/938 [00:05<00:59, 14.26it/s, loss=0.684, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   9%|▉         | 85/938 [00:06<01:00, 14.11it/s, loss=0.675, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   9%|▉         | 86/938 [00:06<01:00, 14.10it/s, loss=0.671, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   9%|▉         | 87/938 [00:06<01:00, 14.05it/s, loss=0.671, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   9%|▉         | 87/938 [00:06<01:00, 14.05it/s, loss=0.667, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   9%|▉         | 88/938 [00:06<01:00, 14.04it/s, loss=0.665, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:   9%|▉         | 89/938 [00:06<01:00, 14.03it/s, loss=0.66, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  10%|▉         | 90/938 [00:06<01:00, 14.06it/s, loss=0.66, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  10%|▉         | 90/938 [00:06<01:00, 14.06it/s, loss=0.657, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  10%|▉         | 91/938 [00:06<01:00, 14.06it/s, loss=0.665, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  10%|▉         | 92/938 [00:06<01:00, 14.08it/s, loss=0.664, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  10%|▉         | 93/938 [00:06<00:59, 14.09it/s, loss=0.664, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  10%|▉         | 93/938 [00:06<00:59, 14.09it/s, loss=0.658, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  10%|█         | 94/938 [00:06<00:59, 14.09it/s, loss=0.658, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  10%|█         | 95/938 [00:06<00:59, 14.07it/s, loss=0.67, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  10%|█         | 96/938 [00:06<00:59, 14.06it/s, loss=0.67, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  10%|█         | 96/938 [00:06<00:59, 14.06it/s, loss=0.667, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  10%|█         | 97/938 [00:06<00:59, 14.09it/s, loss=0.667, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  10%|█         | 98/938 [00:06<00:59, 14.10it/s, loss=0.666, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  11%|█         | 99/938 [00:07<00:59, 14.12it/s, loss=0.666, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  11%|█         | 99/938 [00:07<00:59, 14.12it/s, loss=0.664, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  11%|█         | 100/938 [00:07<00:59, 14.13it/s, loss=0.653, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  11%|█         | 101/938 [00:07<00:59, 14.12it/s, loss=0.656, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  11%|█         | 102/938 [00:07<00:59, 14.14it/s, loss=0.656, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  11%|█         | 102/938 [00:07<00:59, 14.14it/s, loss=0.657, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  11%|█         | 103/938 [00:07<00:59, 14.15it/s, loss=0.661, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  11%|█         | 104/938 [00:07<00:58, 14.16it/s, loss=0.662, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  11%|█         | 105/938 [00:07<00:58, 14.16it/s, loss=0.662, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  11%|█         | 105/938 [00:07<00:58, 14.16it/s, loss=0.663, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  11%|█▏        | 106/938 [00:07<00:58, 14.16it/s, loss=0.669, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  11%|█▏        | 107/938 [00:07<00:58, 14.13it/s, loss=0.674, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  12%|█▏        | 108/938 [00:07<00:58, 14.10it/s, loss=0.674, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  12%|█▏        | 108/938 [00:07<00:58, 14.10it/s, loss=0.672, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  12%|█▏        | 109/938 [00:07<00:58, 14.11it/s, loss=0.676, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  12%|█▏        | 110/938 [00:07<00:58, 14.13it/s, loss=0.676, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  12%|█▏        | 111/938 [00:07<00:58, 14.12it/s, loss=0.676, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  12%|█▏        | 111/938 [00:07<00:58, 14.12it/s, loss=0.678, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  12%|█▏        | 112/938 [00:07<00:58, 14.13it/s, loss=0.687, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  12%|█▏        | 113/938 [00:08<00:58, 14.11it/s, loss=0.686, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  12%|█▏        | 114/938 [00:08<00:58, 14.12it/s, loss=0.686, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  12%|█▏        | 114/938 [00:08<00:58, 14.12it/s, loss=0.684, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  12%|█▏        | 115/938 [00:08<00:58, 14.12it/s, loss=0.677, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  12%|█▏        | 116/938 [00:08<00:58, 14.13it/s, loss=0.675, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  12%|█▏        | 117/938 [00:08<00:58, 14.14it/s, loss=0.675, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  12%|█▏        | 117/938 [00:08<00:58, 14.14it/s, loss=0.68, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  13%|█▎        | 118/938 [00:08<00:58, 14.10it/s, loss=0.687, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  13%|█▎        | 119/938 [00:08<00:58, 14.11it/s, loss=0.682, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  13%|█▎        | 120/938 [00:08<00:57, 14.13it/s, loss=0.682, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  13%|█▎        | 120/938 [00:08<00:57, 14.13it/s, loss=0.681, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  13%|█▎        | 121/938 [00:08<00:57, 14.15it/s, loss=0.676, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  13%|█▎        | 122/938 [00:08<00:57, 14.15it/s, loss=0.668, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  13%|█▎        | 123/938 [00:08<00:57, 14.17it/s, loss=0.668, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  13%|█▎        | 123/938 [00:08<00:57, 14.17it/s, loss=0.662, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  13%|█▎        | 124/938 [00:08<00:57, 14.15it/s, loss=0.658, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  13%|█▎        | 125/938 [00:08<00:57, 14.17it/s, loss=0.655, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  13%|█▎        | 126/938 [00:08<00:57, 14.18it/s, loss=0.655, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  13%|█▎        | 126/938 [00:08<00:57, 14.18it/s, loss=0.657, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  14%|█▎        | 127/938 [00:08<00:57, 14.20it/s, loss=0.65, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  14%|█▎        | 128/938 [00:09<00:57, 14.19it/s, loss=0.661, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  14%|█▍        | 129/938 [00:09<00:56, 14.20it/s, loss=0.661, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  14%|█▍        | 129/938 [00:09<00:56, 14.20it/s, loss=0.673, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  14%|█▍        | 130/938 [00:09<00:56, 14.18it/s, loss=0.685, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  14%|█▍        | 131/938 [00:09<00:56, 14.19it/s, loss=0.688, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  14%|█▍        | 132/938 [00:09<00:56, 14.19it/s, loss=0.688, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  14%|█▍        | 132/938 [00:09<00:56, 14.19it/s, loss=0.69, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  14%|█▍        | 133/938 [00:09<00:56, 14.20it/s, loss=0.689, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  14%|█▍        | 134/938 [00:09<00:56, 14.20it/s, loss=0.685, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  14%|█▍        | 135/938 [00:09<00:56, 14.23it/s, loss=0.685, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  14%|█▍        | 135/938 [00:09<00:56, 14.23it/s, loss=0.676, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  14%|█▍        | 136/938 [00:09<00:56, 14.23it/s, loss=0.683, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  15%|█▍        | 137/938 [00:09<00:56, 14.23it/s, loss=0.684, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  15%|█▍        | 138/938 [00:09<00:56, 14.24it/s, loss=0.684, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  15%|█▍        | 138/938 [00:09<00:56, 14.24it/s, loss=0.689, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  15%|█▍        | 139/938 [00:09<00:56, 14.21it/s, loss=0.698, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  15%|█▍        | 140/938 [00:09<00:56, 14.22it/s, loss=0.699, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  15%|█▌        | 141/938 [00:09<00:56, 14.21it/s, loss=0.699, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  15%|█▌        | 141/938 [00:09<00:56, 14.21it/s, loss=0.705, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  15%|█▌        | 142/938 [00:09<00:55, 14.23it/s, loss=0.707, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  15%|█▌        | 143/938 [00:10<00:55, 14.21it/s, loss=0.714, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  15%|█▌        | 144/938 [00:10<00:55, 14.19it/s, loss=0.714, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  15%|█▌        | 144/938 [00:10<00:55, 14.19it/s, loss=0.715, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  15%|█▌        | 145/938 [00:10<00:55, 14.18it/s, loss=0.726, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  16%|█▌        | 146/938 [00:10<00:55, 14.21it/s, loss=0.729, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  16%|█▌        | 147/938 [00:10<00:55, 14.19it/s, loss=0.729, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  16%|█▌        | 147/938 [00:10<00:55, 14.18it/s, loss=0.733, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  16%|█▌        | 148/938 [00:10<00:55, 14.13it/s, loss=0.733, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  16%|█▌        | 149/938 [00:10<00:55, 14.13it/s, loss=0.716, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  16%|█▌        | 150/938 [00:10<00:55, 14.12it/s, loss=0.716, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  16%|█▌        | 150/938 [00:10<00:55, 14.12it/s, loss=0.715, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  16%|█▌        | 151/938 [00:10<00:55, 14.11it/s, loss=0.705, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  16%|█▌        | 152/938 [00:10<00:55, 14.11it/s, loss=0.7, v_num=11, val_rmse=0.554, train_rmse=0.726]  
Epoch 2:  16%|█▋        | 153/938 [00:10<00:55, 14.12it/s, loss=0.7, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  16%|█▋        | 153/938 [00:10<00:55, 14.12it/s, loss=0.703, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  16%|█▋        | 154/938 [00:10<00:55, 14.12it/s, loss=0.708, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  17%|█▋        | 155/938 [00:10<00:55, 14.12it/s, loss=0.711, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  17%|█▋        | 156/938 [00:11<00:55, 14.08it/s, loss=0.711, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  17%|█▋        | 156/938 [00:11<00:55, 14.08it/s, loss=0.706, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  17%|█▋        | 157/938 [00:11<00:55, 14.10it/s, loss=0.704, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  17%|█▋        | 158/938 [00:11<00:55, 14.11it/s, loss=0.702, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  17%|█▋        | 159/938 [00:11<00:55, 14.12it/s, loss=0.702, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  17%|█▋        | 159/938 [00:11<00:55, 14.12it/s, loss=0.703, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  17%|█▋        | 160/938 [00:11<00:55, 14.13it/s, loss=0.707, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  17%|█▋        | 161/938 [00:11<00:54, 14.14it/s, loss=0.71, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  17%|█▋        | 162/938 [00:11<00:54, 14.15it/s, loss=0.71, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  17%|█▋        | 162/938 [00:11<00:54, 14.15it/s, loss=0.715, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  17%|█▋        | 163/938 [00:11<00:54, 14.16it/s, loss=0.713, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  17%|█▋        | 164/938 [00:11<00:54, 14.17it/s, loss=0.72, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  18%|█▊        | 165/938 [00:11<00:54, 14.15it/s, loss=0.72, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  18%|█▊        | 165/938 [00:11<00:54, 14.15it/s, loss=0.717, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  18%|█▊        | 166/938 [00:11<00:54, 14.16it/s, loss=0.706, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  18%|█▊        | 167/938 [00:11<00:54, 14.15it/s, loss=0.71, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  18%|█▊        | 168/938 [00:11<00:54, 14.16it/s, loss=0.71, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  18%|█▊        | 168/938 [00:11<00:54, 14.16it/s, loss=0.7, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  18%|█▊        | 169/938 [00:11<00:54, 14.16it/s, loss=0.706, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  18%|█▊        | 170/938 [00:12<00:54, 14.16it/s, loss=0.698, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  18%|█▊        | 171/938 [00:12<00:54, 14.17it/s, loss=0.698, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  18%|█▊        | 171/938 [00:12<00:54, 14.17it/s, loss=0.696, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  18%|█▊        | 172/938 [00:12<00:54, 14.18it/s, loss=0.695, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  18%|█▊        | 173/938 [00:12<00:53, 14.17it/s, loss=0.691, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  19%|█▊        | 174/938 [00:12<00:53, 14.17it/s, loss=0.691, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  19%|█▊        | 174/938 [00:12<00:53, 14.17it/s, loss=0.687, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  19%|█▊        | 175/938 [00:12<00:53, 14.18it/s, loss=0.689, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  19%|█▉        | 176/938 [00:12<00:53, 14.17it/s, loss=0.692, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  19%|█▉        | 177/938 [00:12<00:53, 14.17it/s, loss=0.692, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  19%|█▉        | 177/938 [00:12<00:53, 14.17it/s, loss=0.691, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  19%|█▉        | 178/938 [00:12<00:53, 14.18it/s, loss=0.684, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  19%|█▉        | 179/938 [00:12<00:53, 14.18it/s, loss=0.68, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  19%|█▉        | 180/938 [00:12<00:53, 14.19it/s, loss=0.68, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  19%|█▉        | 180/938 [00:12<00:53, 14.19it/s, loss=0.677, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  19%|█▉        | 181/938 [00:12<00:53, 14.18it/s, loss=0.674, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  19%|█▉        | 182/938 [00:12<00:53, 14.18it/s, loss=0.668, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  20%|█▉        | 183/938 [00:12<00:53, 14.18it/s, loss=0.668, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  20%|█▉        | 183/938 [00:12<00:53, 14.18it/s, loss=0.672, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  20%|█▉        | 184/938 [00:12<00:53, 14.19it/s, loss=0.681, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  20%|█▉        | 185/938 [00:13<00:53, 14.18it/s, loss=0.688, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  20%|█▉        | 186/938 [00:13<00:53, 14.18it/s, loss=0.688, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  20%|█▉        | 186/938 [00:13<00:53, 14.18it/s, loss=0.689, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  20%|█▉        | 187/938 [00:13<00:52, 14.18it/s, loss=0.687, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  20%|██        | 188/938 [00:13<00:52, 14.19it/s, loss=0.686, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  20%|██        | 189/938 [00:13<00:52, 14.19it/s, loss=0.686, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  20%|██        | 189/938 [00:13<00:52, 14.19it/s, loss=0.678, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  20%|██        | 190/938 [00:13<00:52, 14.21it/s, loss=0.68, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  20%|██        | 191/938 [00:13<00:52, 14.20it/s, loss=0.69, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  20%|██        | 192/938 [00:13<00:52, 14.21it/s, loss=0.69, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  20%|██        | 192/938 [00:13<00:52, 14.21it/s, loss=0.691, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  21%|██        | 193/938 [00:13<00:52, 14.22it/s, loss=0.693, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  21%|██        | 194/938 [00:13<00:52, 14.22it/s, loss=0.702, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  21%|██        | 195/938 [00:13<00:52, 14.23it/s, loss=0.702, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  21%|██        | 195/938 [00:13<00:52, 14.23it/s, loss=0.698, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  21%|██        | 196/938 [00:13<00:52, 14.23it/s, loss=0.695, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  21%|██        | 197/938 [00:13<00:52, 14.24it/s, loss=0.692, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  21%|██        | 198/938 [00:13<00:51, 14.24it/s, loss=0.692, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  21%|██        | 198/938 [00:13<00:51, 14.24it/s, loss=0.688, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  21%|██        | 199/938 [00:13<00:51, 14.24it/s, loss=0.686, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  21%|██▏       | 200/938 [00:14<00:51, 14.24it/s, loss=0.682, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  21%|██▏       | 201/938 [00:14<00:51, 14.24it/s, loss=0.682, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  21%|██▏       | 201/938 [00:14<00:51, 14.24it/s, loss=0.68, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  22%|██▏       | 202/938 [00:14<00:51, 14.24it/s, loss=0.683, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  22%|██▏       | 203/938 [00:14<00:51, 14.25it/s, loss=0.672, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  22%|██▏       | 204/938 [00:14<00:51, 14.25it/s, loss=0.672, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  22%|██▏       | 204/938 [00:14<00:51, 14.25it/s, loss=0.656, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  22%|██▏       | 205/938 [00:14<00:51, 14.24it/s, loss=0.637, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  22%|██▏       | 206/938 [00:14<00:51, 14.25it/s, loss=0.637, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  22%|██▏       | 207/938 [00:14<00:51, 14.25it/s, loss=0.637, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  22%|██▏       | 207/938 [00:14<00:51, 14.25it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  22%|██▏       | 208/938 [00:14<00:51, 14.25it/s, loss=0.647, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  22%|██▏       | 209/938 [00:14<00:51, 14.26it/s, loss=0.647, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  22%|██▏       | 210/938 [00:14<00:51, 14.26it/s, loss=0.647, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  22%|██▏       | 210/938 [00:14<00:51, 14.25it/s, loss=0.651, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  22%|██▏       | 211/938 [00:14<00:50, 14.27it/s, loss=0.64, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  23%|██▎       | 212/938 [00:14<00:50, 14.26it/s, loss=0.637, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  23%|██▎       | 213/938 [00:14<00:50, 14.26it/s, loss=0.637, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  23%|██▎       | 213/938 [00:14<00:50, 14.26it/s, loss=0.64, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  23%|██▎       | 214/938 [00:15<00:50, 14.26it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  23%|██▎       | 215/938 [00:15<00:50, 14.26it/s, loss=0.643, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  23%|██▎       | 216/938 [00:15<00:50, 14.27it/s, loss=0.643, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  23%|██▎       | 216/938 [00:15<00:50, 14.27it/s, loss=0.642, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  23%|██▎       | 217/938 [00:15<00:50, 14.28it/s, loss=0.652, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  23%|██▎       | 218/938 [00:15<00:50, 14.28it/s, loss=0.649, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  23%|██▎       | 219/938 [00:15<00:50, 14.27it/s, loss=0.649, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  23%|██▎       | 219/938 [00:15<00:50, 14.27it/s, loss=0.652, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  23%|██▎       | 220/938 [00:15<00:50, 14.27it/s, loss=0.654, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  24%|██▎       | 221/938 [00:15<00:50, 14.27it/s, loss=0.655, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  24%|██▎       | 222/938 [00:15<00:50, 14.27it/s, loss=0.655, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  24%|██▎       | 222/938 [00:15<00:50, 14.27it/s, loss=0.651, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  24%|██▍       | 223/938 [00:15<00:50, 14.28it/s, loss=0.652, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  24%|██▍       | 224/938 [00:15<00:49, 14.28it/s, loss=0.655, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  24%|██▍       | 225/938 [00:15<00:49, 14.29it/s, loss=0.655, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  24%|██▍       | 225/938 [00:15<00:49, 14.29it/s, loss=0.657, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  24%|██▍       | 226/938 [00:15<00:49, 14.25it/s, loss=0.663, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  24%|██▍       | 227/938 [00:15<00:49, 14.26it/s, loss=0.659, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  24%|██▍       | 228/938 [00:15<00:49, 14.25it/s, loss=0.659, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  24%|██▍       | 228/938 [00:15<00:49, 14.25it/s, loss=0.649, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  24%|██▍       | 229/938 [00:16<00:49, 14.24it/s, loss=0.658, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  25%|██▍       | 230/938 [00:16<00:49, 14.25it/s, loss=0.647, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  25%|██▍       | 231/938 [00:16<00:49, 14.26it/s, loss=0.647, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  25%|██▍       | 231/938 [00:16<00:49, 14.26it/s, loss=0.652, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  25%|██▍       | 232/938 [00:16<00:49, 14.26it/s, loss=0.654, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  25%|██▍       | 233/938 [00:16<00:49, 14.26it/s, loss=0.658, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  25%|██▍       | 234/938 [00:16<00:49, 14.26it/s, loss=0.658, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  25%|██▍       | 234/938 [00:16<00:49, 14.26it/s, loss=0.654, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  25%|██▌       | 235/938 [00:16<00:49, 14.26it/s, loss=0.655, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  25%|██▌       | 236/938 [00:16<00:49, 14.26it/s, loss=0.66, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  25%|██▌       | 237/938 [00:16<00:49, 14.25it/s, loss=0.66, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  25%|██▌       | 237/938 [00:16<00:49, 14.25it/s, loss=0.659, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  25%|██▌       | 238/938 [00:16<00:49, 14.25it/s, loss=0.668, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  25%|██▌       | 239/938 [00:16<00:49, 14.25it/s, loss=0.676, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  26%|██▌       | 240/938 [00:16<00:48, 14.26it/s, loss=0.676, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  26%|██▌       | 240/938 [00:16<00:48, 14.26it/s, loss=0.68, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  26%|██▌       | 241/938 [00:16<00:48, 14.27it/s, loss=0.678, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  26%|██▌       | 242/938 [00:16<00:48, 14.27it/s, loss=0.688, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  26%|██▌       | 243/938 [00:17<00:48, 14.26it/s, loss=0.688, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  26%|██▌       | 243/938 [00:17<00:48, 14.26it/s, loss=0.69, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  26%|██▌       | 244/938 [00:17<00:48, 14.27it/s, loss=0.686, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  26%|██▌       | 245/938 [00:17<00:48, 14.26it/s, loss=0.688, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  26%|██▌       | 246/938 [00:17<00:48, 14.27it/s, loss=0.688, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  26%|██▌       | 246/938 [00:17<00:48, 14.27it/s, loss=0.683, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  26%|██▋       | 247/938 [00:17<00:48, 14.26it/s, loss=0.687, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  26%|██▋       | 248/938 [00:17<00:48, 14.25it/s, loss=0.694, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  27%|██▋       | 249/938 [00:17<00:48, 14.26it/s, loss=0.694, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  27%|██▋       | 249/938 [00:17<00:48, 14.26it/s, loss=0.696, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  27%|██▋       | 250/938 [00:17<00:48, 14.26it/s, loss=0.704, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  27%|██▋       | 251/938 [00:17<00:48, 14.25it/s, loss=0.704, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  27%|██▋       | 252/938 [00:17<00:48, 14.26it/s, loss=0.704, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  27%|██▋       | 252/938 [00:17<00:48, 14.26it/s, loss=0.702, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  27%|██▋       | 253/938 [00:17<00:48, 14.26it/s, loss=0.7, v_num=11, val_rmse=0.554, train_rmse=0.726]  
Epoch 2:  27%|██▋       | 254/938 [00:17<00:47, 14.26it/s, loss=0.696, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  27%|██▋       | 255/938 [00:17<00:47, 14.27it/s, loss=0.696, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  27%|██▋       | 255/938 [00:17<00:47, 14.27it/s, loss=0.699, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  27%|██▋       | 256/938 [00:17<00:47, 14.27it/s, loss=0.701, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  27%|██▋       | 257/938 [00:17<00:47, 14.28it/s, loss=0.705, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  28%|██▊       | 258/938 [00:18<00:47, 14.29it/s, loss=0.705, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  28%|██▊       | 258/938 [00:18<00:47, 14.29it/s, loss=0.705, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  28%|██▊       | 259/938 [00:18<00:47, 14.29it/s, loss=0.695, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  28%|██▊       | 260/938 [00:18<00:47, 14.29it/s, loss=0.695, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  28%|██▊       | 261/938 [00:18<00:47, 14.30it/s, loss=0.695, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  28%|██▊       | 261/938 [00:18<00:47, 14.30it/s, loss=0.696, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  28%|██▊       | 262/938 [00:18<00:47, 14.30it/s, loss=0.692, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  28%|██▊       | 263/938 [00:18<00:47, 14.30it/s, loss=0.692, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  28%|██▊       | 264/938 [00:18<00:47, 14.31it/s, loss=0.692, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  28%|██▊       | 264/938 [00:18<00:47, 14.31it/s, loss=0.689, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  28%|██▊       | 265/938 [00:18<00:47, 14.29it/s, loss=0.683, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  28%|██▊       | 266/938 [00:18<00:47, 14.29it/s, loss=0.686, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  28%|██▊       | 267/938 [00:18<00:46, 14.29it/s, loss=0.686, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  28%|██▊       | 267/938 [00:18<00:46, 14.29it/s, loss=0.681, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  29%|██▊       | 268/938 [00:18<00:46, 14.29it/s, loss=0.682, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  29%|██▊       | 269/938 [00:18<00:46, 14.29it/s, loss=0.672, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  29%|██▉       | 270/938 [00:18<00:46, 14.26it/s, loss=0.672, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  29%|██▉       | 270/938 [00:18<00:46, 14.26it/s, loss=0.661, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  29%|██▉       | 271/938 [00:19<00:46, 14.26it/s, loss=0.664, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  29%|██▉       | 272/938 [00:19<00:46, 14.27it/s, loss=0.661, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  29%|██▉       | 273/938 [00:19<00:46, 14.27it/s, loss=0.661, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  29%|██▉       | 273/938 [00:19<00:46, 14.27it/s, loss=0.666, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  29%|██▉       | 274/938 [00:19<00:46, 14.26it/s, loss=0.675, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  29%|██▉       | 275/938 [00:19<00:46, 14.25it/s, loss=0.671, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  29%|██▉       | 276/938 [00:19<00:46, 14.25it/s, loss=0.671, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  29%|██▉       | 276/938 [00:19<00:46, 14.25it/s, loss=0.662, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  30%|██▉       | 277/938 [00:19<00:46, 14.26it/s, loss=0.65, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  30%|██▉       | 278/938 [00:19<00:46, 14.26it/s, loss=0.648, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  30%|██▉       | 279/938 [00:19<00:46, 14.26it/s, loss=0.648, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  30%|██▉       | 279/938 [00:19<00:46, 14.26it/s, loss=0.647, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  30%|██▉       | 280/938 [00:19<00:46, 14.26it/s, loss=0.649, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  30%|██▉       | 281/938 [00:19<00:46, 14.26it/s, loss=0.648, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  30%|███       | 282/938 [00:19<00:46, 14.26it/s, loss=0.648, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  30%|███       | 282/938 [00:19<00:46, 14.26it/s, loss=0.648, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  30%|███       | 283/938 [00:19<00:45, 14.26it/s, loss=0.648, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  30%|███       | 284/938 [00:19<00:45, 14.27it/s, loss=0.654, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  30%|███       | 285/938 [00:19<00:45, 14.26it/s, loss=0.654, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  30%|███       | 285/938 [00:19<00:45, 14.26it/s, loss=0.664, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  30%|███       | 286/938 [00:20<00:45, 14.27it/s, loss=0.661, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  31%|███       | 287/938 [00:20<00:45, 14.27it/s, loss=0.674, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  31%|███       | 288/938 [00:20<00:45, 14.27it/s, loss=0.674, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  31%|███       | 288/938 [00:20<00:45, 14.26it/s, loss=0.675, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  31%|███       | 289/938 [00:20<00:45, 14.27it/s, loss=0.674, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  31%|███       | 290/938 [00:20<00:45, 14.26it/s, loss=0.679, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  31%|███       | 291/938 [00:20<00:45, 14.26it/s, loss=0.679, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  31%|███       | 291/938 [00:20<00:45, 14.26it/s, loss=0.678, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  31%|███       | 292/938 [00:20<00:45, 14.27it/s, loss=0.676, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  31%|███       | 293/938 [00:20<00:45, 14.27it/s, loss=0.665, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  31%|███▏      | 294/938 [00:20<00:45, 14.27it/s, loss=0.665, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  31%|███▏      | 294/938 [00:20<00:45, 14.27it/s, loss=0.664, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  31%|███▏      | 295/938 [00:20<00:45, 14.28it/s, loss=0.665, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  32%|███▏      | 296/938 [00:20<00:44, 14.28it/s, loss=0.663, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  32%|███▏      | 297/938 [00:20<00:44, 14.27it/s, loss=0.663, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  32%|███▏      | 297/938 [00:20<00:44, 14.27it/s, loss=0.674, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  32%|███▏      | 298/938 [00:20<00:44, 14.25it/s, loss=0.676, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  32%|███▏      | 299/938 [00:20<00:44, 14.25it/s, loss=0.675, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  32%|███▏      | 300/938 [00:21<00:44, 14.25it/s, loss=0.675, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  32%|███▏      | 300/938 [00:21<00:44, 14.25it/s, loss=0.669, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  32%|███▏      | 301/938 [00:21<00:44, 14.26it/s, loss=0.672, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  32%|███▏      | 302/938 [00:21<00:44, 14.25it/s, loss=0.67, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  32%|███▏      | 303/938 [00:21<00:44, 14.25it/s, loss=0.67, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  32%|███▏      | 303/938 [00:21<00:44, 14.25it/s, loss=0.672, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  32%|███▏      | 304/938 [00:21<00:44, 14.25it/s, loss=0.669, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  33%|███▎      | 305/938 [00:21<00:44, 14.25it/s, loss=0.668, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  33%|███▎      | 306/938 [00:21<00:44, 14.25it/s, loss=0.668, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  33%|███▎      | 306/938 [00:21<00:44, 14.25it/s, loss=0.668, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  33%|███▎      | 307/938 [00:21<00:44, 14.25it/s, loss=0.659, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  33%|███▎      | 308/938 [00:21<00:44, 14.26it/s, loss=0.657, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  33%|███▎      | 309/938 [00:21<00:44, 14.25it/s, loss=0.657, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  33%|███▎      | 309/938 [00:21<00:44, 14.25it/s, loss=0.661, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  33%|███▎      | 310/938 [00:21<00:44, 14.26it/s, loss=0.658, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  33%|███▎      | 311/938 [00:21<00:43, 14.26it/s, loss=0.66, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  33%|███▎      | 312/938 [00:21<00:43, 14.27it/s, loss=0.66, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  33%|███▎      | 312/938 [00:21<00:43, 14.27it/s, loss=0.664, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  33%|███▎      | 313/938 [00:21<00:43, 14.27it/s, loss=0.666, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  33%|███▎      | 314/938 [00:21<00:43, 14.28it/s, loss=0.665, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  34%|███▎      | 315/938 [00:22<00:43, 14.28it/s, loss=0.665, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  34%|███▎      | 315/938 [00:22<00:43, 14.28it/s, loss=0.668, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  34%|███▎      | 316/938 [00:22<00:43, 14.27it/s, loss=0.674, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  34%|███▍      | 317/938 [00:22<00:43, 14.27it/s, loss=0.667, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  34%|███▍      | 318/938 [00:22<00:43, 14.26it/s, loss=0.667, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  34%|███▍      | 318/938 [00:22<00:43, 14.26it/s, loss=0.666, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  34%|███▍      | 319/938 [00:22<00:43, 14.25it/s, loss=0.674, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  34%|███▍      | 320/938 [00:22<00:43, 14.25it/s, loss=0.674, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  34%|███▍      | 321/938 [00:22<00:43, 14.26it/s, loss=0.674, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  34%|███▍      | 321/938 [00:22<00:43, 14.26it/s, loss=0.672, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  34%|███▍      | 322/938 [00:22<00:43, 14.26it/s, loss=0.677, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  34%|███▍      | 323/938 [00:22<00:43, 14.26it/s, loss=0.676, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  35%|███▍      | 324/938 [00:22<00:43, 14.27it/s, loss=0.676, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  35%|███▍      | 324/938 [00:22<00:43, 14.27it/s, loss=0.684, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  35%|███▍      | 325/938 [00:22<00:42, 14.27it/s, loss=0.689, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  35%|███▍      | 326/938 [00:22<00:42, 14.27it/s, loss=0.69, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  35%|███▍      | 327/938 [00:22<00:42, 14.28it/s, loss=0.69, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  35%|███▍      | 327/938 [00:22<00:42, 14.28it/s, loss=0.686, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  35%|███▍      | 328/938 [00:22<00:42, 14.28it/s, loss=0.684, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  35%|███▌      | 329/938 [00:23<00:42, 14.29it/s, loss=0.69, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  35%|███▌      | 330/938 [00:23<00:42, 14.29it/s, loss=0.69, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  35%|███▌      | 330/938 [00:23<00:42, 14.29it/s, loss=0.694, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  35%|███▌      | 331/938 [00:23<00:42, 14.29it/s, loss=0.693, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  35%|███▌      | 332/938 [00:23<00:42, 14.29it/s, loss=0.697, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  36%|███▌      | 333/938 [00:23<00:42, 14.30it/s, loss=0.697, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  36%|███▌      | 333/938 [00:23<00:42, 14.30it/s, loss=0.691, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  36%|███▌      | 334/938 [00:23<00:42, 14.29it/s, loss=0.686, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  36%|███▌      | 335/938 [00:23<00:42, 14.29it/s, loss=0.684, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  36%|███▌      | 336/938 [00:23<00:42, 14.28it/s, loss=0.684, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  36%|███▌      | 336/938 [00:23<00:42, 14.28it/s, loss=0.679, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  36%|███▌      | 337/938 [00:23<00:42, 14.28it/s, loss=0.679, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  36%|███▌      | 338/938 [00:23<00:42, 14.28it/s, loss=0.68, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  36%|███▌      | 339/938 [00:23<00:41, 14.27it/s, loss=0.68, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  36%|███▌      | 339/938 [00:23<00:41, 14.27it/s, loss=0.667, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  36%|███▌      | 340/938 [00:23<00:41, 14.28it/s, loss=0.672, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  36%|███▋      | 341/938 [00:23<00:41, 14.27it/s, loss=0.67, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  36%|███▋      | 342/938 [00:23<00:41, 14.27it/s, loss=0.67, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  36%|███▋      | 342/938 [00:23<00:41, 14.27it/s, loss=0.663, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  37%|███▋      | 343/938 [00:24<00:41, 14.26it/s, loss=0.664, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  37%|███▋      | 344/938 [00:24<00:41, 14.26it/s, loss=0.66, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  37%|███▋      | 345/938 [00:24<00:41, 14.25it/s, loss=0.66, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  37%|███▋      | 345/938 [00:24<00:41, 14.25it/s, loss=0.652, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  37%|███▋      | 346/938 [00:24<00:41, 14.25it/s, loss=0.66, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  37%|███▋      | 347/938 [00:24<00:41, 14.25it/s, loss=0.664, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  37%|███▋      | 348/938 [00:24<00:41, 14.25it/s, loss=0.664, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  37%|███▋      | 348/938 [00:24<00:41, 14.25it/s, loss=0.661, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  37%|███▋      | 349/938 [00:24<00:41, 14.25it/s, loss=0.657, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  37%|███▋      | 350/938 [00:24<00:41, 14.26it/s, loss=0.661, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  37%|███▋      | 351/938 [00:24<00:41, 14.26it/s, loss=0.661, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  37%|███▋      | 351/938 [00:24<00:41, 14.26it/s, loss=0.657, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  38%|███▊      | 352/938 [00:24<00:41, 14.26it/s, loss=0.666, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  38%|███▊      | 353/938 [00:24<00:41, 14.25it/s, loss=0.669, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  38%|███▊      | 354/938 [00:24<00:40, 14.25it/s, loss=0.669, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  38%|███▊      | 354/938 [00:24<00:40, 14.25it/s, loss=0.678, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  38%|███▊      | 355/938 [00:24<00:40, 14.26it/s, loss=0.673, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  38%|███▊      | 356/938 [00:24<00:40, 14.25it/s, loss=0.673, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  38%|███▊      | 357/938 [00:25<00:40, 14.25it/s, loss=0.673, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  38%|███▊      | 357/938 [00:25<00:40, 14.25it/s, loss=0.68, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  38%|███▊      | 358/938 [00:25<00:40, 14.24it/s, loss=0.682, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  38%|███▊      | 359/938 [00:25<00:40, 14.24it/s, loss=0.689, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  38%|███▊      | 360/938 [00:25<00:40, 14.25it/s, loss=0.689, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  38%|███▊      | 360/938 [00:25<00:40, 14.25it/s, loss=0.686, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  38%|███▊      | 361/938 [00:25<00:40, 14.24it/s, loss=0.685, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  39%|███▊      | 362/938 [00:25<00:40, 14.25it/s, loss=0.688, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  39%|███▊      | 363/938 [00:25<00:40, 14.24it/s, loss=0.688, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  39%|███▊      | 363/938 [00:25<00:40, 14.24it/s, loss=0.685, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  39%|███▉      | 364/938 [00:25<00:40, 14.23it/s, loss=0.679, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  39%|███▉      | 365/938 [00:25<00:40, 14.23it/s, loss=0.686, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  39%|███▉      | 366/938 [00:25<00:40, 14.23it/s, loss=0.686, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  39%|███▉      | 366/938 [00:25<00:40, 14.23it/s, loss=0.674, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  39%|███▉      | 367/938 [00:25<00:40, 14.23it/s, loss=0.669, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  39%|███▉      | 368/938 [00:25<00:40, 14.23it/s, loss=0.671, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  39%|███▉      | 369/938 [00:25<00:39, 14.23it/s, loss=0.671, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  39%|███▉      | 369/938 [00:25<00:39, 14.23it/s, loss=0.677, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  39%|███▉      | 370/938 [00:25<00:39, 14.23it/s, loss=0.673, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  40%|███▉      | 371/938 [00:26<00:39, 14.24it/s, loss=0.681, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  40%|███▉      | 372/938 [00:26<00:39, 14.24it/s, loss=0.681, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  40%|███▉      | 372/938 [00:26<00:39, 14.24it/s, loss=0.671, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  40%|███▉      | 373/938 [00:26<00:39, 14.22it/s, loss=0.678, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  40%|███▉      | 374/938 [00:26<00:39, 14.23it/s, loss=0.667, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  40%|███▉      | 375/938 [00:26<00:39, 14.23it/s, loss=0.667, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  40%|███▉      | 375/938 [00:26<00:39, 14.23it/s, loss=0.669, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  40%|████      | 376/938 [00:26<00:39, 14.22it/s, loss=0.674, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  40%|████      | 377/938 [00:26<00:39, 14.22it/s, loss=0.668, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  40%|████      | 378/938 [00:26<00:39, 14.22it/s, loss=0.668, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  40%|████      | 378/938 [00:26<00:39, 14.22it/s, loss=0.664, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  40%|████      | 379/938 [00:26<00:39, 14.22it/s, loss=0.661, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  41%|████      | 380/938 [00:26<00:39, 14.23it/s, loss=0.657, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  41%|████      | 381/938 [00:26<00:39, 14.23it/s, loss=0.657, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  41%|████      | 381/938 [00:26<00:39, 14.23it/s, loss=0.655, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  41%|████      | 382/938 [00:26<00:39, 14.23it/s, loss=0.655, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  41%|████      | 383/938 [00:26<00:38, 14.24it/s, loss=0.66, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  41%|████      | 384/938 [00:26<00:38, 14.24it/s, loss=0.66, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  41%|████      | 384/938 [00:26<00:38, 14.24it/s, loss=0.658, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  41%|████      | 385/938 [00:27<00:38, 14.25it/s, loss=0.652, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  41%|████      | 386/938 [00:27<00:38, 14.25it/s, loss=0.654, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  41%|████▏     | 387/938 [00:27<00:38, 14.26it/s, loss=0.654, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  41%|████▏     | 387/938 [00:27<00:38, 14.26it/s, loss=0.66, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  41%|████▏     | 388/938 [00:27<00:38, 14.26it/s, loss=0.665, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  41%|████▏     | 389/938 [00:27<00:38, 14.26it/s, loss=0.65, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  42%|████▏     | 390/938 [00:27<00:38, 14.26it/s, loss=0.65, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  42%|████▏     | 390/938 [00:27<00:38, 14.26it/s, loss=0.649, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  42%|████▏     | 391/938 [00:27<00:38, 14.25it/s, loss=0.647, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  42%|████▏     | 392/938 [00:27<00:38, 14.26it/s, loss=0.64, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  42%|████▏     | 393/938 [00:27<00:38, 14.26it/s, loss=0.64, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  42%|████▏     | 393/938 [00:27<00:38, 14.26it/s, loss=0.641, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  42%|████▏     | 394/938 [00:27<00:38, 14.26it/s, loss=0.647, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  42%|████▏     | 395/938 [00:27<00:38, 14.27it/s, loss=0.643, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  42%|████▏     | 396/938 [00:27<00:37, 14.27it/s, loss=0.643, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  42%|████▏     | 396/938 [00:27<00:37, 14.27it/s, loss=0.647, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  42%|████▏     | 397/938 [00:27<00:37, 14.27it/s, loss=0.64, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  42%|████▏     | 398/938 [00:27<00:37, 14.27it/s, loss=0.64, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  43%|████▎     | 399/938 [00:27<00:37, 14.26it/s, loss=0.64, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  43%|████▎     | 399/938 [00:27<00:37, 14.26it/s, loss=0.644, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  43%|████▎     | 400/938 [00:28<00:37, 14.26it/s, loss=0.646, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  43%|████▎     | 401/938 [00:28<00:37, 14.27it/s, loss=0.646, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  43%|████▎     | 402/938 [00:28<00:37, 14.26it/s, loss=0.646, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  43%|████▎     | 402/938 [00:28<00:37, 14.26it/s, loss=0.647, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  43%|████▎     | 403/938 [00:28<00:37, 14.25it/s, loss=0.643, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  43%|████▎     | 404/938 [00:28<00:37, 14.25it/s, loss=0.658, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  43%|████▎     | 405/938 [00:28<00:37, 14.25it/s, loss=0.658, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  43%|████▎     | 405/938 [00:28<00:37, 14.25it/s, loss=0.661, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  43%|████▎     | 406/938 [00:28<00:37, 14.25it/s, loss=0.662, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  43%|████▎     | 407/938 [00:28<00:37, 14.26it/s, loss=0.66, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  43%|████▎     | 408/938 [00:28<00:37, 14.26it/s, loss=0.66, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  43%|████▎     | 408/938 [00:28<00:37, 14.26it/s, loss=0.661, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  44%|████▎     | 409/938 [00:28<00:37, 14.26it/s, loss=0.665, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  44%|████▎     | 410/938 [00:28<00:37, 14.26it/s, loss=0.661, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  44%|████▍     | 411/938 [00:28<00:36, 14.26it/s, loss=0.661, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  44%|████▍     | 411/938 [00:28<00:36, 14.26it/s, loss=0.66, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  44%|████▍     | 412/938 [00:28<00:36, 14.26it/s, loss=0.668, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  44%|████▍     | 413/938 [00:28<00:36, 14.27it/s, loss=0.661, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  44%|████▍     | 414/938 [00:29<00:36, 14.26it/s, loss=0.661, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  44%|████▍     | 414/938 [00:29<00:36, 14.26it/s, loss=0.666, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  44%|████▍     | 415/938 [00:29<00:36, 14.26it/s, loss=0.673, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  44%|████▍     | 416/938 [00:29<00:36, 14.27it/s, loss=0.667, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  44%|████▍     | 417/938 [00:29<00:36, 14.26it/s, loss=0.667, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  44%|████▍     | 417/938 [00:29<00:36, 14.26it/s, loss=0.67, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  45%|████▍     | 418/938 [00:29<00:36, 14.26it/s, loss=0.671, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  45%|████▍     | 419/938 [00:29<00:36, 14.27it/s, loss=0.666, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  45%|████▍     | 420/938 [00:29<00:36, 14.27it/s, loss=0.666, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  45%|████▍     | 420/938 [00:29<00:36, 14.27it/s, loss=0.675, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  45%|████▍     | 421/938 [00:29<00:36, 14.27it/s, loss=0.672, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  45%|████▍     | 422/938 [00:29<00:36, 14.28it/s, loss=0.663, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  45%|████▌     | 423/938 [00:29<00:36, 14.27it/s, loss=0.663, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  45%|████▌     | 423/938 [00:29<00:36, 14.27it/s, loss=0.662, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  45%|████▌     | 424/938 [00:29<00:36, 14.27it/s, loss=0.652, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  45%|████▌     | 425/938 [00:29<00:35, 14.28it/s, loss=0.65, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  45%|████▌     | 426/938 [00:29<00:35, 14.27it/s, loss=0.65, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  45%|████▌     | 426/938 [00:29<00:35, 14.27it/s, loss=0.652, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  46%|████▌     | 427/938 [00:29<00:35, 14.27it/s, loss=0.658, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  46%|████▌     | 428/938 [00:29<00:35, 14.27it/s, loss=0.662, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  46%|████▌     | 429/938 [00:30<00:35, 14.27it/s, loss=0.662, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  46%|████▌     | 429/938 [00:30<00:35, 14.27it/s, loss=0.663, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  46%|████▌     | 430/938 [00:30<00:35, 14.28it/s, loss=0.67, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  46%|████▌     | 431/938 [00:30<00:35, 14.28it/s, loss=0.668, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  46%|████▌     | 432/938 [00:30<00:35, 14.28it/s, loss=0.668, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  46%|████▌     | 432/938 [00:30<00:35, 14.28it/s, loss=0.668, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  46%|████▌     | 433/938 [00:30<00:35, 14.28it/s, loss=0.668, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  46%|████▋     | 434/938 [00:30<00:35, 14.29it/s, loss=0.662, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  46%|████▋     | 435/938 [00:30<00:35, 14.28it/s, loss=0.662, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  46%|████▋     | 435/938 [00:30<00:35, 14.28it/s, loss=0.661, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  46%|████▋     | 436/938 [00:30<00:35, 14.28it/s, loss=0.666, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  47%|████▋     | 437/938 [00:30<00:35, 14.28it/s, loss=0.664, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  47%|████▋     | 438/938 [00:30<00:35, 14.28it/s, loss=0.664, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  47%|████▋     | 438/938 [00:30<00:35, 14.28it/s, loss=0.668, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  47%|████▋     | 439/938 [00:30<00:34, 14.27it/s, loss=0.668, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  47%|████▋     | 440/938 [00:30<00:34, 14.28it/s, loss=0.66, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  47%|████▋     | 441/938 [00:30<00:34, 14.28it/s, loss=0.66, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  47%|████▋     | 441/938 [00:30<00:34, 14.28it/s, loss=0.665, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  47%|████▋     | 442/938 [00:30<00:34, 14.28it/s, loss=0.666, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  47%|████▋     | 443/938 [00:31<00:34, 14.28it/s, loss=0.665, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  47%|████▋     | 444/938 [00:31<00:34, 14.28it/s, loss=0.665, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  47%|████▋     | 444/938 [00:31<00:34, 14.28it/s, loss=0.67, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  47%|████▋     | 445/938 [00:31<00:34, 14.28it/s, loss=0.668, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  48%|████▊     | 446/938 [00:31<00:34, 14.27it/s, loss=0.667, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  48%|████▊     | 447/938 [00:31<00:34, 14.27it/s, loss=0.667, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  48%|████▊     | 447/938 [00:31<00:34, 14.27it/s, loss=0.659, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  48%|████▊     | 448/938 [00:31<00:34, 14.28it/s, loss=0.652, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  48%|████▊     | 449/938 [00:31<00:34, 14.28it/s, loss=0.652, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  48%|████▊     | 450/938 [00:31<00:34, 14.28it/s, loss=0.652, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  48%|████▊     | 450/938 [00:31<00:34, 14.28it/s, loss=0.649, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  48%|████▊     | 451/938 [00:31<00:34, 14.25it/s, loss=0.651, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  48%|████▊     | 452/938 [00:31<00:34, 14.25it/s, loss=0.643, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  48%|████▊     | 453/938 [00:31<00:34, 14.25it/s, loss=0.643, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  48%|████▊     | 453/938 [00:31<00:34, 14.25it/s, loss=0.646, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  48%|████▊     | 454/938 [00:31<00:33, 14.25it/s, loss=0.643, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  49%|████▊     | 455/938 [00:31<00:33, 14.26it/s, loss=0.635, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  49%|████▊     | 456/938 [00:31<00:33, 14.26it/s, loss=0.635, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  49%|████▊     | 456/938 [00:31<00:33, 14.26it/s, loss=0.63, v_num=11, val_rmse=0.554, train_rmse=0.726] 
Epoch 2:  49%|████▊     | 457/938 [00:32<00:33, 14.26it/s, loss=0.625, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  49%|████▉     | 458/938 [00:32<00:33, 14.26it/s, loss=0.625, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  49%|████▉     | 459/938 [00:32<00:33, 14.26it/s, loss=0.625, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  49%|████▉     | 459/938 [00:32<00:33, 14.26it/s, loss=0.625, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  49%|████▉     | 460/938 [00:32<00:33, 14.27it/s, loss=0.625, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  49%|████▉     | 461/938 [00:32<00:33, 14.27it/s, loss=0.622, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  49%|████▉     | 462/938 [00:32<00:33, 14.27it/s, loss=0.622, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  49%|████▉     | 462/938 [00:32<00:33, 14.27it/s, loss=0.625, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  49%|████▉     | 463/938 [00:32<00:33, 14.27it/s, loss=0.628, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  49%|████▉     | 464/938 [00:32<00:33, 14.27it/s, loss=0.621, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  50%|████▉     | 465/938 [00:32<00:33, 14.28it/s, loss=0.621, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  50%|████▉     | 465/938 [00:32<00:33, 14.28it/s, loss=0.633, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  50%|████▉     | 466/938 [00:32<00:33, 14.27it/s, loss=0.629, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  50%|████▉     | 467/938 [00:32<00:33, 14.27it/s, loss=0.638, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  50%|████▉     | 468/938 [00:32<00:32, 14.28it/s, loss=0.638, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  50%|████▉     | 468/938 [00:32<00:32, 14.28it/s, loss=0.642, v_num=11, val_rmse=0.554, train_rmse=0.726]
Epoch 2:  50%|█████     | 469/938 [00:32<00:32, 14.29it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]
Epoch 2:  50%|█████     | 471/938 [00:32<00:32, 14.32it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:   1%|          | 3/469 [00:00<00:21, 21.60it/s]
Epoch 2:  51%|█████     | 474/938 [00:33<00:32, 14.36it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:   1%|▏         | 6/469 [00:00<00:19, 23.92it/s]
Epoch 2:  51%|█████     | 477/938 [00:33<00:32, 14.40it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:   2%|▏         | 9/469 [00:00<00:19, 24.04it/s]
Epoch 2:  51%|█████     | 480/938 [00:33<00:31, 14.44it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:   3%|▎         | 12/469 [00:00<00:18, 24.92it/s]
Epoch 2:  51%|█████▏    | 483/938 [00:33<00:31, 14.48it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:   3%|▎         | 15/469 [00:00<00:18, 24.52it/s]
Epoch 2:  52%|█████▏    | 486/938 [00:33<00:31, 14.51it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:   4%|▍         | 18/469 [00:00<00:18, 24.55it/s]
Epoch 2:  52%|█████▏    | 489/938 [00:33<00:30, 14.55it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:   4%|▍         | 21/469 [00:00<00:17, 25.05it/s]
Epoch 2:  52%|█████▏    | 492/938 [00:33<00:30, 14.59it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:   5%|▌         | 24/469 [00:00<00:17, 24.95it/s]
Epoch 2:  53%|█████▎    | 495/938 [00:33<00:30, 14.63it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:   6%|▌         | 27/469 [00:01<00:17, 25.53it/s]
Epoch 2:  53%|█████▎    | 498/938 [00:33<00:29, 14.67it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:   6%|▋         | 30/469 [00:01<00:16, 25.93it/s]
Epoch 2:  53%|█████▎    | 501/938 [00:34<00:29, 14.71it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:   7%|▋         | 33/469 [00:01<00:17, 25.06it/s]
Epoch 2:  54%|█████▎    | 504/938 [00:34<00:29, 14.74it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:   8%|▊         | 36/469 [00:01<00:17, 24.43it/s]
Epoch 2:  54%|█████▍    | 507/938 [00:34<00:29, 14.77it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:   8%|▊         | 39/469 [00:01<00:16, 25.55it/s]
Epoch 2:  54%|█████▍    | 510/938 [00:34<00:28, 14.82it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:   9%|▉         | 42/469 [00:01<00:16, 26.48it/s]
Epoch 2:  55%|█████▍    | 513/938 [00:34<00:28, 14.85it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  10%|▉         | 45/469 [00:01<00:17, 24.63it/s]
Epoch 2:  55%|█████▌    | 516/938 [00:34<00:28, 14.88it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  10%|█         | 48/469 [00:01<00:17, 23.56it/s]
Epoch 2:  55%|█████▌    | 519/938 [00:34<00:28, 14.91it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  11%|█         | 51/469 [00:02<00:17, 24.04it/s]
Epoch 2:  56%|█████▌    | 522/938 [00:34<00:27, 14.94it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  12%|█▏        | 54/469 [00:02<00:17, 24.14it/s]
Epoch 2:  56%|█████▌    | 525/938 [00:35<00:27, 14.98it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  12%|█▏        | 57/469 [00:02<00:16, 24.80it/s]
Epoch 2:  56%|█████▋    | 528/938 [00:35<00:27, 15.01it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  13%|█▎        | 60/469 [00:02<00:16, 24.36it/s]
Epoch 2:  57%|█████▋    | 531/938 [00:35<00:27, 15.04it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  13%|█▎        | 63/469 [00:02<00:16, 24.71it/s]
Epoch 2:  57%|█████▋    | 534/938 [00:35<00:26, 15.08it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  14%|█▍        | 66/469 [00:02<00:16, 24.49it/s]
Epoch 2:  57%|█████▋    | 537/938 [00:35<00:26, 15.11it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  15%|█▍        | 69/469 [00:02<00:15, 25.03it/s]
Epoch 2:  58%|█████▊    | 540/938 [00:35<00:26, 15.15it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  15%|█▌        | 72/469 [00:02<00:16, 24.70it/s]
Epoch 2:  58%|█████▊    | 543/938 [00:35<00:26, 15.17it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  16%|█▌        | 75/469 [00:03<00:16, 24.14it/s]
Epoch 2:  58%|█████▊    | 546/938 [00:35<00:25, 15.20it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  17%|█▋        | 78/469 [00:03<00:15, 25.03it/s]
Epoch 2:  59%|█████▊    | 549/938 [00:36<00:25, 15.24it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  17%|█▋        | 81/469 [00:03<00:15, 25.64it/s]
Epoch 2:  59%|█████▉    | 552/938 [00:36<00:25, 15.28it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  18%|█▊        | 84/469 [00:03<00:15, 25.53it/s]
Epoch 2:  59%|█████▉    | 555/938 [00:36<00:25, 15.31it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  19%|█▊        | 87/469 [00:03<00:14, 25.80it/s]
Epoch 2:  59%|█████▉    | 558/938 [00:36<00:24, 15.35it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  19%|█▉        | 90/469 [00:03<00:14, 26.46it/s]
Epoch 2:  60%|█████▉    | 561/938 [00:36<00:24, 15.38it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  20%|█▉        | 93/469 [00:03<00:14, 25.91it/s]
Epoch 2:  60%|██████    | 564/938 [00:36<00:24, 15.41it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  20%|██        | 96/469 [00:03<00:14, 25.11it/s]
Epoch 2:  60%|██████    | 567/938 [00:36<00:24, 15.44it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  21%|██        | 99/469 [00:03<00:14, 26.14it/s]
Epoch 2:  61%|██████    | 570/938 [00:36<00:23, 15.48it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  22%|██▏       | 102/469 [00:04<00:14, 25.73it/s]
Epoch 2:  61%|██████    | 573/938 [00:36<00:23, 15.51it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  22%|██▏       | 105/469 [00:04<00:14, 25.71it/s]
Epoch 2:  61%|██████▏   | 576/938 [00:37<00:23, 15.54it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  23%|██▎       | 108/469 [00:04<00:13, 26.03it/s]
Epoch 2:  62%|██████▏   | 579/938 [00:37<00:23, 15.58it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  24%|██▎       | 111/469 [00:04<00:13, 26.45it/s]
Epoch 2:  62%|██████▏   | 582/938 [00:37<00:22, 15.61it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  24%|██▍       | 114/469 [00:04<00:13, 26.66it/s]
Epoch 2:  62%|██████▏   | 585/938 [00:37<00:22, 15.64it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  25%|██▍       | 117/469 [00:04<00:13, 25.97it/s]
Epoch 2:  63%|██████▎   | 588/938 [00:37<00:22, 15.68it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  26%|██▌       | 120/469 [00:04<00:13, 26.29it/s]
Epoch 2:  63%|██████▎   | 591/938 [00:37<00:22, 15.71it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  26%|██▌       | 123/469 [00:04<00:13, 26.20it/s]
Epoch 2:  63%|██████▎   | 594/938 [00:37<00:21, 15.74it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  27%|██▋       | 126/469 [00:04<00:13, 26.10it/s]
Epoch 2:  64%|██████▎   | 597/938 [00:37<00:21, 15.77it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  28%|██▊       | 129/469 [00:05<00:13, 25.70it/s]
Epoch 2:  64%|██████▍   | 600/938 [00:37<00:21, 15.80it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  28%|██▊       | 132/469 [00:05<00:12, 25.98it/s]
Epoch 2:  64%|██████▍   | 603/938 [00:38<00:21, 15.84it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  29%|██▉       | 135/469 [00:05<00:12, 26.50it/s]
Epoch 2:  65%|██████▍   | 606/938 [00:38<00:20, 15.87it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  29%|██▉       | 138/469 [00:05<00:12, 27.06it/s]
Epoch 2:  65%|██████▍   | 609/938 [00:38<00:20, 15.90it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  30%|███       | 141/469 [00:05<00:12, 26.67it/s]
Epoch 2:  65%|██████▌   | 612/938 [00:38<00:20, 15.93it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  31%|███       | 144/469 [00:05<00:12, 26.47it/s]
Epoch 2:  66%|██████▌   | 615/938 [00:38<00:20, 15.96it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  31%|███▏      | 147/469 [00:05<00:12, 25.90it/s]
Epoch 2:  66%|██████▌   | 618/938 [00:38<00:20, 15.99it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  32%|███▏      | 150/469 [00:05<00:12, 25.39it/s]
Epoch 2:  66%|██████▌   | 621/938 [00:38<00:19, 16.01it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  33%|███▎      | 153/469 [00:06<00:12, 24.75it/s]
Epoch 2:  67%|██████▋   | 624/938 [00:38<00:19, 16.04it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  33%|███▎      | 156/469 [00:06<00:12, 24.38it/s]
Epoch 2:  67%|██████▋   | 627/938 [00:39<00:19, 16.06it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  34%|███▍      | 159/469 [00:06<00:12, 24.90it/s]
Epoch 2:  67%|██████▋   | 630/938 [00:39<00:19, 16.09it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  35%|███▍      | 162/469 [00:06<00:11, 25.75it/s]
Epoch 2:  67%|██████▋   | 633/938 [00:39<00:18, 16.13it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  35%|███▌      | 165/469 [00:06<00:12, 24.85it/s]
Epoch 2:  68%|██████▊   | 636/938 [00:39<00:18, 16.15it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  36%|███▌      | 168/469 [00:06<00:11, 25.27it/s]
Epoch 2:  68%|██████▊   | 639/938 [00:39<00:18, 16.18it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  36%|███▋      | 171/469 [00:06<00:11, 25.34it/s]
Epoch 2:  68%|██████▊   | 642/938 [00:39<00:18, 16.21it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  37%|███▋      | 174/469 [00:06<00:11, 25.21it/s]
Epoch 2:  69%|██████▉   | 645/938 [00:39<00:18, 16.23it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  38%|███▊      | 177/469 [00:06<00:11, 25.65it/s]
Epoch 2:  69%|██████▉   | 648/938 [00:39<00:17, 16.26it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  38%|███▊      | 180/469 [00:07<00:11, 25.37it/s]
Epoch 2:  69%|██████▉   | 651/938 [00:39<00:17, 16.29it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  39%|███▉      | 183/469 [00:07<00:11, 25.50it/s]
Epoch 2:  70%|██████▉   | 654/938 [00:40<00:17, 16.32it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  40%|███▉      | 186/469 [00:07<00:10, 26.02it/s]
Epoch 2:  70%|███████   | 657/938 [00:40<00:17, 16.35it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  40%|████      | 189/469 [00:07<00:10, 25.86it/s]
Epoch 2:  70%|███████   | 660/938 [00:40<00:16, 16.37it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  41%|████      | 192/469 [00:07<00:10, 25.49it/s]
Epoch 2:  71%|███████   | 663/938 [00:40<00:16, 16.39it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  42%|████▏     | 195/469 [00:07<00:11, 23.77it/s]
Epoch 2:  71%|███████   | 666/938 [00:40<00:16, 16.41it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  42%|████▏     | 198/469 [00:07<00:10, 24.71it/s]
Epoch 2:  71%|███████▏  | 669/938 [00:40<00:16, 16.44it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  43%|████▎     | 201/469 [00:07<00:10, 24.72it/s]
Epoch 2:  72%|███████▏  | 672/938 [00:40<00:16, 16.47it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  43%|████▎     | 204/469 [00:08<00:10, 24.84it/s]
Epoch 2:  72%|███████▏  | 675/938 [00:40<00:15, 16.49it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  44%|████▍     | 207/469 [00:08<00:10, 25.30it/s]
Epoch 2:  72%|███████▏  | 678/938 [00:41<00:15, 16.52it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  45%|████▍     | 210/469 [00:08<00:09, 25.94it/s]
Epoch 2:  73%|███████▎  | 681/938 [00:41<00:15, 16.55it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  45%|████▌     | 213/469 [00:08<00:09, 25.92it/s]
Epoch 2:  73%|███████▎  | 684/938 [00:41<00:15, 16.57it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  46%|████▌     | 216/469 [00:08<00:09, 26.28it/s]
Epoch 2:  73%|███████▎  | 687/938 [00:41<00:15, 16.60it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  47%|████▋     | 219/469 [00:08<00:09, 26.56it/s]
Epoch 2:  74%|███████▎  | 690/938 [00:41<00:14, 16.63it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  47%|████▋     | 222/469 [00:08<00:09, 25.50it/s]
Epoch 2:  74%|███████▍  | 693/938 [00:41<00:14, 16.65it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  48%|████▊     | 225/469 [00:08<00:09, 25.09it/s]
Epoch 2:  74%|███████▍  | 696/938 [00:41<00:14, 16.67it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  49%|████▊     | 228/469 [00:08<00:09, 25.15it/s]
Epoch 2:  75%|███████▍  | 699/938 [00:41<00:14, 16.70it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  49%|████▉     | 231/469 [00:09<00:09, 26.12it/s]
Epoch 2:  75%|███████▍  | 702/938 [00:41<00:14, 16.73it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  50%|████▉     | 234/469 [00:09<00:08, 26.68it/s]
Epoch 2:  75%|███████▌  | 705/938 [00:42<00:13, 16.75it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  51%|█████     | 237/469 [00:09<00:09, 25.71it/s]
Epoch 2:  75%|███████▌  | 708/938 [00:42<00:13, 16.78it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  51%|█████     | 240/469 [00:09<00:08, 25.98it/s]
Epoch 2:  76%|███████▌  | 711/938 [00:42<00:13, 16.80it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  52%|█████▏    | 243/469 [00:09<00:08, 26.75it/s]
Epoch 2:  76%|███████▌  | 714/938 [00:42<00:13, 16.83it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  52%|█████▏    | 246/469 [00:09<00:08, 27.28it/s]
Epoch 2:  76%|███████▋  | 717/938 [00:42<00:13, 16.86it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  53%|█████▎    | 249/469 [00:09<00:08, 27.14it/s]
Epoch 2:  77%|███████▋  | 720/938 [00:42<00:12, 16.89it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  54%|█████▎    | 252/469 [00:09<00:08, 26.60it/s]
Epoch 2:  77%|███████▋  | 723/938 [00:42<00:12, 16.91it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  54%|█████▍    | 255/469 [00:10<00:08, 26.50it/s]
Epoch 2:  77%|███████▋  | 726/938 [00:42<00:12, 16.94it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  55%|█████▌    | 258/469 [00:10<00:07, 26.74it/s]
Epoch 2:  78%|███████▊  | 729/938 [00:42<00:12, 16.96it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  56%|█████▌    | 261/469 [00:10<00:07, 26.76it/s]
Epoch 2:  78%|███████▊  | 732/938 [00:43<00:12, 16.99it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  56%|█████▋    | 264/469 [00:10<00:08, 25.57it/s]
Epoch 2:  78%|███████▊  | 735/938 [00:43<00:11, 17.00it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  57%|█████▋    | 267/469 [00:10<00:08, 25.20it/s]
Epoch 2:  79%|███████▊  | 738/938 [00:43<00:11, 17.03it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  58%|█████▊    | 270/469 [00:10<00:07, 25.40it/s]
Epoch 2:  79%|███████▉  | 741/938 [00:43<00:11, 17.05it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  58%|█████▊    | 273/469 [00:10<00:07, 25.56it/s]
Epoch 2:  79%|███████▉  | 744/938 [00:43<00:11, 17.07it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  59%|█████▉    | 276/469 [00:10<00:07, 25.67it/s]
Epoch 2:  80%|███████▉  | 747/938 [00:43<00:11, 17.10it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  59%|█████▉    | 279/469 [00:10<00:07, 25.88it/s]
Epoch 2:  80%|███████▉  | 750/938 [00:43<00:10, 17.12it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  60%|██████    | 282/469 [00:11<00:07, 25.12it/s]
Epoch 2:  80%|████████  | 753/938 [00:43<00:10, 17.14it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  61%|██████    | 285/469 [00:11<00:07, 25.34it/s]
Epoch 2:  81%|████████  | 756/938 [00:44<00:10, 17.16it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  61%|██████▏   | 288/469 [00:11<00:07, 25.01it/s]
Epoch 2:  81%|████████  | 759/938 [00:44<00:10, 17.18it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  62%|██████▏   | 291/469 [00:11<00:07, 23.17it/s]
Epoch 2:  81%|████████  | 762/938 [00:44<00:10, 17.19it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  63%|██████▎   | 294/469 [00:11<00:07, 23.86it/s]
Epoch 2:  82%|████████▏ | 765/938 [00:44<00:10, 17.22it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  63%|██████▎   | 297/469 [00:11<00:07, 24.34it/s]
Epoch 2:  82%|████████▏ | 768/938 [00:44<00:09, 17.24it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  64%|██████▍   | 300/469 [00:11<00:06, 24.55it/s]
Epoch 2:  82%|████████▏ | 771/938 [00:44<00:09, 17.26it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  65%|██████▍   | 303/469 [00:11<00:06, 24.59it/s]
Epoch 2:  83%|████████▎ | 774/938 [00:44<00:09, 17.28it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  65%|██████▌   | 306/469 [00:12<00:06, 24.19it/s]
Epoch 2:  83%|████████▎ | 777/938 [00:44<00:09, 17.30it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  66%|██████▌   | 309/469 [00:12<00:06, 24.82it/s]
Epoch 2:  83%|████████▎ | 780/938 [00:45<00:09, 17.32it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  67%|██████▋   | 312/469 [00:12<00:06, 24.40it/s]
Epoch 2:  83%|████████▎ | 783/938 [00:45<00:08, 17.33it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  67%|██████▋   | 315/469 [00:12<00:06, 25.15it/s]
Epoch 2:  84%|████████▍ | 786/938 [00:45<00:08, 17.36it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  68%|██████▊   | 318/469 [00:12<00:05, 25.48it/s]
Epoch 2:  84%|████████▍ | 789/938 [00:45<00:08, 17.38it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  68%|██████▊   | 321/469 [00:12<00:05, 25.21it/s]
Epoch 2:  84%|████████▍ | 792/938 [00:45<00:08, 17.40it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  69%|██████▉   | 324/469 [00:12<00:05, 24.60it/s]
Epoch 2:  85%|████████▍ | 795/938 [00:45<00:08, 17.42it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  70%|██████▉   | 327/469 [00:12<00:05, 24.17it/s]
Epoch 2:  85%|████████▌ | 798/938 [00:45<00:08, 17.43it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  70%|███████   | 330/469 [00:13<00:05, 24.70it/s]
Epoch 2:  85%|████████▌ | 801/938 [00:45<00:07, 17.46it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  71%|███████   | 333/469 [00:13<00:05, 24.47it/s]
Epoch 2:  86%|████████▌ | 804/938 [00:46<00:07, 17.47it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  72%|███████▏  | 336/469 [00:13<00:05, 24.54it/s]
Epoch 2:  86%|████████▌ | 807/938 [00:46<00:07, 17.49it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  72%|███████▏  | 339/469 [00:13<00:05, 24.28it/s]
Epoch 2:  86%|████████▋ | 810/938 [00:46<00:07, 17.51it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  73%|███████▎  | 342/469 [00:13<00:05, 25.38it/s]
Epoch 2:  87%|████████▋ | 813/938 [00:46<00:07, 17.54it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  74%|███████▎  | 345/469 [00:13<00:04, 25.33it/s]
Epoch 2:  87%|████████▋ | 816/938 [00:46<00:06, 17.55it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  74%|███████▍  | 348/469 [00:13<00:04, 25.16it/s]
Epoch 2:  87%|████████▋ | 819/938 [00:46<00:06, 17.57it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  75%|███████▍  | 351/469 [00:13<00:04, 25.29it/s]
Epoch 2:  88%|████████▊ | 822/938 [00:46<00:06, 17.59it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  75%|███████▌  | 354/469 [00:13<00:04, 24.76it/s]
Epoch 2:  88%|████████▊ | 825/938 [00:46<00:06, 17.61it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  76%|███████▌  | 357/469 [00:14<00:04, 24.93it/s]
Epoch 2:  88%|████████▊ | 828/938 [00:46<00:06, 17.63it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  77%|███████▋  | 360/469 [00:14<00:04, 25.25it/s]
Epoch 2:  89%|████████▊ | 831/938 [00:47<00:06, 17.65it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  77%|███████▋  | 363/469 [00:14<00:04, 25.28it/s]
Epoch 2:  89%|████████▉ | 834/938 [00:47<00:05, 17.67it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  78%|███████▊  | 366/469 [00:14<00:03, 26.14it/s]
Epoch 2:  89%|████████▉ | 837/938 [00:47<00:05, 17.69it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  79%|███████▊  | 369/469 [00:14<00:03, 26.11it/s]
Epoch 2:  90%|████████▉ | 840/938 [00:47<00:05, 17.71it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  79%|███████▉  | 372/469 [00:14<00:03, 26.44it/s]
Epoch 2:  90%|████████▉ | 843/938 [00:47<00:05, 17.73it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  80%|███████▉  | 375/469 [00:14<00:03, 26.33it/s]
Epoch 2:  90%|█████████ | 846/938 [00:47<00:05, 17.75it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  81%|████████  | 378/469 [00:14<00:03, 26.11it/s]
Epoch 2:  91%|█████████ | 849/938 [00:47<00:05, 17.77it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  81%|████████  | 381/469 [00:15<00:03, 25.72it/s]
Epoch 2:  91%|█████████ | 852/938 [00:47<00:04, 17.80it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  82%|████████▏ | 384/469 [00:15<00:03, 26.17it/s]
Epoch 2:  91%|█████████ | 855/938 [00:47<00:04, 17.82it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  83%|████████▎ | 387/469 [00:15<00:03, 26.16it/s]
Epoch 2:  91%|█████████▏| 858/938 [00:48<00:04, 17.83it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  83%|████████▎ | 390/469 [00:15<00:02, 26.48it/s]
Epoch 2:  92%|█████████▏| 861/938 [00:48<00:04, 17.86it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  84%|████████▍ | 393/469 [00:15<00:02, 25.76it/s]
Epoch 2:  92%|█████████▏| 864/938 [00:48<00:04, 17.87it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  84%|████████▍ | 396/469 [00:15<00:02, 26.14it/s]
Epoch 2:  92%|█████████▏| 867/938 [00:48<00:03, 17.89it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  85%|████████▌ | 399/469 [00:15<00:02, 25.79it/s]
Epoch 2:  93%|█████████▎| 870/938 [00:48<00:03, 17.91it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  86%|████████▌ | 402/469 [00:15<00:02, 26.00it/s]
Epoch 2:  93%|█████████▎| 873/938 [00:48<00:03, 17.93it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  86%|████████▋ | 405/469 [00:15<00:02, 26.20it/s]
Epoch 2:  93%|█████████▎| 876/938 [00:48<00:03, 17.95it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  87%|████████▋ | 408/469 [00:16<00:02, 26.50it/s]
Epoch 2:  94%|█████████▎| 879/938 [00:48<00:03, 17.97it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  88%|████████▊ | 411/469 [00:16<00:02, 26.33it/s]
Epoch 2:  94%|█████████▍| 882/938 [00:49<00:03, 17.99it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  88%|████████▊ | 414/469 [00:16<00:02, 26.32it/s]
Epoch 2:  94%|█████████▍| 885/938 [00:49<00:02, 18.01it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  89%|████████▉ | 417/469 [00:16<00:01, 27.15it/s]
Epoch 2:  95%|█████████▍| 888/938 [00:49<00:02, 18.03it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  90%|████████▉ | 420/469 [00:16<00:01, 25.88it/s]
Epoch 2:  95%|█████████▍| 891/938 [00:49<00:02, 18.04it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  90%|█████████ | 423/469 [00:16<00:01, 25.31it/s]
Epoch 2:  95%|█████████▌| 894/938 [00:49<00:02, 18.06it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  91%|█████████ | 426/469 [00:16<00:01, 26.12it/s]
Epoch 2:  96%|█████████▌| 897/938 [00:49<00:02, 18.08it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  91%|█████████▏| 429/469 [00:16<00:01, 26.24it/s]
Epoch 2:  96%|█████████▌| 900/938 [00:49<00:02, 18.10it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  92%|█████████▏| 432/469 [00:16<00:01, 26.74it/s]
Epoch 2:  96%|█████████▋| 903/938 [00:49<00:01, 18.12it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  93%|█████████▎| 435/469 [00:17<00:01, 27.27it/s]
Epoch 2:  97%|█████████▋| 906/938 [00:49<00:01, 18.15it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  93%|█████████▎| 438/469 [00:17<00:01, 27.23it/s]
Epoch 2:  97%|█████████▋| 909/938 [00:50<00:01, 18.16it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  94%|█████████▍| 441/469 [00:17<00:01, 26.54it/s]
Epoch 2:  97%|█████████▋| 912/938 [00:50<00:01, 18.18it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  95%|█████████▍| 444/469 [00:17<00:00, 26.06it/s]
Epoch 2:  98%|█████████▊| 915/938 [00:50<00:01, 18.20it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  95%|█████████▌| 447/469 [00:17<00:00, 26.53it/s]
Epoch 2:  98%|█████████▊| 918/938 [00:50<00:01, 18.22it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  96%|█████████▌| 450/469 [00:17<00:00, 27.11it/s]
Epoch 2:  98%|█████████▊| 921/938 [00:50<00:00, 18.24it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  97%|█████████▋| 453/469 [00:17<00:00, 26.85it/s]
Epoch 2:  99%|█████████▊| 924/938 [00:50<00:00, 18.26it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  97%|█████████▋| 456/469 [00:17<00:00, 26.84it/s]
Epoch 2:  99%|█████████▉| 927/938 [00:50<00:00, 18.28it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  98%|█████████▊| 459/469 [00:17<00:00, 27.23it/s]
Epoch 2:  99%|█████████▉| 930/938 [00:50<00:00, 18.30it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  99%|█████████▊| 462/469 [00:18<00:00, 26.29it/s]
Epoch 2:  99%|█████████▉| 933/938 [00:50<00:00, 18.31it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating:  99%|█████████▉| 465/469 [00:18<00:00, 26.13it/s]
Epoch 2: 100%|█████████▉| 936/938 [00:51<00:00, 18.33it/s, loss=0.639, v_num=11, val_rmse=0.554, train_rmse=0.726]

Validating: 100%|█████████▉| 468/469 [00:18<00:00, 25.95it/s]
Epoch 2: 100%|██████████| 938/938 [00:51<00:00, 18.33it/s, loss=0.639, v_num=11, val_rmse=0.522, train_rmse=0.726]

                                                             
Epoch 2: 100%|██████████| 938/938 [00:51<00:00, 18.32it/s, loss=0.639, v_num=11, val_rmse=0.522, train_rmse=0.676]
Epoch 2: 100%|██████████| 938/938 [00:51<00:00, 18.28it/s, loss=0.639, v_num=11, val_rmse=0.522, train_rmse=0.676]LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]


Testing: 0it [00:00, ?it/s]
Testing:   0%|          | 2/469 [00:00<00:26, 17.91it/s]
Testing:   1%|          | 5/469 [00:00<00:20, 22.64it/s]
Testing:   2%|▏         | 8/469 [00:00<00:20, 22.86it/s]
Testing:   2%|▏         | 11/469 [00:00<00:18, 24.20it/s]
Testing:   3%|▎         | 14/469 [00:00<00:18, 24.83it/s]
Testing:   4%|▎         | 17/469 [00:00<00:17, 25.39it/s]
Testing:   4%|▍         | 20/469 [00:00<00:17, 25.92it/s]
Testing:   5%|▍         | 23/469 [00:00<00:17, 25.88it/s]
Testing:   6%|▌         | 26/469 [00:01<00:17, 26.04it/s]
Testing:   6%|▌         | 29/469 [00:01<00:16, 26.18it/s]
Testing:   7%|▋         | 32/469 [00:01<00:16, 25.74it/s]
Testing:   7%|▋         | 35/469 [00:01<00:16, 25.70it/s]
Testing:   8%|▊         | 38/469 [00:01<00:17, 25.31it/s]
Testing:   9%|▊         | 41/469 [00:01<00:17, 25.11it/s]
Testing:   9%|▉         | 44/469 [00:01<00:16, 25.43it/s]
Testing:  10%|█         | 47/469 [00:01<00:16, 25.54it/s]
Testing:  11%|█         | 50/469 [00:02<00:17, 24.56it/s]
Testing:  11%|█▏        | 53/469 [00:02<00:16, 24.71it/s]
Testing:  12%|█▏        | 56/469 [00:02<00:17, 23.13it/s]
Testing:  13%|█▎        | 59/469 [00:02<00:17, 23.05it/s]
Testing:  13%|█▎        | 62/469 [00:02<00:17, 23.65it/s]
Testing:  14%|█▍        | 65/469 [00:02<00:16, 23.94it/s]
Testing:  14%|█▍        | 68/469 [00:02<00:15, 25.38it/s]
Testing:  15%|█▌        | 71/469 [00:02<00:15, 25.32it/s]
Testing:  16%|█▌        | 74/469 [00:02<00:15, 25.07it/s]
Testing:  16%|█▋        | 77/469 [00:03<00:15, 25.22it/s]
Testing:  17%|█▋        | 80/469 [00:03<00:15, 25.56it/s]
Testing:  18%|█▊        | 83/469 [00:03<00:15, 25.41it/s]
Testing:  18%|█▊        | 86/469 [00:03<00:14, 26.31it/s]
Testing:  19%|█▉        | 89/469 [00:03<00:15, 25.33it/s]
Testing:  20%|█▉        | 92/469 [00:03<00:14, 26.12it/s]
Testing:  20%|██        | 95/469 [00:03<00:14, 26.36it/s]
Testing:  21%|██        | 98/469 [00:03<00:15, 23.68it/s]
Testing:  22%|██▏       | 101/469 [00:04<00:15, 23.87it/s]
Testing:  22%|██▏       | 104/469 [00:04<00:15, 24.20it/s]
Testing:  23%|██▎       | 107/469 [00:04<00:14, 25.38it/s]
Testing:  23%|██▎       | 110/469 [00:04<00:14, 25.21it/s]
Testing:  24%|██▍       | 113/469 [00:04<00:14, 24.79it/s]
Testing:  25%|██▍       | 116/469 [00:04<00:14, 24.96it/s]
Testing:  25%|██▌       | 119/469 [00:04<00:13, 25.18it/s]
Testing:  26%|██▌       | 122/469 [00:04<00:14, 24.37it/s]
Testing:  27%|██▋       | 125/469 [00:05<00:13, 25.22it/s]
Testing:  27%|██▋       | 128/469 [00:05<00:13, 25.44it/s]
Testing:  28%|██▊       | 131/469 [00:05<00:13, 25.16it/s]
Testing:  29%|██▊       | 134/469 [00:05<00:13, 24.48it/s]
Testing:  29%|██▉       | 137/469 [00:05<00:13, 25.15it/s]
Testing:  30%|██▉       | 140/469 [00:05<00:12, 25.52it/s]
Testing:  30%|███       | 143/469 [00:05<00:12, 25.60it/s]
Testing:  31%|███       | 146/469 [00:05<00:12, 24.95it/s]
Testing:  32%|███▏      | 149/469 [00:05<00:12, 25.07it/s]
Testing:  32%|███▏      | 152/469 [00:06<00:13, 24.18it/s]
Testing:  33%|███▎      | 155/469 [00:06<00:12, 24.52it/s]
Testing:  34%|███▎      | 158/469 [00:06<00:12, 25.07it/s]
Testing:  34%|███▍      | 161/469 [00:06<00:12, 25.64it/s]
Testing:  35%|███▍      | 164/469 [00:06<00:11, 25.97it/s]
Testing:  36%|███▌      | 167/469 [00:06<00:11, 26.19it/s]
Testing:  36%|███▌      | 170/469 [00:06<00:11, 25.36it/s]
Testing:  37%|███▋      | 173/469 [00:06<00:12, 24.45it/s]
Testing:  38%|███▊      | 176/469 [00:07<00:11, 24.46it/s]
Testing:  38%|███▊      | 179/469 [00:07<00:11, 25.68it/s]
Testing:  39%|███▉      | 182/469 [00:07<00:11, 25.47it/s]
Testing:  39%|███▉      | 185/469 [00:07<00:11, 24.74it/s]
Testing:  40%|████      | 188/469 [00:07<00:11, 24.20it/s]
Testing:  41%|████      | 191/469 [00:07<00:11, 24.03it/s]
Testing:  41%|████▏     | 194/469 [00:07<00:11, 24.27it/s]
Testing:  42%|████▏     | 197/469 [00:07<00:11, 24.61it/s]
Testing:  43%|████▎     | 200/469 [00:08<00:10, 25.54it/s]
Testing:  43%|████▎     | 203/469 [00:08<00:10, 25.04it/s]
Testing:  44%|████▍     | 206/469 [00:08<00:10, 24.98it/s]
Testing:  45%|████▍     | 209/469 [00:08<00:10, 24.96it/s]
Testing:  45%|████▌     | 212/469 [00:08<00:10, 24.42it/s]
Testing:  46%|████▌     | 215/469 [00:08<00:09, 25.85it/s]
Testing:  46%|████▋     | 218/469 [00:08<00:09, 25.35it/s]
Testing:  47%|████▋     | 221/469 [00:08<00:09, 25.50it/s]
Testing:  48%|████▊     | 224/469 [00:08<00:09, 25.14it/s]
Testing:  48%|████▊     | 227/469 [00:09<00:09, 25.26it/s]
Testing:  49%|████▉     | 230/469 [00:09<00:09, 25.57it/s]
Testing:  50%|████▉     | 233/469 [00:09<00:09, 25.91it/s]
Testing:  50%|█████     | 236/469 [00:09<00:08, 26.54it/s]
Testing:  51%|█████     | 239/469 [00:09<00:09, 25.45it/s]
Testing:  52%|█████▏    | 242/469 [00:09<00:09, 24.79it/s]
Testing:  52%|█████▏    | 245/469 [00:09<00:08, 24.96it/s]
Testing:  53%|█████▎    | 248/469 [00:09<00:09, 23.74it/s]
Testing:  54%|█████▎    | 251/469 [00:10<00:08, 24.41it/s]
Testing:  54%|█████▍    | 254/469 [00:10<00:08, 25.24it/s]
Testing:  55%|█████▍    | 257/469 [00:10<00:08, 24.85it/s]
Testing:  55%|█████▌    | 260/469 [00:10<00:08, 24.35it/s]
Testing:  56%|█████▌    | 263/469 [00:10<00:08, 23.97it/s]
Testing:  57%|█████▋    | 266/469 [00:10<00:08, 23.01it/s]
Testing:  57%|█████▋    | 269/469 [00:10<00:09, 21.96it/s]
Testing:  58%|█████▊    | 272/469 [00:10<00:08, 22.81it/s]
Testing:  59%|█████▊    | 275/469 [00:11<00:08, 23.81it/s]
Testing:  59%|█████▉    | 278/469 [00:11<00:07, 24.41it/s]
Testing:  60%|█████▉    | 281/469 [00:11<00:07, 24.39it/s]
Testing:  61%|██████    | 284/469 [00:11<00:07, 25.12it/s]
Testing:  61%|██████    | 287/469 [00:11<00:07, 25.04it/s]
Testing:  62%|██████▏   | 290/469 [00:11<00:07, 25.14it/s]
Testing:  62%|██████▏   | 293/469 [00:11<00:07, 25.13it/s]
Testing:  63%|██████▎   | 296/469 [00:11<00:07, 22.85it/s]
Testing:  64%|██████▍   | 299/469 [00:12<00:07, 24.00it/s]
Testing:  64%|██████▍   | 302/469 [00:12<00:06, 24.13it/s]
Testing:  65%|██████▌   | 305/469 [00:12<00:06, 23.57it/s]
Testing:  66%|██████▌   | 308/469 [00:12<00:06, 23.92it/s]
Testing:  66%|██████▋   | 311/469 [00:12<00:06, 24.75it/s]
Testing:  67%|██████▋   | 314/469 [00:12<00:06, 24.52it/s]
Testing:  68%|██████▊   | 317/469 [00:12<00:06, 24.36it/s]
Testing:  68%|██████▊   | 320/469 [00:12<00:06, 24.48it/s]
Testing:  69%|██████▉   | 323/469 [00:13<00:06, 24.06it/s]
Testing:  70%|██████▉   | 326/469 [00:13<00:05, 24.24it/s]
Testing:  70%|███████   | 329/469 [00:13<00:05, 24.94it/s]
Testing:  71%|███████   | 332/469 [00:13<00:05, 25.52it/s]
Testing:  71%|███████▏  | 335/469 [00:13<00:05, 25.88it/s]
Testing:  72%|███████▏  | 338/469 [00:13<00:05, 24.88it/s]
Testing:  73%|███████▎  | 341/469 [00:13<00:05, 24.93it/s]
Testing:  73%|███████▎  | 344/469 [00:13<00:04, 25.15it/s]
Testing:  74%|███████▍  | 347/469 [00:13<00:04, 25.53it/s]
Testing:  75%|███████▍  | 350/469 [00:14<00:04, 24.83it/s]
Testing:  75%|███████▌  | 353/469 [00:14<00:04, 24.33it/s]
Testing:  76%|███████▌  | 356/469 [00:14<00:04, 25.60it/s]
Testing:  77%|███████▋  | 359/469 [00:14<00:04, 26.11it/s]
Testing:  77%|███████▋  | 363/469 [00:14<00:03, 27.21it/s]
Testing:  78%|███████▊  | 366/469 [00:14<00:03, 26.70it/s]
Testing:  79%|███████▊  | 369/469 [00:14<00:03, 26.80it/s]
Testing:  79%|███████▉  | 372/469 [00:14<00:04, 23.72it/s]
Testing:  80%|███████▉  | 375/469 [00:15<00:03, 23.82it/s]
Testing:  81%|████████  | 378/469 [00:15<00:03, 24.20it/s]
Testing:  81%|████████  | 381/469 [00:15<00:03, 24.89it/s]
Testing:  82%|████████▏ | 384/469 [00:15<00:03, 25.16it/s]
Testing:  83%|████████▎ | 387/469 [00:15<00:03, 25.01it/s]
Testing:  83%|████████▎ | 390/469 [00:15<00:03, 25.03it/s]
Testing:  84%|████████▍ | 393/469 [00:15<00:03, 25.24it/s]
Testing:  84%|████████▍ | 396/469 [00:15<00:02, 25.77it/s]
Testing:  85%|████████▌ | 399/469 [00:16<00:02, 25.48it/s]
Testing:  86%|████████▌ | 402/469 [00:16<00:02, 25.45it/s]
Testing:  86%|████████▋ | 405/469 [00:16<00:02, 24.55it/s]
Testing:  87%|████████▋ | 408/469 [00:16<00:02, 24.75it/s]
Testing:  88%|████████▊ | 411/469 [00:16<00:02, 24.94it/s]
Testing:  88%|████████▊ | 414/469 [00:16<00:02, 24.75it/s]
Testing:  89%|████████▉ | 417/469 [00:16<00:02, 24.61it/s]
Testing:  90%|████████▉ | 420/469 [00:16<00:02, 23.64it/s]
Testing:  90%|█████████ | 423/469 [00:17<00:01, 23.73it/s]
Testing:  91%|█████████ | 426/469 [00:17<00:01, 23.99it/s]
Testing:  91%|█████████▏| 429/469 [00:17<00:01, 23.51it/s]
Testing:  92%|█████████▏| 432/469 [00:17<00:01, 24.85it/s]
Testing:  93%|█████████▎| 435/469 [00:17<00:01, 24.96it/s]
Testing:  93%|█████████▎| 438/469 [00:17<00:01, 25.35it/s]
Testing:  94%|█████████▍| 441/469 [00:17<00:01, 24.87it/s]
Testing:  95%|█████████▍| 444/469 [00:17<00:00, 25.59it/s]
Testing:  95%|█████████▌| 447/469 [00:17<00:00, 24.92it/s]
Testing:  96%|█████████▌| 450/469 [00:18<00:00, 25.76it/s]
Testing:  97%|█████████▋| 453/469 [00:18<00:00, 26.19it/s]
Testing:  97%|█████████▋| 456/469 [00:18<00:00, 25.88it/s]
Testing:  98%|█████████▊| 459/469 [00:18<00:00, 25.21it/s]
Testing:  99%|█████████▊| 462/469 [00:18<00:00, 25.29it/s]
Testing:  99%|█████████▉| 465/469 [00:18<00:00, 25.73it/s]
Testing: 100%|█████████▉| 468/469 [00:18<00:00, 25.57it/s]--------------------------------------------------------------------------------
DATALOADER:0 TEST RESULTS
{'test_rmse': 0.5213741660118103}
--------------------------------------------------------------------------------

Testing: 100%|██████████| 469/469 [00:18<00:00, 24.90it/s]
  0%|          | 0/469 [02:56<?, ?it/s]
Global seed set to 47

['p_np'] False
2 1
iupac_vocab_size: 1491
training... 1491

  0%|          | 0/469 [00:00<?, ?it/s]Some weights of the model checkpoint at checkpoints/iupac were not used when initializing GPT2ForSequenceClassification: ['lm_head.weight']
- This IS expected if you are initializing GPT2ForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing GPT2ForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
GPU available: True, used: True
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]

  | Name        | Type                          | Params
--------------------------------------------------------------
0 | transformer | GPT2ForSequenceClassification | 7.1 M 
--------------------------------------------------------------
75.9 K    Trainable params
7.0 M     Non-trainable params
7.1 M     Total params
28.416    Total estimated model params size (MB)

Validation sanity check: 0it [00:00, ?it/s]
Validation sanity check:   0%|          | 0/2 [00:00<?, ?it/s]
Validation sanity check: 100%|██████████| 2/2 [00:00<00:00, 19.54it/s]
                                                                      Global seed set to 47


Training: 0it [00:00, ?it/s]
Training:   0%|          | 0/938 [00:00<?, ?it/s]
Epoch 0:   0%|          | 0/938 [00:00<?, ?it/s] 
Epoch 0:   0%|          | 1/938 [00:00<02:03,  7.58it/s]
Epoch 0:   0%|          | 1/938 [00:00<02:04,  7.55it/s, loss=3.54, v_num=12]
Epoch 0:   0%|          | 2/938 [00:00<01:36,  9.67it/s, loss=3.55, v_num=12]
Epoch 0:   0%|          | 3/938 [00:00<01:30, 10.39it/s, loss=3.55, v_num=12]
Epoch 0:   0%|          | 3/938 [00:00<01:30, 10.37it/s, loss=3.53, v_num=12]
Epoch 0:   0%|          | 4/938 [00:00<01:27, 10.68it/s, loss=3.64, v_num=12]
Epoch 0:   1%|          | 5/938 [00:00<01:28, 10.57it/s, loss=3.64, v_num=12]
Epoch 0:   1%|          | 5/938 [00:00<01:28, 10.55it/s, loss=3.65, v_num=12]
Epoch 0:   1%|          | 6/938 [00:00<01:22, 11.24it/s, loss=3.62, v_num=12]
Epoch 0:   1%|          | 7/938 [00:00<01:20, 11.53it/s, loss=3.62, v_num=12]
Epoch 0:   1%|          | 7/938 [00:00<01:20, 11.52it/s, loss=3.58, v_num=12]
Epoch 0:   1%|          | 8/938 [00:00<01:17, 11.97it/s, loss=3.56, v_num=12]
Epoch 0:   1%|          | 9/938 [00:00<01:18, 11.85it/s, loss=3.56, v_num=12]
Epoch 0:   1%|          | 9/938 [00:00<01:18, 11.84it/s, loss=3.51, v_num=12]
Epoch 0:   1%|          | 10/938 [00:00<01:18, 11.88it/s, loss=3.48, v_num=12]
Epoch 0:   1%|          | 11/938 [00:00<01:17, 11.89it/s, loss=3.48, v_num=12]
Epoch 0:   1%|          | 11/938 [00:00<01:17, 11.89it/s, loss=3.43, v_num=12]
Epoch 0:   1%|▏         | 12/938 [00:00<01:15, 12.24it/s, loss=3.44, v_num=12]
Epoch 0:   1%|▏         | 13/938 [00:01<01:15, 12.24it/s, loss=3.44, v_num=12]
Epoch 0:   1%|▏         | 13/938 [00:01<01:15, 12.23it/s, loss=3.41, v_num=12]
Epoch 0:   1%|▏         | 14/938 [00:01<01:15, 12.29it/s, loss=3.41, v_num=12]
Epoch 0:   2%|▏         | 15/938 [00:01<01:14, 12.41it/s, loss=3.41, v_num=12]
Epoch 0:   2%|▏         | 15/938 [00:01<01:14, 12.41it/s, loss=3.4, v_num=12] 
Epoch 0:   2%|▏         | 16/938 [00:01<01:14, 12.42it/s, loss=3.39, v_num=12]
Epoch 0:   2%|▏         | 17/938 [00:01<01:13, 12.54it/s, loss=3.39, v_num=12]
Epoch 0:   2%|▏         | 17/938 [00:01<01:13, 12.54it/s, loss=3.36, v_num=12]
Epoch 0:   2%|▏         | 18/938 [00:01<01:13, 12.57it/s, loss=3.33, v_num=12]
Epoch 0:   2%|▏         | 19/938 [00:01<01:12, 12.65it/s, loss=3.33, v_num=12]
Epoch 0:   2%|▏         | 19/938 [00:01<01:12, 12.65it/s, loss=3.32, v_num=12]
Epoch 0:   2%|▏         | 20/938 [00:01<01:12, 12.75it/s, loss=3.31, v_num=12]
Epoch 0:   2%|▏         | 21/938 [00:01<01:11, 12.90it/s, loss=3.31, v_num=12]
Epoch 0:   2%|▏         | 21/938 [00:01<01:11, 12.90it/s, loss=3.28, v_num=12]
Epoch 0:   2%|▏         | 22/938 [00:01<01:10, 12.95it/s, loss=3.24, v_num=12]
Epoch 0:   2%|▏         | 23/938 [00:01<01:10, 13.06it/s, loss=3.24, v_num=12]
Epoch 0:   2%|▏         | 23/938 [00:01<01:10, 13.06it/s, loss=3.19, v_num=12]
Epoch 0:   3%|▎         | 24/938 [00:01<01:09, 13.11it/s, loss=3.11, v_num=12]
Epoch 0:   3%|▎         | 25/938 [00:01<01:10, 12.99it/s, loss=3.11, v_num=12]
Epoch 0:   3%|▎         | 25/938 [00:01<01:10, 12.99it/s, loss=3.04, v_num=12]
Epoch 0:   3%|▎         | 26/938 [00:02<01:10, 13.00it/s, loss=2.99, v_num=12]
Epoch 0:   3%|▎         | 27/938 [00:02<01:10, 12.86it/s, loss=2.99, v_num=12]
Epoch 0:   3%|▎         | 27/938 [00:02<01:10, 12.86it/s, loss=2.95, v_num=12]
Epoch 0:   3%|▎         | 28/938 [00:02<01:10, 12.89it/s, loss=2.89, v_num=12]
Epoch 0:   3%|▎         | 29/938 [00:02<01:10, 12.87it/s, loss=2.89, v_num=12]
Epoch 0:   3%|▎         | 29/938 [00:02<01:10, 12.87it/s, loss=2.84, v_num=12]
Epoch 0:   3%|▎         | 30/938 [00:02<01:09, 12.98it/s, loss=2.79, v_num=12]
Epoch 0:   3%|▎         | 31/938 [00:02<01:09, 12.97it/s, loss=2.79, v_num=12]
Epoch 0:   3%|▎         | 31/938 [00:02<01:09, 12.97it/s, loss=2.75, v_num=12]
Epoch 0:   3%|▎         | 32/938 [00:02<01:09, 13.05it/s, loss=2.68, v_num=12]
Epoch 0:   4%|▎         | 33/938 [00:02<01:09, 13.11it/s, loss=2.68, v_num=12]
Epoch 0:   4%|▎         | 33/938 [00:02<01:09, 13.11it/s, loss=2.61, v_num=12]
Epoch 0:   4%|▎         | 34/938 [00:02<01:08, 13.12it/s, loss=2.55, v_num=12]
Epoch 0:   4%|▎         | 35/938 [00:02<01:08, 13.17it/s, loss=2.55, v_num=12]
Epoch 0:   4%|▎         | 35/938 [00:02<01:08, 13.17it/s, loss=2.45, v_num=12]
Epoch 0:   4%|▍         | 36/938 [00:02<01:08, 13.17it/s, loss=2.38, v_num=12]
Epoch 0:   4%|▍         | 37/938 [00:02<01:08, 13.15it/s, loss=2.38, v_num=12]
Epoch 0:   4%|▍         | 37/938 [00:02<01:08, 13.15it/s, loss=2.32, v_num=12]
Epoch 0:   4%|▍         | 38/938 [00:02<01:08, 13.20it/s, loss=2.26, v_num=12]
Epoch 0:   4%|▍         | 39/938 [00:02<01:07, 13.23it/s, loss=2.26, v_num=12]
Epoch 0:   4%|▍         | 39/938 [00:02<01:07, 13.23it/s, loss=2.2, v_num=12] 
Epoch 0:   4%|▍         | 40/938 [00:03<01:07, 13.28it/s, loss=2.12, v_num=12]
Epoch 0:   4%|▍         | 41/938 [00:03<01:07, 13.35it/s, loss=2.12, v_num=12]
Epoch 0:   4%|▍         | 41/938 [00:03<01:07, 13.35it/s, loss=2.05, v_num=12]
Epoch 0:   4%|▍         | 42/938 [00:03<01:07, 13.22it/s, loss=2, v_num=12]   
Epoch 0:   5%|▍         | 43/938 [00:03<01:08, 13.15it/s, loss=2, v_num=12]
Epoch 0:   5%|▍         | 43/938 [00:03<01:08, 13.14it/s, loss=1.95, v_num=12]
Epoch 0:   5%|▍         | 44/938 [00:03<01:07, 13.16it/s, loss=1.88, v_num=12]
Epoch 0:   5%|▍         | 45/938 [00:03<01:07, 13.22it/s, loss=1.88, v_num=12]
Epoch 0:   5%|▍         | 45/938 [00:03<01:07, 13.22it/s, loss=1.86, v_num=12]
Epoch 0:   5%|▍         | 46/938 [00:03<01:07, 13.20it/s, loss=1.84, v_num=12]
Epoch 0:   5%|▌         | 47/938 [00:03<01:07, 13.27it/s, loss=1.84, v_num=12]
Epoch 0:   5%|▌         | 47/938 [00:03<01:07, 13.27it/s, loss=1.8, v_num=12] 
Epoch 0:   5%|▌         | 48/938 [00:03<01:07, 13.20it/s, loss=1.77, v_num=12]
Epoch 0:   5%|▌         | 49/938 [00:03<01:07, 13.23it/s, loss=1.77, v_num=12]
Epoch 0:   5%|▌         | 49/938 [00:03<01:07, 13.23it/s, loss=1.74, v_num=12]
Epoch 0:   5%|▌         | 50/938 [00:03<01:06, 13.26it/s, loss=1.72, v_num=12]
Epoch 0:   5%|▌         | 51/938 [00:03<01:06, 13.32it/s, loss=1.72, v_num=12]
Epoch 0:   5%|▌         | 51/938 [00:03<01:06, 13.32it/s, loss=1.7, v_num=12] 
Epoch 0:   6%|▌         | 52/938 [00:03<01:06, 13.34it/s, loss=1.68, v_num=12]
Epoch 0:   6%|▌         | 53/938 [00:03<01:06, 13.39it/s, loss=1.68, v_num=12]
Epoch 0:   6%|▌         | 53/938 [00:03<01:06, 13.39it/s, loss=1.67, v_num=12]
Epoch 0:   6%|▌         | 54/938 [00:04<01:05, 13.42it/s, loss=1.65, v_num=12]
Epoch 0:   6%|▌         | 55/938 [00:04<01:05, 13.48it/s, loss=1.65, v_num=12]
Epoch 0:   6%|▌         | 55/938 [00:04<01:05, 13.48it/s, loss=1.66, v_num=12]
Epoch 0:   6%|▌         | 56/938 [00:04<01:05, 13.53it/s, loss=1.66, v_num=12]
Epoch 0:   6%|▌         | 57/938 [00:04<01:05, 13.51it/s, loss=1.66, v_num=12]
Epoch 0:   6%|▌         | 57/938 [00:04<01:05, 13.51it/s, loss=1.66, v_num=12]
Epoch 0:   6%|▌         | 58/938 [00:04<01:05, 13.51it/s, loss=1.66, v_num=12]
Epoch 0:   6%|▋         | 59/938 [00:04<01:04, 13.54it/s, loss=1.66, v_num=12]
Epoch 0:   6%|▋         | 59/938 [00:04<01:04, 13.54it/s, loss=1.66, v_num=12]
Epoch 0:   6%|▋         | 60/938 [00:04<01:04, 13.54it/s, loss=1.66, v_num=12]
Epoch 0:   7%|▋         | 61/938 [00:04<01:04, 13.55it/s, loss=1.66, v_num=12]
Epoch 0:   7%|▋         | 61/938 [00:04<01:04, 13.55it/s, loss=1.68, v_num=12]
Epoch 0:   7%|▋         | 62/938 [00:04<01:04, 13.55it/s, loss=1.69, v_num=12]
Epoch 0:   7%|▋         | 63/938 [00:04<01:04, 13.57it/s, loss=1.69, v_num=12]
Epoch 0:   7%|▋         | 63/938 [00:04<01:04, 13.57it/s, loss=1.7, v_num=12] 
Epoch 0:   7%|▋         | 64/938 [00:04<01:04, 13.58it/s, loss=1.71, v_num=12]
Epoch 0:   7%|▋         | 65/938 [00:04<01:04, 13.58it/s, loss=1.71, v_num=12]
Epoch 0:   7%|▋         | 65/938 [00:04<01:04, 13.58it/s, loss=1.73, v_num=12]
Epoch 0:   7%|▋         | 66/938 [00:04<01:04, 13.61it/s, loss=1.71, v_num=12]
Epoch 0:   7%|▋         | 67/938 [00:04<01:03, 13.64it/s, loss=1.71, v_num=12]
Epoch 0:   7%|▋         | 67/938 [00:04<01:03, 13.64it/s, loss=1.7, v_num=12] 
Epoch 0:   7%|▋         | 68/938 [00:04<01:03, 13.66it/s, loss=1.7, v_num=12]
Epoch 0:   7%|▋         | 69/938 [00:05<01:03, 13.61it/s, loss=1.7, v_num=12]
Epoch 0:   7%|▋         | 69/938 [00:05<01:03, 13.61it/s, loss=1.71, v_num=12]
Epoch 0:   7%|▋         | 70/938 [00:05<01:04, 13.56it/s, loss=1.72, v_num=12]
Epoch 0:   8%|▊         | 71/938 [00:05<01:04, 13.51it/s, loss=1.72, v_num=12]
Epoch 0:   8%|▊         | 71/938 [00:05<01:04, 13.50it/s, loss=1.72, v_num=12]
Epoch 0:   8%|▊         | 72/938 [00:05<01:03, 13.53it/s, loss=1.71, v_num=12]
Epoch 0:   8%|▊         | 73/938 [00:05<01:03, 13.55it/s, loss=1.71, v_num=12]
Epoch 0:   8%|▊         | 73/938 [00:05<01:03, 13.55it/s, loss=1.71, v_num=12]
Epoch 0:   8%|▊         | 74/938 [00:05<01:03, 13.56it/s, loss=1.7, v_num=12] 
Epoch 0:   8%|▊         | 75/938 [00:05<01:03, 13.60it/s, loss=1.7, v_num=12]
Epoch 0:   8%|▊         | 75/938 [00:05<01:03, 13.60it/s, loss=1.72, v_num=12]
Epoch 0:   8%|▊         | 76/938 [00:05<01:03, 13.57it/s, loss=1.72, v_num=12]
Epoch 0:   8%|▊         | 77/938 [00:05<01:03, 13.57it/s, loss=1.72, v_num=12]
Epoch 0:   8%|▊         | 77/938 [00:05<01:03, 13.57it/s, loss=1.71, v_num=12]
Epoch 0:   8%|▊         | 78/938 [00:05<01:03, 13.53it/s, loss=1.7, v_num=12] 
Epoch 0:   8%|▊         | 79/938 [00:05<01:03, 13.56it/s, loss=1.7, v_num=12]
Epoch 0:   8%|▊         | 79/938 [00:05<01:03, 13.56it/s, loss=1.69, v_num=12]
Epoch 0:   9%|▊         | 80/938 [00:05<01:03, 13.56it/s, loss=1.68, v_num=12]
Epoch 0:   9%|▊         | 81/938 [00:05<01:03, 13.57it/s, loss=1.68, v_num=12]
Epoch 0:   9%|▊         | 81/938 [00:05<01:03, 13.57it/s, loss=1.64, v_num=12]
Epoch 0:   9%|▊         | 82/938 [00:06<01:03, 13.58it/s, loss=1.63, v_num=12]
Epoch 0:   9%|▉         | 83/938 [00:06<01:02, 13.58it/s, loss=1.63, v_num=12]
Epoch 0:   9%|▉         | 83/938 [00:06<01:02, 13.58it/s, loss=1.64, v_num=12]
Epoch 0:   9%|▉         | 84/938 [00:06<01:02, 13.58it/s, loss=1.66, v_num=12]
Epoch 0:   9%|▉         | 85/938 [00:06<01:02, 13.58it/s, loss=1.66, v_num=12]
Epoch 0:   9%|▉         | 85/938 [00:06<01:02, 13.58it/s, loss=1.64, v_num=12]
Epoch 0:   9%|▉         | 86/938 [00:06<01:02, 13.54it/s, loss=1.64, v_num=12]
Epoch 0:   9%|▉         | 87/938 [00:06<01:02, 13.55it/s, loss=1.64, v_num=12]
Epoch 0:   9%|▉         | 87/938 [00:06<01:02, 13.55it/s, loss=1.65, v_num=12]
Epoch 0:   9%|▉         | 88/938 [00:06<01:03, 13.42it/s, loss=1.66, v_num=12]
Epoch 0:   9%|▉         | 89/938 [00:06<01:03, 13.41it/s, loss=1.66, v_num=12]
Epoch 0:   9%|▉         | 89/938 [00:06<01:03, 13.41it/s, loss=1.65, v_num=12]
Epoch 0:  10%|▉         | 90/938 [00:06<01:03, 13.42it/s, loss=1.65, v_num=12]
Epoch 0:  10%|▉         | 91/938 [00:06<01:03, 13.41it/s, loss=1.65, v_num=12]
Epoch 0:  10%|▉         | 91/938 [00:06<01:03, 13.41it/s, loss=1.65, v_num=12]
Epoch 0:  10%|▉         | 92/938 [00:06<01:03, 13.42it/s, loss=1.67, v_num=12]
Epoch 0:  10%|▉         | 93/938 [00:06<01:02, 13.45it/s, loss=1.67, v_num=12]
Epoch 0:  10%|▉         | 93/938 [00:06<01:02, 13.45it/s, loss=1.67, v_num=12]
Epoch 0:  10%|█         | 94/938 [00:06<01:02, 13.44it/s, loss=1.67, v_num=12]
Epoch 0:  10%|█         | 95/938 [00:07<01:02, 13.46it/s, loss=1.67, v_num=12]
Epoch 0:  10%|█         | 95/938 [00:07<01:02, 13.46it/s, loss=1.66, v_num=12]
Epoch 0:  10%|█         | 96/938 [00:07<01:02, 13.46it/s, loss=1.66, v_num=12]
Epoch 0:  10%|█         | 97/938 [00:07<01:02, 13.48it/s, loss=1.66, v_num=12]
Epoch 0:  10%|█         | 97/938 [00:07<01:02, 13.48it/s, loss=1.67, v_num=12]
Epoch 0:  10%|█         | 98/938 [00:07<01:02, 13.50it/s, loss=1.68, v_num=12]
Epoch 0:  11%|█         | 99/938 [00:07<01:02, 13.42it/s, loss=1.68, v_num=12]
Epoch 0:  11%|█         | 99/938 [00:07<01:02, 13.42it/s, loss=1.69, v_num=12]
Epoch 0:  11%|█         | 100/938 [00:07<01:02, 13.43it/s, loss=1.7, v_num=12]
Epoch 0:  11%|█         | 101/938 [00:07<01:02, 13.45it/s, loss=1.7, v_num=12]
Epoch 0:  11%|█         | 101/938 [00:07<01:02, 13.45it/s, loss=1.71, v_num=12]
Epoch 0:  11%|█         | 102/938 [00:07<01:02, 13.47it/s, loss=1.71, v_num=12]
Epoch 0:  11%|█         | 103/938 [00:07<01:02, 13.42it/s, loss=1.71, v_num=12]
Epoch 0:  11%|█         | 103/938 [00:07<01:02, 13.42it/s, loss=1.72, v_num=12]
Epoch 0:  11%|█         | 104/938 [00:07<01:02, 13.41it/s, loss=1.69, v_num=12]
Epoch 0:  11%|█         | 105/938 [00:07<01:02, 13.39it/s, loss=1.69, v_num=12]
Epoch 0:  11%|█         | 105/938 [00:07<01:02, 13.39it/s, loss=1.68, v_num=12]
Epoch 0:  11%|█▏        | 106/938 [00:07<01:02, 13.41it/s, loss=1.69, v_num=12]
Epoch 0:  11%|█▏        | 107/938 [00:07<01:01, 13.40it/s, loss=1.69, v_num=12]
Epoch 0:  11%|█▏        | 107/938 [00:07<01:01, 13.40it/s, loss=1.68, v_num=12]
Epoch 0:  12%|█▏        | 108/938 [00:08<01:01, 13.43it/s, loss=1.68, v_num=12]
Epoch 0:  12%|█▏        | 109/938 [00:08<01:01, 13.44it/s, loss=1.68, v_num=12]
Epoch 0:  12%|█▏        | 109/938 [00:08<01:01, 13.44it/s, loss=1.68, v_num=12]
Epoch 0:  12%|█▏        | 110/938 [00:08<01:01, 13.47it/s, loss=1.68, v_num=12]
Epoch 0:  12%|█▏        | 111/938 [00:08<01:01, 13.48it/s, loss=1.68, v_num=12]
Epoch 0:  12%|█▏        | 111/938 [00:08<01:01, 13.48it/s, loss=1.67, v_num=12]
Epoch 0:  12%|█▏        | 112/938 [00:08<01:01, 13.51it/s, loss=1.65, v_num=12]
Epoch 0:  12%|█▏        | 113/938 [00:08<01:01, 13.50it/s, loss=1.65, v_num=12]
Epoch 0:  12%|█▏        | 113/938 [00:08<01:01, 13.50it/s, loss=1.67, v_num=12]
Epoch 0:  12%|█▏        | 114/938 [00:08<01:01, 13.50it/s, loss=1.66, v_num=12]
Epoch 0:  12%|█▏        | 115/938 [00:08<01:00, 13.53it/s, loss=1.66, v_num=12]
Epoch 0:  12%|█▏        | 115/938 [00:08<01:00, 13.53it/s, loss=1.67, v_num=12]
Epoch 0:  12%|█▏        | 116/938 [00:08<01:00, 13.51it/s, loss=1.66, v_num=12]
Epoch 0:  12%|█▏        | 117/938 [00:08<01:00, 13.51it/s, loss=1.66, v_num=12]
Epoch 0:  12%|█▏        | 117/938 [00:08<01:00, 13.51it/s, loss=1.65, v_num=12]
Epoch 0:  13%|█▎        | 118/938 [00:08<01:00, 13.53it/s, loss=1.63, v_num=12]
Epoch 0:  13%|█▎        | 119/938 [00:08<01:00, 13.52it/s, loss=1.63, v_num=12]
Epoch 0:  13%|█▎        | 119/938 [00:08<01:00, 13.52it/s, loss=1.62, v_num=12]
Epoch 0:  13%|█▎        | 120/938 [00:08<01:00, 13.53it/s, loss=1.62, v_num=12]
Epoch 0:  13%|█▎        | 121/938 [00:08<01:00, 13.52it/s, loss=1.62, v_num=12]
Epoch 0:  13%|█▎        | 121/938 [00:08<01:00, 13.52it/s, loss=1.62, v_num=12]
Epoch 0:  13%|█▎        | 122/938 [00:09<01:00, 13.52it/s, loss=1.64, v_num=12]
Epoch 0:  13%|█▎        | 123/938 [00:09<01:00, 13.53it/s, loss=1.64, v_num=12]
Epoch 0:  13%|█▎        | 123/938 [00:09<01:00, 13.53it/s, loss=1.62, v_num=12]
Epoch 0:  13%|█▎        | 124/938 [00:09<01:00, 13.54it/s, loss=1.63, v_num=12]
Epoch 0:  13%|█▎        | 125/938 [00:09<01:00, 13.55it/s, loss=1.63, v_num=12]
Epoch 0:  13%|█▎        | 125/938 [00:09<01:00, 13.55it/s, loss=1.64, v_num=12]
Epoch 0:  13%|█▎        | 126/938 [00:09<00:59, 13.55it/s, loss=1.64, v_num=12]
Epoch 0:  14%|█▎        | 127/938 [00:09<00:59, 13.55it/s, loss=1.64, v_num=12]
Epoch 0:  14%|█▎        | 127/938 [00:09<00:59, 13.55it/s, loss=1.65, v_num=12]
Epoch 0:  14%|█▎        | 128/938 [00:09<00:59, 13.53it/s, loss=1.63, v_num=12]
Epoch 0:  14%|█▍        | 129/938 [00:09<00:59, 13.55it/s, loss=1.63, v_num=12]
Epoch 0:  14%|█▍        | 129/938 [00:09<00:59, 13.55it/s, loss=1.63, v_num=12]
Epoch 0:  14%|█▍        | 130/938 [00:09<00:59, 13.55it/s, loss=1.61, v_num=12]
Epoch 0:  14%|█▍        | 131/938 [00:09<00:59, 13.53it/s, loss=1.61, v_num=12]
Epoch 0:  14%|█▍        | 131/938 [00:09<00:59, 13.53it/s, loss=1.61, v_num=12]
Epoch 0:  14%|█▍        | 132/938 [00:09<00:59, 13.52it/s, loss=1.61, v_num=12]
Epoch 0:  14%|█▍        | 133/938 [00:09<00:59, 13.53it/s, loss=1.61, v_num=12]
Epoch 0:  14%|█▍        | 133/938 [00:09<00:59, 13.53it/s, loss=1.62, v_num=12]
Epoch 0:  14%|█▍        | 134/938 [00:09<00:59, 13.53it/s, loss=1.6, v_num=12] 
Epoch 0:  14%|█▍        | 135/938 [00:09<00:59, 13.53it/s, loss=1.6, v_num=12]
Epoch 0:  14%|█▍        | 135/938 [00:09<00:59, 13.53it/s, loss=1.56, v_num=12]
Epoch 0:  14%|█▍        | 136/938 [00:10<00:59, 13.55it/s, loss=1.55, v_num=12]
Epoch 0:  15%|█▍        | 137/938 [00:10<00:59, 13.55it/s, loss=1.55, v_num=12]
Epoch 0:  15%|█▍        | 137/938 [00:10<00:59, 13.55it/s, loss=1.56, v_num=12]
Epoch 0:  15%|█▍        | 138/938 [00:10<00:58, 13.57it/s, loss=1.57, v_num=12]
Epoch 0:  15%|█▍        | 139/938 [00:10<00:58, 13.57it/s, loss=1.57, v_num=12]
Epoch 0:  15%|█▍        | 139/938 [00:10<00:58, 13.57it/s, loss=1.57, v_num=12]
Epoch 0:  15%|█▍        | 140/938 [00:10<00:58, 13.58it/s, loss=1.57, v_num=12]
Epoch 0:  15%|█▌        | 141/938 [00:10<00:58, 13.57it/s, loss=1.57, v_num=12]
Epoch 0:  15%|█▌        | 141/938 [00:10<00:58, 13.57it/s, loss=1.56, v_num=12]
Epoch 0:  15%|█▌        | 142/938 [00:10<00:58, 13.58it/s, loss=1.54, v_num=12]
Epoch 0:  15%|█▌        | 143/938 [00:10<00:58, 13.59it/s, loss=1.54, v_num=12]
Epoch 0:  15%|█▌        | 143/938 [00:10<00:58, 13.58it/s, loss=1.54, v_num=12]
Epoch 0:  15%|█▌        | 144/938 [00:10<00:58, 13.58it/s, loss=1.54, v_num=12]
Epoch 0:  15%|█▌        | 145/938 [00:10<00:58, 13.58it/s, loss=1.54, v_num=12]
Epoch 0:  15%|█▌        | 145/938 [00:10<00:58, 13.58it/s, loss=1.52, v_num=12]
Epoch 0:  16%|█▌        | 146/938 [00:10<00:58, 13.60it/s, loss=1.49, v_num=12]
Epoch 0:  16%|█▌        | 147/938 [00:10<00:58, 13.60it/s, loss=1.49, v_num=12]
Epoch 0:  16%|█▌        | 147/938 [00:10<00:58, 13.60it/s, loss=1.48, v_num=12]
Epoch 0:  16%|█▌        | 148/938 [00:10<00:58, 13.60it/s, loss=1.47, v_num=12]
Epoch 0:  16%|█▌        | 149/938 [00:10<00:58, 13.59it/s, loss=1.47, v_num=12]
Epoch 0:  16%|█▌        | 149/938 [00:10<00:58, 13.59it/s, loss=1.45, v_num=12]
Epoch 0:  16%|█▌        | 150/938 [00:11<00:57, 13.61it/s, loss=1.45, v_num=12]
Epoch 0:  16%|█▌        | 151/938 [00:11<00:57, 13.60it/s, loss=1.45, v_num=12]
Epoch 0:  16%|█▌        | 151/938 [00:11<00:57, 13.60it/s, loss=1.44, v_num=12]
Epoch 0:  16%|█▌        | 152/938 [00:11<00:57, 13.59it/s, loss=1.43, v_num=12]
Epoch 0:  16%|█▋        | 153/938 [00:11<00:57, 13.58it/s, loss=1.43, v_num=12]
Epoch 0:  16%|█▋        | 153/938 [00:11<00:57, 13.58it/s, loss=1.39, v_num=12]
Epoch 0:  16%|█▋        | 154/938 [00:11<00:57, 13.59it/s, loss=1.4, v_num=12] 
Epoch 0:  17%|█▋        | 155/938 [00:11<00:57, 13.57it/s, loss=1.4, v_num=12]
Epoch 0:  17%|█▋        | 155/938 [00:11<00:57, 13.57it/s, loss=1.4, v_num=12]
Epoch 0:  17%|█▋        | 156/938 [00:11<00:57, 13.57it/s, loss=1.4, v_num=12]
Epoch 0:  17%|█▋        | 157/938 [00:11<00:57, 13.57it/s, loss=1.4, v_num=12]
Epoch 0:  17%|█▋        | 157/938 [00:11<00:57, 13.57it/s, loss=1.39, v_num=12]
Epoch 0:  17%|█▋        | 158/938 [00:11<00:57, 13.58it/s, loss=1.37, v_num=12]
Epoch 0:  17%|█▋        | 159/938 [00:11<00:57, 13.59it/s, loss=1.37, v_num=12]
Epoch 0:  17%|█▋        | 159/938 [00:11<00:57, 13.59it/s, loss=1.37, v_num=12]
Epoch 0:  17%|█▋        | 160/938 [00:11<00:57, 13.60it/s, loss=1.34, v_num=12]
Epoch 0:  17%|█▋        | 161/938 [00:11<00:57, 13.62it/s, loss=1.34, v_num=12]
Epoch 0:  17%|█▋        | 161/938 [00:11<00:57, 13.62it/s, loss=1.32, v_num=12]
Epoch 0:  17%|█▋        | 162/938 [00:11<00:57, 13.61it/s, loss=1.31, v_num=12]
Epoch 0:  17%|█▋        | 163/938 [00:11<00:56, 13.62it/s, loss=1.31, v_num=12]
Epoch 0:  17%|█▋        | 163/938 [00:11<00:56, 13.62it/s, loss=1.3, v_num=12] 
Epoch 0:  17%|█▋        | 164/938 [00:12<00:56, 13.61it/s, loss=1.28, v_num=12]
Epoch 0:  18%|█▊        | 165/938 [00:12<00:56, 13.61it/s, loss=1.28, v_num=12]
Epoch 0:  18%|█▊        | 165/938 [00:12<00:56, 13.61it/s, loss=1.28, v_num=12]
Epoch 0:  18%|█▊        | 166/938 [00:12<00:56, 13.62it/s, loss=1.29, v_num=12]
Epoch 0:  18%|█▊        | 167/938 [00:12<00:56, 13.62it/s, loss=1.29, v_num=12]
Epoch 0:  18%|█▊        | 167/938 [00:12<00:56, 13.62it/s, loss=1.28, v_num=12]
Epoch 0:  18%|█▊        | 168/938 [00:12<00:56, 13.63it/s, loss=1.27, v_num=12]
Epoch 0:  18%|█▊        | 169/938 [00:12<00:56, 13.64it/s, loss=1.27, v_num=12]
Epoch 0:  18%|█▊        | 169/938 [00:12<00:56, 13.64it/s, loss=1.26, v_num=12]
Epoch 0:  18%|█▊        | 170/938 [00:12<00:56, 13.64it/s, loss=1.26, v_num=12]
Epoch 0:  18%|█▊        | 171/938 [00:12<00:56, 13.65it/s, loss=1.26, v_num=12]
Epoch 0:  18%|█▊        | 171/938 [00:12<00:56, 13.65it/s, loss=1.26, v_num=12]
Epoch 0:  18%|█▊        | 172/938 [00:12<00:56, 13.66it/s, loss=1.25, v_num=12]
Epoch 0:  18%|█▊        | 173/938 [00:12<00:55, 13.67it/s, loss=1.25, v_num=12]
Epoch 0:  18%|█▊        | 173/938 [00:12<00:55, 13.67it/s, loss=1.24, v_num=12]
Epoch 0:  19%|█▊        | 174/938 [00:12<00:55, 13.66it/s, loss=1.24, v_num=12]
Epoch 0:  19%|█▊        | 175/938 [00:12<00:55, 13.67it/s, loss=1.24, v_num=12]
Epoch 0:  19%|█▊        | 175/938 [00:12<00:55, 13.67it/s, loss=1.23, v_num=12]
Epoch 0:  19%|█▉        | 176/938 [00:12<00:55, 13.68it/s, loss=1.22, v_num=12]
Epoch 0:  19%|█▉        | 177/938 [00:12<00:55, 13.68it/s, loss=1.22, v_num=12]
Epoch 0:  19%|█▉        | 177/938 [00:12<00:55, 13.68it/s, loss=1.21, v_num=12]
Epoch 0:  19%|█▉        | 178/938 [00:13<00:55, 13.68it/s, loss=1.21, v_num=12]
Epoch 0:  19%|█▉        | 179/938 [00:13<00:55, 13.69it/s, loss=1.21, v_num=12]
Epoch 0:  19%|█▉        | 179/938 [00:13<00:55, 13.69it/s, loss=1.2, v_num=12] 
Epoch 0:  19%|█▉        | 180/938 [00:13<00:55, 13.70it/s, loss=1.2, v_num=12]
Epoch 0:  19%|█▉        | 181/938 [00:13<00:55, 13.69it/s, loss=1.2, v_num=12]
Epoch 0:  19%|█▉        | 181/938 [00:13<00:55, 13.69it/s, loss=1.2, v_num=12]
Epoch 0:  19%|█▉        | 182/938 [00:13<00:55, 13.69it/s, loss=1.19, v_num=12]
Epoch 0:  20%|█▉        | 183/938 [00:13<00:55, 13.69it/s, loss=1.19, v_num=12]
Epoch 0:  20%|█▉        | 183/938 [00:13<00:55, 13.69it/s, loss=1.18, v_num=12]
Epoch 0:  20%|█▉        | 184/938 [00:13<00:55, 13.69it/s, loss=1.17, v_num=12]
Epoch 0:  20%|█▉        | 185/938 [00:13<00:54, 13.70it/s, loss=1.17, v_num=12]
Epoch 0:  20%|█▉        | 185/938 [00:13<00:54, 13.70it/s, loss=1.17, v_num=12]
Epoch 0:  20%|█▉        | 186/938 [00:13<00:54, 13.72it/s, loss=1.16, v_num=12]
Epoch 0:  20%|█▉        | 187/938 [00:13<00:54, 13.70it/s, loss=1.16, v_num=12]
Epoch 0:  20%|█▉        | 187/938 [00:13<00:54, 13.70it/s, loss=1.14, v_num=12]
Epoch 0:  20%|██        | 188/938 [00:13<00:54, 13.71it/s, loss=1.14, v_num=12]
Epoch 0:  20%|██        | 189/938 [00:13<00:54, 13.72it/s, loss=1.14, v_num=12]
Epoch 0:  20%|██        | 189/938 [00:13<00:54, 13.72it/s, loss=1.14, v_num=12]
Epoch 0:  20%|██        | 190/938 [00:13<00:54, 13.73it/s, loss=1.12, v_num=12]
Epoch 0:  20%|██        | 191/938 [00:13<00:54, 13.73it/s, loss=1.12, v_num=12]
Epoch 0:  20%|██        | 191/938 [00:13<00:54, 13.73it/s, loss=1.11, v_num=12]
Epoch 0:  20%|██        | 192/938 [00:13<00:54, 13.73it/s, loss=1.11, v_num=12]
Epoch 0:  21%|██        | 193/938 [00:14<00:54, 13.71it/s, loss=1.11, v_num=12]
Epoch 0:  21%|██        | 193/938 [00:14<00:54, 13.71it/s, loss=1.1, v_num=12] 
Epoch 0:  21%|██        | 194/938 [00:14<00:54, 13.71it/s, loss=1.09, v_num=12]
Epoch 0:  21%|██        | 195/938 [00:14<00:54, 13.73it/s, loss=1.09, v_num=12]
Epoch 0:  21%|██        | 195/938 [00:14<00:54, 13.73it/s, loss=1.1, v_num=12] 
Epoch 0:  21%|██        | 196/938 [00:14<00:54, 13.73it/s, loss=1.08, v_num=12]
Epoch 0:  21%|██        | 197/938 [00:14<00:53, 13.74it/s, loss=1.08, v_num=12]
Epoch 0:  21%|██        | 197/938 [00:14<00:53, 13.74it/s, loss=1.07, v_num=12]
Epoch 0:  21%|██        | 198/938 [00:14<00:53, 13.73it/s, loss=1.06, v_num=12]
Epoch 0:  21%|██        | 199/938 [00:14<00:53, 13.70it/s, loss=1.06, v_num=12]
Epoch 0:  21%|██        | 199/938 [00:14<00:53, 13.70it/s, loss=1.06, v_num=12]
Epoch 0:  21%|██▏       | 200/938 [00:14<00:53, 13.70it/s, loss=1.05, v_num=12]
Epoch 0:  21%|██▏       | 201/938 [00:14<00:53, 13.71it/s, loss=1.05, v_num=12]
Epoch 0:  21%|██▏       | 201/938 [00:14<00:53, 13.71it/s, loss=1.05, v_num=12]
Epoch 0:  22%|██▏       | 202/938 [00:14<00:53, 13.70it/s, loss=1.06, v_num=12]
Epoch 0:  22%|██▏       | 203/938 [00:14<00:53, 13.71it/s, loss=1.06, v_num=12]
Epoch 0:  22%|██▏       | 203/938 [00:14<00:53, 13.71it/s, loss=1.07, v_num=12]
Epoch 0:  22%|██▏       | 204/938 [00:14<00:53, 13.71it/s, loss=1.06, v_num=12]
Epoch 0:  22%|██▏       | 205/938 [00:14<00:53, 13.71it/s, loss=1.06, v_num=12]
Epoch 0:  22%|██▏       | 205/938 [00:14<00:53, 13.71it/s, loss=1.05, v_num=12]
Epoch 0:  22%|██▏       | 206/938 [00:15<00:53, 13.71it/s, loss=1.04, v_num=12]
Epoch 0:  22%|██▏       | 207/938 [00:15<00:53, 13.72it/s, loss=1.04, v_num=12]
Epoch 0:  22%|██▏       | 207/938 [00:15<00:53, 13.72it/s, loss=1.05, v_num=12]
Epoch 0:  22%|██▏       | 208/938 [00:15<00:53, 13.71it/s, loss=1.06, v_num=12]
Epoch 0:  22%|██▏       | 209/938 [00:15<00:53, 13.71it/s, loss=1.06, v_num=12]
Epoch 0:  22%|██▏       | 209/938 [00:15<00:53, 13.71it/s, loss=1.05, v_num=12]
Epoch 0:  22%|██▏       | 210/938 [00:15<00:53, 13.70it/s, loss=1.04, v_num=12]
Epoch 0:  22%|██▏       | 211/938 [00:15<00:53, 13.70it/s, loss=1.04, v_num=12]
Epoch 0:  22%|██▏       | 211/938 [00:15<00:53, 13.70it/s, loss=1.03, v_num=12]
Epoch 0:  23%|██▎       | 212/938 [00:15<00:53, 13.69it/s, loss=1.03, v_num=12]
Epoch 0:  23%|██▎       | 213/938 [00:15<00:52, 13.71it/s, loss=1.03, v_num=12]
Epoch 0:  23%|██▎       | 213/938 [00:15<00:52, 13.71it/s, loss=1.01, v_num=12]
Epoch 0:  23%|██▎       | 214/938 [00:15<00:52, 13.69it/s, loss=1.01, v_num=12]
Epoch 0:  23%|██▎       | 215/938 [00:15<00:52, 13.69it/s, loss=1.01, v_num=12]
Epoch 0:  23%|██▎       | 215/938 [00:15<00:52, 13.69it/s, loss=1, v_num=12]   
Epoch 0:  23%|██▎       | 216/938 [00:15<00:52, 13.69it/s, loss=1.01, v_num=12]
Epoch 0:  23%|██▎       | 217/938 [00:15<00:52, 13.69it/s, loss=1.01, v_num=12]
Epoch 0:  23%|██▎       | 217/938 [00:15<00:52, 13.69it/s, loss=1, v_num=12]   
Epoch 0:  23%|██▎       | 218/938 [00:15<00:52, 13.70it/s, loss=1.01, v_num=12]
Epoch 0:  23%|██▎       | 219/938 [00:15<00:52, 13.70it/s, loss=1.01, v_num=12]
Epoch 0:  23%|██▎       | 219/938 [00:15<00:52, 13.70it/s, loss=1, v_num=12]   
Epoch 0:  23%|██▎       | 220/938 [00:16<00:52, 13.70it/s, loss=1.02, v_num=12]
Epoch 0:  24%|██▎       | 221/938 [00:16<00:52, 13.70it/s, loss=1.02, v_num=12]
Epoch 0:  24%|██▎       | 221/938 [00:16<00:52, 13.70it/s, loss=1.02, v_num=12]
Epoch 0:  24%|██▎       | 222/938 [00:16<00:52, 13.71it/s, loss=1.01, v_num=12]
Epoch 0:  24%|██▍       | 223/938 [00:16<00:52, 13.67it/s, loss=1.01, v_num=12]
Epoch 0:  24%|██▍       | 223/938 [00:16<00:52, 13.66it/s, loss=1.01, v_num=12]
Epoch 0:  24%|██▍       | 224/938 [00:16<00:52, 13.67it/s, loss=1.02, v_num=12]
Epoch 0:  24%|██▍       | 225/938 [00:16<00:52, 13.67it/s, loss=1.02, v_num=12]
Epoch 0:  24%|██▍       | 225/938 [00:16<00:52, 13.67it/s, loss=1.01, v_num=12]
Epoch 0:  24%|██▍       | 226/938 [00:16<00:52, 13.68it/s, loss=1.01, v_num=12]
Epoch 0:  24%|██▍       | 227/938 [00:16<00:51, 13.68it/s, loss=1.01, v_num=12]
Epoch 0:  24%|██▍       | 227/938 [00:16<00:51, 13.68it/s, loss=0.99, v_num=12]
Epoch 0:  24%|██▍       | 228/938 [00:16<00:51, 13.69it/s, loss=0.993, v_num=12]
Epoch 0:  24%|██▍       | 229/938 [00:16<00:51, 13.68it/s, loss=0.993, v_num=12]
Epoch 0:  24%|██▍       | 229/938 [00:16<00:51, 13.68it/s, loss=1.01, v_num=12] 
Epoch 0:  25%|██▍       | 230/938 [00:16<00:51, 13.69it/s, loss=1.01, v_num=12]
Epoch 0:  25%|██▍       | 231/938 [00:16<00:51, 13.69it/s, loss=1.01, v_num=12]
Epoch 0:  25%|██▍       | 231/938 [00:16<00:51, 13.69it/s, loss=1.02, v_num=12]
Epoch 0:  25%|██▍       | 232/938 [00:16<00:51, 13.70it/s, loss=1.02, v_num=12]
Epoch 0:  25%|██▍       | 233/938 [00:17<00:51, 13.71it/s, loss=1.02, v_num=12]
Epoch 0:  25%|██▍       | 233/938 [00:17<00:51, 13.71it/s, loss=1.04, v_num=12]
Epoch 0:  25%|██▍       | 234/938 [00:17<00:51, 13.69it/s, loss=1.04, v_num=12]
Epoch 0:  25%|██▌       | 235/938 [00:17<00:51, 13.70it/s, loss=1.04, v_num=12]
Epoch 0:  25%|██▌       | 235/938 [00:17<00:51, 13.70it/s, loss=1.04, v_num=12]
Epoch 0:  25%|██▌       | 236/938 [00:17<00:51, 13.68it/s, loss=1.04, v_num=12]
Epoch 0:  25%|██▌       | 237/938 [00:17<00:51, 13.69it/s, loss=1.04, v_num=12]
Epoch 0:  25%|██▌       | 237/938 [00:17<00:51, 13.69it/s, loss=1.06, v_num=12]
Epoch 0:  25%|██▌       | 238/938 [00:17<00:51, 13.70it/s, loss=1.05, v_num=12]
Epoch 0:  25%|██▌       | 239/938 [00:17<00:50, 13.71it/s, loss=1.05, v_num=12]
Epoch 0:  25%|██▌       | 239/938 [00:17<00:50, 13.71it/s, loss=1.05, v_num=12]
Epoch 0:  26%|██▌       | 240/938 [00:17<00:50, 13.71it/s, loss=1.04, v_num=12]
Epoch 0:  26%|██▌       | 241/938 [00:17<00:50, 13.71it/s, loss=1.04, v_num=12]
Epoch 0:  26%|██▌       | 241/938 [00:17<00:50, 13.71it/s, loss=1.03, v_num=12]
Epoch 0:  26%|██▌       | 242/938 [00:17<00:50, 13.71it/s, loss=1.04, v_num=12]
Epoch 0:  26%|██▌       | 243/938 [00:17<00:50, 13.71it/s, loss=1.04, v_num=12]
Epoch 0:  26%|██▌       | 243/938 [00:17<00:50, 13.71it/s, loss=1.02, v_num=12]
Epoch 0:  26%|██▌       | 244/938 [00:17<00:50, 13.70it/s, loss=1.02, v_num=12]
Epoch 0:  26%|██▌       | 245/938 [00:17<00:50, 13.70it/s, loss=1.02, v_num=12]
Epoch 0:  26%|██▌       | 245/938 [00:17<00:50, 13.70it/s, loss=1.01, v_num=12]
Epoch 0:  26%|██▌       | 246/938 [00:17<00:50, 13.71it/s, loss=1.02, v_num=12]
Epoch 0:  26%|██▋       | 247/938 [00:18<00:50, 13.70it/s, loss=1.02, v_num=12]
Epoch 0:  26%|██▋       | 247/938 [00:18<00:50, 13.70it/s, loss=1.02, v_num=12]
Epoch 0:  26%|██▋       | 248/938 [00:18<00:50, 13.71it/s, loss=0.991, v_num=12]
Epoch 0:  27%|██▋       | 249/938 [00:18<00:50, 13.71it/s, loss=0.991, v_num=12]
Epoch 0:  27%|██▋       | 249/938 [00:18<00:50, 13.71it/s, loss=0.991, v_num=12]
Epoch 0:  27%|██▋       | 250/938 [00:18<00:50, 13.73it/s, loss=0.988, v_num=12]
Epoch 0:  27%|██▋       | 251/938 [00:18<00:50, 13.73it/s, loss=0.988, v_num=12]
Epoch 0:  27%|██▋       | 251/938 [00:18<00:50, 13.73it/s, loss=0.977, v_num=12]
Epoch 0:  27%|██▋       | 252/938 [00:18<00:49, 13.74it/s, loss=0.964, v_num=12]
Epoch 0:  27%|██▋       | 253/938 [00:18<00:49, 13.74it/s, loss=0.964, v_num=12]
Epoch 0:  27%|██▋       | 253/938 [00:18<00:49, 13.74it/s, loss=0.958, v_num=12]
Epoch 0:  27%|██▋       | 254/938 [00:18<00:49, 13.74it/s, loss=0.949, v_num=12]
Epoch 0:  27%|██▋       | 255/938 [00:18<00:49, 13.74it/s, loss=0.949, v_num=12]
Epoch 0:  27%|██▋       | 255/938 [00:18<00:49, 13.74it/s, loss=0.95, v_num=12] 
Epoch 0:  27%|██▋       | 256/938 [00:18<00:49, 13.74it/s, loss=0.959, v_num=12]
Epoch 0:  27%|██▋       | 257/938 [00:18<00:49, 13.74it/s, loss=0.959, v_num=12]
Epoch 0:  27%|██▋       | 257/938 [00:18<00:49, 13.74it/s, loss=0.947, v_num=12]
Epoch 0:  28%|██▊       | 258/938 [00:18<00:49, 13.75it/s, loss=0.948, v_num=12]
Epoch 0:  28%|██▊       | 259/938 [00:18<00:49, 13.75it/s, loss=0.948, v_num=12]
Epoch 0:  28%|██▊       | 259/938 [00:18<00:49, 13.75it/s, loss=0.937, v_num=12]
Epoch 0:  28%|██▊       | 260/938 [00:18<00:49, 13.76it/s, loss=0.924, v_num=12]
Epoch 0:  28%|██▊       | 261/938 [00:18<00:49, 13.75it/s, loss=0.924, v_num=12]
Epoch 0:  28%|██▊       | 261/938 [00:18<00:49, 13.75it/s, loss=0.918, v_num=12]
Epoch 0:  28%|██▊       | 262/938 [00:19<00:49, 13.75it/s, loss=0.905, v_num=12]
Epoch 0:  28%|██▊       | 263/938 [00:19<00:49, 13.75it/s, loss=0.905, v_num=12]
Epoch 0:  28%|██▊       | 263/938 [00:19<00:49, 13.75it/s, loss=0.914, v_num=12]
Epoch 0:  28%|██▊       | 264/938 [00:19<00:48, 13.76it/s, loss=0.916, v_num=12]
Epoch 0:  28%|██▊       | 265/938 [00:19<00:48, 13.77it/s, loss=0.916, v_num=12]
Epoch 0:  28%|██▊       | 265/938 [00:19<00:48, 13.77it/s, loss=0.927, v_num=12]
Epoch 0:  28%|██▊       | 266/938 [00:19<00:48, 13.78it/s, loss=0.923, v_num=12]
Epoch 0:  28%|██▊       | 267/938 [00:19<00:48, 13.79it/s, loss=0.923, v_num=12]
Epoch 0:  28%|██▊       | 267/938 [00:19<00:48, 13.79it/s, loss=0.926, v_num=12]
Epoch 0:  29%|██▊       | 268/938 [00:19<00:48, 13.78it/s, loss=0.936, v_num=12]
Epoch 0:  29%|██▊       | 269/938 [00:19<00:48, 13.78it/s, loss=0.936, v_num=12]
Epoch 0:  29%|██▊       | 269/938 [00:19<00:48, 13.78it/s, loss=0.927, v_num=12]
Epoch 0:  29%|██▉       | 270/938 [00:19<00:48, 13.78it/s, loss=0.926, v_num=12]
Epoch 0:  29%|██▉       | 271/938 [00:19<00:48, 13.78it/s, loss=0.926, v_num=12]
Epoch 0:  29%|██▉       | 271/938 [00:19<00:48, 13.78it/s, loss=0.935, v_num=12]
Epoch 0:  29%|██▉       | 272/938 [00:19<00:48, 13.78it/s, loss=0.938, v_num=12]
Epoch 0:  29%|██▉       | 273/938 [00:19<00:48, 13.78it/s, loss=0.938, v_num=12]
Epoch 0:  29%|██▉       | 273/938 [00:19<00:48, 13.78it/s, loss=0.933, v_num=12]
Epoch 0:  29%|██▉       | 274/938 [00:19<00:48, 13.79it/s, loss=0.944, v_num=12]
Epoch 0:  29%|██▉       | 275/938 [00:19<00:48, 13.78it/s, loss=0.944, v_num=12]
Epoch 0:  29%|██▉       | 275/938 [00:19<00:48, 13.78it/s, loss=0.946, v_num=12]
Epoch 0:  29%|██▉       | 276/938 [00:20<00:48, 13.77it/s, loss=0.937, v_num=12]
Epoch 0:  30%|██▉       | 277/938 [00:20<00:48, 13.77it/s, loss=0.937, v_num=12]
Epoch 0:  30%|██▉       | 277/938 [00:20<00:48, 13.77it/s, loss=0.943, v_num=12]
Epoch 0:  30%|██▉       | 278/938 [00:20<00:47, 13.77it/s, loss=0.944, v_num=12]
Epoch 0:  30%|██▉       | 279/938 [00:20<00:47, 13.77it/s, loss=0.944, v_num=12]
Epoch 0:  30%|██▉       | 279/938 [00:20<00:47, 13.76it/s, loss=0.951, v_num=12]
Epoch 0:  30%|██▉       | 280/938 [00:20<00:47, 13.76it/s, loss=0.961, v_num=12]
Epoch 0:  30%|██▉       | 281/938 [00:20<00:47, 13.77it/s, loss=0.961, v_num=12]
Epoch 0:  30%|██▉       | 281/938 [00:20<00:47, 13.77it/s, loss=0.969, v_num=12]
Epoch 0:  30%|███       | 282/938 [00:20<00:47, 13.76it/s, loss=0.968, v_num=12]
Epoch 0:  30%|███       | 283/938 [00:20<00:47, 13.76it/s, loss=0.968, v_num=12]
Epoch 0:  30%|███       | 283/938 [00:20<00:47, 13.76it/s, loss=0.966, v_num=12]
Epoch 0:  30%|███       | 284/938 [00:20<00:47, 13.76it/s, loss=0.972, v_num=12]
Epoch 0:  30%|███       | 285/938 [00:20<00:47, 13.75it/s, loss=0.972, v_num=12]
Epoch 0:  30%|███       | 285/938 [00:20<00:47, 13.75it/s, loss=0.972, v_num=12]
Epoch 0:  30%|███       | 286/938 [00:20<00:47, 13.75it/s, loss=0.963, v_num=12]
Epoch 0:  31%|███       | 287/938 [00:20<00:47, 13.73it/s, loss=0.963, v_num=12]
Epoch 0:  31%|███       | 287/938 [00:20<00:47, 13.73it/s, loss=0.961, v_num=12]
Epoch 0:  31%|███       | 288/938 [00:20<00:47, 13.73it/s, loss=0.964, v_num=12]
Epoch 0:  31%|███       | 289/938 [00:21<00:47, 13.74it/s, loss=0.964, v_num=12]
Epoch 0:  31%|███       | 289/938 [00:21<00:47, 13.74it/s, loss=0.964, v_num=12]
Epoch 0:  31%|███       | 290/938 [00:21<00:47, 13.75it/s, loss=0.961, v_num=12]
Epoch 0:  31%|███       | 291/938 [00:21<00:47, 13.75it/s, loss=0.961, v_num=12]
Epoch 0:  31%|███       | 291/938 [00:21<00:47, 13.75it/s, loss=0.957, v_num=12]
Epoch 0:  31%|███       | 292/938 [00:21<00:46, 13.75it/s, loss=0.966, v_num=12]
Epoch 0:  31%|███       | 293/938 [00:21<00:46, 13.75it/s, loss=0.966, v_num=12]
Epoch 0:  31%|███       | 293/938 [00:21<00:46, 13.75it/s, loss=0.969, v_num=12]
Epoch 0:  31%|███▏      | 294/938 [00:21<00:46, 13.75it/s, loss=0.958, v_num=12]
Epoch 0:  31%|███▏      | 295/938 [00:21<00:46, 13.75it/s, loss=0.958, v_num=12]
Epoch 0:  31%|███▏      | 295/938 [00:21<00:46, 13.75it/s, loss=0.948, v_num=12]
Epoch 0:  32%|███▏      | 296/938 [00:21<00:46, 13.75it/s, loss=0.953, v_num=12]
Epoch 0:  32%|███▏      | 297/938 [00:21<00:46, 13.75it/s, loss=0.953, v_num=12]
Epoch 0:  32%|███▏      | 297/938 [00:21<00:46, 13.75it/s, loss=0.951, v_num=12]
Epoch 0:  32%|███▏      | 298/938 [00:21<00:46, 13.74it/s, loss=0.944, v_num=12]
Epoch 0:  32%|███▏      | 299/938 [00:21<00:46, 13.74it/s, loss=0.944, v_num=12]
Epoch 0:  32%|███▏      | 299/938 [00:21<00:46, 13.74it/s, loss=0.932, v_num=12]
Epoch 0:  32%|███▏      | 300/938 [00:21<00:46, 13.74it/s, loss=0.923, v_num=12]
Epoch 0:  32%|███▏      | 301/938 [00:21<00:46, 13.75it/s, loss=0.923, v_num=12]
Epoch 0:  32%|███▏      | 301/938 [00:21<00:46, 13.75it/s, loss=0.916, v_num=12]
Epoch 0:  32%|███▏      | 302/938 [00:21<00:46, 13.75it/s, loss=0.921, v_num=12]
Epoch 0:  32%|███▏      | 303/938 [00:22<00:46, 13.75it/s, loss=0.921, v_num=12]
Epoch 0:  32%|███▏      | 303/938 [00:22<00:46, 13.75it/s, loss=0.918, v_num=12]
Epoch 0:  32%|███▏      | 304/938 [00:22<00:46, 13.74it/s, loss=0.905, v_num=12]
Epoch 0:  33%|███▎      | 305/938 [00:22<00:46, 13.74it/s, loss=0.905, v_num=12]
Epoch 0:  33%|███▎      | 305/938 [00:22<00:46, 13.74it/s, loss=0.903, v_num=12]
Epoch 0:  33%|███▎      | 306/938 [00:22<00:46, 13.74it/s, loss=0.92, v_num=12] 
Epoch 0:  33%|███▎      | 307/938 [00:22<00:45, 13.74it/s, loss=0.92, v_num=12]
Epoch 0:  33%|███▎      | 307/938 [00:22<00:45, 13.74it/s, loss=0.921, v_num=12]
Epoch 0:  33%|███▎      | 308/938 [00:22<00:45, 13.73it/s, loss=0.921, v_num=12]
Epoch 0:  33%|███▎      | 309/938 [00:22<00:45, 13.73it/s, loss=0.921, v_num=12]
Epoch 0:  33%|███▎      | 309/938 [00:22<00:45, 13.73it/s, loss=0.923, v_num=12]
Epoch 0:  33%|███▎      | 310/938 [00:22<00:45, 13.74it/s, loss=0.928, v_num=12]
Epoch 0:  33%|███▎      | 311/938 [00:22<00:45, 13.74it/s, loss=0.928, v_num=12]
Epoch 0:  33%|███▎      | 311/938 [00:22<00:45, 13.74it/s, loss=0.928, v_num=12]
Epoch 0:  33%|███▎      | 312/938 [00:22<00:45, 13.73it/s, loss=0.927, v_num=12]
Epoch 0:  33%|███▎      | 313/938 [00:22<00:45, 13.74it/s, loss=0.927, v_num=12]
Epoch 0:  33%|███▎      | 313/938 [00:22<00:45, 13.74it/s, loss=0.927, v_num=12]
Epoch 0:  33%|███▎      | 314/938 [00:22<00:45, 13.74it/s, loss=0.934, v_num=12]
Epoch 0:  34%|███▎      | 315/938 [00:22<00:45, 13.74it/s, loss=0.934, v_num=12]
Epoch 0:  34%|███▎      | 315/938 [00:22<00:45, 13.74it/s, loss=0.946, v_num=12]
Epoch 0:  34%|███▎      | 316/938 [00:23<00:45, 13.73it/s, loss=0.946, v_num=12]
Epoch 0:  34%|███▍      | 317/938 [00:23<00:45, 13.74it/s, loss=0.946, v_num=12]
Epoch 0:  34%|███▍      | 317/938 [00:23<00:45, 13.74it/s, loss=0.942, v_num=12]
Epoch 0:  34%|███▍      | 318/938 [00:23<00:45, 13.74it/s, loss=0.941, v_num=12]
Epoch 0:  34%|███▍      | 319/938 [00:23<00:45, 13.74it/s, loss=0.941, v_num=12]
Epoch 0:  34%|███▍      | 319/938 [00:23<00:45, 13.74it/s, loss=0.937, v_num=12]
Epoch 0:  34%|███▍      | 320/938 [00:23<00:44, 13.74it/s, loss=0.935, v_num=12]
Epoch 0:  34%|███▍      | 321/938 [00:23<00:44, 13.74it/s, loss=0.935, v_num=12]
Epoch 0:  34%|███▍      | 321/938 [00:23<00:44, 13.74it/s, loss=0.936, v_num=12]
Epoch 0:  34%|███▍      | 322/938 [00:23<00:44, 13.75it/s, loss=0.939, v_num=12]
Epoch 0:  34%|███▍      | 323/938 [00:23<00:44, 13.76it/s, loss=0.939, v_num=12]
Epoch 0:  34%|███▍      | 323/938 [00:23<00:44, 13.76it/s, loss=0.943, v_num=12]
Epoch 0:  35%|███▍      | 324/938 [00:23<00:44, 13.76it/s, loss=0.939, v_num=12]
Epoch 0:  35%|███▍      | 325/938 [00:23<00:44, 13.76it/s, loss=0.939, v_num=12]
Epoch 0:  35%|███▍      | 325/938 [00:23<00:44, 13.76it/s, loss=0.934, v_num=12]
Epoch 0:  35%|███▍      | 326/938 [00:23<00:44, 13.77it/s, loss=0.924, v_num=12]
Epoch 0:  35%|███▍      | 327/938 [00:23<00:44, 13.76it/s, loss=0.924, v_num=12]
Epoch 0:  35%|███▍      | 327/938 [00:23<00:44, 13.76it/s, loss=0.932, v_num=12]
Epoch 0:  35%|███▍      | 328/938 [00:23<00:44, 13.76it/s, loss=0.926, v_num=12]
Epoch 0:  35%|███▌      | 329/938 [00:23<00:44, 13.76it/s, loss=0.926, v_num=12]
Epoch 0:  35%|███▌      | 329/938 [00:23<00:44, 13.76it/s, loss=0.918, v_num=12]
Epoch 0:  35%|███▌      | 330/938 [00:23<00:44, 13.76it/s, loss=0.918, v_num=12]
Epoch 0:  35%|███▌      | 331/938 [00:24<00:44, 13.76it/s, loss=0.918, v_num=12]
Epoch 0:  35%|███▌      | 331/938 [00:24<00:44, 13.76it/s, loss=0.915, v_num=12]
Epoch 0:  35%|███▌      | 332/938 [00:24<00:44, 13.77it/s, loss=0.9, v_num=12]  
Epoch 0:  36%|███▌      | 333/938 [00:24<00:43, 13.77it/s, loss=0.9, v_num=12]
Epoch 0:  36%|███▌      | 333/938 [00:24<00:43, 13.77it/s, loss=0.894, v_num=12]
Epoch 0:  36%|███▌      | 334/938 [00:24<00:43, 13.77it/s, loss=0.896, v_num=12]
Epoch 0:  36%|███▌      | 335/938 [00:24<00:43, 13.77it/s, loss=0.896, v_num=12]
Epoch 0:  36%|███▌      | 335/938 [00:24<00:43, 13.77it/s, loss=0.89, v_num=12] 
Epoch 0:  36%|███▌      | 336/938 [00:24<00:43, 13.77it/s, loss=0.872, v_num=12]
Epoch 0:  36%|███▌      | 337/938 [00:24<00:43, 13.77it/s, loss=0.872, v_num=12]
Epoch 0:  36%|███▌      | 337/938 [00:24<00:43, 13.77it/s, loss=0.861, v_num=12]
Epoch 0:  36%|███▌      | 338/938 [00:24<00:43, 13.78it/s, loss=0.877, v_num=12]
Epoch 0:  36%|███▌      | 339/938 [00:24<00:43, 13.78it/s, loss=0.877, v_num=12]
Epoch 0:  36%|███▌      | 339/938 [00:24<00:43, 13.78it/s, loss=0.886, v_num=12]
Epoch 0:  36%|███▌      | 340/938 [00:24<00:43, 13.78it/s, loss=0.886, v_num=12]
Epoch 0:  36%|███▋      | 341/938 [00:24<00:43, 13.79it/s, loss=0.886, v_num=12]
Epoch 0:  36%|███▋      | 341/938 [00:24<00:43, 13.79it/s, loss=0.884, v_num=12]
Epoch 0:  36%|███▋      | 342/938 [00:24<00:43, 13.79it/s, loss=0.867, v_num=12]
Epoch 0:  37%|███▋      | 343/938 [00:24<00:43, 13.79it/s, loss=0.867, v_num=12]
Epoch 0:  37%|███▋      | 343/938 [00:24<00:43, 13.79it/s, loss=0.857, v_num=12]
Epoch 0:  37%|███▋      | 344/938 [00:24<00:43, 13.79it/s, loss=0.868, v_num=12]
Epoch 0:  37%|███▋      | 345/938 [00:25<00:43, 13.78it/s, loss=0.868, v_num=12]
Epoch 0:  37%|███▋      | 345/938 [00:25<00:43, 13.78it/s, loss=0.873, v_num=12]
Epoch 0:  37%|███▋      | 346/938 [00:25<00:43, 13.76it/s, loss=0.872, v_num=12]
Epoch 0:  37%|███▋      | 347/938 [00:25<00:42, 13.76it/s, loss=0.872, v_num=12]
Epoch 0:  37%|███▋      | 347/938 [00:25<00:42, 13.76it/s, loss=0.857, v_num=12]
Epoch 0:  37%|███▋      | 348/938 [00:25<00:42, 13.75it/s, loss=0.851, v_num=12]
Epoch 0:  37%|███▋      | 349/938 [00:25<00:42, 13.74it/s, loss=0.851, v_num=12]
Epoch 0:  37%|███▋      | 349/938 [00:25<00:42, 13.74it/s, loss=0.859, v_num=12]
Epoch 0:  37%|███▋      | 350/938 [00:25<00:42, 13.74it/s, loss=0.854, v_num=12]
Epoch 0:  37%|███▋      | 351/938 [00:25<00:42, 13.74it/s, loss=0.854, v_num=12]
Epoch 0:  37%|███▋      | 351/938 [00:25<00:42, 13.74it/s, loss=0.852, v_num=12]
Epoch 0:  38%|███▊      | 352/938 [00:25<00:42, 13.72it/s, loss=0.858, v_num=12]
Epoch 0:  38%|███▊      | 353/938 [00:25<00:42, 13.72it/s, loss=0.858, v_num=12]
Epoch 0:  38%|███▊      | 353/938 [00:25<00:42, 13.72it/s, loss=0.857, v_num=12]
Epoch 0:  38%|███▊      | 354/938 [00:25<00:42, 13.72it/s, loss=0.849, v_num=12]
Epoch 0:  38%|███▊      | 355/938 [00:25<00:42, 13.73it/s, loss=0.849, v_num=12]
Epoch 0:  38%|███▊      | 355/938 [00:25<00:42, 13.73it/s, loss=0.844, v_num=12]
Epoch 0:  38%|███▊      | 356/938 [00:25<00:42, 13.72it/s, loss=0.849, v_num=12]
Epoch 0:  38%|███▊      | 357/938 [00:26<00:42, 13.73it/s, loss=0.849, v_num=12]
Epoch 0:  38%|███▊      | 357/938 [00:26<00:42, 13.73it/s, loss=0.855, v_num=12]
Epoch 0:  38%|███▊      | 358/938 [00:26<00:42, 13.73it/s, loss=0.851, v_num=12]
Epoch 0:  38%|███▊      | 359/938 [00:26<00:42, 13.74it/s, loss=0.851, v_num=12]
Epoch 0:  38%|███▊      | 359/938 [00:26<00:42, 13.73it/s, loss=0.845, v_num=12]
Epoch 0:  38%|███▊      | 360/938 [00:26<00:42, 13.73it/s, loss=0.835, v_num=12]
Epoch 0:  38%|███▊      | 361/938 [00:26<00:42, 13.74it/s, loss=0.835, v_num=12]
Epoch 0:  38%|███▊      | 361/938 [00:26<00:42, 13.73it/s, loss=0.834, v_num=12]
Epoch 0:  39%|███▊      | 362/938 [00:26<00:41, 13.74it/s, loss=0.84, v_num=12] 
Epoch 0:  39%|███▊      | 363/938 [00:26<00:41, 13.75it/s, loss=0.84, v_num=12]
Epoch 0:  39%|███▊      | 363/938 [00:26<00:41, 13.75it/s, loss=0.842, v_num=12]
Epoch 0:  39%|███▉      | 364/938 [00:26<00:41, 13.74it/s, loss=0.835, v_num=12]
Epoch 0:  39%|███▉      | 365/938 [00:26<00:41, 13.74it/s, loss=0.835, v_num=12]
Epoch 0:  39%|███▉      | 365/938 [00:26<00:41, 13.74it/s, loss=0.827, v_num=12]
Epoch 0:  39%|███▉      | 366/938 [00:26<00:41, 13.75it/s, loss=0.829, v_num=12]
Epoch 0:  39%|███▉      | 367/938 [00:26<00:41, 13.74it/s, loss=0.829, v_num=12]
Epoch 0:  39%|███▉      | 367/938 [00:26<00:41, 13.74it/s, loss=0.831, v_num=12]
Epoch 0:  39%|███▉      | 368/938 [00:26<00:41, 13.74it/s, loss=0.837, v_num=12]
Epoch 0:  39%|███▉      | 369/938 [00:26<00:41, 13.74it/s, loss=0.837, v_num=12]
Epoch 0:  39%|███▉      | 369/938 [00:26<00:41, 13.74it/s, loss=0.834, v_num=12]
Epoch 0:  39%|███▉      | 370/938 [00:26<00:41, 13.73it/s, loss=0.832, v_num=12]
Epoch 0:  40%|███▉      | 371/938 [00:27<00:41, 13.73it/s, loss=0.832, v_num=12]
Epoch 0:  40%|███▉      | 371/938 [00:27<00:41, 13.73it/s, loss=0.84, v_num=12] 
Epoch 0:  40%|███▉      | 372/938 [00:27<00:41, 13.71it/s, loss=0.837, v_num=12]
Epoch 0:  40%|███▉      | 373/938 [00:27<00:41, 13.71it/s, loss=0.837, v_num=12]
Epoch 0:  40%|███▉      | 373/938 [00:27<00:41, 13.71it/s, loss=0.839, v_num=12]
Epoch 0:  40%|███▉      | 374/938 [00:27<00:41, 13.71it/s, loss=0.839, v_num=12]
Epoch 0:  40%|███▉      | 375/938 [00:27<00:41, 13.71it/s, loss=0.839, v_num=12]
Epoch 0:  40%|███▉      | 375/938 [00:27<00:41, 13.71it/s, loss=0.847, v_num=12]
Epoch 0:  40%|████      | 376/938 [00:27<00:40, 13.72it/s, loss=0.86, v_num=12] 
Epoch 0:  40%|████      | 377/938 [00:27<00:40, 13.72it/s, loss=0.86, v_num=12]
Epoch 0:  40%|████      | 377/938 [00:27<00:40, 13.72it/s, loss=0.853, v_num=12]
Epoch 0:  40%|████      | 378/938 [00:27<00:40, 13.72it/s, loss=0.845, v_num=12]
Epoch 0:  40%|████      | 379/938 [00:27<00:40, 13.72it/s, loss=0.845, v_num=12]
Epoch 0:  40%|████      | 379/938 [00:27<00:40, 13.72it/s, loss=0.849, v_num=12]
Epoch 0:  41%|████      | 380/938 [00:27<00:40, 13.72it/s, loss=0.867, v_num=12]
Epoch 0:  41%|████      | 381/938 [00:27<00:40, 13.72it/s, loss=0.867, v_num=12]
Epoch 0:  41%|████      | 381/938 [00:27<00:40, 13.72it/s, loss=0.866, v_num=12]
Epoch 0:  41%|████      | 382/938 [00:27<00:40, 13.73it/s, loss=0.863, v_num=12]
Epoch 0:  41%|████      | 383/938 [00:27<00:40, 13.73it/s, loss=0.863, v_num=12]
Epoch 0:  41%|████      | 383/938 [00:27<00:40, 13.73it/s, loss=0.86, v_num=12] 
Epoch 0:  41%|████      | 384/938 [00:27<00:40, 13.74it/s, loss=0.849, v_num=12]
Epoch 0:  41%|████      | 385/938 [00:28<00:40, 13.73it/s, loss=0.849, v_num=12]
Epoch 0:  41%|████      | 385/938 [00:28<00:40, 13.73it/s, loss=0.876, v_num=12]
Epoch 0:  41%|████      | 386/938 [00:28<00:40, 13.73it/s, loss=0.872, v_num=12]
Epoch 0:  41%|████▏     | 387/938 [00:28<00:40, 13.73it/s, loss=0.872, v_num=12]
Epoch 0:  41%|████▏     | 387/938 [00:28<00:40, 13.73it/s, loss=0.872, v_num=12]
Epoch 0:  41%|████▏     | 388/938 [00:28<00:40, 13.73it/s, loss=0.877, v_num=12]
Epoch 0:  41%|████▏     | 389/938 [00:28<00:39, 13.73it/s, loss=0.877, v_num=12]
Epoch 0:  41%|████▏     | 389/938 [00:28<00:39, 13.73it/s, loss=0.874, v_num=12]
Epoch 0:  42%|████▏     | 390/938 [00:28<00:39, 13.74it/s, loss=0.875, v_num=12]
Epoch 0:  42%|████▏     | 391/938 [00:28<00:39, 13.74it/s, loss=0.875, v_num=12]
Epoch 0:  42%|████▏     | 391/938 [00:28<00:39, 13.73it/s, loss=0.864, v_num=12]
Epoch 0:  42%|████▏     | 392/938 [00:28<00:39, 13.74it/s, loss=0.881, v_num=12]
Epoch 0:  42%|████▏     | 393/938 [00:28<00:39, 13.75it/s, loss=0.881, v_num=12]
Epoch 0:  42%|████▏     | 393/938 [00:28<00:39, 13.75it/s, loss=0.871, v_num=12]
Epoch 0:  42%|████▏     | 394/938 [00:28<00:39, 13.75it/s, loss=0.873, v_num=12]
Epoch 0:  42%|████▏     | 395/938 [00:28<00:39, 13.75it/s, loss=0.873, v_num=12]
Epoch 0:  42%|████▏     | 395/938 [00:28<00:39, 13.75it/s, loss=0.859, v_num=12]
Epoch 0:  42%|████▏     | 396/938 [00:28<00:39, 13.76it/s, loss=0.845, v_num=12]
Epoch 0:  42%|████▏     | 397/938 [00:28<00:39, 13.76it/s, loss=0.845, v_num=12]
Epoch 0:  42%|████▏     | 397/938 [00:28<00:39, 13.76it/s, loss=0.852, v_num=12]
Epoch 0:  42%|████▏     | 398/938 [00:28<00:39, 13.76it/s, loss=0.859, v_num=12]
Epoch 0:  43%|████▎     | 399/938 [00:29<00:39, 13.76it/s, loss=0.859, v_num=12]
Epoch 0:  43%|████▎     | 399/938 [00:29<00:39, 13.76it/s, loss=0.863, v_num=12]
Epoch 0:  43%|████▎     | 400/938 [00:29<00:39, 13.76it/s, loss=0.862, v_num=12]
Epoch 0:  43%|████▎     | 401/938 [00:29<00:39, 13.75it/s, loss=0.862, v_num=12]
Epoch 0:  43%|████▎     | 401/938 [00:29<00:39, 13.75it/s, loss=0.865, v_num=12]
Epoch 0:  43%|████▎     | 402/938 [00:29<00:38, 13.75it/s, loss=0.87, v_num=12] 
Epoch 0:  43%|████▎     | 403/938 [00:29<00:38, 13.75it/s, loss=0.87, v_num=12]
Epoch 0:  43%|████▎     | 403/938 [00:29<00:38, 13.75it/s, loss=0.87, v_num=12]
Epoch 0:  43%|████▎     | 404/938 [00:29<00:38, 13.76it/s, loss=0.873, v_num=12]
Epoch 0:  43%|████▎     | 405/938 [00:29<00:38, 13.76it/s, loss=0.873, v_num=12]
Epoch 0:  43%|████▎     | 405/938 [00:29<00:38, 13.76it/s, loss=0.844, v_num=12]
Epoch 0:  43%|████▎     | 406/938 [00:29<00:38, 13.76it/s, loss=0.845, v_num=12]
Epoch 0:  43%|████▎     | 407/938 [00:29<00:38, 13.76it/s, loss=0.845, v_num=12]
Epoch 0:  43%|████▎     | 407/938 [00:29<00:38, 13.76it/s, loss=0.852, v_num=12]
Epoch 0:  43%|████▎     | 408/938 [00:29<00:38, 13.76it/s, loss=0.849, v_num=12]
Epoch 0:  44%|████▎     | 409/938 [00:29<00:38, 13.76it/s, loss=0.849, v_num=12]
Epoch 0:  44%|████▎     | 409/938 [00:29<00:38, 13.76it/s, loss=0.851, v_num=12]
Epoch 0:  44%|████▎     | 410/938 [00:29<00:38, 13.76it/s, loss=0.854, v_num=12]
Epoch 0:  44%|████▍     | 411/938 [00:29<00:38, 13.75it/s, loss=0.854, v_num=12]
Epoch 0:  44%|████▍     | 411/938 [00:29<00:38, 13.75it/s, loss=0.857, v_num=12]
Epoch 0:  44%|████▍     | 412/938 [00:29<00:38, 13.74it/s, loss=0.843, v_num=12]
Epoch 0:  44%|████▍     | 413/938 [00:30<00:38, 13.74it/s, loss=0.843, v_num=12]
Epoch 0:  44%|████▍     | 413/938 [00:30<00:38, 13.74it/s, loss=0.843, v_num=12]
Epoch 0:  44%|████▍     | 414/938 [00:30<00:38, 13.74it/s, loss=0.846, v_num=12]
Epoch 0:  44%|████▍     | 415/938 [00:30<00:38, 13.74it/s, loss=0.846, v_num=12]
Epoch 0:  44%|████▍     | 415/938 [00:30<00:38, 13.74it/s, loss=0.857, v_num=12]
Epoch 0:  44%|████▍     | 416/938 [00:30<00:37, 13.75it/s, loss=0.856, v_num=12]
Epoch 0:  44%|████▍     | 417/938 [00:30<00:37, 13.75it/s, loss=0.856, v_num=12]
Epoch 0:  44%|████▍     | 417/938 [00:30<00:37, 13.75it/s, loss=0.85, v_num=12] 
Epoch 0:  45%|████▍     | 418/938 [00:30<00:37, 13.75it/s, loss=0.842, v_num=12]
Epoch 0:  45%|████▍     | 419/938 [00:30<00:37, 13.75it/s, loss=0.842, v_num=12]
Epoch 0:  45%|████▍     | 419/938 [00:30<00:37, 13.75it/s, loss=0.833, v_num=12]
Epoch 0:  45%|████▍     | 420/938 [00:30<00:37, 13.75it/s, loss=0.831, v_num=12]
Epoch 0:  45%|████▍     | 421/938 [00:30<00:37, 13.75it/s, loss=0.831, v_num=12]
Epoch 0:  45%|████▍     | 421/938 [00:30<00:37, 13.75it/s, loss=0.829, v_num=12]
Epoch 0:  45%|████▍     | 422/938 [00:30<00:37, 13.75it/s, loss=0.814, v_num=12]
Epoch 0:  45%|████▌     | 423/938 [00:30<00:37, 13.75it/s, loss=0.814, v_num=12]
Epoch 0:  45%|████▌     | 423/938 [00:30<00:37, 13.75it/s, loss=0.812, v_num=12]
Epoch 0:  45%|████▌     | 424/938 [00:30<00:37, 13.75it/s, loss=0.811, v_num=12]
Epoch 0:  45%|████▌     | 425/938 [00:30<00:37, 13.74it/s, loss=0.811, v_num=12]
Epoch 0:  45%|████▌     | 425/938 [00:30<00:37, 13.74it/s, loss=0.82, v_num=12] 
Epoch 0:  45%|████▌     | 426/938 [00:30<00:37, 13.74it/s, loss=0.825, v_num=12]
Epoch 0:  46%|████▌     | 427/938 [00:31<00:37, 13.75it/s, loss=0.825, v_num=12]
Epoch 0:  46%|████▌     | 427/938 [00:31<00:37, 13.75it/s, loss=0.82, v_num=12] 
Epoch 0:  46%|████▌     | 428/938 [00:31<00:37, 13.74it/s, loss=0.81, v_num=12]
Epoch 0:  46%|████▌     | 429/938 [00:31<00:37, 13.73it/s, loss=0.81, v_num=12]
Epoch 0:  46%|████▌     | 429/938 [00:31<00:37, 13.73it/s, loss=0.812, v_num=12]
Epoch 0:  46%|████▌     | 430/938 [00:31<00:36, 13.73it/s, loss=0.811, v_num=12]
Epoch 0:  46%|████▌     | 431/938 [00:31<00:36, 13.74it/s, loss=0.811, v_num=12]
Epoch 0:  46%|████▌     | 431/938 [00:31<00:36, 13.74it/s, loss=0.808, v_num=12]
Epoch 0:  46%|████▌     | 432/938 [00:31<00:36, 13.73it/s, loss=0.817, v_num=12]
Epoch 0:  46%|████▌     | 433/938 [00:31<00:36, 13.73it/s, loss=0.817, v_num=12]
Epoch 0:  46%|████▌     | 433/938 [00:31<00:36, 13.73it/s, loss=0.824, v_num=12]
Epoch 0:  46%|████▋     | 434/938 [00:31<00:36, 13.72it/s, loss=0.818, v_num=12]
Epoch 0:  46%|████▋     | 435/938 [00:31<00:36, 13.73it/s, loss=0.818, v_num=12]
Epoch 0:  46%|████▋     | 435/938 [00:31<00:36, 13.73it/s, loss=0.812, v_num=12]
Epoch 0:  46%|████▋     | 436/938 [00:31<00:36, 13.72it/s, loss=0.808, v_num=12]
Epoch 0:  47%|████▋     | 437/938 [00:31<00:36, 13.73it/s, loss=0.808, v_num=12]
Epoch 0:  47%|████▋     | 437/938 [00:31<00:36, 13.73it/s, loss=0.814, v_num=12]
Epoch 0:  47%|████▋     | 438/938 [00:31<00:36, 13.73it/s, loss=0.805, v_num=12]
Epoch 0:  47%|████▋     | 439/938 [00:31<00:36, 13.73it/s, loss=0.805, v_num=12]
Epoch 0:  47%|████▋     | 439/938 [00:31<00:36, 13.73it/s, loss=0.802, v_num=12]
Epoch 0:  47%|████▋     | 440/938 [00:32<00:36, 13.73it/s, loss=0.798, v_num=12]
Epoch 0:  47%|████▋     | 441/938 [00:32<00:36, 13.74it/s, loss=0.798, v_num=12]
Epoch 0:  47%|████▋     | 441/938 [00:32<00:36, 13.73it/s, loss=0.797, v_num=12]
Epoch 0:  47%|████▋     | 442/938 [00:32<00:36, 13.73it/s, loss=0.809, v_num=12]
Epoch 0:  47%|████▋     | 443/938 [00:32<00:36, 13.74it/s, loss=0.809, v_num=12]
Epoch 0:  47%|████▋     | 443/938 [00:32<00:36, 13.74it/s, loss=0.809, v_num=12]
Epoch 0:  47%|████▋     | 444/938 [00:32<00:35, 13.74it/s, loss=0.821, v_num=12]
Epoch 0:  47%|████▋     | 445/938 [00:32<00:35, 13.73it/s, loss=0.821, v_num=12]
Epoch 0:  47%|████▋     | 445/938 [00:32<00:35, 13.73it/s, loss=0.812, v_num=12]
Epoch 0:  48%|████▊     | 446/938 [00:32<00:35, 13.73it/s, loss=0.802, v_num=12]
Epoch 0:  48%|████▊     | 447/938 [00:32<00:35, 13.74it/s, loss=0.802, v_num=12]
Epoch 0:  48%|████▊     | 447/938 [00:32<00:35, 13.74it/s, loss=0.794, v_num=12]
Epoch 0:  48%|████▊     | 448/938 [00:32<00:35, 13.74it/s, loss=0.795, v_num=12]
Epoch 0:  48%|████▊     | 449/938 [00:32<00:35, 13.74it/s, loss=0.795, v_num=12]
Epoch 0:  48%|████▊     | 449/938 [00:32<00:35, 13.74it/s, loss=0.791, v_num=12]
Epoch 0:  48%|████▊     | 450/938 [00:32<00:35, 13.74it/s, loss=0.794, v_num=12]
Epoch 0:  48%|████▊     | 451/938 [00:32<00:35, 13.74it/s, loss=0.794, v_num=12]
Epoch 0:  48%|████▊     | 451/938 [00:32<00:35, 13.73it/s, loss=0.8, v_num=12]  
Epoch 0:  48%|████▊     | 452/938 [00:32<00:35, 13.74it/s, loss=0.8, v_num=12]
Epoch 0:  48%|████▊     | 453/938 [00:32<00:35, 13.74it/s, loss=0.8, v_num=12]
Epoch 0:  48%|████▊     | 453/938 [00:32<00:35, 13.74it/s, loss=0.801, v_num=12]
Epoch 0:  48%|████▊     | 454/938 [00:33<00:35, 13.75it/s, loss=0.805, v_num=12]
Epoch 0:  49%|████▊     | 455/938 [00:33<00:35, 13.74it/s, loss=0.805, v_num=12]
Epoch 0:  49%|████▊     | 455/938 [00:33<00:35, 13.73it/s, loss=0.81, v_num=12] 
Epoch 0:  49%|████▊     | 456/938 [00:33<00:35, 13.74it/s, loss=0.826, v_num=12]
Epoch 0:  49%|████▊     | 457/938 [00:33<00:35, 13.74it/s, loss=0.826, v_num=12]
Epoch 0:  49%|████▊     | 457/938 [00:33<00:35, 13.74it/s, loss=0.827, v_num=12]
Epoch 0:  49%|████▉     | 458/938 [00:33<00:34, 13.75it/s, loss=0.837, v_num=12]
Epoch 0:  49%|████▉     | 459/938 [00:33<00:34, 13.75it/s, loss=0.837, v_num=12]
Epoch 0:  49%|████▉     | 459/938 [00:33<00:34, 13.75it/s, loss=0.848, v_num=12]
Epoch 0:  49%|████▉     | 460/938 [00:33<00:34, 13.75it/s, loss=0.84, v_num=12] 
Epoch 0:  49%|████▉     | 461/938 [00:33<00:34, 13.75it/s, loss=0.84, v_num=12]
Epoch 0:  49%|████▉     | 461/938 [00:33<00:34, 13.75it/s, loss=0.849, v_num=12]
Epoch 0:  49%|████▉     | 462/938 [00:33<00:34, 13.75it/s, loss=0.851, v_num=12]
Epoch 0:  49%|████▉     | 463/938 [00:33<00:34, 13.76it/s, loss=0.851, v_num=12]
Epoch 0:  49%|████▉     | 463/938 [00:33<00:34, 13.76it/s, loss=0.858, v_num=12]
Epoch 0:  49%|████▉     | 464/938 [00:33<00:34, 13.73it/s, loss=0.858, v_num=12]
Epoch 0:  50%|████▉     | 465/938 [00:33<00:34, 13.73it/s, loss=0.858, v_num=12]
Epoch 0:  50%|████▉     | 465/938 [00:33<00:34, 13.73it/s, loss=0.862, v_num=12]
Epoch 0:  50%|████▉     | 466/938 [00:33<00:34, 13.73it/s, loss=0.869, v_num=12]
Epoch 0:  50%|████▉     | 467/938 [00:34<00:34, 13.73it/s, loss=0.869, v_num=12]
Epoch 0:  50%|████▉     | 467/938 [00:34<00:34, 13.73it/s, loss=0.879, v_num=12]
Epoch 0:  50%|████▉     | 468/938 [00:34<00:34, 13.73it/s, loss=0.883, v_num=12]
Epoch 0:  50%|█████     | 469/938 [00:34<00:34, 13.74it/s, loss=0.883, v_num=12]
Epoch 0:  50%|█████     | 469/938 [00:34<00:34, 13.74it/s, loss=0.883, v_num=12]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]

Validating:   0%|          | 2/469 [00:00<00:24, 18.75it/s]
Epoch 0:  50%|█████     | 472/938 [00:34<00:33, 13.79it/s, loss=0.883, v_num=12]

Validating:   1%|          | 5/469 [00:00<00:23, 19.60it/s]
Epoch 0:  51%|█████     | 475/938 [00:34<00:33, 13.81it/s, loss=0.883, v_num=12]

Validating:   2%|▏         | 8/469 [00:00<00:22, 20.30it/s]
Epoch 0:  51%|█████     | 478/938 [00:34<00:33, 13.84it/s, loss=0.883, v_num=12]

Validating:   2%|▏         | 11/469 [00:00<00:20, 22.57it/s]
Epoch 0:  51%|█████▏    | 481/938 [00:34<00:32, 13.89it/s, loss=0.883, v_num=12]

Validating:   3%|▎         | 14/469 [00:00<00:18, 24.06it/s]
Epoch 0:  52%|█████▏    | 484/938 [00:34<00:32, 13.93it/s, loss=0.883, v_num=12]

Validating:   4%|▎         | 17/469 [00:00<00:19, 23.33it/s]
Epoch 0:  52%|█████▏    | 487/938 [00:34<00:32, 13.96it/s, loss=0.883, v_num=12]

Validating:   4%|▍         | 20/469 [00:00<00:18, 24.11it/s]
Epoch 0:  52%|█████▏    | 490/938 [00:35<00:32, 14.00it/s, loss=0.883, v_num=12]

Validating:   5%|▍         | 23/469 [00:00<00:18, 24.15it/s]
Epoch 0:  53%|█████▎    | 493/938 [00:35<00:31, 14.03it/s, loss=0.883, v_num=12]

Validating:   6%|▌         | 26/469 [00:01<00:17, 25.00it/s]
Epoch 0:  53%|█████▎    | 496/938 [00:35<00:31, 14.08it/s, loss=0.883, v_num=12]

Validating:   6%|▌         | 29/469 [00:01<00:18, 23.48it/s]
Epoch 0:  53%|█████▎    | 499/938 [00:35<00:31, 14.10it/s, loss=0.883, v_num=12]

Validating:   7%|▋         | 32/469 [00:01<00:18, 23.88it/s]
Epoch 0:  54%|█████▎    | 502/938 [00:35<00:30, 14.14it/s, loss=0.883, v_num=12]

Validating:   7%|▋         | 35/469 [00:01<00:17, 24.55it/s]
Epoch 0:  54%|█████▍    | 505/938 [00:35<00:30, 14.18it/s, loss=0.883, v_num=12]

Validating:   8%|▊         | 38/469 [00:01<00:17, 25.20it/s]
Epoch 0:  54%|█████▍    | 508/938 [00:35<00:30, 14.22it/s, loss=0.883, v_num=12]

Validating:   9%|▊         | 41/469 [00:01<00:16, 25.35it/s]
Epoch 0:  54%|█████▍    | 511/938 [00:35<00:29, 14.26it/s, loss=0.883, v_num=12]

Validating:   9%|▉         | 44/469 [00:01<00:17, 24.96it/s]
Epoch 0:  55%|█████▍    | 514/938 [00:35<00:29, 14.29it/s, loss=0.883, v_num=12]

Validating:  10%|█         | 47/469 [00:01<00:17, 24.15it/s]
Epoch 0:  55%|█████▌    | 517/938 [00:36<00:29, 14.32it/s, loss=0.883, v_num=12]

Validating:  11%|█         | 50/469 [00:02<00:16, 24.94it/s]
Epoch 0:  55%|█████▌    | 520/938 [00:36<00:29, 14.36it/s, loss=0.883, v_num=12]

Validating:  11%|█▏        | 53/469 [00:02<00:17, 24.44it/s]
Epoch 0:  56%|█████▌    | 523/938 [00:36<00:28, 14.39it/s, loss=0.883, v_num=12]

Validating:  12%|█▏        | 56/469 [00:02<00:16, 24.38it/s]
Epoch 0:  56%|█████▌    | 526/938 [00:36<00:28, 14.42it/s, loss=0.883, v_num=12]

Validating:  13%|█▎        | 59/469 [00:02<00:17, 23.66it/s]
Epoch 0:  56%|█████▋    | 529/938 [00:36<00:28, 14.45it/s, loss=0.883, v_num=12]

Validating:  13%|█▎        | 62/469 [00:02<00:17, 23.59it/s]
Epoch 0:  57%|█████▋    | 532/938 [00:36<00:28, 14.48it/s, loss=0.883, v_num=12]

Validating:  14%|█▍        | 65/469 [00:02<00:16, 24.01it/s]
Epoch 0:  57%|█████▋    | 535/938 [00:36<00:27, 14.52it/s, loss=0.883, v_num=12]

Validating:  14%|█▍        | 68/469 [00:02<00:16, 24.23it/s]
Epoch 0:  57%|█████▋    | 538/938 [00:36<00:27, 14.55it/s, loss=0.883, v_num=12]

Validating:  15%|█▌        | 71/469 [00:02<00:16, 24.30it/s]
Epoch 0:  58%|█████▊    | 541/938 [00:37<00:27, 14.58it/s, loss=0.883, v_num=12]

Validating:  16%|█▌        | 74/469 [00:03<00:15, 25.39it/s]
Epoch 0:  58%|█████▊    | 544/938 [00:37<00:26, 14.62it/s, loss=0.883, v_num=12]

Validating:  16%|█▋        | 77/469 [00:03<00:15, 25.42it/s]
Epoch 0:  58%|█████▊    | 547/938 [00:37<00:26, 14.66it/s, loss=0.883, v_num=12]

Validating:  17%|█▋        | 80/469 [00:03<00:15, 24.55it/s]
Epoch 0:  59%|█████▊    | 550/938 [00:37<00:26, 14.69it/s, loss=0.883, v_num=12]

Validating:  18%|█▊        | 83/469 [00:03<00:15, 24.75it/s]
Epoch 0:  59%|█████▉    | 553/938 [00:37<00:26, 14.72it/s, loss=0.883, v_num=12]

Validating:  18%|█▊        | 86/469 [00:03<00:15, 25.34it/s]
Epoch 0:  59%|█████▉    | 556/938 [00:37<00:25, 14.76it/s, loss=0.883, v_num=12]

Validating:  19%|█▉        | 89/469 [00:03<00:14, 25.98it/s]
Epoch 0:  60%|█████▉    | 559/938 [00:37<00:25, 14.79it/s, loss=0.883, v_num=12]

Validating:  20%|█▉        | 92/469 [00:03<00:17, 22.05it/s]
Epoch 0:  60%|█████▉    | 562/938 [00:37<00:25, 14.80it/s, loss=0.883, v_num=12]

Validating:  20%|██        | 95/469 [00:03<00:17, 21.90it/s]
Epoch 0:  60%|██████    | 565/938 [00:38<00:25, 14.82it/s, loss=0.883, v_num=12]

Validating:  21%|██        | 98/469 [00:04<00:16, 23.01it/s]
Epoch 0:  61%|██████    | 568/938 [00:38<00:24, 14.86it/s, loss=0.883, v_num=12]

Validating:  22%|██▏       | 101/469 [00:04<00:16, 22.94it/s]
Epoch 0:  61%|██████    | 571/938 [00:38<00:24, 14.89it/s, loss=0.883, v_num=12]

Validating:  22%|██▏       | 104/469 [00:04<00:15, 23.83it/s]
Epoch 0:  61%|██████    | 574/938 [00:38<00:24, 14.92it/s, loss=0.883, v_num=12]

Validating:  23%|██▎       | 107/469 [00:04<00:14, 24.50it/s]
Epoch 0:  62%|██████▏   | 577/938 [00:38<00:24, 14.95it/s, loss=0.883, v_num=12]

Validating:  23%|██▎       | 110/469 [00:04<00:14, 25.34it/s]
Epoch 0:  62%|██████▏   | 580/938 [00:38<00:23, 14.99it/s, loss=0.883, v_num=12]

Validating:  24%|██▍       | 113/469 [00:04<00:13, 25.49it/s]
Epoch 0:  62%|██████▏   | 583/938 [00:38<00:23, 15.02it/s, loss=0.883, v_num=12]

Validating:  25%|██▍       | 116/469 [00:04<00:14, 24.66it/s]
Epoch 0:  62%|██████▏   | 586/938 [00:38<00:23, 15.05it/s, loss=0.883, v_num=12]

Validating:  25%|██▌       | 119/469 [00:04<00:14, 23.47it/s]
Epoch 0:  63%|██████▎   | 589/938 [00:39<00:23, 15.07it/s, loss=0.883, v_num=12]

Validating:  26%|██▌       | 122/469 [00:05<00:14, 24.52it/s]
Epoch 0:  63%|██████▎   | 592/938 [00:39<00:22, 15.10it/s, loss=0.883, v_num=12]

Validating:  27%|██▋       | 125/469 [00:05<00:13, 24.70it/s]
Epoch 0:  63%|██████▎   | 595/938 [00:39<00:22, 15.13it/s, loss=0.883, v_num=12]

Validating:  27%|██▋       | 128/469 [00:05<00:13, 24.44it/s]
Epoch 0:  64%|██████▍   | 598/938 [00:39<00:22, 15.16it/s, loss=0.883, v_num=12]

Validating:  28%|██▊       | 131/469 [00:05<00:14, 24.07it/s]
Epoch 0:  64%|██████▍   | 601/938 [00:39<00:22, 15.19it/s, loss=0.883, v_num=12]

Validating:  29%|██▊       | 134/469 [00:05<00:14, 23.34it/s]
Epoch 0:  64%|██████▍   | 604/938 [00:39<00:21, 15.21it/s, loss=0.883, v_num=12]

Validating:  29%|██▉       | 137/469 [00:05<00:13, 23.72it/s]
Epoch 0:  65%|██████▍   | 607/938 [00:39<00:21, 15.24it/s, loss=0.883, v_num=12]

Validating:  30%|██▉       | 140/469 [00:05<00:13, 24.25it/s]
Epoch 0:  65%|██████▌   | 610/938 [00:39<00:21, 15.27it/s, loss=0.883, v_num=12]

Validating:  30%|███       | 143/469 [00:05<00:13, 24.10it/s]
Epoch 0:  65%|██████▌   | 613/938 [00:40<00:21, 15.30it/s, loss=0.883, v_num=12]

Validating:  31%|███       | 146/469 [00:06<00:13, 24.19it/s]
Epoch 0:  66%|██████▌   | 616/938 [00:40<00:21, 15.32it/s, loss=0.883, v_num=12]

Validating:  32%|███▏      | 149/469 [00:06<00:13, 24.23it/s]
Epoch 0:  66%|██████▌   | 619/938 [00:40<00:20, 15.35it/s, loss=0.883, v_num=12]

Validating:  32%|███▏      | 152/469 [00:06<00:13, 23.71it/s]
Epoch 0:  66%|██████▋   | 622/938 [00:40<00:20, 15.38it/s, loss=0.883, v_num=12]

Validating:  33%|███▎      | 155/469 [00:06<00:13, 24.13it/s]
Epoch 0:  67%|██████▋   | 625/938 [00:40<00:20, 15.40it/s, loss=0.883, v_num=12]

Validating:  34%|███▎      | 158/469 [00:06<00:13, 23.57it/s]
Epoch 0:  67%|██████▋   | 628/938 [00:40<00:20, 15.43it/s, loss=0.883, v_num=12]

Validating:  34%|███▍      | 161/469 [00:06<00:12, 24.47it/s]
Epoch 0:  67%|██████▋   | 631/938 [00:40<00:19, 15.46it/s, loss=0.883, v_num=12]

Validating:  35%|███▍      | 164/469 [00:06<00:12, 24.77it/s]
Epoch 0:  68%|██████▊   | 634/938 [00:40<00:19, 15.49it/s, loss=0.883, v_num=12]

Validating:  36%|███▌      | 167/469 [00:06<00:12, 24.75it/s]
Epoch 0:  68%|██████▊   | 637/938 [00:41<00:19, 15.52it/s, loss=0.883, v_num=12]

Validating:  36%|███▌      | 170/469 [00:07<00:11, 24.93it/s]
Epoch 0:  68%|██████▊   | 640/938 [00:41<00:19, 15.54it/s, loss=0.883, v_num=12]

Validating:  37%|███▋      | 173/469 [00:07<00:11, 25.27it/s]
Epoch 0:  69%|██████▊   | 643/938 [00:41<00:18, 15.57it/s, loss=0.883, v_num=12]

Validating:  38%|███▊      | 176/469 [00:07<00:11, 24.77it/s]
Epoch 0:  69%|██████▉   | 646/938 [00:41<00:18, 15.60it/s, loss=0.883, v_num=12]

Validating:  38%|███▊      | 179/469 [00:07<00:12, 23.69it/s]
Epoch 0:  69%|██████▉   | 649/938 [00:41<00:18, 15.62it/s, loss=0.883, v_num=12]

Validating:  39%|███▉      | 182/469 [00:07<00:11, 23.97it/s]
Epoch 0:  70%|██████▉   | 652/938 [00:41<00:18, 15.64it/s, loss=0.883, v_num=12]

Validating:  39%|███▉      | 185/469 [00:07<00:11, 24.66it/s]
Epoch 0:  70%|██████▉   | 655/938 [00:41<00:18, 15.67it/s, loss=0.883, v_num=12]

Validating:  40%|████      | 188/469 [00:07<00:11, 25.24it/s]
Epoch 0:  70%|███████   | 658/938 [00:41<00:17, 15.70it/s, loss=0.883, v_num=12]

Validating:  41%|████      | 191/469 [00:07<00:10, 25.73it/s]
Epoch 0:  70%|███████   | 661/938 [00:42<00:17, 15.73it/s, loss=0.883, v_num=12]

Validating:  41%|████▏     | 194/469 [00:08<00:10, 25.69it/s]
Epoch 0:  71%|███████   | 664/938 [00:42<00:17, 15.76it/s, loss=0.883, v_num=12]

Validating:  42%|████▏     | 197/469 [00:08<00:11, 24.55it/s]
Epoch 0:  71%|███████   | 667/938 [00:42<00:17, 15.78it/s, loss=0.883, v_num=12]

Validating:  43%|████▎     | 200/469 [00:08<00:11, 24.33it/s]
Epoch 0:  71%|███████▏  | 670/938 [00:42<00:16, 15.80it/s, loss=0.883, v_num=12]

Validating:  43%|████▎     | 203/469 [00:08<00:10, 24.29it/s]
Epoch 0:  72%|███████▏  | 673/938 [00:42<00:16, 15.83it/s, loss=0.883, v_num=12]

Validating:  44%|████▍     | 206/469 [00:08<00:10, 24.61it/s]
Epoch 0:  72%|███████▏  | 676/938 [00:42<00:16, 15.86it/s, loss=0.883, v_num=12]

Validating:  45%|████▍     | 209/469 [00:08<00:10, 24.96it/s]
Epoch 0:  72%|███████▏  | 679/938 [00:42<00:16, 15.88it/s, loss=0.883, v_num=12]

Validating:  45%|████▌     | 212/469 [00:08<00:10, 24.92it/s]
Epoch 0:  73%|███████▎  | 682/938 [00:42<00:16, 15.91it/s, loss=0.883, v_num=12]

Validating:  46%|████▌     | 215/469 [00:08<00:10, 24.96it/s]
Epoch 0:  73%|███████▎  | 685/938 [00:42<00:15, 15.93it/s, loss=0.883, v_num=12]

Validating:  46%|████▋     | 218/469 [00:08<00:09, 25.19it/s]
Epoch 0:  73%|███████▎  | 688/938 [00:43<00:15, 15.96it/s, loss=0.883, v_num=12]

Validating:  47%|████▋     | 221/469 [00:09<00:09, 25.33it/s]
Epoch 0:  74%|███████▎  | 691/938 [00:43<00:15, 15.99it/s, loss=0.883, v_num=12]

Validating:  48%|████▊     | 224/469 [00:09<00:09, 25.29it/s]
Epoch 0:  74%|███████▍  | 694/938 [00:43<00:15, 16.01it/s, loss=0.883, v_num=12]

Validating:  48%|████▊     | 227/469 [00:09<00:09, 24.74it/s]
Epoch 0:  74%|███████▍  | 697/938 [00:43<00:15, 16.03it/s, loss=0.883, v_num=12]

Validating:  49%|████▉     | 230/469 [00:09<00:09, 24.10it/s]
Epoch 0:  75%|███████▍  | 700/938 [00:43<00:14, 16.05it/s, loss=0.883, v_num=12]

Validating:  50%|████▉     | 233/469 [00:09<00:09, 24.52it/s]
Epoch 0:  75%|███████▍  | 703/938 [00:43<00:14, 16.08it/s, loss=0.883, v_num=12]

Validating:  50%|█████     | 236/469 [00:09<00:09, 25.31it/s]
Epoch 0:  75%|███████▌  | 706/938 [00:43<00:14, 16.11it/s, loss=0.883, v_num=12]

Validating:  51%|█████     | 239/469 [00:09<00:09, 23.93it/s]
Epoch 0:  76%|███████▌  | 709/938 [00:43<00:14, 16.12it/s, loss=0.883, v_num=12]

Validating:  52%|█████▏    | 242/469 [00:09<00:09, 24.92it/s]
Epoch 0:  76%|███████▌  | 712/938 [00:44<00:13, 16.15it/s, loss=0.883, v_num=12]

Validating:  52%|█████▏    | 245/469 [00:10<00:09, 24.06it/s]
Epoch 0:  76%|███████▌  | 715/938 [00:44<00:13, 16.17it/s, loss=0.883, v_num=12]

Validating:  53%|█████▎    | 248/469 [00:10<00:09, 24.28it/s]
Epoch 0:  77%|███████▋  | 718/938 [00:44<00:13, 16.19it/s, loss=0.883, v_num=12]

Validating:  54%|█████▎    | 251/469 [00:10<00:08, 25.60it/s]
Epoch 0:  77%|███████▋  | 721/938 [00:44<00:13, 16.22it/s, loss=0.883, v_num=12]

Validating:  54%|█████▍    | 254/469 [00:10<00:08, 26.16it/s]
Epoch 0:  77%|███████▋  | 724/938 [00:44<00:13, 16.25it/s, loss=0.883, v_num=12]

Validating:  55%|█████▍    | 257/469 [00:10<00:08, 25.75it/s]
Epoch 0:  78%|███████▊  | 727/938 [00:44<00:12, 16.28it/s, loss=0.883, v_num=12]

Validating:  55%|█████▌    | 260/469 [00:10<00:08, 24.80it/s]
Epoch 0:  78%|███████▊  | 730/938 [00:44<00:12, 16.29it/s, loss=0.883, v_num=12]

Validating:  56%|█████▌    | 263/469 [00:10<00:08, 23.63it/s]
Epoch 0:  78%|███████▊  | 733/938 [00:44<00:12, 16.31it/s, loss=0.883, v_num=12]

Validating:  57%|█████▋    | 266/469 [00:10<00:08, 24.54it/s]
Epoch 0:  78%|███████▊  | 736/938 [00:45<00:12, 16.34it/s, loss=0.883, v_num=12]

Validating:  57%|█████▋    | 269/469 [00:11<00:08, 24.70it/s]
Epoch 0:  79%|███████▉  | 739/938 [00:45<00:12, 16.36it/s, loss=0.883, v_num=12]

Validating:  58%|█████▊    | 272/469 [00:11<00:07, 25.78it/s]
Epoch 0:  79%|███████▉  | 742/938 [00:45<00:11, 16.39it/s, loss=0.883, v_num=12]

Validating:  59%|█████▊    | 275/469 [00:11<00:07, 25.50it/s]
Epoch 0:  79%|███████▉  | 745/938 [00:45<00:11, 16.41it/s, loss=0.883, v_num=12]

Validating:  59%|█████▉    | 278/469 [00:11<00:07, 25.68it/s]
Epoch 0:  80%|███████▉  | 748/938 [00:45<00:11, 16.44it/s, loss=0.883, v_num=12]

Validating:  60%|█████▉    | 281/469 [00:11<00:07, 25.64it/s]
Epoch 0:  80%|████████  | 751/938 [00:45<00:11, 16.46it/s, loss=0.883, v_num=12]

Validating:  61%|██████    | 284/469 [00:11<00:07, 25.83it/s]
Epoch 0:  80%|████████  | 754/938 [00:45<00:11, 16.48it/s, loss=0.883, v_num=12]

Validating:  61%|██████    | 287/469 [00:11<00:07, 26.00it/s]
Epoch 0:  81%|████████  | 757/938 [00:45<00:10, 16.51it/s, loss=0.883, v_num=12]

Validating:  62%|██████▏   | 290/469 [00:11<00:07, 25.14it/s]
Epoch 0:  81%|████████  | 760/938 [00:45<00:10, 16.53it/s, loss=0.883, v_num=12]

Validating:  62%|██████▏   | 293/469 [00:11<00:06, 26.07it/s]
Epoch 0:  81%|████████▏ | 763/938 [00:46<00:10, 16.55it/s, loss=0.883, v_num=12]

Validating:  63%|██████▎   | 296/469 [00:12<00:06, 25.66it/s]
Epoch 0:  82%|████████▏ | 766/938 [00:46<00:10, 16.58it/s, loss=0.883, v_num=12]

Validating:  64%|██████▍   | 299/469 [00:12<00:06, 25.36it/s]
Epoch 0:  82%|████████▏ | 769/938 [00:46<00:10, 16.60it/s, loss=0.883, v_num=12]

Validating:  64%|██████▍   | 302/469 [00:12<00:06, 25.83it/s]
Epoch 0:  82%|████████▏ | 772/938 [00:46<00:09, 16.62it/s, loss=0.883, v_num=12]

Validating:  65%|██████▌   | 305/469 [00:12<00:06, 25.57it/s]
Epoch 0:  83%|████████▎ | 775/938 [00:46<00:09, 16.64it/s, loss=0.883, v_num=12]

Validating:  66%|██████▌   | 308/469 [00:12<00:06, 25.56it/s]
Epoch 0:  83%|████████▎ | 778/938 [00:46<00:09, 16.67it/s, loss=0.883, v_num=12]

Validating:  66%|██████▋   | 311/469 [00:12<00:06, 25.31it/s]
Epoch 0:  83%|████████▎ | 781/938 [00:46<00:09, 16.69it/s, loss=0.883, v_num=12]

Validating:  67%|██████▋   | 314/469 [00:12<00:06, 24.68it/s]
Epoch 0:  84%|████████▎ | 784/938 [00:46<00:09, 16.71it/s, loss=0.883, v_num=12]

Validating:  68%|██████▊   | 317/469 [00:12<00:06, 25.32it/s]
Epoch 0:  84%|████████▍ | 787/938 [00:47<00:09, 16.73it/s, loss=0.883, v_num=12]

Validating:  68%|██████▊   | 320/469 [00:13<00:05, 24.91it/s]
Epoch 0:  84%|████████▍ | 790/938 [00:47<00:08, 16.75it/s, loss=0.883, v_num=12]

Validating:  69%|██████▉   | 323/469 [00:13<00:05, 25.13it/s]
Epoch 0:  85%|████████▍ | 793/938 [00:47<00:08, 16.77it/s, loss=0.883, v_num=12]

Validating:  70%|██████▉   | 326/469 [00:13<00:05, 26.20it/s]
Epoch 0:  85%|████████▍ | 796/938 [00:47<00:08, 16.80it/s, loss=0.883, v_num=12]

Validating:  70%|███████   | 329/469 [00:13<00:05, 25.02it/s]
Epoch 0:  85%|████████▌ | 799/938 [00:47<00:08, 16.81it/s, loss=0.883, v_num=12]

Validating:  71%|███████   | 332/469 [00:13<00:05, 24.41it/s]
Epoch 0:  86%|████████▌ | 802/938 [00:47<00:08, 16.83it/s, loss=0.883, v_num=12]

Validating:  71%|███████▏  | 335/469 [00:13<00:05, 24.37it/s]
Epoch 0:  86%|████████▌ | 805/938 [00:47<00:07, 16.85it/s, loss=0.883, v_num=12]

Validating:  72%|███████▏  | 338/469 [00:13<00:05, 24.30it/s]
Epoch 0:  86%|████████▌ | 808/938 [00:47<00:07, 16.87it/s, loss=0.883, v_num=12]

Validating:  73%|███████▎  | 341/469 [00:13<00:05, 24.71it/s]
Epoch 0:  86%|████████▋ | 811/938 [00:48<00:07, 16.89it/s, loss=0.883, v_num=12]

Validating:  73%|███████▎  | 344/469 [00:14<00:05, 24.68it/s]
Epoch 0:  87%|████████▋ | 814/938 [00:48<00:07, 16.91it/s, loss=0.883, v_num=12]

Validating:  74%|███████▍  | 347/469 [00:14<00:04, 24.96it/s]
Epoch 0:  87%|████████▋ | 817/938 [00:48<00:07, 16.93it/s, loss=0.883, v_num=12]

Validating:  75%|███████▍  | 350/469 [00:14<00:04, 25.88it/s]
Epoch 0:  87%|████████▋ | 820/938 [00:48<00:06, 16.96it/s, loss=0.883, v_num=12]

Validating:  75%|███████▌  | 353/469 [00:14<00:04, 25.83it/s]
Epoch 0:  88%|████████▊ | 823/938 [00:48<00:06, 16.98it/s, loss=0.883, v_num=12]

Validating:  76%|███████▌  | 356/469 [00:14<00:04, 25.51it/s]
Epoch 0:  88%|████████▊ | 826/938 [00:48<00:06, 17.00it/s, loss=0.883, v_num=12]

Validating:  77%|███████▋  | 359/469 [00:14<00:04, 26.02it/s]
Epoch 0:  88%|████████▊ | 829/938 [00:48<00:06, 17.02it/s, loss=0.883, v_num=12]

Validating:  77%|███████▋  | 362/469 [00:14<00:04, 26.45it/s]
Epoch 0:  89%|████████▊ | 832/938 [00:48<00:06, 17.04it/s, loss=0.883, v_num=12]

Validating:  78%|███████▊  | 365/469 [00:14<00:03, 26.95it/s]
Epoch 0:  89%|████████▉ | 835/938 [00:48<00:06, 17.07it/s, loss=0.883, v_num=12]

Validating:  78%|███████▊  | 368/469 [00:14<00:03, 26.62it/s]
Epoch 0:  89%|████████▉ | 838/938 [00:49<00:05, 17.09it/s, loss=0.883, v_num=12]

Validating:  79%|███████▉  | 371/469 [00:15<00:03, 26.40it/s]
Epoch 0:  90%|████████▉ | 841/938 [00:49<00:05, 17.11it/s, loss=0.883, v_num=12]

Validating:  80%|███████▉  | 374/469 [00:15<00:03, 26.89it/s]
Epoch 0:  90%|████████▉ | 844/938 [00:49<00:05, 17.13it/s, loss=0.883, v_num=12]

Validating:  80%|████████  | 377/469 [00:15<00:03, 25.93it/s]
Epoch 0:  90%|█████████ | 847/938 [00:49<00:05, 17.15it/s, loss=0.883, v_num=12]

Validating:  81%|████████  | 380/469 [00:15<00:03, 25.45it/s]
Epoch 0:  91%|█████████ | 850/938 [00:49<00:05, 17.17it/s, loss=0.883, v_num=12]

Validating:  82%|████████▏ | 383/469 [00:15<00:03, 25.86it/s]
Epoch 0:  91%|█████████ | 853/938 [00:49<00:04, 17.19it/s, loss=0.883, v_num=12]

Validating:  82%|████████▏ | 386/469 [00:15<00:03, 26.17it/s]
Epoch 0:  91%|█████████▏| 856/938 [00:49<00:04, 17.21it/s, loss=0.883, v_num=12]

Validating:  83%|████████▎ | 389/469 [00:15<00:02, 26.85it/s]
Epoch 0:  92%|█████████▏| 859/938 [00:49<00:04, 17.24it/s, loss=0.883, v_num=12]

Validating:  84%|████████▎ | 392/469 [00:15<00:02, 25.97it/s]
Epoch 0:  92%|█████████▏| 862/938 [00:49<00:04, 17.25it/s, loss=0.883, v_num=12]

Validating:  84%|████████▍ | 395/469 [00:15<00:02, 26.36it/s]
Epoch 0:  92%|█████████▏| 865/938 [00:50<00:04, 17.28it/s, loss=0.883, v_num=12]

Validating:  85%|████████▍ | 398/469 [00:16<00:02, 26.31it/s]
Epoch 0:  93%|█████████▎| 868/938 [00:50<00:04, 17.30it/s, loss=0.883, v_num=12]

Validating:  86%|████████▌ | 402/469 [00:16<00:02, 26.79it/s]
Epoch 0:  93%|█████████▎| 872/938 [00:50<00:03, 17.33it/s, loss=0.883, v_num=12]

Validating:  86%|████████▋ | 405/469 [00:16<00:02, 26.86it/s]
Epoch 0:  93%|█████████▎| 876/938 [00:50<00:03, 17.35it/s, loss=0.883, v_num=12]

Validating:  87%|████████▋ | 408/469 [00:16<00:02, 26.86it/s]
Epoch 0:  94%|█████████▍| 880/938 [00:50<00:03, 17.38it/s, loss=0.883, v_num=12]

Validating:  88%|████████▊ | 411/469 [00:16<00:02, 26.73it/s]

Validating:  88%|████████▊ | 414/469 [00:16<00:02, 26.57it/s]
Epoch 0:  94%|█████████▍| 884/938 [00:50<00:03, 17.41it/s, loss=0.883, v_num=12]

Validating:  89%|████████▉ | 417/469 [00:16<00:01, 26.35it/s]
Epoch 0:  95%|█████████▍| 888/938 [00:50<00:02, 17.43it/s, loss=0.883, v_num=12]

Validating:  90%|████████▉ | 420/469 [00:16<00:01, 26.67it/s]
Epoch 0:  95%|█████████▌| 892/938 [00:51<00:02, 17.46it/s, loss=0.883, v_num=12]

Validating:  90%|█████████ | 423/469 [00:16<00:01, 26.53it/s]

Validating:  91%|█████████ | 426/469 [00:17<00:01, 26.53it/s]
Epoch 0:  96%|█████████▌| 896/938 [00:51<00:02, 17.49it/s, loss=0.883, v_num=12]

Validating:  91%|█████████▏| 429/469 [00:17<00:01, 26.51it/s]
Epoch 0:  96%|█████████▌| 900/938 [00:51<00:02, 17.52it/s, loss=0.883, v_num=12]

Validating:  92%|█████████▏| 432/469 [00:17<00:01, 25.84it/s]
Epoch 0:  96%|█████████▋| 904/938 [00:51<00:01, 17.53it/s, loss=0.883, v_num=12]

Validating:  93%|█████████▎| 435/469 [00:17<00:01, 25.33it/s]

Validating:  93%|█████████▎| 438/469 [00:17<00:01, 25.09it/s]
Epoch 0:  97%|█████████▋| 908/938 [00:51<00:01, 17.56it/s, loss=0.883, v_num=12]

Validating:  94%|█████████▍| 441/469 [00:17<00:01, 24.82it/s]
Epoch 0:  97%|█████████▋| 912/938 [00:51<00:01, 17.58it/s, loss=0.883, v_num=12]

Validating:  95%|█████████▍| 444/469 [00:17<00:00, 25.84it/s]
Epoch 0:  98%|█████████▊| 916/938 [00:52<00:01, 17.61it/s, loss=0.883, v_num=12]

Validating:  95%|█████████▌| 447/469 [00:17<00:00, 25.67it/s]

Validating:  96%|█████████▌| 450/469 [00:18<00:00, 25.69it/s]
Epoch 0:  98%|█████████▊| 920/938 [00:52<00:01, 17.63it/s, loss=0.883, v_num=12]

Validating:  97%|█████████▋| 453/469 [00:18<00:00, 26.40it/s]
Epoch 0:  99%|█████████▊| 924/938 [00:52<00:00, 17.66it/s, loss=0.883, v_num=12]

Validating:  97%|█████████▋| 456/469 [00:18<00:00, 26.53it/s]
Epoch 0:  99%|█████████▉| 928/938 [00:52<00:00, 17.68it/s, loss=0.883, v_num=12]

Validating:  98%|█████████▊| 459/469 [00:18<00:00, 26.23it/s]

Validating:  99%|█████████▊| 462/469 [00:18<00:00, 26.10it/s]
Epoch 0:  99%|█████████▉| 932/938 [00:52<00:00, 17.71it/s, loss=0.883, v_num=12]

Validating:  99%|█████████▉| 465/469 [00:18<00:00, 26.00it/s]
Epoch 0: 100%|█████████▉| 936/938 [00:52<00:00, 17.73it/s, loss=0.883, v_num=12]

Validating: 100%|█████████▉| 468/469 [00:18<00:00, 26.36it/s]
Epoch 0: 100%|██████████| 938/938 [00:52<00:00, 17.73it/s, loss=0.883, v_num=12, val_rmse=0.693]

                                                             
Epoch 0: 100%|██████████| 938/938 [00:52<00:00, 17.72it/s, loss=0.883, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 0:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.883, v_num=12, val_rmse=0.693, train_rmse=1.250]          
Epoch 1:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.883, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   0%|          | 1/938 [00:00<01:13, 12.69it/s, loss=0.875, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   0%|          | 2/938 [00:00<01:08, 13.69it/s, loss=0.866, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   0%|          | 3/938 [00:00<01:14, 12.56it/s, loss=0.861, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   0%|          | 4/938 [00:00<01:12, 12.92it/s, loss=0.861, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   0%|          | 4/938 [00:00<01:12, 12.89it/s, loss=0.862, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   1%|          | 5/938 [00:00<01:12, 12.81it/s, loss=0.852, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   1%|          | 6/938 [00:00<01:11, 12.94it/s, loss=0.842, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   1%|          | 7/938 [00:00<01:10, 13.21it/s, loss=0.827, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   1%|          | 8/938 [00:00<01:10, 13.20it/s, loss=0.827, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   1%|          | 8/938 [00:00<01:10, 13.19it/s, loss=0.826, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   1%|          | 9/938 [00:00<01:08, 13.47it/s, loss=0.826, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   1%|          | 10/938 [00:00<01:08, 13.47it/s, loss=0.818, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   1%|          | 11/938 [00:00<01:08, 13.58it/s, loss=0.828, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   1%|▏         | 12/938 [00:00<01:07, 13.78it/s, loss=0.828, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   1%|▏         | 12/938 [00:00<01:07, 13.77it/s, loss=0.813, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   1%|▏         | 13/938 [00:00<01:06, 13.96it/s, loss=0.81, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:   1%|▏         | 14/938 [00:01<01:09, 13.25it/s, loss=0.803, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   2%|▏         | 15/938 [00:01<01:08, 13.39it/s, loss=0.793, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   2%|▏         | 16/938 [00:01<01:07, 13.60it/s, loss=0.793, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   2%|▏         | 16/938 [00:01<01:07, 13.59it/s, loss=0.792, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   2%|▏         | 17/938 [00:01<01:07, 13.58it/s, loss=0.794, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   2%|▏         | 18/938 [00:01<01:07, 13.64it/s, loss=0.79, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:   2%|▏         | 19/938 [00:01<01:06, 13.81it/s, loss=0.797, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   2%|▏         | 20/938 [00:01<01:06, 13.79it/s, loss=0.797, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   2%|▏         | 20/938 [00:01<01:06, 13.79it/s, loss=0.798, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   2%|▏         | 21/938 [00:01<01:06, 13.83it/s, loss=0.795, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   2%|▏         | 22/938 [00:01<01:07, 13.53it/s, loss=0.806, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   2%|▏         | 23/938 [00:01<01:07, 13.59it/s, loss=0.801, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   3%|▎         | 24/938 [00:01<01:07, 13.59it/s, loss=0.801, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   3%|▎         | 24/938 [00:01<01:07, 13.59it/s, loss=0.804, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   3%|▎         | 25/938 [00:01<01:07, 13.62it/s, loss=0.811, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   3%|▎         | 26/938 [00:01<01:06, 13.65it/s, loss=0.813, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   3%|▎         | 27/938 [00:01<01:06, 13.64it/s, loss=0.82, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:   3%|▎         | 28/938 [00:02<01:06, 13.61it/s, loss=0.82, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   3%|▎         | 28/938 [00:02<01:06, 13.60it/s, loss=0.819, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   3%|▎         | 29/938 [00:02<01:06, 13.61it/s, loss=0.818, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   3%|▎         | 30/938 [00:02<01:06, 13.64it/s, loss=0.822, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   3%|▎         | 31/938 [00:02<01:06, 13.60it/s, loss=0.816, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   3%|▎         | 32/938 [00:02<01:06, 13.56it/s, loss=0.816, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   3%|▎         | 32/938 [00:02<01:06, 13.56it/s, loss=0.826, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   4%|▎         | 33/938 [00:02<01:06, 13.54it/s, loss=0.823, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   4%|▎         | 34/938 [00:02<01:07, 13.47it/s, loss=0.822, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   4%|▎         | 35/938 [00:02<01:06, 13.55it/s, loss=0.812, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   4%|▍         | 36/938 [00:02<01:06, 13.57it/s, loss=0.812, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   4%|▍         | 36/938 [00:02<01:06, 13.57it/s, loss=0.818, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   4%|▍         | 37/938 [00:02<01:06, 13.64it/s, loss=0.815, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   4%|▍         | 38/938 [00:02<01:06, 13.63it/s, loss=0.816, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   4%|▍         | 39/938 [00:02<01:05, 13.67it/s, loss=0.807, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   4%|▍         | 40/938 [00:02<01:05, 13.73it/s, loss=0.807, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   4%|▍         | 40/938 [00:02<01:05, 13.72it/s, loss=0.807, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   4%|▍         | 41/938 [00:02<01:05, 13.72it/s, loss=0.809, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   4%|▍         | 42/938 [00:03<01:05, 13.76it/s, loss=0.805, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   5%|▍         | 43/938 [00:03<01:05, 13.75it/s, loss=0.808, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   5%|▍         | 44/938 [00:03<01:04, 13.80it/s, loss=0.808, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   5%|▍         | 44/938 [00:03<01:04, 13.80it/s, loss=0.806, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   5%|▍         | 45/938 [00:03<01:04, 13.78it/s, loss=0.815, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   5%|▍         | 46/938 [00:03<01:04, 13.77it/s, loss=0.822, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   5%|▌         | 47/938 [00:03<01:05, 13.69it/s, loss=0.815, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   5%|▌         | 48/938 [00:03<01:04, 13.71it/s, loss=0.815, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   5%|▌         | 48/938 [00:03<01:04, 13.71it/s, loss=0.812, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   5%|▌         | 49/938 [00:03<01:04, 13.71it/s, loss=0.811, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   5%|▌         | 50/938 [00:03<01:04, 13.67it/s, loss=0.807, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   5%|▌         | 51/938 [00:03<01:04, 13.72it/s, loss=0.81, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:   6%|▌         | 52/938 [00:03<01:04, 13.73it/s, loss=0.81, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   6%|▌         | 52/938 [00:03<01:04, 13.73it/s, loss=0.808, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   6%|▌         | 53/938 [00:03<01:04, 13.70it/s, loss=0.816, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   6%|▌         | 54/938 [00:03<01:04, 13.75it/s, loss=0.814, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   6%|▌         | 55/938 [00:03<01:04, 13.77it/s, loss=0.826, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   6%|▌         | 56/938 [00:04<01:03, 13.83it/s, loss=0.826, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   6%|▌         | 56/938 [00:04<01:03, 13.82it/s, loss=0.824, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   6%|▌         | 57/938 [00:04<01:03, 13.83it/s, loss=0.826, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   6%|▌         | 58/938 [00:04<01:03, 13.87it/s, loss=0.822, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   6%|▋         | 59/938 [00:04<01:03, 13.86it/s, loss=0.828, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   6%|▋         | 60/938 [00:04<01:03, 13.91it/s, loss=0.828, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   6%|▋         | 60/938 [00:04<01:03, 13.91it/s, loss=0.817, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   7%|▋         | 61/938 [00:04<01:02, 13.93it/s, loss=0.822, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   7%|▋         | 62/938 [00:04<01:02, 13.94it/s, loss=0.811, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   7%|▋         | 63/938 [00:04<01:02, 13.98it/s, loss=0.806, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   7%|▋         | 64/938 [00:04<01:02, 13.99it/s, loss=0.806, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   7%|▋         | 64/938 [00:04<01:02, 13.99it/s, loss=0.796, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   7%|▋         | 65/938 [00:04<01:02, 13.97it/s, loss=0.786, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   7%|▋         | 66/938 [00:04<01:02, 13.98it/s, loss=0.787, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   7%|▋         | 67/938 [00:04<01:02, 13.99it/s, loss=0.784, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   7%|▋         | 68/938 [00:04<01:02, 13.99it/s, loss=0.784, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   7%|▋         | 68/938 [00:04<01:02, 13.98it/s, loss=0.782, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   7%|▋         | 69/938 [00:04<01:02, 13.95it/s, loss=0.784, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   7%|▋         | 70/938 [00:05<01:02, 13.94it/s, loss=0.782, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   8%|▊         | 71/938 [00:05<01:02, 13.97it/s, loss=0.78, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:   8%|▊         | 72/938 [00:05<01:01, 13.97it/s, loss=0.78, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   8%|▊         | 72/938 [00:05<01:02, 13.97it/s, loss=0.773, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   8%|▊         | 73/938 [00:05<01:02, 13.95it/s, loss=0.766, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   8%|▊         | 74/938 [00:05<01:01, 13.94it/s, loss=0.767, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   8%|▊         | 75/938 [00:05<01:01, 13.97it/s, loss=0.764, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   8%|▊         | 76/938 [00:05<01:01, 13.95it/s, loss=0.764, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   8%|▊         | 76/938 [00:05<01:01, 13.95it/s, loss=0.768, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   8%|▊         | 77/938 [00:05<01:01, 13.96it/s, loss=0.758, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   8%|▊         | 78/938 [00:05<01:01, 13.94it/s, loss=0.757, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   8%|▊         | 79/938 [00:05<01:01, 13.94it/s, loss=0.775, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   9%|▊         | 80/938 [00:05<01:01, 13.97it/s, loss=0.775, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   9%|▊         | 80/938 [00:05<01:01, 13.97it/s, loss=0.782, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   9%|▊         | 81/938 [00:05<01:01, 13.97it/s, loss=0.785, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   9%|▊         | 82/938 [00:05<01:01, 14.00it/s, loss=0.792, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   9%|▉         | 83/938 [00:05<01:00, 14.03it/s, loss=0.795, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   9%|▉         | 84/938 [00:05<01:00, 14.04it/s, loss=0.795, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   9%|▉         | 84/938 [00:05<01:00, 14.04it/s, loss=0.801, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   9%|▉         | 85/938 [00:06<01:00, 14.04it/s, loss=0.791, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   9%|▉         | 86/938 [00:06<01:00, 14.07it/s, loss=0.788, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   9%|▉         | 87/938 [00:06<01:00, 14.07it/s, loss=0.789, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   9%|▉         | 88/938 [00:06<01:00, 14.09it/s, loss=0.789, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   9%|▉         | 88/938 [00:06<01:00, 14.09it/s, loss=0.799, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:   9%|▉         | 89/938 [00:06<01:00, 14.07it/s, loss=0.791, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  10%|▉         | 90/938 [00:06<01:00, 14.06it/s, loss=0.791, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  10%|▉         | 91/938 [00:06<01:00, 14.06it/s, loss=0.79, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  10%|▉         | 92/938 [00:06<01:00, 14.08it/s, loss=0.79, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  10%|▉         | 92/938 [00:06<01:00, 14.07it/s, loss=0.785, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  10%|▉         | 93/938 [00:06<00:59, 14.09it/s, loss=0.788, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  10%|█         | 94/938 [00:06<00:59, 14.09it/s, loss=0.795, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  10%|█         | 95/938 [00:06<00:59, 14.11it/s, loss=0.794, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  10%|█         | 96/938 [00:06<00:59, 14.12it/s, loss=0.794, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  10%|█         | 96/938 [00:06<00:59, 14.12it/s, loss=0.778, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  10%|█         | 97/938 [00:06<00:59, 14.13it/s, loss=0.779, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  10%|█         | 98/938 [00:06<00:59, 14.14it/s, loss=0.78, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  11%|█         | 99/938 [00:06<00:59, 14.17it/s, loss=0.75, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  11%|█         | 100/938 [00:07<00:59, 14.18it/s, loss=0.75, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  11%|█         | 100/938 [00:07<00:59, 14.18it/s, loss=0.752, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  11%|█         | 101/938 [00:07<00:59, 14.18it/s, loss=0.744, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  11%|█         | 102/938 [00:07<00:58, 14.18it/s, loss=0.743, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  11%|█         | 103/938 [00:07<00:58, 14.20it/s, loss=0.741, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  11%|█         | 104/938 [00:07<00:58, 14.19it/s, loss=0.741, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  11%|█         | 104/938 [00:07<00:58, 14.19it/s, loss=0.739, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  11%|█         | 105/938 [00:07<00:58, 14.18it/s, loss=0.742, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  11%|█▏        | 106/938 [00:07<00:58, 14.17it/s, loss=0.734, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  11%|█▏        | 107/938 [00:07<00:58, 14.20it/s, loss=0.73, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  12%|█▏        | 108/938 [00:07<00:58, 14.20it/s, loss=0.73, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  12%|█▏        | 108/938 [00:07<00:58, 14.20it/s, loss=0.726, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  12%|█▏        | 109/938 [00:07<00:58, 14.19it/s, loss=0.729, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  12%|█▏        | 110/938 [00:07<00:58, 14.18it/s, loss=0.729, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  12%|█▏        | 111/938 [00:07<00:58, 14.19it/s, loss=0.726, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  12%|█▏        | 112/938 [00:07<00:58, 14.18it/s, loss=0.726, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  12%|█▏        | 112/938 [00:07<00:58, 14.18it/s, loss=0.728, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  12%|█▏        | 113/938 [00:07<00:58, 14.18it/s, loss=0.729, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  12%|█▏        | 114/938 [00:08<00:58, 14.19it/s, loss=0.738, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  12%|█▏        | 115/938 [00:08<00:58, 14.16it/s, loss=0.749, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  12%|█▏        | 116/938 [00:08<00:58, 14.15it/s, loss=0.749, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  12%|█▏        | 116/938 [00:08<00:58, 14.15it/s, loss=0.755, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  12%|█▏        | 117/938 [00:08<00:58, 14.15it/s, loss=0.761, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  13%|█▎        | 118/938 [00:08<00:58, 14.13it/s, loss=0.763, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  13%|█▎        | 119/938 [00:08<00:57, 14.15it/s, loss=0.776, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  13%|█▎        | 120/938 [00:08<00:57, 14.16it/s, loss=0.776, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  13%|█▎        | 120/938 [00:08<00:57, 14.16it/s, loss=0.78, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  13%|█▎        | 121/938 [00:08<00:57, 14.17it/s, loss=0.786, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  13%|█▎        | 122/938 [00:08<00:57, 14.14it/s, loss=0.799, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  13%|█▎        | 123/938 [00:08<00:57, 14.16it/s, loss=0.799, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  13%|█▎        | 124/938 [00:08<00:57, 14.17it/s, loss=0.799, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  13%|█▎        | 124/938 [00:08<00:57, 14.17it/s, loss=0.803, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  13%|█▎        | 125/938 [00:08<00:57, 14.17it/s, loss=0.807, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  13%|█▎        | 126/938 [00:08<00:57, 14.19it/s, loss=0.809, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  14%|█▎        | 127/938 [00:08<00:57, 14.19it/s, loss=0.815, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  14%|█▎        | 128/938 [00:09<00:57, 14.20it/s, loss=0.815, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  14%|█▎        | 128/938 [00:09<00:57, 14.20it/s, loss=0.825, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  14%|█▍        | 129/938 [00:09<00:56, 14.23it/s, loss=0.818, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  14%|█▍        | 130/938 [00:09<00:56, 14.22it/s, loss=0.819, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  14%|█▍        | 131/938 [00:09<00:56, 14.21it/s, loss=0.819, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  14%|█▍        | 132/938 [00:09<00:56, 14.23it/s, loss=0.819, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  14%|█▍        | 132/938 [00:09<00:56, 14.23it/s, loss=0.819, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  14%|█▍        | 133/938 [00:09<00:56, 14.23it/s, loss=0.816, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  14%|█▍        | 134/938 [00:09<00:56, 14.22it/s, loss=0.801, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  14%|█▍        | 135/938 [00:09<00:56, 14.23it/s, loss=0.795, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  14%|█▍        | 136/938 [00:09<00:56, 14.24it/s, loss=0.795, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  14%|█▍        | 136/938 [00:09<00:56, 14.24it/s, loss=0.799, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  15%|█▍        | 137/938 [00:09<00:56, 14.23it/s, loss=0.79, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  15%|█▍        | 138/938 [00:09<00:56, 14.23it/s, loss=0.784, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  15%|█▍        | 139/938 [00:09<00:56, 14.24it/s, loss=0.77, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  15%|█▍        | 140/938 [00:09<00:56, 14.22it/s, loss=0.77, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  15%|█▍        | 140/938 [00:09<00:56, 14.22it/s, loss=0.763, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  15%|█▌        | 141/938 [00:09<00:55, 14.23it/s, loss=0.767, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  15%|█▌        | 142/938 [00:09<00:56, 14.20it/s, loss=0.759, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  15%|█▌        | 143/938 [00:10<00:55, 14.22it/s, loss=0.76, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  15%|█▌        | 144/938 [00:10<00:55, 14.23it/s, loss=0.76, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  15%|█▌        | 144/938 [00:10<00:55, 14.23it/s, loss=0.769, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  15%|█▌        | 145/938 [00:10<00:55, 14.23it/s, loss=0.773, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  16%|█▌        | 146/938 [00:10<00:55, 14.23it/s, loss=0.771, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  16%|█▌        | 147/938 [00:10<00:55, 14.25it/s, loss=0.765, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  16%|█▌        | 148/938 [00:10<00:55, 14.25it/s, loss=0.765, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  16%|█▌        | 148/938 [00:10<00:55, 14.25it/s, loss=0.763, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  16%|█▌        | 149/938 [00:10<00:55, 14.24it/s, loss=0.769, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  16%|█▌        | 150/938 [00:10<00:55, 14.25it/s, loss=0.771, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  16%|█▌        | 151/938 [00:10<00:55, 14.25it/s, loss=0.781, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  16%|█▌        | 152/938 [00:10<00:55, 14.26it/s, loss=0.781, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  16%|█▌        | 152/938 [00:10<00:55, 14.26it/s, loss=0.785, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  16%|█▋        | 153/938 [00:10<00:55, 14.27it/s, loss=0.788, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  16%|█▋        | 154/938 [00:10<00:54, 14.26it/s, loss=0.789, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  17%|█▋        | 155/938 [00:10<00:54, 14.26it/s, loss=0.783, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  17%|█▋        | 156/938 [00:10<00:54, 14.27it/s, loss=0.783, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  17%|█▋        | 156/938 [00:10<00:54, 14.27it/s, loss=0.786, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  17%|█▋        | 157/938 [00:11<00:54, 14.27it/s, loss=0.792, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  17%|█▋        | 158/938 [00:11<00:54, 14.28it/s, loss=0.804, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  17%|█▋        | 159/938 [00:11<00:54, 14.30it/s, loss=0.811, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  17%|█▋        | 160/938 [00:11<00:54, 14.29it/s, loss=0.811, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  17%|█▋        | 160/938 [00:11<00:54, 14.29it/s, loss=0.817, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  17%|█▋        | 161/938 [00:11<00:54, 14.30it/s, loss=0.814, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  17%|█▋        | 162/938 [00:11<00:54, 14.31it/s, loss=0.816, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  17%|█▋        | 163/938 [00:11<00:54, 14.27it/s, loss=0.815, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  17%|█▋        | 164/938 [00:11<00:54, 14.29it/s, loss=0.815, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  17%|█▋        | 164/938 [00:11<00:54, 14.29it/s, loss=0.804, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  18%|█▊        | 165/938 [00:11<00:54, 14.28it/s, loss=0.799, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  18%|█▊        | 166/938 [00:11<00:54, 14.29it/s, loss=0.808, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  18%|█▊        | 167/938 [00:11<00:53, 14.29it/s, loss=0.805, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  18%|█▊        | 168/938 [00:11<00:53, 14.28it/s, loss=0.805, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  18%|█▊        | 168/938 [00:11<00:53, 14.28it/s, loss=0.796, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  18%|█▊        | 169/938 [00:11<00:53, 14.28it/s, loss=0.792, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  18%|█▊        | 170/938 [00:11<00:53, 14.29it/s, loss=0.794, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  18%|█▊        | 171/938 [00:11<00:53, 14.28it/s, loss=0.788, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  18%|█▊        | 172/938 [00:12<00:53, 14.28it/s, loss=0.788, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  18%|█▊        | 172/938 [00:12<00:53, 14.28it/s, loss=0.794, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  18%|█▊        | 173/938 [00:12<00:53, 14.29it/s, loss=0.795, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  19%|█▊        | 174/938 [00:12<00:53, 14.29it/s, loss=0.795, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  19%|█▊        | 175/938 [00:12<00:53, 14.28it/s, loss=0.803, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  19%|█▉        | 176/938 [00:12<00:53, 14.29it/s, loss=0.803, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  19%|█▉        | 176/938 [00:12<00:53, 14.29it/s, loss=0.797, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  19%|█▉        | 177/938 [00:12<00:53, 14.27it/s, loss=0.797, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  19%|█▉        | 178/938 [00:12<00:53, 14.26it/s, loss=0.787, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  19%|█▉        | 179/938 [00:12<00:53, 14.28it/s, loss=0.791, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  19%|█▉        | 180/938 [00:12<00:53, 14.28it/s, loss=0.791, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  19%|█▉        | 180/938 [00:12<00:53, 14.28it/s, loss=0.784, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  19%|█▉        | 181/938 [00:12<00:53, 14.28it/s, loss=0.781, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  19%|█▉        | 182/938 [00:12<00:52, 14.28it/s, loss=0.783, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  20%|█▉        | 183/938 [00:12<00:52, 14.29it/s, loss=0.777, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  20%|█▉        | 184/938 [00:12<00:52, 14.28it/s, loss=0.777, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  20%|█▉        | 184/938 [00:12<00:52, 14.28it/s, loss=0.774, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  20%|█▉        | 185/938 [00:12<00:52, 14.26it/s, loss=0.773, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  20%|█▉        | 186/938 [00:13<00:52, 14.26it/s, loss=0.76, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  20%|█▉        | 187/938 [00:13<00:52, 14.26it/s, loss=0.763, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  20%|██        | 188/938 [00:13<00:52, 14.26it/s, loss=0.763, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  20%|██        | 188/938 [00:13<00:52, 14.26it/s, loss=0.775, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  20%|██        | 189/938 [00:13<00:52, 14.26it/s, loss=0.777, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  20%|██        | 190/938 [00:13<00:52, 14.26it/s, loss=0.771, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  20%|██        | 191/938 [00:13<00:52, 14.25it/s, loss=0.774, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  20%|██        | 192/938 [00:13<00:52, 14.25it/s, loss=0.774, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  20%|██        | 192/938 [00:13<00:52, 14.25it/s, loss=0.766, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  21%|██        | 193/938 [00:13<00:52, 14.26it/s, loss=0.755, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  21%|██        | 194/938 [00:13<00:52, 14.26it/s, loss=0.749, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  21%|██        | 195/938 [00:13<00:52, 14.27it/s, loss=0.74, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  21%|██        | 196/938 [00:13<00:51, 14.28it/s, loss=0.74, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  21%|██        | 196/938 [00:13<00:51, 14.28it/s, loss=0.739, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  21%|██        | 197/938 [00:13<00:51, 14.27it/s, loss=0.743, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  21%|██        | 198/938 [00:13<00:51, 14.27it/s, loss=0.747, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  21%|██        | 199/938 [00:13<00:51, 14.27it/s, loss=0.737, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  21%|██▏       | 200/938 [00:14<00:51, 14.27it/s, loss=0.737, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  21%|██▏       | 200/938 [00:14<00:51, 14.27it/s, loss=0.743, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  21%|██▏       | 201/938 [00:14<00:51, 14.26it/s, loss=0.738, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  22%|██▏       | 202/938 [00:14<00:51, 14.27it/s, loss=0.728, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  22%|██▏       | 203/938 [00:14<00:51, 14.27it/s, loss=0.742, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  22%|██▏       | 204/938 [00:14<00:51, 14.28it/s, loss=0.742, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  22%|██▏       | 204/938 [00:14<00:51, 14.28it/s, loss=0.749, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  22%|██▏       | 205/938 [00:14<00:51, 14.28it/s, loss=0.75, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  22%|██▏       | 206/938 [00:14<00:51, 14.27it/s, loss=0.758, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  22%|██▏       | 207/938 [00:14<00:51, 14.27it/s, loss=0.759, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  22%|██▏       | 208/938 [00:14<00:51, 14.28it/s, loss=0.759, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  22%|██▏       | 208/938 [00:14<00:51, 14.28it/s, loss=0.747, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  22%|██▏       | 209/938 [00:14<00:51, 14.29it/s, loss=0.743, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  22%|██▏       | 210/938 [00:14<00:50, 14.28it/s, loss=0.749, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  22%|██▏       | 211/938 [00:14<00:50, 14.30it/s, loss=0.747, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  23%|██▎       | 212/938 [00:14<00:50, 14.30it/s, loss=0.747, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  23%|██▎       | 212/938 [00:14<00:50, 14.30it/s, loss=0.757, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  23%|██▎       | 213/938 [00:14<00:50, 14.30it/s, loss=0.766, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  23%|██▎       | 214/938 [00:14<00:50, 14.31it/s, loss=0.768, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  23%|██▎       | 215/938 [00:15<00:50, 14.30it/s, loss=0.775, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  23%|██▎       | 216/938 [00:15<00:50, 14.31it/s, loss=0.775, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  23%|██▎       | 216/938 [00:15<00:50, 14.31it/s, loss=0.775, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  23%|██▎       | 217/938 [00:15<00:50, 14.30it/s, loss=0.773, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  23%|██▎       | 218/938 [00:15<00:50, 14.31it/s, loss=0.776, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  23%|██▎       | 219/938 [00:15<00:50, 14.31it/s, loss=0.776, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  23%|██▎       | 220/938 [00:15<00:50, 14.32it/s, loss=0.776, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  23%|██▎       | 220/938 [00:15<00:50, 14.32it/s, loss=0.766, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  24%|██▎       | 221/938 [00:15<00:50, 14.32it/s, loss=0.767, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  24%|██▎       | 222/938 [00:15<00:49, 14.32it/s, loss=0.771, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  24%|██▍       | 223/938 [00:15<00:49, 14.33it/s, loss=0.762, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  24%|██▍       | 224/938 [00:15<00:49, 14.33it/s, loss=0.762, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  24%|██▍       | 224/938 [00:15<00:49, 14.33it/s, loss=0.763, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  24%|██▍       | 225/938 [00:15<00:49, 14.32it/s, loss=0.764, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  24%|██▍       | 226/938 [00:15<00:49, 14.32it/s, loss=0.756, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  24%|██▍       | 227/938 [00:15<00:49, 14.31it/s, loss=0.756, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  24%|██▍       | 228/938 [00:15<00:49, 14.33it/s, loss=0.756, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  24%|██▍       | 228/938 [00:15<00:49, 14.33it/s, loss=0.76, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  24%|██▍       | 229/938 [00:15<00:49, 14.31it/s, loss=0.76, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  25%|██▍       | 230/938 [00:16<00:49, 14.31it/s, loss=0.76, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  25%|██▍       | 231/938 [00:16<00:49, 14.32it/s, loss=0.757, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  25%|██▍       | 232/938 [00:16<00:49, 14.32it/s, loss=0.757, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  25%|██▍       | 232/938 [00:16<00:49, 14.32it/s, loss=0.741, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  25%|██▍       | 233/938 [00:16<00:49, 14.25it/s, loss=0.738, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  25%|██▍       | 234/938 [00:16<00:49, 14.25it/s, loss=0.736, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  25%|██▌       | 235/938 [00:16<00:49, 14.26it/s, loss=0.724, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  25%|██▌       | 236/938 [00:16<00:49, 14.26it/s, loss=0.724, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  25%|██▌       | 236/938 [00:16<00:49, 14.26it/s, loss=0.732, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  25%|██▌       | 237/938 [00:16<00:49, 14.26it/s, loss=0.728, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  25%|██▌       | 238/938 [00:16<00:49, 14.26it/s, loss=0.72, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  25%|██▌       | 239/938 [00:16<00:49, 14.26it/s, loss=0.722, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  26%|██▌       | 240/938 [00:16<00:48, 14.27it/s, loss=0.722, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  26%|██▌       | 240/938 [00:16<00:48, 14.27it/s, loss=0.718, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  26%|██▌       | 241/938 [00:16<00:48, 14.27it/s, loss=0.712, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  26%|██▌       | 242/938 [00:16<00:48, 14.27it/s, loss=0.721, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  26%|██▌       | 243/938 [00:17<00:48, 14.28it/s, loss=0.725, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  26%|██▌       | 244/938 [00:17<00:48, 14.28it/s, loss=0.725, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  26%|██▌       | 244/938 [00:17<00:48, 14.28it/s, loss=0.717, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  26%|██▌       | 245/938 [00:17<00:48, 14.28it/s, loss=0.714, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  26%|██▌       | 246/938 [00:17<00:48, 14.29it/s, loss=0.719, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  26%|██▋       | 247/938 [00:17<00:48, 14.29it/s, loss=0.728, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  26%|██▋       | 248/938 [00:17<00:48, 14.28it/s, loss=0.728, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  26%|██▋       | 248/938 [00:17<00:48, 14.28it/s, loss=0.724, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  27%|██▋       | 249/938 [00:17<00:48, 14.29it/s, loss=0.725, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  27%|██▋       | 250/938 [00:17<00:48, 14.29it/s, loss=0.716, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  27%|██▋       | 251/938 [00:17<00:48, 14.29it/s, loss=0.717, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  27%|██▋       | 252/938 [00:17<00:47, 14.30it/s, loss=0.717, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  27%|██▋       | 252/938 [00:17<00:47, 14.30it/s, loss=0.724, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  27%|██▋       | 253/938 [00:17<00:47, 14.30it/s, loss=0.725, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  27%|██▋       | 254/938 [00:17<00:47, 14.31it/s, loss=0.728, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  27%|██▋       | 255/938 [00:17<00:47, 14.31it/s, loss=0.733, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  27%|██▋       | 256/938 [00:17<00:47, 14.31it/s, loss=0.733, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  27%|██▋       | 256/938 [00:17<00:47, 14.31it/s, loss=0.725, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  27%|██▋       | 257/938 [00:17<00:47, 14.31it/s, loss=0.719, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  28%|██▊       | 258/938 [00:18<00:47, 14.31it/s, loss=0.718, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  28%|██▊       | 259/938 [00:18<00:47, 14.31it/s, loss=0.723, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  28%|██▊       | 260/938 [00:18<00:47, 14.32it/s, loss=0.723, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  28%|██▊       | 260/938 [00:18<00:47, 14.32it/s, loss=0.73, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  28%|██▊       | 261/938 [00:18<00:47, 14.32it/s, loss=0.734, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  28%|██▊       | 262/938 [00:18<00:47, 14.31it/s, loss=0.733, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  28%|██▊       | 263/938 [00:18<00:47, 14.31it/s, loss=0.738, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  28%|██▊       | 264/938 [00:18<00:47, 14.32it/s, loss=0.738, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  28%|██▊       | 264/938 [00:18<00:47, 14.32it/s, loss=0.737, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  28%|██▊       | 265/938 [00:18<00:47, 14.31it/s, loss=0.744, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  28%|██▊       | 266/938 [00:18<00:46, 14.31it/s, loss=0.748, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  28%|██▊       | 267/938 [00:18<00:46, 14.30it/s, loss=0.741, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  29%|██▊       | 268/938 [00:18<00:46, 14.30it/s, loss=0.741, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  29%|██▊       | 268/938 [00:18<00:46, 14.30it/s, loss=0.743, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  29%|██▊       | 269/938 [00:18<00:46, 14.30it/s, loss=0.747, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  29%|██▉       | 270/938 [00:18<00:46, 14.29it/s, loss=0.753, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  29%|██▉       | 271/938 [00:18<00:46, 14.30it/s, loss=0.756, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  29%|██▉       | 272/938 [00:19<00:46, 14.30it/s, loss=0.756, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  29%|██▉       | 272/938 [00:19<00:46, 14.30it/s, loss=0.76, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  29%|██▉       | 273/938 [00:19<00:46, 14.30it/s, loss=0.76, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  29%|██▉       | 274/938 [00:19<00:46, 14.29it/s, loss=0.758, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  29%|██▉       | 275/938 [00:19<00:46, 14.30it/s, loss=0.743, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  29%|██▉       | 276/938 [00:19<00:46, 14.31it/s, loss=0.743, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  29%|██▉       | 276/938 [00:19<00:46, 14.31it/s, loss=0.742, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  30%|██▉       | 277/938 [00:19<00:46, 14.31it/s, loss=0.751, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  30%|██▉       | 278/938 [00:19<00:46, 14.32it/s, loss=0.761, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  30%|██▉       | 279/938 [00:19<00:46, 14.31it/s, loss=0.756, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  30%|██▉       | 280/938 [00:19<00:46, 14.30it/s, loss=0.756, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  30%|██▉       | 280/938 [00:19<00:46, 14.30it/s, loss=0.762, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  30%|██▉       | 281/938 [00:19<00:45, 14.30it/s, loss=0.766, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  30%|███       | 282/938 [00:19<00:45, 14.30it/s, loss=0.755, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  30%|███       | 283/938 [00:19<00:45, 14.30it/s, loss=0.748, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  30%|███       | 284/938 [00:19<00:45, 14.29it/s, loss=0.748, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  30%|███       | 284/938 [00:19<00:45, 14.29it/s, loss=0.746, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  30%|███       | 285/938 [00:19<00:45, 14.28it/s, loss=0.743, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  30%|███       | 286/938 [00:20<00:45, 14.28it/s, loss=0.749, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  31%|███       | 287/938 [00:20<00:45, 14.28it/s, loss=0.75, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  31%|███       | 288/938 [00:20<00:45, 14.29it/s, loss=0.75, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  31%|███       | 288/938 [00:20<00:45, 14.29it/s, loss=0.737, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  31%|███       | 289/938 [00:20<00:45, 14.28it/s, loss=0.738, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  31%|███       | 290/938 [00:20<00:45, 14.24it/s, loss=0.734, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  31%|███       | 291/938 [00:20<00:45, 14.25it/s, loss=0.725, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  31%|███       | 292/938 [00:20<00:45, 14.26it/s, loss=0.725, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  31%|███       | 292/938 [00:20<00:45, 14.26it/s, loss=0.719, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  31%|███       | 293/938 [00:20<00:45, 14.26it/s, loss=0.722, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  31%|███▏      | 294/938 [00:20<00:45, 14.26it/s, loss=0.722, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  31%|███▏      | 295/938 [00:20<00:45, 14.26it/s, loss=0.732, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  32%|███▏      | 296/938 [00:20<00:44, 14.27it/s, loss=0.732, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  32%|███▏      | 296/938 [00:20<00:45, 14.27it/s, loss=0.734, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  32%|███▏      | 297/938 [00:20<00:44, 14.26it/s, loss=0.738, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  32%|███▏      | 298/938 [00:20<00:44, 14.28it/s, loss=0.733, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  32%|███▏      | 299/938 [00:20<00:44, 14.28it/s, loss=0.732, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  32%|███▏      | 300/938 [00:21<00:44, 14.27it/s, loss=0.732, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  32%|███▏      | 300/938 [00:21<00:44, 14.27it/s, loss=0.725, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  32%|███▏      | 301/938 [00:21<00:44, 14.28it/s, loss=0.728, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  32%|███▏      | 302/938 [00:21<00:44, 14.28it/s, loss=0.735, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  32%|███▏      | 303/938 [00:21<00:44, 14.27it/s, loss=0.731, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  32%|███▏      | 304/938 [00:21<00:44, 14.28it/s, loss=0.731, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  32%|███▏      | 304/938 [00:21<00:44, 14.28it/s, loss=0.736, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  33%|███▎      | 305/938 [00:21<00:44, 14.28it/s, loss=0.73, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  33%|███▎      | 306/938 [00:21<00:44, 14.28it/s, loss=0.734, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  33%|███▎      | 307/938 [00:21<00:44, 14.29it/s, loss=0.737, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  33%|███▎      | 308/938 [00:21<00:44, 14.29it/s, loss=0.737, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  33%|███▎      | 308/938 [00:21<00:44, 14.29it/s, loss=0.759, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  33%|███▎      | 309/938 [00:21<00:43, 14.30it/s, loss=0.758, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  33%|███▎      | 310/938 [00:21<00:43, 14.31it/s, loss=0.763, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  33%|███▎      | 311/938 [00:21<00:43, 14.31it/s, loss=0.764, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  33%|███▎      | 312/938 [00:21<00:43, 14.32it/s, loss=0.764, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  33%|███▎      | 312/938 [00:21<00:43, 14.32it/s, loss=0.759, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  33%|███▎      | 313/938 [00:21<00:43, 14.32it/s, loss=0.761, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  33%|███▎      | 314/938 [00:21<00:43, 14.31it/s, loss=0.758, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  34%|███▎      | 315/938 [00:22<00:43, 14.31it/s, loss=0.76, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  34%|███▎      | 316/938 [00:22<00:43, 14.32it/s, loss=0.76, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  34%|███▎      | 316/938 [00:22<00:43, 14.32it/s, loss=0.77, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  34%|███▍      | 317/938 [00:22<00:43, 14.31it/s, loss=0.769, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  34%|███▍      | 318/938 [00:22<00:43, 14.31it/s, loss=0.77, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  34%|███▍      | 319/938 [00:22<00:43, 14.32it/s, loss=0.774, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  34%|███▍      | 320/938 [00:22<00:43, 14.33it/s, loss=0.774, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  34%|███▍      | 320/938 [00:22<00:43, 14.33it/s, loss=0.78, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  34%|███▍      | 321/938 [00:22<00:43, 14.32it/s, loss=0.781, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  34%|███▍      | 322/938 [00:22<00:42, 14.33it/s, loss=0.779, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  34%|███▍      | 323/938 [00:22<00:42, 14.33it/s, loss=0.776, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  35%|███▍      | 324/938 [00:22<00:42, 14.34it/s, loss=0.776, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  35%|███▍      | 324/938 [00:22<00:42, 14.34it/s, loss=0.783, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  35%|███▍      | 325/938 [00:22<00:42, 14.34it/s, loss=0.783, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  35%|███▍      | 326/938 [00:22<00:42, 14.34it/s, loss=0.767, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  35%|███▍      | 327/938 [00:22<00:42, 14.34it/s, loss=0.757, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  35%|███▍      | 328/938 [00:22<00:42, 14.34it/s, loss=0.757, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  35%|███▍      | 328/938 [00:22<00:42, 14.34it/s, loss=0.742, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  35%|███▌      | 329/938 [00:22<00:42, 14.35it/s, loss=0.742, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  35%|███▌      | 330/938 [00:22<00:42, 14.35it/s, loss=0.745, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  35%|███▌      | 331/938 [00:23<00:42, 14.36it/s, loss=0.749, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  35%|███▌      | 332/938 [00:23<00:42, 14.35it/s, loss=0.749, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  35%|███▌      | 332/938 [00:23<00:42, 14.35it/s, loss=0.752, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  36%|███▌      | 333/938 [00:23<00:42, 14.35it/s, loss=0.749, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  36%|███▌      | 334/938 [00:23<00:42, 14.36it/s, loss=0.759, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  36%|███▌      | 335/938 [00:23<00:42, 14.36it/s, loss=0.767, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  36%|███▌      | 336/938 [00:23<00:41, 14.36it/s, loss=0.767, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  36%|███▌      | 336/938 [00:23<00:41, 14.36it/s, loss=0.756, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  36%|███▌      | 337/938 [00:23<00:41, 14.36it/s, loss=0.754, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  36%|███▌      | 338/938 [00:23<00:41, 14.37it/s, loss=0.743, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  36%|███▌      | 339/938 [00:23<00:41, 14.36it/s, loss=0.747, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  36%|███▌      | 340/938 [00:23<00:41, 14.35it/s, loss=0.747, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  36%|███▌      | 340/938 [00:23<00:41, 14.35it/s, loss=0.741, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  36%|███▋      | 341/938 [00:23<00:41, 14.36it/s, loss=0.735, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  36%|███▋      | 342/938 [00:23<00:41, 14.36it/s, loss=0.737, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  37%|███▋      | 343/938 [00:23<00:41, 14.37it/s, loss=0.741, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  37%|███▋      | 344/938 [00:23<00:41, 14.36it/s, loss=0.741, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  37%|███▋      | 344/938 [00:23<00:41, 14.36it/s, loss=0.73, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  37%|███▋      | 345/938 [00:24<00:41, 14.36it/s, loss=0.731, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  37%|███▋      | 346/938 [00:24<00:41, 14.37it/s, loss=0.732, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  37%|███▋      | 347/938 [00:24<00:41, 14.37it/s, loss=0.735, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  37%|███▋      | 348/938 [00:24<00:41, 14.37it/s, loss=0.735, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  37%|███▋      | 348/938 [00:24<00:41, 14.36it/s, loss=0.743, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  37%|███▋      | 349/938 [00:24<00:40, 14.37it/s, loss=0.735, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  37%|███▋      | 350/938 [00:24<00:40, 14.36it/s, loss=0.728, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  37%|███▋      | 351/938 [00:24<00:40, 14.36it/s, loss=0.726, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  38%|███▊      | 352/938 [00:24<00:40, 14.37it/s, loss=0.726, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  38%|███▊      | 352/938 [00:24<00:40, 14.37it/s, loss=0.723, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  38%|███▊      | 353/938 [00:24<00:40, 14.37it/s, loss=0.721, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  38%|███▊      | 354/938 [00:24<00:40, 14.37it/s, loss=0.72, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  38%|███▊      | 355/938 [00:24<00:40, 14.38it/s, loss=0.713, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  38%|███▊      | 356/938 [00:24<00:40, 14.37it/s, loss=0.713, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  38%|███▊      | 356/938 [00:24<00:40, 14.37it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  38%|███▊      | 357/938 [00:24<00:40, 14.38it/s, loss=0.707, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  38%|███▊      | 358/938 [00:24<00:40, 14.37it/s, loss=0.715, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  38%|███▊      | 359/938 [00:24<00:40, 14.37it/s, loss=0.702, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  38%|███▊      | 360/938 [00:25<00:40, 14.37it/s, loss=0.702, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  38%|███▊      | 360/938 [00:25<00:40, 14.36it/s, loss=0.699, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  38%|███▊      | 361/938 [00:25<00:40, 14.37it/s, loss=0.701, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  39%|███▊      | 362/938 [00:25<00:40, 14.37it/s, loss=0.696, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  39%|███▊      | 363/938 [00:25<00:40, 14.36it/s, loss=0.697, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  39%|███▉      | 364/938 [00:25<00:40, 14.35it/s, loss=0.697, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  39%|███▉      | 364/938 [00:25<00:40, 14.35it/s, loss=0.704, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  39%|███▉      | 365/938 [00:25<00:39, 14.35it/s, loss=0.707, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  39%|███▉      | 366/938 [00:25<00:39, 14.35it/s, loss=0.71, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  39%|███▉      | 367/938 [00:25<00:39, 14.35it/s, loss=0.714, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  39%|███▉      | 368/938 [00:25<00:39, 14.35it/s, loss=0.714, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  39%|███▉      | 368/938 [00:25<00:39, 14.35it/s, loss=0.714, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  39%|███▉      | 369/938 [00:25<00:39, 14.35it/s, loss=0.722, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  39%|███▉      | 370/938 [00:25<00:39, 14.34it/s, loss=0.727, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  40%|███▉      | 371/938 [00:25<00:39, 14.35it/s, loss=0.725, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  40%|███▉      | 372/938 [00:25<00:39, 14.35it/s, loss=0.725, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  40%|███▉      | 372/938 [00:25<00:39, 14.35it/s, loss=0.726, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  40%|███▉      | 373/938 [00:26<00:39, 14.34it/s, loss=0.723, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  40%|███▉      | 374/938 [00:26<00:39, 14.33it/s, loss=0.72, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  40%|███▉      | 375/938 [00:26<00:39, 14.33it/s, loss=0.725, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  40%|████      | 376/938 [00:26<00:39, 14.33it/s, loss=0.725, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  40%|████      | 376/938 [00:26<00:39, 14.33it/s, loss=0.726, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  40%|████      | 377/938 [00:26<00:39, 14.33it/s, loss=0.722, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  40%|████      | 378/938 [00:26<00:39, 14.31it/s, loss=0.724, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  40%|████      | 379/938 [00:26<00:39, 14.31it/s, loss=0.733, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  41%|████      | 380/938 [00:26<00:38, 14.32it/s, loss=0.733, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  41%|████      | 380/938 [00:26<00:38, 14.32it/s, loss=0.741, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  41%|████      | 381/938 [00:26<00:38, 14.33it/s, loss=0.74, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  41%|████      | 382/938 [00:26<00:38, 14.33it/s, loss=0.741, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  41%|████      | 383/938 [00:26<00:38, 14.34it/s, loss=0.74, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  41%|████      | 384/938 [00:26<00:38, 14.34it/s, loss=0.74, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  41%|████      | 384/938 [00:26<00:38, 14.34it/s, loss=0.739, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  41%|████      | 385/938 [00:26<00:38, 14.34it/s, loss=0.739, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  41%|████      | 386/938 [00:26<00:38, 14.34it/s, loss=0.737, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  41%|████▏     | 387/938 [00:26<00:38, 14.35it/s, loss=0.736, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  41%|████▏     | 388/938 [00:27<00:38, 14.35it/s, loss=0.736, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  41%|████▏     | 388/938 [00:27<00:38, 14.35it/s, loss=0.73, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  41%|████▏     | 389/938 [00:27<00:38, 14.35it/s, loss=0.734, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  42%|████▏     | 390/938 [00:27<00:38, 14.35it/s, loss=0.735, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  42%|████▏     | 391/938 [00:27<00:38, 14.35it/s, loss=0.736, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  42%|████▏     | 392/938 [00:27<00:38, 14.35it/s, loss=0.736, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  42%|████▏     | 392/938 [00:27<00:38, 14.35it/s, loss=0.734, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  42%|████▏     | 393/938 [00:27<00:37, 14.35it/s, loss=0.742, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  42%|████▏     | 394/938 [00:27<00:37, 14.36it/s, loss=0.735, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  42%|████▏     | 395/938 [00:27<00:37, 14.36it/s, loss=0.728, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  42%|████▏     | 396/938 [00:27<00:37, 14.36it/s, loss=0.728, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  42%|████▏     | 396/938 [00:27<00:37, 14.36it/s, loss=0.728, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  42%|████▏     | 397/938 [00:27<00:37, 14.36it/s, loss=0.731, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  42%|████▏     | 398/938 [00:27<00:37, 14.36it/s, loss=0.722, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  43%|████▎     | 399/938 [00:27<00:37, 14.36it/s, loss=0.729, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  43%|████▎     | 400/938 [00:27<00:37, 14.36it/s, loss=0.729, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  43%|████▎     | 400/938 [00:27<00:37, 14.36it/s, loss=0.723, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  43%|████▎     | 401/938 [00:27<00:37, 14.35it/s, loss=0.715, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  43%|████▎     | 402/938 [00:28<00:37, 14.35it/s, loss=0.717, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  43%|████▎     | 403/938 [00:28<00:37, 14.36it/s, loss=0.713, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  43%|████▎     | 404/938 [00:28<00:37, 14.36it/s, loss=0.713, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  43%|████▎     | 404/938 [00:28<00:37, 14.36it/s, loss=0.701, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  43%|████▎     | 405/938 [00:28<00:37, 14.36it/s, loss=0.696, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  43%|████▎     | 406/938 [00:28<00:37, 14.36it/s, loss=0.701, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  43%|████▎     | 407/938 [00:28<00:36, 14.36it/s, loss=0.706, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  43%|████▎     | 408/938 [00:28<00:36, 14.35it/s, loss=0.706, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  43%|████▎     | 408/938 [00:28<00:36, 14.35it/s, loss=0.705, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  44%|████▎     | 409/938 [00:28<00:36, 14.34it/s, loss=0.699, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  44%|████▎     | 410/938 [00:28<00:36, 14.32it/s, loss=0.699, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  44%|████▍     | 411/938 [00:28<00:36, 14.32it/s, loss=0.706, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  44%|████▍     | 412/938 [00:28<00:36, 14.32it/s, loss=0.706, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  44%|████▍     | 412/938 [00:28<00:36, 14.32it/s, loss=0.705, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  44%|████▍     | 413/938 [00:28<00:36, 14.32it/s, loss=0.695, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  44%|████▍     | 414/938 [00:28<00:36, 14.32it/s, loss=0.703, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  44%|████▍     | 415/938 [00:28<00:36, 14.32it/s, loss=0.713, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  44%|████▍     | 416/938 [00:29<00:36, 14.32it/s, loss=0.713, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  44%|████▍     | 416/938 [00:29<00:36, 14.32it/s, loss=0.721, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  44%|████▍     | 417/938 [00:29<00:36, 14.32it/s, loss=0.73, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  45%|████▍     | 418/938 [00:29<00:36, 14.32it/s, loss=0.733, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  45%|████▍     | 419/938 [00:29<00:36, 14.32it/s, loss=0.722, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  45%|████▍     | 420/938 [00:29<00:36, 14.30it/s, loss=0.722, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  45%|████▍     | 420/938 [00:29<00:36, 14.30it/s, loss=0.722, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  45%|████▍     | 421/938 [00:29<00:36, 14.31it/s, loss=0.725, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  45%|████▍     | 422/938 [00:29<00:36, 14.31it/s, loss=0.721, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  45%|████▌     | 423/938 [00:29<00:35, 14.32it/s, loss=0.728, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  45%|████▌     | 424/938 [00:29<00:35, 14.32it/s, loss=0.728, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  45%|████▌     | 424/938 [00:29<00:35, 14.32it/s, loss=0.729, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  45%|████▌     | 425/938 [00:29<00:35, 14.31it/s, loss=0.728, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  45%|████▌     | 426/938 [00:29<00:35, 14.31it/s, loss=0.733, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  46%|████▌     | 427/938 [00:29<00:35, 14.30it/s, loss=0.726, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  46%|████▌     | 428/938 [00:29<00:35, 14.31it/s, loss=0.726, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  46%|████▌     | 428/938 [00:29<00:35, 14.31it/s, loss=0.725, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  46%|████▌     | 429/938 [00:29<00:35, 14.31it/s, loss=0.719, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  46%|████▌     | 430/938 [00:30<00:35, 14.31it/s, loss=0.715, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  46%|████▌     | 431/938 [00:30<00:35, 14.30it/s, loss=0.708, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  46%|████▌     | 432/938 [00:30<00:35, 14.29it/s, loss=0.708, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  46%|████▌     | 432/938 [00:30<00:35, 14.29it/s, loss=0.713, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  46%|████▌     | 433/938 [00:30<00:35, 14.29it/s, loss=0.708, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  46%|████▋     | 434/938 [00:30<00:35, 14.30it/s, loss=0.706, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  46%|████▋     | 435/938 [00:30<00:35, 14.30it/s, loss=0.706, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  46%|████▋     | 436/938 [00:30<00:35, 14.29it/s, loss=0.706, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  46%|████▋     | 436/938 [00:30<00:35, 14.29it/s, loss=0.703, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  47%|████▋     | 437/938 [00:30<00:35, 14.30it/s, loss=0.696, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  47%|████▋     | 438/938 [00:30<00:34, 14.29it/s, loss=0.695, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  47%|████▋     | 439/938 [00:30<00:34, 14.30it/s, loss=0.697, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  47%|████▋     | 440/938 [00:30<00:34, 14.30it/s, loss=0.697, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  47%|████▋     | 440/938 [00:30<00:34, 14.30it/s, loss=0.7, v_num=12, val_rmse=0.693, train_rmse=1.250]  
Epoch 1:  47%|████▋     | 441/938 [00:30<00:34, 14.30it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  47%|████▋     | 442/938 [00:30<00:34, 14.30it/s, loss=0.712, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  47%|████▋     | 443/938 [00:30<00:34, 14.30it/s, loss=0.715, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  47%|████▋     | 444/938 [00:31<00:34, 14.30it/s, loss=0.715, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  47%|████▋     | 444/938 [00:31<00:34, 14.30it/s, loss=0.719, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  47%|████▋     | 445/938 [00:31<00:34, 14.30it/s, loss=0.73, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  48%|████▊     | 446/938 [00:31<00:34, 14.30it/s, loss=0.718, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  48%|████▊     | 447/938 [00:31<00:34, 14.30it/s, loss=0.717, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  48%|████▊     | 448/938 [00:31<00:34, 14.30it/s, loss=0.717, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  48%|████▊     | 448/938 [00:31<00:34, 14.30it/s, loss=0.719, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  48%|████▊     | 449/938 [00:31<00:34, 14.30it/s, loss=0.724, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  48%|████▊     | 450/938 [00:31<00:34, 14.30it/s, loss=0.729, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  48%|████▊     | 451/938 [00:31<00:34, 14.30it/s, loss=0.73, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  48%|████▊     | 452/938 [00:31<00:33, 14.30it/s, loss=0.73, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  48%|████▊     | 452/938 [00:31<00:33, 14.30it/s, loss=0.727, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  48%|████▊     | 453/938 [00:31<00:33, 14.30it/s, loss=0.736, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  48%|████▊     | 454/938 [00:31<00:33, 14.31it/s, loss=0.726, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  49%|████▊     | 455/938 [00:31<00:33, 14.31it/s, loss=0.718, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  49%|████▊     | 456/938 [00:31<00:33, 14.31it/s, loss=0.718, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  49%|████▊     | 456/938 [00:31<00:33, 14.31it/s, loss=0.711, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  49%|████▊     | 457/938 [00:31<00:33, 14.31it/s, loss=0.712, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  49%|████▉     | 458/938 [00:31<00:33, 14.31it/s, loss=0.713, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  49%|████▉     | 459/938 [00:32<00:33, 14.30it/s, loss=0.717, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  49%|████▉     | 460/938 [00:32<00:33, 14.30it/s, loss=0.717, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  49%|████▉     | 460/938 [00:32<00:33, 14.30it/s, loss=0.716, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  49%|████▉     | 461/938 [00:32<00:33, 14.31it/s, loss=0.711, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  49%|████▉     | 462/938 [00:32<00:33, 14.31it/s, loss=0.708, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  49%|████▉     | 463/938 [00:32<00:33, 14.31it/s, loss=0.7, v_num=12, val_rmse=0.693, train_rmse=1.250]  
Epoch 1:  49%|████▉     | 464/938 [00:32<00:33, 14.32it/s, loss=0.7, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  49%|████▉     | 464/938 [00:32<00:33, 14.32it/s, loss=0.706, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  50%|████▉     | 465/938 [00:32<00:33, 14.31it/s, loss=0.705, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  50%|████▉     | 466/938 [00:32<00:32, 14.31it/s, loss=0.706, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  50%|████▉     | 467/938 [00:32<00:32, 14.32it/s, loss=0.71, v_num=12, val_rmse=0.693, train_rmse=1.250] 
Epoch 1:  50%|████▉     | 468/938 [00:32<00:32, 14.32it/s, loss=0.71, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  50%|████▉     | 468/938 [00:32<00:32, 14.32it/s, loss=0.71, v_num=12, val_rmse=0.693, train_rmse=1.250]
Epoch 1:  50%|█████     | 469/938 [00:32<00:32, 14.33it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]
Epoch 1:  50%|█████     | 472/938 [00:32<00:32, 14.38it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:   1%|          | 3/469 [00:00<00:19, 23.47it/s]

Validating:   1%|▏         | 6/469 [00:00<00:19, 23.65it/s]
Epoch 1:  51%|█████     | 476/938 [00:32<00:32, 14.43it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:   2%|▏         | 9/469 [00:00<00:18, 24.79it/s]
Epoch 1:  51%|█████     | 480/938 [00:33<00:31, 14.49it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:   3%|▎         | 12/469 [00:00<00:18, 24.59it/s]
Epoch 1:  52%|█████▏    | 484/938 [00:33<00:31, 14.54it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:   3%|▎         | 15/469 [00:00<00:18, 24.68it/s]

Validating:   4%|▍         | 18/469 [00:00<00:17, 25.87it/s]
Epoch 1:  52%|█████▏    | 488/938 [00:33<00:30, 14.59it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:   4%|▍         | 21/469 [00:00<00:17, 25.76it/s]
Epoch 1:  52%|█████▏    | 492/938 [00:33<00:30, 14.64it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:   5%|▌         | 24/469 [00:00<00:17, 25.45it/s]
Epoch 1:  53%|█████▎    | 496/938 [00:33<00:30, 14.69it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:   6%|▌         | 27/469 [00:01<00:17, 25.88it/s]

Validating:   6%|▋         | 30/469 [00:01<00:16, 25.98it/s]
Epoch 1:  53%|█████▎    | 500/938 [00:33<00:29, 14.75it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:   7%|▋         | 33/469 [00:01<00:16, 26.18it/s]
Epoch 1:  54%|█████▎    | 504/938 [00:34<00:29, 14.80it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:   8%|▊         | 36/469 [00:01<00:16, 26.46it/s]
Epoch 1:  54%|█████▍    | 508/938 [00:34<00:28, 14.85it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:   8%|▊         | 39/469 [00:01<00:16, 26.81it/s]

Validating:   9%|▉         | 42/469 [00:01<00:16, 25.36it/s]
Epoch 1:  55%|█████▍    | 512/938 [00:34<00:28, 14.90it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  10%|▉         | 45/469 [00:01<00:16, 25.41it/s]
Epoch 1:  55%|█████▌    | 516/938 [00:34<00:28, 14.94it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  10%|█         | 48/469 [00:01<00:16, 25.07it/s]
Epoch 1:  55%|█████▌    | 520/938 [00:34<00:27, 14.99it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  11%|█         | 51/469 [00:02<00:16, 25.51it/s]

Validating:  12%|█▏        | 54/469 [00:02<00:16, 24.83it/s]
Epoch 1:  56%|█████▌    | 524/938 [00:34<00:27, 15.03it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  12%|█▏        | 57/469 [00:02<00:16, 25.09it/s]
Epoch 1:  56%|█████▋    | 528/938 [00:35<00:27, 15.08it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  13%|█▎        | 60/469 [00:02<00:17, 23.78it/s]
Epoch 1:  57%|█████▋    | 532/938 [00:35<00:26, 15.12it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  13%|█▎        | 63/469 [00:02<00:16, 24.29it/s]

Validating:  14%|█▍        | 66/469 [00:02<00:16, 24.06it/s]
Epoch 1:  57%|█████▋    | 536/938 [00:35<00:26, 15.16it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  15%|█▍        | 69/469 [00:02<00:15, 25.24it/s]
Epoch 1:  58%|█████▊    | 540/938 [00:35<00:26, 15.21it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  15%|█▌        | 72/469 [00:02<00:15, 25.93it/s]
Epoch 1:  58%|█████▊    | 544/938 [00:35<00:25, 15.26it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  16%|█▌        | 75/469 [00:02<00:15, 25.90it/s]

Validating:  17%|█▋        | 78/469 [00:03<00:14, 26.88it/s]
Epoch 1:  58%|█████▊    | 548/938 [00:35<00:25, 15.31it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  17%|█▋        | 81/469 [00:03<00:14, 26.16it/s]
Epoch 1:  59%|█████▉    | 552/938 [00:35<00:25, 15.35it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  18%|█▊        | 84/469 [00:03<00:15, 25.66it/s]
Epoch 1:  59%|█████▉    | 556/938 [00:36<00:24, 15.40it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  19%|█▊        | 87/469 [00:03<00:14, 26.10it/s]

Validating:  19%|█▉        | 90/469 [00:03<00:14, 25.50it/s]
Epoch 1:  60%|█████▉    | 560/938 [00:36<00:24, 15.44it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  20%|█▉        | 93/469 [00:03<00:14, 25.42it/s]
Epoch 1:  60%|██████    | 564/938 [00:36<00:24, 15.48it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  20%|██        | 96/469 [00:03<00:15, 24.60it/s]
Epoch 1:  61%|██████    | 568/938 [00:36<00:23, 15.52it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  21%|██        | 99/469 [00:03<00:14, 24.72it/s]

Validating:  22%|██▏       | 102/469 [00:04<00:14, 25.11it/s]
Epoch 1:  61%|██████    | 572/938 [00:36<00:23, 15.56it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  22%|██▏       | 105/469 [00:04<00:15, 23.84it/s]
Epoch 1:  61%|██████▏   | 576/938 [00:36<00:23, 15.60it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  23%|██▎       | 108/469 [00:04<00:15, 24.02it/s]
Epoch 1:  62%|██████▏   | 580/938 [00:37<00:22, 15.64it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  24%|██▎       | 111/469 [00:04<00:14, 24.13it/s]

Validating:  24%|██▍       | 114/469 [00:04<00:14, 23.92it/s]
Epoch 1:  62%|██████▏   | 584/938 [00:37<00:22, 15.67it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  25%|██▍       | 117/469 [00:04<00:14, 24.37it/s]
Epoch 1:  63%|██████▎   | 588/938 [00:37<00:22, 15.71it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  26%|██▌       | 120/469 [00:04<00:13, 24.96it/s]
Epoch 1:  63%|██████▎   | 592/938 [00:37<00:21, 15.75it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  26%|██▌       | 123/469 [00:04<00:13, 24.79it/s]

Validating:  27%|██▋       | 126/469 [00:05<00:15, 22.54it/s]
Epoch 1:  64%|██████▎   | 596/938 [00:37<00:21, 15.77it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  28%|██▊       | 129/469 [00:05<00:14, 23.30it/s]
Epoch 1:  64%|██████▍   | 600/938 [00:37<00:21, 15.82it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  28%|██▊       | 132/469 [00:05<00:13, 24.57it/s]
Epoch 1:  64%|██████▍   | 604/938 [00:38<00:21, 15.86it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  29%|██▉       | 135/469 [00:05<00:13, 25.51it/s]

Validating:  29%|██▉       | 138/469 [00:05<00:13, 25.41it/s]
Epoch 1:  65%|██████▍   | 608/938 [00:38<00:20, 15.90it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  30%|███       | 141/469 [00:05<00:13, 24.91it/s]
Epoch 1:  65%|██████▌   | 612/938 [00:38<00:20, 15.94it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  31%|███       | 144/469 [00:05<00:12, 25.37it/s]
Epoch 1:  66%|██████▌   | 616/938 [00:38<00:20, 15.98it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  31%|███▏      | 147/469 [00:05<00:12, 25.90it/s]

Validating:  32%|███▏      | 150/469 [00:05<00:12, 26.03it/s]
Epoch 1:  66%|██████▌   | 620/938 [00:38<00:19, 16.02it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  33%|███▎      | 153/469 [00:06<00:12, 25.98it/s]
Epoch 1:  67%|██████▋   | 624/938 [00:38<00:19, 16.06it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  33%|███▎      | 156/469 [00:06<00:11, 26.13it/s]
Epoch 1:  67%|██████▋   | 628/938 [00:39<00:19, 16.10it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  34%|███▍      | 159/469 [00:06<00:11, 26.73it/s]

Validating:  35%|███▍      | 162/469 [00:06<00:11, 27.02it/s]
Epoch 1:  67%|██████▋   | 632/938 [00:39<00:18, 16.15it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  35%|███▌      | 165/469 [00:06<00:11, 27.07it/s]
Epoch 1:  68%|██████▊   | 636/938 [00:39<00:18, 16.19it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  36%|███▌      | 168/469 [00:06<00:11, 26.91it/s]
Epoch 1:  68%|██████▊   | 640/938 [00:39<00:18, 16.23it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  36%|███▋      | 171/469 [00:06<00:11, 26.80it/s]

Validating:  37%|███▋      | 174/469 [00:06<00:10, 27.59it/s]
Epoch 1:  69%|██████▊   | 644/938 [00:39<00:18, 16.27it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  38%|███▊      | 177/469 [00:06<00:10, 27.53it/s]
Epoch 1:  69%|██████▉   | 648/938 [00:39<00:17, 16.31it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  38%|███▊      | 180/469 [00:07<00:10, 27.31it/s]
Epoch 1:  70%|██████▉   | 652/938 [00:39<00:17, 16.35it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  39%|███▉      | 183/469 [00:07<00:11, 25.63it/s]

Validating:  40%|███▉      | 186/469 [00:07<00:10, 25.80it/s]
Epoch 1:  70%|██████▉   | 656/938 [00:40<00:17, 16.38it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  40%|████      | 189/469 [00:07<00:11, 25.38it/s]
Epoch 1:  70%|███████   | 660/938 [00:40<00:16, 16.41it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  41%|████      | 192/469 [00:07<00:11, 24.87it/s]
Epoch 1:  71%|███████   | 664/938 [00:40<00:16, 16.44it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  42%|████▏     | 195/469 [00:07<00:11, 24.41it/s]

Validating:  42%|████▏     | 198/469 [00:07<00:10, 24.92it/s]
Epoch 1:  71%|███████   | 668/938 [00:40<00:16, 16.48it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  43%|████▎     | 201/469 [00:07<00:10, 25.26it/s]
Epoch 1:  72%|███████▏  | 672/938 [00:40<00:16, 16.52it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  43%|████▎     | 204/469 [00:08<00:10, 25.71it/s]
Epoch 1:  72%|███████▏  | 676/938 [00:40<00:15, 16.55it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  44%|████▍     | 207/469 [00:08<00:10, 25.92it/s]

Validating:  45%|████▍     | 210/469 [00:08<00:10, 25.31it/s]
Epoch 1:  72%|███████▏  | 680/938 [00:41<00:15, 16.58it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  45%|████▌     | 213/469 [00:08<00:10, 25.52it/s]
Epoch 1:  73%|███████▎  | 684/938 [00:41<00:15, 16.62it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  46%|████▌     | 216/469 [00:08<00:09, 25.74it/s]
Epoch 1:  73%|███████▎  | 688/938 [00:41<00:15, 16.65it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  47%|████▋     | 219/469 [00:08<00:09, 25.86it/s]

Validating:  47%|████▋     | 222/469 [00:08<00:09, 25.57it/s]
Epoch 1:  74%|███████▍  | 692/938 [00:41<00:14, 16.69it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  48%|████▊     | 225/469 [00:08<00:09, 24.69it/s]
Epoch 1:  74%|███████▍  | 696/938 [00:41<00:14, 16.72it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  49%|████▊     | 228/469 [00:09<00:10, 23.00it/s]
Epoch 1:  75%|███████▍  | 700/938 [00:41<00:14, 16.73it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  49%|████▉     | 231/469 [00:09<00:09, 23.91it/s]

Validating:  50%|████▉     | 234/469 [00:09<00:09, 24.32it/s]
Epoch 1:  75%|███████▌  | 704/938 [00:41<00:13, 16.77it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  51%|█████     | 237/469 [00:09<00:09, 24.82it/s]
Epoch 1:  75%|███████▌  | 708/938 [00:42<00:13, 16.80it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  51%|█████     | 240/469 [00:09<00:09, 24.01it/s]
Epoch 1:  76%|███████▌  | 712/938 [00:42<00:13, 16.83it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  52%|█████▏    | 243/469 [00:09<00:09, 24.59it/s]

Validating:  52%|█████▏    | 246/469 [00:09<00:08, 25.36it/s]
Epoch 1:  76%|███████▋  | 716/938 [00:42<00:13, 16.86it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  53%|█████▎    | 249/469 [00:09<00:08, 25.58it/s]
Epoch 1:  77%|███████▋  | 720/938 [00:42<00:12, 16.90it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  54%|█████▎    | 252/469 [00:09<00:08, 26.33it/s]
Epoch 1:  77%|███████▋  | 724/938 [00:42<00:12, 16.93it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  54%|█████▍    | 255/469 [00:10<00:08, 25.53it/s]

Validating:  55%|█████▌    | 258/469 [00:10<00:08, 25.60it/s]
Epoch 1:  78%|███████▊  | 728/938 [00:42<00:12, 16.96it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  56%|█████▌    | 261/469 [00:10<00:08, 25.85it/s]
Epoch 1:  78%|███████▊  | 732/938 [00:43<00:12, 17.00it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  56%|█████▋    | 264/469 [00:10<00:08, 25.39it/s]
Epoch 1:  78%|███████▊  | 736/938 [00:43<00:11, 17.03it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  57%|█████▋    | 267/469 [00:10<00:07, 26.10it/s]

Validating:  58%|█████▊    | 270/469 [00:10<00:07, 25.61it/s]
Epoch 1:  79%|███████▉  | 740/938 [00:43<00:11, 17.06it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  58%|█████▊    | 273/469 [00:10<00:08, 24.42it/s]
Epoch 1:  79%|███████▉  | 744/938 [00:43<00:11, 17.08it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  59%|█████▉    | 276/469 [00:10<00:07, 24.43it/s]
Epoch 1:  80%|███████▉  | 748/938 [00:43<00:11, 17.11it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  59%|█████▉    | 279/469 [00:11<00:07, 24.97it/s]

Validating:  60%|██████    | 282/469 [00:11<00:07, 25.28it/s]
Epoch 1:  80%|████████  | 752/938 [00:43<00:10, 17.14it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  61%|██████    | 285/469 [00:11<00:06, 26.30it/s]
Epoch 1:  81%|████████  | 756/938 [00:44<00:10, 17.17it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  61%|██████▏   | 288/469 [00:11<00:06, 26.11it/s]
Epoch 1:  81%|████████  | 760/938 [00:44<00:10, 17.20it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  62%|██████▏   | 291/469 [00:11<00:06, 25.76it/s]

Validating:  63%|██████▎   | 294/469 [00:11<00:07, 23.76it/s]
Epoch 1:  81%|████████▏ | 764/938 [00:44<00:10, 17.22it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  63%|██████▎   | 297/469 [00:11<00:06, 25.01it/s]
Epoch 1:  82%|████████▏ | 768/938 [00:44<00:09, 17.26it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  64%|██████▍   | 300/469 [00:11<00:06, 25.92it/s]
Epoch 1:  82%|████████▏ | 772/938 [00:44<00:09, 17.29it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  65%|██████▍   | 303/469 [00:11<00:06, 25.69it/s]

Validating:  65%|██████▌   | 306/469 [00:12<00:06, 26.06it/s]
Epoch 1:  83%|████████▎ | 776/938 [00:44<00:09, 17.32it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  66%|██████▌   | 309/469 [00:12<00:06, 25.97it/s]
Epoch 1:  83%|████████▎ | 780/938 [00:44<00:09, 17.35it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  67%|██████▋   | 312/469 [00:12<00:06, 25.96it/s]
Epoch 1:  84%|████████▎ | 784/938 [00:45<00:08, 17.38it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  67%|██████▋   | 315/469 [00:12<00:05, 26.15it/s]

Validating:  68%|██████▊   | 318/469 [00:12<00:05, 25.94it/s]
Epoch 1:  84%|████████▍ | 788/938 [00:45<00:08, 17.41it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  68%|██████▊   | 321/469 [00:12<00:05, 24.86it/s]
Epoch 1:  84%|████████▍ | 792/938 [00:45<00:08, 17.43it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  69%|██████▉   | 324/469 [00:12<00:05, 24.83it/s]
Epoch 1:  85%|████████▍ | 796/938 [00:45<00:08, 17.46it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  70%|██████▉   | 327/469 [00:12<00:05, 25.33it/s]

Validating:  70%|███████   | 330/469 [00:13<00:05, 26.16it/s]
Epoch 1:  85%|████████▌ | 800/938 [00:45<00:07, 17.49it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  71%|███████   | 333/469 [00:13<00:05, 26.02it/s]
Epoch 1:  86%|████████▌ | 804/938 [00:45<00:07, 17.51it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  72%|███████▏  | 336/469 [00:13<00:05, 24.72it/s]
Epoch 1:  86%|████████▌ | 808/938 [00:46<00:07, 17.54it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  72%|███████▏  | 339/469 [00:13<00:05, 25.29it/s]

Validating:  73%|███████▎  | 342/469 [00:13<00:04, 25.98it/s]
Epoch 1:  87%|████████▋ | 812/938 [00:46<00:07, 17.57it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  74%|███████▎  | 345/469 [00:13<00:04, 26.06it/s]
Epoch 1:  87%|████████▋ | 816/938 [00:46<00:06, 17.60it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  74%|███████▍  | 348/469 [00:13<00:04, 26.03it/s]
Epoch 1:  87%|████████▋ | 820/938 [00:46<00:06, 17.63it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  75%|███████▍  | 351/469 [00:13<00:04, 26.97it/s]

Validating:  75%|███████▌  | 354/469 [00:13<00:04, 26.24it/s]
Epoch 1:  88%|████████▊ | 824/938 [00:46<00:06, 17.66it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  76%|███████▌  | 357/469 [00:14<00:04, 25.73it/s]
Epoch 1:  88%|████████▊ | 828/938 [00:46<00:06, 17.68it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  77%|███████▋  | 360/469 [00:14<00:04, 25.30it/s]
Epoch 1:  89%|████████▊ | 832/938 [00:47<00:05, 17.70it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  77%|███████▋  | 363/469 [00:14<00:04, 24.70it/s]

Validating:  78%|███████▊  | 366/469 [00:14<00:04, 24.75it/s]
Epoch 1:  89%|████████▉ | 836/938 [00:47<00:05, 17.73it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  79%|███████▊  | 369/469 [00:14<00:03, 25.41it/s]
Epoch 1:  90%|████████▉ | 840/938 [00:47<00:05, 17.75it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  79%|███████▉  | 372/469 [00:14<00:03, 25.64it/s]
Epoch 1:  90%|████████▉ | 844/938 [00:47<00:05, 17.78it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  80%|███████▉  | 375/469 [00:14<00:03, 25.85it/s]

Validating:  81%|████████  | 378/469 [00:14<00:03, 24.91it/s]
Epoch 1:  90%|█████████ | 848/938 [00:47<00:05, 17.80it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  81%|████████  | 381/469 [00:15<00:03, 25.51it/s]
Epoch 1:  91%|█████████ | 852/938 [00:47<00:04, 17.83it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  82%|████████▏ | 384/469 [00:15<00:03, 26.08it/s]
Epoch 1:  91%|█████████▏| 856/938 [00:47<00:04, 17.86it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  83%|████████▎ | 387/469 [00:15<00:03, 25.96it/s]

Validating:  83%|████████▎ | 390/469 [00:15<00:03, 25.80it/s]
Epoch 1:  92%|█████████▏| 860/938 [00:48<00:04, 17.88it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  84%|████████▍ | 393/469 [00:15<00:02, 25.60it/s]
Epoch 1:  92%|█████████▏| 864/938 [00:48<00:04, 17.91it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  84%|████████▍ | 396/469 [00:15<00:02, 25.42it/s]
Epoch 1:  93%|█████████▎| 868/938 [00:48<00:03, 17.93it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  85%|████████▌ | 399/469 [00:15<00:02, 24.53it/s]

Validating:  86%|████████▌ | 402/469 [00:15<00:02, 25.23it/s]
Epoch 1:  93%|█████████▎| 872/938 [00:48<00:03, 17.95it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  86%|████████▋ | 405/469 [00:15<00:02, 25.71it/s]
Epoch 1:  93%|█████████▎| 876/938 [00:48<00:03, 17.98it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  87%|████████▋ | 408/469 [00:16<00:02, 25.70it/s]
Epoch 1:  94%|█████████▍| 880/938 [00:48<00:03, 18.01it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  88%|████████▊ | 411/469 [00:16<00:02, 26.27it/s]

Validating:  88%|████████▊ | 414/469 [00:16<00:02, 26.91it/s]
Epoch 1:  94%|█████████▍| 884/938 [00:49<00:02, 18.04it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  89%|████████▉ | 417/469 [00:16<00:01, 26.93it/s]
Epoch 1:  95%|█████████▍| 888/938 [00:49<00:02, 18.06it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  90%|████████▉ | 420/469 [00:16<00:01, 25.19it/s]
Epoch 1:  95%|█████████▌| 892/938 [00:49<00:02, 18.08it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  90%|█████████ | 423/469 [00:16<00:01, 24.91it/s]

Validating:  91%|█████████ | 426/469 [00:16<00:01, 24.98it/s]
Epoch 1:  96%|█████████▌| 896/938 [00:49<00:02, 18.10it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  91%|█████████▏| 429/469 [00:16<00:01, 24.14it/s]
Epoch 1:  96%|█████████▌| 900/938 [00:49<00:02, 18.11it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  92%|█████████▏| 432/469 [00:17<00:01, 23.24it/s]
Epoch 1:  96%|█████████▋| 904/938 [00:49<00:01, 18.13it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  93%|█████████▎| 435/469 [00:17<00:01, 23.64it/s]

Validating:  93%|█████████▎| 438/469 [00:17<00:01, 22.86it/s]
Epoch 1:  97%|█████████▋| 908/938 [00:50<00:01, 18.15it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  94%|█████████▍| 441/469 [00:17<00:01, 23.50it/s]
Epoch 1:  97%|█████████▋| 912/938 [00:50<00:01, 18.17it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  95%|█████████▍| 444/469 [00:17<00:01, 24.08it/s]
Epoch 1:  98%|█████████▊| 916/938 [00:50<00:01, 18.19it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  95%|█████████▌| 447/469 [00:17<00:00, 24.51it/s]

Validating:  96%|█████████▌| 450/469 [00:17<00:00, 24.31it/s]
Epoch 1:  98%|█████████▊| 920/938 [00:50<00:00, 18.21it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  97%|█████████▋| 453/469 [00:17<00:00, 25.03it/s]
Epoch 1:  99%|█████████▊| 924/938 [00:50<00:00, 18.23it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  97%|█████████▋| 456/469 [00:18<00:00, 25.63it/s]
Epoch 1:  99%|█████████▉| 928/938 [00:50<00:00, 18.26it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  98%|█████████▊| 459/469 [00:18<00:00, 25.13it/s]
Epoch 1:  99%|█████████▉| 932/938 [00:50<00:00, 18.29it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating:  99%|█████████▊| 463/469 [00:18<00:00, 25.99it/s]

Validating:  99%|█████████▉| 466/469 [00:18<00:00, 26.35it/s]
Epoch 1: 100%|█████████▉| 936/938 [00:51<00:00, 18.31it/s, loss=0.709, v_num=12, val_rmse=0.693, train_rmse=1.250]

Validating: 100%|██████████| 469/469 [00:18<00:00, 26.56it/s]
Epoch 1: 100%|██████████| 938/938 [00:51<00:00, 18.30it/s, loss=0.709, v_num=12, val_rmse=0.568, train_rmse=1.250]

                                                             
Epoch 1: 100%|██████████| 938/938 [00:51<00:00, 18.30it/s, loss=0.709, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 1:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.709, v_num=12, val_rmse=0.568, train_rmse=0.755]          
Epoch 2:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.709, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   0%|          | 1/938 [00:00<01:20, 11.66it/s, loss=0.709, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   0%|          | 2/938 [00:00<01:09, 13.51it/s, loss=0.708, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   0%|          | 3/938 [00:00<01:10, 13.28it/s, loss=0.714, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   0%|          | 4/938 [00:00<01:08, 13.56it/s, loss=0.714, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   0%|          | 4/938 [00:00<01:09, 13.53it/s, loss=0.717, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   1%|          | 5/938 [00:00<01:11, 13.12it/s, loss=0.718, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   1%|          | 6/938 [00:00<01:12, 12.92it/s, loss=0.723, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   1%|          | 7/938 [00:00<01:10, 13.12it/s, loss=0.721, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   1%|          | 8/938 [00:00<01:09, 13.37it/s, loss=0.721, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   1%|          | 8/938 [00:00<01:09, 13.36it/s, loss=0.715, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   1%|          | 9/938 [00:00<01:10, 13.24it/s, loss=0.719, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   1%|          | 10/938 [00:00<01:09, 13.33it/s, loss=0.72, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   1%|          | 11/938 [00:00<01:09, 13.38it/s, loss=0.724, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   1%|▏         | 12/938 [00:00<01:08, 13.55it/s, loss=0.724, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   1%|▏         | 12/938 [00:00<01:08, 13.54it/s, loss=0.719, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   1%|▏         | 13/938 [00:00<01:07, 13.63it/s, loss=0.724, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   1%|▏         | 14/938 [00:01<01:07, 13.73it/s, loss=0.728, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   2%|▏         | 15/938 [00:01<01:07, 13.67it/s, loss=0.722, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   2%|▏         | 16/938 [00:01<01:07, 13.66it/s, loss=0.722, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   2%|▏         | 16/938 [00:01<01:07, 13.65it/s, loss=0.712, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   2%|▏         | 17/938 [00:01<01:06, 13.76it/s, loss=0.711, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   2%|▏         | 18/938 [00:01<01:07, 13.72it/s, loss=0.716, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   2%|▏         | 19/938 [00:01<01:06, 13.79it/s, loss=0.712, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   2%|▏         | 20/938 [00:01<01:06, 13.85it/s, loss=0.712, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   2%|▏         | 20/938 [00:01<01:06, 13.84it/s, loss=0.709, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   2%|▏         | 21/938 [00:01<01:05, 14.05it/s, loss=0.706, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   2%|▏         | 22/938 [00:01<01:05, 13.98it/s, loss=0.712, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   2%|▏         | 23/938 [00:01<01:05, 14.02it/s, loss=0.715, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   3%|▎         | 24/938 [00:01<01:05, 14.03it/s, loss=0.715, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   3%|▎         | 24/938 [00:01<01:05, 14.02it/s, loss=0.709, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   3%|▎         | 25/938 [00:01<01:05, 13.85it/s, loss=0.711, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   3%|▎         | 26/938 [00:01<01:05, 13.93it/s, loss=0.707, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   3%|▎         | 27/938 [00:01<01:05, 13.98it/s, loss=0.707, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   3%|▎         | 28/938 [00:01<01:04, 14.01it/s, loss=0.707, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   3%|▎         | 28/938 [00:01<01:04, 14.01it/s, loss=0.714, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   3%|▎         | 29/938 [00:02<01:05, 13.85it/s, loss=0.705, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   3%|▎         | 30/938 [00:02<01:05, 13.88it/s, loss=0.705, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   3%|▎         | 31/938 [00:02<01:05, 13.82it/s, loss=0.701, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   3%|▎         | 32/938 [00:02<01:05, 13.75it/s, loss=0.701, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   3%|▎         | 32/938 [00:02<01:05, 13.75it/s, loss=0.71, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:   4%|▎         | 33/938 [00:02<01:06, 13.59it/s, loss=0.717, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   4%|▎         | 34/938 [00:02<01:06, 13.58it/s, loss=0.711, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   4%|▎         | 35/938 [00:02<01:06, 13.61it/s, loss=0.716, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   4%|▍         | 36/938 [00:02<01:06, 13.62it/s, loss=0.716, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   4%|▍         | 36/938 [00:02<01:06, 13.62it/s, loss=0.719, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   4%|▍         | 37/938 [00:02<01:06, 13.57it/s, loss=0.721, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   4%|▍         | 38/938 [00:02<01:06, 13.63it/s, loss=0.71, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:   4%|▍         | 39/938 [00:02<01:06, 13.56it/s, loss=0.71, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   4%|▍         | 40/938 [00:02<01:06, 13.58it/s, loss=0.71, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   4%|▍         | 40/938 [00:02<01:06, 13.57it/s, loss=0.713, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   4%|▍         | 41/938 [00:03<01:05, 13.62it/s, loss=0.709, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   4%|▍         | 42/938 [00:03<01:05, 13.62it/s, loss=0.7, v_num=12, val_rmse=0.568, train_rmse=0.755]  
Epoch 2:   5%|▍         | 43/938 [00:03<01:05, 13.58it/s, loss=0.702, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   5%|▍         | 44/938 [00:03<01:05, 13.63it/s, loss=0.702, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   5%|▍         | 44/938 [00:03<01:05, 13.63it/s, loss=0.702, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   5%|▍         | 45/938 [00:03<01:06, 13.44it/s, loss=0.708, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   5%|▍         | 46/938 [00:03<01:06, 13.44it/s, loss=0.708, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   5%|▌         | 47/938 [00:03<01:06, 13.49it/s, loss=0.712, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   5%|▌         | 48/938 [00:03<01:06, 13.48it/s, loss=0.712, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   5%|▌         | 48/938 [00:03<01:06, 13.48it/s, loss=0.708, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   5%|▌         | 49/938 [00:03<01:05, 13.48it/s, loss=0.719, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   5%|▌         | 50/938 [00:03<01:05, 13.49it/s, loss=0.71, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:   5%|▌         | 51/938 [00:03<01:05, 13.51it/s, loss=0.708, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   6%|▌         | 52/938 [00:03<01:05, 13.48it/s, loss=0.708, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   6%|▌         | 52/938 [00:03<01:05, 13.48it/s, loss=0.7, v_num=12, val_rmse=0.568, train_rmse=0.755]  
Epoch 2:   6%|▌         | 53/938 [00:03<01:05, 13.53it/s, loss=0.682, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   6%|▌         | 54/938 [00:03<01:05, 13.51it/s, loss=0.687, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   6%|▌         | 55/938 [00:04<01:05, 13.52it/s, loss=0.687, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   6%|▌         | 56/938 [00:04<01:05, 13.54it/s, loss=0.687, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   6%|▌         | 56/938 [00:04<01:05, 13.54it/s, loss=0.698, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   6%|▌         | 57/938 [00:04<01:04, 13.57it/s, loss=0.702, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   6%|▌         | 58/938 [00:04<01:04, 13.54it/s, loss=0.714, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   6%|▋         | 59/938 [00:04<01:04, 13.56it/s, loss=0.716, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   6%|▋         | 60/938 [00:04<01:04, 13.58it/s, loss=0.716, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   6%|▋         | 60/938 [00:04<01:04, 13.58it/s, loss=0.716, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   7%|▋         | 61/938 [00:04<01:04, 13.59it/s, loss=0.714, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   7%|▋         | 62/938 [00:04<01:04, 13.59it/s, loss=0.721, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   7%|▋         | 63/938 [00:04<01:04, 13.63it/s, loss=0.713, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   7%|▋         | 64/938 [00:04<01:04, 13.61it/s, loss=0.713, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   7%|▋         | 64/938 [00:04<01:04, 13.61it/s, loss=0.715, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   7%|▋         | 65/938 [00:04<01:04, 13.62it/s, loss=0.706, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   7%|▋         | 66/938 [00:04<01:04, 13.62it/s, loss=0.706, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   7%|▋         | 67/938 [00:04<01:04, 13.60it/s, loss=0.712, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   7%|▋         | 68/938 [00:05<01:03, 13.60it/s, loss=0.712, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   7%|▋         | 68/938 [00:05<01:03, 13.60it/s, loss=0.711, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   7%|▋         | 69/938 [00:05<01:04, 13.53it/s, loss=0.704, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   7%|▋         | 70/938 [00:05<01:04, 13.51it/s, loss=0.716, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   8%|▊         | 71/938 [00:05<01:03, 13.56it/s, loss=0.717, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   8%|▊         | 72/938 [00:05<01:03, 13.58it/s, loss=0.717, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   8%|▊         | 72/938 [00:05<01:03, 13.58it/s, loss=0.719, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   8%|▊         | 73/938 [00:05<01:03, 13.54it/s, loss=0.738, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   8%|▊         | 74/938 [00:05<01:03, 13.55it/s, loss=0.729, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   8%|▊         | 75/938 [00:05<01:03, 13.56it/s, loss=0.717, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   8%|▊         | 76/938 [00:05<01:03, 13.59it/s, loss=0.717, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   8%|▊         | 76/938 [00:05<01:03, 13.58it/s, loss=0.705, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   8%|▊         | 77/938 [00:05<01:03, 13.60it/s, loss=0.707, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   8%|▊         | 78/938 [00:05<01:03, 13.62it/s, loss=0.701, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   8%|▊         | 79/938 [00:05<01:03, 13.61it/s, loss=0.705, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   9%|▊         | 80/938 [00:05<01:03, 13.59it/s, loss=0.705, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   9%|▊         | 80/938 [00:05<01:03, 13.59it/s, loss=0.712, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   9%|▊         | 81/938 [00:05<01:03, 13.53it/s, loss=0.711, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   9%|▊         | 82/938 [00:06<01:03, 13.54it/s, loss=0.713, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   9%|▉         | 83/938 [00:06<01:03, 13.55it/s, loss=0.714, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   9%|▉         | 84/938 [00:06<01:03, 13.51it/s, loss=0.714, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   9%|▉         | 84/938 [00:06<01:03, 13.51it/s, loss=0.715, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   9%|▉         | 85/938 [00:06<01:03, 13.49it/s, loss=0.714, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   9%|▉         | 86/938 [00:06<01:03, 13.51it/s, loss=0.713, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   9%|▉         | 87/938 [00:06<01:02, 13.51it/s, loss=0.704, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   9%|▉         | 88/938 [00:06<01:02, 13.52it/s, loss=0.704, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   9%|▉         | 88/938 [00:06<01:02, 13.52it/s, loss=0.714, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:   9%|▉         | 89/938 [00:06<01:02, 13.55it/s, loss=0.722, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  10%|▉         | 90/938 [00:06<01:02, 13.53it/s, loss=0.718, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  10%|▉         | 91/938 [00:06<01:02, 13.51it/s, loss=0.723, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  10%|▉         | 92/938 [00:06<01:02, 13.53it/s, loss=0.723, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  10%|▉         | 92/938 [00:06<01:02, 13.52it/s, loss=0.721, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  10%|▉         | 93/938 [00:06<01:02, 13.47it/s, loss=0.7, v_num=12, val_rmse=0.568, train_rmse=0.755]  
Epoch 2:  10%|█         | 94/938 [00:06<01:02, 13.47it/s, loss=0.705, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  10%|█         | 95/938 [00:07<01:02, 13.47it/s, loss=0.717, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  10%|█         | 96/938 [00:07<01:02, 13.49it/s, loss=0.717, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  10%|█         | 96/938 [00:07<01:02, 13.49it/s, loss=0.716, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  10%|█         | 97/938 [00:07<01:02, 13.48it/s, loss=0.705, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  10%|█         | 98/938 [00:07<01:02, 13.46it/s, loss=0.704, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  11%|█         | 99/938 [00:07<01:02, 13.46it/s, loss=0.697, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  11%|█         | 100/938 [00:07<01:02, 13.48it/s, loss=0.697, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  11%|█         | 100/938 [00:07<01:02, 13.47it/s, loss=0.689, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  11%|█         | 101/938 [00:07<01:02, 13.48it/s, loss=0.696, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  11%|█         | 102/938 [00:07<01:02, 13.48it/s, loss=0.69, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  11%|█         | 103/938 [00:07<01:01, 13.49it/s, loss=0.685, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  11%|█         | 104/938 [00:07<01:01, 13.51it/s, loss=0.685, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  11%|█         | 104/938 [00:07<01:01, 13.50it/s, loss=0.684, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  11%|█         | 105/938 [00:07<01:01, 13.53it/s, loss=0.682, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  11%|█▏        | 106/938 [00:07<01:01, 13.54it/s, loss=0.68, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  11%|█▏        | 107/938 [00:07<01:01, 13.56it/s, loss=0.686, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  12%|█▏        | 108/938 [00:07<01:01, 13.58it/s, loss=0.686, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  12%|█▏        | 108/938 [00:07<01:01, 13.58it/s, loss=0.675, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  12%|█▏        | 109/938 [00:08<01:01, 13.56it/s, loss=0.668, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  12%|█▏        | 110/938 [00:08<01:00, 13.59it/s, loss=0.663, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  12%|█▏        | 111/938 [00:08<01:00, 13.59it/s, loss=0.653, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  12%|█▏        | 112/938 [00:08<01:00, 13.62it/s, loss=0.653, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  12%|█▏        | 112/938 [00:08<01:00, 13.62it/s, loss=0.654, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  12%|█▏        | 113/938 [00:08<01:00, 13.63it/s, loss=0.658, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  12%|█▏        | 114/938 [00:08<01:00, 13.63it/s, loss=0.653, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  12%|█▏        | 115/938 [00:08<01:00, 13.64it/s, loss=0.651, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  12%|█▏        | 116/938 [00:08<01:00, 13.64it/s, loss=0.651, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  12%|█▏        | 116/938 [00:08<01:00, 13.64it/s, loss=0.655, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  12%|█▏        | 117/938 [00:08<01:00, 13.68it/s, loss=0.663, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  13%|█▎        | 118/938 [00:08<00:59, 13.70it/s, loss=0.675, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  13%|█▎        | 119/938 [00:08<00:59, 13.69it/s, loss=0.681, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  13%|█▎        | 120/938 [00:08<00:59, 13.72it/s, loss=0.681, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  13%|█▎        | 120/938 [00:08<00:59, 13.72it/s, loss=0.692, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  13%|█▎        | 121/938 [00:08<00:59, 13.73it/s, loss=0.684, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  13%|█▎        | 122/938 [00:08<00:59, 13.72it/s, loss=0.687, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  13%|█▎        | 123/938 [00:08<00:59, 13.71it/s, loss=0.69, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  13%|█▎        | 124/938 [00:09<00:59, 13.71it/s, loss=0.69, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  13%|█▎        | 124/938 [00:09<00:59, 13.71it/s, loss=0.694, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  13%|█▎        | 125/938 [00:09<00:59, 13.72it/s, loss=0.697, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  13%|█▎        | 126/938 [00:09<00:59, 13.74it/s, loss=0.697, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  14%|█▎        | 127/938 [00:09<00:58, 13.75it/s, loss=0.695, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  14%|█▎        | 128/938 [00:09<00:58, 13.73it/s, loss=0.695, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  14%|█▎        | 128/938 [00:09<00:58, 13.73it/s, loss=0.7, v_num=12, val_rmse=0.568, train_rmse=0.755]  
Epoch 2:  14%|█▍        | 129/938 [00:09<00:58, 13.75it/s, loss=0.697, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  14%|█▍        | 130/938 [00:09<00:58, 13.76it/s, loss=0.696, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  14%|█▍        | 131/938 [00:09<00:58, 13.77it/s, loss=0.706, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  14%|█▍        | 132/938 [00:09<00:58, 13.76it/s, loss=0.706, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  14%|█▍        | 132/938 [00:09<00:58, 13.76it/s, loss=0.711, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  14%|█▍        | 133/938 [00:09<00:58, 13.77it/s, loss=0.712, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  14%|█▍        | 134/938 [00:09<00:58, 13.78it/s, loss=0.721, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  14%|█▍        | 135/938 [00:09<00:58, 13.78it/s, loss=0.716, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  14%|█▍        | 136/938 [00:09<00:58, 13.82it/s, loss=0.716, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  14%|█▍        | 136/938 [00:09<00:58, 13.82it/s, loss=0.716, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  15%|█▍        | 137/938 [00:09<00:57, 13.82it/s, loss=0.718, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  15%|█▍        | 138/938 [00:09<00:57, 13.82it/s, loss=0.7, v_num=12, val_rmse=0.568, train_rmse=0.755]  
Epoch 2:  15%|█▍        | 139/938 [00:10<00:57, 13.84it/s, loss=0.698, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  15%|█▍        | 140/938 [00:10<00:57, 13.84it/s, loss=0.698, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  15%|█▍        | 140/938 [00:10<00:57, 13.84it/s, loss=0.687, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  15%|█▌        | 141/938 [00:10<00:57, 13.84it/s, loss=0.694, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  15%|█▌        | 142/938 [00:10<00:57, 13.85it/s, loss=0.705, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  15%|█▌        | 143/938 [00:10<00:57, 13.80it/s, loss=0.701, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  15%|█▌        | 144/938 [00:10<00:57, 13.81it/s, loss=0.701, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  15%|█▌        | 144/938 [00:10<00:57, 13.81it/s, loss=0.702, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  15%|█▌        | 145/938 [00:10<00:57, 13.82it/s, loss=0.718, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  16%|█▌        | 146/938 [00:10<00:57, 13.82it/s, loss=0.731, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  16%|█▌        | 147/938 [00:10<00:57, 13.80it/s, loss=0.731, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  16%|█▌        | 148/938 [00:10<00:57, 13.82it/s, loss=0.731, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  16%|█▌        | 148/938 [00:10<00:57, 13.81it/s, loss=0.731, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  16%|█▌        | 149/938 [00:10<00:57, 13.82it/s, loss=0.731, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  16%|█▌        | 150/938 [00:10<00:56, 13.83it/s, loss=0.736, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  16%|█▌        | 151/938 [00:10<00:56, 13.83it/s, loss=0.728, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  16%|█▌        | 152/938 [00:10<00:56, 13.82it/s, loss=0.728, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  16%|█▌        | 152/938 [00:10<00:56, 13.82it/s, loss=0.723, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  16%|█▋        | 153/938 [00:11<00:56, 13.84it/s, loss=0.735, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  16%|█▋        | 154/938 [00:11<00:56, 13.83it/s, loss=0.728, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  17%|█▋        | 155/938 [00:11<00:56, 13.82it/s, loss=0.73, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  17%|█▋        | 156/938 [00:11<00:56, 13.82it/s, loss=0.73, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  17%|█▋        | 156/938 [00:11<00:56, 13.82it/s, loss=0.728, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  17%|█▋        | 157/938 [00:11<00:56, 13.82it/s, loss=0.722, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  17%|█▋        | 158/938 [00:11<00:56, 13.81it/s, loss=0.729, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  17%|█▋        | 159/938 [00:11<00:56, 13.80it/s, loss=0.732, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  17%|█▋        | 160/938 [00:11<00:56, 13.81it/s, loss=0.732, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  17%|█▋        | 160/938 [00:11<00:56, 13.81it/s, loss=0.738, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  17%|█▋        | 161/938 [00:11<00:56, 13.82it/s, loss=0.739, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  17%|█▋        | 162/938 [00:11<00:56, 13.81it/s, loss=0.732, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  17%|█▋        | 163/938 [00:11<00:56, 13.81it/s, loss=0.73, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  17%|█▋        | 164/938 [00:11<00:56, 13.79it/s, loss=0.73, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  17%|█▋        | 164/938 [00:11<00:56, 13.79it/s, loss=0.736, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  18%|█▊        | 165/938 [00:11<00:56, 13.80it/s, loss=0.736, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  18%|█▊        | 166/938 [00:12<00:55, 13.81it/s, loss=0.725, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  18%|█▊        | 167/938 [00:12<00:55, 13.80it/s, loss=0.727, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  18%|█▊        | 168/938 [00:12<00:55, 13.81it/s, loss=0.727, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  18%|█▊        | 168/938 [00:12<00:55, 13.81it/s, loss=0.73, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  18%|█▊        | 169/938 [00:12<00:55, 13.79it/s, loss=0.745, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  18%|█▊        | 170/938 [00:12<00:55, 13.79it/s, loss=0.742, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  18%|█▊        | 171/938 [00:12<00:55, 13.77it/s, loss=0.745, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  18%|█▊        | 172/938 [00:12<00:55, 13.78it/s, loss=0.745, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  18%|█▊        | 172/938 [00:12<00:55, 13.78it/s, loss=0.743, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  18%|█▊        | 173/938 [00:12<00:55, 13.78it/s, loss=0.738, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  19%|█▊        | 174/938 [00:12<00:55, 13.79it/s, loss=0.739, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  19%|█▊        | 175/938 [00:12<00:55, 13.80it/s, loss=0.744, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  19%|█▉        | 176/938 [00:12<00:55, 13.80it/s, loss=0.744, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  19%|█▉        | 176/938 [00:12<00:55, 13.80it/s, loss=0.754, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  19%|█▉        | 177/938 [00:12<00:55, 13.80it/s, loss=0.751, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  19%|█▉        | 178/938 [00:12<00:55, 13.80it/s, loss=0.755, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  19%|█▉        | 179/938 [00:12<00:55, 13.80it/s, loss=0.753, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  19%|█▉        | 180/938 [00:13<00:54, 13.79it/s, loss=0.753, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  19%|█▉        | 180/938 [00:13<00:54, 13.79it/s, loss=0.75, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  19%|█▉        | 181/938 [00:13<00:54, 13.81it/s, loss=0.743, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  19%|█▉        | 182/938 [00:13<00:54, 13.81it/s, loss=0.732, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  20%|█▉        | 183/938 [00:13<00:54, 13.82it/s, loss=0.734, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  20%|█▉        | 184/938 [00:13<00:54, 13.80it/s, loss=0.734, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  20%|█▉        | 184/938 [00:13<00:54, 13.80it/s, loss=0.724, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  20%|█▉        | 185/938 [00:13<00:54, 13.80it/s, loss=0.707, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  20%|█▉        | 186/938 [00:13<00:54, 13.80it/s, loss=0.706, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  20%|█▉        | 187/938 [00:13<00:54, 13.81it/s, loss=0.709, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  20%|██        | 188/938 [00:13<00:54, 13.82it/s, loss=0.709, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  20%|██        | 188/938 [00:13<00:54, 13.82it/s, loss=0.702, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  20%|██        | 189/938 [00:13<00:54, 13.81it/s, loss=0.688, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  20%|██        | 190/938 [00:13<00:54, 13.83it/s, loss=0.685, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  20%|██        | 191/938 [00:13<00:54, 13.83it/s, loss=0.68, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  20%|██        | 192/938 [00:13<00:53, 13.84it/s, loss=0.68, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  20%|██        | 192/938 [00:13<00:53, 13.84it/s, loss=0.675, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  21%|██        | 193/938 [00:13<00:53, 13.84it/s, loss=0.673, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  21%|██        | 194/938 [00:14<00:53, 13.85it/s, loss=0.676, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  21%|██        | 195/938 [00:14<00:53, 13.82it/s, loss=0.676, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  21%|██        | 196/938 [00:14<00:53, 13.83it/s, loss=0.676, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  21%|██        | 196/938 [00:14<00:53, 13.83it/s, loss=0.675, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  21%|██        | 197/938 [00:14<00:53, 13.83it/s, loss=0.672, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  21%|██        | 198/938 [00:14<00:53, 13.84it/s, loss=0.674, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  21%|██        | 199/938 [00:14<00:53, 13.84it/s, loss=0.671, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  21%|██▏       | 200/938 [00:14<00:53, 13.85it/s, loss=0.671, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  21%|██▏       | 200/938 [00:14<00:53, 13.85it/s, loss=0.675, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  21%|██▏       | 201/938 [00:14<00:53, 13.85it/s, loss=0.682, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  22%|██▏       | 202/938 [00:14<00:53, 13.84it/s, loss=0.69, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  22%|██▏       | 203/938 [00:14<00:53, 13.85it/s, loss=0.692, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  22%|██▏       | 204/938 [00:14<00:52, 13.86it/s, loss=0.692, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  22%|██▏       | 204/938 [00:14<00:52, 13.85it/s, loss=0.688, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  22%|██▏       | 205/938 [00:14<00:52, 13.86it/s, loss=0.7, v_num=12, val_rmse=0.568, train_rmse=0.755]  
Epoch 2:  22%|██▏       | 206/938 [00:14<00:52, 13.87it/s, loss=0.699, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  22%|██▏       | 207/938 [00:14<00:52, 13.86it/s, loss=0.688, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  22%|██▏       | 208/938 [00:15<00:52, 13.86it/s, loss=0.688, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  22%|██▏       | 208/938 [00:15<00:52, 13.86it/s, loss=0.691, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  22%|██▏       | 209/938 [00:15<00:52, 13.86it/s, loss=0.684, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  22%|██▏       | 210/938 [00:15<00:52, 13.86it/s, loss=0.684, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  22%|██▏       | 211/938 [00:15<00:52, 13.87it/s, loss=0.689, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  23%|██▎       | 212/938 [00:15<00:52, 13.89it/s, loss=0.689, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  23%|██▎       | 212/938 [00:15<00:52, 13.89it/s, loss=0.689, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  23%|██▎       | 213/938 [00:15<00:52, 13.88it/s, loss=0.685, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  23%|██▎       | 214/938 [00:15<00:52, 13.89it/s, loss=0.69, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  23%|██▎       | 215/938 [00:15<00:52, 13.90it/s, loss=0.682, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  23%|██▎       | 216/938 [00:15<00:51, 13.90it/s, loss=0.682, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  23%|██▎       | 216/938 [00:15<00:51, 13.90it/s, loss=0.671, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  23%|██▎       | 217/938 [00:15<00:51, 13.91it/s, loss=0.671, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  23%|██▎       | 218/938 [00:15<00:51, 13.91it/s, loss=0.66, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  23%|██▎       | 219/938 [00:15<00:51, 13.92it/s, loss=0.66, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  23%|██▎       | 220/938 [00:15<00:51, 13.91it/s, loss=0.66, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  23%|██▎       | 220/938 [00:15<00:51, 13.91it/s, loss=0.657, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  24%|██▎       | 221/938 [00:15<00:51, 13.92it/s, loss=0.649, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  24%|██▎       | 222/938 [00:15<00:51, 13.92it/s, loss=0.648, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  24%|██▍       | 223/938 [00:16<00:51, 13.91it/s, loss=0.642, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  24%|██▍       | 224/938 [00:16<00:51, 13.91it/s, loss=0.642, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  24%|██▍       | 224/938 [00:16<00:51, 13.91it/s, loss=0.652, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  24%|██▍       | 225/938 [00:16<00:51, 13.92it/s, loss=0.645, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  24%|██▍       | 226/938 [00:16<00:51, 13.91it/s, loss=0.643, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  24%|██▍       | 227/938 [00:16<00:51, 13.91it/s, loss=0.647, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  24%|██▍       | 228/938 [00:16<00:51, 13.89it/s, loss=0.647, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  24%|██▍       | 228/938 [00:16<00:51, 13.89it/s, loss=0.649, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  24%|██▍       | 229/938 [00:16<00:51, 13.89it/s, loss=0.654, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  25%|██▍       | 230/938 [00:16<00:50, 13.90it/s, loss=0.659, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  25%|██▍       | 231/938 [00:16<00:50, 13.88it/s, loss=0.661, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  25%|██▍       | 232/938 [00:16<00:50, 13.87it/s, loss=0.661, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  25%|██▍       | 232/938 [00:16<00:50, 13.87it/s, loss=0.673, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  25%|██▍       | 233/938 [00:16<00:50, 13.87it/s, loss=0.674, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  25%|██▍       | 234/938 [00:16<00:50, 13.87it/s, loss=0.678, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  25%|██▌       | 235/938 [00:16<00:50, 13.87it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  25%|██▌       | 236/938 [00:16<00:50, 13.88it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  25%|██▌       | 236/938 [00:16<00:50, 13.88it/s, loss=0.682, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  25%|██▌       | 237/938 [00:17<00:50, 13.88it/s, loss=0.686, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  25%|██▌       | 238/938 [00:17<00:50, 13.89it/s, loss=0.69, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  25%|██▌       | 239/938 [00:17<00:50, 13.89it/s, loss=0.695, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  26%|██▌       | 240/938 [00:17<00:50, 13.89it/s, loss=0.695, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  26%|██▌       | 240/938 [00:17<00:50, 13.89it/s, loss=0.693, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  26%|██▌       | 241/938 [00:17<00:50, 13.90it/s, loss=0.69, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  26%|██▌       | 242/938 [00:17<00:50, 13.88it/s, loss=0.694, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  26%|██▌       | 243/938 [00:17<00:50, 13.88it/s, loss=0.711, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  26%|██▌       | 244/938 [00:17<00:50, 13.88it/s, loss=0.711, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  26%|██▌       | 244/938 [00:17<00:50, 13.88it/s, loss=0.71, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  26%|██▌       | 245/938 [00:17<00:49, 13.88it/s, loss=0.712, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  26%|██▌       | 246/938 [00:17<00:49, 13.89it/s, loss=0.725, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  26%|██▋       | 247/938 [00:17<00:49, 13.89it/s, loss=0.734, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  26%|██▋       | 248/938 [00:17<00:49, 13.88it/s, loss=0.734, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  26%|██▋       | 248/938 [00:17<00:49, 13.88it/s, loss=0.736, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  27%|██▋       | 249/938 [00:17<00:49, 13.87it/s, loss=0.748, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  27%|██▋       | 250/938 [00:18<00:49, 13.88it/s, loss=0.748, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  27%|██▋       | 251/938 [00:18<00:49, 13.88it/s, loss=0.748, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  27%|██▋       | 252/938 [00:18<00:49, 13.87it/s, loss=0.748, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  27%|██▋       | 252/938 [00:18<00:49, 13.87it/s, loss=0.741, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  27%|██▋       | 253/938 [00:18<00:49, 13.87it/s, loss=0.747, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  27%|██▋       | 254/938 [00:18<00:49, 13.88it/s, loss=0.744, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  27%|██▋       | 255/938 [00:18<00:49, 13.87it/s, loss=0.749, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  27%|██▋       | 256/938 [00:18<00:49, 13.86it/s, loss=0.749, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  27%|██▋       | 256/938 [00:18<00:49, 13.86it/s, loss=0.753, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  27%|██▋       | 257/938 [00:18<00:49, 13.86it/s, loss=0.751, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  28%|██▊       | 258/938 [00:18<00:49, 13.85it/s, loss=0.755, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  28%|██▊       | 259/938 [00:18<00:49, 13.85it/s, loss=0.752, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  28%|██▊       | 260/938 [00:18<00:48, 13.84it/s, loss=0.752, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  28%|██▊       | 260/938 [00:18<00:48, 13.84it/s, loss=0.756, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  28%|██▊       | 261/938 [00:18<00:48, 13.85it/s, loss=0.768, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  28%|██▊       | 262/938 [00:18<00:48, 13.84it/s, loss=0.762, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  28%|██▊       | 263/938 [00:19<00:48, 13.84it/s, loss=0.762, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  28%|██▊       | 264/938 [00:19<00:48, 13.84it/s, loss=0.762, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  28%|██▊       | 264/938 [00:19<00:48, 13.84it/s, loss=0.752, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  28%|██▊       | 265/938 [00:19<00:48, 13.85it/s, loss=0.748, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  28%|██▊       | 266/938 [00:19<00:48, 13.85it/s, loss=0.73, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  28%|██▊       | 267/938 [00:19<00:48, 13.84it/s, loss=0.718, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  29%|██▊       | 268/938 [00:19<00:48, 13.84it/s, loss=0.718, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  29%|██▊       | 268/938 [00:19<00:48, 13.84it/s, loss=0.706, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  29%|██▊       | 269/938 [00:19<00:48, 13.85it/s, loss=0.698, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  29%|██▉       | 270/938 [00:19<00:48, 13.84it/s, loss=0.693, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  29%|██▉       | 271/938 [00:19<00:48, 13.84it/s, loss=0.705, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  29%|██▉       | 272/938 [00:19<00:48, 13.84it/s, loss=0.705, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  29%|██▉       | 272/938 [00:19<00:48, 13.84it/s, loss=0.701, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  29%|██▉       | 273/938 [00:19<00:48, 13.84it/s, loss=0.699, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  29%|██▉       | 274/938 [00:19<00:48, 13.83it/s, loss=0.691, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  29%|██▉       | 275/938 [00:19<00:47, 13.82it/s, loss=0.695, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  29%|██▉       | 276/938 [00:19<00:47, 13.82it/s, loss=0.695, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  29%|██▉       | 276/938 [00:19<00:47, 13.82it/s, loss=0.684, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  30%|██▉       | 277/938 [00:20<00:47, 13.82it/s, loss=0.689, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  30%|██▉       | 278/938 [00:20<00:47, 13.83it/s, loss=0.68, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  30%|██▉       | 279/938 [00:20<00:47, 13.83it/s, loss=0.68, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  30%|██▉       | 280/938 [00:20<00:47, 13.81it/s, loss=0.68, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  30%|██▉       | 280/938 [00:20<00:47, 13.81it/s, loss=0.676, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  30%|██▉       | 281/938 [00:20<00:47, 13.81it/s, loss=0.668, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  30%|███       | 282/938 [00:20<00:47, 13.77it/s, loss=0.677, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  30%|███       | 283/938 [00:20<00:47, 13.72it/s, loss=0.667, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  30%|███       | 284/938 [00:20<00:47, 13.72it/s, loss=0.667, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  30%|███       | 284/938 [00:20<00:47, 13.72it/s, loss=0.677, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  30%|███       | 285/938 [00:20<00:47, 13.72it/s, loss=0.673, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  30%|███       | 286/938 [00:20<00:47, 13.72it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  31%|███       | 287/938 [00:20<00:47, 13.69it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  31%|███       | 288/938 [00:21<00:47, 13.70it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  31%|███       | 288/938 [00:21<00:47, 13.70it/s, loss=0.689, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  31%|███       | 289/938 [00:21<00:47, 13.70it/s, loss=0.689, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  31%|███       | 290/938 [00:21<00:47, 13.71it/s, loss=0.692, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  31%|███       | 291/938 [00:21<00:47, 13.71it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  31%|███       | 292/938 [00:21<00:47, 13.70it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  31%|███       | 292/938 [00:21<00:47, 13.70it/s, loss=0.684, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  31%|███       | 293/938 [00:21<00:47, 13.70it/s, loss=0.687, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  31%|███▏      | 294/938 [00:21<00:47, 13.70it/s, loss=0.691, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  31%|███▏      | 295/938 [00:21<00:46, 13.71it/s, loss=0.684, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  32%|███▏      | 296/938 [00:21<00:46, 13.71it/s, loss=0.684, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  32%|███▏      | 296/938 [00:21<00:46, 13.70it/s, loss=0.691, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  32%|███▏      | 297/938 [00:21<00:46, 13.71it/s, loss=0.694, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  32%|███▏      | 298/938 [00:21<00:46, 13.70it/s, loss=0.701, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  32%|███▏      | 299/938 [00:21<00:46, 13.71it/s, loss=0.702, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  32%|███▏      | 300/938 [00:21<00:46, 13.71it/s, loss=0.702, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  32%|███▏      | 300/938 [00:21<00:46, 13.71it/s, loss=0.698, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  32%|███▏      | 301/938 [00:21<00:46, 13.71it/s, loss=0.695, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  32%|███▏      | 302/938 [00:22<00:46, 13.71it/s, loss=0.684, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  32%|███▏      | 303/938 [00:22<00:46, 13.72it/s, loss=0.681, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  32%|███▏      | 304/938 [00:22<00:46, 13.72it/s, loss=0.681, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  32%|███▏      | 304/938 [00:22<00:46, 13.72it/s, loss=0.674, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  33%|███▎      | 305/938 [00:22<00:46, 13.73it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  33%|███▎      | 306/938 [00:22<00:46, 13.74it/s, loss=0.676, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  33%|███▎      | 307/938 [00:22<00:45, 13.74it/s, loss=0.685, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  33%|███▎      | 308/938 [00:22<00:45, 13.74it/s, loss=0.685, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  33%|███▎      | 308/938 [00:22<00:45, 13.74it/s, loss=0.674, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  33%|███▎      | 309/938 [00:22<00:45, 13.74it/s, loss=0.669, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  33%|███▎      | 310/938 [00:22<00:45, 13.75it/s, loss=0.666, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  33%|███▎      | 311/938 [00:22<00:45, 13.74it/s, loss=0.669, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  33%|███▎      | 312/938 [00:22<00:45, 13.74it/s, loss=0.669, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  33%|███▎      | 312/938 [00:22<00:45, 13.74it/s, loss=0.667, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  33%|███▎      | 313/938 [00:22<00:45, 13.73it/s, loss=0.666, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  33%|███▎      | 314/938 [00:22<00:45, 13.72it/s, loss=0.667, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  34%|███▎      | 315/938 [00:22<00:45, 13.72it/s, loss=0.669, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  34%|███▎      | 316/938 [00:23<00:45, 13.71it/s, loss=0.669, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  34%|███▎      | 316/938 [00:23<00:45, 13.71it/s, loss=0.68, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  34%|███▍      | 317/938 [00:23<00:45, 13.71it/s, loss=0.673, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  34%|███▍      | 318/938 [00:23<00:45, 13.71it/s, loss=0.665, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  34%|███▍      | 319/938 [00:23<00:45, 13.71it/s, loss=0.664, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  34%|███▍      | 320/938 [00:23<00:45, 13.69it/s, loss=0.664, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  34%|███▍      | 320/938 [00:23<00:45, 13.69it/s, loss=0.672, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  34%|███▍      | 321/938 [00:23<00:45, 13.68it/s, loss=0.676, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  34%|███▍      | 322/938 [00:23<00:44, 13.69it/s, loss=0.685, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  34%|███▍      | 323/938 [00:23<00:44, 13.69it/s, loss=0.686, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  35%|███▍      | 324/938 [00:23<00:44, 13.69it/s, loss=0.686, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  35%|███▍      | 324/938 [00:23<00:44, 13.69it/s, loss=0.686, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  35%|███▍      | 325/938 [00:23<00:44, 13.69it/s, loss=0.685, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  35%|███▍      | 326/938 [00:23<00:44, 13.69it/s, loss=0.689, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  35%|███▍      | 327/938 [00:23<00:44, 13.69it/s, loss=0.683, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  35%|███▍      | 328/938 [00:23<00:44, 13.69it/s, loss=0.683, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  35%|███▍      | 328/938 [00:23<00:44, 13.69it/s, loss=0.69, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  35%|███▌      | 329/938 [00:24<00:44, 13.70it/s, loss=0.7, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  35%|███▌      | 330/938 [00:24<00:44, 13.70it/s, loss=0.705, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  35%|███▌      | 331/938 [00:24<00:44, 13.70it/s, loss=0.709, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  35%|███▌      | 332/938 [00:24<00:44, 13.70it/s, loss=0.709, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  35%|███▌      | 332/938 [00:24<00:44, 13.70it/s, loss=0.708, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  36%|███▌      | 333/938 [00:24<00:44, 13.70it/s, loss=0.699, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  36%|███▌      | 334/938 [00:24<00:44, 13.69it/s, loss=0.693, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  36%|███▌      | 335/938 [00:24<00:44, 13.69it/s, loss=0.688, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  36%|███▌      | 336/938 [00:24<00:43, 13.70it/s, loss=0.688, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  36%|███▌      | 336/938 [00:24<00:43, 13.70it/s, loss=0.678, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  36%|███▌      | 337/938 [00:24<00:43, 13.70it/s, loss=0.667, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  36%|███▌      | 338/938 [00:24<00:43, 13.71it/s, loss=0.671, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  36%|███▌      | 339/938 [00:24<00:43, 13.71it/s, loss=0.678, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  36%|███▌      | 340/938 [00:24<00:43, 13.71it/s, loss=0.678, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  36%|███▌      | 340/938 [00:24<00:43, 13.71it/s, loss=0.673, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  36%|███▋      | 341/938 [00:24<00:43, 13.72it/s, loss=0.67, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  36%|███▋      | 342/938 [00:24<00:43, 13.72it/s, loss=0.676, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  37%|███▋      | 343/938 [00:25<00:43, 13.71it/s, loss=0.677, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  37%|███▋      | 344/938 [00:25<00:43, 13.73it/s, loss=0.677, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  37%|███▋      | 344/938 [00:25<00:43, 13.73it/s, loss=0.681, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  37%|███▋      | 345/938 [00:25<00:43, 13.72it/s, loss=0.683, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  37%|███▋      | 346/938 [00:25<00:43, 13.71it/s, loss=0.684, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  37%|███▋      | 347/938 [00:25<00:43, 13.71it/s, loss=0.682, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  37%|███▋      | 348/938 [00:25<00:43, 13.72it/s, loss=0.682, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  37%|███▋      | 348/938 [00:25<00:43, 13.72it/s, loss=0.688, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  37%|███▋      | 349/938 [00:25<00:42, 13.72it/s, loss=0.684, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  37%|███▋      | 350/938 [00:25<00:42, 13.72it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  37%|███▋      | 351/938 [00:25<00:42, 13.69it/s, loss=0.682, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  38%|███▊      | 352/938 [00:25<00:42, 13.68it/s, loss=0.682, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  38%|███▊      | 352/938 [00:25<00:42, 13.68it/s, loss=0.682, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  38%|███▊      | 353/938 [00:25<00:42, 13.68it/s, loss=0.69, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  38%|███▊      | 354/938 [00:25<00:42, 13.69it/s, loss=0.703, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  38%|███▊      | 355/938 [00:25<00:42, 13.69it/s, loss=0.708, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  38%|███▊      | 356/938 [00:26<00:42, 13.69it/s, loss=0.708, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  38%|███▊      | 356/938 [00:26<00:42, 13.69it/s, loss=0.709, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  38%|███▊      | 357/938 [00:26<00:42, 13.68it/s, loss=0.724, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  38%|███▊      | 358/938 [00:26<00:42, 13.69it/s, loss=0.725, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  38%|███▊      | 359/938 [00:26<00:42, 13.69it/s, loss=0.721, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  38%|███▊      | 360/938 [00:26<00:42, 13.69it/s, loss=0.721, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  38%|███▊      | 360/938 [00:26<00:42, 13.69it/s, loss=0.731, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  38%|███▊      | 361/938 [00:26<00:42, 13.69it/s, loss=0.738, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  39%|███▊      | 362/938 [00:26<00:42, 13.69it/s, loss=0.73, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  39%|███▊      | 363/938 [00:26<00:42, 13.69it/s, loss=0.735, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  39%|███▉      | 364/938 [00:26<00:41, 13.68it/s, loss=0.735, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  39%|███▉      | 364/938 [00:26<00:41, 13.68it/s, loss=0.733, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  39%|███▉      | 365/938 [00:26<00:41, 13.67it/s, loss=0.731, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  39%|███▉      | 366/938 [00:26<00:41, 13.68it/s, loss=0.735, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  39%|███▉      | 367/938 [00:26<00:41, 13.68it/s, loss=0.741, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  39%|███▉      | 368/938 [00:26<00:41, 13.67it/s, loss=0.741, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  39%|███▉      | 368/938 [00:26<00:41, 13.67it/s, loss=0.736, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  39%|███▉      | 369/938 [00:26<00:41, 13.68it/s, loss=0.734, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  39%|███▉      | 370/938 [00:27<00:41, 13.68it/s, loss=0.738, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  40%|███▉      | 371/938 [00:27<00:41, 13.67it/s, loss=0.729, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  40%|███▉      | 372/938 [00:27<00:41, 13.68it/s, loss=0.729, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  40%|███▉      | 372/938 [00:27<00:41, 13.68it/s, loss=0.729, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  40%|███▉      | 373/938 [00:27<00:41, 13.68it/s, loss=0.728, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  40%|███▉      | 374/938 [00:27<00:41, 13.68it/s, loss=0.72, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  40%|███▉      | 375/938 [00:27<00:41, 13.65it/s, loss=0.724, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  40%|████      | 376/938 [00:27<00:41, 13.66it/s, loss=0.724, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  40%|████      | 376/938 [00:27<00:41, 13.66it/s, loss=0.726, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  40%|████      | 377/938 [00:27<00:41, 13.65it/s, loss=0.734, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  40%|████      | 378/938 [00:27<00:41, 13.65it/s, loss=0.734, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  40%|████      | 379/938 [00:27<00:40, 13.66it/s, loss=0.725, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  41%|████      | 380/938 [00:27<00:40, 13.66it/s, loss=0.725, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  41%|████      | 380/938 [00:27<00:40, 13.66it/s, loss=0.717, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  41%|████      | 381/938 [00:27<00:40, 13.67it/s, loss=0.712, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  41%|████      | 382/938 [00:27<00:40, 13.66it/s, loss=0.706, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  41%|████      | 383/938 [00:28<00:40, 13.67it/s, loss=0.698, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  41%|████      | 384/938 [00:28<00:40, 13.67it/s, loss=0.698, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  41%|████      | 384/938 [00:28<00:40, 13.67it/s, loss=0.695, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  41%|████      | 385/938 [00:28<00:40, 13.67it/s, loss=0.694, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  41%|████      | 386/938 [00:28<00:40, 13.67it/s, loss=0.692, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  41%|████▏     | 387/938 [00:28<00:40, 13.67it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  41%|████▏     | 388/938 [00:28<00:40, 13.67it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  41%|████▏     | 388/938 [00:28<00:40, 13.67it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  41%|████▏     | 389/938 [00:28<00:40, 13.68it/s, loss=0.682, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  42%|████▏     | 390/938 [00:28<00:40, 13.67it/s, loss=0.683, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  42%|████▏     | 391/938 [00:28<00:40, 13.67it/s, loss=0.685, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  42%|████▏     | 392/938 [00:28<00:39, 13.67it/s, loss=0.685, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  42%|████▏     | 392/938 [00:28<00:39, 13.67it/s, loss=0.684, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  42%|████▏     | 393/938 [00:28<00:39, 13.68it/s, loss=0.682, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  42%|████▏     | 394/938 [00:28<00:39, 13.68it/s, loss=0.68, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  42%|████▏     | 395/938 [00:28<00:39, 13.68it/s, loss=0.673, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  42%|████▏     | 396/938 [00:28<00:39, 13.68it/s, loss=0.673, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  42%|████▏     | 396/938 [00:28<00:39, 13.68it/s, loss=0.682, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  42%|████▏     | 397/938 [00:29<00:39, 13.69it/s, loss=0.678, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  42%|████▏     | 398/938 [00:29<00:39, 13.69it/s, loss=0.68, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  43%|████▎     | 399/938 [00:29<00:39, 13.68it/s, loss=0.684, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  43%|████▎     | 400/938 [00:29<00:39, 13.68it/s, loss=0.684, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  43%|████▎     | 400/938 [00:29<00:39, 13.68it/s, loss=0.683, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  43%|████▎     | 401/938 [00:29<00:39, 13.69it/s, loss=0.684, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  43%|████▎     | 402/938 [00:29<00:39, 13.68it/s, loss=0.691, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  43%|████▎     | 403/938 [00:29<00:39, 13.68it/s, loss=0.69, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  43%|████▎     | 404/938 [00:29<00:39, 13.68it/s, loss=0.69, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  43%|████▎     | 404/938 [00:29<00:39, 13.68it/s, loss=0.696, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  43%|████▎     | 405/938 [00:29<00:38, 13.68it/s, loss=0.699, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  43%|████▎     | 406/938 [00:29<00:38, 13.68it/s, loss=0.702, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  43%|████▎     | 407/938 [00:29<00:38, 13.68it/s, loss=0.71, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  43%|████▎     | 408/938 [00:29<00:38, 13.68it/s, loss=0.71, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  43%|████▎     | 408/938 [00:29<00:38, 13.68it/s, loss=0.716, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  44%|████▎     | 409/938 [00:29<00:38, 13.68it/s, loss=0.714, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  44%|████▎     | 410/938 [00:29<00:38, 13.68it/s, loss=0.712, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  44%|████▍     | 411/938 [00:30<00:38, 13.68it/s, loss=0.712, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  44%|████▍     | 412/938 [00:30<00:38, 13.69it/s, loss=0.712, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  44%|████▍     | 412/938 [00:30<00:38, 13.69it/s, loss=0.712, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  44%|████▍     | 413/938 [00:30<00:38, 13.68it/s, loss=0.712, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  44%|████▍     | 414/938 [00:30<00:38, 13.68it/s, loss=0.714, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  44%|████▍     | 415/938 [00:30<00:38, 13.68it/s, loss=0.709, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  44%|████▍     | 416/938 [00:30<00:38, 13.69it/s, loss=0.709, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  44%|████▍     | 416/938 [00:30<00:38, 13.69it/s, loss=0.696, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  44%|████▍     | 417/938 [00:30<00:38, 13.68it/s, loss=0.686, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  45%|████▍     | 418/938 [00:30<00:37, 13.69it/s, loss=0.682, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  45%|████▍     | 419/938 [00:30<00:37, 13.69it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  45%|████▍     | 420/938 [00:30<00:37, 13.70it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  45%|████▍     | 420/938 [00:30<00:37, 13.70it/s, loss=0.681, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  45%|████▍     | 421/938 [00:30<00:37, 13.70it/s, loss=0.672, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  45%|████▍     | 422/938 [00:30<00:37, 13.71it/s, loss=0.668, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  45%|████▌     | 423/938 [00:30<00:37, 13.71it/s, loss=0.673, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  45%|████▌     | 424/938 [00:30<00:37, 13.71it/s, loss=0.673, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  45%|████▌     | 424/938 [00:30<00:37, 13.71it/s, loss=0.669, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  45%|████▌     | 425/938 [00:30<00:37, 13.72it/s, loss=0.673, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  45%|████▌     | 426/938 [00:31<00:37, 13.72it/s, loss=0.672, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  46%|████▌     | 427/938 [00:31<00:37, 13.72it/s, loss=0.671, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  46%|████▌     | 428/938 [00:31<00:37, 13.72it/s, loss=0.671, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  46%|████▌     | 428/938 [00:31<00:37, 13.72it/s, loss=0.663, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  46%|████▌     | 429/938 [00:31<00:37, 13.71it/s, loss=0.662, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  46%|████▌     | 430/938 [00:31<00:37, 13.71it/s, loss=0.654, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  46%|████▌     | 431/938 [00:31<00:36, 13.71it/s, loss=0.653, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  46%|████▌     | 432/938 [00:31<00:36, 13.72it/s, loss=0.653, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  46%|████▌     | 432/938 [00:31<00:36, 13.71it/s, loss=0.657, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  46%|████▌     | 433/938 [00:31<00:36, 13.71it/s, loss=0.655, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  46%|████▋     | 434/938 [00:31<00:36, 13.72it/s, loss=0.645, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  46%|████▋     | 435/938 [00:31<00:36, 13.72it/s, loss=0.657, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  46%|████▋     | 436/938 [00:31<00:36, 13.71it/s, loss=0.657, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  46%|████▋     | 436/938 [00:31<00:36, 13.71it/s, loss=0.666, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  47%|████▋     | 437/938 [00:31<00:36, 13.71it/s, loss=0.671, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  47%|████▋     | 438/938 [00:31<00:36, 13.71it/s, loss=0.669, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  47%|████▋     | 439/938 [00:32<00:36, 13.71it/s, loss=0.672, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  47%|████▋     | 440/938 [00:32<00:36, 13.72it/s, loss=0.672, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  47%|████▋     | 440/938 [00:32<00:36, 13.72it/s, loss=0.668, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  47%|████▋     | 441/938 [00:32<00:36, 13.72it/s, loss=0.678, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  47%|████▋     | 442/938 [00:32<00:36, 13.72it/s, loss=0.682, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  47%|████▋     | 443/938 [00:32<00:36, 13.73it/s, loss=0.694, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  47%|████▋     | 444/938 [00:32<00:35, 13.73it/s, loss=0.694, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  47%|████▋     | 444/938 [00:32<00:35, 13.73it/s, loss=0.694, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  47%|████▋     | 445/938 [00:32<00:35, 13.73it/s, loss=0.691, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  48%|████▊     | 446/938 [00:32<00:35, 13.73it/s, loss=0.69, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  48%|████▊     | 447/938 [00:32<00:35, 13.72it/s, loss=0.687, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  48%|████▊     | 448/938 [00:32<00:35, 13.72it/s, loss=0.687, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  48%|████▊     | 448/938 [00:32<00:35, 13.72it/s, loss=0.691, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  48%|████▊     | 449/938 [00:32<00:35, 13.73it/s, loss=0.693, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  48%|████▊     | 450/938 [00:32<00:35, 13.72it/s, loss=0.702, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  48%|████▊     | 451/938 [00:32<00:35, 13.72it/s, loss=0.705, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  48%|████▊     | 452/938 [00:32<00:35, 13.72it/s, loss=0.705, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  48%|████▊     | 452/938 [00:32<00:35, 13.72it/s, loss=0.705, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  48%|████▊     | 453/938 [00:33<00:35, 13.72it/s, loss=0.706, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  48%|████▊     | 454/938 [00:33<00:35, 13.73it/s, loss=0.715, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  49%|████▊     | 455/938 [00:33<00:35, 13.73it/s, loss=0.71, v_num=12, val_rmse=0.568, train_rmse=0.755] 
Epoch 2:  49%|████▊     | 456/938 [00:33<00:35, 13.73it/s, loss=0.71, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  49%|████▊     | 456/938 [00:33<00:35, 13.73it/s, loss=0.708, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  49%|████▊     | 457/938 [00:33<00:35, 13.73it/s, loss=0.701, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  49%|████▉     | 458/938 [00:33<00:34, 13.73it/s, loss=0.697, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  49%|████▉     | 459/938 [00:33<00:34, 13.73it/s, loss=0.697, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  49%|████▉     | 460/938 [00:33<00:34, 13.72it/s, loss=0.697, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  49%|████▉     | 460/938 [00:33<00:34, 13.72it/s, loss=0.697, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  49%|████▉     | 461/938 [00:33<00:34, 13.73it/s, loss=0.691, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  49%|████▉     | 462/938 [00:33<00:34, 13.73it/s, loss=0.687, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  49%|████▉     | 463/938 [00:33<00:34, 13.73it/s, loss=0.677, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  49%|████▉     | 464/938 [00:33<00:34, 13.73it/s, loss=0.677, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  49%|████▉     | 464/938 [00:33<00:34, 13.73it/s, loss=0.678, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  50%|████▉     | 465/938 [00:33<00:34, 13.73it/s, loss=0.675, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  50%|████▉     | 466/938 [00:33<00:34, 13.74it/s, loss=0.676, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  50%|████▉     | 467/938 [00:34<00:34, 13.73it/s, loss=0.675, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  50%|████▉     | 468/938 [00:34<00:34, 13.72it/s, loss=0.675, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  50%|████▉     | 468/938 [00:34<00:34, 13.72it/s, loss=0.672, v_num=12, val_rmse=0.568, train_rmse=0.755]
Epoch 2:  50%|█████     | 469/938 [00:34<00:34, 13.74it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]

Validating:   0%|          | 2/469 [00:00<00:27, 16.96it/s]
Epoch 2:  50%|█████     | 472/938 [00:34<00:33, 13.78it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:   1%|          | 5/469 [00:00<00:21, 21.81it/s]
Epoch 2:  51%|█████     | 476/938 [00:34<00:33, 13.83it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:   2%|▏         | 8/469 [00:00<00:20, 22.61it/s]
Epoch 2:  51%|█████     | 480/938 [00:34<00:32, 13.88it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:   2%|▏         | 11/469 [00:00<00:19, 23.13it/s]

Validating:   3%|▎         | 14/469 [00:00<00:20, 21.75it/s]
Epoch 2:  52%|█████▏    | 484/938 [00:34<00:32, 13.92it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:   4%|▎         | 17/469 [00:00<00:19, 22.98it/s]
Epoch 2:  52%|█████▏    | 488/938 [00:34<00:32, 13.97it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:   4%|▍         | 20/469 [00:00<00:18, 24.26it/s]
Epoch 2:  52%|█████▏    | 492/938 [00:35<00:31, 14.02it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:   5%|▍         | 23/469 [00:00<00:18, 24.12it/s]

Validating:   6%|▌         | 26/469 [00:01<00:19, 23.15it/s]
Epoch 2:  53%|█████▎    | 496/938 [00:35<00:31, 14.06it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:   6%|▌         | 29/469 [00:01<00:19, 23.01it/s]
Epoch 2:  53%|█████▎    | 500/938 [00:35<00:31, 14.11it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:   7%|▋         | 32/469 [00:01<00:18, 23.29it/s]
Epoch 2:  54%|█████▎    | 504/938 [00:35<00:30, 14.15it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:   7%|▋         | 35/469 [00:01<00:18, 23.64it/s]

Validating:   8%|▊         | 38/469 [00:01<00:17, 24.60it/s]
Epoch 2:  54%|█████▍    | 508/938 [00:35<00:30, 14.20it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:   9%|▊         | 41/469 [00:01<00:17, 24.79it/s]
Epoch 2:  55%|█████▍    | 512/938 [00:35<00:29, 14.25it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:   9%|▉         | 44/469 [00:01<00:17, 24.75it/s]
Epoch 2:  55%|█████▌    | 516/938 [00:36<00:29, 14.30it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  10%|█         | 47/469 [00:01<00:16, 25.28it/s]

Validating:  11%|█         | 50/469 [00:02<00:16, 25.85it/s]
Epoch 2:  55%|█████▌    | 520/938 [00:36<00:29, 14.35it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  11%|█▏        | 53/469 [00:02<00:16, 25.02it/s]
Epoch 2:  56%|█████▌    | 524/938 [00:36<00:28, 14.40it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  12%|█▏        | 56/469 [00:02<00:16, 25.30it/s]
Epoch 2:  56%|█████▋    | 528/938 [00:36<00:28, 14.45it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  13%|█▎        | 59/469 [00:02<00:15, 26.04it/s]

Validating:  13%|█▎        | 62/469 [00:02<00:15, 26.50it/s]
Epoch 2:  57%|█████▋    | 532/938 [00:36<00:27, 14.50it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  14%|█▍        | 65/469 [00:02<00:15, 25.58it/s]
Epoch 2:  57%|█████▋    | 536/938 [00:36<00:27, 14.54it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  14%|█▍        | 68/469 [00:02<00:15, 25.98it/s]
Epoch 2:  58%|█████▊    | 540/938 [00:36<00:27, 14.60it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  15%|█▌        | 71/469 [00:02<00:15, 25.97it/s]

Validating:  16%|█▌        | 74/469 [00:03<00:15, 25.93it/s]
Epoch 2:  58%|█████▊    | 544/938 [00:37<00:26, 14.64it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  16%|█▋        | 77/469 [00:03<00:15, 25.84it/s]
Epoch 2:  58%|█████▊    | 548/938 [00:37<00:26, 14.69it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  17%|█▋        | 80/469 [00:03<00:14, 26.45it/s]
Epoch 2:  59%|█████▉    | 552/938 [00:37<00:26, 14.73it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  18%|█▊        | 83/469 [00:03<00:15, 25.26it/s]

Validating:  18%|█▊        | 86/469 [00:03<00:15, 25.41it/s]
Epoch 2:  59%|█████▉    | 556/938 [00:37<00:25, 14.78it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  19%|█▉        | 89/469 [00:03<00:14, 25.42it/s]
Epoch 2:  60%|█████▉    | 560/938 [00:37<00:25, 14.82it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  20%|█▉        | 92/469 [00:03<00:14, 25.57it/s]
Epoch 2:  60%|██████    | 564/938 [00:37<00:25, 14.86it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  20%|██        | 95/469 [00:03<00:14, 25.48it/s]

Validating:  21%|██        | 98/469 [00:03<00:14, 25.21it/s]
Epoch 2:  61%|██████    | 568/938 [00:38<00:24, 14.91it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  22%|██▏       | 101/469 [00:04<00:14, 24.81it/s]
Epoch 2:  61%|██████    | 572/938 [00:38<00:24, 14.95it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  22%|██▏       | 104/469 [00:04<00:14, 25.18it/s]
Epoch 2:  61%|██████▏   | 576/938 [00:38<00:24, 14.99it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  23%|██▎       | 107/469 [00:04<00:14, 24.85it/s]

Validating:  23%|██▎       | 110/469 [00:04<00:15, 23.40it/s]
Epoch 2:  62%|██████▏   | 580/938 [00:38<00:23, 15.02it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  24%|██▍       | 113/469 [00:04<00:14, 23.88it/s]
Epoch 2:  62%|██████▏   | 584/938 [00:38<00:23, 15.06it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  25%|██▍       | 116/469 [00:04<00:14, 24.04it/s]
Epoch 2:  63%|██████▎   | 588/938 [00:38<00:23, 15.10it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  25%|██▌       | 119/469 [00:04<00:14, 24.09it/s]

Validating:  26%|██▌       | 122/469 [00:04<00:14, 24.02it/s]
Epoch 2:  63%|██████▎   | 592/938 [00:39<00:22, 15.14it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  27%|██▋       | 125/469 [00:05<00:14, 24.36it/s]
Epoch 2:  64%|██████▎   | 596/938 [00:39<00:22, 15.18it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  27%|██▋       | 128/469 [00:05<00:13, 25.22it/s]
Epoch 2:  64%|██████▍   | 600/938 [00:39<00:22, 15.22it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  28%|██▊       | 131/469 [00:05<00:13, 25.19it/s]

Validating:  29%|██▊       | 134/469 [00:05<00:13, 25.75it/s]
Epoch 2:  64%|██████▍   | 604/938 [00:39<00:21, 15.27it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  29%|██▉       | 137/469 [00:05<00:13, 24.94it/s]
Epoch 2:  65%|██████▍   | 608/938 [00:39<00:21, 15.30it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  30%|██▉       | 140/469 [00:05<00:13, 25.27it/s]
Epoch 2:  65%|██████▌   | 612/938 [00:39<00:21, 15.34it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  30%|███       | 143/469 [00:05<00:13, 25.02it/s]

Validating:  31%|███       | 146/469 [00:05<00:12, 24.88it/s]
Epoch 2:  66%|██████▌   | 616/938 [00:40<00:20, 15.38it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  32%|███▏      | 149/469 [00:06<00:12, 25.97it/s]
Epoch 2:  66%|██████▌   | 620/938 [00:40<00:20, 15.42it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  32%|███▏      | 152/469 [00:06<00:12, 26.29it/s]
Epoch 2:  67%|██████▋   | 624/938 [00:40<00:20, 15.46it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  33%|███▎      | 155/469 [00:06<00:12, 25.97it/s]

Validating:  34%|███▎      | 158/469 [00:06<00:12, 25.91it/s]
Epoch 2:  67%|██████▋   | 628/938 [00:40<00:19, 15.50it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  34%|███▍      | 161/469 [00:06<00:11, 25.96it/s]
Epoch 2:  67%|██████▋   | 632/938 [00:40<00:19, 15.54it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  35%|███▍      | 164/469 [00:06<00:11, 25.94it/s]
Epoch 2:  68%|██████▊   | 636/938 [00:40<00:19, 15.58it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  36%|███▌      | 167/469 [00:06<00:11, 25.91it/s]

Validating:  36%|███▌      | 170/469 [00:06<00:11, 25.14it/s]
Epoch 2:  68%|██████▊   | 640/938 [00:40<00:19, 15.62it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  37%|███▋      | 173/469 [00:06<00:11, 25.19it/s]
Epoch 2:  69%|██████▊   | 644/938 [00:41<00:18, 15.66it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  38%|███▊      | 176/469 [00:07<00:11, 24.81it/s]
Epoch 2:  69%|██████▉   | 648/938 [00:41<00:18, 15.69it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  38%|███▊      | 179/469 [00:07<00:11, 25.35it/s]

Validating:  39%|███▉      | 182/469 [00:07<00:11, 25.41it/s]
Epoch 2:  70%|██████▉   | 652/938 [00:41<00:18, 15.73it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  39%|███▉      | 185/469 [00:07<00:11, 25.13it/s]
Epoch 2:  70%|██████▉   | 656/938 [00:41<00:17, 15.76it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  40%|████      | 188/469 [00:07<00:11, 24.77it/s]
Epoch 2:  70%|███████   | 660/938 [00:41<00:17, 15.80it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  41%|████      | 191/469 [00:07<00:11, 25.00it/s]

Validating:  41%|████▏     | 194/469 [00:07<00:11, 23.62it/s]
Epoch 2:  71%|███████   | 664/938 [00:41<00:17, 15.82it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  42%|████▏     | 197/469 [00:07<00:11, 23.41it/s]
Epoch 2:  71%|███████   | 668/938 [00:42<00:17, 15.86it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  43%|████▎     | 200/469 [00:08<00:11, 24.33it/s]
Epoch 2:  72%|███████▏  | 672/938 [00:42<00:16, 15.89it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  43%|████▎     | 203/469 [00:08<00:10, 24.55it/s]

Validating:  44%|████▍     | 206/469 [00:08<00:10, 25.26it/s]
Epoch 2:  72%|███████▏  | 676/938 [00:42<00:16, 15.93it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  45%|████▍     | 209/469 [00:08<00:10, 24.23it/s]
Epoch 2:  72%|███████▏  | 680/938 [00:42<00:16, 15.96it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  45%|████▌     | 212/469 [00:08<00:10, 24.04it/s]
Epoch 2:  73%|███████▎  | 684/938 [00:42<00:15, 15.99it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  46%|████▌     | 215/469 [00:08<00:10, 24.25it/s]

Validating:  46%|████▋     | 218/469 [00:08<00:10, 25.06it/s]
Epoch 2:  73%|███████▎  | 688/938 [00:42<00:15, 16.03it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  47%|████▋     | 221/469 [00:08<00:09, 25.60it/s]
Epoch 2:  74%|███████▍  | 692/938 [00:43<00:15, 16.07it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  48%|████▊     | 224/469 [00:09<00:09, 25.82it/s]
Epoch 2:  74%|███████▍  | 696/938 [00:43<00:15, 16.10it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  48%|████▊     | 227/469 [00:09<00:09, 25.37it/s]

Validating:  49%|████▉     | 230/469 [00:09<00:09, 25.83it/s]
Epoch 2:  75%|███████▍  | 700/938 [00:43<00:14, 16.13it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  50%|████▉     | 233/469 [00:09<00:09, 25.36it/s]
Epoch 2:  75%|███████▌  | 704/938 [00:43<00:14, 16.17it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  50%|█████     | 236/469 [00:09<00:08, 26.33it/s]
Epoch 2:  75%|███████▌  | 708/938 [00:43<00:14, 16.21it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  51%|█████     | 239/469 [00:09<00:08, 26.48it/s]

Validating:  52%|█████▏    | 242/469 [00:09<00:08, 26.37it/s]
Epoch 2:  76%|███████▌  | 712/938 [00:43<00:13, 16.24it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  52%|█████▏    | 245/469 [00:09<00:08, 25.44it/s]
Epoch 2:  76%|███████▋  | 716/938 [00:44<00:13, 16.27it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  53%|█████▎    | 248/469 [00:09<00:09, 23.68it/s]
Epoch 2:  77%|███████▋  | 720/938 [00:44<00:13, 16.29it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  54%|█████▎    | 251/469 [00:10<00:09, 23.58it/s]

Validating:  54%|█████▍    | 254/469 [00:10<00:09, 23.58it/s]
Epoch 2:  77%|███████▋  | 724/938 [00:44<00:13, 16.32it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  55%|█████▍    | 257/469 [00:10<00:08, 24.70it/s]
Epoch 2:  78%|███████▊  | 728/938 [00:44<00:12, 16.35it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  55%|█████▌    | 260/469 [00:10<00:08, 24.53it/s]
Epoch 2:  78%|███████▊  | 732/938 [00:44<00:12, 16.38it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  56%|█████▌    | 263/469 [00:10<00:08, 23.91it/s]

Validating:  57%|█████▋    | 266/469 [00:10<00:08, 24.70it/s]
Epoch 2:  78%|███████▊  | 736/938 [00:44<00:12, 16.41it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  57%|█████▋    | 269/469 [00:10<00:08, 24.17it/s]
Epoch 2:  79%|███████▉  | 740/938 [00:45<00:12, 16.44it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  58%|█████▊    | 272/469 [00:10<00:08, 24.14it/s]
Epoch 2:  79%|███████▉  | 744/938 [00:45<00:11, 16.47it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  59%|█████▊    | 275/469 [00:11<00:08, 23.86it/s]

Validating:  59%|█████▉    | 278/469 [00:11<00:07, 24.07it/s]
Epoch 2:  80%|███████▉  | 748/938 [00:45<00:11, 16.49it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  60%|█████▉    | 281/469 [00:11<00:07, 23.86it/s]
Epoch 2:  80%|████████  | 752/938 [00:45<00:11, 16.52it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  61%|██████    | 284/469 [00:11<00:07, 24.82it/s]
Epoch 2:  81%|████████  | 756/938 [00:45<00:10, 16.55it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  61%|██████    | 287/469 [00:11<00:07, 25.17it/s]

Validating:  62%|██████▏   | 290/469 [00:11<00:07, 25.34it/s]
Epoch 2:  81%|████████  | 760/938 [00:45<00:10, 16.59it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  62%|██████▏   | 293/469 [00:11<00:07, 24.96it/s]
Epoch 2:  81%|████████▏ | 764/938 [00:45<00:10, 16.61it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  63%|██████▎   | 296/469 [00:11<00:06, 25.32it/s]
Epoch 2:  82%|████████▏ | 768/938 [00:46<00:10, 16.64it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  64%|██████▍   | 299/469 [00:12<00:06, 24.99it/s]

Validating:  64%|██████▍   | 302/469 [00:12<00:06, 25.18it/s]
Epoch 2:  82%|████████▏ | 772/938 [00:46<00:09, 16.67it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  65%|██████▌   | 305/469 [00:12<00:06, 25.65it/s]
Epoch 2:  83%|████████▎ | 776/938 [00:46<00:09, 16.71it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  66%|██████▌   | 308/469 [00:12<00:06, 25.82it/s]
Epoch 2:  83%|████████▎ | 780/938 [00:46<00:09, 16.73it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  66%|██████▋   | 311/469 [00:12<00:06, 25.45it/s]

Validating:  67%|██████▋   | 314/469 [00:12<00:06, 24.93it/s]
Epoch 2:  84%|████████▎ | 784/938 [00:46<00:09, 16.76it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  68%|██████▊   | 317/469 [00:12<00:06, 24.48it/s]
Epoch 2:  84%|████████▍ | 788/938 [00:46<00:08, 16.79it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  68%|██████▊   | 320/469 [00:12<00:06, 24.79it/s]
Epoch 2:  84%|████████▍ | 792/938 [00:47<00:08, 16.81it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  69%|██████▉   | 323/469 [00:13<00:05, 25.13it/s]

Validating:  70%|██████▉   | 326/469 [00:13<00:05, 24.28it/s]
Epoch 2:  85%|████████▍ | 796/938 [00:47<00:08, 16.84it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  70%|███████   | 329/469 [00:13<00:05, 24.04it/s]
Epoch 2:  85%|████████▌ | 800/938 [00:47<00:08, 16.87it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  71%|███████   | 332/469 [00:13<00:05, 23.37it/s]
Epoch 2:  86%|████████▌ | 804/938 [00:47<00:07, 16.88it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  71%|███████▏  | 335/469 [00:13<00:05, 22.80it/s]

Validating:  72%|███████▏  | 338/469 [00:13<00:05, 24.29it/s]
Epoch 2:  86%|████████▌ | 808/938 [00:47<00:07, 16.91it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  73%|███████▎  | 341/469 [00:13<00:05, 25.13it/s]
Epoch 2:  87%|████████▋ | 812/938 [00:47<00:07, 16.94it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  73%|███████▎  | 344/469 [00:13<00:04, 25.65it/s]
Epoch 2:  87%|████████▋ | 816/938 [00:48<00:07, 16.97it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  74%|███████▍  | 347/469 [00:13<00:04, 26.19it/s]

Validating:  75%|███████▍  | 350/469 [00:14<00:04, 24.90it/s]
Epoch 2:  87%|████████▋ | 820/938 [00:48<00:06, 17.00it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  75%|███████▌  | 353/469 [00:14<00:04, 25.10it/s]
Epoch 2:  88%|████████▊ | 824/938 [00:48<00:06, 17.03it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  76%|███████▌  | 356/469 [00:14<00:04, 24.93it/s]
Epoch 2:  88%|████████▊ | 828/938 [00:48<00:06, 17.05it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  77%|███████▋  | 359/469 [00:14<00:04, 25.40it/s]

Validating:  77%|███████▋  | 362/469 [00:14<00:04, 25.76it/s]
Epoch 2:  89%|████████▊ | 832/938 [00:48<00:06, 17.08it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  78%|███████▊  | 365/469 [00:14<00:04, 24.75it/s]
Epoch 2:  89%|████████▉ | 836/938 [00:48<00:05, 17.10it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  78%|███████▊  | 368/469 [00:14<00:03, 25.28it/s]
Epoch 2:  90%|████████▉ | 840/938 [00:49<00:05, 17.13it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  79%|███████▉  | 371/469 [00:14<00:03, 24.90it/s]

Validating:  80%|███████▉  | 374/469 [00:15<00:03, 25.14it/s]
Epoch 2:  90%|████████▉ | 844/938 [00:49<00:05, 17.16it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  80%|████████  | 377/469 [00:15<00:03, 24.84it/s]
Epoch 2:  90%|█████████ | 848/938 [00:49<00:05, 17.18it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  81%|████████  | 380/469 [00:15<00:03, 25.43it/s]
Epoch 2:  91%|█████████ | 852/938 [00:49<00:04, 17.21it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  82%|████████▏ | 383/469 [00:15<00:03, 25.09it/s]

Validating:  82%|████████▏ | 386/469 [00:15<00:03, 24.94it/s]
Epoch 2:  91%|█████████▏| 856/938 [00:49<00:04, 17.23it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  83%|████████▎ | 389/469 [00:15<00:03, 24.18it/s]
Epoch 2:  92%|█████████▏| 860/938 [00:49<00:04, 17.25it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  84%|████████▎ | 392/469 [00:15<00:03, 24.69it/s]
Epoch 2:  92%|█████████▏| 864/938 [00:50<00:04, 17.28it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  84%|████████▍ | 395/469 [00:15<00:02, 24.88it/s]

Validating:  85%|████████▍ | 398/469 [00:16<00:02, 25.73it/s]
Epoch 2:  93%|█████████▎| 868/938 [00:50<00:04, 17.31it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  86%|████████▌ | 401/469 [00:16<00:02, 24.44it/s]
Epoch 2:  93%|█████████▎| 872/938 [00:50<00:03, 17.33it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  86%|████████▌ | 404/469 [00:16<00:02, 24.13it/s]
Epoch 2:  93%|█████████▎| 876/938 [00:50<00:03, 17.35it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  87%|████████▋ | 407/469 [00:16<00:02, 24.83it/s]

Validating:  87%|████████▋ | 410/469 [00:16<00:02, 24.76it/s]
Epoch 2:  94%|█████████▍| 880/938 [00:50<00:03, 17.37it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  88%|████████▊ | 413/469 [00:16<00:02, 25.03it/s]
Epoch 2:  94%|█████████▍| 884/938 [00:50<00:03, 17.40it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  89%|████████▊ | 416/469 [00:16<00:02, 25.71it/s]
Epoch 2:  95%|█████████▍| 888/938 [00:50<00:02, 17.43it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  89%|████████▉ | 419/469 [00:16<00:01, 25.72it/s]

Validating:  90%|████████▉ | 422/469 [00:16<00:01, 24.97it/s]
Epoch 2:  95%|█████████▌| 892/938 [00:51<00:02, 17.45it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  91%|█████████ | 425/469 [00:17<00:01, 25.09it/s]
Epoch 2:  96%|█████████▌| 896/938 [00:51<00:02, 17.48it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  91%|█████████▏| 428/469 [00:17<00:01, 25.51it/s]
Epoch 2:  96%|█████████▌| 900/938 [00:51<00:02, 17.50it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  92%|█████████▏| 431/469 [00:17<00:01, 25.44it/s]

Validating:  93%|█████████▎| 434/469 [00:17<00:01, 24.12it/s]
Epoch 2:  96%|█████████▋| 904/938 [00:51<00:01, 17.52it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  93%|█████████▎| 437/469 [00:17<00:01, 25.07it/s]
Epoch 2:  97%|█████████▋| 908/938 [00:51<00:01, 17.54it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  94%|█████████▍| 440/469 [00:17<00:01, 25.33it/s]
Epoch 2:  97%|█████████▋| 912/938 [00:51<00:01, 17.57it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  94%|█████████▍| 443/469 [00:17<00:01, 25.01it/s]

Validating:  95%|█████████▌| 446/469 [00:17<00:00, 24.03it/s]
Epoch 2:  98%|█████████▊| 916/938 [00:52<00:01, 17.58it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  96%|█████████▌| 449/469 [00:18<00:00, 24.15it/s]
Epoch 2:  98%|█████████▊| 920/938 [00:52<00:01, 17.60it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  96%|█████████▋| 452/469 [00:18<00:00, 24.00it/s]
Epoch 2:  99%|█████████▊| 924/938 [00:52<00:00, 17.63it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  97%|█████████▋| 455/469 [00:18<00:00, 24.19it/s]

Validating:  98%|█████████▊| 458/469 [00:18<00:00, 25.10it/s]
Epoch 2:  99%|█████████▉| 928/938 [00:52<00:00, 17.65it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  98%|█████████▊| 461/469 [00:18<00:00, 23.87it/s]
Epoch 2:  99%|█████████▉| 932/938 [00:52<00:00, 17.67it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating:  99%|█████████▉| 464/469 [00:18<00:00, 24.43it/s]
Epoch 2: 100%|█████████▉| 936/938 [00:52<00:00, 17.69it/s, loss=0.679, v_num=12, val_rmse=0.568, train_rmse=0.755]

Validating: 100%|█████████▉| 467/469 [00:18<00:00, 23.92it/s]
Epoch 2: 100%|██████████| 938/938 [00:53<00:00, 17.69it/s, loss=0.679, v_num=12, val_rmse=0.516, train_rmse=0.755]

                                                             
Epoch 2: 100%|██████████| 938/938 [00:53<00:00, 17.68it/s, loss=0.679, v_num=12, val_rmse=0.516, train_rmse=0.699]
Epoch 2: 100%|██████████| 938/938 [00:53<00:00, 17.65it/s, loss=0.679, v_num=12, val_rmse=0.516, train_rmse=0.699]LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]


Testing: 0it [00:00, ?it/s]
Testing:   0%|          | 2/469 [00:00<00:29, 15.70it/s]
Testing:   1%|          | 5/469 [00:00<00:22, 20.80it/s]
Testing:   2%|▏         | 8/469 [00:00<00:20, 22.30it/s]
Testing:   2%|▏         | 11/469 [00:00<00:19, 22.93it/s]
Testing:   3%|▎         | 14/469 [00:00<00:19, 23.76it/s]
Testing:   4%|▎         | 17/469 [00:00<00:18, 24.84it/s]
Testing:   4%|▍         | 20/469 [00:00<00:18, 24.79it/s]
Testing:   5%|▍         | 23/469 [00:00<00:17, 25.83it/s]
Testing:   6%|▌         | 26/469 [00:01<00:17, 25.89it/s]
Testing:   6%|▌         | 29/469 [00:01<00:16, 26.06it/s]
Testing:   7%|▋         | 32/469 [00:01<00:16, 25.99it/s]
Testing:   7%|▋         | 35/469 [00:01<00:16, 25.95it/s]
Testing:   8%|▊         | 38/469 [00:01<00:16, 26.29it/s]
Testing:   9%|▊         | 41/469 [00:01<00:16, 26.75it/s]
Testing:   9%|▉         | 44/469 [00:01<00:16, 26.40it/s]
Testing:  10%|█         | 47/469 [00:01<00:16, 25.91it/s]
Testing:  11%|█         | 50/469 [00:02<00:16, 24.92it/s]
Testing:  11%|█▏        | 53/469 [00:02<00:16, 25.55it/s]
Testing:  12%|█▏        | 56/469 [00:02<00:16, 25.75it/s]
Testing:  13%|█▎        | 59/469 [00:02<00:15, 25.91it/s]
Testing:  13%|█▎        | 62/469 [00:02<00:15, 26.02it/s]
Testing:  14%|█▍        | 65/469 [00:02<00:15, 25.80it/s]
Testing:  14%|█▍        | 68/469 [00:02<00:15, 25.57it/s]
Testing:  15%|█▌        | 71/469 [00:02<00:15, 25.43it/s]
Testing:  16%|█▌        | 74/469 [00:02<00:15, 24.89it/s]
Testing:  16%|█▋        | 77/469 [00:03<00:15, 25.41it/s]
Testing:  17%|█▋        | 80/469 [00:03<00:15, 25.43it/s]
Testing:  18%|█▊        | 83/469 [00:03<00:15, 24.79it/s]
Testing:  18%|█▊        | 86/469 [00:03<00:15, 24.71it/s]
Testing:  19%|█▉        | 89/469 [00:03<00:15, 24.98it/s]
Testing:  20%|█▉        | 92/469 [00:03<00:15, 24.04it/s]
Testing:  20%|██        | 95/469 [00:03<00:15, 24.88it/s]
Testing:  21%|██        | 98/469 [00:03<00:15, 24.52it/s]
Testing:  22%|██▏       | 101/469 [00:04<00:14, 25.06it/s]
Testing:  22%|██▏       | 104/469 [00:04<00:14, 24.64it/s]
Testing:  23%|██▎       | 107/469 [00:04<00:14, 24.98it/s]
Testing:  23%|██▎       | 110/469 [00:04<00:13, 25.91it/s]
Testing:  24%|██▍       | 113/469 [00:04<00:14, 25.19it/s]
Testing:  25%|██▍       | 116/469 [00:04<00:15, 23.45it/s]
Testing:  25%|██▌       | 119/469 [00:04<00:14, 24.60it/s]
Testing:  26%|██▌       | 122/469 [00:04<00:13, 25.40it/s]
Testing:  27%|██▋       | 125/469 [00:04<00:13, 25.28it/s]
Testing:  27%|██▋       | 128/469 [00:05<00:13, 25.04it/s]
Testing:  28%|██▊       | 131/469 [00:05<00:13, 25.88it/s]
Testing:  29%|██▊       | 134/469 [00:05<00:12, 26.56it/s]
Testing:  29%|██▉       | 137/469 [00:05<00:13, 24.63it/s]
Testing:  30%|██▉       | 140/469 [00:05<00:13, 24.47it/s]
Testing:  30%|███       | 143/469 [00:05<00:12, 25.37it/s]
Testing:  31%|███       | 146/469 [00:05<00:12, 25.53it/s]
Testing:  32%|███▏      | 149/469 [00:05<00:12, 25.02it/s]
Testing:  32%|███▏      | 152/469 [00:06<00:12, 25.09it/s]
Testing:  33%|███▎      | 155/469 [00:06<00:12, 24.86it/s]
Testing:  34%|███▎      | 158/469 [00:06<00:12, 25.81it/s]
Testing:  34%|███▍      | 161/469 [00:06<00:11, 25.72it/s]
Testing:  35%|███▍      | 164/469 [00:06<00:12, 24.15it/s]
Testing:  36%|███▌      | 167/469 [00:06<00:12, 24.44it/s]
Testing:  36%|███▌      | 170/469 [00:06<00:12, 24.77it/s]
Testing:  37%|███▋      | 173/469 [00:06<00:12, 24.50it/s]
Testing:  38%|███▊      | 176/469 [00:07<00:11, 24.66it/s]
Testing:  38%|███▊      | 179/469 [00:07<00:11, 24.79it/s]
Testing:  39%|███▉      | 182/469 [00:07<00:11, 24.84it/s]
Testing:  39%|███▉      | 185/469 [00:07<00:11, 25.38it/s]
Testing:  40%|████      | 188/469 [00:07<00:10, 25.73it/s]
Testing:  41%|████      | 191/469 [00:07<00:11, 24.17it/s]
Testing:  41%|████▏     | 194/469 [00:07<00:11, 24.47it/s]
Testing:  42%|████▏     | 197/469 [00:07<00:10, 24.84it/s]
Testing:  43%|████▎     | 200/469 [00:07<00:10, 25.34it/s]
Testing:  43%|████▎     | 203/469 [00:08<00:10, 25.19it/s]
Testing:  44%|████▍     | 206/469 [00:08<00:10, 23.96it/s]
Testing:  45%|████▍     | 209/469 [00:08<00:10, 24.11it/s]
Testing:  45%|████▌     | 212/469 [00:08<00:10, 24.26it/s]
Testing:  46%|████▌     | 215/469 [00:08<00:09, 25.43it/s]
Testing:  46%|████▋     | 218/469 [00:08<00:10, 24.24it/s]
Testing:  47%|████▋     | 221/469 [00:08<00:10, 23.96it/s]
Testing:  48%|████▊     | 224/469 [00:08<00:10, 23.85it/s]
Testing:  49%|████▊     | 228/469 [00:09<00:09, 25.44it/s]
Testing:  49%|████▉     | 231/469 [00:09<00:09, 25.39it/s]
Testing:  50%|████▉     | 234/469 [00:09<00:09, 24.82it/s]
Testing:  51%|█████     | 237/469 [00:09<00:09, 25.72it/s]
Testing:  51%|█████     | 240/469 [00:09<00:09, 24.66it/s]
Testing:  52%|█████▏    | 243/469 [00:09<00:09, 23.20it/s]
Testing:  52%|█████▏    | 246/469 [00:09<00:09, 23.85it/s]
Testing:  53%|█████▎    | 249/469 [00:09<00:09, 24.35it/s]
Testing:  54%|█████▎    | 252/469 [00:10<00:08, 25.12it/s]
Testing:  54%|█████▍    | 255/469 [00:10<00:08, 25.52it/s]
Testing:  55%|█████▌    | 258/469 [00:10<00:08, 24.79it/s]
Testing:  56%|█████▌    | 261/469 [00:10<00:08, 24.01it/s]
Testing:  56%|█████▋    | 264/469 [00:10<00:08, 24.50it/s]
Testing:  57%|█████▋    | 267/469 [00:10<00:08, 25.06it/s]
Testing:  58%|█████▊    | 270/469 [00:10<00:08, 24.72it/s]
Testing:  58%|█████▊    | 273/469 [00:10<00:07, 24.66it/s]
Testing:  59%|█████▉    | 276/469 [00:11<00:07, 25.17it/s]
Testing:  59%|█████▉    | 279/469 [00:11<00:07, 25.42it/s]
Testing:  60%|██████    | 282/469 [00:11<00:07, 25.30it/s]
Testing:  61%|██████    | 285/469 [00:11<00:07, 25.78it/s]
Testing:  61%|██████▏   | 288/469 [00:11<00:06, 26.00it/s]
Testing:  62%|██████▏   | 291/469 [00:11<00:06, 26.84it/s]
Testing:  63%|██████▎   | 294/469 [00:11<00:06, 26.65it/s]
Testing:  63%|██████▎   | 297/469 [00:11<00:06, 26.92it/s]
Testing:  64%|██████▍   | 300/469 [00:11<00:06, 25.35it/s]
Testing:  65%|██████▍   | 303/469 [00:12<00:06, 25.23it/s]
Testing:  65%|██████▌   | 306/469 [00:12<00:06, 23.37it/s]
Testing:  66%|██████▌   | 309/469 [00:12<00:06, 24.21it/s]
Testing:  67%|██████▋   | 312/469 [00:12<00:06, 24.00it/s]
Testing:  67%|██████▋   | 315/469 [00:12<00:06, 24.48it/s]
Testing:  68%|██████▊   | 318/469 [00:12<00:06, 24.87it/s]
Testing:  68%|██████▊   | 321/469 [00:12<00:05, 25.16it/s]
Testing:  69%|██████▉   | 324/469 [00:12<00:05, 25.16it/s]
Testing:  70%|██████▉   | 327/469 [00:13<00:05, 25.35it/s]
Testing:  70%|███████   | 330/469 [00:13<00:05, 26.23it/s]
Testing:  71%|███████   | 333/469 [00:13<00:05, 25.92it/s]
Testing:  72%|███████▏  | 336/469 [00:13<00:05, 26.06it/s]
Testing:  72%|███████▏  | 339/469 [00:13<00:05, 25.54it/s]
Testing:  73%|███████▎  | 342/469 [00:13<00:05, 24.98it/s]
Testing:  74%|███████▎  | 345/469 [00:13<00:04, 26.15it/s]
Testing:  74%|███████▍  | 348/469 [00:13<00:04, 25.88it/s]
Testing:  75%|███████▍  | 351/469 [00:14<00:04, 24.90it/s]
Testing:  75%|███████▌  | 354/469 [00:14<00:04, 24.04it/s]
Testing:  76%|███████▌  | 357/469 [00:14<00:04, 24.14it/s]
Testing:  77%|███████▋  | 360/469 [00:14<00:04, 23.54it/s]
Testing:  77%|███████▋  | 363/469 [00:14<00:04, 23.50it/s]
Testing:  78%|███████▊  | 366/469 [00:14<00:04, 24.28it/s]
Testing:  79%|███████▊  | 369/469 [00:14<00:04, 24.11it/s]
Testing:  79%|███████▉  | 372/469 [00:14<00:03, 24.93it/s]
Testing:  80%|███████▉  | 375/469 [00:15<00:03, 25.44it/s]
Testing:  81%|████████  | 378/469 [00:15<00:03, 26.07it/s]
Testing:  81%|████████  | 381/469 [00:15<00:03, 26.45it/s]
Testing:  82%|████████▏ | 384/469 [00:15<00:03, 23.90it/s]
Testing:  83%|████████▎ | 387/469 [00:15<00:03, 23.90it/s]
Testing:  83%|████████▎ | 390/469 [00:15<00:03, 24.82it/s]
Testing:  84%|████████▍ | 393/469 [00:15<00:03, 24.80it/s]
Testing:  84%|████████▍ | 396/469 [00:15<00:02, 24.49it/s]
Testing:  85%|████████▌ | 399/469 [00:15<00:02, 25.25it/s]
Testing:  86%|████████▌ | 402/469 [00:16<00:02, 25.97it/s]
Testing:  86%|████████▋ | 405/469 [00:16<00:02, 26.10it/s]
Testing:  87%|████████▋ | 408/469 [00:16<00:02, 26.45it/s]
Testing:  88%|████████▊ | 411/469 [00:16<00:02, 26.28it/s]
Testing:  88%|████████▊ | 414/469 [00:16<00:02, 25.96it/s]
Testing:  89%|████████▉ | 417/469 [00:16<00:02, 25.82it/s]
Testing:  90%|████████▉ | 420/469 [00:16<00:01, 25.31it/s]
Testing:  90%|█████████ | 423/469 [00:16<00:01, 24.89it/s]
Testing:  91%|█████████ | 426/469 [00:17<00:01, 24.70it/s]
Testing:  91%|█████████▏| 429/469 [00:17<00:01, 25.39it/s]
Testing:  92%|█████████▏| 432/469 [00:17<00:01, 25.91it/s]
Testing:  93%|█████████▎| 435/469 [00:17<00:01, 26.61it/s]
Testing:  93%|█████████▎| 438/469 [00:17<00:01, 27.32it/s]
Testing:  94%|█████████▍| 441/469 [00:17<00:01, 26.84it/s]
Testing:  95%|█████████▍| 444/469 [00:17<00:00, 26.26it/s]
Testing:  95%|█████████▌| 447/469 [00:17<00:00, 26.39it/s]
Testing:  96%|█████████▌| 450/469 [00:17<00:00, 25.08it/s]
Testing:  97%|█████████▋| 453/469 [00:18<00:00, 25.07it/s]
Testing:  97%|█████████▋| 456/469 [00:18<00:00, 25.09it/s]
Testing:  98%|█████████▊| 459/469 [00:18<00:00, 25.67it/s]
Testing:  99%|█████████▊| 462/469 [00:18<00:00, 26.11it/s]
Testing:  99%|█████████▉| 465/469 [00:18<00:00, 26.85it/s]
Testing: 100%|█████████▉| 468/469 [00:18<00:00, 27.58it/s]--------------------------------------------------------------------------------
DATALOADER:0 TEST RESULTS
{'test_rmse': 0.5162707567214966}
--------------------------------------------------------------------------------

Testing: 100%|██████████| 469/469 [00:18<00:00, 25.15it/s]
  0%|          | 0/469 [02:57<?, ?it/s]
Global seed set to 48

['p_np'] False
2 1
iupac_vocab_size: 1491
training... 1491

  0%|          | 0/469 [00:00<?, ?it/s]Some weights of the model checkpoint at checkpoints/iupac were not used when initializing GPT2ForSequenceClassification: ['lm_head.weight']
- This IS expected if you are initializing GPT2ForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing GPT2ForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
GPU available: True, used: True
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]

  | Name        | Type                          | Params
--------------------------------------------------------------
0 | transformer | GPT2ForSequenceClassification | 7.1 M 
--------------------------------------------------------------
75.9 K    Trainable params
7.0 M     Non-trainable params
7.1 M     Total params
28.416    Total estimated model params size (MB)

Validation sanity check: 0it [00:00, ?it/s]
Validation sanity check:   0%|          | 0/2 [00:00<?, ?it/s]
                                                              Global seed set to 48


Training: 0it [00:00, ?it/s]
Training:   0%|          | 0/938 [00:00<?, ?it/s]
Epoch 0:   0%|          | 0/938 [00:00<?, ?it/s] 
Epoch 0:   0%|          | 1/938 [00:00<01:35,  9.85it/s]
Epoch 0:   0%|          | 1/938 [00:00<01:35,  9.81it/s, loss=3.5, v_num=13]
Epoch 0:   0%|          | 2/938 [00:00<01:24, 11.02it/s, loss=3.5, v_num=13]
Epoch 0:   0%|          | 3/938 [00:00<01:20, 11.65it/s, loss=3.5, v_num=13]
Epoch 0:   0%|          | 3/938 [00:00<01:20, 11.63it/s, loss=3.43, v_num=13]
Epoch 0:   0%|          | 4/938 [00:00<01:13, 12.66it/s, loss=3.35, v_num=13]
Epoch 0:   1%|          | 5/938 [00:00<01:11, 13.07it/s, loss=3.35, v_num=13]
Epoch 0:   1%|          | 5/938 [00:00<01:11, 13.05it/s, loss=3.4, v_num=13] 
Epoch 0:   1%|          | 6/938 [00:00<01:10, 13.15it/s, loss=3.36, v_num=13]
Epoch 0:   1%|          | 7/938 [00:00<01:09, 13.40it/s, loss=3.36, v_num=13]
Epoch 0:   1%|          | 7/938 [00:00<01:09, 13.39it/s, loss=3.39, v_num=13]
Epoch 0:   1%|          | 8/938 [00:00<01:09, 13.48it/s, loss=3.45, v_num=13]
Epoch 0:   1%|          | 9/938 [00:00<01:07, 13.79it/s, loss=3.45, v_num=13]
Epoch 0:   1%|          | 9/938 [00:00<01:07, 13.78it/s, loss=3.42, v_num=13]
Epoch 0:   1%|          | 10/938 [00:00<01:06, 13.91it/s, loss=3.42, v_num=13]
Epoch 0:   1%|          | 11/938 [00:00<01:08, 13.53it/s, loss=3.42, v_num=13]
Epoch 0:   1%|          | 11/938 [00:00<01:08, 13.51it/s, loss=3.41, v_num=13]
Epoch 0:   1%|▏         | 12/938 [00:00<01:10, 13.19it/s, loss=3.42, v_num=13]
Epoch 0:   1%|▏         | 13/938 [00:00<01:10, 13.07it/s, loss=3.42, v_num=13]
Epoch 0:   1%|▏         | 13/938 [00:00<01:10, 13.06it/s, loss=3.44, v_num=13]
Epoch 0:   1%|▏         | 14/938 [00:01<01:10, 13.17it/s, loss=3.4, v_num=13] 
Epoch 0:   2%|▏         | 15/938 [00:01<01:09, 13.32it/s, loss=3.4, v_num=13]
Epoch 0:   2%|▏         | 15/938 [00:01<01:09, 13.31it/s, loss=3.4, v_num=13]
Epoch 0:   2%|▏         | 16/938 [00:01<01:08, 13.52it/s, loss=3.38, v_num=13]
Epoch 0:   2%|▏         | 17/938 [00:01<01:07, 13.67it/s, loss=3.38, v_num=13]
Epoch 0:   2%|▏         | 17/938 [00:01<01:07, 13.66it/s, loss=3.36, v_num=13]
Epoch 0:   2%|▏         | 18/938 [00:01<01:07, 13.65it/s, loss=3.32, v_num=13]
Epoch 0:   2%|▏         | 19/938 [00:01<01:08, 13.50it/s, loss=3.32, v_num=13]
Epoch 0:   2%|▏         | 19/938 [00:01<01:08, 13.49it/s, loss=3.31, v_num=13]
Epoch 0:   2%|▏         | 20/938 [00:01<01:07, 13.58it/s, loss=3.27, v_num=13]
Epoch 0:   2%|▏         | 21/938 [00:01<01:07, 13.62it/s, loss=3.27, v_num=13]
Epoch 0:   2%|▏         | 21/938 [00:01<01:07, 13.62it/s, loss=3.22, v_num=13]
Epoch 0:   2%|▏         | 22/938 [00:01<01:06, 13.68it/s, loss=3.15, v_num=13]
Epoch 0:   2%|▏         | 23/938 [00:01<01:06, 13.79it/s, loss=3.15, v_num=13]
Epoch 0:   2%|▏         | 23/938 [00:01<01:06, 13.78it/s, loss=3.11, v_num=13]
Epoch 0:   3%|▎         | 24/938 [00:01<01:06, 13.84it/s, loss=3.07, v_num=13]
Epoch 0:   3%|▎         | 25/938 [00:01<01:05, 13.93it/s, loss=3.07, v_num=13]
Epoch 0:   3%|▎         | 25/938 [00:01<01:05, 13.93it/s, loss=3.01, v_num=13]
Epoch 0:   3%|▎         | 26/938 [00:01<01:05, 13.95it/s, loss=2.98, v_num=13]
Epoch 0:   3%|▎         | 27/938 [00:01<01:05, 13.96it/s, loss=2.98, v_num=13]
Epoch 0:   3%|▎         | 27/938 [00:01<01:05, 13.96it/s, loss=2.91, v_num=13]
Epoch 0:   3%|▎         | 28/938 [00:01<01:04, 14.03it/s, loss=2.8, v_num=13] 
Epoch 0:   3%|▎         | 29/938 [00:02<01:04, 14.00it/s, loss=2.8, v_num=13]
Epoch 0:   3%|▎         | 29/938 [00:02<01:04, 14.00it/s, loss=2.74, v_num=13]
Epoch 0:   3%|▎         | 30/938 [00:02<01:04, 14.02it/s, loss=2.67, v_num=13]
Epoch 0:   3%|▎         | 31/938 [00:02<01:04, 14.00it/s, loss=2.67, v_num=13]
Epoch 0:   3%|▎         | 31/938 [00:02<01:04, 13.99it/s, loss=2.57, v_num=13]
Epoch 0:   3%|▎         | 32/938 [00:02<01:04, 13.96it/s, loss=2.49, v_num=13]
Epoch 0:   4%|▎         | 33/938 [00:02<01:04, 14.03it/s, loss=2.49, v_num=13]
Epoch 0:   4%|▎         | 33/938 [00:02<01:04, 14.03it/s, loss=2.39, v_num=13]
Epoch 0:   4%|▎         | 34/938 [00:02<01:04, 14.08it/s, loss=2.32, v_num=13]
Epoch 0:   4%|▎         | 35/938 [00:02<01:03, 14.15it/s, loss=2.32, v_num=13]
Epoch 0:   4%|▎         | 35/938 [00:02<01:03, 14.15it/s, loss=2.24, v_num=13]
Epoch 0:   4%|▍         | 36/938 [00:02<01:03, 14.13it/s, loss=2.18, v_num=13]
Epoch 0:   4%|▍         | 37/938 [00:02<01:03, 14.14it/s, loss=2.18, v_num=13]
Epoch 0:   4%|▍         | 37/938 [00:02<01:03, 14.14it/s, loss=2.11, v_num=13]
Epoch 0:   4%|▍         | 38/938 [00:02<01:03, 14.11it/s, loss=2.05, v_num=13]
Epoch 0:   4%|▍         | 39/938 [00:02<01:03, 14.13it/s, loss=2.05, v_num=13]
Epoch 0:   4%|▍         | 39/938 [00:02<01:03, 14.13it/s, loss=1.98, v_num=13]
Epoch 0:   4%|▍         | 40/938 [00:02<01:03, 14.17it/s, loss=1.95, v_num=13]
Epoch 0:   4%|▍         | 41/938 [00:02<01:03, 14.18it/s, loss=1.95, v_num=13]
Epoch 0:   4%|▍         | 41/938 [00:02<01:03, 14.18it/s, loss=1.9, v_num=13] 
Epoch 0:   4%|▍         | 42/938 [00:02<01:02, 14.24it/s, loss=1.86, v_num=13]
Epoch 0:   5%|▍         | 43/938 [00:03<01:02, 14.21it/s, loss=1.86, v_num=13]
Epoch 0:   5%|▍         | 43/938 [00:03<01:02, 14.21it/s, loss=1.84, v_num=13]
Epoch 0:   5%|▍         | 44/938 [00:03<01:02, 14.24it/s, loss=1.8, v_num=13] 
Epoch 0:   5%|▍         | 45/938 [00:03<01:02, 14.26it/s, loss=1.8, v_num=13]
Epoch 0:   5%|▍         | 45/938 [00:03<01:02, 14.26it/s, loss=1.78, v_num=13]
Epoch 0:   5%|▍         | 46/938 [00:03<01:02, 14.28it/s, loss=1.72, v_num=13]
Epoch 0:   5%|▌         | 47/938 [00:03<01:02, 14.33it/s, loss=1.72, v_num=13]
Epoch 0:   5%|▌         | 47/938 [00:03<01:02, 14.32it/s, loss=1.7, v_num=13] 
Epoch 0:   5%|▌         | 48/938 [00:03<01:01, 14.36it/s, loss=1.69, v_num=13]
Epoch 0:   5%|▌         | 49/938 [00:03<01:01, 14.38it/s, loss=1.69, v_num=13]
Epoch 0:   5%|▌         | 49/938 [00:03<01:01, 14.38it/s, loss=1.67, v_num=13]
Epoch 0:   5%|▌         | 50/938 [00:03<01:01, 14.39it/s, loss=1.67, v_num=13]
Epoch 0:   5%|▌         | 51/938 [00:03<01:01, 14.38it/s, loss=1.67, v_num=13]
Epoch 0:   5%|▌         | 51/938 [00:03<01:01, 14.38it/s, loss=1.69, v_num=13]
Epoch 0:   6%|▌         | 52/938 [00:03<01:01, 14.38it/s, loss=1.68, v_num=13]
Epoch 0:   6%|▌         | 53/938 [00:03<01:01, 14.40it/s, loss=1.68, v_num=13]
Epoch 0:   6%|▌         | 53/938 [00:03<01:01, 14.40it/s, loss=1.67, v_num=13]
Epoch 0:   6%|▌         | 54/938 [00:03<01:01, 14.41it/s, loss=1.68, v_num=13]
Epoch 0:   6%|▌         | 55/938 [00:03<01:01, 14.34it/s, loss=1.68, v_num=13]
Epoch 0:   6%|▌         | 55/938 [00:03<01:01, 14.34it/s, loss=1.69, v_num=13]
Epoch 0:   6%|▌         | 56/938 [00:03<01:01, 14.39it/s, loss=1.71, v_num=13]
Epoch 0:   6%|▌         | 57/938 [00:03<01:01, 14.43it/s, loss=1.71, v_num=13]
Epoch 0:   6%|▌         | 57/938 [00:03<01:01, 14.43it/s, loss=1.71, v_num=13]
Epoch 0:   6%|▌         | 58/938 [00:04<01:01, 14.41it/s, loss=1.72, v_num=13]
Epoch 0:   6%|▋         | 59/938 [00:04<01:01, 14.38it/s, loss=1.72, v_num=13]
Epoch 0:   6%|▋         | 59/938 [00:04<01:01, 14.38it/s, loss=1.73, v_num=13]
Epoch 0:   6%|▋         | 60/938 [00:04<01:01, 14.30it/s, loss=1.73, v_num=13]
Epoch 0:   7%|▋         | 61/938 [00:04<01:01, 14.33it/s, loss=1.73, v_num=13]
Epoch 0:   7%|▋         | 61/938 [00:04<01:01, 14.33it/s, loss=1.73, v_num=13]
Epoch 0:   7%|▋         | 62/938 [00:04<01:01, 14.30it/s, loss=1.74, v_num=13]
Epoch 0:   7%|▋         | 63/938 [00:04<01:01, 14.25it/s, loss=1.74, v_num=13]
Epoch 0:   7%|▋         | 63/938 [00:04<01:01, 14.25it/s, loss=1.72, v_num=13]
Epoch 0:   7%|▋         | 64/938 [00:04<01:01, 14.26it/s, loss=1.73, v_num=13]
Epoch 0:   7%|▋         | 65/938 [00:04<01:01, 14.30it/s, loss=1.73, v_num=13]
Epoch 0:   7%|▋         | 65/938 [00:04<01:01, 14.29it/s, loss=1.69, v_num=13]
Epoch 0:   7%|▋         | 66/938 [00:04<01:00, 14.32it/s, loss=1.71, v_num=13]
Epoch 0:   7%|▋         | 67/938 [00:04<01:00, 14.34it/s, loss=1.71, v_num=13]
Epoch 0:   7%|▋         | 67/938 [00:04<01:00, 14.34it/s, loss=1.71, v_num=13]
Epoch 0:   7%|▋         | 68/938 [00:04<01:00, 14.34it/s, loss=1.72, v_num=13]
Epoch 0:   7%|▋         | 69/938 [00:04<01:00, 14.33it/s, loss=1.72, v_num=13]
Epoch 0:   7%|▋         | 69/938 [00:04<01:00, 14.32it/s, loss=1.72, v_num=13]
Epoch 0:   7%|▋         | 70/938 [00:04<01:00, 14.30it/s, loss=1.7, v_num=13] 
Epoch 0:   8%|▊         | 71/938 [00:04<01:00, 14.33it/s, loss=1.7, v_num=13]
Epoch 0:   8%|▊         | 71/938 [00:04<01:00, 14.33it/s, loss=1.69, v_num=13]
Epoch 0:   8%|▊         | 72/938 [00:05<01:00, 14.31it/s, loss=1.69, v_num=13]
Epoch 0:   8%|▊         | 73/938 [00:05<01:00, 14.29it/s, loss=1.69, v_num=13]
Epoch 0:   8%|▊         | 73/938 [00:05<01:00, 14.29it/s, loss=1.69, v_num=13]
Epoch 0:   8%|▊         | 74/938 [00:05<01:00, 14.31it/s, loss=1.71, v_num=13]
Epoch 0:   8%|▊         | 75/938 [00:05<01:00, 14.32it/s, loss=1.71, v_num=13]
Epoch 0:   8%|▊         | 75/938 [00:05<01:00, 14.32it/s, loss=1.69, v_num=13]
Epoch 0:   8%|▊         | 76/938 [00:05<01:00, 14.32it/s, loss=1.65, v_num=13]
Epoch 0:   8%|▊         | 77/938 [00:05<01:00, 14.35it/s, loss=1.65, v_num=13]
Epoch 0:   8%|▊         | 77/938 [00:05<01:00, 14.35it/s, loss=1.64, v_num=13]
Epoch 0:   8%|▊         | 78/938 [00:05<01:00, 14.18it/s, loss=1.64, v_num=13]
Epoch 0:   8%|▊         | 79/938 [00:05<01:00, 14.16it/s, loss=1.64, v_num=13]
Epoch 0:   8%|▊         | 79/938 [00:05<01:00, 14.16it/s, loss=1.64, v_num=13]
Epoch 0:   9%|▊         | 80/938 [00:05<01:00, 14.15it/s, loss=1.63, v_num=13]
Epoch 0:   9%|▊         | 81/938 [00:05<01:00, 14.17it/s, loss=1.63, v_num=13]
Epoch 0:   9%|▊         | 81/938 [00:05<01:00, 14.17it/s, loss=1.63, v_num=13]
Epoch 0:   9%|▊         | 82/938 [00:05<01:00, 14.17it/s, loss=1.63, v_num=13]
Epoch 0:   9%|▉         | 83/938 [00:05<01:00, 14.17it/s, loss=1.63, v_num=13]
Epoch 0:   9%|▉         | 83/938 [00:05<01:00, 14.17it/s, loss=1.66, v_num=13]
Epoch 0:   9%|▉         | 84/938 [00:05<01:00, 14.19it/s, loss=1.67, v_num=13]
Epoch 0:   9%|▉         | 85/938 [00:05<01:00, 14.20it/s, loss=1.67, v_num=13]
Epoch 0:   9%|▉         | 85/938 [00:05<01:00, 14.19it/s, loss=1.69, v_num=13]
Epoch 0:   9%|▉         | 86/938 [00:06<01:00, 14.19it/s, loss=1.68, v_num=13]
Epoch 0:   9%|▉         | 87/938 [00:06<01:00, 14.14it/s, loss=1.68, v_num=13]
Epoch 0:   9%|▉         | 87/938 [00:06<01:00, 14.14it/s, loss=1.69, v_num=13]
Epoch 0:   9%|▉         | 88/938 [00:06<00:59, 14.18it/s, loss=1.69, v_num=13]
Epoch 0:   9%|▉         | 89/938 [00:06<00:59, 14.19it/s, loss=1.69, v_num=13]
Epoch 0:   9%|▉         | 89/938 [00:06<00:59, 14.19it/s, loss=1.69, v_num=13]
Epoch 0:  10%|▉         | 90/938 [00:06<00:59, 14.21it/s, loss=1.7, v_num=13] 
Epoch 0:  10%|▉         | 91/938 [00:06<00:59, 14.22it/s, loss=1.7, v_num=13]
Epoch 0:  10%|▉         | 91/938 [00:06<00:59, 14.22it/s, loss=1.71, v_num=13]
Epoch 0:  10%|▉         | 92/938 [00:06<00:59, 14.21it/s, loss=1.72, v_num=13]
Epoch 0:  10%|▉         | 93/938 [00:06<00:59, 14.20it/s, loss=1.72, v_num=13]
Epoch 0:  10%|▉         | 93/938 [00:06<00:59, 14.20it/s, loss=1.72, v_num=13]
Epoch 0:  10%|█         | 94/938 [00:06<00:59, 14.20it/s, loss=1.69, v_num=13]
Epoch 0:  10%|█         | 95/938 [00:06<00:59, 14.20it/s, loss=1.69, v_num=13]
Epoch 0:  10%|█         | 95/938 [00:06<00:59, 14.20it/s, loss=1.69, v_num=13]
Epoch 0:  10%|█         | 96/938 [00:06<00:59, 14.20it/s, loss=1.69, v_num=13]
Epoch 0:  10%|█         | 97/938 [00:06<00:59, 14.17it/s, loss=1.69, v_num=13]
Epoch 0:  10%|█         | 97/938 [00:06<00:59, 14.17it/s, loss=1.68, v_num=13]
Epoch 0:  10%|█         | 98/938 [00:06<00:59, 14.15it/s, loss=1.68, v_num=13]
Epoch 0:  11%|█         | 99/938 [00:06<00:59, 14.18it/s, loss=1.68, v_num=13]
Epoch 0:  11%|█         | 99/938 [00:06<00:59, 14.17it/s, loss=1.67, v_num=13]
Epoch 0:  11%|█         | 100/938 [00:07<00:59, 14.15it/s, loss=1.66, v_num=13]
Epoch 0:  11%|█         | 101/938 [00:07<00:59, 14.14it/s, loss=1.66, v_num=13]
Epoch 0:  11%|█         | 101/938 [00:07<00:59, 14.14it/s, loss=1.66, v_num=13]
Epoch 0:  11%|█         | 102/938 [00:07<00:59, 14.08it/s, loss=1.66, v_num=13]
Epoch 0:  11%|█         | 103/938 [00:07<00:59, 14.02it/s, loss=1.66, v_num=13]
Epoch 0:  11%|█         | 103/938 [00:07<00:59, 14.02it/s, loss=1.64, v_num=13]
Epoch 0:  11%|█         | 104/938 [00:07<00:59, 14.07it/s, loss=1.62, v_num=13]
Epoch 0:  11%|█         | 105/938 [00:07<00:59, 14.07it/s, loss=1.62, v_num=13]
Epoch 0:  11%|█         | 105/938 [00:07<00:59, 14.06it/s, loss=1.63, v_num=13]
Epoch 0:  11%|█▏        | 106/938 [00:07<00:59, 14.09it/s, loss=1.62, v_num=13]
Epoch 0:  11%|█▏        | 107/938 [00:07<00:58, 14.11it/s, loss=1.62, v_num=13]
Epoch 0:  11%|█▏        | 107/938 [00:07<00:58, 14.10it/s, loss=1.63, v_num=13]
Epoch 0:  12%|█▏        | 108/938 [00:07<00:58, 14.11it/s, loss=1.62, v_num=13]
Epoch 0:  12%|█▏        | 109/938 [00:07<00:58, 14.10it/s, loss=1.62, v_num=13]
Epoch 0:  12%|█▏        | 109/938 [00:07<00:58, 14.10it/s, loss=1.64, v_num=13]
Epoch 0:  12%|█▏        | 110/938 [00:07<00:58, 14.12it/s, loss=1.65, v_num=13]
Epoch 0:  12%|█▏        | 111/938 [00:07<00:58, 14.11it/s, loss=1.65, v_num=13]
Epoch 0:  12%|█▏        | 111/938 [00:07<00:58, 14.11it/s, loss=1.66, v_num=13]
Epoch 0:  12%|█▏        | 112/938 [00:07<00:58, 14.13it/s, loss=1.67, v_num=13]
Epoch 0:  12%|█▏        | 113/938 [00:07<00:58, 14.13it/s, loss=1.67, v_num=13]
Epoch 0:  12%|█▏        | 113/938 [00:07<00:58, 14.13it/s, loss=1.69, v_num=13]
Epoch 0:  12%|█▏        | 114/938 [00:08<00:58, 14.12it/s, loss=1.7, v_num=13] 
Epoch 0:  12%|█▏        | 115/938 [00:08<00:58, 14.13it/s, loss=1.7, v_num=13]
Epoch 0:  12%|█▏        | 115/938 [00:08<00:58, 14.12it/s, loss=1.7, v_num=13]
Epoch 0:  12%|█▏        | 116/938 [00:08<00:58, 14.14it/s, loss=1.7, v_num=13]
Epoch 0:  12%|█▏        | 117/938 [00:08<00:58, 14.14it/s, loss=1.7, v_num=13]
Epoch 0:  12%|█▏        | 117/938 [00:08<00:58, 14.14it/s, loss=1.7, v_num=13]
Epoch 0:  13%|█▎        | 118/938 [00:08<00:57, 14.15it/s, loss=1.71, v_num=13]
Epoch 0:  13%|█▎        | 119/938 [00:08<00:57, 14.15it/s, loss=1.71, v_num=13]
Epoch 0:  13%|█▎        | 119/938 [00:08<00:57, 14.15it/s, loss=1.69, v_num=13]
Epoch 0:  13%|█▎        | 120/938 [00:08<00:57, 14.17it/s, loss=1.68, v_num=13]
Epoch 0:  13%|█▎        | 121/938 [00:08<00:57, 14.17it/s, loss=1.68, v_num=13]
Epoch 0:  13%|█▎        | 121/938 [00:08<00:57, 14.17it/s, loss=1.67, v_num=13]
Epoch 0:  13%|█▎        | 122/938 [00:08<00:57, 14.18it/s, loss=1.66, v_num=13]
Epoch 0:  13%|█▎        | 123/938 [00:08<00:57, 14.17it/s, loss=1.66, v_num=13]
Epoch 0:  13%|█▎        | 123/938 [00:08<00:57, 14.17it/s, loss=1.64, v_num=13]
Epoch 0:  13%|█▎        | 124/938 [00:08<00:57, 14.17it/s, loss=1.62, v_num=13]
Epoch 0:  13%|█▎        | 125/938 [00:08<00:57, 14.19it/s, loss=1.62, v_num=13]
Epoch 0:  13%|█▎        | 125/938 [00:08<00:57, 14.19it/s, loss=1.6, v_num=13] 
Epoch 0:  13%|█▎        | 126/938 [00:08<00:57, 14.18it/s, loss=1.61, v_num=13]
Epoch 0:  14%|█▎        | 127/938 [00:08<00:57, 14.14it/s, loss=1.61, v_num=13]
Epoch 0:  14%|█▎        | 127/938 [00:08<00:57, 14.14it/s, loss=1.58, v_num=13]
Epoch 0:  14%|█▎        | 128/938 [00:09<00:57, 14.14it/s, loss=1.56, v_num=13]
Epoch 0:  14%|█▍        | 129/938 [00:09<00:57, 14.16it/s, loss=1.56, v_num=13]
Epoch 0:  14%|█▍        | 129/938 [00:09<00:57, 14.15it/s, loss=1.53, v_num=13]
Epoch 0:  14%|█▍        | 130/938 [00:09<00:57, 14.15it/s, loss=1.48, v_num=13]
Epoch 0:  14%|█▍        | 131/938 [00:09<00:57, 14.13it/s, loss=1.48, v_num=13]
Epoch 0:  14%|█▍        | 131/938 [00:09<00:57, 14.12it/s, loss=1.45, v_num=13]
Epoch 0:  14%|█▍        | 132/938 [00:09<00:57, 14.10it/s, loss=1.42, v_num=13]
Epoch 0:  14%|█▍        | 133/938 [00:09<00:57, 14.11it/s, loss=1.42, v_num=13]
Epoch 0:  14%|█▍        | 133/938 [00:09<00:57, 14.11it/s, loss=1.38, v_num=13]
Epoch 0:  14%|█▍        | 134/938 [00:09<00:57, 14.07it/s, loss=1.36, v_num=13]
Epoch 0:  14%|█▍        | 135/938 [00:09<00:57, 14.09it/s, loss=1.36, v_num=13]
Epoch 0:  14%|█▍        | 135/938 [00:09<00:57, 14.09it/s, loss=1.33, v_num=13]
Epoch 0:  14%|█▍        | 136/938 [00:09<00:56, 14.09it/s, loss=1.3, v_num=13] 
Epoch 0:  15%|█▍        | 137/938 [00:09<00:56, 14.10it/s, loss=1.3, v_num=13]
Epoch 0:  15%|█▍        | 137/938 [00:09<00:56, 14.10it/s, loss=1.28, v_num=13]
Epoch 0:  15%|█▍        | 138/938 [00:09<00:56, 14.10it/s, loss=1.26, v_num=13]
Epoch 0:  15%|█▍        | 139/938 [00:09<00:56, 14.08it/s, loss=1.26, v_num=13]
Epoch 0:  15%|█▍        | 139/938 [00:09<00:56, 14.08it/s, loss=1.26, v_num=13]
Epoch 0:  15%|█▍        | 140/938 [00:09<00:56, 14.07it/s, loss=1.25, v_num=13]
Epoch 0:  15%|█▌        | 141/938 [00:10<00:56, 14.08it/s, loss=1.25, v_num=13]
Epoch 0:  15%|█▌        | 141/938 [00:10<00:56, 14.08it/s, loss=1.23, v_num=13]
Epoch 0:  15%|█▌        | 142/938 [00:10<00:56, 14.07it/s, loss=1.21, v_num=13]
Epoch 0:  15%|█▌        | 143/938 [00:10<00:56, 14.08it/s, loss=1.21, v_num=13]
Epoch 0:  15%|█▌        | 143/938 [00:10<00:56, 14.08it/s, loss=1.21, v_num=13]
Epoch 0:  15%|█▌        | 144/938 [00:10<00:56, 14.09it/s, loss=1.21, v_num=13]
Epoch 0:  15%|█▌        | 145/938 [00:10<00:56, 14.09it/s, loss=1.21, v_num=13]
Epoch 0:  15%|█▌        | 145/938 [00:10<00:56, 14.09it/s, loss=1.2, v_num=13] 
Epoch 0:  16%|█▌        | 146/938 [00:10<00:56, 14.08it/s, loss=1.18, v_num=13]
Epoch 0:  16%|█▌        | 147/938 [00:10<00:56, 14.11it/s, loss=1.18, v_num=13]
Epoch 0:  16%|█▌        | 147/938 [00:10<00:56, 14.10it/s, loss=1.16, v_num=13]
Epoch 0:  16%|█▌        | 148/938 [00:10<00:56, 14.10it/s, loss=1.15, v_num=13]
Epoch 0:  16%|█▌        | 149/938 [00:10<00:55, 14.11it/s, loss=1.15, v_num=13]
Epoch 0:  16%|█▌        | 149/938 [00:10<00:55, 14.11it/s, loss=1.13, v_num=13]
Epoch 0:  16%|█▌        | 150/938 [00:10<00:55, 14.13it/s, loss=1.11, v_num=13]
Epoch 0:  16%|█▌        | 151/938 [00:10<00:55, 14.13it/s, loss=1.11, v_num=13]
Epoch 0:  16%|█▌        | 151/938 [00:10<00:55, 14.13it/s, loss=1.11, v_num=13]
Epoch 0:  16%|█▌        | 152/938 [00:10<00:55, 14.14it/s, loss=1.1, v_num=13] 
Epoch 0:  16%|█▋        | 153/938 [00:10<00:55, 14.14it/s, loss=1.1, v_num=13]
Epoch 0:  16%|█▋        | 153/938 [00:10<00:55, 14.14it/s, loss=1.09, v_num=13]
Epoch 0:  16%|█▋        | 154/938 [00:10<00:55, 14.14it/s, loss=1.08, v_num=13]
Epoch 0:  17%|█▋        | 155/938 [00:10<00:55, 14.16it/s, loss=1.08, v_num=13]
Epoch 0:  17%|█▋        | 155/938 [00:10<00:55, 14.16it/s, loss=1.09, v_num=13]
Epoch 0:  17%|█▋        | 156/938 [00:11<00:55, 14.15it/s, loss=1.09, v_num=13]
Epoch 0:  17%|█▋        | 157/938 [00:11<00:55, 14.15it/s, loss=1.09, v_num=13]
Epoch 0:  17%|█▋        | 157/938 [00:11<00:55, 14.15it/s, loss=1.1, v_num=13] 
Epoch 0:  17%|█▋        | 158/938 [00:11<00:55, 14.12it/s, loss=1.09, v_num=13]
Epoch 0:  17%|█▋        | 159/938 [00:11<00:55, 14.14it/s, loss=1.09, v_num=13]
Epoch 0:  17%|█▋        | 159/938 [00:11<00:55, 14.14it/s, loss=1.1, v_num=13] 
Epoch 0:  17%|█▋        | 160/938 [00:11<00:55, 14.13it/s, loss=1.08, v_num=13]
Epoch 0:  17%|█▋        | 161/938 [00:11<00:54, 14.14it/s, loss=1.08, v_num=13]
Epoch 0:  17%|█▋        | 161/938 [00:11<00:54, 14.14it/s, loss=1.08, v_num=13]
Epoch 0:  17%|█▋        | 162/938 [00:11<00:54, 14.16it/s, loss=1.07, v_num=13]
Epoch 0:  17%|█▋        | 163/938 [00:11<00:54, 14.17it/s, loss=1.07, v_num=13]
Epoch 0:  17%|█▋        | 163/938 [00:11<00:54, 14.17it/s, loss=1.07, v_num=13]
Epoch 0:  17%|█▋        | 164/938 [00:11<00:54, 14.19it/s, loss=1.07, v_num=13]
Epoch 0:  18%|█▊        | 165/938 [00:11<00:54, 14.19it/s, loss=1.07, v_num=13]
Epoch 0:  18%|█▊        | 165/938 [00:11<00:54, 14.19it/s, loss=1.07, v_num=13]
Epoch 0:  18%|█▊        | 166/938 [00:11<00:54, 14.20it/s, loss=1.05, v_num=13]
Epoch 0:  18%|█▊        | 167/938 [00:11<00:54, 14.20it/s, loss=1.05, v_num=13]
Epoch 0:  18%|█▊        | 167/938 [00:11<00:54, 14.20it/s, loss=1.05, v_num=13]
Epoch 0:  18%|█▊        | 168/938 [00:11<00:54, 14.18it/s, loss=1.06, v_num=13]
Epoch 0:  18%|█▊        | 169/938 [00:11<00:54, 14.12it/s, loss=1.06, v_num=13]
Epoch 0:  18%|█▊        | 169/938 [00:11<00:54, 14.12it/s, loss=1.06, v_num=13]
Epoch 0:  18%|█▊        | 170/938 [00:12<00:54, 14.13it/s, loss=1.07, v_num=13]
Epoch 0:  18%|█▊        | 171/938 [00:12<00:54, 14.15it/s, loss=1.07, v_num=13]
Epoch 0:  18%|█▊        | 171/938 [00:12<00:54, 14.15it/s, loss=1.06, v_num=13]
Epoch 0:  18%|█▊        | 172/938 [00:12<00:54, 14.15it/s, loss=1.06, v_num=13]
Epoch 0:  18%|█▊        | 173/938 [00:12<00:54, 14.15it/s, loss=1.06, v_num=13]
Epoch 0:  18%|█▊        | 173/938 [00:12<00:54, 14.15it/s, loss=1.06, v_num=13]
Epoch 0:  19%|█▊        | 174/938 [00:12<00:53, 14.17it/s, loss=1.05, v_num=13]
Epoch 0:  19%|█▊        | 175/938 [00:12<00:53, 14.18it/s, loss=1.05, v_num=13]
Epoch 0:  19%|█▊        | 175/938 [00:12<00:53, 14.18it/s, loss=1.04, v_num=13]
Epoch 0:  19%|█▉        | 176/938 [00:12<00:53, 14.19it/s, loss=1.03, v_num=13]
Epoch 0:  19%|█▉        | 177/938 [00:12<00:53, 14.20it/s, loss=1.03, v_num=13]
Epoch 0:  19%|█▉        | 177/938 [00:12<00:53, 14.20it/s, loss=1.02, v_num=13]
Epoch 0:  19%|█▉        | 178/938 [00:12<00:53, 14.20it/s, loss=1.02, v_num=13]
Epoch 0:  19%|█▉        | 179/938 [00:12<00:53, 14.19it/s, loss=1.02, v_num=13]
Epoch 0:  19%|█▉        | 179/938 [00:12<00:53, 14.19it/s, loss=1, v_num=13]   
Epoch 0:  19%|█▉        | 180/938 [00:12<00:53, 14.20it/s, loss=1.01, v_num=13]
Epoch 0:  19%|█▉        | 181/938 [00:12<00:53, 14.19it/s, loss=1.01, v_num=13]
Epoch 0:  19%|█▉        | 181/938 [00:12<00:53, 14.19it/s, loss=1.01, v_num=13]
Epoch 0:  19%|█▉        | 182/938 [00:12<00:53, 14.19it/s, loss=1.02, v_num=13]
Epoch 0:  20%|█▉        | 183/938 [00:12<00:53, 14.19it/s, loss=1.02, v_num=13]
Epoch 0:  20%|█▉        | 183/938 [00:12<00:53, 14.19it/s, loss=1, v_num=13]   
Epoch 0:  20%|█▉        | 184/938 [00:12<00:53, 14.19it/s, loss=1.01, v_num=13]
Epoch 0:  20%|█▉        | 185/938 [00:13<00:53, 14.17it/s, loss=1.01, v_num=13]
Epoch 0:  20%|█▉        | 185/938 [00:13<00:53, 14.17it/s, loss=1.01, v_num=13]
Epoch 0:  20%|█▉        | 186/938 [00:13<00:53, 14.18it/s, loss=1, v_num=13]   
Epoch 0:  20%|█▉        | 187/938 [00:13<00:52, 14.19it/s, loss=1, v_num=13]
Epoch 0:  20%|█▉        | 187/938 [00:13<00:52, 14.19it/s, loss=1.01, v_num=13]
Epoch 0:  20%|██        | 188/938 [00:13<00:52, 14.18it/s, loss=1.02, v_num=13]
Epoch 0:  20%|██        | 189/938 [00:13<00:52, 14.19it/s, loss=1.02, v_num=13]
Epoch 0:  20%|██        | 189/938 [00:13<00:52, 14.19it/s, loss=1.02, v_num=13]
Epoch 0:  20%|██        | 190/938 [00:13<00:52, 14.18it/s, loss=1.03, v_num=13]
Epoch 0:  20%|██        | 191/938 [00:13<00:52, 14.18it/s, loss=1.03, v_num=13]
Epoch 0:  20%|██        | 191/938 [00:13<00:52, 14.18it/s, loss=1.02, v_num=13]
Epoch 0:  20%|██        | 192/938 [00:13<00:52, 14.20it/s, loss=1.02, v_num=13]
Epoch 0:  21%|██        | 193/938 [00:13<00:52, 14.17it/s, loss=1.02, v_num=13]
Epoch 0:  21%|██        | 193/938 [00:13<00:52, 14.17it/s, loss=1.03, v_num=13]
Epoch 0:  21%|██        | 194/938 [00:13<00:52, 14.18it/s, loss=1.05, v_num=13]
Epoch 0:  21%|██        | 195/938 [00:13<00:52, 14.19it/s, loss=1.05, v_num=13]
Epoch 0:  21%|██        | 195/938 [00:13<00:52, 14.18it/s, loss=1.05, v_num=13]
Epoch 0:  21%|██        | 196/938 [00:13<00:52, 14.18it/s, loss=1.06, v_num=13]
Epoch 0:  21%|██        | 197/938 [00:13<00:52, 14.18it/s, loss=1.06, v_num=13]
Epoch 0:  21%|██        | 197/938 [00:13<00:52, 14.18it/s, loss=1.04, v_num=13]
Epoch 0:  21%|██        | 198/938 [00:13<00:52, 14.17it/s, loss=1.05, v_num=13]
Epoch 0:  21%|██        | 199/938 [00:14<00:52, 14.18it/s, loss=1.05, v_num=13]
Epoch 0:  21%|██        | 199/938 [00:14<00:52, 14.18it/s, loss=1.05, v_num=13]
Epoch 0:  21%|██▏       | 200/938 [00:14<00:52, 14.19it/s, loss=1.04, v_num=13]
Epoch 0:  21%|██▏       | 201/938 [00:14<00:51, 14.19it/s, loss=1.04, v_num=13]
Epoch 0:  21%|██▏       | 201/938 [00:14<00:51, 14.19it/s, loss=1.03, v_num=13]
Epoch 0:  22%|██▏       | 202/938 [00:14<00:51, 14.19it/s, loss=1.03, v_num=13]
Epoch 0:  22%|██▏       | 203/938 [00:14<00:51, 14.20it/s, loss=1.03, v_num=13]
Epoch 0:  22%|██▏       | 203/938 [00:14<00:51, 14.20it/s, loss=1.02, v_num=13]
Epoch 0:  22%|██▏       | 204/938 [00:14<00:51, 14.20it/s, loss=1.01, v_num=13]
Epoch 0:  22%|██▏       | 205/938 [00:14<00:51, 14.20it/s, loss=1.01, v_num=13]
Epoch 0:  22%|██▏       | 205/938 [00:14<00:51, 14.20it/s, loss=1, v_num=13]   
Epoch 0:  22%|██▏       | 206/938 [00:14<00:51, 14.19it/s, loss=1.01, v_num=13]
Epoch 0:  22%|██▏       | 207/938 [00:14<00:51, 14.19it/s, loss=1.01, v_num=13]
Epoch 0:  22%|██▏       | 207/938 [00:14<00:51, 14.18it/s, loss=1.01, v_num=13]
Epoch 0:  22%|██▏       | 208/938 [00:14<00:51, 14.19it/s, loss=1, v_num=13]   
Epoch 0:  22%|██▏       | 209/938 [00:14<00:51, 14.20it/s, loss=1, v_num=13]
Epoch 0:  22%|██▏       | 209/938 [00:14<00:51, 14.20it/s, loss=0.988, v_num=13]
Epoch 0:  22%|██▏       | 210/938 [00:14<00:51, 14.18it/s, loss=0.977, v_num=13]
Epoch 0:  22%|██▏       | 211/938 [00:14<00:51, 14.19it/s, loss=0.977, v_num=13]
Epoch 0:  22%|██▏       | 211/938 [00:14<00:51, 14.19it/s, loss=0.976, v_num=13]
Epoch 0:  23%|██▎       | 212/938 [00:14<00:51, 14.20it/s, loss=0.975, v_num=13]
Epoch 0:  23%|██▎       | 213/938 [00:15<00:51, 14.20it/s, loss=0.975, v_num=13]
Epoch 0:  23%|██▎       | 213/938 [00:15<00:51, 14.20it/s, loss=0.954, v_num=13]
Epoch 0:  23%|██▎       | 214/938 [00:15<00:51, 14.19it/s, loss=0.959, v_num=13]
Epoch 0:  23%|██▎       | 215/938 [00:15<00:50, 14.20it/s, loss=0.959, v_num=13]
Epoch 0:  23%|██▎       | 215/938 [00:15<00:50, 14.20it/s, loss=0.954, v_num=13]
Epoch 0:  23%|██▎       | 216/938 [00:15<00:50, 14.21it/s, loss=0.948, v_num=13]
Epoch 0:  23%|██▎       | 217/938 [00:15<00:50, 14.20it/s, loss=0.948, v_num=13]
Epoch 0:  23%|██▎       | 217/938 [00:15<00:50, 14.20it/s, loss=0.948, v_num=13]
Epoch 0:  23%|██▎       | 218/938 [00:15<00:50, 14.21it/s, loss=0.951, v_num=13]
Epoch 0:  23%|██▎       | 219/938 [00:15<00:50, 14.20it/s, loss=0.951, v_num=13]
Epoch 0:  23%|██▎       | 219/938 [00:15<00:50, 14.20it/s, loss=0.951, v_num=13]
Epoch 0:  23%|██▎       | 220/938 [00:15<00:50, 14.19it/s, loss=0.968, v_num=13]
Epoch 0:  24%|██▎       | 221/938 [00:15<00:50, 14.17it/s, loss=0.968, v_num=13]
Epoch 0:  24%|██▎       | 221/938 [00:15<00:50, 14.17it/s, loss=0.97, v_num=13] 
Epoch 0:  24%|██▎       | 222/938 [00:15<00:50, 14.17it/s, loss=0.978, v_num=13]
Epoch 0:  24%|██▍       | 223/938 [00:15<00:50, 14.18it/s, loss=0.978, v_num=13]
Epoch 0:  24%|██▍       | 223/938 [00:15<00:50, 14.18it/s, loss=0.997, v_num=13]
Epoch 0:  24%|██▍       | 224/938 [00:15<00:50, 14.18it/s, loss=0.987, v_num=13]
Epoch 0:  24%|██▍       | 225/938 [00:15<00:50, 14.19it/s, loss=0.987, v_num=13]
Epoch 0:  24%|██▍       | 225/938 [00:15<00:50, 14.19it/s, loss=0.993, v_num=13]
Epoch 0:  24%|██▍       | 226/938 [00:15<00:50, 14.20it/s, loss=0.984, v_num=13]
Epoch 0:  24%|██▍       | 227/938 [00:15<00:50, 14.21it/s, loss=0.984, v_num=13]
Epoch 0:  24%|██▍       | 227/938 [00:15<00:50, 14.20it/s, loss=0.976, v_num=13]
Epoch 0:  24%|██▍       | 228/938 [00:16<00:49, 14.20it/s, loss=0.971, v_num=13]
Epoch 0:  24%|██▍       | 229/938 [00:16<00:49, 14.21it/s, loss=0.971, v_num=13]
Epoch 0:  24%|██▍       | 229/938 [00:16<00:49, 14.21it/s, loss=0.97, v_num=13] 
Epoch 0:  25%|██▍       | 230/938 [00:16<00:49, 14.20it/s, loss=0.965, v_num=13]
Epoch 0:  25%|██▍       | 231/938 [00:16<00:49, 14.20it/s, loss=0.965, v_num=13]
Epoch 0:  25%|██▍       | 231/938 [00:16<00:49, 14.20it/s, loss=0.964, v_num=13]
Epoch 0:  25%|██▍       | 232/938 [00:16<00:49, 14.21it/s, loss=0.967, v_num=13]
Epoch 0:  25%|██▍       | 233/938 [00:16<00:49, 14.20it/s, loss=0.967, v_num=13]
Epoch 0:  25%|██▍       | 233/938 [00:16<00:49, 14.20it/s, loss=0.977, v_num=13]
Epoch 0:  25%|██▍       | 234/938 [00:16<00:49, 14.21it/s, loss=0.954, v_num=13]
Epoch 0:  25%|██▌       | 235/938 [00:16<00:49, 14.22it/s, loss=0.954, v_num=13]
Epoch 0:  25%|██▌       | 235/938 [00:16<00:49, 14.22it/s, loss=0.947, v_num=13]
Epoch 0:  25%|██▌       | 236/938 [00:16<00:49, 14.23it/s, loss=0.948, v_num=13]
Epoch 0:  25%|██▌       | 237/938 [00:16<00:49, 14.24it/s, loss=0.948, v_num=13]
Epoch 0:  25%|██▌       | 237/938 [00:16<00:49, 14.24it/s, loss=0.96, v_num=13] 
Epoch 0:  25%|██▌       | 238/938 [00:16<00:49, 14.25it/s, loss=0.956, v_num=13]
Epoch 0:  25%|██▌       | 239/938 [00:16<00:49, 14.19it/s, loss=0.956, v_num=13]
Epoch 0:  25%|██▌       | 239/938 [00:16<00:49, 14.19it/s, loss=0.958, v_num=13]
Epoch 0:  26%|██▌       | 240/938 [00:16<00:49, 14.18it/s, loss=0.94, v_num=13] 
Epoch 0:  26%|██▌       | 241/938 [00:16<00:49, 14.20it/s, loss=0.94, v_num=13]
Epoch 0:  26%|██▌       | 241/938 [00:16<00:49, 14.20it/s, loss=0.936, v_num=13]
Epoch 0:  26%|██▌       | 242/938 [00:17<00:49, 14.19it/s, loss=0.924, v_num=13]
Epoch 0:  26%|██▌       | 243/938 [00:17<00:49, 14.18it/s, loss=0.924, v_num=13]
Epoch 0:  26%|██▌       | 243/938 [00:17<00:49, 14.18it/s, loss=0.914, v_num=13]
Epoch 0:  26%|██▌       | 244/938 [00:17<00:48, 14.18it/s, loss=0.903, v_num=13]
Epoch 0:  26%|██▌       | 245/938 [00:17<00:48, 14.17it/s, loss=0.903, v_num=13]
Epoch 0:  26%|██▌       | 245/938 [00:17<00:48, 14.17it/s, loss=0.891, v_num=13]
Epoch 0:  26%|██▌       | 246/938 [00:17<00:48, 14.18it/s, loss=0.892, v_num=13]
Epoch 0:  26%|██▋       | 247/938 [00:17<00:48, 14.18it/s, loss=0.892, v_num=13]
Epoch 0:  26%|██▋       | 247/938 [00:17<00:48, 14.18it/s, loss=0.89, v_num=13] 
Epoch 0:  26%|██▋       | 248/938 [00:17<00:48, 14.16it/s, loss=0.89, v_num=13]
Epoch 0:  27%|██▋       | 249/938 [00:17<00:48, 14.15it/s, loss=0.89, v_num=13]
Epoch 0:  27%|██▋       | 249/938 [00:17<00:48, 14.15it/s, loss=0.892, v_num=13]
Epoch 0:  27%|██▋       | 250/938 [00:17<00:48, 14.15it/s, loss=0.887, v_num=13]
Epoch 0:  27%|██▋       | 251/938 [00:17<00:48, 14.15it/s, loss=0.887, v_num=13]
Epoch 0:  27%|██▋       | 251/938 [00:17<00:48, 14.15it/s, loss=0.878, v_num=13]
Epoch 0:  27%|██▋       | 252/938 [00:17<00:48, 14.15it/s, loss=0.881, v_num=13]
Epoch 0:  27%|██▋       | 253/938 [00:17<00:48, 14.16it/s, loss=0.881, v_num=13]
Epoch 0:  27%|██▋       | 253/938 [00:17<00:48, 14.16it/s, loss=0.874, v_num=13]
Epoch 0:  27%|██▋       | 254/938 [00:17<00:48, 14.16it/s, loss=0.877, v_num=13]
Epoch 0:  27%|██▋       | 255/938 [00:18<00:48, 14.16it/s, loss=0.877, v_num=13]
Epoch 0:  27%|██▋       | 255/938 [00:18<00:48, 14.16it/s, loss=0.876, v_num=13]
Epoch 0:  27%|██▋       | 256/938 [00:18<00:48, 14.17it/s, loss=0.876, v_num=13]
Epoch 0:  27%|██▋       | 257/938 [00:18<00:48, 14.18it/s, loss=0.876, v_num=13]
Epoch 0:  27%|██▋       | 257/938 [00:18<00:48, 14.18it/s, loss=0.864, v_num=13]
Epoch 0:  28%|██▊       | 258/938 [00:18<00:47, 14.17it/s, loss=0.857, v_num=13]
Epoch 0:  28%|██▊       | 259/938 [00:18<00:47, 14.17it/s, loss=0.857, v_num=13]
Epoch 0:  28%|██▊       | 259/938 [00:18<00:47, 14.17it/s, loss=0.847, v_num=13]
Epoch 0:  28%|██▊       | 260/938 [00:18<00:47, 14.18it/s, loss=0.842, v_num=13]
Epoch 0:  28%|██▊       | 261/938 [00:18<00:47, 14.17it/s, loss=0.842, v_num=13]
Epoch 0:  28%|██▊       | 261/938 [00:18<00:47, 14.17it/s, loss=0.842, v_num=13]
Epoch 0:  28%|██▊       | 262/938 [00:18<00:47, 14.18it/s, loss=0.847, v_num=13]
Epoch 0:  28%|██▊       | 263/938 [00:18<00:47, 14.18it/s, loss=0.847, v_num=13]
Epoch 0:  28%|██▊       | 263/938 [00:18<00:47, 14.18it/s, loss=0.846, v_num=13]
Epoch 0:  28%|██▊       | 264/938 [00:18<00:47, 14.19it/s, loss=0.856, v_num=13]
Epoch 0:  28%|██▊       | 265/938 [00:18<00:47, 14.19it/s, loss=0.856, v_num=13]
Epoch 0:  28%|██▊       | 265/938 [00:18<00:47, 14.19it/s, loss=0.866, v_num=13]
Epoch 0:  28%|██▊       | 266/938 [00:18<00:47, 14.20it/s, loss=0.862, v_num=13]
Epoch 0:  28%|██▊       | 267/938 [00:18<00:47, 14.20it/s, loss=0.862, v_num=13]
Epoch 0:  28%|██▊       | 267/938 [00:18<00:47, 14.20it/s, loss=0.866, v_num=13]
Epoch 0:  29%|██▊       | 268/938 [00:18<00:47, 14.16it/s, loss=0.873, v_num=13]
Epoch 0:  29%|██▊       | 269/938 [00:18<00:47, 14.18it/s, loss=0.873, v_num=13]
Epoch 0:  29%|██▊       | 269/938 [00:18<00:47, 14.18it/s, loss=0.864, v_num=13]
Epoch 0:  29%|██▉       | 270/938 [00:19<00:47, 14.19it/s, loss=0.876, v_num=13]
Epoch 0:  29%|██▉       | 271/938 [00:19<00:46, 14.20it/s, loss=0.876, v_num=13]
Epoch 0:  29%|██▉       | 271/938 [00:19<00:46, 14.20it/s, loss=0.88, v_num=13] 
Epoch 0:  29%|██▉       | 272/938 [00:19<00:46, 14.19it/s, loss=0.864, v_num=13]
Epoch 0:  29%|██▉       | 273/938 [00:19<00:46, 14.19it/s, loss=0.864, v_num=13]
Epoch 0:  29%|██▉       | 273/938 [00:19<00:46, 14.19it/s, loss=0.855, v_num=13]
Epoch 0:  29%|██▉       | 274/938 [00:19<00:46, 14.19it/s, loss=0.863, v_num=13]
Epoch 0:  29%|██▉       | 275/938 [00:19<00:46, 14.19it/s, loss=0.863, v_num=13]
Epoch 0:  29%|██▉       | 275/938 [00:19<00:46, 14.19it/s, loss=0.873, v_num=13]
Epoch 0:  29%|██▉       | 276/938 [00:19<00:46, 14.19it/s, loss=0.874, v_num=13]
Epoch 0:  30%|██▉       | 277/938 [00:19<00:46, 14.20it/s, loss=0.874, v_num=13]
Epoch 0:  30%|██▉       | 277/938 [00:19<00:46, 14.19it/s, loss=0.877, v_num=13]
Epoch 0:  30%|██▉       | 278/938 [00:19<00:46, 14.20it/s, loss=0.874, v_num=13]
Epoch 0:  30%|██▉       | 279/938 [00:19<00:46, 14.20it/s, loss=0.874, v_num=13]
Epoch 0:  30%|██▉       | 279/938 [00:19<00:46, 14.20it/s, loss=0.873, v_num=13]
Epoch 0:  30%|██▉       | 280/938 [00:19<00:46, 14.21it/s, loss=0.88, v_num=13] 
Epoch 0:  30%|██▉       | 281/938 [00:19<00:46, 14.21it/s, loss=0.88, v_num=13]
Epoch 0:  30%|██▉       | 281/938 [00:19<00:46, 14.21it/s, loss=0.886, v_num=13]
Epoch 0:  30%|███       | 282/938 [00:19<00:46, 14.21it/s, loss=0.88, v_num=13] 
Epoch 0:  30%|███       | 283/938 [00:19<00:46, 14.22it/s, loss=0.88, v_num=13]
Epoch 0:  30%|███       | 283/938 [00:19<00:46, 14.22it/s, loss=0.876, v_num=13]
Epoch 0:  30%|███       | 284/938 [00:19<00:46, 14.21it/s, loss=0.883, v_num=13]
Epoch 0:  30%|███       | 285/938 [00:20<00:45, 14.22it/s, loss=0.883, v_num=13]
Epoch 0:  30%|███       | 285/938 [00:20<00:45, 14.22it/s, loss=0.877, v_num=13]
Epoch 0:  30%|███       | 286/938 [00:20<00:45, 14.23it/s, loss=0.876, v_num=13]
Epoch 0:  31%|███       | 287/938 [00:20<00:45, 14.23it/s, loss=0.876, v_num=13]
Epoch 0:  31%|███       | 287/938 [00:20<00:45, 14.23it/s, loss=0.882, v_num=13]
Epoch 0:  31%|███       | 288/938 [00:20<00:45, 14.23it/s, loss=0.882, v_num=13]
Epoch 0:  31%|███       | 289/938 [00:20<00:45, 14.23it/s, loss=0.882, v_num=13]
Epoch 0:  31%|███       | 289/938 [00:20<00:45, 14.23it/s, loss=0.882, v_num=13]
Epoch 0:  31%|███       | 290/938 [00:20<00:45, 14.24it/s, loss=0.884, v_num=13]
Epoch 0:  31%|███       | 291/938 [00:20<00:45, 14.24it/s, loss=0.884, v_num=13]
Epoch 0:  31%|███       | 291/938 [00:20<00:45, 14.24it/s, loss=0.885, v_num=13]
Epoch 0:  31%|███       | 292/938 [00:20<00:45, 14.24it/s, loss=0.893, v_num=13]
Epoch 0:  31%|███       | 293/938 [00:20<00:45, 14.25it/s, loss=0.893, v_num=13]
Epoch 0:  31%|███       | 293/938 [00:20<00:45, 14.25it/s, loss=0.901, v_num=13]
Epoch 0:  31%|███▏      | 294/938 [00:20<00:45, 14.25it/s, loss=0.891, v_num=13]
Epoch 0:  31%|███▏      | 295/938 [00:20<00:45, 14.24it/s, loss=0.891, v_num=13]
Epoch 0:  31%|███▏      | 295/938 [00:20<00:45, 14.24it/s, loss=0.881, v_num=13]
Epoch 0:  32%|███▏      | 296/938 [00:20<00:45, 14.25it/s, loss=0.876, v_num=13]
Epoch 0:  32%|███▏      | 297/938 [00:20<00:45, 14.23it/s, loss=0.876, v_num=13]
Epoch 0:  32%|███▏      | 297/938 [00:20<00:45, 14.23it/s, loss=0.879, v_num=13]
Epoch 0:  32%|███▏      | 298/938 [00:20<00:44, 14.24it/s, loss=0.878, v_num=13]
Epoch 0:  32%|███▏      | 299/938 [00:20<00:44, 14.25it/s, loss=0.878, v_num=13]
Epoch 0:  32%|███▏      | 299/938 [00:20<00:44, 14.25it/s, loss=0.872, v_num=13]
Epoch 0:  32%|███▏      | 300/938 [00:21<00:44, 14.25it/s, loss=0.888, v_num=13]
Epoch 0:  32%|███▏      | 301/938 [00:21<00:44, 14.25it/s, loss=0.888, v_num=13]
Epoch 0:  32%|███▏      | 301/938 [00:21<00:44, 14.25it/s, loss=0.882, v_num=13]
Epoch 0:  32%|███▏      | 302/938 [00:21<00:44, 14.26it/s, loss=0.884, v_num=13]
Epoch 0:  32%|███▏      | 303/938 [00:21<00:44, 14.26it/s, loss=0.884, v_num=13]
Epoch 0:  32%|███▏      | 303/938 [00:21<00:44, 14.26it/s, loss=0.891, v_num=13]
Epoch 0:  32%|███▏      | 304/938 [00:21<00:44, 14.26it/s, loss=0.882, v_num=13]
Epoch 0:  33%|███▎      | 305/938 [00:21<00:44, 14.27it/s, loss=0.882, v_num=13]
Epoch 0:  33%|███▎      | 305/938 [00:21<00:44, 14.27it/s, loss=0.892, v_num=13]
Epoch 0:  33%|███▎      | 306/938 [00:21<00:44, 14.26it/s, loss=0.895, v_num=13]
Epoch 0:  33%|███▎      | 307/938 [00:21<00:44, 14.26it/s, loss=0.895, v_num=13]
Epoch 0:  33%|███▎      | 307/938 [00:21<00:44, 14.26it/s, loss=0.882, v_num=13]
Epoch 0:  33%|███▎      | 308/938 [00:21<00:44, 14.28it/s, loss=0.87, v_num=13] 
Epoch 0:  33%|███▎      | 309/938 [00:21<00:44, 14.27it/s, loss=0.87, v_num=13]
Epoch 0:  33%|███▎      | 309/938 [00:21<00:44, 14.27it/s, loss=0.871, v_num=13]
Epoch 0:  33%|███▎      | 310/938 [00:21<00:44, 14.26it/s, loss=0.88, v_num=13] 
Epoch 0:  33%|███▎      | 311/938 [00:21<00:43, 14.27it/s, loss=0.88, v_num=13]
Epoch 0:  33%|███▎      | 311/938 [00:21<00:43, 14.27it/s, loss=0.878, v_num=13]
Epoch 0:  33%|███▎      | 312/938 [00:21<00:43, 14.28it/s, loss=0.87, v_num=13] 
Epoch 0:  33%|███▎      | 313/938 [00:21<00:43, 14.28it/s, loss=0.87, v_num=13]
Epoch 0:  33%|███▎      | 313/938 [00:21<00:43, 14.28it/s, loss=0.865, v_num=13]
Epoch 0:  33%|███▎      | 314/938 [00:21<00:43, 14.29it/s, loss=0.863, v_num=13]
Epoch 0:  34%|███▎      | 315/938 [00:22<00:43, 14.29it/s, loss=0.863, v_num=13]
Epoch 0:  34%|███▎      | 315/938 [00:22<00:43, 14.29it/s, loss=0.866, v_num=13]
Epoch 0:  34%|███▎      | 316/938 [00:22<00:43, 14.28it/s, loss=0.878, v_num=13]
Epoch 0:  34%|███▍      | 317/938 [00:22<00:43, 14.28it/s, loss=0.878, v_num=13]
Epoch 0:  34%|███▍      | 317/938 [00:22<00:43, 14.28it/s, loss=0.872, v_num=13]
Epoch 0:  34%|███▍      | 318/938 [00:22<00:43, 14.26it/s, loss=0.872, v_num=13]
Epoch 0:  34%|███▍      | 319/938 [00:22<00:43, 14.27it/s, loss=0.872, v_num=13]
Epoch 0:  34%|███▍      | 319/938 [00:22<00:43, 14.27it/s, loss=0.883, v_num=13]
Epoch 0:  34%|███▍      | 320/938 [00:22<00:43, 14.27it/s, loss=0.871, v_num=13]
Epoch 0:  34%|███▍      | 321/938 [00:22<00:43, 14.26it/s, loss=0.871, v_num=13]
Epoch 0:  34%|███▍      | 321/938 [00:22<00:43, 14.26it/s, loss=0.868, v_num=13]
Epoch 0:  34%|███▍      | 322/938 [00:22<00:43, 14.27it/s, loss=0.867, v_num=13]
Epoch 0:  34%|███▍      | 323/938 [00:22<00:43, 14.27it/s, loss=0.867, v_num=13]
Epoch 0:  34%|███▍      | 323/938 [00:22<00:43, 14.27it/s, loss=0.863, v_num=13]
Epoch 0:  35%|███▍      | 324/938 [00:22<00:43, 14.27it/s, loss=0.865, v_num=13]
Epoch 0:  35%|███▍      | 325/938 [00:22<00:42, 14.28it/s, loss=0.865, v_num=13]
Epoch 0:  35%|███▍      | 325/938 [00:22<00:42, 14.28it/s, loss=0.851, v_num=13]
Epoch 0:  35%|███▍      | 326/938 [00:22<00:42, 14.28it/s, loss=0.852, v_num=13]
Epoch 0:  35%|███▍      | 327/938 [00:22<00:42, 14.28it/s, loss=0.852, v_num=13]
Epoch 0:  35%|███▍      | 327/938 [00:22<00:42, 14.28it/s, loss=0.85, v_num=13] 
Epoch 0:  35%|███▍      | 328/938 [00:22<00:42, 14.29it/s, loss=0.85, v_num=13]
Epoch 0:  35%|███▌      | 329/938 [00:23<00:42, 14.29it/s, loss=0.85, v_num=13]
Epoch 0:  35%|███▌      | 329/938 [00:23<00:42, 14.29it/s, loss=0.854, v_num=13]
Epoch 0:  35%|███▌      | 330/938 [00:23<00:42, 14.29it/s, loss=0.832, v_num=13]
Epoch 0:  35%|███▌      | 331/938 [00:23<00:42, 14.30it/s, loss=0.832, v_num=13]
Epoch 0:  35%|███▌      | 331/938 [00:23<00:42, 14.30it/s, loss=0.834, v_num=13]
Epoch 0:  35%|███▌      | 332/938 [00:23<00:42, 14.29it/s, loss=0.833, v_num=13]
Epoch 0:  36%|███▌      | 333/938 [00:23<00:42, 14.30it/s, loss=0.833, v_num=13]
Epoch 0:  36%|███▌      | 333/938 [00:23<00:42, 14.30it/s, loss=0.837, v_num=13]
Epoch 0:  36%|███▌      | 334/938 [00:23<00:42, 14.30it/s, loss=0.84, v_num=13] 
Epoch 0:  36%|███▌      | 335/938 [00:23<00:42, 14.29it/s, loss=0.84, v_num=13]
Epoch 0:  36%|███▌      | 335/938 [00:23<00:42, 14.29it/s, loss=0.836, v_num=13]
Epoch 0:  36%|███▌      | 336/938 [00:23<00:42, 14.29it/s, loss=0.825, v_num=13]
Epoch 0:  36%|███▌      | 337/938 [00:23<00:42, 14.29it/s, loss=0.825, v_num=13]
Epoch 0:  36%|███▌      | 337/938 [00:23<00:42, 14.29it/s, loss=0.83, v_num=13] 
Epoch 0:  36%|███▌      | 338/938 [00:23<00:41, 14.30it/s, loss=0.82, v_num=13]
Epoch 0:  36%|███▌      | 339/938 [00:23<00:41, 14.30it/s, loss=0.82, v_num=13]
Epoch 0:  36%|███▌      | 339/938 [00:23<00:41, 14.30it/s, loss=0.817, v_num=13]
Epoch 0:  36%|███▌      | 340/938 [00:23<00:41, 14.30it/s, loss=0.809, v_num=13]
Epoch 0:  36%|███▋      | 341/938 [00:23<00:41, 14.30it/s, loss=0.809, v_num=13]
Epoch 0:  36%|███▋      | 341/938 [00:23<00:41, 14.30it/s, loss=0.814, v_num=13]
Epoch 0:  36%|███▋      | 342/938 [00:23<00:41, 14.30it/s, loss=0.818, v_num=13]
Epoch 0:  37%|███▋      | 343/938 [00:23<00:41, 14.31it/s, loss=0.818, v_num=13]
Epoch 0:  37%|███▋      | 343/938 [00:23<00:41, 14.31it/s, loss=0.809, v_num=13]
Epoch 0:  37%|███▋      | 344/938 [00:24<00:41, 14.31it/s, loss=0.804, v_num=13]
Epoch 0:  37%|███▋      | 345/938 [00:24<00:41, 14.31it/s, loss=0.804, v_num=13]
Epoch 0:  37%|███▋      | 345/938 [00:24<00:41, 14.31it/s, loss=0.802, v_num=13]
Epoch 0:  37%|███▋      | 346/938 [00:24<00:41, 14.32it/s, loss=0.796, v_num=13]
Epoch 0:  37%|███▋      | 347/938 [00:24<00:41, 14.31it/s, loss=0.796, v_num=13]
Epoch 0:  37%|███▋      | 347/938 [00:24<00:41, 14.31it/s, loss=0.806, v_num=13]
Epoch 0:  37%|███▋      | 348/938 [00:24<00:41, 14.31it/s, loss=0.807, v_num=13]
Epoch 0:  37%|███▋      | 349/938 [00:24<00:41, 14.32it/s, loss=0.807, v_num=13]
Epoch 0:  37%|███▋      | 349/938 [00:24<00:41, 14.32it/s, loss=0.804, v_num=13]
Epoch 0:  37%|███▋      | 350/938 [00:24<00:41, 14.31it/s, loss=0.815, v_num=13]
Epoch 0:  37%|███▋      | 351/938 [00:24<00:41, 14.32it/s, loss=0.815, v_num=13]
Epoch 0:  37%|███▋      | 351/938 [00:24<00:41, 14.32it/s, loss=0.82, v_num=13] 
Epoch 0:  38%|███▊      | 352/938 [00:24<00:40, 14.32it/s, loss=0.832, v_num=13]
Epoch 0:  38%|███▊      | 353/938 [00:24<00:40, 14.32it/s, loss=0.832, v_num=13]
Epoch 0:  38%|███▊      | 353/938 [00:24<00:40, 14.32it/s, loss=0.833, v_num=13]
Epoch 0:  38%|███▊      | 354/938 [00:24<00:40, 14.32it/s, loss=0.834, v_num=13]
Epoch 0:  38%|███▊      | 355/938 [00:24<00:40, 14.32it/s, loss=0.834, v_num=13]
Epoch 0:  38%|███▊      | 355/938 [00:24<00:40, 14.32it/s, loss=0.837, v_num=13]
Epoch 0:  38%|███▊      | 356/938 [00:24<00:40, 14.31it/s, loss=0.834, v_num=13]
Epoch 0:  38%|███▊      | 357/938 [00:24<00:40, 14.31it/s, loss=0.834, v_num=13]
Epoch 0:  38%|███▊      | 357/938 [00:24<00:40, 14.31it/s, loss=0.834, v_num=13]
Epoch 0:  38%|███▊      | 358/938 [00:25<00:40, 14.30it/s, loss=0.841, v_num=13]
Epoch 0:  38%|███▊      | 359/938 [00:25<00:40, 14.30it/s, loss=0.841, v_num=13]
Epoch 0:  38%|███▊      | 359/938 [00:25<00:40, 14.30it/s, loss=0.838, v_num=13]
Epoch 0:  38%|███▊      | 360/938 [00:25<00:40, 14.30it/s, loss=0.843, v_num=13]
Epoch 0:  38%|███▊      | 361/938 [00:25<00:40, 14.30it/s, loss=0.843, v_num=13]
Epoch 0:  38%|███▊      | 361/938 [00:25<00:40, 14.30it/s, loss=0.846, v_num=13]
Epoch 0:  39%|███▊      | 362/938 [00:25<00:40, 14.30it/s, loss=0.838, v_num=13]
Epoch 0:  39%|███▊      | 363/938 [00:25<00:40, 14.31it/s, loss=0.838, v_num=13]
Epoch 0:  39%|███▊      | 363/938 [00:25<00:40, 14.31it/s, loss=0.846, v_num=13]
Epoch 0:  39%|███▉      | 364/938 [00:25<00:40, 14.31it/s, loss=0.857, v_num=13]
Epoch 0:  39%|███▉      | 365/938 [00:25<00:40, 14.32it/s, loss=0.857, v_num=13]
Epoch 0:  39%|███▉      | 365/938 [00:25<00:40, 14.32it/s, loss=0.861, v_num=13]
Epoch 0:  39%|███▉      | 366/938 [00:25<00:39, 14.32it/s, loss=0.868, v_num=13]
Epoch 0:  39%|███▉      | 367/938 [00:25<00:39, 14.31it/s, loss=0.868, v_num=13]
Epoch 0:  39%|███▉      | 367/938 [00:25<00:39, 14.31it/s, loss=0.867, v_num=13]
Epoch 0:  39%|███▉      | 368/938 [00:25<00:39, 14.31it/s, loss=0.868, v_num=13]
Epoch 0:  39%|███▉      | 369/938 [00:25<00:39, 14.31it/s, loss=0.868, v_num=13]
Epoch 0:  39%|███▉      | 369/938 [00:25<00:39, 14.31it/s, loss=0.873, v_num=13]
Epoch 0:  39%|███▉      | 370/938 [00:25<00:39, 14.31it/s, loss=0.87, v_num=13] 
Epoch 0:  40%|███▉      | 371/938 [00:25<00:39, 14.32it/s, loss=0.87, v_num=13]
Epoch 0:  40%|███▉      | 371/938 [00:25<00:39, 14.32it/s, loss=0.866, v_num=13]
Epoch 0:  40%|███▉      | 372/938 [00:25<00:39, 14.32it/s, loss=0.857, v_num=13]
Epoch 0:  40%|███▉      | 373/938 [00:26<00:39, 14.31it/s, loss=0.857, v_num=13]
Epoch 0:  40%|███▉      | 373/938 [00:26<00:39, 14.31it/s, loss=0.853, v_num=13]
Epoch 0:  40%|███▉      | 374/938 [00:26<00:39, 14.32it/s, loss=0.851, v_num=13]
Epoch 0:  40%|███▉      | 375/938 [00:26<00:39, 14.32it/s, loss=0.851, v_num=13]
Epoch 0:  40%|███▉      | 375/938 [00:26<00:39, 14.32it/s, loss=0.849, v_num=13]
Epoch 0:  40%|████      | 376/938 [00:26<00:39, 14.33it/s, loss=0.852, v_num=13]
Epoch 0:  40%|████      | 377/938 [00:26<00:39, 14.33it/s, loss=0.852, v_num=13]
Epoch 0:  40%|████      | 377/938 [00:26<00:39, 14.33it/s, loss=0.855, v_num=13]
Epoch 0:  40%|████      | 378/938 [00:26<00:39, 14.33it/s, loss=0.863, v_num=13]
Epoch 0:  40%|████      | 379/938 [00:26<00:39, 14.32it/s, loss=0.863, v_num=13]
Epoch 0:  40%|████      | 379/938 [00:26<00:39, 14.32it/s, loss=0.864, v_num=13]
Epoch 0:  41%|████      | 380/938 [00:26<00:38, 14.32it/s, loss=0.856, v_num=13]
Epoch 0:  41%|████      | 381/938 [00:26<00:38, 14.33it/s, loss=0.856, v_num=13]
Epoch 0:  41%|████      | 381/938 [00:26<00:38, 14.33it/s, loss=0.85, v_num=13] 
Epoch 0:  41%|████      | 382/938 [00:26<00:38, 14.33it/s, loss=0.86, v_num=13]
Epoch 0:  41%|████      | 383/938 [00:26<00:38, 14.34it/s, loss=0.86, v_num=13]
Epoch 0:  41%|████      | 383/938 [00:26<00:38, 14.34it/s, loss=0.861, v_num=13]
Epoch 0:  41%|████      | 384/938 [00:26<00:38, 14.34it/s, loss=0.85, v_num=13] 
Epoch 0:  41%|████      | 385/938 [00:26<00:38, 14.35it/s, loss=0.85, v_num=13]
Epoch 0:  41%|████      | 385/938 [00:26<00:38, 14.35it/s, loss=0.838, v_num=13]
Epoch 0:  41%|████      | 386/938 [00:26<00:38, 14.34it/s, loss=0.839, v_num=13]
Epoch 0:  41%|████▏     | 387/938 [00:26<00:38, 14.34it/s, loss=0.839, v_num=13]
Epoch 0:  41%|████▏     | 387/938 [00:26<00:38, 14.34it/s, loss=0.839, v_num=13]
Epoch 0:  41%|████▏     | 388/938 [00:27<00:38, 14.35it/s, loss=0.844, v_num=13]
Epoch 0:  41%|████▏     | 389/938 [00:27<00:38, 14.34it/s, loss=0.844, v_num=13]
Epoch 0:  41%|████▏     | 389/938 [00:27<00:38, 14.34it/s, loss=0.846, v_num=13]
Epoch 0:  42%|████▏     | 390/938 [00:27<00:38, 14.34it/s, loss=0.844, v_num=13]
Epoch 0:  42%|████▏     | 391/938 [00:27<00:38, 14.35it/s, loss=0.844, v_num=13]
Epoch 0:  42%|████▏     | 391/938 [00:27<00:38, 14.35it/s, loss=0.845, v_num=13]
Epoch 0:  42%|████▏     | 392/938 [00:27<00:38, 14.35it/s, loss=0.851, v_num=13]
Epoch 0:  42%|████▏     | 393/938 [00:27<00:37, 14.35it/s, loss=0.851, v_num=13]
Epoch 0:  42%|████▏     | 393/938 [00:27<00:37, 14.35it/s, loss=0.855, v_num=13]
Epoch 0:  42%|████▏     | 394/938 [00:27<00:37, 14.35it/s, loss=0.858, v_num=13]
Epoch 0:  42%|████▏     | 395/938 [00:27<00:37, 14.36it/s, loss=0.858, v_num=13]
Epoch 0:  42%|████▏     | 395/938 [00:27<00:37, 14.35it/s, loss=0.864, v_num=13]
Epoch 0:  42%|████▏     | 396/938 [00:27<00:37, 14.35it/s, loss=0.863, v_num=13]
Epoch 0:  42%|████▏     | 397/938 [00:27<00:37, 14.35it/s, loss=0.863, v_num=13]
Epoch 0:  42%|████▏     | 397/938 [00:27<00:37, 14.35it/s, loss=0.854, v_num=13]
Epoch 0:  42%|████▏     | 398/938 [00:27<00:37, 14.35it/s, loss=0.844, v_num=13]
Epoch 0:  43%|████▎     | 399/938 [00:27<00:37, 14.35it/s, loss=0.844, v_num=13]
Epoch 0:  43%|████▎     | 399/938 [00:27<00:37, 14.35it/s, loss=0.846, v_num=13]
Epoch 0:  43%|████▎     | 400/938 [00:27<00:37, 14.35it/s, loss=0.849, v_num=13]
Epoch 0:  43%|████▎     | 401/938 [00:27<00:37, 14.35it/s, loss=0.849, v_num=13]
Epoch 0:  43%|████▎     | 401/938 [00:27<00:37, 14.35it/s, loss=0.846, v_num=13]
Epoch 0:  43%|████▎     | 402/938 [00:27<00:37, 14.36it/s, loss=0.842, v_num=13]
Epoch 0:  43%|████▎     | 403/938 [00:28<00:37, 14.36it/s, loss=0.842, v_num=13]
Epoch 0:  43%|████▎     | 403/938 [00:28<00:37, 14.36it/s, loss=0.837, v_num=13]
Epoch 0:  43%|████▎     | 404/938 [00:28<00:37, 14.36it/s, loss=0.833, v_num=13]
Epoch 0:  43%|████▎     | 405/938 [00:28<00:37, 14.36it/s, loss=0.833, v_num=13]
Epoch 0:  43%|████▎     | 405/938 [00:28<00:37, 14.36it/s, loss=0.843, v_num=13]
Epoch 0:  43%|████▎     | 406/938 [00:28<00:37, 14.36it/s, loss=0.831, v_num=13]
Epoch 0:  43%|████▎     | 407/938 [00:28<00:36, 14.37it/s, loss=0.831, v_num=13]
Epoch 0:  43%|████▎     | 407/938 [00:28<00:36, 14.37it/s, loss=0.83, v_num=13] 
Epoch 0:  43%|████▎     | 408/938 [00:28<00:36, 14.37it/s, loss=0.83, v_num=13]
Epoch 0:  44%|████▎     | 409/938 [00:28<00:36, 14.36it/s, loss=0.83, v_num=13]
Epoch 0:  44%|████▎     | 409/938 [00:28<00:36, 14.36it/s, loss=0.836, v_num=13]
Epoch 0:  44%|████▎     | 410/938 [00:28<00:36, 14.37it/s, loss=0.839, v_num=13]
Epoch 0:  44%|████▍     | 411/938 [00:28<00:36, 14.37it/s, loss=0.839, v_num=13]
Epoch 0:  44%|████▍     | 411/938 [00:28<00:36, 14.37it/s, loss=0.829, v_num=13]
Epoch 0:  44%|████▍     | 412/938 [00:28<00:36, 14.37it/s, loss=0.833, v_num=13]
Epoch 0:  44%|████▍     | 413/938 [00:28<00:36, 14.37it/s, loss=0.833, v_num=13]
Epoch 0:  44%|████▍     | 413/938 [00:28<00:36, 14.37it/s, loss=0.843, v_num=13]
Epoch 0:  44%|████▍     | 414/938 [00:28<00:36, 14.37it/s, loss=0.842, v_num=13]
Epoch 0:  44%|████▍     | 415/938 [00:28<00:36, 14.37it/s, loss=0.842, v_num=13]
Epoch 0:  44%|████▍     | 415/938 [00:28<00:36, 14.37it/s, loss=0.832, v_num=13]
Epoch 0:  44%|████▍     | 416/938 [00:28<00:36, 14.37it/s, loss=0.829, v_num=13]
Epoch 0:  44%|████▍     | 417/938 [00:29<00:36, 14.38it/s, loss=0.829, v_num=13]
Epoch 0:  44%|████▍     | 417/938 [00:29<00:36, 14.38it/s, loss=0.833, v_num=13]
Epoch 0:  45%|████▍     | 418/938 [00:29<00:36, 14.38it/s, loss=0.833, v_num=13]
Epoch 0:  45%|████▍     | 419/938 [00:29<00:36, 14.38it/s, loss=0.833, v_num=13]
Epoch 0:  45%|████▍     | 419/938 [00:29<00:36, 14.38it/s, loss=0.834, v_num=13]
Epoch 0:  45%|████▍     | 420/938 [00:29<00:36, 14.38it/s, loss=0.835, v_num=13]
Epoch 0:  45%|████▍     | 421/938 [00:29<00:35, 14.39it/s, loss=0.835, v_num=13]
Epoch 0:  45%|████▍     | 421/938 [00:29<00:35, 14.39it/s, loss=0.83, v_num=13] 
Epoch 0:  45%|████▍     | 422/938 [00:29<00:35, 14.39it/s, loss=0.83, v_num=13]
Epoch 0:  45%|████▌     | 423/938 [00:29<00:35, 14.39it/s, loss=0.83, v_num=13]
Epoch 0:  45%|████▌     | 423/938 [00:29<00:35, 14.39it/s, loss=0.833, v_num=13]
Epoch 0:  45%|████▌     | 424/938 [00:29<00:35, 14.39it/s, loss=0.842, v_num=13]
Epoch 0:  45%|████▌     | 425/938 [00:29<00:35, 14.39it/s, loss=0.842, v_num=13]
Epoch 0:  45%|████▌     | 425/938 [00:29<00:35, 14.39it/s, loss=0.851, v_num=13]
Epoch 0:  45%|████▌     | 426/938 [00:29<00:35, 14.39it/s, loss=0.858, v_num=13]
Epoch 0:  46%|████▌     | 427/938 [00:29<00:35, 14.39it/s, loss=0.858, v_num=13]
Epoch 0:  46%|████▌     | 427/938 [00:29<00:35, 14.39it/s, loss=0.85, v_num=13] 
Epoch 0:  46%|████▌     | 428/938 [00:29<00:35, 14.39it/s, loss=0.843, v_num=13]
Epoch 0:  46%|████▌     | 429/938 [00:29<00:35, 14.39it/s, loss=0.843, v_num=13]
Epoch 0:  46%|████▌     | 429/938 [00:29<00:35, 14.39it/s, loss=0.848, v_num=13]
Epoch 0:  46%|████▌     | 430/938 [00:29<00:35, 14.40it/s, loss=0.838, v_num=13]
Epoch 0:  46%|████▌     | 431/938 [00:29<00:35, 14.40it/s, loss=0.838, v_num=13]
Epoch 0:  46%|████▌     | 431/938 [00:29<00:35, 14.40it/s, loss=0.84, v_num=13] 
Epoch 0:  46%|████▌     | 432/938 [00:29<00:35, 14.40it/s, loss=0.834, v_num=13]
Epoch 0:  46%|████▌     | 433/938 [00:30<00:35, 14.39it/s, loss=0.834, v_num=13]
Epoch 0:  46%|████▌     | 433/938 [00:30<00:35, 14.39it/s, loss=0.828, v_num=13]
Epoch 0:  46%|████▋     | 434/938 [00:30<00:35, 14.38it/s, loss=0.821, v_num=13]
Epoch 0:  46%|████▋     | 435/938 [00:30<00:34, 14.39it/s, loss=0.821, v_num=13]
Epoch 0:  46%|████▋     | 435/938 [00:30<00:34, 14.39it/s, loss=0.837, v_num=13]
Epoch 0:  46%|████▋     | 436/938 [00:30<00:34, 14.39it/s, loss=0.849, v_num=13]
Epoch 0:  47%|████▋     | 437/938 [00:30<00:34, 14.40it/s, loss=0.849, v_num=13]
Epoch 0:  47%|████▋     | 437/938 [00:30<00:34, 14.40it/s, loss=0.858, v_num=13]
Epoch 0:  47%|████▋     | 438/938 [00:30<00:34, 14.40it/s, loss=0.861, v_num=13]
Epoch 0:  47%|████▋     | 439/938 [00:30<00:34, 14.40it/s, loss=0.861, v_num=13]
Epoch 0:  47%|████▋     | 439/938 [00:30<00:34, 14.40it/s, loss=0.854, v_num=13]
Epoch 0:  47%|████▋     | 440/938 [00:30<00:34, 14.40it/s, loss=0.858, v_num=13]
Epoch 0:  47%|████▋     | 441/938 [00:30<00:34, 14.40it/s, loss=0.858, v_num=13]
Epoch 0:  47%|████▋     | 441/938 [00:30<00:34, 14.40it/s, loss=0.862, v_num=13]
Epoch 0:  47%|████▋     | 442/938 [00:30<00:34, 14.40it/s, loss=0.867, v_num=13]
Epoch 0:  47%|████▋     | 443/938 [00:30<00:34, 14.41it/s, loss=0.867, v_num=13]
Epoch 0:  47%|████▋     | 443/938 [00:30<00:34, 14.41it/s, loss=0.863, v_num=13]
Epoch 0:  47%|████▋     | 444/938 [00:30<00:34, 14.41it/s, loss=0.854, v_num=13]
Epoch 0:  47%|████▋     | 445/938 [00:30<00:34, 14.41it/s, loss=0.854, v_num=13]
Epoch 0:  47%|████▋     | 445/938 [00:30<00:34, 14.41it/s, loss=0.84, v_num=13] 
Epoch 0:  48%|████▊     | 446/938 [00:30<00:34, 14.41it/s, loss=0.843, v_num=13]
Epoch 0:  48%|████▊     | 447/938 [00:30<00:34, 14.42it/s, loss=0.843, v_num=13]
Epoch 0:  48%|████▊     | 447/938 [00:30<00:34, 14.42it/s, loss=0.842, v_num=13]
Epoch 0:  48%|████▊     | 448/938 [00:31<00:33, 14.42it/s, loss=0.849, v_num=13]
Epoch 0:  48%|████▊     | 449/938 [00:31<00:33, 14.42it/s, loss=0.849, v_num=13]
Epoch 0:  48%|████▊     | 449/938 [00:31<00:33, 14.42it/s, loss=0.834, v_num=13]
Epoch 0:  48%|████▊     | 450/938 [00:31<00:33, 14.42it/s, loss=0.837, v_num=13]
Epoch 0:  48%|████▊     | 451/938 [00:31<00:33, 14.43it/s, loss=0.837, v_num=13]
Epoch 0:  48%|████▊     | 451/938 [00:31<00:33, 14.43it/s, loss=0.837, v_num=13]
Epoch 0:  48%|████▊     | 452/938 [00:31<00:33, 14.43it/s, loss=0.836, v_num=13]
Epoch 0:  48%|████▊     | 453/938 [00:31<00:33, 14.43it/s, loss=0.836, v_num=13]
Epoch 0:  48%|████▊     | 453/938 [00:31<00:33, 14.43it/s, loss=0.833, v_num=13]
Epoch 0:  48%|████▊     | 454/938 [00:31<00:33, 14.43it/s, loss=0.833, v_num=13]
Epoch 0:  49%|████▊     | 455/938 [00:31<00:33, 14.44it/s, loss=0.833, v_num=13]
Epoch 0:  49%|████▊     | 455/938 [00:31<00:33, 14.43it/s, loss=0.823, v_num=13]
Epoch 0:  49%|████▊     | 456/938 [00:31<00:33, 14.44it/s, loss=0.811, v_num=13]
Epoch 0:  49%|████▊     | 457/938 [00:31<00:33, 14.44it/s, loss=0.811, v_num=13]
Epoch 0:  49%|████▊     | 457/938 [00:31<00:33, 14.44it/s, loss=0.802, v_num=13]
Epoch 0:  49%|████▉     | 458/938 [00:31<00:33, 14.44it/s, loss=0.808, v_num=13]
Epoch 0:  49%|████▉     | 459/938 [00:31<00:33, 14.44it/s, loss=0.808, v_num=13]
Epoch 0:  49%|████▉     | 459/938 [00:31<00:33, 14.44it/s, loss=0.812, v_num=13]
Epoch 0:  49%|████▉     | 460/938 [00:31<00:33, 14.43it/s, loss=0.805, v_num=13]
Epoch 0:  49%|████▉     | 461/938 [00:31<00:33, 14.43it/s, loss=0.805, v_num=13]
Epoch 0:  49%|████▉     | 461/938 [00:31<00:33, 14.43it/s, loss=0.809, v_num=13]
Epoch 0:  49%|████▉     | 462/938 [00:32<00:32, 14.43it/s, loss=0.812, v_num=13]
Epoch 0:  49%|████▉     | 463/938 [00:32<00:32, 14.44it/s, loss=0.812, v_num=13]
Epoch 0:  49%|████▉     | 463/938 [00:32<00:32, 14.44it/s, loss=0.809, v_num=13]
Epoch 0:  49%|████▉     | 464/938 [00:32<00:32, 14.43it/s, loss=0.822, v_num=13]
Epoch 0:  50%|████▉     | 465/938 [00:32<00:32, 14.44it/s, loss=0.822, v_num=13]
Epoch 0:  50%|████▉     | 465/938 [00:32<00:32, 14.44it/s, loss=0.819, v_num=13]
Epoch 0:  50%|████▉     | 466/938 [00:32<00:32, 14.44it/s, loss=0.811, v_num=13]
Epoch 0:  50%|████▉     | 467/938 [00:32<00:32, 14.44it/s, loss=0.811, v_num=13]
Epoch 0:  50%|████▉     | 467/938 [00:32<00:32, 14.44it/s, loss=0.83, v_num=13] 
Epoch 0:  50%|████▉     | 468/938 [00:32<00:32, 14.45it/s, loss=0.825, v_num=13]
Epoch 0:  50%|█████     | 469/938 [00:32<00:32, 14.46it/s, loss=0.825, v_num=13]
Epoch 0:  50%|█████     | 469/938 [00:32<00:32, 14.46it/s, loss=0.833, v_num=13]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]

Validating:   1%|          | 3/469 [00:00<00:19, 23.79it/s]
Epoch 0:  50%|█████     | 473/938 [00:32<00:32, 14.52it/s, loss=0.833, v_num=13]

Validating:   1%|▏         | 6/469 [00:00<00:17, 25.77it/s]
Epoch 0:  51%|█████     | 477/938 [00:32<00:31, 14.58it/s, loss=0.833, v_num=13]

Validating:   2%|▏         | 9/469 [00:00<00:18, 25.38it/s]
Epoch 0:  51%|█████▏    | 481/938 [00:32<00:31, 14.64it/s, loss=0.833, v_num=13]

Validating:   3%|▎         | 12/469 [00:00<00:17, 26.22it/s]
Epoch 0:  52%|█████▏    | 485/938 [00:33<00:30, 14.70it/s, loss=0.833, v_num=13]

Validating:   3%|▎         | 16/469 [00:00<00:16, 27.25it/s]

Validating:   4%|▍         | 19/469 [00:00<00:16, 26.96it/s]
Epoch 0:  52%|█████▏    | 489/938 [00:33<00:30, 14.75it/s, loss=0.833, v_num=13]

Validating:   5%|▍         | 22/469 [00:00<00:16, 27.69it/s]
Epoch 0:  53%|█████▎    | 493/938 [00:33<00:30, 14.80it/s, loss=0.833, v_num=13]

Validating:   5%|▌         | 25/469 [00:00<00:15, 27.95it/s]
Epoch 0:  53%|█████▎    | 497/938 [00:33<00:29, 14.86it/s, loss=0.833, v_num=13]

Validating:   6%|▌         | 28/469 [00:01<00:16, 27.31it/s]

Validating:   7%|▋         | 31/469 [00:01<00:15, 27.57it/s]
Epoch 0:  53%|█████▎    | 501/938 [00:33<00:29, 14.92it/s, loss=0.833, v_num=13]

Validating:   7%|▋         | 34/469 [00:01<00:16, 27.03it/s]
Epoch 0:  54%|█████▍    | 505/938 [00:33<00:28, 14.96it/s, loss=0.833, v_num=13]

Validating:   8%|▊         | 37/469 [00:01<00:16, 25.56it/s]
Epoch 0:  54%|█████▍    | 509/938 [00:33<00:28, 15.01it/s, loss=0.833, v_num=13]

Validating:   9%|▊         | 40/469 [00:01<00:16, 25.95it/s]

Validating:   9%|▉         | 43/469 [00:01<00:16, 26.09it/s]
Epoch 0:  55%|█████▍    | 513/938 [00:34<00:28, 15.06it/s, loss=0.833, v_num=13]

Validating:  10%|▉         | 46/469 [00:01<00:15, 26.87it/s]
Epoch 0:  55%|█████▌    | 517/938 [00:34<00:27, 15.12it/s, loss=0.833, v_num=13]

Validating:  10%|█         | 49/469 [00:01<00:16, 26.09it/s]
Epoch 0:  56%|█████▌    | 521/938 [00:34<00:27, 15.16it/s, loss=0.833, v_num=13]

Validating:  11%|█         | 52/469 [00:01<00:16, 25.26it/s]

Validating:  12%|█▏        | 55/469 [00:02<00:16, 25.49it/s]
Epoch 0:  56%|█████▌    | 525/938 [00:34<00:27, 15.20it/s, loss=0.833, v_num=13]

Validating:  12%|█▏        | 58/469 [00:02<00:16, 25.49it/s]
Epoch 0:  56%|█████▋    | 529/938 [00:34<00:26, 15.25it/s, loss=0.833, v_num=13]

Validating:  13%|█▎        | 61/469 [00:02<00:16, 25.18it/s]
Epoch 0:  57%|█████▋    | 533/938 [00:34<00:26, 15.30it/s, loss=0.833, v_num=13]

Validating:  14%|█▎        | 64/469 [00:02<00:15, 26.18it/s]

Validating:  14%|█▍        | 67/469 [00:02<00:15, 25.95it/s]
Epoch 0:  57%|█████▋    | 537/938 [00:34<00:26, 15.35it/s, loss=0.833, v_num=13]

Validating:  15%|█▍        | 70/469 [00:02<00:15, 25.41it/s]
Epoch 0:  58%|█████▊    | 541/938 [00:35<00:25, 15.39it/s, loss=0.833, v_num=13]

Validating:  16%|█▌        | 73/469 [00:02<00:15, 25.78it/s]
Epoch 0:  58%|█████▊    | 545/938 [00:35<00:25, 15.43it/s, loss=0.833, v_num=13]

Validating:  16%|█▌        | 76/469 [00:02<00:15, 25.48it/s]

Validating:  17%|█▋        | 79/469 [00:03<00:15, 25.26it/s]
Epoch 0:  59%|█████▊    | 549/938 [00:35<00:25, 15.48it/s, loss=0.833, v_num=13]

Validating:  17%|█▋        | 82/469 [00:03<00:15, 25.33it/s]
Epoch 0:  59%|█████▉    | 553/938 [00:35<00:24, 15.52it/s, loss=0.833, v_num=13]

Validating:  18%|█▊        | 85/469 [00:03<00:14, 25.75it/s]
Epoch 0:  59%|█████▉    | 557/938 [00:35<00:24, 15.57it/s, loss=0.833, v_num=13]

Validating:  19%|█▉        | 88/469 [00:03<00:14, 26.10it/s]

Validating:  19%|█▉        | 91/469 [00:03<00:14, 25.90it/s]
Epoch 0:  60%|█████▉    | 561/938 [00:35<00:24, 15.61it/s, loss=0.833, v_num=13]

Validating:  20%|██        | 94/469 [00:03<00:14, 25.81it/s]
Epoch 0:  60%|██████    | 565/938 [00:36<00:23, 15.66it/s, loss=0.833, v_num=13]

Validating:  21%|██        | 97/469 [00:03<00:14, 25.89it/s]
Epoch 0:  61%|██████    | 569/938 [00:36<00:23, 15.70it/s, loss=0.833, v_num=13]

Validating:  21%|██▏       | 100/469 [00:03<00:13, 26.46it/s]

Validating:  22%|██▏       | 103/469 [00:03<00:13, 26.16it/s]
Epoch 0:  61%|██████    | 573/938 [00:36<00:23, 15.75it/s, loss=0.833, v_num=13]

Validating:  23%|██▎       | 106/469 [00:04<00:13, 27.09it/s]
Epoch 0:  62%|██████▏   | 577/938 [00:36<00:22, 15.80it/s, loss=0.833, v_num=13]

Validating:  23%|██▎       | 109/469 [00:04<00:13, 26.39it/s]
Epoch 0:  62%|██████▏   | 581/938 [00:36<00:22, 15.84it/s, loss=0.833, v_num=13]

Validating:  24%|██▍       | 112/469 [00:04<00:13, 25.70it/s]

Validating:  25%|██▍       | 115/469 [00:04<00:13, 26.65it/s]
Epoch 0:  62%|██████▏   | 585/938 [00:36<00:22, 15.88it/s, loss=0.833, v_num=13]

Validating:  25%|██▌       | 118/469 [00:04<00:13, 26.90it/s]
Epoch 0:  63%|██████▎   | 589/938 [00:36<00:21, 15.92it/s, loss=0.833, v_num=13]

Validating:  26%|██▌       | 121/469 [00:04<00:13, 26.58it/s]
Epoch 0:  63%|██████▎   | 593/938 [00:37<00:21, 15.97it/s, loss=0.833, v_num=13]

Validating:  26%|██▋       | 124/469 [00:04<00:12, 26.60it/s]

Validating:  27%|██▋       | 127/469 [00:04<00:12, 26.96it/s]
Epoch 0:  64%|██████▎   | 597/938 [00:37<00:21, 16.01it/s, loss=0.833, v_num=13]

Validating:  28%|██▊       | 130/469 [00:04<00:12, 27.09it/s]
Epoch 0:  64%|██████▍   | 601/938 [00:37<00:20, 16.06it/s, loss=0.833, v_num=13]

Validating:  28%|██▊       | 133/469 [00:05<00:12, 27.07it/s]
Epoch 0:  64%|██████▍   | 605/938 [00:37<00:20, 16.10it/s, loss=0.833, v_num=13]

Validating:  29%|██▉       | 136/469 [00:05<00:12, 27.46it/s]

Validating:  30%|██▉       | 139/469 [00:05<00:12, 26.87it/s]
Epoch 0:  65%|██████▍   | 609/938 [00:37<00:20, 16.14it/s, loss=0.833, v_num=13]

Validating:  30%|███       | 142/469 [00:05<00:11, 27.50it/s]
Epoch 0:  65%|██████▌   | 613/938 [00:37<00:20, 16.19it/s, loss=0.833, v_num=13]

Validating:  31%|███       | 145/469 [00:05<00:11, 27.27it/s]
Epoch 0:  66%|██████▌   | 617/938 [00:38<00:19, 16.23it/s, loss=0.833, v_num=13]

Validating:  32%|███▏      | 148/469 [00:05<00:11, 27.33it/s]

Validating:  32%|███▏      | 151/469 [00:05<00:11, 27.48it/s]
Epoch 0:  66%|██████▌   | 621/938 [00:38<00:19, 16.27it/s, loss=0.833, v_num=13]

Validating:  33%|███▎      | 154/469 [00:05<00:11, 26.65it/s]
Epoch 0:  67%|██████▋   | 625/938 [00:38<00:19, 16.31it/s, loss=0.833, v_num=13]

Validating:  33%|███▎      | 157/469 [00:05<00:11, 26.71it/s]
Epoch 0:  67%|██████▋   | 629/938 [00:38<00:18, 16.35it/s, loss=0.833, v_num=13]

Validating:  34%|███▍      | 160/469 [00:06<00:11, 26.30it/s]

Validating:  35%|███▍      | 163/469 [00:06<00:11, 25.75it/s]
Epoch 0:  67%|██████▋   | 633/938 [00:38<00:18, 16.39it/s, loss=0.833, v_num=13]

Validating:  35%|███▌      | 166/469 [00:06<00:11, 26.20it/s]
Epoch 0:  68%|██████▊   | 637/938 [00:38<00:18, 16.43it/s, loss=0.833, v_num=13]

Validating:  36%|███▌      | 169/469 [00:06<00:11, 26.44it/s]
Epoch 0:  68%|██████▊   | 641/938 [00:38<00:18, 16.46it/s, loss=0.833, v_num=13]

Validating:  37%|███▋      | 172/469 [00:06<00:12, 24.51it/s]

Validating:  37%|███▋      | 175/469 [00:06<00:11, 25.16it/s]
Epoch 0:  69%|██████▉   | 645/938 [00:39<00:17, 16.49it/s, loss=0.833, v_num=13]

Validating:  38%|███▊      | 178/469 [00:06<00:11, 25.72it/s]
Epoch 0:  69%|██████▉   | 649/938 [00:39<00:17, 16.53it/s, loss=0.833, v_num=13]

Validating:  39%|███▊      | 181/469 [00:06<00:10, 26.19it/s]
Epoch 0:  70%|██████▉   | 653/938 [00:39<00:17, 16.57it/s, loss=0.833, v_num=13]

Validating:  39%|███▉      | 184/469 [00:07<00:11, 25.80it/s]

Validating:  40%|███▉      | 187/469 [00:07<00:10, 26.33it/s]
Epoch 0:  70%|███████   | 657/938 [00:39<00:16, 16.61it/s, loss=0.833, v_num=13]

Validating:  41%|████      | 190/469 [00:07<00:10, 26.58it/s]
Epoch 0:  70%|███████   | 661/938 [00:39<00:16, 16.65it/s, loss=0.833, v_num=13]

Validating:  41%|████      | 193/469 [00:07<00:10, 26.17it/s]
Epoch 0:  71%|███████   | 665/938 [00:39<00:16, 16.68it/s, loss=0.833, v_num=13]

Validating:  42%|████▏     | 196/469 [00:07<00:10, 25.47it/s]

Validating:  42%|████▏     | 199/469 [00:07<00:10, 25.77it/s]
Epoch 0:  71%|███████▏  | 669/938 [00:40<00:16, 16.71it/s, loss=0.833, v_num=13]

Validating:  43%|████▎     | 202/469 [00:07<00:10, 25.64it/s]
Epoch 0:  72%|███████▏  | 673/938 [00:40<00:15, 16.75it/s, loss=0.833, v_num=13]

Validating:  44%|████▎     | 205/469 [00:07<00:10, 24.67it/s]
Epoch 0:  72%|███████▏  | 677/938 [00:40<00:15, 16.77it/s, loss=0.833, v_num=13]

Validating:  44%|████▍     | 208/469 [00:07<00:10, 24.51it/s]

Validating:  45%|████▍     | 211/469 [00:08<00:10, 24.76it/s]
Epoch 0:  73%|███████▎  | 681/938 [00:40<00:15, 16.81it/s, loss=0.833, v_num=13]

Validating:  46%|████▌     | 214/469 [00:08<00:09, 25.76it/s]
Epoch 0:  73%|███████▎  | 685/938 [00:40<00:15, 16.85it/s, loss=0.833, v_num=13]

Validating:  46%|████▋     | 217/469 [00:08<00:09, 25.80it/s]
Epoch 0:  73%|███████▎  | 689/938 [00:40<00:14, 16.88it/s, loss=0.833, v_num=13]

Validating:  47%|████▋     | 220/469 [00:08<00:09, 25.75it/s]

Validating:  48%|████▊     | 223/469 [00:08<00:09, 25.10it/s]
Epoch 0:  74%|███████▍  | 693/938 [00:40<00:14, 16.91it/s, loss=0.833, v_num=13]

Validating:  48%|████▊     | 226/469 [00:08<00:09, 25.24it/s]
Epoch 0:  74%|███████▍  | 697/938 [00:41<00:14, 16.94it/s, loss=0.833, v_num=13]

Validating:  49%|████▉     | 229/469 [00:08<00:09, 25.68it/s]
Epoch 0:  75%|███████▍  | 701/938 [00:41<00:13, 16.98it/s, loss=0.833, v_num=13]

Validating:  49%|████▉     | 232/469 [00:08<00:09, 25.61it/s]

Validating:  50%|█████     | 235/469 [00:08<00:08, 26.48it/s]
Epoch 0:  75%|███████▌  | 705/938 [00:41<00:13, 17.01it/s, loss=0.833, v_num=13]

Validating:  51%|█████     | 238/469 [00:09<00:08, 26.47it/s]
Epoch 0:  76%|███████▌  | 709/938 [00:41<00:13, 17.05it/s, loss=0.833, v_num=13]

Validating:  51%|█████▏    | 241/469 [00:09<00:08, 26.73it/s]
Epoch 0:  76%|███████▌  | 713/938 [00:41<00:13, 17.09it/s, loss=0.833, v_num=13]

Validating:  52%|█████▏    | 244/469 [00:09<00:08, 27.62it/s]

Validating:  53%|█████▎    | 247/469 [00:09<00:08, 26.99it/s]
Epoch 0:  76%|███████▋  | 717/938 [00:41<00:12, 17.12it/s, loss=0.833, v_num=13]

Validating:  53%|█████▎    | 250/469 [00:09<00:08, 25.93it/s]
Epoch 0:  77%|███████▋  | 721/938 [00:42<00:12, 17.14it/s, loss=0.833, v_num=13]

Validating:  54%|█████▍    | 253/469 [00:09<00:09, 23.90it/s]
Epoch 0:  77%|███████▋  | 725/938 [00:42<00:12, 17.17it/s, loss=0.833, v_num=13]

Validating:  55%|█████▍    | 256/469 [00:09<00:08, 24.71it/s]

Validating:  55%|█████▌    | 259/469 [00:09<00:08, 25.35it/s]
Epoch 0:  78%|███████▊  | 729/938 [00:42<00:12, 17.20it/s, loss=0.833, v_num=13]

Validating:  56%|█████▌    | 262/469 [00:10<00:08, 25.76it/s]
Epoch 0:  78%|███████▊  | 733/938 [00:42<00:11, 17.24it/s, loss=0.833, v_num=13]

Validating:  57%|█████▋    | 265/469 [00:10<00:07, 26.09it/s]
Epoch 0:  79%|███████▊  | 737/938 [00:42<00:11, 17.26it/s, loss=0.833, v_num=13]

Validating:  57%|█████▋    | 268/469 [00:10<00:08, 24.22it/s]

Validating:  58%|█████▊    | 271/469 [00:10<00:08, 24.42it/s]
Epoch 0:  79%|███████▉  | 741/938 [00:42<00:11, 17.29it/s, loss=0.833, v_num=13]

Validating:  58%|█████▊    | 274/469 [00:10<00:07, 24.87it/s]
Epoch 0:  79%|███████▉  | 745/938 [00:43<00:11, 17.32it/s, loss=0.833, v_num=13]

Validating:  59%|█████▉    | 277/469 [00:10<00:07, 24.26it/s]
Epoch 0:  80%|███████▉  | 749/938 [00:43<00:10, 17.34it/s, loss=0.833, v_num=13]

Validating:  60%|█████▉    | 280/469 [00:10<00:07, 24.10it/s]

Validating:  60%|██████    | 283/469 [00:10<00:07, 25.11it/s]
Epoch 0:  80%|████████  | 753/938 [00:43<00:10, 17.37it/s, loss=0.833, v_num=13]

Validating:  61%|██████    | 286/469 [00:11<00:07, 24.44it/s]
Epoch 0:  81%|████████  | 757/938 [00:43<00:10, 17.40it/s, loss=0.833, v_num=13]

Validating:  62%|██████▏   | 289/469 [00:11<00:07, 25.02it/s]
Epoch 0:  81%|████████  | 761/938 [00:43<00:10, 17.43it/s, loss=0.833, v_num=13]

Validating:  62%|██████▏   | 292/469 [00:11<00:07, 24.88it/s]

Validating:  63%|██████▎   | 295/469 [00:11<00:07, 24.30it/s]
Epoch 0:  82%|████████▏ | 765/938 [00:43<00:09, 17.45it/s, loss=0.833, v_num=13]

Validating:  64%|██████▎   | 298/469 [00:11<00:07, 24.24it/s]
Epoch 0:  82%|████████▏ | 769/938 [00:44<00:09, 17.47it/s, loss=0.833, v_num=13]

Validating:  64%|██████▍   | 301/469 [00:11<00:06, 24.12it/s]
Epoch 0:  82%|████████▏ | 773/938 [00:44<00:09, 17.51it/s, loss=0.833, v_num=13]

Validating:  65%|██████▍   | 304/469 [00:11<00:06, 25.53it/s]

Validating:  65%|██████▌   | 307/469 [00:11<00:06, 25.37it/s]
Epoch 0:  83%|████████▎ | 777/938 [00:44<00:09, 17.54it/s, loss=0.833, v_num=13]

Validating:  66%|██████▌   | 310/469 [00:11<00:06, 25.05it/s]
Epoch 0:  83%|████████▎ | 781/938 [00:44<00:08, 17.56it/s, loss=0.833, v_num=13]

Validating:  67%|██████▋   | 313/469 [00:12<00:05, 26.32it/s]
Epoch 0:  84%|████████▎ | 785/938 [00:44<00:08, 17.59it/s, loss=0.833, v_num=13]

Validating:  67%|██████▋   | 316/469 [00:12<00:05, 25.96it/s]

Validating:  68%|██████▊   | 319/469 [00:12<00:05, 26.54it/s]
Epoch 0:  84%|████████▍ | 789/938 [00:44<00:08, 17.63it/s, loss=0.833, v_num=13]

Validating:  69%|██████▊   | 322/469 [00:12<00:05, 25.66it/s]
Epoch 0:  85%|████████▍ | 793/938 [00:44<00:08, 17.65it/s, loss=0.833, v_num=13]

Validating:  69%|██████▉   | 325/469 [00:12<00:05, 25.88it/s]
Epoch 0:  85%|████████▍ | 797/938 [00:45<00:07, 17.68it/s, loss=0.833, v_num=13]

Validating:  70%|██████▉   | 328/469 [00:12<00:05, 25.49it/s]

Validating:  71%|███████   | 331/469 [00:12<00:05, 24.99it/s]
Epoch 0:  85%|████████▌ | 801/938 [00:45<00:07, 17.70it/s, loss=0.833, v_num=13]

Validating:  71%|███████   | 334/469 [00:12<00:05, 26.01it/s]
Epoch 0:  86%|████████▌ | 805/938 [00:45<00:07, 17.74it/s, loss=0.833, v_num=13]

Validating:  72%|███████▏  | 337/469 [00:13<00:05, 26.02it/s]
Epoch 0:  86%|████████▌ | 809/938 [00:45<00:07, 17.76it/s, loss=0.833, v_num=13]

Validating:  72%|███████▏  | 340/469 [00:13<00:04, 26.26it/s]

Validating:  73%|███████▎  | 343/469 [00:13<00:04, 27.12it/s]
Epoch 0:  87%|████████▋ | 813/938 [00:45<00:07, 17.80it/s, loss=0.833, v_num=13]

Validating:  74%|███████▍  | 346/469 [00:13<00:04, 26.60it/s]
Epoch 0:  87%|████████▋ | 817/938 [00:45<00:06, 17.83it/s, loss=0.833, v_num=13]

Validating:  74%|███████▍  | 349/469 [00:13<00:04, 26.46it/s]
Epoch 0:  88%|████████▊ | 821/938 [00:45<00:06, 17.85it/s, loss=0.833, v_num=13]

Validating:  75%|███████▌  | 352/469 [00:13<00:04, 26.13it/s]

Validating:  76%|███████▌  | 355/469 [00:13<00:04, 26.35it/s]
Epoch 0:  88%|████████▊ | 825/938 [00:46<00:06, 17.88it/s, loss=0.833, v_num=13]

Validating:  76%|███████▋  | 358/469 [00:13<00:04, 24.37it/s]
Epoch 0:  88%|████████▊ | 829/938 [00:46<00:06, 17.89it/s, loss=0.833, v_num=13]

Validating:  77%|███████▋  | 361/469 [00:13<00:04, 24.39it/s]
Epoch 0:  89%|████████▉ | 833/938 [00:46<00:05, 17.92it/s, loss=0.833, v_num=13]

Validating:  78%|███████▊  | 364/469 [00:14<00:04, 24.84it/s]

Validating:  78%|███████▊  | 367/469 [00:14<00:04, 25.25it/s]
Epoch 0:  89%|████████▉ | 837/938 [00:46<00:05, 17.95it/s, loss=0.833, v_num=13]

Validating:  79%|███████▉  | 370/469 [00:14<00:03, 25.52it/s]
Epoch 0:  90%|████████▉ | 841/938 [00:46<00:05, 17.97it/s, loss=0.833, v_num=13]

Validating:  80%|███████▉  | 373/469 [00:14<00:03, 24.99it/s]
Epoch 0:  90%|█████████ | 845/938 [00:46<00:05, 18.00it/s, loss=0.833, v_num=13]

Validating:  80%|████████  | 376/469 [00:14<00:03, 26.16it/s]

Validating:  81%|████████  | 379/469 [00:14<00:03, 26.41it/s]
Epoch 0:  91%|█████████ | 849/938 [00:47<00:04, 18.03it/s, loss=0.833, v_num=13]

Validating:  81%|████████▏ | 382/469 [00:14<00:03, 26.18it/s]
Epoch 0:  91%|█████████ | 853/938 [00:47<00:04, 18.05it/s, loss=0.833, v_num=13]

Validating:  82%|████████▏ | 385/469 [00:14<00:03, 26.35it/s]
Epoch 0:  91%|█████████▏| 857/938 [00:47<00:04, 18.08it/s, loss=0.833, v_num=13]

Validating:  83%|████████▎ | 388/469 [00:14<00:03, 26.37it/s]

Validating:  83%|████████▎ | 391/469 [00:15<00:03, 25.84it/s]
Epoch 0:  92%|█████████▏| 861/938 [00:47<00:04, 18.10it/s, loss=0.833, v_num=13]

Validating:  84%|████████▍ | 394/469 [00:15<00:02, 25.77it/s]
Epoch 0:  92%|█████████▏| 865/938 [00:47<00:04, 18.13it/s, loss=0.833, v_num=13]

Validating:  85%|████████▍ | 397/469 [00:15<00:02, 24.76it/s]
Epoch 0:  93%|█████████▎| 869/938 [00:47<00:03, 18.15it/s, loss=0.833, v_num=13]

Validating:  85%|████████▌ | 400/469 [00:15<00:02, 25.30it/s]

Validating:  86%|████████▌ | 403/469 [00:15<00:02, 25.48it/s]
Epoch 0:  93%|█████████▎| 873/938 [00:48<00:03, 18.17it/s, loss=0.833, v_num=13]

Validating:  87%|████████▋ | 406/469 [00:15<00:02, 25.79it/s]
Epoch 0:  93%|█████████▎| 877/938 [00:48<00:03, 18.20it/s, loss=0.833, v_num=13]

Validating:  87%|████████▋ | 409/469 [00:15<00:02, 23.92it/s]
Epoch 0:  94%|█████████▍| 881/938 [00:48<00:03, 18.21it/s, loss=0.833, v_num=13]

Validating:  88%|████████▊ | 412/469 [00:15<00:02, 24.67it/s]

Validating:  88%|████████▊ | 415/469 [00:16<00:02, 24.76it/s]
Epoch 0:  94%|█████████▍| 885/938 [00:48<00:02, 18.24it/s, loss=0.833, v_num=13]

Validating:  89%|████████▉ | 418/469 [00:16<00:02, 24.65it/s]
Epoch 0:  95%|█████████▍| 889/938 [00:48<00:02, 18.26it/s, loss=0.833, v_num=13]

Validating:  90%|████████▉ | 421/469 [00:16<00:01, 24.33it/s]
Epoch 0:  95%|█████████▌| 893/938 [00:48<00:02, 18.27it/s, loss=0.833, v_num=13]

Validating:  90%|█████████ | 424/469 [00:16<00:01, 23.88it/s]

Validating:  91%|█████████ | 427/469 [00:16<00:01, 24.70it/s]
Epoch 0:  96%|█████████▌| 897/938 [00:49<00:02, 18.30it/s, loss=0.833, v_num=13]

Validating:  92%|█████████▏| 430/469 [00:16<00:01, 25.71it/s]
Epoch 0:  96%|█████████▌| 901/938 [00:49<00:02, 18.33it/s, loss=0.833, v_num=13]

Validating:  92%|█████████▏| 433/469 [00:16<00:01, 26.04it/s]
Epoch 0:  96%|█████████▋| 905/938 [00:49<00:01, 18.35it/s, loss=0.833, v_num=13]

Validating:  93%|█████████▎| 436/469 [00:16<00:01, 25.51it/s]

Validating:  94%|█████████▎| 439/469 [00:17<00:01, 25.80it/s]
Epoch 0:  97%|█████████▋| 909/938 [00:49<00:01, 18.37it/s, loss=0.833, v_num=13]

Validating:  94%|█████████▍| 442/469 [00:17<00:01, 26.25it/s]
Epoch 0:  97%|█████████▋| 913/938 [00:49<00:01, 18.40it/s, loss=0.833, v_num=13]

Validating:  95%|█████████▍| 445/469 [00:17<00:00, 26.48it/s]
Epoch 0:  98%|█████████▊| 917/938 [00:49<00:01, 18.42it/s, loss=0.833, v_num=13]

Validating:  96%|█████████▌| 448/469 [00:17<00:00, 25.82it/s]

Validating:  96%|█████████▌| 451/469 [00:17<00:00, 26.01it/s]
Epoch 0:  98%|█████████▊| 921/938 [00:49<00:00, 18.45it/s, loss=0.833, v_num=13]

Validating:  97%|█████████▋| 454/469 [00:17<00:00, 25.36it/s]
Epoch 0:  99%|█████████▊| 925/938 [00:50<00:00, 18.47it/s, loss=0.833, v_num=13]

Validating:  97%|█████████▋| 457/469 [00:17<00:00, 26.41it/s]
Epoch 0:  99%|█████████▉| 929/938 [00:50<00:00, 18.49it/s, loss=0.833, v_num=13]

Validating:  98%|█████████▊| 460/469 [00:17<00:00, 26.86it/s]

Validating:  99%|█████████▊| 463/469 [00:17<00:00, 26.57it/s]
Epoch 0:  99%|█████████▉| 933/938 [00:50<00:00, 18.52it/s, loss=0.833, v_num=13]

Validating:  99%|█████████▉| 466/469 [00:18<00:00, 26.82it/s]
Epoch 0: 100%|█████████▉| 937/938 [00:50<00:00, 18.54it/s, loss=0.833, v_num=13]
Epoch 0: 100%|██████████| 938/938 [00:50<00:00, 18.54it/s, loss=0.833, v_num=13, val_rmse=0.717]

                                                             
Epoch 0: 100%|██████████| 938/938 [00:50<00:00, 18.53it/s, loss=0.833, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 0:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.833, v_num=13, val_rmse=0.717, train_rmse=1.190]          
Epoch 1:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.833, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   0%|          | 1/938 [00:00<01:14, 12.53it/s, loss=0.839, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   0%|          | 2/938 [00:00<01:04, 14.59it/s, loss=0.842, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   0%|          | 3/938 [00:00<00:58, 15.92it/s, loss=0.844, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   0%|          | 4/938 [00:00<01:00, 15.40it/s, loss=0.844, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   0%|          | 4/938 [00:00<01:00, 15.37it/s, loss=0.842, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   1%|          | 5/938 [00:00<01:01, 15.15it/s, loss=0.849, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   1%|          | 6/938 [00:00<01:02, 15.02it/s, loss=0.846, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   1%|          | 7/938 [00:00<01:01, 15.09it/s, loss=0.842, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   1%|          | 8/938 [00:00<01:02, 14.83it/s, loss=0.842, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   1%|          | 8/938 [00:00<01:02, 14.82it/s, loss=0.839, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   1%|          | 9/938 [00:00<01:02, 14.84it/s, loss=0.832, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   1%|          | 10/938 [00:00<01:02, 14.89it/s, loss=0.836, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   1%|          | 11/938 [00:00<01:06, 13.97it/s, loss=0.836, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   1%|▏         | 12/938 [00:00<01:05, 14.08it/s, loss=0.836, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   1%|▏         | 12/938 [00:00<01:05, 14.07it/s, loss=0.835, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   1%|▏         | 13/938 [00:00<01:04, 14.37it/s, loss=0.826, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   1%|▏         | 14/938 [00:00<01:03, 14.62it/s, loss=0.832, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   2%|▏         | 15/938 [00:01<01:03, 14.63it/s, loss=0.823, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   2%|▏         | 16/938 [00:01<01:02, 14.78it/s, loss=0.823, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   2%|▏         | 16/938 [00:01<01:02, 14.77it/s, loss=0.827, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   2%|▏         | 17/938 [00:01<01:01, 15.02it/s, loss=0.836, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   2%|▏         | 18/938 [00:01<01:01, 15.05it/s, loss=0.822, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   2%|▏         | 19/938 [00:01<01:01, 15.06it/s, loss=0.82, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:   2%|▏         | 20/938 [00:01<01:01, 15.05it/s, loss=0.82, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   2%|▏         | 20/938 [00:01<01:01, 15.04it/s, loss=0.81, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   2%|▏         | 21/938 [00:01<01:01, 14.86it/s, loss=0.812, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   2%|▏         | 22/938 [00:01<01:02, 14.75it/s, loss=0.813, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   2%|▏         | 23/938 [00:01<01:02, 14.74it/s, loss=0.804, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   3%|▎         | 24/938 [00:01<01:02, 14.71it/s, loss=0.804, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   3%|▎         | 24/938 [00:01<01:02, 14.71it/s, loss=0.802, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   3%|▎         | 25/938 [00:01<01:01, 14.80it/s, loss=0.805, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   3%|▎         | 26/938 [00:01<01:01, 14.80it/s, loss=0.808, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   3%|▎         | 27/938 [00:01<01:01, 14.74it/s, loss=0.809, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   3%|▎         | 28/938 [00:01<01:01, 14.86it/s, loss=0.809, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   3%|▎         | 28/938 [00:01<01:01, 14.85it/s, loss=0.807, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   3%|▎         | 29/938 [00:01<01:01, 14.85it/s, loss=0.803, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   3%|▎         | 30/938 [00:02<01:01, 14.75it/s, loss=0.789, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   3%|▎         | 31/938 [00:02<01:01, 14.70it/s, loss=0.796, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   3%|▎         | 32/938 [00:02<01:01, 14.77it/s, loss=0.796, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   3%|▎         | 32/938 [00:02<01:01, 14.77it/s, loss=0.789, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   4%|▎         | 33/938 [00:02<01:01, 14.74it/s, loss=0.785, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   4%|▎         | 34/938 [00:02<01:01, 14.81it/s, loss=0.779, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   4%|▎         | 35/938 [00:02<01:00, 14.87it/s, loss=0.775, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   4%|▍         | 36/938 [00:02<01:00, 14.92it/s, loss=0.775, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   4%|▍         | 36/938 [00:02<01:00, 14.91it/s, loss=0.779, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   4%|▍         | 37/938 [00:02<01:00, 14.94it/s, loss=0.767, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   4%|▍         | 38/938 [00:02<01:00, 14.87it/s, loss=0.772, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   4%|▍         | 39/938 [00:02<01:00, 14.79it/s, loss=0.769, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   4%|▍         | 40/938 [00:02<01:00, 14.78it/s, loss=0.769, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   4%|▍         | 40/938 [00:02<01:00, 14.78it/s, loss=0.768, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   4%|▍         | 41/938 [00:02<01:00, 14.75it/s, loss=0.764, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   4%|▍         | 42/938 [00:02<01:00, 14.74it/s, loss=0.754, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   5%|▍         | 43/938 [00:02<01:00, 14.74it/s, loss=0.753, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   5%|▍         | 44/938 [00:02<01:00, 14.79it/s, loss=0.753, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   5%|▍         | 44/938 [00:02<01:00, 14.78it/s, loss=0.748, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   5%|▍         | 45/938 [00:03<01:00, 14.78it/s, loss=0.735, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   5%|▍         | 46/938 [00:03<01:00, 14.80it/s, loss=0.736, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   5%|▌         | 47/938 [00:03<01:00, 14.81it/s, loss=0.74, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:   5%|▌         | 48/938 [00:03<00:59, 14.85it/s, loss=0.74, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   5%|▌         | 48/938 [00:03<00:59, 14.85it/s, loss=0.741, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   5%|▌         | 49/938 [00:03<00:59, 14.85it/s, loss=0.749, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   5%|▌         | 50/938 [00:03<00:59, 14.91it/s, loss=0.757, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   5%|▌         | 51/938 [00:03<00:59, 14.91it/s, loss=0.748, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   6%|▌         | 52/938 [00:03<00:59, 14.91it/s, loss=0.748, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   6%|▌         | 52/938 [00:03<00:59, 14.91it/s, loss=0.75, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:   6%|▌         | 53/938 [00:03<00:59, 14.96it/s, loss=0.752, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   6%|▌         | 54/938 [00:03<00:59, 14.83it/s, loss=0.748, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   6%|▌         | 55/938 [00:03<00:59, 14.82it/s, loss=0.75, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:   6%|▌         | 56/938 [00:03<00:59, 14.82it/s, loss=0.75, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   6%|▌         | 56/938 [00:03<00:59, 14.82it/s, loss=0.752, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   6%|▌         | 57/938 [00:03<00:59, 14.81it/s, loss=0.764, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   6%|▌         | 58/938 [00:03<00:59, 14.82it/s, loss=0.762, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   6%|▋         | 59/938 [00:03<00:59, 14.82it/s, loss=0.768, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   6%|▋         | 60/938 [00:04<00:59, 14.85it/s, loss=0.768, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   6%|▋         | 60/938 [00:04<00:59, 14.85it/s, loss=0.772, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   7%|▋         | 61/938 [00:04<00:59, 14.85it/s, loss=0.776, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   7%|▋         | 62/938 [00:04<00:59, 14.81it/s, loss=0.78, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:   7%|▋         | 63/938 [00:04<00:59, 14.82it/s, loss=0.78, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   7%|▋         | 64/938 [00:04<00:58, 14.84it/s, loss=0.78, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   7%|▋         | 64/938 [00:04<00:58, 14.84it/s, loss=0.785, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   7%|▋         | 65/938 [00:04<00:58, 14.83it/s, loss=0.791, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   7%|▋         | 66/938 [00:04<00:58, 14.81it/s, loss=0.793, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   7%|▋         | 67/938 [00:04<00:58, 14.87it/s, loss=0.79, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:   7%|▋         | 68/938 [00:04<00:58, 14.89it/s, loss=0.79, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   7%|▋         | 68/938 [00:04<00:58, 14.89it/s, loss=0.793, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   7%|▋         | 69/938 [00:04<00:58, 14.90it/s, loss=0.787, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   7%|▋         | 70/938 [00:04<00:58, 14.90it/s, loss=0.781, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   8%|▊         | 71/938 [00:04<00:58, 14.91it/s, loss=0.785, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   8%|▊         | 72/938 [00:04<00:58, 14.92it/s, loss=0.785, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   8%|▊         | 72/938 [00:04<00:58, 14.92it/s, loss=0.794, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   8%|▊         | 73/938 [00:04<00:57, 14.96it/s, loss=0.791, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   8%|▊         | 74/938 [00:04<00:57, 14.94it/s, loss=0.798, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   8%|▊         | 75/938 [00:05<00:57, 14.96it/s, loss=0.795, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   8%|▊         | 76/938 [00:05<00:57, 14.98it/s, loss=0.795, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   8%|▊         | 76/938 [00:05<00:57, 14.98it/s, loss=0.793, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   8%|▊         | 77/938 [00:05<00:57, 14.99it/s, loss=0.783, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   8%|▊         | 78/938 [00:05<00:57, 15.01it/s, loss=0.778, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   8%|▊         | 79/938 [00:05<00:57, 15.06it/s, loss=0.783, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   9%|▊         | 80/938 [00:05<00:56, 15.07it/s, loss=0.783, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   9%|▊         | 80/938 [00:05<00:56, 15.07it/s, loss=0.782, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   9%|▊         | 81/938 [00:05<00:56, 15.06it/s, loss=0.774, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   9%|▊         | 82/938 [00:05<00:56, 15.11it/s, loss=0.778, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   9%|▉         | 83/938 [00:05<00:56, 15.13it/s, loss=0.777, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   9%|▉         | 84/938 [00:05<00:56, 15.15it/s, loss=0.777, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   9%|▉         | 84/938 [00:05<00:56, 15.15it/s, loss=0.782, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   9%|▉         | 85/938 [00:05<00:56, 15.17it/s, loss=0.785, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   9%|▉         | 86/938 [00:05<00:56, 15.17it/s, loss=0.774, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   9%|▉         | 87/938 [00:05<00:56, 15.15it/s, loss=0.769, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   9%|▉         | 88/938 [00:05<00:56, 15.13it/s, loss=0.769, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   9%|▉         | 88/938 [00:05<00:56, 15.13it/s, loss=0.767, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:   9%|▉         | 89/938 [00:05<00:56, 15.05it/s, loss=0.767, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  10%|▉         | 90/938 [00:05<00:56, 15.07it/s, loss=0.774, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  10%|▉         | 91/938 [00:06<00:56, 15.08it/s, loss=0.775, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  10%|▉         | 92/938 [00:06<00:56, 15.05it/s, loss=0.775, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  10%|▉         | 92/938 [00:06<00:56, 15.05it/s, loss=0.76, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  10%|▉         | 93/938 [00:06<00:56, 15.08it/s, loss=0.765, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  10%|█         | 94/938 [00:06<00:55, 15.08it/s, loss=0.763, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  10%|█         | 95/938 [00:06<00:56, 15.04it/s, loss=0.764, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  10%|█         | 96/938 [00:06<00:55, 15.04it/s, loss=0.764, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  10%|█         | 96/938 [00:06<00:55, 15.04it/s, loss=0.753, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  10%|█         | 97/938 [00:06<00:56, 15.01it/s, loss=0.753, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  10%|█         | 98/938 [00:06<00:55, 15.01it/s, loss=0.765, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  11%|█         | 99/938 [00:06<00:55, 15.01it/s, loss=0.753, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  11%|█         | 100/938 [00:06<00:55, 15.00it/s, loss=0.753, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  11%|█         | 100/938 [00:06<00:55, 15.00it/s, loss=0.748, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  11%|█         | 101/938 [00:06<00:55, 15.04it/s, loss=0.75, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  11%|█         | 102/938 [00:06<00:56, 14.90it/s, loss=0.753, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  11%|█         | 103/938 [00:06<00:56, 14.88it/s, loss=0.76, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  11%|█         | 104/938 [00:06<00:56, 14.88it/s, loss=0.76, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  11%|█         | 104/938 [00:06<00:56, 14.88it/s, loss=0.754, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  11%|█         | 105/938 [00:07<00:55, 14.88it/s, loss=0.745, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  11%|█▏        | 106/938 [00:07<00:55, 14.86it/s, loss=0.764, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  11%|█▏        | 107/938 [00:07<00:55, 14.86it/s, loss=0.773, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  12%|█▏        | 108/938 [00:07<00:55, 14.87it/s, loss=0.773, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  12%|█▏        | 108/938 [00:07<00:55, 14.87it/s, loss=0.777, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  12%|█▏        | 109/938 [00:07<00:55, 14.91it/s, loss=0.772, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  12%|█▏        | 110/938 [00:07<00:55, 14.92it/s, loss=0.766, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  12%|█▏        | 111/938 [00:07<00:55, 14.94it/s, loss=0.758, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  12%|█▏        | 112/938 [00:07<00:55, 14.96it/s, loss=0.758, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  12%|█▏        | 112/938 [00:07<00:55, 14.96it/s, loss=0.771, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  12%|█▏        | 113/938 [00:07<00:55, 14.97it/s, loss=0.771, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  12%|█▏        | 114/938 [00:07<00:55, 14.98it/s, loss=0.767, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  12%|█▏        | 115/938 [00:07<00:54, 14.97it/s, loss=0.767, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  12%|█▏        | 116/938 [00:07<00:55, 14.94it/s, loss=0.767, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  12%|█▏        | 116/938 [00:07<00:55, 14.94it/s, loss=0.787, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  12%|█▏        | 117/938 [00:07<00:55, 14.90it/s, loss=0.79, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  13%|█▎        | 118/938 [00:07<00:54, 14.91it/s, loss=0.787, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  13%|█▎        | 119/938 [00:07<00:55, 14.89it/s, loss=0.794, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  13%|█▎        | 120/938 [00:08<00:54, 14.91it/s, loss=0.794, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  13%|█▎        | 120/938 [00:08<00:54, 14.91it/s, loss=0.796, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  13%|█▎        | 121/938 [00:08<00:54, 14.89it/s, loss=0.791, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  13%|█▎        | 122/938 [00:08<00:54, 14.89it/s, loss=0.782, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  13%|█▎        | 123/938 [00:08<00:54, 14.91it/s, loss=0.78, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  13%|█▎        | 124/938 [00:08<00:54, 14.93it/s, loss=0.78, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  13%|█▎        | 124/938 [00:08<00:54, 14.93it/s, loss=0.783, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  13%|█▎        | 125/938 [00:08<00:54, 14.93it/s, loss=0.79, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  13%|█▎        | 126/938 [00:08<00:54, 14.95it/s, loss=0.775, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  14%|█▎        | 127/938 [00:08<00:54, 14.94it/s, loss=0.777, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  14%|█▎        | 128/938 [00:08<00:54, 14.92it/s, loss=0.777, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  14%|█▎        | 128/938 [00:08<00:54, 14.92it/s, loss=0.774, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  14%|█▍        | 129/938 [00:08<00:54, 14.89it/s, loss=0.779, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  14%|█▍        | 130/938 [00:08<00:54, 14.89it/s, loss=0.778, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  14%|█▍        | 131/938 [00:08<00:54, 14.83it/s, loss=0.783, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  14%|█▍        | 132/938 [00:08<00:54, 14.83it/s, loss=0.783, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  14%|█▍        | 132/938 [00:08<00:54, 14.83it/s, loss=0.784, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  14%|█▍        | 133/938 [00:08<00:54, 14.79it/s, loss=0.781, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  14%|█▍        | 134/938 [00:09<00:54, 14.80it/s, loss=0.791, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  14%|█▍        | 135/938 [00:09<00:54, 14.82it/s, loss=0.786, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  14%|█▍        | 136/938 [00:09<00:54, 14.84it/s, loss=0.786, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  14%|█▍        | 136/938 [00:09<00:54, 14.83it/s, loss=0.772, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  15%|█▍        | 137/938 [00:09<00:53, 14.83it/s, loss=0.775, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  15%|█▍        | 138/938 [00:09<00:53, 14.84it/s, loss=0.762, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  15%|█▍        | 139/938 [00:09<00:53, 14.82it/s, loss=0.756, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  15%|█▍        | 140/938 [00:09<00:53, 14.83it/s, loss=0.756, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  15%|█▍        | 140/938 [00:09<00:53, 14.83it/s, loss=0.76, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  15%|█▌        | 141/938 [00:09<00:53, 14.84it/s, loss=0.764, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  15%|█▌        | 142/938 [00:09<00:53, 14.83it/s, loss=0.773, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  15%|█▌        | 143/938 [00:09<00:53, 14.84it/s, loss=0.765, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  15%|█▌        | 144/938 [00:09<00:53, 14.81it/s, loss=0.765, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  15%|█▌        | 144/938 [00:09<00:53, 14.81it/s, loss=0.758, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  15%|█▌        | 145/938 [00:09<00:53, 14.81it/s, loss=0.75, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  16%|█▌        | 146/938 [00:09<00:53, 14.80it/s, loss=0.745, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  16%|█▌        | 147/938 [00:09<00:53, 14.80it/s, loss=0.74, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  16%|█▌        | 148/938 [00:09<00:53, 14.81it/s, loss=0.74, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  16%|█▌        | 148/938 [00:09<00:53, 14.81it/s, loss=0.743, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  16%|█▌        | 149/938 [00:10<00:53, 14.81it/s, loss=0.74, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  16%|█▌        | 150/938 [00:10<00:53, 14.81it/s, loss=0.745, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  16%|█▌        | 151/938 [00:10<00:53, 14.83it/s, loss=0.746, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  16%|█▌        | 152/938 [00:10<00:53, 14.82it/s, loss=0.746, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  16%|█▌        | 152/938 [00:10<00:53, 14.82it/s, loss=0.737, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  16%|█▋        | 153/938 [00:10<00:52, 14.84it/s, loss=0.733, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  16%|█▋        | 154/938 [00:10<00:52, 14.85it/s, loss=0.73, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  17%|█▋        | 155/938 [00:10<00:52, 14.87it/s, loss=0.736, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  17%|█▋        | 156/938 [00:10<00:52, 14.87it/s, loss=0.736, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  17%|█▋        | 156/938 [00:10<00:52, 14.87it/s, loss=0.737, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  17%|█▋        | 157/938 [00:10<00:52, 14.87it/s, loss=0.738, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  17%|█▋        | 158/938 [00:10<00:52, 14.87it/s, loss=0.736, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  17%|█▋        | 159/938 [00:10<00:52, 14.89it/s, loss=0.742, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  17%|█▋        | 160/938 [00:10<00:52, 14.90it/s, loss=0.742, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  17%|█▋        | 160/938 [00:10<00:52, 14.90it/s, loss=0.738, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  17%|█▋        | 161/938 [00:10<00:52, 14.89it/s, loss=0.738, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  17%|█▋        | 162/938 [00:10<00:52, 14.90it/s, loss=0.74, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  17%|█▋        | 163/938 [00:10<00:51, 14.91it/s, loss=0.74, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  17%|█▋        | 164/938 [00:10<00:51, 14.92it/s, loss=0.74, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  17%|█▋        | 164/938 [00:10<00:51, 14.92it/s, loss=0.745, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  18%|█▊        | 165/938 [00:11<00:51, 14.93it/s, loss=0.757, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  18%|█▊        | 166/938 [00:11<00:51, 14.93it/s, loss=0.762, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  18%|█▊        | 167/938 [00:11<00:51, 14.93it/s, loss=0.76, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  18%|█▊        | 168/938 [00:11<00:51, 14.94it/s, loss=0.76, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  18%|█▊        | 168/938 [00:11<00:51, 14.94it/s, loss=0.756, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  18%|█▊        | 169/938 [00:11<00:51, 14.94it/s, loss=0.762, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  18%|█▊        | 170/938 [00:11<00:51, 14.95it/s, loss=0.765, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  18%|█▊        | 171/938 [00:11<00:51, 14.96it/s, loss=0.76, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  18%|█▊        | 172/938 [00:11<00:51, 14.94it/s, loss=0.76, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  18%|█▊        | 172/938 [00:11<00:51, 14.94it/s, loss=0.768, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  18%|█▊        | 173/938 [00:11<00:51, 14.94it/s, loss=0.767, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  19%|█▊        | 174/938 [00:11<00:51, 14.97it/s, loss=0.754, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  19%|█▊        | 175/938 [00:11<00:50, 14.98it/s, loss=0.756, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  19%|█▉        | 176/938 [00:11<00:50, 14.98it/s, loss=0.756, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  19%|█▉        | 176/938 [00:11<00:50, 14.98it/s, loss=0.757, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  19%|█▉        | 177/938 [00:11<00:50, 14.99it/s, loss=0.75, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  19%|█▉        | 178/938 [00:11<00:50, 15.00it/s, loss=0.753, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  19%|█▉        | 179/938 [00:11<00:50, 14.99it/s, loss=0.751, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  19%|█▉        | 180/938 [00:12<00:50, 15.00it/s, loss=0.751, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  19%|█▉        | 180/938 [00:12<00:50, 14.99it/s, loss=0.753, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  19%|█▉        | 181/938 [00:12<00:50, 15.00it/s, loss=0.763, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  19%|█▉        | 182/938 [00:12<00:50, 14.99it/s, loss=0.763, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  20%|█▉        | 183/938 [00:12<00:50, 14.98it/s, loss=0.769, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  20%|█▉        | 184/938 [00:12<00:50, 14.98it/s, loss=0.769, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  20%|█▉        | 184/938 [00:12<00:50, 14.98it/s, loss=0.756, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  20%|█▉        | 185/938 [00:12<00:50, 14.98it/s, loss=0.75, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  20%|█▉        | 186/938 [00:12<00:50, 14.97it/s, loss=0.747, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  20%|█▉        | 187/938 [00:12<00:50, 14.97it/s, loss=0.752, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  20%|██        | 188/938 [00:12<00:50, 14.98it/s, loss=0.752, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  20%|██        | 188/938 [00:12<00:50, 14.98it/s, loss=0.753, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  20%|██        | 189/938 [00:12<00:49, 14.98it/s, loss=0.749, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  20%|██        | 190/938 [00:12<00:49, 14.98it/s, loss=0.755, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  20%|██        | 191/938 [00:12<00:49, 14.99it/s, loss=0.766, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  20%|██        | 192/938 [00:12<00:49, 14.98it/s, loss=0.766, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  20%|██        | 192/938 [00:12<00:49, 14.98it/s, loss=0.761, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  21%|██        | 193/938 [00:12<00:49, 14.98it/s, loss=0.758, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  21%|██        | 194/938 [00:12<00:49, 14.98it/s, loss=0.765, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  21%|██        | 195/938 [00:13<00:49, 14.95it/s, loss=0.767, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  21%|██        | 196/938 [00:13<00:49, 14.95it/s, loss=0.767, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  21%|██        | 196/938 [00:13<00:49, 14.95it/s, loss=0.766, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  21%|██        | 197/938 [00:13<00:49, 14.95it/s, loss=0.772, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  21%|██        | 198/938 [00:13<00:49, 14.95it/s, loss=0.767, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  21%|██        | 199/938 [00:13<00:49, 14.96it/s, loss=0.772, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  21%|██▏       | 200/938 [00:13<00:49, 14.97it/s, loss=0.772, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  21%|██▏       | 200/938 [00:13<00:49, 14.97it/s, loss=0.768, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  21%|██▏       | 201/938 [00:13<00:49, 14.96it/s, loss=0.764, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  22%|██▏       | 202/938 [00:13<00:49, 14.97it/s, loss=0.753, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  22%|██▏       | 203/938 [00:13<00:49, 14.98it/s, loss=0.769, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  22%|██▏       | 204/938 [00:13<00:49, 14.97it/s, loss=0.769, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  22%|██▏       | 204/938 [00:13<00:49, 14.97it/s, loss=0.779, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  22%|██▏       | 205/938 [00:13<00:48, 14.98it/s, loss=0.779, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  22%|██▏       | 206/938 [00:13<00:48, 14.98it/s, loss=0.785, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  22%|██▏       | 207/938 [00:13<00:48, 14.99it/s, loss=0.788, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  22%|██▏       | 208/938 [00:13<00:48, 15.00it/s, loss=0.788, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  22%|██▏       | 208/938 [00:13<00:48, 15.00it/s, loss=0.781, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  22%|██▏       | 209/938 [00:13<00:48, 14.99it/s, loss=0.78, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  22%|██▏       | 210/938 [00:14<00:48, 14.97it/s, loss=0.787, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  22%|██▏       | 211/938 [00:14<00:48, 14.97it/s, loss=0.777, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  23%|██▎       | 212/938 [00:14<00:48, 14.97it/s, loss=0.777, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  23%|██▎       | 212/938 [00:14<00:48, 14.97it/s, loss=0.775, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  23%|██▎       | 213/938 [00:14<00:48, 14.98it/s, loss=0.782, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  23%|██▎       | 214/938 [00:14<00:48, 14.98it/s, loss=0.789, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  23%|██▎       | 215/938 [00:14<00:48, 14.98it/s, loss=0.792, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  23%|██▎       | 216/938 [00:14<00:48, 14.98it/s, loss=0.792, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  23%|██▎       | 216/938 [00:14<00:48, 14.98it/s, loss=0.785, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  23%|██▎       | 217/938 [00:14<00:48, 14.97it/s, loss=0.783, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  23%|██▎       | 218/938 [00:14<00:48, 14.96it/s, loss=0.794, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  23%|██▎       | 219/938 [00:14<00:48, 14.97it/s, loss=0.789, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  23%|██▎       | 220/938 [00:14<00:47, 14.97it/s, loss=0.789, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  23%|██▎       | 220/938 [00:14<00:47, 14.97it/s, loss=0.793, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  24%|██▎       | 221/938 [00:14<00:47, 14.97it/s, loss=0.787, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  24%|██▎       | 222/938 [00:14<00:47, 14.97it/s, loss=0.783, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  24%|██▍       | 223/938 [00:14<00:47, 14.97it/s, loss=0.767, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  24%|██▍       | 224/938 [00:14<00:47, 14.96it/s, loss=0.767, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  24%|██▍       | 224/938 [00:14<00:47, 14.96it/s, loss=0.764, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  24%|██▍       | 225/938 [00:15<00:47, 14.96it/s, loss=0.762, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  24%|██▍       | 226/938 [00:15<00:47, 14.96it/s, loss=0.759, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  24%|██▍       | 227/938 [00:15<00:47, 14.96it/s, loss=0.758, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  24%|██▍       | 228/938 [00:15<00:47, 14.97it/s, loss=0.758, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  24%|██▍       | 228/938 [00:15<00:47, 14.97it/s, loss=0.763, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  24%|██▍       | 229/938 [00:15<00:47, 14.95it/s, loss=0.76, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  25%|██▍       | 230/938 [00:15<00:47, 14.97it/s, loss=0.743, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  25%|██▍       | 231/938 [00:15<00:47, 14.98it/s, loss=0.74, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  25%|██▍       | 232/938 [00:15<00:47, 14.98it/s, loss=0.74, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  25%|██▍       | 232/938 [00:15<00:47, 14.98it/s, loss=0.741, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  25%|██▍       | 233/938 [00:15<00:47, 14.99it/s, loss=0.74, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  25%|██▍       | 234/938 [00:15<00:47, 14.97it/s, loss=0.733, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  25%|██▌       | 235/938 [00:15<00:46, 14.97it/s, loss=0.723, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  25%|██▌       | 236/938 [00:15<00:46, 14.98it/s, loss=0.723, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  25%|██▌       | 236/938 [00:15<00:46, 14.98it/s, loss=0.733, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  25%|██▌       | 237/938 [00:15<00:46, 14.99it/s, loss=0.737, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  25%|██▌       | 238/938 [00:15<00:46, 14.98it/s, loss=0.733, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  25%|██▌       | 239/938 [00:15<00:46, 14.97it/s, loss=0.737, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  26%|██▌       | 240/938 [00:16<00:46, 14.97it/s, loss=0.737, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  26%|██▌       | 240/938 [00:16<00:46, 14.97it/s, loss=0.732, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  26%|██▌       | 241/938 [00:16<00:46, 14.97it/s, loss=0.731, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  26%|██▌       | 242/938 [00:16<00:46, 14.96it/s, loss=0.731, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  26%|██▌       | 243/938 [00:16<00:46, 14.93it/s, loss=0.723, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  26%|██▌       | 244/938 [00:16<00:46, 14.93it/s, loss=0.723, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  26%|██▌       | 244/938 [00:16<00:46, 14.93it/s, loss=0.72, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  26%|██▌       | 245/938 [00:16<00:46, 14.93it/s, loss=0.72, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  26%|██▌       | 246/938 [00:16<00:46, 14.93it/s, loss=0.72, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  26%|██▋       | 247/938 [00:16<00:46, 14.93it/s, loss=0.714, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  26%|██▋       | 248/938 [00:16<00:46, 14.93it/s, loss=0.714, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  26%|██▋       | 248/938 [00:16<00:46, 14.93it/s, loss=0.711, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  27%|██▋       | 249/938 [00:16<00:46, 14.94it/s, loss=0.713, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  27%|██▋       | 250/938 [00:16<00:46, 14.94it/s, loss=0.712, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  27%|██▋       | 251/938 [00:16<00:46, 14.93it/s, loss=0.714, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  27%|██▋       | 252/938 [00:16<00:45, 14.93it/s, loss=0.714, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  27%|██▋       | 252/938 [00:16<00:45, 14.93it/s, loss=0.718, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  27%|██▋       | 253/938 [00:16<00:45, 14.91it/s, loss=0.72, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  27%|██▋       | 254/938 [00:17<00:45, 14.92it/s, loss=0.715, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  27%|██▋       | 255/938 [00:17<00:45, 14.92it/s, loss=0.715, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  27%|██▋       | 256/938 [00:17<00:45, 14.92it/s, loss=0.715, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  27%|██▋       | 256/938 [00:17<00:45, 14.92it/s, loss=0.71, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  27%|██▋       | 257/938 [00:17<00:45, 14.92it/s, loss=0.695, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  28%|██▊       | 258/938 [00:17<00:45, 14.92it/s, loss=0.703, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  28%|██▊       | 259/938 [00:17<00:45, 14.92it/s, loss=0.698, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  28%|██▊       | 260/938 [00:17<00:45, 14.93it/s, loss=0.698, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  28%|██▊       | 260/938 [00:17<00:45, 14.93it/s, loss=0.702, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  28%|██▊       | 261/938 [00:17<00:45, 14.94it/s, loss=0.702, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  28%|██▊       | 262/938 [00:17<00:45, 14.93it/s, loss=0.719, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  28%|██▊       | 263/938 [00:17<00:45, 14.93it/s, loss=0.731, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  28%|██▊       | 264/938 [00:17<00:45, 14.92it/s, loss=0.731, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  28%|██▊       | 264/938 [00:17<00:45, 14.92it/s, loss=0.739, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  28%|██▊       | 265/938 [00:17<00:45, 14.91it/s, loss=0.748, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  28%|██▊       | 266/938 [00:17<00:45, 14.90it/s, loss=0.748, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  28%|██▊       | 267/938 [00:17<00:45, 14.90it/s, loss=0.75, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  29%|██▊       | 268/938 [00:17<00:44, 14.90it/s, loss=0.75, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  29%|██▊       | 268/938 [00:17<00:44, 14.90it/s, loss=0.748, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  29%|██▊       | 269/938 [00:18<00:44, 14.90it/s, loss=0.744, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  29%|██▉       | 270/938 [00:18<00:44, 14.90it/s, loss=0.743, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  29%|██▉       | 271/938 [00:18<00:44, 14.91it/s, loss=0.751, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  29%|██▉       | 272/938 [00:18<00:44, 14.91it/s, loss=0.751, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  29%|██▉       | 272/938 [00:18<00:44, 14.91it/s, loss=0.744, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  29%|██▉       | 273/938 [00:18<00:44, 14.90it/s, loss=0.739, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  29%|██▉       | 274/938 [00:18<00:44, 14.91it/s, loss=0.749, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  29%|██▉       | 275/938 [00:18<00:44, 14.91it/s, loss=0.755, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  29%|██▉       | 276/938 [00:18<00:44, 14.91it/s, loss=0.755, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  29%|██▉       | 276/938 [00:18<00:44, 14.91it/s, loss=0.756, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  30%|██▉       | 277/938 [00:18<00:44, 14.92it/s, loss=0.764, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  30%|██▉       | 278/938 [00:18<00:44, 14.92it/s, loss=0.769, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  30%|██▉       | 279/938 [00:18<00:44, 14.92it/s, loss=0.767, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  30%|██▉       | 280/938 [00:18<00:44, 14.94it/s, loss=0.767, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  30%|██▉       | 280/938 [00:18<00:44, 14.93it/s, loss=0.758, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  30%|██▉       | 281/938 [00:18<00:44, 14.93it/s, loss=0.754, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  30%|███       | 282/938 [00:18<00:43, 14.93it/s, loss=0.748, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  30%|███       | 283/938 [00:18<00:43, 14.94it/s, loss=0.738, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  30%|███       | 284/938 [00:19<00:43, 14.95it/s, loss=0.738, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  30%|███       | 284/938 [00:19<00:43, 14.95it/s, loss=0.74, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  30%|███       | 285/938 [00:19<00:43, 14.95it/s, loss=0.733, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  30%|███       | 286/938 [00:19<00:43, 14.94it/s, loss=0.743, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  31%|███       | 287/938 [00:19<00:43, 14.94it/s, loss=0.739, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  31%|███       | 288/938 [00:19<00:43, 14.94it/s, loss=0.739, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  31%|███       | 288/938 [00:19<00:43, 14.94it/s, loss=0.748, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  31%|███       | 289/938 [00:19<00:43, 14.95it/s, loss=0.754, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  31%|███       | 290/938 [00:19<00:43, 14.95it/s, loss=0.753, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  31%|███       | 291/938 [00:19<00:43, 14.95it/s, loss=0.745, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  31%|███       | 292/938 [00:19<00:43, 14.96it/s, loss=0.745, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  31%|███       | 292/938 [00:19<00:43, 14.96it/s, loss=0.75, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  31%|███       | 293/938 [00:19<00:43, 14.96it/s, loss=0.756, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  31%|███▏      | 294/938 [00:19<00:43, 14.97it/s, loss=0.752, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  31%|███▏      | 295/938 [00:19<00:42, 14.99it/s, loss=0.742, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  32%|███▏      | 296/938 [00:19<00:42, 14.99it/s, loss=0.742, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  32%|███▏      | 296/938 [00:19<00:42, 14.99it/s, loss=0.739, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  32%|███▏      | 297/938 [00:19<00:42, 14.98it/s, loss=0.739, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  32%|███▏      | 298/938 [00:19<00:42, 14.99it/s, loss=0.736, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  32%|███▏      | 299/938 [00:19<00:42, 14.98it/s, loss=0.737, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  32%|███▏      | 300/938 [00:20<00:42, 14.98it/s, loss=0.737, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  32%|███▏      | 300/938 [00:20<00:42, 14.98it/s, loss=0.734, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  32%|███▏      | 301/938 [00:20<00:42, 14.99it/s, loss=0.737, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  32%|███▏      | 302/938 [00:20<00:42, 14.99it/s, loss=0.73, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  32%|███▏      | 303/938 [00:20<00:42, 14.99it/s, loss=0.732, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  32%|███▏      | 304/938 [00:20<00:42, 14.99it/s, loss=0.732, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  32%|███▏      | 304/938 [00:20<00:42, 14.99it/s, loss=0.723, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  33%|███▎      | 305/938 [00:20<00:42, 15.00it/s, loss=0.72, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  33%|███▎      | 306/938 [00:20<00:42, 14.99it/s, loss=0.703, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  33%|███▎      | 307/938 [00:20<00:42, 14.99it/s, loss=0.705, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  33%|███▎      | 308/938 [00:20<00:42, 14.99it/s, loss=0.705, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  33%|███▎      | 308/938 [00:20<00:42, 14.99it/s, loss=0.703, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  33%|███▎      | 309/938 [00:20<00:41, 14.99it/s, loss=0.7, v_num=13, val_rmse=0.717, train_rmse=1.190]  
Epoch 1:  33%|███▎      | 310/938 [00:20<00:41, 15.00it/s, loss=0.699, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  33%|███▎      | 311/938 [00:20<00:41, 14.99it/s, loss=0.705, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  33%|███▎      | 312/938 [00:20<00:41, 15.00it/s, loss=0.705, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  33%|███▎      | 312/938 [00:20<00:41, 15.00it/s, loss=0.711, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  33%|███▎      | 313/938 [00:20<00:41, 15.00it/s, loss=0.702, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  33%|███▎      | 314/938 [00:20<00:41, 15.00it/s, loss=0.701, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  34%|███▎      | 315/938 [00:20<00:41, 15.01it/s, loss=0.712, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  34%|███▎      | 316/938 [00:21<00:41, 15.01it/s, loss=0.712, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  34%|███▎      | 316/938 [00:21<00:41, 15.01it/s, loss=0.712, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  34%|███▍      | 317/938 [00:21<00:41, 15.01it/s, loss=0.703, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  34%|███▍      | 318/938 [00:21<00:41, 15.01it/s, loss=0.701, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  34%|███▍      | 319/938 [00:21<00:41, 15.01it/s, loss=0.702, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  34%|███▍      | 320/938 [00:21<00:41, 15.01it/s, loss=0.702, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  34%|███▍      | 320/938 [00:21<00:41, 15.01it/s, loss=0.717, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  34%|███▍      | 321/938 [00:21<00:41, 15.01it/s, loss=0.716, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  34%|███▍      | 322/938 [00:21<00:41, 15.02it/s, loss=0.721, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  34%|███▍      | 323/938 [00:21<00:40, 15.02it/s, loss=0.726, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  35%|███▍      | 324/938 [00:21<00:40, 15.03it/s, loss=0.726, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  35%|███▍      | 324/938 [00:21<00:40, 15.03it/s, loss=0.733, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  35%|███▍      | 325/938 [00:21<00:40, 15.03it/s, loss=0.733, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  35%|███▍      | 326/938 [00:21<00:40, 15.04it/s, loss=0.743, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  35%|███▍      | 327/938 [00:21<00:40, 15.04it/s, loss=0.743, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  35%|███▍      | 328/938 [00:21<00:40, 15.04it/s, loss=0.743, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  35%|███▍      | 328/938 [00:21<00:40, 15.04it/s, loss=0.739, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  35%|███▌      | 329/938 [00:21<00:40, 15.04it/s, loss=0.739, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  35%|███▌      | 330/938 [00:21<00:40, 15.05it/s, loss=0.749, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  35%|███▌      | 331/938 [00:21<00:40, 15.05it/s, loss=0.739, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  35%|███▌      | 332/938 [00:22<00:40, 15.05it/s, loss=0.739, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  35%|███▌      | 332/938 [00:22<00:40, 15.05it/s, loss=0.734, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  36%|███▌      | 333/938 [00:22<00:40, 15.05it/s, loss=0.734, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  36%|███▌      | 334/938 [00:22<00:40, 15.06it/s, loss=0.738, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  36%|███▌      | 335/938 [00:22<00:40, 15.06it/s, loss=0.728, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  36%|███▌      | 336/938 [00:22<00:40, 15.04it/s, loss=0.728, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  36%|███▌      | 336/938 [00:22<00:40, 15.04it/s, loss=0.728, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  36%|███▌      | 337/938 [00:22<00:39, 15.05it/s, loss=0.738, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  36%|███▌      | 338/938 [00:22<00:39, 15.05it/s, loss=0.725, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  36%|███▌      | 339/938 [00:22<00:39, 15.05it/s, loss=0.725, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  36%|███▌      | 340/938 [00:22<00:39, 15.05it/s, loss=0.725, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  36%|███▌      | 340/938 [00:22<00:39, 15.05it/s, loss=0.72, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  36%|███▋      | 341/938 [00:22<00:39, 15.05it/s, loss=0.728, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  36%|███▋      | 342/938 [00:22<00:39, 15.05it/s, loss=0.735, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  37%|███▋      | 343/938 [00:22<00:39, 15.05it/s, loss=0.722, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  37%|███▋      | 344/938 [00:22<00:39, 15.06it/s, loss=0.722, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  37%|███▋      | 344/938 [00:22<00:39, 15.06it/s, loss=0.717, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  37%|███▋      | 345/938 [00:22<00:39, 15.06it/s, loss=0.722, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  37%|███▋      | 346/938 [00:22<00:39, 15.06it/s, loss=0.71, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  37%|███▋      | 347/938 [00:23<00:39, 15.06it/s, loss=0.71, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  37%|███▋      | 348/938 [00:23<00:39, 15.05it/s, loss=0.71, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  37%|███▋      | 348/938 [00:23<00:39, 15.05it/s, loss=0.708, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  37%|███▋      | 349/938 [00:23<00:39, 15.05it/s, loss=0.705, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  37%|███▋      | 350/938 [00:23<00:39, 15.05it/s, loss=0.689, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  37%|███▋      | 351/938 [00:23<00:39, 15.04it/s, loss=0.693, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  38%|███▊      | 352/938 [00:23<00:38, 15.04it/s, loss=0.693, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  38%|███▊      | 352/938 [00:23<00:38, 15.04it/s, loss=0.69, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  38%|███▊      | 353/938 [00:23<00:38, 15.05it/s, loss=0.689, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  38%|███▊      | 354/938 [00:23<00:38, 15.04it/s, loss=0.693, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  38%|███▊      | 355/938 [00:23<00:38, 15.04it/s, loss=0.702, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  38%|███▊      | 356/938 [00:23<00:38, 15.05it/s, loss=0.702, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  38%|███▊      | 356/938 [00:23<00:38, 15.05it/s, loss=0.704, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  38%|███▊      | 357/938 [00:23<00:38, 15.05it/s, loss=0.698, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  38%|███▊      | 358/938 [00:23<00:38, 15.05it/s, loss=0.698, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  38%|███▊      | 359/938 [00:23<00:38, 15.06it/s, loss=0.7, v_num=13, val_rmse=0.717, train_rmse=1.190]  
Epoch 1:  38%|███▊      | 360/938 [00:23<00:38, 15.05it/s, loss=0.7, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  38%|███▊      | 360/938 [00:23<00:38, 15.05it/s, loss=0.703, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  38%|███▊      | 361/938 [00:23<00:38, 15.05it/s, loss=0.689, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  39%|███▊      | 362/938 [00:24<00:38, 15.05it/s, loss=0.679, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  39%|███▊      | 363/938 [00:24<00:38, 15.05it/s, loss=0.689, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  39%|███▉      | 364/938 [00:24<00:38, 15.05it/s, loss=0.689, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  39%|███▉      | 364/938 [00:24<00:38, 15.05it/s, loss=0.684, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  39%|███▉      | 365/938 [00:24<00:38, 15.05it/s, loss=0.682, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  39%|███▉      | 366/938 [00:24<00:38, 15.05it/s, loss=0.695, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  39%|███▉      | 367/938 [00:24<00:37, 15.06it/s, loss=0.694, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  39%|███▉      | 368/938 [00:24<00:37, 15.06it/s, loss=0.694, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  39%|███▉      | 368/938 [00:24<00:37, 15.05it/s, loss=0.7, v_num=13, val_rmse=0.717, train_rmse=1.190]  
Epoch 1:  39%|███▉      | 369/938 [00:24<00:37, 15.05it/s, loss=0.707, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  39%|███▉      | 370/938 [00:24<00:37, 15.05it/s, loss=0.721, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  40%|███▉      | 371/938 [00:24<00:37, 15.06it/s, loss=0.723, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  40%|███▉      | 372/938 [00:24<00:37, 15.06it/s, loss=0.723, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  40%|███▉      | 372/938 [00:24<00:37, 15.06it/s, loss=0.73, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  40%|███▉      | 373/938 [00:24<00:37, 15.06it/s, loss=0.726, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  40%|███▉      | 374/938 [00:24<00:37, 15.06it/s, loss=0.714, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  40%|███▉      | 375/938 [00:24<00:37, 15.07it/s, loss=0.716, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  40%|████      | 376/938 [00:24<00:37, 15.07it/s, loss=0.716, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  40%|████      | 376/938 [00:24<00:37, 15.07it/s, loss=0.72, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  40%|████      | 377/938 [00:25<00:37, 15.07it/s, loss=0.72, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  40%|████      | 378/938 [00:25<00:37, 15.07it/s, loss=0.729, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  40%|████      | 379/938 [00:25<00:37, 15.07it/s, loss=0.724, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  41%|████      | 380/938 [00:25<00:37, 15.08it/s, loss=0.724, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  41%|████      | 380/938 [00:25<00:37, 15.08it/s, loss=0.718, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  41%|████      | 381/938 [00:25<00:36, 15.07it/s, loss=0.724, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  41%|████      | 382/938 [00:25<00:36, 15.08it/s, loss=0.731, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  41%|████      | 383/938 [00:25<00:36, 15.08it/s, loss=0.726, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  41%|████      | 384/938 [00:25<00:36, 15.09it/s, loss=0.726, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  41%|████      | 384/938 [00:25<00:36, 15.09it/s, loss=0.741, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  41%|████      | 385/938 [00:25<00:36, 15.09it/s, loss=0.742, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  41%|████      | 386/938 [00:25<00:36, 15.09it/s, loss=0.739, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  41%|████▏     | 387/938 [00:25<00:36, 15.09it/s, loss=0.747, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  41%|████▏     | 388/938 [00:25<00:36, 15.10it/s, loss=0.747, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  41%|████▏     | 388/938 [00:25<00:36, 15.10it/s, loss=0.751, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  41%|████▏     | 389/938 [00:25<00:36, 15.10it/s, loss=0.748, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  42%|████▏     | 390/938 [00:25<00:36, 15.09it/s, loss=0.742, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  42%|████▏     | 391/938 [00:25<00:36, 15.10it/s, loss=0.733, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  42%|████▏     | 392/938 [00:25<00:36, 15.10it/s, loss=0.733, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  42%|████▏     | 392/938 [00:25<00:36, 15.10it/s, loss=0.731, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  42%|████▏     | 393/938 [00:26<00:36, 15.10it/s, loss=0.744, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  42%|████▏     | 394/938 [00:26<00:36, 15.11it/s, loss=0.745, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  42%|████▏     | 395/938 [00:26<00:35, 15.11it/s, loss=0.74, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  42%|████▏     | 396/938 [00:26<00:35, 15.11it/s, loss=0.74, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  42%|████▏     | 396/938 [00:26<00:35, 15.11it/s, loss=0.735, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  42%|████▏     | 397/938 [00:26<00:35, 15.12it/s, loss=0.742, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  42%|████▏     | 398/938 [00:26<00:35, 15.11it/s, loss=0.74, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  43%|████▎     | 399/938 [00:26<00:35, 15.11it/s, loss=0.749, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  43%|████▎     | 400/938 [00:26<00:35, 15.11it/s, loss=0.749, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  43%|████▎     | 400/938 [00:26<00:35, 15.11it/s, loss=0.76, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  43%|████▎     | 401/938 [00:26<00:35, 15.12it/s, loss=0.758, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  43%|████▎     | 402/938 [00:26<00:35, 15.12it/s, loss=0.752, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  43%|████▎     | 403/938 [00:26<00:35, 15.12it/s, loss=0.757, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  43%|████▎     | 404/938 [00:26<00:35, 15.12it/s, loss=0.757, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  43%|████▎     | 404/938 [00:26<00:35, 15.12it/s, loss=0.756, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  43%|████▎     | 405/938 [00:26<00:35, 15.12it/s, loss=0.745, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  43%|████▎     | 406/938 [00:26<00:35, 15.12it/s, loss=0.746, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  43%|████▎     | 407/938 [00:26<00:35, 15.11it/s, loss=0.737, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  43%|████▎     | 408/938 [00:27<00:35, 15.11it/s, loss=0.737, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  43%|████▎     | 408/938 [00:27<00:35, 15.11it/s, loss=0.722, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  44%|████▎     | 409/938 [00:27<00:35, 15.11it/s, loss=0.725, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  44%|████▎     | 410/938 [00:27<00:34, 15.11it/s, loss=0.724, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  44%|████▍     | 411/938 [00:27<00:34, 15.11it/s, loss=0.734, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  44%|████▍     | 412/938 [00:27<00:34, 15.12it/s, loss=0.734, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  44%|████▍     | 412/938 [00:27<00:34, 15.11it/s, loss=0.728, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  44%|████▍     | 413/938 [00:27<00:34, 15.11it/s, loss=0.719, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  44%|████▍     | 414/938 [00:27<00:34, 15.11it/s, loss=0.72, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  44%|████▍     | 415/938 [00:27<00:34, 15.11it/s, loss=0.723, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  44%|████▍     | 416/938 [00:27<00:34, 15.11it/s, loss=0.723, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  44%|████▍     | 416/938 [00:27<00:34, 15.11it/s, loss=0.713, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  44%|████▍     | 417/938 [00:27<00:34, 15.11it/s, loss=0.706, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  45%|████▍     | 418/938 [00:27<00:34, 15.11it/s, loss=0.712, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  45%|████▍     | 419/938 [00:27<00:34, 15.11it/s, loss=0.714, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  45%|████▍     | 420/938 [00:27<00:34, 15.11it/s, loss=0.714, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  45%|████▍     | 420/938 [00:27<00:34, 15.11it/s, loss=0.701, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  45%|████▍     | 421/938 [00:27<00:34, 15.11it/s, loss=0.704, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  45%|████▍     | 422/938 [00:27<00:34, 15.12it/s, loss=0.706, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  45%|████▌     | 423/938 [00:27<00:34, 15.12it/s, loss=0.7, v_num=13, val_rmse=0.717, train_rmse=1.190]  
Epoch 1:  45%|████▌     | 424/938 [00:28<00:33, 15.12it/s, loss=0.7, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  45%|████▌     | 424/938 [00:28<00:33, 15.12it/s, loss=0.691, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  45%|████▌     | 425/938 [00:28<00:33, 15.12it/s, loss=0.69, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  45%|████▌     | 426/938 [00:28<00:33, 15.12it/s, loss=0.685, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  46%|████▌     | 427/938 [00:28<00:33, 15.12it/s, loss=0.687, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  46%|████▌     | 428/938 [00:28<00:33, 15.12it/s, loss=0.687, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  46%|████▌     | 428/938 [00:28<00:33, 15.12it/s, loss=0.694, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  46%|████▌     | 429/938 [00:28<00:33, 15.12it/s, loss=0.695, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  46%|████▌     | 430/938 [00:28<00:33, 15.12it/s, loss=0.693, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  46%|████▌     | 431/938 [00:28<00:33, 15.13it/s, loss=0.694, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  46%|████▌     | 432/938 [00:28<00:33, 15.13it/s, loss=0.694, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  46%|████▌     | 432/938 [00:28<00:33, 15.13it/s, loss=0.694, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  46%|████▌     | 433/938 [00:28<00:33, 15.13it/s, loss=0.697, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  46%|████▋     | 434/938 [00:28<00:33, 15.13it/s, loss=0.699, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  46%|████▋     | 435/938 [00:28<00:33, 15.12it/s, loss=0.698, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  46%|████▋     | 436/938 [00:28<00:33, 15.12it/s, loss=0.698, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  46%|████▋     | 436/938 [00:28<00:33, 15.12it/s, loss=0.708, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  47%|████▋     | 437/938 [00:28<00:33, 15.12it/s, loss=0.717, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  47%|████▋     | 438/938 [00:28<00:33, 15.12it/s, loss=0.703, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  47%|████▋     | 439/938 [00:29<00:32, 15.13it/s, loss=0.698, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  47%|████▋     | 440/938 [00:29<00:32, 15.14it/s, loss=0.698, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  47%|████▋     | 440/938 [00:29<00:32, 15.13it/s, loss=0.699, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  47%|████▋     | 441/938 [00:29<00:32, 15.13it/s, loss=0.7, v_num=13, val_rmse=0.717, train_rmse=1.190]  
Epoch 1:  47%|████▋     | 442/938 [00:29<00:32, 15.13it/s, loss=0.698, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  47%|████▋     | 443/938 [00:29<00:32, 15.14it/s, loss=0.698, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  47%|████▋     | 444/938 [00:29<00:32, 15.14it/s, loss=0.698, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  47%|████▋     | 444/938 [00:29<00:32, 15.14it/s, loss=0.696, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  47%|████▋     | 445/938 [00:29<00:32, 15.14it/s, loss=0.7, v_num=13, val_rmse=0.717, train_rmse=1.190]  
Epoch 1:  48%|████▊     | 446/938 [00:29<00:32, 15.14it/s, loss=0.708, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  48%|████▊     | 447/938 [00:29<00:32, 15.14it/s, loss=0.712, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  48%|████▊     | 448/938 [00:29<00:32, 15.14it/s, loss=0.712, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  48%|████▊     | 448/938 [00:29<00:32, 15.14it/s, loss=0.715, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  48%|████▊     | 449/938 [00:29<00:32, 15.14it/s, loss=0.718, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  48%|████▊     | 450/938 [00:29<00:32, 15.14it/s, loss=0.719, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  48%|████▊     | 451/938 [00:29<00:32, 15.14it/s, loss=0.716, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  48%|████▊     | 452/938 [00:29<00:32, 15.15it/s, loss=0.716, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  48%|████▊     | 452/938 [00:29<00:32, 15.15it/s, loss=0.714, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  48%|████▊     | 453/938 [00:29<00:32, 15.15it/s, loss=0.709, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  48%|████▊     | 454/938 [00:29<00:31, 15.15it/s, loss=0.703, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  49%|████▊     | 455/938 [00:30<00:31, 15.16it/s, loss=0.703, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  49%|████▊     | 456/938 [00:30<00:31, 15.16it/s, loss=0.703, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  49%|████▊     | 456/938 [00:30<00:31, 15.16it/s, loss=0.7, v_num=13, val_rmse=0.717, train_rmse=1.190]  
Epoch 1:  49%|████▊     | 457/938 [00:30<00:31, 15.16it/s, loss=0.691, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  49%|████▉     | 458/938 [00:30<00:31, 15.17it/s, loss=0.69, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  49%|████▉     | 459/938 [00:30<00:31, 15.17it/s, loss=0.686, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  49%|████▉     | 460/938 [00:30<00:31, 15.17it/s, loss=0.686, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  49%|████▉     | 460/938 [00:30<00:31, 15.17it/s, loss=0.69, v_num=13, val_rmse=0.717, train_rmse=1.190] 
Epoch 1:  49%|████▉     | 461/938 [00:30<00:31, 15.17it/s, loss=0.678, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  49%|████▉     | 462/938 [00:30<00:31, 15.18it/s, loss=0.675, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  49%|████▉     | 463/938 [00:30<00:31, 15.18it/s, loss=0.678, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  49%|████▉     | 464/938 [00:30<00:31, 15.18it/s, loss=0.678, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  49%|████▉     | 464/938 [00:30<00:31, 15.18it/s, loss=0.682, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  50%|████▉     | 465/938 [00:30<00:31, 15.18it/s, loss=0.683, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  50%|████▉     | 466/938 [00:30<00:31, 15.18it/s, loss=0.681, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  50%|████▉     | 467/938 [00:30<00:31, 15.16it/s, loss=0.675, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  50%|████▉     | 468/938 [00:30<00:30, 15.17it/s, loss=0.675, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  50%|████▉     | 468/938 [00:30<00:30, 15.17it/s, loss=0.668, v_num=13, val_rmse=0.717, train_rmse=1.190]
Epoch 1:  50%|█████     | 469/938 [00:30<00:30, 15.18it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]
Epoch 1:  50%|█████     | 472/938 [00:31<00:30, 15.22it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:   1%|          | 3/469 [00:00<00:21, 21.86it/s]

Validating:   1%|▏         | 6/469 [00:00<00:18, 24.46it/s]
Epoch 1:  51%|█████     | 476/938 [00:31<00:30, 15.28it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:   2%|▏         | 9/469 [00:00<00:18, 25.30it/s]
Epoch 1:  51%|█████     | 480/938 [00:31<00:29, 15.33it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:   3%|▎         | 12/469 [00:00<00:18, 24.92it/s]
Epoch 1:  52%|█████▏    | 484/938 [00:31<00:29, 15.39it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:   3%|▎         | 15/469 [00:00<00:18, 25.03it/s]

Validating:   4%|▍         | 18/469 [00:00<00:17, 25.16it/s]
Epoch 1:  52%|█████▏    | 488/938 [00:31<00:29, 15.43it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:   4%|▍         | 21/469 [00:00<00:17, 25.70it/s]
Epoch 1:  52%|█████▏    | 492/938 [00:31<00:28, 15.48it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:   5%|▌         | 24/469 [00:00<00:16, 26.52it/s]
Epoch 1:  53%|█████▎    | 496/938 [00:31<00:28, 15.54it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:   6%|▌         | 27/469 [00:01<00:16, 26.27it/s]

Validating:   6%|▋         | 30/469 [00:01<00:16, 26.82it/s]
Epoch 1:  53%|█████▎    | 500/938 [00:32<00:28, 15.59it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:   7%|▋         | 33/469 [00:01<00:15, 27.49it/s]
Epoch 1:  54%|█████▎    | 504/938 [00:32<00:27, 15.65it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:   8%|▊         | 36/469 [00:01<00:16, 26.69it/s]
Epoch 1:  54%|█████▍    | 508/938 [00:32<00:27, 15.69it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:   8%|▊         | 39/469 [00:01<00:16, 25.82it/s]

Validating:   9%|▉         | 42/469 [00:01<00:16, 26.19it/s]
Epoch 1:  55%|█████▍    | 512/938 [00:32<00:27, 15.74it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  10%|▉         | 45/469 [00:01<00:16, 26.18it/s]
Epoch 1:  55%|█████▌    | 516/938 [00:32<00:26, 15.79it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  10%|█         | 48/469 [00:01<00:15, 26.81it/s]
Epoch 1:  55%|█████▌    | 520/938 [00:32<00:26, 15.84it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  11%|█         | 51/469 [00:01<00:16, 25.91it/s]

Validating:  12%|█▏        | 54/469 [00:02<00:15, 26.04it/s]
Epoch 1:  56%|█████▌    | 524/938 [00:32<00:26, 15.88it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  12%|█▏        | 57/469 [00:02<00:15, 26.83it/s]
Epoch 1:  56%|█████▋    | 528/938 [00:33<00:25, 15.94it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  13%|█▎        | 60/469 [00:02<00:15, 27.21it/s]
Epoch 1:  57%|█████▋    | 532/938 [00:33<00:25, 15.99it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  13%|█▎        | 63/469 [00:02<00:15, 26.99it/s]
Epoch 1:  57%|█████▋    | 536/938 [00:33<00:25, 16.04it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  14%|█▍        | 67/469 [00:02<00:14, 28.11it/s]

Validating:  15%|█▍        | 70/469 [00:02<00:14, 28.08it/s]
Epoch 1:  58%|█████▊    | 540/938 [00:33<00:24, 16.10it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  16%|█▌        | 73/469 [00:02<00:14, 28.00it/s]
Epoch 1:  58%|█████▊    | 544/938 [00:33<00:24, 16.14it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  16%|█▌        | 76/469 [00:02<00:14, 27.28it/s]
Epoch 1:  58%|█████▊    | 548/938 [00:33<00:24, 16.19it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  17%|█▋        | 79/469 [00:02<00:14, 26.19it/s]

Validating:  17%|█▋        | 82/469 [00:03<00:14, 26.10it/s]
Epoch 1:  59%|█████▉    | 552/938 [00:34<00:23, 16.23it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  18%|█▊        | 85/469 [00:03<00:14, 26.81it/s]
Epoch 1:  59%|█████▉    | 556/938 [00:34<00:23, 16.28it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  19%|█▉        | 88/469 [00:03<00:14, 27.08it/s]
Epoch 1:  60%|█████▉    | 560/938 [00:34<00:23, 16.33it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  19%|█▉        | 91/469 [00:03<00:14, 26.98it/s]

Validating:  20%|██        | 94/469 [00:03<00:13, 27.66it/s]
Epoch 1:  60%|██████    | 564/938 [00:34<00:22, 16.37it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  21%|██        | 97/469 [00:03<00:13, 27.64it/s]
Epoch 1:  61%|██████    | 568/938 [00:34<00:22, 16.43it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  22%|██▏       | 101/469 [00:03<00:13, 28.15it/s]
Epoch 1:  61%|██████    | 572/938 [00:34<00:22, 16.47it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  22%|██▏       | 104/469 [00:03<00:13, 27.77it/s]
Epoch 1:  61%|██████▏   | 576/938 [00:34<00:21, 16.51it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  23%|██▎       | 107/469 [00:04<00:13, 27.57it/s]

Validating:  23%|██▎       | 110/469 [00:04<00:13, 27.08it/s]
Epoch 1:  62%|██████▏   | 580/938 [00:35<00:21, 16.56it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  24%|██▍       | 113/469 [00:04<00:13, 26.21it/s]
Epoch 1:  62%|██████▏   | 584/938 [00:35<00:21, 16.60it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  25%|██▍       | 116/469 [00:04<00:13, 26.88it/s]
Epoch 1:  63%|██████▎   | 588/938 [00:35<00:21, 16.64it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  25%|██▌       | 119/469 [00:04<00:13, 26.43it/s]

Validating:  26%|██▌       | 122/469 [00:04<00:12, 27.16it/s]
Epoch 1:  63%|██████▎   | 592/938 [00:35<00:20, 16.69it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  27%|██▋       | 125/469 [00:04<00:12, 27.51it/s]
Epoch 1:  64%|██████▎   | 596/938 [00:35<00:20, 16.73it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  27%|██▋       | 128/469 [00:04<00:12, 27.24it/s]
Epoch 1:  64%|██████▍   | 600/938 [00:35<00:20, 16.77it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  28%|██▊       | 131/469 [00:04<00:12, 26.95it/s]

Validating:  29%|██▊       | 134/469 [00:05<00:12, 27.59it/s]
Epoch 1:  64%|██████▍   | 604/938 [00:35<00:19, 16.82it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  29%|██▉       | 137/469 [00:05<00:12, 26.58it/s]
Epoch 1:  65%|██████▍   | 608/938 [00:36<00:19, 16.85it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  30%|██▉       | 140/469 [00:05<00:12, 26.06it/s]
Epoch 1:  65%|██████▌   | 612/938 [00:36<00:19, 16.89it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  30%|███       | 143/469 [00:05<00:12, 25.90it/s]

Validating:  31%|███       | 146/469 [00:05<00:12, 25.96it/s]
Epoch 1:  66%|██████▌   | 616/938 [00:36<00:19, 16.93it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  32%|███▏      | 149/469 [00:05<00:12, 26.33it/s]
Epoch 1:  66%|██████▌   | 620/938 [00:36<00:18, 16.97it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  32%|███▏      | 152/469 [00:05<00:12, 26.31it/s]
Epoch 1:  67%|██████▋   | 624/938 [00:36<00:18, 17.01it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  33%|███▎      | 155/469 [00:05<00:11, 26.20it/s]

Validating:  34%|███▎      | 158/469 [00:05<00:11, 26.04it/s]
Epoch 1:  67%|██████▋   | 628/938 [00:36<00:18, 17.04it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  34%|███▍      | 161/469 [00:06<00:11, 26.31it/s]
Epoch 1:  67%|██████▋   | 632/938 [00:36<00:17, 17.09it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  35%|███▍      | 164/469 [00:06<00:11, 26.46it/s]
Epoch 1:  68%|██████▊   | 636/938 [00:37<00:17, 17.12it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  36%|███▌      | 167/469 [00:06<00:11, 26.89it/s]
Epoch 1:  68%|██████▊   | 640/938 [00:37<00:17, 17.17it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  36%|███▋      | 171/469 [00:06<00:10, 27.45it/s]

Validating:  37%|███▋      | 174/469 [00:06<00:10, 27.60it/s]
Epoch 1:  69%|██████▊   | 644/938 [00:37<00:17, 17.21it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  38%|███▊      | 177/469 [00:06<00:10, 27.42it/s]
Epoch 1:  69%|██████▉   | 648/938 [00:37<00:16, 17.24it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  38%|███▊      | 180/469 [00:06<00:10, 27.24it/s]
Epoch 1:  70%|██████▉   | 652/938 [00:37<00:16, 17.28it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  39%|███▉      | 183/469 [00:06<00:10, 26.59it/s]

Validating:  40%|███▉      | 186/469 [00:06<00:10, 26.22it/s]
Epoch 1:  70%|██████▉   | 656/938 [00:37<00:16, 17.32it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  41%|████      | 190/469 [00:07<00:10, 27.61it/s]
Epoch 1:  70%|███████   | 660/938 [00:38<00:16, 17.36it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  41%|████      | 193/469 [00:07<00:10, 26.94it/s]
Epoch 1:  71%|███████   | 664/938 [00:38<00:15, 17.40it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  42%|████▏     | 196/469 [00:07<00:10, 26.70it/s]
Epoch 1:  71%|███████   | 668/938 [00:38<00:15, 17.43it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  42%|████▏     | 199/469 [00:07<00:10, 26.70it/s]

Validating:  43%|████▎     | 202/469 [00:07<00:09, 27.21it/s]
Epoch 1:  72%|███████▏  | 672/938 [00:38<00:15, 17.47it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  44%|████▎     | 205/469 [00:07<00:09, 27.52it/s]
Epoch 1:  72%|███████▏  | 676/938 [00:38<00:14, 17.51it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  44%|████▍     | 208/469 [00:07<00:09, 27.42it/s]
Epoch 1:  72%|███████▏  | 680/938 [00:38<00:14, 17.54it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  45%|████▍     | 211/469 [00:07<00:09, 26.98it/s]

Validating:  46%|████▌     | 214/469 [00:08<00:09, 26.72it/s]
Epoch 1:  73%|███████▎  | 684/938 [00:38<00:14, 17.58it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  46%|████▋     | 217/469 [00:08<00:09, 27.18it/s]
Epoch 1:  73%|███████▎  | 688/938 [00:39<00:14, 17.62it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  47%|████▋     | 221/469 [00:08<00:08, 27.66it/s]
Epoch 1:  74%|███████▍  | 692/938 [00:39<00:13, 17.66it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  48%|████▊     | 224/469 [00:08<00:08, 27.48it/s]
Epoch 1:  74%|███████▍  | 696/938 [00:39<00:13, 17.69it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  48%|████▊     | 227/469 [00:08<00:08, 27.01it/s]

Validating:  49%|████▉     | 230/469 [00:08<00:08, 27.27it/s]
Epoch 1:  75%|███████▍  | 700/938 [00:39<00:13, 17.72it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  50%|████▉     | 233/469 [00:08<00:08, 26.83it/s]
Epoch 1:  75%|███████▌  | 704/938 [00:39<00:13, 17.75it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  50%|█████     | 236/469 [00:08<00:08, 26.23it/s]
Epoch 1:  75%|███████▌  | 708/938 [00:39<00:12, 17.79it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  51%|█████     | 239/469 [00:08<00:08, 26.70it/s]

Validating:  52%|█████▏    | 242/469 [00:09<00:08, 26.82it/s]
Epoch 1:  76%|███████▌  | 712/938 [00:39<00:12, 17.82it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  52%|█████▏    | 245/469 [00:09<00:08, 27.16it/s]
Epoch 1:  76%|███████▋  | 716/938 [00:40<00:12, 17.86it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  53%|█████▎    | 248/469 [00:09<00:08, 27.12it/s]
Epoch 1:  77%|███████▋  | 720/938 [00:40<00:12, 17.89it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  54%|█████▎    | 251/469 [00:09<00:08, 27.20it/s]

Validating:  54%|█████▍    | 254/469 [00:09<00:07, 27.85it/s]
Epoch 1:  77%|███████▋  | 724/938 [00:40<00:11, 17.93it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  55%|█████▌    | 258/469 [00:09<00:07, 28.16it/s]
Epoch 1:  78%|███████▊  | 728/938 [00:40<00:11, 17.97it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  56%|█████▌    | 261/469 [00:09<00:07, 27.57it/s]
Epoch 1:  78%|███████▊  | 732/938 [00:40<00:11, 18.00it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  56%|█████▋    | 264/469 [00:09<00:07, 27.56it/s]
Epoch 1:  78%|███████▊  | 736/938 [00:40<00:11, 18.04it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  57%|█████▋    | 267/469 [00:09<00:07, 27.65it/s]

Validating:  58%|█████▊    | 270/469 [00:10<00:07, 27.55it/s]
Epoch 1:  79%|███████▉  | 740/938 [00:40<00:10, 18.07it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  58%|█████▊    | 273/469 [00:10<00:07, 27.46it/s]
Epoch 1:  79%|███████▉  | 744/938 [00:41<00:10, 18.10it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  59%|█████▉    | 276/469 [00:10<00:07, 27.52it/s]
Epoch 1:  80%|███████▉  | 748/938 [00:41<00:10, 18.13it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  59%|█████▉    | 279/469 [00:10<00:07, 27.06it/s]

Validating:  60%|██████    | 282/469 [00:10<00:07, 25.62it/s]
Epoch 1:  80%|████████  | 752/938 [00:41<00:10, 18.15it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  61%|██████    | 285/469 [00:10<00:07, 25.64it/s]
Epoch 1:  81%|████████  | 756/938 [00:41<00:10, 18.18it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  61%|██████▏   | 288/469 [00:10<00:07, 25.73it/s]
Epoch 1:  81%|████████  | 760/938 [00:41<00:09, 18.21it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  62%|██████▏   | 291/469 [00:10<00:06, 26.16it/s]

Validating:  63%|██████▎   | 294/469 [00:10<00:06, 26.87it/s]
Epoch 1:  81%|████████▏ | 764/938 [00:41<00:09, 18.25it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  64%|██████▎   | 298/469 [00:11<00:06, 27.84it/s]
Epoch 1:  82%|████████▏ | 768/938 [00:42<00:09, 18.28it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  64%|██████▍   | 301/469 [00:11<00:06, 27.21it/s]
Epoch 1:  82%|████████▏ | 772/938 [00:42<00:09, 18.30it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  65%|██████▍   | 304/469 [00:11<00:06, 25.73it/s]
Epoch 1:  83%|████████▎ | 776/938 [00:42<00:08, 18.33it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  65%|██████▌   | 307/469 [00:11<00:06, 26.10it/s]

Validating:  66%|██████▌   | 310/469 [00:11<00:06, 26.09it/s]
Epoch 1:  83%|████████▎ | 780/938 [00:42<00:08, 18.36it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  67%|██████▋   | 313/469 [00:11<00:06, 25.33it/s]
Epoch 1:  84%|████████▎ | 784/938 [00:42<00:08, 18.38it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  67%|██████▋   | 316/469 [00:11<00:05, 26.25it/s]
Epoch 1:  84%|████████▍ | 788/938 [00:42<00:08, 18.41it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  68%|██████▊   | 319/469 [00:11<00:05, 25.63it/s]

Validating:  69%|██████▊   | 322/469 [00:12<00:05, 25.48it/s]
Epoch 1:  84%|████████▍ | 792/938 [00:42<00:07, 18.44it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  69%|██████▉   | 325/469 [00:12<00:05, 26.35it/s]
Epoch 1:  85%|████████▍ | 796/938 [00:43<00:07, 18.47it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  70%|██████▉   | 328/469 [00:12<00:05, 26.29it/s]
Epoch 1:  85%|████████▌ | 800/938 [00:43<00:07, 18.49it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  71%|███████   | 331/469 [00:12<00:05, 25.09it/s]

Validating:  71%|███████   | 334/469 [00:12<00:05, 24.18it/s]
Epoch 1:  86%|████████▌ | 804/938 [00:43<00:07, 18.51it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  72%|███████▏  | 337/469 [00:12<00:05, 24.46it/s]
Epoch 1:  86%|████████▌ | 808/938 [00:43<00:07, 18.54it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  72%|███████▏  | 340/469 [00:12<00:05, 25.08it/s]
Epoch 1:  87%|████████▋ | 812/938 [00:43<00:06, 18.56it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  73%|███████▎  | 343/469 [00:12<00:04, 26.20it/s]

Validating:  74%|███████▍  | 346/469 [00:13<00:04, 24.92it/s]
Epoch 1:  87%|████████▋ | 816/938 [00:43<00:06, 18.58it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  74%|███████▍  | 349/469 [00:13<00:05, 23.64it/s]
Epoch 1:  87%|████████▋ | 820/938 [00:44<00:06, 18.60it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  75%|███████▌  | 352/469 [00:13<00:04, 24.78it/s]
Epoch 1:  88%|████████▊ | 824/938 [00:44<00:06, 18.63it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  76%|███████▌  | 355/469 [00:13<00:04, 25.43it/s]

Validating:  76%|███████▋  | 358/469 [00:13<00:04, 25.70it/s]
Epoch 1:  88%|████████▊ | 828/938 [00:44<00:05, 18.66it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  77%|███████▋  | 361/469 [00:13<00:04, 25.82it/s]
Epoch 1:  89%|████████▊ | 832/938 [00:44<00:05, 18.69it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  78%|███████▊  | 364/469 [00:13<00:04, 24.93it/s]
Epoch 1:  89%|████████▉ | 836/938 [00:44<00:05, 18.70it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  78%|███████▊  | 368/469 [00:13<00:03, 26.79it/s]
Epoch 1:  90%|████████▉ | 840/938 [00:44<00:05, 18.74it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  79%|███████▉  | 371/469 [00:13<00:03, 26.52it/s]

Validating:  80%|███████▉  | 374/469 [00:14<00:03, 26.81it/s]
Epoch 1:  90%|████████▉ | 844/938 [00:44<00:05, 18.76it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  80%|████████  | 377/469 [00:14<00:03, 27.14it/s]
Epoch 1:  90%|█████████ | 848/938 [00:45<00:04, 18.79it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  81%|████████  | 380/469 [00:14<00:03, 26.87it/s]
Epoch 1:  91%|█████████ | 852/938 [00:45<00:04, 18.82it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  82%|████████▏ | 383/469 [00:14<00:03, 27.22it/s]

Validating:  82%|████████▏ | 386/469 [00:14<00:03, 26.74it/s]
Epoch 1:  91%|█████████▏| 856/938 [00:45<00:04, 18.84it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  83%|████████▎ | 389/469 [00:14<00:02, 27.01it/s]
Epoch 1:  92%|█████████▏| 860/938 [00:45<00:04, 18.87it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  84%|████████▎ | 392/469 [00:14<00:02, 26.71it/s]
Epoch 1:  92%|█████████▏| 864/938 [00:45<00:03, 18.89it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  84%|████████▍ | 395/469 [00:14<00:02, 26.52it/s]

Validating:  85%|████████▍ | 398/469 [00:14<00:02, 26.54it/s]
Epoch 1:  93%|█████████▎| 868/938 [00:45<00:03, 18.92it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  86%|████████▌ | 401/469 [00:15<00:02, 26.22it/s]
Epoch 1:  93%|█████████▎| 872/938 [00:46<00:03, 18.94it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  86%|████████▌ | 404/469 [00:15<00:02, 25.43it/s]
Epoch 1:  93%|█████████▎| 876/938 [00:46<00:03, 18.96it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  87%|████████▋ | 407/469 [00:15<00:02, 24.69it/s]

Validating:  87%|████████▋ | 410/469 [00:15<00:02, 24.93it/s]
Epoch 1:  94%|█████████▍| 880/938 [00:46<00:03, 18.98it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  88%|████████▊ | 413/469 [00:15<00:02, 25.20it/s]
Epoch 1:  94%|█████████▍| 884/938 [00:46<00:02, 19.00it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  89%|████████▊ | 416/469 [00:15<00:02, 25.32it/s]
Epoch 1:  95%|█████████▍| 888/938 [00:46<00:02, 19.01it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  89%|████████▉ | 419/469 [00:15<00:02, 23.82it/s]

Validating:  90%|████████▉ | 422/469 [00:15<00:01, 24.19it/s]
Epoch 1:  95%|█████████▌| 892/938 [00:46<00:02, 19.03it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  91%|█████████ | 425/469 [00:16<00:01, 24.99it/s]
Epoch 1:  96%|█████████▌| 896/938 [00:47<00:02, 19.06it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  91%|█████████▏| 428/469 [00:16<00:01, 25.27it/s]
Epoch 1:  96%|█████████▌| 900/938 [00:47<00:01, 19.08it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  92%|█████████▏| 431/469 [00:16<00:01, 25.23it/s]

Validating:  93%|█████████▎| 434/469 [00:16<00:01, 25.18it/s]
Epoch 1:  96%|█████████▋| 904/938 [00:47<00:01, 19.10it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  93%|█████████▎| 437/469 [00:16<00:01, 25.93it/s]
Epoch 1:  97%|█████████▋| 908/938 [00:47<00:01, 19.12it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  94%|█████████▍| 440/469 [00:16<00:01, 25.52it/s]
Epoch 1:  97%|█████████▋| 912/938 [00:47<00:01, 19.15it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  94%|█████████▍| 443/469 [00:16<00:01, 25.82it/s]

Validating:  95%|█████████▌| 446/469 [00:16<00:00, 26.00it/s]
Epoch 1:  98%|█████████▊| 916/938 [00:47<00:01, 19.17it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  96%|█████████▌| 449/469 [00:17<00:00, 25.14it/s]
Epoch 1:  98%|█████████▊| 920/938 [00:47<00:00, 19.19it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  96%|█████████▋| 452/469 [00:17<00:00, 25.29it/s]
Epoch 1:  99%|█████████▊| 924/938 [00:48<00:00, 19.21it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  97%|█████████▋| 455/469 [00:17<00:00, 25.81it/s]

Validating:  98%|█████████▊| 458/469 [00:17<00:00, 26.04it/s]
Epoch 1:  99%|█████████▉| 928/938 [00:48<00:00, 19.23it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  98%|█████████▊| 461/469 [00:17<00:00, 26.64it/s]
Epoch 1:  99%|█████████▉| 932/938 [00:48<00:00, 19.26it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating:  99%|█████████▉| 464/469 [00:17<00:00, 24.71it/s]
Epoch 1: 100%|█████████▉| 936/938 [00:48<00:00, 19.27it/s, loss=0.666, v_num=13, val_rmse=0.717, train_rmse=1.190]

Validating: 100%|█████████▉| 467/469 [00:17<00:00, 25.03it/s]
Epoch 1: 100%|██████████| 938/938 [00:48<00:00, 19.27it/s, loss=0.666, v_num=13, val_rmse=0.557, train_rmse=1.190]

                                                             
Epoch 1: 100%|██████████| 938/938 [00:48<00:00, 19.26it/s, loss=0.666, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 1:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.666, v_num=13, val_rmse=0.557, train_rmse=0.743]          
Epoch 2:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.666, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   0%|          | 1/938 [00:00<01:10, 13.25it/s, loss=0.664, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   0%|          | 2/938 [00:00<01:11, 13.04it/s, loss=0.663, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   0%|          | 3/938 [00:00<01:09, 13.55it/s, loss=0.668, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   0%|          | 4/938 [00:00<01:04, 14.53it/s, loss=0.668, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   0%|          | 4/938 [00:00<01:04, 14.50it/s, loss=0.665, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   1%|          | 5/938 [00:00<01:03, 14.67it/s, loss=0.665, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   1%|          | 6/938 [00:00<01:01, 15.05it/s, loss=0.66, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:   1%|          | 7/938 [00:00<01:02, 14.82it/s, loss=0.654, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   1%|          | 8/938 [00:00<01:03, 14.71it/s, loss=0.654, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   1%|          | 8/938 [00:00<01:03, 14.69it/s, loss=0.662, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   1%|          | 9/938 [00:00<01:02, 14.92it/s, loss=0.67, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:   1%|          | 10/938 [00:00<01:01, 15.04it/s, loss=0.671, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   1%|          | 11/938 [00:00<01:01, 14.98it/s, loss=0.676, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   1%|▏         | 12/938 [00:00<01:02, 14.79it/s, loss=0.676, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   1%|▏         | 12/938 [00:00<01:02, 14.78it/s, loss=0.68, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:   1%|▏         | 13/938 [00:00<01:01, 14.94it/s, loss=0.689, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   1%|▏         | 14/938 [00:00<01:02, 14.69it/s, loss=0.682, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   2%|▏         | 15/938 [00:01<01:02, 14.81it/s, loss=0.682, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   2%|▏         | 16/938 [00:01<01:01, 14.95it/s, loss=0.682, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   2%|▏         | 16/938 [00:01<01:01, 14.94it/s, loss=0.698, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   2%|▏         | 17/938 [00:01<01:01, 15.06it/s, loss=0.696, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   2%|▏         | 18/938 [00:01<01:03, 14.57it/s, loss=0.696, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   2%|▏         | 19/938 [00:01<01:01, 14.83it/s, loss=0.706, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   2%|▏         | 20/938 [00:01<01:02, 14.76it/s, loss=0.706, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   2%|▏         | 20/938 [00:01<01:02, 14.76it/s, loss=0.701, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   2%|▏         | 21/938 [00:01<01:02, 14.58it/s, loss=0.699, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   2%|▏         | 22/938 [00:01<01:02, 14.62it/s, loss=0.702, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   2%|▏         | 23/938 [00:01<01:02, 14.61it/s, loss=0.695, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   3%|▎         | 24/938 [00:01<01:02, 14.58it/s, loss=0.695, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   3%|▎         | 24/938 [00:01<01:02, 14.58it/s, loss=0.704, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   3%|▎         | 25/938 [00:01<01:02, 14.58it/s, loss=0.717, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   3%|▎         | 26/938 [00:01<01:02, 14.62it/s, loss=0.717, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   3%|▎         | 27/938 [00:01<01:02, 14.61it/s, loss=0.728, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   3%|▎         | 28/938 [00:01<01:02, 14.59it/s, loss=0.728, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   3%|▎         | 28/938 [00:01<01:02, 14.59it/s, loss=0.721, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   3%|▎         | 29/938 [00:01<01:02, 14.58it/s, loss=0.713, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   3%|▎         | 30/938 [00:02<01:02, 14.51it/s, loss=0.714, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   3%|▎         | 31/938 [00:02<01:02, 14.43it/s, loss=0.72, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:   3%|▎         | 32/938 [00:02<01:02, 14.40it/s, loss=0.72, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   3%|▎         | 32/938 [00:02<01:02, 14.39it/s, loss=0.722, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   4%|▎         | 33/938 [00:02<01:03, 14.33it/s, loss=0.722, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   4%|▎         | 34/938 [00:02<01:02, 14.38it/s, loss=0.723, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   4%|▎         | 35/938 [00:02<01:03, 14.30it/s, loss=0.724, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   4%|▍         | 36/938 [00:02<01:02, 14.38it/s, loss=0.724, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   4%|▍         | 36/938 [00:02<01:02, 14.38it/s, loss=0.72, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:   4%|▍         | 37/938 [00:02<01:02, 14.39it/s, loss=0.714, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   4%|▍         | 38/938 [00:02<01:02, 14.45it/s, loss=0.718, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   4%|▍         | 39/938 [00:02<01:02, 14.46it/s, loss=0.71, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:   4%|▍         | 40/938 [00:02<01:02, 14.48it/s, loss=0.71, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   4%|▍         | 40/938 [00:02<01:02, 14.48it/s, loss=0.718, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   4%|▍         | 41/938 [00:02<01:01, 14.53it/s, loss=0.722, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   4%|▍         | 42/938 [00:02<01:01, 14.53it/s, loss=0.717, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   5%|▍         | 43/938 [00:02<01:01, 14.56it/s, loss=0.725, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   5%|▍         | 44/938 [00:03<01:01, 14.55it/s, loss=0.725, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   5%|▍         | 44/938 [00:03<01:01, 14.55it/s, loss=0.718, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   5%|▍         | 45/938 [00:03<01:01, 14.54it/s, loss=0.718, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   5%|▍         | 46/938 [00:03<01:01, 14.51it/s, loss=0.721, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   5%|▌         | 47/938 [00:03<01:01, 14.49it/s, loss=0.719, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   5%|▌         | 48/938 [00:03<01:01, 14.54it/s, loss=0.719, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   5%|▌         | 48/938 [00:03<01:01, 14.53it/s, loss=0.726, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   5%|▌         | 49/938 [00:03<01:01, 14.52it/s, loss=0.725, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   5%|▌         | 50/938 [00:03<01:01, 14.51it/s, loss=0.718, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   5%|▌         | 51/938 [00:03<01:00, 14.56it/s, loss=0.703, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   6%|▌         | 52/938 [00:03<01:01, 14.50it/s, loss=0.703, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   6%|▌         | 52/938 [00:03<01:01, 14.49it/s, loss=0.707, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   6%|▌         | 53/938 [00:03<01:00, 14.53it/s, loss=0.705, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   6%|▌         | 54/938 [00:03<01:00, 14.56it/s, loss=0.704, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   6%|▌         | 55/938 [00:03<01:00, 14.59it/s, loss=0.702, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   6%|▌         | 56/938 [00:03<01:00, 14.57it/s, loss=0.702, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   6%|▌         | 56/938 [00:03<01:00, 14.57it/s, loss=0.694, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   6%|▌         | 57/938 [00:03<01:00, 14.59it/s, loss=0.7, v_num=13, val_rmse=0.557, train_rmse=0.743]  
Epoch 2:   6%|▌         | 58/938 [00:03<01:00, 14.56it/s, loss=0.701, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   6%|▋         | 59/938 [00:04<01:00, 14.59it/s, loss=0.701, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   6%|▋         | 60/938 [00:04<01:00, 14.56it/s, loss=0.701, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   6%|▋         | 60/938 [00:04<01:00, 14.56it/s, loss=0.69, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:   7%|▋         | 61/938 [00:04<01:00, 14.59it/s, loss=0.691, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   7%|▋         | 62/938 [00:04<01:00, 14.59it/s, loss=0.69, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:   7%|▋         | 63/938 [00:04<00:59, 14.65it/s, loss=0.686, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   7%|▋         | 64/938 [00:04<00:59, 14.66it/s, loss=0.686, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   7%|▋         | 64/938 [00:04<00:59, 14.66it/s, loss=0.691, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   7%|▋         | 65/938 [00:04<00:59, 14.69it/s, loss=0.686, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   7%|▋         | 66/938 [00:04<00:59, 14.67it/s, loss=0.686, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   7%|▋         | 67/938 [00:04<00:59, 14.62it/s, loss=0.686, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   7%|▋         | 68/938 [00:04<00:59, 14.65it/s, loss=0.686, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   7%|▋         | 68/938 [00:04<00:59, 14.65it/s, loss=0.68, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:   7%|▋         | 69/938 [00:04<00:59, 14.67it/s, loss=0.68, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   7%|▋         | 70/938 [00:04<00:59, 14.66it/s, loss=0.684, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   8%|▊         | 71/938 [00:04<00:59, 14.57it/s, loss=0.691, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   8%|▊         | 72/938 [00:04<00:59, 14.57it/s, loss=0.691, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   8%|▊         | 72/938 [00:04<00:59, 14.57it/s, loss=0.686, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   8%|▊         | 73/938 [00:05<00:59, 14.59it/s, loss=0.687, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   8%|▊         | 74/938 [00:05<00:59, 14.57it/s, loss=0.694, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   8%|▊         | 75/938 [00:05<00:59, 14.52it/s, loss=0.702, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   8%|▊         | 76/938 [00:05<00:59, 14.52it/s, loss=0.702, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   8%|▊         | 76/938 [00:05<00:59, 14.52it/s, loss=0.7, v_num=13, val_rmse=0.557, train_rmse=0.743]  
Epoch 2:   8%|▊         | 77/938 [00:05<00:59, 14.54it/s, loss=0.695, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   8%|▊         | 78/938 [00:05<00:59, 14.56it/s, loss=0.687, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   8%|▊         | 79/938 [00:05<00:59, 14.53it/s, loss=0.693, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   9%|▊         | 80/938 [00:05<00:58, 14.58it/s, loss=0.693, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   9%|▊         | 80/938 [00:05<00:58, 14.58it/s, loss=0.695, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   9%|▊         | 81/938 [00:05<00:58, 14.57it/s, loss=0.689, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   9%|▊         | 82/938 [00:05<00:58, 14.56it/s, loss=0.695, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   9%|▉         | 83/938 [00:05<00:58, 14.59it/s, loss=0.702, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   9%|▉         | 84/938 [00:05<00:58, 14.58it/s, loss=0.702, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   9%|▉         | 84/938 [00:05<00:58, 14.58it/s, loss=0.698, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   9%|▉         | 85/938 [00:05<00:58, 14.57it/s, loss=0.698, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   9%|▉         | 86/938 [00:05<00:58, 14.57it/s, loss=0.702, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   9%|▉         | 87/938 [00:05<00:58, 14.59it/s, loss=0.697, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   9%|▉         | 88/938 [00:06<00:58, 14.52it/s, loss=0.697, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:   9%|▉         | 88/938 [00:06<00:58, 14.52it/s, loss=0.69, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:   9%|▉         | 89/938 [00:06<00:58, 14.48it/s, loss=0.699, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  10%|▉         | 90/938 [00:06<00:58, 14.50it/s, loss=0.702, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  10%|▉         | 91/938 [00:06<00:58, 14.47it/s, loss=0.693, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  10%|▉         | 92/938 [00:06<00:58, 14.47it/s, loss=0.693, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  10%|▉         | 92/938 [00:06<00:58, 14.47it/s, loss=0.689, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  10%|▉         | 93/938 [00:06<00:58, 14.46it/s, loss=0.689, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  10%|█         | 94/938 [00:06<00:58, 14.47it/s, loss=0.691, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  10%|█         | 95/938 [00:06<00:58, 14.44it/s, loss=0.682, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  10%|█         | 96/938 [00:06<00:58, 14.43it/s, loss=0.682, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  10%|█         | 96/938 [00:06<00:58, 14.43it/s, loss=0.679, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  10%|█         | 97/938 [00:06<00:58, 14.46it/s, loss=0.686, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  10%|█         | 98/938 [00:06<00:58, 14.46it/s, loss=0.69, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  11%|█         | 99/938 [00:06<00:58, 14.45it/s, loss=0.688, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  11%|█         | 100/938 [00:06<00:57, 14.48it/s, loss=0.688, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  11%|█         | 100/938 [00:06<00:57, 14.48it/s, loss=0.689, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  11%|█         | 101/938 [00:06<00:57, 14.49it/s, loss=0.697, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  11%|█         | 102/938 [00:07<00:57, 14.49it/s, loss=0.704, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  11%|█         | 103/938 [00:07<00:57, 14.49it/s, loss=0.7, v_num=13, val_rmse=0.557, train_rmse=0.743]  
Epoch 2:  11%|█         | 104/938 [00:07<00:57, 14.51it/s, loss=0.7, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  11%|█         | 104/938 [00:07<00:57, 14.51it/s, loss=0.703, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  11%|█         | 105/938 [00:07<00:57, 14.49it/s, loss=0.696, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  11%|█▏        | 106/938 [00:07<00:57, 14.50it/s, loss=0.693, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  11%|█▏        | 107/938 [00:07<00:57, 14.51it/s, loss=0.696, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  12%|█▏        | 108/938 [00:07<00:57, 14.50it/s, loss=0.696, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  12%|█▏        | 108/938 [00:07<00:57, 14.50it/s, loss=0.702, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  12%|█▏        | 109/938 [00:07<00:57, 14.51it/s, loss=0.698, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  12%|█▏        | 110/938 [00:07<00:57, 14.48it/s, loss=0.694, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  12%|█▏        | 111/938 [00:07<00:57, 14.49it/s, loss=0.695, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  12%|█▏        | 112/938 [00:07<00:56, 14.51it/s, loss=0.695, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  12%|█▏        | 112/938 [00:07<00:56, 14.51it/s, loss=0.699, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  12%|█▏        | 113/938 [00:07<00:56, 14.51it/s, loss=0.694, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  12%|█▏        | 114/938 [00:07<00:56, 14.49it/s, loss=0.693, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  12%|█▏        | 115/938 [00:07<00:56, 14.51it/s, loss=0.693, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  12%|█▏        | 116/938 [00:08<00:56, 14.50it/s, loss=0.693, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  12%|█▏        | 116/938 [00:08<00:56, 14.50it/s, loss=0.7, v_num=13, val_rmse=0.557, train_rmse=0.743]  
Epoch 2:  12%|█▏        | 117/938 [00:08<00:56, 14.47it/s, loss=0.696, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  13%|█▎        | 118/938 [00:08<00:56, 14.48it/s, loss=0.693, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  13%|█▎        | 119/938 [00:08<00:56, 14.48it/s, loss=0.69, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  13%|█▎        | 120/938 [00:08<00:56, 14.47it/s, loss=0.69, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  13%|█▎        | 120/938 [00:08<00:56, 14.47it/s, loss=0.682, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  13%|█▎        | 121/938 [00:08<00:56, 14.47it/s, loss=0.684, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  13%|█▎        | 122/938 [00:08<00:56, 14.46it/s, loss=0.678, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  13%|█▎        | 123/938 [00:08<00:56, 14.46it/s, loss=0.676, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  13%|█▎        | 124/938 [00:08<00:56, 14.46it/s, loss=0.676, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  13%|█▎        | 124/938 [00:08<00:56, 14.46it/s, loss=0.677, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  13%|█▎        | 125/938 [00:08<00:56, 14.47it/s, loss=0.678, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  13%|█▎        | 126/938 [00:08<00:56, 14.47it/s, loss=0.677, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  14%|█▎        | 127/938 [00:08<00:55, 14.50it/s, loss=0.676, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  14%|█▎        | 128/938 [00:08<00:55, 14.49it/s, loss=0.676, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  14%|█▎        | 128/938 [00:08<00:55, 14.49it/s, loss=0.677, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  14%|█▍        | 129/938 [00:08<00:55, 14.49it/s, loss=0.677, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  14%|█▍        | 130/938 [00:08<00:55, 14.49it/s, loss=0.679, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  14%|█▍        | 131/938 [00:09<00:55, 14.51it/s, loss=0.682, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  14%|█▍        | 132/938 [00:09<00:55, 14.52it/s, loss=0.682, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  14%|█▍        | 132/938 [00:09<00:55, 14.51it/s, loss=0.688, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  14%|█▍        | 133/938 [00:09<00:55, 14.51it/s, loss=0.695, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  14%|█▍        | 134/938 [00:09<00:55, 14.49it/s, loss=0.693, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  14%|█▍        | 135/938 [00:09<00:55, 14.48it/s, loss=0.692, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  14%|█▍        | 136/938 [00:09<00:55, 14.49it/s, loss=0.692, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  14%|█▍        | 136/938 [00:09<00:55, 14.49it/s, loss=0.689, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  15%|█▍        | 137/938 [00:09<00:55, 14.49it/s, loss=0.685, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  15%|█▍        | 138/938 [00:09<00:55, 14.48it/s, loss=0.684, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  15%|█▍        | 139/938 [00:09<00:55, 14.49it/s, loss=0.682, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  15%|█▍        | 140/938 [00:09<00:55, 14.50it/s, loss=0.682, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  15%|█▍        | 140/938 [00:09<00:55, 14.49it/s, loss=0.692, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  15%|█▌        | 141/938 [00:09<00:54, 14.51it/s, loss=0.687, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  15%|█▌        | 142/938 [00:09<00:54, 14.53it/s, loss=0.69, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  15%|█▌        | 143/938 [00:09<00:54, 14.51it/s, loss=0.688, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  15%|█▌        | 144/938 [00:09<00:54, 14.51it/s, loss=0.688, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  15%|█▌        | 144/938 [00:09<00:54, 14.51it/s, loss=0.687, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  15%|█▌        | 145/938 [00:09<00:54, 14.53it/s, loss=0.685, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  16%|█▌        | 146/938 [00:10<00:54, 14.52it/s, loss=0.688, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  16%|█▌        | 147/938 [00:10<00:54, 14.51it/s, loss=0.689, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  16%|█▌        | 148/938 [00:10<00:54, 14.51it/s, loss=0.689, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  16%|█▌        | 148/938 [00:10<00:54, 14.51it/s, loss=0.691, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  16%|█▌        | 149/938 [00:10<00:54, 14.52it/s, loss=0.687, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  16%|█▌        | 150/938 [00:10<00:54, 14.54it/s, loss=0.684, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  16%|█▌        | 151/938 [00:10<00:54, 14.55it/s, loss=0.683, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  16%|█▌        | 152/938 [00:10<00:53, 14.56it/s, loss=0.683, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  16%|█▌        | 152/938 [00:10<00:53, 14.56it/s, loss=0.676, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  16%|█▋        | 153/938 [00:10<00:53, 14.54it/s, loss=0.672, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  16%|█▋        | 154/938 [00:10<00:53, 14.56it/s, loss=0.667, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  17%|█▋        | 155/938 [00:10<00:53, 14.56it/s, loss=0.676, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  17%|█▋        | 156/938 [00:10<00:53, 14.55it/s, loss=0.676, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  17%|█▋        | 156/938 [00:10<00:53, 14.55it/s, loss=0.677, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  17%|█▋        | 157/938 [00:10<00:53, 14.56it/s, loss=0.678, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  17%|█▋        | 158/938 [00:10<00:53, 14.54it/s, loss=0.685, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  17%|█▋        | 159/938 [00:10<00:53, 14.56it/s, loss=0.684, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  17%|█▋        | 160/938 [00:10<00:53, 14.57it/s, loss=0.684, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  17%|█▋        | 160/938 [00:10<00:53, 14.56it/s, loss=0.679, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  17%|█▋        | 161/938 [00:11<00:53, 14.56it/s, loss=0.681, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  17%|█▋        | 162/938 [00:11<00:53, 14.57it/s, loss=0.676, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  17%|█▋        | 163/938 [00:11<00:53, 14.57it/s, loss=0.679, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  17%|█▋        | 164/938 [00:11<00:53, 14.57it/s, loss=0.679, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  17%|█▋        | 164/938 [00:11<00:53, 14.57it/s, loss=0.673, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  18%|█▊        | 165/938 [00:11<00:53, 14.56it/s, loss=0.682, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  18%|█▊        | 166/938 [00:11<00:53, 14.56it/s, loss=0.679, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  18%|█▊        | 167/938 [00:11<00:52, 14.57it/s, loss=0.678, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  18%|█▊        | 168/938 [00:11<00:52, 14.57it/s, loss=0.678, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  18%|█▊        | 168/938 [00:11<00:52, 14.57it/s, loss=0.685, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  18%|█▊        | 169/938 [00:11<00:52, 14.58it/s, loss=0.696, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  18%|█▊        | 170/938 [00:11<00:52, 14.50it/s, loss=0.704, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  18%|█▊        | 171/938 [00:11<00:52, 14.50it/s, loss=0.711, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  18%|█▊        | 172/938 [00:11<00:52, 14.50it/s, loss=0.711, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  18%|█▊        | 172/938 [00:11<00:52, 14.50it/s, loss=0.709, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  18%|█▊        | 173/938 [00:11<00:52, 14.50it/s, loss=0.71, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  19%|█▊        | 174/938 [00:11<00:52, 14.51it/s, loss=0.713, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  19%|█▊        | 175/938 [00:12<00:52, 14.50it/s, loss=0.705, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  19%|█▉        | 176/938 [00:12<00:52, 14.50it/s, loss=0.705, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  19%|█▉        | 176/938 [00:12<00:52, 14.50it/s, loss=0.706, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  19%|█▉        | 177/938 [00:12<00:52, 14.51it/s, loss=0.709, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  19%|█▉        | 178/938 [00:12<00:52, 14.50it/s, loss=0.704, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  19%|█▉        | 179/938 [00:12<00:52, 14.52it/s, loss=0.703, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  19%|█▉        | 180/938 [00:12<00:52, 14.51it/s, loss=0.703, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  19%|█▉        | 180/938 [00:12<00:52, 14.51it/s, loss=0.711, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  19%|█▉        | 181/938 [00:12<00:52, 14.52it/s, loss=0.703, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  19%|█▉        | 182/938 [00:12<00:52, 14.53it/s, loss=0.698, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  20%|█▉        | 183/938 [00:12<00:51, 14.54it/s, loss=0.694, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  20%|█▉        | 184/938 [00:12<00:51, 14.55it/s, loss=0.694, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  20%|█▉        | 184/938 [00:12<00:51, 14.55it/s, loss=0.699, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  20%|█▉        | 185/938 [00:12<00:51, 14.57it/s, loss=0.693, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  20%|█▉        | 186/938 [00:12<00:51, 14.56it/s, loss=0.695, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  20%|█▉        | 187/938 [00:12<00:51, 14.57it/s, loss=0.7, v_num=13, val_rmse=0.557, train_rmse=0.743]  
Epoch 2:  20%|██        | 188/938 [00:12<00:51, 14.56it/s, loss=0.7, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  20%|██        | 188/938 [00:12<00:51, 14.56it/s, loss=0.686, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  20%|██        | 189/938 [00:12<00:51, 14.55it/s, loss=0.678, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  20%|██        | 190/938 [00:13<00:51, 14.56it/s, loss=0.674, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  20%|██        | 191/938 [00:13<00:51, 14.57it/s, loss=0.67, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  20%|██        | 192/938 [00:13<00:51, 14.57it/s, loss=0.67, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  20%|██        | 192/938 [00:13<00:51, 14.57it/s, loss=0.676, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  21%|██        | 193/938 [00:13<00:51, 14.57it/s, loss=0.683, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  21%|██        | 194/938 [00:13<00:51, 14.58it/s, loss=0.685, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  21%|██        | 195/938 [00:13<00:51, 14.56it/s, loss=0.687, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  21%|██        | 196/938 [00:13<00:50, 14.56it/s, loss=0.687, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  21%|██        | 196/938 [00:13<00:50, 14.56it/s, loss=0.681, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  21%|██        | 197/938 [00:13<00:50, 14.55it/s, loss=0.687, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  21%|██        | 198/938 [00:13<00:50, 14.55it/s, loss=0.689, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  21%|██        | 199/938 [00:13<00:50, 14.56it/s, loss=0.697, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  21%|██▏       | 200/938 [00:13<00:50, 14.55it/s, loss=0.697, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  21%|██▏       | 200/938 [00:13<00:50, 14.55it/s, loss=0.701, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  21%|██▏       | 201/938 [00:13<00:50, 14.56it/s, loss=0.708, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  22%|██▏       | 202/938 [00:13<00:50, 14.55it/s, loss=0.708, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  22%|██▏       | 203/938 [00:13<00:50, 14.55it/s, loss=0.709, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  22%|██▏       | 204/938 [00:14<00:50, 14.55it/s, loss=0.709, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  22%|██▏       | 204/938 [00:14<00:50, 14.55it/s, loss=0.705, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  22%|██▏       | 205/938 [00:14<00:50, 14.54it/s, loss=0.703, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  22%|██▏       | 206/938 [00:14<00:50, 14.55it/s, loss=0.696, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  22%|██▏       | 207/938 [00:14<00:50, 14.55it/s, loss=0.688, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  22%|██▏       | 208/938 [00:14<00:50, 14.56it/s, loss=0.688, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  22%|██▏       | 208/938 [00:14<00:50, 14.56it/s, loss=0.696, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  22%|██▏       | 209/938 [00:14<00:50, 14.56it/s, loss=0.693, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  22%|██▏       | 210/938 [00:14<00:49, 14.57it/s, loss=0.685, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  22%|██▏       | 211/938 [00:14<00:49, 14.56it/s, loss=0.682, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  23%|██▎       | 212/938 [00:14<00:49, 14.56it/s, loss=0.682, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  23%|██▎       | 212/938 [00:14<00:49, 14.56it/s, loss=0.676, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  23%|██▎       | 213/938 [00:14<00:49, 14.57it/s, loss=0.667, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  23%|██▎       | 214/938 [00:14<00:49, 14.57it/s, loss=0.664, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  23%|██▎       | 215/938 [00:14<00:49, 14.56it/s, loss=0.661, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  23%|██▎       | 216/938 [00:14<00:49, 14.58it/s, loss=0.661, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  23%|██▎       | 216/938 [00:14<00:49, 14.58it/s, loss=0.664, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  23%|██▎       | 217/938 [00:14<00:49, 14.58it/s, loss=0.655, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  23%|██▎       | 218/938 [00:14<00:49, 14.59it/s, loss=0.65, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  23%|██▎       | 219/938 [00:15<00:49, 14.58it/s, loss=0.641, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  23%|██▎       | 220/938 [00:15<00:49, 14.58it/s, loss=0.641, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  23%|██▎       | 220/938 [00:15<00:49, 14.58it/s, loss=0.641, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  24%|██▎       | 221/938 [00:15<00:49, 14.58it/s, loss=0.646, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  24%|██▎       | 222/938 [00:15<00:49, 14.58it/s, loss=0.649, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  24%|██▍       | 223/938 [00:15<00:49, 14.59it/s, loss=0.659, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  24%|██▍       | 224/938 [00:15<00:48, 14.59it/s, loss=0.659, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  24%|██▍       | 224/938 [00:15<00:48, 14.59it/s, loss=0.663, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  24%|██▍       | 225/938 [00:15<00:48, 14.58it/s, loss=0.665, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  24%|██▍       | 226/938 [00:15<00:48, 14.58it/s, loss=0.675, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  24%|██▍       | 227/938 [00:15<00:48, 14.58it/s, loss=0.681, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  24%|██▍       | 228/938 [00:15<00:48, 14.59it/s, loss=0.681, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  24%|██▍       | 228/938 [00:15<00:48, 14.59it/s, loss=0.686, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  24%|██▍       | 229/938 [00:15<00:48, 14.59it/s, loss=0.695, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  25%|██▍       | 230/938 [00:15<00:48, 14.59it/s, loss=0.699, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  25%|██▍       | 231/938 [00:15<00:48, 14.59it/s, loss=0.695, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  25%|██▍       | 232/938 [00:15<00:48, 14.59it/s, loss=0.695, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  25%|██▍       | 232/938 [00:15<00:48, 14.59it/s, loss=0.698, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  25%|██▍       | 233/938 [00:15<00:48, 14.58it/s, loss=0.708, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  25%|██▍       | 234/938 [00:16<00:48, 14.58it/s, loss=0.708, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  25%|██▌       | 235/938 [00:16<00:48, 14.58it/s, loss=0.711, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  25%|██▌       | 236/938 [00:16<00:48, 14.55it/s, loss=0.711, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  25%|██▌       | 236/938 [00:16<00:48, 14.55it/s, loss=0.716, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  25%|██▌       | 237/938 [00:16<00:48, 14.55it/s, loss=0.72, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  25%|██▌       | 238/938 [00:16<00:48, 14.55it/s, loss=0.72, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  25%|██▌       | 239/938 [00:16<00:48, 14.55it/s, loss=0.728, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  26%|██▌       | 240/938 [00:16<00:47, 14.55it/s, loss=0.728, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  26%|██▌       | 240/938 [00:16<00:47, 14.55it/s, loss=0.722, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  26%|██▌       | 241/938 [00:16<00:47, 14.55it/s, loss=0.718, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  26%|██▌       | 242/938 [00:16<00:47, 14.55it/s, loss=0.72, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  26%|██▌       | 243/938 [00:16<00:47, 14.55it/s, loss=0.719, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  26%|██▌       | 244/938 [00:16<00:47, 14.56it/s, loss=0.719, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  26%|██▌       | 244/938 [00:16<00:47, 14.56it/s, loss=0.717, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  26%|██▌       | 245/938 [00:16<00:47, 14.57it/s, loss=0.714, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  26%|██▌       | 246/938 [00:16<00:47, 14.54it/s, loss=0.705, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  26%|██▋       | 247/938 [00:16<00:47, 14.55it/s, loss=0.704, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  26%|██▋       | 248/938 [00:17<00:47, 14.56it/s, loss=0.704, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  26%|██▋       | 248/938 [00:17<00:47, 14.56it/s, loss=0.702, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  27%|██▋       | 249/938 [00:17<00:47, 14.56it/s, loss=0.697, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  27%|██▋       | 250/938 [00:17<00:47, 14.53it/s, loss=0.696, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  27%|██▋       | 251/938 [00:17<00:47, 14.55it/s, loss=0.699, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  27%|██▋       | 252/938 [00:17<00:47, 14.55it/s, loss=0.699, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  27%|██▋       | 252/938 [00:17<00:47, 14.55it/s, loss=0.695, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  27%|██▋       | 253/938 [00:17<00:47, 14.54it/s, loss=0.686, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  27%|██▋       | 254/938 [00:17<00:46, 14.56it/s, loss=0.676, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  27%|██▋       | 255/938 [00:17<00:46, 14.55it/s, loss=0.669, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  27%|██▋       | 256/938 [00:17<00:46, 14.55it/s, loss=0.669, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  27%|██▋       | 256/938 [00:17<00:46, 14.55it/s, loss=0.669, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  27%|██▋       | 257/938 [00:17<00:46, 14.56it/s, loss=0.66, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  28%|██▊       | 258/938 [00:17<00:46, 14.56it/s, loss=0.662, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  28%|██▊       | 259/938 [00:17<00:46, 14.55it/s, loss=0.66, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  28%|██▊       | 260/938 [00:17<00:46, 14.56it/s, loss=0.66, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  28%|██▊       | 260/938 [00:17<00:46, 14.56it/s, loss=0.654, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  28%|██▊       | 261/938 [00:17<00:46, 14.56it/s, loss=0.653, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  28%|██▊       | 262/938 [00:17<00:46, 14.56it/s, loss=0.647, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  28%|██▊       | 263/938 [00:18<00:46, 14.57it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  28%|██▊       | 264/938 [00:18<00:46, 14.57it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  28%|██▊       | 264/938 [00:18<00:46, 14.57it/s, loss=0.641, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  28%|██▊       | 265/938 [00:18<00:46, 14.56it/s, loss=0.641, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  28%|██▊       | 266/938 [00:18<00:46, 14.57it/s, loss=0.646, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  28%|██▊       | 267/938 [00:18<00:46, 14.55it/s, loss=0.64, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  29%|██▊       | 268/938 [00:18<00:46, 14.55it/s, loss=0.64, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  29%|██▊       | 268/938 [00:18<00:46, 14.55it/s, loss=0.64, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  29%|██▊       | 269/938 [00:18<00:45, 14.55it/s, loss=0.634, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  29%|██▉       | 270/938 [00:18<00:45, 14.56it/s, loss=0.635, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  29%|██▉       | 271/938 [00:18<00:45, 14.56it/s, loss=0.634, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  29%|██▉       | 272/938 [00:18<00:45, 14.56it/s, loss=0.634, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  29%|██▉       | 272/938 [00:18<00:45, 14.56it/s, loss=0.628, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  29%|██▉       | 273/938 [00:18<00:45, 14.56it/s, loss=0.629, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  29%|██▉       | 274/938 [00:18<00:45, 14.56it/s, loss=0.64, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  29%|██▉       | 275/938 [00:18<00:45, 14.55it/s, loss=0.65, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  29%|██▉       | 276/938 [00:18<00:45, 14.55it/s, loss=0.65, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  29%|██▉       | 276/938 [00:18<00:45, 14.55it/s, loss=0.647, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  30%|██▉       | 277/938 [00:19<00:45, 14.55it/s, loss=0.665, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  30%|██▉       | 278/938 [00:19<00:45, 14.55it/s, loss=0.664, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  30%|██▉       | 279/938 [00:19<00:45, 14.56it/s, loss=0.664, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  30%|██▉       | 280/938 [00:19<00:45, 14.56it/s, loss=0.664, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  30%|██▉       | 280/938 [00:19<00:45, 14.56it/s, loss=0.671, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  30%|██▉       | 281/938 [00:19<00:45, 14.56it/s, loss=0.663, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  30%|███       | 282/938 [00:19<00:45, 14.56it/s, loss=0.663, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  30%|███       | 283/938 [00:19<00:44, 14.56it/s, loss=0.666, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  30%|███       | 284/938 [00:19<00:44, 14.56it/s, loss=0.666, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  30%|███       | 284/938 [00:19<00:44, 14.56it/s, loss=0.666, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  30%|███       | 285/938 [00:19<00:44, 14.56it/s, loss=0.666, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  30%|███       | 286/938 [00:19<00:44, 14.56it/s, loss=0.678, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  31%|███       | 287/938 [00:19<00:44, 14.56it/s, loss=0.678, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  31%|███       | 288/938 [00:19<00:44, 14.57it/s, loss=0.678, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  31%|███       | 288/938 [00:19<00:44, 14.57it/s, loss=0.664, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  31%|███       | 289/938 [00:19<00:44, 14.58it/s, loss=0.668, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  31%|███       | 290/938 [00:19<00:44, 14.57it/s, loss=0.672, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  31%|███       | 291/938 [00:19<00:44, 14.57it/s, loss=0.675, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  31%|███       | 292/938 [00:20<00:44, 14.58it/s, loss=0.675, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  31%|███       | 292/938 [00:20<00:44, 14.57it/s, loss=0.693, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  31%|███       | 293/938 [00:20<00:44, 14.58it/s, loss=0.692, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  31%|███▏      | 294/938 [00:20<00:44, 14.56it/s, loss=0.69, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  31%|███▏      | 295/938 [00:20<00:44, 14.57it/s, loss=0.676, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  32%|███▏      | 296/938 [00:20<00:44, 14.57it/s, loss=0.676, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  32%|███▏      | 296/938 [00:20<00:44, 14.56it/s, loss=0.675, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  32%|███▏      | 297/938 [00:20<00:44, 14.57it/s, loss=0.661, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  32%|███▏      | 298/938 [00:20<00:43, 14.57it/s, loss=0.667, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  32%|███▏      | 299/938 [00:20<00:43, 14.56it/s, loss=0.667, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  32%|███▏      | 300/938 [00:20<00:43, 14.55it/s, loss=0.667, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  32%|███▏      | 300/938 [00:20<00:43, 14.55it/s, loss=0.663, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  32%|███▏      | 301/938 [00:20<00:43, 14.56it/s, loss=0.671, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  32%|███▏      | 302/938 [00:20<00:43, 14.56it/s, loss=0.668, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  32%|███▏      | 303/938 [00:20<00:43, 14.55it/s, loss=0.668, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  32%|███▏      | 304/938 [00:20<00:43, 14.57it/s, loss=0.668, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  32%|███▏      | 304/938 [00:20<00:43, 14.57it/s, loss=0.673, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  33%|███▎      | 305/938 [00:20<00:43, 14.57it/s, loss=0.688, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  33%|███▎      | 306/938 [00:21<00:43, 14.57it/s, loss=0.673, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  33%|███▎      | 307/938 [00:21<00:43, 14.57it/s, loss=0.676, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  33%|███▎      | 308/938 [00:21<00:43, 14.57it/s, loss=0.676, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  33%|███▎      | 308/938 [00:21<00:43, 14.57it/s, loss=0.687, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  33%|███▎      | 309/938 [00:21<00:43, 14.57it/s, loss=0.685, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  33%|███▎      | 310/938 [00:21<00:43, 14.56it/s, loss=0.691, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  33%|███▎      | 311/938 [00:21<00:43, 14.55it/s, loss=0.698, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  33%|███▎      | 312/938 [00:21<00:43, 14.55it/s, loss=0.698, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  33%|███▎      | 312/938 [00:21<00:43, 14.55it/s, loss=0.69, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  33%|███▎      | 313/938 [00:21<00:42, 14.56it/s, loss=0.695, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  33%|███▎      | 314/938 [00:21<00:42, 14.56it/s, loss=0.688, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  34%|███▎      | 315/938 [00:21<00:42, 14.56it/s, loss=0.695, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  34%|███▎      | 316/938 [00:21<00:42, 14.56it/s, loss=0.695, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  34%|███▎      | 316/938 [00:21<00:42, 14.56it/s, loss=0.699, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  34%|███▍      | 317/938 [00:21<00:42, 14.57it/s, loss=0.699, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  34%|███▍      | 318/938 [00:21<00:42, 14.57it/s, loss=0.701, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  34%|███▍      | 319/938 [00:21<00:42, 14.55it/s, loss=0.701, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  34%|███▍      | 320/938 [00:21<00:42, 14.56it/s, loss=0.701, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  34%|███▍      | 320/938 [00:21<00:42, 14.56it/s, loss=0.698, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  34%|███▍      | 321/938 [00:22<00:42, 14.56it/s, loss=0.705, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  34%|███▍      | 322/938 [00:22<00:42, 14.56it/s, loss=0.708, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  34%|███▍      | 323/938 [00:22<00:42, 14.56it/s, loss=0.707, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  35%|███▍      | 324/938 [00:22<00:42, 14.57it/s, loss=0.707, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  35%|███▍      | 324/938 [00:22<00:42, 14.57it/s, loss=0.707, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  35%|███▍      | 325/938 [00:22<00:42, 14.56it/s, loss=0.7, v_num=13, val_rmse=0.557, train_rmse=0.743]  
Epoch 2:  35%|███▍      | 326/938 [00:22<00:42, 14.56it/s, loss=0.705, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  35%|███▍      | 327/938 [00:22<00:41, 14.57it/s, loss=0.704, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  35%|███▍      | 328/938 [00:22<00:41, 14.57it/s, loss=0.704, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  35%|███▍      | 328/938 [00:22<00:41, 14.57it/s, loss=0.703, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  35%|███▌      | 329/938 [00:22<00:41, 14.57it/s, loss=0.701, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  35%|███▌      | 330/938 [00:22<00:41, 14.58it/s, loss=0.704, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  35%|███▌      | 331/938 [00:22<00:41, 14.57it/s, loss=0.698, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  35%|███▌      | 332/938 [00:22<00:41, 14.58it/s, loss=0.698, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  35%|███▌      | 332/938 [00:22<00:41, 14.57it/s, loss=0.704, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  36%|███▌      | 333/938 [00:22<00:41, 14.58it/s, loss=0.695, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  36%|███▌      | 334/938 [00:22<00:41, 14.58it/s, loss=0.698, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  36%|███▌      | 335/938 [00:23<00:41, 14.57it/s, loss=0.71, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  36%|███▌      | 336/938 [00:23<00:41, 14.57it/s, loss=0.71, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  36%|███▌      | 336/938 [00:23<00:41, 14.57it/s, loss=0.707, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  36%|███▌      | 337/938 [00:23<00:41, 14.56it/s, loss=0.709, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  36%|███▌      | 338/938 [00:23<00:41, 14.56it/s, loss=0.7, v_num=13, val_rmse=0.557, train_rmse=0.743]  
Epoch 2:  36%|███▌      | 339/938 [00:23<00:41, 14.56it/s, loss=0.694, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  36%|███▌      | 340/938 [00:23<00:41, 14.57it/s, loss=0.694, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  36%|███▌      | 340/938 [00:23<00:41, 14.57it/s, loss=0.697, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  36%|███▋      | 341/938 [00:23<00:40, 14.57it/s, loss=0.686, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  36%|███▋      | 342/938 [00:23<00:40, 14.58it/s, loss=0.682, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  37%|███▋      | 343/938 [00:23<00:40, 14.57it/s, loss=0.684, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  37%|███▋      | 344/938 [00:23<00:40, 14.56it/s, loss=0.684, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  37%|███▋      | 344/938 [00:23<00:40, 14.56it/s, loss=0.68, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  37%|███▋      | 345/938 [00:23<00:40, 14.55it/s, loss=0.675, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  37%|███▋      | 346/938 [00:23<00:40, 14.55it/s, loss=0.671, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  37%|███▋      | 347/938 [00:23<00:40, 14.55it/s, loss=0.675, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  37%|███▋      | 348/938 [00:23<00:40, 14.56it/s, loss=0.675, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  37%|███▋      | 348/938 [00:23<00:40, 14.56it/s, loss=0.673, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  37%|███▋      | 349/938 [00:23<00:40, 14.54it/s, loss=0.674, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  37%|███▋      | 350/938 [00:24<00:40, 14.55it/s, loss=0.665, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  37%|███▋      | 351/938 [00:24<00:40, 14.55it/s, loss=0.664, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  38%|███▊      | 352/938 [00:24<00:40, 14.56it/s, loss=0.664, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  38%|███▊      | 352/938 [00:24<00:40, 14.56it/s, loss=0.658, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  38%|███▊      | 353/938 [00:24<00:40, 14.56it/s, loss=0.657, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  38%|███▊      | 354/938 [00:24<00:40, 14.57it/s, loss=0.658, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  38%|███▊      | 355/938 [00:24<00:40, 14.57it/s, loss=0.648, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  38%|███▊      | 356/938 [00:24<00:39, 14.57it/s, loss=0.648, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  38%|███▊      | 356/938 [00:24<00:39, 14.57it/s, loss=0.644, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  38%|███▊      | 357/938 [00:24<00:39, 14.57it/s, loss=0.647, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  38%|███▊      | 358/938 [00:24<00:39, 14.57it/s, loss=0.655, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  38%|███▊      | 359/938 [00:24<00:39, 14.55it/s, loss=0.657, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  38%|███▊      | 360/938 [00:24<00:39, 14.54it/s, loss=0.657, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  38%|███▊      | 360/938 [00:24<00:39, 14.54it/s, loss=0.655, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  38%|███▊      | 361/938 [00:24<00:39, 14.54it/s, loss=0.657, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  39%|███▊      | 362/938 [00:24<00:39, 14.53it/s, loss=0.658, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  39%|███▊      | 363/938 [00:24<00:39, 14.53it/s, loss=0.654, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  39%|███▉      | 364/938 [00:25<00:39, 14.54it/s, loss=0.654, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  39%|███▉      | 364/938 [00:25<00:39, 14.54it/s, loss=0.649, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  39%|███▉      | 365/938 [00:25<00:39, 14.54it/s, loss=0.652, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  39%|███▉      | 366/938 [00:25<00:39, 14.55it/s, loss=0.653, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  39%|███▉      | 367/938 [00:25<00:39, 14.55it/s, loss=0.653, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  39%|███▉      | 368/938 [00:25<00:39, 14.55it/s, loss=0.653, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  39%|███▉      | 368/938 [00:25<00:39, 14.55it/s, loss=0.655, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  39%|███▉      | 369/938 [00:25<00:39, 14.55it/s, loss=0.656, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  39%|███▉      | 370/938 [00:25<00:39, 14.55it/s, loss=0.657, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  40%|███▉      | 371/938 [00:25<00:38, 14.55it/s, loss=0.656, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  40%|███▉      | 372/938 [00:25<00:38, 14.55it/s, loss=0.656, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  40%|███▉      | 372/938 [00:25<00:38, 14.55it/s, loss=0.653, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  40%|███▉      | 373/938 [00:25<00:38, 14.56it/s, loss=0.657, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  40%|███▉      | 374/938 [00:25<00:38, 14.56it/s, loss=0.659, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  40%|███▉      | 375/938 [00:25<00:38, 14.56it/s, loss=0.659, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  40%|████      | 376/938 [00:25<00:38, 14.56it/s, loss=0.659, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  40%|████      | 376/938 [00:25<00:38, 14.56it/s, loss=0.664, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  40%|████      | 377/938 [00:25<00:38, 14.56it/s, loss=0.655, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  40%|████      | 378/938 [00:25<00:38, 14.56it/s, loss=0.652, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  40%|████      | 379/938 [00:26<00:38, 14.56it/s, loss=0.664, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  41%|████      | 380/938 [00:26<00:38, 14.56it/s, loss=0.664, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  41%|████      | 380/938 [00:26<00:38, 14.56it/s, loss=0.672, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  41%|████      | 381/938 [00:26<00:38, 14.56it/s, loss=0.673, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  41%|████      | 382/938 [00:26<00:38, 14.56it/s, loss=0.681, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  41%|████      | 383/938 [00:26<00:38, 14.56it/s, loss=0.68, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  41%|████      | 384/938 [00:26<00:38, 14.56it/s, loss=0.68, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  41%|████      | 384/938 [00:26<00:38, 14.56it/s, loss=0.68, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  41%|████      | 385/938 [00:26<00:37, 14.57it/s, loss=0.675, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  41%|████      | 386/938 [00:26<00:37, 14.57it/s, loss=0.671, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  41%|████▏     | 387/938 [00:26<00:37, 14.56it/s, loss=0.673, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  41%|████▏     | 388/938 [00:26<00:37, 14.57it/s, loss=0.673, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  41%|████▏     | 388/938 [00:26<00:37, 14.57it/s, loss=0.668, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  41%|████▏     | 389/938 [00:26<00:37, 14.57it/s, loss=0.672, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  42%|████▏     | 390/938 [00:26<00:37, 14.58it/s, loss=0.672, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  42%|████▏     | 391/938 [00:26<00:37, 14.57it/s, loss=0.68, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  42%|████▏     | 392/938 [00:26<00:37, 14.57it/s, loss=0.68, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  42%|████▏     | 392/938 [00:26<00:37, 14.57it/s, loss=0.696, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  42%|████▏     | 393/938 [00:26<00:37, 14.57it/s, loss=0.698, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  42%|████▏     | 394/938 [00:27<00:37, 14.58it/s, loss=0.695, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  42%|████▏     | 395/938 [00:27<00:37, 14.55it/s, loss=0.71, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  42%|████▏     | 396/938 [00:27<00:37, 14.55it/s, loss=0.71, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  42%|████▏     | 396/938 [00:27<00:37, 14.55it/s, loss=0.716, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  42%|████▏     | 397/938 [00:27<00:37, 14.54it/s, loss=0.717, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  42%|████▏     | 398/938 [00:27<00:37, 14.55it/s, loss=0.713, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  43%|████▎     | 399/938 [00:27<00:37, 14.54it/s, loss=0.7, v_num=13, val_rmse=0.557, train_rmse=0.743]  
Epoch 2:  43%|████▎     | 400/938 [00:27<00:37, 14.54it/s, loss=0.7, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  43%|████▎     | 400/938 [00:27<00:37, 14.54it/s, loss=0.701, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  43%|████▎     | 401/938 [00:27<00:36, 14.54it/s, loss=0.698, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  43%|████▎     | 402/938 [00:27<00:36, 14.53it/s, loss=0.689, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  43%|████▎     | 403/938 [00:27<00:36, 14.53it/s, loss=0.696, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  43%|████▎     | 404/938 [00:27<00:36, 14.53it/s, loss=0.696, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  43%|████▎     | 404/938 [00:27<00:36, 14.53it/s, loss=0.697, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  43%|████▎     | 405/938 [00:27<00:36, 14.54it/s, loss=0.698, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  43%|████▎     | 406/938 [00:27<00:36, 14.53it/s, loss=0.707, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  43%|████▎     | 407/938 [00:28<00:36, 14.53it/s, loss=0.701, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  43%|████▎     | 408/938 [00:28<00:36, 14.54it/s, loss=0.701, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  43%|████▎     | 408/938 [00:28<00:36, 14.54it/s, loss=0.707, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  44%|████▎     | 409/938 [00:28<00:36, 14.54it/s, loss=0.709, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  44%|████▎     | 410/938 [00:28<00:36, 14.54it/s, loss=0.704, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  44%|████▍     | 411/938 [00:28<00:36, 14.55it/s, loss=0.688, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  44%|████▍     | 412/938 [00:28<00:36, 14.54it/s, loss=0.688, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  44%|████▍     | 412/938 [00:28<00:36, 14.54it/s, loss=0.673, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  44%|████▍     | 413/938 [00:28<00:36, 14.54it/s, loss=0.67, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  44%|████▍     | 414/938 [00:28<00:36, 14.54it/s, loss=0.669, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  44%|████▍     | 415/938 [00:28<00:35, 14.54it/s, loss=0.654, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  44%|████▍     | 416/938 [00:28<00:35, 14.54it/s, loss=0.654, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  44%|████▍     | 416/938 [00:28<00:35, 14.54it/s, loss=0.646, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  44%|████▍     | 417/938 [00:28<00:35, 14.54it/s, loss=0.655, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  45%|████▍     | 418/938 [00:28<00:35, 14.54it/s, loss=0.659, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  45%|████▍     | 419/938 [00:28<00:35, 14.54it/s, loss=0.658, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  45%|████▍     | 420/938 [00:28<00:35, 14.55it/s, loss=0.658, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  45%|████▍     | 420/938 [00:28<00:35, 14.55it/s, loss=0.648, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  45%|████▍     | 421/938 [00:28<00:35, 14.54it/s, loss=0.652, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  45%|████▍     | 422/938 [00:29<00:35, 14.54it/s, loss=0.659, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  45%|████▌     | 423/938 [00:29<00:35, 14.55it/s, loss=0.656, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  45%|████▌     | 424/938 [00:29<00:35, 14.54it/s, loss=0.656, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  45%|████▌     | 424/938 [00:29<00:35, 14.54it/s, loss=0.657, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  45%|████▌     | 425/938 [00:29<00:35, 14.55it/s, loss=0.655, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  45%|████▌     | 426/938 [00:29<00:35, 14.55it/s, loss=0.656, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  46%|████▌     | 427/938 [00:29<00:35, 14.55it/s, loss=0.66, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  46%|████▌     | 428/938 [00:29<00:35, 14.55it/s, loss=0.66, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  46%|████▌     | 428/938 [00:29<00:35, 14.55it/s, loss=0.667, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  46%|████▌     | 429/938 [00:29<00:34, 14.55it/s, loss=0.667, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  46%|████▌     | 430/938 [00:29<00:34, 14.55it/s, loss=0.67, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  46%|████▌     | 431/938 [00:29<00:34, 14.55it/s, loss=0.674, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  46%|████▌     | 432/938 [00:29<00:34, 14.55it/s, loss=0.674, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  46%|████▌     | 432/938 [00:29<00:34, 14.55it/s, loss=0.675, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  46%|████▌     | 433/938 [00:29<00:34, 14.56it/s, loss=0.685, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  46%|████▋     | 434/938 [00:29<00:34, 14.54it/s, loss=0.691, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  46%|████▋     | 435/938 [00:29<00:34, 14.55it/s, loss=0.692, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  46%|████▋     | 436/938 [00:29<00:34, 14.55it/s, loss=0.692, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  46%|████▋     | 436/938 [00:29<00:34, 14.55it/s, loss=0.689, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  47%|████▋     | 437/938 [00:30<00:34, 14.56it/s, loss=0.683, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  47%|████▋     | 438/938 [00:30<00:34, 14.56it/s, loss=0.69, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  47%|████▋     | 439/938 [00:30<00:34, 14.56it/s, loss=0.691, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  47%|████▋     | 440/938 [00:30<00:34, 14.56it/s, loss=0.691, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  47%|████▋     | 440/938 [00:30<00:34, 14.56it/s, loss=0.689, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  47%|████▋     | 441/938 [00:30<00:34, 14.56it/s, loss=0.691, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  47%|████▋     | 442/938 [00:30<00:34, 14.56it/s, loss=0.697, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  47%|████▋     | 443/938 [00:30<00:34, 14.55it/s, loss=0.701, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  47%|████▋     | 444/938 [00:30<00:33, 14.56it/s, loss=0.701, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  47%|████▋     | 444/938 [00:30<00:33, 14.56it/s, loss=0.701, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  47%|████▋     | 445/938 [00:30<00:33, 14.55it/s, loss=0.702, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  48%|████▊     | 446/938 [00:30<00:33, 14.55it/s, loss=0.702, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  48%|████▊     | 447/938 [00:30<00:33, 14.55it/s, loss=0.702, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  48%|████▊     | 448/938 [00:30<00:33, 14.56it/s, loss=0.702, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  48%|████▊     | 448/938 [00:30<00:33, 14.56it/s, loss=0.694, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  48%|████▊     | 449/938 [00:30<00:33, 14.55it/s, loss=0.698, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  48%|████▊     | 450/938 [00:30<00:33, 14.56it/s, loss=0.695, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  48%|████▊     | 451/938 [00:30<00:33, 14.56it/s, loss=0.699, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  48%|████▊     | 452/938 [00:31<00:33, 14.57it/s, loss=0.699, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  48%|████▊     | 452/938 [00:31<00:33, 14.57it/s, loss=0.7, v_num=13, val_rmse=0.557, train_rmse=0.743]  
Epoch 2:  48%|████▊     | 453/938 [00:31<00:33, 14.57it/s, loss=0.689, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  48%|████▊     | 454/938 [00:31<00:33, 14.57it/s, loss=0.685, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  49%|████▊     | 455/938 [00:31<00:33, 14.57it/s, loss=0.677, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  49%|████▊     | 456/938 [00:31<00:33, 14.57it/s, loss=0.677, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  49%|████▊     | 456/938 [00:31<00:33, 14.57it/s, loss=0.672, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  49%|████▊     | 457/938 [00:31<00:33, 14.57it/s, loss=0.665, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  49%|████▉     | 458/938 [00:31<00:32, 14.58it/s, loss=0.652, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  49%|████▉     | 459/938 [00:31<00:32, 14.57it/s, loss=0.653, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  49%|████▉     | 460/938 [00:31<00:32, 14.54it/s, loss=0.653, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  49%|████▉     | 460/938 [00:31<00:32, 14.54it/s, loss=0.661, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  49%|████▉     | 461/938 [00:31<00:32, 14.54it/s, loss=0.66, v_num=13, val_rmse=0.557, train_rmse=0.743] 
Epoch 2:  49%|████▉     | 462/938 [00:31<00:32, 14.54it/s, loss=0.652, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  49%|████▉     | 463/938 [00:31<00:32, 14.54it/s, loss=0.651, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  49%|████▉     | 464/938 [00:31<00:32, 14.54it/s, loss=0.651, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  49%|████▉     | 464/938 [00:31<00:32, 14.54it/s, loss=0.644, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  50%|████▉     | 465/938 [00:31<00:32, 14.54it/s, loss=0.648, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  50%|████▉     | 466/938 [00:32<00:32, 14.54it/s, loss=0.641, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  50%|████▉     | 467/938 [00:32<00:32, 14.54it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  50%|████▉     | 468/938 [00:32<00:32, 14.55it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  50%|████▉     | 468/938 [00:32<00:32, 14.55it/s, loss=0.646, v_num=13, val_rmse=0.557, train_rmse=0.743]
Epoch 2:  50%|█████     | 469/938 [00:32<00:32, 14.56it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]

Validating:   0%|          | 2/469 [00:00<00:23, 19.96it/s]
Epoch 2:  50%|█████     | 472/938 [00:32<00:31, 14.60it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:   1%|          | 5/469 [00:00<00:19, 23.38it/s]
Epoch 2:  51%|█████     | 476/938 [00:32<00:31, 14.66it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:   2%|▏         | 8/469 [00:00<00:18, 25.30it/s]
Epoch 2:  51%|█████     | 480/938 [00:32<00:31, 14.72it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:   2%|▏         | 11/469 [00:00<00:17, 25.79it/s]

Validating:   3%|▎         | 14/469 [00:00<00:18, 24.55it/s]
Epoch 2:  52%|█████▏    | 484/938 [00:32<00:30, 14.76it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:   4%|▎         | 17/469 [00:00<00:18, 24.44it/s]
Epoch 2:  52%|█████▏    | 488/938 [00:32<00:30, 14.81it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:   4%|▍         | 20/469 [00:00<00:17, 26.03it/s]
Epoch 2:  52%|█████▏    | 492/938 [00:33<00:30, 14.86it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:   5%|▍         | 23/469 [00:00<00:17, 25.17it/s]

Validating:   6%|▌         | 26/469 [00:01<00:17, 26.03it/s]
Epoch 2:  53%|█████▎    | 496/938 [00:33<00:29, 14.92it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:   6%|▌         | 29/469 [00:01<00:17, 25.46it/s]
Epoch 2:  53%|█████▎    | 500/938 [00:33<00:29, 14.96it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:   7%|▋         | 32/469 [00:01<00:17, 24.49it/s]
Epoch 2:  54%|█████▎    | 504/938 [00:33<00:28, 15.01it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:   7%|▋         | 35/469 [00:01<00:17, 25.32it/s]

Validating:   8%|▊         | 38/469 [00:01<00:16, 25.66it/s]
Epoch 2:  54%|█████▍    | 508/938 [00:33<00:28, 15.06it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:   9%|▊         | 41/469 [00:01<00:16, 25.61it/s]
Epoch 2:  55%|█████▍    | 512/938 [00:33<00:28, 15.11it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:   9%|▉         | 44/469 [00:01<00:16, 25.56it/s]
Epoch 2:  55%|█████▌    | 516/938 [00:34<00:27, 15.16it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  10%|█         | 47/469 [00:01<00:16, 25.82it/s]

Validating:  11%|█         | 50/469 [00:02<00:17, 23.40it/s]
Epoch 2:  55%|█████▌    | 520/938 [00:34<00:27, 15.19it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  11%|█▏        | 53/469 [00:02<00:17, 24.34it/s]
Epoch 2:  56%|█████▌    | 524/938 [00:34<00:27, 15.24it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  12%|█▏        | 56/469 [00:02<00:16, 24.53it/s]
Epoch 2:  56%|█████▋    | 528/938 [00:34<00:26, 15.29it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  13%|█▎        | 59/469 [00:02<00:16, 25.18it/s]

Validating:  13%|█▎        | 62/469 [00:02<00:16, 24.21it/s]
Epoch 2:  57%|█████▋    | 532/938 [00:34<00:26, 15.33it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  14%|█▍        | 65/469 [00:02<00:16, 24.90it/s]
Epoch 2:  57%|█████▋    | 536/938 [00:34<00:26, 15.37it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  14%|█▍        | 68/469 [00:02<00:16, 24.75it/s]
Epoch 2:  58%|█████▊    | 540/938 [00:35<00:25, 15.42it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  15%|█▌        | 71/469 [00:02<00:15, 25.49it/s]

Validating:  16%|█▌        | 74/469 [00:02<00:15, 25.47it/s]
Epoch 2:  58%|█████▊    | 544/938 [00:35<00:25, 15.47it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  16%|█▋        | 77/469 [00:03<00:15, 25.92it/s]
Epoch 2:  58%|█████▊    | 548/938 [00:35<00:25, 15.51it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  17%|█▋        | 80/469 [00:03<00:15, 25.74it/s]
Epoch 2:  59%|█████▉    | 552/938 [00:35<00:24, 15.55it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  18%|█▊        | 83/469 [00:03<00:15, 24.98it/s]

Validating:  18%|█▊        | 86/469 [00:03<00:15, 24.88it/s]
Epoch 2:  59%|█████▉    | 556/938 [00:35<00:24, 15.59it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  19%|█▉        | 89/469 [00:03<00:14, 25.77it/s]
Epoch 2:  60%|█████▉    | 560/938 [00:35<00:24, 15.65it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  20%|█▉        | 92/469 [00:03<00:14, 25.98it/s]
Epoch 2:  60%|██████    | 564/938 [00:35<00:23, 15.69it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  20%|██        | 95/469 [00:03<00:14, 26.69it/s]

Validating:  21%|██        | 98/469 [00:03<00:14, 26.38it/s]
Epoch 2:  61%|██████    | 568/938 [00:36<00:23, 15.74it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  22%|██▏       | 101/469 [00:03<00:13, 27.02it/s]
Epoch 2:  61%|██████    | 572/938 [00:36<00:23, 15.78it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  22%|██▏       | 104/469 [00:04<00:14, 25.12it/s]
Epoch 2:  61%|██████▏   | 576/938 [00:36<00:22, 15.82it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  23%|██▎       | 107/469 [00:04<00:14, 25.36it/s]

Validating:  23%|██▎       | 110/469 [00:04<00:13, 25.67it/s]
Epoch 2:  62%|██████▏   | 580/938 [00:36<00:22, 15.86it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  24%|██▍       | 113/469 [00:04<00:13, 25.75it/s]
Epoch 2:  62%|██████▏   | 584/938 [00:36<00:22, 15.91it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  25%|██▍       | 116/469 [00:04<00:13, 26.79it/s]
Epoch 2:  63%|██████▎   | 588/938 [00:36<00:21, 15.95it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  25%|██▌       | 119/469 [00:04<00:12, 27.10it/s]

Validating:  26%|██▌       | 122/469 [00:04<00:12, 26.84it/s]
Epoch 2:  63%|██████▎   | 592/938 [00:37<00:21, 16.00it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  27%|██▋       | 125/469 [00:04<00:13, 26.18it/s]
Epoch 2:  64%|██████▎   | 596/938 [00:37<00:21, 16.04it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  27%|██▋       | 128/469 [00:05<00:12, 26.37it/s]
Epoch 2:  64%|██████▍   | 600/938 [00:37<00:21, 16.08it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  28%|██▊       | 131/469 [00:05<00:13, 25.94it/s]

Validating:  29%|██▊       | 134/469 [00:05<00:12, 26.26it/s]
Epoch 2:  64%|██████▍   | 604/938 [00:37<00:20, 16.12it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  29%|██▉       | 137/469 [00:05<00:12, 25.82it/s]
Epoch 2:  65%|██████▍   | 608/938 [00:37<00:20, 16.16it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  30%|██▉       | 140/469 [00:05<00:12, 26.59it/s]
Epoch 2:  65%|██████▌   | 612/938 [00:37<00:20, 16.20it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  30%|███       | 143/469 [00:05<00:12, 26.99it/s]

Validating:  31%|███       | 146/469 [00:05<00:12, 26.87it/s]
Epoch 2:  66%|██████▌   | 616/938 [00:37<00:19, 16.25it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  32%|███▏      | 149/469 [00:05<00:12, 26.55it/s]
Epoch 2:  66%|██████▌   | 620/938 [00:38<00:19, 16.28it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  32%|███▏      | 152/469 [00:05<00:12, 26.38it/s]
Epoch 2:  67%|██████▋   | 624/938 [00:38<00:19, 16.33it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  33%|███▎      | 155/469 [00:06<00:11, 26.82it/s]

Validating:  34%|███▎      | 158/469 [00:06<00:12, 25.10it/s]
Epoch 2:  67%|██████▋   | 628/938 [00:38<00:18, 16.36it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  34%|███▍      | 161/469 [00:06<00:12, 25.62it/s]
Epoch 2:  67%|██████▋   | 632/938 [00:38<00:18, 16.39it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  35%|███▍      | 164/469 [00:06<00:12, 24.22it/s]
Epoch 2:  68%|██████▊   | 636/938 [00:38<00:18, 16.42it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  36%|███▌      | 167/469 [00:06<00:12, 24.79it/s]

Validating:  36%|███▌      | 170/469 [00:06<00:12, 24.20it/s]
Epoch 2:  68%|██████▊   | 640/938 [00:38<00:18, 16.46it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  37%|███▋      | 173/469 [00:06<00:11, 25.64it/s]
Epoch 2:  69%|██████▊   | 644/938 [00:39<00:17, 16.50it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  38%|███▊      | 176/469 [00:06<00:11, 25.76it/s]
Epoch 2:  69%|██████▉   | 648/938 [00:39<00:17, 16.54it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  38%|███▊      | 179/469 [00:06<00:11, 26.27it/s]

Validating:  39%|███▉      | 182/469 [00:07<00:11, 25.06it/s]
Epoch 2:  70%|██████▉   | 652/938 [00:39<00:17, 16.57it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  39%|███▉      | 185/469 [00:07<00:11, 25.45it/s]
Epoch 2:  70%|██████▉   | 656/938 [00:39<00:16, 16.61it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  40%|████      | 188/469 [00:07<00:10, 26.24it/s]
Epoch 2:  70%|███████   | 660/938 [00:39<00:16, 16.65it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  41%|████      | 191/469 [00:07<00:10, 27.14it/s]

Validating:  41%|████▏     | 194/469 [00:07<00:10, 27.23it/s]
Epoch 2:  71%|███████   | 664/938 [00:39<00:16, 16.69it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  42%|████▏     | 197/469 [00:07<00:09, 27.64it/s]
Epoch 2:  71%|███████   | 668/938 [00:39<00:16, 16.73it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  43%|████▎     | 200/469 [00:07<00:10, 26.23it/s]
Epoch 2:  72%|███████▏  | 672/938 [00:40<00:15, 16.76it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  43%|████▎     | 203/469 [00:07<00:10, 26.18it/s]

Validating:  44%|████▍     | 206/469 [00:08<00:10, 26.17it/s]
Epoch 2:  72%|███████▏  | 676/938 [00:40<00:15, 16.80it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  45%|████▍     | 209/469 [00:08<00:10, 24.09it/s]
Epoch 2:  72%|███████▏  | 680/938 [00:40<00:15, 16.82it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  45%|████▌     | 212/469 [00:08<00:10, 24.71it/s]
Epoch 2:  73%|███████▎  | 684/938 [00:40<00:15, 16.86it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  46%|████▌     | 215/469 [00:08<00:10, 25.21it/s]

Validating:  46%|████▋     | 218/469 [00:08<00:09, 25.98it/s]
Epoch 2:  73%|███████▎  | 688/938 [00:40<00:14, 16.89it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  47%|████▋     | 221/469 [00:08<00:09, 25.43it/s]
Epoch 2:  74%|███████▍  | 692/938 [00:40<00:14, 16.93it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  48%|████▊     | 224/469 [00:08<00:09, 25.70it/s]
Epoch 2:  74%|███████▍  | 696/938 [00:41<00:14, 16.96it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  48%|████▊     | 227/469 [00:08<00:09, 26.35it/s]

Validating:  49%|████▉     | 230/469 [00:08<00:09, 26.52it/s]
Epoch 2:  75%|███████▍  | 700/938 [00:41<00:14, 17.00it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  50%|████▉     | 233/469 [00:09<00:08, 27.04it/s]
Epoch 2:  75%|███████▌  | 704/938 [00:41<00:13, 17.04it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  50%|█████     | 236/469 [00:09<00:08, 27.78it/s]
Epoch 2:  75%|███████▌  | 708/938 [00:41<00:13, 17.07it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  51%|█████     | 239/469 [00:09<00:08, 27.45it/s]

Validating:  52%|█████▏    | 242/469 [00:09<00:08, 26.45it/s]
Epoch 2:  76%|███████▌  | 712/938 [00:41<00:13, 17.11it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  52%|█████▏    | 245/469 [00:09<00:08, 25.33it/s]
Epoch 2:  76%|███████▋  | 716/938 [00:41<00:12, 17.13it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  53%|█████▎    | 248/469 [00:09<00:08, 25.73it/s]
Epoch 2:  77%|███████▋  | 720/938 [00:41<00:12, 17.17it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  54%|█████▎    | 251/469 [00:09<00:08, 25.83it/s]

Validating:  54%|█████▍    | 254/469 [00:09<00:08, 26.10it/s]
Epoch 2:  77%|███████▋  | 724/938 [00:42<00:12, 17.20it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  55%|█████▍    | 257/469 [00:09<00:07, 26.77it/s]
Epoch 2:  78%|███████▊  | 728/938 [00:42<00:12, 17.24it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  55%|█████▌    | 260/469 [00:10<00:07, 26.67it/s]
Epoch 2:  78%|███████▊  | 732/938 [00:42<00:11, 17.27it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  56%|█████▌    | 263/469 [00:10<00:07, 26.86it/s]

Validating:  57%|█████▋    | 266/469 [00:10<00:08, 24.98it/s]
Epoch 2:  78%|███████▊  | 736/938 [00:42<00:11, 17.29it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  57%|█████▋    | 269/469 [00:10<00:08, 24.93it/s]
Epoch 2:  79%|███████▉  | 740/938 [00:42<00:11, 17.32it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  58%|█████▊    | 272/469 [00:10<00:07, 25.57it/s]
Epoch 2:  79%|███████▉  | 744/938 [00:42<00:11, 17.36it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  59%|█████▊    | 275/469 [00:10<00:07, 26.24it/s]

Validating:  59%|█████▉    | 278/469 [00:10<00:07, 26.06it/s]
Epoch 2:  80%|███████▉  | 748/938 [00:43<00:10, 17.39it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  60%|█████▉    | 281/469 [00:10<00:07, 25.96it/s]
Epoch 2:  80%|████████  | 752/938 [00:43<00:10, 17.42it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  61%|██████    | 284/469 [00:11<00:07, 26.27it/s]
Epoch 2:  81%|████████  | 756/938 [00:43<00:10, 17.45it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  61%|██████    | 287/469 [00:11<00:06, 26.54it/s]

Validating:  62%|██████▏   | 290/469 [00:11<00:06, 25.78it/s]
Epoch 2:  81%|████████  | 760/938 [00:43<00:10, 17.48it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  62%|██████▏   | 293/469 [00:11<00:06, 26.41it/s]
Epoch 2:  81%|████████▏ | 764/938 [00:43<00:09, 17.52it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  63%|██████▎   | 296/469 [00:11<00:06, 26.03it/s]
Epoch 2:  82%|████████▏ | 768/938 [00:43<00:09, 17.54it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  64%|██████▍   | 299/469 [00:11<00:06, 26.00it/s]

Validating:  64%|██████▍   | 302/469 [00:11<00:06, 25.98it/s]
Epoch 2:  82%|████████▏ | 772/938 [00:43<00:09, 17.57it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  65%|██████▌   | 305/469 [00:11<00:06, 26.30it/s]
Epoch 2:  83%|████████▎ | 776/938 [00:44<00:09, 17.60it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  66%|██████▌   | 308/469 [00:11<00:06, 25.71it/s]
Epoch 2:  83%|████████▎ | 780/938 [00:44<00:08, 17.63it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  66%|██████▋   | 311/469 [00:12<00:06, 26.14it/s]

Validating:  67%|██████▋   | 314/469 [00:12<00:05, 26.25it/s]
Epoch 2:  84%|████████▎ | 784/938 [00:44<00:08, 17.66it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  68%|██████▊   | 317/469 [00:12<00:05, 26.68it/s]
Epoch 2:  84%|████████▍ | 788/938 [00:44<00:08, 17.69it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  68%|██████▊   | 320/469 [00:12<00:05, 25.63it/s]
Epoch 2:  84%|████████▍ | 792/938 [00:44<00:08, 17.72it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  69%|██████▉   | 323/469 [00:12<00:05, 25.70it/s]

Validating:  70%|██████▉   | 326/469 [00:12<00:05, 26.79it/s]
Epoch 2:  85%|████████▍ | 796/938 [00:44<00:08, 17.75it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  70%|███████   | 329/469 [00:12<00:05, 26.69it/s]
Epoch 2:  85%|████████▌ | 800/938 [00:44<00:07, 17.78it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  71%|███████   | 332/469 [00:12<00:05, 26.62it/s]
Epoch 2:  86%|████████▌ | 804/938 [00:45<00:07, 17.81it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  71%|███████▏  | 335/469 [00:12<00:04, 26.91it/s]

Validating:  72%|███████▏  | 338/469 [00:13<00:04, 26.82it/s]
Epoch 2:  86%|████████▌ | 808/938 [00:45<00:07, 17.84it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  73%|███████▎  | 341/469 [00:13<00:04, 26.86it/s]
Epoch 2:  87%|████████▋ | 812/938 [00:45<00:07, 17.87it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  73%|███████▎  | 344/469 [00:13<00:04, 27.39it/s]
Epoch 2:  87%|████████▋ | 816/938 [00:45<00:06, 17.90it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  74%|███████▍  | 347/469 [00:13<00:04, 27.13it/s]

Validating:  75%|███████▍  | 350/469 [00:13<00:04, 27.36it/s]
Epoch 2:  87%|████████▋ | 820/938 [00:45<00:06, 17.93it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  75%|███████▌  | 353/469 [00:13<00:04, 27.62it/s]
Epoch 2:  88%|████████▊ | 824/938 [00:45<00:06, 17.96it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  76%|███████▌  | 356/469 [00:13<00:04, 27.09it/s]
Epoch 2:  88%|████████▊ | 828/938 [00:46<00:06, 17.99it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  77%|███████▋  | 359/469 [00:13<00:04, 27.37it/s]

Validating:  77%|███████▋  | 362/469 [00:13<00:03, 26.99it/s]
Epoch 2:  89%|████████▊ | 832/938 [00:46<00:05, 18.02it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  78%|███████▊  | 365/469 [00:14<00:03, 26.24it/s]
Epoch 2:  89%|████████▉ | 836/938 [00:46<00:05, 18.04it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  78%|███████▊  | 368/469 [00:14<00:03, 26.49it/s]
Epoch 2:  90%|████████▉ | 840/938 [00:46<00:05, 18.07it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  79%|███████▉  | 371/469 [00:14<00:03, 26.47it/s]

Validating:  80%|███████▉  | 374/469 [00:14<00:03, 26.42it/s]
Epoch 2:  90%|████████▉ | 844/938 [00:46<00:05, 18.10it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  80%|████████  | 377/469 [00:14<00:03, 26.33it/s]
Epoch 2:  90%|█████████ | 848/938 [00:46<00:04, 18.13it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  81%|████████  | 380/469 [00:14<00:03, 26.45it/s]
Epoch 2:  91%|█████████ | 852/938 [00:46<00:04, 18.15it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  82%|████████▏ | 383/469 [00:14<00:03, 26.40it/s]

Validating:  82%|████████▏ | 386/469 [00:14<00:03, 26.73it/s]
Epoch 2:  91%|█████████▏| 856/938 [00:47<00:04, 18.18it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  83%|████████▎ | 389/469 [00:14<00:03, 25.91it/s]
Epoch 2:  92%|█████████▏| 860/938 [00:47<00:04, 18.20it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  84%|████████▎ | 392/469 [00:15<00:02, 26.32it/s]
Epoch 2:  92%|█████████▏| 864/938 [00:47<00:04, 18.23it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  84%|████████▍ | 395/469 [00:15<00:02, 26.26it/s]

Validating:  85%|████████▍ | 398/469 [00:15<00:02, 26.36it/s]
Epoch 2:  93%|█████████▎| 868/938 [00:47<00:03, 18.26it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  86%|████████▌ | 401/469 [00:15<00:02, 25.17it/s]
Epoch 2:  93%|█████████▎| 872/938 [00:47<00:03, 18.28it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  86%|████████▌ | 404/469 [00:15<00:02, 26.04it/s]
Epoch 2:  93%|█████████▎| 876/938 [00:47<00:03, 18.30it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  87%|████████▋ | 407/469 [00:15<00:02, 25.13it/s]

Validating:  87%|████████▋ | 410/469 [00:15<00:02, 24.98it/s]
Epoch 2:  94%|█████████▍| 880/938 [00:48<00:03, 18.32it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  88%|████████▊ | 413/469 [00:15<00:02, 24.99it/s]
Epoch 2:  94%|█████████▍| 884/938 [00:48<00:02, 18.34it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  89%|████████▊ | 416/469 [00:16<00:02, 26.13it/s]
Epoch 2:  95%|█████████▍| 888/938 [00:48<00:02, 18.37it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  89%|████████▉ | 419/469 [00:16<00:01, 25.73it/s]

Validating:  90%|████████▉ | 422/469 [00:16<00:01, 26.38it/s]
Epoch 2:  95%|█████████▌| 892/938 [00:48<00:02, 18.40it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  91%|█████████ | 425/469 [00:16<00:01, 26.90it/s]
Epoch 2:  96%|█████████▌| 896/938 [00:48<00:02, 18.43it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  91%|█████████▏| 428/469 [00:16<00:01, 27.64it/s]
Epoch 2:  96%|█████████▌| 900/938 [00:48<00:02, 18.46it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  92%|█████████▏| 431/469 [00:16<00:01, 28.04it/s]

Validating:  93%|█████████▎| 434/469 [00:16<00:01, 27.68it/s]
Epoch 2:  96%|█████████▋| 904/938 [00:48<00:01, 18.48it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  93%|█████████▎| 437/469 [00:16<00:01, 27.27it/s]
Epoch 2:  97%|█████████▋| 908/938 [00:49<00:01, 18.51it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  94%|█████████▍| 440/469 [00:16<00:01, 27.16it/s]
Epoch 2:  97%|█████████▋| 912/938 [00:49<00:01, 18.54it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  94%|█████████▍| 443/469 [00:17<00:00, 27.88it/s]

Validating:  95%|█████████▌| 446/469 [00:17<00:00, 27.12it/s]
Epoch 2:  98%|█████████▊| 916/938 [00:49<00:01, 18.56it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  96%|█████████▌| 450/469 [00:17<00:00, 28.41it/s]
Epoch 2:  98%|█████████▊| 920/938 [00:49<00:00, 18.59it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  97%|█████████▋| 453/469 [00:17<00:00, 27.76it/s]
Epoch 2:  99%|█████████▊| 924/938 [00:49<00:00, 18.62it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  97%|█████████▋| 456/469 [00:17<00:00, 26.72it/s]
Epoch 2:  99%|█████████▉| 928/938 [00:49<00:00, 18.64it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  98%|█████████▊| 459/469 [00:17<00:00, 26.21it/s]

Validating:  99%|█████████▊| 462/469 [00:17<00:00, 25.30it/s]
Epoch 2:  99%|█████████▉| 932/938 [00:49<00:00, 18.65it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating:  99%|█████████▉| 465/469 [00:17<00:00, 26.26it/s]
Epoch 2: 100%|█████████▉| 936/938 [00:50<00:00, 18.68it/s, loss=0.638, v_num=13, val_rmse=0.557, train_rmse=0.743]

Validating: 100%|█████████▉| 468/469 [00:17<00:00, 26.41it/s]
Epoch 2: 100%|██████████| 938/938 [00:50<00:00, 18.68it/s, loss=0.638, v_num=13, val_rmse=0.538, train_rmse=0.743]

                                                             
Epoch 2: 100%|██████████| 938/938 [00:50<00:00, 18.67it/s, loss=0.638, v_num=13, val_rmse=0.538, train_rmse=0.684]
Epoch 2: 100%|██████████| 938/938 [00:50<00:00, 18.64it/s, loss=0.638, v_num=13, val_rmse=0.538, train_rmse=0.684]LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]


Testing: 0it [00:00, ?it/s]
Testing:   1%|          | 3/469 [00:00<00:19, 23.90it/s]
Testing:   1%|▏         | 6/469 [00:00<00:19, 23.40it/s]
Testing:   2%|▏         | 9/469 [00:00<00:18, 24.36it/s]
Testing:   3%|▎         | 12/469 [00:00<00:17, 25.41it/s]
Testing:   3%|▎         | 15/469 [00:00<00:18, 25.10it/s]
Testing:   4%|▍         | 18/469 [00:00<00:18, 24.40it/s]
Testing:   4%|▍         | 21/469 [00:00<00:18, 24.37it/s]
Testing:   5%|▌         | 24/469 [00:00<00:18, 24.43it/s]
Testing:   6%|▌         | 27/469 [00:01<00:18, 24.02it/s]
Testing:   6%|▋         | 30/469 [00:01<00:17, 24.62it/s]
Testing:   7%|▋         | 33/469 [00:01<00:17, 24.44it/s]
Testing:   8%|▊         | 36/469 [00:01<00:17, 24.95it/s]
Testing:   8%|▊         | 39/469 [00:01<00:16, 25.45it/s]
Testing:   9%|▉         | 43/469 [00:01<00:16, 26.45it/s]
Testing:  10%|▉         | 46/469 [00:01<00:16, 25.71it/s]
Testing:  10%|█         | 49/469 [00:01<00:16, 24.74it/s]
Testing:  11%|█         | 52/469 [00:02<00:16, 24.79it/s]
Testing:  12%|█▏        | 55/469 [00:02<00:16, 25.33it/s]
Testing:  12%|█▏        | 58/469 [00:02<00:15, 26.43it/s]
Testing:  13%|█▎        | 61/469 [00:02<00:15, 26.14it/s]
Testing:  14%|█▎        | 64/469 [00:02<00:15, 26.02it/s]
Testing:  14%|█▍        | 67/469 [00:02<00:16, 24.64it/s]
Testing:  15%|█▍        | 70/469 [00:02<00:16, 24.89it/s]
Testing:  16%|█▌        | 73/469 [00:02<00:16, 24.08it/s]
Testing:  16%|█▌        | 76/469 [00:03<00:16, 23.61it/s]
Testing:  17%|█▋        | 79/469 [00:03<00:16, 23.83it/s]
Testing:  17%|█▋        | 82/469 [00:03<00:16, 24.12it/s]
Testing:  18%|█▊        | 85/469 [00:03<00:16, 23.30it/s]
Testing:  19%|█▉        | 88/469 [00:03<00:15, 23.92it/s]
Testing:  19%|█▉        | 91/469 [00:03<00:15, 23.99it/s]
Testing:  20%|██        | 94/469 [00:03<00:15, 23.75it/s]
Testing:  21%|██        | 97/469 [00:03<00:15, 24.20it/s]
Testing:  21%|██▏       | 100/469 [00:04<00:14, 24.66it/s]
Testing:  22%|██▏       | 103/469 [00:04<00:14, 24.50it/s]
Testing:  23%|██▎       | 106/469 [00:04<00:14, 25.10it/s]
Testing:  23%|██▎       | 109/469 [00:04<00:14, 25.59it/s]
Testing:  24%|██▍       | 112/469 [00:04<00:14, 25.45it/s]
Testing:  25%|██▍       | 115/469 [00:04<00:14, 24.66it/s]
Testing:  25%|██▌       | 118/469 [00:04<00:15, 23.21it/s]
Testing:  26%|██▌       | 121/469 [00:04<00:14, 23.90it/s]
Testing:  26%|██▋       | 124/469 [00:05<00:14, 24.46it/s]
Testing:  27%|██▋       | 127/469 [00:05<00:13, 25.15it/s]
Testing:  28%|██▊       | 130/469 [00:05<00:13, 24.41it/s]
Testing:  28%|██▊       | 133/469 [00:05<00:13, 24.26it/s]
Testing:  29%|██▉       | 136/469 [00:05<00:13, 25.28it/s]
Testing:  30%|██▉       | 139/469 [00:05<00:12, 25.98it/s]
Testing:  30%|███       | 142/469 [00:05<00:12, 25.63it/s]
Testing:  31%|███       | 145/469 [00:05<00:12, 25.17it/s]
Testing:  32%|███▏      | 148/469 [00:05<00:12, 25.48it/s]
Testing:  32%|███▏      | 151/469 [00:06<00:12, 24.84it/s]
Testing:  33%|███▎      | 154/469 [00:06<00:12, 25.59it/s]
Testing:  33%|███▎      | 157/469 [00:06<00:11, 26.11it/s]
Testing:  34%|███▍      | 160/469 [00:06<00:11, 26.15it/s]
Testing:  35%|███▍      | 163/469 [00:06<00:11, 26.56it/s]
Testing:  35%|███▌      | 166/469 [00:06<00:11, 26.65it/s]
Testing:  36%|███▌      | 169/469 [00:06<00:11, 26.26it/s]
Testing:  37%|███▋      | 172/469 [00:06<00:11, 25.85it/s]
Testing:  37%|███▋      | 175/469 [00:07<00:11, 26.38it/s]
Testing:  38%|███▊      | 178/469 [00:07<00:11, 25.85it/s]
Testing:  39%|███▊      | 181/469 [00:07<00:11, 25.56it/s]
Testing:  39%|███▉      | 184/469 [00:07<00:11, 25.29it/s]
Testing:  40%|███▉      | 187/469 [00:07<00:10, 25.78it/s]
Testing:  41%|████      | 190/469 [00:07<00:10, 26.15it/s]
Testing:  41%|████      | 193/469 [00:07<00:11, 24.53it/s]
Testing:  42%|████▏     | 196/469 [00:07<00:10, 24.85it/s]
Testing:  42%|████▏     | 199/469 [00:07<00:11, 24.38it/s]
Testing:  43%|████▎     | 202/469 [00:08<00:11, 24.09it/s]
Testing:  44%|████▎     | 205/469 [00:08<00:10, 24.19it/s]
Testing:  44%|████▍     | 208/469 [00:08<00:10, 24.72it/s]
Testing:  45%|████▍     | 211/469 [00:08<00:10, 23.67it/s]
Testing:  46%|████▌     | 214/469 [00:08<00:10, 23.94it/s]
Testing:  46%|████▋     | 217/469 [00:08<00:10, 24.28it/s]
Testing:  47%|████▋     | 220/469 [00:08<00:09, 25.32it/s]
Testing:  48%|████▊     | 223/469 [00:08<00:09, 25.84it/s]
Testing:  48%|████▊     | 226/469 [00:09<00:09, 25.38it/s]
Testing:  49%|████▉     | 229/469 [00:09<00:09, 26.14it/s]
Testing:  49%|████▉     | 232/469 [00:09<00:09, 25.51it/s]
Testing:  50%|█████     | 235/469 [00:09<00:09, 24.62it/s]
Testing:  51%|█████     | 238/469 [00:09<00:09, 25.04it/s]
Testing:  51%|█████▏    | 241/469 [00:09<00:08, 25.73it/s]
Testing:  52%|█████▏    | 244/469 [00:09<00:08, 25.75it/s]
Testing:  53%|█████▎    | 247/469 [00:09<00:08, 26.57it/s]
Testing:  53%|█████▎    | 250/469 [00:09<00:08, 26.75it/s]
Testing:  54%|█████▍    | 253/469 [00:10<00:08, 25.37it/s]
Testing:  55%|█████▍    | 256/469 [00:10<00:08, 26.32it/s]
Testing:  55%|█████▌    | 259/469 [00:10<00:07, 26.60it/s]
Testing:  56%|█████▌    | 262/469 [00:10<00:08, 25.80it/s]
Testing:  57%|█████▋    | 265/469 [00:10<00:08, 25.37it/s]
Testing:  57%|█████▋    | 268/469 [00:10<00:07, 25.58it/s]
Testing:  58%|█████▊    | 271/469 [00:10<00:07, 25.83it/s]
Testing:  58%|█████▊    | 274/469 [00:10<00:07, 26.17it/s]
Testing:  59%|█████▉    | 277/469 [00:11<00:07, 26.30it/s]
Testing:  60%|█████▉    | 280/469 [00:11<00:07, 26.66it/s]
Testing:  60%|██████    | 283/469 [00:11<00:07, 25.99it/s]
Testing:  61%|██████    | 286/469 [00:11<00:06, 26.53it/s]
Testing:  62%|██████▏   | 289/469 [00:11<00:06, 25.88it/s]
Testing:  62%|██████▏   | 292/469 [00:11<00:06, 25.71it/s]
Testing:  63%|██████▎   | 295/469 [00:11<00:06, 25.82it/s]
Testing:  64%|██████▎   | 298/469 [00:11<00:07, 24.42it/s]
Testing:  64%|██████▍   | 301/469 [00:11<00:06, 24.47it/s]
Testing:  65%|██████▍   | 304/469 [00:12<00:06, 25.51it/s]
Testing:  65%|██████▌   | 307/469 [00:12<00:06, 24.94it/s]
Testing:  66%|██████▌   | 310/469 [00:12<00:06, 25.81it/s]
Testing:  67%|██████▋   | 313/469 [00:12<00:05, 26.45it/s]
Testing:  67%|██████▋   | 316/469 [00:12<00:05, 26.44it/s]
Testing:  68%|██████▊   | 319/469 [00:12<00:05, 26.30it/s]
Testing:  69%|██████▊   | 322/469 [00:12<00:05, 26.78it/s]
Testing:  69%|██████▉   | 325/469 [00:12<00:05, 26.12it/s]
Testing:  70%|██████▉   | 328/469 [00:12<00:05, 26.63it/s]
Testing:  71%|███████   | 331/469 [00:13<00:05, 26.40it/s]
Testing:  71%|███████   | 334/469 [00:13<00:04, 27.20it/s]
Testing:  72%|███████▏  | 337/469 [00:13<00:05, 25.85it/s]
Testing:  72%|███████▏  | 340/469 [00:13<00:05, 23.51it/s]
Testing:  73%|███████▎  | 343/469 [00:13<00:05, 23.78it/s]
Testing:  74%|███████▍  | 346/469 [00:13<00:05, 24.53it/s]
Testing:  74%|███████▍  | 349/469 [00:13<00:04, 24.05it/s]
Testing:  75%|███████▌  | 352/469 [00:13<00:04, 23.86it/s]
Testing:  76%|███████▌  | 355/469 [00:14<00:04, 24.54it/s]
Testing:  76%|███████▋  | 358/469 [00:14<00:04, 24.87it/s]
Testing:  77%|███████▋  | 361/469 [00:14<00:04, 25.04it/s]
Testing:  78%|███████▊  | 364/469 [00:14<00:04, 24.61it/s]
Testing:  78%|███████▊  | 367/469 [00:14<00:04, 24.90it/s]
Testing:  79%|███████▉  | 370/469 [00:14<00:03, 25.02it/s]
Testing:  80%|███████▉  | 373/469 [00:14<00:03, 25.06it/s]
Testing:  80%|████████  | 376/469 [00:14<00:03, 24.41it/s]
Testing:  81%|████████  | 379/469 [00:15<00:03, 24.78it/s]
Testing:  81%|████████▏ | 382/469 [00:15<00:03, 24.45it/s]
Testing:  82%|████████▏ | 385/469 [00:15<00:03, 24.64it/s]
Testing:  83%|████████▎ | 388/469 [00:15<00:03, 25.34it/s]
Testing:  83%|████████▎ | 391/469 [00:15<00:03, 25.80it/s]
Testing:  84%|████████▍ | 394/469 [00:15<00:02, 25.37it/s]
Testing:  85%|████████▍ | 397/469 [00:15<00:02, 24.42it/s]
Testing:  85%|████████▌ | 400/469 [00:15<00:02, 24.06it/s]
Testing:  86%|████████▌ | 403/469 [00:16<00:02, 24.41it/s]
Testing:  87%|████████▋ | 406/469 [00:16<00:02, 24.86it/s]
Testing:  87%|████████▋ | 409/469 [00:16<00:02, 24.66it/s]
Testing:  88%|████████▊ | 412/469 [00:16<00:02, 24.39it/s]
Testing:  88%|████████▊ | 415/469 [00:16<00:02, 24.52it/s]
Testing:  89%|████████▉ | 418/469 [00:16<00:02, 23.13it/s]
Testing:  90%|████████▉ | 421/469 [00:16<00:01, 24.13it/s]
Testing:  90%|█████████ | 424/469 [00:16<00:01, 24.66it/s]
Testing:  91%|█████████ | 427/469 [00:17<00:01, 24.88it/s]
Testing:  92%|█████████▏| 430/469 [00:17<00:01, 24.83it/s]
Testing:  92%|█████████▏| 433/469 [00:17<00:01, 24.35it/s]
Testing:  93%|█████████▎| 436/469 [00:17<00:01, 24.79it/s]
Testing:  94%|█████████▎| 439/469 [00:17<00:01, 25.31it/s]
Testing:  94%|█████████▍| 442/469 [00:17<00:01, 24.97it/s]
Testing:  95%|█████████▍| 445/469 [00:17<00:00, 25.03it/s]
Testing:  96%|█████████▌| 448/469 [00:17<00:00, 25.93it/s]
Testing:  96%|█████████▌| 451/469 [00:17<00:00, 23.67it/s]
Testing:  97%|█████████▋| 454/469 [00:18<00:00, 22.15it/s]
Testing:  97%|█████████▋| 457/469 [00:18<00:00, 22.86it/s]
Testing:  98%|█████████▊| 460/469 [00:18<00:00, 24.14it/s]
Testing:  99%|█████████▊| 463/469 [00:18<00:00, 23.77it/s]
Testing:  99%|█████████▉| 466/469 [00:18<00:00, 24.49it/s]
Testing: 100%|██████████| 469/469 [00:18<00:00, 25.64it/s]--------------------------------------------------------------------------------
DATALOADER:0 TEST RESULTS
{'test_rmse': 0.5377797484397888}
--------------------------------------------------------------------------------

Testing: 100%|██████████| 469/469 [00:18<00:00, 25.02it/s]
  0%|          | 0/469 [02:49<?, ?it/s]
Global seed set to 49

['p_np'] False
2 1
iupac_vocab_size: 1491
training... 1491

  0%|          | 0/469 [00:00<?, ?it/s]Some weights of the model checkpoint at checkpoints/iupac were not used when initializing GPT2ForSequenceClassification: ['lm_head.weight']
- This IS expected if you are initializing GPT2ForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing GPT2ForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
GPU available: True, used: True
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]

  | Name        | Type                          | Params
--------------------------------------------------------------
0 | transformer | GPT2ForSequenceClassification | 7.1 M 
--------------------------------------------------------------
75.9 K    Trainable params
7.0 M     Non-trainable params
7.1 M     Total params
28.416    Total estimated model params size (MB)

Validation sanity check: 0it [00:00, ?it/s]
Validation sanity check:   0%|          | 0/2 [00:00<?, ?it/s]
                                                              Global seed set to 49


Training: 0it [00:00, ?it/s]
Training:   0%|          | 0/938 [00:00<?, ?it/s]
Epoch 0:   0%|          | 0/938 [00:00<?, ?it/s] 
Epoch 0:   0%|          | 1/938 [00:00<01:35,  9.86it/s]
Epoch 0:   0%|          | 1/938 [00:00<01:35,  9.83it/s, loss=3.77, v_num=15]
Epoch 0:   0%|          | 2/938 [00:00<01:15, 12.35it/s, loss=3.75, v_num=15]
Epoch 0:   0%|          | 3/938 [00:00<01:10, 13.19it/s, loss=3.75, v_num=15]
Epoch 0:   0%|          | 3/938 [00:00<01:11, 13.17it/s, loss=3.8, v_num=15] 
Epoch 0:   0%|          | 4/938 [00:00<01:08, 13.67it/s, loss=3.8, v_num=15]
Epoch 0:   1%|          | 5/938 [00:00<01:14, 12.53it/s, loss=3.8, v_num=15]
Epoch 0:   1%|          | 5/938 [00:00<01:14, 12.51it/s, loss=3.75, v_num=15]
Epoch 0:   1%|          | 6/938 [00:00<01:13, 12.68it/s, loss=3.72, v_num=15]
Epoch 0:   1%|          | 7/938 [00:00<01:11, 13.08it/s, loss=3.72, v_num=15]
Epoch 0:   1%|          | 7/938 [00:00<01:11, 13.07it/s, loss=3.7, v_num=15] 
Epoch 0:   1%|          | 8/938 [00:00<01:11, 13.00it/s, loss=3.75, v_num=15]
Epoch 0:   1%|          | 9/938 [00:00<01:10, 13.10it/s, loss=3.75, v_num=15]
Epoch 0:   1%|          | 9/938 [00:00<01:10, 13.09it/s, loss=3.68, v_num=15]
Epoch 0:   1%|          | 10/938 [00:00<01:11, 12.96it/s, loss=3.67, v_num=15]
Epoch 0:   1%|          | 11/938 [00:00<01:11, 12.95it/s, loss=3.67, v_num=15]
Epoch 0:   1%|          | 11/938 [00:00<01:11, 12.95it/s, loss=3.68, v_num=15]
Epoch 0:   1%|▏         | 12/938 [00:00<01:10, 13.22it/s, loss=3.63, v_num=15]
Epoch 0:   1%|▏         | 13/938 [00:00<01:09, 13.37it/s, loss=3.63, v_num=15]
Epoch 0:   1%|▏         | 13/938 [00:00<01:09, 13.37it/s, loss=3.59, v_num=15]
Epoch 0:   1%|▏         | 14/938 [00:01<01:08, 13.40it/s, loss=3.55, v_num=15]
Epoch 0:   2%|▏         | 15/938 [00:01<01:08, 13.49it/s, loss=3.55, v_num=15]
Epoch 0:   2%|▏         | 15/938 [00:01<01:08, 13.49it/s, loss=3.53, v_num=15]
Epoch 0:   2%|▏         | 16/938 [00:01<01:09, 13.30it/s, loss=3.49, v_num=15]
Epoch 0:   2%|▏         | 17/938 [00:01<01:09, 13.19it/s, loss=3.49, v_num=15]
Epoch 0:   2%|▏         | 17/938 [00:01<01:09, 13.19it/s, loss=3.47, v_num=15]
Epoch 0:   2%|▏         | 18/938 [00:01<01:09, 13.19it/s, loss=3.42, v_num=15]
Epoch 0:   2%|▏         | 19/938 [00:01<01:08, 13.36it/s, loss=3.42, v_num=15]
Epoch 0:   2%|▏         | 19/938 [00:01<01:08, 13.35it/s, loss=3.38, v_num=15]
Epoch 0:   2%|▏         | 20/938 [00:01<01:08, 13.43it/s, loss=3.32, v_num=15]
Epoch 0:   2%|▏         | 21/938 [00:01<01:07, 13.50it/s, loss=3.32, v_num=15]
Epoch 0:   2%|▏         | 21/938 [00:01<01:07, 13.49it/s, loss=3.25, v_num=15]
Epoch 0:   2%|▏         | 22/938 [00:01<01:07, 13.52it/s, loss=3.18, v_num=15]
Epoch 0:   2%|▏         | 23/938 [00:01<01:09, 13.14it/s, loss=3.18, v_num=15]
Epoch 0:   2%|▏         | 23/938 [00:01<01:09, 13.14it/s, loss=3.08, v_num=15]
Epoch 0:   3%|▎         | 24/938 [00:01<01:09, 13.08it/s, loss=3, v_num=15]   
Epoch 0:   3%|▎         | 25/938 [00:01<01:09, 13.20it/s, loss=3, v_num=15]
Epoch 0:   3%|▎         | 25/938 [00:01<01:09, 13.20it/s, loss=2.91, v_num=15]
Epoch 0:   3%|▎         | 26/938 [00:01<01:08, 13.23it/s, loss=2.83, v_num=15]
Epoch 0:   3%|▎         | 27/938 [00:02<01:08, 13.26it/s, loss=2.83, v_num=15]
Epoch 0:   3%|▎         | 27/938 [00:02<01:08, 13.26it/s, loss=2.75, v_num=15]
Epoch 0:   3%|▎         | 28/938 [00:02<01:08, 13.32it/s, loss=2.62, v_num=15]
Epoch 0:   3%|▎         | 29/938 [00:02<01:08, 13.35it/s, loss=2.62, v_num=15]
Epoch 0:   3%|▎         | 29/938 [00:02<01:08, 13.35it/s, loss=2.54, v_num=15]
Epoch 0:   3%|▎         | 30/938 [00:02<01:07, 13.40it/s, loss=2.46, v_num=15]
Epoch 0:   3%|▎         | 31/938 [00:02<01:07, 13.42it/s, loss=2.46, v_num=15]
Epoch 0:   3%|▎         | 31/938 [00:02<01:07, 13.42it/s, loss=2.36, v_num=15]
Epoch 0:   3%|▎         | 32/938 [00:02<01:07, 13.45it/s, loss=2.3, v_num=15] 
Epoch 0:   4%|▎         | 33/938 [00:02<01:07, 13.47it/s, loss=2.3, v_num=15]
Epoch 0:   4%|▎         | 33/938 [00:02<01:07, 13.47it/s, loss=2.24, v_num=15]
Epoch 0:   4%|▎         | 34/938 [00:02<01:06, 13.55it/s, loss=2.18, v_num=15]
Epoch 0:   4%|▎         | 35/938 [00:02<01:07, 13.34it/s, loss=2.18, v_num=15]
Epoch 0:   4%|▎         | 35/938 [00:02<01:07, 13.33it/s, loss=2.11, v_num=15]
Epoch 0:   4%|▍         | 36/938 [00:02<01:07, 13.37it/s, loss=2.06, v_num=15]
Epoch 0:   4%|▍         | 37/938 [00:02<01:07, 13.35it/s, loss=2.06, v_num=15]
Epoch 0:   4%|▍         | 37/938 [00:02<01:07, 13.35it/s, loss=1.99, v_num=15]
Epoch 0:   4%|▍         | 38/938 [00:02<01:07, 13.24it/s, loss=1.94, v_num=15]
Epoch 0:   4%|▍         | 39/938 [00:02<01:07, 13.29it/s, loss=1.94, v_num=15]
Epoch 0:   4%|▍         | 39/938 [00:02<01:07, 13.28it/s, loss=1.89, v_num=15]
Epoch 0:   4%|▍         | 40/938 [00:02<01:07, 13.36it/s, loss=1.87, v_num=15]
Epoch 0:   4%|▍         | 41/938 [00:03<01:07, 13.36it/s, loss=1.87, v_num=15]
Epoch 0:   4%|▍         | 41/938 [00:03<01:07, 13.36it/s, loss=1.83, v_num=15]
Epoch 0:   4%|▍         | 42/938 [00:03<01:07, 13.30it/s, loss=1.79, v_num=15]
Epoch 0:   5%|▍         | 43/938 [00:03<01:07, 13.31it/s, loss=1.79, v_num=15]
Epoch 0:   5%|▍         | 43/938 [00:03<01:07, 13.30it/s, loss=1.78, v_num=15]
Epoch 0:   5%|▍         | 44/938 [00:03<01:07, 13.30it/s, loss=1.76, v_num=15]
Epoch 0:   5%|▍         | 45/938 [00:03<01:06, 13.36it/s, loss=1.76, v_num=15]
Epoch 0:   5%|▍         | 45/938 [00:03<01:06, 13.36it/s, loss=1.75, v_num=15]
Epoch 0:   5%|▍         | 46/938 [00:03<01:06, 13.43it/s, loss=1.75, v_num=15]
Epoch 0:   5%|▌         | 47/938 [00:03<01:06, 13.49it/s, loss=1.75, v_num=15]
Epoch 0:   5%|▌         | 47/938 [00:03<01:06, 13.49it/s, loss=1.74, v_num=15]
Epoch 0:   5%|▌         | 48/938 [00:03<01:05, 13.49it/s, loss=1.76, v_num=15]
Epoch 0:   5%|▌         | 49/938 [00:03<01:05, 13.53it/s, loss=1.76, v_num=15]
Epoch 0:   5%|▌         | 49/938 [00:03<01:05, 13.53it/s, loss=1.74, v_num=15]
Epoch 0:   5%|▌         | 50/938 [00:03<01:05, 13.54it/s, loss=1.75, v_num=15]
Epoch 0:   5%|▌         | 51/938 [00:03<01:05, 13.53it/s, loss=1.75, v_num=15]
Epoch 0:   5%|▌         | 51/938 [00:03<01:05, 13.53it/s, loss=1.74, v_num=15]
Epoch 0:   6%|▌         | 52/938 [00:03<01:05, 13.59it/s, loss=1.72, v_num=15]
Epoch 0:   6%|▌         | 53/938 [00:03<01:05, 13.60it/s, loss=1.72, v_num=15]
Epoch 0:   6%|▌         | 53/938 [00:03<01:05, 13.60it/s, loss=1.71, v_num=15]
Epoch 0:   6%|▌         | 54/938 [00:03<01:05, 13.58it/s, loss=1.71, v_num=15]
Epoch 0:   6%|▌         | 55/938 [00:04<01:05, 13.55it/s, loss=1.71, v_num=15]
Epoch 0:   6%|▌         | 55/938 [00:04<01:05, 13.54it/s, loss=1.69, v_num=15]
Epoch 0:   6%|▌         | 56/938 [00:04<01:04, 13.59it/s, loss=1.67, v_num=15]
Epoch 0:   6%|▌         | 57/938 [00:04<01:04, 13.56it/s, loss=1.67, v_num=15]
Epoch 0:   6%|▌         | 57/938 [00:04<01:04, 13.56it/s, loss=1.67, v_num=15]
Epoch 0:   6%|▌         | 58/938 [00:04<01:04, 13.58it/s, loss=1.67, v_num=15]
Epoch 0:   6%|▋         | 59/938 [00:04<01:04, 13.60it/s, loss=1.67, v_num=15]
Epoch 0:   6%|▋         | 59/938 [00:04<01:04, 13.60it/s, loss=1.67, v_num=15]
Epoch 0:   6%|▋         | 60/938 [00:04<01:04, 13.64it/s, loss=1.69, v_num=15]
Epoch 0:   7%|▋         | 61/938 [00:04<01:04, 13.63it/s, loss=1.69, v_num=15]
Epoch 0:   7%|▋         | 61/938 [00:04<01:04, 13.63it/s, loss=1.68, v_num=15]
Epoch 0:   7%|▋         | 62/938 [00:04<01:04, 13.65it/s, loss=1.68, v_num=15]
Epoch 0:   7%|▋         | 63/938 [00:04<01:03, 13.69it/s, loss=1.68, v_num=15]
Epoch 0:   7%|▋         | 63/938 [00:04<01:03, 13.69it/s, loss=1.68, v_num=15]
Epoch 0:   7%|▋         | 64/938 [00:04<01:03, 13.70it/s, loss=1.67, v_num=15]
Epoch 0:   7%|▋         | 65/938 [00:04<01:03, 13.72it/s, loss=1.67, v_num=15]
Epoch 0:   7%|▋         | 65/938 [00:04<01:03, 13.71it/s, loss=1.68, v_num=15]
Epoch 0:   7%|▋         | 66/938 [00:04<01:04, 13.53it/s, loss=1.68, v_num=15]
Epoch 0:   7%|▋         | 67/938 [00:04<01:04, 13.56it/s, loss=1.68, v_num=15]
Epoch 0:   7%|▋         | 67/938 [00:04<01:04, 13.56it/s, loss=1.67, v_num=15]
Epoch 0:   7%|▋         | 68/938 [00:05<01:04, 13.57it/s, loss=1.66, v_num=15]
Epoch 0:   7%|▋         | 69/938 [00:05<01:04, 13.54it/s, loss=1.66, v_num=15]
Epoch 0:   7%|▋         | 69/938 [00:05<01:04, 13.53it/s, loss=1.68, v_num=15]
Epoch 0:   7%|▋         | 70/938 [00:05<01:04, 13.53it/s, loss=1.66, v_num=15]
Epoch 0:   8%|▊         | 71/938 [00:05<01:04, 13.54it/s, loss=1.66, v_num=15]
Epoch 0:   8%|▊         | 71/938 [00:05<01:04, 13.53it/s, loss=1.68, v_num=15]
Epoch 0:   8%|▊         | 72/938 [00:05<01:03, 13.55it/s, loss=1.69, v_num=15]
Epoch 0:   8%|▊         | 73/938 [00:05<01:03, 13.55it/s, loss=1.69, v_num=15]
Epoch 0:   8%|▊         | 73/938 [00:05<01:03, 13.55it/s, loss=1.69, v_num=15]
Epoch 0:   8%|▊         | 74/938 [00:05<01:03, 13.57it/s, loss=1.66, v_num=15]
Epoch 0:   8%|▊         | 75/938 [00:05<01:03, 13.55it/s, loss=1.66, v_num=15]
Epoch 0:   8%|▊         | 75/938 [00:05<01:03, 13.54it/s, loss=1.69, v_num=15]
Epoch 0:   8%|▊         | 76/938 [00:05<01:03, 13.58it/s, loss=1.69, v_num=15]
Epoch 0:   8%|▊         | 77/938 [00:05<01:03, 13.56it/s, loss=1.69, v_num=15]
Epoch 0:   8%|▊         | 77/938 [00:05<01:03, 13.56it/s, loss=1.69, v_num=15]
Epoch 0:   8%|▊         | 78/938 [00:05<01:03, 13.55it/s, loss=1.69, v_num=15]
Epoch 0:   8%|▊         | 79/938 [00:05<01:03, 13.51it/s, loss=1.69, v_num=15]
Epoch 0:   8%|▊         | 79/938 [00:05<01:03, 13.51it/s, loss=1.69, v_num=15]
Epoch 0:   9%|▊         | 80/938 [00:05<01:03, 13.54it/s, loss=1.68, v_num=15]
Epoch 0:   9%|▊         | 81/938 [00:05<01:03, 13.53it/s, loss=1.68, v_num=15]
Epoch 0:   9%|▊         | 81/938 [00:05<01:03, 13.53it/s, loss=1.68, v_num=15]
Epoch 0:   9%|▊         | 82/938 [00:06<01:03, 13.54it/s, loss=1.69, v_num=15]
Epoch 0:   9%|▉         | 83/938 [00:06<01:03, 13.53it/s, loss=1.69, v_num=15]
Epoch 0:   9%|▉         | 83/938 [00:06<01:03, 13.53it/s, loss=1.67, v_num=15]
Epoch 0:   9%|▉         | 84/938 [00:06<01:03, 13.55it/s, loss=1.68, v_num=15]
Epoch 0:   9%|▉         | 85/938 [00:06<01:02, 13.57it/s, loss=1.68, v_num=15]
Epoch 0:   9%|▉         | 85/938 [00:06<01:02, 13.57it/s, loss=1.69, v_num=15]
Epoch 0:   9%|▉         | 86/938 [00:06<01:02, 13.55it/s, loss=1.68, v_num=15]
Epoch 0:   9%|▉         | 87/938 [00:06<01:02, 13.58it/s, loss=1.68, v_num=15]
Epoch 0:   9%|▉         | 87/938 [00:06<01:02, 13.58it/s, loss=1.68, v_num=15]
Epoch 0:   9%|▉         | 88/938 [00:06<01:02, 13.58it/s, loss=1.68, v_num=15]
Epoch 0:   9%|▉         | 89/938 [00:06<01:02, 13.60it/s, loss=1.68, v_num=15]
Epoch 0:   9%|▉         | 89/938 [00:06<01:02, 13.60it/s, loss=1.68, v_num=15]
Epoch 0:  10%|▉         | 90/938 [00:06<01:02, 13.57it/s, loss=1.69, v_num=15]
Epoch 0:  10%|▉         | 91/938 [00:06<01:02, 13.57it/s, loss=1.69, v_num=15]
Epoch 0:  10%|▉         | 91/938 [00:06<01:02, 13.56it/s, loss=1.68, v_num=15]
Epoch 0:  10%|▉         | 92/938 [00:06<01:02, 13.59it/s, loss=1.68, v_num=15]
Epoch 0:  10%|▉         | 93/938 [00:06<01:02, 13.59it/s, loss=1.68, v_num=15]
Epoch 0:  10%|▉         | 93/938 [00:06<01:02, 13.59it/s, loss=1.68, v_num=15]
Epoch 0:  10%|█         | 94/938 [00:06<01:01, 13.62it/s, loss=1.68, v_num=15]
Epoch 0:  10%|█         | 95/938 [00:06<01:01, 13.61it/s, loss=1.68, v_num=15]
Epoch 0:  10%|█         | 95/938 [00:06<01:01, 13.60it/s, loss=1.66, v_num=15]
Epoch 0:  10%|█         | 96/938 [00:07<01:01, 13.63it/s, loss=1.67, v_num=15]
Epoch 0:  10%|█         | 97/938 [00:07<01:01, 13.65it/s, loss=1.67, v_num=15]
Epoch 0:  10%|█         | 97/938 [00:07<01:01, 13.65it/s, loss=1.68, v_num=15]
Epoch 0:  10%|█         | 98/938 [00:07<01:01, 13.65it/s, loss=1.66, v_num=15]
Epoch 0:  11%|█         | 99/938 [00:07<01:01, 13.65it/s, loss=1.66, v_num=15]
Epoch 0:  11%|█         | 99/938 [00:07<01:01, 13.65it/s, loss=1.66, v_num=15]
Epoch 0:  11%|█         | 100/938 [00:07<01:01, 13.68it/s, loss=1.65, v_num=15]
Epoch 0:  11%|█         | 101/938 [00:07<01:01, 13.69it/s, loss=1.65, v_num=15]
Epoch 0:  11%|█         | 101/938 [00:07<01:01, 13.69it/s, loss=1.66, v_num=15]
Epoch 0:  11%|█         | 102/938 [00:07<01:01, 13.68it/s, loss=1.65, v_num=15]
Epoch 0:  11%|█         | 103/938 [00:07<01:00, 13.69it/s, loss=1.65, v_num=15]
Epoch 0:  11%|█         | 103/938 [00:07<01:00, 13.69it/s, loss=1.64, v_num=15]
Epoch 0:  11%|█         | 104/938 [00:07<01:00, 13.70it/s, loss=1.63, v_num=15]
Epoch 0:  11%|█         | 105/938 [00:07<01:00, 13.72it/s, loss=1.63, v_num=15]
Epoch 0:  11%|█         | 105/938 [00:07<01:00, 13.72it/s, loss=1.6, v_num=15] 
Epoch 0:  11%|█▏        | 106/938 [00:07<01:00, 13.75it/s, loss=1.57, v_num=15]
Epoch 0:  11%|█▏        | 107/938 [00:07<01:00, 13.78it/s, loss=1.57, v_num=15]
Epoch 0:  11%|█▏        | 107/938 [00:07<01:00, 13.78it/s, loss=1.55, v_num=15]
Epoch 0:  12%|█▏        | 108/938 [00:07<01:00, 13.76it/s, loss=1.54, v_num=15]
Epoch 0:  12%|█▏        | 109/938 [00:07<01:00, 13.77it/s, loss=1.54, v_num=15]
Epoch 0:  12%|█▏        | 109/938 [00:07<01:00, 13.77it/s, loss=1.49, v_num=15]
Epoch 0:  12%|█▏        | 110/938 [00:07<01:00, 13.76it/s, loss=1.45, v_num=15]
Epoch 0:  12%|█▏        | 111/938 [00:08<01:00, 13.71it/s, loss=1.45, v_num=15]
Epoch 0:  12%|█▏        | 111/938 [00:08<01:00, 13.71it/s, loss=1.43, v_num=15]
Epoch 0:  12%|█▏        | 112/938 [00:08<01:00, 13.70it/s, loss=1.42, v_num=15]
Epoch 0:  12%|█▏        | 113/938 [00:08<01:00, 13.69it/s, loss=1.42, v_num=15]
Epoch 0:  12%|█▏        | 113/938 [00:08<01:00, 13.69it/s, loss=1.39, v_num=15]
Epoch 0:  12%|█▏        | 114/938 [00:08<01:00, 13.71it/s, loss=1.4, v_num=15] 
Epoch 0:  12%|█▏        | 115/938 [00:08<01:00, 13.69it/s, loss=1.4, v_num=15]
Epoch 0:  12%|█▏        | 115/938 [00:08<01:00, 13.69it/s, loss=1.38, v_num=15]
Epoch 0:  12%|█▏        | 116/938 [00:08<01:00, 13.70it/s, loss=1.35, v_num=15]
Epoch 0:  12%|█▏        | 117/938 [00:08<00:59, 13.70it/s, loss=1.35, v_num=15]
Epoch 0:  12%|█▏        | 117/938 [00:08<00:59, 13.70it/s, loss=1.33, v_num=15]
Epoch 0:  13%|█▎        | 118/938 [00:08<00:59, 13.69it/s, loss=1.32, v_num=15]
Epoch 0:  13%|█▎        | 119/938 [00:08<00:59, 13.68it/s, loss=1.32, v_num=15]
Epoch 0:  13%|█▎        | 119/938 [00:08<00:59, 13.68it/s, loss=1.29, v_num=15]
Epoch 0:  13%|█▎        | 120/938 [00:08<00:59, 13.71it/s, loss=1.26, v_num=15]
Epoch 0:  13%|█▎        | 121/938 [00:08<00:59, 13.67it/s, loss=1.26, v_num=15]
Epoch 0:  13%|█▎        | 121/938 [00:08<00:59, 13.67it/s, loss=1.23, v_num=15]
Epoch 0:  13%|█▎        | 122/938 [00:08<00:59, 13.69it/s, loss=1.23, v_num=15]
Epoch 0:  13%|█▎        | 123/938 [00:08<00:59, 13.70it/s, loss=1.23, v_num=15]
Epoch 0:  13%|█▎        | 123/938 [00:08<00:59, 13.70it/s, loss=1.2, v_num=15] 
Epoch 0:  13%|█▎        | 124/938 [00:09<00:59, 13.72it/s, loss=1.17, v_num=15]
Epoch 0:  13%|█▎        | 125/938 [00:09<00:59, 13.70it/s, loss=1.17, v_num=15]
Epoch 0:  13%|█▎        | 125/938 [00:09<00:59, 13.70it/s, loss=1.17, v_num=15]
Epoch 0:  13%|█▎        | 126/938 [00:09<00:59, 13.71it/s, loss=1.18, v_num=15]
Epoch 0:  14%|█▎        | 127/938 [00:09<00:59, 13.71it/s, loss=1.18, v_num=15]
Epoch 0:  14%|█▎        | 127/938 [00:09<00:59, 13.71it/s, loss=1.17, v_num=15]
Epoch 0:  14%|█▎        | 128/938 [00:09<00:59, 13.72it/s, loss=1.18, v_num=15]
Epoch 0:  14%|█▍        | 129/938 [00:09<00:58, 13.73it/s, loss=1.18, v_num=15]
Epoch 0:  14%|█▍        | 129/938 [00:09<00:58, 13.73it/s, loss=1.18, v_num=15]
Epoch 0:  14%|█▍        | 130/938 [00:09<00:58, 13.73it/s, loss=1.18, v_num=15]
Epoch 0:  14%|█▍        | 131/938 [00:09<00:58, 13.74it/s, loss=1.18, v_num=15]
Epoch 0:  14%|█▍        | 131/938 [00:09<00:58, 13.74it/s, loss=1.16, v_num=15]
Epoch 0:  14%|█▍        | 132/938 [00:09<00:58, 13.75it/s, loss=1.15, v_num=15]
Epoch 0:  14%|█▍        | 133/938 [00:09<00:58, 13.76it/s, loss=1.15, v_num=15]
Epoch 0:  14%|█▍        | 133/938 [00:09<00:58, 13.76it/s, loss=1.15, v_num=15]
Epoch 0:  14%|█▍        | 134/938 [00:09<00:58, 13.78it/s, loss=1.13, v_num=15]
Epoch 0:  14%|█▍        | 135/938 [00:09<00:58, 13.78it/s, loss=1.13, v_num=15]
Epoch 0:  14%|█▍        | 135/938 [00:09<00:58, 13.78it/s, loss=1.12, v_num=15]
Epoch 0:  14%|█▍        | 136/938 [00:09<00:58, 13.78it/s, loss=1.12, v_num=15]
Epoch 0:  15%|█▍        | 137/938 [00:09<00:58, 13.79it/s, loss=1.12, v_num=15]
Epoch 0:  15%|█▍        | 137/938 [00:09<00:58, 13.79it/s, loss=1.12, v_num=15]
Epoch 0:  15%|█▍        | 138/938 [00:10<00:58, 13.78it/s, loss=1.11, v_num=15]
Epoch 0:  15%|█▍        | 139/938 [00:10<00:57, 13.78it/s, loss=1.11, v_num=15]
Epoch 0:  15%|█▍        | 139/938 [00:10<00:57, 13.78it/s, loss=1.1, v_num=15] 
Epoch 0:  15%|█▍        | 140/938 [00:10<00:57, 13.79it/s, loss=1.11, v_num=15]
Epoch 0:  15%|█▌        | 141/938 [00:10<00:57, 13.78it/s, loss=1.11, v_num=15]
Epoch 0:  15%|█▌        | 141/938 [00:10<00:57, 13.77it/s, loss=1.09, v_num=15]
Epoch 0:  15%|█▌        | 142/938 [00:10<00:57, 13.77it/s, loss=1.09, v_num=15]
Epoch 0:  15%|█▌        | 143/938 [00:10<00:57, 13.75it/s, loss=1.09, v_num=15]
Epoch 0:  15%|█▌        | 143/938 [00:10<00:57, 13.75it/s, loss=1.08, v_num=15]
Epoch 0:  15%|█▌        | 144/938 [00:10<00:57, 13.74it/s, loss=1.09, v_num=15]
Epoch 0:  15%|█▌        | 145/938 [00:10<00:57, 13.76it/s, loss=1.09, v_num=15]
Epoch 0:  15%|█▌        | 145/938 [00:10<00:57, 13.76it/s, loss=1.08, v_num=15]
Epoch 0:  16%|█▌        | 146/938 [00:10<00:57, 13.77it/s, loss=1.07, v_num=15]
Epoch 0:  16%|█▌        | 147/938 [00:10<00:57, 13.78it/s, loss=1.07, v_num=15]
Epoch 0:  16%|█▌        | 147/938 [00:10<00:57, 13.78it/s, loss=1.08, v_num=15]
Epoch 0:  16%|█▌        | 148/938 [00:10<00:57, 13.79it/s, loss=1.05, v_num=15]
Epoch 0:  16%|█▌        | 149/938 [00:10<00:57, 13.78it/s, loss=1.05, v_num=15]
Epoch 0:  16%|█▌        | 149/938 [00:10<00:57, 13.78it/s, loss=1.05, v_num=15]
Epoch 0:  16%|█▌        | 150/938 [00:10<00:57, 13.76it/s, loss=1.05, v_num=15]
Epoch 0:  16%|█▌        | 151/938 [00:10<00:57, 13.78it/s, loss=1.05, v_num=15]
Epoch 0:  16%|█▌        | 151/938 [00:10<00:57, 13.78it/s, loss=1.03, v_num=15]
Epoch 0:  16%|█▌        | 152/938 [00:11<00:57, 13.77it/s, loss=1.03, v_num=15]
Epoch 0:  16%|█▋        | 153/938 [00:11<00:56, 13.78it/s, loss=1.03, v_num=15]
Epoch 0:  16%|█▋        | 153/938 [00:11<00:56, 13.78it/s, loss=1.02, v_num=15]
Epoch 0:  16%|█▋        | 154/938 [00:11<00:56, 13.77it/s, loss=1.02, v_num=15]
Epoch 0:  17%|█▋        | 155/938 [00:11<00:56, 13.77it/s, loss=1.02, v_num=15]
Epoch 0:  17%|█▋        | 155/938 [00:11<00:56, 13.77it/s, loss=1.02, v_num=15]
Epoch 0:  17%|█▋        | 156/938 [00:11<00:56, 13.76it/s, loss=1.03, v_num=15]
Epoch 0:  17%|█▋        | 157/938 [00:11<00:56, 13.77it/s, loss=1.03, v_num=15]
Epoch 0:  17%|█▋        | 157/938 [00:11<00:56, 13.77it/s, loss=1.03, v_num=15]
Epoch 0:  17%|█▋        | 158/938 [00:11<00:56, 13.77it/s, loss=1.02, v_num=15]
Epoch 0:  17%|█▋        | 159/938 [00:11<00:56, 13.77it/s, loss=1.02, v_num=15]
Epoch 0:  17%|█▋        | 159/938 [00:11<00:56, 13.77it/s, loss=1.02, v_num=15]
Epoch 0:  17%|█▋        | 160/938 [00:11<00:56, 13.77it/s, loss=1.01, v_num=15]
Epoch 0:  17%|█▋        | 161/938 [00:11<00:56, 13.77it/s, loss=1.01, v_num=15]
Epoch 0:  17%|█▋        | 161/938 [00:11<00:56, 13.77it/s, loss=1.02, v_num=15]
Epoch 0:  17%|█▋        | 162/938 [00:11<00:56, 13.74it/s, loss=1.01, v_num=15]
Epoch 0:  17%|█▋        | 163/938 [00:11<00:56, 13.76it/s, loss=1.01, v_num=15]
Epoch 0:  17%|█▋        | 163/938 [00:11<00:56, 13.76it/s, loss=1.01, v_num=15]
Epoch 0:  17%|█▋        | 164/938 [00:11<00:56, 13.76it/s, loss=1.01, v_num=15]
Epoch 0:  18%|█▊        | 165/938 [00:11<00:56, 13.76it/s, loss=1.01, v_num=15]
Epoch 0:  18%|█▊        | 165/938 [00:11<00:56, 13.76it/s, loss=1.01, v_num=15]
Epoch 0:  18%|█▊        | 166/938 [00:12<00:56, 13.78it/s, loss=1.01, v_num=15]
Epoch 0:  18%|█▊        | 167/938 [00:12<00:55, 13.79it/s, loss=1.01, v_num=15]
Epoch 0:  18%|█▊        | 167/938 [00:12<00:55, 13.79it/s, loss=0.993, v_num=15]
Epoch 0:  18%|█▊        | 168/938 [00:12<00:55, 13.80it/s, loss=0.998, v_num=15]
Epoch 0:  18%|█▊        | 169/938 [00:12<00:55, 13.81it/s, loss=0.998, v_num=15]
Epoch 0:  18%|█▊        | 169/938 [00:12<00:55, 13.81it/s, loss=1.01, v_num=15] 
Epoch 0:  18%|█▊        | 170/938 [00:12<00:55, 13.82it/s, loss=1.01, v_num=15]
Epoch 0:  18%|█▊        | 171/938 [00:12<00:55, 13.81it/s, loss=1.01, v_num=15]
Epoch 0:  18%|█▊        | 171/938 [00:12<00:55, 13.81it/s, loss=1.03, v_num=15]
Epoch 0:  18%|█▊        | 172/938 [00:12<00:55, 13.82it/s, loss=1.03, v_num=15]
Epoch 0:  18%|█▊        | 173/938 [00:12<00:55, 13.83it/s, loss=1.03, v_num=15]
Epoch 0:  18%|█▊        | 173/938 [00:12<00:55, 13.83it/s, loss=1.04, v_num=15]
Epoch 0:  19%|█▊        | 174/938 [00:12<00:55, 13.85it/s, loss=1.02, v_num=15]
Epoch 0:  19%|█▊        | 175/938 [00:12<00:55, 13.87it/s, loss=1.02, v_num=15]
Epoch 0:  19%|█▊        | 175/938 [00:12<00:55, 13.87it/s, loss=1.02, v_num=15]
Epoch 0:  19%|█▉        | 176/938 [00:12<00:54, 13.86it/s, loss=1.02, v_num=15]
Epoch 0:  19%|█▉        | 177/938 [00:12<00:54, 13.87it/s, loss=1.02, v_num=15]
Epoch 0:  19%|█▉        | 177/938 [00:12<00:54, 13.87it/s, loss=1.02, v_num=15]
Epoch 0:  19%|█▉        | 178/938 [00:12<00:54, 13.86it/s, loss=1.01, v_num=15]
Epoch 0:  19%|█▉        | 179/938 [00:12<00:54, 13.87it/s, loss=1.01, v_num=15]
Epoch 0:  19%|█▉        | 179/938 [00:12<00:54, 13.87it/s, loss=1.01, v_num=15]
Epoch 0:  19%|█▉        | 180/938 [00:12<00:54, 13.87it/s, loss=1.03, v_num=15]
Epoch 0:  19%|█▉        | 181/938 [00:13<00:54, 13.87it/s, loss=1.03, v_num=15]
Epoch 0:  19%|█▉        | 181/938 [00:13<00:54, 13.87it/s, loss=1.03, v_num=15]
Epoch 0:  19%|█▉        | 182/938 [00:13<00:54, 13.86it/s, loss=1.04, v_num=15]
Epoch 0:  20%|█▉        | 183/938 [00:13<00:54, 13.86it/s, loss=1.04, v_num=15]
Epoch 0:  20%|█▉        | 183/938 [00:13<00:54, 13.86it/s, loss=1.03, v_num=15]
Epoch 0:  20%|█▉        | 184/938 [00:13<00:54, 13.85it/s, loss=1.04, v_num=15]
Epoch 0:  20%|█▉        | 185/938 [00:13<00:54, 13.86it/s, loss=1.04, v_num=15]
Epoch 0:  20%|█▉        | 185/938 [00:13<00:54, 13.86it/s, loss=1.04, v_num=15]
Epoch 0:  20%|█▉        | 186/938 [00:13<00:54, 13.85it/s, loss=1.03, v_num=15]
Epoch 0:  20%|█▉        | 187/938 [00:13<00:54, 13.84it/s, loss=1.03, v_num=15]
Epoch 0:  20%|█▉        | 187/938 [00:13<00:54, 13.84it/s, loss=1.03, v_num=15]
Epoch 0:  20%|██        | 188/938 [00:13<00:54, 13.85it/s, loss=1.02, v_num=15]
Epoch 0:  20%|██        | 189/938 [00:13<00:54, 13.84it/s, loss=1.02, v_num=15]
Epoch 0:  20%|██        | 189/938 [00:13<00:54, 13.84it/s, loss=1.02, v_num=15]
Epoch 0:  20%|██        | 190/938 [00:13<00:54, 13.84it/s, loss=1.03, v_num=15]
Epoch 0:  20%|██        | 191/938 [00:13<00:53, 13.84it/s, loss=1.03, v_num=15]
Epoch 0:  20%|██        | 191/938 [00:13<00:53, 13.84it/s, loss=1.02, v_num=15]
Epoch 0:  20%|██        | 192/938 [00:13<00:53, 13.86it/s, loss=1.01, v_num=15]
Epoch 0:  21%|██        | 193/938 [00:13<00:53, 13.85it/s, loss=1.01, v_num=15]
Epoch 0:  21%|██        | 193/938 [00:13<00:53, 13.85it/s, loss=1, v_num=15]   
Epoch 0:  21%|██        | 194/938 [00:14<00:53, 13.85it/s, loss=1, v_num=15]
Epoch 0:  21%|██        | 195/938 [00:14<00:53, 13.84it/s, loss=1, v_num=15]
Epoch 0:  21%|██        | 195/938 [00:14<00:53, 13.84it/s, loss=1, v_num=15]
Epoch 0:  21%|██        | 196/938 [00:14<00:53, 13.83it/s, loss=0.984, v_num=15]
Epoch 0:  21%|██        | 197/938 [00:14<00:53, 13.82it/s, loss=0.984, v_num=15]
Epoch 0:  21%|██        | 197/938 [00:14<00:53, 13.82it/s, loss=0.975, v_num=15]
Epoch 0:  21%|██        | 198/938 [00:14<00:53, 13.83it/s, loss=0.981, v_num=15]
Epoch 0:  21%|██        | 199/938 [00:14<00:53, 13.77it/s, loss=0.981, v_num=15]
Epoch 0:  21%|██        | 199/938 [00:14<00:53, 13.77it/s, loss=0.984, v_num=15]
Epoch 0:  21%|██▏       | 200/938 [00:14<00:53, 13.78it/s, loss=0.96, v_num=15] 
Epoch 0:  21%|██▏       | 201/938 [00:14<00:53, 13.79it/s, loss=0.96, v_num=15]
Epoch 0:  21%|██▏       | 201/938 [00:14<00:53, 13.79it/s, loss=0.954, v_num=15]
Epoch 0:  22%|██▏       | 202/938 [00:14<00:53, 13.79it/s, loss=0.952, v_num=15]
Epoch 0:  22%|██▏       | 203/938 [00:14<00:53, 13.80it/s, loss=0.952, v_num=15]
Epoch 0:  22%|██▏       | 203/938 [00:14<00:53, 13.80it/s, loss=0.955, v_num=15]
Epoch 0:  22%|██▏       | 204/938 [00:14<00:53, 13.79it/s, loss=0.956, v_num=15]
Epoch 0:  22%|██▏       | 205/938 [00:14<00:53, 13.80it/s, loss=0.956, v_num=15]
Epoch 0:  22%|██▏       | 205/938 [00:14<00:53, 13.80it/s, loss=0.954, v_num=15]
Epoch 0:  22%|██▏       | 206/938 [00:14<00:53, 13.80it/s, loss=0.961, v_num=15]
Epoch 0:  22%|██▏       | 207/938 [00:15<00:52, 13.80it/s, loss=0.961, v_num=15]
Epoch 0:  22%|██▏       | 207/938 [00:15<00:52, 13.80it/s, loss=0.962, v_num=15]
Epoch 0:  22%|██▏       | 208/938 [00:15<00:52, 13.79it/s, loss=0.968, v_num=15]
Epoch 0:  22%|██▏       | 209/938 [00:15<00:52, 13.79it/s, loss=0.968, v_num=15]
Epoch 0:  22%|██▏       | 209/938 [00:15<00:52, 13.79it/s, loss=0.955, v_num=15]
Epoch 0:  22%|██▏       | 210/938 [00:15<00:52, 13.78it/s, loss=0.942, v_num=15]
Epoch 0:  22%|██▏       | 211/938 [00:15<00:52, 13.78it/s, loss=0.942, v_num=15]
Epoch 0:  22%|██▏       | 211/938 [00:15<00:52, 13.78it/s, loss=0.94, v_num=15] 
Epoch 0:  23%|██▎       | 212/938 [00:15<00:52, 13.77it/s, loss=0.942, v_num=15]
Epoch 0:  23%|██▎       | 213/938 [00:15<00:52, 13.77it/s, loss=0.942, v_num=15]
Epoch 0:  23%|██▎       | 213/938 [00:15<00:52, 13.77it/s, loss=0.944, v_num=15]
Epoch 0:  23%|██▎       | 214/938 [00:15<00:52, 13.77it/s, loss=0.942, v_num=15]
Epoch 0:  23%|██▎       | 215/938 [00:15<00:52, 13.77it/s, loss=0.942, v_num=15]
Epoch 0:  23%|██▎       | 215/938 [00:15<00:52, 13.77it/s, loss=0.939, v_num=15]
Epoch 0:  23%|██▎       | 216/938 [00:15<00:52, 13.76it/s, loss=0.944, v_num=15]
Epoch 0:  23%|██▎       | 217/938 [00:15<00:52, 13.74it/s, loss=0.944, v_num=15]
Epoch 0:  23%|██▎       | 217/938 [00:15<00:52, 13.74it/s, loss=0.949, v_num=15]
Epoch 0:  23%|██▎       | 218/938 [00:15<00:52, 13.75it/s, loss=0.943, v_num=15]
Epoch 0:  23%|██▎       | 219/938 [00:15<00:52, 13.76it/s, loss=0.943, v_num=15]
Epoch 0:  23%|██▎       | 219/938 [00:15<00:52, 13.76it/s, loss=0.935, v_num=15]
Epoch 0:  23%|██▎       | 220/938 [00:16<00:52, 13.75it/s, loss=0.93, v_num=15] 
Epoch 0:  24%|██▎       | 221/938 [00:16<00:52, 13.75it/s, loss=0.93, v_num=15]
Epoch 0:  24%|██▎       | 221/938 [00:16<00:52, 13.75it/s, loss=0.928, v_num=15]
Epoch 0:  24%|██▎       | 222/938 [00:16<00:52, 13.75it/s, loss=0.923, v_num=15]
Epoch 0:  24%|██▍       | 223/938 [00:16<00:51, 13.76it/s, loss=0.923, v_num=15]
Epoch 0:  24%|██▍       | 223/938 [00:16<00:51, 13.76it/s, loss=0.926, v_num=15]
Epoch 0:  24%|██▍       | 224/938 [00:16<00:51, 13.75it/s, loss=0.921, v_num=15]
Epoch 0:  24%|██▍       | 225/938 [00:16<00:51, 13.76it/s, loss=0.921, v_num=15]
Epoch 0:  24%|██▍       | 225/938 [00:16<00:51, 13.76it/s, loss=0.931, v_num=15]
Epoch 0:  24%|██▍       | 226/938 [00:16<00:51, 13.76it/s, loss=0.93, v_num=15] 
Epoch 0:  24%|██▍       | 227/938 [00:16<00:51, 13.75it/s, loss=0.93, v_num=15]
Epoch 0:  24%|██▍       | 227/938 [00:16<00:51, 13.75it/s, loss=0.924, v_num=15]
Epoch 0:  24%|██▍       | 228/938 [00:16<00:51, 13.74it/s, loss=0.911, v_num=15]
Epoch 0:  24%|██▍       | 229/938 [00:16<00:51, 13.73it/s, loss=0.911, v_num=15]
Epoch 0:  24%|██▍       | 229/938 [00:16<00:51, 13.73it/s, loss=0.911, v_num=15]
Epoch 0:  25%|██▍       | 230/938 [00:16<00:51, 13.75it/s, loss=0.914, v_num=15]
Epoch 0:  25%|██▍       | 231/938 [00:16<00:51, 13.74it/s, loss=0.914, v_num=15]
Epoch 0:  25%|██▍       | 231/938 [00:16<00:51, 13.74it/s, loss=0.928, v_num=15]
Epoch 0:  25%|██▍       | 232/938 [00:16<00:51, 13.74it/s, loss=0.931, v_num=15]
Epoch 0:  25%|██▍       | 233/938 [00:16<00:51, 13.76it/s, loss=0.931, v_num=15]
Epoch 0:  25%|██▍       | 233/938 [00:16<00:51, 13.75it/s, loss=0.921, v_num=15]
Epoch 0:  25%|██▍       | 234/938 [00:17<00:51, 13.76it/s, loss=0.916, v_num=15]
Epoch 0:  25%|██▌       | 235/938 [00:17<00:51, 13.76it/s, loss=0.916, v_num=15]
Epoch 0:  25%|██▌       | 235/938 [00:17<00:51, 13.76it/s, loss=0.918, v_num=15]
Epoch 0:  25%|██▌       | 236/938 [00:17<00:51, 13.76it/s, loss=0.91, v_num=15] 
Epoch 0:  25%|██▌       | 237/938 [00:17<00:51, 13.74it/s, loss=0.91, v_num=15]
Epoch 0:  25%|██▌       | 237/938 [00:17<00:51, 13.74it/s, loss=0.903, v_num=15]
Epoch 0:  25%|██▌       | 238/938 [00:17<00:50, 13.75it/s, loss=0.899, v_num=15]
Epoch 0:  25%|██▌       | 239/938 [00:17<00:50, 13.76it/s, loss=0.899, v_num=15]
Epoch 0:  25%|██▌       | 239/938 [00:17<00:50, 13.76it/s, loss=0.912, v_num=15]
Epoch 0:  26%|██▌       | 240/938 [00:17<00:50, 13.76it/s, loss=0.915, v_num=15]
Epoch 0:  26%|██▌       | 241/938 [00:17<00:50, 13.77it/s, loss=0.915, v_num=15]
Epoch 0:  26%|██▌       | 241/938 [00:17<00:50, 13.77it/s, loss=0.904, v_num=15]
Epoch 0:  26%|██▌       | 242/938 [00:17<00:50, 13.77it/s, loss=0.896, v_num=15]
Epoch 0:  26%|██▌       | 243/938 [00:17<00:50, 13.76it/s, loss=0.896, v_num=15]
Epoch 0:  26%|██▌       | 243/938 [00:17<00:50, 13.76it/s, loss=0.892, v_num=15]
Epoch 0:  26%|██▌       | 244/938 [00:17<00:50, 13.77it/s, loss=0.888, v_num=15]
Epoch 0:  26%|██▌       | 245/938 [00:17<00:50, 13.77it/s, loss=0.888, v_num=15]
Epoch 0:  26%|██▌       | 245/938 [00:17<00:50, 13.77it/s, loss=0.873, v_num=15]
Epoch 0:  26%|██▌       | 246/938 [00:17<00:50, 13.77it/s, loss=0.867, v_num=15]
Epoch 0:  26%|██▋       | 247/938 [00:17<00:50, 13.77it/s, loss=0.867, v_num=15]
Epoch 0:  26%|██▋       | 247/938 [00:17<00:50, 13.77it/s, loss=0.867, v_num=15]
Epoch 0:  26%|██▋       | 248/938 [00:18<00:50, 13.77it/s, loss=0.875, v_num=15]
Epoch 0:  27%|██▋       | 249/938 [00:18<00:50, 13.76it/s, loss=0.875, v_num=15]
Epoch 0:  27%|██▋       | 249/938 [00:18<00:50, 13.76it/s, loss=0.88, v_num=15] 
Epoch 0:  27%|██▋       | 250/938 [00:18<00:50, 13.76it/s, loss=0.884, v_num=15]
Epoch 0:  27%|██▋       | 251/938 [00:18<00:49, 13.76it/s, loss=0.884, v_num=15]
Epoch 0:  27%|██▋       | 251/938 [00:18<00:49, 13.76it/s, loss=0.857, v_num=15]
Epoch 0:  27%|██▋       | 252/938 [00:18<00:49, 13.77it/s, loss=0.849, v_num=15]
Epoch 0:  27%|██▋       | 253/938 [00:18<00:49, 13.77it/s, loss=0.849, v_num=15]
Epoch 0:  27%|██▋       | 253/938 [00:18<00:49, 13.77it/s, loss=0.862, v_num=15]
Epoch 0:  27%|██▋       | 254/938 [00:18<00:49, 13.77it/s, loss=0.87, v_num=15] 
Epoch 0:  27%|██▋       | 255/938 [00:18<00:49, 13.77it/s, loss=0.87, v_num=15]
Epoch 0:  27%|██▋       | 255/938 [00:18<00:49, 13.77it/s, loss=0.866, v_num=15]
Epoch 0:  27%|██▋       | 256/938 [00:18<00:49, 13.76it/s, loss=0.865, v_num=15]
Epoch 0:  27%|██▋       | 257/938 [00:18<00:49, 13.77it/s, loss=0.865, v_num=15]
Epoch 0:  27%|██▋       | 257/938 [00:18<00:49, 13.77it/s, loss=0.885, v_num=15]
Epoch 0:  28%|██▊       | 258/938 [00:18<00:49, 13.77it/s, loss=0.893, v_num=15]
Epoch 0:  28%|██▊       | 259/938 [00:18<00:49, 13.78it/s, loss=0.893, v_num=15]
Epoch 0:  28%|██▊       | 259/938 [00:18<00:49, 13.78it/s, loss=0.896, v_num=15]
Epoch 0:  28%|██▊       | 260/938 [00:18<00:49, 13.78it/s, loss=0.889, v_num=15]
Epoch 0:  28%|██▊       | 261/938 [00:18<00:49, 13.77it/s, loss=0.889, v_num=15]
Epoch 0:  28%|██▊       | 261/938 [00:18<00:49, 13.77it/s, loss=0.895, v_num=15]
Epoch 0:  28%|██▊       | 262/938 [00:19<00:49, 13.78it/s, loss=0.9, v_num=15]  
Epoch 0:  28%|██▊       | 263/938 [00:19<00:48, 13.78it/s, loss=0.9, v_num=15]
Epoch 0:  28%|██▊       | 263/938 [00:19<00:48, 13.78it/s, loss=0.905, v_num=15]
Epoch 0:  28%|██▊       | 264/938 [00:19<00:48, 13.78it/s, loss=0.907, v_num=15]
Epoch 0:  28%|██▊       | 265/938 [00:19<00:48, 13.78it/s, loss=0.907, v_num=15]
Epoch 0:  28%|██▊       | 265/938 [00:19<00:48, 13.78it/s, loss=0.915, v_num=15]
Epoch 0:  28%|██▊       | 266/938 [00:19<00:48, 13.77it/s, loss=0.918, v_num=15]
Epoch 0:  28%|██▊       | 267/938 [00:19<00:48, 13.77it/s, loss=0.918, v_num=15]
Epoch 0:  28%|██▊       | 267/938 [00:19<00:48, 13.77it/s, loss=0.914, v_num=15]
Epoch 0:  29%|██▊       | 268/938 [00:19<00:48, 13.77it/s, loss=0.905, v_num=15]
Epoch 0:  29%|██▊       | 269/938 [00:19<00:48, 13.76it/s, loss=0.905, v_num=15]
Epoch 0:  29%|██▊       | 269/938 [00:19<00:48, 13.76it/s, loss=0.897, v_num=15]
Epoch 0:  29%|██▉       | 270/938 [00:19<00:48, 13.76it/s, loss=0.896, v_num=15]
Epoch 0:  29%|██▉       | 271/938 [00:19<00:48, 13.75it/s, loss=0.896, v_num=15]
Epoch 0:  29%|██▉       | 271/938 [00:19<00:48, 13.75it/s, loss=0.899, v_num=15]
Epoch 0:  29%|██▉       | 272/938 [00:19<00:48, 13.75it/s, loss=0.905, v_num=15]
Epoch 0:  29%|██▉       | 273/938 [00:19<00:48, 13.75it/s, loss=0.905, v_num=15]
Epoch 0:  29%|██▉       | 273/938 [00:19<00:48, 13.75it/s, loss=0.896, v_num=15]
Epoch 0:  29%|██▉       | 274/938 [00:19<00:48, 13.75it/s, loss=0.891, v_num=15]
Epoch 0:  29%|██▉       | 275/938 [00:19<00:48, 13.76it/s, loss=0.891, v_num=15]
Epoch 0:  29%|██▉       | 275/938 [00:19<00:48, 13.76it/s, loss=0.889, v_num=15]
Epoch 0:  29%|██▉       | 276/938 [00:20<00:48, 13.76it/s, loss=0.896, v_num=15]
Epoch 0:  30%|██▉       | 277/938 [00:20<00:48, 13.77it/s, loss=0.896, v_num=15]
Epoch 0:  30%|██▉       | 277/938 [00:20<00:48, 13.77it/s, loss=0.875, v_num=15]
Epoch 0:  30%|██▉       | 278/938 [00:20<00:47, 13.77it/s, loss=0.878, v_num=15]
Epoch 0:  30%|██▉       | 279/938 [00:20<00:47, 13.77it/s, loss=0.878, v_num=15]
Epoch 0:  30%|██▉       | 279/938 [00:20<00:47, 13.77it/s, loss=0.866, v_num=15]
Epoch 0:  30%|██▉       | 280/938 [00:20<00:47, 13.77it/s, loss=0.874, v_num=15]
Epoch 0:  30%|██▉       | 281/938 [00:20<00:47, 13.77it/s, loss=0.874, v_num=15]
Epoch 0:  30%|██▉       | 281/938 [00:20<00:47, 13.77it/s, loss=0.874, v_num=15]
Epoch 0:  30%|███       | 282/938 [00:20<00:47, 13.77it/s, loss=0.877, v_num=15]
Epoch 0:  30%|███       | 283/938 [00:20<00:47, 13.73it/s, loss=0.877, v_num=15]
Epoch 0:  30%|███       | 283/938 [00:20<00:47, 13.73it/s, loss=0.876, v_num=15]
Epoch 0:  30%|███       | 284/938 [00:20<00:47, 13.73it/s, loss=0.873, v_num=15]
Epoch 0:  30%|███       | 285/938 [00:20<00:47, 13.74it/s, loss=0.873, v_num=15]
Epoch 0:  30%|███       | 285/938 [00:20<00:47, 13.74it/s, loss=0.866, v_num=15]
Epoch 0:  30%|███       | 286/938 [00:20<00:47, 13.73it/s, loss=0.855, v_num=15]
Epoch 0:  31%|███       | 287/938 [00:20<00:47, 13.74it/s, loss=0.855, v_num=15]
Epoch 0:  31%|███       | 287/938 [00:20<00:47, 13.74it/s, loss=0.864, v_num=15]
Epoch 0:  31%|███       | 288/938 [00:20<00:47, 13.75it/s, loss=0.869, v_num=15]
Epoch 0:  31%|███       | 289/938 [00:21<00:47, 13.74it/s, loss=0.869, v_num=15]
Epoch 0:  31%|███       | 289/938 [00:21<00:47, 13.74it/s, loss=0.869, v_num=15]
Epoch 0:  31%|███       | 290/938 [00:21<00:47, 13.75it/s, loss=0.86, v_num=15] 
Epoch 0:  31%|███       | 291/938 [00:21<00:47, 13.75it/s, loss=0.86, v_num=15]
Epoch 0:  31%|███       | 291/938 [00:21<00:47, 13.75it/s, loss=0.857, v_num=15]
Epoch 0:  31%|███       | 292/938 [00:21<00:46, 13.75it/s, loss=0.856, v_num=15]
Epoch 0:  31%|███       | 293/938 [00:21<00:46, 13.76it/s, loss=0.856, v_num=15]
Epoch 0:  31%|███       | 293/938 [00:21<00:46, 13.76it/s, loss=0.853, v_num=15]
Epoch 0:  31%|███▏      | 294/938 [00:21<00:46, 13.76it/s, loss=0.861, v_num=15]
Epoch 0:  31%|███▏      | 295/938 [00:21<00:46, 13.76it/s, loss=0.861, v_num=15]
Epoch 0:  31%|███▏      | 295/938 [00:21<00:46, 13.75it/s, loss=0.857, v_num=15]
Epoch 0:  32%|███▏      | 296/938 [00:21<00:46, 13.76it/s, loss=0.854, v_num=15]
Epoch 0:  32%|███▏      | 297/938 [00:21<00:46, 13.76it/s, loss=0.854, v_num=15]
Epoch 0:  32%|███▏      | 297/938 [00:21<00:46, 13.76it/s, loss=0.855, v_num=15]
Epoch 0:  32%|███▏      | 298/938 [00:21<00:46, 13.77it/s, loss=0.851, v_num=15]
Epoch 0:  32%|███▏      | 299/938 [00:21<00:46, 13.76it/s, loss=0.851, v_num=15]
Epoch 0:  32%|███▏      | 299/938 [00:21<00:46, 13.75it/s, loss=0.846, v_num=15]
Epoch 0:  32%|███▏      | 300/938 [00:21<00:46, 13.76it/s, loss=0.846, v_num=15]
Epoch 0:  32%|███▏      | 301/938 [00:21<00:46, 13.75it/s, loss=0.846, v_num=15]
Epoch 0:  32%|███▏      | 301/938 [00:21<00:46, 13.75it/s, loss=0.842, v_num=15]
Epoch 0:  32%|███▏      | 302/938 [00:21<00:46, 13.76it/s, loss=0.828, v_num=15]
Epoch 0:  32%|███▏      | 303/938 [00:22<00:46, 13.75it/s, loss=0.828, v_num=15]
Epoch 0:  32%|███▏      | 303/938 [00:22<00:46, 13.75it/s, loss=0.829, v_num=15]
Epoch 0:  32%|███▏      | 304/938 [00:22<00:46, 13.76it/s, loss=0.828, v_num=15]
Epoch 0:  33%|███▎      | 305/938 [00:22<00:46, 13.76it/s, loss=0.828, v_num=15]
Epoch 0:  33%|███▎      | 305/938 [00:22<00:46, 13.76it/s, loss=0.831, v_num=15]
Epoch 0:  33%|███▎      | 306/938 [00:22<00:45, 13.76it/s, loss=0.838, v_num=15]
Epoch 0:  33%|███▎      | 307/938 [00:22<00:45, 13.76it/s, loss=0.838, v_num=15]
Epoch 0:  33%|███▎      | 307/938 [00:22<00:45, 13.76it/s, loss=0.834, v_num=15]
Epoch 0:  33%|███▎      | 308/938 [00:22<00:45, 13.76it/s, loss=0.838, v_num=15]
Epoch 0:  33%|███▎      | 309/938 [00:22<00:45, 13.76it/s, loss=0.838, v_num=15]
Epoch 0:  33%|███▎      | 309/938 [00:22<00:45, 13.76it/s, loss=0.834, v_num=15]
Epoch 0:  33%|███▎      | 310/938 [00:22<00:45, 13.76it/s, loss=0.837, v_num=15]
Epoch 0:  33%|███▎      | 311/938 [00:22<00:45, 13.75it/s, loss=0.837, v_num=15]
Epoch 0:  33%|███▎      | 311/938 [00:22<00:45, 13.75it/s, loss=0.844, v_num=15]
Epoch 0:  33%|███▎      | 312/938 [00:22<00:45, 13.76it/s, loss=0.839, v_num=15]
Epoch 0:  33%|███▎      | 313/938 [00:22<00:45, 13.76it/s, loss=0.839, v_num=15]
Epoch 0:  33%|███▎      | 313/938 [00:22<00:45, 13.76it/s, loss=0.848, v_num=15]
Epoch 0:  33%|███▎      | 314/938 [00:22<00:45, 13.75it/s, loss=0.844, v_num=15]
Epoch 0:  34%|███▎      | 315/938 [00:22<00:45, 13.73it/s, loss=0.844, v_num=15]
Epoch 0:  34%|███▎      | 315/938 [00:22<00:45, 13.73it/s, loss=0.859, v_num=15]
Epoch 0:  34%|███▎      | 316/938 [00:23<00:45, 13.73it/s, loss=0.864, v_num=15]
Epoch 0:  34%|███▍      | 317/938 [00:23<00:45, 13.74it/s, loss=0.864, v_num=15]
Epoch 0:  34%|███▍      | 317/938 [00:23<00:45, 13.74it/s, loss=0.862, v_num=15]
Epoch 0:  34%|███▍      | 318/938 [00:23<00:45, 13.75it/s, loss=0.858, v_num=15]
Epoch 0:  34%|███▍      | 319/938 [00:23<00:45, 13.75it/s, loss=0.858, v_num=15]
Epoch 0:  34%|███▍      | 319/938 [00:23<00:45, 13.75it/s, loss=0.862, v_num=15]
Epoch 0:  34%|███▍      | 320/938 [00:23<00:44, 13.75it/s, loss=0.858, v_num=15]
Epoch 0:  34%|███▍      | 321/938 [00:23<00:44, 13.75it/s, loss=0.858, v_num=15]
Epoch 0:  34%|███▍      | 321/938 [00:23<00:44, 13.75it/s, loss=0.861, v_num=15]
Epoch 0:  34%|███▍      | 322/938 [00:23<00:44, 13.74it/s, loss=0.865, v_num=15]
Epoch 0:  34%|███▍      | 323/938 [00:23<00:44, 13.74it/s, loss=0.865, v_num=15]
Epoch 0:  34%|███▍      | 323/938 [00:23<00:44, 13.74it/s, loss=0.873, v_num=15]
Epoch 0:  35%|███▍      | 324/938 [00:23<00:44, 13.75it/s, loss=0.872, v_num=15]
Epoch 0:  35%|███▍      | 325/938 [00:23<00:44, 13.75it/s, loss=0.872, v_num=15]
Epoch 0:  35%|███▍      | 325/938 [00:23<00:44, 13.75it/s, loss=0.865, v_num=15]
Epoch 0:  35%|███▍      | 326/938 [00:23<00:44, 13.75it/s, loss=0.869, v_num=15]
Epoch 0:  35%|███▍      | 327/938 [00:23<00:44, 13.74it/s, loss=0.869, v_num=15]
Epoch 0:  35%|███▍      | 327/938 [00:23<00:44, 13.74it/s, loss=0.864, v_num=15]
Epoch 0:  35%|███▍      | 328/938 [00:23<00:44, 13.73it/s, loss=0.869, v_num=15]
Epoch 0:  35%|███▌      | 329/938 [00:23<00:44, 13.73it/s, loss=0.869, v_num=15]
Epoch 0:  35%|███▌      | 329/938 [00:23<00:44, 13.73it/s, loss=0.875, v_num=15]
Epoch 0:  35%|███▌      | 330/938 [00:24<00:44, 13.74it/s, loss=0.866, v_num=15]
Epoch 0:  35%|███▌      | 331/938 [00:24<00:44, 13.74it/s, loss=0.866, v_num=15]
Epoch 0:  35%|███▌      | 331/938 [00:24<00:44, 13.74it/s, loss=0.867, v_num=15]
Epoch 0:  35%|███▌      | 332/938 [00:24<00:44, 13.74it/s, loss=0.864, v_num=15]
Epoch 0:  36%|███▌      | 333/938 [00:24<00:44, 13.74it/s, loss=0.864, v_num=15]
Epoch 0:  36%|███▌      | 333/938 [00:24<00:44, 13.74it/s, loss=0.869, v_num=15]
Epoch 0:  36%|███▌      | 334/938 [00:24<00:43, 13.75it/s, loss=0.866, v_num=15]
Epoch 0:  36%|███▌      | 335/938 [00:24<00:43, 13.75it/s, loss=0.866, v_num=15]
Epoch 0:  36%|███▌      | 335/938 [00:24<00:43, 13.75it/s, loss=0.86, v_num=15] 
Epoch 0:  36%|███▌      | 336/938 [00:24<00:43, 13.74it/s, loss=0.856, v_num=15]
Epoch 0:  36%|███▌      | 337/938 [00:24<00:43, 13.75it/s, loss=0.856, v_num=15]
Epoch 0:  36%|███▌      | 337/938 [00:24<00:43, 13.74it/s, loss=0.866, v_num=15]
Epoch 0:  36%|███▌      | 338/938 [00:24<00:43, 13.75it/s, loss=0.865, v_num=15]
Epoch 0:  36%|███▌      | 339/938 [00:24<00:43, 13.74it/s, loss=0.865, v_num=15]
Epoch 0:  36%|███▌      | 339/938 [00:24<00:43, 13.74it/s, loss=0.858, v_num=15]
Epoch 0:  36%|███▌      | 340/938 [00:24<00:43, 13.74it/s, loss=0.861, v_num=15]
Epoch 0:  36%|███▋      | 341/938 [00:24<00:43, 13.74it/s, loss=0.861, v_num=15]
Epoch 0:  36%|███▋      | 341/938 [00:24<00:43, 13.74it/s, loss=0.864, v_num=15]
Epoch 0:  36%|███▋      | 342/938 [00:24<00:43, 13.75it/s, loss=0.86, v_num=15] 
Epoch 0:  37%|███▋      | 343/938 [00:24<00:43, 13.75it/s, loss=0.86, v_num=15]
Epoch 0:  37%|███▋      | 343/938 [00:24<00:43, 13.75it/s, loss=0.842, v_num=15]
Epoch 0:  37%|███▋      | 344/938 [00:25<00:43, 13.75it/s, loss=0.844, v_num=15]
Epoch 0:  37%|███▋      | 345/938 [00:25<00:43, 13.75it/s, loss=0.844, v_num=15]
Epoch 0:  37%|███▋      | 345/938 [00:25<00:43, 13.75it/s, loss=0.847, v_num=15]
Epoch 0:  37%|███▋      | 346/938 [00:25<00:43, 13.76it/s, loss=0.852, v_num=15]
Epoch 0:  37%|███▋      | 347/938 [00:25<00:42, 13.76it/s, loss=0.852, v_num=15]
Epoch 0:  37%|███▋      | 347/938 [00:25<00:42, 13.76it/s, loss=0.852, v_num=15]
Epoch 0:  37%|███▋      | 348/938 [00:25<00:42, 13.76it/s, loss=0.844, v_num=15]
Epoch 0:  37%|███▋      | 349/938 [00:25<00:42, 13.77it/s, loss=0.844, v_num=15]
Epoch 0:  37%|███▋      | 349/938 [00:25<00:42, 13.76it/s, loss=0.837, v_num=15]
Epoch 0:  37%|███▋      | 350/938 [00:25<00:42, 13.76it/s, loss=0.849, v_num=15]
Epoch 0:  37%|███▋      | 351/938 [00:25<00:42, 13.77it/s, loss=0.849, v_num=15]
Epoch 0:  37%|███▋      | 351/938 [00:25<00:42, 13.77it/s, loss=0.855, v_num=15]
Epoch 0:  38%|███▊      | 352/938 [00:25<00:42, 13.77it/s, loss=0.858, v_num=15]
Epoch 0:  38%|███▊      | 353/938 [00:25<00:42, 13.77it/s, loss=0.858, v_num=15]
Epoch 0:  38%|███▊      | 353/938 [00:25<00:42, 13.77it/s, loss=0.843, v_num=15]
Epoch 0:  38%|███▊      | 354/938 [00:25<00:42, 13.77it/s, loss=0.846, v_num=15]
Epoch 0:  38%|███▊      | 355/938 [00:25<00:42, 13.77it/s, loss=0.846, v_num=15]
Epoch 0:  38%|███▊      | 355/938 [00:25<00:42, 13.77it/s, loss=0.842, v_num=15]
Epoch 0:  38%|███▊      | 356/938 [00:25<00:42, 13.78it/s, loss=0.843, v_num=15]
Epoch 0:  38%|███▊      | 357/938 [00:25<00:42, 13.79it/s, loss=0.843, v_num=15]
Epoch 0:  38%|███▊      | 357/938 [00:25<00:42, 13.79it/s, loss=0.844, v_num=15]
Epoch 0:  38%|███▊      | 358/938 [00:25<00:42, 13.78it/s, loss=0.843, v_num=15]
Epoch 0:  38%|███▊      | 359/938 [00:26<00:42, 13.77it/s, loss=0.843, v_num=15]
Epoch 0:  38%|███▊      | 359/938 [00:26<00:42, 13.77it/s, loss=0.838, v_num=15]
Epoch 0:  38%|███▊      | 360/938 [00:26<00:41, 13.77it/s, loss=0.839, v_num=15]
Epoch 0:  38%|███▊      | 361/938 [00:26<00:41, 13.78it/s, loss=0.839, v_num=15]
Epoch 0:  38%|███▊      | 361/938 [00:26<00:41, 13.78it/s, loss=0.839, v_num=15]
Epoch 0:  39%|███▊      | 362/938 [00:26<00:41, 13.77it/s, loss=0.842, v_num=15]
Epoch 0:  39%|███▊      | 363/938 [00:26<00:41, 13.77it/s, loss=0.842, v_num=15]
Epoch 0:  39%|███▊      | 363/938 [00:26<00:41, 13.77it/s, loss=0.85, v_num=15] 
Epoch 0:  39%|███▉      | 364/938 [00:26<00:41, 13.77it/s, loss=0.847, v_num=15]
Epoch 0:  39%|███▉      | 365/938 [00:26<00:41, 13.77it/s, loss=0.847, v_num=15]
Epoch 0:  39%|███▉      | 365/938 [00:26<00:41, 13.77it/s, loss=0.84, v_num=15] 
Epoch 0:  39%|███▉      | 366/938 [00:26<00:41, 13.78it/s, loss=0.833, v_num=15]
Epoch 0:  39%|███▉      | 367/938 [00:26<00:41, 13.79it/s, loss=0.833, v_num=15]
Epoch 0:  39%|███▉      | 367/938 [00:26<00:41, 13.79it/s, loss=0.822, v_num=15]
Epoch 0:  39%|███▉      | 368/938 [00:26<00:41, 13.78it/s, loss=0.824, v_num=15]
Epoch 0:  39%|███▉      | 369/938 [00:26<00:41, 13.78it/s, loss=0.824, v_num=15]
Epoch 0:  39%|███▉      | 369/938 [00:26<00:41, 13.78it/s, loss=0.825, v_num=15]
Epoch 0:  39%|███▉      | 370/938 [00:26<00:41, 13.79it/s, loss=0.819, v_num=15]
Epoch 0:  40%|███▉      | 371/938 [00:26<00:41, 13.79it/s, loss=0.819, v_num=15]
Epoch 0:  40%|███▉      | 371/938 [00:26<00:41, 13.79it/s, loss=0.803, v_num=15]
Epoch 0:  40%|███▉      | 372/938 [00:26<00:41, 13.79it/s, loss=0.805, v_num=15]
Epoch 0:  40%|███▉      | 373/938 [00:27<00:40, 13.79it/s, loss=0.805, v_num=15]
Epoch 0:  40%|███▉      | 373/938 [00:27<00:40, 13.79it/s, loss=0.814, v_num=15]
Epoch 0:  40%|███▉      | 374/938 [00:27<00:40, 13.80it/s, loss=0.81, v_num=15] 
Epoch 0:  40%|███▉      | 375/938 [00:27<00:40, 13.79it/s, loss=0.81, v_num=15]
Epoch 0:  40%|███▉      | 375/938 [00:27<00:40, 13.79it/s, loss=0.806, v_num=15]
Epoch 0:  40%|████      | 376/938 [00:27<00:40, 13.80it/s, loss=0.816, v_num=15]
Epoch 0:  40%|████      | 377/938 [00:27<00:40, 13.80it/s, loss=0.816, v_num=15]
Epoch 0:  40%|████      | 377/938 [00:27<00:40, 13.80it/s, loss=0.816, v_num=15]
Epoch 0:  40%|████      | 378/938 [00:27<00:40, 13.80it/s, loss=0.81, v_num=15] 
Epoch 0:  40%|████      | 379/938 [00:27<00:40, 13.79it/s, loss=0.81, v_num=15]
Epoch 0:  40%|████      | 379/938 [00:27<00:40, 13.79it/s, loss=0.821, v_num=15]
Epoch 0:  41%|████      | 380/938 [00:27<00:40, 13.80it/s, loss=0.815, v_num=15]
Epoch 0:  41%|████      | 381/938 [00:27<00:40, 13.80it/s, loss=0.815, v_num=15]
Epoch 0:  41%|████      | 381/938 [00:27<00:40, 13.80it/s, loss=0.81, v_num=15] 
Epoch 0:  41%|████      | 382/938 [00:27<00:40, 13.80it/s, loss=0.817, v_num=15]
Epoch 0:  41%|████      | 383/938 [00:27<00:40, 13.80it/s, loss=0.817, v_num=15]
Epoch 0:  41%|████      | 383/938 [00:27<00:40, 13.80it/s, loss=0.83, v_num=15] 
Epoch 0:  41%|████      | 384/938 [00:27<00:40, 13.80it/s, loss=0.839, v_num=15]
Epoch 0:  41%|████      | 385/938 [00:27<00:40, 13.81it/s, loss=0.839, v_num=15]
Epoch 0:  41%|████      | 385/938 [00:27<00:40, 13.81it/s, loss=0.844, v_num=15]
Epoch 0:  41%|████      | 386/938 [00:27<00:39, 13.81it/s, loss=0.852, v_num=15]
Epoch 0:  41%|████▏     | 387/938 [00:28<00:39, 13.81it/s, loss=0.852, v_num=15]
Epoch 0:  41%|████▏     | 387/938 [00:28<00:39, 13.81it/s, loss=0.869, v_num=15]
Epoch 0:  41%|████▏     | 388/938 [00:28<00:39, 13.81it/s, loss=0.869, v_num=15]
Epoch 0:  41%|████▏     | 389/938 [00:28<00:39, 13.81it/s, loss=0.869, v_num=15]
Epoch 0:  41%|████▏     | 389/938 [00:28<00:39, 13.81it/s, loss=0.876, v_num=15]
Epoch 0:  42%|████▏     | 390/938 [00:28<00:39, 13.80it/s, loss=0.879, v_num=15]
Epoch 0:  42%|████▏     | 391/938 [00:28<00:39, 13.81it/s, loss=0.879, v_num=15]
Epoch 0:  42%|████▏     | 391/938 [00:28<00:39, 13.80it/s, loss=0.887, v_num=15]
Epoch 0:  42%|████▏     | 392/938 [00:28<00:39, 13.81it/s, loss=0.89, v_num=15] 
Epoch 0:  42%|████▏     | 393/938 [00:28<00:39, 13.81it/s, loss=0.89, v_num=15]
Epoch 0:  42%|████▏     | 393/938 [00:28<00:39, 13.81it/s, loss=0.881, v_num=15]
Epoch 0:  42%|████▏     | 394/938 [00:28<00:39, 13.81it/s, loss=0.881, v_num=15]
Epoch 0:  42%|████▏     | 395/938 [00:28<00:39, 13.80it/s, loss=0.881, v_num=15]
Epoch 0:  42%|████▏     | 395/938 [00:28<00:39, 13.80it/s, loss=0.882, v_num=15]
Epoch 0:  42%|████▏     | 396/938 [00:28<00:39, 13.79it/s, loss=0.869, v_num=15]
Epoch 0:  42%|████▏     | 397/938 [00:28<00:39, 13.80it/s, loss=0.869, v_num=15]
Epoch 0:  42%|████▏     | 397/938 [00:28<00:39, 13.80it/s, loss=0.864, v_num=15]
Epoch 0:  42%|████▏     | 398/938 [00:28<00:39, 13.80it/s, loss=0.877, v_num=15]
Epoch 0:  43%|████▎     | 399/938 [00:28<00:39, 13.79it/s, loss=0.877, v_num=15]
Epoch 0:  43%|████▎     | 399/938 [00:28<00:39, 13.79it/s, loss=0.862, v_num=15]
Epoch 0:  43%|████▎     | 400/938 [00:29<00:39, 13.79it/s, loss=0.863, v_num=15]
Epoch 0:  43%|████▎     | 401/938 [00:29<00:38, 13.78it/s, loss=0.863, v_num=15]
Epoch 0:  43%|████▎     | 401/938 [00:29<00:38, 13.78it/s, loss=0.865, v_num=15]
Epoch 0:  43%|████▎     | 402/938 [00:29<00:38, 13.78it/s, loss=0.859, v_num=15]
Epoch 0:  43%|████▎     | 403/938 [00:29<00:38, 13.79it/s, loss=0.859, v_num=15]
Epoch 0:  43%|████▎     | 403/938 [00:29<00:38, 13.79it/s, loss=0.849, v_num=15]
Epoch 0:  43%|████▎     | 404/938 [00:29<00:38, 13.79it/s, loss=0.846, v_num=15]
Epoch 0:  43%|████▎     | 405/938 [00:29<00:38, 13.78it/s, loss=0.846, v_num=15]
Epoch 0:  43%|████▎     | 405/938 [00:29<00:38, 13.78it/s, loss=0.848, v_num=15]
Epoch 0:  43%|████▎     | 406/938 [00:29<00:38, 13.78it/s, loss=0.831, v_num=15]
Epoch 0:  43%|████▎     | 407/938 [00:29<00:38, 13.78it/s, loss=0.831, v_num=15]
Epoch 0:  43%|████▎     | 407/938 [00:29<00:38, 13.78it/s, loss=0.816, v_num=15]
Epoch 0:  43%|████▎     | 408/938 [00:29<00:38, 13.78it/s, loss=0.814, v_num=15]
Epoch 0:  44%|████▎     | 409/938 [00:29<00:38, 13.79it/s, loss=0.814, v_num=15]
Epoch 0:  44%|████▎     | 409/938 [00:29<00:38, 13.79it/s, loss=0.821, v_num=15]
Epoch 0:  44%|████▎     | 410/938 [00:29<00:38, 13.78it/s, loss=0.824, v_num=15]
Epoch 0:  44%|████▍     | 411/938 [00:29<00:38, 13.78it/s, loss=0.824, v_num=15]
Epoch 0:  44%|████▍     | 411/938 [00:29<00:38, 13.78it/s, loss=0.822, v_num=15]
Epoch 0:  44%|████▍     | 412/938 [00:29<00:38, 13.78it/s, loss=0.818, v_num=15]
Epoch 0:  44%|████▍     | 413/938 [00:29<00:38, 13.79it/s, loss=0.818, v_num=15]
Epoch 0:  44%|████▍     | 413/938 [00:29<00:38, 13.79it/s, loss=0.823, v_num=15]
Epoch 0:  44%|████▍     | 414/938 [00:30<00:38, 13.78it/s, loss=0.824, v_num=15]
Epoch 0:  44%|████▍     | 415/938 [00:30<00:37, 13.79it/s, loss=0.824, v_num=15]
Epoch 0:  44%|████▍     | 415/938 [00:30<00:37, 13.79it/s, loss=0.827, v_num=15]
Epoch 0:  44%|████▍     | 416/938 [00:30<00:37, 13.78it/s, loss=0.822, v_num=15]
Epoch 0:  44%|████▍     | 417/938 [00:30<00:37, 13.79it/s, loss=0.822, v_num=15]
Epoch 0:  44%|████▍     | 417/938 [00:30<00:37, 13.79it/s, loss=0.819, v_num=15]
Epoch 0:  45%|████▍     | 418/938 [00:30<00:37, 13.78it/s, loss=0.809, v_num=15]
Epoch 0:  45%|████▍     | 419/938 [00:30<00:37, 13.78it/s, loss=0.809, v_num=15]
Epoch 0:  45%|████▍     | 419/938 [00:30<00:37, 13.78it/s, loss=0.821, v_num=15]
Epoch 0:  45%|████▍     | 420/938 [00:30<00:37, 13.78it/s, loss=0.825, v_num=15]
Epoch 0:  45%|████▍     | 421/938 [00:30<00:37, 13.78it/s, loss=0.825, v_num=15]
Epoch 0:  45%|████▍     | 421/938 [00:30<00:37, 13.78it/s, loss=0.829, v_num=15]
Epoch 0:  45%|████▍     | 422/938 [00:30<00:37, 13.78it/s, loss=0.826, v_num=15]
Epoch 0:  45%|████▌     | 423/938 [00:30<00:37, 13.78it/s, loss=0.826, v_num=15]
Epoch 0:  45%|████▌     | 423/938 [00:30<00:37, 13.78it/s, loss=0.814, v_num=15]
Epoch 0:  45%|████▌     | 424/938 [00:30<00:37, 13.77it/s, loss=0.799, v_num=15]
Epoch 0:  45%|████▌     | 425/938 [00:30<00:37, 13.77it/s, loss=0.799, v_num=15]
Epoch 0:  45%|████▌     | 425/938 [00:30<00:37, 13.77it/s, loss=0.804, v_num=15]
Epoch 0:  45%|████▌     | 426/938 [00:30<00:37, 13.77it/s, loss=0.823, v_num=15]
Epoch 0:  46%|████▌     | 427/938 [00:31<00:37, 13.77it/s, loss=0.823, v_num=15]
Epoch 0:  46%|████▌     | 427/938 [00:31<00:37, 13.77it/s, loss=0.825, v_num=15]
Epoch 0:  46%|████▌     | 428/938 [00:31<00:37, 13.78it/s, loss=0.821, v_num=15]
Epoch 0:  46%|████▌     | 429/938 [00:31<00:36, 13.78it/s, loss=0.821, v_num=15]
Epoch 0:  46%|████▌     | 429/938 [00:31<00:36, 13.78it/s, loss=0.811, v_num=15]
Epoch 0:  46%|████▌     | 430/938 [00:31<00:36, 13.78it/s, loss=0.802, v_num=15]
Epoch 0:  46%|████▌     | 431/938 [00:31<00:36, 13.78it/s, loss=0.802, v_num=15]
Epoch 0:  46%|████▌     | 431/938 [00:31<00:36, 13.78it/s, loss=0.808, v_num=15]
Epoch 0:  46%|████▌     | 432/938 [00:31<00:36, 13.79it/s, loss=0.807, v_num=15]
Epoch 0:  46%|████▌     | 433/938 [00:31<00:36, 13.80it/s, loss=0.807, v_num=15]
Epoch 0:  46%|████▌     | 433/938 [00:31<00:36, 13.80it/s, loss=0.801, v_num=15]
Epoch 0:  46%|████▋     | 434/938 [00:31<00:36, 13.80it/s, loss=0.798, v_num=15]
Epoch 0:  46%|████▋     | 435/938 [00:31<00:36, 13.80it/s, loss=0.798, v_num=15]
Epoch 0:  46%|████▋     | 435/938 [00:31<00:36, 13.80it/s, loss=0.794, v_num=15]
Epoch 0:  46%|████▋     | 436/938 [00:31<00:36, 13.79it/s, loss=0.793, v_num=15]
Epoch 0:  47%|████▋     | 437/938 [00:31<00:36, 13.79it/s, loss=0.793, v_num=15]
Epoch 0:  47%|████▋     | 437/938 [00:31<00:36, 13.79it/s, loss=0.79, v_num=15] 
Epoch 0:  47%|████▋     | 438/938 [00:31<00:36, 13.79it/s, loss=0.789, v_num=15]
Epoch 0:  47%|████▋     | 439/938 [00:31<00:36, 13.80it/s, loss=0.789, v_num=15]
Epoch 0:  47%|████▋     | 439/938 [00:31<00:36, 13.80it/s, loss=0.793, v_num=15]
Epoch 0:  47%|████▋     | 440/938 [00:31<00:36, 13.79it/s, loss=0.795, v_num=15]
Epoch 0:  47%|████▋     | 441/938 [00:31<00:36, 13.79it/s, loss=0.795, v_num=15]
Epoch 0:  47%|████▋     | 441/938 [00:31<00:36, 13.79it/s, loss=0.788, v_num=15]
Epoch 0:  47%|████▋     | 442/938 [00:32<00:35, 13.79it/s, loss=0.793, v_num=15]
Epoch 0:  47%|████▋     | 443/938 [00:32<00:35, 13.80it/s, loss=0.793, v_num=15]
Epoch 0:  47%|████▋     | 443/938 [00:32<00:35, 13.80it/s, loss=0.802, v_num=15]
Epoch 0:  47%|████▋     | 444/938 [00:32<00:35, 13.80it/s, loss=0.806, v_num=15]
Epoch 0:  47%|████▋     | 445/938 [00:32<00:35, 13.79it/s, loss=0.806, v_num=15]
Epoch 0:  47%|████▋     | 445/938 [00:32<00:35, 13.79it/s, loss=0.798, v_num=15]
Epoch 0:  48%|████▊     | 446/938 [00:32<00:35, 13.79it/s, loss=0.78, v_num=15] 
Epoch 0:  48%|████▊     | 447/938 [00:32<00:35, 13.79it/s, loss=0.78, v_num=15]
Epoch 0:  48%|████▊     | 447/938 [00:32<00:35, 13.79it/s, loss=0.786, v_num=15]
Epoch 0:  48%|████▊     | 448/938 [00:32<00:35, 13.79it/s, loss=0.782, v_num=15]
Epoch 0:  48%|████▊     | 449/938 [00:32<00:35, 13.80it/s, loss=0.782, v_num=15]
Epoch 0:  48%|████▊     | 449/938 [00:32<00:35, 13.80it/s, loss=0.772, v_num=15]
Epoch 0:  48%|████▊     | 450/938 [00:32<00:35, 13.79it/s, loss=0.78, v_num=15] 
Epoch 0:  48%|████▊     | 451/938 [00:32<00:35, 13.79it/s, loss=0.78, v_num=15]
Epoch 0:  48%|████▊     | 451/938 [00:32<00:35, 13.79it/s, loss=0.774, v_num=15]
Epoch 0:  48%|████▊     | 452/938 [00:32<00:35, 13.80it/s, loss=0.77, v_num=15] 
Epoch 0:  48%|████▊     | 453/938 [00:32<00:35, 13.79it/s, loss=0.77, v_num=15]
Epoch 0:  48%|████▊     | 453/938 [00:32<00:35, 13.79it/s, loss=0.773, v_num=15]
Epoch 0:  48%|████▊     | 454/938 [00:32<00:35, 13.79it/s, loss=0.773, v_num=15]
Epoch 0:  49%|████▊     | 455/938 [00:32<00:35, 13.79it/s, loss=0.773, v_num=15]
Epoch 0:  49%|████▊     | 455/938 [00:32<00:35, 13.79it/s, loss=0.785, v_num=15]
Epoch 0:  49%|████▊     | 456/938 [00:33<00:34, 13.79it/s, loss=0.788, v_num=15]
Epoch 0:  49%|████▊     | 457/938 [00:33<00:34, 13.79it/s, loss=0.788, v_num=15]
Epoch 0:  49%|████▊     | 457/938 [00:33<00:34, 13.79it/s, loss=0.785, v_num=15]
Epoch 0:  49%|████▉     | 458/938 [00:33<00:34, 13.79it/s, loss=0.788, v_num=15]
Epoch 0:  49%|████▉     | 459/938 [00:33<00:34, 13.79it/s, loss=0.788, v_num=15]
Epoch 0:  49%|████▉     | 459/938 [00:33<00:34, 13.79it/s, loss=0.786, v_num=15]
Epoch 0:  49%|████▉     | 460/938 [00:33<00:34, 13.79it/s, loss=0.787, v_num=15]
Epoch 0:  49%|████▉     | 461/938 [00:33<00:34, 13.79it/s, loss=0.787, v_num=15]
Epoch 0:  49%|████▉     | 461/938 [00:33<00:34, 13.79it/s, loss=0.791, v_num=15]
Epoch 0:  49%|████▉     | 462/938 [00:33<00:34, 13.79it/s, loss=0.783, v_num=15]
Epoch 0:  49%|████▉     | 463/938 [00:33<00:34, 13.79it/s, loss=0.783, v_num=15]
Epoch 0:  49%|████▉     | 463/938 [00:33<00:34, 13.79it/s, loss=0.78, v_num=15] 
Epoch 0:  49%|████▉     | 464/938 [00:33<00:34, 13.79it/s, loss=0.782, v_num=15]
Epoch 0:  50%|████▉     | 465/938 [00:33<00:34, 13.79it/s, loss=0.782, v_num=15]
Epoch 0:  50%|████▉     | 465/938 [00:33<00:34, 13.79it/s, loss=0.792, v_num=15]
Epoch 0:  50%|████▉     | 466/938 [00:33<00:34, 13.79it/s, loss=0.795, v_num=15]
Epoch 0:  50%|████▉     | 467/938 [00:33<00:34, 13.79it/s, loss=0.795, v_num=15]
Epoch 0:  50%|████▉     | 467/938 [00:33<00:34, 13.79it/s, loss=0.795, v_num=15]
Epoch 0:  50%|████▉     | 468/938 [00:33<00:34, 13.79it/s, loss=0.793, v_num=15]
Epoch 0:  50%|█████     | 469/938 [00:33<00:33, 13.80it/s, loss=0.793, v_num=15]
Epoch 0:  50%|█████     | 469/938 [00:33<00:33, 13.80it/s, loss=0.807, v_num=15]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]

Validating:   0%|          | 2/469 [00:00<00:23, 19.88it/s]
Epoch 0:  50%|█████     | 472/938 [00:34<00:33, 13.84it/s, loss=0.807, v_num=15]

Validating:   1%|          | 5/469 [00:00<00:21, 21.63it/s]
Epoch 0:  51%|█████     | 475/938 [00:34<00:33, 13.88it/s, loss=0.807, v_num=15]

Validating:   2%|▏         | 8/469 [00:00<00:19, 23.72it/s]
Epoch 0:  51%|█████     | 478/938 [00:34<00:33, 13.92it/s, loss=0.807, v_num=15]

Validating:   2%|▏         | 11/469 [00:00<00:18, 24.26it/s]
Epoch 0:  51%|█████▏    | 481/938 [00:34<00:32, 13.96it/s, loss=0.807, v_num=15]

Validating:   3%|▎         | 14/469 [00:00<00:19, 23.09it/s]
Epoch 0:  52%|█████▏    | 484/938 [00:34<00:32, 13.99it/s, loss=0.807, v_num=15]

Validating:   4%|▎         | 17/469 [00:00<00:18, 24.69it/s]
Epoch 0:  52%|█████▏    | 487/938 [00:34<00:32, 14.03it/s, loss=0.807, v_num=15]

Validating:   4%|▍         | 20/469 [00:00<00:17, 25.88it/s]
Epoch 0:  52%|█████▏    | 490/938 [00:34<00:31, 14.07it/s, loss=0.807, v_num=15]

Validating:   5%|▍         | 23/469 [00:00<00:17, 25.79it/s]
Epoch 0:  53%|█████▎    | 493/938 [00:34<00:31, 14.11it/s, loss=0.807, v_num=15]

Validating:   6%|▌         | 26/469 [00:01<00:17, 25.50it/s]
Epoch 0:  53%|█████▎    | 496/938 [00:35<00:31, 14.15it/s, loss=0.807, v_num=15]

Validating:   6%|▌         | 29/469 [00:01<00:18, 24.15it/s]
Epoch 0:  53%|█████▎    | 499/938 [00:35<00:30, 14.18it/s, loss=0.807, v_num=15]

Validating:   7%|▋         | 32/469 [00:01<00:18, 24.14it/s]
Epoch 0:  54%|█████▎    | 502/938 [00:35<00:30, 14.21it/s, loss=0.807, v_num=15]

Validating:   7%|▋         | 35/469 [00:01<00:17, 24.34it/s]
Epoch 0:  54%|█████▍    | 505/938 [00:35<00:30, 14.25it/s, loss=0.807, v_num=15]

Validating:   8%|▊         | 38/469 [00:01<00:19, 22.65it/s]
Epoch 0:  54%|█████▍    | 508/938 [00:35<00:30, 14.27it/s, loss=0.807, v_num=15]

Validating:   9%|▊         | 41/469 [00:01<00:18, 22.86it/s]
Epoch 0:  54%|█████▍    | 511/938 [00:35<00:29, 14.31it/s, loss=0.807, v_num=15]

Validating:   9%|▉         | 44/469 [00:01<00:17, 23.62it/s]
Epoch 0:  55%|█████▍    | 514/938 [00:35<00:29, 14.34it/s, loss=0.807, v_num=15]

Validating:  10%|█         | 47/469 [00:02<00:19, 21.50it/s]
Epoch 0:  55%|█████▌    | 517/938 [00:36<00:29, 14.36it/s, loss=0.807, v_num=15]

Validating:  11%|█         | 50/469 [00:02<00:18, 22.88it/s]
Epoch 0:  55%|█████▌    | 520/938 [00:36<00:29, 14.40it/s, loss=0.807, v_num=15]

Validating:  11%|█▏        | 53/469 [00:02<00:17, 23.81it/s]
Epoch 0:  56%|█████▌    | 523/938 [00:36<00:28, 14.43it/s, loss=0.807, v_num=15]

Validating:  12%|█▏        | 56/469 [00:02<00:17, 24.24it/s]
Epoch 0:  56%|█████▌    | 526/938 [00:36<00:28, 14.47it/s, loss=0.807, v_num=15]

Validating:  13%|█▎        | 59/469 [00:02<00:16, 24.70it/s]
Epoch 0:  56%|█████▋    | 529/938 [00:36<00:28, 14.51it/s, loss=0.807, v_num=15]

Validating:  13%|█▎        | 62/469 [00:02<00:15, 25.63it/s]
Epoch 0:  57%|█████▋    | 532/938 [00:36<00:27, 14.55it/s, loss=0.807, v_num=15]

Validating:  14%|█▍        | 65/469 [00:02<00:16, 24.82it/s]
Epoch 0:  57%|█████▋    | 535/938 [00:36<00:27, 14.58it/s, loss=0.807, v_num=15]

Validating:  14%|█▍        | 68/469 [00:02<00:16, 24.78it/s]
Epoch 0:  57%|█████▋    | 538/938 [00:36<00:27, 14.61it/s, loss=0.807, v_num=15]

Validating:  15%|█▌        | 71/469 [00:02<00:16, 23.95it/s]
Epoch 0:  58%|█████▊    | 541/938 [00:36<00:27, 14.64it/s, loss=0.807, v_num=15]

Validating:  16%|█▌        | 74/469 [00:03<00:16, 23.91it/s]
Epoch 0:  58%|█████▊    | 544/938 [00:37<00:26, 14.67it/s, loss=0.807, v_num=15]

Validating:  16%|█▋        | 77/469 [00:03<00:16, 24.39it/s]
Epoch 0:  58%|█████▊    | 547/938 [00:37<00:26, 14.70it/s, loss=0.807, v_num=15]

Validating:  17%|█▋        | 80/469 [00:03<00:15, 24.47it/s]
Epoch 0:  59%|█████▊    | 550/938 [00:37<00:26, 14.74it/s, loss=0.807, v_num=15]

Validating:  18%|█▊        | 83/469 [00:03<00:15, 24.78it/s]
Epoch 0:  59%|█████▉    | 553/938 [00:37<00:26, 14.77it/s, loss=0.807, v_num=15]

Validating:  18%|█▊        | 86/469 [00:03<00:15, 24.89it/s]
Epoch 0:  59%|█████▉    | 556/938 [00:37<00:25, 14.80it/s, loss=0.807, v_num=15]

Validating:  19%|█▉        | 89/469 [00:03<00:15, 25.26it/s]
Epoch 0:  60%|█████▉    | 559/938 [00:37<00:25, 14.84it/s, loss=0.807, v_num=15]

Validating:  20%|█▉        | 92/469 [00:03<00:15, 25.05it/s]
Epoch 0:  60%|█████▉    | 562/938 [00:37<00:25, 14.87it/s, loss=0.807, v_num=15]

Validating:  20%|██        | 95/469 [00:03<00:14, 25.14it/s]
Epoch 0:  60%|██████    | 565/938 [00:37<00:25, 14.90it/s, loss=0.807, v_num=15]

Validating:  21%|██        | 98/469 [00:04<00:15, 24.16it/s]
Epoch 0:  61%|██████    | 568/938 [00:38<00:24, 14.93it/s, loss=0.807, v_num=15]

Validating:  22%|██▏       | 101/469 [00:04<00:14, 25.20it/s]
Epoch 0:  61%|██████    | 571/938 [00:38<00:24, 14.96it/s, loss=0.807, v_num=15]

Validating:  22%|██▏       | 104/469 [00:04<00:14, 24.83it/s]
Epoch 0:  61%|██████    | 574/938 [00:38<00:24, 14.99it/s, loss=0.807, v_num=15]

Validating:  23%|██▎       | 107/469 [00:04<00:14, 25.77it/s]
Epoch 0:  62%|██████▏   | 577/938 [00:38<00:24, 15.03it/s, loss=0.807, v_num=15]

Validating:  23%|██▎       | 110/469 [00:04<00:14, 25.60it/s]
Epoch 0:  62%|██████▏   | 580/938 [00:38<00:23, 15.06it/s, loss=0.807, v_num=15]

Validating:  24%|██▍       | 113/469 [00:04<00:14, 25.19it/s]
Epoch 0:  62%|██████▏   | 583/938 [00:38<00:23, 15.09it/s, loss=0.807, v_num=15]

Validating:  25%|██▍       | 116/469 [00:04<00:13, 25.31it/s]
Epoch 0:  62%|██████▏   | 586/938 [00:38<00:23, 15.12it/s, loss=0.807, v_num=15]

Validating:  25%|██▌       | 119/469 [00:04<00:13, 25.11it/s]
Epoch 0:  63%|██████▎   | 589/938 [00:38<00:23, 15.15it/s, loss=0.807, v_num=15]

Validating:  26%|██▌       | 122/469 [00:04<00:13, 25.47it/s]
Epoch 0:  63%|██████▎   | 592/938 [00:38<00:22, 15.18it/s, loss=0.807, v_num=15]

Validating:  27%|██▋       | 125/469 [00:05<00:13, 25.81it/s]
Epoch 0:  63%|██████▎   | 595/938 [00:39<00:22, 15.22it/s, loss=0.807, v_num=15]

Validating:  27%|██▋       | 128/469 [00:05<00:13, 26.01it/s]
Epoch 0:  64%|██████▍   | 598/938 [00:39<00:22, 15.25it/s, loss=0.807, v_num=15]

Validating:  28%|██▊       | 131/469 [00:05<00:12, 26.11it/s]
Epoch 0:  64%|██████▍   | 601/938 [00:39<00:22, 15.28it/s, loss=0.807, v_num=15]

Validating:  29%|██▊       | 134/469 [00:05<00:13, 25.11it/s]
Epoch 0:  64%|██████▍   | 604/938 [00:39<00:21, 15.31it/s, loss=0.807, v_num=15]

Validating:  29%|██▉       | 137/469 [00:05<00:13, 24.98it/s]
Epoch 0:  65%|██████▍   | 607/938 [00:39<00:21, 15.34it/s, loss=0.807, v_num=15]

Validating:  30%|██▉       | 140/469 [00:05<00:13, 24.92it/s]
Epoch 0:  65%|██████▌   | 610/938 [00:39<00:21, 15.37it/s, loss=0.807, v_num=15]

Validating:  30%|███       | 143/469 [00:05<00:12, 25.27it/s]
Epoch 0:  65%|██████▌   | 613/938 [00:39<00:21, 15.40it/s, loss=0.807, v_num=15]

Validating:  31%|███       | 146/469 [00:05<00:12, 25.24it/s]
Epoch 0:  66%|██████▌   | 616/938 [00:39<00:20, 15.43it/s, loss=0.807, v_num=15]

Validating:  32%|███▏      | 149/469 [00:06<00:12, 25.19it/s]
Epoch 0:  66%|██████▌   | 619/938 [00:40<00:20, 15.45it/s, loss=0.807, v_num=15]

Validating:  32%|███▏      | 152/469 [00:06<00:12, 26.09it/s]
Epoch 0:  66%|██████▋   | 622/938 [00:40<00:20, 15.49it/s, loss=0.807, v_num=15]

Validating:  33%|███▎      | 155/469 [00:06<00:11, 26.22it/s]
Epoch 0:  67%|██████▋   | 625/938 [00:40<00:20, 15.52it/s, loss=0.807, v_num=15]

Validating:  34%|███▎      | 158/469 [00:06<00:12, 24.98it/s]
Epoch 0:  67%|██████▋   | 628/938 [00:40<00:19, 15.54it/s, loss=0.807, v_num=15]

Validating:  34%|███▍      | 161/469 [00:06<00:12, 24.96it/s]
Epoch 0:  67%|██████▋   | 631/938 [00:40<00:19, 15.57it/s, loss=0.807, v_num=15]

Validating:  35%|███▍      | 164/469 [00:06<00:12, 25.27it/s]
Epoch 0:  68%|██████▊   | 634/938 [00:40<00:19, 15.60it/s, loss=0.807, v_num=15]

Validating:  36%|███▌      | 167/469 [00:06<00:11, 25.70it/s]
Epoch 0:  68%|██████▊   | 637/938 [00:40<00:19, 15.63it/s, loss=0.807, v_num=15]

Validating:  36%|███▌      | 170/469 [00:06<00:11, 25.45it/s]
Epoch 0:  68%|██████▊   | 640/938 [00:40<00:19, 15.66it/s, loss=0.807, v_num=15]

Validating:  37%|███▋      | 173/469 [00:06<00:11, 25.51it/s]
Epoch 0:  69%|██████▊   | 643/938 [00:40<00:18, 15.69it/s, loss=0.807, v_num=15]

Validating:  38%|███▊      | 176/469 [00:07<00:11, 25.21it/s]
Epoch 0:  69%|██████▉   | 646/938 [00:41<00:18, 15.71it/s, loss=0.807, v_num=15]

Validating:  38%|███▊      | 179/469 [00:07<00:11, 25.47it/s]
Epoch 0:  69%|██████▉   | 649/938 [00:41<00:18, 15.74it/s, loss=0.807, v_num=15]

Validating:  39%|███▉      | 182/469 [00:07<00:11, 24.59it/s]
Epoch 0:  70%|██████▉   | 652/938 [00:41<00:18, 15.76it/s, loss=0.807, v_num=15]

Validating:  39%|███▉      | 185/469 [00:07<00:11, 25.47it/s]
Epoch 0:  70%|██████▉   | 655/938 [00:41<00:17, 15.80it/s, loss=0.807, v_num=15]

Validating:  40%|████      | 188/469 [00:07<00:11, 23.58it/s]
Epoch 0:  70%|███████   | 658/938 [00:41<00:17, 15.81it/s, loss=0.807, v_num=15]

Validating:  41%|████      | 191/469 [00:07<00:11, 23.28it/s]
Epoch 0:  70%|███████   | 661/938 [00:41<00:17, 15.83it/s, loss=0.807, v_num=15]

Validating:  41%|████▏     | 194/469 [00:07<00:12, 21.94it/s]
Epoch 0:  71%|███████   | 664/938 [00:41<00:17, 15.85it/s, loss=0.807, v_num=15]

Validating:  42%|████▏     | 197/469 [00:08<00:12, 22.14it/s]
Epoch 0:  71%|███████   | 667/938 [00:42<00:17, 15.87it/s, loss=0.807, v_num=15]

Validating:  43%|████▎     | 200/469 [00:08<00:12, 21.86it/s]
Epoch 0:  71%|███████▏  | 670/938 [00:42<00:16, 15.89it/s, loss=0.807, v_num=15]

Validating:  43%|████▎     | 203/469 [00:08<00:11, 22.39it/s]
Epoch 0:  72%|███████▏  | 673/938 [00:42<00:16, 15.91it/s, loss=0.807, v_num=15]

Validating:  44%|████▍     | 206/469 [00:08<00:11, 22.91it/s]
Epoch 0:  72%|███████▏  | 676/938 [00:42<00:16, 15.93it/s, loss=0.807, v_num=15]

Validating:  45%|████▍     | 209/469 [00:08<00:11, 23.46it/s]
Epoch 0:  72%|███████▏  | 679/938 [00:42<00:16, 15.96it/s, loss=0.807, v_num=15]

Validating:  45%|████▌     | 212/469 [00:08<00:11, 23.02it/s]
Epoch 0:  73%|███████▎  | 682/938 [00:42<00:16, 15.98it/s, loss=0.807, v_num=15]

Validating:  46%|████▌     | 215/469 [00:08<00:10, 24.12it/s]
Epoch 0:  73%|███████▎  | 685/938 [00:42<00:15, 16.01it/s, loss=0.807, v_num=15]

Validating:  46%|████▋     | 218/469 [00:08<00:10, 24.29it/s]
Epoch 0:  73%|███████▎  | 688/938 [00:42<00:15, 16.03it/s, loss=0.807, v_num=15]

Validating:  47%|████▋     | 221/469 [00:09<00:10, 23.82it/s]
Epoch 0:  74%|███████▎  | 691/938 [00:43<00:15, 16.05it/s, loss=0.807, v_num=15]

Validating:  48%|████▊     | 224/469 [00:09<00:10, 24.01it/s]
Epoch 0:  74%|███████▍  | 694/938 [00:43<00:15, 16.08it/s, loss=0.807, v_num=15]

Validating:  48%|████▊     | 227/469 [00:09<00:10, 23.72it/s]
Epoch 0:  74%|███████▍  | 697/938 [00:43<00:14, 16.10it/s, loss=0.807, v_num=15]

Validating:  49%|████▉     | 230/469 [00:09<00:10, 23.41it/s]
Epoch 0:  75%|███████▍  | 700/938 [00:43<00:14, 16.12it/s, loss=0.807, v_num=15]

Validating:  50%|████▉     | 233/469 [00:09<00:09, 23.95it/s]
Epoch 0:  75%|███████▍  | 703/938 [00:43<00:14, 16.14it/s, loss=0.807, v_num=15]

Validating:  50%|█████     | 236/469 [00:09<00:09, 24.22it/s]
Epoch 0:  75%|███████▌  | 706/938 [00:43<00:14, 16.17it/s, loss=0.807, v_num=15]

Validating:  51%|█████     | 239/469 [00:09<00:09, 24.52it/s]
Epoch 0:  76%|███████▌  | 709/938 [00:43<00:14, 16.19it/s, loss=0.807, v_num=15]

Validating:  52%|█████▏    | 242/469 [00:09<00:09, 25.07it/s]
Epoch 0:  76%|███████▌  | 712/938 [00:43<00:13, 16.22it/s, loss=0.807, v_num=15]

Validating:  52%|█████▏    | 245/469 [00:10<00:09, 23.86it/s]
Epoch 0:  76%|███████▌  | 715/938 [00:44<00:13, 16.23it/s, loss=0.807, v_num=15]

Validating:  53%|█████▎    | 248/469 [00:10<00:09, 24.00it/s]
Epoch 0:  77%|███████▋  | 718/938 [00:44<00:13, 16.26it/s, loss=0.807, v_num=15]

Validating:  54%|█████▎    | 251/469 [00:10<00:09, 24.07it/s]
Epoch 0:  77%|███████▋  | 721/938 [00:44<00:13, 16.28it/s, loss=0.807, v_num=15]

Validating:  54%|█████▍    | 254/469 [00:10<00:08, 24.13it/s]
Epoch 0:  77%|███████▋  | 724/938 [00:44<00:13, 16.30it/s, loss=0.807, v_num=15]

Validating:  55%|█████▍    | 257/469 [00:10<00:08, 24.59it/s]
Epoch 0:  78%|███████▊  | 727/938 [00:44<00:12, 16.33it/s, loss=0.807, v_num=15]

Validating:  55%|█████▌    | 260/469 [00:10<00:08, 24.74it/s]
Epoch 0:  78%|███████▊  | 730/938 [00:44<00:12, 16.35it/s, loss=0.807, v_num=15]

Validating:  56%|█████▌    | 263/469 [00:10<00:08, 24.73it/s]
Epoch 0:  78%|███████▊  | 733/938 [00:44<00:12, 16.37it/s, loss=0.807, v_num=15]

Validating:  57%|█████▋    | 266/469 [00:10<00:08, 25.14it/s]
Epoch 0:  78%|███████▊  | 736/938 [00:44<00:12, 16.40it/s, loss=0.807, v_num=15]

Validating:  57%|█████▋    | 269/469 [00:11<00:08, 24.90it/s]
Epoch 0:  79%|███████▉  | 739/938 [00:45<00:12, 16.42it/s, loss=0.807, v_num=15]

Validating:  58%|█████▊    | 272/469 [00:11<00:07, 25.26it/s]
Epoch 0:  79%|███████▉  | 742/938 [00:45<00:11, 16.44it/s, loss=0.807, v_num=15]

Validating:  59%|█████▊    | 275/469 [00:11<00:07, 24.81it/s]
Epoch 0:  79%|███████▉  | 745/938 [00:45<00:11, 16.46it/s, loss=0.807, v_num=15]

Validating:  59%|█████▉    | 278/469 [00:11<00:07, 24.47it/s]
Epoch 0:  80%|███████▉  | 748/938 [00:45<00:11, 16.48it/s, loss=0.807, v_num=15]

Validating:  60%|█████▉    | 281/469 [00:11<00:07, 25.17it/s]
Epoch 0:  80%|████████  | 751/938 [00:45<00:11, 16.51it/s, loss=0.807, v_num=15]

Validating:  61%|██████    | 284/469 [00:11<00:07, 25.07it/s]
Epoch 0:  80%|████████  | 754/938 [00:45<00:11, 16.53it/s, loss=0.807, v_num=15]

Validating:  61%|██████    | 287/469 [00:11<00:07, 25.65it/s]
Epoch 0:  81%|████████  | 757/938 [00:45<00:10, 16.56it/s, loss=0.807, v_num=15]

Validating:  62%|██████▏   | 290/469 [00:11<00:07, 25.40it/s]
Epoch 0:  81%|████████  | 760/938 [00:45<00:10, 16.58it/s, loss=0.807, v_num=15]

Validating:  62%|██████▏   | 293/469 [00:11<00:06, 25.63it/s]
Epoch 0:  81%|████████▏ | 763/938 [00:45<00:10, 16.60it/s, loss=0.807, v_num=15]

Validating:  63%|██████▎   | 296/469 [00:12<00:06, 25.93it/s]
Epoch 0:  82%|████████▏ | 766/938 [00:46<00:10, 16.63it/s, loss=0.807, v_num=15]

Validating:  64%|██████▍   | 299/469 [00:12<00:06, 26.00it/s]
Epoch 0:  82%|████████▏ | 769/938 [00:46<00:10, 16.65it/s, loss=0.807, v_num=15]

Validating:  64%|██████▍   | 302/469 [00:12<00:06, 25.44it/s]
Epoch 0:  82%|████████▏ | 772/938 [00:46<00:09, 16.67it/s, loss=0.807, v_num=15]

Validating:  65%|██████▌   | 305/469 [00:12<00:06, 25.42it/s]
Epoch 0:  83%|████████▎ | 775/938 [00:46<00:09, 16.69it/s, loss=0.807, v_num=15]

Validating:  66%|██████▌   | 308/469 [00:12<00:06, 25.31it/s]
Epoch 0:  83%|████████▎ | 778/938 [00:46<00:09, 16.72it/s, loss=0.807, v_num=15]

Validating:  66%|██████▋   | 311/469 [00:12<00:06, 25.25it/s]
Epoch 0:  83%|████████▎ | 781/938 [00:46<00:09, 16.74it/s, loss=0.807, v_num=15]

Validating:  67%|██████▋   | 314/469 [00:12<00:06, 24.01it/s]
Epoch 0:  84%|████████▎ | 784/938 [00:46<00:09, 16.75it/s, loss=0.807, v_num=15]

Validating:  68%|██████▊   | 317/469 [00:12<00:06, 22.65it/s]
Epoch 0:  84%|████████▍ | 787/938 [00:46<00:09, 16.76it/s, loss=0.807, v_num=15]

Validating:  68%|██████▊   | 320/469 [00:13<00:06, 22.73it/s]
Epoch 0:  84%|████████▍ | 790/938 [00:47<00:08, 16.78it/s, loss=0.807, v_num=15]

Validating:  69%|██████▉   | 323/469 [00:13<00:06, 23.55it/s]
Epoch 0:  85%|████████▍ | 793/938 [00:47<00:08, 16.80it/s, loss=0.807, v_num=15]

Validating:  70%|██████▉   | 326/469 [00:13<00:06, 23.75it/s]
Epoch 0:  85%|████████▍ | 796/938 [00:47<00:08, 16.82it/s, loss=0.807, v_num=15]

Validating:  70%|███████   | 329/469 [00:13<00:05, 24.70it/s]
Epoch 0:  85%|████████▌ | 799/938 [00:47<00:08, 16.84it/s, loss=0.807, v_num=15]

Validating:  71%|███████   | 332/469 [00:13<00:05, 23.18it/s]
Epoch 0:  86%|████████▌ | 802/938 [00:47<00:08, 16.85it/s, loss=0.807, v_num=15]

Validating:  71%|███████▏  | 335/469 [00:13<00:05, 24.46it/s]
Epoch 0:  86%|████████▌ | 805/938 [00:47<00:07, 16.88it/s, loss=0.807, v_num=15]

Validating:  72%|███████▏  | 338/469 [00:13<00:05, 24.48it/s]
Epoch 0:  86%|████████▌ | 808/938 [00:47<00:07, 16.90it/s, loss=0.807, v_num=15]

Validating:  73%|███████▎  | 341/469 [00:13<00:05, 24.82it/s]
Epoch 0:  86%|████████▋ | 811/938 [00:47<00:07, 16.92it/s, loss=0.807, v_num=15]

Validating:  73%|███████▎  | 344/469 [00:14<00:05, 24.11it/s]
Epoch 0:  87%|████████▋ | 814/938 [00:48<00:07, 16.94it/s, loss=0.807, v_num=15]

Validating:  74%|███████▍  | 347/469 [00:14<00:04, 24.42it/s]
Epoch 0:  87%|████████▋ | 817/938 [00:48<00:07, 16.96it/s, loss=0.807, v_num=15]

Validating:  75%|███████▍  | 350/469 [00:14<00:04, 25.11it/s]
Epoch 0:  87%|████████▋ | 820/938 [00:48<00:06, 16.98it/s, loss=0.807, v_num=15]

Validating:  75%|███████▌  | 353/469 [00:14<00:04, 25.37it/s]
Epoch 0:  88%|████████▊ | 823/938 [00:48<00:06, 17.00it/s, loss=0.807, v_num=15]

Validating:  76%|███████▌  | 356/469 [00:14<00:04, 26.13it/s]
Epoch 0:  88%|████████▊ | 826/938 [00:48<00:06, 17.03it/s, loss=0.807, v_num=15]

Validating:  77%|███████▋  | 359/469 [00:14<00:04, 25.77it/s]
Epoch 0:  88%|████████▊ | 829/938 [00:48<00:06, 17.05it/s, loss=0.807, v_num=15]

Validating:  77%|███████▋  | 362/469 [00:14<00:04, 25.41it/s]
Epoch 0:  89%|████████▊ | 832/938 [00:48<00:06, 17.06it/s, loss=0.807, v_num=15]

Validating:  78%|███████▊  | 365/469 [00:14<00:04, 25.28it/s]
Epoch 0:  89%|████████▉ | 835/938 [00:48<00:06, 17.08it/s, loss=0.807, v_num=15]

Validating:  78%|███████▊  | 368/469 [00:15<00:04, 24.08it/s]
Epoch 0:  89%|████████▉ | 838/938 [00:49<00:05, 17.10it/s, loss=0.807, v_num=15]

Validating:  79%|███████▉  | 371/469 [00:15<00:03, 24.61it/s]
Epoch 0:  90%|████████▉ | 841/938 [00:49<00:05, 17.12it/s, loss=0.807, v_num=15]

Validating:  80%|███████▉  | 374/469 [00:15<00:03, 24.89it/s]
Epoch 0:  90%|████████▉ | 844/938 [00:49<00:05, 17.14it/s, loss=0.807, v_num=15]

Validating:  80%|████████  | 377/469 [00:15<00:03, 24.37it/s]
Epoch 0:  90%|█████████ | 847/938 [00:49<00:05, 17.15it/s, loss=0.807, v_num=15]

Validating:  81%|████████  | 380/469 [00:15<00:03, 23.90it/s]
Epoch 0:  91%|█████████ | 850/938 [00:49<00:05, 17.17it/s, loss=0.807, v_num=15]

Validating:  82%|████████▏ | 383/469 [00:15<00:03, 24.74it/s]
Epoch 0:  91%|█████████ | 853/938 [00:49<00:04, 17.19it/s, loss=0.807, v_num=15]

Validating:  82%|████████▏ | 386/469 [00:15<00:03, 25.00it/s]
Epoch 0:  91%|█████████▏| 856/938 [00:49<00:04, 17.21it/s, loss=0.807, v_num=15]

Validating:  83%|████████▎ | 389/469 [00:15<00:03, 24.98it/s]
Epoch 0:  92%|█████████▏| 859/938 [00:49<00:04, 17.23it/s, loss=0.807, v_num=15]

Validating:  84%|████████▎ | 392/469 [00:15<00:03, 23.98it/s]
Epoch 0:  92%|█████████▏| 862/938 [00:49<00:04, 17.24it/s, loss=0.807, v_num=15]

Validating:  84%|████████▍ | 395/469 [00:16<00:03, 24.02it/s]
Epoch 0:  92%|█████████▏| 865/938 [00:50<00:04, 17.26it/s, loss=0.807, v_num=15]

Validating:  85%|████████▍ | 398/469 [00:16<00:03, 23.64it/s]
Epoch 0:  93%|█████████▎| 868/938 [00:50<00:04, 17.27it/s, loss=0.807, v_num=15]

Validating:  86%|████████▌ | 401/469 [00:16<00:02, 23.76it/s]
Epoch 0:  93%|█████████▎| 871/938 [00:50<00:03, 17.29it/s, loss=0.807, v_num=15]

Validating:  86%|████████▌ | 404/469 [00:16<00:02, 24.31it/s]
Epoch 0:  93%|█████████▎| 874/938 [00:50<00:03, 17.31it/s, loss=0.807, v_num=15]

Validating:  87%|████████▋ | 407/469 [00:16<00:02, 25.00it/s]
Epoch 0:  93%|█████████▎| 877/938 [00:50<00:03, 17.33it/s, loss=0.807, v_num=15]

Validating:  87%|████████▋ | 410/469 [00:16<00:02, 25.47it/s]
Epoch 0:  94%|█████████▍| 880/938 [00:50<00:03, 17.35it/s, loss=0.807, v_num=15]

Validating:  88%|████████▊ | 413/469 [00:16<00:02, 25.33it/s]
Epoch 0:  94%|█████████▍| 883/938 [00:50<00:03, 17.37it/s, loss=0.807, v_num=15]

Validating:  89%|████████▊ | 416/469 [00:16<00:02, 25.29it/s]
Epoch 0:  94%|█████████▍| 886/938 [00:50<00:02, 17.39it/s, loss=0.807, v_num=15]

Validating:  90%|████████▉ | 420/469 [00:17<00:01, 26.86it/s]
Epoch 0:  95%|█████████▍| 890/938 [00:51<00:02, 17.42it/s, loss=0.807, v_num=15]

Validating:  90%|█████████ | 423/469 [00:17<00:01, 26.81it/s]
Epoch 0:  95%|█████████▌| 894/938 [00:51<00:02, 17.45it/s, loss=0.807, v_num=15]

Validating:  91%|█████████ | 426/469 [00:17<00:01, 27.41it/s]
Epoch 0:  96%|█████████▌| 898/938 [00:51<00:02, 17.48it/s, loss=0.807, v_num=15]

Validating:  91%|█████████▏| 429/469 [00:17<00:01, 27.00it/s]

Validating:  92%|█████████▏| 432/469 [00:17<00:01, 26.86it/s]
Epoch 0:  96%|█████████▌| 902/938 [00:51<00:02, 17.50it/s, loss=0.807, v_num=15]

Validating:  93%|█████████▎| 435/469 [00:17<00:01, 26.67it/s]
Epoch 0:  97%|█████████▋| 906/938 [00:51<00:01, 17.53it/s, loss=0.807, v_num=15]

Validating:  93%|█████████▎| 438/469 [00:17<00:01, 26.87it/s]
Epoch 0:  97%|█████████▋| 910/938 [00:51<00:01, 17.56it/s, loss=0.807, v_num=15]

Validating:  94%|█████████▍| 441/469 [00:17<00:01, 26.76it/s]

Validating:  95%|█████████▍| 444/469 [00:17<00:00, 25.84it/s]
Epoch 0:  97%|█████████▋| 914/938 [00:51<00:01, 17.58it/s, loss=0.807, v_num=15]

Validating:  95%|█████████▌| 447/469 [00:18<00:00, 24.85it/s]
Epoch 0:  98%|█████████▊| 918/938 [00:52<00:01, 17.60it/s, loss=0.807, v_num=15]

Validating:  96%|█████████▌| 450/469 [00:18<00:00, 24.63it/s]
Epoch 0:  98%|█████████▊| 922/938 [00:52<00:00, 17.62it/s, loss=0.807, v_num=15]

Validating:  97%|█████████▋| 453/469 [00:18<00:00, 24.76it/s]

Validating:  97%|█████████▋| 456/469 [00:18<00:00, 26.07it/s]
Epoch 0:  99%|█████████▊| 926/938 [00:52<00:00, 17.65it/s, loss=0.807, v_num=15]

Validating:  98%|█████████▊| 459/469 [00:18<00:00, 26.51it/s]
Epoch 0:  99%|█████████▉| 930/938 [00:52<00:00, 17.67it/s, loss=0.807, v_num=15]

Validating:  99%|█████████▊| 462/469 [00:18<00:00, 26.73it/s]
Epoch 0: 100%|█████████▉| 934/938 [00:52<00:00, 17.70it/s, loss=0.807, v_num=15]

Validating:  99%|█████████▉| 465/469 [00:18<00:00, 26.29it/s]
Epoch 0: 100%|██████████| 938/938 [00:52<00:00, 17.73it/s, loss=0.807, v_num=15]

Validating: 100%|██████████| 469/469 [00:18<00:00, 29.30it/s]
Epoch 0: 100%|██████████| 938/938 [00:52<00:00, 17.72it/s, loss=0.807, v_num=15, val_rmse=0.674]

                                                             
Epoch 0: 100%|██████████| 938/938 [00:52<00:00, 17.71it/s, loss=0.807, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 0:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.807, v_num=15, val_rmse=0.674, train_rmse=1.150]          
Epoch 1:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.807, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   0%|          | 1/938 [00:00<01:13, 12.69it/s, loss=0.801, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   0%|          | 2/938 [00:00<01:08, 13.60it/s, loss=0.804, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   0%|          | 3/938 [00:00<01:04, 14.51it/s, loss=0.805, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   0%|          | 4/938 [00:00<01:04, 14.51it/s, loss=0.805, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   0%|          | 4/938 [00:00<01:04, 14.49it/s, loss=0.801, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   1%|          | 5/938 [00:00<01:04, 14.43it/s, loss=0.795, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   1%|          | 6/938 [00:00<01:03, 14.66it/s, loss=0.781, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   1%|          | 7/938 [00:00<01:05, 14.25it/s, loss=0.779, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   1%|          | 8/938 [00:00<01:06, 14.07it/s, loss=0.779, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   1%|          | 8/938 [00:00<01:06, 14.05it/s, loss=0.78, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:   1%|          | 9/938 [00:00<01:07, 13.84it/s, loss=0.779, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   1%|          | 10/938 [00:00<01:05, 14.10it/s, loss=0.776, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   1%|          | 11/938 [00:00<01:04, 14.35it/s, loss=0.762, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   1%|▏         | 12/938 [00:00<01:05, 14.15it/s, loss=0.762, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   1%|▏         | 12/938 [00:00<01:05, 14.14it/s, loss=0.766, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   1%|▏         | 13/938 [00:00<01:05, 14.21it/s, loss=0.77, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:   1%|▏         | 14/938 [00:00<01:04, 14.23it/s, loss=0.77, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   2%|▏         | 15/938 [00:01<01:04, 14.24it/s, loss=0.773, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   2%|▏         | 16/938 [00:01<01:03, 14.41it/s, loss=0.773, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   2%|▏         | 16/938 [00:01<01:04, 14.40it/s, loss=0.762, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   2%|▏         | 17/938 [00:01<01:04, 14.31it/s, loss=0.767, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   2%|▏         | 18/938 [00:01<01:04, 14.28it/s, loss=0.766, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   2%|▏         | 19/938 [00:01<01:03, 14.43it/s, loss=0.778, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   2%|▏         | 20/938 [00:01<01:03, 14.45it/s, loss=0.778, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   2%|▏         | 20/938 [00:01<01:03, 14.44it/s, loss=0.778, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   2%|▏         | 21/938 [00:01<01:03, 14.43it/s, loss=0.781, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   2%|▏         | 22/938 [00:01<01:03, 14.50it/s, loss=0.778, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   2%|▏         | 23/938 [00:01<01:02, 14.54it/s, loss=0.787, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   3%|▎         | 24/938 [00:01<01:02, 14.53it/s, loss=0.787, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   3%|▎         | 24/938 [00:01<01:02, 14.52it/s, loss=0.787, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   3%|▎         | 25/938 [00:01<01:02, 14.59it/s, loss=0.791, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   3%|▎         | 26/938 [00:01<01:02, 14.51it/s, loss=0.797, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   3%|▎         | 27/938 [00:01<01:02, 14.57it/s, loss=0.798, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   3%|▎         | 28/938 [00:01<01:02, 14.56it/s, loss=0.798, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   3%|▎         | 28/938 [00:01<01:02, 14.56it/s, loss=0.799, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   3%|▎         | 29/938 [00:01<01:02, 14.54it/s, loss=0.795, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   3%|▎         | 30/938 [00:02<01:02, 14.52it/s, loss=0.793, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   3%|▎         | 31/938 [00:02<01:02, 14.58it/s, loss=0.795, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   3%|▎         | 32/938 [00:02<01:02, 14.58it/s, loss=0.795, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   3%|▎         | 32/938 [00:02<01:02, 14.58it/s, loss=0.793, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   4%|▎         | 33/938 [00:02<01:02, 14.60it/s, loss=0.798, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   4%|▎         | 34/938 [00:02<01:01, 14.65it/s, loss=0.798, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   4%|▎         | 35/938 [00:02<01:01, 14.62it/s, loss=0.799, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   4%|▍         | 36/938 [00:02<01:01, 14.64it/s, loss=0.799, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   4%|▍         | 36/938 [00:02<01:01, 14.64it/s, loss=0.807, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   4%|▍         | 37/938 [00:02<01:01, 14.65it/s, loss=0.798, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   4%|▍         | 38/938 [00:02<01:01, 14.66it/s, loss=0.798, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   4%|▍         | 39/938 [00:02<01:01, 14.68it/s, loss=0.791, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   4%|▍         | 40/938 [00:02<01:00, 14.72it/s, loss=0.791, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   4%|▍         | 40/938 [00:02<01:01, 14.72it/s, loss=0.781, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   4%|▍         | 41/938 [00:02<01:01, 14.70it/s, loss=0.774, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   4%|▍         | 42/938 [00:02<01:00, 14.70it/s, loss=0.773, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   5%|▍         | 43/938 [00:02<01:00, 14.74it/s, loss=0.766, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   5%|▍         | 44/938 [00:02<01:00, 14.71it/s, loss=0.766, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   5%|▍         | 44/938 [00:02<01:00, 14.71it/s, loss=0.767, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   5%|▍         | 45/938 [00:03<01:00, 14.75it/s, loss=0.762, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   5%|▍         | 46/938 [00:03<01:00, 14.77it/s, loss=0.767, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   5%|▌         | 47/938 [00:03<01:00, 14.63it/s, loss=0.772, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   5%|▌         | 48/938 [00:03<01:00, 14.66it/s, loss=0.772, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   5%|▌         | 48/938 [00:03<01:00, 14.66it/s, loss=0.773, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   5%|▌         | 49/938 [00:03<01:00, 14.70it/s, loss=0.776, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   5%|▌         | 50/938 [00:03<01:00, 14.73it/s, loss=0.772, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   5%|▌         | 51/938 [00:03<01:00, 14.71it/s, loss=0.77, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:   6%|▌         | 52/938 [00:03<00:59, 14.78it/s, loss=0.77, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   6%|▌         | 52/938 [00:03<00:59, 14.78it/s, loss=0.77, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   6%|▌         | 53/938 [00:03<00:59, 14.76it/s, loss=0.762, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   6%|▌         | 54/938 [00:03<01:00, 14.72it/s, loss=0.761, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   6%|▌         | 55/938 [00:03<00:59, 14.77it/s, loss=0.752, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   6%|▌         | 56/938 [00:03<00:59, 14.79it/s, loss=0.752, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   6%|▌         | 56/938 [00:03<00:59, 14.78it/s, loss=0.744, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   6%|▌         | 57/938 [00:03<00:59, 14.79it/s, loss=0.749, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   6%|▌         | 58/938 [00:03<00:59, 14.82it/s, loss=0.752, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   6%|▋         | 59/938 [00:03<00:59, 14.81it/s, loss=0.757, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   6%|▋         | 60/938 [00:04<00:59, 14.84it/s, loss=0.757, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   6%|▋         | 60/938 [00:04<00:59, 14.84it/s, loss=0.752, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   7%|▋         | 61/938 [00:04<00:59, 14.83it/s, loss=0.751, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   7%|▋         | 62/938 [00:04<00:59, 14.83it/s, loss=0.758, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   7%|▋         | 63/938 [00:04<00:58, 14.86it/s, loss=0.758, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   7%|▋         | 64/938 [00:04<00:58, 14.86it/s, loss=0.758, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   7%|▋         | 64/938 [00:04<00:58, 14.86it/s, loss=0.757, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   7%|▋         | 65/938 [00:04<00:58, 14.86it/s, loss=0.765, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   7%|▋         | 66/938 [00:04<00:58, 14.87it/s, loss=0.758, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   7%|▋         | 67/938 [00:04<00:58, 14.88it/s, loss=0.752, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   7%|▋         | 68/938 [00:04<00:58, 14.86it/s, loss=0.752, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   7%|▋         | 68/938 [00:04<00:58, 14.86it/s, loss=0.747, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   7%|▋         | 69/938 [00:04<00:58, 14.88it/s, loss=0.748, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   7%|▋         | 70/938 [00:04<00:58, 14.87it/s, loss=0.751, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   8%|▊         | 71/938 [00:04<00:58, 14.83it/s, loss=0.753, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   8%|▊         | 72/938 [00:04<00:58, 14.82it/s, loss=0.753, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   8%|▊         | 72/938 [00:04<00:58, 14.82it/s, loss=0.743, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   8%|▊         | 73/938 [00:04<00:58, 14.83it/s, loss=0.74, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:   8%|▊         | 74/938 [00:04<00:58, 14.81it/s, loss=0.742, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   8%|▊         | 75/938 [00:05<00:58, 14.81it/s, loss=0.75, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:   8%|▊         | 76/938 [00:05<00:58, 14.83it/s, loss=0.75, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   8%|▊         | 76/938 [00:05<00:58, 14.83it/s, loss=0.751, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   8%|▊         | 77/938 [00:05<00:58, 14.79it/s, loss=0.744, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   8%|▊         | 78/938 [00:05<00:58, 14.78it/s, loss=0.739, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   8%|▊         | 79/938 [00:05<00:58, 14.80it/s, loss=0.732, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   9%|▊         | 80/938 [00:05<00:58, 14.78it/s, loss=0.732, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   9%|▊         | 80/938 [00:05<00:58, 14.78it/s, loss=0.741, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   9%|▊         | 81/938 [00:05<00:57, 14.80it/s, loss=0.743, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   9%|▊         | 82/938 [00:05<00:57, 14.80it/s, loss=0.73, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:   9%|▉         | 83/938 [00:05<00:57, 14.76it/s, loss=0.729, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   9%|▉         | 84/938 [00:05<00:57, 14.75it/s, loss=0.729, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   9%|▉         | 84/938 [00:05<00:57, 14.75it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   9%|▉         | 85/938 [00:05<00:58, 14.70it/s, loss=0.721, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   9%|▉         | 86/938 [00:05<00:58, 14.65it/s, loss=0.713, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   9%|▉         | 87/938 [00:05<00:57, 14.68it/s, loss=0.707, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   9%|▉         | 88/938 [00:06<00:58, 14.61it/s, loss=0.707, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   9%|▉         | 88/938 [00:06<00:58, 14.61it/s, loss=0.716, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:   9%|▉         | 89/938 [00:06<00:58, 14.60it/s, loss=0.717, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  10%|▉         | 90/938 [00:06<00:57, 14.63it/s, loss=0.726, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  10%|▉         | 91/938 [00:06<00:57, 14.63it/s, loss=0.732, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  10%|▉         | 92/938 [00:06<00:57, 14.62it/s, loss=0.732, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  10%|▉         | 92/938 [00:06<00:57, 14.62it/s, loss=0.737, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  10%|▉         | 93/938 [00:06<00:57, 14.61it/s, loss=0.738, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  10%|█         | 94/938 [00:06<00:57, 14.63it/s, loss=0.737, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  10%|█         | 95/938 [00:06<00:57, 14.65it/s, loss=0.735, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  10%|█         | 96/938 [00:06<00:57, 14.66it/s, loss=0.735, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  10%|█         | 96/938 [00:06<00:57, 14.66it/s, loss=0.734, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  10%|█         | 97/938 [00:06<00:57, 14.64it/s, loss=0.745, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  10%|█         | 98/938 [00:06<00:57, 14.66it/s, loss=0.741, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  11%|█         | 99/938 [00:06<00:57, 14.67it/s, loss=0.744, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  11%|█         | 100/938 [00:06<00:57, 14.63it/s, loss=0.744, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  11%|█         | 100/938 [00:06<00:57, 14.63it/s, loss=0.739, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  11%|█         | 101/938 [00:06<00:57, 14.64it/s, loss=0.747, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  11%|█         | 102/938 [00:06<00:57, 14.66it/s, loss=0.751, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  11%|█         | 103/938 [00:07<00:56, 14.68it/s, loss=0.751, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  11%|█         | 104/938 [00:07<00:56, 14.69it/s, loss=0.751, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  11%|█         | 104/938 [00:07<00:56, 14.69it/s, loss=0.759, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  11%|█         | 105/938 [00:07<00:56, 14.70it/s, loss=0.751, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  11%|█▏        | 106/938 [00:07<00:56, 14.67it/s, loss=0.762, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  11%|█▏        | 107/938 [00:07<00:56, 14.66it/s, loss=0.773, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  12%|█▏        | 108/938 [00:07<00:56, 14.69it/s, loss=0.773, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  12%|█▏        | 108/938 [00:07<00:56, 14.69it/s, loss=0.765, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  12%|█▏        | 109/938 [00:07<00:56, 14.66it/s, loss=0.771, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  12%|█▏        | 110/938 [00:07<00:56, 14.67it/s, loss=0.76, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  12%|█▏        | 111/938 [00:07<00:56, 14.66it/s, loss=0.756, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  12%|█▏        | 112/938 [00:07<00:56, 14.66it/s, loss=0.756, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  12%|█▏        | 112/938 [00:07<00:56, 14.66it/s, loss=0.75, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  12%|█▏        | 113/938 [00:07<00:56, 14.64it/s, loss=0.754, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  12%|█▏        | 114/938 [00:07<00:56, 14.57it/s, loss=0.745, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  12%|█▏        | 115/938 [00:07<00:56, 14.55it/s, loss=0.744, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  12%|█▏        | 116/938 [00:07<00:56, 14.55it/s, loss=0.744, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  12%|█▏        | 116/938 [00:07<00:56, 14.54it/s, loss=0.75, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  12%|█▏        | 117/938 [00:08<00:56, 14.53it/s, loss=0.742, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  13%|█▎        | 118/938 [00:08<00:56, 14.53it/s, loss=0.739, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  13%|█▎        | 119/938 [00:08<00:56, 14.54it/s, loss=0.745, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  13%|█▎        | 120/938 [00:08<00:56, 14.54it/s, loss=0.745, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  13%|█▎        | 120/938 [00:08<00:56, 14.54it/s, loss=0.747, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  13%|█▎        | 121/938 [00:08<00:56, 14.53it/s, loss=0.74, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  13%|█▎        | 122/938 [00:08<00:56, 14.54it/s, loss=0.738, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  13%|█▎        | 123/938 [00:08<00:56, 14.53it/s, loss=0.736, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  13%|█▎        | 124/938 [00:08<00:56, 14.53it/s, loss=0.736, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  13%|█▎        | 124/938 [00:08<00:56, 14.53it/s, loss=0.731, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  13%|█▎        | 125/938 [00:08<00:55, 14.55it/s, loss=0.738, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  13%|█▎        | 126/938 [00:08<00:55, 14.53it/s, loss=0.732, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  14%|█▎        | 127/938 [00:08<00:55, 14.53it/s, loss=0.731, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  14%|█▎        | 128/938 [00:08<00:55, 14.55it/s, loss=0.731, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  14%|█▎        | 128/938 [00:08<00:55, 14.55it/s, loss=0.732, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  14%|█▍        | 129/938 [00:08<00:55, 14.56it/s, loss=0.714, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  14%|█▍        | 130/938 [00:08<00:55, 14.56it/s, loss=0.726, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  14%|█▍        | 131/938 [00:08<00:55, 14.57it/s, loss=0.727, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  14%|█▍        | 132/938 [00:09<00:55, 14.57it/s, loss=0.727, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  14%|█▍        | 132/938 [00:09<00:55, 14.57it/s, loss=0.732, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  14%|█▍        | 133/938 [00:09<00:55, 14.54it/s, loss=0.735, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  14%|█▍        | 134/938 [00:09<00:55, 14.57it/s, loss=0.755, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  14%|█▍        | 135/938 [00:09<00:55, 14.58it/s, loss=0.758, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  14%|█▍        | 136/938 [00:09<00:54, 14.58it/s, loss=0.758, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  14%|█▍        | 136/938 [00:09<00:55, 14.58it/s, loss=0.758, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  15%|█▍        | 137/938 [00:09<00:54, 14.60it/s, loss=0.757, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  15%|█▍        | 138/938 [00:09<00:54, 14.59it/s, loss=0.769, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  15%|█▍        | 139/938 [00:09<00:54, 14.60it/s, loss=0.761, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  15%|█▍        | 140/938 [00:09<00:54, 14.60it/s, loss=0.761, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  15%|█▍        | 140/938 [00:09<00:54, 14.60it/s, loss=0.766, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  15%|█▌        | 141/938 [00:09<00:54, 14.60it/s, loss=0.773, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  15%|█▌        | 142/938 [00:09<00:54, 14.59it/s, loss=0.775, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  15%|█▌        | 143/938 [00:09<00:54, 14.60it/s, loss=0.775, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  15%|█▌        | 144/938 [00:09<00:54, 14.59it/s, loss=0.775, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  15%|█▌        | 144/938 [00:09<00:54, 14.59it/s, loss=0.773, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  15%|█▌        | 145/938 [00:09<00:54, 14.58it/s, loss=0.772, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  16%|█▌        | 146/938 [00:09<00:54, 14.60it/s, loss=0.781, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  16%|█▌        | 147/938 [00:10<00:54, 14.61it/s, loss=0.775, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  16%|█▌        | 148/938 [00:10<00:54, 14.59it/s, loss=0.775, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  16%|█▌        | 148/938 [00:10<00:54, 14.59it/s, loss=0.773, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  16%|█▌        | 149/938 [00:10<00:54, 14.60it/s, loss=0.784, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  16%|█▌        | 150/938 [00:10<00:54, 14.58it/s, loss=0.767, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  16%|█▌        | 151/938 [00:10<00:53, 14.59it/s, loss=0.766, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  16%|█▌        | 152/938 [00:10<00:53, 14.59it/s, loss=0.766, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  16%|█▌        | 152/938 [00:10<00:53, 14.59it/s, loss=0.773, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  16%|█▋        | 153/938 [00:10<00:53, 14.59it/s, loss=0.762, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  16%|█▋        | 154/938 [00:10<00:53, 14.59it/s, loss=0.746, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  17%|█▋        | 155/938 [00:10<00:53, 14.59it/s, loss=0.741, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  17%|█▋        | 156/938 [00:10<00:53, 14.58it/s, loss=0.741, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  17%|█▋        | 156/938 [00:10<00:53, 14.58it/s, loss=0.739, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  17%|█▋        | 157/938 [00:10<00:53, 14.59it/s, loss=0.744, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  17%|█▋        | 158/938 [00:10<00:53, 14.59it/s, loss=0.736, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  17%|█▋        | 159/938 [00:10<00:53, 14.60it/s, loss=0.736, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  17%|█▋        | 160/938 [00:10<00:53, 14.61it/s, loss=0.736, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  17%|█▋        | 160/938 [00:10<00:53, 14.61it/s, loss=0.735, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  17%|█▋        | 161/938 [00:11<00:53, 14.60it/s, loss=0.736, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  17%|█▋        | 162/938 [00:11<00:53, 14.60it/s, loss=0.734, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  17%|█▋        | 163/938 [00:11<00:53, 14.60it/s, loss=0.748, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  17%|█▋        | 164/938 [00:11<00:52, 14.61it/s, loss=0.748, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  17%|█▋        | 164/938 [00:11<00:52, 14.61it/s, loss=0.759, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  18%|█▊        | 165/938 [00:11<00:52, 14.62it/s, loss=0.756, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  18%|█▊        | 166/938 [00:11<00:52, 14.59it/s, loss=0.742, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  18%|█▊        | 167/938 [00:11<00:52, 14.59it/s, loss=0.739, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  18%|█▊        | 168/938 [00:11<00:52, 14.59it/s, loss=0.739, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  18%|█▊        | 168/938 [00:11<00:52, 14.59it/s, loss=0.747, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  18%|█▊        | 169/938 [00:11<00:52, 14.59it/s, loss=0.753, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  18%|█▊        | 170/938 [00:11<00:52, 14.59it/s, loss=0.755, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  18%|█▊        | 171/938 [00:11<00:52, 14.60it/s, loss=0.752, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  18%|█▊        | 172/938 [00:11<00:52, 14.59it/s, loss=0.752, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  18%|█▊        | 172/938 [00:11<00:52, 14.59it/s, loss=0.747, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  18%|█▊        | 173/938 [00:11<00:52, 14.59it/s, loss=0.766, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  19%|█▊        | 174/938 [00:11<00:52, 14.57it/s, loss=0.769, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  19%|█▊        | 175/938 [00:12<00:52, 14.57it/s, loss=0.77, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  19%|█▉        | 176/938 [00:12<00:52, 14.58it/s, loss=0.77, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  19%|█▉        | 176/938 [00:12<00:52, 14.58it/s, loss=0.779, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  19%|█▉        | 177/938 [00:12<00:52, 14.59it/s, loss=0.774, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  19%|█▉        | 178/938 [00:12<00:52, 14.59it/s, loss=0.777, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  19%|█▉        | 179/938 [00:12<00:51, 14.61it/s, loss=0.779, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  19%|█▉        | 180/938 [00:12<00:51, 14.60it/s, loss=0.779, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  19%|█▉        | 180/938 [00:12<00:51, 14.60it/s, loss=0.776, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  19%|█▉        | 181/938 [00:12<00:51, 14.61it/s, loss=0.77, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  19%|█▉        | 182/938 [00:12<00:51, 14.61it/s, loss=0.778, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  20%|█▉        | 183/938 [00:12<00:51, 14.59it/s, loss=0.77, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  20%|█▉        | 184/938 [00:12<00:51, 14.59it/s, loss=0.77, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  20%|█▉        | 184/938 [00:12<00:51, 14.59it/s, loss=0.763, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  20%|█▉        | 185/938 [00:12<00:51, 14.60it/s, loss=0.771, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  20%|█▉        | 186/938 [00:12<00:51, 14.60it/s, loss=0.776, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  20%|█▉        | 187/938 [00:12<00:51, 14.59it/s, loss=0.77, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  20%|██        | 188/938 [00:12<00:51, 14.62it/s, loss=0.77, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  20%|██        | 188/938 [00:12<00:51, 14.62it/s, loss=0.769, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  20%|██        | 189/938 [00:12<00:51, 14.61it/s, loss=0.767, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  20%|██        | 190/938 [00:13<00:51, 14.61it/s, loss=0.775, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  20%|██        | 191/938 [00:13<00:51, 14.61it/s, loss=0.769, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  20%|██        | 192/938 [00:13<00:51, 14.62it/s, loss=0.769, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  20%|██        | 192/938 [00:13<00:51, 14.62it/s, loss=0.77, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  21%|██        | 193/938 [00:13<00:51, 14.60it/s, loss=0.765, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  21%|██        | 194/938 [00:13<00:50, 14.62it/s, loss=0.76, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  21%|██        | 195/938 [00:13<00:50, 14.63it/s, loss=0.751, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  21%|██        | 196/938 [00:13<00:50, 14.63it/s, loss=0.751, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  21%|██        | 196/938 [00:13<00:50, 14.63it/s, loss=0.744, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  21%|██        | 197/938 [00:13<00:50, 14.63it/s, loss=0.738, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  21%|██        | 198/938 [00:13<00:50, 14.63it/s, loss=0.734, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  21%|██        | 199/938 [00:13<00:50, 14.64it/s, loss=0.732, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  21%|██▏       | 200/938 [00:13<00:50, 14.63it/s, loss=0.732, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  21%|██▏       | 200/938 [00:13<00:50, 14.63it/s, loss=0.724, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  21%|██▏       | 201/938 [00:13<00:50, 14.63it/s, loss=0.718, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  22%|██▏       | 202/938 [00:13<00:50, 14.63it/s, loss=0.713, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  22%|██▏       | 203/938 [00:13<00:50, 14.63it/s, loss=0.706, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  22%|██▏       | 204/938 [00:13<00:50, 14.63it/s, loss=0.706, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  22%|██▏       | 204/938 [00:13<00:50, 14.63it/s, loss=0.702, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  22%|██▏       | 205/938 [00:14<00:50, 14.63it/s, loss=0.702, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  22%|██▏       | 206/938 [00:14<00:50, 14.60it/s, loss=0.712, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  22%|██▏       | 207/938 [00:14<00:50, 14.61it/s, loss=0.713, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  22%|██▏       | 208/938 [00:14<00:49, 14.61it/s, loss=0.713, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  22%|██▏       | 208/938 [00:14<00:49, 14.61it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  22%|██▏       | 209/938 [00:14<00:49, 14.60it/s, loss=0.735, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  22%|██▏       | 210/938 [00:14<00:49, 14.61it/s, loss=0.731, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  22%|██▏       | 211/938 [00:14<00:49, 14.61it/s, loss=0.735, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  23%|██▎       | 212/938 [00:14<00:49, 14.62it/s, loss=0.735, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  23%|██▎       | 212/938 [00:14<00:49, 14.62it/s, loss=0.729, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  23%|██▎       | 213/938 [00:14<00:49, 14.62it/s, loss=0.721, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  23%|██▎       | 214/938 [00:14<00:49, 14.61it/s, loss=0.728, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  23%|██▎       | 215/938 [00:14<00:49, 14.59it/s, loss=0.736, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  23%|██▎       | 216/938 [00:14<00:49, 14.57it/s, loss=0.736, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  23%|██▎       | 216/938 [00:14<00:49, 14.57it/s, loss=0.737, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  23%|██▎       | 217/938 [00:14<00:49, 14.57it/s, loss=0.74, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  23%|██▎       | 218/938 [00:14<00:49, 14.58it/s, loss=0.741, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  23%|██▎       | 219/938 [00:15<00:49, 14.58it/s, loss=0.742, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  23%|██▎       | 220/938 [00:15<00:49, 14.59it/s, loss=0.742, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  23%|██▎       | 220/938 [00:15<00:49, 14.59it/s, loss=0.749, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  24%|██▎       | 221/938 [00:15<00:49, 14.60it/s, loss=0.751, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  24%|██▎       | 222/938 [00:15<00:49, 14.60it/s, loss=0.75, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  24%|██▍       | 223/938 [00:15<00:48, 14.60it/s, loss=0.747, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  24%|██▍       | 224/938 [00:15<00:48, 14.59it/s, loss=0.747, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  24%|██▍       | 224/938 [00:15<00:48, 14.59it/s, loss=0.757, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  24%|██▍       | 225/938 [00:15<00:48, 14.60it/s, loss=0.751, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  24%|██▍       | 226/938 [00:15<00:48, 14.60it/s, loss=0.743, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  24%|██▍       | 227/938 [00:15<00:48, 14.61it/s, loss=0.75, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  24%|██▍       | 228/938 [00:15<00:48, 14.60it/s, loss=0.75, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  24%|██▍       | 228/938 [00:15<00:48, 14.60it/s, loss=0.735, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  24%|██▍       | 229/938 [00:15<00:48, 14.61it/s, loss=0.724, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  25%|██▍       | 230/938 [00:15<00:48, 14.62it/s, loss=0.724, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  25%|██▍       | 231/938 [00:15<00:48, 14.61it/s, loss=0.732, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  25%|██▍       | 232/938 [00:15<00:48, 14.61it/s, loss=0.732, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  25%|██▍       | 232/938 [00:15<00:48, 14.61it/s, loss=0.751, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  25%|██▍       | 233/938 [00:15<00:48, 14.61it/s, loss=0.757, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  25%|██▍       | 234/938 [00:16<00:48, 14.62it/s, loss=0.75, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  25%|██▌       | 235/938 [00:16<00:48, 14.62it/s, loss=0.745, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  25%|██▌       | 236/938 [00:16<00:48, 14.61it/s, loss=0.745, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  25%|██▌       | 236/938 [00:16<00:48, 14.61it/s, loss=0.733, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  25%|██▌       | 237/938 [00:16<00:47, 14.60it/s, loss=0.729, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  25%|██▌       | 238/938 [00:16<00:47, 14.61it/s, loss=0.729, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  25%|██▌       | 239/938 [00:16<00:47, 14.61it/s, loss=0.731, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  26%|██▌       | 240/938 [00:16<00:47, 14.62it/s, loss=0.731, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  26%|██▌       | 240/938 [00:16<00:47, 14.62it/s, loss=0.723, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  26%|██▌       | 241/938 [00:16<00:47, 14.63it/s, loss=0.727, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  26%|██▌       | 242/938 [00:16<00:47, 14.62it/s, loss=0.726, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  26%|██▌       | 243/938 [00:16<00:47, 14.62it/s, loss=0.731, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  26%|██▌       | 244/938 [00:16<00:47, 14.63it/s, loss=0.731, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  26%|██▌       | 244/938 [00:16<00:47, 14.63it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  26%|██▌       | 245/938 [00:16<00:47, 14.63it/s, loss=0.726, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  26%|██▌       | 246/938 [00:16<00:47, 14.63it/s, loss=0.727, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  26%|██▋       | 247/938 [00:16<00:47, 14.65it/s, loss=0.731, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  26%|██▋       | 248/938 [00:16<00:47, 14.64it/s, loss=0.731, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  26%|██▋       | 248/938 [00:16<00:47, 14.64it/s, loss=0.738, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  27%|██▋       | 249/938 [00:17<00:47, 14.64it/s, loss=0.734, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  27%|██▋       | 250/938 [00:17<00:46, 14.64it/s, loss=0.732, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  27%|██▋       | 251/938 [00:17<00:46, 14.62it/s, loss=0.716, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  27%|██▋       | 252/938 [00:17<00:46, 14.61it/s, loss=0.716, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  27%|██▋       | 252/938 [00:17<00:46, 14.61it/s, loss=0.712, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  27%|██▋       | 253/938 [00:17<00:46, 14.62it/s, loss=0.715, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  27%|██▋       | 254/938 [00:17<00:46, 14.62it/s, loss=0.715, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  27%|██▋       | 255/938 [00:17<00:46, 14.61it/s, loss=0.715, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  27%|██▋       | 256/938 [00:17<00:46, 14.60it/s, loss=0.715, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  27%|██▋       | 256/938 [00:17<00:46, 14.60it/s, loss=0.724, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  27%|██▋       | 257/938 [00:17<00:46, 14.60it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  28%|██▊       | 258/938 [00:17<00:46, 14.59it/s, loss=0.726, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  28%|██▊       | 259/938 [00:17<00:46, 14.58it/s, loss=0.727, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  28%|██▊       | 260/938 [00:17<00:46, 14.59it/s, loss=0.727, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  28%|██▊       | 260/938 [00:17<00:46, 14.59it/s, loss=0.726, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  28%|██▊       | 261/938 [00:17<00:46, 14.59it/s, loss=0.723, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  28%|██▊       | 262/938 [00:17<00:46, 14.59it/s, loss=0.723, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  28%|██▊       | 263/938 [00:18<00:46, 14.59it/s, loss=0.73, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  28%|██▊       | 264/938 [00:18<00:46, 14.60it/s, loss=0.73, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  28%|██▊       | 264/938 [00:18<00:46, 14.60it/s, loss=0.723, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  28%|██▊       | 265/938 [00:18<00:46, 14.55it/s, loss=0.729, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  28%|██▊       | 266/938 [00:18<00:46, 14.54it/s, loss=0.727, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  28%|██▊       | 267/938 [00:18<00:46, 14.54it/s, loss=0.724, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  29%|██▊       | 268/938 [00:18<00:46, 14.55it/s, loss=0.724, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  29%|██▊       | 268/938 [00:18<00:46, 14.55it/s, loss=0.71, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  29%|██▊       | 269/938 [00:18<00:45, 14.55it/s, loss=0.704, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  29%|██▉       | 270/938 [00:18<00:45, 14.55it/s, loss=0.708, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  29%|██▉       | 271/938 [00:18<00:45, 14.55it/s, loss=0.731, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  29%|██▉       | 272/938 [00:18<00:45, 14.55it/s, loss=0.731, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  29%|██▉       | 272/938 [00:18<00:45, 14.55it/s, loss=0.721, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  29%|██▉       | 273/938 [00:18<00:45, 14.54it/s, loss=0.716, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  29%|██▉       | 274/938 [00:18<00:45, 14.55it/s, loss=0.716, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  29%|██▉       | 275/938 [00:18<00:45, 14.55it/s, loss=0.714, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  29%|██▉       | 276/938 [00:18<00:45, 14.54it/s, loss=0.714, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  29%|██▉       | 276/938 [00:18<00:45, 14.54it/s, loss=0.719, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  30%|██▉       | 277/938 [00:19<00:45, 14.54it/s, loss=0.718, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  30%|██▉       | 278/938 [00:19<00:45, 14.55it/s, loss=0.726, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  30%|██▉       | 279/938 [00:19<00:45, 14.55it/s, loss=0.717, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  30%|██▉       | 280/938 [00:19<00:45, 14.55it/s, loss=0.717, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  30%|██▉       | 280/938 [00:19<00:45, 14.55it/s, loss=0.723, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  30%|██▉       | 281/938 [00:19<00:45, 14.56it/s, loss=0.72, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  30%|███       | 282/938 [00:19<00:45, 14.55it/s, loss=0.723, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  30%|███       | 283/938 [00:19<00:45, 14.55it/s, loss=0.714, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  30%|███       | 284/938 [00:19<00:44, 14.56it/s, loss=0.714, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  30%|███       | 284/938 [00:19<00:44, 14.56it/s, loss=0.726, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  30%|███       | 285/938 [00:19<00:44, 14.53it/s, loss=0.721, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  30%|███       | 286/938 [00:19<00:44, 14.53it/s, loss=0.722, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  31%|███       | 287/938 [00:19<00:44, 14.52it/s, loss=0.724, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  31%|███       | 288/938 [00:19<00:44, 14.52it/s, loss=0.724, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  31%|███       | 288/938 [00:19<00:44, 14.52it/s, loss=0.72, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  31%|███       | 289/938 [00:19<00:44, 14.52it/s, loss=0.722, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  31%|███       | 290/938 [00:20<00:44, 14.48it/s, loss=0.718, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  31%|███       | 291/938 [00:20<00:44, 14.49it/s, loss=0.701, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  31%|███       | 292/938 [00:20<00:44, 14.49it/s, loss=0.701, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  31%|███       | 292/938 [00:20<00:44, 14.49it/s, loss=0.698, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  31%|███       | 293/938 [00:20<00:44, 14.47it/s, loss=0.697, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  31%|███▏      | 294/938 [00:20<00:44, 14.47it/s, loss=0.697, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  31%|███▏      | 295/938 [00:20<00:44, 14.47it/s, loss=0.699, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  32%|███▏      | 296/938 [00:20<00:44, 14.48it/s, loss=0.699, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  32%|███▏      | 296/938 [00:20<00:44, 14.48it/s, loss=0.693, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  32%|███▏      | 297/938 [00:20<00:44, 14.48it/s, loss=0.692, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  32%|███▏      | 298/938 [00:20<00:44, 14.45it/s, loss=0.687, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  32%|███▏      | 299/938 [00:20<00:44, 14.46it/s, loss=0.7, v_num=15, val_rmse=0.674, train_rmse=1.150]  
Epoch 1:  32%|███▏      | 300/938 [00:20<00:44, 14.47it/s, loss=0.7, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  32%|███▏      | 300/938 [00:20<00:44, 14.47it/s, loss=0.708, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  32%|███▏      | 301/938 [00:20<00:44, 14.48it/s, loss=0.706, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  32%|███▏      | 302/938 [00:20<00:43, 14.48it/s, loss=0.7, v_num=15, val_rmse=0.674, train_rmse=1.150]  
Epoch 1:  32%|███▏      | 303/938 [00:20<00:43, 14.48it/s, loss=0.698, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  32%|███▏      | 304/938 [00:20<00:43, 14.48it/s, loss=0.698, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  32%|███▏      | 304/938 [00:20<00:43, 14.48it/s, loss=0.69, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  33%|███▎      | 305/938 [00:21<00:43, 14.47it/s, loss=0.683, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  33%|███▎      | 306/938 [00:21<00:43, 14.47it/s, loss=0.678, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  33%|███▎      | 307/938 [00:21<00:43, 14.46it/s, loss=0.684, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  33%|███▎      | 308/938 [00:21<00:43, 14.47it/s, loss=0.684, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  33%|███▎      | 308/938 [00:21<00:43, 14.47it/s, loss=0.693, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  33%|███▎      | 309/938 [00:21<00:43, 14.47it/s, loss=0.695, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  33%|███▎      | 310/938 [00:21<00:43, 14.47it/s, loss=0.696, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  33%|███▎      | 311/938 [00:21<00:43, 14.47it/s, loss=0.698, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  33%|███▎      | 312/938 [00:21<00:43, 14.48it/s, loss=0.698, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  33%|███▎      | 312/938 [00:21<00:43, 14.48it/s, loss=0.691, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  33%|███▎      | 313/938 [00:21<00:43, 14.46it/s, loss=0.692, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  33%|███▎      | 314/938 [00:21<00:43, 14.45it/s, loss=0.69, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  34%|███▎      | 315/938 [00:21<00:43, 14.44it/s, loss=0.699, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  34%|███▎      | 316/938 [00:21<00:43, 14.44it/s, loss=0.699, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  34%|███▎      | 316/938 [00:21<00:43, 14.44it/s, loss=0.696, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  34%|███▍      | 317/938 [00:21<00:42, 14.44it/s, loss=0.698, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  34%|███▍      | 318/938 [00:22<00:42, 14.44it/s, loss=0.692, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  34%|███▍      | 319/938 [00:22<00:42, 14.44it/s, loss=0.684, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  34%|███▍      | 320/938 [00:22<00:42, 14.45it/s, loss=0.684, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  34%|███▍      | 320/938 [00:22<00:42, 14.45it/s, loss=0.677, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  34%|███▍      | 321/938 [00:22<00:42, 14.46it/s, loss=0.689, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  34%|███▍      | 322/938 [00:22<00:42, 14.46it/s, loss=0.69, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  34%|███▍      | 323/938 [00:22<00:42, 14.45it/s, loss=0.692, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  35%|███▍      | 324/938 [00:22<00:42, 14.44it/s, loss=0.692, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  35%|███▍      | 324/938 [00:22<00:42, 14.44it/s, loss=0.695, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  35%|███▍      | 325/938 [00:22<00:42, 14.45it/s, loss=0.703, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  35%|███▍      | 326/938 [00:22<00:42, 14.45it/s, loss=0.706, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  35%|███▍      | 327/938 [00:22<00:42, 14.45it/s, loss=0.698, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  35%|███▍      | 328/938 [00:22<00:42, 14.44it/s, loss=0.698, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  35%|███▍      | 328/938 [00:22<00:42, 14.44it/s, loss=0.699, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  35%|███▌      | 329/938 [00:22<00:42, 14.44it/s, loss=0.697, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  35%|███▌      | 330/938 [00:22<00:42, 14.45it/s, loss=0.696, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  35%|███▌      | 331/938 [00:22<00:41, 14.46it/s, loss=0.706, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  35%|███▌      | 332/938 [00:22<00:41, 14.46it/s, loss=0.706, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  35%|███▌      | 332/938 [00:22<00:41, 14.46it/s, loss=0.717, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  36%|███▌      | 333/938 [00:23<00:41, 14.45it/s, loss=0.72, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  36%|███▌      | 334/938 [00:23<00:41, 14.45it/s, loss=0.718, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  36%|███▌      | 335/938 [00:23<00:41, 14.45it/s, loss=0.718, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  36%|███▌      | 336/938 [00:23<00:41, 14.44it/s, loss=0.718, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  36%|███▌      | 336/938 [00:23<00:41, 14.44it/s, loss=0.719, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  36%|███▌      | 337/938 [00:23<00:41, 14.44it/s, loss=0.723, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  36%|███▌      | 338/938 [00:23<00:41, 14.45it/s, loss=0.724, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  36%|███▌      | 339/938 [00:23<00:41, 14.45it/s, loss=0.726, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  36%|███▌      | 340/938 [00:23<00:41, 14.44it/s, loss=0.726, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  36%|███▌      | 340/938 [00:23<00:41, 14.44it/s, loss=0.726, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  36%|███▋      | 341/938 [00:23<00:41, 14.45it/s, loss=0.717, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  36%|███▋      | 342/938 [00:23<00:41, 14.44it/s, loss=0.719, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  37%|███▋      | 343/938 [00:23<00:41, 14.44it/s, loss=0.718, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  37%|███▋      | 344/938 [00:23<00:41, 14.43it/s, loss=0.718, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  37%|███▋      | 344/938 [00:23<00:41, 14.43it/s, loss=0.709, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  37%|███▋      | 345/938 [00:23<00:41, 14.42it/s, loss=0.703, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  37%|███▋      | 346/938 [00:24<00:41, 14.42it/s, loss=0.714, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  37%|███▋      | 347/938 [00:24<00:40, 14.42it/s, loss=0.717, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  37%|███▋      | 348/938 [00:24<00:40, 14.42it/s, loss=0.717, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  37%|███▋      | 348/938 [00:24<00:40, 14.42it/s, loss=0.716, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  37%|███▋      | 349/938 [00:24<00:40, 14.43it/s, loss=0.719, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  37%|███▋      | 350/938 [00:24<00:40, 14.43it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  37%|███▋      | 351/938 [00:24<00:40, 14.42it/s, loss=0.728, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  38%|███▊      | 352/938 [00:24<00:40, 14.43it/s, loss=0.728, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  38%|███▊      | 352/938 [00:24<00:40, 14.43it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  38%|███▊      | 353/938 [00:24<00:40, 14.43it/s, loss=0.719, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  38%|███▊      | 354/938 [00:24<00:40, 14.44it/s, loss=0.723, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  38%|███▊      | 355/938 [00:24<00:40, 14.44it/s, loss=0.724, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  38%|███▊      | 356/938 [00:24<00:40, 14.43it/s, loss=0.724, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  38%|███▊      | 356/938 [00:24<00:40, 14.43it/s, loss=0.723, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  38%|███▊      | 357/938 [00:24<00:40, 14.43it/s, loss=0.721, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  38%|███▊      | 358/938 [00:24<00:40, 14.44it/s, loss=0.723, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  38%|███▊      | 359/938 [00:24<00:40, 14.43it/s, loss=0.726, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  38%|███▊      | 360/938 [00:24<00:40, 14.43it/s, loss=0.726, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  38%|███▊      | 360/938 [00:24<00:40, 14.43it/s, loss=0.729, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  38%|███▊      | 361/938 [00:25<00:39, 14.43it/s, loss=0.736, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  39%|███▊      | 362/938 [00:25<00:39, 14.42it/s, loss=0.737, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  39%|███▊      | 363/938 [00:25<00:39, 14.42it/s, loss=0.74, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  39%|███▉      | 364/938 [00:25<00:39, 14.42it/s, loss=0.74, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  39%|███▉      | 364/938 [00:25<00:39, 14.42it/s, loss=0.754, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  39%|███▉      | 365/938 [00:25<00:39, 14.42it/s, loss=0.756, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  39%|███▉      | 366/938 [00:25<00:39, 14.42it/s, loss=0.743, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  39%|███▉      | 367/938 [00:25<00:39, 14.41it/s, loss=0.746, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  39%|███▉      | 368/938 [00:25<00:39, 14.41it/s, loss=0.746, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  39%|███▉      | 368/938 [00:25<00:39, 14.41it/s, loss=0.744, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  39%|███▉      | 369/938 [00:25<00:39, 14.42it/s, loss=0.743, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  39%|███▉      | 370/938 [00:25<00:39, 14.42it/s, loss=0.751, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  40%|███▉      | 371/938 [00:25<00:39, 14.42it/s, loss=0.742, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  40%|███▉      | 372/938 [00:25<00:39, 14.42it/s, loss=0.742, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  40%|███▉      | 372/938 [00:25<00:39, 14.42it/s, loss=0.74, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  40%|███▉      | 373/938 [00:25<00:39, 14.42it/s, loss=0.744, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  40%|███▉      | 374/938 [00:25<00:39, 14.42it/s, loss=0.74, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  40%|███▉      | 375/938 [00:25<00:39, 14.42it/s, loss=0.729, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  40%|████      | 376/938 [00:26<00:38, 14.43it/s, loss=0.729, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  40%|████      | 376/938 [00:26<00:38, 14.42it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  40%|████      | 377/938 [00:26<00:38, 14.42it/s, loss=0.722, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  40%|████      | 378/938 [00:26<00:38, 14.42it/s, loss=0.72, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  40%|████      | 379/938 [00:26<00:38, 14.43it/s, loss=0.717, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  41%|████      | 380/938 [00:26<00:38, 14.43it/s, loss=0.717, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  41%|████      | 380/938 [00:26<00:38, 14.43it/s, loss=0.713, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  41%|████      | 381/938 [00:26<00:38, 14.43it/s, loss=0.716, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  41%|████      | 382/938 [00:26<00:38, 14.43it/s, loss=0.712, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  41%|████      | 383/938 [00:26<00:38, 14.43it/s, loss=0.706, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  41%|████      | 384/938 [00:26<00:38, 14.43it/s, loss=0.706, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  41%|████      | 384/938 [00:26<00:38, 14.43it/s, loss=0.713, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  41%|████      | 385/938 [00:26<00:38, 14.43it/s, loss=0.71, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  41%|████      | 386/938 [00:26<00:38, 14.43it/s, loss=0.708, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  41%|████▏     | 387/938 [00:26<00:38, 14.44it/s, loss=0.7, v_num=15, val_rmse=0.674, train_rmse=1.150]  
Epoch 1:  41%|████▏     | 388/938 [00:26<00:38, 14.44it/s, loss=0.7, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  41%|████▏     | 388/938 [00:26<00:38, 14.44it/s, loss=0.691, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  41%|████▏     | 389/938 [00:26<00:38, 14.44it/s, loss=0.691, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  42%|████▏     | 390/938 [00:27<00:37, 14.44it/s, loss=0.67, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  42%|████▏     | 391/938 [00:27<00:37, 14.44it/s, loss=0.667, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  42%|████▏     | 392/938 [00:27<00:37, 14.44it/s, loss=0.667, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  42%|████▏     | 392/938 [00:27<00:37, 14.44it/s, loss=0.668, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  42%|████▏     | 393/938 [00:27<00:37, 14.41it/s, loss=0.669, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  42%|████▏     | 394/938 [00:27<00:37, 14.41it/s, loss=0.676, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  42%|████▏     | 395/938 [00:27<00:37, 14.41it/s, loss=0.676, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  42%|████▏     | 396/938 [00:27<00:37, 14.41it/s, loss=0.676, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  42%|████▏     | 396/938 [00:27<00:37, 14.41it/s, loss=0.679, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  42%|████▏     | 397/938 [00:27<00:37, 14.41it/s, loss=0.682, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  42%|████▏     | 398/938 [00:27<00:37, 14.41it/s, loss=0.687, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  43%|████▎     | 399/938 [00:27<00:37, 14.40it/s, loss=0.691, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  43%|████▎     | 400/938 [00:27<00:37, 14.40it/s, loss=0.691, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  43%|████▎     | 400/938 [00:27<00:37, 14.40it/s, loss=0.7, v_num=15, val_rmse=0.674, train_rmse=1.150]  
Epoch 1:  43%|████▎     | 401/938 [00:27<00:37, 14.40it/s, loss=0.694, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  43%|████▎     | 402/938 [00:27<00:37, 14.40it/s, loss=0.697, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  43%|████▎     | 403/938 [00:27<00:37, 14.40it/s, loss=0.7, v_num=15, val_rmse=0.674, train_rmse=1.150]  
Epoch 1:  43%|████▎     | 404/938 [00:28<00:37, 14.40it/s, loss=0.7, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  43%|████▎     | 404/938 [00:28<00:37, 14.40it/s, loss=0.689, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  43%|████▎     | 405/938 [00:28<00:37, 14.40it/s, loss=0.687, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  43%|████▎     | 406/938 [00:28<00:36, 14.40it/s, loss=0.687, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  43%|████▎     | 407/938 [00:28<00:36, 14.40it/s, loss=0.683, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  43%|████▎     | 408/938 [00:28<00:36, 14.40it/s, loss=0.683, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  43%|████▎     | 408/938 [00:28<00:36, 14.40it/s, loss=0.695, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  44%|████▎     | 409/938 [00:28<00:36, 14.40it/s, loss=0.691, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  44%|████▎     | 410/938 [00:28<00:36, 14.41it/s, loss=0.697, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  44%|████▍     | 411/938 [00:28<00:36, 14.41it/s, loss=0.696, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  44%|████▍     | 412/938 [00:28<00:36, 14.42it/s, loss=0.696, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  44%|████▍     | 412/938 [00:28<00:36, 14.42it/s, loss=0.696, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  44%|████▍     | 413/938 [00:28<00:36, 14.41it/s, loss=0.701, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  44%|████▍     | 414/938 [00:28<00:36, 14.40it/s, loss=0.701, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  44%|████▍     | 415/938 [00:28<00:36, 14.41it/s, loss=0.703, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  44%|████▍     | 416/938 [00:28<00:36, 14.41it/s, loss=0.703, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  44%|████▍     | 416/938 [00:28<00:36, 14.41it/s, loss=0.713, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  44%|████▍     | 417/938 [00:28<00:36, 14.41it/s, loss=0.714, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  45%|████▍     | 418/938 [00:29<00:36, 14.41it/s, loss=0.719, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  45%|████▍     | 419/938 [00:29<00:36, 14.42it/s, loss=0.72, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  45%|████▍     | 420/938 [00:29<00:35, 14.42it/s, loss=0.72, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  45%|████▍     | 420/938 [00:29<00:35, 14.42it/s, loss=0.716, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  45%|████▍     | 421/938 [00:29<00:35, 14.42it/s, loss=0.711, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  45%|████▍     | 422/938 [00:29<00:35, 14.42it/s, loss=0.708, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  45%|████▌     | 423/938 [00:29<00:35, 14.42it/s, loss=0.706, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  45%|████▌     | 424/938 [00:29<00:35, 14.43it/s, loss=0.706, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  45%|████▌     | 424/938 [00:29<00:35, 14.43it/s, loss=0.708, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  45%|████▌     | 425/938 [00:29<00:35, 14.43it/s, loss=0.722, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  45%|████▌     | 426/938 [00:29<00:35, 14.43it/s, loss=0.726, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  46%|████▌     | 427/938 [00:29<00:35, 14.43it/s, loss=0.732, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  46%|████▌     | 428/938 [00:29<00:35, 14.43it/s, loss=0.732, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  46%|████▌     | 428/938 [00:29<00:35, 14.43it/s, loss=0.735, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  46%|████▌     | 429/938 [00:29<00:35, 14.43it/s, loss=0.735, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  46%|████▌     | 430/938 [00:29<00:35, 14.42it/s, loss=0.732, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  46%|████▌     | 431/938 [00:29<00:35, 14.43it/s, loss=0.737, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  46%|████▌     | 432/938 [00:29<00:35, 14.43it/s, loss=0.737, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  46%|████▌     | 432/938 [00:29<00:35, 14.43it/s, loss=0.736, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  46%|████▌     | 433/938 [00:30<00:34, 14.43it/s, loss=0.723, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  46%|████▋     | 434/938 [00:30<00:34, 14.44it/s, loss=0.715, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  46%|████▋     | 435/938 [00:30<00:34, 14.43it/s, loss=0.722, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  46%|████▋     | 436/938 [00:30<00:34, 14.44it/s, loss=0.722, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  46%|████▋     | 436/938 [00:30<00:34, 14.43it/s, loss=0.719, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  47%|████▋     | 437/938 [00:30<00:34, 14.44it/s, loss=0.717, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  47%|████▋     | 438/938 [00:30<00:34, 14.44it/s, loss=0.709, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  47%|████▋     | 439/938 [00:30<00:34, 14.44it/s, loss=0.698, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  47%|████▋     | 440/938 [00:30<00:34, 14.44it/s, loss=0.698, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  47%|████▋     | 440/938 [00:30<00:34, 14.44it/s, loss=0.704, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  47%|████▋     | 441/938 [00:30<00:34, 14.45it/s, loss=0.708, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  47%|████▋     | 442/938 [00:30<00:34, 14.45it/s, loss=0.71, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  47%|████▋     | 443/938 [00:30<00:34, 14.45it/s, loss=0.709, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  47%|████▋     | 444/938 [00:30<00:34, 14.45it/s, loss=0.709, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  47%|████▋     | 444/938 [00:30<00:34, 14.45it/s, loss=0.701, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  47%|████▋     | 445/938 [00:30<00:34, 14.45it/s, loss=0.689, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  48%|████▊     | 446/938 [00:30<00:34, 14.44it/s, loss=0.691, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  48%|████▊     | 447/938 [00:30<00:34, 14.42it/s, loss=0.696, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  48%|████▊     | 448/938 [00:31<00:33, 14.42it/s, loss=0.696, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  48%|████▊     | 448/938 [00:31<00:33, 14.42it/s, loss=0.687, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  48%|████▊     | 449/938 [00:31<00:33, 14.42it/s, loss=0.687, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  48%|████▊     | 450/938 [00:31<00:33, 14.42it/s, loss=0.696, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  48%|████▊     | 451/938 [00:31<00:33, 14.42it/s, loss=0.701, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  48%|████▊     | 452/938 [00:31<00:33, 14.43it/s, loss=0.701, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  48%|████▊     | 452/938 [00:31<00:33, 14.43it/s, loss=0.706, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  48%|████▊     | 453/938 [00:31<00:33, 14.43it/s, loss=0.713, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  48%|████▊     | 454/938 [00:31<00:33, 14.44it/s, loss=0.715, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  49%|████▊     | 455/938 [00:31<00:33, 14.43it/s, loss=0.71, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  49%|████▊     | 456/938 [00:31<00:33, 14.41it/s, loss=0.71, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  49%|████▊     | 456/938 [00:31<00:33, 14.41it/s, loss=0.705, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  49%|████▊     | 457/938 [00:31<00:33, 14.41it/s, loss=0.705, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  49%|████▉     | 458/938 [00:31<00:33, 14.41it/s, loss=0.704, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  49%|████▉     | 459/938 [00:31<00:33, 14.41it/s, loss=0.711, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  49%|████▉     | 460/938 [00:31<00:33, 14.41it/s, loss=0.711, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  49%|████▉     | 460/938 [00:31<00:33, 14.41it/s, loss=0.702, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  49%|████▉     | 461/938 [00:31<00:33, 14.42it/s, loss=0.702, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  49%|████▉     | 462/938 [00:32<00:33, 14.42it/s, loss=0.701, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  49%|████▉     | 463/938 [00:32<00:32, 14.41it/s, loss=0.705, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  49%|████▉     | 464/938 [00:32<00:32, 14.41it/s, loss=0.705, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  49%|████▉     | 464/938 [00:32<00:32, 14.41it/s, loss=0.713, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  50%|████▉     | 465/938 [00:32<00:32, 14.42it/s, loss=0.72, v_num=15, val_rmse=0.674, train_rmse=1.150] 
Epoch 1:  50%|████▉     | 466/938 [00:32<00:32, 14.42it/s, loss=0.72, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  50%|████▉     | 467/938 [00:32<00:32, 14.43it/s, loss=0.721, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  50%|████▉     | 468/938 [00:32<00:32, 14.43it/s, loss=0.721, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  50%|████▉     | 468/938 [00:32<00:32, 14.43it/s, loss=0.718, v_num=15, val_rmse=0.674, train_rmse=1.150]
Epoch 1:  50%|█████     | 469/938 [00:32<00:32, 14.44it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]

Validating:   0%|          | 2/469 [00:00<00:24, 19.17it/s]
Epoch 1:  50%|█████     | 472/938 [00:32<00:32, 14.49it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:   1%|          | 5/469 [00:00<00:19, 24.29it/s]
Epoch 1:  51%|█████     | 476/938 [00:32<00:31, 14.54it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:   2%|▏         | 8/469 [00:00<00:18, 24.37it/s]
Epoch 1:  51%|█████     | 480/938 [00:32<00:31, 14.59it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:   2%|▏         | 11/469 [00:00<00:18, 24.85it/s]

Validating:   3%|▎         | 14/469 [00:00<00:17, 25.49it/s]
Epoch 1:  52%|█████▏    | 484/938 [00:33<00:30, 14.65it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:   4%|▎         | 17/469 [00:00<00:18, 25.02it/s]
Epoch 1:  52%|█████▏    | 488/938 [00:33<00:30, 14.70it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:   4%|▍         | 20/469 [00:00<00:17, 25.59it/s]
Epoch 1:  52%|█████▏    | 492/938 [00:33<00:30, 14.75it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:   5%|▍         | 23/469 [00:00<00:17, 25.04it/s]

Validating:   6%|▌         | 26/469 [00:01<00:18, 24.13it/s]
Epoch 1:  53%|█████▎    | 496/938 [00:33<00:29, 14.79it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:   6%|▌         | 29/469 [00:01<00:17, 24.92it/s]
Epoch 1:  53%|█████▎    | 500/938 [00:33<00:29, 14.84it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:   7%|▋         | 32/469 [00:01<00:17, 25.21it/s]
Epoch 1:  54%|█████▎    | 504/938 [00:33<00:29, 14.89it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:   7%|▋         | 35/469 [00:01<00:16, 25.57it/s]

Validating:   8%|▊         | 38/469 [00:01<00:17, 24.92it/s]
Epoch 1:  54%|█████▍    | 508/938 [00:34<00:28, 14.94it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:   9%|▊         | 41/469 [00:01<00:16, 25.50it/s]
Epoch 1:  55%|█████▍    | 512/938 [00:34<00:28, 14.99it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:   9%|▉         | 44/469 [00:01<00:16, 25.16it/s]
Epoch 1:  55%|█████▌    | 516/938 [00:34<00:28, 15.04it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  10%|█         | 47/469 [00:01<00:16, 25.71it/s]

Validating:  11%|█         | 50/469 [00:01<00:16, 25.25it/s]
Epoch 1:  55%|█████▌    | 520/938 [00:34<00:27, 15.08it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  11%|█▏        | 53/469 [00:02<00:16, 25.30it/s]
Epoch 1:  56%|█████▌    | 524/938 [00:34<00:27, 15.13it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  12%|█▏        | 56/469 [00:02<00:15, 25.93it/s]
Epoch 1:  56%|█████▋    | 528/938 [00:34<00:27, 15.18it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  13%|█▎        | 59/469 [00:02<00:15, 26.52it/s]

Validating:  13%|█▎        | 62/469 [00:02<00:15, 26.45it/s]
Epoch 1:  57%|█████▋    | 532/938 [00:34<00:26, 15.23it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  14%|█▍        | 65/469 [00:02<00:15, 25.84it/s]
Epoch 1:  57%|█████▋    | 536/938 [00:35<00:26, 15.28it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  14%|█▍        | 68/469 [00:02<00:15, 25.58it/s]
Epoch 1:  58%|█████▊    | 540/938 [00:35<00:25, 15.32it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  15%|█▌        | 71/469 [00:02<00:15, 25.13it/s]

Validating:  16%|█▌        | 74/469 [00:02<00:18, 21.81it/s]
Epoch 1:  58%|█████▊    | 544/938 [00:35<00:25, 15.34it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  16%|█▋        | 77/469 [00:03<00:17, 23.04it/s]
Epoch 1:  58%|█████▊    | 548/938 [00:35<00:25, 15.39it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  17%|█▋        | 80/469 [00:03<00:15, 24.53it/s]
Epoch 1:  59%|█████▉    | 552/938 [00:35<00:25, 15.44it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  18%|█▊        | 83/469 [00:03<00:15, 25.18it/s]

Validating:  18%|█▊        | 86/469 [00:03<00:15, 24.93it/s]
Epoch 1:  59%|█████▉    | 556/938 [00:35<00:24, 15.48it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  19%|█▉        | 89/469 [00:03<00:15, 25.10it/s]
Epoch 1:  60%|█████▉    | 560/938 [00:36<00:24, 15.52it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  20%|█▉        | 92/469 [00:03<00:14, 25.50it/s]
Epoch 1:  60%|██████    | 564/938 [00:36<00:24, 15.57it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  20%|██        | 95/469 [00:03<00:14, 25.27it/s]

Validating:  21%|██        | 98/469 [00:03<00:15, 24.66it/s]
Epoch 1:  61%|██████    | 568/938 [00:36<00:23, 15.60it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  22%|██▏       | 101/469 [00:04<00:14, 25.14it/s]
Epoch 1:  61%|██████    | 572/938 [00:36<00:23, 15.65it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  22%|██▏       | 104/469 [00:04<00:14, 25.21it/s]
Epoch 1:  61%|██████▏   | 576/938 [00:36<00:23, 15.69it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  23%|██▎       | 107/469 [00:04<00:14, 25.61it/s]

Validating:  23%|██▎       | 110/469 [00:04<00:13, 25.83it/s]
Epoch 1:  62%|██████▏   | 580/938 [00:36<00:22, 15.73it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  24%|██▍       | 113/469 [00:04<00:13, 25.95it/s]
Epoch 1:  62%|██████▏   | 584/938 [00:37<00:22, 15.78it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  25%|██▍       | 116/469 [00:04<00:13, 26.63it/s]
Epoch 1:  63%|██████▎   | 588/938 [00:37<00:22, 15.82it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  25%|██▌       | 119/469 [00:04<00:13, 26.12it/s]

Validating:  26%|██▌       | 122/469 [00:04<00:13, 25.61it/s]
Epoch 1:  63%|██████▎   | 592/938 [00:37<00:21, 15.86it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  27%|██▋       | 125/469 [00:04<00:13, 25.73it/s]
Epoch 1:  64%|██████▎   | 596/938 [00:37<00:21, 15.90it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  27%|██▋       | 128/469 [00:05<00:13, 26.04it/s]
Epoch 1:  64%|██████▍   | 600/938 [00:37<00:21, 15.95it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  28%|██▊       | 131/469 [00:05<00:12, 26.44it/s]

Validating:  29%|██▊       | 134/469 [00:05<00:12, 27.00it/s]
Epoch 1:  64%|██████▍   | 604/938 [00:37<00:20, 15.99it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  29%|██▉       | 137/469 [00:05<00:12, 26.60it/s]
Epoch 1:  65%|██████▍   | 608/938 [00:37<00:20, 16.03it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  30%|██▉       | 140/469 [00:05<00:12, 26.65it/s]
Epoch 1:  65%|██████▌   | 612/938 [00:38<00:20, 16.07it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  30%|███       | 143/469 [00:05<00:12, 26.38it/s]

Validating:  31%|███       | 146/469 [00:05<00:12, 25.92it/s]
Epoch 1:  66%|██████▌   | 616/938 [00:38<00:19, 16.11it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  32%|███▏      | 149/469 [00:05<00:11, 26.92it/s]
Epoch 1:  66%|██████▌   | 620/938 [00:38<00:19, 16.15it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  32%|███▏      | 152/469 [00:05<00:12, 25.68it/s]
Epoch 1:  67%|██████▋   | 624/938 [00:38<00:19, 16.19it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  33%|███▎      | 155/469 [00:06<00:12, 25.31it/s]

Validating:  34%|███▎      | 158/469 [00:06<00:11, 26.04it/s]
Epoch 1:  67%|██████▋   | 628/938 [00:38<00:19, 16.23it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  34%|███▍      | 161/469 [00:06<00:11, 26.10it/s]
Epoch 1:  67%|██████▋   | 632/938 [00:38<00:18, 16.27it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  35%|███▍      | 164/469 [00:06<00:12, 25.22it/s]
Epoch 1:  68%|██████▊   | 636/938 [00:39<00:18, 16.30it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  36%|███▌      | 167/469 [00:06<00:12, 24.09it/s]

Validating:  36%|███▌      | 170/469 [00:06<00:11, 24.92it/s]
Epoch 1:  68%|██████▊   | 640/938 [00:39<00:18, 16.33it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  37%|███▋      | 173/469 [00:06<00:11, 24.71it/s]
Epoch 1:  69%|██████▊   | 644/938 [00:39<00:17, 16.37it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  38%|███▊      | 176/469 [00:06<00:11, 25.57it/s]
Epoch 1:  69%|██████▉   | 648/938 [00:39<00:17, 16.40it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  38%|███▊      | 179/469 [00:07<00:11, 24.71it/s]

Validating:  39%|███▉      | 182/469 [00:07<00:11, 25.08it/s]
Epoch 1:  70%|██████▉   | 652/938 [00:39<00:17, 16.44it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  39%|███▉      | 185/469 [00:07<00:11, 25.78it/s]
Epoch 1:  70%|██████▉   | 656/938 [00:39<00:17, 16.48it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  40%|████      | 188/469 [00:07<00:10, 26.00it/s]
Epoch 1:  70%|███████   | 660/938 [00:39<00:16, 16.52it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  41%|████      | 191/469 [00:07<00:11, 23.95it/s]

Validating:  41%|████▏     | 194/469 [00:07<00:11, 24.05it/s]
Epoch 1:  71%|███████   | 664/938 [00:40<00:16, 16.54it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  42%|████▏     | 197/469 [00:07<00:11, 23.96it/s]
Epoch 1:  71%|███████   | 668/938 [00:40<00:16, 16.57it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  43%|████▎     | 200/469 [00:07<00:10, 24.66it/s]
Epoch 1:  72%|███████▏  | 672/938 [00:40<00:16, 16.60it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  43%|████▎     | 203/469 [00:08<00:11, 24.05it/s]

Validating:  44%|████▍     | 206/469 [00:08<00:11, 23.29it/s]
Epoch 1:  72%|███████▏  | 676/938 [00:40<00:15, 16.62it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  45%|████▍     | 209/469 [00:08<00:10, 24.11it/s]
Epoch 1:  72%|███████▏  | 680/938 [00:40<00:15, 16.66it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  45%|████▌     | 212/469 [00:08<00:10, 23.83it/s]
Epoch 1:  73%|███████▎  | 684/938 [00:40<00:15, 16.69it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  46%|████▌     | 215/469 [00:08<00:10, 24.47it/s]

Validating:  46%|████▋     | 218/469 [00:08<00:10, 24.87it/s]
Epoch 1:  73%|███████▎  | 688/938 [00:41<00:14, 16.72it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  47%|████▋     | 221/469 [00:08<00:09, 24.97it/s]
Epoch 1:  74%|███████▍  | 692/938 [00:41<00:14, 16.76it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  48%|████▊     | 224/469 [00:08<00:09, 25.38it/s]
Epoch 1:  74%|███████▍  | 696/938 [00:41<00:14, 16.78it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  48%|████▊     | 227/469 [00:09<00:10, 23.09it/s]

Validating:  49%|████▉     | 230/469 [00:09<00:10, 23.88it/s]
Epoch 1:  75%|███████▍  | 700/938 [00:41<00:14, 16.81it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  50%|████▉     | 233/469 [00:09<00:09, 24.45it/s]
Epoch 1:  75%|███████▌  | 704/938 [00:41<00:13, 16.84it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  50%|█████     | 236/469 [00:09<00:09, 24.67it/s]
Epoch 1:  75%|███████▌  | 708/938 [00:41<00:13, 16.88it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  51%|█████     | 239/469 [00:09<00:09, 25.16it/s]

Validating:  52%|█████▏    | 242/469 [00:09<00:08, 26.29it/s]
Epoch 1:  76%|███████▌  | 712/938 [00:42<00:13, 16.91it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  52%|█████▏    | 245/469 [00:09<00:08, 26.41it/s]
Epoch 1:  76%|███████▋  | 716/938 [00:42<00:13, 16.95it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  53%|█████▎    | 248/469 [00:09<00:09, 24.32it/s]
Epoch 1:  77%|███████▋  | 720/938 [00:42<00:12, 16.97it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  54%|█████▎    | 251/469 [00:09<00:08, 25.47it/s]

Validating:  54%|█████▍    | 254/469 [00:10<00:08, 25.88it/s]
Epoch 1:  77%|███████▋  | 724/938 [00:42<00:12, 17.01it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  55%|█████▍    | 257/469 [00:10<00:08, 24.72it/s]
Epoch 1:  78%|███████▊  | 728/938 [00:42<00:12, 17.03it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  55%|█████▌    | 260/469 [00:10<00:08, 23.68it/s]
Epoch 1:  78%|███████▊  | 732/938 [00:42<00:12, 17.05it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  56%|█████▌    | 263/469 [00:10<00:08, 24.40it/s]

Validating:  57%|█████▋    | 266/469 [00:10<00:08, 25.24it/s]
Epoch 1:  78%|███████▊  | 736/938 [00:43<00:11, 17.09it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  57%|█████▋    | 269/469 [00:10<00:07, 25.68it/s]
Epoch 1:  79%|███████▉  | 740/938 [00:43<00:11, 17.12it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  58%|█████▊    | 272/469 [00:10<00:07, 26.33it/s]
Epoch 1:  79%|███████▉  | 744/938 [00:43<00:11, 17.16it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  59%|█████▊    | 275/469 [00:10<00:07, 26.15it/s]

Validating:  59%|█████▉    | 278/469 [00:11<00:07, 26.46it/s]
Epoch 1:  80%|███████▉  | 748/938 [00:43<00:11, 17.19it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  60%|█████▉    | 281/469 [00:11<00:07, 26.15it/s]
Epoch 1:  80%|████████  | 752/938 [00:43<00:10, 17.22it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  61%|██████    | 284/469 [00:11<00:07, 26.22it/s]
Epoch 1:  81%|████████  | 756/938 [00:43<00:10, 17.25it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  61%|██████    | 287/469 [00:11<00:06, 26.79it/s]

Validating:  62%|██████▏   | 290/469 [00:11<00:06, 26.64it/s]
Epoch 1:  81%|████████  | 760/938 [00:43<00:10, 17.29it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  62%|██████▏   | 293/469 [00:11<00:06, 26.83it/s]
Epoch 1:  81%|████████▏ | 764/938 [00:44<00:10, 17.32it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  63%|██████▎   | 296/469 [00:11<00:06, 26.94it/s]
Epoch 1:  82%|████████▏ | 768/938 [00:44<00:09, 17.35it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  64%|██████▍   | 299/469 [00:11<00:06, 27.02it/s]

Validating:  64%|██████▍   | 302/469 [00:11<00:06, 27.01it/s]
Epoch 1:  82%|████████▏ | 772/938 [00:44<00:09, 17.38it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  65%|██████▌   | 305/469 [00:12<00:06, 26.15it/s]
Epoch 1:  83%|████████▎ | 776/938 [00:44<00:09, 17.41it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  66%|██████▌   | 308/469 [00:12<00:06, 25.61it/s]
Epoch 1:  83%|████████▎ | 780/938 [00:44<00:09, 17.44it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  66%|██████▋   | 311/469 [00:12<00:06, 25.43it/s]

Validating:  67%|██████▋   | 314/469 [00:12<00:05, 26.54it/s]
Epoch 1:  84%|████████▎ | 784/938 [00:44<00:08, 17.47it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  68%|██████▊   | 317/469 [00:12<00:05, 26.61it/s]
Epoch 1:  84%|████████▍ | 788/938 [00:45<00:08, 17.50it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  68%|██████▊   | 320/469 [00:12<00:05, 26.25it/s]
Epoch 1:  84%|████████▍ | 792/938 [00:45<00:08, 17.53it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  69%|██████▉   | 323/469 [00:12<00:05, 26.92it/s]

Validating:  70%|██████▉   | 326/469 [00:12<00:05, 26.08it/s]
Epoch 1:  85%|████████▍ | 796/938 [00:45<00:08, 17.56it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  70%|███████   | 329/469 [00:12<00:05, 25.71it/s]
Epoch 1:  85%|████████▌ | 800/938 [00:45<00:07, 17.59it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  71%|███████   | 332/469 [00:13<00:05, 26.48it/s]
Epoch 1:  86%|████████▌ | 804/938 [00:45<00:07, 17.62it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  71%|███████▏  | 335/469 [00:13<00:04, 27.07it/s]

Validating:  72%|███████▏  | 338/469 [00:13<00:04, 26.60it/s]
Epoch 1:  86%|████████▌ | 808/938 [00:45<00:07, 17.65it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  73%|███████▎  | 341/469 [00:13<00:04, 26.20it/s]
Epoch 1:  87%|████████▋ | 812/938 [00:45<00:07, 17.68it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  73%|███████▎  | 344/469 [00:13<00:05, 24.91it/s]
Epoch 1:  87%|████████▋ | 816/938 [00:46<00:06, 17.69it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  74%|███████▍  | 347/469 [00:13<00:04, 24.93it/s]

Validating:  75%|███████▍  | 350/469 [00:13<00:04, 25.35it/s]
Epoch 1:  87%|████████▋ | 820/938 [00:46<00:06, 17.72it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  75%|███████▌  | 353/469 [00:13<00:04, 24.56it/s]
Epoch 1:  88%|████████▊ | 824/938 [00:46<00:06, 17.74it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  76%|███████▌  | 356/469 [00:14<00:04, 23.76it/s]
Epoch 1:  88%|████████▊ | 828/938 [00:46<00:06, 17.77it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  77%|███████▋  | 359/469 [00:14<00:04, 24.52it/s]

Validating:  77%|███████▋  | 362/469 [00:14<00:04, 24.24it/s]
Epoch 1:  89%|████████▊ | 832/938 [00:46<00:05, 17.79it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  78%|███████▊  | 365/469 [00:14<00:04, 24.78it/s]
Epoch 1:  89%|████████▉ | 836/938 [00:46<00:05, 17.81it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  78%|███████▊  | 368/469 [00:14<00:03, 25.75it/s]
Epoch 1:  90%|████████▉ | 840/938 [00:47<00:05, 17.85it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  79%|███████▉  | 371/469 [00:14<00:03, 25.07it/s]

Validating:  80%|███████▉  | 374/469 [00:14<00:03, 25.64it/s]
Epoch 1:  90%|████████▉ | 844/938 [00:47<00:05, 17.87it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  80%|████████  | 377/469 [00:14<00:03, 25.99it/s]
Epoch 1:  90%|█████████ | 848/938 [00:47<00:05, 17.89it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  81%|████████  | 380/469 [00:14<00:03, 26.02it/s]
Epoch 1:  91%|█████████ | 852/938 [00:47<00:04, 17.92it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  82%|████████▏ | 383/469 [00:15<00:03, 26.30it/s]

Validating:  82%|████████▏ | 386/469 [00:15<00:03, 25.71it/s]
Epoch 1:  91%|█████████▏| 856/938 [00:47<00:04, 17.95it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  83%|████████▎ | 389/469 [00:15<00:03, 26.46it/s]
Epoch 1:  92%|█████████▏| 860/938 [00:47<00:04, 17.98it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  84%|████████▎ | 392/469 [00:15<00:02, 26.37it/s]
Epoch 1:  92%|█████████▏| 864/938 [00:47<00:04, 18.00it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  84%|████████▍ | 395/469 [00:15<00:02, 25.83it/s]

Validating:  85%|████████▍ | 398/469 [00:15<00:02, 26.42it/s]
Epoch 1:  93%|█████████▎| 868/938 [00:48<00:03, 18.03it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  86%|████████▌ | 401/469 [00:15<00:02, 26.75it/s]
Epoch 1:  93%|█████████▎| 872/938 [00:48<00:03, 18.06it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  86%|████████▌ | 404/469 [00:15<00:02, 26.95it/s]
Epoch 1:  93%|█████████▎| 876/938 [00:48<00:03, 18.09it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  87%|████████▋ | 407/469 [00:15<00:02, 27.53it/s]

Validating:  87%|████████▋ | 410/469 [00:16<00:02, 26.56it/s]
Epoch 1:  94%|█████████▍| 880/938 [00:48<00:03, 18.11it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  88%|████████▊ | 413/469 [00:16<00:02, 26.14it/s]
Epoch 1:  94%|█████████▍| 884/938 [00:48<00:02, 18.14it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  89%|████████▊ | 416/469 [00:16<00:01, 27.04it/s]
Epoch 1:  95%|█████████▍| 888/938 [00:48<00:02, 18.16it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  89%|████████▉ | 419/469 [00:16<00:01, 26.86it/s]

Validating:  90%|████████▉ | 422/469 [00:16<00:01, 27.13it/s]
Epoch 1:  95%|█████████▌| 892/938 [00:49<00:02, 18.19it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  91%|█████████ | 425/469 [00:16<00:01, 26.76it/s]
Epoch 1:  96%|█████████▌| 896/938 [00:49<00:02, 18.22it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  91%|█████████▏| 429/469 [00:16<00:01, 27.70it/s]
Epoch 1:  96%|█████████▌| 900/938 [00:49<00:02, 18.25it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  92%|█████████▏| 432/469 [00:16<00:01, 27.63it/s]
Epoch 1:  96%|█████████▋| 904/938 [00:49<00:01, 18.28it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  93%|█████████▎| 435/469 [00:17<00:01, 27.58it/s]

Validating:  93%|█████████▎| 438/469 [00:17<00:01, 26.60it/s]
Epoch 1:  97%|█████████▋| 908/938 [00:49<00:01, 18.30it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  94%|█████████▍| 441/469 [00:17<00:01, 26.24it/s]
Epoch 1:  97%|█████████▋| 912/938 [00:49<00:01, 18.32it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  95%|█████████▍| 444/469 [00:17<00:00, 25.95it/s]
Epoch 1:  98%|█████████▊| 916/938 [00:49<00:01, 18.35it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  95%|█████████▌| 447/469 [00:17<00:00, 26.72it/s]

Validating:  96%|█████████▌| 450/469 [00:17<00:00, 25.31it/s]
Epoch 1:  98%|█████████▊| 920/938 [00:50<00:00, 18.36it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  97%|█████████▋| 453/469 [00:17<00:00, 25.30it/s]
Epoch 1:  99%|█████████▊| 924/938 [00:50<00:00, 18.39it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  97%|█████████▋| 456/469 [00:17<00:00, 23.81it/s]
Epoch 1:  99%|█████████▉| 928/938 [00:50<00:00, 18.40it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  98%|█████████▊| 459/469 [00:17<00:00, 24.65it/s]

Validating:  99%|█████████▊| 462/469 [00:18<00:00, 24.39it/s]
Epoch 1:  99%|█████████▉| 932/938 [00:50<00:00, 18.42it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating:  99%|█████████▉| 465/469 [00:18<00:00, 24.59it/s]
Epoch 1: 100%|█████████▉| 936/938 [00:50<00:00, 18.44it/s, loss=0.725, v_num=15, val_rmse=0.674, train_rmse=1.150]

Validating: 100%|█████████▉| 468/469 [00:18<00:00, 24.85it/s]
Epoch 1: 100%|██████████| 938/938 [00:50<00:00, 18.44it/s, loss=0.725, v_num=15, val_rmse=0.553, train_rmse=1.150]

                                                             
Epoch 1: 100%|██████████| 938/938 [00:50<00:00, 18.44it/s, loss=0.725, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 1:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.725, v_num=15, val_rmse=0.553, train_rmse=0.732]          
Epoch 2:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.725, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   0%|          | 1/938 [00:00<01:19, 11.79it/s, loss=0.721, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   0%|          | 2/938 [00:00<01:15, 12.42it/s, loss=0.712, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   0%|          | 3/938 [00:00<01:04, 14.41it/s, loss=0.71, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:   0%|          | 4/938 [00:00<01:04, 14.55it/s, loss=0.71, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   0%|          | 4/938 [00:00<01:04, 14.52it/s, loss=0.71, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   1%|          | 5/938 [00:00<01:03, 14.59it/s, loss=0.713, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   1%|          | 6/938 [00:00<01:03, 14.75it/s, loss=0.711, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   1%|          | 7/938 [00:00<01:01, 15.14it/s, loss=0.711, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   1%|          | 8/938 [00:00<01:01, 15.24it/s, loss=0.711, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   1%|          | 8/938 [00:00<01:01, 15.23it/s, loss=0.713, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   1%|          | 9/938 [00:00<01:00, 15.23it/s, loss=0.709, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   1%|          | 10/938 [00:00<01:01, 15.04it/s, loss=0.702, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   1%|          | 11/938 [00:00<01:01, 15.05it/s, loss=0.697, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   1%|▏         | 12/938 [00:00<01:01, 15.09it/s, loss=0.697, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   1%|▏         | 12/938 [00:00<01:01, 15.08it/s, loss=0.691, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   1%|▏         | 13/938 [00:00<01:00, 15.21it/s, loss=0.704, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   1%|▏         | 14/938 [00:00<01:00, 15.19it/s, loss=0.703, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   2%|▏         | 15/938 [00:00<01:01, 15.05it/s, loss=0.707, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   2%|▏         | 16/938 [00:01<01:00, 15.18it/s, loss=0.707, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   2%|▏         | 16/938 [00:01<01:00, 15.17it/s, loss=0.703, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   2%|▏         | 17/938 [00:01<01:00, 15.23it/s, loss=0.697, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   2%|▏         | 18/938 [00:01<01:00, 15.32it/s, loss=0.694, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   2%|▏         | 19/938 [00:01<01:00, 15.11it/s, loss=0.696, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   2%|▏         | 20/938 [00:01<01:00, 15.09it/s, loss=0.696, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   2%|▏         | 20/938 [00:01<01:00, 15.09it/s, loss=0.682, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   2%|▏         | 21/938 [00:01<01:00, 15.19it/s, loss=0.679, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   2%|▏         | 22/938 [00:01<01:00, 15.03it/s, loss=0.686, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   2%|▏         | 23/938 [00:01<01:01, 14.93it/s, loss=0.681, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   3%|▎         | 24/938 [00:01<01:01, 14.88it/s, loss=0.681, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   3%|▎         | 24/938 [00:01<01:01, 14.87it/s, loss=0.679, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   3%|▎         | 25/938 [00:01<01:01, 14.92it/s, loss=0.675, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   3%|▎         | 26/938 [00:01<01:01, 14.92it/s, loss=0.682, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   3%|▎         | 27/938 [00:01<01:01, 14.91it/s, loss=0.686, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   3%|▎         | 28/938 [00:01<01:01, 14.85it/s, loss=0.686, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   3%|▎         | 28/938 [00:01<01:01, 14.84it/s, loss=0.686, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   3%|▎         | 29/938 [00:01<01:01, 14.72it/s, loss=0.691, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   3%|▎         | 30/938 [00:02<01:01, 14.80it/s, loss=0.693, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   3%|▎         | 31/938 [00:02<01:01, 14.74it/s, loss=0.703, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   3%|▎         | 32/938 [00:02<01:01, 14.70it/s, loss=0.703, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   3%|▎         | 32/938 [00:02<01:01, 14.69it/s, loss=0.703, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   4%|▎         | 33/938 [00:02<01:01, 14.62it/s, loss=0.694, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   4%|▎         | 34/938 [00:02<01:01, 14.64it/s, loss=0.69, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:   4%|▎         | 35/938 [00:02<01:02, 14.56it/s, loss=0.679, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   4%|▍         | 36/938 [00:02<01:01, 14.58it/s, loss=0.679, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   4%|▍         | 36/938 [00:02<01:01, 14.58it/s, loss=0.684, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   4%|▍         | 37/938 [00:02<01:01, 14.54it/s, loss=0.688, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   4%|▍         | 38/938 [00:02<01:01, 14.60it/s, loss=0.687, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   4%|▍         | 39/938 [00:02<01:01, 14.55it/s, loss=0.689, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   4%|▍         | 40/938 [00:02<01:01, 14.53it/s, loss=0.689, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   4%|▍         | 40/938 [00:02<01:01, 14.53it/s, loss=0.691, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   4%|▍         | 41/938 [00:02<01:01, 14.53it/s, loss=0.694, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   4%|▍         | 42/938 [00:02<01:01, 14.57it/s, loss=0.685, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   5%|▍         | 43/938 [00:02<01:01, 14.61it/s, loss=0.686, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   5%|▍         | 44/938 [00:03<01:01, 14.51it/s, loss=0.686, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   5%|▍         | 44/938 [00:03<01:01, 14.51it/s, loss=0.685, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   5%|▍         | 45/938 [00:03<01:01, 14.55it/s, loss=0.69, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:   5%|▍         | 46/938 [00:03<01:01, 14.52it/s, loss=0.684, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   5%|▌         | 47/938 [00:03<01:01, 14.48it/s, loss=0.684, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   5%|▌         | 48/938 [00:03<01:01, 14.50it/s, loss=0.684, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   5%|▌         | 48/938 [00:03<01:01, 14.50it/s, loss=0.687, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   5%|▌         | 49/938 [00:03<01:01, 14.50it/s, loss=0.682, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   5%|▌         | 50/938 [00:03<01:01, 14.51it/s, loss=0.686, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   5%|▌         | 51/938 [00:03<01:00, 14.55it/s, loss=0.679, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   6%|▌         | 52/938 [00:03<01:01, 14.52it/s, loss=0.679, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   6%|▌         | 52/938 [00:03<01:01, 14.51it/s, loss=0.681, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   6%|▌         | 53/938 [00:03<01:00, 14.56it/s, loss=0.683, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   6%|▌         | 54/938 [00:03<01:01, 14.42it/s, loss=0.687, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   6%|▌         | 55/938 [00:03<01:01, 14.38it/s, loss=0.697, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   6%|▌         | 56/938 [00:03<01:01, 14.41it/s, loss=0.697, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   6%|▌         | 56/938 [00:03<01:01, 14.41it/s, loss=0.695, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   6%|▌         | 57/938 [00:03<01:01, 14.43it/s, loss=0.696, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   6%|▌         | 58/938 [00:04<01:01, 14.42it/s, loss=0.691, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   6%|▋         | 59/938 [00:04<01:00, 14.46it/s, loss=0.695, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   6%|▋         | 60/938 [00:04<01:00, 14.47it/s, loss=0.695, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   6%|▋         | 60/938 [00:04<01:00, 14.46it/s, loss=0.701, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   7%|▋         | 61/938 [00:04<01:00, 14.47it/s, loss=0.699, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   7%|▋         | 62/938 [00:04<01:00, 14.46it/s, loss=0.714, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   7%|▋         | 63/938 [00:04<01:00, 14.45it/s, loss=0.719, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   7%|▋         | 64/938 [00:04<01:00, 14.41it/s, loss=0.719, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   7%|▋         | 64/938 [00:04<01:00, 14.40it/s, loss=0.727, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   7%|▋         | 65/938 [00:04<01:00, 14.37it/s, loss=0.727, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   7%|▋         | 66/938 [00:04<01:00, 14.40it/s, loss=0.725, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   7%|▋         | 67/938 [00:04<01:00, 14.39it/s, loss=0.718, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   7%|▋         | 68/938 [00:04<01:00, 14.41it/s, loss=0.718, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   7%|▋         | 68/938 [00:04<01:00, 14.41it/s, loss=0.714, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   7%|▋         | 69/938 [00:04<01:00, 14.36it/s, loss=0.714, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   7%|▋         | 70/938 [00:04<01:00, 14.33it/s, loss=0.71, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:   8%|▊         | 71/938 [00:04<01:00, 14.31it/s, loss=0.713, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   8%|▊         | 72/938 [00:05<01:00, 14.29it/s, loss=0.713, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   8%|▊         | 72/938 [00:05<01:00, 14.29it/s, loss=0.721, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   8%|▊         | 73/938 [00:05<01:00, 14.29it/s, loss=0.725, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   8%|▊         | 74/938 [00:05<01:00, 14.30it/s, loss=0.721, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   8%|▊         | 75/938 [00:05<01:00, 14.28it/s, loss=0.716, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   8%|▊         | 76/938 [00:05<01:00, 14.18it/s, loss=0.716, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   8%|▊         | 76/938 [00:05<01:00, 14.18it/s, loss=0.706, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   8%|▊         | 77/938 [00:05<01:00, 14.21it/s, loss=0.705, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   8%|▊         | 78/938 [00:05<01:00, 14.19it/s, loss=0.705, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   8%|▊         | 79/938 [00:05<01:00, 14.21it/s, loss=0.699, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   9%|▊         | 80/938 [00:05<01:00, 14.20it/s, loss=0.699, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   9%|▊         | 80/938 [00:05<01:00, 14.20it/s, loss=0.697, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   9%|▊         | 81/938 [00:05<01:00, 14.16it/s, loss=0.699, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   9%|▊         | 82/938 [00:05<01:00, 14.17it/s, loss=0.683, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   9%|▉         | 83/938 [00:05<01:00, 14.21it/s, loss=0.675, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   9%|▉         | 84/938 [00:05<01:00, 14.23it/s, loss=0.675, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   9%|▉         | 84/938 [00:05<01:00, 14.22it/s, loss=0.663, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   9%|▉         | 85/938 [00:05<00:59, 14.24it/s, loss=0.663, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   9%|▉         | 86/938 [00:06<00:59, 14.22it/s, loss=0.668, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   9%|▉         | 87/938 [00:06<00:59, 14.22it/s, loss=0.67, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:   9%|▉         | 88/938 [00:06<00:59, 14.22it/s, loss=0.67, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   9%|▉         | 88/938 [00:06<00:59, 14.22it/s, loss=0.673, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:   9%|▉         | 89/938 [00:06<00:59, 14.21it/s, loss=0.675, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  10%|▉         | 90/938 [00:06<00:59, 14.18it/s, loss=0.676, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  10%|▉         | 91/938 [00:06<00:59, 14.17it/s, loss=0.677, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  10%|▉         | 92/938 [00:06<00:59, 14.18it/s, loss=0.677, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  10%|▉         | 92/938 [00:06<00:59, 14.18it/s, loss=0.675, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  10%|▉         | 93/938 [00:06<00:59, 14.17it/s, loss=0.667, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  10%|█         | 94/938 [00:06<00:59, 14.18it/s, loss=0.678, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  10%|█         | 95/938 [00:06<00:59, 14.19it/s, loss=0.682, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  10%|█         | 96/938 [00:06<00:59, 14.22it/s, loss=0.682, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  10%|█         | 96/938 [00:06<00:59, 14.22it/s, loss=0.693, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  10%|█         | 97/938 [00:06<00:59, 14.18it/s, loss=0.694, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  10%|█         | 98/938 [00:06<00:59, 14.18it/s, loss=0.691, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  11%|█         | 99/938 [00:06<00:59, 14.17it/s, loss=0.7, v_num=15, val_rmse=0.553, train_rmse=0.732]  
Epoch 2:  11%|█         | 100/938 [00:07<00:59, 14.16it/s, loss=0.7, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  11%|█         | 100/938 [00:07<00:59, 14.16it/s, loss=0.7, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  11%|█         | 101/938 [00:07<00:59, 14.15it/s, loss=0.703, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  11%|█         | 102/938 [00:07<00:59, 14.16it/s, loss=0.712, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  11%|█         | 103/938 [00:07<00:58, 14.16it/s, loss=0.725, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  11%|█         | 104/938 [00:07<00:59, 14.12it/s, loss=0.725, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  11%|█         | 104/938 [00:07<00:59, 14.11it/s, loss=0.728, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  11%|█         | 105/938 [00:07<00:58, 14.12it/s, loss=0.729, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  11%|█▏        | 106/938 [00:07<00:58, 14.12it/s, loss=0.729, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  11%|█▏        | 107/938 [00:07<00:58, 14.11it/s, loss=0.722, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  12%|█▏        | 108/938 [00:07<00:58, 14.12it/s, loss=0.722, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  12%|█▏        | 108/938 [00:07<00:58, 14.12it/s, loss=0.72, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  12%|█▏        | 109/938 [00:07<00:58, 14.09it/s, loss=0.721, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  12%|█▏        | 110/938 [00:07<00:58, 14.11it/s, loss=0.727, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  12%|█▏        | 111/938 [00:07<00:58, 14.08it/s, loss=0.724, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  12%|█▏        | 112/938 [00:07<00:58, 14.09it/s, loss=0.724, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  12%|█▏        | 112/938 [00:07<00:58, 14.09it/s, loss=0.719, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  12%|█▏        | 113/938 [00:08<00:58, 14.10it/s, loss=0.728, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  12%|█▏        | 114/938 [00:08<00:58, 14.10it/s, loss=0.716, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  12%|█▏        | 115/938 [00:08<00:58, 14.09it/s, loss=0.706, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  12%|█▏        | 116/938 [00:08<00:58, 14.07it/s, loss=0.706, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  12%|█▏        | 116/938 [00:08<00:58, 14.07it/s, loss=0.696, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  12%|█▏        | 117/938 [00:08<00:58, 14.07it/s, loss=0.69, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  13%|█▎        | 118/938 [00:08<00:58, 14.08it/s, loss=0.695, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  13%|█▎        | 119/938 [00:08<00:58, 14.08it/s, loss=0.696, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  13%|█▎        | 120/938 [00:08<00:58, 14.05it/s, loss=0.696, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  13%|█▎        | 120/938 [00:08<00:58, 14.05it/s, loss=0.697, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  13%|█▎        | 121/938 [00:08<00:58, 14.03it/s, loss=0.688, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  13%|█▎        | 122/938 [00:08<00:58, 14.05it/s, loss=0.684, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  13%|█▎        | 123/938 [00:08<00:58, 14.05it/s, loss=0.665, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  13%|█▎        | 124/938 [00:08<00:58, 14.01it/s, loss=0.665, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  13%|█▎        | 124/938 [00:08<00:58, 14.01it/s, loss=0.661, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  13%|█▎        | 125/938 [00:08<00:58, 13.98it/s, loss=0.658, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  13%|█▎        | 126/938 [00:09<00:58, 13.96it/s, loss=0.655, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  14%|█▎        | 127/938 [00:09<00:58, 13.97it/s, loss=0.659, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  14%|█▎        | 128/938 [00:09<00:57, 13.97it/s, loss=0.659, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  14%|█▎        | 128/938 [00:09<00:57, 13.97it/s, loss=0.655, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  14%|█▍        | 129/938 [00:09<00:57, 13.96it/s, loss=0.652, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  14%|█▍        | 130/938 [00:09<00:57, 13.96it/s, loss=0.653, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  14%|█▍        | 131/938 [00:09<00:57, 13.96it/s, loss=0.655, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  14%|█▍        | 132/938 [00:09<00:57, 13.96it/s, loss=0.655, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  14%|█▍        | 132/938 [00:09<00:57, 13.96it/s, loss=0.652, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  14%|█▍        | 133/938 [00:09<00:57, 13.95it/s, loss=0.641, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  14%|█▍        | 134/938 [00:09<00:57, 13.94it/s, loss=0.646, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  14%|█▍        | 135/938 [00:09<00:57, 13.91it/s, loss=0.648, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  14%|█▍        | 136/938 [00:09<00:57, 13.92it/s, loss=0.648, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  14%|█▍        | 136/938 [00:09<00:57, 13.92it/s, loss=0.653, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  15%|█▍        | 137/938 [00:09<00:57, 13.93it/s, loss=0.657, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  15%|█▍        | 138/938 [00:09<00:57, 13.93it/s, loss=0.652, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  15%|█▍        | 139/938 [00:09<00:57, 13.96it/s, loss=0.652, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  15%|█▍        | 140/938 [00:10<00:57, 13.96it/s, loss=0.652, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  15%|█▍        | 140/938 [00:10<00:57, 13.96it/s, loss=0.65, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  15%|█▌        | 141/938 [00:10<00:57, 13.97it/s, loss=0.654, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  15%|█▌        | 142/938 [00:10<00:56, 13.97it/s, loss=0.655, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  15%|█▌        | 143/938 [00:10<00:56, 13.95it/s, loss=0.664, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  15%|█▌        | 144/938 [00:10<00:56, 13.95it/s, loss=0.664, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  15%|█▌        | 144/938 [00:10<00:56, 13.95it/s, loss=0.674, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  15%|█▌        | 145/938 [00:10<00:56, 13.96it/s, loss=0.674, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  16%|█▌        | 146/938 [00:10<00:56, 13.97it/s, loss=0.674, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  16%|█▌        | 147/938 [00:10<00:56, 13.97it/s, loss=0.678, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  16%|█▌        | 148/938 [00:10<00:56, 13.98it/s, loss=0.678, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  16%|█▌        | 148/938 [00:10<00:56, 13.98it/s, loss=0.679, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  16%|█▌        | 149/938 [00:10<00:56, 14.00it/s, loss=0.689, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  16%|█▌        | 150/938 [00:10<00:56, 13.99it/s, loss=0.688, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  16%|█▌        | 151/938 [00:10<00:56, 13.96it/s, loss=0.687, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  16%|█▌        | 152/938 [00:10<00:56, 13.95it/s, loss=0.687, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  16%|█▌        | 152/938 [00:10<00:56, 13.95it/s, loss=0.69, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  16%|█▋        | 153/938 [00:10<00:56, 13.97it/s, loss=0.69, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  16%|█▋        | 154/938 [00:11<00:56, 13.96it/s, loss=0.686, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  17%|█▋        | 155/938 [00:11<00:56, 13.95it/s, loss=0.692, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  17%|█▋        | 156/938 [00:11<00:56, 13.95it/s, loss=0.692, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  17%|█▋        | 156/938 [00:11<00:56, 13.95it/s, loss=0.692, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  17%|█▋        | 157/938 [00:11<00:55, 13.95it/s, loss=0.689, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  17%|█▋        | 158/938 [00:11<00:55, 13.97it/s, loss=0.695, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  17%|█▋        | 159/938 [00:11<00:55, 13.97it/s, loss=0.683, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  17%|█▋        | 160/938 [00:11<00:55, 13.97it/s, loss=0.683, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  17%|█▋        | 160/938 [00:11<00:55, 13.97it/s, loss=0.69, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  17%|█▋        | 161/938 [00:11<00:55, 13.96it/s, loss=0.691, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  17%|█▋        | 162/938 [00:11<00:55, 13.98it/s, loss=0.687, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  17%|█▋        | 163/938 [00:11<00:55, 13.97it/s, loss=0.687, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  17%|█▋        | 164/938 [00:11<00:55, 13.98it/s, loss=0.687, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  17%|█▋        | 164/938 [00:11<00:55, 13.98it/s, loss=0.678, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  18%|█▊        | 165/938 [00:11<00:55, 13.99it/s, loss=0.678, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  18%|█▊        | 166/938 [00:11<00:55, 13.97it/s, loss=0.681, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  18%|█▊        | 167/938 [00:11<00:55, 13.98it/s, loss=0.678, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  18%|█▊        | 168/938 [00:12<00:55, 13.96it/s, loss=0.678, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  18%|█▊        | 168/938 [00:12<00:55, 13.96it/s, loss=0.678, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  18%|█▊        | 169/938 [00:12<00:55, 13.96it/s, loss=0.665, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  18%|█▊        | 170/938 [00:12<00:55, 13.93it/s, loss=0.665, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  18%|█▊        | 171/938 [00:12<00:55, 13.93it/s, loss=0.664, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  18%|█▊        | 172/938 [00:12<00:54, 13.94it/s, loss=0.664, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  18%|█▊        | 172/938 [00:12<00:54, 13.94it/s, loss=0.665, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  18%|█▊        | 173/938 [00:12<00:54, 13.96it/s, loss=0.662, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  19%|█▊        | 174/938 [00:12<00:54, 13.97it/s, loss=0.664, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  19%|█▊        | 175/938 [00:12<00:54, 13.97it/s, loss=0.664, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  19%|█▉        | 176/938 [00:12<00:54, 13.98it/s, loss=0.664, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  19%|█▉        | 176/938 [00:12<00:54, 13.98it/s, loss=0.654, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  19%|█▉        | 177/938 [00:12<00:54, 13.97it/s, loss=0.659, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  19%|█▉        | 178/938 [00:12<00:54, 13.98it/s, loss=0.653, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  19%|█▉        | 179/938 [00:12<00:54, 13.97it/s, loss=0.653, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  19%|█▉        | 180/938 [00:12<00:54, 13.96it/s, loss=0.653, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  19%|█▉        | 180/938 [00:12<00:54, 13.96it/s, loss=0.648, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  19%|█▉        | 181/938 [00:12<00:54, 13.96it/s, loss=0.647, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  19%|█▉        | 182/938 [00:13<00:54, 13.95it/s, loss=0.655, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  20%|█▉        | 183/938 [00:13<00:54, 13.96it/s, loss=0.657, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  20%|█▉        | 184/938 [00:13<00:54, 13.93it/s, loss=0.657, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  20%|█▉        | 184/938 [00:13<00:54, 13.93it/s, loss=0.66, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  20%|█▉        | 185/938 [00:13<00:54, 13.94it/s, loss=0.657, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  20%|█▉        | 186/938 [00:13<00:53, 13.93it/s, loss=0.655, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  20%|█▉        | 187/938 [00:13<00:53, 13.93it/s, loss=0.655, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  20%|██        | 188/938 [00:13<00:53, 13.93it/s, loss=0.655, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  20%|██        | 188/938 [00:13<00:53, 13.93it/s, loss=0.66, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  20%|██        | 189/938 [00:13<00:53, 13.93it/s, loss=0.662, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  20%|██        | 190/938 [00:13<00:53, 13.94it/s, loss=0.655, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  20%|██        | 191/938 [00:13<00:53, 13.93it/s, loss=0.663, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  20%|██        | 192/938 [00:13<00:53, 13.87it/s, loss=0.663, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  20%|██        | 192/938 [00:13<00:53, 13.87it/s, loss=0.665, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  21%|██        | 193/938 [00:13<00:53, 13.89it/s, loss=0.675, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  21%|██        | 194/938 [00:13<00:53, 13.89it/s, loss=0.671, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  21%|██        | 195/938 [00:14<00:53, 13.90it/s, loss=0.669, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  21%|██        | 196/938 [00:14<00:53, 13.89it/s, loss=0.669, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  21%|██        | 196/938 [00:14<00:53, 13.89it/s, loss=0.685, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  21%|██        | 197/938 [00:14<00:53, 13.87it/s, loss=0.684, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  21%|██        | 198/938 [00:14<00:53, 13.87it/s, loss=0.692, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  21%|██        | 199/938 [00:14<00:53, 13.86it/s, loss=0.702, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  21%|██▏       | 200/938 [00:14<00:53, 13.87it/s, loss=0.702, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  21%|██▏       | 200/938 [00:14<00:53, 13.87it/s, loss=0.709, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  21%|██▏       | 201/938 [00:14<00:53, 13.84it/s, loss=0.703, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  22%|██▏       | 202/938 [00:14<00:53, 13.86it/s, loss=0.704, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  22%|██▏       | 203/938 [00:14<00:52, 13.87it/s, loss=0.703, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  22%|██▏       | 204/938 [00:14<00:52, 13.88it/s, loss=0.703, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  22%|██▏       | 204/938 [00:14<00:52, 13.88it/s, loss=0.702, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  22%|██▏       | 205/938 [00:14<00:52, 13.89it/s, loss=0.702, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  22%|██▏       | 206/938 [00:14<00:52, 13.88it/s, loss=0.699, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  22%|██▏       | 207/938 [00:14<00:52, 13.89it/s, loss=0.699, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  22%|██▏       | 208/938 [00:14<00:52, 13.88it/s, loss=0.699, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  22%|██▏       | 208/938 [00:14<00:52, 13.88it/s, loss=0.707, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  22%|██▏       | 209/938 [00:15<00:52, 13.89it/s, loss=0.706, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  22%|██▏       | 210/938 [00:15<00:52, 13.88it/s, loss=0.717, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  22%|██▏       | 211/938 [00:15<00:52, 13.88it/s, loss=0.711, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  23%|██▎       | 212/938 [00:15<00:52, 13.88it/s, loss=0.711, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  23%|██▎       | 212/938 [00:15<00:52, 13.88it/s, loss=0.707, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  23%|██▎       | 213/938 [00:15<00:52, 13.88it/s, loss=0.694, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  23%|██▎       | 214/938 [00:15<00:52, 13.89it/s, loss=0.7, v_num=15, val_rmse=0.553, train_rmse=0.732]  
Epoch 2:  23%|██▎       | 215/938 [00:15<00:52, 13.90it/s, loss=0.69, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  23%|██▎       | 216/938 [00:15<00:51, 13.91it/s, loss=0.69, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  23%|██▎       | 216/938 [00:15<00:51, 13.91it/s, loss=0.685, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  23%|██▎       | 217/938 [00:15<00:51, 13.92it/s, loss=0.679, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  23%|██▎       | 218/938 [00:15<00:51, 13.93it/s, loss=0.673, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  23%|██▎       | 219/938 [00:15<00:51, 13.93it/s, loss=0.666, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  23%|██▎       | 220/938 [00:15<00:51, 13.92it/s, loss=0.666, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  23%|██▎       | 220/938 [00:15<00:51, 13.92it/s, loss=0.67, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  24%|██▎       | 221/938 [00:15<00:51, 13.92it/s, loss=0.669, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  24%|██▎       | 222/938 [00:15<00:51, 13.93it/s, loss=0.658, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  24%|██▍       | 223/938 [00:16<00:51, 13.92it/s, loss=0.659, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  24%|██▍       | 224/938 [00:16<00:51, 13.93it/s, loss=0.659, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  24%|██▍       | 224/938 [00:16<00:51, 13.93it/s, loss=0.66, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  24%|██▍       | 225/938 [00:16<00:51, 13.93it/s, loss=0.661, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  24%|██▍       | 226/938 [00:16<00:51, 13.93it/s, loss=0.653, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  24%|██▍       | 227/938 [00:16<00:51, 13.93it/s, loss=0.661, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  24%|██▍       | 228/938 [00:16<00:51, 13.92it/s, loss=0.661, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  24%|██▍       | 228/938 [00:16<00:51, 13.92it/s, loss=0.64, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  24%|██▍       | 229/938 [00:16<00:50, 13.92it/s, loss=0.642, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  25%|██▍       | 230/938 [00:16<00:50, 13.91it/s, loss=0.637, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  25%|██▍       | 231/938 [00:16<00:50, 13.90it/s, loss=0.639, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  25%|██▍       | 232/938 [00:16<00:50, 13.89it/s, loss=0.639, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  25%|██▍       | 232/938 [00:16<00:50, 13.89it/s, loss=0.635, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  25%|██▍       | 233/938 [00:16<00:50, 13.88it/s, loss=0.641, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  25%|██▍       | 234/938 [00:16<00:50, 13.89it/s, loss=0.641, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  25%|██▌       | 235/938 [00:16<00:50, 13.89it/s, loss=0.646, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  25%|██▌       | 236/938 [00:17<00:50, 13.87it/s, loss=0.646, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  25%|██▌       | 236/938 [00:17<00:50, 13.87it/s, loss=0.648, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  25%|██▌       | 237/938 [00:17<00:50, 13.86it/s, loss=0.651, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  25%|██▌       | 238/938 [00:17<00:50, 13.86it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  25%|██▌       | 239/938 [00:17<00:50, 13.87it/s, loss=0.655, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  26%|██▌       | 240/938 [00:17<00:50, 13.87it/s, loss=0.655, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  26%|██▌       | 240/938 [00:17<00:50, 13.87it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  26%|██▌       | 241/938 [00:17<00:50, 13.88it/s, loss=0.65, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  26%|██▌       | 242/938 [00:17<00:50, 13.87it/s, loss=0.659, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  26%|██▌       | 243/938 [00:17<00:50, 13.88it/s, loss=0.655, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  26%|██▌       | 244/938 [00:17<00:49, 13.88it/s, loss=0.655, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  26%|██▌       | 244/938 [00:17<00:49, 13.88it/s, loss=0.658, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  26%|██▌       | 245/938 [00:17<00:49, 13.89it/s, loss=0.655, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  26%|██▌       | 246/938 [00:17<00:49, 13.91it/s, loss=0.666, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  26%|██▋       | 247/938 [00:17<00:49, 13.91it/s, loss=0.663, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  26%|██▋       | 248/938 [00:17<00:49, 13.90it/s, loss=0.663, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  26%|██▋       | 248/938 [00:17<00:49, 13.90it/s, loss=0.664, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  27%|██▋       | 249/938 [00:17<00:49, 13.89it/s, loss=0.66, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  27%|██▋       | 250/938 [00:17<00:49, 13.89it/s, loss=0.663, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  27%|██▋       | 251/938 [00:18<00:49, 13.90it/s, loss=0.669, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  27%|██▋       | 252/938 [00:18<00:49, 13.91it/s, loss=0.669, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  27%|██▋       | 252/938 [00:18<00:49, 13.91it/s, loss=0.679, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  27%|██▋       | 253/938 [00:18<00:49, 13.90it/s, loss=0.68, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  27%|██▋       | 254/938 [00:18<00:49, 13.90it/s, loss=0.676, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  27%|██▋       | 255/938 [00:18<00:49, 13.90it/s, loss=0.679, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  27%|██▋       | 256/938 [00:18<00:49, 13.91it/s, loss=0.679, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  27%|██▋       | 256/938 [00:18<00:49, 13.91it/s, loss=0.676, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  27%|██▋       | 257/938 [00:18<00:48, 13.91it/s, loss=0.669, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  28%|██▊       | 258/938 [00:18<00:48, 13.90it/s, loss=0.677, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  28%|██▊       | 259/938 [00:18<00:48, 13.89it/s, loss=0.671, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  28%|██▊       | 260/938 [00:18<00:48, 13.90it/s, loss=0.671, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  28%|██▊       | 260/938 [00:18<00:48, 13.90it/s, loss=0.666, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  28%|██▊       | 261/938 [00:18<00:48, 13.89it/s, loss=0.672, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  28%|██▊       | 262/938 [00:18<00:48, 13.89it/s, loss=0.673, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  28%|██▊       | 263/938 [00:18<00:48, 13.90it/s, loss=0.681, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  28%|██▊       | 264/938 [00:18<00:48, 13.90it/s, loss=0.681, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  28%|██▊       | 264/938 [00:18<00:48, 13.90it/s, loss=0.688, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  28%|██▊       | 265/938 [00:19<00:48, 13.90it/s, loss=0.69, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  28%|██▊       | 266/938 [00:19<00:48, 13.91it/s, loss=0.685, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  28%|██▊       | 267/938 [00:19<00:48, 13.90it/s, loss=0.684, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  29%|██▊       | 268/938 [00:19<00:48, 13.92it/s, loss=0.684, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  29%|██▊       | 268/938 [00:19<00:48, 13.92it/s, loss=0.686, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  29%|██▊       | 269/938 [00:19<00:48, 13.91it/s, loss=0.695, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  29%|██▉       | 270/938 [00:19<00:48, 13.92it/s, loss=0.687, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  29%|██▉       | 271/938 [00:19<00:47, 13.93it/s, loss=0.675, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  29%|██▉       | 272/938 [00:19<00:47, 13.93it/s, loss=0.675, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  29%|██▉       | 272/938 [00:19<00:47, 13.93it/s, loss=0.664, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  29%|██▉       | 273/938 [00:19<00:47, 13.93it/s, loss=0.668, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  29%|██▉       | 274/938 [00:19<00:47, 13.92it/s, loss=0.674, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  29%|██▉       | 275/938 [00:19<00:47, 13.93it/s, loss=0.678, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  29%|██▉       | 276/938 [00:19<00:47, 13.93it/s, loss=0.678, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  29%|██▉       | 276/938 [00:19<00:47, 13.93it/s, loss=0.677, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  30%|██▉       | 277/938 [00:19<00:47, 13.94it/s, loss=0.68, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  30%|██▉       | 278/938 [00:19<00:47, 13.93it/s, loss=0.676, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  30%|██▉       | 279/938 [00:20<00:47, 13.92it/s, loss=0.676, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  30%|██▉       | 280/938 [00:20<00:47, 13.92it/s, loss=0.676, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  30%|██▉       | 280/938 [00:20<00:47, 13.92it/s, loss=0.679, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  30%|██▉       | 281/938 [00:20<00:47, 13.93it/s, loss=0.673, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  30%|███       | 282/938 [00:20<00:47, 13.94it/s, loss=0.669, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  30%|███       | 283/938 [00:20<00:47, 13.92it/s, loss=0.66, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  30%|███       | 284/938 [00:20<00:46, 13.92it/s, loss=0.66, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  30%|███       | 284/938 [00:20<00:46, 13.92it/s, loss=0.651, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  30%|███       | 285/938 [00:20<00:46, 13.92it/s, loss=0.651, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  30%|███       | 286/938 [00:20<00:46, 13.91it/s, loss=0.657, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  31%|███       | 287/938 [00:20<00:46, 13.91it/s, loss=0.654, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  31%|███       | 288/938 [00:20<00:46, 13.91it/s, loss=0.654, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  31%|███       | 288/938 [00:20<00:46, 13.91it/s, loss=0.658, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  31%|███       | 289/938 [00:20<00:46, 13.92it/s, loss=0.664, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  31%|███       | 290/938 [00:20<00:46, 13.92it/s, loss=0.671, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  31%|███       | 291/938 [00:20<00:46, 13.93it/s, loss=0.672, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  31%|███       | 292/938 [00:20<00:46, 13.93it/s, loss=0.672, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  31%|███       | 292/938 [00:20<00:46, 13.93it/s, loss=0.675, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  31%|███       | 293/938 [00:21<00:46, 13.94it/s, loss=0.67, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  31%|███▏      | 294/938 [00:21<00:46, 13.94it/s, loss=0.665, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  31%|███▏      | 295/938 [00:21<00:46, 13.94it/s, loss=0.661, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  32%|███▏      | 296/938 [00:21<00:46, 13.95it/s, loss=0.661, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  32%|███▏      | 296/938 [00:21<00:46, 13.95it/s, loss=0.66, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  32%|███▏      | 297/938 [00:21<00:45, 13.95it/s, loss=0.669, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  32%|███▏      | 298/938 [00:21<00:45, 13.95it/s, loss=0.672, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  32%|███▏      | 299/938 [00:21<00:45, 13.96it/s, loss=0.679, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  32%|███▏      | 300/938 [00:21<00:45, 13.95it/s, loss=0.679, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  32%|███▏      | 300/938 [00:21<00:45, 13.95it/s, loss=0.681, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  32%|███▏      | 301/938 [00:21<00:45, 13.95it/s, loss=0.688, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  32%|███▏      | 302/938 [00:21<00:45, 13.95it/s, loss=0.691, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  32%|███▏      | 303/938 [00:21<00:45, 13.94it/s, loss=0.691, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  32%|███▏      | 304/938 [00:21<00:45, 13.94it/s, loss=0.691, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  32%|███▏      | 304/938 [00:21<00:45, 13.94it/s, loss=0.695, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  33%|███▎      | 305/938 [00:21<00:45, 13.95it/s, loss=0.691, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  33%|███▎      | 306/938 [00:21<00:45, 13.94it/s, loss=0.69, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  33%|███▎      | 307/938 [00:22<00:45, 13.95it/s, loss=0.689, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  33%|███▎      | 308/938 [00:22<00:45, 13.94it/s, loss=0.689, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  33%|███▎      | 308/938 [00:22<00:45, 13.94it/s, loss=0.691, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  33%|███▎      | 309/938 [00:22<00:45, 13.92it/s, loss=0.689, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  33%|███▎      | 310/938 [00:22<00:45, 13.92it/s, loss=0.68, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  33%|███▎      | 311/938 [00:22<00:45, 13.92it/s, loss=0.682, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  33%|███▎      | 312/938 [00:22<00:44, 13.91it/s, loss=0.682, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  33%|███▎      | 312/938 [00:22<00:44, 13.91it/s, loss=0.678, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  33%|███▎      | 313/938 [00:22<00:44, 13.91it/s, loss=0.682, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  33%|███▎      | 314/938 [00:22<00:44, 13.92it/s, loss=0.685, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  34%|███▎      | 315/938 [00:22<00:44, 13.91it/s, loss=0.682, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  34%|███▎      | 316/938 [00:22<00:44, 13.91it/s, loss=0.682, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  34%|███▎      | 316/938 [00:22<00:44, 13.91it/s, loss=0.684, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  34%|███▍      | 317/938 [00:22<00:44, 13.92it/s, loss=0.683, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  34%|███▍      | 318/938 [00:22<00:44, 13.92it/s, loss=0.684, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  34%|███▍      | 319/938 [00:22<00:44, 13.92it/s, loss=0.673, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  34%|███▍      | 320/938 [00:22<00:44, 13.92it/s, loss=0.673, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  34%|███▍      | 320/938 [00:22<00:44, 13.92it/s, loss=0.664, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  34%|███▍      | 321/938 [00:23<00:44, 13.92it/s, loss=0.661, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  34%|███▍      | 322/938 [00:23<00:44, 13.92it/s, loss=0.655, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  34%|███▍      | 323/938 [00:23<00:44, 13.92it/s, loss=0.655, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  35%|███▍      | 324/938 [00:23<00:44, 13.92it/s, loss=0.655, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  35%|███▍      | 324/938 [00:23<00:44, 13.92it/s, loss=0.656, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  35%|███▍      | 325/938 [00:23<00:44, 13.91it/s, loss=0.668, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  35%|███▍      | 326/938 [00:23<00:43, 13.92it/s, loss=0.671, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  35%|███▍      | 327/938 [00:23<00:43, 13.92it/s, loss=0.675, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  35%|███▍      | 328/938 [00:23<00:43, 13.92it/s, loss=0.675, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  35%|███▍      | 328/938 [00:23<00:43, 13.92it/s, loss=0.674, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  35%|███▌      | 329/938 [00:23<00:43, 13.90it/s, loss=0.662, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  35%|███▌      | 330/938 [00:23<00:43, 13.90it/s, loss=0.662, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  35%|███▌      | 331/938 [00:23<00:43, 13.90it/s, loss=0.657, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  35%|███▌      | 332/938 [00:23<00:43, 13.90it/s, loss=0.657, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  35%|███▌      | 332/938 [00:23<00:43, 13.90it/s, loss=0.665, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  36%|███▌      | 333/938 [00:23<00:43, 13.90it/s, loss=0.66, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  36%|███▌      | 334/938 [00:24<00:43, 13.91it/s, loss=0.655, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  36%|███▌      | 335/938 [00:24<00:43, 13.90it/s, loss=0.661, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  36%|███▌      | 336/938 [00:24<00:43, 13.89it/s, loss=0.661, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  36%|███▌      | 336/938 [00:24<00:43, 13.89it/s, loss=0.668, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  36%|███▌      | 337/938 [00:24<00:43, 13.90it/s, loss=0.66, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  36%|███▌      | 338/938 [00:24<00:43, 13.90it/s, loss=0.654, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  36%|███▌      | 339/938 [00:24<00:43, 13.90it/s, loss=0.663, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  36%|███▌      | 340/938 [00:24<00:43, 13.89it/s, loss=0.663, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  36%|███▌      | 340/938 [00:24<00:43, 13.89it/s, loss=0.673, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  36%|███▋      | 341/938 [00:24<00:42, 13.90it/s, loss=0.668, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  36%|███▋      | 342/938 [00:24<00:42, 13.89it/s, loss=0.671, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  37%|███▋      | 343/938 [00:24<00:42, 13.90it/s, loss=0.671, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  37%|███▋      | 344/938 [00:24<00:42, 13.91it/s, loss=0.671, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  37%|███▋      | 344/938 [00:24<00:42, 13.91it/s, loss=0.664, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  37%|███▋      | 345/938 [00:24<00:42, 13.92it/s, loss=0.652, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  37%|███▋      | 346/938 [00:24<00:42, 13.92it/s, loss=0.65, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  37%|███▋      | 347/938 [00:24<00:42, 13.92it/s, loss=0.65, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  37%|███▋      | 348/938 [00:24<00:42, 13.92it/s, loss=0.65, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  37%|███▋      | 348/938 [00:24<00:42, 13.92it/s, loss=0.651, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  37%|███▋      | 349/938 [00:25<00:42, 13.93it/s, loss=0.658, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  37%|███▋      | 350/938 [00:25<00:42, 13.93it/s, loss=0.659, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  37%|███▋      | 351/938 [00:25<00:42, 13.93it/s, loss=0.667, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  38%|███▊      | 352/938 [00:25<00:42, 13.94it/s, loss=0.667, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  38%|███▊      | 352/938 [00:25<00:42, 13.93it/s, loss=0.671, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  38%|███▊      | 353/938 [00:25<00:41, 13.94it/s, loss=0.671, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  38%|███▊      | 354/938 [00:25<00:41, 13.94it/s, loss=0.674, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  38%|███▊      | 355/938 [00:25<00:41, 13.94it/s, loss=0.668, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  38%|███▊      | 356/938 [00:25<00:41, 13.95it/s, loss=0.668, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  38%|███▊      | 356/938 [00:25<00:41, 13.95it/s, loss=0.662, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  38%|███▊      | 357/938 [00:25<00:41, 13.95it/s, loss=0.66, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  38%|███▊      | 358/938 [00:25<00:41, 13.95it/s, loss=0.663, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  38%|███▊      | 359/938 [00:25<00:41, 13.96it/s, loss=0.668, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  38%|███▊      | 360/938 [00:25<00:41, 13.96it/s, loss=0.668, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  38%|███▊      | 360/938 [00:25<00:41, 13.96it/s, loss=0.662, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  38%|███▊      | 361/938 [00:25<00:41, 13.96it/s, loss=0.663, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  39%|███▊      | 362/938 [00:25<00:41, 13.96it/s, loss=0.661, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  39%|███▊      | 363/938 [00:25<00:41, 13.96it/s, loss=0.663, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  39%|███▉      | 364/938 [00:26<00:41, 13.96it/s, loss=0.663, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  39%|███▉      | 364/938 [00:26<00:41, 13.96it/s, loss=0.662, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  39%|███▉      | 365/938 [00:26<00:41, 13.96it/s, loss=0.672, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  39%|███▉      | 366/938 [00:26<00:40, 13.96it/s, loss=0.666, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  39%|███▉      | 367/938 [00:26<00:40, 13.97it/s, loss=0.671, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  39%|███▉      | 368/938 [00:26<00:40, 13.98it/s, loss=0.671, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  39%|███▉      | 368/938 [00:26<00:40, 13.98it/s, loss=0.662, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  39%|███▉      | 369/938 [00:26<00:40, 13.98it/s, loss=0.658, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  39%|███▉      | 370/938 [00:26<00:40, 13.98it/s, loss=0.66, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  40%|███▉      | 371/938 [00:26<00:40, 13.98it/s, loss=0.656, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  40%|███▉      | 372/938 [00:26<00:40, 13.99it/s, loss=0.656, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  40%|███▉      | 372/938 [00:26<00:40, 13.99it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  40%|███▉      | 373/938 [00:26<00:40, 13.98it/s, loss=0.647, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  40%|███▉      | 374/938 [00:26<00:40, 13.98it/s, loss=0.642, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  40%|███▉      | 375/938 [00:26<00:40, 13.98it/s, loss=0.643, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  40%|████      | 376/938 [00:26<00:40, 13.98it/s, loss=0.643, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  40%|████      | 376/938 [00:26<00:40, 13.98it/s, loss=0.641, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  40%|████      | 377/938 [00:26<00:40, 13.99it/s, loss=0.656, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  40%|████      | 378/938 [00:27<00:40, 13.99it/s, loss=0.652, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  40%|████      | 379/938 [00:27<00:39, 13.99it/s, loss=0.647, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  41%|████      | 380/938 [00:27<00:39, 13.99it/s, loss=0.647, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  41%|████      | 380/938 [00:27<00:39, 13.99it/s, loss=0.647, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  41%|████      | 381/938 [00:27<00:39, 13.99it/s, loss=0.652, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  41%|████      | 382/938 [00:27<00:39, 13.99it/s, loss=0.655, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  41%|████      | 383/938 [00:27<00:39, 13.99it/s, loss=0.65, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  41%|████      | 384/938 [00:27<00:39, 13.98it/s, loss=0.65, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  41%|████      | 384/938 [00:27<00:39, 13.98it/s, loss=0.651, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  41%|████      | 385/938 [00:27<00:39, 13.99it/s, loss=0.642, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  41%|████      | 386/938 [00:27<00:39, 13.98it/s, loss=0.638, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  41%|████▏     | 387/938 [00:27<00:39, 13.98it/s, loss=0.637, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  41%|████▏     | 388/938 [00:27<00:39, 13.98it/s, loss=0.637, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  41%|████▏     | 388/938 [00:27<00:39, 13.98it/s, loss=0.645, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  41%|████▏     | 389/938 [00:27<00:39, 13.99it/s, loss=0.647, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  42%|████▏     | 390/938 [00:27<00:39, 13.99it/s, loss=0.659, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  42%|████▏     | 391/938 [00:27<00:39, 13.99it/s, loss=0.659, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  42%|████▏     | 392/938 [00:28<00:39, 13.99it/s, loss=0.659, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  42%|████▏     | 392/938 [00:28<00:39, 13.99it/s, loss=0.652, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  42%|████▏     | 393/938 [00:28<00:38, 13.99it/s, loss=0.656, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  42%|████▏     | 394/938 [00:28<00:38, 13.98it/s, loss=0.669, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  42%|████▏     | 395/938 [00:28<00:38, 13.98it/s, loss=0.678, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  42%|████▏     | 396/938 [00:28<00:38, 13.97it/s, loss=0.678, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  42%|████▏     | 396/938 [00:28<00:38, 13.97it/s, loss=0.687, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  42%|████▏     | 397/938 [00:28<00:38, 13.98it/s, loss=0.68, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  42%|████▏     | 398/938 [00:28<00:38, 13.98it/s, loss=0.682, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  43%|████▎     | 399/938 [00:28<00:38, 13.98it/s, loss=0.678, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  43%|████▎     | 400/938 [00:28<00:38, 13.98it/s, loss=0.678, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  43%|████▎     | 400/938 [00:28<00:38, 13.98it/s, loss=0.685, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  43%|████▎     | 401/938 [00:28<00:38, 13.98it/s, loss=0.687, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  43%|████▎     | 402/938 [00:28<00:38, 13.98it/s, loss=0.689, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  43%|████▎     | 403/938 [00:28<00:38, 13.98it/s, loss=0.693, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  43%|████▎     | 404/938 [00:28<00:38, 13.98it/s, loss=0.693, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  43%|████▎     | 404/938 [00:28<00:38, 13.97it/s, loss=0.696, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  43%|████▎     | 405/938 [00:28<00:38, 13.97it/s, loss=0.697, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  43%|████▎     | 406/938 [00:29<00:38, 13.97it/s, loss=0.707, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  43%|████▎     | 407/938 [00:29<00:38, 13.97it/s, loss=0.695, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  43%|████▎     | 408/938 [00:29<00:37, 13.96it/s, loss=0.695, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  43%|████▎     | 408/938 [00:29<00:37, 13.96it/s, loss=0.693, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  44%|████▎     | 409/938 [00:29<00:37, 13.96it/s, loss=0.687, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  44%|████▎     | 410/938 [00:29<00:37, 13.96it/s, loss=0.668, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  44%|████▍     | 411/938 [00:29<00:37, 13.97it/s, loss=0.67, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  44%|████▍     | 412/938 [00:29<00:37, 13.97it/s, loss=0.67, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  44%|████▍     | 412/938 [00:29<00:37, 13.97it/s, loss=0.672, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  44%|████▍     | 413/938 [00:29<00:37, 13.97it/s, loss=0.674, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  44%|████▍     | 414/938 [00:29<00:37, 13.97it/s, loss=0.672, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  44%|████▍     | 415/938 [00:29<00:37, 13.97it/s, loss=0.673, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  44%|████▍     | 416/938 [00:29<00:37, 13.97it/s, loss=0.673, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  44%|████▍     | 416/938 [00:29<00:37, 13.97it/s, loss=0.662, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  44%|████▍     | 417/938 [00:29<00:37, 13.98it/s, loss=0.656, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  45%|████▍     | 418/938 [00:29<00:37, 13.98it/s, loss=0.659, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  45%|████▍     | 419/938 [00:29<00:37, 13.98it/s, loss=0.659, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  45%|████▍     | 420/938 [00:30<00:37, 13.97it/s, loss=0.659, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  45%|████▍     | 420/938 [00:30<00:37, 13.97it/s, loss=0.652, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  45%|████▍     | 421/938 [00:30<00:36, 13.98it/s, loss=0.645, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  45%|████▍     | 422/938 [00:30<00:36, 13.98it/s, loss=0.653, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  45%|████▌     | 423/938 [00:30<00:36, 13.98it/s, loss=0.653, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  45%|████▌     | 424/938 [00:30<00:36, 13.99it/s, loss=0.653, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  45%|████▌     | 424/938 [00:30<00:36, 13.99it/s, loss=0.655, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  45%|████▌     | 425/938 [00:30<00:36, 13.98it/s, loss=0.65, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  45%|████▌     | 426/938 [00:30<00:36, 13.95it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  46%|████▌     | 427/938 [00:30<00:36, 13.94it/s, loss=0.652, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  46%|████▌     | 428/938 [00:30<00:36, 13.94it/s, loss=0.652, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  46%|████▌     | 428/938 [00:30<00:36, 13.94it/s, loss=0.65, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  46%|████▌     | 429/938 [00:30<00:36, 13.94it/s, loss=0.661, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  46%|████▌     | 430/938 [00:30<00:36, 13.94it/s, loss=0.666, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  46%|████▌     | 431/938 [00:30<00:36, 13.94it/s, loss=0.668, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  46%|████▌     | 432/938 [00:30<00:36, 13.94it/s, loss=0.668, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  46%|████▌     | 432/938 [00:30<00:36, 13.94it/s, loss=0.67, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  46%|████▌     | 433/938 [00:31<00:36, 13.94it/s, loss=0.672, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  46%|████▋     | 434/938 [00:31<00:36, 13.94it/s, loss=0.663, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  46%|████▋     | 435/938 [00:31<00:36, 13.94it/s, loss=0.66, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  46%|████▋     | 436/938 [00:31<00:36, 13.93it/s, loss=0.66, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  46%|████▋     | 436/938 [00:31<00:36, 13.93it/s, loss=0.662, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  47%|████▋     | 437/938 [00:31<00:35, 13.93it/s, loss=0.669, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  47%|████▋     | 438/938 [00:31<00:35, 13.93it/s, loss=0.673, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  47%|████▋     | 439/938 [00:31<00:35, 13.93it/s, loss=0.676, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  47%|████▋     | 440/938 [00:31<00:35, 13.93it/s, loss=0.676, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  47%|████▋     | 440/938 [00:31<00:35, 13.93it/s, loss=0.676, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  47%|████▋     | 441/938 [00:31<00:35, 13.93it/s, loss=0.674, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  47%|████▋     | 442/938 [00:31<00:35, 13.93it/s, loss=0.665, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  47%|████▋     | 443/938 [00:31<00:35, 13.93it/s, loss=0.657, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  47%|████▋     | 444/938 [00:31<00:35, 13.93it/s, loss=0.657, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  47%|████▋     | 444/938 [00:31<00:35, 13.93it/s, loss=0.656, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  47%|████▋     | 445/938 [00:31<00:35, 13.94it/s, loss=0.66, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  48%|████▊     | 446/938 [00:32<00:35, 13.93it/s, loss=0.66, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  48%|████▊     | 447/938 [00:32<00:35, 13.94it/s, loss=0.662, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  48%|████▊     | 448/938 [00:32<00:35, 13.93it/s, loss=0.662, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  48%|████▊     | 448/938 [00:32<00:35, 13.93it/s, loss=0.672, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  48%|████▊     | 449/938 [00:32<00:35, 13.94it/s, loss=0.666, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  48%|████▊     | 450/938 [00:32<00:35, 13.94it/s, loss=0.668, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  48%|████▊     | 451/938 [00:32<00:34, 13.94it/s, loss=0.664, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  48%|████▊     | 452/938 [00:32<00:34, 13.94it/s, loss=0.664, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  48%|████▊     | 452/938 [00:32<00:34, 13.94it/s, loss=0.674, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  48%|████▊     | 453/938 [00:32<00:34, 13.94it/s, loss=0.671, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  48%|████▊     | 454/938 [00:32<00:34, 13.94it/s, loss=0.672, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  49%|████▊     | 455/938 [00:32<00:34, 13.94it/s, loss=0.668, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  49%|████▊     | 456/938 [00:32<00:34, 13.94it/s, loss=0.668, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  49%|████▊     | 456/938 [00:32<00:34, 13.94it/s, loss=0.674, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  49%|████▊     | 457/938 [00:32<00:34, 13.94it/s, loss=0.669, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  49%|████▉     | 458/938 [00:32<00:34, 13.94it/s, loss=0.666, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  49%|████▉     | 459/938 [00:32<00:34, 13.93it/s, loss=0.667, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  49%|████▉     | 460/938 [00:33<00:34, 13.93it/s, loss=0.667, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  49%|████▉     | 460/938 [00:33<00:34, 13.93it/s, loss=0.671, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  49%|████▉     | 461/938 [00:33<00:34, 13.93it/s, loss=0.673, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  49%|████▉     | 462/938 [00:33<00:34, 13.93it/s, loss=0.67, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  49%|████▉     | 463/938 [00:33<00:34, 13.93it/s, loss=0.677, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  49%|████▉     | 464/938 [00:33<00:34, 13.90it/s, loss=0.677, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  49%|████▉     | 464/938 [00:33<00:34, 13.90it/s, loss=0.667, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  50%|████▉     | 465/938 [00:33<00:34, 13.90it/s, loss=0.669, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  50%|████▉     | 466/938 [00:33<00:33, 13.89it/s, loss=0.67, v_num=15, val_rmse=0.553, train_rmse=0.732] 
Epoch 2:  50%|████▉     | 467/938 [00:33<00:33, 13.90it/s, loss=0.667, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  50%|████▉     | 468/938 [00:33<00:33, 13.89it/s, loss=0.667, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  50%|████▉     | 468/938 [00:33<00:33, 13.89it/s, loss=0.657, v_num=15, val_rmse=0.553, train_rmse=0.732]
Epoch 2:  50%|█████     | 469/938 [00:33<00:33, 13.90it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]

Validating:   0%|          | 2/469 [00:00<00:25, 18.12it/s]
Epoch 2:  50%|█████     | 472/938 [00:33<00:33, 13.94it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:   1%|          | 5/469 [00:00<00:20, 22.50it/s]
Epoch 2:  51%|█████     | 476/938 [00:34<00:33, 14.00it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:   2%|▏         | 8/469 [00:00<00:18, 24.82it/s]
Epoch 2:  51%|█████     | 480/938 [00:34<00:32, 14.05it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:   2%|▏         | 11/469 [00:00<00:18, 24.75it/s]

Validating:   3%|▎         | 14/469 [00:00<00:18, 24.87it/s]
Epoch 2:  52%|█████▏    | 484/938 [00:34<00:32, 14.10it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:   4%|▎         | 17/469 [00:00<00:17, 25.35it/s]
Epoch 2:  52%|█████▏    | 488/938 [00:34<00:31, 14.16it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:   4%|▍         | 20/469 [00:00<00:18, 24.74it/s]
Epoch 2:  52%|█████▏    | 492/938 [00:34<00:31, 14.20it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:   5%|▍         | 23/469 [00:00<00:18, 24.38it/s]

Validating:   6%|▌         | 26/469 [00:01<00:18, 24.51it/s]
Epoch 2:  53%|█████▎    | 496/938 [00:34<00:31, 14.25it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:   6%|▌         | 29/469 [00:01<00:17, 25.84it/s]
Epoch 2:  53%|█████▎    | 500/938 [00:34<00:30, 14.31it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:   7%|▋         | 32/469 [00:01<00:17, 25.48it/s]
Epoch 2:  54%|█████▎    | 504/938 [00:35<00:30, 14.36it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:   7%|▋         | 35/469 [00:01<00:17, 25.32it/s]

Validating:   8%|▊         | 38/469 [00:01<00:17, 24.39it/s]
Epoch 2:  54%|█████▍    | 508/938 [00:35<00:29, 14.40it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:   9%|▊         | 41/469 [00:01<00:16, 25.41it/s]
Epoch 2:  55%|█████▍    | 512/938 [00:35<00:29, 14.45it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:   9%|▉         | 44/469 [00:01<00:16, 26.00it/s]
Epoch 2:  55%|█████▌    | 516/938 [00:35<00:29, 14.51it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  10%|█         | 47/469 [00:01<00:16, 26.09it/s]

Validating:  11%|█         | 50/469 [00:01<00:15, 26.50it/s]
Epoch 2:  55%|█████▌    | 520/938 [00:35<00:28, 14.56it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  11%|█▏        | 53/469 [00:02<00:16, 25.28it/s]
Epoch 2:  56%|█████▌    | 524/938 [00:35<00:28, 14.60it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  12%|█▏        | 56/469 [00:02<00:16, 25.63it/s]
Epoch 2:  56%|█████▋    | 528/938 [00:36<00:27, 14.65it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  13%|█▎        | 59/469 [00:02<00:16, 25.60it/s]

Validating:  13%|█▎        | 62/469 [00:02<00:16, 24.67it/s]
Epoch 2:  57%|█████▋    | 532/938 [00:36<00:27, 14.69it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  14%|█▍        | 65/469 [00:02<00:15, 25.49it/s]
Epoch 2:  57%|█████▋    | 536/938 [00:36<00:27, 14.74it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  14%|█▍        | 68/469 [00:02<00:15, 25.30it/s]
Epoch 2:  58%|█████▊    | 540/938 [00:36<00:26, 14.78it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  15%|█▌        | 71/469 [00:02<00:15, 25.61it/s]

Validating:  16%|█▌        | 74/469 [00:02<00:15, 25.37it/s]
Epoch 2:  58%|█████▊    | 544/938 [00:36<00:26, 14.83it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  16%|█▋        | 77/469 [00:03<00:15, 25.39it/s]
Epoch 2:  58%|█████▊    | 548/938 [00:36<00:26, 14.87it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  17%|█▋        | 80/469 [00:03<00:15, 24.98it/s]
Epoch 2:  59%|█████▉    | 552/938 [00:37<00:25, 14.92it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  18%|█▊        | 83/469 [00:03<00:15, 25.29it/s]

Validating:  18%|█▊        | 86/469 [00:03<00:15, 25.11it/s]
Epoch 2:  59%|█████▉    | 556/938 [00:37<00:25, 14.96it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  19%|█▉        | 89/469 [00:03<00:16, 23.02it/s]
Epoch 2:  60%|█████▉    | 560/938 [00:37<00:25, 14.99it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  20%|█▉        | 92/469 [00:03<00:16, 23.29it/s]
Epoch 2:  60%|██████    | 564/938 [00:37<00:24, 15.03it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  20%|██        | 95/469 [00:03<00:16, 22.58it/s]

Validating:  21%|██        | 98/469 [00:03<00:15, 23.28it/s]
Epoch 2:  61%|██████    | 568/938 [00:37<00:24, 15.07it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  22%|██▏       | 101/469 [00:04<00:15, 24.40it/s]
Epoch 2:  61%|██████    | 572/938 [00:37<00:24, 15.11it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  22%|██▏       | 104/469 [00:04<00:14, 24.96it/s]
Epoch 2:  61%|██████▏   | 576/938 [00:37<00:23, 15.16it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  23%|██▎       | 107/469 [00:04<00:14, 25.44it/s]

Validating:  23%|██▎       | 110/469 [00:04<00:14, 25.29it/s]
Epoch 2:  62%|██████▏   | 580/938 [00:38<00:23, 15.20it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  24%|██▍       | 113/469 [00:04<00:14, 25.27it/s]
Epoch 2:  62%|██████▏   | 584/938 [00:38<00:23, 15.24it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  25%|██▍       | 116/469 [00:04<00:14, 25.03it/s]
Epoch 2:  63%|██████▎   | 588/938 [00:38<00:22, 15.28it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  25%|██▌       | 119/469 [00:04<00:13, 25.49it/s]

Validating:  26%|██▌       | 122/469 [00:04<00:14, 23.93it/s]
Epoch 2:  63%|██████▎   | 592/938 [00:38<00:22, 15.32it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  27%|██▋       | 125/469 [00:05<00:13, 24.69it/s]
Epoch 2:  64%|██████▎   | 596/938 [00:38<00:22, 15.36it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  27%|██▋       | 128/469 [00:05<00:13, 24.67it/s]
Epoch 2:  64%|██████▍   | 600/938 [00:38<00:21, 15.40it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  28%|██▊       | 131/469 [00:05<00:13, 24.89it/s]

Validating:  29%|██▊       | 134/469 [00:05<00:13, 25.34it/s]
Epoch 2:  64%|██████▍   | 604/938 [00:39<00:21, 15.44it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  29%|██▉       | 137/469 [00:05<00:13, 25.05it/s]
Epoch 2:  65%|██████▍   | 608/938 [00:39<00:21, 15.48it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  30%|██▉       | 140/469 [00:05<00:13, 25.16it/s]
Epoch 2:  65%|██████▌   | 612/938 [00:39<00:21, 15.50it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  30%|███       | 143/469 [00:05<00:14, 22.97it/s]

Validating:  31%|███       | 146/469 [00:05<00:14, 22.05it/s]
Epoch 2:  66%|██████▌   | 616/938 [00:39<00:20, 15.53it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  32%|███▏      | 149/469 [00:06<00:14, 22.40it/s]
Epoch 2:  66%|██████▌   | 620/938 [00:39<00:20, 15.57it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  32%|███▏      | 152/469 [00:06<00:13, 22.96it/s]
Epoch 2:  67%|██████▋   | 624/938 [00:40<00:20, 15.60it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  33%|███▎      | 155/469 [00:06<00:13, 23.29it/s]

Validating:  34%|███▎      | 158/469 [00:06<00:13, 22.88it/s]
Epoch 2:  67%|██████▋   | 628/938 [00:40<00:19, 15.63it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  34%|███▍      | 161/469 [00:06<00:13, 22.84it/s]
Epoch 2:  67%|██████▋   | 632/938 [00:40<00:19, 15.66it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  35%|███▍      | 164/469 [00:06<00:12, 23.56it/s]
Epoch 2:  68%|██████▊   | 636/938 [00:40<00:19, 15.70it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  36%|███▌      | 167/469 [00:06<00:12, 23.31it/s]

Validating:  36%|███▌      | 170/469 [00:06<00:12, 23.44it/s]
Epoch 2:  68%|██████▊   | 640/938 [00:40<00:18, 15.73it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  37%|███▋      | 173/469 [00:07<00:12, 24.02it/s]
Epoch 2:  69%|██████▊   | 644/938 [00:40<00:18, 15.77it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  38%|███▊      | 176/469 [00:07<00:13, 22.44it/s]
Epoch 2:  69%|██████▉   | 648/938 [00:41<00:18, 15.79it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  38%|███▊      | 179/469 [00:07<00:12, 23.21it/s]

Validating:  39%|███▉      | 182/469 [00:07<00:12, 23.82it/s]
Epoch 2:  70%|██████▉   | 652/938 [00:41<00:18, 15.83it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  39%|███▉      | 185/469 [00:07<00:12, 23.31it/s]
Epoch 2:  70%|██████▉   | 656/938 [00:41<00:17, 15.85it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  40%|████      | 188/469 [00:07<00:12, 22.95it/s]
Epoch 2:  70%|███████   | 660/938 [00:41<00:17, 15.89it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  41%|████      | 191/469 [00:07<00:11, 24.21it/s]

Validating:  41%|████▏     | 194/469 [00:07<00:11, 23.69it/s]
Epoch 2:  71%|███████   | 664/938 [00:41<00:17, 15.92it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  42%|████▏     | 197/469 [00:08<00:11, 24.45it/s]
Epoch 2:  71%|███████   | 668/938 [00:41<00:16, 15.96it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  43%|████▎     | 200/469 [00:08<00:10, 24.76it/s]
Epoch 2:  72%|███████▏  | 672/938 [00:42<00:16, 15.99it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  43%|████▎     | 203/469 [00:08<00:10, 25.14it/s]

Validating:  44%|████▍     | 206/469 [00:08<00:10, 25.41it/s]
Epoch 2:  72%|███████▏  | 676/938 [00:42<00:16, 16.03it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  45%|████▍     | 209/469 [00:08<00:10, 25.55it/s]
Epoch 2:  72%|███████▏  | 680/938 [00:42<00:16, 16.07it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  45%|████▌     | 212/469 [00:08<00:10, 25.35it/s]
Epoch 2:  73%|███████▎  | 684/938 [00:42<00:15, 16.10it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  46%|████▌     | 215/469 [00:08<00:09, 25.47it/s]

Validating:  46%|████▋     | 218/469 [00:08<00:09, 25.90it/s]
Epoch 2:  73%|███████▎  | 688/938 [00:42<00:15, 16.14it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  47%|████▋     | 221/469 [00:09<00:09, 25.76it/s]
Epoch 2:  74%|███████▍  | 692/938 [00:42<00:15, 16.17it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  48%|████▊     | 224/469 [00:09<00:09, 25.18it/s]
Epoch 2:  74%|███████▍  | 696/938 [00:42<00:14, 16.20it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  48%|████▊     | 227/469 [00:09<00:09, 25.12it/s]

Validating:  49%|████▉     | 230/469 [00:09<00:09, 24.10it/s]
Epoch 2:  75%|███████▍  | 700/938 [00:43<00:14, 16.23it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  50%|████▉     | 233/469 [00:09<00:09, 24.37it/s]
Epoch 2:  75%|███████▌  | 704/938 [00:43<00:14, 16.26it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  50%|█████     | 236/469 [00:09<00:09, 25.23it/s]
Epoch 2:  75%|███████▌  | 708/938 [00:43<00:14, 16.29it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  51%|█████     | 239/469 [00:09<00:09, 24.42it/s]

Validating:  52%|█████▏    | 242/469 [00:09<00:09, 23.81it/s]
Epoch 2:  76%|███████▌  | 712/938 [00:43<00:13, 16.32it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  52%|█████▏    | 245/469 [00:09<00:08, 25.18it/s]
Epoch 2:  76%|███████▋  | 716/938 [00:43<00:13, 16.36it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  53%|█████▎    | 248/469 [00:10<00:08, 25.21it/s]
Epoch 2:  77%|███████▋  | 720/938 [00:43<00:13, 16.39it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  54%|█████▎    | 251/469 [00:10<00:08, 25.59it/s]

Validating:  54%|█████▍    | 254/469 [00:10<00:08, 25.61it/s]
Epoch 2:  77%|███████▋  | 724/938 [00:44<00:13, 16.42it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  55%|█████▍    | 257/469 [00:10<00:08, 24.43it/s]
Epoch 2:  78%|███████▊  | 728/938 [00:44<00:12, 16.45it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  55%|█████▌    | 260/469 [00:10<00:08, 24.83it/s]
Epoch 2:  78%|███████▊  | 732/938 [00:44<00:12, 16.48it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  56%|█████▌    | 263/469 [00:10<00:08, 25.12it/s]

Validating:  57%|█████▋    | 266/469 [00:10<00:07, 25.78it/s]
Epoch 2:  78%|███████▊  | 736/938 [00:44<00:12, 16.52it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  57%|█████▋    | 269/469 [00:10<00:07, 25.98it/s]
Epoch 2:  79%|███████▉  | 740/938 [00:44<00:11, 16.55it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  58%|█████▊    | 272/469 [00:11<00:07, 25.58it/s]
Epoch 2:  79%|███████▉  | 744/938 [00:44<00:11, 16.58it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  59%|█████▊    | 275/469 [00:11<00:07, 25.33it/s]

Validating:  59%|█████▉    | 278/469 [00:11<00:07, 25.81it/s]
Epoch 2:  80%|███████▉  | 748/938 [00:45<00:11, 16.61it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  60%|█████▉    | 281/469 [00:11<00:07, 25.18it/s]
Epoch 2:  80%|████████  | 752/938 [00:45<00:11, 16.64it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  61%|██████    | 284/469 [00:11<00:07, 25.14it/s]
Epoch 2:  81%|████████  | 756/938 [00:45<00:10, 16.67it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  61%|██████    | 287/469 [00:11<00:07, 24.91it/s]

Validating:  62%|██████▏   | 290/469 [00:11<00:07, 25.27it/s]
Epoch 2:  81%|████████  | 760/938 [00:45<00:10, 16.70it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  62%|██████▏   | 293/469 [00:11<00:07, 24.69it/s]
Epoch 2:  81%|████████▏ | 764/938 [00:45<00:10, 16.72it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  63%|██████▎   | 296/469 [00:12<00:07, 24.05it/s]
Epoch 2:  82%|████████▏ | 768/938 [00:45<00:10, 16.75it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  64%|██████▍   | 299/469 [00:12<00:07, 23.45it/s]

Validating:  64%|██████▍   | 302/469 [00:12<00:06, 24.82it/s]
Epoch 2:  82%|████████▏ | 772/938 [00:46<00:09, 16.78it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  65%|██████▌   | 305/469 [00:12<00:06, 25.54it/s]
Epoch 2:  83%|████████▎ | 776/938 [00:46<00:09, 16.81it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  66%|██████▌   | 308/469 [00:12<00:06, 25.86it/s]
Epoch 2:  83%|████████▎ | 780/938 [00:46<00:09, 16.85it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  66%|██████▋   | 311/469 [00:12<00:06, 26.17it/s]

Validating:  67%|██████▋   | 314/469 [00:12<00:05, 26.14it/s]
Epoch 2:  84%|████████▎ | 784/938 [00:46<00:09, 16.88it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  68%|██████▊   | 317/469 [00:12<00:06, 24.68it/s]
Epoch 2:  84%|████████▍ | 788/938 [00:46<00:08, 16.89it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  68%|██████▊   | 320/469 [00:12<00:06, 23.55it/s]
Epoch 2:  84%|████████▍ | 792/938 [00:46<00:08, 16.92it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  69%|██████▉   | 323/469 [00:13<00:05, 24.70it/s]

Validating:  70%|██████▉   | 326/469 [00:13<00:05, 24.93it/s]
Epoch 2:  85%|████████▍ | 796/938 [00:46<00:08, 16.95it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  70%|███████   | 329/469 [00:13<00:05, 25.91it/s]
Epoch 2:  85%|████████▌ | 800/938 [00:47<00:08, 16.98it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  71%|███████   | 332/469 [00:13<00:05, 25.41it/s]
Epoch 2:  86%|████████▌ | 804/938 [00:47<00:07, 17.01it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  71%|███████▏  | 335/469 [00:13<00:05, 25.38it/s]

Validating:  72%|███████▏  | 338/469 [00:13<00:05, 25.30it/s]
Epoch 2:  86%|████████▌ | 808/938 [00:47<00:07, 17.04it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  73%|███████▎  | 341/469 [00:13<00:05, 25.16it/s]
Epoch 2:  87%|████████▋ | 812/938 [00:47<00:07, 17.06it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  73%|███████▎  | 344/469 [00:13<00:04, 25.13it/s]
Epoch 2:  87%|████████▋ | 816/938 [00:47<00:07, 17.09it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  74%|███████▍  | 347/469 [00:14<00:04, 25.17it/s]

Validating:  75%|███████▍  | 350/469 [00:14<00:04, 25.38it/s]
Epoch 2:  87%|████████▋ | 820/938 [00:47<00:06, 17.12it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  75%|███████▌  | 353/469 [00:14<00:04, 25.43it/s]
Epoch 2:  88%|████████▊ | 824/938 [00:48<00:06, 17.15it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  76%|███████▌  | 356/469 [00:14<00:04, 24.94it/s]
Epoch 2:  88%|████████▊ | 828/938 [00:48<00:06, 17.17it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  77%|███████▋  | 359/469 [00:14<00:04, 24.72it/s]

Validating:  77%|███████▋  | 362/469 [00:14<00:04, 25.40it/s]
Epoch 2:  89%|████████▊ | 832/938 [00:48<00:06, 17.20it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  78%|███████▊  | 365/469 [00:14<00:04, 24.22it/s]
Epoch 2:  89%|████████▉ | 836/938 [00:48<00:05, 17.22it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  78%|███████▊  | 368/469 [00:14<00:04, 23.82it/s]
Epoch 2:  90%|████████▉ | 840/938 [00:48<00:05, 17.23it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  79%|███████▉  | 371/469 [00:15<00:04, 23.18it/s]

Validating:  80%|███████▉  | 374/469 [00:15<00:04, 23.02it/s]
Epoch 2:  90%|████████▉ | 844/938 [00:48<00:05, 17.25it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  80%|████████  | 377/469 [00:15<00:03, 23.36it/s]
Epoch 2:  90%|█████████ | 848/938 [00:49<00:05, 17.28it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  81%|████████  | 380/469 [00:15<00:03, 23.86it/s]
Epoch 2:  91%|█████████ | 852/938 [00:49<00:04, 17.30it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  82%|████████▏ | 383/469 [00:15<00:03, 24.34it/s]

Validating:  82%|████████▏ | 386/469 [00:15<00:03, 24.39it/s]
Epoch 2:  91%|█████████▏| 856/938 [00:49<00:04, 17.33it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  83%|████████▎ | 389/469 [00:15<00:03, 24.41it/s]
Epoch 2:  92%|█████████▏| 860/938 [00:49<00:04, 17.35it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  84%|████████▎ | 392/469 [00:15<00:03, 24.42it/s]
Epoch 2:  92%|█████████▏| 864/938 [00:49<00:04, 17.38it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  84%|████████▍ | 395/469 [00:16<00:02, 24.71it/s]

Validating:  85%|████████▍ | 398/469 [00:16<00:02, 24.98it/s]
Epoch 2:  93%|█████████▎| 868/938 [00:49<00:04, 17.40it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  86%|████████▌ | 401/469 [00:16<00:02, 23.85it/s]
Epoch 2:  93%|█████████▎| 872/938 [00:50<00:03, 17.42it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  86%|████████▌ | 404/469 [00:16<00:02, 24.88it/s]
Epoch 2:  93%|█████████▎| 876/938 [00:50<00:03, 17.45it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  87%|████████▋ | 407/469 [00:16<00:02, 25.94it/s]

Validating:  87%|████████▋ | 410/469 [00:16<00:02, 25.98it/s]
Epoch 2:  94%|█████████▍| 880/938 [00:50<00:03, 17.48it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  88%|████████▊ | 413/469 [00:16<00:02, 25.38it/s]
Epoch 2:  94%|█████████▍| 884/938 [00:50<00:03, 17.50it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  89%|████████▊ | 416/469 [00:16<00:02, 25.03it/s]
Epoch 2:  95%|█████████▍| 888/938 [00:50<00:02, 17.52it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  89%|████████▉ | 419/469 [00:16<00:02, 24.19it/s]

Validating:  90%|████████▉ | 422/469 [00:17<00:01, 24.88it/s]
Epoch 2:  95%|█████████▌| 892/938 [00:50<00:02, 17.54it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  91%|█████████ | 425/469 [00:17<00:01, 24.23it/s]
Epoch 2:  96%|█████████▌| 896/938 [00:51<00:02, 17.56it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  91%|█████████▏| 428/469 [00:17<00:01, 24.24it/s]
Epoch 2:  96%|█████████▌| 900/938 [00:51<00:02, 17.59it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  92%|█████████▏| 431/469 [00:17<00:01, 24.28it/s]

Validating:  93%|█████████▎| 434/469 [00:17<00:01, 24.38it/s]
Epoch 2:  96%|█████████▋| 904/938 [00:51<00:01, 17.61it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  93%|█████████▎| 437/469 [00:17<00:01, 25.12it/s]
Epoch 2:  97%|█████████▋| 908/938 [00:51<00:01, 17.63it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  94%|█████████▍| 440/469 [00:17<00:01, 26.24it/s]
Epoch 2:  97%|█████████▋| 912/938 [00:51<00:01, 17.67it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  94%|█████████▍| 443/469 [00:17<00:00, 26.87it/s]

Validating:  95%|█████████▌| 446/469 [00:18<00:00, 26.00it/s]
Epoch 2:  98%|█████████▊| 916/938 [00:51<00:01, 17.69it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  96%|█████████▌| 449/469 [00:18<00:00, 25.64it/s]
Epoch 2:  98%|█████████▊| 920/938 [00:51<00:01, 17.71it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  96%|█████████▋| 452/469 [00:18<00:00, 25.82it/s]
Epoch 2:  99%|█████████▊| 924/938 [00:52<00:00, 17.73it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  97%|█████████▋| 455/469 [00:18<00:00, 25.67it/s]

Validating:  98%|█████████▊| 458/469 [00:18<00:00, 25.48it/s]
Epoch 2:  99%|█████████▉| 928/938 [00:52<00:00, 17.76it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  98%|█████████▊| 461/469 [00:18<00:00, 25.56it/s]
Epoch 2:  99%|█████████▉| 932/938 [00:52<00:00, 17.78it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating:  99%|█████████▉| 464/469 [00:18<00:00, 25.50it/s]
Epoch 2: 100%|█████████▉| 936/938 [00:52<00:00, 17.81it/s, loss=0.649, v_num=15, val_rmse=0.553, train_rmse=0.732]

Validating: 100%|█████████▉| 467/469 [00:18<00:00, 26.03it/s]
Epoch 2: 100%|██████████| 938/938 [00:52<00:00, 17.81it/s, loss=0.649, v_num=15, val_rmse=0.523, train_rmse=0.732]

                                                             
Epoch 2: 100%|██████████| 938/938 [00:52<00:00, 17.80it/s, loss=0.649, v_num=15, val_rmse=0.523, train_rmse=0.674]
Epoch 2: 100%|██████████| 938/938 [00:52<00:00, 17.76it/s, loss=0.649, v_num=15, val_rmse=0.523, train_rmse=0.674]LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]


Testing: 0it [00:00, ?it/s]
Testing:   1%|          | 3/469 [00:00<00:21, 21.47it/s]
Testing:   1%|▏         | 6/469 [00:00<00:19, 23.54it/s]
Testing:   2%|▏         | 9/469 [00:00<00:19, 23.68it/s]
Testing:   3%|▎         | 12/469 [00:00<00:19, 24.05it/s]
Testing:   3%|▎         | 15/469 [00:00<00:18, 24.08it/s]
Testing:   4%|▍         | 18/469 [00:00<00:18, 24.85it/s]
Testing:   4%|▍         | 21/469 [00:00<00:18, 24.56it/s]
Testing:   5%|▌         | 24/469 [00:00<00:17, 25.04it/s]
Testing:   6%|▌         | 27/469 [00:01<00:17, 24.88it/s]
Testing:   6%|▋         | 30/469 [00:01<00:17, 25.41it/s]
Testing:   7%|▋         | 33/469 [00:01<00:17, 25.64it/s]
Testing:   8%|▊         | 36/469 [00:01<00:16, 26.78it/s]
Testing:   8%|▊         | 39/469 [00:01<00:16, 26.70it/s]
Testing:   9%|▉         | 42/469 [00:01<00:16, 26.11it/s]
Testing:  10%|▉         | 45/469 [00:01<00:16, 24.97it/s]
Testing:  10%|█         | 48/469 [00:01<00:16, 25.06it/s]
Testing:  11%|█         | 51/469 [00:02<00:17, 24.37it/s]
Testing:  12%|█▏        | 54/469 [00:02<00:16, 24.52it/s]
Testing:  12%|█▏        | 57/469 [00:02<00:15, 25.94it/s]
Testing:  13%|█▎        | 60/469 [00:02<00:15, 25.64it/s]
Testing:  13%|█▎        | 63/469 [00:02<00:16, 24.66it/s]
Testing:  14%|█▍        | 66/469 [00:02<00:16, 25.12it/s]
Testing:  15%|█▍        | 69/469 [00:02<00:15, 25.31it/s]
Testing:  16%|█▌        | 73/469 [00:02<00:14, 26.55it/s]
Testing:  16%|█▌        | 76/469 [00:03<00:14, 26.58it/s]
Testing:  17%|█▋        | 79/469 [00:03<00:14, 26.54it/s]
Testing:  17%|█▋        | 82/469 [00:03<00:15, 24.80it/s]
Testing:  18%|█▊        | 85/469 [00:03<00:15, 24.68it/s]
Testing:  19%|█▉        | 88/469 [00:03<00:14, 25.43it/s]
Testing:  19%|█▉        | 91/469 [00:03<00:14, 25.62it/s]
Testing:  20%|██        | 94/469 [00:03<00:14, 25.86it/s]
Testing:  21%|██        | 97/469 [00:03<00:14, 25.95it/s]
Testing:  21%|██▏       | 100/469 [00:03<00:15, 24.36it/s]
Testing:  22%|██▏       | 103/469 [00:04<00:14, 24.76it/s]
Testing:  23%|██▎       | 106/469 [00:04<00:14, 24.49it/s]
Testing:  23%|██▎       | 109/469 [00:04<00:14, 24.07it/s]
Testing:  24%|██▍       | 112/469 [00:04<00:15, 23.65it/s]
Testing:  25%|██▍       | 115/469 [00:04<00:15, 23.28it/s]
Testing:  25%|██▌       | 118/469 [00:04<00:14, 23.79it/s]
Testing:  26%|██▌       | 121/469 [00:04<00:14, 23.75it/s]
Testing:  26%|██▋       | 124/469 [00:04<00:14, 23.55it/s]
Testing:  27%|██▋       | 127/469 [00:05<00:14, 24.09it/s]
Testing:  28%|██▊       | 130/469 [00:05<00:14, 24.06it/s]
Testing:  28%|██▊       | 133/469 [00:05<00:13, 24.49it/s]
Testing:  29%|██▉       | 136/469 [00:05<00:13, 25.34it/s]
Testing:  30%|██▉       | 139/469 [00:05<00:12, 25.76it/s]
Testing:  30%|███       | 142/469 [00:05<00:12, 25.40it/s]
Testing:  31%|███       | 145/469 [00:05<00:12, 26.00it/s]
Testing:  32%|███▏      | 148/469 [00:05<00:12, 26.21it/s]
Testing:  32%|███▏      | 151/469 [00:06<00:12, 25.53it/s]
Testing:  33%|███▎      | 154/469 [00:06<00:12, 25.18it/s]
Testing:  33%|███▎      | 157/469 [00:06<00:12, 25.38it/s]
Testing:  34%|███▍      | 160/469 [00:06<00:11, 26.27it/s]
Testing:  35%|███▍      | 163/469 [00:06<00:11, 25.59it/s]
Testing:  35%|███▌      | 166/469 [00:06<00:11, 26.24it/s]
Testing:  36%|███▌      | 169/469 [00:06<00:11, 25.82it/s]
Testing:  37%|███▋      | 172/469 [00:06<00:11, 26.66it/s]
Testing:  37%|███▋      | 175/469 [00:06<00:11, 26.42it/s]
Testing:  38%|███▊      | 178/469 [00:07<00:10, 26.46it/s]
Testing:  39%|███▊      | 181/469 [00:07<00:10, 26.38it/s]
Testing:  39%|███▉      | 184/469 [00:07<00:11, 25.54it/s]
Testing:  40%|███▉      | 187/469 [00:07<00:11, 24.86it/s]
Testing:  41%|████      | 190/469 [00:07<00:11, 24.95it/s]
Testing:  41%|████      | 193/469 [00:07<00:11, 25.02it/s]
Testing:  42%|████▏     | 196/469 [00:07<00:10, 25.53it/s]
Testing:  42%|████▏     | 199/469 [00:07<00:10, 25.06it/s]
Testing:  43%|████▎     | 202/469 [00:08<00:10, 24.86it/s]
Testing:  44%|████▎     | 205/469 [00:08<00:10, 24.97it/s]
Testing:  44%|████▍     | 208/469 [00:08<00:10, 25.43it/s]
Testing:  45%|████▍     | 211/469 [00:08<00:10, 25.36it/s]
Testing:  46%|████▌     | 214/469 [00:08<00:10, 24.44it/s]
Testing:  46%|████▋     | 217/469 [00:08<00:09, 25.67it/s]
Testing:  47%|████▋     | 220/469 [00:08<00:09, 25.71it/s]
Testing:  48%|████▊     | 223/469 [00:08<00:09, 25.12it/s]
Testing:  48%|████▊     | 226/469 [00:08<00:09, 25.36it/s]
Testing:  49%|████▉     | 229/469 [00:09<00:09, 25.47it/s]
Testing:  49%|████▉     | 232/469 [00:09<00:09, 25.92it/s]
Testing:  50%|█████     | 235/469 [00:09<00:08, 26.18it/s]
Testing:  51%|█████     | 238/469 [00:09<00:08, 26.13it/s]
Testing:  51%|█████▏    | 241/469 [00:09<00:08, 25.59it/s]
Testing:  52%|█████▏    | 244/469 [00:09<00:09, 24.58it/s]
Testing:  53%|█████▎    | 247/469 [00:09<00:08, 25.75it/s]
Testing:  53%|█████▎    | 250/469 [00:09<00:08, 26.18it/s]
Testing:  54%|█████▍    | 253/469 [00:10<00:08, 26.95it/s]
Testing:  55%|█████▍    | 256/469 [00:10<00:08, 26.49it/s]
Testing:  55%|█████▌    | 259/469 [00:10<00:08, 26.05it/s]
Testing:  56%|█████▌    | 262/469 [00:10<00:07, 26.45it/s]
Testing:  57%|█████▋    | 265/469 [00:10<00:07, 26.71it/s]
Testing:  57%|█████▋    | 268/469 [00:10<00:08, 23.63it/s]
Testing:  58%|█████▊    | 271/469 [00:10<00:08, 23.26it/s]
Testing:  58%|█████▊    | 274/469 [00:10<00:08, 23.76it/s]
Testing:  59%|█████▉    | 277/469 [00:11<00:08, 23.92it/s]
Testing:  60%|█████▉    | 280/469 [00:11<00:07, 24.58it/s]
Testing:  60%|██████    | 283/469 [00:11<00:07, 23.94it/s]
Testing:  61%|██████    | 286/469 [00:11<00:07, 23.91it/s]
Testing:  62%|██████▏   | 289/469 [00:11<00:07, 23.85it/s]
Testing:  62%|██████▏   | 292/469 [00:11<00:07, 24.69it/s]
Testing:  63%|██████▎   | 295/469 [00:11<00:06, 24.86it/s]
Testing:  64%|██████▎   | 298/469 [00:11<00:06, 25.33it/s]
Testing:  64%|██████▍   | 301/469 [00:11<00:06, 25.11it/s]
Testing:  65%|██████▍   | 304/469 [00:12<00:06, 25.57it/s]
Testing:  65%|██████▌   | 307/469 [00:12<00:06, 25.02it/s]
Testing:  66%|██████▌   | 310/469 [00:12<00:06, 24.66it/s]
Testing:  67%|██████▋   | 313/469 [00:12<00:06, 25.31it/s]
Testing:  67%|██████▋   | 316/469 [00:12<00:06, 25.18it/s]
Testing:  68%|██████▊   | 319/469 [00:12<00:05, 25.56it/s]
Testing:  69%|██████▊   | 322/469 [00:12<00:05, 24.69it/s]
Testing:  69%|██████▉   | 325/469 [00:12<00:05, 24.53it/s]
Testing:  70%|██████▉   | 328/469 [00:13<00:05, 24.55it/s]
Testing:  71%|███████   | 331/469 [00:13<00:05, 25.40it/s]
Testing:  71%|███████   | 334/469 [00:13<00:05, 25.48it/s]
Testing:  72%|███████▏  | 337/469 [00:13<00:05, 25.28it/s]
Testing:  72%|███████▏  | 340/469 [00:13<00:05, 25.16it/s]
Testing:  73%|███████▎  | 343/469 [00:13<00:04, 25.74it/s]
Testing:  74%|███████▍  | 346/469 [00:13<00:04, 25.27it/s]
Testing:  74%|███████▍  | 349/469 [00:13<00:04, 24.88it/s]
Testing:  75%|███████▌  | 352/469 [00:14<00:04, 24.76it/s]
Testing:  76%|███████▌  | 355/469 [00:14<00:04, 25.78it/s]
Testing:  76%|███████▋  | 358/469 [00:14<00:04, 25.69it/s]
Testing:  77%|███████▋  | 361/469 [00:14<00:04, 25.39it/s]
Testing:  78%|███████▊  | 364/469 [00:14<00:04, 24.18it/s]
Testing:  78%|███████▊  | 367/469 [00:14<00:04, 24.24it/s]
Testing:  79%|███████▉  | 370/469 [00:14<00:04, 24.20it/s]
Testing:  80%|███████▉  | 373/469 [00:14<00:03, 25.10it/s]
Testing:  80%|████████  | 376/469 [00:14<00:03, 25.05it/s]
Testing:  81%|████████  | 379/469 [00:15<00:03, 24.94it/s]
Testing:  81%|████████▏ | 382/469 [00:15<00:03, 25.63it/s]
Testing:  82%|████████▏ | 385/469 [00:15<00:03, 25.15it/s]
Testing:  83%|████████▎ | 388/469 [00:15<00:03, 25.86it/s]
Testing:  83%|████████▎ | 391/469 [00:15<00:03, 25.96it/s]
Testing:  84%|████████▍ | 394/469 [00:15<00:02, 26.20it/s]
Testing:  85%|████████▍ | 397/469 [00:15<00:02, 25.81it/s]
Testing:  85%|████████▌ | 400/469 [00:15<00:02, 25.79it/s]
Testing:  86%|████████▌ | 403/469 [00:16<00:02, 25.95it/s]
Testing:  87%|████████▋ | 406/469 [00:16<00:02, 25.61it/s]
Testing:  87%|████████▋ | 409/469 [00:16<00:02, 23.84it/s]
Testing:  88%|████████▊ | 412/469 [00:16<00:02, 24.11it/s]
Testing:  88%|████████▊ | 415/469 [00:16<00:02, 24.93it/s]
Testing:  89%|████████▉ | 418/469 [00:16<00:02, 25.06it/s]
Testing:  90%|████████▉ | 421/469 [00:16<00:01, 24.74it/s]
Testing:  90%|█████████ | 424/469 [00:16<00:01, 23.37it/s]
Testing:  91%|█████████ | 427/469 [00:17<00:01, 24.16it/s]
Testing:  92%|█████████▏| 430/469 [00:17<00:01, 25.29it/s]
Testing:  92%|█████████▏| 433/469 [00:17<00:01, 24.30it/s]
Testing:  93%|█████████▎| 436/469 [00:17<00:01, 25.44it/s]
Testing:  94%|█████████▎| 439/469 [00:17<00:01, 25.60it/s]
Testing:  94%|█████████▍| 442/469 [00:17<00:01, 23.75it/s]
Testing:  95%|█████████▍| 445/469 [00:17<00:00, 24.84it/s]
Testing:  96%|█████████▌| 448/469 [00:17<00:00, 25.96it/s]
Testing:  96%|█████████▌| 451/469 [00:17<00:00, 26.19it/s]
Testing:  97%|█████████▋| 454/469 [00:18<00:00, 25.49it/s]
Testing:  97%|█████████▋| 457/469 [00:18<00:00, 26.03it/s]
Testing:  98%|█████████▊| 460/469 [00:18<00:00, 25.57it/s]
Testing:  99%|█████████▊| 463/469 [00:18<00:00, 25.84it/s]
Testing:  99%|█████████▉| 466/469 [00:18<00:00, 26.75it/s]--------------------------------------------------------------------------------
DATALOADER:0 TEST RESULTS
{'test_rmse': 0.5236741900444031}
--------------------------------------------------------------------------------

Testing: 100%|██████████| 469/469 [00:18<00:00, 25.20it/s]
  0%|          | 0/469 [02:56<?, ?it/s]
Global seed set to 50

['p_np'] False
2 1
iupac_vocab_size: 1491
training... 1491

  0%|          | 0/469 [00:00<?, ?it/s]Some weights of the model checkpoint at checkpoints/iupac were not used when initializing GPT2ForSequenceClassification: ['lm_head.weight']
- This IS expected if you are initializing GPT2ForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing GPT2ForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
GPU available: True, used: True
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]

  | Name        | Type                          | Params
--------------------------------------------------------------
0 | transformer | GPT2ForSequenceClassification | 7.1 M 
--------------------------------------------------------------
75.9 K    Trainable params
7.0 M     Non-trainable params
7.1 M     Total params
28.416    Total estimated model params size (MB)

Validation sanity check: 0it [00:00, ?it/s]
Validation sanity check:   0%|          | 0/2 [00:00<?, ?it/s]
                                                              Global seed set to 50


Training: 0it [00:00, ?it/s]
Training:   0%|          | 0/938 [00:00<?, ?it/s]
Epoch 0:   0%|          | 0/938 [00:00<?, ?it/s] 
Epoch 0:   0%|          | 1/938 [00:00<01:38,  9.51it/s]
Epoch 0:   0%|          | 1/938 [00:00<01:39,  9.46it/s, loss=3.44, v_num=16]
Epoch 0:   0%|          | 2/938 [00:00<01:26, 10.80it/s, loss=3.5, v_num=16] 
Epoch 0:   0%|          | 3/938 [00:00<01:16, 12.30it/s, loss=3.5, v_num=16]
Epoch 0:   0%|          | 3/938 [00:00<01:16, 12.27it/s, loss=3.43, v_num=16]
Epoch 0:   0%|          | 4/938 [00:00<01:12, 12.83it/s, loss=3.34, v_num=16]
Epoch 0:   1%|          | 5/938 [00:00<01:12, 12.86it/s, loss=3.34, v_num=16]
Epoch 0:   1%|          | 5/938 [00:00<01:12, 12.85it/s, loss=3.34, v_num=16]
Epoch 0:   1%|          | 6/938 [00:00<01:08, 13.59it/s, loss=3.39, v_num=16]
Epoch 0:   1%|          | 7/938 [00:00<01:13, 12.70it/s, loss=3.39, v_num=16]
Epoch 0:   1%|          | 7/938 [00:00<01:13, 12.69it/s, loss=3.42, v_num=16]
Epoch 0:   1%|          | 8/938 [00:00<01:12, 12.87it/s, loss=3.4, v_num=16] 
Epoch 0:   1%|          | 9/938 [00:00<01:10, 13.12it/s, loss=3.4, v_num=16]
Epoch 0:   1%|          | 9/938 [00:00<01:10, 13.11it/s, loss=3.43, v_num=16]
Epoch 0:   1%|          | 10/938 [00:00<01:10, 13.12it/s, loss=3.4, v_num=16]
Epoch 0:   1%|          | 11/938 [00:00<01:10, 13.08it/s, loss=3.4, v_num=16]
Epoch 0:   1%|          | 11/938 [00:00<01:10, 13.08it/s, loss=3.41, v_num=16]
Epoch 0:   1%|▏         | 12/938 [00:00<01:09, 13.28it/s, loss=3.4, v_num=16] 
Epoch 0:   1%|▏         | 13/938 [00:00<01:09, 13.39it/s, loss=3.4, v_num=16]
Epoch 0:   1%|▏         | 13/938 [00:00<01:09, 13.38it/s, loss=3.4, v_num=16]
Epoch 0:   1%|▏         | 14/938 [00:01<01:09, 13.38it/s, loss=3.37, v_num=16]
Epoch 0:   2%|▏         | 15/938 [00:01<01:08, 13.56it/s, loss=3.37, v_num=16]
Epoch 0:   2%|▏         | 15/938 [00:01<01:08, 13.55it/s, loss=3.38, v_num=16]
Epoch 0:   2%|▏         | 16/938 [00:01<01:07, 13.66it/s, loss=3.37, v_num=16]
Epoch 0:   2%|▏         | 17/938 [00:01<01:10, 13.10it/s, loss=3.37, v_num=16]
Epoch 0:   2%|▏         | 17/938 [00:01<01:10, 13.10it/s, loss=3.35, v_num=16]
Epoch 0:   2%|▏         | 18/938 [00:01<01:09, 13.20it/s, loss=3.33, v_num=16]
Epoch 0:   2%|▏         | 19/938 [00:01<01:09, 13.23it/s, loss=3.33, v_num=16]
Epoch 0:   2%|▏         | 19/938 [00:01<01:09, 13.23it/s, loss=3.34, v_num=16]
Epoch 0:   2%|▏         | 20/938 [00:01<01:09, 13.29it/s, loss=3.32, v_num=16]
Epoch 0:   2%|▏         | 21/938 [00:01<01:08, 13.33it/s, loss=3.32, v_num=16]
Epoch 0:   2%|▏         | 21/938 [00:01<01:08, 13.32it/s, loss=3.28, v_num=16]
Epoch 0:   2%|▏         | 22/938 [00:01<01:08, 13.44it/s, loss=3.21, v_num=16]
Epoch 0:   2%|▏         | 23/938 [00:01<01:07, 13.54it/s, loss=3.21, v_num=16]
Epoch 0:   2%|▏         | 23/938 [00:01<01:07, 13.54it/s, loss=3.17, v_num=16]
Epoch 0:   3%|▎         | 24/938 [00:01<01:07, 13.60it/s, loss=3.14, v_num=16]
Epoch 0:   3%|▎         | 25/938 [00:01<01:07, 13.57it/s, loss=3.14, v_num=16]
Epoch 0:   3%|▎         | 25/938 [00:01<01:07, 13.56it/s, loss=3.08, v_num=16]
Epoch 0:   3%|▎         | 26/938 [00:01<01:06, 13.67it/s, loss=3, v_num=16]   
Epoch 0:   3%|▎         | 27/938 [00:01<01:07, 13.51it/s, loss=3, v_num=16]
Epoch 0:   3%|▎         | 27/938 [00:01<01:07, 13.50it/s, loss=2.94, v_num=16]
Epoch 0:   3%|▎         | 28/938 [00:02<01:07, 13.53it/s, loss=2.88, v_num=16]
Epoch 0:   3%|▎         | 29/938 [00:02<01:06, 13.63it/s, loss=2.88, v_num=16]
Epoch 0:   3%|▎         | 29/938 [00:02<01:06, 13.63it/s, loss=2.79, v_num=16]
Epoch 0:   3%|▎         | 30/938 [00:02<01:06, 13.59it/s, loss=2.73, v_num=16]
Epoch 0:   3%|▎         | 31/938 [00:02<01:06, 13.67it/s, loss=2.73, v_num=16]
Epoch 0:   3%|▎         | 31/938 [00:02<01:06, 13.66it/s, loss=2.64, v_num=16]
Epoch 0:   3%|▎         | 32/938 [00:02<01:06, 13.66it/s, loss=2.58, v_num=16]
Epoch 0:   4%|▎         | 33/938 [00:02<01:05, 13.74it/s, loss=2.58, v_num=16]
Epoch 0:   4%|▎         | 33/938 [00:02<01:05, 13.74it/s, loss=2.5, v_num=16] 
Epoch 0:   4%|▎         | 34/938 [00:02<01:05, 13.71it/s, loss=2.43, v_num=16]
Epoch 0:   4%|▎         | 35/938 [00:02<01:05, 13.79it/s, loss=2.43, v_num=16]
Epoch 0:   4%|▎         | 35/938 [00:02<01:05, 13.79it/s, loss=2.33, v_num=16]
Epoch 0:   4%|▍         | 36/938 [00:02<01:05, 13.81it/s, loss=2.25, v_num=16]
Epoch 0:   4%|▍         | 37/938 [00:02<01:04, 13.89it/s, loss=2.25, v_num=16]
Epoch 0:   4%|▍         | 37/938 [00:02<01:04, 13.89it/s, loss=2.19, v_num=16]
Epoch 0:   4%|▍         | 38/938 [00:02<01:04, 13.99it/s, loss=2.12, v_num=16]
Epoch 0:   4%|▍         | 39/938 [00:02<01:04, 13.98it/s, loss=2.12, v_num=16]
Epoch 0:   4%|▍         | 39/938 [00:02<01:04, 13.98it/s, loss=2.03, v_num=16]
Epoch 0:   4%|▍         | 40/938 [00:02<01:04, 14.03it/s, loss=1.98, v_num=16]
Epoch 0:   4%|▍         | 41/938 [00:02<01:03, 14.05it/s, loss=1.98, v_num=16]
Epoch 0:   4%|▍         | 41/938 [00:02<01:03, 14.05it/s, loss=1.94, v_num=16]
Epoch 0:   4%|▍         | 42/938 [00:02<01:03, 14.03it/s, loss=1.9, v_num=16] 
Epoch 0:   5%|▍         | 43/938 [00:03<01:03, 14.09it/s, loss=1.9, v_num=16]
Epoch 0:   5%|▍         | 43/938 [00:03<01:03, 14.09it/s, loss=1.86, v_num=16]
Epoch 0:   5%|▍         | 44/938 [00:03<01:03, 14.08it/s, loss=1.85, v_num=16]
Epoch 0:   5%|▍         | 45/938 [00:03<01:03, 14.05it/s, loss=1.85, v_num=16]
Epoch 0:   5%|▍         | 45/938 [00:03<01:03, 14.05it/s, loss=1.82, v_num=16]
Epoch 0:   5%|▍         | 46/938 [00:03<01:03, 14.10it/s, loss=1.8, v_num=16] 
Epoch 0:   5%|▌         | 47/938 [00:03<01:03, 14.06it/s, loss=1.8, v_num=16]
Epoch 0:   5%|▌         | 47/938 [00:03<01:03, 14.05it/s, loss=1.78, v_num=16]
Epoch 0:   5%|▌         | 48/938 [00:03<01:03, 14.09it/s, loss=1.75, v_num=16]
Epoch 0:   5%|▌         | 49/938 [00:03<01:03, 14.06it/s, loss=1.75, v_num=16]
Epoch 0:   5%|▌         | 49/938 [00:03<01:03, 14.06it/s, loss=1.74, v_num=16]
Epoch 0:   5%|▌         | 50/938 [00:03<01:03, 14.03it/s, loss=1.75, v_num=16]
Epoch 0:   5%|▌         | 51/938 [00:03<01:03, 14.00it/s, loss=1.75, v_num=16]
Epoch 0:   5%|▌         | 51/938 [00:03<01:03, 13.99it/s, loss=1.72, v_num=16]
Epoch 0:   6%|▌         | 52/938 [00:03<01:03, 14.02it/s, loss=1.71, v_num=16]
Epoch 0:   6%|▌         | 53/938 [00:03<01:03, 14.04it/s, loss=1.71, v_num=16]
Epoch 0:   6%|▌         | 53/938 [00:03<01:03, 14.04it/s, loss=1.72, v_num=16]
Epoch 0:   6%|▌         | 54/938 [00:03<01:03, 14.01it/s, loss=1.72, v_num=16]
Epoch 0:   6%|▌         | 55/938 [00:03<01:03, 13.99it/s, loss=1.72, v_num=16]
Epoch 0:   6%|▌         | 55/938 [00:03<01:03, 13.99it/s, loss=1.71, v_num=16]
Epoch 0:   6%|▌         | 56/938 [00:04<01:03, 13.97it/s, loss=1.72, v_num=16]
Epoch 0:   6%|▌         | 57/938 [00:04<01:03, 13.98it/s, loss=1.72, v_num=16]
Epoch 0:   6%|▌         | 57/938 [00:04<01:03, 13.97it/s, loss=1.73, v_num=16]
Epoch 0:   6%|▌         | 58/938 [00:04<01:02, 14.00it/s, loss=1.74, v_num=16]
Epoch 0:   6%|▋         | 59/938 [00:04<01:02, 13.96it/s, loss=1.74, v_num=16]
Epoch 0:   6%|▋         | 59/938 [00:04<01:02, 13.96it/s, loss=1.73, v_num=16]
Epoch 0:   6%|▋         | 60/938 [00:04<01:02, 13.94it/s, loss=1.73, v_num=16]
Epoch 0:   7%|▋         | 61/938 [00:04<01:02, 13.99it/s, loss=1.73, v_num=16]
Epoch 0:   7%|▋         | 61/938 [00:04<01:02, 13.99it/s, loss=1.71, v_num=16]
Epoch 0:   7%|▋         | 62/938 [00:04<01:02, 13.95it/s, loss=1.73, v_num=16]
Epoch 0:   7%|▋         | 63/938 [00:04<01:02, 13.96it/s, loss=1.73, v_num=16]
Epoch 0:   7%|▋         | 63/938 [00:04<01:02, 13.96it/s, loss=1.73, v_num=16]
Epoch 0:   7%|▋         | 64/938 [00:04<01:02, 13.93it/s, loss=1.7, v_num=16] 
Epoch 0:   7%|▋         | 65/938 [00:04<01:02, 13.94it/s, loss=1.7, v_num=16]
Epoch 0:   7%|▋         | 65/938 [00:04<01:02, 13.94it/s, loss=1.68, v_num=16]
Epoch 0:   7%|▋         | 66/938 [00:04<01:02, 13.95it/s, loss=1.71, v_num=16]
Epoch 0:   7%|▋         | 67/938 [00:04<01:02, 13.92it/s, loss=1.71, v_num=16]
Epoch 0:   7%|▋         | 67/938 [00:04<01:02, 13.92it/s, loss=1.7, v_num=16] 
Epoch 0:   7%|▋         | 68/938 [00:04<01:02, 13.94it/s, loss=1.71, v_num=16]
Epoch 0:   7%|▋         | 69/938 [00:04<01:02, 13.91it/s, loss=1.71, v_num=16]
Epoch 0:   7%|▋         | 69/938 [00:04<01:02, 13.90it/s, loss=1.7, v_num=16] 
Epoch 0:   7%|▋         | 70/938 [00:05<01:02, 13.91it/s, loss=1.67, v_num=16]
Epoch 0:   8%|▊         | 71/938 [00:05<01:02, 13.95it/s, loss=1.67, v_num=16]
Epoch 0:   8%|▊         | 71/938 [00:05<01:02, 13.94it/s, loss=1.68, v_num=16]
Epoch 0:   8%|▊         | 72/938 [00:05<01:02, 13.96it/s, loss=1.67, v_num=16]
Epoch 0:   8%|▊         | 73/938 [00:05<01:01, 13.98it/s, loss=1.67, v_num=16]
Epoch 0:   8%|▊         | 73/938 [00:05<01:01, 13.98it/s, loss=1.68, v_num=16]
Epoch 0:   8%|▊         | 74/938 [00:05<01:01, 14.02it/s, loss=1.68, v_num=16]
Epoch 0:   8%|▊         | 75/938 [00:05<01:01, 14.02it/s, loss=1.68, v_num=16]
Epoch 0:   8%|▊         | 75/938 [00:05<01:01, 14.02it/s, loss=1.68, v_num=16]
Epoch 0:   8%|▊         | 76/938 [00:05<01:01, 14.03it/s, loss=1.67, v_num=16]
Epoch 0:   8%|▊         | 77/938 [00:05<01:01, 14.03it/s, loss=1.67, v_num=16]
Epoch 0:   8%|▊         | 77/938 [00:05<01:01, 14.03it/s, loss=1.66, v_num=16]
Epoch 0:   8%|▊         | 78/938 [00:05<01:01, 14.02it/s, loss=1.65, v_num=16]
Epoch 0:   8%|▊         | 79/938 [00:05<01:01, 14.02it/s, loss=1.65, v_num=16]
Epoch 0:   8%|▊         | 79/938 [00:05<01:01, 14.02it/s, loss=1.64, v_num=16]
Epoch 0:   9%|▊         | 80/938 [00:05<01:01, 14.00it/s, loss=1.65, v_num=16]
Epoch 0:   9%|▊         | 81/938 [00:05<01:00, 14.05it/s, loss=1.65, v_num=16]
Epoch 0:   9%|▊         | 81/938 [00:05<01:00, 14.05it/s, loss=1.65, v_num=16]
Epoch 0:   9%|▊         | 82/938 [00:05<01:00, 14.04it/s, loss=1.64, v_num=16]
Epoch 0:   9%|▉         | 83/938 [00:05<01:00, 14.04it/s, loss=1.64, v_num=16]
Epoch 0:   9%|▉         | 83/938 [00:05<01:00, 14.04it/s, loss=1.65, v_num=16]
Epoch 0:   9%|▉         | 84/938 [00:05<01:00, 14.02it/s, loss=1.64, v_num=16]
Epoch 0:   9%|▉         | 85/938 [00:06<01:00, 14.04it/s, loss=1.64, v_num=16]
Epoch 0:   9%|▉         | 85/938 [00:06<01:00, 14.03it/s, loss=1.64, v_num=16]
Epoch 0:   9%|▉         | 86/938 [00:06<01:00, 14.02it/s, loss=1.62, v_num=16]
Epoch 0:   9%|▉         | 87/938 [00:06<01:00, 14.00it/s, loss=1.62, v_num=16]
Epoch 0:   9%|▉         | 87/938 [00:06<01:00, 14.00it/s, loss=1.63, v_num=16]
Epoch 0:   9%|▉         | 88/938 [00:06<01:00, 14.02it/s, loss=1.63, v_num=16]
Epoch 0:   9%|▉         | 89/938 [00:06<01:00, 13.93it/s, loss=1.63, v_num=16]
Epoch 0:   9%|▉         | 89/938 [00:06<01:00, 13.93it/s, loss=1.62, v_num=16]
Epoch 0:  10%|▉         | 90/938 [00:06<01:00, 13.94it/s, loss=1.64, v_num=16]
Epoch 0:  10%|▉         | 91/938 [00:06<01:00, 13.96it/s, loss=1.64, v_num=16]
Epoch 0:  10%|▉         | 91/938 [00:06<01:00, 13.96it/s, loss=1.63, v_num=16]
Epoch 0:  10%|▉         | 92/938 [00:06<01:00, 13.97it/s, loss=1.62, v_num=16]
Epoch 0:  10%|▉         | 93/938 [00:06<01:00, 13.97it/s, loss=1.62, v_num=16]
Epoch 0:  10%|▉         | 93/938 [00:06<01:00, 13.97it/s, loss=1.62, v_num=16]
Epoch 0:  10%|█         | 94/938 [00:06<01:00, 13.98it/s, loss=1.63, v_num=16]
Epoch 0:  10%|█         | 95/938 [00:06<01:00, 14.00it/s, loss=1.63, v_num=16]
Epoch 0:  10%|█         | 95/938 [00:06<01:00, 14.00it/s, loss=1.64, v_num=16]
Epoch 0:  10%|█         | 96/938 [00:06<01:00, 14.02it/s, loss=1.65, v_num=16]
Epoch 0:  10%|█         | 97/938 [00:06<00:59, 14.03it/s, loss=1.65, v_num=16]
Epoch 0:  10%|█         | 97/938 [00:06<00:59, 14.03it/s, loss=1.64, v_num=16]
Epoch 0:  10%|█         | 98/938 [00:06<00:59, 14.06it/s, loss=1.65, v_num=16]
Epoch 0:  11%|█         | 99/938 [00:07<00:59, 14.00it/s, loss=1.65, v_num=16]
Epoch 0:  11%|█         | 99/938 [00:07<00:59, 14.00it/s, loss=1.65, v_num=16]
Epoch 0:  11%|█         | 100/938 [00:07<00:59, 14.02it/s, loss=1.64, v_num=16]
Epoch 0:  11%|█         | 101/938 [00:07<00:59, 14.05it/s, loss=1.64, v_num=16]
Epoch 0:  11%|█         | 101/938 [00:07<00:59, 14.05it/s, loss=1.63, v_num=16]
Epoch 0:  11%|█         | 102/938 [00:07<00:59, 14.04it/s, loss=1.64, v_num=16]
Epoch 0:  11%|█         | 103/938 [00:07<00:59, 14.06it/s, loss=1.64, v_num=16]
Epoch 0:  11%|█         | 103/938 [00:07<00:59, 14.06it/s, loss=1.64, v_num=16]
Epoch 0:  11%|█         | 104/938 [00:07<00:59, 14.07it/s, loss=1.63, v_num=16]
Epoch 0:  11%|█         | 105/938 [00:07<00:59, 14.07it/s, loss=1.63, v_num=16]
Epoch 0:  11%|█         | 105/938 [00:07<00:59, 14.07it/s, loss=1.62, v_num=16]
Epoch 0:  11%|█▏        | 106/938 [00:07<00:59, 14.06it/s, loss=1.61, v_num=16]
Epoch 0:  11%|█▏        | 107/938 [00:07<00:59, 14.08it/s, loss=1.61, v_num=16]
Epoch 0:  11%|█▏        | 107/938 [00:07<00:59, 14.08it/s, loss=1.61, v_num=16]
Epoch 0:  12%|█▏        | 108/938 [00:07<00:58, 14.08it/s, loss=1.6, v_num=16] 
Epoch 0:  12%|█▏        | 109/938 [00:07<00:58, 14.09it/s, loss=1.6, v_num=16]
Epoch 0:  12%|█▏        | 109/938 [00:07<00:58, 14.09it/s, loss=1.61, v_num=16]
Epoch 0:  12%|█▏        | 110/938 [00:07<00:58, 14.10it/s, loss=1.61, v_num=16]
Epoch 0:  12%|█▏        | 111/938 [00:07<00:58, 14.12it/s, loss=1.61, v_num=16]
Epoch 0:  12%|█▏        | 111/938 [00:07<00:58, 14.11it/s, loss=1.62, v_num=16]
Epoch 0:  12%|█▏        | 112/938 [00:07<00:58, 14.11it/s, loss=1.63, v_num=16]
Epoch 0:  12%|█▏        | 113/938 [00:08<00:58, 14.12it/s, loss=1.63, v_num=16]
Epoch 0:  12%|█▏        | 113/938 [00:08<00:58, 14.11it/s, loss=1.61, v_num=16]
Epoch 0:  12%|█▏        | 114/938 [00:08<00:58, 14.11it/s, loss=1.61, v_num=16]
Epoch 0:  12%|█▏        | 115/938 [00:08<00:58, 14.08it/s, loss=1.61, v_num=16]
Epoch 0:  12%|█▏        | 115/938 [00:08<00:58, 14.08it/s, loss=1.63, v_num=16]
Epoch 0:  12%|█▏        | 116/938 [00:08<00:58, 14.07it/s, loss=1.62, v_num=16]
Epoch 0:  12%|█▏        | 117/938 [00:08<00:58, 14.07it/s, loss=1.62, v_num=16]
Epoch 0:  12%|█▏        | 117/938 [00:08<00:58, 14.07it/s, loss=1.62, v_num=16]
Epoch 0:  13%|█▎        | 118/938 [00:08<00:58, 14.05it/s, loss=1.61, v_num=16]
Epoch 0:  13%|█▎        | 119/938 [00:08<00:58, 14.05it/s, loss=1.61, v_num=16]
Epoch 0:  13%|█▎        | 119/938 [00:08<00:58, 14.05it/s, loss=1.62, v_num=16]
Epoch 0:  13%|█▎        | 120/938 [00:08<00:58, 14.05it/s, loss=1.61, v_num=16]
Epoch 0:  13%|█▎        | 121/938 [00:08<00:58, 14.06it/s, loss=1.61, v_num=16]
Epoch 0:  13%|█▎        | 121/938 [00:08<00:58, 14.06it/s, loss=1.62, v_num=16]
Epoch 0:  13%|█▎        | 122/938 [00:08<00:57, 14.08it/s, loss=1.6, v_num=16] 
Epoch 0:  13%|█▎        | 123/938 [00:08<00:57, 14.10it/s, loss=1.6, v_num=16]
Epoch 0:  13%|█▎        | 123/938 [00:08<00:57, 14.09it/s, loss=1.61, v_num=16]
Epoch 0:  13%|█▎        | 124/938 [00:08<00:57, 14.10it/s, loss=1.61, v_num=16]
Epoch 0:  13%|█▎        | 125/938 [00:08<00:57, 14.10it/s, loss=1.61, v_num=16]
Epoch 0:  13%|█▎        | 125/938 [00:08<00:57, 14.10it/s, loss=1.59, v_num=16]
Epoch 0:  13%|█▎        | 126/938 [00:08<00:57, 14.10it/s, loss=1.59, v_num=16]
Epoch 0:  14%|█▎        | 127/938 [00:08<00:57, 14.11it/s, loss=1.59, v_num=16]
Epoch 0:  14%|█▎        | 127/938 [00:08<00:57, 14.11it/s, loss=1.58, v_num=16]
Epoch 0:  14%|█▎        | 128/938 [00:09<00:57, 14.12it/s, loss=1.58, v_num=16]
Epoch 0:  14%|█▍        | 129/938 [00:09<00:57, 14.12it/s, loss=1.58, v_num=16]
Epoch 0:  14%|█▍        | 129/938 [00:09<00:57, 14.12it/s, loss=1.59, v_num=16]
Epoch 0:  14%|█▍        | 130/938 [00:09<00:57, 14.12it/s, loss=1.61, v_num=16]
Epoch 0:  14%|█▍        | 131/938 [00:09<00:57, 14.13it/s, loss=1.61, v_num=16]
Epoch 0:  14%|█▍        | 131/938 [00:09<00:57, 14.13it/s, loss=1.6, v_num=16] 
Epoch 0:  14%|█▍        | 132/938 [00:09<00:56, 14.15it/s, loss=1.58, v_num=16]
Epoch 0:  14%|█▍        | 133/938 [00:09<00:56, 14.15it/s, loss=1.58, v_num=16]
Epoch 0:  14%|█▍        | 133/938 [00:09<00:56, 14.15it/s, loss=1.59, v_num=16]
Epoch 0:  14%|█▍        | 134/938 [00:09<00:56, 14.15it/s, loss=1.58, v_num=16]
Epoch 0:  14%|█▍        | 135/938 [00:09<00:56, 14.14it/s, loss=1.58, v_num=16]
Epoch 0:  14%|█▍        | 135/938 [00:09<00:56, 14.14it/s, loss=1.56, v_num=16]
Epoch 0:  14%|█▍        | 136/938 [00:09<00:56, 14.16it/s, loss=1.54, v_num=16]
Epoch 0:  15%|█▍        | 137/938 [00:09<00:56, 14.16it/s, loss=1.54, v_num=16]
Epoch 0:  15%|█▍        | 137/938 [00:09<00:56, 14.16it/s, loss=1.52, v_num=16]
Epoch 0:  15%|█▍        | 138/938 [00:09<00:56, 14.17it/s, loss=1.53, v_num=16]
Epoch 0:  15%|█▍        | 139/938 [00:09<00:56, 14.17it/s, loss=1.53, v_num=16]
Epoch 0:  15%|█▍        | 139/938 [00:09<00:56, 14.17it/s, loss=1.5, v_num=16] 
Epoch 0:  15%|█▍        | 140/938 [00:09<00:56, 14.16it/s, loss=1.49, v_num=16]
Epoch 0:  15%|█▌        | 141/938 [00:09<00:56, 14.12it/s, loss=1.49, v_num=16]
Epoch 0:  15%|█▌        | 141/938 [00:09<00:56, 14.12it/s, loss=1.48, v_num=16]
Epoch 0:  15%|█▌        | 142/938 [00:10<00:56, 14.12it/s, loss=1.47, v_num=16]
Epoch 0:  15%|█▌        | 143/938 [00:10<00:56, 14.12it/s, loss=1.47, v_num=16]
Epoch 0:  15%|█▌        | 143/938 [00:10<00:56, 14.12it/s, loss=1.44, v_num=16]
Epoch 0:  15%|█▌        | 144/938 [00:10<00:56, 14.11it/s, loss=1.42, v_num=16]
Epoch 0:  15%|█▌        | 145/938 [00:10<00:56, 14.11it/s, loss=1.42, v_num=16]
Epoch 0:  15%|█▌        | 145/938 [00:10<00:56, 14.11it/s, loss=1.41, v_num=16]
Epoch 0:  16%|█▌        | 146/938 [00:10<00:56, 14.12it/s, loss=1.4, v_num=16] 
Epoch 0:  16%|█▌        | 147/938 [00:10<00:55, 14.13it/s, loss=1.4, v_num=16]
Epoch 0:  16%|█▌        | 147/938 [00:10<00:55, 14.13it/s, loss=1.39, v_num=16]
Epoch 0:  16%|█▌        | 148/938 [00:10<00:55, 14.13it/s, loss=1.36, v_num=16]
Epoch 0:  16%|█▌        | 149/938 [00:10<00:55, 14.14it/s, loss=1.36, v_num=16]
Epoch 0:  16%|█▌        | 149/938 [00:10<00:55, 14.14it/s, loss=1.31, v_num=16]
Epoch 0:  16%|█▌        | 150/938 [00:10<00:55, 14.15it/s, loss=1.28, v_num=16]
Epoch 0:  16%|█▌        | 151/938 [00:10<00:55, 14.15it/s, loss=1.28, v_num=16]
Epoch 0:  16%|█▌        | 151/938 [00:10<00:55, 14.15it/s, loss=1.26, v_num=16]
Epoch 0:  16%|█▌        | 152/938 [00:10<00:55, 14.13it/s, loss=1.25, v_num=16]
Epoch 0:  16%|█▋        | 153/938 [00:10<00:55, 14.15it/s, loss=1.25, v_num=16]
Epoch 0:  16%|█▋        | 153/938 [00:10<00:55, 14.15it/s, loss=1.22, v_num=16]
Epoch 0:  16%|█▋        | 154/938 [00:10<00:55, 14.15it/s, loss=1.2, v_num=16] 
Epoch 0:  17%|█▋        | 155/938 [00:10<00:55, 14.16it/s, loss=1.2, v_num=16]
Epoch 0:  17%|█▋        | 155/938 [00:10<00:55, 14.16it/s, loss=1.17, v_num=16]
Epoch 0:  17%|█▋        | 156/938 [00:11<00:55, 14.17it/s, loss=1.16, v_num=16]
Epoch 0:  17%|█▋        | 157/938 [00:11<00:55, 14.18it/s, loss=1.16, v_num=16]
Epoch 0:  17%|█▋        | 157/938 [00:11<00:55, 14.18it/s, loss=1.15, v_num=16]
Epoch 0:  17%|█▋        | 158/938 [00:11<00:55, 14.17it/s, loss=1.12, v_num=16]
Epoch 0:  17%|█▋        | 159/938 [00:11<00:54, 14.17it/s, loss=1.12, v_num=16]
Epoch 0:  17%|█▋        | 159/938 [00:11<00:54, 14.16it/s, loss=1.13, v_num=16]
Epoch 0:  17%|█▋        | 160/938 [00:11<00:54, 14.17it/s, loss=1.11, v_num=16]
Epoch 0:  17%|█▋        | 161/938 [00:11<00:54, 14.19it/s, loss=1.11, v_num=16]
Epoch 0:  17%|█▋        | 161/938 [00:11<00:54, 14.18it/s, loss=1.1, v_num=16] 
Epoch 0:  17%|█▋        | 162/938 [00:11<00:54, 14.20it/s, loss=1.1, v_num=16]
Epoch 0:  17%|█▋        | 163/938 [00:11<00:54, 14.21it/s, loss=1.1, v_num=16]
Epoch 0:  17%|█▋        | 163/938 [00:11<00:54, 14.21it/s, loss=1.1, v_num=16]
Epoch 0:  17%|█▋        | 164/938 [00:11<00:54, 14.21it/s, loss=1.09, v_num=16]
Epoch 0:  18%|█▊        | 165/938 [00:11<00:54, 14.21it/s, loss=1.09, v_num=16]
Epoch 0:  18%|█▊        | 165/938 [00:11<00:54, 14.21it/s, loss=1.09, v_num=16]
Epoch 0:  18%|█▊        | 166/938 [00:11<00:54, 14.20it/s, loss=1.09, v_num=16]
Epoch 0:  18%|█▊        | 167/938 [00:11<00:54, 14.21it/s, loss=1.09, v_num=16]
Epoch 0:  18%|█▊        | 167/938 [00:11<00:54, 14.21it/s, loss=1.08, v_num=16]
Epoch 0:  18%|█▊        | 168/938 [00:11<00:54, 14.22it/s, loss=1.08, v_num=16]
Epoch 0:  18%|█▊        | 169/938 [00:11<00:54, 14.23it/s, loss=1.08, v_num=16]
Epoch 0:  18%|█▊        | 169/938 [00:11<00:54, 14.23it/s, loss=1.08, v_num=16]
Epoch 0:  18%|█▊        | 170/938 [00:11<00:53, 14.24it/s, loss=1.07, v_num=16]
Epoch 0:  18%|█▊        | 171/938 [00:12<00:53, 14.23it/s, loss=1.07, v_num=16]
Epoch 0:  18%|█▊        | 171/938 [00:12<00:53, 14.23it/s, loss=1.06, v_num=16]
Epoch 0:  18%|█▊        | 172/938 [00:12<00:53, 14.23it/s, loss=1.07, v_num=16]
Epoch 0:  18%|█▊        | 173/938 [00:12<00:53, 14.23it/s, loss=1.07, v_num=16]
Epoch 0:  18%|█▊        | 173/938 [00:12<00:53, 14.23it/s, loss=1.07, v_num=16]
Epoch 0:  19%|█▊        | 174/938 [00:12<00:53, 14.24it/s, loss=1.06, v_num=16]
Epoch 0:  19%|█▊        | 175/938 [00:12<00:53, 14.25it/s, loss=1.06, v_num=16]
Epoch 0:  19%|█▊        | 175/938 [00:12<00:53, 14.25it/s, loss=1.06, v_num=16]
Epoch 0:  19%|█▉        | 176/938 [00:12<00:53, 14.25it/s, loss=1.06, v_num=16]
Epoch 0:  19%|█▉        | 177/938 [00:12<00:53, 14.26it/s, loss=1.06, v_num=16]
Epoch 0:  19%|█▉        | 177/938 [00:12<00:53, 14.26it/s, loss=1.07, v_num=16]
Epoch 0:  19%|█▉        | 178/938 [00:12<00:53, 14.27it/s, loss=1.06, v_num=16]
Epoch 0:  19%|█▉        | 179/938 [00:12<00:53, 14.27it/s, loss=1.06, v_num=16]
Epoch 0:  19%|█▉        | 179/938 [00:12<00:53, 14.27it/s, loss=1.05, v_num=16]
Epoch 0:  19%|█▉        | 180/938 [00:12<00:53, 14.28it/s, loss=1.05, v_num=16]
Epoch 0:  19%|█▉        | 181/938 [00:12<00:52, 14.28it/s, loss=1.05, v_num=16]
Epoch 0:  19%|█▉        | 181/938 [00:12<00:52, 14.28it/s, loss=1.03, v_num=16]
Epoch 0:  19%|█▉        | 182/938 [00:12<00:52, 14.29it/s, loss=1.02, v_num=16]
Epoch 0:  20%|█▉        | 183/938 [00:12<00:52, 14.28it/s, loss=1.02, v_num=16]
Epoch 0:  20%|█▉        | 183/938 [00:12<00:52, 14.28it/s, loss=1.03, v_num=16]
Epoch 0:  20%|█▉        | 184/938 [00:12<00:52, 14.27it/s, loss=1.02, v_num=16]
Epoch 0:  20%|█▉        | 185/938 [00:12<00:52, 14.28it/s, loss=1.02, v_num=16]
Epoch 0:  20%|█▉        | 185/938 [00:12<00:52, 14.28it/s, loss=1.02, v_num=16]
Epoch 0:  20%|█▉        | 186/938 [00:13<00:52, 14.27it/s, loss=0.999, v_num=16]
Epoch 0:  20%|█▉        | 187/938 [00:13<00:52, 14.26it/s, loss=0.999, v_num=16]
Epoch 0:  20%|█▉        | 187/938 [00:13<00:52, 14.26it/s, loss=0.993, v_num=16]
Epoch 0:  20%|██        | 188/938 [00:13<00:52, 14.26it/s, loss=0.987, v_num=16]
Epoch 0:  20%|██        | 189/938 [00:13<00:52, 14.28it/s, loss=0.987, v_num=16]
Epoch 0:  20%|██        | 189/938 [00:13<00:52, 14.28it/s, loss=0.975, v_num=16]
Epoch 0:  20%|██        | 190/938 [00:13<00:52, 14.28it/s, loss=0.981, v_num=16]
Epoch 0:  20%|██        | 191/938 [00:13<00:52, 14.27it/s, loss=0.981, v_num=16]
Epoch 0:  20%|██        | 191/938 [00:13<00:52, 14.27it/s, loss=0.979, v_num=16]
Epoch 0:  20%|██        | 192/938 [00:13<00:52, 14.28it/s, loss=0.961, v_num=16]
Epoch 0:  21%|██        | 193/938 [00:13<00:52, 14.28it/s, loss=0.961, v_num=16]
Epoch 0:  21%|██        | 193/938 [00:13<00:52, 14.28it/s, loss=0.955, v_num=16]
Epoch 0:  21%|██        | 194/938 [00:13<00:52, 14.29it/s, loss=0.955, v_num=16]
Epoch 0:  21%|██        | 195/938 [00:13<00:51, 14.30it/s, loss=0.955, v_num=16]
Epoch 0:  21%|██        | 195/938 [00:13<00:51, 14.30it/s, loss=0.955, v_num=16]
Epoch 0:  21%|██        | 196/938 [00:13<00:51, 14.30it/s, loss=0.95, v_num=16] 
Epoch 0:  21%|██        | 197/938 [00:13<00:51, 14.30it/s, loss=0.95, v_num=16]
Epoch 0:  21%|██        | 197/938 [00:13<00:51, 14.30it/s, loss=0.934, v_num=16]
Epoch 0:  21%|██        | 198/938 [00:13<00:51, 14.30it/s, loss=0.947, v_num=16]
Epoch 0:  21%|██        | 199/938 [00:13<00:51, 14.30it/s, loss=0.947, v_num=16]
Epoch 0:  21%|██        | 199/938 [00:13<00:51, 14.30it/s, loss=0.938, v_num=16]
Epoch 0:  21%|██▏       | 200/938 [00:13<00:51, 14.31it/s, loss=0.942, v_num=16]
Epoch 0:  21%|██▏       | 201/938 [00:14<00:51, 14.31it/s, loss=0.942, v_num=16]
Epoch 0:  21%|██▏       | 201/938 [00:14<00:51, 14.31it/s, loss=0.943, v_num=16]
Epoch 0:  22%|██▏       | 202/938 [00:14<00:51, 14.31it/s, loss=0.955, v_num=16]
Epoch 0:  22%|██▏       | 203/938 [00:14<00:51, 14.31it/s, loss=0.955, v_num=16]
Epoch 0:  22%|██▏       | 203/938 [00:14<00:51, 14.31it/s, loss=0.958, v_num=16]
Epoch 0:  22%|██▏       | 204/938 [00:14<00:51, 14.31it/s, loss=0.967, v_num=16]
Epoch 0:  22%|██▏       | 205/938 [00:14<00:51, 14.31it/s, loss=0.967, v_num=16]
Epoch 0:  22%|██▏       | 205/938 [00:14<00:51, 14.31it/s, loss=0.966, v_num=16]
Epoch 0:  22%|██▏       | 206/938 [00:14<00:51, 14.32it/s, loss=0.97, v_num=16] 
Epoch 0:  22%|██▏       | 207/938 [00:14<00:51, 14.31it/s, loss=0.97, v_num=16]
Epoch 0:  22%|██▏       | 207/938 [00:14<00:51, 14.31it/s, loss=0.978, v_num=16]
Epoch 0:  22%|██▏       | 208/938 [00:14<00:51, 14.30it/s, loss=0.972, v_num=16]
Epoch 0:  22%|██▏       | 209/938 [00:14<00:50, 14.31it/s, loss=0.972, v_num=16]
Epoch 0:  22%|██▏       | 209/938 [00:14<00:50, 14.31it/s, loss=0.987, v_num=16]
Epoch 0:  22%|██▏       | 210/938 [00:14<00:50, 14.31it/s, loss=0.98, v_num=16] 
Epoch 0:  22%|██▏       | 211/938 [00:14<00:50, 14.32it/s, loss=0.98, v_num=16]
Epoch 0:  22%|██▏       | 211/938 [00:14<00:50, 14.32it/s, loss=0.986, v_num=16]
Epoch 0:  23%|██▎       | 212/938 [00:14<00:50, 14.32it/s, loss=0.997, v_num=16]
Epoch 0:  23%|██▎       | 213/938 [00:14<00:50, 14.32it/s, loss=0.997, v_num=16]
Epoch 0:  23%|██▎       | 213/938 [00:14<00:50, 14.32it/s, loss=0.992, v_num=16]
Epoch 0:  23%|██▎       | 214/938 [00:14<00:50, 14.33it/s, loss=0.988, v_num=16]
Epoch 0:  23%|██▎       | 215/938 [00:15<00:50, 14.33it/s, loss=0.988, v_num=16]
Epoch 0:  23%|██▎       | 215/938 [00:15<00:50, 14.32it/s, loss=0.987, v_num=16]
Epoch 0:  23%|██▎       | 216/938 [00:15<00:50, 14.33it/s, loss=0.997, v_num=16]
Epoch 0:  23%|██▎       | 217/938 [00:15<00:50, 14.34it/s, loss=0.997, v_num=16]
Epoch 0:  23%|██▎       | 217/938 [00:15<00:50, 14.33it/s, loss=1, v_num=16]    
Epoch 0:  23%|██▎       | 218/938 [00:15<00:50, 14.34it/s, loss=0.992, v_num=16]
Epoch 0:  23%|██▎       | 219/938 [00:15<00:50, 14.34it/s, loss=0.992, v_num=16]
Epoch 0:  23%|██▎       | 219/938 [00:15<00:50, 14.34it/s, loss=0.992, v_num=16]
Epoch 0:  23%|██▎       | 220/938 [00:15<00:50, 14.32it/s, loss=0.986, v_num=16]
Epoch 0:  24%|██▎       | 221/938 [00:15<00:50, 14.33it/s, loss=0.986, v_num=16]
Epoch 0:  24%|██▎       | 221/938 [00:15<00:50, 14.33it/s, loss=0.986, v_num=16]
Epoch 0:  24%|██▎       | 222/938 [00:15<00:50, 14.29it/s, loss=0.974, v_num=16]
Epoch 0:  24%|██▍       | 223/938 [00:15<00:50, 14.29it/s, loss=0.974, v_num=16]
Epoch 0:  24%|██▍       | 223/938 [00:15<00:50, 14.29it/s, loss=0.977, v_num=16]
Epoch 0:  24%|██▍       | 224/938 [00:15<00:49, 14.30it/s, loss=0.974, v_num=16]
Epoch 0:  24%|██▍       | 225/938 [00:15<00:49, 14.30it/s, loss=0.974, v_num=16]
Epoch 0:  24%|██▍       | 225/938 [00:15<00:49, 14.30it/s, loss=0.969, v_num=16]
Epoch 0:  24%|██▍       | 226/938 [00:15<00:49, 14.30it/s, loss=0.97, v_num=16] 
Epoch 0:  24%|██▍       | 227/938 [00:15<00:49, 14.30it/s, loss=0.97, v_num=16]
Epoch 0:  24%|██▍       | 227/938 [00:15<00:49, 14.29it/s, loss=0.968, v_num=16]
Epoch 0:  24%|██▍       | 228/938 [00:15<00:49, 14.30it/s, loss=0.967, v_num=16]
Epoch 0:  24%|██▍       | 229/938 [00:16<00:49, 14.29it/s, loss=0.967, v_num=16]
Epoch 0:  24%|██▍       | 229/938 [00:16<00:49, 14.29it/s, loss=0.957, v_num=16]
Epoch 0:  25%|██▍       | 230/938 [00:16<00:49, 14.29it/s, loss=0.955, v_num=16]
Epoch 0:  25%|██▍       | 231/938 [00:16<00:49, 14.29it/s, loss=0.955, v_num=16]
Epoch 0:  25%|██▍       | 231/938 [00:16<00:49, 14.29it/s, loss=0.964, v_num=16]
Epoch 0:  25%|██▍       | 232/938 [00:16<00:49, 14.29it/s, loss=0.951, v_num=16]
Epoch 0:  25%|██▍       | 233/938 [00:16<00:49, 14.30it/s, loss=0.951, v_num=16]
Epoch 0:  25%|██▍       | 233/938 [00:16<00:49, 14.30it/s, loss=0.956, v_num=16]
Epoch 0:  25%|██▍       | 234/938 [00:16<00:49, 14.30it/s, loss=0.946, v_num=16]
Epoch 0:  25%|██▌       | 235/938 [00:16<00:49, 14.29it/s, loss=0.946, v_num=16]
Epoch 0:  25%|██▌       | 235/938 [00:16<00:49, 14.29it/s, loss=0.946, v_num=16]
Epoch 0:  25%|██▌       | 236/938 [00:16<00:49, 14.30it/s, loss=0.931, v_num=16]
Epoch 0:  25%|██▌       | 237/938 [00:16<00:49, 14.30it/s, loss=0.931, v_num=16]
Epoch 0:  25%|██▌       | 237/938 [00:16<00:49, 14.30it/s, loss=0.94, v_num=16] 
Epoch 0:  25%|██▌       | 238/938 [00:16<00:48, 14.31it/s, loss=0.945, v_num=16]
Epoch 0:  25%|██▌       | 239/938 [00:16<00:48, 14.31it/s, loss=0.945, v_num=16]
Epoch 0:  25%|██▌       | 239/938 [00:16<00:48, 14.31it/s, loss=0.949, v_num=16]
Epoch 0:  26%|██▌       | 240/938 [00:16<00:48, 14.31it/s, loss=0.949, v_num=16]
Epoch 0:  26%|██▌       | 241/938 [00:16<00:48, 14.32it/s, loss=0.949, v_num=16]
Epoch 0:  26%|██▌       | 241/938 [00:16<00:48, 14.32it/s, loss=0.938, v_num=16]
Epoch 0:  26%|██▌       | 242/938 [00:16<00:48, 14.32it/s, loss=0.936, v_num=16]
Epoch 0:  26%|██▌       | 243/938 [00:16<00:48, 14.31it/s, loss=0.936, v_num=16]
Epoch 0:  26%|██▌       | 243/938 [00:16<00:48, 14.31it/s, loss=0.925, v_num=16]
Epoch 0:  26%|██▌       | 244/938 [00:17<00:48, 14.31it/s, loss=0.926, v_num=16]
Epoch 0:  26%|██▌       | 245/938 [00:17<00:48, 14.31it/s, loss=0.926, v_num=16]
Epoch 0:  26%|██▌       | 245/938 [00:17<00:48, 14.31it/s, loss=0.92, v_num=16] 
Epoch 0:  26%|██▌       | 246/938 [00:17<00:48, 14.29it/s, loss=0.913, v_num=16]
Epoch 0:  26%|██▋       | 247/938 [00:17<00:48, 14.28it/s, loss=0.913, v_num=16]
Epoch 0:  26%|██▋       | 247/938 [00:17<00:48, 14.28it/s, loss=0.906, v_num=16]
Epoch 0:  26%|██▋       | 248/938 [00:17<00:48, 14.26it/s, loss=0.92, v_num=16] 
Epoch 0:  27%|██▋       | 249/938 [00:17<00:48, 14.26it/s, loss=0.92, v_num=16]
Epoch 0:  27%|██▋       | 249/938 [00:17<00:48, 14.26it/s, loss=0.918, v_num=16]
Epoch 0:  27%|██▋       | 250/938 [00:17<00:48, 14.26it/s, loss=0.916, v_num=16]
Epoch 0:  27%|██▋       | 251/938 [00:17<00:48, 14.26it/s, loss=0.916, v_num=16]
Epoch 0:  27%|██▋       | 251/938 [00:17<00:48, 14.26it/s, loss=0.899, v_num=16]
Epoch 0:  27%|██▋       | 252/938 [00:17<00:48, 14.26it/s, loss=0.903, v_num=16]
Epoch 0:  27%|██▋       | 253/938 [00:17<00:48, 14.26it/s, loss=0.903, v_num=16]
Epoch 0:  27%|██▋       | 253/938 [00:17<00:48, 14.26it/s, loss=0.9, v_num=16]  
Epoch 0:  27%|██▋       | 254/938 [00:17<00:47, 14.26it/s, loss=0.912, v_num=16]
Epoch 0:  27%|██▋       | 255/938 [00:17<00:47, 14.25it/s, loss=0.912, v_num=16]
Epoch 0:  27%|██▋       | 255/938 [00:17<00:47, 14.25it/s, loss=0.912, v_num=16]
Epoch 0:  27%|██▋       | 256/938 [00:17<00:47, 14.24it/s, loss=0.909, v_num=16]
Epoch 0:  27%|██▋       | 257/938 [00:18<00:47, 14.24it/s, loss=0.909, v_num=16]
Epoch 0:  27%|██▋       | 257/938 [00:18<00:47, 14.24it/s, loss=0.888, v_num=16]
Epoch 0:  28%|██▊       | 258/938 [00:18<00:47, 14.24it/s, loss=0.892, v_num=16]
Epoch 0:  28%|██▊       | 259/938 [00:18<00:47, 14.26it/s, loss=0.892, v_num=16]
Epoch 0:  28%|██▊       | 259/938 [00:18<00:47, 14.26it/s, loss=0.901, v_num=16]
Epoch 0:  28%|██▊       | 260/938 [00:18<00:47, 14.26it/s, loss=0.894, v_num=16]
Epoch 0:  28%|██▊       | 261/938 [00:18<00:47, 14.27it/s, loss=0.894, v_num=16]
Epoch 0:  28%|██▊       | 261/938 [00:18<00:47, 14.27it/s, loss=0.913, v_num=16]
Epoch 0:  28%|██▊       | 262/938 [00:18<00:47, 14.28it/s, loss=0.93, v_num=16] 
Epoch 0:  28%|██▊       | 263/938 [00:18<00:47, 14.27it/s, loss=0.93, v_num=16]
Epoch 0:  28%|██▊       | 263/938 [00:18<00:47, 14.27it/s, loss=0.924, v_num=16]
Epoch 0:  28%|██▊       | 264/938 [00:18<00:47, 14.28it/s, loss=0.92, v_num=16] 
Epoch 0:  28%|██▊       | 265/938 [00:18<00:47, 14.28it/s, loss=0.92, v_num=16]
Epoch 0:  28%|██▊       | 265/938 [00:18<00:47, 14.28it/s, loss=0.93, v_num=16]
Epoch 0:  28%|██▊       | 266/938 [00:18<00:47, 14.27it/s, loss=0.936, v_num=16]
Epoch 0:  28%|██▊       | 267/938 [00:18<00:47, 14.27it/s, loss=0.936, v_num=16]
Epoch 0:  28%|██▊       | 267/938 [00:18<00:47, 14.27it/s, loss=0.937, v_num=16]
Epoch 0:  29%|██▊       | 268/938 [00:18<00:46, 14.27it/s, loss=0.921, v_num=16]
Epoch 0:  29%|██▊       | 269/938 [00:18<00:46, 14.27it/s, loss=0.921, v_num=16]
Epoch 0:  29%|██▊       | 269/938 [00:18<00:46, 14.27it/s, loss=0.922, v_num=16]
Epoch 0:  29%|██▉       | 270/938 [00:18<00:46, 14.28it/s, loss=0.917, v_num=16]
Epoch 0:  29%|██▉       | 271/938 [00:18<00:46, 14.28it/s, loss=0.917, v_num=16]
Epoch 0:  29%|██▉       | 271/938 [00:18<00:46, 14.28it/s, loss=0.926, v_num=16]
Epoch 0:  29%|██▉       | 272/938 [00:19<00:46, 14.28it/s, loss=0.925, v_num=16]
Epoch 0:  29%|██▉       | 273/938 [00:19<00:46, 14.29it/s, loss=0.925, v_num=16]
Epoch 0:  29%|██▉       | 273/938 [00:19<00:46, 14.29it/s, loss=0.93, v_num=16] 
Epoch 0:  29%|██▉       | 274/938 [00:19<00:46, 14.28it/s, loss=0.921, v_num=16]
Epoch 0:  29%|██▉       | 275/938 [00:19<00:46, 14.27it/s, loss=0.921, v_num=16]
Epoch 0:  29%|██▉       | 275/938 [00:19<00:46, 14.27it/s, loss=0.922, v_num=16]
Epoch 0:  29%|██▉       | 276/938 [00:19<00:46, 14.27it/s, loss=0.929, v_num=16]
Epoch 0:  30%|██▉       | 277/938 [00:19<00:46, 14.29it/s, loss=0.929, v_num=16]
Epoch 0:  30%|██▉       | 277/938 [00:19<00:46, 14.29it/s, loss=0.931, v_num=16]
Epoch 0:  30%|██▉       | 278/938 [00:19<00:46, 14.28it/s, loss=0.917, v_num=16]
Epoch 0:  30%|██▉       | 279/938 [00:19<00:46, 14.27it/s, loss=0.917, v_num=16]
Epoch 0:  30%|██▉       | 279/938 [00:19<00:46, 14.27it/s, loss=0.907, v_num=16]
Epoch 0:  30%|██▉       | 280/938 [00:19<00:46, 14.29it/s, loss=0.905, v_num=16]
Epoch 0:  30%|██▉       | 281/938 [00:19<00:46, 14.27it/s, loss=0.905, v_num=16]
Epoch 0:  30%|██▉       | 281/938 [00:19<00:46, 14.27it/s, loss=0.894, v_num=16]
Epoch 0:  30%|███       | 282/938 [00:19<00:45, 14.27it/s, loss=0.888, v_num=16]
Epoch 0:  30%|███       | 283/938 [00:19<00:45, 14.26it/s, loss=0.888, v_num=16]
Epoch 0:  30%|███       | 283/938 [00:19<00:45, 14.26it/s, loss=0.899, v_num=16]
Epoch 0:  30%|███       | 284/938 [00:19<00:45, 14.27it/s, loss=0.904, v_num=16]
Epoch 0:  30%|███       | 285/938 [00:19<00:45, 14.25it/s, loss=0.904, v_num=16]
Epoch 0:  30%|███       | 285/938 [00:20<00:45, 14.25it/s, loss=0.9, v_num=16]  
Epoch 0:  30%|███       | 286/938 [00:20<00:45, 14.25it/s, loss=0.903, v_num=16]
Epoch 0:  31%|███       | 287/938 [00:20<00:45, 14.25it/s, loss=0.903, v_num=16]
Epoch 0:  31%|███       | 287/938 [00:20<00:45, 14.25it/s, loss=0.905, v_num=16]
Epoch 0:  31%|███       | 288/938 [00:20<00:45, 14.26it/s, loss=0.908, v_num=16]
Epoch 0:  31%|███       | 289/938 [00:20<00:45, 14.27it/s, loss=0.908, v_num=16]
Epoch 0:  31%|███       | 289/938 [00:20<00:45, 14.27it/s, loss=0.906, v_num=16]
Epoch 0:  31%|███       | 290/938 [00:20<00:45, 14.26it/s, loss=0.911, v_num=16]
Epoch 0:  31%|███       | 291/938 [00:20<00:45, 14.26it/s, loss=0.911, v_num=16]
Epoch 0:  31%|███       | 291/938 [00:20<00:45, 14.26it/s, loss=0.911, v_num=16]
Epoch 0:  31%|███       | 292/938 [00:20<00:45, 14.26it/s, loss=0.897, v_num=16]
Epoch 0:  31%|███       | 293/938 [00:20<00:45, 14.26it/s, loss=0.897, v_num=16]
Epoch 0:  31%|███       | 293/938 [00:20<00:45, 14.26it/s, loss=0.884, v_num=16]
Epoch 0:  31%|███▏      | 294/938 [00:20<00:45, 14.27it/s, loss=0.883, v_num=16]
Epoch 0:  31%|███▏      | 295/938 [00:20<00:45, 14.27it/s, loss=0.883, v_num=16]
Epoch 0:  31%|███▏      | 295/938 [00:20<00:45, 14.27it/s, loss=0.872, v_num=16]
Epoch 0:  32%|███▏      | 296/938 [00:20<00:44, 14.28it/s, loss=0.869, v_num=16]
Epoch 0:  32%|███▏      | 297/938 [00:20<00:44, 14.27it/s, loss=0.869, v_num=16]
Epoch 0:  32%|███▏      | 297/938 [00:20<00:44, 14.27it/s, loss=0.867, v_num=16]
Epoch 0:  32%|███▏      | 298/938 [00:20<00:44, 14.28it/s, loss=0.868, v_num=16]
Epoch 0:  32%|███▏      | 299/938 [00:20<00:44, 14.29it/s, loss=0.868, v_num=16]
Epoch 0:  32%|███▏      | 299/938 [00:20<00:44, 14.29it/s, loss=0.865, v_num=16]
Epoch 0:  32%|███▏      | 300/938 [00:21<00:44, 14.28it/s, loss=0.869, v_num=16]
Epoch 0:  32%|███▏      | 301/938 [00:21<00:44, 14.28it/s, loss=0.869, v_num=16]
Epoch 0:  32%|███▏      | 301/938 [00:21<00:44, 14.28it/s, loss=0.867, v_num=16]
Epoch 0:  32%|███▏      | 302/938 [00:21<00:44, 14.28it/s, loss=0.864, v_num=16]
Epoch 0:  32%|███▏      | 303/938 [00:21<00:44, 14.29it/s, loss=0.864, v_num=16]
Epoch 0:  32%|███▏      | 303/938 [00:21<00:44, 14.29it/s, loss=0.853, v_num=16]
Epoch 0:  32%|███▏      | 304/938 [00:21<00:44, 14.28it/s, loss=0.844, v_num=16]
Epoch 0:  33%|███▎      | 305/938 [00:21<00:44, 14.28it/s, loss=0.844, v_num=16]
Epoch 0:  33%|███▎      | 305/938 [00:21<00:44, 14.28it/s, loss=0.837, v_num=16]
Epoch 0:  33%|███▎      | 306/938 [00:21<00:44, 14.28it/s, loss=0.836, v_num=16]
Epoch 0:  33%|███▎      | 307/938 [00:21<00:44, 14.28it/s, loss=0.836, v_num=16]
Epoch 0:  33%|███▎      | 307/938 [00:21<00:44, 14.28it/s, loss=0.832, v_num=16]
Epoch 0:  33%|███▎      | 308/938 [00:21<00:44, 14.28it/s, loss=0.832, v_num=16]
Epoch 0:  33%|███▎      | 309/938 [00:21<00:44, 14.28it/s, loss=0.832, v_num=16]
Epoch 0:  33%|███▎      | 309/938 [00:21<00:44, 14.28it/s, loss=0.827, v_num=16]
Epoch 0:  33%|███▎      | 310/938 [00:21<00:43, 14.28it/s, loss=0.829, v_num=16]
Epoch 0:  33%|███▎      | 311/938 [00:21<00:43, 14.28it/s, loss=0.829, v_num=16]
Epoch 0:  33%|███▎      | 311/938 [00:21<00:43, 14.28it/s, loss=0.827, v_num=16]
Epoch 0:  33%|███▎      | 312/938 [00:21<00:43, 14.29it/s, loss=0.828, v_num=16]
Epoch 0:  33%|███▎      | 313/938 [00:21<00:43, 14.28it/s, loss=0.828, v_num=16]
Epoch 0:  33%|███▎      | 313/938 [00:21<00:43, 14.28it/s, loss=0.83, v_num=16] 
Epoch 0:  33%|███▎      | 314/938 [00:21<00:43, 14.29it/s, loss=0.839, v_num=16]
Epoch 0:  34%|███▎      | 315/938 [00:22<00:43, 14.29it/s, loss=0.839, v_num=16]
Epoch 0:  34%|███▎      | 315/938 [00:22<00:43, 14.29it/s, loss=0.844, v_num=16]
Epoch 0:  34%|███▎      | 316/938 [00:22<00:43, 14.29it/s, loss=0.843, v_num=16]
Epoch 0:  34%|███▍      | 317/938 [00:22<00:43, 14.30it/s, loss=0.843, v_num=16]
Epoch 0:  34%|███▍      | 317/938 [00:22<00:43, 14.29it/s, loss=0.841, v_num=16]
Epoch 0:  34%|███▍      | 318/938 [00:22<00:43, 14.30it/s, loss=0.83, v_num=16] 
Epoch 0:  34%|███▍      | 319/938 [00:22<00:43, 14.31it/s, loss=0.83, v_num=16]
Epoch 0:  34%|███▍      | 319/938 [00:22<00:43, 14.31it/s, loss=0.824, v_num=16]
Epoch 0:  34%|███▍      | 320/938 [00:22<00:43, 14.32it/s, loss=0.825, v_num=16]
Epoch 0:  34%|███▍      | 321/938 [00:22<00:43, 14.31it/s, loss=0.825, v_num=16]
Epoch 0:  34%|███▍      | 321/938 [00:22<00:43, 14.31it/s, loss=0.825, v_num=16]
Epoch 0:  34%|███▍      | 322/938 [00:22<00:43, 14.31it/s, loss=0.819, v_num=16]
Epoch 0:  34%|███▍      | 323/938 [00:22<00:42, 14.32it/s, loss=0.819, v_num=16]
Epoch 0:  34%|███▍      | 323/938 [00:22<00:42, 14.32it/s, loss=0.814, v_num=16]
Epoch 0:  35%|███▍      | 324/938 [00:22<00:42, 14.32it/s, loss=0.815, v_num=16]
Epoch 0:  35%|███▍      | 325/938 [00:22<00:42, 14.33it/s, loss=0.815, v_num=16]
Epoch 0:  35%|███▍      | 325/938 [00:22<00:42, 14.33it/s, loss=0.821, v_num=16]
Epoch 0:  35%|███▍      | 326/938 [00:22<00:42, 14.34it/s, loss=0.816, v_num=16]
Epoch 0:  35%|███▍      | 327/938 [00:22<00:42, 14.30it/s, loss=0.816, v_num=16]
Epoch 0:  35%|███▍      | 327/938 [00:22<00:42, 14.30it/s, loss=0.819, v_num=16]
Epoch 0:  35%|███▍      | 328/938 [00:22<00:42, 14.31it/s, loss=0.81, v_num=16] 
Epoch 0:  35%|███▌      | 329/938 [00:22<00:42, 14.31it/s, loss=0.81, v_num=16]
Epoch 0:  35%|███▌      | 329/938 [00:22<00:42, 14.31it/s, loss=0.823, v_num=16]
Epoch 0:  35%|███▌      | 330/938 [00:23<00:42, 14.31it/s, loss=0.829, v_num=16]
Epoch 0:  35%|███▌      | 331/938 [00:23<00:42, 14.31it/s, loss=0.829, v_num=16]
Epoch 0:  35%|███▌      | 331/938 [00:23<00:42, 14.31it/s, loss=0.824, v_num=16]
Epoch 0:  35%|███▌      | 332/938 [00:23<00:42, 14.32it/s, loss=0.827, v_num=16]
Epoch 0:  36%|███▌      | 333/938 [00:23<00:42, 14.31it/s, loss=0.827, v_num=16]
Epoch 0:  36%|███▌      | 333/938 [00:23<00:42, 14.31it/s, loss=0.836, v_num=16]
Epoch 0:  36%|███▌      | 334/938 [00:23<00:42, 14.32it/s, loss=0.832, v_num=16]
Epoch 0:  36%|███▌      | 335/938 [00:23<00:42, 14.33it/s, loss=0.832, v_num=16]
Epoch 0:  36%|███▌      | 335/938 [00:23<00:42, 14.33it/s, loss=0.824, v_num=16]
Epoch 0:  36%|███▌      | 336/938 [00:23<00:42, 14.33it/s, loss=0.816, v_num=16]
Epoch 0:  36%|███▌      | 337/938 [00:23<00:41, 14.33it/s, loss=0.816, v_num=16]
Epoch 0:  36%|███▌      | 337/938 [00:23<00:41, 14.33it/s, loss=0.819, v_num=16]
Epoch 0:  36%|███▌      | 338/938 [00:23<00:41, 14.34it/s, loss=0.818, v_num=16]
Epoch 0:  36%|███▌      | 339/938 [00:23<00:41, 14.34it/s, loss=0.818, v_num=16]
Epoch 0:  36%|███▌      | 339/938 [00:23<00:41, 14.34it/s, loss=0.824, v_num=16]
Epoch 0:  36%|███▌      | 340/938 [00:23<00:41, 14.34it/s, loss=0.82, v_num=16] 
Epoch 0:  36%|███▋      | 341/938 [00:23<00:41, 14.34it/s, loss=0.82, v_num=16]
Epoch 0:  36%|███▋      | 341/938 [00:23<00:41, 14.34it/s, loss=0.816, v_num=16]
Epoch 0:  36%|███▋      | 342/938 [00:23<00:41, 14.34it/s, loss=0.814, v_num=16]
Epoch 0:  37%|███▋      | 343/938 [00:23<00:41, 14.34it/s, loss=0.814, v_num=16]
Epoch 0:  37%|███▋      | 343/938 [00:23<00:41, 14.34it/s, loss=0.817, v_num=16]
Epoch 0:  37%|███▋      | 344/938 [00:23<00:41, 14.34it/s, loss=0.826, v_num=16]
Epoch 0:  37%|███▋      | 345/938 [00:24<00:41, 14.35it/s, loss=0.826, v_num=16]
Epoch 0:  37%|███▋      | 345/938 [00:24<00:41, 14.35it/s, loss=0.826, v_num=16]
Epoch 0:  37%|███▋      | 346/938 [00:24<00:41, 14.35it/s, loss=0.826, v_num=16]
Epoch 0:  37%|███▋      | 347/938 [00:24<00:41, 14.35it/s, loss=0.826, v_num=16]
Epoch 0:  37%|███▋      | 347/938 [00:24<00:41, 14.35it/s, loss=0.829, v_num=16]
Epoch 0:  37%|███▋      | 348/938 [00:24<00:41, 14.35it/s, loss=0.839, v_num=16]
Epoch 0:  37%|███▋      | 349/938 [00:24<00:41, 14.34it/s, loss=0.839, v_num=16]
Epoch 0:  37%|███▋      | 349/938 [00:24<00:41, 14.34it/s, loss=0.838, v_num=16]
Epoch 0:  37%|███▋      | 350/938 [00:24<00:41, 14.34it/s, loss=0.823, v_num=16]
Epoch 0:  37%|███▋      | 351/938 [00:24<00:40, 14.34it/s, loss=0.823, v_num=16]
Epoch 0:  37%|███▋      | 351/938 [00:24<00:40, 14.34it/s, loss=0.825, v_num=16]
Epoch 0:  38%|███▊      | 352/938 [00:24<00:40, 14.34it/s, loss=0.818, v_num=16]
Epoch 0:  38%|███▊      | 353/938 [00:24<00:40, 14.33it/s, loss=0.818, v_num=16]
Epoch 0:  38%|███▊      | 353/938 [00:24<00:40, 14.33it/s, loss=0.813, v_num=16]
Epoch 0:  38%|███▊      | 354/938 [00:24<00:40, 14.34it/s, loss=0.806, v_num=16]
Epoch 0:  38%|███▊      | 355/938 [00:24<00:40, 14.34it/s, loss=0.806, v_num=16]
Epoch 0:  38%|███▊      | 355/938 [00:24<00:40, 14.34it/s, loss=0.809, v_num=16]
Epoch 0:  38%|███▊      | 356/938 [00:24<00:40, 14.34it/s, loss=0.807, v_num=16]
Epoch 0:  38%|███▊      | 357/938 [00:24<00:40, 14.34it/s, loss=0.807, v_num=16]
Epoch 0:  38%|███▊      | 357/938 [00:24<00:40, 14.34it/s, loss=0.808, v_num=16]
Epoch 0:  38%|███▊      | 358/938 [00:24<00:40, 14.34it/s, loss=0.815, v_num=16]
Epoch 0:  38%|███▊      | 359/938 [00:25<00:40, 14.33it/s, loss=0.815, v_num=16]
Epoch 0:  38%|███▊      | 359/938 [00:25<00:40, 14.33it/s, loss=0.807, v_num=16]
Epoch 0:  38%|███▊      | 360/938 [00:25<00:40, 14.33it/s, loss=0.811, v_num=16]
Epoch 0:  38%|███▊      | 361/938 [00:25<00:40, 14.33it/s, loss=0.811, v_num=16]
Epoch 0:  38%|███▊      | 361/938 [00:25<00:40, 14.33it/s, loss=0.815, v_num=16]
Epoch 0:  39%|███▊      | 362/938 [00:25<00:40, 14.33it/s, loss=0.819, v_num=16]
Epoch 0:  39%|███▊      | 363/938 [00:25<00:40, 14.34it/s, loss=0.819, v_num=16]
Epoch 0:  39%|███▊      | 363/938 [00:25<00:40, 14.34it/s, loss=0.821, v_num=16]
Epoch 0:  39%|███▉      | 364/938 [00:25<00:40, 14.35it/s, loss=0.808, v_num=16]
Epoch 0:  39%|███▉      | 365/938 [00:25<00:39, 14.35it/s, loss=0.808, v_num=16]
Epoch 0:  39%|███▉      | 365/938 [00:25<00:39, 14.35it/s, loss=0.802, v_num=16]
Epoch 0:  39%|███▉      | 366/938 [00:25<00:39, 14.36it/s, loss=0.801, v_num=16]
Epoch 0:  39%|███▉      | 367/938 [00:25<00:39, 14.35it/s, loss=0.801, v_num=16]
Epoch 0:  39%|███▉      | 367/938 [00:25<00:39, 14.35it/s, loss=0.796, v_num=16]
Epoch 0:  39%|███▉      | 368/938 [00:25<00:39, 14.35it/s, loss=0.795, v_num=16]
Epoch 0:  39%|███▉      | 369/938 [00:25<00:39, 14.35it/s, loss=0.795, v_num=16]
Epoch 0:  39%|███▉      | 369/938 [00:25<00:39, 14.35it/s, loss=0.792, v_num=16]
Epoch 0:  39%|███▉      | 370/938 [00:25<00:39, 14.34it/s, loss=0.798, v_num=16]
Epoch 0:  40%|███▉      | 371/938 [00:25<00:39, 14.35it/s, loss=0.798, v_num=16]
Epoch 0:  40%|███▉      | 371/938 [00:25<00:39, 14.35it/s, loss=0.806, v_num=16]
Epoch 0:  40%|███▉      | 372/938 [00:25<00:39, 14.35it/s, loss=0.812, v_num=16]
Epoch 0:  40%|███▉      | 373/938 [00:25<00:39, 14.35it/s, loss=0.812, v_num=16]
Epoch 0:  40%|███▉      | 373/938 [00:25<00:39, 14.35it/s, loss=0.814, v_num=16]
Epoch 0:  40%|███▉      | 374/938 [00:26<00:39, 14.35it/s, loss=0.814, v_num=16]
Epoch 0:  40%|███▉      | 375/938 [00:26<00:39, 14.34it/s, loss=0.814, v_num=16]
Epoch 0:  40%|███▉      | 375/938 [00:26<00:39, 14.34it/s, loss=0.821, v_num=16]
Epoch 0:  40%|████      | 376/938 [00:26<00:39, 14.34it/s, loss=0.821, v_num=16]
Epoch 0:  40%|████      | 377/938 [00:26<00:39, 14.34it/s, loss=0.821, v_num=16]
Epoch 0:  40%|████      | 377/938 [00:26<00:39, 14.34it/s, loss=0.821, v_num=16]
Epoch 0:  40%|████      | 378/938 [00:26<00:39, 14.34it/s, loss=0.822, v_num=16]
Epoch 0:  40%|████      | 379/938 [00:26<00:38, 14.34it/s, loss=0.822, v_num=16]
Epoch 0:  40%|████      | 379/938 [00:26<00:38, 14.34it/s, loss=0.827, v_num=16]
Epoch 0:  41%|████      | 380/938 [00:26<00:38, 14.34it/s, loss=0.823, v_num=16]
Epoch 0:  41%|████      | 381/938 [00:26<00:38, 14.34it/s, loss=0.823, v_num=16]
Epoch 0:  41%|████      | 381/938 [00:26<00:38, 14.34it/s, loss=0.827, v_num=16]
Epoch 0:  41%|████      | 382/938 [00:26<00:38, 14.34it/s, loss=0.834, v_num=16]
Epoch 0:  41%|████      | 383/938 [00:26<00:38, 14.34it/s, loss=0.834, v_num=16]
Epoch 0:  41%|████      | 383/938 [00:26<00:38, 14.34it/s, loss=0.831, v_num=16]
Epoch 0:  41%|████      | 384/938 [00:26<00:38, 14.33it/s, loss=0.829, v_num=16]
Epoch 0:  41%|████      | 385/938 [00:26<00:38, 14.33it/s, loss=0.829, v_num=16]
Epoch 0:  41%|████      | 385/938 [00:26<00:38, 14.33it/s, loss=0.832, v_num=16]
Epoch 0:  41%|████      | 386/938 [00:26<00:38, 14.34it/s, loss=0.832, v_num=16]
Epoch 0:  41%|████▏     | 387/938 [00:26<00:38, 14.34it/s, loss=0.832, v_num=16]
Epoch 0:  41%|████▏     | 387/938 [00:26<00:38, 14.34it/s, loss=0.83, v_num=16] 
Epoch 0:  41%|████▏     | 388/938 [00:27<00:38, 14.35it/s, loss=0.819, v_num=16]
Epoch 0:  41%|████▏     | 389/938 [00:27<00:38, 14.35it/s, loss=0.819, v_num=16]
Epoch 0:  41%|████▏     | 389/938 [00:27<00:38, 14.35it/s, loss=0.814, v_num=16]
Epoch 0:  42%|████▏     | 390/938 [00:27<00:38, 14.34it/s, loss=0.812, v_num=16]
Epoch 0:  42%|████▏     | 391/938 [00:27<00:38, 14.34it/s, loss=0.812, v_num=16]
Epoch 0:  42%|████▏     | 391/938 [00:27<00:38, 14.34it/s, loss=0.807, v_num=16]
Epoch 0:  42%|████▏     | 392/938 [00:27<00:38, 14.35it/s, loss=0.807, v_num=16]
Epoch 0:  42%|████▏     | 393/938 [00:27<00:37, 14.36it/s, loss=0.807, v_num=16]
Epoch 0:  42%|████▏     | 393/938 [00:27<00:37, 14.36it/s, loss=0.811, v_num=16]
Epoch 0:  42%|████▏     | 394/938 [00:27<00:37, 14.36it/s, loss=0.813, v_num=16]
Epoch 0:  42%|████▏     | 395/938 [00:27<00:37, 14.36it/s, loss=0.813, v_num=16]
Epoch 0:  42%|████▏     | 395/938 [00:27<00:37, 14.36it/s, loss=0.81, v_num=16] 
Epoch 0:  42%|████▏     | 396/938 [00:27<00:37, 14.35it/s, loss=0.811, v_num=16]
Epoch 0:  42%|████▏     | 397/938 [00:27<00:37, 14.36it/s, loss=0.811, v_num=16]
Epoch 0:  42%|████▏     | 397/938 [00:27<00:37, 14.36it/s, loss=0.813, v_num=16]
Epoch 0:  42%|████▏     | 398/938 [00:27<00:37, 14.36it/s, loss=0.823, v_num=16]
Epoch 0:  43%|████▎     | 399/938 [00:27<00:37, 14.36it/s, loss=0.823, v_num=16]
Epoch 0:  43%|████▎     | 399/938 [00:27<00:37, 14.36it/s, loss=0.814, v_num=16]
Epoch 0:  43%|████▎     | 400/938 [00:27<00:37, 14.35it/s, loss=0.822, v_num=16]
Epoch 0:  43%|████▎     | 401/938 [00:27<00:37, 14.35it/s, loss=0.822, v_num=16]
Epoch 0:  43%|████▎     | 401/938 [00:27<00:37, 14.35it/s, loss=0.818, v_num=16]
Epoch 0:  43%|████▎     | 402/938 [00:28<00:37, 14.35it/s, loss=0.816, v_num=16]
Epoch 0:  43%|████▎     | 403/938 [00:28<00:37, 14.35it/s, loss=0.816, v_num=16]
Epoch 0:  43%|████▎     | 403/938 [00:28<00:37, 14.35it/s, loss=0.824, v_num=16]
Epoch 0:  43%|████▎     | 404/938 [00:28<00:37, 14.36it/s, loss=0.833, v_num=16]
Epoch 0:  43%|████▎     | 405/938 [00:28<00:37, 14.36it/s, loss=0.833, v_num=16]
Epoch 0:  43%|████▎     | 405/938 [00:28<00:37, 14.36it/s, loss=0.835, v_num=16]
Epoch 0:  43%|████▎     | 406/938 [00:28<00:37, 14.35it/s, loss=0.846, v_num=16]
Epoch 0:  43%|████▎     | 407/938 [00:28<00:37, 14.34it/s, loss=0.846, v_num=16]
Epoch 0:  43%|████▎     | 407/938 [00:28<00:37, 14.34it/s, loss=0.846, v_num=16]
Epoch 0:  43%|████▎     | 408/938 [00:28<00:36, 14.34it/s, loss=0.852, v_num=16]
Epoch 0:  44%|████▎     | 409/938 [00:28<00:36, 14.34it/s, loss=0.852, v_num=16]
Epoch 0:  44%|████▎     | 409/938 [00:28<00:36, 14.34it/s, loss=0.867, v_num=16]
Epoch 0:  44%|████▎     | 410/938 [00:28<00:36, 14.34it/s, loss=0.869, v_num=16]
Epoch 0:  44%|████▍     | 411/938 [00:28<00:36, 14.34it/s, loss=0.869, v_num=16]
Epoch 0:  44%|████▍     | 411/938 [00:28<00:36, 14.34it/s, loss=0.867, v_num=16]
Epoch 0:  44%|████▍     | 412/938 [00:28<00:36, 14.34it/s, loss=0.868, v_num=16]
Epoch 0:  44%|████▍     | 413/938 [00:28<00:36, 14.34it/s, loss=0.868, v_num=16]
Epoch 0:  44%|████▍     | 413/938 [00:28<00:36, 14.34it/s, loss=0.856, v_num=16]
Epoch 0:  44%|████▍     | 414/938 [00:28<00:36, 14.35it/s, loss=0.861, v_num=16]
Epoch 0:  44%|████▍     | 415/938 [00:28<00:36, 14.35it/s, loss=0.861, v_num=16]
Epoch 0:  44%|████▍     | 415/938 [00:28<00:36, 14.35it/s, loss=0.857, v_num=16]
Epoch 0:  44%|████▍     | 416/938 [00:28<00:36, 14.36it/s, loss=0.853, v_num=16]
Epoch 0:  44%|████▍     | 417/938 [00:29<00:36, 14.35it/s, loss=0.853, v_num=16]
Epoch 0:  44%|████▍     | 417/938 [00:29<00:36, 14.35it/s, loss=0.849, v_num=16]
Epoch 0:  45%|████▍     | 418/938 [00:29<00:36, 14.35it/s, loss=0.835, v_num=16]
Epoch 0:  45%|████▍     | 419/938 [00:29<00:36, 14.35it/s, loss=0.835, v_num=16]
Epoch 0:  45%|████▍     | 419/938 [00:29<00:36, 14.35it/s, loss=0.838, v_num=16]
Epoch 0:  45%|████▍     | 420/938 [00:29<00:36, 14.35it/s, loss=0.826, v_num=16]
Epoch 0:  45%|████▍     | 421/938 [00:29<00:36, 14.35it/s, loss=0.826, v_num=16]
Epoch 0:  45%|████▍     | 421/938 [00:29<00:36, 14.35it/s, loss=0.828, v_num=16]
Epoch 0:  45%|████▍     | 422/938 [00:29<00:35, 14.35it/s, loss=0.823, v_num=16]
Epoch 0:  45%|████▌     | 423/938 [00:29<00:35, 14.35it/s, loss=0.823, v_num=16]
Epoch 0:  45%|████▌     | 423/938 [00:29<00:35, 14.35it/s, loss=0.815, v_num=16]
Epoch 0:  45%|████▌     | 424/938 [00:29<00:35, 14.36it/s, loss=0.808, v_num=16]
Epoch 0:  45%|████▌     | 425/938 [00:29<00:35, 14.36it/s, loss=0.808, v_num=16]
Epoch 0:  45%|████▌     | 425/938 [00:29<00:35, 14.36it/s, loss=0.8, v_num=16]  
Epoch 0:  45%|████▌     | 426/938 [00:29<00:35, 14.36it/s, loss=0.779, v_num=16]
Epoch 0:  46%|████▌     | 427/938 [00:29<00:35, 14.36it/s, loss=0.779, v_num=16]
Epoch 0:  46%|████▌     | 427/938 [00:29<00:35, 14.36it/s, loss=0.777, v_num=16]
Epoch 0:  46%|████▌     | 428/938 [00:29<00:35, 14.35it/s, loss=0.771, v_num=16]
Epoch 0:  46%|████▌     | 429/938 [00:29<00:35, 14.36it/s, loss=0.771, v_num=16]
Epoch 0:  46%|████▌     | 429/938 [00:29<00:35, 14.36it/s, loss=0.761, v_num=16]
Epoch 0:  46%|████▌     | 430/938 [00:29<00:35, 14.36it/s, loss=0.752, v_num=16]
Epoch 0:  46%|████▌     | 431/938 [00:30<00:35, 14.36it/s, loss=0.752, v_num=16]
Epoch 0:  46%|████▌     | 431/938 [00:30<00:35, 14.36it/s, loss=0.746, v_num=16]
Epoch 0:  46%|████▌     | 432/938 [00:30<00:35, 14.36it/s, loss=0.738, v_num=16]
Epoch 0:  46%|████▌     | 433/938 [00:30<00:35, 14.37it/s, loss=0.738, v_num=16]
Epoch 0:  46%|████▌     | 433/938 [00:30<00:35, 14.37it/s, loss=0.752, v_num=16]
Epoch 0:  46%|████▋     | 434/938 [00:30<00:35, 14.37it/s, loss=0.748, v_num=16]
Epoch 0:  46%|████▋     | 435/938 [00:30<00:35, 14.37it/s, loss=0.748, v_num=16]
Epoch 0:  46%|████▋     | 435/938 [00:30<00:35, 14.37it/s, loss=0.751, v_num=16]
Epoch 0:  46%|████▋     | 436/938 [00:30<00:34, 14.37it/s, loss=0.752, v_num=16]
Epoch 0:  47%|████▋     | 437/938 [00:30<00:34, 14.38it/s, loss=0.752, v_num=16]
Epoch 0:  47%|████▋     | 437/938 [00:30<00:34, 14.38it/s, loss=0.756, v_num=16]
Epoch 0:  47%|████▋     | 438/938 [00:30<00:34, 14.38it/s, loss=0.756, v_num=16]
Epoch 0:  47%|████▋     | 439/938 [00:30<00:34, 14.38it/s, loss=0.756, v_num=16]
Epoch 0:  47%|████▋     | 439/938 [00:30<00:34, 14.38it/s, loss=0.761, v_num=16]
Epoch 0:  47%|████▋     | 440/938 [00:30<00:34, 14.39it/s, loss=0.761, v_num=16]
Epoch 0:  47%|████▋     | 441/938 [00:30<00:34, 14.39it/s, loss=0.761, v_num=16]
Epoch 0:  47%|████▋     | 441/938 [00:30<00:34, 14.39it/s, loss=0.75, v_num=16] 
Epoch 0:  47%|████▋     | 442/938 [00:30<00:34, 14.39it/s, loss=0.739, v_num=16]
Epoch 0:  47%|████▋     | 443/938 [00:30<00:34, 14.38it/s, loss=0.739, v_num=16]
Epoch 0:  47%|████▋     | 443/938 [00:30<00:34, 14.38it/s, loss=0.732, v_num=16]
Epoch 0:  47%|████▋     | 444/938 [00:30<00:34, 14.39it/s, loss=0.739, v_num=16]
Epoch 0:  47%|████▋     | 445/938 [00:30<00:34, 14.38it/s, loss=0.739, v_num=16]
Epoch 0:  47%|████▋     | 445/938 [00:30<00:34, 14.38it/s, loss=0.74, v_num=16] 
Epoch 0:  48%|████▊     | 446/938 [00:31<00:34, 14.38it/s, loss=0.751, v_num=16]
Epoch 0:  48%|████▊     | 447/938 [00:31<00:34, 14.38it/s, loss=0.751, v_num=16]
Epoch 0:  48%|████▊     | 447/938 [00:31<00:34, 14.38it/s, loss=0.746, v_num=16]
Epoch 0:  48%|████▊     | 448/938 [00:31<00:34, 14.38it/s, loss=0.754, v_num=16]
Epoch 0:  48%|████▊     | 449/938 [00:31<00:33, 14.39it/s, loss=0.754, v_num=16]
Epoch 0:  48%|████▊     | 449/938 [00:31<00:33, 14.39it/s, loss=0.747, v_num=16]
Epoch 0:  48%|████▊     | 450/938 [00:31<00:33, 14.39it/s, loss=0.749, v_num=16]
Epoch 0:  48%|████▊     | 451/938 [00:31<00:33, 14.39it/s, loss=0.749, v_num=16]
Epoch 0:  48%|████▊     | 451/938 [00:31<00:33, 14.39it/s, loss=0.748, v_num=16]
Epoch 0:  48%|████▊     | 452/938 [00:31<00:33, 14.39it/s, loss=0.751, v_num=16]
Epoch 0:  48%|████▊     | 453/938 [00:31<00:33, 14.40it/s, loss=0.751, v_num=16]
Epoch 0:  48%|████▊     | 453/938 [00:31<00:33, 14.40it/s, loss=0.742, v_num=16]
Epoch 0:  48%|████▊     | 454/938 [00:31<00:33, 14.40it/s, loss=0.741, v_num=16]
Epoch 0:  49%|████▊     | 455/938 [00:31<00:33, 14.39it/s, loss=0.741, v_num=16]
Epoch 0:  49%|████▊     | 455/938 [00:31<00:33, 14.39it/s, loss=0.743, v_num=16]
Epoch 0:  49%|████▊     | 456/938 [00:31<00:33, 14.39it/s, loss=0.753, v_num=16]
Epoch 0:  49%|████▊     | 457/938 [00:31<00:33, 14.39it/s, loss=0.753, v_num=16]
Epoch 0:  49%|████▊     | 457/938 [00:31<00:33, 14.39it/s, loss=0.752, v_num=16]
Epoch 0:  49%|████▉     | 458/938 [00:31<00:33, 14.39it/s, loss=0.753, v_num=16]
Epoch 0:  49%|████▉     | 459/938 [00:31<00:33, 14.40it/s, loss=0.753, v_num=16]
Epoch 0:  49%|████▉     | 459/938 [00:31<00:33, 14.40it/s, loss=0.755, v_num=16]
Epoch 0:  49%|████▉     | 460/938 [00:31<00:33, 14.40it/s, loss=0.76, v_num=16] 
Epoch 0:  49%|████▉     | 461/938 [00:32<00:33, 14.40it/s, loss=0.76, v_num=16]
Epoch 0:  49%|████▉     | 461/938 [00:32<00:33, 14.40it/s, loss=0.767, v_num=16]
Epoch 0:  49%|████▉     | 462/938 [00:32<00:33, 14.40it/s, loss=0.779, v_num=16]
Epoch 0:  49%|████▉     | 463/938 [00:32<00:32, 14.40it/s, loss=0.779, v_num=16]
Epoch 0:  49%|████▉     | 463/938 [00:32<00:32, 14.40it/s, loss=0.787, v_num=16]
Epoch 0:  49%|████▉     | 464/938 [00:32<00:32, 14.40it/s, loss=0.784, v_num=16]
Epoch 0:  50%|████▉     | 465/938 [00:32<00:32, 14.40it/s, loss=0.784, v_num=16]
Epoch 0:  50%|████▉     | 465/938 [00:32<00:32, 14.40it/s, loss=0.783, v_num=16]
Epoch 0:  50%|████▉     | 466/938 [00:32<00:32, 14.40it/s, loss=0.778, v_num=16]
Epoch 0:  50%|████▉     | 467/938 [00:32<00:32, 14.41it/s, loss=0.778, v_num=16]
Epoch 0:  50%|████▉     | 467/938 [00:32<00:32, 14.41it/s, loss=0.781, v_num=16]
Epoch 0:  50%|████▉     | 468/938 [00:32<00:32, 14.40it/s, loss=0.771, v_num=16]
Epoch 0:  50%|█████     | 469/938 [00:32<00:32, 14.41it/s, loss=0.771, v_num=16]
Epoch 0:  50%|█████     | 469/938 [00:32<00:32, 14.41it/s, loss=0.771, v_num=16]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]

Validating:   0%|          | 2/469 [00:00<00:24, 19.05it/s]
Epoch 0:  50%|█████     | 472/938 [00:32<00:32, 14.46it/s, loss=0.771, v_num=16]

Validating:   1%|          | 5/469 [00:00<00:20, 23.00it/s]
Epoch 0:  51%|█████     | 475/938 [00:32<00:31, 14.50it/s, loss=0.771, v_num=16]

Validating:   2%|▏         | 8/469 [00:00<00:19, 23.60it/s]
Epoch 0:  51%|█████     | 478/938 [00:32<00:31, 14.53it/s, loss=0.771, v_num=16]

Validating:   2%|▏         | 11/469 [00:00<00:18, 25.02it/s]
Epoch 0:  51%|█████▏    | 481/938 [00:33<00:31, 14.58it/s, loss=0.771, v_num=16]

Validating:   3%|▎         | 14/469 [00:00<00:18, 25.23it/s]
Epoch 0:  52%|█████▏    | 484/938 [00:33<00:31, 14.61it/s, loss=0.771, v_num=16]

Validating:   4%|▎         | 17/469 [00:00<00:18, 24.81it/s]
Epoch 0:  52%|█████▏    | 487/938 [00:33<00:30, 14.65it/s, loss=0.771, v_num=16]

Validating:   4%|▍         | 20/469 [00:00<00:17, 25.15it/s]
Epoch 0:  52%|█████▏    | 490/938 [00:33<00:30, 14.69it/s, loss=0.771, v_num=16]

Validating:   5%|▍         | 23/469 [00:00<00:17, 26.22it/s]
Epoch 0:  53%|█████▎    | 493/938 [00:33<00:30, 14.73it/s, loss=0.771, v_num=16]

Validating:   6%|▌         | 26/469 [00:01<00:18, 24.60it/s]
Epoch 0:  53%|█████▎    | 496/938 [00:33<00:29, 14.76it/s, loss=0.771, v_num=16]

Validating:   6%|▌         | 29/469 [00:01<00:17, 24.93it/s]
Epoch 0:  53%|█████▎    | 499/938 [00:33<00:29, 14.80it/s, loss=0.771, v_num=16]

Validating:   7%|▋         | 32/469 [00:01<00:16, 25.95it/s]
Epoch 0:  54%|█████▎    | 502/938 [00:33<00:29, 14.84it/s, loss=0.771, v_num=16]

Validating:   7%|▋         | 35/469 [00:01<00:16, 26.46it/s]
Epoch 0:  54%|█████▍    | 505/938 [00:33<00:29, 14.88it/s, loss=0.771, v_num=16]

Validating:   8%|▊         | 38/469 [00:01<00:16, 26.82it/s]
Epoch 0:  54%|█████▍    | 508/938 [00:34<00:28, 14.92it/s, loss=0.771, v_num=16]

Validating:   9%|▊         | 41/469 [00:01<00:16, 26.68it/s]
Epoch 0:  54%|█████▍    | 511/938 [00:34<00:28, 14.96it/s, loss=0.771, v_num=16]

Validating:   9%|▉         | 44/469 [00:01<00:16, 25.81it/s]
Epoch 0:  55%|█████▍    | 514/938 [00:34<00:28, 14.99it/s, loss=0.771, v_num=16]

Validating:  10%|█         | 47/469 [00:01<00:16, 25.80it/s]
Epoch 0:  55%|█████▌    | 517/938 [00:34<00:28, 15.03it/s, loss=0.771, v_num=16]

Validating:  11%|█         | 50/469 [00:02<00:17, 23.43it/s]
Epoch 0:  55%|█████▌    | 520/938 [00:34<00:27, 15.05it/s, loss=0.771, v_num=16]

Validating:  11%|█▏        | 53/469 [00:02<00:18, 22.19it/s]
Epoch 0:  56%|█████▌    | 523/938 [00:34<00:27, 15.07it/s, loss=0.771, v_num=16]

Validating:  12%|█▏        | 56/469 [00:02<00:18, 22.94it/s]
Epoch 0:  56%|█████▌    | 526/938 [00:34<00:27, 15.10it/s, loss=0.771, v_num=16]

Validating:  13%|█▎        | 59/469 [00:02<00:16, 24.13it/s]
Epoch 0:  56%|█████▋    | 529/938 [00:34<00:27, 15.14it/s, loss=0.771, v_num=16]

Validating:  13%|█▎        | 62/469 [00:02<00:16, 24.67it/s]
Epoch 0:  57%|█████▋    | 532/938 [00:35<00:26, 15.18it/s, loss=0.771, v_num=16]

Validating:  14%|█▍        | 65/469 [00:02<00:15, 25.50it/s]
Epoch 0:  57%|█████▋    | 535/938 [00:35<00:26, 15.22it/s, loss=0.771, v_num=16]

Validating:  14%|█▍        | 68/469 [00:02<00:15, 25.88it/s]
Epoch 0:  57%|█████▋    | 538/938 [00:35<00:26, 15.25it/s, loss=0.771, v_num=16]

Validating:  15%|█▌        | 71/469 [00:02<00:15, 26.24it/s]
Epoch 0:  58%|█████▊    | 541/938 [00:35<00:25, 15.29it/s, loss=0.771, v_num=16]

Validating:  16%|█▌        | 74/469 [00:02<00:14, 26.73it/s]
Epoch 0:  58%|█████▊    | 544/938 [00:35<00:25, 15.33it/s, loss=0.771, v_num=16]

Validating:  16%|█▋        | 77/469 [00:03<00:14, 26.33it/s]
Epoch 0:  58%|█████▊    | 547/938 [00:35<00:25, 15.36it/s, loss=0.771, v_num=16]

Validating:  17%|█▋        | 80/469 [00:03<00:15, 25.59it/s]
Epoch 0:  59%|█████▊    | 550/938 [00:35<00:25, 15.39it/s, loss=0.771, v_num=16]

Validating:  18%|█▊        | 83/469 [00:03<00:15, 25.27it/s]
Epoch 0:  59%|█████▉    | 553/938 [00:35<00:24, 15.43it/s, loss=0.771, v_num=16]

Validating:  18%|█▊        | 86/469 [00:03<00:14, 25.86it/s]
Epoch 0:  59%|█████▉    | 556/938 [00:35<00:24, 15.46it/s, loss=0.771, v_num=16]

Validating:  19%|█▉        | 89/469 [00:03<00:14, 25.48it/s]
Epoch 0:  60%|█████▉    | 559/938 [00:36<00:24, 15.49it/s, loss=0.771, v_num=16]

Validating:  20%|█▉        | 92/469 [00:03<00:14, 25.25it/s]
Epoch 0:  60%|█████▉    | 562/938 [00:36<00:24, 15.52it/s, loss=0.771, v_num=16]

Validating:  20%|██        | 95/469 [00:03<00:15, 23.81it/s]
Epoch 0:  60%|██████    | 565/938 [00:36<00:23, 15.54it/s, loss=0.771, v_num=16]

Validating:  21%|██        | 98/469 [00:03<00:16, 22.90it/s]
Epoch 0:  61%|██████    | 568/938 [00:36<00:23, 15.57it/s, loss=0.771, v_num=16]

Validating:  22%|██▏       | 101/469 [00:04<00:15, 24.05it/s]
Epoch 0:  61%|██████    | 571/938 [00:36<00:23, 15.60it/s, loss=0.771, v_num=16]

Validating:  22%|██▏       | 104/469 [00:04<00:14, 24.69it/s]
Epoch 0:  61%|██████    | 574/938 [00:36<00:23, 15.63it/s, loss=0.771, v_num=16]

Validating:  23%|██▎       | 107/469 [00:04<00:14, 24.64it/s]
Epoch 0:  62%|██████▏   | 577/938 [00:36<00:23, 15.66it/s, loss=0.771, v_num=16]

Validating:  23%|██▎       | 110/469 [00:04<00:14, 24.83it/s]
Epoch 0:  62%|██████▏   | 580/938 [00:36<00:22, 15.70it/s, loss=0.771, v_num=16]

Validating:  24%|██▍       | 113/469 [00:04<00:14, 25.29it/s]
Epoch 0:  62%|██████▏   | 583/938 [00:37<00:22, 15.73it/s, loss=0.771, v_num=16]

Validating:  25%|██▍       | 116/469 [00:04<00:13, 25.78it/s]
Epoch 0:  62%|██████▏   | 586/938 [00:37<00:22, 15.76it/s, loss=0.771, v_num=16]

Validating:  25%|██▌       | 119/469 [00:04<00:13, 25.79it/s]
Epoch 0:  63%|██████▎   | 589/938 [00:37<00:22, 15.79it/s, loss=0.771, v_num=16]

Validating:  26%|██▌       | 122/469 [00:04<00:13, 25.76it/s]
Epoch 0:  63%|██████▎   | 592/938 [00:37<00:21, 15.82it/s, loss=0.771, v_num=16]

Validating:  27%|██▋       | 125/469 [00:04<00:13, 25.59it/s]
Epoch 0:  63%|██████▎   | 595/938 [00:37<00:21, 15.85it/s, loss=0.771, v_num=16]

Validating:  27%|██▋       | 128/469 [00:05<00:13, 25.91it/s]
Epoch 0:  64%|██████▍   | 598/938 [00:37<00:21, 15.89it/s, loss=0.771, v_num=16]

Validating:  28%|██▊       | 131/469 [00:05<00:12, 26.32it/s]
Epoch 0:  64%|██████▍   | 601/938 [00:37<00:21, 15.92it/s, loss=0.771, v_num=16]

Validating:  29%|██▊       | 134/469 [00:05<00:12, 25.85it/s]
Epoch 0:  64%|██████▍   | 604/938 [00:37<00:20, 15.95it/s, loss=0.771, v_num=16]

Validating:  29%|██▉       | 137/469 [00:05<00:12, 25.97it/s]
Epoch 0:  65%|██████▍   | 607/938 [00:37<00:20, 15.98it/s, loss=0.771, v_num=16]

Validating:  30%|██▉       | 140/469 [00:05<00:13, 24.58it/s]
Epoch 0:  65%|██████▌   | 610/938 [00:38<00:20, 16.00it/s, loss=0.771, v_num=16]

Validating:  30%|███       | 143/469 [00:05<00:13, 24.84it/s]
Epoch 0:  65%|██████▌   | 613/938 [00:38<00:20, 16.03it/s, loss=0.771, v_num=16]

Validating:  31%|███       | 146/469 [00:05<00:13, 24.50it/s]
Epoch 0:  66%|██████▌   | 616/938 [00:38<00:20, 16.05it/s, loss=0.771, v_num=16]

Validating:  32%|███▏      | 149/469 [00:05<00:12, 25.51it/s]
Epoch 0:  66%|██████▌   | 619/938 [00:38<00:19, 16.09it/s, loss=0.771, v_num=16]

Validating:  32%|███▏      | 152/469 [00:06<00:12, 25.43it/s]
Epoch 0:  66%|██████▋   | 622/938 [00:38<00:19, 16.12it/s, loss=0.771, v_num=16]

Validating:  33%|███▎      | 155/469 [00:06<00:12, 25.95it/s]
Epoch 0:  67%|██████▋   | 625/938 [00:38<00:19, 16.15it/s, loss=0.771, v_num=16]

Validating:  34%|███▎      | 158/469 [00:06<00:11, 26.97it/s]
Epoch 0:  67%|██████▋   | 628/938 [00:38<00:19, 16.18it/s, loss=0.771, v_num=16]

Validating:  34%|███▍      | 161/469 [00:06<00:11, 27.13it/s]
Epoch 0:  67%|██████▋   | 631/938 [00:38<00:18, 16.21it/s, loss=0.771, v_num=16]

Validating:  35%|███▍      | 164/469 [00:06<00:11, 27.42it/s]
Epoch 0:  68%|██████▊   | 634/938 [00:39<00:18, 16.25it/s, loss=0.771, v_num=16]

Validating:  36%|███▌      | 167/469 [00:06<00:11, 27.09it/s]
Epoch 0:  68%|██████▊   | 637/938 [00:39<00:18, 16.28it/s, loss=0.771, v_num=16]

Validating:  36%|███▌      | 170/469 [00:06<00:10, 27.22it/s]
Epoch 0:  68%|██████▊   | 640/938 [00:39<00:18, 16.31it/s, loss=0.771, v_num=16]

Validating:  37%|███▋      | 173/469 [00:06<00:10, 27.76it/s]
Epoch 0:  69%|██████▊   | 643/938 [00:39<00:18, 16.34it/s, loss=0.771, v_num=16]

Validating:  38%|███▊      | 176/469 [00:06<00:10, 27.57it/s]
Epoch 0:  69%|██████▉   | 646/938 [00:39<00:17, 16.37it/s, loss=0.771, v_num=16]

Validating:  38%|███▊      | 179/469 [00:07<00:10, 27.02it/s]
Epoch 0:  69%|██████▉   | 649/938 [00:39<00:17, 16.40it/s, loss=0.771, v_num=16]

Validating:  39%|███▉      | 182/469 [00:07<00:10, 26.44it/s]
Epoch 0:  70%|██████▉   | 652/938 [00:39<00:17, 16.43it/s, loss=0.771, v_num=16]

Validating:  39%|███▉      | 185/469 [00:07<00:10, 26.43it/s]
Epoch 0:  70%|██████▉   | 655/938 [00:39<00:17, 16.45it/s, loss=0.771, v_num=16]

Validating:  40%|████      | 188/469 [00:07<00:10, 26.80it/s]
Epoch 0:  70%|███████   | 658/938 [00:39<00:16, 16.48it/s, loss=0.771, v_num=16]

Validating:  41%|████      | 191/469 [00:07<00:10, 26.56it/s]
Epoch 0:  70%|███████   | 661/938 [00:40<00:16, 16.51it/s, loss=0.771, v_num=16]

Validating:  41%|████▏     | 194/469 [00:07<00:10, 25.58it/s]
Epoch 0:  71%|███████   | 664/938 [00:40<00:16, 16.53it/s, loss=0.771, v_num=16]

Validating:  42%|████▏     | 197/469 [00:07<00:10, 26.09it/s]
Epoch 0:  71%|███████   | 667/938 [00:40<00:16, 16.56it/s, loss=0.771, v_num=16]

Validating:  43%|████▎     | 200/469 [00:07<00:10, 25.45it/s]
Epoch 0:  71%|███████▏  | 670/938 [00:40<00:16, 16.59it/s, loss=0.771, v_num=16]

Validating:  43%|████▎     | 203/469 [00:07<00:10, 25.56it/s]
Epoch 0:  72%|███████▏  | 673/938 [00:40<00:15, 16.61it/s, loss=0.771, v_num=16]

Validating:  44%|████▍     | 206/469 [00:08<00:10, 25.74it/s]
Epoch 0:  72%|███████▏  | 676/938 [00:40<00:15, 16.64it/s, loss=0.771, v_num=16]

Validating:  45%|████▍     | 209/469 [00:08<00:10, 25.85it/s]
Epoch 0:  72%|███████▏  | 679/938 [00:40<00:15, 16.67it/s, loss=0.771, v_num=16]

Validating:  45%|████▌     | 212/469 [00:08<00:09, 26.45it/s]
Epoch 0:  73%|███████▎  | 682/938 [00:40<00:15, 16.70it/s, loss=0.771, v_num=16]

Validating:  46%|████▌     | 215/469 [00:08<00:09, 25.91it/s]
Epoch 0:  73%|███████▎  | 685/938 [00:40<00:15, 16.72it/s, loss=0.771, v_num=16]

Validating:  46%|████▋     | 218/469 [00:08<00:10, 24.80it/s]
Epoch 0:  73%|███████▎  | 688/938 [00:41<00:14, 16.74it/s, loss=0.771, v_num=16]

Validating:  47%|████▋     | 221/469 [00:08<00:09, 24.90it/s]
Epoch 0:  74%|███████▎  | 691/938 [00:41<00:14, 16.76it/s, loss=0.771, v_num=16]

Validating:  48%|████▊     | 224/469 [00:08<00:09, 25.79it/s]
Epoch 0:  74%|███████▍  | 694/938 [00:41<00:14, 16.79it/s, loss=0.771, v_num=16]

Validating:  48%|████▊     | 227/469 [00:08<00:09, 25.58it/s]
Epoch 0:  74%|███████▍  | 697/938 [00:41<00:14, 16.82it/s, loss=0.771, v_num=16]

Validating:  49%|████▉     | 230/469 [00:09<00:09, 25.16it/s]
Epoch 0:  75%|███████▍  | 700/938 [00:41<00:14, 16.84it/s, loss=0.771, v_num=16]

Validating:  50%|████▉     | 233/469 [00:09<00:09, 25.90it/s]
Epoch 0:  75%|███████▍  | 703/938 [00:41<00:13, 16.87it/s, loss=0.771, v_num=16]

Validating:  50%|█████     | 236/469 [00:09<00:08, 26.28it/s]
Epoch 0:  75%|███████▌  | 706/938 [00:41<00:13, 16.90it/s, loss=0.771, v_num=16]

Validating:  51%|█████     | 239/469 [00:09<00:09, 25.19it/s]
Epoch 0:  76%|███████▌  | 709/938 [00:41<00:13, 16.91it/s, loss=0.771, v_num=16]

Validating:  52%|█████▏    | 242/469 [00:09<00:08, 25.72it/s]
Epoch 0:  76%|███████▌  | 712/938 [00:42<00:13, 16.94it/s, loss=0.771, v_num=16]

Validating:  52%|█████▏    | 245/469 [00:09<00:08, 25.45it/s]
Epoch 0:  76%|███████▌  | 715/938 [00:42<00:13, 16.96it/s, loss=0.771, v_num=16]

Validating:  53%|█████▎    | 248/469 [00:09<00:08, 24.78it/s]
Epoch 0:  77%|███████▋  | 718/938 [00:42<00:12, 16.98it/s, loss=0.771, v_num=16]

Validating:  54%|█████▎    | 251/469 [00:09<00:08, 25.96it/s]
Epoch 0:  77%|███████▋  | 721/938 [00:42<00:12, 17.01it/s, loss=0.771, v_num=16]

Validating:  54%|█████▍    | 254/469 [00:09<00:08, 25.92it/s]
Epoch 0:  77%|███████▋  | 724/938 [00:42<00:12, 17.04it/s, loss=0.771, v_num=16]

Validating:  55%|█████▍    | 257/469 [00:10<00:08, 26.26it/s]
Epoch 0:  78%|███████▊  | 727/938 [00:42<00:12, 17.06it/s, loss=0.771, v_num=16]

Validating:  55%|█████▌    | 260/469 [00:10<00:08, 25.94it/s]
Epoch 0:  78%|███████▊  | 730/938 [00:42<00:12, 17.09it/s, loss=0.771, v_num=16]

Validating:  56%|█████▌    | 263/469 [00:10<00:08, 25.64it/s]
Epoch 0:  78%|███████▊  | 733/938 [00:42<00:11, 17.11it/s, loss=0.771, v_num=16]

Validating:  57%|█████▋    | 266/469 [00:10<00:07, 25.47it/s]
Epoch 0:  78%|███████▊  | 736/938 [00:42<00:11, 17.13it/s, loss=0.771, v_num=16]

Validating:  57%|█████▋    | 269/469 [00:10<00:07, 26.17it/s]
Epoch 0:  79%|███████▉  | 739/938 [00:43<00:11, 17.16it/s, loss=0.771, v_num=16]

Validating:  58%|█████▊    | 272/469 [00:10<00:07, 26.36it/s]
Epoch 0:  79%|███████▉  | 742/938 [00:43<00:11, 17.18it/s, loss=0.771, v_num=16]

Validating:  59%|█████▊    | 275/469 [00:10<00:07, 25.28it/s]
Epoch 0:  79%|███████▉  | 745/938 [00:43<00:11, 17.20it/s, loss=0.771, v_num=16]

Validating:  59%|█████▉    | 278/469 [00:10<00:07, 25.16it/s]
Epoch 0:  80%|███████▉  | 748/938 [00:43<00:11, 17.22it/s, loss=0.771, v_num=16]

Validating:  60%|█████▉    | 281/469 [00:10<00:07, 25.90it/s]
Epoch 0:  80%|████████  | 751/938 [00:43<00:10, 17.25it/s, loss=0.771, v_num=16]

Validating:  61%|██████    | 284/469 [00:11<00:07, 25.87it/s]
Epoch 0:  80%|████████  | 754/938 [00:43<00:10, 17.27it/s, loss=0.771, v_num=16]

Validating:  61%|██████    | 287/469 [00:11<00:06, 26.29it/s]
Epoch 0:  81%|████████  | 757/938 [00:43<00:10, 17.30it/s, loss=0.771, v_num=16]

Validating:  62%|██████▏   | 290/469 [00:11<00:06, 26.45it/s]
Epoch 0:  81%|████████  | 760/938 [00:43<00:10, 17.32it/s, loss=0.771, v_num=16]

Validating:  62%|██████▏   | 293/469 [00:11<00:06, 26.02it/s]
Epoch 0:  81%|████████▏ | 763/938 [00:44<00:10, 17.34it/s, loss=0.771, v_num=16]

Validating:  63%|██████▎   | 296/469 [00:11<00:06, 26.83it/s]
Epoch 0:  82%|████████▏ | 766/938 [00:44<00:09, 17.37it/s, loss=0.771, v_num=16]

Validating:  64%|██████▍   | 299/469 [00:11<00:06, 26.10it/s]
Epoch 0:  82%|████████▏ | 769/938 [00:44<00:09, 17.39it/s, loss=0.771, v_num=16]

Validating:  64%|██████▍   | 302/469 [00:11<00:06, 25.33it/s]
Epoch 0:  82%|████████▏ | 772/938 [00:44<00:09, 17.41it/s, loss=0.771, v_num=16]

Validating:  65%|██████▌   | 305/469 [00:11<00:06, 26.39it/s]
Epoch 0:  83%|████████▎ | 775/938 [00:44<00:09, 17.43it/s, loss=0.771, v_num=16]

Validating:  66%|██████▌   | 308/469 [00:12<00:06, 26.65it/s]
Epoch 0:  83%|████████▎ | 778/938 [00:44<00:09, 17.46it/s, loss=0.771, v_num=16]

Validating:  66%|██████▋   | 311/469 [00:12<00:06, 25.81it/s]
Epoch 0:  83%|████████▎ | 781/938 [00:44<00:08, 17.48it/s, loss=0.771, v_num=16]

Validating:  67%|██████▋   | 314/469 [00:12<00:05, 26.88it/s]
Epoch 0:  84%|████████▎ | 784/938 [00:44<00:08, 17.50it/s, loss=0.771, v_num=16]

Validating:  68%|██████▊   | 317/469 [00:12<00:05, 26.59it/s]
Epoch 0:  84%|████████▍ | 787/938 [00:44<00:08, 17.52it/s, loss=0.771, v_num=16]

Validating:  68%|██████▊   | 320/469 [00:12<00:05, 27.20it/s]
Epoch 0:  84%|████████▍ | 790/938 [00:45<00:08, 17.55it/s, loss=0.771, v_num=16]

Validating:  69%|██████▉   | 323/469 [00:12<00:05, 26.93it/s]
Epoch 0:  85%|████████▍ | 793/938 [00:45<00:08, 17.57it/s, loss=0.771, v_num=16]

Validating:  70%|██████▉   | 326/469 [00:12<00:05, 27.17it/s]
Epoch 0:  85%|████████▍ | 796/938 [00:45<00:08, 17.60it/s, loss=0.771, v_num=16]

Validating:  70%|███████   | 329/469 [00:12<00:05, 26.34it/s]
Epoch 0:  85%|████████▌ | 799/938 [00:45<00:07, 17.62it/s, loss=0.771, v_num=16]

Validating:  71%|███████   | 332/469 [00:12<00:05, 25.87it/s]
Epoch 0:  86%|████████▌ | 802/938 [00:45<00:07, 17.64it/s, loss=0.771, v_num=16]

Validating:  71%|███████▏  | 335/469 [00:13<00:05, 24.74it/s]
Epoch 0:  86%|████████▌ | 805/938 [00:45<00:07, 17.65it/s, loss=0.771, v_num=16]

Validating:  72%|███████▏  | 338/469 [00:13<00:05, 24.58it/s]
Epoch 0:  86%|████████▌ | 808/938 [00:45<00:07, 17.67it/s, loss=0.771, v_num=16]

Validating:  73%|███████▎  | 341/469 [00:13<00:04, 25.63it/s]
Epoch 0:  86%|████████▋ | 811/938 [00:45<00:07, 17.69it/s, loss=0.771, v_num=16]

Validating:  73%|███████▎  | 344/469 [00:13<00:05, 24.46it/s]
Epoch 0:  87%|████████▋ | 814/938 [00:45<00:07, 17.71it/s, loss=0.771, v_num=16]

Validating:  74%|███████▍  | 347/469 [00:13<00:04, 24.41it/s]
Epoch 0:  87%|████████▋ | 817/938 [00:46<00:06, 17.72it/s, loss=0.771, v_num=16]

Validating:  75%|███████▍  | 350/469 [00:13<00:04, 24.29it/s]
Epoch 0:  87%|████████▋ | 820/938 [00:46<00:06, 17.74it/s, loss=0.771, v_num=16]

Validating:  75%|███████▌  | 353/469 [00:13<00:04, 24.81it/s]
Epoch 0:  88%|████████▊ | 823/938 [00:46<00:06, 17.76it/s, loss=0.771, v_num=16]

Validating:  76%|███████▌  | 356/469 [00:13<00:04, 25.45it/s]
Epoch 0:  88%|████████▊ | 826/938 [00:46<00:06, 17.78it/s, loss=0.771, v_num=16]

Validating:  77%|███████▋  | 359/469 [00:14<00:04, 25.03it/s]
Epoch 0:  88%|████████▊ | 829/938 [00:46<00:06, 17.80it/s, loss=0.771, v_num=16]

Validating:  77%|███████▋  | 362/469 [00:14<00:04, 25.06it/s]
Epoch 0:  89%|████████▊ | 832/938 [00:46<00:05, 17.82it/s, loss=0.771, v_num=16]

Validating:  78%|███████▊  | 365/469 [00:14<00:04, 25.25it/s]
Epoch 0:  89%|████████▉ | 835/938 [00:46<00:05, 17.84it/s, loss=0.771, v_num=16]

Validating:  78%|███████▊  | 368/469 [00:14<00:04, 24.48it/s]
Epoch 0:  89%|████████▉ | 838/938 [00:46<00:05, 17.85it/s, loss=0.771, v_num=16]

Validating:  79%|███████▉  | 371/469 [00:14<00:04, 24.08it/s]
Epoch 0:  90%|████████▉ | 841/938 [00:47<00:05, 17.87it/s, loss=0.771, v_num=16]

Validating:  80%|███████▉  | 374/469 [00:14<00:03, 24.49it/s]
Epoch 0:  90%|████████▉ | 844/938 [00:47<00:05, 17.89it/s, loss=0.771, v_num=16]

Validating:  80%|████████  | 377/469 [00:14<00:03, 24.10it/s]
Epoch 0:  90%|█████████ | 847/938 [00:47<00:05, 17.90it/s, loss=0.771, v_num=16]

Validating:  81%|████████  | 380/469 [00:14<00:03, 24.55it/s]
Epoch 0:  91%|█████████ | 850/938 [00:47<00:04, 17.92it/s, loss=0.771, v_num=16]

Validating:  82%|████████▏ | 383/469 [00:14<00:03, 25.31it/s]
Epoch 0:  91%|█████████ | 853/938 [00:47<00:04, 17.94it/s, loss=0.771, v_num=16]

Validating:  82%|████████▏ | 386/469 [00:15<00:03, 24.52it/s]
Epoch 0:  91%|█████████▏| 856/938 [00:47<00:04, 17.95it/s, loss=0.771, v_num=16]

Validating:  83%|████████▎ | 389/469 [00:15<00:03, 24.52it/s]
Epoch 0:  92%|█████████▏| 859/938 [00:47<00:04, 17.97it/s, loss=0.771, v_num=16]

Validating:  84%|████████▎ | 392/469 [00:15<00:03, 25.30it/s]
Epoch 0:  92%|█████████▏| 862/938 [00:47<00:04, 17.99it/s, loss=0.771, v_num=16]

Validating:  84%|████████▍ | 395/469 [00:15<00:02, 25.35it/s]
Epoch 0:  92%|█████████▏| 865/938 [00:48<00:04, 18.01it/s, loss=0.771, v_num=16]

Validating:  85%|████████▍ | 398/469 [00:15<00:02, 25.73it/s]
Epoch 0:  93%|█████████▎| 868/938 [00:48<00:03, 18.03it/s, loss=0.771, v_num=16]

Validating:  86%|████████▌ | 401/469 [00:15<00:02, 25.52it/s]
Epoch 0:  93%|█████████▎| 871/938 [00:48<00:03, 18.05it/s, loss=0.771, v_num=16]

Validating:  86%|████████▌ | 404/469 [00:15<00:02, 25.21it/s]
Epoch 0:  93%|█████████▎| 874/938 [00:48<00:03, 18.07it/s, loss=0.771, v_num=16]

Validating:  87%|████████▋ | 407/469 [00:15<00:02, 25.66it/s]
Epoch 0:  93%|█████████▎| 877/938 [00:48<00:03, 18.09it/s, loss=0.771, v_num=16]

Validating:  87%|████████▋ | 410/469 [00:16<00:02, 25.44it/s]
Epoch 0:  94%|█████████▍| 880/938 [00:48<00:03, 18.10it/s, loss=0.771, v_num=16]

Validating:  88%|████████▊ | 413/469 [00:16<00:02, 25.21it/s]
Epoch 0:  94%|█████████▍| 883/938 [00:48<00:03, 18.12it/s, loss=0.771, v_num=16]

Validating:  89%|████████▊ | 416/469 [00:16<00:02, 24.74it/s]
Epoch 0:  94%|█████████▍| 886/938 [00:48<00:02, 18.13it/s, loss=0.771, v_num=16]

Validating:  89%|████████▉ | 419/469 [00:16<00:01, 25.54it/s]
Epoch 0:  95%|█████████▍| 889/938 [00:48<00:02, 18.15it/s, loss=0.771, v_num=16]

Validating:  90%|████████▉ | 422/469 [00:16<00:01, 26.01it/s]
Epoch 0:  95%|█████████▌| 892/938 [00:49<00:02, 18.17it/s, loss=0.771, v_num=16]

Validating:  91%|█████████ | 425/469 [00:16<00:01, 26.15it/s]
Epoch 0:  95%|█████████▌| 895/938 [00:49<00:02, 18.19it/s, loss=0.771, v_num=16]

Validating:  91%|█████████▏| 428/469 [00:16<00:01, 25.11it/s]
Epoch 0:  96%|█████████▌| 898/938 [00:49<00:02, 18.21it/s, loss=0.771, v_num=16]

Validating:  92%|█████████▏| 431/469 [00:16<00:01, 25.55it/s]
Epoch 0:  96%|█████████▌| 901/938 [00:49<00:02, 18.23it/s, loss=0.771, v_num=16]

Validating:  93%|█████████▎| 434/469 [00:17<00:01, 24.55it/s]
Epoch 0:  96%|█████████▋| 904/938 [00:49<00:01, 18.24it/s, loss=0.771, v_num=16]

Validating:  93%|█████████▎| 437/469 [00:17<00:01, 25.46it/s]
Epoch 0:  97%|█████████▋| 907/938 [00:49<00:01, 18.26it/s, loss=0.771, v_num=16]

Validating:  94%|█████████▍| 440/469 [00:17<00:01, 26.21it/s]
Epoch 0:  97%|█████████▋| 910/938 [00:49<00:01, 18.28it/s, loss=0.771, v_num=16]

Validating:  94%|█████████▍| 443/469 [00:17<00:00, 26.63it/s]
Epoch 0:  97%|█████████▋| 913/938 [00:49<00:01, 18.30it/s, loss=0.771, v_num=16]

Validating:  95%|█████████▌| 446/469 [00:17<00:00, 26.09it/s]
Epoch 0:  98%|█████████▊| 916/938 [00:50<00:01, 18.32it/s, loss=0.771, v_num=16]

Validating:  96%|█████████▌| 449/469 [00:17<00:00, 26.34it/s]
Epoch 0:  98%|█████████▊| 919/938 [00:50<00:01, 18.33it/s, loss=0.771, v_num=16]

Validating:  96%|█████████▋| 452/469 [00:17<00:00, 24.92it/s]
Epoch 0:  98%|█████████▊| 922/938 [00:50<00:00, 18.34it/s, loss=0.771, v_num=16]

Validating:  97%|█████████▋| 455/469 [00:17<00:00, 24.71it/s]
Epoch 0:  99%|█████████▊| 925/938 [00:50<00:00, 18.36it/s, loss=0.771, v_num=16]

Validating:  98%|█████████▊| 458/469 [00:17<00:00, 24.26it/s]
Epoch 0:  99%|█████████▉| 928/938 [00:50<00:00, 18.37it/s, loss=0.771, v_num=16]

Validating:  98%|█████████▊| 461/469 [00:18<00:00, 24.62it/s]
Epoch 0:  99%|█████████▉| 931/938 [00:50<00:00, 18.39it/s, loss=0.771, v_num=16]

Validating:  99%|█████████▉| 464/469 [00:18<00:00, 24.78it/s]
Epoch 0: 100%|█████████▉| 934/938 [00:50<00:00, 18.40it/s, loss=0.771, v_num=16]

Validating: 100%|█████████▉| 467/469 [00:18<00:00, 25.26it/s]
Epoch 0: 100%|█████████▉| 937/938 [00:50<00:00, 18.42it/s, loss=0.771, v_num=16]
Epoch 0: 100%|██████████| 938/938 [00:50<00:00, 18.42it/s, loss=0.771, v_num=16, val_rmse=0.654]

                                                             
Epoch 0: 100%|██████████| 938/938 [00:50<00:00, 18.41it/s, loss=0.771, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 0:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.771, v_num=16, val_rmse=0.654, train_rmse=1.190]          
Epoch 1:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.771, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   0%|          | 1/938 [00:00<01:23, 11.23it/s, loss=0.774, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   0%|          | 2/938 [00:00<01:13, 12.73it/s, loss=0.767, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   0%|          | 3/938 [00:00<01:06, 14.08it/s, loss=0.767, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   0%|          | 3/938 [00:00<01:06, 14.05it/s, loss=0.767, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   0%|          | 4/938 [00:00<01:07, 13.92it/s, loss=0.762, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   1%|          | 5/938 [00:00<01:03, 14.75it/s, loss=0.759, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   1%|          | 6/938 [00:00<01:02, 14.83it/s, loss=0.759, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   1%|          | 6/938 [00:00<01:02, 14.81it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   1%|          | 7/938 [00:00<01:02, 14.81it/s, loss=0.753, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   1%|          | 8/938 [00:00<01:03, 14.76it/s, loss=0.754, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   1%|          | 9/938 [00:00<01:02, 14.76it/s, loss=0.754, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   1%|          | 9/938 [00:00<01:03, 14.74it/s, loss=0.756, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   1%|          | 10/938 [00:00<01:03, 14.57it/s, loss=0.756, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   1%|          | 11/938 [00:00<01:03, 14.62it/s, loss=0.75, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:   1%|▏         | 12/938 [00:00<01:03, 14.58it/s, loss=0.75, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   1%|▏         | 12/938 [00:00<01:03, 14.57it/s, loss=0.741, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   1%|▏         | 13/938 [00:00<01:03, 14.64it/s, loss=0.732, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   1%|▏         | 14/938 [00:00<01:02, 14.75it/s, loss=0.721, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   2%|▏         | 15/938 [00:01<01:02, 14.76it/s, loss=0.721, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   2%|▏         | 15/938 [00:01<01:02, 14.75it/s, loss=0.721, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   2%|▏         | 16/938 [00:01<01:01, 14.87it/s, loss=0.72, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:   2%|▏         | 17/938 [00:01<01:01, 14.95it/s, loss=0.716, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   2%|▏         | 18/938 [00:01<01:01, 14.91it/s, loss=0.716, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   2%|▏         | 18/938 [00:01<01:01, 14.90it/s, loss=0.717, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   2%|▏         | 19/938 [00:01<01:01, 14.93it/s, loss=0.722, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   2%|▏         | 20/938 [00:01<01:01, 14.89it/s, loss=0.718, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   2%|▏         | 21/938 [00:01<01:01, 14.94it/s, loss=0.718, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   2%|▏         | 21/938 [00:01<01:01, 14.94it/s, loss=0.72, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:   2%|▏         | 22/938 [00:01<01:01, 14.92it/s, loss=0.729, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   2%|▏         | 23/938 [00:01<01:01, 14.95it/s, loss=0.732, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   3%|▎         | 24/938 [00:01<01:01, 14.87it/s, loss=0.732, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   3%|▎         | 24/938 [00:01<01:01, 14.86it/s, loss=0.726, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   3%|▎         | 25/938 [00:01<01:02, 14.70it/s, loss=0.732, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   3%|▎         | 26/938 [00:01<01:02, 14.57it/s, loss=0.737, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   3%|▎         | 27/938 [00:01<01:02, 14.47it/s, loss=0.737, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   3%|▎         | 27/938 [00:01<01:02, 14.47it/s, loss=0.722, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   3%|▎         | 28/938 [00:01<01:02, 14.49it/s, loss=0.719, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   3%|▎         | 29/938 [00:01<01:02, 14.51it/s, loss=0.717, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   3%|▎         | 30/938 [00:02<01:02, 14.53it/s, loss=0.717, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   3%|▎         | 30/938 [00:02<01:02, 14.53it/s, loss=0.708, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   3%|▎         | 31/938 [00:02<01:02, 14.52it/s, loss=0.705, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   3%|▎         | 32/938 [00:02<01:02, 14.47it/s, loss=0.709, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   4%|▎         | 33/938 [00:02<01:02, 14.46it/s, loss=0.709, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   4%|▎         | 33/938 [00:02<01:02, 14.46it/s, loss=0.726, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   4%|▎         | 34/938 [00:02<01:02, 14.44it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   4%|▎         | 35/938 [00:02<01:02, 14.46it/s, loss=0.742, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   4%|▍         | 36/938 [00:02<01:02, 14.46it/s, loss=0.742, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   4%|▍         | 36/938 [00:02<01:02, 14.46it/s, loss=0.741, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   4%|▍         | 37/938 [00:02<01:02, 14.40it/s, loss=0.743, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   4%|▍         | 38/938 [00:02<01:02, 14.36it/s, loss=0.743, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   4%|▍         | 39/938 [00:02<01:02, 14.33it/s, loss=0.743, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   4%|▍         | 39/938 [00:02<01:02, 14.32it/s, loss=0.743, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   4%|▍         | 40/938 [00:02<01:02, 14.37it/s, loss=0.756, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   4%|▍         | 41/938 [00:02<01:02, 14.40it/s, loss=0.754, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   4%|▍         | 42/938 [00:02<01:02, 14.41it/s, loss=0.754, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   4%|▍         | 42/938 [00:02<01:02, 14.41it/s, loss=0.757, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   5%|▍         | 43/938 [00:02<01:02, 14.42it/s, loss=0.75, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:   5%|▍         | 44/938 [00:03<01:02, 14.37it/s, loss=0.754, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   5%|▍         | 45/938 [00:03<01:02, 14.33it/s, loss=0.754, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   5%|▍         | 45/938 [00:03<01:02, 14.33it/s, loss=0.756, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   5%|▍         | 46/938 [00:03<01:02, 14.29it/s, loss=0.751, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   5%|▌         | 47/938 [00:03<01:02, 14.28it/s, loss=0.752, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   5%|▌         | 48/938 [00:03<01:02, 14.22it/s, loss=0.752, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   5%|▌         | 48/938 [00:03<01:02, 14.22it/s, loss=0.754, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   5%|▌         | 49/938 [00:03<01:02, 14.26it/s, loss=0.746, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   5%|▌         | 50/938 [00:03<01:02, 14.24it/s, loss=0.754, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   5%|▌         | 51/938 [00:03<01:02, 14.19it/s, loss=0.754, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   5%|▌         | 51/938 [00:03<01:02, 14.18it/s, loss=0.76, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:   6%|▌         | 52/938 [00:03<01:02, 14.22it/s, loss=0.767, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   6%|▌         | 53/938 [00:03<01:02, 14.15it/s, loss=0.754, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   6%|▌         | 54/938 [00:03<01:02, 14.11it/s, loss=0.754, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   6%|▌         | 54/938 [00:03<01:02, 14.11it/s, loss=0.736, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   6%|▌         | 55/938 [00:03<01:02, 14.09it/s, loss=0.743, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   6%|▌         | 56/938 [00:03<01:02, 14.15it/s, loss=0.75, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:   6%|▌         | 57/938 [00:04<01:02, 14.15it/s, loss=0.75, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   6%|▌         | 57/938 [00:04<01:02, 14.15it/s, loss=0.753, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   6%|▌         | 58/938 [00:04<01:02, 14.15it/s, loss=0.755, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   6%|▋         | 59/938 [00:04<01:02, 14.11it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   6%|▋         | 60/938 [00:04<01:02, 14.10it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   6%|▋         | 60/938 [00:04<01:02, 14.09it/s, loss=0.732, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   7%|▋         | 61/938 [00:04<01:02, 14.08it/s, loss=0.736, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   7%|▋         | 62/938 [00:04<01:02, 14.11it/s, loss=0.731, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   7%|▋         | 63/938 [00:04<01:02, 14.03it/s, loss=0.731, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   7%|▋         | 63/938 [00:04<01:02, 14.03it/s, loss=0.74, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:   7%|▋         | 64/938 [00:04<01:02, 14.07it/s, loss=0.745, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   7%|▋         | 65/938 [00:04<01:02, 14.04it/s, loss=0.74, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:   7%|▋         | 66/938 [00:04<01:02, 14.05it/s, loss=0.74, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   7%|▋         | 66/938 [00:04<01:02, 14.05it/s, loss=0.746, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   7%|▋         | 67/938 [00:04<01:02, 14.05it/s, loss=0.744, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   7%|▋         | 68/938 [00:04<01:01, 14.07it/s, loss=0.742, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   7%|▋         | 69/938 [00:04<01:01, 14.04it/s, loss=0.742, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   7%|▋         | 69/938 [00:04<01:01, 14.04it/s, loss=0.752, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   7%|▋         | 70/938 [00:04<01:01, 14.07it/s, loss=0.754, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   8%|▊         | 71/938 [00:05<01:01, 14.04it/s, loss=0.747, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   8%|▊         | 72/938 [00:05<01:01, 14.06it/s, loss=0.747, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   8%|▊         | 72/938 [00:05<01:01, 14.06it/s, loss=0.737, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   8%|▊         | 73/938 [00:05<01:01, 14.01it/s, loss=0.733, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   8%|▊         | 74/938 [00:05<01:01, 13.99it/s, loss=0.737, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   8%|▊         | 75/938 [00:05<01:01, 13.95it/s, loss=0.737, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   8%|▊         | 75/938 [00:05<01:01, 13.95it/s, loss=0.731, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   8%|▊         | 76/938 [00:05<01:01, 13.98it/s, loss=0.734, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   8%|▊         | 77/938 [00:05<01:01, 13.98it/s, loss=0.728, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   8%|▊         | 78/938 [00:05<01:01, 13.99it/s, loss=0.728, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   8%|▊         | 78/938 [00:05<01:01, 13.99it/s, loss=0.73, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:   8%|▊         | 79/938 [00:05<01:01, 14.01it/s, loss=0.732, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   9%|▊         | 80/938 [00:05<01:01, 14.01it/s, loss=0.741, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   9%|▊         | 81/938 [00:05<01:01, 14.01it/s, loss=0.741, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   9%|▊         | 81/938 [00:05<01:01, 14.01it/s, loss=0.742, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   9%|▊         | 82/938 [00:05<01:01, 13.99it/s, loss=0.746, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   9%|▉         | 83/938 [00:05<01:00, 14.03it/s, loss=0.735, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   9%|▉         | 84/938 [00:05<01:00, 14.06it/s, loss=0.735, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   9%|▉         | 84/938 [00:05<01:00, 14.06it/s, loss=0.73, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:   9%|▉         | 85/938 [00:06<01:00, 14.06it/s, loss=0.723, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   9%|▉         | 86/938 [00:06<01:00, 14.05it/s, loss=0.723, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   9%|▉         | 87/938 [00:06<01:00, 14.07it/s, loss=0.723, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   9%|▉         | 87/938 [00:06<01:00, 14.07it/s, loss=0.721, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   9%|▉         | 88/938 [00:06<01:00, 14.07it/s, loss=0.722, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:   9%|▉         | 89/938 [00:06<01:00, 14.05it/s, loss=0.724, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  10%|▉         | 90/938 [00:06<01:00, 14.05it/s, loss=0.724, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  10%|▉         | 90/938 [00:06<01:00, 14.05it/s, loss=0.719, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  10%|▉         | 91/938 [00:06<01:00, 14.03it/s, loss=0.715, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  10%|▉         | 92/938 [00:06<01:00, 14.04it/s, loss=0.726, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  10%|▉         | 93/938 [00:06<01:00, 14.06it/s, loss=0.726, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  10%|▉         | 93/938 [00:06<01:00, 14.05it/s, loss=0.73, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  10%|█         | 94/938 [00:06<01:00, 14.06it/s, loss=0.729, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  10%|█         | 95/938 [00:06<00:59, 14.09it/s, loss=0.733, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  10%|█         | 96/938 [00:06<00:59, 14.09it/s, loss=0.733, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  10%|█         | 96/938 [00:06<00:59, 14.09it/s, loss=0.726, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  10%|█         | 97/938 [00:06<00:59, 14.13it/s, loss=0.731, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  10%|█         | 98/938 [00:06<00:59, 14.13it/s, loss=0.721, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  11%|█         | 99/938 [00:07<00:59, 14.12it/s, loss=0.721, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  11%|█         | 99/938 [00:07<00:59, 14.12it/s, loss=0.726, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  11%|█         | 100/938 [00:07<00:59, 14.16it/s, loss=0.72, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  11%|█         | 101/938 [00:07<00:59, 14.14it/s, loss=0.71, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  11%|█         | 102/938 [00:07<00:59, 14.15it/s, loss=0.71, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  11%|█         | 102/938 [00:07<00:59, 14.15it/s, loss=0.708, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  11%|█         | 103/938 [00:07<00:58, 14.16it/s, loss=0.714, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  11%|█         | 104/938 [00:07<00:58, 14.14it/s, loss=0.72, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  11%|█         | 105/938 [00:07<00:58, 14.16it/s, loss=0.72, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  11%|█         | 105/938 [00:07<00:58, 14.16it/s, loss=0.715, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  11%|█▏        | 106/938 [00:07<00:58, 14.15it/s, loss=0.712, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  11%|█▏        | 107/938 [00:07<00:58, 14.11it/s, loss=0.717, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  12%|█▏        | 108/938 [00:07<00:58, 14.12it/s, loss=0.717, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  12%|█▏        | 108/938 [00:07<00:58, 14.12it/s, loss=0.715, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  12%|█▏        | 109/938 [00:07<00:58, 14.13it/s, loss=0.705, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  12%|█▏        | 110/938 [00:07<00:58, 14.09it/s, loss=0.706, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  12%|█▏        | 111/938 [00:07<00:58, 14.11it/s, loss=0.706, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  12%|█▏        | 111/938 [00:07<00:58, 14.11it/s, loss=0.718, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  12%|█▏        | 112/938 [00:07<00:58, 14.12it/s, loss=0.719, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  12%|█▏        | 113/938 [00:08<00:58, 14.11it/s, loss=0.728, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  12%|█▏        | 114/938 [00:08<00:58, 14.11it/s, loss=0.728, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  12%|█▏        | 114/938 [00:08<00:58, 14.11it/s, loss=0.728, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  12%|█▏        | 115/938 [00:08<00:58, 14.11it/s, loss=0.732, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  12%|█▏        | 116/938 [00:08<00:58, 14.01it/s, loss=0.73, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  12%|█▏        | 117/938 [00:08<00:58, 14.00it/s, loss=0.73, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  12%|█▏        | 117/938 [00:08<00:58, 14.00it/s, loss=0.721, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  13%|█▎        | 118/938 [00:08<00:58, 14.00it/s, loss=0.73, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  13%|█▎        | 119/938 [00:08<00:58, 13.97it/s, loss=0.73, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  13%|█▎        | 120/938 [00:08<00:58, 13.99it/s, loss=0.73, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  13%|█▎        | 120/938 [00:08<00:58, 13.98it/s, loss=0.735, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  13%|█▎        | 121/938 [00:08<00:58, 14.00it/s, loss=0.738, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  13%|█▎        | 122/938 [00:08<00:58, 14.00it/s, loss=0.73, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  13%|█▎        | 123/938 [00:08<00:58, 14.02it/s, loss=0.73, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  13%|█▎        | 123/938 [00:08<00:58, 14.02it/s, loss=0.728, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  13%|█▎        | 124/938 [00:08<00:58, 14.02it/s, loss=0.728, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  13%|█▎        | 125/938 [00:08<00:57, 14.04it/s, loss=0.733, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  13%|█▎        | 126/938 [00:08<00:57, 14.05it/s, loss=0.733, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  13%|█▎        | 126/938 [00:08<00:57, 14.05it/s, loss=0.734, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  14%|█▎        | 127/938 [00:09<00:57, 14.07it/s, loss=0.732, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  14%|█▎        | 128/938 [00:09<00:57, 14.09it/s, loss=0.739, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  14%|█▍        | 129/938 [00:09<00:57, 14.07it/s, loss=0.739, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  14%|█▍        | 129/938 [00:09<00:57, 14.07it/s, loss=0.743, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  14%|█▍        | 130/938 [00:09<00:57, 14.06it/s, loss=0.738, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  14%|█▍        | 131/938 [00:09<00:57, 14.06it/s, loss=0.734, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  14%|█▍        | 132/938 [00:09<00:57, 14.07it/s, loss=0.734, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  14%|█▍        | 132/938 [00:09<00:57, 14.07it/s, loss=0.727, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  14%|█▍        | 133/938 [00:09<00:57, 14.08it/s, loss=0.726, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  14%|█▍        | 134/938 [00:09<00:57, 14.06it/s, loss=0.73, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  14%|█▍        | 135/938 [00:09<00:57, 14.06it/s, loss=0.73, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  14%|█▍        | 135/938 [00:09<00:57, 14.06it/s, loss=0.725, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  14%|█▍        | 136/938 [00:09<00:57, 14.06it/s, loss=0.738, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  15%|█▍        | 137/938 [00:09<00:56, 14.08it/s, loss=0.741, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  15%|█▍        | 138/938 [00:09<00:56, 14.06it/s, loss=0.741, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  15%|█▍        | 138/938 [00:09<00:56, 14.06it/s, loss=0.742, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  15%|█▍        | 139/938 [00:09<00:56, 14.07it/s, loss=0.735, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  15%|█▍        | 140/938 [00:09<00:56, 14.06it/s, loss=0.735, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  15%|█▌        | 141/938 [00:10<00:56, 14.08it/s, loss=0.735, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  15%|█▌        | 141/938 [00:10<00:56, 14.08it/s, loss=0.746, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  15%|█▌        | 142/938 [00:10<00:56, 14.08it/s, loss=0.752, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  15%|█▌        | 143/938 [00:10<00:56, 14.08it/s, loss=0.741, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  15%|█▌        | 144/938 [00:10<00:56, 14.08it/s, loss=0.741, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  15%|█▌        | 144/938 [00:10<00:56, 14.08it/s, loss=0.737, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  15%|█▌        | 145/938 [00:10<00:56, 14.07it/s, loss=0.742, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  16%|█▌        | 146/938 [00:10<00:56, 14.08it/s, loss=0.754, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  16%|█▌        | 147/938 [00:10<00:56, 14.08it/s, loss=0.754, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  16%|█▌        | 147/938 [00:10<00:56, 14.07it/s, loss=0.756, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  16%|█▌        | 148/938 [00:10<00:56, 14.07it/s, loss=0.755, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  16%|█▌        | 149/938 [00:10<00:56, 14.08it/s, loss=0.766, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  16%|█▌        | 150/938 [00:10<00:55, 14.08it/s, loss=0.766, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  16%|█▌        | 150/938 [00:10<00:55, 14.08it/s, loss=0.772, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  16%|█▌        | 151/938 [00:10<00:55, 14.09it/s, loss=0.772, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  16%|█▌        | 152/938 [00:10<00:55, 14.10it/s, loss=0.777, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  16%|█▋        | 153/938 [00:10<00:55, 14.11it/s, loss=0.777, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  16%|█▋        | 153/938 [00:10<00:55, 14.11it/s, loss=0.774, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  16%|█▋        | 154/938 [00:10<00:55, 14.09it/s, loss=0.772, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  17%|█▋        | 155/938 [00:10<00:55, 14.09it/s, loss=0.768, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  17%|█▋        | 156/938 [00:11<00:55, 14.08it/s, loss=0.768, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  17%|█▋        | 156/938 [00:11<00:55, 14.08it/s, loss=0.754, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  17%|█▋        | 157/938 [00:11<00:55, 14.02it/s, loss=0.765, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  17%|█▋        | 158/938 [00:11<00:55, 14.01it/s, loss=0.762, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  17%|█▋        | 159/938 [00:11<00:55, 14.02it/s, loss=0.762, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  17%|█▋        | 159/938 [00:11<00:55, 14.02it/s, loss=0.769, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  17%|█▋        | 160/938 [00:11<00:55, 13.95it/s, loss=0.776, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  17%|█▋        | 161/938 [00:11<00:55, 13.92it/s, loss=0.761, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  17%|█▋        | 162/938 [00:11<00:55, 13.93it/s, loss=0.761, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  17%|█▋        | 162/938 [00:11<00:55, 13.93it/s, loss=0.762, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  17%|█▋        | 163/938 [00:11<00:55, 13.93it/s, loss=0.773, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  17%|█▋        | 164/938 [00:11<00:55, 13.94it/s, loss=0.772, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  18%|█▊        | 165/938 [00:11<00:55, 13.95it/s, loss=0.772, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  18%|█▊        | 165/938 [00:11<00:55, 13.95it/s, loss=0.764, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  18%|█▊        | 166/938 [00:11<00:55, 13.97it/s, loss=0.753, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  18%|█▊        | 167/938 [00:11<00:55, 13.97it/s, loss=0.753, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  18%|█▊        | 168/938 [00:12<00:55, 13.95it/s, loss=0.753, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  18%|█▊        | 168/938 [00:12<00:55, 13.95it/s, loss=0.755, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  18%|█▊        | 169/938 [00:12<00:55, 13.96it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  18%|█▊        | 170/938 [00:12<00:55, 13.93it/s, loss=0.744, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  18%|█▊        | 171/938 [00:12<00:55, 13.93it/s, loss=0.744, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  18%|█▊        | 171/938 [00:12<00:55, 13.93it/s, loss=0.752, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  18%|█▊        | 172/938 [00:12<00:54, 13.96it/s, loss=0.745, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  18%|█▊        | 173/938 [00:12<00:54, 13.95it/s, loss=0.743, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  19%|█▊        | 174/938 [00:12<00:54, 13.95it/s, loss=0.743, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  19%|█▊        | 174/938 [00:12<00:54, 13.95it/s, loss=0.745, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  19%|█▊        | 175/938 [00:12<00:54, 13.95it/s, loss=0.74, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  19%|█▉        | 176/938 [00:12<00:54, 13.94it/s, loss=0.753, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  19%|█▉        | 177/938 [00:12<00:54, 13.95it/s, loss=0.753, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  19%|█▉        | 177/938 [00:12<00:54, 13.95it/s, loss=0.752, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  19%|█▉        | 178/938 [00:12<00:54, 13.95it/s, loss=0.752, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  19%|█▉        | 179/938 [00:12<00:54, 13.98it/s, loss=0.755, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  19%|█▉        | 180/938 [00:12<00:54, 13.99it/s, loss=0.755, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  19%|█▉        | 180/938 [00:12<00:54, 13.98it/s, loss=0.753, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  19%|█▉        | 181/938 [00:12<00:54, 13.98it/s, loss=0.756, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  19%|█▉        | 182/938 [00:13<00:54, 13.99it/s, loss=0.759, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  20%|█▉        | 183/938 [00:13<00:53, 14.00it/s, loss=0.759, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  20%|█▉        | 183/938 [00:13<00:53, 13.99it/s, loss=0.763, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  20%|█▉        | 184/938 [00:13<00:53, 13.99it/s, loss=0.765, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  20%|█▉        | 185/938 [00:13<00:53, 13.99it/s, loss=0.772, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  20%|█▉        | 186/938 [00:13<00:53, 14.01it/s, loss=0.772, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  20%|█▉        | 186/938 [00:13<00:53, 14.01it/s, loss=0.77, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  20%|█▉        | 187/938 [00:13<00:53, 14.01it/s, loss=0.762, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  20%|██        | 188/938 [00:13<00:53, 14.00it/s, loss=0.755, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  20%|██        | 189/938 [00:13<00:53, 14.02it/s, loss=0.755, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  20%|██        | 189/938 [00:13<00:53, 14.02it/s, loss=0.752, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  20%|██        | 190/938 [00:13<00:53, 14.02it/s, loss=0.756, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  20%|██        | 191/938 [00:13<00:53, 14.02it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  20%|██        | 192/938 [00:13<00:53, 14.01it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  20%|██        | 192/938 [00:13<00:53, 14.01it/s, loss=0.753, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  21%|██        | 193/938 [00:13<00:53, 14.00it/s, loss=0.759, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  21%|██        | 194/938 [00:13<00:53, 13.99it/s, loss=0.761, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  21%|██        | 195/938 [00:13<00:53, 14.01it/s, loss=0.761, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  21%|██        | 195/938 [00:13<00:53, 14.01it/s, loss=0.769, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  21%|██        | 196/938 [00:13<00:52, 14.01it/s, loss=0.761, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  21%|██        | 197/938 [00:14<00:52, 14.01it/s, loss=0.753, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  21%|██        | 198/938 [00:14<00:52, 14.01it/s, loss=0.753, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  21%|██        | 198/938 [00:14<00:52, 14.00it/s, loss=0.752, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  21%|██        | 199/938 [00:14<00:52, 14.00it/s, loss=0.751, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  21%|██▏       | 200/938 [00:14<00:52, 14.00it/s, loss=0.739, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  21%|██▏       | 201/938 [00:14<00:52, 14.00it/s, loss=0.739, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  21%|██▏       | 201/938 [00:14<00:52, 14.00it/s, loss=0.742, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  22%|██▏       | 202/938 [00:14<00:52, 14.00it/s, loss=0.742, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  22%|██▏       | 203/938 [00:14<00:52, 14.00it/s, loss=0.739, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  22%|██▏       | 204/938 [00:14<00:52, 14.01it/s, loss=0.739, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  22%|██▏       | 204/938 [00:14<00:52, 14.01it/s, loss=0.731, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  22%|██▏       | 205/938 [00:14<00:52, 14.01it/s, loss=0.728, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  22%|██▏       | 206/938 [00:14<00:52, 14.02it/s, loss=0.734, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  22%|██▏       | 207/938 [00:14<00:52, 14.02it/s, loss=0.734, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  22%|██▏       | 207/938 [00:14<00:52, 14.02it/s, loss=0.744, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  22%|██▏       | 208/938 [00:14<00:52, 14.02it/s, loss=0.75, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  22%|██▏       | 209/938 [00:14<00:51, 14.03it/s, loss=0.744, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  22%|██▏       | 210/938 [00:15<00:52, 13.99it/s, loss=0.744, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  22%|██▏       | 210/938 [00:15<00:52, 13.99it/s, loss=0.753, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  22%|██▏       | 211/938 [00:15<00:51, 13.99it/s, loss=0.754, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  23%|██▎       | 212/938 [00:15<00:51, 13.99it/s, loss=0.75, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  23%|██▎       | 213/938 [00:15<00:51, 13.97it/s, loss=0.75, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  23%|██▎       | 213/938 [00:15<00:51, 13.97it/s, loss=0.744, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  23%|██▎       | 214/938 [00:15<00:51, 13.98it/s, loss=0.735, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  23%|██▎       | 215/938 [00:15<00:51, 13.99it/s, loss=0.728, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  23%|██▎       | 216/938 [00:15<00:51, 13.99it/s, loss=0.728, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  23%|██▎       | 216/938 [00:15<00:51, 13.99it/s, loss=0.723, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  23%|██▎       | 217/938 [00:15<00:51, 13.99it/s, loss=0.736, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  23%|██▎       | 218/938 [00:15<00:51, 13.98it/s, loss=0.747, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  23%|██▎       | 219/938 [00:15<00:51, 13.99it/s, loss=0.747, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  23%|██▎       | 219/938 [00:15<00:51, 13.99it/s, loss=0.743, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  23%|██▎       | 220/938 [00:15<00:51, 14.00it/s, loss=0.744, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  24%|██▎       | 221/938 [00:15<00:51, 13.99it/s, loss=0.747, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  24%|██▎       | 222/938 [00:15<00:51, 13.99it/s, loss=0.747, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  24%|██▎       | 222/938 [00:15<00:51, 13.99it/s, loss=0.743, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  24%|██▍       | 223/938 [00:15<00:51, 13.99it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  24%|██▍       | 224/938 [00:16<00:51, 14.00it/s, loss=0.763, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  24%|██▍       | 225/938 [00:16<00:50, 13.99it/s, loss=0.763, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  24%|██▍       | 225/938 [00:16<00:50, 13.99it/s, loss=0.769, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  24%|██▍       | 226/938 [00:16<00:50, 14.00it/s, loss=0.767, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  24%|██▍       | 227/938 [00:16<00:50, 14.01it/s, loss=0.76, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  24%|██▍       | 228/938 [00:16<00:50, 14.01it/s, loss=0.76, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  24%|██▍       | 228/938 [00:16<00:50, 14.01it/s, loss=0.761, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  24%|██▍       | 229/938 [00:16<00:50, 14.02it/s, loss=0.763, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  25%|██▍       | 230/938 [00:16<00:50, 14.02it/s, loss=0.75, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  25%|██▍       | 231/938 [00:16<00:50, 14.02it/s, loss=0.75, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  25%|██▍       | 231/938 [00:16<00:50, 14.02it/s, loss=0.743, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  25%|██▍       | 232/938 [00:16<00:50, 14.02it/s, loss=0.743, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  25%|██▍       | 233/938 [00:16<00:50, 14.02it/s, loss=0.747, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  25%|██▍       | 234/938 [00:16<00:50, 14.01it/s, loss=0.747, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  25%|██▍       | 234/938 [00:16<00:50, 14.01it/s, loss=0.754, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  25%|██▌       | 235/938 [00:16<00:50, 14.01it/s, loss=0.764, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  25%|██▌       | 236/938 [00:16<00:50, 14.01it/s, loss=0.765, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  25%|██▌       | 237/938 [00:16<00:50, 14.01it/s, loss=0.765, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  25%|██▌       | 237/938 [00:16<00:50, 14.01it/s, loss=0.753, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  25%|██▌       | 238/938 [00:16<00:49, 14.00it/s, loss=0.732, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  25%|██▌       | 239/938 [00:17<00:50, 13.97it/s, loss=0.734, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  26%|██▌       | 240/938 [00:17<00:49, 13.98it/s, loss=0.734, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  26%|██▌       | 240/938 [00:17<00:49, 13.98it/s, loss=0.746, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  26%|██▌       | 241/938 [00:17<00:49, 13.98it/s, loss=0.742, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  26%|██▌       | 242/938 [00:17<00:49, 13.98it/s, loss=0.747, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  26%|██▌       | 243/938 [00:17<00:49, 13.97it/s, loss=0.747, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  26%|██▌       | 243/938 [00:17<00:49, 13.97it/s, loss=0.742, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  26%|██▌       | 244/938 [00:17<00:49, 13.98it/s, loss=0.733, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  26%|██▌       | 245/938 [00:17<00:49, 13.97it/s, loss=0.725, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  26%|██▌       | 246/938 [00:17<00:49, 13.97it/s, loss=0.725, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  26%|██▌       | 246/938 [00:17<00:49, 13.97it/s, loss=0.72, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  26%|██▋       | 247/938 [00:17<00:49, 13.97it/s, loss=0.729, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  26%|██▋       | 248/938 [00:17<00:49, 13.97it/s, loss=0.725, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  27%|██▋       | 249/938 [00:17<00:49, 13.97it/s, loss=0.725, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  27%|██▋       | 249/938 [00:17<00:49, 13.97it/s, loss=0.728, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  27%|██▋       | 250/938 [00:17<00:49, 13.97it/s, loss=0.727, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  27%|██▋       | 251/938 [00:17<00:49, 13.97it/s, loss=0.73, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  27%|██▋       | 252/938 [00:18<00:49, 13.97it/s, loss=0.73, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  27%|██▋       | 252/938 [00:18<00:49, 13.97it/s, loss=0.735, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  27%|██▋       | 253/938 [00:18<00:49, 13.97it/s, loss=0.727, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  27%|██▋       | 254/938 [00:18<00:48, 13.97it/s, loss=0.72, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  27%|██▋       | 255/938 [00:18<00:48, 13.98it/s, loss=0.72, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  27%|██▋       | 255/938 [00:18<00:48, 13.98it/s, loss=0.708, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  27%|██▋       | 256/938 [00:18<00:48, 13.97it/s, loss=0.724, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  27%|██▋       | 257/938 [00:18<00:48, 13.97it/s, loss=0.726, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  28%|██▊       | 258/938 [00:18<00:48, 13.96it/s, loss=0.726, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  28%|██▊       | 258/938 [00:18<00:48, 13.96it/s, loss=0.744, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  28%|██▊       | 259/938 [00:18<00:48, 13.95it/s, loss=0.746, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  28%|██▊       | 260/938 [00:18<00:48, 13.94it/s, loss=0.729, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  28%|██▊       | 261/938 [00:18<00:48, 13.95it/s, loss=0.729, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  28%|██▊       | 261/938 [00:18<00:48, 13.95it/s, loss=0.724, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  28%|██▊       | 262/938 [00:18<00:48, 13.95it/s, loss=0.721, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  28%|██▊       | 263/938 [00:18<00:48, 13.95it/s, loss=0.716, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  28%|██▊       | 264/938 [00:18<00:48, 13.95it/s, loss=0.716, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  28%|██▊       | 264/938 [00:18<00:48, 13.94it/s, loss=0.718, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  28%|██▊       | 265/938 [00:18<00:48, 13.95it/s, loss=0.728, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  28%|██▊       | 266/938 [00:19<00:48, 13.95it/s, loss=0.728, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  28%|██▊       | 267/938 [00:19<00:48, 13.94it/s, loss=0.728, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  28%|██▊       | 267/938 [00:19<00:48, 13.94it/s, loss=0.719, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  29%|██▊       | 268/938 [00:19<00:47, 13.96it/s, loss=0.717, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  29%|██▊       | 269/938 [00:19<00:47, 13.95it/s, loss=0.709, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  29%|██▉       | 270/938 [00:19<00:47, 13.96it/s, loss=0.709, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  29%|██▉       | 270/938 [00:19<00:47, 13.95it/s, loss=0.718, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  29%|██▉       | 271/938 [00:19<00:47, 13.96it/s, loss=0.716, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  29%|██▉       | 272/938 [00:19<00:47, 13.95it/s, loss=0.719, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  29%|██▉       | 273/938 [00:19<00:47, 13.94it/s, loss=0.719, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  29%|██▉       | 273/938 [00:19<00:47, 13.94it/s, loss=0.718, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  29%|██▉       | 274/938 [00:19<00:47, 13.95it/s, loss=0.713, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  29%|██▉       | 275/938 [00:19<00:47, 13.95it/s, loss=0.711, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  29%|██▉       | 276/938 [00:19<00:47, 13.95it/s, loss=0.711, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  29%|██▉       | 276/938 [00:19<00:47, 13.95it/s, loss=0.695, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  30%|██▉       | 277/938 [00:19<00:47, 13.95it/s, loss=0.691, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  30%|██▉       | 278/938 [00:19<00:47, 13.96it/s, loss=0.681, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  30%|██▉       | 279/938 [00:19<00:47, 13.96it/s, loss=0.681, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  30%|██▉       | 279/938 [00:19<00:47, 13.96it/s, loss=0.669, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  30%|██▉       | 280/938 [00:20<00:47, 13.97it/s, loss=0.679, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  30%|██▉       | 281/938 [00:20<00:47, 13.96it/s, loss=0.682, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  30%|███       | 282/938 [00:20<00:47, 13.95it/s, loss=0.682, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  30%|███       | 282/938 [00:20<00:47, 13.95it/s, loss=0.674, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  30%|███       | 283/938 [00:20<00:46, 13.95it/s, loss=0.673, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  30%|███       | 284/938 [00:20<00:46, 13.95it/s, loss=0.673, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  30%|███       | 285/938 [00:20<00:46, 13.95it/s, loss=0.673, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  30%|███       | 285/938 [00:20<00:46, 13.95it/s, loss=0.663, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  30%|███       | 286/938 [00:20<00:46, 13.95it/s, loss=0.663, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  31%|███       | 287/938 [00:20<00:46, 13.95it/s, loss=0.672, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  31%|███       | 288/938 [00:20<00:46, 13.95it/s, loss=0.672, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  31%|███       | 288/938 [00:20<00:46, 13.94it/s, loss=0.674, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  31%|███       | 289/938 [00:20<00:46, 13.95it/s, loss=0.681, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  31%|███       | 290/938 [00:20<00:46, 13.95it/s, loss=0.679, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  31%|███       | 291/938 [00:20<00:46, 13.96it/s, loss=0.679, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  31%|███       | 291/938 [00:20<00:46, 13.96it/s, loss=0.689, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  31%|███       | 292/938 [00:20<00:46, 13.95it/s, loss=0.686, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  31%|███       | 293/938 [00:20<00:46, 13.96it/s, loss=0.695, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  31%|███▏      | 294/938 [00:21<00:46, 13.96it/s, loss=0.695, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  31%|███▏      | 294/938 [00:21<00:46, 13.96it/s, loss=0.7, v_num=16, val_rmse=0.654, train_rmse=1.190]  
Epoch 1:  31%|███▏      | 295/938 [00:21<00:46, 13.96it/s, loss=0.706, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  32%|███▏      | 296/938 [00:21<00:45, 13.96it/s, loss=0.709, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  32%|███▏      | 297/938 [00:21<00:45, 13.97it/s, loss=0.709, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  32%|███▏      | 297/938 [00:21<00:45, 13.97it/s, loss=0.714, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  32%|███▏      | 298/938 [00:21<00:45, 13.96it/s, loss=0.721, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  32%|███▏      | 299/938 [00:21<00:45, 13.96it/s, loss=0.722, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  32%|███▏      | 300/938 [00:21<00:45, 13.95it/s, loss=0.722, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  32%|███▏      | 300/938 [00:21<00:45, 13.95it/s, loss=0.711, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  32%|███▏      | 301/938 [00:21<00:45, 13.95it/s, loss=0.718, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  32%|███▏      | 302/938 [00:21<00:45, 13.94it/s, loss=0.722, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  32%|███▏      | 303/938 [00:21<00:45, 13.95it/s, loss=0.722, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  32%|███▏      | 303/938 [00:21<00:45, 13.95it/s, loss=0.729, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  32%|███▏      | 304/938 [00:21<00:45, 13.95it/s, loss=0.726, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  33%|███▎      | 305/938 [00:21<00:45, 13.96it/s, loss=0.732, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  33%|███▎      | 306/938 [00:21<00:45, 13.97it/s, loss=0.732, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  33%|███▎      | 306/938 [00:21<00:45, 13.97it/s, loss=0.742, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  33%|███▎      | 307/938 [00:21<00:45, 13.96it/s, loss=0.739, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  33%|███▎      | 308/938 [00:22<00:45, 13.97it/s, loss=0.738, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  33%|███▎      | 309/938 [00:22<00:45, 13.98it/s, loss=0.738, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  33%|███▎      | 309/938 [00:22<00:45, 13.98it/s, loss=0.732, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  33%|███▎      | 310/938 [00:22<00:44, 13.98it/s, loss=0.735, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  33%|███▎      | 311/938 [00:22<00:44, 13.97it/s, loss=0.734, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  33%|███▎      | 312/938 [00:22<00:44, 13.96it/s, loss=0.734, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  33%|███▎      | 312/938 [00:22<00:44, 13.96it/s, loss=0.733, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  33%|███▎      | 313/938 [00:22<00:44, 13.96it/s, loss=0.729, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  33%|███▎      | 314/938 [00:22<00:44, 13.93it/s, loss=0.728, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  34%|███▎      | 315/938 [00:22<00:44, 13.92it/s, loss=0.728, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  34%|███▎      | 315/938 [00:22<00:44, 13.92it/s, loss=0.735, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  34%|███▎      | 316/938 [00:22<00:44, 13.92it/s, loss=0.739, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  34%|███▍      | 317/938 [00:22<00:44, 13.92it/s, loss=0.737, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  34%|███▍      | 318/938 [00:22<00:44, 13.93it/s, loss=0.737, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  34%|███▍      | 318/938 [00:22<00:44, 13.93it/s, loss=0.724, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  34%|███▍      | 319/938 [00:22<00:44, 13.93it/s, loss=0.727, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  34%|███▍      | 320/938 [00:22<00:44, 13.94it/s, loss=0.736, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  34%|███▍      | 321/938 [00:23<00:44, 13.94it/s, loss=0.736, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  34%|███▍      | 321/938 [00:23<00:44, 13.94it/s, loss=0.731, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  34%|███▍      | 322/938 [00:23<00:44, 13.94it/s, loss=0.733, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  34%|███▍      | 323/938 [00:23<00:44, 13.95it/s, loss=0.724, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  35%|███▍      | 324/938 [00:23<00:44, 13.95it/s, loss=0.724, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  35%|███▍      | 324/938 [00:23<00:44, 13.95it/s, loss=0.725, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  35%|███▍      | 325/938 [00:23<00:43, 13.95it/s, loss=0.72, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  35%|███▍      | 326/938 [00:23<00:43, 13.96it/s, loss=0.706, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  35%|███▍      | 327/938 [00:23<00:43, 13.95it/s, loss=0.706, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  35%|███▍      | 327/938 [00:23<00:43, 13.95it/s, loss=0.708, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  35%|███▍      | 328/938 [00:23<00:43, 13.95it/s, loss=0.706, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  35%|███▌      | 329/938 [00:23<00:43, 13.93it/s, loss=0.708, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  35%|███▌      | 330/938 [00:23<00:43, 13.94it/s, loss=0.708, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  35%|███▌      | 330/938 [00:23<00:43, 13.94it/s, loss=0.703, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  35%|███▌      | 331/938 [00:23<00:43, 13.93it/s, loss=0.696, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  35%|███▌      | 332/938 [00:23<00:43, 13.91it/s, loss=0.697, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  36%|███▌      | 333/938 [00:23<00:43, 13.92it/s, loss=0.697, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  36%|███▌      | 333/938 [00:23<00:43, 13.92it/s, loss=0.702, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  36%|███▌      | 334/938 [00:23<00:43, 13.92it/s, loss=0.705, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  36%|███▌      | 335/938 [00:24<00:43, 13.91it/s, loss=0.699, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  36%|███▌      | 336/938 [00:24<00:43, 13.91it/s, loss=0.699, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  36%|███▌      | 336/938 [00:24<00:43, 13.91it/s, loss=0.689, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  36%|███▌      | 337/938 [00:24<00:43, 13.90it/s, loss=0.697, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  36%|███▌      | 338/938 [00:24<00:43, 13.90it/s, loss=0.694, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  36%|███▌      | 339/938 [00:24<00:43, 13.90it/s, loss=0.694, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  36%|███▌      | 339/938 [00:24<00:43, 13.90it/s, loss=0.695, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  36%|███▌      | 340/938 [00:24<00:43, 13.90it/s, loss=0.69, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  36%|███▋      | 341/938 [00:24<00:42, 13.90it/s, loss=0.687, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  36%|███▋      | 342/938 [00:24<00:42, 13.89it/s, loss=0.687, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  36%|███▋      | 342/938 [00:24<00:42, 13.89it/s, loss=0.691, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  37%|███▋      | 343/938 [00:24<00:42, 13.89it/s, loss=0.699, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  37%|███▋      | 344/938 [00:24<00:42, 13.90it/s, loss=0.698, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  37%|███▋      | 345/938 [00:24<00:42, 13.90it/s, loss=0.698, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  37%|███▋      | 345/938 [00:24<00:42, 13.90it/s, loss=0.696, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  37%|███▋      | 346/938 [00:24<00:42, 13.89it/s, loss=0.708, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  37%|███▋      | 347/938 [00:24<00:42, 13.89it/s, loss=0.704, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  37%|███▋      | 348/938 [00:25<00:42, 13.89it/s, loss=0.704, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  37%|███▋      | 348/938 [00:25<00:42, 13.89it/s, loss=0.705, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  37%|███▋      | 349/938 [00:25<00:42, 13.89it/s, loss=0.702, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  37%|███▋      | 350/938 [00:25<00:42, 13.89it/s, loss=0.694, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  37%|███▋      | 351/938 [00:25<00:42, 13.88it/s, loss=0.694, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  37%|███▋      | 351/938 [00:25<00:42, 13.88it/s, loss=0.69, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  38%|███▊      | 352/938 [00:25<00:42, 13.89it/s, loss=0.69, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  38%|███▊      | 353/938 [00:25<00:42, 13.88it/s, loss=0.682, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  38%|███▊      | 354/938 [00:25<00:42, 13.88it/s, loss=0.682, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  38%|███▊      | 354/938 [00:25<00:42, 13.88it/s, loss=0.686, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  38%|███▊      | 355/938 [00:25<00:42, 13.87it/s, loss=0.678, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  38%|███▊      | 356/938 [00:25<00:41, 13.88it/s, loss=0.678, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  38%|███▊      | 357/938 [00:25<00:41, 13.89it/s, loss=0.678, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  38%|███▊      | 357/938 [00:25<00:41, 13.89it/s, loss=0.674, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  38%|███▊      | 358/938 [00:25<00:41, 13.88it/s, loss=0.685, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  38%|███▊      | 359/938 [00:25<00:41, 13.87it/s, loss=0.688, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  38%|███▊      | 360/938 [00:25<00:41, 13.87it/s, loss=0.688, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  38%|███▊      | 360/938 [00:25<00:41, 13.87it/s, loss=0.688, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  38%|███▊      | 361/938 [00:26<00:41, 13.88it/s, loss=0.691, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  39%|███▊      | 362/938 [00:26<00:41, 13.88it/s, loss=0.692, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  39%|███▊      | 363/938 [00:26<00:41, 13.88it/s, loss=0.692, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  39%|███▊      | 363/938 [00:26<00:41, 13.88it/s, loss=0.689, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  39%|███▉      | 364/938 [00:26<00:41, 13.88it/s, loss=0.691, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  39%|███▉      | 365/938 [00:26<00:41, 13.88it/s, loss=0.697, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  39%|███▉      | 366/938 [00:26<00:41, 13.87it/s, loss=0.697, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  39%|███▉      | 366/938 [00:26<00:41, 13.87it/s, loss=0.689, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  39%|███▉      | 367/938 [00:26<00:41, 13.88it/s, loss=0.688, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  39%|███▉      | 368/938 [00:26<00:41, 13.88it/s, loss=0.686, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  39%|███▉      | 369/938 [00:26<00:40, 13.88it/s, loss=0.686, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  39%|███▉      | 369/938 [00:26<00:40, 13.88it/s, loss=0.703, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  39%|███▉      | 370/938 [00:26<00:40, 13.88it/s, loss=0.709, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  40%|███▉      | 371/938 [00:26<00:40, 13.88it/s, loss=0.712, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  40%|███▉      | 372/938 [00:26<00:40, 13.89it/s, loss=0.712, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  40%|███▉      | 372/938 [00:26<00:40, 13.89it/s, loss=0.704, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  40%|███▉      | 373/938 [00:26<00:40, 13.88it/s, loss=0.701, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  40%|███▉      | 374/938 [00:26<00:40, 13.89it/s, loss=0.7, v_num=16, val_rmse=0.654, train_rmse=1.190]  
Epoch 1:  40%|███▉      | 375/938 [00:26<00:40, 13.89it/s, loss=0.7, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  40%|███▉      | 375/938 [00:26<00:40, 13.89it/s, loss=0.703, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  40%|████      | 376/938 [00:27<00:40, 13.89it/s, loss=0.706, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  40%|████      | 377/938 [00:27<00:40, 13.90it/s, loss=0.704, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  40%|████      | 378/938 [00:27<00:40, 13.90it/s, loss=0.704, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  40%|████      | 378/938 [00:27<00:40, 13.90it/s, loss=0.701, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  40%|████      | 379/938 [00:27<00:40, 13.91it/s, loss=0.702, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  41%|████      | 380/938 [00:27<00:40, 13.90it/s, loss=0.697, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  41%|████      | 381/938 [00:27<00:40, 13.91it/s, loss=0.697, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  41%|████      | 381/938 [00:27<00:40, 13.91it/s, loss=0.69, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  41%|████      | 382/938 [00:27<00:39, 13.91it/s, loss=0.687, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  41%|████      | 383/938 [00:27<00:39, 13.91it/s, loss=0.686, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  41%|████      | 384/938 [00:27<00:39, 13.91it/s, loss=0.686, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  41%|████      | 384/938 [00:27<00:39, 13.91it/s, loss=0.685, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  41%|████      | 385/938 [00:27<00:39, 13.91it/s, loss=0.689, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  41%|████      | 386/938 [00:27<00:39, 13.91it/s, loss=0.691, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  41%|████▏     | 387/938 [00:27<00:39, 13.91it/s, loss=0.691, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  41%|████▏     | 387/938 [00:27<00:39, 13.91it/s, loss=0.688, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  41%|████▏     | 388/938 [00:27<00:39, 13.92it/s, loss=0.684, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  41%|████▏     | 389/938 [00:27<00:39, 13.91it/s, loss=0.67, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  42%|████▏     | 390/938 [00:28<00:39, 13.91it/s, loss=0.67, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  42%|████▏     | 390/938 [00:28<00:39, 13.91it/s, loss=0.663, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  42%|████▏     | 391/938 [00:28<00:39, 13.92it/s, loss=0.669, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  42%|████▏     | 392/938 [00:28<00:39, 13.92it/s, loss=0.668, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  42%|████▏     | 393/938 [00:28<00:39, 13.92it/s, loss=0.668, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  42%|████▏     | 393/938 [00:28<00:39, 13.92it/s, loss=0.667, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  42%|████▏     | 394/938 [00:28<00:39, 13.92it/s, loss=0.664, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  42%|████▏     | 395/938 [00:28<00:39, 13.92it/s, loss=0.668, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  42%|████▏     | 396/938 [00:28<00:38, 13.92it/s, loss=0.668, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  42%|████▏     | 396/938 [00:28<00:38, 13.92it/s, loss=0.67, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  42%|████▏     | 397/938 [00:28<00:38, 13.93it/s, loss=0.669, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  42%|████▏     | 398/938 [00:28<00:38, 13.93it/s, loss=0.671, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  43%|████▎     | 399/938 [00:28<00:38, 13.93it/s, loss=0.671, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  43%|████▎     | 399/938 [00:28<00:38, 13.93it/s, loss=0.665, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  43%|████▎     | 400/938 [00:28<00:38, 13.93it/s, loss=0.677, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  43%|████▎     | 401/938 [00:28<00:38, 13.93it/s, loss=0.685, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  43%|████▎     | 402/938 [00:28<00:38, 13.94it/s, loss=0.685, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  43%|████▎     | 402/938 [00:28<00:38, 13.94it/s, loss=0.678, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  43%|████▎     | 403/938 [00:28<00:38, 13.94it/s, loss=0.688, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  43%|████▎     | 404/938 [00:28<00:38, 13.95it/s, loss=0.688, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  43%|████▎     | 405/938 [00:29<00:38, 13.95it/s, loss=0.688, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  43%|████▎     | 405/938 [00:29<00:38, 13.95it/s, loss=0.684, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  43%|████▎     | 406/938 [00:29<00:38, 13.95it/s, loss=0.681, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  43%|████▎     | 407/938 [00:29<00:38, 13.95it/s, loss=0.686, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  43%|████▎     | 408/938 [00:29<00:37, 13.95it/s, loss=0.686, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  43%|████▎     | 408/938 [00:29<00:37, 13.95it/s, loss=0.689, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  44%|████▎     | 409/938 [00:29<00:37, 13.95it/s, loss=0.692, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  44%|████▎     | 410/938 [00:29<00:37, 13.95it/s, loss=0.696, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  44%|████▍     | 411/938 [00:29<00:37, 13.96it/s, loss=0.696, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  44%|████▍     | 411/938 [00:29<00:37, 13.96it/s, loss=0.698, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  44%|████▍     | 412/938 [00:29<00:37, 13.96it/s, loss=0.704, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  44%|████▍     | 413/938 [00:29<00:37, 13.96it/s, loss=0.706, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  44%|████▍     | 414/938 [00:29<00:37, 13.96it/s, loss=0.706, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  44%|████▍     | 414/938 [00:29<00:37, 13.96it/s, loss=0.701, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  44%|████▍     | 415/938 [00:29<00:37, 13.96it/s, loss=0.698, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  44%|████▍     | 416/938 [00:29<00:37, 13.95it/s, loss=0.705, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  44%|████▍     | 417/938 [00:29<00:37, 13.95it/s, loss=0.705, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  44%|████▍     | 417/938 [00:29<00:37, 13.95it/s, loss=0.702, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  45%|████▍     | 418/938 [00:29<00:37, 13.95it/s, loss=0.706, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  45%|████▍     | 419/938 [00:30<00:37, 13.95it/s, loss=0.703, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  45%|████▍     | 420/938 [00:30<00:37, 13.95it/s, loss=0.703, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  45%|████▍     | 420/938 [00:30<00:37, 13.95it/s, loss=0.701, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  45%|████▍     | 421/938 [00:30<00:37, 13.95it/s, loss=0.701, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  45%|████▍     | 422/938 [00:30<00:36, 13.95it/s, loss=0.703, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  45%|████▌     | 423/938 [00:30<00:36, 13.95it/s, loss=0.703, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  45%|████▌     | 423/938 [00:30<00:36, 13.95it/s, loss=0.693, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  45%|████▌     | 424/938 [00:30<00:36, 13.94it/s, loss=0.693, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  45%|████▌     | 425/938 [00:30<00:36, 13.94it/s, loss=0.693, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  45%|████▌     | 426/938 [00:30<00:36, 13.94it/s, loss=0.693, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  45%|████▌     | 426/938 [00:30<00:36, 13.94it/s, loss=0.69, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  46%|████▌     | 427/938 [00:30<00:36, 13.93it/s, loss=0.69, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  46%|████▌     | 428/938 [00:30<00:36, 13.94it/s, loss=0.694, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  46%|████▌     | 429/938 [00:30<00:36, 13.95it/s, loss=0.694, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  46%|████▌     | 429/938 [00:30<00:36, 13.95it/s, loss=0.698, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  46%|████▌     | 430/938 [00:30<00:36, 13.95it/s, loss=0.703, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  46%|████▌     | 431/938 [00:30<00:36, 13.95it/s, loss=0.701, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  46%|████▌     | 432/938 [00:30<00:36, 13.94it/s, loss=0.701, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  46%|████▌     | 432/938 [00:30<00:36, 13.94it/s, loss=0.707, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  46%|████▌     | 433/938 [00:31<00:36, 13.94it/s, loss=0.705, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  46%|████▋     | 434/938 [00:31<00:36, 13.94it/s, loss=0.702, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  46%|████▋     | 435/938 [00:31<00:36, 13.95it/s, loss=0.702, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  46%|████▋     | 435/938 [00:31<00:36, 13.95it/s, loss=0.717, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  46%|████▋     | 436/938 [00:31<00:35, 13.95it/s, loss=0.715, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  47%|████▋     | 437/938 [00:31<00:35, 13.95it/s, loss=0.721, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  47%|████▋     | 438/938 [00:31<00:35, 13.95it/s, loss=0.721, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  47%|████▋     | 438/938 [00:31<00:35, 13.95it/s, loss=0.717, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  47%|████▋     | 439/938 [00:31<00:35, 13.95it/s, loss=0.723, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  47%|████▋     | 440/938 [00:31<00:35, 13.95it/s, loss=0.719, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  47%|████▋     | 441/938 [00:31<00:35, 13.95it/s, loss=0.719, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  47%|████▋     | 441/938 [00:31<00:35, 13.95it/s, loss=0.719, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  47%|████▋     | 442/938 [00:31<00:35, 13.96it/s, loss=0.714, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  47%|████▋     | 443/938 [00:31<00:35, 13.96it/s, loss=0.718, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  47%|████▋     | 444/938 [00:31<00:35, 13.96it/s, loss=0.718, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  47%|████▋     | 444/938 [00:31<00:35, 13.96it/s, loss=0.717, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  47%|████▋     | 445/938 [00:31<00:35, 13.96it/s, loss=0.715, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  48%|████▊     | 446/938 [00:31<00:35, 13.97it/s, loss=0.719, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  48%|████▊     | 447/938 [00:32<00:35, 13.96it/s, loss=0.719, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  48%|████▊     | 447/938 [00:32<00:35, 13.96it/s, loss=0.713, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  48%|████▊     | 448/938 [00:32<00:35, 13.96it/s, loss=0.711, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  48%|████▊     | 449/938 [00:32<00:35, 13.95it/s, loss=0.705, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  48%|████▊     | 450/938 [00:32<00:34, 13.95it/s, loss=0.705, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  48%|████▊     | 450/938 [00:32<00:34, 13.95it/s, loss=0.712, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  48%|████▊     | 451/938 [00:32<00:34, 13.96it/s, loss=0.715, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  48%|████▊     | 452/938 [00:32<00:34, 13.95it/s, loss=0.709, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  48%|████▊     | 453/938 [00:32<00:34, 13.96it/s, loss=0.709, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  48%|████▊     | 453/938 [00:32<00:34, 13.96it/s, loss=0.723, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  48%|████▊     | 454/938 [00:32<00:34, 13.96it/s, loss=0.739, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  49%|████▊     | 455/938 [00:32<00:34, 13.96it/s, loss=0.722, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  49%|████▊     | 456/938 [00:32<00:34, 13.95it/s, loss=0.722, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  49%|████▊     | 456/938 [00:32<00:34, 13.95it/s, loss=0.722, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  49%|████▊     | 457/938 [00:32<00:34, 13.95it/s, loss=0.72, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  49%|████▉     | 458/938 [00:32<00:34, 13.95it/s, loss=0.722, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  49%|████▉     | 459/938 [00:32<00:34, 13.95it/s, loss=0.722, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  49%|████▉     | 459/938 [00:32<00:34, 13.95it/s, loss=0.72, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  49%|████▉     | 460/938 [00:32<00:34, 13.94it/s, loss=0.727, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  49%|████▉     | 461/938 [00:33<00:34, 13.94it/s, loss=0.726, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  49%|████▉     | 462/938 [00:33<00:34, 13.94it/s, loss=0.726, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  49%|████▉     | 462/938 [00:33<00:34, 13.94it/s, loss=0.735, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  49%|████▉     | 463/938 [00:33<00:34, 13.94it/s, loss=0.73, v_num=16, val_rmse=0.654, train_rmse=1.190] 
Epoch 1:  49%|████▉     | 464/938 [00:33<00:33, 13.95it/s, loss=0.733, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  50%|████▉     | 465/938 [00:33<00:33, 13.95it/s, loss=0.733, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  50%|████▉     | 465/938 [00:33<00:33, 13.95it/s, loss=0.739, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  50%|████▉     | 466/938 [00:33<00:33, 13.95it/s, loss=0.735, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  50%|████▉     | 467/938 [00:33<00:33, 13.96it/s, loss=0.748, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  50%|████▉     | 468/938 [00:33<00:33, 13.96it/s, loss=0.748, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  50%|████▉     | 468/938 [00:33<00:33, 13.96it/s, loss=0.744, v_num=16, val_rmse=0.654, train_rmse=1.190]
Epoch 1:  50%|█████     | 469/938 [00:33<00:33, 13.97it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]
Epoch 1:  50%|█████     | 471/938 [00:33<00:33, 14.00it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:   0%|          | 2/469 [00:00<00:25, 18.30it/s]
Epoch 1:  51%|█████     | 474/938 [00:33<00:33, 14.04it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:   1%|          | 5/469 [00:00<00:21, 21.89it/s]
Epoch 1:  51%|█████     | 477/938 [00:33<00:32, 14.08it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:   2%|▏         | 8/469 [00:00<00:20, 22.96it/s]
Epoch 1:  51%|█████     | 480/938 [00:34<00:32, 14.12it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:   2%|▏         | 11/469 [00:00<00:18, 24.29it/s]
Epoch 1:  51%|█████▏    | 483/938 [00:34<00:32, 14.15it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:   3%|▎         | 14/469 [00:00<00:18, 24.42it/s]
Epoch 1:  52%|█████▏    | 486/938 [00:34<00:31, 14.19it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:   4%|▎         | 17/469 [00:00<00:18, 24.43it/s]
Epoch 1:  52%|█████▏    | 489/938 [00:34<00:31, 14.23it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:   4%|▍         | 20/469 [00:00<00:17, 25.18it/s]
Epoch 1:  52%|█████▏    | 492/938 [00:34<00:31, 14.27it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:   5%|▍         | 23/469 [00:00<00:17, 24.88it/s]
Epoch 1:  53%|█████▎    | 495/938 [00:34<00:30, 14.31it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:   6%|▌         | 26/469 [00:01<00:17, 24.83it/s]
Epoch 1:  53%|█████▎    | 498/938 [00:34<00:30, 14.34it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:   6%|▌         | 29/469 [00:01<00:18, 23.99it/s]
Epoch 1:  53%|█████▎    | 501/938 [00:34<00:30, 14.38it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:   7%|▋         | 32/469 [00:01<00:17, 25.52it/s]
Epoch 1:  54%|█████▎    | 504/938 [00:34<00:30, 14.41it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:   7%|▋         | 35/469 [00:01<00:18, 24.11it/s]
Epoch 1:  54%|█████▍    | 507/938 [00:35<00:29, 14.45it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:   8%|▊         | 38/469 [00:01<00:18, 23.92it/s]
Epoch 1:  54%|█████▍    | 510/938 [00:35<00:29, 14.48it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:   9%|▊         | 41/469 [00:01<00:18, 22.65it/s]
Epoch 1:  55%|█████▍    | 513/938 [00:35<00:29, 14.49it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:   9%|▉         | 44/469 [00:01<00:19, 21.65it/s]
Epoch 1:  55%|█████▌    | 516/938 [00:35<00:29, 14.52it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  10%|█         | 47/469 [00:02<00:19, 22.05it/s]
Epoch 1:  55%|█████▌    | 519/938 [00:35<00:28, 14.56it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  11%|█         | 50/469 [00:02<00:18, 23.03it/s]
Epoch 1:  56%|█████▌    | 522/938 [00:35<00:28, 14.59it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  11%|█▏        | 53/469 [00:02<00:18, 22.86it/s]
Epoch 1:  56%|█████▌    | 525/938 [00:35<00:28, 14.62it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  12%|█▏        | 56/469 [00:02<00:17, 23.45it/s]
Epoch 1:  56%|█████▋    | 528/938 [00:36<00:27, 14.65it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  13%|█▎        | 59/469 [00:02<00:18, 22.69it/s]
Epoch 1:  57%|█████▋    | 531/938 [00:36<00:27, 14.69it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  13%|█▎        | 62/469 [00:02<00:17, 23.87it/s]
Epoch 1:  57%|█████▋    | 534/938 [00:36<00:27, 14.72it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  14%|█▍        | 65/469 [00:02<00:16, 24.80it/s]
Epoch 1:  57%|█████▋    | 537/938 [00:36<00:27, 14.75it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  14%|█▍        | 68/469 [00:02<00:16, 24.22it/s]
Epoch 1:  58%|█████▊    | 540/938 [00:36<00:26, 14.79it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  15%|█▌        | 71/469 [00:02<00:15, 24.94it/s]
Epoch 1:  58%|█████▊    | 543/938 [00:36<00:26, 14.82it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  16%|█▌        | 74/469 [00:03<00:16, 24.61it/s]
Epoch 1:  58%|█████▊    | 546/938 [00:36<00:26, 14.84it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  16%|█▋        | 77/469 [00:03<00:17, 22.59it/s]
Epoch 1:  59%|█████▊    | 549/938 [00:36<00:26, 14.87it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  17%|█▋        | 80/469 [00:03<00:16, 23.37it/s]
Epoch 1:  59%|█████▉    | 552/938 [00:37<00:25, 14.90it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  18%|█▊        | 83/469 [00:03<00:16, 23.60it/s]
Epoch 1:  59%|█████▉    | 555/938 [00:37<00:25, 14.93it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  18%|█▊        | 86/469 [00:03<00:16, 23.48it/s]
Epoch 1:  59%|█████▉    | 558/938 [00:37<00:25, 14.96it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  19%|█▉        | 89/469 [00:03<00:16, 23.74it/s]
Epoch 1:  60%|█████▉    | 561/938 [00:37<00:25, 14.99it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  20%|█▉        | 92/469 [00:03<00:16, 23.21it/s]
Epoch 1:  60%|██████    | 564/938 [00:37<00:24, 15.02it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  20%|██        | 95/469 [00:04<00:16, 22.98it/s]
Epoch 1:  60%|██████    | 567/938 [00:37<00:24, 15.05it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  21%|██        | 98/469 [00:04<00:15, 23.53it/s]
Epoch 1:  61%|██████    | 570/938 [00:37<00:24, 15.08it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  22%|██▏       | 101/469 [00:04<00:15, 23.38it/s]
Epoch 1:  61%|██████    | 573/938 [00:37<00:24, 15.11it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  22%|██▏       | 104/469 [00:04<00:15, 23.90it/s]
Epoch 1:  61%|██████▏   | 576/938 [00:38<00:23, 15.14it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  23%|██▎       | 107/469 [00:04<00:14, 24.20it/s]
Epoch 1:  62%|██████▏   | 579/938 [00:38<00:23, 15.16it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  23%|██▎       | 110/469 [00:04<00:15, 23.82it/s]
Epoch 1:  62%|██████▏   | 582/938 [00:38<00:23, 15.20it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  24%|██▍       | 113/469 [00:04<00:14, 24.04it/s]
Epoch 1:  62%|██████▏   | 585/938 [00:38<00:23, 15.22it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  25%|██▍       | 116/469 [00:04<00:14, 23.83it/s]
Epoch 1:  63%|██████▎   | 588/938 [00:38<00:22, 15.25it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  25%|██▌       | 119/469 [00:05<00:14, 23.91it/s]
Epoch 1:  63%|██████▎   | 591/938 [00:38<00:22, 15.28it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  26%|██▌       | 122/469 [00:05<00:14, 24.14it/s]
Epoch 1:  63%|██████▎   | 594/938 [00:38<00:22, 15.31it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  27%|██▋       | 125/469 [00:05<00:14, 24.11it/s]
Epoch 1:  64%|██████▎   | 597/938 [00:38<00:22, 15.33it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  27%|██▋       | 128/469 [00:05<00:14, 23.43it/s]
Epoch 1:  64%|██████▍   | 600/938 [00:39<00:22, 15.36it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  28%|██▊       | 131/469 [00:05<00:14, 23.51it/s]
Epoch 1:  64%|██████▍   | 603/938 [00:39<00:21, 15.39it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  29%|██▊       | 134/469 [00:05<00:14, 23.78it/s]
Epoch 1:  65%|██████▍   | 606/938 [00:39<00:21, 15.42it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  29%|██▉       | 137/469 [00:05<00:13, 23.76it/s]
Epoch 1:  65%|██████▍   | 609/938 [00:39<00:21, 15.44it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  30%|██▉       | 140/469 [00:05<00:13, 24.03it/s]
Epoch 1:  65%|██████▌   | 612/938 [00:39<00:21, 15.47it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  30%|███       | 143/469 [00:06<00:13, 24.17it/s]
Epoch 1:  66%|██████▌   | 615/938 [00:39<00:20, 15.50it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  31%|███       | 146/469 [00:06<00:13, 23.43it/s]
Epoch 1:  66%|██████▌   | 618/938 [00:39<00:20, 15.52it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  32%|███▏      | 149/469 [00:06<00:13, 24.36it/s]
Epoch 1:  66%|██████▌   | 621/938 [00:39<00:20, 15.55it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  32%|███▏      | 152/469 [00:06<00:13, 22.89it/s]
Epoch 1:  67%|██████▋   | 624/938 [00:40<00:20, 15.57it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  33%|███▎      | 155/469 [00:06<00:13, 23.50it/s]
Epoch 1:  67%|██████▋   | 627/938 [00:40<00:19, 15.60it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  34%|███▎      | 158/469 [00:06<00:13, 23.63it/s]
Epoch 1:  67%|██████▋   | 630/938 [00:40<00:19, 15.62it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  34%|███▍      | 161/469 [00:06<00:13, 23.05it/s]
Epoch 1:  67%|██████▋   | 633/938 [00:40<00:19, 15.65it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  35%|███▍      | 164/469 [00:06<00:12, 23.55it/s]
Epoch 1:  68%|██████▊   | 636/938 [00:40<00:19, 15.68it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  36%|███▌      | 167/469 [00:07<00:12, 24.96it/s]
Epoch 1:  68%|██████▊   | 639/938 [00:40<00:19, 15.70it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  36%|███▌      | 170/469 [00:07<00:12, 24.64it/s]
Epoch 1:  68%|██████▊   | 642/938 [00:40<00:18, 15.73it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  37%|███▋      | 173/469 [00:07<00:12, 24.39it/s]
Epoch 1:  69%|██████▉   | 645/938 [00:40<00:18, 15.76it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  38%|███▊      | 176/469 [00:07<00:11, 24.99it/s]
Epoch 1:  69%|██████▉   | 648/938 [00:41<00:18, 15.79it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  38%|███▊      | 179/469 [00:07<00:11, 25.15it/s]
Epoch 1:  69%|██████▉   | 651/938 [00:41<00:18, 15.81it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  39%|███▉      | 182/469 [00:07<00:11, 25.33it/s]
Epoch 1:  70%|██████▉   | 654/938 [00:41<00:17, 15.84it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  39%|███▉      | 185/469 [00:07<00:11, 24.41it/s]
Epoch 1:  70%|███████   | 657/938 [00:41<00:17, 15.86it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  40%|████      | 188/469 [00:07<00:11, 24.67it/s]
Epoch 1:  70%|███████   | 660/938 [00:41<00:17, 15.90it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  41%|████      | 191/469 [00:07<00:10, 25.43it/s]
Epoch 1:  71%|███████   | 663/938 [00:41<00:17, 15.91it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  41%|████▏     | 194/469 [00:08<00:11, 24.29it/s]
Epoch 1:  71%|███████   | 666/938 [00:41<00:17, 15.94it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  42%|████▏     | 197/469 [00:08<00:11, 24.20it/s]
Epoch 1:  71%|███████▏  | 669/938 [00:41<00:16, 15.96it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  43%|████▎     | 200/469 [00:08<00:11, 24.26it/s]
Epoch 1:  72%|███████▏  | 672/938 [00:42<00:16, 15.99it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  43%|████▎     | 203/469 [00:08<00:10, 24.92it/s]
Epoch 1:  72%|███████▏  | 675/938 [00:42<00:16, 16.02it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  44%|████▍     | 206/469 [00:08<00:10, 24.83it/s]
Epoch 1:  72%|███████▏  | 678/938 [00:42<00:16, 16.04it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  45%|████▍     | 209/469 [00:08<00:10, 25.62it/s]
Epoch 1:  73%|███████▎  | 681/938 [00:42<00:15, 16.07it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  45%|████▌     | 212/469 [00:08<00:10, 24.73it/s]
Epoch 1:  73%|███████▎  | 684/938 [00:42<00:15, 16.10it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  46%|████▌     | 215/469 [00:08<00:10, 25.18it/s]
Epoch 1:  73%|███████▎  | 687/938 [00:42<00:15, 16.12it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  46%|████▋     | 218/469 [00:09<00:09, 25.64it/s]
Epoch 1:  74%|███████▎  | 690/938 [00:42<00:15, 16.15it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  47%|████▋     | 221/469 [00:09<00:09, 25.08it/s]
Epoch 1:  74%|███████▍  | 693/938 [00:42<00:15, 16.17it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  48%|████▊     | 224/469 [00:09<00:09, 25.13it/s]
Epoch 1:  74%|███████▍  | 696/938 [00:42<00:14, 16.20it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  48%|████▊     | 227/469 [00:09<00:09, 24.71it/s]
Epoch 1:  75%|███████▍  | 699/938 [00:43<00:14, 16.22it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  49%|████▉     | 230/469 [00:09<00:09, 25.64it/s]
Epoch 1:  75%|███████▍  | 702/938 [00:43<00:14, 16.25it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  50%|████▉     | 233/469 [00:09<00:09, 25.12it/s]
Epoch 1:  75%|███████▌  | 705/938 [00:43<00:14, 16.26it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  50%|█████     | 236/469 [00:09<00:09, 24.08it/s]
Epoch 1:  75%|███████▌  | 708/938 [00:43<00:14, 16.29it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  51%|█████     | 239/469 [00:09<00:09, 24.20it/s]
Epoch 1:  76%|███████▌  | 711/938 [00:43<00:13, 16.31it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  52%|█████▏    | 242/469 [00:10<00:09, 24.82it/s]
Epoch 1:  76%|███████▌  | 714/938 [00:43<00:13, 16.34it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  52%|█████▏    | 245/469 [00:10<00:09, 24.71it/s]
Epoch 1:  76%|███████▋  | 717/938 [00:43<00:13, 16.36it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  53%|█████▎    | 248/469 [00:10<00:09, 23.29it/s]
Epoch 1:  77%|███████▋  | 720/938 [00:43<00:13, 16.38it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  54%|█████▎    | 251/469 [00:10<00:09, 24.08it/s]
Epoch 1:  77%|███████▋  | 723/938 [00:44<00:13, 16.40it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  54%|█████▍    | 254/469 [00:10<00:08, 24.88it/s]
Epoch 1:  77%|███████▋  | 726/938 [00:44<00:12, 16.43it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  55%|█████▍    | 257/469 [00:10<00:08, 24.96it/s]
Epoch 1:  78%|███████▊  | 729/938 [00:44<00:12, 16.45it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  55%|█████▌    | 260/469 [00:10<00:08, 24.74it/s]
Epoch 1:  78%|███████▊  | 732/938 [00:44<00:12, 16.47it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  56%|█████▌    | 263/469 [00:10<00:08, 24.56it/s]
Epoch 1:  78%|███████▊  | 735/938 [00:44<00:12, 16.49it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  57%|█████▋    | 266/469 [00:11<00:08, 24.68it/s]
Epoch 1:  79%|███████▊  | 738/938 [00:44<00:12, 16.52it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  57%|█████▋    | 269/469 [00:11<00:08, 24.27it/s]
Epoch 1:  79%|███████▉  | 741/938 [00:44<00:11, 16.54it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  58%|█████▊    | 272/469 [00:11<00:07, 25.03it/s]
Epoch 1:  79%|███████▉  | 744/938 [00:44<00:11, 16.56it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  59%|█████▊    | 275/469 [00:11<00:07, 24.86it/s]
Epoch 1:  80%|███████▉  | 747/938 [00:45<00:11, 16.58it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  59%|█████▉    | 278/469 [00:11<00:07, 25.19it/s]
Epoch 1:  80%|███████▉  | 750/938 [00:45<00:11, 16.60it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  60%|█████▉    | 281/469 [00:11<00:07, 24.12it/s]
Epoch 1:  80%|████████  | 753/938 [00:45<00:11, 16.62it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  61%|██████    | 284/469 [00:11<00:07, 24.50it/s]
Epoch 1:  81%|████████  | 756/938 [00:45<00:10, 16.65it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  61%|██████    | 287/469 [00:11<00:07, 24.96it/s]
Epoch 1:  81%|████████  | 759/938 [00:45<00:10, 16.67it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  62%|██████▏   | 290/469 [00:11<00:07, 25.39it/s]
Epoch 1:  81%|████████  | 762/938 [00:45<00:10, 16.69it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  62%|██████▏   | 293/469 [00:12<00:07, 24.74it/s]
Epoch 1:  82%|████████▏ | 765/938 [00:45<00:10, 16.71it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  63%|██████▎   | 296/469 [00:12<00:07, 24.28it/s]
Epoch 1:  82%|████████▏ | 768/938 [00:45<00:10, 16.73it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  64%|██████▍   | 299/469 [00:12<00:07, 23.90it/s]
Epoch 1:  82%|████████▏ | 771/938 [00:46<00:09, 16.75it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  64%|██████▍   | 302/469 [00:12<00:06, 24.33it/s]
Epoch 1:  83%|████████▎ | 774/938 [00:46<00:09, 16.77it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  65%|██████▌   | 305/469 [00:12<00:06, 24.20it/s]
Epoch 1:  83%|████████▎ | 777/938 [00:46<00:09, 16.79it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  66%|██████▌   | 308/469 [00:12<00:06, 23.53it/s]
Epoch 1:  83%|████████▎ | 780/938 [00:46<00:09, 16.81it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  66%|██████▋   | 311/469 [00:12<00:06, 24.02it/s]
Epoch 1:  83%|████████▎ | 783/938 [00:46<00:09, 16.83it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  67%|██████▋   | 314/469 [00:12<00:06, 24.79it/s]
Epoch 1:  84%|████████▍ | 786/938 [00:46<00:09, 16.85it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  68%|██████▊   | 317/469 [00:13<00:05, 25.56it/s]
Epoch 1:  84%|████████▍ | 789/938 [00:46<00:08, 16.88it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  68%|██████▊   | 320/469 [00:13<00:06, 24.77it/s]
Epoch 1:  84%|████████▍ | 792/938 [00:46<00:08, 16.89it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  69%|██████▉   | 323/469 [00:13<00:06, 24.17it/s]
Epoch 1:  85%|████████▍ | 795/938 [00:47<00:08, 16.91it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  70%|██████▉   | 326/469 [00:13<00:05, 24.44it/s]
Epoch 1:  85%|████████▌ | 798/938 [00:47<00:08, 16.93it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  70%|███████   | 329/469 [00:13<00:05, 24.52it/s]
Epoch 1:  85%|████████▌ | 801/938 [00:47<00:08, 16.95it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  71%|███████   | 332/469 [00:13<00:05, 24.93it/s]
Epoch 1:  86%|████████▌ | 804/938 [00:47<00:07, 16.97it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  71%|███████▏  | 335/469 [00:13<00:05, 24.27it/s]
Epoch 1:  86%|████████▌ | 807/938 [00:47<00:07, 16.99it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  72%|███████▏  | 338/469 [00:13<00:05, 24.05it/s]
Epoch 1:  86%|████████▋ | 810/938 [00:47<00:07, 17.01it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  73%|███████▎  | 341/469 [00:14<00:05, 24.05it/s]
Epoch 1:  87%|████████▋ | 813/938 [00:47<00:07, 17.03it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  73%|███████▎  | 344/469 [00:14<00:05, 22.95it/s]
Epoch 1:  87%|████████▋ | 816/938 [00:47<00:07, 17.04it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  74%|███████▍  | 347/469 [00:14<00:05, 23.29it/s]
Epoch 1:  87%|████████▋ | 819/938 [00:48<00:06, 17.05it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  75%|███████▍  | 350/469 [00:14<00:04, 24.23it/s]
Epoch 1:  88%|████████▊ | 822/938 [00:48<00:06, 17.08it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  75%|███████▌  | 353/469 [00:14<00:04, 24.97it/s]
Epoch 1:  88%|████████▊ | 825/938 [00:48<00:06, 17.10it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  76%|███████▌  | 356/469 [00:14<00:04, 24.86it/s]
Epoch 1:  88%|████████▊ | 828/938 [00:48<00:06, 17.11it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  77%|███████▋  | 359/469 [00:14<00:04, 23.75it/s]
Epoch 1:  89%|████████▊ | 831/938 [00:48<00:06, 17.13it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  77%|███████▋  | 362/469 [00:14<00:04, 23.89it/s]
Epoch 1:  89%|████████▉ | 834/938 [00:48<00:06, 17.15it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  78%|███████▊  | 365/469 [00:15<00:04, 24.49it/s]
Epoch 1:  89%|████████▉ | 837/938 [00:48<00:05, 17.17it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  78%|███████▊  | 368/469 [00:15<00:04, 24.77it/s]
Epoch 1:  90%|████████▉ | 840/938 [00:48<00:05, 17.19it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  79%|███████▉  | 371/469 [00:15<00:03, 24.96it/s]
Epoch 1:  90%|████████▉ | 843/938 [00:48<00:05, 17.21it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  80%|███████▉  | 374/469 [00:15<00:03, 24.57it/s]
Epoch 1:  90%|█████████ | 846/938 [00:49<00:05, 17.23it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  80%|████████  | 377/469 [00:15<00:03, 24.99it/s]
Epoch 1:  91%|█████████ | 849/938 [00:49<00:05, 17.25it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  81%|████████  | 380/469 [00:15<00:03, 24.65it/s]
Epoch 1:  91%|█████████ | 852/938 [00:49<00:04, 17.27it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  82%|████████▏ | 383/469 [00:15<00:03, 25.19it/s]
Epoch 1:  91%|█████████ | 855/938 [00:49<00:04, 17.29it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  82%|████████▏ | 386/469 [00:15<00:03, 25.53it/s]
Epoch 1:  91%|█████████▏| 858/938 [00:49<00:04, 17.31it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  83%|████████▎ | 389/469 [00:16<00:03, 25.97it/s]
Epoch 1:  92%|█████████▏| 861/938 [00:49<00:04, 17.33it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  84%|████████▎ | 392/469 [00:16<00:02, 25.75it/s]
Epoch 1:  92%|█████████▏| 864/938 [00:49<00:04, 17.35it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  84%|████████▍ | 395/469 [00:16<00:02, 25.58it/s]
Epoch 1:  92%|█████████▏| 867/938 [00:49<00:04, 17.36it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  85%|████████▍ | 398/469 [00:16<00:02, 24.97it/s]
Epoch 1:  93%|█████████▎| 870/938 [00:50<00:03, 17.38it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  86%|████████▌ | 401/469 [00:16<00:02, 24.63it/s]
Epoch 1:  93%|█████████▎| 873/938 [00:50<00:03, 17.40it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  86%|████████▌ | 404/469 [00:16<00:02, 24.76it/s]
Epoch 1:  93%|█████████▎| 876/938 [00:50<00:03, 17.42it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  87%|████████▋ | 407/469 [00:16<00:02, 25.55it/s]
Epoch 1:  94%|█████████▎| 879/938 [00:50<00:03, 17.43it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  87%|████████▋ | 410/469 [00:16<00:02, 24.83it/s]
Epoch 1:  94%|█████████▍| 882/938 [00:50<00:03, 17.45it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  88%|████████▊ | 413/469 [00:17<00:02, 25.30it/s]
Epoch 1:  94%|█████████▍| 885/938 [00:50<00:03, 17.47it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  89%|████████▊ | 416/469 [00:17<00:02, 24.48it/s]
Epoch 1:  95%|█████████▍| 888/938 [00:50<00:02, 17.49it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  89%|████████▉ | 419/469 [00:17<00:01, 25.22it/s]
Epoch 1:  95%|█████████▍| 891/938 [00:50<00:02, 17.51it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  90%|████████▉ | 422/469 [00:17<00:01, 25.49it/s]
Epoch 1:  95%|█████████▌| 894/938 [00:51<00:02, 17.52it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  91%|█████████ | 425/469 [00:17<00:01, 24.30it/s]
Epoch 1:  96%|█████████▌| 897/938 [00:51<00:02, 17.54it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  91%|█████████▏| 428/469 [00:17<00:01, 24.88it/s]
Epoch 1:  96%|█████████▌| 900/938 [00:51<00:02, 17.56it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  92%|█████████▏| 431/469 [00:17<00:01, 24.90it/s]
Epoch 1:  96%|█████████▋| 903/938 [00:51<00:01, 17.58it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  93%|█████████▎| 434/469 [00:17<00:01, 25.25it/s]
Epoch 1:  97%|█████████▋| 906/938 [00:51<00:01, 17.59it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  93%|█████████▎| 437/469 [00:17<00:01, 24.60it/s]
Epoch 1:  97%|█████████▋| 909/938 [00:51<00:01, 17.61it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  94%|█████████▍| 440/469 [00:18<00:01, 25.14it/s]
Epoch 1:  97%|█████████▋| 912/938 [00:51<00:01, 17.63it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  94%|█████████▍| 443/469 [00:18<00:01, 25.36it/s]
Epoch 1:  98%|█████████▊| 915/938 [00:51<00:01, 17.65it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  95%|█████████▌| 446/469 [00:18<00:00, 25.60it/s]
Epoch 1:  98%|█████████▊| 918/938 [00:52<00:01, 17.65it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  96%|█████████▌| 449/469 [00:18<00:00, 22.59it/s]
Epoch 1:  98%|█████████▊| 921/938 [00:52<00:00, 17.67it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  96%|█████████▋| 452/469 [00:18<00:00, 23.55it/s]
Epoch 1:  99%|█████████▊| 924/938 [00:52<00:00, 17.68it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  97%|█████████▋| 455/469 [00:18<00:00, 23.35it/s]
Epoch 1:  99%|█████████▉| 927/938 [00:52<00:00, 17.70it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  98%|█████████▊| 458/469 [00:18<00:00, 23.85it/s]
Epoch 1:  99%|█████████▉| 930/938 [00:52<00:00, 17.71it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  98%|█████████▊| 461/469 [00:18<00:00, 24.10it/s]
Epoch 1:  99%|█████████▉| 933/938 [00:52<00:00, 17.73it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating:  99%|█████████▉| 464/469 [00:19<00:00, 24.58it/s]
Epoch 1: 100%|█████████▉| 936/938 [00:52<00:00, 17.75it/s, loss=0.749, v_num=16, val_rmse=0.654, train_rmse=1.190]

Validating: 100%|█████████▉| 467/469 [00:19<00:00, 25.70it/s]
Epoch 1: 100%|██████████| 938/938 [00:52<00:00, 17.76it/s, loss=0.749, v_num=16, val_rmse=0.579, train_rmse=1.190]

                                                             
Epoch 1: 100%|██████████| 938/938 [00:52<00:00, 17.75it/s, loss=0.749, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 1:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.749, v_num=16, val_rmse=0.579, train_rmse=0.724]          
Epoch 2:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.749, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   0%|          | 1/938 [00:00<01:28, 10.54it/s, loss=0.745, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   0%|          | 2/938 [00:00<01:16, 12.21it/s, loss=0.747, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   0%|          | 3/938 [00:00<01:07, 13.76it/s, loss=0.747, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   0%|          | 3/938 [00:00<01:08, 13.72it/s, loss=0.748, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   0%|          | 4/938 [00:00<01:11, 13.03it/s, loss=0.738, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   1%|          | 5/938 [00:00<01:08, 13.53it/s, loss=0.729, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   1%|          | 6/938 [00:00<01:09, 13.37it/s, loss=0.729, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   1%|          | 6/938 [00:00<01:09, 13.35it/s, loss=0.729, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   1%|          | 7/938 [00:00<01:07, 13.81it/s, loss=0.721, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   1%|          | 8/938 [00:00<01:08, 13.67it/s, loss=0.725, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   1%|          | 9/938 [00:00<01:07, 13.69it/s, loss=0.725, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   1%|          | 9/938 [00:00<01:07, 13.68it/s, loss=0.724, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   1%|          | 10/938 [00:00<01:09, 13.42it/s, loss=0.725, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   1%|          | 11/938 [00:00<01:07, 13.64it/s, loss=0.712, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   1%|▏         | 12/938 [00:00<01:07, 13.65it/s, loss=0.712, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   1%|▏         | 12/938 [00:00<01:07, 13.64it/s, loss=0.716, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   1%|▏         | 13/938 [00:00<01:07, 13.73it/s, loss=0.714, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   1%|▏         | 14/938 [00:01<01:06, 13.94it/s, loss=0.72, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:   2%|▏         | 15/938 [00:01<01:06, 13.94it/s, loss=0.72, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   2%|▏         | 15/938 [00:01<01:06, 13.93it/s, loss=0.71, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   2%|▏         | 16/938 [00:01<01:05, 14.08it/s, loss=0.704, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   2%|▏         | 17/938 [00:01<01:05, 14.08it/s, loss=0.704, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   2%|▏         | 18/938 [00:01<01:04, 14.16it/s, loss=0.704, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   2%|▏         | 18/938 [00:01<01:05, 14.15it/s, loss=0.698, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   2%|▏         | 19/938 [00:01<01:05, 14.08it/s, loss=0.711, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   2%|▏         | 20/938 [00:01<01:05, 14.08it/s, loss=0.705, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   2%|▏         | 21/938 [00:01<01:05, 14.08it/s, loss=0.705, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   2%|▏         | 21/938 [00:01<01:05, 14.08it/s, loss=0.696, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   2%|▏         | 22/938 [00:01<01:04, 14.16it/s, loss=0.694, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   2%|▏         | 23/938 [00:01<01:05, 14.05it/s, loss=0.683, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   3%|▎         | 24/938 [00:01<01:05, 13.99it/s, loss=0.683, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   3%|▎         | 24/938 [00:01<01:05, 13.99it/s, loss=0.681, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   3%|▎         | 25/938 [00:01<01:04, 14.14it/s, loss=0.687, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   3%|▎         | 26/938 [00:01<01:04, 14.03it/s, loss=0.685, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   3%|▎         | 27/938 [00:01<01:05, 13.97it/s, loss=0.685, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   3%|▎         | 27/938 [00:01<01:05, 13.96it/s, loss=0.69, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:   3%|▎         | 28/938 [00:01<01:04, 14.04it/s, loss=0.684, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   3%|▎         | 29/938 [00:02<01:04, 13.99it/s, loss=0.683, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   3%|▎         | 30/938 [00:02<01:04, 14.07it/s, loss=0.683, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   3%|▎         | 30/938 [00:02<01:04, 14.06it/s, loss=0.688, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   3%|▎         | 31/938 [00:02<01:04, 14.10it/s, loss=0.692, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   3%|▎         | 32/938 [00:02<01:04, 14.02it/s, loss=0.686, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   4%|▎         | 33/938 [00:02<01:04, 14.04it/s, loss=0.686, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   4%|▎         | 33/938 [00:02<01:04, 14.03it/s, loss=0.681, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   4%|▎         | 34/938 [00:02<01:04, 14.04it/s, loss=0.676, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   4%|▎         | 35/938 [00:02<01:04, 14.07it/s, loss=0.679, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   4%|▍         | 36/938 [00:02<01:03, 14.14it/s, loss=0.679, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   4%|▍         | 36/938 [00:02<01:03, 14.13it/s, loss=0.68, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:   4%|▍         | 37/938 [00:02<01:03, 14.09it/s, loss=0.68, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   4%|▍         | 38/938 [00:02<01:03, 14.09it/s, loss=0.673, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   4%|▍         | 39/938 [00:02<01:03, 14.09it/s, loss=0.673, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   4%|▍         | 39/938 [00:02<01:03, 14.09it/s, loss=0.664, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   4%|▍         | 40/938 [00:02<01:03, 14.14it/s, loss=0.666, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   4%|▍         | 41/938 [00:02<01:03, 14.15it/s, loss=0.66, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:   4%|▍         | 42/938 [00:02<01:03, 14.19it/s, loss=0.66, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   4%|▍         | 42/938 [00:02<01:03, 14.19it/s, loss=0.655, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   5%|▍         | 43/938 [00:03<01:02, 14.22it/s, loss=0.662, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   5%|▍         | 44/938 [00:03<01:02, 14.22it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   5%|▍         | 45/938 [00:03<01:03, 14.14it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   5%|▍         | 45/938 [00:03<01:03, 14.14it/s, loss=0.648, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   5%|▍         | 46/938 [00:03<01:03, 14.15it/s, loss=0.652, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   5%|▌         | 47/938 [00:03<01:02, 14.24it/s, loss=0.648, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   5%|▌         | 48/938 [00:03<01:02, 14.21it/s, loss=0.648, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   5%|▌         | 48/938 [00:03<01:02, 14.21it/s, loss=0.643, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   5%|▌         | 49/938 [00:03<01:02, 14.22it/s, loss=0.65, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:   5%|▌         | 50/938 [00:03<01:02, 14.18it/s, loss=0.652, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   5%|▌         | 51/938 [00:03<01:02, 14.21it/s, loss=0.652, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   5%|▌         | 51/938 [00:03<01:02, 14.21it/s, loss=0.65, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:   6%|▌         | 52/938 [00:03<01:02, 14.18it/s, loss=0.657, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   6%|▌         | 53/938 [00:03<01:02, 14.15it/s, loss=0.663, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   6%|▌         | 54/938 [00:03<01:02, 14.07it/s, loss=0.663, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   6%|▌         | 54/938 [00:03<01:02, 14.07it/s, loss=0.669, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   6%|▌         | 55/938 [00:03<01:02, 14.12it/s, loss=0.67, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:   6%|▌         | 56/938 [00:04<01:03, 13.91it/s, loss=0.671, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   6%|▌         | 57/938 [00:04<01:03, 13.95it/s, loss=0.671, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   6%|▌         | 57/938 [00:04<01:03, 13.94it/s, loss=0.673, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   6%|▌         | 58/938 [00:04<01:03, 13.92it/s, loss=0.682, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   6%|▋         | 59/938 [00:04<01:03, 13.93it/s, loss=0.686, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   6%|▋         | 60/938 [00:04<01:03, 13.91it/s, loss=0.686, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   6%|▋         | 60/938 [00:04<01:03, 13.91it/s, loss=0.687, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   7%|▋         | 61/938 [00:04<01:02, 13.92it/s, loss=0.694, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   7%|▋         | 62/938 [00:04<01:02, 13.95it/s, loss=0.697, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   7%|▋         | 63/938 [00:04<01:02, 13.97it/s, loss=0.697, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   7%|▋         | 63/938 [00:04<01:02, 13.96it/s, loss=0.696, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   7%|▋         | 64/938 [00:04<01:02, 13.98it/s, loss=0.709, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   7%|▋         | 65/938 [00:04<01:02, 13.91it/s, loss=0.703, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   7%|▋         | 66/938 [00:04<01:02, 13.93it/s, loss=0.703, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   7%|▋         | 66/938 [00:04<01:02, 13.92it/s, loss=0.701, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   7%|▋         | 67/938 [00:04<01:02, 13.94it/s, loss=0.701, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   7%|▋         | 68/938 [00:04<01:02, 13.93it/s, loss=0.709, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   7%|▋         | 69/938 [00:04<01:02, 13.92it/s, loss=0.709, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   7%|▋         | 69/938 [00:04<01:02, 13.92it/s, loss=0.703, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   7%|▋         | 70/938 [00:05<01:02, 13.93it/s, loss=0.693, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   8%|▊         | 71/938 [00:05<01:02, 13.94it/s, loss=0.699, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   8%|▊         | 72/938 [00:05<01:01, 13.98it/s, loss=0.699, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   8%|▊         | 72/938 [00:05<01:01, 13.98it/s, loss=0.688, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   8%|▊         | 73/938 [00:05<01:01, 13.99it/s, loss=0.687, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   8%|▊         | 74/938 [00:05<01:01, 13.98it/s, loss=0.683, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   8%|▊         | 75/938 [00:05<01:01, 13.98it/s, loss=0.683, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   8%|▊         | 75/938 [00:05<01:01, 13.98it/s, loss=0.686, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   8%|▊         | 76/938 [00:05<01:01, 13.99it/s, loss=0.686, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   8%|▊         | 77/938 [00:05<01:01, 13.96it/s, loss=0.685, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   8%|▊         | 78/938 [00:05<01:01, 13.97it/s, loss=0.685, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   8%|▊         | 78/938 [00:05<01:01, 13.97it/s, loss=0.681, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   8%|▊         | 79/938 [00:05<01:01, 13.95it/s, loss=0.681, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   9%|▊         | 80/938 [00:05<01:01, 13.98it/s, loss=0.674, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   9%|▊         | 81/938 [00:05<01:01, 13.99it/s, loss=0.674, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   9%|▊         | 81/938 [00:05<01:01, 13.99it/s, loss=0.683, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   9%|▊         | 82/938 [00:05<01:01, 14.00it/s, loss=0.685, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   9%|▉         | 83/938 [00:05<01:01, 13.98it/s, loss=0.688, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   9%|▉         | 84/938 [00:05<01:00, 14.01it/s, loss=0.688, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   9%|▉         | 84/938 [00:05<01:00, 14.01it/s, loss=0.689, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   9%|▉         | 85/938 [00:06<01:00, 14.04it/s, loss=0.693, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   9%|▉         | 86/938 [00:06<01:00, 14.01it/s, loss=0.699, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   9%|▉         | 87/938 [00:06<01:00, 14.03it/s, loss=0.699, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   9%|▉         | 87/938 [00:06<01:00, 14.03it/s, loss=0.702, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   9%|▉         | 88/938 [00:06<01:00, 14.01it/s, loss=0.699, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:   9%|▉         | 89/938 [00:06<01:00, 14.02it/s, loss=0.695, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  10%|▉         | 90/938 [00:06<01:00, 14.00it/s, loss=0.695, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  10%|▉         | 90/938 [00:06<01:00, 14.00it/s, loss=0.691, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  10%|▉         | 91/938 [00:06<01:00, 13.98it/s, loss=0.69, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  10%|▉         | 92/938 [00:06<01:00, 13.98it/s, loss=0.695, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  10%|▉         | 93/938 [00:06<01:00, 13.98it/s, loss=0.695, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  10%|▉         | 93/938 [00:06<01:00, 13.98it/s, loss=0.688, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  10%|█         | 94/938 [00:06<01:00, 13.97it/s, loss=0.693, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  10%|█         | 95/938 [00:06<01:00, 14.00it/s, loss=0.697, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  10%|█         | 96/938 [00:06<01:00, 14.01it/s, loss=0.697, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  10%|█         | 96/938 [00:06<01:00, 14.01it/s, loss=0.695, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  10%|█         | 97/938 [00:06<00:59, 14.02it/s, loss=0.702, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  10%|█         | 98/938 [00:06<00:59, 14.00it/s, loss=0.697, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  11%|█         | 99/938 [00:07<00:59, 13.99it/s, loss=0.697, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  11%|█         | 99/938 [00:07<00:59, 13.99it/s, loss=0.69, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  11%|█         | 100/938 [00:07<00:59, 13.98it/s, loss=0.698, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  11%|█         | 101/938 [00:07<00:59, 13.99it/s, loss=0.687, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  11%|█         | 102/938 [00:07<00:59, 13.99it/s, loss=0.687, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  11%|█         | 102/938 [00:07<00:59, 13.99it/s, loss=0.682, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  11%|█         | 103/938 [00:07<00:59, 13.99it/s, loss=0.684, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  11%|█         | 104/938 [00:07<00:59, 14.00it/s, loss=0.675, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  11%|█         | 105/938 [00:07<00:59, 13.98it/s, loss=0.675, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  11%|█         | 105/938 [00:07<00:59, 13.98it/s, loss=0.673, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  11%|█▏        | 106/938 [00:07<00:59, 14.00it/s, loss=0.67, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  11%|█▏        | 107/938 [00:07<00:59, 13.98it/s, loss=0.663, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  12%|█▏        | 108/938 [00:07<00:59, 13.99it/s, loss=0.663, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  12%|█▏        | 108/938 [00:07<00:59, 13.99it/s, loss=0.668, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  12%|█▏        | 109/938 [00:07<00:59, 14.00it/s, loss=0.666, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  12%|█▏        | 110/938 [00:07<00:59, 14.00it/s, loss=0.672, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  12%|█▏        | 111/938 [00:07<00:59, 13.99it/s, loss=0.672, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  12%|█▏        | 111/938 [00:07<00:59, 13.99it/s, loss=0.67, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  12%|█▏        | 112/938 [00:07<00:58, 14.02it/s, loss=0.672, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  12%|█▏        | 113/938 [00:08<00:58, 14.03it/s, loss=0.674, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  12%|█▏        | 114/938 [00:08<00:58, 14.01it/s, loss=0.674, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  12%|█▏        | 114/938 [00:08<00:58, 14.01it/s, loss=0.669, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  12%|█▏        | 115/938 [00:08<00:58, 14.03it/s, loss=0.668, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  12%|█▏        | 116/938 [00:08<00:58, 14.01it/s, loss=0.662, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  12%|█▏        | 117/938 [00:08<00:58, 13.97it/s, loss=0.662, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  12%|█▏        | 117/938 [00:08<00:58, 13.97it/s, loss=0.661, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  13%|█▎        | 118/938 [00:08<00:58, 13.98it/s, loss=0.664, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  13%|█▎        | 119/938 [00:08<00:58, 14.00it/s, loss=0.668, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  13%|█▎        | 120/938 [00:08<00:58, 14.01it/s, loss=0.668, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  13%|█▎        | 120/938 [00:08<00:58, 14.01it/s, loss=0.667, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  13%|█▎        | 121/938 [00:08<00:58, 14.01it/s, loss=0.667, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  13%|█▎        | 122/938 [00:08<00:58, 14.01it/s, loss=0.66, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  13%|█▎        | 123/938 [00:08<00:58, 13.99it/s, loss=0.66, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  13%|█▎        | 123/938 [00:08<00:58, 13.99it/s, loss=0.654, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  13%|█▎        | 124/938 [00:08<00:58, 14.01it/s, loss=0.653, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  13%|█▎        | 125/938 [00:08<00:58, 14.00it/s, loss=0.66, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  13%|█▎        | 126/938 [00:08<00:57, 14.01it/s, loss=0.66, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  13%|█▎        | 126/938 [00:08<00:57, 14.01it/s, loss=0.663, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  14%|█▎        | 127/938 [00:09<00:57, 14.00it/s, loss=0.662, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  14%|█▎        | 128/938 [00:09<00:57, 14.01it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  14%|█▍        | 129/938 [00:09<00:57, 14.00it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  14%|█▍        | 129/938 [00:09<00:57, 14.00it/s, loss=0.671, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  14%|█▍        | 130/938 [00:09<00:57, 14.02it/s, loss=0.674, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  14%|█▍        | 131/938 [00:09<00:57, 14.04it/s, loss=0.676, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  14%|█▍        | 132/938 [00:09<00:57, 14.04it/s, loss=0.676, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  14%|█▍        | 132/938 [00:09<00:57, 14.04it/s, loss=0.676, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  14%|█▍        | 133/938 [00:09<00:57, 14.01it/s, loss=0.68, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  14%|█▍        | 134/938 [00:09<00:57, 14.03it/s, loss=0.676, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  14%|█▍        | 135/938 [00:09<00:57, 14.05it/s, loss=0.676, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  14%|█▍        | 135/938 [00:09<00:57, 14.05it/s, loss=0.678, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  14%|█▍        | 136/938 [00:09<00:57, 14.04it/s, loss=0.685, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  15%|█▍        | 137/938 [00:09<00:56, 14.05it/s, loss=0.679, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  15%|█▍        | 138/938 [00:09<00:56, 14.07it/s, loss=0.679, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  15%|█▍        | 138/938 [00:09<00:56, 14.07it/s, loss=0.678, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  15%|█▍        | 139/938 [00:09<00:56, 14.07it/s, loss=0.673, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  15%|█▍        | 140/938 [00:09<00:56, 14.08it/s, loss=0.671, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  15%|█▌        | 141/938 [00:10<00:56, 14.06it/s, loss=0.671, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  15%|█▌        | 141/938 [00:10<00:56, 14.06it/s, loss=0.674, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  15%|█▌        | 142/938 [00:10<00:56, 14.06it/s, loss=0.679, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  15%|█▌        | 143/938 [00:10<00:56, 14.05it/s, loss=0.684, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  15%|█▌        | 144/938 [00:10<00:56, 14.06it/s, loss=0.684, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  15%|█▌        | 144/938 [00:10<00:56, 14.06it/s, loss=0.689, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  15%|█▌        | 145/938 [00:10<00:56, 14.06it/s, loss=0.684, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  16%|█▌        | 146/938 [00:10<00:56, 14.07it/s, loss=0.678, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  16%|█▌        | 147/938 [00:10<00:56, 14.06it/s, loss=0.678, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  16%|█▌        | 147/938 [00:10<00:56, 14.06it/s, loss=0.681, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  16%|█▌        | 148/938 [00:10<00:56, 14.06it/s, loss=0.678, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  16%|█▌        | 149/938 [00:10<00:56, 14.05it/s, loss=0.672, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  16%|█▌        | 150/938 [00:10<00:56, 14.04it/s, loss=0.672, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  16%|█▌        | 150/938 [00:10<00:56, 14.04it/s, loss=0.669, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  16%|█▌        | 151/938 [00:10<00:56, 14.05it/s, loss=0.665, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  16%|█▌        | 152/938 [00:10<00:55, 14.04it/s, loss=0.666, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  16%|█▋        | 153/938 [00:10<00:55, 14.05it/s, loss=0.666, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  16%|█▋        | 153/938 [00:10<00:55, 14.05it/s, loss=0.657, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  16%|█▋        | 154/938 [00:10<00:55, 14.04it/s, loss=0.665, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  17%|█▋        | 155/938 [00:11<00:55, 14.04it/s, loss=0.661, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  17%|█▋        | 156/938 [00:11<00:55, 14.04it/s, loss=0.661, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  17%|█▋        | 156/938 [00:11<00:55, 14.04it/s, loss=0.666, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  17%|█▋        | 157/938 [00:11<00:55, 14.02it/s, loss=0.672, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  17%|█▋        | 158/938 [00:11<00:55, 14.02it/s, loss=0.671, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  17%|█▋        | 159/938 [00:11<00:55, 14.03it/s, loss=0.671, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  17%|█▋        | 159/938 [00:11<00:55, 14.03it/s, loss=0.673, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  17%|█▋        | 160/938 [00:11<00:55, 14.02it/s, loss=0.666, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  17%|█▋        | 161/938 [00:11<00:55, 14.03it/s, loss=0.669, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  17%|█▋        | 162/938 [00:11<00:55, 14.02it/s, loss=0.669, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  17%|█▋        | 162/938 [00:11<00:55, 14.01it/s, loss=0.669, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  17%|█▋        | 163/938 [00:11<00:55, 14.00it/s, loss=0.668, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  17%|█▋        | 164/938 [00:11<00:55, 13.98it/s, loss=0.66, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  18%|█▊        | 165/938 [00:11<00:55, 13.98it/s, loss=0.66, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  18%|█▊        | 165/938 [00:11<00:55, 13.98it/s, loss=0.67, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  18%|█▊        | 166/938 [00:11<00:55, 13.98it/s, loss=0.678, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  18%|█▊        | 167/938 [00:11<00:55, 13.97it/s, loss=0.689, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  18%|█▊        | 168/938 [00:12<00:55, 13.98it/s, loss=0.689, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  18%|█▊        | 168/938 [00:12<00:55, 13.98it/s, loss=0.7, v_num=16, val_rmse=0.579, train_rmse=0.724]  
Epoch 2:  18%|█▊        | 169/938 [00:12<00:55, 13.98it/s, loss=0.694, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  18%|█▊        | 170/938 [00:12<00:54, 14.00it/s, loss=0.687, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  18%|█▊        | 171/938 [00:12<00:54, 14.00it/s, loss=0.687, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  18%|█▊        | 171/938 [00:12<00:54, 14.00it/s, loss=0.696, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  18%|█▊        | 172/938 [00:12<00:54, 14.01it/s, loss=0.698, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  18%|█▊        | 173/938 [00:12<00:54, 14.01it/s, loss=0.708, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  19%|█▊        | 174/938 [00:12<00:54, 14.01it/s, loss=0.708, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  19%|█▊        | 174/938 [00:12<00:54, 14.01it/s, loss=0.708, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  19%|█▊        | 175/938 [00:12<00:54, 14.02it/s, loss=0.709, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  19%|█▉        | 176/938 [00:12<00:54, 14.00it/s, loss=0.696, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  19%|█▉        | 177/938 [00:12<00:54, 13.99it/s, loss=0.696, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  19%|█▉        | 177/938 [00:12<00:54, 13.99it/s, loss=0.689, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  19%|█▉        | 178/938 [00:12<00:54, 13.99it/s, loss=0.687, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  19%|█▉        | 179/938 [00:12<00:54, 14.00it/s, loss=0.689, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  19%|█▉        | 180/938 [00:12<00:54, 13.98it/s, loss=0.689, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  19%|█▉        | 180/938 [00:12<00:54, 13.98it/s, loss=0.687, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  19%|█▉        | 181/938 [00:12<00:54, 13.97it/s, loss=0.684, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  19%|█▉        | 182/938 [00:13<00:54, 13.97it/s, loss=0.686, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  20%|█▉        | 183/938 [00:13<00:54, 13.97it/s, loss=0.686, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  20%|█▉        | 183/938 [00:13<00:54, 13.97it/s, loss=0.687, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  20%|█▉        | 184/938 [00:13<00:53, 13.96it/s, loss=0.691, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  20%|█▉        | 185/938 [00:13<00:53, 13.98it/s, loss=0.682, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  20%|█▉        | 186/938 [00:13<00:53, 13.95it/s, loss=0.682, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  20%|█▉        | 186/938 [00:13<00:53, 13.95it/s, loss=0.672, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  20%|█▉        | 187/938 [00:13<00:53, 13.95it/s, loss=0.663, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  20%|██        | 188/938 [00:13<00:53, 13.96it/s, loss=0.657, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  20%|██        | 189/938 [00:13<00:53, 13.96it/s, loss=0.657, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  20%|██        | 189/938 [00:13<00:53, 13.96it/s, loss=0.653, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  20%|██        | 190/938 [00:13<00:53, 13.97it/s, loss=0.654, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  20%|██        | 191/938 [00:13<00:53, 13.97it/s, loss=0.649, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  20%|██        | 192/938 [00:13<00:53, 13.96it/s, loss=0.649, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  20%|██        | 192/938 [00:13<00:53, 13.96it/s, loss=0.646, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  21%|██        | 193/938 [00:13<00:53, 13.97it/s, loss=0.644, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  21%|██        | 194/938 [00:13<00:53, 13.96it/s, loss=0.652, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  21%|██        | 195/938 [00:13<00:53, 13.96it/s, loss=0.652, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  21%|██        | 195/938 [00:13<00:53, 13.96it/s, loss=0.648, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  21%|██        | 196/938 [00:14<00:53, 13.95it/s, loss=0.66, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  21%|██        | 197/938 [00:14<00:53, 13.95it/s, loss=0.665, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  21%|██        | 198/938 [00:14<00:53, 13.95it/s, loss=0.665, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  21%|██        | 198/938 [00:14<00:53, 13.95it/s, loss=0.672, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  21%|██        | 199/938 [00:14<00:53, 13.94it/s, loss=0.677, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  21%|██▏       | 200/938 [00:14<00:52, 13.96it/s, loss=0.681, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  21%|██▏       | 201/938 [00:14<00:52, 13.96it/s, loss=0.681, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  21%|██▏       | 201/938 [00:14<00:52, 13.96it/s, loss=0.683, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  22%|██▏       | 202/938 [00:14<00:52, 13.96it/s, loss=0.691, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  22%|██▏       | 203/938 [00:14<00:52, 13.95it/s, loss=0.69, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  22%|██▏       | 204/938 [00:14<00:52, 13.96it/s, loss=0.69, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  22%|██▏       | 204/938 [00:14<00:52, 13.96it/s, loss=0.689, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  22%|██▏       | 205/938 [00:14<00:52, 13.97it/s, loss=0.694, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  22%|██▏       | 206/938 [00:14<00:52, 13.98it/s, loss=0.704, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  22%|██▏       | 207/938 [00:14<00:52, 13.99it/s, loss=0.704, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  22%|██▏       | 207/938 [00:14<00:52, 13.99it/s, loss=0.7, v_num=16, val_rmse=0.579, train_rmse=0.724]  
Epoch 2:  22%|██▏       | 208/938 [00:14<00:52, 13.98it/s, loss=0.705, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  22%|██▏       | 209/938 [00:14<00:52, 13.99it/s, loss=0.708, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  22%|██▏       | 210/938 [00:15<00:52, 13.99it/s, loss=0.708, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  22%|██▏       | 210/938 [00:15<00:52, 13.99it/s, loss=0.713, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  22%|██▏       | 211/938 [00:15<00:51, 14.00it/s, loss=0.714, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  23%|██▎       | 212/938 [00:15<00:51, 14.00it/s, loss=0.716, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  23%|██▎       | 213/938 [00:15<00:51, 14.01it/s, loss=0.716, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  23%|██▎       | 213/938 [00:15<00:51, 14.01it/s, loss=0.714, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  23%|██▎       | 214/938 [00:15<00:51, 14.00it/s, loss=0.704, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  23%|██▎       | 215/938 [00:15<00:51, 13.99it/s, loss=0.709, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  23%|██▎       | 216/938 [00:15<00:51, 13.97it/s, loss=0.709, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  23%|██▎       | 216/938 [00:15<00:51, 13.97it/s, loss=0.703, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  23%|██▎       | 217/938 [00:15<00:51, 13.97it/s, loss=0.701, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  23%|██▎       | 218/938 [00:15<00:51, 13.96it/s, loss=0.7, v_num=16, val_rmse=0.579, train_rmse=0.724]  
Epoch 2:  23%|██▎       | 219/938 [00:15<00:51, 13.96it/s, loss=0.7, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  23%|██▎       | 219/938 [00:15<00:51, 13.96it/s, loss=0.698, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  23%|██▎       | 220/938 [00:15<00:51, 13.96it/s, loss=0.701, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  24%|██▎       | 221/938 [00:15<00:51, 13.97it/s, loss=0.695, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  24%|██▎       | 222/938 [00:15<00:51, 13.98it/s, loss=0.695, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  24%|██▎       | 222/938 [00:15<00:51, 13.98it/s, loss=0.688, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  24%|██▍       | 223/938 [00:15<00:51, 13.98it/s, loss=0.681, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  24%|██▍       | 224/938 [00:16<00:51, 13.98it/s, loss=0.681, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  24%|██▍       | 225/938 [00:16<00:50, 14.00it/s, loss=0.681, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  24%|██▍       | 225/938 [00:16<00:50, 14.00it/s, loss=0.672, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  24%|██▍       | 226/938 [00:16<00:50, 13.99it/s, loss=0.669, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  24%|██▍       | 227/938 [00:16<00:50, 14.00it/s, loss=0.666, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  24%|██▍       | 228/938 [00:16<00:50, 14.00it/s, loss=0.666, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  24%|██▍       | 228/938 [00:16<00:50, 14.00it/s, loss=0.667, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  24%|██▍       | 229/938 [00:16<00:50, 14.00it/s, loss=0.675, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  25%|██▍       | 230/938 [00:16<00:50, 14.00it/s, loss=0.678, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  25%|██▍       | 231/938 [00:16<00:50, 14.00it/s, loss=0.678, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  25%|██▍       | 231/938 [00:16<00:50, 14.00it/s, loss=0.673, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  25%|██▍       | 232/938 [00:16<00:50, 14.00it/s, loss=0.665, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  25%|██▍       | 233/938 [00:16<00:50, 14.00it/s, loss=0.676, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  25%|██▍       | 234/938 [00:16<00:50, 14.00it/s, loss=0.676, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  25%|██▍       | 234/938 [00:16<00:50, 14.00it/s, loss=0.678, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  25%|██▌       | 235/938 [00:16<00:50, 14.01it/s, loss=0.675, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  25%|██▌       | 236/938 [00:16<00:50, 14.00it/s, loss=0.674, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  25%|██▌       | 237/938 [00:16<00:50, 14.00it/s, loss=0.674, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  25%|██▌       | 237/938 [00:16<00:50, 14.00it/s, loss=0.67, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  25%|██▌       | 238/938 [00:17<00:50, 14.00it/s, loss=0.661, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  25%|██▌       | 239/938 [00:17<00:49, 14.00it/s, loss=0.657, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  26%|██▌       | 240/938 [00:17<00:49, 14.00it/s, loss=0.657, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  26%|██▌       | 240/938 [00:17<00:49, 14.00it/s, loss=0.654, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  26%|██▌       | 241/938 [00:17<00:49, 14.01it/s, loss=0.659, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  26%|██▌       | 242/938 [00:17<00:49, 14.01it/s, loss=0.66, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  26%|██▌       | 243/938 [00:17<00:49, 14.01it/s, loss=0.66, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  26%|██▌       | 243/938 [00:17<00:49, 14.01it/s, loss=0.661, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  26%|██▌       | 244/938 [00:17<00:49, 14.00it/s, loss=0.659, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  26%|██▌       | 245/938 [00:17<00:49, 14.00it/s, loss=0.668, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  26%|██▌       | 246/938 [00:17<00:49, 14.00it/s, loss=0.668, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  26%|██▌       | 246/938 [00:17<00:49, 14.00it/s, loss=0.671, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  26%|██▋       | 247/938 [00:17<00:49, 13.99it/s, loss=0.673, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  26%|██▋       | 248/938 [00:17<00:49, 13.99it/s, loss=0.667, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  27%|██▋       | 249/938 [00:17<00:49, 13.99it/s, loss=0.667, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  27%|██▋       | 249/938 [00:17<00:49, 13.99it/s, loss=0.661, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  27%|██▋       | 250/938 [00:17<00:49, 13.98it/s, loss=0.654, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  27%|██▋       | 251/938 [00:17<00:49, 13.99it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  27%|██▋       | 252/938 [00:18<00:49, 13.98it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  27%|██▋       | 252/938 [00:18<00:49, 13.98it/s, loss=0.659, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  27%|██▋       | 253/938 [00:18<00:48, 13.98it/s, loss=0.652, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  27%|██▋       | 254/938 [00:18<00:48, 13.99it/s, loss=0.648, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  27%|██▋       | 255/938 [00:18<00:48, 13.99it/s, loss=0.648, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  27%|██▋       | 255/938 [00:18<00:48, 13.99it/s, loss=0.652, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  27%|██▋       | 256/938 [00:18<00:48, 13.99it/s, loss=0.652, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  27%|██▋       | 257/938 [00:18<00:48, 13.98it/s, loss=0.653, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  28%|██▊       | 258/938 [00:18<00:48, 13.98it/s, loss=0.653, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  28%|██▊       | 258/938 [00:18<00:48, 13.98it/s, loss=0.658, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  28%|██▊       | 259/938 [00:18<00:48, 13.97it/s, loss=0.66, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  28%|██▊       | 260/938 [00:18<00:48, 13.97it/s, loss=0.668, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  28%|██▊       | 261/938 [00:18<00:48, 13.96it/s, loss=0.668, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  28%|██▊       | 261/938 [00:18<00:48, 13.96it/s, loss=0.664, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  28%|██▊       | 262/938 [00:18<00:48, 13.97it/s, loss=0.66, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  28%|██▊       | 263/938 [00:18<00:48, 13.96it/s, loss=0.657, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  28%|██▊       | 264/938 [00:18<00:48, 13.97it/s, loss=0.657, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  28%|██▊       | 264/938 [00:18<00:48, 13.97it/s, loss=0.651, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  28%|██▊       | 265/938 [00:18<00:48, 13.97it/s, loss=0.65, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  28%|██▊       | 266/938 [00:19<00:48, 13.96it/s, loss=0.639, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  28%|██▊       | 267/938 [00:19<00:48, 13.97it/s, loss=0.639, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  28%|██▊       | 267/938 [00:19<00:48, 13.97it/s, loss=0.64, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  29%|██▊       | 268/938 [00:19<00:47, 13.98it/s, loss=0.635, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  29%|██▊       | 269/938 [00:19<00:47, 13.99it/s, loss=0.633, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  29%|██▉       | 270/938 [00:19<00:47, 13.99it/s, loss=0.633, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  29%|██▉       | 270/938 [00:19<00:47, 13.99it/s, loss=0.634, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  29%|██▉       | 271/938 [00:19<00:47, 13.99it/s, loss=0.631, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  29%|██▉       | 272/938 [00:19<00:47, 13.98it/s, loss=0.636, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  29%|██▉       | 273/938 [00:19<00:47, 13.98it/s, loss=0.636, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  29%|██▉       | 273/938 [00:19<00:47, 13.98it/s, loss=0.633, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  29%|██▉       | 274/938 [00:19<00:47, 13.98it/s, loss=0.629, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  29%|██▉       | 275/938 [00:19<00:47, 13.98it/s, loss=0.622, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  29%|██▉       | 276/938 [00:19<00:47, 13.97it/s, loss=0.622, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  29%|██▉       | 276/938 [00:19<00:47, 13.97it/s, loss=0.622, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  30%|██▉       | 277/938 [00:19<00:47, 13.98it/s, loss=0.615, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  30%|██▉       | 278/938 [00:19<00:47, 13.97it/s, loss=0.619, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  30%|██▉       | 279/938 [00:19<00:47, 13.98it/s, loss=0.619, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  30%|██▉       | 279/938 [00:19<00:47, 13.98it/s, loss=0.623, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  30%|██▉       | 280/938 [00:20<00:47, 13.99it/s, loss=0.615, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  30%|██▉       | 281/938 [00:20<00:46, 13.99it/s, loss=0.622, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  30%|███       | 282/938 [00:20<00:46, 14.00it/s, loss=0.622, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  30%|███       | 282/938 [00:20<00:46, 14.00it/s, loss=0.63, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  30%|███       | 283/938 [00:20<00:46, 13.99it/s, loss=0.638, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  30%|███       | 284/938 [00:20<00:46, 14.00it/s, loss=0.644, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  30%|███       | 285/938 [00:20<00:46, 14.01it/s, loss=0.644, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  30%|███       | 285/938 [00:20<00:46, 14.01it/s, loss=0.642, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  30%|███       | 286/938 [00:20<00:46, 14.01it/s, loss=0.644, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  31%|███       | 287/938 [00:20<00:46, 14.02it/s, loss=0.649, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  31%|███       | 288/938 [00:20<00:46, 14.03it/s, loss=0.649, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  31%|███       | 288/938 [00:20<00:46, 14.02it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  31%|███       | 289/938 [00:20<00:46, 14.02it/s, loss=0.651, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  31%|███       | 290/938 [00:20<00:46, 14.02it/s, loss=0.657, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  31%|███       | 291/938 [00:20<00:46, 14.03it/s, loss=0.657, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  31%|███       | 291/938 [00:20<00:46, 14.03it/s, loss=0.653, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  31%|███       | 292/938 [00:20<00:46, 14.03it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  31%|███       | 293/938 [00:20<00:45, 14.03it/s, loss=0.658, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  31%|███▏      | 294/938 [00:20<00:45, 14.04it/s, loss=0.658, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  31%|███▏      | 294/938 [00:20<00:45, 14.04it/s, loss=0.662, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  31%|███▏      | 295/938 [00:21<00:45, 14.04it/s, loss=0.668, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  32%|███▏      | 296/938 [00:21<00:45, 14.05it/s, loss=0.673, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  32%|███▏      | 297/938 [00:21<00:45, 14.05it/s, loss=0.673, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  32%|███▏      | 297/938 [00:21<00:45, 14.05it/s, loss=0.689, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  32%|███▏      | 298/938 [00:21<00:45, 14.05it/s, loss=0.688, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  32%|███▏      | 299/938 [00:21<00:45, 14.06it/s, loss=0.686, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  32%|███▏      | 300/938 [00:21<00:45, 14.06it/s, loss=0.686, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  32%|███▏      | 300/938 [00:21<00:45, 14.06it/s, loss=0.69, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  32%|███▏      | 301/938 [00:21<00:45, 14.06it/s, loss=0.684, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  32%|███▏      | 302/938 [00:21<00:45, 14.06it/s, loss=0.677, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  32%|███▏      | 303/938 [00:21<00:45, 14.06it/s, loss=0.677, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  32%|███▏      | 303/938 [00:21<00:45, 14.06it/s, loss=0.669, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  32%|███▏      | 304/938 [00:21<00:45, 14.07it/s, loss=0.672, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  33%|███▎      | 305/938 [00:21<00:44, 14.07it/s, loss=0.675, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  33%|███▎      | 306/938 [00:21<00:44, 14.08it/s, loss=0.675, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  33%|███▎      | 306/938 [00:21<00:44, 14.08it/s, loss=0.675, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  33%|███▎      | 307/938 [00:21<00:44, 14.08it/s, loss=0.672, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  33%|███▎      | 308/938 [00:21<00:44, 14.09it/s, loss=0.673, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  33%|███▎      | 309/938 [00:21<00:44, 14.09it/s, loss=0.673, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  33%|███▎      | 309/938 [00:21<00:44, 14.09it/s, loss=0.68, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  33%|███▎      | 310/938 [00:21<00:44, 14.10it/s, loss=0.676, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  33%|███▎      | 311/938 [00:22<00:44, 14.09it/s, loss=0.682, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  33%|███▎      | 312/938 [00:22<00:44, 14.10it/s, loss=0.682, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  33%|███▎      | 312/938 [00:22<00:44, 14.10it/s, loss=0.674, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  33%|███▎      | 313/938 [00:22<00:44, 14.09it/s, loss=0.674, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  33%|███▎      | 314/938 [00:22<00:44, 14.09it/s, loss=0.669, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  34%|███▎      | 315/938 [00:22<00:44, 14.09it/s, loss=0.669, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  34%|███▎      | 315/938 [00:22<00:44, 14.09it/s, loss=0.668, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  34%|███▎      | 316/938 [00:22<00:44, 14.09it/s, loss=0.661, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  34%|███▍      | 317/938 [00:22<00:44, 14.08it/s, loss=0.655, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  34%|███▍      | 318/938 [00:22<00:44, 14.09it/s, loss=0.655, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  34%|███▍      | 318/938 [00:22<00:44, 14.09it/s, loss=0.643, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  34%|███▍      | 319/938 [00:22<00:43, 14.08it/s, loss=0.645, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  34%|███▍      | 320/938 [00:22<00:43, 14.08it/s, loss=0.646, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  34%|███▍      | 321/938 [00:22<00:43, 14.09it/s, loss=0.646, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  34%|███▍      | 321/938 [00:22<00:43, 14.09it/s, loss=0.645, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  34%|███▍      | 322/938 [00:22<00:43, 14.08it/s, loss=0.644, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  34%|███▍      | 323/938 [00:22<00:43, 14.09it/s, loss=0.649, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  35%|███▍      | 324/938 [00:23<00:43, 14.08it/s, loss=0.649, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  35%|███▍      | 324/938 [00:23<00:43, 14.08it/s, loss=0.645, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  35%|███▍      | 325/938 [00:23<00:43, 14.09it/s, loss=0.646, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  35%|███▍      | 326/938 [00:23<00:43, 14.09it/s, loss=0.651, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  35%|███▍      | 327/938 [00:23<00:43, 14.09it/s, loss=0.651, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  35%|███▍      | 327/938 [00:23<00:43, 14.09it/s, loss=0.646, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  35%|███▍      | 328/938 [00:23<00:43, 14.09it/s, loss=0.643, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  35%|███▌      | 329/938 [00:23<00:43, 14.09it/s, loss=0.639, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  35%|███▌      | 330/938 [00:23<00:43, 14.10it/s, loss=0.639, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  35%|███▌      | 330/938 [00:23<00:43, 14.10it/s, loss=0.638, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  35%|███▌      | 331/938 [00:23<00:43, 14.09it/s, loss=0.638, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  35%|███▌      | 332/938 [00:23<00:43, 14.09it/s, loss=0.639, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  36%|███▌      | 333/938 [00:23<00:42, 14.10it/s, loss=0.639, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  36%|███▌      | 333/938 [00:23<00:42, 14.10it/s, loss=0.632, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  36%|███▌      | 334/938 [00:23<00:42, 14.11it/s, loss=0.631, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  36%|███▌      | 335/938 [00:23<00:42, 14.11it/s, loss=0.63, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  36%|███▌      | 336/938 [00:23<00:42, 14.12it/s, loss=0.63, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  36%|███▌      | 336/938 [00:23<00:42, 14.12it/s, loss=0.624, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  36%|███▌      | 337/938 [00:23<00:42, 14.11it/s, loss=0.626, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  36%|███▌      | 338/938 [00:23<00:42, 14.12it/s, loss=0.637, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  36%|███▌      | 339/938 [00:24<00:42, 14.12it/s, loss=0.637, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  36%|███▌      | 339/938 [00:24<00:42, 14.12it/s, loss=0.637, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  36%|███▌      | 340/938 [00:24<00:42, 14.09it/s, loss=0.635, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  36%|███▋      | 341/938 [00:24<00:42, 14.09it/s, loss=0.636, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  36%|███▋      | 342/938 [00:24<00:42, 14.09it/s, loss=0.636, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  36%|███▋      | 342/938 [00:24<00:42, 14.09it/s, loss=0.644, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  37%|███▋      | 343/938 [00:24<00:42, 14.10it/s, loss=0.639, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  37%|███▋      | 344/938 [00:24<00:42, 14.09it/s, loss=0.643, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  37%|███▋      | 345/938 [00:24<00:42, 14.09it/s, loss=0.643, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  37%|███▋      | 345/938 [00:24<00:42, 14.09it/s, loss=0.635, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  37%|███▋      | 346/938 [00:24<00:41, 14.10it/s, loss=0.627, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  37%|███▋      | 347/938 [00:24<00:41, 14.10it/s, loss=0.632, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  37%|███▋      | 348/938 [00:24<00:41, 14.10it/s, loss=0.632, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  37%|███▋      | 348/938 [00:24<00:41, 14.10it/s, loss=0.63, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  37%|███▋      | 349/938 [00:24<00:41, 14.09it/s, loss=0.632, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  37%|███▋      | 350/938 [00:24<00:41, 14.10it/s, loss=0.633, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  37%|███▋      | 351/938 [00:24<00:41, 14.10it/s, loss=0.633, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  37%|███▋      | 351/938 [00:24<00:41, 14.10it/s, loss=0.63, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  38%|███▊      | 352/938 [00:24<00:41, 14.10it/s, loss=0.632, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  38%|███▊      | 353/938 [00:25<00:41, 14.11it/s, loss=0.629, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  38%|███▊      | 354/938 [00:25<00:41, 14.11it/s, loss=0.629, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  38%|███▊      | 354/938 [00:25<00:41, 14.11it/s, loss=0.638, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  38%|███▊      | 355/938 [00:25<00:41, 14.11it/s, loss=0.642, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  38%|███▊      | 356/938 [00:25<00:41, 14.12it/s, loss=0.652, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  38%|███▊      | 357/938 [00:25<00:41, 14.10it/s, loss=0.652, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  38%|███▊      | 357/938 [00:25<00:41, 14.10it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  38%|███▊      | 358/938 [00:25<00:41, 14.10it/s, loss=0.661, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  38%|███▊      | 359/938 [00:25<00:41, 14.09it/s, loss=0.662, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  38%|███▊      | 360/938 [00:25<00:41, 14.09it/s, loss=0.662, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  38%|███▊      | 360/938 [00:25<00:41, 14.09it/s, loss=0.659, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  38%|███▊      | 361/938 [00:25<00:40, 14.10it/s, loss=0.658, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  39%|███▊      | 362/938 [00:25<00:40, 14.09it/s, loss=0.646, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  39%|███▊      | 363/938 [00:25<00:40, 14.09it/s, loss=0.646, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  39%|███▊      | 363/938 [00:25<00:40, 14.09it/s, loss=0.647, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  39%|███▉      | 364/938 [00:25<00:40, 14.07it/s, loss=0.643, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  39%|███▉      | 365/938 [00:25<00:40, 14.07it/s, loss=0.644, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  39%|███▉      | 366/938 [00:25<00:40, 14.08it/s, loss=0.644, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  39%|███▉      | 366/938 [00:25<00:40, 14.08it/s, loss=0.64, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  39%|███▉      | 367/938 [00:26<00:40, 14.08it/s, loss=0.64, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  39%|███▉      | 368/938 [00:26<00:40, 14.09it/s, loss=0.645, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  39%|███▉      | 369/938 [00:26<00:40, 14.09it/s, loss=0.645, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  39%|███▉      | 369/938 [00:26<00:40, 14.09it/s, loss=0.645, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  39%|███▉      | 370/938 [00:26<00:40, 14.08it/s, loss=0.641, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  40%|███▉      | 371/938 [00:26<00:40, 14.08it/s, loss=0.641, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  40%|███▉      | 372/938 [00:26<00:40, 14.09it/s, loss=0.641, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  40%|███▉      | 372/938 [00:26<00:40, 14.09it/s, loss=0.644, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  40%|███▉      | 373/938 [00:26<00:40, 14.09it/s, loss=0.65, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  40%|███▉      | 374/938 [00:26<00:40, 14.10it/s, loss=0.647, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  40%|███▉      | 375/938 [00:26<00:39, 14.10it/s, loss=0.647, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  40%|███▉      | 375/938 [00:26<00:39, 14.10it/s, loss=0.646, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  40%|████      | 376/938 [00:26<00:39, 14.09it/s, loss=0.643, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  40%|████      | 377/938 [00:26<00:39, 14.09it/s, loss=0.634, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  40%|████      | 378/938 [00:26<00:39, 14.09it/s, loss=0.634, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  40%|████      | 378/938 [00:26<00:39, 14.09it/s, loss=0.625, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  40%|████      | 379/938 [00:26<00:39, 14.09it/s, loss=0.618, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  41%|████      | 380/938 [00:26<00:39, 14.10it/s, loss=0.615, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  41%|████      | 381/938 [00:27<00:39, 14.09it/s, loss=0.615, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  41%|████      | 381/938 [00:27<00:39, 14.09it/s, loss=0.619, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  41%|████      | 382/938 [00:27<00:39, 14.09it/s, loss=0.623, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  41%|████      | 383/938 [00:27<00:39, 14.09it/s, loss=0.628, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  41%|████      | 384/938 [00:27<00:39, 14.08it/s, loss=0.628, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  41%|████      | 384/938 [00:27<00:39, 14.08it/s, loss=0.637, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  41%|████      | 385/938 [00:27<00:39, 14.08it/s, loss=0.64, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  41%|████      | 386/938 [00:27<00:39, 14.08it/s, loss=0.654, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  41%|████▏     | 387/938 [00:27<00:39, 14.07it/s, loss=0.654, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  41%|████▏     | 387/938 [00:27<00:39, 14.07it/s, loss=0.651, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  41%|████▏     | 388/938 [00:27<00:39, 14.07it/s, loss=0.645, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  41%|████▏     | 389/938 [00:27<00:39, 14.07it/s, loss=0.642, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  42%|████▏     | 390/938 [00:27<00:38, 14.07it/s, loss=0.642, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  42%|████▏     | 390/938 [00:27<00:38, 14.07it/s, loss=0.644, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  42%|████▏     | 391/938 [00:27<00:38, 14.07it/s, loss=0.651, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  42%|████▏     | 392/938 [00:27<00:38, 14.08it/s, loss=0.645, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  42%|████▏     | 393/938 [00:27<00:38, 14.09it/s, loss=0.645, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  42%|████▏     | 393/938 [00:27<00:38, 14.09it/s, loss=0.642, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  42%|████▏     | 394/938 [00:27<00:38, 14.09it/s, loss=0.644, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  42%|████▏     | 395/938 [00:28<00:38, 14.09it/s, loss=0.64, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  42%|████▏     | 396/938 [00:28<00:38, 14.07it/s, loss=0.64, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  42%|████▏     | 396/938 [00:28<00:38, 14.07it/s, loss=0.642, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  42%|████▏     | 397/938 [00:28<00:38, 14.08it/s, loss=0.648, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  42%|████▏     | 398/938 [00:28<00:38, 14.08it/s, loss=0.653, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  43%|████▎     | 399/938 [00:28<00:38, 14.08it/s, loss=0.653, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  43%|████▎     | 399/938 [00:28<00:38, 14.08it/s, loss=0.654, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  43%|████▎     | 400/938 [00:28<00:38, 14.09it/s, loss=0.661, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  43%|████▎     | 401/938 [00:28<00:38, 14.09it/s, loss=0.661, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  43%|████▎     | 402/938 [00:28<00:38, 14.09it/s, loss=0.661, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  43%|████▎     | 402/938 [00:28<00:38, 14.09it/s, loss=0.661, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  43%|████▎     | 403/938 [00:28<00:37, 14.10it/s, loss=0.672, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  43%|████▎     | 404/938 [00:28<00:37, 14.11it/s, loss=0.665, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  43%|████▎     | 405/938 [00:28<00:37, 14.10it/s, loss=0.665, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  43%|████▎     | 405/938 [00:28<00:37, 14.10it/s, loss=0.669, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  43%|████▎     | 406/938 [00:28<00:37, 14.10it/s, loss=0.665, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  43%|████▎     | 407/938 [00:28<00:37, 14.10it/s, loss=0.669, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  43%|████▎     | 408/938 [00:28<00:37, 14.09it/s, loss=0.669, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  43%|████▎     | 408/938 [00:28<00:37, 14.09it/s, loss=0.671, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  44%|████▎     | 409/938 [00:29<00:37, 14.10it/s, loss=0.672, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  44%|████▎     | 410/938 [00:29<00:37, 14.10it/s, loss=0.667, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  44%|████▍     | 411/938 [00:29<00:37, 14.10it/s, loss=0.667, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  44%|████▍     | 411/938 [00:29<00:37, 14.10it/s, loss=0.683, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  44%|████▍     | 412/938 [00:29<00:37, 14.10it/s, loss=0.682, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  44%|████▍     | 413/938 [00:29<00:37, 14.09it/s, loss=0.688, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  44%|████▍     | 414/938 [00:29<00:37, 14.10it/s, loss=0.688, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  44%|████▍     | 414/938 [00:29<00:37, 14.10it/s, loss=0.686, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  44%|████▍     | 415/938 [00:29<00:37, 14.09it/s, loss=0.684, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  44%|████▍     | 416/938 [00:29<00:37, 14.10it/s, loss=0.682, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  44%|████▍     | 417/938 [00:29<00:36, 14.09it/s, loss=0.682, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  44%|████▍     | 417/938 [00:29<00:36, 14.09it/s, loss=0.671, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  45%|████▍     | 418/938 [00:29<00:36, 14.10it/s, loss=0.669, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  45%|████▍     | 419/938 [00:29<00:36, 14.10it/s, loss=0.675, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  45%|████▍     | 420/938 [00:29<00:36, 14.11it/s, loss=0.675, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  45%|████▍     | 420/938 [00:29<00:36, 14.11it/s, loss=0.673, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  45%|████▍     | 421/938 [00:29<00:36, 14.11it/s, loss=0.665, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  45%|████▍     | 422/938 [00:29<00:36, 14.11it/s, loss=0.667, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  45%|████▌     | 423/938 [00:29<00:36, 14.11it/s, loss=0.667, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  45%|████▌     | 423/938 [00:29<00:36, 14.11it/s, loss=0.659, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  45%|████▌     | 424/938 [00:30<00:36, 14.11it/s, loss=0.672, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  45%|████▌     | 425/938 [00:30<00:36, 14.11it/s, loss=0.663, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  45%|████▌     | 426/938 [00:30<00:36, 14.11it/s, loss=0.663, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  45%|████▌     | 426/938 [00:30<00:36, 14.11it/s, loss=0.662, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  46%|████▌     | 427/938 [00:30<00:36, 14.11it/s, loss=0.671, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  46%|████▌     | 428/938 [00:30<00:36, 14.11it/s, loss=0.666, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  46%|████▌     | 429/938 [00:30<00:36, 14.11it/s, loss=0.666, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  46%|████▌     | 429/938 [00:30<00:36, 14.11it/s, loss=0.676, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  46%|████▌     | 430/938 [00:30<00:36, 14.10it/s, loss=0.686, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  46%|████▌     | 431/938 [00:30<00:35, 14.10it/s, loss=0.674, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  46%|████▌     | 432/938 [00:30<00:35, 14.11it/s, loss=0.674, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  46%|████▌     | 432/938 [00:30<00:35, 14.11it/s, loss=0.681, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  46%|████▌     | 433/938 [00:30<00:35, 14.11it/s, loss=0.686, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  46%|████▋     | 434/938 [00:30<00:35, 14.11it/s, loss=0.689, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  46%|████▋     | 435/938 [00:30<00:35, 14.11it/s, loss=0.689, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  46%|████▋     | 435/938 [00:30<00:35, 14.11it/s, loss=0.692, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  46%|████▋     | 436/938 [00:30<00:35, 14.11it/s, loss=0.692, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  47%|████▋     | 437/938 [00:30<00:35, 14.11it/s, loss=0.697, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  47%|████▋     | 438/938 [00:31<00:35, 14.11it/s, loss=0.697, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  47%|████▋     | 438/938 [00:31<00:35, 14.11it/s, loss=0.693, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  47%|████▋     | 439/938 [00:31<00:35, 14.10it/s, loss=0.684, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  47%|████▋     | 440/938 [00:31<00:35, 14.11it/s, loss=0.684, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  47%|████▋     | 441/938 [00:31<00:35, 14.11it/s, loss=0.684, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  47%|████▋     | 441/938 [00:31<00:35, 14.11it/s, loss=0.689, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  47%|████▋     | 442/938 [00:31<00:35, 14.11it/s, loss=0.687, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  47%|████▋     | 443/938 [00:31<00:35, 14.11it/s, loss=0.695, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  47%|████▋     | 444/938 [00:31<00:35, 14.11it/s, loss=0.695, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  47%|████▋     | 444/938 [00:31<00:35, 14.11it/s, loss=0.683, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  47%|████▋     | 445/938 [00:31<00:34, 14.11it/s, loss=0.691, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  48%|████▊     | 446/938 [00:31<00:34, 14.10it/s, loss=0.694, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  48%|████▊     | 447/938 [00:31<00:34, 14.10it/s, loss=0.694, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  48%|████▊     | 447/938 [00:31<00:34, 14.10it/s, loss=0.683, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  48%|████▊     | 448/938 [00:31<00:34, 14.10it/s, loss=0.701, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  48%|████▊     | 449/938 [00:31<00:34, 14.10it/s, loss=0.689, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  48%|████▊     | 450/938 [00:31<00:34, 14.10it/s, loss=0.689, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  48%|████▊     | 450/938 [00:31<00:34, 14.10it/s, loss=0.689, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  48%|████▊     | 451/938 [00:31<00:34, 14.10it/s, loss=0.68, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  48%|████▊     | 452/938 [00:32<00:34, 14.10it/s, loss=0.68, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  48%|████▊     | 453/938 [00:32<00:34, 14.10it/s, loss=0.68, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  48%|████▊     | 453/938 [00:32<00:34, 14.10it/s, loss=0.672, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  48%|████▊     | 454/938 [00:32<00:34, 14.10it/s, loss=0.671, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  49%|████▊     | 455/938 [00:32<00:34, 14.10it/s, loss=0.675, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  49%|████▊     | 456/938 [00:32<00:34, 14.10it/s, loss=0.675, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  49%|████▊     | 456/938 [00:32<00:34, 14.10it/s, loss=0.673, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  49%|████▊     | 457/938 [00:32<00:34, 14.11it/s, loss=0.671, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  49%|████▉     | 458/938 [00:32<00:34, 14.11it/s, loss=0.675, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  49%|████▉     | 459/938 [00:32<00:33, 14.11it/s, loss=0.675, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  49%|████▉     | 459/938 [00:32<00:33, 14.11it/s, loss=0.678, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  49%|████▉     | 460/938 [00:32<00:33, 14.11it/s, loss=0.679, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  49%|████▉     | 461/938 [00:32<00:33, 14.11it/s, loss=0.676, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  49%|████▉     | 462/938 [00:32<00:33, 14.11it/s, loss=0.676, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  49%|████▉     | 462/938 [00:32<00:33, 14.11it/s, loss=0.682, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  49%|████▉     | 463/938 [00:32<00:33, 14.11it/s, loss=0.673, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  49%|████▉     | 464/938 [00:32<00:33, 14.12it/s, loss=0.674, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  50%|████▉     | 465/938 [00:32<00:33, 14.11it/s, loss=0.674, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  50%|████▉     | 465/938 [00:32<00:33, 14.11it/s, loss=0.668, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  50%|████▉     | 466/938 [00:33<00:33, 14.11it/s, loss=0.666, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  50%|████▉     | 467/938 [00:33<00:33, 14.11it/s, loss=0.664, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  50%|████▉     | 468/938 [00:33<00:33, 14.08it/s, loss=0.664, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2:  50%|████▉     | 468/938 [00:33<00:33, 14.08it/s, loss=0.65, v_num=16, val_rmse=0.579, train_rmse=0.724] 
Epoch 2:  50%|█████     | 469/938 [00:33<00:33, 14.10it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]
Epoch 2:  50%|█████     | 472/938 [00:33<00:32, 14.15it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:   1%|          | 3/469 [00:00<00:22, 20.42it/s]

Validating:   1%|▏         | 6/469 [00:00<00:19, 23.40it/s]
Epoch 2:  51%|█████     | 476/938 [00:33<00:32, 14.19it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:   2%|▏         | 9/469 [00:00<00:19, 23.91it/s]
Epoch 2:  51%|█████     | 480/938 [00:33<00:32, 14.25it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:   3%|▎         | 12/469 [00:00<00:20, 22.79it/s]
Epoch 2:  52%|█████▏    | 484/938 [00:33<00:31, 14.28it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:   3%|▎         | 15/469 [00:00<00:19, 23.12it/s]

Validating:   4%|▍         | 18/469 [00:00<00:18, 23.98it/s]
Epoch 2:  52%|█████▏    | 488/938 [00:34<00:31, 14.34it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:   4%|▍         | 21/469 [00:00<00:17, 25.13it/s]
Epoch 2:  52%|█████▏    | 492/938 [00:34<00:30, 14.39it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:   5%|▌         | 24/469 [00:01<00:19, 22.52it/s]
Epoch 2:  53%|█████▎    | 496/938 [00:34<00:30, 14.43it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:   6%|▌         | 27/469 [00:01<00:19, 22.85it/s]

Validating:   6%|▋         | 30/469 [00:01<00:19, 23.01it/s]
Epoch 2:  53%|█████▎    | 500/938 [00:34<00:30, 14.47it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:   7%|▋         | 33/469 [00:01<00:19, 22.92it/s]
Epoch 2:  54%|█████▎    | 504/938 [00:34<00:29, 14.51it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:   8%|▊         | 36/469 [00:01<00:17, 24.08it/s]
Epoch 2:  54%|█████▍    | 508/938 [00:34<00:29, 14.56it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:   8%|▊         | 39/469 [00:01<00:16, 25.56it/s]

Validating:   9%|▉         | 42/469 [00:01<00:16, 25.44it/s]
Epoch 2:  55%|█████▍    | 512/938 [00:35<00:29, 14.62it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  10%|▉         | 46/469 [00:01<00:15, 26.75it/s]
Epoch 2:  55%|█████▌    | 516/938 [00:35<00:28, 14.67it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  10%|█         | 49/469 [00:02<00:16, 24.94it/s]
Epoch 2:  55%|█████▌    | 520/938 [00:35<00:28, 14.71it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  11%|█         | 52/469 [00:02<00:16, 25.56it/s]
Epoch 2:  56%|█████▌    | 524/938 [00:35<00:28, 14.76it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  12%|█▏        | 55/469 [00:02<00:16, 25.62it/s]

Validating:  12%|█▏        | 58/469 [00:02<00:16, 25.65it/s]
Epoch 2:  56%|█████▋    | 528/938 [00:35<00:27, 14.81it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  13%|█▎        | 61/469 [00:02<00:15, 26.00it/s]
Epoch 2:  57%|█████▋    | 532/938 [00:35<00:27, 14.86it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  14%|█▎        | 64/469 [00:02<00:15, 26.10it/s]
Epoch 2:  57%|█████▋    | 536/938 [00:35<00:26, 14.91it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  14%|█▍        | 67/469 [00:02<00:15, 26.14it/s]

Validating:  15%|█▍        | 70/469 [00:02<00:15, 25.77it/s]
Epoch 2:  58%|█████▊    | 540/938 [00:36<00:26, 14.95it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  16%|█▌        | 73/469 [00:02<00:15, 24.96it/s]
Epoch 2:  58%|█████▊    | 544/938 [00:36<00:26, 15.00it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  16%|█▌        | 76/469 [00:03<00:15, 26.06it/s]
Epoch 2:  58%|█████▊    | 548/938 [00:36<00:25, 15.05it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  17%|█▋        | 79/469 [00:03<00:15, 25.53it/s]

Validating:  17%|█▋        | 82/469 [00:03<00:14, 25.99it/s]
Epoch 2:  59%|█████▉    | 552/938 [00:36<00:25, 15.09it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  18%|█▊        | 85/469 [00:03<00:14, 26.40it/s]
Epoch 2:  59%|█████▉    | 556/938 [00:36<00:25, 15.14it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  19%|█▉        | 88/469 [00:03<00:14, 26.40it/s]
Epoch 2:  60%|█████▉    | 560/938 [00:36<00:24, 15.19it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  19%|█▉        | 91/469 [00:03<00:14, 25.96it/s]

Validating:  20%|██        | 94/469 [00:03<00:14, 25.86it/s]
Epoch 2:  60%|██████    | 564/938 [00:37<00:24, 15.23it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  21%|██        | 97/469 [00:03<00:13, 26.70it/s]
Epoch 2:  61%|██████    | 568/938 [00:37<00:24, 15.28it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  21%|██▏       | 100/469 [00:03<00:13, 26.54it/s]
Epoch 2:  61%|██████    | 572/938 [00:37<00:23, 15.32it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  22%|██▏       | 103/469 [00:04<00:13, 26.63it/s]

Validating:  23%|██▎       | 106/469 [00:04<00:13, 26.99it/s]
Epoch 2:  61%|██████▏   | 576/938 [00:37<00:23, 15.37it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  23%|██▎       | 109/469 [00:04<00:13, 27.09it/s]
Epoch 2:  62%|██████▏   | 580/938 [00:37<00:23, 15.42it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  24%|██▍       | 112/469 [00:04<00:13, 27.34it/s]
Epoch 2:  62%|██████▏   | 584/938 [00:37<00:22, 15.46it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  25%|██▍       | 115/469 [00:04<00:13, 26.79it/s]

Validating:  25%|██▌       | 118/469 [00:04<00:12, 27.25it/s]
Epoch 2:  63%|██████▎   | 588/938 [00:37<00:22, 15.51it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  26%|██▌       | 121/469 [00:04<00:12, 27.77it/s]
Epoch 2:  63%|██████▎   | 592/938 [00:38<00:22, 15.55it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  26%|██▋       | 124/469 [00:04<00:13, 25.28it/s]
Epoch 2:  64%|██████▎   | 596/938 [00:38<00:21, 15.58it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  27%|██▋       | 127/469 [00:05<00:14, 23.65it/s]

Validating:  28%|██▊       | 130/469 [00:05<00:14, 23.89it/s]
Epoch 2:  64%|██████▍   | 600/938 [00:38<00:21, 15.61it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  28%|██▊       | 133/469 [00:05<00:14, 23.95it/s]
Epoch 2:  64%|██████▍   | 604/938 [00:38<00:21, 15.65it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  29%|██▉       | 136/469 [00:05<00:13, 24.04it/s]
Epoch 2:  65%|██████▍   | 608/938 [00:38<00:21, 15.69it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  30%|██▉       | 139/469 [00:05<00:13, 24.07it/s]

Validating:  30%|███       | 142/469 [00:05<00:12, 25.23it/s]
Epoch 2:  65%|██████▌   | 612/938 [00:38<00:20, 15.73it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  31%|███       | 145/469 [00:05<00:12, 25.58it/s]
Epoch 2:  66%|██████▌   | 616/938 [00:39<00:20, 15.77it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  32%|███▏      | 148/469 [00:05<00:12, 25.43it/s]
Epoch 2:  66%|██████▌   | 620/938 [00:39<00:20, 15.81it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  32%|███▏      | 151/469 [00:05<00:12, 26.15it/s]

Validating:  33%|███▎      | 154/469 [00:06<00:12, 25.47it/s]
Epoch 2:  67%|██████▋   | 624/938 [00:39<00:19, 15.85it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  33%|███▎      | 157/469 [00:06<00:12, 25.90it/s]
Epoch 2:  67%|██████▋   | 628/938 [00:39<00:19, 15.89it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  34%|███▍      | 160/469 [00:06<00:12, 25.70it/s]
Epoch 2:  67%|██████▋   | 632/938 [00:39<00:19, 15.93it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  35%|███▍      | 163/469 [00:06<00:12, 25.38it/s]

Validating:  35%|███▌      | 166/469 [00:06<00:11, 25.89it/s]
Epoch 2:  68%|██████▊   | 636/938 [00:39<00:18, 15.97it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  36%|███▌      | 169/469 [00:06<00:11, 25.67it/s]
Epoch 2:  68%|██████▊   | 640/938 [00:39<00:18, 16.01it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  37%|███▋      | 172/469 [00:06<00:11, 26.34it/s]
Epoch 2:  69%|██████▊   | 644/938 [00:40<00:18, 16.05it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  37%|███▋      | 175/469 [00:06<00:10, 27.02it/s]

Validating:  38%|███▊      | 178/469 [00:07<00:10, 26.55it/s]
Epoch 2:  69%|██████▉   | 648/938 [00:40<00:18, 16.09it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  39%|███▊      | 181/469 [00:07<00:10, 26.46it/s]
Epoch 2:  70%|██████▉   | 652/938 [00:40<00:17, 16.12it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  39%|███▉      | 184/469 [00:07<00:10, 26.14it/s]
Epoch 2:  70%|██████▉   | 656/938 [00:40<00:17, 16.16it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  40%|███▉      | 187/469 [00:07<00:10, 26.05it/s]

Validating:  41%|████      | 190/469 [00:07<00:10, 25.72it/s]
Epoch 2:  70%|███████   | 660/938 [00:40<00:17, 16.20it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  41%|████      | 193/469 [00:07<00:10, 25.55it/s]
Epoch 2:  71%|███████   | 664/938 [00:40<00:16, 16.23it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  42%|████▏     | 196/469 [00:07<00:10, 25.60it/s]
Epoch 2:  71%|███████   | 668/938 [00:41<00:16, 16.27it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  42%|████▏     | 199/469 [00:07<00:10, 26.28it/s]

Validating:  43%|████▎     | 202/469 [00:07<00:10, 26.41it/s]
Epoch 2:  72%|███████▏  | 672/938 [00:41<00:16, 16.31it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  44%|████▎     | 205/469 [00:08<00:10, 25.18it/s]
Epoch 2:  72%|███████▏  | 676/938 [00:41<00:16, 16.34it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  44%|████▍     | 208/469 [00:08<00:10, 24.97it/s]
Epoch 2:  72%|███████▏  | 680/938 [00:41<00:15, 16.37it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  45%|████▍     | 211/469 [00:08<00:10, 24.43it/s]

Validating:  46%|████▌     | 214/469 [00:08<00:10, 24.05it/s]
Epoch 2:  73%|███████▎  | 684/938 [00:41<00:15, 16.40it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  46%|████▋     | 217/469 [00:08<00:09, 25.27it/s]
Epoch 2:  73%|███████▎  | 688/938 [00:41<00:15, 16.43it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  47%|████▋     | 220/469 [00:08<00:09, 25.30it/s]
Epoch 2:  74%|███████▍  | 692/938 [00:42<00:14, 16.47it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  48%|████▊     | 223/469 [00:08<00:09, 25.15it/s]

Validating:  48%|████▊     | 226/469 [00:08<00:09, 24.57it/s]
Epoch 2:  74%|███████▍  | 696/938 [00:42<00:14, 16.50it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  49%|████▉     | 229/469 [00:09<00:09, 24.94it/s]
Epoch 2:  75%|███████▍  | 700/938 [00:42<00:14, 16.53it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  49%|████▉     | 232/469 [00:09<00:09, 25.50it/s]
Epoch 2:  75%|███████▌  | 704/938 [00:42<00:14, 16.57it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  50%|█████     | 235/469 [00:09<00:09, 24.03it/s]

Validating:  51%|█████     | 238/469 [00:09<00:09, 23.89it/s]
Epoch 2:  75%|███████▌  | 708/938 [00:42<00:13, 16.59it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  51%|█████▏    | 241/469 [00:09<00:09, 23.70it/s]
Epoch 2:  76%|███████▌  | 712/938 [00:42<00:13, 16.62it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  52%|█████▏    | 244/469 [00:09<00:09, 24.49it/s]
Epoch 2:  76%|███████▋  | 716/938 [00:42<00:13, 16.65it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  53%|█████▎    | 247/469 [00:09<00:08, 25.72it/s]

Validating:  53%|█████▎    | 250/469 [00:09<00:08, 26.68it/s]
Epoch 2:  77%|███████▋  | 720/938 [00:43<00:13, 16.69it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  54%|█████▍    | 253/469 [00:09<00:08, 26.81it/s]
Epoch 2:  77%|███████▋  | 724/938 [00:43<00:12, 16.72it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  55%|█████▍    | 256/469 [00:10<00:08, 25.56it/s]
Epoch 2:  78%|███████▊  | 728/938 [00:43<00:12, 16.75it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  55%|█████▌    | 259/469 [00:10<00:08, 25.15it/s]

Validating:  56%|█████▌    | 262/469 [00:10<00:08, 25.21it/s]
Epoch 2:  78%|███████▊  | 732/938 [00:43<00:12, 16.78it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  57%|█████▋    | 265/469 [00:10<00:08, 25.48it/s]
Epoch 2:  78%|███████▊  | 736/938 [00:43<00:12, 16.82it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  57%|█████▋    | 268/469 [00:10<00:08, 24.88it/s]
Epoch 2:  79%|███████▉  | 740/938 [00:43<00:11, 16.84it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  58%|█████▊    | 271/469 [00:10<00:07, 25.57it/s]

Validating:  58%|█████▊    | 274/469 [00:10<00:07, 25.32it/s]
Epoch 2:  79%|███████▉  | 744/938 [00:44<00:11, 16.87it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  59%|█████▉    | 277/469 [00:10<00:07, 25.43it/s]
Epoch 2:  80%|███████▉  | 748/938 [00:44<00:11, 16.91it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  60%|█████▉    | 280/469 [00:11<00:07, 24.51it/s]
Epoch 2:  80%|████████  | 752/938 [00:44<00:10, 16.93it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  60%|██████    | 283/469 [00:11<00:07, 24.68it/s]

Validating:  61%|██████    | 286/469 [00:11<00:07, 24.02it/s]
Epoch 2:  81%|████████  | 756/938 [00:44<00:10, 16.95it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  62%|██████▏   | 289/469 [00:11<00:07, 23.55it/s]
Epoch 2:  81%|████████  | 760/938 [00:44<00:10, 16.97it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  62%|██████▏   | 292/469 [00:11<00:07, 23.76it/s]
Epoch 2:  81%|████████▏ | 764/938 [00:44<00:10, 17.01it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  63%|██████▎   | 295/469 [00:11<00:07, 24.45it/s]

Validating:  64%|██████▎   | 298/469 [00:11<00:06, 24.55it/s]
Epoch 2:  82%|████████▏ | 768/938 [00:45<00:09, 17.03it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  64%|██████▍   | 301/469 [00:11<00:06, 24.75it/s]
Epoch 2:  82%|████████▏ | 772/938 [00:45<00:09, 17.06it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  65%|██████▍   | 304/469 [00:12<00:06, 24.66it/s]
Epoch 2:  83%|████████▎ | 776/938 [00:45<00:09, 17.09it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  65%|██████▌   | 307/469 [00:12<00:06, 25.36it/s]

Validating:  66%|██████▌   | 310/469 [00:12<00:06, 25.66it/s]
Epoch 2:  83%|████████▎ | 780/938 [00:45<00:09, 17.12it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  67%|██████▋   | 313/469 [00:12<00:06, 25.55it/s]
Epoch 2:  84%|████████▎ | 784/938 [00:45<00:08, 17.15it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  67%|██████▋   | 316/469 [00:12<00:05, 26.30it/s]
Epoch 2:  84%|████████▍ | 788/938 [00:45<00:08, 17.19it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  68%|██████▊   | 319/469 [00:12<00:05, 26.73it/s]

Validating:  69%|██████▊   | 322/469 [00:12<00:05, 25.00it/s]
Epoch 2:  84%|████████▍ | 792/938 [00:46<00:08, 17.21it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  69%|██████▉   | 325/469 [00:12<00:05, 25.63it/s]
Epoch 2:  85%|████████▍ | 796/938 [00:46<00:08, 17.24it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  70%|██████▉   | 328/469 [00:12<00:05, 25.62it/s]
Epoch 2:  85%|████████▌ | 800/938 [00:46<00:07, 17.27it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  71%|███████   | 331/469 [00:13<00:05, 25.08it/s]

Validating:  71%|███████   | 334/469 [00:13<00:05, 25.62it/s]
Epoch 2:  86%|████████▌ | 804/938 [00:46<00:07, 17.30it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  72%|███████▏  | 337/469 [00:13<00:04, 26.63it/s]
Epoch 2:  86%|████████▌ | 808/938 [00:46<00:07, 17.33it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  72%|███████▏  | 340/469 [00:13<00:04, 26.89it/s]
Epoch 2:  87%|████████▋ | 812/938 [00:46<00:07, 17.36it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  73%|███████▎  | 343/469 [00:13<00:04, 27.52it/s]

Validating:  74%|███████▍  | 346/469 [00:13<00:04, 27.59it/s]
Epoch 2:  87%|████████▋ | 816/938 [00:46<00:07, 17.40it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  74%|███████▍  | 349/469 [00:13<00:04, 27.67it/s]
Epoch 2:  87%|████████▋ | 820/938 [00:47<00:06, 17.43it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  75%|███████▌  | 352/469 [00:13<00:04, 27.54it/s]
Epoch 2:  88%|████████▊ | 824/938 [00:47<00:06, 17.46it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  76%|███████▌  | 355/469 [00:13<00:04, 26.94it/s]

Validating:  76%|███████▋  | 358/469 [00:14<00:04, 26.89it/s]
Epoch 2:  88%|████████▊ | 828/938 [00:47<00:06, 17.49it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  77%|███████▋  | 361/469 [00:14<00:03, 27.58it/s]
Epoch 2:  89%|████████▊ | 832/938 [00:47<00:06, 17.52it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  78%|███████▊  | 364/469 [00:14<00:03, 27.55it/s]
Epoch 2:  89%|████████▉ | 836/938 [00:47<00:05, 17.55it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  78%|███████▊  | 367/469 [00:14<00:03, 27.65it/s]

Validating:  79%|███████▉  | 370/469 [00:14<00:03, 26.93it/s]
Epoch 2:  90%|████████▉ | 840/938 [00:47<00:05, 17.58it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  80%|███████▉  | 373/469 [00:14<00:03, 26.87it/s]
Epoch 2:  90%|████████▉ | 844/938 [00:47<00:05, 17.61it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  80%|████████  | 376/469 [00:14<00:03, 27.02it/s]
Epoch 2:  90%|█████████ | 848/938 [00:48<00:05, 17.64it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  81%|████████  | 379/469 [00:14<00:03, 27.09it/s]

Validating:  81%|████████▏ | 382/469 [00:14<00:03, 25.75it/s]
Epoch 2:  91%|█████████ | 852/938 [00:48<00:04, 17.66it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  82%|████████▏ | 385/469 [00:15<00:03, 26.39it/s]
Epoch 2:  91%|█████████▏| 856/938 [00:48<00:04, 17.69it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  83%|████████▎ | 388/469 [00:15<00:03, 26.80it/s]
Epoch 2:  92%|█████████▏| 860/938 [00:48<00:04, 17.70it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  83%|████████▎ | 391/469 [00:15<00:03, 24.82it/s]

Validating:  84%|████████▍ | 394/469 [00:15<00:03, 24.97it/s]
Epoch 2:  92%|█████████▏| 864/938 [00:48<00:04, 17.73it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  85%|████████▍ | 397/469 [00:15<00:02, 25.18it/s]
Epoch 2:  93%|█████████▎| 868/938 [00:48<00:03, 17.76it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  85%|████████▌ | 400/469 [00:15<00:02, 25.44it/s]
Epoch 2:  93%|█████████▎| 872/938 [00:49<00:03, 17.78it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  86%|████████▌ | 403/469 [00:15<00:02, 25.67it/s]

Validating:  87%|████████▋ | 406/469 [00:15<00:02, 26.02it/s]
Epoch 2:  93%|█████████▎| 876/938 [00:49<00:03, 17.81it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  87%|████████▋ | 409/469 [00:16<00:02, 26.12it/s]
Epoch 2:  94%|█████████▍| 880/938 [00:49<00:03, 17.84it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  88%|████████▊ | 412/469 [00:16<00:02, 25.83it/s]
Epoch 2:  94%|█████████▍| 884/938 [00:49<00:03, 17.86it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  88%|████████▊ | 415/469 [00:16<00:02, 25.65it/s]

Validating:  89%|████████▉ | 418/469 [00:16<00:01, 25.83it/s]
Epoch 2:  95%|█████████▍| 888/938 [00:49<00:02, 17.88it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  90%|████████▉ | 421/469 [00:16<00:01, 25.61it/s]
Epoch 2:  95%|█████████▌| 892/938 [00:49<00:02, 17.91it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  90%|█████████ | 424/469 [00:16<00:01, 25.53it/s]
Epoch 2:  96%|█████████▌| 896/938 [00:49<00:02, 17.93it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  91%|█████████ | 427/469 [00:16<00:01, 25.01it/s]

Validating:  92%|█████████▏| 430/469 [00:16<00:01, 25.67it/s]
Epoch 2:  96%|█████████▌| 900/938 [00:50<00:02, 17.95it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  92%|█████████▏| 433/469 [00:16<00:01, 26.51it/s]
Epoch 2:  96%|█████████▋| 904/938 [00:50<00:01, 17.99it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  93%|█████████▎| 436/469 [00:17<00:01, 26.27it/s]
Epoch 2:  97%|█████████▋| 908/938 [00:50<00:01, 18.01it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  94%|█████████▎| 439/469 [00:17<00:01, 26.52it/s]

Validating:  94%|█████████▍| 442/469 [00:17<00:01, 25.76it/s]
Epoch 2:  97%|█████████▋| 912/938 [00:50<00:01, 18.03it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  95%|█████████▍| 445/469 [00:17<00:00, 24.85it/s]
Epoch 2:  98%|█████████▊| 916/938 [00:50<00:01, 18.05it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  96%|█████████▌| 448/469 [00:17<00:00, 25.01it/s]
Epoch 2:  98%|█████████▊| 920/938 [00:50<00:00, 18.07it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  96%|█████████▌| 451/469 [00:17<00:00, 25.81it/s]

Validating:  97%|█████████▋| 454/469 [00:17<00:00, 26.35it/s]
Epoch 2:  99%|█████████▊| 924/938 [00:51<00:00, 18.10it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  97%|█████████▋| 457/469 [00:17<00:00, 26.44it/s]
Epoch 2:  99%|█████████▉| 928/938 [00:51<00:00, 18.13it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  98%|█████████▊| 460/469 [00:17<00:00, 27.35it/s]
Epoch 2:  99%|█████████▉| 932/938 [00:51<00:00, 18.15it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]

Validating:  99%|█████████▊| 463/469 [00:18<00:00, 27.64it/s]

Validating:  99%|█████████▉| 466/469 [00:18<00:00, 27.18it/s]
Epoch 2: 100%|█████████▉| 936/938 [00:51<00:00, 18.18it/s, loss=0.656, v_num=16, val_rmse=0.579, train_rmse=0.724]
Epoch 2: 100%|██████████| 938/938 [00:51<00:00, 18.19it/s, loss=0.656, v_num=16, val_rmse=0.511, train_rmse=0.724]

                                                             
Epoch 2: 100%|██████████| 938/938 [00:51<00:00, 18.18it/s, loss=0.656, v_num=16, val_rmse=0.511, train_rmse=0.668]
Epoch 2: 100%|██████████| 938/938 [00:51<00:00, 18.14it/s, loss=0.656, v_num=16, val_rmse=0.511, train_rmse=0.668]LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]


Testing: 0it [00:00, ?it/s]
Testing:   0%|          | 2/469 [00:00<00:28, 16.67it/s]
Testing:   1%|          | 5/469 [00:00<00:23, 19.46it/s]
Testing:   2%|▏         | 8/469 [00:00<00:20, 22.21it/s]
Testing:   2%|▏         | 11/469 [00:00<00:19, 23.46it/s]
Testing:   3%|▎         | 14/469 [00:00<00:18, 24.14it/s]
Testing:   4%|▎         | 17/469 [00:00<00:17, 25.63it/s]
Testing:   4%|▍         | 20/469 [00:00<00:17, 26.11it/s]
Testing:   5%|▍         | 23/469 [00:00<00:17, 26.08it/s]
Testing:   6%|▌         | 26/469 [00:01<00:17, 25.45it/s]
Testing:   6%|▌         | 29/469 [00:01<00:17, 25.37it/s]
Testing:   7%|▋         | 32/469 [00:01<00:17, 25.50it/s]
Testing:   7%|▋         | 35/469 [00:01<00:17, 24.21it/s]
Testing:   8%|▊         | 38/469 [00:01<00:17, 24.02it/s]
Testing:   9%|▊         | 41/469 [00:01<00:17, 25.02it/s]
Testing:   9%|▉         | 44/469 [00:01<00:16, 25.40it/s]
Testing:  10%|█         | 47/469 [00:01<00:16, 25.67it/s]
Testing:  11%|█         | 50/469 [00:02<00:16, 25.06it/s]
Testing:  11%|█▏        | 53/469 [00:02<00:16, 25.50it/s]
Testing:  12%|█▏        | 56/469 [00:02<00:15, 26.37it/s]
Testing:  13%|█▎        | 59/469 [00:02<00:15, 26.83it/s]
Testing:  13%|█▎        | 62/469 [00:02<00:15, 26.76it/s]
Testing:  14%|█▍        | 65/469 [00:02<00:15, 26.86it/s]
Testing:  14%|█▍        | 68/469 [00:02<00:14, 26.76it/s]
Testing:  15%|█▌        | 71/469 [00:02<00:15, 26.48it/s]
Testing:  16%|█▌        | 74/469 [00:02<00:14, 27.34it/s]
Testing:  16%|█▋        | 77/469 [00:03<00:14, 26.82it/s]
Testing:  17%|█▋        | 80/469 [00:03<00:14, 26.25it/s]
Testing:  18%|█▊        | 83/469 [00:03<00:14, 26.01it/s]
Testing:  18%|█▊        | 86/469 [00:03<00:14, 26.29it/s]
Testing:  19%|█▉        | 89/469 [00:03<00:14, 26.33it/s]
Testing:  20%|█▉        | 92/469 [00:03<00:14, 26.59it/s]
Testing:  20%|██        | 95/469 [00:03<00:14, 26.70it/s]
Testing:  21%|██        | 98/469 [00:03<00:13, 26.94it/s]
Testing:  22%|██▏       | 101/469 [00:03<00:13, 26.51it/s]
Testing:  22%|██▏       | 104/469 [00:04<00:13, 26.64it/s]
Testing:  23%|██▎       | 107/469 [00:04<00:13, 26.21it/s]
Testing:  23%|██▎       | 110/469 [00:04<00:15, 23.71it/s]
Testing:  24%|██▍       | 113/469 [00:04<00:14, 24.89it/s]
Testing:  25%|██▍       | 116/469 [00:04<00:13, 26.00it/s]
Testing:  25%|██▌       | 119/469 [00:04<00:13, 26.46it/s]
Testing:  26%|██▌       | 122/469 [00:04<00:12, 26.73it/s]
Testing:  27%|██▋       | 125/469 [00:04<00:13, 26.00it/s]
Testing:  27%|██▋       | 128/469 [00:04<00:13, 26.14it/s]
Testing:  28%|██▊       | 131/469 [00:05<00:12, 27.05it/s]
Testing:  29%|██▊       | 134/469 [00:05<00:12, 27.68it/s]
Testing:  29%|██▉       | 137/469 [00:05<00:11, 27.87it/s]
Testing:  30%|██▉       | 140/469 [00:05<00:11, 27.72it/s]
Testing:  30%|███       | 143/469 [00:05<00:11, 27.53it/s]
Testing:  31%|███       | 146/469 [00:05<00:12, 26.79it/s]
Testing:  32%|███▏      | 149/469 [00:05<00:12, 26.66it/s]
Testing:  32%|███▏      | 152/469 [00:05<00:12, 25.83it/s]
Testing:  33%|███▎      | 155/469 [00:05<00:11, 26.26it/s]
Testing:  34%|███▎      | 158/469 [00:06<00:11, 26.03it/s]
Testing:  34%|███▍      | 161/469 [00:06<00:12, 25.14it/s]
Testing:  35%|███▍      | 164/469 [00:06<00:11, 25.85it/s]
Testing:  36%|███▌      | 167/469 [00:06<00:11, 25.97it/s]
Testing:  36%|███▌      | 170/469 [00:06<00:11, 26.37it/s]
Testing:  37%|███▋      | 173/469 [00:06<00:11, 26.45it/s]
Testing:  38%|███▊      | 176/469 [00:06<00:10, 26.67it/s]
Testing:  38%|███▊      | 179/469 [00:06<00:11, 26.29it/s]
Testing:  39%|███▉      | 182/469 [00:07<00:10, 26.28it/s]
Testing:  39%|███▉      | 185/469 [00:07<00:10, 26.10it/s]
Testing:  40%|████      | 188/469 [00:07<00:10, 25.55it/s]
Testing:  41%|████      | 191/469 [00:07<00:10, 25.87it/s]
Testing:  41%|████▏     | 194/469 [00:07<00:10, 25.98it/s]
Testing:  42%|████▏     | 197/469 [00:07<00:10, 25.12it/s]
Testing:  43%|████▎     | 200/469 [00:07<00:10, 25.12it/s]
Testing:  43%|████▎     | 203/469 [00:07<00:10, 25.50it/s]
Testing:  44%|████▍     | 206/469 [00:07<00:10, 25.33it/s]
Testing:  45%|████▍     | 209/469 [00:08<00:10, 24.97it/s]
Testing:  45%|████▌     | 212/469 [00:08<00:10, 25.11it/s]
Testing:  46%|████▌     | 215/469 [00:08<00:10, 24.60it/s]
Testing:  46%|████▋     | 218/469 [00:08<00:09, 25.48it/s]
Testing:  47%|████▋     | 221/469 [00:08<00:09, 25.38it/s]
Testing:  48%|████▊     | 224/469 [00:08<00:09, 25.31it/s]
Testing:  48%|████▊     | 227/469 [00:08<00:09, 25.89it/s]
Testing:  49%|████▉     | 230/469 [00:08<00:09, 26.02it/s]
Testing:  50%|████▉     | 233/469 [00:09<00:08, 26.25it/s]
Testing:  50%|█████     | 236/469 [00:09<00:08, 26.77it/s]
Testing:  51%|█████     | 239/469 [00:09<00:08, 26.49it/s]
Testing:  52%|█████▏    | 242/469 [00:09<00:08, 26.37it/s]
Testing:  52%|█████▏    | 245/469 [00:09<00:08, 26.20it/s]
Testing:  53%|█████▎    | 248/469 [00:09<00:08, 26.83it/s]
Testing:  54%|█████▎    | 251/469 [00:09<00:08, 26.81it/s]
Testing:  54%|█████▍    | 254/469 [00:09<00:08, 25.57it/s]
Testing:  55%|█████▍    | 257/469 [00:09<00:08, 25.12it/s]
Testing:  55%|█████▌    | 260/469 [00:10<00:08, 25.02it/s]
Testing:  56%|█████▌    | 263/469 [00:10<00:08, 25.38it/s]
Testing:  57%|█████▋    | 266/469 [00:10<00:07, 26.04it/s]
Testing:  57%|█████▋    | 269/469 [00:10<00:07, 25.78it/s]
Testing:  58%|█████▊    | 272/469 [00:10<00:07, 25.76it/s]
Testing:  59%|█████▊    | 275/469 [00:10<00:07, 24.48it/s]
Testing:  59%|█████▉    | 278/469 [00:10<00:07, 24.43it/s]
Testing:  60%|█████▉    | 281/469 [00:10<00:07, 25.05it/s]
Testing:  61%|██████    | 284/469 [00:11<00:07, 24.12it/s]
Testing:  61%|██████    | 287/469 [00:11<00:07, 24.50it/s]
Testing:  62%|██████▏   | 290/469 [00:11<00:06, 25.80it/s]
Testing:  62%|██████▏   | 293/469 [00:11<00:06, 26.77it/s]
Testing:  63%|██████▎   | 296/469 [00:11<00:06, 27.55it/s]
Testing:  64%|██████▍   | 299/469 [00:11<00:06, 26.14it/s]
Testing:  64%|██████▍   | 302/469 [00:11<00:06, 26.68it/s]
Testing:  65%|██████▌   | 305/469 [00:11<00:06, 24.88it/s]
Testing:  66%|██████▌   | 308/469 [00:11<00:06, 24.85it/s]
Testing:  66%|██████▋   | 311/469 [00:12<00:06, 25.44it/s]
Testing:  67%|██████▋   | 314/469 [00:12<00:06, 25.78it/s]
Testing:  68%|██████▊   | 317/469 [00:12<00:05, 26.03it/s]
Testing:  68%|██████▊   | 321/469 [00:12<00:05, 27.49it/s]
Testing:  69%|██████▉   | 324/469 [00:12<00:05, 27.37it/s]
Testing:  70%|██████▉   | 327/469 [00:12<00:05, 27.42it/s]
Testing:  70%|███████   | 330/469 [00:12<00:05, 27.20it/s]
Testing:  71%|███████   | 333/469 [00:12<00:05, 27.05it/s]
Testing:  72%|███████▏  | 336/469 [00:12<00:04, 26.97it/s]
Testing:  72%|███████▏  | 339/469 [00:13<00:04, 26.32it/s]
Testing:  73%|███████▎  | 342/469 [00:13<00:04, 25.78it/s]
Testing:  74%|███████▎  | 345/469 [00:13<00:04, 25.73it/s]
Testing:  74%|███████▍  | 348/469 [00:13<00:04, 25.92it/s]
Testing:  75%|███████▍  | 351/469 [00:13<00:04, 26.15it/s]
Testing:  75%|███████▌  | 354/469 [00:13<00:04, 25.08it/s]
Testing:  76%|███████▌  | 357/469 [00:13<00:04, 25.61it/s]
Testing:  77%|███████▋  | 360/469 [00:13<00:04, 25.52it/s]
Testing:  77%|███████▋  | 363/469 [00:14<00:04, 25.81it/s]
Testing:  78%|███████▊  | 366/469 [00:14<00:03, 26.86it/s]
Testing:  79%|███████▊  | 369/469 [00:14<00:04, 24.45it/s]
Testing:  79%|███████▉  | 372/469 [00:14<00:03, 24.58it/s]
Testing:  80%|███████▉  | 375/469 [00:14<00:03, 24.83it/s]
Testing:  81%|████████  | 378/469 [00:14<00:03, 23.31it/s]
Testing:  81%|████████  | 381/469 [00:14<00:03, 24.56it/s]
Testing:  82%|████████▏ | 384/469 [00:14<00:03, 24.56it/s]
Testing:  83%|████████▎ | 387/469 [00:15<00:03, 24.58it/s]
Testing:  83%|████████▎ | 390/469 [00:15<00:03, 25.14it/s]
Testing:  84%|████████▍ | 393/469 [00:15<00:02, 25.78it/s]
Testing:  84%|████████▍ | 396/469 [00:15<00:02, 25.39it/s]
Testing:  85%|████████▌ | 399/469 [00:15<00:02, 25.71it/s]
Testing:  86%|████████▌ | 403/469 [00:15<00:02, 26.67it/s]
Testing:  87%|████████▋ | 406/469 [00:15<00:02, 25.38it/s]
Testing:  87%|████████▋ | 409/469 [00:15<00:02, 25.07it/s]
Testing:  88%|████████▊ | 412/469 [00:15<00:02, 25.80it/s]
Testing:  88%|████████▊ | 415/469 [00:16<00:02, 25.31it/s]
Testing:  89%|████████▉ | 418/469 [00:16<00:01, 25.92it/s]
Testing:  90%|████████▉ | 421/469 [00:16<00:01, 26.79it/s]
Testing:  90%|█████████ | 424/469 [00:16<00:01, 26.09it/s]
Testing:  91%|█████████ | 427/469 [00:16<00:01, 24.54it/s]
Testing:  92%|█████████▏| 431/469 [00:16<00:01, 25.61it/s]
Testing:  93%|█████████▎| 434/469 [00:16<00:01, 25.98it/s]
Testing:  93%|█████████▎| 437/469 [00:16<00:01, 26.48it/s]
Testing:  94%|█████████▍| 440/469 [00:17<00:01, 27.09it/s]
Testing:  94%|█████████▍| 443/469 [00:17<00:00, 27.30it/s]
Testing:  95%|█████████▌| 446/469 [00:17<00:00, 26.98it/s]
Testing:  96%|█████████▌| 449/469 [00:17<00:00, 27.30it/s]
Testing:  96%|█████████▋| 452/469 [00:17<00:00, 26.72it/s]
Testing:  97%|█████████▋| 455/469 [00:17<00:00, 26.65it/s]
Testing:  98%|█████████▊| 458/469 [00:17<00:00, 26.66it/s]
Testing:  98%|█████████▊| 461/469 [00:17<00:00, 27.07it/s]
Testing:  99%|█████████▉| 464/469 [00:17<00:00, 27.01it/s]
Testing: 100%|█████████▉| 467/469 [00:18<00:00, 27.57it/s]--------------------------------------------------------------------------------
DATALOADER:0 TEST RESULTS
{'test_rmse': 0.5114961266517639}
--------------------------------------------------------------------------------

Testing: 100%|██████████| 469/469 [00:18<00:00, 25.89it/s]
  0%|          | 0/469 [02:54<?, ?it/s]
Global seed set to 51

['p_np'] False
2 1
iupac_vocab_size: 1491
training... 1491

  0%|          | 0/469 [00:00<?, ?it/s]Some weights of the model checkpoint at checkpoints/iupac were not used when initializing GPT2ForSequenceClassification: ['lm_head.weight']
- This IS expected if you are initializing GPT2ForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing GPT2ForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
GPU available: True, used: True
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]

  | Name        | Type                          | Params
--------------------------------------------------------------
0 | transformer | GPT2ForSequenceClassification | 7.1 M 
--------------------------------------------------------------
75.9 K    Trainable params
7.0 M     Non-trainable params
7.1 M     Total params
28.416    Total estimated model params size (MB)

Validation sanity check: 0it [00:00, ?it/s]
Validation sanity check:   0%|          | 0/2 [00:00<?, ?it/s]
                                                              Global seed set to 51


Training: 0it [00:00, ?it/s]
Training:   0%|          | 0/938 [00:00<?, ?it/s]
Epoch 0:   0%|          | 0/938 [00:00<?, ?it/s] 
Epoch 0:   0%|          | 1/938 [00:00<01:34,  9.87it/s]
Epoch 0:   0%|          | 1/938 [00:00<01:35,  9.83it/s, loss=3.65, v_num=17]
Epoch 0:   0%|          | 2/938 [00:00<01:16, 12.19it/s, loss=3.52, v_num=17]
Epoch 0:   0%|          | 3/938 [00:00<01:13, 12.77it/s, loss=3.52, v_num=17]
Epoch 0:   0%|          | 3/938 [00:00<01:13, 12.74it/s, loss=3.57, v_num=17]
Epoch 0:   0%|          | 4/938 [00:00<01:10, 13.26it/s, loss=3.59, v_num=17]
Epoch 0:   1%|          | 5/938 [00:00<01:07, 13.90it/s, loss=3.59, v_num=17]
Epoch 0:   1%|          | 5/938 [00:00<01:07, 13.89it/s, loss=3.58, v_num=17]
Epoch 0:   1%|          | 6/938 [00:00<01:04, 14.42it/s, loss=3.62, v_num=17]
Epoch 0:   1%|          | 7/938 [00:00<01:06, 13.96it/s, loss=3.62, v_num=17]
Epoch 0:   1%|          | 7/938 [00:00<01:06, 13.95it/s, loss=3.65, v_num=17]
Epoch 0:   1%|          | 8/938 [00:00<01:07, 13.78it/s, loss=3.63, v_num=17]
Epoch 0:   1%|          | 9/938 [00:00<01:06, 14.06it/s, loss=3.63, v_num=17]
Epoch 0:   1%|          | 9/938 [00:00<01:06, 14.05it/s, loss=3.66, v_num=17]
Epoch 0:   1%|          | 10/938 [00:00<01:05, 14.15it/s, loss=3.63, v_num=17]
Epoch 0:   1%|          | 11/938 [00:00<01:05, 14.20it/s, loss=3.63, v_num=17]
Epoch 0:   1%|          | 11/938 [00:00<01:05, 14.19it/s, loss=3.59, v_num=17]
Epoch 0:   1%|▏         | 12/938 [00:00<01:04, 14.42it/s, loss=3.61, v_num=17]
Epoch 0:   1%|▏         | 13/938 [00:00<01:03, 14.49it/s, loss=3.61, v_num=17]
Epoch 0:   1%|▏         | 13/938 [00:00<01:03, 14.48it/s, loss=3.57, v_num=17]
Epoch 0:   1%|▏         | 14/938 [00:00<01:03, 14.51it/s, loss=3.55, v_num=17]
Epoch 0:   2%|▏         | 15/938 [00:01<01:02, 14.67it/s, loss=3.55, v_num=17]
Epoch 0:   2%|▏         | 15/938 [00:01<01:02, 14.67it/s, loss=3.55, v_num=17]
Epoch 0:   2%|▏         | 16/938 [00:01<01:03, 14.51it/s, loss=3.54, v_num=17]
Epoch 0:   2%|▏         | 17/938 [00:01<01:03, 14.58it/s, loss=3.54, v_num=17]
Epoch 0:   2%|▏         | 17/938 [00:01<01:03, 14.57it/s, loss=3.52, v_num=17]
Epoch 0:   2%|▏         | 18/938 [00:01<01:03, 14.54it/s, loss=3.52, v_num=17]
Epoch 0:   2%|▏         | 19/938 [00:01<01:03, 14.57it/s, loss=3.52, v_num=17]
Epoch 0:   2%|▏         | 19/938 [00:01<01:03, 14.57it/s, loss=3.48, v_num=17]
Epoch 0:   2%|▏         | 20/938 [00:01<01:02, 14.65it/s, loss=3.46, v_num=17]
Epoch 0:   2%|▏         | 21/938 [00:01<01:02, 14.65it/s, loss=3.46, v_num=17]
Epoch 0:   2%|▏         | 21/938 [00:01<01:02, 14.64it/s, loss=3.42, v_num=17]
Epoch 0:   2%|▏         | 22/938 [00:01<01:02, 14.67it/s, loss=3.4, v_num=17] 
Epoch 0:   2%|▏         | 23/938 [00:01<01:03, 14.33it/s, loss=3.4, v_num=17]
Epoch 0:   2%|▏         | 23/938 [00:01<01:03, 14.32it/s, loss=3.37, v_num=17]
Epoch 0:   3%|▎         | 24/938 [00:01<01:03, 14.31it/s, loss=3.34, v_num=17]
Epoch 0:   3%|▎         | 25/938 [00:01<01:04, 14.25it/s, loss=3.34, v_num=17]
Epoch 0:   3%|▎         | 25/938 [00:01<01:04, 14.25it/s, loss=3.3, v_num=17] 
Epoch 0:   3%|▎         | 26/938 [00:01<01:03, 14.32it/s, loss=3.24, v_num=17]
Epoch 0:   3%|▎         | 27/938 [00:01<01:03, 14.25it/s, loss=3.24, v_num=17]
Epoch 0:   3%|▎         | 27/938 [00:01<01:03, 14.24it/s, loss=3.18, v_num=17]
Epoch 0:   3%|▎         | 28/938 [00:01<01:03, 14.26it/s, loss=3.13, v_num=17]
Epoch 0:   3%|▎         | 29/938 [00:02<01:05, 13.88it/s, loss=3.13, v_num=17]
Epoch 0:   3%|▎         | 29/938 [00:02<01:05, 13.88it/s, loss=3.09, v_num=17]
Epoch 0:   3%|▎         | 30/938 [00:02<01:05, 13.86it/s, loss=3.05, v_num=17]
Epoch 0:   3%|▎         | 31/938 [00:02<01:05, 13.83it/s, loss=3.05, v_num=17]
Epoch 0:   3%|▎         | 31/938 [00:02<01:05, 13.83it/s, loss=3, v_num=17]   
Epoch 0:   3%|▎         | 32/938 [00:02<01:05, 13.91it/s, loss=2.93, v_num=17]
Epoch 0:   4%|▎         | 33/938 [00:02<01:04, 13.96it/s, loss=2.93, v_num=17]
Epoch 0:   4%|▎         | 33/938 [00:02<01:04, 13.96it/s, loss=2.9, v_num=17] 
Epoch 0:   4%|▎         | 34/938 [00:02<01:04, 14.01it/s, loss=2.84, v_num=17]
Epoch 0:   4%|▎         | 35/938 [00:02<01:04, 14.03it/s, loss=2.84, v_num=17]
Epoch 0:   4%|▎         | 35/938 [00:02<01:04, 14.03it/s, loss=2.76, v_num=17]
Epoch 0:   4%|▍         | 36/938 [00:02<01:04, 14.05it/s, loss=2.7, v_num=17] 
Epoch 0:   4%|▍         | 37/938 [00:02<01:04, 14.07it/s, loss=2.7, v_num=17]
Epoch 0:   4%|▍         | 37/938 [00:02<01:04, 14.07it/s, loss=2.63, v_num=17]
Epoch 0:   4%|▍         | 38/938 [00:02<01:03, 14.08it/s, loss=2.56, v_num=17]
Epoch 0:   4%|▍         | 39/938 [00:02<01:03, 14.09it/s, loss=2.56, v_num=17]
Epoch 0:   4%|▍         | 39/938 [00:02<01:03, 14.09it/s, loss=2.5, v_num=17] 
Epoch 0:   4%|▍         | 40/938 [00:02<01:03, 14.04it/s, loss=2.46, v_num=17]
Epoch 0:   4%|▍         | 41/938 [00:02<01:04, 13.92it/s, loss=2.46, v_num=17]
Epoch 0:   4%|▍         | 41/938 [00:02<01:04, 13.92it/s, loss=2.4, v_num=17] 
Epoch 0:   4%|▍         | 42/938 [00:03<01:04, 13.98it/s, loss=2.34, v_num=17]
Epoch 0:   5%|▍         | 43/938 [00:03<01:03, 14.00it/s, loss=2.34, v_num=17]
Epoch 0:   5%|▍         | 43/938 [00:03<01:03, 14.00it/s, loss=2.27, v_num=17]
Epoch 0:   5%|▍         | 44/938 [00:03<01:03, 14.02it/s, loss=2.21, v_num=17]
Epoch 0:   5%|▍         | 45/938 [00:03<01:03, 14.07it/s, loss=2.21, v_num=17]
Epoch 0:   5%|▍         | 45/938 [00:03<01:03, 14.07it/s, loss=2.15, v_num=17]
Epoch 0:   5%|▍         | 46/938 [00:03<01:03, 14.04it/s, loss=2.1, v_num=17] 
Epoch 0:   5%|▌         | 47/938 [00:03<01:03, 14.01it/s, loss=2.1, v_num=17]
Epoch 0:   5%|▌         | 47/938 [00:03<01:03, 14.01it/s, loss=2.05, v_num=17]
Epoch 0:   5%|▌         | 48/938 [00:03<01:03, 13.98it/s, loss=2, v_num=17]   
Epoch 0:   5%|▌         | 49/938 [00:03<01:03, 14.02it/s, loss=2, v_num=17]
Epoch 0:   5%|▌         | 49/938 [00:03<01:03, 14.02it/s, loss=1.94, v_num=17]
Epoch 0:   5%|▌         | 50/938 [00:03<01:03, 14.01it/s, loss=1.89, v_num=17]
Epoch 0:   5%|▌         | 51/938 [00:03<01:03, 14.04it/s, loss=1.89, v_num=17]
Epoch 0:   5%|▌         | 51/938 [00:03<01:03, 14.03it/s, loss=1.87, v_num=17]
Epoch 0:   6%|▌         | 52/938 [00:03<01:03, 14.00it/s, loss=1.83, v_num=17]
Epoch 0:   6%|▌         | 53/938 [00:03<01:02, 14.05it/s, loss=1.83, v_num=17]
Epoch 0:   6%|▌         | 53/938 [00:03<01:03, 14.05it/s, loss=1.79, v_num=17]
Epoch 0:   6%|▌         | 54/938 [00:03<01:02, 14.04it/s, loss=1.78, v_num=17]
Epoch 0:   6%|▌         | 55/938 [00:03<01:02, 14.02it/s, loss=1.78, v_num=17]
Epoch 0:   6%|▌         | 55/938 [00:03<01:03, 14.02it/s, loss=1.75, v_num=17]
Epoch 0:   6%|▌         | 56/938 [00:03<01:02, 14.04it/s, loss=1.72, v_num=17]
Epoch 0:   6%|▌         | 57/938 [00:04<01:02, 14.02it/s, loss=1.72, v_num=17]
Epoch 0:   6%|▌         | 57/938 [00:04<01:02, 14.01it/s, loss=1.71, v_num=17]
Epoch 0:   6%|▌         | 58/938 [00:04<01:02, 13.99it/s, loss=1.71, v_num=17]
Epoch 0:   6%|▋         | 59/938 [00:04<01:02, 13.98it/s, loss=1.71, v_num=17]
Epoch 0:   6%|▋         | 59/938 [00:04<01:02, 13.98it/s, loss=1.69, v_num=17]
Epoch 0:   6%|▋         | 60/938 [00:04<01:02, 14.01it/s, loss=1.65, v_num=17]
Epoch 0:   7%|▋         | 61/938 [00:04<01:02, 14.02it/s, loss=1.65, v_num=17]
Epoch 0:   7%|▋         | 61/938 [00:04<01:02, 14.02it/s, loss=1.64, v_num=17]
Epoch 0:   7%|▋         | 62/938 [00:04<01:02, 14.05it/s, loss=1.63, v_num=17]
Epoch 0:   7%|▋         | 63/938 [00:04<01:02, 14.05it/s, loss=1.63, v_num=17]
Epoch 0:   7%|▋         | 63/938 [00:04<01:02, 14.04it/s, loss=1.63, v_num=17]
Epoch 0:   7%|▋         | 64/938 [00:04<01:02, 13.98it/s, loss=1.62, v_num=17]
Epoch 0:   7%|▋         | 65/938 [00:04<01:02, 13.90it/s, loss=1.62, v_num=17]
Epoch 0:   7%|▋         | 65/938 [00:04<01:02, 13.90it/s, loss=1.63, v_num=17]
Epoch 0:   7%|▋         | 66/938 [00:04<01:02, 13.95it/s, loss=1.64, v_num=17]
Epoch 0:   7%|▋         | 67/938 [00:04<01:02, 13.93it/s, loss=1.64, v_num=17]
Epoch 0:   7%|▋         | 67/938 [00:04<01:02, 13.92it/s, loss=1.63, v_num=17]
Epoch 0:   7%|▋         | 68/938 [00:04<01:02, 13.88it/s, loss=1.65, v_num=17]
Epoch 0:   7%|▋         | 69/938 [00:04<01:02, 13.87it/s, loss=1.65, v_num=17]
Epoch 0:   7%|▋         | 69/938 [00:04<01:02, 13.87it/s, loss=1.65, v_num=17]
Epoch 0:   7%|▋         | 70/938 [00:05<01:02, 13.87it/s, loss=1.64, v_num=17]
Epoch 0:   8%|▊         | 71/938 [00:05<01:02, 13.87it/s, loss=1.64, v_num=17]
Epoch 0:   8%|▊         | 71/938 [00:05<01:02, 13.87it/s, loss=1.64, v_num=17]
Epoch 0:   8%|▊         | 72/938 [00:05<01:02, 13.88it/s, loss=1.65, v_num=17]
Epoch 0:   8%|▊         | 73/938 [00:05<01:02, 13.91it/s, loss=1.65, v_num=17]
Epoch 0:   8%|▊         | 73/938 [00:05<01:02, 13.91it/s, loss=1.66, v_num=17]
Epoch 0:   8%|▊         | 74/938 [00:05<01:02, 13.91it/s, loss=1.64, v_num=17]
Epoch 0:   8%|▊         | 75/938 [00:05<01:01, 13.95it/s, loss=1.64, v_num=17]
Epoch 0:   8%|▊         | 75/938 [00:05<01:01, 13.95it/s, loss=1.66, v_num=17]
Epoch 0:   8%|▊         | 76/938 [00:05<01:01, 13.91it/s, loss=1.67, v_num=17]
Epoch 0:   8%|▊         | 77/938 [00:05<01:01, 13.91it/s, loss=1.67, v_num=17]
Epoch 0:   8%|▊         | 77/938 [00:05<01:01, 13.91it/s, loss=1.67, v_num=17]
Epoch 0:   8%|▊         | 78/938 [00:05<01:01, 13.94it/s, loss=1.67, v_num=17]
Epoch 0:   8%|▊         | 79/938 [00:05<01:01, 13.94it/s, loss=1.67, v_num=17]
Epoch 0:   8%|▊         | 79/938 [00:05<01:01, 13.94it/s, loss=1.67, v_num=17]
Epoch 0:   9%|▊         | 80/938 [00:05<01:01, 13.93it/s, loss=1.68, v_num=17]
Epoch 0:   9%|▊         | 81/938 [00:05<01:01, 13.95it/s, loss=1.68, v_num=17]
Epoch 0:   9%|▊         | 81/938 [00:05<01:01, 13.95it/s, loss=1.7, v_num=17] 
Epoch 0:   9%|▊         | 82/938 [00:05<01:01, 13.93it/s, loss=1.7, v_num=17]
Epoch 0:   9%|▉         | 83/938 [00:05<01:01, 13.95it/s, loss=1.7, v_num=17]
Epoch 0:   9%|▉         | 83/938 [00:05<01:01, 13.95it/s, loss=1.69, v_num=17]
Epoch 0:   9%|▉         | 84/938 [00:06<01:01, 13.93it/s, loss=1.7, v_num=17] 
Epoch 0:   9%|▉         | 85/938 [00:06<01:01, 13.93it/s, loss=1.7, v_num=17]
Epoch 0:   9%|▉         | 85/938 [00:06<01:01, 13.93it/s, loss=1.7, v_num=17]
Epoch 0:   9%|▉         | 86/938 [00:06<01:01, 13.96it/s, loss=1.71, v_num=17]
Epoch 0:   9%|▉         | 87/938 [00:06<01:00, 13.95it/s, loss=1.71, v_num=17]
Epoch 0:   9%|▉         | 87/938 [00:06<01:01, 13.95it/s, loss=1.7, v_num=17] 
Epoch 0:   9%|▉         | 88/938 [00:06<01:00, 13.95it/s, loss=1.69, v_num=17]
Epoch 0:   9%|▉         | 89/938 [00:06<01:00, 13.97it/s, loss=1.69, v_num=17]
Epoch 0:   9%|▉         | 89/938 [00:06<01:00, 13.97it/s, loss=1.68, v_num=17]
Epoch 0:  10%|▉         | 90/938 [00:06<01:00, 13.99it/s, loss=1.67, v_num=17]
Epoch 0:  10%|▉         | 91/938 [00:06<01:00, 14.00it/s, loss=1.67, v_num=17]
Epoch 0:  10%|▉         | 91/938 [00:06<01:00, 14.00it/s, loss=1.66, v_num=17]
Epoch 0:  10%|▉         | 92/938 [00:06<01:00, 14.00it/s, loss=1.65, v_num=17]
Epoch 0:  10%|▉         | 93/938 [00:06<01:00, 14.00it/s, loss=1.65, v_num=17]
Epoch 0:  10%|▉         | 93/938 [00:06<01:00, 14.00it/s, loss=1.66, v_num=17]
Epoch 0:  10%|█         | 94/938 [00:06<01:00, 14.02it/s, loss=1.65, v_num=17]
Epoch 0:  10%|█         | 95/938 [00:06<01:00, 14.01it/s, loss=1.65, v_num=17]
Epoch 0:  10%|█         | 95/938 [00:06<01:00, 14.01it/s, loss=1.65, v_num=17]
Epoch 0:  10%|█         | 96/938 [00:06<01:00, 14.00it/s, loss=1.65, v_num=17]
Epoch 0:  10%|█         | 97/938 [00:06<00:59, 14.03it/s, loss=1.65, v_num=17]
Epoch 0:  10%|█         | 97/938 [00:06<00:59, 14.03it/s, loss=1.65, v_num=17]
Epoch 0:  10%|█         | 98/938 [00:06<00:59, 14.01it/s, loss=1.64, v_num=17]
Epoch 0:  11%|█         | 99/938 [00:07<00:59, 14.01it/s, loss=1.64, v_num=17]
Epoch 0:  11%|█         | 99/938 [00:07<00:59, 14.01it/s, loss=1.63, v_num=17]
Epoch 0:  11%|█         | 100/938 [00:07<00:59, 14.04it/s, loss=1.65, v_num=17]
Epoch 0:  11%|█         | 101/938 [00:07<00:59, 14.07it/s, loss=1.65, v_num=17]
Epoch 0:  11%|█         | 101/938 [00:07<00:59, 14.07it/s, loss=1.65, v_num=17]
Epoch 0:  11%|█         | 102/938 [00:07<00:59, 14.08it/s, loss=1.66, v_num=17]
Epoch 0:  11%|█         | 103/938 [00:07<00:59, 14.08it/s, loss=1.66, v_num=17]
Epoch 0:  11%|█         | 103/938 [00:07<00:59, 14.08it/s, loss=1.67, v_num=17]
Epoch 0:  11%|█         | 104/938 [00:07<00:59, 14.06it/s, loss=1.65, v_num=17]
Epoch 0:  11%|█         | 105/938 [00:07<00:59, 14.06it/s, loss=1.65, v_num=17]
Epoch 0:  11%|█         | 105/938 [00:07<00:59, 14.06it/s, loss=1.64, v_num=17]
Epoch 0:  11%|█▏        | 106/938 [00:07<00:59, 14.07it/s, loss=1.63, v_num=17]
Epoch 0:  11%|█▏        | 107/938 [00:07<00:59, 14.06it/s, loss=1.63, v_num=17]
Epoch 0:  11%|█▏        | 107/938 [00:07<00:59, 14.06it/s, loss=1.64, v_num=17]
Epoch 0:  12%|█▏        | 108/938 [00:07<00:58, 14.07it/s, loss=1.64, v_num=17]
Epoch 0:  12%|█▏        | 109/938 [00:07<00:58, 14.07it/s, loss=1.64, v_num=17]
Epoch 0:  12%|█▏        | 109/938 [00:07<00:58, 14.06it/s, loss=1.65, v_num=17]
Epoch 0:  12%|█▏        | 110/938 [00:07<00:58, 14.09it/s, loss=1.65, v_num=17]
Epoch 0:  12%|█▏        | 111/938 [00:07<00:58, 14.11it/s, loss=1.65, v_num=17]
Epoch 0:  12%|█▏        | 111/938 [00:07<00:58, 14.11it/s, loss=1.64, v_num=17]
Epoch 0:  12%|█▏        | 112/938 [00:07<00:58, 14.09it/s, loss=1.64, v_num=17]
Epoch 0:  12%|█▏        | 113/938 [00:08<00:58, 14.10it/s, loss=1.64, v_num=17]
Epoch 0:  12%|█▏        | 113/938 [00:08<00:58, 14.09it/s, loss=1.64, v_num=17]
Epoch 0:  12%|█▏        | 114/938 [00:08<00:58, 14.06it/s, loss=1.65, v_num=17]
Epoch 0:  12%|█▏        | 115/938 [00:08<00:58, 14.08it/s, loss=1.65, v_num=17]
Epoch 0:  12%|█▏        | 115/938 [00:08<00:58, 14.08it/s, loss=1.64, v_num=17]
Epoch 0:  12%|█▏        | 116/938 [00:08<00:58, 14.10it/s, loss=1.62, v_num=17]
Epoch 0:  12%|█▏        | 117/938 [00:08<00:58, 14.09it/s, loss=1.62, v_num=17]
Epoch 0:  12%|█▏        | 117/938 [00:08<00:58, 14.09it/s, loss=1.61, v_num=17]
Epoch 0:  13%|█▎        | 118/938 [00:08<00:58, 14.11it/s, loss=1.6, v_num=17] 
Epoch 0:  13%|█▎        | 119/938 [00:08<00:58, 14.09it/s, loss=1.6, v_num=17]
Epoch 0:  13%|█▎        | 119/938 [00:08<00:58, 14.09it/s, loss=1.6, v_num=17]
Epoch 0:  13%|█▎        | 120/938 [00:08<00:58, 14.05it/s, loss=1.59, v_num=17]
Epoch 0:  13%|█▎        | 121/938 [00:08<00:58, 13.99it/s, loss=1.59, v_num=17]
Epoch 0:  13%|█▎        | 121/938 [00:08<00:58, 13.99it/s, loss=1.56, v_num=17]
Epoch 0:  13%|█▎        | 122/938 [00:08<00:58, 13.99it/s, loss=1.54, v_num=17]
Epoch 0:  13%|█▎        | 123/938 [00:08<00:58, 13.97it/s, loss=1.54, v_num=17]
Epoch 0:  13%|█▎        | 123/938 [00:08<00:58, 13.97it/s, loss=1.53, v_num=17]
Epoch 0:  13%|█▎        | 124/938 [00:08<00:58, 13.99it/s, loss=1.52, v_num=17]
Epoch 0:  13%|█▎        | 125/938 [00:08<00:58, 14.01it/s, loss=1.52, v_num=17]
Epoch 0:  13%|█▎        | 125/938 [00:08<00:58, 14.01it/s, loss=1.5, v_num=17] 
Epoch 0:  13%|█▎        | 126/938 [00:08<00:57, 14.00it/s, loss=1.49, v_num=17]
Epoch 0:  14%|█▎        | 127/938 [00:09<00:57, 14.02it/s, loss=1.49, v_num=17]
Epoch 0:  14%|█▎        | 127/938 [00:09<00:57, 14.02it/s, loss=1.48, v_num=17]
Epoch 0:  14%|█▎        | 128/938 [00:09<00:57, 14.02it/s, loss=1.48, v_num=17]
Epoch 0:  14%|█▍        | 129/938 [00:09<00:57, 14.04it/s, loss=1.48, v_num=17]
Epoch 0:  14%|█▍        | 129/938 [00:09<00:57, 14.04it/s, loss=1.45, v_num=17]
Epoch 0:  14%|█▍        | 130/938 [00:09<00:57, 14.05it/s, loss=1.45, v_num=17]
Epoch 0:  14%|█▍        | 131/938 [00:09<00:57, 14.01it/s, loss=1.45, v_num=17]
Epoch 0:  14%|█▍        | 131/938 [00:09<00:57, 14.01it/s, loss=1.45, v_num=17]
Epoch 0:  14%|█▍        | 132/938 [00:09<00:57, 14.00it/s, loss=1.44, v_num=17]
Epoch 0:  14%|█▍        | 133/938 [00:09<00:57, 13.99it/s, loss=1.44, v_num=17]
Epoch 0:  14%|█▍        | 133/938 [00:09<00:57, 13.99it/s, loss=1.43, v_num=17]
Epoch 0:  14%|█▍        | 134/938 [00:09<00:57, 13.99it/s, loss=1.4, v_num=17] 
Epoch 0:  14%|█▍        | 135/938 [00:09<00:57, 13.99it/s, loss=1.4, v_num=17]
Epoch 0:  14%|█▍        | 135/938 [00:09<00:57, 13.99it/s, loss=1.37, v_num=17]
Epoch 0:  14%|█▍        | 136/938 [00:09<00:57, 14.01it/s, loss=1.37, v_num=17]
Epoch 0:  15%|█▍        | 137/938 [00:09<00:57, 14.01it/s, loss=1.37, v_num=17]
Epoch 0:  15%|█▍        | 137/938 [00:09<00:57, 14.01it/s, loss=1.36, v_num=17]
Epoch 0:  15%|█▍        | 138/938 [00:09<00:57, 13.91it/s, loss=1.35, v_num=17]
Epoch 0:  15%|█▍        | 139/938 [00:09<00:57, 13.93it/s, loss=1.35, v_num=17]
Epoch 0:  15%|█▍        | 139/938 [00:09<00:57, 13.93it/s, loss=1.33, v_num=17]
Epoch 0:  15%|█▍        | 140/938 [00:10<00:57, 13.95it/s, loss=1.3, v_num=17] 
Epoch 0:  15%|█▌        | 141/938 [00:10<00:57, 13.96it/s, loss=1.3, v_num=17]
Epoch 0:  15%|█▌        | 141/938 [00:10<00:57, 13.96it/s, loss=1.29, v_num=17]
Epoch 0:  15%|█▌        | 142/938 [00:10<00:56, 13.97it/s, loss=1.28, v_num=17]
Epoch 0:  15%|█▌        | 143/938 [00:10<00:56, 13.97it/s, loss=1.28, v_num=17]
Epoch 0:  15%|█▌        | 143/938 [00:10<00:56, 13.97it/s, loss=1.27, v_num=17]
Epoch 0:  15%|█▌        | 144/938 [00:10<00:56, 13.95it/s, loss=1.28, v_num=17]
Epoch 0:  15%|█▌        | 145/938 [00:10<00:56, 13.97it/s, loss=1.28, v_num=17]
Epoch 0:  15%|█▌        | 145/938 [00:10<00:56, 13.97it/s, loss=1.29, v_num=17]
Epoch 0:  16%|█▌        | 146/938 [00:10<00:56, 13.97it/s, loss=1.28, v_num=17]
Epoch 0:  16%|█▌        | 147/938 [00:10<00:56, 13.96it/s, loss=1.28, v_num=17]
Epoch 0:  16%|█▌        | 147/938 [00:10<00:56, 13.96it/s, loss=1.29, v_num=17]
Epoch 0:  16%|█▌        | 148/938 [00:10<00:56, 13.96it/s, loss=1.26, v_num=17]
Epoch 0:  16%|█▌        | 149/938 [00:10<00:56, 13.96it/s, loss=1.26, v_num=17]
Epoch 0:  16%|█▌        | 149/938 [00:10<00:56, 13.96it/s, loss=1.26, v_num=17]
Epoch 0:  16%|█▌        | 150/938 [00:10<00:56, 13.96it/s, loss=1.26, v_num=17]
Epoch 0:  16%|█▌        | 151/938 [00:10<00:56, 13.97it/s, loss=1.26, v_num=17]
Epoch 0:  16%|█▌        | 151/938 [00:10<00:56, 13.97it/s, loss=1.24, v_num=17]
Epoch 0:  16%|█▌        | 152/938 [00:10<00:56, 13.97it/s, loss=1.22, v_num=17]
Epoch 0:  16%|█▋        | 153/938 [00:10<00:56, 13.97it/s, loss=1.22, v_num=17]
Epoch 0:  16%|█▋        | 153/938 [00:10<00:56, 13.97it/s, loss=1.22, v_num=17]
Epoch 0:  16%|█▋        | 154/938 [00:11<00:56, 13.96it/s, loss=1.21, v_num=17]
Epoch 0:  17%|█▋        | 155/938 [00:11<00:56, 13.95it/s, loss=1.21, v_num=17]
Epoch 0:  17%|█▋        | 155/938 [00:11<00:56, 13.94it/s, loss=1.22, v_num=17]
Epoch 0:  17%|█▋        | 156/938 [00:11<00:56, 13.93it/s, loss=1.2, v_num=17] 
Epoch 0:  17%|█▋        | 157/938 [00:11<00:56, 13.93it/s, loss=1.2, v_num=17]
Epoch 0:  17%|█▋        | 157/938 [00:11<00:56, 13.93it/s, loss=1.19, v_num=17]
Epoch 0:  17%|█▋        | 158/938 [00:11<00:56, 13.92it/s, loss=1.19, v_num=17]
Epoch 0:  17%|█▋        | 159/938 [00:11<00:55, 13.92it/s, loss=1.19, v_num=17]
Epoch 0:  17%|█▋        | 159/938 [00:11<00:55, 13.92it/s, loss=1.19, v_num=17]
Epoch 0:  17%|█▋        | 160/938 [00:11<00:55, 13.93it/s, loss=1.18, v_num=17]
Epoch 0:  17%|█▋        | 161/938 [00:11<00:55, 13.92it/s, loss=1.18, v_num=17]
Epoch 0:  17%|█▋        | 161/938 [00:11<00:55, 13.92it/s, loss=1.16, v_num=17]
Epoch 0:  17%|█▋        | 162/938 [00:11<00:55, 13.91it/s, loss=1.15, v_num=17]
Epoch 0:  17%|█▋        | 163/938 [00:11<00:55, 13.92it/s, loss=1.15, v_num=17]
Epoch 0:  17%|█▋        | 163/938 [00:11<00:55, 13.92it/s, loss=1.13, v_num=17]
Epoch 0:  17%|█▋        | 164/938 [00:11<00:55, 13.92it/s, loss=1.11, v_num=17]
Epoch 0:  18%|█▊        | 165/938 [00:11<00:55, 13.94it/s, loss=1.11, v_num=17]
Epoch 0:  18%|█▊        | 165/938 [00:11<00:55, 13.94it/s, loss=1.1, v_num=17] 
Epoch 0:  18%|█▊        | 166/938 [00:11<00:55, 13.92it/s, loss=1.09, v_num=17]
Epoch 0:  18%|█▊        | 167/938 [00:11<00:55, 13.92it/s, loss=1.09, v_num=17]
Epoch 0:  18%|█▊        | 167/938 [00:11<00:55, 13.92it/s, loss=1.07, v_num=17]
Epoch 0:  18%|█▊        | 168/938 [00:12<00:55, 13.92it/s, loss=1.07, v_num=17]
Epoch 0:  18%|█▊        | 169/938 [00:12<00:55, 13.94it/s, loss=1.07, v_num=17]
Epoch 0:  18%|█▊        | 169/938 [00:12<00:55, 13.94it/s, loss=1.06, v_num=17]
Epoch 0:  18%|█▊        | 170/938 [00:12<00:55, 13.90it/s, loss=1.06, v_num=17]
Epoch 0:  18%|█▊        | 171/938 [00:12<00:55, 13.90it/s, loss=1.06, v_num=17]
Epoch 0:  18%|█▊        | 171/938 [00:12<00:55, 13.90it/s, loss=1.06, v_num=17]
Epoch 0:  18%|█▊        | 172/938 [00:12<00:55, 13.91it/s, loss=1.05, v_num=17]
Epoch 0:  18%|█▊        | 173/938 [00:12<00:55, 13.90it/s, loss=1.05, v_num=17]
Epoch 0:  18%|█▊        | 173/938 [00:12<00:55, 13.90it/s, loss=1.04, v_num=17]
Epoch 0:  19%|█▊        | 174/938 [00:12<00:54, 13.90it/s, loss=1.05, v_num=17]
Epoch 0:  19%|█▊        | 175/938 [00:12<00:54, 13.89it/s, loss=1.05, v_num=17]
Epoch 0:  19%|█▊        | 175/938 [00:12<00:54, 13.89it/s, loss=1.04, v_num=17]
Epoch 0:  19%|█▉        | 176/938 [00:12<00:54, 13.89it/s, loss=1.03, v_num=17]
Epoch 0:  19%|█▉        | 177/938 [00:12<00:54, 13.88it/s, loss=1.03, v_num=17]
Epoch 0:  19%|█▉        | 177/938 [00:12<00:54, 13.88it/s, loss=1.02, v_num=17]
Epoch 0:  19%|█▉        | 178/938 [00:12<00:54, 13.89it/s, loss=1.03, v_num=17]
Epoch 0:  19%|█▉        | 179/938 [00:12<00:54, 13.87it/s, loss=1.03, v_num=17]
Epoch 0:  19%|█▉        | 179/938 [00:12<00:54, 13.87it/s, loss=1.04, v_num=17]
Epoch 0:  19%|█▉        | 180/938 [00:12<00:54, 13.87it/s, loss=1.04, v_num=17]
Epoch 0:  19%|█▉        | 181/938 [00:13<00:54, 13.86it/s, loss=1.04, v_num=17]
Epoch 0:  19%|█▉        | 181/938 [00:13<00:54, 13.86it/s, loss=1.05, v_num=17]
Epoch 0:  19%|█▉        | 182/938 [00:13<00:54, 13.85it/s, loss=1.05, v_num=17]
Epoch 0:  20%|█▉        | 183/938 [00:13<00:54, 13.84it/s, loss=1.05, v_num=17]
Epoch 0:  20%|█▉        | 183/938 [00:13<00:54, 13.84it/s, loss=1.07, v_num=17]
Epoch 0:  20%|█▉        | 184/938 [00:13<00:54, 13.84it/s, loss=1.09, v_num=17]
Epoch 0:  20%|█▉        | 185/938 [00:13<00:54, 13.84it/s, loss=1.09, v_num=17]
Epoch 0:  20%|█▉        | 185/938 [00:13<00:54, 13.84it/s, loss=1.1, v_num=17] 
Epoch 0:  20%|█▉        | 186/938 [00:13<00:54, 13.83it/s, loss=1.09, v_num=17]
Epoch 0:  20%|█▉        | 187/938 [00:13<00:54, 13.83it/s, loss=1.09, v_num=17]
Epoch 0:  20%|█▉        | 187/938 [00:13<00:54, 13.83it/s, loss=1.09, v_num=17]
Epoch 0:  20%|██        | 188/938 [00:13<00:54, 13.85it/s, loss=1.09, v_num=17]
Epoch 0:  20%|██        | 189/938 [00:13<00:54, 13.85it/s, loss=1.09, v_num=17]
Epoch 0:  20%|██        | 189/938 [00:13<00:54, 13.85it/s, loss=1.09, v_num=17]
Epoch 0:  20%|██        | 190/938 [00:13<00:54, 13.85it/s, loss=1.08, v_num=17]
Epoch 0:  20%|██        | 191/938 [00:13<00:53, 13.86it/s, loss=1.08, v_num=17]
Epoch 0:  20%|██        | 191/938 [00:13<00:53, 13.86it/s, loss=1.07, v_num=17]
Epoch 0:  20%|██        | 192/938 [00:13<00:53, 13.86it/s, loss=1.08, v_num=17]
Epoch 0:  21%|██        | 193/938 [00:13<00:53, 13.86it/s, loss=1.08, v_num=17]
Epoch 0:  21%|██        | 193/938 [00:13<00:53, 13.86it/s, loss=1.07, v_num=17]
Epoch 0:  21%|██        | 194/938 [00:14<00:53, 13.85it/s, loss=1.06, v_num=17]
Epoch 0:  21%|██        | 195/938 [00:14<00:53, 13.85it/s, loss=1.06, v_num=17]
Epoch 0:  21%|██        | 195/938 [00:14<00:53, 13.85it/s, loss=1.07, v_num=17]
Epoch 0:  21%|██        | 196/938 [00:14<00:53, 13.83it/s, loss=1.07, v_num=17]
Epoch 0:  21%|██        | 197/938 [00:14<00:53, 13.82it/s, loss=1.07, v_num=17]
Epoch 0:  21%|██        | 197/938 [00:14<00:53, 13.82it/s, loss=1.06, v_num=17]
Epoch 0:  21%|██        | 198/938 [00:14<00:53, 13.82it/s, loss=1.05, v_num=17]
Epoch 0:  21%|██        | 199/938 [00:14<00:53, 13.83it/s, loss=1.05, v_num=17]
Epoch 0:  21%|██        | 199/938 [00:14<00:53, 13.83it/s, loss=1.04, v_num=17]
Epoch 0:  21%|██▏       | 200/938 [00:14<00:53, 13.84it/s, loss=1.04, v_num=17]
Epoch 0:  21%|██▏       | 201/938 [00:14<00:53, 13.85it/s, loss=1.04, v_num=17]
Epoch 0:  21%|██▏       | 201/938 [00:14<00:53, 13.85it/s, loss=1.04, v_num=17]
Epoch 0:  22%|██▏       | 202/938 [00:14<00:53, 13.85it/s, loss=1.05, v_num=17]
Epoch 0:  22%|██▏       | 203/938 [00:14<00:53, 13.84it/s, loss=1.05, v_num=17]
Epoch 0:  22%|██▏       | 203/938 [00:14<00:53, 13.84it/s, loss=1.04, v_num=17]
Epoch 0:  22%|██▏       | 204/938 [00:14<00:52, 13.86it/s, loss=1.02, v_num=17]
Epoch 0:  22%|██▏       | 205/938 [00:14<00:52, 13.85it/s, loss=1.02, v_num=17]
Epoch 0:  22%|██▏       | 205/938 [00:14<00:52, 13.85it/s, loss=1.01, v_num=17]
Epoch 0:  22%|██▏       | 206/938 [00:14<00:52, 13.83it/s, loss=1.01, v_num=17]
Epoch 0:  22%|██▏       | 207/938 [00:14<00:52, 13.83it/s, loss=1.01, v_num=17]
Epoch 0:  22%|██▏       | 207/938 [00:14<00:52, 13.83it/s, loss=1, v_num=17]   
Epoch 0:  22%|██▏       | 208/938 [00:15<00:52, 13.84it/s, loss=0.998, v_num=17]
Epoch 0:  22%|██▏       | 209/938 [00:15<00:52, 13.84it/s, loss=0.998, v_num=17]
Epoch 0:  22%|██▏       | 209/938 [00:15<00:52, 13.84it/s, loss=0.994, v_num=17]
Epoch 0:  22%|██▏       | 210/938 [00:15<00:52, 13.85it/s, loss=0.998, v_num=17]
Epoch 0:  22%|██▏       | 211/938 [00:15<00:52, 13.86it/s, loss=0.998, v_num=17]
Epoch 0:  22%|██▏       | 211/938 [00:15<00:52, 13.86it/s, loss=1, v_num=17]    
Epoch 0:  23%|██▎       | 212/938 [00:15<00:52, 13.85it/s, loss=1, v_num=17]
Epoch 0:  23%|██▎       | 213/938 [00:15<00:52, 13.87it/s, loss=1, v_num=17]
Epoch 0:  23%|██▎       | 213/938 [00:15<00:52, 13.87it/s, loss=1, v_num=17]
Epoch 0:  23%|██▎       | 214/938 [00:15<00:52, 13.88it/s, loss=0.998, v_num=17]
Epoch 0:  23%|██▎       | 215/938 [00:15<00:52, 13.85it/s, loss=0.998, v_num=17]
Epoch 0:  23%|██▎       | 215/938 [00:15<00:52, 13.85it/s, loss=1.01, v_num=17] 
Epoch 0:  23%|██▎       | 216/938 [00:15<00:52, 13.86it/s, loss=1.01, v_num=17]
Epoch 0:  23%|██▎       | 217/938 [00:15<00:52, 13.85it/s, loss=1.01, v_num=17]
Epoch 0:  23%|██▎       | 217/938 [00:15<00:52, 13.85it/s, loss=1.03, v_num=17]
Epoch 0:  23%|██▎       | 218/938 [00:15<00:51, 13.86it/s, loss=1.03, v_num=17]
Epoch 0:  23%|██▎       | 219/938 [00:15<00:51, 13.87it/s, loss=1.03, v_num=17]
Epoch 0:  23%|██▎       | 219/938 [00:15<00:51, 13.87it/s, loss=1.03, v_num=17]
Epoch 0:  23%|██▎       | 220/938 [00:15<00:51, 13.87it/s, loss=1.02, v_num=17]
Epoch 0:  24%|██▎       | 221/938 [00:15<00:51, 13.88it/s, loss=1.02, v_num=17]
Epoch 0:  24%|██▎       | 221/938 [00:15<00:51, 13.88it/s, loss=1.02, v_num=17]
Epoch 0:  24%|██▎       | 222/938 [00:16<00:51, 13.87it/s, loss=0.992, v_num=17]
Epoch 0:  24%|██▍       | 223/938 [00:16<00:51, 13.87it/s, loss=0.992, v_num=17]
Epoch 0:  24%|██▍       | 223/938 [00:16<00:51, 13.87it/s, loss=0.981, v_num=17]
Epoch 0:  24%|██▍       | 224/938 [00:16<00:51, 13.88it/s, loss=0.993, v_num=17]
Epoch 0:  24%|██▍       | 225/938 [00:16<00:51, 13.87it/s, loss=0.993, v_num=17]
Epoch 0:  24%|██▍       | 225/938 [00:16<00:51, 13.87it/s, loss=1, v_num=17]    
Epoch 0:  24%|██▍       | 226/938 [00:16<00:51, 13.88it/s, loss=0.991, v_num=17]
Epoch 0:  24%|██▍       | 227/938 [00:16<00:51, 13.86it/s, loss=0.991, v_num=17]
Epoch 0:  24%|██▍       | 227/938 [00:16<00:51, 13.86it/s, loss=1.01, v_num=17] 
Epoch 0:  24%|██▍       | 228/938 [00:16<00:51, 13.86it/s, loss=1.01, v_num=17]
Epoch 0:  24%|██▍       | 229/938 [00:16<00:51, 13.86it/s, loss=1.01, v_num=17]
Epoch 0:  24%|██▍       | 229/938 [00:16<00:51, 13.86it/s, loss=1.01, v_num=17]
Epoch 0:  25%|██▍       | 230/938 [00:16<00:51, 13.86it/s, loss=1.01, v_num=17]
Epoch 0:  25%|██▍       | 231/938 [00:16<00:51, 13.85it/s, loss=1.01, v_num=17]
Epoch 0:  25%|██▍       | 231/938 [00:16<00:51, 13.84it/s, loss=0.993, v_num=17]
Epoch 0:  25%|██▍       | 232/938 [00:16<00:51, 13.84it/s, loss=0.983, v_num=17]
Epoch 0:  25%|██▍       | 233/938 [00:16<00:50, 13.84it/s, loss=0.983, v_num=17]
Epoch 0:  25%|██▍       | 233/938 [00:16<00:50, 13.84it/s, loss=0.978, v_num=17]
Epoch 0:  25%|██▍       | 234/938 [00:16<00:50, 13.85it/s, loss=0.983, v_num=17]
Epoch 0:  25%|██▌       | 235/938 [00:16<00:50, 13.85it/s, loss=0.983, v_num=17]
Epoch 0:  25%|██▌       | 235/938 [00:16<00:50, 13.85it/s, loss=0.979, v_num=17]
Epoch 0:  25%|██▌       | 236/938 [00:17<00:50, 13.85it/s, loss=0.976, v_num=17]
Epoch 0:  25%|██▌       | 237/938 [00:17<00:50, 13.85it/s, loss=0.976, v_num=17]
Epoch 0:  25%|██▌       | 237/938 [00:17<00:50, 13.85it/s, loss=0.956, v_num=17]
Epoch 0:  25%|██▌       | 238/938 [00:17<00:50, 13.85it/s, loss=0.959, v_num=17]
Epoch 0:  25%|██▌       | 239/938 [00:17<00:50, 13.85it/s, loss=0.959, v_num=17]
Epoch 0:  25%|██▌       | 239/938 [00:17<00:50, 13.85it/s, loss=0.957, v_num=17]
Epoch 0:  26%|██▌       | 240/938 [00:17<00:50, 13.84it/s, loss=0.963, v_num=17]
Epoch 0:  26%|██▌       | 241/938 [00:17<00:50, 13.85it/s, loss=0.963, v_num=17]
Epoch 0:  26%|██▌       | 241/938 [00:17<00:50, 13.85it/s, loss=0.968, v_num=17]
Epoch 0:  26%|██▌       | 242/938 [00:17<00:50, 13.85it/s, loss=0.961, v_num=17]
Epoch 0:  26%|██▌       | 243/938 [00:17<00:50, 13.85it/s, loss=0.961, v_num=17]
Epoch 0:  26%|██▌       | 243/938 [00:17<00:50, 13.85it/s, loss=0.958, v_num=17]
Epoch 0:  26%|██▌       | 244/938 [00:17<00:50, 13.84it/s, loss=0.95, v_num=17] 
Epoch 0:  26%|██▌       | 245/938 [00:17<00:50, 13.84it/s, loss=0.95, v_num=17]
Epoch 0:  26%|██▌       | 245/938 [00:17<00:50, 13.84it/s, loss=0.941, v_num=17]
Epoch 0:  26%|██▌       | 246/938 [00:17<00:49, 13.84it/s, loss=0.952, v_num=17]
Epoch 0:  26%|██▋       | 247/938 [00:17<00:49, 13.86it/s, loss=0.952, v_num=17]
Epoch 0:  26%|██▋       | 247/938 [00:17<00:49, 13.86it/s, loss=0.938, v_num=17]
Epoch 0:  26%|██▋       | 248/938 [00:17<00:49, 13.87it/s, loss=0.94, v_num=17] 
Epoch 0:  27%|██▋       | 249/938 [00:17<00:49, 13.86it/s, loss=0.94, v_num=17]
Epoch 0:  27%|██▋       | 249/938 [00:17<00:49, 13.86it/s, loss=0.933, v_num=17]
Epoch 0:  27%|██▋       | 250/938 [00:18<00:49, 13.87it/s, loss=0.928, v_num=17]
Epoch 0:  27%|██▋       | 251/938 [00:18<00:49, 13.86it/s, loss=0.928, v_num=17]
Epoch 0:  27%|██▋       | 251/938 [00:18<00:49, 13.86it/s, loss=0.936, v_num=17]
Epoch 0:  27%|██▋       | 252/938 [00:18<00:49, 13.87it/s, loss=0.939, v_num=17]
Epoch 0:  27%|██▋       | 253/938 [00:18<00:49, 13.85it/s, loss=0.939, v_num=17]
Epoch 0:  27%|██▋       | 253/938 [00:18<00:49, 13.85it/s, loss=0.94, v_num=17] 
Epoch 0:  27%|██▋       | 254/938 [00:18<00:49, 13.85it/s, loss=0.938, v_num=17]
Epoch 0:  27%|██▋       | 255/938 [00:18<00:49, 13.86it/s, loss=0.938, v_num=17]
Epoch 0:  27%|██▋       | 255/938 [00:18<00:49, 13.86it/s, loss=0.925, v_num=17]
Epoch 0:  27%|██▋       | 256/938 [00:18<00:49, 13.86it/s, loss=0.927, v_num=17]
Epoch 0:  27%|██▋       | 257/938 [00:18<00:49, 13.86it/s, loss=0.927, v_num=17]
Epoch 0:  27%|██▋       | 257/938 [00:18<00:49, 13.86it/s, loss=0.935, v_num=17]
Epoch 0:  28%|██▊       | 258/938 [00:18<00:49, 13.87it/s, loss=0.931, v_num=17]
Epoch 0:  28%|██▊       | 259/938 [00:18<00:48, 13.88it/s, loss=0.931, v_num=17]
Epoch 0:  28%|██▊       | 259/938 [00:18<00:48, 13.88it/s, loss=0.941, v_num=17]
Epoch 0:  28%|██▊       | 260/938 [00:18<00:48, 13.88it/s, loss=0.932, v_num=17]
Epoch 0:  28%|██▊       | 261/938 [00:18<00:48, 13.88it/s, loss=0.932, v_num=17]
Epoch 0:  28%|██▊       | 261/938 [00:18<00:48, 13.88it/s, loss=0.938, v_num=17]
Epoch 0:  28%|██▊       | 262/938 [00:18<00:48, 13.88it/s, loss=0.952, v_num=17]
Epoch 0:  28%|██▊       | 263/938 [00:18<00:48, 13.88it/s, loss=0.952, v_num=17]
Epoch 0:  28%|██▊       | 263/938 [00:18<00:48, 13.88it/s, loss=0.956, v_num=17]
Epoch 0:  28%|██▊       | 264/938 [00:19<00:48, 13.87it/s, loss=0.959, v_num=17]
Epoch 0:  28%|██▊       | 265/938 [00:19<00:48, 13.88it/s, loss=0.959, v_num=17]
Epoch 0:  28%|██▊       | 265/938 [00:19<00:48, 13.88it/s, loss=0.964, v_num=17]
Epoch 0:  28%|██▊       | 266/938 [00:19<00:48, 13.88it/s, loss=0.954, v_num=17]
Epoch 0:  28%|██▊       | 267/938 [00:19<00:48, 13.88it/s, loss=0.954, v_num=17]
Epoch 0:  28%|██▊       | 267/938 [00:19<00:48, 13.88it/s, loss=0.947, v_num=17]
Epoch 0:  29%|██▊       | 268/938 [00:19<00:48, 13.88it/s, loss=0.95, v_num=17] 
Epoch 0:  29%|██▊       | 269/938 [00:19<00:48, 13.89it/s, loss=0.95, v_num=17]
Epoch 0:  29%|██▊       | 269/938 [00:19<00:48, 13.89it/s, loss=0.953, v_num=17]
Epoch 0:  29%|██▉       | 270/938 [00:19<00:48, 13.88it/s, loss=0.952, v_num=17]
Epoch 0:  29%|██▉       | 271/938 [00:19<00:48, 13.88it/s, loss=0.952, v_num=17]
Epoch 0:  29%|██▉       | 271/938 [00:19<00:48, 13.88it/s, loss=0.95, v_num=17] 
Epoch 0:  29%|██▉       | 272/938 [00:19<00:47, 13.88it/s, loss=0.948, v_num=17]
Epoch 0:  29%|██▉       | 273/938 [00:19<00:47, 13.87it/s, loss=0.948, v_num=17]
Epoch 0:  29%|██▉       | 273/938 [00:19<00:47, 13.87it/s, loss=0.945, v_num=17]
Epoch 0:  29%|██▉       | 274/938 [00:19<00:47, 13.86it/s, loss=0.947, v_num=17]
Epoch 0:  29%|██▉       | 275/938 [00:19<00:47, 13.86it/s, loss=0.947, v_num=17]
Epoch 0:  29%|██▉       | 275/938 [00:19<00:47, 13.86it/s, loss=0.951, v_num=17]
Epoch 0:  29%|██▉       | 276/938 [00:19<00:47, 13.86it/s, loss=0.947, v_num=17]
Epoch 0:  30%|██▉       | 277/938 [00:19<00:47, 13.86it/s, loss=0.947, v_num=17]
Epoch 0:  30%|██▉       | 277/938 [00:19<00:47, 13.86it/s, loss=0.943, v_num=17]
Epoch 0:  30%|██▉       | 278/938 [00:20<00:47, 13.85it/s, loss=0.949, v_num=17]
Epoch 0:  30%|██▉       | 279/938 [00:20<00:47, 13.85it/s, loss=0.949, v_num=17]
Epoch 0:  30%|██▉       | 279/938 [00:20<00:47, 13.85it/s, loss=0.941, v_num=17]
Epoch 0:  30%|██▉       | 280/938 [00:20<00:47, 13.84it/s, loss=0.95, v_num=17] 
Epoch 0:  30%|██▉       | 281/938 [00:20<00:47, 13.83it/s, loss=0.95, v_num=17]
Epoch 0:  30%|██▉       | 281/938 [00:20<00:47, 13.83it/s, loss=0.942, v_num=17]
Epoch 0:  30%|███       | 282/938 [00:20<00:47, 13.83it/s, loss=0.937, v_num=17]
Epoch 0:  30%|███       | 283/938 [00:20<00:47, 13.84it/s, loss=0.937, v_num=17]
Epoch 0:  30%|███       | 283/938 [00:20<00:47, 13.84it/s, loss=0.936, v_num=17]
Epoch 0:  30%|███       | 284/938 [00:20<00:47, 13.80it/s, loss=0.934, v_num=17]
Epoch 0:  30%|███       | 285/938 [00:20<00:47, 13.79it/s, loss=0.934, v_num=17]
Epoch 0:  30%|███       | 285/938 [00:20<00:47, 13.79it/s, loss=0.924, v_num=17]
Epoch 0:  30%|███       | 286/938 [00:20<00:47, 13.80it/s, loss=0.926, v_num=17]
Epoch 0:  31%|███       | 287/938 [00:20<00:47, 13.79it/s, loss=0.926, v_num=17]
Epoch 0:  31%|███       | 287/938 [00:20<00:47, 13.79it/s, loss=0.946, v_num=17]
Epoch 0:  31%|███       | 288/938 [00:20<00:47, 13.80it/s, loss=0.934, v_num=17]
Epoch 0:  31%|███       | 289/938 [00:20<00:47, 13.80it/s, loss=0.934, v_num=17]
Epoch 0:  31%|███       | 289/938 [00:20<00:47, 13.80it/s, loss=0.936, v_num=17]
Epoch 0:  31%|███       | 290/938 [00:21<00:46, 13.80it/s, loss=0.938, v_num=17]
Epoch 0:  31%|███       | 291/938 [00:21<00:46, 13.81it/s, loss=0.938, v_num=17]
Epoch 0:  31%|███       | 291/938 [00:21<00:46, 13.81it/s, loss=0.939, v_num=17]
Epoch 0:  31%|███       | 292/938 [00:21<00:46, 13.80it/s, loss=0.942, v_num=17]
Epoch 0:  31%|███       | 293/938 [00:21<00:46, 13.80it/s, loss=0.942, v_num=17]
Epoch 0:  31%|███       | 293/938 [00:21<00:46, 13.80it/s, loss=0.943, v_num=17]
Epoch 0:  31%|███▏      | 294/938 [00:21<00:46, 13.80it/s, loss=0.942, v_num=17]
Epoch 0:  31%|███▏      | 295/938 [00:21<00:46, 13.80it/s, loss=0.942, v_num=17]
Epoch 0:  31%|███▏      | 295/938 [00:21<00:46, 13.80it/s, loss=0.942, v_num=17]
Epoch 0:  32%|███▏      | 296/938 [00:21<00:46, 13.80it/s, loss=0.935, v_num=17]
Epoch 0:  32%|███▏      | 297/938 [00:21<00:46, 13.80it/s, loss=0.935, v_num=17]
Epoch 0:  32%|███▏      | 297/938 [00:21<00:46, 13.80it/s, loss=0.936, v_num=17]
Epoch 0:  32%|███▏      | 298/938 [00:21<00:46, 13.80it/s, loss=0.932, v_num=17]
Epoch 0:  32%|███▏      | 299/938 [00:21<00:46, 13.81it/s, loss=0.932, v_num=17]
Epoch 0:  32%|███▏      | 299/938 [00:21<00:46, 13.81it/s, loss=0.946, v_num=17]
Epoch 0:  32%|███▏      | 300/938 [00:21<00:46, 13.81it/s, loss=0.928, v_num=17]
Epoch 0:  32%|███▏      | 301/938 [00:21<00:46, 13.81it/s, loss=0.928, v_num=17]
Epoch 0:  32%|███▏      | 301/938 [00:21<00:46, 13.81it/s, loss=0.926, v_num=17]
Epoch 0:  32%|███▏      | 302/938 [00:21<00:46, 13.81it/s, loss=0.928, v_num=17]
Epoch 0:  32%|███▏      | 303/938 [00:21<00:45, 13.81it/s, loss=0.928, v_num=17]
Epoch 0:  32%|███▏      | 303/938 [00:21<00:45, 13.81it/s, loss=0.918, v_num=17]
Epoch 0:  32%|███▏      | 304/938 [00:22<00:45, 13.81it/s, loss=0.919, v_num=17]
Epoch 0:  33%|███▎      | 305/938 [00:22<00:45, 13.81it/s, loss=0.919, v_num=17]
Epoch 0:  33%|███▎      | 305/938 [00:22<00:45, 13.81it/s, loss=0.927, v_num=17]
Epoch 0:  33%|███▎      | 306/938 [00:22<00:45, 13.81it/s, loss=0.923, v_num=17]
Epoch 0:  33%|███▎      | 307/938 [00:22<00:45, 13.82it/s, loss=0.923, v_num=17]
Epoch 0:  33%|███▎      | 307/938 [00:22<00:45, 13.82it/s, loss=0.907, v_num=17]
Epoch 0:  33%|███▎      | 308/938 [00:22<00:45, 13.83it/s, loss=0.907, v_num=17]
Epoch 0:  33%|███▎      | 309/938 [00:22<00:45, 13.83it/s, loss=0.907, v_num=17]
Epoch 0:  33%|███▎      | 309/938 [00:22<00:45, 13.83it/s, loss=0.908, v_num=17]
Epoch 0:  33%|███▎      | 310/938 [00:22<00:45, 13.83it/s, loss=0.908, v_num=17]
Epoch 0:  33%|███▎      | 311/938 [00:22<00:45, 13.83it/s, loss=0.908, v_num=17]
Epoch 0:  33%|███▎      | 311/938 [00:22<00:45, 13.83it/s, loss=0.901, v_num=17]
Epoch 0:  33%|███▎      | 312/938 [00:22<00:45, 13.83it/s, loss=0.893, v_num=17]
Epoch 0:  33%|███▎      | 313/938 [00:22<00:45, 13.82it/s, loss=0.893, v_num=17]
Epoch 0:  33%|███▎      | 313/938 [00:22<00:45, 13.82it/s, loss=0.894, v_num=17]
Epoch 0:  33%|███▎      | 314/938 [00:22<00:45, 13.81it/s, loss=0.892, v_num=17]
Epoch 0:  34%|███▎      | 315/938 [00:22<00:45, 13.81it/s, loss=0.892, v_num=17]
Epoch 0:  34%|███▎      | 315/938 [00:22<00:45, 13.81it/s, loss=0.89, v_num=17] 
Epoch 0:  34%|███▎      | 316/938 [00:22<00:45, 13.81it/s, loss=0.891, v_num=17]
Epoch 0:  34%|███▍      | 317/938 [00:22<00:44, 13.81it/s, loss=0.891, v_num=17]
Epoch 0:  34%|███▍      | 317/938 [00:22<00:44, 13.81it/s, loss=0.891, v_num=17]
Epoch 0:  34%|███▍      | 318/938 [00:23<00:44, 13.81it/s, loss=0.897, v_num=17]
Epoch 0:  34%|███▍      | 319/938 [00:23<00:44, 13.81it/s, loss=0.897, v_num=17]
Epoch 0:  34%|███▍      | 319/938 [00:23<00:44, 13.81it/s, loss=0.887, v_num=17]
Epoch 0:  34%|███▍      | 320/938 [00:23<00:44, 13.81it/s, loss=0.897, v_num=17]
Epoch 0:  34%|███▍      | 321/938 [00:23<00:44, 13.81it/s, loss=0.897, v_num=17]
Epoch 0:  34%|███▍      | 321/938 [00:23<00:44, 13.81it/s, loss=0.895, v_num=17]
Epoch 0:  34%|███▍      | 322/938 [00:23<00:44, 13.81it/s, loss=0.89, v_num=17] 
Epoch 0:  34%|███▍      | 323/938 [00:23<00:44, 13.81it/s, loss=0.89, v_num=17]
Epoch 0:  34%|███▍      | 323/938 [00:23<00:44, 13.81it/s, loss=0.892, v_num=17]
Epoch 0:  35%|███▍      | 324/938 [00:23<00:44, 13.82it/s, loss=0.885, v_num=17]
Epoch 0:  35%|███▍      | 325/938 [00:23<00:44, 13.82it/s, loss=0.885, v_num=17]
Epoch 0:  35%|███▍      | 325/938 [00:23<00:44, 13.82it/s, loss=0.891, v_num=17]
Epoch 0:  35%|███▍      | 326/938 [00:23<00:44, 13.82it/s, loss=0.886, v_num=17]
Epoch 0:  35%|███▍      | 327/938 [00:23<00:44, 13.83it/s, loss=0.886, v_num=17]
Epoch 0:  35%|███▍      | 327/938 [00:23<00:44, 13.83it/s, loss=0.889, v_num=17]
Epoch 0:  35%|███▍      | 328/938 [00:23<00:44, 13.82it/s, loss=0.894, v_num=17]
Epoch 0:  35%|███▌      | 329/938 [00:23<00:44, 13.82it/s, loss=0.894, v_num=17]
Epoch 0:  35%|███▌      | 329/938 [00:23<00:44, 13.82it/s, loss=0.892, v_num=17]
Epoch 0:  35%|███▌      | 330/938 [00:23<00:44, 13.78it/s, loss=0.889, v_num=17]
Epoch 0:  35%|███▌      | 331/938 [00:24<00:44, 13.78it/s, loss=0.889, v_num=17]
Epoch 0:  35%|███▌      | 331/938 [00:24<00:44, 13.78it/s, loss=0.896, v_num=17]
Epoch 0:  35%|███▌      | 332/938 [00:24<00:43, 13.78it/s, loss=0.905, v_num=17]
Epoch 0:  36%|███▌      | 333/938 [00:24<00:43, 13.79it/s, loss=0.905, v_num=17]
Epoch 0:  36%|███▌      | 333/938 [00:24<00:43, 13.79it/s, loss=0.911, v_num=17]
Epoch 0:  36%|███▌      | 334/938 [00:24<00:43, 13.79it/s, loss=0.913, v_num=17]
Epoch 0:  36%|███▌      | 335/938 [00:24<00:43, 13.78it/s, loss=0.913, v_num=17]
Epoch 0:  36%|███▌      | 335/938 [00:24<00:43, 13.78it/s, loss=0.918, v_num=17]
Epoch 0:  36%|███▌      | 336/938 [00:24<00:43, 13.78it/s, loss=0.914, v_num=17]
Epoch 0:  36%|███▌      | 337/938 [00:24<00:43, 13.79it/s, loss=0.914, v_num=17]
Epoch 0:  36%|███▌      | 337/938 [00:24<00:43, 13.79it/s, loss=0.909, v_num=17]
Epoch 0:  36%|███▌      | 338/938 [00:24<00:43, 13.79it/s, loss=0.902, v_num=17]
Epoch 0:  36%|███▌      | 339/938 [00:24<00:43, 13.79it/s, loss=0.902, v_num=17]
Epoch 0:  36%|███▌      | 339/938 [00:24<00:43, 13.79it/s, loss=0.901, v_num=17]
Epoch 0:  36%|███▌      | 340/938 [00:24<00:43, 13.79it/s, loss=0.898, v_num=17]
Epoch 0:  36%|███▋      | 341/938 [00:24<00:43, 13.79it/s, loss=0.898, v_num=17]
Epoch 0:  36%|███▋      | 341/938 [00:24<00:43, 13.79it/s, loss=0.909, v_num=17]
Epoch 0:  36%|███▋      | 342/938 [00:24<00:43, 13.78it/s, loss=0.903, v_num=17]
Epoch 0:  37%|███▋      | 343/938 [00:24<00:43, 13.79it/s, loss=0.903, v_num=17]
Epoch 0:  37%|███▋      | 343/938 [00:24<00:43, 13.79it/s, loss=0.91, v_num=17] 
Epoch 0:  37%|███▋      | 344/938 [00:24<00:43, 13.79it/s, loss=0.915, v_num=17]
Epoch 0:  37%|███▋      | 345/938 [00:25<00:43, 13.79it/s, loss=0.915, v_num=17]
Epoch 0:  37%|███▋      | 345/938 [00:25<00:43, 13.79it/s, loss=0.907, v_num=17]
Epoch 0:  37%|███▋      | 346/938 [00:25<00:42, 13.79it/s, loss=0.908, v_num=17]
Epoch 0:  37%|███▋      | 347/938 [00:25<00:42, 13.80it/s, loss=0.908, v_num=17]
Epoch 0:  37%|███▋      | 347/938 [00:25<00:42, 13.80it/s, loss=0.904, v_num=17]
Epoch 0:  37%|███▋      | 348/938 [00:25<00:42, 13.80it/s, loss=0.894, v_num=17]
Epoch 0:  37%|███▋      | 349/938 [00:25<00:42, 13.80it/s, loss=0.894, v_num=17]
Epoch 0:  37%|███▋      | 349/938 [00:25<00:42, 13.80it/s, loss=0.886, v_num=17]
Epoch 0:  37%|███▋      | 350/938 [00:25<00:42, 13.80it/s, loss=0.885, v_num=17]
Epoch 0:  37%|███▋      | 351/938 [00:25<00:42, 13.81it/s, loss=0.885, v_num=17]
Epoch 0:  37%|███▋      | 351/938 [00:25<00:42, 13.81it/s, loss=0.891, v_num=17]
Epoch 0:  38%|███▊      | 352/938 [00:25<00:42, 13.81it/s, loss=0.884, v_num=17]
Epoch 0:  38%|███▊      | 353/938 [00:25<00:42, 13.81it/s, loss=0.884, v_num=17]
Epoch 0:  38%|███▊      | 353/938 [00:25<00:42, 13.81it/s, loss=0.878, v_num=17]
Epoch 0:  38%|███▊      | 354/938 [00:25<00:42, 13.82it/s, loss=0.872, v_num=17]
Epoch 0:  38%|███▊      | 355/938 [00:25<00:42, 13.82it/s, loss=0.872, v_num=17]
Epoch 0:  38%|███▊      | 355/938 [00:25<00:42, 13.82it/s, loss=0.872, v_num=17]
Epoch 0:  38%|███▊      | 356/938 [00:25<00:42, 13.82it/s, loss=0.882, v_num=17]
Epoch 0:  38%|███▊      | 357/938 [00:25<00:42, 13.81it/s, loss=0.882, v_num=17]
Epoch 0:  38%|███▊      | 357/938 [00:25<00:42, 13.81it/s, loss=0.887, v_num=17]
Epoch 0:  38%|███▊      | 358/938 [00:25<00:41, 13.82it/s, loss=0.883, v_num=17]
Epoch 0:  38%|███▊      | 359/938 [00:26<00:41, 13.80it/s, loss=0.883, v_num=17]
Epoch 0:  38%|███▊      | 359/938 [00:26<00:41, 13.80it/s, loss=0.891, v_num=17]
Epoch 0:  38%|███▊      | 360/938 [00:26<00:41, 13.81it/s, loss=0.893, v_num=17]
Epoch 0:  38%|███▊      | 361/938 [00:26<00:41, 13.81it/s, loss=0.893, v_num=17]
Epoch 0:  38%|███▊      | 361/938 [00:26<00:41, 13.81it/s, loss=0.882, v_num=17]
Epoch 0:  39%|███▊      | 362/938 [00:26<00:41, 13.81it/s, loss=0.889, v_num=17]
Epoch 0:  39%|███▊      | 363/938 [00:26<00:41, 13.82it/s, loss=0.889, v_num=17]
Epoch 0:  39%|███▊      | 363/938 [00:26<00:41, 13.82it/s, loss=0.895, v_num=17]
Epoch 0:  39%|███▉      | 364/938 [00:26<00:41, 13.82it/s, loss=0.896, v_num=17]
Epoch 0:  39%|███▉      | 365/938 [00:26<00:41, 13.82it/s, loss=0.896, v_num=17]
Epoch 0:  39%|███▉      | 365/938 [00:26<00:41, 13.82it/s, loss=0.888, v_num=17]
Epoch 0:  39%|███▉      | 366/938 [00:26<00:41, 13.84it/s, loss=0.888, v_num=17]
Epoch 0:  39%|███▉      | 367/938 [00:26<00:41, 13.84it/s, loss=0.888, v_num=17]
Epoch 0:  39%|███▉      | 367/938 [00:26<00:41, 13.84it/s, loss=0.889, v_num=17]
Epoch 0:  39%|███▉      | 368/938 [00:26<00:41, 13.84it/s, loss=0.893, v_num=17]
Epoch 0:  39%|███▉      | 369/938 [00:26<00:41, 13.84it/s, loss=0.893, v_num=17]
Epoch 0:  39%|███▉      | 369/938 [00:26<00:41, 13.84it/s, loss=0.903, v_num=17]
Epoch 0:  39%|███▉      | 370/938 [00:26<00:41, 13.84it/s, loss=0.905, v_num=17]
Epoch 0:  40%|███▉      | 371/938 [00:26<00:40, 13.85it/s, loss=0.905, v_num=17]
Epoch 0:  40%|███▉      | 371/938 [00:26<00:40, 13.85it/s, loss=0.901, v_num=17]
Epoch 0:  40%|███▉      | 372/938 [00:26<00:40, 13.85it/s, loss=0.901, v_num=17]
Epoch 0:  40%|███▉      | 373/938 [00:26<00:40, 13.86it/s, loss=0.901, v_num=17]
Epoch 0:  40%|███▉      | 373/938 [00:26<00:40, 13.86it/s, loss=0.904, v_num=17]
Epoch 0:  40%|███▉      | 374/938 [00:26<00:40, 13.86it/s, loss=0.896, v_num=17]
Epoch 0:  40%|███▉      | 375/938 [00:27<00:40, 13.86it/s, loss=0.896, v_num=17]
Epoch 0:  40%|███▉      | 375/938 [00:27<00:40, 13.86it/s, loss=0.889, v_num=17]
Epoch 0:  40%|████      | 376/938 [00:27<00:40, 13.85it/s, loss=0.881, v_num=17]
Epoch 0:  40%|████      | 377/938 [00:27<00:40, 13.85it/s, loss=0.881, v_num=17]
Epoch 0:  40%|████      | 377/938 [00:27<00:40, 13.85it/s, loss=0.871, v_num=17]
Epoch 0:  40%|████      | 378/938 [00:27<00:40, 13.85it/s, loss=0.876, v_num=17]
Epoch 0:  40%|████      | 379/938 [00:27<00:40, 13.85it/s, loss=0.876, v_num=17]
Epoch 0:  40%|████      | 379/938 [00:27<00:40, 13.85it/s, loss=0.862, v_num=17]
Epoch 0:  41%|████      | 380/938 [00:27<00:40, 13.85it/s, loss=0.859, v_num=17]
Epoch 0:  41%|████      | 381/938 [00:27<00:40, 13.85it/s, loss=0.859, v_num=17]
Epoch 0:  41%|████      | 381/938 [00:27<00:40, 13.85it/s, loss=0.855, v_num=17]
Epoch 0:  41%|████      | 382/938 [00:27<00:40, 13.86it/s, loss=0.854, v_num=17]
Epoch 0:  41%|████      | 383/938 [00:27<00:40, 13.86it/s, loss=0.854, v_num=17]
Epoch 0:  41%|████      | 383/938 [00:27<00:40, 13.86it/s, loss=0.845, v_num=17]
Epoch 0:  41%|████      | 384/938 [00:27<00:39, 13.85it/s, loss=0.844, v_num=17]
Epoch 0:  41%|████      | 385/938 [00:27<00:39, 13.85it/s, loss=0.844, v_num=17]
Epoch 0:  41%|████      | 385/938 [00:27<00:39, 13.85it/s, loss=0.85, v_num=17] 
Epoch 0:  41%|████      | 386/938 [00:27<00:39, 13.85it/s, loss=0.86, v_num=17]
Epoch 0:  41%|████▏     | 387/938 [00:27<00:39, 13.86it/s, loss=0.86, v_num=17]
Epoch 0:  41%|████▏     | 387/938 [00:27<00:39, 13.86it/s, loss=0.857, v_num=17]
Epoch 0:  41%|████▏     | 388/938 [00:27<00:39, 13.86it/s, loss=0.859, v_num=17]
Epoch 0:  41%|████▏     | 389/938 [00:28<00:39, 13.86it/s, loss=0.859, v_num=17]
Epoch 0:  41%|████▏     | 389/938 [00:28<00:39, 13.86it/s, loss=0.848, v_num=17]
Epoch 0:  42%|████▏     | 390/938 [00:28<00:39, 13.86it/s, loss=0.86, v_num=17] 
Epoch 0:  42%|████▏     | 391/938 [00:28<00:39, 13.87it/s, loss=0.86, v_num=17]
Epoch 0:  42%|████▏     | 391/938 [00:28<00:39, 13.87it/s, loss=0.862, v_num=17]
Epoch 0:  42%|████▏     | 392/938 [00:28<00:39, 13.87it/s, loss=0.86, v_num=17] 
Epoch 0:  42%|████▏     | 393/938 [00:28<00:39, 13.87it/s, loss=0.86, v_num=17]
Epoch 0:  42%|████▏     | 393/938 [00:28<00:39, 13.86it/s, loss=0.857, v_num=17]
Epoch 0:  42%|████▏     | 394/938 [00:28<00:39, 13.87it/s, loss=0.864, v_num=17]
Epoch 0:  42%|████▏     | 395/938 [00:28<00:39, 13.87it/s, loss=0.864, v_num=17]
Epoch 0:  42%|████▏     | 395/938 [00:28<00:39, 13.87it/s, loss=0.865, v_num=17]
Epoch 0:  42%|████▏     | 396/938 [00:28<00:39, 13.87it/s, loss=0.863, v_num=17]
Epoch 0:  42%|████▏     | 397/938 [00:28<00:38, 13.87it/s, loss=0.863, v_num=17]
Epoch 0:  42%|████▏     | 397/938 [00:28<00:38, 13.87it/s, loss=0.864, v_num=17]
Epoch 0:  42%|████▏     | 398/938 [00:28<00:38, 13.87it/s, loss=0.863, v_num=17]
Epoch 0:  43%|████▎     | 399/938 [00:28<00:38, 13.87it/s, loss=0.863, v_num=17]
Epoch 0:  43%|████▎     | 399/938 [00:28<00:38, 13.87it/s, loss=0.874, v_num=17]
Epoch 0:  43%|████▎     | 400/938 [00:28<00:38, 13.87it/s, loss=0.884, v_num=17]
Epoch 0:  43%|████▎     | 401/938 [00:28<00:38, 13.87it/s, loss=0.884, v_num=17]
Epoch 0:  43%|████▎     | 401/938 [00:28<00:38, 13.87it/s, loss=0.88, v_num=17] 
Epoch 0:  43%|████▎     | 402/938 [00:28<00:38, 13.87it/s, loss=0.882, v_num=17]
Epoch 0:  43%|████▎     | 403/938 [00:29<00:38, 13.87it/s, loss=0.882, v_num=17]
Epoch 0:  43%|████▎     | 403/938 [00:29<00:38, 13.87it/s, loss=0.875, v_num=17]
Epoch 0:  43%|████▎     | 404/938 [00:29<00:38, 13.88it/s, loss=0.874, v_num=17]
Epoch 0:  43%|████▎     | 405/938 [00:29<00:38, 13.88it/s, loss=0.874, v_num=17]
Epoch 0:  43%|████▎     | 405/938 [00:29<00:38, 13.88it/s, loss=0.876, v_num=17]
Epoch 0:  43%|████▎     | 406/938 [00:29<00:38, 13.88it/s, loss=0.869, v_num=17]
Epoch 0:  43%|████▎     | 407/938 [00:29<00:38, 13.88it/s, loss=0.869, v_num=17]
Epoch 0:  43%|████▎     | 407/938 [00:29<00:38, 13.88it/s, loss=0.878, v_num=17]
Epoch 0:  43%|████▎     | 408/938 [00:29<00:38, 13.89it/s, loss=0.873, v_num=17]
Epoch 0:  44%|████▎     | 409/938 [00:29<00:38, 13.89it/s, loss=0.873, v_num=17]
Epoch 0:  44%|████▎     | 409/938 [00:29<00:38, 13.89it/s, loss=0.879, v_num=17]
Epoch 0:  44%|████▎     | 410/938 [00:29<00:37, 13.90it/s, loss=0.861, v_num=17]
Epoch 0:  44%|████▍     | 411/938 [00:29<00:37, 13.90it/s, loss=0.861, v_num=17]
Epoch 0:  44%|████▍     | 411/938 [00:29<00:37, 13.90it/s, loss=0.846, v_num=17]
Epoch 0:  44%|████▍     | 412/938 [00:29<00:37, 13.90it/s, loss=0.855, v_num=17]
Epoch 0:  44%|████▍     | 413/938 [00:29<00:37, 13.90it/s, loss=0.855, v_num=17]
Epoch 0:  44%|████▍     | 413/938 [00:29<00:37, 13.90it/s, loss=0.849, v_num=17]
Epoch 0:  44%|████▍     | 414/938 [00:29<00:37, 13.90it/s, loss=0.85, v_num=17] 
Epoch 0:  44%|████▍     | 415/938 [00:29<00:37, 13.90it/s, loss=0.85, v_num=17]
Epoch 0:  44%|████▍     | 415/938 [00:29<00:37, 13.90it/s, loss=0.845, v_num=17]
Epoch 0:  44%|████▍     | 416/938 [00:29<00:37, 13.90it/s, loss=0.853, v_num=17]
Epoch 0:  44%|████▍     | 417/938 [00:30<00:37, 13.90it/s, loss=0.853, v_num=17]
Epoch 0:  44%|████▍     | 417/938 [00:30<00:37, 13.90it/s, loss=0.859, v_num=17]
Epoch 0:  45%|████▍     | 418/938 [00:30<00:37, 13.90it/s, loss=0.858, v_num=17]
Epoch 0:  45%|████▍     | 419/938 [00:30<00:37, 13.90it/s, loss=0.858, v_num=17]
Epoch 0:  45%|████▍     | 419/938 [00:30<00:37, 13.90it/s, loss=0.85, v_num=17] 
Epoch 0:  45%|████▍     | 420/938 [00:30<00:37, 13.89it/s, loss=0.842, v_num=17]
Epoch 0:  45%|████▍     | 421/938 [00:30<00:37, 13.90it/s, loss=0.842, v_num=17]
Epoch 0:  45%|████▍     | 421/938 [00:30<00:37, 13.90it/s, loss=0.849, v_num=17]
Epoch 0:  45%|████▍     | 422/938 [00:30<00:37, 13.90it/s, loss=0.838, v_num=17]
Epoch 0:  45%|████▌     | 423/938 [00:30<00:37, 13.90it/s, loss=0.838, v_num=17]
Epoch 0:  45%|████▌     | 423/938 [00:30<00:37, 13.90it/s, loss=0.848, v_num=17]
Epoch 0:  45%|████▌     | 424/938 [00:30<00:36, 13.90it/s, loss=0.854, v_num=17]
Epoch 0:  45%|████▌     | 425/938 [00:30<00:36, 13.90it/s, loss=0.854, v_num=17]
Epoch 0:  45%|████▌     | 425/938 [00:30<00:36, 13.90it/s, loss=0.849, v_num=17]
Epoch 0:  45%|████▌     | 426/938 [00:30<00:36, 13.90it/s, loss=0.848, v_num=17]
Epoch 0:  46%|████▌     | 427/938 [00:30<00:36, 13.91it/s, loss=0.848, v_num=17]
Epoch 0:  46%|████▌     | 427/938 [00:30<00:36, 13.91it/s, loss=0.84, v_num=17] 
Epoch 0:  46%|████▌     | 428/938 [00:30<00:36, 13.90it/s, loss=0.855, v_num=17]
Epoch 0:  46%|████▌     | 429/938 [00:30<00:36, 13.89it/s, loss=0.855, v_num=17]
Epoch 0:  46%|████▌     | 429/938 [00:30<00:36, 13.89it/s, loss=0.851, v_num=17]
Epoch 0:  46%|████▌     | 430/938 [00:30<00:36, 13.89it/s, loss=0.857, v_num=17]
Epoch 0:  46%|████▌     | 431/938 [00:31<00:36, 13.89it/s, loss=0.857, v_num=17]
Epoch 0:  46%|████▌     | 431/938 [00:31<00:36, 13.89it/s, loss=0.864, v_num=17]
Epoch 0:  46%|████▌     | 432/938 [00:31<00:36, 13.89it/s, loss=0.857, v_num=17]
Epoch 0:  46%|████▌     | 433/938 [00:31<00:36, 13.89it/s, loss=0.857, v_num=17]
Epoch 0:  46%|████▌     | 433/938 [00:31<00:36, 13.89it/s, loss=0.875, v_num=17]
Epoch 0:  46%|████▋     | 434/938 [00:31<00:36, 13.90it/s, loss=0.871, v_num=17]
Epoch 0:  46%|████▋     | 435/938 [00:31<00:36, 13.89it/s, loss=0.871, v_num=17]
Epoch 0:  46%|████▋     | 435/938 [00:31<00:36, 13.89it/s, loss=0.878, v_num=17]
Epoch 0:  46%|████▋     | 436/938 [00:31<00:36, 13.89it/s, loss=0.869, v_num=17]
Epoch 0:  47%|████▋     | 437/938 [00:31<00:36, 13.89it/s, loss=0.869, v_num=17]
Epoch 0:  47%|████▋     | 437/938 [00:31<00:36, 13.89it/s, loss=0.877, v_num=17]
Epoch 0:  47%|████▋     | 438/938 [00:31<00:35, 13.89it/s, loss=0.88, v_num=17] 
Epoch 0:  47%|████▋     | 439/938 [00:31<00:35, 13.89it/s, loss=0.88, v_num=17]
Epoch 0:  47%|████▋     | 439/938 [00:31<00:35, 13.89it/s, loss=0.881, v_num=17]
Epoch 0:  47%|████▋     | 440/938 [00:31<00:35, 13.89it/s, loss=0.883, v_num=17]
Epoch 0:  47%|████▋     | 441/938 [00:31<00:35, 13.89it/s, loss=0.883, v_num=17]
Epoch 0:  47%|████▋     | 441/938 [00:31<00:35, 13.89it/s, loss=0.878, v_num=17]
Epoch 0:  47%|████▋     | 442/938 [00:31<00:35, 13.89it/s, loss=0.878, v_num=17]
Epoch 0:  47%|████▋     | 443/938 [00:31<00:35, 13.90it/s, loss=0.878, v_num=17]
Epoch 0:  47%|████▋     | 443/938 [00:31<00:35, 13.90it/s, loss=0.878, v_num=17]
Epoch 0:  47%|████▋     | 444/938 [00:31<00:35, 13.90it/s, loss=0.866, v_num=17]
Epoch 0:  47%|████▋     | 445/938 [00:32<00:35, 13.90it/s, loss=0.866, v_num=17]
Epoch 0:  47%|████▋     | 445/938 [00:32<00:35, 13.90it/s, loss=0.87, v_num=17] 
Epoch 0:  48%|████▊     | 446/938 [00:32<00:35, 13.90it/s, loss=0.869, v_num=17]
Epoch 0:  48%|████▊     | 447/938 [00:32<00:35, 13.90it/s, loss=0.869, v_num=17]
Epoch 0:  48%|████▊     | 447/938 [00:32<00:35, 13.90it/s, loss=0.871, v_num=17]
Epoch 0:  48%|████▊     | 448/938 [00:32<00:35, 13.90it/s, loss=0.859, v_num=17]
Epoch 0:  48%|████▊     | 449/938 [00:32<00:35, 13.89it/s, loss=0.859, v_num=17]
Epoch 0:  48%|████▊     | 449/938 [00:32<00:35, 13.89it/s, loss=0.871, v_num=17]
Epoch 0:  48%|████▊     | 450/938 [00:32<00:35, 13.90it/s, loss=0.871, v_num=17]
Epoch 0:  48%|████▊     | 451/938 [00:32<00:35, 13.89it/s, loss=0.871, v_num=17]
Epoch 0:  48%|████▊     | 451/938 [00:32<00:35, 13.89it/s, loss=0.879, v_num=17]
Epoch 0:  48%|████▊     | 452/938 [00:32<00:34, 13.90it/s, loss=0.884, v_num=17]
Epoch 0:  48%|████▊     | 453/938 [00:32<00:34, 13.89it/s, loss=0.884, v_num=17]
Epoch 0:  48%|████▊     | 453/938 [00:32<00:34, 13.89it/s, loss=0.871, v_num=17]
Epoch 0:  48%|████▊     | 454/938 [00:32<00:34, 13.90it/s, loss=0.875, v_num=17]
Epoch 0:  49%|████▊     | 455/938 [00:32<00:34, 13.90it/s, loss=0.875, v_num=17]
Epoch 0:  49%|████▊     | 455/938 [00:32<00:34, 13.90it/s, loss=0.868, v_num=17]
Epoch 0:  49%|████▊     | 456/938 [00:32<00:34, 13.89it/s, loss=0.874, v_num=17]
Epoch 0:  49%|████▊     | 457/938 [00:32<00:34, 13.89it/s, loss=0.874, v_num=17]
Epoch 0:  49%|████▊     | 457/938 [00:32<00:34, 13.89it/s, loss=0.869, v_num=17]
Epoch 0:  49%|████▉     | 458/938 [00:32<00:34, 13.89it/s, loss=0.864, v_num=17]
Epoch 0:  49%|████▉     | 459/938 [00:33<00:34, 13.89it/s, loss=0.864, v_num=17]
Epoch 0:  49%|████▉     | 459/938 [00:33<00:34, 13.89it/s, loss=0.873, v_num=17]
Epoch 0:  49%|████▉     | 460/938 [00:33<00:34, 13.89it/s, loss=0.869, v_num=17]
Epoch 0:  49%|████▉     | 461/938 [00:33<00:34, 13.89it/s, loss=0.869, v_num=17]
Epoch 0:  49%|████▉     | 461/938 [00:33<00:34, 13.89it/s, loss=0.868, v_num=17]
Epoch 0:  49%|████▉     | 462/938 [00:33<00:34, 13.89it/s, loss=0.881, v_num=17]
Epoch 0:  49%|████▉     | 463/938 [00:33<00:34, 13.89it/s, loss=0.881, v_num=17]
Epoch 0:  49%|████▉     | 463/938 [00:33<00:34, 13.89it/s, loss=0.872, v_num=17]
Epoch 0:  49%|████▉     | 464/938 [00:33<00:34, 13.89it/s, loss=0.874, v_num=17]
Epoch 0:  50%|████▉     | 465/938 [00:33<00:34, 13.89it/s, loss=0.874, v_num=17]
Epoch 0:  50%|████▉     | 465/938 [00:33<00:34, 13.89it/s, loss=0.87, v_num=17] 
Epoch 0:  50%|████▉     | 466/938 [00:33<00:33, 13.89it/s, loss=0.87, v_num=17]
Epoch 0:  50%|████▉     | 467/938 [00:33<00:33, 13.89it/s, loss=0.87, v_num=17]
Epoch 0:  50%|████▉     | 467/938 [00:33<00:33, 13.89it/s, loss=0.861, v_num=17]
Epoch 0:  50%|████▉     | 468/938 [00:33<00:33, 13.89it/s, loss=0.86, v_num=17] 
Epoch 0:  50%|█████     | 469/938 [00:33<00:33, 13.90it/s, loss=0.86, v_num=17]
Epoch 0:  50%|█████     | 469/938 [00:33<00:33, 13.90it/s, loss=0.845, v_num=17]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]

Validating:   0%|          | 2/469 [00:00<00:24, 19.42it/s]
Epoch 0:  50%|█████     | 472/938 [00:33<00:33, 13.95it/s, loss=0.845, v_num=17]

Validating:   1%|          | 4/469 [00:00<00:23, 19.47it/s]
Epoch 0:  51%|█████     | 475/938 [00:33<00:33, 13.98it/s, loss=0.845, v_num=17]

Validating:   1%|▏         | 7/469 [00:00<00:19, 23.36it/s]
Epoch 0:  51%|█████     | 478/938 [00:34<00:32, 14.02it/s, loss=0.845, v_num=17]

Validating:   2%|▏         | 10/469 [00:00<00:18, 24.26it/s]
Epoch 0:  51%|█████▏    | 481/938 [00:34<00:32, 14.06it/s, loss=0.845, v_num=17]

Validating:   3%|▎         | 13/469 [00:00<00:19, 23.62it/s]
Epoch 0:  52%|█████▏    | 484/938 [00:34<00:32, 14.09it/s, loss=0.845, v_num=17]

Validating:   3%|▎         | 16/469 [00:00<00:20, 22.06it/s]
Epoch 0:  52%|█████▏    | 487/938 [00:34<00:31, 14.12it/s, loss=0.845, v_num=17]

Validating:   4%|▍         | 19/469 [00:00<00:19, 22.80it/s]
Epoch 0:  52%|█████▏    | 490/938 [00:34<00:31, 14.15it/s, loss=0.845, v_num=17]

Validating:   5%|▍         | 22/469 [00:00<00:19, 23.27it/s]
Epoch 0:  53%|█████▎    | 493/938 [00:34<00:31, 14.19it/s, loss=0.845, v_num=17]

Validating:   5%|▌         | 25/469 [00:01<00:19, 23.15it/s]
Epoch 0:  53%|█████▎    | 496/938 [00:34<00:31, 14.22it/s, loss=0.845, v_num=17]

Validating:   6%|▌         | 28/469 [00:01<00:19, 22.13it/s]
Epoch 0:  53%|█████▎    | 499/938 [00:35<00:30, 14.25it/s, loss=0.845, v_num=17]

Validating:   7%|▋         | 31/469 [00:01<00:19, 22.24it/s]
Epoch 0:  54%|█████▎    | 502/938 [00:35<00:30, 14.28it/s, loss=0.845, v_num=17]

Validating:   7%|▋         | 34/469 [00:01<00:19, 22.88it/s]
Epoch 0:  54%|█████▍    | 505/938 [00:35<00:30, 14.32it/s, loss=0.845, v_num=17]

Validating:   8%|▊         | 37/469 [00:01<00:18, 23.19it/s]
Epoch 0:  54%|█████▍    | 508/938 [00:35<00:29, 14.35it/s, loss=0.845, v_num=17]

Validating:   9%|▊         | 40/469 [00:01<00:18, 23.51it/s]
Epoch 0:  54%|█████▍    | 511/938 [00:35<00:29, 14.38it/s, loss=0.845, v_num=17]

Validating:   9%|▉         | 43/469 [00:01<00:18, 23.25it/s]
Epoch 0:  55%|█████▍    | 514/938 [00:35<00:29, 14.41it/s, loss=0.845, v_num=17]

Validating:  10%|▉         | 46/469 [00:02<00:18, 23.02it/s]
Epoch 0:  55%|█████▌    | 517/938 [00:35<00:29, 14.45it/s, loss=0.845, v_num=17]

Validating:  10%|█         | 49/469 [00:02<00:17, 23.60it/s]
Epoch 0:  55%|█████▌    | 520/938 [00:35<00:28, 14.48it/s, loss=0.845, v_num=17]

Validating:  11%|█         | 52/469 [00:02<00:17, 24.48it/s]
Epoch 0:  56%|█████▌    | 523/938 [00:36<00:28, 14.52it/s, loss=0.845, v_num=17]

Validating:  12%|█▏        | 55/469 [00:02<00:16, 25.42it/s]
Epoch 0:  56%|█████▌    | 526/938 [00:36<00:28, 14.56it/s, loss=0.845, v_num=17]

Validating:  12%|█▏        | 58/469 [00:02<00:16, 25.56it/s]
Epoch 0:  56%|█████▋    | 529/938 [00:36<00:28, 14.58it/s, loss=0.845, v_num=17]

Validating:  13%|█▎        | 61/469 [00:02<00:17, 23.56it/s]
Epoch 0:  57%|█████▋    | 532/938 [00:36<00:27, 14.62it/s, loss=0.845, v_num=17]

Validating:  14%|█▎        | 64/469 [00:02<00:16, 24.99it/s]
Epoch 0:  57%|█████▋    | 535/938 [00:36<00:27, 14.65it/s, loss=0.845, v_num=17]

Validating:  14%|█▍        | 67/469 [00:02<00:16, 24.56it/s]
Epoch 0:  57%|█████▋    | 538/938 [00:36<00:27, 14.69it/s, loss=0.845, v_num=17]

Validating:  15%|█▍        | 70/469 [00:02<00:15, 24.99it/s]
Epoch 0:  58%|█████▊    | 541/938 [00:36<00:26, 14.72it/s, loss=0.845, v_num=17]

Validating:  16%|█▌        | 73/469 [00:03<00:15, 25.22it/s]
Epoch 0:  58%|█████▊    | 544/938 [00:36<00:26, 14.76it/s, loss=0.845, v_num=17]

Validating:  16%|█▌        | 76/469 [00:03<00:15, 24.63it/s]
Epoch 0:  58%|█████▊    | 547/938 [00:36<00:26, 14.79it/s, loss=0.845, v_num=17]

Validating:  17%|█▋        | 79/469 [00:03<00:15, 24.55it/s]
Epoch 0:  59%|█████▊    | 550/938 [00:37<00:26, 14.82it/s, loss=0.845, v_num=17]

Validating:  17%|█▋        | 82/469 [00:03<00:15, 24.60it/s]
Epoch 0:  59%|█████▉    | 553/938 [00:37<00:25, 14.85it/s, loss=0.845, v_num=17]

Validating:  18%|█▊        | 85/469 [00:03<00:15, 24.89it/s]
Epoch 0:  59%|█████▉    | 556/938 [00:37<00:25, 14.89it/s, loss=0.845, v_num=17]

Validating:  19%|█▉        | 88/469 [00:03<00:15, 25.24it/s]
Epoch 0:  60%|█████▉    | 559/938 [00:37<00:25, 14.92it/s, loss=0.845, v_num=17]

Validating:  19%|█▉        | 91/469 [00:03<00:14, 25.39it/s]
Epoch 0:  60%|█████▉    | 562/938 [00:37<00:25, 14.96it/s, loss=0.845, v_num=17]

Validating:  20%|██        | 94/469 [00:03<00:14, 25.23it/s]
Epoch 0:  60%|██████    | 565/938 [00:37<00:24, 14.99it/s, loss=0.845, v_num=17]

Validating:  21%|██        | 97/469 [00:04<00:14, 25.62it/s]
Epoch 0:  61%|██████    | 568/938 [00:37<00:24, 15.02it/s, loss=0.845, v_num=17]

Validating:  21%|██▏       | 100/469 [00:04<00:14, 24.97it/s]
Epoch 0:  61%|██████    | 571/938 [00:37<00:24, 15.05it/s, loss=0.845, v_num=17]

Validating:  22%|██▏       | 103/469 [00:04<00:14, 24.77it/s]
Epoch 0:  61%|██████    | 574/938 [00:38<00:24, 15.08it/s, loss=0.845, v_num=17]

Validating:  23%|██▎       | 106/469 [00:04<00:14, 24.66it/s]
Epoch 0:  62%|██████▏   | 577/938 [00:38<00:23, 15.11it/s, loss=0.845, v_num=17]

Validating:  23%|██▎       | 109/469 [00:04<00:15, 23.80it/s]
Epoch 0:  62%|██████▏   | 580/938 [00:38<00:23, 15.14it/s, loss=0.845, v_num=17]

Validating:  24%|██▍       | 112/469 [00:04<00:14, 24.01it/s]
Epoch 0:  62%|██████▏   | 583/938 [00:38<00:23, 15.17it/s, loss=0.845, v_num=17]

Validating:  25%|██▍       | 115/469 [00:04<00:14, 24.08it/s]
Epoch 0:  62%|██████▏   | 586/938 [00:38<00:23, 15.19it/s, loss=0.845, v_num=17]

Validating:  25%|██▌       | 118/469 [00:04<00:14, 24.56it/s]
Epoch 0:  63%|██████▎   | 589/938 [00:38<00:22, 15.22it/s, loss=0.845, v_num=17]

Validating:  26%|██▌       | 121/469 [00:05<00:14, 24.79it/s]
Epoch 0:  63%|██████▎   | 592/938 [00:38<00:22, 15.26it/s, loss=0.845, v_num=17]

Validating:  26%|██▋       | 124/469 [00:05<00:13, 24.71it/s]
Epoch 0:  63%|██████▎   | 595/938 [00:38<00:22, 15.29it/s, loss=0.845, v_num=17]

Validating:  27%|██▋       | 127/469 [00:05<00:13, 24.93it/s]
Epoch 0:  64%|██████▍   | 598/938 [00:39<00:22, 15.32it/s, loss=0.845, v_num=17]

Validating:  28%|██▊       | 130/469 [00:05<00:13, 25.64it/s]
Epoch 0:  64%|██████▍   | 601/938 [00:39<00:21, 15.35it/s, loss=0.845, v_num=17]

Validating:  28%|██▊       | 133/469 [00:05<00:13, 25.78it/s]
Epoch 0:  64%|██████▍   | 604/938 [00:39<00:21, 15.38it/s, loss=0.845, v_num=17]

Validating:  29%|██▉       | 136/469 [00:05<00:12, 25.73it/s]
Epoch 0:  65%|██████▍   | 607/938 [00:39<00:21, 15.41it/s, loss=0.845, v_num=17]

Validating:  30%|██▉       | 139/469 [00:05<00:13, 24.72it/s]
Epoch 0:  65%|██████▌   | 610/938 [00:39<00:21, 15.44it/s, loss=0.845, v_num=17]

Validating:  30%|███       | 142/469 [00:05<00:12, 25.38it/s]
Epoch 0:  65%|██████▌   | 613/938 [00:39<00:21, 15.47it/s, loss=0.845, v_num=17]

Validating:  31%|███       | 145/469 [00:05<00:12, 25.78it/s]
Epoch 0:  66%|██████▌   | 616/938 [00:39<00:20, 15.50it/s, loss=0.845, v_num=17]

Validating:  32%|███▏      | 148/469 [00:06<00:12, 25.59it/s]
Epoch 0:  66%|██████▌   | 619/938 [00:39<00:20, 15.53it/s, loss=0.845, v_num=17]

Validating:  32%|███▏      | 151/469 [00:06<00:13, 24.11it/s]
Epoch 0:  66%|██████▋   | 622/938 [00:39<00:20, 15.55it/s, loss=0.845, v_num=17]

Validating:  33%|███▎      | 154/469 [00:06<00:12, 24.27it/s]
Epoch 0:  67%|██████▋   | 625/938 [00:40<00:20, 15.58it/s, loss=0.845, v_num=17]

Validating:  33%|███▎      | 157/469 [00:06<00:12, 24.48it/s]
Epoch 0:  67%|██████▋   | 628/938 [00:40<00:19, 15.61it/s, loss=0.845, v_num=17]

Validating:  34%|███▍      | 160/469 [00:06<00:12, 24.91it/s]
Epoch 0:  67%|██████▋   | 631/938 [00:40<00:19, 15.63it/s, loss=0.845, v_num=17]

Validating:  35%|███▍      | 163/469 [00:06<00:12, 24.52it/s]
Epoch 0:  68%|██████▊   | 634/938 [00:40<00:19, 15.66it/s, loss=0.845, v_num=17]

Validating:  35%|███▌      | 166/469 [00:06<00:12, 24.25it/s]
Epoch 0:  68%|██████▊   | 637/938 [00:40<00:19, 15.69it/s, loss=0.845, v_num=17]

Validating:  36%|███▌      | 169/469 [00:06<00:12, 24.11it/s]
Epoch 0:  68%|██████▊   | 640/938 [00:40<00:18, 15.71it/s, loss=0.845, v_num=17]

Validating:  37%|███▋      | 172/469 [00:07<00:12, 24.41it/s]
Epoch 0:  69%|██████▊   | 643/938 [00:40<00:18, 15.74it/s, loss=0.845, v_num=17]

Validating:  37%|███▋      | 175/469 [00:07<00:12, 24.12it/s]
Epoch 0:  69%|██████▉   | 646/938 [00:40<00:18, 15.76it/s, loss=0.845, v_num=17]

Validating:  38%|███▊      | 178/469 [00:07<00:11, 24.95it/s]
Epoch 0:  69%|██████▉   | 649/938 [00:41<00:18, 15.79it/s, loss=0.845, v_num=17]

Validating:  39%|███▊      | 181/469 [00:07<00:11, 25.32it/s]
Epoch 0:  70%|██████▉   | 652/938 [00:41<00:18, 15.82it/s, loss=0.845, v_num=17]

Validating:  39%|███▉      | 184/469 [00:07<00:11, 25.19it/s]
Epoch 0:  70%|██████▉   | 655/938 [00:41<00:17, 15.85it/s, loss=0.845, v_num=17]

Validating:  40%|███▉      | 187/469 [00:07<00:11, 24.05it/s]
Epoch 0:  70%|███████   | 658/938 [00:41<00:17, 15.87it/s, loss=0.845, v_num=17]

Validating:  41%|████      | 190/469 [00:07<00:11, 24.36it/s]
Epoch 0:  70%|███████   | 661/938 [00:41<00:17, 15.89it/s, loss=0.845, v_num=17]

Validating:  41%|████      | 193/469 [00:07<00:11, 23.81it/s]
Epoch 0:  71%|███████   | 664/938 [00:41<00:17, 15.92it/s, loss=0.845, v_num=17]

Validating:  42%|████▏     | 196/469 [00:08<00:11, 24.29it/s]
Epoch 0:  71%|███████   | 667/938 [00:41<00:16, 15.94it/s, loss=0.845, v_num=17]

Validating:  42%|████▏     | 199/469 [00:08<00:11, 24.54it/s]
Epoch 0:  71%|███████▏  | 670/938 [00:41<00:16, 15.97it/s, loss=0.845, v_num=17]

Validating:  43%|████▎     | 202/469 [00:08<00:10, 24.59it/s]
Epoch 0:  72%|███████▏  | 673/938 [00:42<00:16, 15.99it/s, loss=0.845, v_num=17]

Validating:  44%|████▎     | 205/469 [00:08<00:10, 25.04it/s]
Epoch 0:  72%|███████▏  | 676/938 [00:42<00:16, 16.02it/s, loss=0.845, v_num=17]

Validating:  44%|████▍     | 208/469 [00:08<00:10, 25.82it/s]
Epoch 0:  72%|███████▏  | 679/938 [00:42<00:16, 16.05it/s, loss=0.845, v_num=17]

Validating:  45%|████▍     | 211/469 [00:08<00:10, 24.65it/s]
Epoch 0:  73%|███████▎  | 682/938 [00:42<00:15, 16.07it/s, loss=0.845, v_num=17]

Validating:  46%|████▌     | 214/469 [00:08<00:10, 23.95it/s]
Epoch 0:  73%|███████▎  | 685/938 [00:42<00:15, 16.09it/s, loss=0.845, v_num=17]

Validating:  46%|████▋     | 217/469 [00:08<00:10, 24.22it/s]
Epoch 0:  73%|███████▎  | 688/938 [00:42<00:15, 16.11it/s, loss=0.845, v_num=17]

Validating:  47%|████▋     | 220/469 [00:09<00:10, 24.41it/s]
Epoch 0:  74%|███████▎  | 691/938 [00:42<00:15, 16.14it/s, loss=0.845, v_num=17]

Validating:  48%|████▊     | 223/469 [00:09<00:10, 24.28it/s]
Epoch 0:  74%|███████▍  | 694/938 [00:42<00:15, 16.16it/s, loss=0.845, v_num=17]

Validating:  48%|████▊     | 226/469 [00:09<00:10, 23.52it/s]
Epoch 0:  74%|███████▍  | 697/938 [00:43<00:14, 16.18it/s, loss=0.845, v_num=17]

Validating:  49%|████▉     | 229/469 [00:09<00:09, 24.05it/s]
Epoch 0:  75%|███████▍  | 700/938 [00:43<00:14, 16.21it/s, loss=0.845, v_num=17]

Validating:  49%|████▉     | 232/469 [00:09<00:09, 24.15it/s]
Epoch 0:  75%|███████▍  | 703/938 [00:43<00:14, 16.23it/s, loss=0.845, v_num=17]

Validating:  50%|█████     | 235/469 [00:09<00:10, 23.24it/s]
Epoch 0:  75%|███████▌  | 706/938 [00:43<00:14, 16.24it/s, loss=0.845, v_num=17]

Validating:  51%|█████     | 238/469 [00:09<00:10, 22.64it/s]
Epoch 0:  76%|███████▌  | 709/938 [00:43<00:14, 16.27it/s, loss=0.845, v_num=17]

Validating:  51%|█████▏    | 241/469 [00:09<00:09, 23.67it/s]
Epoch 0:  76%|███████▌  | 712/938 [00:43<00:13, 16.29it/s, loss=0.845, v_num=17]

Validating:  52%|█████▏    | 244/469 [00:10<00:09, 23.42it/s]
Epoch 0:  76%|███████▌  | 715/938 [00:43<00:13, 16.31it/s, loss=0.845, v_num=17]

Validating:  53%|█████▎    | 247/469 [00:10<00:09, 24.39it/s]
Epoch 0:  77%|███████▋  | 718/938 [00:43<00:13, 16.34it/s, loss=0.845, v_num=17]

Validating:  53%|█████▎    | 250/469 [00:10<00:08, 24.96it/s]
Epoch 0:  77%|███████▋  | 721/938 [00:44<00:13, 16.36it/s, loss=0.845, v_num=17]

Validating:  54%|█████▍    | 253/469 [00:10<00:09, 23.75it/s]
Epoch 0:  77%|███████▋  | 724/938 [00:44<00:13, 16.38it/s, loss=0.845, v_num=17]

Validating:  55%|█████▍    | 256/469 [00:10<00:09, 23.00it/s]
Epoch 0:  78%|███████▊  | 727/938 [00:44<00:12, 16.40it/s, loss=0.845, v_num=17]

Validating:  55%|█████▌    | 259/469 [00:10<00:09, 22.86it/s]
Epoch 0:  78%|███████▊  | 730/938 [00:44<00:12, 16.41it/s, loss=0.845, v_num=17]

Validating:  56%|█████▌    | 262/469 [00:10<00:08, 24.10it/s]
Epoch 0:  78%|███████▊  | 733/938 [00:44<00:12, 16.44it/s, loss=0.845, v_num=17]

Validating:  57%|█████▋    | 265/469 [00:10<00:08, 24.08it/s]
Epoch 0:  78%|███████▊  | 736/938 [00:44<00:12, 16.46it/s, loss=0.845, v_num=17]

Validating:  57%|█████▋    | 268/469 [00:11<00:08, 23.87it/s]
Epoch 0:  79%|███████▉  | 739/938 [00:44<00:12, 16.48it/s, loss=0.845, v_num=17]

Validating:  58%|█████▊    | 271/469 [00:11<00:08, 22.88it/s]
Epoch 0:  79%|███████▉  | 742/938 [00:44<00:11, 16.49it/s, loss=0.845, v_num=17]

Validating:  58%|█████▊    | 274/469 [00:11<00:08, 23.28it/s]
Epoch 0:  79%|███████▉  | 745/938 [00:45<00:11, 16.52it/s, loss=0.845, v_num=17]

Validating:  59%|█████▉    | 277/469 [00:11<00:08, 22.44it/s]
Epoch 0:  80%|███████▉  | 748/938 [00:45<00:11, 16.53it/s, loss=0.845, v_num=17]

Validating:  60%|█████▉    | 280/469 [00:11<00:08, 23.04it/s]
Epoch 0:  80%|████████  | 751/938 [00:45<00:11, 16.55it/s, loss=0.845, v_num=17]

Validating:  60%|██████    | 283/469 [00:11<00:07, 23.28it/s]
Epoch 0:  80%|████████  | 754/938 [00:45<00:11, 16.57it/s, loss=0.845, v_num=17]

Validating:  61%|██████    | 286/469 [00:11<00:07, 24.36it/s]
Epoch 0:  81%|████████  | 757/938 [00:45<00:10, 16.60it/s, loss=0.845, v_num=17]

Validating:  62%|██████▏   | 289/469 [00:11<00:07, 24.72it/s]
Epoch 0:  81%|████████  | 760/938 [00:45<00:10, 16.62it/s, loss=0.845, v_num=17]

Validating:  62%|██████▏   | 292/469 [00:12<00:07, 24.31it/s]
Epoch 0:  81%|████████▏ | 763/938 [00:45<00:10, 16.64it/s, loss=0.845, v_num=17]

Validating:  63%|██████▎   | 295/469 [00:12<00:07, 24.63it/s]
Epoch 0:  82%|████████▏ | 766/938 [00:45<00:10, 16.66it/s, loss=0.845, v_num=17]

Validating:  64%|██████▎   | 298/469 [00:12<00:07, 24.20it/s]
Epoch 0:  82%|████████▏ | 769/938 [00:46<00:10, 16.68it/s, loss=0.845, v_num=17]

Validating:  64%|██████▍   | 301/469 [00:12<00:07, 23.99it/s]
Epoch 0:  82%|████████▏ | 772/938 [00:46<00:09, 16.70it/s, loss=0.845, v_num=17]

Validating:  65%|██████▍   | 304/469 [00:12<00:06, 24.71it/s]
Epoch 0:  83%|████████▎ | 775/938 [00:46<00:09, 16.72it/s, loss=0.845, v_num=17]

Validating:  65%|██████▌   | 307/469 [00:12<00:06, 25.38it/s]
Epoch 0:  83%|████████▎ | 778/938 [00:46<00:09, 16.75it/s, loss=0.845, v_num=17]

Validating:  66%|██████▌   | 310/469 [00:12<00:06, 25.32it/s]
Epoch 0:  83%|████████▎ | 781/938 [00:46<00:09, 16.77it/s, loss=0.845, v_num=17]

Validating:  67%|██████▋   | 313/469 [00:12<00:06, 24.50it/s]
Epoch 0:  84%|████████▎ | 784/938 [00:46<00:09, 16.79it/s, loss=0.845, v_num=17]

Validating:  67%|██████▋   | 316/469 [00:13<00:06, 23.51it/s]
Epoch 0:  84%|████████▍ | 787/938 [00:46<00:08, 16.80it/s, loss=0.845, v_num=17]

Validating:  68%|██████▊   | 319/469 [00:13<00:06, 23.97it/s]
Epoch 0:  84%|████████▍ | 790/938 [00:46<00:08, 16.82it/s, loss=0.845, v_num=17]

Validating:  69%|██████▊   | 322/469 [00:13<00:06, 24.12it/s]
Epoch 0:  85%|████████▍ | 793/938 [00:47<00:08, 16.84it/s, loss=0.845, v_num=17]

Validating:  69%|██████▉   | 325/469 [00:13<00:05, 25.31it/s]
Epoch 0:  85%|████████▍ | 796/938 [00:47<00:08, 16.87it/s, loss=0.845, v_num=17]

Validating:  70%|██████▉   | 328/469 [00:13<00:05, 23.74it/s]
Epoch 0:  85%|████████▌ | 799/938 [00:47<00:08, 16.88it/s, loss=0.845, v_num=17]

Validating:  71%|███████   | 331/469 [00:13<00:05, 23.27it/s]
Epoch 0:  86%|████████▌ | 802/938 [00:47<00:08, 16.89it/s, loss=0.845, v_num=17]

Validating:  71%|███████   | 334/469 [00:13<00:05, 23.19it/s]
Epoch 0:  86%|████████▌ | 805/938 [00:47<00:07, 16.91it/s, loss=0.845, v_num=17]

Validating:  72%|███████▏  | 337/469 [00:13<00:05, 23.80it/s]
Epoch 0:  86%|████████▌ | 808/938 [00:47<00:07, 16.94it/s, loss=0.845, v_num=17]

Validating:  72%|███████▏  | 340/469 [00:14<00:05, 24.90it/s]
Epoch 0:  86%|████████▋ | 811/938 [00:47<00:07, 16.96it/s, loss=0.845, v_num=17]

Validating:  73%|███████▎  | 343/469 [00:14<00:04, 25.48it/s]
Epoch 0:  87%|████████▋ | 814/938 [00:47<00:07, 16.98it/s, loss=0.845, v_num=17]

Validating:  74%|███████▍  | 346/469 [00:14<00:04, 25.11it/s]
Epoch 0:  87%|████████▋ | 817/938 [00:48<00:07, 17.00it/s, loss=0.845, v_num=17]

Validating:  74%|███████▍  | 349/469 [00:14<00:05, 23.91it/s]
Epoch 0:  87%|████████▋ | 820/938 [00:48<00:06, 17.01it/s, loss=0.845, v_num=17]

Validating:  75%|███████▌  | 352/469 [00:14<00:04, 24.42it/s]
Epoch 0:  88%|████████▊ | 823/938 [00:48<00:06, 17.04it/s, loss=0.845, v_num=17]

Validating:  76%|███████▌  | 355/469 [00:14<00:04, 23.21it/s]
Epoch 0:  88%|████████▊ | 826/938 [00:48<00:06, 17.05it/s, loss=0.845, v_num=17]

Validating:  76%|███████▋  | 358/469 [00:14<00:04, 23.74it/s]
Epoch 0:  88%|████████▊ | 829/938 [00:48<00:06, 17.06it/s, loss=0.845, v_num=17]

Validating:  77%|███████▋  | 361/469 [00:14<00:04, 24.39it/s]
Epoch 0:  89%|████████▊ | 832/938 [00:48<00:06, 17.08it/s, loss=0.845, v_num=17]

Validating:  78%|███████▊  | 364/469 [00:15<00:04, 25.03it/s]
Epoch 0:  89%|████████▉ | 835/938 [00:48<00:06, 17.11it/s, loss=0.845, v_num=17]

Validating:  78%|███████▊  | 367/469 [00:15<00:03, 25.76it/s]
Epoch 0:  89%|████████▉ | 838/938 [00:48<00:05, 17.13it/s, loss=0.845, v_num=17]

Validating:  79%|███████▉  | 370/469 [00:15<00:03, 25.52it/s]
Epoch 0:  90%|████████▉ | 841/938 [00:49<00:05, 17.15it/s, loss=0.845, v_num=17]

Validating:  80%|███████▉  | 373/469 [00:15<00:03, 25.48it/s]
Epoch 0:  90%|████████▉ | 844/938 [00:49<00:05, 17.17it/s, loss=0.845, v_num=17]

Validating:  80%|████████  | 376/469 [00:15<00:03, 25.08it/s]
Epoch 0:  90%|█████████ | 847/938 [00:49<00:05, 17.19it/s, loss=0.845, v_num=17]

Validating:  81%|████████  | 379/469 [00:15<00:03, 25.79it/s]
Epoch 0:  91%|█████████ | 850/938 [00:49<00:05, 17.21it/s, loss=0.845, v_num=17]

Validating:  81%|████████▏ | 382/469 [00:15<00:03, 25.52it/s]
Epoch 0:  91%|█████████ | 853/938 [00:49<00:04, 17.23it/s, loss=0.845, v_num=17]

Validating:  82%|████████▏ | 385/469 [00:15<00:03, 25.39it/s]
Epoch 0:  91%|█████████▏| 856/938 [00:49<00:04, 17.25it/s, loss=0.845, v_num=17]

Validating:  83%|████████▎ | 388/469 [00:15<00:03, 24.52it/s]
Epoch 0:  92%|█████████▏| 859/938 [00:49<00:04, 17.26it/s, loss=0.845, v_num=17]

Validating:  83%|████████▎ | 391/469 [00:16<00:03, 24.79it/s]
Epoch 0:  92%|█████████▏| 862/938 [00:49<00:04, 17.28it/s, loss=0.845, v_num=17]

Validating:  84%|████████▍ | 394/469 [00:16<00:03, 24.01it/s]
Epoch 0:  92%|█████████▏| 865/938 [00:50<00:04, 17.30it/s, loss=0.845, v_num=17]

Validating:  85%|████████▍ | 397/469 [00:16<00:02, 25.18it/s]
Epoch 0:  93%|█████████▎| 868/938 [00:50<00:04, 17.32it/s, loss=0.845, v_num=17]

Validating:  85%|████████▌ | 400/469 [00:16<00:02, 24.43it/s]
Epoch 0:  93%|█████████▎| 871/938 [00:50<00:03, 17.33it/s, loss=0.845, v_num=17]

Validating:  86%|████████▌ | 403/469 [00:16<00:02, 23.84it/s]
Epoch 0:  93%|█████████▎| 874/938 [00:50<00:03, 17.35it/s, loss=0.845, v_num=17]

Validating:  87%|████████▋ | 406/469 [00:16<00:02, 24.08it/s]
Epoch 0:  93%|█████████▎| 877/938 [00:50<00:03, 17.36it/s, loss=0.845, v_num=17]

Validating:  87%|████████▋ | 409/469 [00:16<00:02, 24.43it/s]
Epoch 0:  94%|█████████▍| 880/938 [00:50<00:03, 17.38it/s, loss=0.845, v_num=17]

Validating:  88%|████████▊ | 412/469 [00:16<00:02, 23.78it/s]
Epoch 0:  94%|█████████▍| 883/938 [00:50<00:03, 17.40it/s, loss=0.845, v_num=17]

Validating:  88%|████████▊ | 415/469 [00:17<00:02, 24.22it/s]
Epoch 0:  94%|█████████▍| 886/938 [00:50<00:02, 17.42it/s, loss=0.845, v_num=17]

Validating:  89%|████████▉ | 418/469 [00:17<00:02, 24.43it/s]
Epoch 0:  95%|█████████▍| 889/938 [00:50<00:02, 17.43it/s, loss=0.845, v_num=17]

Validating:  90%|████████▉ | 421/469 [00:17<00:01, 24.97it/s]
Epoch 0:  95%|█████████▌| 892/938 [00:51<00:02, 17.45it/s, loss=0.845, v_num=17]

Validating:  90%|█████████ | 424/469 [00:17<00:01, 24.32it/s]
Epoch 0:  95%|█████████▌| 895/938 [00:51<00:02, 17.47it/s, loss=0.845, v_num=17]

Validating:  91%|█████████ | 427/469 [00:17<00:01, 24.45it/s]
Epoch 0:  96%|█████████▌| 898/938 [00:51<00:02, 17.49it/s, loss=0.845, v_num=17]

Validating:  92%|█████████▏| 430/469 [00:17<00:01, 24.59it/s]
Epoch 0:  96%|█████████▌| 901/938 [00:51<00:02, 17.50it/s, loss=0.845, v_num=17]

Validating:  92%|█████████▏| 433/469 [00:17<00:01, 24.29it/s]
Epoch 0:  96%|█████████▋| 904/938 [00:51<00:01, 17.52it/s, loss=0.845, v_num=17]

Validating:  93%|█████████▎| 436/469 [00:17<00:01, 24.47it/s]
Epoch 0:  97%|█████████▋| 907/938 [00:51<00:01, 17.53it/s, loss=0.845, v_num=17]

Validating:  94%|█████████▎| 439/469 [00:18<00:01, 23.95it/s]
Epoch 0:  97%|█████████▋| 910/938 [00:51<00:01, 17.55it/s, loss=0.845, v_num=17]

Validating:  94%|█████████▍| 442/469 [00:18<00:01, 24.58it/s]
Epoch 0:  97%|█████████▋| 913/938 [00:51<00:01, 17.57it/s, loss=0.845, v_num=17]

Validating:  95%|█████████▍| 445/469 [00:18<00:00, 25.33it/s]
Epoch 0:  98%|█████████▊| 916/938 [00:52<00:01, 17.59it/s, loss=0.845, v_num=17]

Validating:  96%|█████████▌| 448/469 [00:18<00:00, 25.76it/s]
Epoch 0:  98%|█████████▊| 919/938 [00:52<00:01, 17.61it/s, loss=0.845, v_num=17]

Validating:  96%|█████████▌| 451/469 [00:18<00:00, 25.30it/s]
Epoch 0:  98%|█████████▊| 922/938 [00:52<00:00, 17.62it/s, loss=0.845, v_num=17]

Validating:  97%|█████████▋| 454/469 [00:18<00:00, 25.92it/s]
Epoch 0:  99%|█████████▊| 925/938 [00:52<00:00, 17.65it/s, loss=0.845, v_num=17]

Validating:  97%|█████████▋| 457/469 [00:18<00:00, 26.85it/s]
Epoch 0:  99%|█████████▉| 928/938 [00:52<00:00, 17.67it/s, loss=0.845, v_num=17]

Validating:  98%|█████████▊| 460/469 [00:18<00:00, 26.52it/s]
Epoch 0:  99%|█████████▉| 931/938 [00:52<00:00, 17.69it/s, loss=0.845, v_num=17]

Validating:  99%|█████████▊| 463/469 [00:18<00:00, 26.72it/s]
Epoch 0: 100%|█████████▉| 934/938 [00:52<00:00, 17.70it/s, loss=0.845, v_num=17]

Validating:  99%|█████████▉| 466/469 [00:19<00:00, 27.03it/s]
Epoch 0: 100%|█████████▉| 937/938 [00:52<00:00, 17.71it/s, loss=0.845, v_num=17]

Validating: 100%|██████████| 469/469 [00:19<00:00, 25.60it/s]
Epoch 0: 100%|██████████| 938/938 [00:52<00:00, 17.71it/s, loss=0.845, v_num=17, val_rmse=0.649]

                                                             
Epoch 0: 100%|██████████| 938/938 [00:52<00:00, 17.70it/s, loss=0.845, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 0:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.845, v_num=17, val_rmse=0.649, train_rmse=1.250]          
Epoch 1:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.845, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   0%|          | 1/938 [00:00<01:30, 10.34it/s, loss=0.842, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   0%|          | 2/938 [00:00<01:13, 12.78it/s, loss=0.828, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   0%|          | 3/938 [00:00<01:09, 13.49it/s, loss=0.828, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   0%|          | 3/938 [00:00<01:09, 13.45it/s, loss=0.828, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   0%|          | 4/938 [00:00<01:08, 13.67it/s, loss=0.822, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   1%|          | 5/938 [00:00<01:05, 14.15it/s, loss=0.818, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   1%|          | 6/938 [00:00<01:07, 13.91it/s, loss=0.818, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   1%|          | 6/938 [00:00<01:07, 13.89it/s, loss=0.831, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   1%|          | 7/938 [00:00<01:05, 14.25it/s, loss=0.823, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   1%|          | 8/938 [00:00<01:04, 14.37it/s, loss=0.826, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   1%|          | 9/938 [00:00<01:05, 14.25it/s, loss=0.826, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   1%|          | 9/938 [00:00<01:05, 14.23it/s, loss=0.827, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   1%|          | 10/938 [00:00<01:06, 13.91it/s, loss=0.818, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   1%|          | 11/938 [00:00<01:05, 14.17it/s, loss=0.809, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   1%|▏         | 12/938 [00:00<01:06, 13.95it/s, loss=0.809, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   1%|▏         | 12/938 [00:00<01:06, 13.94it/s, loss=0.807, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   1%|▏         | 13/938 [00:00<01:07, 13.78it/s, loss=0.809, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   1%|▏         | 14/938 [00:01<01:06, 13.86it/s, loss=0.805, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   2%|▏         | 15/938 [00:01<01:06, 13.83it/s, loss=0.805, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   2%|▏         | 15/938 [00:01<01:06, 13.82it/s, loss=0.802, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   2%|▏         | 16/938 [00:01<01:07, 13.66it/s, loss=0.803, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   2%|▏         | 17/938 [00:01<01:06, 13.86it/s, loss=0.806, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   2%|▏         | 18/938 [00:01<01:06, 13.74it/s, loss=0.806, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   2%|▏         | 18/938 [00:01<01:06, 13.73it/s, loss=0.812, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   2%|▏         | 19/938 [00:01<01:07, 13.60it/s, loss=0.824, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   2%|▏         | 20/938 [00:01<01:07, 13.61it/s, loss=0.832, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   2%|▏         | 21/938 [00:01<01:07, 13.64it/s, loss=0.832, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   2%|▏         | 21/938 [00:01<01:07, 13.63it/s, loss=0.833, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   2%|▏         | 22/938 [00:01<01:07, 13.61it/s, loss=0.843, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   2%|▏         | 23/938 [00:01<01:06, 13.78it/s, loss=0.841, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   3%|▎         | 24/938 [00:01<01:06, 13.73it/s, loss=0.841, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   3%|▎         | 24/938 [00:01<01:06, 13.72it/s, loss=0.846, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   3%|▎         | 25/938 [00:01<01:06, 13.70it/s, loss=0.853, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   3%|▎         | 26/938 [00:01<01:05, 13.85it/s, loss=0.84, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:   3%|▎         | 27/938 [00:01<01:06, 13.78it/s, loss=0.84, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   3%|▎         | 27/938 [00:01<01:06, 13.78it/s, loss=0.853, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   3%|▎         | 28/938 [00:02<01:05, 13.82it/s, loss=0.851, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   3%|▎         | 29/938 [00:02<01:05, 13.85it/s, loss=0.848, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   3%|▎         | 30/938 [00:02<01:05, 13.87it/s, loss=0.848, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   3%|▎         | 30/938 [00:02<01:05, 13.87it/s, loss=0.847, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   3%|▎         | 31/938 [00:02<01:05, 13.83it/s, loss=0.865, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   3%|▎         | 32/938 [00:02<01:05, 13.87it/s, loss=0.877, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   4%|▎         | 33/938 [00:02<01:05, 13.91it/s, loss=0.877, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   4%|▎         | 33/938 [00:02<01:05, 13.91it/s, loss=0.865, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   4%|▎         | 34/938 [00:02<01:05, 13.88it/s, loss=0.866, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   4%|▎         | 35/938 [00:02<01:04, 13.96it/s, loss=0.868, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   4%|▍         | 36/938 [00:02<01:04, 14.00it/s, loss=0.868, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   4%|▍         | 36/938 [00:02<01:04, 14.00it/s, loss=0.863, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   4%|▍         | 37/938 [00:02<01:04, 14.02it/s, loss=0.856, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   4%|▍         | 38/938 [00:02<01:04, 13.96it/s, loss=0.864, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   4%|▍         | 39/938 [00:02<01:04, 13.95it/s, loss=0.864, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   4%|▍         | 39/938 [00:02<01:04, 13.95it/s, loss=0.849, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   4%|▍         | 40/938 [00:02<01:04, 13.90it/s, loss=0.851, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   4%|▍         | 41/938 [00:02<01:04, 13.90it/s, loss=0.853, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   4%|▍         | 42/938 [00:03<01:04, 13.92it/s, loss=0.853, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   4%|▍         | 42/938 [00:03<01:04, 13.92it/s, loss=0.85, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:   5%|▍         | 43/938 [00:03<01:04, 13.92it/s, loss=0.846, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   5%|▍         | 44/938 [00:03<01:04, 13.81it/s, loss=0.85, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:   5%|▍         | 45/938 [00:03<01:04, 13.83it/s, loss=0.85, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   5%|▍         | 45/938 [00:03<01:04, 13.83it/s, loss=0.858, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   5%|▍         | 46/938 [00:03<01:04, 13.81it/s, loss=0.862, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   5%|▌         | 47/938 [00:03<01:04, 13.84it/s, loss=0.86, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:   5%|▌         | 48/938 [00:03<01:04, 13.87it/s, loss=0.86, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   5%|▌         | 48/938 [00:03<01:04, 13.86it/s, loss=0.854, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   5%|▌         | 49/938 [00:03<01:03, 13.91it/s, loss=0.865, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   5%|▌         | 50/938 [00:03<01:03, 13.91it/s, loss=0.871, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   5%|▌         | 51/938 [00:03<01:03, 13.99it/s, loss=0.871, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   5%|▌         | 51/938 [00:03<01:03, 13.99it/s, loss=0.863, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   6%|▌         | 52/938 [00:03<01:03, 14.01it/s, loss=0.854, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   6%|▌         | 53/938 [00:03<01:03, 14.04it/s, loss=0.859, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   6%|▌         | 54/938 [00:03<01:03, 14.02it/s, loss=0.859, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   6%|▌         | 54/938 [00:03<01:03, 14.02it/s, loss=0.869, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   6%|▌         | 55/938 [00:03<01:02, 14.04it/s, loss=0.873, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   6%|▌         | 56/938 [00:03<01:02, 14.05it/s, loss=0.878, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   6%|▌         | 57/938 [00:04<01:02, 14.01it/s, loss=0.878, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   6%|▌         | 57/938 [00:04<01:02, 14.01it/s, loss=0.869, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   6%|▌         | 58/938 [00:04<01:03, 13.97it/s, loss=0.868, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   6%|▋         | 59/938 [00:04<01:03, 13.88it/s, loss=0.864, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   6%|▋         | 60/938 [00:04<01:03, 13.92it/s, loss=0.864, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   6%|▋         | 60/938 [00:04<01:03, 13.92it/s, loss=0.855, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   7%|▋         | 61/938 [00:04<01:02, 13.95it/s, loss=0.856, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   7%|▋         | 62/938 [00:04<01:02, 13.94it/s, loss=0.856, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   7%|▋         | 63/938 [00:04<01:02, 13.91it/s, loss=0.856, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   7%|▋         | 63/938 [00:04<01:02, 13.91it/s, loss=0.859, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   7%|▋         | 64/938 [00:04<01:02, 13.89it/s, loss=0.858, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   7%|▋         | 65/938 [00:04<01:03, 13.69it/s, loss=0.849, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   7%|▋         | 66/938 [00:04<01:04, 13.60it/s, loss=0.849, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   7%|▋         | 66/938 [00:04<01:04, 13.60it/s, loss=0.85, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:   7%|▋         | 67/938 [00:04<01:04, 13.61it/s, loss=0.848, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   7%|▋         | 68/938 [00:04<01:03, 13.64it/s, loss=0.849, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   7%|▋         | 69/938 [00:05<01:03, 13.64it/s, loss=0.849, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   7%|▋         | 69/938 [00:05<01:03, 13.64it/s, loss=0.838, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   7%|▋         | 70/938 [00:05<01:03, 13.60it/s, loss=0.838, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   8%|▊         | 71/938 [00:05<01:03, 13.66it/s, loss=0.83, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:   8%|▊         | 72/938 [00:05<01:03, 13.60it/s, loss=0.83, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   8%|▊         | 72/938 [00:05<01:03, 13.60it/s, loss=0.828, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   8%|▊         | 73/938 [00:05<01:03, 13.63it/s, loss=0.822, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   8%|▊         | 74/938 [00:05<01:03, 13.66it/s, loss=0.813, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   8%|▊         | 75/938 [00:05<01:03, 13.66it/s, loss=0.813, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   8%|▊         | 75/938 [00:05<01:03, 13.66it/s, loss=0.812, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   8%|▊         | 76/938 [00:05<01:03, 13.63it/s, loss=0.808, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   8%|▊         | 77/938 [00:05<01:03, 13.62it/s, loss=0.832, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   8%|▊         | 78/938 [00:05<01:03, 13.63it/s, loss=0.832, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   8%|▊         | 78/938 [00:05<01:03, 13.63it/s, loss=0.819, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   8%|▊         | 79/938 [00:05<01:03, 13.60it/s, loss=0.829, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   9%|▊         | 80/938 [00:05<01:03, 13.60it/s, loss=0.834, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   9%|▊         | 81/938 [00:05<01:03, 13.59it/s, loss=0.834, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   9%|▊         | 81/938 [00:05<01:03, 13.58it/s, loss=0.824, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   9%|▊         | 82/938 [00:06<01:02, 13.60it/s, loss=0.825, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   9%|▉         | 83/938 [00:06<01:02, 13.62it/s, loss=0.821, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   9%|▉         | 84/938 [00:06<01:02, 13.62it/s, loss=0.821, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   9%|▉         | 84/938 [00:06<01:02, 13.62it/s, loss=0.812, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   9%|▉         | 85/938 [00:06<01:02, 13.64it/s, loss=0.813, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   9%|▉         | 86/938 [00:06<01:02, 13.61it/s, loss=0.803, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   9%|▉         | 87/938 [00:06<01:02, 13.61it/s, loss=0.803, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   9%|▉         | 87/938 [00:06<01:02, 13.61it/s, loss=0.796, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   9%|▉         | 88/938 [00:06<01:02, 13.63it/s, loss=0.798, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:   9%|▉         | 89/938 [00:06<01:02, 13.62it/s, loss=0.796, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  10%|▉         | 90/938 [00:06<01:02, 13.58it/s, loss=0.796, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  10%|▉         | 90/938 [00:06<01:02, 13.58it/s, loss=0.784, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  10%|▉         | 91/938 [00:06<01:02, 13.60it/s, loss=0.796, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  10%|▉         | 92/938 [00:06<01:02, 13.59it/s, loss=0.802, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  10%|▉         | 93/938 [00:06<01:02, 13.60it/s, loss=0.802, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  10%|▉         | 93/938 [00:06<01:02, 13.59it/s, loss=0.798, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  10%|█         | 94/938 [00:06<01:01, 13.62it/s, loss=0.803, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  10%|█         | 95/938 [00:06<01:01, 13.64it/s, loss=0.801, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  10%|█         | 96/938 [00:07<01:01, 13.64it/s, loss=0.801, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  10%|█         | 96/938 [00:07<01:01, 13.64it/s, loss=0.806, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  10%|█         | 97/938 [00:07<01:01, 13.62it/s, loss=0.798, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  10%|█         | 98/938 [00:07<01:01, 13.63it/s, loss=0.817, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  11%|█         | 99/938 [00:07<01:01, 13.60it/s, loss=0.817, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  11%|█         | 99/938 [00:07<01:01, 13.60it/s, loss=0.814, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  11%|█         | 100/938 [00:07<01:01, 13.60it/s, loss=0.81, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  11%|█         | 101/938 [00:07<01:01, 13.51it/s, loss=0.814, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  11%|█         | 102/938 [00:07<01:01, 13.52it/s, loss=0.814, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  11%|█         | 102/938 [00:07<01:01, 13.52it/s, loss=0.817, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  11%|█         | 103/938 [00:07<01:01, 13.52it/s, loss=0.819, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  11%|█         | 104/938 [00:07<01:01, 13.56it/s, loss=0.817, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  11%|█         | 105/938 [00:07<01:01, 13.57it/s, loss=0.817, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  11%|█         | 105/938 [00:07<01:01, 13.57it/s, loss=0.812, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  11%|█▏        | 106/938 [00:07<01:01, 13.59it/s, loss=0.828, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  11%|█▏        | 107/938 [00:07<01:01, 13.60it/s, loss=0.827, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  12%|█▏        | 108/938 [00:07<01:00, 13.61it/s, loss=0.827, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  12%|█▏        | 108/938 [00:07<01:01, 13.61it/s, loss=0.826, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  12%|█▏        | 109/938 [00:07<01:00, 13.63it/s, loss=0.839, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  12%|█▏        | 110/938 [00:08<01:00, 13.64it/s, loss=0.832, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  12%|█▏        | 111/938 [00:08<01:00, 13.67it/s, loss=0.832, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  12%|█▏        | 111/938 [00:08<01:00, 13.66it/s, loss=0.826, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  12%|█▏        | 112/938 [00:08<01:00, 13.66it/s, loss=0.814, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  12%|█▏        | 113/938 [00:08<01:00, 13.67it/s, loss=0.818, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  12%|█▏        | 114/938 [00:08<01:00, 13.62it/s, loss=0.818, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  12%|█▏        | 114/938 [00:08<01:00, 13.62it/s, loss=0.822, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  12%|█▏        | 115/938 [00:08<01:00, 13.63it/s, loss=0.828, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  12%|█▏        | 116/938 [00:08<01:00, 13.65it/s, loss=0.827, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  12%|█▏        | 117/938 [00:08<01:00, 13.64it/s, loss=0.827, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  12%|█▏        | 117/938 [00:08<01:00, 13.64it/s, loss=0.837, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  13%|█▎        | 118/938 [00:08<01:00, 13.64it/s, loss=0.822, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  13%|█▎        | 119/938 [00:08<00:59, 13.66it/s, loss=0.819, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  13%|█▎        | 120/938 [00:08<00:59, 13.65it/s, loss=0.819, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  13%|█▎        | 120/938 [00:08<00:59, 13.65it/s, loss=0.818, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  13%|█▎        | 121/938 [00:08<00:59, 13.63it/s, loss=0.826, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  13%|█▎        | 122/938 [00:08<00:59, 13.61it/s, loss=0.833, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  13%|█▎        | 123/938 [00:09<00:59, 13.59it/s, loss=0.833, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  13%|█▎        | 123/938 [00:09<00:59, 13.59it/s, loss=0.833, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  13%|█▎        | 124/938 [00:09<00:59, 13.57it/s, loss=0.838, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  13%|█▎        | 125/938 [00:09<00:59, 13.56it/s, loss=0.829, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  13%|█▎        | 126/938 [00:09<00:59, 13.54it/s, loss=0.829, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  13%|█▎        | 126/938 [00:09<00:59, 13.54it/s, loss=0.819, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  14%|█▎        | 127/938 [00:09<00:59, 13.56it/s, loss=0.838, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  14%|█▎        | 128/938 [00:09<00:59, 13.54it/s, loss=0.849, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  14%|█▍        | 129/938 [00:09<00:59, 13.56it/s, loss=0.849, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  14%|█▍        | 129/938 [00:09<00:59, 13.55it/s, loss=0.835, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  14%|█▍        | 130/938 [00:09<00:59, 13.57it/s, loss=0.843, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  14%|█▍        | 131/938 [00:09<00:59, 13.57it/s, loss=0.855, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  14%|█▍        | 132/938 [00:09<00:59, 13.59it/s, loss=0.855, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  14%|█▍        | 132/938 [00:09<00:59, 13.59it/s, loss=0.861, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  14%|█▍        | 133/938 [00:09<00:59, 13.59it/s, loss=0.867, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  14%|█▍        | 134/938 [00:09<00:59, 13.62it/s, loss=0.863, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  14%|█▍        | 135/938 [00:09<00:59, 13.59it/s, loss=0.863, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  14%|█▍        | 135/938 [00:09<00:59, 13.59it/s, loss=0.85, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  14%|█▍        | 136/938 [00:09<00:58, 13.60it/s, loss=0.851, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  15%|█▍        | 137/938 [00:10<00:58, 13.61it/s, loss=0.835, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  15%|█▍        | 138/938 [00:10<00:58, 13.62it/s, loss=0.835, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  15%|█▍        | 138/938 [00:10<00:58, 13.62it/s, loss=0.839, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  15%|█▍        | 139/938 [00:10<00:58, 13.62it/s, loss=0.84, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  15%|█▍        | 140/938 [00:10<00:58, 13.63it/s, loss=0.847, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  15%|█▌        | 141/938 [00:10<00:58, 13.61it/s, loss=0.847, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  15%|█▌        | 141/938 [00:10<00:58, 13.61it/s, loss=0.835, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  15%|█▌        | 142/938 [00:10<00:58, 13.57it/s, loss=0.832, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  15%|█▌        | 143/938 [00:10<00:58, 13.58it/s, loss=0.835, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  15%|█▌        | 144/938 [00:10<00:58, 13.58it/s, loss=0.835, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  15%|█▌        | 144/938 [00:10<00:58, 13.58it/s, loss=0.834, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  15%|█▌        | 145/938 [00:10<00:58, 13.57it/s, loss=0.845, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  16%|█▌        | 146/938 [00:10<00:58, 13.59it/s, loss=0.839, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  16%|█▌        | 147/938 [00:10<00:58, 13.58it/s, loss=0.839, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  16%|█▌        | 147/938 [00:10<00:58, 13.58it/s, loss=0.814, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  16%|█▌        | 148/938 [00:10<00:58, 13.59it/s, loss=0.798, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  16%|█▌        | 149/938 [00:10<00:58, 13.58it/s, loss=0.803, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  16%|█▌        | 150/938 [00:11<00:57, 13.60it/s, loss=0.803, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  16%|█▌        | 150/938 [00:11<00:57, 13.60it/s, loss=0.802, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  16%|█▌        | 151/938 [00:11<00:57, 13.60it/s, loss=0.785, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  16%|█▌        | 152/938 [00:11<00:57, 13.62it/s, loss=0.786, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  16%|█▋        | 153/938 [00:11<00:57, 13.60it/s, loss=0.786, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  16%|█▋        | 153/938 [00:11<00:57, 13.60it/s, loss=0.792, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  16%|█▋        | 154/938 [00:11<00:57, 13.62it/s, loss=0.786, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  17%|█▋        | 155/938 [00:11<00:57, 13.63it/s, loss=0.801, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  17%|█▋        | 156/938 [00:11<00:57, 13.60it/s, loss=0.801, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  17%|█▋        | 156/938 [00:11<00:57, 13.60it/s, loss=0.801, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  17%|█▋        | 157/938 [00:11<00:57, 13.61it/s, loss=0.8, v_num=17, val_rmse=0.649, train_rmse=1.250]  
Epoch 1:  17%|█▋        | 158/938 [00:11<00:57, 13.61it/s, loss=0.796, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  17%|█▋        | 159/938 [00:11<00:57, 13.62it/s, loss=0.796, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  17%|█▋        | 159/938 [00:11<00:57, 13.62it/s, loss=0.791, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  17%|█▋        | 160/938 [00:11<00:57, 13.56it/s, loss=0.786, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  17%|█▋        | 161/938 [00:11<00:57, 13.56it/s, loss=0.801, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  17%|█▋        | 162/938 [00:11<00:57, 13.56it/s, loss=0.801, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  17%|█▋        | 162/938 [00:11<00:57, 13.56it/s, loss=0.794, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  17%|█▋        | 163/938 [00:12<00:57, 13.58it/s, loss=0.791, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  17%|█▋        | 164/938 [00:12<00:57, 13.58it/s, loss=0.796, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  18%|█▊        | 165/938 [00:12<00:56, 13.60it/s, loss=0.796, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  18%|█▊        | 165/938 [00:12<00:56, 13.60it/s, loss=0.796, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  18%|█▊        | 166/938 [00:12<00:56, 13.59it/s, loss=0.798, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  18%|█▊        | 167/938 [00:12<00:56, 13.59it/s, loss=0.801, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  18%|█▊        | 168/938 [00:12<00:56, 13.59it/s, loss=0.801, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  18%|█▊        | 168/938 [00:12<00:56, 13.58it/s, loss=0.8, v_num=17, val_rmse=0.649, train_rmse=1.250]  
Epoch 1:  18%|█▊        | 169/938 [00:12<00:56, 13.60it/s, loss=0.798, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  18%|█▊        | 170/938 [00:12<00:56, 13.59it/s, loss=0.797, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  18%|█▊        | 171/938 [00:12<00:56, 13.60it/s, loss=0.797, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  18%|█▊        | 171/938 [00:12<00:56, 13.60it/s, loss=0.798, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  18%|█▊        | 172/938 [00:12<00:56, 13.59it/s, loss=0.794, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  18%|█▊        | 173/938 [00:12<00:56, 13.59it/s, loss=0.784, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  19%|█▊        | 174/938 [00:12<00:56, 13.59it/s, loss=0.784, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  19%|█▊        | 174/938 [00:12<00:56, 13.59it/s, loss=0.787, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  19%|█▊        | 175/938 [00:12<00:56, 13.60it/s, loss=0.776, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  19%|█▉        | 176/938 [00:12<00:56, 13.60it/s, loss=0.769, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  19%|█▉        | 177/938 [00:12<00:55, 13.62it/s, loss=0.769, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  19%|█▉        | 177/938 [00:12<00:55, 13.62it/s, loss=0.78, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  19%|█▉        | 178/938 [00:13<00:55, 13.60it/s, loss=0.775, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  19%|█▉        | 179/938 [00:13<00:55, 13.60it/s, loss=0.776, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  19%|█▉        | 180/938 [00:13<00:55, 13.61it/s, loss=0.776, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  19%|█▉        | 180/938 [00:13<00:55, 13.61it/s, loss=0.772, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  19%|█▉        | 181/938 [00:13<00:55, 13.62it/s, loss=0.761, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  19%|█▉        | 182/938 [00:13<00:55, 13.64it/s, loss=0.757, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  20%|█▉        | 183/938 [00:13<00:55, 13.65it/s, loss=0.757, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  20%|█▉        | 183/938 [00:13<00:55, 13.65it/s, loss=0.754, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  20%|█▉        | 184/938 [00:13<00:55, 13.62it/s, loss=0.748, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  20%|█▉        | 185/938 [00:13<00:55, 13.64it/s, loss=0.74, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  20%|█▉        | 186/938 [00:13<00:55, 13.63it/s, loss=0.74, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  20%|█▉        | 186/938 [00:13<00:55, 13.63it/s, loss=0.744, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  20%|█▉        | 187/938 [00:13<00:55, 13.64it/s, loss=0.746, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  20%|██        | 188/938 [00:13<00:54, 13.65it/s, loss=0.752, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  20%|██        | 189/938 [00:13<00:54, 13.64it/s, loss=0.752, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  20%|██        | 189/938 [00:13<00:54, 13.64it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  20%|██        | 190/938 [00:13<00:54, 13.64it/s, loss=0.763, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  20%|██        | 191/938 [00:13<00:54, 13.66it/s, loss=0.762, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  20%|██        | 192/938 [00:14<00:54, 13.67it/s, loss=0.762, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  20%|██        | 192/938 [00:14<00:54, 13.67it/s, loss=0.764, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  21%|██        | 193/938 [00:14<00:54, 13.66it/s, loss=0.765, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  21%|██        | 194/938 [00:14<00:54, 13.68it/s, loss=0.765, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  21%|██        | 195/938 [00:14<00:54, 13.66it/s, loss=0.765, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  21%|██        | 195/938 [00:14<00:54, 13.66it/s, loss=0.765, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  21%|██        | 196/938 [00:14<00:54, 13.67it/s, loss=0.763, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  21%|██        | 197/938 [00:14<00:54, 13.67it/s, loss=0.756, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  21%|██        | 198/938 [00:14<00:54, 13.68it/s, loss=0.756, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  21%|██        | 198/938 [00:14<00:54, 13.68it/s, loss=0.775, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  21%|██        | 199/938 [00:14<00:53, 13.69it/s, loss=0.786, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  21%|██▏       | 200/938 [00:14<00:53, 13.67it/s, loss=0.787, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  21%|██▏       | 201/938 [00:14<00:53, 13.67it/s, loss=0.787, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  21%|██▏       | 201/938 [00:14<00:53, 13.67it/s, loss=0.791, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  22%|██▏       | 202/938 [00:14<00:53, 13.67it/s, loss=0.792, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  22%|██▏       | 203/938 [00:14<00:53, 13.68it/s, loss=0.792, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  22%|██▏       | 204/938 [00:14<00:53, 13.67it/s, loss=0.792, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  22%|██▏       | 204/938 [00:14<00:53, 13.66it/s, loss=0.792, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  22%|██▏       | 205/938 [00:15<00:53, 13.67it/s, loss=0.802, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  22%|██▏       | 206/938 [00:15<00:53, 13.66it/s, loss=0.797, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  22%|██▏       | 207/938 [00:15<00:53, 13.67it/s, loss=0.797, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  22%|██▏       | 207/938 [00:15<00:53, 13.67it/s, loss=0.796, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  22%|██▏       | 208/938 [00:15<00:53, 13.67it/s, loss=0.794, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  22%|██▏       | 209/938 [00:15<00:53, 13.67it/s, loss=0.797, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  22%|██▏       | 210/938 [00:15<00:53, 13.68it/s, loss=0.797, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  22%|██▏       | 210/938 [00:15<00:53, 13.68it/s, loss=0.796, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  22%|██▏       | 211/938 [00:15<00:53, 13.69it/s, loss=0.801, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  23%|██▎       | 212/938 [00:15<00:53, 13.69it/s, loss=0.799, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  23%|██▎       | 213/938 [00:15<00:52, 13.69it/s, loss=0.799, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  23%|██▎       | 213/938 [00:15<00:52, 13.69it/s, loss=0.795, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  23%|██▎       | 214/938 [00:15<00:52, 13.70it/s, loss=0.8, v_num=17, val_rmse=0.649, train_rmse=1.250]  
Epoch 1:  23%|██▎       | 215/938 [00:15<00:52, 13.68it/s, loss=0.798, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  23%|██▎       | 216/938 [00:15<00:52, 13.68it/s, loss=0.798, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  23%|██▎       | 216/938 [00:15<00:52, 13.68it/s, loss=0.803, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  23%|██▎       | 217/938 [00:15<00:52, 13.67it/s, loss=0.797, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  23%|██▎       | 218/938 [00:15<00:52, 13.67it/s, loss=0.79, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  23%|██▎       | 219/938 [00:16<00:52, 13.68it/s, loss=0.79, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  23%|██▎       | 219/938 [00:16<00:52, 13.68it/s, loss=0.786, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  23%|██▎       | 220/938 [00:16<00:52, 13.69it/s, loss=0.792, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  24%|██▎       | 221/938 [00:16<00:52, 13.68it/s, loss=0.792, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  24%|██▎       | 222/938 [00:16<00:52, 13.69it/s, loss=0.792, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  24%|██▎       | 222/938 [00:16<00:52, 13.69it/s, loss=0.795, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  24%|██▍       | 223/938 [00:16<00:52, 13.69it/s, loss=0.796, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  24%|██▍       | 224/938 [00:16<00:52, 13.68it/s, loss=0.798, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  24%|██▍       | 225/938 [00:16<00:52, 13.66it/s, loss=0.798, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  24%|██▍       | 225/938 [00:16<00:52, 13.66it/s, loss=0.795, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  24%|██▍       | 226/938 [00:16<00:52, 13.66it/s, loss=0.795, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  24%|██▍       | 227/938 [00:16<00:52, 13.66it/s, loss=0.798, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  24%|██▍       | 228/938 [00:16<00:51, 13.65it/s, loss=0.798, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  24%|██▍       | 228/938 [00:16<00:52, 13.65it/s, loss=0.789, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  24%|██▍       | 229/938 [00:16<00:51, 13.65it/s, loss=0.785, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  25%|██▍       | 230/938 [00:16<00:51, 13.65it/s, loss=0.78, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  25%|██▍       | 231/938 [00:16<00:51, 13.66it/s, loss=0.78, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  25%|██▍       | 231/938 [00:16<00:51, 13.66it/s, loss=0.78, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  25%|██▍       | 232/938 [00:16<00:51, 13.65it/s, loss=0.801, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  25%|██▍       | 233/938 [00:17<00:51, 13.65it/s, loss=0.802, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  25%|██▍       | 234/938 [00:17<00:51, 13.67it/s, loss=0.802, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  25%|██▍       | 234/938 [00:17<00:51, 13.66it/s, loss=0.795, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  25%|██▌       | 235/938 [00:17<00:51, 13.67it/s, loss=0.793, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  25%|██▌       | 236/938 [00:17<00:51, 13.69it/s, loss=0.791, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  25%|██▌       | 237/938 [00:17<00:51, 13.68it/s, loss=0.791, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  25%|██▌       | 237/938 [00:17<00:51, 13.68it/s, loss=0.788, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  25%|██▌       | 238/938 [00:17<00:51, 13.68it/s, loss=0.773, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  25%|██▌       | 239/938 [00:17<00:51, 13.69it/s, loss=0.772, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  26%|██▌       | 240/938 [00:17<00:50, 13.70it/s, loss=0.772, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  26%|██▌       | 240/938 [00:17<00:50, 13.70it/s, loss=0.771, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  26%|██▌       | 241/938 [00:17<00:50, 13.70it/s, loss=0.765, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  26%|██▌       | 242/938 [00:17<00:50, 13.70it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  26%|██▌       | 243/938 [00:17<00:50, 13.70it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  26%|██▌       | 243/938 [00:17<00:50, 13.70it/s, loss=0.758, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  26%|██▌       | 244/938 [00:17<00:50, 13.70it/s, loss=0.76, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  26%|██▌       | 245/938 [00:17<00:50, 13.69it/s, loss=0.747, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  26%|██▌       | 246/938 [00:17<00:50, 13.70it/s, loss=0.747, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  26%|██▌       | 246/938 [00:17<00:50, 13.70it/s, loss=0.748, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  26%|██▋       | 247/938 [00:18<00:50, 13.70it/s, loss=0.757, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  26%|██▋       | 248/938 [00:18<00:50, 13.71it/s, loss=0.771, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  27%|██▋       | 249/938 [00:18<00:50, 13.70it/s, loss=0.771, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  27%|██▋       | 249/938 [00:18<00:50, 13.70it/s, loss=0.769, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  27%|██▋       | 250/938 [00:18<00:50, 13.71it/s, loss=0.77, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  27%|██▋       | 251/938 [00:18<00:50, 13.70it/s, loss=0.77, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  27%|██▋       | 252/938 [00:18<00:50, 13.70it/s, loss=0.77, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  27%|██▋       | 252/938 [00:18<00:50, 13.70it/s, loss=0.761, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  27%|██▋       | 253/938 [00:18<00:49, 13.71it/s, loss=0.758, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  27%|██▋       | 254/938 [00:18<00:49, 13.70it/s, loss=0.757, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  27%|██▋       | 255/938 [00:18<00:49, 13.71it/s, loss=0.757, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  27%|██▋       | 255/938 [00:18<00:49, 13.71it/s, loss=0.761, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  27%|██▋       | 256/938 [00:18<00:49, 13.72it/s, loss=0.763, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  27%|██▋       | 257/938 [00:18<00:49, 13.73it/s, loss=0.765, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  28%|██▊       | 258/938 [00:18<00:49, 13.73it/s, loss=0.765, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  28%|██▊       | 258/938 [00:18<00:49, 13.73it/s, loss=0.779, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  28%|██▊       | 259/938 [00:18<00:49, 13.72it/s, loss=0.774, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  28%|██▊       | 260/938 [00:18<00:49, 13.72it/s, loss=0.778, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  28%|██▊       | 261/938 [00:19<00:49, 13.73it/s, loss=0.778, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  28%|██▊       | 261/938 [00:19<00:49, 13.73it/s, loss=0.784, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  28%|██▊       | 262/938 [00:19<00:49, 13.74it/s, loss=0.789, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  28%|██▊       | 263/938 [00:19<00:49, 13.73it/s, loss=0.794, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  28%|██▊       | 264/938 [00:19<00:49, 13.73it/s, loss=0.794, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  28%|██▊       | 264/938 [00:19<00:49, 13.73it/s, loss=0.798, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  28%|██▊       | 265/938 [00:19<00:49, 13.73it/s, loss=0.805, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  28%|██▊       | 266/938 [00:19<00:48, 13.73it/s, loss=0.803, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  28%|██▊       | 267/938 [00:19<00:48, 13.73it/s, loss=0.803, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  28%|██▊       | 267/938 [00:19<00:48, 13.73it/s, loss=0.801, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  29%|██▊       | 268/938 [00:19<00:48, 13.73it/s, loss=0.793, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  29%|██▊       | 269/938 [00:19<00:48, 13.74it/s, loss=0.791, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  29%|██▉       | 270/938 [00:19<00:48, 13.74it/s, loss=0.791, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  29%|██▉       | 270/938 [00:19<00:48, 13.74it/s, loss=0.793, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  29%|██▉       | 271/938 [00:19<00:48, 13.74it/s, loss=0.79, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  29%|██▉       | 272/938 [00:19<00:48, 13.74it/s, loss=0.784, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  29%|██▉       | 273/938 [00:19<00:48, 13.75it/s, loss=0.784, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  29%|██▉       | 273/938 [00:19<00:48, 13.75it/s, loss=0.791, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  29%|██▉       | 274/938 [00:19<00:48, 13.76it/s, loss=0.788, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  29%|██▉       | 275/938 [00:19<00:48, 13.76it/s, loss=0.788, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  29%|██▉       | 276/938 [00:20<00:48, 13.77it/s, loss=0.788, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  29%|██▉       | 276/938 [00:20<00:48, 13.77it/s, loss=0.79, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  30%|██▉       | 277/938 [00:20<00:48, 13.77it/s, loss=0.788, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  30%|██▉       | 278/938 [00:20<00:47, 13.77it/s, loss=0.782, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  30%|██▉       | 279/938 [00:20<00:47, 13.77it/s, loss=0.782, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  30%|██▉       | 279/938 [00:20<00:47, 13.77it/s, loss=0.78, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  30%|██▉       | 280/938 [00:20<00:47, 13.78it/s, loss=0.765, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  30%|██▉       | 281/938 [00:20<00:47, 13.77it/s, loss=0.762, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  30%|███       | 282/938 [00:20<00:47, 13.78it/s, loss=0.762, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  30%|███       | 282/938 [00:20<00:47, 13.78it/s, loss=0.765, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  30%|███       | 283/938 [00:20<00:47, 13.78it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  30%|███       | 284/938 [00:20<00:47, 13.78it/s, loss=0.75, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  30%|███       | 285/938 [00:20<00:47, 13.79it/s, loss=0.75, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  30%|███       | 285/938 [00:20<00:47, 13.79it/s, loss=0.751, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  30%|███       | 286/938 [00:20<00:47, 13.79it/s, loss=0.763, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  31%|███       | 287/938 [00:20<00:47, 13.80it/s, loss=0.768, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  31%|███       | 288/938 [00:20<00:47, 13.80it/s, loss=0.768, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  31%|███       | 288/938 [00:20<00:47, 13.80it/s, loss=0.769, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  31%|███       | 289/938 [00:20<00:47, 13.78it/s, loss=0.763, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  31%|███       | 290/938 [00:21<00:46, 13.79it/s, loss=0.769, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  31%|███       | 291/938 [00:21<00:46, 13.80it/s, loss=0.769, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  31%|███       | 291/938 [00:21<00:46, 13.80it/s, loss=0.772, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  31%|███       | 292/938 [00:21<00:46, 13.80it/s, loss=0.769, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  31%|███       | 293/938 [00:21<00:46, 13.80it/s, loss=0.768, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  31%|███▏      | 294/938 [00:21<00:46, 13.81it/s, loss=0.768, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  31%|███▏      | 294/938 [00:21<00:46, 13.81it/s, loss=0.783, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  31%|███▏      | 295/938 [00:21<00:46, 13.80it/s, loss=0.779, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  32%|███▏      | 296/938 [00:21<00:46, 13.81it/s, loss=0.775, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  32%|███▏      | 297/938 [00:21<00:46, 13.82it/s, loss=0.775, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  32%|███▏      | 297/938 [00:21<00:46, 13.82it/s, loss=0.776, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  32%|███▏      | 298/938 [00:21<00:46, 13.82it/s, loss=0.776, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  32%|███▏      | 299/938 [00:21<00:46, 13.82it/s, loss=0.775, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  32%|███▏      | 300/938 [00:21<00:46, 13.82it/s, loss=0.775, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  32%|███▏      | 300/938 [00:21<00:46, 13.82it/s, loss=0.784, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  32%|███▏      | 301/938 [00:21<00:46, 13.81it/s, loss=0.78, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  32%|███▏      | 302/938 [00:21<00:46, 13.81it/s, loss=0.784, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  32%|███▏      | 303/938 [00:21<00:45, 13.81it/s, loss=0.784, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  32%|███▏      | 303/938 [00:21<00:45, 13.81it/s, loss=0.781, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  32%|███▏      | 304/938 [00:22<00:45, 13.81it/s, loss=0.777, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  33%|███▎      | 305/938 [00:22<00:45, 13.81it/s, loss=0.776, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  33%|███▎      | 306/938 [00:22<00:45, 13.81it/s, loss=0.776, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  33%|███▎      | 306/938 [00:22<00:45, 13.81it/s, loss=0.771, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  33%|███▎      | 307/938 [00:22<00:45, 13.82it/s, loss=0.763, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  33%|███▎      | 308/938 [00:22<00:45, 13.82it/s, loss=0.77, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  33%|███▎      | 309/938 [00:22<00:45, 13.82it/s, loss=0.77, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  33%|███▎      | 309/938 [00:22<00:45, 13.82it/s, loss=0.775, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  33%|███▎      | 310/938 [00:22<00:45, 13.82it/s, loss=0.779, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  33%|███▎      | 311/938 [00:22<00:45, 13.83it/s, loss=0.782, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  33%|███▎      | 312/938 [00:22<00:45, 13.83it/s, loss=0.782, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  33%|███▎      | 312/938 [00:22<00:45, 13.83it/s, loss=0.785, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  33%|███▎      | 313/938 [00:22<00:45, 13.83it/s, loss=0.776, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  33%|███▎      | 314/938 [00:22<00:45, 13.84it/s, loss=0.765, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  34%|███▎      | 315/938 [00:22<00:45, 13.83it/s, loss=0.765, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  34%|███▎      | 315/938 [00:22<00:45, 13.83it/s, loss=0.771, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  34%|███▎      | 316/938 [00:22<00:44, 13.84it/s, loss=0.765, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  34%|███▍      | 317/938 [00:22<00:44, 13.84it/s, loss=0.766, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  34%|███▍      | 318/938 [00:22<00:44, 13.85it/s, loss=0.766, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  34%|███▍      | 318/938 [00:22<00:44, 13.84it/s, loss=0.781, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  34%|███▍      | 319/938 [00:23<00:44, 13.85it/s, loss=0.79, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  34%|███▍      | 320/938 [00:23<00:44, 13.86it/s, loss=0.788, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  34%|███▍      | 321/938 [00:23<00:44, 13.84it/s, loss=0.788, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  34%|███▍      | 321/938 [00:23<00:44, 13.84it/s, loss=0.784, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  34%|███▍      | 322/938 [00:23<00:44, 13.84it/s, loss=0.765, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  34%|███▍      | 323/938 [00:23<00:44, 13.85it/s, loss=0.765, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  35%|███▍      | 324/938 [00:23<00:44, 13.86it/s, loss=0.765, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  35%|███▍      | 324/938 [00:23<00:44, 13.86it/s, loss=0.765, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  35%|███▍      | 325/938 [00:23<00:44, 13.86it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  35%|███▍      | 326/938 [00:23<00:44, 13.87it/s, loss=0.755, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  35%|███▍      | 327/938 [00:23<00:44, 13.86it/s, loss=0.755, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  35%|███▍      | 327/938 [00:23<00:44, 13.86it/s, loss=0.748, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  35%|███▍      | 328/938 [00:23<00:44, 13.86it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  35%|███▌      | 329/938 [00:23<00:43, 13.87it/s, loss=0.754, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  35%|███▌      | 330/938 [00:23<00:43, 13.87it/s, loss=0.754, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  35%|███▌      | 330/938 [00:23<00:43, 13.87it/s, loss=0.737, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  35%|███▌      | 331/938 [00:23<00:43, 13.87it/s, loss=0.729, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  35%|███▌      | 332/938 [00:23<00:43, 13.88it/s, loss=0.72, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  36%|███▌      | 333/938 [00:23<00:43, 13.89it/s, loss=0.72, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  36%|███▌      | 333/938 [00:23<00:43, 13.89it/s, loss=0.726, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  36%|███▌      | 334/938 [00:24<00:43, 13.88it/s, loss=0.737, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  36%|███▌      | 335/938 [00:24<00:43, 13.89it/s, loss=0.742, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  36%|███▌      | 336/938 [00:24<00:43, 13.89it/s, loss=0.742, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  36%|███▌      | 336/938 [00:24<00:43, 13.89it/s, loss=0.746, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  36%|███▌      | 337/938 [00:24<00:43, 13.89it/s, loss=0.751, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  36%|███▌      | 338/938 [00:24<00:43, 13.91it/s, loss=0.74, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  36%|███▌      | 339/938 [00:24<00:43, 13.91it/s, loss=0.74, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  36%|███▌      | 339/938 [00:24<00:43, 13.91it/s, loss=0.727, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  36%|███▌      | 340/938 [00:24<00:42, 13.91it/s, loss=0.721, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  36%|███▋      | 341/938 [00:24<00:42, 13.91it/s, loss=0.721, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  36%|███▋      | 342/938 [00:24<00:42, 13.92it/s, loss=0.721, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  36%|███▋      | 342/938 [00:24<00:42, 13.92it/s, loss=0.727, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  37%|███▋      | 343/938 [00:24<00:42, 13.92it/s, loss=0.727, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  37%|███▋      | 344/938 [00:24<00:42, 13.92it/s, loss=0.731, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  37%|███▋      | 345/938 [00:24<00:42, 13.92it/s, loss=0.731, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  37%|███▋      | 345/938 [00:24<00:42, 13.92it/s, loss=0.736, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  37%|███▋      | 346/938 [00:24<00:42, 13.93it/s, loss=0.74, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  37%|███▋      | 347/938 [00:24<00:42, 13.93it/s, loss=0.751, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  37%|███▋      | 348/938 [00:24<00:42, 13.94it/s, loss=0.751, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  37%|███▋      | 348/938 [00:24<00:42, 13.94it/s, loss=0.733, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  37%|███▋      | 349/938 [00:25<00:42, 13.94it/s, loss=0.733, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  37%|███▋      | 350/938 [00:25<00:42, 13.95it/s, loss=0.737, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  37%|███▋      | 351/938 [00:25<00:42, 13.94it/s, loss=0.737, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  37%|███▋      | 351/938 [00:25<00:42, 13.94it/s, loss=0.736, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  38%|███▊      | 352/938 [00:25<00:42, 13.94it/s, loss=0.749, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  38%|███▊      | 353/938 [00:25<00:41, 13.95it/s, loss=0.748, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  38%|███▊      | 354/938 [00:25<00:41, 13.95it/s, loss=0.748, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  38%|███▊      | 354/938 [00:25<00:41, 13.95it/s, loss=0.736, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  38%|███▊      | 355/938 [00:25<00:41, 13.96it/s, loss=0.724, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  38%|███▊      | 356/938 [00:25<00:41, 13.97it/s, loss=0.726, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  38%|███▊      | 357/938 [00:25<00:41, 13.96it/s, loss=0.726, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  38%|███▊      | 357/938 [00:25<00:41, 13.96it/s, loss=0.719, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  38%|███▊      | 358/938 [00:25<00:41, 13.96it/s, loss=0.711, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  38%|███▊      | 359/938 [00:25<00:41, 13.97it/s, loss=0.711, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  38%|███▊      | 360/938 [00:25<00:41, 13.97it/s, loss=0.711, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  38%|███▊      | 360/938 [00:25<00:41, 13.97it/s, loss=0.722, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  38%|███▊      | 361/938 [00:25<00:41, 13.97it/s, loss=0.722, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  39%|███▊      | 362/938 [00:25<00:41, 13.97it/s, loss=0.72, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  39%|███▊      | 363/938 [00:25<00:41, 13.97it/s, loss=0.72, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  39%|███▊      | 363/938 [00:25<00:41, 13.97it/s, loss=0.724, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  39%|███▉      | 364/938 [00:26<00:41, 13.98it/s, loss=0.722, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  39%|███▉      | 365/938 [00:26<00:40, 13.98it/s, loss=0.725, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  39%|███▉      | 366/938 [00:26<00:40, 13.98it/s, loss=0.725, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  39%|███▉      | 366/938 [00:26<00:40, 13.98it/s, loss=0.721, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  39%|███▉      | 367/938 [00:26<00:40, 13.98it/s, loss=0.705, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  39%|███▉      | 368/938 [00:26<00:40, 13.99it/s, loss=0.699, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  39%|███▉      | 369/938 [00:26<00:40, 13.99it/s, loss=0.699, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  39%|███▉      | 369/938 [00:26<00:40, 13.99it/s, loss=0.713, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  39%|███▉      | 370/938 [00:26<00:40, 13.99it/s, loss=0.716, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  40%|███▉      | 371/938 [00:26<00:40, 13.99it/s, loss=0.714, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  40%|███▉      | 372/938 [00:26<00:40, 13.99it/s, loss=0.714, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  40%|███▉      | 372/938 [00:26<00:40, 13.98it/s, loss=0.71, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  40%|███▉      | 373/938 [00:26<00:40, 13.99it/s, loss=0.707, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  40%|███▉      | 374/938 [00:26<00:40, 14.00it/s, loss=0.709, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  40%|███▉      | 375/938 [00:26<00:40, 14.00it/s, loss=0.709, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  40%|███▉      | 375/938 [00:26<00:40, 14.00it/s, loss=0.71, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  40%|████      | 376/938 [00:26<00:40, 14.00it/s, loss=0.709, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  40%|████      | 377/938 [00:26<00:40, 14.00it/s, loss=0.708, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  40%|████      | 378/938 [00:26<00:39, 14.01it/s, loss=0.708, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  40%|████      | 378/938 [00:26<00:39, 14.01it/s, loss=0.71, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  40%|████      | 379/938 [00:27<00:39, 14.01it/s, loss=0.716, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  41%|████      | 380/938 [00:27<00:39, 14.01it/s, loss=0.706, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  41%|████      | 381/938 [00:27<00:39, 14.02it/s, loss=0.706, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  41%|████      | 381/938 [00:27<00:39, 14.02it/s, loss=0.714, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  41%|████      | 382/938 [00:27<00:39, 14.02it/s, loss=0.72, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  41%|████      | 383/938 [00:27<00:39, 14.02it/s, loss=0.723, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  41%|████      | 384/938 [00:27<00:39, 14.02it/s, loss=0.723, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  41%|████      | 384/938 [00:27<00:39, 14.02it/s, loss=0.73, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  41%|████      | 385/938 [00:27<00:39, 14.02it/s, loss=0.727, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  41%|████      | 386/938 [00:27<00:39, 14.03it/s, loss=0.727, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  41%|████▏     | 387/938 [00:27<00:39, 14.02it/s, loss=0.727, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  41%|████▏     | 387/938 [00:27<00:39, 14.02it/s, loss=0.735, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  41%|████▏     | 388/938 [00:27<00:39, 14.03it/s, loss=0.735, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  41%|████▏     | 389/938 [00:27<00:39, 14.04it/s, loss=0.724, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  42%|████▏     | 390/938 [00:27<00:39, 14.04it/s, loss=0.724, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  42%|████▏     | 390/938 [00:27<00:39, 14.04it/s, loss=0.726, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  42%|████▏     | 391/938 [00:27<00:38, 14.04it/s, loss=0.732, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  42%|████▏     | 392/938 [00:27<00:38, 14.04it/s, loss=0.731, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  42%|████▏     | 393/938 [00:27<00:38, 14.04it/s, loss=0.731, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  42%|████▏     | 393/938 [00:27<00:38, 14.04it/s, loss=0.733, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  42%|████▏     | 394/938 [00:28<00:38, 14.04it/s, loss=0.734, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  42%|████▏     | 395/938 [00:28<00:38, 14.05it/s, loss=0.739, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  42%|████▏     | 396/938 [00:28<00:38, 14.05it/s, loss=0.739, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  42%|████▏     | 396/938 [00:28<00:38, 14.05it/s, loss=0.744, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  42%|████▏     | 397/938 [00:28<00:38, 14.05it/s, loss=0.738, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  42%|████▏     | 398/938 [00:28<00:38, 14.06it/s, loss=0.739, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  43%|████▎     | 399/938 [00:28<00:38, 14.05it/s, loss=0.739, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  43%|████▎     | 399/938 [00:28<00:38, 14.05it/s, loss=0.738, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  43%|████▎     | 400/938 [00:28<00:38, 14.06it/s, loss=0.744, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  43%|████▎     | 401/938 [00:28<00:38, 14.06it/s, loss=0.747, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  43%|████▎     | 402/938 [00:28<00:38, 14.06it/s, loss=0.747, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  43%|████▎     | 402/938 [00:28<00:38, 14.06it/s, loss=0.745, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  43%|████▎     | 403/938 [00:28<00:38, 14.05it/s, loss=0.746, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  43%|████▎     | 404/938 [00:28<00:38, 14.05it/s, loss=0.74, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  43%|████▎     | 405/938 [00:28<00:37, 14.05it/s, loss=0.74, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  43%|████▎     | 405/938 [00:28<00:37, 14.05it/s, loss=0.742, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  43%|████▎     | 406/938 [00:28<00:37, 14.05it/s, loss=0.745, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  43%|████▎     | 407/938 [00:28<00:37, 14.05it/s, loss=0.75, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  43%|████▎     | 408/938 [00:29<00:37, 14.05it/s, loss=0.75, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  43%|████▎     | 408/938 [00:29<00:37, 14.05it/s, loss=0.758, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  44%|████▎     | 409/938 [00:29<00:37, 14.06it/s, loss=0.762, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  44%|████▎     | 410/938 [00:29<00:37, 14.06it/s, loss=0.762, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  44%|████▍     | 411/938 [00:29<00:37, 14.05it/s, loss=0.762, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  44%|████▍     | 411/938 [00:29<00:37, 14.05it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  44%|████▍     | 412/938 [00:29<00:37, 14.06it/s, loss=0.748, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  44%|████▍     | 413/938 [00:29<00:37, 14.06it/s, loss=0.753, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  44%|████▍     | 414/938 [00:29<00:37, 14.06it/s, loss=0.753, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  44%|████▍     | 414/938 [00:29<00:37, 14.06it/s, loss=0.753, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  44%|████▍     | 415/938 [00:29<00:37, 14.07it/s, loss=0.769, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  44%|████▍     | 416/938 [00:29<00:37, 14.07it/s, loss=0.768, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  44%|████▍     | 417/938 [00:29<00:37, 14.06it/s, loss=0.768, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  44%|████▍     | 417/938 [00:29<00:37, 14.06it/s, loss=0.776, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  45%|████▍     | 418/938 [00:29<00:36, 14.07it/s, loss=0.774, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  45%|████▍     | 419/938 [00:29<00:36, 14.07it/s, loss=0.779, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  45%|████▍     | 420/938 [00:29<00:36, 14.07it/s, loss=0.779, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  45%|████▍     | 420/938 [00:29<00:36, 14.07it/s, loss=0.778, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  45%|████▍     | 421/938 [00:29<00:36, 14.07it/s, loss=0.782, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  45%|████▍     | 422/938 [00:29<00:36, 14.07it/s, loss=0.782, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  45%|████▌     | 423/938 [00:30<00:36, 14.08it/s, loss=0.782, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  45%|████▌     | 423/938 [00:30<00:36, 14.08it/s, loss=0.775, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  45%|████▌     | 424/938 [00:30<00:36, 14.08it/s, loss=0.774, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  45%|████▌     | 425/938 [00:30<00:36, 14.08it/s, loss=0.772, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  45%|████▌     | 426/938 [00:30<00:36, 14.08it/s, loss=0.772, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  45%|████▌     | 426/938 [00:30<00:36, 14.08it/s, loss=0.776, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  46%|████▌     | 427/938 [00:30<00:36, 14.09it/s, loss=0.773, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  46%|████▌     | 428/938 [00:30<00:36, 14.08it/s, loss=0.771, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  46%|████▌     | 429/938 [00:30<00:36, 14.08it/s, loss=0.771, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  46%|████▌     | 429/938 [00:30<00:36, 14.08it/s, loss=0.768, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  46%|████▌     | 430/938 [00:30<00:36, 14.09it/s, loss=0.769, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  46%|████▌     | 431/938 [00:30<00:35, 14.09it/s, loss=0.774, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  46%|████▌     | 432/938 [00:30<00:35, 14.09it/s, loss=0.774, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  46%|████▌     | 432/938 [00:30<00:35, 14.09it/s, loss=0.788, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  46%|████▌     | 433/938 [00:30<00:35, 14.09it/s, loss=0.785, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  46%|████▋     | 434/938 [00:30<00:35, 14.10it/s, loss=0.781, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  46%|████▋     | 435/938 [00:30<00:35, 14.10it/s, loss=0.781, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  46%|████▋     | 435/938 [00:30<00:35, 14.10it/s, loss=0.764, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  46%|████▋     | 436/938 [00:30<00:35, 14.10it/s, loss=0.76, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  47%|████▋     | 437/938 [00:30<00:35, 14.10it/s, loss=0.763, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  47%|████▋     | 438/938 [00:31<00:35, 14.10it/s, loss=0.763, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  47%|████▋     | 438/938 [00:31<00:35, 14.10it/s, loss=0.769, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  47%|████▋     | 439/938 [00:31<00:35, 14.10it/s, loss=0.776, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  47%|████▋     | 440/938 [00:31<00:35, 14.11it/s, loss=0.775, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  47%|████▋     | 441/938 [00:31<00:35, 14.02it/s, loss=0.775, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  47%|████▋     | 441/938 [00:31<00:35, 14.02it/s, loss=0.772, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  47%|████▋     | 442/938 [00:31<00:35, 14.02it/s, loss=0.77, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  47%|████▋     | 443/938 [00:31<00:35, 14.02it/s, loss=0.767, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  47%|████▋     | 444/938 [00:31<00:35, 14.01it/s, loss=0.767, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  47%|████▋     | 444/938 [00:31<00:35, 14.01it/s, loss=0.771, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  47%|████▋     | 445/938 [00:31<00:35, 14.02it/s, loss=0.77, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  48%|████▊     | 446/938 [00:31<00:35, 14.02it/s, loss=0.766, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  48%|████▊     | 447/938 [00:31<00:35, 14.01it/s, loss=0.766, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  48%|████▊     | 447/938 [00:31<00:35, 14.01it/s, loss=0.767, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  48%|████▊     | 448/938 [00:31<00:34, 14.02it/s, loss=0.764, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  48%|████▊     | 449/938 [00:32<00:34, 14.02it/s, loss=0.757, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  48%|████▊     | 450/938 [00:32<00:34, 14.03it/s, loss=0.757, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  48%|████▊     | 450/938 [00:32<00:34, 14.03it/s, loss=0.755, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  48%|████▊     | 451/938 [00:32<00:34, 14.03it/s, loss=0.75, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  48%|████▊     | 452/938 [00:32<00:34, 14.03it/s, loss=0.747, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  48%|████▊     | 453/938 [00:32<00:34, 14.03it/s, loss=0.747, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  48%|████▊     | 453/938 [00:32<00:34, 14.03it/s, loss=0.747, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  48%|████▊     | 454/938 [00:32<00:34, 14.03it/s, loss=0.752, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  49%|████▊     | 455/938 [00:32<00:34, 14.04it/s, loss=0.76, v_num=17, val_rmse=0.649, train_rmse=1.250] 
Epoch 1:  49%|████▊     | 456/938 [00:32<00:34, 14.04it/s, loss=0.76, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  49%|████▊     | 456/938 [00:32<00:34, 14.04it/s, loss=0.757, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  49%|████▊     | 457/938 [00:32<00:34, 14.04it/s, loss=0.751, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  49%|████▉     | 458/938 [00:32<00:34, 14.04it/s, loss=0.749, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  49%|████▉     | 459/938 [00:32<00:34, 14.04it/s, loss=0.749, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  49%|████▉     | 459/938 [00:32<00:34, 14.04it/s, loss=0.744, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  49%|████▉     | 460/938 [00:32<00:34, 14.04it/s, loss=0.743, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  49%|████▉     | 461/938 [00:32<00:33, 14.05it/s, loss=0.742, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  49%|████▉     | 462/938 [00:32<00:33, 14.05it/s, loss=0.742, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  49%|████▉     | 462/938 [00:32<00:33, 14.05it/s, loss=0.744, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  49%|████▉     | 463/938 [00:32<00:33, 14.05it/s, loss=0.749, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  49%|████▉     | 464/938 [00:33<00:33, 14.06it/s, loss=0.745, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  50%|████▉     | 465/938 [00:33<00:33, 14.06it/s, loss=0.745, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  50%|████▉     | 465/938 [00:33<00:33, 14.06it/s, loss=0.752, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  50%|████▉     | 466/938 [00:33<00:33, 14.06it/s, loss=0.742, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  50%|████▉     | 467/938 [00:33<00:33, 14.06it/s, loss=0.748, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  50%|████▉     | 468/938 [00:33<00:33, 14.06it/s, loss=0.748, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  50%|████▉     | 468/938 [00:33<00:33, 14.06it/s, loss=0.749, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1:  50%|█████     | 469/938 [00:33<00:33, 14.07it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]
Epoch 1:  50%|█████     | 471/938 [00:33<00:33, 14.10it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:   1%|          | 3/469 [00:00<00:21, 22.18it/s]
Epoch 1:  51%|█████     | 474/938 [00:33<00:32, 14.14it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:   1%|▏         | 6/469 [00:00<00:20, 22.63it/s]
Epoch 1:  51%|█████     | 477/938 [00:33<00:32, 14.18it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:   2%|▏         | 9/469 [00:00<00:19, 23.00it/s]
Epoch 1:  51%|█████     | 480/938 [00:33<00:32, 14.21it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:   3%|▎         | 12/469 [00:00<00:19, 24.04it/s]
Epoch 1:  51%|█████▏    | 483/938 [00:33<00:31, 14.26it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:   3%|▎         | 15/469 [00:00<00:17, 25.48it/s]
Epoch 1:  52%|█████▏    | 486/938 [00:33<00:31, 14.30it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:   4%|▍         | 18/469 [00:00<00:18, 24.53it/s]
Epoch 1:  52%|█████▏    | 489/938 [00:34<00:31, 14.33it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:   4%|▍         | 21/469 [00:00<00:17, 25.32it/s]
Epoch 1:  52%|█████▏    | 492/938 [00:34<00:31, 14.37it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:   5%|▌         | 24/469 [00:00<00:17, 24.95it/s]
Epoch 1:  53%|█████▎    | 495/938 [00:34<00:30, 14.41it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:   6%|▌         | 27/469 [00:01<00:17, 25.55it/s]
Epoch 1:  53%|█████▎    | 498/938 [00:34<00:30, 14.45it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:   6%|▋         | 30/469 [00:01<00:17, 25.47it/s]
Epoch 1:  53%|█████▎    | 501/938 [00:34<00:30, 14.49it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:   7%|▋         | 33/469 [00:01<00:16, 25.92it/s]
Epoch 1:  54%|█████▎    | 504/938 [00:34<00:29, 14.53it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:   8%|▊         | 36/469 [00:01<00:18, 23.74it/s]
Epoch 1:  54%|█████▍    | 507/938 [00:34<00:29, 14.55it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:   8%|▊         | 39/469 [00:01<00:18, 23.59it/s]
Epoch 1:  54%|█████▍    | 510/938 [00:34<00:29, 14.58it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:   9%|▉         | 42/469 [00:01<00:17, 24.25it/s]
Epoch 1:  55%|█████▍    | 513/938 [00:35<00:29, 14.61it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  10%|▉         | 45/469 [00:01<00:18, 22.78it/s]
Epoch 1:  55%|█████▌    | 516/938 [00:35<00:28, 14.64it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  10%|█         | 48/469 [00:01<00:17, 23.48it/s]
Epoch 1:  55%|█████▌    | 519/938 [00:35<00:28, 14.68it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  11%|█         | 51/469 [00:02<00:17, 24.22it/s]
Epoch 1:  56%|█████▌    | 522/938 [00:35<00:28, 14.72it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  12%|█▏        | 54/469 [00:02<00:16, 24.79it/s]
Epoch 1:  56%|█████▌    | 525/938 [00:35<00:27, 14.75it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  12%|█▏        | 57/469 [00:02<00:16, 24.69it/s]
Epoch 1:  56%|█████▋    | 528/938 [00:35<00:27, 14.78it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  13%|█▎        | 60/469 [00:02<00:16, 24.20it/s]
Epoch 1:  57%|█████▋    | 531/938 [00:35<00:27, 14.82it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  13%|█▎        | 63/469 [00:02<00:16, 24.74it/s]
Epoch 1:  57%|█████▋    | 534/938 [00:35<00:27, 14.85it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  14%|█▍        | 66/469 [00:02<00:16, 25.01it/s]
Epoch 1:  57%|█████▋    | 537/938 [00:36<00:26, 14.89it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  15%|█▍        | 69/469 [00:02<00:15, 25.32it/s]
Epoch 1:  58%|█████▊    | 540/938 [00:36<00:26, 14.92it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  15%|█▌        | 72/469 [00:02<00:15, 25.36it/s]
Epoch 1:  58%|█████▊    | 543/938 [00:36<00:26, 14.96it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  16%|█▌        | 75/469 [00:03<00:15, 25.56it/s]
Epoch 1:  58%|█████▊    | 546/938 [00:36<00:26, 14.99it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  17%|█▋        | 78/469 [00:03<00:15, 26.03it/s]
Epoch 1:  59%|█████▊    | 550/938 [00:36<00:25, 15.04it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  17%|█▋        | 81/469 [00:03<00:14, 26.26it/s]

Validating:  18%|█▊        | 84/469 [00:03<00:15, 24.97it/s]
Epoch 1:  59%|█████▉    | 554/938 [00:36<00:25, 15.08it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  19%|█▊        | 87/469 [00:03<00:14, 25.55it/s]
Epoch 1:  59%|█████▉    | 558/938 [00:36<00:25, 15.13it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  19%|█▉        | 90/469 [00:03<00:15, 25.17it/s]
Epoch 1:  60%|█████▉    | 562/938 [00:37<00:24, 15.17it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  20%|█▉        | 93/469 [00:03<00:14, 25.80it/s]

Validating:  20%|██        | 96/469 [00:03<00:14, 25.40it/s]
Epoch 1:  60%|██████    | 566/938 [00:37<00:24, 15.21it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  21%|██        | 99/469 [00:03<00:14, 25.29it/s]
Epoch 1:  61%|██████    | 570/938 [00:37<00:24, 15.26it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  22%|██▏       | 102/469 [00:04<00:14, 26.00it/s]
Epoch 1:  61%|██████    | 574/938 [00:37<00:23, 15.30it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  22%|██▏       | 105/469 [00:04<00:14, 25.98it/s]

Validating:  23%|██▎       | 108/469 [00:04<00:13, 25.85it/s]
Epoch 1:  62%|██████▏   | 578/938 [00:37<00:23, 15.35it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  24%|██▎       | 111/469 [00:04<00:13, 25.82it/s]
Epoch 1:  62%|██████▏   | 582/938 [00:37<00:23, 15.39it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  24%|██▍       | 114/469 [00:04<00:13, 25.84it/s]
Epoch 1:  62%|██████▏   | 586/938 [00:37<00:22, 15.43it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  25%|██▍       | 117/469 [00:04<00:13, 25.89it/s]

Validating:  26%|██▌       | 120/469 [00:04<00:13, 26.57it/s]
Epoch 1:  63%|██████▎   | 590/938 [00:38<00:22, 15.48it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  26%|██▌       | 123/469 [00:04<00:13, 26.51it/s]
Epoch 1:  63%|██████▎   | 594/938 [00:38<00:22, 15.52it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  27%|██▋       | 126/469 [00:05<00:13, 25.63it/s]
Epoch 1:  64%|██████▍   | 598/938 [00:38<00:21, 15.56it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  28%|██▊       | 129/469 [00:05<00:13, 26.10it/s]

Validating:  28%|██▊       | 132/469 [00:05<00:12, 26.64it/s]
Epoch 1:  64%|██████▍   | 602/938 [00:38<00:21, 15.61it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  29%|██▉       | 135/469 [00:05<00:13, 24.15it/s]
Epoch 1:  65%|██████▍   | 606/938 [00:38<00:21, 15.63it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  29%|██▉       | 138/469 [00:05<00:13, 23.81it/s]
Epoch 1:  65%|██████▌   | 610/938 [00:38<00:20, 15.67it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  30%|███       | 141/469 [00:05<00:13, 25.16it/s]

Validating:  31%|███       | 144/469 [00:05<00:12, 25.46it/s]
Epoch 1:  65%|██████▌   | 614/938 [00:39<00:20, 15.71it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  31%|███▏      | 147/469 [00:05<00:12, 25.06it/s]
Epoch 1:  66%|██████▌   | 618/938 [00:39<00:20, 15.75it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  32%|███▏      | 150/469 [00:05<00:12, 25.46it/s]
Epoch 1:  66%|██████▋   | 622/938 [00:39<00:20, 15.79it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  33%|███▎      | 153/469 [00:06<00:12, 25.69it/s]

Validating:  33%|███▎      | 156/469 [00:06<00:12, 25.78it/s]
Epoch 1:  67%|██████▋   | 626/938 [00:39<00:19, 15.83it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  34%|███▍      | 159/469 [00:06<00:12, 25.71it/s]
Epoch 1:  67%|██████▋   | 630/938 [00:39<00:19, 15.87it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  35%|███▍      | 162/469 [00:06<00:12, 25.14it/s]
Epoch 1:  68%|██████▊   | 634/938 [00:39<00:19, 15.90it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  35%|███▌      | 165/469 [00:06<00:12, 24.61it/s]

Validating:  36%|███▌      | 168/469 [00:06<00:11, 25.67it/s]
Epoch 1:  68%|██████▊   | 638/938 [00:40<00:18, 15.94it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  36%|███▋      | 171/469 [00:06<00:11, 25.73it/s]
Epoch 1:  68%|██████▊   | 642/938 [00:40<00:18, 15.98it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  37%|███▋      | 174/469 [00:06<00:12, 24.26it/s]
Epoch 1:  69%|██████▉   | 646/938 [00:40<00:18, 15.99it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  38%|███▊      | 177/469 [00:07<00:12, 22.94it/s]

Validating:  38%|███▊      | 180/469 [00:07<00:12, 23.99it/s]
Epoch 1:  69%|██████▉   | 650/938 [00:40<00:17, 16.04it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  39%|███▉      | 183/469 [00:07<00:11, 24.39it/s]
Epoch 1:  70%|██████▉   | 654/938 [00:40<00:17, 16.07it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  40%|███▉      | 186/469 [00:07<00:11, 25.12it/s]
Epoch 1:  70%|███████   | 658/938 [00:40<00:17, 16.11it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  40%|████      | 189/469 [00:07<00:11, 25.39it/s]

Validating:  41%|████      | 192/469 [00:07<00:10, 26.18it/s]
Epoch 1:  71%|███████   | 662/938 [00:40<00:17, 16.15it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  42%|████▏     | 195/469 [00:07<00:10, 26.39it/s]
Epoch 1:  71%|███████   | 666/938 [00:41<00:16, 16.19it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  42%|████▏     | 198/469 [00:07<00:10, 24.80it/s]
Epoch 1:  71%|███████▏  | 670/938 [00:41<00:16, 16.22it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  43%|████▎     | 201/469 [00:08<00:10, 24.55it/s]

Validating:  43%|████▎     | 204/469 [00:08<00:10, 25.70it/s]
Epoch 1:  72%|███████▏  | 674/938 [00:41<00:16, 16.26it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  44%|████▍     | 207/469 [00:08<00:09, 26.27it/s]
Epoch 1:  72%|███████▏  | 678/938 [00:41<00:15, 16.29it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  45%|████▍     | 210/469 [00:08<00:10, 25.85it/s]
Epoch 1:  73%|███████▎  | 682/938 [00:41<00:15, 16.33it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  45%|████▌     | 213/469 [00:08<00:09, 26.38it/s]

Validating:  46%|████▌     | 216/469 [00:08<00:09, 26.22it/s]
Epoch 1:  73%|███████▎  | 686/938 [00:41<00:15, 16.37it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  47%|████▋     | 219/469 [00:08<00:09, 25.88it/s]
Epoch 1:  74%|███████▎  | 690/938 [00:42<00:15, 16.40it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  47%|████▋     | 222/469 [00:08<00:09, 25.72it/s]
Epoch 1:  74%|███████▍  | 694/938 [00:42<00:14, 16.44it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  48%|████▊     | 225/469 [00:08<00:09, 26.25it/s]

Validating:  49%|████▊     | 228/469 [00:09<00:09, 25.11it/s]
Epoch 1:  74%|███████▍  | 698/938 [00:42<00:14, 16.46it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  49%|████▉     | 231/469 [00:09<00:09, 25.83it/s]
Epoch 1:  75%|███████▍  | 702/938 [00:42<00:14, 16.50it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  50%|████▉     | 234/469 [00:09<00:09, 25.52it/s]
Epoch 1:  75%|███████▌  | 706/938 [00:42<00:14, 16.53it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  51%|█████     | 237/469 [00:09<00:09, 25.25it/s]

Validating:  51%|█████     | 240/469 [00:09<00:08, 25.62it/s]
Epoch 1:  76%|███████▌  | 710/938 [00:42<00:13, 16.57it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  52%|█████▏    | 243/469 [00:09<00:09, 24.37it/s]
Epoch 1:  76%|███████▌  | 714/938 [00:43<00:13, 16.59it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  52%|█████▏    | 246/469 [00:09<00:09, 24.43it/s]
Epoch 1:  77%|███████▋  | 718/938 [00:43<00:13, 16.62it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  53%|█████▎    | 249/469 [00:09<00:08, 25.19it/s]

Validating:  54%|█████▎    | 252/469 [00:10<00:08, 25.03it/s]
Epoch 1:  77%|███████▋  | 722/938 [00:43<00:12, 16.66it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  54%|█████▍    | 255/469 [00:10<00:08, 26.09it/s]
Epoch 1:  77%|███████▋  | 726/938 [00:43<00:12, 16.69it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  55%|█████▌    | 258/469 [00:10<00:08, 26.37it/s]
Epoch 1:  78%|███████▊  | 730/938 [00:43<00:12, 16.73it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  56%|█████▌    | 261/469 [00:10<00:08, 25.77it/s]

Validating:  56%|█████▋    | 264/469 [00:10<00:07, 26.67it/s]
Epoch 1:  78%|███████▊  | 734/938 [00:43<00:12, 16.76it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  57%|█████▋    | 267/469 [00:10<00:07, 26.94it/s]
Epoch 1:  79%|███████▊  | 738/938 [00:43<00:11, 16.80it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  58%|█████▊    | 270/469 [00:10<00:07, 26.42it/s]
Epoch 1:  79%|███████▉  | 742/938 [00:44<00:11, 16.82it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  58%|█████▊    | 273/469 [00:10<00:07, 24.72it/s]

Validating:  59%|█████▉    | 276/469 [00:10<00:07, 25.32it/s]
Epoch 1:  80%|███████▉  | 746/938 [00:44<00:11, 16.85it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  59%|█████▉    | 279/469 [00:11<00:07, 25.25it/s]
Epoch 1:  80%|███████▉  | 750/938 [00:44<00:11, 16.88it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  60%|██████    | 282/469 [00:11<00:07, 24.64it/s]
Epoch 1:  80%|████████  | 754/938 [00:44<00:10, 16.91it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  61%|██████    | 285/469 [00:11<00:07, 25.59it/s]

Validating:  61%|██████▏   | 288/469 [00:11<00:06, 26.01it/s]
Epoch 1:  81%|████████  | 758/938 [00:44<00:10, 16.94it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  62%|██████▏   | 291/469 [00:11<00:07, 24.96it/s]
Epoch 1:  81%|████████  | 762/938 [00:44<00:10, 16.97it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  63%|██████▎   | 294/469 [00:11<00:06, 25.53it/s]
Epoch 1:  82%|████████▏ | 766/938 [00:45<00:10, 17.00it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  63%|██████▎   | 297/469 [00:11<00:06, 25.90it/s]

Validating:  64%|██████▍   | 300/469 [00:11<00:06, 26.83it/s]
Epoch 1:  82%|████████▏ | 770/938 [00:45<00:09, 17.04it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  65%|██████▍   | 303/469 [00:11<00:06, 25.77it/s]
Epoch 1:  83%|████████▎ | 774/938 [00:45<00:09, 17.06it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  65%|██████▌   | 306/469 [00:12<00:06, 25.99it/s]
Epoch 1:  83%|████████▎ | 778/938 [00:45<00:09, 17.10it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  66%|██████▌   | 309/469 [00:12<00:05, 26.69it/s]

Validating:  67%|██████▋   | 312/469 [00:12<00:05, 26.62it/s]
Epoch 1:  83%|████████▎ | 782/938 [00:45<00:09, 17.13it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  67%|██████▋   | 315/469 [00:12<00:05, 26.74it/s]
Epoch 1:  84%|████████▍ | 786/938 [00:45<00:08, 17.16it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  68%|██████▊   | 318/469 [00:12<00:05, 26.23it/s]
Epoch 1:  84%|████████▍ | 790/938 [00:45<00:08, 17.19it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  68%|██████▊   | 321/469 [00:12<00:05, 26.27it/s]

Validating:  69%|██████▉   | 324/469 [00:12<00:05, 25.28it/s]
Epoch 1:  85%|████████▍ | 794/938 [00:46<00:08, 17.21it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  70%|██████▉   | 327/469 [00:12<00:05, 25.35it/s]
Epoch 1:  85%|████████▌ | 798/938 [00:46<00:08, 17.24it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  70%|███████   | 330/469 [00:13<00:05, 24.70it/s]
Epoch 1:  86%|████████▌ | 802/938 [00:46<00:07, 17.27it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  71%|███████   | 333/469 [00:13<00:05, 24.82it/s]

Validating:  72%|███████▏  | 336/469 [00:13<00:05, 24.58it/s]
Epoch 1:  86%|████████▌ | 806/938 [00:46<00:07, 17.29it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  72%|███████▏  | 339/469 [00:13<00:05, 24.86it/s]
Epoch 1:  86%|████████▋ | 810/938 [00:46<00:07, 17.32it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  73%|███████▎  | 342/469 [00:13<00:04, 25.42it/s]
Epoch 1:  87%|████████▋ | 814/938 [00:46<00:07, 17.35it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  74%|███████▎  | 345/469 [00:13<00:04, 25.37it/s]

Validating:  74%|███████▍  | 348/469 [00:13<00:04, 25.90it/s]
Epoch 1:  87%|████████▋ | 818/938 [00:47<00:06, 17.38it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  75%|███████▍  | 351/469 [00:13<00:04, 26.37it/s]
Epoch 1:  88%|████████▊ | 822/938 [00:47<00:06, 17.41it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  75%|███████▌  | 354/469 [00:13<00:04, 26.33it/s]
Epoch 1:  88%|████████▊ | 826/938 [00:47<00:06, 17.44it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  76%|███████▌  | 357/469 [00:14<00:04, 26.70it/s]

Validating:  77%|███████▋  | 360/469 [00:14<00:04, 27.21it/s]
Epoch 1:  88%|████████▊ | 830/938 [00:47<00:06, 17.47it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  77%|███████▋  | 363/469 [00:14<00:03, 27.34it/s]
Epoch 1:  89%|████████▉ | 834/938 [00:47<00:05, 17.50it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  78%|███████▊  | 366/469 [00:14<00:03, 27.67it/s]
Epoch 1:  89%|████████▉ | 838/938 [00:47<00:05, 17.53it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  79%|███████▊  | 369/469 [00:14<00:03, 26.62it/s]

Validating:  79%|███████▉  | 372/469 [00:14<00:03, 26.15it/s]
Epoch 1:  90%|████████▉ | 842/938 [00:47<00:05, 17.55it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  80%|███████▉  | 375/469 [00:14<00:03, 26.59it/s]
Epoch 1:  90%|█████████ | 846/938 [00:48<00:05, 17.59it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  81%|████████  | 378/469 [00:14<00:03, 26.74it/s]
Epoch 1:  91%|█████████ | 850/938 [00:48<00:04, 17.61it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  81%|████████  | 381/469 [00:14<00:03, 26.39it/s]

Validating:  82%|████████▏ | 384/469 [00:15<00:03, 26.72it/s]
Epoch 1:  91%|█████████ | 854/938 [00:48<00:04, 17.64it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  83%|████████▎ | 387/469 [00:15<00:03, 26.53it/s]
Epoch 1:  91%|█████████▏| 858/938 [00:48<00:04, 17.67it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  83%|████████▎ | 390/469 [00:15<00:02, 26.55it/s]
Epoch 1:  92%|█████████▏| 862/938 [00:48<00:04, 17.70it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  84%|████████▍ | 393/469 [00:15<00:02, 26.77it/s]

Validating:  84%|████████▍ | 396/469 [00:15<00:02, 26.13it/s]
Epoch 1:  92%|█████████▏| 866/938 [00:48<00:04, 17.72it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  85%|████████▌ | 399/469 [00:15<00:02, 25.70it/s]
Epoch 1:  93%|█████████▎| 870/938 [00:49<00:03, 17.75it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  86%|████████▌ | 402/469 [00:15<00:02, 25.70it/s]
Epoch 1:  93%|█████████▎| 874/938 [00:49<00:03, 17.77it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  86%|████████▋ | 405/469 [00:15<00:02, 25.68it/s]

Validating:  87%|████████▋ | 408/469 [00:16<00:02, 24.88it/s]
Epoch 1:  94%|█████████▎| 878/938 [00:49<00:03, 17.79it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  88%|████████▊ | 411/469 [00:16<00:02, 25.63it/s]
Epoch 1:  94%|█████████▍| 882/938 [00:49<00:03, 17.82it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  88%|████████▊ | 414/469 [00:16<00:02, 26.41it/s]
Epoch 1:  94%|█████████▍| 886/938 [00:49<00:02, 17.85it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  89%|████████▉ | 417/469 [00:16<00:01, 26.34it/s]

Validating:  90%|████████▉ | 420/469 [00:16<00:01, 25.70it/s]
Epoch 1:  95%|█████████▍| 890/938 [00:49<00:02, 17.87it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  90%|█████████ | 423/469 [00:16<00:01, 25.59it/s]
Epoch 1:  95%|█████████▌| 894/938 [00:49<00:02, 17.89it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  91%|█████████ | 426/469 [00:16<00:01, 25.47it/s]
Epoch 1:  96%|█████████▌| 898/938 [00:50<00:02, 17.92it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  91%|█████████▏| 429/469 [00:16<00:01, 26.03it/s]

Validating:  92%|█████████▏| 432/469 [00:16<00:01, 25.42it/s]
Epoch 1:  96%|█████████▌| 902/938 [00:50<00:02, 17.94it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  93%|█████████▎| 435/469 [00:17<00:01, 25.99it/s]
Epoch 1:  97%|█████████▋| 906/938 [00:50<00:01, 17.96it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  93%|█████████▎| 438/469 [00:17<00:01, 25.61it/s]
Epoch 1:  97%|█████████▋| 910/938 [00:50<00:01, 17.99it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  94%|█████████▍| 441/469 [00:17<00:01, 26.25it/s]

Validating:  95%|█████████▍| 444/469 [00:17<00:00, 25.95it/s]
Epoch 1:  97%|█████████▋| 914/938 [00:50<00:01, 18.02it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  95%|█████████▌| 447/469 [00:17<00:00, 25.78it/s]
Epoch 1:  98%|█████████▊| 918/938 [00:50<00:01, 18.04it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  96%|█████████▌| 450/469 [00:17<00:00, 25.49it/s]
Epoch 1:  98%|█████████▊| 922/938 [00:51<00:00, 18.06it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  97%|█████████▋| 453/469 [00:17<00:00, 25.53it/s]

Validating:  97%|█████████▋| 456/469 [00:17<00:00, 26.27it/s]
Epoch 1:  99%|█████████▊| 926/938 [00:51<00:00, 18.09it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  98%|█████████▊| 459/469 [00:17<00:00, 25.94it/s]
Epoch 1:  99%|█████████▉| 930/938 [00:51<00:00, 18.11it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  99%|█████████▊| 462/469 [00:18<00:00, 26.15it/s]
Epoch 1: 100%|█████████▉| 934/938 [00:51<00:00, 18.13it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]

Validating:  99%|█████████▉| 465/469 [00:18<00:00, 25.76it/s]

Validating: 100%|█████████▉| 468/469 [00:18<00:00, 26.08it/s]
Epoch 1: 100%|██████████| 938/938 [00:51<00:00, 18.16it/s, loss=0.759, v_num=17, val_rmse=0.649, train_rmse=1.250]
Epoch 1: 100%|██████████| 938/938 [00:51<00:00, 18.15it/s, loss=0.759, v_num=17, val_rmse=0.565, train_rmse=1.250]

                                                             
Epoch 1: 100%|██████████| 938/938 [00:51<00:00, 18.14it/s, loss=0.759, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 1:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.759, v_num=17, val_rmse=0.565, train_rmse=0.785]          
Epoch 2:   0%|          | 0/938 [00:00<?, ?it/s, loss=0.759, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   0%|          | 1/938 [00:00<01:20, 11.69it/s, loss=0.758, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   0%|          | 2/938 [00:00<01:19, 11.78it/s, loss=0.76, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:   0%|          | 3/938 [00:00<01:12, 12.96it/s, loss=0.765, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   0%|          | 4/938 [00:00<01:10, 13.16it/s, loss=0.765, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   0%|          | 4/938 [00:00<01:11, 13.14it/s, loss=0.762, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   1%|          | 5/938 [00:00<01:09, 13.43it/s, loss=0.754, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   1%|          | 6/938 [00:00<01:10, 13.30it/s, loss=0.748, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   1%|          | 7/938 [00:00<01:11, 13.11it/s, loss=0.75, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:   1%|          | 8/938 [00:00<01:09, 13.44it/s, loss=0.75, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   1%|          | 8/938 [00:00<01:09, 13.43it/s, loss=0.744, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   1%|          | 9/938 [00:00<01:07, 13.68it/s, loss=0.744, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   1%|          | 10/938 [00:00<01:07, 13.74it/s, loss=0.741, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   1%|          | 11/938 [00:00<01:07, 13.73it/s, loss=0.737, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   1%|▏         | 12/938 [00:00<01:07, 13.74it/s, loss=0.737, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   1%|▏         | 12/938 [00:00<01:07, 13.73it/s, loss=0.73, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:   1%|▏         | 13/938 [00:00<01:07, 13.72it/s, loss=0.729, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   1%|▏         | 14/938 [00:01<01:07, 13.75it/s, loss=0.728, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   2%|▏         | 15/938 [00:01<01:06, 13.78it/s, loss=0.721, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   2%|▏         | 16/938 [00:01<01:06, 13.83it/s, loss=0.721, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   2%|▏         | 16/938 [00:01<01:06, 13.83it/s, loss=0.714, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   2%|▏         | 17/938 [00:01<01:05, 13.95it/s, loss=0.725, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   2%|▏         | 18/938 [00:01<01:04, 14.19it/s, loss=0.716, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   2%|▏         | 19/938 [00:01<01:05, 14.03it/s, loss=0.721, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   2%|▏         | 20/938 [00:01<01:05, 14.07it/s, loss=0.721, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   2%|▏         | 20/938 [00:01<01:05, 14.07it/s, loss=0.711, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   2%|▏         | 21/938 [00:01<01:04, 14.23it/s, loss=0.711, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   2%|▏         | 22/938 [00:01<01:03, 14.33it/s, loss=0.71, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:   2%|▏         | 23/938 [00:01<01:04, 14.29it/s, loss=0.7, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:   3%|▎         | 24/938 [00:01<01:03, 14.34it/s, loss=0.7, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   3%|▎         | 24/938 [00:01<01:03, 14.34it/s, loss=0.71, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   3%|▎         | 25/938 [00:01<01:04, 14.26it/s, loss=0.713, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   3%|▎         | 26/938 [00:01<01:03, 14.33it/s, loss=0.712, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   3%|▎         | 27/938 [00:01<01:03, 14.37it/s, loss=0.716, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   3%|▎         | 28/938 [00:01<01:03, 14.38it/s, loss=0.716, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   3%|▎         | 28/938 [00:01<01:03, 14.38it/s, loss=0.725, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   3%|▎         | 29/938 [00:02<01:03, 14.39it/s, loss=0.729, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   3%|▎         | 30/938 [00:02<01:02, 14.47it/s, loss=0.726, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   3%|▎         | 31/938 [00:02<01:03, 14.38it/s, loss=0.729, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   3%|▎         | 32/938 [00:02<01:02, 14.43it/s, loss=0.729, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   3%|▎         | 32/938 [00:02<01:02, 14.43it/s, loss=0.74, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:   4%|▎         | 33/938 [00:02<01:02, 14.44it/s, loss=0.748, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   4%|▎         | 34/938 [00:02<01:02, 14.49it/s, loss=0.75, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:   4%|▎         | 35/938 [00:02<01:02, 14.44it/s, loss=0.765, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   4%|▍         | 36/938 [00:02<01:02, 14.46it/s, loss=0.765, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   4%|▍         | 36/938 [00:02<01:02, 14.45it/s, loss=0.767, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   4%|▍         | 37/938 [00:02<01:02, 14.41it/s, loss=0.762, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   4%|▍         | 38/938 [00:02<01:02, 14.39it/s, loss=0.759, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   4%|▍         | 39/938 [00:02<01:02, 14.33it/s, loss=0.755, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   4%|▍         | 40/938 [00:02<01:02, 14.43it/s, loss=0.755, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   4%|▍         | 40/938 [00:02<01:02, 14.42it/s, loss=0.758, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   4%|▍         | 41/938 [00:02<01:02, 14.42it/s, loss=0.757, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   4%|▍         | 42/938 [00:02<01:01, 14.47it/s, loss=0.758, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   5%|▍         | 43/938 [00:02<01:01, 14.50it/s, loss=0.76, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:   5%|▍         | 44/938 [00:03<01:01, 14.52it/s, loss=0.76, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   5%|▍         | 44/938 [00:03<01:01, 14.52it/s, loss=0.75, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   5%|▍         | 45/938 [00:03<01:02, 14.27it/s, loss=0.748, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   5%|▍         | 46/938 [00:03<01:02, 14.28it/s, loss=0.749, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   5%|▌         | 47/938 [00:03<01:02, 14.30it/s, loss=0.753, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   5%|▌         | 48/938 [00:03<01:02, 14.30it/s, loss=0.753, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   5%|▌         | 48/938 [00:03<01:02, 14.30it/s, loss=0.759, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   5%|▌         | 49/938 [00:03<01:02, 14.31it/s, loss=0.754, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   5%|▌         | 50/938 [00:03<01:02, 14.28it/s, loss=0.746, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   5%|▌         | 51/938 [00:03<01:02, 14.29it/s, loss=0.743, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   6%|▌         | 52/938 [00:03<01:01, 14.33it/s, loss=0.743, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   6%|▌         | 52/938 [00:03<01:01, 14.32it/s, loss=0.73, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:   6%|▌         | 53/938 [00:03<01:02, 14.27it/s, loss=0.724, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   6%|▌         | 54/938 [00:03<01:02, 14.26it/s, loss=0.723, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   6%|▌         | 55/938 [00:03<01:02, 14.23it/s, loss=0.714, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   6%|▌         | 56/938 [00:03<01:01, 14.28it/s, loss=0.714, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   6%|▌         | 56/938 [00:03<01:01, 14.28it/s, loss=0.714, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   6%|▌         | 57/938 [00:03<01:01, 14.31it/s, loss=0.716, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   6%|▌         | 58/938 [00:04<01:01, 14.31it/s, loss=0.72, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:   6%|▋         | 59/938 [00:04<01:01, 14.32it/s, loss=0.72, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   6%|▋         | 60/938 [00:04<01:01, 14.32it/s, loss=0.72, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   6%|▋         | 60/938 [00:04<01:01, 14.32it/s, loss=0.73, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   7%|▋         | 61/938 [00:04<01:01, 14.29it/s, loss=0.734, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   7%|▋         | 62/938 [00:04<01:01, 14.35it/s, loss=0.733, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   7%|▋         | 63/938 [00:04<01:00, 14.35it/s, loss=0.734, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   7%|▋         | 64/938 [00:04<01:00, 14.35it/s, loss=0.734, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   7%|▋         | 64/938 [00:04<01:00, 14.35it/s, loss=0.73, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:   7%|▋         | 65/938 [00:04<01:00, 14.39it/s, loss=0.732, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   7%|▋         | 66/938 [00:04<01:00, 14.38it/s, loss=0.733, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   7%|▋         | 67/938 [00:04<01:00, 14.37it/s, loss=0.722, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   7%|▋         | 68/938 [00:04<01:00, 14.37it/s, loss=0.722, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   7%|▋         | 68/938 [00:04<01:00, 14.37it/s, loss=0.71, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:   7%|▋         | 69/938 [00:04<01:00, 14.37it/s, loss=0.712, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   7%|▋         | 70/938 [00:04<01:00, 14.38it/s, loss=0.723, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   8%|▊         | 71/938 [00:04<01:00, 14.41it/s, loss=0.724, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   8%|▊         | 72/938 [00:04<01:00, 14.40it/s, loss=0.724, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   8%|▊         | 72/938 [00:05<01:00, 14.40it/s, loss=0.73, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:   8%|▊         | 73/938 [00:05<01:00, 14.41it/s, loss=0.727, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   8%|▊         | 74/938 [00:05<00:59, 14.42it/s, loss=0.721, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   8%|▊         | 75/938 [00:05<00:59, 14.42it/s, loss=0.723, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   8%|▊         | 76/938 [00:05<00:59, 14.40it/s, loss=0.723, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   8%|▊         | 76/938 [00:05<00:59, 14.40it/s, loss=0.708, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   8%|▊         | 77/938 [00:05<00:59, 14.41it/s, loss=0.703, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   8%|▊         | 78/938 [00:05<00:59, 14.43it/s, loss=0.698, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   8%|▊         | 79/938 [00:05<00:59, 14.40it/s, loss=0.698, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   9%|▊         | 80/938 [00:05<00:59, 14.45it/s, loss=0.698, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   9%|▊         | 80/938 [00:05<00:59, 14.45it/s, loss=0.691, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   9%|▊         | 81/938 [00:05<00:59, 14.44it/s, loss=0.689, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   9%|▊         | 82/938 [00:05<00:59, 14.43it/s, loss=0.699, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   9%|▉         | 83/938 [00:05<00:59, 14.46it/s, loss=0.695, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   9%|▉         | 84/938 [00:05<00:58, 14.48it/s, loss=0.695, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   9%|▉         | 84/938 [00:05<00:59, 14.47it/s, loss=0.703, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   9%|▉         | 85/938 [00:05<00:58, 14.47it/s, loss=0.701, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   9%|▉         | 86/938 [00:05<00:58, 14.47it/s, loss=0.695, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   9%|▉         | 87/938 [00:06<00:58, 14.47it/s, loss=0.692, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   9%|▉         | 88/938 [00:06<00:58, 14.43it/s, loss=0.692, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   9%|▉         | 88/938 [00:06<00:58, 14.43it/s, loss=0.703, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:   9%|▉         | 89/938 [00:06<00:58, 14.46it/s, loss=0.702, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  10%|▉         | 90/938 [00:06<00:58, 14.43it/s, loss=0.694, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  10%|▉         | 91/938 [00:06<00:58, 14.43it/s, loss=0.696, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  10%|▉         | 92/938 [00:06<00:58, 14.44it/s, loss=0.696, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  10%|▉         | 92/938 [00:06<00:58, 14.44it/s, loss=0.7, v_num=17, val_rmse=0.565, train_rmse=0.785]  
Epoch 2:  10%|▉         | 93/938 [00:06<00:58, 14.37it/s, loss=0.704, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  10%|█         | 94/938 [00:06<00:58, 14.39it/s, loss=0.706, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  10%|█         | 95/938 [00:06<00:58, 14.36it/s, loss=0.711, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  10%|█         | 96/938 [00:06<00:58, 14.38it/s, loss=0.711, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  10%|█         | 96/938 [00:06<00:58, 14.38it/s, loss=0.723, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  10%|█         | 97/938 [00:06<00:58, 14.37it/s, loss=0.725, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  10%|█         | 98/938 [00:06<00:58, 14.36it/s, loss=0.743, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  11%|█         | 99/938 [00:06<00:58, 14.35it/s, loss=0.748, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  11%|█         | 100/938 [00:06<00:58, 14.34it/s, loss=0.748, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  11%|█         | 100/938 [00:06<00:58, 14.34it/s, loss=0.754, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  11%|█         | 101/938 [00:07<00:58, 14.34it/s, loss=0.751, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  11%|█         | 102/938 [00:07<00:58, 14.35it/s, loss=0.738, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  11%|█         | 103/938 [00:07<00:58, 14.31it/s, loss=0.745, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  11%|█         | 104/938 [00:07<00:58, 14.30it/s, loss=0.745, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  11%|█         | 104/938 [00:07<00:58, 14.30it/s, loss=0.748, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  11%|█         | 105/938 [00:07<00:58, 14.30it/s, loss=0.746, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  11%|█▏        | 106/938 [00:07<00:58, 14.31it/s, loss=0.749, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  11%|█▏        | 107/938 [00:07<00:58, 14.32it/s, loss=0.754, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  12%|█▏        | 108/938 [00:07<00:57, 14.32it/s, loss=0.754, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  12%|█▏        | 108/938 [00:07<00:57, 14.32it/s, loss=0.751, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  12%|█▏        | 109/938 [00:07<00:57, 14.30it/s, loss=0.75, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  12%|█▏        | 110/938 [00:07<00:57, 14.31it/s, loss=0.753, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  12%|█▏        | 111/938 [00:07<00:57, 14.31it/s, loss=0.752, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  12%|█▏        | 112/938 [00:07<00:57, 14.30it/s, loss=0.752, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  12%|█▏        | 112/938 [00:07<00:57, 14.30it/s, loss=0.752, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  12%|█▏        | 113/938 [00:07<00:57, 14.30it/s, loss=0.751, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  12%|█▏        | 114/938 [00:07<00:57, 14.31it/s, loss=0.763, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  12%|█▏        | 115/938 [00:08<00:57, 14.30it/s, loss=0.753, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  12%|█▏        | 116/938 [00:08<00:57, 14.32it/s, loss=0.753, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  12%|█▏        | 116/938 [00:08<00:57, 14.32it/s, loss=0.758, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  12%|█▏        | 117/938 [00:08<00:57, 14.31it/s, loss=0.767, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  13%|█▎        | 118/938 [00:08<00:57, 14.33it/s, loss=0.758, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  13%|█▎        | 119/938 [00:08<00:57, 14.33it/s, loss=0.752, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  13%|█▎        | 120/938 [00:08<00:57, 14.30it/s, loss=0.752, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  13%|█▎        | 120/938 [00:08<00:57, 14.30it/s, loss=0.747, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  13%|█▎        | 121/938 [00:08<00:57, 14.25it/s, loss=0.748, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  13%|█▎        | 122/938 [00:08<00:57, 14.25it/s, loss=0.75, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  13%|█▎        | 123/938 [00:08<00:57, 14.29it/s, loss=0.75, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  13%|█▎        | 124/938 [00:08<00:56, 14.30it/s, loss=0.75, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  13%|█▎        | 124/938 [00:08<00:56, 14.30it/s, loss=0.743, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  13%|█▎        | 125/938 [00:08<00:56, 14.29it/s, loss=0.755, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  13%|█▎        | 126/938 [00:08<00:56, 14.32it/s, loss=0.757, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  14%|█▎        | 127/938 [00:08<00:56, 14.33it/s, loss=0.764, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  14%|█▎        | 128/938 [00:08<00:56, 14.31it/s, loss=0.764, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  14%|█▎        | 128/938 [00:08<00:56, 14.31it/s, loss=0.757, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  14%|█▍        | 129/938 [00:09<00:56, 14.32it/s, loss=0.765, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  14%|█▍        | 130/938 [00:09<00:56, 14.31it/s, loss=0.768, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  14%|█▍        | 131/938 [00:09<00:56, 14.31it/s, loss=0.764, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  14%|█▍        | 132/938 [00:09<00:56, 14.33it/s, loss=0.764, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  14%|█▍        | 132/938 [00:09<00:56, 14.33it/s, loss=0.755, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  14%|█▍        | 133/938 [00:09<00:56, 14.32it/s, loss=0.755, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  14%|█▍        | 134/938 [00:09<00:56, 14.32it/s, loss=0.74, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  14%|█▍        | 135/938 [00:09<00:56, 14.33it/s, loss=0.746, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  14%|█▍        | 136/938 [00:09<00:56, 14.31it/s, loss=0.746, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  14%|█▍        | 136/938 [00:09<00:56, 14.31it/s, loss=0.738, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  15%|█▍        | 137/938 [00:09<00:56, 14.30it/s, loss=0.734, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  15%|█▍        | 138/938 [00:09<00:55, 14.30it/s, loss=0.725, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  15%|█▍        | 139/938 [00:09<00:55, 14.29it/s, loss=0.718, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  15%|█▍        | 140/938 [00:09<00:55, 14.28it/s, loss=0.718, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  15%|█▍        | 140/938 [00:09<00:55, 14.28it/s, loss=0.713, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  15%|█▌        | 141/938 [00:09<00:55, 14.28it/s, loss=0.711, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  15%|█▌        | 142/938 [00:09<00:55, 14.29it/s, loss=0.717, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  15%|█▌        | 143/938 [00:10<00:55, 14.29it/s, loss=0.716, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  15%|█▌        | 144/938 [00:10<00:55, 14.28it/s, loss=0.716, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  15%|█▌        | 144/938 [00:10<00:55, 14.28it/s, loss=0.718, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  15%|█▌        | 145/938 [00:10<00:55, 14.29it/s, loss=0.702, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  16%|█▌        | 146/938 [00:10<00:55, 14.30it/s, loss=0.699, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  16%|█▌        | 147/938 [00:10<00:55, 14.29it/s, loss=0.695, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  16%|█▌        | 148/938 [00:10<00:55, 14.29it/s, loss=0.695, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  16%|█▌        | 148/938 [00:10<00:55, 14.29it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  16%|█▌        | 149/938 [00:10<00:55, 14.30it/s, loss=0.693, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  16%|█▌        | 150/938 [00:10<00:55, 14.30it/s, loss=0.689, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  16%|█▌        | 151/938 [00:10<00:55, 14.28it/s, loss=0.694, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  16%|█▌        | 152/938 [00:10<00:54, 14.30it/s, loss=0.694, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  16%|█▌        | 152/938 [00:10<00:54, 14.30it/s, loss=0.698, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  16%|█▋        | 153/938 [00:10<00:54, 14.29it/s, loss=0.704, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  16%|█▋        | 154/938 [00:10<00:54, 14.29it/s, loss=0.713, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  17%|█▋        | 155/938 [00:10<00:54, 14.29it/s, loss=0.717, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  17%|█▋        | 156/938 [00:10<00:54, 14.29it/s, loss=0.717, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  17%|█▋        | 156/938 [00:10<00:54, 14.29it/s, loss=0.712, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  17%|█▋        | 157/938 [00:10<00:54, 14.29it/s, loss=0.712, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  17%|█▋        | 158/938 [00:11<00:54, 14.31it/s, loss=0.722, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  17%|█▋        | 159/938 [00:11<00:54, 14.30it/s, loss=0.729, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  17%|█▋        | 160/938 [00:11<00:54, 14.32it/s, loss=0.729, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  17%|█▋        | 160/938 [00:11<00:54, 14.31it/s, loss=0.732, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  17%|█▋        | 161/938 [00:11<00:54, 14.31it/s, loss=0.744, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  17%|█▋        | 162/938 [00:11<00:54, 14.30it/s, loss=0.748, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  17%|█▋        | 163/938 [00:11<00:54, 14.31it/s, loss=0.745, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  17%|█▋        | 164/938 [00:11<00:54, 14.30it/s, loss=0.745, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  17%|█▋        | 164/938 [00:11<00:54, 14.30it/s, loss=0.743, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  18%|█▊        | 165/938 [00:11<00:54, 14.31it/s, loss=0.748, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  18%|█▊        | 166/938 [00:11<00:53, 14.32it/s, loss=0.753, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  18%|█▊        | 167/938 [00:11<00:53, 14.34it/s, loss=0.751, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  18%|█▊        | 168/938 [00:11<00:53, 14.35it/s, loss=0.751, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  18%|█▊        | 168/938 [00:11<00:53, 14.35it/s, loss=0.749, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  18%|█▊        | 169/938 [00:11<00:53, 14.34it/s, loss=0.752, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  18%|█▊        | 170/938 [00:11<00:53, 14.35it/s, loss=0.764, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  18%|█▊        | 171/938 [00:11<00:53, 14.35it/s, loss=0.759, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  18%|█▊        | 172/938 [00:11<00:53, 14.35it/s, loss=0.759, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  18%|█▊        | 172/938 [00:11<00:53, 14.35it/s, loss=0.755, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  18%|█▊        | 173/938 [00:12<00:53, 14.36it/s, loss=0.745, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  19%|█▊        | 174/938 [00:12<00:53, 14.36it/s, loss=0.744, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  19%|█▊        | 175/938 [00:12<00:53, 14.36it/s, loss=0.738, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  19%|█▉        | 176/938 [00:12<00:53, 14.37it/s, loss=0.738, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  19%|█▉        | 176/938 [00:12<00:53, 14.36it/s, loss=0.75, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  19%|█▉        | 177/938 [00:12<00:52, 14.38it/s, loss=0.744, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  19%|█▉        | 178/938 [00:12<00:52, 14.38it/s, loss=0.739, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  19%|█▉        | 179/938 [00:12<00:52, 14.39it/s, loss=0.737, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  19%|█▉        | 180/938 [00:12<00:52, 14.39it/s, loss=0.737, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  19%|█▉        | 180/938 [00:12<00:52, 14.39it/s, loss=0.734, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  19%|█▉        | 181/938 [00:12<00:52, 14.40it/s, loss=0.728, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  19%|█▉        | 182/938 [00:12<00:52, 14.41it/s, loss=0.721, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  20%|█▉        | 183/938 [00:12<00:52, 14.40it/s, loss=0.722, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  20%|█▉        | 184/938 [00:12<00:52, 14.40it/s, loss=0.722, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  20%|█▉        | 184/938 [00:12<00:52, 14.40it/s, loss=0.718, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  20%|█▉        | 185/938 [00:12<00:52, 14.40it/s, loss=0.72, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  20%|█▉        | 186/938 [00:12<00:52, 14.41it/s, loss=0.713, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  20%|█▉        | 187/938 [00:12<00:52, 14.42it/s, loss=0.719, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  20%|██        | 188/938 [00:13<00:52, 14.42it/s, loss=0.719, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  20%|██        | 188/938 [00:13<00:52, 14.42it/s, loss=0.726, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  20%|██        | 189/938 [00:13<00:52, 14.38it/s, loss=0.729, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  20%|██        | 190/938 [00:13<00:52, 14.36it/s, loss=0.727, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  20%|██        | 191/938 [00:13<00:51, 14.39it/s, loss=0.733, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  20%|██        | 192/938 [00:13<00:51, 14.39it/s, loss=0.733, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  20%|██        | 192/938 [00:13<00:51, 14.39it/s, loss=0.734, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  21%|██        | 193/938 [00:13<00:51, 14.40it/s, loss=0.736, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  21%|██        | 194/938 [00:13<00:51, 14.39it/s, loss=0.733, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  21%|██        | 195/938 [00:13<00:51, 14.39it/s, loss=0.734, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  21%|██        | 196/938 [00:13<00:51, 14.39it/s, loss=0.734, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  21%|██        | 196/938 [00:13<00:51, 14.39it/s, loss=0.729, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  21%|██        | 197/938 [00:13<00:51, 14.39it/s, loss=0.737, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  21%|██        | 198/938 [00:13<00:51, 14.39it/s, loss=0.734, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  21%|██        | 199/938 [00:13<00:51, 14.39it/s, loss=0.735, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  21%|██▏       | 200/938 [00:13<00:51, 14.40it/s, loss=0.735, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  21%|██▏       | 200/938 [00:13<00:51, 14.40it/s, loss=0.741, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  21%|██▏       | 201/938 [00:13<00:51, 14.41it/s, loss=0.74, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  22%|██▏       | 202/938 [00:14<00:51, 14.41it/s, loss=0.746, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  22%|██▏       | 203/938 [00:14<00:50, 14.42it/s, loss=0.746, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  22%|██▏       | 204/938 [00:14<00:50, 14.42it/s, loss=0.746, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  22%|██▏       | 204/938 [00:14<00:50, 14.42it/s, loss=0.755, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  22%|██▏       | 205/938 [00:14<00:50, 14.41it/s, loss=0.753, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  22%|██▏       | 206/938 [00:14<00:50, 14.41it/s, loss=0.759, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  22%|██▏       | 207/938 [00:14<00:50, 14.42it/s, loss=0.751, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  22%|██▏       | 208/938 [00:14<00:50, 14.42it/s, loss=0.751, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  22%|██▏       | 208/938 [00:14<00:50, 14.42it/s, loss=0.746, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  22%|██▏       | 209/938 [00:14<00:50, 14.43it/s, loss=0.733, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  22%|██▏       | 210/938 [00:14<00:50, 14.43it/s, loss=0.726, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  22%|██▏       | 211/938 [00:14<00:50, 14.43it/s, loss=0.726, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  23%|██▎       | 212/938 [00:14<00:50, 14.44it/s, loss=0.726, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  23%|██▎       | 212/938 [00:14<00:50, 14.44it/s, loss=0.731, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  23%|██▎       | 213/938 [00:14<00:50, 14.43it/s, loss=0.737, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  23%|██▎       | 214/938 [00:14<00:50, 14.44it/s, loss=0.731, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  23%|██▎       | 215/938 [00:14<00:50, 14.44it/s, loss=0.738, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  23%|██▎       | 216/938 [00:14<00:49, 14.45it/s, loss=0.738, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  23%|██▎       | 216/938 [00:14<00:49, 14.45it/s, loss=0.737, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  23%|██▎       | 217/938 [00:15<00:49, 14.46it/s, loss=0.73, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  23%|██▎       | 218/938 [00:15<00:49, 14.46it/s, loss=0.731, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  23%|██▎       | 219/938 [00:15<00:49, 14.46it/s, loss=0.729, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  23%|██▎       | 220/938 [00:15<00:49, 14.46it/s, loss=0.729, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  23%|██▎       | 220/938 [00:15<00:49, 14.46it/s, loss=0.719, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  24%|██▎       | 221/938 [00:15<00:49, 14.46it/s, loss=0.722, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  24%|██▎       | 222/938 [00:15<00:49, 14.47it/s, loss=0.724, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  24%|██▍       | 223/938 [00:15<00:49, 14.46it/s, loss=0.728, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  24%|██▍       | 224/938 [00:15<00:49, 14.47it/s, loss=0.728, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  24%|██▍       | 224/938 [00:15<00:49, 14.47it/s, loss=0.728, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  24%|██▍       | 225/938 [00:15<00:49, 14.47it/s, loss=0.727, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  24%|██▍       | 226/938 [00:15<00:49, 14.47it/s, loss=0.727, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  24%|██▍       | 227/938 [00:15<00:49, 14.48it/s, loss=0.74, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  24%|██▍       | 228/938 [00:15<00:49, 14.43it/s, loss=0.74, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  24%|██▍       | 228/938 [00:15<00:49, 14.43it/s, loss=0.739, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  24%|██▍       | 229/938 [00:15<00:49, 14.42it/s, loss=0.747, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  25%|██▍       | 230/938 [00:15<00:49, 14.41it/s, loss=0.743, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  25%|██▍       | 231/938 [00:16<00:49, 14.42it/s, loss=0.743, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  25%|██▍       | 232/938 [00:16<00:48, 14.42it/s, loss=0.743, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  25%|██▍       | 232/938 [00:16<00:48, 14.41it/s, loss=0.735, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  25%|██▍       | 233/938 [00:16<00:48, 14.41it/s, loss=0.728, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  25%|██▍       | 234/938 [00:16<00:48, 14.42it/s, loss=0.737, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  25%|██▌       | 235/938 [00:16<00:48, 14.42it/s, loss=0.724, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  25%|██▌       | 236/938 [00:16<00:48, 14.42it/s, loss=0.724, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  25%|██▌       | 236/938 [00:16<00:48, 14.42it/s, loss=0.73, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  25%|██▌       | 237/938 [00:16<00:48, 14.43it/s, loss=0.728, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  25%|██▌       | 238/938 [00:16<00:48, 14.44it/s, loss=0.734, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  25%|██▌       | 239/938 [00:16<00:48, 14.43it/s, loss=0.734, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  26%|██▌       | 240/938 [00:16<00:48, 14.44it/s, loss=0.734, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  26%|██▌       | 240/938 [00:16<00:48, 14.44it/s, loss=0.745, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  26%|██▌       | 241/938 [00:16<00:48, 14.44it/s, loss=0.741, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  26%|██▌       | 242/938 [00:16<00:48, 14.43it/s, loss=0.731, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  26%|██▌       | 243/938 [00:16<00:48, 14.44it/s, loss=0.73, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  26%|██▌       | 244/938 [00:16<00:48, 14.44it/s, loss=0.73, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  26%|██▌       | 244/938 [00:16<00:48, 14.44it/s, loss=0.729, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  26%|██▌       | 245/938 [00:16<00:48, 14.43it/s, loss=0.734, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  26%|██▌       | 246/938 [00:17<00:47, 14.42it/s, loss=0.735, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  26%|██▋       | 247/938 [00:17<00:47, 14.43it/s, loss=0.72, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  26%|██▋       | 248/938 [00:17<00:47, 14.44it/s, loss=0.72, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  26%|██▋       | 248/938 [00:17<00:47, 14.44it/s, loss=0.719, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  27%|██▋       | 249/938 [00:17<00:47, 14.43it/s, loss=0.714, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  27%|██▋       | 250/938 [00:17<00:47, 14.44it/s, loss=0.719, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  27%|██▋       | 251/938 [00:17<00:47, 14.43it/s, loss=0.714, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  27%|██▋       | 252/938 [00:17<00:47, 14.42it/s, loss=0.714, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  27%|██▋       | 252/938 [00:17<00:47, 14.42it/s, loss=0.717, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  27%|██▋       | 253/938 [00:17<00:47, 14.43it/s, loss=0.715, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  27%|██▋       | 254/938 [00:17<00:47, 14.43it/s, loss=0.729, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  27%|██▋       | 255/938 [00:17<00:47, 14.43it/s, loss=0.734, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  27%|██▋       | 256/938 [00:17<00:47, 14.43it/s, loss=0.734, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  27%|██▋       | 256/938 [00:17<00:47, 14.43it/s, loss=0.734, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  27%|██▋       | 257/938 [00:17<00:47, 14.42it/s, loss=0.737, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  28%|██▊       | 258/938 [00:17<00:47, 14.42it/s, loss=0.731, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  28%|██▊       | 259/938 [00:17<00:47, 14.41it/s, loss=0.731, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  28%|██▊       | 260/938 [00:18<00:47, 14.42it/s, loss=0.731, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  28%|██▊       | 260/938 [00:18<00:47, 14.42it/s, loss=0.723, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  28%|██▊       | 261/938 [00:18<00:46, 14.42it/s, loss=0.716, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  28%|██▊       | 262/938 [00:18<00:46, 14.42it/s, loss=0.723, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  28%|██▊       | 263/938 [00:18<00:46, 14.42it/s, loss=0.719, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  28%|██▊       | 264/938 [00:18<00:46, 14.43it/s, loss=0.719, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  28%|██▊       | 264/938 [00:18<00:46, 14.43it/s, loss=0.721, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  28%|██▊       | 265/938 [00:18<00:46, 14.43it/s, loss=0.724, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  28%|██▊       | 266/938 [00:18<00:46, 14.42it/s, loss=0.724, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  28%|██▊       | 267/938 [00:18<00:46, 14.42it/s, loss=0.726, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  29%|██▊       | 268/938 [00:18<00:46, 14.42it/s, loss=0.726, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  29%|██▊       | 268/938 [00:18<00:46, 14.42it/s, loss=0.74, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  29%|██▊       | 269/938 [00:18<00:46, 14.43it/s, loss=0.743, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  29%|██▉       | 270/938 [00:18<00:46, 14.42it/s, loss=0.744, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  29%|██▉       | 271/938 [00:18<00:46, 14.42it/s, loss=0.75, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  29%|██▉       | 272/938 [00:18<00:46, 14.43it/s, loss=0.75, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  29%|██▉       | 272/938 [00:18<00:46, 14.42it/s, loss=0.757, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  29%|██▉       | 273/938 [00:18<00:46, 14.43it/s, loss=0.763, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  29%|██▉       | 274/938 [00:18<00:46, 14.43it/s, loss=0.742, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  29%|██▉       | 275/938 [00:19<00:45, 14.44it/s, loss=0.745, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  29%|██▉       | 276/938 [00:19<00:45, 14.44it/s, loss=0.745, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  29%|██▉       | 276/938 [00:19<00:45, 14.44it/s, loss=0.736, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  30%|██▉       | 277/938 [00:19<00:45, 14.44it/s, loss=0.737, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  30%|██▉       | 278/938 [00:19<00:45, 14.44it/s, loss=0.744, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  30%|██▉       | 279/938 [00:19<00:45, 14.45it/s, loss=0.746, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  30%|██▉       | 280/938 [00:19<00:45, 14.45it/s, loss=0.746, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  30%|██▉       | 280/938 [00:19<00:45, 14.45it/s, loss=0.756, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  30%|██▉       | 281/938 [00:19<00:45, 14.45it/s, loss=0.761, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  30%|███       | 282/938 [00:19<00:45, 14.46it/s, loss=0.752, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  30%|███       | 283/938 [00:19<00:45, 14.45it/s, loss=0.747, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  30%|███       | 284/938 [00:19<00:45, 14.44it/s, loss=0.747, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  30%|███       | 284/938 [00:19<00:45, 14.44it/s, loss=0.738, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  30%|███       | 285/938 [00:19<00:45, 14.45it/s, loss=0.736, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  30%|███       | 286/938 [00:19<00:45, 14.44it/s, loss=0.726, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  31%|███       | 287/938 [00:19<00:45, 14.44it/s, loss=0.73, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  31%|███       | 288/938 [00:19<00:44, 14.45it/s, loss=0.73, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  31%|███       | 288/938 [00:19<00:44, 14.45it/s, loss=0.722, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  31%|███       | 289/938 [00:20<00:44, 14.45it/s, loss=0.716, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  31%|███       | 290/938 [00:20<00:44, 14.44it/s, loss=0.718, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  31%|███       | 291/938 [00:20<00:44, 14.46it/s, loss=0.712, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  31%|███       | 292/938 [00:20<00:44, 14.46it/s, loss=0.712, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  31%|███       | 292/938 [00:20<00:44, 14.46it/s, loss=0.705, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  31%|███       | 293/938 [00:20<00:44, 14.46it/s, loss=0.699, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  31%|███▏      | 294/938 [00:20<00:44, 14.46it/s, loss=0.7, v_num=17, val_rmse=0.565, train_rmse=0.785]  
Epoch 2:  31%|███▏      | 295/938 [00:20<00:44, 14.46it/s, loss=0.695, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  32%|███▏      | 296/938 [00:20<00:44, 14.46it/s, loss=0.695, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  32%|███▏      | 296/938 [00:20<00:44, 14.46it/s, loss=0.707, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  32%|███▏      | 297/938 [00:20<00:44, 14.46it/s, loss=0.716, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  32%|███▏      | 298/938 [00:20<00:44, 14.45it/s, loss=0.713, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  32%|███▏      | 299/938 [00:20<00:44, 14.45it/s, loss=0.706, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  32%|███▏      | 300/938 [00:20<00:44, 14.45it/s, loss=0.706, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  32%|███▏      | 300/938 [00:20<00:44, 14.45it/s, loss=0.693, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  32%|███▏      | 301/938 [00:20<00:44, 14.46it/s, loss=0.701, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  32%|███▏      | 302/938 [00:20<00:43, 14.47it/s, loss=0.696, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  32%|███▏      | 303/938 [00:20<00:43, 14.47it/s, loss=0.704, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  32%|███▏      | 304/938 [00:21<00:43, 14.46it/s, loss=0.704, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  32%|███▏      | 304/938 [00:21<00:43, 14.46it/s, loss=0.71, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  33%|███▎      | 305/938 [00:21<00:43, 14.46it/s, loss=0.711, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  33%|███▎      | 306/938 [00:21<00:43, 14.46it/s, loss=0.722, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  33%|███▎      | 307/938 [00:21<00:43, 14.46it/s, loss=0.718, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  33%|███▎      | 308/938 [00:21<00:43, 14.45it/s, loss=0.718, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  33%|███▎      | 308/938 [00:21<00:43, 14.45it/s, loss=0.722, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  33%|███▎      | 309/938 [00:21<00:43, 14.45it/s, loss=0.731, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  33%|███▎      | 310/938 [00:21<00:43, 14.44it/s, loss=0.722, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  33%|███▎      | 311/938 [00:21<00:43, 14.44it/s, loss=0.721, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  33%|███▎      | 312/938 [00:21<00:43, 14.44it/s, loss=0.721, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  33%|███▎      | 312/938 [00:21<00:43, 14.44it/s, loss=0.719, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  33%|███▎      | 313/938 [00:21<00:43, 14.44it/s, loss=0.726, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  33%|███▎      | 314/938 [00:21<00:43, 14.43it/s, loss=0.725, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  34%|███▎      | 315/938 [00:21<00:43, 14.42it/s, loss=0.728, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  34%|███▎      | 316/938 [00:21<00:43, 14.42it/s, loss=0.728, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  34%|███▎      | 316/938 [00:21<00:43, 14.42it/s, loss=0.722, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  34%|███▍      | 317/938 [00:21<00:43, 14.41it/s, loss=0.707, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  34%|███▍      | 318/938 [00:22<00:43, 14.42it/s, loss=0.706, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  34%|███▍      | 319/938 [00:22<00:42, 14.42it/s, loss=0.716, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  34%|███▍      | 320/938 [00:22<00:42, 14.43it/s, loss=0.716, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  34%|███▍      | 320/938 [00:22<00:42, 14.43it/s, loss=0.719, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  34%|███▍      | 321/938 [00:22<00:42, 14.43it/s, loss=0.704, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  34%|███▍      | 322/938 [00:22<00:42, 14.43it/s, loss=0.709, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  34%|███▍      | 323/938 [00:22<00:42, 14.43it/s, loss=0.711, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  35%|███▍      | 324/938 [00:22<00:42, 14.44it/s, loss=0.711, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  35%|███▍      | 324/938 [00:22<00:42, 14.44it/s, loss=0.719, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  35%|███▍      | 325/938 [00:22<00:42, 14.44it/s, loss=0.715, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  35%|███▍      | 326/938 [00:22<00:42, 14.44it/s, loss=0.702, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  35%|███▍      | 327/938 [00:22<00:42, 14.45it/s, loss=0.705, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  35%|███▍      | 328/938 [00:22<00:42, 14.45it/s, loss=0.705, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  35%|███▍      | 328/938 [00:22<00:42, 14.45it/s, loss=0.718, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  35%|███▌      | 329/938 [00:22<00:42, 14.45it/s, loss=0.714, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  35%|███▌      | 330/938 [00:22<00:42, 14.44it/s, loss=0.726, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  35%|███▌      | 331/938 [00:22<00:42, 14.44it/s, loss=0.737, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  35%|███▌      | 332/938 [00:22<00:41, 14.44it/s, loss=0.737, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  35%|███▌      | 332/938 [00:22<00:41, 14.44it/s, loss=0.748, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  36%|███▌      | 333/938 [00:23<00:41, 14.44it/s, loss=0.745, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  36%|███▌      | 334/938 [00:23<00:41, 14.42it/s, loss=0.751, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  36%|███▌      | 335/938 [00:23<00:41, 14.42it/s, loss=0.752, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  36%|███▌      | 336/938 [00:23<00:41, 14.41it/s, loss=0.752, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  36%|███▌      | 336/938 [00:23<00:41, 14.41it/s, loss=0.752, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  36%|███▌      | 337/938 [00:23<00:41, 14.42it/s, loss=0.758, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  36%|███▌      | 338/938 [00:23<00:41, 14.42it/s, loss=0.761, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  36%|███▌      | 339/938 [00:23<00:41, 14.41it/s, loss=0.755, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  36%|███▌      | 340/938 [00:23<00:41, 14.42it/s, loss=0.755, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  36%|███▌      | 340/938 [00:23<00:41, 14.42it/s, loss=0.756, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  36%|███▋      | 341/938 [00:23<00:41, 14.42it/s, loss=0.761, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  36%|███▋      | 342/938 [00:23<00:41, 14.42it/s, loss=0.764, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  37%|███▋      | 343/938 [00:23<00:41, 14.41it/s, loss=0.76, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  37%|███▋      | 344/938 [00:23<00:41, 14.41it/s, loss=0.76, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  37%|███▋      | 344/938 [00:23<00:41, 14.41it/s, loss=0.749, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  37%|███▋      | 345/938 [00:23<00:41, 14.41it/s, loss=0.751, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  37%|███▋      | 346/938 [00:24<00:41, 14.41it/s, loss=0.758, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  37%|███▋      | 347/938 [00:24<00:41, 14.41it/s, loss=0.753, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  37%|███▋      | 348/938 [00:24<00:40, 14.40it/s, loss=0.753, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  37%|███▋      | 348/938 [00:24<00:40, 14.40it/s, loss=0.739, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  37%|███▋      | 349/938 [00:24<00:40, 14.39it/s, loss=0.736, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  37%|███▋      | 350/938 [00:24<00:40, 14.39it/s, loss=0.725, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  37%|███▋      | 351/938 [00:24<00:40, 14.39it/s, loss=0.718, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  38%|███▊      | 352/938 [00:24<00:40, 14.39it/s, loss=0.718, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  38%|███▊      | 352/938 [00:24<00:40, 14.39it/s, loss=0.711, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  38%|███▊      | 353/938 [00:24<00:40, 14.38it/s, loss=0.704, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  38%|███▊      | 354/938 [00:24<00:40, 14.39it/s, loss=0.706, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  38%|███▊      | 355/938 [00:24<00:40, 14.39it/s, loss=0.707, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  38%|███▊      | 356/938 [00:24<00:40, 14.39it/s, loss=0.707, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  38%|███▊      | 356/938 [00:24<00:40, 14.38it/s, loss=0.696, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  38%|███▊      | 357/938 [00:24<00:40, 14.39it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  38%|███▊      | 358/938 [00:24<00:40, 14.38it/s, loss=0.69, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  38%|███▊      | 359/938 [00:24<00:40, 14.39it/s, loss=0.69, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  38%|███▊      | 360/938 [00:25<00:40, 14.39it/s, loss=0.69, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  38%|███▊      | 360/938 [00:25<00:40, 14.39it/s, loss=0.688, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  38%|███▊      | 361/938 [00:25<00:40, 14.38it/s, loss=0.69, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  39%|███▊      | 362/938 [00:25<00:40, 14.39it/s, loss=0.684, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  39%|███▊      | 363/938 [00:25<00:39, 14.39it/s, loss=0.683, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  39%|███▉      | 364/938 [00:25<00:39, 14.39it/s, loss=0.683, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  39%|███▉      | 364/938 [00:25<00:39, 14.39it/s, loss=0.683, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  39%|███▉      | 365/938 [00:25<00:39, 14.38it/s, loss=0.679, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  39%|███▉      | 366/938 [00:25<00:39, 14.39it/s, loss=0.682, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  39%|███▉      | 367/938 [00:25<00:39, 14.39it/s, loss=0.684, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  39%|███▉      | 368/938 [00:25<00:39, 14.39it/s, loss=0.684, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  39%|███▉      | 368/938 [00:25<00:39, 14.39it/s, loss=0.674, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  39%|███▉      | 369/938 [00:25<00:39, 14.38it/s, loss=0.681, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  39%|███▉      | 370/938 [00:25<00:39, 14.36it/s, loss=0.674, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  40%|███▉      | 371/938 [00:25<00:39, 14.37it/s, loss=0.673, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  40%|███▉      | 372/938 [00:25<00:39, 14.36it/s, loss=0.673, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  40%|███▉      | 372/938 [00:25<00:39, 14.36it/s, loss=0.674, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  40%|███▉      | 373/938 [00:25<00:39, 14.36it/s, loss=0.678, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  40%|███▉      | 374/938 [00:26<00:39, 14.37it/s, loss=0.676, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  40%|███▉      | 375/938 [00:26<00:39, 14.36it/s, loss=0.677, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  40%|████      | 376/938 [00:26<00:39, 14.36it/s, loss=0.677, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  40%|████      | 376/938 [00:26<00:39, 14.36it/s, loss=0.681, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  40%|████      | 377/938 [00:26<00:39, 14.36it/s, loss=0.681, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  40%|████      | 378/938 [00:26<00:39, 14.35it/s, loss=0.674, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  40%|████      | 379/938 [00:26<00:38, 14.35it/s, loss=0.674, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  41%|████      | 380/938 [00:26<00:38, 14.35it/s, loss=0.674, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  41%|████      | 380/938 [00:26<00:38, 14.35it/s, loss=0.677, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  41%|████      | 381/938 [00:26<00:38, 14.35it/s, loss=0.672, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  41%|████      | 382/938 [00:26<00:38, 14.34it/s, loss=0.689, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  41%|████      | 383/938 [00:26<00:38, 14.34it/s, loss=0.695, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  41%|████      | 384/938 [00:26<00:38, 14.34it/s, loss=0.695, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  41%|████      | 384/938 [00:26<00:38, 14.34it/s, loss=0.696, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  41%|████      | 385/938 [00:26<00:38, 14.34it/s, loss=0.692, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  41%|████      | 386/938 [00:26<00:38, 14.34it/s, loss=0.696, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  41%|████▏     | 387/938 [00:26<00:38, 14.33it/s, loss=0.704, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  41%|████▏     | 388/938 [00:27<00:38, 14.34it/s, loss=0.704, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  41%|████▏     | 388/938 [00:27<00:38, 14.34it/s, loss=0.71, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  41%|████▏     | 389/938 [00:27<00:38, 14.32it/s, loss=0.705, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  42%|████▏     | 390/938 [00:27<00:38, 14.32it/s, loss=0.713, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  42%|████▏     | 391/938 [00:27<00:38, 14.32it/s, loss=0.716, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  42%|████▏     | 392/938 [00:27<00:38, 14.33it/s, loss=0.716, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  42%|████▏     | 392/938 [00:27<00:38, 14.33it/s, loss=0.716, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  42%|████▏     | 393/938 [00:27<00:38, 14.33it/s, loss=0.713, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  42%|████▏     | 394/938 [00:27<00:37, 14.33it/s, loss=0.715, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  42%|████▏     | 395/938 [00:27<00:37, 14.33it/s, loss=0.709, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  42%|████▏     | 396/938 [00:27<00:37, 14.33it/s, loss=0.709, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  42%|████▏     | 396/938 [00:27<00:37, 14.32it/s, loss=0.713, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  42%|████▏     | 397/938 [00:27<00:37, 14.32it/s, loss=0.717, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  42%|████▏     | 398/938 [00:27<00:37, 14.33it/s, loss=0.727, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  43%|████▎     | 399/938 [00:27<00:37, 14.33it/s, loss=0.733, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  43%|████▎     | 400/938 [00:27<00:37, 14.33it/s, loss=0.733, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  43%|████▎     | 400/938 [00:27<00:37, 14.33it/s, loss=0.737, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  43%|████▎     | 401/938 [00:27<00:37, 14.33it/s, loss=0.75, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  43%|████▎     | 402/938 [00:28<00:37, 14.33it/s, loss=0.745, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  43%|████▎     | 403/938 [00:28<00:37, 14.33it/s, loss=0.73, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  43%|████▎     | 404/938 [00:28<00:37, 14.33it/s, loss=0.73, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  43%|████▎     | 404/938 [00:28<00:37, 14.33it/s, loss=0.735, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  43%|████▎     | 405/938 [00:28<00:37, 14.33it/s, loss=0.743, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  43%|████▎     | 406/938 [00:28<00:37, 14.32it/s, loss=0.736, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  43%|████▎     | 407/938 [00:28<00:37, 14.32it/s, loss=0.732, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  43%|████▎     | 408/938 [00:28<00:37, 14.30it/s, loss=0.732, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  43%|████▎     | 408/938 [00:28<00:37, 14.30it/s, loss=0.735, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  44%|████▎     | 409/938 [00:28<00:36, 14.31it/s, loss=0.73, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  44%|████▎     | 410/938 [00:28<00:36, 14.31it/s, loss=0.719, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  44%|████▍     | 411/938 [00:28<00:36, 14.30it/s, loss=0.717, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  44%|████▍     | 412/938 [00:28<00:36, 14.29it/s, loss=0.717, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  44%|████▍     | 412/938 [00:28<00:36, 14.29it/s, loss=0.715, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  44%|████▍     | 413/938 [00:28<00:36, 14.29it/s, loss=0.719, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  44%|████▍     | 414/938 [00:29<00:36, 14.25it/s, loss=0.724, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  44%|████▍     | 415/938 [00:29<00:36, 14.26it/s, loss=0.726, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  44%|████▍     | 416/938 [00:29<00:36, 14.25it/s, loss=0.726, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  44%|████▍     | 416/938 [00:29<00:36, 14.25it/s, loss=0.727, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  44%|████▍     | 417/938 [00:29<00:36, 14.26it/s, loss=0.722, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  45%|████▍     | 418/938 [00:29<00:36, 14.25it/s, loss=0.718, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  45%|████▍     | 419/938 [00:29<00:36, 14.26it/s, loss=0.715, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  45%|████▍     | 420/938 [00:29<00:36, 14.25it/s, loss=0.715, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  45%|████▍     | 420/938 [00:29<00:36, 14.24it/s, loss=0.719, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  45%|████▍     | 421/938 [00:29<00:36, 14.23it/s, loss=0.708, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  45%|████▍     | 422/938 [00:29<00:36, 14.23it/s, loss=0.701, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  45%|████▌     | 423/938 [00:29<00:36, 14.23it/s, loss=0.704, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  45%|████▌     | 424/938 [00:29<00:36, 14.23it/s, loss=0.704, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  45%|████▌     | 424/938 [00:29<00:36, 14.23it/s, loss=0.695, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  45%|████▌     | 425/938 [00:29<00:36, 14.23it/s, loss=0.688, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  45%|████▌     | 426/938 [00:29<00:35, 14.23it/s, loss=0.691, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  46%|████▌     | 427/938 [00:30<00:35, 14.23it/s, loss=0.691, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  46%|████▌     | 428/938 [00:30<00:35, 14.24it/s, loss=0.691, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  46%|████▌     | 428/938 [00:30<00:35, 14.24it/s, loss=0.693, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  46%|████▌     | 429/938 [00:30<00:35, 14.24it/s, loss=0.709, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  46%|████▌     | 430/938 [00:30<00:35, 14.24it/s, loss=0.719, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  46%|████▌     | 431/938 [00:30<00:35, 14.24it/s, loss=0.725, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  46%|████▌     | 432/938 [00:30<00:35, 14.23it/s, loss=0.725, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  46%|████▌     | 432/938 [00:30<00:35, 14.23it/s, loss=0.727, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  46%|████▌     | 433/938 [00:30<00:35, 14.24it/s, loss=0.731, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  46%|████▋     | 434/938 [00:30<00:35, 14.24it/s, loss=0.726, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  46%|████▋     | 435/938 [00:30<00:35, 14.23it/s, loss=0.723, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  46%|████▋     | 436/938 [00:30<00:35, 14.24it/s, loss=0.723, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  46%|████▋     | 436/938 [00:30<00:35, 14.23it/s, loss=0.719, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  47%|████▋     | 437/938 [00:30<00:35, 14.23it/s, loss=0.724, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  47%|████▋     | 438/938 [00:30<00:35, 14.23it/s, loss=0.725, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  47%|████▋     | 439/938 [00:30<00:35, 14.23it/s, loss=0.726, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  47%|████▋     | 440/938 [00:30<00:34, 14.23it/s, loss=0.726, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  47%|████▋     | 440/938 [00:30<00:34, 14.23it/s, loss=0.724, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  47%|████▋     | 441/938 [00:30<00:34, 14.23it/s, loss=0.72, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  47%|████▋     | 442/938 [00:31<00:34, 14.23it/s, loss=0.72, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  47%|████▋     | 443/938 [00:31<00:34, 14.22it/s, loss=0.724, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  47%|████▋     | 444/938 [00:31<00:34, 14.22it/s, loss=0.724, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  47%|████▋     | 444/938 [00:31<00:34, 14.22it/s, loss=0.728, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  47%|████▋     | 445/938 [00:31<00:34, 14.20it/s, loss=0.726, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  48%|████▊     | 446/938 [00:31<00:34, 14.19it/s, loss=0.728, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  48%|████▊     | 447/938 [00:31<00:34, 14.19it/s, loss=0.73, v_num=17, val_rmse=0.565, train_rmse=0.785] 
Epoch 2:  48%|████▊     | 448/938 [00:31<00:34, 14.20it/s, loss=0.73, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  48%|████▊     | 448/938 [00:31<00:34, 14.20it/s, loss=0.727, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  48%|████▊     | 449/938 [00:31<00:34, 14.20it/s, loss=0.715, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  48%|████▊     | 450/938 [00:31<00:34, 14.18it/s, loss=0.716, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  48%|████▊     | 451/938 [00:31<00:34, 14.19it/s, loss=0.707, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  48%|████▊     | 452/938 [00:31<00:34, 14.19it/s, loss=0.707, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  48%|████▊     | 452/938 [00:31<00:34, 14.19it/s, loss=0.702, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  48%|████▊     | 453/938 [00:31<00:34, 14.18it/s, loss=0.703, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  48%|████▊     | 454/938 [00:32<00:34, 14.18it/s, loss=0.693, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  49%|████▊     | 455/938 [00:32<00:34, 14.18it/s, loss=0.692, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  49%|████▊     | 456/938 [00:32<00:33, 14.18it/s, loss=0.692, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  49%|████▊     | 456/938 [00:32<00:33, 14.18it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  49%|████▊     | 457/938 [00:32<00:33, 14.18it/s, loss=0.703, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  49%|████▉     | 458/938 [00:32<00:33, 14.18it/s, loss=0.701, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  49%|████▉     | 459/938 [00:32<00:33, 14.18it/s, loss=0.703, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  49%|████▉     | 460/938 [00:32<00:33, 14.18it/s, loss=0.703, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  49%|████▉     | 460/938 [00:32<00:33, 14.18it/s, loss=0.695, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  49%|████▉     | 461/938 [00:32<00:33, 14.18it/s, loss=0.701, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  49%|████▉     | 462/938 [00:32<00:33, 14.18it/s, loss=0.7, v_num=17, val_rmse=0.565, train_rmse=0.785]  
Epoch 2:  49%|████▉     | 463/938 [00:32<00:33, 14.18it/s, loss=0.698, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  49%|████▉     | 464/938 [00:32<00:33, 14.18it/s, loss=0.698, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  49%|████▉     | 464/938 [00:32<00:33, 14.18it/s, loss=0.705, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  50%|████▉     | 465/938 [00:32<00:33, 14.18it/s, loss=0.705, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  50%|████▉     | 466/938 [00:32<00:33, 14.19it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  50%|████▉     | 467/938 [00:32<00:33, 14.19it/s, loss=0.693, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  50%|████▉     | 468/938 [00:32<00:33, 14.19it/s, loss=0.693, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  50%|████▉     | 468/938 [00:32<00:33, 14.19it/s, loss=0.694, v_num=17, val_rmse=0.565, train_rmse=0.785]
Epoch 2:  50%|█████     | 469/938 [00:33<00:33, 14.20it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/469 [00:00<?, ?it/s]
Epoch 2:  50%|█████     | 472/938 [00:33<00:32, 14.25it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:   1%|          | 3/469 [00:00<00:19, 24.22it/s]

Validating:   1%|▏         | 6/469 [00:00<00:18, 25.33it/s]
Epoch 2:  51%|█████     | 476/938 [00:33<00:32, 14.31it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:   2%|▏         | 9/469 [00:00<00:19, 23.89it/s]
Epoch 2:  51%|█████     | 480/938 [00:33<00:31, 14.35it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:   3%|▎         | 12/469 [00:00<00:19, 23.31it/s]
Epoch 2:  52%|█████▏    | 484/938 [00:33<00:31, 14.40it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:   3%|▎         | 15/469 [00:00<00:18, 24.74it/s]

Validating:   4%|▍         | 18/469 [00:00<00:17, 25.45it/s]
Epoch 2:  52%|█████▏    | 488/938 [00:33<00:31, 14.46it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:   4%|▍         | 21/469 [00:00<00:17, 26.17it/s]
Epoch 2:  52%|█████▏    | 492/938 [00:33<00:30, 14.52it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:   5%|▌         | 24/469 [00:00<00:17, 24.88it/s]
Epoch 2:  53%|█████▎    | 496/938 [00:34<00:30, 14.55it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:   6%|▌         | 27/469 [00:01<00:18, 24.11it/s]

Validating:   6%|▋         | 30/469 [00:01<00:18, 24.36it/s]
Epoch 2:  53%|█████▎    | 500/938 [00:34<00:29, 14.60it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:   7%|▋         | 33/469 [00:01<00:18, 23.58it/s]
Epoch 2:  54%|█████▎    | 504/938 [00:34<00:29, 14.64it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:   8%|▊         | 36/469 [00:01<00:17, 24.45it/s]
Epoch 2:  54%|█████▍    | 508/938 [00:34<00:29, 14.70it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:   8%|▊         | 39/469 [00:01<00:17, 24.88it/s]

Validating:   9%|▉         | 42/469 [00:01<00:16, 25.13it/s]
Epoch 2:  55%|█████▍    | 512/938 [00:34<00:28, 14.74it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  10%|▉         | 45/469 [00:01<00:17, 24.93it/s]
Epoch 2:  55%|█████▌    | 516/938 [00:34<00:28, 14.79it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  10%|█         | 48/469 [00:01<00:18, 22.99it/s]
Epoch 2:  55%|█████▌    | 520/938 [00:35<00:28, 14.82it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  11%|█         | 51/469 [00:02<00:17, 23.86it/s]

Validating:  12%|█▏        | 54/469 [00:02<00:18, 22.99it/s]
Epoch 2:  56%|█████▌    | 524/938 [00:35<00:27, 14.86it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  12%|█▏        | 57/469 [00:02<00:17, 23.11it/s]
Epoch 2:  56%|█████▋    | 528/938 [00:35<00:27, 14.90it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  13%|█▎        | 60/469 [00:02<00:17, 23.10it/s]
Epoch 2:  57%|█████▋    | 532/938 [00:35<00:27, 14.95it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  13%|█▎        | 63/469 [00:02<00:17, 23.54it/s]

Validating:  14%|█▍        | 66/469 [00:02<00:17, 23.44it/s]
Epoch 2:  57%|█████▋    | 536/938 [00:35<00:26, 14.98it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  15%|█▍        | 69/469 [00:02<00:16, 24.13it/s]
Epoch 2:  58%|█████▊    | 540/938 [00:35<00:26, 15.03it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  15%|█▌        | 72/469 [00:02<00:15, 24.92it/s]
Epoch 2:  58%|█████▊    | 544/938 [00:36<00:26, 15.08it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  16%|█▌        | 75/469 [00:03<00:16, 24.53it/s]

Validating:  17%|█▋        | 78/469 [00:03<00:16, 23.73it/s]
Epoch 2:  58%|█████▊    | 548/938 [00:36<00:25, 15.11it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  17%|█▋        | 81/469 [00:03<00:16, 24.21it/s]
Epoch 2:  59%|█████▉    | 552/938 [00:36<00:25, 15.16it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  18%|█▊        | 84/469 [00:03<00:15, 24.56it/s]
Epoch 2:  59%|█████▉    | 556/938 [00:36<00:25, 15.19it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  19%|█▊        | 87/469 [00:03<00:16, 22.50it/s]

Validating:  19%|█▉        | 90/469 [00:03<00:16, 23.25it/s]
Epoch 2:  60%|█████▉    | 560/938 [00:36<00:24, 15.23it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  20%|█▉        | 93/469 [00:03<00:16, 22.23it/s]
Epoch 2:  60%|██████    | 564/938 [00:36<00:24, 15.26it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  20%|██        | 96/469 [00:04<00:16, 23.00it/s]
Epoch 2:  61%|██████    | 568/938 [00:37<00:24, 15.30it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  21%|██        | 99/469 [00:04<00:15, 23.72it/s]

Validating:  22%|██▏       | 102/469 [00:04<00:15, 23.47it/s]
Epoch 2:  61%|██████    | 572/938 [00:37<00:23, 15.34it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  22%|██▏       | 105/469 [00:04<00:15, 23.63it/s]
Epoch 2:  61%|██████▏   | 576/938 [00:37<00:23, 15.38it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  23%|██▎       | 108/469 [00:04<00:14, 24.13it/s]
Epoch 2:  62%|██████▏   | 580/938 [00:37<00:23, 15.42it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  24%|██▎       | 111/469 [00:04<00:14, 24.03it/s]

Validating:  24%|██▍       | 114/469 [00:04<00:14, 24.99it/s]
Epoch 2:  62%|██████▏   | 584/938 [00:37<00:22, 15.46it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  25%|██▍       | 117/469 [00:04<00:14, 25.06it/s]
Epoch 2:  63%|██████▎   | 588/938 [00:37<00:22, 15.51it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  26%|██▌       | 120/469 [00:04<00:14, 24.76it/s]
Epoch 2:  63%|██████▎   | 592/938 [00:38<00:22, 15.54it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  26%|██▌       | 123/469 [00:05<00:14, 24.37it/s]

Validating:  27%|██▋       | 126/469 [00:05<00:13, 24.94it/s]
Epoch 2:  64%|██████▎   | 596/938 [00:38<00:21, 15.58it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  28%|██▊       | 129/469 [00:05<00:13, 25.28it/s]
Epoch 2:  64%|██████▍   | 600/938 [00:38<00:21, 15.62it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  28%|██▊       | 132/469 [00:05<00:13, 25.03it/s]
Epoch 2:  64%|██████▍   | 604/938 [00:38<00:21, 15.66it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  29%|██▉       | 135/469 [00:05<00:13, 24.59it/s]

Validating:  29%|██▉       | 138/469 [00:05<00:13, 24.14it/s]
Epoch 2:  65%|██████▍   | 608/938 [00:38<00:21, 15.69it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  30%|███       | 141/469 [00:05<00:13, 23.44it/s]
Epoch 2:  65%|██████▌   | 612/938 [00:38<00:20, 15.72it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  31%|███       | 144/469 [00:05<00:13, 24.03it/s]
Epoch 2:  66%|██████▌   | 616/938 [00:39<00:20, 15.76it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  31%|███▏      | 147/469 [00:06<00:13, 24.24it/s]

Validating:  32%|███▏      | 150/469 [00:06<00:13, 24.44it/s]
Epoch 2:  66%|██████▌   | 620/938 [00:39<00:20, 15.80it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  33%|███▎      | 153/469 [00:06<00:12, 24.61it/s]
Epoch 2:  67%|██████▋   | 624/938 [00:39<00:19, 15.84it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  33%|███▎      | 156/469 [00:06<00:12, 24.96it/s]
Epoch 2:  67%|██████▋   | 628/938 [00:39<00:19, 15.87it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  34%|███▍      | 159/469 [00:06<00:12, 24.35it/s]

Validating:  35%|███▍      | 162/469 [00:06<00:13, 23.58it/s]
Epoch 2:  67%|██████▋   | 632/938 [00:39<00:19, 15.90it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  35%|███▌      | 165/469 [00:06<00:12, 23.51it/s]
Epoch 2:  68%|██████▊   | 636/938 [00:39<00:18, 15.93it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  36%|███▌      | 168/469 [00:06<00:12, 23.61it/s]
Epoch 2:  68%|██████▊   | 640/938 [00:40<00:18, 15.97it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  36%|███▋      | 171/469 [00:07<00:12, 24.00it/s]

Validating:  37%|███▋      | 174/469 [00:07<00:12, 23.80it/s]
Epoch 2:  69%|██████▊   | 644/938 [00:40<00:18, 16.00it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  38%|███▊      | 177/469 [00:07<00:12, 23.25it/s]
Epoch 2:  69%|██████▉   | 648/938 [00:40<00:18, 16.03it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  38%|███▊      | 180/469 [00:07<00:12, 23.50it/s]
Epoch 2:  70%|██████▉   | 652/938 [00:40<00:17, 16.07it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  39%|███▉      | 183/469 [00:07<00:11, 23.86it/s]

Validating:  40%|███▉      | 186/469 [00:07<00:11, 23.90it/s]
Epoch 2:  70%|██████▉   | 656/938 [00:40<00:17, 16.10it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  40%|████      | 189/469 [00:07<00:11, 24.96it/s]
Epoch 2:  70%|███████   | 660/938 [00:40<00:17, 16.14it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  41%|████      | 192/469 [00:07<00:11, 25.03it/s]
Epoch 2:  71%|███████   | 664/938 [00:41<00:16, 16.17it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  42%|████▏     | 195/469 [00:08<00:10, 25.30it/s]

Validating:  42%|████▏     | 198/469 [00:08<00:10, 26.30it/s]
Epoch 2:  71%|███████   | 668/938 [00:41<00:16, 16.21it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  43%|████▎     | 201/469 [00:08<00:10, 26.11it/s]
Epoch 2:  72%|███████▏  | 672/938 [00:41<00:16, 16.25it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  43%|████▎     | 204/469 [00:08<00:09, 26.82it/s]
Epoch 2:  72%|███████▏  | 676/938 [00:41<00:16, 16.29it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  44%|████▍     | 207/469 [00:08<00:09, 26.39it/s]

Validating:  45%|████▍     | 210/469 [00:08<00:10, 24.92it/s]
Epoch 2:  72%|███████▏  | 680/938 [00:41<00:15, 16.32it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  45%|████▌     | 213/469 [00:08<00:10, 25.26it/s]
Epoch 2:  73%|███████▎  | 684/938 [00:41<00:15, 16.35it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  46%|████▌     | 216/469 [00:08<00:09, 25.55it/s]
Epoch 2:  73%|███████▎  | 688/938 [00:41<00:15, 16.39it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  47%|████▋     | 219/469 [00:08<00:09, 25.54it/s]

Validating:  47%|████▋     | 222/469 [00:09<00:09, 25.05it/s]
Epoch 2:  74%|███████▍  | 692/938 [00:42<00:14, 16.42it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  48%|████▊     | 225/469 [00:09<00:09, 25.25it/s]
Epoch 2:  74%|███████▍  | 696/938 [00:42<00:14, 16.45it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  49%|████▊     | 228/469 [00:09<00:09, 24.69it/s]
Epoch 2:  75%|███████▍  | 700/938 [00:42<00:14, 16.48it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  49%|████▉     | 231/469 [00:09<00:09, 25.18it/s]

Validating:  50%|████▉     | 234/469 [00:09<00:09, 25.67it/s]
Epoch 2:  75%|███████▌  | 704/938 [00:42<00:14, 16.52it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  51%|█████     | 237/469 [00:09<00:09, 24.10it/s]
Epoch 2:  75%|███████▌  | 708/938 [00:42<00:13, 16.54it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  51%|█████     | 240/469 [00:09<00:09, 23.58it/s]
Epoch 2:  76%|███████▌  | 712/938 [00:42<00:13, 16.56it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  52%|█████▏    | 243/469 [00:09<00:09, 23.38it/s]

Validating:  52%|█████▏    | 246/469 [00:10<00:09, 24.18it/s]
Epoch 2:  76%|███████▋  | 716/938 [00:43<00:13, 16.60it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  53%|█████▎    | 249/469 [00:10<00:09, 22.98it/s]
Epoch 2:  77%|███████▋  | 720/938 [00:43<00:13, 16.62it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  54%|█████▎    | 252/469 [00:10<00:08, 24.21it/s]
Epoch 2:  77%|███████▋  | 724/938 [00:43<00:12, 16.65it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  54%|█████▍    | 255/469 [00:10<00:08, 24.09it/s]

Validating:  55%|█████▌    | 258/469 [00:10<00:09, 23.09it/s]
Epoch 2:  78%|███████▊  | 728/938 [00:43<00:12, 16.67it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  56%|█████▌    | 261/469 [00:10<00:08, 23.22it/s]
Epoch 2:  78%|███████▊  | 732/938 [00:43<00:12, 16.70it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  56%|█████▋    | 264/469 [00:10<00:08, 24.35it/s]
Epoch 2:  78%|███████▊  | 736/938 [00:43<00:12, 16.73it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  57%|█████▋    | 267/469 [00:11<00:08, 23.90it/s]

Validating:  58%|█████▊    | 270/469 [00:11<00:08, 23.65it/s]
Epoch 2:  79%|███████▉  | 740/938 [00:44<00:11, 16.76it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  58%|█████▊    | 273/469 [00:11<00:08, 23.70it/s]
Epoch 2:  79%|███████▉  | 744/938 [00:44<00:11, 16.79it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  59%|█████▉    | 276/469 [00:11<00:08, 23.70it/s]
Epoch 2:  80%|███████▉  | 748/938 [00:44<00:11, 16.81it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  59%|█████▉    | 279/469 [00:11<00:07, 24.24it/s]

Validating:  60%|██████    | 282/469 [00:11<00:07, 24.32it/s]
Epoch 2:  80%|████████  | 752/938 [00:44<00:11, 16.84it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  61%|██████    | 285/469 [00:11<00:07, 24.57it/s]
Epoch 2:  81%|████████  | 756/938 [00:44<00:10, 16.87it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  61%|██████▏   | 288/469 [00:11<00:07, 24.09it/s]
Epoch 2:  81%|████████  | 760/938 [00:44<00:10, 16.89it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  62%|██████▏   | 291/469 [00:12<00:07, 23.97it/s]

Validating:  63%|██████▎   | 294/469 [00:12<00:07, 24.62it/s]
Epoch 2:  81%|████████▏ | 764/938 [00:45<00:10, 16.92it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  63%|██████▎   | 297/469 [00:12<00:06, 25.11it/s]
Epoch 2:  82%|████████▏ | 768/938 [00:45<00:10, 16.95it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  64%|██████▍   | 300/469 [00:12<00:06, 24.84it/s]
Epoch 2:  82%|████████▏ | 772/938 [00:45<00:09, 16.98it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  65%|██████▍   | 303/469 [00:12<00:06, 25.27it/s]

Validating:  65%|██████▌   | 306/469 [00:12<00:06, 24.68it/s]
Epoch 2:  83%|████████▎ | 776/938 [00:45<00:09, 17.01it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  66%|██████▌   | 309/469 [00:12<00:06, 24.70it/s]
Epoch 2:  83%|████████▎ | 780/938 [00:45<00:09, 17.03it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  67%|██████▋   | 312/469 [00:12<00:06, 24.20it/s]
Epoch 2:  84%|████████▎ | 784/938 [00:45<00:09, 17.06it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  67%|██████▋   | 315/469 [00:12<00:06, 23.94it/s]

Validating:  68%|██████▊   | 318/469 [00:13<00:06, 25.03it/s]
Epoch 2:  84%|████████▍ | 788/938 [00:46<00:08, 17.09it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  68%|██████▊   | 321/469 [00:13<00:05, 24.85it/s]
Epoch 2:  84%|████████▍ | 792/938 [00:46<00:08, 17.12it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  69%|██████▉   | 324/469 [00:13<00:05, 24.80it/s]
Epoch 2:  85%|████████▍ | 796/938 [00:46<00:08, 17.14it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  70%|██████▉   | 327/469 [00:13<00:05, 24.31it/s]

Validating:  70%|███████   | 330/469 [00:13<00:05, 24.58it/s]
Epoch 2:  85%|████████▌ | 800/938 [00:46<00:08, 17.17it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  71%|███████   | 333/469 [00:13<00:05, 24.72it/s]
Epoch 2:  86%|████████▌ | 804/938 [00:46<00:07, 17.19it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  72%|███████▏  | 336/469 [00:13<00:05, 24.92it/s]
Epoch 2:  86%|████████▌ | 808/938 [00:46<00:07, 17.22it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  72%|███████▏  | 339/469 [00:13<00:05, 24.23it/s]

Validating:  73%|███████▎  | 342/469 [00:14<00:05, 25.16it/s]
Epoch 2:  87%|████████▋ | 812/938 [00:47<00:07, 17.25it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  74%|███████▎  | 345/469 [00:14<00:05, 23.90it/s]
Epoch 2:  87%|████████▋ | 816/938 [00:47<00:07, 17.26it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  74%|███████▍  | 348/469 [00:14<00:05, 23.45it/s]
Epoch 2:  87%|████████▋ | 820/938 [00:47<00:06, 17.28it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  75%|███████▍  | 351/469 [00:14<00:05, 23.45it/s]

Validating:  75%|███████▌  | 354/469 [00:14<00:04, 23.65it/s]
Epoch 2:  88%|████████▊ | 824/938 [00:47<00:06, 17.31it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  76%|███████▌  | 357/469 [00:14<00:04, 24.00it/s]
Epoch 2:  88%|████████▊ | 828/938 [00:47<00:06, 17.34it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  77%|███████▋  | 360/469 [00:14<00:04, 23.94it/s]
Epoch 2:  89%|████████▊ | 832/938 [00:47<00:06, 17.36it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  77%|███████▋  | 363/469 [00:14<00:04, 23.86it/s]

Validating:  78%|███████▊  | 366/469 [00:15<00:04, 23.25it/s]
Epoch 2:  89%|████████▉ | 836/938 [00:48<00:05, 17.37it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  79%|███████▊  | 369/469 [00:15<00:04, 22.35it/s]
Epoch 2:  90%|████████▉ | 840/938 [00:48<00:05, 17.39it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  79%|███████▉  | 372/469 [00:15<00:04, 22.41it/s]
Epoch 2:  90%|████████▉ | 844/938 [00:48<00:05, 17.40it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  80%|███████▉  | 375/469 [00:15<00:04, 21.33it/s]

Validating:  81%|████████  | 378/469 [00:15<00:03, 22.96it/s]
Epoch 2:  90%|█████████ | 848/938 [00:48<00:05, 17.43it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  81%|████████  | 381/469 [00:15<00:03, 23.53it/s]
Epoch 2:  91%|█████████ | 852/938 [00:48<00:04, 17.45it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  82%|████████▏ | 384/469 [00:15<00:03, 23.71it/s]
Epoch 2:  91%|█████████▏| 856/938 [00:48<00:04, 17.47it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  83%|████████▎ | 387/469 [00:15<00:03, 24.11it/s]

Validating:  83%|████████▎ | 390/469 [00:16<00:03, 24.14it/s]
Epoch 2:  92%|█████████▏| 860/938 [00:49<00:04, 17.50it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  84%|████████▍ | 393/469 [00:16<00:03, 23.64it/s]
Epoch 2:  92%|█████████▏| 864/938 [00:49<00:04, 17.52it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  84%|████████▍ | 396/469 [00:16<00:03, 23.96it/s]
Epoch 2:  93%|█████████▎| 868/938 [00:49<00:03, 17.54it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  85%|████████▌ | 399/469 [00:16<00:02, 24.05it/s]

Validating:  86%|████████▌ | 402/469 [00:16<00:02, 23.34it/s]
Epoch 2:  93%|█████████▎| 872/938 [00:49<00:03, 17.56it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  86%|████████▋ | 405/469 [00:16<00:02, 23.39it/s]
Epoch 2:  93%|█████████▎| 876/938 [00:49<00:03, 17.58it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  87%|████████▋ | 408/469 [00:16<00:02, 23.75it/s]
Epoch 2:  94%|█████████▍| 880/938 [00:49<00:03, 17.60it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  88%|████████▊ | 411/469 [00:17<00:02, 24.43it/s]

Validating:  88%|████████▊ | 414/469 [00:17<00:02, 24.65it/s]
Epoch 2:  94%|█████████▍| 884/938 [00:50<00:03, 17.63it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  89%|████████▉ | 417/469 [00:17<00:02, 24.68it/s]
Epoch 2:  95%|█████████▍| 888/938 [00:50<00:02, 17.65it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  90%|████████▉ | 420/469 [00:17<00:01, 24.92it/s]
Epoch 2:  95%|█████████▌| 892/938 [00:50<00:02, 17.67it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  90%|█████████ | 423/469 [00:17<00:02, 22.78it/s]

Validating:  91%|█████████ | 426/469 [00:17<00:01, 22.32it/s]
Epoch 2:  96%|█████████▌| 896/938 [00:50<00:02, 17.68it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  91%|█████████▏| 429/469 [00:17<00:01, 23.26it/s]
Epoch 2:  96%|█████████▌| 900/938 [00:50<00:02, 17.70it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  92%|█████████▏| 432/469 [00:17<00:01, 24.22it/s]
Epoch 2:  96%|█████████▋| 904/938 [00:50<00:01, 17.73it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  93%|█████████▎| 435/469 [00:17<00:01, 24.90it/s]

Validating:  93%|█████████▎| 438/469 [00:18<00:01, 25.66it/s]
Epoch 2:  97%|█████████▋| 908/938 [00:51<00:01, 17.76it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  94%|█████████▍| 441/469 [00:18<00:01, 25.71it/s]
Epoch 2:  97%|█████████▋| 912/938 [00:51<00:01, 17.78it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  95%|█████████▍| 444/469 [00:18<00:00, 26.20it/s]
Epoch 2:  98%|█████████▊| 916/938 [00:51<00:01, 17.81it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  95%|█████████▌| 447/469 [00:18<00:00, 25.93it/s]

Validating:  96%|█████████▌| 450/469 [00:18<00:00, 25.39it/s]
Epoch 2:  98%|█████████▊| 920/938 [00:51<00:01, 17.83it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  97%|█████████▋| 453/469 [00:18<00:00, 26.12it/s]
Epoch 2:  99%|█████████▊| 924/938 [00:51<00:00, 17.85it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  97%|█████████▋| 456/469 [00:18<00:00, 25.22it/s]
Epoch 2:  99%|█████████▉| 928/938 [00:51<00:00, 17.88it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  98%|█████████▊| 459/469 [00:18<00:00, 25.20it/s]

Validating:  99%|█████████▊| 462/469 [00:19<00:00, 23.38it/s]
Epoch 2:  99%|█████████▉| 932/938 [00:52<00:00, 17.89it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating:  99%|█████████▉| 465/469 [00:19<00:00, 23.84it/s]
Epoch 2: 100%|█████████▉| 936/938 [00:52<00:00, 17.91it/s, loss=0.697, v_num=17, val_rmse=0.565, train_rmse=0.785]

Validating: 100%|█████████▉| 468/469 [00:19<00:00, 24.09it/s]
Epoch 2: 100%|██████████| 938/938 [00:52<00:00, 17.91it/s, loss=0.697, v_num=17, val_rmse=0.524, train_rmse=0.785]

                                                             
Epoch 2: 100%|██████████| 938/938 [00:52<00:00, 17.90it/s, loss=0.697, v_num=17, val_rmse=0.524, train_rmse=0.724]
Epoch 2: 100%|██████████| 938/938 [00:52<00:00, 17.86it/s, loss=0.697, v_num=17, val_rmse=0.524, train_rmse=0.724]LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]


Testing: 0it [00:00, ?it/s]
Testing:   0%|          | 2/469 [00:00<00:27, 17.09it/s]
Testing:   1%|          | 5/469 [00:00<00:21, 22.07it/s]
Testing:   2%|▏         | 8/469 [00:00<00:19, 23.98it/s]
Testing:   2%|▏         | 11/469 [00:00<00:18, 24.44it/s]
Testing:   3%|▎         | 14/469 [00:00<00:18, 24.74it/s]
Testing:   4%|▎         | 17/469 [00:00<00:18, 24.97it/s]
Testing:   4%|▍         | 20/469 [00:00<00:17, 25.66it/s]
Testing:   5%|▍         | 23/469 [00:00<00:17, 25.97it/s]
Testing:   6%|▌         | 26/469 [00:01<00:16, 26.83it/s]
Testing:   6%|▌         | 29/469 [00:01<00:17, 25.86it/s]
Testing:   7%|▋         | 32/469 [00:01<00:17, 25.50it/s]
Testing:   7%|▋         | 35/469 [00:01<00:16, 26.16it/s]
Testing:   8%|▊         | 38/469 [00:01<00:16, 26.51it/s]
Testing:   9%|▊         | 41/469 [00:01<00:16, 26.73it/s]
Testing:   9%|▉         | 44/469 [00:01<00:15, 26.73it/s]
Testing:  10%|█         | 47/469 [00:01<00:15, 27.01it/s]
Testing:  11%|█         | 50/469 [00:01<00:15, 26.95it/s]
Testing:  11%|█▏        | 53/469 [00:02<00:15, 26.42it/s]
Testing:  12%|█▏        | 56/469 [00:02<00:15, 26.48it/s]
Testing:  13%|█▎        | 59/469 [00:02<00:16, 24.95it/s]
Testing:  13%|█▎        | 62/469 [00:02<00:17, 22.92it/s]
Testing:  14%|█▍        | 65/469 [00:02<00:17, 23.08it/s]
Testing:  14%|█▍        | 68/469 [00:02<00:16, 23.62it/s]
Testing:  15%|█▌        | 71/469 [00:02<00:16, 23.53it/s]
Testing:  16%|█▌        | 74/469 [00:02<00:16, 23.87it/s]
Testing:  16%|█▋        | 77/469 [00:03<00:16, 23.72it/s]
Testing:  17%|█▋        | 80/469 [00:03<00:16, 24.27it/s]
Testing:  18%|█▊        | 83/469 [00:03<00:16, 24.02it/s]
Testing:  18%|█▊        | 86/469 [00:03<00:15, 24.04it/s]
Testing:  19%|█▉        | 89/469 [00:03<00:15, 24.79it/s]
Testing:  20%|█▉        | 92/469 [00:03<00:15, 24.61it/s]
Testing:  20%|██        | 95/469 [00:03<00:15, 24.77it/s]
Testing:  21%|██        | 98/469 [00:03<00:15, 23.67it/s]
Testing:  22%|██▏       | 101/469 [00:04<00:15, 23.95it/s]
Testing:  22%|██▏       | 104/469 [00:04<00:15, 24.21it/s]
Testing:  23%|██▎       | 107/469 [00:04<00:14, 24.20it/s]
Testing:  23%|██▎       | 110/469 [00:04<00:14, 24.65it/s]
Testing:  24%|██▍       | 113/469 [00:04<00:13, 25.54it/s]
Testing:  25%|██▍       | 116/469 [00:04<00:14, 24.92it/s]
Testing:  25%|██▌       | 119/469 [00:04<00:13, 25.09it/s]
Testing:  26%|██▌       | 122/469 [00:04<00:13, 24.96it/s]
Testing:  27%|██▋       | 125/469 [00:05<00:13, 25.09it/s]
Testing:  27%|██▋       | 128/469 [00:05<00:13, 24.46it/s]
Testing:  28%|██▊       | 131/469 [00:05<00:13, 24.26it/s]
Testing:  29%|██▊       | 134/469 [00:05<00:13, 24.87it/s]
Testing:  29%|██▉       | 137/469 [00:05<00:13, 24.34it/s]
Testing:  30%|██▉       | 140/469 [00:05<00:13, 24.63it/s]
Testing:  30%|███       | 143/469 [00:05<00:13, 24.07it/s]
Testing:  31%|███       | 146/469 [00:05<00:13, 23.66it/s]
Testing:  32%|███▏      | 149/469 [00:06<00:13, 23.99it/s]
Testing:  32%|███▏      | 152/469 [00:06<00:13, 24.28it/s]
Testing:  33%|███▎      | 155/469 [00:06<00:12, 24.24it/s]
Testing:  34%|███▎      | 158/469 [00:06<00:12, 25.12it/s]
Testing:  34%|███▍      | 161/469 [00:06<00:12, 24.94it/s]
Testing:  35%|███▍      | 164/469 [00:06<00:12, 25.25it/s]
Testing:  36%|███▌      | 167/469 [00:06<00:11, 25.66it/s]
Testing:  36%|███▌      | 170/469 [00:06<00:11, 25.81it/s]
Testing:  37%|███▋      | 173/469 [00:06<00:11, 25.65it/s]
Testing:  38%|███▊      | 176/469 [00:07<00:11, 24.57it/s]
Testing:  38%|███▊      | 179/469 [00:07<00:11, 24.92it/s]
Testing:  39%|███▉      | 182/469 [00:07<00:11, 25.27it/s]
Testing:  39%|███▉      | 185/469 [00:07<00:11, 24.78it/s]
Testing:  40%|████      | 188/469 [00:07<00:11, 25.46it/s]
Testing:  41%|████      | 191/469 [00:07<00:11, 25.17it/s]
Testing:  41%|████▏     | 194/469 [00:07<00:11, 24.85it/s]
Testing:  42%|████▏     | 197/469 [00:07<00:10, 25.40it/s]
Testing:  43%|████▎     | 200/469 [00:08<00:11, 24.44it/s]
Testing:  43%|████▎     | 203/469 [00:08<00:10, 24.90it/s]
Testing:  44%|████▍     | 206/469 [00:08<00:10, 24.91it/s]
Testing:  45%|████▍     | 209/469 [00:08<00:10, 25.04it/s]
Testing:  45%|████▌     | 212/469 [00:08<00:10, 25.05it/s]
Testing:  46%|████▌     | 215/469 [00:08<00:10, 24.29it/s]
Testing:  46%|████▋     | 218/469 [00:08<00:10, 24.54it/s]
Testing:  47%|████▋     | 221/469 [00:08<00:09, 25.01it/s]
Testing:  48%|████▊     | 224/469 [00:09<00:09, 24.78it/s]
Testing:  48%|████▊     | 227/469 [00:09<00:09, 25.14it/s]
Testing:  49%|████▉     | 230/469 [00:09<00:09, 24.55it/s]
Testing:  50%|████▉     | 233/469 [00:09<00:09, 23.68it/s]
Testing:  50%|█████     | 236/469 [00:09<00:09, 24.34it/s]
Testing:  51%|█████     | 239/469 [00:09<00:09, 24.73it/s]
Testing:  52%|█████▏    | 242/469 [00:09<00:09, 24.74it/s]
Testing:  52%|█████▏    | 245/469 [00:09<00:09, 22.97it/s]
Testing:  53%|█████▎    | 248/469 [00:10<00:09, 24.41it/s]
Testing:  54%|█████▎    | 251/469 [00:10<00:08, 24.68it/s]
Testing:  54%|█████▍    | 254/469 [00:10<00:08, 25.07it/s]
Testing:  55%|█████▍    | 257/469 [00:10<00:08, 24.88it/s]
Testing:  55%|█████▌    | 260/469 [00:10<00:08, 25.15it/s]
Testing:  56%|█████▌    | 263/469 [00:10<00:08, 24.94it/s]
Testing:  57%|█████▋    | 266/469 [00:10<00:08, 24.69it/s]
Testing:  57%|█████▋    | 269/469 [00:10<00:07, 25.35it/s]
Testing:  58%|█████▊    | 272/469 [00:10<00:07, 24.95it/s]
Testing:  59%|█████▊    | 275/469 [00:11<00:07, 25.55it/s]
Testing:  59%|█████▉    | 278/469 [00:11<00:08, 23.84it/s]
Testing:  60%|█████▉    | 281/469 [00:11<00:07, 24.57it/s]
Testing:  61%|██████    | 284/469 [00:11<00:07, 24.31it/s]
Testing:  61%|██████    | 287/469 [00:11<00:07, 24.17it/s]
Testing:  62%|██████▏   | 290/469 [00:11<00:07, 24.42it/s]
Testing:  62%|██████▏   | 293/469 [00:11<00:07, 24.25it/s]
Testing:  63%|██████▎   | 296/469 [00:11<00:07, 24.64it/s]
Testing:  64%|██████▍   | 299/469 [00:12<00:06, 25.66it/s]
Testing:  64%|██████▍   | 302/469 [00:12<00:06, 26.41it/s]
Testing:  65%|██████▌   | 305/469 [00:12<00:06, 26.67it/s]
Testing:  66%|██████▌   | 308/469 [00:12<00:06, 26.65it/s]
Testing:  66%|██████▋   | 311/469 [00:12<00:05, 26.76it/s]
Testing:  67%|██████▋   | 314/469 [00:12<00:05, 27.23it/s]
Testing:  68%|██████▊   | 317/469 [00:12<00:05, 27.19it/s]
Testing:  68%|██████▊   | 320/469 [00:12<00:05, 25.24it/s]
Testing:  69%|██████▉   | 323/469 [00:12<00:05, 25.71it/s]
Testing:  70%|██████▉   | 326/469 [00:13<00:05, 26.06it/s]
Testing:  70%|███████   | 329/469 [00:13<00:05, 26.51it/s]
Testing:  71%|███████   | 332/469 [00:13<00:05, 26.91it/s]
Testing:  71%|███████▏  | 335/469 [00:13<00:05, 26.42it/s]
Testing:  72%|███████▏  | 338/469 [00:13<00:05, 25.35it/s]
Testing:  73%|███████▎  | 341/469 [00:13<00:05, 23.80it/s]
Testing:  73%|███████▎  | 344/469 [00:13<00:05, 24.21it/s]
Testing:  74%|███████▍  | 347/469 [00:13<00:04, 24.46it/s]
Testing:  75%|███████▍  | 350/469 [00:14<00:04, 24.62it/s]
Testing:  75%|███████▌  | 353/469 [00:14<00:04, 24.90it/s]
Testing:  76%|███████▌  | 356/469 [00:14<00:04, 24.51it/s]
Testing:  77%|███████▋  | 359/469 [00:14<00:04, 24.79it/s]
Testing:  77%|███████▋  | 362/469 [00:14<00:04, 24.18it/s]
Testing:  78%|███████▊  | 365/469 [00:14<00:04, 24.91it/s]
Testing:  78%|███████▊  | 368/469 [00:14<00:04, 24.52it/s]
Testing:  79%|███████▉  | 371/469 [00:14<00:03, 25.48it/s]
Testing:  80%|███████▉  | 374/469 [00:15<00:03, 24.40it/s]
Testing:  80%|████████  | 377/469 [00:15<00:03, 23.86it/s]
Testing:  81%|████████  | 380/469 [00:15<00:03, 23.18it/s]
Testing:  82%|████████▏ | 383/469 [00:15<00:03, 22.76it/s]
Testing:  82%|████████▏ | 386/469 [00:15<00:03, 23.60it/s]
Testing:  83%|████████▎ | 389/469 [00:15<00:03, 22.28it/s]
Testing:  84%|████████▎ | 392/469 [00:15<00:03, 22.73it/s]
Testing:  84%|████████▍ | 395/469 [00:15<00:03, 23.58it/s]
Testing:  85%|████████▍ | 398/469 [00:16<00:03, 23.21it/s]
Testing:  86%|████████▌ | 401/469 [00:16<00:03, 21.62it/s]
Testing:  86%|████████▌ | 404/469 [00:16<00:03, 21.46it/s]
Testing:  87%|████████▋ | 407/469 [00:16<00:02, 22.72it/s]
Testing:  87%|████████▋ | 410/469 [00:16<00:02, 23.84it/s]
Testing:  88%|████████▊ | 413/469 [00:16<00:02, 24.40it/s]
Testing:  89%|████████▊ | 416/469 [00:16<00:02, 24.60it/s]
Testing:  89%|████████▉ | 419/469 [00:16<00:02, 24.98it/s]
Testing:  90%|████████▉ | 422/469 [00:17<00:01, 25.60it/s]
Testing:  91%|█████████ | 425/469 [00:17<00:01, 24.97it/s]
Testing:  91%|█████████▏| 428/469 [00:17<00:01, 24.88it/s]
Testing:  92%|█████████▏| 431/469 [00:17<00:01, 24.64it/s]
Testing:  93%|█████████▎| 434/469 [00:17<00:01, 25.30it/s]
Testing:  93%|█████████▎| 437/469 [00:17<00:01, 24.93it/s]
Testing:  94%|█████████▍| 440/469 [00:17<00:01, 25.06it/s]
Testing:  94%|█████████▍| 443/469 [00:17<00:01, 23.67it/s]
Testing:  95%|█████████▌| 446/469 [00:18<00:00, 23.89it/s]
Testing:  96%|█████████▌| 449/469 [00:18<00:00, 23.66it/s]
Testing:  96%|█████████▋| 452/469 [00:18<00:00, 23.82it/s]
Testing:  97%|█████████▋| 455/469 [00:18<00:00, 23.60it/s]
Testing:  98%|█████████▊| 458/469 [00:18<00:00, 23.47it/s]
Testing:  98%|█████████▊| 461/469 [00:18<00:00, 23.71it/s]
Testing:  99%|█████████▉| 464/469 [00:18<00:00, 24.66it/s]
Testing: 100%|█████████▉| 467/469 [00:18<00:00, 25.38it/s]--------------------------------------------------------------------------------
DATALOADER:0 TEST RESULTS
{'test_rmse': 0.5241828560829163}
--------------------------------------------------------------------------------

Testing: 100%|██████████| 469/469 [00:18<00:00, 24.71it/s]
  0%|          | 0/469 [02:57<?, ?it/s]

Mean RMSE: 0.524 (+/-0.008)