diff --git "a/llama2-7b.log" "b/llama2-7b.log"
new file mode 100644--- /dev/null
+++ "b/llama2-7b.log"
@@ -0,0 +1,1862 @@
+nohup: ignoring input
+/opt/conda/envs/pytorch/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:472: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers.
+  warnings.warn(
+
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:07<00:07,  7.39s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:10<00:00,  4.67s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:10<00:00,  5.08s/it]
+/opt/conda/envs/pytorch/lib/python3.10/site-packages/transformers/utils/hub.py:374: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers.
+  warnings.warn(
+Repo card metadata block was not found. Setting CardData to empty.
+/opt/conda/envs/pytorch/lib/python3.10/site-packages/peft/utils/other.py:122: FutureWarning: prepare_model_for_int8_training is deprecated and will be removed in a future version. Use prepare_model_for_kbit_training instead.
+  warnings.warn(
+Using pad_token, but it is not set yet.
+
  0%|          | 0/1848 [00:00<?, ?it/s]You're using a LlamaTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
+`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
+
  0%|          | 1/1848 [00:20<10:32:23, 20.54s/it]
                                                   

  0%|          | 1/1848 [00:20<10:32:23, 20.54s/it]
  0%|          | 2/1848 [00:40<10:20:46, 20.18s/it]
                                                   

  0%|          | 2/1848 [00:40<10:20:46, 20.18s/it]
  0%|          | 3/1848 [01:00<10:16:38, 20.05s/it]
                                                   

  0%|          | 3/1848 [01:00<10:16:38, 20.05s/it]
  0%|          | 4/1848 [01:20<10:14:55, 20.01s/it]
                                                   

  0%|          | 4/1848 [01:20<10:14:55, 20.01s/it]
  0%|          | 5/1848 [01:40<10:13:52, 19.99s/it]
                                                   

  0%|          | 5/1848 [01:40<10:13:52, 19.99s/it]
  0%|          | 6/1848 [02:00<10:12:20, 19.95s/it]
                                                   

  0%|          | 6/1848 [02:00<10:12:20, 19.95s/it]
  0%|          | 7/1848 [02:20<10:12:42, 19.97s/it]
                                                   

  0%|          | 7/1848 [02:20<10:12:42, 19.97s/it]
  0%|          | 8/1848 [02:40<10:12:34, 19.98s/it]
                                                   

  0%|          | 8/1848 [02:40<10:12:34, 19.98s/it]
  0%|          | 9/1848 [03:00<10:11:33, 19.95s/it]
                                                   

  0%|          | 9/1848 [03:00<10:11:33, 19.95s/it]
  1%|          | 10/1848 [03:20<10:11:48, 19.97s/it]
                                                    

  1%|          | 10/1848 [03:20<10:11:48, 19.97s/it]
  1%|          | 11/1848 [03:39<10:11:02, 19.96s/it]
                                                    

  1%|          | 11/1848 [03:39<10:11:02, 19.96s/it]
  1%|          | 12/1848 [03:59<10:10:57, 19.97s/it]
                                                    

  1%|          | 12/1848 [03:59<10:10:57, 19.97s/it]
  1%|          | 13/1848 [04:19<10:11:14, 19.99s/it]
                                                    

  1%|          | 13/1848 [04:19<10:11:14, 19.99s/it]
  1%|          | 14/1848 [04:39<10:10:31, 19.97s/it]
                                                    

  1%|          | 14/1848 [04:39<10:10:31, 19.97s/it]
  1%|          | 15/1848 [04:59<10:10:22, 19.98s/it]
                                                    

  1%|          | 15/1848 [04:59<10:10:22, 19.98s/it]
  1%|          | 16/1848 [05:19<10:09:20, 19.96s/it]
                                                    

  1%|          | 16/1848 [05:19<10:09:20, 19.96s/it]
  1%|          | 17/1848 [05:39<10:09:06, 19.96s/it]
                                                    

  1%|          | 17/1848 [05:39<10:09:06, 19.96s/it]
  1%|          | 18/1848 [05:59<10:08:42, 19.96s/it]
                                                    

  1%|          | 18/1848 [05:59<10:08:42, 19.96s/it]
  1%|          | 19/1848 [06:19<10:09:16, 19.99s/it]
                                                    

  1%|          | 19/1848 [06:19<10:09:16, 19.99s/it]
  1%|          | 20/1848 [06:39<10:08:34, 19.98s/it]
                                                    

  1%|          | 20/1848 [06:39<10:08:34, 19.98s/it]
  1%|          | 21/1848 [06:59<10:07:53, 19.96s/it]
                                                    

  1%|          | 21/1848 [06:59<10:07:53, 19.96s/it]
  1%|          | 22/1848 [07:19<10:07:00, 19.95s/it]
                                                    

  1%|          | 22/1848 [07:19<10:07:00, 19.95s/it]
  1%|          | 23/1848 [07:37<9:46:51, 19.29s/it] 
                                                   

  1%|          | 23/1848 [07:37<9:46:51, 19.29s/it]
  1%|▏         | 24/1848 [07:57<9:52:36, 19.49s/it]
                                                   

  1%|▏         | 24/1848 [07:57<9:52:36, 19.49s/it]
  1%|▏         | 25/1848 [08:17<9:56:40, 19.64s/it]
                                                   

  1%|▏         | 25/1848 [08:17<9:56:40, 19.64s/it]
  1%|▏         | 26/1848 [08:37<9:59:17, 19.74s/it]
                                                   

  1%|▏         | 26/1848 [08:37<9:59:17, 19.74s/it]
  1%|▏         | 27/1848 [08:57<10:00:53, 19.80s/it]
                                                    

  1%|▏         | 27/1848 [08:57<10:00:53, 19.80s/it]
  2%|▏         | 28/1848 [09:17<10:02:18, 19.86s/it]
                                                    

  2%|▏         | 28/1848 [09:17<10:02:18, 19.86s/it]
  2%|▏         | 29/1848 [09:37<10:02:50, 19.88s/it]
                                                    

  2%|▏         | 29/1848 [09:37<10:02:50, 19.88s/it]
  2%|▏         | 30/1848 [09:57<10:03:33, 19.92s/it]
                                                    

  2%|▏         | 30/1848 [09:57<10:03:33, 19.92s/it]
  2%|▏         | 31/1848 [10:17<10:03:32, 19.93s/it]
                                                    

  2%|▏         | 31/1848 [10:17<10:03:32, 19.93s/it]
  2%|▏         | 32/1848 [10:37<10:03:29, 19.94s/it]
                                                    

  2%|▏         | 32/1848 [10:37<10:03:29, 19.94s/it]
  2%|▏         | 33/1848 [10:56<10:02:44, 19.93s/it]
                                                    

  2%|▏         | 33/1848 [10:56<10:02:44, 19.93s/it]
  2%|▏         | 34/1848 [11:16<10:02:48, 19.94s/it]
                                                    

  2%|▏         | 34/1848 [11:16<10:02:48, 19.94s/it]
  2%|▏         | 35/1848 [11:36<10:02:50, 19.95s/it]
                                                    

  2%|▏         | 35/1848 [11:36<10:02:50, 19.95s/it]
  2%|▏         | 36/1848 [11:56<10:03:05, 19.97s/it]
                                                    

  2%|▏         | 36/1848 [11:56<10:03:05, 19.97s/it]
  2%|▏         | 37/1848 [12:16<10:02:40, 19.97s/it]
                                                    

  2%|▏         | 37/1848 [12:16<10:02:40, 19.97s/it]
  2%|▏         | 38/1848 [12:36<10:02:17, 19.97s/it]
                                                    

  2%|▏         | 38/1848 [12:36<10:02:17, 19.97s/it]
  2%|▏         | 39/1848 [12:56<10:01:20, 19.95s/it]
                                                    

  2%|▏         | 39/1848 [12:56<10:01:20, 19.95s/it]
  2%|▏         | 40/1848 [13:16<10:01:03, 19.95s/it]
                                                    

  2%|▏         | 40/1848 [13:16<10:01:03, 19.95s/it]
  2%|▏         | 41/1848 [13:36<10:01:31, 19.97s/it]
                                                    

  2%|▏         | 41/1848 [13:36<10:01:31, 19.97s/it]
  2%|▏         | 42/1848 [13:56<10:00:32, 19.95s/it]
                                                    

  2%|▏         | 42/1848 [13:56<10:00:32, 19.95s/it]
  2%|▏         | 43/1848 [14:16<9:59:49, 19.94s/it] 
                                                   

  2%|▏         | 43/1848 [14:16<9:59:49, 19.94s/it]
  2%|▏         | 44/1848 [14:36<9:59:12, 19.93s/it]
                                                   

  2%|▏         | 44/1848 [14:36<9:59:12, 19.93s/it]
  2%|▏         | 45/1848 [14:56<9:58:52, 19.93s/it]
                                                   

  2%|▏         | 45/1848 [14:56<9:58:52, 19.93s/it]
  2%|▏         | 46/1848 [15:16<9:59:35, 19.96s/it]
                                                   

  2%|▏         | 46/1848 [15:16<9:59:35, 19.96s/it]
  3%|▎         | 47/1848 [15:36<9:59:06, 19.96s/it]
                                                   

  3%|▎         | 47/1848 [15:36<9:59:06, 19.96s/it]
  3%|▎         | 48/1848 [15:56<9:58:54, 19.96s/it]
                                                   

  3%|▎         | 48/1848 [15:56<9:58:54, 19.96s/it]
  3%|▎         | 49/1848 [16:16<9:58:05, 19.95s/it]
                                                   

  3%|▎         | 49/1848 [16:16<9:58:05, 19.95s/it]
  3%|▎         | 50/1848 [16:36<9:57:22, 19.93s/it]
                                                   

  3%|▎         | 50/1848 [16:36<9:57:22, 19.93s/it]
  3%|▎         | 51/1848 [16:56<9:57:03, 19.93s/it]
                                                   

  3%|▎         | 51/1848 [16:56<9:57:03, 19.93s/it]
  3%|▎         | 52/1848 [17:16<9:56:28, 19.93s/it]
                                                   

  3%|▎         | 52/1848 [17:16<9:56:28, 19.93s/it]
  3%|▎         | 53/1848 [17:35<9:56:12, 19.93s/it]
                                                   

  3%|▎         | 53/1848 [17:35<9:56:12, 19.93s/it]
  3%|▎         | 54/1848 [17:55<9:56:04, 19.94s/it]
                                                   

  3%|▎         | 54/1848 [17:55<9:56:04, 19.94s/it]
  3%|▎         | 55/1848 [18:15<9:55:30, 19.93s/it]
                                                   

  3%|▎         | 55/1848 [18:15<9:55:30, 19.93s/it]
  3%|▎         | 56/1848 [18:35<9:55:12, 19.93s/it]
                                                   

  3%|▎         | 56/1848 [18:35<9:55:12, 19.93s/it]
  3%|▎         | 57/1848 [18:55<9:55:21, 19.95s/it]
                                                   

  3%|▎         | 57/1848 [18:55<9:55:21, 19.95s/it]
  3%|▎         | 58/1848 [19:15<9:55:06, 19.95s/it]
                                                   

  3%|▎         | 58/1848 [19:15<9:55:06, 19.95s/it]
  3%|▎         | 59/1848 [19:35<9:54:30, 19.94s/it]
                                                   

  3%|▎         | 59/1848 [19:35<9:54:30, 19.94s/it]
  3%|▎         | 60/1848 [19:55<9:53:26, 19.91s/it]
                                                   

  3%|▎         | 60/1848 [19:55<9:53:26, 19.91s/it]
  3%|▎         | 61/1848 [20:15<9:53:25, 19.92s/it]
                                                   

  3%|▎         | 61/1848 [20:15<9:53:25, 19.92s/it]
  3%|▎         | 62/1848 [20:35<9:52:36, 19.91s/it]
                                                   

  3%|▎         | 62/1848 [20:35<9:52:36, 19.91s/it]
  3%|▎         | 63/1848 [20:55<9:52:58, 19.93s/it]
                                                   

  3%|▎         | 63/1848 [20:55<9:52:58, 19.93s/it]
  3%|▎         | 64/1848 [21:15<9:53:02, 19.95s/it]
                                                   

  3%|▎         | 64/1848 [21:15<9:53:02, 19.95s/it]
  4%|▎         | 65/1848 [21:35<9:52:34, 19.94s/it]
                                                   

  4%|▎         | 65/1848 [21:35<9:52:34, 19.94s/it]
  4%|▎         | 66/1848 [21:55<9:53:05, 19.97s/it]
                                                   

  4%|▎         | 66/1848 [21:55<9:53:05, 19.97s/it]
  4%|▎         | 67/1848 [22:15<9:53:11, 19.98s/it]
                                                   

  4%|▎         | 67/1848 [22:15<9:53:11, 19.98s/it]
  4%|▎         | 68/1848 [22:35<9:52:02, 19.96s/it]
                                                   

  4%|▎         | 68/1848 [22:35<9:52:02, 19.96s/it]
  4%|▎         | 69/1848 [22:55<9:51:37, 19.95s/it]
                                                   

  4%|▎         | 69/1848 [22:55<9:51:37, 19.95s/it]
  4%|▍         | 70/1848 [23:15<9:51:52, 19.97s/it]
                                                   

  4%|▍         | 70/1848 [23:15<9:51:52, 19.97s/it]
  4%|▍         | 71/1848 [23:34<9:50:55, 19.95s/it]
                                                   

  4%|▍         | 71/1848 [23:34<9:50:55, 19.95s/it]
  4%|▍         | 72/1848 [23:54<9:50:49, 19.96s/it]
                                                   

  4%|▍         | 72/1848 [23:54<9:50:49, 19.96s/it]
  4%|▍         | 73/1848 [24:14<9:50:29, 19.96s/it]
                                                   

  4%|▍         | 73/1848 [24:14<9:50:29, 19.96s/it]
  4%|▍         | 74/1848 [24:34<9:50:06, 19.96s/it]
                                                   

  4%|▍         | 74/1848 [24:34<9:50:06, 19.96s/it]
  4%|▍         | 75/1848 [24:54<9:49:22, 19.95s/it]
                                                   

  4%|▍         | 75/1848 [24:54<9:49:22, 19.95s/it]
  4%|▍         | 76/1848 [25:14<9:49:02, 19.95s/it]
                                                   

  4%|▍         | 76/1848 [25:14<9:49:02, 19.95s/it]
  4%|▍         | 77/1848 [25:34<9:48:51, 19.95s/it]
                                                   

  4%|▍         | 77/1848 [25:34<9:48:51, 19.95s/it]
  4%|▍         | 78/1848 [25:54<9:48:31, 19.95s/it]
                                                   

  4%|▍         | 78/1848 [25:54<9:48:31, 19.95s/it]
  4%|▍         | 79/1848 [26:14<9:48:15, 19.95s/it]
                                                   

  4%|▍         | 79/1848 [26:14<9:48:15, 19.95s/it]
  4%|▍         | 80/1848 [26:34<9:47:31, 19.94s/it]
                                                   

  4%|▍         | 80/1848 [26:34<9:47:31, 19.94s/it]
  4%|▍         | 81/1848 [26:54<9:47:54, 19.96s/it]
                                                   

  4%|▍         | 81/1848 [26:54<9:47:54, 19.96s/it]
  4%|▍         | 82/1848 [27:14<9:47:31, 19.96s/it]
                                                   

  4%|▍         | 82/1848 [27:14<9:47:31, 19.96s/it]
  4%|▍         | 83/1848 [27:34<9:46:48, 19.95s/it]
                                                   

  4%|▍         | 83/1848 [27:34<9:46:48, 19.95s/it]
  5%|▍         | 84/1848 [27:54<9:46:28, 19.95s/it]
                                                   

  5%|▍         | 84/1848 [27:54<9:46:28, 19.95s/it]
  5%|▍         | 85/1848 [28:14<9:46:25, 19.96s/it]
                                                   

  5%|▍         | 85/1848 [28:14<9:46:25, 19.96s/it]
  5%|▍         | 86/1848 [28:34<9:45:51, 19.95s/it]
                                                   

  5%|▍         | 86/1848 [28:34<9:45:51, 19.95s/it]
  5%|▍         | 87/1848 [28:54<9:45:05, 19.93s/it]
                                                   

  5%|▍         | 87/1848 [28:54<9:45:05, 19.93s/it]
  5%|▍         | 88/1848 [29:14<9:45:04, 19.95s/it]
                                                   

  5%|▍         | 88/1848 [29:14<9:45:04, 19.95s/it]
  5%|▍         | 89/1848 [29:34<9:44:35, 19.94s/it]
                                                   

  5%|▍         | 89/1848 [29:34<9:44:35, 19.94s/it]
  5%|▍         | 90/1848 [29:53<9:44:11, 19.94s/it]
                                                   

  5%|▍         | 90/1848 [29:53<9:44:11, 19.94s/it]
  5%|▍         | 91/1848 [30:13<9:44:06, 19.95s/it]
                                                   

  5%|▍         | 91/1848 [30:13<9:44:06, 19.95s/it]
  5%|▍         | 92/1848 [30:33<9:43:03, 19.92s/it]
                                                   

  5%|▍         | 92/1848 [30:33<9:43:03, 19.92s/it]
  5%|▌         | 93/1848 [30:53<9:42:49, 19.93s/it]
                                                   

  5%|▌         | 93/1848 [30:53<9:42:49, 19.93s/it]
  5%|▌         | 94/1848 [31:13<9:42:41, 19.93s/it]
                                                   

  5%|▌         | 94/1848 [31:13<9:42:41, 19.93s/it]
  5%|▌         | 95/1848 [31:33<9:42:52, 19.95s/it]
                                                   

  5%|▌         | 95/1848 [31:33<9:42:52, 19.95s/it]
  5%|▌         | 96/1848 [31:53<9:42:36, 19.95s/it]
                                                   

  5%|▌         | 96/1848 [31:53<9:42:36, 19.95s/it]
  5%|▌         | 97/1848 [32:13<9:41:55, 19.94s/it]
                                                   

  5%|▌         | 97/1848 [32:13<9:41:55, 19.94s/it]
  5%|▌         | 98/1848 [32:33<9:41:50, 19.95s/it]
                                                   

  5%|▌         | 98/1848 [32:33<9:41:50, 19.95s/it]
  5%|▌         | 99/1848 [32:53<9:41:29, 19.95s/it]
                                                   

  5%|▌         | 99/1848 [32:53<9:41:29, 19.95s/it]
  5%|▌         | 100/1848 [33:13<9:41:12, 19.95s/it]
                                                    

  5%|▌         | 100/1848 [33:13<9:41:12, 19.95s/it]
  5%|▌         | 101/1848 [33:34<9:50:18, 20.27s/it]
                                                    

  5%|▌         | 101/1848 [33:34<9:50:18, 20.27s/it]
  6%|▌         | 102/1848 [33:54<9:47:03, 20.17s/it]
                                                    

  6%|▌         | 102/1848 [33:54<9:47:03, 20.17s/it]
  6%|▌         | 103/1848 [34:14<9:44:46, 20.11s/it]
                                                    

  6%|▌         | 103/1848 [34:14<9:44:46, 20.11s/it]
  6%|▌         | 104/1848 [34:34<9:43:21, 20.07s/it]
                                                    

  6%|▌         | 104/1848 [34:34<9:43:21, 20.07s/it]
  6%|▌         | 105/1848 [34:54<9:41:35, 20.02s/it]
                                                    

  6%|▌         | 105/1848 [34:54<9:41:35, 20.02s/it]
  6%|▌         | 106/1848 [35:14<9:39:51, 19.97s/it]
                                                    

  6%|▌         | 106/1848 [35:14<9:39:51, 19.97s/it]
  6%|▌         | 107/1848 [35:34<9:39:08, 19.96s/it]
                                                    

  6%|▌         | 107/1848 [35:34<9:39:08, 19.96s/it]
  6%|▌         | 108/1848 [35:53<9:37:18, 19.91s/it]
                                                    

  6%|▌         | 108/1848 [35:53<9:37:18, 19.91s/it]
  6%|▌         | 109/1848 [36:13<9:37:03, 19.91s/it]
                                                    

  6%|▌         | 109/1848 [36:13<9:37:03, 19.91s/it]
  6%|▌         | 110/1848 [36:33<9:37:32, 19.94s/it]
                                                    

  6%|▌         | 110/1848 [36:33<9:37:32, 19.94s/it]
  6%|▌         | 111/1848 [36:53<9:36:59, 19.93s/it]
                                                    

  6%|▌         | 111/1848 [36:53<9:36:59, 19.93s/it]
  6%|▌         | 112/1848 [37:13<9:36:20, 19.92s/it]
                                                    

  6%|▌         | 112/1848 [37:13<9:36:20, 19.92s/it]
  6%|▌         | 113/1848 [37:33<9:36:36, 19.94s/it]
                                                    
{'loss': 1.5526, 'learning_rate': 1.4092370129870131e-05, 'epoch': 0.0}
+{'loss': 1.5433, 'learning_rate': 1.408474025974026e-05, 'epoch': 0.0}
+{'loss': 1.6301, 'learning_rate': 1.407711038961039e-05, 'epoch': 0.0}
+{'loss': 1.4464, 'learning_rate': 1.406948051948052e-05, 'epoch': 0.01}
+{'loss': 1.5914, 'learning_rate': 1.4061850649350651e-05, 'epoch': 0.01}
+{'loss': 1.3921, 'learning_rate': 1.405422077922078e-05, 'epoch': 0.01}
+{'loss': 1.4631, 'learning_rate': 1.4046590909090909e-05, 'epoch': 0.01}
+{'loss': 1.536, 'learning_rate': 1.403896103896104e-05, 'epoch': 0.01}
+{'loss': 1.5771, 'learning_rate': 1.4031331168831168e-05, 'epoch': 0.01}
+{'loss': 1.7726, 'learning_rate': 1.4023701298701299e-05, 'epoch': 0.02}
+{'loss': 1.5586, 'learning_rate': 1.401607142857143e-05, 'epoch': 0.02}
+{'loss': 1.4274, 'learning_rate': 1.400844155844156e-05, 'epoch': 0.02}
+{'loss': 1.3808, 'learning_rate': 1.4000811688311689e-05, 'epoch': 0.02}
+{'loss': 1.3625, 'learning_rate': 1.3993181818181819e-05, 'epoch': 0.02}
+{'loss': 1.3933, 'learning_rate': 1.398555194805195e-05, 'epoch': 0.02}
+{'loss': 1.6056, 'learning_rate': 1.3977922077922078e-05, 'epoch': 0.03}
+{'loss': 1.3856, 'learning_rate': 1.3970292207792209e-05, 'epoch': 0.03}
+{'loss': 1.4664, 'learning_rate': 1.396266233766234e-05, 'epoch': 0.03}
+{'loss': 1.4192, 'learning_rate': 1.3955032467532466e-05, 'epoch': 0.03}
+{'loss': 1.7521, 'learning_rate': 1.3947402597402597e-05, 'epoch': 0.03}
+{'loss': 1.5137, 'learning_rate': 1.3939772727272727e-05, 'epoch': 0.03}
+{'loss': 1.4668, 'learning_rate': 1.3932142857142858e-05, 'epoch': 0.04}
+{'loss': 1.5488, 'learning_rate': 1.3924512987012987e-05, 'epoch': 0.04}
+{'loss': 1.3526, 'learning_rate': 1.3916883116883117e-05, 'epoch': 0.04}
+{'loss': 1.3949, 'learning_rate': 1.3909253246753248e-05, 'epoch': 0.04}
+{'loss': 1.5166, 'learning_rate': 1.3901623376623377e-05, 'epoch': 0.04}
+{'loss': 1.3448, 'learning_rate': 1.3893993506493507e-05, 'epoch': 0.04}
+{'loss': 1.2783, 'learning_rate': 1.3886363636363638e-05, 'epoch': 0.05}
+{'loss': 1.4795, 'learning_rate': 1.3878733766233768e-05, 'epoch': 0.05}
+{'loss': 1.5968, 'learning_rate': 1.3871103896103897e-05, 'epoch': 0.05}
+{'loss': 1.4057, 'learning_rate': 1.3863474025974026e-05, 'epoch': 0.05}
+{'loss': 1.4839, 'learning_rate': 1.3855844155844156e-05, 'epoch': 0.05}
+{'loss': 1.4443, 'learning_rate': 1.3848214285714285e-05, 'epoch': 0.05}
+{'loss': 1.6602, 'learning_rate': 1.3840584415584415e-05, 'epoch': 0.06}
+{'loss': 1.3424, 'learning_rate': 1.3832954545454546e-05, 'epoch': 0.06}
+{'loss': 1.497, 'learning_rate': 1.3825324675324676e-05, 'epoch': 0.06}
+{'loss': 1.5593, 'learning_rate': 1.3817694805194805e-05, 'epoch': 0.06}
+{'loss': 1.6779, 'learning_rate': 1.3810064935064936e-05, 'epoch': 0.06}
+{'loss': 1.7035, 'learning_rate': 1.3802435064935066e-05, 'epoch': 0.06}
+{'loss': 1.3916, 'learning_rate': 1.3794805194805195e-05, 'epoch': 0.06}
+{'loss': 1.3803, 'learning_rate': 1.3787175324675326e-05, 'epoch': 0.07}
+{'loss': 1.4854, 'learning_rate': 1.3779545454545456e-05, 'epoch': 0.07}
+{'loss': 1.3735, 'learning_rate': 1.3771915584415585e-05, 'epoch': 0.07}
+{'loss': 1.5322, 'learning_rate': 1.3764285714285714e-05, 'epoch': 0.07}
+{'loss': 1.3965, 'learning_rate': 1.3756655844155844e-05, 'epoch': 0.07}
+{'loss': 1.387, 'learning_rate': 1.3749025974025975e-05, 'epoch': 0.07}
+{'loss': 1.3877, 'learning_rate': 1.3741396103896103e-05, 'epoch': 0.08}
+{'loss': 1.4045, 'learning_rate': 1.3733766233766234e-05, 'epoch': 0.08}
+{'loss': 1.4934, 'learning_rate': 1.3726136363636364e-05, 'epoch': 0.08}
+{'loss': 1.6657, 'learning_rate': 1.3718506493506493e-05, 'epoch': 0.08}
+{'loss': 1.3867, 'learning_rate': 1.3710876623376624e-05, 'epoch': 0.08}
+{'loss': 1.5064, 'learning_rate': 1.3703246753246754e-05, 'epoch': 0.08}
+{'loss': 1.2674, 'learning_rate': 1.3695616883116885e-05, 'epoch': 0.09}
+{'loss': 1.198, 'learning_rate': 1.3687987012987014e-05, 'epoch': 0.09}
+{'loss': 1.4513, 'learning_rate': 1.3680357142857144e-05, 'epoch': 0.09}
+{'loss': 1.4557, 'learning_rate': 1.3672727272727273e-05, 'epoch': 0.09}
+{'loss': 1.5939, 'learning_rate': 1.3665097402597402e-05, 'epoch': 0.09}
+{'loss': 1.4544, 'learning_rate': 1.3657467532467532e-05, 'epoch': 0.09}
+{'loss': 1.527, 'learning_rate': 1.3649837662337663e-05, 'epoch': 0.1}
+{'loss': 1.4746, 'learning_rate': 1.3642207792207793e-05, 'epoch': 0.1}
+{'loss': 1.3757, 'learning_rate': 1.3634577922077922e-05, 'epoch': 0.1}
+{'loss': 1.5794, 'learning_rate': 1.3626948051948052e-05, 'epoch': 0.1}
+{'loss': 1.3203, 'learning_rate': 1.3619318181818183e-05, 'epoch': 0.1}
+{'loss': 1.3629, 'learning_rate': 1.3611688311688312e-05, 'epoch': 0.1}
+{'loss': 1.4602, 'learning_rate': 1.3604058441558442e-05, 'epoch': 0.11}
+{'loss': 1.4734, 'learning_rate': 1.3596428571428573e-05, 'epoch': 0.11}
+{'loss': 1.2285, 'learning_rate': 1.3588798701298703e-05, 'epoch': 0.11}
+{'loss': 1.5664, 'learning_rate': 1.3581168831168832e-05, 'epoch': 0.11}
+{'loss': 1.2714, 'learning_rate': 1.3573538961038961e-05, 'epoch': 0.11}
+{'loss': 1.2741, 'learning_rate': 1.3565909090909091e-05, 'epoch': 0.11}
+{'loss': 1.5036, 'learning_rate': 1.355827922077922e-05, 'epoch': 0.12}
+{'loss': 1.4638, 'learning_rate': 1.355064935064935e-05, 'epoch': 0.12}
+{'loss': 1.4893, 'learning_rate': 1.3543019480519481e-05, 'epoch': 0.12}
+{'loss': 1.5395, 'learning_rate': 1.3535389610389612e-05, 'epoch': 0.12}
+{'loss': 1.5829, 'learning_rate': 1.352775974025974e-05, 'epoch': 0.12}
+{'loss': 1.2989, 'learning_rate': 1.3520129870129871e-05, 'epoch': 0.12}
+{'loss': 1.5344, 'learning_rate': 1.3512500000000001e-05, 'epoch': 0.12}
+{'loss': 1.3065, 'learning_rate': 1.350487012987013e-05, 'epoch': 0.13}
+{'loss': 1.2581, 'learning_rate': 1.349724025974026e-05, 'epoch': 0.13}
+{'loss': 1.4582, 'learning_rate': 1.348961038961039e-05, 'epoch': 0.13}
+{'loss': 1.2262, 'learning_rate': 1.348198051948052e-05, 'epoch': 0.13}
+{'loss': 1.508, 'learning_rate': 1.3474350649350649e-05, 'epoch': 0.13}
+{'loss': 1.3379, 'learning_rate': 1.346672077922078e-05, 'epoch': 0.13}
+{'loss': 1.2839, 'learning_rate': 1.345909090909091e-05, 'epoch': 0.14}
+{'loss': 1.62, 'learning_rate': 1.3451461038961039e-05, 'epoch': 0.14}
+{'loss': 1.2938, 'learning_rate': 1.344383116883117e-05, 'epoch': 0.14}
+{'loss': 1.3257, 'learning_rate': 1.34362012987013e-05, 'epoch': 0.14}
+{'loss': 1.2192, 'learning_rate': 1.3428571428571429e-05, 'epoch': 0.14}
+{'loss': 1.2598, 'learning_rate': 1.3420941558441559e-05, 'epoch': 0.14}
+{'loss': 1.3164, 'learning_rate': 1.341331168831169e-05, 'epoch': 0.15}
+{'loss': 1.2557, 'learning_rate': 1.340568181818182e-05, 'epoch': 0.15}
+{'loss': 1.2988, 'learning_rate': 1.3398051948051949e-05, 'epoch': 0.15}
+{'loss': 1.6454, 'learning_rate': 1.3390422077922078e-05, 'epoch': 0.15}
+{'loss': 1.2387, 'learning_rate': 1.3382792207792208e-05, 'epoch': 0.15}
+{'loss': 1.3542, 'learning_rate': 1.3375162337662337e-05, 'epoch': 0.15}
+{'loss': 1.5282, 'learning_rate': 1.3367532467532467e-05, 'epoch': 0.16}
+{'loss': 1.4482, 'learning_rate': 1.3359902597402598e-05, 'epoch': 0.16}
+{'loss': 1.1914, 'learning_rate': 1.3352272727272728e-05, 'epoch': 0.16}
+{'loss': 1.4809, 'learning_rate': 1.3344642857142857e-05, 'epoch': 0.16}
+{'loss': 1.4833, 'learning_rate': 1.3337012987012988e-05, 'epoch': 0.16}
+{'loss': 1.4928, 'learning_rate': 1.3329383116883118e-05, 'epoch': 0.16}
+{'loss': 1.1595, 'learning_rate': 1.3321753246753247e-05, 'epoch': 0.17}
+{'loss': 1.4382, 'learning_rate': 1.3314123376623378e-05, 'epoch': 0.17}
+{'loss': 1.5168, 'learning_rate': 1.3306493506493508e-05, 'epoch': 0.17}
+{'loss': 1.3912, 'learning_rate': 1.3298863636363637e-05, 'epoch': 0.17}
+{'loss': 1.571, 'learning_rate': 1.3291233766233766e-05, 'epoch': 0.17}
+{'loss': 1.1933, 'learning_rate': 1.3283603896103896e-05, 'epoch': 0.17}
+{'loss': 1.3237, 'learning_rate': 1.3275974025974027e-05, 'epoch': 0.18}
+{'loss': 1.281, 'learning_rate': 1.3268344155844155e-05, 'epoch': 0.18}
+{'loss': 1.2898, 'learning_rate': 1.3260714285714286e-05, 'epoch': 0.18}
+{'loss': 1.4582, 'learning_rate': 1.3253084415584416e-05, 'epoch': 0.18}
+{'loss': 1.6352, 'learning_rate': 1.3245454545454547e-05, 'epoch': 0.18}
+
  6%|▌         | 113/1848 [37:33<9:36:36, 19.94s/it]
  6%|▌         | 114/1848 [37:53<9:36:47, 19.96s/it]
                                                    

  6%|▌         | 114/1848 [37:53<9:36:47, 19.96s/it]
  6%|▌         | 115/1848 [38:13<9:35:40, 19.93s/it]
                                                    

  6%|▌         | 115/1848 [38:13<9:35:40, 19.93s/it]
  6%|▋         | 116/1848 [38:33<9:35:12, 19.93s/it]
                                                    

  6%|▋         | 116/1848 [38:33<9:35:12, 19.93s/it]
  6%|▋         | 117/1848 [38:53<9:34:03, 19.90s/it]
                                                    

  6%|▋         | 117/1848 [38:53<9:34:03, 19.90s/it]
  6%|▋         | 118/1848 [39:13<9:34:19, 19.92s/it]
                                                    

  6%|▋         | 118/1848 [39:13<9:34:19, 19.92s/it]
  6%|▋         | 119/1848 [39:33<9:34:39, 19.94s/it]
                                                    

  6%|▋         | 119/1848 [39:33<9:34:39, 19.94s/it]
  6%|▋         | 120/1848 [39:53<9:33:58, 19.93s/it]
                                                    

  6%|▋         | 120/1848 [39:53<9:33:58, 19.93s/it]
  7%|▋         | 121/1848 [40:12<9:32:43, 19.90s/it]
                                                    

  7%|▋         | 121/1848 [40:12<9:32:43, 19.90s/it]
  7%|▋         | 122/1848 [40:32<9:32:09, 19.89s/it]
                                                    

  7%|▋         | 122/1848 [40:32<9:32:09, 19.89s/it]
  7%|▋         | 123/1848 [40:52<9:32:21, 19.91s/it]
                                                    

  7%|▋         | 123/1848 [40:52<9:32:21, 19.91s/it]
  7%|▋         | 124/1848 [41:12<9:32:52, 19.94s/it]
                                                    

  7%|▋         | 124/1848 [41:12<9:32:52, 19.94s/it]
  7%|▋         | 125/1848 [41:32<9:32:00, 19.92s/it]
                                                    

  7%|▋         | 125/1848 [41:32<9:32:00, 19.92s/it]
  7%|▋         | 126/1848 [41:52<9:31:59, 19.93s/it]
                                                    

  7%|▋         | 126/1848 [41:52<9:31:59, 19.93s/it]
  7%|▋         | 127/1848 [42:12<9:31:39, 19.93s/it]
                                                    

  7%|▋         | 127/1848 [42:12<9:31:39, 19.93s/it]
  7%|▋         | 128/1848 [42:32<9:31:24, 19.93s/it]
                                                    

  7%|▋         | 128/1848 [42:32<9:31:24, 19.93s/it]
  7%|▋         | 129/1848 [42:52<9:31:15, 19.94s/it]
                                                    

  7%|▋         | 129/1848 [42:52<9:31:15, 19.94s/it]
  7%|▋         | 130/1848 [43:12<9:31:02, 19.94s/it]
                                                    

  7%|▋         | 130/1848 [43:12<9:31:02, 19.94s/it]
  7%|▋         | 131/1848 [43:32<9:30:50, 19.95s/it]
                                                    

  7%|▋         | 131/1848 [43:32<9:30:50, 19.95s/it]
  7%|▋         | 132/1848 [43:52<9:29:15, 19.90s/it]
                                                    

  7%|▋         | 132/1848 [43:52<9:29:15, 19.90s/it]
  7%|▋         | 133/1848 [44:11<9:29:12, 19.91s/it]
                                                    

  7%|▋         | 133/1848 [44:11<9:29:12, 19.91s/it]
  7%|▋         | 134/1848 [44:31<9:29:38, 19.94s/it]
                                                    

  7%|▋         | 134/1848 [44:31<9:29:38, 19.94s/it]
  7%|▋         | 135/1848 [44:51<9:29:34, 19.95s/it]
                                                    

  7%|▋         | 135/1848 [44:51<9:29:34, 19.95s/it]
  7%|▋         | 136/1848 [45:11<9:29:09, 19.95s/it]
                                                    

  7%|▋         | 136/1848 [45:11<9:29:09, 19.95s/it]
  7%|▋         | 137/1848 [45:31<9:28:41, 19.94s/it]
                                                    

  7%|▋         | 137/1848 [45:31<9:28:41, 19.94s/it]
  7%|▋         | 138/1848 [45:51<9:29:02, 19.97s/it]
                                                    

  7%|▋         | 138/1848 [45:51<9:29:02, 19.97s/it]
  8%|▊         | 139/1848 [46:11<9:29:02, 19.98s/it]
                                                    

  8%|▊         | 139/1848 [46:11<9:29:02, 19.98s/it]
  8%|▊         | 140/1848 [46:31<9:28:20, 19.97s/it]
                                                    

  8%|▊         | 140/1848 [46:31<9:28:20, 19.97s/it]
  8%|▊         | 141/1848 [46:51<9:27:08, 19.93s/it]
                                                    

  8%|▊         | 141/1848 [46:51<9:27:08, 19.93s/it]
  8%|▊         | 142/1848 [47:11<9:26:55, 19.94s/it]
                                                    

  8%|▊         | 142/1848 [47:11<9:26:55, 19.94s/it]
  8%|▊         | 143/1848 [47:31<9:26:34, 19.94s/it]
                                                    

  8%|▊         | 143/1848 [47:31<9:26:34, 19.94s/it]
  8%|▊         | 144/1848 [47:51<9:25:37, 19.92s/it]
                                                    

  8%|▊         | 144/1848 [47:51<9:25:37, 19.92s/it]
  8%|▊         | 145/1848 [48:11<9:25:30, 19.92s/it]
                                                    

  8%|▊         | 145/1848 [48:11<9:25:30, 19.92s/it]
  8%|▊         | 146/1848 [48:31<9:25:54, 19.95s/it]
                                                    

  8%|▊         | 146/1848 [48:31<9:25:54, 19.95s/it]
  8%|▊         | 147/1848 [48:51<9:25:47, 19.96s/it]
                                                    

  8%|▊         | 147/1848 [48:51<9:25:47, 19.96s/it]
  8%|▊         | 148/1848 [49:11<9:25:24, 19.96s/it]
                                                    

  8%|▊         | 148/1848 [49:11<9:25:24, 19.96s/it]
  8%|▊         | 149/1848 [49:31<9:23:47, 19.91s/it]
                                                    

  8%|▊         | 149/1848 [49:31<9:23:47, 19.91s/it]
  8%|▊         | 150/1848 [49:50<9:23:00, 19.89s/it]
                                                    

  8%|▊         | 150/1848 [49:50<9:23:00, 19.89s/it]
  8%|▊         | 151/1848 [50:10<9:22:23, 19.88s/it]
                                                    

  8%|▊         | 151/1848 [50:10<9:22:23, 19.88s/it]
  8%|▊         | 152/1848 [50:30<9:22:11, 19.89s/it]
                                                    

  8%|▊         | 152/1848 [50:30<9:22:11, 19.89s/it]
  8%|▊         | 153/1848 [50:50<9:21:48, 19.89s/it]
                                                    

  8%|▊         | 153/1848 [50:50<9:21:48, 19.89s/it]
  8%|▊         | 154/1848 [51:10<9:21:43, 19.90s/it]
                                                    

  8%|▊         | 154/1848 [51:10<9:21:43, 19.90s/it]
  8%|▊         | 155/1848 [51:30<9:21:07, 19.89s/it]
                                                    

  8%|▊         | 155/1848 [51:30<9:21:07, 19.89s/it]
  8%|▊         | 156/1848 [51:50<9:21:18, 19.90s/it]
                                                    

  8%|▊         | 156/1848 [51:50<9:21:18, 19.90s/it]
  8%|▊         | 157/1848 [52:10<9:21:10, 19.91s/it]
                                                    

  8%|▊         | 157/1848 [52:10<9:21:10, 19.91s/it]
  9%|▊         | 158/1848 [52:29<9:16:54, 19.77s/it]
                                                    

  9%|▊         | 158/1848 [52:29<9:16:54, 19.77s/it]
  9%|▊         | 159/1848 [52:49<9:17:26, 19.80s/it]
                                                    

  9%|▊         | 159/1848 [52:49<9:17:26, 19.80s/it]
  9%|▊         | 160/1848 [53:09<9:18:13, 19.84s/it]
                                                    

  9%|▊         | 160/1848 [53:09<9:18:13, 19.84s/it]
  9%|▊         | 161/1848 [53:29<9:18:14, 19.85s/it]
                                                    

  9%|▊         | 161/1848 [53:29<9:18:14, 19.85s/it]
  9%|▉         | 162/1848 [53:49<9:18:24, 19.87s/it]
                                                    

  9%|▉         | 162/1848 [53:49<9:18:24, 19.87s/it]
  9%|▉         | 163/1848 [54:09<9:18:46, 19.90s/it]
                                                    

  9%|▉         | 163/1848 [54:09<9:18:46, 19.90s/it]
  9%|▉         | 164/1848 [54:29<9:18:29, 19.90s/it]
                                                    

  9%|▉         | 164/1848 [54:29<9:18:29, 19.90s/it]
  9%|▉         | 165/1848 [54:49<9:18:29, 19.91s/it]
                                                    

  9%|▉         | 165/1848 [54:49<9:18:29, 19.91s/it]
  9%|▉         | 166/1848 [55:08<9:17:59, 19.90s/it]
                                                    

  9%|▉         | 166/1848 [55:08<9:17:59, 19.90s/it]
  9%|▉         | 167/1848 [55:28<9:16:37, 19.87s/it]
                                                    

  9%|▉         | 167/1848 [55:28<9:16:37, 19.87s/it]
  9%|▉         | 168/1848 [55:48<9:16:52, 19.89s/it]
                                                    

  9%|▉         | 168/1848 [55:48<9:16:52, 19.89s/it]
  9%|▉         | 169/1848 [56:08<9:17:20, 19.92s/it]
                                                    

  9%|▉         | 169/1848 [56:08<9:17:20, 19.92s/it]
  9%|▉         | 170/1848 [56:28<9:16:32, 19.90s/it]
                                                    

  9%|▉         | 170/1848 [56:28<9:16:32, 19.90s/it]
  9%|▉         | 171/1848 [56:48<9:16:26, 19.91s/it]
                                                    

  9%|▉         | 171/1848 [56:48<9:16:26, 19.91s/it]
  9%|▉         | 172/1848 [57:08<9:16:29, 19.92s/it]
                                                    

  9%|▉         | 172/1848 [57:08<9:16:29, 19.92s/it]
  9%|▉         | 173/1848 [57:28<9:16:14, 19.93s/it]
                                                    

  9%|▉         | 173/1848 [57:28<9:16:14, 19.93s/it]
  9%|▉         | 174/1848 [57:48<9:15:33, 19.91s/it]
                                                    

  9%|▉         | 174/1848 [57:48<9:15:33, 19.91s/it]
  9%|▉         | 175/1848 [58:08<9:14:51, 19.90s/it]
                                                    

  9%|▉         | 175/1848 [58:08<9:14:51, 19.90s/it]
 10%|▉         | 176/1848 [58:27<9:14:31, 19.90s/it]
                                                    

 10%|▉         | 176/1848 [58:27<9:14:31, 19.90s/it]
 10%|▉         | 177/1848 [58:47<9:14:05, 19.90s/it]
                                                    

 10%|▉         | 177/1848 [58:47<9:14:05, 19.90s/it]
 10%|▉         | 178/1848 [59:07<9:13:59, 19.90s/it]
                                                    

 10%|▉         | 178/1848 [59:07<9:13:59, 19.90s/it]
 10%|▉         | 179/1848 [59:27<9:13:43, 19.91s/it]
                                                    

 10%|▉         | 179/1848 [59:27<9:13:43, 19.91s/it]
 10%|▉         | 180/1848 [59:47<9:14:02, 19.93s/it]
                                                    

 10%|▉         | 180/1848 [59:47<9:14:02, 19.93s/it]
 10%|▉         | 181/1848 [1:00:07<9:13:49, 19.93s/it]
                                                      

 10%|▉         | 181/1848 [1:00:07<9:13:49, 19.93s/it]
 10%|▉         | 182/1848 [1:00:27<9:13:20, 19.93s/it]
                                                      

 10%|▉         | 182/1848 [1:00:27<9:13:20, 19.93s/it]
 10%|▉         | 183/1848 [1:00:47<9:13:00, 19.93s/it]
                                                      

 10%|▉         | 183/1848 [1:00:47<9:13:00, 19.93s/it]
 10%|▉         | 184/1848 [1:01:07<9:13:26, 19.96s/it]
                                                      

 10%|▉         | 184/1848 [1:01:07<9:13:26, 19.96s/it]
 10%|█         | 185/1848 [1:01:27<9:12:56, 19.95s/it]
                                                      

 10%|█         | 185/1848 [1:01:27<9:12:56, 19.95s/it]
 10%|█         | 186/1848 [1:01:47<9:12:18, 19.94s/it]
                                                      

 10%|█         | 186/1848 [1:01:47<9:12:18, 19.94s/it]
 10%|█         | 187/1848 [1:02:07<9:12:15, 19.95s/it]
                                                      

 10%|█         | 187/1848 [1:02:07<9:12:15, 19.95s/it]
 10%|█         | 188/1848 [1:02:27<9:11:16, 19.93s/it]
                                                      

 10%|█         | 188/1848 [1:02:27<9:11:16, 19.93s/it]
 10%|█         | 189/1848 [1:02:47<9:11:29, 19.95s/it]
                                                      

 10%|█         | 189/1848 [1:02:47<9:11:29, 19.95s/it]
 10%|█         | 190/1848 [1:03:07<9:10:33, 19.92s/it]
                                                      

 10%|█         | 190/1848 [1:03:07<9:10:33, 19.92s/it]
 10%|█         | 191/1848 [1:03:27<9:11:07, 19.96s/it]
                                                      

 10%|█         | 191/1848 [1:03:27<9:11:07, 19.96s/it]
 10%|█         | 192/1848 [1:03:47<9:10:46, 19.96s/it]
                                                      

 10%|█         | 192/1848 [1:03:47<9:10:46, 19.96s/it]
 10%|█         | 193/1848 [1:04:07<9:10:48, 19.97s/it]
                                                      

 10%|█         | 193/1848 [1:04:07<9:10:48, 19.97s/it]
 10%|█         | 194/1848 [1:04:27<9:10:42, 19.98s/it]
                                                      

 10%|█         | 194/1848 [1:04:27<9:10:42, 19.98s/it]
 11%|█         | 195/1848 [1:04:47<9:10:59, 20.00s/it]
                                                      

 11%|█         | 195/1848 [1:04:47<9:10:59, 20.00s/it]
 11%|█         | 196/1848 [1:05:07<9:10:43, 20.00s/it]
                                                      

 11%|█         | 196/1848 [1:05:07<9:10:43, 20.00s/it]
 11%|█         | 197/1848 [1:05:27<9:10:03, 19.99s/it]
                                                      

 11%|█         | 197/1848 [1:05:27<9:10:03, 19.99s/it]
 11%|█         | 198/1848 [1:05:46<9:09:10, 19.97s/it]
                                                      

 11%|█         | 198/1848 [1:05:46<9:09:10, 19.97s/it]
 11%|█         | 199/1848 [1:06:06<9:08:38, 19.96s/it]
                                                      

 11%|█         | 199/1848 [1:06:06<9:08:38, 19.96s/it]
 11%|█         | 200/1848 [1:06:26<9:08:27, 19.97s/it]
                                                      

 11%|█         | 200/1848 [1:06:26<9:08:27, 19.97s/it]
 11%|█         | 201/1848 [1:06:47<9:14:58, 20.22s/it]
                                                      

 11%|█         | 201/1848 [1:06:47<9:14:58, 20.22s/it]
 11%|█         | 202/1848 [1:07:07<9:12:21, 20.13s/it]
                                                      

 11%|█         | 202/1848 [1:07:07<9:12:21, 20.13s/it]
 11%|█         | 203/1848 [1:07:27<9:10:01, 20.06s/it]
                                                      

 11%|█         | 203/1848 [1:07:27<9:10:01, 20.06s/it]
 11%|█         | 204/1848 [1:07:47<9:09:05, 20.04s/it]
                                                      

 11%|█         | 204/1848 [1:07:47<9:09:05, 20.04s/it]
 11%|█         | 205/1848 [1:08:07<9:09:00, 20.05s/it]
                                                      

 11%|█         | 205/1848 [1:08:07<9:09:00, 20.05s/it]
 11%|█         | 206/1848 [1:08:27<9:07:51, 20.02s/it]
                                                      

 11%|█         | 206/1848 [1:08:27<9:07:51, 20.02s/it]
 11%|█         | 207/1848 [1:08:47<9:07:26, 20.02s/it]
                                                      

 11%|█         | 207/1848 [1:08:47<9:07:26, 20.02s/it]
 11%|█▏        | 208/1848 [1:09:07<9:06:38, 20.00s/it]
                                                      

 11%|█▏        | 208/1848 [1:09:07<9:06:38, 20.00s/it]
 11%|█▏        | 209/1848 [1:09:27<9:06:10, 19.99s/it]
                                                      

 11%|█▏        | 209/1848 [1:09:27<9:06:10, 19.99s/it]
 11%|█▏        | 210/1848 [1:09:47<9:05:20, 19.98s/it]
                                                      

 11%|█▏        | 210/1848 [1:09:47<9:05:20, 19.98s/it]
 11%|█▏        | 211/1848 [1:10:07<9:05:09, 19.98s/it]
                                                      

 11%|█▏        | 211/1848 [1:10:07<9:05:09, 19.98s/it]
 11%|█▏        | 212/1848 [1:10:27<9:04:44, 19.98s/it]
                                                      

 11%|█▏        | 212/1848 [1:10:27<9:04:44, 19.98s/it]
 12%|█▏        | 213/1848 [1:10:47<9:04:20, 19.98s/it]
                                                      

 12%|█▏        | 213/1848 [1:10:47<9:04:20, 19.98s/it]
 12%|█▏        | 214/1848 [1:11:07<9:03:53, 19.97s/it]
                                                      

 12%|█▏        | 214/1848 [1:11:07<9:03:53, 19.97s/it]
 12%|█▏        | 215/1848 [1:11:27<9:03:46, 19.98s/it]
                                                      

 12%|█▏        | 215/1848 [1:11:27<9:03:46, 19.98s/it]
 12%|█▏        | 216/1848 [1:11:47<9:03:26, 19.98s/it]
                                                      

 12%|█▏        | 216/1848 [1:11:47<9:03:26, 19.98s/it]
 12%|█▏        | 217/1848 [1:12:07<9:02:48, 19.97s/it]
                                                      

 12%|█▏        | 217/1848 [1:12:07<9:02:48, 19.97s/it]
 12%|█▏        | 218/1848 [1:12:27<9:02:27, 19.97s/it]
                                                      

 12%|█▏        | 218/1848 [1:12:27<9:02:27, 19.97s/it]
 12%|█▏        | 219/1848 [1:12:47<9:02:30, 19.98s/it]
                                                      

 12%|█▏        | 219/1848 [1:12:47<9:02:30, 19.98s/it]
 12%|█▏        | 220/1848 [1:13:07<9:01:58, 19.97s/it]
                                                      

 12%|█▏        | 220/1848 [1:13:07<9:01:58, 19.97s/it]
 12%|█▏        | 221/1848 [1:13:27<9:01:35, 19.97s/it]
                                                      

 12%|█▏        | 221/1848 [1:13:27<9:01:35, 19.97s/it]
 12%|█▏        | 222/1848 [1:13:47<9:01:32, 19.98s/it]
                                                      

 12%|█▏        | 222/1848 [1:13:47<9:01:32, 19.98s/it]
 12%|█▏        | 223/1848 [1:14:07<9:01:23, 19.99s/it]
                                                      

 12%|█▏        | 223/1848 [1:14:07<9:01:23, 19.99s/it]
 12%|█▏        | 224/1848 [1:14:27<9:00:44, 19.98s/it]
                                                      

 12%|█▏        | 224/1848 [1:14:27<9:00:44, 19.98s/it]
 12%|█▏        | 225/1848 [1:14:47<9:00:23, 19.98s/it]
                                                      
{'loss': 1.2795, 'learning_rate': 1.3237824675324676e-05, 'epoch': 0.18}
+{'loss': 1.3248, 'learning_rate': 1.3230194805194806e-05, 'epoch': 0.19}
+{'loss': 1.2624, 'learning_rate': 1.3222564935064937e-05, 'epoch': 0.19}
+{'loss': 1.1749, 'learning_rate': 1.3214935064935066e-05, 'epoch': 0.19}
+{'loss': 1.3509, 'learning_rate': 1.3207305194805196e-05, 'epoch': 0.19}
+{'loss': 1.3204, 'learning_rate': 1.3199675324675325e-05, 'epoch': 0.19}
+{'loss': 1.2597, 'learning_rate': 1.3192045454545454e-05, 'epoch': 0.19}
+{'loss': 1.4429, 'learning_rate': 1.3184415584415584e-05, 'epoch': 0.19}
+{'loss': 1.342, 'learning_rate': 1.3176785714285715e-05, 'epoch': 0.2}
+{'loss': 1.5016, 'learning_rate': 1.3169155844155845e-05, 'epoch': 0.2}
+{'loss': 1.3346, 'learning_rate': 1.3161525974025974e-05, 'epoch': 0.2}
+{'loss': 1.1038, 'learning_rate': 1.3153896103896104e-05, 'epoch': 0.2}
+{'loss': 1.3052, 'learning_rate': 1.3146266233766235e-05, 'epoch': 0.2}
+{'loss': 1.2896, 'learning_rate': 1.3138636363636364e-05, 'epoch': 0.2}
+{'loss': 1.2456, 'learning_rate': 1.3131006493506494e-05, 'epoch': 0.21}
+{'loss': 1.2886, 'learning_rate': 1.3123376623376625e-05, 'epoch': 0.21}
+{'loss': 1.2267, 'learning_rate': 1.3115746753246754e-05, 'epoch': 0.21}
+{'loss': 1.3822, 'learning_rate': 1.3108116883116882e-05, 'epoch': 0.21}
+{'loss': 1.3868, 'learning_rate': 1.3100487012987013e-05, 'epoch': 0.21}
+{'loss': 1.514, 'learning_rate': 1.3092857142857143e-05, 'epoch': 0.21}
+{'loss': 1.2942, 'learning_rate': 1.3085227272727272e-05, 'epoch': 0.22}
+{'loss': 1.3634, 'learning_rate': 1.3077597402597403e-05, 'epoch': 0.22}
+{'loss': 1.4405, 'learning_rate': 1.3069967532467533e-05, 'epoch': 0.22}
+{'loss': 1.1387, 'learning_rate': 1.3062337662337664e-05, 'epoch': 0.22}
+{'loss': 1.3391, 'learning_rate': 1.3054707792207792e-05, 'epoch': 0.22}
+{'loss': 1.4527, 'learning_rate': 1.3047077922077923e-05, 'epoch': 0.22}
+{'loss': 1.3765, 'learning_rate': 1.3039448051948053e-05, 'epoch': 0.23}
+{'loss': 1.3788, 'learning_rate': 1.3031818181818182e-05, 'epoch': 0.23}
+{'loss': 1.2942, 'learning_rate': 1.3024188311688313e-05, 'epoch': 0.23}
+{'loss': 1.3371, 'learning_rate': 1.3016558441558442e-05, 'epoch': 0.23}
+{'loss': 1.2737, 'learning_rate': 1.3008928571428572e-05, 'epoch': 0.23}
+{'loss': 1.233, 'learning_rate': 1.3001298701298701e-05, 'epoch': 0.23}
+{'loss': 1.2004, 'learning_rate': 1.2993668831168831e-05, 'epoch': 0.24}
+{'loss': 1.4848, 'learning_rate': 1.2986038961038962e-05, 'epoch': 0.24}
+{'loss': 1.2523, 'learning_rate': 1.297840909090909e-05, 'epoch': 0.24}
+{'loss': 1.2575, 'learning_rate': 1.2970779220779221e-05, 'epoch': 0.24}
+{'loss': 1.2293, 'learning_rate': 1.2963149350649352e-05, 'epoch': 0.24}
+{'loss': 1.3846, 'learning_rate': 1.295551948051948e-05, 'epoch': 0.24}
+{'loss': 1.2502, 'learning_rate': 1.2947889610389611e-05, 'epoch': 0.25}
+{'loss': 1.2189, 'learning_rate': 1.2940259740259741e-05, 'epoch': 0.25}
+{'loss': 1.4056, 'learning_rate': 1.2932629870129872e-05, 'epoch': 0.25}
+{'loss': 1.2403, 'learning_rate': 1.2925e-05, 'epoch': 0.25}
+{'loss': 1.2488, 'learning_rate': 1.291737012987013e-05, 'epoch': 0.25}
+{'loss': 1.3499, 'learning_rate': 1.290974025974026e-05, 'epoch': 0.25}
+{'loss': 1.2737, 'learning_rate': 1.2902110389610389e-05, 'epoch': 0.25}
+{'loss': 1.4582, 'learning_rate': 1.289448051948052e-05, 'epoch': 0.26}
+{'loss': 1.2974, 'learning_rate': 1.288685064935065e-05, 'epoch': 0.26}
+{'loss': 1.3197, 'learning_rate': 1.287922077922078e-05, 'epoch': 0.26}
+{'loss': 1.2754, 'learning_rate': 1.287159090909091e-05, 'epoch': 0.26}
+{'loss': 1.4818, 'learning_rate': 1.286396103896104e-05, 'epoch': 0.26}
+{'loss': 1.2535, 'learning_rate': 1.285633116883117e-05, 'epoch': 0.26}
+{'loss': 1.0157, 'learning_rate': 1.2848701298701299e-05, 'epoch': 0.27}
+{'loss': 1.2641, 'learning_rate': 1.284107142857143e-05, 'epoch': 0.27}
+{'loss': 1.2784, 'learning_rate': 1.283344155844156e-05, 'epoch': 0.27}
+{'loss': 1.6431, 'learning_rate': 1.2825811688311689e-05, 'epoch': 0.27}
+{'loss': 1.3568, 'learning_rate': 1.2818181818181818e-05, 'epoch': 0.27}
+{'loss': 1.0697, 'learning_rate': 1.2810551948051948e-05, 'epoch': 0.27}
+{'loss': 1.3241, 'learning_rate': 1.2802922077922079e-05, 'epoch': 0.28}
+{'loss': 1.301, 'learning_rate': 1.2795292207792207e-05, 'epoch': 0.28}
+{'loss': 1.3826, 'learning_rate': 1.2787662337662338e-05, 'epoch': 0.28}
+{'loss': 1.1745, 'learning_rate': 1.2780032467532468e-05, 'epoch': 0.28}
+{'loss': 1.1939, 'learning_rate': 1.2772402597402599e-05, 'epoch': 0.28}
+{'loss': 1.5136, 'learning_rate': 1.2764772727272728e-05, 'epoch': 0.28}
+{'loss': 1.2149, 'learning_rate': 1.2757142857142858e-05, 'epoch': 0.29}
+{'loss': 1.3089, 'learning_rate': 1.2749512987012989e-05, 'epoch': 0.29}
+{'loss': 1.1936, 'learning_rate': 1.2741883116883117e-05, 'epoch': 0.29}
+{'loss': 1.1948, 'learning_rate': 1.2734253246753246e-05, 'epoch': 0.29}
+{'loss': 1.3591, 'learning_rate': 1.2726623376623377e-05, 'epoch': 0.29}
+{'loss': 1.3832, 'learning_rate': 1.2718993506493507e-05, 'epoch': 0.29}
+{'loss': 1.3069, 'learning_rate': 1.2711363636363636e-05, 'epoch': 0.3}
+{'loss': 1.2614, 'learning_rate': 1.2703733766233767e-05, 'epoch': 0.3}
+{'loss': 1.2341, 'learning_rate': 1.2696103896103897e-05, 'epoch': 0.3}
+{'loss': 1.2003, 'learning_rate': 1.2688474025974026e-05, 'epoch': 0.3}
+{'loss': 1.1325, 'learning_rate': 1.2680844155844156e-05, 'epoch': 0.3}
+{'loss': 1.4205, 'learning_rate': 1.2673214285714287e-05, 'epoch': 0.3}
+{'loss': 1.5772, 'learning_rate': 1.2665584415584416e-05, 'epoch': 0.31}
+{'loss': 1.192, 'learning_rate': 1.2657954545454546e-05, 'epoch': 0.31}
+{'loss': 1.28, 'learning_rate': 1.2650324675324677e-05, 'epoch': 0.31}
+{'loss': 1.3713, 'learning_rate': 1.2642694805194806e-05, 'epoch': 0.31}
+{'loss': 1.2841, 'learning_rate': 1.2635064935064934e-05, 'epoch': 0.31}
+{'loss': 1.1625, 'learning_rate': 1.2627435064935065e-05, 'epoch': 0.31}
+{'loss': 1.5268, 'learning_rate': 1.2619805194805195e-05, 'epoch': 0.31}
+{'loss': 1.1656, 'learning_rate': 1.2612175324675324e-05, 'epoch': 0.32}
+{'loss': 1.2714, 'learning_rate': 1.2604545454545455e-05, 'epoch': 0.32}
+{'loss': 1.2722, 'learning_rate': 1.2596915584415585e-05, 'epoch': 0.32}
+{'loss': 1.2457, 'learning_rate': 1.2589285714285716e-05, 'epoch': 0.32}
+{'loss': 1.4466, 'learning_rate': 1.2581655844155844e-05, 'epoch': 0.32}
+{'loss': 1.275, 'learning_rate': 1.2574025974025975e-05, 'epoch': 0.32}
+{'loss': 1.3175, 'learning_rate': 1.2566396103896105e-05, 'epoch': 0.33}
+{'loss': 1.4071, 'learning_rate': 1.2558766233766234e-05, 'epoch': 0.33}
+{'loss': 1.5763, 'learning_rate': 1.2551136363636365e-05, 'epoch': 0.33}
+{'loss': 1.4066, 'learning_rate': 1.2543506493506494e-05, 'epoch': 0.33}
+{'loss': 1.3941, 'learning_rate': 1.2535876623376624e-05, 'epoch': 0.33}
+{'loss': 1.2965, 'learning_rate': 1.2528246753246753e-05, 'epoch': 0.33}
+{'loss': 1.3594, 'learning_rate': 1.2520616883116883e-05, 'epoch': 0.34}
+{'loss': 1.2127, 'learning_rate': 1.2512987012987014e-05, 'epoch': 0.34}
+{'loss': 1.2558, 'learning_rate': 1.2505357142857143e-05, 'epoch': 0.34}
+{'loss': 1.4006, 'learning_rate': 1.2497727272727273e-05, 'epoch': 0.34}
+{'loss': 1.19, 'learning_rate': 1.2490097402597404e-05, 'epoch': 0.34}
+{'loss': 1.234, 'learning_rate': 1.2482467532467534e-05, 'epoch': 0.34}
+{'loss': 1.0974, 'learning_rate': 1.2474837662337663e-05, 'epoch': 0.35}
+{'loss': 1.0152, 'learning_rate': 1.2467207792207793e-05, 'epoch': 0.35}
+{'loss': 1.2909, 'learning_rate': 1.2459577922077924e-05, 'epoch': 0.35}
+{'loss': 1.2231, 'learning_rate': 1.2451948051948051e-05, 'epoch': 0.35}
+{'loss': 1.4096, 'learning_rate': 1.2444318181818182e-05, 'epoch': 0.35}
+{'loss': 1.26, 'learning_rate': 1.2436688311688312e-05, 'epoch': 0.35}
+{'loss': 1.2424, 'learning_rate': 1.242905844155844e-05, 'epoch': 0.36}
+{'loss': 1.46, 'learning_rate': 1.2421428571428571e-05, 'epoch': 0.36}
+{'loss': 1.221, 'learning_rate': 1.2413798701298702e-05, 'epoch': 0.36}
+{'loss': 1.1717, 'learning_rate': 1.2406168831168832e-05, 'epoch': 0.36}
+{'loss': 1.2587, 'learning_rate': 1.2398538961038961e-05, 'epoch': 0.36}
+{'loss': 1.1398, 'learning_rate': 1.2390909090909092e-05, 'epoch': 0.36}
+
 12%|█▏        | 225/1848 [1:14:47<9:00:23, 19.98s/it]
 12%|█▏        | 226/1848 [1:15:07<8:59:42, 19.96s/it]
                                                      

 12%|█▏        | 226/1848 [1:15:07<8:59:42, 19.96s/it]
 12%|█▏        | 227/1848 [1:15:27<8:59:48, 19.98s/it]
                                                      

 12%|█▏        | 227/1848 [1:15:27<8:59:48, 19.98s/it]
 12%|█▏        | 228/1848 [1:15:47<8:59:12, 19.97s/it]
                                                      

 12%|█▏        | 228/1848 [1:15:47<8:59:12, 19.97s/it]
 12%|█▏        | 229/1848 [1:16:06<8:58:40, 19.96s/it]
                                                      

 12%|█▏        | 229/1848 [1:16:06<8:58:40, 19.96s/it]
 12%|█▏        | 230/1848 [1:16:26<8:58:05, 19.95s/it]
                                                      

 12%|█▏        | 230/1848 [1:16:26<8:58:05, 19.95s/it]
 12%|█▎        | 231/1848 [1:16:46<8:57:21, 19.94s/it]
                                                      

 12%|█▎        | 231/1848 [1:16:46<8:57:21, 19.94s/it]
 13%|█▎        | 232/1848 [1:17:06<8:57:11, 19.95s/it]
                                                      

 13%|█▎        | 232/1848 [1:17:06<8:57:11, 19.95s/it]
 13%|█▎        | 233/1848 [1:17:26<8:57:17, 19.96s/it]
                                                      

 13%|█▎        | 233/1848 [1:17:26<8:57:17, 19.96s/it]
 13%|█▎        | 234/1848 [1:17:46<8:57:09, 19.97s/it]
                                                      

 13%|█▎        | 234/1848 [1:17:46<8:57:09, 19.97s/it]
 13%|█▎        | 235/1848 [1:18:06<8:56:59, 19.97s/it]
                                                      

 13%|█▎        | 235/1848 [1:18:06<8:56:59, 19.97s/it]
 13%|█▎        | 236/1848 [1:18:26<8:56:43, 19.98s/it]
                                                      

 13%|█▎        | 236/1848 [1:18:26<8:56:43, 19.98s/it]
 13%|█▎        | 237/1848 [1:18:46<8:56:23, 19.98s/it]
                                                      

 13%|█▎        | 237/1848 [1:18:46<8:56:23, 19.98s/it]
 13%|█▎        | 238/1848 [1:19:06<8:55:20, 19.95s/it]
                                                      

 13%|█▎        | 238/1848 [1:19:06<8:55:20, 19.95s/it]
 13%|█▎        | 239/1848 [1:19:26<8:54:54, 19.95s/it]
                                                      

 13%|█▎        | 239/1848 [1:19:26<8:54:54, 19.95s/it]
 13%|█▎        | 240/1848 [1:19:46<8:54:35, 19.95s/it]
                                                      

 13%|█▎        | 240/1848 [1:19:46<8:54:35, 19.95s/it]
 13%|█▎        | 241/1848 [1:20:06<8:54:40, 19.96s/it]
                                                      

 13%|█▎        | 241/1848 [1:20:06<8:54:40, 19.96s/it]
 13%|█▎        | 242/1848 [1:20:26<8:54:11, 19.96s/it]
                                                      

 13%|█▎        | 242/1848 [1:20:26<8:54:11, 19.96s/it]
 13%|█▎        | 243/1848 [1:20:46<8:54:00, 19.96s/it]
                                                      

 13%|█▎        | 243/1848 [1:20:46<8:54:00, 19.96s/it]
 13%|█▎        | 244/1848 [1:21:06<8:53:33, 19.96s/it]
                                                      

 13%|█▎        | 244/1848 [1:21:06<8:53:33, 19.96s/it]
 13%|█▎        | 245/1848 [1:21:26<8:53:12, 19.96s/it]
                                                      

 13%|█▎        | 245/1848 [1:21:26<8:53:12, 19.96s/it]
 13%|█▎        | 246/1848 [1:21:46<8:53:06, 19.97s/it]
                                                      

 13%|█▎        | 246/1848 [1:21:46<8:53:06, 19.97s/it]
 13%|█▎        | 247/1848 [1:22:06<8:52:57, 19.97s/it]
                                                      

 13%|█▎        | 247/1848 [1:22:06<8:52:57, 19.97s/it]
 13%|█▎        | 248/1848 [1:22:26<8:52:16, 19.96s/it]
                                                      

 13%|█▎        | 248/1848 [1:22:26<8:52:16, 19.96s/it]
 13%|█▎        | 249/1848 [1:22:46<8:51:56, 19.96s/it]
                                                      

 13%|█▎        | 249/1848 [1:22:46<8:51:56, 19.96s/it]
 14%|█▎        | 250/1848 [1:23:06<8:51:22, 19.95s/it]
                                                      

 14%|█▎        | 250/1848 [1:23:06<8:51:22, 19.95s/it]
 14%|█▎        | 251/1848 [1:23:25<8:50:38, 19.94s/it]
                                                      

 14%|█▎        | 251/1848 [1:23:25<8:50:38, 19.94s/it]
 14%|█▎        | 252/1848 [1:23:45<8:50:24, 19.94s/it]
                                                      

 14%|█▎        | 252/1848 [1:23:45<8:50:24, 19.94s/it]
 14%|█▎        | 253/1848 [1:24:05<8:49:52, 19.93s/it]
                                                      

 14%|█▎        | 253/1848 [1:24:05<8:49:52, 19.93s/it]
 14%|█▎        | 254/1848 [1:24:25<8:49:10, 19.92s/it]
                                                      

 14%|█▎        | 254/1848 [1:24:25<8:49:10, 19.92s/it]
 14%|█▍        | 255/1848 [1:24:45<8:48:49, 19.92s/it]
                                                      

 14%|█▍        | 255/1848 [1:24:45<8:48:49, 19.92s/it]
 14%|█▍        | 256/1848 [1:25:05<8:49:06, 19.94s/it]
                                                      

 14%|█▍        | 256/1848 [1:25:05<8:49:06, 19.94s/it]
 14%|█▍        | 257/1848 [1:25:25<8:48:22, 19.93s/it]
                                                      

 14%|█▍        | 257/1848 [1:25:25<8:48:22, 19.93s/it]
 14%|█▍        | 258/1848 [1:25:45<8:48:07, 19.93s/it]
                                                      

 14%|█▍        | 258/1848 [1:25:45<8:48:07, 19.93s/it]
 14%|█▍        | 259/1848 [1:26:05<8:48:35, 19.96s/it]
                                                      

 14%|█▍        | 259/1848 [1:26:05<8:48:35, 19.96s/it]
 14%|█▍        | 260/1848 [1:26:25<8:47:51, 19.94s/it]
                                                      

 14%|█▍        | 260/1848 [1:26:25<8:47:51, 19.94s/it]
 14%|█▍        | 261/1848 [1:26:45<8:47:43, 19.95s/it]
                                                      

 14%|█▍        | 261/1848 [1:26:45<8:47:43, 19.95s/it]
 14%|█▍        | 262/1848 [1:27:05<8:47:25, 19.95s/it]
                                                      

 14%|█▍        | 262/1848 [1:27:05<8:47:25, 19.95s/it]
 14%|█▍        | 263/1848 [1:27:25<8:47:10, 19.96s/it]
                                                      

 14%|█▍        | 263/1848 [1:27:25<8:47:10, 19.96s/it]
 14%|█▍        | 264/1848 [1:27:45<8:46:37, 19.95s/it]
                                                      

 14%|█▍        | 264/1848 [1:27:45<8:46:37, 19.95s/it]
 14%|█▍        | 265/1848 [1:28:05<8:46:44, 19.97s/it]
                                                      

 14%|█▍        | 265/1848 [1:28:05<8:46:44, 19.97s/it]
 14%|█▍        | 266/1848 [1:28:25<8:46:12, 19.96s/it]
                                                      

 14%|█▍        | 266/1848 [1:28:25<8:46:12, 19.96s/it]
 14%|█▍        | 267/1848 [1:28:45<8:45:39, 19.95s/it]
                                                      

 14%|█▍        | 267/1848 [1:28:45<8:45:39, 19.95s/it]
 15%|█▍        | 268/1848 [1:29:05<8:45:20, 19.95s/it]
                                                      

 15%|█▍        | 268/1848 [1:29:05<8:45:20, 19.95s/it]
 15%|█▍        | 269/1848 [1:29:24<8:44:38, 19.94s/it]
                                                      

 15%|█▍        | 269/1848 [1:29:24<8:44:38, 19.94s/it]
 15%|█▍        | 270/1848 [1:29:44<8:44:18, 19.94s/it]
                                                      

 15%|█▍        | 270/1848 [1:29:44<8:44:18, 19.94s/it]
 15%|█▍        | 271/1848 [1:30:04<8:43:57, 19.93s/it]
                                                      

 15%|█▍        | 271/1848 [1:30:04<8:43:57, 19.93s/it]
 15%|█▍        | 272/1848 [1:30:24<8:43:36, 19.93s/it]
                                                      

 15%|█▍        | 272/1848 [1:30:24<8:43:36, 19.93s/it]
 15%|█▍        | 273/1848 [1:30:44<8:43:43, 19.95s/it]
                                                      

 15%|█▍        | 273/1848 [1:30:44<8:43:43, 19.95s/it]
 15%|█▍        | 274/1848 [1:31:04<8:43:32, 19.96s/it]
                                                      

 15%|█▍        | 274/1848 [1:31:04<8:43:32, 19.96s/it]
 15%|█▍        | 275/1848 [1:31:24<8:43:10, 19.96s/it]
                                                      

 15%|█▍        | 275/1848 [1:31:24<8:43:10, 19.96s/it]
 15%|█▍        | 276/1848 [1:31:44<8:42:13, 19.93s/it]
                                                      

 15%|█▍        | 276/1848 [1:31:44<8:42:13, 19.93s/it]
 15%|█▍        | 277/1848 [1:32:04<8:41:36, 19.92s/it]
                                                      

 15%|█▍        | 277/1848 [1:32:04<8:41:36, 19.92s/it]
 15%|█▌        | 278/1848 [1:32:24<8:41:07, 19.92s/it]
                                                      

 15%|█▌        | 278/1848 [1:32:24<8:41:07, 19.92s/it]
 15%|█▌        | 279/1848 [1:32:44<8:41:16, 19.93s/it]
                                                      

 15%|█▌        | 279/1848 [1:32:44<8:41:16, 19.93s/it]
 15%|█▌        | 280/1848 [1:33:04<8:40:55, 19.93s/it]
                                                      

 15%|█▌        | 280/1848 [1:33:04<8:40:55, 19.93s/it]
 15%|█▌        | 281/1848 [1:33:24<8:40:51, 19.94s/it]
                                                      

 15%|█▌        | 281/1848 [1:33:24<8:40:51, 19.94s/it]
 15%|█▌        | 282/1848 [1:33:44<8:41:05, 19.97s/it]
                                                      

 15%|█▌        | 282/1848 [1:33:44<8:41:05, 19.97s/it]
 15%|█▌        | 283/1848 [1:34:04<8:40:40, 19.96s/it]
                                                      

 15%|█▌        | 283/1848 [1:34:04<8:40:40, 19.96s/it]
 15%|█▌        | 284/1848 [1:34:24<8:40:05, 19.95s/it]
                                                      

 15%|█▌        | 284/1848 [1:34:24<8:40:05, 19.95s/it]
 15%|█▌        | 285/1848 [1:34:44<8:39:42, 19.95s/it]
                                                      

 15%|█▌        | 285/1848 [1:34:44<8:39:42, 19.95s/it]
 15%|█▌        | 286/1848 [1:35:04<8:39:25, 19.95s/it]
                                                      

 15%|█▌        | 286/1848 [1:35:04<8:39:25, 19.95s/it]
 16%|█▌        | 287/1848 [1:35:23<8:38:32, 19.93s/it]
                                                      

 16%|█▌        | 287/1848 [1:35:23<8:38:32, 19.93s/it]
 16%|█▌        | 288/1848 [1:35:43<8:38:26, 19.94s/it]
                                                      

 16%|█▌        | 288/1848 [1:35:43<8:38:26, 19.94s/it]
 16%|█▌        | 289/1848 [1:36:03<8:37:57, 19.93s/it]
                                                      

 16%|█▌        | 289/1848 [1:36:03<8:37:57, 19.93s/it]
 16%|█▌        | 290/1848 [1:36:23<8:37:40, 19.94s/it]
                                                      

 16%|█▌        | 290/1848 [1:36:23<8:37:40, 19.94s/it]
 16%|█▌        | 291/1848 [1:36:43<8:37:48, 19.95s/it]
                                                      

 16%|█▌        | 291/1848 [1:36:43<8:37:48, 19.95s/it]
 16%|█▌        | 292/1848 [1:37:03<8:37:10, 19.94s/it]
                                                      

 16%|█▌        | 292/1848 [1:37:03<8:37:10, 19.94s/it]
 16%|█▌        | 293/1848 [1:37:23<8:35:51, 19.90s/it]
                                                      

 16%|█▌        | 293/1848 [1:37:23<8:35:51, 19.90s/it]
 16%|█▌        | 294/1848 [1:37:43<8:35:44, 19.91s/it]
                                                      

 16%|█▌        | 294/1848 [1:37:43<8:35:44, 19.91s/it]
 16%|█▌        | 295/1848 [1:38:03<8:35:50, 19.93s/it]
                                                      

 16%|█▌        | 295/1848 [1:38:03<8:35:50, 19.93s/it]
 16%|█▌        | 296/1848 [1:38:23<8:35:34, 19.93s/it]
                                                      

 16%|█▌        | 296/1848 [1:38:23<8:35:34, 19.93s/it]
 16%|█▌        | 297/1848 [1:38:43<8:35:32, 19.94s/it]
                                                      

 16%|█▌        | 297/1848 [1:38:43<8:35:32, 19.94s/it]
 16%|█▌        | 298/1848 [1:39:03<8:35:00, 19.94s/it]
                                                      

 16%|█▌        | 298/1848 [1:39:03<8:35:00, 19.94s/it]
 16%|█▌        | 299/1848 [1:39:23<8:34:27, 19.93s/it]
                                                      

 16%|█▌        | 299/1848 [1:39:23<8:34:27, 19.93s/it]
 16%|█▌        | 300/1848 [1:39:43<8:34:10, 19.93s/it]
                                                      

 16%|█▌        | 300/1848 [1:39:43<8:34:10, 19.93s/it]
 16%|█▋        | 301/1848 [1:40:03<8:39:41, 20.16s/it]
                                                      

 16%|█▋        | 301/1848 [1:40:03<8:39:41, 20.16s/it]
 16%|█▋        | 302/1848 [1:40:23<8:37:14, 20.07s/it]
                                                      

 16%|█▋        | 302/1848 [1:40:23<8:37:14, 20.07s/it]
 16%|█▋        | 303/1848 [1:40:43<8:35:45, 20.03s/it]
                                                      

 16%|█▋        | 303/1848 [1:40:43<8:35:45, 20.03s/it]
 16%|█▋        | 304/1848 [1:41:03<8:34:39, 20.00s/it]
                                                      

 16%|█▋        | 304/1848 [1:41:03<8:34:39, 20.00s/it]
 17%|█▋        | 305/1848 [1:41:23<8:33:16, 19.96s/it]
                                                      

 17%|█▋        | 305/1848 [1:41:23<8:33:16, 19.96s/it]
 17%|█▋        | 306/1848 [1:41:43<8:32:39, 19.95s/it]
                                                      

 17%|█▋        | 306/1848 [1:41:43<8:32:39, 19.95s/it]
 17%|█▋        | 307/1848 [1:42:03<8:31:05, 19.90s/it]
                                                      

 17%|█▋        | 307/1848 [1:42:03<8:31:05, 19.90s/it]
 17%|█▋        | 308/1848 [1:42:22<8:30:37, 19.89s/it]
                                                      

 17%|█▋        | 308/1848 [1:42:22<8:30:37, 19.89s/it]
 17%|█▋        | 309/1848 [1:42:42<8:30:12, 19.89s/it]
                                                      

 17%|█▋        | 309/1848 [1:42:42<8:30:12, 19.89s/it]
 17%|█▋        | 310/1848 [1:43:02<8:29:38, 19.88s/it]
                                                      

 17%|█▋        | 310/1848 [1:43:02<8:29:38, 19.88s/it]
 17%|█▋        | 311/1848 [1:43:22<8:29:28, 19.89s/it]
                                                      

 17%|█▋        | 311/1848 [1:43:22<8:29:28, 19.89s/it]
 17%|█▋        | 312/1848 [1:43:42<8:29:37, 19.91s/it]
                                                      

 17%|█▋        | 312/1848 [1:43:42<8:29:37, 19.91s/it]
 17%|█▋        | 313/1848 [1:44:02<8:29:17, 19.91s/it]
                                                      

 17%|█▋        | 313/1848 [1:44:02<8:29:17, 19.91s/it]
 17%|█▋        | 314/1848 [1:44:22<8:29:24, 19.92s/it]
                                                      

 17%|█▋        | 314/1848 [1:44:22<8:29:24, 19.92s/it]
 17%|█▋        | 315/1848 [1:44:42<8:29:13, 19.93s/it]
                                                      

 17%|█▋        | 315/1848 [1:44:42<8:29:13, 19.93s/it]
 17%|█▋        | 316/1848 [1:45:02<8:28:15, 19.91s/it]
                                                      

 17%|█▋        | 316/1848 [1:45:02<8:28:15, 19.91s/it]
 17%|█▋        | 317/1848 [1:45:22<8:28:03, 19.91s/it]
                                                      

 17%|█▋        | 317/1848 [1:45:22<8:28:03, 19.91s/it]
 17%|█▋        | 318/1848 [1:45:42<8:28:01, 19.92s/it]
                                                      

 17%|█▋        | 318/1848 [1:45:42<8:28:01, 19.92s/it]
 17%|█▋        | 319/1848 [1:46:01<8:27:03, 19.90s/it]
                                                      

 17%|█▋        | 319/1848 [1:46:01<8:27:03, 19.90s/it]
 17%|█▋        | 320/1848 [1:46:21<8:26:35, 19.89s/it]
                                                      

 17%|█▋        | 320/1848 [1:46:21<8:26:35, 19.89s/it]
 17%|█▋        | 321/1848 [1:46:41<8:26:38, 19.91s/it]
                                                      

 17%|█▋        | 321/1848 [1:46:41<8:26:38, 19.91s/it]
 17%|█▋        | 322/1848 [1:47:01<8:26:42, 19.92s/it]
                                                      

 17%|█▋        | 322/1848 [1:47:01<8:26:42, 19.92s/it]
 17%|█▋        | 323/1848 [1:47:21<8:25:48, 19.90s/it]
                                                      

 17%|█▋        | 323/1848 [1:47:21<8:25:48, 19.90s/it]
 18%|█▊        | 324/1848 [1:47:41<8:25:37, 19.91s/it]
                                                      

 18%|█▊        | 324/1848 [1:47:41<8:25:37, 19.91s/it]
 18%|█▊        | 325/1848 [1:48:01<8:25:37, 19.92s/it]
                                                      

 18%|█▊        | 325/1848 [1:48:01<8:25:37, 19.92s/it]
 18%|█▊        | 326/1848 [1:48:21<8:25:30, 19.93s/it]
                                                      

 18%|█▊        | 326/1848 [1:48:21<8:25:30, 19.93s/it]
 18%|█▊        | 327/1848 [1:48:41<8:25:05, 19.92s/it]
                                                      

 18%|█▊        | 327/1848 [1:48:41<8:25:05, 19.92s/it]
 18%|█▊        | 328/1848 [1:49:01<8:24:40, 19.92s/it]
                                                      

 18%|█▊        | 328/1848 [1:49:01<8:24:40, 19.92s/it]
 18%|█▊        | 329/1848 [1:49:20<8:23:36, 19.89s/it]
                                                      

 18%|█▊        | 329/1848 [1:49:20<8:23:36, 19.89s/it]
 18%|█▊        | 330/1848 [1:49:40<8:22:50, 19.88s/it]
                                                      

 18%|█▊        | 330/1848 [1:49:40<8:22:50, 19.88s/it]
 18%|█▊        | 331/1848 [1:50:00<8:22:03, 19.86s/it]
                                                      

 18%|█▊        | 331/1848 [1:50:00<8:22:03, 19.86s/it]
 18%|█▊        | 332/1848 [1:50:20<8:22:58, 19.91s/it]
                                                      

 18%|█▊        | 332/1848 [1:50:20<8:22:58, 19.91s/it]
 18%|█▊        | 333/1848 [1:50:40<8:22:28, 19.90s/it]
                                                      

 18%|█▊        | 333/1848 [1:50:40<8:22:28, 19.90s/it]
 18%|█▊        | 334/1848 [1:51:00<8:22:34, 19.92s/it]
                                                      

 18%|█▊        | 334/1848 [1:51:00<8:22:34, 19.92s/it]
 18%|█▊        | 335/1848 [1:51:20<8:21:59, 19.91s/it]
                                                      

 18%|█▊        | 335/1848 [1:51:20<8:21:59, 19.91s/it]
 18%|█▊        | 336/1848 [1:51:40<8:21:48, 19.91s/it]
                                                      

 18%|█▊        | 336/1848 [1:51:40<8:21:48, 19.91s/it]
 18%|█▊        | 337/1848 [1:52:00<8:21:21, 19.91s/it]
                                                      

 18%|█▊        | 337/1848 [1:52:00<8:21:21, 19.91s/it]
 18%|█▊        | 338/1848 [1:52:20<8:21:59, 19.95s/it]
                                                      
{'loss': 1.392, 'learning_rate': 1.2383279220779222e-05, 'epoch': 0.37}
+{'loss': 1.212, 'learning_rate': 1.2375649350649351e-05, 'epoch': 0.37}
+{'loss': 1.3254, 'learning_rate': 1.2368019480519481e-05, 'epoch': 0.37}
+{'loss': 1.2686, 'learning_rate': 1.236038961038961e-05, 'epoch': 0.37}
+{'loss': 1.1731, 'learning_rate': 1.235275974025974e-05, 'epoch': 0.37}
+{'loss': 1.2323, 'learning_rate': 1.234512987012987e-05, 'epoch': 0.37}
+{'loss': 1.0833, 'learning_rate': 1.23375e-05, 'epoch': 0.38}
+{'loss': 1.3241, 'learning_rate': 1.232987012987013e-05, 'epoch': 0.38}
+{'loss': 1.485, 'learning_rate': 1.232224025974026e-05, 'epoch': 0.38}
+{'loss': 1.1528, 'learning_rate': 1.231461038961039e-05, 'epoch': 0.38}
+{'loss': 1.2282, 'learning_rate': 1.230698051948052e-05, 'epoch': 0.38}
+{'loss': 1.2526, 'learning_rate': 1.229935064935065e-05, 'epoch': 0.38}
+{'loss': 1.3231, 'learning_rate': 1.229172077922078e-05, 'epoch': 0.38}
+{'loss': 1.3807, 'learning_rate': 1.228409090909091e-05, 'epoch': 0.39}
+{'loss': 1.5031, 'learning_rate': 1.227646103896104e-05, 'epoch': 0.39}
+{'loss': 1.292, 'learning_rate': 1.226883116883117e-05, 'epoch': 0.39}
+{'loss': 1.3318, 'learning_rate': 1.2261201298701298e-05, 'epoch': 0.39}
+{'loss': 1.1987, 'learning_rate': 1.2253571428571429e-05, 'epoch': 0.39}
+{'loss': 1.4584, 'learning_rate': 1.224594155844156e-05, 'epoch': 0.39}
+{'loss': 1.2854, 'learning_rate': 1.2238311688311688e-05, 'epoch': 0.4}
+{'loss': 1.2995, 'learning_rate': 1.2230681818181819e-05, 'epoch': 0.4}
+{'loss': 1.1981, 'learning_rate': 1.2223051948051949e-05, 'epoch': 0.4}
+{'loss': 1.3104, 'learning_rate': 1.2215422077922078e-05, 'epoch': 0.4}
+{'loss': 1.395, 'learning_rate': 1.2207792207792208e-05, 'epoch': 0.4}
+{'loss': 1.2354, 'learning_rate': 1.2200162337662339e-05, 'epoch': 0.4}
+{'loss': 1.1673, 'learning_rate': 1.2192532467532468e-05, 'epoch': 0.41}
+{'loss': 1.283, 'learning_rate': 1.2184902597402598e-05, 'epoch': 0.41}
+{'loss': 1.3706, 'learning_rate': 1.2177272727272729e-05, 'epoch': 0.41}
+{'loss': 1.2342, 'learning_rate': 1.2169642857142857e-05, 'epoch': 0.41}
+{'loss': 1.5176, 'learning_rate': 1.2162012987012986e-05, 'epoch': 0.41}
+{'loss': 1.3579, 'learning_rate': 1.2154383116883117e-05, 'epoch': 0.41}
+{'loss': 1.2439, 'learning_rate': 1.2146753246753247e-05, 'epoch': 0.42}
+{'loss': 1.3789, 'learning_rate': 1.2139123376623376e-05, 'epoch': 0.42}
+{'loss': 1.3021, 'learning_rate': 1.2131493506493507e-05, 'epoch': 0.42}
+{'loss': 1.3114, 'learning_rate': 1.2123863636363637e-05, 'epoch': 0.42}
+{'loss': 1.3676, 'learning_rate': 1.2116233766233768e-05, 'epoch': 0.42}
+{'loss': 1.2756, 'learning_rate': 1.2108603896103896e-05, 'epoch': 0.42}
+{'loss': 1.5378, 'learning_rate': 1.2100974025974027e-05, 'epoch': 0.43}
+{'loss': 1.3035, 'learning_rate': 1.2093344155844157e-05, 'epoch': 0.43}
+{'loss': 1.271, 'learning_rate': 1.2085714285714286e-05, 'epoch': 0.43}
+{'loss': 1.2633, 'learning_rate': 1.2078084415584417e-05, 'epoch': 0.43}
+{'loss': 1.2901, 'learning_rate': 1.2070454545454545e-05, 'epoch': 0.43}
+{'loss': 1.3305, 'learning_rate': 1.2062824675324676e-05, 'epoch': 0.43}
+{'loss': 1.1847, 'learning_rate': 1.2055194805194805e-05, 'epoch': 0.44}
+{'loss': 1.2768, 'learning_rate': 1.2047564935064935e-05, 'epoch': 0.44}
+{'loss': 1.293, 'learning_rate': 1.2039935064935066e-05, 'epoch': 0.44}
+{'loss': 1.2981, 'learning_rate': 1.2032305194805195e-05, 'epoch': 0.44}
+{'loss': 1.1048, 'learning_rate': 1.2024675324675325e-05, 'epoch': 0.44}
+{'loss': 1.2966, 'learning_rate': 1.2017045454545456e-05, 'epoch': 0.44}
+{'loss': 1.0567, 'learning_rate': 1.2009415584415586e-05, 'epoch': 0.44}
+{'loss': 1.1597, 'learning_rate': 1.2001785714285715e-05, 'epoch': 0.45}
+{'loss': 1.5763, 'learning_rate': 1.1994155844155845e-05, 'epoch': 0.45}
+{'loss': 1.3988, 'learning_rate': 1.1986525974025974e-05, 'epoch': 0.45}
+{'loss': 1.4684, 'learning_rate': 1.1978896103896103e-05, 'epoch': 0.45}
+{'loss': 1.2883, 'learning_rate': 1.1971266233766233e-05, 'epoch': 0.45}
+{'loss': 1.1965, 'learning_rate': 1.1963636363636364e-05, 'epoch': 0.45}
+{'loss': 1.1529, 'learning_rate': 1.1956006493506493e-05, 'epoch': 0.46}
+{'loss': 1.1418, 'learning_rate': 1.1948376623376623e-05, 'epoch': 0.46}
+{'loss': 1.2422, 'learning_rate': 1.1940746753246754e-05, 'epoch': 0.46}
+{'loss': 1.3107, 'learning_rate': 1.1933116883116884e-05, 'epoch': 0.46}
+{'loss': 1.395, 'learning_rate': 1.1925487012987013e-05, 'epoch': 0.46}
+{'loss': 1.1799, 'learning_rate': 1.1917857142857144e-05, 'epoch': 0.46}
+{'loss': 1.2834, 'learning_rate': 1.1910227272727274e-05, 'epoch': 0.47}
+{'loss': 1.1329, 'learning_rate': 1.1902597402597403e-05, 'epoch': 0.47}
+{'loss': 1.5212, 'learning_rate': 1.1894967532467533e-05, 'epoch': 0.47}
+{'loss': 1.1787, 'learning_rate': 1.1887337662337662e-05, 'epoch': 0.47}
+{'loss': 1.0634, 'learning_rate': 1.1879707792207793e-05, 'epoch': 0.47}
+{'loss': 1.446, 'learning_rate': 1.1872077922077921e-05, 'epoch': 0.47}
+{'loss': 1.2704, 'learning_rate': 1.1864448051948052e-05, 'epoch': 0.48}
+{'loss': 1.458, 'learning_rate': 1.1856818181818182e-05, 'epoch': 0.48}
+{'loss': 1.2732, 'learning_rate': 1.1849188311688311e-05, 'epoch': 0.48}
+{'loss': 1.2196, 'learning_rate': 1.1841558441558442e-05, 'epoch': 0.48}
+{'loss': 1.3199, 'learning_rate': 1.1833928571428572e-05, 'epoch': 0.48}
+{'loss': 1.2125, 'learning_rate': 1.1826298701298703e-05, 'epoch': 0.48}
+{'loss': 1.2336, 'learning_rate': 1.1818668831168832e-05, 'epoch': 0.49}
+{'loss': 1.1428, 'learning_rate': 1.1811038961038962e-05, 'epoch': 0.49}
+{'loss': 1.5524, 'learning_rate': 1.1803409090909093e-05, 'epoch': 0.49}
+{'loss': 1.3928, 'learning_rate': 1.1795779220779221e-05, 'epoch': 0.49}
+{'loss': 1.1503, 'learning_rate': 1.178814935064935e-05, 'epoch': 0.49}
+{'loss': 1.2228, 'learning_rate': 1.178051948051948e-05, 'epoch': 0.49}
+{'loss': 1.3721, 'learning_rate': 1.1772889610389611e-05, 'epoch': 0.5}
+{'loss': 1.3084, 'learning_rate': 1.176525974025974e-05, 'epoch': 0.5}
+{'loss': 1.3709, 'learning_rate': 1.175762987012987e-05, 'epoch': 0.5}
+{'loss': 1.2056, 'learning_rate': 1.1750000000000001e-05, 'epoch': 0.5}
+{'loss': 1.1071, 'learning_rate': 1.174237012987013e-05, 'epoch': 0.5}
+{'loss': 1.2954, 'learning_rate': 1.173474025974026e-05, 'epoch': 0.5}
+{'loss': 1.2466, 'learning_rate': 1.172711038961039e-05, 'epoch': 0.5}
+{'loss': 1.1082, 'learning_rate': 1.1719480519480521e-05, 'epoch': 0.51}
+{'loss': 1.3029, 'learning_rate': 1.171185064935065e-05, 'epoch': 0.51}
+{'loss': 1.1976, 'learning_rate': 1.170422077922078e-05, 'epoch': 0.51}
+{'loss': 1.297, 'learning_rate': 1.169659090909091e-05, 'epoch': 0.51}
+{'loss': 1.2204, 'learning_rate': 1.1688961038961038e-05, 'epoch': 0.51}
+{'loss': 1.4572, 'learning_rate': 1.1681331168831169e-05, 'epoch': 0.51}
+{'loss': 1.3001, 'learning_rate': 1.16737012987013e-05, 'epoch': 0.52}
+{'loss': 1.3188, 'learning_rate': 1.1666071428571428e-05, 'epoch': 0.52}
+{'loss': 1.4327, 'learning_rate': 1.1658441558441559e-05, 'epoch': 0.52}
+{'loss': 1.1586, 'learning_rate': 1.1650811688311689e-05, 'epoch': 0.52}
+{'loss': 1.2011, 'learning_rate': 1.164318181818182e-05, 'epoch': 0.52}
+{'loss': 1.2097, 'learning_rate': 1.1635551948051948e-05, 'epoch': 0.52}
+{'loss': 1.2332, 'learning_rate': 1.1627922077922079e-05, 'epoch': 0.53}
+{'loss': 1.3374, 'learning_rate': 1.162029220779221e-05, 'epoch': 0.53}
+{'loss': 1.152, 'learning_rate': 1.1612662337662338e-05, 'epoch': 0.53}
+{'loss': 1.2202, 'learning_rate': 1.1605032467532467e-05, 'epoch': 0.53}
+{'loss': 1.149, 'learning_rate': 1.1597402597402597e-05, 'epoch': 0.53}
+{'loss': 1.3427, 'learning_rate': 1.1589772727272728e-05, 'epoch': 0.53}
+{'loss': 1.4922, 'learning_rate': 1.1582142857142857e-05, 'epoch': 0.54}
+{'loss': 1.269, 'learning_rate': 1.1574512987012987e-05, 'epoch': 0.54}
+{'loss': 1.0884, 'learning_rate': 1.1566883116883118e-05, 'epoch': 0.54}
+{'loss': 1.2827, 'learning_rate': 1.1559253246753247e-05, 'epoch': 0.54}
+{'loss': 0.9949, 'learning_rate': 1.1551623376623377e-05, 'epoch': 0.54}
+{'loss': 1.4618, 'learning_rate': 1.1543993506493508e-05, 'epoch': 0.54}
+{'loss': 1.1753, 'learning_rate': 1.1536363636363638e-05, 'epoch': 0.55}
+{'loss': 1.2604, 'learning_rate': 1.1528733766233767e-05, 'epoch': 0.55}
+
 18%|█▊        | 338/1848 [1:52:20<8:21:59, 19.95s/it]
 18%|█▊        | 339/1848 [1:52:40<8:20:56, 19.92s/it]
                                                      

 18%|█▊        | 339/1848 [1:52:40<8:20:56, 19.92s/it]
 18%|█▊        | 340/1848 [1:53:00<8:20:34, 19.92s/it]
                                                      

 18%|█▊        | 340/1848 [1:53:00<8:20:34, 19.92s/it]
 18%|█▊        | 341/1848 [1:53:19<8:20:00, 19.91s/it]
                                                      

 18%|█▊        | 341/1848 [1:53:19<8:20:00, 19.91s/it]
 19%|█▊        | 342/1848 [1:53:39<8:19:31, 19.90s/it]
                                                      

 19%|█▊        | 342/1848 [1:53:39<8:19:31, 19.90s/it]
 19%|█▊        | 343/1848 [1:53:59<8:19:14, 19.90s/it]
                                                      

 19%|█▊        | 343/1848 [1:53:59<8:19:14, 19.90s/it]
 19%|█▊        | 344/1848 [1:54:19<8:19:10, 19.91s/it]
                                                      

 19%|█▊        | 344/1848 [1:54:19<8:19:10, 19.91s/it]
 19%|█▊        | 345/1848 [1:54:39<8:18:21, 19.89s/it]
                                                      

 19%|█▊        | 345/1848 [1:54:39<8:18:21, 19.89s/it]
 19%|█▊        | 346/1848 [1:54:59<8:18:15, 19.90s/it]
                                                      

 19%|█▊        | 346/1848 [1:54:59<8:18:15, 19.90s/it]
 19%|█▉        | 347/1848 [1:55:19<8:17:45, 19.90s/it]
                                                      

 19%|█▉        | 347/1848 [1:55:19<8:17:45, 19.90s/it]
 19%|█▉        | 348/1848 [1:55:39<8:17:23, 19.90s/it]
                                                      

 19%|█▉        | 348/1848 [1:55:39<8:17:23, 19.90s/it]
 19%|█▉        | 349/1848 [1:55:59<8:16:54, 19.89s/it]
                                                      

 19%|█▉        | 349/1848 [1:55:59<8:16:54, 19.89s/it]
 19%|█▉        | 350/1848 [1:56:18<8:16:53, 19.90s/it]
                                                      

 19%|█▉        | 350/1848 [1:56:18<8:16:53, 19.90s/it]
 19%|█▉        | 351/1848 [1:56:38<8:16:34, 19.90s/it]
                                                      

 19%|█▉        | 351/1848 [1:56:38<8:16:34, 19.90s/it]
 19%|█▉        | 352/1848 [1:56:58<8:16:37, 19.92s/it]
                                                      

 19%|█▉        | 352/1848 [1:56:58<8:16:37, 19.92s/it]
 19%|█▉        | 353/1848 [1:57:18<8:16:06, 19.91s/it]
                                                      

 19%|█▉        | 353/1848 [1:57:18<8:16:06, 19.91s/it]
 19%|█▉        | 354/1848 [1:57:38<8:16:01, 19.92s/it]
                                                      

 19%|█▉        | 354/1848 [1:57:38<8:16:01, 19.92s/it]
 19%|█▉        | 355/1848 [1:57:58<8:15:41, 19.92s/it]
                                                      

 19%|█▉        | 355/1848 [1:57:58<8:15:41, 19.92s/it]
 19%|█▉        | 356/1848 [1:58:18<8:15:25, 19.92s/it]
                                                      

 19%|█▉        | 356/1848 [1:58:18<8:15:25, 19.92s/it]
 19%|█▉        | 357/1848 [1:58:38<8:14:48, 19.91s/it]
                                                      

 19%|█▉        | 357/1848 [1:58:38<8:14:48, 19.91s/it]
 19%|█▉        | 358/1848 [1:58:58<8:14:52, 19.93s/it]
                                                      

 19%|█▉        | 358/1848 [1:58:58<8:14:52, 19.93s/it]
 19%|█▉        | 359/1848 [1:59:18<8:14:21, 19.92s/it]
                                                      

 19%|█▉        | 359/1848 [1:59:18<8:14:21, 19.92s/it]
 19%|█▉        | 360/1848 [1:59:38<8:14:02, 19.92s/it]
                                                      

 19%|█▉        | 360/1848 [1:59:38<8:14:02, 19.92s/it]
 20%|█▉        | 361/1848 [1:59:58<8:14:20, 19.95s/it]
                                                      

 20%|█▉        | 361/1848 [1:59:58<8:14:20, 19.95s/it]
 20%|█▉        | 362/1848 [2:00:18<8:13:06, 19.91s/it]
                                                      

 20%|█▉        | 362/1848 [2:00:18<8:13:06, 19.91s/it]
 20%|█▉        | 363/1848 [2:00:37<8:12:25, 19.90s/it]
                                                      

 20%|█▉        | 363/1848 [2:00:37<8:12:25, 19.90s/it]
 20%|█▉        | 364/1848 [2:00:57<8:11:51, 19.89s/it]
                                                      

 20%|█▉        | 364/1848 [2:00:57<8:11:51, 19.89s/it]
 20%|█▉        | 365/1848 [2:01:17<8:11:03, 19.87s/it]
                                                      

 20%|█▉        | 365/1848 [2:01:17<8:11:03, 19.87s/it]
 20%|█▉        | 366/1848 [2:01:37<8:11:33, 19.90s/it]
                                                      

 20%|█▉        | 366/1848 [2:01:37<8:11:33, 19.90s/it]
 20%|█▉        | 367/1848 [2:01:57<8:11:23, 19.91s/it]
                                                      

 20%|█▉        | 367/1848 [2:01:57<8:11:23, 19.91s/it]
 20%|█▉        | 368/1848 [2:02:17<8:11:12, 19.91s/it]
                                                      

 20%|█▉        | 368/1848 [2:02:17<8:11:12, 19.91s/it]
 20%|█▉        | 369/1848 [2:02:37<8:10:30, 19.90s/it]
                                                      

 20%|█▉        | 369/1848 [2:02:37<8:10:30, 19.90s/it]
 20%|██        | 370/1848 [2:02:57<8:10:36, 19.92s/it]
                                                      

 20%|██        | 370/1848 [2:02:57<8:10:36, 19.92s/it]
 20%|██        | 371/1848 [2:03:17<8:10:18, 19.92s/it]
                                                      

 20%|██        | 371/1848 [2:03:17<8:10:18, 19.92s/it]
 20%|██        | 372/1848 [2:03:37<8:10:11, 19.93s/it]
                                                      

 20%|██        | 372/1848 [2:03:37<8:10:11, 19.93s/it]
 20%|██        | 373/1848 [2:03:57<8:09:57, 19.93s/it]
                                                      

 20%|██        | 373/1848 [2:03:57<8:09:57, 19.93s/it]
 20%|██        | 374/1848 [2:04:16<8:09:24, 19.92s/it]
                                                      

 20%|██        | 374/1848 [2:04:16<8:09:24, 19.92s/it]
 20%|██        | 375/1848 [2:04:36<8:08:49, 19.91s/it]
                                                      

 20%|██        | 375/1848 [2:04:36<8:08:49, 19.91s/it]
 20%|██        | 376/1848 [2:04:56<8:08:43, 19.92s/it]
                                                      

 20%|██        | 376/1848 [2:04:56<8:08:43, 19.92s/it]
 20%|██        | 377/1848 [2:05:16<8:08:47, 19.94s/it]
                                                      

 20%|██        | 377/1848 [2:05:16<8:08:47, 19.94s/it]
 20%|██        | 378/1848 [2:05:36<8:08:36, 19.94s/it]
                                                      

 20%|██        | 378/1848 [2:05:36<8:08:36, 19.94s/it]
 21%|██        | 379/1848 [2:05:56<8:08:03, 19.93s/it]
                                                      

 21%|██        | 379/1848 [2:05:56<8:08:03, 19.93s/it]
 21%|██        | 380/1848 [2:06:16<8:07:25, 19.92s/it]
                                                      

 21%|██        | 380/1848 [2:06:16<8:07:25, 19.92s/it]
 21%|██        | 381/1848 [2:06:36<8:07:34, 19.94s/it]
                                                      

 21%|██        | 381/1848 [2:06:36<8:07:34, 19.94s/it]
 21%|██        | 382/1848 [2:06:56<8:06:59, 19.93s/it]
                                                      

 21%|██        | 382/1848 [2:06:56<8:06:59, 19.93s/it]
 21%|██        | 383/1848 [2:07:16<8:06:45, 19.94s/it]
                                                      

 21%|██        | 383/1848 [2:07:16<8:06:45, 19.94s/it]
 21%|██        | 384/1848 [2:07:36<8:06:42, 19.95s/it]
                                                      

 21%|██        | 384/1848 [2:07:36<8:06:42, 19.95s/it]
 21%|██        | 385/1848 [2:07:56<8:06:11, 19.94s/it]
                                                      

 21%|██        | 385/1848 [2:07:56<8:06:11, 19.94s/it]
 21%|██        | 386/1848 [2:08:16<8:06:19, 19.96s/it]
                                                      

 21%|██        | 386/1848 [2:08:16<8:06:19, 19.96s/it]
 21%|██        | 387/1848 [2:08:36<8:05:34, 19.94s/it]
                                                      

 21%|██        | 387/1848 [2:08:36<8:05:34, 19.94s/it]
 21%|██        | 388/1848 [2:08:56<8:05:05, 19.94s/it]
                                                      

 21%|██        | 388/1848 [2:08:56<8:05:05, 19.94s/it]
 21%|██        | 389/1848 [2:09:16<8:04:50, 19.94s/it]
                                                      

 21%|██        | 389/1848 [2:09:16<8:04:50, 19.94s/it]
 21%|██        | 390/1848 [2:09:35<8:04:38, 19.94s/it]
                                                      

 21%|██        | 390/1848 [2:09:35<8:04:38, 19.94s/it]
 21%|██        | 391/1848 [2:09:55<8:04:50, 19.97s/it]
                                                      

 21%|██        | 391/1848 [2:09:55<8:04:50, 19.97s/it]
 21%|██        | 392/1848 [2:10:15<8:04:03, 19.95s/it]
                                                      

 21%|██        | 392/1848 [2:10:15<8:04:03, 19.95s/it]
 21%|██▏       | 393/1848 [2:10:35<8:03:28, 19.94s/it]
                                                      

 21%|██▏       | 393/1848 [2:10:35<8:03:28, 19.94s/it]
 21%|██▏       | 394/1848 [2:10:55<8:03:05, 19.94s/it]
                                                      

 21%|██▏       | 394/1848 [2:10:55<8:03:05, 19.94s/it]
 21%|██▏       | 395/1848 [2:11:15<8:02:34, 19.93s/it]
                                                      

 21%|██▏       | 395/1848 [2:11:15<8:02:34, 19.93s/it]
 21%|██▏       | 396/1848 [2:11:35<8:02:38, 19.94s/it]
                                                      

 21%|██▏       | 396/1848 [2:11:35<8:02:38, 19.94s/it]
 21%|██▏       | 397/1848 [2:11:55<8:02:13, 19.94s/it]
                                                      

 21%|██▏       | 397/1848 [2:11:55<8:02:13, 19.94s/it]
 22%|██▏       | 398/1848 [2:12:15<8:01:35, 19.93s/it]
                                                      

 22%|██▏       | 398/1848 [2:12:15<8:01:35, 19.93s/it]
 22%|██▏       | 399/1848 [2:12:35<8:01:34, 19.94s/it]
                                                      

 22%|██▏       | 399/1848 [2:12:35<8:01:34, 19.94s/it]
 22%|██▏       | 400/1848 [2:12:55<8:01:09, 19.94s/it]
                                                      

 22%|██▏       | 400/1848 [2:12:55<8:01:09, 19.94s/it]
 22%|██▏       | 401/1848 [2:13:16<8:06:42, 20.18s/it]
                                                      

 22%|██▏       | 401/1848 [2:13:16<8:06:42, 20.18s/it]
 22%|██▏       | 402/1848 [2:13:36<8:04:17, 20.10s/it]
                                                      

 22%|██▏       | 402/1848 [2:13:36<8:04:17, 20.10s/it]
 22%|██▏       | 403/1848 [2:13:55<8:02:46, 20.05s/it]
                                                      

 22%|██▏       | 403/1848 [2:13:55<8:02:46, 20.05s/it]
 22%|██▏       | 404/1848 [2:14:15<8:01:24, 20.00s/it]
                                                      

 22%|██▏       | 404/1848 [2:14:15<8:01:24, 20.00s/it]
 22%|██▏       | 405/1848 [2:14:35<8:00:31, 19.98s/it]
                                                      

 22%|██▏       | 405/1848 [2:14:35<8:00:31, 19.98s/it]
 22%|██▏       | 406/1848 [2:14:55<7:58:50, 19.92s/it]
                                                      

 22%|██▏       | 406/1848 [2:14:55<7:58:50, 19.92s/it]
 22%|██▏       | 407/1848 [2:15:15<7:58:27, 19.92s/it]
                                                      

 22%|██▏       | 407/1848 [2:15:15<7:58:27, 19.92s/it]
 22%|██▏       | 408/1848 [2:15:35<7:57:34, 19.90s/it]
                                                      

 22%|██▏       | 408/1848 [2:15:35<7:57:34, 19.90s/it]
 22%|██▏       | 409/1848 [2:15:55<7:57:17, 19.90s/it]
                                                      

 22%|██▏       | 409/1848 [2:15:55<7:57:17, 19.90s/it]
 22%|██▏       | 410/1848 [2:16:15<7:57:18, 19.92s/it]
                                                      

 22%|██▏       | 410/1848 [2:16:15<7:57:18, 19.92s/it]
 22%|██▏       | 411/1848 [2:16:35<7:57:05, 19.92s/it]
                                                      

 22%|██▏       | 411/1848 [2:16:35<7:57:05, 19.92s/it]
 22%|██▏       | 412/1848 [2:16:55<7:56:36, 19.91s/it]
                                                      

 22%|██▏       | 412/1848 [2:16:55<7:56:36, 19.91s/it]
 22%|██▏       | 413/1848 [2:17:14<7:56:33, 19.93s/it]
                                                      

 22%|██▏       | 413/1848 [2:17:14<7:56:33, 19.93s/it]
 22%|██▏       | 414/1848 [2:17:34<7:56:24, 19.93s/it]
                                                      

 22%|██▏       | 414/1848 [2:17:34<7:56:24, 19.93s/it]
 22%|██▏       | 415/1848 [2:17:54<7:55:33, 19.91s/it]
                                                      

 22%|██▏       | 415/1848 [2:17:54<7:55:33, 19.91s/it]
 23%|██▎       | 416/1848 [2:18:14<7:55:09, 19.91s/it]
                                                      

 23%|██▎       | 416/1848 [2:18:14<7:55:09, 19.91s/it]
 23%|██▎       | 417/1848 [2:18:34<7:54:49, 19.91s/it]
                                                      

 23%|██▎       | 417/1848 [2:18:34<7:54:49, 19.91s/it]
 23%|██▎       | 418/1848 [2:18:54<7:54:58, 19.93s/it]
                                                      

 23%|██▎       | 418/1848 [2:18:54<7:54:58, 19.93s/it]
 23%|██▎       | 419/1848 [2:19:14<7:54:21, 19.92s/it]
                                                      

 23%|██▎       | 419/1848 [2:19:14<7:54:21, 19.92s/it]
 23%|██▎       | 420/1848 [2:19:34<7:53:54, 19.91s/it]
                                                      

 23%|██▎       | 420/1848 [2:19:34<7:53:54, 19.91s/it]
 23%|██▎       | 421/1848 [2:19:54<7:53:43, 19.92s/it]
                                                      

 23%|██▎       | 421/1848 [2:19:54<7:53:43, 19.92s/it]
 23%|██▎       | 422/1848 [2:20:14<7:52:55, 19.90s/it]
                                                      

 23%|██▎       | 422/1848 [2:20:14<7:52:55, 19.90s/it]
 23%|██▎       | 423/1848 [2:20:34<7:53:08, 19.92s/it]
                                                      

 23%|██▎       | 423/1848 [2:20:34<7:53:08, 19.92s/it]
 23%|██▎       | 424/1848 [2:20:54<7:52:50, 19.92s/it]
                                                      

 23%|██▎       | 424/1848 [2:20:54<7:52:50, 19.92s/it]
 23%|██▎       | 425/1848 [2:21:14<7:52:56, 19.94s/it]
                                                      

 23%|██▎       | 425/1848 [2:21:14<7:52:56, 19.94s/it]
 23%|██▎       | 426/1848 [2:21:33<7:52:13, 19.92s/it]
                                                      

 23%|██▎       | 426/1848 [2:21:33<7:52:13, 19.92s/it]
 23%|██▎       | 427/1848 [2:21:53<7:51:30, 19.91s/it]
                                                      

 23%|██▎       | 427/1848 [2:21:53<7:51:30, 19.91s/it]
 23%|██▎       | 428/1848 [2:22:13<7:51:13, 19.91s/it]
                                                      

 23%|██▎       | 428/1848 [2:22:13<7:51:13, 19.91s/it]
 23%|██▎       | 429/1848 [2:22:33<7:51:29, 19.94s/it]
                                                      

 23%|██▎       | 429/1848 [2:22:33<7:51:29, 19.94s/it]
 23%|██▎       | 430/1848 [2:22:53<7:50:46, 19.92s/it]
                                                      

 23%|██▎       | 430/1848 [2:22:53<7:50:46, 19.92s/it]
 23%|██▎       | 431/1848 [2:23:13<7:50:42, 19.93s/it]
                                                      

 23%|██▎       | 431/1848 [2:23:13<7:50:42, 19.93s/it]
 23%|██▎       | 432/1848 [2:23:33<7:50:14, 19.93s/it]
                                                      

 23%|██▎       | 432/1848 [2:23:33<7:50:14, 19.93s/it]
 23%|██▎       | 433/1848 [2:23:53<7:49:55, 19.93s/it]
                                                      

 23%|██▎       | 433/1848 [2:23:53<7:49:55, 19.93s/it]
 23%|██▎       | 434/1848 [2:24:13<7:49:16, 19.91s/it]
                                                      

 23%|██▎       | 434/1848 [2:24:13<7:49:16, 19.91s/it]
 24%|██▎       | 435/1848 [2:24:33<7:48:46, 19.91s/it]
                                                      

 24%|██▎       | 435/1848 [2:24:33<7:48:46, 19.91s/it]
 24%|██▎       | 436/1848 [2:24:53<7:48:38, 19.91s/it]
                                                      

 24%|██▎       | 436/1848 [2:24:53<7:48:38, 19.91s/it]
 24%|██▎       | 437/1848 [2:25:13<7:48:34, 19.93s/it]
                                                      

 24%|██▎       | 437/1848 [2:25:13<7:48:34, 19.93s/it]
 24%|██▎       | 438/1848 [2:25:32<7:48:27, 19.93s/it]
                                                      

 24%|██▎       | 438/1848 [2:25:32<7:48:27, 19.93s/it]
 24%|██▍       | 439/1848 [2:25:52<7:48:09, 19.94s/it]
                                                      

 24%|██▍       | 439/1848 [2:25:52<7:48:09, 19.94s/it]
 24%|██▍       | 440/1848 [2:26:12<7:47:45, 19.93s/it]
                                                      

 24%|██▍       | 440/1848 [2:26:12<7:47:45, 19.93s/it]
 24%|██▍       | 441/1848 [2:26:32<7:47:51, 19.95s/it]
                                                      

 24%|██▍       | 441/1848 [2:26:32<7:47:51, 19.95s/it]
 24%|██▍       | 442/1848 [2:26:52<7:47:04, 19.93s/it]
                                                      

 24%|██▍       | 442/1848 [2:26:52<7:47:04, 19.93s/it]
 24%|██▍       | 443/1848 [2:27:12<7:46:43, 19.93s/it]
                                                      

 24%|██▍       | 443/1848 [2:27:12<7:46:43, 19.93s/it]
 24%|██▍       | 444/1848 [2:27:32<7:46:40, 19.94s/it]
                                                      

 24%|██▍       | 444/1848 [2:27:32<7:46:40, 19.94s/it]
 24%|██▍       | 445/1848 [2:27:52<7:46:11, 19.94s/it]
                                                      

 24%|██▍       | 445/1848 [2:27:52<7:46:11, 19.94s/it]
 24%|██▍       | 446/1848 [2:28:12<7:45:54, 19.94s/it]
                                                      

 24%|██▍       | 446/1848 [2:28:12<7:45:54, 19.94s/it]
 24%|██▍       | 447/1848 [2:28:32<7:45:39, 19.94s/it]
                                                      

 24%|██▍       | 447/1848 [2:28:32<7:45:39, 19.94s/it]
 24%|██▍       | 448/1848 [2:28:52<7:44:39, 19.91s/it]
                                                      

 24%|██▍       | 448/1848 [2:28:52<7:44:39, 19.91s/it]
 24%|██▍       | 449/1848 [2:29:12<7:44:04, 19.90s/it]
                                                      

 24%|██▍       | 449/1848 [2:29:12<7:44:04, 19.90s/it]
 24%|██▍       | 450/1848 [2:29:32<7:43:49, 19.91s/it]
                                                      
{'loss': 1.1706, 'learning_rate': 1.1521103896103897e-05, 'epoch': 0.55}
+{'loss': 1.2884, 'learning_rate': 1.1513474025974026e-05, 'epoch': 0.55}
+{'loss': 1.4375, 'learning_rate': 1.1505844155844155e-05, 'epoch': 0.55}
+{'loss': 1.3879, 'learning_rate': 1.1498214285714285e-05, 'epoch': 0.55}
+{'loss': 1.2017, 'learning_rate': 1.1490584415584416e-05, 'epoch': 0.56}
+{'loss': 1.2392, 'learning_rate': 1.1482954545454546e-05, 'epoch': 0.56}
+{'loss': 1.3252, 'learning_rate': 1.1475324675324675e-05, 'epoch': 0.56}
+{'loss': 1.4254, 'learning_rate': 1.1467694805194806e-05, 'epoch': 0.56}
+{'loss': 1.126, 'learning_rate': 1.1460064935064936e-05, 'epoch': 0.56}
+{'loss': 1.4821, 'learning_rate': 1.1452435064935065e-05, 'epoch': 0.56}
+{'loss': 1.1915, 'learning_rate': 1.1444805194805196e-05, 'epoch': 0.56}
+{'loss': 1.2189, 'learning_rate': 1.1437175324675326e-05, 'epoch': 0.57}
+{'loss': 1.227, 'learning_rate': 1.1429545454545455e-05, 'epoch': 0.57}
+{'loss': 1.4366, 'learning_rate': 1.1421915584415585e-05, 'epoch': 0.57}
+{'loss': 1.3972, 'learning_rate': 1.1414285714285714e-05, 'epoch': 0.57}
+{'loss': 1.3478, 'learning_rate': 1.1406655844155845e-05, 'epoch': 0.57}
+{'loss': 1.1426, 'learning_rate': 1.1399025974025973e-05, 'epoch': 0.57}
+{'loss': 1.0733, 'learning_rate': 1.1391396103896104e-05, 'epoch': 0.58}
+{'loss': 1.3505, 'learning_rate': 1.1383766233766234e-05, 'epoch': 0.58}
+{'loss': 1.0904, 'learning_rate': 1.1376136363636363e-05, 'epoch': 0.58}
+{'loss': 1.4269, 'learning_rate': 1.1368506493506494e-05, 'epoch': 0.58}
+{'loss': 1.3171, 'learning_rate': 1.1360876623376624e-05, 'epoch': 0.58}
+{'loss': 1.2509, 'learning_rate': 1.1353246753246755e-05, 'epoch': 0.58}
+{'loss': 1.2586, 'learning_rate': 1.1345616883116884e-05, 'epoch': 0.59}
+{'loss': 1.2584, 'learning_rate': 1.1337987012987014e-05, 'epoch': 0.59}
+{'loss': 1.1984, 'learning_rate': 1.1330357142857145e-05, 'epoch': 0.59}
+{'loss': 1.4175, 'learning_rate': 1.1322727272727272e-05, 'epoch': 0.59}
+{'loss': 1.4828, 'learning_rate': 1.1315097402597402e-05, 'epoch': 0.59}
+{'loss': 1.1902, 'learning_rate': 1.1307467532467533e-05, 'epoch': 0.59}
+{'loss': 1.1694, 'learning_rate': 1.1299837662337663e-05, 'epoch': 0.6}
+{'loss': 1.2906, 'learning_rate': 1.1292207792207792e-05, 'epoch': 0.6}
+{'loss': 1.0729, 'learning_rate': 1.1284577922077922e-05, 'epoch': 0.6}
+{'loss': 1.1119, 'learning_rate': 1.1276948051948053e-05, 'epoch': 0.6}
+{'loss': 1.1442, 'learning_rate': 1.1269318181818182e-05, 'epoch': 0.6}
+{'loss': 1.2184, 'learning_rate': 1.1261688311688312e-05, 'epoch': 0.6}
+{'loss': 1.2012, 'learning_rate': 1.1254058441558443e-05, 'epoch': 0.61}
+{'loss': 1.3171, 'learning_rate': 1.1246428571428573e-05, 'epoch': 0.61}
+{'loss': 1.3582, 'learning_rate': 1.1238798701298702e-05, 'epoch': 0.61}
+{'loss': 1.3426, 'learning_rate': 1.1231168831168831e-05, 'epoch': 0.61}
+{'loss': 1.1679, 'learning_rate': 1.1223538961038961e-05, 'epoch': 0.61}
+{'loss': 1.2662, 'learning_rate': 1.121590909090909e-05, 'epoch': 0.61}
+{'loss': 1.3046, 'learning_rate': 1.120827922077922e-05, 'epoch': 0.62}
+{'loss': 1.3308, 'learning_rate': 1.1200649350649351e-05, 'epoch': 0.62}
+{'loss': 1.2688, 'learning_rate': 1.119301948051948e-05, 'epoch': 0.62}
+{'loss': 1.1716, 'learning_rate': 1.118538961038961e-05, 'epoch': 0.62}
+{'loss': 1.1562, 'learning_rate': 1.1177759740259741e-05, 'epoch': 0.62}
+{'loss': 1.2724, 'learning_rate': 1.1170129870129871e-05, 'epoch': 0.62}
+{'loss': 1.2287, 'learning_rate': 1.11625e-05, 'epoch': 0.62}
+{'loss': 1.3218, 'learning_rate': 1.115487012987013e-05, 'epoch': 0.63}
+{'loss': 1.3035, 'learning_rate': 1.1147240259740261e-05, 'epoch': 0.63}
+{'loss': 1.2677, 'learning_rate': 1.113961038961039e-05, 'epoch': 0.63}
+{'loss': 1.3939, 'learning_rate': 1.1131980519480519e-05, 'epoch': 0.63}
+{'loss': 1.2971, 'learning_rate': 1.112435064935065e-05, 'epoch': 0.63}
+{'loss': 1.3575, 'learning_rate': 1.111672077922078e-05, 'epoch': 0.63}
+{'loss': 1.0896, 'learning_rate': 1.1109090909090909e-05, 'epoch': 0.64}
+{'loss': 1.0819, 'learning_rate': 1.110146103896104e-05, 'epoch': 0.64}
+{'loss': 1.3077, 'learning_rate': 1.109383116883117e-05, 'epoch': 0.64}
+{'loss': 1.219, 'learning_rate': 1.1086201298701298e-05, 'epoch': 0.64}
+{'loss': 1.134, 'learning_rate': 1.1078571428571429e-05, 'epoch': 0.64}
+{'loss': 1.2066, 'learning_rate': 1.107094155844156e-05, 'epoch': 0.64}
+{'loss': 1.0778, 'learning_rate': 1.106331168831169e-05, 'epoch': 0.65}
+{'loss': 1.3514, 'learning_rate': 1.1055681818181819e-05, 'epoch': 0.65}
+{'loss': 1.3695, 'learning_rate': 1.104805194805195e-05, 'epoch': 0.65}
+{'loss': 1.3197, 'learning_rate': 1.1040422077922078e-05, 'epoch': 0.65}
+{'loss': 1.0505, 'learning_rate': 1.1032792207792207e-05, 'epoch': 0.65}
+{'loss': 1.4356, 'learning_rate': 1.1025162337662337e-05, 'epoch': 0.65}
+{'loss': 1.2974, 'learning_rate': 1.1017532467532468e-05, 'epoch': 0.66}
+{'loss': 1.2525, 'learning_rate': 1.1009902597402598e-05, 'epoch': 0.66}
+{'loss': 1.5539, 'learning_rate': 1.1002272727272727e-05, 'epoch': 0.66}
+{'loss': 1.4519, 'learning_rate': 1.0994642857142858e-05, 'epoch': 0.66}
+{'loss': 1.3634, 'learning_rate': 1.0987012987012988e-05, 'epoch': 0.66}
+{'loss': 1.2532, 'learning_rate': 1.0979383116883117e-05, 'epoch': 0.66}
+{'loss': 1.33, 'learning_rate': 1.0971753246753247e-05, 'epoch': 0.67}
+{'loss': 1.3781, 'learning_rate': 1.0964123376623378e-05, 'epoch': 0.67}
+{'loss': 1.2783, 'learning_rate': 1.0956493506493508e-05, 'epoch': 0.67}
+{'loss': 1.2158, 'learning_rate': 1.0948863636363636e-05, 'epoch': 0.67}
+{'loss': 1.2207, 'learning_rate': 1.0941233766233766e-05, 'epoch': 0.67}
+{'loss': 1.3628, 'learning_rate': 1.0933603896103897e-05, 'epoch': 0.67}
+{'loss': 1.2518, 'learning_rate': 1.0925974025974025e-05, 'epoch': 0.68}
+{'loss': 1.2881, 'learning_rate': 1.0918344155844156e-05, 'epoch': 0.68}
+{'loss': 1.1865, 'learning_rate': 1.0910714285714286e-05, 'epoch': 0.68}
+{'loss': 1.3434, 'learning_rate': 1.0903084415584415e-05, 'epoch': 0.68}
+{'loss': 1.337, 'learning_rate': 1.0895454545454546e-05, 'epoch': 0.68}
+{'loss': 1.3625, 'learning_rate': 1.0887824675324676e-05, 'epoch': 0.68}
+{'loss': 1.4909, 'learning_rate': 1.0880194805194807e-05, 'epoch': 0.69}
+{'loss': 1.2713, 'learning_rate': 1.0872564935064936e-05, 'epoch': 0.69}
+{'loss': 1.237, 'learning_rate': 1.0864935064935066e-05, 'epoch': 0.69}
+{'loss': 1.1254, 'learning_rate': 1.0857305194805195e-05, 'epoch': 0.69}
+{'loss': 1.3516, 'learning_rate': 1.0849675324675324e-05, 'epoch': 0.69}
+{'loss': 1.2355, 'learning_rate': 1.0842045454545454e-05, 'epoch': 0.69}
+{'loss': 1.4649, 'learning_rate': 1.0834415584415585e-05, 'epoch': 0.69}
+{'loss': 1.3947, 'learning_rate': 1.0826785714285715e-05, 'epoch': 0.7}
+{'loss': 1.247, 'learning_rate': 1.0819155844155844e-05, 'epoch': 0.7}
+{'loss': 1.2519, 'learning_rate': 1.0811525974025974e-05, 'epoch': 0.7}
+{'loss': 1.3365, 'learning_rate': 1.0803896103896105e-05, 'epoch': 0.7}
+{'loss': 1.2232, 'learning_rate': 1.0796266233766234e-05, 'epoch': 0.7}
+{'loss': 1.5287, 'learning_rate': 1.0788636363636364e-05, 'epoch': 0.7}
+{'loss': 1.2319, 'learning_rate': 1.0781006493506495e-05, 'epoch': 0.71}
+{'loss': 1.3321, 'learning_rate': 1.0773376623376625e-05, 'epoch': 0.71}
+{'loss': 1.2423, 'learning_rate': 1.0765746753246754e-05, 'epoch': 0.71}
+{'loss': 1.3389, 'learning_rate': 1.0758116883116883e-05, 'epoch': 0.71}
+{'loss': 1.2857, 'learning_rate': 1.0750487012987013e-05, 'epoch': 0.71}
+{'loss': 1.2882, 'learning_rate': 1.0742857142857142e-05, 'epoch': 0.71}
+{'loss': 1.253, 'learning_rate': 1.0735227272727273e-05, 'epoch': 0.72}
+{'loss': 1.1981, 'learning_rate': 1.0727597402597403e-05, 'epoch': 0.72}
+{'loss': 1.0101, 'learning_rate': 1.0719967532467534e-05, 'epoch': 0.72}
+{'loss': 1.2596, 'learning_rate': 1.0712337662337662e-05, 'epoch': 0.72}
+{'loss': 1.2464, 'learning_rate': 1.0704707792207793e-05, 'epoch': 0.72}
+{'loss': 1.1835, 'learning_rate': 1.0697077922077923e-05, 'epoch': 0.72}
+{'loss': 1.3934, 'learning_rate': 1.0689448051948052e-05, 'epoch': 0.73}
+{'loss': 1.0661, 'learning_rate': 1.0681818181818183e-05, 'epoch': 0.73}
+{'loss': 1.3827, 'learning_rate': 1.0674188311688313e-05, 'epoch': 0.73}
+
 24%|██▍       | 450/1848 [2:29:32<7:43:49, 19.91s/it]
 24%|██▍       | 451/1848 [2:29:51<7:43:16, 19.90s/it]
                                                      

 24%|██▍       | 451/1848 [2:29:51<7:43:16, 19.90s/it]
 24%|██▍       | 452/1848 [2:30:11<7:43:12, 19.91s/it]
                                                      

 24%|██▍       | 452/1848 [2:30:11<7:43:12, 19.91s/it]
 25%|██▍       | 453/1848 [2:30:31<7:43:01, 19.92s/it]
                                                      

 25%|██▍       | 453/1848 [2:30:31<7:43:01, 19.92s/it]
 25%|██▍       | 454/1848 [2:30:51<7:42:53, 19.92s/it]
                                                      

 25%|██▍       | 454/1848 [2:30:51<7:42:53, 19.92s/it]
 25%|██▍       | 455/1848 [2:31:11<7:42:37, 19.93s/it]
                                                      

 25%|██▍       | 455/1848 [2:31:11<7:42:37, 19.93s/it]
 25%|██▍       | 456/1848 [2:31:31<7:42:34, 19.94s/it]
                                                      

 25%|██▍       | 456/1848 [2:31:31<7:42:34, 19.94s/it]
 25%|██▍       | 457/1848 [2:31:51<7:42:29, 19.95s/it]
                                                      

 25%|██▍       | 457/1848 [2:31:51<7:42:29, 19.95s/it]
 25%|██▍       | 458/1848 [2:32:11<7:42:13, 19.95s/it]
                                                      

 25%|██▍       | 458/1848 [2:32:11<7:42:13, 19.95s/it]
 25%|██▍       | 459/1848 [2:32:31<7:41:26, 19.93s/it]
                                                      

 25%|██▍       | 459/1848 [2:32:31<7:41:26, 19.93s/it]
 25%|██▍       | 460/1848 [2:32:51<7:41:17, 19.94s/it]
                                                      

 25%|██▍       | 460/1848 [2:32:51<7:41:17, 19.94s/it]
 25%|██▍       | 461/1848 [2:33:11<7:41:23, 19.96s/it]
                                                      

 25%|██▍       | 461/1848 [2:33:11<7:41:23, 19.96s/it]
 25%|██▌       | 462/1848 [2:33:31<7:40:47, 19.95s/it]
                                                      

 25%|██▌       | 462/1848 [2:33:31<7:40:47, 19.95s/it]
 25%|██▌       | 463/1848 [2:33:51<7:40:03, 19.93s/it]
                                                      

 25%|██▌       | 463/1848 [2:33:51<7:40:03, 19.93s/it]
 25%|██▌       | 464/1848 [2:34:11<7:40:00, 19.94s/it]
                                                      

 25%|██▌       | 464/1848 [2:34:11<7:40:00, 19.94s/it]
 25%|██▌       | 465/1848 [2:34:31<7:39:37, 19.94s/it]
                                                      

 25%|██▌       | 465/1848 [2:34:31<7:39:37, 19.94s/it]
 25%|██▌       | 466/1848 [2:34:51<7:39:19, 19.94s/it]
                                                      

 25%|██▌       | 466/1848 [2:34:51<7:39:19, 19.94s/it]
 25%|██▌       | 467/1848 [2:35:10<7:38:23, 19.92s/it]
                                                      

 25%|██▌       | 467/1848 [2:35:10<7:38:23, 19.92s/it]
 25%|██▌       | 468/1848 [2:35:30<7:38:07, 19.92s/it]
                                                      

 25%|██▌       | 468/1848 [2:35:30<7:38:07, 19.92s/it]
 25%|██▌       | 469/1848 [2:35:50<7:37:44, 19.92s/it]
                                                      

 25%|██▌       | 469/1848 [2:35:50<7:37:44, 19.92s/it]
 25%|██▌       | 470/1848 [2:36:10<7:37:40, 19.93s/it]
                                                      

 25%|██▌       | 470/1848 [2:36:10<7:37:40, 19.93s/it]
 25%|██▌       | 471/1848 [2:36:30<7:37:43, 19.94s/it]
                                                      

 25%|██▌       | 471/1848 [2:36:30<7:37:43, 19.94s/it]
 26%|██▌       | 472/1848 [2:36:50<7:37:01, 19.93s/it]
                                                      

 26%|██▌       | 472/1848 [2:36:50<7:37:01, 19.93s/it]
 26%|██▌       | 473/1848 [2:37:10<7:36:55, 19.94s/it]
                                                      

 26%|██▌       | 473/1848 [2:37:10<7:36:55, 19.94s/it]
 26%|██▌       | 474/1848 [2:37:30<7:36:59, 19.96s/it]
                                                      

 26%|██▌       | 474/1848 [2:37:30<7:36:59, 19.96s/it]
 26%|██▌       | 475/1848 [2:37:50<7:36:29, 19.95s/it]
                                                      

 26%|██▌       | 475/1848 [2:37:50<7:36:29, 19.95s/it]
 26%|██▌       | 476/1848 [2:38:10<7:36:20, 19.96s/it]
                                                      

 26%|██▌       | 476/1848 [2:38:10<7:36:20, 19.96s/it]
 26%|██▌       | 477/1848 [2:38:30<7:35:53, 19.95s/it]
                                                      

 26%|██▌       | 477/1848 [2:38:30<7:35:53, 19.95s/it]
 26%|██▌       | 478/1848 [2:38:50<7:35:10, 19.93s/it]
                                                      

 26%|██▌       | 478/1848 [2:38:50<7:35:10, 19.93s/it]
 26%|██▌       | 479/1848 [2:39:10<7:34:57, 19.94s/it]
                                                      

 26%|██▌       | 479/1848 [2:39:10<7:34:57, 19.94s/it]
 26%|██▌       | 480/1848 [2:39:30<7:34:28, 19.93s/it]
                                                      

 26%|██▌       | 480/1848 [2:39:30<7:34:28, 19.93s/it]
 26%|██▌       | 481/1848 [2:39:50<7:33:55, 19.92s/it]
                                                      

 26%|██▌       | 481/1848 [2:39:50<7:33:55, 19.92s/it]
 26%|██▌       | 482/1848 [2:40:09<7:33:19, 19.91s/it]
                                                      

 26%|██▌       | 482/1848 [2:40:09<7:33:19, 19.91s/it]
 26%|██▌       | 483/1848 [2:40:29<7:32:28, 19.89s/it]
                                                      

 26%|██▌       | 483/1848 [2:40:29<7:32:28, 19.89s/it]
 26%|██▌       | 484/1848 [2:40:49<7:33:02, 19.93s/it]
                                                      

 26%|██▌       | 484/1848 [2:40:49<7:33:02, 19.93s/it]
 26%|██▌       | 485/1848 [2:41:09<7:32:35, 19.92s/it]
                                                      

 26%|██▌       | 485/1848 [2:41:09<7:32:35, 19.92s/it]
 26%|██▋       | 486/1848 [2:41:29<7:32:26, 19.93s/it]
                                                      

 26%|██▋       | 486/1848 [2:41:29<7:32:26, 19.93s/it]
 26%|██▋       | 487/1848 [2:41:49<7:32:15, 19.94s/it]
                                                      

 26%|██▋       | 487/1848 [2:41:49<7:32:15, 19.94s/it]
 26%|██▋       | 488/1848 [2:42:09<7:32:08, 19.95s/it]
                                                      

 26%|██▋       | 488/1848 [2:42:09<7:32:08, 19.95s/it]
 26%|██▋       | 489/1848 [2:42:29<7:31:53, 19.95s/it]
                                                      

 26%|██▋       | 489/1848 [2:42:29<7:31:53, 19.95s/it]
 27%|██▋       | 490/1848 [2:42:49<7:31:42, 19.96s/it]
                                                      

 27%|██▋       | 490/1848 [2:42:49<7:31:42, 19.96s/it]
 27%|██▋       | 491/1848 [2:43:09<7:31:56, 19.98s/it]
                                                      

 27%|██▋       | 491/1848 [2:43:09<7:31:56, 19.98s/it]
 27%|██▋       | 492/1848 [2:43:29<7:31:39, 19.99s/it]
                                                      

 27%|██▋       | 492/1848 [2:43:29<7:31:39, 19.99s/it]
 27%|██▋       | 493/1848 [2:43:49<7:31:04, 19.97s/it]
                                                      

 27%|██▋       | 493/1848 [2:43:49<7:31:04, 19.97s/it]
 27%|██▋       | 494/1848 [2:44:09<7:30:27, 19.96s/it]
                                                      

 27%|██▋       | 494/1848 [2:44:09<7:30:27, 19.96s/it]
 27%|██▋       | 495/1848 [2:44:29<7:29:32, 19.94s/it]
                                                      

 27%|██▋       | 495/1848 [2:44:29<7:29:32, 19.94s/it]
 27%|██▋       | 496/1848 [2:44:49<7:29:03, 19.93s/it]
                                                      

 27%|██▋       | 496/1848 [2:44:49<7:29:03, 19.93s/it]
 27%|██▋       | 497/1848 [2:45:09<7:28:52, 19.94s/it]
                                                      

 27%|██▋       | 497/1848 [2:45:09<7:28:52, 19.94s/it]
 27%|██▋       | 498/1848 [2:45:29<7:28:15, 19.92s/it]
                                                      

 27%|██▋       | 498/1848 [2:45:29<7:28:15, 19.92s/it]
 27%|██▋       | 499/1848 [2:45:49<7:28:20, 19.94s/it]
                                                      

 27%|██▋       | 499/1848 [2:45:49<7:28:20, 19.94s/it]
 27%|██▋       | 500/1848 [2:46:09<7:27:59, 19.94s/it]
                                                      

 27%|██▋       | 500/1848 [2:46:09<7:27:59, 19.94s/it]
 27%|██▋       | 501/1848 [2:46:29<7:33:35, 20.20s/it]
                                                      

 27%|██▋       | 501/1848 [2:46:29<7:33:35, 20.20s/it]
 27%|██▋       | 502/1848 [2:46:49<7:31:25, 20.12s/it]
                                                      

 27%|██▋       | 502/1848 [2:46:49<7:31:25, 20.12s/it]
 27%|██▋       | 503/1848 [2:47:09<7:30:16, 20.09s/it]
                                                      

 27%|██▋       | 503/1848 [2:47:09<7:30:16, 20.09s/it]
 27%|██▋       | 504/1848 [2:47:29<7:28:51, 20.04s/it]
                                                      

 27%|██▋       | 504/1848 [2:47:29<7:28:51, 20.04s/it]
 27%|██▋       | 505/1848 [2:47:49<7:27:58, 20.01s/it]
                                                      

 27%|██▋       | 505/1848 [2:47:49<7:27:58, 20.01s/it]
 27%|██▋       | 506/1848 [2:48:09<7:27:19, 20.00s/it]
                                                      

 27%|██▋       | 506/1848 [2:48:09<7:27:19, 20.00s/it]
 27%|██▋       | 507/1848 [2:48:29<7:26:26, 19.98s/it]
                                                      

 27%|██▋       | 507/1848 [2:48:29<7:26:26, 19.98s/it]
 27%|██▋       | 508/1848 [2:48:49<7:26:05, 19.97s/it]
                                                      

 27%|██▋       | 508/1848 [2:48:49<7:26:05, 19.97s/it]
 28%|██▊       | 509/1848 [2:49:09<7:25:34, 19.97s/it]
                                                      

 28%|██▊       | 509/1848 [2:49:09<7:25:34, 19.97s/it]
 28%|██▊       | 510/1848 [2:49:29<7:25:30, 19.98s/it]
                                                      

 28%|██▊       | 510/1848 [2:49:29<7:25:30, 19.98s/it]
 28%|██▊       | 511/1848 [2:49:49<7:24:52, 19.96s/it]
                                                      

 28%|██▊       | 511/1848 [2:49:49<7:24:52, 19.96s/it]
 28%|██▊       | 512/1848 [2:50:09<7:24:02, 19.94s/it]
                                                      

 28%|██▊       | 512/1848 [2:50:09<7:24:02, 19.94s/it]
 28%|██▊       | 513/1848 [2:50:29<7:24:00, 19.96s/it]
                                                      

 28%|██▊       | 513/1848 [2:50:29<7:24:00, 19.96s/it]
 28%|██▊       | 514/1848 [2:50:49<7:23:15, 19.94s/it]
                                                      

 28%|██▊       | 514/1848 [2:50:49<7:23:15, 19.94s/it]
 28%|██▊       | 515/1848 [2:51:09<7:22:52, 19.93s/it]
                                                      

 28%|██▊       | 515/1848 [2:51:09<7:22:52, 19.93s/it]
 28%|██▊       | 516/1848 [2:51:29<7:22:22, 19.93s/it]
                                                      

 28%|██▊       | 516/1848 [2:51:29<7:22:22, 19.93s/it]
 28%|██▊       | 517/1848 [2:51:48<7:22:15, 19.94s/it]
                                                      

 28%|██▊       | 517/1848 [2:51:48<7:22:15, 19.94s/it]
 28%|██▊       | 518/1848 [2:52:08<7:21:39, 19.92s/it]
                                                      

 28%|██▊       | 518/1848 [2:52:08<7:21:39, 19.92s/it]
 28%|██▊       | 519/1848 [2:52:28<7:21:04, 19.91s/it]
                                                      

 28%|██▊       | 519/1848 [2:52:28<7:21:04, 19.91s/it]
 28%|██▊       | 520/1848 [2:52:48<7:21:09, 19.93s/it]
                                                      

 28%|██▊       | 520/1848 [2:52:48<7:21:09, 19.93s/it]
 28%|██▊       | 521/1848 [2:53:08<7:21:05, 19.94s/it]
                                                      

 28%|██▊       | 521/1848 [2:53:08<7:21:05, 19.94s/it]
 28%|██▊       | 522/1848 [2:53:28<7:20:32, 19.93s/it]
                                                      

 28%|██▊       | 522/1848 [2:53:28<7:20:32, 19.93s/it]
 28%|██▊       | 523/1848 [2:53:48<7:20:08, 19.93s/it]
                                                      

 28%|██▊       | 523/1848 [2:53:48<7:20:08, 19.93s/it]
 28%|██▊       | 524/1848 [2:54:08<7:19:21, 19.91s/it]
                                                      

 28%|██▊       | 524/1848 [2:54:08<7:19:21, 19.91s/it]
 28%|██▊       | 525/1848 [2:54:28<7:19:06, 19.91s/it]
                                                      

 28%|██▊       | 525/1848 [2:54:28<7:19:06, 19.91s/it]
 28%|██▊       | 526/1848 [2:54:48<7:18:14, 19.89s/it]
                                                      

 28%|██▊       | 526/1848 [2:54:48<7:18:14, 19.89s/it]
 29%|██▊       | 527/1848 [2:55:08<7:17:50, 19.89s/it]
                                                      

 29%|██▊       | 527/1848 [2:55:08<7:17:50, 19.89s/it]
 29%|██▊       | 528/1848 [2:55:27<7:17:59, 19.91s/it]
                                                      

 29%|██▊       | 528/1848 [2:55:28<7:17:59, 19.91s/it]
 29%|██▊       | 529/1848 [2:55:47<7:18:13, 19.93s/it]
                                                      

 29%|██▊       | 529/1848 [2:55:47<7:18:13, 19.93s/it]
 29%|██▊       | 530/1848 [2:56:07<7:17:53, 19.93s/it]
                                                      

 29%|██▊       | 530/1848 [2:56:07<7:17:53, 19.93s/it]
 29%|██▊       | 531/1848 [2:56:27<7:17:27, 19.93s/it]
                                                      

 29%|██▊       | 531/1848 [2:56:27<7:17:27, 19.93s/it]
 29%|██▉       | 532/1848 [2:56:47<7:16:54, 19.92s/it]
                                                      

 29%|██▉       | 532/1848 [2:56:47<7:16:54, 19.92s/it]
 29%|██▉       | 533/1848 [2:57:07<7:16:13, 19.90s/it]
                                                      

 29%|██▉       | 533/1848 [2:57:07<7:16:13, 19.90s/it]
 29%|██▉       | 534/1848 [2:57:27<7:15:51, 19.90s/it]
                                                      

 29%|██▉       | 534/1848 [2:57:27<7:15:51, 19.90s/it]
 29%|██▉       | 535/1848 [2:57:47<7:16:07, 19.93s/it]
                                                      

 29%|██▉       | 535/1848 [2:57:47<7:16:07, 19.93s/it]
 29%|██▉       | 536/1848 [2:58:07<7:15:55, 19.94s/it]
                                                      

 29%|██▉       | 536/1848 [2:58:07<7:15:55, 19.94s/it]
 29%|██▉       | 537/1848 [2:58:27<7:15:44, 19.94s/it]
                                                      

 29%|██▉       | 537/1848 [2:58:27<7:15:44, 19.94s/it]
 29%|██▉       | 538/1848 [2:58:47<7:15:32, 19.95s/it]
                                                      

 29%|██▉       | 538/1848 [2:58:47<7:15:32, 19.95s/it]
 29%|██▉       | 539/1848 [2:59:07<7:14:57, 19.94s/it]
                                                      

 29%|██▉       | 539/1848 [2:59:07<7:14:57, 19.94s/it]
 29%|██▉       | 540/1848 [2:59:27<7:15:11, 19.96s/it]
                                                      

 29%|██▉       | 540/1848 [2:59:27<7:15:11, 19.96s/it]
 29%|██▉       | 541/1848 [2:59:47<7:14:53, 19.96s/it]
                                                      

 29%|██▉       | 541/1848 [2:59:47<7:14:53, 19.96s/it]
 29%|██▉       | 542/1848 [3:00:07<7:14:45, 19.97s/it]
                                                      

 29%|██▉       | 542/1848 [3:00:07<7:14:45, 19.97s/it]
 29%|██▉       | 543/1848 [3:00:27<7:13:57, 19.95s/it]
                                                      

 29%|██▉       | 543/1848 [3:00:27<7:13:57, 19.95s/it]
 29%|██▉       | 544/1848 [3:00:47<7:13:16, 19.94s/it]
                                                      

 29%|██▉       | 544/1848 [3:00:47<7:13:16, 19.94s/it]
 29%|██▉       | 545/1848 [3:01:06<7:12:53, 19.93s/it]
                                                      

 29%|██▉       | 545/1848 [3:01:07<7:12:53, 19.93s/it]
 30%|██▉       | 546/1848 [3:01:27<7:13:17, 19.97s/it]
                                                      

 30%|██▉       | 546/1848 [3:01:27<7:13:17, 19.97s/it]
 30%|██▉       | 547/1848 [3:01:46<7:12:46, 19.96s/it]
                                                      

 30%|██▉       | 547/1848 [3:01:46<7:12:46, 19.96s/it]
 30%|██▉       | 548/1848 [3:02:06<7:12:23, 19.96s/it]
                                                      

 30%|██▉       | 548/1848 [3:02:06<7:12:23, 19.96s/it]
 30%|██▉       | 549/1848 [3:02:26<7:12:22, 19.97s/it]
                                                      

 30%|██▉       | 549/1848 [3:02:26<7:12:22, 19.97s/it]
 30%|██▉       | 550/1848 [3:02:46<7:12:14, 19.98s/it]
                                                      

 30%|██▉       | 550/1848 [3:02:46<7:12:14, 19.98s/it]
 30%|██▉       | 551/1848 [3:03:06<7:11:40, 19.97s/it]
                                                      

 30%|██▉       | 551/1848 [3:03:06<7:11:40, 19.97s/it]
 30%|██▉       | 552/1848 [3:03:26<7:11:07, 19.96s/it]
                                                      

 30%|██▉       | 552/1848 [3:03:26<7:11:07, 19.96s/it]
 30%|██▉       | 553/1848 [3:03:46<7:11:12, 19.98s/it]
                                                      

 30%|██▉       | 553/1848 [3:03:46<7:11:12, 19.98s/it]
 30%|██▉       | 554/1848 [3:04:06<7:10:45, 19.97s/it]
                                                      

 30%|██▉       | 554/1848 [3:04:06<7:10:45, 19.97s/it]
 30%|███       | 555/1848 [3:04:26<7:10:28, 19.98s/it]
                                                      

 30%|███       | 555/1848 [3:04:26<7:10:28, 19.98s/it]
 30%|███       | 556/1848 [3:04:46<7:09:36, 19.95s/it]
                                                      

 30%|███       | 556/1848 [3:04:46<7:09:36, 19.95s/it]
 30%|███       | 557/1848 [3:05:06<7:09:02, 19.94s/it]
                                                      

 30%|███       | 557/1848 [3:05:06<7:09:02, 19.94s/it]
 30%|███       | 558/1848 [3:05:26<7:08:41, 19.94s/it]
                                                      

 30%|███       | 558/1848 [3:05:26<7:08:41, 19.94s/it]
 30%|███       | 559/1848 [3:05:46<7:08:59, 19.97s/it]
                                                      

 30%|███       | 559/1848 [3:05:46<7:08:59, 19.97s/it]
 30%|███       | 560/1848 [3:06:06<7:08:03, 19.94s/it]
                                                      

 30%|███       | 560/1848 [3:06:06<7:08:03, 19.94s/it]
 30%|███       | 561/1848 [3:06:26<7:06:57, 19.90s/it]
                                                      

 30%|███       | 561/1848 [3:06:26<7:06:57, 19.90s/it]
 30%|███       | 562/1848 [3:06:46<7:07:13, 19.93s/it]
                                                      

 30%|███       | 562/1848 [3:06:46<7:07:13, 19.93s/it]
 30%|███       | 563/1848 [3:07:06<7:07:14, 19.95s/it]
                                                      
{'loss': 1.3796, 'learning_rate': 1.0666558441558442e-05, 'epoch': 0.73}
+{'loss': 1.1271, 'learning_rate': 1.065892857142857e-05, 'epoch': 0.73}
+{'loss': 1.1879, 'learning_rate': 1.0651298701298701e-05, 'epoch': 0.73}
+{'loss': 1.3932, 'learning_rate': 1.0643668831168832e-05, 'epoch': 0.74}
+{'loss': 1.2512, 'learning_rate': 1.063603896103896e-05, 'epoch': 0.74}
+{'loss': 1.2227, 'learning_rate': 1.0628409090909091e-05, 'epoch': 0.74}
+{'loss': 1.1136, 'learning_rate': 1.0620779220779222e-05, 'epoch': 0.74}
+{'loss': 1.1376, 'learning_rate': 1.061314935064935e-05, 'epoch': 0.74}
+{'loss': 1.1801, 'learning_rate': 1.0605519480519481e-05, 'epoch': 0.74}
+{'loss': 1.2142, 'learning_rate': 1.0597889610389611e-05, 'epoch': 0.75}
+{'loss': 1.1762, 'learning_rate': 1.0590259740259742e-05, 'epoch': 0.75}
+{'loss': 1.1215, 'learning_rate': 1.058262987012987e-05, 'epoch': 0.75}
+{'loss': 1.1987, 'learning_rate': 1.0575e-05, 'epoch': 0.75}
+{'loss': 1.3087, 'learning_rate': 1.056737012987013e-05, 'epoch': 0.75}
+{'loss': 1.1867, 'learning_rate': 1.0559740259740259e-05, 'epoch': 0.75}
+{'loss': 1.2116, 'learning_rate': 1.055211038961039e-05, 'epoch': 0.75}
+{'loss': 1.0717, 'learning_rate': 1.054448051948052e-05, 'epoch': 0.76}
+{'loss': 1.2473, 'learning_rate': 1.053685064935065e-05, 'epoch': 0.76}
+{'loss': 1.4873, 'learning_rate': 1.0529220779220779e-05, 'epoch': 0.76}
+{'loss': 1.5121, 'learning_rate': 1.052159090909091e-05, 'epoch': 0.76}
+{'loss': 1.2001, 'learning_rate': 1.051396103896104e-05, 'epoch': 0.76}
+{'loss': 1.2241, 'learning_rate': 1.0506331168831169e-05, 'epoch': 0.76}
+{'loss': 1.3403, 'learning_rate': 1.04987012987013e-05, 'epoch': 0.77}
+{'loss': 1.0678, 'learning_rate': 1.049107142857143e-05, 'epoch': 0.77}
+{'loss': 1.1171, 'learning_rate': 1.0483441558441559e-05, 'epoch': 0.77}
+{'loss': 1.1222, 'learning_rate': 1.0475811688311688e-05, 'epoch': 0.77}
+{'loss': 1.2457, 'learning_rate': 1.0468181818181818e-05, 'epoch': 0.77}
+{'loss': 1.3102, 'learning_rate': 1.0460551948051949e-05, 'epoch': 0.77}
+{'loss': 1.1656, 'learning_rate': 1.0452922077922077e-05, 'epoch': 0.78}
+{'loss': 1.1559, 'learning_rate': 1.0445292207792208e-05, 'epoch': 0.78}
+{'loss': 1.1074, 'learning_rate': 1.0437662337662338e-05, 'epoch': 0.78}
+{'loss': 1.3517, 'learning_rate': 1.0430032467532467e-05, 'epoch': 0.78}
+{'loss': 1.2846, 'learning_rate': 1.0422402597402598e-05, 'epoch': 0.78}
+{'loss': 1.5502, 'learning_rate': 1.0414772727272728e-05, 'epoch': 0.78}
+{'loss': 1.1709, 'learning_rate': 1.0407142857142859e-05, 'epoch': 0.79}
+{'loss': 1.3137, 'learning_rate': 1.0399512987012987e-05, 'epoch': 0.79}
+{'loss': 1.0997, 'learning_rate': 1.0391883116883118e-05, 'epoch': 0.79}
+{'loss': 1.1527, 'learning_rate': 1.0384253246753247e-05, 'epoch': 0.79}
+{'loss': 1.2351, 'learning_rate': 1.0376623376623376e-05, 'epoch': 0.79}
+{'loss': 1.1368, 'learning_rate': 1.0368993506493506e-05, 'epoch': 0.79}
+{'loss': 1.214, 'learning_rate': 1.0361363636363637e-05, 'epoch': 0.8}
+{'loss': 1.0636, 'learning_rate': 1.0353733766233767e-05, 'epoch': 0.8}
+{'loss': 1.2763, 'learning_rate': 1.0346103896103896e-05, 'epoch': 0.8}
+{'loss': 1.15, 'learning_rate': 1.0338474025974026e-05, 'epoch': 0.8}
+{'loss': 1.3322, 'learning_rate': 1.0330844155844157e-05, 'epoch': 0.8}
+{'loss': 1.326, 'learning_rate': 1.0323214285714286e-05, 'epoch': 0.8}
+{'loss': 1.2125, 'learning_rate': 1.0315584415584416e-05, 'epoch': 0.81}
+{'loss': 1.0606, 'learning_rate': 1.0307954545454547e-05, 'epoch': 0.81}
+{'loss': 1.3238, 'learning_rate': 1.0300324675324677e-05, 'epoch': 0.81}
+{'loss': 1.2118, 'learning_rate': 1.0292694805194806e-05, 'epoch': 0.81}
+{'loss': 1.1086, 'learning_rate': 1.0285064935064935e-05, 'epoch': 0.81}
+{'loss': 1.1554, 'learning_rate': 1.0277435064935065e-05, 'epoch': 0.81}
+{'loss': 1.2242, 'learning_rate': 1.0269805194805194e-05, 'epoch': 0.81}
+{'loss': 1.3557, 'learning_rate': 1.0262175324675325e-05, 'epoch': 0.82}
+{'loss': 1.1942, 'learning_rate': 1.0254545454545455e-05, 'epoch': 0.82}
+{'loss': 1.1402, 'learning_rate': 1.0246915584415586e-05, 'epoch': 0.82}
+{'loss': 1.2951, 'learning_rate': 1.0239285714285714e-05, 'epoch': 0.82}
+{'loss': 1.1942, 'learning_rate': 1.0231655844155845e-05, 'epoch': 0.82}
+{'loss': 1.2907, 'learning_rate': 1.0224025974025975e-05, 'epoch': 0.82}
+{'loss': 1.399, 'learning_rate': 1.0216396103896104e-05, 'epoch': 0.83}
+{'loss': 1.3473, 'learning_rate': 1.0208766233766235e-05, 'epoch': 0.83}
+{'loss': 1.2693, 'learning_rate': 1.0201136363636365e-05, 'epoch': 0.83}
+{'loss': 1.1169, 'learning_rate': 1.0193506493506492e-05, 'epoch': 0.83}
+{'loss': 1.333, 'learning_rate': 1.0185876623376623e-05, 'epoch': 0.83}
+{'loss': 1.1432, 'learning_rate': 1.0178246753246753e-05, 'epoch': 0.83}
+{'loss': 1.1896, 'learning_rate': 1.0170616883116884e-05, 'epoch': 0.84}
+{'loss': 1.1462, 'learning_rate': 1.0162987012987013e-05, 'epoch': 0.84}
+{'loss': 1.3072, 'learning_rate': 1.0155357142857143e-05, 'epoch': 0.84}
+{'loss': 1.2179, 'learning_rate': 1.0147727272727274e-05, 'epoch': 0.84}
+{'loss': 1.2965, 'learning_rate': 1.0140097402597402e-05, 'epoch': 0.84}
+{'loss': 1.0908, 'learning_rate': 1.0132467532467533e-05, 'epoch': 0.84}
+{'loss': 1.2296, 'learning_rate': 1.0124837662337663e-05, 'epoch': 0.85}
+{'loss': 1.2919, 'learning_rate': 1.0117207792207794e-05, 'epoch': 0.85}
+{'loss': 1.3606, 'learning_rate': 1.0109577922077923e-05, 'epoch': 0.85}
+{'loss': 1.4584, 'learning_rate': 1.0101948051948052e-05, 'epoch': 0.85}
+{'loss': 1.2766, 'learning_rate': 1.0094318181818182e-05, 'epoch': 0.85}
+{'loss': 1.1672, 'learning_rate': 1.008668831168831e-05, 'epoch': 0.85}
+{'loss': 1.2176, 'learning_rate': 1.0079058441558441e-05, 'epoch': 0.86}
+{'loss': 1.3978, 'learning_rate': 1.0071428571428572e-05, 'epoch': 0.86}
+{'loss': 1.1606, 'learning_rate': 1.0063798701298702e-05, 'epoch': 0.86}
+{'loss': 1.1301, 'learning_rate': 1.0056168831168831e-05, 'epoch': 0.86}
+{'loss': 1.1659, 'learning_rate': 1.0048538961038962e-05, 'epoch': 0.86}
+{'loss': 1.3467, 'learning_rate': 1.0040909090909092e-05, 'epoch': 0.86}
+{'loss': 1.3618, 'learning_rate': 1.0033279220779221e-05, 'epoch': 0.87}
+{'loss': 1.4673, 'learning_rate': 1.0025649350649351e-05, 'epoch': 0.87}
+{'loss': 1.0896, 'learning_rate': 1.0018019480519482e-05, 'epoch': 0.87}
+{'loss': 1.4226, 'learning_rate': 1.001038961038961e-05, 'epoch': 0.87}
+{'loss': 1.1734, 'learning_rate': 1.000275974025974e-05, 'epoch': 0.87}
+{'loss': 1.2999, 'learning_rate': 9.99512987012987e-06, 'epoch': 0.87}
+{'loss': 1.301, 'learning_rate': 9.9875e-06, 'epoch': 0.88}
+{'loss': 1.1769, 'learning_rate': 9.97987012987013e-06, 'epoch': 0.88}
+{'loss': 1.1281, 'learning_rate': 9.97224025974026e-06, 'epoch': 0.88}
+{'loss': 1.1756, 'learning_rate': 9.96461038961039e-06, 'epoch': 0.88}
+{'loss': 1.2677, 'learning_rate': 9.95698051948052e-06, 'epoch': 0.88}
+{'loss': 1.3818, 'learning_rate': 9.94935064935065e-06, 'epoch': 0.88}
+{'loss': 1.2947, 'learning_rate': 9.94172077922078e-06, 'epoch': 0.88}
+{'loss': 1.1504, 'learning_rate': 9.93409090909091e-06, 'epoch': 0.89}
+{'loss': 1.3446, 'learning_rate': 9.92646103896104e-06, 'epoch': 0.89}
+{'loss': 1.2038, 'learning_rate': 9.91883116883117e-06, 'epoch': 0.89}
+{'loss': 1.2361, 'learning_rate': 9.911201298701299e-06, 'epoch': 0.89}
+{'loss': 1.1385, 'learning_rate': 9.903571428571428e-06, 'epoch': 0.89}
+{'loss': 1.2525, 'learning_rate': 9.895941558441558e-06, 'epoch': 0.89}
+{'loss': 1.19, 'learning_rate': 9.888311688311689e-06, 'epoch': 0.9}
+{'loss': 1.2646, 'learning_rate': 9.880681818181819e-06, 'epoch': 0.9}
+{'loss': 1.1396, 'learning_rate': 9.873051948051948e-06, 'epoch': 0.9}
+{'loss': 1.1275, 'learning_rate': 9.865422077922078e-06, 'epoch': 0.9}
+{'loss': 1.2581, 'learning_rate': 9.857792207792209e-06, 'epoch': 0.9}
+{'loss': 1.234, 'learning_rate': 9.850162337662338e-06, 'epoch': 0.9}
+{'loss': 1.0915, 'learning_rate': 9.842532467532468e-06, 'epoch': 0.91}
+{'loss': 1.0278, 'learning_rate': 9.834902597402599e-06, 'epoch': 0.91}
+{'loss': 1.3569, 'learning_rate': 9.827272727272729e-06, 'epoch': 0.91}
+{'loss': 1.264, 'learning_rate': 9.819642857142856e-06, 'epoch': 0.91}
+{'loss': 1.2587, 'learning_rate': 9.812012987012987e-06, 'epoch': 0.91}
+
 30%|███       | 563/1848 [3:07:06<7:07:14, 19.95s/it]
 31%|███       | 564/1848 [3:07:26<7:06:41, 19.94s/it]
                                                      

 31%|███       | 564/1848 [3:07:26<7:06:41, 19.94s/it]
 31%|███       | 565/1848 [3:07:46<7:06:38, 19.95s/it]
                                                      

 31%|███       | 565/1848 [3:07:46<7:06:38, 19.95s/it]
 31%|███       | 566/1848 [3:08:06<7:05:45, 19.93s/it]
                                                      

 31%|███       | 566/1848 [3:08:06<7:05:45, 19.93s/it]
 31%|███       | 567/1848 [3:08:26<7:06:03, 19.96s/it]
                                                      

 31%|███       | 567/1848 [3:08:26<7:06:03, 19.96s/it]
 31%|███       | 568/1848 [3:08:46<7:05:52, 19.96s/it]
                                                      

 31%|███       | 568/1848 [3:08:46<7:05:52, 19.96s/it]
 31%|███       | 569/1848 [3:09:06<7:05:43, 19.97s/it]
                                                      

 31%|███       | 569/1848 [3:09:06<7:05:43, 19.97s/it]
 31%|███       | 570/1848 [3:09:25<7:05:07, 19.96s/it]
                                                      

 31%|███       | 570/1848 [3:09:25<7:05:07, 19.96s/it]
 31%|███       | 571/1848 [3:09:45<7:04:36, 19.95s/it]
                                                      

 31%|███       | 571/1848 [3:09:45<7:04:36, 19.95s/it]
 31%|███       | 572/1848 [3:10:05<7:04:23, 19.96s/it]
                                                      

 31%|███       | 572/1848 [3:10:05<7:04:23, 19.96s/it]
 31%|███       | 573/1848 [3:10:25<7:04:10, 19.96s/it]
                                                      

 31%|███       | 573/1848 [3:10:25<7:04:10, 19.96s/it]
 31%|███       | 574/1848 [3:10:45<7:04:04, 19.97s/it]
                                                      

 31%|███       | 574/1848 [3:10:45<7:04:04, 19.97s/it]
 31%|███       | 575/1848 [3:11:05<7:02:36, 19.92s/it]
                                                      

 31%|███       | 575/1848 [3:11:05<7:02:36, 19.92s/it]
 31%|███       | 576/1848 [3:11:25<7:02:35, 19.93s/it]
                                                      

 31%|███       | 576/1848 [3:11:25<7:02:35, 19.93s/it]
 31%|███       | 577/1848 [3:11:45<7:02:26, 19.94s/it]
                                                      

 31%|███       | 577/1848 [3:11:45<7:02:26, 19.94s/it]
 31%|███▏      | 578/1848 [3:12:05<7:01:39, 19.92s/it]
                                                      

 31%|███▏      | 578/1848 [3:12:05<7:01:39, 19.92s/it]
 31%|███▏      | 579/1848 [3:12:25<7:01:55, 19.95s/it]
                                                      

 31%|███▏      | 579/1848 [3:12:25<7:01:55, 19.95s/it]
 31%|███▏      | 580/1848 [3:12:45<7:01:35, 19.95s/it]
                                                      

 31%|███▏      | 580/1848 [3:12:45<7:01:35, 19.95s/it]
 31%|███▏      | 581/1848 [3:13:05<7:01:43, 19.97s/it]
                                                      

 31%|███▏      | 581/1848 [3:13:05<7:01:43, 19.97s/it]
 31%|███▏      | 582/1848 [3:13:25<7:01:09, 19.96s/it]
                                                      

 31%|███▏      | 582/1848 [3:13:25<7:01:09, 19.96s/it]
 32%|███▏      | 583/1848 [3:13:45<7:00:58, 19.97s/it]
                                                      

 32%|███▏      | 583/1848 [3:13:45<7:00:58, 19.97s/it]
 32%|███▏      | 584/1848 [3:14:05<7:00:56, 19.98s/it]
                                                      

 32%|███▏      | 584/1848 [3:14:05<7:00:56, 19.98s/it]
 32%|███▏      | 585/1848 [3:14:25<7:00:36, 19.98s/it]
                                                      

 32%|███▏      | 585/1848 [3:14:25<7:00:36, 19.98s/it]
 32%|███▏      | 586/1848 [3:14:45<6:59:25, 19.94s/it]
                                                      

 32%|███▏      | 586/1848 [3:14:45<6:59:25, 19.94s/it]
 32%|███▏      | 587/1848 [3:15:05<6:58:58, 19.94s/it]
                                                      

 32%|███▏      | 587/1848 [3:15:05<6:58:58, 19.94s/it]
 32%|███▏      | 588/1848 [3:15:25<6:58:43, 19.94s/it]
                                                      

 32%|███▏      | 588/1848 [3:15:25<6:58:43, 19.94s/it]
 32%|███▏      | 589/1848 [3:15:44<6:58:24, 19.94s/it]
                                                      

 32%|███▏      | 589/1848 [3:15:44<6:58:24, 19.94s/it]
 32%|███▏      | 590/1848 [3:16:04<6:58:37, 19.97s/it]
                                                      

 32%|███▏      | 590/1848 [3:16:04<6:58:37, 19.97s/it]
 32%|███▏      | 591/1848 [3:16:24<6:58:15, 19.96s/it]
                                                      

 32%|███▏      | 591/1848 [3:16:24<6:58:15, 19.96s/it]
 32%|███▏      | 592/1848 [3:16:44<6:58:02, 19.97s/it]
                                                      

 32%|███▏      | 592/1848 [3:16:44<6:58:02, 19.97s/it]
 32%|███▏      | 593/1848 [3:17:04<6:57:31, 19.96s/it]
                                                      

 32%|███▏      | 593/1848 [3:17:04<6:57:31, 19.96s/it]
 32%|███▏      | 594/1848 [3:17:24<6:57:10, 19.96s/it]
                                                      

 32%|███▏      | 594/1848 [3:17:24<6:57:10, 19.96s/it]
 32%|███▏      | 595/1848 [3:17:44<6:57:05, 19.97s/it]
                                                      

 32%|███▏      | 595/1848 [3:17:44<6:57:05, 19.97s/it]
 32%|███▏      | 596/1848 [3:18:04<6:56:46, 19.97s/it]
                                                      

 32%|███▏      | 596/1848 [3:18:04<6:56:46, 19.97s/it]
 32%|███▏      | 597/1848 [3:18:24<6:55:41, 19.94s/it]
                                                      

 32%|███▏      | 597/1848 [3:18:24<6:55:41, 19.94s/it]
 32%|███▏      | 598/1848 [3:18:44<6:55:37, 19.95s/it]
                                                      

 32%|███▏      | 598/1848 [3:18:44<6:55:37, 19.95s/it]
 32%|███▏      | 599/1848 [3:19:04<6:55:34, 19.96s/it]
                                                      

 32%|███▏      | 599/1848 [3:19:04<6:55:34, 19.96s/it]
 32%|███▏      | 600/1848 [3:19:24<6:54:55, 19.95s/it]
                                                      

 32%|███▏      | 600/1848 [3:19:24<6:54:55, 19.95s/it]
 33%|███▎      | 601/1848 [3:19:45<7:00:01, 20.21s/it]
                                                      

 33%|███▎      | 601/1848 [3:19:45<7:00:01, 20.21s/it]
 33%|███▎      | 602/1848 [3:20:05<6:57:40, 20.11s/it]
                                                      

 33%|███▎      | 602/1848 [3:20:05<6:57:40, 20.11s/it]
 33%|███▎      | 603/1848 [3:20:25<6:56:05, 20.05s/it]
                                                      

 33%|███▎      | 603/1848 [3:20:25<6:56:05, 20.05s/it]
 33%|███▎      | 604/1848 [3:20:45<6:55:11, 20.02s/it]
                                                      

 33%|███▎      | 604/1848 [3:20:45<6:55:11, 20.02s/it]
 33%|███▎      | 605/1848 [3:21:05<6:54:42, 20.02s/it]
                                                      

 33%|███▎      | 605/1848 [3:21:05<6:54:42, 20.02s/it]
 33%|███▎      | 606/1848 [3:21:25<6:54:09, 20.01s/it]
                                                      

 33%|███▎      | 606/1848 [3:21:25<6:54:09, 20.01s/it]
 33%|███▎      | 607/1848 [3:21:45<6:53:30, 19.99s/it]
                                                      

 33%|███▎      | 607/1848 [3:21:45<6:53:30, 19.99s/it]
 33%|███▎      | 608/1848 [3:22:04<6:52:21, 19.95s/it]
                                                      

 33%|███▎      | 608/1848 [3:22:04<6:52:21, 19.95s/it]
 33%|███▎      | 609/1848 [3:22:24<6:51:52, 19.95s/it]
                                                      

 33%|███▎      | 609/1848 [3:22:24<6:51:52, 19.95s/it]
 33%|███▎      | 610/1848 [3:22:44<6:51:40, 19.95s/it]
                                                      

 33%|███▎      | 610/1848 [3:22:44<6:51:40, 19.95s/it]
 33%|███▎      | 611/1848 [3:23:04<6:51:43, 19.97s/it]
                                                      

 33%|███▎      | 611/1848 [3:23:04<6:51:43, 19.97s/it]
 33%|███▎      | 612/1848 [3:23:24<6:51:15, 19.96s/it]
                                                      

 33%|███▎      | 612/1848 [3:23:24<6:51:15, 19.96s/it]
 33%|███▎      | 613/1848 [3:23:44<6:51:13, 19.98s/it]
                                                      

 33%|███▎      | 613/1848 [3:23:44<6:51:13, 19.98s/it]
 33%|███▎      | 614/1848 [3:24:04<6:50:37, 19.97s/it]
                                                      

 33%|███▎      | 614/1848 [3:24:04<6:50:37, 19.97s/it]
 33%|██��▎      | 615/1848 [3:24:24<6:49:48, 19.94s/it]
                                                      

 33%|███▎      | 615/1848 [3:24:24<6:49:48, 19.94s/it]
 33%|███▎      | 616/1848 [3:24:32<5:34:48, 16.31s/it]
                                                      

 33%|███▎      | 616/1848 [3:24:32<5:34:48, 16.31s/it]
 33%|███▎      | 617/1848 [3:24:52<5:57:09, 17.41s/it]
                                                      

 33%|███▎      | 617/1848 [3:24:52<5:57:09, 17.41s/it]
 33%|███▎      | 618/1848 [3:25:12<6:12:41, 18.18s/it]
                                                      

 33%|███▎      | 618/1848 [3:25:12<6:12:41, 18.18s/it]
 33%|███▎      | 619/1848 [3:25:32<6:22:59, 18.70s/it]
                                                      

 33%|███▎      | 619/1848 [3:25:32<6:22:59, 18.70s/it]
 34%|███▎      | 620/1848 [3:25:52<6:30:06, 19.06s/it]
                                                      

 34%|███▎      | 620/1848 [3:25:52<6:30:06, 19.06s/it]
 34%|███▎      | 621/1848 [3:26:12<6:35:13, 19.33s/it]
                                                      

 34%|███▎      | 621/1848 [3:26:12<6:35:13, 19.33s/it]
 34%|███▎      | 622/1848 [3:26:32<6:39:07, 19.53s/it]
                                                      

 34%|███▎      | 622/1848 [3:26:32<6:39:07, 19.53s/it]
 34%|███▎      | 623/1848 [3:26:52<6:41:24, 19.66s/it]
                                                      

 34%|███▎      | 623/1848 [3:26:52<6:41:24, 19.66s/it]
 34%|███▍      | 624/1848 [3:27:12<6:42:18, 19.72s/it]
                                                      

 34%|███▍      | 624/1848 [3:27:12<6:42:18, 19.72s/it]
 34%|███▍      | 625/1848 [3:27:31<6:43:30, 19.80s/it]
                                                      

 34%|███▍      | 625/1848 [3:27:31<6:43:30, 19.80s/it]
 34%|███▍      | 626/1848 [3:27:51<6:44:14, 19.85s/it]
                                                      

 34%|███▍      | 626/1848 [3:27:51<6:44:14, 19.85s/it]
 34%|███▍      | 627/1848 [3:28:11<6:44:47, 19.89s/it]
                                                      

 34%|███▍      | 627/1848 [3:28:11<6:44:47, 19.89s/it]
 34%|███▍      | 628/1848 [3:28:31<6:45:22, 19.94s/it]
                                                      

 34%|███▍      | 628/1848 [3:28:31<6:45:22, 19.94s/it]
 34%|███▍      | 629/1848 [3:28:51<6:45:29, 19.96s/it]
                                                      

 34%|███▍      | 629/1848 [3:28:51<6:45:29, 19.96s/it]
 34%|███▍      | 630/1848 [3:29:11<6:45:17, 19.96s/it]
                                                      

 34%|███▍      | 630/1848 [3:29:11<6:45:17, 19.96s/it]
 34%|███▍      | 631/1848 [3:29:31<6:44:46, 19.96s/it]
                                                      

 34%|███▍      | 631/1848 [3:29:31<6:44:46, 19.96s/it]
 34%|███▍      | 632/1848 [3:29:51<6:44:44, 19.97s/it]
                                                      

 34%|███▍      | 632/1848 [3:29:51<6:44:44, 19.97s/it]
 34%|███▍      | 633/1848 [3:30:11<6:44:10, 19.96s/it]
                                                      

 34%|███▍      | 633/1848 [3:30:11<6:44:10, 19.96s/it]
 34%|███▍      | 634/1848 [3:30:31<6:43:30, 19.94s/it]
                                                      

 34%|███▍      | 634/1848 [3:30:31<6:43:30, 19.94s/it]
 34%|███▍      | 635/1848 [3:30:51<6:43:07, 19.94s/it]
                                                      

 34%|███▍      | 635/1848 [3:30:51<6:43:07, 19.94s/it]
 34%|███▍      | 636/1848 [3:31:11<6:42:58, 19.95s/it]
                                                      

 34%|███▍      | 636/1848 [3:31:11<6:42:58, 19.95s/it]
 34%|███▍      | 637/1848 [3:31:31<6:42:34, 19.95s/it]
                                                      

 34%|███▍      | 637/1848 [3:31:31<6:42:34, 19.95s/it]
 35%|███▍      | 638/1848 [3:31:51<6:42:36, 19.96s/it]
                                                      

 35%|███▍      | 638/1848 [3:31:51<6:42:36, 19.96s/it]
 35%|███▍      | 639/1848 [3:32:11<6:42:10, 19.96s/it]
                                                      

 35%|███▍      | 639/1848 [3:32:11<6:42:10, 19.96s/it]
 35%|███▍      | 640/1848 [3:32:31<6:41:33, 19.94s/it]
                                                      

 35%|███▍      | 640/1848 [3:32:31<6:41:33, 19.94s/it]
 35%|███▍      | 641/1848 [3:32:51<6:41:13, 19.95s/it]
                                                      

 35%|███▍      | 641/1848 [3:32:51<6:41:13, 19.95s/it]
 35%|███▍      | 642/1848 [3:33:11<6:40:43, 19.94s/it]
                                                      

 35%|███▍      | 642/1848 [3:33:11<6:40:43, 19.94s/it]
 35%|███▍      | 643/1848 [3:33:31<6:40:40, 19.95s/it]
                                                      

 35%|███▍      | 643/1848 [3:33:31<6:40:40, 19.95s/it]
 35%|███▍      | 644/1848 [3:33:51<6:39:56, 19.93s/it]
                                                      

 35%|███▍      | 644/1848 [3:33:51<6:39:56, 19.93s/it]
 35%|███▍      | 645/1848 [3:34:11<6:39:52, 19.94s/it]
                                                      

 35%|███▍      | 645/1848 [3:34:11<6:39:52, 19.94s/it]
 35%|███▍      | 646/1848 [3:34:31<6:39:43, 19.95s/it]
                                                      

 35%|███▍      | 646/1848 [3:34:31<6:39:43, 19.95s/it]
 35%|███▌      | 647/1848 [3:34:51<6:39:11, 19.94s/it]
                                                      

 35%|███▌      | 647/1848 [3:34:51<6:39:11, 19.94s/it]
 35%|███▌      | 648/1848 [3:35:10<6:38:49, 19.94s/it]
                                                      

 35%|███▌      | 648/1848 [3:35:10<6:38:49, 19.94s/it]
 35%|███▌      | 649/1848 [3:35:30<6:38:29, 19.94s/it]
                                                      

 35%|███▌      | 649/1848 [3:35:30<6:38:29, 19.94s/it]
 35%|███▌      | 650/1848 [3:35:50<6:38:07, 19.94s/it]
                                                      

 35%|███▌      | 650/1848 [3:35:50<6:38:07, 19.94s/it]
 35%|███▌      | 651/1848 [3:36:10<6:38:08, 19.96s/it]
                                                      

 35%|███▌      | 651/1848 [3:36:10<6:38:08, 19.96s/it]
 35%|███▌      | 652/1848 [3:36:30<6:37:52, 19.96s/it]
                                                      

 35%|███▌      | 652/1848 [3:36:30<6:37:52, 19.96s/it]
 35%|███▌      | 653/1848 [3:36:50<6:37:31, 19.96s/it]
                                                      

 35%|███▌      | 653/1848 [3:36:50<6:37:31, 19.96s/it]
 35%|███▌      | 654/1848 [3:37:10<6:37:03, 19.95s/it]
                                                      

 35%|███▌      | 654/1848 [3:37:10<6:37:03, 19.95s/it]
 35%|███▌      | 655/1848 [3:37:30<6:36:58, 19.97s/it]
                                                      

 35%|███▌      | 655/1848 [3:37:30<6:36:58, 19.97s/it]
 35%|███▌      | 656/1848 [3:37:50<6:36:35, 19.96s/it]
                                                      

 35%|███▌      | 656/1848 [3:37:50<6:36:35, 19.96s/it]
 36%|███▌      | 657/1848 [3:38:10<6:36:27, 19.97s/it]
                                                      

 36%|███▌      | 657/1848 [3:38:10<6:36:27, 19.97s/it]
 36%|███▌      | 658/1848 [3:38:30<6:35:50, 19.96s/it]
                                                      

 36%|███▌      | 658/1848 [3:38:30<6:35:50, 19.96s/it]
 36%|███▌      | 659/1848 [3:38:50<6:35:57, 19.98s/it]
                                                      

 36%|███▌      | 659/1848 [3:38:50<6:35:57, 19.98s/it]
 36%|███▌      | 660/1848 [3:39:10<6:35:03, 19.95s/it]
                                                      

 36%|███▌      | 660/1848 [3:39:10<6:35:03, 19.95s/it]
 36%|███▌      | 661/1848 [3:39:30<6:34:45, 19.95s/it]
                                                      

 36%|███▌      | 661/1848 [3:39:30<6:34:45, 19.95s/it]
 36%|███▌      | 662/1848 [3:39:50<6:34:08, 19.94s/it]
                                                      

 36%|███▌      | 662/1848 [3:39:50<6:34:08, 19.94s/it]
 36%|███▌      | 663/1848 [3:40:10<6:33:53, 19.94s/it]
                                                      

 36%|███▌      | 663/1848 [3:40:10<6:33:53, 19.94s/it]
 36%|███▌      | 664/1848 [3:40:30<6:33:43, 19.95s/it]
                                                      

 36%|███▌      | 664/1848 [3:40:30<6:33:43, 19.95s/it]
 36%|███▌      | 665/1848 [3:40:50<6:33:07, 19.94s/it]
                                                      

 36%|███▌      | 665/1848 [3:40:50<6:33:07, 19.94s/it]
 36%|███▌      | 666/1848 [3:41:10<6:33:07, 19.96s/it]
                                                      

 36%|███▌      | 666/1848 [3:41:10<6:33:07, 19.96s/it]
 36%|███▌      | 667/1848 [3:41:30<6:32:30, 19.94s/it]
                                                      

 36%|███▌      | 667/1848 [3:41:30<6:32:30, 19.94s/it]
 36%|███▌      | 668/1848 [3:41:50<6:32:10, 19.94s/it]
                                                      

 36%|███▌      | 668/1848 [3:41:50<6:32:10, 19.94s/it]
 36%|███▌      | 669/1848 [3:42:10<6:31:56, 19.95s/it]
                                                      

 36%|███▌      | 669/1848 [3:42:10<6:31:56, 19.95s/it]
 36%|███▋      | 670/1848 [3:42:29<6:31:27, 19.94s/it]
                                                      

 36%|███▋      | 670/1848 [3:42:29<6:31:27, 19.94s/it]
 36%|███▋      | 671/1848 [3:42:49<6:30:52, 19.93s/it]
                                                      

 36%|███▋      | 671/1848 [3:42:49<6:30:52, 19.93s/it]
 36%|███▋      | 672/1848 [3:43:09<6:30:15, 19.91s/it]
                                                      

 36%|███▋      | 672/1848 [3:43:09<6:30:15, 19.91s/it]
 36%|███▋      | 673/1848 [3:43:29<6:30:07, 19.92s/it]
                                                      

 36%|███▋      | 673/1848 [3:43:29<6:30:07, 19.92s/it]
 36%|███▋      | 674/1848 [3:43:49<6:29:37, 19.91s/it]
                                                      

 36%|███▋      | 674/1848 [3:43:49<6:29:37, 19.91s/it]
 37%|███▋      | 675/1848 [3:44:09<6:29:15, 19.91s/it]
                                                      

 37%|███▋      | 675/1848 [3:44:09<6:29:15, 19.91s/it]
 37%|███▋      | 676/1848 [3:44:29<6:29:15, 19.93s/it]
                                                      

 37%|███▋      | 676/1848 [3:44:29<6:29:15, 19.93s/it]
 37%|███▋      | 677/1848 [3:44:49<6:29:20, 19.95s/it]
                                                      
{'loss': 1.1561, 'learning_rate': 9.804383116883117e-06, 'epoch': 0.91}
+{'loss': 1.2159, 'learning_rate': 9.796753246753246e-06, 'epoch': 0.92}
+{'loss': 1.4736, 'learning_rate': 9.789123376623377e-06, 'epoch': 0.92}
+{'loss': 1.2511, 'learning_rate': 9.781493506493507e-06, 'epoch': 0.92}
+{'loss': 1.2838, 'learning_rate': 9.773863636363638e-06, 'epoch': 0.92}
+{'loss': 1.2276, 'learning_rate': 9.766233766233766e-06, 'epoch': 0.92}
+{'loss': 1.2341, 'learning_rate': 9.758603896103897e-06, 'epoch': 0.92}
+{'loss': 1.1915, 'learning_rate': 9.750974025974027e-06, 'epoch': 0.93}
+{'loss': 1.1791, 'learning_rate': 9.743344155844156e-06, 'epoch': 0.93}
+{'loss': 1.1864, 'learning_rate': 9.735714285714287e-06, 'epoch': 0.93}
+{'loss': 0.9571, 'learning_rate': 9.728084415584415e-06, 'epoch': 0.93}
+{'loss': 1.3418, 'learning_rate': 9.720454545454546e-06, 'epoch': 0.93}
+{'loss': 1.3262, 'learning_rate': 9.712824675324675e-06, 'epoch': 0.93}
+{'loss': 1.0959, 'learning_rate': 9.705194805194805e-06, 'epoch': 0.94}
+{'loss': 1.4531, 'learning_rate': 9.697564935064936e-06, 'epoch': 0.94}
+{'loss': 1.2073, 'learning_rate': 9.689935064935065e-06, 'epoch': 0.94}
+{'loss': 1.2904, 'learning_rate': 9.682305194805195e-06, 'epoch': 0.94}
+{'loss': 1.1753, 'learning_rate': 9.674675324675326e-06, 'epoch': 0.94}
+{'loss': 1.2653, 'learning_rate': 9.667045454545454e-06, 'epoch': 0.94}
+{'loss': 1.1623, 'learning_rate': 9.659415584415585e-06, 'epoch': 0.94}
+{'loss': 1.1059, 'learning_rate': 9.651785714285715e-06, 'epoch': 0.95}
+{'loss': 1.1666, 'learning_rate': 9.644155844155846e-06, 'epoch': 0.95}
+{'loss': 1.2168, 'learning_rate': 9.636525974025975e-06, 'epoch': 0.95}
+{'loss': 1.4224, 'learning_rate': 9.628896103896103e-06, 'epoch': 0.95}
+{'loss': 1.129, 'learning_rate': 9.621266233766234e-06, 'epoch': 0.95}
+{'loss': 1.0755, 'learning_rate': 9.613636363636363e-06, 'epoch': 0.95}
+{'loss': 1.1345, 'learning_rate': 9.606006493506493e-06, 'epoch': 0.96}
+{'loss': 1.303, 'learning_rate': 9.598376623376624e-06, 'epoch': 0.96}
+{'loss': 1.2, 'learning_rate': 9.590746753246754e-06, 'epoch': 0.96}
+{'loss': 1.2235, 'learning_rate': 9.583116883116883e-06, 'epoch': 0.96}
+{'loss': 1.384, 'learning_rate': 9.575487012987014e-06, 'epoch': 0.96}
+{'loss': 1.3019, 'learning_rate': 9.567857142857144e-06, 'epoch': 0.96}
+{'loss': 1.2273, 'learning_rate': 9.560227272727273e-06, 'epoch': 0.97}
+{'loss': 1.0863, 'learning_rate': 9.552597402597403e-06, 'epoch': 0.97}
+{'loss': 1.6304, 'learning_rate': 9.544967532467534e-06, 'epoch': 0.97}
+{'loss': 1.2321, 'learning_rate': 9.537337662337663e-06, 'epoch': 0.97}
+{'loss': 1.1845, 'learning_rate': 9.529707792207791e-06, 'epoch': 0.97}
+{'loss': 1.2188, 'learning_rate': 9.522077922077922e-06, 'epoch': 0.97}
+{'loss': 1.1631, 'learning_rate': 9.514448051948052e-06, 'epoch': 0.98}
+{'loss': 1.3793, 'learning_rate': 9.506818181818181e-06, 'epoch': 0.98}
+{'loss': 0.9781, 'learning_rate': 9.499188311688312e-06, 'epoch': 0.98}
+{'loss': 1.2006, 'learning_rate': 9.491558441558442e-06, 'epoch': 0.98}
+{'loss': 1.2602, 'learning_rate': 9.483928571428573e-06, 'epoch': 0.98}
+{'loss': 1.2249, 'learning_rate': 9.476298701298702e-06, 'epoch': 0.98}
+{'loss': 1.2246, 'learning_rate': 9.468668831168832e-06, 'epoch': 0.99}
+{'loss': 1.1202, 'learning_rate': 9.461038961038963e-06, 'epoch': 0.99}
+{'loss': 1.0401, 'learning_rate': 9.453409090909091e-06, 'epoch': 0.99}
+{'loss': 1.2793, 'learning_rate': 9.44577922077922e-06, 'epoch': 0.99}
+{'loss': 1.208, 'learning_rate': 9.43814935064935e-06, 'epoch': 0.99}
+{'loss': 1.1169, 'learning_rate': 9.43051948051948e-06, 'epoch': 0.99}
+{'loss': 1.3247, 'learning_rate': 9.42288961038961e-06, 'epoch': 1.0}
+{'loss': 1.1051, 'learning_rate': 9.41525974025974e-06, 'epoch': 1.0}
+{'loss': 1.4497, 'learning_rate': 9.407629870129871e-06, 'epoch': 1.0}
+{'loss': 1.4602, 'learning_rate': 9.4e-06, 'epoch': 1.0}
+{'loss': 1.2572, 'learning_rate': 9.39237012987013e-06, 'epoch': 1.0}
+{'loss': 1.2605, 'learning_rate': 9.38474025974026e-06, 'epoch': 1.0}
+{'loss': 1.4325, 'learning_rate': 9.37711038961039e-06, 'epoch': 1.0}
+{'loss': 1.3855, 'learning_rate': 9.36948051948052e-06, 'epoch': 1.01}
+{'loss': 1.2837, 'learning_rate': 9.36185064935065e-06, 'epoch': 1.01}
+{'loss': 1.2559, 'learning_rate': 9.35422077922078e-06, 'epoch': 1.01}
+{'loss': 1.2488, 'learning_rate': 9.346590909090908e-06, 'epoch': 1.01}
+{'loss': 1.4314, 'learning_rate': 9.338961038961039e-06, 'epoch': 1.01}
+{'loss': 1.1367, 'learning_rate': 9.33133116883117e-06, 'epoch': 1.01}
+{'loss': 1.3465, 'learning_rate': 9.323701298701298e-06, 'epoch': 1.02}
+{'loss': 1.0297, 'learning_rate': 9.316071428571428e-06, 'epoch': 1.02}
+{'loss': 1.3392, 'learning_rate': 9.308441558441559e-06, 'epoch': 1.02}
+{'loss': 1.2574, 'learning_rate': 9.30081168831169e-06, 'epoch': 1.02}
+{'loss': 1.2196, 'learning_rate': 9.293181818181818e-06, 'epoch': 1.02}
+{'loss': 1.3139, 'learning_rate': 9.285551948051949e-06, 'epoch': 1.02}
+{'loss': 1.4133, 'learning_rate': 9.27792207792208e-06, 'epoch': 1.03}
+{'loss': 1.2295, 'learning_rate': 9.270292207792208e-06, 'epoch': 1.03}
+{'loss': 1.3582, 'learning_rate': 9.262662337662339e-06, 'epoch': 1.03}
+{'loss': 1.2966, 'learning_rate': 9.255032467532467e-06, 'epoch': 1.03}
+{'loss': 1.2079, 'learning_rate': 9.247402597402598e-06, 'epoch': 1.03}
+{'loss': 1.1841, 'learning_rate': 9.239772727272727e-06, 'epoch': 1.03}
+{'loss': 1.1589, 'learning_rate': 9.232142857142857e-06, 'epoch': 1.04}
+{'loss': 1.1105, 'learning_rate': 9.224512987012988e-06, 'epoch': 1.04}
+{'loss': 1.2667, 'learning_rate': 9.216883116883117e-06, 'epoch': 1.04}
+{'loss': 1.1804, 'learning_rate': 9.209253246753247e-06, 'epoch': 1.04}
+{'loss': 1.0709, 'learning_rate': 9.201623376623378e-06, 'epoch': 1.04}
+{'loss': 1.2082, 'learning_rate': 9.193993506493508e-06, 'epoch': 1.04}
+{'loss': 1.3435, 'learning_rate': 9.186363636363637e-06, 'epoch': 1.05}
+{'loss': 1.4123, 'learning_rate': 9.178733766233767e-06, 'epoch': 1.05}
+{'loss': 1.0904, 'learning_rate': 9.171103896103898e-06, 'epoch': 1.05}
+{'loss': 1.1442, 'learning_rate': 9.163474025974027e-06, 'epoch': 1.05}
+{'loss': 1.4938, 'learning_rate': 9.155844155844155e-06, 'epoch': 1.05}
+{'loss': 1.2161, 'learning_rate': 9.148214285714286e-06, 'epoch': 1.05}
+{'loss': 1.184, 'learning_rate': 9.140584415584415e-06, 'epoch': 1.06}
+{'loss': 1.1835, 'learning_rate': 9.132954545454545e-06, 'epoch': 1.06}
+{'loss': 1.2054, 'learning_rate': 9.125324675324676e-06, 'epoch': 1.06}
+{'loss': 1.2623, 'learning_rate': 9.117694805194806e-06, 'epoch': 1.06}
+{'loss': 1.2513, 'learning_rate': 9.110064935064935e-06, 'epoch': 1.06}
+{'loss': 1.1491, 'learning_rate': 9.102435064935066e-06, 'epoch': 1.06}
+{'loss': 1.0773, 'learning_rate': 9.094805194805196e-06, 'epoch': 1.06}
+{'loss': 1.3106, 'learning_rate': 9.087175324675325e-06, 'epoch': 1.07}
+{'loss': 1.3625, 'learning_rate': 9.079545454545455e-06, 'epoch': 1.07}
+{'loss': 1.0741, 'learning_rate': 9.071915584415584e-06, 'epoch': 1.07}
+{'loss': 1.3016, 'learning_rate': 9.064285714285715e-06, 'epoch': 1.07}
+{'loss': 1.2527, 'learning_rate': 9.056655844155843e-06, 'epoch': 1.07}
+{'loss': 1.154, 'learning_rate': 9.049025974025974e-06, 'epoch': 1.07}
+{'loss': 1.4876, 'learning_rate': 9.041396103896104e-06, 'epoch': 1.08}
+{'loss': 1.3429, 'learning_rate': 9.033766233766233e-06, 'epoch': 1.08}
+{'loss': 1.363, 'learning_rate': 9.026136363636364e-06, 'epoch': 1.08}
+{'loss': 1.2967, 'learning_rate': 9.018506493506494e-06, 'epoch': 1.08}
+{'loss': 1.1399, 'learning_rate': 9.010876623376625e-06, 'epoch': 1.08}
+{'loss': 1.1999, 'learning_rate': 9.003246753246754e-06, 'epoch': 1.08}
+{'loss': 1.1704, 'learning_rate': 8.995616883116884e-06, 'epoch': 1.09}
+{'loss': 1.0627, 'learning_rate': 8.987987012987015e-06, 'epoch': 1.09}
+{'loss': 1.4747, 'learning_rate': 8.980357142857143e-06, 'epoch': 1.09}
+{'loss': 1.3067, 'learning_rate': 8.972727272727272e-06, 'epoch': 1.09}
+{'loss': 1.3222, 'learning_rate': 8.965097402597403e-06, 'epoch': 1.09}
+{'loss': 1.4672, 'learning_rate': 8.957467532467533e-06, 'epoch': 1.09}
+{'loss': 1.2164, 'learning_rate': 8.949837662337662e-06, 'epoch': 1.1}
+{'loss': 1.1363, 'learning_rate': 8.942207792207792e-06, 'epoch': 1.1}
+
 37%|███▋      | 677/1848 [3:44:49<6:29:20, 19.95s/it]
 37%|███▋      | 678/1848 [3:45:09<6:29:19, 19.97s/it]
                                                      

 37%|███▋      | 678/1848 [3:45:09<6:29:19, 19.97s/it]
 37%|███▋      | 679/1848 [3:45:29<6:28:54, 19.96s/it]
                                                      

 37%|███▋      | 679/1848 [3:45:29<6:28:54, 19.96s/it]
 37%|███▋      | 680/1848 [3:45:49<6:28:49, 19.97s/it]
                                                      

 37%|███▋      | 680/1848 [3:45:49<6:28:49, 19.97s/it]
 37%|███▋      | 681/1848 [3:46:09<6:27:56, 19.95s/it]
                                                      

 37%|███▋      | 681/1848 [3:46:09<6:27:56, 19.95s/it]
 37%|███▋      | 682/1848 [3:46:29<6:27:31, 19.94s/it]
                                                      

 37%|███▋      | 682/1848 [3:46:29<6:27:31, 19.94s/it]
 37%|███▋      | 683/1848 [3:46:49<6:27:10, 19.94s/it]
                                                      

 37%|███▋      | 683/1848 [3:46:49<6:27:10, 19.94s/it]
 37%|███▋      | 684/1848 [3:47:09<6:26:37, 19.93s/it]
                                                      

 37%|███▋      | 684/1848 [3:47:09<6:26:37, 19.93s/it]
 37%|███▋      | 685/1848 [3:47:28<6:26:27, 19.94s/it]
                                                      

 37%|███▋      | 685/1848 [3:47:28<6:26:27, 19.94s/it]
 37%|███▋      | 686/1848 [3:47:48<6:25:56, 19.93s/it]
                                                      

 37%|███▋      | 686/1848 [3:47:48<6:25:56, 19.93s/it]
 37%|███▋      | 687/1848 [3:48:08<6:25:43, 19.93s/it]
                                                      

 37%|███▋      | 687/1848 [3:48:08<6:25:43, 19.93s/it]
 37%|███▋      | 688/1848 [3:48:28<6:25:37, 19.95s/it]
                                                      

 37%|███▋      | 688/1848 [3:48:28<6:25:37, 19.95s/it]
 37%|███▋      | 689/1848 [3:48:48<6:25:05, 19.94s/it]
                                                      

 37%|███▋      | 689/1848 [3:48:48<6:25:05, 19.94s/it]
 37%|███▋      | 690/1848 [3:49:08<6:25:06, 19.95s/it]
                                                      

 37%|███▋      | 690/1848 [3:49:08<6:25:06, 19.95s/it]
 37%|███▋      | 691/1848 [3:49:28<6:24:30, 19.94s/it]
                                                      

 37%|███▋      | 691/1848 [3:49:28<6:24:30, 19.94s/it]
 37%|███▋      | 692/1848 [3:49:48<6:24:12, 19.94s/it]
                                                      

 37%|███▋      | 692/1848 [3:49:48<6:24:12, 19.94s/it]
 38%|███▊      | 693/1848 [3:50:08<6:23:56, 19.95s/it]
                                                      

 38%|███▊      | 693/1848 [3:50:08<6:23:56, 19.95s/it]
 38%|███▊      | 694/1848 [3:50:28<6:23:55, 19.96s/it]
                                                      

 38%|███▊      | 694/1848 [3:50:28<6:23:55, 19.96s/it]
 38%|███▊      | 695/1848 [3:50:48<6:23:40, 19.97s/it]
                                                      

 38%|███▊      | 695/1848 [3:50:48<6:23:40, 19.97s/it]
 38%|███▊      | 696/1848 [3:51:08<6:22:50, 19.94s/it]
                                                      

 38%|███▊      | 696/1848 [3:51:08<6:22:50, 19.94s/it]
 38%|███▊      | 697/1848 [3:51:28<6:22:31, 19.94s/it]
                                                      

 38%|███▊      | 697/1848 [3:51:28<6:22:31, 19.94s/it]
 38%|███▊      | 698/1848 [3:51:48<6:22:04, 19.93s/it]
                                                      

 38%|███▊      | 698/1848 [3:51:48<6:22:04, 19.93s/it]
 38%|███▊      | 699/1848 [3:52:08<6:21:48, 19.94s/it]
                                                      

 38%|███▊      | 699/1848 [3:52:08<6:21:48, 19.94s/it]
 38%|███▊      | 700/1848 [3:52:28<6:21:07, 19.92s/it]
                                                      

 38%|███▊      | 700/1848 [3:52:28<6:21:07, 19.92s/it]
 38%|███▊      | 701/1848 [3:52:48<6:25:22, 20.16s/it]
                                                      

 38%|███▊      | 701/1848 [3:52:48<6:25:22, 20.16s/it]
 38%|███▊      | 702/1848 [3:53:08<6:23:45, 20.09s/it]
                                                      

 38%|███▊      | 702/1848 [3:53:08<6:23:45, 20.09s/it]
 38%|███▊      | 703/1848 [3:53:28<6:22:22, 20.04s/it]
                                                      

 38%|███▊      | 703/1848 [3:53:28<6:22:22, 20.04s/it]
 38%|███▊      | 704/1848 [3:53:48<6:21:30, 20.01s/it]
                                                      

 38%|███▊      | 704/1848 [3:53:48<6:21:30, 20.01s/it]
 38%|███▊      | 705/1848 [3:54:08<6:20:35, 19.98s/it]
                                                      

 38%|███▊      | 705/1848 [3:54:08<6:20:35, 19.98s/it]
 38%|███▊      | 706/1848 [3:54:28<6:20:13, 19.98s/it]
                                                      

 38%|███▊      | 706/1848 [3:54:28<6:20:13, 19.98s/it]
 38%|███▊      | 707/1848 [3:54:48<6:19:33, 19.96s/it]
                                                      

 38%|███▊      | 707/1848 [3:54:48<6:19:33, 19.96s/it]
 38%|███▊      | 708/1848 [3:55:08<6:19:09, 19.96s/it]
                                                      

 38%|███▊      | 708/1848 [3:55:08<6:19:09, 19.96s/it]
 38%|███▊      | 709/1848 [3:55:28<6:18:43, 19.95s/it]
                                                      

 38%|███▊      | 709/1848 [3:55:28<6:18:43, 19.95s/it]
 38%|███▊      | 710/1848 [3:55:48<6:17:53, 19.92s/it]
                                                      

 38%|███▊      | 710/1848 [3:55:48<6:17:53, 19.92s/it]
 38%|███▊      | 711/1848 [3:56:08<6:17:59, 19.95s/it]
                                                      

 38%|███▊      | 711/1848 [3:56:08<6:17:59, 19.95s/it]
 39%|███▊      | 712/1848 [3:56:28<6:17:26, 19.93s/it]
                                                      

 39%|███▊      | 712/1848 [3:56:28<6:17:26, 19.93s/it]
 39%|███▊      | 713/1848 [3:56:47<6:17:03, 19.93s/it]
                                                      

 39%|███▊      | 713/1848 [3:56:47<6:17:03, 19.93s/it]
 39%|███▊      | 714/1848 [3:57:07<6:16:40, 19.93s/it]
                                                      

 39%|███▊      | 714/1848 [3:57:07<6:16:40, 19.93s/it]
 39%|███▊      | 715/1848 [3:57:27<6:16:52, 19.96s/it]
                                                      

 39%|███▊      | 715/1848 [3:57:27<6:16:52, 19.96s/it]
 39%|███▊      | 716/1848 [3:57:47<6:16:17, 19.94s/it]
                                                      

 39%|███▊      | 716/1848 [3:57:47<6:16:17, 19.94s/it]
 39%|███▉      | 717/1848 [3:58:07<6:16:26, 19.97s/it]
                                                      

 39%|███▉      | 717/1848 [3:58:07<6:16:26, 19.97s/it]
 39%|███▉      | 718/1848 [3:58:27<6:16:01, 19.97s/it]
                                                      

 39%|███▉      | 718/1848 [3:58:27<6:16:01, 19.97s/it]
 39%|███▉      | 719/1848 [3:58:47<6:15:55, 19.98s/it]
                                                      

 39%|███▉      | 719/1848 [3:58:47<6:15:55, 19.98s/it]
 39%|███▉      | 720/1848 [3:59:07<6:15:10, 19.96s/it]
                                                      

 39%|███▉      | 720/1848 [3:59:07<6:15:10, 19.96s/it]
 39%|███▉      | 721/1848 [3:59:27<6:14:51, 19.96s/it]
                                                      

 39%|███▉      | 721/1848 [3:59:27<6:14:51, 19.96s/it]
 39%|███▉      | 722/1848 [3:59:47<6:14:19, 19.95s/it]
                                                      

 39%|███▉      | 722/1848 [3:59:47<6:14:19, 19.95s/it]
 39%|███▉      | 723/1848 [4:00:07<6:14:16, 19.96s/it]
                                                      

 39%|███▉      | 723/1848 [4:00:07<6:14:16, 19.96s/it]
 39%|███▉      | 724/1848 [4:00:27<6:14:04, 19.97s/it]
                                                      

 39%|███▉      | 724/1848 [4:00:27<6:14:04, 19.97s/it]
 39%|███▉      | 725/1848 [4:00:47<6:13:43, 19.97s/it]
                                                      

 39%|███▉      | 725/1848 [4:00:47<6:13:43, 19.97s/it]
 39%|███▉      | 726/1848 [4:01:07<6:13:17, 19.96s/it]
                                                      

 39%|███▉      | 726/1848 [4:01:07<6:13:17, 19.96s/it]
 39%|███▉      | 727/1848 [4:01:27<6:13:26, 19.99s/it]
                                                      

 39%|███▉      | 727/1848 [4:01:27<6:13:26, 19.99s/it]
 39%|███▉      | 728/1848 [4:01:47<6:12:45, 19.97s/it]
                                                      

 39%|███▉      | 728/1848 [4:01:47<6:12:45, 19.97s/it]
 39%|███▉      | 729/1848 [4:02:07<6:12:19, 19.96s/it]
                                                      

 39%|███▉      | 729/1848 [4:02:07<6:12:19, 19.96s/it]
 40%|███▉      | 730/1848 [4:02:27<6:11:48, 19.95s/it]
                                                      

 40%|███▉      | 730/1848 [4:02:27<6:11:48, 19.95s/it]
 40%|███▉      | 731/1848 [4:02:47<6:11:45, 19.97s/it]
                                                      

 40%|███▉      | 731/1848 [4:02:47<6:11:45, 19.97s/it]
 40%|███▉      | 732/1848 [4:03:07<6:11:38, 19.98s/it]
                                                      

 40%|███▉      | 732/1848 [4:03:07<6:11:38, 19.98s/it]
 40%|███▉      | 733/1848 [4:03:27<6:11:32, 19.99s/it]
                                                      

 40%|███▉      | 733/1848 [4:03:27<6:11:32, 19.99s/it]
 40%|███▉      | 734/1848 [4:03:47<6:10:50, 19.97s/it]
                                                      

 40%|███▉      | 734/1848 [4:03:47<6:10:50, 19.97s/it]
 40%|███▉      | 735/1848 [4:04:07<6:10:14, 19.96s/it]
                                                      

 40%|███▉      | 735/1848 [4:04:07<6:10:14, 19.96s/it]
 40%|███▉      | 736/1848 [4:04:27<6:09:44, 19.95s/it]
                                                      

 40%|███▉      | 736/1848 [4:04:27<6:09:44, 19.95s/it]
 40%|███▉      | 737/1848 [4:04:47<6:09:23, 19.95s/it]
                                                      

 40%|███▉      | 737/1848 [4:04:47<6:09:23, 19.95s/it]
 40%|███▉      | 738/1848 [4:05:06<6:08:29, 19.92s/it]
                                                      

 40%|███▉      | 738/1848 [4:05:06<6:08:29, 19.92s/it]
 40%|███▉      | 739/1848 [4:05:26<6:07:51, 19.90s/it]
                                                      

 40%|███▉      | 739/1848 [4:05:26<6:07:51, 19.90s/it]
 40%|████      | 740/1848 [4:05:46<6:07:45, 19.91s/it]
                                                      

 40%|████      | 740/1848 [4:05:46<6:07:45, 19.91s/it]
 40%|████      | 741/1848 [4:06:06<6:07:26, 19.92s/it]
                                                      

 40%|████      | 741/1848 [4:06:06<6:07:26, 19.92s/it]
 40%|████      | 742/1848 [4:06:26<6:07:31, 19.94s/it]
                                                      

 40%|████      | 742/1848 [4:06:26<6:07:31, 19.94s/it]
 40%|████      | 743/1848 [4:06:46<6:07:21, 19.95s/it]
                                                      

 40%|████      | 743/1848 [4:06:46<6:07:21, 19.95s/it]
 40%|████      | 744/1848 [4:07:06<6:07:06, 19.95s/it]
                                                      

 40%|████      | 744/1848 [4:07:06<6:07:06, 19.95s/it]
 40%|████      | 745/1848 [4:07:26<6:06:46, 19.95s/it]
                                                      

 40%|████      | 745/1848 [4:07:26<6:06:46, 19.95s/it]
 40%|████      | 746/1848 [4:07:46<6:06:39, 19.96s/it]
                                                      

 40%|████      | 746/1848 [4:07:46<6:06:39, 19.96s/it]
 40%|████      | 747/1848 [4:08:06<6:06:20, 19.96s/it]
                                                      

 40%|████      | 747/1848 [4:08:06<6:06:20, 19.96s/it]
 40%|████      | 748/1848 [4:08:26<6:05:40, 19.95s/it]
                                                      

 40%|████      | 748/1848 [4:08:26<6:05:40, 19.95s/it]
 41%|████      | 749/1848 [4:08:46<6:05:36, 19.96s/it]
                                                      

 41%|████      | 749/1848 [4:08:46<6:05:36, 19.96s/it]
 41%|████      | 750/1848 [4:09:06<6:05:11, 19.96s/it]
                                                      

 41%|████      | 750/1848 [4:09:06<6:05:11, 19.96s/it]
 41%|████      | 751/1848 [4:09:26<6:04:32, 19.94s/it]
                                                      

 41%|████      | 751/1848 [4:09:26<6:04:32, 19.94s/it]
 41%|████      | 752/1848 [4:09:46<6:04:07, 19.93s/it]
                                                      

 41%|████      | 752/1848 [4:09:46<6:04:07, 19.93s/it]
 41%|████      | 753/1848 [4:10:06<6:03:46, 19.93s/it]
                                                      

 41%|████      | 753/1848 [4:10:06<6:03:46, 19.93s/it]
 41%|████      | 754/1848 [4:10:26<6:03:45, 19.95s/it]
                                                      

 41%|████      | 754/1848 [4:10:26<6:03:45, 19.95s/it]
 41%|████      | 755/1848 [4:10:46<6:03:25, 19.95s/it]
                                                      

 41%|████      | 755/1848 [4:10:46<6:03:25, 19.95s/it]
 41%|████      | 756/1848 [4:11:05<6:02:45, 19.93s/it]
                                                      

 41%|████      | 756/1848 [4:11:05<6:02:45, 19.93s/it]
 41%|████      | 757/1848 [4:11:25<6:02:56, 19.96s/it]
                                                      

 41%|████      | 757/1848 [4:11:25<6:02:56, 19.96s/it]
 41%|████      | 758/1848 [4:11:45<6:02:10, 19.94s/it]
                                                      

 41%|████      | 758/1848 [4:11:45<6:02:10, 19.94s/it]
 41%|████      | 759/1848 [4:12:05<6:02:12, 19.96s/it]
                                                      

 41%|████      | 759/1848 [4:12:05<6:02:12, 19.96s/it]
 41%|████      | 760/1848 [4:12:25<6:01:52, 19.96s/it]
                                                      

 41%|████      | 760/1848 [4:12:25<6:01:52, 19.96s/it]
 41%|████      | 761/1848 [4:12:45<6:01:12, 19.94s/it]
                                                      

 41%|████      | 761/1848 [4:12:45<6:01:12, 19.94s/it]
 41%|████      | 762/1848 [4:13:05<6:01:05, 19.95s/it]
                                                      

 41%|████      | 762/1848 [4:13:05<6:01:05, 19.95s/it]
 41%|████▏     | 763/1848 [4:13:25<6:00:27, 19.93s/it]
                                                      

 41%|████▏     | 763/1848 [4:13:25<6:00:27, 19.93s/it]
 41%|████▏     | 764/1848 [4:13:45<6:00:22, 19.95s/it]
                                                      

 41%|████▏     | 764/1848 [4:13:45<6:00:22, 19.95s/it]
 41%|████▏     | 765/1848 [4:14:05<5:59:35, 19.92s/it]
                                                      

 41%|████▏     | 765/1848 [4:14:05<5:59:35, 19.92s/it]
 41%|████▏     | 766/1848 [4:14:25<5:59:19, 19.93s/it]
                                                      

 41%|████▏     | 766/1848 [4:14:25<5:59:19, 19.93s/it]
 42%|████▏     | 767/1848 [4:14:45<5:58:45, 19.91s/it]
                                                      

 42%|████▏     | 767/1848 [4:14:45<5:58:45, 19.91s/it]
 42%|████▏     | 768/1848 [4:15:05<5:58:52, 19.94s/it]
                                                      

 42%|████▏     | 768/1848 [4:15:05<5:58:52, 19.94s/it]
 42%|████▏     | 769/1848 [4:15:25<5:58:07, 19.91s/it]
                                                      

 42%|████▏     | 769/1848 [4:15:25<5:58:07, 19.91s/it]
 42%|████▏     | 770/1848 [4:15:45<5:57:51, 19.92s/it]
                                                      

 42%|████▏     | 770/1848 [4:15:45<5:57:51, 19.92s/it]
 42%|████▏     | 771/1848 [4:16:04<5:57:23, 19.91s/it]
                                                      

 42%|████▏     | 771/1848 [4:16:04<5:57:23, 19.91s/it]
 42%|████▏     | 772/1848 [4:16:24<5:57:06, 19.91s/it]
                                                      

 42%|████▏     | 772/1848 [4:16:24<5:57:06, 19.91s/it]
 42%|████▏     | 773/1848 [4:16:44<5:56:28, 19.90s/it]
                                                      

 42%|████▏     | 773/1848 [4:16:44<5:56:28, 19.90s/it]
 42%|████▏     | 774/1848 [4:17:04<5:56:00, 19.89s/it]
                                                      

 42%|████▏     | 774/1848 [4:17:04<5:56:00, 19.89s/it]
 42%|████▏     | 775/1848 [4:17:24<5:56:02, 19.91s/it]
                                                      

 42%|████▏     | 775/1848 [4:17:24<5:56:02, 19.91s/it]
 42%|████▏     | 776/1848 [4:17:44<5:56:09, 19.93s/it]
                                                      

 42%|████▏     | 776/1848 [4:17:44<5:56:09, 19.93s/it]
 42%|████▏     | 777/1848 [4:18:04<5:55:49, 19.93s/it]
                                                      

 42%|████▏     | 777/1848 [4:18:04<5:55:49, 19.93s/it]
 42%|████▏     | 778/1848 [4:18:24<5:55:41, 19.95s/it]
                                                      

 42%|████▏     | 778/1848 [4:18:24<5:55:41, 19.95s/it]
 42%|████▏     | 779/1848 [4:18:44<5:55:20, 19.94s/it]
                                                      

 42%|████▏     | 779/1848 [4:18:44<5:55:20, 19.94s/it]
 42%|████▏     | 780/1848 [4:19:04<5:54:40, 19.93s/it]
                                                      

 42%|████▏     | 780/1848 [4:19:04<5:54:40, 19.93s/it]
 42%|████▏     | 781/1848 [4:19:24<5:54:35, 19.94s/it]
                                                      

 42%|████▏     | 781/1848 [4:19:24<5:54:35, 19.94s/it]
 42%|████▏     | 782/1848 [4:19:44<5:54:18, 19.94s/it]
                                                      

 42%|████▏     | 782/1848 [4:19:44<5:54:18, 19.94s/it]
 42%|████▏     | 783/1848 [4:20:04<5:54:06, 19.95s/it]
                                                      

 42%|████▏     | 783/1848 [4:20:04<5:54:06, 19.95s/it]
 42%|████▏     | 784/1848 [4:20:24<5:53:53, 19.96s/it]
                                                      

 42%|████▏     | 784/1848 [4:20:24<5:53:53, 19.96s/it]
 42%|████▏     | 785/1848 [4:20:44<5:53:47, 19.97s/it]
                                                      

 42%|████▏     | 785/1848 [4:20:44<5:53:47, 19.97s/it]
 43%|████▎     | 786/1848 [4:21:04<5:53:12, 19.96s/it]
                                                      

 43%|████▎     | 786/1848 [4:21:04<5:53:12, 19.96s/it]
 43%|████▎     | 787/1848 [4:21:23<5:52:34, 19.94s/it]
                                                      

 43%|████▎     | 787/1848 [4:21:23<5:52:34, 19.94s/it]
 43%|████▎     | 788/1848 [4:21:43<5:52:24, 19.95s/it]
                                                      

 43%|████▎     | 788/1848 [4:21:43<5:52:24, 19.95s/it]
 43%|████▎     | 789/1848 [4:22:03<5:51:55, 19.94s/it]
                                                      

 43%|████▎     | 789/1848 [4:22:03<5:51:55, 19.94s/it]
 43%|████▎     | 790/1848 [4:22:23<5:52:02, 19.97s/it]
                                                      

 43%|████▎     | 790/1848 [4:22:23<5:52:02, 19.97s/it]
 43%|████▎     | 791/1848 [4:22:43<5:51:37, 19.96s/it]
                                                      
{'loss': 1.1973, 'learning_rate': 8.934577922077923e-06, 'epoch': 1.1}
+{'loss': 1.1082, 'learning_rate': 8.926948051948052e-06, 'epoch': 1.1}
+{'loss': 1.3239, 'learning_rate': 8.919318181818182e-06, 'epoch': 1.1}
+{'loss': 1.1811, 'learning_rate': 8.911688311688313e-06, 'epoch': 1.1}
+{'loss': 1.4169, 'learning_rate': 8.904058441558442e-06, 'epoch': 1.11}
+{'loss': 1.327, 'learning_rate': 8.896428571428572e-06, 'epoch': 1.11}
+{'loss': 1.298, 'learning_rate': 8.888798701298703e-06, 'epoch': 1.11}
+{'loss': 1.2019, 'learning_rate': 8.881168831168831e-06, 'epoch': 1.11}
+{'loss': 1.1327, 'learning_rate': 8.87353896103896e-06, 'epoch': 1.11}
+{'loss': 1.293, 'learning_rate': 8.86590909090909e-06, 'epoch': 1.11}
+{'loss': 1.3004, 'learning_rate': 8.858279220779221e-06, 'epoch': 1.12}
+{'loss': 1.258, 'learning_rate': 8.85064935064935e-06, 'epoch': 1.12}
+{'loss': 1.2154, 'learning_rate': 8.84301948051948e-06, 'epoch': 1.12}
+{'loss': 1.1026, 'learning_rate': 8.835389610389611e-06, 'epoch': 1.12}
+{'loss': 1.1777, 'learning_rate': 8.827759740259741e-06, 'epoch': 1.12}
+{'loss': 1.3272, 'learning_rate': 8.82012987012987e-06, 'epoch': 1.12}
+{'loss': 1.0799, 'learning_rate': 8.8125e-06, 'epoch': 1.12}
+{'loss': 1.0912, 'learning_rate': 8.804870129870131e-06, 'epoch': 1.13}
+{'loss': 1.2853, 'learning_rate': 8.79724025974026e-06, 'epoch': 1.13}
+{'loss': 1.1219, 'learning_rate': 8.78961038961039e-06, 'epoch': 1.13}
+{'loss': 1.4704, 'learning_rate': 8.78198051948052e-06, 'epoch': 1.13}
+{'loss': 1.0823, 'learning_rate': 8.77435064935065e-06, 'epoch': 1.13}
+{'loss': 0.938, 'learning_rate': 8.766720779220779e-06, 'epoch': 1.13}
+{'loss': 1.6825, 'learning_rate': 8.75909090909091e-06, 'epoch': 1.14}
+{'loss': 1.4342, 'learning_rate': 8.75146103896104e-06, 'epoch': 1.14}
+{'loss': 1.1411, 'learning_rate': 8.743831168831168e-06, 'epoch': 1.14}
+{'loss': 1.109, 'learning_rate': 8.736201298701299e-06, 'epoch': 1.14}
+{'loss': 1.1438, 'learning_rate': 8.72857142857143e-06, 'epoch': 1.14}
+{'loss': 1.0978, 'learning_rate': 8.72094155844156e-06, 'epoch': 1.14}
+{'loss': 1.3208, 'learning_rate': 8.713311688311689e-06, 'epoch': 1.15}
+{'loss': 1.0653, 'learning_rate': 8.70568181818182e-06, 'epoch': 1.15}
+{'loss': 1.1478, 'learning_rate': 8.69805194805195e-06, 'epoch': 1.15}
+{'loss': 1.176, 'learning_rate': 8.690422077922077e-06, 'epoch': 1.15}
+{'loss': 1.446, 'learning_rate': 8.682792207792207e-06, 'epoch': 1.15}
+{'loss': 1.2677, 'learning_rate': 8.675162337662338e-06, 'epoch': 1.15}
+{'loss': 1.4785, 'learning_rate': 8.667532467532467e-06, 'epoch': 1.16}
+{'loss': 1.4128, 'learning_rate': 8.659902597402597e-06, 'epoch': 1.16}
+{'loss': 1.4073, 'learning_rate': 8.652272727272728e-06, 'epoch': 1.16}
+{'loss': 1.51, 'learning_rate': 8.644642857142858e-06, 'epoch': 1.16}
+{'loss': 1.3917, 'learning_rate': 8.637012987012987e-06, 'epoch': 1.16}
+{'loss': 1.0331, 'learning_rate': 8.629383116883117e-06, 'epoch': 1.16}
+{'loss': 1.0073, 'learning_rate': 8.621753246753248e-06, 'epoch': 1.17}
+{'loss': 1.291, 'learning_rate': 8.614123376623377e-06, 'epoch': 1.17}
+{'loss': 1.1617, 'learning_rate': 8.606493506493507e-06, 'epoch': 1.17}
+{'loss': 1.2349, 'learning_rate': 8.598863636363636e-06, 'epoch': 1.17}
+{'loss': 1.2418, 'learning_rate': 8.591233766233767e-06, 'epoch': 1.17}
+{'loss': 1.1669, 'learning_rate': 8.583603896103895e-06, 'epoch': 1.17}
+{'loss': 1.3913, 'learning_rate': 8.575974025974026e-06, 'epoch': 1.18}
+{'loss': 1.3073, 'learning_rate': 8.568344155844156e-06, 'epoch': 1.18}
+{'loss': 1.1933, 'learning_rate': 8.560714285714285e-06, 'epoch': 1.18}
+{'loss': 1.0963, 'learning_rate': 8.553084415584416e-06, 'epoch': 1.18}
+{'loss': 1.1209, 'learning_rate': 8.545454545454546e-06, 'epoch': 1.18}
+{'loss': 1.2876, 'learning_rate': 8.537824675324677e-06, 'epoch': 1.18}
+{'loss': 1.3056, 'learning_rate': 8.530194805194805e-06, 'epoch': 1.19}
+{'loss': 1.0698, 'learning_rate': 8.522564935064936e-06, 'epoch': 1.19}
+{'loss': 1.2019, 'learning_rate': 8.514935064935066e-06, 'epoch': 1.19}
+{'loss': 1.0792, 'learning_rate': 8.507305194805195e-06, 'epoch': 1.19}
+{'loss': 1.4732, 'learning_rate': 8.499675324675324e-06, 'epoch': 1.19}
+{'loss': 1.1708, 'learning_rate': 8.492045454545455e-06, 'epoch': 1.19}
+{'loss': 1.2363, 'learning_rate': 8.484415584415585e-06, 'epoch': 1.19}
+{'loss': 1.288, 'learning_rate': 8.476785714285714e-06, 'epoch': 1.2}
+{'loss': 1.366, 'learning_rate': 8.469155844155844e-06, 'epoch': 1.2}
+{'loss': 1.3984, 'learning_rate': 8.461525974025975e-06, 'epoch': 1.2}
+{'loss': 1.2394, 'learning_rate': 8.453896103896104e-06, 'epoch': 1.2}
+{'loss': 1.17, 'learning_rate': 8.446266233766234e-06, 'epoch': 1.2}
+{'loss': 1.2506, 'learning_rate': 8.438636363636365e-06, 'epoch': 1.2}
+{'loss': 1.1979, 'learning_rate': 8.431006493506494e-06, 'epoch': 1.21}
+{'loss': 1.1298, 'learning_rate': 8.423376623376624e-06, 'epoch': 1.21}
+{'loss': 1.1771, 'learning_rate': 8.415746753246754e-06, 'epoch': 1.21}
+{'loss': 1.2038, 'learning_rate': 8.408116883116883e-06, 'epoch': 1.21}
+{'loss': 1.0808, 'learning_rate': 8.400487012987012e-06, 'epoch': 1.21}
+{'loss': 1.1343, 'learning_rate': 8.392857142857143e-06, 'epoch': 1.21}
+{'loss': 1.2369, 'learning_rate': 8.385227272727273e-06, 'epoch': 1.22}
+{'loss': 1.2792, 'learning_rate': 8.377597402597402e-06, 'epoch': 1.22}
+{'loss': 1.1266, 'learning_rate': 8.369967532467532e-06, 'epoch': 1.22}
+{'loss': 1.094, 'learning_rate': 8.362337662337663e-06, 'epoch': 1.22}
+{'loss': 1.1429, 'learning_rate': 8.354707792207793e-06, 'epoch': 1.22}
+{'loss': 1.2601, 'learning_rate': 8.347077922077922e-06, 'epoch': 1.22}
+{'loss': 1.2095, 'learning_rate': 8.339448051948053e-06, 'epoch': 1.23}
+{'loss': 1.3563, 'learning_rate': 8.331818181818183e-06, 'epoch': 1.23}
+{'loss': 1.232, 'learning_rate': 8.324188311688312e-06, 'epoch': 1.23}
+{'loss': 1.4091, 'learning_rate': 8.31655844155844e-06, 'epoch': 1.23}
+{'loss': 1.3718, 'learning_rate': 8.308928571428571e-06, 'epoch': 1.23}
+{'loss': 1.2168, 'learning_rate': 8.301298701298702e-06, 'epoch': 1.23}
+{'loss': 1.39, 'learning_rate': 8.29366883116883e-06, 'epoch': 1.24}
+{'loss': 1.2865, 'learning_rate': 8.286038961038961e-06, 'epoch': 1.24}
+{'loss': 1.2454, 'learning_rate': 8.278409090909092e-06, 'epoch': 1.24}
+{'loss': 1.0959, 'learning_rate': 8.27077922077922e-06, 'epoch': 1.24}
+{'loss': 1.3704, 'learning_rate': 8.263149350649351e-06, 'epoch': 1.24}
+{'loss': 1.2978, 'learning_rate': 8.255519480519481e-06, 'epoch': 1.24}
+{'loss': 1.3518, 'learning_rate': 8.247889610389612e-06, 'epoch': 1.25}
+{'loss': 1.0841, 'learning_rate': 8.24025974025974e-06, 'epoch': 1.25}
+{'loss': 1.1811, 'learning_rate': 8.232629870129871e-06, 'epoch': 1.25}
+{'loss': 1.341, 'learning_rate': 8.225e-06, 'epoch': 1.25}
+{'loss': 1.2639, 'learning_rate': 8.217370129870129e-06, 'epoch': 1.25}
+{'loss': 1.2336, 'learning_rate': 8.20974025974026e-06, 'epoch': 1.25}
+{'loss': 1.1356, 'learning_rate': 8.20211038961039e-06, 'epoch': 1.25}
+{'loss': 1.3084, 'learning_rate': 8.19448051948052e-06, 'epoch': 1.26}
+{'loss': 1.2247, 'learning_rate': 8.186850649350649e-06, 'epoch': 1.26}
+{'loss': 1.1785, 'learning_rate': 8.17922077922078e-06, 'epoch': 1.26}
+{'loss': 1.217, 'learning_rate': 8.17159090909091e-06, 'epoch': 1.26}
+{'loss': 1.2103, 'learning_rate': 8.163961038961039e-06, 'epoch': 1.26}
+{'loss': 1.0053, 'learning_rate': 8.15633116883117e-06, 'epoch': 1.26}
+{'loss': 1.2639, 'learning_rate': 8.1487012987013e-06, 'epoch': 1.27}
+{'loss': 1.1619, 'learning_rate': 8.141071428571429e-06, 'epoch': 1.27}
+{'loss': 1.1376, 'learning_rate': 8.13344155844156e-06, 'epoch': 1.27}
+{'loss': 1.4675, 'learning_rate': 8.125811688311688e-06, 'epoch': 1.27}
+{'loss': 1.0484, 'learning_rate': 8.118181818181819e-06, 'epoch': 1.27}
+{'loss': 1.2948, 'learning_rate': 8.110551948051947e-06, 'epoch': 1.27}
+{'loss': 1.3818, 'learning_rate': 8.102922077922078e-06, 'epoch': 1.28}
+{'loss': 1.3305, 'learning_rate': 8.095292207792208e-06, 'epoch': 1.28}
+{'loss': 1.0584, 'learning_rate': 8.087662337662337e-06, 'epoch': 1.28}
+{'loss': 1.2448, 'learning_rate': 8.080032467532468e-06, 'epoch': 1.28}
+{'loss': 1.0695, 'learning_rate': 8.072402597402598e-06, 'epoch': 1.28}
+
 43%|████▎     | 791/1848 [4:22:43<5:51:37, 19.96s/it]
 43%|████▎     | 792/1848 [4:23:03<5:51:00, 19.94s/it]
                                                      

 43%|████▎     | 792/1848 [4:23:03<5:51:00, 19.94s/it]
 43%|████▎     | 793/1848 [4:23:23<5:50:11, 19.92s/it]
                                                      

 43%|████▎     | 793/1848 [4:23:23<5:50:11, 19.92s/it]
 43%|████▎     | 794/1848 [4:23:43<5:50:13, 19.94s/it]
                                                      

 43%|████▎     | 794/1848 [4:23:43<5:50:13, 19.94s/it]
 43%|████▎     | 795/1848 [4:24:03<5:49:27, 19.91s/it]
                                                      

 43%|████▎     | 795/1848 [4:24:03<5:49:27, 19.91s/it]
 43%|████▎     | 796/1848 [4:24:23<5:49:18, 19.92s/it]
                                                      

 43%|████▎     | 796/1848 [4:24:23<5:49:18, 19.92s/it]
 43%|████▎     | 797/1848 [4:24:43<5:49:35, 19.96s/it]
                                                      

 43%|████▎     | 797/1848 [4:24:43<5:49:35, 19.96s/it]
 43%|████▎     | 798/1848 [4:25:03<5:49:29, 19.97s/it]
                                                      

 43%|████▎     | 798/1848 [4:25:03<5:49:29, 19.97s/it]
 43%|████▎     | 799/1848 [4:25:23<5:49:11, 19.97s/it]
                                                      

 43%|████▎     | 799/1848 [4:25:23<5:49:11, 19.97s/it]
 43%|████▎     | 800/1848 [4:25:43<5:48:53, 19.97s/it]
                                                      

 43%|████▎     | 800/1848 [4:25:43<5:48:53, 19.97s/it]
 43%|████▎     | 801/1848 [4:26:04<5:52:55, 20.23s/it]
                                                      

 43%|████▎     | 801/1848 [4:26:04<5:52:55, 20.23s/it]
 43%|████▎     | 802/1848 [4:26:24<5:51:27, 20.16s/it]
                                                      

 43%|████▎     | 802/1848 [4:26:24<5:51:27, 20.16s/it]
 43%|████▎     | 803/1848 [4:26:44<5:50:16, 20.11s/it]
                                                      

 43%|████▎     | 803/1848 [4:26:44<5:50:16, 20.11s/it]
 44%|████▎     | 804/1848 [4:27:04<5:49:12, 20.07s/it]
                                                      

 44%|███���▎     | 804/1848 [4:27:04<5:49:12, 20.07s/it]
 44%|████▎     | 805/1848 [4:27:24<5:48:33, 20.05s/it]
                                                      

 44%|████▎     | 805/1848 [4:27:24<5:48:33, 20.05s/it]
 44%|████▎     | 806/1848 [4:27:44<5:47:46, 20.03s/it]
                                                      

 44%|████▎     | 806/1848 [4:27:44<5:47:46, 20.03s/it]
 44%|████▎     | 807/1848 [4:28:04<5:47:05, 20.01s/it]
                                                      

 44%|████▎     | 807/1848 [4:28:04<5:47:05, 20.01s/it]
 44%|████▎     | 808/1848 [4:28:24<5:46:48, 20.01s/it]
                                                      

 44%|████▎     | 808/1848 [4:28:24<5:46:48, 20.01s/it]
 44%|████▍     | 809/1848 [4:28:43<5:45:37, 19.96s/it]
                                                      

 44%|████▍     | 809/1848 [4:28:43<5:45:37, 19.96s/it]
 44%|████▍     | 810/1848 [4:29:03<5:45:35, 19.98s/it]
                                                      

 44%|████▍     | 810/1848 [4:29:03<5:45:35, 19.98s/it]
 44%|████▍     | 811/1848 [4:29:23<5:44:47, 19.95s/it]
                                                      

 44%|████▍     | 811/1848 [4:29:23<5:44:47, 19.95s/it]
 44%|████▍     | 812/1848 [4:29:43<5:44:39, 19.96s/it]
                                                      

 44%|████▍     | 812/1848 [4:29:43<5:44:39, 19.96s/it]
 44%|████▍     | 813/1848 [4:30:03<5:44:19, 19.96s/it]
                                                      

 44%|████▍     | 813/1848 [4:30:03<5:44:19, 19.96s/it]
 44%|████▍     | 814/1848 [4:30:23<5:44:02, 19.96s/it]
                                                      

 44%|████▍     | 814/1848 [4:30:23<5:44:02, 19.96s/it]
 44%|████▍     | 815/1848 [4:30:43<5:43:38, 19.96s/it]
                                                      

 44%|████▍     | 815/1848 [4:30:43<5:43:38, 19.96s/it]
 44%|████▍     | 816/1848 [4:31:03<5:43:01, 19.94s/it]
                                                      

 44%|████▍     | 816/1848 [4:31:03<5:43:01, 19.94s/it]
 44%|████▍     | 817/1848 [4:31:23<5:42:51, 19.95s/it]
                                                      

 44%|████▍     | 817/1848 [4:31:23<5:42:51, 19.95s/it]
 44%|████▍     | 818/1848 [4:31:43<5:42:34, 19.96s/it]
                                                      

 44%|████▍     | 818/1848 [4:31:43<5:42:34, 19.96s/it]
 44%|████▍     | 819/1848 [4:32:03<5:42:28, 19.97s/it]
                                                      

 44%|████▍     | 819/1848 [4:32:03<5:42:28, 19.97s/it]
 44%|████▍     | 820/1848 [4:32:23<5:41:58, 19.96s/it]
                                                      

 44%|████▍     | 820/1848 [4:32:23<5:41:58, 19.96s/it]
 44%|████▍     | 821/1848 [4:32:43<5:41:24, 19.95s/it]
                                                      

 44%|████▍     | 821/1848 [4:32:43<5:41:24, 19.95s/it]
 44%|████▍     | 822/1848 [4:33:03<5:41:08, 19.95s/it]
                                                      

 44%|████▍     | 822/1848 [4:33:03<5:41:08, 19.95s/it]
 45%|████▍     | 823/1848 [4:33:23<5:41:08, 19.97s/it]
                                                      

 45%|████▍     | 823/1848 [4:33:23<5:41:08, 19.97s/it]
 45%|████▍     | 824/1848 [4:33:43<5:40:52, 19.97s/it]
                                                      

 45%|████▍     | 824/1848 [4:33:43<5:40:52, 19.97s/it]
 45%|████▍     | 825/1848 [4:34:03<5:40:34, 19.98s/it]
                                                      

 45%|████▍     | 825/1848 [4:34:03<5:40:34, 19.98s/it]
 45%|████▍     | 826/1848 [4:34:23<5:40:27, 19.99s/it]
                                                      

 45%|████▍     | 826/1848 [4:34:23<5:40:27, 19.99s/it]
 45%|████▍     | 827/1848 [4:34:43<5:40:07, 19.99s/it]
                                                      

 45%|████▍     | 827/1848 [4:34:43<5:40:07, 19.99s/it]
 45%|████▍     | 828/1848 [4:35:03<5:39:23, 19.96s/it]
                                                      

 45%|████▍     | 828/1848 [4:35:03<5:39:23, 19.96s/it]
 45%|████▍     | 829/1848 [4:35:23<5:38:59, 19.96s/it]
                                                      

 45%|████▍     | 829/1848 [4:35:23<5:38:59, 19.96s/it]
 45%|████▍     | 830/1848 [4:35:43<5:38:57, 19.98s/it]
                                                      

 45%|████▍     | 830/1848 [4:35:43<5:38:57, 19.98s/it]
 45%|████▍     | 831/1848 [4:36:03<5:38:15, 19.96s/it]
                                                      

 45%|████▍     | 831/1848 [4:36:03<5:38:15, 19.96s/it]
 45%|████▌     | 832/1848 [4:36:23<5:37:45, 19.95s/it]
                                                      

 45%|████▌     | 832/1848 [4:36:23<5:37:45, 19.95s/it]
 45%|████▌     | 833/1848 [4:36:43<5:37:43, 19.96s/it]
                                                      

 45%|████▌     | 833/1848 [4:36:43<5:37:43, 19.96s/it]
 45%|████▌     | 834/1848 [4:37:02<5:37:27, 19.97s/it]
                                                      

 45%|████▌     | 834/1848 [4:37:02<5:37:27, 19.97s/it]
 45%|████▌     | 835/1848 [4:37:22<5:36:43, 19.94s/it]
                                                      

 45%|████▌     | 835/1848 [4:37:22<5:36:43, 19.94s/it]
 45%|████▌     | 836/1848 [4:37:42<5:36:11, 19.93s/it]
                                                      

 45%|████▌     | 836/1848 [4:37:42<5:36:11, 19.93s/it]
 45%|████▌     | 837/1848 [4:38:02<5:35:43, 19.92s/it]
                                                      

 45%|████▌     | 837/1848 [4:38:02<5:35:43, 19.92s/it]
 45%|████▌     | 838/1848 [4:38:22<5:35:16, 19.92s/it]
                                                      

 45%|████▌     | 838/1848 [4:38:22<5:35:16, 19.92s/it]
 45%|████▌     | 839/1848 [4:38:42<5:34:49, 19.91s/it]
                                                      

 45%|████▌     | 839/1848 [4:38:42<5:34:49, 19.91s/it]
 45%|████▌     | 840/1848 [4:39:02<5:35:08, 19.95s/it]
                                                      

 45%|████▌     | 840/1848 [4:39:02<5:35:08, 19.95s/it]
 46%|████▌     | 841/1848 [4:39:22<5:34:53, 19.95s/it]
                                                      

 46%|████▌     | 841/1848 [4:39:22<5:34:53, 19.95s/it]
 46%|████▌     | 842/1848 [4:39:42<5:34:40, 19.96s/it]
                                                      

 46%|████▌     | 842/1848 [4:39:42<5:34:40, 19.96s/it]
 46%|████▌     | 843/1848 [4:40:02<5:34:02, 19.94s/it]
                                                      

 46%|████▌     | 843/1848 [4:40:02<5:34:02, 19.94s/it]
 46%|████▌     | 844/1848 [4:40:22<5:33:42, 19.94s/it]
                                                      

 46%|████▌     | 844/1848 [4:40:22<5:33:42, 19.94s/it]
 46%|████▌     | 845/1848 [4:40:42<5:33:27, 19.95s/it]
                                                      

 46%|████▌     | 845/1848 [4:40:42<5:33:27, 19.95s/it]
 46%|████▌     | 846/1848 [4:41:02<5:33:24, 19.96s/it]
                                                      

 46%|████▌     | 846/1848 [4:41:02<5:33:24, 19.96s/it]
 46%|████▌     | 847/1848 [4:41:22<5:33:30, 19.99s/it]
                                                      

 46%|████▌     | 847/1848 [4:41:22<5:33:30, 19.99s/it]
 46%|████▌     | 848/1848 [4:41:42<5:33:11, 19.99s/it]
                                                      

 46%|████▌     | 848/1848 [4:41:42<5:33:11, 19.99s/it]
 46%|████▌     | 849/1848 [4:42:02<5:32:40, 19.98s/it]
                                                      

 46%|████▌     | 849/1848 [4:42:02<5:32:40, 19.98s/it]
 46%|████▌     | 850/1848 [4:42:22<5:32:04, 19.96s/it]
                                                      

 46%|████▌     | 850/1848 [4:42:22<5:32:04, 19.96s/it]
 46%|████▌     | 851/1848 [4:42:42<5:31:53, 19.97s/it]
                                                      

 46%|████▌     | 851/1848 [4:42:42<5:31:53, 19.97s/it]
 46%|████▌     | 852/1848 [4:43:02<5:31:32, 19.97s/it]
                                                      

 46%|████▌     | 852/1848 [4:43:02<5:31:32, 19.97s/it]
 46%|████▌     | 853/1848 [4:43:22<5:31:15, 19.98s/it]
                                                      

 46%|████▌     | 853/1848 [4:43:22<5:31:15, 19.98s/it]
 46%|████▌     | 854/1848 [4:43:42<5:30:41, 19.96s/it]
                                                      

 46%|████▌     | 854/1848 [4:43:42<5:30:41, 19.96s/it]
 46%|████▋     | 855/1848 [4:44:02<5:30:24, 19.96s/it]
                                                      

 46%|████▋     | 855/1848 [4:44:02<5:30:24, 19.96s/it]
 46%|████▋     | 856/1848 [4:44:21<5:30:00, 19.96s/it]
                                                      

 46%|████▋     | 856/1848 [4:44:22<5:30:00, 19.96s/it]
 46%|████▋     | 857/1848 [4:44:41<5:29:26, 19.95s/it]
                                                      

 46%|████▋     | 857/1848 [4:44:41<5:29:26, 19.95s/it]
 46%|████▋     | 858/1848 [4:45:01<5:29:12, 19.95s/it]
                                                      

 46%|████▋     | 858/1848 [4:45:01<5:29:12, 19.95s/it]
 46%|████▋     | 859/1848 [4:45:21<5:28:53, 19.95s/it]
                                                      

 46%|████▋     | 859/1848 [4:45:21<5:28:53, 19.95s/it]
 47%|████▋     | 860/1848 [4:45:41<5:28:25, 19.95s/it]
                                                      

 47%|████▋     | 860/1848 [4:45:41<5:28:25, 19.95s/it]
 47%|████▋     | 861/1848 [4:46:01<5:28:19, 19.96s/it]
                                                      

 47%|████▋     | 861/1848 [4:46:01<5:28:19, 19.96s/it]
 47%|████▋     | 862/1848 [4:46:21<5:28:03, 19.96s/it]
                                                      

 47%|████▋     | 862/1848 [4:46:21<5:28:03, 19.96s/it]
 47%|████▋     | 863/1848 [4:46:41<5:27:12, 19.93s/it]
                                                      

 47%|████▋     | 863/1848 [4:46:41<5:27:12, 19.93s/it]
 47%|████▋     | 864/1848 [4:47:01<5:27:04, 19.94s/it]
                                                      

 47%|████▋     | 864/1848 [4:47:01<5:27:04, 19.94s/it]
 47%|████▋     | 865/1848 [4:47:21<5:26:23, 19.92s/it]
                                                      

 47%|████▋     | 865/1848 [4:47:21<5:26:23, 19.92s/it]
 47%|████▋     | 866/1848 [4:47:41<5:26:06, 19.93s/it]
                                                      

 47%|████▋     | 866/1848 [4:47:41<5:26:06, 19.93s/it]
 47%|████▋     | 867/1848 [4:48:01<5:26:00, 19.94s/it]
                                                      

 47%|████▋     | 867/1848 [4:48:01<5:26:00, 19.94s/it]
 47%|████▋     | 868/1848 [4:48:21<5:26:03, 19.96s/it]
                                                      

 47%|████▋     | 868/1848 [4:48:21<5:26:03, 19.96s/it]
 47%|████▋     | 869/1848 [4:48:41<5:25:43, 19.96s/it]
                                                      

 47%|████▋     | 869/1848 [4:48:41<5:25:43, 19.96s/it]
 47%|████▋     | 870/1848 [4:49:01<5:25:31, 19.97s/it]
                                                      

 47%|████▋     | 870/1848 [4:49:01<5:25:31, 19.97s/it]
 47%|████▋     | 871/1848 [4:49:21<5:25:17, 19.98s/it]
                                                      

 47%|████▋     | 871/1848 [4:49:21<5:25:17, 19.98s/it]
 47%|████▋     | 872/1848 [4:49:41<5:24:37, 19.96s/it]
                                                      

 47%|████▋     | 872/1848 [4:49:41<5:24:37, 19.96s/it]
 47%|████▋     | 873/1848 [4:50:01<5:24:03, 19.94s/it]
                                                      

 47%|████▋     | 873/1848 [4:50:01<5:24:03, 19.94s/it]
 47%|████▋     | 874/1848 [4:50:21<5:23:56, 19.95s/it]
                                                      

 47%|████▋     | 874/1848 [4:50:21<5:23:56, 19.95s/it]
 47%|████▋     | 875/1848 [4:50:41<5:23:39, 19.96s/it]
                                                      

 47%|████▋     | 875/1848 [4:50:41<5:23:39, 19.96s/it]
 47%|████▋     | 876/1848 [4:51:01<5:23:21, 19.96s/it]
                                                      

 47%|████▋     | 876/1848 [4:51:01<5:23:21, 19.96s/it]
 47%|████▋     | 877/1848 [4:51:20<5:23:01, 19.96s/it]
                                                      

 47%|████▋     | 877/1848 [4:51:20<5:23:01, 19.96s/it]
 48%|████▊     | 878/1848 [4:51:40<5:22:40, 19.96s/it]
                                                      

 48%|████▊     | 878/1848 [4:51:40<5:22:40, 19.96s/it]
 48%|████▊     | 879/1848 [4:52:00<5:22:34, 19.97s/it]
                                                      

 48%|████▊     | 879/1848 [4:52:00<5:22:34, 19.97s/it]
 48%|████▊     | 880/1848 [4:52:20<5:22:28, 19.99s/it]
                                                      

 48%|████▊     | 880/1848 [4:52:20<5:22:28, 19.99s/it]
 48%|████▊     | 881/1848 [4:52:40<5:21:57, 19.98s/it]
                                                      

 48%|████▊     | 881/1848 [4:52:40<5:21:57, 19.98s/it]
 48%|████▊     | 882/1848 [4:53:00<5:21:18, 19.96s/it]
                                                      

 48%|████▊     | 882/1848 [4:53:00<5:21:18, 19.96s/it]
 48%|████▊     | 883/1848 [4:53:20<5:20:58, 19.96s/it]
                                                      

 48%|████▊     | 883/1848 [4:53:20<5:20:58, 19.96s/it]
 48%|████▊     | 884/1848 [4:53:40<5:20:27, 19.95s/it]
                                                      

 48%|████▊     | 884/1848 [4:53:40<5:20:27, 19.95s/it]
 48%|████▊     | 885/1848 [4:54:00<5:20:27, 19.97s/it]
                                                      

 48%|████▊     | 885/1848 [4:54:00<5:20:27, 19.97s/it]
 48%|████▊     | 886/1848 [4:54:20<5:19:45, 19.94s/it]
                                                      

 48%|████▊     | 886/1848 [4:54:20<5:19:45, 19.94s/it]
 48%|████▊     | 887/1848 [4:54:40<5:19:36, 19.95s/it]
                                                      

 48%|████▊     | 887/1848 [4:54:40<5:19:36, 19.95s/it]
 48%|████▊     | 888/1848 [4:55:00<5:19:26, 19.96s/it]
                                                      

 48%|████▊     | 888/1848 [4:55:00<5:19:26, 19.96s/it]
 48%|████▊     | 889/1848 [4:55:20<5:18:41, 19.94s/it]
                                                      

 48%|████▊     | 889/1848 [4:55:20<5:18:41, 19.94s/it]
 48%|████▊     | 890/1848 [4:55:40<5:18:27, 19.94s/it]
                                                      

 48%|████▊     | 890/1848 [4:55:40<5:18:27, 19.94s/it]
 48%|████▊     | 891/1848 [4:56:00<5:18:11, 19.95s/it]
                                                      

 48%|████▊     | 891/1848 [4:56:00<5:18:11, 19.95s/it]
 48%|████▊     | 892/1848 [4:56:20<5:17:41, 19.94s/it]
                                                      

 48%|████▊     | 892/1848 [4:56:20<5:17:41, 19.94s/it]
 48%|████▊     | 893/1848 [4:56:40<5:17:38, 19.96s/it]
                                                      

 48%|████▊     | 893/1848 [4:56:40<5:17:38, 19.96s/it]
 48%|████▊     | 894/1848 [4:57:00<5:17:06, 19.94s/it]
                                                      

 48%|████▊     | 894/1848 [4:57:00<5:17:06, 19.94s/it]
 48%|████▊     | 895/1848 [4:57:20<5:16:24, 19.92s/it]
                                                      

 48%|████▊     | 895/1848 [4:57:20<5:16:24, 19.92s/it]
 48%|████▊     | 896/1848 [4:57:40<5:16:07, 19.92s/it]
                                                      

 48%|████▊     | 896/1848 [4:57:40<5:16:07, 19.92s/it]
 49%|████▊     | 897/1848 [4:57:59<5:15:33, 19.91s/it]
                                                      

 49%|████▊     | 897/1848 [4:57:59<5:15:33, 19.91s/it]
 49%|████▊     | 898/1848 [4:58:19<5:15:29, 19.93s/it]
                                                      

 49%|████▊     | 898/1848 [4:58:19<5:15:29, 19.93s/it]
 49%|████▊     | 899/1848 [4:58:39<5:15:24, 19.94s/it]
                                                      

 49%|████▊     | 899/1848 [4:58:39<5:15:24, 19.94s/it]
 49%|████▊     | 900/1848 [4:58:59<5:14:39, 19.91s/it]
                                                      

 49%|████▊     | 900/1848 [4:58:59<5:14:39, 19.91s/it]
 49%|████▉     | 901/1848 [4:59:20<5:18:26, 20.18s/it]
                                                      

 49%|████▉     | 901/1848 [4:59:20<5:18:26, 20.18s/it]
 49%|████▉     | 902/1848 [4:59:40<5:17:07, 20.11s/it]
                                                      

 49%|████▉     | 902/1848 [4:59:40<5:17:07, 20.11s/it]
 49%|████▉     | 903/1848 [5:00:00<5:16:16, 20.08s/it]
                                                      

 49%|████▉     | 903/1848 [5:00:00<5:16:16, 20.08s/it]
 49%|████▉     | 904/1848 [5:00:20<5:15:16, 20.04s/it]
                                                      

 49%|████▉     | 904/1848 [5:00:20<5:15:16, 20.04s/it]
 49%|████▉     | 905/1848 [5:00:40<5:14:14, 19.99s/it]
                                                      
{'loss': 1.1341, 'learning_rate': 8.064772727272729e-06, 'epoch': 1.28}
+{'loss': 1.4785, 'learning_rate': 8.057142857142857e-06, 'epoch': 1.29}
+{'loss': 1.2785, 'learning_rate': 8.049512987012988e-06, 'epoch': 1.29}
+{'loss': 1.254, 'learning_rate': 8.041883116883118e-06, 'epoch': 1.29}
+{'loss': 1.1968, 'learning_rate': 8.034253246753247e-06, 'epoch': 1.29}
+{'loss': 1.2362, 'learning_rate': 8.026623376623376e-06, 'epoch': 1.29}
+{'loss': 0.9649, 'learning_rate': 8.018993506493507e-06, 'epoch': 1.29}
+{'loss': 1.3062, 'learning_rate': 8.011363636363637e-06, 'epoch': 1.3}
+{'loss': 1.2303, 'learning_rate': 8.003733766233766e-06, 'epoch': 1.3}
+{'loss': 1.204, 'learning_rate': 7.996103896103896e-06, 'epoch': 1.3}
+{'loss': 1.1377, 'learning_rate': 7.988474025974027e-06, 'epoch': 1.3}
+{'loss': 1.1156, 'learning_rate': 7.980844155844156e-06, 'epoch': 1.3}
+{'loss': 1.5326, 'learning_rate': 7.973214285714286e-06, 'epoch': 1.3}
+{'loss': 1.2169, 'learning_rate': 7.965584415584417e-06, 'epoch': 1.31}
+{'loss': 1.2056, 'learning_rate': 7.957954545454547e-06, 'epoch': 1.31}
+{'loss': 1.1859, 'learning_rate': 7.950324675324676e-06, 'epoch': 1.31}
+{'loss': 1.2824, 'learning_rate': 7.942694805194805e-06, 'epoch': 1.31}
+{'loss': 1.2047, 'learning_rate': 7.935064935064935e-06, 'epoch': 1.31}
+{'loss': 1.5401, 'learning_rate': 7.927435064935064e-06, 'epoch': 1.31}
+{'loss': 1.2289, 'learning_rate': 7.919805194805195e-06, 'epoch': 1.31}
+{'loss': 1.3026, 'learning_rate': 7.912175324675325e-06, 'epoch': 1.32}
+{'loss': 1.1078, 'learning_rate': 7.904545454545454e-06, 'epoch': 1.32}
+{'loss': 1.2094, 'learning_rate': 7.896915584415584e-06, 'epoch': 1.32}
+{'loss': 1.2961, 'learning_rate': 7.889285714285715e-06, 'epoch': 1.32}
+{'loss': 1.1502, 'learning_rate': 7.881655844155845e-06, 'epoch': 1.32}
+{'loss': 1.0864, 'learning_rate': 7.874025974025974e-06, 'epoch': 1.32}
+{'loss': 1.1561, 'learning_rate': 7.866396103896105e-06, 'epoch': 1.33}
+{'loss': 1.2993, 'learning_rate': 7.858766233766235e-06, 'epoch': 1.33}
+{'loss': 1.1748, 'learning_rate': 7.851136363636364e-06, 'epoch': 1.33}
+{'loss': 1.2056, 'learning_rate': 7.843506493506493e-06, 'epoch': 1.33}
+{'loss': 1.2172, 'learning_rate': 7.835876623376623e-06, 'epoch': 1.33}
+{'loss': 1.29, 'learning_rate': 7.828246753246754e-06, 'epoch': 1.33}
+{'loss': 1.2049, 'learning_rate': 7.820616883116883e-06, 'epoch': 1.34}
+{'loss': 1.1793, 'learning_rate': 7.812987012987013e-06, 'epoch': 1.34}
+{'loss': 1.1376, 'learning_rate': 7.805357142857144e-06, 'epoch': 1.34}
+{'loss': 1.1068, 'learning_rate': 7.797727272727272e-06, 'epoch': 1.34}
+{'loss': 1.1335, 'learning_rate': 7.790097402597403e-06, 'epoch': 1.34}
+{'loss': 1.2551, 'learning_rate': 7.782467532467533e-06, 'epoch': 1.34}
+{'loss': 1.1892, 'learning_rate': 7.774837662337664e-06, 'epoch': 1.35}
+{'loss': 1.0798, 'learning_rate': 7.767207792207793e-06, 'epoch': 1.35}
+{'loss': 1.2086, 'learning_rate': 7.759577922077923e-06, 'epoch': 1.35}
+{'loss': 1.2483, 'learning_rate': 7.751948051948052e-06, 'epoch': 1.35}
+{'loss': 1.176, 'learning_rate': 7.74431818181818e-06, 'epoch': 1.35}
+{'loss': 1.1445, 'learning_rate': 7.736688311688311e-06, 'epoch': 1.35}
+{'loss': 1.2085, 'learning_rate': 7.729058441558442e-06, 'epoch': 1.36}
+{'loss': 1.2948, 'learning_rate': 7.721428571428572e-06, 'epoch': 1.36}
+{'loss': 1.4978, 'learning_rate': 7.713798701298701e-06, 'epoch': 1.36}
+{'loss': 1.2588, 'learning_rate': 7.706168831168832e-06, 'epoch': 1.36}
+{'loss': 1.1356, 'learning_rate': 7.698538961038962e-06, 'epoch': 1.36}
+{'loss': 1.2366, 'learning_rate': 7.690909090909091e-06, 'epoch': 1.36}
+{'loss': 1.2854, 'learning_rate': 7.683279220779221e-06, 'epoch': 1.37}
+{'loss': 1.3647, 'learning_rate': 7.675649350649352e-06, 'epoch': 1.37}
+{'loss': 1.3014, 'learning_rate': 7.66801948051948e-06, 'epoch': 1.37}
+{'loss': 1.1258, 'learning_rate': 7.660389610389611e-06, 'epoch': 1.37}
+{'loss': 1.2919, 'learning_rate': 7.65275974025974e-06, 'epoch': 1.37}
+{'loss': 1.138, 'learning_rate': 7.64512987012987e-06, 'epoch': 1.37}
+{'loss': 1.0783, 'learning_rate': 7.6375e-06, 'epoch': 1.38}
+{'loss': 1.1984, 'learning_rate': 7.62987012987013e-06, 'epoch': 1.38}
+{'loss': 1.1032, 'learning_rate': 7.62224025974026e-06, 'epoch': 1.38}
+{'loss': 1.2318, 'learning_rate': 7.614610389610389e-06, 'epoch': 1.38}
+{'loss': 1.2921, 'learning_rate': 7.60698051948052e-06, 'epoch': 1.38}
+{'loss': 1.1886, 'learning_rate': 7.59935064935065e-06, 'epoch': 1.38}
+{'loss': 1.194, 'learning_rate': 7.59172077922078e-06, 'epoch': 1.38}
+{'loss': 1.2682, 'learning_rate': 7.5840909090909086e-06, 'epoch': 1.39}
+{'loss': 1.2802, 'learning_rate': 7.576461038961039e-06, 'epoch': 1.39}
+{'loss': 1.1854, 'learning_rate': 7.5688311688311696e-06, 'epoch': 1.39}
+{'loss': 1.3474, 'learning_rate': 7.561201298701298e-06, 'epoch': 1.39}
+{'loss': 1.4048, 'learning_rate': 7.553571428571429e-06, 'epoch': 1.39}
+{'loss': 1.0848, 'learning_rate': 7.545941558441559e-06, 'epoch': 1.39}
+{'loss': 1.1738, 'learning_rate': 7.538311688311689e-06, 'epoch': 1.4}
+{'loss': 1.1978, 'learning_rate': 7.530681818181818e-06, 'epoch': 1.4}
+{'loss': 1.2023, 'learning_rate': 7.523051948051948e-06, 'epoch': 1.4}
+{'loss': 1.4352, 'learning_rate': 7.515422077922079e-06, 'epoch': 1.4}
+{'loss': 1.1163, 'learning_rate': 7.507792207792208e-06, 'epoch': 1.4}
+{'loss': 1.3311, 'learning_rate': 7.500162337662338e-06, 'epoch': 1.4}
+{'loss': 1.0629, 'learning_rate': 7.492532467532468e-06, 'epoch': 1.41}
+{'loss': 1.1268, 'learning_rate': 7.484902597402598e-06, 'epoch': 1.41}
+{'loss': 1.0461, 'learning_rate': 7.477272727272727e-06, 'epoch': 1.41}
+{'loss': 1.3333, 'learning_rate': 7.4696428571428576e-06, 'epoch': 1.41}
+{'loss': 1.2214, 'learning_rate': 7.462012987012988e-06, 'epoch': 1.41}
+{'loss': 1.238, 'learning_rate': 7.454383116883117e-06, 'epoch': 1.41}
+{'loss': 1.2533, 'learning_rate': 7.4467532467532465e-06, 'epoch': 1.42}
+{'loss': 1.2074, 'learning_rate': 7.439123376623377e-06, 'epoch': 1.42}
+{'loss': 1.1031, 'learning_rate': 7.4314935064935075e-06, 'epoch': 1.42}
+{'loss': 1.3408, 'learning_rate': 7.423863636363636e-06, 'epoch': 1.42}
+{'loss': 1.2447, 'learning_rate': 7.416233766233767e-06, 'epoch': 1.42}
+{'loss': 1.3305, 'learning_rate': 7.408603896103897e-06, 'epoch': 1.42}
+{'loss': 1.1175, 'learning_rate': 7.400974025974026e-06, 'epoch': 1.43}
+{'loss': 1.1452, 'learning_rate': 7.393344155844156e-06, 'epoch': 1.43}
+{'loss': 1.1333, 'learning_rate': 7.385714285714286e-06, 'epoch': 1.43}
+{'loss': 1.1066, 'learning_rate': 7.378084415584415e-06, 'epoch': 1.43}
+{'loss': 1.2183, 'learning_rate': 7.3704545454545456e-06, 'epoch': 1.43}
+{'loss': 1.1068, 'learning_rate': 7.362824675324676e-06, 'epoch': 1.43}
+{'loss': 1.1002, 'learning_rate': 7.355194805194806e-06, 'epoch': 1.44}
+{'loss': 1.2151, 'learning_rate': 7.3475649350649345e-06, 'epoch': 1.44}
+{'loss': 1.06, 'learning_rate': 7.339935064935065e-06, 'epoch': 1.44}
+{'loss': 1.2025, 'learning_rate': 7.3323051948051955e-06, 'epoch': 1.44}
+{'loss': 1.3258, 'learning_rate': 7.324675324675324e-06, 'epoch': 1.44}
+{'loss': 1.3693, 'learning_rate': 7.317045454545455e-06, 'epoch': 1.44}
+{'loss': 1.3617, 'learning_rate': 7.3094155844155845e-06, 'epoch': 1.44}
+{'loss': 1.3646, 'learning_rate': 7.301785714285715e-06, 'epoch': 1.45}
+{'loss': 1.4634, 'learning_rate': 7.294155844155844e-06, 'epoch': 1.45}
+{'loss': 1.3254, 'learning_rate': 7.286525974025974e-06, 'epoch': 1.45}
+{'loss': 1.3256, 'learning_rate': 7.278896103896105e-06, 'epoch': 1.45}
+{'loss': 1.2279, 'learning_rate': 7.271266233766234e-06, 'epoch': 1.45}
+{'loss': 1.4127, 'learning_rate': 7.263636363636364e-06, 'epoch': 1.45}
+{'loss': 1.3893, 'learning_rate': 7.256006493506494e-06, 'epoch': 1.46}
+{'loss': 1.0239, 'learning_rate': 7.248376623376624e-06, 'epoch': 1.46}
+{'loss': 1.2108, 'learning_rate': 7.240746753246753e-06, 'epoch': 1.46}
+{'loss': 1.1374, 'learning_rate': 7.2331168831168835e-06, 'epoch': 1.46}
+{'loss': 1.0872, 'learning_rate': 7.225487012987014e-06, 'epoch': 1.46}
+{'loss': 1.2094, 'learning_rate': 7.217857142857143e-06, 'epoch': 1.46}
+{'loss': 1.1462, 'learning_rate': 7.2102272727272725e-06, 'epoch': 1.47}
+{'loss': 1.1183, 'learning_rate': 7.202597402597403e-06, 'epoch': 1.47}
+
 49%|████▉     | 905/1848 [5:00:40<5:14:14, 19.99s/it]
 49%|████▉     | 906/1848 [5:01:00<5:13:23, 19.96s/it]
                                                      

 49%|████▉     | 906/1848 [5:01:00<5:13:23, 19.96s/it]
 49%|████▉     | 907/1848 [5:01:20<5:13:02, 19.96s/it]
                                                      

 49%|████▉     | 907/1848 [5:01:20<5:13:02, 19.96s/it]
 49%|████▉     | 908/1848 [5:01:40<5:12:35, 19.95s/it]
                                                      

 49%|████▉     | 908/1848 [5:01:40<5:12:35, 19.95s/it]
 49%|████▉     | 909/1848 [5:01:59<5:12:12, 19.95s/it]
                                                      

 49%|████▉     | 909/1848 [5:01:59<5:12:12, 19.95s/it]
 49%|████▉     | 910/1848 [5:02:19<5:11:49, 19.95s/it]
                                                      

 49%|████▉     | 910/1848 [5:02:19<5:11:49, 19.95s/it]
 49%|████▉     | 911/1848 [5:02:39<5:11:13, 19.93s/it]
                                                      

 49%|████▉     | 911/1848 [5:02:39<5:11:13, 19.93s/it]
 49%|████▉     | 912/1848 [5:02:59<5:10:42, 19.92s/it]
                                                      

 49%|████▉     | 912/1848 [5:02:59<5:10:42, 19.92s/it]
 49%|████▉     | 913/1848 [5:03:19<5:10:37, 19.93s/it]
                                                      

 49%|████▉     | 913/1848 [5:03:19<5:10:37, 19.93s/it]
 49%|████▉     | 914/1848 [5:03:39<5:10:19, 19.94s/it]
                                                      

 49%|████▉     | 914/1848 [5:03:39<5:10:19, 19.94s/it]
 50%|████▉     | 915/1848 [5:03:59<5:10:05, 19.94s/it]
                                                      

 50%|████▉     | 915/1848 [5:03:59<5:10:05, 19.94s/it]
 50%|████▉     | 916/1848 [5:04:19<5:09:45, 19.94s/it]
                                                      

 50%|████▉     | 916/1848 [5:04:19<5:09:45, 19.94s/it]
 50%|████▉     | 917/1848 [5:04:39<5:09:15, 19.93s/it]
                                                      

 50%|████▉     | 917/1848 [5:04:39<5:09:15, 19.93s/it]
 50%|████▉     | 918/1848 [5:04:59<5:09:18, 19.96s/it]
                                                      

 50%|████▉     | 918/1848 [5:04:59<5:09:18, 19.96s/it]
 50%|████▉     | 919/1848 [5:05:19<5:09:12, 19.97s/it]
                                                      

 50%|████▉     | 919/1848 [5:05:19<5:09:12, 19.97s/it]
 50%|████▉     | 920/1848 [5:05:39<5:08:50, 19.97s/it]
                                                      

 50%|████▉     | 920/1848 [5:05:39<5:08:50, 19.97s/it]
 50%|████▉     | 921/1848 [5:05:59<5:08:05, 19.94s/it]
                                                      

 50%|████▉     | 921/1848 [5:05:59<5:08:05, 19.94s/it]
 50%|████▉     | 922/1848 [5:06:19<5:08:18, 19.98s/it]
                                                      

 50%|████▉     | 922/1848 [5:06:19<5:08:18, 19.98s/it]
 50%|████▉     | 923/1848 [5:06:39<5:07:35, 19.95s/it]
                                                      

 50%|████▉     | 923/1848 [5:06:39<5:07:35, 19.95s/it]
 50%|█████     | 924/1848 [5:06:59<5:07:09, 19.95s/it]
                                                      

 50%|█████     | 924/1848 [5:06:59<5:07:09, 19.95s/it]
 50%|█████     | 925/1848 [5:07:19<5:06:56, 19.95s/it]
                                                      

 50%|█████     | 925/1848 [5:07:19<5:06:56, 19.95s/it]
 50%|█████     | 926/1848 [5:07:39<5:06:45, 19.96s/it]
                                                      

 50%|█████     | 926/1848 [5:07:39<5:06:45, 19.96s/it]
 50%|█████     | 927/1848 [5:07:59<5:06:26, 19.96s/it]
                                                      

 50%|█████     | 927/1848 [5:07:59<5:06:26, 19.96s/it]
 50%|█████     | 928/1848 [5:08:19<5:05:57, 19.95s/it]
                                                      

 50%|█████     | 928/1848 [5:08:19<5:05:57, 19.95s/it]
 50%|█████     | 929/1848 [5:08:38<5:05:46, 19.96s/it]
                                                      

 50%|█████     | 929/1848 [5:08:38<5:05:46, 19.96s/it]
 50%|█████     | 930/1848 [5:08:58<5:05:25, 19.96s/it]
                                                      

 50%|█████     | 930/1848 [5:08:58<5:05:25, 19.96s/it]
 50%|█████     | 931/1848 [5:09:18<5:05:10, 19.97s/it]
                                                      

 50%|█████     | 931/1848 [5:09:18<5:05:10, 19.97s/it]
 50%|█████     | 932/1848 [5:09:38<5:04:49, 19.97s/it]
                                                      

 50%|█████     | 932/1848 [5:09:38<5:04:49, 19.97s/it]
 50%|█████     | 933/1848 [5:09:58<5:04:18, 19.95s/it]
                                                      

 50%|█████     | 933/1848 [5:09:58<5:04:18, 19.95s/it]
 51%|█████     | 934/1848 [5:10:18<5:03:39, 19.93s/it]
                                                      

 51%|█████     | 934/1848 [5:10:18<5:03:39, 19.93s/it]
 51%|█████     | 935/1848 [5:10:38<5:03:35, 19.95s/it]
                                                      

 51%|█████     | 935/1848 [5:10:38<5:03:35, 19.95s/it]
 51%|█████     | 936/1848 [5:10:58<5:03:00, 19.94s/it]
                                                      

 51%|█████     | 936/1848 [5:10:58<5:03:00, 19.94s/it]
 51%|█████     | 937/1848 [5:11:18<5:02:49, 19.94s/it]
                                                      

 51%|█████     | 937/1848 [5:11:18<5:02:49, 19.94s/it]
 51%|█████     | 938/1848 [5:11:38<5:02:25, 19.94s/it]
                                                      

 51%|█████     | 938/1848 [5:11:38<5:02:25, 19.94s/it]
 51%|█████     | 939/1848 [5:11:58<5:02:22, 19.96s/it]
                                                      

 51%|█████     | 939/1848 [5:11:58<5:02:22, 19.96s/it]
 51%|█████     | 940/1848 [5:12:18<5:02:14, 19.97s/it]
                                                      

 51%|█████     | 940/1848 [5:12:18<5:02:14, 19.97s/it]
 51%|█████     | 941/1848 [5:12:38<5:01:49, 19.97s/it]
                                                      

 51%|█████     | 941/1848 [5:12:38<5:01:49, 19.97s/it]
 51%|█████     | 942/1848 [5:12:58<5:01:29, 19.97s/it]
                                                      

 51%|█████     | 942/1848 [5:12:58<5:01:29, 19.97s/it]
 51%|█████     | 943/1848 [5:13:18<5:01:09, 19.97s/it]
                                                      

 51%|█████     | 943/1848 [5:13:18<5:01:09, 19.97s/it]
 51%|█████     | 944/1848 [5:13:38<5:00:38, 19.95s/it]
                                                      

 51%|█████     | 944/1848 [5:13:38<5:00:38, 19.95s/it]
 51%|█████     | 945/1848 [5:13:58<5:00:23, 19.96s/it]
                                                      

 51%|█████     | 945/1848 [5:13:58<5:00:23, 19.96s/it]
 51%|█████     | 946/1848 [5:14:18<5:00:30, 19.99s/it]
                                                      

 51%|█████     | 946/1848 [5:14:18<5:00:30, 19.99s/it]
 51%|█████     | 947/1848 [5:14:38<5:00:10, 19.99s/it]
                                                      

 51%|█████     | 947/1848 [5:14:38<5:00:10, 19.99s/it]
 51%|█████▏    | 948/1848 [5:14:58<4:59:32, 19.97s/it]
                                                      

 51%|█████▏    | 948/1848 [5:14:58<4:59:32, 19.97s/it]
 51%|█████▏    | 949/1848 [5:15:18<4:59:21, 19.98s/it]
                                                      

 51%|█████▏    | 949/1848 [5:15:18<4:59:21, 19.98s/it]
 51%|█████▏    | 950/1848 [5:15:38<4:58:50, 19.97s/it]
                                                      

 51%|█████▏    | 950/1848 [5:15:38<4:58:50, 19.97s/it]
 51%|█████▏    | 951/1848 [5:15:58<4:58:24, 19.96s/it]
                                                      

 51%|█████▏    | 951/1848 [5:15:58<4:58:24, 19.96s/it]
 52%|█████▏    | 952/1848 [5:16:18<4:58:16, 19.97s/it]
                                                      

 52%|████���▏    | 952/1848 [5:16:18<4:58:16, 19.97s/it]
 52%|█████▏    | 953/1848 [5:16:38<4:58:07, 19.99s/it]
                                                      

 52%|█████▏    | 953/1848 [5:16:38<4:58:07, 19.99s/it]
 52%|█████▏    | 954/1848 [5:16:58<4:58:07, 20.01s/it]
                                                      

 52%|█████▏    | 954/1848 [5:16:58<4:58:07, 20.01s/it]
 52%|█████▏    | 955/1848 [5:17:18<4:57:44, 20.00s/it]
                                                      

 52%|█████▏    | 955/1848 [5:17:18<4:57:44, 20.00s/it]
 52%|█████▏    | 956/1848 [5:17:38<4:57:07, 19.99s/it]
                                                      

 52%|█████▏    | 956/1848 [5:17:38<4:57:07, 19.99s/it]
 52%|█████▏    | 957/1848 [5:17:58<4:56:56, 20.00s/it]
                                                      

 52%|█████▏    | 957/1848 [5:17:58<4:56:56, 20.00s/it]
 52%|█████▏    | 958/1848 [5:18:18<4:56:07, 19.96s/it]
                                                      

 52%|█████▏    | 958/1848 [5:18:18<4:56:07, 19.96s/it]
 52%|█████▏    | 959/1848 [5:18:38<4:55:40, 19.96s/it]
                                                      

 52%|█████▏    | 959/1848 [5:18:38<4:55:40, 19.96s/it]
 52%|█████▏    | 960/1848 [5:18:57<4:55:21, 19.96s/it]
                                                      

 52%|█████▏    | 960/1848 [5:18:57<4:55:21, 19.96s/it]
 52%|█████▏    | 961/1848 [5:19:17<4:55:04, 19.96s/it]
                                                      

 52%|█████▏    | 961/1848 [5:19:17<4:55:04, 19.96s/it]
 52%|█████▏    | 962/1848 [5:19:37<4:54:36, 19.95s/it]
                                                      

 52%|█████▏    | 962/1848 [5:19:37<4:54:36, 19.95s/it]
 52%|█████▏    | 963/1848 [5:19:57<4:54:14, 19.95s/it]
                                                      

 52%|█████▏    | 963/1848 [5:19:57<4:54:14, 19.95s/it]
 52%|█████▏    | 964/1848 [5:20:17<4:54:11, 19.97s/it]
                                                      

 52%|█████▏    | 964/1848 [5:20:17<4:54:11, 19.97s/it]
 52%|█████▏    | 965/1848 [5:20:37<4:53:55, 19.97s/it]
                                                      

 52%|█████▏    | 965/1848 [5:20:37<4:53:55, 19.97s/it]
 52%|█████▏    | 966/1848 [5:20:57<4:53:20, 19.96s/it]
                                                      

 52%|█████▏    | 966/1848 [5:20:57<4:53:20, 19.96s/it]
 52%|█████▏    | 967/1848 [5:21:17<4:53:07, 19.96s/it]
                                                      

 52%|█████▏    | 967/1848 [5:21:17<4:53:07, 19.96s/it]
 52%|█████▏    | 968/1848 [5:21:37<4:53:04, 19.98s/it]
                                                      

 52%|█████▏    | 968/1848 [5:21:37<4:53:04, 19.98s/it]
 52%|█████▏    | 969/1848 [5:21:57<4:52:29, 19.97s/it]
                                                      

 52%|█████▏    | 969/1848 [5:21:57<4:52:29, 19.97s/it]
 52%|█████▏    | 970/1848 [5:22:17<4:52:09, 19.97s/it]
                                                      

 52%|█████▏    | 970/1848 [5:22:17<4:52:09, 19.97s/it]
 53%|█████▎    | 971/1848 [5:22:37<4:51:35, 19.95s/it]
                                                      

 53%|█████▎    | 971/1848 [5:22:37<4:51:35, 19.95s/it]
 53%|█████▎    | 972/1848 [5:22:57<4:51:16, 19.95s/it]
                                                      

 53%|█████▎    | 972/1848 [5:22:57<4:51:16, 19.95s/it]
 53%|█████▎    | 973/1848 [5:23:17<4:51:09, 19.97s/it]
                                                      

 53%|█████▎    | 973/1848 [5:23:17<4:51:09, 19.97s/it]
 53%|█████▎    | 974/1848 [5:23:37<4:50:37, 19.95s/it]
                                                      

 53%|█████▎    | 974/1848 [5:23:37<4:50:37, 19.95s/it]
 53%|█████▎    | 975/1848 [5:23:57<4:50:04, 19.94s/it]
                                                      

 53%|█████▎    | 975/1848 [5:23:57<4:50:04, 19.94s/it]
 53%|█████▎    | 976/1848 [5:24:17<4:50:05, 19.96s/it]
                                                      

 53%|█████▎    | 976/1848 [5:24:17<4:50:05, 19.96s/it]
 53%|█████▎    | 977/1848 [5:24:37<4:49:58, 19.98s/it]
                                                      

 53%|█████▎    | 977/1848 [5:24:37<4:49:58, 19.98s/it]
 53%|█████▎    | 978/1848 [5:24:57<4:49:23, 19.96s/it]
                                                      

 53%|█████▎    | 978/1848 [5:24:57<4:49:23, 19.96s/it]
 53%|█████▎    | 979/1848 [5:25:17<4:49:14, 19.97s/it]
                                                      

 53%|█████▎    | 979/1848 [5:25:17<4:49:14, 19.97s/it]
 53%|█████▎    | 980/1848 [5:25:37<4:49:22, 20.00s/it]
                                                      

 53%|█████▎    | 980/1848 [5:25:37<4:49:22, 20.00s/it]
 53%|█████▎    | 981/1848 [5:25:57<4:49:09, 20.01s/it]
                                                      

 53%|█████▎    | 981/1848 [5:25:57<4:49:09, 20.01s/it]
 53%|█████▎    | 982/1848 [5:26:17<4:48:37, 20.00s/it]
                                                      

 53%|█████▎    | 982/1848 [5:26:17<4:48:37, 20.00s/it]
 53%|█████▎    | 983/1848 [5:26:37<4:48:29, 20.01s/it]
                                                      

 53%|█████▎    | 983/1848 [5:26:37<4:48:29, 20.01s/it]
 53%|█████▎    | 984/1848 [5:26:57<4:48:04, 20.01s/it]
                                                      

 53%|█████▎    | 984/1848 [5:26:57<4:48:04, 20.01s/it]
 53%|█████▎    | 985/1848 [5:27:17<4:47:30, 19.99s/it]
                                                      

 53%|█████▎    | 985/1848 [5:27:17<4:47:30, 19.99s/it]
 53%|█████▎    | 986/1848 [5:27:37<4:47:16, 20.00s/it]
                                                      

 53%|█████▎    | 986/1848 [5:27:37<4:47:16, 20.00s/it]
 53%|█████▎    | 987/1848 [5:27:57<4:46:46, 19.98s/it]
                                                      

 53%|█████▎    | 987/1848 [5:27:57<4:46:46, 19.98s/it]
 53%|█████▎    | 988/1848 [5:28:17<4:46:18, 19.97s/it]
                                                      

 53%|█████▎    | 988/1848 [5:28:17<4:46:18, 19.97s/it]
 54%|█████▎    | 989/1848 [5:28:37<4:46:10, 19.99s/it]
                                                      

 54%|█████▎    | 989/1848 [5:28:37<4:46:10, 19.99s/it]
 54%|█████▎    | 990/1848 [5:28:57<4:45:39, 19.98s/it]
                                                      

 54%|█████▎    | 990/1848 [5:28:57<4:45:39, 19.98s/it]
 54%|█████▎    | 991/1848 [5:29:17<4:44:57, 19.95s/it]
                                                      

 54%|█████▎    | 991/1848 [5:29:17<4:44:57, 19.95s/it]
 54%|█████▎    | 992/1848 [5:29:37<4:44:57, 19.97s/it]
                                                      

 54%|█████▎    | 992/1848 [5:29:37<4:44:57, 19.97s/it]
 54%|█████▎    | 993/1848 [5:29:57<4:44:35, 19.97s/it]
                                                      

 54%|█████▎    | 993/1848 [5:29:57<4:44:35, 19.97s/it]
 54%|█████▍    | 994/1848 [5:30:17<4:44:21, 19.98s/it]
                                                      

 54%|█████▍    | 994/1848 [5:30:17<4:44:21, 19.98s/it]
 54%|█████▍    | 995/1848 [5:30:37<4:44:00, 19.98s/it]
                                                      

 54%|█████▍    | 995/1848 [5:30:37<4:44:00, 19.98s/it]
 54%|█████▍    | 996/1848 [5:30:57<4:43:39, 19.98s/it]
                                                      

 54%|█████▍    | 996/1848 [5:30:57<4:43:39, 19.98s/it]
 54%|█████▍    | 997/1848 [5:31:16<4:43:16, 19.97s/it]
                                                      

 54%|█████▍    | 997/1848 [5:31:16<4:43:16, 19.97s/it]
 54%|█████▍    | 998/1848 [5:31:36<4:42:45, 19.96s/it]
                                                      

 54%|█████▍    | 998/1848 [5:31:36<4:42:45, 19.96s/it]
 54%|█████▍    | 999/1848 [5:31:56<4:42:12, 19.94s/it]
                                                      

 54%|█████▍    | 999/1848 [5:31:56<4:42:12, 19.94s/it]
 54%|█████▍    | 1000/1848 [5:32:16<4:42:08, 19.96s/it]
                                                       

 54%|█████▍    | 1000/1848 [5:32:16<4:42:08, 19.96s/it]
 54%|█████▍    | 1001/1848 [5:32:37<4:45:27, 20.22s/it]
                                                       

 54%|█████▍    | 1001/1848 [5:32:37<4:45:27, 20.22s/it]
 54%|█████▍    | 1002/1848 [5:32:57<4:44:06, 20.15s/it]
                                                       

 54%|█████▍    | 1002/1848 [5:32:57<4:44:06, 20.15s/it]
 54%|█████▍    | 1003/1848 [5:33:17<4:42:41, 20.07s/it]
                                                       

 54%|█████▍    | 1003/1848 [5:33:17<4:42:41, 20.07s/it]
 54%|█████▍    | 1004/1848 [5:33:37<4:41:34, 20.02s/it]
                                                       

 54%|█████▍    | 1004/1848 [5:33:37<4:41:34, 20.02s/it]
 54%|█████▍    | 1005/1848 [5:33:57<4:40:51, 19.99s/it]
                                                       

 54%|█████▍    | 1005/1848 [5:33:57<4:40:51, 19.99s/it]
 54%|█████▍    | 1006/1848 [5:34:17<4:40:07, 19.96s/it]
                                                       

 54%|█████▍    | 1006/1848 [5:34:17<4:40:07, 19.96s/it]
 54%|█████▍    | 1007/1848 [5:34:37<4:39:46, 19.96s/it]
                                                       

 54%|█████▍    | 1007/1848 [5:34:37<4:39:46, 19.96s/it]
 55%|█████▍    | 1008/1848 [5:34:57<4:39:49, 19.99s/it]
                                                       

 55%|█████▍    | 1008/1848 [5:34:57<4:39:49, 19.99s/it]
 55%|█████▍    | 1009/1848 [5:35:17<4:39:20, 19.98s/it]
                                                       

 55%|█████▍    | 1009/1848 [5:35:17<4:39:20, 19.98s/it]
 55%|█████▍    | 1010/1848 [5:35:37<4:39:13, 19.99s/it]
                                                       

 55%|█████▍    | 1010/1848 [5:35:37<4:39:13, 19.99s/it]
 55%|█████▍    | 1011/1848 [5:35:57<4:38:35, 19.97s/it]
                                                       

 55%|█████▍    | 1011/1848 [5:35:57<4:38:35, 19.97s/it]
 55%|█████▍    | 1012/1848 [5:36:17<4:38:21, 19.98s/it]
                                                       

 55%|█████▍    | 1012/1848 [5:36:17<4:38:21, 19.98s/it]
 55%|█████▍    | 1013/1848 [5:36:37<4:38:07, 19.98s/it]
                                                       

 55%|█████▍    | 1013/1848 [5:36:37<4:38:07, 19.98s/it]
 55%|█████▍    | 1014/1848 [5:36:57<4:37:50, 19.99s/it]
                                                       

 55%|█████▍    | 1014/1848 [5:36:57<4:37:50, 19.99s/it]
 55%|█████▍    | 1015/1848 [5:37:17<4:37:32, 19.99s/it]
                                                       

 55%|█████▍    | 1015/1848 [5:37:17<4:37:32, 19.99s/it]
 55%|█████▍    | 1016/1848 [5:37:37<4:36:46, 19.96s/it]
                                                       

 55%|█████▍    | 1016/1848 [5:37:37<4:36:46, 19.96s/it]
 55%|█████▌    | 1017/1848 [5:37:56<4:36:25, 19.96s/it]
                                                       

 55%|█████▌    | 1017/1848 [5:37:56<4:36:25, 19.96s/it]
 55%|█████▌    | 1018/1848 [5:38:16<4:36:03, 19.96s/it]
                                                       

 55%|█████▌    | 1018/1848 [5:38:16<4:36:03, 19.96s/it]
 55%|█████▌    | 1019/1848 [5:38:36<4:35:37, 19.95s/it]
                                                       
{'loss': 1.4544, 'learning_rate': 7.1949675324675335e-06, 'epoch': 1.47}
+{'loss': 1.1764, 'learning_rate': 7.187337662337662e-06, 'epoch': 1.47}
+{'loss': 1.1377, 'learning_rate': 7.179707792207793e-06, 'epoch': 1.47}
+{'loss': 1.3966, 'learning_rate': 7.172077922077923e-06, 'epoch': 1.47}
+{'loss': 1.4155, 'learning_rate': 7.164448051948051e-06, 'epoch': 1.48}
+{'loss': 1.5016, 'learning_rate': 7.156818181818182e-06, 'epoch': 1.48}
+{'loss': 1.2639, 'learning_rate': 7.149188311688312e-06, 'epoch': 1.48}
+{'loss': 1.2035, 'learning_rate': 7.141558441558441e-06, 'epoch': 1.48}
+{'loss': 1.2106, 'learning_rate': 7.1339285714285716e-06, 'epoch': 1.48}
+{'loss': 1.269, 'learning_rate': 7.126298701298702e-06, 'epoch': 1.48}
+{'loss': 1.1679, 'learning_rate': 7.118668831168832e-06, 'epoch': 1.49}
+{'loss': 1.1454, 'learning_rate': 7.1110389610389605e-06, 'epoch': 1.49}
+{'loss': 1.1284, 'learning_rate': 7.103409090909091e-06, 'epoch': 1.49}
+{'loss': 1.2083, 'learning_rate': 7.0957792207792215e-06, 'epoch': 1.49}
+{'loss': 1.2754, 'learning_rate': 7.08814935064935e-06, 'epoch': 1.49}
+{'loss': 1.2012, 'learning_rate': 7.080519480519481e-06, 'epoch': 1.49}
+{'loss': 1.2925, 'learning_rate': 7.0728896103896105e-06, 'epoch': 1.5}
+{'loss': 1.1588, 'learning_rate': 7.065259740259741e-06, 'epoch': 1.5}
+{'loss': 1.2532, 'learning_rate': 7.05762987012987e-06, 'epoch': 1.5}
+{'loss': 1.3521, 'learning_rate': 7.05e-06, 'epoch': 1.5}
+{'loss': 1.3238, 'learning_rate': 7.04237012987013e-06, 'epoch': 1.5}
+{'loss': 1.0931, 'learning_rate': 7.03474025974026e-06, 'epoch': 1.5}
+{'loss': 0.985, 'learning_rate': 7.02711038961039e-06, 'epoch': 1.5}
+{'loss': 1.26, 'learning_rate': 7.01948051948052e-06, 'epoch': 1.51}
+{'loss': 1.1819, 'learning_rate': 7.011850649350649e-06, 'epoch': 1.51}
+{'loss': 1.1246, 'learning_rate': 7.00422077922078e-06, 'epoch': 1.51}
+{'loss': 1.3913, 'learning_rate': 6.9965909090909095e-06, 'epoch': 1.51}
+{'loss': 1.5025, 'learning_rate': 6.988961038961039e-06, 'epoch': 1.51}
+{'loss': 1.3858, 'learning_rate': 6.98133116883117e-06, 'epoch': 1.51}
+{'loss': 1.2936, 'learning_rate': 6.9737012987012985e-06, 'epoch': 1.52}
+{'loss': 1.1908, 'learning_rate': 6.966071428571429e-06, 'epoch': 1.52}
+{'loss': 1.1105, 'learning_rate': 6.958441558441559e-06, 'epoch': 1.52}
+{'loss': 1.1334, 'learning_rate': 6.950811688311688e-06, 'epoch': 1.52}
+{'loss': 1.313, 'learning_rate': 6.943181818181819e-06, 'epoch': 1.52}
+{'loss': 1.0119, 'learning_rate': 6.9355519480519484e-06, 'epoch': 1.52}
+{'loss': 1.142, 'learning_rate': 6.927922077922078e-06, 'epoch': 1.53}
+{'loss': 1.2191, 'learning_rate': 6.920292207792208e-06, 'epoch': 1.53}
+{'loss': 1.0899, 'learning_rate': 6.912662337662338e-06, 'epoch': 1.53}
+{'loss': 1.2083, 'learning_rate': 6.905032467532468e-06, 'epoch': 1.53}
+{'loss': 1.3271, 'learning_rate': 6.8974025974025975e-06, 'epoch': 1.53}
+{'loss': 1.2596, 'learning_rate': 6.889772727272728e-06, 'epoch': 1.53}
+{'loss': 1.1775, 'learning_rate': 6.882142857142857e-06, 'epoch': 1.54}
+{'loss': 1.3662, 'learning_rate': 6.874512987012987e-06, 'epoch': 1.54}
+{'loss': 1.1633, 'learning_rate': 6.866883116883117e-06, 'epoch': 1.54}
+{'loss': 1.4245, 'learning_rate': 6.859253246753247e-06, 'epoch': 1.54}
+{'loss': 1.1142, 'learning_rate': 6.851623376623377e-06, 'epoch': 1.54}
+{'loss': 1.1912, 'learning_rate': 6.843993506493507e-06, 'epoch': 1.54}
+{'loss': 1.2218, 'learning_rate': 6.8363636363636364e-06, 'epoch': 1.55}
+{'loss': 1.1449, 'learning_rate': 6.828733766233766e-06, 'epoch': 1.55}
+{'loss': 1.266, 'learning_rate': 6.821103896103897e-06, 'epoch': 1.55}
+{'loss': 1.0783, 'learning_rate': 6.813474025974026e-06, 'epoch': 1.55}
+{'loss': 1.4685, 'learning_rate': 6.805844155844156e-06, 'epoch': 1.55}
+{'loss': 1.364, 'learning_rate': 6.798214285714286e-06, 'epoch': 1.55}
+{'loss': 1.1521, 'learning_rate': 6.790584415584416e-06, 'epoch': 1.56}
+{'loss': 1.1778, 'learning_rate': 6.782954545454546e-06, 'epoch': 1.56}
+{'loss': 1.2726, 'learning_rate': 6.775324675324675e-06, 'epoch': 1.56}
+{'loss': 1.0461, 'learning_rate': 6.767694805194806e-06, 'epoch': 1.56}
+{'loss': 1.4191, 'learning_rate': 6.7600649350649355e-06, 'epoch': 1.56}
+{'loss': 1.1882, 'learning_rate': 6.752435064935065e-06, 'epoch': 1.56}
+{'loss': 1.3641, 'learning_rate': 6.744805194805195e-06, 'epoch': 1.56}
+{'loss': 1.1529, 'learning_rate': 6.7371753246753245e-06, 'epoch': 1.57}
+{'loss': 1.1319, 'learning_rate': 6.729545454545455e-06, 'epoch': 1.57}
+{'loss': 1.4686, 'learning_rate': 6.721915584415585e-06, 'epoch': 1.57}
+{'loss': 1.429, 'learning_rate': 6.714285714285714e-06, 'epoch': 1.57}
+{'loss': 1.2052, 'learning_rate': 6.706655844155845e-06, 'epoch': 1.57}
+{'loss': 1.1542, 'learning_rate': 6.699025974025974e-06, 'epoch': 1.57}
+{'loss': 1.3645, 'learning_rate': 6.691396103896104e-06, 'epoch': 1.58}
+{'loss': 1.2182, 'learning_rate': 6.683766233766234e-06, 'epoch': 1.58}
+{'loss': 1.0124, 'learning_rate': 6.676136363636364e-06, 'epoch': 1.58}
+{'loss': 1.3172, 'learning_rate': 6.668506493506494e-06, 'epoch': 1.58}
+{'loss': 1.1657, 'learning_rate': 6.6608766233766235e-06, 'epoch': 1.58}
+{'loss': 1.2416, 'learning_rate': 6.653246753246754e-06, 'epoch': 1.58}
+{'loss': 1.3707, 'learning_rate': 6.645616883116883e-06, 'epoch': 1.59}
+{'loss': 1.2101, 'learning_rate': 6.637987012987013e-06, 'epoch': 1.59}
+{'loss': 1.0991, 'learning_rate': 6.630357142857143e-06, 'epoch': 1.59}
+{'loss': 1.2596, 'learning_rate': 6.6227272727272735e-06, 'epoch': 1.59}
+{'loss': 1.2892, 'learning_rate': 6.615097402597403e-06, 'epoch': 1.59}
+{'loss': 1.2003, 'learning_rate': 6.607467532467533e-06, 'epoch': 1.59}
+{'loss': 1.1754, 'learning_rate': 6.599837662337662e-06, 'epoch': 1.6}
+{'loss': 1.1711, 'learning_rate': 6.592207792207792e-06, 'epoch': 1.6}
+{'loss': 1.3105, 'learning_rate': 6.5845779220779226e-06, 'epoch': 1.6}
+{'loss': 1.1924, 'learning_rate': 6.576948051948052e-06, 'epoch': 1.6}
+{'loss': 1.4842, 'learning_rate': 6.569318181818182e-06, 'epoch': 1.6}
+{'loss': 1.3011, 'learning_rate': 6.561688311688312e-06, 'epoch': 1.6}
+{'loss': 1.2704, 'learning_rate': 6.554058441558441e-06, 'epoch': 1.61}
+{'loss': 1.3909, 'learning_rate': 6.546428571428572e-06, 'epoch': 1.61}
+{'loss': 1.0959, 'learning_rate': 6.538798701298701e-06, 'epoch': 1.61}
+{'loss': 1.4069, 'learning_rate': 6.531168831168832e-06, 'epoch': 1.61}
+{'loss': 1.2509, 'learning_rate': 6.5235389610389615e-06, 'epoch': 1.61}
+{'loss': 1.242, 'learning_rate': 6.515909090909091e-06, 'epoch': 1.61}
+{'loss': 1.191, 'learning_rate': 6.508279220779221e-06, 'epoch': 1.62}
+{'loss': 1.2094, 'learning_rate': 6.5006493506493504e-06, 'epoch': 1.62}
+{'loss': 1.2699, 'learning_rate': 6.493019480519481e-06, 'epoch': 1.62}
+{'loss': 1.0511, 'learning_rate': 6.485389610389611e-06, 'epoch': 1.62}
+{'loss': 1.2213, 'learning_rate': 6.47775974025974e-06, 'epoch': 1.62}
+{'loss': 1.2633, 'learning_rate': 6.470129870129871e-06, 'epoch': 1.62}
+{'loss': 1.3453, 'learning_rate': 6.4625e-06, 'epoch': 1.62}
+{'loss': 1.1041, 'learning_rate': 6.45487012987013e-06, 'epoch': 1.63}
+{'loss': 1.4094, 'learning_rate': 6.44724025974026e-06, 'epoch': 1.63}
+{'loss': 1.2807, 'learning_rate': 6.43961038961039e-06, 'epoch': 1.63}
+{'loss': 1.3178, 'learning_rate': 6.43198051948052e-06, 'epoch': 1.63}
+{'loss': 1.1967, 'learning_rate': 6.4243506493506495e-06, 'epoch': 1.63}
+{'loss': 1.2463, 'learning_rate': 6.41672077922078e-06, 'epoch': 1.63}
+{'loss': 1.1007, 'learning_rate': 6.409090909090909e-06, 'epoch': 1.64}
+{'loss': 1.2528, 'learning_rate': 6.401461038961039e-06, 'epoch': 1.64}
+{'loss': 1.0695, 'learning_rate': 6.393831168831169e-06, 'epoch': 1.64}
+{'loss': 1.4708, 'learning_rate': 6.3862012987012994e-06, 'epoch': 1.64}
+{'loss': 1.2202, 'learning_rate': 6.378571428571429e-06, 'epoch': 1.64}
+{'loss': 1.1261, 'learning_rate': 6.370941558441559e-06, 'epoch': 1.64}
+{'loss': 1.2121, 'learning_rate': 6.363311688311688e-06, 'epoch': 1.65}
+{'loss': 1.062, 'learning_rate': 6.355681818181818e-06, 'epoch': 1.65}
+{'loss': 1.2656, 'learning_rate': 6.3480519480519485e-06, 'epoch': 1.65}
+{'loss': 1.1798, 'learning_rate': 6.340422077922078e-06, 'epoch': 1.65}
+{'loss': 1.1952, 'learning_rate': 6.332792207792208e-06, 'epoch': 1.65}
+
 55%|█████▌    | 1019/1848 [5:38:36<4:35:37, 19.95s/it]
 55%|█████▌    | 1020/1848 [5:38:56<4:35:25, 19.96s/it]
                                                       

 55%|█████▌    | 1020/1848 [5:38:56<4:35:25, 19.96s/it]
 55%|█████▌    | 1021/1848 [5:39:16<4:35:15, 19.97s/it]
                                                       

 55%|█████▌    | 1021/1848 [5:39:16<4:35:15, 19.97s/it]
 55%|█████▌    | 1022/1848 [5:39:36<4:34:40, 19.95s/it]
                                                       

 55%|█████▌    | 1022/1848 [5:39:36<4:34:40, 19.95s/it]
 55%|█████▌    | 1023/1848 [5:39:56<4:34:29, 19.96s/it]
                                                       

 55%|█████▌    | 1023/1848 [5:39:56<4:34:29, 19.96s/it]
 55%|█████▌    | 1024/1848 [5:40:16<4:34:16, 19.97s/it]
                                                       

 55%|█████▌    | 1024/1848 [5:40:16<4:34:16, 19.97s/it]
 55%|█████▌    | 1025/1848 [5:40:36<4:34:10, 19.99s/it]
                                                       

 55%|█████▌    | 1025/1848 [5:40:36<4:34:10, 19.99s/it]
 56%|█████▌    | 1026/1848 [5:40:56<4:33:35, 19.97s/it]
                                                       

 56%|█████▌    | 1026/1848 [5:40:56<4:33:35, 19.97s/it]
 56%|█████▌    | 1027/1848 [5:41:16<4:33:42, 20.00s/it]
                                                       

 56%|█████▌    | 1027/1848 [5:41:16<4:33:42, 20.00s/it]
 56%|█████▌    | 1028/1848 [5:41:36<4:32:59, 19.97s/it]
                                                       

 56%|█████▌    | 1028/1848 [5:41:36<4:32:59, 19.97s/it]
 56%|█████▌    | 1029/1848 [5:41:56<4:32:23, 19.96s/it]
                                                       

 56%|█████▌    | 1029/1848 [5:41:56<4:32:23, 19.96s/it]
 56%|█████▌    | 1030/1848 [5:42:16<4:32:03, 19.96s/it]
                                                       

 56%|█████▌    | 1030/1848 [5:42:16<4:32:03, 19.96s/it]
 56%|█████▌    | 1031/1848 [5:42:36<4:31:49, 19.96s/it]
                                                       

 56%|█████▌    | 1031/1848 [5:42:36<4:31:49, 19.96s/it]
 56%|█████▌    | 1032/1848 [5:42:56<4:31:30, 19.96s/it]
                                                       

 56%|█████▌    | 1032/1848 [5:42:56<4:31:30, 19.96s/it]
 56%|█████▌    | 1033/1848 [5:43:16<4:30:57, 19.95s/it]
                                                       

 56%|█████▌    | 1033/1848 [5:43:16<4:30:57, 19.95s/it]
 56%|█████▌    | 1034/1848 [5:43:36<4:30:39, 19.95s/it]
                                                       

 56%|█████▌    | 1034/1848 [5:43:36<4:30:39, 19.95s/it]
 56%|█████▌    | 1035/1848 [5:43:56<4:30:31, 19.97s/it]
                                                       

 56%|█████▌    | 1035/1848 [5:43:56<4:30:31, 19.97s/it]
 56%|█████▌    | 1036/1848 [5:44:16<4:30:26, 19.98s/it]
                                                       

 56%|█████▌    | 1036/1848 [5:44:16<4:30:26, 19.98s/it]
 56%|█████▌    | 1037/1848 [5:44:36<4:30:00, 19.98s/it]
                                                       

 56%|█████▌    | 1037/1848 [5:44:36<4:30:00, 19.98s/it]
 56%|█████▌    | 1038/1848 [5:44:56<4:29:53, 19.99s/it]
                                                       

 56%|█████▌    | 1038/1848 [5:44:56<4:29:53, 19.99s/it]
 56%|█████▌    | 1039/1848 [5:45:16<4:29:11, 19.97s/it]
                                                       

 56%|█████▌    | 1039/1848 [5:45:16<4:29:11, 19.97s/it]
 56%|█████▋    | 1040/1848 [5:45:36<4:28:53, 19.97s/it]
                                                       

 56%|█████▋    | 1040/1848 [5:45:36<4:28:53, 19.97s/it]
 56%|█████▋    | 1041/1848 [5:45:56<4:28:26, 19.96s/it]
                                                       

 56%|█████▋    | 1041/1848 [5:45:56<4:28:26, 19.96s/it]
 56%|█████▋    | 1042/1848 [5:46:16<4:28:17, 19.97s/it]
                                                       

 56%|█████▋    | 1042/1848 [5:46:16<4:28:17, 19.97s/it]
 56%|█████▋    | 1043/1848 [5:46:36<4:28:03, 19.98s/it]
                                                       

 56%|█████▋    | 1043/1848 [5:46:36<4:28:03, 19.98s/it]
 56%|█████▋    | 1044/1848 [5:46:56<4:27:33, 19.97s/it]
                                                       

 56%|█████▋    | 1044/1848 [5:46:56<4:27:33, 19.97s/it]
 57%|█████▋    | 1045/1848 [5:47:16<4:27:14, 19.97s/it]
                                                       

 57%|█████▋    | 1045/1848 [5:47:16<4:27:14, 19.97s/it]
 57%|█████▋    | 1046/1848 [5:47:35<4:26:34, 19.94s/it]
                                                       

 57%|█████▋    | 1046/1848 [5:47:35<4:26:34, 19.94s/it]
 57%|█████▋    | 1047/1848 [5:47:55<4:26:22, 19.95s/it]
                                                       

 57%|█████▋    | 1047/1848 [5:47:55<4:26:22, 19.95s/it]
 57%|█████▋    | 1048/1848 [5:48:15<4:25:44, 19.93s/it]
                                                       

 57%|█████▋    | 1048/1848 [5:48:15<4:25:44, 19.93s/it]
 57%|█████▋    | 1049/1848 [5:48:35<4:25:39, 19.95s/it]
                                                       

 57%|█████▋    | 1049/1848 [5:48:35<4:25:39, 19.95s/it]
 57%|█████▋    | 1050/1848 [5:48:55<4:25:18, 19.95s/it]
                                                       

 57%|█████▋    | 1050/1848 [5:48:55<4:25:18, 19.95s/it]
 57%|█████▋    | 1051/1848 [5:49:15<4:24:54, 19.94s/it]
                                                       

 57%|█████▋    | 1051/1848 [5:49:15<4:24:54, 19.94s/it]
 57%|█████▋    | 1052/1848 [5:49:35<4:24:23, 19.93s/it]
                                                       

 57%|█████▋    | 1052/1848 [5:49:35<4:24:23, 19.93s/it]
 57%|█████▋    | 1053/1848 [5:49:55<4:24:01, 19.93s/it]
                                                       

 57%|█████▋    | 1053/1848 [5:49:55<4:24:01, 19.93s/it]
 57%|█████▋    | 1054/1848 [5:50:15<4:24:07, 19.96s/it]
                                                       

 57%|█████▋    | 1054/1848 [5:50:15<4:24:07, 19.96s/it]
 57%|█████▋    | 1055/1848 [5:50:35<4:23:44, 19.96s/it]
                                                       

 57%|█████▋    | 1055/1848 [5:50:35<4:23:44, 19.96s/it]
 57%|█████▋    | 1056/1848 [5:50:55<4:23:20, 19.95s/it]
                                                       

 57%|█████▋    | 1056/1848 [5:50:55<4:23:20, 19.95s/it]
 57%|█████▋    | 1057/1848 [5:51:15<4:23:00, 19.95s/it]
                                                       

 57%|█████▋    | 1057/1848 [5:51:15<4:23:00, 19.95s/it]
 57%|█████▋    | 1058/1848 [5:51:35<4:22:53, 19.97s/it]
                                                       

 57%|█████▋    | 1058/1848 [5:51:35<4:22:53, 19.97s/it]
 57%|█████▋    | 1059/1848 [5:51:55<4:22:23, 19.95s/it]
                                                       

 57%|█████▋    | 1059/1848 [5:51:55<4:22:23, 19.95s/it]
 57%|█████▋    | 1060/1848 [5:52:15<4:21:35, 19.92s/it]
                                                       

 57%|█████▋    | 1060/1848 [5:52:15<4:21:35, 19.92s/it]
 57%|█████▋    | 1061/1848 [5:52:35<4:21:34, 19.94s/it]
                                                       

 57%|█████▋    | 1061/1848 [5:52:35<4:21:34, 19.94s/it]
 57%|█████▋    | 1062/1848 [5:52:55<4:21:16, 19.95s/it]
                                                       

 57%|█████▋    | 1062/1848 [5:52:55<4:21:16, 19.95s/it]
 58%|█████▊    | 1063/1848 [5:53:15<4:20:59, 19.95s/it]
                                                       

 58%|█████▊    | 1063/1848 [5:53:15<4:20:59, 19.95s/it]
 58%|█████▊    | 1064/1848 [5:53:34<4:20:30, 19.94s/it]
                                                       

 58%|█████▊    | 1064/1848 [5:53:34<4:20:30, 19.94s/it]
 58%|█████▊    | 1065/1848 [5:53:54<4:19:55, 19.92s/it]
                                                       

 58%|█████▊    | 1065/1848 [5:53:54<4:19:55, 19.92s/it]
 58%|█████▊    | 1066/1848 [5:54:14<4:19:52, 19.94s/it]
                                                       

 58%|█████▊    | 1066/1848 [5:54:14<4:19:52, 19.94s/it]
 58%|█████▊    | 1067/1848 [5:54:34<4:19:46, 19.96s/it]
                                                       

 58%|█████▊    | 1067/1848 [5:54:34<4:19:46, 19.96s/it]
 58%|█████▊    | 1068/1848 [5:54:54<4:19:29, 19.96s/it]
                                                       

 58%|█████▊    | 1068/1848 [5:54:54<4:19:29, 19.96s/it]
 58%|█████▊    | 1069/1848 [5:55:14<4:19:05, 19.96s/it]
                                                       

 58%|█████▊    | 1069/1848 [5:55:14<4:19:05, 19.96s/it]
 58%|█████▊    | 1070/1848 [5:55:34<4:18:49, 19.96s/it]
                                                       

 58%|█████▊    | 1070/1848 [5:55:34<4:18:49, 19.96s/it]
 58%|█████▊    | 1071/1848 [5:55:54<4:18:07, 19.93s/it]
                                                       

 58%|█████▊    | 1071/1848 [5:55:54<4:18:07, 19.93s/it]
 58%|█████▊    | 1072/1848 [5:56:14<4:17:47, 19.93s/it]
                                                       

 58%|█████▊    | 1072/1848 [5:56:14<4:17:47, 19.93s/it]
 58%|█████▊    | 1073/1848 [5:56:34<4:17:06, 19.91s/it]
                                                       

 58%|█████▊    | 1073/1848 [5:56:34<4:17:06, 19.91s/it]
 58%|█████▊    | 1074/1848 [5:56:54<4:16:57, 19.92s/it]
                                                       

 58%|█████▊    | 1074/1848 [5:56:54<4:16:57, 19.92s/it]
 58%|█████▊    | 1075/1848 [5:57:14<4:16:51, 19.94s/it]
                                                       

 58%|█████▊    | 1075/1848 [5:57:14<4:16:51, 19.94s/it]
 58%|█████▊    | 1076/1848 [5:57:34<4:16:24, 19.93s/it]
                                                       

 58%|█████▊    | 1076/1848 [5:57:34<4:16:24, 19.93s/it]
 58%|█████▊    | 1077/1848 [5:57:54<4:16:33, 19.97s/it]
                                                       

 58%|█████▊    | 1077/1848 [5:57:54<4:16:33, 19.97s/it]
 58%|█████▊    | 1078/1848 [5:58:14<4:16:06, 19.96s/it]
                                                       

 58%|█████▊    | 1078/1848 [5:58:14<4:16:06, 19.96s/it]
 58%|█████▊    | 1079/1848 [5:58:34<4:15:50, 19.96s/it]
                                                       

 58%|█████▊    | 1079/1848 [5:58:34<4:15:50, 19.96s/it]
 58%|█████▊    | 1080/1848 [5:58:54<4:15:29, 19.96s/it]
                                                       

 58%|█████▊    | 1080/1848 [5:58:54<4:15:29, 19.96s/it]
 58%|█████▊    | 1081/1848 [5:59:13<4:14:47, 19.93s/it]
                                                       

 58%|█████▊    | 1081/1848 [5:59:13<4:14:47, 19.93s/it]
 59%|█████▊    | 1082/1848 [5:59:33<4:14:17, 19.92s/it]
                                                       

 59%|█████▊    | 1082/1848 [5:59:33<4:14:17, 19.92s/it]
 59%|█████▊    | 1083/1848 [5:59:53<4:13:42, 19.90s/it]
                                                       

 59%|█████▊    | 1083/1848 [5:59:53<4:13:42, 19.90s/it]
 59%|█████▊    | 1084/1848 [6:00:13<4:13:32, 19.91s/it]
                                                       

 59%|█████▊    | 1084/1848 [6:00:13<4:13:32, 19.91s/it]
 59%|█████▊    | 1085/1848 [6:00:33<4:13:16, 19.92s/it]
                                                       

 59%|█████▊    | 1085/1848 [6:00:33<4:13:16, 19.92s/it]
 59%|█████▉    | 1086/1848 [6:00:53<4:12:55, 19.92s/it]
                                                       

 59%|█████▉    | 1086/1848 [6:00:53<4:12:55, 19.92s/it]
 59%|█████▉    | 1087/1848 [6:01:13<4:12:41, 19.92s/it]
                                                       

 59%|█████▉    | 1087/1848 [6:01:13<4:12:41, 19.92s/it]
 59%|█████▉    | 1088/1848 [6:01:33<4:12:42, 19.95s/it]
                                                       

 59%|█████▉    | 1088/1848 [6:01:33<4:12:42, 19.95s/it]
 59%|█████▉    | 1089/1848 [6:01:53<4:12:21, 19.95s/it]
                                                       

 59%|█████▉    | 1089/1848 [6:01:53<4:12:21, 19.95s/it]
 59%|█████▉    | 1090/1848 [6:02:13<4:12:04, 19.95s/it]
                                                       

 59%|█████▉    | 1090/1848 [6:02:13<4:12:04, 19.95s/it]
 59%|█████▉    | 1091/1848 [6:02:33<4:11:31, 19.94s/it]
                                                       

 59%|█████▉    | 1091/1848 [6:02:33<4:11:31, 19.94s/it]
 59%|█████▉    | 1092/1848 [6:02:53<4:10:55, 19.91s/it]
                                                       

 59%|█████▉    | 1092/1848 [6:02:53<4:10:55, 19.91s/it]
 59%|█████▉    | 1093/1848 [6:03:13<4:10:34, 19.91s/it]
                                                       

 59%|█████▉    | 1093/1848 [6:03:13<4:10:34, 19.91s/it]
 59%|█████▉    | 1094/1848 [6:03:32<4:10:04, 19.90s/it]
                                                       

 59%|█████▉    | 1094/1848 [6:03:32<4:10:04, 19.90s/it]
 59%|█████▉    | 1095/1848 [6:03:52<4:10:07, 19.93s/it]
                                                       

 59%|█████▉    | 1095/1848 [6:03:52<4:10:07, 19.93s/it]
 59%|█████▉    | 1096/1848 [6:04:12<4:09:45, 19.93s/it]
                                                       

 59%|█████▉    | 1096/1848 [6:04:12<4:09:45, 19.93s/it]
 59%|█████▉    | 1097/1848 [6:04:32<4:09:42, 19.95s/it]
                                                       

 59%|█████▉    | 1097/1848 [6:04:32<4:09:42, 19.95s/it]
 59%|█████▉    | 1098/1848 [6:04:51<4:04:10, 19.53s/it]
                                                       

 59%|█████▉    | 1098/1848 [6:04:51<4:04:10, 19.53s/it]
 59%|█████▉    | 1099/1848 [6:05:11<4:05:16, 19.65s/it]
                                                       

 59%|█████▉    | 1099/1848 [6:05:11<4:05:16, 19.65s/it]
 60%|█████▉    | 1100/1848 [6:05:31<4:05:46, 19.72s/it]
                                                       

 60%|█████▉    | 1100/1848 [6:05:31<4:05:46, 19.72s/it]
 60%|█████▉    | 1101/1848 [6:05:51<4:09:35, 20.05s/it]
                                                       

 60%|█████▉    | 1101/1848 [6:05:52<4:09:35, 20.05s/it]
 60%|█████▉    | 1102/1848 [6:06:11<4:08:53, 20.02s/it]
                                                       

 60%|█████▉    | 1102/1848 [6:06:11<4:08:53, 20.02s/it]
 60%|█████▉    | 1103/1848 [6:06:31<4:08:08, 19.98s/it]
                                                       

 60%|█████▉    | 1103/1848 [6:06:31<4:08:08, 19.98s/it]
 60%|█████▉    | 1104/1848 [6:06:51<4:07:31, 19.96s/it]
                                                       

 60%|█████▉    | 1104/1848 [6:06:51<4:07:31, 19.96s/it]
 60%|█████▉    | 1105/1848 [6:07:11<4:07:13, 19.96s/it]
                                                       

 60%|█████▉    | 1105/1848 [6:07:11<4:07:13, 19.96s/it]
 60%|█████▉    | 1106/1848 [6:07:31<4:06:56, 19.97s/it]
                                                       

 60%|█████▉    | 1106/1848 [6:07:31<4:06:56, 19.97s/it]
 60%|█████▉    | 1107/1848 [6:07:51<4:06:19, 19.95s/it]
                                                       

 60%|█████▉    | 1107/1848 [6:07:51<4:06:19, 19.95s/it]
 60%|█████▉    | 1108/1848 [6:08:11<4:06:01, 19.95s/it]
                                                       

 60%|█████▉    | 1108/1848 [6:08:11<4:06:01, 19.95s/it]
 60%|██████    | 1109/1848 [6:08:31<4:05:33, 19.94s/it]
                                                       

 60%|██████    | 1109/1848 [6:08:31<4:05:33, 19.94s/it]
 60%|██████    | 1110/1848 [6:08:51<4:05:15, 19.94s/it]
                                                       

 60%|██████    | 1110/1848 [6:08:51<4:05:15, 19.94s/it]
 60%|██████    | 1111/1848 [6:09:11<4:04:53, 19.94s/it]
                                                       

 60%|██████    | 1111/1848 [6:09:11<4:04:53, 19.94s/it]
 60%|██████    | 1112/1848 [6:09:31<4:04:44, 19.95s/it]
                                                       

 60%|██████    | 1112/1848 [6:09:31<4:04:44, 19.95s/it]
 60%|██████    | 1113/1848 [6:09:51<4:04:19, 19.94s/it]
                                                       

 60%|██████    | 1113/1848 [6:09:51<4:04:19, 19.94s/it]
 60%|██████    | 1114/1848 [6:10:11<4:04:03, 19.95s/it]
                                                       

 60%|██████    | 1114/1848 [6:10:11<4:04:03, 19.95s/it]
 60%|██████    | 1115/1848 [6:10:31<4:03:41, 19.95s/it]
                                                       

 60%|██████    | 1115/1848 [6:10:31<4:03:41, 19.95s/it]
 60%|██████    | 1116/1848 [6:10:51<4:03:09, 19.93s/it]
                                                       

 60%|██████    | 1116/1848 [6:10:51<4:03:09, 19.93s/it]
 60%|██████    | 1117/1848 [6:11:11<4:02:59, 19.94s/it]
                                                       

 60%|██████    | 1117/1848 [6:11:11<4:02:59, 19.94s/it]
 60%|██████    | 1118/1848 [6:11:30<4:02:41, 19.95s/it]
                                                       

 60%|██████    | 1118/1848 [6:11:30<4:02:41, 19.95s/it]
 61%|██████    | 1119/1848 [6:11:50<4:02:19, 19.94s/it]
                                                       

 61%|██████    | 1119/1848 [6:11:50<4:02:19, 19.94s/it]
 61%|██████    | 1120/1848 [6:12:10<4:02:07, 19.95s/it]
                                                       

 61%|██████    | 1120/1848 [6:12:10<4:02:07, 19.95s/it]
 61%|██████    | 1121/1848 [6:12:30<4:01:45, 19.95s/it]
                                                       

 61%|██████    | 1121/1848 [6:12:30<4:01:45, 19.95s/it]
 61%|██████    | 1122/1848 [6:12:50<4:01:36, 19.97s/it]
                                                       

 61%|██████    | 1122/1848 [6:12:50<4:01:36, 19.97s/it]
 61%|██████    | 1123/1848 [6:13:10<4:01:08, 19.96s/it]
                                                       

 61%|██████    | 1123/1848 [6:13:10<4:01:08, 19.96s/it]
 61%|██████    | 1124/1848 [6:13:30<4:00:33, 19.94s/it]
                                                       

 61%|██████    | 1124/1848 [6:13:30<4:00:33, 19.94s/it]
 61%|██████    | 1125/1848 [6:13:50<4:00:02, 19.92s/it]
                                                       

 61%|██████    | 1125/1848 [6:13:50<4:00:02, 19.92s/it]
 61%|██████    | 1126/1848 [6:14:10<3:59:28, 19.90s/it]
                                                       

 61%|██████    | 1126/1848 [6:14:10<3:59:28, 19.90s/it]
 61%|██████    | 1127/1848 [6:14:30<3:59:20, 19.92s/it]
                                                       

 61%|██████    | 1127/1848 [6:14:30<3:59:20, 19.92s/it]
 61%|██████    | 1128/1848 [6:14:50<3:59:06, 19.93s/it]
                                                       

 61%|██████    | 1128/1848 [6:14:50<3:59:06, 19.93s/it]
 61%|██████    | 1129/1848 [6:15:10<3:58:48, 19.93s/it]
                                                       

 61%|██████    | 1129/1848 [6:15:10<3:58:48, 19.93s/it]
 61%|██████    | 1130/1848 [6:15:30<3:58:19, 19.92s/it]
                                                       

 61%|██████    | 1130/1848 [6:15:30<3:58:19, 19.92s/it]
 61%|██████    | 1131/1848 [6:15:50<3:58:06, 19.93s/it]
                                                       

 61%|██████    | 1131/1848 [6:15:50<3:58:06, 19.93s/it]
 61%|██████▏   | 1132/1848 [6:16:10<3:58:02, 19.95s/it]
                                                       
{'loss': 1.0847, 'learning_rate': 6.325162337662338e-06, 'epoch': 1.65}
+{'loss': 1.0617, 'learning_rate': 6.317532467532467e-06, 'epoch': 1.66}
+{'loss': 1.1458, 'learning_rate': 6.309902597402598e-06, 'epoch': 1.66}
+{'loss': 1.4278, 'learning_rate': 6.302272727272727e-06, 'epoch': 1.66}
+{'loss': 1.6504, 'learning_rate': 6.294642857142858e-06, 'epoch': 1.66}
+{'loss': 1.2847, 'learning_rate': 6.2870129870129875e-06, 'epoch': 1.66}
+{'loss': 1.2907, 'learning_rate': 6.279383116883117e-06, 'epoch': 1.66}
+{'loss': 1.2291, 'learning_rate': 6.271753246753247e-06, 'epoch': 1.67}
+{'loss': 1.0099, 'learning_rate': 6.264123376623376e-06, 'epoch': 1.67}
+{'loss': 1.1244, 'learning_rate': 6.256493506493507e-06, 'epoch': 1.67}
+{'loss': 1.2291, 'learning_rate': 6.2488636363636366e-06, 'epoch': 1.67}
+{'loss': 1.2093, 'learning_rate': 6.241233766233767e-06, 'epoch': 1.67}
+{'loss': 1.2527, 'learning_rate': 6.233603896103897e-06, 'epoch': 1.67}
+{'loss': 1.1803, 'learning_rate': 6.2259740259740255e-06, 'epoch': 1.68}
+{'loss': 1.1649, 'learning_rate': 6.218344155844156e-06, 'epoch': 1.68}
+{'loss': 1.1441, 'learning_rate': 6.210714285714286e-06, 'epoch': 1.68}
+{'loss': 1.1021, 'learning_rate': 6.203084415584416e-06, 'epoch': 1.68}
+{'loss': 1.2695, 'learning_rate': 6.195454545454546e-06, 'epoch': 1.68}
+{'loss': 1.1446, 'learning_rate': 6.1878246753246755e-06, 'epoch': 1.68}
+{'loss': 1.3309, 'learning_rate': 6.180194805194805e-06, 'epoch': 1.69}
+{'loss': 1.3674, 'learning_rate': 6.172564935064935e-06, 'epoch': 1.69}
+{'loss': 1.1927, 'learning_rate': 6.164935064935065e-06, 'epoch': 1.69}
+{'loss': 1.4741, 'learning_rate': 6.157305194805195e-06, 'epoch': 1.69}
+{'loss': 1.2384, 'learning_rate': 6.149675324675325e-06, 'epoch': 1.69}
+{'loss': 1.3601, 'learning_rate': 6.142045454545455e-06, 'epoch': 1.69}
+{'loss': 1.3492, 'learning_rate': 6.134415584415585e-06, 'epoch': 1.69}
+{'loss': 1.0729, 'learning_rate': 6.126785714285714e-06, 'epoch': 1.7}
+{'loss': 1.323, 'learning_rate': 6.119155844155844e-06, 'epoch': 1.7}
+{'loss': 1.4426, 'learning_rate': 6.1115259740259745e-06, 'epoch': 1.7}
+{'loss': 1.2539, 'learning_rate': 6.103896103896104e-06, 'epoch': 1.7}
+{'loss': 1.1657, 'learning_rate': 6.096266233766234e-06, 'epoch': 1.7}
+{'loss': 1.1005, 'learning_rate': 6.088636363636364e-06, 'epoch': 1.7}
+{'loss': 1.3275, 'learning_rate': 6.081006493506493e-06, 'epoch': 1.71}
+{'loss': 1.2653, 'learning_rate': 6.073376623376624e-06, 'epoch': 1.71}
+{'loss': 1.4142, 'learning_rate': 6.065746753246753e-06, 'epoch': 1.71}
+{'loss': 1.2319, 'learning_rate': 6.058116883116884e-06, 'epoch': 1.71}
+{'loss': 1.3714, 'learning_rate': 6.0504870129870134e-06, 'epoch': 1.71}
+{'loss': 1.1074, 'learning_rate': 6.042857142857143e-06, 'epoch': 1.71}
+{'loss': 1.281, 'learning_rate': 6.035227272727273e-06, 'epoch': 1.72}
+{'loss': 1.318, 'learning_rate': 6.027597402597402e-06, 'epoch': 1.72}
+{'loss': 1.1968, 'learning_rate': 6.019967532467533e-06, 'epoch': 1.72}
+{'loss': 1.2907, 'learning_rate': 6.0123376623376625e-06, 'epoch': 1.72}
+{'loss': 1.2408, 'learning_rate': 6.004707792207793e-06, 'epoch': 1.72}
+{'loss': 1.173, 'learning_rate': 5.997077922077923e-06, 'epoch': 1.72}
+{'loss': 1.2479, 'learning_rate': 5.9894480519480515e-06, 'epoch': 1.73}
+{'loss': 1.1199, 'learning_rate': 5.981818181818182e-06, 'epoch': 1.73}
+{'loss': 1.161, 'learning_rate': 5.974188311688312e-06, 'epoch': 1.73}
+{'loss': 1.3859, 'learning_rate': 5.966558441558442e-06, 'epoch': 1.73}
+{'loss': 1.1034, 'learning_rate': 5.958928571428572e-06, 'epoch': 1.73}
+{'loss': 1.1255, 'learning_rate': 5.9512987012987014e-06, 'epoch': 1.73}
+{'loss': 1.0866, 'learning_rate': 5.943668831168831e-06, 'epoch': 1.74}
+{'loss': 1.0856, 'learning_rate': 5.936038961038961e-06, 'epoch': 1.74}
+{'loss': 1.558, 'learning_rate': 5.928409090909091e-06, 'epoch': 1.74}
+{'loss': 1.2987, 'learning_rate': 5.920779220779221e-06, 'epoch': 1.74}
+{'loss': 1.0323, 'learning_rate': 5.913149350649351e-06, 'epoch': 1.74}
+{'loss': 1.2317, 'learning_rate': 5.905519480519481e-06, 'epoch': 1.74}
+{'loss': 1.1348, 'learning_rate': 5.897889610389611e-06, 'epoch': 1.75}
+{'loss': 1.2817, 'learning_rate': 5.89025974025974e-06, 'epoch': 1.75}
+{'loss': 1.1258, 'learning_rate': 5.88262987012987e-06, 'epoch': 1.75}
+{'loss': 1.0356, 'learning_rate': 5.8750000000000005e-06, 'epoch': 1.75}
+{'loss': 1.3006, 'learning_rate': 5.86737012987013e-06, 'epoch': 1.75}
+{'loss': 1.0259, 'learning_rate': 5.859740259740261e-06, 'epoch': 1.75}
+{'loss': 1.2581, 'learning_rate': 5.85211038961039e-06, 'epoch': 1.75}
+{'loss': 1.3394, 'learning_rate': 5.844480519480519e-06, 'epoch': 1.76}
+{'loss': 1.2247, 'learning_rate': 5.83685064935065e-06, 'epoch': 1.76}
+{'loss': 1.174, 'learning_rate': 5.829220779220779e-06, 'epoch': 1.76}
+{'loss': 1.4444, 'learning_rate': 5.82159090909091e-06, 'epoch': 1.76}
+{'loss': 1.3726, 'learning_rate': 5.813961038961039e-06, 'epoch': 1.76}
+{'loss': 1.2033, 'learning_rate': 5.806331168831169e-06, 'epoch': 1.76}
+{'loss': 1.3146, 'learning_rate': 5.798701298701299e-06, 'epoch': 1.77}
+{'loss': 1.1275, 'learning_rate': 5.791071428571428e-06, 'epoch': 1.77}
+{'loss': 1.0346, 'learning_rate': 5.783441558441559e-06, 'epoch': 1.77}
+{'loss': 1.3304, 'learning_rate': 5.7758116883116885e-06, 'epoch': 1.77}
+{'loss': 1.3057, 'learning_rate': 5.768181818181819e-06, 'epoch': 1.77}
+{'loss': 1.3484, 'learning_rate': 5.760551948051949e-06, 'epoch': 1.77}
+{'loss': 1.1843, 'learning_rate': 5.7529220779220775e-06, 'epoch': 1.78}
+{'loss': 1.1711, 'learning_rate': 5.745292207792208e-06, 'epoch': 1.78}
+{'loss': 1.3331, 'learning_rate': 5.737662337662338e-06, 'epoch': 1.78}
+{'loss': 1.2187, 'learning_rate': 5.730032467532468e-06, 'epoch': 1.78}
+{'loss': 1.2799, 'learning_rate': 5.722402597402598e-06, 'epoch': 1.78}
+{'loss': 1.2266, 'learning_rate': 5.714772727272727e-06, 'epoch': 1.78}
+{'loss': 1.6517, 'learning_rate': 5.707142857142857e-06, 'epoch': 1.79}
+{'loss': 1.2797, 'learning_rate': 5.699512987012987e-06, 'epoch': 1.79}
+{'loss': 1.1288, 'learning_rate': 5.691883116883117e-06, 'epoch': 1.79}
+{'loss': 1.2885, 'learning_rate': 5.684253246753247e-06, 'epoch': 1.79}
+{'loss': 1.1112, 'learning_rate': 5.676623376623377e-06, 'epoch': 1.79}
+{'loss': 1.2666, 'learning_rate': 5.668993506493507e-06, 'epoch': 1.79}
+{'loss': 1.2581, 'learning_rate': 5.661363636363636e-06, 'epoch': 1.8}
+{'loss': 1.462, 'learning_rate': 5.653733766233766e-06, 'epoch': 1.8}
+{'loss': 1.1004, 'learning_rate': 5.646103896103896e-06, 'epoch': 1.8}
+{'loss': 1.1619, 'learning_rate': 5.6384740259740265e-06, 'epoch': 1.8}
+{'loss': 1.2291, 'learning_rate': 5.630844155844156e-06, 'epoch': 1.8}
+{'loss': 1.2411, 'learning_rate': 5.623214285714287e-06, 'epoch': 1.8}
+{'loss': 1.1709, 'learning_rate': 5.6155844155844154e-06, 'epoch': 1.81}
+{'loss': 1.1703, 'learning_rate': 5.607954545454545e-06, 'epoch': 1.81}
+{'loss': 1.0743, 'learning_rate': 5.600324675324676e-06, 'epoch': 1.81}
+{'loss': 1.2157, 'learning_rate': 5.592694805194805e-06, 'epoch': 1.81}
+{'loss': 1.3011, 'learning_rate': 5.585064935064936e-06, 'epoch': 1.81}
+{'loss': 1.1065, 'learning_rate': 5.577435064935065e-06, 'epoch': 1.81}
+{'loss': 1.288, 'learning_rate': 5.569805194805195e-06, 'epoch': 1.81}
+{'loss': 1.2992, 'learning_rate': 5.562175324675325e-06, 'epoch': 1.82}
+{'loss': 1.1878, 'learning_rate': 5.554545454545454e-06, 'epoch': 1.82}
+{'loss': 1.2319, 'learning_rate': 5.546915584415585e-06, 'epoch': 1.82}
+{'loss': 1.1889, 'learning_rate': 5.5392857142857145e-06, 'epoch': 1.82}
+{'loss': 1.0408, 'learning_rate': 5.531655844155845e-06, 'epoch': 1.82}
+{'loss': 1.1732, 'learning_rate': 5.524025974025975e-06, 'epoch': 1.82}
+{'loss': 1.3994, 'learning_rate': 5.5163961038961034e-06, 'epoch': 1.83}
+{'loss': 1.2023, 'learning_rate': 5.508766233766234e-06, 'epoch': 1.83}
+{'loss': 1.1767, 'learning_rate': 5.501136363636364e-06, 'epoch': 1.83}
+{'loss': 1.2793, 'learning_rate': 5.493506493506494e-06, 'epoch': 1.83}
+{'loss': 1.2445, 'learning_rate': 5.485876623376624e-06, 'epoch': 1.83}
+{'loss': 1.2141, 'learning_rate': 5.478246753246754e-06, 'epoch': 1.83}
+{'loss': 1.438, 'learning_rate': 5.470616883116883e-06, 'epoch': 1.84}
+
 61%|██████▏   | 1132/1848 [6:16:10<3:58:02, 19.95s/it]
 61%|██████▏   | 1133/1848 [6:16:30<3:57:46, 19.95s/it]
                                                       

 61%|██████▏   | 1133/1848 [6:16:30<3:57:46, 19.95s/it]
 61%|██████▏   | 1134/1848 [6:16:49<3:57:22, 19.95s/it]
                                                       

 61%|██████▏   | 1134/1848 [6:16:49<3:57:22, 19.95s/it]
 61%|██████▏   | 1135/1848 [6:17:09<3:56:57, 19.94s/it]
                                                       

 61%|██████▏   | 1135/1848 [6:17:09<3:56:57, 19.94s/it]
 61%|██████▏   | 1136/1848 [6:17:29<3:56:48, 19.96s/it]
                                                       

 61%|██████▏   | 1136/1848 [6:17:29<3:56:48, 19.96s/it]
 62%|██████▏   | 1137/1848 [6:17:49<3:56:21, 19.95s/it]
                                                       

 62%|██████▏   | 1137/1848 [6:17:49<3:56:21, 19.95s/it]
 62%|██████▏   | 1138/1848 [6:18:09<3:55:57, 19.94s/it]
                                                       

 62%|██████▏   | 1138/1848 [6:18:09<3:55:57, 19.94s/it]
 62%|██████▏   | 1139/1848 [6:18:29<3:55:43, 19.95s/it]
                                                       

 62%|██████▏   | 1139/1848 [6:18:29<3:55:43, 19.95s/it]
 62%|██████▏   | 1140/1848 [6:18:49<3:55:11, 19.93s/it]
                                                       

 62%|██████▏   | 1140/1848 [6:18:49<3:55:11, 19.93s/it]
 62%|██████▏   | 1141/1848 [6:19:09<3:54:55, 19.94s/it]
                                                       

 62%|██████▏   | 1141/1848 [6:19:09<3:54:55, 19.94s/it]
 62%|██████▏   | 1142/1848 [6:19:29<3:54:37, 19.94s/it]
                                                       

 62%|██████▏   | 1142/1848 [6:19:29<3:54:37, 19.94s/it]
 62%|██████▏   | 1143/1848 [6:19:49<3:54:17, 19.94s/it]
                                                       

 62%|██████▏   | 1143/1848 [6:19:49<3:54:17, 19.94s/it]
 62%|██████▏   | 1144/1848 [6:20:09<3:54:03, 19.95s/it]
                                                       

 62%|██████▏   | 1144/1848 [6:20:09<3:54:03, 19.95s/it]
 62%|██████▏   | 1145/1848 [6:20:29<3:53:27, 19.93s/it]
                                                       

 62%|██████▏   | 1145/1848 [6:20:29<3:53:27, 19.93s/it]
 62%|██████▏   | 1146/1848 [6:20:49<3:52:56, 19.91s/it]
                                                       

 62%|██████▏   | 1146/1848 [6:20:49<3:52:56, 19.91s/it]
 62%|██████▏   | 1147/1848 [6:21:09<3:52:37, 19.91s/it]
                                                       

 62%|██████▏   | 1147/1848 [6:21:09<3:52:37, 19.91s/it]
 62%|██████▏   | 1148/1848 [6:21:29<3:52:27, 19.92s/it]
                                                       

 62%|██████▏   | 1148/1848 [6:21:29<3:52:27, 19.92s/it]
 62%|██████▏   | 1149/1848 [6:21:48<3:52:09, 19.93s/it]
                                                       

 62%|██████▏   | 1149/1848 [6:21:48<3:52:09, 19.93s/it]
 62%|██████▏   | 1150/1848 [6:22:08<3:51:36, 19.91s/it]
                                                       

 62%|██████▏   | 1150/1848 [6:22:08<3:51:36, 19.91s/it]
 62%|██████▏   | 1151/1848 [6:22:28<3:51:10, 19.90s/it]
                                                       

 62%|██████▏   | 1151/1848 [6:22:28<3:51:10, 19.90s/it]
 62%|██████▏   | 1152/1848 [6:22:48<3:51:07, 19.92s/it]
                                                       

 62%|██████▏   | 1152/1848 [6:22:48<3:51:07, 19.92s/it]
 62%|██████▏   | 1153/1848 [6:23:08<3:50:44, 19.92s/it]
                                                       

 62%|██████▏   | 1153/1848 [6:23:08<3:50:44, 19.92s/it]
 62%|██████▏   | 1154/1848 [6:23:28<3:50:24, 19.92s/it]
                                                       

 62%|██████▏   | 1154/1848 [6:23:28<3:50:24, 19.92s/it]
 62%|██████▎   | 1155/1848 [6:23:48<3:50:27, 19.95s/it]
                                                       

 62%|██████▎   | 1155/1848 [6:23:48<3:50:27, 19.95s/it]
 63%|██████▎   | 1156/1848 [6:24:08<3:50:10, 19.96s/it]
                                                       

 63%|██████▎   | 1156/1848 [6:24:08<3:50:10, 19.96s/it]
 63%|██████▎   | 1157/1848 [6:24:28<3:49:43, 19.95s/it]
                                                       

 63%|██████▎   | 1157/1848 [6:24:28<3:49:43, 19.95s/it]
 63%|██████▎   | 1158/1848 [6:24:48<3:49:20, 19.94s/it]
                                                       

 63%|██████▎   | 1158/1848 [6:24:48<3:49:20, 19.94s/it]
 63%|██████▎   | 1159/1848 [6:25:08<3:48:56, 19.94s/it]
                                                       

 63%|██████▎   | 1159/1848 [6:25:08<3:48:56, 19.94s/it]
 63%|██████▎   | 1160/1848 [6:25:28<3:48:38, 19.94s/it]
                                                       

 63%|██████▎   | 1160/1848 [6:25:28<3:48:38, 19.94s/it]
 63%|██████▎   | 1161/1848 [6:25:48<3:48:11, 19.93s/it]
                                                       

 63%|██████▎   | 1161/1848 [6:25:48<3:48:11, 19.93s/it]
 63%|██████▎   | 1162/1848 [6:26:08<3:47:53, 19.93s/it]
                                                       

 63%|██████▎   | 1162/1848 [6:26:08<3:47:53, 19.93s/it]
 63%|██████▎   | 1163/1848 [6:26:27<3:47:08, 19.90s/it]
                                                       

 63%|██████▎   | 1163/1848 [6:26:27<3:47:08, 19.90s/it]
 63%|██████▎   | 1164/1848 [6:26:47<3:46:51, 19.90s/it]
                                                       

 63%|██████▎   | 1164/1848 [6:26:47<3:46:51, 19.90s/it]
 63%|██████▎   | 1165/1848 [6:27:07<3:46:35, 19.91s/it]
                                                       

 63%|██████▎   | 1165/1848 [6:27:07<3:46:35, 19.91s/it]
 63%|██████▎   | 1166/1848 [6:27:27<3:46:17, 19.91s/it]
                                                       

 63%|██████▎   | 1166/1848 [6:27:27<3:46:17, 19.91s/it]
 63%|██████▎   | 1167/1848 [6:27:47<3:46:11, 19.93s/it]
                                                       

 63%|██████▎   | 1167/1848 [6:27:47<3:46:11, 19.93s/it]
 63%|██████▎   | 1168/1848 [6:28:07<3:45:48, 19.92s/it]
                                                       

 63%|██████▎   | 1168/1848 [6:28:07<3:45:48, 19.92s/it]
 63%|██████▎   | 1169/1848 [6:28:27<3:45:30, 19.93s/it]
                                                       

 63%|██████▎   | 1169/1848 [6:28:27<3:45:30, 19.93s/it]
 63%|██████▎   | 1170/1848 [6:28:47<3:45:04, 19.92s/it]
                                                       

 63%|██████▎   | 1170/1848 [6:28:47<3:45:04, 19.92s/it]
 63%|██████▎   | 1171/1848 [6:29:07<3:44:44, 19.92s/it]
                                                       

 63%|██████▎   | 1171/1848 [6:29:07<3:44:44, 19.92s/it]
 63%|██████▎   | 1172/1848 [6:29:27<3:44:26, 19.92s/it]
                                                       

 63%|██████▎   | 1172/1848 [6:29:27<3:44:26, 19.92s/it]
 63%|██████▎   | 1173/1848 [6:29:47<3:43:53, 19.90s/it]
                                                       

 63%|██████▎   | 1173/1848 [6:29:47<3:43:53, 19.90s/it]
 64%|██████▎   | 1174/1848 [6:30:06<3:43:31, 19.90s/it]
                                                       

 64%|██████▎   | 1174/1848 [6:30:06<3:43:31, 19.90s/it]
 64%|██████▎   | 1175/1848 [6:30:26<3:43:12, 19.90s/it]
                                                       

 64%|██████▎   | 1175/1848 [6:30:26<3:43:12, 19.90s/it]
 64%|██████▎   | 1176/1848 [6:30:46<3:42:59, 19.91s/it]
                                                       

 64%|██████▎   | 1176/1848 [6:30:46<3:42:59, 19.91s/it]
 64%|██████▎   | 1177/1848 [6:31:06<3:42:44, 19.92s/it]
                                                       

 64%|██████▎   | 1177/1848 [6:31:06<3:42:44, 19.92s/it]
 64%|██████▎   | 1178/1848 [6:31:26<3:42:27, 19.92s/it]
                                                       

 64%|██████▎   | 1178/1848 [6:31:26<3:42:27, 19.92s/it]
 64%|██████▍   | 1179/1848 [6:31:46<3:42:22, 19.94s/it]
                                                       

 64%|██████▍   | 1179/1848 [6:31:46<3:42:22, 19.94s/it]
 64%|██████▍   | 1180/1848 [6:32:06<3:41:55, 19.93s/it]
                                                       

 64%|██████▍   | 1180/1848 [6:32:06<3:41:55, 19.93s/it]
 64%|██████▍   | 1181/1848 [6:32:26<3:41:33, 19.93s/it]
                                                       

 64%|██████▍   | 1181/1848 [6:32:26<3:41:33, 19.93s/it]
 64%|██████▍   | 1182/1848 [6:32:46<3:41:02, 19.91s/it]
                                                       

 64%|██████▍   | 1182/1848 [6:32:46<3:41:02, 19.91s/it]
 64%|██████▍   | 1183/1848 [6:33:06<3:40:43, 19.91s/it]
                                                       

 64%|██████▍   | 1183/1848 [6:33:06<3:40:43, 19.91s/it]
 64%|██████▍   | 1184/1848 [6:33:26<3:40:23, 19.91s/it]
                                                       

 64%|██████▍   | 1184/1848 [6:33:26<3:40:23, 19.91s/it]
 64%|██████▍   | 1185/1848 [6:33:46<3:40:09, 19.92s/it]
                                                       

 64%|██████▍   | 1185/1848 [6:33:46<3:40:09, 19.92s/it]
 64%|██████▍   | 1186/1848 [6:34:06<3:40:03, 19.95s/it]
                                                       

 64%|██████▍   | 1186/1848 [6:34:06<3:40:03, 19.95s/it]
 64%|██████▍   | 1187/1848 [6:34:26<3:39:45, 19.95s/it]
                                                       

 64%|██████▍   | 1187/1848 [6:34:26<3:39:45, 19.95s/it]
 64%|██████▍   | 1188/1848 [6:34:46<3:39:33, 19.96s/it]
                                                       

 64%|██████▍   | 1188/1848 [6:34:46<3:39:33, 19.96s/it]
 64%|██████▍   | 1189/1848 [6:35:05<3:38:56, 19.93s/it]
                                                       

 64%|██████▍   | 1189/1848 [6:35:05<3:38:56, 19.93s/it]
 64%|██████▍   | 1190/1848 [6:35:25<3:38:47, 19.95s/it]
                                                       

 64%|██████▍   | 1190/1848 [6:35:25<3:38:47, 19.95s/it]
 64%|██████▍   | 1191/1848 [6:35:45<3:38:17, 19.93s/it]
                                                       

 64%|██████▍   | 1191/1848 [6:35:45<3:38:17, 19.93s/it]
 65%|██████▍   | 1192/1848 [6:36:05<3:37:52, 19.93s/it]
                                                       

 65%|██████▍   | 1192/1848 [6:36:05<3:37:52, 19.93s/it]
 65%|██████▍   | 1193/1848 [6:36:25<3:37:37, 19.94s/it]
                                                       

 65%|██████▍   | 1193/1848 [6:36:25<3:37:37, 19.94s/it]
 65%|██████▍   | 1194/1848 [6:36:45<3:37:29, 19.95s/it]
                                                       

 65%|██████▍   | 1194/1848 [6:36:45<3:37:29, 19.95s/it]
 65%|██████▍   | 1195/1848 [6:37:05<3:37:01, 19.94s/it]
                                                       

 65%|██████▍   | 1195/1848 [6:37:05<3:37:01, 19.94s/it]
 65%|██████▍   | 1196/1848 [6:37:25<3:36:41, 19.94s/it]
                                                       

 65%|██████▍   | 1196/1848 [6:37:25<3:36:41, 19.94s/it]
 65%|██████▍   | 1197/1848 [6:37:45<3:36:14, 19.93s/it]
                                                       

 65%|██████▍   | 1197/1848 [6:37:45<3:36:14, 19.93s/it]
 65%|██████▍   | 1198/1848 [6:38:05<3:35:40, 19.91s/it]
                                                       

 65%|██████▍   | 1198/1848 [6:38:05<3:35:40, 19.91s/it]
 65%|██████▍   | 1199/1848 [6:38:25<3:35:14, 19.90s/it]
                                                       

 65%|██████▍   | 1199/1848 [6:38:25<3:35:14, 19.90s/it]
 65%|██████▍   | 1200/1848 [6:38:45<3:34:55, 19.90s/it]
                                                       

 65%|██████▍   | 1200/1848 [6:38:45<3:34:55, 19.90s/it]
 65%|██████▍   | 1201/1848 [6:39:05<3:37:35, 20.18s/it]
                                                       

 65%|██████▍   | 1201/1848 [6:39:05<3:37:35, 20.18s/it]
 65%|██████▌   | 1202/1848 [6:39:25<3:36:11, 20.08s/it]
                                                       

 65%|██████▌   | 1202/1848 [6:39:25<3:36:11, 20.08s/it]
 65%|██████▌   | 1203/1848 [6:39:45<3:35:19, 20.03s/it]
                                                       

 65%|██████▌   | 1203/1848 [6:39:45<3:35:19, 20.03s/it]
 65%|██████▌   | 1204/1848 [6:40:05<3:34:39, 20.00s/it]
                                                       

 65%|██████▌   | 1204/1848 [6:40:05<3:34:39, 20.00s/it]
 65%|██████▌   | 1205/1848 [6:40:25<3:34:02, 19.97s/it]
                                                       

 65%|██████▌   | 1205/1848 [6:40:25<3:34:02, 19.97s/it]
 65%|██████▌   | 1206/1848 [6:40:45<3:33:33, 19.96s/it]
                                                       

 65%|██████▌   | 1206/1848 [6:40:45<3:33:33, 19.96s/it]
 65%|██████▌   | 1207/1848 [6:41:05<3:33:03, 19.94s/it]
                                                       

 65%|██████▌   | 1207/1848 [6:41:05<3:33:03, 19.94s/it]
 65%|██████▌   | 1208/1848 [6:41:25<3:32:27, 19.92s/it]
                                                       

 65%|██████▌   | 1208/1848 [6:41:25<3:32:27, 19.92s/it]
 65%|██████▌   | 1209/1848 [6:41:45<3:32:07, 19.92s/it]
                                                       

 65%|██████▌   | 1209/1848 [6:41:45<3:32:07, 19.92s/it]
 65%|██████▌   | 1210/1848 [6:42:05<3:31:52, 19.93s/it]
                                                       

 65%|██████▌   | 1210/1848 [6:42:05<3:31:52, 19.93s/it]
 66%|██████▌   | 1211/1848 [6:42:24<3:31:24, 19.91s/it]
                                                       

 66%|██████▌   | 1211/1848 [6:42:24<3:31:24, 19.91s/it]
 66%|██████▌   | 1212/1848 [6:42:44<3:31:08, 19.92s/it]
                                                       

 66%|██████▌   | 1212/1848 [6:42:44<3:31:08, 19.92s/it]
 66%|██████▌   | 1213/1848 [6:43:04<3:30:49, 19.92s/it]
                                                       

 66%|██████▌   | 1213/1848 [6:43:04<3:30:49, 19.92s/it]
 66%|██████▌   | 1214/1848 [6:43:24<3:30:24, 19.91s/it]
                                                       

 66%|██████▌   | 1214/1848 [6:43:24<3:30:24, 19.91s/it]
 66%|██████▌   | 1215/1848 [6:43:44<3:30:05, 19.91s/it]
                                                       

 66%|██████▌   | 1215/1848 [6:43:44<3:30:05, 19.91s/it]
 66%|██████▌   | 1216/1848 [6:44:04<3:29:52, 19.92s/it]
                                                       

 66%|██████▌   | 1216/1848 [6:44:04<3:29:52, 19.92s/it]
 66%|██████▌   | 1217/1848 [6:44:24<3:29:27, 19.92s/it]
                                                       

 66%|██████▌   | 1217/1848 [6:44:24<3:29:27, 19.92s/it]
 66%|██████▌   | 1218/1848 [6:44:44<3:29:11, 19.92s/it]
                                                       

 66%|██████▌   | 1218/1848 [6:44:44<3:29:11, 19.92s/it]
 66%|██████▌   | 1219/1848 [6:45:04<3:28:45, 19.91s/it]
                                                       

 66%|██████▌   | 1219/1848 [6:45:04<3:28:45, 19.91s/it]
 66%|██████▌   | 1220/1848 [6:45:24<3:28:30, 19.92s/it]
                                                       

 66%|██████▌   | 1220/1848 [6:45:24<3:28:30, 19.92s/it]
 66%|██████▌   | 1221/1848 [6:45:44<3:28:07, 19.92s/it]
                                                       

 66%|██████▌   | 1221/1848 [6:45:44<3:28:07, 19.92s/it]
 66%|██████▌   | 1222/1848 [6:46:04<3:27:43, 19.91s/it]
                                                       

 66%|██████▌   | 1222/1848 [6:46:04<3:27:43, 19.91s/it]
 66%|██████▌   | 1223/1848 [6:46:23<3:27:21, 19.91s/it]
                                                       

 66%|██████▌   | 1223/1848 [6:46:23<3:27:21, 19.91s/it]
 66%|██████▌   | 1224/1848 [6:46:43<3:27:00, 19.90s/it]
                                                       

 66%|██████▌   | 1224/1848 [6:46:43<3:27:00, 19.90s/it]
 66%|██████▋   | 1225/1848 [6:47:03<3:26:43, 19.91s/it]
                                                       

 66%|██████▋   | 1225/1848 [6:47:03<3:26:43, 19.91s/it]
 66%|██████▋   | 1226/1848 [6:47:23<3:26:13, 19.89s/it]
                                                       

 66%|██████▋   | 1226/1848 [6:47:23<3:26:13, 19.89s/it]
 66%|██████▋   | 1227/1848 [6:47:43<3:26:06, 19.91s/it]
                                                       

 66%|██████▋   | 1227/1848 [6:47:43<3:26:06, 19.91s/it]
 66%|██████▋   | 1228/1848 [6:48:03<3:25:49, 19.92s/it]
                                                       

 66%|██████▋   | 1228/1848 [6:48:03<3:25:49, 19.92s/it]
 67%|██████▋   | 1229/1848 [6:48:23<3:25:24, 19.91s/it]
                                                       

 67%|██████▋   | 1229/1848 [6:48:23<3:25:24, 19.91s/it]
 67%|██████▋   | 1230/1848 [6:48:43<3:25:02, 19.91s/it]
                                                       

 67%|██████▋   | 1230/1848 [6:48:43<3:25:02, 19.91s/it]
 67%|██████▋   | 1231/1848 [6:49:03<3:24:45, 19.91s/it]
                                                       

 67%|██████▋   | 1231/1848 [6:49:03<3:24:45, 19.91s/it]
 67%|██████▋   | 1232/1848 [6:49:11<2:47:13, 16.29s/it]
                                                       

 67%|██████▋   | 1232/1848 [6:49:11<2:47:13, 16.29s/it]
 67%|██████▋   | 1233/1848 [6:49:30<2:58:08, 17.38s/it]
                                                       

 67%|██████▋   | 1233/1848 [6:49:30<2:58:08, 17.38s/it]
 67%|██████▋   | 1234/1848 [6:49:50<3:05:45, 18.15s/it]
                                                       

 67%|██████▋   | 1234/1848 [6:49:50<3:05:45, 18.15s/it]
 67%|██████▋   | 1235/1848 [6:50:10<3:11:01, 18.70s/it]
                                                       

 67%|██████▋   | 1235/1848 [6:50:10<3:11:01, 18.70s/it]
 67%|██████▋   | 1236/1848 [6:50:30<3:14:24, 19.06s/it]
                                                       

 67%|██████▋   | 1236/1848 [6:50:30<3:14:24, 19.06s/it]
 67%|██████���   | 1237/1848 [6:50:50<3:16:35, 19.31s/it]
                                                       

 67%|██████▋   | 1237/1848 [6:50:50<3:16:35, 19.31s/it]
 67%|██████▋   | 1238/1848 [6:51:10<3:18:06, 19.49s/it]
                                                       

 67%|██████▋   | 1238/1848 [6:51:10<3:18:06, 19.49s/it]
 67%|██████▋   | 1239/1848 [6:51:30<3:18:56, 19.60s/it]
                                                       

 67%|██████▋   | 1239/1848 [6:51:30<3:18:56, 19.60s/it]
 67%|██████▋   | 1240/1848 [6:51:50<3:19:26, 19.68s/it]
                                                       

 67%|██████▋   | 1240/1848 [6:51:50<3:19:26, 19.68s/it]
 67%|██████▋   | 1241/1848 [6:52:10<3:19:53, 19.76s/it]
                                                       

 67%|██████▋   | 1241/1848 [6:52:10<3:19:53, 19.76s/it]
 67%|██████▋   | 1242/1848 [6:52:30<3:20:20, 19.84s/it]
                                                       

 67%|██████▋   | 1242/1848 [6:52:30<3:20:20, 19.84s/it]
 67%|██████▋   | 1243/1848 [6:52:50<3:20:10, 19.85s/it]
                                                       

 67%|██████▋   | 1243/1848 [6:52:50<3:20:10, 19.85s/it]
 67%|██████▋   | 1244/1848 [6:53:10<3:20:02, 19.87s/it]
                                                       

 67%|██████▋   | 1244/1848 [6:53:10<3:20:02, 19.87s/it]
 67%|██████▋   | 1245/1848 [6:53:29<3:19:44, 19.87s/it]
                                                       

 67%|██████▋   | 1245/1848 [6:53:29<3:19:44, 19.87s/it]
 67%|██████▋   | 1246/1848 [6:53:49<3:19:28, 19.88s/it]
                                                       
{'loss': 1.2771, 'learning_rate': 5.462987012987013e-06, 'epoch': 1.84}
+{'loss': 0.9435, 'learning_rate': 5.455357142857143e-06, 'epoch': 1.84}
+{'loss': 1.2876, 'learning_rate': 5.447727272727273e-06, 'epoch': 1.84}
+{'loss': 1.5912, 'learning_rate': 5.440097402597403e-06, 'epoch': 1.84}
+{'loss': 1.2119, 'learning_rate': 5.432467532467533e-06, 'epoch': 1.84}
+{'loss': 1.2114, 'learning_rate': 5.424837662337662e-06, 'epoch': 1.85}
+{'loss': 1.2743, 'learning_rate': 5.417207792207792e-06, 'epoch': 1.85}
+{'loss': 1.3762, 'learning_rate': 5.409577922077922e-06, 'epoch': 1.85}
+{'loss': 1.2293, 'learning_rate': 5.4019480519480525e-06, 'epoch': 1.85}
+{'loss': 1.28, 'learning_rate': 5.394318181818182e-06, 'epoch': 1.85}
+{'loss': 1.2822, 'learning_rate': 5.386688311688313e-06, 'epoch': 1.85}
+{'loss': 1.4081, 'learning_rate': 5.379058441558441e-06, 'epoch': 1.86}
+{'loss': 1.3003, 'learning_rate': 5.371428571428571e-06, 'epoch': 1.86}
+{'loss': 1.2556, 'learning_rate': 5.3637987012987016e-06, 'epoch': 1.86}
+{'loss': 1.0489, 'learning_rate': 5.356168831168831e-06, 'epoch': 1.86}
+{'loss': 1.114, 'learning_rate': 5.348538961038962e-06, 'epoch': 1.86}
+{'loss': 1.3266, 'learning_rate': 5.340909090909091e-06, 'epoch': 1.86}
+{'loss': 1.2424, 'learning_rate': 5.333279220779221e-06, 'epoch': 1.87}
+{'loss': 1.4534, 'learning_rate': 5.325649350649351e-06, 'epoch': 1.87}
+{'loss': 1.1446, 'learning_rate': 5.31801948051948e-06, 'epoch': 1.87}
+{'loss': 1.3131, 'learning_rate': 5.310389610389611e-06, 'epoch': 1.87}
+{'loss': 1.4133, 'learning_rate': 5.3027597402597405e-06, 'epoch': 1.87}
+{'loss': 1.0769, 'learning_rate': 5.295129870129871e-06, 'epoch': 1.87}
+{'loss': 1.0921, 'learning_rate': 5.2875e-06, 'epoch': 1.88}
+{'loss': 1.1035, 'learning_rate': 5.2798701298701294e-06, 'epoch': 1.88}
+{'loss': 1.3811, 'learning_rate': 5.27224025974026e-06, 'epoch': 1.88}
+{'loss': 1.2665, 'learning_rate': 5.2646103896103896e-06, 'epoch': 1.88}
+{'loss': 1.1038, 'learning_rate': 5.25698051948052e-06, 'epoch': 1.88}
+{'loss': 1.1658, 'learning_rate': 5.24935064935065e-06, 'epoch': 1.88}
+{'loss': 1.2704, 'learning_rate': 5.241720779220779e-06, 'epoch': 1.88}
+{'loss': 1.2266, 'learning_rate': 5.234090909090909e-06, 'epoch': 1.89}
+{'loss': 1.3456, 'learning_rate': 5.226461038961039e-06, 'epoch': 1.89}
+{'loss': 1.363, 'learning_rate': 5.218831168831169e-06, 'epoch': 1.89}
+{'loss': 1.1507, 'learning_rate': 5.211201298701299e-06, 'epoch': 1.89}
+{'loss': 1.2236, 'learning_rate': 5.203571428571429e-06, 'epoch': 1.89}
+{'loss': 1.0927, 'learning_rate': 5.195941558441559e-06, 'epoch': 1.89}
+{'loss': 1.374, 'learning_rate': 5.188311688311688e-06, 'epoch': 1.9}
+{'loss': 1.2453, 'learning_rate': 5.180681818181818e-06, 'epoch': 1.9}
+{'loss': 1.0457, 'learning_rate': 5.173051948051948e-06, 'epoch': 1.9}
+{'loss': 1.2628, 'learning_rate': 5.1654220779220784e-06, 'epoch': 1.9}
+{'loss': 1.1305, 'learning_rate': 5.157792207792208e-06, 'epoch': 1.9}
+{'loss': 1.4142, 'learning_rate': 5.150162337662339e-06, 'epoch': 1.9}
+{'loss': 1.3279, 'learning_rate': 5.142532467532467e-06, 'epoch': 1.91}
+{'loss': 1.2106, 'learning_rate': 5.134902597402597e-06, 'epoch': 1.91}
+{'loss': 1.2259, 'learning_rate': 5.1272727272727275e-06, 'epoch': 1.91}
+{'loss': 1.2168, 'learning_rate': 5.119642857142857e-06, 'epoch': 1.91}
+{'loss': 1.3623, 'learning_rate': 5.112012987012988e-06, 'epoch': 1.91}
+{'loss': 1.0661, 'learning_rate': 5.104383116883117e-06, 'epoch': 1.91}
+{'loss': 1.1379, 'learning_rate': 5.096753246753246e-06, 'epoch': 1.92}
+{'loss': 1.3847, 'learning_rate': 5.089123376623377e-06, 'epoch': 1.92}
+{'loss': 1.3082, 'learning_rate': 5.081493506493506e-06, 'epoch': 1.92}
+{'loss': 0.9827, 'learning_rate': 5.073863636363637e-06, 'epoch': 1.92}
+{'loss': 1.3036, 'learning_rate': 5.0662337662337664e-06, 'epoch': 1.92}
+{'loss': 1.148, 'learning_rate': 5.058603896103897e-06, 'epoch': 1.92}
+{'loss': 1.4213, 'learning_rate': 5.050974025974026e-06, 'epoch': 1.93}
+{'loss': 1.1937, 'learning_rate': 5.043344155844155e-06, 'epoch': 1.93}
+{'loss': 1.2717, 'learning_rate': 5.035714285714286e-06, 'epoch': 1.93}
+{'loss': 1.0978, 'learning_rate': 5.0280844155844156e-06, 'epoch': 1.93}
+{'loss': 1.1653, 'learning_rate': 5.020454545454546e-06, 'epoch': 1.93}
+{'loss': 1.2085, 'learning_rate': 5.012824675324676e-06, 'epoch': 1.93}
+{'loss': 1.114, 'learning_rate': 5.005194805194805e-06, 'epoch': 1.94}
+{'loss': 1.2008, 'learning_rate': 4.997564935064935e-06, 'epoch': 1.94}
+{'loss': 1.2008, 'learning_rate': 4.989935064935065e-06, 'epoch': 1.94}
+{'loss': 1.3505, 'learning_rate': 4.982305194805195e-06, 'epoch': 1.94}
+{'loss': 1.1827, 'learning_rate': 4.974675324675325e-06, 'epoch': 1.94}
+{'loss': 1.0622, 'learning_rate': 4.967045454545455e-06, 'epoch': 1.94}
+{'loss': 1.5759, 'learning_rate': 4.959415584415585e-06, 'epoch': 1.94}
+{'loss': 1.3996, 'learning_rate': 4.951785714285714e-06, 'epoch': 1.95}
+{'loss': 1.3678, 'learning_rate': 4.944155844155844e-06, 'epoch': 1.95}
+{'loss': 1.1498, 'learning_rate': 4.936525974025974e-06, 'epoch': 1.95}
+{'loss': 1.1411, 'learning_rate': 4.928896103896104e-06, 'epoch': 1.95}
+{'loss': 1.2244, 'learning_rate': 4.921266233766234e-06, 'epoch': 1.95}
+{'loss': 1.0235, 'learning_rate': 4.9136363636363646e-06, 'epoch': 1.95}
+{'loss': 1.1712, 'learning_rate': 4.906006493506493e-06, 'epoch': 1.96}
+{'loss': 1.1322, 'learning_rate': 4.898376623376623e-06, 'epoch': 1.96}
+{'loss': 1.2903, 'learning_rate': 4.8907467532467535e-06, 'epoch': 1.96}
+{'loss': 1.3377, 'learning_rate': 4.883116883116883e-06, 'epoch': 1.96}
+{'loss': 1.2791, 'learning_rate': 4.875487012987014e-06, 'epoch': 1.96}
+{'loss': 1.1251, 'learning_rate': 4.867857142857143e-06, 'epoch': 1.96}
+{'loss': 1.1606, 'learning_rate': 4.860227272727273e-06, 'epoch': 1.97}
+{'loss': 1.3742, 'learning_rate': 4.852597402597403e-06, 'epoch': 1.97}
+{'loss': 1.2147, 'learning_rate': 4.844967532467532e-06, 'epoch': 1.97}
+{'loss': 1.174, 'learning_rate': 4.837337662337663e-06, 'epoch': 1.97}
+{'loss': 1.1308, 'learning_rate': 4.8297077922077924e-06, 'epoch': 1.97}
+{'loss': 1.151, 'learning_rate': 4.822077922077923e-06, 'epoch': 1.97}
+{'loss': 1.1989, 'learning_rate': 4.814448051948052e-06, 'epoch': 1.98}
+{'loss': 1.1799, 'learning_rate': 4.806818181818181e-06, 'epoch': 1.98}
+{'loss': 1.0103, 'learning_rate': 4.799188311688312e-06, 'epoch': 1.98}
+{'loss': 0.9693, 'learning_rate': 4.7915584415584415e-06, 'epoch': 1.98}
+{'loss': 1.5067, 'learning_rate': 4.783928571428572e-06, 'epoch': 1.98}
+{'loss': 1.3291, 'learning_rate': 4.776298701298702e-06, 'epoch': 1.98}
+{'loss': 1.1311, 'learning_rate': 4.768668831168831e-06, 'epoch': 1.99}
+{'loss': 1.2407, 'learning_rate': 4.761038961038961e-06, 'epoch': 1.99}
+{'loss': 1.1264, 'learning_rate': 4.753409090909091e-06, 'epoch': 1.99}
+{'loss': 1.3606, 'learning_rate': 4.745779220779221e-06, 'epoch': 1.99}
+{'loss': 1.1398, 'learning_rate': 4.738149350649351e-06, 'epoch': 1.99}
+{'loss': 1.4493, 'learning_rate': 4.730519480519481e-06, 'epoch': 1.99}
+{'loss': 1.2783, 'learning_rate': 4.72288961038961e-06, 'epoch': 2.0}
+{'loss': 1.2723, 'learning_rate': 4.71525974025974e-06, 'epoch': 2.0}
+{'loss': 1.3532, 'learning_rate': 4.70762987012987e-06, 'epoch': 2.0}
+{'loss': 1.1159, 'learning_rate': 4.7e-06, 'epoch': 2.0}
+{'loss': 1.2903, 'learning_rate': 4.69237012987013e-06, 'epoch': 2.0}
+{'loss': 1.1813, 'learning_rate': 4.68474025974026e-06, 'epoch': 2.0}
+{'loss': 1.1797, 'learning_rate': 4.67711038961039e-06, 'epoch': 2.0}
+{'loss': 1.3245, 'learning_rate': 4.669480519480519e-06, 'epoch': 2.01}
+{'loss': 1.3485, 'learning_rate': 4.661850649350649e-06, 'epoch': 2.01}
+{'loss': 1.1953, 'learning_rate': 4.6542207792207795e-06, 'epoch': 2.01}
+{'loss': 1.2146, 'learning_rate': 4.646590909090909e-06, 'epoch': 2.01}
+{'loss': 1.2431, 'learning_rate': 4.63896103896104e-06, 'epoch': 2.01}
+{'loss': 1.3553, 'learning_rate': 4.631331168831169e-06, 'epoch': 2.01}
+{'loss': 0.9906, 'learning_rate': 4.623701298701299e-06, 'epoch': 2.02}
+{'loss': 1.3134, 'learning_rate': 4.616071428571429e-06, 'epoch': 2.02}
+{'loss': 1.3398, 'learning_rate': 4.608441558441558e-06, 'epoch': 2.02}
+{'loss': 1.2985, 'learning_rate': 4.600811688311689e-06, 'epoch': 2.02}
+
 67%|██████▋   | 1246/1848 [6:53:49<3:19:28, 19.88s/it]
 67%|███��██▋   | 1247/1848 [6:54:09<3:19:15, 19.89s/it]
                                                       

 67%|██████▋   | 1247/1848 [6:54:09<3:19:15, 19.89s/it]
 68%|██████▊   | 1248/1848 [6:54:29<3:19:06, 19.91s/it]
                                                       

 68%|██████▊   | 1248/1848 [6:54:29<3:19:06, 19.91s/it]
 68%|██████▊   | 1249/1848 [6:54:49<3:18:51, 19.92s/it]
                                                       

 68%|██████▊   | 1249/1848 [6:54:49<3:18:51, 19.92s/it]
 68%|██████▊   | 1250/1848 [6:55:09<3:18:29, 19.92s/it]
                                                       

 68%|██████▊   | 1250/1848 [6:55:09<3:18:29, 19.92s/it]
 68%|██████▊   | 1251/1848 [6:55:29<3:18:02, 19.90s/it]
                                                       

 68%|██████▊   | 1251/1848 [6:55:29<3:18:02, 19.90s/it]
 68%|██████▊   | 1252/1848 [6:55:49<3:17:41, 19.90s/it]
                                                       

 68%|██████▊   | 1252/1848 [6:55:49<3:17:41, 19.90s/it]
 68%|██████▊   | 1253/1848 [6:56:09<3:17:22, 19.90s/it]
                                                       

 68%|██████▊   | 1253/1848 [6:56:09<3:17:22, 19.90s/it]
 68%|██████▊   | 1254/1848 [6:56:29<3:17:05, 19.91s/it]
                                                       

 68%|██████▊   | 1254/1848 [6:56:29<3:17:05, 19.91s/it]
 68%|██████▊   | 1255/1848 [6:56:49<3:17:03, 19.94s/it]
                                                       

 68%|██████▊   | 1255/1848 [6:56:49<3:17:03, 19.94s/it]
 68%|██████▊   | 1256/1848 [6:57:09<3:16:34, 19.92s/it]
                                                       

 68%|██████▊   | 1256/1848 [6:57:09<3:16:34, 19.92s/it]
 68%|██████▊   | 1257/1848 [6:57:28<3:16:11, 19.92s/it]
                                                       

 68%|██████▊   | 1257/1848 [6:57:28<3:16:11, 19.92s/it]
 68%|██████▊   | 1258/1848 [6:57:48<3:15:54, 19.92s/it]
                                                       

 68%|██████▊   | 1258/1848 [6:57:48<3:15:54, 19.92s/it]
 68%|██████▊   | 1259/1848 [6:58:08<3:15:44, 19.94s/it]
                                                       

 68%|██████▊   | 1259/1848 [6:58:08<3:15:44, 19.94s/it]
 68%|██████▊   | 1260/1848 [6:58:28<3:15:20, 19.93s/it]
                                                       

 68%|██████▊   | 1260/1848 [6:58:28<3:15:20, 19.93s/it]
 68%|██████▊   | 1261/1848 [6:58:48<3:15:07, 19.95s/it]
                                                       

 68%|██████▊   | 1261/1848 [6:58:48<3:15:07, 19.95s/it]
 68%|██████▊   | 1262/1848 [6:59:08<3:14:26, 19.91s/it]
                                                       

 68%|██████▊   | 1262/1848 [6:59:08<3:14:26, 19.91s/it]
 68%|██████▊   | 1263/1848 [6:59:28<3:14:06, 19.91s/it]
                                                       

 68%|██████▊   | 1263/1848 [6:59:28<3:14:06, 19.91s/it]
 68%|██████▊   | 1264/1848 [6:59:48<3:13:54, 19.92s/it]
                                                       

 68%|██████▊   | 1264/1848 [6:59:48<3:13:54, 19.92s/it]
 68%|██████▊   | 1265/1848 [7:00:08<3:13:35, 19.92s/it]
                                                       

 68%|██████▊   | 1265/1848 [7:00:08<3:13:35, 19.92s/it]
 69%|██████▊   | 1266/1848 [7:00:28<3:13:18, 19.93s/it]
                                                       

 69%|██████▊   | 1266/1848 [7:00:28<3:13:18, 19.93s/it]
 69%|██████▊   | 1267/1848 [7:00:48<3:12:55, 19.92s/it]
                                                       

 69%|██████▊   | 1267/1848 [7:00:48<3:12:55, 19.92s/it]
 69%|██████▊   | 1268/1848 [7:01:08<3:12:35, 19.92s/it]
                                                       

 69%|██████▊   | 1268/1848 [7:01:08<3:12:35, 19.92s/it]
 69%|██████▊   | 1269/1848 [7:01:28<3:12:24, 19.94s/it]
                                                       

 69%|██████▊   | 1269/1848 [7:01:28<3:12:24, 19.94s/it]
 69%|██████▊   | 1270/1848 [7:01:48<3:11:48, 19.91s/it]
                                                       

 69%|██████▊   | 1270/1848 [7:01:48<3:11:48, 19.91s/it]
 69%|██████▉   | 1271/1848 [7:02:07<3:11:27, 19.91s/it]
                                                       

 69%|██████▉   | 1271/1848 [7:02:07<3:11:27, 19.91s/it]
 69%|██████▉   | 1272/1848 [7:02:27<3:11:01, 19.90s/it]
                                                       

 69%|██████▉   | 1272/1848 [7:02:27<3:11:01, 19.90s/it]
 69%|██████▉   | 1273/1848 [7:02:47<3:10:50, 19.91s/it]
                                                       

 69%|██████▉   | 1273/1848 [7:02:47<3:10:50, 19.91s/it]
 69%|██████▉   | 1274/1848 [7:03:07<3:10:37, 19.93s/it]
                                                       

 69%|██████▉   | 1274/1848 [7:03:07<3:10:37, 19.93s/it]
 69%|██████▉   | 1275/1848 [7:03:27<3:10:19, 19.93s/it]
                                                       

 69%|██████▉   | 1275/1848 [7:03:27<3:10:19, 19.93s/it]
 69%|██████▉   | 1276/1848 [7:03:47<3:09:55, 19.92s/it]
                                                       

 69%|██████▉   | 1276/1848 [7:03:47<3:09:55, 19.92s/it]
 69%|██████▉   | 1277/1848 [7:04:07<3:09:35, 19.92s/it]
                                                       

 69%|██████▉   | 1277/1848 [7:04:07<3:09:35, 19.92s/it]
 69%|██████▉   | 1278/1848 [7:04:27<3:09:02, 19.90s/it]
                                                       

 69%|██████▉   | 1278/1848 [7:04:27<3:09:02, 19.90s/it]
 69%|██████▉   | 1279/1848 [7:04:47<3:08:43, 19.90s/it]
                                                       

 69%|██████▉   | 1279/1848 [7:04:47<3:08:43, 19.90s/it]
 69%|██████▉   | 1280/1848 [7:05:07<3:08:28, 19.91s/it]
                                                       

 69%|██████▉   | 1280/1848 [7:05:07<3:08:28, 19.91s/it]
 69%|██████▉   | 1281/1848 [7:05:27<3:08:11, 19.91s/it]
                                                       

 69%|██████▉   | 1281/1848 [7:05:27<3:08:11, 19.91s/it]
 69%|██████▉   | 1282/1848 [7:05:47<3:07:58, 19.93s/it]
                                                       

 69%|██████▉   | 1282/1848 [7:05:47<3:07:58, 19.93s/it]
 69%|██████▉   | 1283/1848 [7:06:06<3:07:36, 19.92s/it]
                                                       

 69%|██████▉   | 1283/1848 [7:06:06<3:07:36, 19.92s/it]
 69%|██████▉   | 1284/1848 [7:06:26<3:07:18, 19.93s/it]
                                                       

 69%|██████▉   | 1284/1848 [7:06:26<3:07:18, 19.93s/it]
 70%|██████▉   | 1285/1848 [7:06:46<3:07:02, 19.93s/it]
                                                       

 70%|██████▉   | 1285/1848 [7:06:46<3:07:02, 19.93s/it]
 70%|██████▉   | 1286/1848 [7:07:06<3:06:53, 19.95s/it]
                                                       

 70%|██████▉   | 1286/1848 [7:07:06<3:06:53, 19.95s/it]
 70%|██████▉   | 1287/1848 [7:07:26<3:06:20, 19.93s/it]
                                                       

 70%|██████▉   | 1287/1848 [7:07:26<3:06:20, 19.93s/it]
 70%|██████▉   | 1288/1848 [7:07:46<3:05:43, 19.90s/it]
                                                       

 70%|██████▉   | 1288/1848 [7:07:46<3:05:43, 19.90s/it]
 70%|██████▉   | 1289/1848 [7:08:06<3:05:22, 19.90s/it]
                                                       

 70%|██████▉   | 1289/1848 [7:08:06<3:05:22, 19.90s/it]
 70%|██████▉   | 1290/1848 [7:08:26<3:04:45, 19.87s/it]
                                                       

 70%|██████▉   | 1290/1848 [7:08:26<3:04:45, 19.87s/it]
 70%|██████▉   | 1291/1848 [7:08:46<3:04:31, 19.88s/it]
                                                       

 70%|██████▉   | 1291/1848 [7:08:46<3:04:31, 19.88s/it]
 70%|██████▉   | 1292/1848 [7:09:06<3:04:15, 19.88s/it]
                                                       

 70%|██████▉   | 1292/1848 [7:09:06<3:04:15, 19.88s/it]
 70%|██████▉   | 1293/1848 [7:09:25<3:03:57, 19.89s/it]
                                                       

 70%|██████▉   | 1293/1848 [7:09:25<3:03:57, 19.89s/it]
 70%|███████   | 1294/1848 [7:09:45<3:03:33, 19.88s/it]
                                                       

 70%|███████   | 1294/1848 [7:09:45<3:03:33, 19.88s/it]
 70%|███████   | 1295/1848 [7:10:05<3:03:30, 19.91s/it]
                                                       

 70%|███████   | 1295/1848 [7:10:05<3:03:30, 19.91s/it]
 70%|███████   | 1296/1848 [7:10:25<3:03:02, 19.90s/it]
                                                       

 70%|███████   | 1296/1848 [7:10:25<3:03:02, 19.90s/it]
 70%|███████   | 1297/1848 [7:10:45<3:02:41, 19.89s/it]
                                                       

 70%|███████   | 1297/1848 [7:10:45<3:02:41, 19.89s/it]
 70%|███████   | 1298/1848 [7:11:05<3:02:30, 19.91s/it]
                                                       

 70%|███████   | 1298/1848 [7:11:05<3:02:30, 19.91s/it]
 70%|██���████   | 1299/1848 [7:11:25<3:01:58, 19.89s/it]
                                                       

 70%|███████   | 1299/1848 [7:11:25<3:01:58, 19.89s/it]
 70%|███████   | 1300/1848 [7:11:45<3:01:46, 19.90s/it]
                                                       

 70%|███████   | 1300/1848 [7:11:45<3:01:46, 19.90s/it]
 70%|███████   | 1301/1848 [7:12:06<3:03:57, 20.18s/it]
                                                       

 70%|███████   | 1301/1848 [7:12:06<3:03:57, 20.18s/it]
 70%|███████   | 1302/1848 [7:12:26<3:03:08, 20.13s/it]
                                                       

 70%|███████   | 1302/1848 [7:12:26<3:03:08, 20.13s/it]
 71%|███████   | 1303/1848 [7:12:45<3:02:05, 20.05s/it]
                                                       

 71%|███████   | 1303/1848 [7:12:45<3:02:05, 20.05s/it]
 71%|███████   | 1304/1848 [7:13:05<3:01:13, 19.99s/it]
                                                       

 71%|███████   | 1304/1848 [7:13:05<3:01:13, 19.99s/it]
 71%|███████   | 1305/1848 [7:13:25<3:00:40, 19.96s/it]
                                                       

 71%|███████   | 1305/1848 [7:13:25<3:00:40, 19.96s/it]
 71%|███████   | 1306/1848 [7:13:45<3:00:20, 19.96s/it]
                                                       

 71%|███████   | 1306/1848 [7:13:45<3:00:20, 19.96s/it]
 71%|███████   | 1307/1848 [7:14:05<2:59:54, 19.95s/it]
                                                       

 71%|███████   | 1307/1848 [7:14:05<2:59:54, 19.95s/it]
 71%|███████   | 1308/1848 [7:14:25<2:59:19, 19.93s/it]
                                                       

 71%|███████   | 1308/1848 [7:14:25<2:59:19, 19.93s/it]
 71%|███████   | 1309/1848 [7:14:45<2:59:05, 19.94s/it]
                                                       

 71%|███████   | 1309/1848 [7:14:45<2:59:05, 19.94s/it]
 71%|███████   | 1310/1848 [7:15:05<2:58:50, 19.94s/it]
                                                       

 71%|███████   | 1310/1848 [7:15:05<2:58:50, 19.94s/it]
 71%|███████   | 1311/1848 [7:15:25<2:58:44, 19.97s/it]
                                                       

 71%|███████   | 1311/1848 [7:15:25<2:58:44, 19.97s/it]
 71%|███████   | 1312/1848 [7:15:45<2:58:14, 19.95s/it]
                                                       

 71%|███████   | 1312/1848 [7:15:45<2:58:14, 19.95s/it]
 71%|███████   | 1313/1848 [7:16:05<2:57:40, 19.93s/it]
                                                       

 71%|███████   | 1313/1848 [7:16:05<2:57:40, 19.93s/it]
 71%|███████   | 1314/1848 [7:16:24<2:57:01, 19.89s/it]
                                                       

 71%|███████   | 1314/1848 [7:16:24<2:57:01, 19.89s/it]
 71%|███████   | 1315/1848 [7:16:44<2:56:46, 19.90s/it]
                                                       

 71%|███████   | 1315/1848 [7:16:44<2:56:46, 19.90s/it]
 71%|███████   | 1316/1848 [7:17:04<2:56:29, 19.91s/it]
                                                       

 71%|███████   | 1316/1848 [7:17:04<2:56:29, 19.91s/it]
 71%|███████▏  | 1317/1848 [7:17:24<2:56:08, 19.90s/it]
                                                       

 71%|███████▏  | 1317/1848 [7:17:24<2:56:08, 19.90s/it]
 71%|███████▏  | 1318/1848 [7:17:44<2:55:44, 19.89s/it]
                                                       

 71%|███████▏  | 1318/1848 [7:17:44<2:55:44, 19.89s/it]
 71%|███████▏  | 1319/1848 [7:18:04<2:55:30, 19.91s/it]
                                                       

 71%|███████▏  | 1319/1848 [7:18:04<2:55:30, 19.91s/it]
 71%|███████▏  | 1320/1848 [7:18:24<2:54:55, 19.88s/it]
                                                       

 71%|███████▏  | 1320/1848 [7:18:24<2:54:55, 19.88s/it]
 71%|███████▏  | 1321/1848 [7:18:44<2:54:38, 19.88s/it]
                                                       

 71%|███████▏  | 1321/1848 [7:18:44<2:54:38, 19.88s/it]
 72%|███████▏  | 1322/1848 [7:19:04<2:54:22, 19.89s/it]
                                                       

 72%|███████▏  | 1322/1848 [7:19:04<2:54:22, 19.89s/it]
 72%|███████▏  | 1323/1848 [7:19:23<2:53:58, 19.88s/it]
                                                       

 72%|███████▏  | 1323/1848 [7:19:23<2:53:58, 19.88s/it]
 72%|███████▏  | 1324/1848 [7:19:43<2:53:52, 19.91s/it]
                                                       

 72%|███████▏  | 1324/1848 [7:19:43<2:53:52, 19.91s/it]
 72%|███████▏  | 1325/1848 [7:20:03<2:53:43, 19.93s/it]
                                                       

 72%|███████▏  | 1325/1848 [7:20:03<2:53:43, 19.93s/it]
 72%|███████▏  | 1326/1848 [7:20:23<2:53:25, 19.93s/it]
                                                       

 72%|███████▏  | 1326/1848 [7:20:23<2:53:25, 19.93s/it]
 72%|███████▏  | 1327/1848 [7:20:43<2:52:52, 19.91s/it]
                                                       

 72%|███████▏  | 1327/1848 [7:20:43<2:52:52, 19.91s/it]
 72%|███████▏  | 1328/1848 [7:21:03<2:52:31, 19.91s/it]
                                                       

 72%|███████▏  | 1328/1848 [7:21:03<2:52:31, 19.91s/it]
 72%|███████▏  | 1329/1848 [7:21:23<2:52:07, 19.90s/it]
                                                       

 72%|███████▏  | 1329/1848 [7:21:23<2:52:07, 19.90s/it]
 72%|███████▏  | 1330/1848 [7:21:43<2:51:52, 19.91s/it]
                                                       

 72%|███████▏  | 1330/1848 [7:21:43<2:51:52, 19.91s/it]
 72%|███████▏  | 1331/1848 [7:22:03<2:51:37, 19.92s/it]
                                                       

 72%|███████▏  | 1331/1848 [7:22:03<2:51:37, 19.92s/it]
 72%|███████▏  | 1332/1848 [7:22:23<2:51:16, 19.92s/it]
                                                       

 72%|███████▏  | 1332/1848 [7:22:23<2:51:16, 19.92s/it]
 72%|███████▏  | 1333/1848 [7:22:43<2:51:07, 19.94s/it]
                                                       

 72%|███████▏  | 1333/1848 [7:22:43<2:51:07, 19.94s/it]
 72%|███████▏  | 1334/1848 [7:23:03<2:50:52, 19.95s/it]
                                                       

 72%|███████▏  | 1334/1848 [7:23:03<2:50:52, 19.95s/it]
 72%|███████▏  | 1335/1848 [7:23:23<2:50:29, 19.94s/it]
                                                       

 72%|███████▏  | 1335/1848 [7:23:23<2:50:29, 19.94s/it]
 72%|███████▏  | 1336/1848 [7:23:43<2:50:10, 19.94s/it]
                                                       

 72%|███████▏  | 1336/1848 [7:23:43<2:50:10, 19.94s/it]
 72%|███████▏  | 1337/1848 [7:24:03<2:49:56, 19.95s/it]
                                                       

 72%|███████▏  | 1337/1848 [7:24:03<2:49:56, 19.95s/it]
 72%|███████▏  | 1338/1848 [7:24:23<2:49:36, 19.95s/it]
                                                       

 72%|███████▏  | 1338/1848 [7:24:23<2:49:36, 19.95s/it]
 72%|███████▏  | 1339/1848 [7:24:42<2:49:06, 19.93s/it]
                                                       

 72%|███████▏  | 1339/1848 [7:24:42<2:49:06, 19.93s/it]
 73%|███████▎  | 1340/1848 [7:25:02<2:48:48, 19.94s/it]
                                                       

 73%|███████▎  | 1340/1848 [7:25:02<2:48:48, 19.94s/it]
 73%|███████▎  | 1341/1848 [7:25:22<2:48:27, 19.94s/it]
                                                       

 73%|███████▎  | 1341/1848 [7:25:22<2:48:27, 19.94s/it]
 73%|███████▎  | 1342/1848 [7:25:42<2:48:17, 19.96s/it]
                                                       

 73%|███████▎  | 1342/1848 [7:25:42<2:48:17, 19.96s/it]
 73%|███████▎  | 1343/1848 [7:26:02<2:47:53, 19.95s/it]
                                                       

 73%|███████▎  | 1343/1848 [7:26:02<2:47:53, 19.95s/it]
 73%|███████▎  | 1344/1848 [7:26:22<2:47:36, 19.95s/it]
                                                       

 73%|███████▎  | 1344/1848 [7:26:22<2:47:36, 19.95s/it]
 73%|███████▎  | 1345/1848 [7:26:42<2:47:23, 19.97s/it]
                                                       

 73%|███████▎  | 1345/1848 [7:26:42<2:47:23, 19.97s/it]
 73%|███████▎  | 1346/1848 [7:27:02<2:46:54, 19.95s/it]
                                                       

 73%|███████▎  | 1346/1848 [7:27:02<2:46:54, 19.95s/it]
 73%|███████▎  | 1347/1848 [7:27:22<2:46:22, 19.92s/it]
                                                       

 73%|███████▎  | 1347/1848 [7:27:22<2:46:22, 19.92s/it]
 73%|███████▎  | 1348/1848 [7:27:42<2:46:00, 19.92s/it]
                                                       

 73%|███████▎  | 1348/1848 [7:27:42<2:46:00, 19.92s/it]
 73%|███████▎  | 1349/1848 [7:28:02<2:45:42, 19.92s/it]
                                                       

 73%|███████▎  | 1349/1848 [7:28:02<2:45:42, 19.92s/it]
 73%|███████▎  | 1350/1848 [7:28:22<2:45:29, 19.94s/it]
                                                       

 73%|███████▎  | 1350/1848 [7:28:22<2:45:29, 19.94s/it]
 73%|███████▎  | 1351/1848 [7:28:42<2:45:03, 19.93s/it]
                                                       

 73%|███████▎  | 1351/1848 [7:28:42<2:45:03, 19.93s/it]
 73%|███████▎  | 1352/1848 [7:29:02<2:44:36, 19.91s/it]
                                                       

 73%|███████▎  | 1352/1848 [7:29:02<2:44:36, 19.91s/it]
 73%|███████▎  | 1353/1848 [7:29:21<2:44:06, 19.89s/it]
                                                       

 73%|███████▎  | 1353/1848 [7:29:21<2:44:06, 19.89s/it]
 73%|███████▎  | 1354/1848 [7:29:41<2:43:41, 19.88s/it]
                                                       

 73%|███████▎  | 1354/1848 [7:29:41<2:43:41, 19.88s/it]
 73%|███████▎  | 1355/1848 [7:30:01<2:43:35, 19.91s/it]
                                                       

 73%|███████▎  | 1355/1848 [7:30:01<2:43:35, 19.91s/it]
 73%|███████▎  | 1356/1848 [7:30:21<2:43:17, 19.91s/it]
                                                       

 73%|███████▎  | 1356/1848 [7:30:21<2:43:17, 19.91s/it]
 73%|███████▎  | 1357/1848 [7:30:41<2:43:07, 19.93s/it]
                                                       

 73%|███████▎  | 1357/1848 [7:30:41<2:43:07, 19.93s/it]
 73%|███████▎  | 1358/1848 [7:31:01<2:42:50, 19.94s/it]
                                                       

 73%|███████▎  | 1358/1848 [7:31:01<2:42:50, 19.94s/it]
 74%|███████▎  | 1359/1848 [7:31:21<2:42:25, 19.93s/it]
                                                       

 74%|███████▎  | 1359/1848 [7:31:21<2:42:25, 19.93s/it]
 74%|███████▎  | 1360/1848 [7:31:41<2:42:05, 19.93s/it]
                                                       
{'loss': 1.341, 'learning_rate': 4.593181818181818e-06, 'epoch': 2.02}
+{'loss': 1.1802, 'learning_rate': 4.585551948051949e-06, 'epoch': 2.02}
+{'loss': 1.2107, 'learning_rate': 4.577922077922078e-06, 'epoch': 2.03}
+{'loss': 1.2933, 'learning_rate': 4.570292207792207e-06, 'epoch': 2.03}
+{'loss': 1.1152, 'learning_rate': 4.562662337662338e-06, 'epoch': 2.03}
+{'loss': 1.5377, 'learning_rate': 4.5550324675324675e-06, 'epoch': 2.03}
+{'loss': 1.2469, 'learning_rate': 4.547402597402598e-06, 'epoch': 2.03}
+{'loss': 1.2589, 'learning_rate': 4.539772727272728e-06, 'epoch': 2.03}
+{'loss': 1.2066, 'learning_rate': 4.532142857142857e-06, 'epoch': 2.04}
+{'loss': 1.2654, 'learning_rate': 4.524512987012987e-06, 'epoch': 2.04}
+{'loss': 1.1953, 'learning_rate': 4.516883116883117e-06, 'epoch': 2.04}
+{'loss': 1.0118, 'learning_rate': 4.509253246753247e-06, 'epoch': 2.04}
+{'loss': 1.074, 'learning_rate': 4.501623376623377e-06, 'epoch': 2.04}
+{'loss': 1.1395, 'learning_rate': 4.493993506493507e-06, 'epoch': 2.04}
+{'loss': 1.1219, 'learning_rate': 4.486363636363636e-06, 'epoch': 2.05}
+{'loss': 1.1061, 'learning_rate': 4.4787337662337666e-06, 'epoch': 2.05}
+{'loss': 1.4471, 'learning_rate': 4.471103896103896e-06, 'epoch': 2.05}
+{'loss': 1.2617, 'learning_rate': 4.463474025974026e-06, 'epoch': 2.05}
+{'loss': 1.1626, 'learning_rate': 4.455844155844156e-06, 'epoch': 2.05}
+{'loss': 1.3622, 'learning_rate': 4.448214285714286e-06, 'epoch': 2.05}
+{'loss': 1.1786, 'learning_rate': 4.440584415584416e-06, 'epoch': 2.06}
+{'loss': 1.2089, 'learning_rate': 4.432954545454545e-06, 'epoch': 2.06}
+{'loss': 1.0661, 'learning_rate': 4.425324675324675e-06, 'epoch': 2.06}
+{'loss': 1.1622, 'learning_rate': 4.4176948051948055e-06, 'epoch': 2.06}
+{'loss': 1.3039, 'learning_rate': 4.410064935064935e-06, 'epoch': 2.06}
+{'loss': 1.1374, 'learning_rate': 4.402435064935066e-06, 'epoch': 2.06}
+{'loss': 1.1936, 'learning_rate': 4.394805194805195e-06, 'epoch': 2.06}
+{'loss': 1.2793, 'learning_rate': 4.387175324675325e-06, 'epoch': 2.07}
+{'loss': 1.1982, 'learning_rate': 4.379545454545455e-06, 'epoch': 2.07}
+{'loss': 1.0253, 'learning_rate': 4.371915584415584e-06, 'epoch': 2.07}
+{'loss': 1.5499, 'learning_rate': 4.364285714285715e-06, 'epoch': 2.07}
+{'loss': 1.0498, 'learning_rate': 4.356655844155844e-06, 'epoch': 2.07}
+{'loss': 1.3855, 'learning_rate': 4.349025974025975e-06, 'epoch': 2.07}
+{'loss': 1.2256, 'learning_rate': 4.341396103896104e-06, 'epoch': 2.08}
+{'loss': 1.1731, 'learning_rate': 4.333766233766233e-06, 'epoch': 2.08}
+{'loss': 1.0955, 'learning_rate': 4.326136363636364e-06, 'epoch': 2.08}
+{'loss': 1.1817, 'learning_rate': 4.3185064935064935e-06, 'epoch': 2.08}
+{'loss': 1.2433, 'learning_rate': 4.310876623376624e-06, 'epoch': 2.08}
+{'loss': 1.327, 'learning_rate': 4.303246753246754e-06, 'epoch': 2.08}
+{'loss': 1.2831, 'learning_rate': 4.295616883116883e-06, 'epoch': 2.09}
+{'loss': 1.2586, 'learning_rate': 4.287987012987013e-06, 'epoch': 2.09}
+{'loss': 1.2962, 'learning_rate': 4.280357142857143e-06, 'epoch': 2.09}
+{'loss': 1.244, 'learning_rate': 4.272727272727273e-06, 'epoch': 2.09}
+{'loss': 1.3517, 'learning_rate': 4.265097402597403e-06, 'epoch': 2.09}
+{'loss': 1.0902, 'learning_rate': 4.257467532467533e-06, 'epoch': 2.09}
+{'loss': 1.3261, 'learning_rate': 4.249837662337662e-06, 'epoch': 2.1}
+{'loss': 1.2419, 'learning_rate': 4.2422077922077925e-06, 'epoch': 2.1}
+{'loss': 1.1154, 'learning_rate': 4.234577922077922e-06, 'epoch': 2.1}
+{'loss': 1.2889, 'learning_rate': 4.226948051948052e-06, 'epoch': 2.1}
+{'loss': 1.2209, 'learning_rate': 4.219318181818182e-06, 'epoch': 2.1}
+{'loss': 1.2253, 'learning_rate': 4.211688311688312e-06, 'epoch': 2.1}
+{'loss': 1.1469, 'learning_rate': 4.204058441558442e-06, 'epoch': 2.11}
+{'loss': 1.1486, 'learning_rate': 4.196428571428571e-06, 'epoch': 2.11}
+{'loss': 1.2625, 'learning_rate': 4.188798701298701e-06, 'epoch': 2.11}
+{'loss': 1.1972, 'learning_rate': 4.1811688311688315e-06, 'epoch': 2.11}
+{'loss': 1.1805, 'learning_rate': 4.173538961038961e-06, 'epoch': 2.11}
+{'loss': 1.0302, 'learning_rate': 4.165909090909092e-06, 'epoch': 2.11}
+{'loss': 1.477, 'learning_rate': 4.15827922077922e-06, 'epoch': 2.12}
+{'loss': 1.3875, 'learning_rate': 4.150649350649351e-06, 'epoch': 2.12}
+{'loss': 1.1173, 'learning_rate': 4.1430194805194806e-06, 'epoch': 2.12}
+{'loss': 1.3599, 'learning_rate': 4.13538961038961e-06, 'epoch': 2.12}
+{'loss': 1.2881, 'learning_rate': 4.127759740259741e-06, 'epoch': 2.12}
+{'loss': 1.2188, 'learning_rate': 4.12012987012987e-06, 'epoch': 2.12}
+{'loss': 1.1051, 'learning_rate': 4.1125e-06, 'epoch': 2.12}
+{'loss': 1.1606, 'learning_rate': 4.10487012987013e-06, 'epoch': 2.13}
+{'loss': 1.0658, 'learning_rate': 4.09724025974026e-06, 'epoch': 2.13}
+{'loss': 1.2999, 'learning_rate': 4.08961038961039e-06, 'epoch': 2.13}
+{'loss': 1.2345, 'learning_rate': 4.0819805194805195e-06, 'epoch': 2.13}
+{'loss': 1.3663, 'learning_rate': 4.07435064935065e-06, 'epoch': 2.13}
+{'loss': 1.2214, 'learning_rate': 4.06672077922078e-06, 'epoch': 2.13}
+{'loss': 1.3502, 'learning_rate': 4.059090909090909e-06, 'epoch': 2.14}
+{'loss': 1.3515, 'learning_rate': 4.051461038961039e-06, 'epoch': 2.14}
+{'loss': 1.2731, 'learning_rate': 4.0438311688311686e-06, 'epoch': 2.14}
+{'loss': 1.1019, 'learning_rate': 4.036201298701299e-06, 'epoch': 2.14}
+{'loss': 1.1673, 'learning_rate': 4.028571428571429e-06, 'epoch': 2.14}
+{'loss': 1.3234, 'learning_rate': 4.020941558441559e-06, 'epoch': 2.14}
+{'loss': 1.1617, 'learning_rate': 4.013311688311688e-06, 'epoch': 2.15}
+{'loss': 1.1013, 'learning_rate': 4.0056818181818185e-06, 'epoch': 2.15}
+{'loss': 1.3413, 'learning_rate': 3.998051948051948e-06, 'epoch': 2.15}
+{'loss': 1.3309, 'learning_rate': 3.990422077922078e-06, 'epoch': 2.15}
+{'loss': 1.3194, 'learning_rate': 3.982792207792208e-06, 'epoch': 2.15}
+{'loss': 1.2103, 'learning_rate': 3.975162337662338e-06, 'epoch': 2.15}
+{'loss': 1.1192, 'learning_rate': 3.967532467532468e-06, 'epoch': 2.16}
+{'loss': 1.353, 'learning_rate': 3.959902597402597e-06, 'epoch': 2.16}
+{'loss': 1.2012, 'learning_rate': 3.952272727272727e-06, 'epoch': 2.16}
+{'loss': 1.1703, 'learning_rate': 3.9446428571428574e-06, 'epoch': 2.16}
+{'loss': 1.1169, 'learning_rate': 3.937012987012987e-06, 'epoch': 2.16}
+{'loss': 1.2343, 'learning_rate': 3.929383116883118e-06, 'epoch': 2.16}
+{'loss': 1.1635, 'learning_rate': 3.921753246753246e-06, 'epoch': 2.17}
+{'loss': 1.237, 'learning_rate': 3.914123376623377e-06, 'epoch': 2.17}
+{'loss': 1.3182, 'learning_rate': 3.9064935064935065e-06, 'epoch': 2.17}
+{'loss': 1.1835, 'learning_rate': 3.898863636363636e-06, 'epoch': 2.17}
+{'loss': 1.1517, 'learning_rate': 3.891233766233767e-06, 'epoch': 2.17}
+{'loss': 1.2883, 'learning_rate': 3.883603896103896e-06, 'epoch': 2.17}
+{'loss': 1.308, 'learning_rate': 3.875974025974026e-06, 'epoch': 2.18}
+{'loss': 1.22, 'learning_rate': 3.868344155844156e-06, 'epoch': 2.18}
+{'loss': 1.2203, 'learning_rate': 3.860714285714286e-06, 'epoch': 2.18}
+{'loss': 1.348, 'learning_rate': 3.853084415584416e-06, 'epoch': 2.18}
+{'loss': 1.2379, 'learning_rate': 3.8454545454545454e-06, 'epoch': 2.18}
+{'loss': 1.2125, 'learning_rate': 3.837824675324676e-06, 'epoch': 2.18}
+{'loss': 1.1824, 'learning_rate': 3.830194805194806e-06, 'epoch': 2.19}
+{'loss': 1.392, 'learning_rate': 3.822564935064935e-06, 'epoch': 2.19}
+{'loss': 1.4542, 'learning_rate': 3.814935064935065e-06, 'epoch': 2.19}
+{'loss': 1.32, 'learning_rate': 3.8073051948051945e-06, 'epoch': 2.19}
+{'loss': 1.1149, 'learning_rate': 3.799675324675325e-06, 'epoch': 2.19}
+{'loss': 1.1154, 'learning_rate': 3.7920454545454543e-06, 'epoch': 2.19}
+{'loss': 1.2375, 'learning_rate': 3.7844155844155848e-06, 'epoch': 2.19}
+{'loss': 1.2141, 'learning_rate': 3.7767857142857144e-06, 'epoch': 2.2}
+{'loss': 1.2483, 'learning_rate': 3.7691558441558445e-06, 'epoch': 2.2}
+{'loss': 1.2984, 'learning_rate': 3.761525974025974e-06, 'epoch': 2.2}
+{'loss': 1.1493, 'learning_rate': 3.753896103896104e-06, 'epoch': 2.2}
+{'loss': 1.3939, 'learning_rate': 3.746266233766234e-06, 'epoch': 2.2}
+{'loss': 1.2434, 'learning_rate': 3.7386363636363635e-06, 'epoch': 2.2}
+{'loss': 1.3741, 'learning_rate': 3.731006493506494e-06, 'epoch': 2.21}
+
 74%|███████▎  | 1360/1848 [7:31:41<2:42:05, 19.93s/it]
 74%|███████▎  | 1361/1848 [7:32:01<2:41:56, 19.95s/it]
                                                       

 74%|███████▎  | 1361/1848 [7:32:01<2:41:56, 19.95s/it]
 74%|███████▎  | 1362/1848 [7:32:21<2:41:32, 19.94s/it]
                                                       

 74%|███████▎  | 1362/1848 [7:32:21<2:41:32, 19.94s/it]
 74%|███████▍  | 1363/1848 [7:32:41<2:40:54, 19.91s/it]
                                                       

 74%|███████▍  | 1363/1848 [7:32:41<2:40:54, 19.91s/it]
 74%|███████▍  | 1364/1848 [7:33:01<2:40:31, 19.90s/it]
                                                       

 74%|███████▍  | 1364/1848 [7:33:01<2:40:31, 19.90s/it]
 74%|███████▍  | 1365/1848 [7:33:20<2:40:08, 19.89s/it]
                                                       

 74%|███████▍  | 1365/1848 [7:33:20<2:40:08, 19.89s/it]
 74%|███████▍  | 1366/1848 [7:33:40<2:39:42, 19.88s/it]
                                                       

 74%|███████▍  | 1366/1848 [7:33:40<2:39:42, 19.88s/it]
 74%|███████▍  | 1367/1848 [7:34:00<2:39:19, 19.88s/it]
                                                       

 74%|███████▍  | 1367/1848 [7:34:00<2:39:19, 19.88s/it]
 74%|███████▍  | 1368/1848 [7:34:20<2:39:06, 19.89s/it]
                                                       

 74%|███████▍  | 1368/1848 [7:34:20<2:39:06, 19.89s/it]
 74%|███████▍  | 1369/1848 [7:34:40<2:38:36, 19.87s/it]
                                                       

 74%|███████▍  | 1369/1848 [7:34:40<2:38:36, 19.87s/it]
 74%|███████▍  | 1370/1848 [7:35:00<2:38:31, 19.90s/it]
                                                       

 74%|███████▍  | 1370/1848 [7:35:00<2:38:31, 19.90s/it]
 74%|███████▍  | 1371/1848 [7:35:20<2:38:19, 19.92s/it]
                                                       

 74%|███████▍  | 1371/1848 [7:35:20<2:38:19, 19.92s/it]
 74%|███████▍  | 1372/1848 [7:35:40<2:37:55, 19.91s/it]
                                                       

 74%|███████▍  | 1372/1848 [7:35:40<2:37:55, 19.91s/it]
 74%|███████▍  | 1373/1848 [7:36:00<2:37:34, 19.90s/it]
                                                       

 74%|███████▍  | 1373/1848 [7:36:00<2:37:34, 19.90s/it]
 74%|███████▍  | 1374/1848 [7:36:20<2:37:16, 19.91s/it]
                                                       

 74%|███████▍  | 1374/1848 [7:36:20<2:37:16, 19.91s/it]
 74%|███████▍  | 1375/1848 [7:36:40<2:37:07, 19.93s/it]
                                                       

 74%|███████▍  | 1375/1848 [7:36:40<2:37:07, 19.93s/it]
 74%|███████▍  | 1376/1848 [7:36:59<2:36:51, 19.94s/it]
                                                       

 74%|███████▍  | 1376/1848 [7:36:59<2:36:51, 19.94s/it]
 75%|███████▍  | 1377/1848 [7:37:19<2:36:26, 19.93s/it]
                                                       

 75%|███████▍  | 1377/1848 [7:37:19<2:36:26, 19.93s/it]
 75%|███████▍  | 1378/1848 [7:37:39<2:36:08, 19.93s/it]
                                                       

 75%|███████▍  | 1378/1848 [7:37:39<2:36:08, 19.93s/it]
 75%|███████▍  | 1379/1848 [7:37:59<2:35:43, 19.92s/it]
                                                       

 75%|███████▍  | 1379/1848 [7:37:59<2:35:43, 19.92s/it]
 75%|███████▍  | 1380/1848 [7:38:19<2:35:36, 19.95s/it]
                                                       

 75%|███████▍  | 1380/1848 [7:38:19<2:35:36, 19.95s/it]
 75%|███████▍  | 1381/1848 [7:38:39<2:35:18, 19.95s/it]
                                                       

 75%|███████▍  | 1381/1848 [7:38:39<2:35:18, 19.95s/it]
 75%|███████▍  | 1382/1848 [7:38:59<2:34:57, 19.95s/it]
                                                       

 75%|███████▍  | 1382/1848 [7:38:59<2:34:57, 19.95s/it]
 75%|███████▍  | 1383/1848 [7:39:19<2:34:37, 19.95s/it]
                                                       

 75%|███████▍  | 1383/1848 [7:39:19<2:34:37, 19.95s/it]
 75%|███████▍  | 1384/1848 [7:39:39<2:34:13, 19.94s/it]
                                                       

 75%|███████▍  | 1384/1848 [7:39:39<2:34:13, 19.94s/it]
 75%|███████▍  | 1385/1848 [7:39:59<2:33:59, 19.96s/it]
                                                       

 75%|███████▍  | 1385/1848 [7:39:59<2:33:59, 19.96s/it]
 75%|███████▌  | 1386/1848 [7:40:19<2:33:37, 19.95s/it]
                                                       

 75%|███████▌  | 1386/1848 [7:40:19<2:33:37, 19.95s/it]
 75%|███████▌  | 1387/1848 [7:40:39<2:33:23, 19.96s/it]
                                                       

 75%|███████▌  | 1387/1848 [7:40:39<2:33:23, 19.96s/it]
 75%|███████▌  | 1388/1848 [7:40:59<2:32:52, 19.94s/it]
                                                       

 75%|███████▌  | 1388/1848 [7:40:59<2:32:52, 19.94s/it]
 75%|███████▌  | 1389/1848 [7:41:19<2:32:40, 19.96s/it]
                                                       

 75%|███████▌  | 1389/1848 [7:41:19<2:32:40, 19.96s/it]
 75%|███████▌  | 1390/1848 [7:41:39<2:32:22, 19.96s/it]
                                                       

 75%|███████▌  | 1390/1848 [7:41:39<2:32:22, 19.96s/it]
 75%|███████▌  | 1391/1848 [7:41:59<2:31:57, 19.95s/it]
                                                       

 75%|███████▌  | 1391/1848 [7:41:59<2:31:57, 19.95s/it]
 75%|███████▌  | 1392/1848 [7:42:19<2:31:28, 19.93s/it]
                                                       

 75%|███████▌  | 1392/1848 [7:42:19<2:31:28, 19.93s/it]
 75%|███████▌  | 1393/1848 [7:42:39<2:31:06, 19.93s/it]
                                                       

 75%|███████▌  | 1393/1848 [7:42:39<2:31:06, 19.93s/it]
 75%|███████▌  | 1394/1848 [7:42:58<2:30:45, 19.92s/it]
                                                       

 75%|███████▌  | 1394/1848 [7:42:58<2:30:45, 19.92s/it]
 75%|███████▌  | 1395/1848 [7:43:18<2:30:20, 19.91s/it]
                                                       

 75%|███████▌  | 1395/1848 [7:43:18<2:30:20, 19.91s/it]
 76%|███████▌  | 1396/1848 [7:43:38<2:30:04, 19.92s/it]
                                                       

 76%|███████▌  | 1396/1848 [7:43:38<2:30:04, 19.92s/it]
 76%|███████▌  | 1397/1848 [7:43:58<2:29:48, 19.93s/it]
                                                       

 76%|███████▌  | 1397/1848 [7:43:58<2:29:48, 19.93s/it]
 76%|███████▌  | 1398/1848 [7:44:18<2:29:32, 19.94s/it]
                                                       

 76%|███████▌  | 1398/1848 [7:44:18<2:29:32, 19.94s/it]
 76%|███████▌  | 1399/1848 [7:44:38<2:29:05, 19.92s/it]
                                                       

 76%|███████▌  | 1399/1848 [7:44:38<2:29:05, 19.92s/it]
 76%|███████▌  | 1400/1848 [7:44:58<2:28:52, 19.94s/it]
                                                       

 76%|███████▌  | 1400/1848 [7:44:58<2:28:52, 19.94s/it]
 76%|███████▌  | 1401/1848 [7:45:19<2:30:24, 20.19s/it]
                                                       

 76%|███████▌  | 1401/1848 [7:45:19<2:30:24, 20.19s/it]
 76%|███████▌  | 1402/1848 [7:45:39<2:29:23, 20.10s/it]
                                                       

 76%|███████▌  | 1402/1848 [7:45:39<2:29:23, 20.10s/it]
 76%|███████▌  | 1403/1848 [7:45:59<2:28:43, 20.05s/it]
                                                       

 76%|███████▌  | 1403/1848 [7:45:59<2:28:43, 20.05s/it]
 76%|███████▌  | 1404/1848 [7:46:19<2:28:14, 20.03s/it]
                                                       

 76%|███████▌  | 1404/1848 [7:46:19<2:28:14, 20.03s/it]
 76%|███████▌  | 1405/1848 [7:46:39<2:27:36, 19.99s/it]
                                                       

 76%|███████▌  | 1405/1848 [7:46:39<2:27:36, 19.99s/it]
 76%|███████▌  | 1406/1848 [7:46:58<2:26:55, 19.94s/it]
                                                       

 76%|███████▌  | 1406/1848 [7:46:58<2:26:55, 19.94s/it]
 76%|███████▌  | 1407/1848 [7:47:18<2:26:20, 19.91s/it]
                                                       

 76%|███████▌  | 1407/1848 [7:47:18<2:26:20, 19.91s/it]
 76%|███████▌  | 1408/1848 [7:47:38<2:25:58, 19.91s/it]
                                                       

 76%|███████▌  | 1408/1848 [7:47:38<2:25:58, 19.91s/it]
 76%|███████▌  | 1409/1848 [7:47:58<2:25:40, 19.91s/it]
                                                       

 76%|███████▌  | 1409/1848 [7:47:58<2:25:40, 19.91s/it]
 76%|███████▋  | 1410/1848 [7:48:18<2:25:21, 19.91s/it]
                                                       

 76%|███████▋  | 1410/1848 [7:48:18<2:25:21, 19.91s/it]
 76%|███████▋  | 1411/1848 [7:48:38<2:25:10, 19.93s/it]
                                                       

 76%|███████▋  | 1411/1848 [7:48:38<2:25:10, 19.93s/it]
 76%|███████▋  | 1412/1848 [7:48:58<2:24:39, 19.91s/it]
                                                       

 76%|███████▋  | 1412/1848 [7:48:58<2:24:39, 19.91s/it]
 76%|███████▋  | 1413/1848 [7:49:18<2:24:31, 19.93s/it]
                                                       

 76%|███████▋  | 1413/1848 [7:49:18<2:24:31, 19.93s/it]
 77%|███████▋  | 1414/1848 [7:49:38<2:24:12, 19.94s/it]
                                                       

 77%|███████▋  | 1414/1848 [7:49:38<2:24:12, 19.94s/it]
 77%|███████▋  | 1415/1848 [7:49:58<2:23:49, 19.93s/it]
                                                       

 77%|███████▋  | 1415/1848 [7:49:58<2:23:49, 19.93s/it]
 77%|███████▋  | 1416/1848 [7:50:17<2:23:16, 19.90s/it]
                                                       

 77%|███████▋  | 1416/1848 [7:50:17<2:23:16, 19.90s/it]
 77%|███████▋  | 1417/1848 [7:50:37<2:22:48, 19.88s/it]
                                                       

 77%|███████▋  | 1417/1848 [7:50:37<2:22:48, 19.88s/it]
 77%|███████▋  | 1418/1848 [7:50:57<2:22:33, 19.89s/it]
                                                       

 77%|███████▋  | 1418/1848 [7:50:57<2:22:33, 19.89s/it]
 77%|███████▋  | 1419/1848 [7:51:17<2:22:18, 19.90s/it]
                                                       

 77%|███████▋  | 1419/1848 [7:51:17<2:22:18, 19.90s/it]
 77%|███████▋  | 1420/1848 [7:51:37<2:22:08, 19.93s/it]
                                                       

 77%|███████▋  | 1420/1848 [7:51:37<2:22:08, 19.93s/it]
 77%|███████▋  | 1421/1848 [7:51:57<2:21:53, 19.94s/it]
                                                       

 77%|███████▋  | 1421/1848 [7:51:57<2:21:53, 19.94s/it]
 77%|███████▋  | 1422/1848 [7:52:17<2:21:37, 19.95s/it]
                                                       

 77%|███████▋  | 1422/1848 [7:52:17<2:21:37, 19.95s/it]
 77%|███████▋  | 1423/1848 [7:52:37<2:21:20, 19.95s/it]
                                                       

 77%|███████▋  | 1423/1848 [7:52:37<2:21:20, 19.95s/it]
 77%|███████▋  | 1424/1848 [7:52:57<2:20:54, 19.94s/it]
                                                       

 77%|███████▋  | 1424/1848 [7:52:57<2:20:54, 19.94s/it]
 77%|███████▋  | 1425/1848 [7:53:17<2:20:33, 19.94s/it]
                                                       

 77%|███████▋  | 1425/1848 [7:53:17<2:20:33, 19.94s/it]
 77%|███████▋  | 1426/1848 [7:53:37<2:20:18, 19.95s/it]
                                                       

 77%|███████▋  | 1426/1848 [7:53:37<2:20:18, 19.95s/it]
 77%|███████▋  | 1427/1848 [7:53:57<2:19:58, 19.95s/it]
                                                       

 77%|███████▋  | 1427/1848 [7:53:57<2:19:58, 19.95s/it]
 77%|███████▋  | 1428/1848 [7:54:17<2:19:35, 19.94s/it]
                                                       

 77%|███████▋  | 1428/1848 [7:54:17<2:19:35, 19.94s/it]
 77%|███████▋  | 1429/1848 [7:54:37<2:19:15, 19.94s/it]
                                                       

 77%|███████▋  | 1429/1848 [7:54:37<2:19:15, 19.94s/it]
 77%|███████▋  | 1430/1848 [7:54:57<2:18:46, 19.92s/it]
                                                       

 77%|███████▋  | 1430/1848 [7:54:57<2:18:46, 19.92s/it]
 77%|███████▋  | 1431/1848 [7:55:16<2:18:28, 19.92s/it]
                                                       

 77%|███████▋  | 1431/1848 [7:55:16<2:18:28, 19.92s/it]
 77%|███████▋  | 1432/1848 [7:55:36<2:18:00, 19.91s/it]
                                                       

 77%|███████▋  | 1432/1848 [7:55:36<2:18:00, 19.91s/it]
 78%|███████▊  | 1433/1848 [7:55:56<2:17:45, 19.92s/it]
                                                       

 78%|███████▊  | 1433/1848 [7:55:56<2:17:45, 19.92s/it]
 78%|███████▊  | 1434/1848 [7:56:16<2:17:31, 19.93s/it]
                                                       

 78%|███████▊  | 1434/1848 [7:56:16<2:17:31, 19.93s/it]
 78%|███████▊  | 1435/1848 [7:56:36<2:17:04, 19.91s/it]
                                                       

 78%|███████▊  | 1435/1848 [7:56:36<2:17:04, 19.91s/it]
 78%|███████▊  | 1436/1848 [7:56:56<2:16:49, 19.93s/it]
                                                       

 78%|███████▊  | 1436/1848 [7:56:56<2:16:49, 19.93s/it]
 78%|███████▊  | 1437/1848 [7:57:16<2:16:36, 19.94s/it]
                                                       

 78%|███████▊  | 1437/1848 [7:57:16<2:16:36, 19.94s/it]
 78%|███████▊  | 1438/1848 [7:57:36<2:16:16, 19.94s/it]
                                                       

 78%|███████▊  | 1438/1848 [7:57:36<2:16:16, 19.94s/it]
 78%|███████▊  | 1439/1848 [7:57:56<2:15:51, 19.93s/it]
                                                       

 78%|███████▊  | 1439/1848 [7:57:56<2:15:51, 19.93s/it]
 78%|███████▊  | 1440/1848 [7:58:16<2:15:30, 19.93s/it]
                                                       

 78%|███████▊  | 1440/1848 [7:58:16<2:15:30, 19.93s/it]
 78%|███████▊  | 1441/1848 [7:58:36<2:15:12, 19.93s/it]
                                                       

 78%|███████▊  | 1441/1848 [7:58:36<2:15:12, 19.93s/it]
 78%|███████▊  | 1442/1848 [7:58:56<2:14:52, 19.93s/it]
                                                       

 78%|███████▊  | 1442/1848 [7:58:56<2:14:52, 19.93s/it]
 78%|███████▊  | 1443/1848 [7:59:16<2:14:32, 19.93s/it]
                                                       

 78%|███████▊  | 1443/1848 [7:59:16<2:14:32, 19.93s/it]
 78%|███████▊  | 1444/1848 [7:59:36<2:14:18, 19.95s/it]
                                                       

 78%|███████▊  | 1444/1848 [7:59:36<2:14:18, 19.95s/it]
 78%|███████▊  | 1445/1848 [7:59:55<2:13:53, 19.93s/it]
                                                       

 78%|███████▊  | 1445/1848 [7:59:55<2:13:53, 19.93s/it]
 78%|███████▊  | 1446/1848 [8:00:15<2:13:29, 19.92s/it]
                                                       

 78%|███████▊  | 1446/1848 [8:00:15<2:13:29, 19.92s/it]
 78%|███████▊  | 1447/1848 [8:00:35<2:13:03, 19.91s/it]
                                                       

 78%|███████▊  | 1447/1848 [8:00:35<2:13:03, 19.91s/it]
 78%|███████▊  | 1448/1848 [8:00:55<2:12:50, 19.93s/it]
                                                       

 78%|███████▊  | 1448/1848 [8:00:55<2:12:50, 19.93s/it]
 78%|███████▊  | 1449/1848 [8:01:15<2:12:32, 19.93s/it]
                                                       

 78%|███████▊  | 1449/1848 [8:01:15<2:12:32, 19.93s/it]
 78%|███████▊  | 1450/1848 [8:01:35<2:12:15, 19.94s/it]
                                                       

 78%|███████▊  | 1450/1848 [8:01:35<2:12:15, 19.94s/it]
 79%|███████▊  | 1451/1848 [8:01:55<2:11:55, 19.94s/it]
                                                       

 79%|███████▊  | 1451/1848 [8:01:55<2:11:55, 19.94s/it]
 79%|███████▊  | 1452/1848 [8:02:15<2:11:23, 19.91s/it]
                                                       

 79%|███████▊  | 1452/1848 [8:02:15<2:11:23, 19.91s/it]
 79%|███████▊  | 1453/1848 [8:02:35<2:10:57, 19.89s/it]
                                                       

 79%|███████▊  | 1453/1848 [8:02:35<2:10:57, 19.89s/it]
 79%|███████▊  | 1454/1848 [8:02:55<2:10:42, 19.91s/it]
                                                       

 79%|███████▊  | 1454/1848 [8:02:55<2:10:42, 19.91s/it]
 79%|███████▊  | 1455/1848 [8:03:15<2:10:19, 19.90s/it]
                                                       

 79%|███████▊  | 1455/1848 [8:03:15<2:10:19, 19.90s/it]
 79%|███████▉  | 1456/1848 [8:03:35<2:10:06, 19.92s/it]
                                                       

 79%|███████▉  | 1456/1848 [8:03:35<2:10:06, 19.92s/it]
 79%|███████▉  | 1457/1848 [8:03:54<2:09:48, 19.92s/it]
                                                       

 79%|███████▉  | 1457/1848 [8:03:54<2:09:48, 19.92s/it]
 79%|███████▉  | 1458/1848 [8:04:14<2:09:23, 19.91s/it]
                                                       

 79%|███████▉  | 1458/1848 [8:04:14<2:09:23, 19.91s/it]
 79%|███████▉  | 1459/1848 [8:04:34<2:09:08, 19.92s/it]
                                                       

 79%|███████▉  | 1459/1848 [8:04:34<2:09:08, 19.92s/it]
 79%|███████▉  | 1460/1848 [8:04:54<2:08:48, 19.92s/it]
                                                       

 79%|███████▉  | 1460/1848 [8:04:54<2:08:48, 19.92s/it]
 79%|███████▉  | 1461/1848 [8:05:14<2:08:20, 19.90s/it]
                                                       

 79%|███████▉  | 1461/1848 [8:05:14<2:08:20, 19.90s/it]
 79%|███████▉  | 1462/1848 [8:05:34<2:07:51, 19.87s/it]
                                                       

 79%|███████▉  | 1462/1848 [8:05:34<2:07:51, 19.87s/it]
 79%|███████▉  | 1463/1848 [8:05:54<2:07:38, 19.89s/it]
                                                       

 79%|███████▉  | 1463/1848 [8:05:54<2:07:38, 19.89s/it]
 79%|███████▉  | 1464/1848 [8:06:14<2:07:22, 19.90s/it]
                                                       

 79%|███████▉  | 1464/1848 [8:06:14<2:07:22, 19.90s/it]
 79%|███████▉  | 1465/1848 [8:06:34<2:07:06, 19.91s/it]
                                                       

 79%|███████▉  | 1465/1848 [8:06:34<2:07:06, 19.91s/it]
 79%|███████▉  | 1466/1848 [8:06:53<2:06:37, 19.89s/it]
                                                       

 79%|███████▉  | 1466/1848 [8:06:53<2:06:37, 19.89s/it]
 79%|███████▉  | 1467/1848 [8:07:13<2:06:20, 19.90s/it]
                                                       

 79%|███████▉  | 1467/1848 [8:07:13<2:06:20, 19.90s/it]
 79%|███████▉  | 1468/1848 [8:07:33<2:05:57, 19.89s/it]
                                                       

 79%|███████▉  | 1468/1848 [8:07:33<2:05:57, 19.89s/it]
 79%|███████▉  | 1469/1848 [8:07:53<2:05:43, 19.90s/it]
                                                       

 79%|███████▉  | 1469/1848 [8:07:53<2:05:43, 19.90s/it]
 80%|███████▉  | 1470/1848 [8:08:13<2:05:34, 19.93s/it]
                                                       

 80%|███████▉  | 1470/1848 [8:08:13<2:05:34, 19.93s/it]
 80%|███████▉  | 1471/1848 [8:08:33<2:05:19, 19.95s/it]
                                                       

 80%|███████▉  | 1471/1848 [8:08:33<2:05:19, 19.95s/it]
 80%|███████▉  | 1472/1848 [8:08:53<2:04:55, 19.93s/it]
                                                       

 80%|███████▉  | 1472/1848 [8:08:53<2:04:55, 19.93s/it]
 80%|███████▉  | 1473/1848 [8:09:13<2:04:31, 19.92s/it]
                                                       
{'loss': 1.2143, 'learning_rate': 3.7233766233766233e-06, 'epoch': 2.21}
+{'loss': 1.0688, 'learning_rate': 3.7157467532467538e-06, 'epoch': 2.21}
+{'loss': 1.2204, 'learning_rate': 3.7081168831168834e-06, 'epoch': 2.21}
+{'loss': 1.2201, 'learning_rate': 3.700487012987013e-06, 'epoch': 2.21}
+{'loss': 1.2868, 'learning_rate': 3.692857142857143e-06, 'epoch': 2.21}
+{'loss': 1.1844, 'learning_rate': 3.6852272727272728e-06, 'epoch': 2.22}
+{'loss': 1.1298, 'learning_rate': 3.677597402597403e-06, 'epoch': 2.22}
+{'loss': 1.0396, 'learning_rate': 3.6699675324675325e-06, 'epoch': 2.22}
+{'loss': 1.3635, 'learning_rate': 3.662337662337662e-06, 'epoch': 2.22}
+{'loss': 1.3508, 'learning_rate': 3.6547077922077922e-06, 'epoch': 2.22}
+{'loss': 1.2894, 'learning_rate': 3.647077922077922e-06, 'epoch': 2.22}
+{'loss': 1.1413, 'learning_rate': 3.6394480519480524e-06, 'epoch': 2.23}
+{'loss': 1.4715, 'learning_rate': 3.631818181818182e-06, 'epoch': 2.23}
+{'loss': 1.172, 'learning_rate': 3.624188311688312e-06, 'epoch': 2.23}
+{'loss': 1.2311, 'learning_rate': 3.6165584415584418e-06, 'epoch': 2.23}
+{'loss': 1.2464, 'learning_rate': 3.6089285714285714e-06, 'epoch': 2.23}
+{'loss': 1.2969, 'learning_rate': 3.6012987012987015e-06, 'epoch': 2.23}
+{'loss': 1.3207, 'learning_rate': 3.593668831168831e-06, 'epoch': 2.24}
+{'loss': 1.2762, 'learning_rate': 3.5860389610389616e-06, 'epoch': 2.24}
+{'loss': 1.224, 'learning_rate': 3.578409090909091e-06, 'epoch': 2.24}
+{'loss': 1.0698, 'learning_rate': 3.5707792207792205e-06, 'epoch': 2.24}
+{'loss': 1.2064, 'learning_rate': 3.563149350649351e-06, 'epoch': 2.24}
+{'loss': 1.1687, 'learning_rate': 3.5555194805194803e-06, 'epoch': 2.24}
+{'loss': 1.1774, 'learning_rate': 3.5478896103896108e-06, 'epoch': 2.25}
+{'loss': 1.2314, 'learning_rate': 3.5402597402597404e-06, 'epoch': 2.25}
+{'loss': 1.2597, 'learning_rate': 3.5326298701298705e-06, 'epoch': 2.25}
+{'loss': 1.1319, 'learning_rate': 3.525e-06, 'epoch': 2.25}
+{'loss': 1.3123, 'learning_rate': 3.51737012987013e-06, 'epoch': 2.25}
+{'loss': 1.0257, 'learning_rate': 3.50974025974026e-06, 'epoch': 2.25}
+{'loss': 1.2352, 'learning_rate': 3.50211038961039e-06, 'epoch': 2.25}
+{'loss': 1.111, 'learning_rate': 3.4944805194805196e-06, 'epoch': 2.26}
+{'loss': 1.0666, 'learning_rate': 3.4868506493506492e-06, 'epoch': 2.26}
+{'loss': 1.0798, 'learning_rate': 3.4792207792207793e-06, 'epoch': 2.26}
+{'loss': 1.2277, 'learning_rate': 3.4715909090909094e-06, 'epoch': 2.26}
+{'loss': 1.2605, 'learning_rate': 3.463961038961039e-06, 'epoch': 2.26}
+{'loss': 1.2061, 'learning_rate': 3.456331168831169e-06, 'epoch': 2.26}
+{'loss': 1.24, 'learning_rate': 3.4487012987012988e-06, 'epoch': 2.27}
+{'loss': 1.1894, 'learning_rate': 3.4410714285714284e-06, 'epoch': 2.27}
+{'loss': 1.1183, 'learning_rate': 3.4334415584415585e-06, 'epoch': 2.27}
+{'loss': 1.5224, 'learning_rate': 3.4258116883116886e-06, 'epoch': 2.27}
+{'loss': 1.4874, 'learning_rate': 3.4181818181818182e-06, 'epoch': 2.27}
+{'loss': 1.2553, 'learning_rate': 3.4105519480519483e-06, 'epoch': 2.27}
+{'loss': 1.2815, 'learning_rate': 3.402922077922078e-06, 'epoch': 2.28}
+{'loss': 1.0524, 'learning_rate': 3.395292207792208e-06, 'epoch': 2.28}
+{'loss': 1.1737, 'learning_rate': 3.3876623376623377e-06, 'epoch': 2.28}
+{'loss': 1.1485, 'learning_rate': 3.3800324675324677e-06, 'epoch': 2.28}
+{'loss': 1.4707, 'learning_rate': 3.3724025974025974e-06, 'epoch': 2.28}
+{'loss': 1.2013, 'learning_rate': 3.3647727272727275e-06, 'epoch': 2.28}
+{'loss': 1.2291, 'learning_rate': 3.357142857142857e-06, 'epoch': 2.29}
+{'loss': 1.2737, 'learning_rate': 3.349512987012987e-06, 'epoch': 2.29}
+{'loss': 1.2688, 'learning_rate': 3.341883116883117e-06, 'epoch': 2.29}
+{'loss': 1.074, 'learning_rate': 3.334253246753247e-06, 'epoch': 2.29}
+{'loss': 1.0968, 'learning_rate': 3.326623376623377e-06, 'epoch': 2.29}
+{'loss': 1.2368, 'learning_rate': 3.3189935064935067e-06, 'epoch': 2.29}
+{'loss': 1.1911, 'learning_rate': 3.3113636363636367e-06, 'epoch': 2.3}
+{'loss': 1.1669, 'learning_rate': 3.3037337662337664e-06, 'epoch': 2.3}
+{'loss': 1.4996, 'learning_rate': 3.296103896103896e-06, 'epoch': 2.3}
+{'loss': 1.4915, 'learning_rate': 3.288474025974026e-06, 'epoch': 2.3}
+{'loss': 1.1572, 'learning_rate': 3.280844155844156e-06, 'epoch': 2.3}
+{'loss': 1.3461, 'learning_rate': 3.273214285714286e-06, 'epoch': 2.3}
+{'loss': 1.1363, 'learning_rate': 3.265584415584416e-06, 'epoch': 2.31}
+{'loss': 1.3002, 'learning_rate': 3.2579545454545456e-06, 'epoch': 2.31}
+{'loss': 1.173, 'learning_rate': 3.2503246753246752e-06, 'epoch': 2.31}
+{'loss': 1.2514, 'learning_rate': 3.2426948051948053e-06, 'epoch': 2.31}
+{'loss': 1.2467, 'learning_rate': 3.2350649350649354e-06, 'epoch': 2.31}
+{'loss': 1.3014, 'learning_rate': 3.227435064935065e-06, 'epoch': 2.31}
+{'loss': 1.3128, 'learning_rate': 3.219805194805195e-06, 'epoch': 2.31}
+{'loss': 1.1618, 'learning_rate': 3.2121753246753247e-06, 'epoch': 2.32}
+{'loss': 0.8769, 'learning_rate': 3.2045454545454544e-06, 'epoch': 2.32}
+{'loss': 1.3883, 'learning_rate': 3.1969155844155845e-06, 'epoch': 2.32}
+{'loss': 1.2138, 'learning_rate': 3.1892857142857145e-06, 'epoch': 2.32}
+{'loss': 1.1678, 'learning_rate': 3.181655844155844e-06, 'epoch': 2.32}
+{'loss': 1.0179, 'learning_rate': 3.1740259740259743e-06, 'epoch': 2.32}
+{'loss': 1.1561, 'learning_rate': 3.166396103896104e-06, 'epoch': 2.33}
+{'loss': 1.1571, 'learning_rate': 3.1587662337662336e-06, 'epoch': 2.33}
+{'loss': 1.1098, 'learning_rate': 3.1511363636363637e-06, 'epoch': 2.33}
+{'loss': 1.1337, 'learning_rate': 3.1435064935064937e-06, 'epoch': 2.33}
+{'loss': 1.0379, 'learning_rate': 3.1358766233766234e-06, 'epoch': 2.33}
+{'loss': 1.4226, 'learning_rate': 3.1282467532467535e-06, 'epoch': 2.33}
+{'loss': 1.2059, 'learning_rate': 3.1206168831168835e-06, 'epoch': 2.34}
+{'loss': 1.0423, 'learning_rate': 3.1129870129870128e-06, 'epoch': 2.34}
+{'loss': 1.1958, 'learning_rate': 3.105357142857143e-06, 'epoch': 2.34}
+{'loss': 1.1559, 'learning_rate': 3.097727272727273e-06, 'epoch': 2.34}
+{'loss': 1.2564, 'learning_rate': 3.0900974025974026e-06, 'epoch': 2.34}
+{'loss': 1.379, 'learning_rate': 3.0824675324675326e-06, 'epoch': 2.34}
+{'loss': 1.4343, 'learning_rate': 3.0748376623376627e-06, 'epoch': 2.35}
+{'loss': 1.3288, 'learning_rate': 3.0672077922077924e-06, 'epoch': 2.35}
+{'loss': 1.1615, 'learning_rate': 3.059577922077922e-06, 'epoch': 2.35}
+{'loss': 1.0975, 'learning_rate': 3.051948051948052e-06, 'epoch': 2.35}
+{'loss': 1.2851, 'learning_rate': 3.044318181818182e-06, 'epoch': 2.35}
+{'loss': 1.2269, 'learning_rate': 3.036688311688312e-06, 'epoch': 2.35}
+{'loss': 1.6102, 'learning_rate': 3.029058441558442e-06, 'epoch': 2.36}
+{'loss': 1.3581, 'learning_rate': 3.0214285714285715e-06, 'epoch': 2.36}
+{'loss': 1.0786, 'learning_rate': 3.013798701298701e-06, 'epoch': 2.36}
+{'loss': 1.0551, 'learning_rate': 3.0061688311688313e-06, 'epoch': 2.36}
+{'loss': 1.0821, 'learning_rate': 2.9985389610389613e-06, 'epoch': 2.36}
+{'loss': 1.263, 'learning_rate': 2.990909090909091e-06, 'epoch': 2.36}
+{'loss': 1.1482, 'learning_rate': 2.983279220779221e-06, 'epoch': 2.37}
+{'loss': 1.1644, 'learning_rate': 2.9756493506493507e-06, 'epoch': 2.37}
+{'loss': 1.2738, 'learning_rate': 2.9680194805194804e-06, 'epoch': 2.37}
+{'loss': 1.3678, 'learning_rate': 2.9603896103896104e-06, 'epoch': 2.37}
+{'loss': 1.4351, 'learning_rate': 2.9527597402597405e-06, 'epoch': 2.37}
+{'loss': 1.2066, 'learning_rate': 2.94512987012987e-06, 'epoch': 2.37}
+{'loss': 1.1868, 'learning_rate': 2.9375000000000003e-06, 'epoch': 2.38}
+{'loss': 1.0129, 'learning_rate': 2.9298701298701303e-06, 'epoch': 2.38}
+{'loss': 1.2446, 'learning_rate': 2.9222402597402596e-06, 'epoch': 2.38}
+{'loss': 1.3008, 'learning_rate': 2.9146103896103896e-06, 'epoch': 2.38}
+{'loss': 1.4, 'learning_rate': 2.9069805194805197e-06, 'epoch': 2.38}
+{'loss': 1.0083, 'learning_rate': 2.8993506493506494e-06, 'epoch': 2.38}
+{'loss': 1.1907, 'learning_rate': 2.8917207792207794e-06, 'epoch': 2.38}
+{'loss': 1.2511, 'learning_rate': 2.8840909090909095e-06, 'epoch': 2.39}
+{'loss': 1.1685, 'learning_rate': 2.8764610389610387e-06, 'epoch': 2.39}
+{'loss': 1.1932, 'learning_rate': 2.868831168831169e-06, 'epoch': 2.39}
+
 80%|███████▉  | 1473/1848 [8:09:13<2:04:31, 19.92s/it]
 80%|███████▉  | 1474/1848 [8:09:33<2:04:18, 19.94s/it]
                                                       

 80%|███████▉  | 1474/1848 [8:09:33<2:04:18, 19.94s/it]
 80%|███████▉  | 1475/1848 [8:09:53<2:03:54, 19.93s/it]
                                                       

 80%|███████▉  | 1475/1848 [8:09:53<2:03:54, 19.93s/it]
 80%|███████▉  | 1476/1848 [8:10:13<2:03:38, 19.94s/it]
                                                       

 80%|███████▉  | 1476/1848 [8:10:13<2:03:38, 19.94s/it]
 80%|███████▉  | 1477/1848 [8:10:33<2:03:18, 19.94s/it]
                                                       

 80%|███████▉  | 1477/1848 [8:10:33<2:03:18, 19.94s/it]
 80%|███████▉  | 1478/1848 [8:10:53<2:03:03, 19.95s/it]
                                                       

 80%|███████▉  | 1478/1848 [8:10:53<2:03:03, 19.95s/it]
 80%|████████  | 1479/1848 [8:11:13<2:02:45, 19.96s/it]
                                                       

 80%|████████  | 1479/1848 [8:11:13<2:02:45, 19.96s/it]
 80%|████████  | 1480/1848 [8:11:33<2:02:17, 19.94s/it]
                                                       

 80%|████████  | 1480/1848 [8:11:33<2:02:17, 19.94s/it]
 80%|████████  | 1481/1848 [8:11:53<2:01:56, 19.94s/it]
                                                       

 80%|████████  | 1481/1848 [8:11:53<2:01:56, 19.94s/it]
 80%|████████  | 1482/1848 [8:12:13<2:01:39, 19.94s/it]
                                                       

 80%|████████  | 1482/1848 [8:12:13<2:01:39, 19.94s/it]
 80%|████████  | 1483/1848 [8:12:32<2:01:19, 19.94s/it]
                                                       

 80%|████████  | 1483/1848 [8:12:32<2:01:19, 19.94s/it]
 80%|████████  | 1484/1848 [8:12:52<2:00:57, 19.94s/it]
                                                       

 80%|████████  | 1484/1848 [8:12:52<2:00:57, 19.94s/it]
 80%|████████  | 1485/1848 [8:13:12<2:00:40, 19.95s/it]
                                                       

 80%|████████  | 1485/1848 [8:13:12<2:00:40, 19.95s/it]
 80%|████████  | 1486/1848 [8:13:32<2:00:18, 19.94s/it]
                                                       

 80%|████████  | 1486/1848 [8:13:32<2:00:18, 19.94s/it]
 80%|████████  | 1487/1848 [8:13:52<1:59:49, 19.92s/it]
                                                       

 80%|████████  | 1487/1848 [8:13:52<1:59:49, 19.92s/it]
 81%|████████  | 1488/1848 [8:14:12<1:59:31, 19.92s/it]
                                                       

 81%|████████  | 1488/1848 [8:14:12<1:59:31, 19.92s/it]
 81%|████████  | 1489/1848 [8:14:32<1:59:11, 19.92s/it]
                                                       

 81%|████████  | 1489/1848 [8:14:32<1:59:11, 19.92s/it]
 81%|████████  | 1490/1848 [8:14:52<1:58:52, 19.92s/it]
                                                       

 81%|████████  | 1490/1848 [8:14:52<1:58:52, 19.92s/it]
 81%|████████  | 1491/1848 [8:15:12<1:58:34, 19.93s/it]
                                                       

 81%|████████  | 1491/1848 [8:15:12<1:58:34, 19.93s/it]
 81%|████████  | 1492/1848 [8:15:32<1:58:14, 19.93s/it]
                                                       

 81%|████████  | 1492/1848 [8:15:32<1:58:14, 19.93s/it]
 81%|████████  | 1493/1848 [8:15:52<1:57:45, 19.90s/it]
                                                       

 81%|████████  | 1493/1848 [8:15:52<1:57:45, 19.90s/it]
 81%|████████  | 1494/1848 [8:16:12<1:57:25, 19.90s/it]
                                                       

 81%|████████  | 1494/1848 [8:16:12<1:57:25, 19.90s/it]
 81%|████████  | 1495/1848 [8:16:31<1:57:09, 19.91s/it]
                                                       

 81%|████████  | 1495/1848 [8:16:31<1:57:09, 19.91s/it]
 81%|████████  | 1496/1848 [8:16:51<1:56:50, 19.91s/it]
                                                       

 81%|████████  | 1496/1848 [8:16:51<1:56:50, 19.91s/it]
 81%|████████  | 1497/1848 [8:17:11<1:56:37, 19.93s/it]
                                                       

 81%|████████  | 1497/1848 [8:17:11<1:56:37, 19.93s/it]
 81%|████████  | 1498/1848 [8:17:31<1:56:22, 19.95s/it]
                                                       

 81%|████████  | 1498/1848 [8:17:31<1:56:22, 19.95s/it]
 81%|████████  | 1499/1848 [8:17:51<1:56:07, 19.96s/it]
                                                       

 81%|████████  | 1499/1848 [8:17:51<1:56:07, 19.96s/it]
 81%|████████  | 1500/1848 [8:18:11<1:55:42, 19.95s/it]
                                                       

 81%|████████  | 1500/1848 [8:18:11<1:55:42, 19.95s/it]
 81%|████████  | 1501/1848 [8:18:32<1:56:48, 20.20s/it]
                                                       

 81%|████████  | 1501/1848 [8:18:32<1:56:48, 20.20s/it]
 81%|████████▏ | 1502/1848 [8:18:52<1:55:56, 20.10s/it]
                                                       

 81%|████████▏ | 1502/1848 [8:18:52<1:55:56, 20.10s/it]
 81%|████████▏ | 1503/1848 [8:19:12<1:55:25, 20.07s/it]
                                                       

 81%|████████▏ | 1503/1848 [8:19:12<1:55:25, 20.07s/it]
 81%|████████▏ | 1504/1848 [8:19:32<1:55:00, 20.06s/it]
                                                       

 81%|████████▏ | 1504/1848 [8:19:32<1:55:00, 20.06s/it]
 81%|████████▏ | 1505/1848 [8:19:52<1:54:27, 20.02s/it]
                                                       

 81%|████████▏ | 1505/1848 [8:19:52<1:54:27, 20.02s/it]
 81%|████████▏ | 1506/1848 [8:20:12<1:53:56, 19.99s/it]
                                                       

 81%|████████▏ | 1506/1848 [8:20:12<1:53:56, 19.99s/it]
 82%|████████▏ | 1507/1848 [8:20:32<1:53:32, 19.98s/it]
                                                       

 82%|████████▏ | 1507/1848 [8:20:32<1:53:32, 19.98s/it]
 82%|████████▏ | 1508/1848 [8:20:52<1:53:08, 19.97s/it]
                                                       

 82%|████████▏ | 1508/1848 [8:20:52<1:53:08, 19.97s/it]
 82%|████████▏ | 1509/1848 [8:21:12<1:52:38, 19.94s/it]
                                                       

 82%|████████▏ | 1509/1848 [8:21:12<1:52:38, 19.94s/it]
 82%|████████▏ | 1510/1848 [8:21:32<1:52:24, 19.95s/it]
                                                       

 82%|████████▏ | 1510/1848 [8:21:32<1:52:24, 19.95s/it]
 82%|████████▏ | 1511/1848 [8:21:52<1:52:06, 19.96s/it]
                                                       

 82%|████████▏ | 1511/1848 [8:21:52<1:52:06, 19.96s/it]
 82%|████████▏ | 1512/1848 [8:22:11<1:51:43, 19.95s/it]
                                                       

 82%|████████▏ | 1512/1848 [8:22:11<1:51:43, 19.95s/it]
 82%|████████▏ | 1513/1848 [8:22:31<1:51:18, 19.93s/it]
                                                       

 82%|████████▏ | 1513/1848 [8:22:31<1:51:18, 19.93s/it]
 82%|████████▏ | 1514/1848 [8:22:51<1:50:54, 19.93s/it]
                                                       

 82%|████████▏ | 1514/1848 [8:22:51<1:50:54, 19.93s/it]
 82%|████████▏ | 1515/1848 [8:23:11<1:50:37, 19.93s/it]
                                                       

 82%|████████▏ | 1515/1848 [8:23:11<1:50:37, 19.93s/it]
 82%|████████▏ | 1516/1848 [8:23:31<1:50:03, 19.89s/it]
                                                       

 82%|████████▏ | 1516/1848 [8:23:31<1:50:03, 19.89s/it]
 82%|████████▏ | 1517/1848 [8:23:51<1:49:50, 19.91s/it]
                                                       

 82%|████████▏ | 1517/1848 [8:23:51<1:49:50, 19.91s/it]
 82%|████████▏ | 1518/1848 [8:24:11<1:49:36, 19.93s/it]
                                                       

 82%|████████▏ | 1518/1848 [8:24:11<1:49:36, 19.93s/it]
 82%|████████▏ | 1519/1848 [8:24:31<1:49:14, 19.92s/it]
                                                       

 82%|████████▏ | 1519/1848 [8:24:31<1:49:14, 19.92s/it]
 82%|████████▏ | 1520/1848 [8:24:51<1:48:52, 19.92s/it]
                                                       

 82%|████████▏ | 1520/1848 [8:24:51<1:48:52, 19.92s/it]
 82%|████████▏ | 1521/1848 [8:25:11<1:48:23, 19.89s/it]
                                                       

 82%|████████▏ | 1521/1848 [8:25:11<1:48:23, 19.89s/it]
 82%|████████▏ | 1522/1848 [8:25:30<1:47:55, 19.86s/it]
                                                       

 82%|████████▏ | 1522/1848 [8:25:30<1:47:55, 19.86s/it]
 82%|████████▏ | 1523/1848 [8:25:50<1:47:38, 19.87s/it]
                                                       

 82%|████████▏ | 1523/1848 [8:25:50<1:47:38, 19.87s/it]
 82%|████████▏ | 1524/1848 [8:26:10<1:47:26, 19.90s/it]
                                                       

 82%|████████▏ | 1524/1848 [8:26:10<1:47:26, 19.90s/it]
 83%|████████▎ | 1525/1848 [8:26:30<1:47:10, 19.91s/it]
                                                       

 83%|████████▎ | 1525/1848 [8:26:30<1:47:10, 19.91s/it]
 83%|████████▎ | 1526/1848 [8:26:50<1:46:53, 19.92s/it]
                                                       

 83%|████████▎ | 1526/1848 [8:26:50<1:46:53, 19.92s/it]
 83%|████████▎ | 1527/1848 [8:27:10<1:46:35, 19.92s/it]
                                                       

 83%|████████▎ | 1527/1848 [8:27:10<1:46:35, 19.92s/it]
 83%|████████▎ | 1528/1848 [8:27:30<1:46:03, 19.89s/it]
                                                       

 83%|████████▎ | 1528/1848 [8:27:30<1:46:03, 19.89s/it]
 83%|████████▎ | 1529/1848 [8:27:50<1:45:40, 19.88s/it]
                                                       

 83%|████████▎ | 1529/1848 [8:27:50<1:45:40, 19.88s/it]
 83%|████████▎ | 1530/1848 [8:28:10<1:45:26, 19.89s/it]
                                                       

 83%|████████▎ | 1530/1848 [8:28:10<1:45:26, 19.89s/it]
 83%|████████▎ | 1531/1848 [8:28:30<1:45:11, 19.91s/it]
                                                       

 83%|████████▎ | 1531/1848 [8:28:30<1:45:11, 19.91s/it]
 83%|████████▎ | 1532/1848 [8:28:50<1:44:55, 19.92s/it]
                                                       

 83%|████████▎ | 1532/1848 [8:28:50<1:44:55, 19.92s/it]
 83%|████████▎ | 1533/1848 [8:29:09<1:44:33, 19.92s/it]
                                                       

 83%|████████▎ | 1533/1848 [8:29:09<1:44:33, 19.92s/it]
 83%|████████▎ | 1534/1848 [8:29:29<1:44:07, 19.90s/it]
                                                       

 83%|████████▎ | 1534/1848 [8:29:29<1:44:07, 19.90s/it]
 83%|████████▎ | 1535/1848 [8:29:48<1:42:42, 19.69s/it]
                                                       

 83%|████████▎ | 1535/1848 [8:29:48<1:42:42, 19.69s/it]
 83%|████████▎ | 1536/1848 [8:30:08<1:42:50, 19.78s/it]
                                                       

 83%|████████▎ | 1536/1848 [8:30:08<1:42:50, 19.78s/it]
 83%|████████▎ | 1537/1848 [8:30:28<1:42:43, 19.82s/it]
                                                       

 83%|████████▎ | 1537/1848 [8:30:28<1:42:43, 19.82s/it]
 83%|████████▎ | 1538/1848 [8:30:48<1:42:22, 19.82s/it]
                                                       

 83%|████████▎ | 1538/1848 [8:30:48<1:42:22, 19.82s/it]
 83%|████████▎ | 1539/1848 [8:31:08<1:42:13, 19.85s/it]
                                                       

 83%|████████▎ | 1539/1848 [8:31:08<1:42:13, 19.85s/it]
 83%|████████▎ | 1540/1848 [8:31:28<1:41:53, 19.85s/it]
                                                       

 83%|████████▎ | 1540/1848 [8:31:28<1:41:53, 19.85s/it]
 83%|████████▎ | 1541/1848 [8:31:48<1:41:27, 19.83s/it]
                                                       

 83%|████████▎ | 1541/1848 [8:31:48<1:41:27, 19.83s/it]
 83%|████████▎ | 1542/1848 [8:32:08<1:41:11, 19.84s/it]
                                                       

 83%|████████▎ | 1542/1848 [8:32:08<1:41:11, 19.84s/it]
 83%|████████▎ | 1543/1848 [8:32:28<1:41:02, 19.88s/it]
                                                       

 83%|████████▎ | 1543/1848 [8:32:28<1:41:02, 19.88s/it]
 84%|████████▎ | 1544/1848 [8:32:48<1:40:50, 19.90s/it]
                                                       

 84%|████████▎ | 1544/1848 [8:32:48<1:40:50, 19.90s/it]
 84%|████████▎ | 1545/1848 [8:33:08<1:40:34, 19.92s/it]
                                                       

 84%|████████▎ | 1545/1848 [8:33:08<1:40:34, 19.92s/it]
 84%|████████▎ | 1546/1848 [8:33:27<1:40:10, 19.90s/it]
                                                       

 84%|████████▎ | 1546/1848 [8:33:27<1:40:10, 19.90s/it]
 84%|████████▎ | 1547/1848 [8:33:47<1:39:52, 19.91s/it]
                                                       

 84%|████████▎ | 1547/1848 [8:33:47<1:39:52, 19.91s/it]
 84%|████████▍ | 1548/1848 [8:34:07<1:39:31, 19.91s/it]
                                                       

 84%|████████▍ | 1548/1848 [8:34:07<1:39:31, 19.91s/it]
 84%|████████▍ | 1549/1848 [8:34:27<1:39:15, 19.92s/it]
                                                       

 84%|████████▍ | 1549/1848 [8:34:27<1:39:15, 19.92s/it]
 84%|████████▍ | 1550/1848 [8:34:47<1:38:53, 19.91s/it]
                                                       

 84%|████████▍ | 1550/1848 [8:34:47<1:38:53, 19.91s/it]
 84%|████████▍ | 1551/1848 [8:35:07<1:38:31, 19.90s/it]
                                                       

 84%|████████▍ | 1551/1848 [8:35:07<1:38:31, 19.90s/it]
 84%|████████▍ | 1552/1848 [8:35:27<1:38:14, 19.92s/it]
                                                       

 84%|████████▍ | 1552/1848 [8:35:27<1:38:14, 19.92s/it]
 84%|████████▍ | 1553/1848 [8:35:47<1:37:55, 19.92s/it]
                                                       

 84%|████████▍ | 1553/1848 [8:35:47<1:37:55, 19.92s/it]
 84%|████████▍ | 1554/1848 [8:36:07<1:37:42, 19.94s/it]
                                                       

 84%|████████▍ | 1554/1848 [8:36:07<1:37:42, 19.94s/it]
 84%|████████▍ | 1555/1848 [8:36:27<1:37:24, 19.95s/it]
                                                       

 84%|████████▍ | 1555/1848 [8:36:27<1:37:24, 19.95s/it]
 84%|████████▍ | 1556/1848 [8:36:47<1:37:08, 19.96s/it]
                                                       

 84%|████████▍ | 1556/1848 [8:36:47<1:37:08, 19.96s/it]
 84%|████████▍ | 1557/1848 [8:37:07<1:36:43, 19.94s/it]
                                                       

 84%|████████▍ | 1557/1848 [8:37:07<1:36:43, 19.94s/it]
 84%|████████▍ | 1558/1848 [8:37:27<1:36:21, 19.94s/it]
                                                       

 84%|████████▍ | 1558/1848 [8:37:27<1:36:21, 19.94s/it]
 84%|████████▍ | 1559/1848 [8:37:46<1:35:57, 19.92s/it]
                                                       

 84%|████████▍ | 1559/1848 [8:37:46<1:35:57, 19.92s/it]
 84%|████████▍ | 1560/1848 [8:38:06<1:35:35, 19.91s/it]
                                                       

 84%|████████▍ | 1560/1848 [8:38:06<1:35:35, 19.91s/it]
 84%|████████▍ | 1561/1848 [8:38:26<1:35:16, 19.92s/it]
                                                       

 84%|████████▍ | 1561/1848 [8:38:26<1:35:16, 19.92s/it]
 85%|████████▍ | 1562/1848 [8:38:46<1:34:59, 19.93s/it]
                                                       

 85%|████████▍ | 1562/1848 [8:38:46<1:34:59, 19.93s/it]
 85%|████████▍ | 1563/1848 [8:39:06<1:34:43, 19.94s/it]
                                                       

 85%|████████▍ | 1563/1848 [8:39:06<1:34:43, 19.94s/it]
 85%|████████▍ | 1564/1848 [8:39:26<1:34:28, 19.96s/it]
                                                       

 85%|████████▍ | 1564/1848 [8:39:26<1:34:28, 19.96s/it]
 85%|████████▍ | 1565/1848 [8:39:46<1:34:03, 19.94s/it]
                                                       

 85%|████████▍ | 1565/1848 [8:39:46<1:34:03, 19.94s/it]
 85%|████████▍ | 1566/1848 [8:40:06<1:33:42, 19.94s/it]
                                                       

 85%|████████▍ | 1566/1848 [8:40:06<1:33:42, 19.94s/it]
 85%|████████▍ | 1567/1848 [8:40:26<1:33:21, 19.93s/it]
                                                       

 85%|████████▍ | 1567/1848 [8:40:26<1:33:21, 19.93s/it]
 85%|████████▍ | 1568/1848 [8:40:46<1:33:00, 19.93s/it]
                                                       

 85%|████████▍ | 1568/1848 [8:40:46<1:33:00, 19.93s/it]
 85%|████████▍ | 1569/1848 [8:41:06<1:32:41, 19.93s/it]
                                                       

 85%|████████▍ | 1569/1848 [8:41:06<1:32:41, 19.93s/it]
 85%|████████▍ | 1570/1848 [8:41:26<1:32:23, 19.94s/it]
                                                       

 85%|████████▍ | 1570/1848 [8:41:26<1:32:23, 19.94s/it]
 85%|████████▌ | 1571/1848 [8:41:46<1:31:57, 19.92s/it]
                                                       

 85%|████████▌ | 1571/1848 [8:41:46<1:31:57, 19.92s/it]
 85%|████████�� | 1572/1848 [8:42:06<1:31:41, 19.93s/it]
                                                       

 85%|████████▌ | 1572/1848 [8:42:06<1:31:41, 19.93s/it]
 85%|████████▌ | 1573/1848 [8:42:25<1:31:17, 19.92s/it]
                                                       

 85%|████████▌ | 1573/1848 [8:42:25<1:31:17, 19.92s/it]
 85%|████████▌ | 1574/1848 [8:42:45<1:31:00, 19.93s/it]
                                                       

 85%|████████▌ | 1574/1848 [8:42:45<1:31:00, 19.93s/it]
 85%|████████▌ | 1575/1848 [8:43:05<1:30:45, 19.95s/it]
                                                       

 85%|████████▌ | 1575/1848 [8:43:05<1:30:45, 19.95s/it]
 85%|████████▌ | 1576/1848 [8:43:25<1:30:25, 19.95s/it]
                                                       

 85%|████████▌ | 1576/1848 [8:43:25<1:30:25, 19.95s/it]
 85%|████████▌ | 1577/1848 [8:43:45<1:30:05, 19.95s/it]
                                                       

 85%|████████▌ | 1577/1848 [8:43:45<1:30:05, 19.95s/it]
 85%|████████▌ | 1578/1848 [8:44:05<1:29:47, 19.95s/it]
                                                       

 85%|████████▌ | 1578/1848 [8:44:05<1:29:47, 19.95s/it]
 85%|████████▌ | 1579/1848 [8:44:25<1:29:28, 19.96s/it]
                                                       

 85%|████████▌ | 1579/1848 [8:44:25<1:29:28, 19.96s/it]
 85%|████████▌ | 1580/1848 [8:44:45<1:29:01, 19.93s/it]
                                                       

 85%|████████▌ | 1580/1848 [8:44:45<1:29:01, 19.93s/it]
 86%|████████▌ | 1581/1848 [8:45:05<1:28:41, 19.93s/it]
                                                       

 86%|████████▌ | 1581/1848 [8:45:05<1:28:41, 19.93s/it]
 86%|████████▌ | 1582/1848 [8:45:25<1:28:20, 19.93s/it]
                                                       

 86%|████████▌ | 1582/1848 [8:45:25<1:28:20, 19.93s/it]
 86%|████████▌ | 1583/1848 [8:45:45<1:28:00, 19.93s/it]
                                                       

 86%|████████▌ | 1583/1848 [8:45:45<1:28:00, 19.93s/it]
 86%|████████▌ | 1584/1848 [8:46:05<1:27:36, 19.91s/it]
                                                       

 86%|████████▌ | 1584/1848 [8:46:05<1:27:36, 19.91s/it]
 86%|████████▌ | 1585/1848 [8:46:25<1:27:20, 19.93s/it]
                                                       

 86%|████████▌ | 1585/1848 [8:46:25<1:27:20, 19.93s/it]
 86%|████████▌ | 1586/1848 [8:46:45<1:26:59, 19.92s/it]
                                                       
{'loss': 1.235, 'learning_rate': 2.861201298701299e-06, 'epoch': 2.39}
+{'loss': 1.3269, 'learning_rate': 2.8535714285714285e-06, 'epoch': 2.39}
+{'loss': 1.3385, 'learning_rate': 2.8459415584415586e-06, 'epoch': 2.39}
+{'loss': 1.1701, 'learning_rate': 2.8383116883116887e-06, 'epoch': 2.4}
+{'loss': 1.2907, 'learning_rate': 2.830681818181818e-06, 'epoch': 2.4}
+{'loss': 1.4009, 'learning_rate': 2.823051948051948e-06, 'epoch': 2.4}
+{'loss': 1.216, 'learning_rate': 2.815422077922078e-06, 'epoch': 2.4}
+{'loss': 1.1593, 'learning_rate': 2.8077922077922077e-06, 'epoch': 2.4}
+{'loss': 1.5541, 'learning_rate': 2.800162337662338e-06, 'epoch': 2.4}
+{'loss': 1.322, 'learning_rate': 2.792532467532468e-06, 'epoch': 2.41}
+{'loss': 1.1077, 'learning_rate': 2.7849025974025975e-06, 'epoch': 2.41}
+{'loss': 1.5604, 'learning_rate': 2.777272727272727e-06, 'epoch': 2.41}
+{'loss': 0.9559, 'learning_rate': 2.7696428571428572e-06, 'epoch': 2.41}
+{'loss': 1.1691, 'learning_rate': 2.7620129870129873e-06, 'epoch': 2.41}
+{'loss': 1.105, 'learning_rate': 2.754383116883117e-06, 'epoch': 2.41}
+{'loss': 1.2709, 'learning_rate': 2.746753246753247e-06, 'epoch': 2.42}
+{'loss': 0.9866, 'learning_rate': 2.739123376623377e-06, 'epoch': 2.42}
+{'loss': 1.204, 'learning_rate': 2.7314935064935064e-06, 'epoch': 2.42}
+{'loss': 1.2701, 'learning_rate': 2.7238636363636364e-06, 'epoch': 2.42}
+{'loss': 1.1641, 'learning_rate': 2.7162337662337665e-06, 'epoch': 2.42}
+{'loss': 1.2108, 'learning_rate': 2.708603896103896e-06, 'epoch': 2.42}
+{'loss': 1.2586, 'learning_rate': 2.7009740259740262e-06, 'epoch': 2.43}
+{'loss': 1.1919, 'learning_rate': 2.6933441558441563e-06, 'epoch': 2.43}
+{'loss': 1.3299, 'learning_rate': 2.6857142857142855e-06, 'epoch': 2.43}
+{'loss': 1.1031, 'learning_rate': 2.6780844155844156e-06, 'epoch': 2.43}
+{'loss': 1.1254, 'learning_rate': 2.6704545454545457e-06, 'epoch': 2.43}
+{'loss': 1.054, 'learning_rate': 2.6628246753246753e-06, 'epoch': 2.43}
+{'loss': 1.2037, 'learning_rate': 2.6551948051948054e-06, 'epoch': 2.44}
+{'loss': 1.092, 'learning_rate': 2.6475649350649355e-06, 'epoch': 2.44}
+{'loss': 1.2901, 'learning_rate': 2.6399350649350647e-06, 'epoch': 2.44}
+{'loss': 1.3202, 'learning_rate': 2.6323051948051948e-06, 'epoch': 2.44}
+{'loss': 1.1695, 'learning_rate': 2.624675324675325e-06, 'epoch': 2.44}
+{'loss': 1.08, 'learning_rate': 2.6170454545454545e-06, 'epoch': 2.44}
+{'loss': 1.4232, 'learning_rate': 2.6094155844155846e-06, 'epoch': 2.44}
+{'loss': 1.1799, 'learning_rate': 2.6017857142857147e-06, 'epoch': 2.45}
+{'loss': 1.2793, 'learning_rate': 2.594155844155844e-06, 'epoch': 2.45}
+{'loss': 1.4072, 'learning_rate': 2.586525974025974e-06, 'epoch': 2.45}
+{'loss': 1.1692, 'learning_rate': 2.578896103896104e-06, 'epoch': 2.45}
+{'loss': 1.2534, 'learning_rate': 2.5712662337662337e-06, 'epoch': 2.45}
+{'loss': 1.1247, 'learning_rate': 2.5636363636363638e-06, 'epoch': 2.45}
+{'loss': 1.275, 'learning_rate': 2.556006493506494e-06, 'epoch': 2.46}
+{'loss': 1.3701, 'learning_rate': 2.548376623376623e-06, 'epoch': 2.46}
+{'loss': 1.19, 'learning_rate': 2.540746753246753e-06, 'epoch': 2.46}
+{'loss': 1.3683, 'learning_rate': 2.5331168831168832e-06, 'epoch': 2.46}
+{'loss': 1.1637, 'learning_rate': 2.525487012987013e-06, 'epoch': 2.46}
+{'loss': 1.281, 'learning_rate': 2.517857142857143e-06, 'epoch': 2.46}
+{'loss': 1.164, 'learning_rate': 2.510227272727273e-06, 'epoch': 2.47}
+{'loss': 1.1163, 'learning_rate': 2.5025974025974027e-06, 'epoch': 2.47}
+{'loss': 1.1501, 'learning_rate': 2.4949675324675323e-06, 'epoch': 2.47}
+{'loss': 1.2161, 'learning_rate': 2.4873376623376624e-06, 'epoch': 2.47}
+{'loss': 1.0824, 'learning_rate': 2.4797077922077925e-06, 'epoch': 2.47}
+{'loss': 1.1982, 'learning_rate': 2.472077922077922e-06, 'epoch': 2.47}
+{'loss': 1.0999, 'learning_rate': 2.464448051948052e-06, 'epoch': 2.48}
+{'loss': 1.1285, 'learning_rate': 2.4568181818181823e-06, 'epoch': 2.48}
+{'loss': 1.1485, 'learning_rate': 2.4491883116883115e-06, 'epoch': 2.48}
+{'loss': 1.1693, 'learning_rate': 2.4415584415584416e-06, 'epoch': 2.48}
+{'loss': 1.1777, 'learning_rate': 2.4339285714285717e-06, 'epoch': 2.48}
+{'loss': 1.1927, 'learning_rate': 2.4262987012987013e-06, 'epoch': 2.48}
+{'loss': 1.1591, 'learning_rate': 2.4186688311688314e-06, 'epoch': 2.49}
+{'loss': 1.2, 'learning_rate': 2.4110389610389615e-06, 'epoch': 2.49}
+{'loss': 1.1642, 'learning_rate': 2.4034090909090907e-06, 'epoch': 2.49}
+{'loss': 1.0512, 'learning_rate': 2.3957792207792208e-06, 'epoch': 2.49}
+{'loss': 1.2437, 'learning_rate': 2.388149350649351e-06, 'epoch': 2.49}
+{'loss': 1.2241, 'learning_rate': 2.3805194805194805e-06, 'epoch': 2.49}
+{'loss': 1.0079, 'learning_rate': 2.3728896103896106e-06, 'epoch': 2.5}
+{'loss': 1.3323, 'learning_rate': 2.3652597402597406e-06, 'epoch': 2.5}
+{'loss': 1.2099, 'learning_rate': 2.35762987012987e-06, 'epoch': 2.5}
+{'loss': 1.2722, 'learning_rate': 2.35e-06, 'epoch': 2.5}
+{'loss': 1.2821, 'learning_rate': 2.34237012987013e-06, 'epoch': 2.5}
+{'loss': 1.2629, 'learning_rate': 2.3347402597402597e-06, 'epoch': 2.5}
+{'loss': 1.1285, 'learning_rate': 2.3271103896103897e-06, 'epoch': 2.5}
+{'loss': 1.018, 'learning_rate': 2.31948051948052e-06, 'epoch': 2.51}
+{'loss': 1.0916, 'learning_rate': 2.3118506493506495e-06, 'epoch': 2.51}
+{'loss': 1.3377, 'learning_rate': 2.304220779220779e-06, 'epoch': 2.51}
+{'loss': 1.2492, 'learning_rate': 2.296590909090909e-06, 'epoch': 2.51}
+{'loss': 1.3113, 'learning_rate': 2.288961038961039e-06, 'epoch': 2.51}
+{'loss': 1.214, 'learning_rate': 2.281331168831169e-06, 'epoch': 2.51}
+{'loss': 1.2096, 'learning_rate': 2.273701298701299e-06, 'epoch': 2.52}
+{'loss': 1.1219, 'learning_rate': 2.2660714285714287e-06, 'epoch': 2.52}
+{'loss': 1.1261, 'learning_rate': 2.2584415584415583e-06, 'epoch': 2.52}
+{'loss': 1.3674, 'learning_rate': 2.2508116883116884e-06, 'epoch': 2.52}
+{'loss': 1.2063, 'learning_rate': 2.243181818181818e-06, 'epoch': 2.52}
+{'loss': 1.1467, 'learning_rate': 2.235551948051948e-06, 'epoch': 2.52}
+{'loss': 1.4469, 'learning_rate': 2.227922077922078e-06, 'epoch': 2.53}
+{'loss': 1.0577, 'learning_rate': 2.220292207792208e-06, 'epoch': 2.53}
+{'loss': 1.6794, 'learning_rate': 2.2126623376623375e-06, 'epoch': 2.53}
+{'loss': 1.054, 'learning_rate': 2.2050324675324676e-06, 'epoch': 2.53}
+{'loss': 1.3548, 'learning_rate': 2.1974025974025976e-06, 'epoch': 2.53}
+{'loss': 1.2476, 'learning_rate': 2.1897727272727273e-06, 'epoch': 2.53}
+{'loss': 1.1042, 'learning_rate': 2.1821428571428574e-06, 'epoch': 2.54}
+{'loss': 1.2907, 'learning_rate': 2.1745129870129874e-06, 'epoch': 2.54}
+{'loss': 1.2582, 'learning_rate': 2.1668831168831167e-06, 'epoch': 2.54}
+{'loss': 1.2468, 'learning_rate': 2.1592532467532467e-06, 'epoch': 2.54}
+{'loss': 1.1752, 'learning_rate': 2.151623376623377e-06, 'epoch': 2.54}
+{'loss': 1.3456, 'learning_rate': 2.1439935064935065e-06, 'epoch': 2.54}
+{'loss': 1.6438, 'learning_rate': 2.1363636363636365e-06, 'epoch': 2.55}
+{'loss': 1.1253, 'learning_rate': 2.1287337662337666e-06, 'epoch': 2.55}
+{'loss': 1.2467, 'learning_rate': 2.1211038961038963e-06, 'epoch': 2.55}
+{'loss': 1.2438, 'learning_rate': 2.113474025974026e-06, 'epoch': 2.55}
+{'loss': 1.0756, 'learning_rate': 2.105844155844156e-06, 'epoch': 2.55}
+{'loss': 1.4494, 'learning_rate': 2.0982142857142857e-06, 'epoch': 2.55}
+{'loss': 1.1139, 'learning_rate': 2.0905844155844157e-06, 'epoch': 2.56}
+{'loss': 1.2276, 'learning_rate': 2.082954545454546e-06, 'epoch': 2.56}
+{'loss': 1.3594, 'learning_rate': 2.0753246753246755e-06, 'epoch': 2.56}
+{'loss': 1.2036, 'learning_rate': 2.067694805194805e-06, 'epoch': 2.56}
+{'loss': 0.9886, 'learning_rate': 2.060064935064935e-06, 'epoch': 2.56}
+{'loss': 1.4009, 'learning_rate': 2.052435064935065e-06, 'epoch': 2.56}
+{'loss': 1.1243, 'learning_rate': 2.044805194805195e-06, 'epoch': 2.56}
+{'loss': 1.1073, 'learning_rate': 2.037175324675325e-06, 'epoch': 2.57}
+{'loss': 1.1604, 'learning_rate': 2.0295454545454546e-06, 'epoch': 2.57}
+{'loss': 1.3477, 'learning_rate': 2.0219155844155843e-06, 'epoch': 2.57}
+{'loss': 1.2262, 'learning_rate': 2.0142857142857144e-06, 'epoch': 2.57}
+{'loss': 1.1804, 'learning_rate': 2.006655844155844e-06, 'epoch': 2.57}
+
 86%|████████▌ | 1586/1848 [8:46:45<1:26:59, 19.92s/it]
 86%|████████▌ | 1587/1848 [8:47:05<1:26:40, 19.92s/it]
                                                       

 86%|████████▌ | 1587/1848 [8:47:05<1:26:40, 19.92s/it]
 86%|████████▌ | 1588/1848 [8:47:25<1:26:23, 19.94s/it]
                                                       

 86%|████████▌ | 1588/1848 [8:47:25<1:26:23, 19.94s/it]
 86%|████████▌ | 1589/1848 [8:47:44<1:26:03, 19.94s/it]
                                                       

 86%|████████▌ | 1589/1848 [8:47:44<1:26:03, 19.94s/it]
 86%|████████▌ | 1590/1848 [8:48:04<1:25:45, 19.94s/it]
                                                       

 86%|████████▌ | 1590/1848 [8:48:04<1:25:45, 19.94s/it]
 86%|████████▌ | 1591/1848 [8:48:24<1:25:28, 19.95s/it]
                                                       

 86%|████████▌ | 1591/1848 [8:48:24<1:25:28, 19.95s/it]
 86%|████████▌ | 1592/1848 [8:48:44<1:25:00, 19.93s/it]
                                                       

 86%|████████▌ | 1592/1848 [8:48:44<1:25:00, 19.93s/it]
 86%|████████▌ | 1593/1848 [8:49:04<1:24:46, 19.95s/it]
                                                       

 86%|████████▌ | 1593/1848 [8:49:04<1:24:46, 19.95s/it]
 86%|████████▋ | 1594/1848 [8:49:24<1:24:26, 19.95s/it]
                                                       

 86%|████████▋ | 1594/1848 [8:49:24<1:24:26, 19.95s/it]
 86%|████████▋ | 1595/1848 [8:49:44<1:24:02, 19.93s/it]
                                                       

 86%|████████▋ | 1595/1848 [8:49:44<1:24:02, 19.93s/it]
 86%|████████▋ | 1596/1848 [8:50:04<1:23:35, 19.90s/it]
                                                       

 86%|████████▋ | 1596/1848 [8:50:04<1:23:35, 19.90s/it]
 86%|████████▋ | 1597/1848 [8:50:24<1:23:07, 19.87s/it]
                                                       

 86%|████████▋ | 1597/1848 [8:50:24<1:23:07, 19.87s/it]
 86%|████████▋ | 1598/1848 [8:50:44<1:22:55, 19.90s/it]
                                                       

 86%|████████▋ | 1598/1848 [8:50:44<1:22:55, 19.90s/it]
 87%|████████▋ | 1599/1848 [8:51:04<1:22:38, 19.91s/it]
                                                       

 87%|████████▋ | 1599/1848 [8:51:04<1:22:38, 19.91s/it]
 87%|████████▋ | 1600/1848 [8:51:24<1:22:18, 19.91s/it]
                                                       

 87%|████████▋ | 1600/1848 [8:51:24<1:22:18, 19.91s/it]
 87%|████████▋ | 1601/1848 [8:51:44<1:23:07, 20.19s/it]
                                                       

 87%|████████▋ | 1601/1848 [8:51:44<1:23:07, 20.19s/it]
 87%|████████▋ | 1602/1848 [8:52:04<1:22:20, 20.09s/it]
                                                       

 87%|████████▋ | 1602/1848 [8:52:04<1:22:20, 20.09s/it]
 87%|████████▋ | 1603/1848 [8:52:24<1:21:48, 20.04s/it]
                                                       

 87%|████████▋ | 1603/1848 [8:52:24<1:21:48, 20.04s/it]
 87%|████████▋ | 1604/1848 [8:52:44<1:21:19, 20.00s/it]
                                                       

 87%|████████▋ | 1604/1848 [8:52:44<1:21:19, 20.00s/it]
 87%|████████▋ | 1605/1848 [8:53:04<1:20:52, 19.97s/it]
                                                       

 87%|████████▋ | 1605/1848 [8:53:04<1:20:52, 19.97s/it]
 87%|████████▋ | 1606/1848 [8:53:24<1:20:30, 19.96s/it]
                                                       

 87%|██████���█▋ | 1606/1848 [8:53:24<1:20:30, 19.96s/it]
 87%|████████▋ | 1607/1848 [8:53:44<1:20:12, 19.97s/it]
                                                       

 87%|████████▋ | 1607/1848 [8:53:44<1:20:12, 19.97s/it]
 87%|████████▋ | 1608/1848 [8:54:04<1:19:39, 19.91s/it]
                                                       

 87%|████████▋ | 1608/1848 [8:54:04<1:19:39, 19.91s/it]
 87%|████████▋ | 1609/1848 [8:54:24<1:19:18, 19.91s/it]
                                                       

 87%|████████▋ | 1609/1848 [8:54:24<1:19:18, 19.91s/it]
 87%|████████▋ | 1610/1848 [8:54:44<1:19:02, 19.93s/it]
                                                       

 87%|████████▋ | 1610/1848 [8:54:44<1:19:02, 19.93s/it]
 87%|████████▋ | 1611/1848 [8:55:03<1:18:34, 19.89s/it]
                                                       

 87%|████████▋ | 1611/1848 [8:55:03<1:18:34, 19.89s/it]
 87%|████████▋ | 1612/1848 [8:55:23<1:18:17, 19.90s/it]
                                                       

 87%|████████▋ | 1612/1848 [8:55:23<1:18:17, 19.90s/it]
 87%|████████▋ | 1613/1848 [8:55:43<1:17:58, 19.91s/it]
                                                       

 87%|████████▋ | 1613/1848 [8:55:43<1:17:58, 19.91s/it]
 87%|████████▋ | 1614/1848 [8:56:03<1:17:38, 19.91s/it]
                                                       

 87%|████████▋ | 1614/1848 [8:56:03<1:17:38, 19.91s/it]
 87%|████████▋ | 1615/1848 [8:56:23<1:17:21, 19.92s/it]
                                                       

 87%|████████▋ | 1615/1848 [8:56:23<1:17:21, 19.92s/it]
 87%|████████▋ | 1616/1848 [8:56:43<1:16:59, 19.91s/it]
                                                       

 87%|████████▋ | 1616/1848 [8:56:43<1:16:59, 19.91s/it]
 88%|████████▊ | 1617/1848 [8:57:03<1:16:44, 19.93s/it]
                                                       

 88%|████████▊ | 1617/1848 [8:57:03<1:16:44, 19.93s/it]
 88%|████████▊ | 1618/1848 [8:57:23<1:16:19, 19.91s/it]
                                                       

 88%|████████▊ | 1618/1848 [8:57:23<1:16:19, 19.91s/it]
 88%|████████▊ | 1619/1848 [8:57:43<1:15:56, 19.90s/it]
                                                       

 88%|████████▊ | 1619/1848 [8:57:43<1:15:56, 19.90s/it]
 88%|████████▊ | 1620/1848 [8:58:03<1:15:33, 19.88s/it]
                                                       

 88%|████████▊ | 1620/1848 [8:58:03<1:15:33, 19.88s/it]
 88%|████████▊ | 1621/1848 [8:58:23<1:15:21, 19.92s/it]
                                                       

 88%|████████▊ | 1621/1848 [8:58:23<1:15:21, 19.92s/it]
 88%|████████▊ | 1622/1848 [8:58:43<1:15:05, 19.93s/it]
                                                       

 88%|████████▊ | 1622/1848 [8:58:43<1:15:05, 19.93s/it]
 88%|████████▊ | 1623/1848 [8:59:02<1:14:42, 19.92s/it]
                                                       

 88%|████████▊ | 1623/1848 [8:59:02<1:14:42, 19.92s/it]
 88%|████████▊ | 1624/1848 [8:59:22<1:14:25, 19.93s/it]
                                                       

 88%|████████▊ | 1624/1848 [8:59:22<1:14:25, 19.93s/it]
 88%|████████▊ | 1625/1848 [8:59:42<1:14:08, 19.95s/it]
                                                       

 88%|████████▊ | 1625/1848 [8:59:42<1:14:08, 19.95s/it]
 88%|████████▊ | 1626/1848 [9:00:02<1:13:45, 19.93s/it]
                                                       

 88%|████████▊ | 1626/1848 [9:00:02<1:13:45, 19.93s/it]
 88%|████████▊ | 1627/1848 [9:00:22<1:13:24, 19.93s/it]
                                                       

 88%|████████▊ | 1627/1848 [9:00:22<1:13:24, 19.93s/it]
 88%|████████▊ | 1628/1848 [9:00:42<1:13:03, 19.93s/it]
                                                       

 88%|████████▊ | 1628/1848 [9:00:42<1:13:03, 19.93s/it]
 88%|████████▊ | 1629/1848 [9:01:02<1:12:45, 19.93s/it]
                                                       

 88%|████████▊ | 1629/1848 [9:01:02<1:12:45, 19.93s/it]
 88%|████████▊ | 1630/1848 [9:01:22<1:12:29, 19.95s/it]
                                                       

 88%|████████▊ | 1630/1848 [9:01:22<1:12:29, 19.95s/it]
 88%|████████▊ | 1631/1848 [9:01:42<1:12:11, 19.96s/it]
                                                       

 88%|████��███▊ | 1631/1848 [9:01:42<1:12:11, 19.96s/it]
 88%|████████▊ | 1632/1848 [9:02:02<1:11:48, 19.95s/it]
                                                       

 88%|████████▊ | 1632/1848 [9:02:02<1:11:48, 19.95s/it]
 88%|████████▊ | 1633/1848 [9:02:22<1:11:24, 19.93s/it]
                                                       

 88%|████████▊ | 1633/1848 [9:02:22<1:11:24, 19.93s/it]
 88%|████████▊ | 1634/1848 [9:02:42<1:11:00, 19.91s/it]
                                                       

 88%|████████▊ | 1634/1848 [9:02:42<1:11:00, 19.91s/it]
 88%|████████▊ | 1635/1848 [9:03:02<1:10:39, 19.90s/it]
                                                       

 88%|████████▊ | 1635/1848 [9:03:02<1:10:39, 19.90s/it]
 89%|████████▊ | 1636/1848 [9:03:22<1:10:24, 19.93s/it]
                                                       

 89%|████████▊ | 1636/1848 [9:03:22<1:10:24, 19.93s/it]
 89%|████████▊ | 1637/1848 [9:03:41<1:10:04, 19.92s/it]
                                                       

 89%|████████▊ | 1637/1848 [9:03:41<1:10:04, 19.92s/it]
 89%|████████▊ | 1638/1848 [9:04:01<1:09:42, 19.92s/it]
                                                       

 89%|████████▊ | 1638/1848 [9:04:01<1:09:42, 19.92s/it]
 89%|████████▊ | 1639/1848 [9:04:21<1:09:23, 19.92s/it]
                                                       

 89%|████████▊ | 1639/1848 [9:04:21<1:09:23, 19.92s/it]
 89%|████████▊ | 1640/1848 [9:04:41<1:09:03, 19.92s/it]
                                                       

 89%|████████▊ | 1640/1848 [9:04:41<1:09:03, 19.92s/it]
 89%|████████▉ | 1641/1848 [9:05:01<1:08:38, 19.90s/it]
                                                       

 89%|████████▉ | 1641/1848 [9:05:01<1:08:38, 19.90s/it]
 89%|████████▉ | 1642/1848 [9:05:21<1:08:19, 19.90s/it]
                                                       

 89%|████████▉ | 1642/1848 [9:05:21<1:08:19, 19.90s/it]
 89%|████████▉ | 1643/1848 [9:05:41<1:07:58, 19.89s/it]
                                                       

 89%|████████▉ | 1643/1848 [9:05:41<1:07:58, 19.89s/it]
 89%|████████▉ | 1644/1848 [9:06:01<1:07:41, 19.91s/it]
                                                       

 89%|████████▉ | 1644/1848 [9:06:01<1:07:41, 19.91s/it]
 89%|████████▉ | 1645/1848 [9:06:21<1:07:24, 19.92s/it]
                                                       

 89%|████████▉ | 1645/1848 [9:06:21<1:07:24, 19.92s/it]
 89%|████████▉ | 1646/1848 [9:06:41<1:06:59, 19.90s/it]
                                                       

 89%|████████▉ | 1646/1848 [9:06:41<1:06:59, 19.90s/it]
 89%|████████▉ | 1647/1848 [9:07:01<1:06:42, 19.91s/it]
                                                       

 89%|████████▉ | 1647/1848 [9:07:01<1:06:42, 19.91s/it]
 89%|████████▉ | 1648/1848 [9:07:20<1:06:24, 19.92s/it]
                                                       

 89%|████████▉ | 1648/1848 [9:07:20<1:06:24, 19.92s/it]
 89%|████████▉ | 1649/1848 [9:07:40<1:05:57, 19.89s/it]
                                                       

 89%|████████▉ | 1649/1848 [9:07:40<1:05:57, 19.89s/it]
 89%|████████▉ | 1650/1848 [9:08:00<1:05:38, 19.89s/it]
                                                       

 89%|████████▉ | 1650/1848 [9:08:00<1:05:38, 19.89s/it]
 89%|████████▉ | 1651/1848 [9:08:20<1:05:23, 19.91s/it]
                                                       

 89%|████████▉ | 1651/1848 [9:08:20<1:05:23, 19.91s/it]
 89%|████████▉ | 1652/1848 [9:08:40<1:05:04, 19.92s/it]
                                                       

 89%|████████▉ | 1652/1848 [9:08:40<1:05:04, 19.92s/it]
 89%|████████▉ | 1653/1848 [9:09:00<1:04:41, 19.91s/it]
                                                       

 89%|████████▉ | 1653/1848 [9:09:00<1:04:41, 19.91s/it]
 90%|████████▉ | 1654/1848 [9:09:20<1:04:23, 19.91s/it]
                                                       

 90%|████████▉ | 1654/1848 [9:09:20<1:04:23, 19.91s/it]
 90%|████████▉ | 1655/1848 [9:09:40<1:04:07, 19.93s/it]
                                                       

 90%|████████▉ | 1655/1848 [9:09:40<1:04:07, 19.93s/it]
 90%|████████▉ | 1656/1848 [9:10:00<1:03:47, 19.94s/it]
                                                       

 90%|████████▉ | 1656/1848 [9:10:00<1:03:47, 19.94s/it]
 90%|████████▉ | 1657/1848 [9:10:20<1:03:22, 19.91s/it]
                                                       

 90%|████████▉ | 1657/1848 [9:10:20<1:03:22, 19.91s/it]
 90%|████████▉ | 1658/1848 [9:10:40<1:02:59, 19.89s/it]
                                                       

 90%|████████▉ | 1658/1848 [9:10:40<1:02:59, 19.89s/it]
 90%|████████▉ | 1659/1848 [9:10:59<1:02:43, 19.91s/it]
                                                       

 90%|████████▉ | 1659/1848 [9:10:59<1:02:43, 19.91s/it]
 90%|████████▉ | 1660/1848 [9:11:19<1:02:19, 19.89s/it]
                                                       

 90%|████████▉ | 1660/1848 [9:11:19<1:02:19, 19.89s/it]
 90%|████████▉ | 1661/1848 [9:11:39<1:01:58, 19.88s/it]
                                                       

 90%|████████▉ | 1661/1848 [9:11:39<1:01:58, 19.88s/it]
 90%|████████▉ | 1662/1848 [9:11:59<1:01:40, 19.89s/it]
                                                       

 90%|████████▉ | 1662/1848 [9:11:59<1:01:40, 19.89s/it]
 90%|████████▉ | 1663/1848 [9:12:19<1:01:19, 19.89s/it]
                                                       

 90%|████████▉ | 1663/1848 [9:12:19<1:01:19, 19.89s/it]
 90%|█████████ | 1664/1848 [9:12:39<1:01:05, 19.92s/it]
                                                       

 90%|█████████ | 1664/1848 [9:12:39<1:01:05, 19.92s/it]
 90%|█████████ | 1665/1848 [9:12:59<1:00:48, 19.94s/it]
                                                       

 90%|█████████ | 1665/1848 [9:12:59<1:00:48, 19.94s/it]
 90%|█████████ | 1666/1848 [9:13:19<1:00:30, 19.95s/it]
                                                       

 90%|█████████ | 1666/1848 [9:13:19<1:00:30, 19.95s/it]
 90%|█████████ | 1667/1848 [9:13:39<1:00:06, 19.93s/it]
                                                       

 90%|█████████ | 1667/1848 [9:13:39<1:00:06, 19.93s/it]
 90%|█████████ | 1668/1848 [9:13:59<59:47, 19.93s/it]  
                                                     

 90%|█████████ | 1668/1848 [9:13:59<59:47, 19.93s/it]
 90%|█████████ | 1669/1848 [9:14:19<59:27, 19.93s/it]
                                                     

 90%|█████████ | 1669/1848 [9:14:19<59:27, 19.93s/it]
 90%|█████████ | 1670/1848 [9:14:39<59:08, 19.94s/it]
                                                     

 90%|█████████ | 1670/1848 [9:14:39<59:08, 19.94s/it]
 90%|█████████ | 1671/1848 [9:14:58<58:44, 19.91s/it]
                                                     

 90%|█████████ | 1671/1848 [9:14:58<58:44, 19.91s/it]
 90%|█████████ | 1672/1848 [9:15:18<58:23, 19.91s/it]
                                                     

 90%|█████████ | 1672/1848 [9:15:18<58:23, 19.91s/it]
 91%|█████████ | 1673/1848 [9:15:38<58:06, 19.92s/it]
                                                     

 91%|█████████ | 1673/1848 [9:15:38<58:06, 19.92s/it]
 91%|█████████ | 1674/1848 [9:15:58<57:51, 19.95s/it]
                                                     

 91%|█████████ | 1674/1848 [9:15:58<57:51, 19.95s/it]
 91%|█████████ | 1675/1848 [9:16:18<57:29, 19.94s/it]
                                                     

 91%|█████████ | 1675/1848 [9:16:18<57:29, 19.94s/it]
 91%|█████████ | 1676/1848 [9:16:38<57:05, 19.92s/it]
                                                     

 91%|█████████ | 1676/1848 [9:16:38<57:05, 19.92s/it]
 91%|█████████ | 1677/1848 [9:16:58<56:45, 19.92s/it]
                                                     

 91%|█████████ | 1677/1848 [9:16:58<56:45, 19.92s/it]
 91%|█████████ | 1678/1848 [9:17:18<56:24, 19.91s/it]
                                                     

 91%|█████████ | 1678/1848 [9:17:18<56:24, 19.91s/it]
 91%|█████████ | 1679/1848 [9:17:38<56:06, 19.92s/it]
                                                     

 91%|█████████ | 1679/1848 [9:17:38<56:06, 19.92s/it]
 91%|█████████ | 1680/1848 [9:17:58<55:50, 19.94s/it]
                                                     

 91%|█████████ | 1680/1848 [9:17:58<55:50, 19.94s/it]
 91%|█████████ | 1681/1848 [9:18:18<55:29, 19.94s/it]
                                                     

 91%|█████████ | 1681/1848 [9:18:18<55:29, 19.94s/it]
 91%|█████████ | 1682/1848 [9:18:38<55:11, 19.95s/it]
                                                     

 91%|█████████ | 1682/1848 [9:18:38<55:11, 19.95s/it]
 91%|█████████ | 1683/1848 [9:18:58<54:51, 19.95s/it]
                                                     

 91%|█████████ | 1683/1848 [9:18:58<54:51, 19.95s/it]
 91%|█████████ | 1684/1848 [9:19:18<54:31, 19.95s/it]
                                                     

 91%|█████████ | 1684/1848 [9:19:18<54:31, 19.95s/it]
 91%|█████████ | 1685/1848 [9:19:38<54:11, 19.95s/it]
                                                     

 91%|█████████ | 1685/1848 [9:19:38<54:11, 19.95s/it]
 91%|█████████ | 1686/1848 [9:19:58<53:51, 19.94s/it]
                                                     

 91%|█████████ | 1686/1848 [9:19:58<53:51, 19.94s/it]
 91%|█████████▏| 1687/1848 [9:20:18<53:32, 19.95s/it]
                                                     

 91%|█████████▏| 1687/1848 [9:20:18<53:32, 19.95s/it]
 91%|█████████▏| 1688/1848 [9:20:37<53:11, 19.95s/it]
                                                     

 91%|█████████▏| 1688/1848 [9:20:37<53:11, 19.95s/it]
 91%|█████████▏| 1689/1848 [9:20:57<52:50, 19.94s/it]
                                                     

 91%|█████████▏| 1689/1848 [9:20:57<52:50, 19.94s/it]
 91%|█████████▏| 1690/1848 [9:21:17<52:31, 19.95s/it]
                                                     

 91%|█████████▏| 1690/1848 [9:21:17<52:31, 19.95s/it]
 92%|█████████▏| 1691/1848 [9:21:37<52:08, 19.93s/it]
                                                     

 92%|█████████▏| 1691/1848 [9:21:37<52:08, 19.93s/it]
 92%|█████████▏| 1692/1848 [9:21:57<51:52, 19.95s/it]
                                                     

 92%|█████████▏| 1692/1848 [9:21:57<51:52, 19.95s/it]
 92%|█████████▏| 1693/1848 [9:22:17<51:33, 19.96s/it]
                                                     

 92%|█████████▏| 1693/1848 [9:22:17<51:33, 19.96s/it]
 92%|█████████▏| 1694/1848 [9:22:37<51:11, 19.94s/it]
                                                     

 92%|█████████▏| 1694/1848 [9:22:37<51:11, 19.94s/it]
 92%|█████████▏| 1695/1848 [9:22:57<50:51, 19.94s/it]
                                                     

 92%|█████████▏| 1695/1848 [9:22:57<50:51, 19.94s/it]
 92%|█████████▏| 1696/1848 [9:23:17<50:30, 19.94s/it]
                                                     

 92%|█████████▏| 1696/1848 [9:23:17<50:30, 19.94s/it]
 92%|█████████▏| 1697/1848 [9:23:37<50:12, 19.95s/it]
                                                     

 92%|█████████▏| 1697/1848 [9:23:37<50:12, 19.95s/it]
 92%|█████████▏| 1698/1848 [9:23:57<49:51, 19.94s/it]
                                                     

 92%|█████████▏| 1698/1848 [9:23:57<49:51, 19.94s/it]
 92%|█████████▏| 1699/1848 [9:24:17<49:27, 19.92s/it]
                                                     
{'loss': 1.2778, 'learning_rate': 1.999025974025974e-06, 'epoch': 2.57}
+{'loss': 1.2201, 'learning_rate': 1.991396103896104e-06, 'epoch': 2.58}
+{'loss': 1.1304, 'learning_rate': 1.983766233766234e-06, 'epoch': 2.58}
+{'loss': 1.1482, 'learning_rate': 1.9761363636363635e-06, 'epoch': 2.58}
+{'loss': 1.1162, 'learning_rate': 1.9685064935064935e-06, 'epoch': 2.58}
+{'loss': 1.2129, 'learning_rate': 1.960876623376623e-06, 'epoch': 2.58}
+{'loss': 1.1017, 'learning_rate': 1.9532467532467533e-06, 'epoch': 2.58}
+{'loss': 1.2016, 'learning_rate': 1.9456168831168833e-06, 'epoch': 2.59}
+{'loss': 1.3339, 'learning_rate': 1.937987012987013e-06, 'epoch': 2.59}
+{'loss': 1.058, 'learning_rate': 1.930357142857143e-06, 'epoch': 2.59}
+{'loss': 1.3185, 'learning_rate': 1.9227272727272727e-06, 'epoch': 2.59}
+{'loss': 1.3387, 'learning_rate': 1.915097402597403e-06, 'epoch': 2.59}
+{'loss': 1.3425, 'learning_rate': 1.9074675324675324e-06, 'epoch': 2.59}
+{'loss': 1.1419, 'learning_rate': 1.8998376623376625e-06, 'epoch': 2.6}
+{'loss': 1.1277, 'learning_rate': 1.8922077922077924e-06, 'epoch': 2.6}
+{'loss': 1.2132, 'learning_rate': 1.8845779220779223e-06, 'epoch': 2.6}
+{'loss': 1.2349, 'learning_rate': 1.876948051948052e-06, 'epoch': 2.6}
+{'loss': 1.1176, 'learning_rate': 1.8693181818181818e-06, 'epoch': 2.6}
+{'loss': 1.0511, 'learning_rate': 1.8616883116883116e-06, 'epoch': 2.6}
+{'loss': 1.3389, 'learning_rate': 1.8540584415584417e-06, 'epoch': 2.61}
+{'loss': 1.2014, 'learning_rate': 1.8464285714285716e-06, 'epoch': 2.61}
+{'loss': 1.2086, 'learning_rate': 1.8387987012987014e-06, 'epoch': 2.61}
+{'loss': 1.2962, 'learning_rate': 1.831168831168831e-06, 'epoch': 2.61}
+{'loss': 1.1354, 'learning_rate': 1.823538961038961e-06, 'epoch': 2.61}
+{'loss': 1.139, 'learning_rate': 1.815909090909091e-06, 'epoch': 2.61}
+{'loss': 1.3333, 'learning_rate': 1.8082792207792209e-06, 'epoch': 2.62}
+{'loss': 1.2352, 'learning_rate': 1.8006493506493507e-06, 'epoch': 2.62}
+{'loss': 1.2097, 'learning_rate': 1.7930194805194808e-06, 'epoch': 2.62}
+{'loss': 1.2063, 'learning_rate': 1.7853896103896103e-06, 'epoch': 2.62}
+{'loss': 1.2092, 'learning_rate': 1.7777597402597401e-06, 'epoch': 2.62}
+{'loss': 1.1302, 'learning_rate': 1.7701298701298702e-06, 'epoch': 2.62}
+{'loss': 0.8814, 'learning_rate': 1.7625e-06, 'epoch': 2.62}
+{'loss': 1.5134, 'learning_rate': 1.75487012987013e-06, 'epoch': 2.63}
+{'loss': 1.1466, 'learning_rate': 1.7472402597402598e-06, 'epoch': 2.63}
+{'loss': 1.2133, 'learning_rate': 1.7396103896103897e-06, 'epoch': 2.63}
+{'loss': 1.2201, 'learning_rate': 1.7319805194805195e-06, 'epoch': 2.63}
+{'loss': 1.3781, 'learning_rate': 1.7243506493506494e-06, 'epoch': 2.63}
+{'loss': 1.1921, 'learning_rate': 1.7167207792207792e-06, 'epoch': 2.63}
+{'loss': 1.0857, 'learning_rate': 1.7090909090909091e-06, 'epoch': 2.64}
+{'loss': 1.4588, 'learning_rate': 1.701461038961039e-06, 'epoch': 2.64}
+{'loss': 1.4739, 'learning_rate': 1.6938311688311688e-06, 'epoch': 2.64}
+{'loss': 1.128, 'learning_rate': 1.6862012987012987e-06, 'epoch': 2.64}
+{'loss': 1.3438, 'learning_rate': 1.6785714285714286e-06, 'epoch': 2.64}
+{'loss': 1.2551, 'learning_rate': 1.6709415584415584e-06, 'epoch': 2.64}
+{'loss': 1.3643, 'learning_rate': 1.6633116883116885e-06, 'epoch': 2.65}
+{'loss': 1.1792, 'learning_rate': 1.6556818181818184e-06, 'epoch': 2.65}
+{'loss': 1.1103, 'learning_rate': 1.648051948051948e-06, 'epoch': 2.65}
+{'loss': 1.1658, 'learning_rate': 1.640422077922078e-06, 'epoch': 2.65}
+{'loss': 1.1525, 'learning_rate': 1.632792207792208e-06, 'epoch': 2.65}
+{'loss': 1.2272, 'learning_rate': 1.6251623376623376e-06, 'epoch': 2.65}
+{'loss': 1.2277, 'learning_rate': 1.6175324675324677e-06, 'epoch': 2.66}
+{'loss': 1.1239, 'learning_rate': 1.6099025974025975e-06, 'epoch': 2.66}
+{'loss': 1.2222, 'learning_rate': 1.6022727272727272e-06, 'epoch': 2.66}
+{'loss': 1.2446, 'learning_rate': 1.5946428571428573e-06, 'epoch': 2.66}
+{'loss': 1.1923, 'learning_rate': 1.5870129870129871e-06, 'epoch': 2.66}
+{'loss': 1.3875, 'learning_rate': 1.5793831168831168e-06, 'epoch': 2.66}
+{'loss': 1.2787, 'learning_rate': 1.5717532467532469e-06, 'epoch': 2.67}
+{'loss': 1.1361, 'learning_rate': 1.5641233766233767e-06, 'epoch': 2.67}
+{'loss': 1.3719, 'learning_rate': 1.5564935064935064e-06, 'epoch': 2.67}
+{'loss': 1.3122, 'learning_rate': 1.5488636363636365e-06, 'epoch': 2.67}
+{'loss': 1.1022, 'learning_rate': 1.5412337662337663e-06, 'epoch': 2.67}
+{'loss': 1.3986, 'learning_rate': 1.5336038961038962e-06, 'epoch': 2.67}
+{'loss': 1.3933, 'learning_rate': 1.525974025974026e-06, 'epoch': 2.68}
+{'loss': 1.5289, 'learning_rate': 1.518344155844156e-06, 'epoch': 2.68}
+{'loss': 1.1084, 'learning_rate': 1.5107142857142858e-06, 'epoch': 2.68}
+{'loss': 1.1632, 'learning_rate': 1.5030844155844156e-06, 'epoch': 2.68}
+{'loss': 1.2777, 'learning_rate': 1.4954545454545455e-06, 'epoch': 2.68}
+{'loss': 1.2898, 'learning_rate': 1.4878246753246754e-06, 'epoch': 2.68}
+{'loss': 1.1947, 'learning_rate': 1.4801948051948052e-06, 'epoch': 2.69}
+{'loss': 1.1012, 'learning_rate': 1.472564935064935e-06, 'epoch': 2.69}
+{'loss': 1.2661, 'learning_rate': 1.4649350649350652e-06, 'epoch': 2.69}
+{'loss': 1.3082, 'learning_rate': 1.4573051948051948e-06, 'epoch': 2.69}
+{'loss': 1.4104, 'learning_rate': 1.4496753246753247e-06, 'epoch': 2.69}
+{'loss': 1.0665, 'learning_rate': 1.4420454545454548e-06, 'epoch': 2.69}
+{'loss': 1.1671, 'learning_rate': 1.4344155844155844e-06, 'epoch': 2.69}
+{'loss': 1.2786, 'learning_rate': 1.4267857142857143e-06, 'epoch': 2.7}
+{'loss': 1.0918, 'learning_rate': 1.4191558441558443e-06, 'epoch': 2.7}
+{'loss': 1.411, 'learning_rate': 1.411525974025974e-06, 'epoch': 2.7}
+{'loss': 1.1753, 'learning_rate': 1.4038961038961039e-06, 'epoch': 2.7}
+{'loss': 1.153, 'learning_rate': 1.396266233766234e-06, 'epoch': 2.7}
+{'loss': 1.1408, 'learning_rate': 1.3886363636363636e-06, 'epoch': 2.7}
+{'loss': 1.2004, 'learning_rate': 1.3810064935064937e-06, 'epoch': 2.71}
+{'loss': 1.4801, 'learning_rate': 1.3733766233766235e-06, 'epoch': 2.71}
+{'loss': 1.2052, 'learning_rate': 1.3657467532467532e-06, 'epoch': 2.71}
+{'loss': 1.1901, 'learning_rate': 1.3581168831168833e-06, 'epoch': 2.71}
+{'loss': 1.2254, 'learning_rate': 1.3504870129870131e-06, 'epoch': 2.71}
+{'loss': 1.0342, 'learning_rate': 1.3428571428571428e-06, 'epoch': 2.71}
+{'loss': 1.0789, 'learning_rate': 1.3352272727272728e-06, 'epoch': 2.72}
+{'loss': 1.2679, 'learning_rate': 1.3275974025974027e-06, 'epoch': 2.72}
+{'loss': 1.2282, 'learning_rate': 1.3199675324675324e-06, 'epoch': 2.72}
+{'loss': 1.1718, 'learning_rate': 1.3123376623376624e-06, 'epoch': 2.72}
+{'loss': 1.5584, 'learning_rate': 1.3047077922077923e-06, 'epoch': 2.72}
+{'loss': 1.2425, 'learning_rate': 1.297077922077922e-06, 'epoch': 2.72}
+{'loss': 1.2278, 'learning_rate': 1.289448051948052e-06, 'epoch': 2.73}
+{'loss': 1.1212, 'learning_rate': 1.2818181818181819e-06, 'epoch': 2.73}
+{'loss': 1.1535, 'learning_rate': 1.2741883116883115e-06, 'epoch': 2.73}
+{'loss': 1.2196, 'learning_rate': 1.2665584415584416e-06, 'epoch': 2.73}
+{'loss': 1.1863, 'learning_rate': 1.2589285714285715e-06, 'epoch': 2.73}
+{'loss': 1.3182, 'learning_rate': 1.2512987012987013e-06, 'epoch': 2.73}
+{'loss': 1.258, 'learning_rate': 1.2436688311688312e-06, 'epoch': 2.74}
+{'loss': 1.2579, 'learning_rate': 1.236038961038961e-06, 'epoch': 2.74}
+{'loss': 1.1068, 'learning_rate': 1.2284090909090911e-06, 'epoch': 2.74}
+{'loss': 1.0226, 'learning_rate': 1.2207792207792208e-06, 'epoch': 2.74}
+{'loss': 1.1999, 'learning_rate': 1.2131493506493507e-06, 'epoch': 2.74}
+{'loss': 1.2992, 'learning_rate': 1.2055194805194807e-06, 'epoch': 2.74}
+{'loss': 1.3143, 'learning_rate': 1.1978896103896104e-06, 'epoch': 2.75}
+{'loss': 1.4205, 'learning_rate': 1.1902597402597402e-06, 'epoch': 2.75}
+{'loss': 1.2238, 'learning_rate': 1.1826298701298703e-06, 'epoch': 2.75}
+{'loss': 1.102, 'learning_rate': 1.175e-06, 'epoch': 2.75}
+{'loss': 1.1832, 'learning_rate': 1.1673701298701298e-06, 'epoch': 2.75}
+{'loss': 1.2117, 'learning_rate': 1.15974025974026e-06, 'epoch': 2.75}
+{'loss': 1.2042, 'learning_rate': 1.1521103896103896e-06, 'epoch': 2.75}
+{'loss': 1.2918, 'learning_rate': 1.1444805194805194e-06, 'epoch': 2.76}
+
 92%|█████████▏| 1699/1848 [9:24:17<49:27, 19.92s/it]
 92%|█████████▏| 1700/1848 [9:24:37<49:08, 19.92s/it]
                                                     

 92%|█████████▏| 1700/1848 [9:24:37<49:08, 19.92s/it]
 92%|█████████▏| 1701/1848 [9:24:57<49:28, 20.19s/it]
                                                     

 92%|█████████▏| 1701/1848 [9:24:57<49:28, 20.19s/it]
 92%|█████████▏| 1702/1848 [9:25:17<48:53, 20.09s/it]
                                                     

 92%|█████████▏| 1702/1848 [9:25:17<48:53, 20.09s/it]
 92%|█████████▏| 1703/1848 [9:25:37<48:25, 20.04s/it]
                                                     

 92%|█████████▏| 1703/1848 [9:25:37<48:25, 20.04s/it]
 92%|█████████▏| 1704/1848 [9:25:57<48:01, 20.01s/it]
                                                     

 92%|█████████▏| 1704/1848 [9:25:57<48:01, 20.01s/it]
 92%|█████████▏| 1705/1848 [9:26:17<47:38, 19.99s/it]
                                                     

 92%|█████████▏| 1705/1848 [9:26:17<47:38, 19.99s/it]
 92%|█████████▏| 1706/1848 [9:26:37<47:18, 19.99s/it]
                                                     

 92%|█████████▏| 1706/1848 [9:26:37<47:18, 19.99s/it]
 92%|█████████▏| 1707/1848 [9:26:57<46:55, 19.97s/it]
                                                     

 92%|█████████▏| 1707/1848 [9:26:57<46:55, 19.97s/it]
 92%|█████████▏| 1708/1848 [9:27:17<46:33, 19.95s/it]
                                                     

 92%|█████████▏| 1708/1848 [9:27:17<46:33, 19.95s/it]
 92%|█████████▏| 1709/1848 [9:27:37<46:09, 19.93s/it]
                                                     

 92%|█████████▏| 1709/1848 [9:27:37<46:09, 19.93s/it]
 93%|█████████▎| 1710/1848 [9:27:57<45:46, 19.90s/it]
                                                     

 93%|█████████▎| 1710/1848 [9:27:57<45:46, 19.90s/it]
 93%|█████████▎| 1711/1848 [9:28:17<45:31, 19.94s/it]
                                                     

 93%|█████████▎| 1711/1848 [9:28:17<45:31, 19.94s/it]
 93%|█████████▎| 1712/1848 [9:28:37<45:13, 19.95s/it]
                                                     

 93%|█████████▎| 1712/1848 [9:28:37<45:13, 19.95s/it]
 93%|█████████▎| 1713/1848 [9:28:57<44:50, 19.93s/it]
                                                     

 93%|█████████▎| 1713/1848 [9:28:57<44:50, 19.93s/it]
 93%|█████████▎| 1714/1848 [9:29:16<44:27, 19.91s/it]
                                                     

 93%|█████████▎| 1714/1848 [9:29:16<44:27, 19.91s/it]
 93%|█████████▎| 1715/1848 [9:29:36<44:09, 19.92s/it]
                                                     

 93%|█████████▎| 1715/1848 [9:29:36<44:09, 19.92s/it]
 93%|█████████▎| 1716/1848 [9:29:56<43:49, 19.92s/it]
                                                     

 93%|█████████▎| 1716/1848 [9:29:56<43:49, 19.92s/it]
 93%|█████████▎| 1717/1848 [9:30:16<43:32, 19.94s/it]
                                                     

 93%|█████████▎| 1717/1848 [9:30:16<43:32, 19.94s/it]
 93%|█████████▎| 1718/1848 [9:30:36<43:09, 19.92s/it]
                                                     

 93%|█████████▎| 1718/1848 [9:30:36<43:09, 19.92s/it]
 93%|█████████▎| 1719/1848 [9:30:56<42:52, 19.94s/it]
                                                     

 93%|█████████▎| 1719/1848 [9:30:56<42:52, 19.94s/it]
 93%|█████████▎| 1720/1848 [9:31:16<42:31, 19.93s/it]
                                                     

 93%|█████████▎| 1720/1848 [9:31:16<42:31, 19.93s/it]
 93%|█████████▎| 1721/1848 [9:31:36<42:15, 19.96s/it]
                                                     

 93%|█████████▎| 1721/1848 [9:31:36<42:15, 19.96s/it]
 93%|█████████▎| 1722/1848 [9:31:56<41:54, 19.96s/it]
                                                     

 93%|█████████▎| 1722/1848 [9:31:56<41:54, 19.96s/it]
 93%|█████████▎| 1723/1848 [9:32:16<41:36, 19.97s/it]
                                                     

 93%|█████████▎| 1723/1848 [9:32:16<41:36, 19.97s/it]
 93%|█████████▎| 1724/1848 [9:32:36<41:17, 19.98s/it]
                                                     

 93%|█████████▎| 1724/1848 [9:32:36<41:17, 19.98s/it]
 93%|█████████▎| 1725/1848 [9:32:56<40:56, 19.97s/it]
                                                     

 93%|█████████▎| 1725/1848 [9:32:56<40:56, 19.97s/it]
 93%|█████████▎| 1726/1848 [9:33:16<40:35, 19.96s/it]
                                                     

 93%|█████████▎| 1726/1848 [9:33:16<40:35, 19.96s/it]
 93%|█████████▎| 1727/1848 [9:33:36<40:13, 19.94s/it]
                                                     

 93%|█████████▎| 1727/1848 [9:33:36<40:13, 19.94s/it]
 94%|█████████▎| 1728/1848 [9:33:56<39:54, 19.95s/it]
                                                     

 94%|█████████▎| 1728/1848 [9:33:56<39:54, 19.95s/it]
 94%|█████████▎| 1729/1848 [9:34:16<39:32, 19.94s/it]
                                                     

 94%|█████████▎| 1729/1848 [9:34:16<39:32, 19.94s/it]
 94%|█████████▎| 1730/1848 [9:34:36<39:15, 19.96s/it]
                                                     

 94%|█████████▎| 1730/1848 [9:34:36<39:15, 19.96s/it]
 94%|█████████▎| 1731/1848 [9:34:56<38:55, 19.96s/it]
                                                     

 94%|█████████▎| 1731/1848 [9:34:56<38:55, 19.96s/it]
 94%|█████████▎| 1732/1848 [9:35:16<38:35, 19.96s/it]
                                                     

 94%|█████████▎| 1732/1848 [9:35:16<38:35, 19.96s/it]
 94%|█████████▍| 1733/1848 [9:35:36<38:13, 19.95s/it]
                                                     

 94%|█████████▍| 1733/1848 [9:35:36<38:13, 19.95s/it]
 94%|█████████▍| 1734/1848 [9:35:56<37:53, 19.94s/it]
                                                     

 94%|█████████▍| 1734/1848 [9:35:56<37:53, 19.94s/it]
 94%|█████████▍| 1735/1848 [9:36:15<37:32, 19.93s/it]
                                                     

 94%|█████████▍| 1735/1848 [9:36:15<37:32, 19.93s/it]
 94%|█████████▍| 1736/1848 [9:36:35<37:12, 19.93s/it]
                                                     

 94%|█████████▍| 1736/1848 [9:36:35<37:12, 19.93s/it]
 94%|█████████▍| 1737/1848 [9:36:55<36:53, 19.94s/it]
                                                     

 94%|█████████▍| 1737/1848 [9:36:55<36:53, 19.94s/it]
 94%|█████████▍| 1738/1848 [9:37:15<36:33, 19.94s/it]
                                                     

 94%|█████████▍| 1738/1848 [9:37:15<36:33, 19.94s/it]
 94%|█████████▍| 1739/1848 [9:37:35<36:16, 19.97s/it]
                                                     

 94%|█████████▍| 1739/1848 [9:37:35<36:16, 19.97s/it]
 94%|█████████▍| 1740/1848 [9:37:55<35:55, 19.96s/it]
                                                     

 94%|█████████▍| 1740/1848 [9:37:55<35:55, 19.96s/it]
 94%|█████████▍| 1741/1848 [9:38:15<35:37, 19.97s/it]
                                                     

 94%|█████████▍| 1741/1848 [9:38:15<35:37, 19.97s/it]
 94%|█████████▍| 1742/1848 [9:38:35<35:12, 19.93s/it]
                                                     

 94%|█████████▍| 1742/1848 [9:38:35<35:12, 19.93s/it]
 94%|█████████▍| 1743/1848 [9:38:55<34:53, 19.94s/it]
                                                     

 94%|█████████▍| 1743/1848 [9:38:55<34:53, 19.94s/it]
 94%|█████████▍| 1744/1848 [9:39:15<34:33, 19.93s/it]
                                                     

 94%|█████████▍| 1744/1848 [9:39:15<34:33, 19.93s/it]
 94%|█████████▍| 1745/1848 [9:39:35<34:15, 19.95s/it]
                                                     

 94%|█████████▍| 1745/1848 [9:39:35<34:15, 19.95s/it]
 94%|█████████▍| 1746/1848 [9:39:55<33:56, 19.97s/it]
                                                     

 94%|█████████▍| 1746/1848 [9:39:55<33:56, 19.97s/it]
 95%|█████████▍| 1747/1848 [9:40:15<33:33, 19.93s/it]
                                                     

 95%|█████████▍| 1747/1848 [9:40:15<33:33, 19.93s/it]
 95%|█████████▍| 1748/1848 [9:40:35<33:13, 19.94s/it]
                                                     

 95%|█████████▍| 1748/1848 [9:40:35<33:13, 19.94s/it]
 95%|█████████▍| 1749/1848 [9:40:55<32:53, 19.93s/it]
                                                     

 95%|█████████▍| 1749/1848 [9:40:55<32:53, 19.93s/it]
 95%|█████████▍| 1750/1848 [9:41:15<32:34, 19.94s/it]
                                                     

 95%|█████████▍| 1750/1848 [9:41:15<32:34, 19.94s/it]
 95%|█████████▍| 1751/1848 [9:41:35<32:13, 19.93s/it]
                                                     

 95%|█████████▍| 1751/1848 [9:41:35<32:13, 19.93s/it]
 95%|█████████▍| 1752/1848 [9:41:55<31:55, 19.96s/it]
                                                     

 95%|█████████▍| 1752/1848 [9:41:55<31:55, 19.96s/it]
 95%|█████████▍| 1753/1848 [9:42:15<31:36, 19.97s/it]
                                                     

 95%|█████████▍| 1753/1848 [9:42:15<31:36, 19.97s/it]
 95%|█████████▍| 1754/1848 [9:42:35<31:17, 19.98s/it]
                                                     

 95%|█████████▍| 1754/1848 [9:42:35<31:17, 19.98s/it]
 95%|█████████▍| 1755/1848 [9:42:54<30:55, 19.95s/it]
                                                     

 95%|█████████▍| 1755/1848 [9:42:54<30:55, 19.95s/it]
 95%|█████████▌| 1756/1848 [9:43:14<30:33, 19.93s/it]
                                                     

 95%|█████████▌| 1756/1848 [9:43:14<30:33, 19.93s/it]
 95%|█████████▌| 1757/1848 [9:43:32<29:15, 19.29s/it]
                                                     

 95%|█████████▌| 1757/1848 [9:43:32<29:15, 19.29s/it]
 95%|█████████▌| 1758/1848 [9:43:52<29:12, 19.47s/it]
                                                     

 95%|█████████▌| 1758/1848 [9:43:52<29:12, 19.47s/it]
 95%|█████████▌| 1759/1848 [9:44:12<29:03, 19.59s/it]
                                                     

 95%|█████████▌| 1759/1848 [9:44:12<29:03, 19.59s/it]
 95%|█████████▌| 1760/1848 [9:44:32<28:53, 19.70s/it]
                                                     

 95%|█████████▌| 1760/1848 [9:44:32<28:53, 19.70s/it]
 95%|█████████▌| 1761/1848 [9:44:52<28:37, 19.75s/it]
                                                     

 95%|█████████▌| 1761/1848 [9:44:52<28:37, 19.75s/it]
 95%|█████████▌| 1762/1848 [9:45:12<28:21, 19.78s/it]
                                                     

 95%|█████████▌| 1762/1848 [9:45:12<28:21, 19.78s/it]
 95%|█████████▌| 1763/1848 [9:45:32<28:06, 19.84s/it]
                                                     

 95%|█████████▌| 1763/1848 [9:45:32<28:06, 19.84s/it]
 95%|█████████▌| 1764/1848 [9:45:51<27:49, 19.88s/it]
                                                     

 95%|█████████▌| 1764/1848 [9:45:51<27:49, 19.88s/it]
 96%|█████████▌| 1765/1848 [9:46:11<27:31, 19.89s/it]
                                                     

 96%|█████████▌| 1765/1848 [9:46:11<27:31, 19.89s/it]
 96%|█████████▌| 1766/1848 [9:46:31<27:12, 19.91s/it]
                                                     

 96%|█████████▌| 1766/1848 [9:46:31<27:12, 19.91s/it]
 96%|█████████▌| 1767/1848 [9:46:51<26:53, 19.92s/it]
                                                     

 96%|█████████▌| 1767/1848 [9:46:51<26:53, 19.92s/it]
 96%|█████████▌| 1768/1848 [9:47:11<26:35, 19.95s/it]
                                                     

 96%|█████████▌| 1768/1848 [9:47:11<26:35, 19.95s/it]
 96%|█████████▌| 1769/1848 [9:47:31<26:15, 19.94s/it]
                                                     

 96%|█████████▌| 1769/1848 [9:47:31<26:15, 19.94s/it]
 96%|█████████▌| 1770/1848 [9:47:51<25:55, 19.95s/it]
                                                     

 96%|█████████▌| 1770/1848 [9:47:51<25:55, 19.95s/it]
 96%|█████████▌| 1771/1848 [9:48:11<25:38, 19.98s/it]
                                                     

 96%|█████████▌| 1771/1848 [9:48:11<25:38, 19.98s/it]
 96%|█████████▌| 1772/1848 [9:48:31<25:19, 20.00s/it]
                                                     

 96%|█████████▌| 1772/1848 [9:48:31<25:19, 20.00s/it]
 96%|█████████▌| 1773/1848 [9:48:51<24:58, 19.98s/it]
                                                     

 96%|█████████▌| 1773/1848 [9:48:51<24:58, 19.98s/it]
 96%|█████████▌| 1774/1848 [9:49:11<24:37, 19.97s/it]
                                                     

 96%|█████████▌| 1774/1848 [9:49:11<24:37, 19.97s/it]
 96%|█████████▌| 1775/1848 [9:49:31<24:18, 19.99s/it]
                                                     

 96%|█████████▌| 1775/1848 [9:49:31<24:18, 19.99s/it]
 96%|█████████▌| 1776/1848 [9:49:51<23:57, 19.96s/it]
                                                     

 96%|█████████▌| 1776/1848 [9:49:51<23:57, 19.96s/it]
 96%|█████████▌| 1777/1848 [9:50:11<23:39, 19.99s/it]
                                                     

 96%|█████████▌| 1777/1848 [9:50:11<23:39, 19.99s/it]
 96%|█████████▌| 1778/1848 [9:50:31<23:17, 19.97s/it]
                                                     

 96%|█████████▌| 1778/1848 [9:50:31<23:17, 19.97s/it]
 96%|█████████▋| 1779/1848 [9:50:51<22:56, 19.95s/it]
                                                     

 96%|█████████▋| 1779/1848 [9:50:51<22:56, 19.95s/it]
 96%|█████████▋| 1780/1848 [9:51:11<22:35, 19.93s/it]
                                                     

 96%|█████████▋| 1780/1848 [9:51:11<22:35, 19.93s/it]
 96%|█████████▋| 1781/1848 [9:51:31<22:15, 19.94s/it]
                                                     

 96%|█████████▋| 1781/1848 [9:51:31<22:15, 19.94s/it]
 96%|█████████▋| 1782/1848 [9:51:51<21:56, 19.94s/it]
                                                     

 96%|█████████▋| 1782/1848 [9:51:51<21:56, 19.94s/it]
 96%|█████████▋| 1783/1848 [9:52:11<21:37, 19.97s/it]
                                                     

 96%|█████████▋| 1783/1848 [9:52:11<21:37, 19.97s/it]
 97%|█████████▋| 1784/1848 [9:52:31<21:16, 19.95s/it]
                                                     

 97%|█████████▋| 1784/1848 [9:52:31<21:16, 19.95s/it]
 97%|█████████▋| 1785/1848 [9:52:51<20:56, 19.95s/it]
                                                     

 97%|█████████▋| 1785/1848 [9:52:51<20:56, 19.95s/it]
 97%|█████████▋| 1786/1848 [9:53:11<20:37, 19.95s/it]
                                                     

 97%|█████████▋| 1786/1848 [9:53:11<20:37, 19.95s/it]
 97%|█████████▋| 1787/1848 [9:53:31<20:17, 19.96s/it]
                                                     

 97%|█████████▋| 1787/1848 [9:53:31<20:17, 19.96s/it]
 97%|█████████▋| 1788/1848 [9:53:51<19:56, 19.94s/it]
                                                     

 97%|█████████▋| 1788/1848 [9:53:51<19:56, 19.94s/it]
 97%|█████████▋| 1789/1848 [9:54:10<19:37, 19.96s/it]
                                                     

 97%|█████████▋| 1789/1848 [9:54:11<19:37, 19.96s/it]
 97%|█████████▋| 1790/1848 [9:54:30<19:17, 19.96s/it]
                                                     

 97%|█████████▋| 1790/1848 [9:54:30<19:17, 19.96s/it]
 97%|█████████▋| 1791/1848 [9:54:50<18:57, 19.95s/it]
                                                     

 97%|█████████▋| 1791/1848 [9:54:50<18:57, 19.95s/it]
 97%|█████████▋| 1792/1848 [9:55:10<18:37, 19.96s/it]
                                                     

 97%|��████████▋| 1792/1848 [9:55:10<18:37, 19.96s/it]
 97%|█████████▋| 1793/1848 [9:55:30<18:17, 19.96s/it]
                                                     

 97%|█████████▋| 1793/1848 [9:55:30<18:17, 19.96s/it]
 97%|█████████▋| 1794/1848 [9:55:50<17:57, 19.95s/it]
                                                     

 97%|█████████▋| 1794/1848 [9:55:50<17:57, 19.95s/it]
 97%|█████████▋| 1795/1848 [9:56:10<17:36, 19.94s/it]
                                                     

 97%|█████████▋| 1795/1848 [9:56:10<17:36, 19.94s/it]
 97%|█████████▋| 1796/1848 [9:56:30<17:16, 19.94s/it]
                                                     

 97%|█████████▋| 1796/1848 [9:56:30<17:16, 19.94s/it]
 97%|█████████▋| 1797/1848 [9:56:50<16:56, 19.92s/it]
                                                     

 97%|█████████▋| 1797/1848 [9:56:50<16:56, 19.92s/it]
 97%|█████████▋| 1798/1848 [9:57:10<16:35, 19.92s/it]
                                                     

 97%|█████████▋| 1798/1848 [9:57:10<16:35, 19.92s/it]
 97%|█████████▋| 1799/1848 [9:57:30<16:16, 19.93s/it]
                                                     

 97%|█████████▋| 1799/1848 [9:57:30<16:16, 19.93s/it]
 97%|█████████▋| 1800/1848 [9:57:50<15:57, 19.94s/it]
                                                     

 97%|█████████▋| 1800/1848 [9:57:50<15:57, 19.94s/it]
 97%|█████████▋| 1801/1848 [9:58:11<15:51, 20.24s/it]
                                                     

 97%|█████████▋| 1801/1848 [9:58:11<15:51, 20.24s/it]
 98%|█████████▊| 1802/1848 [9:58:31<15:26, 20.15s/it]
                                                     

 98%|█████████▊| 1802/1848 [9:58:31<15:26, 20.15s/it]
 98%|█████████▊| 1803/1848 [9:58:51<15:04, 20.11s/it]
                                                     

 98%|█████████▊| 1803/1848 [9:58:51<15:04, 20.11s/it]
 98%|█████████▊| 1804/1848 [9:59:11<14:43, 20.08s/it]
                                                     

 98%|█████████▊| 1804/1848 [9:59:11<14:43, 20.08s/it]
 98%|█████████▊| 1805/1848 [9:59:31<14:21, 20.03s/it]
                                                     

 98%|█████████▊| 1805/1848 [9:59:31<14:21, 20.03s/it]
 98%|█████████▊| 1806/1848 [9:59:51<14:00, 20.02s/it]
                                                     

 98%|█████████▊| 1806/1848 [9:59:51<14:00, 20.02s/it]
 98%|█████████▊| 1807/1848 [10:00:11<13:40, 20.00s/it]
                                                      

 98%|█████████▊| 1807/1848 [10:00:11<13:40, 20.00s/it]
 98%|█████████▊| 1808/1848 [10:00:31<13:19, 19.98s/it]
                                                      

 98%|█████████▊| 1808/1848 [10:00:31<13:19, 19.98s/it]
 98%|█████████▊| 1809/1848 [10:00:50<12:58, 19.96s/it]
                                                      

 98%|█████████▊| 1809/1848 [10:00:50<12:58, 19.96s/it]
 98%|█████████▊| 1810/1848 [10:01:10<12:39, 19.98s/it]
                                                      

 98%|█████████▊| 1810/1848 [10:01:10<12:39, 19.98s/it]
 98%|█████████▊| 1811/1848 [10:01:30<12:17, 19.94s/it]
                                                      

 98%|█████████▊| 1811/1848 [10:01:30<12:17, 19.94s/it]
 98%|█████████▊| 1812/1848 [10:01:50<11:58, 19.95s/it]
                                                      

 98%|█████████▊| 1812/1848 [10:01:50<11:58, 19.95s/it]
 98%|█████████▊| 1813/1848 [10:02:10<11:37, 19.93s/it]
                                                      
{'loss': 1.3322, 'learning_rate': 1.1368506493506495e-06, 'epoch': 2.76}
+{'loss': 1.4347, 'learning_rate': 1.1292207792207792e-06, 'epoch': 2.76}
+{'loss': 1.2322, 'learning_rate': 1.121590909090909e-06, 'epoch': 2.76}
+{'loss': 1.2541, 'learning_rate': 1.113961038961039e-06, 'epoch': 2.76}
+{'loss': 1.1976, 'learning_rate': 1.1063311688311687e-06, 'epoch': 2.76}
+{'loss': 1.354, 'learning_rate': 1.0987012987012988e-06, 'epoch': 2.77}
+{'loss': 0.9581, 'learning_rate': 1.0910714285714287e-06, 'epoch': 2.77}
+{'loss': 1.3277, 'learning_rate': 1.0834415584415583e-06, 'epoch': 2.77}
+{'loss': 1.2349, 'learning_rate': 1.0758116883116884e-06, 'epoch': 2.77}
+{'loss': 1.1987, 'learning_rate': 1.0681818181818183e-06, 'epoch': 2.77}
+{'loss': 1.1831, 'learning_rate': 1.0605519480519481e-06, 'epoch': 2.77}
+{'loss': 1.3668, 'learning_rate': 1.052922077922078e-06, 'epoch': 2.78}
+{'loss': 1.1844, 'learning_rate': 1.0452922077922079e-06, 'epoch': 2.78}
+{'loss': 1.4333, 'learning_rate': 1.0376623376623377e-06, 'epoch': 2.78}
+{'loss': 1.1757, 'learning_rate': 1.0300324675324676e-06, 'epoch': 2.78}
+{'loss': 1.1565, 'learning_rate': 1.0224025974025975e-06, 'epoch': 2.78}
+{'loss': 1.171, 'learning_rate': 1.0147727272727273e-06, 'epoch': 2.78}
+{'loss': 1.2552, 'learning_rate': 1.0071428571428572e-06, 'epoch': 2.79}
+{'loss': 1.2108, 'learning_rate': 9.99512987012987e-07, 'epoch': 2.79}
+{'loss': 1.3327, 'learning_rate': 9.91883116883117e-07, 'epoch': 2.79}
+{'loss': 1.217, 'learning_rate': 9.842532467532468e-07, 'epoch': 2.79}
+{'loss': 1.1045, 'learning_rate': 9.766233766233766e-07, 'epoch': 2.79}
+{'loss': 1.2356, 'learning_rate': 9.689935064935065e-07, 'epoch': 2.79}
+{'loss': 1.3212, 'learning_rate': 9.613636363636364e-07, 'epoch': 2.8}
+{'loss': 1.2106, 'learning_rate': 9.537337662337662e-07, 'epoch': 2.8}
+{'loss': 1.2333, 'learning_rate': 9.461038961038962e-07, 'epoch': 2.8}
+{'loss': 1.2607, 'learning_rate': 9.38474025974026e-07, 'epoch': 2.8}
+{'loss': 1.2777, 'learning_rate': 9.308441558441558e-07, 'epoch': 2.8}
+{'loss': 1.3449, 'learning_rate': 9.232142857142858e-07, 'epoch': 2.8}
+{'loss': 1.1772, 'learning_rate': 9.155844155844155e-07, 'epoch': 2.81}
+{'loss': 1.2164, 'learning_rate': 9.079545454545455e-07, 'epoch': 2.81}
+{'loss': 1.2933, 'learning_rate': 9.003246753246754e-07, 'epoch': 2.81}
+{'loss': 1.2996, 'learning_rate': 8.926948051948051e-07, 'epoch': 2.81}
+{'loss': 1.1414, 'learning_rate': 8.850649350649351e-07, 'epoch': 2.81}
+{'loss': 1.1852, 'learning_rate': 8.77435064935065e-07, 'epoch': 2.81}
+{'loss': 1.1453, 'learning_rate': 8.698051948051948e-07, 'epoch': 2.81}
+{'loss': 1.1343, 'learning_rate': 8.621753246753247e-07, 'epoch': 2.82}
+{'loss': 1.3304, 'learning_rate': 8.545454545454546e-07, 'epoch': 2.82}
+{'loss': 1.4085, 'learning_rate': 8.469155844155844e-07, 'epoch': 2.82}
+{'loss': 1.1237, 'learning_rate': 8.392857142857143e-07, 'epoch': 2.82}
+{'loss': 1.2302, 'learning_rate': 8.316558441558443e-07, 'epoch': 2.82}
+{'loss': 1.151, 'learning_rate': 8.24025974025974e-07, 'epoch': 2.82}
+{'loss': 1.084, 'learning_rate': 8.16396103896104e-07, 'epoch': 2.83}
+{'loss': 1.4384, 'learning_rate': 8.087662337662338e-07, 'epoch': 2.83}
+{'loss': 1.1691, 'learning_rate': 8.011363636363636e-07, 'epoch': 2.83}
+{'loss': 1.1954, 'learning_rate': 7.935064935064936e-07, 'epoch': 2.83}
+{'loss': 1.1842, 'learning_rate': 7.858766233766234e-07, 'epoch': 2.83}
+{'loss': 1.1795, 'learning_rate': 7.782467532467532e-07, 'epoch': 2.83}
+{'loss': 1.1578, 'learning_rate': 7.706168831168832e-07, 'epoch': 2.84}
+{'loss': 1.036, 'learning_rate': 7.62987012987013e-07, 'epoch': 2.84}
+{'loss': 1.2931, 'learning_rate': 7.553571428571429e-07, 'epoch': 2.84}
+{'loss': 1.2247, 'learning_rate': 7.477272727272727e-07, 'epoch': 2.84}
+{'loss': 1.2419, 'learning_rate': 7.400974025974026e-07, 'epoch': 2.84}
+{'loss': 1.4095, 'learning_rate': 7.324675324675326e-07, 'epoch': 2.84}
+{'loss': 1.2385, 'learning_rate': 7.248376623376623e-07, 'epoch': 2.85}
+{'loss': 1.2256, 'learning_rate': 7.172077922077922e-07, 'epoch': 2.85}
+{'loss': 1.366, 'learning_rate': 7.095779220779222e-07, 'epoch': 2.85}
+{'loss': 1.212, 'learning_rate': 7.019480519480519e-07, 'epoch': 2.85}
+{'loss': 1.4153, 'learning_rate': 6.943181818181818e-07, 'epoch': 2.85}
+{'loss': 1.1577, 'learning_rate': 6.866883116883118e-07, 'epoch': 2.85}
+{'loss': 1.3719, 'learning_rate': 6.790584415584416e-07, 'epoch': 2.86}
+{'loss': 1.2042, 'learning_rate': 6.714285714285714e-07, 'epoch': 2.86}
+{'loss': 1.2464, 'learning_rate': 6.637987012987014e-07, 'epoch': 2.86}
+{'loss': 1.2126, 'learning_rate': 6.561688311688312e-07, 'epoch': 2.86}
+{'loss': 1.0319, 'learning_rate': 6.48538961038961e-07, 'epoch': 2.86}
+{'loss': 1.2647, 'learning_rate': 6.409090909090909e-07, 'epoch': 2.86}
+{'loss': 1.2014, 'learning_rate': 6.332792207792208e-07, 'epoch': 2.87}
+{'loss': 1.1851, 'learning_rate': 6.256493506493507e-07, 'epoch': 2.87}
+{'loss': 1.3253, 'learning_rate': 6.180194805194805e-07, 'epoch': 2.87}
+{'loss': 1.4361, 'learning_rate': 6.103896103896104e-07, 'epoch': 2.87}
+{'loss': 1.2092, 'learning_rate': 6.027597402597404e-07, 'epoch': 2.87}
+{'loss': 1.159, 'learning_rate': 5.951298701298701e-07, 'epoch': 2.87}
+{'loss': 1.0212, 'learning_rate': 5.875e-07, 'epoch': 2.88}
+{'loss': 1.2371, 'learning_rate': 5.7987012987013e-07, 'epoch': 2.88}
+{'loss': 1.2735, 'learning_rate': 5.722402597402597e-07, 'epoch': 2.88}
+{'loss': 1.2361, 'learning_rate': 5.646103896103896e-07, 'epoch': 2.88}
+{'loss': 1.3102, 'learning_rate': 5.569805194805195e-07, 'epoch': 2.88}
+{'loss': 1.3141, 'learning_rate': 5.493506493506494e-07, 'epoch': 2.88}
+{'loss': 1.1948, 'learning_rate': 5.417207792207792e-07, 'epoch': 2.88}
+{'loss': 1.3191, 'learning_rate': 5.340909090909091e-07, 'epoch': 2.89}
+{'loss': 1.1343, 'learning_rate': 5.26461038961039e-07, 'epoch': 2.89}
+{'loss': 1.1865, 'learning_rate': 5.188311688311689e-07, 'epoch': 2.89}
+{'loss': 1.157, 'learning_rate': 5.112012987012987e-07, 'epoch': 2.89}
+{'loss': 1.1386, 'learning_rate': 5.035714285714286e-07, 'epoch': 2.89}
+{'loss': 1.1271, 'learning_rate': 4.959415584415585e-07, 'epoch': 2.89}
+{'loss': 1.1566, 'learning_rate': 4.883116883116883e-07, 'epoch': 2.9}
+{'loss': 1.0934, 'learning_rate': 4.806818181818182e-07, 'epoch': 2.9}
+{'loss': 1.091, 'learning_rate': 4.730519480519481e-07, 'epoch': 2.9}
+{'loss': 1.4174, 'learning_rate': 4.654220779220779e-07, 'epoch': 2.9}
+{'loss': 1.6776, 'learning_rate': 4.5779220779220777e-07, 'epoch': 2.9}
+{'loss': 1.5345, 'learning_rate': 4.501623376623377e-07, 'epoch': 2.9}
+{'loss': 1.308, 'learning_rate': 4.4253246753246755e-07, 'epoch': 2.91}
+{'loss': 1.3174, 'learning_rate': 4.349025974025974e-07, 'epoch': 2.91}
+{'loss': 1.2974, 'learning_rate': 4.272727272727273e-07, 'epoch': 2.91}
+{'loss': 1.1429, 'learning_rate': 4.1964285714285714e-07, 'epoch': 2.91}
+{'loss': 1.3925, 'learning_rate': 4.12012987012987e-07, 'epoch': 2.91}
+{'loss': 1.1584, 'learning_rate': 4.043831168831169e-07, 'epoch': 2.91}
+{'loss': 1.423, 'learning_rate': 3.967532467532468e-07, 'epoch': 2.92}
+{'loss': 1.149, 'learning_rate': 3.891233766233766e-07, 'epoch': 2.92}
+{'loss': 1.169, 'learning_rate': 3.814935064935065e-07, 'epoch': 2.92}
+{'loss': 1.1767, 'learning_rate': 3.738636363636364e-07, 'epoch': 2.92}
+{'loss': 1.2685, 'learning_rate': 3.662337662337663e-07, 'epoch': 2.92}
+{'loss': 1.1508, 'learning_rate': 3.586038961038961e-07, 'epoch': 2.92}
+{'loss': 1.114, 'learning_rate': 3.5097402597402596e-07, 'epoch': 2.93}
+{'loss': 1.3372, 'learning_rate': 3.433441558441559e-07, 'epoch': 2.93}
+{'loss': 1.0877, 'learning_rate': 3.357142857142857e-07, 'epoch': 2.93}
+{'loss': 1.2651, 'learning_rate': 3.280844155844156e-07, 'epoch': 2.93}
+{'loss': 1.1993, 'learning_rate': 3.2045454545454547e-07, 'epoch': 2.93}
+{'loss': 1.1073, 'learning_rate': 3.1282467532467533e-07, 'epoch': 2.93}
+{'loss': 1.3659, 'learning_rate': 3.051948051948052e-07, 'epoch': 2.94}
+{'loss': 1.0769, 'learning_rate': 2.9756493506493506e-07, 'epoch': 2.94}
+{'loss': 1.0804, 'learning_rate': 2.89935064935065e-07, 'epoch': 2.94}
+{'loss': 1.3615, 'learning_rate': 2.823051948051948e-07, 'epoch': 2.94}
+{'loss': 1.1453, 'learning_rate': 2.746753246753247e-07, 'epoch': 2.94}
+
 98%|█████████▊| 1813/1848 [10:02:10<11:37, 19.93s/it]
 98%|█████████▊| 1814/1848 [10:02:30<11:16, 19.91s/it]
                                                      

 98%|█████████▊| 1814/1848 [10:02:30<11:16, 19.91s/it]
 98%|█████████▊| 1815/1848 [10:02:50<10:56, 19.90s/it]
                                                      

 98%|█████████▊| 1815/1848 [10:02:50<10:56, 19.90s/it]
 98%|█████████▊| 1816/1848 [10:03:10<10:38, 19.94s/it]
                                                      

 98%|█████████▊| 1816/1848 [10:03:10<10:38, 19.94s/it]
 98%|█████████▊| 1817/1848 [10:03:30<10:17, 19.92s/it]
                                                      

 98%|█████████▊| 1817/1848 [10:03:30<10:17, 19.92s/it]
 98%|█████████▊| 1818/1848 [10:03:50<09:57, 19.93s/it]
                                                      

 98%|█████████▊| 1818/1848 [10:03:50<09:57, 19.93s/it]
 98%|█████████▊| 1819/1848 [10:04:10<09:38, 19.94s/it]
                                                      

 98%|█████████▊| 1819/1848 [10:04:10<09:38, 19.94s/it]
 98%|█████████▊| 1820/1848 [10:04:30<09:18, 19.94s/it]
                                                      

 98%|█████████▊| 1820/1848 [10:04:30<09:18, 19.94s/it]
 99%|█████████▊| 1821/1848 [10:04:50<08:58, 19.94s/it]
                                                      

 99%|█████████▊| 1821/1848 [10:04:50<08:58, 19.94s/it]
 99%|█████████▊| 1822/1848 [10:05:10<08:38, 19.93s/it]
                                                      

 99%|█████████▊| 1822/1848 [10:05:10<08:38, 19.93s/it]
 99%|█████████▊| 1823/1848 [10:05:29<08:17, 19.91s/it]
                                                      

 99%|█████████▊| 1823/1848 [10:05:29<08:17, 19.91s/it]
 99%|█████████▊| 1824/1848 [10:05:49<07:58, 19.92s/it]
                                                      

 99%|█████████▊| 1824/1848 [10:05:49<07:58, 19.92s/it]
 99%|█████████▉| 1825/1848 [10:06:09<07:38, 19.92s/it]
                                                      

 99%|█████████▉| 1825/1848 [10:06:09<07:38, 19.92s/it]
 99%|█████████▉| 1826/1848 [10:06:29<07:18, 19.93s/it]
                                                      

 99%|█████████▉| 1826/1848 [10:06:29<07:18, 19.93s/it]
 99%|█████████▉| 1827/1848 [10:06:49<06:58, 19.93s/it]
                                                      

 99%|█████████▉| 1827/1848 [10:06:49<06:58, 19.93s/it]
 99%|█████████▉| 1828/1848 [10:07:09<06:38, 19.93s/it]
                                                      

 99%|█████████▉| 1828/1848 [10:07:09<06:38, 19.93s/it]
 99%|█████████▉| 1829/1848 [10:07:29<06:18, 19.95s/it]
                                                      

 99%|█████████▉| 1829/1848 [10:07:29<06:18, 19.95s/it]
 99%|█████████▉| 1830/1848 [10:07:49<05:58, 19.93s/it]
                                                      

 99%|█████████▉| 1830/1848 [10:07:49<05:58, 19.93s/it]
 99%|█████████▉| 1831/1848 [10:08:09<05:38, 19.90s/it]
                                                      

 99%|█████████▉| 1831/1848 [10:08:09<05:38, 19.90s/it]
 99%|█████████▉| 1832/1848 [10:08:29<05:18, 19.92s/it]
                                                      

 99%|█████████▉| 1832/1848 [10:08:29<05:18, 19.92s/it]
 99%|█████████▉| 1833/1848 [10:08:49<04:58, 19.91s/it]
                                                      

 99%|█████████▉| 1833/1848 [10:08:49<04:58, 19.91s/it]
 99%|█████████▉| 1834/1848 [10:09:09<04:38, 19.90s/it]
                                                      

 99%|█████████▉| 1834/1848 [10:09:09<04:38, 19.90s/it]
 99%|█████████▉| 1835/1848 [10:09:28<04:18, 19.89s/it]
                                                      

 99%|█████████▉| 1835/1848 [10:09:28<04:18, 19.89s/it]
 99%|█████████▉| 1836/1848 [10:09:48<03:58, 19.88s/it]
                                                      

 99%|█████████▉| 1836/1848 [10:09:48<03:58, 19.88s/it]
 99%|█████████▉| 1837/1848 [10:10:08<03:38, 19.90s/it]
                                                      

 99%|█████████▉| 1837/1848 [10:10:08<03:38, 19.90s/it]
 99%|█████████▉| 1838/1848 [10:10:28<03:18, 19.89s/it]
                                                      

 99%|█████████▉| 1838/1848 [10:10:28<03:18, 19.89s/it]
100%|█████████▉| 1839/1848 [10:10:48<02:58, 19.87s/it]
                                                      

100%|█████████▉| 1839/1848 [10:10:48<02:58, 19.87s/it]
100%|█████████▉| 1840/1848 [10:11:08<02:38, 19.87s/it]
                                                      

100%|█████████▉| 1840/1848 [10:11:08<02:38, 19.87s/it]
100%|█████████▉| 1841/1848 [10:11:28<02:19, 19.87s/it]
                                                      

100%|█████████▉| 1841/1848 [10:11:28<02:19, 19.87s/it]
100%|█████████▉| 1842/1848 [10:11:47<01:59, 19.86s/it]
                                                      

100%|█████████▉| 1842/1848 [10:11:47<01:59, 19.86s/it]
100%|█████████▉| 1843/1848 [10:12:07<01:39, 19.88s/it]
                                                      

100%|█████████▉| 1843/1848 [10:12:07<01:39, 19.88s/it]
100%|█████████▉| 1844/1848 [10:12:27<01:19, 19.89s/it]
                                                      

100%|█████████▉| 1844/1848 [10:12:27<01:19, 19.89s/it]
100%|█████████▉| 1845/1848 [10:12:47<00:59, 19.87s/it]
                                                      

100%|█████████▉| 1845/1848 [10:12:47<00:59, 19.87s/it]
100%|█████████▉| 1846/1848 [10:13:07<00:39, 19.87s/it]
                                                      

100%|█████████▉| 1846/1848 [10:13:07<00:39, 19.87s/it]
100%|█████████▉| 1847/1848 [10:13:27<00:19, 19.87s/it]
                                                      

100%|█████████▉| 1847/1848 [10:13:27<00:19, 19.87s/it]
100%|██████████| 1848/1848 [10:13:35<00:00, 16.25s/it]
                                                      

100%|██████████| 1848/1848 [10:13:35<00:00, 16.25s/it]
                                                      

100%|██████████| 1848/1848 [10:13:35<00:00, 16.25s/it]
100%|██████████| 1848/1848 [10:13:35<00:00, 19.92s/it]
+{'loss': 1.2589, 'learning_rate': 2.6704545454545457e-07, 'epoch': 2.94}
+{'loss': 1.1165, 'learning_rate': 2.5941558441558443e-07, 'epoch': 2.94}
+{'loss': 1.3162, 'learning_rate': 2.517857142857143e-07, 'epoch': 2.95}
+{'loss': 0.984, 'learning_rate': 2.4415584415584416e-07, 'epoch': 2.95}
+{'loss': 1.2467, 'learning_rate': 2.3652597402597405e-07, 'epoch': 2.95}
+{'loss': 1.2537, 'learning_rate': 2.2889610389610389e-07, 'epoch': 2.95}
+{'loss': 1.2593, 'learning_rate': 2.2126623376623378e-07, 'epoch': 2.95}
+{'loss': 1.2277, 'learning_rate': 2.1363636363636364e-07, 'epoch': 2.95}
+{'loss': 1.1536, 'learning_rate': 2.060064935064935e-07, 'epoch': 2.96}
+{'loss': 1.2452, 'learning_rate': 1.983766233766234e-07, 'epoch': 2.96}
+{'loss': 1.1635, 'learning_rate': 1.9074675324675326e-07, 'epoch': 2.96}
+{'loss': 1.3754, 'learning_rate': 1.8311688311688315e-07, 'epoch': 2.96}
+{'loss': 1.3265, 'learning_rate': 1.7548701298701298e-07, 'epoch': 2.96}
+{'loss': 1.2604, 'learning_rate': 1.6785714285714285e-07, 'epoch': 2.96}
+{'loss': 1.0593, 'learning_rate': 1.6022727272727274e-07, 'epoch': 2.97}
+{'loss': 1.2107, 'learning_rate': 1.525974025974026e-07, 'epoch': 2.97}
+{'loss': 1.2971, 'learning_rate': 1.449675324675325e-07, 'epoch': 2.97}
+{'loss': 1.102, 'learning_rate': 1.3733766233766235e-07, 'epoch': 2.97}
+{'loss': 1.2374, 'learning_rate': 1.2970779220779222e-07, 'epoch': 2.97}
+{'loss': 1.1801, 'learning_rate': 1.2207792207792208e-07, 'epoch': 2.97}
+{'loss': 1.1599, 'learning_rate': 1.1444805194805194e-07, 'epoch': 2.98}
+{'loss': 1.0671, 'learning_rate': 1.0681818181818182e-07, 'epoch': 2.98}
+{'loss': 1.1637, 'learning_rate': 9.91883116883117e-08, 'epoch': 2.98}
+{'loss': 1.226, 'learning_rate': 9.155844155844157e-08, 'epoch': 2.98}
+{'loss': 1.0673, 'learning_rate': 8.392857142857142e-08, 'epoch': 2.98}
+{'loss': 1.1571, 'learning_rate': 7.62987012987013e-08, 'epoch': 2.98}
+{'loss': 1.2029, 'learning_rate': 6.866883116883118e-08, 'epoch': 2.99}
+{'loss': 1.1848, 'learning_rate': 6.103896103896104e-08, 'epoch': 2.99}
+{'loss': 1.3635, 'learning_rate': 5.340909090909091e-08, 'epoch': 2.99}
+{'loss': 1.2953, 'learning_rate': 4.5779220779220786e-08, 'epoch': 2.99}
+{'loss': 1.1682, 'learning_rate': 3.814935064935065e-08, 'epoch': 2.99}
+{'loss': 1.2329, 'learning_rate': 3.051948051948052e-08, 'epoch': 2.99}
+{'loss': 1.5078, 'learning_rate': 2.2889610389610393e-08, 'epoch': 3.0}
+{'loss': 1.2804, 'learning_rate': 1.525974025974026e-08, 'epoch': 3.0}
+{'loss': 1.0954, 'learning_rate': 7.62987012987013e-09, 'epoch': 3.0}
+{'loss': 1.1847, 'learning_rate': 0.0, 'epoch': 3.0}
+{'train_runtime': 36815.2039, 'train_samples_per_second': 0.802, 'train_steps_per_second': 0.05, 'train_loss': 1.253900460028029, 'epoch': 3.0}