Using the `WANDB_DISABLED` environment variable is deprecated and will be removed in v5. Use the --report_to flag to control the integrations used for logging result (for instance --report_to none). 0%| | 0/3 [00:00> loading configuration file /home/yujiepan/bert-base-uncased-imdb/config.json [INFO|configuration_utils.py:720] 2023-07-03 01:07:03,672 >> Model config BertConfig { "_name_or_path": "/home/yujiepan/bert-base-uncased-imdb", "architectures": [ "BertForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": 0, "1": 1 }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "0": 0, "1": 1 }, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 0, "position_embedding_type": "absolute", "problem_type": "single_label_classification", "torch_dtype": "float32", "transformers_version": "4.27.4", "type_vocab_size": 2, "use_cache": true, "vocab_size": 30522 } [INFO|tokenization_utils_base.py:1800] 2023-07-03 01:07:03,674 >> loading file vocab.txt [INFO|tokenization_utils_base.py:1800] 2023-07-03 01:07:03,674 >> loading file tokenizer.json [INFO|tokenization_utils_base.py:1800] 2023-07-03 01:07:03,674 >> loading file added_tokens.json [INFO|tokenization_utils_base.py:1800] 2023-07-03 01:07:03,674 >> loading file special_tokens_map.json [INFO|tokenization_utils_base.py:1800] 2023-07-03 01:07:03,674 >> loading file tokenizer_config.json [INFO|modeling_utils.py:2400] 2023-07-03 01:07:03,725 >> loading weights file /home/yujiepan/bert-base-uncased-imdb/pytorch_model.bin [INFO|modeling_utils.py:3034] 2023-07-03 01:07:04,944 >> All model checkpoint weights were used when initializing BertForSequenceClassification. [INFO|modeling_utils.py:3042] 2023-07-03 01:07:04,944 >> All the weights of BertForSequenceClassification were initialized from the model checkpoint at /home/yujiepan/bert-base-uncased-imdb. If your task is similar to the task the model of the checkpoint was trained on, you can already use BertForSequenceClassification for predictions without further training. Running tokenizer on dataset: 0%| | 0/25000 [00:00> Using cuda_amp half precision backend [INFO|trainer.py:738] 2023-07-03 01:07:36,915 >> The following columns in the training set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: text. If text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [INFO|trainer.py:1741] 2023-07-03 01:07:36,919 >> ***** Running training ***** [INFO|trainer.py:1742] 2023-07-03 01:07:36,919 >> Num examples = 25000 [INFO|trainer.py:1743] 2023-07-03 01:07:36,919 >> Num Epochs = 6 [INFO|trainer.py:1744] 2023-07-03 01:07:36,919 >> Instantaneous batch size per device = 32 [INFO|trainer.py:1745] 2023-07-03 01:07:36,919 >> Total train batch size (w. parallel, distributed & accumulation) = 32 [INFO|trainer.py:1746] 2023-07-03 01:07:36,919 >> Gradient Accumulation steps = 1 [INFO|trainer.py:1747] 2023-07-03 01:07:36,919 >> Total optimization steps = 4692 [INFO|trainer.py:1748] 2023-07-03 01:07:36,920 >> Number of trainable parameters = 109483778 0%| | 0/4692 [00:00> You're using a BertTokenizerFast 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. 0%| | 1/4692 [00:01<1:19:02, 1.01s/it] 0%| | 2/4692 [00:01<44:38, 1.75it/s] 0%| | 3/4692 [00:01<34:03, 2.30it/s] 0%| | 4/4692 [00:01<30:28, 2.56it/s] 0%| | 5/4692 [00:02<27:33, 2.83it/s] 0%| | 6/4692 [00:02<25:13, 3.10it/s] 0%| | 7/4692 [00:02<23:54, 3.27it/s] 0%| | 8/4692 [00:02<22:54, 3.41it/s] 0%| | 9/4692 [00:03<22:18, 3.50it/s] 0%| | 10/4692 [00:03<21:43, 3.59it/s] 0%| | 11/4692 [00:03<21:34, 3.61it/s] 0%| | 12/4692 [00:04<21:26, 3.64it/s] 0%| | 13/4692 [00:04<21:17, 3.66it/s] 0%| | 14/4692 [00:04<21:13, 3.67it/s] 0%| | 15/4692 [00:04<21:08, 3.69it/s] 0%| | 16/4692 [00:05<21:01, 3.71it/s] 0%| | 17/4692 [00:05<21:00, 3.71it/s] 0%| | 18/4692 [00:05<20:58, 3.71it/s] 0%| | 19/4692 [00:05<21:02, 3.70it/s] 0%| | 20/4692 [00:06<21:00, 3.71it/s] 0%| | 21/4692 [00:06<20:59, 3.71it/s] 0%| | 22/4692 [00:06<20:59, 3.71it/s] 0%| | 23/4692 [00:06<20:59, 3.71it/s] 1%| | 24/4692 [00:07<20:55, 3.72it/s] 1%| | 25/4692 [00:07<20:46, 3.75it/s] 1%| | 26/4692 [00:07<20:40, 3.76it/s] 1%| | 27/4692 [00:08<20:44, 3.75it/s] 1%| | 28/4692 [00:08<20:47, 3.74it/s] 1%| | 29/4692 [00:08<20:50, 3.73it/s] 1%| | 30/4692 [00:08<20:44, 3.75it/s] 1%| | 31/4692 [00:09<20:45, 3.74it/s] 1%| | 32/4692 [00:09<20:47, 3.74it/s] 1%| | 33/4692 [00:09<20:43, 3.75it/s] 1%| | 34/4692 [00:09<20:41, 3.75it/s] 1%| | 35/4692 [00:10<20:37, 3.76it/s] 1%| | 36/4692 [00:10<20:40, 3.75it/s] 1%| | 37/4692 [00:10<20:43, 3.74it/s] 1%| | 38/4692 [00:10<20:40, 3.75it/s] 1%| | 39/4692 [00:11<20:37, 3.76it/s] 1%| | 40/4692 [00:11<20:39, 3.75it/s] 1%| | 41/4692 [00:11<20:38, 3.75it/s] 1%| | 42/4692 [00:12<20:41, 3.75it/s] 1%| | 43/4692 [00:12<20:39, 3.75it/s] 1%| | 44/4692 [00:12<20:34, 3.76it/s] 1%| | 45/4692 [00:12<20:37, 3.76it/s] 1%| | 46/4692 [00:13<20:37, 3.75it/s] 1%| | 47/4692 [00:13<20:38, 3.75it/s] 1%| | 48/4692 [00:13<20:37, 3.75it/s] 1%| | 49/4692 [00:13<20:39, 3.74it/s] 1%| | 50/4692 [00:14<20:38, 3.75it/s] 1%| | 51/4692 [00:14<20:39, 3.74it/s] 1%| | 52/4692 [00:14<20:38, 3.75it/s] 1%| | 53/4692 [00:14<20:33, 3.76it/s] 1%| | 54/4692 [00:15<20:29, 3.77it/s] 1%| | 55/4692 [00:15<20:26, 3.78it/s] 1%| | 56/4692 [00:15<20:26, 3.78it/s] 1%| | 57/4692 [00:16<20:31, 3.77it/s] 1%| | 58/4692 [00:16<20:28, 3.77it/s] 1%|▏ | 59/4692 [00:16<20:26, 3.78it/s] 1%|▏ | 60/4692 [00:16<20:24, 3.78it/s] 1%|▏ | 61/4692 [00:17<20:24, 3.78it/s] 1%|▏ | 62/4692 [00:17<20:24, 3.78it/s] 1%|▏ | 63/4692 [00:17<20:26, 3.77it/s] 1%|▏ | 64/4692 [00:17<20:25, 3.78it/s] 1%|▏ | 65/4692 [00:18<20:32, 3.75it/s] 1%|▏ | 66/4692 [00:18<20:29, 3.76it/s] 1%|▏ | 67/4692 [00:18<20:26, 3.77it/s] 1%|▏ | 68/4692 [00:18<20:27, 3.77it/s] 1%|▏ | 69/4692 [00:19<20:26, 3.77it/s] 1%|▏ | 70/4692 [00:19<20:29, 3.76it/s] 2%|▏ | 71/4692 [00:19<20:29, 3.76it/s] 2%|▏ | 72/4692 [00:20<20:27, 3.76it/s] 2%|▏ | 73/4692 [00:20<20:26, 3.77it/s] 2%|▏ | 74/4692 [00:20<20:29, 3.75it/s] 2%|▏ | 75/4692 [00:20<20:26, 3.76it/s] 2%|▏ | 76/4692 [00:21<20:26, 3.76it/s] 2%|▏ | 77/4692 [00:21<20:23, 3.77it/s] 2%|▏ | 78/4692 [00:21<20:29, 3.75it/s] 2%|▏ | 79/4692 [00:21<20:29, 3.75it/s] 2%|▏ | 80/4692 [00:22<20:25, 3.76it/s] 2%|▏ | 81/4692 [00:22<20:21, 3.78it/s] 2%|▏ | 82/4692 [00:22<20:18, 3.78it/s] 2%|▏ | 83/4692 [00:22<20:21, 3.77it/s] 2%|▏ | 84/4692 [00:23<20:24, 3.76it/s] 2%|▏ | 85/4692 [00:23<20:28, 3.75it/s] 2%|▏ | 86/4692 [00:23<20:29, 3.75it/s] 2%|▏ | 87/4692 [00:24<20:25, 3.76it/s] 2%|▏ | 88/4692 [00:24<20:21, 3.77it/s] 2%|▏ | 89/4692 [00:24<20:19, 3.77it/s] 2%|▏ | 90/4692 [00:24<20:20, 3.77it/s] 2%|▏ | 91/4692 [00:25<20:20, 3.77it/s] 2%|▏ | 92/4692 [00:25<20:20, 3.77it/s] 2%|▏ | 93/4692 [00:25<20:16, 3.78it/s] 2%|▏ | 94/4692 [00:25<20:15, 3.78it/s] 2%|▏ | 95/4692 [00:26<20:22, 3.76it/s] 2%|▏ | 96/4692 [00:26<20:22, 3.76it/s] 2%|▏ | 97/4692 [00:26<20:17, 3.77it/s] 2%|▏ | 98/4692 [00:26<20:21, 3.76it/s] 2%|▏ | 99/4692 [00:27<20:18, 3.77it/s] 2%|▏ | 100/4692 [00:27<20:17, 3.77it/s] 2%|▏ | 101/4692 [00:27<20:13, 3.78it/s] 2%|▏ | 102/4692 [00:27<20:16, 3.77it/s] 2%|▏ | 103/4692 [00:28<20:22, 3.75it/s] 2%|▏ | 104/4692 [00:28<20:25, 3.74it/s] 2%|▏ | 105/4692 [00:28<20:24, 3.75it/s] 2%|▏ | 106/4692 [00:29<20:23, 3.75it/s] 2%|▏ | 107/4692 [00:29<20:24, 3.74it/s] 2%|▏ | 108/4692 [00:29<20:21, 3.75it/s] 2%|▏ | 109/4692 [00:29<20:18, 3.76it/s] 2%|▏ | 110/4692 [00:30<20:22, 3.75it/s] 2%|▏ | 111/4692 [00:30<20:23, 3.75it/s] 2%|▏ | 112/4692 [00:30<20:20, 3.75it/s] 2%|▏ | 113/4692 [00:30<20:17, 3.76it/s] 2%|▏ | 114/4692 [00:31<20:17, 3.76it/s] 2%|▏ | 115/4692 [00:31<20:15, 3.77it/s] 2%|▏ | 116/4692 [00:31<20:12, 3.78it/s] 2%|▏ | 117/4692 [00:31<20:12, 3.77it/s] 3%|▎ | 118/4692 [00:32<20:19, 3.75it/s] 3%|▎ | 119/4692 [00:32<20:22, 3.74it/s] 3%|▎ | 120/4692 [00:32<20:19, 3.75it/s] 3%|▎ | 121/4692 [00:33<20:15, 3.76it/s] 3%|▎ | 122/4692 [00:33<20:13, 3.76it/s] 3%|▎ | 123/4692 [00:33<20:13, 3.77it/s] 3%|▎ | 124/4692 [00:33<20:10, 3.77it/s] 3%|▎ | 125/4692 [00:34<20:08, 3.78it/s] 3%|▎ | 126/4692 [00:34<20:07, 3.78it/s] 3%|▎ | 127/4692 [00:34<20:06, 3.79it/s] 3%|▎ | 128/4692 [00:34<20:12, 3.77it/s] 3%|▎ | 129/4692 [00:35<20:17, 3.75it/s] 3%|▎ | 130/4692 [00:35<20:22, 3.73it/s] 3%|▎ | 131/4692 [00:35<20:21, 3.73it/s] 3%|▎ | 132/4692 [00:35<20:19, 3.74it/s] 3%|▎ | 133/4692 [00:36<20:15, 3.75it/s] 3%|▎ | 134/4692 [00:36<20:12, 3.76it/s] 3%|▎ | 135/4692 [00:36<20:08, 3.77it/s] 3%|▎ | 136/4692 [00:37<20:05, 3.78it/s] 3%|▎ | 137/4692 [00:37<20:04, 3.78it/s] 3%|▎ | 138/4692 [00:37<20:12, 3.76it/s] 3%|▎ | 139/4692 [00:37<20:23, 3.72it/s] 3%|▎ | 140/4692 [00:38<20:32, 3.69it/s] 3%|▎ | 141/4692 [00:38<20:40, 3.67it/s] 3%|▎ | 142/4692 [00:38<20:48, 3.64it/s] 3%|▎ | 143/4692 [00:38<20:53, 3.63it/s] 3%|▎ | 144/4692 [00:39<21:00, 3.61it/s] 3%|▎ | 145/4692 [00:39<21:01, 3.60it/s] 3%|▎ | 146/4692 [00:39<21:02, 3.60it/s] 3%|▎ | 147/4692 [00:40<21:01, 3.60it/s] 3%|▎ | 148/4692 [00:40<21:07, 3.59it/s] 3%|▎ | 149/4692 [00:40<21:08, 3.58it/s] 3%|▎ | 150/4692 [00:40<21:14, 3.56it/s] 3%|▎ | 151/4692 [00:41<21:10, 3.57it/s] 3%|▎ | 152/4692 [00:41<21:11, 3.57it/s] 3%|▎ | 153/4692 [00:41<21:15, 3.56it/s] 3%|▎ | 154/4692 [00:42<21:21, 3.54it/s] 3%|▎ | 155/4692 [00:42<21:18, 3.55it/s] 3%|▎ | 156/4692 [00:42<21:13, 3.56it/s] 3%|▎ | 157/4692 [00:42<21:09, 3.57it/s] 3%|▎ | 158/4692 [00:43<21:08, 3.57it/s] 3%|▎ | 159/4692 [00:43<21:09, 3.57it/s] 3%|▎ | 160/4692 [00:43<20:49, 3.63it/s] 3%|▎ | 161/4692 [00:43<20:31, 3.68it/s] 3%|▎ | 162/4692 [00:44<20:42, 3.65it/s] 3%|▎ | 163/4692 [00:44<20:47, 3.63it/s] 3%|▎ | 164/4692 [00:44<20:52, 3.61it/s] 4%|▎ | 165/4692 [00:45<20:55, 3.61it/s] 4%|▎ | 166/4692 [00:45<20:58, 3.60it/s] 4%|▎ | 167/4692 [00:45<20:58, 3.60it/s] 4%|▎ | 168/4692 [00:45<20:56, 3.60it/s] 4%|▎ | 169/4692 [00:46<21:02, 3.58it/s] 4%|▎ | 170/4692 [00:46<21:02, 3.58it/s] 4%|▎ | 171/4692 [00:46<21:00, 3.59it/s] 4%|▎ | 172/4692 [00:47<20:55, 3.60it/s] 4%|▎ | 173/4692 [00:47<20:57, 3.59it/s] 4%|▎ | 174/4692 [00:47<21:01, 3.58it/s] 4%|▎ | 175/4692 [00:47<21:01, 3.58it/s] 4%|▍ | 176/4692 [00:48<21:00, 3.58it/s] 4%|▍ | 177/4692 [00:48<21:00, 3.58it/s] 4%|▍ | 178/4692 [00:48<20:56, 3.59it/s] 4%|▍ | 179/4692 [00:48<20:52, 3.60it/s] 4%|▍ | 180/4692 [00:49<20:50, 3.61it/s] 4%|▍ | 181/4692 [00:49<20:53, 3.60it/s] 4%|▍ | 182/4692 [00:49<20:59, 3.58it/s] 4%|▍ | 183/4692 [00:50<20:56, 3.59it/s] 4%|▍ | 184/4692 [00:50<21:03, 3.57it/s] 4%|▍ | 185/4692 [00:50<21:02, 3.57it/s] 4%|▍ | 186/4692 [00:50<21:01, 3.57it/s] 4%|▍ | 187/4692 [00:51<21:02, 3.57it/s] 4%|▍ | 188/4692 [00:51<20:57, 3.58it/s] 4%|▍ | 189/4692 [00:51<20:54, 3.59it/s] 4%|▍ | 190/4692 [00:52<20:55, 3.59it/s] 4%|▍ | 191/4692 [00:52<20:58, 3.58it/s] 4%|▍ | 192/4692 [00:52<20:58, 3.58it/s] 4%|▍ | 193/4692 [00:52<20:59, 3.57it/s] 4%|▍ | 194/4692 [00:53<21:00, 3.57it/s] 4%|▍ | 195/4692 [00:53<21:00, 3.57it/s] 4%|▍ | 196/4692 [00:53<21:02, 3.56it/s] 4%|▍ | 197/4692 [00:54<21:03, 3.56it/s] 4%|▍ | 198/4692 [00:54<21:02, 3.56it/s] 4%|▍ | 199/4692 [00:54<21:03, 3.56it/s] 4%|▍ | 200/4692 [00:54<20:58, 3.57it/s] 4%|▍ | 201/4692 [00:55<20:52, 3.58it/s] 4%|▍ | 202/4692 [00:55<20:57, 3.57it/s] 4%|▍ | 203/4692 [00:55<20:57, 3.57it/s] 4%|▍ | 204/4692 [00:55<20:57, 3.57it/s] 4%|▍ | 205/4692 [00:56<20:55, 3.58it/s] 4%|▍ | 206/4692 [00:56<20:53, 3.58it/s] 4%|▍ | 207/4692 [00:56<20:56, 3.57it/s] 4%|▍ | 208/4692 [00:57<20:53, 3.58it/s] 4%|▍ | 209/4692 [00:57<20:52, 3.58it/s] 4%|▍ | 210/4692 [00:57<20:49, 3.59it/s] 4%|▍ | 211/4692 [00:57<20:48, 3.59it/s] 5%|▍ | 212/4692 [00:58<20:53, 3.57it/s] 5%|▍ | 213/4692 [00:58<20:53, 3.57it/s] 5%|▍ | 214/4692 [00:58<20:59, 3.56it/s] 5%|▍ | 215/4692 [00:59<20:55, 3.57it/s] 5%|▍ | 216/4692 [00:59<20:51, 3.58it/s] 5%|▍ | 217/4692 [00:59<20:52, 3.57it/s] 5%|▍ | 218/4692 [00:59<20:51, 3.58it/s] 5%|▍ | 219/4692 [01:00<20:50, 3.58it/s] 5%|▍ | 220/4692 [01:00<20:50, 3.58it/s] 5%|▍ | 221/4692 [01:00<20:51, 3.57it/s] 5%|▍ | 222/4692 [01:01<20:48, 3.58it/s] 5%|▍ | 223/4692 [01:01<20:45, 3.59it/s] 5%|▍ | 224/4692 [01:01<20:48, 3.58it/s] 5%|▍ | 225/4692 [01:01<20:48, 3.58it/s] 5%|▍ | 226/4692 [01:02<20:48, 3.58it/s] 5%|▍ | 227/4692 [01:02<20:52, 3.57it/s] 5%|▍ | 228/4692 [01:02<20:51, 3.57it/s] 5%|▍ | 229/4692 [01:02<20:46, 3.58it/s] 5%|▍ | 230/4692 [01:03<20:42, 3.59it/s] 5%|▍ | 231/4692 [01:03<20:42, 3.59it/s] 5%|▍ | 232/4692 [01:03<20:39, 3.60it/s] 5%|▍ | 233/4692 [01:04<20:37, 3.60it/s] 5%|▍ | 234/4692 [01:04<20:40, 3.59it/s] 5%|▌ | 235/4692 [01:04<20:44, 3.58it/s] 5%|▌ | 236/4692 [01:04<20:42, 3.59it/s] 5%|▌ | 237/4692 [01:05<20:41, 3.59it/s] 5%|▌ | 238/4692 [01:05<20:45, 3.58it/s] 5%|▌ | 239/4692 [01:05<20:43, 3.58it/s] 5%|▌ | 240/4692 [01:06<20:43, 3.58it/s] 5%|▌ | 241/4692 [01:06<20:47, 3.57it/s] 5%|▌ | 242/4692 [01:06<20:43, 3.58it/s] 5%|▌ | 243/4692 [01:06<20:41, 3.58it/s] 5%|▌ | 244/4692 [01:07<20:37, 3.59it/s] 5%|▌ | 245/4692 [01:07<20:38, 3.59it/s] 5%|▌ | 246/4692 [01:07<20:17, 3.65it/s] 5%|▌ | 247/4692 [01:07<20:22, 3.64it/s] 5%|▌ | 248/4692 [01:08<20:29, 3.61it/s] 5%|▌ | 249/4692 [01:08<20:35, 3.60it/s] 5%|▌ | 250/4692 [01:08<20:34, 3.60it/s] 5%|▌ | 251/4692 [01:09<20:37, 3.59it/s] 5%|▌ | 252/4692 [01:09<20:40, 3.58it/s] 5%|▌ | 253/4692 [01:09<20:43, 3.57it/s] 5%|▌ | 254/4692 [01:09<20:47, 3.56it/s] 5%|▌ | 255/4692 [01:10<20:44, 3.57it/s] 5%|▌ | 256/4692 [01:10<20:49, 3.55it/s] 5%|▌ | 257/4692 [01:10<20:47, 3.55it/s] 5%|▌ | 258/4692 [01:11<20:49, 3.55it/s] 6%|▌ | 259/4692 [01:11<20:43, 3.57it/s] 6%|▌ | 260/4692 [01:11<20:40, 3.57it/s] 6%|▌ | 261/4692 [01:11<20:42, 3.57it/s] 6%|▌ | 262/4692 [01:12<20:40, 3.57it/s] 6%|▌ | 263/4692 [01:12<20:37, 3.58it/s] 6%|▌ | 264/4692 [01:12<20:34, 3.59it/s] 6%|▌ | 265/4692 [01:13<20:39, 3.57it/s] 6%|▌ | 266/4692 [01:13<20:37, 3.58it/s] 6%|▌ | 267/4692 [01:13<20:39, 3.57it/s] 6%|▌ | 268/4692 [01:13<20:37, 3.57it/s] 6%|▌ | 269/4692 [01:14<20:41, 3.56it/s] 6%|▌ | 270/4692 [01:14<20:35, 3.58it/s] 6%|▌ | 271/4692 [01:14<20:35, 3.58it/s] 6%|▌ | 272/4692 [01:14<20:33, 3.58it/s] 6%|▌ | 273/4692 [01:15<20:37, 3.57it/s] 6%|▌ | 274/4692 [01:15<20:40, 3.56it/s] 6%|▌ | 275/4692 [01:15<20:41, 3.56it/s] 6%|▌ | 276/4692 [01:16<20:37, 3.57it/s] 6%|▌ | 277/4692 [01:16<20:37, 3.57it/s] 6%|▌ | 278/4692 [01:16<20:38, 3.56it/s] 6%|▌ | 279/4692 [01:16<20:37, 3.57it/s] 6%|▌ | 280/4692 [01:17<20:36, 3.57it/s] 6%|▌ | 281/4692 [01:17<20:35, 3.57it/s] 6%|▌ | 282/4692 [01:17<20:33, 3.58it/s] 6%|▌ | 283/4692 [01:18<20:35, 3.57it/s] 6%|▌ | 284/4692 [01:18<20:34, 3.57it/s] 6%|▌ | 285/4692 [01:18<20:30, 3.58it/s] 6%|▌ | 286/4692 [01:18<20:30, 3.58it/s] 6%|▌ | 287/4692 [01:19<20:27, 3.59it/s] 6%|▌ | 288/4692 [01:19<20:29, 3.58it/s] 6%|▌ | 289/4692 [01:19<20:32, 3.57it/s] 6%|▌ | 290/4692 [01:20<20:32, 3.57it/s] 6%|▌ | 291/4692 [01:20<20:32, 3.57it/s] 6%|▌ | 292/4692 [01:20<20:36, 3.56it/s] 6%|▌ | 293/4692 [01:20<20:34, 3.56it/s] 6%|▋ | 294/4692 [01:21<20:34, 3.56it/s] 6%|▋ | 295/4692 [01:21<20:30, 3.57it/s] 6%|▋ | 296/4692 [01:21<20:31, 3.57it/s] 6%|▋ | 297/4692 [01:21<20:31, 3.57it/s] 6%|▋ | 298/4692 [01:22<20:30, 3.57it/s] 6%|▋ | 299/4692 [01:22<20:29, 3.57it/s] 6%|▋ | 300/4692 [01:22<20:28, 3.58it/s] 6%|▋ | 301/4692 [01:23<20:29, 3.57it/s] 6%|▋ | 302/4692 [01:23<20:29, 3.57it/s] 6%|▋ | 303/4692 [01:23<20:28, 3.57it/s] 6%|▋ | 304/4692 [01:23<20:28, 3.57it/s] 7%|▋ | 305/4692 [01:24<20:29, 3.57it/s] 7%|▋ | 306/4692 [01:24<20:28, 3.57it/s] 7%|▋ | 307/4692 [01:24<20:24, 3.58it/s] 7%|▋ | 308/4692 [01:25<20:21, 3.59it/s] 7%|▋ | 309/4692 [01:25<20:22, 3.59it/s] 7%|▋ | 310/4692 [01:25<20:21, 3.59it/s] 7%|▋ | 311/4692 [01:25<20:27, 3.57it/s] 7%|▋ | 312/4692 [01:26<20:28, 3.57it/s] 7%|▋ | 313/4692 [01:26<20:28, 3.56it/s] 7%|▋ | 314/4692 [01:26<20:24, 3.58it/s] 7%|▋ | 315/4692 [01:27<20:23, 3.58it/s] 7%|▋ | 316/4692 [01:27<20:21, 3.58it/s] 7%|▋ | 317/4692 [01:27<20:21, 3.58it/s] 7%|▋ | 318/4692 [01:27<20:26, 3.57it/s] 7%|▋ | 319/4692 [01:28<20:29, 3.56it/s] 7%|▋ | 320/4692 [01:28<20:27, 3.56it/s] 7%|▋ | 321/4692 [01:28<20:25, 3.57it/s] 7%|▋ | 322/4692 [01:28<20:26, 3.56it/s] 7%|▋ | 323/4692 [01:29<20:27, 3.56it/s] 7%|▋ | 324/4692 [01:29<20:28, 3.55it/s] 7%|▋ | 325/4692 [01:29<20:30, 3.55it/s] 7%|▋ | 326/4692 [01:30<20:27, 3.56it/s] 7%|▋ | 327/4692 [01:30<20:25, 3.56it/s] 7%|▋ | 328/4692 [01:30<20:25, 3.56it/s] 7%|▋ | 329/4692 [01:30<20:23, 3.57it/s] 7%|▋ | 330/4692 [01:31<20:24, 3.56it/s] 7%|▋ | 331/4692 [01:31<20:20, 3.57it/s] 7%|▋ | 332/4692 [01:31<20:16, 3.58it/s] 7%|▋ | 333/4692 [01:32<20:16, 3.58it/s] 7%|▋ | 334/4692 [01:32<20:16, 3.58it/s] 7%|▋ | 335/4692 [01:32<20:18, 3.58it/s] 7%|▋ | 336/4692 [01:32<20:16, 3.58it/s] 7%|▋ | 337/4692 [01:33<20:14, 3.59it/s] 7%|▋ | 338/4692 [01:33<20:18, 3.57it/s] 7%|▋ | 339/4692 [01:33<20:16, 3.58it/s] 7%|▋ | 340/4692 [01:34<20:17, 3.57it/s] 7%|▋ | 341/4692 [01:34<20:21, 3.56it/s] 7%|▋ | 342/4692 [01:34<20:19, 3.57it/s] 7%|▋ | 343/4692 [01:34<20:18, 3.57it/s] 7%|▋ | 344/4692 [01:35<20:18, 3.57it/s] 7%|▋ | 345/4692 [01:35<20:21, 3.56it/s] 7%|▋ | 346/4692 [01:35<20:18, 3.57it/s] 7%|▋ | 347/4692 [01:35<20:16, 3.57it/s] 7%|▋ | 348/4692 [01:36<20:14, 3.58it/s] 7%|▋ | 349/4692 [01:36<20:13, 3.58it/s] 7%|▋ | 350/4692 [01:36<20:11, 3.58it/s] 7%|▋ | 351/4692 [01:37<20:11, 3.58it/s] 8%|▊ | 352/4692 [01:37<20:08, 3.59it/s] 8%|▊ | 353/4692 [01:37<20:08, 3.59it/s] 8%|▊ | 354/4692 [01:37<20:07, 3.59it/s] 8%|▊ | 355/4692 [01:38<20:07, 3.59it/s] 8%|▊ | 356/4692 [01:38<20:16, 3.56it/s] 8%|▊ | 357/4692 [01:38<20:13, 3.57it/s] 8%|▊ | 358/4692 [01:39<20:15, 3.57it/s] 8%|▊ | 359/4692 [01:39<20:15, 3.56it/s] 8%|▊ | 360/4692 [01:39<20:17, 3.56it/s] 8%|▊ | 361/4692 [01:39<20:14, 3.56it/s] 8%|▊ | 362/4692 [01:40<20:15, 3.56it/s] 8%|▊ | 363/4692 [01:40<20:10, 3.58it/s] 8%|▊ | 364/4692 [01:40<20:08, 3.58it/s] 8%|▊ | 365/4692 [01:41<20:13, 3.57it/s] 8%|▊ | 366/4692 [01:41<20:12, 3.57it/s] 8%|▊ | 367/4692 [01:41<20:12, 3.57it/s] 8%|▊ | 368/4692 [01:41<20:17, 3.55it/s] 8%|▊ | 369/4692 [01:42<20:17, 3.55it/s] 8%|▊ | 370/4692 [01:42<20:11, 3.57it/s] 8%|▊ | 371/4692 [01:42<20:09, 3.57it/s] 8%|▊ | 372/4692 [01:42<20:08, 3.57it/s] 8%|▊ | 373/4692 [01:43<20:05, 3.58it/s] 8%|▊ | 374/4692 [01:43<20:01, 3.59it/s] 8%|▊ | 375/4692 [01:43<20:01, 3.59it/s] 8%|▊ | 376/4692 [01:44<20:00, 3.60it/s] 8%|▊ | 377/4692 [01:44<20:01, 3.59it/s] 8%|▊ | 378/4692 [01:44<19:59, 3.60it/s] 8%|▊ | 379/4692 [01:44<20:01, 3.59it/s] 8%|▊ | 380/4692 [01:45<20:02, 3.59it/s] 8%|▊ | 381/4692 [01:45<20:01, 3.59it/s] 8%|▊ | 382/4692 [01:45<20:01, 3.59it/s] 8%|▊ | 383/4692 [01:46<20:02, 3.58it/s] 8%|▊ | 384/4692 [01:46<20:01, 3.58it/s] 8%|▊ | 385/4692 [01:46<20:03, 3.58it/s] 8%|▊ | 386/4692 [01:46<20:02, 3.58it/s] 8%|▊ | 387/4692 [01:47<20:00, 3.59it/s] 8%|▊ | 388/4692 [01:47<20:01, 3.58it/s] 8%|▊ | 389/4692 [01:47<20:01, 3.58it/s] 8%|▊ | 390/4692 [01:47<19:57, 3.59it/s] 8%|▊ | 391/4692 [01:48<19:55, 3.60it/s][INFO|trainer.py:738] 2023-07-03 01:09:25,195 >> The following columns in the evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: text. If text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3069] 2023-07-03 01:09:25,198 >> ***** Running Evaluation ***** [INFO|trainer.py:3071] 2023-07-03 01:09:25,198 >> Num examples = 25000 [INFO|trainer.py:3074] 2023-07-03 01:09:25,198 >> Batch size = 64 0%| | 0/391 [00:00> Saving model checkpoint to /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-391 [INFO|configuration_utils.py:457] 2023-07-03 01:10:30,680 >> Configuration saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-391/config.json [INFO|modeling_utils.py:1762] 2023-07-03 01:10:31,297 >> Model weights saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-391/pytorch_model.bin [INFO|tokenization_utils_base.py:2163] 2023-07-03 01:10:31,298 >> tokenizer config file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-391/tokenizer_config.json [INFO|tokenization_utils_base.py:2170] 2023-07-03 01:10:31,298 >> Special tokens file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-391/special_tokens_map.json 8%|▊ | 392/4692 [02:55<24:25:59, 20.46s/it] 8%|▊ | 393/4692 [02:56<17:11:53, 14.40s/it] 8%|▊ | 394/4692 [02:56<12:08:11, 10.17s/it] 8%|▊ | 395/4692 [02:56<8:35:37, 7.20s/it] 8%|▊ | 396/4692 [02:56<6:06:54, 5.12s/it] 8%|▊ | 397/4692 [02:57<4:22:50, 3.67s/it] 8%|▊ | 398/4692 [02:57<3:10:02, 2.66s/it] 9%|▊ | 399/4692 [02:57<2:19:04, 1.94s/it] 9%|▊ | 400/4692 [02:58<1:43:20, 1.44s/it] 9%|▊ | 401/4692 [02:58<1:18:15, 1.09s/it] 9%|▊ | 402/4692 [02:58<1:00:46, 1.18it/s] 9%|▊ | 403/4692 [02:58<48:33, 1.47it/s] 9%|▊ | 404/4692 [02:59<39:56, 1.79it/s] 9%|▊ | 405/4692 [02:59<33:55, 2.11it/s] 9%|▊ | 406/4692 [02:59<29:40, 2.41it/s] 9%|▊ | 407/4692 [03:00<26:46, 2.67it/s] 9%|▊ | 408/4692 [03:00<24:42, 2.89it/s] 9%|▊ | 409/4692 [03:00<23:17, 3.07it/s] 9%|▊ | 410/4692 [03:00<22:16, 3.20it/s] 9%|▉ | 411/4692 [03:01<21:32, 3.31it/s] 9%|▉ | 412/4692 [03:01<21:03, 3.39it/s] 9%|▉ | 413/4692 [03:01<20:47, 3.43it/s] 9%|▉ | 414/4692 [03:01<20:18, 3.51it/s] 9%|▉ | 415/4692 [03:02<19:50, 3.59it/s] 9%|▉ | 416/4692 [03:02<19:28, 3.66it/s] 9%|▉ | 417/4692 [03:02<19:15, 3.70it/s] 9%|▉ | 418/4692 [03:03<19:11, 3.71it/s] 9%|▉ | 419/4692 [03:03<19:03, 3.74it/s] 9%|▉ | 420/4692 [03:03<18:56, 3.76it/s] 9%|▉ | 421/4692 [03:03<18:51, 3.77it/s] 9%|▉ | 422/4692 [03:04<18:48, 3.78it/s] 9%|▉ | 423/4692 [03:04<18:48, 3.78it/s] 9%|▉ | 424/4692 [03:04<18:47, 3.78it/s] 9%|▉ | 425/4692 [03:04<18:46, 3.79it/s] 9%|▉ | 426/4692 [03:05<18:49, 3.78it/s] 9%|▉ | 427/4692 [03:05<18:46, 3.79it/s] 9%|▉ | 428/4692 [03:05<18:44, 3.79it/s] 9%|▉ | 429/4692 [03:05<18:47, 3.78it/s] 9%|▉ | 430/4692 [03:06<18:44, 3.79it/s] 9%|▉ | 431/4692 [03:06<18:43, 3.79it/s] 9%|▉ | 432/4692 [03:06<18:43, 3.79it/s] 9%|▉ | 433/4692 [03:06<18:44, 3.79it/s] 9%|▉ | 434/4692 [03:07<18:42, 3.79it/s] 9%|▉ | 435/4692 [03:07<18:42, 3.79it/s] 9%|▉ | 436/4692 [03:07<18:40, 3.80it/s] 9%|▉ | 437/4692 [03:08<18:39, 3.80it/s] 9%|▉ | 438/4692 [03:08<18:45, 3.78it/s] 9%|▉ | 439/4692 [03:08<18:42, 3.79it/s] 9%|▉ | 440/4692 [03:08<18:42, 3.79it/s] 9%|▉ | 441/4692 [03:09<18:44, 3.78it/s] 9%|▉ | 442/4692 [03:09<18:39, 3.79it/s] 9%|▉ | 443/4692 [03:09<18:39, 3.79it/s] 9%|▉ | 444/4692 [03:09<18:39, 3.80it/s] 9%|▉ | 445/4692 [03:10<18:43, 3.78it/s] 10%|▉ | 446/4692 [03:10<18:41, 3.78it/s] 10%|▉ | 447/4692 [03:10<18:38, 3.79it/s] 10%|▉ | 448/4692 [03:10<18:35, 3.80it/s] 10%|▉ | 449/4692 [03:11<18:34, 3.81it/s] 10%|▉ | 450/4692 [03:11<18:32, 3.81it/s] 10%|▉ | 451/4692 [03:11<18:36, 3.80it/s] 10%|▉ | 452/4692 [03:11<18:52, 3.74it/s] 10%|▉ | 453/4692 [03:12<18:46, 3.76it/s] 10%|▉ | 454/4692 [03:12<18:40, 3.78it/s] 10%|▉ | 455/4692 [03:12<18:41, 3.78it/s] 10%|▉ | 456/4692 [03:13<18:44, 3.77it/s] 10%|▉ | 457/4692 [03:13<18:40, 3.78it/s] 10%|▉ | 458/4692 [03:13<18:36, 3.79it/s] 10%|▉ | 459/4692 [03:13<18:40, 3.78it/s] 10%|▉ | 460/4692 [03:14<18:36, 3.79it/s] 10%|▉ | 461/4692 [03:14<18:32, 3.80it/s] 10%|▉ | 462/4692 [03:14<18:29, 3.81it/s] 10%|▉ | 463/4692 [03:14<18:31, 3.80it/s] 10%|▉ | 464/4692 [03:15<18:31, 3.80it/s] 10%|▉ | 465/4692 [03:15<18:29, 3.81it/s] 10%|▉ | 466/4692 [03:15<18:30, 3.80it/s] 10%|▉ | 467/4692 [03:15<18:37, 3.78it/s] 10%|▉ | 468/4692 [03:16<18:37, 3.78it/s] 10%|▉ | 469/4692 [03:16<18:33, 3.79it/s] 10%|█ | 470/4692 [03:16<18:32, 3.80it/s] 10%|█ | 471/4692 [03:16<18:35, 3.78it/s] 10%|█ | 472/4692 [03:17<18:34, 3.79it/s] 10%|█ | 473/4692 [03:17<18:35, 3.78it/s] 10%|█ | 474/4692 [03:17<18:33, 3.79it/s] 10%|█ | 475/4692 [03:18<18:33, 3.79it/s] 10%|█ | 476/4692 [03:18<18:30, 3.80it/s] 10%|█ | 477/4692 [03:18<18:26, 3.81it/s] 10%|█ | 478/4692 [03:18<18:27, 3.80it/s] 10%|█ | 479/4692 [03:19<18:28, 3.80it/s] 10%|█ | 480/4692 [03:19<18:27, 3.80it/s] 10%|█ | 481/4692 [03:19<18:26, 3.80it/s] 10%|█ | 482/4692 [03:19<18:25, 3.81it/s] 10%|█ | 483/4692 [03:20<18:24, 3.81it/s] 10%|█ | 484/4692 [03:20<18:23, 3.81it/s] 10%|█ | 485/4692 [03:20<18:26, 3.80it/s] 10%|█ | 486/4692 [03:20<18:30, 3.79it/s] 10%|█ | 487/4692 [03:21<18:29, 3.79it/s] 10%|█ | 488/4692 [03:21<18:24, 3.81it/s] 10%|█ | 489/4692 [03:21<18:23, 3.81it/s] 10%|█ | 490/4692 [03:21<18:31, 3.78it/s] 10%|█ | 491/4692 [03:22<18:27, 3.79it/s] 10%|█ | 492/4692 [03:22<18:29, 3.79it/s] 11%|█ | 493/4692 [03:22<18:30, 3.78it/s] 11%|█ | 494/4692 [03:23<18:28, 3.79it/s] 11%|█ | 495/4692 [03:23<18:24, 3.80it/s] 11%|█ | 496/4692 [03:23<18:24, 3.80it/s] 11%|█ | 497/4692 [03:23<18:24, 3.80it/s] 11%|█ | 498/4692 [03:24<18:21, 3.81it/s] 11%|█ | 499/4692 [03:24<18:19, 3.81it/s] 11%|█ | 500/4692 [03:24<18:26, 3.79it/s] 11%|█ | 500/4692 [03:24<18:26, 3.79it/s] 11%|█ | 501/4692 [03:24<18:33, 3.76it/s] 11%|█ | 502/4692 [03:25<18:29, 3.77it/s] 11%|█ | 503/4692 [03:25<18:27, 3.78it/s] 11%|█ | 504/4692 [03:25<18:25, 3.79it/s] 11%|█ | 505/4692 [03:25<18:29, 3.77it/s] 11%|█ | 506/4692 [03:26<18:29, 3.77it/s] 11%|█ | 507/4692 [03:26<18:25, 3.79it/s] 11%|█ | 508/4692 [03:26<18:23, 3.79it/s] 11%|█ | 509/4692 [03:27<18:25, 3.78it/s] 11%|█ | 510/4692 [03:27<18:24, 3.79it/s] 11%|█ | 511/4692 [03:27<18:20, 3.80it/s] 11%|█ | 512/4692 [03:27<18:21, 3.80it/s] 11%|█ | 513/4692 [03:28<18:24, 3.78it/s] 11%|█ | 514/4692 [03:28<18:21, 3.79it/s] 11%|█ | 515/4692 [03:28<18:16, 3.81it/s] 11%|█ | 516/4692 [03:28<18:19, 3.80it/s] 11%|█ | 517/4692 [03:29<18:19, 3.80it/s] 11%|█ | 518/4692 [03:29<18:18, 3.80it/s] 11%|█ | 519/4692 [03:29<18:14, 3.81it/s] 11%|█ | 520/4692 [03:29<18:17, 3.80it/s] 11%|█ | 521/4692 [03:30<18:16, 3.80it/s] 11%|█ | 522/4692 [03:30<18:14, 3.81it/s] 11%|█ | 523/4692 [03:30<20:30, 3.39it/s] 11%|█ | 524/4692 [03:31<19:49, 3.50it/s] 11%|█ | 525/4692 [03:31<19:19, 3.60it/s] 11%|█ | 526/4692 [03:31<18:57, 3.66it/s] 11%|█ | 527/4692 [03:31<18:46, 3.70it/s] 11%|█▏ | 528/4692 [03:32<18:38, 3.72it/s] 11%|█▏ | 529/4692 [03:32<18:30, 3.75it/s] 11%|█▏ | 530/4692 [03:32<18:22, 3.77it/s] 11%|█▏ | 531/4692 [03:32<18:26, 3.76it/s] 11%|█▏ | 532/4692 [03:33<18:26, 3.76it/s] 11%|█▏ | 533/4692 [03:33<18:21, 3.77it/s] 11%|█▏ | 534/4692 [03:33<18:16, 3.79it/s] 11%|█▏ | 535/4692 [03:33<18:19, 3.78it/s] 11%|█▏ | 536/4692 [03:34<18:22, 3.77it/s] 11%|█▏ | 537/4692 [03:34<18:22, 3.77it/s] 11%|█▏ | 538/4692 [03:34<18:20, 3.77it/s] 11%|█▏ | 539/4692 [03:35<18:16, 3.79it/s] 12%|█▏ | 540/4692 [03:35<18:14, 3.79it/s] 12%|█▏ | 541/4692 [03:35<18:13, 3.80it/s] 12%|█▏ | 542/4692 [03:35<18:11, 3.80it/s] 12%|█▏ | 543/4692 [03:36<18:10, 3.80it/s] 12%|█▏ | 544/4692 [03:36<18:11, 3.80it/s] 12%|█▏ | 545/4692 [03:36<18:12, 3.80it/s] 12%|█▏ | 546/4692 [03:36<18:12, 3.79it/s] 12%|█▏ | 547/4692 [03:37<18:12, 3.80it/s] 12%|█▏ | 548/4692 [03:37<18:10, 3.80it/s] 12%|█▏ | 549/4692 [03:37<18:08, 3.81it/s] 12%|█▏ | 550/4692 [03:37<18:16, 3.78it/s] 12%|█▏ | 551/4692 [03:38<18:13, 3.79it/s] 12%|█▏ | 552/4692 [03:38<18:10, 3.80it/s] 12%|█▏ | 553/4692 [03:38<18:09, 3.80it/s] 12%|█▏ | 554/4692 [03:38<18:14, 3.78it/s] 12%|█▏ | 555/4692 [03:39<18:17, 3.77it/s] 12%|█▏ | 556/4692 [03:39<18:20, 3.76it/s] 12%|█▏ | 557/4692 [03:39<18:15, 3.78it/s] 12%|█▏ | 558/4692 [03:40<18:15, 3.77it/s] 12%|█▏ | 559/4692 [03:40<18:13, 3.78it/s] 12%|█▏ | 560/4692 [03:40<18:10, 3.79it/s] 12%|█▏ | 561/4692 [03:40<18:06, 3.80it/s] 12%|█▏ | 562/4692 [03:41<18:07, 3.80it/s] 12%|█▏ | 563/4692 [03:41<18:07, 3.80it/s] 12%|█▏ | 564/4692 [03:41<18:06, 3.80it/s] 12%|█▏ | 565/4692 [03:41<18:04, 3.81it/s] 12%|█▏ | 566/4692 [03:42<18:03, 3.81it/s] 12%|█▏ | 567/4692 [03:42<18:02, 3.81it/s] 12%|█▏ | 568/4692 [03:42<18:03, 3.81it/s] 12%|█▏ | 569/4692 [03:42<18:04, 3.80it/s] 12%|█▏ | 570/4692 [03:43<18:07, 3.79it/s] 12%|█▏ | 571/4692 [03:43<18:04, 3.80it/s] 12%|█▏ | 572/4692 [03:43<18:00, 3.81it/s] 12%|█▏ | 573/4692 [03:43<18:01, 3.81it/s] 12%|█▏ | 574/4692 [03:44<18:02, 3.80it/s] 12%|█▏ | 575/4692 [03:44<18:00, 3.81it/s] 12%|█▏ | 576/4692 [03:44<17:59, 3.81it/s] 12%|█▏ | 577/4692 [03:45<18:03, 3.80it/s] 12%|█▏ | 578/4692 [03:45<18:05, 3.79it/s] 12%|█▏ | 579/4692 [03:45<18:00, 3.81it/s] 12%|█▏ | 580/4692 [03:45<18:00, 3.81it/s] 12%|█▏ | 581/4692 [03:46<18:06, 3.78it/s] 12%|█▏ | 582/4692 [03:46<18:03, 3.79it/s] 12%|█▏ | 583/4692 [03:46<18:00, 3.80it/s] 12%|█▏ | 584/4692 [03:46<17:59, 3.81it/s] 12%|█▏ | 585/4692 [03:47<17:57, 3.81it/s] 12%|█▏ | 586/4692 [03:47<17:56, 3.81it/s] 13%|█▎ | 587/4692 [03:47<17:58, 3.81it/s] 13%|█▎ | 588/4692 [03:47<18:04, 3.78it/s] 13%|█▎ | 589/4692 [03:48<18:04, 3.78it/s] 13%|█▎ | 590/4692 [03:48<18:02, 3.79it/s] 13%|█▎ | 591/4692 [03:48<17:58, 3.80it/s] 13%|█▎ | 592/4692 [03:48<18:01, 3.79it/s] 13%|█▎ | 593/4692 [03:49<18:06, 3.77it/s] 13%|█▎ | 594/4692 [03:49<18:02, 3.79it/s] 13%|█▎ | 595/4692 [03:49<17:59, 3.79it/s] 13%|█▎ | 596/4692 [03:50<17:57, 3.80it/s] 13%|█▎ | 597/4692 [03:50<18:01, 3.79it/s] 13%|█▎ | 598/4692 [03:50<17:58, 3.79it/s] 13%|█▎ | 599/4692 [03:50<17:59, 3.79it/s] 13%|█▎ | 600/4692 [03:51<18:01, 3.78it/s] 13%|█▎ | 601/4692 [03:51<18:08, 3.76it/s] 13%|█▎ | 602/4692 [03:51<18:12, 3.74it/s] 13%|█▎ | 603/4692 [03:51<18:14, 3.74it/s] 13%|█▎ | 604/4692 [03:52<18:11, 3.74it/s] 13%|█▎ | 605/4692 [03:52<18:07, 3.76it/s] 13%|█▎ | 606/4692 [03:52<18:07, 3.76it/s] 13%|█▎ | 607/4692 [03:52<18:05, 3.76it/s] 13%|█▎ | 608/4692 [03:53<18:05, 3.76it/s] 13%|█▎ | 609/4692 [03:53<18:04, 3.77it/s] 13%|█▎ | 610/4692 [03:53<18:05, 3.76it/s] 13%|█▎ | 611/4692 [03:54<18:03, 3.77it/s] 13%|█▎ | 612/4692 [03:54<18:03, 3.76it/s] 13%|█▎ | 613/4692 [03:54<18:04, 3.76it/s] 13%|█▎ | 614/4692 [03:54<18:02, 3.77it/s] 13%|█▎ | 615/4692 [03:55<18:01, 3.77it/s] 13%|█▎ | 616/4692 [03:55<18:02, 3.77it/s] 13%|█▎ | 617/4692 [03:55<18:00, 3.77it/s] 13%|█▎ | 618/4692 [03:55<17:58, 3.78it/s] 13%|█▎ | 619/4692 [03:56<17:58, 3.78it/s] 13%|█▎ | 620/4692 [03:56<18:00, 3.77it/s] 13%|█▎ | 621/4692 [03:56<17:59, 3.77it/s] 13%|█▎ | 622/4692 [03:56<17:59, 3.77it/s] 13%|█▎ | 623/4692 [03:57<17:58, 3.77it/s] 13%|█▎ | 624/4692 [03:57<17:57, 3.77it/s] 13%|█▎ | 625/4692 [03:57<17:57, 3.77it/s] 13%|█▎ | 626/4692 [03:58<17:55, 3.78it/s] 13%|█▎ | 627/4692 [03:58<17:55, 3.78it/s] 13%|█▎ | 628/4692 [03:58<17:54, 3.78it/s] 13%|█▎ | 629/4692 [03:58<17:59, 3.76it/s] 13%|█▎ | 630/4692 [03:59<18:04, 3.74it/s] 13%|█▎ | 631/4692 [03:59<18:04, 3.74it/s] 13%|█▎ | 632/4692 [03:59<18:02, 3.75it/s] 13%|█▎ | 633/4692 [03:59<18:05, 3.74it/s] 14%|█▎ | 634/4692 [04:00<18:05, 3.74it/s] 14%|█▎ | 635/4692 [04:00<18:01, 3.75it/s] 14%|█▎ | 636/4692 [04:00<18:01, 3.75it/s] 14%|█▎ | 637/4692 [04:00<18:04, 3.74it/s] 14%|█▎ | 638/4692 [04:01<18:03, 3.74it/s] 14%|█▎ | 639/4692 [04:01<18:02, 3.74it/s] 14%|█▎ | 640/4692 [04:01<18:00, 3.75it/s] 14%|█▎ | 641/4692 [04:02<17:58, 3.76it/s] 14%|█▎ | 642/4692 [04:02<17:58, 3.76it/s] 14%|█▎ | 643/4692 [04:02<18:06, 3.73it/s] 14%|█▎ | 644/4692 [04:02<18:02, 3.74it/s] 14%|█▎ | 645/4692 [04:03<18:00, 3.75it/s] 14%|█▍ | 646/4692 [04:03<17:58, 3.75it/s] 14%|█▍ | 647/4692 [04:03<17:58, 3.75it/s] 14%|█▍ | 648/4692 [04:03<18:00, 3.74it/s] 14%|█▍ | 649/4692 [04:04<18:02, 3.74it/s] 14%|█▍ | 650/4692 [04:04<18:00, 3.74it/s] 14%|█▍ | 651/4692 [04:04<18:02, 3.73it/s] 14%|█▍ | 652/4692 [04:04<18:00, 3.74it/s] 14%|█▍ | 653/4692 [04:05<17:57, 3.75it/s] 14%|█▍ | 654/4692 [04:05<17:57, 3.75it/s] 14%|█▍ | 655/4692 [04:05<17:57, 3.75it/s] 14%|█▍ | 656/4692 [04:06<17:56, 3.75it/s] 14%|█▍ | 657/4692 [04:06<17:55, 3.75it/s] 14%|█▍ | 658/4692 [04:06<17:54, 3.75it/s] 14%|█▍ | 659/4692 [04:06<17:55, 3.75it/s] 14%|█▍ | 660/4692 [04:07<17:55, 3.75it/s] 14%|█▍ | 661/4692 [04:07<17:52, 3.76it/s] 14%|█▍ | 662/4692 [04:07<17:51, 3.76it/s] 14%|█▍ | 663/4692 [04:07<17:52, 3.76it/s] 14%|█▍ | 664/4692 [04:08<17:52, 3.75it/s] 14%|█▍ | 665/4692 [04:08<17:51, 3.76it/s] 14%|█▍ | 666/4692 [04:08<17:53, 3.75it/s] 14%|█▍ | 667/4692 [04:08<17:52, 3.75it/s] 14%|█▍ | 668/4692 [04:09<17:55, 3.74it/s] 14%|█▍ | 669/4692 [04:09<17:56, 3.74it/s] 14%|█▍ | 670/4692 [04:09<17:54, 3.74it/s] 14%|█▍ | 671/4692 [04:10<17:55, 3.74it/s] 14%|█▍ | 672/4692 [04:10<17:54, 3.74it/s] 14%|█▍ | 673/4692 [04:10<17:53, 3.74it/s] 14%|█▍ | 674/4692 [04:10<17:49, 3.76it/s] 14%|█▍ | 675/4692 [04:11<17:48, 3.76it/s] 14%|█▍ | 676/4692 [04:11<17:48, 3.76it/s] 14%|█▍ | 677/4692 [04:11<17:46, 3.76it/s] 14%|█▍ | 678/4692 [04:11<17:47, 3.76it/s] 14%|█▍ | 679/4692 [04:12<17:46, 3.76it/s] 14%|█▍ | 680/4692 [04:12<17:55, 3.73it/s] 15%|█▍ | 681/4692 [04:12<17:52, 3.74it/s] 15%|█▍ | 682/4692 [04:12<17:49, 3.75it/s] 15%|█▍ | 683/4692 [04:13<17:48, 3.75it/s] 15%|█▍ | 684/4692 [04:13<17:46, 3.76it/s] 15%|█▍ | 685/4692 [04:13<17:44, 3.76it/s] 15%|█▍ | 686/4692 [04:14<17:46, 3.76it/s] 15%|█▍ | 687/4692 [04:14<17:47, 3.75it/s] 15%|█▍ | 688/4692 [04:14<17:47, 3.75it/s] 15%|█▍ | 689/4692 [04:14<17:45, 3.76it/s] 15%|█▍ | 690/4692 [04:15<17:42, 3.77it/s] 15%|█▍ | 691/4692 [04:15<17:42, 3.77it/s] 15%|█▍ | 692/4692 [04:15<17:44, 3.76it/s] 15%|█▍ | 693/4692 [04:15<17:44, 3.76it/s] 15%|█▍ | 694/4692 [04:16<17:44, 3.76it/s] 15%|█▍ | 695/4692 [04:16<17:45, 3.75it/s] 15%|█▍ | 696/4692 [04:16<17:46, 3.75it/s] 15%|█▍ | 697/4692 [04:16<17:46, 3.74it/s] 15%|█▍ | 698/4692 [04:17<17:44, 3.75it/s] 15%|█▍ | 699/4692 [04:17<17:40, 3.76it/s] 15%|█▍ | 700/4692 [04:17<17:41, 3.76it/s] 15%|█▍ | 701/4692 [04:18<17:45, 3.75it/s] 15%|█▍ | 702/4692 [04:18<17:45, 3.74it/s] 15%|█▍ | 703/4692 [04:18<17:46, 3.74it/s] 15%|█▌ | 704/4692 [04:18<17:45, 3.74it/s] 15%|█▌ | 705/4692 [04:19<17:43, 3.75it/s] 15%|█▌ | 706/4692 [04:19<17:43, 3.75it/s] 15%|█▌ | 707/4692 [04:19<17:42, 3.75it/s] 15%|█▌ | 708/4692 [04:19<17:45, 3.74it/s] 15%|█▌ | 709/4692 [04:20<17:43, 3.75it/s] 15%|█▌ | 710/4692 [04:20<17:42, 3.75it/s] 15%|█▌ | 711/4692 [04:20<17:42, 3.75it/s] 15%|█▌ | 712/4692 [04:20<17:42, 3.75it/s] 15%|█▌ | 713/4692 [04:21<17:42, 3.74it/s] 15%|█▌ | 714/4692 [04:21<17:43, 3.74it/s] 15%|█▌ | 715/4692 [04:21<17:40, 3.75it/s] 15%|█▌ | 716/4692 [04:22<17:39, 3.75it/s] 15%|█▌ | 717/4692 [04:22<17:36, 3.76it/s] 15%|█▌ | 718/4692 [04:22<17:42, 3.74it/s] 15%|█▌ | 719/4692 [04:22<17:44, 3.73it/s] 15%|█▌ | 720/4692 [04:23<17:48, 3.72it/s] 15%|█▌ | 721/4692 [04:23<17:44, 3.73it/s] 15%|█▌ | 722/4692 [04:23<17:42, 3.74it/s] 15%|█▌ | 723/4692 [04:23<17:38, 3.75it/s] 15%|█▌ | 724/4692 [04:24<17:35, 3.76it/s] 15%|█▌ | 725/4692 [04:24<17:33, 3.76it/s] 15%|█▌ | 726/4692 [04:24<17:34, 3.76it/s] 15%|█▌ | 727/4692 [04:24<17:33, 3.76it/s] 16%|█▌ | 728/4692 [04:25<17:37, 3.75it/s] 16%|█▌ | 729/4692 [04:25<17:35, 3.75it/s] 16%|█▌ | 730/4692 [04:25<17:32, 3.77it/s] 16%|█▌ | 731/4692 [04:26<17:38, 3.74it/s] 16%|█▌ | 732/4692 [04:26<17:44, 3.72it/s] 16%|█▌ | 733/4692 [04:26<17:43, 3.72it/s] 16%|█▌ | 734/4692 [04:26<17:38, 3.74it/s] 16%|█▌ | 735/4692 [04:27<17:37, 3.74it/s] 16%|█▌ | 736/4692 [04:27<17:36, 3.74it/s] 16%|█▌ | 737/4692 [04:27<17:35, 3.75it/s] 16%|█▌ | 738/4692 [04:27<17:34, 3.75it/s] 16%|█▌ | 739/4692 [04:28<17:33, 3.75it/s] 16%|█▌ | 740/4692 [04:28<17:33, 3.75it/s] 16%|█▌ | 741/4692 [04:28<17:32, 3.75it/s] 16%|█▌ | 742/4692 [04:28<17:29, 3.76it/s] 16%|█▌ | 743/4692 [04:29<17:31, 3.76it/s] 16%|█▌ | 744/4692 [04:29<17:32, 3.75it/s] 16%|█▌ | 745/4692 [04:29<17:32, 3.75it/s] 16%|█▌ | 746/4692 [04:30<17:36, 3.74it/s] 16%|█▌ | 747/4692 [04:30<17:35, 3.74it/s] 16%|█▌ | 748/4692 [04:30<17:33, 3.74it/s] 16%|█▌ | 749/4692 [04:30<17:31, 3.75it/s] 16%|█▌ | 750/4692 [04:31<17:29, 3.76it/s] 16%|█▌ | 751/4692 [04:31<17:29, 3.76it/s] 16%|█▌ | 752/4692 [04:31<17:26, 3.76it/s] 16%|█▌ | 753/4692 [04:31<17:27, 3.76it/s] 16%|█▌ | 754/4692 [04:32<17:28, 3.75it/s] 16%|█▌ | 755/4692 [04:32<17:28, 3.75it/s] 16%|█▌ | 756/4692 [04:32<17:28, 3.75it/s] 16%|█▌ | 757/4692 [04:32<17:26, 3.76it/s] 16%|█▌ | 758/4692 [04:33<17:24, 3.77it/s] 16%|█▌ | 759/4692 [04:33<17:31, 3.74it/s] 16%|█▌ | 760/4692 [04:33<17:30, 3.74it/s] 16%|█▌ | 761/4692 [04:34<17:33, 3.73it/s] 16%|█▌ | 762/4692 [04:34<17:31, 3.74it/s] 16%|█▋ | 763/4692 [04:34<17:28, 3.75it/s] 16%|█▋ | 764/4692 [04:34<17:32, 3.73it/s] 16%|█▋ | 765/4692 [04:35<17:29, 3.74it/s] 16%|█▋ | 766/4692 [04:35<17:29, 3.74it/s] 16%|█▋ | 767/4692 [04:35<17:26, 3.75it/s] 16%|█▋ | 768/4692 [04:35<17:25, 3.75it/s] 16%|█▋ | 769/4692 [04:36<17:24, 3.76it/s] 16%|█▋ | 770/4692 [04:36<17:25, 3.75it/s] 16%|█▋ | 771/4692 [04:36<17:26, 3.75it/s] 16%|█▋ | 772/4692 [04:36<17:25, 3.75it/s] 16%|█▋ | 773/4692 [04:37<17:24, 3.75it/s] 16%|█▋ | 774/4692 [04:37<17:24, 3.75it/s] 17%|█▋ | 775/4692 [04:37<17:23, 3.75it/s] 17%|█▋ | 776/4692 [04:38<17:23, 3.75it/s] 17%|█▋ | 777/4692 [04:38<17:21, 3.76it/s] 17%|█▋ | 778/4692 [04:38<17:20, 3.76it/s] 17%|█▋ | 779/4692 [04:38<17:21, 3.76it/s] 17%|█▋ | 780/4692 [04:39<17:22, 3.75it/s] 17%|█▋ | 781/4692 [04:39<17:21, 3.75it/s][INFO|trainer.py:738] 2023-07-03 01:12:16,362 >> The following columns in the evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: text. If text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3069] 2023-07-03 01:12:16,366 >> ***** Running Evaluation ***** [INFO|trainer.py:3071] 2023-07-03 01:12:16,366 >> Num examples = 25000 [INFO|trainer.py:3074] 2023-07-03 01:12:16,366 >> Batch size = 64 0%| | 0/391 [00:00> Saving model checkpoint to /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-782 [INFO|configuration_utils.py:457] 2023-07-03 01:13:20,957 >> Configuration saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-782/config.json [INFO|modeling_utils.py:1762] 2023-07-03 01:13:21,482 >> Model weights saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-782/pytorch_model.bin [INFO|tokenization_utils_base.py:2163] 2023-07-03 01:13:21,483 >> tokenizer config file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-782/tokenizer_config.json [INFO|tokenization_utils_base.py:2170] 2023-07-03 01:13:21,483 >> Special tokens file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-782/special_tokens_map.json [INFO|trainer.py:2893] 2023-07-03 01:13:22,636 >> Deleting older checkpoint [/nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-391] due to args.save_total_limit 17%|█▋ | 783/4692 [05:46<16:53:24, 15.55s/it] 17%|█▋ | 784/4692 [05:46<12:46:16, 11.76s/it] 17%|█▋ | 785/4692 [05:46<9:30:17, 8.76s/it] 17%|█▋ | 786/4692 [05:46<6:59:47, 6.45s/it] 17%|█▋ | 787/4692 [05:47<5:07:02, 4.72s/it] 17%|█▋ | 788/4692 [05:47<3:44:12, 3.45s/it] 17%|█▋ | 789/4692 [05:47<2:44:13, 2.52s/it] 17%|█▋ | 790/4692 [05:47<2:01:12, 1.86s/it] 17%|█▋ | 791/4692 [05:48<1:30:34, 1.39s/it] 17%|█▋ | 792/4692 [05:48<1:08:48, 1.06s/it] 17%|█▋ | 793/4692 [05:48<53:23, 1.22it/s] 17%|█▋ | 794/4692 [05:49<42:31, 1.53it/s] 17%|█▋ | 795/4692 [05:49<34:55, 1.86it/s] 17%|█▋ | 796/4692 [05:49<29:33, 2.20it/s] 17%|█▋ | 797/4692 [05:49<25:45, 2.52it/s] 17%|█▋ | 798/4692 [05:50<23:09, 2.80it/s] 17%|█▋ | 799/4692 [05:50<21:17, 3.05it/s] 17%|█▋ | 800/4692 [05:50<20:00, 3.24it/s] 17%|█▋ | 801/4692 [05:50<19:05, 3.40it/s] 17%|█▋ | 802/4692 [05:51<18:30, 3.50it/s] 17%|█▋ | 803/4692 [05:51<18:02, 3.59it/s] 17%|█▋ | 804/4692 [05:51<17:42, 3.66it/s] 17%|█▋ | 805/4692 [05:51<17:28, 3.71it/s] 17%|█▋ | 806/4692 [05:52<17:20, 3.74it/s] 17%|█▋ | 807/4692 [05:52<17:15, 3.75it/s] 17%|█▋ | 808/4692 [05:52<17:13, 3.76it/s] 17%|█▋ | 809/4692 [05:52<17:13, 3.76it/s] 17%|█▋ | 810/4692 [05:53<17:12, 3.76it/s] 17%|█▋ | 811/4692 [05:53<17:08, 3.77it/s] 17%|█▋ | 812/4692 [05:53<17:03, 3.79it/s] 17%|█▋ | 813/4692 [05:54<17:04, 3.79it/s] 17%|█▋ | 814/4692 [05:54<17:06, 3.78it/s] 17%|█▋ | 815/4692 [05:54<17:05, 3.78it/s] 17%|█▋ | 816/4692 [05:54<17:01, 3.79it/s] 17%|█▋ | 817/4692 [05:55<17:01, 3.79it/s] 17%|█▋ | 818/4692 [05:55<17:01, 3.79it/s] 17%|█▋ | 819/4692 [05:55<16:57, 3.81it/s] 17%|█▋ | 820/4692 [05:55<16:56, 3.81it/s] 17%|█▋ | 821/4692 [05:56<16:58, 3.80it/s] 18%|█▊ | 822/4692 [05:56<16:56, 3.81it/s] 18%|█▊ | 823/4692 [05:56<16:55, 3.81it/s] 18%|█▊ | 824/4692 [05:56<16:54, 3.81it/s] 18%|█▊ | 825/4692 [05:57<16:56, 3.80it/s] 18%|█▊ | 826/4692 [05:57<16:56, 3.80it/s] 18%|█▊ | 827/4692 [05:57<16:56, 3.80it/s] 18%|█▊ | 828/4692 [05:57<16:55, 3.81it/s] 18%|█▊ | 829/4692 [05:58<16:54, 3.81it/s] 18%|█▊ | 830/4692 [05:58<16:55, 3.80it/s] 18%|█▊ | 831/4692 [05:58<16:57, 3.79it/s] 18%|█▊ | 832/4692 [05:59<16:58, 3.79it/s] 18%|█▊ | 833/4692 [05:59<16:59, 3.79it/s] 18%|█▊ | 834/4692 [05:59<16:57, 3.79it/s] 18%|█▊ | 835/4692 [05:59<16:56, 3.79it/s] 18%|█▊ | 836/4692 [06:00<16:53, 3.80it/s] 18%|█▊ | 837/4692 [06:00<16:53, 3.80it/s] 18%|█▊ | 838/4692 [06:00<16:55, 3.79it/s] 18%|█▊ | 839/4692 [06:00<16:54, 3.80it/s] 18%|█▊ | 840/4692 [06:01<16:52, 3.81it/s] 18%|█▊ | 841/4692 [06:01<16:53, 3.80it/s] 18%|█▊ | 842/4692 [06:01<16:53, 3.80it/s] 18%|█▊ | 843/4692 [06:01<16:50, 3.81it/s] 18%|█▊ | 844/4692 [06:02<16:49, 3.81it/s] 18%|█▊ | 845/4692 [06:02<16:48, 3.81it/s] 18%|█▊ | 846/4692 [06:02<16:47, 3.82it/s] 18%|█▊ | 847/4692 [06:02<16:47, 3.82it/s] 18%|█▊ | 848/4692 [06:03<16:46, 3.82it/s] 18%|█▊ | 849/4692 [06:03<16:47, 3.81it/s] 18%|█▊ | 850/4692 [06:03<16:45, 3.82it/s] 18%|█▊ | 851/4692 [06:04<16:47, 3.81it/s] 18%|█▊ | 852/4692 [06:04<16:45, 3.82it/s] 18%|█▊ | 853/4692 [06:04<16:53, 3.79it/s] 18%|█▊ | 854/4692 [06:04<16:51, 3.80it/s] 18%|█▊ | 855/4692 [06:05<16:50, 3.80it/s] 18%|█▊ | 856/4692 [06:05<17:00, 3.76it/s] 18%|█▊ | 857/4692 [06:05<17:14, 3.71it/s] 18%|█▊ | 858/4692 [06:05<17:23, 3.67it/s] 18%|█▊ | 859/4692 [06:06<17:30, 3.65it/s] 18%|█▊ | 860/4692 [06:06<17:33, 3.64it/s] 18%|█▊ | 861/4692 [06:06<17:36, 3.62it/s] 18%|█▊ | 862/4692 [06:07<17:38, 3.62it/s] 18%|█▊ | 863/4692 [06:07<17:42, 3.60it/s] 18%|█▊ | 864/4692 [06:07<17:43, 3.60it/s] 18%|█▊ | 865/4692 [06:07<17:43, 3.60it/s] 18%|█▊ | 866/4692 [06:08<17:44, 3.60it/s] 18%|█▊ | 867/4692 [06:08<17:43, 3.60it/s] 18%|█▊ | 868/4692 [06:08<17:42, 3.60it/s] 19%|█▊ | 869/4692 [06:08<17:43, 3.60it/s] 19%|█▊ | 870/4692 [06:09<17:41, 3.60it/s] 19%|█▊ | 871/4692 [06:09<17:47, 3.58it/s] 19%|█▊ | 872/4692 [06:09<17:44, 3.59it/s] 19%|█▊ | 873/4692 [06:10<17:42, 3.59it/s] 19%|█▊ | 874/4692 [06:10<17:44, 3.59it/s] 19%|█▊ | 875/4692 [06:10<17:44, 3.59it/s] 19%|█▊ | 876/4692 [06:10<17:42, 3.59it/s] 19%|█▊ | 877/4692 [06:11<17:42, 3.59it/s] 19%|█▊ | 878/4692 [06:11<17:41, 3.59it/s] 19%|█▊ | 879/4692 [06:11<17:41, 3.59it/s] 19%|█▉ | 880/4692 [06:12<17:43, 3.59it/s] 19%|█▉ | 881/4692 [06:12<17:41, 3.59it/s] 19%|█▉ | 882/4692 [06:12<17:42, 3.59it/s] 19%|█▉ | 883/4692 [06:12<17:41, 3.59it/s] 19%|█▉ | 884/4692 [06:13<17:40, 3.59it/s] 19%|█▉ | 885/4692 [06:13<17:40, 3.59it/s] 19%|█▉ | 886/4692 [06:13<17:38, 3.60it/s] 19%|█▉ | 887/4692 [06:13<17:38, 3.60it/s] 19%|█▉ | 888/4692 [06:14<17:36, 3.60it/s] 19%|█▉ | 889/4692 [06:14<17:36, 3.60it/s] 19%|█▉ | 890/4692 [06:14<17:36, 3.60it/s] 19%|█▉ | 891/4692 [06:15<17:34, 3.60it/s] 19%|█▉ | 892/4692 [06:15<17:35, 3.60it/s] 19%|█▉ | 893/4692 [06:15<17:35, 3.60it/s] 19%|█▉ | 894/4692 [06:15<17:37, 3.59it/s] 19%|█▉ | 895/4692 [06:16<17:38, 3.59it/s] 19%|█▉ | 896/4692 [06:16<17:38, 3.59it/s] 19%|█▉ | 897/4692 [06:16<17:37, 3.59it/s] 19%|█▉ | 898/4692 [06:17<17:38, 3.58it/s] 19%|█▉ | 899/4692 [06:17<17:38, 3.58it/s] 19%|█▉ | 900/4692 [06:17<17:35, 3.59it/s] 19%|█▉ | 901/4692 [06:17<17:34, 3.60it/s] 19%|█▉ | 902/4692 [06:18<17:33, 3.60it/s] 19%|█▉ | 903/4692 [06:18<17:35, 3.59it/s] 19%|█▉ | 904/4692 [06:18<17:34, 3.59it/s] 19%|█▉ | 905/4692 [06:19<17:34, 3.59it/s] 19%|█▉ | 906/4692 [06:19<17:34, 3.59it/s] 19%|█▉ | 907/4692 [06:19<17:34, 3.59it/s] 19%|█▉ | 908/4692 [06:19<17:32, 3.59it/s] 19%|█▉ | 909/4692 [06:20<17:32, 3.60it/s] 19%|█▉ | 910/4692 [06:20<17:30, 3.60it/s] 19%|█▉ | 911/4692 [06:20<17:31, 3.60it/s] 19%|█▉ | 912/4692 [06:20<17:29, 3.60it/s] 19%|█▉ | 913/4692 [06:21<17:29, 3.60it/s] 19%|█▉ | 914/4692 [06:21<17:28, 3.60it/s] 20%|█▉ | 915/4692 [06:21<17:26, 3.61it/s] 20%|█▉ | 916/4692 [06:22<17:27, 3.61it/s] 20%|█▉ | 917/4692 [06:22<17:28, 3.60it/s] 20%|█▉ | 918/4692 [06:22<17:29, 3.60it/s] 20%|█▉ | 919/4692 [06:22<17:31, 3.59it/s] 20%|█▉ | 920/4692 [06:23<17:30, 3.59it/s] 20%|█▉ | 921/4692 [06:23<17:30, 3.59it/s] 20%|█▉ | 922/4692 [06:23<17:28, 3.59it/s] 20%|█▉ | 923/4692 [06:24<17:31, 3.58it/s] 20%|█▉ | 924/4692 [06:24<17:32, 3.58it/s] 20%|█▉ | 925/4692 [06:24<17:29, 3.59it/s] 20%|█▉ | 926/4692 [06:24<17:28, 3.59it/s] 20%|█▉ | 927/4692 [06:25<17:27, 3.60it/s] 20%|█▉ | 928/4692 [06:25<17:27, 3.59it/s] 20%|█▉ | 929/4692 [06:25<17:26, 3.59it/s] 20%|█▉ | 930/4692 [06:25<17:25, 3.60it/s] 20%|█▉ | 931/4692 [06:26<17:24, 3.60it/s] 20%|█▉ | 932/4692 [06:26<17:23, 3.60it/s] 20%|█▉ | 933/4692 [06:26<17:24, 3.60it/s] 20%|█▉ | 934/4692 [06:27<17:24, 3.60it/s] 20%|█▉ | 935/4692 [06:27<17:24, 3.60it/s] 20%|█▉ | 936/4692 [06:27<17:23, 3.60it/s] 20%|█▉ | 937/4692 [06:27<17:22, 3.60it/s] 20%|█▉ | 938/4692 [06:28<17:23, 3.60it/s] 20%|██ | 939/4692 [06:28<17:23, 3.60it/s] 20%|██ | 940/4692 [06:28<17:23, 3.60it/s] 20%|██ | 941/4692 [06:29<17:22, 3.60it/s] 20%|██ | 942/4692 [06:29<17:21, 3.60it/s] 20%|██ | 943/4692 [06:29<17:21, 3.60it/s] 20%|██ | 944/4692 [06:29<17:20, 3.60it/s] 20%|██ | 945/4692 [06:30<17:21, 3.60it/s] 20%|██ | 946/4692 [06:30<17:19, 3.60it/s] 20%|██ | 947/4692 [06:30<17:20, 3.60it/s] 20%|██ | 948/4692 [06:30<17:20, 3.60it/s] 20%|██ | 949/4692 [06:31<17:19, 3.60it/s] 20%|██ | 950/4692 [06:31<17:20, 3.60it/s] 20%|██ | 951/4692 [06:31<17:19, 3.60it/s] 20%|██ | 952/4692 [06:32<17:19, 3.60it/s] 20%|██ | 953/4692 [06:32<17:19, 3.60it/s] 20%|██ | 954/4692 [06:32<17:17, 3.60it/s] 20%|██ | 955/4692 [06:32<17:18, 3.60it/s] 20%|██ | 956/4692 [06:33<17:19, 3.60it/s] 20%|██ | 957/4692 [06:33<17:16, 3.60it/s] 20%|██ | 958/4692 [06:33<17:16, 3.60it/s] 20%|██ | 959/4692 [06:34<17:17, 3.60it/s] 20%|██ | 960/4692 [06:34<17:17, 3.60it/s] 20%|██ | 961/4692 [06:34<17:18, 3.59it/s] 21%|██ | 962/4692 [06:34<17:17, 3.60it/s] 21%|██ | 963/4692 [06:35<17:16, 3.60it/s] 21%|██ | 964/4692 [06:35<17:15, 3.60it/s] 21%|██ | 965/4692 [06:35<17:17, 3.59it/s] 21%|██ | 966/4692 [06:35<17:17, 3.59it/s] 21%|██ | 967/4692 [06:36<17:16, 3.59it/s] 21%|██ | 968/4692 [06:36<17:16, 3.59it/s] 21%|██ | 969/4692 [06:36<17:14, 3.60it/s] 21%|██ | 970/4692 [06:37<17:14, 3.60it/s] 21%|██ | 971/4692 [06:37<17:13, 3.60it/s] 21%|██ | 972/4692 [06:37<17:11, 3.61it/s] 21%|██ | 973/4692 [06:37<17:11, 3.60it/s] 21%|██ | 974/4692 [06:38<17:13, 3.60it/s] 21%|██ | 975/4692 [06:38<17:13, 3.60it/s] 21%|██ | 976/4692 [06:38<17:12, 3.60it/s] 21%|██ | 977/4692 [06:39<17:10, 3.60it/s] 21%|██ | 978/4692 [06:39<17:11, 3.60it/s] 21%|██ | 979/4692 [06:39<17:10, 3.60it/s] 21%|██ | 980/4692 [06:39<17:10, 3.60it/s] 21%|██ | 981/4692 [06:40<17:10, 3.60it/s] 21%|██ | 982/4692 [06:40<17:10, 3.60it/s] 21%|██ | 983/4692 [06:40<17:10, 3.60it/s] 21%|██ | 984/4692 [06:40<17:08, 3.60it/s] 21%|██ | 985/4692 [06:41<17:08, 3.61it/s] 21%|██ | 986/4692 [06:41<17:08, 3.60it/s] 21%|██ | 987/4692 [06:41<17:07, 3.61it/s] 21%|██ | 988/4692 [06:42<17:08, 3.60it/s] 21%|██ | 989/4692 [06:42<17:08, 3.60it/s] 21%|██ | 990/4692 [06:42<17:08, 3.60it/s] 21%|██ | 991/4692 [06:42<17:07, 3.60it/s] 21%|██ | 992/4692 [06:43<17:04, 3.61it/s] 21%|██ | 993/4692 [06:43<17:06, 3.60it/s] 21%|██ | 994/4692 [06:43<17:05, 3.61it/s] 21%|██ | 995/4692 [06:44<17:07, 3.60it/s] 21%|██ | 996/4692 [06:44<17:07, 3.60it/s] 21%|██ | 997/4692 [06:44<17:08, 3.59it/s] 21%|██▏ | 998/4692 [06:44<17:11, 3.58it/s] 21%|██▏ | 999/4692 [06:45<17:10, 3.58it/s] 21%|██▏ | 1000/4692 [06:45<17:09, 3.59it/s] 21%|██▏ | 1000/4692 [06:45<17:09, 3.59it/s] 21%|██▏ | 1001/4692 [06:45<17:07, 3.59it/s] 21%|██▏ | 1002/4692 [06:45<17:08, 3.59it/s] 21%|██▏ | 1003/4692 [06:46<17:07, 3.59it/s] 21%|██▏ | 1004/4692 [06:46<17:10, 3.58it/s] 21%|██▏ | 1005/4692 [06:46<17:06, 3.59it/s] 21%|██▏ | 1006/4692 [06:47<17:05, 3.59it/s] 21%|██▏ | 1007/4692 [06:47<17:06, 3.59it/s] 21%|██▏ | 1008/4692 [06:47<17:03, 3.60it/s] 22%|██▏ | 1009/4692 [06:47<17:03, 3.60it/s] 22%|██▏ | 1010/4692 [06:48<17:03, 3.60it/s] 22%|██▏ | 1011/4692 [06:48<17:05, 3.59it/s] 22%|██▏ | 1012/4692 [06:48<17:06, 3.59it/s] 22%|██▏ | 1013/4692 [06:49<17:04, 3.59it/s] 22%|██▏ | 1014/4692 [06:49<17:03, 3.59it/s] 22%|██▏ | 1015/4692 [06:49<17:02, 3.60it/s] 22%|██▏ | 1016/4692 [06:49<17:01, 3.60it/s] 22%|██▏ | 1017/4692 [06:50<17:02, 3.60it/s] 22%|██▏ | 1018/4692 [06:50<17:02, 3.59it/s] 22%|██▏ | 1019/4692 [06:50<17:01, 3.59it/s] 22%|██▏ | 1020/4692 [06:50<17:01, 3.59it/s] 22%|██▏ | 1021/4692 [06:51<17:00, 3.60it/s] 22%|██▏ | 1022/4692 [06:51<16:57, 3.61it/s] 22%|██▏ | 1023/4692 [06:51<16:57, 3.61it/s] 22%|██▏ | 1024/4692 [06:52<16:58, 3.60it/s] 22%|██▏ | 1025/4692 [06:52<16:58, 3.60it/s] 22%|██▏ | 1026/4692 [06:52<16:59, 3.60it/s] 22%|██▏ | 1027/4692 [06:52<16:58, 3.60it/s] 22%|██▏ | 1028/4692 [06:53<16:59, 3.59it/s] 22%|██▏ | 1029/4692 [06:53<17:00, 3.59it/s] 22%|██▏ | 1030/4692 [06:53<16:55, 3.61it/s] 22%|██▏ | 1031/4692 [06:54<16:43, 3.65it/s] 22%|██▏ | 1032/4692 [06:54<16:35, 3.68it/s] 22%|██▏ | 1033/4692 [06:54<16:29, 3.70it/s] 22%|██▏ | 1034/4692 [06:54<16:24, 3.72it/s] 22%|██▏ | 1035/4692 [06:55<16:24, 3.72it/s] 22%|██▏ | 1036/4692 [06:55<16:22, 3.72it/s] 22%|██▏ | 1037/4692 [06:55<16:19, 3.73it/s] 22%|██▏ | 1038/4692 [06:55<16:16, 3.74it/s] 22%|██▏ | 1039/4692 [06:56<16:15, 3.74it/s] 22%|██▏ | 1040/4692 [06:56<16:12, 3.75it/s] 22%|██▏ | 1041/4692 [06:56<16:11, 3.76it/s] 22%|██▏ | 1042/4692 [06:56<16:11, 3.76it/s] 22%|██▏ | 1043/4692 [06:57<16:11, 3.76it/s] 22%|██▏ | 1044/4692 [06:57<16:09, 3.76it/s] 22%|██▏ | 1045/4692 [06:57<16:08, 3.77it/s] 22%|██▏ | 1046/4692 [06:58<16:11, 3.75it/s] 22%|██▏ | 1047/4692 [06:58<16:10, 3.76it/s] 22%|██▏ | 1048/4692 [06:58<16:11, 3.75it/s] 22%|██▏ | 1049/4692 [06:58<16:11, 3.75it/s] 22%|██▏ | 1050/4692 [06:59<16:09, 3.75it/s] 22%|██▏ | 1051/4692 [06:59<16:09, 3.75it/s] 22%|██▏ | 1052/4692 [06:59<16:08, 3.76it/s] 22%|██▏ | 1053/4692 [06:59<16:09, 3.75it/s] 22%|██▏ | 1054/4692 [07:00<16:10, 3.75it/s] 22%|██▏ | 1055/4692 [07:00<16:10, 3.75it/s] 23%|██▎ | 1056/4692 [07:00<16:09, 3.75it/s] 23%|██▎ | 1057/4692 [07:00<16:09, 3.75it/s] 23%|██▎ | 1058/4692 [07:01<16:10, 3.74it/s] 23%|██▎ | 1059/4692 [07:01<16:09, 3.75it/s] 23%|██▎ | 1060/4692 [07:01<16:07, 3.75it/s] 23%|██▎ | 1061/4692 [07:02<16:07, 3.75it/s] 23%|██▎ | 1062/4692 [07:02<16:05, 3.76it/s] 23%|██▎ | 1063/4692 [07:02<16:04, 3.76it/s] 23%|██▎ | 1064/4692 [07:02<16:03, 3.77it/s] 23%|██▎ | 1065/4692 [07:03<16:08, 3.75it/s] 23%|██▎ | 1066/4692 [07:03<16:05, 3.75it/s] 23%|██▎ | 1067/4692 [07:03<16:03, 3.76it/s] 23%|██▎ | 1068/4692 [07:03<16:03, 3.76it/s] 23%|██▎ | 1069/4692 [07:04<16:04, 3.76it/s] 23%|██▎ | 1070/4692 [07:04<16:03, 3.76it/s] 23%|██▎ | 1071/4692 [07:04<16:03, 3.76it/s] 23%|██▎ | 1072/4692 [07:04<16:03, 3.76it/s] 23%|██▎ | 1073/4692 [07:05<16:03, 3.75it/s] 23%|██▎ | 1074/4692 [07:05<16:04, 3.75it/s] 23%|██▎ | 1075/4692 [07:05<16:03, 3.76it/s] 23%|██▎ | 1076/4692 [07:06<16:02, 3.76it/s] 23%|██▎ | 1077/4692 [07:06<16:02, 3.75it/s] 23%|██▎ | 1078/4692 [07:06<16:03, 3.75it/s] 23%|██▎ | 1079/4692 [07:06<16:01, 3.76it/s] 23%|██▎ | 1080/4692 [07:07<16:02, 3.75it/s] 23%|██▎ | 1081/4692 [07:07<16:01, 3.75it/s] 23%|██▎ | 1082/4692 [07:07<15:59, 3.76it/s] 23%|██▎ | 1083/4692 [07:07<15:58, 3.76it/s] 23%|██▎ | 1084/4692 [07:08<15:56, 3.77it/s] 23%|██▎ | 1085/4692 [07:08<15:59, 3.76it/s] 23%|██▎ | 1086/4692 [07:08<15:55, 3.77it/s] 23%|██▎ | 1087/4692 [07:08<15:55, 3.77it/s] 23%|██▎ | 1088/4692 [07:09<15:56, 3.77it/s] 23%|██▎ | 1089/4692 [07:09<15:56, 3.77it/s] 23%|██▎ | 1090/4692 [07:09<15:55, 3.77it/s] 23%|██▎ | 1091/4692 [07:09<15:57, 3.76it/s] 23%|██▎ | 1092/4692 [07:10<15:56, 3.76it/s] 23%|██▎ | 1093/4692 [07:10<15:56, 3.76it/s] 23%|██▎ | 1094/4692 [07:10<15:57, 3.76it/s] 23%|██▎ | 1095/4692 [07:11<15:57, 3.76it/s] 23%|██▎ | 1096/4692 [07:11<15:57, 3.75it/s] 23%|██▎ | 1097/4692 [07:11<15:56, 3.76it/s] 23%|██▎ | 1098/4692 [07:11<15:56, 3.76it/s] 23%|██▎ | 1099/4692 [07:12<16:00, 3.74it/s] 23%|██▎ | 1100/4692 [07:12<15:57, 3.75it/s] 23%|██▎ | 1101/4692 [07:12<15:57, 3.75it/s] 23%|██▎ | 1102/4692 [07:12<15:54, 3.76it/s] 24%|██▎ | 1103/4692 [07:13<15:57, 3.75it/s] 24%|██▎ | 1104/4692 [07:13<15:56, 3.75it/s] 24%|██▎ | 1105/4692 [07:13<15:54, 3.76it/s] 24%|██▎ | 1106/4692 [07:13<15:57, 3.75it/s] 24%|██▎ | 1107/4692 [07:14<15:58, 3.74it/s] 24%|██▎ | 1108/4692 [07:14<15:56, 3.75it/s] 24%|██▎ | 1109/4692 [07:14<15:55, 3.75it/s] 24%|██▎ | 1110/4692 [07:15<15:55, 3.75it/s] 24%|██▎ | 1111/4692 [07:15<15:55, 3.75it/s] 24%|██▎ | 1112/4692 [07:15<15:53, 3.76it/s] 24%|██▎ | 1113/4692 [07:15<15:53, 3.75it/s] 24%|██▎ | 1114/4692 [07:16<15:52, 3.75it/s] 24%|██▍ | 1115/4692 [07:16<15:53, 3.75it/s] 24%|██▍ | 1116/4692 [07:16<15:53, 3.75it/s] 24%|██▍ | 1117/4692 [07:16<15:48, 3.77it/s] 24%|██▍ | 1118/4692 [07:17<15:46, 3.77it/s] 24%|██▍ | 1119/4692 [07:17<15:45, 3.78it/s] 24%|██▍ | 1120/4692 [07:17<15:45, 3.78it/s] 24%|██▍ | 1121/4692 [07:17<15:49, 3.76it/s] 24%|██▍ | 1122/4692 [07:18<15:50, 3.76it/s] 24%|██▍ | 1123/4692 [07:18<15:49, 3.76it/s] 24%|██▍ | 1124/4692 [07:18<15:49, 3.76it/s] 24%|██▍ | 1125/4692 [07:19<15:49, 3.76it/s] 24%|██▍ | 1126/4692 [07:19<15:50, 3.75it/s] 24%|██▍ | 1127/4692 [07:19<15:49, 3.75it/s] 24%|██▍ | 1128/4692 [07:19<15:48, 3.76it/s] 24%|██▍ | 1129/4692 [07:20<15:48, 3.76it/s] 24%|██▍ | 1130/4692 [07:20<15:48, 3.76it/s] 24%|██▍ | 1131/4692 [07:20<15:47, 3.76it/s] 24%|██▍ | 1132/4692 [07:20<15:46, 3.76it/s] 24%|██▍ | 1133/4692 [07:21<15:45, 3.76it/s] 24%|██▍ | 1134/4692 [07:21<15:46, 3.76it/s] 24%|██▍ | 1135/4692 [07:21<15:48, 3.75it/s] 24%|██▍ | 1136/4692 [07:21<15:48, 3.75it/s] 24%|██▍ | 1137/4692 [07:22<15:47, 3.75it/s] 24%|██▍ | 1138/4692 [07:22<15:47, 3.75it/s] 24%|██▍ | 1139/4692 [07:22<15:47, 3.75it/s] 24%|██▍ | 1140/4692 [07:23<15:45, 3.76it/s] 24%|██▍ | 1141/4692 [07:23<15:45, 3.75it/s] 24%|██▍ | 1142/4692 [07:23<15:46, 3.75it/s] 24%|██▍ | 1143/4692 [07:23<15:45, 3.75it/s] 24%|██▍ | 1144/4692 [07:24<15:43, 3.76it/s] 24%|██▍ | 1145/4692 [07:24<15:45, 3.75it/s] 24%|██▍ | 1146/4692 [07:24<15:45, 3.75it/s] 24%|██▍ | 1147/4692 [07:24<15:42, 3.76it/s] 24%|██▍ | 1148/4692 [07:25<15:42, 3.76it/s] 24%|██▍ | 1149/4692 [07:25<15:43, 3.76it/s] 25%|██▍ | 1150/4692 [07:25<15:43, 3.75it/s] 25%|██▍ | 1151/4692 [07:25<15:42, 3.76it/s] 25%|██▍ | 1152/4692 [07:26<15:42, 3.75it/s] 25%|██▍ | 1153/4692 [07:26<15:44, 3.75it/s] 25%|██▍ | 1154/4692 [07:26<15:42, 3.76it/s] 25%|██▍ | 1155/4692 [07:27<15:43, 3.75it/s] 25%|██▍ | 1156/4692 [07:27<15:42, 3.75it/s] 25%|██▍ | 1157/4692 [07:27<15:40, 3.76it/s] 25%|██▍ | 1158/4692 [07:27<15:40, 3.76it/s] 25%|██▍ | 1159/4692 [07:28<15:39, 3.76it/s] 25%|██▍ | 1160/4692 [07:28<15:40, 3.76it/s] 25%|██▍ | 1161/4692 [07:28<15:41, 3.75it/s] 25%|██▍ | 1162/4692 [07:28<15:41, 3.75it/s] 25%|██▍ | 1163/4692 [07:29<15:41, 3.75it/s] 25%|██▍ | 1164/4692 [07:29<15:43, 3.74it/s] 25%|██▍ | 1165/4692 [07:29<15:41, 3.75it/s] 25%|██▍ | 1166/4692 [07:29<15:40, 3.75it/s] 25%|██▍ | 1167/4692 [07:30<15:51, 3.70it/s] 25%|██▍ | 1168/4692 [07:30<15:53, 3.70it/s] 25%|██▍ | 1169/4692 [07:30<15:49, 3.71it/s] 25%|██▍ | 1170/4692 [07:31<15:46, 3.72it/s] 25%|██▍ | 1171/4692 [07:31<15:44, 3.73it/s] 25%|██▍ | 1172/4692 [07:31<15:42, 3.74it/s] 25%|██▌ | 1173/4692 [07:31<15:41, 3.74it/s][INFO|trainer.py:738] 2023-07-03 01:15:08,769 >> The following columns in the evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: text. If text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3069] 2023-07-03 01:15:08,772 >> ***** Running Evaluation ***** [INFO|trainer.py:3071] 2023-07-03 01:15:08,772 >> Num examples = 25000 [INFO|trainer.py:3074] 2023-07-03 01:15:08,772 >> Batch size = 64 0%| | 0/391 [00:00> Saving model checkpoint to /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-1173 [INFO|configuration_utils.py:457] 2023-07-03 01:16:13,643 >> Configuration saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-1173/config.json [INFO|modeling_utils.py:1762] 2023-07-03 01:16:14,203 >> Model weights saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-1173/pytorch_model.bin [INFO|tokenization_utils_base.py:2163] 2023-07-03 01:16:14,203 >> tokenizer config file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-1173/tokenizer_config.json [INFO|tokenization_utils_base.py:2170] 2023-07-03 01:16:14,204 >> Special tokens file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-1173/special_tokens_map.json [INFO|trainer.py:2893] 2023-07-03 01:16:15,360 >> Deleting older checkpoint [/nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-782] due to args.save_total_limit 25%|██▌ | 1174/4692 [08:38<19:49:29, 20.29s/it] 25%|██▌ | 1175/4692 [08:39<13:57:08, 14.28s/it] 25%|██▌ | 1176/4692 [08:39<9:50:31, 10.08s/it] 25%|██▌ | 1177/4692 [08:39<6:57:58, 7.13s/it] 25%|██▌ | 1178/4692 [08:39<4:57:13, 5.07s/it] 25%|██▌ | 1179/4692 [08:40<3:32:45, 3.63s/it] 25%|██▌ | 1180/4692 [08:40<2:33:33, 2.62s/it] 25%|██▌ | 1181/4692 [08:40<1:52:11, 1.92s/it] 25%|██▌ | 1182/4692 [08:40<1:23:10, 1.42s/it] 25%|██▌ | 1183/4692 [08:41<1:02:52, 1.08s/it] 25%|██▌ | 1184/4692 [08:41<48:40, 1.20it/s] 25%|██▌ | 1185/4692 [08:41<38:43, 1.51it/s] 25%|██▌ | 1186/4692 [08:42<31:43, 1.84it/s] 25%|██▌ | 1187/4692 [08:42<26:51, 2.18it/s] 25%|██▌ | 1188/4692 [08:42<23:27, 2.49it/s] 25%|██▌ | 1189/4692 [08:42<21:02, 2.78it/s] 25%|██▌ | 1190/4692 [08:43<19:21, 3.01it/s] 25%|██▌ | 1191/4692 [08:43<18:08, 3.22it/s] 25%|██▌ | 1192/4692 [08:43<17:17, 3.37it/s] 25%|██▌ | 1193/4692 [08:43<16:44, 3.49it/s] 25%|██▌ | 1194/4692 [08:44<16:23, 3.56it/s] 25%|██▌ | 1195/4692 [08:44<16:07, 3.62it/s] 25%|██▌ | 1196/4692 [08:44<15:57, 3.65it/s] 26%|██▌ | 1197/4692 [08:44<15:52, 3.67it/s] 26%|██▌ | 1198/4692 [08:45<15:46, 3.69it/s] 26%|██▌ | 1199/4692 [08:45<15:39, 3.72it/s] 26%|██▌ | 1200/4692 [08:45<15:36, 3.73it/s] 26%|██▌ | 1201/4692 [08:46<15:33, 3.74it/s] 26%|██▌ | 1202/4692 [08:46<15:31, 3.74it/s] 26%|██▌ | 1203/4692 [08:46<15:30, 3.75it/s] 26%|██▌ | 1204/4692 [08:46<15:29, 3.75it/s] 26%|██▌ | 1205/4692 [08:47<15:28, 3.75it/s] 26%|██▌ | 1206/4692 [08:47<15:27, 3.76it/s] 26%|██▌ | 1207/4692 [08:47<15:24, 3.77it/s] 26%|██▌ | 1208/4692 [08:47<15:24, 3.77it/s] 26%|██▌ | 1209/4692 [08:48<15:21, 3.78it/s] 26%|██▌ | 1210/4692 [08:48<15:17, 3.79it/s] 26%|██▌ | 1211/4692 [08:48<15:14, 3.81it/s] 26%|██▌ | 1212/4692 [08:48<15:15, 3.80it/s] 26%|██▌ | 1213/4692 [08:49<15:19, 3.78it/s] 26%|██▌ | 1214/4692 [08:49<15:19, 3.78it/s] 26%|██▌ | 1215/4692 [08:49<15:19, 3.78it/s] 26%|██▌ | 1216/4692 [08:50<15:21, 3.77it/s] 26%|██▌ | 1217/4692 [08:50<15:20, 3.78it/s] 26%|██▌ | 1218/4692 [08:50<15:19, 3.78it/s] 26%|██▌ | 1219/4692 [08:50<15:19, 3.78it/s] 26%|██▌ | 1220/4692 [08:51<15:20, 3.77it/s] 26%|██▌ | 1221/4692 [08:51<15:20, 3.77it/s] 26%|██▌ | 1222/4692 [08:51<15:19, 3.77it/s] 26%|██▌ | 1223/4692 [08:51<15:20, 3.77it/s] 26%|██▌ | 1224/4692 [08:52<15:20, 3.77it/s] 26%|██▌ | 1225/4692 [08:52<15:20, 3.77it/s] 26%|██▌ | 1226/4692 [08:52<15:20, 3.77it/s] 26%|██▌ | 1227/4692 [08:52<15:18, 3.77it/s] 26%|██▌ | 1228/4692 [08:53<15:15, 3.78it/s] 26%|██▌ | 1229/4692 [08:53<15:15, 3.78it/s] 26%|██▌ | 1230/4692 [08:53<15:15, 3.78it/s] 26%|██▌ | 1231/4692 [08:53<15:16, 3.78it/s] 26%|██▋ | 1232/4692 [08:54<15:17, 3.77it/s] 26%|██▋ | 1233/4692 [08:54<15:17, 3.77it/s] 26%|██▋ | 1234/4692 [08:54<15:31, 3.71it/s] 26%|██▋ | 1235/4692 [08:55<15:47, 3.65it/s] 26%|██▋ | 1236/4692 [08:55<15:56, 3.61it/s] 26%|██▋ | 1237/4692 [08:55<15:58, 3.60it/s] 26%|██▋ | 1238/4692 [08:55<15:59, 3.60it/s] 26%|██▋ | 1239/4692 [08:56<15:59, 3.60it/s] 26%|██▋ | 1240/4692 [08:56<16:03, 3.58it/s] 26%|██▋ | 1241/4692 [08:56<16:02, 3.59it/s] 26%|██▋ | 1242/4692 [08:57<16:13, 3.54it/s] 26%|██▋ | 1243/4692 [08:57<16:13, 3.54it/s] 27%|██▋ | 1244/4692 [08:57<16:10, 3.55it/s] 27%|██▋ | 1245/4692 [08:57<16:10, 3.55it/s] 27%|██▋ | 1246/4692 [08:58<16:08, 3.56it/s] 27%|██▋ | 1247/4692 [08:58<16:09, 3.55it/s] 27%|██▋ | 1248/4692 [08:58<16:07, 3.56it/s] 27%|██▋ | 1249/4692 [08:59<16:07, 3.56it/s] 27%|██▋ | 1250/4692 [08:59<16:05, 3.56it/s] 27%|██▋ | 1251/4692 [08:59<16:07, 3.55it/s] 27%|██▋ | 1252/4692 [08:59<16:24, 3.49it/s] 27%|██▋ | 1253/4692 [09:00<16:58, 3.38it/s] 27%|██▋ | 1254/4692 [09:00<16:45, 3.42it/s] 27%|██▋ | 1255/4692 [09:00<16:37, 3.45it/s] 27%|██▋ | 1256/4692 [09:01<16:29, 3.47it/s] 27%|██▋ | 1257/4692 [09:01<16:20, 3.50it/s] 27%|██▋ | 1258/4692 [09:01<16:16, 3.52it/s] 27%|██▋ | 1259/4692 [09:01<16:12, 3.53it/s] 27%|██▋ | 1260/4692 [09:02<16:09, 3.54it/s] 27%|██▋ | 1261/4692 [09:02<16:09, 3.54it/s] 27%|██▋ | 1262/4692 [09:02<16:06, 3.55it/s] 27%|██▋ | 1263/4692 [09:03<16:04, 3.56it/s] 27%|██▋ | 1264/4692 [09:03<16:03, 3.56it/s] 27%|██▋ | 1265/4692 [09:03<16:04, 3.55it/s] 27%|██▋ | 1266/4692 [09:03<16:02, 3.56it/s] 27%|██▋ | 1267/4692 [09:04<15:59, 3.57it/s] 27%|██▋ | 1268/4692 [09:04<15:59, 3.57it/s] 27%|██▋ | 1269/4692 [09:04<15:59, 3.57it/s] 27%|██▋ | 1270/4692 [09:04<15:58, 3.57it/s] 27%|██▋ | 1271/4692 [09:05<15:58, 3.57it/s] 27%|██▋ | 1272/4692 [09:05<16:03, 3.55it/s] 27%|██▋ | 1273/4692 [09:05<16:00, 3.56it/s] 27%|██▋ | 1274/4692 [09:06<15:56, 3.57it/s] 27%|██▋ | 1275/4692 [09:06<15:45, 3.62it/s] 27%|██▋ | 1276/4692 [09:06<15:37, 3.64it/s] 27%|██▋ | 1277/4692 [09:06<15:28, 3.68it/s] 27%|██▋ | 1278/4692 [09:07<15:24, 3.69it/s] 27%|██▋ | 1279/4692 [09:07<15:27, 3.68it/s] 27%|██▋ | 1280/4692 [09:07<15:20, 3.71it/s] 27%|██▋ | 1281/4692 [09:07<15:41, 3.62it/s] 27%|██▋ | 1282/4692 [09:08<16:22, 3.47it/s] 27%|██▋ | 1283/4692 [09:08<16:43, 3.40it/s] 27%|██▋ | 1284/4692 [09:08<16:38, 3.41it/s] 27%|██▋ | 1285/4692 [09:09<16:11, 3.51it/s] 27%|██▋ | 1286/4692 [09:09<15:53, 3.57it/s] 27%|██▋ | 1287/4692 [09:09<15:56, 3.56it/s] 27%|██▋ | 1288/4692 [09:10<16:04, 3.53it/s] 27%|██▋ | 1289/4692 [09:10<15:55, 3.56it/s] 27%|██▋ | 1290/4692 [09:10<15:42, 3.61it/s] 28%|██▊ | 1291/4692 [09:10<15:59, 3.54it/s] 28%|██▊ | 1292/4692 [09:11<16:24, 3.45it/s] 28%|██▊ | 1293/4692 [09:11<16:33, 3.42it/s] 28%|██▊ | 1294/4692 [09:11<16:38, 3.40it/s] 28%|██▊ | 1295/4692 [09:12<16:48, 3.37it/s] 28%|██▊ | 1296/4692 [09:12<16:46, 3.37it/s] 28%|██▊ | 1297/4692 [09:12<16:42, 3.39it/s] 28%|██▊ | 1298/4692 [09:12<16:54, 3.35it/s] 28%|██▊ | 1299/4692 [09:13<17:01, 3.32it/s] 28%|██▊ | 1300/4692 [09:13<17:20, 3.26it/s] 28%|██▊ | 1301/4692 [09:13<17:14, 3.28it/s] 28%|██▊ | 1302/4692 [09:14<17:06, 3.30it/s] 28%|██▊ | 1303/4692 [09:14<20:17, 2.78it/s] 28%|██▊ | 1304/4692 [09:15<22:53, 2.47it/s] 28%|██▊ | 1305/4692 [09:15<24:31, 2.30it/s] 28%|██▊ | 1306/4692 [09:16<25:54, 2.18it/s] 28%|██▊ | 1307/4692 [09:16<26:52, 2.10it/s] 28%|██▊ | 1308/4692 [09:17<27:33, 2.05it/s] 28%|██▊ | 1309/4692 [09:17<28:21, 1.99it/s] 28%|██▊ | 1310/4692 [09:18<28:58, 1.94it/s] 28%|██▊ | 1311/4692 [09:18<29:31, 1.91it/s] 28%|██▊ | 1312/4692 [09:19<29:10, 1.93it/s] 28%|██▊ | 1313/4692 [09:19<29:34, 1.90it/s] 28%|██▊ | 1314/4692 [09:20<29:45, 1.89it/s] 28%|██▊ | 1315/4692 [09:20<29:59, 1.88it/s] 28%|██▊ | 1316/4692 [09:21<30:03, 1.87it/s] 28%|██▊ | 1317/4692 [09:22<30:14, 1.86it/s] 28%|██▊ | 1318/4692 [09:22<30:35, 1.84it/s] 28%|██▊ | 1319/4692 [09:23<30:43, 1.83it/s] 28%|██▊ | 1320/4692 [09:23<30:48, 1.82it/s] 28%|██▊ | 1321/4692 [09:24<30:54, 1.82it/s] 28%|██▊ | 1322/4692 [09:24<31:06, 1.81it/s] 28%|██▊ | 1323/4692 [09:25<31:08, 1.80it/s] 28%|██▊ | 1324/4692 [09:25<31:14, 1.80it/s] 28%|██▊ | 1325/4692 [09:26<31:12, 1.80it/s] 28%|██▊ | 1326/4692 [09:27<31:19, 1.79it/s] 28%|██▊ | 1327/4692 [09:27<31:23, 1.79it/s] 28%|██▊ | 1328/4692 [09:28<31:23, 1.79it/s] 28%|██▊ | 1329/4692 [09:28<31:27, 1.78it/s] 28%|██▊ | 1330/4692 [09:29<31:27, 1.78it/s] 28%|██▊ | 1331/4692 [09:29<31:26, 1.78it/s] 28%|██▊ | 1332/4692 [09:30<31:34, 1.77it/s] 28%|██▊ | 1333/4692 [09:31<31:22, 1.78it/s] 28%|██▊ | 1334/4692 [09:31<31:10, 1.79it/s] 28%|██▊ | 1335/4692 [09:32<31:07, 1.80it/s] 28%|██▊ | 1336/4692 [09:32<31:13, 1.79it/s] 28%|██▊ | 1337/4692 [09:33<31:09, 1.79it/s] 29%|██▊ | 1338/4692 [09:33<31:11, 1.79it/s] 29%|██▊ | 1339/4692 [09:34<31:07, 1.80it/s] 29%|██▊ | 1340/4692 [09:34<31:13, 1.79it/s] 29%|██▊ | 1341/4692 [09:35<31:28, 1.77it/s] 29%|██▊ | 1342/4692 [09:36<31:28, 1.77it/s] 29%|██▊ | 1343/4692 [09:36<31:23, 1.78it/s] 29%|██▊ | 1344/4692 [09:37<31:33, 1.77it/s] 29%|██▊ | 1345/4692 [09:37<31:33, 1.77it/s] 29%|██▊ | 1346/4692 [09:38<31:22, 1.78it/s] 29%|██▊ | 1347/4692 [09:38<31:11, 1.79it/s] 29%|██▊ | 1348/4692 [09:39<31:15, 1.78it/s] 29%|██▉ | 1349/4692 [09:39<31:13, 1.78it/s] 29%|██▉ | 1350/4692 [09:40<31:19, 1.78it/s] 29%|██▉ | 1351/4692 [09:41<31:16, 1.78it/s] 29%|██▉ | 1352/4692 [09:41<31:11, 1.78it/s] 29%|██▉ | 1353/4692 [09:42<31:10, 1.79it/s] 29%|██▉ | 1354/4692 [09:42<31:05, 1.79it/s] 29%|██▉ | 1355/4692 [09:43<31:16, 1.78it/s] 29%|██▉ | 1356/4692 [09:43<31:16, 1.78it/s] 29%|██▉ | 1357/4692 [09:44<31:15, 1.78it/s] 29%|██▉ | 1358/4692 [09:45<31:10, 1.78it/s] 29%|██▉ | 1359/4692 [09:45<31:16, 1.78it/s] 29%|██▉ | 1360/4692 [09:46<31:11, 1.78it/s] 29%|██▉ | 1361/4692 [09:46<31:14, 1.78it/s] 29%|██▉ | 1362/4692 [09:47<31:08, 1.78it/s] 29%|██▉ | 1363/4692 [09:47<31:20, 1.77it/s] 29%|██▉ | 1364/4692 [09:48<31:32, 1.76it/s] 29%|██▉ | 1365/4692 [09:48<31:18, 1.77it/s] 29%|██▉ | 1366/4692 [09:49<31:13, 1.77it/s] 29%|██▉ | 1367/4692 [09:50<31:09, 1.78it/s] 29%|██▉ | 1368/4692 [09:50<31:10, 1.78it/s] 29%|██▉ | 1369/4692 [09:51<31:11, 1.78it/s] 29%|██▉ | 1370/4692 [09:51<30:54, 1.79it/s] 29%|██▉ | 1371/4692 [09:52<30:55, 1.79it/s] 29%|██▉ | 1372/4692 [09:52<31:01, 1.78it/s] 29%|██▉ | 1373/4692 [09:53<31:10, 1.77it/s] 29%|██▉ | 1374/4692 [09:54<31:09, 1.78it/s] 29%|██▉ | 1375/4692 [09:54<31:00, 1.78it/s] 29%|██▉ | 1376/4692 [09:55<31:12, 1.77it/s] 29%|██▉ | 1377/4692 [09:55<31:04, 1.78it/s] 29%|██▉ | 1378/4692 [09:56<31:08, 1.77it/s] 29%|██▉ | 1379/4692 [09:56<31:15, 1.77it/s] 29%|██▉ | 1380/4692 [09:57<31:05, 1.78it/s] 29%|██▉ | 1381/4692 [09:58<31:10, 1.77it/s] 29%|██▉ | 1382/4692 [09:58<31:00, 1.78it/s] 29%|██▉ | 1383/4692 [09:59<31:05, 1.77it/s] 29%|██▉ | 1384/4692 [09:59<31:02, 1.78it/s] 30%|██▉ | 1385/4692 [10:00<30:55, 1.78it/s] 30%|██▉ | 1386/4692 [10:00<30:54, 1.78it/s] 30%|██▉ | 1387/4692 [10:01<31:06, 1.77it/s] 30%|██▉ | 1388/4692 [10:01<31:13, 1.76it/s] 30%|██▉ | 1389/4692 [10:02<31:04, 1.77it/s] 30%|██▉ | 1390/4692 [10:03<30:55, 1.78it/s] 30%|██▉ | 1391/4692 [10:03<30:44, 1.79it/s] 30%|██▉ | 1392/4692 [10:04<30:52, 1.78it/s] 30%|██▉ | 1393/4692 [10:04<30:53, 1.78it/s] 30%|██▉ | 1394/4692 [10:05<30:55, 1.78it/s] 30%|██▉ | 1395/4692 [10:05<30:50, 1.78it/s] 30%|██▉ | 1396/4692 [10:06<30:44, 1.79it/s] 30%|██▉ | 1397/4692 [10:06<30:44, 1.79it/s] 30%|██▉ | 1398/4692 [10:07<30:40, 1.79it/s] 30%|██▉ | 1399/4692 [10:08<30:45, 1.78it/s] 30%|██▉ | 1400/4692 [10:08<30:38, 1.79it/s] 30%|██▉ | 1401/4692 [10:09<30:50, 1.78it/s] 30%|██▉ | 1402/4692 [10:09<30:58, 1.77it/s] 30%|██▉ | 1403/4692 [10:10<30:58, 1.77it/s] 30%|██▉ | 1404/4692 [10:10<30:53, 1.77it/s] 30%|██▉ | 1405/4692 [10:11<30:44, 1.78it/s] 30%|██▉ | 1406/4692 [10:12<30:52, 1.77it/s] 30%|██▉ | 1407/4692 [10:12<30:59, 1.77it/s] 30%|███ | 1408/4692 [10:13<30:49, 1.78it/s] 30%|███ | 1409/4692 [10:13<30:36, 1.79it/s] 30%|███ | 1410/4692 [10:14<30:41, 1.78it/s] 30%|███ | 1411/4692 [10:14<30:48, 1.78it/s] 30%|███ | 1412/4692 [10:15<30:42, 1.78it/s] 30%|███ | 1413/4692 [10:15<30:33, 1.79it/s] 30%|███ | 1414/4692 [10:16<30:28, 1.79it/s] 30%|███ | 1415/4692 [10:17<30:35, 1.79it/s] 30%|███ | 1416/4692 [10:17<30:42, 1.78it/s] 30%|███ | 1417/4692 [10:18<30:42, 1.78it/s] 30%|███ | 1418/4692 [10:18<30:36, 1.78it/s] 30%|███ | 1419/4692 [10:19<30:34, 1.78it/s] 30%|███ | 1420/4692 [10:19<30:36, 1.78it/s] 30%|███ | 1421/4692 [10:20<30:36, 1.78it/s] 30%|███ | 1422/4692 [10:21<30:31, 1.78it/s] 30%|███ | 1423/4692 [10:21<30:26, 1.79it/s] 30%|███ | 1424/4692 [10:22<30:26, 1.79it/s] 30%|███ | 1425/4692 [10:22<30:32, 1.78it/s] 30%|███ | 1426/4692 [10:23<30:46, 1.77it/s] 30%|███ | 1427/4692 [10:23<30:50, 1.76it/s] 30%|███ | 1428/4692 [10:24<30:45, 1.77it/s] 30%|███ | 1429/4692 [10:24<30:43, 1.77it/s] 30%|███ | 1430/4692 [10:25<30:46, 1.77it/s] 30%|███ | 1431/4692 [10:26<30:49, 1.76it/s] 31%|███ | 1432/4692 [10:26<31:03, 1.75it/s] 31%|███ | 1433/4692 [10:27<30:55, 1.76it/s] 31%|███ | 1434/4692 [10:27<30:48, 1.76it/s] 31%|███ | 1435/4692 [10:28<30:43, 1.77it/s] 31%|███ | 1436/4692 [10:28<30:43, 1.77it/s] 31%|███ | 1437/4692 [10:29<30:43, 1.77it/s] 31%|███ | 1438/4692 [10:30<30:40, 1.77it/s] 31%|███ | 1439/4692 [10:30<30:28, 1.78it/s] 31%|███ | 1440/4692 [10:31<30:17, 1.79it/s] 31%|███ | 1441/4692 [10:31<30:26, 1.78it/s] 31%|███ | 1442/4692 [10:32<30:35, 1.77it/s] 31%|███ | 1443/4692 [10:32<30:29, 1.78it/s] 31%|███ | 1444/4692 [10:33<30:24, 1.78it/s] 31%|███ | 1445/4692 [10:34<30:24, 1.78it/s] 31%|███ | 1446/4692 [10:34<30:46, 1.76it/s] 31%|███ | 1447/4692 [10:35<30:38, 1.77it/s] 31%|███ | 1448/4692 [10:35<30:36, 1.77it/s] 31%|███ | 1449/4692 [10:36<30:56, 1.75it/s] 31%|███ | 1450/4692 [10:36<30:41, 1.76it/s] 31%|███ | 1451/4692 [10:37<30:43, 1.76it/s] 31%|███ | 1452/4692 [10:38<30:57, 1.74it/s] 31%|███ | 1453/4692 [10:38<30:34, 1.77it/s] 31%|███ | 1454/4692 [10:39<30:39, 1.76it/s] 31%|███ | 1455/4692 [10:39<30:45, 1.75it/s] 31%|███ | 1456/4692 [10:40<30:24, 1.77it/s] 31%|███ | 1457/4692 [10:40<30:36, 1.76it/s] 31%|███ | 1458/4692 [10:41<30:38, 1.76it/s] 31%|███ | 1459/4692 [10:41<30:29, 1.77it/s] 31%|███ | 1460/4692 [10:42<30:49, 1.75it/s] 31%|███ | 1461/4692 [10:43<30:36, 1.76it/s] 31%|███ | 1462/4692 [10:43<30:32, 1.76it/s] 31%|███ | 1463/4692 [10:44<30:48, 1.75it/s] 31%|███ | 1464/4692 [10:44<30:33, 1.76it/s] 31%|███ | 1465/4692 [10:45<30:35, 1.76it/s] 31%|███ | 1466/4692 [10:45<30:50, 1.74it/s] 31%|███▏ | 1467/4692 [10:46<30:33, 1.76it/s] 31%|███▏ | 1468/4692 [10:47<30:44, 1.75it/s] 31%|███▏ | 1469/4692 [10:47<30:58, 1.73it/s] 31%|███▏ | 1470/4692 [10:48<30:42, 1.75it/s] 31%|███▏ | 1471/4692 [10:48<30:54, 1.74it/s] 31%|███▏ | 1472/4692 [10:49<31:00, 1.73it/s] 31%|███▏ | 1473/4692 [10:49<30:39, 1.75it/s] 31%|███▏ | 1474/4692 [10:50<30:56, 1.73it/s] 31%|███▏ | 1475/4692 [10:51<30:41, 1.75it/s] 31%|███▏ | 1476/4692 [10:51<30:31, 1.76it/s] 31%|███▏ | 1477/4692 [10:52<30:47, 1.74it/s] 32%|███▏ | 1478/4692 [10:52<30:31, 1.75it/s] 32%|███▏ | 1479/4692 [10:53<30:22, 1.76it/s] 32%|███▏ | 1480/4692 [10:53<30:41, 1.74it/s] 32%|███▏ | 1481/4692 [10:54<30:20, 1.76it/s] 32%|███▏ | 1482/4692 [10:55<30:25, 1.76it/s] 32%|███▏ | 1483/4692 [10:55<30:38, 1.75it/s] 32%|███▏ | 1484/4692 [10:56<30:19, 1.76it/s] 32%|███▏ | 1485/4692 [10:56<30:35, 1.75it/s] 32%|███▏ | 1486/4692 [10:57<30:31, 1.75it/s] 32%|███▏ | 1487/4692 [10:57<30:22, 1.76it/s] 32%|███▏ | 1488/4692 [10:58<30:37, 1.74it/s] 32%|███▏ | 1489/4692 [10:59<30:19, 1.76it/s] 32%|███▏ | 1490/4692 [10:59<30:16, 1.76it/s] 32%|███▏ | 1491/4692 [11:00<30:36, 1.74it/s] 32%|███▏ | 1492/4692 [11:00<30:20, 1.76it/s] 32%|███▏ | 1493/4692 [11:01<30:23, 1.75it/s] 32%|███▏ | 1494/4692 [11:01<30:38, 1.74it/s] 32%|███▏ | 1495/4692 [11:02<30:19, 1.76it/s] 32%|███▏ | 1496/4692 [11:03<30:23, 1.75it/s] 32%|███▏ | 1497/4692 [11:03<30:35, 1.74it/s] 32%|███▏ | 1498/4692 [11:04<30:18, 1.76it/s] 32%|███▏ | 1499/4692 [11:04<30:33, 1.74it/s] 32%|███▏ | 1500/4692 [11:05<30:40, 1.73it/s] 32%|███▏ | 1500/4692 [11:05<30:40, 1.73it/s] 32%|███▏ | 1501/4692 [11:05<30:23, 1.75it/s] 32%|███▏ | 1502/4692 [11:06<30:36, 1.74it/s] 32%|███▏ | 1503/4692 [11:07<30:24, 1.75it/s] 32%|███▏ | 1504/4692 [11:07<30:21, 1.75it/s] 32%|███▏ | 1505/4692 [11:08<30:36, 1.74it/s] 32%|███▏ | 1506/4692 [11:08<30:17, 1.75it/s] 32%|███▏ | 1507/4692 [11:09<30:27, 1.74it/s] 32%|███▏ | 1508/4692 [11:10<30:39, 1.73it/s] 32%|███▏ | 1509/4692 [11:10<30:18, 1.75it/s] 32%|███▏ | 1510/4692 [11:11<30:19, 1.75it/s] 32%|███▏ | 1511/4692 [11:11<30:26, 1.74it/s] 32%|███▏ | 1512/4692 [11:12<30:10, 1.76it/s] 32%|███▏ | 1513/4692 [11:12<30:11, 1.76it/s] 32%|███▏ | 1514/4692 [11:13<30:23, 1.74it/s] 32%|███▏ | 1515/4692 [11:13<30:06, 1.76it/s] 32%|███▏ | 1516/4692 [11:14<30:09, 1.76it/s] 32%|███▏ | 1517/4692 [11:15<30:24, 1.74it/s] 32%|███▏ | 1518/4692 [11:15<30:02, 1.76it/s] 32%|███▏ | 1519/4692 [11:16<30:18, 1.75it/s] 32%|███▏ | 1520/4692 [11:16<30:32, 1.73it/s] 32%|███▏ | 1521/4692 [11:17<30:06, 1.76it/s] 32%|███▏ | 1522/4692 [11:18<30:26, 1.74it/s] 32%|███▏ | 1523/4692 [11:18<30:23, 1.74it/s] 32%|███▏ | 1524/4692 [11:19<30:16, 1.74it/s] 33%|███▎ | 1525/4692 [11:19<30:27, 1.73it/s] 33%|███▎ | 1526/4692 [11:20<30:11, 1.75it/s] 33%|███▎ | 1527/4692 [11:20<30:12, 1.75it/s] 33%|███▎ | 1528/4692 [11:21<30:25, 1.73it/s] 33%|███▎ | 1529/4692 [11:22<30:04, 1.75it/s] 33%|███▎ | 1530/4692 [11:22<30:04, 1.75it/s] 33%|███▎ | 1531/4692 [11:23<30:22, 1.73it/s] 33%|███▎ | 1532/4692 [11:23<30:04, 1.75it/s] 33%|███▎ | 1533/4692 [11:24<30:07, 1.75it/s] 33%|███▎ | 1534/4692 [11:24<30:22, 1.73it/s] 33%|███▎ | 1535/4692 [11:25<30:04, 1.75it/s] 33%|███▎ | 1536/4692 [11:26<30:02, 1.75it/s] 33%|███▎ | 1537/4692 [11:26<30:15, 1.74it/s] 33%|███▎ | 1538/4692 [11:27<29:55, 1.76it/s] 33%|███▎ | 1539/4692 [11:27<29:58, 1.75it/s] 33%|███▎ | 1540/4692 [11:28<30:13, 1.74it/s] 33%|███▎ | 1541/4692 [11:28<29:57, 1.75it/s] 33%|███▎ | 1542/4692 [11:29<30:04, 1.75it/s] 33%|███▎ | 1543/4692 [11:30<30:19, 1.73it/s] 33%|███▎ | 1544/4692 [11:30<30:04, 1.74it/s] 33%|███▎ | 1545/4692 [11:31<30:10, 1.74it/s] 33%|███▎ | 1546/4692 [11:31<30:23, 1.73it/s] 33%|███▎ | 1547/4692 [11:32<30:05, 1.74it/s] 33%|███▎ | 1548/4692 [11:32<30:12, 1.73it/s] 33%|███▎ | 1549/4692 [11:33<30:22, 1.72it/s] 33%|███▎ | 1550/4692 [11:34<30:05, 1.74it/s] 33%|███▎ | 1551/4692 [11:34<30:15, 1.73it/s] 33%|███▎ | 1552/4692 [11:35<30:22, 1.72it/s] 33%|███▎ | 1553/4692 [11:35<30:02, 1.74it/s] 33%|███▎ | 1554/4692 [11:36<30:08, 1.73it/s] 33%|███▎ | 1555/4692 [11:36<29:50, 1.75it/s] 33%|███▎ | 1556/4692 [11:37<29:46, 1.76it/s] 33%|███▎ | 1557/4692 [11:38<29:57, 1.74it/s] 33%|███▎ | 1558/4692 [11:38<29:40, 1.76it/s] 33%|███▎ | 1559/4692 [11:39<29:44, 1.76it/s] 33%|███▎ | 1560/4692 [11:39<29:58, 1.74it/s] 33%|███▎ | 1561/4692 [11:40<29:36, 1.76it/s] 33%|███▎ | 1562/4692 [11:40<29:51, 1.75it/s] 33%|███▎ | 1563/4692 [11:41<29:30, 1.77it/s] 33%|███▎ | 1564/4692 [11:41<23:50, 2.19it/s][INFO|trainer.py:738] 2023-07-03 01:19:18,637 >> The following columns in the evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: text. If text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3069] 2023-07-03 01:19:18,640 >> ***** Running Evaluation ***** [INFO|trainer.py:3071] 2023-07-03 01:19:18,641 >> Num examples = 25000 [INFO|trainer.py:3074] 2023-07-03 01:19:18,641 >> Batch size = 64 0%| | 0/391 [00:00> Saving model checkpoint to /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-1564 [INFO|configuration_utils.py:457] 2023-07-03 01:21:28,961 >> Configuration saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-1564/config.json [INFO|modeling_utils.py:1762] 2023-07-03 01:21:29,520 >> Model weights saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-1564/pytorch_model.bin [INFO|tokenization_utils_base.py:2163] 2023-07-03 01:21:29,521 >> tokenizer config file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-1564/tokenizer_config.json [INFO|tokenization_utils_base.py:2170] 2023-07-03 01:21:29,521 >> Special tokens file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-1564/special_tokens_map.json [INFO|trainer.py:2893] 2023-07-03 01:21:30,678 >> Deleting older checkpoint [/nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-1173] due to args.save_total_limit 33%|███▎ | 1565/4692 [13:54<34:52:06, 40.14s/it] 33%|███▎ | 1566/4692 [13:55<24:32:49, 28.27s/it] 33%|███▎ | 1567/4692 [13:55<17:19:09, 19.95s/it] 33%|███▎ | 1568/4692 [13:56<12:15:50, 14.13s/it] 33%|███▎ | 1569/4692 [13:56<8:43:43, 10.06s/it] 33%|███▎ | 1570/4692 [13:57<6:15:01, 7.21s/it] 33%|███▎ | 1571/4692 [13:57<4:30:49, 5.21s/it] 34%|███▎ | 1572/4692 [13:58<3:18:17, 3.81s/it] 34%|███▎ | 1573/4692 [13:58<2:27:22, 2.84s/it] 34%|███▎ | 1574/4692 [13:59<1:51:37, 2.15s/it] 34%|███▎ | 1575/4692 [13:59<1:26:52, 1.67s/it] 34%|███▎ | 1576/4692 [14:00<1:09:23, 1.34s/it] 34%|███▎ | 1577/4692 [14:01<57:03, 1.10s/it] 34%|███▎ | 1578/4692 [14:01<48:39, 1.07it/s] 34%|███▎ | 1579/4692 [14:02<42:33, 1.22it/s] 34%|███▎ | 1580/4692 [14:02<38:17, 1.35it/s] 34%|███▎ | 1581/4692 [14:03<35:27, 1.46it/s] 34%|███▎ | 1582/4692 [14:03<33:26, 1.55it/s] 34%|███▎ | 1583/4692 [14:04<31:59, 1.62it/s] 34%|███▍ | 1584/4692 [14:04<31:06, 1.67it/s] 34%|███▍ | 1585/4692 [14:05<30:29, 1.70it/s] 34%|███▍ | 1586/4692 [14:06<29:36, 1.75it/s] 34%|███▍ | 1587/4692 [14:06<29:36, 1.75it/s] 34%|███▍ | 1588/4692 [14:07<29:15, 1.77it/s] 34%|███▍ | 1589/4692 [14:07<29:16, 1.77it/s] 34%|███▍ | 1590/4692 [14:08<29:22, 1.76it/s] 34%|███▍ | 1591/4692 [14:08<29:06, 1.78it/s] 34%|███▍ | 1592/4692 [14:09<29:24, 1.76it/s] 34%|███▍ | 1593/4692 [14:10<29:09, 1.77it/s] 34%|███▍ | 1594/4692 [14:10<28:57, 1.78it/s] 34%|███▍ | 1595/4692 [14:11<29:11, 1.77it/s] 34%|███▍ | 1596/4692 [14:11<28:59, 1.78it/s] 34%|███▍ | 1597/4692 [14:12<29:07, 1.77it/s] 34%|███▍ | 1598/4692 [14:12<28:58, 1.78it/s] 34%|███▍ | 1599/4692 [14:13<28:44, 1.79it/s] 34%|███▍ | 1600/4692 [14:13<29:05, 1.77it/s] 34%|███▍ | 1601/4692 [14:14<28:53, 1.78it/s] 34%|███▍ | 1602/4692 [14:15<29:10, 1.77it/s] 34%|███▍ | 1603/4692 [14:15<29:11, 1.76it/s] 34%|███▍ | 1604/4692 [14:16<29:02, 1.77it/s] 34%|███▍ | 1605/4692 [14:16<29:11, 1.76it/s] 34%|███▍ | 1606/4692 [14:17<28:49, 1.78it/s] 34%|███▍ | 1607/4692 [14:17<28:57, 1.78it/s] 34%|███▍ | 1608/4692 [14:18<29:03, 1.77it/s] 34%|███▍ | 1609/4692 [14:19<28:58, 1.77it/s] 34%|███▍ | 1610/4692 [14:19<29:02, 1.77it/s] 34%|███▍ | 1611/4692 [14:20<28:46, 1.78it/s] 34%|███▍ | 1612/4692 [14:20<28:51, 1.78it/s] 34%|███▍ | 1613/4692 [14:21<28:54, 1.78it/s] 34%|███▍ | 1614/4692 [14:21<28:49, 1.78it/s] 34%|███▍ | 1615/4692 [14:22<28:54, 1.77it/s] 34%|███▍ | 1616/4692 [14:22<28:44, 1.78it/s] 34%|███▍ | 1617/4692 [14:23<28:49, 1.78it/s] 34%|███▍ | 1618/4692 [14:24<29:03, 1.76it/s] 35%|███▍ | 1619/4692 [14:24<28:42, 1.78it/s] 35%|███▍ | 1620/4692 [14:25<29:01, 1.76it/s] 35%|███▍ | 1621/4692 [14:25<28:43, 1.78it/s] 35%|███▍ | 1622/4692 [14:26<28:32, 1.79it/s] 35%|███▍ | 1623/4692 [14:26<28:48, 1.78it/s] 35%|███▍ | 1624/4692 [14:27<28:39, 1.78it/s] 35%|███▍ | 1625/4692 [14:28<28:51, 1.77it/s] 35%|███▍ | 1626/4692 [14:28<28:41, 1.78it/s] 35%|███▍ | 1627/4692 [14:29<28:43, 1.78it/s] 35%|███▍ | 1628/4692 [14:29<28:54, 1.77it/s] 35%|███▍ | 1629/4692 [14:30<28:39, 1.78it/s] 35%|███▍ | 1630/4692 [14:30<28:53, 1.77it/s] 35%|███▍ | 1631/4692 [14:31<28:52, 1.77it/s] 35%|███▍ | 1632/4692 [14:31<28:45, 1.77it/s] 35%|███▍ | 1633/4692 [14:32<28:53, 1.76it/s] 35%|███▍ | 1634/4692 [14:33<28:25, 1.79it/s] 35%|███▍ | 1635/4692 [14:33<28:42, 1.77it/s] 35%|███▍ | 1636/4692 [14:34<28:45, 1.77it/s] 35%|███▍ | 1637/4692 [14:34<28:35, 1.78it/s] 35%|███▍ | 1638/4692 [14:35<28:46, 1.77it/s] 35%|███▍ | 1639/4692 [14:35<28:33, 1.78it/s] 35%|███▍ | 1640/4692 [14:36<28:36, 1.78it/s] 35%|███▍ | 1641/4692 [14:37<28:45, 1.77it/s] 35%|███▍ | 1642/4692 [14:37<28:29, 1.78it/s] 35%|███▌ | 1643/4692 [14:38<28:42, 1.77it/s] 35%|███▌ | 1644/4692 [14:38<28:24, 1.79it/s] 35%|███▌ | 1645/4692 [14:39<28:28, 1.78it/s] 35%|███▌ | 1646/4692 [14:39<28:41, 1.77it/s] 35%|███▌ | 1647/4692 [14:40<28:28, 1.78it/s] 35%|███▌ | 1648/4692 [14:40<28:45, 1.76it/s] 35%|███▌ | 1649/4692 [14:41<28:33, 1.78it/s] 35%|███▌ | 1650/4692 [14:42<28:25, 1.78it/s] 35%|███▌ | 1651/4692 [14:42<28:35, 1.77it/s] 35%|███▌ | 1652/4692 [14:43<28:19, 1.79it/s] 35%|███▌ | 1653/4692 [14:43<28:37, 1.77it/s] 35%|███▌ | 1654/4692 [14:44<28:32, 1.77it/s] 35%|███▌ | 1655/4692 [14:44<28:19, 1.79it/s] 35%|███▌ | 1656/4692 [14:45<28:29, 1.78it/s] 35%|███▌ | 1657/4692 [14:46<28:18, 1.79it/s] 35%|███▌ | 1658/4692 [14:46<28:36, 1.77it/s] 35%|███▌ | 1659/4692 [14:47<28:30, 1.77it/s] 35%|███▌ | 1660/4692 [14:47<28:23, 1.78it/s] 35%|███▌ | 1661/4692 [14:48<28:39, 1.76it/s] 35%|███▌ | 1662/4692 [14:48<28:20, 1.78it/s] 35%|███▌ | 1663/4692 [14:49<28:29, 1.77it/s] 35%|███▌ | 1664/4692 [14:49<28:31, 1.77it/s] 35%|███▌ | 1665/4692 [14:50<28:23, 1.78it/s] 36%|███▌ | 1666/4692 [14:51<28:31, 1.77it/s] 36%|███▌ | 1667/4692 [14:51<28:14, 1.79it/s] 36%|███▌ | 1668/4692 [14:52<28:25, 1.77it/s] 36%|███▌ | 1669/4692 [14:52<28:24, 1.77it/s] 36%|███▌ | 1670/4692 [14:53<28:24, 1.77it/s] 36%|███▌ | 1671/4692 [14:53<28:30, 1.77it/s] 36%|███▌ | 1672/4692 [14:54<28:17, 1.78it/s] 36%|███▌ | 1673/4692 [14:55<28:17, 1.78it/s] 36%|███▌ | 1674/4692 [14:55<28:21, 1.77it/s] 36%|███▌ | 1675/4692 [14:56<28:10, 1.78it/s] 36%|███▌ | 1676/4692 [14:56<28:25, 1.77it/s] 36%|███▌ | 1677/4692 [14:57<28:08, 1.79it/s] 36%|███▌ | 1678/4692 [14:57<28:17, 1.78it/s] 36%|███▌ | 1679/4692 [14:58<28:29, 1.76it/s] 36%|███▌ | 1680/4692 [14:58<28:10, 1.78it/s] 36%|███▌ | 1681/4692 [14:59<28:24, 1.77it/s] 36%|███▌ | 1682/4692 [15:00<28:10, 1.78it/s] 36%|███▌ | 1683/4692 [15:00<27:59, 1.79it/s] 36%|███▌ | 1684/4692 [15:01<28:15, 1.77it/s] 36%|███▌ | 1685/4692 [15:01<28:03, 1.79it/s] 36%|███▌ | 1686/4692 [15:02<28:17, 1.77it/s] 36%|███▌ | 1687/4692 [15:02<28:04, 1.78it/s] 36%|███▌ | 1688/4692 [15:03<27:59, 1.79it/s] 36%|███▌ | 1689/4692 [15:04<28:09, 1.78it/s] 36%|███▌ | 1690/4692 [15:04<27:56, 1.79it/s] 36%|███▌ | 1691/4692 [15:05<28:07, 1.78it/s] 36%|███▌ | 1692/4692 [15:05<27:51, 1.79it/s] 36%|███▌ | 1693/4692 [15:06<27:43, 1.80it/s] 36%|███▌ | 1694/4692 [15:06<27:57, 1.79it/s] 36%|███▌ | 1695/4692 [15:07<27:46, 1.80it/s] 36%|███▌ | 1696/4692 [15:07<28:08, 1.77it/s] 36%|███▌ | 1697/4692 [15:08<27:55, 1.79it/s] 36%|███▌ | 1698/4692 [15:09<27:50, 1.79it/s] 36%|███▌ | 1699/4692 [15:09<28:12, 1.77it/s] 36%|███▌ | 1700/4692 [15:10<28:04, 1.78it/s] 36%|███▋ | 1701/4692 [15:10<28:09, 1.77it/s] 36%|███▋ | 1702/4692 [15:11<28:24, 1.75it/s] 36%|███▋ | 1703/4692 [15:11<28:10, 1.77it/s] 36%|███▋ | 1704/4692 [15:12<28:19, 1.76it/s] 36%|███▋ | 1705/4692 [15:13<28:30, 1.75it/s] 36%|███▋ | 1706/4692 [15:13<28:15, 1.76it/s] 36%|███▋ | 1707/4692 [15:14<28:25, 1.75it/s] 36%|███▋ | 1708/4692 [15:14<28:27, 1.75it/s] 36%|███▋ | 1709/4692 [15:15<28:12, 1.76it/s] 36%|███▋ | 1710/4692 [15:15<28:22, 1.75it/s] 36%|███▋ | 1711/4692 [15:16<28:04, 1.77it/s] 36%|███▋ | 1712/4692 [15:17<28:13, 1.76it/s] 37%|███▋ | 1713/4692 [15:17<28:23, 1.75it/s] 37%|███▋ | 1714/4692 [15:18<28:11, 1.76it/s] 37%|███▋ | 1715/4692 [15:18<28:08, 1.76it/s] 37%|███▋ | 1716/4692 [15:19<28:19, 1.75it/s] 37%|███▋ | 1717/4692 [15:19<28:06, 1.76it/s] 37%|███▋ | 1718/4692 [15:20<28:06, 1.76it/s] 37%|███▋ | 1719/4692 [15:21<28:14, 1.75it/s] 37%|███▋ | 1720/4692 [15:21<27:53, 1.78it/s] 37%|███▋ | 1721/4692 [15:22<28:04, 1.76it/s] 37%|███▋ | 1722/4692 [15:22<28:14, 1.75it/s] 37%|███▋ | 1723/4692 [15:23<27:54, 1.77it/s] 37%|███▋ | 1724/4692 [15:23<28:09, 1.76it/s] 37%|███▋ | 1725/4692 [15:24<27:57, 1.77it/s] 37%|███▋ | 1726/4692 [15:24<27:59, 1.77it/s] 37%|███▋ | 1727/4692 [15:25<28:08, 1.76it/s] 37%|███▋ | 1728/4692 [15:26<27:54, 1.77it/s] 37%|███▋ | 1729/4692 [15:26<27:56, 1.77it/s] 37%|███▋ | 1730/4692 [15:27<28:12, 1.75it/s] 37%|███▋ | 1731/4692 [15:27<27:58, 1.76it/s] 37%|███▋ | 1732/4692 [15:28<27:55, 1.77it/s] 37%|███▋ | 1733/4692 [15:28<28:13, 1.75it/s] 37%|███▋ | 1734/4692 [15:29<28:00, 1.76it/s] 37%|███▋ | 1735/4692 [15:30<27:57, 1.76it/s] 37%|███▋ | 1736/4692 [15:30<28:12, 1.75it/s] 37%|███▋ | 1737/4692 [15:31<27:57, 1.76it/s] 37%|███▋ | 1738/4692 [15:31<27:55, 1.76it/s] 37%|███▋ | 1739/4692 [15:32<28:13, 1.74it/s] 37%|███▋ | 1740/4692 [15:32<27:57, 1.76it/s] 37%|███▋ | 1741/4692 [15:33<28:06, 1.75it/s] 37%|███▋ | 1742/4692 [15:34<28:14, 1.74it/s] 37%|███▋ | 1743/4692 [15:34<27:58, 1.76it/s] 37%|███▋ | 1744/4692 [15:35<28:08, 1.75it/s] 37%|███▋ | 1745/4692 [15:35<28:07, 1.75it/s] 37%|███▋ | 1746/4692 [15:36<27:56, 1.76it/s] 37%|███▋ | 1747/4692 [15:36<28:07, 1.74it/s] 37%|███▋ | 1748/4692 [15:37<27:54, 1.76it/s] 37%|███▋ | 1749/4692 [15:38<27:58, 1.75it/s] 37%|███▋ | 1750/4692 [15:38<28:05, 1.75it/s] 37%|███▋ | 1751/4692 [15:39<27:51, 1.76it/s] 37%|███▋ | 1752/4692 [15:39<27:48, 1.76it/s] 37%|███▋ | 1753/4692 [15:40<27:59, 1.75it/s] 37%|███▋ | 1754/4692 [15:40<27:40, 1.77it/s] 37%|███▋ | 1755/4692 [15:41<27:44, 1.76it/s] 37%|███▋ | 1756/4692 [15:42<27:54, 1.75it/s] 37%|███▋ | 1757/4692 [15:42<27:41, 1.77it/s] 37%|███▋ | 1758/4692 [15:43<27:53, 1.75it/s] 37%|███▋ | 1759/4692 [15:43<27:44, 1.76it/s] 38%|███▊ | 1760/4692 [15:44<27:42, 1.76it/s] 38%|███▊ | 1761/4692 [15:44<27:55, 1.75it/s] 38%|███▊ | 1762/4692 [15:45<27:41, 1.76it/s] 38%|███▊ | 1763/4692 [15:46<27:42, 1.76it/s] 38%|███▊ | 1764/4692 [15:46<27:56, 1.75it/s] 38%|███▊ | 1765/4692 [15:47<27:43, 1.76it/s] 38%|███▊ | 1766/4692 [15:47<27:43, 1.76it/s] 38%|███▊ | 1767/4692 [15:48<27:58, 1.74it/s] 38%|███▊ | 1768/4692 [15:48<27:45, 1.76it/s] 38%|███▊ | 1769/4692 [15:49<27:45, 1.76it/s] 38%|███▊ | 1770/4692 [15:50<27:56, 1.74it/s] 38%|███▊ | 1771/4692 [15:50<27:36, 1.76it/s] 38%|███▊ | 1772/4692 [15:51<27:37, 1.76it/s] 38%|███▊ | 1773/4692 [15:51<27:46, 1.75it/s] 38%|███▊ | 1774/4692 [15:52<27:29, 1.77it/s] 38%|███▊ | 1775/4692 [15:52<27:43, 1.75it/s] 38%|███▊ | 1776/4692 [15:53<27:44, 1.75it/s] 38%|███▊ | 1777/4692 [15:54<27:35, 1.76it/s] 38%|███▊ | 1778/4692 [15:54<27:49, 1.75it/s] 38%|███▊ | 1779/4692 [15:55<27:31, 1.76it/s] 38%|███▊ | 1780/4692 [15:55<27:32, 1.76it/s] 38%|███▊ | 1781/4692 [15:56<27:45, 1.75it/s] 38%|███▊ | 1782/4692 [15:56<27:29, 1.76it/s] 38%|███▊ | 1783/4692 [15:57<27:35, 1.76it/s] 38%|███▊ | 1784/4692 [15:58<27:51, 1.74it/s] 38%|███▊ | 1785/4692 [15:58<27:30, 1.76it/s] 38%|███▊ | 1786/4692 [15:59<27:39, 1.75it/s] 38%|███▊ | 1787/4692 [15:59<27:27, 1.76it/s] 38%|███▊ | 1788/4692 [16:00<27:22, 1.77it/s] 38%|███▊ | 1789/4692 [16:00<27:33, 1.76it/s] 38%|███▊ | 1790/4692 [16:01<27:14, 1.78it/s] 38%|███▊ | 1791/4692 [16:02<27:29, 1.76it/s] 38%|███▊ | 1792/4692 [16:02<27:38, 1.75it/s] 38%|███▊ | 1793/4692 [16:03<27:23, 1.76it/s] 38%|███▊ | 1794/4692 [16:03<27:36, 1.75it/s] 38%|███▊ | 1795/4692 [16:04<27:23, 1.76it/s] 38%|███▊ | 1796/4692 [16:04<27:27, 1.76it/s] 38%|███▊ | 1797/4692 [16:05<27:39, 1.74it/s] 38%|███▊ | 1798/4692 [16:05<27:21, 1.76it/s] 38%|███▊ | 1799/4692 [16:06<27:26, 1.76it/s] 38%|███▊ | 1800/4692 [16:07<27:41, 1.74it/s] 38%|███▊ | 1801/4692 [16:07<27:21, 1.76it/s] 38%|███▊ | 1802/4692 [16:08<27:32, 1.75it/s] 38%|███▊ | 1803/4692 [16:08<27:13, 1.77it/s] 38%|███▊ | 1804/4692 [16:09<27:15, 1.77it/s] 38%|███▊ | 1805/4692 [16:09<27:19, 1.76it/s] 38%|███▊ | 1806/4692 [16:10<27:07, 1.77it/s] 39%|███▊ | 1807/4692 [16:11<27:25, 1.75it/s] 39%|███▊ | 1808/4692 [16:11<27:38, 1.74it/s] 39%|███▊ | 1809/4692 [16:12<27:16, 1.76it/s] 39%|███▊ | 1810/4692 [16:12<27:28, 1.75it/s] 39%|███▊ | 1811/4692 [16:13<27:12, 1.76it/s] 39%|███▊ | 1812/4692 [16:13<27:10, 1.77it/s] 39%|███▊ | 1813/4692 [16:14<27:27, 1.75it/s] 39%|███▊ | 1814/4692 [16:15<27:14, 1.76it/s] 39%|███▊ | 1815/4692 [16:15<27:22, 1.75it/s] 39%|███▊ | 1816/4692 [16:16<27:37, 1.74it/s] 39%|███▊ | 1817/4692 [16:16<27:06, 1.77it/s] 39%|███▊ | 1818/4692 [16:17<27:18, 1.75it/s] 39%|███▉ | 1819/4692 [16:17<27:03, 1.77it/s] 39%|███▉ | 1820/4692 [16:18<27:06, 1.77it/s] 39%|███▉ | 1821/4692 [16:19<27:25, 1.75it/s] 39%|███▉ | 1822/4692 [16:19<27:07, 1.76it/s] 39%|███▉ | 1823/4692 [16:20<27:13, 1.76it/s] 39%|███▉ | 1824/4692 [16:20<27:27, 1.74it/s] 39%|███▉ | 1825/4692 [16:21<26:57, 1.77it/s] 39%|███▉ | 1826/4692 [16:21<27:13, 1.75it/s] 39%|███▉ | 1827/4692 [16:22<24:55, 1.92it/s] 39%|███▉ | 1828/4692 [16:22<21:26, 2.23it/s] 39%|███▉ | 1829/4692 [16:22<19:00, 2.51it/s] 39%|███▉ | 1830/4692 [16:23<17:19, 2.75it/s] 39%|███▉ | 1831/4692 [16:23<16:08, 2.95it/s] 39%|███▉ | 1832/4692 [16:23<15:18, 3.11it/s] 39%|███▉ | 1833/4692 [16:24<14:42, 3.24it/s] 39%|███▉ | 1834/4692 [16:24<14:35, 3.26it/s] 39%|███▉ | 1835/4692 [16:24<18:04, 2.63it/s] 39%|███▉ | 1836/4692 [16:25<20:46, 2.29it/s] 39%|███▉ | 1837/4692 [16:26<22:35, 2.11it/s] 39%|███▉ | 1838/4692 [16:26<23:43, 2.00it/s] 39%|███▉ | 1839/4692 [16:27<24:25, 1.95it/s] 39%|███▉ | 1840/4692 [16:27<24:57, 1.90it/s] 39%|███▉ | 1841/4692 [16:28<25:27, 1.87it/s] 39%|███▉ | 1842/4692 [16:28<25:39, 1.85it/s] 39%|███▉ | 1843/4692 [16:29<26:03, 1.82it/s] 39%|███▉ | 1844/4692 [16:29<26:09, 1.81it/s] 39%|███▉ | 1845/4692 [16:30<26:21, 1.80it/s] 39%|███▉ | 1846/4692 [16:31<26:29, 1.79it/s] 39%|███▉ | 1847/4692 [16:31<26:35, 1.78it/s] 39%|███▉ | 1848/4692 [16:32<26:28, 1.79it/s] 39%|███▉ | 1849/4692 [16:32<26:18, 1.80it/s] 39%|███▉ | 1850/4692 [16:33<26:23, 1.79it/s] 39%|███▉ | 1851/4692 [16:33<26:18, 1.80it/s] 39%|███▉ | 1852/4692 [16:34<26:26, 1.79it/s] 39%|███▉ | 1853/4692 [16:34<26:32, 1.78it/s] 40%|███▉ | 1854/4692 [16:35<26:30, 1.78it/s] 40%|███▉ | 1855/4692 [16:36<26:34, 1.78it/s] 40%|███▉ | 1856/4692 [16:36<26:27, 1.79it/s] 40%|███▉ | 1857/4692 [16:37<26:30, 1.78it/s] 40%|███▉ | 1858/4692 [16:37<26:33, 1.78it/s] 40%|███▉ | 1859/4692 [16:38<26:33, 1.78it/s] 40%|███▉ | 1860/4692 [16:38<26:36, 1.77it/s] 40%|███▉ | 1861/4692 [16:39<26:31, 1.78it/s] 40%|███▉ | 1862/4692 [16:40<26:30, 1.78it/s] 40%|███▉ | 1863/4692 [16:40<26:29, 1.78it/s] 40%|███▉ | 1864/4692 [16:41<26:35, 1.77it/s] 40%|███▉ | 1865/4692 [16:41<26:32, 1.77it/s] 40%|███▉ | 1866/4692 [16:42<26:26, 1.78it/s] 40%|███▉ | 1867/4692 [16:42<26:29, 1.78it/s] 40%|███▉ | 1868/4692 [16:43<26:26, 1.78it/s] 40%|███▉ | 1869/4692 [16:43<26:22, 1.78it/s] 40%|███▉ | 1870/4692 [16:44<26:18, 1.79it/s] 40%|███▉ | 1871/4692 [16:45<26:13, 1.79it/s] 40%|███▉ | 1872/4692 [16:45<26:17, 1.79it/s] 40%|███▉ | 1873/4692 [16:46<26:07, 1.80it/s] 40%|███▉ | 1874/4692 [16:46<26:11, 1.79it/s] 40%|███▉ | 1875/4692 [16:47<26:12, 1.79it/s] 40%|███▉ | 1876/4692 [16:47<26:05, 1.80it/s] 40%|████ | 1877/4692 [16:48<25:47, 1.82it/s] 40%|████ | 1878/4692 [16:48<25:57, 1.81it/s] 40%|████ | 1879/4692 [16:49<25:52, 1.81it/s] 40%|████ | 1880/4692 [16:50<25:46, 1.82it/s] 40%|████ | 1881/4692 [16:50<25:56, 1.81it/s] 40%|████ | 1882/4692 [16:51<25:54, 1.81it/s] 40%|████ | 1883/4692 [16:51<25:55, 1.81it/s] 40%|████ | 1884/4692 [16:52<26:00, 1.80it/s] 40%|████ | 1885/4692 [16:52<26:04, 1.79it/s] 40%|████ | 1886/4692 [16:53<26:03, 1.79it/s] 40%|████ | 1887/4692 [16:53<25:50, 1.81it/s] 40%|████ | 1888/4692 [16:54<25:46, 1.81it/s] 40%|████ | 1889/4692 [16:55<25:55, 1.80it/s] 40%|████ | 1890/4692 [16:55<25:49, 1.81it/s] 40%|████ | 1891/4692 [16:56<25:44, 1.81it/s] 40%|████ | 1892/4692 [16:56<25:51, 1.80it/s] 40%|████ | 1893/4692 [16:57<25:49, 1.81it/s] 40%|████ | 1894/4692 [16:57<25:46, 1.81it/s] 40%|████ | 1895/4692 [16:58<25:45, 1.81it/s] 40%|████ | 1896/4692 [16:58<25:53, 1.80it/s] 40%|████ | 1897/4692 [16:59<25:54, 1.80it/s] 40%|████ | 1898/4692 [17:00<25:57, 1.79it/s] 40%|████ | 1899/4692 [17:00<26:00, 1.79it/s] 40%|████ | 1900/4692 [17:01<26:04, 1.79it/s] 41%|████ | 1901/4692 [17:01<25:55, 1.79it/s] 41%|████ | 1902/4692 [17:02<25:48, 1.80it/s] 41%|████ | 1903/4692 [17:02<25:53, 1.79it/s] 41%|████ | 1904/4692 [17:03<25:48, 1.80it/s] 41%|████ | 1905/4692 [17:03<25:50, 1.80it/s] 41%|████ | 1906/4692 [17:04<25:43, 1.80it/s] 41%|████ | 1907/4692 [17:05<25:48, 1.80it/s] 41%|████ | 1908/4692 [17:05<25:45, 1.80it/s] 41%|████ | 1909/4692 [17:06<25:48, 1.80it/s] 41%|████ | 1910/4692 [17:06<25:49, 1.80it/s] 41%|████ | 1911/4692 [17:07<25:52, 1.79it/s] 41%|████ | 1912/4692 [17:07<25:43, 1.80it/s] 41%|████ | 1913/4692 [17:08<25:35, 1.81it/s] 41%|████ | 1914/4692 [17:08<25:42, 1.80it/s] 41%|████ | 1915/4692 [17:09<25:50, 1.79it/s] 41%|████ | 1916/4692 [17:10<25:46, 1.80it/s] 41%|████ | 1917/4692 [17:10<25:39, 1.80it/s] 41%|████ | 1918/4692 [17:11<25:46, 1.79it/s] 41%|████ | 1919/4692 [17:11<25:45, 1.79it/s] 41%|████ | 1920/4692 [17:12<25:45, 1.79it/s] 41%|████ | 1921/4692 [17:12<25:39, 1.80it/s] 41%|████ | 1922/4692 [17:13<25:39, 1.80it/s] 41%|████ | 1923/4692 [17:13<25:35, 1.80it/s] 41%|████ | 1924/4692 [17:14<25:41, 1.80it/s] 41%|████ | 1925/4692 [17:15<25:46, 1.79it/s] 41%|████ | 1926/4692 [17:15<25:36, 1.80it/s] 41%|████ | 1927/4692 [17:16<25:36, 1.80it/s] 41%|████ | 1928/4692 [17:16<25:38, 1.80it/s] 41%|████ | 1929/4692 [17:17<25:39, 1.79it/s] 41%|████ | 1930/4692 [17:17<25:31, 1.80it/s] 41%|████ | 1931/4692 [17:18<25:28, 1.81it/s] 41%|████ | 1932/4692 [17:18<25:35, 1.80it/s] 41%|████ | 1933/4692 [17:19<25:33, 1.80it/s] 41%|████ | 1934/4692 [17:20<25:33, 1.80it/s] 41%|████ | 1935/4692 [17:20<25:33, 1.80it/s] 41%|████▏ | 1936/4692 [17:21<25:24, 1.81it/s] 41%|████▏ | 1937/4692 [17:21<25:10, 1.82it/s] 41%|████▏ | 1938/4692 [17:22<25:19, 1.81it/s] 41%|████▏ | 1939/4692 [17:22<25:19, 1.81it/s] 41%|████▏ | 1940/4692 [17:23<25:12, 1.82it/s] 41%|████▏ | 1941/4692 [17:23<25:22, 1.81it/s] 41%|████▏ | 1942/4692 [17:24<25:17, 1.81it/s] 41%|████▏ | 1943/4692 [17:24<25:10, 1.82it/s] 41%|████▏ | 1944/4692 [17:25<25:19, 1.81it/s] 41%|████▏ | 1945/4692 [17:26<25:16, 1.81it/s] 41%|████▏ | 1946/4692 [17:26<25:21, 1.80it/s] 41%|████▏ | 1947/4692 [17:27<25:24, 1.80it/s] 42%|████▏ | 1948/4692 [17:27<25:17, 1.81it/s] 42%|████▏ | 1949/4692 [17:28<25:06, 1.82it/s] 42%|████▏ | 1950/4692 [17:28<25:12, 1.81it/s] 42%|████▏ | 1951/4692 [17:29<25:08, 1.82it/s] 42%|████▏ | 1952/4692 [17:29<25:06, 1.82it/s] 42%|████▏ | 1953/4692 [17:30<25:15, 1.81it/s] 42%|████▏ | 1954/4692 [17:31<25:09, 1.81it/s] 42%|████▏ | 1955/4692 [17:31<25:04, 1.82it/s][INFO|trainer.py:738] 2023-07-03 01:25:08,535 >> The following columns in the evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: text. If text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3069] 2023-07-03 01:25:08,537 >> ***** Running Evaluation ***** [INFO|trainer.py:3071] 2023-07-03 01:25:08,538 >> Num examples = 25000 [INFO|trainer.py:3074] 2023-07-03 01:25:08,538 >> Batch size = 64 0%| | 0/391 [00:00> Saving model checkpoint to /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-1955 [INFO|configuration_utils.py:457] 2023-07-03 01:27:22,150 >> Configuration saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-1955/config.json [INFO|modeling_utils.py:1762] 2023-07-03 01:27:22,688 >> Model weights saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-1955/pytorch_model.bin [INFO|tokenization_utils_base.py:2163] 2023-07-03 01:27:22,689 >> tokenizer config file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-1955/tokenizer_config.json [INFO|tokenization_utils_base.py:2170] 2023-07-03 01:27:22,689 >> Special tokens file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-1955/special_tokens_map.json 42%|████▏ | 1956/4692 [19:47<31:16:10, 41.14s/it] 42%|████▏ | 1957/4692 [19:48<22:00:20, 28.97s/it] 42%|████▏ | 1958/4692 [19:48<15:31:26, 20.44s/it] 42%|████▏ | 1959/4692 [19:49<10:59:37, 14.48s/it] 42%|████▏ | 1960/4692 [19:49<7:49:00, 10.30s/it] 42%|████▏ | 1961/4692 [19:50<5:36:09, 7.39s/it] 42%|████▏ | 1962/4692 [19:50<4:02:40, 5.33s/it] 42%|████▏ | 1963/4692 [19:51<2:57:28, 3.90s/it] 42%|████▏ | 1964/4692 [19:51<2:12:04, 2.90s/it] 42%|████▏ | 1965/4692 [19:52<1:39:59, 2.20s/it] 42%|████▏ | 1966/4692 [19:53<1:17:54, 1.71s/it] 42%|████▏ | 1967/4692 [19:53<1:01:59, 1.36s/it] 42%|████▏ | 1968/4692 [19:54<51:03, 1.12s/it] 42%|████▏ | 1969/4692 [19:54<43:39, 1.04it/s] 42%|████▏ | 1970/4692 [19:55<37:56, 1.20it/s] 42%|████▏ | 1971/4692 [19:55<34:21, 1.32it/s] 42%|████▏ | 1972/4692 [19:56<29:44, 1.52it/s] 42%|████▏ | 1973/4692 [19:56<24:27, 1.85it/s] 42%|████▏ | 1974/4692 [19:56<20:44, 2.18it/s] 42%|████▏ | 1975/4692 [19:57<18:10, 2.49it/s] 42%|████▏ | 1976/4692 [19:57<16:22, 2.76it/s] 42%|████▏ | 1977/4692 [19:57<15:06, 2.99it/s] 42%|████▏ | 1978/4692 [19:57<14:11, 3.19it/s] 42%|████▏ | 1979/4692 [19:58<13:33, 3.34it/s] 42%|████▏ | 1980/4692 [19:58<14:02, 3.22it/s] 42%|████▏ | 1981/4692 [19:59<17:18, 2.61it/s] 42%|████▏ | 1982/4692 [19:59<19:38, 2.30it/s] 42%|████▏ | 1983/4692 [20:00<21:18, 2.12it/s] 42%|████▏ | 1984/4692 [20:00<22:31, 2.00it/s] 42%|████▏ | 1985/4692 [20:01<23:09, 1.95it/s] 42%|████▏ | 1986/4692 [20:01<23:43, 1.90it/s] 42%|████▏ | 1987/4692 [20:02<24:10, 1.86it/s] 42%|████▏ | 1988/4692 [20:02<24:18, 1.85it/s] 42%|████▏ | 1989/4692 [20:03<24:33, 1.83it/s] 42%|████▏ | 1990/4692 [20:04<24:46, 1.82it/s] 42%|████▏ | 1991/4692 [20:04<24:44, 1.82it/s] 42%|████▏ | 1992/4692 [20:05<24:42, 1.82it/s] 42%|████▏ | 1993/4692 [20:05<24:35, 1.83it/s] 42%|████▏ | 1994/4692 [20:06<24:31, 1.83it/s] 43%|████▎ | 1995/4692 [20:06<24:46, 1.81it/s] 43%|████▎ | 1996/4692 [20:07<24:39, 1.82it/s] 43%|████▎ | 1997/4692 [20:07<24:33, 1.83it/s] 43%|████▎ | 1998/4692 [20:08<24:44, 1.81it/s] 43%|████▎ | 1999/4692 [20:09<24:41, 1.82it/s] 43%|████▎ | 2000/4692 [20:09<24:42, 1.82it/s] 43%|████▎ | 2000/4692 [20:09<24:42, 1.82it/s] 43%|████▎ | 2001/4692 [20:10<24:51, 1.80it/s] 43%|████▎ | 2002/4692 [20:10<24:43, 1.81it/s] 43%|████▎ | 2003/4692 [20:11<24:46, 1.81it/s] 43%|████▎ | 2004/4692 [20:11<24:52, 1.80it/s] 43%|████▎ | 2005/4692 [20:12<24:42, 1.81it/s] 43%|████▎ | 2006/4692 [20:12<24:43, 1.81it/s] 43%|████▎ | 2007/4692 [20:13<24:44, 1.81it/s] 43%|████▎ | 2008/4692 [20:14<24:52, 1.80it/s] 43%|████▎ | 2009/4692 [20:14<24:45, 1.81it/s] 43%|████▎ | 2010/4692 [20:15<24:46, 1.80it/s] 43%|████▎ | 2011/4692 [20:15<24:51, 1.80it/s] 43%|████▎ | 2012/4692 [20:16<24:42, 1.81it/s] 43%|████▎ | 2013/4692 [20:16<24:39, 1.81it/s] 43%|████▎ | 2014/4692 [20:17<24:44, 1.80it/s] 43%|████▎ | 2015/4692 [20:17<24:42, 1.81it/s] 43%|████▎ | 2016/4692 [20:18<24:37, 1.81it/s] 43%|████▎ | 2017/4692 [20:19<24:42, 1.80it/s] 43%|████▎ | 2018/4692 [20:19<24:38, 1.81it/s] 43%|████▎ | 2019/4692 [20:20<24:34, 1.81it/s] 43%|████▎ | 2020/4692 [20:20<24:41, 1.80it/s] 43%|████▎ | 2021/4692 [20:21<24:37, 1.81it/s] 43%|████▎ | 2022/4692 [20:21<24:07, 1.84it/s] 43%|████▎ | 2023/4692 [20:22<24:10, 1.84it/s] 43%|████▎ | 2024/4692 [20:22<24:16, 1.83it/s] 43%|████▎ | 2025/4692 [20:23<24:29, 1.82it/s] 43%|████▎ | 2026/4692 [20:23<24:28, 1.82it/s] 43%|████▎ | 2027/4692 [20:24<24:25, 1.82it/s] 43%|████▎ | 2028/4692 [20:25<24:32, 1.81it/s] 43%|████▎ | 2029/4692 [20:25<24:27, 1.81it/s] 43%|████▎ | 2030/4692 [20:26<24:26, 1.82it/s] 43%|████▎ | 2031/4692 [20:26<24:33, 1.81it/s] 43%|████▎ | 2032/4692 [20:27<24:33, 1.81it/s] 43%|████▎ | 2033/4692 [20:27<24:21, 1.82it/s] 43%|████▎ | 2034/4692 [20:28<24:30, 1.81it/s] 43%|████▎ | 2035/4692 [20:28<24:24, 1.81it/s] 43%|████▎ | 2036/4692 [20:29<24:21, 1.82it/s] 43%|████▎ | 2037/4692 [20:30<24:31, 1.80it/s] 43%|████▎ | 2038/4692 [20:30<24:29, 1.81it/s] 43%|████▎ | 2039/4692 [20:31<24:20, 1.82it/s] 43%|████▎ | 2040/4692 [20:31<24:28, 1.81it/s] 43%|████▎ | 2041/4692 [20:32<24:18, 1.82it/s] 44%|████▎ | 2042/4692 [20:32<24:17, 1.82it/s] 44%|████▎ | 2043/4692 [20:33<24:26, 1.81it/s] 44%|████▎ | 2044/4692 [20:33<24:23, 1.81it/s] 44%|████▎ | 2045/4692 [20:34<24:22, 1.81it/s] 44%|████▎ | 2046/4692 [20:35<24:29, 1.80it/s] 44%|████▎ | 2047/4692 [20:35<24:35, 1.79it/s] 44%|████▎ | 2048/4692 [20:36<24:30, 1.80it/s] 44%|████▎ | 2049/4692 [20:36<24:24, 1.81it/s] 44%|████▎ | 2050/4692 [20:37<24:28, 1.80it/s] 44%|████▎ | 2051/4692 [20:37<24:20, 1.81it/s] 44%|████▎ | 2052/4692 [20:38<24:15, 1.81it/s] 44%|████▍ | 2053/4692 [20:38<24:24, 1.80it/s] 44%|████▍ | 2054/4692 [20:39<24:15, 1.81it/s] 44%|████▍ | 2055/4692 [20:39<24:10, 1.82it/s] 44%|████▍ | 2056/4692 [20:40<24:19, 1.81it/s] 44%|████▍ | 2057/4692 [20:41<24:13, 1.81it/s] 44%|████▍ | 2058/4692 [20:41<24:14, 1.81it/s] 44%|████▍ | 2059/4692 [20:42<24:18, 1.80it/s] 44%|████▍ | 2060/4692 [20:42<24:17, 1.81it/s] 44%|████▍ | 2061/4692 [20:43<24:01, 1.83it/s] 44%|████▍ | 2062/4692 [20:43<24:11, 1.81it/s] 44%|████▍ | 2063/4692 [20:44<24:09, 1.81it/s] 44%|████▍ | 2064/4692 [20:44<24:05, 1.82it/s] 44%|████▍ | 2065/4692 [20:45<24:10, 1.81it/s] 44%|████▍ | 2066/4692 [20:46<24:04, 1.82it/s] 44%|████▍ | 2067/4692 [20:46<24:02, 1.82it/s] 44%|████▍ | 2068/4692 [20:47<24:06, 1.81it/s] 44%|████▍ | 2069/4692 [20:47<24:00, 1.82it/s] 44%|████▍ | 2070/4692 [20:48<23:52, 1.83it/s] 44%|████▍ | 2071/4692 [20:48<24:04, 1.81it/s] 44%|████▍ | 2072/4692 [20:49<24:02, 1.82it/s] 44%|████▍ | 2073/4692 [20:49<24:00, 1.82it/s] 44%|████▍ | 2074/4692 [20:50<24:11, 1.80it/s] 44%|████▍ | 2075/4692 [20:51<24:11, 1.80it/s] 44%|████▍ | 2076/4692 [20:51<24:10, 1.80it/s] 44%|████▍ | 2077/4692 [20:52<24:15, 1.80it/s] 44%|████▍ | 2078/4692 [20:52<24:20, 1.79it/s] 44%|████▍ | 2079/4692 [20:53<24:10, 1.80it/s] 44%|████▍ | 2080/4692 [20:53<24:00, 1.81it/s] 44%|████▍ | 2081/4692 [20:54<24:08, 1.80it/s] 44%|████▍ | 2082/4692 [20:54<24:05, 1.81it/s] 44%|████▍ | 2083/4692 [20:55<23:59, 1.81it/s] 44%|████▍ | 2084/4692 [20:56<24:02, 1.81it/s] 44%|████▍ | 2085/4692 [20:56<24:07, 1.80it/s] 44%|████▍ | 2086/4692 [20:57<24:01, 1.81it/s] 44%|████▍ | 2087/4692 [20:57<23:58, 1.81it/s] 45%|████▍ | 2088/4692 [20:58<24:05, 1.80it/s] 45%|████▍ | 2089/4692 [20:58<23:58, 1.81it/s] 45%|████▍ | 2090/4692 [20:59<23:55, 1.81it/s] 45%|████▍ | 2091/4692 [20:59<24:08, 1.80it/s] 45%|████▍ | 2092/4692 [21:00<24:15, 1.79it/s] 45%|████▍ | 2093/4692 [21:01<24:21, 1.78it/s] 45%|████▍ | 2094/4692 [21:01<24:16, 1.78it/s] 45%|████▍ | 2095/4692 [21:02<24:13, 1.79it/s] 45%|████▍ | 2096/4692 [21:02<24:11, 1.79it/s] 45%|████▍ | 2097/4692 [21:03<24:15, 1.78it/s] 45%|████▍ | 2098/4692 [21:03<24:22, 1.77it/s] 45%|████▍ | 2099/4692 [21:04<24:18, 1.78it/s] 45%|████▍ | 2100/4692 [21:04<24:13, 1.78it/s] 45%|████▍ | 2101/4692 [21:05<24:14, 1.78it/s] 45%|████▍ | 2102/4692 [21:06<24:12, 1.78it/s] 45%|████▍ | 2103/4692 [21:06<24:20, 1.77it/s] 45%|████▍ | 2104/4692 [21:07<24:19, 1.77it/s] 45%|████▍ | 2105/4692 [21:07<24:12, 1.78it/s] 45%|████▍ | 2106/4692 [21:08<24:10, 1.78it/s] 45%|████▍ | 2107/4692 [21:08<24:10, 1.78it/s] 45%|████▍ | 2108/4692 [21:09<24:07, 1.78it/s] 45%|████▍ | 2109/4692 [21:10<24:15, 1.77it/s] 45%|████▍ | 2110/4692 [21:10<24:13, 1.78it/s] 45%|████▍ | 2111/4692 [21:11<24:05, 1.79it/s] 45%|████▌ | 2112/4692 [21:11<23:59, 1.79it/s] 45%|████▌ | 2113/4692 [21:12<24:02, 1.79it/s] 45%|████▌ | 2114/4692 [21:12<24:02, 1.79it/s] 45%|████▌ | 2115/4692 [21:13<24:02, 1.79it/s] 45%|████▌ | 2116/4692 [21:13<23:57, 1.79it/s] 45%|████▌ | 2117/4692 [21:14<24:06, 1.78it/s] 45%|████▌ | 2118/4692 [21:15<24:13, 1.77it/s] 45%|████▌ | 2119/4692 [21:15<24:08, 1.78it/s] 45%|████▌ | 2120/4692 [21:16<24:04, 1.78it/s] 45%|████▌ | 2121/4692 [21:16<24:04, 1.78it/s] 45%|████▌ | 2122/4692 [21:17<24:01, 1.78it/s] 45%|████▌ | 2123/4692 [21:17<24:05, 1.78it/s] 45%|████▌ | 2124/4692 [21:18<23:59, 1.78it/s] 45%|████▌ | 2125/4692 [21:18<23:50, 1.79it/s] 45%|████▌ | 2126/4692 [21:19<23:53, 1.79it/s] 45%|████▌ | 2127/4692 [21:20<24:11, 1.77it/s] 45%|████▌ | 2128/4692 [21:20<23:59, 1.78it/s] 45%|████▌ | 2129/4692 [21:21<24:02, 1.78it/s] 45%|████▌ | 2130/4692 [21:21<24:16, 1.76it/s] 45%|████▌ | 2131/4692 [21:22<24:07, 1.77it/s] 45%|████▌ | 2132/4692 [21:22<24:19, 1.75it/s] 45%|████▌ | 2133/4692 [21:23<24:27, 1.74it/s] 45%|████▌ | 2134/4692 [21:24<24:10, 1.76it/s] 46%|████▌ | 2135/4692 [21:24<24:24, 1.75it/s] 46%|████▌ | 2136/4692 [21:25<24:18, 1.75it/s] 46%|████▌ | 2137/4692 [21:25<24:15, 1.76it/s] 46%|████▌ | 2138/4692 [21:26<24:22, 1.75it/s] 46%|████▌ | 2139/4692 [21:26<24:10, 1.76it/s] 46%|████▌ | 2140/4692 [21:27<24:11, 1.76it/s] 46%|████▌ | 2141/4692 [21:28<24:20, 1.75it/s] 46%|████▌ | 2142/4692 [21:28<24:00, 1.77it/s] 46%|████▌ | 2143/4692 [21:29<23:59, 1.77it/s] 46%|████▌ | 2144/4692 [21:29<24:07, 1.76it/s] 46%|████▌ | 2145/4692 [21:30<23:50, 1.78it/s] 46%|████▌ | 2146/4692 [21:30<24:04, 1.76it/s] 46%|████▌ | 2147/4692 [21:31<23:47, 1.78it/s] 46%|████▌ | 2148/4692 [21:32<23:53, 1.77it/s] 46%|████▌ | 2149/4692 [21:32<23:54, 1.77it/s] 46%|████▌ | 2150/4692 [21:33<23:45, 1.78it/s] 46%|████▌ | 2151/4692 [21:33<23:55, 1.77it/s] 46%|████▌ | 2152/4692 [21:34<23:39, 1.79it/s] 46%|████▌ | 2153/4692 [21:34<23:48, 1.78it/s] 46%|████▌ | 2154/4692 [21:35<23:42, 1.78it/s] 46%|████▌ | 2155/4692 [21:35<23:46, 1.78it/s] 46%|████▌ | 2156/4692 [21:36<23:59, 1.76it/s] 46%|████▌ | 2157/4692 [21:37<23:43, 1.78it/s] 46%|████▌ | 2158/4692 [21:37<23:52, 1.77it/s] 46%|████▌ | 2159/4692 [21:38<23:49, 1.77it/s] 46%|████▌ | 2160/4692 [21:38<23:47, 1.77it/s] 46%|████▌ | 2161/4692 [21:39<23:56, 1.76it/s] 46%|████▌ | 2162/4692 [21:39<23:41, 1.78it/s] 46%|████▌ | 2163/4692 [21:40<23:46, 1.77it/s] 46%|████▌ | 2164/4692 [21:41<23:49, 1.77it/s] 46%|████▌ | 2165/4692 [21:41<23:43, 1.78it/s] 46%|████▌ | 2166/4692 [21:42<23:52, 1.76it/s] 46%|████▌ | 2167/4692 [21:42<23:40, 1.78it/s] 46%|████▌ | 2168/4692 [21:43<23:38, 1.78it/s] 46%|████▌ | 2169/4692 [21:43<23:47, 1.77it/s] 46%|████▌ | 2170/4692 [21:44<23:31, 1.79it/s] 46%|████▋ | 2171/4692 [21:44<23:40, 1.77it/s] 46%|████▋ | 2172/4692 [21:45<23:26, 1.79it/s] 46%|████▋ | 2173/4692 [21:46<23:28, 1.79it/s] 46%|████▋ | 2174/4692 [21:46<23:36, 1.78it/s] 46%|████▋ | 2175/4692 [21:47<23:29, 1.79it/s] 46%|████▋ | 2176/4692 [21:47<23:44, 1.77it/s] 46%|████▋ | 2177/4692 [21:48<23:32, 1.78it/s] 46%|████▋ | 2178/4692 [21:48<23:26, 1.79it/s] 46%|████▋ | 2179/4692 [21:49<23:35, 1.78it/s] 46%|████▋ | 2180/4692 [21:50<23:22, 1.79it/s] 46%|████▋ | 2181/4692 [21:50<23:34, 1.78it/s] 47%|████▋ | 2182/4692 [21:51<23:18, 1.80it/s] 47%|████▋ | 2183/4692 [21:51<23:26, 1.78it/s] 47%|████▋ | 2184/4692 [21:52<23:27, 1.78it/s] 47%|████▋ | 2185/4692 [21:52<23:19, 1.79it/s] 47%|████▋ | 2186/4692 [21:53<23:30, 1.78it/s] 47%|████▋ | 2187/4692 [21:53<23:21, 1.79it/s] 47%|████▋ | 2188/4692 [21:54<23:30, 1.78it/s] 47%|████▋ | 2189/4692 [21:55<23:29, 1.78it/s] 47%|████▋ | 2190/4692 [21:55<23:29, 1.77it/s] 47%|████▋ | 2191/4692 [21:56<23:42, 1.76it/s] 47%|████▋ | 2192/4692 [21:56<23:26, 1.78it/s] 47%|████▋ | 2193/4692 [21:57<23:26, 1.78it/s] 47%|████▋ | 2194/4692 [21:57<23:33, 1.77it/s] 47%|████▋ | 2195/4692 [21:58<23:14, 1.79it/s] 47%|████▋ | 2196/4692 [21:59<23:26, 1.77it/s] 47%|████▋ | 2197/4692 [21:59<23:14, 1.79it/s] 47%|████▋ | 2198/4692 [22:00<23:25, 1.77it/s] 47%|████▋ | 2199/4692 [22:00<23:16, 1.79it/s] 47%|████▋ | 2200/4692 [22:01<23:10, 1.79it/s] 47%|████▋ | 2201/4692 [22:01<23:20, 1.78it/s] 47%|████▋ | 2202/4692 [22:02<23:05, 1.80it/s] 47%|████▋ | 2203/4692 [22:02<23:20, 1.78it/s] 47%|████▋ | 2204/4692 [22:03<23:09, 1.79it/s] 47%|████▋ | 2205/4692 [22:04<23:17, 1.78it/s] 47%|████▋ | 2206/4692 [22:04<23:19, 1.78it/s] 47%|████▋ | 2207/4692 [22:05<23:03, 1.80it/s] 47%|████▋ | 2208/4692 [22:05<23:13, 1.78it/s] 47%|████▋ | 2209/4692 [22:06<22:54, 1.81it/s] 47%|████▋ | 2210/4692 [22:06<23:11, 1.78it/s] 47%|████▋ | 2211/4692 [22:07<22:58, 1.80it/s] 47%|████▋ | 2212/4692 [22:07<23:06, 1.79it/s] 47%|████▋ | 2213/4692 [22:08<22:54, 1.80it/s] 47%|████▋ | 2214/4692 [22:09<22:54, 1.80it/s] 47%|████▋ | 2215/4692 [22:09<23:01, 1.79it/s] 47%|████▋ | 2216/4692 [22:10<22:58, 1.80it/s] 47%|████▋ | 2217/4692 [22:10<22:53, 1.80it/s] 47%|████▋ | 2218/4692 [22:11<22:27, 1.84it/s] 47%|████▋ | 2219/4692 [22:11<22:48, 1.81it/s] 47%|████▋ | 2220/4692 [22:12<22:39, 1.82it/s] 47%|████▋ | 2221/4692 [22:12<22:52, 1.80it/s] 47%|████▋ | 2222/4692 [22:13<22:41, 1.81it/s] 47%|████▋ | 2223/4692 [22:14<22:56, 1.79it/s] 47%|████▋ | 2224/4692 [22:14<22:55, 1.79it/s] 47%|████▋ | 2225/4692 [22:15<23:00, 1.79it/s] 47%|████▋ | 2226/4692 [22:15<23:11, 1.77it/s] 47%|████▋ | 2227/4692 [22:16<22:51, 1.80it/s] 47%|████▋ | 2228/4692 [22:16<22:48, 1.80it/s] 48%|████▊ | 2229/4692 [22:17<22:42, 1.81it/s] 48%|████▊ | 2230/4692 [22:17<22:58, 1.79it/s] 48%|████▊ | 2231/4692 [22:18<23:14, 1.77it/s] 48%|████▊ | 2232/4692 [22:19<22:58, 1.79it/s] 48%|████▊ | 2233/4692 [22:19<23:13, 1.77it/s] 48%|████▊ | 2234/4692 [22:20<22:55, 1.79it/s] 48%|████▊ | 2235/4692 [22:20<22:58, 1.78it/s] 48%|████▊ | 2236/4692 [22:21<23:05, 1.77it/s] 48%|████▊ | 2237/4692 [22:21<22:55, 1.78it/s] 48%|████▊ | 2238/4692 [22:22<23:08, 1.77it/s] 48%|████▊ | 2239/4692 [22:23<22:54, 1.78it/s] 48%|████▊ | 2240/4692 [22:23<23:00, 1.78it/s] 48%|████▊ | 2241/4692 [22:24<22:58, 1.78it/s] 48%|████▊ | 2242/4692 [22:24<22:53, 1.78it/s] 48%|████▊ | 2243/4692 [22:25<23:09, 1.76it/s] 48%|████▊ | 2244/4692 [22:25<22:52, 1.78it/s] 48%|████▊ | 2245/4692 [22:26<23:07, 1.76it/s] 48%|████▊ | 2246/4692 [22:26<22:55, 1.78it/s] 48%|████▊ | 2247/4692 [22:27<22:56, 1.78it/s] 48%|████▊ | 2248/4692 [22:28<23:07, 1.76it/s] 48%|████▊ | 2249/4692 [22:28<22:50, 1.78it/s] 48%|████▊ | 2250/4692 [22:29<23:04, 1.76it/s] 48%|████▊ | 2251/4692 [22:29<22:51, 1.78it/s] 48%|████▊ | 2252/4692 [22:30<22:44, 1.79it/s] 48%|████▊ | 2253/4692 [22:30<23:01, 1.77it/s] 48%|████▊ | 2254/4692 [22:31<22:44, 1.79it/s] 48%|████▊ | 2255/4692 [22:32<23:00, 1.77it/s] 48%|████▊ | 2256/4692 [22:32<22:56, 1.77it/s] 48%|████▊ | 2257/4692 [22:33<22:57, 1.77it/s] 48%|████▊ | 2258/4692 [22:33<23:14, 1.75it/s] 48%|████▊ | 2259/4692 [22:34<22:54, 1.77it/s] 48%|████▊ | 2260/4692 [22:34<22:56, 1.77it/s] 48%|████▊ | 2261/4692 [22:35<23:08, 1.75it/s] 48%|████▊ | 2262/4692 [22:36<22:54, 1.77it/s] 48%|████▊ | 2263/4692 [22:36<23:06, 1.75it/s] 48%|████▊ | 2264/4692 [22:37<23:00, 1.76it/s] 48%|████▊ | 2265/4692 [22:37<23:04, 1.75it/s] 48%|████▊ | 2266/4692 [22:38<23:14, 1.74it/s] 48%|████▊ | 2267/4692 [22:38<22:57, 1.76it/s] 48%|████▊ | 2268/4692 [22:39<23:00, 1.76it/s] 48%|████▊ | 2269/4692 [22:40<23:16, 1.74it/s] 48%|████▊ | 2270/4692 [22:40<23:00, 1.75it/s] 48%|████▊ | 2271/4692 [22:41<22:58, 1.76it/s] 48%|████▊ | 2272/4692 [22:41<23:11, 1.74it/s] 48%|████▊ | 2273/4692 [22:42<22:57, 1.76it/s] 48%|████▊ | 2274/4692 [22:42<23:01, 1.75it/s] 48%|████▊ | 2275/4692 [22:43<23:11, 1.74it/s] 49%|████▊ | 2276/4692 [22:44<22:56, 1.76it/s] 49%|████▊ | 2277/4692 [22:44<22:59, 1.75it/s] 49%|████▊ | 2278/4692 [22:45<23:05, 1.74it/s] 49%|████▊ | 2279/4692 [22:45<22:55, 1.75it/s] 49%|████▊ | 2280/4692 [22:46<23:01, 1.75it/s] 49%|████▊ | 2281/4692 [22:46<22:46, 1.76it/s] 49%|████▊ | 2282/4692 [22:47<22:46, 1.76it/s] 49%|████▊ | 2283/4692 [22:48<22:57, 1.75it/s] 49%|████▊ | 2284/4692 [22:48<22:43, 1.77it/s] 49%|████▊ | 2285/4692 [22:49<22:47, 1.76it/s] 49%|████▊ | 2286/4692 [22:49<22:50, 1.76it/s] 49%|████▊ | 2287/4692 [22:50<22:47, 1.76it/s] 49%|████▉ | 2288/4692 [22:50<22:54, 1.75it/s] 49%|████▉ | 2289/4692 [22:51<22:38, 1.77it/s] 49%|████▉ | 2290/4692 [22:52<22:41, 1.76it/s] 49%|████▉ | 2291/4692 [22:52<22:57, 1.74it/s] 49%|████▉ | 2292/4692 [22:53<22:45, 1.76it/s] 49%|████▉ | 2293/4692 [22:53<22:46, 1.76it/s] 49%|████▉ | 2294/4692 [22:54<22:52, 1.75it/s] 49%|████▉ | 2295/4692 [22:54<22:35, 1.77it/s] 49%|████▉ | 2296/4692 [22:55<22:52, 1.75it/s] 49%|████▉ | 2297/4692 [22:56<22:51, 1.75it/s] 49%|████▉ | 2298/4692 [22:56<22:43, 1.76it/s] 49%|████▉ | 2299/4692 [22:57<22:55, 1.74it/s] 49%|████▉ | 2300/4692 [22:57<22:33, 1.77it/s] 49%|████▉ | 2301/4692 [22:58<22:41, 1.76it/s] 49%|████▉ | 2302/4692 [22:58<22:45, 1.75it/s] 49%|████▉ | 2303/4692 [22:59<22:30, 1.77it/s] 49%|████▉ | 2304/4692 [22:59<22:34, 1.76it/s] 49%|████▉ | 2305/4692 [23:00<22:47, 1.75it/s] 49%|████▉ | 2306/4692 [23:01<22:35, 1.76it/s] 49%|████▉ | 2307/4692 [23:01<22:47, 1.74it/s] 49%|████▉ | 2308/4692 [23:02<22:57, 1.73it/s] 49%|████▉ | 2309/4692 [23:02<22:37, 1.75it/s] 49%|████▉ | 2310/4692 [23:03<22:52, 1.74it/s] 49%|████▉ | 2311/4692 [23:04<22:53, 1.73it/s] 49%|████▉ | 2312/4692 [23:04<22:41, 1.75it/s] 49%|████▉ | 2313/4692 [23:05<22:50, 1.74it/s] 49%|████▉ | 2314/4692 [23:05<22:46, 1.74it/s] 49%|████▉ | 2315/4692 [23:06<22:34, 1.75it/s] 49%|████▉ | 2316/4692 [23:06<22:47, 1.74it/s] 49%|████▉ | 2317/4692 [23:07<22:36, 1.75it/s] 49%|████▉ | 2318/4692 [23:08<22:37, 1.75it/s] 49%|████▉ | 2319/4692 [23:08<22:52, 1.73it/s] 49%|████▉ | 2320/4692 [23:09<22:40, 1.74it/s] 49%|████▉ | 2321/4692 [23:09<22:39, 1.74it/s] 49%|████▉ | 2322/4692 [23:10<22:48, 1.73it/s] 50%|████▉ | 2323/4692 [23:10<22:31, 1.75it/s] 50%|████▉ | 2324/4692 [23:11<22:38, 1.74it/s] 50%|████▉ | 2325/4692 [23:12<22:45, 1.73it/s] 50%|████▉ | 2326/4692 [23:12<22:24, 1.76it/s] 50%|████▉ | 2327/4692 [23:13<22:17, 1.77it/s] 50%|████▉ | 2328/4692 [23:13<22:24, 1.76it/s] 50%|████▉ | 2329/4692 [23:14<22:11, 1.77it/s] 50%|████▉ | 2330/4692 [23:14<22:24, 1.76it/s] 50%|████▉ | 2331/4692 [23:15<22:39, 1.74it/s] 50%|████▉ | 2332/4692 [23:16<22:25, 1.75it/s] 50%|████▉ | 2333/4692 [23:16<22:32, 1.74it/s] 50%|████▉ | 2334/4692 [23:17<22:34, 1.74it/s] 50%|████▉ | 2335/4692 [23:17<22:24, 1.75it/s] 50%|████▉ | 2336/4692 [23:18<22:33, 1.74it/s] 50%|████▉ | 2337/4692 [23:18<22:28, 1.75it/s] 50%|████▉ | 2338/4692 [23:19<22:17, 1.76it/s] 50%|████▉ | 2339/4692 [23:20<22:26, 1.75it/s] 50%|████▉ | 2340/4692 [23:20<22:11, 1.77it/s] 50%|████▉ | 2341/4692 [23:21<22:11, 1.77it/s] 50%|████▉ | 2342/4692 [23:21<22:07, 1.77it/s] 50%|████▉ | 2343/4692 [23:22<22:01, 1.78it/s] 50%|████▉ | 2344/4692 [23:22<22:11, 1.76it/s] 50%|████▉ | 2345/4692 [23:23<22:00, 1.78it/s] 50%|█████ | 2346/4692 [23:23<17:53, 2.18it/s][INFO|trainer.py:738] 2023-07-03 01:31:00,534 >> The following columns in the evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: text. If text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3069] 2023-07-03 01:31:00,536 >> ***** Running Evaluation ***** [INFO|trainer.py:3071] 2023-07-03 01:31:00,536 >> Num examples = 25000 [INFO|trainer.py:3074] 2023-07-03 01:31:00,536 >> Batch size = 64 0%| | 0/391 [00:00> Saving model checkpoint to /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-2346 [INFO|configuration_utils.py:457] 2023-07-03 01:33:10,801 >> Configuration saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-2346/config.json [INFO|modeling_utils.py:1762] 2023-07-03 01:33:11,372 >> Model weights saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-2346/pytorch_model.bin [INFO|tokenization_utils_base.py:2163] 2023-07-03 01:33:11,372 >> tokenizer config file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-2346/tokenizer_config.json [INFO|tokenization_utils_base.py:2170] 2023-07-03 01:33:11,372 >> Special tokens file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-2346/special_tokens_map.json [INFO|trainer.py:2893] 2023-07-03 01:33:12,546 >> Deleting older checkpoint [/nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-1955] due to args.save_total_limit 50%|█████ | 2347/4692 [25:36<26:08:39, 40.14s/it] 50%|█████ | 2348/4692 [25:36<18:24:23, 28.27s/it] 50%|█████ | 2349/4692 [25:37<12:59:13, 19.95s/it] 50%|█████ | 2350/4692 [25:38<9:12:03, 14.14s/it] 50%|█████ | 2351/4692 [25:38<6:32:56, 10.07s/it] 50%|█████ | 2352/4692 [25:39<4:41:35, 7.22s/it] 50%|█████ | 2353/4692 [25:39<3:23:51, 5.23s/it] 50%|█████ | 2354/4692 [25:40<2:29:05, 3.83s/it] 50%|█████ | 2355/4692 [25:40<1:51:00, 2.85s/it] 50%|█████ | 2356/4692 [25:41<1:24:30, 2.17s/it] 50%|█████ | 2357/4692 [25:42<1:05:33, 1.68s/it] 50%|█████ | 2358/4692 [25:42<52:33, 1.35s/it] 50%|█████ | 2359/4692 [25:43<43:36, 1.12s/it] 50%|█████ | 2360/4692 [25:43<36:57, 1.05it/s] 50%|█████ | 2361/4692 [25:44<32:43, 1.19it/s] 50%|█████ | 2362/4692 [25:44<29:41, 1.31it/s] 50%|█████ | 2363/4692 [25:45<27:18, 1.42it/s] 50%|█████ | 2364/4692 [25:46<25:52, 1.50it/s] 50%|█████ | 2365/4692 [25:46<24:26, 1.59it/s] 50%|█████ | 2366/4692 [25:47<23:44, 1.63it/s] 50%|█████ | 2367/4692 [25:47<23:20, 1.66it/s] 50%|█████ | 2368/4692 [25:48<22:39, 1.71it/s] 50%|█████ | 2369/4692 [25:48<22:34, 1.72it/s] 51%|█████ | 2370/4692 [25:49<22:13, 1.74it/s] 51%|█████ | 2371/4692 [25:49<22:05, 1.75it/s] 51%|█████ | 2372/4692 [25:50<22:15, 1.74it/s] 51%|█████ | 2373/4692 [25:51<22:00, 1.76it/s] 51%|█████ | 2374/4692 [25:51<22:01, 1.75it/s] 51%|█████ | 2375/4692 [25:52<22:15, 1.73it/s] 51%|█████ | 2376/4692 [25:52<21:53, 1.76it/s] 51%|█████ | 2377/4692 [25:53<22:05, 1.75it/s] 51%|█████ | 2378/4692 [25:53<21:53, 1.76it/s] 51%|█████ | 2379/4692 [25:54<21:47, 1.77it/s] 51%|█████ | 2380/4692 [25:55<21:59, 1.75it/s] 51%|█████ | 2381/4692 [25:55<21:46, 1.77it/s] 51%|█████ | 2382/4692 [25:56<21:56, 1.76it/s] 51%|█████ | 2383/4692 [25:56<21:51, 1.76it/s] 51%|█████ | 2384/4692 [25:57<21:51, 1.76it/s] 51%|█████ | 2385/4692 [25:57<21:58, 1.75it/s] 51%|█████ | 2386/4692 [25:58<21:38, 1.78it/s] 51%|█████ | 2387/4692 [25:59<21:49, 1.76it/s] 51%|█████ | 2388/4692 [25:59<21:52, 1.76it/s] 51%|█████ | 2389/4692 [26:00<21:46, 1.76it/s] 51%|█████ | 2390/4692 [26:00<21:58, 1.75it/s] 51%|█████ | 2391/4692 [26:01<21:43, 1.77it/s] 51%|█████ | 2392/4692 [26:01<21:47, 1.76it/s] 51%|█████ | 2393/4692 [26:02<21:55, 1.75it/s] 51%|█████ | 2394/4692 [26:03<21:43, 1.76it/s] 51%|█████ | 2395/4692 [26:03<21:43, 1.76it/s] 51%|█████ | 2396/4692 [26:04<21:56, 1.74it/s] 51%|█████ | 2397/4692 [26:04<21:43, 1.76it/s] 51%|█████ | 2398/4692 [26:05<21:55, 1.74it/s] 51%|█████ | 2399/4692 [26:05<21:56, 1.74it/s] 51%|█████ | 2400/4692 [26:06<21:47, 1.75it/s] 51%|█████ | 2401/4692 [26:07<22:00, 1.73it/s] 51%|█████ | 2402/4692 [26:07<21:45, 1.75it/s] 51%|█████ | 2403/4692 [26:08<21:44, 1.75it/s] 51%|█████ | 2404/4692 [26:08<21:50, 1.75it/s] 51%|█████▏ | 2405/4692 [26:09<21:33, 1.77it/s] 51%|█████▏ | 2406/4692 [26:09<21:44, 1.75it/s] 51%|█████▏ | 2407/4692 [26:10<21:55, 1.74it/s] 51%|█████▏ | 2408/4692 [26:11<21:38, 1.76it/s] 51%|█████▏ | 2409/4692 [26:11<21:48, 1.75it/s] 51%|█████▏ | 2410/4692 [26:12<21:33, 1.76it/s] 51%|█████▏ | 2411/4692 [26:12<21:24, 1.78it/s] 51%|█████▏ | 2412/4692 [26:13<21:32, 1.76it/s] 51%|█████▏ | 2413/4692 [26:13<21:22, 1.78it/s] 51%|█████▏ | 2414/4692 [26:14<21:30, 1.77it/s] 51%|█████▏ | 2415/4692 [26:15<21:09, 1.79it/s] 51%|█████▏ | 2416/4692 [26:15<21:22, 1.77it/s] 52%|█████▏ | 2417/4692 [26:16<21:44, 1.74it/s] 52%|█████▏ | 2418/4692 [26:16<21:25, 1.77it/s] 52%|█████▏ | 2419/4692 [26:17<21:26, 1.77it/s] 52%|█████▏ | 2420/4692 [26:17<21:41, 1.75it/s] 52%|█████▏ | 2421/4692 [26:18<21:28, 1.76it/s] 52%|█████▏ | 2422/4692 [26:19<21:32, 1.76it/s] 52%|█████▏ | 2423/4692 [26:19<21:41, 1.74it/s] 52%|█████▏ | 2424/4692 [26:20<21:29, 1.76it/s] 52%|█████▏ | 2425/4692 [26:20<21:35, 1.75it/s] 52%|█████▏ | 2426/4692 [26:21<21:42, 1.74it/s] 52%|█████▏ | 2427/4692 [26:21<21:26, 1.76it/s] 52%|█████▏ | 2428/4692 [26:22<21:39, 1.74it/s] 52%|█████▏ | 2429/4692 [26:23<21:33, 1.75it/s] 52%|█████▏ | 2430/4692 [26:23<21:30, 1.75it/s] 52%|█████▏ | 2431/4692 [26:24<21:36, 1.74it/s] 52%|█████▏ | 2432/4692 [26:24<21:26, 1.76it/s] 52%|█████▏ | 2433/4692 [26:25<21:29, 1.75it/s] 52%|█████▏ | 2434/4692 [26:25<21:38, 1.74it/s] 52%|█████▏ | 2435/4692 [26:26<21:25, 1.76it/s] 52%|█████▏ | 2436/4692 [26:27<21:19, 1.76it/s] 52%|█████▏ | 2437/4692 [26:27<21:32, 1.74it/s] 52%|█████▏ | 2438/4692 [26:28<21:18, 1.76it/s] 52%|█████▏ | 2439/4692 [26:28<21:19, 1.76it/s] 52%|█████▏ | 2440/4692 [26:29<21:31, 1.74it/s] 52%|█████▏ | 2441/4692 [26:29<21:17, 1.76it/s] 52%|█████▏ | 2442/4692 [26:30<21:17, 1.76it/s] 52%|█████▏ | 2443/4692 [26:31<21:24, 1.75it/s] 52%|█████▏ | 2444/4692 [26:31<21:14, 1.76it/s] 52%|█████▏ | 2445/4692 [26:32<21:19, 1.76it/s] 52%|█████▏ | 2446/4692 [26:32<21:29, 1.74it/s] 52%|█████▏ | 2447/4692 [26:33<21:15, 1.76it/s] 52%|█████▏ | 2448/4692 [26:33<21:23, 1.75it/s] 52%|█████▏ | 2449/4692 [26:34<21:33, 1.73it/s] 52%|█████▏ | 2450/4692 [26:34<21:14, 1.76it/s] 52%|█████▏ | 2451/4692 [26:35<21:17, 1.75it/s] 52%|█████▏ | 2452/4692 [26:36<21:00, 1.78it/s] 52%|█████▏ | 2453/4692 [26:36<21:00, 1.78it/s] 52%|█████▏ | 2454/4692 [26:37<21:09, 1.76it/s] 52%|█████▏ | 2455/4692 [26:37<21:02, 1.77it/s] 52%|█████▏ | 2456/4692 [26:38<21:06, 1.77it/s] 52%|█████▏ | 2457/4692 [26:38<21:18, 1.75it/s] 52%|█████▏ | 2458/4692 [26:39<21:07, 1.76it/s] 52%|█████▏ | 2459/4692 [26:40<21:13, 1.75it/s] 52%|█████▏ | 2460/4692 [26:40<21:25, 1.74it/s] 52%|█████▏ | 2461/4692 [26:41<21:15, 1.75it/s] 52%|█████▏ | 2462/4692 [26:41<21:11, 1.75it/s] 52%|█████▏ | 2463/4692 [26:42<21:15, 1.75it/s] 53%|█████▎ | 2464/4692 [26:42<21:03, 1.76it/s] 53%|█████▎ | 2465/4692 [26:43<21:13, 1.75it/s] 53%|█████▎ | 2466/4692 [26:44<21:16, 1.74it/s] 53%|█████▎ | 2467/4692 [26:44<21:05, 1.76it/s] 53%|█████▎ | 2468/4692 [26:45<21:15, 1.74it/s] 53%|█████▎ | 2469/4692 [26:45<21:07, 1.75it/s] 53%|█████▎ | 2470/4692 [26:46<21:03, 1.76it/s] 53%|█████▎ | 2471/4692 [26:46<21:12, 1.74it/s] 53%|█████▎ | 2472/4692 [26:47<21:05, 1.75it/s] 53%|█████▎ | 2473/4692 [26:48<21:00, 1.76it/s] 53%|█████▎ | 2474/4692 [26:48<21:09, 1.75it/s] 53%|█████▎ | 2475/4692 [26:49<20:57, 1.76it/s] 53%|█████▎ | 2476/4692 [26:49<20:56, 1.76it/s] 53%|█████▎ | 2477/4692 [26:50<21:03, 1.75it/s] 53%|█████▎ | 2478/4692 [26:50<20:52, 1.77it/s] 53%|█████▎ | 2479/4692 [26:51<20:56, 1.76it/s] 53%|█████▎ | 2480/4692 [26:52<21:05, 1.75it/s] 53%|█████▎ | 2481/4692 [26:52<20:59, 1.76it/s] 53%|█████▎ | 2482/4692 [26:53<21:02, 1.75it/s] 53%|█████▎ | 2483/4692 [26:53<21:06, 1.74it/s] 53%|█████▎ | 2484/4692 [26:54<20:50, 1.77it/s] 53%|█████▎ | 2485/4692 [26:54<21:03, 1.75it/s] 53%|█████▎ | 2486/4692 [26:55<21:03, 1.75it/s] 53%|█████▎ | 2487/4692 [26:56<20:55, 1.76it/s] 53%|█████▎ | 2488/4692 [26:56<21:05, 1.74it/s] 53%|█████▎ | 2489/4692 [26:57<21:00, 1.75it/s] 53%|█████▎ | 2490/4692 [26:57<20:57, 1.75it/s] 53%|█████▎ | 2491/4692 [26:58<21:07, 1.74it/s] 53%|█████▎ | 2492/4692 [26:58<20:52, 1.76it/s] 53%|█████▎ | 2493/4692 [26:59<20:52, 1.76it/s] 53%|█████▎ | 2494/4692 [27:00<21:01, 1.74it/s] 53%|█████▎ | 2495/4692 [27:00<20:48, 1.76it/s] 53%|█████▎ | 2496/4692 [27:01<20:46, 1.76it/s] 53%|█████▎ | 2497/4692 [27:01<20:59, 1.74it/s] 53%|█████▎ | 2498/4692 [27:02<20:45, 1.76it/s] 53%|█████▎ | 2499/4692 [27:02<20:54, 1.75it/s] 53%|█████▎ | 2500/4692 [27:03<21:01, 1.74it/s] 53%|█████▎ | 2500/4692 [27:03<21:01, 1.74it/s] 53%|█████▎ | 2501/4692 [27:04<20:48, 1.75it/s] 53%|█████▎ | 2502/4692 [27:04<20:54, 1.75it/s] 53%|█████▎ | 2503/4692 [27:05<20:49, 1.75it/s] 53%|█████▎ | 2504/4692 [27:05<20:32, 1.78it/s] 53%|█████▎ | 2505/4692 [27:06<20:52, 1.75it/s] 53%|█████▎ | 2506/4692 [27:06<20:38, 1.76it/s] 53%|█████▎ | 2507/4692 [27:07<19:53, 1.83it/s] 53%|█████▎ | 2508/4692 [27:07<16:59, 2.14it/s] 53%|█████▎ | 2509/4692 [27:07<14:59, 2.43it/s] 53%|█████▎ | 2510/4692 [27:08<13:33, 2.68it/s] 54%|█████▎ | 2511/4692 [27:08<12:33, 2.89it/s] 54%|█████▎ | 2512/4692 [27:08<11:49, 3.07it/s] 54%|█████▎ | 2513/4692 [27:09<11:21, 3.20it/s] 54%|█████▎ | 2514/4692 [27:09<12:07, 3.00it/s] 54%|█████▎ | 2515/4692 [27:10<14:36, 2.48it/s] 54%|█████▎ | 2516/4692 [27:10<16:15, 2.23it/s] 54%|█████▎ | 2517/4692 [27:11<17:30, 2.07it/s] 54%|█████▎ | 2518/4692 [27:11<18:19, 1.98it/s] 54%|█████▎ | 2519/4692 [27:12<18:57, 1.91it/s] 54%|█████▎ | 2520/4692 [27:12<19:19, 1.87it/s] 54%|█████▎ | 2521/4692 [27:13<19:37, 1.84it/s] 54%|█████▍ | 2522/4692 [27:13<19:49, 1.82it/s] 54%|█████▍ | 2523/4692 [27:14<19:52, 1.82it/s] 54%|█████▍ | 2524/4692 [27:15<20:04, 1.80it/s] 54%|█████▍ | 2525/4692 [27:15<19:59, 1.81it/s] 54%|█████▍ | 2526/4692 [27:16<20:07, 1.79it/s] 54%|█████▍ | 2527/4692 [27:16<20:05, 1.80it/s] 54%|█████▍ | 2528/4692 [27:17<20:11, 1.79it/s] 54%|█████▍ | 2529/4692 [27:17<20:08, 1.79it/s] 54%|█████▍ | 2530/4692 [27:18<20:02, 1.80it/s] 54%|█████▍ | 2531/4692 [27:18<19:58, 1.80it/s] 54%|█████▍ | 2532/4692 [27:19<20:08, 1.79it/s] 54%|█████▍ | 2533/4692 [27:20<20:12, 1.78it/s] 54%|█████▍ | 2534/4692 [27:20<20:07, 1.79it/s] 54%|█████▍ | 2535/4692 [27:21<20:08, 1.78it/s] 54%|█████▍ | 2536/4692 [27:21<20:08, 1.78it/s] 54%|█████▍ | 2537/4692 [27:22<20:10, 1.78it/s] 54%|█████▍ | 2538/4692 [27:22<20:13, 1.77it/s] 54%|█████▍ | 2539/4692 [27:23<20:05, 1.79it/s] 54%|█████▍ | 2540/4692 [27:24<20:07, 1.78it/s] 54%|█████▍ | 2541/4692 [27:24<20:09, 1.78it/s] 54%|█████▍ | 2542/4692 [27:25<20:05, 1.78it/s] 54%|█████▍ | 2543/4692 [27:25<20:09, 1.78it/s] 54%|█████▍ | 2544/4692 [27:26<20:15, 1.77it/s] 54%|█████▍ | 2545/4692 [27:26<20:10, 1.77it/s] 54%|█████▍ | 2546/4692 [27:27<20:05, 1.78it/s] 54%|█████▍ | 2547/4692 [27:27<20:06, 1.78it/s] 54%|█████▍ | 2548/4692 [27:28<20:10, 1.77it/s] 54%|█████▍ | 2549/4692 [27:29<20:04, 1.78it/s] 54%|█████▍ | 2550/4692 [27:29<19:59, 1.79it/s] 54%|█████▍ | 2551/4692 [27:30<19:53, 1.79it/s] 54%|█████▍ | 2552/4692 [27:30<19:58, 1.79it/s] 54%|█████▍ | 2553/4692 [27:31<19:56, 1.79it/s] 54%|█████▍ | 2554/4692 [27:31<19:52, 1.79it/s] 54%|█████▍ | 2555/4692 [27:32<19:50, 1.80it/s] 54%|█████▍ | 2556/4692 [27:33<19:55, 1.79it/s] 54%|█████▍ | 2557/4692 [27:33<19:55, 1.79it/s] 55%|█████▍ | 2558/4692 [27:34<19:39, 1.81it/s] 55%|█████▍ | 2559/4692 [27:34<19:41, 1.81it/s] 55%|█████▍ | 2560/4692 [27:35<19:41, 1.80it/s] 55%|█████▍ | 2561/4692 [27:35<19:36, 1.81it/s] 55%|█████▍ | 2562/4692 [27:36<19:35, 1.81it/s] 55%|█████▍ | 2563/4692 [27:36<19:40, 1.80it/s] 55%|█████▍ | 2564/4692 [27:37<19:34, 1.81it/s] 55%|█████▍ | 2565/4692 [27:37<19:30, 1.82it/s] 55%|█████▍ | 2566/4692 [27:38<19:27, 1.82it/s] 55%|█████▍ | 2567/4692 [27:39<19:32, 1.81it/s] 55%|█████▍ | 2568/4692 [27:39<19:41, 1.80it/s] 55%|█████▍ | 2569/4692 [27:40<19:37, 1.80it/s] 55%|█████▍ | 2570/4692 [27:40<19:30, 1.81it/s] 55%|█████▍ | 2571/4692 [27:41<19:36, 1.80it/s] 55%|█████▍ | 2572/4692 [27:41<19:34, 1.81it/s] 55%|█████▍ | 2573/4692 [27:42<19:30, 1.81it/s] 55%|█████▍ | 2574/4692 [27:42<19:33, 1.80it/s] 55%|█████▍ | 2575/4692 [27:43<19:31, 1.81it/s] 55%|█████▍ | 2576/4692 [27:44<19:26, 1.81it/s] 55%|█████▍ | 2577/4692 [27:44<19:24, 1.82it/s] 55%|█████▍ | 2578/4692 [27:45<19:22, 1.82it/s] 55%|█████▍ | 2579/4692 [27:45<19:29, 1.81it/s] 55%|█████▍ | 2580/4692 [27:46<19:29, 1.81it/s] 55%|█████▌ | 2581/4692 [27:46<19:16, 1.82it/s] 55%|█████▌ | 2582/4692 [27:47<19:22, 1.81it/s] 55%|█████▌ | 2583/4692 [27:47<19:21, 1.82it/s] 55%|█████▌ | 2584/4692 [27:48<19:18, 1.82it/s] 55%|█████▌ | 2585/4692 [27:49<19:25, 1.81it/s] 55%|█████▌ | 2586/4692 [27:49<19:23, 1.81it/s] 55%|█████▌ | 2587/4692 [27:50<19:25, 1.81it/s] 55%|█████▌ | 2588/4692 [27:50<19:27, 1.80it/s] 55%|█████▌ | 2589/4692 [27:51<19:29, 1.80it/s] 55%|█████▌ | 2590/4692 [27:51<19:23, 1.81it/s] 55%|█████▌ | 2591/4692 [27:52<19:18, 1.81it/s] 55%|█████▌ | 2592/4692 [27:52<19:23, 1.80it/s] 55%|█████▌ | 2593/4692 [27:53<19:21, 1.81it/s] 55%|█████▌ | 2594/4692 [27:54<19:16, 1.81it/s] 55%|█████▌ | 2595/4692 [27:54<19:22, 1.80it/s] 55%|█████▌ | 2596/4692 [27:55<19:20, 1.81it/s] 55%|█████▌ | 2597/4692 [27:55<19:16, 1.81it/s] 55%|█████▌ | 2598/4692 [27:56<19:20, 1.80it/s] 55%|█████▌ | 2599/4692 [27:56<19:17, 1.81it/s] 55%|█████▌ | 2600/4692 [27:57<19:18, 1.81it/s] 55%|█████▌ | 2601/4692 [27:57<19:12, 1.81it/s] 55%|█████▌ | 2602/4692 [27:58<19:16, 1.81it/s] 55%|█████▌ | 2603/4692 [27:58<19:10, 1.82it/s] 55%|█████▌ | 2604/4692 [27:59<19:11, 1.81it/s] 56%|█████▌ | 2605/4692 [28:00<19:16, 1.81it/s] 56%|█████▌ | 2606/4692 [28:00<19:20, 1.80it/s] 56%|█████▌ | 2607/4692 [28:01<19:15, 1.80it/s] 56%|█████▌ | 2608/4692 [28:01<19:07, 1.82it/s] 56%|█████▌ | 2609/4692 [28:02<19:14, 1.80it/s] 56%|█████▌ | 2610/4692 [28:02<19:10, 1.81it/s] 56%|█████▌ | 2611/4692 [28:03<19:11, 1.81it/s] 56%|█████▌ | 2612/4692 [28:03<19:14, 1.80it/s] 56%|█████▌ | 2613/4692 [28:04<19:16, 1.80it/s] 56%|█████▌ | 2614/4692 [28:05<19:14, 1.80it/s] 56%|█████▌ | 2615/4692 [28:05<19:12, 1.80it/s] 56%|█████▌ | 2616/4692 [28:06<19:18, 1.79it/s] 56%|█████▌ | 2617/4692 [28:06<19:14, 1.80it/s] 56%|█████▌ | 2618/4692 [28:07<19:12, 1.80it/s] 56%|█████▌ | 2619/4692 [28:07<19:09, 1.80it/s] 56%|█████▌ | 2620/4692 [28:08<19:12, 1.80it/s] 56%|█████▌ | 2621/4692 [28:08<19:17, 1.79it/s] 56%|█████▌ | 2622/4692 [28:09<19:17, 1.79it/s] 56%|█████▌ | 2623/4692 [28:10<19:14, 1.79it/s] 56%|█████▌ | 2624/4692 [28:10<19:15, 1.79it/s] 56%|█████▌ | 2625/4692 [28:11<19:16, 1.79it/s] 56%|█████▌ | 2626/4692 [28:11<19:21, 1.78it/s] 56%|█████▌ | 2627/4692 [28:12<19:24, 1.77it/s] 56%|█████▌ | 2628/4692 [28:12<19:20, 1.78it/s] 56%|█████▌ | 2629/4692 [28:13<19:21, 1.78it/s] 56%|█████▌ | 2630/4692 [28:14<19:21, 1.78it/s] 56%|█████▌ | 2631/4692 [28:14<19:31, 1.76it/s] 56%|█████▌ | 2632/4692 [28:15<19:25, 1.77it/s] 56%|█████▌ | 2633/4692 [28:15<19:23, 1.77it/s] 56%|█████▌ | 2634/4692 [28:16<19:12, 1.79it/s] 56%|█████▌ | 2635/4692 [28:16<19:14, 1.78it/s] 56%|█████▌ | 2636/4692 [28:17<19:20, 1.77it/s] 56%|█████▌ | 2637/4692 [28:17<19:10, 1.79it/s] 56%|█████▌ | 2638/4692 [28:18<19:02, 1.80it/s] 56%|█████▌ | 2639/4692 [28:19<19:07, 1.79it/s] 56%|█████▋ | 2640/4692 [28:19<19:06, 1.79it/s] 56%|█████▋ | 2641/4692 [28:20<19:10, 1.78it/s] 56%|█████▋ | 2642/4692 [28:20<19:10, 1.78it/s] 56%|█████▋ | 2643/4692 [28:21<19:13, 1.78it/s] 56%|█████▋ | 2644/4692 [28:21<19:15, 1.77it/s] 56%|█████▋ | 2645/4692 [28:22<19:11, 1.78it/s] 56%|█████▋ | 2646/4692 [28:23<19:05, 1.79it/s] 56%|█████▋ | 2647/4692 [28:23<19:10, 1.78it/s] 56%|█████▋ | 2648/4692 [28:24<19:09, 1.78it/s] 56%|█████▋ | 2649/4692 [28:24<19:09, 1.78it/s] 56%|█████▋ | 2650/4692 [28:25<19:04, 1.78it/s] 57%|█████▋ | 2651/4692 [28:25<19:04, 1.78it/s] 57%|█████▋ | 2652/4692 [28:26<19:03, 1.78it/s] 57%|█████▋ | 2653/4692 [28:26<19:06, 1.78it/s] 57%|█████▋ | 2654/4692 [28:27<19:01, 1.79it/s] 57%|█████▋ | 2655/4692 [28:28<19:03, 1.78it/s] 57%|█████▋ | 2656/4692 [28:28<18:56, 1.79it/s] 57%|█████▋ | 2657/4692 [28:29<19:00, 1.79it/s] 57%|█████▋ | 2658/4692 [28:29<19:11, 1.77it/s] 57%|█████▋ | 2659/4692 [28:30<19:02, 1.78it/s] 57%|█████▋ | 2660/4692 [28:30<19:01, 1.78it/s] 57%|█████▋ | 2661/4692 [28:31<19:13, 1.76it/s] 57%|█████▋ | 2662/4692 [28:32<18:59, 1.78it/s] 57%|█████▋ | 2663/4692 [28:32<19:09, 1.77it/s] 57%|█████▋ | 2664/4692 [28:33<19:05, 1.77it/s] 57%|█████▋ | 2665/4692 [28:33<19:03, 1.77it/s] 57%|█████▋ | 2666/4692 [28:34<19:06, 1.77it/s] 57%|█████▋ | 2667/4692 [28:34<18:52, 1.79it/s] 57%|█████▋ | 2668/4692 [28:35<18:59, 1.78it/s] 57%|█████▋ | 2669/4692 [28:35<18:42, 1.80it/s] 57%|█████▋ | 2670/4692 [28:36<18:42, 1.80it/s] 57%|█████▋ | 2671/4692 [28:37<18:52, 1.78it/s] 57%|█████▋ | 2672/4692 [28:37<18:45, 1.79it/s] 57%|█████▋ | 2673/4692 [28:38<19:03, 1.77it/s] 57%|█████▋ | 2674/4692 [28:38<18:55, 1.78it/s] 57%|█████▋ | 2675/4692 [28:39<19:01, 1.77it/s] 57%|█████▋ | 2676/4692 [28:39<19:12, 1.75it/s] 57%|█████▋ | 2677/4692 [28:40<19:02, 1.76it/s] 57%|█████▋ | 2678/4692 [28:41<18:57, 1.77it/s] 57%|█████▋ | 2679/4692 [28:41<19:10, 1.75it/s] 57%|█████▋ | 2680/4692 [28:42<18:57, 1.77it/s] 57%|█████▋ | 2681/4692 [28:42<19:01, 1.76it/s] 57%|█████▋ | 2682/4692 [28:43<19:08, 1.75it/s] 57%|█████▋ | 2683/4692 [28:43<18:52, 1.77it/s] 57%|█████▋ | 2684/4692 [28:44<19:08, 1.75it/s] 57%|█████▋ | 2685/4692 [28:45<19:08, 1.75it/s] 57%|█████▋ | 2686/4692 [28:45<19:02, 1.76it/s] 57%|█████▋ | 2687/4692 [28:46<19:12, 1.74it/s] 57%|█████▋ | 2688/4692 [28:46<19:04, 1.75it/s] 57%|█████▋ | 2689/4692 [28:47<19:02, 1.75it/s] 57%|█████▋ | 2690/4692 [28:47<19:08, 1.74it/s] 57%|█████▋ | 2691/4692 [28:48<18:57, 1.76it/s] 57%|█████▋ | 2692/4692 [28:49<18:54, 1.76it/s] 57%|█████▋ | 2693/4692 [28:49<19:05, 1.74it/s] 57%|█████▋ | 2694/4692 [28:50<18:54, 1.76it/s] 57%|█████▋ | 2695/4692 [28:50<18:53, 1.76it/s] 57%|█████▋ | 2696/4692 [28:51<19:04, 1.74it/s] 57%|█████▋ | 2697/4692 [28:51<18:54, 1.76it/s] 58%|█████▊ | 2698/4692 [28:52<18:56, 1.75it/s] 58%|█████▊ | 2699/4692 [28:53<19:07, 1.74it/s] 58%|█████▊ | 2700/4692 [28:53<18:54, 1.76it/s] 58%|█████▊ | 2701/4692 [28:54<18:57, 1.75it/s] 58%|█████▊ | 2702/4692 [28:54<19:02, 1.74it/s] 58%|█████▊ | 2703/4692 [28:55<18:47, 1.76it/s] 58%|█████▊ | 2704/4692 [28:55<18:58, 1.75it/s] 58%|█████▊ | 2705/4692 [28:56<18:46, 1.76it/s] 58%|█████▊ | 2706/4692 [28:57<18:45, 1.76it/s] 58%|█████▊ | 2707/4692 [28:57<18:53, 1.75it/s] 58%|█████▊ | 2708/4692 [28:58<18:41, 1.77it/s] 58%|█████▊ | 2709/4692 [28:58<18:46, 1.76it/s] 58%|█████▊ | 2710/4692 [28:59<18:44, 1.76it/s] 58%|█████▊ | 2711/4692 [28:59<18:36, 1.77it/s] 58%|█████▊ | 2712/4692 [29:00<18:39, 1.77it/s] 58%|█████▊ | 2713/4692 [29:00<18:28, 1.79it/s] 58%|█████▊ | 2714/4692 [29:01<18:43, 1.76it/s] 58%|█████▊ | 2715/4692 [29:02<18:40, 1.77it/s] 58%|█████▊ | 2716/4692 [29:02<18:37, 1.77it/s] 58%|█████▊ | 2717/4692 [29:03<18:45, 1.75it/s] 58%|█████▊ | 2718/4692 [29:03<18:34, 1.77it/s] 58%|█████▊ | 2719/4692 [29:04<18:38, 1.76it/s] 58%|█████▊ | 2720/4692 [29:04<18:48, 1.75it/s] 58%|█████▊ | 2721/4692 [29:05<18:39, 1.76it/s] 58%|█████▊ | 2722/4692 [29:06<18:47, 1.75it/s] 58%|█████▊ | 2723/4692 [29:06<18:51, 1.74it/s] 58%|█████▊ | 2724/4692 [29:07<18:37, 1.76it/s] 58%|█████▊ | 2725/4692 [29:07<18:40, 1.76it/s] 58%|█████▊ | 2726/4692 [29:08<18:24, 1.78it/s] 58%|█████▊ | 2727/4692 [29:08<18:27, 1.77it/s] 58%|█████▊ | 2728/4692 [29:09<18:38, 1.76it/s] 58%|█████▊ | 2729/4692 [29:10<18:28, 1.77it/s] 58%|█████▊ | 2730/4692 [29:10<18:36, 1.76it/s] 58%|█████▊ | 2731/4692 [29:11<18:44, 1.74it/s] 58%|█████▊ | 2732/4692 [29:11<18:33, 1.76it/s] 58%|█████▊ | 2733/4692 [29:12<18:43, 1.74it/s] 58%|█████▊ | 2734/4692 [29:12<18:42, 1.74it/s] 58%|█████▊ | 2735/4692 [29:13<18:33, 1.76it/s] 58%|█████▊ | 2736/4692 [29:14<18:44, 1.74it/s] 58%|█████▊ | 2737/4692 [29:14<18:33, 1.76it/s][INFO|trainer.py:738] 2023-07-03 01:36:51,568 >> The following columns in the evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: text. If text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3069] 2023-07-03 01:36:51,572 >> ***** Running Evaluation ***** [INFO|trainer.py:3071] 2023-07-03 01:36:51,572 >> Num examples = 25000 [INFO|trainer.py:3074] 2023-07-03 01:36:51,572 >> Batch size = 64 0%| | 0/391 [00:00> Saving model checkpoint to /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-2737 [INFO|configuration_utils.py:457] 2023-07-03 01:39:02,075 >> Configuration saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-2737/config.json [INFO|modeling_utils.py:1762] 2023-07-03 01:39:02,644 >> Model weights saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-2737/pytorch_model.bin [INFO|tokenization_utils_base.py:2163] 2023-07-03 01:39:02,644 >> tokenizer config file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-2737/tokenizer_config.json [INFO|tokenization_utils_base.py:2170] 2023-07-03 01:39:02,644 >> Special tokens file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-2737/special_tokens_map.json [INFO|trainer.py:2893] 2023-07-03 01:39:03,786 >> Deleting older checkpoint [/nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-2346] due to args.save_total_limit 58%|█████▊ | 2738/4692 [31:27<21:51:16, 40.26s/it] 58%|█████▊ | 2739/4692 [31:28<15:22:54, 28.35s/it] 58%|█████▊ | 2740/4692 [31:28<10:51:06, 20.01s/it] 58%|█████▊ | 2741/4692 [31:29<7:40:51, 14.17s/it] 58%|█████▊ | 2742/4692 [31:29<5:27:51, 10.09s/it] 58%|█████▊ | 2743/4692 [31:30<3:54:49, 7.23s/it] 58%|█████▊ | 2744/4692 [31:30<2:49:38, 5.23s/it] 59%|█████▊ | 2745/4692 [31:31<2:04:02, 3.82s/it] 59%|█████▊ | 2746/4692 [31:31<1:32:15, 2.84s/it] 59%|█████▊ | 2747/4692 [31:32<1:09:55, 2.16s/it] 59%|█████▊ | 2748/4692 [31:33<54:12, 1.67s/it] 59%|█████▊ | 2749/4692 [31:33<43:22, 1.34s/it] 59%|█████▊ | 2750/4692 [31:34<35:38, 1.10s/it] 59%|█████▊ | 2751/4692 [31:34<30:15, 1.07it/s] 59%|█████▊ | 2752/4692 [31:35<26:40, 1.21it/s] 59%|█████▊ | 2753/4692 [31:35<24:04, 1.34it/s] 59%|█████▊ | 2754/4692 [31:36<22:10, 1.46it/s] 59%|█████▊ | 2755/4692 [31:36<20:53, 1.55it/s] 59%|█████▊ | 2756/4692 [31:37<20:05, 1.61it/s] 59%|█████▉ | 2757/4692 [31:38<19:30, 1.65it/s] 59%|█████▉ | 2758/4692 [31:38<18:59, 1.70it/s] 59%|█████▉ | 2759/4692 [31:39<18:35, 1.73it/s] 59%|█████▉ | 2760/4692 [31:39<18:27, 1.74it/s] 59%|█████▉ | 2761/4692 [31:40<18:13, 1.77it/s] 59%|█████▉ | 2762/4692 [31:40<18:06, 1.78it/s] 59%|█████▉ | 2763/4692 [31:41<17:57, 1.79it/s] 59%|█████▉ | 2764/4692 [31:41<17:56, 1.79it/s] 59%|█████▉ | 2765/4692 [31:42<17:47, 1.81it/s] 59%|█████▉ | 2766/4692 [31:43<17:47, 1.80it/s] 59%|█████▉ | 2767/4692 [31:43<17:53, 1.79it/s] 59%|█████▉ | 2768/4692 [31:44<17:45, 1.81it/s] 59%|█████▉ | 2769/4692 [31:44<17:47, 1.80it/s] 59%|█████▉ | 2770/4692 [31:45<17:48, 1.80it/s] 59%|█████▉ | 2771/4692 [31:45<17:50, 1.80it/s] 59%|█████▉ | 2772/4692 [31:46<17:45, 1.80it/s] 59%|█████▉ | 2773/4692 [31:46<17:41, 1.81it/s] 59%|█████▉ | 2774/4692 [31:47<17:48, 1.80it/s] 59%|█████▉ | 2775/4692 [31:48<17:40, 1.81it/s] 59%|█████▉ | 2776/4692 [31:48<17:33, 1.82it/s] 59%|█████▉ | 2777/4692 [31:49<17:38, 1.81it/s] 59%|█████▉ | 2778/4692 [31:49<17:37, 1.81it/s] 59%|█████▉ | 2779/4692 [31:50<17:31, 1.82it/s] 59%|█████▉ | 2780/4692 [31:50<17:36, 1.81it/s] 59%|█████▉ | 2781/4692 [31:51<17:33, 1.81it/s] 59%|█████▉ | 2782/4692 [31:51<17:31, 1.82it/s] 59%|█████▉ | 2783/4692 [31:52<17:36, 1.81it/s] 59%|█████▉ | 2784/4692 [31:53<17:35, 1.81it/s] 59%|█████▉ | 2785/4692 [31:53<17:30, 1.81it/s] 59%|█████▉ | 2786/4692 [31:54<17:33, 1.81it/s] 59%|█████▉ | 2787/4692 [31:54<17:31, 1.81it/s] 59%|█████▉ | 2788/4692 [31:55<17:28, 1.82it/s] 59%|█████▉ | 2789/4692 [31:55<17:30, 1.81it/s] 59%|█████▉ | 2790/4692 [31:56<17:35, 1.80it/s] 59%|█████▉ | 2791/4692 [31:56<17:32, 1.81it/s] 60%|█████▉ | 2792/4692 [31:57<17:28, 1.81it/s] 60%|█████▉ | 2793/4692 [31:57<17:28, 1.81it/s] 60%|█████▉ | 2794/4692 [31:58<17:23, 1.82it/s] 60%|█████▉ | 2795/4692 [31:59<17:27, 1.81it/s] 60%|█████▉ | 2796/4692 [31:59<17:30, 1.80it/s] 60%|█████▉ | 2797/4692 [32:00<17:26, 1.81it/s] 60%|█████▉ | 2798/4692 [32:00<17:18, 1.82it/s] 60%|█████▉ | 2799/4692 [32:01<17:32, 1.80it/s] 60%|█████▉ | 2800/4692 [32:01<17:32, 1.80it/s] 60%|█████▉ | 2801/4692 [32:02<17:46, 1.77it/s] 60%|█████▉ | 2802/4692 [32:02<17:33, 1.79it/s] 60%|█████▉ | 2803/4692 [32:03<17:38, 1.78it/s] 60%|█████▉ | 2804/4692 [32:04<17:38, 1.78it/s] 60%|█████▉ | 2805/4692 [32:04<17:33, 1.79it/s] 60%|█████▉ | 2806/4692 [32:05<17:46, 1.77it/s] 60%|█████▉ | 2807/4692 [32:05<17:40, 1.78it/s] 60%|█████▉ | 2808/4692 [32:06<17:44, 1.77it/s] 60%|█████▉ | 2809/4692 [32:06<17:53, 1.75it/s] 60%|█████▉ | 2810/4692 [32:07<17:41, 1.77it/s] 60%|█████▉ | 2811/4692 [32:08<17:46, 1.76it/s] 60%|█████▉ | 2812/4692 [32:08<17:44, 1.77it/s] 60%|█████▉ | 2813/4692 [32:09<17:48, 1.76it/s] 60%|█████▉ | 2814/4692 [32:09<17:53, 1.75it/s] 60%|█████▉ | 2815/4692 [32:10<17:38, 1.77it/s] 60%|██████ | 2816/4692 [32:10<17:39, 1.77it/s] 60%|██████ | 2817/4692 [32:11<17:49, 1.75it/s] 60%|██████ | 2818/4692 [32:12<17:39, 1.77it/s] 60%|██████ | 2819/4692 [32:12<17:49, 1.75it/s] 60%|██████ | 2820/4692 [32:13<17:47, 1.75it/s] 60%|██████ | 2821/4692 [32:13<17:44, 1.76it/s] 60%|██████ | 2822/4692 [32:14<17:50, 1.75it/s] 60%|██████ | 2823/4692 [32:14<17:38, 1.77it/s] 60%|██████ | 2824/4692 [32:15<17:43, 1.76it/s] 60%|██████ | 2825/4692 [32:16<17:50, 1.74it/s] 60%|██████ | 2826/4692 [32:16<17:37, 1.76it/s] 60%|██████ | 2827/4692 [32:17<17:41, 1.76it/s] 60%|██████ | 2828/4692 [32:17<17:49, 1.74it/s] 60%|██████ | 2829/4692 [32:18<17:38, 1.76it/s] 60%|██████ | 2830/4692 [32:18<17:45, 1.75it/s] 60%|██████ | 2831/4692 [32:19<17:41, 1.75it/s] 60%|██████ | 2832/4692 [32:20<17:37, 1.76it/s] 60%|██████ | 2833/4692 [32:20<17:42, 1.75it/s] 60%|██████ | 2834/4692 [32:21<17:35, 1.76it/s] 60%|██████ | 2835/4692 [32:21<17:36, 1.76it/s] 60%|██████ | 2836/4692 [32:22<17:41, 1.75it/s] 60%|██████ | 2837/4692 [32:22<17:31, 1.76it/s] 60%|██████ | 2838/4692 [32:23<17:35, 1.76it/s] 61%|██████ | 2839/4692 [32:24<17:46, 1.74it/s] 61%|██████ | 2840/4692 [32:24<17:34, 1.76it/s] 61%|██████ | 2841/4692 [32:25<17:38, 1.75it/s] 61%|██████ | 2842/4692 [32:25<17:34, 1.75it/s] 61%|██████ | 2843/4692 [32:26<17:31, 1.76it/s] 61%|██████ | 2844/4692 [32:26<17:39, 1.74it/s] 61%|██████ | 2845/4692 [32:27<17:24, 1.77it/s] 61%|██████ | 2846/4692 [32:28<17:23, 1.77it/s] 61%|██████ | 2847/4692 [32:28<17:33, 1.75it/s] 61%|██████ | 2848/4692 [32:29<17:20, 1.77it/s] 61%|██████ | 2849/4692 [32:29<17:29, 1.76it/s] 61%|██████ | 2850/4692 [32:30<17:34, 1.75it/s] 61%|██████ | 2851/4692 [32:30<17:25, 1.76it/s] 61%|██████ | 2852/4692 [32:31<17:34, 1.74it/s] 61%|██████ | 2853/4692 [32:31<17:23, 1.76it/s] 61%|██████ | 2854/4692 [32:32<17:26, 1.76it/s] 61%|██████ | 2855/4692 [32:33<17:33, 1.74it/s] 61%|██████ | 2856/4692 [32:33<17:13, 1.78it/s] 61%|██████ | 2857/4692 [32:34<17:24, 1.76it/s] 61%|██████ | 2858/4692 [32:34<17:30, 1.75it/s] 61%|██████ | 2859/4692 [32:35<17:20, 1.76it/s] 61%|██████ | 2860/4692 [32:36<17:29, 1.75it/s] 61%|██████ | 2861/4692 [32:36<17:22, 1.76it/s] 61%|██████ | 2862/4692 [32:37<17:24, 1.75it/s] 61%|██████ | 2863/4692 [32:37<17:28, 1.74it/s] 61%|██████ | 2864/4692 [32:38<17:18, 1.76it/s] 61%|██████ | 2865/4692 [32:38<17:17, 1.76it/s] 61%|██████ | 2866/4692 [32:39<17:24, 1.75it/s] 61%|██████ | 2867/4692 [32:39<17:12, 1.77it/s] 61%|██████ | 2868/4692 [32:40<17:17, 1.76it/s] 61%|██████ | 2869/4692 [32:41<17:26, 1.74it/s] 61%|██████ | 2870/4692 [32:41<17:12, 1.77it/s] 61%|██████ | 2871/4692 [32:42<17:20, 1.75it/s] 61%|██████ | 2872/4692 [32:42<16:58, 1.79it/s] 61%|██████ | 2873/4692 [32:43<17:03, 1.78it/s] 61%|██████▏ | 2874/4692 [32:43<17:14, 1.76it/s] 61%|██████▏ | 2875/4692 [32:44<17:02, 1.78it/s] 61%|██████▏ | 2876/4692 [32:45<17:12, 1.76it/s] 61%|██████▏ | 2877/4692 [32:45<17:01, 1.78it/s] 61%|██████▏ | 2878/4692 [32:46<17:03, 1.77it/s] 61%|██████▏ | 2879/4692 [32:46<17:11, 1.76it/s] 61%|██████▏ | 2880/4692 [32:47<16:59, 1.78it/s] 61%|██████▏ | 2881/4692 [32:47<17:00, 1.77it/s] 61%|██████▏ | 2882/4692 [32:48<17:08, 1.76it/s] 61%|██████▏ | 2883/4692 [32:49<16:59, 1.77it/s] 61%|██████▏ | 2884/4692 [32:49<17:07, 1.76it/s] 61%|██████▏ | 2885/4692 [32:50<17:13, 1.75it/s] 62%|██████▏ | 2886/4692 [32:50<17:04, 1.76it/s] 62%|██████▏ | 2887/4692 [32:51<17:11, 1.75it/s] 62%|██████▏ | 2888/4692 [32:51<17:09, 1.75it/s] 62%|██████▏ | 2889/4692 [32:52<17:03, 1.76it/s] 62%|██████▏ | 2890/4692 [32:53<17:12, 1.75it/s] 62%|██████▏ | 2891/4692 [32:53<17:05, 1.76it/s] 62%|██████▏ | 2892/4692 [32:54<17:03, 1.76it/s] 62%|██████▏ | 2893/4692 [32:54<17:09, 1.75it/s] 62%|██████▏ | 2894/4692 [32:55<16:58, 1.77it/s] 62%|██████▏ | 2895/4692 [32:55<16:54, 1.77it/s] 62%|██████▏ | 2896/4692 [32:56<16:59, 1.76it/s] 62%|██████▏ | 2897/4692 [32:56<16:51, 1.77it/s] 62%|██████▏ | 2898/4692 [32:57<16:59, 1.76it/s] 62%|██████▏ | 2899/4692 [32:58<17:05, 1.75it/s] 62%|██████▏ | 2900/4692 [32:58<16:55, 1.76it/s] 62%|██████▏ | 2901/4692 [32:59<17:03, 1.75it/s] 62%|██████▏ | 2902/4692 [32:59<17:02, 1.75it/s] 62%|██████▏ | 2903/4692 [33:00<16:55, 1.76it/s] 62%|██████▏ | 2904/4692 [33:00<17:00, 1.75it/s] 62%|██████▏ | 2905/4692 [33:01<16:51, 1.77it/s] 62%|██████▏ | 2906/4692 [33:02<16:48, 1.77it/s] 62%|██████▏ | 2907/4692 [33:02<16:58, 1.75it/s] 62%|██████▏ | 2908/4692 [33:03<16:48, 1.77it/s] 62%|██████▏ | 2909/4692 [33:03<16:45, 1.77it/s] 62%|██████▏ | 2910/4692 [33:04<16:52, 1.76it/s] 62%|██████▏ | 2911/4692 [33:04<16:43, 1.77it/s] 62%|██████▏ | 2912/4692 [33:05<16:51, 1.76it/s] 62%|██████▏ | 2913/4692 [33:06<16:55, 1.75it/s] 62%|██████▏ | 2914/4692 [33:06<16:50, 1.76it/s] 62%|██████▏ | 2915/4692 [33:07<16:57, 1.75it/s] 62%|██████▏ | 2916/4692 [33:07<16:55, 1.75it/s] 62%|██████▏ | 2917/4692 [33:08<16:48, 1.76it/s] 62%|██████▏ | 2918/4692 [33:08<16:55, 1.75it/s] 62%|██████▏ | 2919/4692 [33:09<16:45, 1.76it/s] 62%|██████▏ | 2920/4692 [33:10<16:38, 1.78it/s] 62%|██████▏ | 2921/4692 [33:10<16:45, 1.76it/s] 62%|██████▏ | 2922/4692 [33:11<16:42, 1.77it/s] 62%|██████▏ | 2923/4692 [33:11<16:41, 1.77it/s] 62%|██████▏ | 2924/4692 [33:12<16:47, 1.76it/s] 62%|██████▏ | 2925/4692 [33:12<16:38, 1.77it/s] 62%|██████▏ | 2926/4692 [33:13<16:39, 1.77it/s] 62%|██████▏ | 2927/4692 [33:14<16:47, 1.75it/s] 62%|██████▏ | 2928/4692 [33:14<16:36, 1.77it/s] 62%|██████▏ | 2929/4692 [33:15<16:45, 1.75it/s] 62%|██████▏ | 2930/4692 [33:15<16:47, 1.75it/s] 62%|██████▏ | 2931/4692 [33:16<16:39, 1.76it/s] 62%|██████▏ | 2932/4692 [33:16<16:43, 1.75it/s] 63%|██████▎ | 2933/4692 [33:17<16:33, 1.77it/s] 63%|██████▎ | 2934/4692 [33:18<16:33, 1.77it/s] 63%|██████▎ | 2935/4692 [33:18<16:44, 1.75it/s] 63%|██████▎ | 2936/4692 [33:19<16:37, 1.76it/s] 63%|██████▎ | 2937/4692 [33:19<16:37, 1.76it/s] 63%|██████▎ | 2938/4692 [33:20<16:44, 1.75it/s] 63%|██████▎ | 2939/4692 [33:20<16:34, 1.76it/s] 63%|██████▎ | 2940/4692 [33:21<16:31, 1.77it/s] 63%|██████▎ | 2941/4692 [33:22<16:39, 1.75it/s] 63%|██████▎ | 2942/4692 [33:22<16:32, 1.76it/s] 63%|██████▎ | 2943/4692 [33:23<16:31, 1.76it/s] 63%|██████▎ | 2944/4692 [33:23<16:36, 1.75it/s] 63%|██████▎ | 2945/4692 [33:24<16:26, 1.77it/s] 63%|██████▎ | 2946/4692 [33:24<16:34, 1.76it/s] 63%|██████▎ | 2947/4692 [33:25<16:35, 1.75it/s] 63%|██████▎ | 2948/4692 [33:25<16:29, 1.76it/s] 63%|██████▎ | 2949/4692 [33:26<16:38, 1.74it/s] 63%|██████▎ | 2950/4692 [33:27<16:32, 1.75it/s] 63%|██████▎ | 2951/4692 [33:27<16:32, 1.75it/s] 63%|██████▎ | 2952/4692 [33:28<16:38, 1.74it/s] 63%|██████▎ | 2953/4692 [33:28<16:29, 1.76it/s] 63%|██████▎ | 2954/4692 [33:29<16:27, 1.76it/s] 63%|██████▎ | 2955/4692 [33:29<16:35, 1.75it/s] 63%|██████▎ | 2956/4692 [33:30<16:26, 1.76it/s] 63%|██████▎ | 2957/4692 [33:31<16:28, 1.76it/s] 63%|██████▎ | 2958/4692 [33:31<16:34, 1.74it/s] 63%|██████▎ | 2959/4692 [33:32<16:24, 1.76it/s] 63%|██████▎ | 2960/4692 [33:32<16:21, 1.76it/s] 63%|██████▎ | 2961/4692 [33:33<16:28, 1.75it/s] 63%|██████▎ | 2962/4692 [33:33<16:21, 1.76it/s] 63%|██████▎ | 2963/4692 [33:34<16:27, 1.75it/s] 63%|██████▎ | 2964/4692 [33:35<16:36, 1.73it/s] 63%|██████▎ | 2965/4692 [33:35<16:26, 1.75it/s] 63%|██████▎ | 2966/4692 [33:36<16:29, 1.74it/s] 63%|██████▎ | 2967/4692 [33:36<16:27, 1.75it/s] 63%|██████▎ | 2968/4692 [33:37<16:18, 1.76it/s] 63%|██████▎ | 2969/4692 [33:37<16:30, 1.74it/s] 63%|██████▎ | 2970/4692 [33:38<16:24, 1.75it/s] 63%|██████▎ | 2971/4692 [33:39<16:21, 1.75it/s] 63%|██████▎ | 2972/4692 [33:39<16:26, 1.74it/s] 63%|██████▎ | 2973/4692 [33:40<16:14, 1.76it/s] 63%|██████▎ | 2974/4692 [33:40<16:11, 1.77it/s] 63%|██████▎ | 2975/4692 [33:41<16:19, 1.75it/s] 63%|██████▎ | 2976/4692 [33:41<16:12, 1.76it/s] 63%|██████▎ | 2977/4692 [33:42<16:12, 1.76it/s] 63%|██████▎ | 2978/4692 [33:43<16:22, 1.75it/s] 63%|██████▎ | 2979/4692 [33:43<16:10, 1.77it/s] 64%|██████▎ | 2980/4692 [33:44<16:10, 1.76it/s] 64%|██████▎ | 2981/4692 [33:44<16:14, 1.76it/s] 64%|██████▎ | 2982/4692 [33:45<16:02, 1.78it/s] 64%|██████▎ | 2983/4692 [33:45<16:11, 1.76it/s] 64%|██████▎ | 2984/4692 [33:46<16:01, 1.78it/s] 64%|██████▎ | 2985/4692 [33:47<16:05, 1.77it/s] 64%|██████▎ | 2986/4692 [33:47<16:11, 1.76it/s] 64%|██████▎ | 2987/4692 [33:48<16:05, 1.77it/s] 64%|██████▎ | 2988/4692 [33:48<16:04, 1.77it/s] 64%|██████▎ | 2989/4692 [33:49<16:14, 1.75it/s] 64%|██████▎ | 2990/4692 [33:49<16:06, 1.76it/s] 64%|██████▎ | 2991/4692 [33:50<16:11, 1.75it/s] 64%|██████▍ | 2992/4692 [33:51<16:16, 1.74it/s] 64%|██████▍ | 2993/4692 [33:51<16:03, 1.76it/s] 64%|██████▍ | 2994/4692 [33:52<16:06, 1.76it/s] 64%|██████▍ | 2995/4692 [33:52<16:05, 1.76it/s] 64%|██████▍ | 2996/4692 [33:53<16:03, 1.76it/s] 64%|██████▍ | 2997/4692 [33:53<16:09, 1.75it/s] 64%|██████▍ | 2998/4692 [33:54<16:00, 1.76it/s] 64%|██████▍ | 2999/4692 [33:55<16:03, 1.76it/s] 64%|██████▍ | 3000/4692 [33:55<16:10, 1.74it/s] 64%|██████▍ | 3000/4692 [33:55<16:10, 1.74it/s] 64%|██████▍ | 3001/4692 [33:56<16:01, 1.76it/s] 64%|██████▍ | 3002/4692 [33:56<16:04, 1.75it/s] 64%|██████▍ | 3003/4692 [33:57<16:09, 1.74it/s] 64%|██████▍ | 3004/4692 [33:57<15:59, 1.76it/s] 64%|██████▍ | 3005/4692 [33:58<15:58, 1.76it/s] 64%|██████▍ | 3006/4692 [33:59<16:06, 1.74it/s] 64%|██████▍ | 3007/4692 [33:59<15:55, 1.76it/s] 64%|██████▍ | 3008/4692 [34:00<15:54, 1.76it/s] 64%|██████▍ | 3009/4692 [34:00<16:01, 1.75it/s] 64%|██████▍ | 3010/4692 [34:01<15:53, 1.76it/s] 64%|██████▍ | 3011/4692 [34:01<16:00, 1.75it/s] 64%|██████▍ | 3012/4692 [34:02<16:00, 1.75it/s] 64%|██████▍ | 3013/4692 [34:03<15:55, 1.76it/s] 64%|██████▍ | 3014/4692 [34:03<16:04, 1.74it/s] 64%|██████▍ | 3015/4692 [34:04<15:54, 1.76it/s] 64%|██████▍ | 3016/4692 [34:04<15:52, 1.76it/s] 64%|██████▍ | 3017/4692 [34:05<15:57, 1.75it/s] 64%|██████▍ | 3018/4692 [34:05<15:50, 1.76it/s] 64%|██████▍ | 3019/4692 [34:06<15:48, 1.76it/s] 64%|██████▍ | 3020/4692 [34:06<15:49, 1.76it/s] 64%|██████▍ | 3021/4692 [34:07<15:40, 1.78it/s] 64%|██████▍ | 3022/4692 [34:08<15:47, 1.76it/s] 64%|██████▍ | 3023/4692 [34:08<15:37, 1.78it/s] 64%|██████▍ | 3024/4692 [34:09<15:35, 1.78it/s] 64%|██████▍ | 3025/4692 [34:09<15:45, 1.76it/s] 64%|██████▍ | 3026/4692 [34:10<15:35, 1.78it/s] 65%|██████▍ | 3027/4692 [34:10<15:40, 1.77it/s] 65%|██████▍ | 3028/4692 [34:11<15:35, 1.78it/s] 65%|██████▍ | 3029/4692 [34:12<15:35, 1.78it/s] 65%|██████▍ | 3030/4692 [34:12<15:43, 1.76it/s] 65%|██████▍ | 3031/4692 [34:13<15:32, 1.78it/s] 65%|██████▍ | 3032/4692 [34:13<15:38, 1.77it/s] 65%|██████▍ | 3033/4692 [34:14<15:37, 1.77it/s] 65%|██████▍ | 3034/4692 [34:14<15:37, 1.77it/s] 65%|██████▍ | 3035/4692 [34:15<15:42, 1.76it/s] 65%|██████▍ | 3036/4692 [34:16<15:29, 1.78it/s] 65%|██████▍ | 3037/4692 [34:16<15:06, 1.83it/s] 65%|██████▍ | 3038/4692 [34:16<12:48, 2.15it/s] 65%|██████▍ | 3039/4692 [34:17<11:11, 2.46it/s] 65%|██████▍ | 3040/4692 [34:17<10:04, 2.73it/s] 65%|██████▍ | 3041/4692 [34:17<09:15, 2.97it/s] 65%|██████▍ | 3042/4692 [34:17<08:40, 3.17it/s] 65%|██████▍ | 3043/4692 [34:18<08:17, 3.31it/s] 65%|██████▍ | 3044/4692 [34:18<07:59, 3.44it/s] 65%|██████▍ | 3045/4692 [34:18<10:13, 2.68it/s] 65%|██████▍ | 3046/4692 [34:19<11:39, 2.35it/s] 65%|██████▍ | 3047/4692 [34:20<12:39, 2.17it/s] 65%|██████▍ | 3048/4692 [34:20<13:27, 2.04it/s] 65%|██████▍ | 3049/4692 [34:21<13:56, 1.96it/s] 65%|██████▌ | 3050/4692 [34:21<14:20, 1.91it/s] 65%|██████▌ | 3051/4692 [34:22<14:39, 1.87it/s] 65%|██████▌ | 3052/4692 [34:22<14:53, 1.84it/s] 65%|██████▌ | 3053/4692 [34:23<15:03, 1.81it/s] 65%|██████▌ | 3054/4692 [34:23<15:13, 1.79it/s] 65%|██████▌ | 3055/4692 [34:24<15:13, 1.79it/s] 65%|██████▌ | 3056/4692 [34:25<15:15, 1.79it/s] 65%|██████▌ | 3057/4692 [34:25<15:09, 1.80it/s] 65%|██████▌ | 3058/4692 [34:26<15:14, 1.79it/s] 65%|██████▌ | 3059/4692 [34:26<15:16, 1.78it/s] 65%|██████▌ | 3060/4692 [34:27<15:14, 1.79it/s] 65%|██████▌ | 3061/4692 [34:27<15:16, 1.78it/s] 65%|██████▌ | 3062/4692 [34:28<15:14, 1.78it/s] 65%|██████▌ | 3063/4692 [34:29<15:17, 1.77it/s] 65%|██████▌ | 3064/4692 [34:29<15:18, 1.77it/s] 65%|██████▌ | 3065/4692 [34:30<15:11, 1.79it/s] 65%|██████▌ | 3066/4692 [34:30<15:08, 1.79it/s] 65%|██████▌ | 3067/4692 [34:31<15:13, 1.78it/s] 65%|██████▌ | 3068/4692 [34:31<15:11, 1.78it/s] 65%|██████▌ | 3069/4692 [34:32<15:06, 1.79it/s] 65%|██████▌ | 3070/4692 [34:32<15:11, 1.78it/s] 65%|██████▌ | 3071/4692 [34:33<15:11, 1.78it/s] 65%|██████▌ | 3072/4692 [34:34<15:12, 1.78it/s] 65%|██████▌ | 3073/4692 [34:34<15:06, 1.79it/s] 66%|██████▌ | 3074/4692 [34:35<15:07, 1.78it/s] 66%|██████▌ | 3075/4692 [34:35<15:07, 1.78it/s] 66%|██████▌ | 3076/4692 [34:36<15:12, 1.77it/s] 66%|██████▌ | 3077/4692 [34:36<15:09, 1.78it/s] 66%|██████▌ | 3078/4692 [34:37<15:09, 1.77it/s] 66%|██████▌ | 3079/4692 [34:38<15:06, 1.78it/s] 66%|██████▌ | 3080/4692 [34:38<15:08, 1.77it/s] 66%|██████▌ | 3081/4692 [34:39<15:07, 1.77it/s] 66%|██████▌ | 3082/4692 [34:39<15:03, 1.78it/s] 66%|██████▌ | 3083/4692 [34:40<15:03, 1.78it/s] 66%|██████▌ | 3084/4692 [34:40<15:05, 1.78it/s] 66%|██████▌ | 3085/4692 [34:41<15:07, 1.77it/s] 66%|██████▌ | 3086/4692 [34:41<15:03, 1.78it/s] 66%|██████▌ | 3087/4692 [34:42<15:01, 1.78it/s] 66%|██████▌ | 3088/4692 [34:43<15:02, 1.78it/s] 66%|██████▌ | 3089/4692 [34:43<14:57, 1.79it/s] 66%|██████▌ | 3090/4692 [34:44<14:52, 1.80it/s] 66%|██████▌ | 3091/4692 [34:44<14:57, 1.78it/s] 66%|██████▌ | 3092/4692 [34:45<15:00, 1.78it/s] 66%|██████▌ | 3093/4692 [34:45<15:06, 1.76it/s] 66%|██████▌ | 3094/4692 [34:46<14:56, 1.78it/s] 66%|██████▌ | 3095/4692 [34:47<14:53, 1.79it/s] 66%|██████▌ | 3096/4692 [34:47<14:57, 1.78it/s] 66%|██████▌ | 3097/4692 [34:48<14:59, 1.77it/s] 66%|██████▌ | 3098/4692 [34:48<14:52, 1.79it/s] 66%|██████▌ | 3099/4692 [34:49<14:52, 1.78it/s] 66%|██████▌ | 3100/4692 [34:49<14:54, 1.78it/s] 66%|██████▌ | 3101/4692 [34:50<14:56, 1.77it/s] 66%|██████▌ | 3102/4692 [34:50<14:54, 1.78it/s] 66%|██████▌ | 3103/4692 [34:51<14:56, 1.77it/s] 66%|██████▌ | 3104/4692 [34:52<14:52, 1.78it/s] 66%|██████▌ | 3105/4692 [34:52<14:50, 1.78it/s] 66%|██████▌ | 3106/4692 [34:53<14:43, 1.79it/s] 66%|██████▌ | 3107/4692 [34:53<14:48, 1.78it/s] 66%|██████▌ | 3108/4692 [34:54<14:52, 1.78it/s] 66%|██████▋ | 3109/4692 [34:54<14:49, 1.78it/s] 66%|██████▋ | 3110/4692 [34:55<14:43, 1.79it/s] 66%|██████▋ | 3111/4692 [34:56<14:46, 1.78it/s] 66%|██████▋ | 3112/4692 [34:56<14:40, 1.79it/s] 66%|██████▋ | 3113/4692 [34:57<14:44, 1.79it/s] 66%|██████▋ | 3114/4692 [34:57<14:40, 1.79it/s] 66%|██████▋ | 3115/4692 [34:58<14:42, 1.79it/s] 66%|██████▋ | 3116/4692 [34:58<14:41, 1.79it/s] 66%|██████▋ | 3117/4692 [34:59<14:43, 1.78it/s] 66%|██████▋ | 3118/4692 [34:59<14:44, 1.78it/s] 66%|██████▋ | 3119/4692 [35:00<14:42, 1.78it/s] 66%|██████▋ | 3120/4692 [35:01<14:41, 1.78it/s] 67%|██████▋ | 3121/4692 [35:01<14:35, 1.79it/s] 67%|██████▋ | 3122/4692 [35:02<14:28, 1.81it/s] 67%|██████▋ | 3123/4692 [35:02<14:32, 1.80it/s] 67%|██████▋ | 3124/4692 [35:03<14:25, 1.81it/s] 67%|██████▋ | 3125/4692 [35:03<14:24, 1.81it/s] 67%|██████▋ | 3126/4692 [35:04<14:27, 1.80it/s] 67%|██████▋ | 3127/4692 [35:04<14:24, 1.81it/s] 67%|██████▋ | 3128/4692 [35:05<11:37, 2.24it/s][INFO|trainer.py:738] 2023-07-03 01:42:42,025 >> The following columns in the evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: text. If text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3069] 2023-07-03 01:42:42,030 >> ***** Running Evaluation ***** [INFO|trainer.py:3071] 2023-07-03 01:42:42,030 >> Num examples = 25000 [INFO|trainer.py:3074] 2023-07-03 01:42:42,030 >> Batch size = 64 0%| | 0/391 [00:00> Saving model checkpoint to /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-3128 [INFO|configuration_utils.py:457] 2023-07-03 01:44:54,515 >> Configuration saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-3128/config.json [INFO|modeling_utils.py:1762] 2023-07-03 01:44:55,086 >> Model weights saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-3128/pytorch_model.bin [INFO|tokenization_utils_base.py:2163] 2023-07-03 01:44:55,087 >> tokenizer config file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-3128/tokenizer_config.json [INFO|tokenization_utils_base.py:2170] 2023-07-03 01:44:55,087 >> Special tokens file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-3128/special_tokens_map.json [INFO|trainer.py:2893] 2023-07-03 01:44:56,205 >> Deleting older checkpoint [/nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-1564] due to args.save_total_limit [INFO|trainer.py:2893] 2023-07-03 01:44:56,364 >> Deleting older checkpoint [/nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-2737] due to args.save_total_limit 67%|██████▋ | 3129/4692 [37:20<17:43:35, 40.83s/it] 67%|██████▋ | 3130/4692 [37:20<12:28:18, 28.74s/it] 67%|██████▋ | 3131/4692 [37:21<8:48:03, 20.30s/it] 67%|██████▋ | 3132/4692 [37:21<6:13:39, 14.37s/it] 67%|██████▋ | 3133/4692 [37:22<4:25:44, 10.23s/it] 67%|██████▋ | 3134/4692 [37:22<3:10:24, 7.33s/it] 67%|██████▋ | 3135/4692 [37:23<2:17:31, 5.30s/it] 67%|██████▋ | 3136/4692 [37:24<1:40:46, 3.89s/it] 67%|██████▋ | 3137/4692 [37:24<1:15:05, 2.90s/it] 67%|██████▋ | 3138/4692 [37:25<56:51, 2.20s/it] 67%|██████▋ | 3139/4692 [37:25<44:19, 1.71s/it] 67%|██████▋ | 3140/4692 [37:26<35:31, 1.37s/it] 67%|██████▋ | 3141/4692 [37:26<29:13, 1.13s/it] 67%|██████▋ | 3142/4692 [37:27<24:57, 1.04it/s] 67%|██████▋ | 3143/4692 [37:28<21:46, 1.19it/s] 67%|██████▋ | 3144/4692 [37:28<19:40, 1.31it/s] 67%|██████▋ | 3145/4692 [37:29<18:17, 1.41it/s] 67%|██████▋ | 3146/4692 [37:29<17:04, 1.51it/s] 67%|██████▋ | 3147/4692 [37:30<16:20, 1.58it/s] 67%|██████▋ | 3148/4692 [37:31<15:57, 1.61it/s] 67%|██████▋ | 3149/4692 [37:31<15:27, 1.66it/s] 67%|██████▋ | 3150/4692 [37:32<15:17, 1.68it/s] 67%|██████▋ | 3151/4692 [37:32<15:12, 1.69it/s] 67%|██████▋ | 3152/4692 [37:33<14:54, 1.72it/s] 67%|██████▋ | 3153/4692 [37:33<14:53, 1.72it/s] 67%|██████▋ | 3154/4692 [37:34<14:46, 1.74it/s] 67%|██████▋ | 3155/4692 [37:34<14:43, 1.74it/s] 67%|██████▋ | 3156/4692 [37:35<14:48, 1.73it/s] 67%|██████▋ | 3157/4692 [37:36<14:37, 1.75it/s] 67%|██████▋ | 3158/4692 [37:36<14:33, 1.76it/s] 67%|██████▋ | 3159/4692 [37:37<14:42, 1.74it/s] 67%|██████▋ | 3160/4692 [37:37<14:33, 1.75it/s] 67%|██████▋ | 3161/4692 [37:38<14:32, 1.76it/s] 67%|██████▋ | 3162/4692 [37:39<14:40, 1.74it/s] 67%|██████▋ | 3163/4692 [37:39<14:29, 1.76it/s] 67%|██████▋ | 3164/4692 [37:40<14:30, 1.76it/s] 67%|██████▋ | 3165/4692 [37:40<14:36, 1.74it/s] 67%|██████▋ | 3166/4692 [37:41<14:27, 1.76it/s] 67%|██████▋ | 3167/4692 [37:41<14:32, 1.75it/s] 68%|██████▊ | 3168/4692 [37:42<14:37, 1.74it/s] 68%|██████▊ | 3169/4692 [37:42<14:27, 1.76it/s] 68%|██████▊ | 3170/4692 [37:43<14:32, 1.75it/s] 68%|██████▊ | 3171/4692 [37:44<14:26, 1.76it/s] 68%|██████▊ | 3172/4692 [37:44<14:27, 1.75it/s] 68%|██████▊ | 3173/4692 [37:45<14:34, 1.74it/s] 68%|██████▊ | 3174/4692 [37:45<14:28, 1.75it/s] 68%|██████▊ | 3175/4692 [37:46<14:32, 1.74it/s] 68%|██████▊ | 3176/4692 [37:47<14:35, 1.73it/s] 68%|██████▊ | 3177/4692 [37:47<14:27, 1.75it/s] 68%|██████▊ | 3178/4692 [37:47<12:19, 2.05it/s] 68%|██████▊ | 3179/4692 [37:48<10:44, 2.35it/s] 68%|██████▊ | 3180/4692 [37:48<09:45, 2.58it/s] 68%|██████▊ | 3181/4692 [37:48<09:03, 2.78it/s] 68%|██████▊ | 3182/4692 [37:49<08:34, 2.93it/s] 68%|██████▊ | 3183/4692 [37:49<08:07, 3.09it/s] 68%|██████▊ | 3184/4692 [37:49<07:48, 3.22it/s] 68%|██████▊ | 3185/4692 [37:50<09:27, 2.66it/s] 68%|██████▊ | 3186/4692 [37:50<10:47, 2.33it/s] 68%|██████▊ | 3187/4692 [37:51<11:52, 2.11it/s] 68%|██████▊ | 3188/4692 [37:51<12:30, 2.00it/s] 68%|██████▊ | 3189/4692 [37:52<12:51, 1.95it/s] 68%|██████▊ | 3190/4692 [37:52<13:04, 1.91it/s] 68%|██████▊ | 3191/4692 [37:53<13:17, 1.88it/s] 68%|██████▊ | 3192/4692 [37:54<13:30, 1.85it/s] 68%|██████▊ | 3193/4692 [37:54<13:40, 1.83it/s] 68%|██████▊ | 3194/4692 [37:55<13:40, 1.83it/s] 68%|██████▊ | 3195/4692 [37:55<13:41, 1.82it/s] 68%|██████▊ | 3196/4692 [37:56<13:47, 1.81it/s] 68%|██████▊ | 3197/4692 [37:56<13:46, 1.81it/s] 68%|██████▊ | 3198/4692 [37:57<13:40, 1.82it/s] 68%|██████▊ | 3199/4692 [37:57<13:43, 1.81it/s] 68%|██████▊ | 3200/4692 [37:58<13:46, 1.80it/s] 68%|██████▊ | 3201/4692 [37:59<13:49, 1.80it/s] 68%|██████▊ | 3202/4692 [37:59<13:46, 1.80it/s] 68%|██████▊ | 3203/4692 [38:00<13:43, 1.81it/s] 68%|██████▊ | 3204/4692 [38:00<13:42, 1.81it/s] 68%|██████▊ | 3205/4692 [38:01<13:47, 1.80it/s] 68%|██████▊ | 3206/4692 [38:01<13:43, 1.80it/s] 68%|██████▊ | 3207/4692 [38:02<13:40, 1.81it/s] 68%|██████▊ | 3208/4692 [38:02<13:43, 1.80it/s] 68%|██████▊ | 3209/4692 [38:03<13:41, 1.81it/s] 68%|██████▊ | 3210/4692 [38:04<13:38, 1.81it/s] 68%|██████▊ | 3211/4692 [38:04<13:42, 1.80it/s] 68%|██████▊ | 3212/4692 [38:05<13:38, 1.81it/s] 68%|██████▊ | 3213/4692 [38:05<13:31, 1.82it/s] 68%|██████▊ | 3214/4692 [38:06<13:38, 1.81it/s] 69%|██████▊ | 3215/4692 [38:06<13:35, 1.81it/s] 69%|██████▊ | 3216/4692 [38:07<13:30, 1.82it/s] 69%|██████▊ | 3217/4692 [38:07<13:34, 1.81it/s] 69%|██████▊ | 3218/4692 [38:08<13:32, 1.81it/s] 69%|██████▊ | 3219/4692 [38:08<13:25, 1.83it/s] 69%|██████▊ | 3220/4692 [38:09<13:29, 1.82it/s] 69%|██████▊ | 3221/4692 [38:10<13:28, 1.82it/s] 69%|██████▊ | 3222/4692 [38:10<13:26, 1.82it/s] 69%|██████▊ | 3223/4692 [38:11<13:33, 1.81it/s] 69%|██████▊ | 3224/4692 [38:11<13:31, 1.81it/s] 69%|██████▊ | 3225/4692 [38:12<13:30, 1.81it/s] 69%|██████▉ | 3226/4692 [38:12<13:31, 1.81it/s] 69%|██████▉ | 3227/4692 [38:13<13:29, 1.81it/s] 69%|██████▉ | 3228/4692 [38:13<13:29, 1.81it/s] 69%|██████▉ | 3229/4692 [38:14<13:31, 1.80it/s] 69%|██████▉ | 3230/4692 [38:15<13:34, 1.80it/s] 69%|██████▉ | 3231/4692 [38:15<13:27, 1.81it/s] 69%|██████▉ | 3232/4692 [38:16<13:27, 1.81it/s] 69%|██████▉ | 3233/4692 [38:16<13:31, 1.80it/s] 69%|██████▉ | 3234/4692 [38:17<13:30, 1.80it/s] 69%|██████▉ | 3235/4692 [38:17<13:24, 1.81it/s] 69%|██████▉ | 3236/4692 [38:18<13:26, 1.80it/s] 69%|██████▉ | 3237/4692 [38:18<13:28, 1.80it/s] 69%|██████▉ | 3238/4692 [38:19<13:29, 1.80it/s] 69%|██████▉ | 3239/4692 [38:20<13:26, 1.80it/s] 69%|██████▉ | 3240/4692 [38:20<13:23, 1.81it/s] 69%|██████▉ | 3241/4692 [38:21<13:25, 1.80it/s] 69%|██████▉ | 3242/4692 [38:21<13:22, 1.81it/s] 69%|██████▉ | 3243/4692 [38:22<13:19, 1.81it/s] 69%|██████▉ | 3244/4692 [38:22<13:23, 1.80it/s] 69%|██████▉ | 3245/4692 [38:23<13:27, 1.79it/s] 69%|██████▉ | 3246/4692 [38:23<13:25, 1.79it/s] 69%|██████▉ | 3247/4692 [38:24<13:25, 1.79it/s] 69%|██████▉ | 3248/4692 [38:25<13:26, 1.79it/s] 69%|██████▉ | 3249/4692 [38:25<13:23, 1.80it/s] 69%|██████▉ | 3250/4692 [38:26<13:23, 1.79it/s] 69%|██████▉ | 3251/4692 [38:26<13:21, 1.80it/s] 69%|██████▉ | 3252/4692 [38:27<13:21, 1.80it/s] 69%|██████▉ | 3253/4692 [38:27<13:26, 1.78it/s] 69%|██████▉ | 3254/4692 [38:28<13:27, 1.78it/s] 69%|██████▉ | 3255/4692 [38:28<13:30, 1.77it/s] 69%|██████▉ | 3256/4692 [38:29<13:25, 1.78it/s] 69%|██████▉ | 3257/4692 [38:30<13:22, 1.79it/s] 69%|██████▉ | 3258/4692 [38:30<13:18, 1.80it/s] 69%|██████▉ | 3259/4692 [38:31<13:21, 1.79it/s] 69%|██████▉ | 3260/4692 [38:31<13:21, 1.79it/s] 70%|██████▉ | 3261/4692 [38:32<13:21, 1.79it/s] 70%|██████▉ | 3262/4692 [38:32<13:20, 1.79it/s] 70%|██████▉ | 3263/4692 [38:33<13:20, 1.79it/s] 70%|██████▉ | 3264/4692 [38:34<13:23, 1.78it/s] 70%|██████▉ | 3265/4692 [38:34<13:19, 1.79it/s] 70%|██████▉ | 3266/4692 [38:35<13:20, 1.78it/s] 70%|██████▉ | 3267/4692 [38:35<13:17, 1.79it/s] 70%|██████▉ | 3268/4692 [38:36<13:20, 1.78it/s] 70%|██████▉ | 3269/4692 [38:36<13:16, 1.79it/s] 70%|██████▉ | 3270/4692 [38:37<13:17, 1.78it/s] 70%|██████▉ | 3271/4692 [38:37<13:15, 1.79it/s] 70%|██████▉ | 3272/4692 [38:38<13:19, 1.78it/s] 70%|██████▉ | 3273/4692 [38:39<13:21, 1.77it/s] 70%|██████▉ | 3274/4692 [38:39<13:17, 1.78it/s] 70%|██████▉ | 3275/4692 [38:40<13:13, 1.79it/s] 70%|██████▉ | 3276/4692 [38:40<13:10, 1.79it/s] 70%|██████▉ | 3277/4692 [38:41<13:07, 1.80it/s] 70%|██████▉ | 3278/4692 [38:41<13:08, 1.79it/s] 70%|██████▉ | 3279/4692 [38:42<13:05, 1.80it/s] 70%|██████▉ | 3280/4692 [38:42<13:07, 1.79it/s] 70%|██████▉ | 3281/4692 [38:43<13:09, 1.79it/s] 70%|██████▉ | 3282/4692 [38:44<13:07, 1.79it/s] 70%|██████▉ | 3283/4692 [38:44<13:03, 1.80it/s] 70%|██████▉ | 3284/4692 [38:45<13:06, 1.79it/s] 70%|███████ | 3285/4692 [38:45<13:05, 1.79it/s] 70%|███████ | 3286/4692 [38:46<13:04, 1.79it/s] 70%|███████ | 3287/4692 [38:46<13:01, 1.80it/s] 70%|███████ | 3288/4692 [38:47<13:01, 1.80it/s] 70%|███████ | 3289/4692 [38:47<13:04, 1.79it/s] 70%|███████ | 3290/4692 [38:48<13:00, 1.80it/s] 70%|███████ | 3291/4692 [38:49<13:01, 1.79it/s] 70%|███████ | 3292/4692 [38:49<13:02, 1.79it/s] 70%|███████ | 3293/4692 [38:50<13:00, 1.79it/s] 70%|███████ | 3294/4692 [38:50<13:03, 1.78it/s] 70%|███████ | 3295/4692 [38:51<12:59, 1.79it/s] 70%|███████ | 3296/4692 [38:51<12:56, 1.80it/s] 70%|███████ | 3297/4692 [38:52<12:56, 1.80it/s] 70%|███████ | 3298/4692 [38:53<12:56, 1.80it/s] 70%|███████ | 3299/4692 [38:53<13:00, 1.79it/s] 70%|███████ | 3300/4692 [38:54<12:56, 1.79it/s] 70%|███████ | 3301/4692 [38:54<12:58, 1.79it/s] 70%|███████ | 3302/4692 [38:55<12:57, 1.79it/s] 70%|███████ | 3303/4692 [38:55<12:58, 1.78it/s] 70%|███████ | 3304/4692 [38:56<13:02, 1.77it/s] 70%|███████ | 3305/4692 [38:56<12:58, 1.78it/s] 70%|███████ | 3306/4692 [38:57<13:00, 1.78it/s] 70%|███████ | 3307/4692 [38:58<12:56, 1.78it/s] 71%|███████ | 3308/4692 [38:58<12:59, 1.78it/s] 71%|███████ | 3309/4692 [38:59<12:58, 1.78it/s] 71%|███████ | 3310/4692 [38:59<12:56, 1.78it/s] 71%|███████ | 3311/4692 [39:00<12:55, 1.78it/s] 71%|███████ | 3312/4692 [39:00<12:52, 1.79it/s] 71%|███████ | 3313/4692 [39:01<12:53, 1.78it/s] 71%|███████ | 3314/4692 [39:01<12:47, 1.79it/s] 71%|███████ | 3315/4692 [39:02<12:42, 1.81it/s] 71%|███████ | 3316/4692 [39:03<12:43, 1.80it/s] 71%|███████ | 3317/4692 [39:03<12:39, 1.81it/s] 71%|███████ | 3318/4692 [39:04<12:36, 1.82it/s] 71%|███████ | 3319/4692 [39:04<12:35, 1.82it/s] 71%|███████ | 3320/4692 [39:05<12:32, 1.82it/s] 71%|███████ | 3321/4692 [39:05<12:33, 1.82it/s] 71%|███████ | 3322/4692 [39:06<12:36, 1.81it/s] 71%|███████ | 3323/4692 [39:06<12:32, 1.82it/s] 71%|███████ | 3324/4692 [39:07<12:33, 1.82it/s] 71%|███████ | 3325/4692 [39:08<12:36, 1.81it/s] 71%|███████ | 3326/4692 [39:08<12:35, 1.81it/s] 71%|███████ | 3327/4692 [39:09<12:28, 1.82it/s] 71%|███████ | 3328/4692 [39:09<12:41, 1.79it/s] 71%|███████ | 3329/4692 [39:10<12:39, 1.79it/s] 71%|███████ | 3330/4692 [39:10<12:38, 1.80it/s] 71%|███████ | 3331/4692 [39:11<12:44, 1.78it/s] 71%|███████ | 3332/4692 [39:11<12:37, 1.80it/s] 71%|███████ | 3333/4692 [39:12<12:43, 1.78it/s] 71%|███████ | 3334/4692 [39:13<12:36, 1.80it/s] 71%|███████ | 3335/4692 [39:13<12:36, 1.79it/s] 71%|███████ | 3336/4692 [39:14<12:41, 1.78it/s] 71%|███████ | 3337/4692 [39:14<12:38, 1.79it/s] 71%|███████ | 3338/4692 [39:15<12:44, 1.77it/s] 71%|███████ | 3339/4692 [39:15<12:34, 1.79it/s] 71%|███████ | 3340/4692 [39:16<12:39, 1.78it/s] 71%|███████ | 3341/4692 [39:16<12:42, 1.77it/s] 71%|███████ | 3342/4692 [39:17<12:40, 1.78it/s] 71%|███████ | 3343/4692 [39:18<12:46, 1.76it/s] 71%|███████▏ | 3344/4692 [39:18<12:41, 1.77it/s] 71%|███████▏ | 3345/4692 [39:19<12:43, 1.76it/s] 71%|███████▏ | 3346/4692 [39:19<12:50, 1.75it/s] 71%|███████▏ | 3347/4692 [39:20<12:43, 1.76it/s] 71%|███████▏ | 3348/4692 [39:20<12:40, 1.77it/s] 71%|███████▏ | 3349/4692 [39:21<12:46, 1.75it/s] 71%|███████▏ | 3350/4692 [39:22<12:37, 1.77it/s] 71%|███████▏ | 3351/4692 [39:22<12:39, 1.77it/s] 71%|███████▏ | 3352/4692 [39:23<12:46, 1.75it/s] 71%|███████▏ | 3353/4692 [39:23<12:38, 1.77it/s] 71%|███████▏ | 3354/4692 [39:24<12:41, 1.76it/s] 72%|███████▏ | 3355/4692 [39:24<12:41, 1.76it/s] 72%|███████▏ | 3356/4692 [39:25<12:38, 1.76it/s] 72%|███████▏ | 3357/4692 [39:26<12:45, 1.74it/s] 72%|███████▏ | 3358/4692 [39:26<12:40, 1.75it/s] 72%|███████▏ | 3359/4692 [39:27<12:39, 1.76it/s] 72%|███████▏ | 3360/4692 [39:27<12:44, 1.74it/s] 72%|███████▏ | 3361/4692 [39:28<12:36, 1.76it/s] 72%|███████▏ | 3362/4692 [39:28<12:35, 1.76it/s] 72%|███████▏ | 3363/4692 [39:29<12:40, 1.75it/s] 72%|███████▏ | 3364/4692 [39:30<12:31, 1.77it/s] 72%|███████▏ | 3365/4692 [39:30<12:30, 1.77it/s] 72%|███████▏ | 3366/4692 [39:31<12:36, 1.75it/s] 72%|███████▏ | 3367/4692 [39:31<12:30, 1.76it/s] 72%|███████▏ | 3368/4692 [39:32<12:34, 1.75it/s] 72%|███████▏ | 3369/4692 [39:32<12:38, 1.75it/s] 72%|███████▏ | 3370/4692 [39:33<12:31, 1.76it/s] 72%|███████▏ | 3371/4692 [39:34<12:36, 1.75it/s] 72%|███████▏ | 3372/4692 [39:34<12:33, 1.75it/s] 72%|███████▏ | 3373/4692 [39:35<12:28, 1.76it/s] 72%|███████▏ | 3374/4692 [39:35<12:35, 1.74it/s] 72%|███████▏ | 3375/4692 [39:36<12:27, 1.76it/s] 72%|███████▏ | 3376/4692 [39:36<12:26, 1.76it/s] 72%|███████▏ | 3377/4692 [39:37<12:29, 1.75it/s] 72%|███████▏ | 3378/4692 [39:38<12:22, 1.77it/s] 72%|███████▏ | 3379/4692 [39:38<12:26, 1.76it/s] 72%|███████▏ | 3380/4692 [39:39<12:23, 1.77it/s] 72%|███████▏ | 3381/4692 [39:39<12:21, 1.77it/s] 72%|███████▏ | 3382/4692 [39:40<12:29, 1.75it/s] 72%|███████▏ | 3383/4692 [39:40<12:31, 1.74it/s] 72%|███████▏ | 3384/4692 [39:41<12:26, 1.75it/s] 72%|███████▏ | 3385/4692 [39:42<12:29, 1.74it/s] 72%|███████▏ | 3386/4692 [39:42<12:19, 1.77it/s] 72%|███████▏ | 3387/4692 [39:43<12:19, 1.76it/s] 72%|███████▏ | 3388/4692 [39:43<12:26, 1.75it/s] 72%|███████▏ | 3389/4692 [39:44<12:18, 1.77it/s] 72%|███████▏ | 3390/4692 [39:44<12:21, 1.76it/s] 72%|███████▏ | 3391/4692 [39:45<12:20, 1.76it/s] 72%|███████▏ | 3392/4692 [39:46<12:19, 1.76it/s] 72%|███████▏ | 3393/4692 [39:46<12:26, 1.74it/s] 72%|███████▏ | 3394/4692 [39:47<12:18, 1.76it/s] 72%|███████▏ | 3395/4692 [39:47<12:15, 1.76it/s] 72%|███████▏ | 3396/4692 [39:48<12:18, 1.75it/s] 72%|███████▏ | 3397/4692 [39:48<12:08, 1.78it/s] 72%|███████▏ | 3398/4692 [39:49<12:13, 1.76it/s] 72%|███████▏ | 3399/4692 [39:50<12:17, 1.75it/s] 72%|███████▏ | 3400/4692 [39:50<12:08, 1.77it/s] 72%|███████▏ | 3401/4692 [39:51<12:13, 1.76it/s] 73%|███████▎ | 3402/4692 [39:51<12:08, 1.77it/s] 73%|███████▎ | 3403/4692 [39:52<12:08, 1.77it/s] 73%|███████▎ | 3404/4692 [39:52<12:15, 1.75it/s] 73%|███████▎ | 3405/4692 [39:53<12:07, 1.77it/s] 73%|███████▎ | 3406/4692 [39:53<12:06, 1.77it/s] 73%|███████▎ | 3407/4692 [39:54<12:14, 1.75it/s] 73%|███████▎ | 3408/4692 [39:55<12:03, 1.78it/s] 73%|███████▎ | 3409/4692 [39:55<12:09, 1.76it/s] 73%|███████▎ | 3410/4692 [39:56<12:07, 1.76it/s] 73%|███████▎ | 3411/4692 [39:56<12:09, 1.76it/s] 73%|███████▎ | 3412/4692 [39:57<12:15, 1.74it/s] 73%|███████▎ | 3413/4692 [39:57<12:06, 1.76it/s] 73%|███████▎ | 3414/4692 [39:58<12:09, 1.75it/s] 73%|███████▎ | 3415/4692 [39:59<12:12, 1.74it/s] 73%|███████▎ | 3416/4692 [39:59<12:06, 1.76it/s] 73%|███████▎ | 3417/4692 [40:00<12:07, 1.75it/s] 73%|███████▎ | 3418/4692 [40:00<12:12, 1.74it/s] 73%|███████▎ | 3419/4692 [40:01<11:59, 1.77it/s] 73%|███████▎ | 3420/4692 [40:01<12:06, 1.75it/s] 73%|███████▎ | 3421/4692 [40:02<12:05, 1.75it/s] 73%|███████▎ | 3422/4692 [40:03<12:05, 1.75it/s] 73%|███████▎ | 3423/4692 [40:03<12:10, 1.74it/s] 73%|███████▎ | 3424/4692 [40:04<12:02, 1.76it/s] 73%|███████▎ | 3425/4692 [40:04<12:01, 1.76it/s] 73%|███████▎ | 3426/4692 [40:05<12:06, 1.74it/s] 73%|███████▎ | 3427/4692 [40:05<11:58, 1.76it/s] 73%|███████▎ | 3428/4692 [40:06<12:01, 1.75it/s] 73%|███████▎ | 3429/4692 [40:07<12:06, 1.74it/s] 73%|███████▎ | 3430/4692 [40:07<11:58, 1.76it/s] 73%|███████▎ | 3431/4692 [40:08<12:05, 1.74it/s] 73%|███████▎ | 3432/4692 [40:08<11:51, 1.77it/s] 73%|███████▎ | 3433/4692 [40:09<11:51, 1.77it/s] 73%|███████▎ | 3434/4692 [40:09<11:56, 1.75it/s] 73%|███████▎ | 3435/4692 [40:10<11:49, 1.77it/s] 73%|███████▎ | 3436/4692 [40:11<11:55, 1.76it/s] 73%|███████▎ | 3437/4692 [40:11<11:49, 1.77it/s] 73%|███████▎ | 3438/4692 [40:12<11:51, 1.76it/s] 73%|███████▎ | 3439/4692 [40:12<12:00, 1.74it/s] 73%|███████▎ | 3440/4692 [40:13<11:52, 1.76it/s] 73%|███████▎ | 3441/4692 [40:13<11:48, 1.76it/s] 73%|███████▎ | 3442/4692 [40:14<11:54, 1.75it/s] 73%|███████▎ | 3443/4692 [40:15<11:48, 1.76it/s] 73%|███████▎ | 3444/4692 [40:15<11:48, 1.76it/s] 73%|███████▎ | 3445/4692 [40:16<11:52, 1.75it/s] 73%|███████▎ | 3446/4692 [40:16<11:44, 1.77it/s] 73%|███████▎ | 3447/4692 [40:17<11:49, 1.75it/s] 73%|███████▎ | 3448/4692 [40:17<11:42, 1.77it/s] 74%|███████▎ | 3449/4692 [40:18<11:36, 1.78it/s] 74%|███████▎ | 3450/4692 [40:19<11:44, 1.76it/s] 74%|███████▎ | 3451/4692 [40:19<11:37, 1.78it/s] 74%|███████▎ | 3452/4692 [40:20<11:45, 1.76it/s] 74%|███████▎ | 3453/4692 [40:20<11:43, 1.76it/s] 74%|███████▎ | 3454/4692 [40:21<11:46, 1.75it/s] 74%|███████▎ | 3455/4692 [40:21<11:48, 1.75it/s] 74%|███████▎ | 3456/4692 [40:22<11:41, 1.76it/s] 74%|███████▎ | 3457/4692 [40:22<11:41, 1.76it/s] 74%|███████▎ | 3458/4692 [40:23<11:48, 1.74it/s] 74%|███████▎ | 3459/4692 [40:24<11:36, 1.77it/s] 74%|███████▎ | 3460/4692 [40:24<11:37, 1.77it/s] 74%|███████▍ | 3461/4692 [40:25<11:40, 1.76it/s] 74%|███████▍ | 3462/4692 [40:25<11:31, 1.78it/s] 74%|███████▍ | 3463/4692 [40:26<11:38, 1.76it/s] 74%|███████▍ | 3464/4692 [40:26<11:36, 1.76it/s] 74%|███████▍ | 3465/4692 [40:27<11:38, 1.76it/s] 74%|███████▍ | 3466/4692 [40:28<11:42, 1.75it/s] 74%|███████▍ | 3467/4692 [40:28<11:36, 1.76it/s] 74%|███████▍ | 3468/4692 [40:29<11:39, 1.75it/s] 74%|███████▍ | 3469/4692 [40:29<11:43, 1.74it/s] 74%|███████▍ | 3470/4692 [40:30<11:33, 1.76it/s] 74%|███████▍ | 3471/4692 [40:30<11:33, 1.76it/s] 74%|███████▍ | 3472/4692 [40:31<11:39, 1.74it/s] 74%|███████▍ | 3473/4692 [40:32<11:30, 1.76it/s] 74%|███████▍ | 3474/4692 [40:32<11:36, 1.75it/s] 74%|███████▍ | 3475/4692 [40:33<11:35, 1.75it/s] 74%|███████▍ | 3476/4692 [40:33<11:32, 1.76it/s] 74%|███████▍ | 3477/4692 [40:34<11:35, 1.75it/s] 74%|███████▍ | 3478/4692 [40:34<11:28, 1.76it/s] 74%|███████▍ | 3479/4692 [40:35<11:33, 1.75it/s] 74%|███████▍ | 3480/4692 [40:36<11:44, 1.72it/s] 74%|███████▍ | 3481/4692 [40:36<11:34, 1.74it/s] 74%|███████▍ | 3482/4692 [40:37<11:33, 1.75it/s] 74%|███████▍ | 3483/4692 [40:37<11:35, 1.74it/s] 74%|███████▍ | 3484/4692 [40:38<11:23, 1.77it/s] 74%|███████▍ | 3485/4692 [40:38<11:28, 1.75it/s] 74%|███████▍ | 3486/4692 [40:39<11:33, 1.74it/s] 74%|███████▍ | 3487/4692 [40:40<11:26, 1.75it/s] 74%|███████▍ | 3488/4692 [40:40<11:30, 1.74it/s] 74%|███████▍ | 3489/4692 [40:41<11:29, 1.75it/s] 74%|███████▍ | 3490/4692 [40:41<11:25, 1.75it/s] 74%|███████▍ | 3491/4692 [40:42<11:28, 1.74it/s] 74%|███████▍ | 3492/4692 [40:42<11:19, 1.77it/s] 74%|███████▍ | 3493/4692 [40:43<11:20, 1.76it/s] 74%|███████▍ | 3494/4692 [40:44<11:22, 1.76it/s] 74%|███████▍ | 3495/4692 [40:44<11:14, 1.78it/s] 75%|███████▍ | 3496/4692 [40:45<11:19, 1.76it/s] 75%|███████▍ | 3497/4692 [40:45<11:21, 1.75it/s] 75%|███████▍ | 3498/4692 [40:46<11:17, 1.76it/s] 75%|███████▍ | 3499/4692 [40:46<11:24, 1.74it/s] 75%|███████▍ | 3500/4692 [40:47<11:21, 1.75it/s] 75%|███████▍ | 3500/4692 [40:47<11:21, 1.75it/s] 75%|███████▍ | 3501/4692 [40:48<11:20, 1.75it/s] 75%|███████▍ | 3502/4692 [40:48<11:24, 1.74it/s] 75%|███████▍ | 3503/4692 [40:49<11:17, 1.76it/s] 75%|███████▍ | 3504/4692 [40:49<11:14, 1.76it/s] 75%|███████▍ | 3505/4692 [40:50<11:20, 1.74it/s] 75%|███████▍ | 3506/4692 [40:50<11:14, 1.76it/s] 75%|███████▍ | 3507/4692 [40:51<11:15, 1.75it/s] 75%|███████▍ | 3508/4692 [40:52<11:17, 1.75it/s] 75%|███████▍ | 3509/4692 [40:52<11:11, 1.76it/s] 75%|███████▍ | 3510/4692 [40:53<11:13, 1.75it/s] 75%|███████▍ | 3511/4692 [40:53<11:16, 1.75it/s] 75%|███████▍ | 3512/4692 [40:54<11:11, 1.76it/s] 75%|███████▍ | 3513/4692 [40:54<11:13, 1.75it/s] 75%|███████▍ | 3514/4692 [40:55<11:10, 1.76it/s] 75%|███████▍ | 3515/4692 [40:56<11:10, 1.76it/s] 75%|███████▍ | 3516/4692 [40:56<11:14, 1.74it/s] 75%|███████▍ | 3517/4692 [40:57<11:06, 1.76it/s] 75%|███████▍ | 3518/4692 [40:57<11:05, 1.76it/s] 75%|███████▌ | 3519/4692 [40:58<11:11, 1.75it/s][INFO|trainer.py:738] 2023-07-03 01:48:35,284 >> The following columns in the evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: text. If text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3069] 2023-07-03 01:48:35,289 >> ***** Running Evaluation ***** [INFO|trainer.py:3071] 2023-07-03 01:48:35,290 >> Num examples = 25000 [INFO|trainer.py:3074] 2023-07-03 01:48:35,290 >> Batch size = 64 0%| | 0/391 [00:00> Saving model checkpoint to /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-3519 [INFO|configuration_utils.py:457] 2023-07-03 01:50:45,811 >> Configuration saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-3519/config.json [INFO|modeling_utils.py:1762] 2023-07-03 01:50:46,420 >> Model weights saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-3519/pytorch_model.bin [INFO|tokenization_utils_base.py:2163] 2023-07-03 01:50:46,421 >> tokenizer config file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-3519/tokenizer_config.json [INFO|tokenization_utils_base.py:2170] 2023-07-03 01:50:46,421 >> Special tokens file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-3519/special_tokens_map.json [INFO|trainer.py:2893] 2023-07-03 01:50:47,729 >> Deleting older checkpoint [/nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-3128] due to args.save_total_limit 75%|███████▌ | 3520/4692 [43:11<13:08:17, 40.36s/it] 75%|███████▌ | 3521/4692 [43:12<9:14:32, 28.41s/it] 75%|███████▌ | 3522/4692 [43:12<6:31:16, 20.07s/it] 75%|███████▌ | 3523/4692 [43:13<4:36:59, 14.22s/it] 75%|███████▌ | 3524/4692 [43:13<3:17:03, 10.12s/it] 75%|███████▌ | 3525/4692 [43:14<2:21:14, 7.26s/it] 75%|███████▌ | 3526/4692 [43:14<1:41:59, 5.25s/it] 75%|███████▌ | 3527/4692 [43:15<1:14:42, 3.85s/it] 75%|███████▌ | 3528/4692 [43:16<55:39, 2.87s/it] 75%|███████▌ | 3529/4692 [43:16<42:08, 2.17s/it] 75%|███████▌ | 3530/4692 [43:17<32:46, 1.69s/it] 75%|███████▌ | 3531/4692 [43:17<26:19, 1.36s/it] 75%|███████▌ | 3532/4692 [43:18<21:36, 1.12s/it] 75%|███████▌ | 3533/4692 [43:18<18:26, 1.05it/s] 75%|███████▌ | 3534/4692 [43:19<16:15, 1.19it/s] 75%|███████▌ | 3535/4692 [43:20<14:32, 1.33it/s] 75%|███████▌ | 3536/4692 [43:20<13:32, 1.42it/s] 75%|███████▌ | 3537/4692 [43:21<12:41, 1.52it/s] 75%|███████▌ | 3538/4692 [43:21<12:07, 1.59it/s] 75%|███████▌ | 3539/4692 [43:22<11:49, 1.62it/s] 75%|███████▌ | 3540/4692 [43:22<11:26, 1.68it/s] 75%|███████▌ | 3541/4692 [43:23<11:21, 1.69it/s] 75%|███████▌ | 3542/4692 [43:24<11:16, 1.70it/s] 76%|███████▌ | 3543/4692 [43:24<11:05, 1.73it/s] 76%|███████▌ | 3544/4692 [43:25<11:05, 1.73it/s] 76%|███████▌ | 3545/4692 [43:25<10:55, 1.75it/s] 76%|███████▌ | 3546/4692 [43:26<10:51, 1.76it/s] 76%|███████▌ | 3547/4692 [43:26<10:56, 1.74it/s] 76%|███████▌ | 3548/4692 [43:27<10:46, 1.77it/s] 76%|███████▌ | 3549/4692 [43:28<10:51, 1.76it/s] 76%|███████▌ | 3550/4692 [43:28<10:47, 1.76it/s] 76%|███████▌ | 3551/4692 [43:29<10:48, 1.76it/s] 76%|███████▌ | 3552/4692 [43:29<10:51, 1.75it/s] 76%|███████▌ | 3553/4692 [43:30<10:45, 1.77it/s] 76%|███████▌ | 3554/4692 [43:30<10:44, 1.77it/s] 76%|███████▌ | 3555/4692 [43:31<10:48, 1.75it/s] 76%|███████▌ | 3556/4692 [43:32<10:43, 1.77it/s] 76%|███████▌ | 3557/4692 [43:32<10:46, 1.76it/s] 76%|███████▌ | 3558/4692 [43:33<10:53, 1.74it/s] 76%|███████▌ | 3559/4692 [43:33<10:44, 1.76it/s] 76%|███████▌ | 3560/4692 [43:34<10:49, 1.74it/s] 76%|███████▌ | 3561/4692 [43:34<10:44, 1.75it/s] 76%|███████▌ | 3562/4692 [43:35<10:45, 1.75it/s] 76%|███████▌ | 3563/4692 [43:36<10:49, 1.74it/s] 76%|███████▌ | 3564/4692 [43:36<10:42, 1.76it/s] 76%|███████▌ | 3565/4692 [43:37<10:39, 1.76it/s] 76%|███████▌ | 3566/4692 [43:37<10:41, 1.75it/s] 76%|███████▌ | 3567/4692 [43:38<10:34, 1.77it/s] 76%|███████▌ | 3568/4692 [43:38<10:39, 1.76it/s] 76%|███████▌ | 3569/4692 [43:39<10:30, 1.78it/s] 76%|███████▌ | 3570/4692 [43:39<10:31, 1.78it/s] 76%|███████▌ | 3571/4692 [43:40<10:37, 1.76it/s] 76%|███████▌ | 3572/4692 [43:41<10:32, 1.77it/s] 76%|███████▌ | 3573/4692 [43:41<10:32, 1.77it/s] 76%|███████▌ | 3574/4692 [43:42<10:36, 1.76it/s] 76%|███████▌ | 3575/4692 [43:42<10:30, 1.77it/s] 76%|███████▌ | 3576/4692 [43:43<10:33, 1.76it/s] 76%|███████▌ | 3577/4692 [43:43<10:32, 1.76it/s] 76%|███████▋ | 3578/4692 [43:44<10:34, 1.75it/s] 76%|███████▋ | 3579/4692 [43:45<10:37, 1.75it/s] 76%|███████▋ | 3580/4692 [43:45<10:28, 1.77it/s] 76%|███████▋ | 3581/4692 [43:46<10:29, 1.77it/s] 76%|███████▋ | 3582/4692 [43:46<10:35, 1.75it/s] 76%|███████▋ | 3583/4692 [43:47<10:29, 1.76it/s] 76%|███████▋ | 3584/4692 [43:47<10:29, 1.76it/s] 76%|███████▋ | 3585/4692 [43:48<10:34, 1.74it/s] 76%|███████▋ | 3586/4692 [43:49<10:27, 1.76it/s] 76%|███████▋ | 3587/4692 [43:49<10:30, 1.75it/s] 76%|███████▋ | 3588/4692 [43:50<10:26, 1.76it/s] 76%|███████▋ | 3589/4692 [43:50<10:20, 1.78it/s] 77%|███████▋ | 3590/4692 [43:51<10:29, 1.75it/s] 77%|███████▋ | 3591/4692 [43:51<10:19, 1.78it/s] 77%|███████▋ | 3592/4692 [43:52<10:26, 1.76it/s] 77%|███████▋ | 3593/4692 [43:53<10:27, 1.75it/s] 77%|███████▋ | 3594/4692 [43:53<10:22, 1.76it/s] 77%|███████▋ | 3595/4692 [43:54<10:28, 1.75it/s] 77%|███████▋ | 3596/4692 [43:54<10:26, 1.75it/s] 77%|███████▋ | 3597/4692 [43:55<10:25, 1.75it/s] 77%|███████▋ | 3598/4692 [43:55<10:27, 1.74it/s] 77%|███████▋ | 3599/4692 [43:56<10:15, 1.78it/s] 77%|███████▋ | 3600/4692 [43:57<10:19, 1.76it/s] 77%|███████▋ | 3601/4692 [43:57<10:24, 1.75it/s] 77%|███████▋ | 3602/4692 [43:58<10:16, 1.77it/s] 77%|███████▋ | 3603/4692 [43:58<10:18, 1.76it/s] 77%|███████▋ | 3604/4692 [43:59<10:11, 1.78it/s] 77%|███████▋ | 3605/4692 [43:59<10:12, 1.77it/s] 77%|███████▋ | 3606/4692 [44:00<10:19, 1.75it/s] 77%|███████▋ | 3607/4692 [44:00<10:12, 1.77it/s] 77%|███████▋ | 3608/4692 [44:01<10:16, 1.76it/s] 77%|███████▋ | 3609/4692 [44:02<10:20, 1.75it/s] 77%|███████▋ | 3610/4692 [44:02<10:13, 1.76it/s] 77%|███████▋ | 3611/4692 [44:03<10:18, 1.75it/s] 77%|███████▋ | 3612/4692 [44:03<10:13, 1.76it/s] 77%|███████▋ | 3613/4692 [44:04<10:10, 1.77it/s] 77%|███████▋ | 3614/4692 [44:04<10:12, 1.76it/s] 77%|███████▋ | 3615/4692 [44:05<10:06, 1.78it/s] 77%|███████▋ | 3616/4692 [44:06<10:10, 1.76it/s] 77%|███████▋ | 3617/4692 [44:06<10:10, 1.76it/s] 77%|███████▋ | 3618/4692 [44:07<10:08, 1.77it/s] 77%|███████▋ | 3619/4692 [44:07<10:13, 1.75it/s] 77%|███████▋ | 3620/4692 [44:08<10:06, 1.77it/s] 77%|███████▋ | 3621/4692 [44:08<10:04, 1.77it/s] 77%|███████▋ | 3622/4692 [44:09<10:12, 1.75it/s] 77%|███████▋ | 3623/4692 [44:10<10:03, 1.77it/s] 77%|███████▋ | 3624/4692 [44:10<10:04, 1.77it/s] 77%|███████▋ | 3625/4692 [44:11<10:09, 1.75it/s] 77%|███████▋ | 3626/4692 [44:11<10:03, 1.77it/s] 77%|███████▋ | 3627/4692 [44:12<10:07, 1.75it/s] 77%|███████▋ | 3628/4692 [44:12<10:05, 1.76it/s] 77%|███████▋ | 3629/4692 [44:13<10:05, 1.75it/s] 77%|███████▋ | 3630/4692 [44:14<10:11, 1.74it/s] 77%|███████▋ | 3631/4692 [44:14<10:03, 1.76it/s] 77%|███████▋ | 3632/4692 [44:15<10:00, 1.77it/s] 77%|███████▋ | 3633/4692 [44:15<10:04, 1.75it/s] 77%|███████▋ | 3634/4692 [44:16<09:57, 1.77it/s] 77%|███████▋ | 3635/4692 [44:16<10:01, 1.76it/s] 77%|███████▋ | 3636/4692 [44:17<10:03, 1.75it/s] 78%|███████▊ | 3637/4692 [44:18<09:59, 1.76it/s] 78%|███████▊ | 3638/4692 [44:18<10:04, 1.74it/s] 78%|███████▊ | 3639/4692 [44:19<09:55, 1.77it/s] 78%|███████▊ | 3640/4692 [44:19<09:56, 1.76it/s] 78%|███████▊ | 3641/4692 [44:20<10:00, 1.75it/s] 78%|███████▊ | 3642/4692 [44:20<09:52, 1.77it/s] 78%|███████▊ | 3643/4692 [44:21<09:57, 1.76it/s] 78%|███████▊ | 3644/4692 [44:22<10:00, 1.75it/s] 78%|███████▊ | 3645/4692 [44:22<09:54, 1.76it/s] 78%|███████▊ | 3646/4692 [44:23<09:57, 1.75it/s] 78%|███████▊ | 3647/4692 [44:23<09:53, 1.76it/s] 78%|███████▊ | 3648/4692 [44:24<09:53, 1.76it/s] 78%|███████▊ | 3649/4692 [44:24<09:58, 1.74it/s] 78%|███████▊ | 3650/4692 [44:25<09:51, 1.76it/s] 78%|███████▊ | 3651/4692 [44:26<09:50, 1.76it/s] 78%|███████▊ | 3652/4692 [44:26<09:56, 1.74it/s] 78%|███████▊ | 3653/4692 [44:27<09:48, 1.76it/s] 78%|███████▊ | 3654/4692 [44:27<09:49, 1.76it/s] 78%|███████▊ | 3655/4692 [44:28<09:53, 1.75it/s] 78%|███████▊ | 3656/4692 [44:28<09:45, 1.77it/s] 78%|███████▊ | 3657/4692 [44:29<09:51, 1.75it/s] 78%|███████▊ | 3658/4692 [44:30<09:49, 1.75it/s] 78%|███████▊ | 3659/4692 [44:30<09:48, 1.75it/s] 78%|███████▊ | 3660/4692 [44:31<09:51, 1.74it/s] 78%|███████▊ | 3661/4692 [44:31<09:44, 1.77it/s] 78%|███████▊ | 3662/4692 [44:32<09:42, 1.77it/s] 78%|███████▊ | 3663/4692 [44:32<09:44, 1.76it/s] 78%|███████▊ | 3664/4692 [44:33<09:39, 1.77it/s] 78%|███████▊ | 3665/4692 [44:33<09:45, 1.75it/s] 78%|███████▊ | 3666/4692 [44:34<09:40, 1.77it/s] 78%|███████▊ | 3667/4692 [44:35<09:39, 1.77it/s] 78%|███████▊ | 3668/4692 [44:35<09:42, 1.76it/s] 78%|███████▊ | 3669/4692 [44:36<09:33, 1.78it/s] 78%|███████▊ | 3670/4692 [44:36<09:39, 1.76it/s] 78%|███████▊ | 3671/4692 [44:37<09:44, 1.75it/s] 78%|███████▊ | 3672/4692 [44:37<09:39, 1.76it/s] 78%|███████▊ | 3673/4692 [44:38<09:43, 1.75it/s] 78%|███████▊ | 3674/4692 [44:39<09:33, 1.78it/s] 78%|███████▊ | 3675/4692 [44:39<09:32, 1.78it/s] 78%|███████▊ | 3676/4692 [44:40<09:37, 1.76it/s] 78%|███████▊ | 3677/4692 [44:40<09:30, 1.78it/s] 78%|███████▊ | 3678/4692 [44:41<09:36, 1.76it/s] 78%|███████▊ | 3679/4692 [44:41<09:39, 1.75it/s] 78%|███████▊ | 3680/4692 [44:42<09:36, 1.76it/s] 78%|███████▊ | 3681/4692 [44:43<09:40, 1.74it/s] 78%|███████▊ | 3682/4692 [44:43<09:32, 1.76it/s] 78%|███████▊ | 3683/4692 [44:44<09:31, 1.76it/s] 79%|███████▊ | 3684/4692 [44:44<09:34, 1.75it/s] 79%|███████▊ | 3685/4692 [44:45<09:29, 1.77it/s] 79%|███████▊ | 3686/4692 [44:45<09:30, 1.76it/s] 79%|███████▊ | 3687/4692 [44:46<09:35, 1.75it/s] 79%|███████▊ | 3688/4692 [44:47<09:30, 1.76it/s] 79%|███████▊ | 3689/4692 [44:47<09:34, 1.74it/s] 79%|███████▊ | 3690/4692 [44:48<09:32, 1.75it/s] 79%|███████▊ | 3691/4692 [44:48<09:32, 1.75it/s] 79%|███████▊ | 3692/4692 [44:49<09:35, 1.74it/s] 79%|███████▊ | 3693/4692 [44:49<09:28, 1.76it/s] 79%|███████▊ | 3694/4692 [44:50<09:27, 1.76it/s] 79%|███████▉ | 3695/4692 [44:51<09:29, 1.75it/s] 79%|███████▉ | 3696/4692 [44:51<09:23, 1.77it/s] 79%|███████▉ | 3697/4692 [44:52<09:26, 1.76it/s] 79%|███████▉ | 3698/4692 [44:52<09:31, 1.74it/s] 79%|███████▉ | 3699/4692 [44:53<09:24, 1.76it/s] 79%|███████▉ | 3700/4692 [44:53<09:28, 1.74it/s] 79%|███████▉ | 3701/4692 [44:54<09:22, 1.76it/s] 79%|███████▉ | 3702/4692 [44:55<09:21, 1.76it/s] 79%|███████▉ | 3703/4692 [44:55<09:24, 1.75it/s] 79%|███████▉ | 3704/4692 [44:56<09:17, 1.77it/s] 79%|███████▉ | 3705/4692 [44:56<09:19, 1.76it/s] 79%|███████▉ | 3706/4692 [44:57<09:16, 1.77it/s] 79%|███████▉ | 3707/4692 [44:57<07:50, 2.09it/s] 79%|███████▉ | 3708/4692 [44:57<06:47, 2.41it/s] 79%|███████▉ | 3709/4692 [44:58<06:06, 2.68it/s] 79%|███████▉ | 3710/4692 [44:58<05:39, 2.89it/s] 79%|███████▉ | 3711/4692 [44:58<05:19, 3.07it/s] 79%|███████▉ | 3712/4692 [44:58<05:04, 3.22it/s] 79%|███████▉ | 3713/4692 [44:59<04:54, 3.33it/s] 79%|███████▉ | 3714/4692 [44:59<05:28, 2.98it/s] 79%|███████▉ | 3715/4692 [45:00<06:32, 2.49it/s] 79%|███████▉ | 3716/4692 [45:00<07:20, 2.22it/s] 79%|███████▉ | 3717/4692 [45:01<07:55, 2.05it/s] 79%|███████▉ | 3718/4692 [45:01<08:14, 1.97it/s] 79%|███████▉ | 3719/4692 [45:02<08:26, 1.92it/s] 79%|███████▉ | 3720/4692 [45:03<08:39, 1.87it/s] 79%|███████▉ | 3721/4692 [45:03<08:45, 1.85it/s] 79%|███████▉ | 3722/4692 [45:04<08:50, 1.83it/s] 79%|███████▉ | 3723/4692 [45:04<08:51, 1.82it/s] 79%|███████▉ | 3724/4692 [45:05<08:52, 1.82it/s] 79%|███████▉ | 3725/4692 [45:05<08:56, 1.80it/s] 79%|███████▉ | 3726/4692 [45:06<08:55, 1.80it/s] 79%|███████▉ | 3727/4692 [45:06<08:56, 1.80it/s] 79%|███████▉ | 3728/4692 [45:07<08:57, 1.79it/s] 79%|███████▉ | 3729/4692 [45:08<08:59, 1.78it/s] 79%|███████▉ | 3730/4692 [45:08<08:57, 1.79it/s] 80%|███████▉ | 3731/4692 [45:09<08:56, 1.79it/s] 80%|███████▉ | 3732/4692 [45:09<08:55, 1.79it/s] 80%|███████▉ | 3733/4692 [45:10<08:55, 1.79it/s] 80%|███████▉ | 3734/4692 [45:10<08:54, 1.79it/s] 80%|███████▉ | 3735/4692 [45:11<08:55, 1.79it/s] 80%|███████▉ | 3736/4692 [45:11<08:52, 1.79it/s] 80%|███████▉ | 3737/4692 [45:12<08:54, 1.79it/s] 80%|███████▉ | 3738/4692 [45:13<08:54, 1.79it/s] 80%|███████▉ | 3739/4692 [45:13<08:51, 1.79it/s] 80%|███████▉ | 3740/4692 [45:14<08:53, 1.79it/s] 80%|███████▉ | 3741/4692 [45:14<08:55, 1.78it/s] 80%|███████▉ | 3742/4692 [45:15<08:53, 1.78it/s] 80%|███████▉ | 3743/4692 [45:15<08:48, 1.80it/s] 80%|███████▉ | 3744/4692 [45:16<08:49, 1.79it/s] 80%|███████▉ | 3745/4692 [45:16<08:49, 1.79it/s] 80%|███████▉ | 3746/4692 [45:17<08:47, 1.79it/s] 80%|███████▉ | 3747/4692 [45:18<08:46, 1.80it/s] 80%|███████▉ | 3748/4692 [45:18<08:44, 1.80it/s] 80%|███████▉ | 3749/4692 [45:19<08:47, 1.79it/s] 80%|███████▉ | 3750/4692 [45:19<08:45, 1.79it/s] 80%|███████▉ | 3751/4692 [45:20<08:45, 1.79it/s] 80%|███████▉ | 3752/4692 [45:20<08:46, 1.79it/s] 80%|███████▉ | 3753/4692 [45:21<08:47, 1.78it/s] 80%|████████ | 3754/4692 [45:22<08:44, 1.79it/s] 80%|████████ | 3755/4692 [45:22<08:41, 1.80it/s] 80%|████████ | 3756/4692 [45:23<08:42, 1.79it/s] 80%|████████ | 3757/4692 [45:23<08:41, 1.79it/s] 80%|████████ | 3758/4692 [45:24<08:40, 1.79it/s] 80%|████████ | 3759/4692 [45:24<08:40, 1.79it/s] 80%|████████ | 3760/4692 [45:25<08:42, 1.78it/s] 80%|████████ | 3761/4692 [45:25<08:44, 1.78it/s] 80%|████████ | 3762/4692 [45:26<08:42, 1.78it/s] 80%|████████ | 3763/4692 [45:27<08:41, 1.78it/s] 80%|████████ | 3764/4692 [45:27<08:38, 1.79it/s] 80%|████████ | 3765/4692 [45:28<08:39, 1.78it/s] 80%|████████ | 3766/4692 [45:28<08:37, 1.79it/s] 80%|████████ | 3767/4692 [45:29<08:38, 1.78it/s] 80%|████████ | 3768/4692 [45:29<08:35, 1.79it/s] 80%|████████ | 3769/4692 [45:30<08:37, 1.78it/s] 80%|████████ | 3770/4692 [45:30<08:34, 1.79it/s] 80%|████████ | 3771/4692 [45:31<08:35, 1.79it/s] 80%|████████ | 3772/4692 [45:32<08:34, 1.79it/s] 80%|████████ | 3773/4692 [45:32<08:35, 1.78it/s] 80%|████████ | 3774/4692 [45:33<08:32, 1.79it/s] 80%|████████ | 3775/4692 [45:33<08:30, 1.80it/s] 80%|████████ | 3776/4692 [45:34<08:28, 1.80it/s] 80%|████████ | 3777/4692 [45:34<08:30, 1.79it/s] 81%|████████ | 3778/4692 [45:35<08:32, 1.78it/s] 81%|████████ | 3779/4692 [45:35<08:32, 1.78it/s] 81%|████████ | 3780/4692 [45:36<08:32, 1.78it/s] 81%|████████ | 3781/4692 [45:37<08:31, 1.78it/s] 81%|████████ | 3782/4692 [45:37<08:30, 1.78it/s] 81%|████████ | 3783/4692 [45:38<08:31, 1.78it/s] 81%|████████ | 3784/4692 [45:38<08:32, 1.77it/s] 81%|████████ | 3785/4692 [45:39<08:29, 1.78it/s] 81%|████████ | 3786/4692 [45:39<08:28, 1.78it/s] 81%|████████ | 3787/4692 [45:40<08:29, 1.78it/s] 81%|████████ | 3788/4692 [45:41<08:29, 1.77it/s] 81%|████████ | 3789/4692 [45:41<08:27, 1.78it/s] 81%|████████ | 3790/4692 [45:42<08:26, 1.78it/s] 81%|████████ | 3791/4692 [45:42<08:26, 1.78it/s] 81%|████████ | 3792/4692 [45:43<08:24, 1.78it/s] 81%|████████ | 3793/4692 [45:43<08:20, 1.80it/s] 81%|████████ | 3794/4692 [45:44<08:22, 1.79it/s] 81%|████████ | 3795/4692 [45:44<08:23, 1.78it/s] 81%|████████ | 3796/4692 [45:45<08:20, 1.79it/s] 81%|████████ | 3797/4692 [45:46<08:19, 1.79it/s] 81%|████████ | 3798/4692 [45:46<08:20, 1.79it/s] 81%|████████ | 3799/4692 [45:47<08:17, 1.79it/s] 81%|████████ | 3800/4692 [45:47<08:13, 1.81it/s] 81%|████████ | 3801/4692 [45:48<08:18, 1.79it/s] 81%|████████ | 3802/4692 [45:48<08:18, 1.78it/s] 81%|████████ | 3803/4692 [45:49<08:14, 1.80it/s] 81%|████████ | 3804/4692 [45:49<08:14, 1.80it/s] 81%|████████ | 3805/4692 [45:50<08:15, 1.79it/s] 81%|████████ | 3806/4692 [45:51<08:13, 1.79it/s] 81%|████████ | 3807/4692 [45:51<08:10, 1.81it/s] 81%|████████ | 3808/4692 [45:52<08:12, 1.80it/s] 81%|████████ | 3809/4692 [45:52<08:14, 1.79it/s] 81%|████████ | 3810/4692 [45:53<08:14, 1.78it/s] 81%|████████ | 3811/4692 [45:53<08:12, 1.79it/s] 81%|████████ | 3812/4692 [45:54<08:13, 1.78it/s] 81%|████████▏ | 3813/4692 [45:55<08:16, 1.77it/s] 81%|████████▏ | 3814/4692 [45:55<08:13, 1.78it/s] 81%|████████▏ | 3815/4692 [45:56<08:09, 1.79it/s] 81%|████████▏ | 3816/4692 [45:56<08:11, 1.78it/s] 81%|████████▏ | 3817/4692 [45:57<08:08, 1.79it/s] 81%|████████▏ | 3818/4692 [45:57<08:06, 1.79it/s] 81%|████████▏ | 3819/4692 [45:58<08:04, 1.80it/s] 81%|████████▏ | 3820/4692 [45:58<08:05, 1.80it/s] 81%|████████▏ | 3821/4692 [45:59<08:05, 1.79it/s] 81%|████████▏ | 3822/4692 [46:00<08:05, 1.79it/s] 81%|████████▏ | 3823/4692 [46:00<08:05, 1.79it/s] 82%|████████▏ | 3824/4692 [46:01<08:07, 1.78it/s] 82%|████████▏ | 3825/4692 [46:01<08:04, 1.79it/s] 82%|████████▏ | 3826/4692 [46:02<07:59, 1.81it/s] 82%|████████▏ | 3827/4692 [46:02<08:02, 1.79it/s] 82%|████████▏ | 3828/4692 [46:03<08:02, 1.79it/s] 82%|████████▏ | 3829/4692 [46:03<08:03, 1.78it/s] 82%|████████▏ | 3830/4692 [46:04<07:59, 1.80it/s] 82%|████████▏ | 3831/4692 [46:05<07:59, 1.79it/s] 82%|████████▏ | 3832/4692 [46:05<07:57, 1.80it/s] 82%|████████▏ | 3833/4692 [46:06<07:56, 1.80it/s] 82%|████████▏ | 3834/4692 [46:06<07:55, 1.80it/s] 82%|████████▏ | 3835/4692 [46:07<07:56, 1.80it/s] 82%|████████▏ | 3836/4692 [46:07<07:55, 1.80it/s] 82%|████████▏ | 3837/4692 [46:08<07:57, 1.79it/s] 82%|████████▏ | 3838/4692 [46:08<07:57, 1.79it/s] 82%|████████▏ | 3839/4692 [46:09<07:57, 1.79it/s] 82%|████████▏ | 3840/4692 [46:10<07:55, 1.79it/s] 82%|████████▏ | 3841/4692 [46:10<07:54, 1.79it/s] 82%|████████▏ | 3842/4692 [46:11<07:52, 1.80it/s] 82%|████████▏ | 3843/4692 [46:11<07:54, 1.79it/s] 82%|████████▏ | 3844/4692 [46:12<07:55, 1.78it/s] 82%|████████▏ | 3845/4692 [46:12<07:53, 1.79it/s] 82%|████████▏ | 3846/4692 [46:13<07:49, 1.80it/s] 82%|████████▏ | 3847/4692 [46:13<07:51, 1.79it/s] 82%|████████▏ | 3848/4692 [46:14<07:52, 1.79it/s] 82%|████████▏ | 3849/4692 [46:15<07:50, 1.79it/s] 82%|████████▏ | 3850/4692 [46:15<07:49, 1.79it/s] 82%|████████▏ | 3851/4692 [46:16<07:51, 1.78it/s] 82%|████████▏ | 3852/4692 [46:16<07:50, 1.79it/s] 82%|████████▏ | 3853/4692 [46:17<07:50, 1.78it/s] 82%|████████▏ | 3854/4692 [46:17<07:49, 1.79it/s] 82%|████████▏ | 3855/4692 [46:18<07:50, 1.78it/s] 82%|████████▏ | 3856/4692 [46:19<07:44, 1.80it/s] 82%|████████▏ | 3857/4692 [46:19<07:48, 1.78it/s] 82%|████████▏ | 3858/4692 [46:20<07:52, 1.76it/s] 82%|████████▏ | 3859/4692 [46:20<07:47, 1.78it/s] 82%|████████▏ | 3860/4692 [46:21<07:50, 1.77it/s] 82%|████████▏ | 3861/4692 [46:21<07:53, 1.75it/s] 82%|████████▏ | 3862/4692 [46:22<07:48, 1.77it/s] 82%|████████▏ | 3863/4692 [46:23<07:53, 1.75it/s] 82%|████████▏ | 3864/4692 [46:23<07:51, 1.76it/s] 82%|████████▏ | 3865/4692 [46:24<07:51, 1.75it/s] 82%|████████▏ | 3866/4692 [46:24<07:53, 1.74it/s] 82%|████████▏ | 3867/4692 [46:25<07:48, 1.76it/s] 82%|████████▏ | 3868/4692 [46:25<07:45, 1.77it/s] 82%|████████▏ | 3869/4692 [46:26<07:48, 1.75it/s] 82%|████████▏ | 3870/4692 [46:26<07:44, 1.77it/s] 83%|████████▎ | 3871/4692 [46:27<07:45, 1.76it/s] 83%|████████▎ | 3872/4692 [46:28<07:48, 1.75it/s] 83%|████████▎ | 3873/4692 [46:28<07:42, 1.77it/s] 83%|████████▎ | 3874/4692 [46:29<07:46, 1.75it/s] 83%|████████▎ | 3875/4692 [46:29<07:44, 1.76it/s] 83%|████████▎ | 3876/4692 [46:30<07:39, 1.77it/s] 83%|████████▎ | 3877/4692 [46:30<07:45, 1.75it/s] 83%|████████▎ | 3878/4692 [46:31<07:40, 1.77it/s] 83%|████████▎ | 3879/4692 [46:32<07:40, 1.77it/s] 83%|████████▎ | 3880/4692 [46:32<07:45, 1.75it/s] 83%|████████▎ | 3881/4692 [46:33<07:40, 1.76it/s] 83%|████████▎ | 3882/4692 [46:33<07:42, 1.75it/s] 83%|████████▎ | 3883/4692 [46:34<07:39, 1.76it/s] 83%|████████▎ | 3884/4692 [46:34<07:36, 1.77it/s] 83%|████████▎ | 3885/4692 [46:35<07:40, 1.75it/s] 83%|████████▎ | 3886/4692 [46:36<07:35, 1.77it/s] 83%|████████▎ | 3887/4692 [46:36<07:37, 1.76it/s] 83%|████████▎ | 3888/4692 [46:37<07:36, 1.76it/s] 83%|████████▎ | 3889/4692 [46:37<07:32, 1.78it/s] 83%|████████▎ | 3890/4692 [46:38<07:34, 1.76it/s] 83%|████████▎ | 3891/4692 [46:38<07:29, 1.78it/s] 83%|████████▎ | 3892/4692 [46:39<07:32, 1.77it/s] 83%|████████▎ | 3893/4692 [46:40<07:29, 1.78it/s] 83%|████████▎ | 3894/4692 [46:40<07:32, 1.76it/s] 83%|████████▎ | 3895/4692 [46:41<07:36, 1.75it/s] 83%|████████▎ | 3896/4692 [46:41<07:30, 1.77it/s] 83%|████████▎ | 3897/4692 [46:42<07:28, 1.77it/s] 83%|████████▎ | 3898/4692 [46:42<07:36, 1.74it/s] 83%|████████▎ | 3899/4692 [46:43<07:32, 1.75it/s] 83%|████████▎ | 3900/4692 [46:44<07:31, 1.75it/s] 83%|████████▎ | 3901/4692 [46:44<07:35, 1.74it/s] 83%|████████▎ | 3902/4692 [46:45<07:26, 1.77it/s] 83%|████████▎ | 3903/4692 [46:45<07:29, 1.75it/s] 83%|████████▎ | 3904/4692 [46:46<07:32, 1.74it/s] 83%|████████▎ | 3905/4692 [46:46<07:26, 1.76it/s] 83%|████████▎ | 3906/4692 [46:47<07:29, 1.75it/s] 83%|████████▎ | 3907/4692 [46:47<07:20, 1.78it/s] 83%|████████▎ | 3908/4692 [46:48<07:21, 1.77it/s] 83%|████████▎ | 3909/4692 [46:49<07:26, 1.76it/s] 83%|████████▎ | 3910/4692 [46:49<05:51, 2.23it/s][INFO|trainer.py:738] 2023-07-03 01:54:26,231 >> The following columns in the evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: text. If text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3069] 2023-07-03 01:54:26,234 >> ***** Running Evaluation ***** [INFO|trainer.py:3071] 2023-07-03 01:54:26,234 >> Num examples = 25000 [INFO|trainer.py:3074] 2023-07-03 01:54:26,235 >> Batch size = 64 0%| | 0/391 [00:00> Saving model checkpoint to /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-3910 [INFO|configuration_utils.py:457] 2023-07-03 01:56:36,772 >> Configuration saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-3910/config.json [INFO|modeling_utils.py:1762] 2023-07-03 01:56:37,332 >> Model weights saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-3910/pytorch_model.bin [INFO|tokenization_utils_base.py:2163] 2023-07-03 01:56:37,333 >> tokenizer config file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-3910/tokenizer_config.json [INFO|tokenization_utils_base.py:2170] 2023-07-03 01:56:37,333 >> Special tokens file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-3910/special_tokens_map.json [INFO|trainer.py:2893] 2023-07-03 01:56:38,483 >> Deleting older checkpoint [/nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-3519] due to args.save_total_limit 83%|████████▎ | 3911/4692 [49:02<8:43:11, 40.19s/it] 83%|████████▎ | 3912/4692 [49:02<6:07:53, 28.30s/it] 83%|████████▎ | 3913/4692 [49:03<4:19:18, 19.97s/it] 83%|████████▎ | 3914/4692 [49:03<3:03:28, 14.15s/it] 83%|████████▎ | 3915/4692 [49:04<2:10:24, 10.07s/it] 83%|████████▎ | 3916/4692 [49:05<1:33:21, 7.22s/it] 83%|████████▎ | 3917/4692 [49:05<1:07:24, 5.22s/it] 84%|████████▎ | 3918/4692 [49:06<49:18, 3.82s/it] 84%|████████▎ | 3919/4692 [49:06<36:43, 2.85s/it] 84%|████████▎ | 3920/4692 [49:07<27:54, 2.17s/it] 84%|████████▎ | 3921/4692 [49:07<21:39, 1.68s/it] 84%|████████▎ | 3922/4692 [49:08<17:19, 1.35s/it] 84%|████████▎ | 3923/4692 [49:08<14:17, 1.12s/it] 84%|████████▎ | 3924/4692 [49:09<12:09, 1.05it/s] 84%|████████▎ | 3925/4692 [49:10<10:38, 1.20it/s] 84%|████████▎ | 3926/4692 [49:10<09:36, 1.33it/s] 84%|████████▎ | 3927/4692 [49:11<08:52, 1.44it/s] 84%|████████▎ | 3928/4692 [49:11<08:21, 1.52it/s] 84%|████████▎ | 3929/4692 [49:12<07:58, 1.59it/s] 84%|████████▍ | 3930/4692 [49:12<07:41, 1.65it/s] 84%|████████▍ | 3931/4692 [49:13<07:32, 1.68it/s] 84%|████████▍ | 3932/4692 [49:14<07:21, 1.72it/s] 84%|████████▍ | 3933/4692 [49:14<07:17, 1.74it/s] 84%|████████▍ | 3934/4692 [49:15<07:12, 1.75it/s] 84%|████████▍ | 3935/4692 [49:15<07:10, 1.76it/s] 84%|████████▍ | 3936/4692 [49:16<07:07, 1.77it/s] 84%|████████▍ | 3937/4692 [49:16<07:07, 1.77it/s] 84%|████████▍ | 3938/4692 [49:17<07:05, 1.77it/s] 84%|████████▍ | 3939/4692 [49:17<07:03, 1.78it/s] 84%|████████▍ | 3940/4692 [49:18<07:03, 1.78it/s] 84%|████████▍ | 3941/4692 [49:19<07:02, 1.78it/s] 84%|████████▍ | 3942/4692 [49:19<06:58, 1.79it/s] 84%|████████▍ | 3943/4692 [49:20<06:56, 1.80it/s] 84%|████████▍ | 3944/4692 [49:20<06:57, 1.79it/s] 84%|████████▍ | 3945/4692 [49:21<06:56, 1.79it/s] 84%|████████▍ | 3946/4692 [49:21<06:57, 1.79it/s] 84%|████████▍ | 3947/4692 [49:22<06:57, 1.78it/s] 84%|████████▍ | 3948/4692 [49:22<06:58, 1.78it/s] 84%|████████▍ | 3949/4692 [49:23<06:56, 1.78it/s] 84%|████████▍ | 3950/4692 [49:24<06:56, 1.78it/s] 84%|████████▍ | 3951/4692 [49:24<06:56, 1.78it/s] 84%|████████▍ | 3952/4692 [49:25<06:56, 1.78it/s] 84%|████████▍ | 3953/4692 [49:25<06:54, 1.78it/s] 84%|████████▍ | 3954/4692 [49:26<06:53, 1.78it/s] 84%|████████▍ | 3955/4692 [49:26<06:53, 1.78it/s] 84%|████████▍ | 3956/4692 [49:27<06:54, 1.78it/s] 84%|████████▍ | 3957/4692 [49:28<06:53, 1.78it/s] 84%|████████▍ | 3958/4692 [49:28<06:52, 1.78it/s] 84%|████████▍ | 3959/4692 [49:29<06:51, 1.78it/s] 84%|████████▍ | 3960/4692 [49:29<06:51, 1.78it/s] 84%|████████▍ | 3961/4692 [49:30<06:47, 1.79it/s] 84%|████████▍ | 3962/4692 [49:30<06:46, 1.79it/s] 84%|████████▍ | 3963/4692 [49:31<06:47, 1.79it/s] 84%|████████▍ | 3964/4692 [49:31<06:44, 1.80it/s] 85%|████████▍ | 3965/4692 [49:32<06:42, 1.81it/s] 85%|████████▍ | 3966/4692 [49:33<06:44, 1.80it/s] 85%|████████▍ | 3967/4692 [49:33<06:42, 1.80it/s] 85%|████████▍ | 3968/4692 [49:34<06:39, 1.81it/s] 85%|████████▍ | 3969/4692 [49:34<06:40, 1.80it/s] 85%|████████▍ | 3970/4692 [49:35<06:39, 1.81it/s] 85%|████████▍ | 3971/4692 [49:35<06:36, 1.82it/s] 85%|████████▍ | 3972/4692 [49:36<06:38, 1.81it/s] 85%|████████▍ | 3973/4692 [49:36<06:38, 1.80it/s] 85%|████████▍ | 3974/4692 [49:37<06:36, 1.81it/s] 85%|████████▍ | 3975/4692 [49:38<06:35, 1.81it/s] 85%|████████▍ | 3976/4692 [49:38<06:36, 1.80it/s] 85%|████████▍ | 3977/4692 [49:39<06:35, 1.81it/s] 85%|████████▍ | 3978/4692 [49:39<06:37, 1.80it/s] 85%|████████▍ | 3979/4692 [49:40<06:38, 1.79it/s] 85%|████████▍ | 3980/4692 [49:40<06:38, 1.79it/s] 85%|████████▍ | 3981/4692 [49:41<06:36, 1.79it/s] 85%|████████▍ | 3982/4692 [49:41<06:35, 1.80it/s] 85%|████████▍ | 3983/4692 [49:42<06:35, 1.79it/s] 85%|████████▍ | 3984/4692 [49:43<06:36, 1.78it/s] 85%|████████▍ | 3985/4692 [49:43<06:36, 1.78it/s] 85%|████████▍ | 3986/4692 [49:44<06:33, 1.79it/s] 85%|████████▍ | 3987/4692 [49:44<06:31, 1.80it/s] 85%|████████▍ | 3988/4692 [49:45<06:30, 1.80it/s] 85%|████████▌ | 3989/4692 [49:45<06:32, 1.79it/s] 85%|████████▌ | 3990/4692 [49:46<06:30, 1.80it/s] 85%|████████▌ | 3991/4692 [49:46<06:28, 1.81it/s] 85%|████████▌ | 3992/4692 [49:47<06:29, 1.80it/s] 85%|████████▌ | 3993/4692 [49:48<06:27, 1.80it/s] 85%|████████▌ | 3994/4692 [49:48<06:27, 1.80it/s] 85%|████████▌ | 3995/4692 [49:49<06:28, 1.79it/s] 85%|████████▌ | 3996/4692 [49:49<06:31, 1.78it/s] 85%|████████▌ | 3997/4692 [49:50<06:27, 1.79it/s] 85%|████████▌ | 3998/4692 [49:50<06:25, 1.80it/s] 85%|████████▌ | 3999/4692 [49:51<06:23, 1.81it/s] 85%|████████▌ | 4000/4692 [49:51<06:27, 1.78it/s] 85%|████████▌ | 4000/4692 [49:51<06:27, 1.78it/s] 85%|████████▌ | 4001/4692 [49:52<06:24, 1.80it/s] 85%|████████▌ | 4002/4692 [49:53<06:29, 1.77it/s] 85%|████████▌ | 4003/4692 [49:53<06:25, 1.79it/s] 85%|████████▌ | 4004/4692 [49:54<06:25, 1.78it/s] 85%|████████▌ | 4005/4692 [49:54<06:28, 1.77it/s] 85%|████████▌ | 4006/4692 [49:55<06:23, 1.79it/s] 85%|████████▌ | 4007/4692 [49:55<06:26, 1.77it/s] 85%|████████▌ | 4008/4692 [49:56<06:21, 1.79it/s] 85%|████████▌ | 4009/4692 [49:57<06:21, 1.79it/s] 85%|████████▌ | 4010/4692 [49:57<06:17, 1.81it/s] 85%|████████▌ | 4011/4692 [49:58<06:19, 1.79it/s] 86%|████████▌ | 4012/4692 [49:58<06:22, 1.78it/s] 86%|████████▌ | 4013/4692 [49:59<06:20, 1.79it/s] 86%|████████▌ | 4014/4692 [49:59<06:23, 1.77it/s] 86%|████████▌ | 4015/4692 [50:00<06:19, 1.78it/s] 86%|████████▌ | 4016/4692 [50:00<06:17, 1.79it/s] 86%|████████▌ | 4017/4692 [50:01<06:18, 1.78it/s] 86%|████████▌ | 4018/4692 [50:02<06:15, 1.79it/s] 86%|████████▌ | 4019/4692 [50:02<06:19, 1.77it/s] 86%|████████▌ | 4020/4692 [50:03<06:16, 1.79it/s] 86%|████████▌ | 4021/4692 [50:03<06:17, 1.78it/s] 86%|████████▌ | 4022/4692 [50:04<06:20, 1.76it/s] 86%|████████▌ | 4023/4692 [50:04<06:14, 1.78it/s] 86%|████████▌ | 4024/4692 [50:05<06:18, 1.76it/s] 86%|████████▌ | 4025/4692 [50:06<06:21, 1.75it/s] 86%|████████▌ | 4026/4692 [50:06<06:16, 1.77it/s] 86%|████████▌ | 4027/4692 [50:07<06:18, 1.75it/s] 86%|████████▌ | 4028/4692 [50:07<06:17, 1.76it/s] 86%|████████▌ | 4029/4692 [50:08<06:17, 1.75it/s] 86%|████████▌ | 4030/4692 [50:08<06:18, 1.75it/s] 86%|████████▌ | 4031/4692 [50:09<06:14, 1.76it/s] 86%|████████▌ | 4032/4692 [50:10<06:14, 1.76it/s] 86%|████████▌ | 4033/4692 [50:10<06:17, 1.74it/s] 86%|████████▌ | 4034/4692 [50:11<06:12, 1.77it/s] 86%|████████▌ | 4035/4692 [50:11<06:13, 1.76it/s] 86%|████████▌ | 4036/4692 [50:12<06:15, 1.75it/s] 86%|████████▌ | 4037/4692 [50:12<06:11, 1.76it/s] 86%|████████▌ | 4038/4692 [50:13<06:12, 1.76it/s] 86%|████████▌ | 4039/4692 [50:14<06:12, 1.75it/s] 86%|████████▌ | 4040/4692 [50:14<06:09, 1.76it/s] 86%|████████▌ | 4041/4692 [50:15<06:12, 1.75it/s] 86%|████████▌ | 4042/4692 [50:15<06:11, 1.75it/s] 86%|████████▌ | 4043/4692 [50:16<06:10, 1.75it/s] 86%|████████▌ | 4044/4692 [50:16<06:11, 1.74it/s] 86%|████████▌ | 4045/4692 [50:17<06:07, 1.76it/s] 86%|████████▌ | 4046/4692 [50:17<06:04, 1.77it/s] 86%|████████▋ | 4047/4692 [50:18<06:06, 1.76it/s] 86%|████████▋ | 4048/4692 [50:19<06:01, 1.78it/s] 86%|████████▋ | 4049/4692 [50:19<06:03, 1.77it/s] 86%|████████▋ | 4050/4692 [50:20<05:58, 1.79it/s] 86%|████████▋ | 4051/4692 [50:20<06:00, 1.78it/s] 86%|████████▋ | 4052/4692 [50:21<06:00, 1.78it/s] 86%|████████▋ | 4053/4692 [50:21<05:59, 1.78it/s] 86%|████████▋ | 4054/4692 [50:22<06:00, 1.77it/s] 86%|████████▋ | 4055/4692 [50:23<05:56, 1.79it/s] 86%|████████▋ | 4056/4692 [50:23<05:59, 1.77it/s] 86%|████████▋ | 4057/4692 [50:24<05:57, 1.78it/s] 86%|████████▋ | 4058/4692 [50:24<05:57, 1.77it/s] 87%|████████▋ | 4059/4692 [50:25<06:00, 1.76it/s] 87%|████████▋ | 4060/4692 [50:25<05:55, 1.78it/s] 87%|████████▋ | 4061/4692 [50:26<05:56, 1.77it/s] 87%|████████▋ | 4062/4692 [50:27<06:01, 1.74it/s] 87%|████████▋ | 4063/4692 [50:27<05:56, 1.76it/s] 87%|████████▋ | 4064/4692 [50:28<05:58, 1.75it/s] 87%|████████▋ | 4065/4692 [50:28<05:56, 1.76it/s] 87%|████████▋ | 4066/4692 [50:29<05:54, 1.77it/s] 87%|████████▋ | 4067/4692 [50:29<05:56, 1.76it/s] 87%|████████▋ | 4068/4692 [50:30<05:52, 1.77it/s] 87%|████████▋ | 4069/4692 [50:30<05:51, 1.77it/s] 87%|████████▋ | 4070/4692 [50:31<05:55, 1.75it/s] 87%|████████▋ | 4071/4692 [50:32<05:51, 1.77it/s] 87%|████████▋ | 4072/4692 [50:32<05:53, 1.76it/s] 87%|████████▋ | 4073/4692 [50:33<05:50, 1.77it/s] 87%|████████▋ | 4074/4692 [50:33<05:49, 1.77it/s] 87%|████████▋ | 4075/4692 [50:34<05:52, 1.75it/s] 87%|████████▋ | 4076/4692 [50:34<05:48, 1.77it/s] 87%|████████▋ | 4077/4692 [50:35<05:48, 1.76it/s] 87%|████████▋ | 4078/4692 [50:36<05:50, 1.75it/s] 87%|████████▋ | 4079/4692 [50:36<05:45, 1.78it/s] 87%|████████▋ | 4080/4692 [50:37<05:48, 1.76it/s] 87%|████████▋ | 4081/4692 [50:37<05:46, 1.76it/s] 87%|████████▋ | 4082/4692 [50:38<05:45, 1.76it/s] 87%|████████▋ | 4083/4692 [50:38<05:46, 1.76it/s] 87%|████████▋ | 4084/4692 [50:39<05:42, 1.77it/s] 87%|████████▋ | 4085/4692 [50:40<05:44, 1.76it/s] 87%|████████▋ | 4086/4692 [50:40<05:46, 1.75it/s] 87%|████████▋ | 4087/4692 [50:41<05:42, 1.76it/s] 87%|████████▋ | 4088/4692 [50:41<05:43, 1.76it/s] 87%|████████▋ | 4089/4692 [50:42<05:45, 1.75it/s] 87%|████████▋ | 4090/4692 [50:42<05:41, 1.76it/s] 87%|████████▋ | 4091/4692 [50:43<05:43, 1.75it/s] 87%|████████▋ | 4092/4692 [50:44<05:41, 1.76it/s] 87%|████████▋ | 4093/4692 [50:44<05:39, 1.76it/s] 87%|████████▋ | 4094/4692 [50:45<05:42, 1.75it/s] 87%|████████▋ | 4095/4692 [50:45<05:37, 1.77it/s] 87%|████████▋ | 4096/4692 [50:46<05:38, 1.76it/s] 87%|████████▋ | 4097/4692 [50:46<05:40, 1.75it/s] 87%|████████▋ | 4098/4692 [50:47<05:37, 1.76it/s] 87%|████████▋ | 4099/4692 [50:48<05:39, 1.75it/s] 87%|████████▋ | 4100/4692 [50:48<05:38, 1.75it/s] 87%|████████▋ | 4101/4692 [50:49<05:36, 1.76it/s] 87%|████████▋ | 4102/4692 [50:49<05:38, 1.74it/s] 87%|████████▋ | 4103/4692 [50:50<05:37, 1.75it/s] 87%|████████▋ | 4104/4692 [50:50<05:36, 1.75it/s] 87%|████████▋ | 4105/4692 [50:51<05:38, 1.74it/s] 88%|████████▊ | 4106/4692 [50:52<05:34, 1.75it/s] 88%|████████▊ | 4107/4692 [50:52<05:33, 1.76it/s] 88%|████████▊ | 4108/4692 [50:53<05:34, 1.74it/s] 88%|████████▊ | 4109/4692 [50:53<05:30, 1.77it/s] 88%|████████▊ | 4110/4692 [50:54<05:30, 1.76it/s] 88%|████████▊ | 4111/4692 [50:54<05:32, 1.75it/s] 88%|████████▊ | 4112/4692 [50:55<05:29, 1.76it/s] 88%|████████▊ | 4113/4692 [50:56<05:31, 1.75it/s] 88%|████████▊ | 4114/4692 [50:56<05:26, 1.77it/s] 88%|████████▊ | 4115/4692 [50:57<05:26, 1.77it/s] 88%|████████▊ | 4116/4692 [50:57<05:28, 1.75it/s] 88%|████████▊ | 4117/4692 [50:58<05:23, 1.78it/s] 88%|████████▊ | 4118/4692 [50:58<05:25, 1.76it/s] 88%|████████▊ | 4119/4692 [50:59<05:27, 1.75it/s] 88%|████████▊ | 4120/4692 [50:59<05:23, 1.77it/s] 88%|████████▊ | 4121/4692 [51:00<05:24, 1.76it/s] 88%|████████▊ | 4122/4692 [51:01<05:19, 1.78it/s] 88%|████████▊ | 4123/4692 [51:01<05:21, 1.77it/s] 88%|████████▊ | 4124/4692 [51:02<05:23, 1.76it/s] 88%|████████▊ | 4125/4692 [51:02<05:20, 1.77it/s] 88%|████████▊ | 4126/4692 [51:03<05:21, 1.76it/s] 88%|████████▊ | 4127/4692 [51:03<05:22, 1.75it/s] 88%|████████▊ | 4128/4692 [51:04<05:19, 1.77it/s] 88%|████████▊ | 4129/4692 [51:05<05:20, 1.76it/s] 88%|████████▊ | 4130/4692 [51:05<05:18, 1.76it/s] 88%|████████▊ | 4131/4692 [51:06<05:19, 1.76it/s] 88%|████████▊ | 4132/4692 [51:06<05:20, 1.75it/s] 88%|████████▊ | 4133/4692 [51:07<05:16, 1.77it/s] 88%|████████▊ | 4134/4692 [51:07<05:15, 1.77it/s] 88%|████████▊ | 4135/4692 [51:08<05:17, 1.75it/s] 88%|████████▊ | 4136/4692 [51:09<05:13, 1.78it/s] 88%|████████▊ | 4137/4692 [51:09<05:16, 1.75it/s] 88%|████████▊ | 4138/4692 [51:10<05:14, 1.76it/s] 88%|████████▊ | 4139/4692 [51:10<05:13, 1.76it/s] 88%|████████▊ | 4140/4692 [51:11<05:14, 1.75it/s] 88%|████████▊ | 4141/4692 [51:11<05:12, 1.77it/s] 88%|████████▊ | 4142/4692 [51:12<05:12, 1.76it/s] 88%|████████▊ | 4143/4692 [51:13<05:13, 1.75it/s] 88%|████████▊ | 4144/4692 [51:13<05:10, 1.77it/s] 88%|████████▊ | 4145/4692 [51:14<05:10, 1.76it/s] 88%|████████▊ | 4146/4692 [51:14<05:11, 1.75it/s] 88%|████████▊ | 4147/4692 [51:15<05:09, 1.76it/s] 88%|████████▊ | 4148/4692 [51:15<05:11, 1.75it/s] 88%|████████▊ | 4149/4692 [51:16<05:08, 1.76it/s] 88%|████████▊ | 4150/4692 [51:17<05:09, 1.75it/s] 88%|████████▊ | 4151/4692 [51:17<05:10, 1.74it/s] 88%|████████▊ | 4152/4692 [51:18<05:07, 1.76it/s] 89%|████████▊ | 4153/4692 [51:18<05:06, 1.76it/s] 89%|████████▊ | 4154/4692 [51:19<05:08, 1.75it/s] 89%|████████▊ | 4155/4692 [51:19<05:04, 1.76it/s] 89%|████████▊ | 4156/4692 [51:20<05:04, 1.76it/s] 89%|████████▊ | 4157/4692 [51:21<05:05, 1.75it/s] 89%|████████▊ | 4158/4692 [51:21<05:02, 1.77it/s] 89%|████████▊ | 4159/4692 [51:22<05:02, 1.76it/s] 89%|████████▊ | 4160/4692 [51:22<04:57, 1.79it/s] 89%|████████▊ | 4161/4692 [51:23<04:59, 1.78it/s] 89%|████████▊ | 4162/4692 [51:23<04:56, 1.78it/s] 89%|████████▊ | 4163/4692 [51:24<04:57, 1.78it/s] 89%|████████▊ | 4164/4692 [51:24<04:59, 1.77it/s] 89%|████████▉ | 4165/4692 [51:25<04:54, 1.79it/s] 89%|████████▉ | 4166/4692 [51:26<04:57, 1.77it/s] 89%|████████▉ | 4167/4692 [51:26<04:53, 1.79it/s] 89%|████████▉ | 4168/4692 [51:27<04:53, 1.79it/s] 89%|████████▉ | 4169/4692 [51:27<04:56, 1.76it/s] 89%|████████▉ | 4170/4692 [51:28<04:51, 1.79it/s] 89%|████████▉ | 4171/4692 [51:28<04:54, 1.77it/s] 89%|████████▉ | 4172/4692 [51:29<04:50, 1.79it/s] 89%|████████▉ | 4173/4692 [51:30<04:49, 1.79it/s] 89%|████████▉ | 4174/4692 [51:30<04:52, 1.77it/s] 89%|████████▉ | 4175/4692 [51:31<04:49, 1.78it/s] 89%|████████▉ | 4176/4692 [51:31<04:53, 1.76it/s] 89%|████████▉ | 4177/4692 [51:32<04:50, 1.77it/s] 89%|████████▉ | 4178/4692 [51:32<04:51, 1.76it/s] 89%|████████▉ | 4179/4692 [51:33<04:53, 1.75it/s] 89%|████████▉ | 4180/4692 [51:33<04:50, 1.76it/s] 89%|████████▉ | 4181/4692 [51:34<04:49, 1.76it/s] 89%|████████▉ | 4182/4692 [51:35<04:50, 1.75it/s] 89%|████████▉ | 4183/4692 [51:35<04:47, 1.77it/s] 89%|████████▉ | 4184/4692 [51:36<04:47, 1.77it/s] 89%|████████▉ | 4185/4692 [51:36<04:50, 1.74it/s] 89%|████████▉ | 4186/4692 [51:37<04:46, 1.77it/s] 89%|████████▉ | 4187/4692 [51:37<04:47, 1.75it/s] 89%|████████▉ | 4188/4692 [51:38<04:48, 1.75it/s] 89%|████████▉ | 4189/4692 [51:39<04:45, 1.76it/s] 89%|████████▉ | 4190/4692 [51:39<04:47, 1.75it/s] 89%|████████▉ | 4191/4692 [51:40<04:45, 1.75it/s] 89%|████████▉ | 4192/4692 [51:40<04:44, 1.76it/s] 89%|████████▉ | 4193/4692 [51:41<04:46, 1.74it/s] 89%|████████▉ | 4194/4692 [51:41<04:43, 1.76it/s] 89%|████████▉ | 4195/4692 [51:42<04:41, 1.77it/s] 89%|████████▉ | 4196/4692 [51:43<04:42, 1.76it/s] 89%|████████▉ | 4197/4692 [51:43<04:40, 1.77it/s] 89%|████████▉ | 4198/4692 [51:44<04:39, 1.76it/s] 89%|████████▉ | 4199/4692 [51:44<04:41, 1.75it/s] 90%|████████▉ | 4200/4692 [51:45<04:38, 1.77it/s] 90%|████████▉ | 4201/4692 [51:45<04:39, 1.76it/s] 90%|████████▉ | 4202/4692 [51:46<04:37, 1.76it/s] 90%|████████▉ | 4203/4692 [51:47<04:36, 1.77it/s] 90%|████████▉ | 4204/4692 [51:47<04:39, 1.75it/s] 90%|████████▉ | 4205/4692 [51:48<04:35, 1.77it/s] 90%|████████▉ | 4206/4692 [51:48<04:34, 1.77it/s] 90%|████████▉ | 4207/4692 [51:49<04:36, 1.76it/s] 90%|████████▉ | 4208/4692 [51:49<04:33, 1.77it/s] 90%|████████▉ | 4209/4692 [51:50<04:33, 1.77it/s] 90%|████████▉ | 4210/4692 [51:51<04:34, 1.75it/s] 90%|████████▉ | 4211/4692 [51:51<04:31, 1.77it/s] 90%|████████▉ | 4212/4692 [51:52<04:32, 1.76it/s] 90%|████████▉ | 4213/4692 [51:52<04:31, 1.76it/s] 90%|████████▉ | 4214/4692 [51:53<04:30, 1.77it/s] 90%|████████▉ | 4215/4692 [51:53<04:32, 1.75it/s] 90%|████████▉ | 4216/4692 [51:54<04:29, 1.77it/s] 90%|████████▉ | 4217/4692 [51:55<04:28, 1.77it/s] 90%|████████▉ | 4218/4692 [51:55<04:31, 1.75it/s] 90%|████████▉ | 4219/4692 [51:56<04:27, 1.77it/s] 90%|████████▉ | 4220/4692 [51:56<04:26, 1.77it/s] 90%|████████▉ | 4221/4692 [51:57<04:28, 1.76it/s] 90%|████████▉ | 4222/4692 [51:57<04:25, 1.77it/s] 90%|█████████ | 4223/4692 [51:58<04:27, 1.76it/s] 90%|█████████ | 4224/4692 [51:59<04:28, 1.75it/s] 90%|█████████ | 4225/4692 [51:59<04:24, 1.76it/s] 90%|█████████ | 4226/4692 [52:00<04:27, 1.74it/s] 90%|█████████ | 4227/4692 [52:00<04:27, 1.74it/s] 90%|█████████ | 4228/4692 [52:01<04:24, 1.75it/s] 90%|█████████ | 4229/4692 [52:01<04:26, 1.74it/s] 90%|█████████ | 4230/4692 [52:02<04:23, 1.75it/s] 90%|█████████ | 4231/4692 [52:03<04:23, 1.75it/s] 90%|█████████ | 4232/4692 [52:03<04:24, 1.74it/s] 90%|█████████ | 4233/4692 [52:04<04:21, 1.76it/s] 90%|█████████ | 4234/4692 [52:04<04:20, 1.76it/s] 90%|█████████ | 4235/4692 [52:05<04:21, 1.75it/s] 90%|█████████ | 4236/4692 [52:05<04:18, 1.76it/s] 90%|█████████ | 4237/4692 [52:06<04:18, 1.76it/s] 90%|█████████ | 4238/4692 [52:07<04:20, 1.75it/s] 90%|█████████ | 4239/4692 [52:07<04:00, 1.88it/s] 90%|█████████ | 4240/4692 [52:07<03:25, 2.20it/s] 90%|█████████ | 4241/4692 [52:07<03:01, 2.48it/s] 90%|█████████ | 4242/4692 [52:08<02:44, 2.73it/s] 90%|█████████ | 4243/4692 [52:08<02:32, 2.94it/s] 90%|█████████ | 4244/4692 [52:08<02:24, 3.11it/s] 90%|█████████ | 4245/4692 [52:09<02:18, 3.24it/s] 90%|█████████ | 4246/4692 [52:09<02:31, 2.95it/s] 91%|█████████ | 4247/4692 [52:10<03:00, 2.47it/s] 91%|█████████ | 4248/4692 [52:10<03:21, 2.21it/s] 91%|█████████ | 4249/4692 [52:11<03:33, 2.07it/s] 91%|█████████ | 4250/4692 [52:11<03:43, 1.98it/s] 91%|█████████ | 4251/4692 [52:12<03:50, 1.91it/s] 91%|█████████ | 4252/4692 [52:12<03:54, 1.87it/s] 91%|█████████ | 4253/4692 [52:13<03:58, 1.84it/s] 91%|█████████ | 4254/4692 [52:14<04:00, 1.82it/s] 91%|█████████ | 4255/4692 [52:14<04:01, 1.81it/s] 91%|█████████ | 4256/4692 [52:15<04:00, 1.82it/s] 91%|█████████ | 4257/4692 [52:15<04:01, 1.80it/s] 91%|█████████ | 4258/4692 [52:16<04:01, 1.80it/s] 91%|█████████ | 4259/4692 [52:16<04:00, 1.80it/s] 91%|█████████ | 4260/4692 [52:17<04:00, 1.79it/s] 91%|█████████ | 4261/4692 [52:17<04:01, 1.78it/s] 91%|█████████ | 4262/4692 [52:18<04:01, 1.78it/s] 91%|█████████ | 4263/4692 [52:19<03:59, 1.79it/s] 91%|█████████ | 4264/4692 [52:19<03:59, 1.79it/s] 91%|█████████ | 4265/4692 [52:20<03:58, 1.79it/s] 91%|█████████ | 4266/4692 [52:20<03:58, 1.79it/s] 91%|█████████ | 4267/4692 [52:21<03:57, 1.79it/s] 91%|█████████ | 4268/4692 [52:21<03:56, 1.79it/s] 91%|█████████ | 4269/4692 [52:22<03:57, 1.78it/s] 91%|█████████ | 4270/4692 [52:22<03:57, 1.78it/s] 91%|█████████ | 4271/4692 [52:23<03:57, 1.77it/s] 91%|█████████ | 4272/4692 [52:24<03:55, 1.78it/s] 91%|█████████ | 4273/4692 [52:24<03:54, 1.79it/s] 91%|█████████ | 4274/4692 [52:25<03:54, 1.78it/s] 91%|█████████ | 4275/4692 [52:25<03:52, 1.79it/s] 91%|█████████ | 4276/4692 [52:26<03:52, 1.79it/s] 91%|█████████ | 4277/4692 [52:26<03:52, 1.79it/s] 91%|█████████ | 4278/4692 [52:27<03:51, 1.79it/s] 91%|█████████ | 4279/4692 [52:27<03:50, 1.79it/s] 91%|█████████ | 4280/4692 [52:28<03:49, 1.80it/s] 91%|█████████ | 4281/4692 [52:29<03:50, 1.79it/s] 91%|█████████▏| 4282/4692 [52:29<03:50, 1.78it/s] 91%|█████████▏| 4283/4692 [52:30<03:49, 1.78it/s] 91%|█████████▏| 4284/4692 [52:30<03:48, 1.78it/s] 91%|█████████▏| 4285/4692 [52:31<03:47, 1.79it/s] 91%|█████████▏| 4286/4692 [52:31<03:46, 1.79it/s] 91%|█████████▏| 4287/4692 [52:32<03:46, 1.79it/s] 91%|█████████▏| 4288/4692 [52:33<03:45, 1.79it/s] 91%|█████████▏| 4289/4692 [52:33<03:45, 1.79it/s] 91%|█████████▏| 4290/4692 [52:34<03:45, 1.78it/s] 91%|█████████▏| 4291/4692 [52:34<03:44, 1.79it/s] 91%|█████████▏| 4292/4692 [52:35<03:44, 1.78it/s] 91%|█████████▏| 4293/4692 [52:35<03:43, 1.79it/s] 92%|█████████▏| 4294/4692 [52:36<03:41, 1.79it/s] 92%|█████████▏| 4295/4692 [52:36<03:42, 1.79it/s] 92%|█████████▏| 4296/4692 [52:37<03:42, 1.78it/s] 92%|█████████▏| 4297/4692 [52:38<03:41, 1.78it/s] 92%|█████████▏| 4298/4692 [52:38<03:40, 1.79it/s] 92%|█████████▏| 4299/4692 [52:39<03:39, 1.79it/s] 92%|█████████▏| 4300/4692 [52:39<03:39, 1.79it/s] 92%|█████████▏| 4301/4692 [52:40<03:38, 1.79it/s][INFO|trainer.py:738] 2023-07-03 02:00:17,229 >> The following columns in the evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: text. If text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3069] 2023-07-03 02:00:17,232 >> ***** Running Evaluation ***** [INFO|trainer.py:3071] 2023-07-03 02:00:17,232 >> Num examples = 25000 [INFO|trainer.py:3074] 2023-07-03 02:00:17,232 >> Batch size = 64 0%| | 0/391 [00:00> Saving model checkpoint to /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-4301 [INFO|configuration_utils.py:457] 2023-07-03 02:02:29,499 >> Configuration saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-4301/config.json [INFO|modeling_utils.py:1762] 2023-07-03 02:02:30,035 >> Model weights saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-4301/pytorch_model.bin [INFO|tokenization_utils_base.py:2163] 2023-07-03 02:02:30,035 >> tokenizer config file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-4301/tokenizer_config.json [INFO|tokenization_utils_base.py:2170] 2023-07-03 02:02:30,035 >> Special tokens file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-4301/special_tokens_map.json 92%|█████████▏| 4302/4692 [54:54<4:24:44, 40.73s/it] 92%|█████████▏| 4303/4692 [54:55<3:05:54, 28.68s/it] 92%|█████████▏| 4304/4692 [54:55<2:10:53, 20.24s/it] 92%|█████████▏| 4305/4692 [54:56<1:32:30, 14.34s/it] 92%|█████████▏| 4306/4692 [54:56<1:05:37, 10.20s/it] 92%|█████████▏| 4307/4692 [54:57<46:56, 7.31s/it] 92%|█████████▏| 4308/4692 [54:58<33:49, 5.28s/it] 92%|█████████▏| 4309/4692 [54:58<24:41, 3.87s/it] 92%|█████████▏| 4310/4692 [54:59<18:20, 2.88s/it] 92%|█████████▏| 4311/4692 [54:59<13:51, 2.18s/it] 92%|█████████▏| 4312/4692 [55:00<10:45, 1.70s/it] 92%|█████████▏| 4313/4692 [55:00<08:32, 1.35s/it] 92%|█████████▏| 4314/4692 [55:01<07:03, 1.12s/it] 92%|█████████▏| 4315/4692 [55:02<05:59, 1.05it/s] 92%|█████████▏| 4316/4692 [55:02<05:13, 1.20it/s] 92%|█████████▏| 4317/4692 [55:03<04:44, 1.32it/s] 92%|█████████▏| 4318/4692 [55:03<04:19, 1.44it/s] 92%|█████████▏| 4319/4692 [55:04<04:04, 1.52it/s] 92%|█████████▏| 4320/4692 [55:04<03:54, 1.59it/s] 92%|█████████▏| 4321/4692 [55:05<03:45, 1.64it/s] 92%|█████████▏| 4322/4692 [55:06<03:41, 1.67it/s] 92%|█████████▏| 4323/4692 [55:06<03:34, 1.72it/s] 92%|█████████▏| 4324/4692 [55:07<03:32, 1.73it/s] 92%|█████████▏| 4325/4692 [55:07<03:31, 1.74it/s] 92%|█████████▏| 4326/4692 [55:08<03:27, 1.76it/s] 92%|█████████▏| 4327/4692 [55:08<03:28, 1.75it/s] 92%|█████████▏| 4328/4692 [55:09<03:24, 1.78it/s] 92%|█████████▏| 4329/4692 [55:09<03:23, 1.78it/s] 92%|█████████▏| 4330/4692 [55:10<03:24, 1.77it/s] 92%|█████████▏| 4331/4692 [55:11<03:22, 1.78it/s] 92%|█████████▏| 4332/4692 [55:11<03:23, 1.77it/s] 92%|█████████▏| 4333/4692 [55:12<03:21, 1.78it/s] 92%|█████████▏| 4334/4692 [55:12<03:19, 1.79it/s] 92%|█████████▏| 4335/4692 [55:13<03:20, 1.78it/s] 92%|█████████▏| 4336/4692 [55:13<03:18, 1.80it/s] 92%|█████████▏| 4337/4692 [55:14<03:19, 1.78it/s] 92%|█████████▏| 4338/4692 [55:14<03:17, 1.79it/s] 92%|█████████▏| 4339/4692 [55:15<03:16, 1.79it/s] 92%|█████████▏| 4340/4692 [55:16<03:17, 1.78it/s] 93%|█████████▎| 4341/4692 [55:16<03:16, 1.79it/s] 93%|█████████▎| 4342/4692 [55:17<03:17, 1.77it/s] 93%|█████████▎| 4343/4692 [55:17<03:13, 1.80it/s] 93%|█████████▎| 4344/4692 [55:18<03:13, 1.80it/s] 93%|█████████▎| 4345/4692 [55:18<03:14, 1.79it/s] 93%|█████████▎| 4346/4692 [55:19<03:13, 1.79it/s] 93%|█████████▎| 4347/4692 [55:20<03:14, 1.77it/s] 93%|█████████▎| 4348/4692 [55:20<03:12, 1.79it/s] 93%|█████████▎| 4349/4692 [55:21<03:12, 1.78it/s] 93%|█████████▎| 4350/4692 [55:21<03:11, 1.79it/s] 93%|█████████▎| 4351/4692 [55:22<03:08, 1.81it/s] 93%|█████████▎| 4352/4692 [55:22<03:09, 1.80it/s] 93%|█████████▎| 4353/4692 [55:23<03:07, 1.80it/s] 93%|█████████▎| 4354/4692 [55:23<03:09, 1.79it/s] 93%|█████████▎| 4355/4692 [55:24<03:07, 1.80it/s] 93%|█████████▎| 4356/4692 [55:25<03:09, 1.78it/s] 93%|█████████▎| 4357/4692 [55:25<03:08, 1.78it/s] 93%|█████████▎| 4358/4692 [55:26<03:06, 1.79it/s] 93%|█████████▎| 4359/4692 [55:26<03:07, 1.77it/s] 93%|█████████▎| 4360/4692 [55:27<03:05, 1.79it/s] 93%|█████████▎| 4361/4692 [55:27<03:06, 1.77it/s] 93%|█████████▎| 4362/4692 [55:28<03:04, 1.78it/s] 93%|█████████▎| 4363/4692 [55:28<03:04, 1.78it/s] 93%|█████████▎| 4364/4692 [55:29<03:05, 1.77it/s] 93%|█████████▎| 4365/4692 [55:30<03:03, 1.79it/s] 93%|█████████▎| 4366/4692 [55:30<03:04, 1.77it/s] 93%|█████████▎| 4367/4692 [55:31<03:05, 1.75it/s] 93%|█████████▎| 4368/4692 [55:31<03:03, 1.76it/s] 93%|█████████▎| 4369/4692 [55:32<03:04, 1.75it/s] 93%|█████████▎| 4370/4692 [55:32<03:04, 1.74it/s] 93%|█████████▎| 4371/4692 [55:33<03:02, 1.76it/s] 93%|█████████▎| 4372/4692 [55:34<03:03, 1.74it/s] 93%|█████████▎| 4373/4692 [55:34<03:02, 1.75it/s] 93%|█████████▎| 4374/4692 [55:35<03:00, 1.76it/s] 93%|█████████▎| 4375/4692 [55:35<03:01, 1.75it/s] 93%|█████████▎| 4376/4692 [55:36<02:59, 1.76it/s] 93%|█████████▎| 4377/4692 [55:36<02:59, 1.76it/s] 93%|█████████▎| 4378/4692 [55:37<03:00, 1.74it/s] 93%|█████████▎| 4379/4692 [55:38<02:58, 1.76it/s] 93%|█████████▎| 4380/4692 [55:38<02:56, 1.76it/s] 93%|█████████▎| 4381/4692 [55:39<02:56, 1.76it/s] 93%|█████████▎| 4382/4692 [55:39<02:29, 2.08it/s] 93%|█████████▎| 4383/4692 [55:39<02:09, 2.38it/s] 93%|█████████▎| 4384/4692 [55:40<01:56, 2.65it/s] 93%|█████████▎| 4385/4692 [55:40<01:46, 2.87it/s] 93%|█████████▎| 4386/4692 [55:40<01:40, 3.06it/s] 93%|█████████▎| 4387/4692 [55:40<01:35, 3.20it/s] 94%|█████████▎| 4388/4692 [55:41<01:36, 3.14it/s] 94%|█████████▎| 4389/4692 [55:41<01:58, 2.56it/s] 94%|█████████▎| 4390/4692 [55:42<02:12, 2.28it/s] 94%|█████████▎| 4391/4692 [55:42<02:22, 2.11it/s] 94%|█████████▎| 4392/4692 [55:43<02:29, 2.00it/s] 94%|█████████▎| 4393/4692 [55:44<02:35, 1.92it/s] 94%|█████████▎| 4394/4692 [55:44<02:37, 1.89it/s] 94%|█████████▎| 4395/4692 [55:45<02:40, 1.85it/s] 94%|█████████▎| 4396/4692 [55:45<02:41, 1.83it/s] 94%|█████████▎| 4397/4692 [55:46<02:42, 1.82it/s] 94%|█████████▎| 4398/4692 [55:46<02:41, 1.82it/s] 94%|█████████▍| 4399/4692 [55:47<02:42, 1.81it/s] 94%|█████████▍| 4400/4692 [55:47<02:42, 1.80it/s] 94%|█████████▍| 4401/4692 [55:48<02:41, 1.80it/s] 94%|█████████▍| 4402/4692 [55:49<02:40, 1.80it/s] 94%|█████████▍| 4403/4692 [55:49<02:40, 1.80it/s] 94%|█████████▍| 4404/4692 [55:50<02:40, 1.80it/s] 94%|█████████▍| 4405/4692 [55:50<02:39, 1.79it/s] 94%|█████████▍| 4406/4692 [55:51<02:38, 1.81it/s] 94%|█████████▍| 4407/4692 [55:51<02:38, 1.80it/s] 94%|█████████▍| 4408/4692 [55:52<02:37, 1.80it/s] 94%|█████████▍| 4409/4692 [55:52<02:37, 1.79it/s] 94%|█████████▍| 4410/4692 [55:53<02:37, 1.79it/s] 94%|█████████▍| 4411/4692 [55:54<02:37, 1.78it/s] 94%|█████████▍| 4412/4692 [55:54<02:36, 1.79it/s] 94%|█████████▍| 4413/4692 [55:55<02:36, 1.79it/s] 94%|█████████▍| 4414/4692 [55:55<02:34, 1.80it/s] 94%|█████████▍| 4415/4692 [55:56<02:35, 1.78it/s] 94%|█████████▍| 4416/4692 [55:56<02:34, 1.79it/s] 94%|█████████▍| 4417/4692 [55:57<02:33, 1.79it/s] 94%|█████████▍| 4418/4692 [55:57<02:32, 1.79it/s] 94%|█████████▍| 4419/4692 [55:58<02:32, 1.79it/s] 94%|█████████▍| 4420/4692 [55:59<02:31, 1.79it/s] 94%|█████████▍| 4421/4692 [55:59<02:31, 1.79it/s] 94%|█████████▍| 4422/4692 [56:00<02:30, 1.79it/s] 94%|█████████▍| 4423/4692 [56:00<02:29, 1.80it/s] 94%|█████████▍| 4424/4692 [56:01<02:29, 1.79it/s] 94%|█████████▍| 4425/4692 [56:01<02:29, 1.79it/s] 94%|█████████▍| 4426/4692 [56:02<02:28, 1.79it/s] 94%|█████████▍| 4427/4692 [56:02<02:28, 1.79it/s] 94%|█████████▍| 4428/4692 [56:03<02:28, 1.78it/s] 94%|█████████▍| 4429/4692 [56:04<02:27, 1.79it/s] 94%|█████████▍| 4430/4692 [56:04<02:26, 1.78it/s] 94%|█████████▍| 4431/4692 [56:05<02:27, 1.78it/s] 94%|█████████▍| 4432/4692 [56:05<02:26, 1.78it/s] 94%|█████████▍| 4433/4692 [56:06<02:24, 1.79it/s] 95%|█████████▍| 4434/4692 [56:06<02:24, 1.79it/s] 95%|█████████▍| 4435/4692 [56:07<02:24, 1.78it/s] 95%|█████████▍| 4436/4692 [56:08<02:23, 1.79it/s] 95%|█████████▍| 4437/4692 [56:08<02:23, 1.78it/s] 95%|█████████▍| 4438/4692 [56:09<02:22, 1.79it/s] 95%|█████████▍| 4439/4692 [56:09<02:21, 1.79it/s] 95%|█████████▍| 4440/4692 [56:10<02:20, 1.79it/s] 95%|█████████▍| 4441/4692 [56:10<02:20, 1.79it/s] 95%|█████████▍| 4442/4692 [56:11<02:19, 1.80it/s] 95%|█████████▍| 4443/4692 [56:11<02:18, 1.80it/s] 95%|█████████▍| 4444/4692 [56:12<02:18, 1.80it/s] 95%|█████████▍| 4445/4692 [56:13<02:17, 1.80it/s] 95%|█████████▍| 4446/4692 [56:13<02:16, 1.80it/s] 95%|█████████▍| 4447/4692 [56:14<02:16, 1.79it/s] 95%|█████████▍| 4448/4692 [56:14<02:16, 1.78it/s] 95%|█████████▍| 4449/4692 [56:15<02:17, 1.77it/s] 95%|█████████▍| 4450/4692 [56:15<02:15, 1.79it/s] 95%|█████████▍| 4451/4692 [56:16<02:14, 1.80it/s] 95%|█████████▍| 4452/4692 [56:16<02:14, 1.79it/s] 95%|█████████▍| 4453/4692 [56:17<02:13, 1.79it/s] 95%|█████████▍| 4454/4692 [56:18<02:13, 1.79it/s] 95%|█████████▍| 4455/4692 [56:18<02:12, 1.79it/s] 95%|█████████▍| 4456/4692 [56:19<02:11, 1.79it/s] 95%|█████████▍| 4457/4692 [56:19<02:11, 1.78it/s] 95%|█████████▌| 4458/4692 [56:20<02:10, 1.79it/s] 95%|█████████▌| 4459/4692 [56:20<02:10, 1.79it/s] 95%|█████████▌| 4460/4692 [56:21<02:09, 1.79it/s] 95%|█████████▌| 4461/4692 [56:22<02:09, 1.79it/s] 95%|█████████▌| 4462/4692 [56:22<02:08, 1.79it/s] 95%|█████████▌| 4463/4692 [56:23<02:07, 1.79it/s] 95%|█████████▌| 4464/4692 [56:23<02:07, 1.79it/s] 95%|█████████▌| 4465/4692 [56:24<02:07, 1.79it/s] 95%|█████████▌| 4466/4692 [56:24<02:06, 1.79it/s] 95%|█████████▌| 4467/4692 [56:25<02:05, 1.79it/s] 95%|█████████▌| 4468/4692 [56:25<02:05, 1.78it/s] 95%|█████████▌| 4469/4692 [56:26<02:05, 1.78it/s] 95%|█████████▌| 4470/4692 [56:27<02:04, 1.78it/s] 95%|█████████▌| 4471/4692 [56:27<02:03, 1.78it/s] 95%|█████████▌| 4472/4692 [56:28<02:02, 1.79it/s] 95%|█████████▌| 4473/4692 [56:28<02:02, 1.79it/s] 95%|█████████▌| 4474/4692 [56:29<02:01, 1.79it/s] 95%|█████████▌| 4475/4692 [56:29<02:02, 1.78it/s] 95%|█████████▌| 4476/4692 [56:30<02:01, 1.78it/s] 95%|█████████▌| 4477/4692 [56:30<02:01, 1.78it/s] 95%|█████████▌| 4478/4692 [56:31<02:00, 1.78it/s] 95%|█████████▌| 4479/4692 [56:32<02:00, 1.77it/s] 95%|█████████▌| 4480/4692 [56:32<01:59, 1.78it/s] 96%|█████████▌| 4481/4692 [56:33<01:57, 1.79it/s] 96%|█████████▌| 4482/4692 [56:33<01:56, 1.80it/s] 96%|█████████▌| 4483/4692 [56:34<01:56, 1.79it/s] 96%|█████████▌| 4484/4692 [56:34<01:56, 1.79it/s] 96%|█████████▌| 4485/4692 [56:35<01:55, 1.79it/s] 96%|█████████▌| 4486/4692 [56:36<01:55, 1.79it/s] 96%|█████████▌| 4487/4692 [56:36<01:54, 1.79it/s] 96%|█████████▌| 4488/4692 [56:37<01:53, 1.79it/s] 96%|█████████▌| 4489/4692 [56:37<01:53, 1.80it/s] 96%|█████████▌| 4490/4692 [56:38<01:52, 1.79it/s] 96%|█████████▌| 4491/4692 [56:38<01:52, 1.78it/s] 96%|█████████▌| 4492/4692 [56:39<01:52, 1.78it/s] 96%|█████████▌| 4493/4692 [56:39<01:51, 1.78it/s] 96%|█████████▌| 4494/4692 [56:40<01:51, 1.78it/s] 96%|█████████▌| 4495/4692 [56:41<01:50, 1.78it/s] 96%|█████████▌| 4496/4692 [56:41<01:50, 1.78it/s] 96%|█████████▌| 4497/4692 [56:42<01:49, 1.79it/s] 96%|█████████▌| 4498/4692 [56:42<01:48, 1.78it/s] 96%|█████████▌| 4499/4692 [56:43<01:47, 1.79it/s] 96%|█████████▌| 4500/4692 [56:43<01:47, 1.79it/s] 96%|█████████▌| 4500/4692 [56:43<01:47, 1.79it/s] 96%|█████████▌| 4501/4692 [56:44<01:46, 1.80it/s] 96%|█████████▌| 4502/4692 [56:44<01:45, 1.81it/s] 96%|█████████▌| 4503/4692 [56:45<01:44, 1.81it/s] 96%|█████████▌| 4504/4692 [56:46<01:44, 1.80it/s] 96%|█████████▌| 4505/4692 [56:46<01:44, 1.80it/s] 96%|█████████▌| 4506/4692 [56:47<01:43, 1.80it/s] 96%|█████████▌| 4507/4692 [56:47<01:43, 1.79it/s] 96%|█████████▌| 4508/4692 [56:48<01:42, 1.79it/s] 96%|█████████▌| 4509/4692 [56:48<01:42, 1.78it/s] 96%|█████████▌| 4510/4692 [56:49<01:41, 1.79it/s] 96%|█████████▌| 4511/4692 [56:49<01:41, 1.78it/s] 96%|█████████▌| 4512/4692 [56:50<01:40, 1.79it/s] 96%|█████████▌| 4513/4692 [56:51<01:40, 1.78it/s] 96%|█████████▌| 4514/4692 [56:51<01:39, 1.78it/s] 96%|█████████▌| 4515/4692 [56:52<01:39, 1.78it/s] 96%|█████████▌| 4516/4692 [56:52<01:38, 1.79it/s] 96%|█████████▋| 4517/4692 [56:53<01:38, 1.78it/s] 96%|█████████▋| 4518/4692 [56:53<01:38, 1.77it/s] 96%|█████████▋| 4519/4692 [56:54<01:37, 1.78it/s] 96%|█████████▋| 4520/4692 [56:55<01:36, 1.79it/s] 96%|█████████▋| 4521/4692 [56:55<01:35, 1.79it/s] 96%|█████████▋| 4522/4692 [56:56<01:35, 1.78it/s] 96%|█████████▋| 4523/4692 [56:56<01:34, 1.79it/s] 96%|█████████▋| 4524/4692 [56:57<01:33, 1.79it/s] 96%|█████████▋| 4525/4692 [56:57<01:33, 1.78it/s] 96%|█████████▋| 4526/4692 [56:58<01:33, 1.78it/s] 96%|█████████▋| 4527/4692 [56:58<01:32, 1.79it/s] 97%|█████████▋| 4528/4692 [56:59<01:31, 1.79it/s] 97%|█████████▋| 4529/4692 [57:00<01:31, 1.79it/s] 97%|█████████▋| 4530/4692 [57:00<01:29, 1.81it/s] 97%|█████████▋| 4531/4692 [57:01<01:29, 1.80it/s] 97%|█████████▋| 4532/4692 [57:01<01:30, 1.77it/s] 97%|█████████▋| 4533/4692 [57:02<01:29, 1.78it/s] 97%|█████████▋| 4534/4692 [57:02<01:29, 1.77it/s] 97%|█████████▋| 4535/4692 [57:03<01:29, 1.75it/s] 97%|█████████▋| 4536/4692 [57:04<01:28, 1.77it/s] 97%|█████████▋| 4537/4692 [57:04<01:28, 1.75it/s] 97%|█████████▋| 4538/4692 [57:05<01:27, 1.76it/s] 97%|█████████▋| 4539/4692 [57:05<01:26, 1.77it/s] 97%|█████████▋| 4540/4692 [57:06<01:26, 1.76it/s] 97%|█████████▋| 4541/4692 [57:06<01:25, 1.77it/s] 97%|█████████▋| 4542/4692 [57:07<01:25, 1.76it/s] 97%|█████████▋| 4543/4692 [57:08<01:26, 1.73it/s] 97%|█████████▋| 4544/4692 [57:08<01:24, 1.75it/s] 97%|█████████▋| 4545/4692 [57:09<01:23, 1.75it/s] 97%|█████████▋| 4546/4692 [57:09<01:23, 1.74it/s] 97%|█████████▋| 4547/4692 [57:10<01:22, 1.76it/s] 97%|█████████▋| 4548/4692 [57:10<01:22, 1.75it/s] 97%|█████████▋| 4549/4692 [57:11<01:21, 1.75it/s] 97%|█████████▋| 4550/4692 [57:12<01:20, 1.76it/s] 97%|█████████▋| 4551/4692 [57:12<01:20, 1.75it/s] 97%|█████████▋| 4552/4692 [57:13<01:18, 1.77it/s] 97%|█████████▋| 4553/4692 [57:13<01:18, 1.78it/s] 97%|█████████▋| 4554/4692 [57:14<01:18, 1.76it/s] 97%|█████████▋| 4555/4692 [57:14<01:17, 1.77it/s] 97%|█████████▋| 4556/4692 [57:15<01:17, 1.76it/s] 97%|█████████▋| 4557/4692 [57:16<01:17, 1.74it/s] 97%|█████████▋| 4558/4692 [57:16<01:16, 1.75it/s] 97%|█████████▋| 4559/4692 [57:17<01:16, 1.75it/s] 97%|█████████▋| 4560/4692 [57:17<01:15, 1.74it/s] 97%|█████████▋| 4561/4692 [57:18<01:14, 1.76it/s] 97%|█████████▋| 4562/4692 [57:18<01:14, 1.75it/s] 97%|█████████▋| 4563/4692 [57:19<01:13, 1.77it/s] 97%|█████████▋| 4564/4692 [57:19<01:12, 1.76it/s] 97%|█████████▋| 4565/4692 [57:20<01:12, 1.75it/s] 97%|█████████▋| 4566/4692 [57:21<01:11, 1.76it/s] 97%|█████████▋| 4567/4692 [57:21<01:11, 1.76it/s] 97%|█████████▋| 4568/4692 [57:22<01:11, 1.75it/s] 97%|█████████▋| 4569/4692 [57:22<01:09, 1.77it/s] 97%|█████████▋| 4570/4692 [57:23<01:10, 1.74it/s] 97%|█████████▋| 4571/4692 [57:23<01:09, 1.74it/s] 97%|█████████▋| 4572/4692 [57:24<01:08, 1.75it/s] 97%|█████████▋| 4573/4692 [57:25<01:08, 1.74it/s] 97%|█████████▋| 4574/4692 [57:25<01:07, 1.76it/s] 98%|█████████▊| 4575/4692 [57:26<01:06, 1.76it/s] 98%|█████████▊| 4576/4692 [57:26<01:06, 1.74it/s] 98%|█████████▊| 4577/4692 [57:27<01:05, 1.75it/s] 98%|█████████▊| 4578/4692 [57:27<01:05, 1.75it/s] 98%|█████████▊| 4579/4692 [57:28<01:05, 1.73it/s] 98%|█████████▊| 4580/4692 [57:29<01:03, 1.75it/s] 98%|█████████▊| 4581/4692 [57:29<01:03, 1.76it/s] 98%|█████████▊| 4582/4692 [57:30<01:03, 1.75it/s] 98%|█████████▊| 4583/4692 [57:30<01:02, 1.76it/s] 98%|█████████▊| 4584/4692 [57:31<01:01, 1.76it/s] 98%|█████████▊| 4585/4692 [57:31<01:01, 1.75it/s] 98%|█████████▊| 4586/4692 [57:32<00:59, 1.77it/s] 98%|█████████▊| 4587/4692 [57:33<00:59, 1.76it/s] 98%|█████████▊| 4588/4692 [57:33<00:58, 1.77it/s] 98%|█████████▊| 4589/4692 [57:34<00:58, 1.76it/s] 98%|█████████▊| 4590/4692 [57:34<00:58, 1.75it/s] 98%|█████████▊| 4591/4692 [57:35<00:57, 1.76it/s] 98%|█████████▊| 4592/4692 [57:35<00:56, 1.76it/s] 98%|█████████▊| 4593/4692 [57:36<00:56, 1.74it/s] 98%|█████████▊| 4594/4692 [57:37<00:55, 1.76it/s] 98%|█████████▊| 4595/4692 [57:37<00:55, 1.76it/s] 98%|█████████▊| 4596/4692 [57:38<00:55, 1.74it/s] 98%|█████████▊| 4597/4692 [57:38<00:54, 1.76it/s] 98%|█████████▊| 4598/4692 [57:39<00:53, 1.75it/s] 98%|█████████▊| 4599/4692 [57:39<00:52, 1.76it/s] 98%|█████████▊| 4600/4692 [57:40<00:52, 1.75it/s] 98%|█████████▊| 4601/4692 [57:41<00:52, 1.74it/s] 98%|█████████▊| 4602/4692 [57:41<00:51, 1.76it/s] 98%|█████████▊| 4603/4692 [57:42<00:50, 1.76it/s] 98%|█████████▊| 4604/4692 [57:42<00:50, 1.75it/s] 98%|█████████▊| 4605/4692 [57:43<00:49, 1.76it/s] 98%|█████████▊| 4606/4692 [57:43<00:48, 1.76it/s] 98%|█████████▊| 4607/4692 [57:44<00:48, 1.74it/s] 98%|█████████▊| 4608/4692 [57:45<00:47, 1.77it/s] 98%|█████████▊| 4609/4692 [57:45<00:47, 1.75it/s] 98%|█████████▊| 4610/4692 [57:46<00:47, 1.74it/s] 98%|█████████▊| 4611/4692 [57:46<00:46, 1.76it/s] 98%|█████████▊| 4612/4692 [57:47<00:45, 1.75it/s] 98%|█████████▊| 4613/4692 [57:47<00:44, 1.77it/s] 98%|█████████▊| 4614/4692 [57:48<00:44, 1.77it/s] 98%|█████████▊| 4615/4692 [57:49<00:43, 1.76it/s] 98%|█████████▊| 4616/4692 [57:49<00:42, 1.77it/s] 98%|█████████▊| 4617/4692 [57:50<00:42, 1.76it/s] 98%|█████████▊| 4618/4692 [57:50<00:41, 1.77it/s] 98%|█████████▊| 4619/4692 [57:51<00:41, 1.77it/s] 98%|█████████▊| 4620/4692 [57:51<00:41, 1.75it/s] 98%|█████████▊| 4621/4692 [57:52<00:40, 1.77it/s] 99%|█████████▊| 4622/4692 [57:53<00:39, 1.76it/s] 99%|█████████▊| 4623/4692 [57:53<00:39, 1.75it/s] 99%|█████████▊| 4624/4692 [57:54<00:38, 1.76it/s] 99%|█████████▊| 4625/4692 [57:54<00:38, 1.75it/s] 99%|█████████▊| 4626/4692 [57:55<00:37, 1.77it/s] 99%|█████████▊| 4627/4692 [57:55<00:36, 1.76it/s] 99%|█████████▊| 4628/4692 [57:56<00:36, 1.75it/s] 99%|█████████▊| 4629/4692 [57:56<00:35, 1.77it/s] 99%|█████████▊| 4630/4692 [57:57<00:35, 1.77it/s] 99%|█████████▊| 4631/4692 [57:58<00:34, 1.76it/s] 99%|█████████▊| 4632/4692 [57:58<00:33, 1.78it/s] 99%|█████████▊| 4633/4692 [57:59<00:33, 1.75it/s] 99%|█████████▉| 4634/4692 [57:59<00:33, 1.75it/s] 99%|█████████▉| 4635/4692 [58:00<00:32, 1.76it/s] 99%|█████████▉| 4636/4692 [58:00<00:32, 1.75it/s] 99%|█████████▉| 4637/4692 [58:01<00:31, 1.77it/s] 99%|█████████▉| 4638/4692 [58:02<00:30, 1.76it/s] 99%|█████████▉| 4639/4692 [58:02<00:30, 1.74it/s] 99%|█████████▉| 4640/4692 [58:03<00:29, 1.77it/s] 99%|█████████▉| 4641/4692 [58:03<00:29, 1.75it/s] 99%|█████████▉| 4642/4692 [58:04<00:28, 1.76it/s] 99%|█████████▉| 4643/4692 [58:04<00:27, 1.75it/s] 99%|█████████▉| 4644/4692 [58:05<00:27, 1.74it/s] 99%|█████████▉| 4645/4692 [58:06<00:26, 1.76it/s] 99%|█████████▉| 4646/4692 [58:06<00:26, 1.77it/s] 99%|█████████▉| 4647/4692 [58:07<00:25, 1.75it/s] 99%|█████████▉| 4648/4692 [58:07<00:24, 1.77it/s] 99%|█████████▉| 4649/4692 [58:08<00:24, 1.76it/s] 99%|█████████▉| 4650/4692 [58:08<00:24, 1.75it/s] 99%|█████████▉| 4651/4692 [58:09<00:23, 1.77it/s] 99%|█████████▉| 4652/4692 [58:10<00:22, 1.76it/s] 99%|█████████▉| 4653/4692 [58:10<00:22, 1.76it/s] 99%|█████████▉| 4654/4692 [58:11<00:21, 1.76it/s] 99%|█████████▉| 4655/4692 [58:11<00:21, 1.75it/s] 99%|█████████▉| 4656/4692 [58:12<00:20, 1.77it/s] 99%|█████████▉| 4657/4692 [58:12<00:19, 1.77it/s] 99%|█████████▉| 4658/4692 [58:13<00:19, 1.75it/s] 99%|█████████▉| 4659/4692 [58:14<00:18, 1.76it/s] 99%|█████████▉| 4660/4692 [58:14<00:18, 1.77it/s] 99%|█████████▉| 4661/4692 [58:15<00:17, 1.75it/s] 99%|█████████▉| 4662/4692 [58:15<00:16, 1.77it/s] 99%|█████████▉| 4663/4692 [58:16<00:16, 1.77it/s] 99%|█████████▉| 4664/4692 [58:16<00:15, 1.75it/s] 99%|█████████▉| 4665/4692 [58:17<00:15, 1.78it/s] 99%|█████████▉| 4666/4692 [58:18<00:14, 1.76it/s] 99%|█████████▉| 4667/4692 [58:18<00:14, 1.78it/s] 99%|█████████▉| 4668/4692 [58:19<00:13, 1.78it/s] 100%|█████████▉| 4669/4692 [58:19<00:13, 1.76it/s] 100%|█████████▉| 4670/4692 [58:20<00:12, 1.77it/s] 100%|█████████▉| 4671/4692 [58:20<00:11, 1.77it/s] 100%|█████████▉| 4672/4692 [58:21<00:11, 1.76it/s] 100%|█████████▉| 4673/4692 [58:21<00:10, 1.77it/s] 100%|█████████▉| 4674/4692 [58:22<00:10, 1.75it/s] 100%|█████████▉| 4675/4692 [58:23<00:09, 1.74it/s] 100%|█████████▉| 4676/4692 [58:23<00:09, 1.76it/s] 100%|█████████▉| 4677/4692 [58:24<00:08, 1.74it/s] 100%|█████████▉| 4678/4692 [58:24<00:08, 1.75it/s] 100%|█████████▉| 4679/4692 [58:25<00:07, 1.76it/s] 100%|█████████▉| 4680/4692 [58:25<00:06, 1.75it/s] 100%|█████████▉| 4681/4692 [58:26<00:06, 1.77it/s] 100%|█████████▉| 4682/4692 [58:27<00:05, 1.77it/s] 100%|█████████▉| 4683/4692 [58:27<00:05, 1.76it/s] 100%|█████████▉| 4684/4692 [58:28<00:04, 1.77it/s] 100%|█████████▉| 4685/4692 [58:28<00:03, 1.77it/s] 100%|█████████▉| 4686/4692 [58:29<00:03, 1.76it/s] 100%|█████████▉| 4687/4692 [58:29<00:02, 1.77it/s] 100%|█████████▉| 4688/4692 [58:30<00:02, 1.75it/s] 100%|█████████▉| 4689/4692 [58:31<00:01, 1.74it/s] 100%|█████████▉| 4690/4692 [58:31<00:01, 1.76it/s] 100%|█████████▉| 4691/4692 [58:32<00:00, 1.75it/s] 100%|██████████| 4692/4692 [58:32<00:00, 2.20it/s][INFO|trainer.py:738] 2023-07-03 02:06:09,343 >> The following columns in the evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: text. If text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3069] 2023-07-03 02:06:09,347 >> ***** Running Evaluation ***** [INFO|trainer.py:3071] 2023-07-03 02:06:09,347 >> Num examples = 25000 [INFO|trainer.py:3074] 2023-07-03 02:06:09,347 >> Batch size = 64 0%| | 0/391 [00:00> Saving model checkpoint to /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-4692 [INFO|configuration_utils.py:457] 2023-07-03 02:08:19,612 >> Configuration saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-4692/config.json [INFO|modeling_utils.py:1762] 2023-07-03 02:08:20,183 >> Model weights saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-4692/pytorch_model.bin [INFO|tokenization_utils_base.py:2163] 2023-07-03 02:08:20,183 >> tokenizer config file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-4692/tokenizer_config.json [INFO|tokenization_utils_base.py:2170] 2023-07-03 02:08:20,184 >> Special tokens file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-4692/special_tokens_map.json [INFO|trainer.py:2893] 2023-07-03 02:08:21,354 >> Deleting older checkpoint [/nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-3910] due to args.save_total_limit [INFO|trainer.py:2893] 2023-07-03 02:08:21,468 >> Deleting older checkpoint [/nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-4301] due to args.save_total_limit [INFO|trainer.py:2013] 2023-07-03 02:08:21,590 >> Training completed. Do not forget to share your model on huggingface.co/models =) [INFO|trainer.py:2133] 2023-07-03 02:08:21,590 >> Loading best model from /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/checkpoint-4692 (score: 0.92816). 100%|██████████| 4692/4692 [1:00:45<00:00, 2.20it/s] 100%|██████████| 4692/4692 [1:00:45<00:00, 1.29it/s] [INFO|trainer.py:2815] 2023-07-03 02:08:22,187 >> Saving model checkpoint to /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6 [INFO|configuration_utils.py:457] 2023-07-03 02:08:22,188 >> Configuration saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/config.json [INFO|modeling_utils.py:1762] 2023-07-03 02:08:22,722 >> Model weights saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/pytorch_model.bin [INFO|tokenization_utils_base.py:2163] 2023-07-03 02:08:22,722 >> tokenizer config file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/tokenizer_config.json [INFO|tokenization_utils_base.py:2170] 2023-07-03 02:08:22,722 >> Special tokens file saved in /nvme1/yujiepan/token-dropping-logs/logs-final/train-imdb-baseline/0703-lr5e-05_warm0.1_epoch6/special_tokens_map.json [INFO|trainer.py:738] 2023-07-03 02:08:22,754 >> The following columns in the evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: text. If text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3069] 2023-07-03 02:08:22,756 >> ***** Running Evaluation ***** [INFO|trainer.py:3071] 2023-07-03 02:08:22,756 >> Num examples = 25000 [INFO|trainer.py:3074] 2023-07-03 02:08:22,756 >> Batch size = 64 0%| | 0/391 [00:00> The following columns in the evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: text. If text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3069] 2023-07-03 02:10:33,188 >> ***** Running Evaluation ***** [INFO|trainer.py:3071] 2023-07-03 02:10:33,188 >> Num examples = 5958 [INFO|trainer.py:3074] 2023-07-03 02:10:33,188 >> Batch size = 64 0%| | 0/94 [00:00