| 07/22/2022 12:31:56 - WARNING - __main__ - Process rank: -1, device: cuda:0, n_gpu: 1distributed training: False, 16-bits training: True | |
| 07/22/2022 12:31:56 - INFO - __main__ - Training/evaluation parameters TrainingArguments( | |
| _n_gpu=1, | |
| adafactor=False, | |
| adam_beta1=0.9, | |
| adam_beta2=0.999, | |
| adam_epsilon=1e-08, | |
| auto_find_batch_size=False, | |
| bf16=False, | |
| bf16_full_eval=False, | |
| data_seed=None, | |
| dataloader_drop_last=False, | |
| dataloader_num_workers=0, | |
| dataloader_pin_memory=True, | |
| ddp_bucket_cap_mb=None, | |
| ddp_find_unused_parameters=None, | |
| debug=[], | |
| deepspeed=None, | |
| disable_tqdm=False, | |
| do_eval=True, | |
| do_predict=True, | |
| do_train=True, | |
| eval_accumulation_steps=None, | |
| eval_delay=0, | |
| eval_steps=None, | |
| evaluation_strategy=IntervalStrategy.NO, | |
| fp16=True, | |
| fp16_backend=auto, | |
| fp16_full_eval=False, | |
| fp16_opt_level=O1, | |
| fsdp=[], | |
| fsdp_min_num_params=0, | |
| full_determinism=False, | |
| gradient_accumulation_steps=1, | |
| gradient_checkpointing=False, | |
| greater_is_better=None, | |
| group_by_length=False, | |
| half_precision_backend=auto, | |
| hub_model_id=None, | |
| hub_private_repo=False, | |
| hub_strategy=HubStrategy.EVERY_SAVE, | |
| hub_token=<HUB_TOKEN>, | |
| ignore_data_skip=False, | |
| include_inputs_for_metrics=False, | |
| jit_mode_eval=False, | |
| label_names=None, | |
| label_smoothing_factor=0.0, | |
| learning_rate=5e-05, | |
| length_column_name=length, | |
| load_best_model_at_end=False, | |
| local_rank=-1, | |
| log_level=-1, | |
| log_level_replica=-1, | |
| log_on_each_node=True, | |
| logging_dir=runs/ebmnlp_hf/BioLinkBERT-base/runs/Jul22_12-31-56_spartan-gpgpu080.hpc.unimelb.edu.au, | |
| logging_first_step=False, | |
| logging_nan_inf_filter=True, | |
| logging_steps=500, | |
| logging_strategy=IntervalStrategy.STEPS, | |
| lr_scheduler_type=SchedulerType.LINEAR, | |
| max_grad_norm=1.0, | |
| max_steps=-1, | |
| metric_for_best_model=None, | |
| mp_parameters=, | |
| no_cuda=False, | |
| num_train_epochs=1.0, | |
| optim=OptimizerNames.ADAMW_HF, | |
| output_dir=runs/ebmnlp_hf/BioLinkBERT-base, | |
| overwrite_output_dir=True, | |
| past_index=-1, | |
| per_device_eval_batch_size=8, | |
| per_device_train_batch_size=32, | |
| prediction_loss_only=False, | |
| push_to_hub=False, | |
| push_to_hub_model_id=None, | |
| push_to_hub_organization=None, | |
| push_to_hub_token=<PUSH_TO_HUB_TOKEN>, | |
| ray_scope=last, | |
| remove_unused_columns=True, | |
| report_to=['tensorboard'], | |
| resume_from_checkpoint=None, | |
| run_name=runs/ebmnlp_hf/BioLinkBERT-base, | |
| save_on_each_node=False, | |
| save_steps=500, | |
| save_strategy=IntervalStrategy.NO, | |
| save_total_limit=None, | |
| seed=42, | |
| sharded_ddp=[], | |
| skip_memory_metrics=True, | |
| tf32=None, | |
| torchdynamo=None, | |
| tpu_metrics_debug=False, | |
| tpu_num_cores=None, | |
| use_ipex=False, | |
| use_legacy_prediction_loop=False, | |
| warmup_ratio=0.0, | |
| warmup_steps=0, | |
| weight_decay=0.0, | |
| xpu_backend=None, | |
| ) | |
| 07/22/2022 12:31:57 - WARNING - datasets.builder - Using custom data configuration default-2d9cec4b8a27d237 | |
| 07/22/2022 12:31:57 - INFO - datasets.builder - Overwrite dataset info from restored data version. | |
| 07/22/2022 12:31:57 - INFO - datasets.info - Loading Dataset info from /home/hungthinht/.cache/huggingface/datasets/json/default-2d9cec4b8a27d237/0.0.0/da492aad5680612e4028e7f6ddc04b1dfcec4b64db470ed7cc5f2bb265b9b6b5 | |
| 07/22/2022 12:31:57 - WARNING - datasets.builder - Reusing dataset json (/home/hungthinht/.cache/huggingface/datasets/json/default-2d9cec4b8a27d237/0.0.0/da492aad5680612e4028e7f6ddc04b1dfcec4b64db470ed7cc5f2bb265b9b6b5) | |
| 07/22/2022 12:31:57 - INFO - datasets.info - Loading Dataset info from /home/hungthinht/.cache/huggingface/datasets/json/default-2d9cec4b8a27d237/0.0.0/da492aad5680612e4028e7f6ddc04b1dfcec4b64db470ed7cc5f2bb265b9b6b5 | |
| 0%| | 0/3 [00:00<?, ?it/s] 100%|██████████| 3/3 [00:00<00:00, 491.92it/s] | |
| [INFO|configuration_utils.py:659] 2022-07-22 12:31:59,048 >> loading configuration file https://huggingface.co/michiyasunaga/BioLinkBERT-base/resolve/main/config.json from cache at /home/hungthinht/.cache/huggingface/transformers/ad032c76cac1f75bba037ba006dcccc1c62ab157749b194df023bfa55e5f4fbf.22ae3f7c73ebda8488a8505a67c1b929a707ae7db67a129f60b7c28acfc38436 | |
| [INFO|configuration_utils.py:708] 2022-07-22 12:31:59,083 >> Model config BertConfig { | |
| "_name_or_path": "michiyasunaga/BioLinkBERT-base", | |
| "architectures": [ | |
| "BertModel" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "classifier_dropout": null, | |
| "finetuning_task": "ner", | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "B-INT", | |
| "1": "B-OUT", | |
| "2": "B-PAR", | |
| "3": "O" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "B-INT": 0, | |
| "B-OUT": 1, | |
| "B-PAR": 2, | |
| "O": 3 | |
| }, | |
| "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", | |
| "transformers_version": "4.20.1", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "vocab_size": 28895 | |
| } | |
| [INFO|tokenization_utils_base.py:1781] 2022-07-22 12:32:05,294 >> loading file https://huggingface.co/michiyasunaga/BioLinkBERT-base/resolve/main/vocab.txt from cache at /home/hungthinht/.cache/huggingface/transformers/9eb712b5fcba51331b49cb69f18de1577371a2582055a298e2546c0c97d3b924.73b5c069d3e40205dd2df2379051c9f47d13c3bad0bcb3cee659c69e3a185a86 | |
| [INFO|tokenization_utils_base.py:1781] 2022-07-22 12:32:05,294 >> loading file https://huggingface.co/michiyasunaga/BioLinkBERT-base/resolve/main/tokenizer.json from cache at /home/hungthinht/.cache/huggingface/transformers/3c720cf86b025f815b1d833b6b39db05e8e7493b6f6a87788c485a946848b4d8.a25e24b89fd9bfd32e3c8d2dbb39879c62152e7f069ab24c97198c004cad94c9 | |
| [INFO|tokenization_utils_base.py:1781] 2022-07-22 12:32:05,294 >> loading file https://huggingface.co/michiyasunaga/BioLinkBERT-base/resolve/main/added_tokens.json from cache at None | |
| [INFO|tokenization_utils_base.py:1781] 2022-07-22 12:32:05,294 >> loading file https://huggingface.co/michiyasunaga/BioLinkBERT-base/resolve/main/special_tokens_map.json from cache at /home/hungthinht/.cache/huggingface/transformers/0598867425495ec6baf3617ab3789f3d8b84ebf869f7b43aa4a2930195a74dbe.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d | |
| [INFO|tokenization_utils_base.py:1781] 2022-07-22 12:32:05,294 >> loading file https://huggingface.co/michiyasunaga/BioLinkBERT-base/resolve/main/tokenizer_config.json from cache at /home/hungthinht/.cache/huggingface/transformers/30e2841862fd496cf36bc8647c9633a1dc319fbf6cc88a80438ca3f89e28339b.fab032bd2aab224bad4dcfc35e3bd6122976da1fa23e4feeb97d8fa65491aded | |
| [INFO|modeling_utils.py:2107] 2022-07-22 12:32:06,276 >> loading weights file https://huggingface.co/michiyasunaga/BioLinkBERT-base/resolve/main/pytorch_model.bin from cache at /home/hungthinht/.cache/huggingface/transformers/76a88449a3eb7019bbc0d164cc39a6a231c8bbe3b9678b8d40977424f0ad934d.f8b95ad9e1dea734685fba5a5b6142b539678b7fc2311981cc14ae61b19f709d | |
| [INFO|modeling_utils.py:2483] 2022-07-22 12:32:07,350 >> All model checkpoint weights were used when initializing BertForTokenClassification. | |
| [WARNING|modeling_utils.py:2485] 2022-07-22 12:32:07,350 >> Some weights of BertForTokenClassification were not initialized from the model checkpoint at michiyasunaga/BioLinkBERT-base and are newly initialized: ['classifier.weight', 'classifier.bias'] | |
| You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. | |
| 07/22/2022 12:32:07 - WARNING - datasets.fingerprint - Parameter 'function'=<function main.<locals>.tokenize_and_align_labels at 0x2ac6e9964940> of the transform datasets.arrow_dataset.Dataset._map_single couldn't be hashed properly, a random hash was used instead. Make sure your transforms and parameters are serializable with pickle or dill for the dataset fingerprinting and caching to work. If you reuse this transform, the caching mechanism will consider it to be different from the previous calls and recompute everything. This warning is only showed once. Subsequent hashing failures won't be showed. | |
| 07/22/2022 12:32:07 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/hungthinht/.cache/huggingface/datasets/json/default-2d9cec4b8a27d237/0.0.0/da492aad5680612e4028e7f6ddc04b1dfcec4b64db470ed7cc5f2bb265b9b6b5/cache-1c80317fa3b1799d.arrow | |
| 07/22/2022 12:32:07 - INFO - datasets.fingerprint - Parameter 'function'=<function main.<locals>.tokenize_and_align_labels at 0x2ac6e99b3d30> of the transform datasets.arrow_dataset.Dataset._map_single couldn't be hashed properly, a random hash was used instead. | |
| 07/22/2022 12:32:07 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/hungthinht/.cache/huggingface/datasets/json/default-2d9cec4b8a27d237/0.0.0/da492aad5680612e4028e7f6ddc04b1dfcec4b64db470ed7cc5f2bb265b9b6b5/cache-bdd640fb06671ad1.arrow | |
| 07/22/2022 12:32:07 - INFO - datasets.fingerprint - Parameter 'function'=<function main.<locals>.tokenize_and_align_labels at 0x2ac6e9964940> of the transform datasets.arrow_dataset.Dataset._map_single couldn't be hashed properly, a random hash was used instead. | |
| 07/22/2022 12:32:07 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/hungthinht/.cache/huggingface/datasets/json/default-2d9cec4b8a27d237/0.0.0/da492aad5680612e4028e7f6ddc04b1dfcec4b64db470ed7cc5f2bb265b9b6b5/cache-3eb13b9046685257.arrow | |
| [INFO|trainer.py:533] 2022-07-22 12:32:09,812 >> Using cuda_amp half precision backend | |
| [INFO|trainer.py:661] 2022-07-22 12:32:09,812 >> The following columns in the training set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: id, ner_tags, word_ids, tokens. If id, ner_tags, word_ids, tokens are not expected by `BertForTokenClassification.forward`, you can safely ignore this message. | |
| /home/hungthinht/miniconda3/lib/python3.9/site-packages/transformers/optimization.py:306: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning | |
| warnings.warn( | |
| [INFO|trainer.py:1516] 2022-07-22 12:32:09,838 >> ***** Running training ***** | |
| [INFO|trainer.py:1517] 2022-07-22 12:32:09,838 >> Num examples = 40935 | |
| [INFO|trainer.py:1518] 2022-07-22 12:32:09,838 >> Num Epochs = 1 | |
| [INFO|trainer.py:1519] 2022-07-22 12:32:09,838 >> Instantaneous batch size per device = 32 | |
| [INFO|trainer.py:1520] 2022-07-22 12:32:09,838 >> Total train batch size (w. parallel, distributed & accumulation) = 32 | |
| [INFO|trainer.py:1521] 2022-07-22 12:32:09,838 >> Gradient Accumulation steps = 1 | |
| [INFO|trainer.py:1522] 2022-07-22 12:32:09,838 >> Total optimization steps = 1280 | |
| 0%| | 0/1280 [00:00<?, ?it/s] 0%| | 1/1280 [00:00<13:42, 1.56it/s] 0%| | 3/1280 [00:00<04:50, 4.39it/s] 0%| | 5/1280 [00:00<03:11, 6.65it/s] 1%| | 7/1280 [00:01<02:31, 8.43it/s] 1%| | 9/1280 [00:01<02:06, 10.01it/s] 1%| | 11/1280 [00:01<01:59, 10.62it/s] 1%| | 13/1280 [00:01<01:49, 11.60it/s] 1%| | 15/1280 [00:01<01:42, 12.29it/s] 1%|▏ | 17/1280 [00:01<01:37, 12.91it/s] 1%|▏ | 19/1280 [00:01<01:33, 13.42it/s] 2%|▏ | 21/1280 [00:02<01:34, 13.33it/s] 2%|▏ | 23/1280 [00:02<01:34, 13.28it/s] 2%|▏ | 25/1280 [00:02<01:35, 13.19it/s] 2%|▏ | 27/1280 [00:02<01:32, 13.51it/s] 2%|▏ | 29/1280 [00:02<01:33, 13.35it/s] 2%|▏ | 31/1280 [00:02<01:37, 12.82it/s] 3%|▎ | 33/1280 [00:03<01:36, 12.92it/s] 3%|▎ | 35/1280 [00:03<01:34, 13.13it/s] 3%|▎ | 37/1280 [00:03<01:40, 12.40it/s] 3%|▎ | 39/1280 [00:03<01:35, 13.03it/s] 3%|▎ | 41/1280 [00:03<01:35, 12.98it/s] 3%|▎ | 43/1280 [00:03<01:33, 13.28it/s] 4%|▎ | 45/1280 [00:03<01:33, 13.23it/s] 4%|▎ | 47/1280 [00:04<01:29, 13.78it/s] 4%|▍ | 49/1280 [00:04<01:26, 14.19it/s] 4%|▍ | 51/1280 [00:04<01:31, 13.42it/s] 4%|▍ | 53/1280 [00:04<01:30, 13.51it/s] 4%|▍ | 55/1280 [00:04<01:34, 12.92it/s] 4%|▍ | 57/1280 [00:04<01:35, 12.77it/s] 5%|▍ | 59/1280 [00:05<01:34, 12.95it/s] 5%|▍ | 61/1280 [00:05<01:31, 13.35it/s] 5%|▍ | 63/1280 [00:05<01:30, 13.39it/s] 5%|▌ | 65/1280 [00:05<01:28, 13.77it/s] 5%|▌ | 67/1280 [00:05<01:28, 13.66it/s] 5%|▌ | 69/1280 [00:05<01:28, 13.61it/s] 6%|▌ | 71/1280 [00:05<01:26, 14.00it/s] 6%|▌ | 73/1280 [00:06<01:34, 12.73it/s] 6%|▌ | 75/1280 [00:06<01:32, 12.96it/s] 6%|▌ | 77/1280 [00:06<01:28, 13.52it/s] 6%|▌ | 79/1280 [00:06<01:27, 13.80it/s] 6%|▋ | 81/1280 [00:06<01:26, 13.85it/s] 6%|▋ | 83/1280 [00:06<01:25, 13.96it/s] 7%|▋ | 85/1280 [00:06<01:23, 14.27it/s] 7%|▋ | 87/1280 [00:07<01:23, 14.30it/s] 7%|▋ | 89/1280 [00:07<01:24, 14.14it/s] 7%|▋ | 91/1280 [00:07<01:23, 14.22it/s] 7%|▋ | 93/1280 [00:07<01:22, 14.45it/s] 7%|▋ | 95/1280 [00:07<01:24, 14.05it/s] 8%|▊ | 97/1280 [00:07<01:26, 13.74it/s] 8%|▊ | 99/1280 [00:07<01:28, 13.27it/s] 8%|▊ | 101/1280 [00:08<01:29, 13.11it/s] 8%|▊ | 103/1280 [00:08<01:29, 13.17it/s] 8%|▊ | 105/1280 [00:08<01:28, 13.34it/s] 8%|▊ | 107/1280 [00:08<01:24, 13.82it/s] 9%|▊ | 109/1280 [00:08<01:28, 13.30it/s] 9%|▊ | 111/1280 [00:08<01:25, 13.65it/s] 9%|▉ | 113/1280 [00:08<01:23, 14.05it/s] 9%|▉ | 115/1280 [00:09<01:32, 12.63it/s] 9%|▉ | 117/1280 [00:09<01:27, 13.26it/s] 9%|▉ | 119/1280 [00:09<01:24, 13.80it/s] 9%|▉ | 121/1280 [00:09<01:23, 13.93it/s] 10%|▉ | 123/1280 [00:09<01:25, 13.57it/s] 10%|▉ | 125/1280 [00:09<01:25, 13.44it/s] 10%|▉ | 127/1280 [00:09<01:24, 13.63it/s] 10%|█ | 129/1280 [00:10<01:23, 13.71it/s] 10%|█ | 131/1280 [00:10<01:21, 14.15it/s] 10%|█ | 133/1280 [00:10<01:22, 13.91it/s] 11%|█ | 135/1280 [00:10<01:22, 13.90it/s] 11%|█ | 137/1280 [00:10<01:23, 13.75it/s] 11%|█ | 139/1280 [00:10<01:21, 13.96it/s] 11%|█ | 141/1280 [00:10<01:19, 14.30it/s] 11%|█ | 143/1280 [00:11<01:18, 14.40it/s] 11%|█▏ | 145/1280 [00:11<01:20, 14.08it/s] 11%|█▏ | 147/1280 [00:11<01:20, 14.06it/s] 12%|█▏ | 149/1280 [00:11<01:18, 14.34it/s] 12%|█▏ | 151/1280 [00:11<01:18, 14.34it/s] 12%|█▏ | 153/1280 [00:11<01:22, 13.70it/s] 12%|█▏ | 155/1280 [00:11<01:22, 13.71it/s] 12%|█▏ | 157/1280 [00:12<01:20, 14.03it/s] 12%|█▏ | 159/1280 [00:12<01:20, 13.98it/s] 13%|█▎ | 161/1280 [00:12<01:23, 13.40it/s] 13%|█▎ | 163/1280 [00:12<01:24, 13.14it/s] 13%|█▎ | 165/1280 [00:12<01:29, 12.51it/s] 13%|█▎ | 167/1280 [00:12<01:24, 13.16it/s] 13%|█▎ | 169/1280 [00:13<01:24, 13.13it/s] 13%|█▎ | 171/1280 [00:13<01:20, 13.70it/s] 14%|█▎ | 173/1280 [00:13<01:17, 14.25it/s] 14%|█▎ | 175/1280 [00:13<01:17, 14.27it/s] 14%|█▍ | 177/1280 [00:13<01:23, 13.16it/s] 14%|█▍ | 179/1280 [00:13<01:20, 13.74it/s] 14%|█▍ | 181/1280 [00:13<01:22, 13.29it/s] 14%|█▍ | 183/1280 [00:14<01:19, 13.74it/s] 14%|█▍ | 185/1280 [00:14<01:17, 14.13it/s] 15%|█▍ | 187/1280 [00:14<01:14, 14.60it/s] 15%|█▍ | 189/1280 [00:14<01:20, 13.53it/s] 15%|█▍ | 191/1280 [00:14<01:20, 13.60it/s] 15%|█▌ | 193/1280 [00:14<01:18, 13.93it/s] 15%|█▌ | 195/1280 [00:14<01:17, 14.06it/s] 15%|█▌ | 197/1280 [00:15<01:16, 14.21it/s] 16%|█▌ | 199/1280 [00:15<01:20, 13.44it/s] 16%|█▌ | 201/1280 [00:15<01:18, 13.80it/s] 16%|█▌ | 203/1280 [00:15<01:16, 14.17it/s] 16%|█▌ | 205/1280 [00:15<01:16, 14.09it/s] 16%|█▌ | 207/1280 [00:15<01:15, 14.28it/s] 16%|█▋ | 209/1280 [00:15<01:17, 13.82it/s] 16%|█▋ | 211/1280 [00:16<01:18, 13.62it/s] 17%|█▋ | 213/1280 [00:16<01:26, 12.31it/s] 17%|█▋ | 215/1280 [00:16<01:26, 12.25it/s] 17%|█▋ | 217/1280 [00:16<01:23, 12.66it/s] 17%|█▋ | 219/1280 [00:16<01:21, 13.10it/s] 17%|█▋ | 221/1280 [00:16<01:18, 13.57it/s] 17%|█▋ | 223/1280 [00:16<01:15, 13.92it/s] 18%|█▊ | 225/1280 [00:17<01:16, 13.76it/s] 18%|█▊ | 227/1280 [00:17<01:17, 13.56it/s] 18%|█▊ | 229/1280 [00:17<01:16, 13.79it/s] 18%|█▊ | 231/1280 [00:17<01:14, 14.05it/s] 18%|█▊ | 233/1280 [00:17<01:12, 14.36it/s] 18%|█▊ | 235/1280 [00:17<01:11, 14.62it/s] 19%|█▊ | 237/1280 [00:17<01:10, 14.76it/s] 19%|█▊ | 239/1280 [00:18<01:11, 14.54it/s] 19%|█▉ | 241/1280 [00:18<01:17, 13.43it/s] 19%|█▉ | 243/1280 [00:18<01:14, 13.94it/s] 19%|█▉ | 245/1280 [00:18<01:12, 14.21it/s] 19%|█▉ | 247/1280 [00:18<01:11, 14.43it/s] 19%|█▉ | 249/1280 [00:18<01:17, 13.35it/s] 20%|█▉ | 251/1280 [00:18<01:15, 13.55it/s] 20%|█▉ | 253/1280 [00:19<01:13, 13.88it/s] 20%|█▉ | 255/1280 [00:19<01:15, 13.57it/s] 20%|██ | 257/1280 [00:19<01:12, 14.04it/s] 20%|██ | 259/1280 [00:19<01:13, 13.85it/s] 20%|██ | 261/1280 [00:19<01:19, 12.82it/s] 21%|██ | 263/1280 [00:19<01:20, 12.68it/s] 21%|██ | 265/1280 [00:20<01:23, 12.09it/s] 21%|██ | 267/1280 [00:20<01:19, 12.68it/s] 21%|██ | 269/1280 [00:20<01:17, 13.06it/s] 21%|██ | 271/1280 [00:20<01:16, 13.27it/s] 21%|██▏ | 273/1280 [00:20<01:14, 13.56it/s] 21%|██▏ | 275/1280 [00:20<01:16, 13.16it/s] 22%|██▏ | 277/1280 [00:20<01:16, 13.14it/s] 22%|██▏ | 279/1280 [00:21<01:16, 13.12it/s] 22%|██▏ | 281/1280 [00:21<01:22, 12.05it/s] 22%|██▏ | 283/1280 [00:21<01:20, 12.31it/s] 22%|██▏ | 285/1280 [00:21<01:19, 12.51it/s] 22%|██▏ | 287/1280 [00:21<01:16, 13.06it/s] 23%|██▎ | 289/1280 [00:21<01:14, 13.34it/s] 23%|██▎ | 291/1280 [00:22<01:12, 13.63it/s] 23%|██▎ | 293/1280 [00:22<01:11, 13.76it/s] 23%|██▎ | 295/1280 [00:22<01:11, 13.85it/s] 23%|██▎ | 297/1280 [00:22<01:18, 12.51it/s] 23%|██▎ | 299/1280 [00:22<01:26, 11.31it/s] 24%|██▎ | 301/1280 [00:22<01:27, 11.14it/s] 24%|██▎ | 303/1280 [00:23<01:26, 11.35it/s] 24%|██▍ | 305/1280 [00:23<01:19, 12.34it/s] 24%|██▍ | 307/1280 [00:23<01:19, 12.30it/s] 24%|██▍ | 309/1280 [00:23<01:15, 12.94it/s] 24%|██▍ | 311/1280 [00:23<01:10, 13.69it/s] 24%|██▍ | 313/1280 [00:23<01:12, 13.35it/s] 25%|██▍ | 315/1280 [00:23<01:12, 13.32it/s] 25%|██▍ | 317/1280 [00:24<01:14, 13.01it/s] 25%|██▍ | 319/1280 [00:24<01:10, 13.55it/s] 25%|██▌ | 321/1280 [00:24<01:08, 14.03it/s] 25%|██▌ | 323/1280 [00:24<01:06, 14.39it/s] 25%|██▌ | 325/1280 [00:24<01:07, 14.20it/s] 26%|██▌ | 327/1280 [00:24<01:06, 14.44it/s] 26%|██▌ | 329/1280 [00:24<01:09, 13.76it/s] 26%|██▌ | 331/1280 [00:25<01:11, 13.22it/s] 26%|██▌ | 333/1280 [00:25<01:13, 12.93it/s] 26%|██▌ | 335/1280 [00:25<01:11, 13.30it/s] 26%|██▋ | 337/1280 [00:25<01:09, 13.62it/s] 26%|██▋ | 339/1280 [00:25<01:07, 13.98it/s] 27%|██▋ | 341/1280 [00:25<01:05, 14.29it/s] 27%|██▋ | 343/1280 [00:25<01:05, 14.20it/s] 27%|██▋ | 345/1280 [00:26<01:05, 14.26it/s] 27%|██▋ | 347/1280 [00:26<01:04, 14.55it/s] 27%|██▋ | 349/1280 [00:26<01:02, 14.80it/s] 27%|██▋ | 351/1280 [00:26<01:03, 14.73it/s] 28%|██▊ | 353/1280 [00:26<01:09, 13.35it/s] 28%|██▊ | 355/1280 [00:26<01:08, 13.55it/s] 28%|██▊ | 357/1280 [00:27<01:09, 13.37it/s] 28%|██▊ | 359/1280 [00:27<01:07, 13.65it/s] 28%|██▊ | 361/1280 [00:27<01:05, 14.12it/s] 28%|██▊ | 363/1280 [00:27<01:08, 13.32it/s] 29%|██▊ | 365/1280 [00:27<01:16, 12.02it/s] 29%|██▊ | 367/1280 [00:27<01:11, 12.68it/s] 29%|██▉ | 369/1280 [00:27<01:11, 12.78it/s] 29%|██▉ | 371/1280 [00:28<01:17, 11.75it/s] 29%|██▉ | 373/1280 [00:28<01:16, 11.91it/s] 29%|██▉ | 375/1280 [00:28<01:13, 12.33it/s] 29%|██▉ | 377/1280 [00:28<01:10, 12.79it/s] 30%|██▉ | 379/1280 [00:28<01:06, 13.54it/s] 30%|██▉ | 381/1280 [00:28<01:04, 13.93it/s] 30%|██▉ | 383/1280 [00:29<01:07, 13.26it/s] 30%|███ | 385/1280 [00:29<01:05, 13.67it/s] 30%|███ | 387/1280 [00:29<01:04, 13.75it/s] 30%|███ | 389/1280 [00:29<01:03, 14.12it/s] 31%|███ | 391/1280 [00:29<01:07, 13.17it/s] 31%|███ | 393/1280 [00:29<01:06, 13.34it/s] 31%|███ | 395/1280 [00:29<01:04, 13.81it/s] 31%|███ | 397/1280 [00:30<01:04, 13.63it/s] 31%|███ | 399/1280 [00:30<01:06, 13.24it/s] 31%|███▏ | 401/1280 [00:30<01:08, 12.91it/s] 31%|███▏ | 403/1280 [00:30<01:04, 13.59it/s] 32%|███▏ | 405/1280 [00:30<01:08, 12.82it/s] 32%|███▏ | 407/1280 [00:30<01:06, 13.16it/s] 32%|███▏ | 409/1280 [00:30<01:04, 13.42it/s] 32%|███▏ | 411/1280 [00:31<01:04, 13.50it/s] 32%|███▏ | 413/1280 [00:31<01:02, 13.85it/s] 32%|███▏ | 415/1280 [00:31<01:06, 13.03it/s] 33%|███▎ | 417/1280 [00:31<01:03, 13.49it/s] 33%|███▎ | 419/1280 [00:31<01:04, 13.29it/s] 33%|███▎ | 421/1280 [00:31<01:02, 13.84it/s] 33%|███▎ | 423/1280 [00:31<01:02, 13.62it/s] 33%|███▎ | 425/1280 [00:32<01:04, 13.20it/s] 33%|███▎ | 427/1280 [00:32<01:07, 12.59it/s] 34%|███▎ | 429/1280 [00:32<01:06, 12.88it/s] 34%|███▎ | 431/1280 [00:32<01:03, 13.38it/s] 34%|███▍ | 433/1280 [00:32<01:01, 13.77it/s] 34%|███▍ | 435/1280 [00:32<00:59, 14.27it/s] 34%|███▍ | 437/1280 [00:33<00:59, 14.20it/s] 34%|███▍ | 439/1280 [00:33<00:58, 14.27it/s] 34%|███▍ | 441/1280 [00:33<01:01, 13.53it/s] 35%|███▍ | 443/1280 [00:33<01:05, 12.86it/s] 35%|███▍ | 445/1280 [00:33<01:05, 12.72it/s] 35%|███▍ | 447/1280 [00:33<01:02, 13.22it/s] 35%|███▌ | 449/1280 [00:34<01:15, 11.03it/s] 35%|███▌ | 451/1280 [00:34<01:14, 11.17it/s] 35%|███▌ | 453/1280 [00:34<01:09, 11.91it/s] 36%|███▌ | 455/1280 [00:34<01:04, 12.80it/s] 36%|███▌ | 457/1280 [00:34<01:01, 13.31it/s] 36%|███▌ | 459/1280 [00:34<00:58, 13.92it/s] 36%|███▌ | 461/1280 [00:34<01:00, 13.61it/s] 36%|███▌ | 463/1280 [00:35<00:58, 14.07it/s] 36%|███▋ | 465/1280 [00:35<00:59, 13.59it/s] 36%|███▋ | 467/1280 [00:35<00:58, 13.91it/s] 37%|███▋ | 469/1280 [00:35<00:57, 14.06it/s] 37%|███▋ | 471/1280 [00:35<01:09, 11.62it/s] 37%|███▋ | 473/1280 [00:35<01:05, 12.30it/s] 37%|███▋ | 475/1280 [00:35<01:02, 12.96it/s] 37%|███▋ | 477/1280 [00:36<01:03, 12.58it/s] 37%|███▋ | 479/1280 [00:36<01:04, 12.32it/s] 38%|███▊ | 481/1280 [00:36<01:01, 12.94it/s] 38%|███▊ | 483/1280 [00:36<01:01, 12.91it/s] 38%|███▊ | 485/1280 [00:36<00:59, 13.40it/s] 38%|███▊ | 487/1280 [00:36<00:57, 13.83it/s] 38%|███▊ | 489/1280 [00:37<00:55, 14.33it/s] 38%|███▊ | 491/1280 [00:37<00:56, 13.88it/s] 39%|███▊ | 493/1280 [00:37<00:57, 13.67it/s] 39%|███▊ | 495/1280 [00:37<00:58, 13.33it/s] 39%|███▉ | 497/1280 [00:37<01:00, 13.00it/s] 39%|███▉ | 499/1280 [00:37<01:02, 12.58it/s] {'loss': 0.5034, 'learning_rate': 3.0546875e-05, 'epoch': 0.39} | |
| 39%|███▉ | 500/1280 [00:37<01:02, 12.58it/s] 39%|███▉ | 501/1280 [00:37<00:59, 13.01it/s] 39%|███▉ | 503/1280 [00:38<00:59, 13.00it/s] 39%|███▉ | 505/1280 [00:38<00:57, 13.56it/s] 40%|███▉ | 507/1280 [00:38<00:56, 13.65it/s] 40%|███▉ | 509/1280 [00:38<00:55, 14.00it/s] 40%|███▉ | 511/1280 [00:38<00:54, 14.15it/s] 40%|████ | 513/1280 [00:38<00:52, 14.51it/s] 40%|████ | 515/1280 [00:38<00:51, 14.82it/s] 40%|████ | 517/1280 [00:39<00:51, 14.91it/s] 41%|████ | 519/1280 [00:39<00:51, 14.73it/s] 41%|████ | 521/1280 [00:39<00:50, 14.90it/s] 41%|████ | 523/1280 [00:39<00:51, 14.74it/s] 41%|████ | 525/1280 [00:39<00:51, 14.75it/s] 41%|████ | 527/1280 [00:39<00:51, 14.61it/s] 41%|████▏ | 529/1280 [00:39<00:53, 14.01it/s] 41%|████▏ | 531/1280 [00:40<00:53, 13.98it/s] 42%|████▏ | 533/1280 [00:40<00:55, 13.37it/s] 42%|████▏ | 535/1280 [00:40<00:53, 13.96it/s] 42%|████▏ | 537/1280 [00:40<00:51, 14.34it/s] 42%|████▏ | 539/1280 [00:40<00:50, 14.62it/s] 42%|████▏ | 541/1280 [00:40<00:51, 14.45it/s] 42%|████▏ | 543/1280 [00:40<00:51, 14.39it/s] 43%|████▎ | 545/1280 [00:41<00:51, 14.38it/s] 43%|████▎ | 547/1280 [00:41<00:53, 13.70it/s] 43%|████▎ | 549/1280 [00:41<00:52, 13.81it/s] 43%|████▎ | 551/1280 [00:41<00:51, 14.17it/s] 43%|████▎ | 553/1280 [00:41<00:49, 14.55it/s] 43%|████▎ | 555/1280 [00:41<00:50, 14.48it/s] 44%|████▎ | 557/1280 [00:41<00:49, 14.50it/s] 44%|████▎ | 559/1280 [00:42<00:52, 13.67it/s] 44%|████▍ | 561/1280 [00:42<00:54, 13.20it/s] 44%|████▍ | 563/1280 [00:42<00:54, 13.13it/s] 44%|████▍ | 565/1280 [00:42<00:52, 13.62it/s] 44%|████▍ | 567/1280 [00:42<00:55, 12.95it/s] 44%|████▍ | 569/1280 [00:42<00:53, 13.33it/s] 45%|████▍ | 571/1280 [00:42<00:51, 13.89it/s] 45%|████▍ | 573/1280 [00:43<00:52, 13.36it/s] 45%|████▍ | 575/1280 [00:43<00:54, 12.91it/s] 45%|████▌ | 577/1280 [00:43<00:51, 13.55it/s] 45%|████▌ | 579/1280 [00:43<00:49, 14.04it/s] 45%|████▌ | 581/1280 [00:43<00:51, 13.70it/s] 46%|████▌ | 583/1280 [00:43<00:52, 13.26it/s] 46%|████▌ | 585/1280 [00:43<00:53, 13.11it/s] 46%|████▌ | 587/1280 [00:44<00:51, 13.55it/s] 46%|████▌ | 589/1280 [00:44<00:50, 13.74it/s] 46%|████▌ | 591/1280 [00:44<00:49, 13.96it/s] 46%|████▋ | 593/1280 [00:44<00:48, 14.28it/s] 46%|████▋ | 595/1280 [00:44<00:49, 13.90it/s] 47%|████▋ | 597/1280 [00:44<00:47, 14.34it/s] 47%|████▋ | 599/1280 [00:44<00:47, 14.34it/s] 47%|████▋ | 601/1280 [00:45<00:46, 14.55it/s] 47%|████▋ | 603/1280 [00:45<00:46, 14.55it/s] 47%|████▋ | 605/1280 [00:45<00:45, 14.70it/s] 47%|████▋ | 607/1280 [00:45<00:48, 13.97it/s] 48%|████▊ | 609/1280 [00:45<00:47, 14.07it/s] 48%|████▊ | 611/1280 [00:45<00:50, 13.35it/s] 48%|████▊ | 613/1280 [00:45<00:50, 13.28it/s] 48%|████▊ | 615/1280 [00:46<00:48, 13.76it/s] 48%|████▊ | 617/1280 [00:46<00:49, 13.31it/s] 48%|████▊ | 619/1280 [00:46<00:52, 12.66it/s] 49%|████▊ | 621/1280 [00:46<00:53, 12.22it/s] 49%|████▊ | 623/1280 [00:46<00:54, 12.09it/s] 49%|████▉ | 625/1280 [00:46<00:51, 12.77it/s] 49%|████▉ | 627/1280 [00:47<00:48, 13.36it/s] 49%|████▉ | 629/1280 [00:47<00:47, 13.73it/s] 49%|████▉ | 631/1280 [00:47<00:47, 13.62it/s] 49%|████▉ | 633/1280 [00:47<00:45, 14.23it/s] 50%|████▉ | 635/1280 [00:47<00:47, 13.64it/s] 50%|████▉ | 637/1280 [00:47<00:46, 13.84it/s] 50%|████▉ | 639/1280 [00:47<00:47, 13.37it/s] 50%|█████ | 641/1280 [00:48<00:47, 13.57it/s] 50%|█████ | 643/1280 [00:48<00:45, 13.94it/s] 50%|█████ | 645/1280 [00:48<00:45, 13.93it/s] 51%|█████ | 647/1280 [00:48<00:45, 14.05it/s] 51%|█████ | 649/1280 [00:48<00:45, 13.75it/s] 51%|█████ | 651/1280 [00:48<00:45, 13.78it/s] 51%|█████ | 653/1280 [00:48<00:45, 13.75it/s] 51%|█████ | 655/1280 [00:49<00:48, 12.96it/s] 51%|█████▏ | 657/1280 [00:49<00:46, 13.39it/s] 51%|█████▏ | 659/1280 [00:49<00:59, 10.40it/s] 52%|█████▏ | 661/1280 [00:49<00:54, 11.31it/s] 52%|█████▏ | 663/1280 [00:49<00:50, 12.15it/s] 52%|█████▏ | 665/1280 [00:49<00:48, 12.66it/s] 52%|█████▏ | 667/1280 [00:50<00:47, 12.87it/s] 52%|█████▏ | 669/1280 [00:50<00:45, 13.51it/s] 52%|█████▏ | 671/1280 [00:50<00:45, 13.30it/s] 53%|█████▎ | 673/1280 [00:50<00:44, 13.66it/s] 53%|█████▎ | 675/1280 [00:50<00:42, 14.17it/s] 53%|█████▎ | 677/1280 [00:50<00:41, 14.55it/s] 53%|█████▎ | 679/1280 [00:50<00:42, 13.98it/s] 53%|█████▎ | 681/1280 [00:51<00:44, 13.57it/s] 53%|█████▎ | 683/1280 [00:51<00:45, 13.16it/s] 54%|█████▎ | 685/1280 [00:51<00:43, 13.80it/s] 54%|█████▎ | 687/1280 [00:51<00:42, 14.09it/s] 54%|█████▍ | 689/1280 [00:51<00:41, 14.30it/s] 54%|█████▍ | 691/1280 [00:51<00:43, 13.66it/s] 54%|█████▍ | 693/1280 [00:51<00:41, 14.12it/s] 54%|█████▍ | 695/1280 [00:52<00:40, 14.39it/s] 54%|█████▍ | 697/1280 [00:52<00:41, 14.00it/s] 55%|█████▍ | 699/1280 [00:52<00:41, 14.01it/s] 55%|█████▍ | 701/1280 [00:52<00:42, 13.76it/s] 55%|█████▍ | 703/1280 [00:52<00:41, 13.84it/s] 55%|█████▌ | 705/1280 [00:52<00:44, 12.89it/s] 55%|█████▌ | 707/1280 [00:53<00:49, 11.66it/s] 55%|█████▌ | 709/1280 [00:53<00:49, 11.53it/s] 56%|█████▌ | 711/1280 [00:53<00:45, 12.41it/s] 56%|█████▌ | 713/1280 [00:53<00:43, 13.18it/s] 56%|█████▌ | 715/1280 [00:53<00:43, 13.07it/s] 56%|█████▌ | 717/1280 [00:53<00:41, 13.52it/s] 56%|█████▌ | 719/1280 [00:53<00:39, 14.09it/s] 56%|█████▋ | 721/1280 [00:54<00:39, 14.08it/s] 56%|█████▋ | 723/1280 [00:54<00:38, 14.30it/s] 57%|█████▋ | 725/1280 [00:54<00:40, 13.81it/s] 57%|█████▋ | 727/1280 [00:54<00:43, 12.79it/s] 57%|█████▋ | 729/1280 [00:54<00:40, 13.52it/s] 57%|█████▋ | 731/1280 [00:54<00:40, 13.48it/s] 57%|█████▋ | 733/1280 [00:54<00:39, 13.75it/s] 57%|█████▋ | 735/1280 [00:55<00:38, 13.98it/s] 58%|█████▊ | 737/1280 [00:55<00:38, 14.14it/s] 58%|█████▊ | 739/1280 [00:55<00:38, 14.14it/s] 58%|█████▊ | 741/1280 [00:55<00:37, 14.21it/s] 58%|█████▊ | 743/1280 [00:55<00:37, 14.26it/s] 58%|█████▊ | 745/1280 [00:55<00:37, 14.41it/s] 58%|█████▊ | 747/1280 [00:55<00:39, 13.50it/s] 59%|█████▊ | 749/1280 [00:56<00:38, 13.89it/s] 59%|█████▊ | 751/1280 [00:56<00:38, 13.58it/s] 59%|█████▉ | 753/1280 [00:56<00:37, 14.00it/s] 59%|█████▉ | 755/1280 [00:56<00:38, 13.68it/s] 59%|█████▉ | 757/1280 [00:56<00:39, 13.40it/s] 59%|█████▉ | 759/1280 [00:56<00:39, 13.28it/s] 59%|█████▉ | 761/1280 [00:56<00:37, 13.68it/s] 60%|█████▉ | 763/1280 [00:57<00:41, 12.40it/s] 60%|█████▉ | 765/1280 [00:57<00:39, 13.07it/s] 60%|█████▉ | 767/1280 [00:57<00:38, 13.46it/s] 60%|██████ | 769/1280 [00:57<00:37, 13.62it/s] 60%|██████ | 771/1280 [00:57<00:38, 13.30it/s] 60%|██████ | 773/1280 [00:57<00:41, 12.28it/s] 61%|██████ | 775/1280 [00:58<00:38, 13.00it/s] 61%|██████ | 777/1280 [00:58<00:41, 12.15it/s] 61%|██████ | 779/1280 [00:58<00:38, 12.88it/s] 61%|██████ | 781/1280 [00:58<00:39, 12.68it/s] 61%|██████ | 783/1280 [00:58<00:38, 12.98it/s] 61%|██████▏ | 785/1280 [00:58<00:36, 13.55it/s] 61%|██████▏ | 787/1280 [00:58<00:35, 13.89it/s] 62%|██████▏ | 789/1280 [00:59<00:37, 13.19it/s] 62%|██████▏ | 791/1280 [00:59<00:38, 12.55it/s] 62%|██████▏ | 793/1280 [00:59<00:37, 12.95it/s] 62%|██████▏ | 795/1280 [00:59<00:36, 13.22it/s] 62%|██████▏ | 797/1280 [00:59<00:35, 13.63it/s] 62%|██████▏ | 799/1280 [00:59<00:35, 13.50it/s] 63%|██████▎ | 801/1280 [01:00<00:34, 13.72it/s] 63%|██████▎ | 803/1280 [01:00<00:35, 13.44it/s] 63%|██████▎ | 805/1280 [01:00<00:34, 13.85it/s] 63%|██████▎ | 807/1280 [01:00<00:35, 13.50it/s] 63%|██████▎ | 809/1280 [01:00<00:34, 13.67it/s] 63%|██████▎ | 811/1280 [01:00<00:33, 14.07it/s] 64%|██████▎ | 813/1280 [01:00<00:33, 13.86it/s] 64%|██████▎ | 815/1280 [01:01<00:33, 13.70it/s] 64%|██████▍ | 817/1280 [01:01<00:32, 14.14it/s] 64%|██████▍ | 819/1280 [01:01<00:33, 13.64it/s] 64%|██████▍ | 821/1280 [01:01<00:32, 13.91it/s] 64%|██████▍ | 823/1280 [01:01<00:32, 14.22it/s] 64%|██████▍ | 825/1280 [01:01<00:31, 14.44it/s] 65%|██████▍ | 827/1280 [01:01<00:31, 14.49it/s] 65%|██████▍ | 829/1280 [01:02<00:31, 14.34it/s] 65%|██████▍ | 831/1280 [01:02<00:32, 13.83it/s] 65%|██████▌ | 833/1280 [01:02<00:32, 13.84it/s] 65%|██████▌ | 835/1280 [01:02<00:38, 11.60it/s] 65%|██████▌ | 837/1280 [01:02<00:40, 10.99it/s] 66%|██████▌ | 839/1280 [01:02<00:40, 10.84it/s] 66%|██████▌ | 841/1280 [01:03<00:39, 11.24it/s] 66%|██████▌ | 843/1280 [01:03<00:37, 11.60it/s] 66%|██████▌ | 845/1280 [01:03<00:36, 11.99it/s] 66%|██████▌ | 847/1280 [01:03<00:34, 12.54it/s] 66%|██████▋ | 849/1280 [01:03<00:33, 13.00it/s] 66%|██████▋ | 851/1280 [01:03<00:32, 13.07it/s] 67%|██████▋ | 853/1280 [01:04<00:34, 12.26it/s] 67%|██████▋ | 855/1280 [01:04<00:32, 13.04it/s] 67%|██████▋ | 857/1280 [01:04<00:31, 13.63it/s] 67%|██████▋ | 859/1280 [01:04<00:31, 13.38it/s] 67%|██████▋ | 861/1280 [01:04<00:30, 13.87it/s] 67%|██████▋ | 863/1280 [01:04<00:32, 12.77it/s] 68%|██████▊ | 865/1280 [01:04<00:30, 13.57it/s] 68%|██████▊ | 867/1280 [01:05<00:30, 13.38it/s] 68%|██████▊ | 869/1280 [01:05<00:30, 13.29it/s] 68%|██████▊ | 871/1280 [01:05<00:30, 13.24it/s] 68%|██████▊ | 873/1280 [01:05<00:31, 13.09it/s] 68%|██████▊ | 875/1280 [01:05<00:30, 13.34it/s] 69%|██████▊ | 877/1280 [01:05<00:29, 13.64it/s] 69%|██████▊ | 879/1280 [01:05<00:28, 13.98it/s] 69%|██████▉ | 881/1280 [01:06<00:28, 13.99it/s] 69%|██████▉ | 883/1280 [01:06<00:29, 13.47it/s] 69%|██████▉ | 885/1280 [01:06<00:28, 13.91it/s] 69%|██████▉ | 887/1280 [01:06<00:28, 13.58it/s] 69%|██████▉ | 889/1280 [01:06<00:29, 13.44it/s] 70%|██████▉ | 891/1280 [01:06<00:30, 12.95it/s] 70%|██████▉ | 893/1280 [01:07<00:31, 12.43it/s] 70%|██████▉ | 895/1280 [01:07<00:31, 12.41it/s] 70%|███████ | 897/1280 [01:07<00:30, 12.37it/s] 70%|███████ | 899/1280 [01:07<00:29, 12.87it/s] 70%|███████ | 901/1280 [01:07<00:29, 12.96it/s] 71%|███████ | 903/1280 [01:07<00:33, 11.24it/s] 71%|███████ | 905/1280 [01:08<00:32, 11.66it/s] 71%|███████ | 907/1280 [01:08<00:30, 12.14it/s] 71%|███████ | 909/1280 [01:08<00:30, 12.32it/s] 71%|███████ | 911/1280 [01:08<00:28, 12.89it/s] 71%|███████▏ | 913/1280 [01:08<00:30, 12.01it/s] 71%|███████▏ | 915/1280 [01:08<00:29, 12.55it/s] 72%|███████▏ | 917/1280 [01:09<00:30, 11.73it/s] 72%|███████▏ | 919/1280 [01:09<00:28, 12.60it/s] 72%|███████▏ | 921/1280 [01:09<00:28, 12.52it/s] 72%|███████▏ | 923/1280 [01:09<00:27, 12.94it/s] 72%|███████▏ | 925/1280 [01:09<00:27, 12.99it/s] 72%|███████▏ | 927/1280 [01:09<00:26, 13.19it/s] 73%|███████▎ | 929/1280 [01:09<00:26, 13.39it/s] 73%|███████▎ | 931/1280 [01:10<00:26, 13.14it/s] 73%|███████▎ | 933/1280 [01:10<00:25, 13.45it/s] 73%|███████▎ | 935/1280 [01:10<00:24, 13.97it/s] 73%|███████▎ | 937/1280 [01:10<00:24, 13.80it/s] 73%|███████▎ | 939/1280 [01:10<00:25, 13.60it/s] 74%|███████▎ | 941/1280 [01:10<00:25, 13.11it/s] 74%|███████▎ | 943/1280 [01:10<00:25, 13.29it/s] 74%|███████▍ | 945/1280 [01:11<00:24, 13.57it/s] 74%|███████▍ | 947/1280 [01:11<00:23, 14.10it/s] 74%|███████▍ | 949/1280 [01:11<00:23, 13.90it/s] 74%|███████▍ | 951/1280 [01:11<00:22, 14.36it/s] 74%|███████▍ | 953/1280 [01:11<00:23, 14.07it/s] 75%|███████▍ | 955/1280 [01:11<00:23, 14.08it/s] 75%|███████▍ | 957/1280 [01:11<00:22, 14.17it/s] 75%|███████▍ | 959/1280 [01:12<00:23, 13.57it/s] 75%|███████▌ | 961/1280 [01:12<00:23, 13.72it/s] 75%|███████▌ | 963/1280 [01:12<00:22, 13.81it/s] 75%|███████▌ | 965/1280 [01:12<00:22, 14.17it/s] 76%|███████▌ | 967/1280 [01:12<00:22, 13.93it/s] 76%|███████▌ | 969/1280 [01:12<00:23, 13.51it/s] 76%|███████▌ | 971/1280 [01:12<00:22, 13.93it/s] 76%|███████▌ | 973/1280 [01:13<00:24, 12.42it/s] 76%|███████▌ | 975/1280 [01:13<00:23, 13.06it/s] 76%|███████▋ | 977/1280 [01:13<00:23, 13.06it/s] 76%|███████▋ | 979/1280 [01:13<00:23, 12.62it/s] 77%|███████▋ | 981/1280 [01:13<00:22, 13.14it/s] 77%|███████▋ | 983/1280 [01:13<00:22, 13.48it/s] 77%|███████▋ | 985/1280 [01:14<00:21, 13.93it/s] 77%|███████▋ | 987/1280 [01:14<00:21, 13.69it/s] 77%|███████▋ | 989/1280 [01:14<00:20, 14.13it/s] 77%|███████▋ | 991/1280 [01:14<00:20, 13.91it/s] 78%|███████▊ | 993/1280 [01:14<00:20, 13.70it/s] 78%|███████▊ | 995/1280 [01:14<00:20, 13.99it/s] 78%|███████▊ | 997/1280 [01:14<00:20, 14.07it/s] 78%|███████▊ | 999/1280 [01:15<00:19, 14.42it/s] {'loss': 0.4383, 'learning_rate': 1.1015625e-05, 'epoch': 0.78} | |
| 78%|███████▊ | 1000/1280 [01:15<00:19, 14.42it/s] 78%|███████▊ | 1001/1280 [01:15<00:19, 14.55it/s] 78%|███████▊ | 1003/1280 [01:15<00:19, 14.46it/s] 79%|███████▊ | 1005/1280 [01:15<00:18, 14.60it/s] 79%|███████▊ | 1007/1280 [01:15<00:19, 14.23it/s] 79%|███████▉ | 1009/1280 [01:15<00:19, 13.56it/s] 79%|███████▉ | 1011/1280 [01:15<00:22, 11.91it/s] 79%|███████▉ | 1013/1280 [01:16<00:21, 12.57it/s] 79%|███████▉ | 1015/1280 [01:16<00:19, 13.30it/s] 79%|███████▉ | 1017/1280 [01:16<00:20, 13.14it/s] 80%|███████▉ | 1019/1280 [01:16<00:20, 13.03it/s] 80%|███████▉ | 1021/1280 [01:16<00:21, 11.95it/s] 80%|███████▉ | 1023/1280 [01:16<00:20, 12.74it/s] 80%|████████ | 1025/1280 [01:16<00:18, 13.53it/s] 80%|████████ | 1027/1280 [01:17<00:17, 14.14it/s] 80%|████████ | 1029/1280 [01:17<00:19, 12.59it/s] 81%|████████ | 1031/1280 [01:17<00:18, 13.11it/s] 81%|████████ | 1033/1280 [01:17<00:18, 13.03it/s] 81%|████████ | 1035/1280 [01:17<00:18, 13.24it/s] 81%|████████ | 1037/1280 [01:17<00:17, 13.70it/s] 81%|████████ | 1039/1280 [01:18<00:17, 14.14it/s] 81%|████████▏ | 1041/1280 [01:18<00:17, 13.52it/s] 81%|████████▏ | 1043/1280 [01:18<00:17, 13.48it/s] 82%|████████▏ | 1045/1280 [01:18<00:17, 13.28it/s] 82%|████████▏ | 1047/1280 [01:18<00:18, 12.72it/s] 82%|████████▏ | 1049/1280 [01:18<00:19, 12.13it/s] 82%|████████▏ | 1051/1280 [01:18<00:18, 12.49it/s] 82%|████████▏ | 1053/1280 [01:19<00:17, 13.07it/s] 82%|████████▏ | 1055/1280 [01:19<00:17, 12.86it/s] 83%|████████▎ | 1057/1280 [01:19<00:16, 13.29it/s] 83%|████████▎ | 1059/1280 [01:19<00:16, 13.08it/s] 83%|████████▎ | 1061/1280 [01:19<00:17, 12.77it/s] 83%|████████▎ | 1063/1280 [01:19<00:16, 13.14it/s] 83%|████████▎ | 1065/1280 [01:20<00:15, 13.57it/s] 83%|████████▎ | 1067/1280 [01:20<00:16, 13.20it/s] 84%|████████▎ | 1069/1280 [01:20<00:15, 13.51it/s] 84%|████████▎ | 1071/1280 [01:20<00:15, 13.27it/s] 84%|████████▍ | 1073/1280 [01:20<00:15, 13.63it/s] 84%|████████▍ | 1075/1280 [01:20<00:15, 13.33it/s] 84%|████████▍ | 1077/1280 [01:20<00:14, 13.82it/s] 84%|████████▍ | 1079/1280 [01:21<00:14, 13.95it/s] 84%|████████▍ | 1081/1280 [01:21<00:14, 13.72it/s] 85%|████████▍ | 1083/1280 [01:21<00:14, 13.93it/s] 85%|████████▍ | 1085/1280 [01:21<00:14, 13.34it/s] 85%|████████▍ | 1087/1280 [01:21<00:13, 13.83it/s] 85%|████████▌ | 1089/1280 [01:21<00:13, 14.19it/s] 85%|████████▌ | 1091/1280 [01:21<00:13, 14.26it/s] 85%|████████▌ | 1093/1280 [01:22<00:13, 13.90it/s] 86%|████████▌ | 1095/1280 [01:22<00:13, 14.11it/s] 86%|████████▌ | 1097/1280 [01:22<00:14, 12.87it/s] 86%|████████▌ | 1099/1280 [01:22<00:13, 12.96it/s] 86%|████████▌ | 1101/1280 [01:22<00:13, 12.95it/s] 86%|████████▌ | 1103/1280 [01:22<00:13, 13.17it/s] 86%|████████▋ | 1105/1280 [01:22<00:13, 13.15it/s] 86%|████████▋ | 1107/1280 [01:23<00:12, 13.42it/s] 87%|████████▋ | 1109/1280 [01:23<00:13, 12.25it/s] 87%|████████▋ | 1111/1280 [01:23<00:13, 12.68it/s] 87%|████████▋ | 1113/1280 [01:23<00:12, 12.98it/s] 87%|████████▋ | 1115/1280 [01:23<00:12, 13.27it/s] 87%|████████▋ | 1117/1280 [01:23<00:13, 12.31it/s] 87%|████████▋ | 1119/1280 [01:24<00:12, 13.07it/s] 88%|████████▊ | 1121/1280 [01:24<00:12, 13.13it/s] 88%|████████▊ | 1123/1280 [01:24<00:11, 13.31it/s] 88%|████████▊ | 1125/1280 [01:24<00:11, 13.65it/s] 88%|████████▊ | 1127/1280 [01:24<00:11, 13.75it/s] 88%|████████▊ | 1129/1280 [01:24<00:10, 14.13it/s] 88%|████████▊ | 1131/1280 [01:24<00:10, 14.35it/s] 89%|████████▊ | 1133/1280 [01:25<00:11, 13.11it/s] 89%|████████▊ | 1135/1280 [01:25<00:10, 13.60it/s] 89%|████████▉ | 1137/1280 [01:25<00:10, 13.88it/s] 89%|████████▉ | 1139/1280 [01:25<00:10, 13.98it/s] 89%|████████▉ | 1141/1280 [01:25<00:10, 13.36it/s] 89%|████████▉ | 1143/1280 [01:25<00:09, 13.85it/s] 89%|████████▉ | 1145/1280 [01:25<00:09, 14.33it/s] 90%|████████▉ | 1147/1280 [01:26<00:10, 13.08it/s] 90%|████████▉ | 1149/1280 [01:26<00:09, 13.74it/s] 90%|████████▉ | 1151/1280 [01:26<00:09, 13.89it/s] 90%|█████████ | 1153/1280 [01:26<00:10, 12.70it/s] 90%|█████████ | 1155/1280 [01:26<00:09, 13.40it/s] 90%|█████████ | 1157/1280 [01:26<00:09, 13.65it/s] 91%|█████████ | 1159/1280 [01:26<00:08, 14.00it/s] 91%|█████████ | 1161/1280 [01:27<00:08, 14.15it/s] 91%|█████████ | 1163/1280 [01:27<00:08, 13.21it/s] 91%|█████████ | 1165/1280 [01:27<00:09, 12.44it/s] 91%|█████████ | 1167/1280 [01:27<00:08, 13.09it/s] 91%|█████████▏| 1169/1280 [01:27<00:08, 12.61it/s] 91%|█████████▏| 1171/1280 [01:27<00:09, 11.76it/s] 92%|█████████▏| 1173/1280 [01:28<00:09, 11.13it/s] 92%|█████████▏| 1175/1280 [01:28<00:08, 11.70it/s] 92%|█████████▏| 1177/1280 [01:28<00:08, 12.50it/s] 92%|█████████▏| 1179/1280 [01:28<00:08, 12.46it/s] 92%|█████████▏| 1181/1280 [01:28<00:07, 13.15it/s] 92%|█████████▏| 1183/1280 [01:28<00:07, 13.68it/s] 93%|█████████▎| 1185/1280 [01:29<00:06, 13.86it/s] 93%|█████████▎| 1187/1280 [01:29<00:07, 12.31it/s] 93%|█████████▎| 1189/1280 [01:29<00:07, 12.85it/s] 93%|█████████▎| 1191/1280 [01:29<00:06, 13.57it/s] 93%|█████████▎| 1193/1280 [01:29<00:06, 13.60it/s] 93%|█████████▎| 1195/1280 [01:29<00:06, 13.90it/s] 94%|█████████▎| 1197/1280 [01:29<00:05, 14.01it/s] 94%|█████████▎| 1199/1280 [01:30<00:05, 14.44it/s] 94%|█████████▍| 1201/1280 [01:30<00:05, 14.41it/s] 94%|█████████▍| 1203/1280 [01:30<00:05, 14.31it/s] 94%|█████████▍| 1205/1280 [01:30<00:05, 14.43it/s] 94%|█████████▍| 1207/1280 [01:30<00:05, 14.51it/s] 94%|█████████▍| 1209/1280 [01:30<00:05, 13.64it/s] 95%|█████████▍| 1211/1280 [01:30<00:04, 13.84it/s] 95%|█████████▍| 1213/1280 [01:31<00:04, 13.71it/s] 95%|█████████▍| 1215/1280 [01:31<00:04, 13.37it/s] 95%|█████████▌| 1217/1280 [01:31<00:04, 13.88it/s] 95%|█████████▌| 1219/1280 [01:31<00:04, 14.40it/s] 95%|█████████▌| 1221/1280 [01:31<00:04, 13.72it/s] 96%|█████████▌| 1223/1280 [01:31<00:04, 13.38it/s] 96%|█████████▌| 1225/1280 [01:31<00:03, 13.90it/s] 96%|█████████▌| 1227/1280 [01:32<00:03, 13.56it/s] 96%|█████████▌| 1229/1280 [01:32<00:03, 13.89it/s] 96%|█████████▌| 1231/1280 [01:32<00:03, 13.30it/s] 96%|█████████▋| 1233/1280 [01:32<00:03, 13.89it/s] 96%|█████████▋| 1235/1280 [01:32<00:03, 14.07it/s] 97%|█████████▋| 1237/1280 [01:32<00:03, 13.96it/s] 97%|█████████▋| 1239/1280 [01:32<00:02, 13.89it/s] 97%|█████████▋| 1241/1280 [01:33<00:02, 13.93it/s] 97%|█████████▋| 1243/1280 [01:33<00:02, 14.01it/s] 97%|█████████▋| 1245/1280 [01:33<00:02, 14.14it/s] 97%|█████████▋| 1247/1280 [01:33<00:02, 13.94it/s] 98%|█████████▊| 1249/1280 [01:33<00:02, 14.24it/s] 98%|█████████▊| 1251/1280 [01:33<00:02, 14.24it/s] 98%|█████████▊| 1253/1280 [01:33<00:01, 14.54it/s] 98%|█████████▊| 1255/1280 [01:34<00:01, 14.18it/s] 98%|█████████▊| 1257/1280 [01:34<00:01, 13.97it/s] 98%|█████████▊| 1259/1280 [01:34<00:01, 13.75it/s] 99%|█████████▊| 1261/1280 [01:34<00:01, 13.85it/s] 99%|█████████▊| 1263/1280 [01:34<00:01, 14.29it/s] 99%|█████████▉| 1265/1280 [01:34<00:01, 12.84it/s] 99%|█████████▉| 1267/1280 [01:35<00:01, 12.50it/s] 99%|█████████▉| 1269/1280 [01:35<00:00, 13.25it/s] 99%|█████████▉| 1271/1280 [01:35<00:00, 13.50it/s] 99%|█████████▉| 1273/1280 [01:35<00:00, 13.58it/s] 100%|█████████▉| 1275/1280 [01:35<00:00, 13.42it/s] 100%|█████████▉| 1277/1280 [01:35<00:00, 13.66it/s] 100%|█████████▉| 1279/1280 [01:35<00:00, 13.79it/s][INFO|trainer.py:1761] 2022-07-22 12:33:45,822 >> | |
| Training completed. Do not forget to share your model on huggingface.co/models =) | |
| {'train_runtime': 95.9834, 'train_samples_per_second': 426.48, 'train_steps_per_second': 13.336, 'train_loss': 0.4583479344844818, 'epoch': 1.0} | |
| 100%|██████████| 1280/1280 [01:35<00:00, 13.79it/s] 100%|██████████| 1280/1280 [01:35<00:00, 13.34it/s] | |
| [INFO|trainer.py:2503] 2022-07-22 12:33:45,829 >> Saving model checkpoint to runs/ebmnlp_hf/BioLinkBERT-base | |
| [INFO|configuration_utils.py:446] 2022-07-22 12:33:45,831 >> Configuration saved in runs/ebmnlp_hf/BioLinkBERT-base/config.json | |
| [INFO|modeling_utils.py:1660] 2022-07-22 12:33:46,435 >> Model weights saved in runs/ebmnlp_hf/BioLinkBERT-base/pytorch_model.bin | |
| [INFO|tokenization_utils_base.py:2123] 2022-07-22 12:33:46,436 >> tokenizer config file saved in runs/ebmnlp_hf/BioLinkBERT-base/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2130] 2022-07-22 12:33:46,436 >> Special tokens file saved in runs/ebmnlp_hf/BioLinkBERT-base/special_tokens_map.json | |
| ***** train metrics ***** | |
| epoch = 1.0 | |
| train_loss = 0.4583 | |
| train_runtime = 0:01:35.98 | |
| train_samples = 40935 | |
| train_samples_per_second = 426.48 | |
| train_steps_per_second = 13.336 | |
| 07/22/2022 12:33:46 - INFO - __main__ - *** Evaluate *** | |
| [INFO|trainer.py:661] 2022-07-22 12:33:46,477 >> The following columns in the evaluation set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: id, ner_tags, word_ids, tokens. If id, ner_tags, word_ids, tokens are not expected by `BertForTokenClassification.forward`, you can safely ignore this message. | |
| [INFO|trainer.py:2753] 2022-07-22 12:33:46,479 >> ***** Running Evaluation ***** | |
| [INFO|trainer.py:2755] 2022-07-22 12:33:46,479 >> Num examples = 10386 | |
| [INFO|trainer.py:2758] 2022-07-22 12:33:46,479 >> Batch size = 8 | |
| 0%| | 0/1299 [00:00<?, ?it/s] 1%| | 8/1299 [00:00<00:17, 72.89it/s] 1%| | 16/1299 [00:00<00:19, 67.39it/s] 2%|▏ | 23/1299 [00:00<00:19, 65.81it/s] 2%|▏ | 30/1299 [00:00<00:19, 64.92it/s] 3%|▎ | 37/1299 [00:00<00:19, 64.65it/s] 3%|▎ | 44/1299 [00:00<00:19, 64.42it/s] 4%|▍ | 51/1299 [00:00<00:19, 64.17it/s] 4%|▍ | 58/1299 [00:00<00:19, 64.09it/s] 5%|▌ | 65/1299 [00:01<00:19, 64.00it/s] 6%|▌ | 72/1299 [00:01<00:19, 63.66it/s] 6%|▌ | 79/1299 [00:01<00:19, 63.73it/s] 7%|▋ | 86/1299 [00:01<00:18, 63.85it/s] 7%|▋ | 93/1299 [00:01<00:19, 63.44it/s] 8%|▊ | 100/1299 [00:01<00:18, 63.49it/s] 8%|▊ | 107/1299 [00:01<00:18, 63.51it/s] 9%|▉ | 114/1299 [00:01<00:18, 63.49it/s] 9%|▉ | 121/1299 [00:01<00:18, 63.40it/s] 10%|▉ | 128/1299 [00:01<00:18, 63.44it/s] 10%|█ | 135/1299 [00:02<00:18, 63.42it/s] 11%|█ | 142/1299 [00:02<00:18, 63.51it/s] 11%|█▏ | 149/1299 [00:02<00:18, 63.64it/s] 12%|█▏ | 156/1299 [00:02<00:17, 63.63it/s] 13%|█▎ | 163/1299 [00:02<00:17, 63.62it/s] 13%|█▎ | 170/1299 [00:02<00:17, 63.74it/s] 14%|█▎ | 177/1299 [00:02<00:17, 63.73it/s] 14%|█▍ | 184/1299 [00:02<00:17, 63.49it/s] 15%|█▍ | 191/1299 [00:02<00:17, 63.53it/s] 15%|█▌ | 198/1299 [00:03<00:17, 63.77it/s] 16%|█▌ | 205/1299 [00:03<00:17, 63.78it/s] 16%|█▋ | 212/1299 [00:03<00:17, 63.85it/s] 17%|█▋ | 219/1299 [00:03<00:16, 63.83it/s] 17%|█▋ | 226/1299 [00:03<00:16, 63.83it/s] 18%|█▊ | 233/1299 [00:03<00:16, 63.89it/s] 18%|█▊ | 240/1299 [00:03<00:16, 63.93it/s] 19%|█▉ | 247/1299 [00:03<00:16, 63.88it/s] 20%|█▉ | 254/1299 [00:03<00:16, 63.93it/s] 20%|██ | 261/1299 [00:04<00:16, 64.00it/s] 21%|██ | 268/1299 [00:04<00:16, 63.84it/s] 21%|██ | 275/1299 [00:04<00:16, 63.91it/s] 22%|██▏ | 282/1299 [00:04<00:15, 63.85it/s] 22%|██▏ | 289/1299 [00:04<00:15, 63.79it/s] 23%|██▎ | 296/1299 [00:04<00:15, 63.79it/s] 23%|██▎ | 303/1299 [00:04<00:15, 63.75it/s] 24%|██▍ | 310/1299 [00:04<00:15, 63.86it/s] 24%|██▍ | 317/1299 [00:04<00:15, 63.86it/s] 25%|██▍ | 324/1299 [00:05<00:15, 63.81it/s] 25%|██▌ | 331/1299 [00:05<00:15, 63.97it/s] 26%|██▌ | 338/1299 [00:05<00:15, 63.88it/s] 27%|██▋ | 345/1299 [00:05<00:14, 63.83it/s] 27%|██▋ | 352/1299 [00:05<00:14, 63.92it/s] 28%|██▊ | 359/1299 [00:05<00:14, 63.93it/s] 28%|██▊ | 366/1299 [00:05<00:14, 63.96it/s] 29%|██▊ | 373/1299 [00:05<00:14, 63.97it/s] 29%|██▉ | 380/1299 [00:05<00:14, 63.79it/s] 30%|██▉ | 387/1299 [00:06<00:14, 63.70it/s] 30%|███ | 394/1299 [00:06<00:14, 63.63it/s] 31%|███ | 401/1299 [00:06<00:14, 63.61it/s] 31%|███▏ | 408/1299 [00:06<00:13, 63.87it/s] 32%|███▏ | 415/1299 [00:06<00:13, 63.91it/s] 32%|███▏ | 422/1299 [00:06<00:13, 63.84it/s] 33%|███▎ | 429/1299 [00:06<00:13, 63.82it/s] 34%|███▎ | 436/1299 [00:06<00:13, 63.95it/s] 34%|███▍ | 443/1299 [00:06<00:13, 64.01it/s] 35%|███▍ | 450/1299 [00:07<00:13, 64.08it/s] 35%|███▌ | 457/1299 [00:07<00:13, 64.04it/s] 36%|███▌ | 464/1299 [00:07<00:13, 64.04it/s] 36%|███▋ | 471/1299 [00:07<00:12, 63.94it/s] 37%|███▋ | 478/1299 [00:07<00:12, 63.82it/s] 37%|███▋ | 485/1299 [00:07<00:12, 63.94it/s] 38%|███▊ | 492/1299 [00:07<00:12, 63.98it/s] 38%|███▊ | 499/1299 [00:07<00:12, 63.71it/s] 39%|███▉ | 506/1299 [00:07<00:12, 63.79it/s] 39%|███▉ | 513/1299 [00:08<00:12, 63.83it/s] 40%|████ | 520/1299 [00:08<00:12, 63.85it/s] 41%|████ | 527/1299 [00:08<00:12, 63.80it/s] 41%|████ | 534/1299 [00:08<00:11, 63.76it/s] 42%|████▏ | 541/1299 [00:08<00:11, 63.91it/s] 42%|████▏ | 548/1299 [00:08<00:11, 64.07it/s] 43%|████▎ | 555/1299 [00:08<00:11, 64.08it/s] 43%|████▎ | 562/1299 [00:08<00:11, 64.13it/s] 44%|████▍ | 569/1299 [00:08<00:11, 64.11it/s] 44%|████▍ | 576/1299 [00:09<00:11, 63.91it/s] 45%|████▍ | 583/1299 [00:09<00:11, 63.98it/s] 45%|████▌ | 590/1299 [00:09<00:11, 63.98it/s] 46%|████▌ | 597/1299 [00:09<00:10, 63.98it/s] 46%|████▋ | 604/1299 [00:09<00:10, 63.92it/s] 47%|████▋ | 611/1299 [00:09<00:10, 63.88it/s] 48%|████▊ | 618/1299 [00:09<00:10, 63.96it/s] 48%|████▊ | 625/1299 [00:09<00:10, 63.78it/s] 49%|████▊ | 632/1299 [00:09<00:10, 63.83it/s] 49%|████▉ | 639/1299 [00:10<00:10, 63.16it/s] 50%|████▉ | 646/1299 [00:10<00:10, 63.26it/s] 50%|█████ | 653/1299 [00:10<00:10, 63.41it/s] 51%|█████ | 660/1299 [00:10<00:10, 63.57it/s] 51%|█████▏ | 667/1299 [00:10<00:09, 63.45it/s] 52%|█████▏ | 674/1299 [00:10<00:09, 63.64it/s] 52%|█████▏ | 681/1299 [00:10<00:09, 63.78it/s] 53%|█████▎ | 688/1299 [00:10<00:09, 63.51it/s] 54%|█████▎ | 695/1299 [00:10<00:09, 63.66it/s] 54%|█████▍ | 702/1299 [00:10<00:09, 63.93it/s] 55%|█████▍ | 709/1299 [00:11<00:09, 63.86it/s] 55%|█████▌ | 716/1299 [00:11<00:09, 63.83it/s] 56%|█████▌ | 723/1299 [00:11<00:09, 63.78it/s] 56%|█████▌ | 730/1299 [00:11<00:08, 63.93it/s] 57%|█████▋ | 737/1299 [00:11<00:08, 63.81it/s] 57%|█████▋ | 744/1299 [00:11<00:08, 63.86it/s] 58%|█████▊ | 751/1299 [00:11<00:08, 64.02it/s] 58%|█████▊ | 758/1299 [00:11<00:08, 63.98it/s] 59%|█████▉ | 765/1299 [00:11<00:08, 63.95it/s] 59%|█████▉ | 772/1299 [00:12<00:08, 63.90it/s] 60%|█████▉ | 779/1299 [00:12<00:08, 64.10it/s] 61%|██████ | 786/1299 [00:12<00:08, 64.00it/s] 61%|██████ | 793/1299 [00:12<00:07, 64.00it/s] 62%|██████▏ | 800/1299 [00:12<00:07, 64.06it/s] 62%|██████▏ | 807/1299 [00:12<00:07, 64.12it/s] 63%|██████▎ | 814/1299 [00:12<00:07, 64.01it/s] 63%|██████▎ | 821/1299 [00:12<00:07, 63.89it/s] 64%|██████▎ | 828/1299 [00:12<00:07, 63.90it/s] 64%|██████▍ | 835/1299 [00:13<00:07, 63.95it/s] 65%|██████▍ | 842/1299 [00:13<00:07, 63.95it/s] 65%|██████▌ | 849/1299 [00:13<00:07, 64.02it/s] 66%|██████▌ | 856/1299 [00:13<00:06, 63.86it/s] 66%|██████▋ | 863/1299 [00:13<00:06, 63.76it/s] 67%|██████▋ | 870/1299 [00:13<00:06, 63.72it/s] 68%|██████▊ | 877/1299 [00:13<00:06, 63.71it/s] 68%|██████▊ | 884/1299 [00:13<00:06, 63.77it/s] 69%|██████▊ | 891/1299 [00:13<00:06, 63.70it/s] 69%|██████▉ | 898/1299 [00:14<00:06, 63.74it/s] 70%|██████▉ | 905/1299 [00:14<00:06, 63.77it/s] 70%|███████ | 912/1299 [00:14<00:06, 63.83it/s] 71%|███████ | 919/1299 [00:14<00:05, 63.81it/s] 71%|███████▏ | 926/1299 [00:14<00:05, 63.89it/s] 72%|███████▏ | 933/1299 [00:14<00:05, 63.91it/s] 72%|███████▏ | 940/1299 [00:14<00:05, 63.97it/s] 73%|███████▎ | 947/1299 [00:14<00:05, 63.93it/s] 73%|███████▎ | 954/1299 [00:14<00:05, 63.87it/s] 74%|███████▍ | 961/1299 [00:15<00:05, 63.71it/s] 75%|███████▍ | 968/1299 [00:15<00:05, 63.72it/s] 75%|███████▌ | 975/1299 [00:15<00:05, 63.85it/s] 76%|███████▌ | 982/1299 [00:15<00:04, 63.93it/s] 76%|███████▌ | 989/1299 [00:15<00:04, 64.09it/s] 77%|███████▋ | 996/1299 [00:15<00:04, 63.93it/s] 77%|███████▋ | 1003/1299 [00:15<00:04, 63.89it/s] 78%|███████▊ | 1010/1299 [00:15<00:04, 63.70it/s] 78%|███████▊ | 1017/1299 [00:15<00:04, 63.75it/s] 79%|███████▉ | 1024/1299 [00:16<00:04, 63.72it/s] 79%|███████▉ | 1031/1299 [00:16<00:04, 63.68it/s] 80%|███████▉ | 1038/1299 [00:16<00:04, 63.76it/s] 80%|████████ | 1045/1299 [00:16<00:03, 63.74it/s] 81%|████████ | 1052/1299 [00:16<00:03, 63.94it/s] 82%|████████▏ | 1059/1299 [00:16<00:03, 63.78it/s] 82%|████████▏ | 1066/1299 [00:16<00:03, 63.74it/s] 83%|████████▎ | 1073/1299 [00:16<00:03, 63.66it/s] 83%|████████▎ | 1080/1299 [00:16<00:03, 63.61it/s] 84%|████████▎ | 1087/1299 [00:17<00:03, 63.64it/s] 84%|████████▍ | 1094/1299 [00:17<00:03, 63.80it/s] 85%|████████▍ | 1101/1299 [00:17<00:03, 63.68it/s] 85%|████████▌ | 1108/1299 [00:17<00:02, 63.77it/s] 86%|████████▌ | 1115/1299 [00:17<00:02, 63.84it/s] 86%|████████▋ | 1122/1299 [00:17<00:02, 63.74it/s] 87%|████████▋ | 1129/1299 [00:17<00:02, 63.80it/s] 87%|████████▋ | 1136/1299 [00:17<00:02, 63.93it/s] 88%|████████▊ | 1143/1299 [00:17<00:02, 63.94it/s] 89%|████████▊ | 1150/1299 [00:18<00:02, 63.91it/s] 89%|████████▉ | 1157/1299 [00:18<00:02, 63.89it/s] 90%|████████▉ | 1164/1299 [00:18<00:02, 63.84it/s] 90%|█████████ | 1171/1299 [00:18<00:02, 63.95it/s] 91%|█████████ | 1178/1299 [00:18<00:01, 63.95it/s] 91%|█████████ | 1185/1299 [00:18<00:01, 64.14it/s] 92%|█████████▏| 1192/1299 [00:18<00:01, 63.65it/s] 92%|█████████▏| 1199/1299 [00:18<00:01, 63.71it/s] 93%|█████████▎| 1206/1299 [00:18<00:01, 63.56it/s] 93%|█████████▎| 1213/1299 [00:18<00:01, 63.57it/s] 94%|█████████▍| 1220/1299 [00:19<00:01, 63.33it/s] 94%|█████████▍| 1227/1299 [00:19<00:01, 63.43it/s] 95%|█████████▍| 1234/1299 [00:19<00:01, 63.49it/s] 96%|█████████▌| 1241/1299 [00:19<00:00, 63.46it/s] 96%|█████████▌| 1248/1299 [00:19<00:00, 63.52it/s] 97%|█████████▋| 1255/1299 [00:19<00:00, 63.43it/s] 97%|█████████▋| 1262/1299 [00:19<00:00, 63.53it/s] 98%|█████████▊| 1269/1299 [00:19<00:00, 63.51it/s] 98%|█████████▊| 1276/1299 [00:19<00:00, 63.48it/s] 99%|█████████▉| 1283/1299 [00:20<00:00, 63.54it/s] 99%|█████████▉| 1290/1299 [00:20<00:00, 63.50it/s] 100%|█████████▉| 1297/1299 [00:20<00:00, 63.56it/s]07/22/2022 12:34:13 - INFO - datasets.metric - Removing /home/hungthinht/.cache/huggingface/metrics/seqeval/default/default_experiment-1-0.arrow | |
| type_name INT | |
| type_name OUT | |
| type_name PAR | |
| 100%|██████████| 1299/1299 [00:26<00:00, 48.70it/s] | |
| ***** eval metrics ***** | |
| epoch = 1.0 | |
| eval_loss = 0.4264 | |
| eval_macro_f1 = 0.7191 | |
| eval_macro_precision = 0.7641 | |
| eval_macro_recall = 0.6793 | |
| eval_runtime = 0:00:26.69 | |
| eval_samples = 10386 | |
| eval_samples_per_second = 389.133 | |
| eval_steps_per_second = 48.67 | |
| 07/22/2022 12:34:13 - INFO - __main__ - *** Predict *** | |
| [INFO|trainer.py:661] 2022-07-22 12:34:13,176 >> The following columns in the test set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: id, ner_tags, word_ids, tokens. If id, ner_tags, word_ids, tokens are not expected by `BertForTokenClassification.forward`, you can safely ignore this message. | |
| [INFO|trainer.py:2753] 2022-07-22 12:34:13,177 >> ***** Running Prediction ***** | |
| [INFO|trainer.py:2755] 2022-07-22 12:34:13,178 >> Num examples = 2076 | |
| [INFO|trainer.py:2758] 2022-07-22 12:34:13,178 >> Batch size = 8 | |
| 0%| | 0/260 [00:00<?, ?it/s] 3%|▎ | 8/260 [00:00<00:03, 72.67it/s] 6%|▌ | 16/260 [00:00<00:03, 67.39it/s] 9%|▉ | 23/260 [00:00<00:03, 66.06it/s] 12%|█▏ | 30/260 [00:00<00:03, 65.17it/s] 14%|█▍ | 37/260 [00:00<00:03, 64.44it/s] 17%|█▋ | 44/260 [00:00<00:03, 64.25it/s] 20%|█▉ | 51/260 [00:00<00:03, 64.15it/s] 22%|██▏ | 58/260 [00:00<00:03, 64.02it/s] 25%|██▌ | 65/260 [00:01<00:03, 63.86it/s] 28%|██▊ | 72/260 [00:01<00:02, 63.76it/s] 30%|███ | 79/260 [00:01<00:02, 63.78it/s] 33%|███▎ | 86/260 [00:01<00:02, 63.62it/s] 36%|███▌ | 93/260 [00:01<00:02, 63.55it/s] 38%|███▊ | 100/260 [00:01<00:02, 63.62it/s] 41%|████ | 107/260 [00:01<00:02, 63.78it/s] 44%|████▍ | 114/260 [00:01<00:02, 63.79it/s] 47%|████▋ | 121/260 [00:01<00:02, 63.79it/s] 49%|████▉ | 128/260 [00:01<00:02, 63.72it/s] 52%|█████▏ | 135/260 [00:02<00:01, 63.79it/s] 55%|█████▍ | 142/260 [00:02<00:01, 63.71it/s] 57%|█████▋ | 149/260 [00:02<00:01, 63.77it/s] 60%|██████ | 156/260 [00:02<00:01, 63.98it/s] 63%|██████▎ | 163/260 [00:02<00:01, 64.06it/s] 65%|██████▌ | 170/260 [00:02<00:01, 64.05it/s] 68%|██████▊ | 177/260 [00:02<00:01, 64.01it/s] 71%|███████ | 184/260 [00:02<00:01, 64.00it/s] 73%|███████▎ | 191/260 [00:02<00:01, 63.86it/s] 76%|███████▌ | 198/260 [00:03<00:00, 63.89it/s] 79%|███████▉ | 205/260 [00:03<00:00, 63.87it/s] 82%|████████▏ | 212/260 [00:03<00:00, 63.81it/s] 84%|████████▍ | 219/260 [00:03<00:00, 63.78it/s] 87%|████████▋ | 226/260 [00:03<00:00, 63.68it/s] 90%|████████▉ | 233/260 [00:03<00:00, 63.76it/s] 92%|█████████▏| 240/260 [00:03<00:00, 63.85it/s] 95%|█████████▌| 247/260 [00:03<00:00, 63.75it/s] 98%|█████████▊| 254/260 [00:03<00:00, 63.90it/s]07/22/2022 12:34:18 - INFO - datasets.metric - Removing /home/hungthinht/.cache/huggingface/metrics/seqeval/default/default_experiment-1-0.arrow | |
| type_name INT | |
| type_name OUT | |
| type_name PAR | |
| ***** test metrics ***** | |
| test_loss = 0.4043 | |
| test_macro_f1 = 0.7406 | |
| test_macro_precision = 0.7578 | |
| test_macro_recall = 0.7467 | |
| test_runtime = 0:00:05.17 | |
| test_samples = 2076 | |
| test_samples_per_second = 401.101 | |
| test_steps_per_second = 50.234 | |
| 100%|██████████| 260/260 [00:07<00:00, 36.10it/s] | |