| 2024-09-05 21:40:16.805233: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. | |
| 2024-09-05 21:40:16.823412: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:485] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered | |
| 2024-09-05 21:40:16.844949: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:8454] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered | |
| 2024-09-05 21:40:16.851514: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1452] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered | |
| 2024-09-05 21:40:16.867297: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. | |
| To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. | |
| 2024-09-05 21:40:18.144744: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT | |
| /usr/local/lib/python3.10/dist-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead | |
| warnings.warn( | |
| 09/05/2024 21:40:20 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False | |
| 09/05/2024 21:40:20 - INFO - __main__ - Training/evaluation parameters TrainingArguments( | |
| _n_gpu=1, | |
| accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None, 'use_configured_state': False}, | |
| adafactor=False, | |
| adam_beta1=0.9, | |
| adam_beta2=0.999, | |
| adam_epsilon=1e-08, | |
| auto_find_batch_size=False, | |
| batch_eval_metrics=False, | |
| bf16=False, | |
| bf16_full_eval=False, | |
| data_seed=None, | |
| dataloader_drop_last=False, | |
| dataloader_num_workers=0, | |
| dataloader_persistent_workers=False, | |
| dataloader_pin_memory=True, | |
| dataloader_prefetch_factor=None, | |
| ddp_backend=None, | |
| ddp_broadcast_buffers=None, | |
| ddp_bucket_cap_mb=None, | |
| ddp_find_unused_parameters=None, | |
| ddp_timeout=1800, | |
| debug=[], | |
| deepspeed=None, | |
| disable_tqdm=False, | |
| dispatch_batches=None, | |
| do_eval=True, | |
| do_predict=True, | |
| do_train=True, | |
| eval_accumulation_steps=None, | |
| eval_delay=0, | |
| eval_do_concat_batches=True, | |
| eval_on_start=False, | |
| eval_steps=None, | |
| eval_strategy=epoch, | |
| eval_use_gather_object=False, | |
| evaluation_strategy=epoch, | |
| fp16=False, | |
| fp16_backend=auto, | |
| fp16_full_eval=False, | |
| fp16_opt_level=O1, | |
| fsdp=[], | |
| fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, | |
| fsdp_min_num_params=0, | |
| fsdp_transformer_layer_cls_to_wrap=None, | |
| full_determinism=False, | |
| gradient_accumulation_steps=2, | |
| gradient_checkpointing=False, | |
| gradient_checkpointing_kwargs=None, | |
| greater_is_better=True, | |
| group_by_length=False, | |
| half_precision_backend=auto, | |
| hub_always_push=False, | |
| hub_model_id=None, | |
| hub_private_repo=False, | |
| hub_strategy=every_save, | |
| hub_token=<HUB_TOKEN>, | |
| ignore_data_skip=False, | |
| include_inputs_for_metrics=False, | |
| include_num_input_tokens_seen=False, | |
| include_tokens_per_second=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=True, | |
| local_rank=0, | |
| log_level=passive, | |
| log_level_replica=warning, | |
| log_on_each_node=True, | |
| logging_dir=/content/dissertation/scripts/ner/output/tb, | |
| logging_first_step=False, | |
| logging_nan_inf_filter=True, | |
| logging_steps=500, | |
| logging_strategy=steps, | |
| lr_scheduler_kwargs={}, | |
| lr_scheduler_type=linear, | |
| max_grad_norm=1.0, | |
| max_steps=-1, | |
| metric_for_best_model=f1, | |
| mp_parameters=, | |
| neftune_noise_alpha=None, | |
| no_cuda=False, | |
| num_train_epochs=10.0, | |
| optim=adamw_torch, | |
| optim_args=None, | |
| optim_target_modules=None, | |
| output_dir=/content/dissertation/scripts/ner/output, | |
| 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=True, | |
| 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'], | |
| restore_callback_states_from_checkpoint=False, | |
| resume_from_checkpoint=None, | |
| run_name=/content/dissertation/scripts/ner/output, | |
| save_on_each_node=False, | |
| save_only_model=False, | |
| save_safetensors=True, | |
| save_steps=500, | |
| save_strategy=epoch, | |
| save_total_limit=None, | |
| seed=42, | |
| skip_memory_metrics=True, | |
| split_batches=None, | |
| tf32=None, | |
| torch_compile=False, | |
| torch_compile_backend=None, | |
| torch_compile_mode=None, | |
| torch_empty_cache_steps=None, | |
| torchdynamo=None, | |
| tpu_metrics_debug=False, | |
| tpu_num_cores=None, | |
| use_cpu=False, | |
| use_ipex=False, | |
| use_legacy_prediction_loop=False, | |
| use_mps_device=False, | |
| warmup_ratio=0.0, | |
| warmup_steps=0, | |
| weight_decay=0.0, | |
| ) | |
| Downloading builder script: 0%| | 0.00/3.98k [00:00<?, ?B/s] Downloading builder script: 100%|██████████| 3.98k/3.98k [00:00<00:00, 43.8kB/s] | |
| Downloading data: 0%| | 0.00/24.2M [00:00<?, ?B/s] Downloading data: 43%|████▎ | 10.5M/24.2M [00:00<00:00, 16.9MB/s] Downloading data: 87%|████████▋ | 21.0M/24.2M [00:00<00:00, 24.4MB/s] Downloading data: 100%|██████████| 24.2M/24.2M [00:01<00:00, 25.1MB/s] Downloading data: 100%|██████████| 24.2M/24.2M [00:01<00:00, 23.0MB/s] | |
| Downloading data: 0%| | 0.00/5.12M [00:00<?, ?B/s] Downloading data: 100%|██████████| 5.12M/5.12M [00:00<00:00, 11.1MB/s] Downloading data: 100%|██████████| 5.12M/5.12M [00:00<00:00, 11.0MB/s] | |
| Downloading data: 0%| | 0.00/7.32M [00:00<?, ?B/s] Downloading data: 100%|██████████| 7.32M/7.32M [00:00<00:00, 16.5MB/s] Downloading data: 100%|██████████| 7.32M/7.32M [00:00<00:00, 16.1MB/s] | |
| Generating train split: 0 examples [00:00, ? examples/s] Generating train split: 595 examples [00:00, 5922.43 examples/s] Generating train split: 1476 examples [00:00, 5882.26 examples/s] Generating train split: 2356 examples [00:00, 5870.99 examples/s] Generating train split: 2970 examples [00:00, 5952.99 examples/s] Generating train split: 3862 examples [00:00, 5944.28 examples/s] Generating train split: 4765 examples [00:00, 5965.14 examples/s] Generating train split: 5649 examples [00:00, 5936.56 examples/s] Generating train split: 6275 examples [00:01, 6014.19 examples/s] Generating train split: 6917 examples [00:01, 6116.41 examples/s] Generating train split: 7802 examples [00:01, 6031.32 examples/s] Generating train split: 8433 examples [00:01, 6095.70 examples/s] Generating train split: 9354 examples [00:01, 6109.41 examples/s] Generating train split: 9971 examples [00:01, 6121.83 examples/s] Generating train split: 10832 examples [00:01, 5983.18 examples/s] Generating train split: 11696 examples [00:01, 5904.12 examples/s] Generating train split: 12321 examples [00:02, 5849.45 examples/s] Generating train split: 12978 examples [00:02, 6028.65 examples/s] Generating train split: 13908 examples [00:02, 6078.24 examples/s] Generating train split: 14536 examples [00:02, 6126.98 examples/s] Generating train split: 15507 examples [00:02, 6244.77 examples/s] Generating train split: 16421 examples [00:02, 6188.49 examples/s] Generating train split: 17313 examples [00:02, 6052.28 examples/s] Generating train split: 17925 examples [00:02, 6063.74 examples/s] Generating train split: 18812 examples [00:03, 6007.71 examples/s] Generating train split: 19423 examples [00:03, 6028.85 examples/s] Generating train split: 20311 examples [00:03, 5951.79 examples/s] Generating train split: 20922 examples [00:03, 5988.23 examples/s] Generating train split: 21761 examples [00:03, 5850.72 examples/s] Generating train split: 22671 examples [00:03, 5888.79 examples/s] Generating train split: 23576 examples [00:03, 5931.45 examples/s] Generating train split: 24178 examples [00:04, 5948.23 examples/s] Generating train split: 24821 examples [00:04, 6066.10 examples/s] Generating train split: 25627 examples [00:04, 5817.87 examples/s] Generating train split: 26483 examples [00:04, 5777.13 examples/s] Generating train split: 27386 examples [00:04, 5852.59 examples/s] Generating train split: 28000 examples [00:04, 5848.72 examples/s] Generating train split: 28620 examples [00:04, 5933.23 examples/s] Generating train split: 29237 examples [00:04, 5991.28 examples/s] Generating train split: 29848 examples [00:04, 6020.55 examples/s] Generating train split: 30564 examples [00:05, 3825.57 examples/s] Generating train split: 31100 examples [00:05, 4121.34 examples/s] Generating train split: 31747 examples [00:05, 4629.87 examples/s] Generating train split: 32594 examples [00:05, 4896.80 examples/s] Generating train split: 32675 examples [00:05, 5736.98 examples/s] | |
| Generating validation split: 0 examples [00:00, ? examples/s] Generating validation split: 646 examples [00:00, 6442.91 examples/s] Generating validation split: 1595 examples [00:00, 6353.65 examples/s] Generating validation split: 2470 examples [00:00, 6092.74 examples/s] Generating validation split: 3364 examples [00:00, 6035.54 examples/s] Generating validation split: 4000 examples [00:00, 6062.77 examples/s] Generating validation split: 4651 examples [00:00, 6187.31 examples/s] Generating validation split: 5561 examples [00:00, 6138.63 examples/s] Generating validation split: 6519 examples [00:01, 6219.67 examples/s] Generating validation split: 7150 examples [00:01, 6236.19 examples/s] Generating validation split: 7354 examples [00:01, 6178.07 examples/s] | |
| Generating test split: 0 examples [00:00, ? examples/s] Generating test split: 700 examples [00:00, 6979.11 examples/s] Generating test split: 1735 examples [00:00, 6745.09 examples/s] Generating test split: 2731 examples [00:00, 6688.28 examples/s] Generating test split: 3453 examples [00:00, 6855.03 examples/s] Generating test split: 4529 examples [00:00, 6981.55 examples/s] Generating test split: 5452 examples [00:00, 6671.43 examples/s] Generating test split: 6359 examples [00:00, 6455.13 examples/s] Generating test split: 7331 examples [00:01, 6446.63 examples/s] Generating test split: 8218 examples [00:01, 6271.43 examples/s] Generating test split: 8884 examples [00:01, 6357.35 examples/s] Generating test split: 9770 examples [00:01, 6201.69 examples/s] Generating test split: 10665 examples [00:01, 6124.45 examples/s] Generating test split: 10838 examples [00:01, 6387.24 examples/s] | |
| [INFO|configuration_utils.py:733] 2024-09-05 21:40:33,477 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/config.json | |
| [INFO|configuration_utils.py:800] 2024-09-05 21:40:33,486 >> Model config RobertaConfig { | |
| "_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es", | |
| "architectures": [ | |
| "RobertaForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 0, | |
| "classifier_dropout": null, | |
| "eos_token_id": 2, | |
| "finetuning_task": "ner", | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "O", | |
| "1": "B-MORFOLOGIA_NEOPLASIA", | |
| "2": "I-MORFOLOGIA_NEOPLASIA" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "B-MORFOLOGIA_NEOPLASIA": 1, | |
| "I-MORFOLOGIA_NEOPLASIA": 2, | |
| "O": 0 | |
| }, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 514, | |
| "model_type": "roberta", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 1, | |
| "position_embedding_type": "absolute", | |
| "transformers_version": "4.44.2", | |
| "type_vocab_size": 1, | |
| "use_cache": true, | |
| "vocab_size": 50262 | |
| } | |
| [INFO|configuration_utils.py:733] 2024-09-05 21:40:33,679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/config.json | |
| [INFO|configuration_utils.py:800] 2024-09-05 21:40:33,680 >> Model config RobertaConfig { | |
| "_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es", | |
| "architectures": [ | |
| "RobertaForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 0, | |
| "classifier_dropout": null, | |
| "eos_token_id": 2, | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 514, | |
| "model_type": "roberta", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 1, | |
| "position_embedding_type": "absolute", | |
| "transformers_version": "4.44.2", | |
| "type_vocab_size": 1, | |
| "use_cache": true, | |
| "vocab_size": 50262 | |
| } | |
| [INFO|tokenization_utils_base.py:2269] 2024-09-05 21:40:35,107 >> loading file vocab.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/vocab.json | |
| [INFO|tokenization_utils_base.py:2269] 2024-09-05 21:40:35,107 >> loading file merges.txt from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/merges.txt | |
| [INFO|tokenization_utils_base.py:2269] 2024-09-05 21:40:35,107 >> loading file tokenizer.json from cache at None | |
| [INFO|tokenization_utils_base.py:2269] 2024-09-05 21:40:35,107 >> loading file added_tokens.json from cache at None | |
| [INFO|tokenization_utils_base.py:2269] 2024-09-05 21:40:35,107 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/special_tokens_map.json | |
| [INFO|tokenization_utils_base.py:2269] 2024-09-05 21:40:35,108 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/tokenizer_config.json | |
| [INFO|configuration_utils.py:733] 2024-09-05 21:40:35,108 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/config.json | |
| [INFO|configuration_utils.py:800] 2024-09-05 21:40:35,109 >> Model config RobertaConfig { | |
| "_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es", | |
| "architectures": [ | |
| "RobertaForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 0, | |
| "classifier_dropout": null, | |
| "eos_token_id": 2, | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 514, | |
| "model_type": "roberta", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 1, | |
| "position_embedding_type": "absolute", | |
| "transformers_version": "4.44.2", | |
| "type_vocab_size": 1, | |
| "use_cache": true, | |
| "vocab_size": 50262 | |
| } | |
| /usr/local/lib/python3.10/dist-packages/transformers/tokenization_utils_base.py:1601: FutureWarning: `clean_up_tokenization_spaces` was not set. It will be set to `True` by default. This behavior will be depracted in transformers v4.45, and will be then set to `False` by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884 | |
| warnings.warn( | |
| [INFO|configuration_utils.py:733] 2024-09-05 21:40:35,189 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/config.json | |
| [INFO|configuration_utils.py:800] 2024-09-05 21:40:35,190 >> Model config RobertaConfig { | |
| "_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es", | |
| "architectures": [ | |
| "RobertaForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 0, | |
| "classifier_dropout": null, | |
| "eos_token_id": 2, | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 514, | |
| "model_type": "roberta", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 1, | |
| "position_embedding_type": "absolute", | |
| "transformers_version": "4.44.2", | |
| "type_vocab_size": 1, | |
| "use_cache": true, | |
| "vocab_size": 50262 | |
| } | |
| [INFO|modeling_utils.py:3678] 2024-09-05 21:40:52,003 >> loading weights file pytorch_model.bin from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/pytorch_model.bin | |
| [INFO|modeling_utils.py:4497] 2024-09-05 21:40:52,139 >> Some weights of the model checkpoint at PlanTL-GOB-ES/bsc-bio-ehr-es were not used when initializing RobertaForTokenClassification: ['lm_head.bias', 'lm_head.decoder.bias', 'lm_head.decoder.weight', 'lm_head.dense.bias', 'lm_head.dense.weight', 'lm_head.layer_norm.bias', 'lm_head.layer_norm.weight'] | |
| - This IS expected if you are initializing RobertaForTokenClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). | |
| - This IS NOT expected if you are initializing RobertaForTokenClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). | |
| [WARNING|modeling_utils.py:4509] 2024-09-05 21:40:52,139 >> Some weights of RobertaForTokenClassification were not initialized from the model checkpoint at PlanTL-GOB-ES/bsc-bio-ehr-es and are newly initialized: ['classifier.bias', 'classifier.weight'] | |
| You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. | |
| Map: 0%| | 0/32675 [00:00<?, ? examples/s] Map: 3%|▎ | 1000/32675 [00:00<00:03, 8902.04 examples/s] Map: 6%|▌ | 2000/32675 [00:00<00:03, 9372.15 examples/s] Map: 9%|▉ | 3000/32675 [00:00<00:03, 9588.32 examples/s] Map: 15%|█▌ | 5000/32675 [00:00<00:02, 9877.07 examples/s] Map: 21%|██▏ | 7000/32675 [00:00<00:02, 10074.22 examples/s] Map: 28%|██▊ | 9000/32675 [00:00<00:02, 10265.15 examples/s] Map: 34%|███▎ | 11000/32675 [00:01<00:02, 10138.74 examples/s] Map: 40%|███▉ | 13000/32675 [00:01<00:01, 10040.70 examples/s] Map: 46%|████▌ | 15000/32675 [00:01<00:01, 10212.51 examples/s] Map: 52%|█████▏ | 17000/32675 [00:01<00:01, 10391.08 examples/s] Map: 58%|█████▊ | 19000/32675 [00:01<00:01, 10305.32 examples/s] Map: 64%|██████▍ | 21000/32675 [00:02<00:01, 10188.67 examples/s] Map: 70%|███████ | 23000/32675 [00:02<00:00, 10148.19 examples/s] Map: 77%|███████▋ | 25000/32675 [00:02<00:00, 10254.71 examples/s] Map: 83%|████████▎ | 27000/32675 [00:02<00:00, 10101.82 examples/s] Map: 89%|████████▉ | 29000/32675 [00:02<00:00, 10246.56 examples/s] Map: 95%|█████████▍| 31000/32675 [00:03<00:00, 10380.88 examples/s] Map: 100%|██████████| 32675/32675 [00:03<00:00, 10207.70 examples/s] Map: 100%|██████████| 32675/32675 [00:03<00:00, 10082.13 examples/s] | |
| Map: 0%| | 0/7354 [00:00<?, ? examples/s] Map: 27%|██▋ | 2000/7354 [00:00<00:00, 10717.09 examples/s] Map: 54%|█████▍ | 4000/7354 [00:00<00:00, 5888.19 examples/s] Map: 82%|████████▏ | 6000/7354 [00:00<00:00, 7324.84 examples/s] Map: 100%|██████████| 7354/7354 [00:00<00:00, 8177.31 examples/s] Map: 100%|██████████| 7354/7354 [00:00<00:00, 7707.40 examples/s] | |
| Map: 0%| | 0/10838 [00:00<?, ? examples/s] Map: 18%|█▊ | 2000/10838 [00:00<00:00, 11389.56 examples/s] Map: 37%|███▋ | 4000/10838 [00:00<00:00, 12180.07 examples/s] Map: 55%|█████▌ | 6000/10838 [00:00<00:00, 11530.39 examples/s] Map: 74%|███████▍ | 8000/10838 [00:00<00:00, 11296.70 examples/s] Map: 92%|█████████▏| 10000/10838 [00:00<00:00, 10940.20 examples/s] Map: 100%|██████████| 10838/10838 [00:00<00:00, 11069.64 examples/s] | |
| /content/dissertation/scripts/ner/run_ner_train.py:397: FutureWarning: load_metric is deprecated and will be removed in the next major version of datasets. Use 'evaluate.load' instead, from the new library 🤗 Evaluate: https://huggingface.co/docs/evaluate | |
| metric = load_metric("seqeval", trust_remote_code=True) | |
| Downloading builder script: 0%| | 0.00/2.47k [00:00<?, ?B/s] Downloading builder script: 6.33kB [00:00, 11.4MB/s] | |
| [INFO|trainer.py:811] 2024-09-05 21:40:58,780 >> The following columns in the training set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: tokens, id, ner_tags. If tokens, id, ner_tags are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. | |
| [INFO|trainer.py:2134] 2024-09-05 21:40:59,480 >> ***** Running training ***** | |
| [INFO|trainer.py:2135] 2024-09-05 21:40:59,480 >> Num examples = 32,675 | |
| [INFO|trainer.py:2136] 2024-09-05 21:40:59,480 >> Num Epochs = 10 | |
| [INFO|trainer.py:2137] 2024-09-05 21:40:59,480 >> Instantaneous batch size per device = 32 | |
| [INFO|trainer.py:2140] 2024-09-05 21:40:59,480 >> Total train batch size (w. parallel, distributed & accumulation) = 64 | |
| [INFO|trainer.py:2141] 2024-09-05 21:40:59,480 >> Gradient Accumulation steps = 2 | |
| [INFO|trainer.py:2142] 2024-09-05 21:40:59,480 >> Total optimization steps = 5,110 | |
| [INFO|trainer.py:2143] 2024-09-05 21:40:59,481 >> Number of trainable parameters = 124,055,043 | |
| 0%| | 0/5110 [00:00<?, ?it/s] 0%| | 1/5110 [00:01<2:22:16, 1.67s/it] 0%| | 2/5110 [00:01<1:12:02, 1.18it/s] 0%| | 3/5110 [00:02<51:48, 1.64it/s] 0%| | 4/5110 [00:02<42:49, 1.99it/s] 0%| | 5/5110 [00:02<35:27, 2.40it/s] 0%| | 6/5110 [00:03<29:48, 2.85it/s] 0%| | 7/5110 [00:03<26:22, 3.23it/s] 0%| | 8/5110 [00:03<26:23, 3.22it/s] 0%| | 9/5110 [00:03<24:08, 3.52it/s] 0%| | 10/5110 [00:04<22:29, 3.78it/s] 0%| | 11/5110 [00:04<20:26, 4.16it/s] 0%| | 12/5110 [00:04<19:25, 4.38it/s] 0%| | 13/5110 [00:04<19:27, 4.36it/s] 0%| | 14/5110 [00:04<19:14, 4.41it/s] 0%| | 15/5110 [00:05<18:27, 4.60it/s] 0%| | 16/5110 [00:05<20:35, 4.12it/s] 0%| | 17/5110 [00:05<19:37, 4.33it/s] 0%| | 18/5110 [00:05<21:44, 3.90it/s] 0%| | 19/5110 [00:06<21:31, 3.94it/s] 0%| | 20/5110 [00:06<20:50, 4.07it/s] 0%| | 21/5110 [00:06<21:23, 3.97it/s] 0%| | 22/5110 [00:06<19:54, 4.26it/s] 0%| | 23/5110 [00:07<22:20, 3.80it/s] 0%| | 24/5110 [00:07<21:32, 3.94it/s] 0%| | 25/5110 [00:07<27:32, 3.08it/s] 1%| | 26/5110 [00:08<24:48, 3.42it/s] 1%| | 27/5110 [00:08<23:09, 3.66it/s] 1%| | 28/5110 [00:08<23:31, 3.60it/s] 1%| | 29/5110 [00:08<21:05, 4.01it/s] 1%| | 30/5110 [00:09<20:35, 4.11it/s] 1%| | 31/5110 [00:09<20:16, 4.18it/s] 1%| | 32/5110 [00:09<23:35, 3.59it/s] 1%| | 33/5110 [00:09<22:53, 3.70it/s] 1%| | 34/5110 [00:10<21:39, 3.90it/s] 1%| | 35/5110 [00:10<20:49, 4.06it/s] 1%| | 36/5110 [00:10<20:26, 4.14it/s] 1%| | 37/5110 [00:10<20:28, 4.13it/s] 1%| | 38/5110 [00:11<23:16, 3.63it/s] 1%| | 39/5110 [00:11<23:30, 3.59it/s] 1%| | 40/5110 [00:11<25:11, 3.35it/s] 1%| | 41/5110 [00:12<23:40, 3.57it/s] 1%| | 42/5110 [00:12<22:36, 3.74it/s] 1%| | 43/5110 [00:12<21:40, 3.90it/s] 1%| | 44/5110 [00:12<20:08, 4.19it/s] 1%| | 45/5110 [00:12<19:09, 4.41it/s] 1%| | 46/5110 [00:13<17:38, 4.79it/s] 1%| | 47/5110 [00:13<17:27, 4.83it/s] 1%| | 48/5110 [00:13<17:53, 4.71it/s] 1%| | 49/5110 [00:13<18:41, 4.51it/s] 1%| | 50/5110 [00:14<19:20, 4.36it/s] 1%| | 51/5110 [00:14<18:50, 4.48it/s] 1%| | 52/5110 [00:14<18:47, 4.49it/s] 1%| | 53/5110 [00:14<18:22, 4.58it/s] 1%| | 54/5110 [00:14<18:09, 4.64it/s] 1%| | 55/5110 [00:15<19:24, 4.34it/s] 1%| | 56/5110 [00:15<19:16, 4.37it/s] 1%| | 57/5110 [00:15<19:11, 4.39it/s] 1%| | 58/5110 [00:15<19:34, 4.30it/s] 1%| | 59/5110 [00:16<19:07, 4.40it/s] 1%| | 60/5110 [00:16<20:20, 4.14it/s] 1%| | 61/5110 [00:16<20:34, 4.09it/s] 1%| | 62/5110 [00:16<19:34, 4.30it/s] 1%| | 63/5110 [00:16<18:46, 4.48it/s] 1%|▏ | 64/5110 [00:17<20:44, 4.05it/s] 1%|▏ | 65/5110 [00:17<19:58, 4.21it/s] 1%|▏ | 66/5110 [00:17<19:55, 4.22it/s] 1%|▏ | 67/5110 [00:17<19:10, 4.38it/s] 1%|▏ | 68/5110 [00:18<20:21, 4.13it/s] 1%|▏ | 69/5110 [00:18<20:41, 4.06it/s] 1%|▏ | 70/5110 [00:18<21:37, 3.89it/s] 1%|▏ | 71/5110 [00:18<19:58, 4.20it/s] 1%|▏ | 72/5110 [00:19<19:39, 4.27it/s] 1%|▏ | 73/5110 [00:19<19:53, 4.22it/s] 1%|▏ | 74/5110 [00:19<18:03, 4.65it/s] 1%|▏ | 75/5110 [00:19<18:01, 4.65it/s] 1%|▏ | 76/5110 [00:20<20:30, 4.09it/s] 2%|▏ | 77/5110 [00:20<20:54, 4.01it/s] 2%|▏ | 78/5110 [00:20<20:50, 4.02it/s] 2%|▏ | 79/5110 [00:20<20:27, 4.10it/s] 2%|▏ | 80/5110 [00:21<18:56, 4.43it/s] 2%|▏ | 81/5110 [00:21<19:44, 4.25it/s] 2%|▏ | 82/5110 [00:21<19:13, 4.36it/s] 2%|▏ | 83/5110 [00:21<20:03, 4.18it/s] 2%|▏ | 84/5110 [00:22<20:20, 4.12it/s] 2%|▏ | 85/5110 [00:22<19:06, 4.38it/s] 2%|▏ | 86/5110 [00:22<19:03, 4.39it/s] 2%|▏ | 87/5110 [00:22<19:49, 4.22it/s] 2%|▏ | 88/5110 [00:22<19:10, 4.36it/s] 2%|▏ | 89/5110 [00:23<18:24, 4.55it/s] 2%|▏ | 90/5110 [00:23<19:29, 4.29it/s] 2%|▏ | 91/5110 [00:23<20:42, 4.04it/s] 2%|▏ | 92/5110 [00:23<21:05, 3.97it/s] 2%|▏ | 93/5110 [00:24<19:11, 4.36it/s] 2%|▏ | 94/5110 [00:24<18:16, 4.57it/s] 2%|▏ | 95/5110 [00:24<17:27, 4.79it/s] 2%|▏ | 96/5110 [00:24<17:39, 4.73it/s] 2%|▏ | 97/5110 [00:25<22:22, 3.73it/s] 2%|▏ | 98/5110 [00:25<22:08, 3.77it/s] 2%|▏ | 99/5110 [00:25<20:44, 4.03it/s] 2%|▏ | 100/5110 [00:25<18:44, 4.46it/s] 2%|▏ | 101/5110 [00:25<19:17, 4.33it/s] 2%|▏ | 102/5110 [00:26<17:52, 4.67it/s] 2%|▏ | 103/5110 [00:26<18:09, 4.60it/s] 2%|▏ | 104/5110 [00:26<18:52, 4.42it/s] 2%|▏ | 105/5110 [00:26<18:15, 4.57it/s] 2%|▏ | 106/5110 [00:27<19:02, 4.38it/s] 2%|▏ | 107/5110 [00:27<19:42, 4.23it/s] 2%|▏ | 108/5110 [00:27<18:44, 4.45it/s] 2%|▏ | 109/5110 [00:27<19:45, 4.22it/s] 2%|▏ | 110/5110 [00:28<19:40, 4.24it/s] 2%|▏ | 111/5110 [00:28<19:16, 4.32it/s] 2%|▏ | 112/5110 [00:28<21:26, 3.89it/s] 2%|▏ | 113/5110 [00:28<20:37, 4.04it/s] 2%|▏ | 114/5110 [00:28<19:52, 4.19it/s] 2%|▏ | 115/5110 [00:29<19:01, 4.38it/s] 2%|▏ | 116/5110 [00:29<19:00, 4.38it/s] 2%|▏ | 117/5110 [00:29<18:27, 4.51it/s] 2%|▏ | 118/5110 [00:29<18:57, 4.39it/s] 2%|▏ | 119/5110 [00:30<19:49, 4.19it/s] 2%|▏ | 120/5110 [00:30<18:10, 4.58it/s] 2%|▏ | 121/5110 [00:30<17:14, 4.82it/s] 2%|▏ | 122/5110 [00:30<17:50, 4.66it/s] 2%|▏ | 123/5110 [00:31<19:53, 4.18it/s] 2%|▏ | 124/5110 [00:31<19:31, 4.26it/s] 2%|▏ | 125/5110 [00:31<20:17, 4.09it/s] 2%|▏ | 126/5110 [00:31<21:55, 3.79it/s] 2%|▏ | 127/5110 [00:32<22:13, 3.74it/s] 3%|▎ | 128/5110 [00:32<21:10, 3.92it/s] 3%|▎ | 129/5110 [00:32<19:12, 4.32it/s] 3%|▎ | 130/5110 [00:32<18:52, 4.40it/s] 3%|▎ | 131/5110 [00:32<19:11, 4.32it/s] 3%|▎ | 132/5110 [00:33<19:09, 4.33it/s] 3%|▎ | 133/5110 [00:33<17:42, 4.68it/s] 3%|▎ | 134/5110 [00:33<17:57, 4.62it/s] 3%|▎ | 135/5110 [00:33<17:18, 4.79it/s] 3%|▎ | 136/5110 [00:33<17:22, 4.77it/s] 3%|▎ | 137/5110 [00:34<17:32, 4.73it/s] 3%|▎ | 138/5110 [00:34<18:00, 4.60it/s] 3%|▎ | 139/5110 [00:34<19:09, 4.33it/s] 3%|▎ | 140/5110 [00:34<19:46, 4.19it/s] 3%|▎ | 141/5110 [00:35<20:11, 4.10it/s] 3%|▎ | 142/5110 [00:35<19:14, 4.30it/s] 3%|▎ | 143/5110 [00:35<20:28, 4.04it/s] 3%|▎ | 144/5110 [00:35<20:35, 4.02it/s] 3%|▎ | 145/5110 [00:36<22:23, 3.70it/s] 3%|▎ | 146/5110 [00:36<22:38, 3.66it/s] 3%|▎ | 147/5110 [00:36<20:36, 4.02it/s] 3%|▎ | 148/5110 [00:37<21:20, 3.88it/s] 3%|▎ | 149/5110 [00:37<19:31, 4.24it/s] 3%|▎ | 150/5110 [00:37<20:03, 4.12it/s] 3%|▎ | 151/5110 [00:37<18:57, 4.36it/s] 3%|▎ | 152/5110 [00:37<17:45, 4.65it/s] 3%|▎ | 153/5110 [00:38<20:25, 4.04it/s] 3%|▎ | 154/5110 [00:38<20:09, 4.10it/s] 3%|▎ | 155/5110 [00:38<18:46, 4.40it/s] 3%|▎ | 156/5110 [00:38<23:15, 3.55it/s] 3%|▎ | 157/5110 [00:39<22:50, 3.61it/s] 3%|▎ | 158/5110 [00:39<21:13, 3.89it/s] 3%|▎ | 159/5110 [00:39<20:02, 4.12it/s] 3%|▎ | 160/5110 [00:39<19:17, 4.28it/s] 3%|▎ | 161/5110 [00:40<18:09, 4.54it/s] 3%|▎ | 162/5110 [00:40<17:42, 4.66it/s] 3%|▎ | 163/5110 [00:40<18:00, 4.58it/s] 3%|▎ | 164/5110 [00:40<18:38, 4.42it/s] 3%|▎ | 165/5110 [00:41<20:00, 4.12it/s] 3%|▎ | 166/5110 [00:41<20:14, 4.07it/s] 3%|▎ | 167/5110 [00:41<20:25, 4.03it/s] 3%|▎ | 168/5110 [00:41<19:48, 4.16it/s] 3%|▎ | 169/5110 [00:41<18:47, 4.38it/s] 3%|▎ | 170/5110 [00:42<18:03, 4.56it/s] 3%|▎ | 171/5110 [00:42<19:15, 4.28it/s] 3%|▎ | 172/5110 [00:42<22:48, 3.61it/s] 3%|▎ | 173/5110 [00:43<22:11, 3.71it/s] 3%|▎ | 174/5110 [00:43<22:03, 3.73it/s] 3%|▎ | 175/5110 [00:43<23:20, 3.52it/s] 3%|▎ | 176/5110 [00:43<22:14, 3.70it/s] 3%|▎ | 177/5110 [00:44<21:59, 3.74it/s] 3%|▎ | 178/5110 [00:44<23:16, 3.53it/s] 4%|▎ | 179/5110 [00:44<22:42, 3.62it/s] 4%|▎ | 180/5110 [00:44<20:57, 3.92it/s] 4%|▎ | 181/5110 [00:45<20:48, 3.95it/s] 4%|▎ | 182/5110 [00:45<19:46, 4.15it/s] 4%|▎ | 183/5110 [00:45<18:18, 4.49it/s] 4%|▎ | 184/5110 [00:45<18:08, 4.53it/s] 4%|▎ | 185/5110 [00:45<17:23, 4.72it/s] 4%|▎ | 186/5110 [00:46<19:02, 4.31it/s] 4%|▎ | 187/5110 [00:46<19:06, 4.29it/s] 4%|▎ | 188/5110 [00:46<18:28, 4.44it/s] 4%|▎ | 189/5110 [00:46<19:41, 4.16it/s] 4%|▎ | 190/5110 [00:47<19:03, 4.30it/s] 4%|▎ | 191/5110 [00:47<20:21, 4.03it/s] 4%|▍ | 192/5110 [00:47<19:30, 4.20it/s] 4%|▍ | 193/5110 [00:47<19:53, 4.12it/s] 4%|▍ | 194/5110 [00:48<19:16, 4.25it/s] 4%|▍ | 195/5110 [00:48<18:41, 4.38it/s] 4%|▍ | 196/5110 [00:48<19:27, 4.21it/s] 4%|▍ | 197/5110 [00:48<20:29, 4.00it/s] 4%|▍ | 198/5110 [00:49<20:30, 3.99it/s] 4%|▍ | 199/5110 [00:49<19:42, 4.15it/s] 4%|▍ | 200/5110 [00:49<19:05, 4.29it/s] 4%|▍ | 201/5110 [00:49<20:02, 4.08it/s] 4%|▍ | 202/5110 [00:50<21:39, 3.78it/s] 4%|▍ | 203/5110 [00:50<23:32, 3.47it/s] 4%|▍ | 204/5110 [00:50<22:56, 3.56it/s] 4%|▍ | 205/5110 [00:51<22:13, 3.68it/s] 4%|▍ | 206/5110 [00:51<20:43, 3.94it/s] 4%|▍ | 207/5110 [00:51<21:00, 3.89it/s] 4%|▍ | 208/5110 [00:51<19:29, 4.19it/s] 4%|▍ | 209/5110 [00:52<21:09, 3.86it/s] 4%|▍ | 210/5110 [00:52<21:22, 3.82it/s] 4%|▍ | 211/5110 [00:52<19:42, 4.14it/s] 4%|▍ | 212/5110 [00:52<19:52, 4.11it/s] 4%|▍ | 213/5110 [00:52<20:33, 3.97it/s] 4%|▍ | 214/5110 [00:53<22:35, 3.61it/s] 4%|▍ | 215/5110 [00:53<21:00, 3.88it/s] 4%|▍ | 216/5110 [00:53<19:08, 4.26it/s] 4%|▍ | 217/5110 [00:53<18:10, 4.49it/s] 4%|▍ | 218/5110 [00:54<17:28, 4.67it/s] 4%|▍ | 219/5110 [00:54<18:50, 4.32it/s] 4%|▍ | 220/5110 [00:54<18:49, 4.33it/s] 4%|▍ | 221/5110 [00:54<18:48, 4.33it/s] 4%|▍ | 222/5110 [00:55<17:48, 4.58it/s] 4%|▍ | 223/5110 [00:55<16:47, 4.85it/s] 4%|▍ | 224/5110 [00:55<16:24, 4.96it/s] 4%|▍ | 225/5110 [00:55<18:26, 4.41it/s] 4%|▍ | 226/5110 [00:55<18:48, 4.33it/s] 4%|▍ | 227/5110 [00:56<19:49, 4.10it/s] 4%|▍ | 228/5110 [00:56<19:25, 4.19it/s] 4%|▍ | 229/5110 [00:56<18:18, 4.44it/s] 5%|▍ | 230/5110 [00:56<19:17, 4.22it/s] 5%|▍ | 231/5110 [00:57<19:19, 4.21it/s] 5%|▍ | 232/5110 [00:57<18:51, 4.31it/s] 5%|▍ | 233/5110 [00:57<19:09, 4.24it/s] 5%|▍ | 234/5110 [00:57<22:39, 3.59it/s] 5%|▍ | 235/5110 [00:58<23:33, 3.45it/s] 5%|▍ | 236/5110 [00:58<23:42, 3.43it/s] 5%|▍ | 237/5110 [00:58<22:35, 3.60it/s] 5%|▍ | 238/5110 [00:59<20:25, 3.98it/s] 5%|▍ | 239/5110 [00:59<20:33, 3.95it/s] 5%|▍ | 240/5110 [00:59<20:43, 3.92it/s] 5%|▍ | 241/5110 [00:59<21:53, 3.71it/s] 5%|▍ | 242/5110 [01:00<20:57, 3.87it/s] 5%|▍ | 243/5110 [01:00<23:51, 3.40it/s] 5%|▍ | 244/5110 [01:00<20:42, 3.92it/s] 5%|▍ | 245/5110 [01:00<21:21, 3.80it/s] 5%|▍ | 246/5110 [01:01<24:39, 3.29it/s] 5%|▍ | 247/5110 [01:01<23:14, 3.49it/s] 5%|▍ | 248/5110 [01:01<22:24, 3.62it/s] 5%|▍ | 249/5110 [01:02<23:12, 3.49it/s] 5%|▍ | 250/5110 [01:02<21:33, 3.76it/s] 5%|▍ | 251/5110 [01:02<20:11, 4.01it/s] 5%|▍ | 252/5110 [01:02<19:47, 4.09it/s] 5%|▍ | 253/5110 [01:02<18:34, 4.36it/s] 5%|▍ | 254/5110 [01:03<17:52, 4.53it/s] 5%|▍ | 255/5110 [01:03<17:25, 4.64it/s] 5%|▌ | 256/5110 [01:03<18:18, 4.42it/s] 5%|▌ | 257/5110 [01:03<18:36, 4.35it/s] 5%|▌ | 258/5110 [01:04<18:14, 4.43it/s] 5%|▌ | 259/5110 [01:04<17:51, 4.53it/s] 5%|▌ | 260/5110 [01:04<17:48, 4.54it/s] 5%|▌ | 261/5110 [01:04<18:08, 4.46it/s] 5%|▌ | 262/5110 [01:05<19:23, 4.17it/s] 5%|▌ | 263/5110 [01:05<18:11, 4.44it/s] 5%|▌ | 264/5110 [01:05<18:35, 4.34it/s] 5%|▌ | 265/5110 [01:05<20:47, 3.88it/s] 5%|▌ | 266/5110 [01:06<20:20, 3.97it/s] 5%|▌ | 267/5110 [01:06<19:45, 4.09it/s] 5%|▌ | 268/5110 [01:06<19:14, 4.19it/s] 5%|▌ | 269/5110 [01:06<17:44, 4.55it/s] 5%|▌ | 270/5110 [01:06<18:16, 4.42it/s] 5%|▌ | 271/5110 [01:07<17:57, 4.49it/s] 5%|▌ | 272/5110 [01:07<18:26, 4.37it/s] 5%|▌ | 273/5110 [01:07<17:19, 4.65it/s] 5%|▌ | 274/5110 [01:07<17:32, 4.60it/s] 5%|▌ | 275/5110 [01:07<17:27, 4.62it/s] 5%|▌ | 276/5110 [01:08<16:29, 4.89it/s] 5%|▌ | 277/5110 [01:08<18:20, 4.39it/s] 5%|▌ | 278/5110 [01:08<17:23, 4.63it/s] 5%|▌ | 279/5110 [01:08<19:30, 4.13it/s] 5%|▌ | 280/5110 [01:09<19:06, 4.21it/s] 5%|▌ | 281/5110 [01:09<20:17, 3.97it/s] 6%|▌ | 282/5110 [01:09<19:39, 4.09it/s] 6%|▌ | 283/5110 [01:09<20:23, 3.95it/s] 6%|▌ | 284/5110 [01:10<18:57, 4.24it/s] 6%|▌ | 285/5110 [01:10<18:55, 4.25it/s] 6%|▌ | 286/5110 [01:10<18:58, 4.24it/s] 6%|▌ | 287/5110 [01:10<18:44, 4.29it/s] 6%|▌ | 288/5110 [01:11<19:08, 4.20it/s] 6%|▌ | 289/5110 [01:11<18:27, 4.35it/s] 6%|▌ | 290/5110 [01:11<18:38, 4.31it/s] 6%|▌ | 291/5110 [01:11<18:57, 4.23it/s] 6%|▌ | 292/5110 [01:12<19:24, 4.14it/s] 6%|▌ | 293/5110 [01:12<19:26, 4.13it/s] 6%|▌ | 294/5110 [01:12<21:31, 3.73it/s] 6%|▌ | 295/5110 [01:12<20:44, 3.87it/s] 6%|▌ | 296/5110 [01:13<19:15, 4.17it/s] 6%|▌ | 297/5110 [01:13<18:16, 4.39it/s] 6%|▌ | 298/5110 [01:13<17:46, 4.51it/s] 6%|▌ | 299/5110 [01:13<17:36, 4.56it/s] 6%|▌ | 300/5110 [01:13<18:00, 4.45it/s] 6%|▌ | 301/5110 [01:14<18:01, 4.45it/s] 6%|▌ | 302/5110 [01:14<18:53, 4.24it/s] 6%|▌ | 303/5110 [01:14<18:06, 4.42it/s] 6%|▌ | 304/5110 [01:14<17:02, 4.70it/s] 6%|▌ | 305/5110 [01:14<16:42, 4.79it/s] 6%|▌ | 306/5110 [01:15<16:42, 4.79it/s] 6%|▌ | 307/5110 [01:15<15:50, 5.05it/s] 6%|▌ | 308/5110 [01:15<15:37, 5.12it/s] 6%|▌ | 309/5110 [01:15<16:48, 4.76it/s] 6%|▌ | 310/5110 [01:15<17:15, 4.64it/s] 6%|▌ | 311/5110 [01:16<16:50, 4.75it/s] 6%|▌ | 312/5110 [01:16<16:51, 4.74it/s] 6%|▌ | 313/5110 [01:16<18:00, 4.44it/s] 6%|▌ | 314/5110 [01:16<17:19, 4.61it/s] 6%|▌ | 315/5110 [01:17<16:56, 4.72it/s] 6%|▌ | 316/5110 [01:17<16:53, 4.73it/s] 6%|▌ | 317/5110 [01:17<17:01, 4.69it/s] 6%|▌ | 318/5110 [01:17<16:36, 4.81it/s] 6%|▌ | 319/5110 [01:17<17:25, 4.58it/s] 6%|▋ | 320/5110 [01:18<17:41, 4.51it/s] 6%|▋ | 321/5110 [01:18<17:29, 4.56it/s] 6%|▋ | 322/5110 [01:18<17:26, 4.58it/s] 6%|▋ | 323/5110 [01:18<17:22, 4.59it/s] 6%|▋ | 324/5110 [01:19<18:04, 4.42it/s] 6%|▋ | 325/5110 [01:19<18:21, 4.34it/s] 6%|▋ | 326/5110 [01:19<18:41, 4.27it/s] 6%|▋ | 327/5110 [01:19<19:30, 4.09it/s] 6%|▋ | 328/5110 [01:19<18:14, 4.37it/s] 6%|▋ | 329/5110 [01:20<17:25, 4.57it/s] 6%|▋ | 330/5110 [01:20<16:54, 4.71it/s] 6%|▋ | 331/5110 [01:20<18:19, 4.35it/s] 6%|▋ | 332/5110 [01:20<18:10, 4.38it/s] 7%|▋ | 333/5110 [01:21<17:23, 4.58it/s] 7%|▋ | 334/5110 [01:21<21:38, 3.68it/s] 7%|▋ | 335/5110 [01:21<20:50, 3.82it/s] 7%|▋ | 336/5110 [01:21<21:36, 3.68it/s] 7%|▋ | 337/5110 [01:22<20:28, 3.89it/s] 7%|▋ | 338/5110 [01:22<19:46, 4.02it/s] 7%|▋ | 339/5110 [01:22<19:29, 4.08it/s] 7%|▋ | 340/5110 [01:22<18:18, 4.34it/s] 7%|▋ | 341/5110 [01:23<18:27, 4.31it/s] 7%|▋ | 342/5110 [01:23<17:18, 4.59it/s] 7%|▋ | 343/5110 [01:23<17:55, 4.43it/s] 7%|▋ | 344/5110 [01:23<19:35, 4.05it/s] 7%|▋ | 345/5110 [01:24<18:48, 4.22it/s] 7%|▋ | 346/5110 [01:24<19:01, 4.17it/s] 7%|▋ | 347/5110 [01:24<19:01, 4.17it/s] 7%|▋ | 348/5110 [01:24<19:28, 4.08it/s] 7%|▋ | 349/5110 [01:25<20:43, 3.83it/s] 7%|▋ | 350/5110 [01:25<19:11, 4.13it/s] 7%|▋ | 351/5110 [01:25<18:25, 4.30it/s] 7%|▋ | 352/5110 [01:25<19:25, 4.08it/s] 7%|▋ | 353/5110 [01:26<19:23, 4.09it/s] 7%|▋ | 354/5110 [01:26<20:57, 3.78it/s] 7%|▋ | 355/5110 [01:26<19:32, 4.06it/s] 7%|▋ | 356/5110 [01:26<19:10, 4.13it/s] 7%|▋ | 357/5110 [01:27<19:14, 4.12it/s] 7%|▋ | 358/5110 [01:27<18:54, 4.19it/s] 7%|▋ | 359/5110 [01:27<18:48, 4.21it/s] 7%|▋ | 360/5110 [01:27<18:41, 4.24it/s] 7%|▋ | 361/5110 [01:28<20:02, 3.95it/s] 7%|▋ | 362/5110 [01:28<21:10, 3.74it/s] 7%|▋ | 363/5110 [01:28<20:45, 3.81it/s] 7%|▋ | 364/5110 [01:28<20:42, 3.82it/s] 7%|▋ | 365/5110 [01:29<19:26, 4.07it/s] 7%|▋ | 366/5110 [01:29<20:55, 3.78it/s] 7%|▋ | 367/5110 [01:29<19:41, 4.01it/s] 7%|▋ | 368/5110 [01:29<20:05, 3.93it/s] 7%|▋ | 369/5110 [01:30<19:21, 4.08it/s] 7%|▋ | 370/5110 [01:30<19:10, 4.12it/s] 7%|▋ | 371/5110 [01:30<18:21, 4.30it/s] 7%|▋ | 372/5110 [01:30<17:59, 4.39it/s] 7%|▋ | 373/5110 [01:31<20:23, 3.87it/s] 7%|▋ | 374/5110 [01:31<19:08, 4.12it/s] 7%|▋ | 375/5110 [01:31<19:38, 4.02it/s] 7%|▋ | 376/5110 [01:31<20:23, 3.87it/s] 7%|▋ | 377/5110 [01:32<20:24, 3.87it/s] 7%|▋ | 378/5110 [01:32<21:52, 3.60it/s] 7%|▋ | 379/5110 [01:32<19:53, 3.96it/s] 7%|▋ | 380/5110 [01:32<18:59, 4.15it/s] 7%|▋ | 381/5110 [01:32<17:32, 4.49it/s] 7%|▋ | 382/5110 [01:33<18:13, 4.32it/s] 7%|▋ | 383/5110 [01:33<20:03, 3.93it/s] 8%|▊ | 384/5110 [01:33<18:50, 4.18it/s] 8%|▊ | 385/5110 [01:33<18:33, 4.24it/s] 8%|▊ | 386/5110 [01:34<18:51, 4.18it/s] 8%|▊ | 387/5110 [01:34<18:45, 4.20it/s] 8%|▊ | 388/5110 [01:34<19:19, 4.07it/s] 8%|▊ | 389/5110 [01:34<18:15, 4.31it/s] 8%|▊ | 390/5110 [01:35<17:07, 4.59it/s] 8%|▊ | 391/5110 [01:35<16:22, 4.80it/s] 8%|▊ | 392/5110 [01:35<17:21, 4.53it/s] 8%|▊ | 393/5110 [01:35<18:45, 4.19it/s] 8%|▊ | 394/5110 [01:35<17:50, 4.41it/s] 8%|▊ | 395/5110 [01:36<16:20, 4.81it/s] 8%|▊ | 396/5110 [01:36<17:09, 4.58it/s] 8%|▊ | 397/5110 [01:36<16:42, 4.70it/s] 8%|▊ | 398/5110 [01:36<19:24, 4.05it/s] 8%|▊ | 399/5110 [01:37<18:06, 4.34it/s] 8%|▊ | 400/5110 [01:37<17:10, 4.57it/s] 8%|▊ | 401/5110 [01:37<16:11, 4.85it/s] 8%|▊ | 402/5110 [01:37<15:31, 5.05it/s] 8%|▊ | 403/5110 [01:37<16:22, 4.79it/s] 8%|▊ | 404/5110 [01:38<18:42, 4.19it/s] 8%|▊ | 405/5110 [01:38<18:00, 4.35it/s] 8%|▊ | 406/5110 [01:38<18:01, 4.35it/s] 8%|▊ | 407/5110 [01:38<18:11, 4.31it/s] 8%|▊ | 408/5110 [01:39<17:29, 4.48it/s] 8%|▊ | 409/5110 [01:39<19:44, 3.97it/s] 8%|▊ | 410/5110 [01:39<18:19, 4.27it/s] 8%|▊ | 411/5110 [01:39<20:42, 3.78it/s] 8%|▊ | 412/5110 [01:40<18:37, 4.20it/s] 8%|▊ | 413/5110 [01:40<17:57, 4.36it/s] 8%|▊ | 414/5110 [01:40<18:08, 4.31it/s] 8%|▊ | 415/5110 [01:40<18:35, 4.21it/s] 8%|▊ | 416/5110 [01:41<18:17, 4.28it/s] 8%|▊ | 417/5110 [01:41<18:06, 4.32it/s] 8%|▊ | 418/5110 [01:41<17:28, 4.47it/s] 8%|▊ | 419/5110 [01:41<19:48, 3.95it/s] 8%|▊ | 420/5110 [01:41<19:07, 4.09it/s] 8%|▊ | 421/5110 [01:42<20:14, 3.86it/s] 8%|▊ | 422/5110 [01:42<19:21, 4.04it/s] 8%|▊ | 423/5110 [01:42<18:30, 4.22it/s] 8%|▊ | 424/5110 [01:42<18:36, 4.20it/s] 8%|▊ | 425/5110 [01:43<17:52, 4.37it/s] 8%|▊ | 426/5110 [01:43<18:07, 4.31it/s] 8%|▊ | 427/5110 [01:43<19:34, 3.99it/s] 8%|▊ | 428/5110 [01:43<19:33, 3.99it/s] 8%|▊ | 429/5110 [01:44<19:26, 4.01it/s] 8%|▊ | 430/5110 [01:44<19:03, 4.09it/s] 8%|▊ | 431/5110 [01:44<20:21, 3.83it/s] 8%|▊ | 432/5110 [01:44<19:23, 4.02it/s] 8%|▊ | 433/5110 [01:45<17:33, 4.44it/s] 8%|▊ | 434/5110 [01:45<17:16, 4.51it/s] 9%|▊ | 435/5110 [01:45<18:13, 4.28it/s] 9%|▊ | 436/5110 [01:45<17:17, 4.50it/s] 9%|▊ | 437/5110 [01:46<20:06, 3.87it/s] 9%|▊ | 438/5110 [01:46<18:47, 4.14it/s] 9%|▊ | 439/5110 [01:46<18:15, 4.26it/s] 9%|▊ | 440/5110 [01:46<17:16, 4.50it/s] 9%|▊ | 441/5110 [01:46<17:11, 4.53it/s] 9%|▊ | 442/5110 [01:47<17:03, 4.56it/s] 9%|▊ | 443/5110 [01:47<16:58, 4.58it/s] 9%|▊ | 444/5110 [01:47<18:27, 4.21it/s] 9%|▊ | 445/5110 [01:47<18:27, 4.21it/s] 9%|▊ | 446/5110 [01:48<18:10, 4.28it/s] 9%|▊ | 447/5110 [01:48<19:21, 4.02it/s] 9%|▉ | 448/5110 [01:48<17:55, 4.33it/s] 9%|▉ | 449/5110 [01:48<17:54, 4.34it/s] 9%|▉ | 450/5110 [01:49<18:09, 4.28it/s] 9%|▉ | 451/5110 [01:49<17:21, 4.47it/s] 9%|▉ | 452/5110 [01:49<17:32, 4.43it/s] 9%|▉ | 453/5110 [01:49<18:36, 4.17it/s] 9%|▉ | 454/5110 [01:50<17:53, 4.34it/s] 9%|▉ | 455/5110 [01:50<17:36, 4.41it/s] 9%|▉ | 456/5110 [01:50<16:56, 4.58it/s] 9%|▉ | 457/5110 [01:50<16:07, 4.81it/s] 9%|▉ | 458/5110 [01:50<18:38, 4.16it/s] 9%|▉ | 459/5110 [01:51<17:21, 4.47it/s] 9%|▉ | 460/5110 [01:51<17:29, 4.43it/s] 9%|▉ | 461/5110 [01:51<16:23, 4.73it/s] 9%|▉ | 462/5110 [01:51<16:37, 4.66it/s] 9%|▉ | 463/5110 [01:51<16:45, 4.62it/s] 9%|▉ | 464/5110 [01:52<17:03, 4.54it/s] 9%|▉ | 465/5110 [01:52<17:45, 4.36it/s] 9%|▉ | 466/5110 [01:52<17:18, 4.47it/s] 9%|▉ | 467/5110 [01:52<18:32, 4.17it/s] 9%|▉ | 468/5110 [01:53<17:48, 4.34it/s] 9%|▉ | 469/5110 [01:53<17:39, 4.38it/s] 9%|▉ | 470/5110 [01:53<17:40, 4.38it/s] 9%|▉ | 471/5110 [01:53<16:34, 4.67it/s] 9%|▉ | 472/5110 [01:53<16:19, 4.74it/s] 9%|▉ | 473/5110 [01:54<16:53, 4.58it/s] 9%|▉ | 474/5110 [01:54<17:21, 4.45it/s] 9%|▉ | 475/5110 [01:54<16:21, 4.72it/s] 9%|▉ | 476/5110 [01:54<17:58, 4.30it/s] 9%|▉ | 477/5110 [01:55<17:04, 4.52it/s] 9%|▉ | 478/5110 [01:55<16:11, 4.77it/s] 9%|▉ | 479/5110 [01:55<17:09, 4.50it/s] 9%|▉ | 480/5110 [01:55<17:22, 4.44it/s] 9%|▉ | 481/5110 [01:56<17:44, 4.35it/s] 9%|▉ | 482/5110 [01:56<18:01, 4.28it/s] 9%|▉ | 483/5110 [01:56<17:27, 4.42it/s] 9%|▉ | 484/5110 [01:56<17:44, 4.35it/s] 9%|▉ | 485/5110 [01:56<18:01, 4.27it/s] 10%|▉ | 486/5110 [01:57<17:27, 4.41it/s] 10%|▉ | 487/5110 [01:57<17:25, 4.42it/s] 10%|▉ | 488/5110 [01:57<16:54, 4.56it/s] 10%|▉ | 489/5110 [01:57<19:23, 3.97it/s] 10%|▉ | 490/5110 [01:58<17:53, 4.30it/s] 10%|▉ | 491/5110 [01:58<17:57, 4.29it/s] 10%|▉ | 492/5110 [01:58<17:20, 4.44it/s] 10%|▉ | 493/5110 [01:58<18:21, 4.19it/s] 10%|▉ | 494/5110 [01:59<17:23, 4.42it/s] 10%|▉ | 495/5110 [01:59<18:03, 4.26it/s] 10%|▉ | 496/5110 [01:59<17:43, 4.34it/s] 10%|▉ | 497/5110 [01:59<18:21, 4.19it/s] 10%|▉ | 498/5110 [01:59<18:25, 4.17it/s] 10%|▉ | 499/5110 [02:00<19:14, 3.99it/s] 10%|▉ | 500/5110 [02:00<18:12, 4.22it/s] 10%|▉ | 500/5110 [02:00<18:12, 4.22it/s] 10%|▉ | 501/5110 [02:00<19:24, 3.96it/s] 10%|▉ | 502/5110 [02:01<19:28, 3.94it/s] 10%|▉ | 503/5110 [02:01<18:31, 4.14it/s] 10%|▉ | 504/5110 [02:01<17:48, 4.31it/s] 10%|▉ | 505/5110 [02:01<17:23, 4.41it/s] 10%|▉ | 506/5110 [02:01<18:47, 4.08it/s] 10%|▉ | 507/5110 [02:02<18:44, 4.09it/s] 10%|▉ | 508/5110 [02:02<17:37, 4.35it/s] 10%|▉ | 509/5110 [02:02<18:05, 4.24it/s] 10%|▉ | 510/5110 [02:02<17:30, 4.38it/s] 10%|█ | 511/5110 [02:02<15:48, 4.85it/s][INFO|trainer.py:811] 2024-09-05 21:43:02,475 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: tokens, id, ner_tags. If tokens, id, ner_tags are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. | |
| [INFO|trainer.py:3819] 2024-09-05 21:43:02,477 >> | |
| ***** Running Evaluation ***** | |
| [INFO|trainer.py:3821] 2024-09-05 21:43:02,477 >> Num examples = 7354 | |
| [INFO|trainer.py:3824] 2024-09-05 21:43:02,477 >> Batch size = 8 | |
| {'loss': 0.0542, 'grad_norm': 0.2284504771232605, 'learning_rate': 4.510763209393347e-05, 'epoch': 0.98} | |
| 0%| | 0/920 [00:00<?, ?it/s][A | |
| 1%| | 9/920 [00:00<00:10, 89.53it/s][A | |
| 2%|▏ | 18/920 [00:00<00:11, 80.67it/s][A | |
| 3%|▎ | 27/920 [00:00<00:11, 80.20it/s][A | |
| 4%|▍ | 36/920 [00:00<00:11, 80.15it/s][A | |
| 5%|▍ | 45/920 [00:00<00:10, 80.03it/s][A | |
| 6%|▌ | 54/920 [00:00<00:11, 75.91it/s][A | |
| 7%|▋ | 62/920 [00:00<00:11, 73.99it/s][A | |
| 8%|▊ | 70/920 [00:00<00:11, 74.77it/s][A | |
| 9%|▊ | 79/920 [00:01<00:10, 77.39it/s][A | |
| 9%|▉ | 87/920 [00:01<00:10, 77.95it/s][A | |
| 10%|█ | 95/920 [00:01<00:10, 77.87it/s][A | |
| 11%|█ | 103/920 [00:01<00:10, 78.49it/s][A | |
| 12%|█▏ | 111/920 [00:01<00:10, 78.11it/s][A | |
| 13%|█▎ | 120/920 [00:01<00:10, 78.92it/s][A | |
| 14%|█▍ | 128/920 [00:01<00:10, 74.71it/s][A | |
| 15%|█▍ | 137/920 [00:01<00:10, 77.16it/s][A | |
| 16%|█▌ | 146/920 [00:01<00:09, 79.00it/s][A | |
| 17%|█▋ | 154/920 [00:01<00:09, 79.03it/s][A | |
| 18%|█▊ | 163/920 [00:02<00:09, 79.61it/s][A | |
| 19%|█▊ | 172/920 [00:02<00:09, 81.23it/s][A | |
| 20%|█▉ | 181/920 [00:02<00:09, 81.86it/s][A | |
| 21%|██ | 190/920 [00:02<00:08, 82.13it/s][A | |
| 22%|██▏ | 199/920 [00:02<00:08, 81.55it/s][A | |
| 23%|██▎ | 208/920 [00:02<00:09, 77.57it/s][A | |
| 24%|██▎ | 217/920 [00:02<00:08, 78.97it/s][A | |
| 24%|██▍ | 225/920 [00:02<00:08, 79.25it/s][A | |
| 25%|██▌ | 234/920 [00:02<00:08, 81.15it/s][A | |
| 26%|██▋ | 243/920 [00:03<00:08, 82.39it/s][A | |
| 27%|██▋ | 252/920 [00:03<00:08, 80.82it/s][A | |
| 28%|██▊ | 261/920 [00:03<00:08, 79.20it/s][A | |
| 29%|██▉ | 269/920 [00:03<00:08, 79.24it/s][A | |
| 30%|███ | 278/920 [00:03<00:07, 80.57it/s][A | |
| 31%|███ | 287/920 [00:03<00:07, 80.61it/s][A | |
| 32%|███▏ | 296/920 [00:03<00:07, 80.74it/s][A | |
| 33%|███▎ | 305/920 [00:03<00:07, 80.19it/s][A | |
| 34%|███▍ | 314/920 [00:03<00:07, 80.93it/s][A | |
| 35%|███▌ | 323/920 [00:04<00:07, 79.78it/s][A | |
| 36%|███▌ | 331/920 [00:04<00:07, 79.02it/s][A | |
| 37%|███▋ | 339/920 [00:04<00:07, 76.52it/s][A | |
| 38%|███▊ | 347/920 [00:04<00:07, 76.64it/s][A | |
| 39%|███▊ | 355/920 [00:04<00:07, 77.24it/s][A | |
| 39%|███▉ | 363/920 [00:04<00:07, 77.76it/s][A | |
| 40%|████ | 372/920 [00:04<00:06, 78.98it/s][A | |
| 41%|████▏ | 381/920 [00:04<00:06, 80.50it/s][A | |
| 42%|████▏ | 390/920 [00:04<00:06, 80.32it/s][A | |
| 43%|████▎ | 399/920 [00:05<00:06, 76.14it/s][A | |
| 44%|████▍ | 407/920 [00:05<00:06, 74.87it/s][A | |
| 45%|████▌ | 416/920 [00:05<00:06, 76.95it/s][A | |
| 46%|████▌ | 425/920 [00:05<00:06, 78.23it/s][A | |
| 47%|████▋ | 434/920 [00:05<00:06, 79.25it/s][A | |
| 48%|████▊ | 443/920 [00:05<00:05, 80.48it/s][A | |
| 49%|████▉ | 452/920 [00:05<00:05, 80.80it/s][A | |
| 50%|█████ | 461/920 [00:05<00:05, 80.93it/s][A | |
| 51%|█████ | 470/920 [00:05<00:05, 80.02it/s][A | |
| 52%|█████▏ | 479/920 [00:06<00:05, 80.23it/s][A | |
| 53%|█████▎ | 488/920 [00:06<00:05, 80.26it/s][A | |
| 54%|█████▍ | 497/920 [00:06<00:05, 80.36it/s][A | |
| 55%|█████▌ | 506/920 [00:06<00:05, 81.30it/s][A | |
| 56%|█████▌ | 515/920 [00:06<00:04, 81.42it/s][A | |
| 57%|█████▋ | 524/920 [00:06<00:04, 81.62it/s][A | |
| 58%|█████▊ | 533/920 [00:06<00:04, 81.99it/s][A | |
| 59%|█████▉ | 542/920 [00:06<00:04, 81.88it/s][A | |
| 60%|█████▉ | 551/920 [00:06<00:04, 78.04it/s][A | |
| 61%|██████ | 559/920 [00:07<00:04, 76.38it/s][A | |
| 62%|██████▏ | 568/920 [00:07<00:04, 77.68it/s][A | |
| 63%|██████▎ | 577/920 [00:07<00:04, 79.04it/s][A | |
| 64%|██████▎ | 585/920 [00:07<00:04, 78.90it/s][A | |
| 65%|██████▍ | 594/920 [00:07<00:04, 80.30it/s][A | |
| 66%|██████▌ | 603/920 [00:07<00:03, 81.40it/s][A | |
| 67%|██████▋ | 612/920 [00:07<00:03, 81.11it/s][A | |
| 68%|██████▊ | 621/920 [00:07<00:03, 79.75it/s][A | |
| 68%|██████▊ | 629/920 [00:07<00:03, 77.84it/s][A | |
| 69%|██████▉ | 637/920 [00:08<00:03, 77.80it/s][A | |
| 70%|███████ | 646/920 [00:08<00:03, 78.99it/s][A | |
| 71%|███████ | 655/920 [00:08<00:03, 79.72it/s][A | |
| 72%|███████▏ | 664/920 [00:08<00:03, 80.67it/s][A | |
| 73%|███████▎ | 673/920 [00:08<00:03, 81.27it/s][A | |
| 74%|███████▍ | 682/920 [00:08<00:02, 82.04it/s][A | |
| 75%|███████▌ | 691/920 [00:08<00:02, 81.85it/s][A | |
| 76%|███████▌ | 700/920 [00:08<00:02, 81.24it/s][A | |
| 77%|███████▋ | 709/920 [00:08<00:02, 80.14it/s][A | |
| 78%|███████▊ | 718/920 [00:09<00:02, 80.64it/s][A | |
| 79%|███████▉ | 727/920 [00:09<00:02, 81.54it/s][A | |
| 80%|████████ | 736/920 [00:09<00:02, 81.40it/s][A | |
| 81%|████████ | 745/920 [00:09<00:02, 77.96it/s][A | |
| 82%|████████▏ | 754/920 [00:09<00:02, 79.48it/s][A | |
| 83%|████████▎ | 762/920 [00:09<00:02, 78.68it/s][A | |
| 84%|████████▍ | 771/920 [00:09<00:01, 80.44it/s][A | |
| 85%|████████▍ | 780/920 [00:09<00:01, 79.54it/s][A | |
| 86%|████████▌ | 789/920 [00:09<00:01, 80.86it/s][A | |
| 87%|████████▋ | 798/920 [00:10<00:01, 80.98it/s][A | |
| 88%|████████▊ | 807/920 [00:10<00:01, 78.75it/s][A | |
| 89%|████████▊ | 816/920 [00:10<00:01, 79.89it/s][A | |
| 90%|████████▉ | 825/920 [00:10<00:01, 81.14it/s][A | |
| 91%|█████████ | 834/920 [00:10<00:01, 81.82it/s][A | |
| 92%|█████████▏| 843/920 [00:10<00:00, 82.50it/s][A | |
| 93%|█████████▎| 852/920 [00:10<00:00, 79.23it/s][A | |
| 93%|█████████▎| 860/920 [00:10<00:00, 77.71it/s][A | |
| 94%|█████████▍| 868/920 [00:10<00:00, 68.84it/s][A | |
| 95%|█████████▌| 877/920 [00:11<00:00, 73.34it/s][A | |
| 96%|█████████▋| 886/920 [00:11<00:00, 75.71it/s][A | |
| 97%|█████████▋| 894/920 [00:11<00:00, 73.74it/s][A | |
| 98%|█████████▊| 902/920 [00:11<00:00, 74.81it/s][A | |
| 99%|█████████▉| 910/920 [00:11<00:00, 74.55it/s][A | |
| 100%|█████████▉| 918/920 [00:11<00:00, 75.64it/s][A | |
| [A 10%|█ | 511/5110 [02:18<15:48, 4.85it/s] | |
| 100%|██████████| 920/920 [00:15<00:00, 75.64it/s][A | |
| [A[INFO|trainer.py:3503] 2024-09-05 21:43:18,141 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-511 | |
| [INFO|configuration_utils.py:472] 2024-09-05 21:43:18,143 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-511/config.json | |
| [INFO|modeling_utils.py:2799] 2024-09-05 21:43:19,170 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-511/model.safetensors | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-05 21:43:19,172 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-511/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-05 21:43:19,172 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-511/special_tokens_map.json | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-05 21:43:21,246 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-05 21:43:21,246 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json | |
| 10%|█ | 512/5110 [02:22<7:30:20, 5.88s/it] 10%|█ | 513/5110 [02:22<5:20:07, 4.18s/it] 10%|█ | 514/5110 [02:22<3:49:21, 2.99s/it] 10%|█ | 515/5110 [02:22<2:45:57, 2.17s/it] 10%|█ | 516/5110 [02:23<2:01:32, 1.59s/it] 10%|█ | 517/5110 [02:23<1:29:30, 1.17s/it] 10%|█ | 518/5110 [02:23<1:07:04, 1.14it/s] 10%|█ | 519/5110 [02:23<53:46, 1.42it/s] 10%|█ | 520/5110 [02:24<44:40, 1.71it/s] 10%|█ | 521/5110 [02:24<37:35, 2.03it/s] 10%|█ | 522/5110 [02:24<32:24, 2.36it/s] 10%|█ | 523/5110 [02:24<28:22, 2.69it/s] 10%|█ | 524/5110 [02:25<24:52, 3.07it/s] 10%|█ | 525/5110 [02:25<22:21, 3.42it/s] 10%|█ | 526/5110 [02:25<21:03, 3.63it/s] 10%|█ | 527/5110 [02:25<22:05, 3.46it/s] 10%|█ | 528/5110 [02:26<23:41, 3.22it/s] 10%|█ | 529/5110 [02:26<21:11, 3.60it/s] 10%|█ | 530/5110 [02:26<20:51, 3.66it/s] 10%|█ | 531/5110 [02:26<19:52, 3.84it/s] 10%|█ | 532/5110 [02:27<19:29, 3.92it/s] 10%|█ | 533/5110 [02:27<18:53, 4.04it/s] 10%|█ | 534/5110 [02:27<18:42, 4.08it/s] 10%|█ | 535/5110 [02:27<19:14, 3.96it/s] 10%|█ | 536/5110 [02:28<21:52, 3.48it/s] 11%|█ | 537/5110 [02:28<21:02, 3.62it/s] 11%|█ | 538/5110 [02:28<19:35, 3.89it/s] 11%|█ | 539/5110 [02:28<19:09, 3.98it/s] 11%|█ | 540/5110 [02:29<19:25, 3.92it/s] 11%|█ | 541/5110 [02:29<18:06, 4.21it/s] 11%|█ | 542/5110 [02:29<20:07, 3.78it/s] 11%|█ | 543/5110 [02:29<20:36, 3.69it/s] 11%|█ | 544/5110 [02:30<20:30, 3.71it/s] 11%|█ | 545/5110 [02:30<18:47, 4.05it/s] 11%|█ | 546/5110 [02:30<18:19, 4.15it/s] 11%|█ | 547/5110 [02:30<18:09, 4.19it/s] 11%|█ | 548/5110 [02:31<17:22, 4.37it/s] 11%|█ | 549/5110 [02:31<17:37, 4.31it/s] 11%|█ | 550/5110 [02:31<17:28, 4.35it/s] 11%|█ | 551/5110 [02:31<17:23, 4.37it/s] 11%|█ | 552/5110 [02:31<16:28, 4.61it/s] 11%|█ | 553/5110 [02:32<15:36, 4.87it/s] 11%|█ | 554/5110 [02:32<15:33, 4.88it/s] 11%|█ | 555/5110 [02:32<16:12, 4.69it/s] 11%|█ | 556/5110 [02:32<17:21, 4.37it/s] 11%|█ | 557/5110 [02:33<18:09, 4.18it/s] 11%|█ | 558/5110 [02:33<18:23, 4.12it/s] 11%|█ | 559/5110 [02:33<17:22, 4.36it/s] 11%|█ | 560/5110 [02:33<17:00, 4.46it/s] 11%|█ | 561/5110 [02:34<17:38, 4.30it/s] 11%|█ | 562/5110 [02:34<17:28, 4.34it/s] 11%|█ | 563/5110 [02:34<17:48, 4.26it/s] 11%|█ | 564/5110 [02:34<19:07, 3.96it/s] 11%|█ | 565/5110 [02:35<20:54, 3.62it/s] 11%|█ | 566/5110 [02:35<20:59, 3.61it/s] 11%|█ | 567/5110 [02:35<19:04, 3.97it/s] 11%|█ | 568/5110 [02:35<19:10, 3.95it/s] 11%|█ | 569/5110 [02:36<18:02, 4.19it/s] 11%|█ | 570/5110 [02:36<20:45, 3.65it/s] 11%|█ | 571/5110 [02:36<21:17, 3.55it/s] 11%|█ | 572/5110 [02:36<19:56, 3.79it/s] 11%|█ | 573/5110 [02:37<19:09, 3.95it/s] |