| 2024-09-05 22:43:35.221687: 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 22:43:35.239699: 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 22:43:35.261393: 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 22:43:35.267947: 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 22:43:35.283519: 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 22:43:36.568969: 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 22:43:38 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False | |
| 09/05/2024 22:43:38 - 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%| | 0.00/3.54k [00:00<?, ?B/s] Downloading builder script: 100%|██████████| 3.54k/3.54k [00:00<00:00, 15.0kB/s] Downloading builder script: 100%|██████████| 3.54k/3.54k [00:00<00:00, 15.0kB/s] | |
| Downloading data: 0%| | 0.00/34.4M [00:00<?, ?B/s] Downloading data: 30%|███ | 10.5M/34.4M [00:00<00:02, 11.3MB/s] Downloading data: 61%|██████ | 21.0M/34.4M [00:01<00:00, 16.4MB/s] Downloading data: 91%|█████████▏| 31.5M/34.4M [00:01<00:00, 19.3MB/s] Downloading data: 100%|██████████| 34.4M/34.4M [00:01<00:00, 18.4MB/s] Downloading data: 100%|██████████| 34.4M/34.4M [00:02<00:00, 17.0MB/s] | |
| Downloading data: 0%| | 0.00/6.96M [00:00<?, ?B/s] Downloading data: 100%|██████████| 6.96M/6.96M [00:00<00:00, 9.66MB/s] Downloading data: 100%|██████████| 6.96M/6.96M [00:00<00:00, 9.57MB/s] | |
| Downloading data: 0%| | 0.00/12.3M [00:00<?, ?B/s] Downloading data: 85%|████████▌ | 10.5M/12.3M [00:00<00:00, 11.7MB/s] Downloading data: 100%|██████████| 12.3M/12.3M [00:00<00:00, 13.4MB/s] | |
| Generating train split: 0 examples [00:00, ? examples/s] Generating train split: 617 examples [00:00, 6150.71 examples/s] Generating train split: 1541 examples [00:00, 6145.46 examples/s] Generating train split: 2451 examples [00:00, 6093.89 examples/s] Generating train split: 3376 examples [00:00, 6119.13 examples/s] Generating train split: 4000 examples [00:00, 6093.30 examples/s] Generating train split: 4690 examples [00:00, 6321.68 examples/s] Generating train split: 5330 examples [00:00, 6258.81 examples/s] Generating train split: 6000 examples [00:00, 6279.89 examples/s] Generating train split: 6674 examples [00:01, 6409.66 examples/s] Generating train split: 7612 examples [00:01, 6338.10 examples/s] Generating train split: 8575 examples [00:01, 6365.45 examples/s] Generating train split: 9503 examples [00:01, 6295.80 examples/s] Generating train split: 10409 examples [00:01, 6208.67 examples/s] Generating train split: 11361 examples [00:01, 6247.79 examples/s] Generating train split: 12000 examples [00:01, 6182.52 examples/s] Generating train split: 12682 examples [00:02, 6335.72 examples/s] Generating train split: 13339 examples [00:02, 6290.80 examples/s] Generating train split: 14000 examples [00:02, 6233.63 examples/s] Generating train split: 14692 examples [00:02, 6419.43 examples/s] Generating train split: 15660 examples [00:02, 6395.32 examples/s] Generating train split: 16520 examples [00:02, 6165.05 examples/s] Generating train split: 17461 examples [00:02, 6198.47 examples/s] Generating train split: 18385 examples [00:02, 6182.35 examples/s] Generating train split: 19320 examples [00:03, 6194.99 examples/s] Generating train split: 19984 examples [00:03, 6295.54 examples/s] Generating train split: 20900 examples [00:03, 6222.76 examples/s] Generating train split: 21806 examples [00:03, 6156.05 examples/s] Generating train split: 22762 examples [00:03, 6219.92 examples/s] Generating train split: 23698 examples [00:03, 6217.78 examples/s] Generating train split: 24669 examples [00:03, 6190.70 examples/s] Generating train split: 25566 examples [00:04, 6121.92 examples/s] Generating train split: 26202 examples [00:04, 6169.45 examples/s] Generating train split: 26882 examples [00:04, 6318.89 examples/s] Generating train split: 27828 examples [00:04, 6311.08 examples/s] Generating train split: 28766 examples [00:04, 6286.67 examples/s] Generating train split: 29714 examples [00:04, 6293.32 examples/s] Generating train split: 30576 examples [00:05, 4233.38 examples/s] Generating train split: 31125 examples [00:05, 4445.75 examples/s] Generating train split: 31770 examples [00:05, 4835.24 examples/s] Generating train split: 31947 examples [00:05, 5962.85 examples/s] | |
| Generating validation split: 0 examples [00:00, ? examples/s] Generating validation split: 707 examples [00:00, 7041.45 examples/s] Generating validation split: 1689 examples [00:00, 6594.13 examples/s] Generating validation split: 2361 examples [00:00, 6490.83 examples/s] Generating validation split: 3352 examples [00:00, 6489.44 examples/s] Generating validation split: 4341 examples [00:00, 6476.95 examples/s] Generating validation split: 5000 examples [00:00, 6383.23 examples/s] Generating validation split: 5708 examples [00:00, 6572.22 examples/s] Generating validation split: 6705 examples [00:01, 6594.95 examples/s] Generating validation split: 6810 examples [00:01, 6504.53 examples/s] | |
| Generating test split: 0 examples [00:00, ? examples/s] Generating test split: 791 examples [00:00, 7886.60 examples/s] Generating test split: 1890 examples [00:00, 7488.43 examples/s] Generating test split: 3000 examples [00:00, 7375.84 examples/s] Generating test split: 3771 examples [00:00, 7475.50 examples/s] Generating test split: 4873 examples [00:00, 7418.70 examples/s] Generating test split: 5633 examples [00:00, 7466.67 examples/s] Generating test split: 6422 examples [00:00, 7585.10 examples/s] Generating test split: 7605 examples [00:01, 7698.04 examples/s] Generating test split: 8422 examples [00:01, 7708.73 examples/s] Generating test split: 9599 examples [00:01, 7751.10 examples/s] Generating test split: 10759 examples [00:01, 7742.01 examples/s] Generating test split: 11924 examples [00:01, 7749.14 examples/s] Generating test split: 12983 examples [00:01, 7518.55 examples/s] Generating test split: 14046 examples [00:01, 7381.89 examples/s] Generating test split: 14614 examples [00:01, 7520.46 examples/s] | |
| [INFO|configuration_utils.py:733] 2024-09-05 22:43:57,301 >> 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 22:43:57,310 >> 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-ENFERMEDAD", | |
| "2": "I-ENFERMEDAD" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "B-ENFERMEDAD": 1, | |
| "I-ENFERMEDAD": 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 22:43:57,806 >> 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 22:43:57,808 >> 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 22:44:00,154 >> 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 22:44:00,154 >> 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 22:44:00,154 >> loading file tokenizer.json from cache at None | |
| [INFO|tokenization_utils_base.py:2269] 2024-09-05 22:44:00,154 >> loading file added_tokens.json from cache at None | |
| [INFO|tokenization_utils_base.py:2269] 2024-09-05 22:44:00,154 >> 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 22:44:00,154 >> 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 22:44:00,155 >> 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 22:44:00,156 >> 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 22:44:00,243 >> 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 22:44:00,244 >> 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 22:44:31,232 >> 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 22:44:31,384 >> 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 22:44:31,384 >> 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%| | 0/31947 [00:00<?, ? examples/s] Map: 3%|▎ | 1000/31947 [00:00<00:03, 9158.31 examples/s] Map: 9%|▉ | 3000/31947 [00:00<00:02, 10209.38 examples/s] Map: 16%|█▌ | 5000/31947 [00:00<00:02, 10615.27 examples/s] Map: 22%|██▏ | 7000/31947 [00:00<00:02, 10870.55 examples/s] Map: 28%|██▊ | 9000/31947 [00:00<00:02, 11076.46 examples/s] Map: 34%|███▍ | 11000/31947 [00:01<00:01, 11059.02 examples/s] Map: 41%|████ | 13000/31947 [00:01<00:01, 11018.18 examples/s] Map: 47%|████▋ | 15000/31947 [00:01<00:01, 11231.44 examples/s] Map: 53%|█████▎ | 17000/31947 [00:01<00:01, 11046.82 examples/s] Map: 59%|█████▉ | 19000/31947 [00:01<00:01, 11163.17 examples/s] Map: 66%|██████▌ | 21000/31947 [00:01<00:00, 11103.32 examples/s] Map: 72%|███████▏ | 23000/31947 [00:02<00:00, 11150.08 examples/s] Map: 78%|███████▊ | 25000/31947 [00:02<00:00, 11126.48 examples/s] Map: 85%|████████▍ | 27000/31947 [00:02<00:00, 11156.06 examples/s] Map: 91%|█████████ | 29000/31947 [00:02<00:00, 11171.85 examples/s] Map: 97%|█████████▋| 31000/31947 [00:02<00:00, 11147.45 examples/s] Map: 100%|██████████| 31947/31947 [00:02<00:00, 10952.44 examples/s] | |
| Map: 0%| | 0/6810 [00:00<?, ? examples/s] Map: 29%|██▉ | 2000/6810 [00:00<00:00, 11218.17 examples/s] Map: 59%|█████▊ | 4000/6810 [00:00<00:00, 11344.49 examples/s] Map: 88%|████████▊ | 6000/6810 [00:00<00:00, 7083.36 examples/s] Map: 100%|██████████| 6810/6810 [00:00<00:00, 8149.18 examples/s] | |
| Map: 0%| | 0/14614 [00:00<?, ? examples/s] Map: 14%|█▎ | 2000/14614 [00:00<00:00, 13116.63 examples/s] Map: 27%|██▋ | 4000/14614 [00:00<00:00, 13065.88 examples/s] Map: 41%|████ | 6000/14614 [00:00<00:00, 13460.26 examples/s] Map: 55%|█████▍ | 8000/14614 [00:00<00:00, 13794.05 examples/s] Map: 68%|██████▊ | 10000/14614 [00:00<00:00, 13651.45 examples/s] Map: 82%|████████▏ | 12000/14614 [00:00<00:00, 13688.96 examples/s] Map: 96%|█████████▌| 14000/14614 [00:01<00:00, 13265.32 examples/s] Map: 100%|██████████| 14614/14614 [00:01<00:00, 13315.87 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, 10.1MB/s] | |
| [INFO|trainer.py:811] 2024-09-05 22:44:38,444 >> The following columns in the training set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: id, ner_tags, tokens. If id, ner_tags, tokens are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. | |
| [INFO|trainer.py:2134] 2024-09-05 22:44:39,141 >> ***** Running training ***** | |
| [INFO|trainer.py:2135] 2024-09-05 22:44:39,141 >> Num examples = 31,947 | |
| [INFO|trainer.py:2136] 2024-09-05 22:44:39,141 >> Num Epochs = 10 | |
| [INFO|trainer.py:2137] 2024-09-05 22:44:39,141 >> Instantaneous batch size per device = 32 | |
| [INFO|trainer.py:2140] 2024-09-05 22:44:39,141 >> Total train batch size (w. parallel, distributed & accumulation) = 64 | |
| [INFO|trainer.py:2141] 2024-09-05 22:44:39,141 >> Gradient Accumulation steps = 2 | |
| [INFO|trainer.py:2142] 2024-09-05 22:44:39,141 >> Total optimization steps = 4,990 | |
| [INFO|trainer.py:2143] 2024-09-05 22:44:39,142 >> Number of trainable parameters = 124,055,043 | |
| 0%| | 0/4990 [00:00<?, ?it/s] 0%| | 1/4990 [00:01<2:30:16, 1.81s/it] 0%| | 2/4990 [00:02<1:13:06, 1.14it/s] 0%| | 3/4990 [00:02<54:01, 1.54it/s] 0%| | 4/4990 [00:02<39:05, 2.13it/s] 0%| | 5/4990 [00:02<33:43, 2.46it/s] 0%| | 6/4990 [00:03<28:27, 2.92it/s] 0%| | 7/4990 [00:03<25:31, 3.25it/s] 0%| | 8/4990 [00:03<23:09, 3.58it/s] 0%| | 9/4990 [00:03<21:53, 3.79it/s] 0%| | 10/4990 [00:04<23:55, 3.47it/s] 0%| | 11/4990 [00:04<21:33, 3.85it/s] 0%| | 12/4990 [00:04<19:54, 4.17it/s] 0%| | 13/4990 [00:04<19:58, 4.15it/s] 0%| | 14/4990 [00:04<18:02, 4.60it/s] 0%| | 15/4990 [00:05<17:14, 4.81it/s] 0%| | 16/4990 [00:05<20:42, 4.00it/s] 0%| | 17/4990 [00:05<19:20, 4.28it/s] 0%| | 18/4990 [00:05<18:15, 4.54it/s] 0%| | 19/4990 [00:06<17:55, 4.62it/s] 0%| | 20/4990 [00:06<18:29, 4.48it/s] 0%| | 21/4990 [00:06<21:02, 3.94it/s] 0%| | 22/4990 [00:06<21:04, 3.93it/s] 0%| | 23/4990 [00:07<20:40, 4.00it/s] 0%| | 24/4990 [00:07<19:12, 4.31it/s] 1%| | 25/4990 [00:07<20:37, 4.01it/s] 1%| | 26/4990 [00:07<20:47, 3.98it/s] 1%| | 27/4990 [00:08<19:34, 4.23it/s] 1%| | 28/4990 [00:08<20:22, 4.06it/s] 1%| | 29/4990 [00:08<19:11, 4.31it/s] 1%| | 30/4990 [00:08<19:31, 4.23it/s] 1%| | 31/4990 [00:08<17:52, 4.63it/s] 1%| | 32/4990 [00:09<19:00, 4.35it/s] 1%| | 33/4990 [00:09<18:14, 4.53it/s] 1%| | 34/4990 [00:09<21:03, 3.92it/s] 1%| | 35/4990 [00:09<19:29, 4.24it/s] 1%| | 36/4990 [00:10<19:19, 4.27it/s] 1%| | 37/4990 [00:10<20:06, 4.10it/s] 1%| | 38/4990 [00:10<19:05, 4.32it/s] 1%| | 39/4990 [00:10<19:34, 4.21it/s] 1%| | 40/4990 [00:11<18:13, 4.53it/s] 1%| | 41/4990 [00:11<19:07, 4.31it/s] 1%| | 42/4990 [00:11<18:29, 4.46it/s] 1%| | 43/4990 [00:11<18:05, 4.56it/s] 1%| | 44/4990 [00:11<16:50, 4.89it/s] 1%| | 45/4990 [00:12<20:00, 4.12it/s] 1%| | 46/4990 [00:12<27:12, 3.03it/s] 1%| | 47/4990 [00:12<23:50, 3.45it/s] 1%| | 48/4990 [00:13<33:35, 2.45it/s] 1%| | 49/4990 [00:13<28:38, 2.88it/s] 1%| | 50/4990 [00:14<26:25, 3.12it/s] 1%| | 51/4990 [00:14<23:04, 3.57it/s] 1%| | 52/4990 [00:14<21:37, 3.81it/s] 1%| | 53/4990 [00:14<19:59, 4.12it/s] 1%| | 54/4990 [00:14<19:15, 4.27it/s] 1%| | 55/4990 [00:15<18:00, 4.57it/s] 1%| | 56/4990 [00:15<17:12, 4.78it/s] 1%| | 57/4990 [00:15<18:08, 4.53it/s] 1%| | 58/4990 [00:15<17:47, 4.62it/s] 1%| | 59/4990 [00:15<17:26, 4.71it/s] 1%| | 60/4990 [00:16<16:18, 5.04it/s] 1%| | 61/4990 [00:16<15:46, 5.21it/s] 1%| | 62/4990 [00:16<15:50, 5.18it/s] 1%|▏ | 63/4990 [00:16<18:57, 4.33it/s] 1%|▏ | 64/4990 [00:17<17:59, 4.56it/s] 1%|▏ | 65/4990 [00:17<19:15, 4.26it/s] 1%|▏ | 66/4990 [00:17<20:47, 3.95it/s] 1%|▏ | 67/4990 [00:17<19:35, 4.19it/s] 1%|▏ | 68/4990 [00:18<24:46, 3.31it/s] 1%|▏ | 69/4990 [00:18<22:55, 3.58it/s] 1%|▏ | 70/4990 [00:18<20:57, 3.91it/s] 1%|▏ | 71/4990 [00:18<22:39, 3.62it/s] 1%|▏ | 72/4990 [00:19<20:35, 3.98it/s] 1%|▏ | 73/4990 [00:19<20:37, 3.97it/s] 1%|▏ | 74/4990 [00:19<27:39, 2.96it/s] 2%|▏ | 75/4990 [00:20<24:16, 3.37it/s] 2%|▏ | 76/4990 [00:20<22:19, 3.67it/s] 2%|▏ | 77/4990 [00:20<20:46, 3.94it/s] 2%|▏ | 78/4990 [00:20<20:46, 3.94it/s] 2%|▏ | 79/4990 [00:21<18:28, 4.43it/s] 2%|▏ | 80/4990 [00:21<17:35, 4.65it/s] 2%|▏ | 81/4990 [00:21<17:10, 4.77it/s] 2%|▏ | 82/4990 [00:21<16:25, 4.98it/s] 2%|▏ | 83/4990 [00:21<16:03, 5.09it/s] 2%|▏ | 84/4990 [00:21<15:10, 5.39it/s] 2%|▏ | 85/4990 [00:22<16:10, 5.06it/s] 2%|▏ | 86/4990 [00:22<16:35, 4.93it/s] 2%|▏ | 87/4990 [00:22<16:18, 5.01it/s] 2%|▏ | 88/4990 [00:22<17:51, 4.57it/s] 2%|▏ | 89/4990 [00:22<16:46, 4.87it/s] 2%|▏ | 90/4990 [00:23<20:39, 3.95it/s] 2%|▏ | 91/4990 [00:23<19:12, 4.25it/s] 2%|▏ | 92/4990 [00:23<17:14, 4.73it/s] 2%|▏ | 93/4990 [00:23<16:22, 4.99it/s] 2%|▏ | 94/4990 [00:24<16:04, 5.07it/s] 2%|▏ | 95/4990 [00:24<14:52, 5.49it/s] 2%|▏ | 96/4990 [00:24<16:39, 4.90it/s] 2%|▏ | 97/4990 [00:24<16:26, 4.96it/s] 2%|▏ | 98/4990 [00:24<16:43, 4.87it/s] 2%|▏ | 99/4990 [00:25<18:01, 4.52it/s] 2%|▏ | 100/4990 [00:25<18:41, 4.36it/s] 2%|▏ | 101/4990 [00:25<17:23, 4.69it/s] 2%|▏ | 102/4990 [00:25<18:07, 4.50it/s] 2%|▏ | 103/4990 [00:26<17:30, 4.65it/s] 2%|▏ | 104/4990 [00:26<16:38, 4.89it/s] 2%|▏ | 105/4990 [00:26<18:38, 4.37it/s] 2%|▏ | 106/4990 [00:26<19:25, 4.19it/s] 2%|▏ | 107/4990 [00:26<18:51, 4.31it/s] 2%|▏ | 108/4990 [00:27<19:44, 4.12it/s] 2%|▏ | 109/4990 [00:27<19:06, 4.26it/s] 2%|▏ | 110/4990 [00:27<21:28, 3.79it/s] 2%|▏ | 111/4990 [00:28<24:21, 3.34it/s] 2%|▏ | 112/4990 [00:28<24:27, 3.32it/s] 2%|▏ | 113/4990 [00:28<23:45, 3.42it/s] 2%|▏ | 114/4990 [00:28<21:22, 3.80it/s] 2%|▏ | 115/4990 [00:29<19:27, 4.18it/s] 2%|▏ | 116/4990 [00:29<19:48, 4.10it/s] 2%|▏ | 117/4990 [00:29<19:08, 4.24it/s] 2%|▏ | 118/4990 [00:29<18:39, 4.35it/s] 2%|▏ | 119/4990 [00:30<18:23, 4.42it/s] 2%|▏ | 120/4990 [00:30<18:14, 4.45it/s] 2%|▏ | 121/4990 [00:30<18:55, 4.29it/s] 2%|▏ | 122/4990 [00:30<17:40, 4.59it/s] 2%|▏ | 123/4990 [00:30<17:21, 4.67it/s] 2%|▏ | 124/4990 [00:31<17:01, 4.76it/s] 3%|▎ | 125/4990 [00:31<16:52, 4.80it/s] 3%|▎ | 126/4990 [00:31<17:10, 4.72it/s] 3%|▎ | 127/4990 [00:31<16:50, 4.81it/s] 3%|▎ | 128/4990 [00:31<16:45, 4.83it/s] 3%|▎ | 129/4990 [00:32<21:17, 3.81it/s] 3%|▎ | 130/4990 [00:32<20:35, 3.94it/s] 3%|▎ | 131/4990 [00:32<18:22, 4.41it/s] 3%|▎ | 132/4990 [00:33<20:55, 3.87it/s] 3%|▎ | 133/4990 [00:33<20:29, 3.95it/s] 3%|▎ | 134/4990 [00:33<21:05, 3.84it/s] 3%|▎ | 135/4990 [00:33<18:52, 4.29it/s] 3%|▎ | 136/4990 [00:33<18:11, 4.45it/s] 3%|▎ | 137/4990 [00:34<20:37, 3.92it/s] 3%|▎ | 138/4990 [00:34<19:47, 4.09it/s] 3%|▎ | 139/4990 [00:34<20:04, 4.03it/s] 3%|▎ | 140/4990 [00:34<18:36, 4.35it/s] 3%|▎ | 141/4990 [00:35<17:43, 4.56it/s] 3%|▎ | 142/4990 [00:35<19:12, 4.21it/s] 3%|▎ | 143/4990 [00:35<19:47, 4.08it/s] 3%|▎ | 144/4990 [00:35<19:21, 4.17it/s] 3%|▎ | 145/4990 [00:36<19:02, 4.24it/s] 3%|▎ | 146/4990 [00:36<18:06, 4.46it/s] 3%|▎ | 147/4990 [00:36<17:49, 4.53it/s] 3%|▎ | 148/4990 [00:36<20:00, 4.03it/s] 3%|▎ | 149/4990 [00:37<18:22, 4.39it/s] 3%|▎ | 150/4990 [00:37<17:22, 4.64it/s] 3%|▎ | 151/4990 [00:37<18:27, 4.37it/s] 3%|▎ | 152/4990 [00:37<17:12, 4.69it/s] 3%|▎ | 153/4990 [00:37<16:54, 4.77it/s] 3%|▎ | 154/4990 [00:38<18:03, 4.46it/s] 3%|▎ | 155/4990 [00:38<19:43, 4.09it/s] 3%|▎ | 156/4990 [00:38<22:01, 3.66it/s] 3%|▎ | 157/4990 [00:38<20:19, 3.96it/s] 3%|▎ | 158/4990 [00:39<19:10, 4.20it/s] 3%|▎ | 159/4990 [00:39<18:20, 4.39it/s] 3%|▎ | 160/4990 [00:39<18:39, 4.32it/s] 3%|▎ | 161/4990 [00:39<19:23, 4.15it/s] 3%|▎ | 162/4990 [00:40<17:41, 4.55it/s] 3%|▎ | 163/4990 [00:40<18:25, 4.37it/s] 3%|▎ | 164/4990 [00:40<21:51, 3.68it/s] 3%|▎ | 165/4990 [00:40<19:57, 4.03it/s] 3%|▎ | 166/4990 [00:41<19:01, 4.23it/s] 3%|▎ | 167/4990 [00:41<17:33, 4.58it/s] 3%|▎ | 168/4990 [00:41<17:10, 4.68it/s] 3%|▎ | 169/4990 [00:41<17:50, 4.50it/s] 3%|▎ | 170/4990 [00:41<18:17, 4.39it/s] 3%|▎ | 171/4990 [00:42<24:41, 3.25it/s] 3%|▎ | 172/4990 [00:42<23:38, 3.40it/s] 3%|▎ | 173/4990 [00:42<20:14, 3.97it/s] 3%|▎ | 174/4990 [00:43<18:57, 4.23it/s] 4%|▎ | 175/4990 [00:43<20:35, 3.90it/s] 4%|▎ | 176/4990 [00:43<19:26, 4.13it/s] 4%|▎ | 177/4990 [00:43<18:45, 4.28it/s] 4%|▎ | 178/4990 [00:44<20:19, 3.95it/s] 4%|▎ | 179/4990 [00:44<21:27, 3.74it/s] 4%|▎ | 180/4990 [00:44<19:52, 4.03it/s] 4%|▎ | 181/4990 [00:44<22:13, 3.61it/s] 4%|▎ | 182/4990 [00:45<19:45, 4.06it/s] 4%|▎ | 183/4990 [00:45<20:41, 3.87it/s] 4%|▎ | 184/4990 [00:45<19:34, 4.09it/s] 4%|▎ | 185/4990 [00:45<19:21, 4.14it/s] 4%|▎ | 186/4990 [00:45<17:20, 4.62it/s] 4%|▎ | 187/4990 [00:46<17:39, 4.53it/s] 4%|▍ | 188/4990 [00:46<17:10, 4.66it/s] 4%|▍ | 189/4990 [00:46<18:32, 4.32it/s] 4%|▍ | 190/4990 [00:46<19:55, 4.01it/s] 4%|▍ | 191/4990 [00:47<23:30, 3.40it/s] 4%|▍ | 192/4990 [00:47<23:09, 3.45it/s] 4%|▍ | 193/4990 [00:47<21:29, 3.72it/s] 4%|▍ | 194/4990 [00:48<22:02, 3.63it/s] 4%|▍ | 195/4990 [00:48<23:06, 3.46it/s] 4%|▍ | 196/4990 [00:48<21:32, 3.71it/s] 4%|▍ | 197/4990 [00:48<21:32, 3.71it/s] 4%|▍ | 198/4990 [00:49<20:39, 3.87it/s] 4%|▍ | 199/4990 [00:49<20:48, 3.84it/s] 4%|▍ | 200/4990 [00:49<19:16, 4.14it/s] 4%|▍ | 201/4990 [00:49<19:27, 4.10it/s] 4%|▍ | 202/4990 [00:50<19:00, 4.20it/s] 4%|▍ | 203/4990 [00:50<18:21, 4.35it/s] 4%|▍ | 204/4990 [00:50<18:16, 4.36it/s] 4%|▍ | 205/4990 [00:50<17:52, 4.46it/s] 4%|▍ | 206/4990 [00:50<17:21, 4.59it/s] 4%|▍ | 207/4990 [00:51<16:07, 4.94it/s] 4%|▍ | 208/4990 [00:51<16:10, 4.93it/s] 4%|▍ | 209/4990 [00:51<16:33, 4.81it/s] 4%|▍ | 210/4990 [00:51<15:59, 4.98it/s] 4%|▍ | 211/4990 [00:52<25:45, 3.09it/s] 4%|▍ | 212/4990 [00:52<23:35, 3.38it/s] 4%|▍ | 213/4990 [00:52<21:35, 3.69it/s] 4%|▍ | 214/4990 [00:53<23:16, 3.42it/s] 4%|▍ | 215/4990 [00:53<20:58, 3.79it/s] 4%|▍ | 216/4990 [00:53<18:47, 4.24it/s] 4%|▍ | 217/4990 [00:53<17:22, 4.58it/s] 4%|▍ | 218/4990 [00:53<18:10, 4.37it/s] 4%|▍ | 219/4990 [00:54<17:11, 4.63it/s] 4%|▍ | 220/4990 [00:54<17:52, 4.45it/s] 4%|▍ | 221/4990 [00:54<17:02, 4.66it/s] 4%|▍ | 222/4990 [00:54<16:22, 4.85it/s] 4%|▍ | 223/4990 [00:54<17:37, 4.51it/s] 4%|▍ | 224/4990 [00:55<17:47, 4.46it/s] 5%|▍ | 225/4990 [00:55<16:55, 4.69it/s] 5%|▍ | 226/4990 [00:55<17:00, 4.67it/s] 5%|▍ | 227/4990 [00:55<18:54, 4.20it/s] 5%|▍ | 228/4990 [00:56<18:35, 4.27it/s] 5%|▍ | 229/4990 [00:56<17:09, 4.63it/s] 5%|▍ | 230/4990 [00:56<15:59, 4.96it/s] 5%|▍ | 231/4990 [00:56<16:38, 4.77it/s] 5%|▍ | 232/4990 [00:56<18:05, 4.38it/s] 5%|▍ | 233/4990 [00:57<19:07, 4.15it/s] 5%|▍ | 234/4990 [00:57<18:25, 4.30it/s] 5%|▍ | 235/4990 [00:57<17:20, 4.57it/s] 5%|▍ | 236/4990 [00:57<16:46, 4.72it/s] 5%|▍ | 237/4990 [00:58<19:32, 4.06it/s] 5%|▍ | 238/4990 [00:58<17:53, 4.43it/s] 5%|▍ | 239/4990 [00:58<19:00, 4.17it/s] 5%|▍ | 240/4990 [00:58<19:40, 4.02it/s] 5%|▍ | 241/4990 [00:59<20:14, 3.91it/s] 5%|▍ | 242/4990 [00:59<20:07, 3.93it/s] 5%|▍ | 243/4990 [00:59<19:07, 4.14it/s] 5%|▍ | 244/4990 [00:59<18:07, 4.37it/s] 5%|▍ | 245/4990 [01:00<17:58, 4.40it/s] 5%|▍ | 246/4990 [01:00<17:06, 4.62it/s] 5%|▍ | 247/4990 [01:00<20:01, 3.95it/s] 5%|▍ | 248/4990 [01:00<19:19, 4.09it/s] 5%|▍ | 249/4990 [01:00<17:50, 4.43it/s] 5%|▌ | 250/4990 [01:01<16:28, 4.80it/s] 5%|▌ | 251/4990 [01:01<18:48, 4.20it/s] 5%|▌ | 252/4990 [01:01<18:18, 4.31it/s] 5%|▌ | 253/4990 [01:01<17:14, 4.58it/s] 5%|▌ | 254/4990 [01:02<17:34, 4.49it/s] 5%|▌ | 255/4990 [01:02<17:32, 4.50it/s] 5%|▌ | 256/4990 [01:02<17:43, 4.45it/s] 5%|▌ | 257/4990 [01:02<18:13, 4.33it/s] 5%|▌ | 258/4990 [01:03<18:56, 4.16it/s] 5%|▌ | 259/4990 [01:03<19:21, 4.07it/s] 5%|▌ | 260/4990 [01:03<18:16, 4.32it/s] 5%|▌ | 261/4990 [01:03<18:59, 4.15it/s] 5%|▌ | 262/4990 [01:04<18:57, 4.16it/s] 5%|▌ | 263/4990 [01:04<16:55, 4.66it/s] 5%|▌ | 264/4990 [01:04<18:45, 4.20it/s] 5%|▌ | 265/4990 [01:04<17:56, 4.39it/s] 5%|▌ | 266/4990 [01:04<19:42, 3.99it/s] 5%|▌ | 267/4990 [01:05<18:13, 4.32it/s] 5%|▌ | 268/4990 [01:05<18:17, 4.30it/s] 5%|▌ | 269/4990 [01:05<17:08, 4.59it/s] 5%|▌ | 270/4990 [01:05<19:52, 3.96it/s] 5%|▌ | 271/4990 [01:06<18:46, 4.19it/s] 5%|▌ | 272/4990 [01:06<17:29, 4.50it/s] 5%|▌ | 273/4990 [01:06<15:47, 4.98it/s] 5%|▌ | 274/4990 [01:06<16:52, 4.66it/s] 6%|▌ | 275/4990 [01:06<16:38, 4.72it/s] 6%|▌ | 276/4990 [01:07<16:59, 4.63it/s] 6%|▌ | 277/4990 [01:07<16:58, 4.63it/s] 6%|▌ | 278/4990 [01:07<19:29, 4.03it/s] 6%|▌ | 279/4990 [01:07<18:14, 4.31it/s] 6%|▌ | 280/4990 [01:08<17:08, 4.58it/s] 6%|▌ | 281/4990 [01:08<18:38, 4.21it/s] 6%|▌ | 282/4990 [01:08<18:20, 4.28it/s] 6%|▌ | 283/4990 [01:08<18:05, 4.34it/s] 6%|▌ | 284/4990 [01:09<26:46, 2.93it/s] 6%|▌ | 285/4990 [01:09<23:57, 3.27it/s] 6%|▌ | 286/4990 [01:09<24:08, 3.25it/s] 6%|▌ | 287/4990 [01:10<21:24, 3.66it/s] 6%|▌ | 288/4990 [01:10<21:50, 3.59it/s] 6%|▌ | 289/4990 [01:10<24:11, 3.24it/s] 6%|▌ | 290/4990 [01:10<21:35, 3.63it/s] 6%|▌ | 291/4990 [01:11<19:00, 4.12it/s] 6%|▌ | 292/4990 [01:11<16:52, 4.64it/s] 6%|▌ | 293/4990 [01:11<20:28, 3.82it/s] 6%|▌ | 294/4990 [01:11<19:33, 4.00it/s] 6%|▌ | 295/4990 [01:12<18:02, 4.34it/s] 6%|▌ | 296/4990 [01:12<21:30, 3.64it/s] 6%|▌ | 297/4990 [01:12<19:57, 3.92it/s] 6%|▌ | 298/4990 [01:12<18:42, 4.18it/s] 6%|▌ | 299/4990 [01:13<17:38, 4.43it/s] 6%|▌ | 300/4990 [01:13<19:28, 4.01it/s] 6%|▌ | 301/4990 [01:13<17:54, 4.36it/s] 6%|▌ | 302/4990 [01:13<20:13, 3.86it/s] 6%|▌ | 303/4990 [01:14<19:54, 3.92it/s] 6%|▌ | 304/4990 [01:14<17:57, 4.35it/s] 6%|▌ | 305/4990 [01:14<16:21, 4.77it/s] 6%|▌ | 306/4990 [01:14<16:41, 4.68it/s] 6%|▌ | 307/4990 [01:15<20:42, 3.77it/s] 6%|▌ | 308/4990 [01:15<19:57, 3.91it/s] 6%|▌ | 309/4990 [01:15<19:21, 4.03it/s] 6%|▌ | 310/4990 [01:15<20:37, 3.78it/s] 6%|▌ | 311/4990 [01:16<19:05, 4.08it/s] 6%|▋ | 312/4990 [01:16<18:20, 4.25it/s] 6%|▋ | 313/4990 [01:16<18:18, 4.26it/s] 6%|▋ | 314/4990 [01:16<21:30, 3.62it/s] 6%|▋ | 315/4990 [01:17<24:15, 3.21it/s] 6%|▋ | 316/4990 [01:17<21:34, 3.61it/s] 6%|▋ | 317/4990 [01:17<19:36, 3.97it/s] 6%|▋ | 318/4990 [01:17<18:45, 4.15it/s] 6%|▋ | 319/4990 [01:18<20:36, 3.78it/s] 6%|▋ | 320/4990 [01:18<19:26, 4.00it/s] 6%|▋ | 321/4990 [01:18<25:04, 3.10it/s] 6%|▋ | 322/4990 [01:19<24:58, 3.11it/s] 6%|▋ | 323/4990 [01:19<22:10, 3.51it/s] 6%|▋ | 324/4990 [01:19<19:27, 4.00it/s] 7%|▋ | 325/4990 [01:19<17:53, 4.35it/s] 7%|▋ | 326/4990 [01:19<17:38, 4.41it/s] 7%|▋ | 327/4990 [01:20<17:05, 4.55it/s] 7%|▋ | 328/4990 [01:20<17:18, 4.49it/s] 7%|▋ | 329/4990 [01:20<16:25, 4.73it/s] 7%|▋ | 330/4990 [01:20<16:40, 4.66it/s] 7%|▋ | 331/4990 [01:21<16:54, 4.59it/s] 7%|▋ | 332/4990 [01:21<17:27, 4.45it/s] 7%|▋ | 333/4990 [01:21<16:18, 4.76it/s] 7%|▋ | 334/4990 [01:21<17:52, 4.34it/s] 7%|▋ | 335/4990 [01:21<17:09, 4.52it/s] 7%|▋ | 336/4990 [01:22<17:30, 4.43it/s] 7%|▋ | 337/4990 [01:22<16:29, 4.70it/s] 7%|▋ | 338/4990 [01:22<17:02, 4.55it/s] 7%|▋ | 339/4990 [01:22<15:53, 4.88it/s] 7%|▋ | 340/4990 [01:23<17:00, 4.56it/s] 7%|▋ | 341/4990 [01:23<17:57, 4.32it/s] 7%|▋ | 342/4990 [01:23<16:47, 4.61it/s] 7%|▋ | 343/4990 [01:23<16:39, 4.65it/s] 7%|▋ | 344/4990 [01:23<18:49, 4.11it/s] 7%|▋ | 345/4990 [01:24<18:24, 4.21it/s] 7%|▋ | 346/4990 [01:24<18:25, 4.20it/s] 7%|▋ | 347/4990 [01:24<17:49, 4.34it/s] 7%|▋ | 348/4990 [01:25<21:54, 3.53it/s] 7%|▋ | 349/4990 [01:25<19:46, 3.91it/s] 7%|▋ | 350/4990 [01:25<18:34, 4.16it/s] 7%|▋ | 351/4990 [01:25<19:12, 4.02it/s] 7%|▋ | 352/4990 [01:25<18:44, 4.13it/s] 7%|▋ | 353/4990 [01:26<18:56, 4.08it/s] 7%|▋ | 354/4990 [01:26<21:46, 3.55it/s] 7%|▋ | 355/4990 [01:26<20:01, 3.86it/s] 7%|▋ | 356/4990 [01:27<19:21, 3.99it/s] 7%|▋ | 357/4990 [01:27<21:47, 3.54it/s] 7%|▋ | 358/4990 [01:27<21:37, 3.57it/s] 7%|▋ | 359/4990 [01:27<19:00, 4.06it/s] 7%|▋ | 360/4990 [01:28<25:44, 3.00it/s] 7%|▋ | 361/4990 [01:28<23:24, 3.29it/s] 7%|▋ | 362/4990 [01:28<20:57, 3.68it/s] 7%|▋ | 363/4990 [01:29<20:22, 3.78it/s] 7%|▋ | 364/4990 [01:29<19:54, 3.87it/s] 7%|▋ | 365/4990 [01:29<19:25, 3.97it/s] 7%|▋ | 366/4990 [01:29<19:23, 3.97it/s] 7%|▋ | 367/4990 [01:29<18:34, 4.15it/s] 7%|▋ | 368/4990 [01:30<18:03, 4.27it/s] 7%|▋ | 369/4990 [01:30<17:28, 4.41it/s] 7%|▋ | 370/4990 [01:30<17:11, 4.48it/s] 7%|▋ | 371/4990 [01:30<16:11, 4.75it/s] 7%|▋ | 372/4990 [01:31<17:34, 4.38it/s] 7%|▋ | 373/4990 [01:31<17:19, 4.44it/s] 7%|▋ | 374/4990 [01:31<16:00, 4.81it/s] 8%|▊ | 375/4990 [01:31<20:11, 3.81it/s] 8%|▊ | 376/4990 [01:32<18:32, 4.15it/s] 8%|▊ | 377/4990 [01:32<21:20, 3.60it/s] 8%|▊ | 378/4990 [01:32<22:36, 3.40it/s] 8%|▊ | 379/4990 [01:32<19:44, 3.89it/s] 8%|▊ | 380/4990 [01:33<18:59, 4.04it/s] 8%|▊ | 381/4990 [01:33<17:49, 4.31it/s] 8%|▊ | 382/4990 [01:33<16:58, 4.52it/s] 8%|▊ | 383/4990 [01:33<20:43, 3.70it/s] 8%|▊ | 384/4990 [01:34<21:08, 3.63it/s] 8%|▊ | 385/4990 [01:34<20:09, 3.81it/s] 8%|▊ | 386/4990 [01:34<18:26, 4.16it/s] 8%|▊ | 387/4990 [01:34<19:58, 3.84it/s] 8%|▊ | 388/4990 [01:35<18:16, 4.20it/s] 8%|▊ | 389/4990 [01:35<17:09, 4.47it/s] 8%|▊ | 390/4990 [01:35<18:00, 4.26it/s] 8%|▊ | 391/4990 [01:35<16:30, 4.64it/s] 8%|▊ | 392/4990 [01:35<16:33, 4.63it/s] 8%|▊ | 393/4990 [01:36<16:58, 4.51it/s] 8%|▊ | 394/4990 [01:36<17:21, 4.41it/s] 8%|▊ | 395/4990 [01:36<18:14, 4.20it/s] 8%|▊ | 396/4990 [01:36<17:54, 4.28it/s] 8%|▊ | 397/4990 [01:37<20:00, 3.83it/s] 8%|▊ | 398/4990 [01:37<20:57, 3.65it/s] 8%|▊ | 399/4990 [01:37<19:37, 3.90it/s] 8%|▊ | 400/4990 [01:37<18:17, 4.18it/s] 8%|▊ | 401/4990 [01:38<18:32, 4.13it/s] 8%|▊ | 402/4990 [01:38<18:10, 4.21it/s] 8%|▊ | 403/4990 [01:38<18:13, 4.19it/s] 8%|▊ | 404/4990 [01:38<19:41, 3.88it/s] 8%|▊ | 405/4990 [01:39<18:10, 4.20it/s] 8%|▊ | 406/4990 [01:39<16:23, 4.66it/s] 8%|▊ | 407/4990 [01:39<15:40, 4.87it/s] 8%|▊ | 408/4990 [01:39<15:57, 4.78it/s] 8%|▊ | 409/4990 [01:39<15:38, 4.88it/s] 8%|▊ | 410/4990 [01:40<15:00, 5.09it/s] 8%|▊ | 411/4990 [01:40<15:47, 4.83it/s] 8%|▊ | 412/4990 [01:40<14:47, 5.16it/s] 8%|▊ | 413/4990 [01:40<15:18, 4.98it/s] 8%|▊ | 414/4990 [01:40<16:28, 4.63it/s] 8%|▊ | 415/4990 [01:41<16:20, 4.67it/s] 8%|▊ | 416/4990 [01:41<20:33, 3.71it/s] 8%|▊ | 417/4990 [01:41<19:17, 3.95it/s] 8%|▊ | 418/4990 [01:42<19:57, 3.82it/s] 8%|▊ | 419/4990 [01:42<19:16, 3.95it/s] 8%|▊ | 420/4990 [01:42<22:02, 3.46it/s] 8%|▊ | 421/4990 [01:42<19:53, 3.83it/s] 8%|▊ | 422/4990 [01:43<19:13, 3.96it/s] 8%|▊ | 423/4990 [01:43<31:34, 2.41it/s] 8%|▊ | 424/4990 [01:44<27:52, 2.73it/s] 9%|▊ | 425/4990 [01:44<25:42, 2.96it/s] 9%|▊ | 426/4990 [01:44<23:08, 3.29it/s] 9%|▊ | 427/4990 [01:45<25:01, 3.04it/s] 9%|▊ | 428/4990 [01:45<23:55, 3.18it/s] 9%|▊ | 429/4990 [01:45<22:57, 3.31it/s] 9%|▊ | 430/4990 [01:45<21:47, 3.49it/s] 9%|▊ | 431/4990 [01:46<19:17, 3.94it/s] 9%|▊ | 432/4990 [01:46<18:49, 4.03it/s] 9%|▊ | 433/4990 [01:46<19:46, 3.84it/s] 9%|▊ | 434/4990 [01:46<19:31, 3.89it/s] 9%|▊ | 435/4990 [01:47<19:29, 3.90it/s] 9%|▊ | 436/4990 [01:47<18:44, 4.05it/s] 9%|▉ | 437/4990 [01:47<18:11, 4.17it/s] 9%|▉ | 438/4990 [01:47<17:39, 4.30it/s] 9%|▉ | 439/4990 [01:47<16:36, 4.57it/s] 9%|▉ | 440/4990 [01:48<16:42, 4.54it/s] 9%|▉ | 441/4990 [01:48<15:52, 4.78it/s] 9%|▉ | 442/4990 [01:48<15:44, 4.82it/s] 9%|▉ | 443/4990 [01:48<16:26, 4.61it/s] 9%|▉ | 444/4990 [01:48<15:30, 4.88it/s] 9%|▉ | 445/4990 [01:49<15:50, 4.78it/s] 9%|▉ | 446/4990 [01:49<16:05, 4.71it/s] 9%|▉ | 447/4990 [01:49<16:00, 4.73it/s] 9%|▉ | 448/4990 [01:49<15:47, 4.80it/s] 9%|▉ | 449/4990 [01:50<16:36, 4.56it/s] 9%|▉ | 450/4990 [01:50<17:59, 4.20it/s] 9%|▉ | 451/4990 [01:50<17:28, 4.33it/s] 9%|▉ | 452/4990 [01:50<18:42, 4.04it/s] 9%|▉ | 453/4990 [01:50<17:46, 4.25it/s] 9%|▉ | 454/4990 [01:51<16:56, 4.46it/s] 9%|▉ | 455/4990 [01:51<15:19, 4.93it/s] 9%|▉ | 456/4990 [01:51<16:12, 4.66it/s] 9%|▉ | 457/4990 [01:51<16:12, 4.66it/s] 9%|▉ | 458/4990 [01:51<15:36, 4.84it/s] 9%|▉ | 459/4990 [01:52<15:01, 5.03it/s] 9%|▉ | 460/4990 [01:52<15:43, 4.80it/s] 9%|▉ | 461/4990 [01:52<14:59, 5.04it/s] 9%|▉ | 462/4990 [01:52<14:54, 5.06it/s] 9%|▉ | 463/4990 [01:52<14:54, 5.06it/s] 9%|▉ | 464/4990 [01:53<14:18, 5.27it/s] 9%|▉ | 465/4990 [01:53<14:20, 5.26it/s] 9%|▉ | 466/4990 [01:53<16:22, 4.61it/s] 9%|▉ | 467/4990 [01:53<17:28, 4.31it/s] 9%|▉ | 468/4990 [01:54<16:50, 4.48it/s] 9%|▉ | 469/4990 [01:54<16:32, 4.56it/s] 9%|▉ | 470/4990 [01:54<16:12, 4.65it/s] 9%|▉ | 471/4990 [01:54<15:48, 4.77it/s] 9%|▉ | 472/4990 [01:54<15:39, 4.81it/s] 9%|▉ | 473/4990 [01:55<17:07, 4.40it/s] 9%|▉ | 474/4990 [01:55<16:56, 4.44it/s] 10%|▉ | 475/4990 [01:55<15:53, 4.73it/s] 10%|▉ | 476/4990 [01:55<16:10, 4.65it/s] 10%|▉ | 477/4990 [01:55<14:48, 5.08it/s] 10%|▉ | 478/4990 [01:56<15:06, 4.98it/s] 10%|▉ | 479/4990 [01:56<16:19, 4.60it/s] 10%|▉ | 480/4990 [01:56<20:10, 3.73it/s] 10%|▉ | 481/4990 [01:56<18:18, 4.10it/s] 10%|▉ | 482/4990 [01:57<17:50, 4.21it/s] 10%|▉ | 483/4990 [01:57<18:20, 4.09it/s] 10%|▉ | 484/4990 [01:57<18:05, 4.15it/s] 10%|▉ | 485/4990 [01:57<17:24, 4.32it/s] 10%|▉ | 486/4990 [01:58<18:36, 4.03it/s] 10%|▉ | 487/4990 [01:58<18:48, 3.99it/s] 10%|▉ | 488/4990 [01:58<17:01, 4.41it/s] 10%|▉ | 489/4990 [01:58<18:50, 3.98it/s] 10%|▉ | 490/4990 [01:59<18:55, 3.96it/s] 10%|▉ | 491/4990 [01:59<17:51, 4.20it/s] 10%|▉ | 492/4990 [01:59<20:24, 3.67it/s] 10%|▉ | 493/4990 [01:59<19:10, 3.91it/s] 10%|▉ | 494/4990 [02:00<28:08, 2.66it/s] 10%|▉ | 495/4990 [02:00<24:55, 3.01it/s] 10%|▉ | 496/4990 [02:01<23:38, 3.17it/s] 10%|▉ | 497/4990 [02:01<21:36, 3.47it/s] 10%|▉ | 498/4990 [02:01<20:01, 3.74it/s] 10%|█ | 499/4990 [02:01<18:19, 4.08it/s][INFO|trainer.py:811] 2024-09-05 22:46:40,950 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: id, ner_tags, tokens. If id, ner_tags, tokens are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. | |
| [INFO|trainer.py:3819] 2024-09-05 22:46:40,953 >> | |
| ***** Running Evaluation ***** | |
| [INFO|trainer.py:3821] 2024-09-05 22:46:40,953 >> Num examples = 6810 | |
| [INFO|trainer.py:3824] 2024-09-05 22:46:40,953 >> Batch size = 8 | |
| 0%| | 0/852 [00:00<?, ?it/s][A | |
| 1%| | 10/852 [00:00<00:09, 92.13it/s][A | |
| 2%|▏ | 20/852 [00:00<00:10, 83.09it/s][A | |
| 3%|▎ | 29/852 [00:00<00:10, 80.96it/s][A | |
| 4%|▍ | 38/852 [00:00<00:10, 79.95it/s][A | |
| 6%|▌ | 47/852 [00:00<00:09, 80.68it/s][A | |
| 7%|▋ | 56/852 [00:00<00:09, 82.11it/s][A | |
| 8%|▊ | 65/852 [00:00<00:09, 81.29it/s][A | |
| 9%|▊ | 74/852 [00:00<00:09, 80.27it/s][A | |
| 10%|▉ | 83/852 [00:01<00:09, 80.29it/s][A | |
| 11%|█ | 92/852 [00:01<00:09, 80.69it/s][A | |
| 12%|█▏ | 101/852 [00:01<00:09, 80.35it/s][A | |
| 13%|█▎ | 110/852 [00:01<00:09, 80.34it/s][A | |
| 14%|█▍ | 119/852 [00:01<00:09, 81.26it/s][A | |
| 15%|█▌ | 128/852 [00:01<00:09, 77.90it/s][A | |
| 16%|█▌ | 137/852 [00:01<00:09, 77.65it/s][A | |
| 17%|█▋ | 146/852 [00:01<00:08, 79.18it/s][A | |
| 18%|█▊ | 154/852 [00:01<00:08, 79.13it/s][A | |
| 19%|█▉ | 163/852 [00:02<00:08, 80.56it/s][A | |
| 20%|██ | 172/852 [00:02<00:08, 81.35it/s][A | |
| 21%|██ | 181/852 [00:02<00:08, 81.29it/s][A | |
| 22%|██▏ | 190/852 [00:02<00:08, 81.87it/s][A | |
| 23%|██▎ | 199/852 [00:02<00:08, 81.13it/s][A | |
| 24%|██▍ | 208/852 [00:02<00:08, 79.64it/s][A | |
| 25%|██▌ | 217/852 [00:02<00:07, 80.28it/s][A | |
| 27%|██▋ | 226/852 [00:02<00:07, 80.94it/s][A | |
| 28%|██▊ | 235/852 [00:02<00:07, 81.14it/s][A | |
| 29%|██▊ | 244/852 [00:03<00:07, 78.91it/s][A | |
| 30%|██▉ | 253/852 [00:03<00:07, 81.38it/s][A | |
| 31%|███ | 262/852 [00:03<00:07, 82.99it/s][A | |
| 32%|███▏ | 271/852 [00:03<00:07, 82.27it/s][A | |
| 33%|███▎ | 280/852 [00:03<00:07, 73.21it/s][A | |
| 34%|███▍ | 288/852 [00:03<00:07, 74.75it/s][A | |
| 35%|███▍ | 297/852 [00:03<00:07, 76.92it/s][A | |
| 36%|███▌ | 306/852 [00:03<00:06, 79.20it/s][A | |
| 37%|███▋ | 315/852 [00:03<00:06, 78.62it/s][A | |
| 38%|███▊ | 324/852 [00:04<00:06, 79.99it/s][A | |
| 39%|███▉ | 333/852 [00:04<00:06, 80.76it/s][A | |
| 40%|████ | 342/852 [00:04<00:06, 82.32it/s][A | |
| 41%|████ | 351/852 [00:04<00:06, 83.01it/s][A | |
| 42%|████▏ | 360/852 [00:04<00:06, 79.91it/s][A | |
| 43%|████▎ | 369/852 [00:04<00:06, 80.40it/s][A | |
| 44%|████▍ | 378/852 [00:04<00:05, 80.95it/s][A | |
| 45%|████▌ | 387/852 [00:04<00:05, 80.69it/s][A | |
| 46%|████▋ | 396/852 [00:04<00:05, 81.56it/s][A | |
| 48%|████▊ | 405/852 [00:05<00:05, 79.23it/s][A | |
| 49%|████▊ | 414/852 [00:05<00:05, 80.26it/s][A | |
| 50%|████▉ | 423/852 [00:05<00:05, 81.17it/s][A | |
| 51%|█████ | 432/852 [00:05<00:05, 80.47it/s][A | |
| 52%|█████▏ | 441/852 [00:05<00:04, 82.22it/s][A | |
| 53%|█████▎ | 450/852 [00:05<00:04, 82.08it/s][A | |
| 54%|█████▍ | 459/852 [00:05<00:04, 82.69it/s][A | |
| 55%|█████▍ | 468/852 [00:05<00:04, 79.57it/s][A | |
| 56%|█████▌ | 476/852 [00:05<00:04, 76.48it/s][A | |
| 57%|█████▋ | 484/852 [00:06<00:04, 76.69it/s][A | |
| 58%|█████▊ | 493/852 [00:06<00:04, 79.25it/s][A | |
| 59%|█████▉ | 502/852 [00:06<00:04, 81.12it/s][A | |
| 60%|█████▉ | 511/852 [00:06<00:04, 81.53it/s][A | |
| 61%|██████ | 520/852 [00:06<00:04, 82.38it/s][A | |
| 62%|██████▏ | 529/852 [00:06<00:04, 80.16it/s][A | |
| 63%|██████▎ | 538/852 [00:06<00:03, 81.91it/s][A | |
| 64%|██████▍ | 547/852 [00:06<00:03, 81.08it/s][A | |
| 65%|██████▌ | 556/852 [00:06<00:03, 78.18it/s][A | |
| 66%|██████▋ | 565/852 [00:07<00:03, 80.35it/s][A | |
| 67%|██████▋ | 574/852 [00:07<00:03, 81.19it/s][A | |
| 68%|██████▊ | 583/852 [00:07<00:03, 80.70it/s][A | |
| 69%|██████▉ | 592/852 [00:07<00:03, 80.43it/s][A | |
| 71%|███████ | 601/852 [00:07<00:03, 80.49it/s][A | |
| 72%|███████▏ | 610/852 [00:07<00:02, 80.86it/s][A | |
| 73%|███████▎ | 619/852 [00:07<00:02, 79.04it/s][A | |
| 74%|███████▎ | 627/852 [00:07<00:02, 78.94it/s][A | |
| 75%|███████▍ | 635/852 [00:07<00:02, 78.41it/s][A | |
| 75%|███████▌ | 643/852 [00:08<00:02, 76.41it/s][A | |
| 77%|███████▋ | 652/852 [00:08<00:02, 78.97it/s][A | |
| 78%|███████▊ | 661/852 [00:08<00:02, 80.15it/s][A | |
| 79%|███████▊ | 670/852 [00:08<00:02, 80.54it/s][A | |
| 80%|███████▉ | 679/852 [00:08<00:02, 80.46it/s][A | |
| 81%|████████ | 688/852 [00:08<00:02, 81.20it/s][A | |
| 82%|████████▏ | 697/852 [00:08<00:01, 81.93it/s][A | |
| 83%|████████▎ | 706/852 [00:08<00:01, 83.09it/s][A | |
| 84%|████████▍ | 715/852 [00:08<00:01, 83.40it/s][A | |
| 85%|████████▍ | 724/852 [00:09<00:01, 82.90it/s][A | |
| 86%|████████▌ | 733/852 [00:09<00:01, 83.77it/s][A | |
| 87%|████████▋ | 742/852 [00:09<00:01, 84.34it/s][A | |
| 88%|████████▊ | 751/852 [00:09<00:01, 83.18it/s][A | |
| 89%|████████▉ | 760/852 [00:09<00:01, 84.50it/s][A | |
| 90%|█████████ | 769/852 [00:09<00:01, 82.87it/s][A | |
| 91%|█████████▏| 778/852 [00:09<00:00, 82.40it/s][A | |
| 92%|█████████▏| 787/852 [00:09<00:00, 81.73it/s][A | |
| 93%|█████████▎| 796/852 [00:09<00:00, 82.64it/s][A | |
| 94%|█████████▍| 805/852 [00:09<00:00, 83.74it/s][A | |
| 96%|█████████▌| 814/852 [00:10<00:00, 82.67it/s][A | |
| 97%|█████████▋| 823/852 [00:10<00:00, 83.63it/s][A | |
| 98%|█████████▊| 832/852 [00:10<00:00, 84.37it/s][A | |
| 99%|█████████▊| 841/852 [00:10<00:00, 83.41it/s][A | |
| 100%|█████████▉| 850/852 [00:10<00:00, 81.97it/s][A | |
| [A 10%|█ | 499/4990 [02:16<18:19, 4.08it/s] | |
| 100%|██████████| 852/852 [00:14<00:00, 81.97it/s][A | |
| [A[INFO|trainer.py:3503] 2024-09-05 22:46:55,159 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-499 | |
| [INFO|configuration_utils.py:472] 2024-09-05 22:46:55,160 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-499/config.json | |
| [INFO|modeling_utils.py:2799] 2024-09-05 22:46:56,182 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-499/model.safetensors | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-05 22:46:56,183 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-499/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-05 22:46:56,183 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-499/special_tokens_map.json | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-05 22:46:58,215 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-05 22:46:58,215 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json | |
| 10%|█ | 500/4990 [02:19<6:45:16, 5.42s/it] 10%|█ | 500/4990 [02:19<6:45:16, 5.42s/it] 10%|█ | 501/4990 [02:19<4:48:18, 3.85s/it] 10%|█ | 502/4990 [02:19<3:26:57, 2.77s/it] 10%|█ | 503/4990 [02:19<2:30:05, 2.01s/it] 10%|█ | 504/4990 [02:20<1:50:49, 1.48s/it] 10%|█ | 505/4990 [02:20<1:24:52, 1.14s/it] 10%|█ | 506/4990 [02:20<1:04:26, 1.16it/s] 10%|█ | 507/4990 [02:20<49:53, 1.50it/s] 10%|█ | 508/4990 [02:21<41:00, 1.82it/s] 10%|█ | 509/4990 [02:21<33:10, 2.25it/s] 10%|█ | 510/4990 [02:21<27:07, 2.75it/s] 10%|█ | 511/4990 [02:21<23:16, 3.21it/s] 10%|█ | 512/4990 [02:21<21:02, 3.55it/s] 10%|█ | 513/4990 [02:22<18:52, 3.95it/s] 10%|█ | 514/4990 [02:22<22:26, 3.32it/s] 10%|█ | 515/4990 [02:22<20:00, 3.73it/s] 10%|█ | 516/4990 [02:22<18:22, 4.06it/s] 10%|█ | 517/4990 [02:23<17:28, 4.27it/s] 10%|█ | 518/4990 [02:23<16:30, 4.52it/s] 10%|█ | 519/4990 [02:23<18:31, 4.02it/s] 10%|█ | 520/4990 [02:23<16:33, 4.50it/s] 10%|█ | 521/4990 [02:24<16:20, 4.56it/s] 10%|█ | 522/4990 [02:24<16:24, 4.54it/s] 10%|█ | 523/4990 [02:24<15:59, 4.65it/s] 11%|█ | 524/4990 [02:24<19:35, 3.80it/s] 11%|█ | 525/4990 [02:25<19:32, 3.81it/s] 11%|█ | 526/4990 [02:25<18:10, 4.09it/s] 11%|█ | 527/4990 [02:25<17:04, 4.36it/s] 11%|█ | 528/4990 [02:25<17:16, 4.31it/s] 11%|█ | 529/4990 [02:25<17:11, 4.33it/s] 11%|█ | 530/4990 [02:26<16:46, 4.43it/s] 11%|█ | 531/4990 [02:26<15:43, 4.73it/s] 11%|█ | 532/4990 [02:26<15:18, 4.85it/s] 11%|█ | 533/4990 [02:26<15:13, 4.88it/s] 11%|█ | 534/4990 [02:27<28:20, 2.62it/s] 11%|█ | 535/4990 [02:27<24:26, 3.04it/s] 11%|█ | 536/4990 [02:28<22:16, 3.33it/s] 11%|█ | 537/4990 [02:28<22:43, 3.27it/s] 11%|█ | 538/4990 [02:28<22:19, 3.32it/s] 11%|█ | 539/4990 [02:28<20:12, 3.67it/s] 11%|█ | 540/4990 [02:29<21:08, 3.51it/s] 11%|█ | 541/4990 [02:29<19:02, 3.89it/s] 11%|█ | 542/4990 [02:29<17:45, 4.17it/s] 11%|█ | 543/4990 [02:29<16:52, 4.39it/s] 11%|█ | 544/4990 [02:29<15:30, 4.78it/s] 11%|█ | 545/4990 [02:30<16:11, 4.58it/s] 11%|█ | 546/4990 [02:30<16:42, 4.43it/s] 11%|█ | 547/4990 [02:30<15:52, 4.66it/s] 11%|█ | 548/4990 [02:30<16:27, 4.50it/s] 11%|█ | 549/4990 [02:31<22:41, 3.26it/s] 11%|█ | 550/4990 [02:31<22:32, 3.28it/s] 11%|█ | 551/4990 [02:31<22:49, 3.24it/s] 11%|█ | 552/4990 [02:32<19:56, 3.71it/s] 11%|█ | 553/4990 [02:32<18:11, 4.06it/s] 11%|█ | 554/4990 [02:32<19:06, 3.87it/s] 11%|█ | 555/4990 [02:32<17:31, 4.22it/s] 11%|█ | 556/4990 [02:32<16:52, 4.38it/s] 11%|█ | 557/4990 [02:33<16:57, 4.36it/s] 11%|█ | 558/4990 [02:33<16:32, 4.47it/s] 11%|█ | 559/4990 [02:33<16:17, 4.53it/s] 11%|█ | 560/4990 [02:33<17:38, 4.19it/s] 11%|█ | 561/4990 [02:34<29:58, 2.46it/s] 11%|█▏ | 562/4990 [02:34<26:44, 2.76it/s] 11%|█▏ | 563/4990 [02:35<29:38, 2.49it/s] 11%|█▏ | 564/4990 [02:35<24:19, 3.03it/s] 11%|█▏ | 565/4990 [02:35<22:20, 3.30it/s] 11%|█▏ | 566/4990 [02:36<19:36, 3.76it/s] 11%|█▏ | 567/4990 [02:36<18:36, 3.96it/s] 11%|█▏ | 568/4990 [02:36<18:25, 4.00it/s] 11%|█▏ | 569/4990 [02:36<17:19, 4.25it/s] 11%|█▏ | 570/4990 [02:37<18:45, 3.93it/s] 11%|█▏ | 571/4990 [02:37<18:27, 3.99it/s] 11%|█▏ | 572/4990 [02:37<21:34, 3.41it/s] 11%|█▏ | 573/4990 [02:37<21:03, 3.50it/s] 12%|█▏ | 574/4990 [02:38<19:30, 3.77it/s] 12%|█▏ | 575/4990 [02:38<18:21, 4.01it/s] 12%|█▏ | 576/4990 [02:38<17:29, 4.21it/s] 12%|█▏ | 577/4990 [02:38<17:17, 4.25it/s] 12%|█▏ | 578/4990 [02:38<16:36, 4.43it/s] 12%|█▏ | 579/4990 [02:39<17:44, 4.14it/s] 12%|█▏ | 580/4990 [02:39<18:01, 4.08it/s] 12%|█▏ | 581/4990 [02:39<22:05, 3.33it/s] 12%|█▏ | 582/4990 [02:40<20:32, 3.58it/s] 12%|█▏ | 583/4990 [02:40<18:21, 4.00it/s] 12%|█▏ | 584/4990 [02:40<17:22, 4.23it/s] 12%|█▏ | 585/4990 [02:40<15:44, 4.66it/s] 12%|█▏ | 586/4990 [02:40<14:56, 4.91it/s] 12%|█▏ | 587/4990 [02:41<15:23, 4.77it/s] 12%|█▏ | 588/4990 [02:41<15:02, 4.88it/s] 12%|█▏ | 589/4990 [02:41<15:48, 4.64it/s] 12%|█▏ | 590/4990 [02:41<16:13, 4.52it/s] 12%|█▏ | 591/4990 [02:42<16:01, 4.58it/s] 12%|█▏ | 592/4990 [02:42<16:48, 4.36it/s] 12%|█▏ | 593/4990 [02:42<17:41, 4.14it/s] 12%|█▏ | 594/4990 [02:42<18:45, 3.91it/s] 12%|█▏ | 595/4990 [02:43<18:12, 4.02it/s] 12%|█▏ | 596/4990 [02:43<16:06, 4.55it/s] 12%|█▏ | 597/4990 [02:43<15:39, 4.67it/s] 12%|█▏ | 598/4990 [02:43<17:10, 4.26it/s] 12%|█▏ | 599/4990 [02:43<17:44, 4.12it/s] 12%|█▏ | 600/4990 [02:44<17:03, 4.29it/s] 12%|█▏ | 601/4990 [02:44<16:09, 4.53it/s] 12%|█▏ | 602/4990 [02:44<15:17, 4.78it/s] 12%|█▏ | 603/4990 [02:44<15:23, 4.75it/s] 12%|█▏ | 604/4990 [02:44<14:31, 5.04it/s] 12%|█▏ | 605/4990 [02:45<16:54, 4.32it/s] 12%|█▏ | 606/4990 [02:45<17:54, 4.08it/s] 12%|█▏ | 607/4990 [02:45<19:41, 3.71it/s] 12%|█▏ | 608/4990 [02:46<17:59, 4.06it/s] 12%|█▏ | 609/4990 [02:46<17:00, 4.29it/s] 12%|█▏ | 610/4990 [02:46<15:46, 4.63it/s] 12%|█▏ | 611/4990 [02:46<15:23, 4.74it/s] 12%|█▏ | 612/4990 [02:46<14:48, 4.93it/s] 12%|█▏ | 613/4990 [02:47<15:47, 4.62it/s] 12%|█▏ | 614/4990 [02:47<14:57, 4.88it/s] 12%|█▏ | 615/4990 [02:47<14:19, 5.09it/s] 12%|█▏ | 616/4990 [02:47<14:04, 5.18it/s] 12%|█▏ | 617/4990 [02:47<13:24, 5.44it/s] 12%|█▏ | 618/4990 [02:47<14:28, 5.03it/s] 12%|█▏ | 619/4990 [02:48<15:06, 4.82it/s] 12%|█▏ | 620/4990 [02:48<15:07, 4.82it/s] 12%|█▏ | 621/4990 [02:48<15:22, 4.73it/s] 12%|█▏ | 622/4990 [02:48<15:06, 4.82it/s] 12%|█▏ | 623/4990 [02:49<15:49, 4.60it/s] 13%|█▎ | 624/4990 [02:49<14:46, 4.92it/s] 13%|█▎ | 625/4990 [02:49<14:36, 4.98it/s] 13%|█▎ | 626/4990 [02:49<14:10, 5.13it/s] 13%|█▎ | 627/4990 [02:49<14:20, 5.07it/s] 13%|█▎ | 628/4990 [02:50<18:54, 3.85it/s] |