| 2024-09-09 12:14:35.494661: 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`. | |
| 2024-09-09 12:14:35.513016: 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 | |
| 2024-09-09 12:14:35.535014: 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 | |
| 2024-09-09 12:14:35.541769: 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 | |
| 2024-09-09 12:14:35.557993: 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. | |
| 2024-09-09 12:14:36.793402: 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( | |
| 09/09/2024 12:14:38 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False | |
| 09/09/2024 12:14:38 - 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%| | 0.00/3.92k [00:00<?, ?B/s] Downloading builder script: 100%|██████████| 3.92k/3.92k [00:00<00:00, 16.0kB/s] Downloading builder script: 100%|██████████| 3.92k/3.92k [00:00<00:00, 16.0kB/s] | |
| Downloading data: 0%| | 0.00/13.7M [00:00<?, ?B/s] Downloading data: 77%|███████▋ | 10.5M/13.7M [00:00<00:00, 10.6MB/s] Downloading data: 100%|██████████| 13.7M/13.7M [00:01<00:00, 11.9MB/s] Downloading data: 100%|██████████| 13.7M/13.7M [00:01<00:00, 11.6MB/s] | |
| Downloading data: 0%| | 0.00/2.93M [00:00<?, ?B/s] Downloading data: 100%|██████████| 2.93M/2.93M [00:00<00:00, 4.24MB/s] Downloading data: 100%|██████████| 2.93M/2.93M [00:00<00:00, 4.22MB/s] | |
| Downloading data: 0%| | 0.00/4.78M [00:00<?, ?B/s] Downloading data: 100%|██████████| 4.78M/4.78M [00:00<00:00, 5.09MB/s] Downloading data: 100%|██████████| 4.78M/4.78M [00:00<00:00, 5.06MB/s] | |
| Generating train split: 0 examples [00:00, ? examples/s] Generating train split: 560 examples [00:00, 5579.69 examples/s] Generating train split: 1362 examples [00:00, 5414.73 examples/s] Generating train split: 1937 examples [00:00, 5541.43 examples/s] Generating train split: 2738 examples [00:00, 5446.93 examples/s] Generating train split: 3592 examples [00:00, 5464.58 examples/s] Generating train split: 4404 examples [00:00, 5442.51 examples/s] Generating train split: 4974 examples [00:00, 5505.21 examples/s] Generating train split: 5832 examples [00:01, 5579.00 examples/s] Generating train split: 6663 examples [00:01, 5563.41 examples/s] Generating train split: 7496 examples [00:01, 5556.89 examples/s] Generating train split: 8300 examples [00:01, 5487.46 examples/s] Generating train split: 8913 examples [00:01, 5633.76 examples/s] Generating train split: 9706 examples [00:01, 5515.35 examples/s] Generating train split: 10294 examples [00:01, 5512.88 examples/s] Generating train split: 10885 examples [00:01, 5612.39 examples/s] Generating train split: 10936 examples [00:01, 5509.85 examples/s] | |
| Generating validation split: 0 examples [00:00, ? examples/s] Generating validation split: 652 examples [00:00, 6495.55 examples/s] Generating validation split: 1504 examples [00:00, 5932.88 examples/s] Generating validation split: 2343 examples [00:00, 5760.31 examples/s] Generating validation split: 2519 examples [00:00, 5753.19 examples/s] | |
| Generating test split: 0 examples [00:00, ? examples/s] Generating test split: 635 examples [00:00, 6320.94 examples/s] Generating test split: 1483 examples [00:00, 5864.12 examples/s] Generating test split: 2322 examples [00:00, 5720.53 examples/s] Generating test split: 2953 examples [00:00, 5902.47 examples/s] Generating test split: 3809 examples [00:00, 5809.22 examples/s] Generating test split: 4047 examples [00:00, 5752.07 examples/s] | |
| [INFO|configuration_utils.py:733] 2024-09-09 12:14:50,533 >> 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] 2024-09-09 12:14:50,537 >> 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-SINTOMA", | |
| "2": "I-SINTOMA" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "B-SINTOMA": 1, | |
| "I-SINTOMA": 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] 2024-09-09 12:14:50,787 >> 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] 2024-09-09 12:14:50,788 >> 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] 2024-09-09 12:14:50,800 >> 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] 2024-09-09 12:14:50,801 >> 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] 2024-09-09 12:14:50,801 >> loading file tokenizer.json from cache at None | |
| [INFO|tokenization_utils_base.py:2269] 2024-09-09 12:14:50,801 >> loading file added_tokens.json from cache at None | |
| [INFO|tokenization_utils_base.py:2269] 2024-09-09 12:14:50,801 >> 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] 2024-09-09 12:14:50,801 >> 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] 2024-09-09 12:14:50,801 >> 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] 2024-09-09 12:14:50,802 >> 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] 2024-09-09 12:14:50,882 >> 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] 2024-09-09 12:14:50,883 >> 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] 2024-09-09 12:14:51,213 >> 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] 2024-09-09 12:14:51,293 >> 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] 2024-09-09 12:14:51,293 >> 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%| | 0/10936 [00:00<?, ? examples/s] Map: 9%|▉ | 1000/10936 [00:00<00:03, 3028.63 examples/s] Map: 18%|█▊ | 2000/10936 [00:00<00:01, 5033.04 examples/s] Map: 27%|██▋ | 3000/10936 [00:00<00:01, 6438.12 examples/s] Map: 37%|███▋ | 4000/10936 [00:00<00:00, 7461.99 examples/s] Map: 46%|████▌ | 5000/10936 [00:00<00:00, 8144.27 examples/s] Map: 64%|██████▍ | 7000/10936 [00:00<00:00, 9096.05 examples/s] Map: 73%|███████▎ | 8000/10936 [00:01<00:00, 9263.87 examples/s] Map: 91%|█████████▏| 10000/10936 [00:01<00:00, 9598.21 examples/s] Map: 100%|██████████| 10936/10936 [00:01<00:00, 8157.31 examples/s] | |
| Map: 0%| | 0/2519 [00:00<?, ? examples/s] Map: 79%|███████▉ | 2000/2519 [00:00<00:00, 10345.28 examples/s] Map: 100%|██████████| 2519/2519 [00:00<00:00, 10154.28 examples/s] | |
| Map: 0%| | 0/4047 [00:00<?, ? examples/s] Map: 49%|████▉ | 2000/4047 [00:00<00:00, 10228.61 examples/s] Map: 99%|█████████▉| 4000/4047 [00:00<00:00, 10327.08 examples/s] Map: 100%|██████████| 4047/4047 [00:00<00:00, 10160.37 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) | |
| [INFO|trainer.py:811] 2024-09-09 12:14:55,082 >> The following columns in the training set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: ner_tags, id, tokens. If ner_tags, id, tokens are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. | |
| [INFO|trainer.py:2134] 2024-09-09 12:14:55,636 >> ***** Running training ***** | |
| [INFO|trainer.py:2135] 2024-09-09 12:14:55,636 >> Num examples = 10,936 | |
| [INFO|trainer.py:2136] 2024-09-09 12:14:55,636 >> Num Epochs = 10 | |
| [INFO|trainer.py:2137] 2024-09-09 12:14:55,636 >> Instantaneous batch size per device = 32 | |
| [INFO|trainer.py:2140] 2024-09-09 12:14:55,636 >> Total train batch size (w. parallel, distributed & accumulation) = 64 | |
| [INFO|trainer.py:2141] 2024-09-09 12:14:55,636 >> Gradient Accumulation steps = 2 | |
| [INFO|trainer.py:2142] 2024-09-09 12:14:55,636 >> Total optimization steps = 1,710 | |
| [INFO|trainer.py:2143] 2024-09-09 12:14:55,637 >> Number of trainable parameters = 124,055,043 | |
| 0%| | 0/1710 [00:00<?, ?it/s] 0%| | 1/1710 [00:01<32:09, 1.13s/it] 0%| | 2/1710 [00:01<19:10, 1.48it/s] 0%| | 3/1710 [00:01<16:10, 1.76it/s] 0%| | 4/1710 [00:02<14:04, 2.02it/s] 0%| | 5/1710 [00:02<13:32, 2.10it/s] 0%| | 6/1710 [00:03<14:07, 2.01it/s] 0%| | 7/1710 [00:03<12:53, 2.20it/s] 0%| | 8/1710 [00:04<12:12, 2.32it/s] 1%| | 9/1710 [00:04<12:30, 2.27it/s] 1%| | 10/1710 [00:04<11:41, 2.42it/s] 1%| | 11/1710 [00:05<12:06, 2.34it/s] 1%| | 12/1710 [00:05<13:56, 2.03it/s] 1%| | 13/1710 [00:06<14:13, 1.99it/s] 1%| | 14/1710 [00:06<14:10, 2.00it/s] 1%| | 15/1710 [00:07<14:07, 2.00it/s] 1%| | 16/1710 [00:08<15:00, 1.88it/s] 1%| | 17/1710 [00:08<13:46, 2.05it/s] 1%| | 18/1710 [00:08<13:39, 2.06it/s] 1%| | 19/1710 [00:09<12:48, 2.20it/s] 1%| | 20/1710 [00:09<12:31, 2.25it/s] 1%| | 21/1710 [00:10<12:28, 2.26it/s] 1%|▏ | 22/1710 [00:10<14:21, 1.96it/s] 1%|▏ | 23/1710 [00:11<14:32, 1.93it/s] 1%|▏ | 24/1710 [00:11<13:26, 2.09it/s] 1%|▏ | 25/1710 [00:12<14:27, 1.94it/s] 2%|▏ | 26/1710 [00:12<13:07, 2.14it/s] 2%|▏ | 27/1710 [00:13<14:22, 1.95it/s] 2%|▏ | 28/1710 [00:13<13:51, 2.02it/s] 2%|▏ | 29/1710 [00:14<14:49, 1.89it/s] 2%|▏ | 30/1710 [00:14<13:40, 2.05it/s] 2%|▏ | 31/1710 [00:15<13:01, 2.15it/s] 2%|▏ | 32/1710 [00:15<14:15, 1.96it/s] 2%|▏ | 33/1710 [00:16<18:22, 1.52it/s] 2%|▏ | 34/1710 [00:17<18:55, 1.48it/s] 2%|▏ | 35/1710 [00:17<16:24, 1.70it/s] 2%|▏ | 36/1710 [00:18<14:21, 1.94it/s] 2%|▏ | 37/1710 [00:19<17:15, 1.62it/s] 2%|▏ | 38/1710 [00:19<15:50, 1.76it/s] 2%|▏ | 39/1710 [00:19<14:13, 1.96it/s] 2%|▏ | 40/1710 [00:20<14:20, 1.94it/s] 2%|▏ | 41/1710 [00:20<13:25, 2.07it/s] 2%|▏ | 42/1710 [00:21<14:16, 1.95it/s] 3%|▎ | 43/1710 [00:21<14:07, 1.97it/s] 3%|▎ | 44/1710 [00:22<13:33, 2.05it/s] 3%|▎ | 45/1710 [00:22<12:56, 2.14it/s] 3%|▎ | 46/1710 [00:23<12:49, 2.16it/s] 3%|▎ | 47/1710 [00:23<12:51, 2.16it/s] 3%|▎ | 48/1710 [00:24<12:06, 2.29it/s] 3%|▎ | 49/1710 [00:24<15:02, 1.84it/s] 3%|▎ | 50/1710 [00:25<14:06, 1.96it/s] 3%|▎ | 51/1710 [00:25<13:11, 2.10it/s] 3%|▎ | 52/1710 [00:26<12:45, 2.17it/s] 3%|▎ | 53/1710 [00:26<12:22, 2.23it/s] 3%|▎ | 54/1710 [00:27<12:33, 2.20it/s] 3%|▎ | 55/1710 [00:27<15:05, 1.83it/s] 3%|▎ | 56/1710 [00:28<13:50, 1.99it/s] 3%|▎ | 57/1710 [00:28<13:48, 2.00it/s] 3%|▎ | 58/1710 [00:29<12:17, 2.24it/s] 3%|▎ | 59/1710 [00:29<11:30, 2.39it/s] 4%|▎ | 60/1710 [00:29<11:26, 2.40it/s] 4%|▎ | 61/1710 [00:30<12:02, 2.28it/s] 4%|▎ | 62/1710 [00:31<14:35, 1.88it/s] 4%|▎ | 63/1710 [00:31<13:25, 2.05it/s] 4%|▎ | 64/1710 [00:31<12:02, 2.28it/s] 4%|▍ | 65/1710 [00:32<12:17, 2.23it/s] 4%|▍ | 66/1710 [00:32<11:20, 2.42it/s] 4%|▍ | 67/1710 [00:33<12:26, 2.20it/s] 4%|▍ | 68/1710 [00:33<12:17, 2.23it/s] 4%|▍ | 69/1710 [00:33<12:09, 2.25it/s] 4%|▍ | 70/1710 [00:34<12:14, 2.23it/s] 4%|▍ | 71/1710 [00:34<11:59, 2.28it/s] 4%|▍ | 72/1710 [00:35<12:12, 2.24it/s] 4%|▍ | 73/1710 [00:35<11:23, 2.40it/s] 4%|▍ | 74/1710 [00:36<11:55, 2.29it/s] 4%|▍ | 75/1710 [00:36<11:33, 2.36it/s] 4%|▍ | 76/1710 [00:37<13:03, 2.09it/s] 5%|▍ | 77/1710 [00:37<13:12, 2.06it/s] 5%|▍ | 78/1710 [00:38<14:10, 1.92it/s] 5%|▍ | 79/1710 [00:38<14:31, 1.87it/s] 5%|▍ | 80/1710 [00:39<13:57, 1.95it/s] 5%|▍ | 81/1710 [00:39<13:52, 1.96it/s] 5%|▍ | 82/1710 [00:40<12:48, 2.12it/s] 5%|▍ | 83/1710 [00:40<14:18, 1.90it/s] 5%|▍ | 84/1710 [00:41<13:36, 1.99it/s] 5%|▍ | 85/1710 [00:41<12:53, 2.10it/s] 5%|▌ | 86/1710 [00:42<12:27, 2.17it/s] 5%|▌ | 87/1710 [00:42<12:30, 2.16it/s] 5%|▌ | 88/1710 [00:43<12:09, 2.22it/s] 5%|▌ | 89/1710 [00:43<12:54, 2.09it/s] 5%|▌ | 90/1710 [00:43<12:16, 2.20it/s] 5%|▌ | 91/1710 [00:44<12:47, 2.11it/s] 5%|▌ | 92/1710 [00:44<12:29, 2.16it/s] 5%|▌ | 93/1710 [00:45<12:22, 2.18it/s] 5%|▌ | 94/1710 [00:45<12:03, 2.23it/s] 6%|▌ | 95/1710 [00:46<12:00, 2.24it/s] 6%|▌ | 96/1710 [00:46<13:09, 2.05it/s] 6%|▌ | 97/1710 [00:47<12:05, 2.22it/s] 6%|▌ | 98/1710 [00:47<11:19, 2.37it/s] 6%|▌ | 99/1710 [00:47<10:59, 2.44it/s] 6%|▌ | 100/1710 [00:48<11:51, 2.26it/s] 6%|▌ | 101/1710 [00:48<11:43, 2.29it/s] 6%|▌ | 102/1710 [00:49<11:46, 2.28it/s] 6%|▌ | 103/1710 [00:49<11:30, 2.33it/s] 6%|▌ | 104/1710 [00:50<12:02, 2.22it/s] 6%|▌ | 105/1710 [00:50<11:09, 2.40it/s] 6%|▌ | 106/1710 [00:50<11:00, 2.43it/s] 6%|▋ | 107/1710 [00:51<11:12, 2.38it/s] 6%|▋ | 108/1710 [00:51<10:58, 2.43it/s] 6%|▋ | 109/1710 [00:52<10:58, 2.43it/s] 6%|▋ | 110/1710 [00:52<11:53, 2.24it/s] 6%|▋ | 111/1710 [00:53<11:47, 2.26it/s] 7%|▋ | 112/1710 [00:53<11:39, 2.29it/s] 7%|▋ | 113/1710 [00:53<11:16, 2.36it/s] 7%|▋ | 114/1710 [00:54<11:12, 2.37it/s] 7%|▋ | 115/1710 [00:54<10:35, 2.51it/s] 7%|▋ | 116/1710 [00:55<11:13, 2.37it/s] 7%|▋ | 117/1710 [00:55<11:17, 2.35it/s] 7%|▋ | 118/1710 [00:56<14:58, 1.77it/s] 7%|▋ | 119/1710 [00:56<14:07, 1.88it/s] 7%|▋ | 120/1710 [00:57<13:45, 1.93it/s] 7%|▋ | 121/1710 [00:57<12:26, 2.13it/s] 7%|▋ | 122/1710 [00:58<11:56, 2.22it/s] 7%|▋ | 123/1710 [00:58<11:05, 2.39it/s] 7%|▋ | 124/1710 [00:58<10:58, 2.41it/s] 7%|▋ | 125/1710 [00:59<10:03, 2.63it/s] 7%|▋ | 126/1710 [00:59<10:30, 2.51it/s] 7%|▋ | 127/1710 [01:00<10:41, 2.47it/s] 7%|▋ | 128/1710 [01:00<10:48, 2.44it/s] 8%|▊ | 129/1710 [01:00<10:51, 2.42it/s] 8%|▊ | 130/1710 [01:01<11:48, 2.23it/s] 8%|▊ | 131/1710 [01:01<11:11, 2.35it/s] 8%|▊ | 132/1710 [01:02<11:31, 2.28it/s] 8%|▊ | 133/1710 [01:02<11:40, 2.25it/s] 8%|▊ | 134/1710 [01:03<10:50, 2.42it/s] 8%|▊ | 135/1710 [01:03<10:17, 2.55it/s] 8%|▊ | 136/1710 [01:03<10:39, 2.46it/s] 8%|▊ | 137/1710 [01:04<11:22, 2.30it/s] 8%|▊ | 138/1710 [01:04<11:21, 2.31it/s] 8%|▊ | 139/1710 [01:05<11:55, 2.20it/s] 8%|▊ | 140/1710 [01:06<14:01, 1.87it/s] 8%|▊ | 141/1710 [01:06<12:55, 2.02it/s] 8%|▊ | 142/1710 [01:07<13:39, 1.91it/s] 8%|▊ | 143/1710 [01:07<12:42, 2.06it/s] 8%|▊ | 144/1710 [01:07<11:24, 2.29it/s] 8%|▊ | 145/1710 [01:08<11:51, 2.20it/s] 9%|▊ | 146/1710 [01:08<12:38, 2.06it/s] 9%|▊ | 147/1710 [01:09<12:53, 2.02it/s] 9%|▊ | 148/1710 [01:09<11:37, 2.24it/s] 9%|▊ | 149/1710 [01:10<13:00, 2.00it/s] 9%|▉ | 150/1710 [01:10<13:03, 1.99it/s] 9%|▉ | 151/1710 [01:11<12:32, 2.07it/s] 9%|▉ | 152/1710 [01:11<12:23, 2.10it/s] 9%|▉ | 153/1710 [01:12<11:41, 2.22it/s] 9%|▉ | 154/1710 [01:12<11:02, 2.35it/s] 9%|▉ | 155/1710 [01:12<10:28, 2.48it/s] 9%|▉ | 156/1710 [01:13<11:00, 2.35it/s] 9%|▉ | 157/1710 [01:13<10:35, 2.44it/s] 9%|▉ | 158/1710 [01:14<10:03, 2.57it/s] 9%|▉ | 159/1710 [01:14<10:55, 2.37it/s] 9%|▉ | 160/1710 [01:14<11:03, 2.34it/s] 9%|▉ | 161/1710 [01:15<10:27, 2.47it/s] 9%|▉ | 162/1710 [01:15<10:53, 2.37it/s] 10%|▉ | 163/1710 [01:16<11:08, 2.31it/s] 10%|▉ | 164/1710 [01:16<10:45, 2.39it/s] 10%|▉ | 165/1710 [01:17<11:08, 2.31it/s] 10%|▉ | 166/1710 [01:17<12:47, 2.01it/s] 10%|▉ | 167/1710 [01:18<11:48, 2.18it/s] 10%|▉ | 168/1710 [01:18<11:28, 2.24it/s] 10%|▉ | 169/1710 [01:19<12:21, 2.08it/s] 10%|▉ | 170/1710 [01:19<11:20, 2.26it/s] 10%|█ | 171/1710 [01:19<11:08, 2.30it/s][INFO|trainer.py:811] 2024-09-09 12:16:15,508 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: ner_tags, id, tokens. If ner_tags, id, tokens are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. | |
| [INFO|trainer.py:3819] 2024-09-09 12:16:15,510 >> | |
| ***** Running Evaluation ***** | |
| [INFO|trainer.py:3821] 2024-09-09 12:16:15,510 >> Num examples = 2519 | |
| [INFO|trainer.py:3824] 2024-09-09 12:16:15,510 >> Batch size = 8 | |
| 0%| | 0/315 [00:00<?, ?it/s][A | |
| 3%|▎ | 8/315 [00:00<00:04, 74.15it/s][A | |
| 5%|▌ | 16/315 [00:00<00:04, 72.87it/s][A | |
| 8%|▊ | 24/315 [00:00<00:03, 74.59it/s][A | |
| 10%|█ | 32/315 [00:00<00:04, 70.63it/s][A | |
| 13%|█▎ | 40/315 [00:00<00:03, 71.80it/s][A | |
| 15%|█▌ | 48/315 [00:00<00:03, 72.49it/s][A | |
| 18%|█▊ | 56/315 [00:00<00:03, 72.18it/s][A | |
| 20%|██ | 64/315 [00:00<00:03, 70.11it/s][A | |
| 23%|██▎ | 72/315 [00:00<00:03, 72.26it/s][A | |
| 25%|██▌ | 80/315 [00:01<00:03, 68.95it/s][A | |
| 28%|██▊ | 87/315 [00:01<00:03, 67.94it/s][A | |
| 30%|███ | 95/315 [00:01<00:03, 69.32it/s][A | |
| 32%|███▏ | 102/315 [00:01<00:03, 65.97it/s][A | |
| 35%|███▍ | 110/315 [00:01<00:02, 68.77it/s][A | |
| 37%|███▋ | 118/315 [00:01<00:02, 70.24it/s][A | |
| 40%|████ | 126/315 [00:01<00:02, 67.00it/s][A | |
| 43%|████▎ | 134/315 [00:01<00:02, 67.51it/s][A | |
| 45%|████▍ | 141/315 [00:02<00:02, 68.03it/s][A | |
| 47%|████▋ | 149/315 [00:02<00:02, 70.61it/s][A | |
| 50%|████▉ | 157/315 [00:02<00:02, 72.86it/s][A | |
| 52%|█████▏ | 165/315 [00:02<00:02, 71.30it/s][A | |
| 55%|█████▍ | 173/315 [00:02<00:02, 70.07it/s][A | |
| 57%|█████▋ | 181/315 [00:02<00:01, 67.81it/s][A | |
| 60%|██████ | 189/315 [00:02<00:01, 68.05it/s][A | |
| 62%|██████▏ | 196/315 [00:02<00:01, 67.00it/s][A | |
| 64%|██████▍ | 203/315 [00:02<00:01, 64.45it/s][A | |
| 67%|██████▋ | 210/315 [00:03<00:01, 65.01it/s][A | |
| 69%|██████▉ | 218/315 [00:03<00:01, 68.74it/s][A | |
| 72%|███████▏ | 226/315 [00:03<00:01, 71.36it/s][A | |
| 75%|███████▍ | 235/315 [00:03<00:01, 74.60it/s][A | |
| 77%|███████▋ | 243/315 [00:03<00:01, 70.81it/s][A | |
| 80%|███████▉ | 251/315 [00:03<00:00, 70.96it/s][A | |
| 82%|████████▏ | 259/315 [00:03<00:00, 68.92it/s][A | |
| 85%|████████▍ | 267/315 [00:03<00:00, 70.16it/s][A | |
| 88%|████████▊ | 276/315 [00:03<00:00, 73.45it/s][A | |
| 90%|█████████ | 284/315 [00:04<00:00, 73.52it/s][A | |
| 93%|█████████▎| 292/315 [00:04<00:00, 71.60it/s][A | |
| 95%|█████████▌| 300/315 [00:04<00:00, 71.31it/s][A | |
| 98%|█████████▊| 308/315 [00:04<00:00, 71.30it/s][A | |
| [A 10%|█ | 171/1710 [01:25<11:08, 2.30it/s] | |
| 100%|██████████| 315/315 [00:05<00:00, 71.30it/s][A | |
| [A[INFO|trainer.py:3503] 2024-09-09 12:16:21,499 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-171 | |
| [INFO|configuration_utils.py:472] 2024-09-09 12:16:21,501 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-171/config.json | |
| [INFO|modeling_utils.py:2799] 2024-09-09 12:16:22,527 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-171/model.safetensors | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:16:22,528 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-171/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:16:22,529 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-171/special_tokens_map.json | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:16:25,565 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:16:25,565 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json | |
| 10%|█ | 172/1710 [01:30<1:27:43, 3.42s/it] 10%|█ | 173/1710 [01:30<1:05:49, 2.57s/it] 10%|█ | 174/1710 [01:31<49:01, 1.92s/it] 10%|█ | 175/1710 [01:31<37:24, 1.46s/it] 10%|█ | 176/1710 [01:32<29:43, 1.16s/it] 10%|█ | 177/1710 [01:32<23:13, 1.10it/s] 10%|█ | 178/1710 [01:32<19:22, 1.32it/s] 10%|█ | 179/1710 [01:33<16:39, 1.53it/s] 11%|█ | 180/1710 [01:33<14:52, 1.71it/s] 11%|█ | 181/1710 [01:34<13:53, 1.84it/s] 11%|█ | 182/1710 [01:34<13:02, 1.95it/s] 11%|█ | 183/1710 [01:34<12:03, 2.11it/s] 11%|█ | 184/1710 [01:35<11:05, 2.29it/s] 11%|█ | 185/1710 [01:35<11:05, 2.29it/s] 11%|█ | 186/1710 [01:36<10:52, 2.33it/s] 11%|█ | 187/1710 [01:36<10:16, 2.47it/s] 11%|█ | 188/1710 [01:37<11:20, 2.24it/s] 11%|█ | 189/1710 [01:37<10:06, 2.51it/s] 11%|█ | 190/1710 [01:37<10:00, 2.53it/s] 11%|█ | 191/1710 [01:38<10:40, 2.37it/s] 11%|█ | 192/1710 [01:38<13:43, 1.84it/s] 11%|█▏ | 193/1710 [01:39<13:01, 1.94it/s] 11%|█▏ | 194/1710 [01:40<14:45, 1.71it/s] 11%|█▏ | 195/1710 [01:40<13:18, 1.90it/s] 11%|█▏ | 196/1710 [01:41<12:48, 1.97it/s] 12%|█▏ | 197/1710 [01:41<11:50, 2.13it/s] 12%|█▏ | 198/1710 [01:41<12:19, 2.05it/s] 12%|█▏ | 199/1710 [01:42<11:26, 2.20it/s] 12%|█▏ | 200/1710 [01:42<11:07, 2.26it/s] 12%|█▏ | 201/1710 [01:43<11:23, 2.21it/s] 12%|█▏ | 202/1710 [01:43<11:44, 2.14it/s] 12%|█▏ | 203/1710 [01:44<11:12, 2.24it/s] 12%|█▏ | 204/1710 [01:44<11:04, 2.27it/s] 12%|█▏ | 205/1710 [01:44<10:26, 2.40it/s] 12%|█▏ | 206/1710 [01:45<10:31, 2.38it/s] 12%|█▏ | 207/1710 [01:45<10:37, 2.36it/s] 12%|█▏ | 208/1710 [01:46<10:40, 2.35it/s] 12%|█▏ | 209/1710 [01:46<10:26, 2.40it/s] 12%|█▏ | 210/1710 [01:47<10:21, 2.41it/s] 12%|█▏ | 211/1710 [01:47<13:31, 1.85it/s] 12%|█▏ | 212/1710 [01:48<12:25, 2.01it/s] 12%|█▏ | 213/1710 [01:48<11:29, 2.17it/s] 13%|█▎ | 214/1710 [01:48<10:48, 2.31it/s] 13%|█▎ | 215/1710 [01:49<11:08, 2.24it/s] 13%|█▎ | 216/1710 [01:49<11:34, 2.15it/s] 13%|█▎ | 217/1710 [01:50<10:57, 2.27it/s] 13%|█▎ | 218/1710 [01:50<11:25, 2.18it/s] 13%|█▎ | 219/1710 [01:51<10:37, 2.34it/s] 13%|█▎ | 220/1710 [01:51<10:59, 2.26it/s] 13%|█▎ | 221/1710 [01:52<11:41, 2.12it/s] 13%|█▎ | 222/1710 [01:52<11:35, 2.14it/s] 13%|█▎ | 223/1710 [01:53<10:35, 2.34it/s] 13%|█▎ | 224/1710 [01:53<10:22, 2.39it/s] 13%|█▎ | 225/1710 [01:53<11:22, 2.18it/s] 13%|█▎ | 226/1710 [01:54<10:48, 2.29it/s] 13%|█▎ | 227/1710 [01:55<15:06, 1.64it/s] 13%|█▎ | 228/1710 [01:55<15:03, 1.64it/s] 13%|█▎ | 229/1710 [01:56<13:49, 1.79it/s] 13%|█▎ | 230/1710 [01:56<13:40, 1.80it/s] 14%|█▎ | 231/1710 [01:57<12:47, 1.93it/s] 14%|█▎ | 232/1710 [01:57<11:18, 2.18it/s] 14%|█▎ | 233/1710 [01:58<11:45, 2.09it/s] 14%|█▎ | 234/1710 [01:58<11:04, 2.22it/s] 14%|█▎ | 235/1710 [01:58<10:23, 2.37it/s] 14%|█▍ | 236/1710 [01:59<10:08, 2.42it/s] 14%|█▍ | 237/1710 [01:59<11:05, 2.21it/s] 14%|█▍ | 238/1710 [02:00<13:19, 1.84it/s] 14%|█▍ | 239/1710 [02:01<12:42, 1.93it/s] 14%|█▍ | 240/1710 [02:01<11:38, 2.10it/s] 14%|█▍ | 241/1710 [02:01<10:37, 2.30it/s] 14%|█▍ | 242/1710 [02:02<10:17, 2.38it/s] 14%|█▍ | 243/1710 [02:02<10:50, 2.25it/s] 14%|█▍ | 244/1710 [02:03<10:29, 2.33it/s] 14%|█▍ | 245/1710 [02:03<10:30, 2.32it/s] 14%|█▍ | 246/1710 [02:04<11:29, 2.12it/s] 14%|█▍ | 247/1710 [02:04<11:58, 2.04it/s] 15%|█▍ | 248/1710 [02:05<11:34, 2.10it/s] 15%|█▍ | 249/1710 [02:05<10:23, 2.34it/s] 15%|█▍ | 250/1710 [02:05<10:26, 2.33it/s] 15%|█▍ | 251/1710 [02:06<10:35, 2.30it/s] 15%|█▍ | 252/1710 [02:06<10:23, 2.34it/s] 15%|█▍ | 253/1710 [02:07<10:17, 2.36it/s] 15%|█▍ | 254/1710 [02:07<12:00, 2.02it/s] 15%|█▍ | 255/1710 [02:08<11:09, 2.17it/s] 15%|█▍ | 256/1710 [02:08<11:16, 2.15it/s] 15%|█▌ | 257/1710 [02:09<11:21, 2.13it/s] 15%|█▌ | 258/1710 [02:09<10:36, 2.28it/s] 15%|█▌ | 259/1710 [02:09<10:12, 2.37it/s] 15%|█▌ | 260/1710 [02:10<10:50, 2.23it/s] 15%|█▌ | 261/1710 [02:10<11:02, 2.19it/s] 15%|█▌ | 262/1710 [02:11<11:02, 2.18it/s] 15%|█▌ | 263/1710 [02:11<10:14, 2.35it/s] 15%|█▌ | 264/1710 [02:12<11:19, 2.13it/s] 15%|█▌ | 265/1710 [02:12<13:03, 1.84it/s] 16%|█▌ | 266/1710 [02:13<11:58, 2.01it/s] 16%|█▌ | 267/1710 [02:13<11:15, 2.14it/s] 16%|█▌ | 268/1710 [02:14<11:35, 2.07it/s] 16%|█▌ | 269/1710 [02:14<11:31, 2.08it/s] 16%|█▌ | 270/1710 [02:15<11:24, 2.11it/s] 16%|█▌ | 271/1710 [02:15<11:16, 2.13it/s] 16%|█▌ | 272/1710 [02:16<11:15, 2.13it/s] 16%|█▌ | 273/1710 [02:16<11:04, 2.16it/s] 16%|█▌ | 274/1710 [02:17<12:48, 1.87it/s] 16%|█▌ | 275/1710 [02:17<11:30, 2.08it/s] 16%|█▌ | 276/1710 [02:17<10:30, 2.28it/s] 16%|█▌ | 277/1710 [02:18<10:22, 2.30it/s] 16%|█▋ | 278/1710 [02:18<10:22, 2.30it/s] 16%|█▋ | 279/1710 [02:19<10:49, 2.20it/s] 16%|█▋ | 280/1710 [02:20<12:41, 1.88it/s] 16%|█▋ | 281/1710 [02:20<12:01, 1.98it/s] 16%|█▋ | 282/1710 [02:21<12:14, 1.94it/s] 17%|█▋ | 283/1710 [02:21<10:55, 2.18it/s] 17%|█▋ | 284/1710 [02:21<10:41, 2.22it/s] 17%|█▋ | 285/1710 [02:22<10:13, 2.32it/s] 17%|█▋ | 286/1710 [02:22<10:22, 2.29it/s] 17%|█▋ | 287/1710 [02:23<10:45, 2.20it/s] 17%|█▋ | 288/1710 [02:23<10:03, 2.36it/s] 17%|█▋ | 289/1710 [02:23<09:55, 2.39it/s] 17%|█▋ | 290/1710 [02:24<10:40, 2.22it/s] 17%|█▋ | 291/1710 [02:24<10:06, 2.34it/s] 17%|█▋ | 292/1710 [02:25<09:28, 2.49it/s] 17%|█▋ | 293/1710 [02:25<12:32, 1.88it/s] 17%|█▋ | 294/1710 [02:26<12:01, 1.96it/s] 17%|█▋ | 295/1710 [02:26<11:05, 2.13it/s] 17%|█▋ | 296/1710 [02:27<11:38, 2.02it/s] 17%|█▋ | 297/1710 [02:27<10:40, 2.20it/s] 17%|█▋ | 298/1710 [02:28<10:08, 2.32it/s] 17%|█▋ | 299/1710 [02:28<10:36, 2.22it/s] 18%|█▊ | 300/1710 [02:29<10:54, 2.15it/s] 18%|█▊ | 301/1710 [02:29<10:41, 2.20it/s] 18%|█▊ | 302/1710 [02:29<10:11, 2.30it/s] 18%|█▊ | 303/1710 [02:30<10:28, 2.24it/s] 18%|█▊ | 304/1710 [02:30<10:20, 2.26it/s] 18%|█▊ | 305/1710 [02:31<10:27, 2.24it/s] 18%|█▊ | 306/1710 [02:31<10:34, 2.21it/s] 18%|█▊ | 307/1710 [02:32<11:00, 2.12it/s] 18%|█▊ | 308/1710 [02:32<11:50, 1.97it/s] 18%|█▊ | 309/1710 [02:33<10:55, 2.14it/s] 18%|█▊ | 310/1710 [02:33<12:16, 1.90it/s] 18%|█▊ | 311/1710 [02:34<11:21, 2.05it/s] 18%|█▊ | 312/1710 [02:34<12:12, 1.91it/s] 18%|█▊ | 313/1710 [02:35<12:28, 1.87it/s] 18%|█▊ | 314/1710 [02:35<12:34, 1.85it/s] 18%|█▊ | 315/1710 [02:36<11:26, 2.03it/s] 18%|█▊ | 316/1710 [02:36<10:34, 2.20it/s] 19%|█▊ | 317/1710 [02:37<12:28, 1.86it/s] 19%|█▊ | 318/1710 [02:38<14:03, 1.65it/s] 19%|█▊ | 319/1710 [02:38<13:08, 1.76it/s] 19%|█▊ | 320/1710 [02:39<12:58, 1.79it/s] 19%|█▉ | 321/1710 [02:39<11:26, 2.02it/s] 19%|█▉ | 322/1710 [02:40<12:01, 1.92it/s] 19%|█▉ | 323/1710 [02:40<12:13, 1.89it/s] 19%|█▉ | 324/1710 [02:41<11:53, 1.94it/s] 19%|█▉ | 325/1710 [02:41<11:28, 2.01it/s] 19%|█▉ | 326/1710 [02:42<10:41, 2.16it/s] 19%|█▉ | 327/1710 [02:42<10:45, 2.14it/s] 19%|█▉ | 328/1710 [02:42<10:48, 2.13it/s] 19%|█▉ | 329/1710 [02:43<09:59, 2.31it/s] 19%|█▉ | 330/1710 [02:43<10:30, 2.19it/s] 19%|█▉ | 331/1710 [02:44<10:30, 2.19it/s] 19%|█▉ | 332/1710 [02:44<10:29, 2.19it/s] 19%|█▉ | 333/1710 [02:45<09:55, 2.31it/s] 20%|█▉ | 334/1710 [02:45<09:40, 2.37it/s] 20%|█▉ | 335/1710 [02:45<09:28, 2.42it/s] 20%|█▉ | 336/1710 [02:46<09:32, 2.40it/s] 20%|█▉ | 337/1710 [02:46<09:06, 2.51it/s] 20%|█▉ | 338/1710 [02:47<09:31, 2.40it/s] 20%|█▉ | 339/1710 [02:47<09:23, 2.44it/s] 20%|█▉ | 340/1710 [02:48<10:43, 2.13it/s] 20%|█▉ | 341/1710 [02:48<12:19, 1.85it/s] 20%|██ | 342/1710 [02:49<11:08, 2.05it/s][INFO|trainer.py:811] 2024-09-09 12:17:44,889 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: ner_tags, id, tokens. If ner_tags, id, tokens are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. | |
| [INFO|trainer.py:3819] 2024-09-09 12:17:44,891 >> | |
| ***** Running Evaluation ***** | |
| [INFO|trainer.py:3821] 2024-09-09 12:17:44,891 >> Num examples = 2519 | |
| [INFO|trainer.py:3824] 2024-09-09 12:17:44,891 >> Batch size = 8 | |
| {'eval_loss': 0.15023551881313324, 'eval_precision': 0.5421052631578948, 'eval_recall': 0.6765188834154351, 'eval_f1': 0.6018991964937911, 'eval_accuracy': 0.9458275851005807, 'eval_runtime': 5.988, 'eval_samples_per_second': 420.673, 'eval_steps_per_second': 52.605, 'epoch': 1.0} | |
| 0%| | 0/315 [00:00<?, ?it/s][A | |
| 3%|▎ | 8/315 [00:00<00:03, 77.06it/s][A | |
| 5%|▌ | 16/315 [00:00<00:03, 75.05it/s][A | |
| 8%|▊ | 24/315 [00:00<00:03, 76.55it/s][A | |
| 10%|█ | 32/315 [00:00<00:03, 71.87it/s][A | |
| 13%|█▎ | 41/315 [00:00<00:03, 75.36it/s][A | |
| 16%|█▌ | 49/315 [00:00<00:03, 74.50it/s][A | |
| 18%|█▊ | 57/315 [00:00<00:03, 74.68it/s][A | |
| 21%|██ | 65/315 [00:00<00:03, 72.13it/s][A | |
| 23%|██▎ | 73/315 [00:00<00:03, 74.30it/s][A | |
| 26%|██▌ | 81/315 [00:01<00:03, 70.26it/s][A | |
| 28%|██▊ | 89/315 [00:01<00:03, 67.44it/s][A | |
| 31%|███ | 97/315 [00:01<00:03, 67.41it/s][A | |
| 33%|███▎ | 105/315 [00:01<00:03, 69.04it/s][A | |
| 36%|███▌ | 113/315 [00:01<00:02, 70.72it/s][A | |
| 38%|███▊ | 121/315 [00:01<00:02, 68.80it/s][A | |
| 41%|████ | 129/315 [00:01<00:02, 69.57it/s][A | |
| 43%|████▎ | 136/315 [00:01<00:02, 68.46it/s][A | |
| 45%|████▌ | 143/315 [00:02<00:02, 68.74it/s][A | |
| 48%|████▊ | 152/315 [00:02<00:02, 72.87it/s][A | |
| 51%|█████ | 160/315 [00:02<00:02, 72.87it/s][A | |
| 53%|█████▎ | 168/315 [00:02<00:02, 71.56it/s][A | |
| 56%|█████▌ | 176/315 [00:02<00:01, 70.53it/s][A | |
| 58%|█████▊ | 184/315 [00:02<00:01, 68.57it/s][A | |
| 61%|██████ | 192/315 [00:02<00:01, 68.80it/s][A | |
| 63%|██████▎ | 199/315 [00:02<00:01, 65.97it/s][A | |
| 65%|██████▌ | 206/315 [00:02<00:01, 64.38it/s][A | |
| 68%|██████▊ | 214/315 [00:03<00:01, 67.85it/s][A | |
| 70%|███████ | 222/315 [00:03<00:01, 69.75it/s][A | |
| 73%|███████▎ | 231/315 [00:03<00:01, 73.13it/s][A | |
| 76%|███████▌ | 239/315 [00:03<00:01, 74.53it/s][A | |
| 78%|███████▊ | 247/315 [00:03<00:00, 70.64it/s][A | |
| 81%|████████ | 255/315 [00:03<00:00, 69.22it/s][A | |
| 83%|████████▎ | 263/315 [00:03<00:00, 70.34it/s][A | |
| 86%|████████▌ | 271/315 [00:03<00:00, 72.74it/s][A | |
| 89%|████████▉ | 280/315 [00:03<00:00, 75.27it/s][A | |
| 91%|█████████▏| 288/315 [00:04<00:00, 72.01it/s][A | |
| 94%|█████████▍| 296/315 [00:04<00:00, 70.20it/s][A | |
| 97%|█████████▋| 304/315 [00:04<00:00, 71.71it/s][A | |
| 99%|█████████▉| 312/315 [00:04<00:00, 72.20it/s][A | |
| [A 20%|██ | 342/1710 [02:55<11:08, 2.05it/s] | |
| 100%|██████████| 315/315 [00:05<00:00, 72.20it/s][A | |
| [A[INFO|trainer.py:3503] 2024-09-09 12:17:50,795 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-342 | |
| [INFO|configuration_utils.py:472] 2024-09-09 12:17:50,796 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-342/config.json | |
| [INFO|modeling_utils.py:2799] 2024-09-09 12:17:51,803 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-342/model.safetensors | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:17:51,804 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-342/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:17:51,804 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-342/special_tokens_map.json | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:17:54,812 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:17:54,812 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json | |
| 20%|██ | 343/1710 [02:59<1:18:27, 3.44s/it] 20%|██ | 344/1710 [02:59<57:22, 2.52s/it] 20%|██ | 345/1710 [03:00<43:17, 1.90s/it] 20%|██ | 346/1710 [03:00<33:11, 1.46s/it] 20%|██ | 347/1710 [03:01<27:33, 1.21s/it] 20%|██ | 348/1710 [03:01<21:44, 1.04it/s] 20%|██ | 349/1710 [03:02<20:28, 1.11it/s] 20%|██ | 350/1710 [03:03<18:14, 1.24it/s] 21%|██ | 351/1710 [03:03<15:22, 1.47it/s] 21%|██ | 352/1710 [03:04<13:56, 1.62it/s] 21%|██ | 353/1710 [03:04<14:17, 1.58it/s] 21%|██ | 354/1710 [03:05<13:53, 1.63it/s] 21%|██ | 355/1710 [03:05<13:50, 1.63it/s] 21%|██ | 356/1710 [03:06<12:28, 1.81it/s] 21%|██ | 357/1710 [03:06<11:08, 2.02it/s] 21%|██ | 358/1710 [03:07<10:43, 2.10it/s] 21%|██ | 359/1710 [03:07<09:37, 2.34it/s] 21%|██ | 360/1710 [03:07<09:03, 2.48it/s] 21%|██ | 361/1710 [03:08<08:53, 2.53it/s] 21%|██ | 362/1710 [03:08<09:32, 2.35it/s] 21%|██ | 363/1710 [03:09<09:32, 2.35it/s] 21%|██▏ | 364/1710 [03:09<08:49, 2.54it/s] 21%|██▏ | 365/1710 [03:09<08:53, 2.52it/s] 21%|██▏ | 366/1710 [03:10<09:56, 2.25it/s] 21%|██▏ | 367/1710 [03:10<09:35, 2.34it/s] 22%|██▏ | 368/1710 [03:11<09:12, 2.43it/s] 22%|██▏ | 369/1710 [03:11<10:02, 2.23it/s] 22%|██▏ | 370/1710 [03:11<09:25, 2.37it/s] 22%|██▏ | 371/1710 [03:12<09:41, 2.30it/s] 22%|██▏ | 372/1710 [03:12<09:22, 2.38it/s] 22%|██▏ | 373/1710 [03:13<09:03, 2.46it/s] 22%|██▏ | 374/1710 [03:13<09:10, 2.43it/s] 22%|██▏ | 375/1710 [03:14<08:54, 2.50it/s] 22%|██▏ | 376/1710 [03:14<09:08, 2.43it/s] 22%|██▏ | 377/1710 [03:14<09:14, 2.40it/s] 22%|██▏ | 378/1710 [03:15<09:53, 2.25it/s] 22%|██▏ | 379/1710 [03:15<10:21, 2.14it/s] 22%|██▏ | 380/1710 [03:16<09:55, 2.23it/s] 22%|██▏ | 381/1710 [03:16<09:40, 2.29it/s] 22%|██▏ | 382/1710 [03:17<09:37, 2.30it/s] 22%|██▏ | 383/1710 [03:17<09:35, 2.31it/s] 22%|██▏ | 384/1710 [03:18<09:47, 2.26it/s] 23%|██▎ | 385/1710 [03:18<09:08, 2.41it/s] 23%|██▎ | 386/1710 [03:19<10:26, 2.11it/s] 23%|██▎ | 387/1710 [03:19<12:56, 1.70it/s] 23%|██▎ | 388/1710 [03:20<12:02, 1.83it/s] 23%|██▎ | 389/1710 [03:20<11:52, 1.86it/s] 23%|██▎ | 390/1710 [03:21<11:20, 1.94it/s] 23%|██▎ | 391/1710 [03:21<10:06, 2.17it/s] 23%|██▎ | 392/1710 [03:22<09:45, 2.25it/s] 23%|██▎ | 393/1710 [03:22<10:25, 2.10it/s] 23%|██▎ | 394/1710 [03:23<10:28, 2.09it/s] 23%|██▎ | 395/1710 [03:23<09:55, 2.21it/s] 23%|██▎ | 396/1710 [03:23<09:36, 2.28it/s] 23%|██▎ | 397/1710 [03:24<10:58, 1.99it/s] 23%|██▎ | 398/1710 [03:25<12:44, 1.72it/s] 23%|██▎ | 399/1710 [03:25<12:00, 1.82it/s] 23%|██▎ | 400/1710 [03:26<11:14, 1.94it/s] 23%|██▎ | 401/1710 [03:26<10:06, 2.16it/s] 24%|██▎ | 402/1710 [03:26<09:23, 2.32it/s] 24%|██▎ | 403/1710 [03:27<10:36, 2.05it/s] 24%|██▎ | 404/1710 [03:27<10:22, 2.10it/s] 24%|██▎ | 405/1710 [03:28<10:20, 2.10it/s] 24%|██▎ | 406/1710 [03:28<09:44, 2.23it/s] 24%|██▍ | 407/1710 [03:29<10:05, 2.15it/s] 24%|██▍ | 408/1710 [03:29<09:21, 2.32it/s] 24%|██▍ | 409/1710 [03:30<09:36, 2.26it/s] 24%|██▍ | 410/1710 [03:30<09:31, 2.28it/s] 24%|██▍ | 411/1710 [03:31<09:52, 2.19it/s] 24%|██▍ | 412/1710 [03:31<09:28, 2.28it/s] 24%|██▍ | 413/1710 [03:31<09:34, 2.26it/s] 24%|██▍ | 414/1710 [03:32<09:32, 2.26it/s] 24%|██▍ | 415/1710 [03:32<09:12, 2.35it/s] 24%|██▍ | 416/1710 [03:33<09:45, 2.21it/s] 24%|██▍ | 417/1710 [03:33<09:32, 2.26it/s] 24%|██▍ | 418/1710 [03:34<09:52, 2.18it/s] 25%|██▍ | 419/1710 [03:34<09:45, 2.21it/s] 25%|██▍ | 420/1710 [03:35<10:07, 2.13it/s] 25%|██▍ | 421/1710 [03:35<09:30, 2.26it/s] 25%|██▍ | 422/1710 [03:35<09:06, 2.36it/s] 25%|██▍ | 423/1710 [03:36<09:18, 2.30it/s] 25%|██▍ | 424/1710 [03:36<09:45, 2.20it/s] 25%|██▍ | 425/1710 [03:37<10:29, 2.04it/s] 25%|██▍ | 426/1710 [03:37<10:44, 1.99it/s] 25%|██▍ | 427/1710 [03:38<10:06, 2.12it/s] 25%|██▌ | 428/1710 [03:39<12:25, 1.72it/s] 25%|██▌ | 429/1710 [03:39<13:00, 1.64it/s] 25%|██▌ | 430/1710 [03:40<11:30, 1.85it/s] 25%|██▌ | 431/1710 [03:40<10:32, 2.02it/s] 25%|██▌ | 432/1710 [03:41<10:52, 1.96it/s] 25%|██▌ | 433/1710 [03:41<10:17, 2.07it/s] 25%|██▌ | 434/1710 [03:42<09:53, 2.15it/s] 25%|██▌ | 435/1710 [03:42<10:07, 2.10it/s] 25%|██▌ | 436/1710 [03:42<10:04, 2.11it/s] 26%|██▌ | 437/1710 [03:43<09:54, 2.14it/s] 26%|██▌ | 438/1710 [03:44<12:59, 1.63it/s] 26%|██▌ | 439/1710 [03:44<11:59, 1.77it/s] 26%|██▌ | 440/1710 [03:45<11:09, 1.90it/s] 26%|██▌ | 441/1710 [03:45<10:51, 1.95it/s] 26%|██▌ | 442/1710 [03:46<10:00, 2.11it/s] 26%|██▌ | 443/1710 [03:46<09:52, 2.14it/s] 26%|██▌ | 444/1710 [03:47<09:27, 2.23it/s] 26%|██▌ | 445/1710 [03:47<09:21, 2.25it/s] 26%|██▌ | 446/1710 [03:47<09:20, 2.26it/s] 26%|██▌ | 447/1710 [03:48<10:06, 2.08it/s] 26%|██▌ | 448/1710 [03:48<10:16, 2.05it/s] 26%|██▋ | 449/1710 [03:49<09:41, 2.17it/s] 26%|██▋ | 450/1710 [03:49<08:58, 2.34it/s] 26%|██▋ | 451/1710 [03:50<08:40, 2.42it/s] 26%|██▋ | 452/1710 [03:50<09:03, 2.32it/s] 26%|██▋ | 453/1710 [03:51<11:05, 1.89it/s] 27%|██▋ | 454/1710 [03:51<10:11, 2.05it/s] 27%|██▋ | 455/1710 [03:52<09:53, 2.11it/s] 27%|██▋ | 456/1710 [03:52<09:22, 2.23it/s] 27%|██▋ | 457/1710 [03:52<08:39, 2.41it/s] 27%|██▋ | 458/1710 [03:53<08:28, 2.46it/s] 27%|██▋ | 459/1710 [03:53<08:43, 2.39it/s] 27%|██▋ | 460/1710 [03:54<08:49, 2.36it/s] 27%|██▋ | 461/1710 [03:54<08:40, 2.40it/s] 27%|██▋ | 462/1710 [03:54<08:55, 2.33it/s] 27%|██▋ | 463/1710 [03:55<09:28, 2.20it/s] 27%|██▋ | 464/1710 [03:56<10:01, 2.07it/s] 27%|██▋ | 465/1710 [03:56<09:38, 2.15it/s] 27%|██▋ | 466/1710 [03:56<08:45, 2.37it/s] 27%|██▋ | 467/1710 [03:57<07:57, 2.60it/s] 27%|██▋ | 468/1710 [03:57<08:14, 2.51it/s] 27%|██▋ | 469/1710 [03:57<08:32, 2.42it/s] 27%|██▋ | 470/1710 [03:58<08:52, 2.33it/s] 28%|██▊ | 471/1710 [03:58<08:19, 2.48it/s] 28%|██▊ | 472/1710 [03:59<08:10, 2.52it/s] 28%|██▊ | 473/1710 [03:59<08:03, 2.56it/s] 28%|██▊ | 474/1710 [03:59<07:52, 2.61it/s] 28%|██▊ | 475/1710 [04:00<08:20, 2.47it/s] 28%|██▊ | 476/1710 [04:00<08:21, 2.46it/s] 28%|██▊ | 477/1710 [04:01<08:47, 2.34it/s] 28%|██▊ | 478/1710 [04:01<09:46, 2.10it/s] 28%|██▊ | 479/1710 [04:02<09:09, 2.24it/s] 28%|██▊ | 480/1710 [04:02<09:29, 2.16it/s] 28%|██▊ | 481/1710 [04:03<09:35, 2.13it/s] 28%|██▊ | 482/1710 [04:03<10:04, 2.03it/s] 28%|██▊ | 483/1710 [04:04<10:04, 2.03it/s] 28%|██▊ | 484/1710 [04:04<09:31, 2.14it/s] 28%|██▊ | 485/1710 [04:05<09:25, 2.16it/s] 28%|██▊ | 486/1710 [04:05<08:45, 2.33it/s] 28%|██▊ | 487/1710 [04:05<09:08, 2.23it/s] 29%|██▊ | 488/1710 [04:06<08:39, 2.35it/s] 29%|██▊ | 489/1710 [04:06<08:23, 2.42it/s] 29%|██▊ | 490/1710 [04:07<08:55, 2.28it/s] 29%|██▊ | 491/1710 [04:07<09:03, 2.24it/s] 29%|██▉ | 492/1710 [04:08<08:39, 2.34it/s] 29%|██▉ | 493/1710 [04:08<09:30, 2.13it/s] 29%|██▉ | 494/1710 [04:09<09:31, 2.13it/s] 29%|██▉ | 495/1710 [04:09<09:39, 2.09it/s] 29%|██▉ | 496/1710 [04:09<08:56, 2.26it/s] 29%|██▉ | 497/1710 [04:10<08:47, 2.30it/s] 29%|██▉ | 498/1710 [04:10<08:51, 2.28it/s] 29%|██▉ | 499/1710 [04:11<08:24, 2.40it/s] 29%|██▉ | 500/1710 [04:11<08:24, 2.40it/s] 29%|██▉ | 500/1710 [04:11<08:24, 2.40it/s] 29%|██▉ | 501/1710 [04:12<08:21, 2.41it/s] 29%|██▉ | 502/1710 [04:12<08:26, 2.39it/s] 29%|██▉ | 503/1710 [04:12<08:06, 2.48it/s] 29%|██▉ | 504/1710 [04:13<08:47, 2.29it/s] 30%|██▉ | 505/1710 [04:13<08:40, 2.32it/s] 30%|██▉ | 506/1710 [04:14<10:01, 2.00it/s] 30%|██▉ | 507/1710 [04:14<09:17, 2.16it/s] 30%|██▉ | 508/1710 [04:15<09:16, 2.16it/s] 30%|██▉ | 509/1710 [04:16<11:07, 1.80it/s] 30%|██▉ | 510/1710 [04:16<11:36, 1.72it/s] 30%|██▉ | 511/1710 [04:17<10:33, 1.89it/s] 30%|██▉ | 512/1710 [04:17<10:06, 1.98it/s] 30%|███ | 513/1710 [04:18<11:39, 1.71it/s][INFO|trainer.py:811] 2024-09-09 12:19:13,918 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: ner_tags, id, tokens. If ner_tags, id, tokens are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. | |
| [INFO|trainer.py:3819] 2024-09-09 12:19:13,920 >> | |
| ***** Running Evaluation ***** | |
| [INFO|trainer.py:3821] 2024-09-09 12:19:13,920 >> Num examples = 2519 | |
| [INFO|trainer.py:3824] 2024-09-09 12:19:13,920 >> Batch size = 8 | |
| {'eval_loss': 0.15393643081188202, 'eval_precision': 0.5957753240518483, 'eval_recall': 0.6792556102900931, 'eval_f1': 0.6347826086956522, 'eval_accuracy': 0.9468221630466168, 'eval_runtime': 5.9023, 'eval_samples_per_second': 426.784, 'eval_steps_per_second': 53.369, 'epoch': 2.0} | |
| {'loss': 0.1273, 'grad_norm': 1.020290732383728, 'learning_rate': 3.538011695906433e-05, 'epoch': 2.92} | |
| 0%| | 0/315 [00:00<?, ?it/s][A | |
| 3%|▎ | 8/315 [00:00<00:04, 76.55it/s][A | |
| 5%|▌ | 16/315 [00:00<00:03, 74.76it/s][A | |
| 8%|▊ | 24/315 [00:00<00:03, 76.64it/s][A | |
| 10%|█ | 32/315 [00:00<00:03, 72.00it/s][A | |
| 13%|█▎ | 41/315 [00:00<00:03, 75.14it/s][A | |
| 16%|█▌ | 49/315 [00:00<00:03, 74.50it/s][A | |
| 18%|█▊ | 57/315 [00:00<00:03, 74.55it/s][A | |
| 21%|██ | 65/315 [00:00<00:03, 71.94it/s][A | |
| 23%|██▎ | 74/315 [00:00<00:03, 74.58it/s][A | |
| 26%|██▌ | 82/315 [00:01<00:03, 70.19it/s][A | |
| 29%|██▊ | 90/315 [00:01<00:03, 67.73it/s][A | |
| 31%|███ | 97/315 [00:01<00:03, 67.21it/s][A | |
| 33%|███▎ | 105/315 [00:01<00:03, 69.02it/s][A | |
| 36%|███▌ | 113/315 [00:01<00:02, 70.49it/s][A | |
| 38%|███▊ | 121/315 [00:01<00:02, 68.91it/s][A | |
| 41%|████ | 129/315 [00:01<00:02, 69.60it/s][A | |
| 43%|████▎ | 136/315 [00:01<00:02, 68.75it/s][A | |
| 45%|████▌ | 143/315 [00:02<00:02, 68.85it/s][A | |
| 48%|████▊ | 152/315 [00:02<00:02, 72.96it/s][A | |
| 51%|█████ | 160/315 [00:02<00:02, 72.98it/s][A | |
| 53%|█████▎ | 168/315 [00:02<00:02, 71.30it/s][A | |
| 56%|█████▌ | 176/315 [00:02<00:01, 70.27it/s][A | |
| 58%|█████▊ | 184/315 [00:02<00:01, 68.32it/s][A | |
| 61%|██████ | 192/315 [00:02<00:01, 68.37it/s][A | |
| 63%|██████▎ | 199/315 [00:02<00:01, 65.58it/s][A | |
| 65%|██████▌ | 206/315 [00:02<00:01, 64.03it/s][A | |
| 68%|██████▊ | 214/315 [00:03<00:01, 67.33it/s][A | |
| 70%|███████ | 222/315 [00:03<00:01, 69.48it/s][A | |
| 73%|███████▎ | 231/315 [00:03<00:01, 72.82it/s][A | |
| 76%|███████▌ | 239/315 [00:03<00:01, 74.16it/s][A | |
| 78%|███████▊ | 247/315 [00:03<00:00, 69.80it/s][A | |
| 81%|████████ | 255/315 [00:03<00:00, 68.36it/s][A | |
| 83%|████████▎ | 263/315 [00:03<00:00, 70.27it/s][A | |
| 86%|████████▌ | 271/315 [00:03<00:00, 72.23it/s][A | |
| 89%|████████▉ | 280/315 [00:03<00:00, 75.28it/s][A | |
| 91%|█████████▏| 288/315 [00:04<00:00, 72.26it/s][A | |
| 94%|█████████▍| 296/315 [00:04<00:00, 70.88it/s][A | |
| 97%|█████████▋| 304/315 [00:04<00:00, 71.92it/s][A | |
| 99%|█████████▉| 312/315 [00:04<00:00, 72.12it/s][A | |
| [A 30%|███ | 513/1710 [04:24<11:39, 1.71it/s] | |
| 100%|██████████| 315/315 [00:05<00:00, 72.12it/s][A | |
| [A[INFO|trainer.py:3503] 2024-09-09 12:19:19,842 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-513 | |
| [INFO|configuration_utils.py:472] 2024-09-09 12:19:19,843 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-513/config.json | |
| [INFO|modeling_utils.py:2799] 2024-09-09 12:19:20,869 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-513/model.safetensors | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:19:20,870 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-513/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:19:20,871 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-513/special_tokens_map.json | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:19:25,899 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:19:25,900 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json | |
| 30%|███ | 514/1710 [04:30<1:23:28, 4.19s/it] 30%|███ | 515/1710 [04:31<1:00:28, 3.04s/it] 30%|███ | 516/1710 [04:31<45:06, 2.27s/it] 30%|███ | 517/1710 [04:32<33:52, 1.70s/it] 30%|███ | 518/1710 [04:32<27:22, 1.38s/it] 30%|███ | 519/1710 [04:33<21:46, 1.10s/it] 30%|███ | 520/1710 [04:33<17:41, 1.12it/s] 30%|███ | 521/1710 [04:33<14:43, 1.35it/s] 31%|███ | 522/1710 [04:34<13:50, 1.43it/s] 31%|███ | 523/1710 [04:34<11:43, 1.69it/s] 31%|███ | 524/1710 [04:35<10:45, 1.84it/s] 31%|███ | 525/1710 [04:35<11:02, 1.79it/s] 31%|███ | 526/1710 [04:36<10:05, 1.96it/s] 31%|███ | 527/1710 [04:36<09:35, 2.05it/s] 31%|███ | 528/1710 [04:37<09:11, 2.14it/s] 31%|███ | 529/1710 [04:37<08:25, 2.34it/s] 31%|███ | 530/1710 [04:38<10:47, 1.82it/s] 31%|███ | 531/1710 [04:38<11:03, 1.78it/s] 31%|███ | 532/1710 [04:39<09:37, 2.04it/s] 31%|███ | 533/1710 [04:39<09:15, 2.12it/s] 31%|███ | 534/1710 [04:40<08:39, 2.26it/s] 31%|███▏ | 535/1710 [04:40<08:24, 2.33it/s] 31%|███▏ | 536/1710 [04:40<08:06, 2.41it/s] 31%|███▏ | 537/1710 [04:41<08:55, 2.19it/s] 31%|███▏ | 538/1710 [04:41<08:33, 2.28it/s] 32%|███▏ | 539/1710 [04:42<08:07, 2.40it/s] 32%|███▏ | 540/1710 [04:42<07:53, 2.47it/s] 32%|███▏ | 541/1710 [04:43<08:37, 2.26it/s] 32%|███▏ | 542/1710 [04:43<07:57, 2.44it/s] 32%|███▏ | 543/1710 [04:43<07:36, 2.56it/s] 32%|███▏ | 544/1710 [04:44<08:21, 2.32it/s] 32%|███▏ | 545/1710 [04:44<09:47, 1.98it/s] 32%|███▏ | 546/1710 [04:45<09:45, 1.99it/s] 32%|███▏ | 547/1710 [04:45<09:04, 2.14it/s] 32%|███▏ | 548/1710 [04:46<09:04, 2.13it/s] 32%|███▏ | 549/1710 [04:46<08:47, 2.20it/s] 32%|███▏ | 550/1710 [04:47<08:38, 2.24it/s] 32%|███▏ | 551/1710 [04:47<08:41, 2.22it/s] 32%|███▏ | 552/1710 [04:47<08:17, 2.33it/s] 32%|███▏ | 553/1710 [04:48<08:07, 2.37it/s] 32%|███▏ | 554/1710 [04:48<07:55, 2.43it/s] 32%|███▏ | 555/1710 [04:49<08:24, 2.29it/s] 33%|███▎ | 556/1710 [04:49<08:19, 2.31it/s] 33%|███▎ | 557/1710 [04:50<08:32, 2.25it/s] 33%|███▎ | 558/1710 [04:50<08:12, 2.34it/s] 33%|███▎ | 559/1710 [04:51<10:56, 1.75it/s] 33%|███▎ | 560/1710 [04:51<10:36, 1.81it/s] 33%|███▎ | 561/1710 [04:52<09:52, 1.94it/s] 33%|███▎ | 562/1710 [04:52<08:49, 2.17it/s] 33%|███▎ | 563/1710 [04:53<08:50, 2.16it/s] 33%|███▎ | 564/1710 [04:53<08:12, 2.33it/s] 33%|███▎ | 565/1710 [04:53<07:39, 2.49it/s] 33%|███▎ | 566/1710 [04:54<07:30, 2.54it/s] 33%|███▎ | 567/1710 [04:54<07:23, 2.58it/s] 33%|███▎ | 568/1710 [04:55<07:50, 2.43it/s] 33%|███▎ | 569/1710 [04:55<07:31, 2.53it/s] 33%|███▎ | 570/1710 [04:56<09:51, 1.93it/s] 33%|███▎ | 571/1710 [04:56<09:39, 1.96it/s] 33%|███▎ | 572/1710 [04:57<09:24, 2.02it/s] 34%|███▎ | 573/1710 [04:57<09:13, 2.05it/s] 34%|███▎ | 574/1710 [04:58<09:36, 1.97it/s] 34%|███▎ | 575/1710 [04:58<09:05, 2.08it/s] 34%|███▎ | 576/1710 [04:59<08:39, 2.18it/s] 34%|███▎ | 577/1710 [04:59<08:34, 2.20it/s] 34%|███▍ | 578/1710 [05:00<08:50, 2.13it/s] 34%|███▍ | 579/1710 [05:00<08:32, 2.21it/s] 34%|███▍ | 580/1710 [05:00<08:06, 2.32it/s] 34%|███▍ | 581/1710 [05:01<08:09, 2.31it/s] 34%|███▍ | 582/1710 [05:01<07:38, 2.46it/s] 34%|███▍ | 583/1710 [05:01<07:14, 2.60it/s] 34%|███▍ | 584/1710 [05:02<07:44, 2.42it/s] 34%|███▍ | 585/1710 [05:02<07:44, 2.42it/s] 34%|███▍ | 586/1710 [05:03<07:47, 2.41it/s] 34%|███▍ | 587/1710 [05:03<09:00, 2.08it/s] 34%|███▍ | 588/1710 [05:04<08:40, 2.16it/s] 34%|███▍ | 589/1710 [05:04<08:32, 2.19it/s] 35%|███▍ | 590/1710 [05:05<08:24, 2.22it/s] 35%|███▍ | 591/1710 [05:05<08:05, 2.30it/s] 35%|███▍ | 592/1710 [05:06<09:13, 2.02it/s] 35%|███▍ | 593/1710 [05:06<09:40, 1.92it/s] 35%|███▍ | 594/1710 [05:07<09:06, 2.04it/s] 35%|███▍ | 595/1710 [05:07<08:42, 2.14it/s] 35%|███▍ | 596/1710 [05:08<08:30, 2.18it/s] 35%|███▍ | 597/1710 [05:08<10:24, 1.78it/s] 35%|███▍ | 598/1710 [05:09<09:48, 1.89it/s] 35%|███▌ | 599/1710 [05:09<08:59, 2.06it/s] 35%|███▌ | 600/1710 [05:10<08:30, 2.17it/s] 35%|███▌ | 601/1710 [05:10<08:19, 2.22it/s] 35%|███▌ | 602/1710 [05:10<08:21, 2.21it/s] 35%|███▌ | 603/1710 [05:11<07:58, 2.31it/s] 35%|███▌ | 604/1710 [05:12<10:18, 1.79it/s] 35%|███▌ | 605/1710 [05:12<09:31, 1.94it/s] 35%|███▌ | 606/1710 [05:13<08:47, 2.09it/s] 35%|███▌ | 607/1710 [05:13<08:18, 2.21it/s] 36%|███▌ | 608/1710 [05:13<08:43, 2.11it/s] 36%|███▌ | 609/1710 [05:14<09:12, 1.99it/s] 36%|███▌ | 610/1710 [05:14<08:54, 2.06it/s] 36%|███▌ | 611/1710 [05:15<08:57, 2.04it/s] 36%|███▌ | 612/1710 [05:15<07:56, 2.30it/s] 36%|███▌ | 613/1710 [05:16<08:03, 2.27it/s] 36%|███▌ | 614/1710 [05:16<08:36, 2.12it/s] 36%|███▌ | 615/1710 [05:17<08:04, 2.26it/s] 36%|███▌ | 616/1710 [05:17<07:38, 2.39it/s] 36%|███▌ | 617/1710 [05:18<08:36, 2.12it/s] 36%|███▌ | 618/1710 [05:18<08:20, 2.18it/s] 36%|███▌ | 619/1710 [05:18<08:13, 2.21it/s] 36%|███▋ | 620/1710 [05:19<08:16, 2.19it/s] 36%|███▋ | 621/1710 [05:19<08:33, 2.12it/s] 36%|███▋ | 622/1710 [05:20<08:24, 2.16it/s] 36%|███▋ | 623/1710 [05:20<08:22, 2.17it/s] 36%|███▋ | 624/1710 [05:21<07:48, 2.32it/s] 37%|███▋ | 625/1710 [05:21<07:59, 2.26it/s] 37%|███▋ | 626/1710 [05:22<07:37, 2.37it/s] 37%|███▋ | 627/1710 [05:22<07:36, 2.37it/s] 37%|███▋ | 628/1710 [05:22<08:07, 2.22it/s] 37%|███▋ | 629/1710 [05:23<07:33, 2.38it/s] 37%|███▋ | 630/1710 [05:23<08:02, 2.24it/s] 37%|███▋ | 631/1710 [05:24<08:40, 2.07it/s] 37%|███▋ | 632/1710 [05:24<08:11, 2.19it/s] 37%|███▋ | 633/1710 [05:25<07:37, 2.35it/s] 37%|███▋ | 634/1710 [05:25<07:31, 2.38it/s] 37%|███▋ | 635/1710 [05:26<08:41, 2.06it/s] 37%|███▋ | 636/1710 [05:26<08:05, 2.21it/s] 37%|███▋ | 637/1710 [05:27<08:06, 2.20it/s] 37%|███▋ | 638/1710 [05:27<07:46, 2.30it/s] 37%|███▋ | 639/1710 [05:27<08:09, 2.19it/s] 37%|███▋ | 640/1710 [05:28<08:13, 2.17it/s] 37%|███▋ | 641/1710 [05:28<08:43, 2.04it/s] 38%|███▊ | 642/1710 [05:29<08:12, 2.17it/s] 38%|███▊ | 643/1710 [05:29<07:43, 2.30it/s] 38%|███▊ | 644/1710 [05:30<08:09, 2.18it/s] 38%|███▊ | 645/1710 [05:30<07:59, 2.22it/s] 38%|███▊ | 646/1710 [05:31<08:13, 2.15it/s] 38%|███▊ | 647/1710 [05:31<08:10, 2.17it/s] 38%|███▊ | 648/1710 [05:31<07:40, 2.31it/s] 38%|███▊ | 649/1710 [05:32<08:02, 2.20it/s] 38%|███▊ | 650/1710 [05:32<07:46, 2.27it/s] 38%|███▊ | 651/1710 [05:33<07:36, 2.32it/s] 38%|███▊ | 652/1710 [05:33<07:36, 2.32it/s] 38%|███▊ | 653/1710 [05:34<08:27, 2.08it/s] 38%|███▊ | 654/1710 [05:34<08:15, 2.13it/s] 38%|███▊ | 655/1710 [05:35<07:37, 2.31it/s] 38%|███▊ | 656/1710 [05:35<07:20, 2.39it/s] 38%|███▊ | 657/1710 [05:35<07:07, 2.46it/s] 38%|███▊ | 658/1710 [05:36<07:23, 2.37it/s] 39%|███▊ | 659/1710 [05:36<07:54, 2.21it/s] 39%|███▊ | 660/1710 [05:37<08:19, 2.10it/s] 39%|███▊ | 661/1710 [05:37<07:50, 2.23it/s] 39%|███▊ | 662/1710 [05:38<07:44, 2.26it/s] 39%|███▉ | 663/1710 [05:38<07:43, 2.26it/s] 39%|███▉ | 664/1710 [05:38<07:08, 2.44it/s] 39%|███▉ | 665/1710 [05:39<06:53, 2.53it/s] 39%|███▉ | 666/1710 [05:39<07:16, 2.39it/s] 39%|███▉ | 667/1710 [05:40<07:20, 2.37it/s] 39%|███▉ | 668/1710 [05:40<07:04, 2.45it/s] 39%|███▉ | 669/1710 [05:41<10:09, 1.71it/s] 39%|███▉ | 670/1710 [05:42<09:09, 1.89it/s] 39%|███▉ | 671/1710 [05:42<08:57, 1.93it/s] 39%|███▉ | 672/1710 [05:43<09:56, 1.74it/s] 39%|███▉ | 673/1710 [05:43<08:53, 1.94it/s] 39%|███▉ | 674/1710 [05:44<08:35, 2.01it/s] 39%|███▉ | 675/1710 [05:44<08:25, 2.05it/s] 40%|███▉ | 676/1710 [05:45<08:25, 2.04it/s] 40%|███▉ | 677/1710 [05:45<08:01, 2.14it/s] 40%|███▉ | 678/1710 [05:45<07:40, 2.24it/s] 40%|███▉ | 679/1710 [05:46<10:30, 1.64it/s] 40%|███▉ | 680/1710 [05:47<09:10, 1.87it/s] 40%|███▉ | 681/1710 [05:47<09:52, 1.74it/s] 40%|███▉ | 682/1710 [05:48<09:09, 1.87it/s] 40%|███▉ | 683/1710 [05:48<08:13, 2.08it/s] 40%|████ | 684/1710 [05:48<07:29, 2.28it/s][INFO|trainer.py:811] 2024-09-09 12:20:44,622 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: ner_tags, id, tokens. If ner_tags, id, tokens are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. | |
| [INFO|trainer.py:3819] 2024-09-09 12:20:44,625 >> | |
| ***** Running Evaluation ***** | |
| [INFO|trainer.py:3821] 2024-09-09 12:20:44,625 >> Num examples = 2519 | |
| [INFO|trainer.py:3824] 2024-09-09 12:20:44,625 >> Batch size = 8 | |
| {'eval_loss': 0.1837530881166458, 'eval_precision': 0.6325831702544031, 'eval_recall': 0.7077175697865353, 'eval_f1': 0.6680444329630587, 'eval_accuracy': 0.9468382046263916, 'eval_runtime': 5.9204, 'eval_samples_per_second': 425.477, 'eval_steps_per_second': 53.206, 'epoch': 3.0} | |
| 0%| | 0/315 [00:00<?, ?it/s][A | |
| 3%|▎ | 8/315 [00:00<00:03, 77.82it/s][A | |
| 5%|▌ | 16/315 [00:00<00:04, 73.85it/s][A | |
| 8%|▊ | 24/315 [00:00<00:03, 75.96it/s][A | |
| 10%|█ | 32/315 [00:00<00:03, 71.57it/s][A | |
| 13%|█▎ | 41/315 [00:00<00:03, 75.27it/s][A | |
| 16%|█▌ | 49/315 [00:00<00:03, 74.26it/s][A | |
| 18%|█▊ | 57/315 [00:00<00:03, 74.33it/s][A | |
| 21%|██ | 65/315 [00:00<00:03, 71.75it/s][A | |
| 23%|██▎ | 73/315 [00:00<00:03, 73.81it/s][A | |
| 26%|██▌ | 81/315 [00:01<00:03, 70.09it/s][A | |
| 28%|██▊ | 89/315 [00:01<00:03, 67.14it/s][A | |
| 31%|███ | 97/315 [00:01<00:03, 67.19it/s][A | |
| 33%|███▎ | 105/315 [00:01<00:03, 68.76it/s][A | |
| 36%|███▌ | 113/315 [00:01<00:02, 70.14it/s][A | |
| 38%|███▊ | 121/315 [00:01<00:02, 68.44it/s][A | |
| 41%|████ | 129/315 [00:01<00:02, 69.46it/s][A | |
| 43%|████▎ | 136/315 [00:01<00:02, 68.80it/s][A | |
| 45%|████▌ | 143/315 [00:02<00:02, 69.00it/s][A | |
| 48%|████▊ | 152/315 [00:02<00:02, 73.01it/s][A | |
| 51%|█████ | 160/315 [00:02<00:02, 73.09it/s][A | |
| 53%|█████▎ | 168/315 [00:02<00:02, 71.75it/s][A | |
| 56%|█████▌ | 176/315 [00:02<00:01, 70.75it/s][A | |
| 58%|█████▊ | 184/315 [00:02<00:01, 68.76it/s][A | |
| 61%|██████ | 192/315 [00:02<00:01, 68.24it/s][A | |
| 63%|██████▎ | 199/315 [00:02<00:01, 65.54it/s][A | |
| 65%|██████▌ | 206/315 [00:02<00:01, 64.34it/s][A | |
| 68%|██████▊ | 214/315 [00:03<00:01, 67.80it/s][A | |
| 70%|███████ | 222/315 [00:03<00:01, 69.65it/s][A | |
| 73%|███████▎ | 231/315 [00:03<00:01, 72.94it/s][A | |
| 76%|███████▌ | 239/315 [00:03<00:01, 74.13it/s][A | |
| 78%|███████▊ | 247/315 [00:03<00:00, 70.32it/s][A | |
| 81%|████████ | 255/315 [00:03<00:00, 69.10it/s][A | |
| 83%|████████▎ | 263/315 [00:03<00:00, 70.38it/s][A | |
| 86%|████████▌ | 271/315 [00:03<00:00, 72.51it/s][A | |
| 89%|████████▉ | 280/315 [00:03<00:00, 74.93it/s][A | |
| 91%|█████████▏| 288/315 [00:04<00:00, 71.84it/s][A | |
| 94%|█████████▍| 296/315 [00:04<00:00, 70.55it/s][A | |
| 97%|█████████▋| 304/315 [00:04<00:00, 71.99it/s][A | |
| 99%|█████████▉| 312/315 [00:04<00:00, 72.72it/s][A | |
| [A 40%|████ | 684/1710 [05:54<07:29, 2.28it/s] | |
| 100%|██████████| 315/315 [00:05<00:00, 72.72it/s][A | |
| [A[INFO|trainer.py:3503] 2024-09-09 12:20:50,545 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-684 | |
| [INFO|configuration_utils.py:472] 2024-09-09 12:20:50,547 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-684/config.json | |
| [INFO|modeling_utils.py:2799] 2024-09-09 12:20:51,556 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-684/model.safetensors | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:20:51,557 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-684/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:20:51,558 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-684/special_tokens_map.json | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:20:54,643 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:20:54,643 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json | |
| 40%|████ | 685/1710 [05:59<58:21, 3.42s/it] 40%|████ | 686/1710 [05:59<43:44, 2.56s/it] 40%|████ | 687/1710 [06:00<33:23, 1.96s/it] 40%|████ | 688/1710 [06:00<26:00, 1.53s/it] 40%|████ | 689/1710 [06:01<20:06, 1.18s/it] 40%|████ | 690/1710 [06:01<16:09, 1.05it/s] 40%|████ | 691/1710 [06:02<13:18, 1.28it/s] 40%|████ | 692/1710 [06:02<11:37, 1.46it/s] 41%|████ | 693/1710 [06:03<12:01, 1.41it/s] 41%|████ | 694/1710 [06:03<10:45, 1.57it/s] 41%|████ | 695/1710 [06:04<09:24, 1.80it/s] 41%|████ | 696/1710 [06:04<08:29, 1.99it/s] 41%|████ | 697/1710 [06:04<07:36, 2.22it/s] 41%|████ | 698/1710 [06:05<08:23, 2.01it/s] 41%|████ | 699/1710 [06:05<07:52, 2.14it/s] 41%|████ | 700/1710 [06:06<07:50, 2.15it/s] 41%|████ | 701/1710 [06:06<08:07, 2.07it/s] 41%|████ | 702/1710 [06:07<07:46, 2.16it/s] 41%|████ | 703/1710 [06:07<07:54, 2.12it/s] 41%|████ | 704/1710 [06:08<07:31, 2.23it/s] 41%|████ | 705/1710 [06:08<07:08, 2.35it/s] 41%|████▏ | 706/1710 [06:08<07:00, 2.39it/s] 41%|████▏ | 707/1710 [06:09<06:42, 2.49it/s] 41%|████▏ | 708/1710 [06:09<06:27, 2.59it/s] 41%|████▏ | 709/1710 [06:10<06:31, 2.55it/s] 42%|████▏ | 710/1710 [06:10<06:26, 2.59it/s] 42%|████▏ | 711/1710 [06:10<06:33, 2.54it/s] 42%|████▏ | 712/1710 [06:11<08:21, 1.99it/s] 42%|████▏ | 713/1710 [06:12<07:48, 2.13it/s] 42%|████▏ | 714/1710 [06:12<07:09, 2.32it/s] 42%|████▏ | 715/1710 [06:12<07:21, 2.25it/s] 42%|████▏ | 716/1710 [06:13<07:31, 2.20it/s] 42%|████▏ | 717/1710 [06:13<07:34, 2.18it/s] 42%|████▏ | 718/1710 [06:14<07:23, 2.24it/s] 42%|████▏ | 719/1710 [06:14<07:04, 2.33it/s] 42%|████▏ | 720/1710 [06:15<08:07, 2.03it/s] 42%|████▏ | 721/1710 [06:16<09:23, 1.75it/s] 42%|████▏ | 722/1710 [06:16<08:31, 1.93it/s] 42%|████▏ | 723/1710 [06:16<08:00, 2.06it/s] 42%|████▏ | 724/1710 [06:17<07:26, 2.21it/s] 42%|████▏ | 725/1710 [06:17<07:33, 2.17it/s] 42%|████▏ | 726/1710 [06:18<07:30, 2.18it/s] 43%|████▎ | 727/1710 [06:18<07:21, 2.22it/s] 43%|████▎ | 728/1710 [06:18<07:16, 2.25it/s] 43%|████▎ | 729/1710 [06:19<07:16, 2.25it/s] 43%|████▎ | 730/1710 [06:19<07:37, 2.14it/s] 43%|████▎ | 731/1710 [06:20<07:16, 2.24it/s] 43%|████▎ | 732/1710 [06:21<09:06, 1.79it/s] 43%|████▎ | 733/1710 [06:21<08:17, 1.97it/s] 43%|████▎ | 734/1710 [06:22<08:05, 2.01it/s] 43%|████▎ | 735/1710 [06:22<07:20, 2.21it/s] 43%|████▎ | 736/1710 [06:22<06:48, 2.39it/s] 43%|████▎ | 737/1710 [06:23<06:53, 2.35it/s] 43%|████▎ | 738/1710 [06:23<06:33, 2.47it/s] 43%|████▎ | 739/1710 [06:23<06:47, 2.38it/s] 43%|████▎ | 740/1710 [06:24<06:53, 2.35it/s] 43%|████▎ | 741/1710 [06:24<07:03, 2.29it/s] 43%|████▎ | 742/1710 [06:25<07:20, 2.20it/s] 43%|████▎ | 743/1710 [06:25<06:52, 2.35it/s] 44%|████▎ | 744/1710 [06:26<06:45, 2.38it/s] 44%|████▎ | 745/1710 [06:26<06:27, 2.49it/s] 44%|████▎ | 746/1710 [06:26<06:33, 2.45it/s] 44%|████▎ | 747/1710 [06:27<06:34, 2.44it/s] 44%|████▎ | 748/1710 [06:27<06:53, 2.33it/s] 44%|████▍ | 749/1710 [06:28<06:32, 2.45it/s] 44%|████▍ | 750/1710 [06:28<07:04, 2.26it/s] 44%|████▍ | 751/1710 [06:29<06:52, 2.32it/s] 44%|████▍ | 752/1710 [06:29<07:07, 2.24it/s] 44%|████▍ | 753/1710 [06:30<07:13, 2.21it/s] 44%|████▍ | 754/1710 [06:30<07:17, 2.19it/s] 44%|████▍ | 755/1710 [06:30<07:24, 2.15it/s] 44%|████▍ | 756/1710 [06:31<07:10, 2.22it/s] 44%|████▍ | 757/1710 [06:31<06:52, 2.31it/s] 44%|████▍ | 758/1710 [06:32<07:40, 2.07it/s] 44%|████▍ | 759/1710 [06:32<07:50, 2.02it/s] 44%|████▍ | 760/1710 [06:33<08:20, 1.90it/s] 45%|████▍ | 761/1710 [06:33<07:52, 2.01it/s] 45%|████▍ | 762/1710 [06:34<10:14, 1.54it/s] 45%|████▍ | 763/1710 [06:35<08:51, 1.78it/s] 45%|████▍ | 764/1710 [06:36<10:01, 1.57it/s] 45%|████▍ | 765/1710 [06:36<09:41, 1.63it/s] 45%|████▍ | 766/1710 [06:37<09:38, 1.63it/s] 45%|████▍ | 767/1710 [06:37<08:34, 1.83it/s] 45%|████▍ | 768/1710 [06:38<08:11, 1.92it/s] 45%|████▍ | 769/1710 [06:38<08:35, 1.83it/s] 45%|████▌ | 770/1710 [06:39<07:59, 1.96it/s] 45%|████▌ | 771/1710 [06:39<07:10, 2.18it/s] 45%|████▌ | 772/1710 [06:40<07:18, 2.14it/s] 45%|████▌ | 773/1710 [06:40<07:18, 2.14it/s] 45%|████▌ | 774/1710 [06:40<07:09, 2.18it/s] 45%|████▌ | 775/1710 [06:41<07:41, 2.03it/s] 45%|████▌ | 776/1710 [06:41<07:22, 2.11it/s] 45%|████▌ | 777/1710 [06:42<06:46, 2.30it/s] 45%|████▌ | 778/1710 [06:42<07:29, 2.07it/s] 46%|████▌ | 779/1710 [06:43<07:40, 2.02it/s] 46%|████▌ | 780/1710 [06:43<07:20, 2.11it/s] 46%|████▌ | 781/1710 [06:44<07:23, 2.09it/s] 46%|████▌ | 782/1710 [06:44<06:49, 2.27it/s] 46%|████▌ | 783/1710 [06:45<06:29, 2.38it/s] 46%|████▌ | 784/1710 [06:45<06:20, 2.43it/s] 46%|████▌ | 785/1710 [06:45<06:20, 2.43it/s] 46%|████▌ | 786/1710 [06:46<06:33, 2.35it/s] 46%|████▌ | 787/1710 [06:46<06:20, 2.42it/s] 46%|████▌ | 788/1710 [06:47<06:37, 2.32it/s] 46%|████▌ | 789/1710 [06:47<07:32, 2.04it/s] 46%|████▌ | 790/1710 [06:48<07:11, 2.13it/s] 46%|████▋ | 791/1710 [06:48<06:46, 2.26it/s] 46%|████▋ | 792/1710 [06:48<06:25, 2.38it/s] 46%|████▋ | 793/1710 [06:49<06:33, 2.33it/s] 46%|████▋ | 794/1710 [06:49<06:33, 2.33it/s] 46%|████▋ | 795/1710 [06:50<06:37, 2.30it/s] 47%|████▋ | 796/1710 [06:50<06:44, 2.26it/s] 47%|████▋ | 797/1710 [06:51<07:03, 2.16it/s] 47%|████▋ | 798/1710 [06:51<06:49, 2.23it/s] 47%|████▋ | 799/1710 [06:52<06:26, 2.36it/s] 47%|████▋ | 800/1710 [06:52<06:12, 2.44it/s] 47%|████▋ | 801/1710 [06:53<07:40, 1.98it/s] 47%|████▋ | 802/1710 [06:53<07:04, 2.14it/s] 47%|████▋ | 803/1710 [06:53<06:59, 2.16it/s] 47%|████▋ | 804/1710 [06:54<07:15, 2.08it/s] 47%|████▋ | 805/1710 [06:54<07:01, 2.15it/s] 47%|████▋ | 806/1710 [06:55<06:39, 2.26it/s] 47%|████▋ | 807/1710 [06:55<06:47, 2.22it/s] 47%|████▋ | 808/1710 [06:56<07:02, 2.13it/s] 47%|████▋ | 809/1710 [06:56<06:48, 2.21it/s] 47%|████▋ | 810/1710 [06:57<06:37, 2.26it/s] 47%|████▋ | 811/1710 [06:57<08:25, 1.78it/s] 47%|████▋ | 812/1710 [06:58<08:27, 1.77it/s] 48%|████▊ | 813/1710 [06:58<07:42, 1.94it/s] 48%|████▊ | 814/1710 [06:59<07:15, 2.06it/s] 48%|████▊ | 815/1710 [06:59<07:01, 2.12it/s] 48%|████▊ | 816/1710 [07:00<06:50, 2.18it/s] 48%|████▊ | 817/1710 [07:00<07:47, 1.91it/s] 48%|████▊ | 818/1710 [07:01<07:30, 1.98it/s] 48%|████▊ | 819/1710 [07:01<07:12, 2.06it/s] 48%|████▊ | 820/1710 [07:02<06:52, 2.16it/s] 48%|████▊ | 821/1710 [07:02<06:21, 2.33it/s] 48%|████▊ | 822/1710 [07:03<06:41, 2.21it/s] 48%|████▊ | 823/1710 [07:03<06:46, 2.18it/s] 48%|████▊ | 824/1710 [07:03<06:27, 2.29it/s] 48%|████▊ | 825/1710 [07:04<06:34, 2.25it/s] 48%|████▊ | 826/1710 [07:04<06:15, 2.36it/s] 48%|████▊ | 827/1710 [07:05<06:25, 2.29it/s] 48%|████▊ | 828/1710 [07:05<06:08, 2.40it/s] 48%|████▊ | 829/1710 [07:06<06:18, 2.33it/s] 49%|████▊ | 830/1710 [07:06<06:09, 2.38it/s] 49%|████▊ | 831/1710 [07:06<05:47, 2.53it/s] 49%|████▊ | 832/1710 [07:07<06:40, 2.19it/s] 49%|████▊ | 833/1710 [07:07<06:10, 2.37it/s] 49%|████▉ | 834/1710 [07:08<06:16, 2.32it/s] 49%|████▉ | 835/1710 [07:08<06:11, 2.36it/s] 49%|████▉ | 836/1710 [07:09<06:44, 2.16it/s] 49%|████▉ | 837/1710 [07:09<07:02, 2.07it/s] 49%|████▉ | 838/1710 [07:10<06:59, 2.08it/s] 49%|████▉ | 839/1710 [07:10<06:50, 2.12it/s] 49%|████▉ | 840/1710 [07:10<06:34, 2.20it/s] 49%|████▉ | 841/1710 [07:11<07:24, 1.95it/s] 49%|████▉ | 842/1710 [07:11<06:39, 2.17it/s] 49%|████▉ | 843/1710 [07:12<06:14, 2.31it/s] 49%|████▉ | 844/1710 [07:12<05:52, 2.46it/s] 49%|████▉ | 845/1710 [07:13<05:44, 2.51it/s] 49%|████▉ | 846/1710 [07:13<05:48, 2.48it/s] 50%|████▉ | 847/1710 [07:13<06:03, 2.37it/s] 50%|████▉ | 848/1710 [07:14<06:24, 2.24it/s] 50%|████▉ | 849/1710 [07:14<06:08, 2.33it/s] 50%|████▉ | 850/1710 [07:15<06:31, 2.20it/s] 50%|████▉ | 851/1710 [07:15<07:16, 1.97it/s] 50%|████▉ | 852/1710 [07:16<06:58, 2.05it/s] 50%|████▉ | 853/1710 [07:16<06:22, 2.24it/s] 50%|████▉ | 854/1710 [07:17<08:00, 1.78it/s] 50%|█████ | 855/1710 [07:17<07:02, 2.03it/s][INFO|trainer.py:811] 2024-09-09 12:22:13,597 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: ner_tags, id, tokens. If ner_tags, id, tokens are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. | |
| [INFO|trainer.py:3819] 2024-09-09 12:22:13,600 >> | |
| ***** Running Evaluation ***** | |
| [INFO|trainer.py:3821] 2024-09-09 12:22:13,600 >> Num examples = 2519 | |
| [INFO|trainer.py:3824] 2024-09-09 12:22:13,600 >> Batch size = 8 | |
| {'eval_loss': 0.20180054008960724, 'eval_precision': 0.6321671525753159, 'eval_recall': 0.7120963327859879, 'eval_f1': 0.6697554697554697, 'eval_accuracy': 0.9466296640893195, 'eval_runtime': 5.9193, 'eval_samples_per_second': 425.559, 'eval_steps_per_second': 53.216, 'epoch': 4.0} | |
| 0%| | 0/315 [00:00<?, ?it/s][A | |
| 3%|▎ | 8/315 [00:00<00:03, 78.93it/s][A | |
| 5%|▌ | 16/315 [00:00<00:03, 75.67it/s][A | |
| 8%|▊ | 24/315 [00:00<00:03, 77.43it/s][A | |
| 10%|█ | 32/315 [00:00<00:03, 72.51it/s][A | |
| 13%|█▎ | 41/315 [00:00<00:03, 76.59it/s][A | |
| 16%|█▌ | 49/315 [00:00<00:03, 75.19it/s][A | |
| 18%|█▊ | 57/315 [00:00<00:03, 75.16it/s][A | |
| 21%|██ | 65/315 [00:00<00:03, 72.01it/s][A | |
| 23%|██▎ | 73/315 [00:00<00:03, 74.00it/s][A | |
| 26%|██▌ | 81/315 [00:01<00:03, 70.34it/s][A | |
| 28%|██▊ | 89/315 [00:01<00:03, 67.95it/s][A | |
| 31%|███ | 97/315 [00:01<00:03, 67.54it/s][A | |
| 33%|███▎ | 105/315 [00:01<00:03, 69.21it/s][A | |
| 36%|███▌ | 113/315 [00:01<00:02, 70.94it/s][A | |
| 38%|███▊ | 121/315 [00:01<00:02, 69.41it/s][A | |
| 41%|████ | 129/315 [00:01<00:02, 70.59it/s][A | |
| 43%|████▎ | 137/315 [00:01<00:02, 70.14it/s][A | |
| 46%|████▌ | 145/315 [00:02<00:02, 70.44it/s][A | |
| 49%|████▉ | 154/315 [00:02<00:02, 73.99it/s][A | |
| 51%|█████▏ | 162/315 [00:02<00:02, 72.44it/s][A | |
| 54%|█████▍ | 170/315 [00:02<00:02, 71.54it/s][A | |
| 57%|█████▋ | 178/315 [00:02<00:01, 70.94it/s][A | |
| 59%|█████▉ | 186/315 [00:02<00:01, 68.96it/s][A | |
| 61%|██████▏ | 193/315 [00:02<00:01, 68.54it/s][A | |
| 63%|██████▎ | 200/315 [00:02<00:01, 65.85it/s][A | |
| 66%|██████▌ | 207/315 [00:02<00:01, 64.60it/s][A | |
| 68%|██████▊ | 215/315 [00:03<00:01, 67.64it/s][A | |
| 71%|███████ | 223/315 [00:03<00:01, 70.13it/s][A | |
| 74%|███████▎ | 232/315 [00:03<00:01, 73.45it/s][A | |
| 76%|███████▌ | 240/315 [00:03<00:01, 73.27it/s][A | |
| 79%|███████▊ | 248/315 [00:03<00:00, 71.10it/s][A | |
| 81%|████████▏ | 256/315 [00:03<00:00, 69.16it/s][A | |
| 84%|████████▍ | 264/315 [00:03<00:00, 70.02it/s][A | |
| 87%|████████▋ | 273/315 [00:03<00:00, 73.29it/s][A | |
| 90%|████████▉ | 282/315 [00:03<00:00, 75.61it/s][A | |
| 92%|█████████▏| 290/315 [00:04<00:00, 71.21it/s][A | |
| 95%|█████████▍| 298/315 [00:04<00:00, 70.13it/s][A | |
| 97%|█████████▋| 306/315 [00:04<00:00, 72.26it/s][A | |
| 100%|█████████▉| 314/315 [00:04<00:00, 70.37it/s][A | |
| [A 50%|█████ | 855/1710 [07:23<07:02, 2.03it/s] | |
| 100%|██████████| 315/315 [00:05<00:00, 70.37it/s][A | |
| [A[INFO|trainer.py:3503] 2024-09-09 12:22:19,502 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-855 | |
| [INFO|configuration_utils.py:472] 2024-09-09 12:22:19,503 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-855/config.json | |
| [INFO|modeling_utils.py:2799] 2024-09-09 12:22:20,520 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-855/model.safetensors | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:22:20,521 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-855/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:22:20,521 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-855/special_tokens_map.json | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:22:23,617 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:22:23,618 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json | |
| 50%|█████ | 856/1710 [07:28<49:47, 3.50s/it] 50%|█████ | 857/1710 [07:28<36:38, 2.58s/it] 50%|█████ | 858/1710 [07:29<27:38, 1.95s/it] 50%|█████ | 859/1710 [07:29<21:05, 1.49s/it] 50%|█████ | 860/1710 [07:30<16:46, 1.18s/it] 50%|█████ | 861/1710 [07:30<13:59, 1.01it/s] 50%|█████ | 862/1710 [07:31<11:25, 1.24it/s] 50%|█████ | 863/1710 [07:31<09:20, 1.51it/s] 51%|█████ | 864/1710 [07:31<08:31, 1.65it/s] 51%|█████ | 865/1710 [07:32<07:42, 1.83it/s] 51%|█████ | 866/1710 [07:32<07:16, 1.93it/s] 51%|█████ | 867/1710 [07:33<06:57, 2.02it/s] 51%|█████ | 868/1710 [07:33<06:51, 2.05it/s] 51%|█████ | 869/1710 [07:34<06:43, 2.08it/s] 51%|█████ | 870/1710 [07:34<07:00, 2.00it/s] 51%|█████ | 871/1710 [07:35<06:47, 2.06it/s] 51%|█████ | 872/1710 [07:35<06:29, 2.15it/s] 51%|█████ | 873/1710 [07:36<06:31, 2.14it/s] 51%|█████ | 874/1710 [07:36<06:16, 2.22it/s] 51%|█████ | 875/1710 [07:36<06:07, 2.27it/s] 51%|█████ | 876/1710 [07:37<05:35, 2.49it/s] 51%|█████▏ | 877/1710 [07:37<05:57, 2.33it/s] 51%|█████▏ | 878/1710 [07:38<06:00, 2.31it/s] 51%|█████▏ | 879/1710 [07:38<05:42, 2.43it/s] 51%|█████▏ | 880/1710 [07:39<06:07, 2.26it/s] 52%|█████▏ | 881/1710 [07:39<06:57, 1.99it/s] 52%|█████▏ | 882/1710 [07:40<06:40, 2.07it/s] 52%|█████▏ | 883/1710 [07:40<07:21, 1.87it/s] 52%|█████▏ | 884/1710 [07:41<06:38, 2.07it/s] 52%|█████▏ | 885/1710 [07:41<06:25, 2.14it/s] 52%|█████▏ | 886/1710 [07:42<06:17, 2.19it/s] 52%|█████▏ | 887/1710 [07:42<07:21, 1.86it/s] 52%|█████▏ | 888/1710 [07:43<07:38, 1.79it/s] 52%|█████▏ | 889/1710 [07:43<08:01, 1.70it/s] 52%|█████▏ | 890/1710 [07:44<07:40, 1.78it/s] 52%|█████▏ | 891/1710 [07:44<07:02, 1.94it/s] 52%|█████▏ | 892/1710 [07:45<06:47, 2.01it/s] 52%|█████▏ | 893/1710 [07:45<06:52, 1.98it/s] 52%|█████▏ | 894/1710 [07:46<06:43, 2.02it/s] 52%|█████▏ | 895/1710 [07:46<06:01, 2.26it/s] 52%|█████▏ | 896/1710 [07:47<05:50, 2.33it/s] 52%|█████▏ | 897/1710 [07:47<06:04, 2.23it/s] 53%|█████▎ | 898/1710 [07:48<06:09, 2.20it/s] 53%|█████▎ | 899/1710 [07:48<05:43, 2.36it/s] 53%|█████▎ | 900/1710 [07:48<05:47, 2.33it/s] 53%|█████▎ | 901/1710 [07:49<06:07, 2.20it/s] 53%|█████▎ | 902/1710 [07:50<08:15, 1.63it/s] 53%|█████▎ | 903/1710 [07:50<07:47, 1.73it/s] 53%|█████▎ | 904/1710 [07:51<07:18, 1.84it/s] 53%|█████▎ | 905/1710 [07:51<06:44, 1.99it/s] 53%|█████▎ | 906/1710 [07:52<06:32, 2.05it/s] 53%|█████▎ | 907/1710 [07:52<06:15, 2.14it/s] 53%|█████▎ | 908/1710 [07:53<06:47, 1.97it/s] 53%|█████▎ | 909/1710 [07:53<06:41, 1.99it/s] 53%|█████▎ | 910/1710 [07:54<06:20, 2.10it/s] 53%|█████▎ | 911/1710 [07:54<06:38, 2.00it/s] 53%|█████▎ | 912/1710 [07:55<06:58, 1.91it/s] 53%|█████▎ | 913/1710 [07:55<06:27, 2.06it/s] 53%|█████▎ | 914/1710 [07:55<05:57, 2.23it/s] 54%|█████▎ | 915/1710 [07:56<06:04, 2.18it/s] 54%|█████▎ | 916/1710 [07:56<05:44, 2.31it/s] 54%|█████▎ | 917/1710 [07:57<05:30, 2.40it/s] 54%|█████▎ | 918/1710 [07:57<05:12, 2.54it/s] 54%|█████▎ | 919/1710 [07:58<05:43, 2.30it/s] 54%|█████▍ | 920/1710 [07:58<05:45, 2.29it/s] 54%|█████▍ | 921/1710 [07:58<05:41, 2.31it/s] 54%|█████▍ | 922/1710 [07:59<06:45, 1.94it/s] 54%|█████▍ | 923/1710 [08:00<06:24, 2.05it/s] 54%|█████▍ | 924/1710 [08:00<06:09, 2.13it/s] 54%|█████▍ | 925/1710 [08:00<05:41, 2.30it/s] 54%|█████▍ | 926/1710 [08:01<05:57, 2.19it/s] 54%|█████▍ | 927/1710 [08:01<06:03, 2.15it/s] 54%|█████▍ | 928/1710 [08:02<06:14, 2.09it/s] 54%|█████▍ | 929/1710 [08:02<05:51, 2.22it/s] 54%|█████▍ | 930/1710 [08:03<05:34, 2.33it/s] 54%|█████▍ | 931/1710 [08:03<05:30, 2.35it/s] 55%|█████▍ | 932/1710 [08:03<05:29, 2.36it/s] 55%|█████▍ | 933/1710 [08:04<06:02, 2.14it/s] 55%|█████▍ | 934/1710 [08:04<06:01, 2.15it/s] 55%|█████▍ | 935/1710 [08:05<05:49, 2.22it/s] 55%|█████▍ | 936/1710 [08:05<05:35, 2.31it/s] 55%|█████▍ | 937/1710 [08:06<06:00, 2.14it/s] 55%|█████▍ | 938/1710 [08:07<08:03, 1.60it/s] 55%|█████▍ | 939/1710 [08:07<07:56, 1.62it/s] 55%|█████▍ | 940/1710 [08:08<07:14, 1.77it/s] 55%|█████▌ | 941/1710 [08:08<07:01, 1.83it/s] 55%|█████▌ | 942/1710 [08:09<06:21, 2.01it/s] 55%|█████▌ | 943/1710 [08:09<06:01, 2.12it/s] 55%|█████▌ | 944/1710 [08:10<06:22, 2.00it/s] 55%|█████▌ | 945/1710 [08:10<05:49, 2.19it/s] 55%|█████▌ | 946/1710 [08:11<05:49, 2.18it/s] 55%|█████▌ | 947/1710 [08:11<06:53, 1.85it/s] 55%|█████▌ | 948/1710 [08:12<06:45, 1.88it/s] 55%|█████▌ | 949/1710 [08:12<06:26, 1.97it/s] 56%|█████▌ | 950/1710 [08:13<07:00, 1.81it/s] 56%|█████▌ | 951/1710 [08:13<07:05, 1.78it/s] 56%|█████▌ | 952/1710 [08:14<06:54, 1.83it/s] 56%|█████▌ | 953/1710 [08:14<06:01, 2.09it/s] 56%|█████▌ | 954/1710 [08:15<05:49, 2.16it/s] 56%|█████▌ | 955/1710 [08:15<05:30, 2.28it/s] 56%|█████▌ | 956/1710 [08:15<05:10, 2.43it/s] 56%|█████▌ | 957/1710 [08:16<05:13, 2.40it/s] 56%|█████▌ | 958/1710 [08:16<05:25, 2.31it/s] 56%|█████▌ | 959/1710 [08:17<05:57, 2.10it/s] 56%|█████▌ | 960/1710 [08:17<05:30, 2.27it/s] 56%|█████▌ | 961/1710 [08:18<05:24, 2.31it/s] 56%|█████▋ | 962/1710 [08:18<05:26, 2.29it/s] 56%|█████▋ | 963/1710 [08:19<05:29, 2.27it/s] 56%|█████▋ | 964/1710 [08:19<05:09, 2.41it/s] 56%|█████▋ | 965/1710 [08:20<06:07, 2.02it/s] 56%|█████▋ | 966/1710 [08:20<05:42, 2.17it/s] 57%|█████▋ | 967/1710 [08:20<05:14, 2.36it/s] 57%|█████▋ | 968/1710 [08:21<05:08, 2.40it/s] 57%|█████▋ | 969/1710 [08:21<05:04, 2.43it/s] 57%|█████▋ | 970/1710 [08:22<05:14, 2.36it/s] 57%|█████▋ | 971/1710 [08:22<04:55, 2.50it/s] 57%|█████▋ | 972/1710 [08:23<06:03, 2.03it/s] 57%|█████▋ | 973/1710 [08:23<06:12, 1.98it/s] 57%|█████▋ | 974/1710 [08:24<07:20, 1.67it/s] 57%|█████▋ | 975/1710 [08:24<06:34, 1.86it/s] 57%|█████▋ | 976/1710 [08:25<06:18, 1.94it/s] 57%|█████▋ | 977/1710 [08:25<05:57, 2.05it/s] 57%|█████▋ | 978/1710 [08:26<06:02, 2.02it/s] 57%|█████▋ | 979/1710 [08:26<05:29, 2.22it/s] 57%|█████▋ | 980/1710 [08:27<05:33, 2.19it/s] 57%|█████▋ | 981/1710 [08:27<05:57, 2.04it/s] 57%|█████▋ | 982/1710 [08:28<06:16, 1.94it/s] 57%|█████▋ | 983/1710 [08:28<06:18, 1.92it/s] 58%|█████▊ | 984/1710 [08:29<05:58, 2.03it/s] 58%|█████▊ | 985/1710 [08:29<05:48, 2.08it/s] 58%|█████▊ | 986/1710 [08:30<05:43, 2.11it/s] 58%|█████▊ | 987/1710 [08:30<05:17, 2.28it/s] 58%|█████▊ | 988/1710 [08:30<05:01, 2.39it/s] 58%|█████▊ | 989/1710 [08:31<05:23, 2.23it/s] 58%|█████▊ | 990/1710 [08:31<05:09, 2.32it/s] 58%|█████▊ | 991/1710 [08:32<04:58, 2.41it/s] 58%|█████▊ | 992/1710 [08:32<04:56, 2.42it/s] 58%|█████▊ | 993/1710 [08:33<05:11, 2.30it/s] 58%|█████▊ | 994/1710 [08:33<04:50, 2.46it/s] 58%|█████▊ | 995/1710 [08:33<04:38, 2.56it/s] 58%|█████▊ | 996/1710 [08:34<04:56, 2.41it/s] 58%|█████▊ | 997/1710 [08:34<04:58, 2.38it/s] 58%|█████▊ | 998/1710 [08:35<04:50, 2.45it/s] 58%|█████▊ | 999/1710 [08:35<04:52, 2.43it/s] 58%|█████▊ | 1000/1710 [08:36<05:34, 2.13it/s] 58%|█████▊ | 1000/1710 [08:36<05:34, 2.13it/s] 59%|█████▊ | 1001/1710 [08:36<05:06, 2.31it/s] 59%|█████▊ | 1002/1710 [08:36<04:50, 2.44it/s] 59%|█████▊ | 1003/1710 [08:37<04:54, 2.40it/s] 59%|█████▊ | 1004/1710 [08:37<05:19, 2.21it/s] 59%|█████▉ | 1005/1710 [08:38<05:13, 2.25it/s] 59%|█████▉ | 1006/1710 [08:38<05:29, 2.14it/s] 59%|█████▉ | 1007/1710 [08:39<05:19, 2.20it/s] 59%|█████▉ | 1008/1710 [08:39<04:51, 2.41it/s] 59%|█████▉ | 1009/1710 [08:39<05:04, 2.30it/s] 59%|█████▉ | 1010/1710 [08:40<05:09, 2.26it/s] 59%|█████▉ | 1011/1710 [08:40<05:03, 2.30it/s] 59%|█████▉ | 1012/1710 [08:41<04:48, 2.42it/s] 59%|█████▉ | 1013/1710 [08:41<04:32, 2.56it/s] 59%|█████▉ | 1014/1710 [08:41<04:22, 2.65it/s] 59%|█████▉ | 1015/1710 [08:42<04:43, 2.45it/s] 59%|█████▉ | 1016/1710 [08:42<04:40, 2.48it/s] 59%|█████▉ | 1017/1710 [08:43<04:50, 2.38it/s] 60%|█████▉ | 1018/1710 [08:43<05:50, 1.98it/s] 60%|█████▉ | 1019/1710 [08:44<06:38, 1.73it/s] 60%|█████▉ | 1020/1710 [08:45<06:03, 1.90it/s] 60%|█████▉ | 1021/1710 [08:45<05:43, 2.00it/s] 60%|█████▉ | 1022/1710 [08:45<05:22, 2.13it/s] 60%|█████▉ | 1023/1710 [08:46<05:06, 2.24it/s] 60%|█████▉ | 1024/1710 [08:46<05:06, 2.24it/s] 60%|█████▉ | 1025/1710 [08:47<05:00, 2.28it/s] 60%|██████ | 1026/1710 [08:47<04:55, 2.32it/s][INFO|trainer.py:811] 2024-09-09 12:23:43,183 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: ner_tags, id, tokens. If ner_tags, id, tokens are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. | |
| [INFO|trainer.py:3819] 2024-09-09 12:23:43,185 >> | |
| ***** Running Evaluation ***** | |
| [INFO|trainer.py:3821] 2024-09-09 12:23:43,185 >> Num examples = 2519 | |
| [INFO|trainer.py:3824] 2024-09-09 12:23:43,185 >> Batch size = 8 | |
| {'eval_loss': 0.21526136994361877, 'eval_precision': 0.6441176470588236, 'eval_recall': 0.7192118226600985, 'eval_f1': 0.6795965865011637, 'eval_accuracy': 0.9465013314511213, 'eval_runtime': 5.9003, 'eval_samples_per_second': 426.928, 'eval_steps_per_second': 53.387, 'epoch': 5.0} | |
| {'loss': 0.0234, 'grad_norm': 1.644018530845642, 'learning_rate': 2.0760233918128656e-05, 'epoch': 5.85} | |
| 0%| | 0/315 [00:00<?, ?it/s][A | |
| 3%|▎ | 8/315 [00:00<00:03, 76.95it/s][A | |
| 5%|▌ | 16/315 [00:00<00:04, 73.21it/s][A | |
| 8%|▊ | 24/315 [00:00<00:03, 74.55it/s][A | |
| 10%|█ | 32/315 [00:00<00:04, 70.51it/s][A | |
| 13%|█▎ | 40/315 [00:00<00:03, 73.42it/s][A | |
| 15%|█▌ | 48/315 [00:00<00:03, 73.85it/s][A | |
| 18%|█▊ | 56/315 [00:00<00:03, 73.02it/s][A | |
| 20%|██ | 64/315 [00:00<00:03, 70.57it/s][A | |
| 23%|██▎ | 72/315 [00:00<00:03, 72.53it/s][A | |
| 25%|██▌ | 80/315 [00:01<00:03, 69.09it/s][A | |
| 28%|██▊ | 87/315 [00:01<00:03, 67.97it/s][A | |
| 30%|███ | 95/315 [00:01<00:03, 69.43it/s][A | |
| 32%|███▏ | 102/315 [00:01<00:03, 65.49it/s][A | |
| 35%|███▍ | 110/315 [00:01<00:02, 68.44it/s][A | |
| 37%|███▋ | 118/315 [00:01<00:02, 69.86it/s][A | |
| 40%|████ | 126/315 [00:01<00:02, 67.35it/s][A | |
| 43%|████▎ | 134/315 [00:01<00:02, 67.80it/s][A | |
| 45%|████▌ | 142/315 [00:02<00:02, 68.12it/s][A | |
| 48%|████▊ | 150/315 [00:02<00:02, 71.28it/s][A | |
| 50%|█████ | 158/315 [00:02<00:02, 73.42it/s][A | |
| 53%|█████▎ | 166/315 [00:02<00:02, 71.60it/s][A | |
| 55%|█████▌ | 174/315 [00:02<00:01, 70.67it/s][A | |
| 58%|█████▊ | 182/315 [00:02<00:01, 68.25it/s][A | |
| 60%|██████ | 189/315 [00:02<00:01, 68.29it/s][A | |
| 62%|██████▏ | 196/315 [00:02<00:01, 67.83it/s][A | |
| 64%|██████▍ | 203/315 [00:02<00:01, 64.48it/s][A | |
| 67%|██████▋ | 210/315 [00:03<00:01, 64.78it/s][A | |
| 69%|██████▉ | 218/315 [00:03<00:01, 68.51it/s][A | |
| 72%|███████▏ | 226/315 [00:03<00:01, 71.02it/s][A | |
| 74%|███████▍ | 234/315 [00:03<00:01, 73.36it/s][A | |
| 77%|███████▋ | 242/315 [00:03<00:01, 70.52it/s][A | |
| 79%|███████▉ | 250/315 [00:03<00:00, 70.36it/s][A | |
| 82%|████████▏ | 258/315 [00:03<00:00, 68.28it/s][A | |
| 84%|████████▍ | 266/315 [00:03<00:00, 69.51it/s][A | |
| 87%|████████▋ | 275/315 [00:03<00:00, 72.89it/s][A | |
| 90%|████████▉ | 283/315 [00:04<00:00, 74.04it/s][A | |
| 92%|█████████▏| 291/315 [00:04<00:00, 70.70it/s][A | |
| 95%|█████████▍| 299/315 [00:04<00:00, 69.87it/s][A | |
| 97%|█████████▋| 307/315 [00:04<00:00, 71.23it/s][A | |
| 100%|██████████| 315/315 [00:04<00:00, 70.17it/s][A | |
| [A 60%|██████ | 1026/1710 [08:53<04:55, 2.32it/s] | |
| 100%|██████████| 315/315 [00:05<00:00, 70.17it/s][A | |
| [A[INFO|trainer.py:3503] 2024-09-09 12:23:49,149 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-1026 | |
| [INFO|configuration_utils.py:472] 2024-09-09 12:23:49,150 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-1026/config.json | |
| [INFO|modeling_utils.py:2799] 2024-09-09 12:23:50,155 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-1026/model.safetensors | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:23:50,156 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-1026/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:23:50,156 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-1026/special_tokens_map.json | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:23:53,206 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:23:53,207 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json | |
| 60%|██████ | 1027/1710 [08:58<39:37, 3.48s/it] 60%|██████ | 1028/1710 [08:58<29:05, 2.56s/it] 60%|██████ | 1029/1710 [08:58<21:41, 1.91s/it] 60%|██████ | 1030/1710 [08:59<16:26, 1.45s/it] 60%|██████ | 1031/1710 [08:59<12:41, 1.12s/it] 60%|██████ | 1032/1710 [09:00<10:32, 1.07it/s] 60%|██████ | 1033/1710 [09:00<08:59, 1.25it/s] 60%|██████ | 1034/1710 [09:01<07:56, 1.42it/s] 61%|██████ | 1035/1710 [09:01<07:15, 1.55it/s] 61%|██████ | 1036/1710 [09:01<06:09, 1.82it/s] 61%|██████ | 1037/1710 [09:02<05:33, 2.02it/s] 61%|██████ | 1038/1710 [09:02<05:15, 2.13it/s] 61%|██████ | 1039/1710 [09:03<04:51, 2.30it/s] 61%|██████ | 1040/1710 [09:03<05:13, 2.14it/s] 61%|██████ | 1041/1710 [09:04<04:55, 2.27it/s] 61%|██████ | 1042/1710 [09:04<04:48, 2.32it/s] 61%|██████ | 1043/1710 [09:04<04:38, 2.39it/s] 61%|██████ | 1044/1710 [09:05<05:08, 2.16it/s] 61%|██████ | 1045/1710 [09:05<04:50, 2.29it/s] 61%|██████ | 1046/1710 [09:06<04:43, 2.35it/s] 61%|██████ | 1047/1710 [09:06<04:48, 2.29it/s] 61%|██████▏ | 1048/1710 [09:07<04:46, 2.31it/s] 61%|██████▏ | 1049/1710 [09:07<04:50, 2.27it/s] 61%|██████▏ | 1050/1710 [09:07<04:38, 2.37it/s] 61%|██████▏ | 1051/1710 [09:08<04:37, 2.38it/s] 62%|██████▏ | 1052/1710 [09:08<04:19, 2.53it/s] 62%|██████▏ | 1053/1710 [09:09<04:18, 2.54it/s] 62%|██████▏ | 1054/1710 [09:09<04:27, 2.45it/s] 62%|██████▏ | 1055/1710 [09:10<04:53, 2.23it/s] 62%|██████▏ | 1056/1710 [09:10<04:24, 2.47it/s] 62%|██████▏ | 1057/1710 [09:10<04:37, 2.36it/s] 62%|██████▏ | 1058/1710 [09:11<04:57, 2.19it/s] 62%|██████▏ | 1059/1710 [09:11<05:03, 2.15it/s] 62%|██████▏ | 1060/1710 [09:12<05:09, 2.10it/s] 62%|██████▏ | 1061/1710 [09:12<05:11, 2.09it/s] 62%|██████▏ | 1062/1710 [09:13<04:58, 2.17it/s] 62%|██████▏ | 1063/1710 [09:13<05:08, 2.09it/s] 62%|██████▏ | 1064/1710 [09:14<04:40, 2.30it/s] 62%|██████▏ | 1065/1710 [09:14<04:20, 2.48it/s] 62%|██████▏ | 1066/1710 [09:14<04:29, 2.39it/s] 62%|██████▏ | 1067/1710 [09:15<04:32, 2.36it/s] 62%|██████▏ | 1068/1710 [09:15<05:05, 2.10it/s] 63%|██████▎ | 1069/1710 [09:16<04:32, 2.35it/s] 63%|██████▎ | 1070/1710 [09:16<04:28, 2.39it/s] 63%|██████▎ | 1071/1710 [09:16<04:18, 2.47it/s] 63%|██████▎ | 1072/1710 [09:17<05:07, 2.08it/s] 63%|██████▎ | 1073/1710 [09:18<05:44, 1.85it/s] 63%|██████▎ | 1074/1710 [09:18<05:55, 1.79it/s] 63%|██████▎ | 1075/1710 [09:19<05:28, 1.93it/s] 63%|██████▎ | 1076/1710 [09:19<05:03, 2.09it/s] 63%|██████▎ | 1077/1710 [09:20<04:43, 2.23it/s] 63%|██████▎ | 1078/1710 [09:20<04:22, 2.41it/s] 63%|██████▎ | 1079/1710 [09:20<04:22, 2.40it/s] 63%|██████▎ | 1080/1710 [09:21<04:25, 2.37it/s] 63%|██████▎ | 1081/1710 [09:21<04:50, 2.17it/s] 63%|██████▎ | 1082/1710 [09:22<04:39, 2.24it/s] 63%|██████▎ | 1083/1710 [09:22<04:30, 2.32it/s] 63%|██████▎ | 1084/1710 [09:23<04:32, 2.29it/s] 63%|██████▎ | 1085/1710 [09:23<04:11, 2.49it/s] 64%|██████▎ | 1086/1710 [09:23<04:00, 2.59it/s] 64%|██████▎ | 1087/1710 [09:24<04:19, 2.40it/s] 64%|██████▎ | 1088/1710 [09:24<04:35, 2.26it/s] 64%|██████▎ | 1089/1710 [09:25<05:35, 1.85it/s] 64%|██████▎ | 1090/1710 [09:25<05:04, 2.04it/s] 64%|██████▍ | 1091/1710 [09:26<04:29, 2.29it/s] 64%|██████▍ | 1092/1710 [09:26<05:02, 2.04it/s] 64%|██████▍ | 1093/1710 [09:27<05:13, 1.97it/s] 64%|██████▍ | 1094/1710 [09:27<04:56, 2.08it/s] 64%|██████▍ | 1095/1710 [09:28<04:38, 2.21it/s] 64%|██████▍ | 1096/1710 [09:28<05:23, 1.90it/s] 64%|██████▍ | 1097/1710 [09:29<04:57, 2.06it/s] 64%|██████▍ | 1098/1710 [09:30<06:33, 1.56it/s] 64%|██████▍ | 1099/1710 [09:30<05:41, 1.79it/s] 64%|██████▍ | 1100/1710 [09:31<05:33, 1.83it/s] 64%|██████▍ | 1101/1710 [09:31<05:38, 1.80it/s] 64%|██████▍ | 1102/1710 [09:32<05:19, 1.90it/s] 65%|██████▍ | 1103/1710 [09:32<04:44, 2.13it/s] 65%|██████▍ | 1104/1710 [09:32<04:31, 2.23it/s] 65%|██████▍ | 1105/1710 [09:33<04:31, 2.23it/s] 65%|██████▍ | 1106/1710 [09:33<04:24, 2.28it/s] 65%|██████▍ | 1107/1710 [09:34<04:28, 2.25it/s] 65%|██████▍ | 1108/1710 [09:34<04:13, 2.37it/s] 65%|██████▍ | 1109/1710 [09:35<04:31, 2.22it/s] 65%|██████▍ | 1110/1710 [09:35<04:38, 2.16it/s] 65%|██████▍ | 1111/1710 [09:36<05:03, 1.97it/s] 65%|██████▌ | 1112/1710 [09:36<05:04, 1.96it/s] 65%|██████▌ | 1113/1710 [09:37<04:49, 2.06it/s] 65%|██████▌ | 1114/1710 [09:37<04:18, 2.30it/s] 65%|██████▌ | 1115/1710 [09:37<04:20, 2.28it/s] 65%|██████▌ | 1116/1710 [09:38<04:15, 2.32it/s] 65%|██████▌ | 1117/1710 [09:38<04:12, 2.35it/s] 65%|██████▌ | 1118/1710 [09:39<04:17, 2.30it/s] 65%|██████▌ | 1119/1710 [09:39<04:29, 2.20it/s] 65%|██████▌ | 1120/1710 [09:40<04:28, 2.20it/s] 66%|██████▌ | 1121/1710 [09:40<04:45, 2.06it/s] 66%|██████▌ | 1122/1710 [09:41<04:44, 2.07it/s] 66%|██████▌ | 1123/1710 [09:41<04:30, 2.17it/s] 66%|██████▌ | 1124/1710 [09:42<04:18, 2.26it/s] 66%|██████▌ | 1125/1710 [09:42<04:41, 2.07it/s] 66%|██████▌ | 1126/1710 [09:43<04:29, 2.16it/s] 66%|██████▌ | 1127/1710 [09:43<04:21, 2.23it/s] 66%|██████▌ | 1128/1710 [09:43<04:41, 2.07it/s] 66%|██████▌ | 1129/1710 [09:44<04:42, 2.06it/s] 66%|██████▌ | 1130/1710 [09:44<04:21, 2.22it/s] 66%|██████▌ | 1131/1710 [09:45<04:12, 2.29it/s] 66%|██████▌ | 1132/1710 [09:45<04:42, 2.05it/s] 66%|██████▋ | 1133/1710 [09:46<04:31, 2.12it/s] 66%|██████▋ | 1134/1710 [09:46<04:02, 2.37it/s] 66%|██████▋ | 1135/1710 [09:47<04:03, 2.36it/s] 66%|██████▋ | 1136/1710 [09:47<03:54, 2.45it/s] 66%|██████▋ | 1137/1710 [09:48<05:01, 1.90it/s] 67%|██████▋ | 1138/1710 [09:48<04:45, 2.01it/s] 67%|██████▋ | 1139/1710 [09:49<04:49, 1.97it/s] 67%|██████▋ | 1140/1710 [09:49<04:36, 2.06it/s] 67%|██████▋ | 1141/1710 [09:49<04:15, 2.23it/s] 67%|██████▋ | 1142/1710 [09:50<04:12, 2.25it/s] 67%|██████▋ | 1143/1710 [09:50<04:04, 2.32it/s] 67%|██████▋ | 1144/1710 [09:51<04:03, 2.33it/s] 67%|██████▋ | 1145/1710 [09:51<03:47, 2.48it/s] 67%|██████▋ | 1146/1710 [09:51<03:48, 2.47it/s] 67%|██████▋ | 1147/1710 [09:52<03:51, 2.43it/s] 67%|██████▋ | 1148/1710 [09:52<04:10, 2.25it/s] 67%|██████▋ | 1149/1710 [09:53<04:03, 2.30it/s] 67%|██████▋ | 1150/1710 [09:53<03:52, 2.41it/s] 67%|██████▋ | 1151/1710 [09:54<03:53, 2.40it/s] 67%|██████▋ | 1152/1710 [09:54<04:14, 2.19it/s] 67%|██████▋ | 1153/1710 [09:55<04:16, 2.17it/s] 67%|██████▋ | 1154/1710 [09:55<04:38, 1.99it/s] 68%|██████▊ | 1155/1710 [09:56<04:29, 2.06it/s] 68%|██████▊ | 1156/1710 [09:56<04:20, 2.13it/s] 68%|██████▊ | 1157/1710 [09:57<04:09, 2.22it/s] 68%|██████▊ | 1158/1710 [09:57<04:18, 2.13it/s] 68%|██████▊ | 1159/1710 [09:57<04:10, 2.20it/s] 68%|██████▊ | 1160/1710 [09:58<04:29, 2.04it/s] 68%|██████▊ | 1161/1710 [09:59<05:03, 1.81it/s] 68%|██████▊ | 1162/1710 [09:59<04:31, 2.02it/s] 68%|██████▊ | 1163/1710 [10:00<04:23, 2.07it/s] 68%|██████▊ | 1164/1710 [10:00<04:11, 2.17it/s] 68%|██████▊ | 1165/1710 [10:00<03:45, 2.42it/s] 68%|██████▊ | 1166/1710 [10:01<03:48, 2.38it/s] 68%|██████▊ | 1167/1710 [10:01<04:29, 2.01it/s] 68%|██████▊ | 1168/1710 [10:02<05:20, 1.69it/s] 68%|██████▊ | 1169/1710 [10:03<04:50, 1.86it/s] 68%|██████▊ | 1170/1710 [10:03<04:29, 2.01it/s] 68%|██████▊ | 1171/1710 [10:03<04:15, 2.11it/s] 69%|██████▊ | 1172/1710 [10:04<04:12, 2.13it/s] 69%|██████▊ | 1173/1710 [10:04<04:26, 2.02it/s] 69%|██████▊ | 1174/1710 [10:05<04:57, 1.80it/s] 69%|██████▊ | 1175/1710 [10:06<05:18, 1.68it/s] 69%|██████▉ | 1176/1710 [10:06<04:45, 1.87it/s] 69%|██████▉ | 1177/1710 [10:07<04:22, 2.03it/s] 69%|██████▉ | 1178/1710 [10:07<04:10, 2.13it/s] 69%|██████▉ | 1179/1710 [10:08<04:16, 2.07it/s] 69%|██████▉ | 1180/1710 [10:08<03:59, 2.22it/s] 69%|██████▉ | 1181/1710 [10:08<03:46, 2.34it/s] 69%|██████▉ | 1182/1710 [10:09<03:45, 2.34it/s] 69%|██████▉ | 1183/1710 [10:09<03:46, 2.33it/s] 69%|██████▉ | 1184/1710 [10:10<03:36, 2.43it/s] 69%|██████▉ | 1185/1710 [10:10<03:53, 2.24it/s] 69%|██████▉ | 1186/1710 [10:10<03:48, 2.29it/s] 69%|██████▉ | 1187/1710 [10:11<04:04, 2.14it/s] 69%|██████▉ | 1188/1710 [10:12<04:12, 2.07it/s] 70%|██████▉ | 1189/1710 [10:12<03:57, 2.20it/s] 70%|██████▉ | 1190/1710 [10:12<03:51, 2.24it/s] 70%|██████▉ | 1191/1710 [10:13<03:57, 2.18it/s] 70%|██████▉ | 1192/1710 [10:13<03:55, 2.20it/s] 70%|██████▉ | 1193/1710 [10:14<03:55, 2.19it/s] 70%|██████▉ | 1194/1710 [10:14<03:50, 2.23it/s] 70%|██████▉ | 1195/1710 [10:15<03:40, 2.33it/s] 70%|██████▉ | 1196/1710 [10:15<03:29, 2.45it/s] 70%|███████ | 1197/1710 [10:15<03:20, 2.56it/s][INFO|trainer.py:811] 2024-09-09 12:25:11,389 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: ner_tags, id, tokens. If ner_tags, id, tokens are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. | |
| [INFO|trainer.py:3819] 2024-09-09 12:25:11,391 >> | |
| ***** Running Evaluation ***** | |
| [INFO|trainer.py:3821] 2024-09-09 12:25:11,392 >> Num examples = 2519 | |
| [INFO|trainer.py:3824] 2024-09-09 12:25:11,392 >> Batch size = 8 | |
| {'eval_loss': 0.24975360929965973, 'eval_precision': 0.6461383139828369, 'eval_recall': 0.7006020799124247, 'eval_f1': 0.6722689075630252, 'eval_accuracy': 0.9469825788443645, 'eval_runtime': 5.9627, 'eval_samples_per_second': 422.461, 'eval_steps_per_second': 52.829, 'epoch': 6.0} | |
| 0%| | 0/315 [00:00<?, ?it/s][A | |
| 3%|▎ | 8/315 [00:00<00:03, 78.25it/s][A | |
| 5%|▌ | 16/315 [00:00<00:03, 75.52it/s][A | |
| 8%|▊ | 24/315 [00:00<00:03, 77.00it/s][A | |
| 10%|█ | 32/315 [00:00<00:03, 72.63it/s][A | |
| 13%|█▎ | 41/315 [00:00<00:03, 75.89it/s][A | |
| 16%|█▌ | 49/315 [00:00<00:03, 75.18it/s][A | |
| 18%|█▊ | 57/315 [00:00<00:03, 75.40it/s][A | |
| 21%|██ | 65/315 [00:00<00:03, 72.21it/s][A | |
| 23%|██▎ | 73/315 [00:00<00:03, 74.33it/s][A | |
| 26%|██▌ | 81/315 [00:01<00:03, 70.75it/s][A | |
| 28%|██▊ | 89/315 [00:01<00:03, 67.39it/s][A | |
| 31%|███ | 97/315 [00:01<00:03, 67.28it/s][A | |
| 33%|███▎ | 105/315 [00:01<00:03, 68.96it/s][A | |
| 36%|███▌ | 113/315 [00:01<00:02, 70.65it/s][A | |
| 38%|███▊ | 121/315 [00:01<00:02, 69.24it/s][A | |
| 41%|████ | 129/315 [00:01<00:02, 70.23it/s][A | |
| 43%|████▎ | 137/315 [00:01<00:02, 69.65it/s][A | |
| 46%|████▌ | 144/315 [00:02<00:02, 69.41it/s][A | |
| 49%|████▊ | 153/315 [00:02<00:02, 73.45it/s][A | |
| 51%|█████ | 161/315 [00:02<00:02, 72.05it/s][A | |
| 54%|█████▎ | 169/315 [00:02<00:02, 71.92it/s][A | |
| 56%|█████▌ | 177/315 [00:02<00:01, 71.59it/s][A | |
| 59%|█████▊ | 185/315 [00:02<00:01, 69.29it/s][A | |
| 61%|██████ | 192/315 [00:02<00:01, 68.95it/s][A | |
| 63%|██████▎ | 199/315 [00:02<00:01, 66.07it/s][A | |
| 65%|██████▌ | 206/315 [00:02<00:01, 64.74it/s][A | |
| 68%|██████▊ | 214/315 [00:03<00:01, 68.47it/s][A | |
| 70%|███████ | 222/315 [00:03<00:01, 70.45it/s][A | |
| 73%|███████▎ | 231/315 [00:03<00:01, 73.74it/s][A | |
| 76%|███████▌ | 239/315 [00:03<00:01, 75.02it/s][A | |
| 78%|███████▊ | 247/315 [00:03<00:00, 70.37it/s][A | |
| 81%|████████ | 255/315 [00:03<00:00, 69.03it/s][A | |
| 83%|████████▎ | 263/315 [00:03<00:00, 70.69it/s][A | |
| 86%|████████▌ | 271/315 [00:03<00:00, 72.53it/s][A | |
| 89%|████████▉ | 280/315 [00:03<00:00, 75.54it/s][A | |
| 91%|█████████▏| 288/315 [00:04<00:00, 72.37it/s][A | |
| 94%|█████████▍| 296/315 [00:04<00:00, 70.67it/s][A | |
| 97%|█████████▋| 304/315 [00:04<00:00, 71.86it/s][A | |
| 99%|█████████▉| 312/315 [00:04<00:00, 72.00it/s][A | |
| [A 70%|███████ | 1197/1710 [10:21<03:20, 2.56it/s] | |
| 100%|██████████| 315/315 [00:05<00:00, 72.00it/s][A | |
| [A[INFO|trainer.py:3503] 2024-09-09 12:25:17,290 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-1197 | |
| [INFO|configuration_utils.py:472] 2024-09-09 12:25:17,291 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-1197/config.json | |
| [INFO|modeling_utils.py:2799] 2024-09-09 12:25:18,342 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-1197/model.safetensors | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:25:18,343 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-1197/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:25:18,343 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-1197/special_tokens_map.json | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:25:23,192 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:25:23,192 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json | |
| 70%|███████ | 1198/1710 [10:28<34:36, 4.06s/it] 70%|███████ | 1199/1710 [10:28<25:27, 2.99s/it] 70%|███████ | 1200/1710 [10:29<18:46, 2.21s/it] 70%|███████ | 1201/1710 [10:29<14:22, 1.69s/it] 70%|███████ | 1202/1710 [10:30<11:19, 1.34s/it] 70%|███████ | 1203/1710 [10:30<09:48, 1.16s/it] 70%|███████ | 1204/1710 [10:31<07:49, 1.08it/s] 70%|███████ | 1205/1710 [10:31<06:28, 1.30it/s] 71%|███████ | 1206/1710 [10:32<05:30, 1.53it/s] 71%|███████ | 1207/1710 [10:32<04:58, 1.69it/s] 71%|███████ | 1208/1710 [10:33<04:29, 1.86it/s] 71%|███████ | 1209/1710 [10:33<03:58, 2.10it/s] 71%|███████ | 1210/1710 [10:34<04:30, 1.85it/s] 71%|███████ | 1211/1710 [10:34<04:30, 1.84it/s] 71%|███████ | 1212/1710 [10:35<04:14, 1.96it/s] 71%|███████ | 1213/1710 [10:35<03:54, 2.12it/s] 71%|███████ | 1214/1710 [10:35<03:33, 2.32it/s] 71%|███████ | 1215/1710 [10:36<03:30, 2.35it/s] 71%|███████ | 1216/1710 [10:36<03:18, 2.48it/s] 71%|███████ | 1217/1710 [10:36<03:23, 2.43it/s] 71%|███████ | 1218/1710 [10:37<03:20, 2.46it/s] 71%|███████▏ | 1219/1710 [10:37<03:11, 2.57it/s] 71%|███████▏ | 1220/1710 [10:38<03:19, 2.46it/s] 71%|███████▏ | 1221/1710 [10:38<03:47, 2.15it/s] 71%|███████▏ | 1222/1710 [10:39<03:42, 2.19it/s] 72%|███████▏ | 1223/1710 [10:39<03:37, 2.24it/s] 72%|███████▏ | 1224/1710 [10:40<04:36, 1.76it/s] 72%|███████▏ | 1225/1710 [10:41<04:44, 1.70it/s] 72%|███████▏ | 1226/1710 [10:41<04:11, 1.93it/s] 72%|███████▏ | 1227/1710 [10:41<04:07, 1.95it/s] 72%|███████▏ | 1228/1710 [10:42<03:48, 2.11it/s] 72%|███████▏ | 1229/1710 [10:42<03:47, 2.12it/s] 72%|███████▏ | 1230/1710 [10:43<03:40, 2.18it/s] 72%|███████▏ | 1231/1710 [10:43<03:35, 2.22it/s] 72%|███████▏ | 1232/1710 [10:44<03:55, 2.03it/s] 72%|███████▏ | 1233/1710 [10:44<03:41, 2.15it/s] 72%|███████▏ | 1234/1710 [10:45<03:56, 2.01it/s] 72%|███████▏ | 1235/1710 [10:45<03:45, 2.11it/s] 72%|███████▏ | 1236/1710 [10:46<03:47, 2.08it/s] 72%|███████▏ | 1237/1710 [10:46<03:33, 2.22it/s] 72%|███████▏ | 1238/1710 [10:46<03:14, 2.43it/s] 72%|███████▏ | 1239/1710 [10:47<03:12, 2.45it/s] 73%|███████▎ | 1240/1710 [10:47<03:16, 2.39it/s] 73%|███████▎ | 1241/1710 [10:48<03:14, 2.42it/s] 73%|███████▎ | 1242/1710 [10:48<03:04, 2.54it/s] 73%|███████▎ | 1243/1710 [10:48<03:08, 2.48it/s] 73%|███████▎ | 1244/1710 [10:49<03:16, 2.37it/s] 73%|███████▎ | 1245/1710 [10:49<03:35, 2.16it/s] 73%|███████▎ | 1246/1710 [10:50<03:33, 2.17it/s] 73%|███████▎ | 1247/1710 [10:50<03:31, 2.19it/s] 73%|███████▎ | 1248/1710 [10:51<03:20, 2.30it/s] 73%|███████▎ | 1249/1710 [10:51<03:06, 2.47it/s] 73%|███████▎ | 1250/1710 [10:52<03:21, 2.28it/s] 73%|███████▎ | 1251/1710 [10:52<03:47, 2.02it/s] 73%|███████▎ | 1252/1710 [10:53<03:43, 2.05it/s] 73%|███████▎ | 1253/1710 [10:53<03:34, 2.13it/s] 73%|███████▎ | 1254/1710 [10:53<03:23, 2.24it/s] 73%|███████▎ | 1255/1710 [10:54<03:18, 2.29it/s] 73%|███████▎ | 1256/1710 [10:54<03:43, 2.03it/s] 74%|███████▎ | 1257/1710 [10:55<03:44, 2.02it/s] 74%|███████▎ | 1258/1710 [10:55<03:28, 2.17it/s] 74%|███████▎ | 1259/1710 [10:56<03:36, 2.08it/s] 74%|███████▎ | 1260/1710 [10:56<03:41, 2.03it/s] 74%|███████▎ | 1261/1710 [10:57<03:42, 2.02it/s] 74%|███████▍ | 1262/1710 [10:57<03:43, 2.00it/s] 74%|███████▍ | 1263/1710 [10:58<03:36, 2.07it/s] 74%|███████▍ | 1264/1710 [10:58<03:20, 2.22it/s] 74%|███████▍ | 1265/1710 [10:59<03:15, 2.27it/s] 74%|███████▍ | 1266/1710 [11:00<04:15, 1.74it/s] 74%|███████▍ | 1267/1710 [11:00<03:44, 1.97it/s] 74%|███████▍ | 1268/1710 [11:00<03:25, 2.15it/s] 74%|███████▍ | 1269/1710 [11:01<03:19, 2.21it/s] 74%|███████▍ | 1270/1710 [11:01<03:33, 2.06it/s] 74%|███████▍ | 1271/1710 [11:02<03:16, 2.23it/s] 74%|███████▍ | 1272/1710 [11:02<03:21, 2.17it/s] 74%|███████▍ | 1273/1710 [11:03<03:22, 2.16it/s] 75%|███████▍ | 1274/1710 [11:03<03:18, 2.20it/s] 75%|███████▍ | 1275/1710 [11:04<03:33, 2.03it/s] 75%|███████▍ | 1276/1710 [11:04<03:24, 2.12it/s] 75%|███████▍ | 1277/1710 [11:05<03:39, 1.98it/s] 75%|███████▍ | 1278/1710 [11:05<04:03, 1.77it/s] 75%|███████▍ | 1279/1710 [11:06<03:33, 2.02it/s] 75%|███████▍ | 1280/1710 [11:06<03:45, 1.91it/s] 75%|███████▍ | 1281/1710 [11:07<03:38, 1.96it/s] 75%|███████▍ | 1282/1710 [11:07<03:26, 2.07it/s] 75%|███████▌ | 1283/1710 [11:08<03:24, 2.09it/s] 75%|███████▌ | 1284/1710 [11:08<03:06, 2.28it/s] 75%|███████▌ | 1285/1710 [11:08<03:07, 2.27it/s] 75%|███████▌ | 1286/1710 [11:09<03:02, 2.32it/s] 75%|███████▌ | 1287/1710 [11:09<03:18, 2.13it/s] 75%|███████▌ | 1288/1710 [11:10<03:08, 2.23it/s] 75%|███████▌ | 1289/1710 [11:10<03:10, 2.22it/s] 75%|███████▌ | 1290/1710 [11:11<02:57, 2.36it/s] 75%|███████▌ | 1291/1710 [11:11<02:49, 2.47it/s] 76%|███████▌ | 1292/1710 [11:11<02:44, 2.54it/s] 76%|███████▌ | 1293/1710 [11:12<02:53, 2.40it/s] 76%|███████▌ | 1294/1710 [11:12<02:59, 2.32it/s] 76%|███████▌ | 1295/1710 [11:13<02:57, 2.33it/s] 76%|███████▌ | 1296/1710 [11:13<03:00, 2.29it/s] 76%|███████▌ | 1297/1710 [11:13<02:55, 2.35it/s] 76%|███████▌ | 1298/1710 [11:14<02:49, 2.42it/s] 76%|███████▌ | 1299/1710 [11:14<02:43, 2.51it/s] 76%|███████▌ | 1300/1710 [11:15<02:40, 2.56it/s] 76%|███████▌ | 1301/1710 [11:15<02:41, 2.53it/s] 76%|███████▌ | 1302/1710 [11:16<03:00, 2.26it/s] 76%|███████▌ | 1303/1710 [11:16<02:59, 2.27it/s] 76%|███████▋ | 1304/1710 [11:16<02:55, 2.32it/s] 76%|███████▋ | 1305/1710 [11:17<03:11, 2.12it/s] 76%|███████▋ | 1306/1710 [11:18<03:20, 2.01it/s] 76%|███████▋ | 1307/1710 [11:18<03:08, 2.14it/s] 76%|███████▋ | 1308/1710 [11:18<03:01, 2.22it/s] 77%|███████▋ | 1309/1710 [11:19<02:57, 2.26it/s] 77%|███████▋ | 1310/1710 [11:19<02:58, 2.24it/s] 77%|███████▋ | 1311/1710 [11:20<02:55, 2.28it/s] 77%|███████▋ | 1312/1710 [11:20<03:02, 2.18it/s] 77%|███████▋ | 1313/1710 [11:21<02:56, 2.25it/s] 77%|███████▋ | 1314/1710 [11:21<02:48, 2.35it/s] 77%|███████▋ | 1315/1710 [11:21<02:49, 2.33it/s] 77%|███████▋ | 1316/1710 [11:22<02:36, 2.51it/s] 77%|███████▋ | 1317/1710 [11:22<02:36, 2.50it/s] 77%|███████▋ | 1318/1710 [11:23<02:49, 2.31it/s] 77%|███████▋ | 1319/1710 [11:23<03:01, 2.15it/s] 77%|███████▋ | 1320/1710 [11:24<02:56, 2.21it/s] 77%|███████▋ | 1321/1710 [11:24<02:49, 2.30it/s] 77%|███████▋ | 1322/1710 [11:25<03:01, 2.13it/s] 77%|███████▋ | 1323/1710 [11:25<03:35, 1.80it/s] 77%|███████▋ | 1324/1710 [11:26<03:09, 2.04it/s] 77%|███████▋ | 1325/1710 [11:26<03:05, 2.07it/s] 78%|███████▊ | 1326/1710 [11:27<03:05, 2.07it/s] 78%|███████▊ | 1327/1710 [11:27<02:47, 2.29it/s] 78%|███████▊ | 1328/1710 [11:27<02:53, 2.20it/s] 78%|███████▊ | 1329/1710 [11:28<03:16, 1.94it/s] 78%|███████▊ | 1330/1710 [11:29<03:11, 1.99it/s] 78%|███████▊ | 1331/1710 [11:29<03:10, 1.99it/s] 78%|███████▊ | 1332/1710 [11:29<02:49, 2.23it/s] 78%|███████▊ | 1333/1710 [11:30<02:57, 2.13it/s] 78%|███████▊ | 1334/1710 [11:30<02:48, 2.23it/s] 78%|███████▊ | 1335/1710 [11:31<02:46, 2.26it/s] 78%|███████▊ | 1336/1710 [11:31<02:34, 2.43it/s] 78%|███████▊ | 1337/1710 [11:31<02:28, 2.52it/s] 78%|███████▊ | 1338/1710 [11:32<02:30, 2.47it/s] 78%|███████▊ | 1339/1710 [11:32<02:26, 2.53it/s] 78%|███████▊ | 1340/1710 [11:33<02:22, 2.60it/s] 78%|███████▊ | 1341/1710 [11:33<02:35, 2.37it/s] 78%|███████▊ | 1342/1710 [11:33<02:36, 2.35it/s] 79%|███████▊ | 1343/1710 [11:34<02:21, 2.60it/s] 79%|███████▊ | 1344/1710 [11:34<02:28, 2.46it/s] 79%|███████▊ | 1345/1710 [11:35<02:28, 2.45it/s] 79%|███████▊ | 1346/1710 [11:35<02:24, 2.52it/s] 79%|███████▉ | 1347/1710 [11:35<02:32, 2.37it/s] 79%|███████▉ | 1348/1710 [11:36<02:27, 2.45it/s] 79%|███████▉ | 1349/1710 [11:36<02:30, 2.39it/s] 79%|███████▉ | 1350/1710 [11:37<02:42, 2.22it/s] 79%|███████▉ | 1351/1710 [11:37<02:45, 2.16it/s] 79%|███████▉ | 1352/1710 [11:38<02:54, 2.05it/s] 79%|███████▉ | 1353/1710 [11:39<03:29, 1.70it/s] 79%|███████▉ | 1354/1710 [11:39<03:37, 1.63it/s] 79%|███████▉ | 1355/1710 [11:40<03:16, 1.80it/s] 79%|███████▉ | 1356/1710 [11:40<02:59, 1.98it/s] 79%|███████▉ | 1357/1710 [11:41<02:43, 2.16it/s] 79%|███████▉ | 1358/1710 [11:41<02:46, 2.12it/s] 79%|███████▉ | 1359/1710 [11:42<02:55, 2.00it/s] 80%|███████▉ | 1360/1710 [11:42<02:40, 2.18it/s] 80%|███████▉ | 1361/1710 [11:42<02:37, 2.22it/s] 80%|███████▉ | 1362/1710 [11:43<02:28, 2.35it/s] 80%|███████▉ | 1363/1710 [11:43<02:34, 2.24it/s] 80%|███████▉ | 1364/1710 [11:44<02:32, 2.27it/s] 80%|███████▉ | 1365/1710 [11:44<02:35, 2.23it/s] 80%|███████▉ | 1366/1710 [11:45<03:36, 1.59it/s] 80%|███████▉ | 1367/1710 [11:46<03:14, 1.76it/s] 80%|████████ | 1368/1710 [11:46<02:55, 1.95it/s][INFO|trainer.py:811] 2024-09-09 12:26:42,159 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: ner_tags, id, tokens. If ner_tags, id, tokens are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. | |
| [INFO|trainer.py:3819] 2024-09-09 12:26:42,162 >> | |
| ***** Running Evaluation ***** | |
| [INFO|trainer.py:3821] 2024-09-09 12:26:42,162 >> Num examples = 2519 | |
| [INFO|trainer.py:3824] 2024-09-09 12:26:42,162 >> Batch size = 8 | |
| {'eval_loss': 0.2653313875198364, 'eval_precision': 0.636231884057971, 'eval_recall': 0.7208538587848933, 'eval_f1': 0.6759045419553503, 'eval_accuracy': 0.9461804998556258, 'eval_runtime': 5.8972, 'eval_samples_per_second': 427.151, 'eval_steps_per_second': 53.415, 'epoch': 7.0} | |
| 0%| | 0/315 [00:00<?, ?it/s][A | |
| 3%|▎ | 8/315 [00:00<00:03, 78.29it/s][A | |
| 5%|▌ | 16/315 [00:00<00:03, 75.02it/s][A | |
| 8%|▊ | 24/315 [00:00<00:03, 76.45it/s][A | |
| 10%|█ | 32/315 [00:00<00:03, 71.97it/s][A | |
| 13%|█▎ | 41/315 [00:00<00:03, 75.79it/s][A | |
| 16%|█▌ | 49/315 [00:00<00:03, 75.07it/s][A | |
| 18%|█▊ | 57/315 [00:00<00:03, 75.43it/s][A | |
| 21%|██ | 65/315 [00:00<00:03, 72.50it/s][A | |
| 23%|██▎ | 73/315 [00:00<00:03, 74.63it/s][A | |
| 26%|██▌ | 81/315 [00:01<00:03, 70.79it/s][A | |
| 28%|██▊ | 89/315 [00:01<00:03, 67.40it/s][A | |
| 31%|███ | 97/315 [00:01<00:03, 67.18it/s][A | |
| 33%|███▎ | 104/315 [00:01<00:03, 67.92it/s][A | |
| 36%|███▌ | 112/315 [00:01<00:02, 69.60it/s][A | |
| 38%|███▊ | 120/315 [00:01<00:02, 69.34it/s][A | |
| 40%|████ | 127/315 [00:01<00:02, 69.05it/s][A | |
| 43%|████▎ | 134/315 [00:01<00:02, 68.57it/s][A | |
| 45%|████▍ | 141/315 [00:01<00:02, 68.63it/s][A | |
| 47%|████▋ | 149/315 [00:02<00:02, 71.03it/s][A | |
| 50%|████▉ | 157/315 [00:02<00:02, 73.48it/s][A | |
| 52%|█████▏ | 165/315 [00:02<00:02, 72.18it/s][A | |
| 55%|█████▍ | 173/315 [00:02<00:01, 71.55it/s][A | |
| 57%|█████▋ | 181/315 [00:02<00:01, 68.79it/s][A | |
| 60%|█████▉ | 188/315 [00:02<00:01, 69.11it/s][A | |
| 62%|██████▏ | 195/315 [00:02<00:01, 67.25it/s][A | |
| 64%|██████▍ | 202/315 [00:02<00:01, 65.91it/s][A | |
| 66%|██████▋ | 209/315 [00:02<00:01, 65.27it/s][A | |
| 69%|██████▉ | 217/315 [00:03<00:01, 68.10it/s][A | |
| 71%|███████▏ | 225/315 [00:03<00:01, 70.76it/s][A | |
| 74%|███████▍ | 234/315 [00:03<00:01, 74.22it/s][A | |
| 77%|███████▋ | 242/315 [00:03<00:01, 71.48it/s][A | |
| 79%|███████▉ | 250/315 [00:03<00:00, 71.21it/s][A | |
| 82%|████████▏ | 258/315 [00:03<00:00, 68.93it/s][A | |
| 84%|████████▍ | 266/315 [00:03<00:00, 70.07it/s][A | |
| 87%|████████▋ | 275/315 [00:03<00:00, 73.61it/s][A | |
| 90%|████████▉ | 283/315 [00:03<00:00, 74.67it/s][A | |
| 92%|█████████▏| 291/315 [00:04<00:00, 72.08it/s][A | |
| 95%|█████████▍| 299/315 [00:04<00:00, 70.98it/s][A | |
| 97%|█████████▋| 307/315 [00:04<00:00, 71.83it/s][A | |
| 100%|██████████| 315/315 [00:04<00:00, 70.52it/s][A | |
| [A 80%|████████ | 1368/1710 [11:52<02:55, 1.95it/s] | |
| 100%|██████████| 315/315 [00:05<00:00, 70.52it/s][A | |
| [A[INFO|trainer.py:3503] 2024-09-09 12:26:48,070 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-1368 | |
| [INFO|configuration_utils.py:472] 2024-09-09 12:26:48,072 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-1368/config.json | |
| [INFO|modeling_utils.py:2799] 2024-09-09 12:26:49,101 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-1368/model.safetensors | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:26:49,102 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-1368/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:26:49,103 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-1368/special_tokens_map.json | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:26:52,194 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:26:52,195 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json | |
| 80%|████████ | 1369/1710 [11:56<19:51, 3.49s/it] 80%|████████ | 1370/1710 [11:57<14:28, 2.56s/it] 80%|████████ | 1371/1710 [11:57<11:06, 1.97s/it] 80%|████████ | 1372/1710 [11:58<08:31, 1.51s/it] 80%|████████ | 1373/1710 [11:59<07:28, 1.33s/it] 80%|████████ | 1374/1710 [11:59<05:54, 1.06s/it] 80%|████████ | 1375/1710 [12:00<04:53, 1.14it/s] 80%|████████ | 1376/1710 [12:00<04:04, 1.37it/s] 81%|████████ | 1377/1710 [12:00<03:26, 1.61it/s] 81%|████████ | 1378/1710 [12:01<02:59, 1.85it/s] 81%|████████ | 1379/1710 [12:01<02:45, 2.00it/s] 81%|████████ | 1380/1710 [12:02<02:33, 2.15it/s] 81%|████████ | 1381/1710 [12:02<02:32, 2.16it/s] 81%|████████ | 1382/1710 [12:03<02:40, 2.05it/s] 81%|████████ | 1383/1710 [12:03<02:37, 2.08it/s] 81%|████████ | 1384/1710 [12:04<02:38, 2.06it/s] 81%|████████ | 1385/1710 [12:04<02:31, 2.14it/s] 81%|████████ | 1386/1710 [12:04<02:37, 2.06it/s] 81%|████████ | 1387/1710 [12:05<02:28, 2.18it/s] 81%|████████ | 1388/1710 [12:05<02:26, 2.20it/s] 81%|████████ | 1389/1710 [12:06<02:26, 2.19it/s] 81%|████████▏ | 1390/1710 [12:06<02:17, 2.32it/s] 81%|████████▏ | 1391/1710 [12:07<02:20, 2.27it/s] 81%|████████▏ | 1392/1710 [12:07<02:18, 2.30it/s] 81%|████████▏ | 1393/1710 [12:07<02:16, 2.32it/s] 82%|████████▏ | 1394/1710 [12:08<02:18, 2.28it/s] 82%|████████▏ | 1395/1710 [12:08<02:13, 2.36it/s] 82%|████████▏ | 1396/1710 [12:09<02:16, 2.29it/s] 82%|████████▏ | 1397/1710 [12:09<02:42, 1.93it/s] 82%|████████▏ | 1398/1710 [12:10<02:31, 2.06it/s] 82%|████████▏ | 1399/1710 [12:11<02:50, 1.82it/s] 82%|████████▏ | 1400/1710 [12:11<02:38, 1.96it/s] 82%|████████▏ | 1401/1710 [12:11<02:22, 2.16it/s] 82%|████████▏ | 1402/1710 [12:12<02:24, 2.13it/s] 82%|████████▏ | 1403/1710 [12:12<02:20, 2.18it/s] 82%|████████▏ | 1404/1710 [12:13<02:21, 2.16it/s] 82%|████████▏ | 1405/1710 [12:13<02:30, 2.03it/s] 82%|████████▏ | 1406/1710 [12:14<02:24, 2.10it/s] 82%|████████▏ | 1407/1710 [12:15<02:52, 1.76it/s] 82%|████████▏ | 1408/1710 [12:16<03:35, 1.40it/s] 82%|████████▏ | 1409/1710 [12:16<03:47, 1.32it/s] 82%|████████▏ | 1410/1710 [12:17<03:23, 1.48it/s] 83%|████████▎ | 1411/1710 [12:17<02:55, 1.71it/s] 83%|████████▎ | 1412/1710 [12:18<02:33, 1.94it/s] 83%|████████▎ | 1413/1710 [12:18<02:23, 2.08it/s] 83%|████████▎ | 1414/1710 [12:18<02:17, 2.16it/s] 83%|████████▎ | 1415/1710 [12:19<02:15, 2.17it/s] 83%|████████▎ | 1416/1710 [12:19<02:07, 2.30it/s] 83%|████████▎ | 1417/1710 [12:20<01:57, 2.49it/s] 83%|████████▎ | 1418/1710 [12:20<01:58, 2.46it/s] 83%|████████▎ | 1419/1710 [12:20<01:54, 2.54it/s] 83%|████████▎ | 1420/1710 [12:21<02:08, 2.26it/s] 83%|████████▎ | 1421/1710 [12:21<02:10, 2.21it/s] 83%|████████▎ | 1422/1710 [12:22<02:06, 2.27it/s] 83%|████████▎ | 1423/1710 [12:22<01:59, 2.41it/s] 83%|████████▎ | 1424/1710 [12:23<02:01, 2.36it/s] 83%|████████▎ | 1425/1710 [12:23<01:57, 2.43it/s] 83%|████████▎ | 1426/1710 [12:24<02:04, 2.29it/s] 83%|████████▎ | 1427/1710 [12:24<02:07, 2.23it/s] 84%|████████▎ | 1428/1710 [12:24<01:56, 2.42it/s] 84%|████████▎ | 1429/1710 [12:25<02:06, 2.23it/s] 84%|████████▎ | 1430/1710 [12:25<02:16, 2.05it/s] 84%|████████▎ | 1431/1710 [12:26<02:13, 2.10it/s] 84%|████████▎ | 1432/1710 [12:26<02:07, 2.18it/s] 84%|████████▍ | 1433/1710 [12:27<01:57, 2.35it/s] 84%|████████▍ | 1434/1710 [12:27<02:11, 2.10it/s] 84%|████████▍ | 1435/1710 [12:28<02:07, 2.16it/s] 84%|████████▍ | 1436/1710 [12:28<02:02, 2.24it/s] 84%|████████▍ | 1437/1710 [12:28<01:56, 2.35it/s] 84%|████████▍ | 1438/1710 [12:29<01:52, 2.43it/s] 84%|████████▍ | 1439/1710 [12:29<01:56, 2.33it/s] 84%|████████▍ | 1440/1710 [12:30<02:07, 2.11it/s] 84%|████████▍ | 1441/1710 [12:30<02:08, 2.09it/s] 84%|████████▍ | 1442/1710 [12:31<02:10, 2.06it/s] 84%|████████▍ | 1443/1710 [12:31<02:04, 2.15it/s] 84%|████████▍ | 1444/1710 [12:32<01:54, 2.31it/s] 85%|████████▍ | 1445/1710 [12:32<01:48, 2.45it/s] 85%|████████▍ | 1446/1710 [12:33<01:57, 2.24it/s] 85%|████████▍ | 1447/1710 [12:33<01:56, 2.25it/s] 85%|████████▍ | 1448/1710 [12:33<01:47, 2.44it/s] 85%|████████▍ | 1449/1710 [12:34<01:46, 2.46it/s] 85%|████████▍ | 1450/1710 [12:34<01:52, 2.31it/s] 85%|████████▍ | 1451/1710 [12:35<02:04, 2.09it/s] 85%|████████▍ | 1452/1710 [12:35<02:05, 2.06it/s] 85%|████████▍ | 1453/1710 [12:36<02:00, 2.12it/s] 85%|████████▌ | 1454/1710 [12:36<01:53, 2.26it/s] 85%|████████▌ | 1455/1710 [12:37<01:51, 2.28it/s] 85%|████████▌ | 1456/1710 [12:37<01:45, 2.41it/s] 85%|████████▌ | 1457/1710 [12:37<01:47, 2.36it/s] 85%|████████▌ | 1458/1710 [12:38<01:44, 2.41it/s] 85%|████████▌ | 1459/1710 [12:38<01:47, 2.33it/s] 85%|████████▌ | 1460/1710 [12:39<01:46, 2.34it/s] 85%|████████▌ | 1461/1710 [12:39<01:53, 2.19it/s] 85%|████████▌ | 1462/1710 [12:40<02:08, 1.94it/s] 86%|████████▌ | 1463/1710 [12:40<01:57, 2.10it/s] 86%|████████▌ | 1464/1710 [12:41<01:51, 2.21it/s] 86%|████████▌ | 1465/1710 [12:41<01:52, 2.18it/s] 86%|████████▌ | 1466/1710 [12:41<01:46, 2.28it/s] 86%|████████▌ | 1467/1710 [12:42<01:45, 2.30it/s] 86%|████████▌ | 1468/1710 [12:42<01:41, 2.38it/s] 86%|████████▌ | 1469/1710 [12:43<01:59, 2.02it/s] 86%|████████▌ | 1470/1710 [12:44<02:15, 1.77it/s] 86%|████████▌ | 1471/1710 [12:44<02:11, 1.82it/s] 86%|████████▌ | 1472/1710 [12:45<02:07, 1.86it/s] 86%|████████▌ | 1473/1710 [12:45<02:00, 1.96it/s] 86%|████████▌ | 1474/1710 [12:46<01:53, 2.09it/s] 86%|████████▋ | 1475/1710 [12:46<01:43, 2.28it/s] 86%|████████▋ | 1476/1710 [12:46<01:42, 2.29it/s] 86%|████████▋ | 1477/1710 [12:47<01:37, 2.38it/s] 86%|████████▋ | 1478/1710 [12:47<01:37, 2.38it/s] 86%|████████▋ | 1479/1710 [12:48<01:39, 2.32it/s] 87%|████████▋ | 1480/1710 [12:48<01:39, 2.30it/s] 87%|████████▋ | 1481/1710 [12:49<01:56, 1.97it/s] 87%|████████▋ | 1482/1710 [12:49<01:47, 2.12it/s] 87%|████████▋ | 1483/1710 [12:50<01:46, 2.13it/s] 87%|████████▋ | 1484/1710 [12:50<01:42, 2.21it/s] 87%|████████▋ | 1485/1710 [12:51<01:58, 1.89it/s] 87%|████████▋ | 1486/1710 [12:51<01:48, 2.07it/s] 87%|████████▋ | 1487/1710 [12:52<01:54, 1.96it/s] 87%|████████▋ | 1488/1710 [12:52<01:42, 2.16it/s] 87%|████████▋ | 1489/1710 [12:52<01:37, 2.28it/s] 87%|████████▋ | 1490/1710 [12:53<02:03, 1.79it/s] 87%|████████▋ | 1491/1710 [12:54<01:48, 2.02it/s] 87%|████████▋ | 1492/1710 [12:54<01:42, 2.13it/s] 87%|████████▋ | 1493/1710 [12:54<01:40, 2.15it/s] 87%|████████▋ | 1494/1710 [12:55<01:41, 2.13it/s] 87%|████████▋ | 1495/1710 [12:55<01:38, 2.19it/s] 87%|████████▋ | 1496/1710 [12:56<01:30, 2.37it/s] 88%|████████▊ | 1497/1710 [12:56<01:30, 2.35it/s] 88%|████████▊ | 1498/1710 [12:57<01:30, 2.35it/s] 88%|████████▊ | 1499/1710 [12:57<01:59, 1.77it/s] 88%|████████▊ | 1500/1710 [12:58<01:50, 1.90it/s] 88%|████████▊ | 1500/1710 [12:58<01:50, 1.90it/s] 88%|████████▊ | 1501/1710 [12:58<01:48, 1.92it/s] 88%|████████▊ | 1502/1710 [12:59<01:37, 2.13it/s] 88%|████████▊ | 1503/1710 [12:59<01:27, 2.37it/s] 88%|████████▊ | 1504/1710 [13:00<01:32, 2.24it/s] 88%|████████▊ | 1505/1710 [13:00<01:29, 2.29it/s] 88%|████████▊ | 1506/1710 [13:01<01:37, 2.09it/s] 88%|████████▊ | 1507/1710 [13:01<01:32, 2.20it/s] 88%|████████▊ | 1508/1710 [13:01<01:24, 2.39it/s] 88%|████████▊ | 1509/1710 [13:02<01:18, 2.57it/s] 88%|████████▊ | 1510/1710 [13:02<01:15, 2.64it/s] 88%|████████▊ | 1511/1710 [13:02<01:17, 2.58it/s] 88%|████████▊ | 1512/1710 [13:03<01:26, 2.29it/s] 88%|████████▊ | 1513/1710 [13:03<01:29, 2.21it/s] 89%|████████▊ | 1514/1710 [13:04<01:20, 2.43it/s] 89%|████████▊ | 1515/1710 [13:04<01:19, 2.47it/s] 89%|████████▊ | 1516/1710 [13:05<01:24, 2.30it/s] 89%|████████▊ | 1517/1710 [13:05<01:21, 2.37it/s] 89%|████████▉ | 1518/1710 [13:05<01:20, 2.40it/s] 89%|████████▉ | 1519/1710 [13:06<01:20, 2.36it/s] 89%|████████▉ | 1520/1710 [13:06<01:17, 2.46it/s] 89%|████████▉ | 1521/1710 [13:07<01:28, 2.13it/s] 89%|████████▉ | 1522/1710 [13:07<01:33, 2.01it/s] 89%|████████▉ | 1523/1710 [13:08<01:32, 2.01it/s] 89%|████████▉ | 1524/1710 [13:08<01:28, 2.10it/s] 89%|████████▉ | 1525/1710 [13:09<01:27, 2.11it/s] 89%|████████▉ | 1526/1710 [13:09<01:21, 2.25it/s] 89%|████████▉ | 1527/1710 [13:09<01:16, 2.38it/s] 89%|████████▉ | 1528/1710 [13:10<01:15, 2.41it/s] 89%|████████▉ | 1529/1710 [13:10<01:15, 2.39it/s] 89%|████████▉ | 1530/1710 [13:11<01:12, 2.47it/s] 90%|████████▉ | 1531/1710 [13:11<01:08, 2.61it/s] 90%|████████▉ | 1532/1710 [13:11<01:13, 2.42it/s] 90%|████████▉ | 1533/1710 [13:12<01:21, 2.17it/s] 90%|████████▉ | 1534/1710 [13:13<01:27, 2.02it/s] 90%|████████▉ | 1535/1710 [13:13<01:23, 2.11it/s] 90%|████████▉ | 1536/1710 [13:14<01:22, 2.11it/s] 90%|████████▉ | 1537/1710 [13:14<01:19, 2.18it/s] 90%|████████▉ | 1538/1710 [13:14<01:17, 2.23it/s] 90%|█████████ | 1539/1710 [13:15<01:15, 2.26it/s][INFO|trainer.py:811] 2024-09-09 12:28:10,968 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: ner_tags, id, tokens. If ner_tags, id, tokens are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. | |
| [INFO|trainer.py:3819] 2024-09-09 12:28:10,970 >> | |
| ***** Running Evaluation ***** | |
| [INFO|trainer.py:3821] 2024-09-09 12:28:10,970 >> Num examples = 2519 | |
| [INFO|trainer.py:3824] 2024-09-09 12:28:10,970 >> Batch size = 8 | |
| {'eval_loss': 0.28080618381500244, 'eval_precision': 0.6529382219989954, 'eval_recall': 0.7115489874110563, 'eval_f1': 0.680984808800419, 'eval_accuracy': 0.9473354935994097, 'eval_runtime': 5.9073, 'eval_samples_per_second': 426.421, 'eval_steps_per_second': 53.324, 'epoch': 8.0} | |
| {'loss': 0.0082, 'grad_norm': 0.22467799484729767, 'learning_rate': 6.140350877192982e-06, 'epoch': 8.77} | |
| 0%| | 0/315 [00:00<?, ?it/s][A | |
| 3%|▎ | 8/315 [00:00<00:03, 78.15it/s][A | |
| 5%|▌ | 16/315 [00:00<00:03, 75.10it/s][A | |
| 8%|▊ | 24/315 [00:00<00:03, 76.23it/s][A | |
| 10%|█ | 32/315 [00:00<00:03, 72.03it/s][A | |
| 13%|█▎ | 41/315 [00:00<00:03, 75.31it/s][A | |
| 16%|█▌ | 49/315 [00:00<00:03, 74.22it/s][A | |
| 18%|█▊ | 57/315 [00:00<00:03, 74.53it/s][A | |
| 21%|██ | 65/315 [00:00<00:03, 71.62it/s][A | |
| 23%|██▎ | 73/315 [00:00<00:03, 73.27it/s][A | |
| 26%|██▌ | 81/315 [00:01<00:03, 69.11it/s][A | |
| 28%|██▊ | 88/315 [00:01<00:03, 66.88it/s][A | |
| 30%|███ | 96/315 [00:01<00:03, 70.07it/s][A | |
| 33%|███▎ | 104/315 [00:01<00:03, 67.39it/s][A | |
| 36%|███▌ | 112/315 [00:01<00:02, 69.18it/s][A | |
| 38%|███▊ | 120/315 [00:01<00:02, 68.81it/s][A | |
| 40%|████ | 127/315 [00:01<00:02, 68.85it/s][A | |
| 43%|████▎ | 134/315 [00:01<00:02, 68.15it/s][A | |
| 45%|████▍ | 141/315 [00:01<00:02, 68.66it/s][A | |
| 47%|████▋ | 149/315 [00:02<00:02, 71.11it/s][A | |
| 50%|████▉ | 157/315 [00:02<00:02, 73.67it/s][A | |
| 52%|█████▏ | 165/315 [00:02<00:02, 72.41it/s][A | |
| 55%|█████▍ | 173/315 [00:02<00:01, 71.77it/s][A | |
| 57%|█████▋ | 181/315 [00:02<00:01, 69.01it/s][A | |
| 60%|██████ | 189/315 [00:02<00:01, 68.89it/s][A | |
| 62%|██████▏ | 196/315 [00:02<00:01, 67.87it/s][A | |
| 64%|██████▍ | 203/315 [00:02<00:01, 65.16it/s][A | |
| 67%|██████▋ | 210/315 [00:03<00:01, 65.43it/s][A | |
| 69%|██████▉ | 218/315 [00:03<00:01, 69.24it/s][A | |
| 72%|███████▏ | 226/315 [00:03<00:01, 71.30it/s][A | |
| 75%|███████▍ | 235/315 [00:03<00:01, 74.27it/s][A | |
| 77%|███████▋ | 243/315 [00:03<00:01, 70.36it/s][A | |
| 80%|███████▉ | 251/315 [00:03<00:00, 70.27it/s][A | |
| 82%|████████▏ | 259/315 [00:03<00:00, 69.06it/s][A | |
| 85%|████████▍ | 267/315 [00:03<00:00, 70.31it/s][A | |
| 88%|████████▊ | 276/315 [00:03<00:00, 73.18it/s][A | |
| 90%|█████████ | 284/315 [00:04<00:00, 73.60it/s][A | |
| 93%|█████████▎| 292/315 [00:04<00:00, 70.96it/s][A | |
| 95%|█████████▌| 300/315 [00:04<00:00, 70.32it/s][A | |
| 98%|█████████▊| 308/315 [00:04<00:00, 70.86it/s][A | |
| [A 90%|█████████ | 1539/1710 [13:21<01:15, 2.26it/s] | |
| 100%|██████████| 315/315 [00:05<00:00, 70.86it/s][A | |
| [A[INFO|trainer.py:3503] 2024-09-09 12:28:16,907 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-1539 | |
| [INFO|configuration_utils.py:472] 2024-09-09 12:28:16,908 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-1539/config.json | |
| [INFO|modeling_utils.py:2799] 2024-09-09 12:28:17,937 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-1539/model.safetensors | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:28:17,938 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-1539/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:28:17,939 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-1539/special_tokens_map.json | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:28:22,554 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:28:22,555 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json | |
| 90%|█████████ | 1540/1710 [13:27<11:03, 3.90s/it] 90%|█████████ | 1541/1710 [13:27<08:00, 2.85s/it] 90%|█████████ | 1542/1710 [13:28<05:53, 2.11s/it] 90%|█████████ | 1543/1710 [13:28<04:32, 1.63s/it] 90%|█████████ | 1544/1710 [13:29<03:37, 1.31s/it] 90%|█████████ | 1545/1710 [13:29<02:50, 1.03s/it] 90%|█████████ | 1546/1710 [13:29<02:18, 1.18it/s] 90%|█████████ | 1547/1710 [13:30<01:55, 1.41it/s] 91%|█████████ | 1548/1710 [13:30<01:37, 1.66it/s] 91%|█████████ | 1549/1710 [13:31<01:27, 1.84it/s] 91%|█████████ | 1550/1710 [13:31<01:19, 2.01it/s] 91%|█████████ | 1551/1710 [13:32<01:31, 1.74it/s] 91%|█████████ | 1552/1710 [13:32<01:23, 1.90it/s] 91%|█████████ | 1553/1710 [13:33<01:15, 2.09it/s] 91%|█████████ | 1554/1710 [13:33<01:17, 2.00it/s] 91%|█████████ | 1555/1710 [13:34<01:16, 2.02it/s] 91%|█████████ | 1556/1710 [13:34<01:12, 2.13it/s] 91%|█████████ | 1557/1710 [13:34<01:10, 2.17it/s] 91%|█████████ | 1558/1710 [13:35<01:05, 2.31it/s] 91%|█████████ | 1559/1710 [13:35<01:05, 2.29it/s] 91%|█████████ | 1560/1710 [13:36<01:04, 2.34it/s] 91%|█████████▏| 1561/1710 [13:36<01:03, 2.35it/s] 91%|█████████▏| 1562/1710 [13:36<01:00, 2.44it/s] 91%|█████████▏| 1563/1710 [13:37<00:58, 2.50it/s] 91%|█████████▏| 1564/1710 [13:37<00:58, 2.52it/s] 92%|█████████▏| 1565/1710 [13:38<00:59, 2.44it/s] 92%|█████████▏| 1566/1710 [13:38<00:56, 2.55it/s] 92%|█████████▏| 1567/1710 [13:39<01:06, 2.14it/s] 92%|█████████▏| 1568/1710 [13:40<01:28, 1.60it/s] 92%|█████████▏| 1569/1710 [13:40<01:26, 1.63it/s] 92%|█████████▏| 1570/1710 [13:41<01:13, 1.90it/s] 92%|█████████▏| 1571/1710 [13:41<01:04, 2.16it/s] 92%|█████████▏| 1572/1710 [13:42<01:26, 1.60it/s] 92%|█████████▏| 1573/1710 [13:42<01:13, 1.86it/s] 92%|█████████▏| 1574/1710 [13:43<01:08, 1.99it/s] 92%|█████████▏| 1575/1710 [13:43<01:04, 2.09it/s] 92%|█████████▏| 1576/1710 [13:43<01:03, 2.13it/s] 92%|█████████▏| 1577/1710 [13:44<00:57, 2.32it/s] 92%|█████████▏| 1578/1710 [13:44<00:53, 2.45it/s] 92%|█████████▏| 1579/1710 [13:45<00:55, 2.34it/s] 92%|█████████▏| 1580/1710 [13:45<00:55, 2.33it/s] 92%|█████████▏| 1581/1710 [13:45<00:55, 2.32it/s] 93%|█████████▎| 1582/1710 [13:46<00:54, 2.36it/s] 93%|█████████▎| 1583/1710 [13:46<00:54, 2.34it/s] 93%|█████████▎| 1584/1710 [13:47<00:54, 2.33it/s] 93%|█████████▎| 1585/1710 [13:47<01:01, 2.03it/s] 93%|█████████▎| 1586/1710 [13:48<00:58, 2.12it/s] 93%|█████████▎| 1587/1710 [13:48<00:54, 2.27it/s] 93%|█████████▎| 1588/1710 [13:49<00:54, 2.25it/s] 93%|█████████▎| 1589/1710 [13:49<01:01, 1.98it/s] 93%|█████████▎| 1590/1710 [13:50<01:04, 1.86it/s] 93%|█████████▎| 1591/1710 [13:50<01:02, 1.91it/s] 93%|█████████▎| 1592/1710 [13:51<00:56, 2.11it/s] 93%|█████████▎| 1593/1710 [13:51<00:53, 2.18it/s] 93%|█████████▎| 1594/1710 [13:52<00:53, 2.18it/s] 93%|█████████▎| 1595/1710 [13:52<01:02, 1.84it/s] 93%|█████████▎| 1596/1710 [13:53<00:57, 1.99it/s] 93%|█████████▎| 1597/1710 [13:53<00:54, 2.07it/s] 93%|█████████▎| 1598/1710 [13:54<00:52, 2.13it/s] 94%|█████████▎| 1599/1710 [13:54<00:49, 2.25it/s] 94%|█████████▎| 1600/1710 [13:55<00:54, 2.03it/s] 94%|█████████▎| 1601/1710 [13:55<00:59, 1.84it/s] 94%|█████████▎| 1602/1710 [13:56<00:57, 1.87it/s] 94%|█████████▎| 1603/1710 [13:56<00:53, 2.00it/s] 94%|█████████▍| 1604/1710 [13:57<00:50, 2.11it/s] 94%|█████████▍| 1605/1710 [13:57<00:50, 2.07it/s] 94%|█████████▍| 1606/1710 [13:58<00:48, 2.16it/s] 94%|█████████▍| 1607/1710 [13:58<00:52, 1.97it/s] 94%|█████████▍| 1608/1710 [13:59<00:52, 1.94it/s] 94%|█████████▍| 1609/1710 [13:59<00:47, 2.13it/s] 94%|█████████▍| 1610/1710 [14:00<00:50, 2.00it/s] 94%|█████████▍| 1611/1710 [14:00<00:51, 1.93it/s] 94%|█████████▍| 1612/1710 [14:01<00:46, 2.09it/s] 94%|█████████▍| 1613/1710 [14:01<00:48, 2.01it/s] 94%|█████████▍| 1614/1710 [14:02<00:46, 2.08it/s] 94%|█████████▍| 1615/1710 [14:02<00:45, 2.08it/s] 95%|█████████▍| 1616/1710 [14:02<00:42, 2.22it/s] 95%|█████████▍| 1617/1710 [14:03<00:42, 2.19it/s] 95%|█████████▍| 1618/1710 [14:03<00:42, 2.18it/s] 95%|█████████▍| 1619/1710 [14:04<00:40, 2.22it/s] 95%|█████████▍| 1620/1710 [14:04<00:41, 2.17it/s] 95%|█████████▍| 1621/1710 [14:05<00:37, 2.39it/s] 95%|█████████▍| 1622/1710 [14:05<00:36, 2.38it/s] 95%|█████████▍| 1623/1710 [14:05<00:36, 2.36it/s] 95%|█████████▍| 1624/1710 [14:06<00:33, 2.53it/s] 95%|█████████▌| 1625/1710 [14:06<00:33, 2.53it/s] 95%|█████████▌| 1626/1710 [14:07<00:32, 2.60it/s] 95%|█████████▌| 1627/1710 [14:07<00:35, 2.33it/s] 95%|█████████▌| 1628/1710 [14:08<00:34, 2.36it/s] 95%|█████████▌| 1629/1710 [14:08<00:33, 2.43it/s] 95%|█████████▌| 1630/1710 [14:08<00:31, 2.54it/s] 95%|█████████▌| 1631/1710 [14:09<00:32, 2.40it/s] 95%|█████████▌| 1632/1710 [14:09<00:31, 2.46it/s] 95%|█████████▌| 1633/1710 [14:10<00:33, 2.28it/s] 96%|█████████▌| 1634/1710 [14:10<00:31, 2.38it/s] 96%|█████████▌| 1635/1710 [14:11<00:33, 2.22it/s] 96%|█████████▌| 1636/1710 [14:11<00:32, 2.26it/s] 96%|█████████▌| 1637/1710 [14:11<00:31, 2.30it/s] 96%|█████████▌| 1638/1710 [14:12<00:31, 2.30it/s] 96%|█████████▌| 1639/1710 [14:12<00:29, 2.40it/s] 96%|█████████▌| 1640/1710 [14:13<00:29, 2.38it/s] 96%|█████████▌| 1641/1710 [14:13<00:29, 2.36it/s] 96%|█████████▌| 1642/1710 [14:13<00:28, 2.38it/s] 96%|█████████▌| 1643/1710 [14:14<00:29, 2.25it/s] 96%|█████████▌| 1644/1710 [14:14<00:26, 2.47it/s] 96%|█████████▌| 1645/1710 [14:15<00:26, 2.49it/s] 96%|█████████▋| 1646/1710 [14:15<00:25, 2.55it/s] 96%|█████████▋| 1647/1710 [14:15<00:26, 2.41it/s] 96%|█████████▋| 1648/1710 [14:16<00:26, 2.38it/s] 96%|█████████▋| 1649/1710 [14:16<00:25, 2.39it/s] 96%|█████████▋| 1650/1710 [14:17<00:25, 2.36it/s] 97%|█████████▋| 1651/1710 [14:17<00:24, 2.40it/s] 97%|█████████▋| 1652/1710 [14:18<00:24, 2.34it/s] 97%|█████████▋| 1653/1710 [14:18<00:24, 2.30it/s] 97%|█████████▋| 1654/1710 [14:18<00:24, 2.32it/s] 97%|█████████▋| 1655/1710 [14:19<00:23, 2.33it/s] 97%|█████████▋| 1656/1710 [14:19<00:24, 2.17it/s] 97%|█████████▋| 1657/1710 [14:20<00:24, 2.16it/s] 97%|█████████▋| 1658/1710 [14:20<00:23, 2.23it/s] 97%|█████████▋| 1659/1710 [14:21<00:21, 2.36it/s] 97%|█████████▋| 1660/1710 [14:21<00:22, 2.27it/s] 97%|█████████▋| 1661/1710 [14:22<00:20, 2.36it/s] 97%|█████████▋| 1662/1710 [14:22<00:21, 2.20it/s] 97%|█████████▋| 1663/1710 [14:22<00:20, 2.34it/s] 97%|█████████▋| 1664/1710 [14:23<00:19, 2.36it/s] 97%|█████████▋| 1665/1710 [14:23<00:20, 2.17it/s] 97%|█████████▋| 1666/1710 [14:24<00:18, 2.33it/s] 97%|█████████▋| 1667/1710 [14:24<00:18, 2.32it/s] 98%|█████████▊| 1668/1710 [14:25<00:19, 2.15it/s] 98%|█████████▊| 1669/1710 [14:25<00:17, 2.31it/s] 98%|█████████▊| 1670/1710 [14:25<00:16, 2.40it/s] 98%|█████████▊| 1671/1710 [14:26<00:17, 2.27it/s] 98%|█████████▊| 1672/1710 [14:26<00:15, 2.41it/s] 98%|█████████▊| 1673/1710 [14:27<00:14, 2.57it/s] 98%|█████████▊| 1674/1710 [14:27<00:13, 2.68it/s] 98%|█████████▊| 1675/1710 [14:27<00:14, 2.45it/s] 98%|█████████▊| 1676/1710 [14:28<00:13, 2.54it/s] 98%|█████████▊| 1677/1710 [14:29<00:16, 2.04it/s] 98%|█████████▊| 1678/1710 [14:29<00:15, 2.06it/s] 98%|█████████▊| 1679/1710 [14:29<00:14, 2.16it/s] 98%|█████████▊| 1680/1710 [14:30<00:13, 2.24it/s] 98%|█████████▊| 1681/1710 [14:30<00:12, 2.30it/s] 98%|█████████▊| 1682/1710 [14:31<00:12, 2.25it/s] 98%|█████████▊| 1683/1710 [14:31<00:11, 2.35it/s] 98%|█████████▊| 1684/1710 [14:32<00:14, 1.86it/s] 99%|█████████▊| 1685/1710 [14:32<00:13, 1.88it/s] 99%|█████████▊| 1686/1710 [14:33<00:11, 2.01it/s] 99%|█████████▊| 1687/1710 [14:33<00:12, 1.86it/s] 99%|█████████▊| 1688/1710 [14:34<00:10, 2.01it/s] 99%|█████████▉| 1689/1710 [14:34<00:09, 2.12it/s] 99%|█████████▉| 1690/1710 [14:35<00:09, 2.14it/s] 99%|█████████▉| 1691/1710 [14:35<00:09, 2.02it/s] 99%|█████████▉| 1692/1710 [14:36<00:08, 2.16it/s] 99%|█████████▉| 1693/1710 [14:36<00:07, 2.18it/s] 99%|█████████▉| 1694/1710 [14:37<00:07, 2.03it/s] 99%|█████████▉| 1695/1710 [14:37<00:07, 1.89it/s] 99%|█████████▉| 1696/1710 [14:38<00:06, 2.10it/s] 99%|█████████▉| 1697/1710 [14:38<00:05, 2.26it/s] 99%|█████████▉| 1698/1710 [14:39<00:05, 2.00it/s] 99%|█████████▉| 1699/1710 [14:39<00:05, 2.06it/s] 99%|█████████▉| 1700/1710 [14:40<00:04, 2.05it/s] 99%|█████████▉| 1701/1710 [14:40<00:05, 1.71it/s] 100%|█████████▉| 1702/1710 [14:41<00:04, 1.76it/s] 100%|█████████▉| 1703/1710 [14:42<00:04, 1.70it/s] 100%|█████████▉| 1704/1710 [14:42<00:03, 1.93it/s] 100%|█████████▉| 1705/1710 [14:43<00:02, 1.80it/s] 100%|█████████▉| 1706/1710 [14:43<00:02, 1.89it/s] 100%|█████████▉| 1707/1710 [14:43<00:01, 2.08it/s] 100%|█████████▉| 1708/1710 [14:44<00:00, 2.09it/s] 100%|█████████▉| 1709/1710 [14:45<00:00, 1.75it/s] 100%|██████████| 1710/1710 [14:45<00:00, 1.94it/s][INFO|trainer.py:3503] 2024-09-09 12:29:41,232 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-1710 | |
| [INFO|configuration_utils.py:472] 2024-09-09 12:29:41,233 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-1710/config.json | |
| [INFO|modeling_utils.py:2799] 2024-09-09 12:29:42,287 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-1710/model.safetensors | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:29:42,288 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-1710/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:29:42,289 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-1710/special_tokens_map.json | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:29:47,798 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:29:47,799 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json | |
| [INFO|trainer.py:811] 2024-09-09 12:29:47,847 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: ner_tags, id, tokens. If ner_tags, id, tokens are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. | |
| [INFO|trainer.py:3819] 2024-09-09 12:29:47,850 >> | |
| ***** Running Evaluation ***** | |
| [INFO|trainer.py:3821] 2024-09-09 12:29:47,850 >> Num examples = 2519 | |
| [INFO|trainer.py:3824] 2024-09-09 12:29:47,850 >> Batch size = 8 | |
| {'eval_loss': 0.2917279005050659, 'eval_precision': 0.6458022851465475, 'eval_recall': 0.7115489874110563, 'eval_f1': 0.6770833333333333, 'eval_accuracy': 0.9466938304084186, 'eval_runtime': 5.9353, 'eval_samples_per_second': 424.408, 'eval_steps_per_second': 53.072, 'epoch': 9.0} | |
| 0%| | 0/315 [00:00<?, ?it/s][A | |
| 3%|▎ | 8/315 [00:00<00:03, 78.48it/s][A | |
| 5%|▌ | 16/315 [00:00<00:03, 75.15it/s][A | |
| 8%|▊ | 24/315 [00:00<00:03, 76.67it/s][A | |
| 10%|█ | 32/315 [00:00<00:03, 72.34it/s][A | |
| 13%|█▎ | 41/315 [00:00<00:03, 75.90it/s][A | |
| 16%|█▌ | 49/315 [00:00<00:03, 74.64it/s][A | |
| 18%|█▊ | 57/315 [00:00<00:03, 74.70it/s][A | |
| 21%|██ | 65/315 [00:00<00:03, 71.45it/s][A | |
| 23%|██▎ | 73/315 [00:00<00:03, 73.28it/s][A | |
| 26%|██▌ | 81/315 [00:01<00:03, 69.66it/s][A | |
| 28%|██▊ | 89/315 [00:01<00:03, 66.63it/s][A | |
| 31%|███ | 97/315 [00:01<00:03, 66.80it/s][A | |
| 33%|███▎ | 104/315 [00:01<00:03, 67.55it/s][A | |
| 36%|███▌ | 112/315 [00:01<00:02, 70.16it/s][A | |
| 38%|███▊ | 120/315 [00:01<00:02, 69.45it/s][A | |
| 40%|████ | 127/315 [00:01<00:02, 68.94it/s][A | |
| 43%|████▎ | 134/315 [00:01<00:02, 68.70it/s][A | |
| 45%|████▍ | 141/315 [00:01<00:02, 69.03it/s][A | |
| 47%|████▋ | 149/315 [00:02<00:02, 71.83it/s][A | |
| 50%|█████ | 158/315 [00:02<00:02, 74.77it/s][A | |
| 53%|█████▎ | 166/315 [00:02<00:02, 71.53it/s][A | |
| 55%|█████▌ | 174/315 [00:02<00:01, 71.33it/s][A | |
| 58%|█████▊ | 182/315 [00:02<00:01, 68.58it/s][A | |
| 60%|██████ | 189/315 [00:02<00:01, 68.46it/s][A | |
| 62%|██████▏ | 196/315 [00:02<00:01, 67.83it/s][A | |
| 64%|██████▍ | 203/315 [00:02<00:01, 64.56it/s][A | |
| 67%|██████▋ | 210/315 [00:03<00:01, 63.19it/s][A | |
| 69%|██████▉ | 217/315 [00:03<00:01, 64.49it/s][A | |
| 71%|███████▏ | 225/315 [00:03<00:01, 67.99it/s][A | |
| 74%|███████▍ | 234/315 [00:03<00:01, 72.14it/s][A | |
| 77%|███████▋ | 242/315 [00:03<00:01, 70.05it/s][A | |
| 79%|███████▉ | 250/315 [00:03<00:00, 70.23it/s][A | |
| 82%|████████▏ | 258/315 [00:03<00:00, 68.35it/s][A | |
| 84%|████████▍ | 266/315 [00:03<00:00, 69.52it/s][A | |
| 87%|████████▋ | 274/315 [00:03<00:00, 72.33it/s][A | |
| 90%|████████▉ | 283/315 [00:04<00:00, 74.24it/s][A | |
| 92%|█████████▏| 291/315 [00:04<00:00, 71.78it/s][A | |
| 95%|█████████▍| 299/315 [00:04<00:00, 70.81it/s][A | |
| 97%|█████████▋| 307/315 [00:04<00:00, 71.90it/s][A | |
| 100%|██████████| 315/315 [00:04<00:00, 70.36it/s][A | |
| [A 100%|██████████| 1710/1710 [14:58<00:00, 1.94it/s] | |
| 100%|██████████| 315/315 [00:05<00:00, 70.36it/s][A | |
| [A[INFO|trainer.py:3503] 2024-09-09 12:29:53,786 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-1710 | |
| [INFO|configuration_utils.py:472] 2024-09-09 12:29:53,788 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-1710/config.json | |
| [INFO|modeling_utils.py:2799] 2024-09-09 12:29:55,303 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-1710/model.safetensors | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:29:55,306 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-1710/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:29:55,306 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-1710/special_tokens_map.json | |
| [INFO|trainer.py:2394] 2024-09-09 12:29:57,247 >> | |
| Training completed. Do not forget to share your model on huggingface.co/models =) | |
| [INFO|trainer.py:2632] 2024-09-09 12:29:57,247 >> Loading best model from /content/dissertation/scripts/ner/output/checkpoint-1368 (score: 0.680984808800419). | |
| 100%|██████████| 1710/1710 [15:01<00:00, 1.94it/s] 100%|██████████| 1710/1710 [15:01<00:00, 1.90it/s] | |
| [INFO|trainer.py:4283] 2024-09-09 12:29:57,436 >> Waiting for the current checkpoint push to be finished, this might take a couple of minutes. | |
| [INFO|trainer.py:3503] 2024-09-09 12:30:42,660 >> Saving model checkpoint to /content/dissertation/scripts/ner/output | |
| [INFO|configuration_utils.py:472] 2024-09-09 12:30:42,661 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json | |
| [INFO|modeling_utils.py:2799] 2024-09-09 12:30:44,034 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:30:44,035 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:30:44,035 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json | |
| [INFO|trainer.py:3503] 2024-09-09 12:30:44,082 >> Saving model checkpoint to /content/dissertation/scripts/ner/output | |
| [INFO|configuration_utils.py:472] 2024-09-09 12:30:44,083 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json | |
| [INFO|modeling_utils.py:2799] 2024-09-09 12:30:47,113 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:30:47,114 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:30:47,114 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json | |
| {'eval_loss': 0.2930145561695099, 'eval_precision': 0.6548403446528129, 'eval_recall': 0.7071702244116037, 'eval_f1': 0.6799999999999999, 'eval_accuracy': 0.9481215310083737, 'eval_runtime': 5.9346, 'eval_samples_per_second': 424.463, 'eval_steps_per_second': 53.079, 'epoch': 10.0} | |
| {'train_runtime': 901.7971, 'train_samples_per_second': 121.269, 'train_steps_per_second': 1.896, 'train_loss': 0.047100042948248794, 'epoch': 10.0} | |
| events.out.tfevents.1725884095.0a1c9bec2a53.15221.0: 0%| | 0.00/10.9k [00:00<?, ?B/s] events.out.tfevents.1725884095.0a1c9bec2a53.15221.0: 100%|██████████| 10.9k/10.9k [00:00<00:00, 33.7kB/s] | |
| ***** train metrics ***** | |
| epoch = 10.0 | |
| total_flos = 4927248GF | |
| train_loss = 0.0471 | |
| train_runtime = 0:15:01.79 | |
| train_samples = 10936 | |
| train_samples_per_second = 121.269 | |
| train_steps_per_second = 1.896 | |
| 09/09/2024 12:30:53 - INFO - __main__ - *** Evaluate *** | |
| [INFO|trainer.py:811] 2024-09-09 12:30:53,235 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: ner_tags, id, tokens. If ner_tags, id, tokens are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. | |
| [INFO|trainer.py:3819] 2024-09-09 12:30:53,237 >> | |
| ***** Running Evaluation ***** | |
| [INFO|trainer.py:3821] 2024-09-09 12:30:53,238 >> Num examples = 2519 | |
| [INFO|trainer.py:3824] 2024-09-09 12:30:53,238 >> Batch size = 8 | |
| 0%| | 0/315 [00:00<?, ?it/s] 3%|▎ | 8/315 [00:00<00:03, 77.97it/s] 5%|▌ | 16/315 [00:00<00:04, 74.16it/s] 8%|▊ | 24/315 [00:00<00:03, 75.60it/s] 10%|█ | 32/315 [00:00<00:03, 70.90it/s] 13%|█▎ | 41/315 [00:00<00:03, 74.36it/s] 16%|█▌ | 49/315 [00:00<00:03, 73.52it/s] 18%|█▊ | 57/315 [00:00<00:03, 73.54it/s] 21%|██ | 65/315 [00:00<00:03, 71.22it/s] 23%|██▎ | 73/315 [00:00<00:03, 72.70it/s] 26%|██▌ | 81/315 [00:01<00:03, 68.36it/s] 28%|██▊ | 88/315 [00:01<00:03, 66.29it/s] 30%|███ | 96/315 [00:01<00:03, 69.40it/s] 33%|███▎ | 103/315 [00:01<00:03, 66.83it/s] 35%|███▌ | 111/315 [00:01<00:02, 69.96it/s] 38%|███▊ | 119/315 [00:01<00:02, 70.96it/s] 40%|████ | 127/315 [00:01<00:02, 69.01it/s] 43%|████▎ | 134/315 [00:01<00:02, 68.00it/s] 45%|████▍ | 141/315 [00:02<00:02, 68.32it/s] 47%|████▋ | 149/315 [00:02<00:02, 70.31it/s] 50%|████▉ | 157/315 [00:02<00:02, 72.60it/s] 52%|█████▏ | 165/315 [00:02<00:02, 71.29it/s] 55%|█████▍ | 173/315 [00:02<00:02, 70.72it/s] 57%|█████▋ | 181/315 [00:02<00:01, 68.66it/s] 60%|█████▉ | 188/315 [00:02<00:01, 68.89it/s] 62%|██████▏ | 195/315 [00:02<00:01, 66.91it/s] 64%|██████▍ | 202/315 [00:02<00:01, 65.15it/s] 66%|██████▋ | 209/315 [00:03<00:01, 65.07it/s] 69%|██████▉ | 217/315 [00:03<00:01, 67.82it/s] 71%|███████▏ | 225/315 [00:03<00:01, 70.30it/s] 74%|███████▍ | 233/315 [00:03<00:01, 72.81it/s] 77%|███████▋ | 241/315 [00:03<00:01, 70.62it/s] 79%|███████▉ | 249/315 [00:03<00:00, 69.72it/s] 82%|████████▏ | 257/315 [00:03<00:00, 67.63it/s] 84%|████████▍ | 265/315 [00:03<00:00, 69.05it/s] 87%|████████▋ | 274/315 [00:03<00:00, 72.50it/s] 90%|████████▉ | 282/315 [00:04<00:00, 74.49it/s] 92%|█████████▏| 290/315 [00:04<00:00, 70.74it/s] 95%|█████████▍| 298/315 [00:04<00:00, 70.04it/s] 97%|█████████▋| 306/315 [00:04<00:00, 71.93it/s] 100%|█████████▉| 314/315 [00:04<00:00, 69.90it/s] 100%|██████████| 315/315 [00:06<00:00, 51.18it/s] | |
| ***** eval metrics ***** | |
| epoch = 10.0 | |
| eval_accuracy = 0.9473 | |
| eval_f1 = 0.681 | |
| eval_loss = 0.2808 | |
| eval_precision = 0.6529 | |
| eval_recall = 0.7115 | |
| eval_runtime = 0:00:06.16 | |
| eval_samples = 2519 | |
| eval_samples_per_second = 408.28 | |
| eval_steps_per_second = 51.055 | |
| 09/09/2024 12:30:59 - INFO - __main__ - *** Predict *** | |
| [INFO|trainer.py:811] 2024-09-09 12:30:59,410 >> The following columns in the test set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: ner_tags, id, tokens. If ner_tags, id, tokens are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. | |
| [INFO|trainer.py:3819] 2024-09-09 12:30:59,412 >> | |
| ***** Running Prediction ***** | |
| [INFO|trainer.py:3821] 2024-09-09 12:30:59,412 >> Num examples = 4047 | |
| [INFO|trainer.py:3824] 2024-09-09 12:30:59,412 >> Batch size = 8 | |
| 0%| | 0/506 [00:00<?, ?it/s] 2%|▏ | 9/506 [00:00<00:05, 89.20it/s] 4%|▎ | 18/506 [00:00<00:06, 76.66it/s] 5%|▌ | 26/506 [00:00<00:06, 76.81it/s] 7%|▋ | 34/506 [00:00<00:06, 75.68it/s] 8%|▊ | 42/506 [00:00<00:06, 73.46it/s] 10%|▉ | 50/506 [00:00<00:06, 73.25it/s] 11%|█▏ | 58/506 [00:00<00:06, 73.76it/s] 13%|█▎ | 66/506 [00:00<00:06, 70.93it/s] 15%|█▍ | 74/506 [00:01<00:06, 71.43it/s] 16%|█▌ | 82/506 [00:01<00:06, 62.16it/s] 18%|█▊ | 89/506 [00:01<00:06, 62.05it/s] 19%|█▉ | 97/506 [00:01<00:06, 65.70it/s] 21%|██ | 105/506 [00:01<00:05, 68.07it/s] 22%|██▏ | 113/506 [00:01<00:05, 70.17it/s] 24%|██▍ | 121/506 [00:01<00:05, 69.38it/s] 25%|██▌ | 129/506 [00:01<00:06, 59.19it/s] 27%|██▋ | 136/506 [00:02<00:06, 57.59it/s] 28%|██▊ | 144/506 [00:02<00:05, 61.37it/s] 30%|███ | 152/506 [00:02<00:05, 64.13it/s] 31%|███▏ | 159/506 [00:02<00:05, 59.74it/s] 33%|███▎ | 166/506 [00:02<00:05, 60.44it/s] 34%|███▍ | 173/506 [00:02<00:05, 62.40it/s] 36%|███▌ | 180/506 [00:02<00:05, 64.04it/s] 37%|███▋ | 188/506 [00:02<00:04, 66.16it/s] 39%|███▊ | 195/506 [00:02<00:04, 66.21it/s] 40%|████ | 203/506 [00:03<00:04, 68.48it/s] 42%|████▏ | 210/506 [00:03<00:04, 65.95it/s] 43%|████▎ | 217/506 [00:03<00:04, 66.63it/s] 44%|████▍ | 224/506 [00:03<00:04, 61.58it/s] 46%|████▌ | 231/506 [00:03<00:04, 63.12it/s] 47%|████▋ | 238/506 [00:03<00:04, 61.97it/s] 49%|████▊ | 246/506 [00:03<00:03, 65.36it/s] 50%|█████ | 253/506 [00:03<00:03, 65.50it/s] 52%|█████▏ | 261/506 [00:03<00:03, 68.54it/s] 53%|█████▎ | 269/506 [00:04<00:03, 71.13it/s] 55%|█████▍ | 277/506 [00:04<00:03, 72.79it/s] 56%|█████▋ | 285/506 [00:04<00:03, 70.62it/s] 58%|█████▊ | 293/506 [00:04<00:02, 71.05it/s] 59%|█████▉ | 301/506 [00:04<00:02, 72.05it/s] 61%|██████ | 309/506 [00:04<00:02, 72.62it/s] 63%|██████▎ | 317/506 [00:04<00:02, 72.83it/s] 64%|██████▍ | 326/506 [00:04<00:02, 75.83it/s] 66%|██████▌ | 335/506 [00:04<00:02, 77.77it/s] 68%|██████▊ | 343/506 [00:05<00:02, 76.74it/s] 69%|██████▉ | 351/506 [00:05<00:02, 76.99it/s] 71%|███████ | 359/506 [00:05<00:01, 76.22it/s] 73%|███████▎ | 367/506 [00:05<00:01, 73.61it/s] 74%|███████▍ | 375/506 [00:05<00:01, 68.17it/s] 75%|███████▌ | 382/506 [00:05<00:01, 67.51it/s] 77%|███████▋ | 389/506 [00:05<00:01, 62.73it/s] 78%|███████▊ | 396/506 [00:05<00:01, 60.98it/s] 80%|███████▉ | 403/506 [00:05<00:01, 57.28it/s] 81%|████████ | 410/506 [00:06<00:01, 59.54it/s] 82%|████████▏ | 417/506 [00:06<00:01, 61.06it/s] 84%|████████▍ | 424/506 [00:06<00:01, 61.58it/s] 85%|████████▌ | 432/506 [00:06<00:01, 66.19it/s] 87%|████████▋ | 439/506 [00:06<00:01, 66.57it/s] 88%|████████▊ | 446/506 [00:06<00:00, 65.56it/s] 90%|████████▉ | 454/506 [00:06<00:00, 67.26it/s] 91%|█████████▏| 462/506 [00:06<00:00, 70.64it/s] 93%|█████████▎| 470/506 [00:06<00:00, 71.31it/s] 94%|█████████▍| 478/506 [00:07<00:00, 72.28it/s] 96%|█████████▌| 486/506 [00:07<00:00, 70.00it/s] 98%|█████████▊| 494/506 [00:07<00:00, 69.30it/s] 99%|█████████▉| 502/506 [00:07<00:00, 71.07it/s] 100%|██████████| 506/506 [00:09<00:00, 51.46it/s] | |
| [INFO|trainer.py:3503] 2024-09-09 12:31:09,424 >> Saving model checkpoint to /content/dissertation/scripts/ner/output | |
| [INFO|configuration_utils.py:472] 2024-09-09 12:31:09,425 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json | |
| [INFO|modeling_utils.py:2799] 2024-09-09 12:31:10,791 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors | |
| [INFO|tokenization_utils_base.py:2684] 2024-09-09 12:31:10,792 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2693] 2024-09-09 12:31:10,793 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json | |
| ***** predict metrics ***** | |
| predict_accuracy = 0.9476 | |
| predict_f1 = 0.691 | |
| predict_loss = 0.3017 | |
| predict_precision = 0.6776 | |
| predict_recall = 0.7049 | |
| predict_runtime = 0:00:09.84 | |
| predict_samples_per_second = 410.896 | |
| predict_steps_per_second = 51.375 | |
| events.out.tfevents.1725885059.0a1c9bec2a53.15221.1: 0%| | 0.00/560 [00:00<?, ?B/s] events.out.tfevents.1725885059.0a1c9bec2a53.15221.1: 100%|██████████| 560/560 [00:00<00:00, 1.97kB/s] | |