2024-08-30 20:25:26.549777: 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`. 2024-08-30 20:25:26.568217: 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 2024-08-30 20:25:26.590253: 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 2024-08-30 20:25:26.597224: 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 2024-08-30 20:25:26.612962: 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. 2024-08-30 20:25:27.916342: 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:1494: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead warnings.warn( 08/30/2024 20:25:29 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False 08/30/2024 20:25:29 - 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, 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=, 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=, 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, torchdynamo=None, tpu_metrics_debug=False, tpu_num_cores=None, use_cpu=False, use_ipex=False, use_legacy_prediction_loop=False, use_mps_device=False, warmup_ratio=0.0, warmup_steps=0, weight_decay=0.0, ) Downloading builder script: 0%| | 0.00/3.54k [00:00> 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] 2024-08-30 20:25:41,923 >> Model config RobertaConfig { "_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es", "architectures": [ "RobertaForMaskedLM" ], "attention_probs_dropout_prob": 0.1, "bos_token_id": 0, "classifier_dropout": null, "eos_token_id": 2, "finetuning_task": "ner", "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "O", "1": "B-ENFERMEDAD", "2": "I-ENFERMEDAD" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "B-ENFERMEDAD": 1, "I-ENFERMEDAD": 2, "O": 0 }, "layer_norm_eps": 1e-05, "max_position_embeddings": 514, "model_type": "roberta", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 1, "position_embedding_type": "absolute", "transformers_version": "4.42.4", "type_vocab_size": 1, "use_cache": true, "vocab_size": 50262 } [INFO|configuration_utils.py:733] 2024-08-30 20:25:42,016 >> 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] 2024-08-30 20:25:42,017 >> 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": "4.42.4", "type_vocab_size": 1, "use_cache": true, "vocab_size": 50262 } [INFO|tokenization_utils_base.py:2161] 2024-08-30 20:25:42,027 >> 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:2161] 2024-08-30 20:25:42,028 >> 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:2161] 2024-08-30 20:25:42,028 >> loading file tokenizer.json from cache at None [INFO|tokenization_utils_base.py:2161] 2024-08-30 20:25:42,028 >> loading file added_tokens.json from cache at None [INFO|tokenization_utils_base.py:2161] 2024-08-30 20:25:42,028 >> 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:2161] 2024-08-30 20:25:42,028 >> 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] 2024-08-30 20:25:42,028 >> 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] 2024-08-30 20:25:42,029 >> 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": "4.42.4", "type_vocab_size": 1, "use_cache": true, "vocab_size": 50262 } [INFO|configuration_utils.py:733] 2024-08-30 20:25:42,112 >> 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] 2024-08-30 20:25:42,113 >> 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": "4.42.4", "type_vocab_size": 1, "use_cache": true, "vocab_size": 50262 } [INFO|modeling_utils.py:3556] 2024-08-30 20:25:42,300 >> 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:4354] 2024-08-30 20:25:42,438 >> 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:4366] 2024-08-30 20:25:42,438 >> 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%| | 0/27229 [00:00> The following columns in the training set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: tokens, ner_tags, id. If tokens, ner_tags, id are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. [INFO|trainer.py:2128] 2024-08-30 20:25:48,850 >> ***** Running training ***** [INFO|trainer.py:2129] 2024-08-30 20:25:48,850 >> Num examples = 27,229 [INFO|trainer.py:2130] 2024-08-30 20:25:48,850 >> Num Epochs = 10 [INFO|trainer.py:2131] 2024-08-30 20:25:48,850 >> Instantaneous batch size per device = 32 [INFO|trainer.py:2134] 2024-08-30 20:25:48,850 >> Total train batch size (w. parallel, distributed & accumulation) = 64 [INFO|trainer.py:2135] 2024-08-30 20:25:48,851 >> Gradient Accumulation steps = 2 [INFO|trainer.py:2136] 2024-08-30 20:25:48,851 >> Total optimization steps = 4,250 [INFO|trainer.py:2137] 2024-08-30 20:25:48,851 >> Number of trainable parameters = 124,055,043 0%| | 0/4250 [00:00> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: tokens, ner_tags, id. If tokens, ner_tags, id are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3788] 2024-08-30 20:27:31,192 >> ***** Running Evaluation ***** [INFO|trainer.py:3790] 2024-08-30 20:27:31,192 >> Num examples = 6810 [INFO|trainer.py:3793] 2024-08-30 20:27:31,192 >> Batch size = 8 0%| | 0/852 [00:00> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-425 [INFO|configuration_utils.py:472] 2024-08-30 20:27:45,882 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-425/config.json [INFO|modeling_utils.py:2690] 2024-08-30 20:27:47,247 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-425/model.safetensors [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:27:47,248 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-425/tokenizer_config.json [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:27:47,248 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-425/special_tokens_map.json [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:27:50,017 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:27:50,017 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json 10%|█ | 426/4250 [02:01<6:17:25, 5.92s/it] 10%|█ | 427/4250 [02:01<4:27:24, 4.20s/it] 10%|█ | 428/4250 [02:01<3:11:11, 3.00s/it] 10%|█ | 429/4250 [02:02<2:20:01, 2.20s/it] 10%|█ | 430/4250 [02:02<1:41:14, 1.59s/it] 10%|█ | 431/4250 [02:02<1:15:55, 1.19s/it] 10%|█ | 432/4250 [02:02<56:49, 1.12it/s] 10%|█ | 433/4250 [02:02<43:08, 1.47it/s] 10%|█ | 434/4250 [02:03<35:31, 1.79it/s] 10%|█ | 435/4250 [02:03<28:25, 2.24it/s] 10%|█ | 436/4250 [02:03<24:21, 2.61it/s] 10%|█ | 437/4250 [02:03<20:52, 3.04it/s] 10%|█ | 438/4250 [02:04<18:32, 3.43it/s] 10%|█ | 439/4250 [02:04<17:05, 3.72it/s] 10%|█ | 440/4250 [02:04<15:35, 4.07it/s] 10%|█ | 441/4250 [02:04<14:45, 4.30it/s] 10%|█ | 442/4250 [02:04<14:42, 4.32it/s] 10%|█ | 443/4250 [02:05<16:22, 3.88it/s] 10%|█ | 444/4250 [02:05<15:35, 4.07it/s] 10%|█ | 445/4250 [02:05<14:09, 4.48it/s] 10%|█ | 446/4250 [02:05<15:10, 4.18it/s] 11%|█ | 447/4250 [02:06<14:17, 4.43it/s] 11%|█ | 448/4250 [02:06<13:13, 4.79it/s] 11%|█ | 449/4250 [02:06<13:06, 4.83it/s] 11%|█ | 450/4250 [02:06<15:05, 4.20it/s] 11%|█ | 451/4250 [02:07<15:49, 4.00it/s] 11%|█ | 452/4250 [02:07<14:54, 4.25it/s] 11%|█ | 453/4250 [02:07<15:41, 4.03it/s] 11%|█ | 454/4250 [02:07<15:39, 4.04it/s] 11%|█ | 455/4250 [02:08<15:58, 3.96it/s] 11%|█ | 456/4250 [02:08<14:30, 4.36it/s] 11%|█ | 457/4250 [02:08<13:21, 4.73it/s] 11%|█ | 458/4250 [02:08<14:27, 4.37it/s] 11%|█ | 459/4250 [02:09<24:59, 2.53it/s] 11%|█ | 460/4250 [02:09<25:16, 2.50it/s] 11%|█ | 461/4250 [02:10<23:13, 2.72it/s] 11%|█ | 462/4250 [02:10<20:18, 3.11it/s] 11%|█ | 463/4250 [02:10<18:00, 3.51it/s] 11%|█ | 464/4250 [02:10<16:52, 3.74it/s] 11%|█ | 465/4250 [02:10<15:29, 4.07it/s] 11%|█ | 466/4250 [02:11<14:52, 4.24it/s] 11%|█ | 467/4250 [02:11<15:16, 4.13it/s] 11%|█ | 468/4250 [02:11<15:22, 4.10it/s] 11%|█ | 469/4250 [02:11<14:56, 4.22it/s] 11%|█ | 470/4250 [02:12<14:16, 4.41it/s] 11%|█ | 471/4250 [02:12<13:02, 4.83it/s] 11%|█ | 472/4250 [02:12<14:34, 4.32it/s] 11%|█ | 473/4250 [02:12<14:11, 4.43it/s] 11%|█ | 474/4250 [02:13<15:34, 4.04it/s] 11%|█ | 475/4250 [02:13<19:44, 3.19it/s] 11%|█ | 476/4250 [02:13<19:06, 3.29it/s] 11%|█ | 477/4250 [02:14<18:12, 3.45it/s] 11%|█ | 478/4250 [02:14<18:34, 3.39it/s] 11%|█▏ | 479/4250 [02:14<17:12, 3.65it/s] 11%|█▏ | 480/4250 [02:14<15:17, 4.11it/s] 11%|█▏ | 481/4250 [02:15<16:05, 3.90it/s] 11%|█▏ | 482/4250 [02:15<17:51, 3.52it/s] 11%|█▏ | 483/4250 [02:15<16:15, 3.86it/s] 11%|█▏ | 484/4250 [02:15<14:39, 4.28it/s] 11%|█▏ | 485/4250 [02:16<14:48, 4.24it/s] 11%|█▏ | 486/4250 [02:16<15:40, 4.00it/s] 11%|█▏ | 487/4250 [02:16<14:28, 4.33it/s] 11%|█▏ | 488/4250 [02:16<14:12, 4.41it/s] 12%|█▏ | 489/4250 [02:17<18:04, 3.47it/s] 12%|█▏ | 490/4250 [02:17<16:37, 3.77it/s] 12%|█▏ | 491/4250 [02:17<16:44, 3.74it/s] 12%|█▏ | 492/4250 [02:17<15:59, 3.92it/s] 12%|█▏ | 493/4250 [02:18<14:35, 4.29it/s] 12%|█▏ | 494/4250 [02:18<15:03, 4.16it/s] 12%|█▏ | 495/4250 [02:18<17:00, 3.68it/s] 12%|█▏ | 496/4250 [02:18<16:06, 3.89it/s] 12%|█▏ | 497/4250 [02:19<14:40, 4.26it/s] 12%|█▏ | 498/4250 [02:19<14:03, 4.45it/s] 12%|█▏ | 499/4250 [02:19<14:47, 4.23it/s] 12%|█▏ | 500/4250 [02:19<14:18, 4.37it/s] 12%|█▏ | 500/4250 [02:19<14:18, 4.37it/s] 12%|█▏ | 501/4250 [02:20<16:50, 3.71it/s] 12%|█▏ | 502/4250 [02:20<18:04, 3.46it/s] 12%|█▏ | 503/4250 [02:20<18:01, 3.47it/s] 12%|█▏ | 504/4250 [02:20<16:50, 3.71it/s] 12%|█▏ | 505/4250 [02:21<15:26, 4.04it/s] 12%|█▏ | 506/4250 [02:21<14:58, 4.17it/s] 12%|█▏ | 507/4250 [02:21<14:47, 4.22it/s] 12%|█▏ | 508/4250 [02:21<14:03, 4.44it/s] 12%|█▏ | 509/4250 [02:21<13:05, 4.76it/s] 12%|█▏ | 510/4250 [02:22<12:58, 4.81it/s] 12%|█▏ | 511/4250 [02:22<15:56, 3.91it/s] 12%|█▏ | 512/4250 [02:22<14:14, 4.37it/s] 12%|█▏ | 513/4250 [02:22<14:20, 4.34it/s] 12%|█▏ | 514/4250 [02:23<16:21, 3.81it/s] 12%|█▏ | 515/4250 [02:23<15:20, 4.06it/s] 12%|█▏ | 516/4250 [02:23<15:04, 4.13it/s] 12%|█▏ | 517/4250 [02:23<15:07, 4.11it/s] 12%|█▏ | 518/4250 [02:24<15:38, 3.98it/s] 12%|█▏ | 519/4250 [02:24<17:20, 3.58it/s] 12%|█▏ | 520/4250 [02:24<17:54, 3.47it/s] 12%|█▏ | 521/4250 [02:25<16:21, 3.80it/s] 12%|█▏ | 522/4250 [02:25<16:01, 3.88it/s] 12%|█▏ | 523/4250 [02:25<17:21, 3.58it/s] 12%|█▏ | 524/4250 [02:26<19:10, 3.24it/s] 12%|█▏ | 525/4250 [02:26<17:24, 3.57it/s] 12%|█▏ | 526/4250 [02:26<15:34, 3.98it/s] 12%|█▏ | 527/4250 [02:26<14:54, 4.16it/s] 12%|█▏ | 528/4250 [02:26<14:49, 4.18it/s] 12%|█▏ | 529/4250 [02:27<15:21, 4.04it/s] 12%|█▏ | 530/4250 [02:27<15:37, 3.97it/s] 12%|█▏ | 531/4250 [02:27<14:29, 4.28it/s] 13%|█▎ | 532/4250 [02:27<16:50, 3.68it/s] 13%|█▎ | 533/4250 [02:28<15:01, 4.12it/s] 13%|█▎ | 534/4250 [02:28<14:09, 4.37it/s] 13%|█▎ | 535/4250 [02:28<14:16, 4.34it/s] 13%|█▎ | 536/4250 [02:28<13:56, 4.44it/s] 13%|█▎ | 537/4250 [02:28<13:24, 4.62it/s] 13%|█▎ | 538/4250 [02:29<14:57, 4.14it/s] 13%|█▎ | 539/4250 [02:29<15:02, 4.11it/s] 13%|█▎ | 540/4250 [02:29<15:33, 3.97it/s] 13%|█▎ | 541/4250 [02:29<14:15, 4.34it/s] 13%|█▎ | 542/4250 [02:30<13:53, 4.45it/s] 13%|█▎ | 543/4250 [02:30<18:51, 3.28it/s] 13%|█▎ | 544/4250 [02:30<17:08, 3.60it/s] 13%|█▎ | 545/4250 [02:31<15:25, 4.00it/s] 13%|█▎ | 546/4250 [02:31<14:10, 4.35it/s] 13%|█▎ | 547/4250 [02:31<13:43, 4.49it/s] 13%|█▎ | 548/4250 [02:31<13:33, 4.55it/s] 13%|█▎ | 549/4250 [02:31<12:51, 4.80it/s] 13%|█▎ | 550/4250 [02:32<12:56, 4.76it/s] 13%|█▎ | 551/4250 [02:32<12:51, 4.79it/s] 13%|█▎ | 552/4250 [02:32<14:06, 4.37it/s] 13%|█▎ | 553/4250 [02:32<13:15, 4.65it/s] 13%|█▎ | 554/4250 [02:32<12:47, 4.81it/s] 13%|█▎ | 555/4250 [02:33<13:01, 4.73it/s] 13%|█▎ | 556/4250 [02:33<16:10, 3.81it/s] 13%|█▎ | 557/4250 [02:33<14:46, 4.16it/s] 13%|█▎ | 558/4250 [02:33<14:18, 4.30it/s] 13%|█▎ | 559/4250 [02:34<14:12, 4.33it/s] 13%|█▎ | 560/4250 [02:34<14:29, 4.25it/s] 13%|█▎ | 561/4250 [02:34<17:17, 3.56it/s] 13%|█▎ | 562/4250 [02:34<15:18, 4.02it/s] 13%|█▎ | 563/4250 [02:35<14:17, 4.30it/s] 13%|█▎ | 564/4250 [02:35<13:29, 4.55it/s] 13%|█▎ | 565/4250 [02:35<14:47, 4.15it/s] 13%|█▎ | 566/4250 [02:35<13:50, 4.44it/s] 13%|█▎ | 567/4250 [02:36<13:15, 4.63it/s] 13%|█▎ | 568/4250 [02:36<13:16, 4.62it/s] 13%|█▎ | 569/4250 [02:36<14:28, 4.24it/s] 13%|█▎ | 570/4250 [02:36<15:19, 4.00it/s] 13%|█▎ | 571/4250 [02:36<13:33, 4.52it/s] 13%|█▎ | 572/4250 [02:37<21:47, 2.81it/s] 13%|█▎ | 573/4250 [02:37<19:22, 3.16it/s] 14%|█▎ | 574/4250 [02:38<16:47, 3.65it/s] 14%|█▎ | 575/4250 [02:38<14:50, 4.13it/s] 14%|█▎ | 576/4250 [02:38<13:21, 4.58it/s] 14%|█▎ | 577/4250 [02:38<12:54, 4.74it/s] 14%|█▎ | 578/4250 [02:38<12:51, 4.76it/s] 14%|█▎ | 579/4250 [02:39<15:21, 3.98it/s] 14%|█▎ | 580/4250 [02:39<13:53, 4.41it/s] 14%|█▎ | 581/4250 [02:39<14:52, 4.11it/s] 14%|█▎ | 582/4250 [02:39<13:19, 4.59it/s] 14%|█▎ | 583/4250 [02:39<12:20, 4.95it/s] 14%|█▎ | 584/4250 [02:40<12:06, 5.05it/s] 14%|█▍ | 585/4250 [02:40<11:19, 5.39it/s] 14%|█▍ | 586/4250 [02:40<11:14, 5.43it/s] 14%|█▍ | 587/4250 [02:40<11:55, 5.12it/s] 14%|█▍ | 588/4250 [02:40<14:39, 4.16it/s] 14%|█▍ | 589/4250 [02:41<13:56, 4.38it/s] 14%|█▍ | 590/4250 [02:41<13:44, 4.44it/s] 14%|█▍ | 591/4250 [02:41<13:26, 4.54it/s] 14%|█▍ | 592/4250 [02:41<13:48, 4.41it/s] 14%|█▍ | 593/4250 [02:42<14:21, 4.24it/s] 14%|█▍ | 594/4250 [02:42<14:04, 4.33it/s] 14%|█▍ | 595/4250 [02:42<13:37, 4.47it/s] 14%|█▍ | 596/4250 [02:42<14:48, 4.11it/s] 14%|█▍ | 597/4250 [02:43<15:50, 3.85it/s] 14%|█▍ | 598/4250 [02:43<17:34, 3.46it/s] 14%|█▍ | 599/4250 [02:43<16:09, 3.77it/s] 14%|█▍ | 600/4250 [02:43<14:52, 4.09it/s] 14%|█▍ | 601/4250 [02:44<14:44, 4.13it/s] 14%|█▍ | 602/4250 [02:44<15:18, 3.97it/s] 14%|█▍ | 603/4250 [02:44<14:03, 4.32it/s] 14%|█▍ | 604/4250 [02:44<13:59, 4.34it/s] 14%|█▍ | 605/4250 [02:45<14:29, 4.19it/s] 14%|█▍ | 606/4250 [02:45<16:38, 3.65it/s] 14%|█▍ | 607/4250 [02:45<14:46, 4.11it/s] 14%|█▍ | 608/4250 [02:45<14:38, 4.15it/s] 14%|█▍ | 609/4250 [02:46<14:26, 4.20it/s] 14%|█▍ | 610/4250 [02:46<13:59, 4.33it/s] 14%|█▍ | 611/4250 [02:46<15:37, 3.88it/s] 14%|█▍ | 612/4250 [02:46<15:20, 3.95it/s] 14%|█▍ | 613/4250 [02:47<15:54, 3.81it/s] 14%|█▍ | 614/4250 [02:47<15:06, 4.01it/s] 14%|█▍ | 615/4250 [02:47<15:03, 4.02it/s] 14%|█▍ | 616/4250 [02:47<13:51, 4.37it/s] 15%|█▍ | 617/4250 [02:48<15:19, 3.95it/s] 15%|█▍ | 618/4250 [02:48<14:58, 4.04it/s] 15%|█▍ | 619/4250 [02:48<14:26, 4.19it/s] 15%|█▍ | 620/4250 [02:48<14:43, 4.11it/s] 15%|█▍ | 621/4250 [02:48<13:36, 4.44it/s] 15%|█▍ | 622/4250 [02:49<14:18, 4.22it/s] 15%|█▍ | 623/4250 [02:49<13:09, 4.59it/s] 15%|█▍ | 624/4250 [02:49<13:37, 4.44it/s] 15%|█▍ | 625/4250 [02:50<16:01, 3.77it/s] 15%|█▍ | 626/4250 [02:50<16:31, 3.65it/s] 15%|█▍ | 627/4250 [02:50<14:19, 4.22it/s] 15%|█▍ | 628/4250 [02:50<13:36, 4.44it/s] 15%|█▍ | 629/4250 [02:50<13:34, 4.44it/s] 15%|█▍ | 630/4250 [02:51<13:17, 4.54it/s] 15%|█▍ | 631/4250 [02:51<13:15, 4.55it/s] 15%|█▍ | 632/4250 [02:51<12:49, 4.70it/s] 15%|█▍ | 633/4250 [02:51<12:11, 4.95it/s] 15%|█▍ | 634/4250 [02:51<12:32, 4.80it/s] 15%|█▍ | 635/4250 [02:52<12:07, 4.97it/s] 15%|█▍ | 636/4250 [02:52<12:08, 4.96it/s] 15%|█▍ | 637/4250 [02:52<11:50, 5.09it/s] 15%|█▌ | 638/4250 [02:52<12:29, 4.82it/s] 15%|█▌ | 639/4250 [02:52<11:32, 5.21it/s] 15%|█▌ | 640/4250 [02:53<12:20, 4.88it/s] 15%|█▌ | 641/4250 [02:53<12:21, 4.87it/s] 15%|█▌ | 642/4250 [02:53<15:13, 3.95it/s] 15%|█▌ | 643/4250 [02:53<14:34, 4.12it/s] 15%|█▌ | 644/4250 [02:54<14:59, 4.01it/s] 15%|█▌ | 645/4250 [02:54<14:11, 4.23it/s] 15%|█▌ | 646/4250 [02:54<16:16, 3.69it/s] 15%|█▌ | 647/4250 [02:55<17:10, 3.50it/s] 15%|█▌ | 648/4250 [02:55<16:58, 3.54it/s] 15%|█▌ | 649/4250 [02:55<16:05, 3.73it/s] 15%|█▌ | 650/4250 [02:55<14:33, 4.12it/s] 15%|█▌ | 651/4250 [02:55<13:34, 4.42it/s] 15%|█▌ | 652/4250 [02:56<13:39, 4.39it/s] 15%|█▌ | 653/4250 [02:56<14:27, 4.15it/s] 15%|█▌ | 654/4250 [02:56<13:44, 4.36it/s] 15%|█▌ | 655/4250 [02:56<13:15, 4.52it/s] 15%|█▌ | 656/4250 [02:57<15:48, 3.79it/s] 15%|█▌ | 657/4250 [02:57<17:41, 3.39it/s] 15%|█▌ | 658/4250 [02:57<16:11, 3.70it/s] 16%|█▌ | 659/4250 [02:57<14:58, 4.00it/s] 16%|█▌ | 660/4250 [02:58<16:40, 3.59it/s] 16%|█▌ | 661/4250 [02:58<14:58, 4.00it/s] 16%|█▌ | 662/4250 [02:58<16:41, 3.58it/s] 16%|█▌ | 663/4250 [02:59<14:59, 3.99it/s] 16%|█▌ | 664/4250 [02:59<14:11, 4.21it/s] 16%|█▌ | 665/4250 [02:59<12:48, 4.67it/s] 16%|█▌ | 666/4250 [02:59<12:26, 4.80it/s] 16%|█▌ | 667/4250 [02:59<11:47, 5.06it/s] 16%|█▌ | 668/4250 [02:59<11:30, 5.19it/s] 16%|█▌ | 669/4250 [03:00<12:43, 4.69it/s] 16%|█▌ | 670/4250 [03:00<14:03, 4.24it/s] 16%|█▌ | 671/4250 [03:00<15:01, 3.97it/s] 16%|█▌ | 672/4250 [03:00<13:59, 4.26it/s] 16%|█▌ | 673/4250 [03:01<12:43, 4.69it/s] 16%|█▌ | 674/4250 [03:01<12:21, 4.82it/s] 16%|█▌ | 675/4250 [03:01<12:53, 4.62it/s] 16%|█▌ | 676/4250 [03:01<13:08, 4.53it/s] 16%|█▌ | 677/4250 [03:02<13:17, 4.48it/s] 16%|█▌ | 678/4250 [03:02<12:17, 4.84it/s] 16%|█▌ | 679/4250 [03:02<14:44, 4.04it/s] 16%|█▌ | 680/4250 [03:02<13:50, 4.30it/s] 16%|█▌ | 681/4250 [03:02<14:10, 4.20it/s] 16%|█▌ | 682/4250 [03:03<14:38, 4.06it/s] 16%|█▌ | 683/4250 [03:03<13:41, 4.34it/s] 16%|█▌ | 684/4250 [03:03<13:34, 4.38it/s] 16%|█▌ | 685/4250 [03:03<13:11, 4.50it/s] 16%|█▌ | 686/4250 [03:04<12:42, 4.67it/s] 16%|█▌ | 687/4250 [03:04<13:14, 4.49it/s] 16%|█▌ | 688/4250 [03:04<14:13, 4.17it/s] 16%|█▌ | 689/4250 [03:04<12:27, 4.77it/s] 16%|█▌ | 690/4250 [03:05<13:31, 4.39it/s] 16%|█▋ | 691/4250 [03:05<15:34, 3.81it/s] 16%|█▋ | 692/4250 [03:05<16:13, 3.65it/s] 16%|█▋ | 693/4250 [03:05<15:02, 3.94it/s] 16%|█▋ | 694/4250 [03:06<16:01, 3.70it/s] 16%|█▋ | 695/4250 [03:06<14:32, 4.07it/s] 16%|█▋ | 696/4250 [03:06<13:14, 4.47it/s] 16%|█▋ | 697/4250 [03:06<12:22, 4.78it/s] 16%|█▋ | 698/4250 [03:06<11:47, 5.02it/s] 16%|█▋ | 699/4250 [03:07<11:26, 5.18it/s] 16%|█▋ | 700/4250 [03:07<11:29, 5.15it/s] 16%|█▋ | 701/4250 [03:07<11:12, 5.28it/s] 17%|█▋ | 702/4250 [03:07<11:36, 5.09it/s] 17%|█▋ | 703/4250 [03:07<12:10, 4.86it/s] 17%|█▋ | 704/4250 [03:08<12:37, 4.68it/s] 17%|█▋ | 705/4250 [03:08<13:36, 4.34it/s] 17%|█▋ | 706/4250 [03:08<12:55, 4.57it/s] 17%|█▋ | 707/4250 [03:08<12:00, 4.92it/s] 17%|█▋ | 708/4250 [03:08<12:57, 4.56it/s] 17%|█▋ | 709/4250 [03:09<12:26, 4.74it/s] 17%|█▋ | 710/4250 [03:09<13:22, 4.41it/s] 17%|█▋ | 711/4250 [03:09<14:00, 4.21it/s] 17%|█▋ | 712/4250 [03:09<12:40, 4.65it/s] 17%|█▋ | 713/4250 [03:10<14:16, 4.13it/s] 17%|█▋ | 714/4250 [03:10<13:43, 4.30it/s] 17%|█▋ | 715/4250 [03:10<12:43, 4.63it/s] 17%|█▋ | 716/4250 [03:10<12:39, 4.65it/s] 17%|█▋ | 717/4250 [03:11<14:06, 4.17it/s] 17%|█▋ | 718/4250 [03:11<13:25, 4.39it/s] 17%|█▋ | 719/4250 [03:11<13:10, 4.46it/s] 17%|█▋ | 720/4250 [03:11<13:16, 4.43it/s] 17%|█▋ | 721/4250 [03:11<12:13, 4.81it/s] 17%|█▋ | 722/4250 [03:12<14:10, 4.15it/s] 17%|█▋ | 723/4250 [03:12<13:25, 4.38it/s] 17%|█▋ | 724/4250 [03:12<16:19, 3.60it/s] 17%|█▋ | 725/4250 [03:13<15:13, 3.86it/s] 17%|█▋ | 726/4250 [03:13<14:18, 4.10it/s] 17%|█▋ | 727/4250 [03:13<13:41, 4.29it/s] 17%|█▋ | 728/4250 [03:13<12:55, 4.54it/s] 17%|█▋ | 729/4250 [03:13<14:45, 3.98it/s] 17%|█▋ | 730/4250 [03:14<13:43, 4.27it/s] 17%|█▋ | 731/4250 [03:14<13:08, 4.46it/s] 17%|█▋ | 732/4250 [03:14<13:43, 4.27it/s] 17%|█▋ | 733/4250 [03:14<13:26, 4.36it/s] 17%|█▋ | 734/4250 [03:15<13:19, 4.40it/s] 17%|█▋ | 735/4250 [03:15<14:34, 4.02it/s] 17%|█▋ | 736/4250 [03:15<14:09, 4.14it/s] 17%|█▋ | 737/4250 [03:15<13:57, 4.19it/s] 17%|█▋ | 738/4250 [03:15<13:10, 4.44it/s] 17%|█▋ | 739/4250 [03:16<13:30, 4.33it/s] 17%|█▋ | 740/4250 [03:16<12:58, 4.51it/s] 17%|█▋ | 741/4250 [03:16<13:08, 4.45it/s] 17%|█▋ | 742/4250 [03:16<13:18, 4.39it/s] 17%|█▋ | 743/4250 [03:17<12:38, 4.63it/s] 18%|█▊ | 744/4250 [03:17<13:18, 4.39it/s] 18%|█▊ | 745/4250 [03:17<13:48, 4.23it/s] 18%|█▊ | 746/4250 [03:17<13:11, 4.43it/s] 18%|█▊ | 747/4250 [03:18<12:58, 4.50it/s] 18%|█▊ | 748/4250 [03:18<13:21, 4.37it/s] 18%|█▊ | 749/4250 [03:18<17:09, 3.40it/s] 18%|█▊ | 750/4250 [03:18<15:33, 3.75it/s] 18%|█▊ | 751/4250 [03:19<15:17, 3.81it/s] 18%|█▊ | 752/4250 [03:19<13:35, 4.29it/s] 18%|█▊ | 753/4250 [03:19<13:38, 4.27it/s] 18%|█▊ | 754/4250 [03:19<14:30, 4.01it/s] 18%|█▊ | 755/4250 [03:20<13:32, 4.30it/s] 18%|█▊ | 756/4250 [03:20<12:43, 4.58it/s] 18%|█▊ | 757/4250 [03:20<12:20, 4.72it/s] 18%|█▊ | 758/4250 [03:20<13:19, 4.37it/s] 18%|█▊ | 759/4250 [03:21<15:10, 3.84it/s] 18%|█▊ | 760/4250 [03:21<14:58, 3.88it/s] 18%|█▊ | 761/4250 [03:21<14:32, 4.00it/s] 18%|█▊ | 762/4250 [03:21<14:27, 4.02it/s] 18%|█▊ | 763/4250 [03:22<15:21, 3.79it/s] 18%|█▊ | 764/4250 [03:22<14:21, 4.05it/s] 18%|█▊ | 765/4250 [03:22<16:37, 3.50it/s] 18%|█▊ | 766/4250 [03:22<14:22, 4.04it/s] 18%|█▊ | 767/4250 [03:22<13:41, 4.24it/s] 18%|█▊ | 768/4250 [03:23<15:25, 3.76it/s] 18%|█▊ | 769/4250 [03:23<14:05, 4.12it/s] 18%|█▊ | 770/4250 [03:23<14:05, 4.12it/s] 18%|█▊ | 771/4250 [03:23<12:38, 4.59it/s] 18%|█▊ | 772/4250 [03:24<11:57, 4.85it/s] 18%|█▊ | 773/4250 [03:24<11:29, 5.04it/s] 18%|█▊ | 774/4250 [03:24<11:34, 5.01it/s] 18%|█▊ | 775/4250 [03:24<11:36, 4.99it/s] 18%|█▊ | 776/4250 [03:24<11:33, 5.01it/s] 18%|█▊ | 777/4250 [03:25<12:59, 4.46it/s] 18%|█▊ | 778/4250 [03:25<12:51, 4.50it/s] 18%|█▊ | 779/4250 [03:25<11:43, 4.93it/s] 18%|█▊ | 780/4250 [03:25<13:25, 4.31it/s] 18%|█▊ | 781/4250 [03:26<12:45, 4.53it/s] 18%|█▊ | 782/4250 [03:26<11:59, 4.82it/s] 18%|█▊ | 783/4250 [03:26<13:10, 4.39it/s] 18%|█▊ | 784/4250 [03:26<12:58, 4.45it/s] 18%|█▊ | 785/4250 [03:26<12:13, 4.73it/s] 18%|█▊ | 786/4250 [03:27<11:53, 4.85it/s] 19%|█▊ | 787/4250 [03:27<12:03, 4.79it/s] 19%|█▊ | 788/4250 [03:27<12:35, 4.58it/s] 19%|█▊ | 789/4250 [03:27<12:08, 4.75it/s] 19%|█▊ | 790/4250 [03:27<11:59, 4.81it/s] 19%|█▊ | 791/4250 [03:28<11:15, 5.12it/s] 19%|█▊ | 792/4250 [03:28<11:03, 5.21it/s] 19%|█▊ | 793/4250 [03:28<11:23, 5.06it/s] 19%|█▊ | 794/4250 [03:28<11:03, 5.21it/s] 19%|█▊ | 795/4250 [03:28<12:03, 4.77it/s] 19%|█▊ | 796/4250 [03:29<11:55, 4.83it/s] 19%|█▉ | 797/4250 [03:29<12:21, 4.66it/s] 19%|█▉ | 798/4250 [03:29<12:15, 4.70it/s] 19%|█▉ | 799/4250 [03:30<17:09, 3.35it/s] 19%|█▉ | 800/4250 [03:30<15:49, 3.63it/s] 19%|█▉ | 801/4250 [03:30<14:19, 4.01it/s] 19%|█▉ | 802/4250 [03:30<13:12, 4.35it/s] 19%|█▉ | 803/4250 [03:30<12:13, 4.70it/s] 19%|█▉ | 804/4250 [03:31<12:23, 4.63it/s] 19%|█▉ | 805/4250 [03:31<15:41, 3.66it/s] 19%|█▉ | 806/4250 [03:31<19:26, 2.95it/s] 19%|█▉ | 807/4250 [03:32<19:31, 2.94it/s] 19%|█▉ | 808/4250 [03:32<17:39, 3.25it/s] 19%|█▉ | 809/4250 [03:32<16:33, 3.46it/s] 19%|█▉ | 810/4250 [03:32<14:33, 3.94it/s] 19%|█▉ | 811/4250 [03:33<13:09, 4.36it/s] 19%|█▉ | 812/4250 [03:33<13:11, 4.35it/s] 19%|█▉ | 813/4250 [03:33<11:59, 4.78it/s] 19%|█▉ | 814/4250 [03:33<12:16, 4.67it/s] 19%|█▉ | 815/4250 [03:34<13:25, 4.27it/s] 19%|█▉ | 816/4250 [03:34<13:30, 4.24it/s] 19%|█▉ | 817/4250 [03:34<12:56, 4.42it/s] 19%|█▉ | 818/4250 [03:35<21:31, 2.66it/s] 19%|█▉ | 819/4250 [03:35<18:20, 3.12it/s] 19%|█▉ | 820/4250 [03:35<16:39, 3.43it/s] 19%|█▉ | 821/4250 [03:35<14:49, 3.86it/s] 19%|█▉ | 822/4250 [03:36<14:33, 3.92it/s] 19%|█▉ | 823/4250 [03:36<16:10, 3.53it/s] 19%|█▉ | 824/4250 [03:36<14:52, 3.84it/s] 19%|█▉ | 825/4250 [03:36<15:12, 3.75it/s] 19%|█▉ | 826/4250 [03:37<13:23, 4.26it/s] 19%|█▉ | 827/4250 [03:37<13:23, 4.26it/s] 19%|█▉ | 828/4250 [03:37<12:12, 4.67it/s] 20%|█▉ | 829/4250 [03:37<13:44, 4.15it/s] 20%|█▉ | 830/4250 [03:38<14:13, 4.01it/s] 20%|█▉ | 831/4250 [03:38<13:38, 4.18it/s] 20%|█▉ | 832/4250 [03:38<13:24, 4.25it/s] 20%|█▉ | 833/4250 [03:38<12:46, 4.46it/s] 20%|█▉ | 834/4250 [03:38<12:18, 4.62it/s] 20%|█▉ | 835/4250 [03:39<13:31, 4.21it/s] 20%|█▉ | 836/4250 [03:39<19:43, 2.89it/s] 20%|█▉ | 837/4250 [03:39<16:56, 3.36it/s] 20%|█▉ | 838/4250 [03:40<15:19, 3.71it/s] 20%|█▉ | 839/4250 [03:40<15:53, 3.58it/s] 20%|█▉ | 840/4250 [03:40<16:13, 3.50it/s] 20%|█▉ | 841/4250 [03:40<15:17, 3.72it/s] 20%|█▉ | 842/4250 [03:41<17:09, 3.31it/s] 20%|█▉ | 843/4250 [03:41<17:20, 3.27it/s] 20%|█▉ | 844/4250 [03:41<15:49, 3.59it/s] 20%|█▉ | 845/4250 [03:42<15:43, 3.61it/s] 20%|█▉ | 846/4250 [03:42<15:03, 3.77it/s] 20%|█▉ | 847/4250 [03:42<14:21, 3.95it/s] 20%|█▉ | 848/4250 [03:42<14:42, 3.85it/s] 20%|█▉ | 849/4250 [03:43<14:54, 3.80it/s] 20%|██ | 850/4250 [03:43<13:35, 4.17it/s] 20%|██ | 851/4250 [03:43<12:52, 4.40it/s][INFO|trainer.py:805] 2024-08-30 20:29:32,380 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: tokens, ner_tags, id. If tokens, ner_tags, id are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3788] 2024-08-30 20:29:32,382 >> ***** Running Evaluation ***** [INFO|trainer.py:3790] 2024-08-30 20:29:32,382 >> Num examples = 6810 [INFO|trainer.py:3793] 2024-08-30 20:29:32,382 >> Batch size = 8 {'eval_loss': 0.07383445650339127, 'eval_precision': 0.7233218588640276, 'eval_recall': 0.786616752456715, 'eval_f1': 0.7536426810132258, 'eval_accuracy': 0.9733340656624604, 'eval_runtime': 14.6851, 'eval_samples_per_second': 463.736, 'eval_steps_per_second': 58.018, 'epoch': 1.0} {'loss': 0.0996, 'grad_norm': 1.1428656578063965, 'learning_rate': 4.411764705882353e-05, 'epoch': 1.18} 0%| | 0/852 [00:00> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-851 [INFO|configuration_utils.py:472] 2024-08-30 20:29:46,799 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-851/config.json [INFO|modeling_utils.py:2690] 2024-08-30 20:29:48,128 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-851/model.safetensors [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:29:48,129 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-851/tokenizer_config.json [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:29:48,129 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-851/special_tokens_map.json [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:29:50,700 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:29:50,700 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json 20%|██ | 852/4250 [04:02<5:33:39, 5.89s/it] 20%|██ | 853/4250 [04:02<3:56:27, 4.18s/it] 20%|██ | 854/4250 [04:02<2:48:45, 2.98s/it] 20%|██ | 855/4250 [04:03<2:01:43, 2.15s/it] 20%|██ | 856/4250 [04:03<1:30:19, 1.60s/it] 20%|██ | 857/4250 [04:03<1:07:28, 1.19s/it] 20%|██ | 858/4250 [04:04<51:33, 1.10it/s] 20%|██ | 859/4250 [04:04<39:41, 1.42it/s] 20%|██ | 860/4250 [04:04<33:01, 1.71it/s] 20%|██ | 861/4250 [04:04<27:01, 2.09it/s] 20%|██ | 862/4250 [04:04<22:22, 2.52it/s] 20%|██ | 863/4250 [04:05<19:26, 2.90it/s] 20%|██ | 864/4250 [04:05<16:35, 3.40it/s] 20%|██ | 865/4250 [04:05<15:36, 3.61it/s] 20%|██ | 866/4250 [04:05<14:19, 3.94it/s] 20%|██ | 867/4250 [04:06<13:56, 4.05it/s] 20%|██ | 868/4250 [04:06<14:50, 3.80it/s] 20%|██ | 869/4250 [04:06<14:02, 4.02it/s] 20%|██ | 870/4250 [04:06<14:22, 3.92it/s] 20%|██ | 871/4250 [04:07<14:52, 3.78it/s] 21%|██ | 872/4250 [04:07<14:39, 3.84it/s] 21%|██ | 873/4250 [04:07<15:03, 3.74it/s] 21%|██ | 874/4250 [04:07<14:24, 3.91it/s] 21%|██ | 875/4250 [04:08<13:07, 4.28it/s] 21%|██ | 876/4250 [04:08<12:42, 4.43it/s] 21%|██ | 877/4250 [04:08<12:10, 4.62it/s] 21%|██ | 878/4250 [04:08<11:23, 4.93it/s] 21%|██ | 879/4250 [04:08<10:50, 5.19it/s] 21%|██ | 880/4250 [04:09<13:23, 4.19it/s] 21%|██ | 881/4250 [04:09<13:29, 4.16it/s] 21%|██ | 882/4250 [04:09<13:03, 4.30it/s] 21%|██ | 883/4250 [04:09<12:50, 4.37it/s] 21%|██ | 884/4250 [04:10<14:27, 3.88it/s] 21%|██ | 885/4250 [04:10<13:32, 4.14it/s] 21%|██ | 886/4250 [04:10<12:44, 4.40it/s] 21%|██ | 887/4250 [04:10<13:23, 4.18it/s] 21%|██ | 888/4250 [04:11<13:39, 4.10it/s] 21%|██ | 889/4250 [04:11<17:51, 3.14it/s] 21%|██ | 890/4250 [04:11<17:04, 3.28it/s] 21%|██ | 891/4250 [04:12<15:03, 3.72it/s] 21%|██ | 892/4250 [04:12<14:24, 3.88it/s] 21%|██ | 893/4250 [04:12<15:29, 3.61it/s] 21%|██ | 894/4250 [04:12<13:46, 4.06it/s] 21%|██ | 895/4250 [04:12<13:44, 4.07it/s] 21%|██ | 896/4250 [04:13<13:33, 4.12it/s] 21%|██ | 897/4250 [04:13<12:54, 4.33it/s] 21%|██ | 898/4250 [04:13<12:45, 4.38it/s] 21%|██ | 899/4250 [04:13<14:34, 3.83it/s] 21%|██ | 900/4250 [04:14<15:34, 3.59it/s] 21%|██ | 901/4250 [04:14<18:51, 2.96it/s] 21%|██ | 902/4250 [04:15<17:19, 3.22it/s] 21%|██ | 903/4250 [04:15<16:18, 3.42it/s] 21%|██▏ | 904/4250 [04:15<15:27, 3.61it/s] 21%|██▏ | 905/4250 [04:15<14:43, 3.78it/s] 21%|██▏ | 906/4250 [04:15<13:48, 4.04it/s] 21%|██▏ | 907/4250 [04:16<15:17, 3.64it/s] 21%|██▏ | 908/4250 [04:16<14:41, 3.79it/s] 21%|██▏ | 909/4250 [04:16<14:02, 3.97it/s] 21%|██▏ | 910/4250 [04:17<13:54, 4.00it/s] 21%|██▏ | 911/4250 [04:17<13:16, 4.19it/s] 21%|██▏ | 912/4250 [04:17<12:58, 4.29it/s] 21%|██▏ | 913/4250 [04:17<16:01, 3.47it/s] 22%|██▏ | 914/4250 [04:18<14:20, 3.88it/s] 22%|██▏ | 915/4250 [04:18<15:46, 3.52it/s] 22%|██▏ | 916/4250 [04:19<22:00, 2.53it/s] 22%|██▏ | 917/4250 [04:19<19:03, 2.91it/s] 22%|██▏ | 918/4250 [04:19<19:11, 2.89it/s] 22%|██▏ | 919/4250 [04:19<17:36, 3.15it/s] 22%|██▏ | 920/4250 [04:20<15:46, 3.52it/s] 22%|██▏ | 921/4250 [04:20<14:31, 3.82it/s] 22%|██▏ | 922/4250 [04:20<13:17, 4.18it/s] 22%|██▏ | 923/4250 [04:20<15:03, 3.68it/s] 22%|██▏ | 924/4250 [04:21<13:44, 4.03it/s] 22%|██▏ | 925/4250 [04:21<12:38, 4.38it/s] 22%|██▏ | 926/4250 [04:21<13:20, 4.15it/s] 22%|██▏ | 927/4250 [04:21<12:15, 4.52it/s] 22%|██▏ | 928/4250 [04:21<11:28, 4.82it/s] 22%|██▏ | 929/4250 [04:22<10:57, 5.05it/s] 22%|██▏ | 930/4250 [04:22<11:29, 4.82it/s] 22%|██▏ | 931/4250 [04:22<11:42, 4.73it/s] 22%|██▏ | 932/4250 [04:22<11:33, 4.78it/s] 22%|██▏ | 933/4250 [04:22<11:56, 4.63it/s] 22%|██▏ | 934/4250 [04:23<11:57, 4.62it/s] 22%|██▏ | 935/4250 [04:23<13:38, 4.05it/s] 22%|██▏ | 936/4250 [04:23<12:45, 4.33it/s] 22%|██▏ | 937/4250 [04:23<13:20, 4.14it/s] 22%|██▏ | 938/4250 [04:24<12:41, 4.35it/s] 22%|██▏ | 939/4250 [04:24<12:20, 4.47it/s] 22%|██▏ | 940/4250 [04:24<12:31, 4.40it/s] 22%|██▏ | 941/4250 [04:24<12:45, 4.32it/s] 22%|██▏ | 942/4250 [04:24<12:25, 4.44it/s] 22%|██▏ | 943/4250 [04:25<11:23, 4.84it/s] 22%|██▏ | 944/4250 [04:25<11:46, 4.68it/s] 22%|██▏ | 945/4250 [04:25<11:30, 4.79it/s] 22%|██▏ | 946/4250 [04:25<12:02, 4.57it/s] 22%|██▏ | 947/4250 [04:25<11:12, 4.91it/s] 22%|██▏ | 948/4250 [04:26<10:56, 5.03it/s] 22%|██▏ | 949/4250 [04:26<11:18, 4.87it/s] 22%|██▏ | 950/4250 [04:26<11:17, 4.87it/s] 22%|██▏ | 951/4250 [04:26<11:18, 4.86it/s] 22%|██▏ | 952/4250 [04:27<12:36, 4.36it/s] 22%|██▏ | 953/4250 [04:27<13:13, 4.15it/s] 22%|██▏ | 954/4250 [04:27<12:14, 4.48it/s] 22%|██▏ | 955/4250 [04:28<18:41, 2.94it/s] 22%|██▏ | 956/4250 [04:28<16:57, 3.24it/s] 23%|██▎ | 957/4250 [04:28<15:22, 3.57it/s] 23%|██▎ | 958/4250 [04:28<14:24, 3.81it/s] 23%|██▎ | 959/4250 [04:29<15:27, 3.55it/s] 23%|██▎ | 960/4250 [04:29<14:01, 3.91it/s] 23%|██▎ | 961/4250 [04:29<16:37, 3.30it/s] 23%|██▎ | 962/4250 [04:29<15:29, 3.54it/s] 23%|██▎ | 963/4250 [04:30<15:55, 3.44it/s] 23%|██▎ | 964/4250 [04:30<20:01, 2.73it/s] 23%|██▎ | 965/4250 [04:31<17:02, 3.21it/s] 23%|██▎ | 966/4250 [04:31<14:21, 3.81it/s] 23%|██▎ | 967/4250 [04:31<14:20, 3.81it/s] 23%|██▎ | 968/4250 [04:31<12:35, 4.34it/s] 23%|██▎ | 969/4250 [04:31<12:28, 4.39it/s] 23%|██▎ | 970/4250 [04:32<12:41, 4.30it/s] 23%|██▎ | 971/4250 [04:32<12:14, 4.46it/s] 23%|██▎ | 972/4250 [04:32<11:57, 4.57it/s] 23%|██▎ | 973/4250 [04:32<11:07, 4.91it/s] 23%|██▎ | 974/4250 [04:32<11:59, 4.55it/s] 23%|██▎ | 975/4250 [04:33<12:04, 4.52it/s] 23%|██▎ | 976/4250 [04:33<12:29, 4.37it/s] 23%|██▎ | 977/4250 [04:33<13:49, 3.94it/s] 23%|██▎ | 978/4250 [04:33<13:15, 4.11it/s] 23%|██▎ | 979/4250 [04:34<12:09, 4.48it/s] 23%|██▎ | 980/4250 [04:34<12:59, 4.19it/s] 23%|██▎ | 981/4250 [04:34<12:15, 4.45it/s] 23%|██▎ | 982/4250 [04:34<11:48, 4.61it/s] 23%|██▎ | 983/4250 [04:35<13:19, 4.09it/s] 23%|██▎ | 984/4250 [04:35<12:44, 4.27it/s] 23%|██▎ | 985/4250 [04:35<14:51, 3.66it/s] 23%|██▎ | 986/4250 [04:35<15:05, 3.60it/s] 23%|██▎ | 987/4250 [04:36<14:49, 3.67it/s] 23%|██▎ | 988/4250 [04:36<13:38, 3.99it/s] 23%|██▎ | 989/4250 [04:36<12:12, 4.45it/s] 23%|██▎ | 990/4250 [04:36<11:58, 4.54it/s] 23%|██▎ | 991/4250 [04:36<11:53, 4.57it/s] 23%|██▎ | 992/4250 [04:37<11:14, 4.83it/s] 23%|██▎ | 993/4250 [04:37<13:48, 3.93it/s] 23%|██▎ | 994/4250 [04:37<14:59, 3.62it/s] 23%|██▎ | 995/4250 [04:38<15:30, 3.50it/s] 23%|██▎ | 996/4250 [04:38<13:53, 3.90it/s] 23%|██▎ | 997/4250 [04:38<15:04, 3.60it/s] 23%|██▎ | 998/4250 [04:38<13:40, 3.96it/s] 24%|██▎ | 999/4250 [04:39<14:17, 3.79it/s] 24%|██▎ | 1000/4250 [04:39<13:16, 4.08it/s] 24%|██▎ | 1000/4250 [04:39<13:16, 4.08it/s] 24%|██▎ | 1001/4250 [04:39<14:07, 3.84it/s] 24%|██▎ | 1002/4250 [04:39<13:34, 3.99it/s] 24%|██▎ | 1003/4250 [04:40<14:53, 3.63it/s] 24%|██▎ | 1004/4250 [04:40<14:03, 3.85it/s] 24%|██▎ | 1005/4250 [04:40<12:32, 4.31it/s] 24%|██▎ | 1006/4250 [04:40<12:05, 4.47it/s] 24%|██▎ | 1007/4250 [04:41<11:55, 4.53it/s] 24%|██▎ | 1008/4250 [04:41<12:02, 4.49it/s] 24%|██▎ | 1009/4250 [04:41<12:14, 4.41it/s] 24%|██▍ | 1010/4250 [04:41<12:00, 4.50it/s] 24%|██▍ | 1011/4250 [04:41<11:45, 4.59it/s] 24%|██▍ | 1012/4250 [04:42<12:28, 4.32it/s] 24%|██▍ | 1013/4250 [04:42<11:59, 4.50it/s] 24%|██▍ | 1014/4250 [04:42<11:29, 4.69it/s] 24%|██▍ | 1015/4250 [04:42<12:16, 4.39it/s] 24%|██▍ | 1016/4250 [04:43<12:57, 4.16it/s] 24%|██▍ | 1017/4250 [04:43<12:16, 4.39it/s] 24%|██▍ | 1018/4250 [04:43<11:46, 4.57it/s] 24%|██▍ | 1019/4250 [04:43<10:34, 5.09it/s] 24%|██▍ | 1020/4250 [04:43<10:14, 5.25it/s] 24%|██▍ | 1021/4250 [04:44<11:10, 4.82it/s] 24%|██▍ | 1022/4250 [04:44<14:03, 3.83it/s] 24%|██▍ | 1023/4250 [04:44<14:35, 3.69it/s] 24%|██▍ | 1024/4250 [04:44<13:30, 3.98it/s] 24%|██▍ | 1025/4250 [04:45<12:30, 4.30it/s] 24%|██▍ | 1026/4250 [04:45<12:44, 4.22it/s] 24%|██▍ | 1027/4250 [04:45<12:10, 4.41it/s] 24%|██▍ | 1028/4250 [04:45<12:56, 4.15it/s] 24%|██▍ | 1029/4250 [04:46<12:00, 4.47it/s] 24%|██▍ | 1030/4250 [04:46<11:22, 4.72it/s] 24%|██▍ | 1031/4250 [04:46<15:14, 3.52it/s] 24%|██▍ | 1032/4250 [04:46<13:59, 3.83it/s] 24%|██▍ | 1033/4250 [04:47<12:55, 4.15it/s] 24%|██▍ | 1034/4250 [04:47<12:45, 4.20it/s] 24%|██▍ | 1035/4250 [04:47<12:03, 4.45it/s] 24%|██▍ | 1036/4250 [04:47<11:35, 4.62it/s] 24%|██▍ | 1037/4250 [04:47<11:29, 4.66it/s] 24%|██▍ | 1038/4250 [04:48<11:58, 4.47it/s] 24%|██▍ | 1039/4250 [04:48<12:56, 4.13it/s] 24%|██▍ | 1040/4250 [04:48<12:32, 4.27it/s] 24%|██▍ | 1041/4250 [04:48<14:19, 3.73it/s] 25%|██▍ | 1042/4250 [04:49<13:58, 3.83it/s] 25%|██▍ | 1043/4250 [04:49<15:42, 3.40it/s] 25%|██▍ | 1044/4250 [04:49<14:04, 3.80it/s] 25%|██▍ | 1045/4250 [04:50<13:28, 3.97it/s] 25%|██▍ | 1046/4250 [04:50<13:04, 4.09it/s] 25%|██▍ | 1047/4250 [04:50<11:57, 4.47it/s] 25%|██▍ | 1048/4250 [04:50<11:08, 4.79it/s] 25%|██▍ | 1049/4250 [04:50<11:10, 4.78it/s] 25%|██▍ | 1050/4250 [04:51<11:01, 4.84it/s] 25%|██▍ | 1051/4250 [04:51<10:28, 5.09it/s] 25%|██▍ | 1052/4250 [04:51<10:06, 5.27it/s] 25%|██▍ | 1053/4250 [04:51<11:28, 4.64it/s] 25%|██▍ | 1054/4250 [04:51<11:01, 4.83it/s] 25%|██▍ | 1055/4250 [04:51<10:33, 5.04it/s] 25%|██▍ | 1056/4250 [04:52<10:33, 5.05it/s] 25%|██▍ | 1057/4250 [04:52<12:04, 4.41it/s] 25%|██▍ | 1058/4250 [04:52<11:19, 4.70it/s] 25%|██▍ | 1059/4250 [04:52<11:17, 4.71it/s] 25%|██▍ | 1060/4250 [04:53<10:49, 4.91it/s] 25%|██▍ | 1061/4250 [04:53<11:53, 4.47it/s] 25%|██▍ | 1062/4250 [04:53<13:35, 3.91it/s] 25%|██▌ | 1063/4250 [04:53<12:51, 4.13it/s] 25%|██▌ | 1064/4250 [04:54<16:17, 3.26it/s] 25%|██▌ | 1065/4250 [04:54<14:34, 3.64it/s] 25%|██▌ | 1066/4250 [04:54<12:39, 4.19it/s] 25%|██▌ | 1067/4250 [04:54<12:20, 4.30it/s] 25%|██▌ | 1068/4250 [04:55<12:27, 4.26it/s] 25%|██▌ | 1069/4250 [04:55<12:13, 4.34it/s] 25%|██▌ | 1070/4250 [04:55<11:29, 4.61it/s] 25%|██▌ | 1071/4250 [04:55<12:50, 4.13it/s] 25%|██▌ | 1072/4250 [04:56<12:33, 4.22it/s] 25%|██▌ | 1073/4250 [04:56<14:21, 3.69it/s] 25%|██▌ | 1074/4250 [04:56<13:43, 3.86it/s] 25%|██▌ | 1075/4250 [04:56<13:25, 3.94it/s] 25%|██▌ | 1076/4250 [04:57<12:49, 4.13it/s] 25%|██▌ | 1077/4250 [04:57<12:08, 4.36it/s] 25%|██▌ | 1078/4250 [04:57<11:17, 4.68it/s] 25%|██▌ | 1079/4250 [04:57<11:06, 4.76it/s] 25%|██▌ | 1080/4250 [04:57<10:34, 5.00it/s] 25%|██▌ | 1081/4250 [04:58<11:46, 4.48it/s] 25%|██▌ | 1082/4250 [04:58<11:39, 4.53it/s] 25%|██▌ | 1083/4250 [04:58<11:02, 4.78it/s] 26%|██▌ | 1084/4250 [04:58<11:01, 4.79it/s] 26%|██▌ | 1085/4250 [04:59<11:44, 4.50it/s] 26%|██▌ | 1086/4250 [04:59<11:22, 4.63it/s] 26%|██▌ | 1087/4250 [04:59<11:08, 4.73it/s] 26%|██▌ | 1088/4250 [04:59<11:28, 4.59it/s] 26%|██▌ | 1089/4250 [04:59<11:20, 4.64it/s] 26%|██▌ | 1090/4250 [05:00<10:48, 4.87it/s] 26%|██▌ | 1091/4250 [05:00<11:48, 4.46it/s] 26%|██▌ | 1092/4250 [05:00<12:23, 4.25it/s] 26%|██▌ | 1093/4250 [05:00<11:26, 4.60it/s] 26%|██▌ | 1094/4250 [05:00<10:57, 4.80it/s] 26%|██▌ | 1095/4250 [05:01<11:45, 4.47it/s] 26%|██▌ | 1096/4250 [05:01<11:10, 4.70it/s] 26%|██▌ | 1097/4250 [05:01<10:52, 4.83it/s] 26%|██▌ | 1098/4250 [05:01<11:06, 4.73it/s] 26%|██▌ | 1099/4250 [05:01<10:32, 4.98it/s] 26%|██▌ | 1100/4250 [05:02<09:59, 5.25it/s] 26%|██▌ | 1101/4250 [05:02<11:03, 4.75it/s] 26%|██▌ | 1102/4250 [05:02<13:56, 3.76it/s] 26%|██▌ | 1103/4250 [05:03<13:44, 3.82it/s] 26%|██▌ | 1104/4250 [05:03<13:05, 4.01it/s] 26%|██▌ | 1105/4250 [05:03<12:21, 4.24it/s] 26%|██▌ | 1106/4250 [05:03<11:22, 4.61it/s] 26%|██▌ | 1107/4250 [05:03<11:15, 4.65it/s] 26%|██▌ | 1108/4250 [05:04<11:20, 4.62it/s] 26%|██▌ | 1109/4250 [05:04<11:20, 4.61it/s] 26%|██▌ | 1110/4250 [05:04<10:59, 4.76it/s] 26%|██▌ | 1111/4250 [05:04<13:47, 3.79it/s] 26%|██▌ | 1112/4250 [05:05<12:07, 4.31it/s] 26%|██▌ | 1113/4250 [05:05<12:54, 4.05it/s] 26%|██▌ | 1114/4250 [05:05<11:35, 4.51it/s] 26%|██▌ | 1115/4250 [05:05<13:21, 3.91it/s] 26%|██▋ | 1116/4250 [05:06<16:14, 3.22it/s] 26%|██▋ | 1117/4250 [05:06<14:31, 3.59it/s] 26%|██▋ | 1118/4250 [05:06<13:52, 3.76it/s] 26%|██▋ | 1119/4250 [05:06<13:31, 3.86it/s] 26%|██▋ | 1120/4250 [05:07<14:42, 3.55it/s] 26%|██▋ | 1121/4250 [05:07<13:31, 3.86it/s] 26%|██▋ | 1122/4250 [05:07<12:12, 4.27it/s] 26%|██▋ | 1123/4250 [05:07<10:52, 4.79it/s] 26%|██▋ | 1124/4250 [05:07<10:53, 4.78it/s] 26%|██▋ | 1125/4250 [05:08<11:49, 4.40it/s] 26%|██▋ | 1126/4250 [05:09<19:50, 2.62it/s] 27%|██▋ | 1127/4250 [05:09<16:46, 3.10it/s] 27%|██▋ | 1128/4250 [05:09<15:07, 3.44it/s] 27%|██▋ | 1129/4250 [05:09<13:57, 3.73it/s] 27%|██▋ | 1130/4250 [05:09<12:16, 4.24it/s] 27%|██▋ | 1131/4250 [05:09<11:54, 4.37it/s] 27%|██▋ | 1132/4250 [05:10<11:37, 4.47it/s] 27%|██▋ | 1133/4250 [05:10<11:13, 4.63it/s] 27%|██▋ | 1134/4250 [05:10<11:30, 4.51it/s] 27%|██▋ | 1135/4250 [05:10<11:02, 4.70it/s] 27%|██▋ | 1136/4250 [05:11<10:53, 4.77it/s] 27%|██▋ | 1137/4250 [05:11<10:53, 4.76it/s] 27%|██▋ | 1138/4250 [05:11<10:25, 4.98it/s] 27%|██▋ | 1139/4250 [05:11<11:44, 4.41it/s] 27%|██▋ | 1140/4250 [05:12<14:07, 3.67it/s] 27%|██▋ | 1141/4250 [05:12<13:03, 3.97it/s] 27%|██▋ | 1142/4250 [05:12<12:14, 4.23it/s] 27%|██▋ | 1143/4250 [05:12<12:36, 4.11it/s] 27%|██▋ | 1144/4250 [05:12<12:09, 4.26it/s] 27%|██▋ | 1145/4250 [05:13<12:06, 4.27it/s] 27%|██▋ | 1146/4250 [05:13<12:04, 4.28it/s] 27%|██▋ | 1147/4250 [05:13<11:05, 4.66it/s] 27%|██▋ | 1148/4250 [05:13<10:33, 4.90it/s] 27%|██▋ | 1149/4250 [05:14<12:34, 4.11it/s] 27%|██▋ | 1150/4250 [05:14<11:30, 4.49it/s] 27%|██▋ | 1151/4250 [05:14<10:55, 4.72it/s] 27%|██▋ | 1152/4250 [05:14<10:49, 4.77it/s] 27%|██▋ | 1153/4250 [05:14<11:38, 4.43it/s] 27%|██▋ | 1154/4250 [05:15<11:02, 4.67it/s] 27%|██▋ | 1155/4250 [05:15<14:55, 3.46it/s] 27%|██▋ | 1156/4250 [05:15<14:18, 3.60it/s] 27%|██▋ | 1157/4250 [05:16<13:50, 3.73it/s] 27%|██▋ | 1158/4250 [05:16<13:04, 3.94it/s] 27%|██▋ | 1159/4250 [05:16<12:32, 4.11it/s] 27%|██▋ | 1160/4250 [05:16<11:40, 4.41it/s] 27%|██▋ | 1161/4250 [05:16<11:19, 4.55it/s] 27%|██▋ | 1162/4250 [05:17<12:48, 4.02it/s] 27%|██▋ | 1163/4250 [05:17<13:08, 3.92it/s] 27%|██▋ | 1164/4250 [05:17<14:03, 3.66it/s] 27%|██▋ | 1165/4250 [05:18<12:57, 3.97it/s] 27%|██▋ | 1166/4250 [05:18<12:27, 4.12it/s] 27%|██▋ | 1167/4250 [05:18<11:25, 4.50it/s] 27%|██▋ | 1168/4250 [05:18<10:50, 4.74it/s] 28%|██▊ | 1169/4250 [05:18<10:30, 4.89it/s] 28%|██▊ | 1170/4250 [05:18<10:20, 4.97it/s] 28%|██▊ | 1171/4250 [05:19<10:25, 4.92it/s] 28%|██▊ | 1172/4250 [05:19<12:44, 4.03it/s] 28%|██▊ | 1173/4250 [05:19<14:07, 3.63it/s] 28%|██▊ | 1174/4250 [05:20<12:39, 4.05it/s] 28%|██▊ | 1175/4250 [05:20<15:00, 3.42it/s] 28%|██▊ | 1176/4250 [05:20<13:39, 3.75it/s] 28%|██▊ | 1177/4250 [05:20<13:37, 3.76it/s] 28%|██▊ | 1178/4250 [05:21<12:01, 4.26it/s] 28%|██▊ | 1179/4250 [05:21<12:00, 4.27it/s] 28%|██▊ | 1180/4250 [05:21<12:08, 4.21it/s] 28%|██▊ | 1181/4250 [05:21<11:13, 4.56it/s] 28%|██▊ | 1182/4250 [05:22<13:45, 3.72it/s] 28%|██▊ | 1183/4250 [05:22<15:24, 3.32it/s] 28%|██▊ | 1184/4250 [05:22<13:02, 3.92it/s] 28%|██▊ | 1185/4250 [05:22<12:57, 3.94it/s] 28%|██▊ | 1186/4250 [05:23<12:07, 4.21it/s] 28%|██▊ | 1187/4250 [05:23<13:37, 3.75it/s] 28%|██▊ | 1188/4250 [05:23<12:28, 4.09it/s] 28%|██▊ | 1189/4250 [05:23<11:53, 4.29it/s] 28%|██▊ | 1190/4250 [05:24<11:00, 4.63it/s] 28%|██▊ | 1191/4250 [05:24<11:18, 4.51it/s] 28%|██▊ | 1192/4250 [05:24<10:39, 4.78it/s] 28%|██▊ | 1193/4250 [05:24<11:06, 4.58it/s] 28%|██▊ | 1194/4250 [05:24<11:38, 4.38it/s] 28%|██▊ | 1195/4250 [05:25<11:15, 4.52it/s] 28%|██▊ | 1196/4250 [05:25<10:34, 4.82it/s] 28%|██▊ | 1197/4250 [05:25<09:53, 5.15it/s] 28%|██▊ | 1198/4250 [05:25<09:53, 5.15it/s] 28%|██▊ | 1199/4250 [05:25<11:21, 4.48it/s] 28%|██▊ | 1200/4250 [05:26<11:00, 4.62it/s] 28%|██▊ | 1201/4250 [05:26<11:15, 4.51it/s] 28%|██▊ | 1202/4250 [05:26<11:43, 4.33it/s] 28%|██▊ | 1203/4250 [05:26<11:34, 4.39it/s] 28%|██▊ | 1204/4250 [05:27<10:42, 4.74it/s] 28%|██▊ | 1205/4250 [05:27<11:04, 4.58it/s] 28%|██▊ | 1206/4250 [05:27<10:57, 4.63it/s] 28%|██▊ | 1207/4250 [05:27<12:37, 4.02it/s] 28%|██▊ | 1208/4250 [05:28<12:19, 4.12it/s] 28%|██▊ | 1209/4250 [05:28<12:55, 3.92it/s] 28%|██▊ | 1210/4250 [05:28<12:44, 3.98it/s] 28%|██▊ | 1211/4250 [05:28<12:00, 4.22it/s] 29%|██▊ | 1212/4250 [05:29<12:06, 4.18it/s] 29%|██▊ | 1213/4250 [05:29<11:33, 4.38it/s] 29%|██▊ | 1214/4250 [05:29<11:03, 4.58it/s] 29%|██▊ | 1215/4250 [05:29<12:21, 4.09it/s] 29%|██▊ | 1216/4250 [05:29<11:24, 4.43it/s] 29%|██▊ | 1217/4250 [05:30<13:05, 3.86it/s] 29%|██▊ | 1218/4250 [05:30<16:04, 3.14it/s] 29%|██▊ | 1219/4250 [05:30<14:00, 3.61it/s] 29%|██▊ | 1220/4250 [05:31<13:39, 3.70it/s] 29%|██▊ | 1221/4250 [05:31<12:28, 4.05it/s] 29%|██▉ | 1222/4250 [05:31<12:42, 3.97it/s] 29%|██▉ | 1223/4250 [05:31<11:43, 4.30it/s] 29%|██▉ | 1224/4250 [05:31<11:19, 4.46it/s] 29%|██▉ | 1225/4250 [05:32<10:35, 4.76it/s] 29%|██▉ | 1226/4250 [05:32<10:34, 4.77it/s] 29%|██▉ | 1227/4250 [05:32<10:37, 4.74it/s] 29%|██▉ | 1228/4250 [05:32<11:08, 4.52it/s] 29%|██▉ | 1229/4250 [05:33<10:51, 4.63it/s] 29%|██▉ | 1230/4250 [05:33<12:15, 4.10it/s] 29%|██▉ | 1231/4250 [05:33<11:25, 4.40it/s] 29%|██▉ | 1232/4250 [05:33<11:28, 4.38it/s] 29%|██▉ | 1233/4250 [05:33<11:24, 4.41it/s] 29%|██▉ | 1234/4250 [05:34<11:06, 4.53it/s] 29%|██▉ | 1235/4250 [05:34<10:19, 4.86it/s] 29%|██▉ | 1236/4250 [05:34<11:37, 4.32it/s] 29%|██▉ | 1237/4250 [05:34<10:33, 4.76it/s] 29%|██▉ | 1238/4250 [05:35<10:48, 4.65it/s] 29%|██▉ | 1239/4250 [05:35<10:41, 4.69it/s] 29%|██▉ | 1240/4250 [05:35<11:04, 4.53it/s] 29%|██▉ | 1241/4250 [05:35<10:48, 4.64it/s] 29%|██▉ | 1242/4250 [05:35<10:29, 4.78it/s] 29%|██▉ | 1243/4250 [05:36<09:50, 5.09it/s] 29%|██▉ | 1244/4250 [05:36<09:54, 5.06it/s] 29%|██▉ | 1245/4250 [05:36<10:26, 4.80it/s] 29%|██▉ | 1246/4250 [05:36<10:19, 4.85it/s] 29%|██▉ | 1247/4250 [05:36<09:51, 5.08it/s] 29%|██▉ | 1248/4250 [05:37<09:47, 5.11it/s] 29%|██▉ | 1249/4250 [05:37<09:36, 5.21it/s] 29%|██▉ | 1250/4250 [05:37<10:01, 4.99it/s] 29%|██▉ | 1251/4250 [05:37<10:10, 4.91it/s] 29%|██▉ | 1252/4250 [05:37<10:38, 4.69it/s] 29%|██▉ | 1253/4250 [05:38<10:59, 4.54it/s] 30%|██▉ | 1254/4250 [05:38<10:42, 4.66it/s] 30%|██▉ | 1255/4250 [05:38<11:47, 4.23it/s] 30%|██▉ | 1256/4250 [05:38<10:42, 4.66it/s] 30%|██▉ | 1257/4250 [05:39<11:15, 4.43it/s] 30%|██▉ | 1258/4250 [05:39<10:36, 4.70it/s] 30%|██▉ | 1259/4250 [05:39<10:52, 4.58it/s] 30%|██▉ | 1260/4250 [05:39<10:21, 4.81it/s] 30%|██▉ | 1261/4250 [05:39<10:18, 4.83it/s] 30%|██▉ | 1262/4250 [05:40<12:01, 4.14it/s] 30%|██▉ | 1263/4250 [05:40<12:15, 4.06it/s] 30%|██▉ | 1264/4250 [05:40<12:13, 4.07it/s] 30%|██▉ | 1265/4250 [05:41<13:39, 3.64it/s] 30%|██▉ | 1266/4250 [05:41<12:25, 4.00it/s] 30%|██▉ | 1267/4250 [05:41<15:57, 3.12it/s] 30%|██▉ | 1268/4250 [05:41<14:55, 3.33it/s] 30%|██▉ | 1269/4250 [05:42<13:28, 3.69it/s] 30%|██▉ | 1270/4250 [05:42<12:54, 3.85it/s] 30%|██▉ | 1271/4250 [05:42<11:38, 4.26it/s] 30%|██▉ | 1272/4250 [05:42<11:38, 4.27it/s] 30%|██▉ | 1273/4250 [05:43<11:24, 4.35it/s] 30%|██▉ | 1274/4250 [05:43<10:26, 4.75it/s] 30%|███ | 1275/4250 [05:43<12:34, 3.95it/s] 30%|███ | 1276/4250 [05:43<12:29, 3.97it/s][INFO|trainer.py:805] 2024-08-30 20:31:32,719 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: tokens, ner_tags, id. If tokens, ner_tags, id are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3788] 2024-08-30 20:31:32,722 >> ***** Running Evaluation ***** [INFO|trainer.py:3790] 2024-08-30 20:31:32,722 >> Num examples = 6810 [INFO|trainer.py:3793] 2024-08-30 20:31:32,722 >> Batch size = 8 {'eval_loss': 0.07865303754806519, 'eval_precision': 0.7363811151463363, 'eval_recall': 0.8065044454843239, 'eval_f1': 0.7698492462311558, 'eval_accuracy': 0.9743364411550661, 'eval_runtime': 14.4143, 'eval_samples_per_second': 472.448, 'eval_steps_per_second': 59.108, 'epoch': 2.0} {'loss': 0.0458, 'grad_norm': 1.476723074913025, 'learning_rate': 3.8235294117647055e-05, 'epoch': 2.35} 0%| | 0/852 [00:00> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-1276 [INFO|configuration_utils.py:472] 2024-08-30 20:31:47,407 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-1276/config.json [INFO|modeling_utils.py:2690] 2024-08-30 20:31:48,772 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-1276/model.safetensors [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:31:48,773 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-1276/tokenizer_config.json [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:31:48,773 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-1276/special_tokens_map.json [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:31:51,081 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:31:51,081 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json 30%|███ | 1277/4250 [06:02<4:45:43, 5.77s/it] 30%|███ | 1278/4250 [06:02<3:23:00, 4.10s/it] 30%|███ | 1279/4250 [06:02<2:25:57, 2.95s/it] 30%|███ | 1280/4250 [06:03<1:45:33, 2.13s/it] 30%|███ | 1281/4250 [06:03<1:17:47, 1.57s/it] 30%|███ | 1282/4250 [06:03<57:30, 1.16s/it] 30%|███ | 1283/4250 [06:03<43:08, 1.15it/s] 30%|███ | 1284/4250 [06:04<38:23, 1.29it/s] 30%|███ | 1285/4250 [06:04<29:41, 1.66it/s] 30%|███ | 1286/4250 [06:04<26:16, 1.88it/s] 30%|███ | 1287/4250 [06:05<24:10, 2.04it/s] 30%|███ | 1288/4250 [06:05<19:37, 2.52it/s] 30%|███ | 1289/4250 [06:05<17:13, 2.87it/s] 30%|███ | 1290/4250 [06:05<14:41, 3.36it/s] 30%|███ | 1291/4250 [06:06<13:49, 3.57it/s] 30%|███ | 1292/4250 [06:06<12:40, 3.89it/s] 30%|███ | 1293/4250 [06:06<12:03, 4.09it/s] 30%|███ | 1294/4250 [06:06<12:35, 3.91it/s] 30%|███ | 1295/4250 [06:07<12:48, 3.85it/s] 30%|███ | 1296/4250 [06:07<11:36, 4.24it/s] 31%|███ | 1297/4250 [06:07<10:58, 4.48it/s] 31%|███ | 1298/4250 [06:07<10:50, 4.54it/s] 31%|███ | 1299/4250 [06:07<11:21, 4.33it/s] 31%|███ | 1300/4250 [06:08<10:41, 4.60it/s] 31%|███ | 1301/4250 [06:08<10:25, 4.71it/s] 31%|███ | 1302/4250 [06:08<10:16, 4.78it/s] 31%|███ | 1303/4250 [06:08<10:04, 4.88it/s] 31%|███ | 1304/4250 [06:08<10:00, 4.91it/s] 31%|███ | 1305/4250 [06:09<11:08, 4.40it/s] 31%|███ | 1306/4250 [06:09<10:42, 4.58it/s] 31%|███ | 1307/4250 [06:09<10:44, 4.57it/s] 31%|███ | 1308/4250 [06:09<11:17, 4.34it/s] 31%|███ | 1309/4250 [06:10<10:33, 4.64it/s] 31%|███ | 1310/4250 [06:10<10:01, 4.89it/s] 31%|███ | 1311/4250 [06:10<10:00, 4.90it/s] 31%|███ | 1312/4250 [06:10<10:06, 4.84it/s] 31%|███ | 1313/4250 [06:10<11:04, 4.42it/s] 31%|███ | 1314/4250 [06:11<10:26, 4.68it/s] 31%|███ | 1315/4250 [06:11<11:14, 4.35it/s] 31%|███ | 1316/4250 [06:11<11:25, 4.28it/s] 31%|███ | 1317/4250 [06:11<12:22, 3.95it/s] 31%|███ | 1318/4250 [06:12<11:31, 4.24it/s] 31%|███ | 1319/4250 [06:12<11:39, 4.19it/s] 31%|███ | 1320/4250 [06:12<10:43, 4.55it/s] 31%|███ | 1321/4250 [06:12<14:19, 3.41it/s] 31%|███ | 1322/4250 [06:13<14:20, 3.40it/s] 31%|███ | 1323/4250 [06:13<12:51, 3.79it/s] 31%|███ | 1324/4250 [06:13<11:47, 4.14it/s] 31%|███ | 1325/4250 [06:13<12:50, 3.80it/s] 31%|███ | 1326/4250 [06:14<12:25, 3.92it/s] 31%|███ | 1327/4250 [06:14<11:18, 4.31it/s] 31%|███ | 1328/4250 [06:14<10:44, 4.53it/s] 31%|███▏ | 1329/4250 [06:14<11:39, 4.18it/s] 31%|███▏ | 1330/4250 [06:15<13:38, 3.57it/s] 31%|███▏ | 1331/4250 [06:15<12:14, 3.97it/s] 31%|███▏ | 1332/4250 [06:15<10:55, 4.45it/s] 31%|███▏ | 1333/4250 [06:16<16:20, 2.98it/s] 31%|███▏ | 1334/4250 [06:16<15:41, 3.10it/s] 31%|███▏ | 1335/4250 [06:16<16:26, 2.95it/s] 31%|███▏ | 1336/4250 [06:17<14:21, 3.38it/s] 31%|███▏ | 1337/4250 [06:17<13:31, 3.59it/s] 31%|███▏ | 1338/4250 [06:17<13:22, 3.63it/s] 32%|███▏ | 1339/4250 [06:17<14:29, 3.35it/s] 32%|███▏ | 1340/4250 [06:18<13:53, 3.49it/s] 32%|███▏ | 1341/4250 [06:18<12:12, 3.97it/s] 32%|███▏ | 1342/4250 [06:18<11:01, 4.40it/s] 32%|███▏ | 1343/4250 [06:18<12:01, 4.03it/s] 32%|███▏ | 1344/4250 [06:19<11:29, 4.21it/s] 32%|███▏ | 1345/4250 [06:19<11:24, 4.25it/s] 32%|███▏ | 1346/4250 [06:19<11:06, 4.35it/s] 32%|███▏ | 1347/4250 [06:19<10:28, 4.62it/s] 32%|███▏ | 1348/4250 [06:20<12:53, 3.75it/s] 32%|███▏ | 1349/4250 [06:20<11:10, 4.33it/s] 32%|███▏ | 1350/4250 [06:20<11:53, 4.06it/s] 32%|███▏ | 1351/4250 [06:20<11:26, 4.22it/s] 32%|███▏ | 1352/4250 [06:20<11:05, 4.35it/s] 32%|███▏ | 1353/4250 [06:21<10:55, 4.42it/s] 32%|███▏ | 1354/4250 [06:21<10:14, 4.72it/s] 32%|███▏ | 1355/4250 [06:21<10:07, 4.76it/s] 32%|███▏ | 1356/4250 [06:21<10:13, 4.71it/s] 32%|███▏ | 1357/4250 [06:21<09:45, 4.94it/s] 32%|███▏ | 1358/4250 [06:22<09:32, 5.05it/s] 32%|███▏ | 1359/4250 [06:22<10:54, 4.42it/s] 32%|███▏ | 1360/4250 [06:22<10:18, 4.67it/s] 32%|███▏ | 1361/4250 [06:22<11:00, 4.37it/s] 32%|███▏ | 1362/4250 [06:23<13:32, 3.55it/s] 32%|███▏ | 1363/4250 [06:23<12:37, 3.81it/s] 32%|███▏ | 1364/4250 [06:23<12:01, 4.00it/s] 32%|███▏ | 1365/4250 [06:23<12:10, 3.95it/s] 32%|███▏ | 1366/4250 [06:24<11:32, 4.17it/s] 32%|███▏ | 1367/4250 [06:24<11:55, 4.03it/s] 32%|███▏ | 1368/4250 [06:24<11:35, 4.14it/s] 32%|███▏ | 1369/4250 [06:24<12:32, 3.83it/s] 32%|███▏ | 1370/4250 [06:25<11:45, 4.08it/s] 32%|███▏ | 1371/4250 [06:25<12:11, 3.94it/s] 32%|███▏ | 1372/4250 [06:25<11:50, 4.05it/s] 32%|███▏ | 1373/4250 [06:25<11:04, 4.33it/s] 32%|███▏ | 1374/4250 [06:26<10:21, 4.63it/s] 32%|███▏ | 1375/4250 [06:26<09:58, 4.80it/s] 32%|███▏ | 1376/4250 [06:26<09:44, 4.92it/s] 32%|███▏ | 1377/4250 [06:26<09:44, 4.92it/s] 32%|███▏ | 1378/4250 [06:26<10:05, 4.75it/s] 32%|███▏ | 1379/4250 [06:27<10:32, 4.54it/s] 32%|███▏ | 1380/4250 [06:27<12:44, 3.75it/s] 32%|███▏ | 1381/4250 [06:27<11:34, 4.13it/s] 33%|███▎ | 1382/4250 [06:27<11:09, 4.28it/s] 33%|███▎ | 1383/4250 [06:28<10:50, 4.40it/s] 33%|███▎ | 1384/4250 [06:28<10:42, 4.46it/s] 33%|███▎ | 1385/4250 [06:28<10:00, 4.77it/s] 33%|███▎ | 1386/4250 [06:28<09:35, 4.98it/s] 33%|███▎ | 1387/4250 [06:28<10:13, 4.67it/s] 33%|███▎ | 1388/4250 [06:29<11:41, 4.08it/s] 33%|███▎ | 1389/4250 [06:29<11:02, 4.32it/s] 33%|███▎ | 1390/4250 [06:29<10:23, 4.59it/s] 33%|███▎ | 1391/4250 [06:29<10:29, 4.54it/s] 33%|███▎ | 1392/4250 [06:29<09:49, 4.85it/s] 33%|███▎ | 1393/4250 [06:30<09:43, 4.89it/s] 33%|███▎ | 1394/4250 [06:30<10:32, 4.51it/s] 33%|███▎ | 1395/4250 [06:30<10:06, 4.70it/s] 33%|███▎ | 1396/4250 [06:30<10:05, 4.71it/s] 33%|███▎ | 1397/4250 [06:31<09:59, 4.76it/s] 33%|███▎ | 1398/4250 [06:31<10:07, 4.70it/s] 33%|███▎ | 1399/4250 [06:31<10:03, 4.72it/s] 33%|███▎ | 1400/4250 [06:31<10:14, 4.64it/s] 33%|███▎ | 1401/4250 [06:31<09:34, 4.96it/s] 33%|███▎ | 1402/4250 [06:32<09:24, 5.05it/s] 33%|███▎ | 1403/4250 [06:32<09:25, 5.03it/s] 33%|███▎ | 1404/4250 [06:32<10:11, 4.66it/s] 33%|███▎ | 1405/4250 [06:32<10:02, 4.72it/s] 33%|███▎ | 1406/4250 [06:33<12:00, 3.95it/s] 33%|███▎ | 1407/4250 [06:33<13:51, 3.42it/s] 33%|███▎ | 1408/4250 [06:33<11:51, 3.99it/s] 33%|███▎ | 1409/4250 [06:33<11:07, 4.26it/s] 33%|███▎ | 1410/4250 [06:33<10:05, 4.69it/s] 33%|███▎ | 1411/4250 [06:34<10:25, 4.54it/s] 33%|███▎ | 1412/4250 [06:34<10:22, 4.56it/s] 33%|███▎ | 1413/4250 [06:34<10:11, 4.64it/s] 33%|███▎ | 1414/4250 [06:34<11:01, 4.29it/s] 33%|███▎ | 1415/4250 [06:35<11:43, 4.03it/s] 33%|███▎ | 1416/4250 [06:35<10:58, 4.30it/s] 33%|███▎ | 1417/4250 [06:35<10:21, 4.56it/s] 33%|███▎ | 1418/4250 [06:35<11:17, 4.18it/s] 33%|███▎ | 1419/4250 [06:36<10:21, 4.55it/s] 33%|███▎ | 1420/4250 [06:36<10:08, 4.65it/s] 33%|███▎ | 1421/4250 [06:36<10:20, 4.56it/s] 33%|███▎ | 1422/4250 [06:36<10:09, 4.64it/s] 33%|███▎ | 1423/4250 [06:37<11:37, 4.05it/s] 34%|███▎ | 1424/4250 [06:37<11:04, 4.25it/s] 34%|███▎ | 1425/4250 [06:37<10:56, 4.30it/s] 34%|███▎ | 1426/4250 [06:37<10:09, 4.64it/s] 34%|███▎ | 1427/4250 [06:37<09:24, 5.00it/s] 34%|███▎ | 1428/4250 [06:37<09:23, 5.00it/s] 34%|███▎ | 1429/4250 [06:38<09:45, 4.82it/s] 34%|███▎ | 1430/4250 [06:38<09:26, 4.98it/s] 34%|███▎ | 1431/4250 [06:38<09:40, 4.86it/s] 34%|███▎ | 1432/4250 [06:38<09:46, 4.81it/s] 34%|███▎ | 1433/4250 [06:39<09:46, 4.80it/s] 34%|███▎ | 1434/4250 [06:39<10:03, 4.67it/s] 34%|███▍ | 1435/4250 [06:39<10:03, 4.66it/s] 34%|███▍ | 1436/4250 [06:39<09:44, 4.82it/s] 34%|███▍ | 1437/4250 [06:39<09:24, 4.99it/s] 34%|███▍ | 1438/4250 [06:40<09:14, 5.07it/s] 34%|███▍ | 1439/4250 [06:40<11:23, 4.11it/s] 34%|███▍ | 1440/4250 [06:40<11:17, 4.15it/s] 34%|███▍ | 1441/4250 [06:40<11:10, 4.19it/s] 34%|███▍ | 1442/4250 [06:41<11:11, 4.18it/s] 34%|███▍ | 1443/4250 [06:41<11:32, 4.05it/s] 34%|███▍ | 1444/4250 [06:41<11:36, 4.03it/s] 34%|███▍ | 1445/4250 [06:41<12:10, 3.84it/s] 34%|███▍ | 1446/4250 [06:42<11:17, 4.14it/s] 34%|███▍ | 1447/4250 [06:42<11:08, 4.19it/s] 34%|███▍ | 1448/4250 [06:42<10:30, 4.45it/s] 34%|███▍ | 1449/4250 [06:42<10:53, 4.29it/s] 34%|███▍ | 1450/4250 [06:43<11:26, 4.08it/s] 34%|███▍ | 1451/4250 [06:43<12:06, 3.85it/s] 34%|███▍ | 1452/4250 [06:43<10:54, 4.27it/s] 34%|███▍ | 1453/4250 [06:43<11:41, 3.99it/s] 34%|███▍ | 1454/4250 [06:44<13:33, 3.44it/s] 34%|███▍ | 1455/4250 [06:44<12:19, 3.78it/s] 34%|███▍ | 1456/4250 [06:44<12:03, 3.86it/s] 34%|███▍ | 1457/4250 [06:44<12:38, 3.68it/s] 34%|███▍ | 1458/4250 [06:45<12:14, 3.80it/s] 34%|███▍ | 1459/4250 [06:45<11:39, 3.99it/s] 34%|███▍ | 1460/4250 [06:45<11:43, 3.97it/s] 34%|███▍ | 1461/4250 [06:45<11:12, 4.15it/s] 34%|███▍ | 1462/4250 [06:46<13:22, 3.48it/s] 34%|███▍ | 1463/4250 [06:46<14:11, 3.27it/s] 34%|███▍ | 1464/4250 [06:46<12:35, 3.69it/s] 34%|███▍ | 1465/4250 [06:47<11:46, 3.94it/s] 34%|███▍ | 1466/4250 [06:47<11:19, 4.10it/s] 35%|███▍ | 1467/4250 [06:47<10:32, 4.40it/s] 35%|███▍ | 1468/4250 [06:47<11:54, 3.89it/s] 35%|███▍ | 1469/4250 [06:48<14:21, 3.23it/s] 35%|███▍ | 1470/4250 [06:48<12:44, 3.64it/s] 35%|███▍ | 1471/4250 [06:48<11:51, 3.91it/s] 35%|███▍ | 1472/4250 [06:48<11:38, 3.98it/s] 35%|███▍ | 1473/4250 [06:49<10:50, 4.27it/s] 35%|███▍ | 1474/4250 [06:49<11:23, 4.06it/s] 35%|███▍ | 1475/4250 [06:49<11:09, 4.14it/s] 35%|███▍ | 1476/4250 [06:49<10:52, 4.25it/s] 35%|███▍ | 1477/4250 [06:49<10:49, 4.27it/s] 35%|███▍ | 1478/4250 [06:50<12:02, 3.84it/s] 35%|███▍ | 1479/4250 [06:50<11:23, 4.05it/s] 35%|███▍ | 1480/4250 [06:50<11:10, 4.13it/s] 35%|███▍ | 1481/4250 [06:51<12:34, 3.67it/s] 35%|███▍ | 1482/4250 [06:51<12:29, 3.69it/s] 35%|███▍ | 1483/4250 [06:51<13:02, 3.54it/s] 35%|███▍ | 1484/4250 [06:51<11:19, 4.07it/s] 35%|███▍ | 1485/4250 [06:52<12:39, 3.64it/s] 35%|███▍ | 1486/4250 [06:52<13:00, 3.54it/s] 35%|███▍ | 1487/4250 [06:52<12:11, 3.77it/s] 35%|███▌ | 1488/4250 [06:52<11:45, 3.92it/s] 35%|███▌ | 1489/4250 [06:53<11:04, 4.15it/s] 35%|███▌ | 1490/4250 [06:53<10:45, 4.27it/s] 35%|███▌ | 1491/4250 [06:53<10:06, 4.55it/s] 35%|███▌ | 1492/4250 [06:53<09:52, 4.66it/s] 35%|███▌ | 1493/4250 [06:54<18:04, 2.54it/s] 35%|███▌ | 1494/4250 [06:54<15:21, 2.99it/s] 35%|███▌ | 1495/4250 [06:54<13:36, 3.37it/s] 35%|███▌ | 1496/4250 [06:55<12:37, 3.63it/s] 35%|███▌ | 1497/4250 [06:55<12:06, 3.79it/s] 35%|███▌ | 1498/4250 [06:55<11:16, 4.07it/s] 35%|███▌ | 1499/4250 [06:55<11:16, 4.07it/s] 35%|███▌ | 1500/4250 [06:56<12:02, 3.80it/s] 35%|███▌ | 1500/4250 [06:56<12:02, 3.80it/s] 35%|███▌ | 1501/4250 [06:56<11:08, 4.11it/s] 35%|███▌ | 1502/4250 [06:56<10:43, 4.27it/s] 35%|███▌ | 1503/4250 [06:56<10:44, 4.27it/s] 35%|███▌ | 1504/4250 [06:57<09:55, 4.61it/s] 35%|███▌ | 1505/4250 [06:57<09:28, 4.83it/s] 35%|███▌ | 1506/4250 [06:57<09:11, 4.98it/s] 35%|███▌ | 1507/4250 [06:57<08:50, 5.17it/s] 35%|███▌ | 1508/4250 [06:57<11:14, 4.06it/s] 36%|███▌ | 1509/4250 [06:58<11:27, 3.99it/s] 36%|███▌ | 1510/4250 [06:58<11:11, 4.08it/s] 36%|███▌ | 1511/4250 [06:58<10:34, 4.32it/s] 36%|███▌ | 1512/4250 [06:58<10:39, 4.28it/s] 36%|███▌ | 1513/4250 [06:59<10:04, 4.52it/s] 36%|███▌ | 1514/4250 [06:59<09:52, 4.61it/s] 36%|███▌ | 1515/4250 [06:59<09:24, 4.84it/s] 36%|███▌ | 1516/4250 [06:59<09:22, 4.86it/s] 36%|███▌ | 1517/4250 [06:59<09:29, 4.80it/s] 36%|███▌ | 1518/4250 [07:00<09:33, 4.76it/s] 36%|███▌ | 1519/4250 [07:00<09:40, 4.70it/s] 36%|███▌ | 1520/4250 [07:00<11:15, 4.04it/s] 36%|███▌ | 1521/4250 [07:00<10:27, 4.35it/s] 36%|███▌ | 1522/4250 [07:01<10:17, 4.42it/s] 36%|███▌ | 1523/4250 [07:01<10:03, 4.52it/s] 36%|███▌ | 1524/4250 [07:01<09:11, 4.94it/s] 36%|███▌ | 1525/4250 [07:01<09:21, 4.85it/s] 36%|███▌ | 1526/4250 [07:01<09:27, 4.80it/s] 36%|███▌ | 1527/4250 [07:02<09:20, 4.86it/s] 36%|███▌ | 1528/4250 [07:02<17:10, 2.64it/s] 36%|███▌ | 1529/4250 [07:03<15:51, 2.86it/s] 36%|███▌ | 1530/4250 [07:03<13:52, 3.27it/s] 36%|███▌ | 1531/4250 [07:03<12:25, 3.65it/s] 36%|███▌ | 1532/4250 [07:03<11:08, 4.06it/s] 36%|███▌ | 1533/4250 [07:03<10:11, 4.44it/s] 36%|███▌ | 1534/4250 [07:04<11:16, 4.02it/s] 36%|███▌ | 1535/4250 [07:04<11:34, 3.91it/s] 36%|███▌ | 1536/4250 [07:04<14:46, 3.06it/s] 36%|███▌ | 1537/4250 [07:05<12:58, 3.49it/s] 36%|███▌ | 1538/4250 [07:05<11:09, 4.05it/s] 36%|███▌ | 1539/4250 [07:05<11:04, 4.08it/s] 36%|███▌ | 1540/4250 [07:05<10:24, 4.34it/s] 36%|███▋ | 1541/4250 [07:05<09:39, 4.68it/s] 36%|███▋ | 1542/4250 [07:06<09:05, 4.97it/s] 36%|███▋ | 1543/4250 [07:06<11:11, 4.03it/s] 36%|███▋ | 1544/4250 [07:06<10:11, 4.43it/s] 36%|███▋ | 1545/4250 [07:06<12:35, 3.58it/s] 36%|███▋ | 1546/4250 [07:07<11:24, 3.95it/s] 36%|███▋ | 1547/4250 [07:07<10:46, 4.18it/s] 36%|███▋ | 1548/4250 [07:07<10:04, 4.47it/s] 36%|███▋ | 1549/4250 [07:07<10:11, 4.41it/s] 36%|███▋ | 1550/4250 [07:08<10:10, 4.42it/s] 36%|███▋ | 1551/4250 [07:08<09:18, 4.83it/s] 37%|███▋ | 1552/4250 [07:08<10:52, 4.13it/s] 37%|███▋ | 1553/4250 [07:08<10:34, 4.25it/s] 37%|███▋ | 1554/4250 [07:08<09:50, 4.56it/s] 37%|███▋ | 1555/4250 [07:09<08:57, 5.01it/s] 37%|███▋ | 1556/4250 [07:09<08:46, 5.12it/s] 37%|███▋ | 1557/4250 [07:09<10:52, 4.13it/s] 37%|███▋ | 1558/4250 [07:09<11:00, 4.08it/s] 37%|███▋ | 1559/4250 [07:10<10:50, 4.14it/s] 37%|███▋ | 1560/4250 [07:10<10:38, 4.21it/s] 37%|███▋ | 1561/4250 [07:10<09:57, 4.50it/s] 37%|███▋ | 1562/4250 [07:10<09:52, 4.54it/s] 37%|███▋ | 1563/4250 [07:11<11:22, 3.94it/s] 37%|███▋ | 1564/4250 [07:11<10:04, 4.44it/s] 37%|███▋ | 1565/4250 [07:11<10:03, 4.45it/s] 37%|███▋ | 1566/4250 [07:11<12:41, 3.52it/s] 37%|███▋ | 1567/4250 [07:12<12:28, 3.58it/s] 37%|███▋ | 1568/4250 [07:12<12:06, 3.69it/s] 37%|███▋ | 1569/4250 [07:12<11:24, 3.91it/s] 37%|███▋ | 1570/4250 [07:12<10:51, 4.12it/s] 37%|███▋ | 1571/4250 [07:13<10:48, 4.13it/s] 37%|███▋ | 1572/4250 [07:13<09:54, 4.50it/s] 37%|███▋ | 1573/4250 [07:13<09:23, 4.75it/s] 37%|███▋ | 1574/4250 [07:13<09:14, 4.82it/s] 37%|███▋ | 1575/4250 [07:13<09:43, 4.59it/s] 37%|███▋ | 1576/4250 [07:14<15:59, 2.79it/s] 37%|███▋ | 1577/4250 [07:14<14:46, 3.01it/s] 37%|███▋ | 1578/4250 [07:15<14:59, 2.97it/s] 37%|███▋ | 1579/4250 [07:15<15:09, 2.94it/s] 37%|███▋ | 1580/4250 [07:15<14:02, 3.17it/s] 37%|███▋ | 1581/4250 [07:15<12:14, 3.63it/s] 37%|███▋ | 1582/4250 [07:16<11:18, 3.93it/s] 37%|███▋ | 1583/4250 [07:16<10:07, 4.39it/s] 37%|███▋ | 1584/4250 [07:16<09:31, 4.67it/s] 37%|███▋ | 1585/4250 [07:16<09:43, 4.57it/s] 37%|███▋ | 1586/4250 [07:16<09:16, 4.79it/s] 37%|███▋ | 1587/4250 [07:17<09:28, 4.68it/s] 37%|███▋ | 1588/4250 [07:17<09:19, 4.76it/s] 37%|███▋ | 1589/4250 [07:17<09:34, 4.63it/s] 37%|███▋ | 1590/4250 [07:17<09:23, 4.72it/s] 37%|███▋ | 1591/4250 [07:18<12:21, 3.59it/s] 37%|███▋ | 1592/4250 [07:18<11:17, 3.92it/s] 37%|███▋ | 1593/4250 [07:18<10:36, 4.18it/s] 38%|███▊ | 1594/4250 [07:18<09:15, 4.78it/s] 38%|███▊ | 1595/4250 [07:18<08:45, 5.05it/s] 38%|███▊ | 1596/4250 [07:19<09:27, 4.68it/s] 38%|███▊ | 1597/4250 [07:19<09:26, 4.69it/s] 38%|███▊ | 1598/4250 [07:19<08:56, 4.94it/s] 38%|███▊ | 1599/4250 [07:19<09:27, 4.67it/s] 38%|███▊ | 1600/4250 [07:20<09:36, 4.59it/s] 38%|███▊ | 1601/4250 [07:20<10:43, 4.12it/s] 38%|███▊ | 1602/4250 [07:20<10:14, 4.31it/s] 38%|███▊ | 1603/4250 [07:20<10:13, 4.31it/s] 38%|███▊ | 1604/4250 [07:21<10:43, 4.11it/s] 38%|███▊ | 1605/4250 [07:21<09:56, 4.44it/s] 38%|███▊ | 1606/4250 [07:21<10:43, 4.11it/s] 38%|███▊ | 1607/4250 [07:21<09:52, 4.46it/s] 38%|███▊ | 1608/4250 [07:21<09:21, 4.71it/s] 38%|███▊ | 1609/4250 [07:22<09:12, 4.78it/s] 38%|███▊ | 1610/4250 [07:22<09:19, 4.71it/s] 38%|███▊ | 1611/4250 [07:22<09:14, 4.76it/s] 38%|███▊ | 1612/4250 [07:22<09:55, 4.43it/s] 38%|███▊ | 1613/4250 [07:22<09:23, 4.68it/s] 38%|███▊ | 1614/4250 [07:23<09:55, 4.42it/s] 38%|███▊ | 1615/4250 [07:23<11:21, 3.86it/s] 38%|███▊ | 1616/4250 [07:23<10:17, 4.26it/s] 38%|███▊ | 1617/4250 [07:23<10:27, 4.20it/s] 38%|███▊ | 1618/4250 [07:24<09:40, 4.54it/s] 38%|███▊ | 1619/4250 [07:24<08:58, 4.89it/s] 38%|███▊ | 1620/4250 [07:24<08:54, 4.92it/s] 38%|███▊ | 1621/4250 [07:24<09:28, 4.62it/s] 38%|███▊ | 1622/4250 [07:24<09:31, 4.60it/s] 38%|███▊ | 1623/4250 [07:25<09:48, 4.46it/s] 38%|███▊ | 1624/4250 [07:25<09:39, 4.53it/s] 38%|███▊ | 1625/4250 [07:25<08:58, 4.87it/s] 38%|███▊ | 1626/4250 [07:25<09:46, 4.47it/s] 38%|███▊ | 1627/4250 [07:26<09:15, 4.72it/s] 38%|███▊ | 1628/4250 [07:26<11:27, 3.81it/s] 38%|███▊ | 1629/4250 [07:26<10:54, 4.00it/s] 38%|███▊ | 1630/4250 [07:26<09:56, 4.39it/s] 38%|███▊ | 1631/4250 [07:26<09:14, 4.72it/s] 38%|███▊ | 1632/4250 [07:27<10:59, 3.97it/s] 38%|███▊ | 1633/4250 [07:27<11:36, 3.76it/s] 38%|███▊ | 1634/4250 [07:27<10:40, 4.08it/s] 38%|███▊ | 1635/4250 [07:28<10:10, 4.29it/s] 38%|███▊ | 1636/4250 [07:28<10:20, 4.22it/s] 39%|███▊ | 1637/4250 [07:28<10:46, 4.04it/s] 39%|███▊ | 1638/4250 [07:28<10:14, 4.25it/s] 39%|███▊ | 1639/4250 [07:28<09:20, 4.66it/s] 39%|███▊ | 1640/4250 [07:29<10:45, 4.04it/s] 39%|███▊ | 1641/4250 [07:29<09:52, 4.40it/s] 39%|███▊ | 1642/4250 [07:29<09:29, 4.58it/s] 39%|███▊ | 1643/4250 [07:29<09:28, 4.58it/s] 39%|███▊ | 1644/4250 [07:30<09:02, 4.81it/s] 39%|███▊ | 1645/4250 [07:30<09:07, 4.75it/s] 39%|███▊ | 1646/4250 [07:30<08:56, 4.85it/s] 39%|███▉ | 1647/4250 [07:30<09:59, 4.35it/s] 39%|███▉ | 1648/4250 [07:31<10:56, 3.96it/s] 39%|███▉ | 1649/4250 [07:31<11:01, 3.93it/s] 39%|███▉ | 1650/4250 [07:31<10:45, 4.03it/s] 39%|███▉ | 1651/4250 [07:32<13:57, 3.10it/s] 39%|███▉ | 1652/4250 [07:32<12:18, 3.52it/s] 39%|███▉ | 1653/4250 [07:32<11:30, 3.76it/s] 39%|███▉ | 1654/4250 [07:32<13:47, 3.14it/s] 39%|███▉ | 1655/4250 [07:33<16:09, 2.68it/s] 39%|███▉ | 1656/4250 [07:33<13:28, 3.21it/s] 39%|███▉ | 1657/4250 [07:33<11:47, 3.66it/s] 39%|███▉ | 1658/4250 [07:34<12:04, 3.58it/s] 39%|███▉ | 1659/4250 [07:34<12:10, 3.55it/s] 39%|███▉ | 1660/4250 [07:34<10:54, 3.96it/s] 39%|███▉ | 1661/4250 [07:34<10:20, 4.17it/s] 39%|███▉ | 1662/4250 [07:34<10:08, 4.25it/s] 39%|███▉ | 1663/4250 [07:35<09:41, 4.45it/s] 39%|███▉ | 1664/4250 [07:35<10:28, 4.11it/s] 39%|███▉ | 1665/4250 [07:35<11:06, 3.88it/s] 39%|███▉ | 1666/4250 [07:35<11:27, 3.76it/s] 39%|███▉ | 1667/4250 [07:36<10:48, 3.99it/s] 39%|███▉ | 1668/4250 [07:36<10:01, 4.30it/s] 39%|███▉ | 1669/4250 [07:36<09:19, 4.61it/s] 39%|███▉ | 1670/4250 [07:36<09:08, 4.71it/s] 39%|███▉ | 1671/4250 [07:37<09:38, 4.46it/s] 39%|███▉ | 1672/4250 [07:37<09:58, 4.31it/s] 39%|███▉ | 1673/4250 [07:37<09:43, 4.42it/s] 39%|███▉ | 1674/4250 [07:37<09:23, 4.57it/s] 39%|███▉ | 1675/4250 [07:37<09:03, 4.74it/s] 39%|███▉ | 1676/4250 [07:38<08:47, 4.88it/s] 39%|███▉ | 1677/4250 [07:38<08:51, 4.85it/s] 39%|███▉ | 1678/4250 [07:38<08:24, 5.09it/s] 40%|███▉ | 1679/4250 [07:38<09:00, 4.76it/s] 40%|███▉ | 1680/4250 [07:38<08:26, 5.08it/s] 40%|███▉ | 1681/4250 [07:39<07:57, 5.38it/s] 40%|███▉ | 1682/4250 [07:39<08:39, 4.94it/s] 40%|███▉ | 1683/4250 [07:39<10:28, 4.09it/s] 40%|███▉ | 1684/4250 [07:39<09:39, 4.43it/s] 40%|███▉ | 1685/4250 [07:40<09:44, 4.39it/s] 40%|███▉ | 1686/4250 [07:40<10:56, 3.91it/s] 40%|███▉ | 1687/4250 [07:40<09:58, 4.28it/s] 40%|███▉ | 1688/4250 [07:40<10:49, 3.94it/s] 40%|███▉ | 1689/4250 [07:41<10:11, 4.19it/s] 40%|███▉ | 1690/4250 [07:41<09:46, 4.36it/s] 40%|███▉ | 1691/4250 [07:41<11:49, 3.61it/s] 40%|███▉ | 1692/4250 [07:41<11:12, 3.81it/s] 40%|███▉ | 1693/4250 [07:42<10:03, 4.24it/s] 40%|███▉ | 1694/4250 [07:42<09:52, 4.32it/s] 40%|███▉ | 1695/4250 [07:42<09:38, 4.42it/s] 40%|███▉ | 1696/4250 [07:42<09:52, 4.31it/s] 40%|███▉ | 1697/4250 [07:42<09:18, 4.57it/s] 40%|███▉ | 1698/4250 [07:43<08:33, 4.97it/s] 40%|███▉ | 1699/4250 [07:43<08:49, 4.82it/s] 40%|████ | 1700/4250 [07:43<09:55, 4.28it/s] 40%|████ | 1701/4250 [07:43<09:27, 4.49it/s] 40%|████ | 1702/4250 [07:44<10:00, 4.24it/s][INFO|trainer.py:805] 2024-08-30 20:33:32,906 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: tokens, ner_tags, id. If tokens, ner_tags, id are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3788] 2024-08-30 20:33:32,909 >> ***** Running Evaluation ***** [INFO|trainer.py:3790] 2024-08-30 20:33:32,909 >> Num examples = 6810 [INFO|trainer.py:3793] 2024-08-30 20:33:32,909 >> Batch size = 8 {'eval_loss': 0.07876282930374146, 'eval_precision': 0.7715297764002657, 'eval_recall': 0.8153954141319607, 'eval_f1': 0.7928563303378454, 'eval_accuracy': 0.9759155258351985, 'eval_runtime': 14.6794, 'eval_samples_per_second': 463.917, 'eval_steps_per_second': 58.041, 'epoch': 3.0} {'loss': 0.0279, 'grad_norm': 0.4094911515712738, 'learning_rate': 3.235294117647059e-05, 'epoch': 3.53} 0%| | 0/852 [00:00> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-1702 [INFO|configuration_utils.py:472] 2024-08-30 20:33:47,736 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-1702/config.json [INFO|modeling_utils.py:2690] 2024-08-30 20:33:49,085 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-1702/model.safetensors [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:33:49,086 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-1702/tokenizer_config.json [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:33:49,086 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-1702/special_tokens_map.json [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:33:51,483 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:33:51,483 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json 40%|████ | 1703/4250 [08:02<4:07:14, 5.82s/it] 40%|████ | 1704/4250 [08:03<2:55:57, 4.15s/it] 40%|████ | 1705/4250 [08:03<2:05:17, 2.95s/it] 40%|████ | 1706/4250 [08:03<1:31:01, 2.15s/it] 40%|████ | 1707/4250 [08:03<1:06:42, 1.57s/it] 40%|████ | 1708/4250 [08:04<50:16, 1.19s/it] 40%|████ | 1709/4250 [08:04<37:27, 1.13it/s] 40%|████ | 1710/4250 [08:04<31:00, 1.37it/s] 40%|████ | 1711/4250 [08:04<23:55, 1.77it/s] 40%|████ | 1712/4250 [08:05<20:06, 2.10it/s] 40%|████ | 1713/4250 [08:05<16:44, 2.53it/s] 40%|████ | 1714/4250 [08:05<15:29, 2.73it/s] 40%|████ | 1715/4250 [08:05<13:49, 3.06it/s] 40%|████ | 1716/4250 [08:06<12:46, 3.30it/s] 40%|████ | 1717/4250 [08:06<11:40, 3.62it/s] 40%|████ | 1718/4250 [08:06<10:29, 4.02it/s] 40%|████ | 1719/4250 [08:06<11:18, 3.73it/s] 40%|████ | 1720/4250 [08:07<10:34, 3.99it/s] 40%|████ | 1721/4250 [08:07<10:57, 3.85it/s] 41%|████ | 1722/4250 [08:07<10:28, 4.02it/s] 41%|████ | 1723/4250 [08:07<10:19, 4.08it/s] 41%|████ | 1724/4250 [08:07<09:18, 4.53it/s] 41%|████ | 1725/4250 [08:08<08:42, 4.83it/s] 41%|████ | 1726/4250 [08:08<08:12, 5.12it/s] 41%|████ | 1727/4250 [08:08<08:18, 5.06it/s] 41%|████ | 1728/4250 [08:08<08:36, 4.88it/s] 41%|████ | 1729/4250 [08:09<11:22, 3.69it/s] 41%|████ | 1730/4250 [08:09<10:53, 3.86it/s] 41%|████ | 1731/4250 [08:09<09:26, 4.45it/s] 41%|████ | 1732/4250 [08:09<11:08, 3.76it/s] 41%|████ | 1733/4250 [08:10<10:38, 3.94it/s] 41%|████ | 1734/4250 [08:10<09:39, 4.34it/s] 41%|████ | 1735/4250 [08:10<08:56, 4.69it/s] 41%|████ | 1736/4250 [08:10<08:29, 4.94it/s] 41%|████ | 1737/4250 [08:11<12:57, 3.23it/s] 41%|████ | 1738/4250 [08:11<11:48, 3.55it/s] 41%|████ | 1739/4250 [08:11<10:34, 3.96it/s] 41%|████ | 1740/4250 [08:11<12:08, 3.44it/s] 41%|████ | 1741/4250 [08:12<10:39, 3.92it/s] 41%|████ | 1742/4250 [08:12<15:00, 2.79it/s] 41%|████ | 1743/4250 [08:12<12:41, 3.29it/s] 41%|████ | 1744/4250 [08:13<11:41, 3.57it/s] 41%|████ | 1745/4250 [08:13<10:27, 3.99it/s] 41%|████ | 1746/4250 [08:13<09:58, 4.18it/s] 41%|████ | 1747/4250 [08:13<09:16, 4.49it/s] 41%|████ | 1748/4250 [08:13<08:51, 4.71it/s] 41%|████ | 1749/4250 [08:14<09:24, 4.43it/s] 41%|████ | 1750/4250 [08:14<09:19, 4.47it/s] 41%|████ | 1751/4250 [08:14<10:13, 4.08it/s] 41%|████ | 1752/4250 [08:14<09:24, 4.43it/s] 41%|████ | 1753/4250 [08:15<09:42, 4.29it/s] 41%|████▏ | 1754/4250 [08:15<10:43, 3.88it/s] 41%|████▏ | 1755/4250 [08:15<10:54, 3.81it/s] 41%|████▏ | 1756/4250 [08:15<10:06, 4.11it/s] 41%|████▏ | 1757/4250 [08:16<11:02, 3.77it/s] 41%|████▏ | 1758/4250 [08:16<12:54, 3.22it/s] 41%|████▏ | 1759/4250 [08:16<11:48, 3.52it/s] 41%|████▏ | 1760/4250 [08:17<11:20, 3.66it/s] 41%|████▏ | 1761/4250 [08:17<15:58, 2.60it/s] 41%|████▏ | 1762/4250 [08:17<13:55, 2.98it/s] 41%|████▏ | 1763/4250 [08:18<13:09, 3.15it/s] 42%|████▏ | 1764/4250 [08:18<13:12, 3.14it/s] 42%|████▏ | 1765/4250 [08:18<11:24, 3.63it/s] 42%|████▏ | 1766/4250 [08:18<10:36, 3.90it/s] 42%|████▏ | 1767/4250 [08:19<09:39, 4.28it/s] 42%|████▏ | 1768/4250 [08:19<10:29, 3.95it/s] 42%|████▏ | 1769/4250 [08:19<09:52, 4.19it/s] 42%|████▏ | 1770/4250 [08:19<09:37, 4.30it/s] 42%|████▏ | 1771/4250 [08:20<09:05, 4.55it/s] 42%|████▏ | 1772/4250 [08:20<08:46, 4.71it/s] 42%|████▏ | 1773/4250 [08:20<08:18, 4.97it/s] 42%|████▏ | 1774/4250 [08:20<08:32, 4.83it/s] 42%|████▏ | 1775/4250 [08:20<08:01, 5.14it/s] 42%|████▏ | 1776/4250 [08:20<07:59, 5.16it/s] 42%|████▏ | 1777/4250 [08:21<08:34, 4.80it/s] 42%|████▏ | 1778/4250 [08:21<09:37, 4.28it/s] 42%|████▏ | 1779/4250 [08:21<10:11, 4.04it/s] 42%|████▏ | 1780/4250 [08:21<09:12, 4.47it/s] 42%|████▏ | 1781/4250 [08:22<09:22, 4.39it/s] 42%|████▏ | 1782/4250 [08:22<09:45, 4.21it/s] 42%|████▏ | 1783/4250 [08:22<09:22, 4.39it/s] 42%|████▏ | 1784/4250 [08:22<10:00, 4.10it/s] 42%|████▏ | 1785/4250 [08:23<10:45, 3.82it/s] 42%|████▏ | 1786/4250 [08:23<09:48, 4.19it/s] 42%|████▏ | 1787/4250 [08:23<12:52, 3.19it/s] 42%|████▏ | 1788/4250 [08:24<11:37, 3.53it/s] 42%|████▏ | 1789/4250 [08:24<10:17, 3.98it/s] 42%|████▏ | 1790/4250 [08:24<09:09, 4.48it/s] 42%|████▏ | 1791/4250 [08:24<08:32, 4.80it/s] 42%|████▏ | 1792/4250 [08:24<07:40, 5.33it/s] 42%|████▏ | 1793/4250 [08:25<08:17, 4.94it/s] 42%|████▏ | 1794/4250 [08:25<08:51, 4.62it/s] 42%|████▏ | 1795/4250 [08:25<08:26, 4.84it/s] 42%|████▏ | 1796/4250 [08:25<08:22, 4.88it/s] 42%|████▏ | 1797/4250 [08:25<07:59, 5.11it/s] 42%|████▏ | 1798/4250 [08:26<08:27, 4.84it/s] 42%|████▏ | 1799/4250 [08:26<08:19, 4.91it/s] 42%|████▏ | 1800/4250 [08:26<08:10, 5.00it/s] 42%|████▏ | 1801/4250 [08:26<08:19, 4.90it/s] 42%|████▏ | 1802/4250 [08:26<09:55, 4.11it/s] 42%|████▏ | 1803/4250 [08:27<09:42, 4.20it/s] 42%|████▏ | 1804/4250 [08:27<09:15, 4.41it/s] 42%|████▏ | 1805/4250 [08:27<09:38, 4.23it/s] 42%|████▏ | 1806/4250 [08:27<09:00, 4.52it/s] 43%|████▎ | 1807/4250 [08:28<10:27, 3.90it/s] 43%|████▎ | 1808/4250 [08:28<10:14, 3.98it/s] 43%|████▎ | 1809/4250 [08:28<09:20, 4.35it/s] 43%|████▎ | 1810/4250 [08:28<10:57, 3.71it/s] 43%|████▎ | 1811/4250 [08:29<10:37, 3.83it/s] 43%|████▎ | 1812/4250 [08:29<09:51, 4.12it/s] 43%|████▎ | 1813/4250 [08:29<10:50, 3.74it/s] 43%|████▎ | 1814/4250 [08:30<12:07, 3.35it/s] 43%|████▎ | 1815/4250 [08:30<11:05, 3.66it/s] 43%|████▎ | 1816/4250 [08:31<16:44, 2.42it/s] 43%|████▎ | 1817/4250 [08:31<14:12, 2.85it/s] 43%|████▎ | 1818/4250 [08:31<12:16, 3.30it/s] 43%|████▎ | 1819/4250 [08:31<10:11, 3.97it/s] 43%|████▎ | 1820/4250 [08:31<10:14, 3.95it/s] 43%|████▎ | 1821/4250 [08:32<09:27, 4.28it/s] 43%|████▎ | 1822/4250 [08:32<09:34, 4.23it/s] 43%|████▎ | 1823/4250 [08:32<08:47, 4.60it/s] 43%|████▎ | 1824/4250 [08:32<08:32, 4.74it/s] 43%|████▎ | 1825/4250 [08:32<09:23, 4.30it/s] 43%|████▎ | 1826/4250 [08:33<10:59, 3.67it/s] 43%|████▎ | 1827/4250 [08:33<10:49, 3.73it/s] 43%|████▎ | 1828/4250 [08:33<10:30, 3.84it/s] 43%|████▎ | 1829/4250 [08:33<09:07, 4.42it/s] 43%|████▎ | 1830/4250 [08:34<09:23, 4.29it/s] 43%|████▎ | 1831/4250 [08:34<09:22, 4.30it/s] 43%|████▎ | 1832/4250 [08:34<08:42, 4.63it/s] 43%|████▎ | 1833/4250 [08:34<08:26, 4.78it/s] 43%|████▎ | 1834/4250 [08:35<09:58, 4.04it/s] 43%|████▎ | 1835/4250 [08:35<09:17, 4.33it/s] 43%|████▎ | 1836/4250 [08:35<09:41, 4.15it/s] 43%|████▎ | 1837/4250 [08:35<09:33, 4.21it/s] 43%|████▎ | 1838/4250 [08:36<09:07, 4.41it/s] 43%|████▎ | 1839/4250 [08:36<08:36, 4.66it/s] 43%|████▎ | 1840/4250 [08:36<10:33, 3.81it/s] 43%|████▎ | 1841/4250 [08:36<11:33, 3.47it/s] 43%|████▎ | 1842/4250 [08:37<10:53, 3.69it/s] 43%|████▎ | 1843/4250 [08:37<09:51, 4.07it/s] 43%|████▎ | 1844/4250 [08:37<09:36, 4.17it/s] 43%|████▎ | 1845/4250 [08:37<08:31, 4.70it/s] 43%|████▎ | 1846/4250 [08:37<08:18, 4.83it/s] 43%|████▎ | 1847/4250 [08:38<11:05, 3.61it/s] 43%|████▎ | 1848/4250 [08:38<11:54, 3.36it/s] 44%|████▎ | 1849/4250 [08:38<11:08, 3.59it/s] 44%|████▎ | 1850/4250 [08:39<10:16, 3.89it/s] 44%|████▎ | 1851/4250 [08:39<09:54, 4.03it/s] 44%|████▎ | 1852/4250 [08:39<09:41, 4.12it/s] 44%|████▎ | 1853/4250 [08:39<08:39, 4.61it/s] 44%|████▎ | 1854/4250 [08:39<08:10, 4.88it/s] 44%|████▎ | 1855/4250 [08:40<08:36, 4.64it/s] 44%|████▎ | 1856/4250 [08:40<08:45, 4.55it/s] 44%|████▎ | 1857/4250 [08:40<08:19, 4.79it/s] 44%|████▎ | 1858/4250 [08:40<08:34, 4.65it/s] 44%|████▎ | 1859/4250 [08:40<08:03, 4.95it/s] 44%|████▍ | 1860/4250 [08:41<08:20, 4.77it/s] 44%|████▍ | 1861/4250 [08:41<09:12, 4.33it/s] 44%|████▍ | 1862/4250 [08:41<09:14, 4.31it/s] 44%|████▍ | 1863/4250 [08:41<09:10, 4.33it/s] 44%|████▍ | 1864/4250 [08:42<08:50, 4.50it/s] 44%|████▍ | 1865/4250 [08:42<08:48, 4.51it/s] 44%|████▍ | 1866/4250 [08:42<08:16, 4.80it/s] 44%|████▍ | 1867/4250 [08:42<07:52, 5.04it/s] 44%|████▍ | 1868/4250 [08:42<08:19, 4.77it/s] 44%|████▍ | 1869/4250 [08:43<10:06, 3.93it/s] 44%|████▍ | 1870/4250 [08:43<09:22, 4.23it/s] 44%|████▍ | 1871/4250 [08:43<10:10, 3.90it/s] 44%|████▍ | 1872/4250 [08:44<09:58, 3.97it/s] 44%|████▍ | 1873/4250 [08:44<08:57, 4.43it/s] 44%|████▍ | 1874/4250 [08:44<09:05, 4.36it/s] 44%|████▍ | 1875/4250 [08:44<08:51, 4.47it/s] 44%|████▍ | 1876/4250 [08:44<08:46, 4.51it/s] 44%|████▍ | 1877/4250 [08:45<09:45, 4.05it/s] 44%|████▍ | 1878/4250 [08:45<08:51, 4.47it/s] 44%|████▍ | 1879/4250 [08:45<08:58, 4.40it/s] 44%|████▍ | 1880/4250 [08:45<08:55, 4.42it/s] 44%|████▍ | 1881/4250 [08:46<08:36, 4.58it/s] 44%|████▍ | 1882/4250 [08:46<10:10, 3.88it/s] 44%|████▍ | 1883/4250 [08:46<10:08, 3.89it/s] 44%|████▍ | 1884/4250 [08:46<09:26, 4.17it/s] 44%|████▍ | 1885/4250 [08:47<09:01, 4.37it/s] 44%|████▍ | 1886/4250 [08:47<08:31, 4.62it/s] 44%|████▍ | 1887/4250 [08:47<08:44, 4.50it/s] 44%|████▍ | 1888/4250 [08:47<08:46, 4.49it/s] 44%|████▍ | 1889/4250 [08:47<08:19, 4.73it/s] 44%|████▍ | 1890/4250 [08:48<08:24, 4.68it/s] 44%|████▍ | 1891/4250 [08:48<08:16, 4.75it/s] 45%|████▍ | 1892/4250 [08:48<07:49, 5.02it/s] 45%|████▍ | 1893/4250 [08:48<08:14, 4.77it/s] 45%|████▍ | 1894/4250 [08:48<08:09, 4.82it/s] 45%|████▍ | 1895/4250 [08:49<08:30, 4.61it/s] 45%|████▍ | 1896/4250 [08:49<08:27, 4.64it/s] 45%|████▍ | 1897/4250 [08:49<08:24, 4.66it/s] 45%|████▍ | 1898/4250 [08:49<09:53, 3.96it/s] 45%|████▍ | 1899/4250 [08:50<10:32, 3.72it/s] 45%|████▍ | 1900/4250 [08:50<13:23, 2.92it/s] 45%|████▍ | 1901/4250 [08:50<11:54, 3.29it/s] 45%|████▍ | 1902/4250 [08:51<10:49, 3.62it/s] 45%|████▍ | 1903/4250 [08:51<10:31, 3.72it/s] 45%|████▍ | 1904/4250 [08:51<11:51, 3.30it/s] 45%|████▍ | 1905/4250 [08:52<10:58, 3.56it/s] 45%|████▍ | 1906/4250 [08:52<10:38, 3.67it/s] 45%|████▍ | 1907/4250 [08:52<10:45, 3.63it/s] 45%|████▍ | 1908/4250 [08:52<09:33, 4.08it/s] 45%|████▍ | 1909/4250 [08:52<08:30, 4.58it/s] 45%|████▍ | 1910/4250 [08:53<08:42, 4.48it/s] 45%|████▍ | 1911/4250 [08:53<09:18, 4.19it/s] 45%|████▍ | 1912/4250 [08:53<09:33, 4.08it/s] 45%|████▌ | 1913/4250 [08:53<10:40, 3.65it/s] 45%|████▌ | 1914/4250 [08:54<10:12, 3.81it/s] 45%|████▌ | 1915/4250 [08:54<09:08, 4.26it/s] 45%|████▌ | 1916/4250 [08:54<08:19, 4.67it/s] 45%|████▌ | 1917/4250 [08:54<07:53, 4.93it/s] 45%|████▌ | 1918/4250 [08:54<07:48, 4.98it/s] 45%|████▌ | 1919/4250 [08:55<08:49, 4.40it/s] 45%|████▌ | 1920/4250 [08:55<09:08, 4.25it/s] 45%|████▌ | 1921/4250 [08:55<08:50, 4.39it/s] 45%|████▌ | 1922/4250 [08:55<08:30, 4.56it/s] 45%|████▌ | 1923/4250 [08:56<09:23, 4.13it/s] 45%|████▌ | 1924/4250 [08:56<10:46, 3.60it/s] 45%|████▌ | 1925/4250 [08:56<10:19, 3.75it/s] 45%|████▌ | 1926/4250 [08:56<09:14, 4.19it/s] 45%|████▌ | 1927/4250 [08:57<09:13, 4.20it/s] 45%|████▌ | 1928/4250 [08:57<08:31, 4.54it/s] 45%|████▌ | 1929/4250 [08:57<08:10, 4.73it/s] 45%|████▌ | 1930/4250 [08:57<07:59, 4.84it/s] 45%|████▌ | 1931/4250 [08:57<07:40, 5.03it/s] 45%|████▌ | 1932/4250 [08:58<08:56, 4.32it/s] 45%|████▌ | 1933/4250 [08:58<09:44, 3.97it/s] 46%|████▌ | 1934/4250 [08:58<09:01, 4.27it/s] 46%|████▌ | 1935/4250 [08:58<08:33, 4.51it/s] 46%|████▌ | 1936/4250 [08:59<08:51, 4.36it/s] 46%|████▌ | 1937/4250 [08:59<09:21, 4.12it/s] 46%|████▌ | 1938/4250 [08:59<08:48, 4.38it/s] 46%|████▌ | 1939/4250 [08:59<09:02, 4.26it/s] 46%|████▌ | 1940/4250 [09:00<08:49, 4.36it/s] 46%|████▌ | 1941/4250 [09:00<08:31, 4.51it/s] 46%|████▌ | 1942/4250 [09:00<07:59, 4.81it/s] 46%|████▌ | 1943/4250 [09:00<07:50, 4.91it/s] 46%|████▌ | 1944/4250 [09:00<07:34, 5.08it/s] 46%|████▌ | 1945/4250 [09:01<08:24, 4.57it/s] 46%|████▌ | 1946/4250 [09:01<07:52, 4.88it/s] 46%|████▌ | 1947/4250 [09:01<07:47, 4.92it/s] 46%|████▌ | 1948/4250 [09:01<07:42, 4.98it/s] 46%|████▌ | 1949/4250 [09:02<09:28, 4.05it/s] 46%|████▌ | 1950/4250 [09:02<08:46, 4.37it/s] 46%|████▌ | 1951/4250 [09:02<10:08, 3.78it/s] 46%|████▌ | 1952/4250 [09:02<10:50, 3.53it/s] 46%|████▌ | 1953/4250 [09:03<11:26, 3.35it/s] 46%|████▌ | 1954/4250 [09:03<10:36, 3.60it/s] 46%|████▌ | 1955/4250 [09:03<09:51, 3.88it/s] 46%|████▌ | 1956/4250 [09:03<08:53, 4.30it/s] 46%|████▌ | 1957/4250 [09:04<08:40, 4.41it/s] 46%|████▌ | 1958/4250 [09:04<08:38, 4.42it/s] 46%|████▌ | 1959/4250 [09:04<10:22, 3.68it/s] 46%|████▌ | 1960/4250 [09:04<10:22, 3.68it/s] 46%|████▌ | 1961/4250 [09:05<11:29, 3.32it/s] 46%|████▌ | 1962/4250 [09:05<10:24, 3.66it/s] 46%|████▌ | 1963/4250 [09:05<09:28, 4.02it/s] 46%|████▌ | 1964/4250 [09:05<09:00, 4.23it/s] 46%|████▌ | 1965/4250 [09:06<08:39, 4.40it/s] 46%|████▋ | 1966/4250 [09:06<07:59, 4.76it/s] 46%|████▋ | 1967/4250 [09:06<08:50, 4.31it/s] 46%|████▋ | 1968/4250 [09:06<08:10, 4.65it/s] 46%|████▋ | 1969/4250 [09:07<14:41, 2.59it/s] 46%|████▋ | 1970/4250 [09:07<13:44, 2.77it/s] 46%|████▋ | 1971/4250 [09:08<11:45, 3.23it/s] 46%|████▋ | 1972/4250 [09:08<12:36, 3.01it/s] 46%|████▋ | 1973/4250 [09:08<11:11, 3.39it/s] 46%|████▋ | 1974/4250 [09:08<10:24, 3.64it/s] 46%|████▋ | 1975/4250 [09:09<09:22, 4.04it/s] 46%|████▋ | 1976/4250 [09:09<09:31, 3.98it/s] 47%|████▋ | 1977/4250 [09:09<08:54, 4.25it/s] 47%|████▋ | 1978/4250 [09:09<08:38, 4.38it/s] 47%|████▋ | 1979/4250 [09:09<08:39, 4.37it/s] 47%|████▋ | 1980/4250 [09:10<08:30, 4.44it/s] 47%|████▋ | 1981/4250 [09:10<08:01, 4.71it/s] 47%|████▋ | 1982/4250 [09:10<08:48, 4.29it/s] 47%|████▋ | 1983/4250 [09:10<08:10, 4.62it/s] 47%|████▋ | 1984/4250 [09:11<08:46, 4.30it/s] 47%|████▋ | 1985/4250 [09:11<08:01, 4.70it/s] 47%|████▋ | 1986/4250 [09:11<07:50, 4.81it/s] 47%|████▋ | 1987/4250 [09:11<08:25, 4.48it/s] 47%|████▋ | 1988/4250 [09:11<07:46, 4.85it/s] 47%|████▋ | 1989/4250 [09:12<07:41, 4.90it/s] 47%|████▋ | 1990/4250 [09:12<07:21, 5.12it/s] 47%|████▋ | 1991/4250 [09:12<07:02, 5.35it/s] 47%|████▋ | 1992/4250 [09:12<08:52, 4.24it/s] 47%|████▋ | 1993/4250 [09:12<08:24, 4.48it/s] 47%|████▋ | 1994/4250 [09:13<08:00, 4.70it/s] 47%|████▋ | 1995/4250 [09:13<07:46, 4.83it/s] 47%|████▋ | 1996/4250 [09:13<08:09, 4.61it/s] 47%|████▋ | 1997/4250 [09:13<08:20, 4.50it/s] 47%|████▋ | 1998/4250 [09:14<08:09, 4.60it/s] 47%|████▋ | 1999/4250 [09:14<08:41, 4.32it/s] 47%|████▋ | 2000/4250 [09:14<08:47, 4.27it/s] 47%|████▋ | 2000/4250 [09:14<08:47, 4.27it/s] 47%|████▋ | 2001/4250 [09:14<10:52, 3.44it/s] 47%|████▋ | 2002/4250 [09:15<10:14, 3.66it/s] 47%|████▋ | 2003/4250 [09:15<09:27, 3.96it/s] 47%|████▋ | 2004/4250 [09:15<09:22, 3.99it/s] 47%|████▋ | 2005/4250 [09:15<08:59, 4.16it/s] 47%|████▋ | 2006/4250 [09:16<08:05, 4.62it/s] 47%|████▋ | 2007/4250 [09:16<08:28, 4.41it/s] 47%|████▋ | 2008/4250 [09:16<08:29, 4.40it/s] 47%|████▋ | 2009/4250 [09:16<08:16, 4.51it/s] 47%|████▋ | 2010/4250 [09:17<09:29, 3.93it/s] 47%|████▋ | 2011/4250 [09:17<08:40, 4.30it/s] 47%|████▋ | 2012/4250 [09:17<08:12, 4.55it/s] 47%|████▋ | 2013/4250 [09:17<09:08, 4.07it/s] 47%|████▋ | 2014/4250 [09:17<08:50, 4.21it/s] 47%|████▋ | 2015/4250 [09:18<09:13, 4.04it/s] 47%|████▋ | 2016/4250 [09:18<08:57, 4.16it/s] 47%|████▋ | 2017/4250 [09:18<08:33, 4.35it/s] 47%|████▋ | 2018/4250 [09:18<08:08, 4.57it/s] 48%|████▊ | 2019/4250 [09:19<08:08, 4.57it/s] 48%|████▊ | 2020/4250 [09:19<07:38, 4.87it/s] 48%|████▊ | 2021/4250 [09:19<07:19, 5.07it/s] 48%|████▊ | 2022/4250 [09:19<06:56, 5.35it/s] 48%|████▊ | 2023/4250 [09:19<07:14, 5.13it/s] 48%|████▊ | 2024/4250 [09:20<08:04, 4.59it/s] 48%|████▊ | 2025/4250 [09:20<08:09, 4.55it/s] 48%|████▊ | 2026/4250 [09:20<09:46, 3.79it/s] 48%|████▊ | 2027/4250 [09:20<09:27, 3.92it/s] 48%|████▊ | 2028/4250 [09:21<09:00, 4.11it/s] 48%|████▊ | 2029/4250 [09:21<08:54, 4.15it/s] 48%|████▊ | 2030/4250 [09:21<08:32, 4.33it/s] 48%|████▊ | 2031/4250 [09:21<08:26, 4.38it/s] 48%|████▊ | 2032/4250 [09:21<07:55, 4.66it/s] 48%|████▊ | 2033/4250 [09:22<07:37, 4.85it/s] 48%|████▊ | 2034/4250 [09:22<07:34, 4.87it/s] 48%|████▊ | 2035/4250 [09:22<08:10, 4.51it/s] 48%|████▊ | 2036/4250 [09:22<08:29, 4.35it/s] 48%|████▊ | 2037/4250 [09:23<08:09, 4.52it/s] 48%|████▊ | 2038/4250 [09:23<09:01, 4.09it/s] 48%|████▊ | 2039/4250 [09:23<08:13, 4.48it/s] 48%|████▊ | 2040/4250 [09:23<08:33, 4.30it/s] 48%|████▊ | 2041/4250 [09:23<07:43, 4.77it/s] 48%|████▊ | 2042/4250 [09:24<07:32, 4.88it/s] 48%|████▊ | 2043/4250 [09:24<08:35, 4.28it/s] 48%|████▊ | 2044/4250 [09:24<08:10, 4.50it/s] 48%|████▊ | 2045/4250 [09:24<07:55, 4.64it/s] 48%|████▊ | 2046/4250 [09:25<10:00, 3.67it/s] 48%|████▊ | 2047/4250 [09:25<08:56, 4.10it/s] 48%|████▊ | 2048/4250 [09:25<08:55, 4.11it/s] 48%|████▊ | 2049/4250 [09:25<08:10, 4.49it/s] 48%|████▊ | 2050/4250 [09:26<09:42, 3.78it/s] 48%|████▊ | 2051/4250 [09:26<09:21, 3.91it/s] 48%|████▊ | 2052/4250 [09:26<09:57, 3.68it/s] 48%|████▊ | 2053/4250 [09:26<08:59, 4.07it/s] 48%|████▊ | 2054/4250 [09:27<08:14, 4.44it/s] 48%|████▊ | 2055/4250 [09:27<07:46, 4.70it/s] 48%|████▊ | 2056/4250 [09:27<07:21, 4.97it/s] 48%|████▊ | 2057/4250 [09:27<07:20, 4.97it/s] 48%|████▊ | 2058/4250 [09:27<06:49, 5.35it/s] 48%|████▊ | 2059/4250 [09:28<07:28, 4.89it/s] 48%|████▊ | 2060/4250 [09:28<07:29, 4.87it/s] 48%|████▊ | 2061/4250 [09:28<08:28, 4.31it/s] 49%|████▊ | 2062/4250 [09:28<08:14, 4.42it/s] 49%|████▊ | 2063/4250 [09:28<07:40, 4.75it/s] 49%|████▊ | 2064/4250 [09:29<08:08, 4.47it/s] 49%|████▊ | 2065/4250 [09:29<09:48, 3.71it/s] 49%|████▊ | 2066/4250 [09:29<09:24, 3.87it/s] 49%|████▊ | 2067/4250 [09:30<11:55, 3.05it/s] 49%|████▊ | 2068/4250 [09:30<11:15, 3.23it/s] 49%|████▊ | 2069/4250 [09:30<10:18, 3.53it/s] 49%|████▊ | 2070/4250 [09:30<09:33, 3.80it/s] 49%|████▊ | 2071/4250 [09:31<10:15, 3.54it/s] 49%|████▉ | 2072/4250 [09:31<09:41, 3.75it/s] 49%|████▉ | 2073/4250 [09:31<09:08, 3.97it/s] 49%|████▉ | 2074/4250 [09:31<09:14, 3.93it/s] 49%|████▉ | 2075/4250 [09:32<08:40, 4.18it/s] 49%|████▉ | 2076/4250 [09:32<08:14, 4.39it/s] 49%|████▉ | 2077/4250 [09:32<08:33, 4.23it/s] 49%|████▉ | 2078/4250 [09:32<08:58, 4.03it/s] 49%|████▉ | 2079/4250 [09:33<08:33, 4.23it/s] 49%|████▉ | 2080/4250 [09:33<09:04, 3.98it/s] 49%|████▉ | 2081/4250 [09:33<08:32, 4.23it/s] 49%|████▉ | 2082/4250 [09:33<08:47, 4.11it/s] 49%|████▉ | 2083/4250 [09:34<09:06, 3.97it/s] 49%|████▉ | 2084/4250 [09:34<08:26, 4.27it/s] 49%|████▉ | 2085/4250 [09:34<07:48, 4.62it/s] 49%|████▉ | 2086/4250 [09:34<07:57, 4.53it/s] 49%|████▉ | 2087/4250 [09:35<09:02, 3.99it/s] 49%|████▉ | 2088/4250 [09:35<08:17, 4.34it/s] 49%|████▉ | 2089/4250 [09:35<07:59, 4.51it/s] 49%|████▉ | 2090/4250 [09:35<08:04, 4.46it/s] 49%|████▉ | 2091/4250 [09:35<08:36, 4.18it/s] 49%|████▉ | 2092/4250 [09:36<08:34, 4.19it/s] 49%|████▉ | 2093/4250 [09:36<07:51, 4.58it/s] 49%|████▉ | 2094/4250 [09:36<07:59, 4.50it/s] 49%|████▉ | 2095/4250 [09:36<07:38, 4.70it/s] 49%|████▉ | 2096/4250 [09:37<07:39, 4.69it/s] 49%|████▉ | 2097/4250 [09:37<07:50, 4.58it/s] 49%|████▉ | 2098/4250 [09:37<07:36, 4.71it/s] 49%|████▉ | 2099/4250 [09:37<07:45, 4.63it/s] 49%|████▉ | 2100/4250 [09:37<07:42, 4.65it/s] 49%|████▉ | 2101/4250 [09:38<07:29, 4.78it/s] 49%|████▉ | 2102/4250 [09:38<07:01, 5.09it/s] 49%|████▉ | 2103/4250 [09:38<06:58, 5.12it/s] 50%|████▉ | 2104/4250 [09:38<06:52, 5.20it/s] 50%|████▉ | 2105/4250 [09:38<06:55, 5.16it/s] 50%|████▉ | 2106/4250 [09:39<08:23, 4.26it/s] 50%|████▉ | 2107/4250 [09:39<07:32, 4.74it/s] 50%|████▉ | 2108/4250 [09:39<07:39, 4.66it/s] 50%|████▉ | 2109/4250 [09:39<07:45, 4.60it/s] 50%|████▉ | 2110/4250 [09:40<08:22, 4.25it/s] 50%|████▉ | 2111/4250 [09:40<08:00, 4.45it/s] 50%|████▉ | 2112/4250 [09:40<12:38, 2.82it/s] 50%|████▉ | 2113/4250 [09:41<10:55, 3.26it/s] 50%|████▉ | 2114/4250 [09:41<10:20, 3.44it/s] 50%|████▉ | 2115/4250 [09:41<09:17, 3.83it/s] 50%|████▉ | 2116/4250 [09:41<09:30, 3.74it/s] 50%|████▉ | 2117/4250 [09:42<09:25, 3.77it/s] 50%|████▉ | 2118/4250 [09:42<08:15, 4.30it/s] 50%|████▉ | 2119/4250 [09:42<07:39, 4.64it/s] 50%|████▉ | 2120/4250 [09:42<07:56, 4.47it/s] 50%|████▉ | 2121/4250 [09:42<08:08, 4.36it/s] 50%|████▉ | 2122/4250 [09:43<07:45, 4.57it/s] 50%|████▉ | 2123/4250 [09:43<07:31, 4.71it/s] 50%|████▉ | 2124/4250 [09:43<07:38, 4.63it/s] 50%|█████ | 2125/4250 [09:43<07:42, 4.59it/s] 50%|█████ | 2126/4250 [09:44<08:23, 4.22it/s] 50%|█████ | 2127/4250 [09:44<08:13, 4.30it/s][INFO|trainer.py:805] 2024-08-30 20:35:33,181 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: tokens, ner_tags, id. If tokens, ner_tags, id are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3788] 2024-08-30 20:35:33,184 >> ***** Running Evaluation ***** [INFO|trainer.py:3790] 2024-08-30 20:35:33,184 >> Num examples = 6810 [INFO|trainer.py:3793] 2024-08-30 20:35:33,184 >> Batch size = 8 {'eval_loss': 0.09221930056810379, 'eval_precision': 0.775441735629613, 'eval_recall': 0.8111839026672906, 'eval_f1': 0.7929102344196683, 'eval_accuracy': 0.9757026926826589, 'eval_runtime': 14.825, 'eval_samples_per_second': 459.361, 'eval_steps_per_second': 57.471, 'epoch': 4.0} {'loss': 0.0169, 'grad_norm': 0.49960169196128845, 'learning_rate': 2.647058823529412e-05, 'epoch': 4.7} 0%| | 0/852 [00:00> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-2127 [INFO|configuration_utils.py:472] 2024-08-30 20:35:47,553 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-2127/config.json [INFO|modeling_utils.py:2690] 2024-08-30 20:35:48,877 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-2127/model.safetensors [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:35:48,878 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-2127/tokenizer_config.json [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:35:48,879 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-2127/special_tokens_map.json [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:35:51,191 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:35:51,191 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json 50%|█████ | 2128/4250 [10:02<3:21:06, 5.69s/it] 50%|█████ | 2129/4250 [10:02<2:22:55, 4.04s/it] 50%|█████ | 2130/4250 [10:03<1:41:39, 2.88s/it] 50%|█████ | 2131/4250 [10:03<1:13:05, 2.07s/it] 50%|█████ | 2132/4250 [10:03<55:00, 1.56s/it] 50%|█████ | 2133/4250 [10:03<41:44, 1.18s/it] 50%|█████ | 2134/4250 [10:04<30:43, 1.15it/s] 50%|█████ | 2135/4250 [10:04<23:51, 1.48it/s] 50%|█████ | 2136/4250 [10:04<19:10, 1.84it/s] 50%|█████ | 2137/4250 [10:04<15:21, 2.29it/s] 50%|█████ | 2138/4250 [10:04<14:05, 2.50it/s] 50%|█████ | 2139/4250 [10:05<12:11, 2.89it/s] 50%|█████ | 2140/4250 [10:05<10:34, 3.33it/s] 50%|█████ | 2141/4250 [10:05<09:43, 3.62it/s] 50%|█████ | 2142/4250 [10:05<10:27, 3.36it/s] 50%|█████ | 2143/4250 [10:06<10:42, 3.28it/s] 50%|█████ | 2144/4250 [10:06<09:58, 3.52it/s] 50%|█████ | 2145/4250 [10:06<09:43, 3.61it/s] 50%|█████ | 2146/4250 [10:06<08:43, 4.02it/s] 51%|█████ | 2147/4250 [10:07<08:24, 4.17it/s] 51%|█████ | 2148/4250 [10:07<08:33, 4.09it/s] 51%|█████ | 2149/4250 [10:07<10:37, 3.30it/s] 51%|█████ | 2150/4250 [10:08<09:41, 3.61it/s] 51%|█████ | 2151/4250 [10:08<08:40, 4.03it/s] 51%|█████ | 2152/4250 [10:08<08:18, 4.21it/s] 51%|█████ | 2153/4250 [10:08<07:26, 4.70it/s] 51%|█████ | 2154/4250 [10:08<07:13, 4.84it/s] 51%|█████ | 2155/4250 [10:09<07:10, 4.86it/s] 51%|█████ | 2156/4250 [10:09<06:57, 5.02it/s] 51%|█████ | 2157/4250 [10:09<07:12, 4.84it/s] 51%|█████ | 2158/4250 [10:09<08:15, 4.22it/s] 51%|█████ | 2159/4250 [10:10<10:52, 3.21it/s] 51%|█████ | 2160/4250 [10:10<09:50, 3.54it/s] 51%|█████ | 2161/4250 [10:10<09:10, 3.80it/s] 51%|█████ | 2162/4250 [10:10<09:48, 3.55it/s] 51%|█████ | 2163/4250 [10:11<09:00, 3.86it/s] 51%|█████ | 2164/4250 [10:11<07:58, 4.36it/s] 51%|█████ | 2165/4250 [10:11<07:40, 4.53it/s] 51%|█████ | 2166/4250 [10:11<07:46, 4.47it/s] 51%|█████ | 2167/4250 [10:12<07:51, 4.42it/s] 51%|█████ | 2168/4250 [10:12<08:15, 4.20it/s] 51%|█████ | 2169/4250 [10:12<07:57, 4.36it/s] 51%|█████ | 2170/4250 [10:12<08:37, 4.02it/s] 51%|█████ | 2171/4250 [10:13<09:48, 3.54it/s] 51%|█████ | 2172/4250 [10:13<08:51, 3.91it/s] 51%|█████ | 2173/4250 [10:13<08:24, 4.11it/s] 51%|█████ | 2174/4250 [10:13<07:51, 4.40it/s] 51%|█████ | 2175/4250 [10:13<07:33, 4.57it/s] 51%|█████ | 2176/4250 [10:14<08:34, 4.03it/s] 51%|█████ | 2177/4250 [10:14<08:18, 4.16it/s] 51%|█████ | 2178/4250 [10:14<08:31, 4.05it/s] 51%|█████▏ | 2179/4250 [10:14<08:20, 4.14it/s] 51%|█████▏ | 2180/4250 [10:15<08:11, 4.21it/s] 51%|█████▏ | 2181/4250 [10:15<09:11, 3.75it/s] 51%|█████▏ | 2182/4250 [10:15<08:43, 3.95it/s] 51%|█████▏ | 2183/4250 [10:15<08:16, 4.17it/s] 51%|█████▏ | 2184/4250 [10:16<08:27, 4.07it/s] 51%|█████▏ | 2185/4250 [10:16<08:06, 4.24it/s] 51%|█████▏ | 2186/4250 [10:16<08:12, 4.19it/s] 51%|█████▏ | 2187/4250 [10:17<09:57, 3.45it/s] 51%|█████▏ | 2188/4250 [10:17<09:15, 3.71it/s] 52%|█████▏ | 2189/4250 [10:17<08:32, 4.02it/s] 52%|█████▏ | 2190/4250 [10:17<07:51, 4.37it/s] 52%|█████▏ | 2191/4250 [10:17<08:36, 3.99it/s] 52%|█████▏ | 2192/4250 [10:18<08:22, 4.09it/s] 52%|█████▏ | 2193/4250 [10:18<07:51, 4.36it/s] 52%|█████▏ | 2194/4250 [10:18<07:06, 4.82it/s] 52%|█████▏ | 2195/4250 [10:18<07:26, 4.60it/s] 52%|█████▏ | 2196/4250 [10:19<08:15, 4.14it/s] 52%|█████▏ | 2197/4250 [10:19<08:38, 3.96it/s] 52%|█████▏ | 2198/4250 [10:19<07:54, 4.32it/s] 52%|█████▏ | 2199/4250 [10:19<07:59, 4.28it/s] 52%|█████▏ | 2200/4250 [10:20<07:34, 4.51it/s] 52%|█████▏ | 2201/4250 [10:20<07:41, 4.44it/s] 52%|█████▏ | 2202/4250 [10:20<07:49, 4.36it/s] 52%|█████▏ | 2203/4250 [10:20<07:22, 4.62it/s] 52%|█████▏ | 2204/4250 [10:20<07:30, 4.55it/s] 52%|█████▏ | 2205/4250 [10:21<09:00, 3.78it/s] 52%|█████▏ | 2206/4250 [10:21<08:11, 4.16it/s] 52%|█████▏ | 2207/4250 [10:21<08:44, 3.90it/s] 52%|█████▏ | 2208/4250 [10:21<08:03, 4.22it/s] 52%|█████▏ | 2209/4250 [10:22<07:19, 4.64it/s] 52%|█████▏ | 2210/4250 [10:22<07:16, 4.68it/s] 52%|█████▏ | 2211/4250 [10:22<07:01, 4.84it/s] 52%|█████▏ | 2212/4250 [10:22<06:43, 5.05it/s] 52%|█████▏ | 2213/4250 [10:22<07:25, 4.58it/s] 52%|█████▏ | 2214/4250 [10:23<07:09, 4.75it/s] 52%|█████▏ | 2215/4250 [10:23<07:11, 4.72it/s] 52%|█████▏ | 2216/4250 [10:23<07:57, 4.26it/s] 52%|█████▏ | 2217/4250 [10:23<07:33, 4.48it/s] 52%|█████▏ | 2218/4250 [10:24<07:41, 4.40it/s] 52%|█████▏ | 2219/4250 [10:24<07:11, 4.70it/s] 52%|█████▏ | 2220/4250 [10:24<06:58, 4.86it/s] 52%|█████▏ | 2221/4250 [10:24<07:38, 4.42it/s] 52%|█████▏ | 2222/4250 [10:24<07:57, 4.25it/s] 52%|█████▏ | 2223/4250 [10:25<07:40, 4.40it/s] 52%|█████▏ | 2224/4250 [10:25<08:01, 4.20it/s] 52%|█████▏ | 2225/4250 [10:25<07:23, 4.57it/s] 52%|█████▏ | 2226/4250 [10:25<07:18, 4.61it/s] 52%|█████▏ | 2227/4250 [10:26<08:37, 3.91it/s] 52%|█████▏ | 2228/4250 [10:26<08:16, 4.08it/s] 52%|█████▏ | 2229/4250 [10:26<07:59, 4.22it/s] 52%|█████▏ | 2230/4250 [10:26<07:43, 4.36it/s] 52%|█████▏ | 2231/4250 [10:27<07:32, 4.46it/s] 53%|█████▎ | 2232/4250 [10:27<07:17, 4.62it/s] 53%|█████▎ | 2233/4250 [10:27<07:18, 4.60it/s] 53%|█████▎ | 2234/4250 [10:27<07:37, 4.41it/s] 53%|█████▎ | 2235/4250 [10:27<07:43, 4.35it/s] 53%|█████▎ | 2236/4250 [10:28<07:55, 4.24it/s] 53%|█████▎ | 2237/4250 [10:28<07:31, 4.46it/s] 53%|█████▎ | 2238/4250 [10:28<06:58, 4.81it/s] 53%|█████▎ | 2239/4250 [10:28<07:23, 4.54it/s] 53%|█████▎ | 2240/4250 [10:28<06:54, 4.85it/s] 53%|█████▎ | 2241/4250 [10:29<06:53, 4.86it/s] 53%|█████▎ | 2242/4250 [10:29<07:19, 4.56it/s] 53%|█████▎ | 2243/4250 [10:29<07:35, 4.40it/s] 53%|█████▎ | 2244/4250 [10:29<07:04, 4.72it/s] 53%|█████▎ | 2245/4250 [10:30<08:22, 3.99it/s] 53%|█████▎ | 2246/4250 [10:30<08:51, 3.77it/s] 53%|█████▎ | 2247/4250 [10:30<08:29, 3.93it/s] 53%|█████▎ | 2248/4250 [10:30<07:40, 4.35it/s] 53%|█████▎ | 2249/4250 [10:31<07:16, 4.58it/s] 53%|█████▎ | 2250/4250 [10:31<07:15, 4.59it/s] 53%|█████▎ | 2251/4250 [10:31<06:46, 4.91it/s] 53%|█████▎ | 2252/4250 [10:31<07:20, 4.53it/s] 53%|█████▎ | 2253/4250 [10:32<08:14, 4.04it/s] 53%|█████▎ | 2254/4250 [10:32<07:40, 4.34it/s] 53%|█████▎ | 2255/4250 [10:32<07:31, 4.42it/s] 53%|█████▎ | 2256/4250 [10:32<08:28, 3.92it/s] 53%|█████▎ | 2257/4250 [10:32<07:52, 4.22it/s] 53%|█████▎ | 2258/4250 [10:33<07:04, 4.69it/s] 53%|█████▎ | 2259/4250 [10:33<08:20, 3.98it/s] 53%|█████▎ | 2260/4250 [10:33<07:32, 4.39it/s] 53%|█████▎ | 2261/4250 [10:33<07:23, 4.48it/s] 53%|█████▎ | 2262/4250 [10:34<07:52, 4.20it/s] 53%|█████▎ | 2263/4250 [10:34<08:09, 4.06it/s] 53%|█████▎ | 2264/4250 [10:34<07:52, 4.21it/s] 53%|█████▎ | 2265/4250 [10:34<07:49, 4.22it/s] 53%|█████▎ | 2266/4250 [10:35<08:11, 4.04it/s] 53%|█████▎ | 2267/4250 [10:35<08:15, 4.00it/s] 53%|█████▎ | 2268/4250 [10:35<07:32, 4.38it/s] 53%|█████▎ | 2269/4250 [10:35<07:00, 4.71it/s] 53%|█████▎ | 2270/4250 [10:35<06:59, 4.72it/s] 53%|█████▎ | 2271/4250 [10:36<08:16, 3.99it/s] 53%|█████▎ | 2272/4250 [10:36<07:59, 4.12it/s] 53%|█████▎ | 2273/4250 [10:37<13:03, 2.52it/s] 54%|█████▎ | 2274/4250 [10:37<10:56, 3.01it/s] 54%|█████▎ | 2275/4250 [10:37<09:35, 3.43it/s] 54%|█████▎ | 2276/4250 [10:37<08:31, 3.86it/s] 54%|█████▎ | 2277/4250 [10:38<08:22, 3.93it/s] 54%|█████▎ | 2278/4250 [10:38<07:56, 4.13it/s] 54%|█████▎ | 2279/4250 [10:38<08:47, 3.74it/s] 54%|█████▎ | 2280/4250 [10:38<08:36, 3.81it/s] 54%|█████▎ | 2281/4250 [10:39<08:22, 3.92it/s] 54%|█████▎ | 2282/4250 [10:39<09:16, 3.54it/s] 54%|█████▎ | 2283/4250 [10:39<08:25, 3.89it/s] 54%|█████▎ | 2284/4250 [10:39<08:08, 4.02it/s] 54%|█████▍ | 2285/4250 [10:40<08:06, 4.04it/s] 54%|█████▍ | 2286/4250 [10:40<08:52, 3.69it/s] 54%|█████▍ | 2287/4250 [10:40<09:04, 3.61it/s] 54%|█████▍ | 2288/4250 [10:40<08:50, 3.70it/s] 54%|█████▍ | 2289/4250 [10:41<08:29, 3.85it/s] 54%|█████▍ | 2290/4250 [10:41<08:17, 3.94it/s] 54%|█████▍ | 2291/4250 [10:41<08:34, 3.81it/s] 54%|█████▍ | 2292/4250 [10:41<08:04, 4.04it/s] 54%|█████▍ | 2293/4250 [10:42<08:18, 3.92it/s] 54%|█████▍ | 2294/4250 [10:42<08:13, 3.97it/s] 54%|█████▍ | 2295/4250 [10:42<07:58, 4.09it/s] 54%|█████▍ | 2296/4250 [10:43<12:06, 2.69it/s] 54%|█████▍ | 2297/4250 [10:43<10:33, 3.08it/s] 54%|█████▍ | 2298/4250 [10:43<10:34, 3.08it/s] 54%|█████▍ | 2299/4250 [10:44<09:09, 3.55it/s] 54%|█████▍ | 2300/4250 [10:44<08:31, 3.81it/s] 54%|█████▍ | 2301/4250 [10:44<07:49, 4.15it/s] 54%|█████▍ | 2302/4250 [10:44<07:27, 4.35it/s] 54%|█████▍ | 2303/4250 [10:45<09:09, 3.54it/s] 54%|█████▍ | 2304/4250 [10:45<07:54, 4.10it/s] 54%|█████▍ | 2305/4250 [10:45<07:35, 4.27it/s] 54%|█████▍ | 2306/4250 [10:45<07:33, 4.28it/s] 54%|█████▍ | 2307/4250 [10:45<07:12, 4.49it/s] 54%|█████▍ | 2308/4250 [10:46<07:13, 4.48it/s] 54%|█████▍ | 2309/4250 [10:46<06:50, 4.73it/s] 54%|█████▍ | 2310/4250 [10:46<07:11, 4.50it/s] 54%|█████▍ | 2311/4250 [10:46<06:56, 4.65it/s] 54%|█████▍ | 2312/4250 [10:46<06:43, 4.81it/s] 54%|█████▍ | 2313/4250 [10:47<06:21, 5.08it/s] 54%|█████▍ | 2314/4250 [10:47<06:11, 5.22it/s] 54%|█████▍ | 2315/4250 [10:47<05:57, 5.42it/s] 54%|█████▍ | 2316/4250 [10:47<06:18, 5.11it/s] 55%|█████▍ | 2317/4250 [10:47<06:06, 5.28it/s] 55%|█████▍ | 2318/4250 [10:48<06:38, 4.85it/s] 55%|█████▍ | 2319/4250 [10:48<09:38, 3.34it/s] 55%|█████▍ | 2320/4250 [10:48<08:34, 3.75it/s] 55%|█████▍ | 2321/4250 [10:49<08:24, 3.82it/s] 55%|█████▍ | 2322/4250 [10:49<08:17, 3.88it/s] 55%|█████▍ | 2323/4250 [10:49<09:04, 3.54it/s] 55%|█████▍ | 2324/4250 [10:49<08:27, 3.79it/s] 55%|█████▍ | 2325/4250 [10:50<07:52, 4.07it/s] 55%|█████▍ | 2326/4250 [10:50<07:54, 4.05it/s] 55%|█████▍ | 2327/4250 [10:50<12:00, 2.67it/s] 55%|█████▍ | 2328/4250 [10:51<10:55, 2.93it/s] 55%|█████▍ | 2329/4250 [10:51<09:19, 3.43it/s] 55%|█████▍ | 2330/4250 [10:51<08:24, 3.80it/s] 55%|█████▍ | 2331/4250 [10:51<08:26, 3.79it/s] 55%|█████▍ | 2332/4250 [10:52<08:08, 3.93it/s] 55%|█████▍ | 2333/4250 [10:52<07:30, 4.26it/s] 55%|█████▍ | 2334/4250 [10:52<07:12, 4.44it/s] 55%|█████▍ | 2335/4250 [10:52<07:44, 4.12it/s] 55%|█████▍ | 2336/4250 [10:52<07:07, 4.48it/s] 55%|█████▍ | 2337/4250 [10:53<07:10, 4.45it/s] 55%|█████▌ | 2338/4250 [10:53<06:37, 4.81it/s] 55%|█████▌ | 2339/4250 [10:53<06:08, 5.19it/s] 55%|█████▌ | 2340/4250 [10:53<06:47, 4.69it/s] 55%|█████▌ | 2341/4250 [10:54<07:08, 4.45it/s] 55%|█████▌ | 2342/4250 [10:54<07:42, 4.13it/s] 55%|█████▌ | 2343/4250 [10:54<07:55, 4.01it/s] 55%|█████▌ | 2344/4250 [10:54<07:02, 4.51it/s] 55%|█████▌ | 2345/4250 [10:54<06:49, 4.65it/s] 55%|█████▌ | 2346/4250 [10:55<07:00, 4.52it/s] 55%|█████▌ | 2347/4250 [10:55<06:46, 4.68it/s] 55%|█████▌ | 2348/4250 [10:55<07:19, 4.33it/s] 55%|█████▌ | 2349/4250 [10:55<06:59, 4.54it/s] 55%|█████▌ | 2350/4250 [10:56<06:55, 4.57it/s] 55%|█████▌ | 2351/4250 [10:56<06:40, 4.74it/s] 55%|█████▌ | 2352/4250 [10:56<06:29, 4.88it/s] 55%|█████▌ | 2353/4250 [10:56<07:03, 4.48it/s] 55%|█████▌ | 2354/4250 [10:57<10:05, 3.13it/s] 55%|█████▌ | 2355/4250 [10:57<10:14, 3.08it/s] 55%|█████▌ | 2356/4250 [10:57<08:47, 3.59it/s] 55%|█████▌ | 2357/4250 [10:57<07:47, 4.05it/s] 55%|█████▌ | 2358/4250 [10:58<08:18, 3.79it/s] 56%|█████▌ | 2359/4250 [10:58<07:56, 3.97it/s] 56%|█████▌ | 2360/4250 [10:58<07:21, 4.28it/s] 56%|█████▌ | 2361/4250 [10:58<06:58, 4.51it/s] 56%|█████▌ | 2362/4250 [10:59<07:02, 4.47it/s] 56%|█████▌ | 2363/4250 [10:59<06:34, 4.78it/s] 56%|█████▌ | 2364/4250 [10:59<06:36, 4.75it/s] 56%|█████▌ | 2365/4250 [10:59<06:12, 5.07it/s] 56%|█████▌ | 2366/4250 [10:59<06:49, 4.60it/s] 56%|█████▌ | 2367/4250 [11:00<07:43, 4.06it/s] 56%|█████▌ | 2368/4250 [11:00<07:32, 4.15it/s] 56%|█████▌ | 2369/4250 [11:00<06:49, 4.59it/s] 56%|█████▌ | 2370/4250 [11:00<06:35, 4.76it/s] 56%|█████▌ | 2371/4250 [11:00<06:17, 4.98it/s] 56%|█████▌ | 2372/4250 [11:01<06:21, 4.92it/s] 56%|█████▌ | 2373/4250 [11:01<06:02, 5.18it/s] 56%|█████▌ | 2374/4250 [11:01<06:46, 4.62it/s] 56%|█████▌ | 2375/4250 [11:01<06:39, 4.69it/s] 56%|█████▌ | 2376/4250 [11:02<06:38, 4.70it/s] 56%|█████▌ | 2377/4250 [11:02<06:40, 4.67it/s] 56%|█████▌ | 2378/4250 [11:02<06:01, 5.19it/s] 56%|█████▌ | 2379/4250 [11:02<05:52, 5.31it/s] 56%|█████▌ | 2380/4250 [11:02<05:40, 5.50it/s] 56%|█████▌ | 2381/4250 [11:03<06:33, 4.75it/s] 56%|█████▌ | 2382/4250 [11:03<07:07, 4.37it/s] 56%|█████▌ | 2383/4250 [11:03<07:20, 4.24it/s] 56%|█████▌ | 2384/4250 [11:03<07:45, 4.01it/s] 56%|█████▌ | 2385/4250 [11:04<07:02, 4.42it/s] 56%|█████▌ | 2386/4250 [11:04<07:23, 4.20it/s] 56%|█████▌ | 2387/4250 [11:04<07:14, 4.29it/s] 56%|█████▌ | 2388/4250 [11:04<07:36, 4.08it/s] 56%|█████▌ | 2389/4250 [11:04<07:08, 4.34it/s] 56%|█████▌ | 2390/4250 [11:05<07:06, 4.36it/s] 56%|█████▋ | 2391/4250 [11:05<06:35, 4.70it/s] 56%|█████▋ | 2392/4250 [11:05<06:20, 4.88it/s] 56%|█████▋ | 2393/4250 [11:05<06:14, 4.96it/s] 56%|█████▋ | 2394/4250 [11:06<06:59, 4.43it/s] 56%|█████▋ | 2395/4250 [11:06<08:32, 3.62it/s] 56%|█████▋ | 2396/4250 [11:06<07:50, 3.94it/s] 56%|█████▋ | 2397/4250 [11:06<08:40, 3.56it/s] 56%|█████▋ | 2398/4250 [11:07<07:30, 4.11it/s] 56%|█████▋ | 2399/4250 [11:07<06:55, 4.46it/s] 56%|█████▋ | 2400/4250 [11:07<06:38, 4.64it/s] 56%|█████▋ | 2401/4250 [11:07<06:17, 4.90it/s] 57%|█████▋ | 2402/4250 [11:07<06:31, 4.72it/s] 57%|█████▋ | 2403/4250 [11:08<07:11, 4.28it/s] 57%|█████▋ | 2404/4250 [11:08<07:04, 4.35it/s] 57%|█████▋ | 2405/4250 [11:08<07:01, 4.38it/s] 57%|█████▋ | 2406/4250 [11:08<06:45, 4.55it/s] 57%|█████▋ | 2407/4250 [11:09<06:30, 4.71it/s] 57%|█████▋ | 2408/4250 [11:09<05:58, 5.13it/s] 57%|█████▋ | 2409/4250 [11:09<06:30, 4.71it/s] 57%|█████▋ | 2410/4250 [11:09<06:13, 4.92it/s] 57%|█████▋ | 2411/4250 [11:09<06:15, 4.89it/s] 57%|█████▋ | 2412/4250 [11:10<06:30, 4.70it/s] 57%|█████▋ | 2413/4250 [11:10<06:20, 4.83it/s] 57%|█████▋ | 2414/4250 [11:10<06:51, 4.46it/s] 57%|█████▋ | 2415/4250 [11:10<08:49, 3.46it/s] 57%|█████▋ | 2416/4250 [11:11<08:30, 3.59it/s] 57%|█████▋ | 2417/4250 [11:11<07:34, 4.03it/s] 57%|█████▋ | 2418/4250 [11:11<08:07, 3.75it/s] 57%|█████▋ | 2419/4250 [11:11<07:31, 4.06it/s] 57%|█████▋ | 2420/4250 [11:12<06:49, 4.46it/s] 57%|█████▋ | 2421/4250 [11:12<07:54, 3.85it/s] 57%|█████▋ | 2422/4250 [11:12<07:52, 3.87it/s] 57%|█████▋ | 2423/4250 [11:12<07:35, 4.01it/s] 57%|█████▋ | 2424/4250 [11:13<07:37, 3.99it/s] 57%|█████▋ | 2425/4250 [11:13<08:06, 3.75it/s] 57%|█████▋ | 2426/4250 [11:13<07:44, 3.92it/s] 57%|█████▋ | 2427/4250 [11:13<07:57, 3.82it/s] 57%|█████▋ | 2428/4250 [11:14<07:08, 4.25it/s] 57%|█████▋ | 2429/4250 [11:14<07:07, 4.26it/s] 57%|█████▋ | 2430/4250 [11:14<08:20, 3.64it/s] 57%|█████▋ | 2431/4250 [11:15<08:19, 3.64it/s] 57%|█████▋ | 2432/4250 [11:15<07:22, 4.11it/s] 57%|█████▋ | 2433/4250 [11:15<06:40, 4.53it/s] 57%|█████▋ | 2434/4250 [11:15<08:01, 3.77it/s] 57%|█████▋ | 2435/4250 [11:15<07:24, 4.08it/s] 57%|█████▋ | 2436/4250 [11:16<07:16, 4.16it/s] 57%|█████▋ | 2437/4250 [11:16<07:21, 4.10it/s] 57%|█████▋ | 2438/4250 [11:16<06:39, 4.54it/s] 57%|█████▋ | 2439/4250 [11:16<08:14, 3.66it/s] 57%|█████▋ | 2440/4250 [11:17<07:31, 4.01it/s] 57%|█████▋ | 2441/4250 [11:17<06:53, 4.38it/s] 57%|█████▋ | 2442/4250 [11:17<06:41, 4.50it/s] 57%|█████▋ | 2443/4250 [11:17<06:21, 4.73it/s] 58%|█████▊ | 2444/4250 [11:17<06:05, 4.94it/s] 58%|█████▊ | 2445/4250 [11:18<06:19, 4.75it/s] 58%|█████▊ | 2446/4250 [11:18<07:37, 3.94it/s] 58%|█████▊ | 2447/4250 [11:18<07:39, 3.92it/s] 58%|█████▊ | 2448/4250 [11:18<06:51, 4.38it/s] 58%|█████▊ | 2449/4250 [11:19<06:31, 4.59it/s] 58%|█████▊ | 2450/4250 [11:19<06:35, 4.55it/s] 58%|█████▊ | 2451/4250 [11:19<06:29, 4.62it/s] 58%|█████▊ | 2452/4250 [11:19<06:11, 4.84it/s] 58%|█████▊ | 2453/4250 [11:20<07:12, 4.16it/s] 58%|█████▊ | 2454/4250 [11:20<07:07, 4.21it/s] 58%|█████▊ | 2455/4250 [11:20<07:30, 3.99it/s] 58%|█████▊ | 2456/4250 [11:20<07:19, 4.08it/s] 58%|█████▊ | 2457/4250 [11:20<06:35, 4.53it/s] 58%|█████▊ | 2458/4250 [11:21<06:14, 4.79it/s] 58%|█████▊ | 2459/4250 [11:21<06:31, 4.57it/s] 58%|█████▊ | 2460/4250 [11:21<06:10, 4.83it/s] 58%|█████▊ | 2461/4250 [11:21<06:22, 4.68it/s] 58%|█████▊ | 2462/4250 [11:21<06:22, 4.68it/s] 58%|█████▊ | 2463/4250 [11:22<06:15, 4.75it/s] 58%|█████▊ | 2464/4250 [11:22<05:53, 5.06it/s] 58%|█████▊ | 2465/4250 [11:22<06:48, 4.37it/s] 58%|█████▊ | 2466/4250 [11:22<06:50, 4.35it/s] 58%|█████▊ | 2467/4250 [11:23<08:50, 3.36it/s] 58%|█████▊ | 2468/4250 [11:23<09:03, 3.28it/s] 58%|█████▊ | 2469/4250 [11:23<07:52, 3.77it/s] 58%|█████▊ | 2470/4250 [11:24<07:16, 4.08it/s] 58%|█████▊ | 2471/4250 [11:24<07:43, 3.84it/s] 58%|█████▊ | 2472/4250 [11:24<07:03, 4.19it/s] 58%|█████▊ | 2473/4250 [11:24<06:57, 4.26it/s] 58%|█████▊ | 2474/4250 [11:25<10:04, 2.94it/s] 58%|█████▊ | 2475/4250 [11:25<08:49, 3.35it/s] 58%|█████▊ | 2476/4250 [11:25<08:03, 3.67it/s] 58%|█████▊ | 2477/4250 [11:26<07:48, 3.79it/s] 58%|█████▊ | 2478/4250 [11:26<07:28, 3.95it/s] 58%|█████▊ | 2479/4250 [11:26<07:09, 4.13it/s] 58%|█████▊ | 2480/4250 [11:26<06:53, 4.28it/s] 58%|█████▊ | 2481/4250 [11:26<06:17, 4.69it/s] 58%|█████▊ | 2482/4250 [11:26<05:55, 4.97it/s] 58%|█████▊ | 2483/4250 [11:27<06:23, 4.61it/s] 58%|█████▊ | 2484/4250 [11:27<07:21, 4.00it/s] 58%|█████▊ | 2485/4250 [11:27<07:29, 3.93it/s] 58%|█████▊ | 2486/4250 [11:28<07:06, 4.13it/s] 59%|█████▊ | 2487/4250 [11:28<08:08, 3.61it/s] 59%|█████▊ | 2488/4250 [11:28<07:27, 3.94it/s] 59%|█████▊ | 2489/4250 [11:28<08:14, 3.56it/s] 59%|█████▊ | 2490/4250 [11:29<07:28, 3.93it/s] 59%|█████▊ | 2491/4250 [11:29<06:56, 4.22it/s] 59%|█████▊ | 2492/4250 [11:29<06:41, 4.38it/s] 59%|█████▊ | 2493/4250 [11:30<10:41, 2.74it/s] 59%|█████▊ | 2494/4250 [11:30<09:13, 3.17it/s] 59%|█████▊ | 2495/4250 [11:30<09:32, 3.07it/s] 59%|█████▊ | 2496/4250 [11:31<08:44, 3.35it/s] 59%|█████▉ | 2497/4250 [11:31<08:26, 3.46it/s] 59%|█████▉ | 2498/4250 [11:31<07:59, 3.66it/s] 59%|█████▉ | 2499/4250 [11:31<07:17, 4.00it/s] 59%|█████▉ | 2500/4250 [11:32<07:58, 3.66it/s] 59%|█████▉ | 2500/4250 [11:32<07:58, 3.66it/s] 59%|█████▉ | 2501/4250 [11:32<07:06, 4.10it/s] 59%|█████▉ | 2502/4250 [11:32<07:04, 4.12it/s] 59%|█████▉ | 2503/4250 [11:32<06:59, 4.17it/s] 59%|█████▉ | 2504/4250 [11:32<06:42, 4.34it/s] 59%|█████▉ | 2505/4250 [11:33<06:12, 4.68it/s] 59%|█████▉ | 2506/4250 [11:33<06:29, 4.48it/s] 59%|█████▉ | 2507/4250 [11:33<06:11, 4.69it/s] 59%|█████▉ | 2508/4250 [11:33<06:47, 4.27it/s] 59%|█████▉ | 2509/4250 [11:34<06:42, 4.33it/s] 59%|█████▉ | 2510/4250 [11:34<06:44, 4.30it/s] 59%|█████▉ | 2511/4250 [11:34<06:25, 4.51it/s] 59%|█████▉ | 2512/4250 [11:34<06:07, 4.73it/s] 59%|█████▉ | 2513/4250 [11:34<06:58, 4.15it/s] 59%|█████▉ | 2514/4250 [11:35<06:40, 4.34it/s] 59%|█████▉ | 2515/4250 [11:35<06:17, 4.60it/s] 59%|█████▉ | 2516/4250 [11:35<06:37, 4.36it/s] 59%|█████▉ | 2517/4250 [11:35<07:40, 3.76it/s] 59%|█████▉ | 2518/4250 [11:36<07:23, 3.90it/s] 59%|█████▉ | 2519/4250 [11:36<06:58, 4.13it/s] 59%|█████▉ | 2520/4250 [11:36<07:03, 4.08it/s] 59%|█████▉ | 2521/4250 [11:36<07:07, 4.04it/s] 59%|█████▉ | 2522/4250 [11:37<07:23, 3.90it/s] 59%|█████▉ | 2523/4250 [11:37<07:42, 3.74it/s] 59%|█████▉ | 2524/4250 [11:37<07:44, 3.71it/s] 59%|█████▉ | 2525/4250 [11:37<07:05, 4.05it/s] 59%|█████▉ | 2526/4250 [11:38<06:35, 4.35it/s] 59%|█████▉ | 2527/4250 [11:38<06:08, 4.68it/s] 59%|█████▉ | 2528/4250 [11:38<06:06, 4.69it/s] 60%|█████▉ | 2529/4250 [11:38<05:58, 4.80it/s] 60%|█████▉ | 2530/4250 [11:38<06:02, 4.75it/s] 60%|█████▉ | 2531/4250 [11:39<06:08, 4.67it/s] 60%|█████▉ | 2532/4250 [11:39<05:52, 4.88it/s] 60%|█████▉ | 2533/4250 [11:39<06:17, 4.54it/s] 60%|█████▉ | 2534/4250 [11:39<07:46, 3.68it/s] 60%|█████▉ | 2535/4250 [11:40<07:05, 4.03it/s] 60%|█████▉ | 2536/4250 [11:40<06:38, 4.30it/s] 60%|█████▉ | 2537/4250 [11:40<07:02, 4.05it/s] 60%|█████▉ | 2538/4250 [11:40<07:16, 3.92it/s] 60%|█████▉ | 2539/4250 [11:41<06:28, 4.40it/s] 60%|█████▉ | 2540/4250 [11:41<06:01, 4.73it/s] 60%|█████▉ | 2541/4250 [11:41<06:36, 4.31it/s] 60%|█████▉ | 2542/4250 [11:41<06:39, 4.27it/s] 60%|█████▉ | 2543/4250 [11:41<06:22, 4.46it/s] 60%|█████▉ | 2544/4250 [11:42<06:00, 4.73it/s] 60%|█████▉ | 2545/4250 [11:42<05:56, 4.78it/s] 60%|█████▉ | 2546/4250 [11:42<05:53, 4.82it/s] 60%|█████▉ | 2547/4250 [11:42<06:16, 4.53it/s] 60%|█████▉ | 2548/4250 [11:43<06:01, 4.70it/s] 60%|█████▉ | 2549/4250 [11:43<05:49, 4.86it/s] 60%|██████ | 2550/4250 [11:43<06:12, 4.57it/s] 60%|██████ | 2551/4250 [11:43<06:25, 4.41it/s] 60%|██████ | 2552/4250 [11:44<07:00, 4.04it/s] 60%|██████ | 2553/4250 [11:44<06:54, 4.09it/s][INFO|trainer.py:805] 2024-08-30 20:37:33,098 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: tokens, ner_tags, id. If tokens, ner_tags, id are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3788] 2024-08-30 20:37:33,100 >> ***** Running Evaluation ***** [INFO|trainer.py:3790] 2024-08-30 20:37:33,100 >> Num examples = 6810 [INFO|trainer.py:3793] 2024-08-30 20:37:33,100 >> Batch size = 8 {'eval_loss': 0.09940312057733536, 'eval_precision': 0.7584782608695653, 'eval_recall': 0.816331305568554, 'eval_f1': 0.7863421230561191, 'eval_accuracy': 0.974439424938553, 'eval_runtime': 14.3671, 'eval_samples_per_second': 473.999, 'eval_steps_per_second': 59.302, 'epoch': 5.0} {'loss': 0.0114, 'grad_norm': 0.6507154703140259, 'learning_rate': 2.058823529411765e-05, 'epoch': 5.88} 0%| | 0/852 [00:00> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-2553 [INFO|configuration_utils.py:472] 2024-08-30 20:37:47,636 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-2553/config.json [INFO|modeling_utils.py:2690] 2024-08-30 20:37:48,898 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-2553/model.safetensors [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:37:48,899 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-2553/tokenizer_config.json [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:37:48,899 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-2553/special_tokens_map.json [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:37:51,199 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:37:51,200 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json 60%|██████ | 2554/4250 [12:02<2:40:40, 5.68s/it] 60%|██████ | 2555/4250 [12:02<1:54:06, 4.04s/it] 60%|██████ | 2556/4250 [12:02<1:21:21, 2.88s/it] 60%|██████ | 2557/4250 [12:03<1:01:11, 2.17s/it] 60%|██████ | 2558/4250 [12:03<44:25, 1.58s/it] 60%|██████ | 2559/4250 [12:03<32:38, 1.16s/it] 60%|██████ | 2560/4250 [12:04<25:12, 1.12it/s] 60%|██████ | 2561/4250 [12:04<19:42, 1.43it/s] 60%|██████ | 2562/4250 [12:04<15:37, 1.80it/s] 60%|██████ | 2563/4250 [12:04<13:45, 2.04it/s] 60%|██████ | 2564/4250 [12:05<11:34, 2.43it/s] 60%|██████ | 2565/4250 [12:05<10:13, 2.75it/s] 60%|██████ | 2566/4250 [12:05<08:58, 3.13it/s] 60%|██████ | 2567/4250 [12:05<09:04, 3.09it/s] 60%|██████ | 2568/4250 [12:06<07:54, 3.54it/s] 60%|██████ | 2569/4250 [12:06<07:08, 3.93it/s] 60%|██████ | 2570/4250 [12:06<06:37, 4.22it/s] 60%|██████ | 2571/4250 [12:06<06:59, 4.00it/s] 61%|██████ | 2572/4250 [12:07<06:30, 4.29it/s] 61%|██████ | 2573/4250 [12:07<06:25, 4.35it/s] 61%|██████ | 2574/4250 [12:07<06:41, 4.18it/s] 61%|██████ | 2575/4250 [12:07<06:28, 4.31it/s] 61%|██████ | 2576/4250 [12:07<06:36, 4.22it/s] 61%|██████ | 2577/4250 [12:08<06:02, 4.62it/s] 61%|██████ | 2578/4250 [12:08<06:12, 4.49it/s] 61%|██████ | 2579/4250 [12:08<06:24, 4.35it/s] 61%|██████ | 2580/4250 [12:08<06:32, 4.26it/s] 61%|██████ | 2581/4250 [12:09<06:51, 4.05it/s] 61%|██████ | 2582/4250 [12:09<06:22, 4.36it/s] 61%|██████ | 2583/4250 [12:09<07:23, 3.76it/s] 61%|██████ | 2584/4250 [12:09<06:56, 4.00it/s] 61%|██████ | 2585/4250 [12:10<08:09, 3.40it/s] 61%|██████ | 2586/4250 [12:10<07:08, 3.88it/s] 61%|██████ | 2587/4250 [12:10<08:07, 3.41it/s] 61%|██████ | 2588/4250 [12:11<07:24, 3.74it/s] 61%|██████ | 2589/4250 [12:11<06:44, 4.11it/s] 61%|██████ | 2590/4250 [12:11<06:56, 3.99it/s] 61%|██████ | 2591/4250 [12:11<06:17, 4.40it/s] 61%|██████ | 2592/4250 [12:12<10:49, 2.55it/s] 61%|██████ | 2593/4250 [12:12<09:21, 2.95it/s] 61%|██████ | 2594/4250 [12:12<08:03, 3.43it/s] 61%|██████ | 2595/4250 [12:13<07:19, 3.77it/s] 61%|██████ | 2596/4250 [12:13<06:35, 4.18it/s] 61%|██████ | 2597/4250 [12:13<06:04, 4.54it/s] 61%|██████ | 2598/4250 [12:13<07:19, 3.76it/s] 61%|██████ | 2599/4250 [12:14<07:04, 3.89it/s] 61%|██████ | 2600/4250 [12:14<07:33, 3.64it/s] 61%|██████ | 2601/4250 [12:14<07:12, 3.82it/s] 61%|██████ | 2602/4250 [12:14<06:51, 4.00it/s] 61%|██████ | 2603/4250 [12:15<06:31, 4.21it/s] 61%|██████▏ | 2604/4250 [12:15<06:32, 4.19it/s] 61%|██████▏ | 2605/4250 [12:15<06:13, 4.41it/s] 61%|██████▏ | 2606/4250 [12:15<06:11, 4.43it/s] 61%|██████▏ | 2607/4250 [12:15<06:20, 4.32it/s] 61%|██████▏ | 2608/4250 [12:16<06:30, 4.20it/s] 61%|██████▏ | 2609/4250 [12:16<06:20, 4.31it/s] 61%|██████▏ | 2610/4250 [12:16<06:06, 4.48it/s] 61%|██████▏ | 2611/4250 [12:16<05:32, 4.93it/s] 61%|██████▏ | 2612/4250 [12:16<05:37, 4.86it/s] 61%|██████▏ | 2613/4250 [12:17<05:38, 4.83it/s] 62%|██████▏ | 2614/4250 [12:17<05:37, 4.85it/s] 62%|██████▏ | 2615/4250 [12:17<05:38, 4.83it/s] 62%|██████▏ | 2616/4250 [12:17<05:17, 5.15it/s] 62%|██████▏ | 2617/4250 [12:17<05:27, 4.99it/s] 62%|██████▏ | 2618/4250 [12:18<05:35, 4.86it/s] 62%|██████▏ | 2619/4250 [12:18<05:31, 4.91it/s] 62%|██████▏ | 2620/4250 [12:18<05:29, 4.95it/s] 62%|██████▏ | 2621/4250 [12:18<05:29, 4.95it/s] 62%|██████▏ | 2622/4250 [12:19<06:01, 4.50it/s] 62%|██████▏ | 2623/4250 [12:19<05:39, 4.79it/s] 62%|██████▏ | 2624/4250 [12:19<05:57, 4.55it/s] 62%|██████▏ | 2625/4250 [12:19<05:42, 4.74it/s] 62%|██████▏ | 2626/4250 [12:19<05:15, 5.14it/s] 62%|██████▏ | 2627/4250 [12:20<05:26, 4.98it/s] 62%|██████▏ | 2628/4250 [12:20<05:54, 4.58it/s] 62%|██████▏ | 2629/4250 [12:20<05:34, 4.85it/s] 62%|██████▏ | 2630/4250 [12:20<05:54, 4.56it/s] 62%|██████▏ | 2631/4250 [12:20<05:29, 4.92it/s] 62%|██████▏ | 2632/4250 [12:21<05:35, 4.83it/s] 62%|██████▏ | 2633/4250 [12:21<05:35, 4.82it/s] 62%|██████▏ | 2634/4250 [12:21<05:07, 5.25it/s] 62%|██████▏ | 2635/4250 [12:21<05:11, 5.19it/s] 62%|██████▏ | 2636/4250 [12:21<06:05, 4.42it/s] 62%|██████▏ | 2637/4250 [12:22<06:07, 4.39it/s] 62%|██████▏ | 2638/4250 [12:22<05:41, 4.72it/s] 62%|██████▏ | 2639/4250 [12:22<05:52, 4.57it/s] 62%|██████▏ | 2640/4250 [12:22<06:51, 3.91it/s] 62%|██████▏ | 2641/4250 [12:23<06:29, 4.14it/s] 62%|██████▏ | 2642/4250 [12:23<05:49, 4.60it/s] 62%|██████▏ | 2643/4250 [12:23<05:42, 4.70it/s] 62%|██████▏ | 2644/4250 [12:23<06:03, 4.42it/s] 62%|██████▏ | 2645/4250 [12:23<05:57, 4.49it/s] 62%|██████▏ | 2646/4250 [12:24<06:01, 4.44it/s] 62%|██████▏ | 2647/4250 [12:24<05:59, 4.46it/s] 62%|██████▏ | 2648/4250 [12:24<06:35, 4.05it/s] 62%|██████▏ | 2649/4250 [12:24<06:28, 4.12it/s] 62%|██████▏ | 2650/4250 [12:25<05:57, 4.47it/s] 62%|██████▏ | 2651/4250 [12:25<05:33, 4.80it/s] 62%|██████▏ | 2652/4250 [12:25<06:47, 3.92it/s] 62%|██████▏ | 2653/4250 [12:25<06:26, 4.13it/s] 62%|██████▏ | 2654/4250 [12:26<06:12, 4.28it/s] 62%|██████▏ | 2655/4250 [12:26<05:56, 4.48it/s] 62%|██████▏ | 2656/4250 [12:26<05:37, 4.73it/s] 63%|██████▎ | 2657/4250 [12:26<05:30, 4.82it/s] 63%|██████▎ | 2658/4250 [12:26<05:18, 4.99it/s] 63%|██████▎ | 2659/4250 [12:27<05:05, 5.20it/s] 63%|██████▎ | 2660/4250 [12:27<05:23, 4.92it/s] 63%|██████▎ | 2661/4250 [12:27<05:00, 5.29it/s] 63%|██████▎ | 2662/4250 [12:27<05:31, 4.79it/s] 63%|██████▎ | 2663/4250 [12:27<05:20, 4.96it/s] 63%|██████▎ | 2664/4250 [12:28<05:25, 4.88it/s] 63%|██████▎ | 2665/4250 [12:28<05:24, 4.89it/s] 63%|██████▎ | 2666/4250 [12:28<05:32, 4.77it/s] 63%|██████▎ | 2667/4250 [12:28<06:58, 3.79it/s] 63%|██████▎ | 2668/4250 [12:29<06:51, 3.84it/s] 63%|██████▎ | 2669/4250 [12:29<06:51, 3.84it/s] 63%|██████▎ | 2670/4250 [12:29<06:23, 4.12it/s] 63%|██████▎ | 2671/4250 [12:29<05:43, 4.60it/s] 63%|██████▎ | 2672/4250 [12:29<05:30, 4.77it/s] 63%|██████▎ | 2673/4250 [12:30<05:05, 5.17it/s] 63%|██████▎ | 2674/4250 [12:30<05:08, 5.10it/s] 63%|██████▎ | 2675/4250 [12:30<05:25, 4.84it/s] 63%|██████▎ | 2676/4250 [12:30<05:35, 4.69it/s] 63%|██████▎ | 2677/4250 [12:31<06:26, 4.07it/s] 63%|██████▎ | 2678/4250 [12:31<06:55, 3.79it/s] 63%|██████▎ | 2679/4250 [12:31<07:31, 3.48it/s] 63%|██████▎ | 2680/4250 [12:31<06:55, 3.78it/s] 63%|██████▎ | 2681/4250 [12:32<06:23, 4.09it/s] 63%|██████▎ | 2682/4250 [12:32<06:49, 3.83it/s] 63%|██████▎ | 2683/4250 [12:32<06:21, 4.10it/s] 63%|██████▎ | 2684/4250 [12:32<06:11, 4.22it/s] 63%|██████▎ | 2685/4250 [12:33<06:32, 3.99it/s] 63%|██████▎ | 2686/4250 [12:33<06:05, 4.28it/s] 63%|██████▎ | 2687/4250 [12:33<05:54, 4.41it/s] 63%|██████▎ | 2688/4250 [12:33<05:14, 4.96it/s] 63%|██████▎ | 2689/4250 [12:33<05:08, 5.06it/s] 63%|██████▎ | 2690/4250 [12:34<04:58, 5.22it/s] 63%|██████▎ | 2691/4250 [12:34<04:29, 5.77it/s] 63%|██████▎ | 2692/4250 [12:34<04:42, 5.52it/s] 63%|██████▎ | 2693/4250 [12:34<05:37, 4.61it/s] 63%|██████▎ | 2694/4250 [12:35<06:33, 3.95it/s] 63%|██████▎ | 2695/4250 [12:35<07:50, 3.30it/s] 63%|██████▎ | 2696/4250 [12:35<06:58, 3.72it/s] 63%|██████▎ | 2697/4250 [12:35<06:09, 4.20it/s] 63%|██████▎ | 2698/4250 [12:36<06:01, 4.30it/s] 64%|██████▎ | 2699/4250 [12:36<06:11, 4.18it/s] 64%|██████▎ | 2700/4250 [12:36<05:42, 4.53it/s] 64%|██████▎ | 2701/4250 [12:36<05:29, 4.70it/s] 64%|██████▎ | 2702/4250 [12:36<05:28, 4.71it/s] 64%|██████▎ | 2703/4250 [12:37<05:54, 4.36it/s] 64%|██████▎ | 2704/4250 [12:37<05:58, 4.32it/s] 64%|██████▎ | 2705/4250 [12:37<05:43, 4.50it/s] 64%|██████▎ | 2706/4250 [12:37<05:29, 4.68it/s] 64%|██████▎ | 2707/4250 [12:38<05:31, 4.66it/s] 64%|██████▎ | 2708/4250 [12:38<05:22, 4.78it/s] 64%|██████▎ | 2709/4250 [12:38<05:21, 4.80it/s] 64%|██████▍ | 2710/4250 [12:38<05:15, 4.88it/s] 64%|██████▍ | 2711/4250 [12:38<05:33, 4.62it/s] 64%|██████▍ | 2712/4250 [12:39<05:14, 4.89it/s] 64%|██████▍ | 2713/4250 [12:39<06:20, 4.04it/s] 64%|██████▍ | 2714/4250 [12:39<06:15, 4.09it/s] 64%|██████▍ | 2715/4250 [12:39<06:02, 4.23it/s] 64%|██████▍ | 2716/4250 [12:40<05:42, 4.48it/s] 64%|██████▍ | 2717/4250 [12:40<05:32, 4.62it/s] 64%|██████▍ | 2718/4250 [12:40<05:59, 4.26it/s] 64%|██████▍ | 2719/4250 [12:41<10:41, 2.39it/s] 64%|██████▍ | 2720/4250 [12:41<08:59, 2.84it/s] 64%|██████▍ | 2721/4250 [12:41<09:32, 2.67it/s] 64%|██████▍ | 2722/4250 [12:42<08:54, 2.86it/s] 64%|██████▍ | 2723/4250 [12:42<07:47, 3.27it/s] 64%|██████▍ | 2724/4250 [12:42<07:05, 3.59it/s] 64%|██████▍ | 2725/4250 [12:42<06:44, 3.77it/s] 64%|██████▍ | 2726/4250 [12:43<06:12, 4.09it/s] 64%|██████▍ | 2727/4250 [12:43<05:42, 4.45it/s] 64%|██████▍ | 2728/4250 [12:43<07:28, 3.39it/s] 64%|██████▍ | 2729/4250 [12:43<06:47, 3.74it/s] 64%|██████▍ | 2730/4250 [12:44<06:06, 4.15it/s] 64%|██████▍ | 2731/4250 [12:44<06:07, 4.14it/s] 64%|██████▍ | 2732/4250 [12:44<05:32, 4.56it/s] 64%|██████▍ | 2733/4250 [12:44<05:19, 4.74it/s] 64%|██████▍ | 2734/4250 [12:44<05:38, 4.49it/s] 64%|██████▍ | 2735/4250 [12:45<05:19, 4.75it/s] 64%|██████▍ | 2736/4250 [12:45<05:07, 4.93it/s] 64%|██████▍ | 2737/4250 [12:45<05:14, 4.81it/s] 64%|██████▍ | 2738/4250 [12:45<05:56, 4.24it/s] 64%|██████▍ | 2739/4250 [12:46<05:41, 4.42it/s] 64%|██████▍ | 2740/4250 [12:46<06:10, 4.08it/s] 64%|██████▍ | 2741/4250 [12:46<05:36, 4.49it/s] 65%|██████▍ | 2742/4250 [12:46<05:41, 4.42it/s] 65%|██████▍ | 2743/4250 [12:47<05:44, 4.37it/s] 65%|██████▍ | 2744/4250 [12:47<05:32, 4.53it/s] 65%|██████▍ | 2745/4250 [12:47<05:33, 4.52it/s] 65%|██████▍ | 2746/4250 [12:47<05:41, 4.40it/s] 65%|██████▍ | 2747/4250 [12:48<06:33, 3.82it/s] 65%|██████▍ | 2748/4250 [12:48<06:29, 3.85it/s] 65%|██████▍ | 2749/4250 [12:48<06:38, 3.76it/s] 65%|██████▍ | 2750/4250 [12:48<06:34, 3.80it/s] 65%|██████▍ | 2751/4250 [12:49<08:02, 3.11it/s] 65%|██████▍ | 2752/4250 [12:49<07:01, 3.55it/s] 65%|██████▍ | 2753/4250 [12:49<07:10, 3.47it/s] 65%|██████▍ | 2754/4250 [12:49<06:28, 3.85it/s] 65%|██████▍ | 2755/4250 [12:50<06:00, 4.15it/s] 65%|██████▍ | 2756/4250 [12:50<05:34, 4.46it/s] 65%|██████▍ | 2757/4250 [12:50<06:37, 3.76it/s] 65%|██████▍ | 2758/4250 [12:50<06:01, 4.13it/s] 65%|██████▍ | 2759/4250 [12:51<05:42, 4.36it/s] 65%|██████▍ | 2760/4250 [12:51<05:16, 4.70it/s] 65%|██████▍ | 2761/4250 [12:51<05:03, 4.91it/s] 65%|██████▍ | 2762/4250 [12:51<05:04, 4.88it/s] 65%|██████▌ | 2763/4250 [12:51<05:00, 4.95it/s] 65%|██████▌ | 2764/4250 [12:52<05:25, 4.57it/s] 65%|██████▌ | 2765/4250 [12:52<05:26, 4.54it/s] 65%|██████▌ | 2766/4250 [12:52<05:42, 4.34it/s] 65%|██████▌ | 2767/4250 [12:52<05:44, 4.30it/s] 65%|██████▌ | 2768/4250 [12:53<05:42, 4.32it/s] 65%|██████▌ | 2769/4250 [12:53<05:16, 4.68it/s] 65%|██████▌ | 2770/4250 [12:53<05:08, 4.80it/s] 65%|██████▌ | 2771/4250 [12:53<05:33, 4.44it/s] 65%|██████▌ | 2772/4250 [12:53<05:25, 4.54it/s] 65%|██████▌ | 2773/4250 [12:54<05:23, 4.57it/s] 65%|██████▌ | 2774/4250 [12:54<05:48, 4.23it/s] 65%|██████▌ | 2775/4250 [12:54<05:37, 4.37it/s] 65%|██████▌ | 2776/4250 [12:54<06:17, 3.91it/s] 65%|██████▌ | 2777/4250 [12:55<05:39, 4.34it/s] 65%|██████▌ | 2778/4250 [12:55<05:19, 4.61it/s] 65%|██████▌ | 2779/4250 [12:55<06:09, 3.98it/s] 65%|██████▌ | 2780/4250 [12:55<05:49, 4.21it/s] 65%|██████▌ | 2781/4250 [12:56<05:34, 4.39it/s] 65%|██████▌ | 2782/4250 [12:56<05:32, 4.41it/s] 65%|██████▌ | 2783/4250 [12:56<06:29, 3.77it/s] 66%|██████▌ | 2784/4250 [12:56<06:24, 3.81it/s] 66%|██████▌ | 2785/4250 [12:57<05:47, 4.22it/s] 66%|██████▌ | 2786/4250 [12:57<05:56, 4.11it/s] 66%|██████▌ | 2787/4250 [12:57<06:00, 4.06it/s] 66%|██████▌ | 2788/4250 [12:57<06:10, 3.94it/s] 66%|██████▌ | 2789/4250 [12:58<05:59, 4.07it/s] 66%|██████▌ | 2790/4250 [12:58<05:32, 4.39it/s] 66%|██████▌ | 2791/4250 [12:58<05:08, 4.73it/s] 66%|██████▌ | 2792/4250 [12:58<06:11, 3.92it/s] 66%|██████▌ | 2793/4250 [12:58<05:45, 4.21it/s] 66%|██████▌ | 2794/4250 [12:59<05:12, 4.65it/s] 66%|██████▌ | 2795/4250 [12:59<05:46, 4.20it/s] 66%|██████▌ | 2796/4250 [12:59<06:04, 3.98it/s] 66%|██████▌ | 2797/4250 [12:59<05:56, 4.08it/s] 66%|██████▌ | 2798/4250 [13:00<05:43, 4.23it/s] 66%|██████▌ | 2799/4250 [13:00<05:50, 4.14it/s] 66%|██████▌ | 2800/4250 [13:00<05:31, 4.38it/s] 66%|██████▌ | 2801/4250 [13:00<05:50, 4.13it/s] 66%|██████▌ | 2802/4250 [13:01<05:52, 4.11it/s] 66%|██████▌ | 2803/4250 [13:01<06:24, 3.76it/s] 66%|██████▌ | 2804/4250 [13:01<06:08, 3.92it/s] 66%|██████▌ | 2805/4250 [13:01<05:35, 4.31it/s] 66%|██████▌ | 2806/4250 [13:02<05:13, 4.61it/s] 66%|██████▌ | 2807/4250 [13:02<04:53, 4.92it/s] 66%|██████▌ | 2808/4250 [13:02<05:07, 4.69it/s] 66%|██████▌ | 2809/4250 [13:02<07:03, 3.40it/s] 66%|██████▌ | 2810/4250 [13:03<06:48, 3.53it/s] 66%|██████▌ | 2811/4250 [13:03<06:28, 3.70it/s] 66%|██████▌ | 2812/4250 [13:03<06:10, 3.88it/s] 66%|██████▌ | 2813/4250 [13:03<06:00, 3.98it/s] 66%|██████▌ | 2814/4250 [13:04<05:39, 4.23it/s] 66%|██████▌ | 2815/4250 [13:04<05:30, 4.34it/s] 66%|██████▋ | 2816/4250 [13:04<05:18, 4.51it/s] 66%|██████▋ | 2817/4250 [13:04<06:44, 3.55it/s] 66%|██████▋ | 2818/4250 [13:05<06:19, 3.77it/s] 66%|██████▋ | 2819/4250 [13:05<05:57, 4.00it/s] 66%|██████▋ | 2820/4250 [13:05<06:48, 3.50it/s] 66%|██████▋ | 2821/4250 [13:05<06:17, 3.78it/s] 66%|██████▋ | 2822/4250 [13:06<06:26, 3.70it/s] 66%|██████▋ | 2823/4250 [13:06<05:47, 4.11it/s] 66%|██████▋ | 2824/4250 [13:06<05:39, 4.20it/s] 66%|██████▋ | 2825/4250 [13:07<07:08, 3.33it/s] 66%|██████▋ | 2826/4250 [13:07<06:31, 3.63it/s] 67%|██████▋ | 2827/4250 [13:07<06:21, 3.73it/s] 67%|██████▋ | 2828/4250 [13:07<05:48, 4.09it/s] 67%|██████▋ | 2829/4250 [13:07<05:50, 4.05it/s] 67%|██████▋ | 2830/4250 [13:08<05:33, 4.25it/s] 67%|██████▋ | 2831/4250 [13:08<05:19, 4.44it/s] 67%|██████▋ | 2832/4250 [13:08<05:51, 4.04it/s] 67%|██████▋ | 2833/4250 [13:08<05:39, 4.17it/s] 67%|██████▋ | 2834/4250 [13:09<05:22, 4.39it/s] 67%|██████▋ | 2835/4250 [13:09<05:34, 4.24it/s] 67%|██████▋ | 2836/4250 [13:09<06:44, 3.50it/s] 67%|██████▋ | 2837/4250 [13:09<06:11, 3.81it/s] 67%|██████▋ | 2838/4250 [13:10<05:53, 3.99it/s] 67%|██████▋ | 2839/4250 [13:10<05:49, 4.04it/s] 67%|██████▋ | 2840/4250 [13:10<05:41, 4.13it/s] 67%|██████▋ | 2841/4250 [13:10<05:54, 3.98it/s] 67%|██████▋ | 2842/4250 [13:11<05:33, 4.23it/s] 67%|██████▋ | 2843/4250 [13:11<05:25, 4.32it/s] 67%|██████▋ | 2844/4250 [13:11<05:28, 4.28it/s] 67%|██████▋ | 2845/4250 [13:11<05:39, 4.14it/s] 67%|██████▋ | 2846/4250 [13:12<06:41, 3.49it/s] 67%|██████▋ | 2847/4250 [13:12<07:21, 3.17it/s] 67%|██████▋ | 2848/4250 [13:12<07:00, 3.34it/s] 67%|██████▋ | 2849/4250 [13:13<06:22, 3.66it/s] 67%|██████▋ | 2850/4250 [13:13<06:15, 3.73it/s] 67%|██████▋ | 2851/4250 [13:13<06:23, 3.64it/s] 67%|██████▋ | 2852/4250 [13:13<06:42, 3.48it/s] 67%|██████▋ | 2853/4250 [13:14<06:41, 3.48it/s] 67%|██████▋ | 2854/4250 [13:14<06:41, 3.48it/s] 67%|██████▋ | 2855/4250 [13:14<06:28, 3.59it/s] 67%|██████▋ | 2856/4250 [13:15<06:08, 3.78it/s] 67%|██████▋ | 2857/4250 [13:15<05:44, 4.04it/s] 67%|██████▋ | 2858/4250 [13:15<05:16, 4.39it/s] 67%|██████▋ | 2859/4250 [13:15<05:22, 4.32it/s] 67%|██████▋ | 2860/4250 [13:15<05:25, 4.28it/s] 67%|██████▋ | 2861/4250 [13:16<05:17, 4.38it/s] 67%|██████▋ | 2862/4250 [13:16<05:37, 4.12it/s] 67%|██████▋ | 2863/4250 [13:17<08:11, 2.82it/s] 67%|██████▋ | 2864/4250 [13:17<07:11, 3.21it/s] 67%|██████▋ | 2865/4250 [13:17<06:20, 3.64it/s] 67%|██████▋ | 2866/4250 [13:17<05:38, 4.09it/s] 67%|██████▋ | 2867/4250 [13:17<05:54, 3.90it/s] 67%|██████▋ | 2868/4250 [13:18<06:21, 3.62it/s] 68%|██████▊ | 2869/4250 [13:18<05:44, 4.01it/s] 68%|██████▊ | 2870/4250 [13:18<05:25, 4.25it/s] 68%|██████▊ | 2871/4250 [13:18<05:42, 4.02it/s] 68%|██████▊ | 2872/4250 [13:19<05:23, 4.26it/s] 68%|██████▊ | 2873/4250 [13:19<05:08, 4.47it/s] 68%|██████▊ | 2874/4250 [13:19<05:22, 4.26it/s] 68%|██████▊ | 2875/4250 [13:19<04:54, 4.67it/s] 68%|██████▊ | 2876/4250 [13:19<04:58, 4.61it/s] 68%|██████▊ | 2877/4250 [13:20<05:50, 3.92it/s] 68%|██████▊ | 2878/4250 [13:20<05:34, 4.10it/s] 68%|██████▊ | 2879/4250 [13:20<05:22, 4.26it/s] 68%|██████▊ | 2880/4250 [13:20<05:09, 4.43it/s] 68%|██████▊ | 2881/4250 [13:21<05:12, 4.38it/s] 68%|██████▊ | 2882/4250 [13:21<05:21, 4.25it/s] 68%|██████▊ | 2883/4250 [13:21<05:30, 4.14it/s] 68%|██████▊ | 2884/4250 [13:21<05:16, 4.32it/s] 68%|██████▊ | 2885/4250 [13:21<04:46, 4.77it/s] 68%|██████▊ | 2886/4250 [13:22<04:31, 5.02it/s] 68%|██████▊ | 2887/4250 [13:22<04:34, 4.97it/s] 68%|██████▊ | 2888/4250 [13:22<05:31, 4.11it/s] 68%|██████▊ | 2889/4250 [13:23<05:58, 3.79it/s] 68%|██████▊ | 2890/4250 [13:23<07:47, 2.91it/s] 68%|██████▊ | 2891/4250 [13:23<07:48, 2.90it/s] 68%|██████▊ | 2892/4250 [13:24<06:55, 3.27it/s] 68%|██████▊ | 2893/4250 [13:24<06:13, 3.63it/s] 68%|██████▊ | 2894/4250 [13:24<05:56, 3.81it/s] 68%|██████▊ | 2895/4250 [13:24<05:17, 4.27it/s] 68%|██████▊ | 2896/4250 [13:24<04:56, 4.56it/s] 68%|██████▊ | 2897/4250 [13:25<04:39, 4.84it/s] 68%|██████▊ | 2898/4250 [13:25<04:49, 4.68it/s] 68%|██████▊ | 2899/4250 [13:25<04:42, 4.79it/s] 68%|██████▊ | 2900/4250 [13:25<05:02, 4.47it/s] 68%|██████▊ | 2901/4250 [13:25<04:51, 4.63it/s] 68%|██████▊ | 2902/4250 [13:26<04:40, 4.81it/s] 68%|██████▊ | 2903/4250 [13:26<04:39, 4.82it/s] 68%|██████▊ | 2904/4250 [13:26<04:32, 4.93it/s] 68%|██████▊ | 2905/4250 [13:26<04:43, 4.74it/s] 68%|██████▊ | 2906/4250 [13:27<04:51, 4.60it/s] 68%|██████▊ | 2907/4250 [13:27<07:45, 2.89it/s] 68%|██████▊ | 2908/4250 [13:27<06:48, 3.29it/s] 68%|██████▊ | 2909/4250 [13:28<06:27, 3.46it/s] 68%|██████▊ | 2910/4250 [13:28<05:43, 3.90it/s] 68%|██████▊ | 2911/4250 [13:28<05:09, 4.33it/s] 69%|██████▊ | 2912/4250 [13:28<05:20, 4.17it/s] 69%|██████▊ | 2913/4250 [13:28<05:06, 4.37it/s] 69%|██████▊ | 2914/4250 [13:29<05:05, 4.38it/s] 69%|██████▊ | 2915/4250 [13:29<04:55, 4.52it/s] 69%|██████▊ | 2916/4250 [13:29<04:55, 4.52it/s] 69%|██████▊ | 2917/4250 [13:30<06:09, 3.61it/s] 69%|██████▊ | 2918/4250 [13:30<06:33, 3.38it/s] 69%|██████▊ | 2919/4250 [13:30<06:35, 3.36it/s] 69%|██████▊ | 2920/4250 [13:30<05:54, 3.75it/s] 69%|██████▊ | 2921/4250 [13:31<05:16, 4.21it/s] 69%|██████▉ | 2922/4250 [13:31<05:32, 3.99it/s] 69%|██████▉ | 2923/4250 [13:31<05:06, 4.32it/s] 69%|██████▉ | 2924/4250 [13:31<06:08, 3.60it/s] 69%|██████▉ | 2925/4250 [13:32<05:30, 4.01it/s] 69%|██████▉ | 2926/4250 [13:32<04:58, 4.44it/s] 69%|██████▉ | 2927/4250 [13:32<05:21, 4.12it/s] 69%|██████▉ | 2928/4250 [13:32<05:04, 4.35it/s] 69%|██████▉ | 2929/4250 [13:32<04:59, 4.42it/s] 69%|██████▉ | 2930/4250 [13:33<05:00, 4.39it/s] 69%|██████▉ | 2931/4250 [13:33<04:43, 4.64it/s] 69%|██████▉ | 2932/4250 [13:33<05:03, 4.35it/s] 69%|██████▉ | 2933/4250 [13:33<05:06, 4.30it/s] 69%|██████▉ | 2934/4250 [13:34<05:22, 4.08it/s] 69%|██████▉ | 2935/4250 [13:34<04:54, 4.47it/s] 69%|██████▉ | 2936/4250 [13:34<04:52, 4.50it/s] 69%|██████▉ | 2937/4250 [13:34<04:48, 4.55it/s] 69%|██████▉ | 2938/4250 [13:34<05:04, 4.31it/s] 69%|██████▉ | 2939/4250 [13:35<04:49, 4.53it/s] 69%|██████▉ | 2940/4250 [13:35<05:24, 4.04it/s] 69%|██████▉ | 2941/4250 [13:35<04:54, 4.45it/s] 69%|██████▉ | 2942/4250 [13:35<05:12, 4.19it/s] 69%|██████▉ | 2943/4250 [13:36<05:44, 3.79it/s] 69%|██████▉ | 2944/4250 [13:36<05:34, 3.90it/s] 69%|██████▉ | 2945/4250 [13:36<05:52, 3.70it/s] 69%|██████▉ | 2946/4250 [13:37<05:41, 3.82it/s] 69%|██████▉ | 2947/4250 [13:37<06:19, 3.43it/s] 69%|██████▉ | 2948/4250 [13:37<06:01, 3.60it/s] 69%|██████▉ | 2949/4250 [13:37<05:25, 4.00it/s] 69%|██████▉ | 2950/4250 [13:38<05:12, 4.15it/s] 69%|██████▉ | 2951/4250 [13:38<05:05, 4.25it/s] 69%|██████▉ | 2952/4250 [13:38<04:45, 4.54it/s] 69%|██████▉ | 2953/4250 [13:38<04:39, 4.65it/s] 70%|██████▉ | 2954/4250 [13:38<04:28, 4.83it/s] 70%|██████▉ | 2955/4250 [13:39<04:31, 4.76it/s] 70%|██████▉ | 2956/4250 [13:39<04:49, 4.47it/s] 70%|██████▉ | 2957/4250 [13:39<04:45, 4.53it/s] 70%|██████▉ | 2958/4250 [13:39<04:33, 4.72it/s] 70%|██████▉ | 2959/4250 [13:39<04:27, 4.83it/s] 70%|██████▉ | 2960/4250 [13:40<05:02, 4.26it/s] 70%|██████▉ | 2961/4250 [13:40<04:57, 4.33it/s] 70%|██████▉ | 2962/4250 [13:40<04:56, 4.34it/s] 70%|██████▉ | 2963/4250 [13:40<04:55, 4.36it/s] 70%|██████▉ | 2964/4250 [13:41<05:04, 4.23it/s] 70%|██████▉ | 2965/4250 [13:41<04:44, 4.51it/s] 70%|██████▉ | 2966/4250 [13:41<04:26, 4.82it/s] 70%|██████▉ | 2967/4250 [13:41<04:23, 4.88it/s] 70%|██████▉ | 2968/4250 [13:41<04:07, 5.17it/s] 70%|██████▉ | 2969/4250 [13:42<04:07, 5.17it/s] 70%|██████▉ | 2970/4250 [13:42<04:34, 4.67it/s] 70%|██████▉ | 2971/4250 [13:42<04:25, 4.82it/s] 70%|██████▉ | 2972/4250 [13:42<04:19, 4.93it/s] 70%|██████▉ | 2973/4250 [13:42<04:29, 4.74it/s] 70%|██████▉ | 2974/4250 [13:43<04:36, 4.61it/s] 70%|███████ | 2975/4250 [13:43<05:06, 4.16it/s] 70%|███████ | 2976/4250 [13:43<05:51, 3.62it/s] 70%|███████ | 2977/4250 [13:43<05:12, 4.07it/s] 70%|███████ | 2978/4250 [13:44<05:10, 4.10it/s][INFO|trainer.py:805] 2024-08-30 20:39:33,180 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: tokens, ner_tags, id. If tokens, ner_tags, id are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3788] 2024-08-30 20:39:33,182 >> ***** Running Evaluation ***** [INFO|trainer.py:3790] 2024-08-30 20:39:33,182 >> Num examples = 6810 [INFO|trainer.py:3793] 2024-08-30 20:39:33,182 >> Batch size = 8 {'eval_loss': 0.10803968459367752, 'eval_precision': 0.7765501691093574, 'eval_recall': 0.8058025269068788, 'eval_f1': 0.7909059593523942, 'eval_accuracy': 0.9764579070948961, 'eval_runtime': 14.5335, 'eval_samples_per_second': 468.572, 'eval_steps_per_second': 58.623, 'epoch': 6.0} 0%| | 0/852 [00:00> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-2978 [INFO|configuration_utils.py:472] 2024-08-30 20:39:47,869 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-2978/config.json [INFO|modeling_utils.py:2690] 2024-08-30 20:39:49,212 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-2978/model.safetensors [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:39:49,213 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-2978/tokenizer_config.json [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:39:49,213 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-2978/special_tokens_map.json [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:39:51,528 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:39:51,528 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json 70%|███████ | 2979/4250 [14:02<2:02:04, 5.76s/it] 70%|███████ | 2980/4250 [14:03<1:26:55, 4.11s/it] 70%|███████ | 2981/4250 [14:03<1:02:05, 2.94s/it] 70%|███████ | 2982/4250 [14:03<45:09, 2.14s/it] 70%|███████ | 2983/4250 [14:03<32:55, 1.56s/it] 70%|███████ | 2984/4250 [14:04<24:24, 1.16s/it] 70%|███████ | 2985/4250 [14:04<19:33, 1.08it/s] 70%|███████ | 2986/4250 [14:04<14:41, 1.43it/s] 70%|███████ | 2987/4250 [14:04<11:37, 1.81it/s] 70%|███████ | 2988/4250 [14:04<09:17, 2.26it/s] 70%|███████ | 2989/4250 [14:05<07:46, 2.70it/s] 70%|███████ | 2990/4250 [14:05<06:32, 3.21it/s] 70%|███████ | 2991/4250 [14:05<06:01, 3.49it/s] 70%|███████ | 2992/4250 [14:05<05:58, 3.51it/s] 70%|███████ | 2993/4250 [14:06<05:13, 4.01it/s] 70%|███████ | 2994/4250 [14:06<05:00, 4.18it/s] 70%|███████ | 2995/4250 [14:06<04:50, 4.32it/s] 70%|███████ | 2996/4250 [14:06<04:45, 4.39it/s] 71%|███████ | 2997/4250 [14:06<04:27, 4.68it/s] 71%|███████ | 2998/4250 [14:07<04:04, 5.13it/s] 71%|███████ | 2999/4250 [14:07<04:37, 4.51it/s] 71%|███████ | 3000/4250 [14:07<05:38, 3.69it/s] 71%|███████ | 3000/4250 [14:07<05:38, 3.69it/s] 71%|███████ | 3001/4250 [14:07<05:13, 3.99it/s] 71%|███████ | 3002/4250 [14:08<04:55, 4.23it/s] 71%|███████ | 3003/4250 [14:08<04:49, 4.31it/s] 71%|███████ | 3004/4250 [14:08<05:08, 4.04it/s] 71%|███████ | 3005/4250 [14:08<04:39, 4.45it/s] 71%|███████ | 3006/4250 [14:09<05:25, 3.82it/s] 71%|███████ | 3007/4250 [14:09<05:52, 3.53it/s] 71%|███████ | 3008/4250 [14:09<05:58, 3.46it/s] 71%|███████ | 3009/4250 [14:09<05:33, 3.72it/s] 71%|███████ | 3010/4250 [14:10<05:53, 3.51it/s] 71%|███████ | 3011/4250 [14:10<05:47, 3.56it/s] 71%|███████ | 3012/4250 [14:10<05:49, 3.54it/s] 71%|███████ | 3013/4250 [14:11<05:40, 3.64it/s] 71%|███████ | 3014/4250 [14:11<05:40, 3.63it/s] 71%|███████ | 3015/4250 [14:11<06:18, 3.26it/s] 71%|███████ | 3016/4250 [14:11<05:35, 3.67it/s] 71%|███████ | 3017/4250 [14:12<05:00, 4.10it/s] 71%|███████ | 3018/4250 [14:12<05:07, 4.01it/s] 71%|███████ | 3019/4250 [14:12<05:05, 4.03it/s] 71%|███████ | 3020/4250 [14:12<04:56, 4.16it/s] 71%|███████ | 3021/4250 [14:13<04:35, 4.47it/s] 71%|███████ | 3022/4250 [14:13<04:23, 4.66it/s] 71%|███████ | 3023/4250 [14:13<04:38, 4.40it/s] 71%|███████ | 3024/4250 [14:13<04:31, 4.52it/s] 71%|███████ | 3025/4250 [14:13<04:02, 5.06it/s] 71%|███████ | 3026/4250 [14:14<04:30, 4.52it/s] 71%|███████ | 3027/4250 [14:14<04:31, 4.50it/s] 71%|███████ | 3028/4250 [14:14<04:46, 4.27it/s] 71%|███████▏ | 3029/4250 [14:14<04:41, 4.33it/s] 71%|███████▏ | 3030/4250 [14:15<04:56, 4.12it/s] 71%|███████▏ | 3031/4250 [14:15<04:45, 4.26it/s] 71%|███████▏ | 3032/4250 [14:15<04:47, 4.23it/s] 71%|███████▏ | 3033/4250 [14:15<05:11, 3.91it/s] 71%|███████▏ | 3034/4250 [14:16<04:55, 4.11it/s] 71%|███████▏ | 3035/4250 [14:16<04:31, 4.48it/s] 71%|███████▏ | 3036/4250 [14:16<04:19, 4.68it/s] 71%|███████▏ | 3037/4250 [14:16<04:07, 4.90it/s] 71%|███████▏ | 3038/4250 [14:16<04:10, 4.85it/s] 72%|███████▏ | 3039/4250 [14:17<04:04, 4.96it/s] 72%|███████▏ | 3040/4250 [14:17<04:05, 4.93it/s] 72%|███████▏ | 3041/4250 [14:17<04:15, 4.73it/s] 72%|███████▏ | 3042/4250 [14:17<04:02, 4.99it/s] 72%|███████▏ | 3043/4250 [14:17<04:10, 4.82it/s] 72%|███████▏ | 3044/4250 [14:18<03:57, 5.07it/s] 72%|███████▏ | 3045/4250 [14:18<03:56, 5.10it/s] 72%|███████▏ | 3046/4250 [14:18<07:02, 2.85it/s] 72%|███████▏ | 3047/4250 [14:19<06:28, 3.10it/s] 72%|███████▏ | 3048/4250 [14:19<05:53, 3.40it/s] 72%|███████▏ | 3049/4250 [14:19<05:36, 3.57it/s] 72%|███████▏ | 3050/4250 [14:19<05:39, 3.53it/s] 72%|███████▏ | 3051/4250 [14:20<05:00, 3.99it/s] 72%|███████▏ | 3052/4250 [14:20<04:50, 4.12it/s] 72%|███████▏ | 3053/4250 [14:20<04:41, 4.26it/s] 72%|███████▏ | 3054/4250 [14:20<04:38, 4.30it/s] 72%|███████▏ | 3055/4250 [14:21<06:12, 3.21it/s] 72%|███████▏ | 3056/4250 [14:21<06:44, 2.95it/s] 72%|███████▏ | 3057/4250 [14:21<05:50, 3.40it/s] 72%|███████▏ | 3058/4250 [14:22<05:15, 3.78it/s] 72%|███████▏ | 3059/4250 [14:22<04:44, 4.19it/s] 72%|███████▏ | 3060/4250 [14:22<04:21, 4.54it/s] 72%|███████▏ | 3061/4250 [14:22<04:18, 4.60it/s] 72%|███████▏ | 3062/4250 [14:22<04:34, 4.33it/s] 72%|███████▏ | 3063/4250 [14:23<04:20, 4.55it/s] 72%|███████▏ | 3064/4250 [14:23<05:18, 3.73it/s] 72%|███████▏ | 3065/4250 [14:23<05:06, 3.87it/s] 72%|███████▏ | 3066/4250 [14:23<04:39, 4.24it/s] 72%|███████▏ | 3067/4250 [14:24<04:26, 4.44it/s] 72%|███████▏ | 3068/4250 [14:24<04:18, 4.57it/s] 72%|███████▏ | 3069/4250 [14:24<04:28, 4.40it/s] 72%|███████▏ | 3070/4250 [14:24<04:33, 4.32it/s] 72%|███████▏ | 3071/4250 [14:24<04:19, 4.54it/s] 72%|███████▏ | 3072/4250 [14:25<04:07, 4.76it/s] 72%|███████▏ | 3073/4250 [14:25<04:54, 3.99it/s] 72%|███████▏ | 3074/4250 [14:25<05:11, 3.78it/s] 72%|███████▏ | 3075/4250 [14:26<04:57, 3.96it/s] 72%|███████▏ | 3076/4250 [14:26<04:29, 4.35it/s] 72%|███████▏ | 3077/4250 [14:26<04:37, 4.23it/s] 72%|███████▏ | 3078/4250 [14:26<04:31, 4.32it/s] 72%|███████▏ | 3079/4250 [14:26<04:15, 4.58it/s] 72%|███████▏ | 3080/4250 [14:27<04:06, 4.75it/s] 72%|███████▏ | 3081/4250 [14:27<03:58, 4.91it/s] 73%|███████▎ | 3082/4250 [14:27<03:58, 4.90it/s] 73%|███████▎ | 3083/4250 [14:27<05:29, 3.54it/s] 73%|███████▎ | 3084/4250 [14:28<05:12, 3.73it/s] 73%|███████▎ | 3085/4250 [14:28<04:37, 4.20it/s] 73%|███████▎ | 3086/4250 [14:28<04:51, 3.99it/s] 73%|███████▎ | 3087/4250 [14:28<04:33, 4.25it/s] 73%|███████▎ | 3088/4250 [14:29<04:32, 4.27it/s] 73%|███████▎ | 3089/4250 [14:29<04:31, 4.28it/s] 73%|███████▎ | 3090/4250 [14:29<04:11, 4.61it/s] 73%|███████▎ | 3091/4250 [14:29<04:10, 4.63it/s] 73%|███████▎ | 3092/4250 [14:30<04:56, 3.91it/s] 73%|███████▎ | 3093/4250 [14:30<04:34, 4.22it/s] 73%|███████▎ | 3094/4250 [14:31<08:09, 2.36it/s] 73%|███████▎ | 3095/4250 [14:31<06:42, 2.87it/s] 73%|███████▎ | 3096/4250 [14:31<05:51, 3.29it/s] 73%|███████▎ | 3097/4250 [14:31<06:14, 3.08it/s] 73%|███████▎ | 3098/4250 [14:32<05:24, 3.55it/s] 73%|███████▎ | 3099/4250 [14:32<04:53, 3.92it/s] 73%|███████▎ | 3100/4250 [14:32<04:45, 4.02it/s] 73%|███████▎ | 3101/4250 [14:32<04:33, 4.20it/s] 73%|███████▎ | 3102/4250 [14:32<04:21, 4.38it/s] 73%|███████▎ | 3103/4250 [14:33<04:10, 4.58it/s] 73%|███████▎ | 3104/4250 [14:33<05:07, 3.73it/s] 73%|███████▎ | 3105/4250 [14:33<05:28, 3.48it/s] 73%|███████▎ | 3106/4250 [14:34<05:40, 3.36it/s] 73%|███████▎ | 3107/4250 [14:34<05:19, 3.58it/s] 73%|███████▎ | 3108/4250 [14:34<04:55, 3.86it/s] 73%|███████▎ | 3109/4250 [14:34<04:49, 3.94it/s] 73%|███████▎ | 3110/4250 [14:34<04:22, 4.34it/s] 73%|███████▎ | 3111/4250 [14:35<04:19, 4.38it/s] 73%|███████▎ | 3112/4250 [14:35<04:02, 4.68it/s] 73%|███████▎ | 3113/4250 [14:35<04:08, 4.57it/s] 73%|███████▎ | 3114/4250 [14:35<04:24, 4.29it/s] 73%|███████▎ | 3115/4250 [14:36<04:06, 4.60it/s] 73%|███████▎ | 3116/4250 [14:36<03:51, 4.89it/s] 73%|███████▎ | 3117/4250 [14:36<03:35, 5.26it/s] 73%|███████▎ | 3118/4250 [14:36<03:54, 4.82it/s] 73%|███████▎ | 3119/4250 [14:36<03:31, 5.36it/s] 73%|███████▎ | 3120/4250 [14:36<03:33, 5.28it/s] 73%|███████▎ | 3121/4250 [14:37<03:40, 5.12it/s] 73%|███████▎ | 3122/4250 [14:37<03:41, 5.09it/s] 73%|███████▎ | 3123/4250 [14:37<03:45, 4.99it/s] 74%|███████▎ | 3124/4250 [14:37<03:37, 5.17it/s] 74%|███████▎ | 3125/4250 [14:38<04:41, 4.00it/s] 74%|███████▎ | 3126/4250 [14:38<04:18, 4.35it/s] 74%|███████▎ | 3127/4250 [14:38<04:13, 4.42it/s] 74%|███████▎ | 3128/4250 [14:38<03:50, 4.88it/s] 74%|███████▎ | 3129/4250 [14:38<04:01, 4.64it/s] 74%|███████▎ | 3130/4250 [14:39<04:05, 4.56it/s] 74%|███████▎ | 3131/4250 [14:39<04:34, 4.08it/s] 74%|███████▎ | 3132/4250 [14:39<04:33, 4.09it/s] 74%|███████▎ | 3133/4250 [14:39<04:22, 4.26it/s] 74%|███████▎ | 3134/4250 [14:40<04:15, 4.37it/s] 74%|███████▍ | 3135/4250 [14:40<03:59, 4.65it/s] 74%|███████▍ | 3136/4250 [14:40<03:48, 4.88it/s] 74%|███████▍ | 3137/4250 [14:40<03:45, 4.94it/s] 74%|███████▍ | 3138/4250 [14:40<04:01, 4.61it/s] 74%|███████▍ | 3139/4250 [14:41<03:48, 4.86it/s] 74%|███████▍ | 3140/4250 [14:41<03:48, 4.86it/s] 74%|███████▍ | 3141/4250 [14:41<03:33, 5.20it/s] 74%|███████▍ | 3142/4250 [14:41<03:26, 5.35it/s] 74%|███████▍ | 3143/4250 [14:41<03:48, 4.85it/s] 74%|███████▍ | 3144/4250 [14:42<03:42, 4.97it/s] 74%|███████▍ | 3145/4250 [14:42<03:42, 4.97it/s] 74%|███████▍ | 3146/4250 [14:42<04:05, 4.49it/s] 74%|███████▍ | 3147/4250 [14:42<03:52, 4.74it/s] 74%|███████▍ | 3148/4250 [14:42<03:42, 4.95it/s] 74%|███████▍ | 3149/4250 [14:43<04:11, 4.38it/s] 74%|███████▍ | 3150/4250 [14:43<04:08, 4.43it/s] 74%|███████▍ | 3151/4250 [14:43<03:51, 4.75it/s] 74%|███████▍ | 3152/4250 [14:43<03:53, 4.71it/s] 74%|███████▍ | 3153/4250 [14:44<03:52, 4.71it/s] 74%|███████▍ | 3154/4250 [14:44<03:59, 4.57it/s] 74%|███████▍ | 3155/4250 [14:44<05:09, 3.54it/s] 74%|███████▍ | 3156/4250 [14:44<05:03, 3.61it/s] 74%|███████▍ | 3157/4250 [14:45<04:21, 4.18it/s] 74%|███████▍ | 3158/4250 [14:45<04:47, 3.80it/s] 74%|███████▍ | 3159/4250 [14:45<05:13, 3.48it/s] 74%|███████▍ | 3160/4250 [14:46<04:55, 3.69it/s] 74%|███████▍ | 3161/4250 [14:46<04:35, 3.95it/s] 74%|███████▍ | 3162/4250 [14:46<04:31, 4.00it/s] 74%|███████▍ | 3163/4250 [14:46<04:13, 4.28it/s] 74%|███████▍ | 3164/4250 [14:46<04:12, 4.30it/s] 74%|███████▍ | 3165/4250 [14:47<05:21, 3.38it/s] 74%|███████▍ | 3166/4250 [14:47<04:59, 3.62it/s] 75%|███████▍ | 3167/4250 [14:47<04:47, 3.76it/s] 75%|███████▍ | 3168/4250 [14:48<04:26, 4.06it/s] 75%|███████▍ | 3169/4250 [14:48<04:03, 4.44it/s] 75%|███████▍ | 3170/4250 [14:48<04:14, 4.24it/s] 75%|███████▍ | 3171/4250 [14:48<04:10, 4.30it/s] 75%|███████▍ | 3172/4250 [14:48<04:21, 4.13it/s] 75%|███████▍ | 3173/4250 [14:49<03:56, 4.56it/s] 75%|███████▍ | 3174/4250 [14:49<04:08, 4.33it/s] 75%|███████▍ | 3175/4250 [14:49<03:57, 4.52it/s] 75%|███████▍ | 3176/4250 [14:49<03:34, 5.01it/s] 75%|███████▍ | 3177/4250 [14:49<04:02, 4.43it/s] 75%|███████▍ | 3178/4250 [14:50<04:16, 4.17it/s] 75%|███████▍ | 3179/4250 [14:50<04:10, 4.27it/s] 75%|███████▍ | 3180/4250 [14:50<03:56, 4.53it/s] 75%|███████▍ | 3181/4250 [14:50<03:49, 4.66it/s] 75%|███████▍ | 3182/4250 [14:51<03:49, 4.65it/s] 75%|███████▍ | 3183/4250 [14:51<03:52, 4.59it/s] 75%|███████▍ | 3184/4250 [14:51<03:57, 4.49it/s] 75%|███████▍ | 3185/4250 [14:51<03:38, 4.88it/s] 75%|███████▍ | 3186/4250 [14:52<05:52, 3.01it/s] 75%|███████▍ | 3187/4250 [14:52<05:48, 3.05it/s] 75%|███████▌ | 3188/4250 [14:52<04:51, 3.65it/s] 75%|███████▌ | 3189/4250 [14:53<05:21, 3.30it/s] 75%|███████▌ | 3190/4250 [14:53<05:33, 3.18it/s] 75%|███████▌ | 3191/4250 [14:53<05:32, 3.19it/s] 75%|███████▌ | 3192/4250 [14:54<06:06, 2.89it/s] 75%|███████▌ | 3193/4250 [14:54<05:06, 3.44it/s] 75%|███████▌ | 3194/4250 [14:54<04:38, 3.79it/s] 75%|███████▌ | 3195/4250 [14:54<04:13, 4.16it/s] 75%|███████▌ | 3196/4250 [14:55<05:09, 3.40it/s] 75%|███████▌ | 3197/4250 [14:55<04:49, 3.64it/s] 75%|███████▌ | 3198/4250 [14:55<04:17, 4.09it/s] 75%|███████▌ | 3199/4250 [14:55<04:03, 4.32it/s] 75%|███████▌ | 3200/4250 [14:56<03:50, 4.56it/s] 75%|███████▌ | 3201/4250 [14:56<04:18, 4.06it/s] 75%|███████▌ | 3202/4250 [14:56<04:02, 4.32it/s] 75%|███████▌ | 3203/4250 [14:56<03:41, 4.73it/s] 75%|███████▌ | 3204/4250 [14:57<04:23, 3.97it/s] 75%|███████▌ | 3205/4250 [14:57<04:24, 3.95it/s] 75%|███████▌ | 3206/4250 [14:57<04:06, 4.23it/s] 75%|███████▌ | 3207/4250 [14:57<03:36, 4.81it/s] 75%|███████▌ | 3208/4250 [14:57<03:41, 4.71it/s] 76%|███████▌ | 3209/4250 [14:58<03:58, 4.37it/s] 76%|███████▌ | 3210/4250 [14:58<03:42, 4.67it/s] 76%|███████▌ | 3211/4250 [14:58<03:57, 4.38it/s] 76%|███████▌ | 3212/4250 [14:58<03:52, 4.47it/s] 76%|███████▌ | 3213/4250 [14:59<03:54, 4.43it/s] 76%|███████▌ | 3214/4250 [14:59<03:37, 4.77it/s] 76%|███████▌ | 3215/4250 [14:59<03:35, 4.80it/s] 76%|███████▌ | 3216/4250 [14:59<04:00, 4.30it/s] 76%|███████▌ | 3217/4250 [14:59<04:00, 4.29it/s] 76%|███████▌ | 3218/4250 [15:00<03:53, 4.42it/s] 76%|███████▌ | 3219/4250 [15:00<03:46, 4.55it/s] 76%|███████▌ | 3220/4250 [15:00<03:41, 4.65it/s] 76%|███████▌ | 3221/4250 [15:00<03:48, 4.51it/s] 76%|███████▌ | 3222/4250 [15:00<03:36, 4.75it/s] 76%|███████▌ | 3223/4250 [15:01<03:54, 4.38it/s] 76%|███████▌ | 3224/4250 [15:01<03:46, 4.54it/s] 76%|███████▌ | 3225/4250 [15:01<03:38, 4.68it/s] 76%|███████▌ | 3226/4250 [15:01<04:24, 3.87it/s] 76%|███████▌ | 3227/4250 [15:02<04:25, 3.85it/s] 76%|███████▌ | 3228/4250 [15:02<05:11, 3.28it/s] 76%|███████▌ | 3229/4250 [15:02<04:46, 3.56it/s] 76%|███████▌ | 3230/4250 [15:03<05:46, 2.94it/s] 76%|███████▌ | 3231/4250 [15:03<05:14, 3.24it/s] 76%|███████▌ | 3232/4250 [15:03<04:50, 3.50it/s] 76%|███████▌ | 3233/4250 [15:04<04:49, 3.52it/s] 76%|███████▌ | 3234/4250 [15:04<07:16, 2.33it/s] 76%|███████▌ | 3235/4250 [15:05<06:03, 2.79it/s] 76%|███████▌ | 3236/4250 [15:05<05:09, 3.27it/s] 76%|███████▌ | 3237/4250 [15:05<04:54, 3.44it/s] 76%|███████▌ | 3238/4250 [15:05<04:24, 3.82it/s] 76%|███████▌ | 3239/4250 [15:05<04:32, 3.71it/s] 76%|███████▌ | 3240/4250 [15:06<04:31, 3.72it/s] 76%|███████▋ | 3241/4250 [15:06<04:18, 3.91it/s] 76%|███████▋ | 3242/4250 [15:06<04:15, 3.94it/s] 76%|███████▋ | 3243/4250 [15:07<04:28, 3.76it/s] 76%|███████▋ | 3244/4250 [15:07<04:14, 3.96it/s] 76%|███████▋ | 3245/4250 [15:07<04:34, 3.66it/s] 76%|███████▋ | 3246/4250 [15:07<04:26, 3.77it/s] 76%|███████▋ | 3247/4250 [15:07<03:58, 4.21it/s] 76%|███████▋ | 3248/4250 [15:08<03:42, 4.51it/s] 76%|███████▋ | 3249/4250 [15:08<03:31, 4.74it/s] 76%|███████▋ | 3250/4250 [15:08<03:37, 4.60it/s] 76%|███████▋ | 3251/4250 [15:08<03:37, 4.60it/s] 77%|███████▋ | 3252/4250 [15:09<04:00, 4.15it/s] 77%|███████▋ | 3253/4250 [15:09<04:58, 3.34it/s] 77%|███████▋ | 3254/4250 [15:09<05:02, 3.29it/s] 77%|███████▋ | 3255/4250 [15:10<04:30, 3.68it/s] 77%|███████▋ | 3256/4250 [15:10<04:20, 3.82it/s] 77%|███████▋ | 3257/4250 [15:10<04:07, 4.01it/s] 77%|███████▋ | 3258/4250 [15:10<03:53, 4.25it/s] 77%|███████▋ | 3259/4250 [15:10<03:28, 4.74it/s] 77%|███████▋ | 3260/4250 [15:11<03:56, 4.19it/s] 77%|███████▋ | 3261/4250 [15:11<03:45, 4.39it/s] 77%|███████▋ | 3262/4250 [15:11<03:38, 4.52it/s] 77%|███████▋ | 3263/4250 [15:11<03:28, 4.73it/s] 77%|███████▋ | 3264/4250 [15:11<03:17, 5.00it/s] 77%|███████▋ | 3265/4250 [15:12<04:40, 3.51it/s] 77%|███████▋ | 3266/4250 [15:12<04:22, 3.75it/s] 77%|███████▋ | 3267/4250 [15:12<03:50, 4.27it/s] 77%|███████▋ | 3268/4250 [15:12<03:36, 4.54it/s] 77%|███████▋ | 3269/4250 [15:13<03:27, 4.73it/s] 77%|███████▋ | 3270/4250 [15:13<03:24, 4.80it/s] 77%|███████▋ | 3271/4250 [15:13<03:31, 4.62it/s] 77%|███████▋ | 3272/4250 [15:13<03:23, 4.80it/s] 77%|███████▋ | 3273/4250 [15:14<03:31, 4.61it/s] 77%|███████▋ | 3274/4250 [15:14<03:24, 4.78it/s] 77%|███████▋ | 3275/4250 [15:14<03:14, 5.02it/s] 77%|███████▋ | 3276/4250 [15:14<03:16, 4.97it/s] 77%|███████▋ | 3277/4250 [15:14<03:09, 5.12it/s] 77%|███████▋ | 3278/4250 [15:14<03:08, 5.15it/s] 77%|███████▋ | 3279/4250 [15:15<03:33, 4.55it/s] 77%|███████▋ | 3280/4250 [15:15<03:44, 4.33it/s] 77%|███████▋ | 3281/4250 [15:15<03:26, 4.70it/s] 77%|███████▋ | 3282/4250 [15:15<03:16, 4.92it/s] 77%|███████▋ | 3283/4250 [15:16<03:08, 5.12it/s] 77%|███████▋ | 3284/4250 [15:16<03:23, 4.75it/s] 77%|███████▋ | 3285/4250 [15:16<03:23, 4.74it/s] 77%|███████▋ | 3286/4250 [15:16<03:17, 4.87it/s] 77%|███████▋ | 3287/4250 [15:16<03:34, 4.50it/s] 77%|███████▋ | 3288/4250 [15:17<03:25, 4.68it/s] 77%|███████▋ | 3289/4250 [15:17<03:11, 5.02it/s] 77%|███████▋ | 3290/4250 [15:17<03:22, 4.73it/s] 77%|███████▋ | 3291/4250 [15:17<03:46, 4.23it/s] 77%|███████▋ | 3292/4250 [15:18<03:53, 4.10it/s] 77%|███████▋ | 3293/4250 [15:18<03:43, 4.28it/s] 78%|███████▊ | 3294/4250 [15:18<03:38, 4.37it/s] 78%|███████▊ | 3295/4250 [15:18<03:35, 4.42it/s] 78%|███████▊ | 3296/4250 [15:18<03:25, 4.64it/s] 78%|███████▊ | 3297/4250 [15:19<03:34, 4.45it/s] 78%|███████▊ | 3298/4250 [15:19<03:21, 4.73it/s] 78%|███████▊ | 3299/4250 [15:19<03:54, 4.05it/s] 78%|███████▊ | 3300/4250 [15:19<04:04, 3.89it/s] 78%|███████▊ | 3301/4250 [15:20<04:02, 3.91it/s] 78%|███████▊ | 3302/4250 [15:20<04:09, 3.80it/s] 78%|███████▊ | 3303/4250 [15:20<04:08, 3.81it/s] 78%|███████▊ | 3304/4250 [15:21<04:02, 3.90it/s] 78%|███████▊ | 3305/4250 [15:21<03:40, 4.28it/s] 78%|███████▊ | 3306/4250 [15:21<03:29, 4.51it/s] 78%|███████▊ | 3307/4250 [15:21<03:28, 4.52it/s] 78%|███████▊ | 3308/4250 [15:21<03:19, 4.72it/s] 78%|███████▊ | 3309/4250 [15:22<03:21, 4.67it/s] 78%|███████▊ | 3310/4250 [15:22<03:16, 4.78it/s] 78%|███████▊ | 3311/4250 [15:22<03:09, 4.95it/s] 78%|███████▊ | 3312/4250 [15:22<03:15, 4.80it/s] 78%|███████▊ | 3313/4250 [15:22<03:16, 4.76it/s] 78%|███████▊ | 3314/4250 [15:23<03:11, 4.89it/s] 78%|███████▊ | 3315/4250 [15:23<03:22, 4.62it/s] 78%|███████▊ | 3316/4250 [15:23<03:14, 4.79it/s] 78%|███████▊ | 3317/4250 [15:23<03:21, 4.63it/s] 78%|███████▊ | 3318/4250 [15:23<03:03, 5.07it/s] 78%|███████▊ | 3319/4250 [15:24<03:02, 5.09it/s] 78%|███████▊ | 3320/4250 [15:24<03:06, 4.99it/s] 78%|███████▊ | 3321/4250 [15:24<03:25, 4.51it/s] 78%|███████▊ | 3322/4250 [15:24<03:36, 4.29it/s] 78%|███████▊ | 3323/4250 [15:25<03:27, 4.48it/s] 78%|███████▊ | 3324/4250 [15:25<03:05, 4.98it/s] 78%|███████▊ | 3325/4250 [15:25<03:14, 4.75it/s] 78%|███████▊ | 3326/4250 [15:25<03:30, 4.39it/s] 78%|███████▊ | 3327/4250 [15:25<03:57, 3.89it/s] 78%|███████▊ | 3328/4250 [15:26<03:43, 4.12it/s] 78%|███████▊ | 3329/4250 [15:26<03:32, 4.33it/s] 78%|███████▊ | 3330/4250 [15:26<03:39, 4.19it/s] 78%|███████▊ | 3331/4250 [15:26<03:45, 4.07it/s] 78%|███████▊ | 3332/4250 [15:27<04:31, 3.38it/s] 78%|███████▊ | 3333/4250 [15:27<04:08, 3.69it/s] 78%|███████▊ | 3334/4250 [15:27<03:44, 4.08it/s] 78%|███████▊ | 3335/4250 [15:27<03:26, 4.44it/s] 78%|███████▊ | 3336/4250 [15:28<03:31, 4.32it/s] 79%|███████▊ | 3337/4250 [15:28<03:23, 4.48it/s] 79%|███████▊ | 3338/4250 [15:28<03:38, 4.18it/s] 79%|███████▊ | 3339/4250 [15:28<03:40, 4.14it/s] 79%|███████▊ | 3340/4250 [15:29<03:24, 4.44it/s] 79%|███████▊ | 3341/4250 [15:29<03:10, 4.78it/s] 79%|███████▊ | 3342/4250 [15:29<03:44, 4.05it/s] 79%|███████▊ | 3343/4250 [15:29<03:34, 4.23it/s] 79%|███████▊ | 3344/4250 [15:29<03:21, 4.49it/s] 79%|███████▊ | 3345/4250 [15:30<03:34, 4.21it/s] 79%|███████▊ | 3346/4250 [15:30<04:13, 3.57it/s] 79%|███████▉ | 3347/4250 [15:31<04:38, 3.24it/s] 79%|███████▉ | 3348/4250 [15:31<04:31, 3.33it/s] 79%|███████▉ | 3349/4250 [15:31<03:59, 3.77it/s] 79%|███████▉ | 3350/4250 [15:31<03:34, 4.20it/s] 79%|███████▉ | 3351/4250 [15:31<03:31, 4.25it/s] 79%|███████▉ | 3352/4250 [15:32<04:10, 3.59it/s] 79%|███████▉ | 3353/4250 [15:32<04:04, 3.67it/s] 79%|███████▉ | 3354/4250 [15:32<03:47, 3.95it/s] 79%|███████▉ | 3355/4250 [15:32<03:27, 4.31it/s] 79%|███████▉ | 3356/4250 [15:33<03:06, 4.79it/s] 79%|███████▉ | 3357/4250 [15:33<02:54, 5.13it/s] 79%|███████▉ | 3358/4250 [15:33<03:09, 4.71it/s] 79%|███████▉ | 3359/4250 [15:33<02:58, 4.98it/s] 79%|███████▉ | 3360/4250 [15:33<03:07, 4.74it/s] 79%|███████▉ | 3361/4250 [15:34<03:05, 4.80it/s] 79%|███████▉ | 3362/4250 [15:34<03:28, 4.25it/s] 79%|███████▉ | 3363/4250 [15:34<04:36, 3.21it/s] 79%|███████▉ | 3364/4250 [15:35<04:03, 3.64it/s] 79%|███████▉ | 3365/4250 [15:35<03:51, 3.82it/s] 79%|███████▉ | 3366/4250 [15:35<03:39, 4.02it/s] 79%|███████▉ | 3367/4250 [15:35<03:29, 4.21it/s] 79%|███████▉ | 3368/4250 [15:35<03:23, 4.33it/s] 79%|███████▉ | 3369/4250 [15:36<03:14, 4.54it/s] 79%|███████▉ | 3370/4250 [15:36<03:09, 4.65it/s] 79%|███████▉ | 3371/4250 [15:36<03:02, 4.81it/s] 79%|███████▉ | 3372/4250 [15:36<03:39, 4.00it/s] 79%|███████▉ | 3373/4250 [15:37<03:24, 4.29it/s] 79%|███████▉ | 3374/4250 [15:37<03:58, 3.67it/s] 79%|███████▉ | 3375/4250 [15:37<03:45, 3.88it/s] 79%|███████▉ | 3376/4250 [15:37<03:38, 4.00it/s] 79%|███████▉ | 3377/4250 [15:38<03:46, 3.85it/s] 79%|███████▉ | 3378/4250 [15:38<03:27, 4.21it/s] 80%|███████▉ | 3379/4250 [15:38<03:25, 4.23it/s] 80%|███████▉ | 3380/4250 [15:38<03:12, 4.51it/s] 80%|███████▉ | 3381/4250 [15:38<03:04, 4.72it/s] 80%|███████▉ | 3382/4250 [15:39<02:52, 5.03it/s] 80%|███████▉ | 3383/4250 [15:39<02:59, 4.82it/s] 80%|███████▉ | 3384/4250 [15:39<02:55, 4.93it/s] 80%|███████▉ | 3385/4250 [15:39<02:55, 4.92it/s] 80%|███████▉ | 3386/4250 [15:40<03:18, 4.35it/s] 80%|███████▉ | 3387/4250 [15:40<03:24, 4.23it/s] 80%|███████▉ | 3388/4250 [15:40<03:16, 4.38it/s] 80%|███████▉ | 3389/4250 [15:40<03:15, 4.40it/s] 80%|███████▉ | 3390/4250 [15:41<04:23, 3.27it/s] 80%|███████▉ | 3391/4250 [15:41<04:09, 3.44it/s] 80%|███████▉ | 3392/4250 [15:41<03:53, 3.67it/s] 80%|███████▉ | 3393/4250 [15:42<04:02, 3.53it/s] 80%|███████▉ | 3394/4250 [15:42<03:53, 3.67it/s] 80%|███████▉ | 3395/4250 [15:42<03:40, 3.88it/s] 80%|███████▉ | 3396/4250 [15:42<03:25, 4.16it/s] 80%|███████▉ | 3397/4250 [15:43<03:48, 3.73it/s] 80%|███████▉ | 3398/4250 [15:43<03:25, 4.15it/s] 80%|███████▉ | 3399/4250 [15:43<03:24, 4.17it/s] 80%|████████ | 3400/4250 [15:43<03:18, 4.28it/s] 80%|████████ | 3401/4250 [15:43<03:01, 4.68it/s] 80%|████████ | 3402/4250 [15:43<02:49, 4.99it/s] 80%|████████ | 3403/4250 [15:44<03:31, 4.00it/s] 80%|████████ | 3404/4250 [15:44<03:16, 4.31it/s][INFO|trainer.py:805] 2024-08-30 20:41:33,404 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: tokens, ner_tags, id. If tokens, ner_tags, id are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3788] 2024-08-30 20:41:33,406 >> ***** Running Evaluation ***** [INFO|trainer.py:3790] 2024-08-30 20:41:33,406 >> Num examples = 6810 [INFO|trainer.py:3793] 2024-08-30 20:41:33,406 >> Batch size = 8 {'eval_loss': 0.11656877398490906, 'eval_precision': 0.7792032410533424, 'eval_recall': 0.810014038371549, 'eval_f1': 0.7943099690260411, 'eval_accuracy': 0.975997912861988, 'eval_runtime': 14.6842, 'eval_samples_per_second': 463.764, 'eval_steps_per_second': 58.022, 'epoch': 7.0} {'loss': 0.0079, 'grad_norm': 0.15811629593372345, 'learning_rate': 1.4705882352941177e-05, 'epoch': 7.05} 0%| | 0/852 [00:00> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-3404 [INFO|configuration_utils.py:472] 2024-08-30 20:41:48,183 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-3404/config.json [INFO|modeling_utils.py:2690] 2024-08-30 20:41:49,516 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-3404/model.safetensors [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:41:49,518 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-3404/tokenizer_config.json [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:41:49,518 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-3404/special_tokens_map.json [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:41:51,822 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:41:51,822 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json 80%|████████ | 3405/4250 [16:03<1:21:49, 5.81s/it] 80%|████████ | 3406/4250 [16:03<57:58, 4.12s/it] 80%|████████ | 3407/4250 [16:03<41:20, 2.94s/it] 80%|████████ | 3408/4250 [16:03<29:36, 2.11s/it] 80%|████████ | 3409/4250 [16:04<21:45, 1.55s/it] 80%|████████ | 3410/4250 [16:04<16:01, 1.15s/it] 80%|████████ | 3411/4250 [16:04<11:57, 1.17it/s] 80%|████████ | 3412/4250 [16:04<09:18, 1.50it/s] 80%|████████ | 3413/4250 [16:04<07:25, 1.88it/s] 80%|████████ | 3414/4250 [16:05<06:04, 2.29it/s] 80%|████████ | 3415/4250 [16:05<05:01, 2.77it/s] 80%|████████ | 3416/4250 [16:05<04:20, 3.21it/s] 80%|████████ | 3417/4250 [16:05<03:56, 3.52it/s] 80%|████████ | 3418/4250 [16:05<03:31, 3.94it/s] 80%|████████ | 3419/4250 [16:06<03:22, 4.11it/s] 80%|████████ | 3420/4250 [16:06<03:11, 4.34it/s] 80%|████████ | 3421/4250 [16:06<02:53, 4.78it/s] 81%|████████ | 3422/4250 [16:06<02:47, 4.94it/s] 81%|████████ | 3423/4250 [16:06<02:55, 4.70it/s] 81%|████████ | 3424/4250 [16:07<02:46, 4.97it/s] 81%|████████ | 3425/4250 [16:07<02:55, 4.70it/s] 81%|████████ | 3426/4250 [16:07<02:43, 5.04it/s] 81%|████████ | 3427/4250 [16:07<02:37, 5.21it/s] 81%|████████ | 3428/4250 [16:07<02:42, 5.05it/s] 81%|████████ | 3429/4250 [16:08<02:45, 4.96it/s] 81%|████████ | 3430/4250 [16:08<02:44, 4.97it/s] 81%|████████ | 3431/4250 [16:08<02:42, 5.05it/s] 81%|████████ | 3432/4250 [16:08<02:34, 5.30it/s] 81%|████████ | 3433/4250 [16:09<03:14, 4.21it/s] 81%|████████ | 3434/4250 [16:09<03:12, 4.24it/s] 81%|████████ | 3435/4250 [16:09<03:24, 3.99it/s] 81%|████████ | 3436/4250 [16:09<03:47, 3.58it/s] 81%|████████ | 3437/4250 [16:10<03:30, 3.86it/s] 81%|████████ | 3438/4250 [16:10<03:28, 3.89it/s] 81%|████████ | 3439/4250 [16:10<03:21, 4.02it/s] 81%|████████ | 3440/4250 [16:10<03:03, 4.40it/s] 81%|████████ | 3441/4250 [16:11<03:13, 4.17it/s] 81%|████████ | 3442/4250 [16:11<02:57, 4.55it/s] 81%|████████ | 3443/4250 [16:11<03:00, 4.47it/s] 81%|████████ | 3444/4250 [16:11<02:59, 4.49it/s] 81%|████████ | 3445/4250 [16:11<03:03, 4.39it/s] 81%|████████ | 3446/4250 [16:12<03:11, 4.20it/s] 81%|████████ | 3447/4250 [16:12<03:00, 4.45it/s] 81%|████████ | 3448/4250 [16:12<02:56, 4.54it/s] 81%|████████ | 3449/4250 [16:12<02:49, 4.73it/s] 81%|████████ | 3450/4250 [16:13<02:58, 4.49it/s] 81%|████████ | 3451/4250 [16:13<03:03, 4.35it/s] 81%|████████ | 3452/4250 [16:13<02:54, 4.56it/s] 81%|████████ | 3453/4250 [16:13<03:24, 3.89it/s] 81%|████████▏ | 3454/4250 [16:14<03:16, 4.05it/s] 81%|████████▏ | 3455/4250 [16:14<02:57, 4.48it/s] 81%|████████▏ | 3456/4250 [16:14<02:59, 4.43it/s] 81%|████████▏ | 3457/4250 [16:14<02:55, 4.52it/s] 81%|████████▏ | 3458/4250 [16:14<02:55, 4.51it/s] 81%|████████▏ | 3459/4250 [16:15<03:00, 4.38it/s] 81%|████████▏ | 3460/4250 [16:15<02:49, 4.65it/s] 81%|████████▏ | 3461/4250 [16:15<02:51, 4.59it/s] 81%|████████▏ | 3462/4250 [16:15<02:41, 4.88it/s] 81%|████████▏ | 3463/4250 [16:15<02:57, 4.44it/s] 82%|████████▏ | 3464/4250 [16:16<03:01, 4.32it/s] 82%|████████▏ | 3465/4250 [16:16<02:52, 4.55it/s] 82%|████████▏ | 3466/4250 [16:16<02:48, 4.66it/s] 82%|████████▏ | 3467/4250 [16:16<02:43, 4.78it/s] 82%|████████▏ | 3468/4250 [16:17<02:40, 4.86it/s] 82%|████████▏ | 3469/4250 [16:17<03:05, 4.21it/s] 82%|████████▏ | 3470/4250 [16:17<02:54, 4.47it/s] 82%|████████▏ | 3471/4250 [16:17<03:01, 4.29it/s] 82%|████████▏ | 3472/4250 [16:18<03:30, 3.69it/s] 82%|████████▏ | 3473/4250 [16:18<03:17, 3.93it/s] 82%|████████▏ | 3474/4250 [16:18<03:10, 4.07it/s] 82%|████████▏ | 3475/4250 [16:18<02:57, 4.38it/s] 82%|████████▏ | 3476/4250 [16:19<02:58, 4.33it/s] 82%|████████▏ | 3477/4250 [16:19<02:51, 4.52it/s] 82%|████████▏ | 3478/4250 [16:19<03:05, 4.17it/s] 82%|████████▏ | 3479/4250 [16:19<02:50, 4.53it/s] 82%|████████▏ | 3480/4250 [16:19<02:37, 4.90it/s] 82%|████████▏ | 3481/4250 [16:19<02:29, 5.13it/s] 82%|████████▏ | 3482/4250 [16:20<03:15, 3.94it/s] 82%|████████▏ | 3483/4250 [16:20<03:38, 3.51it/s] 82%|████████▏ | 3484/4250 [16:21<03:38, 3.50it/s] 82%|████████▏ | 3485/4250 [16:21<03:33, 3.58it/s] 82%|████████▏ | 3486/4250 [16:21<03:17, 3.88it/s] 82%|████████▏ | 3487/4250 [16:21<03:14, 3.93it/s] 82%|████████▏ | 3488/4250 [16:21<03:00, 4.23it/s] 82%|████████▏ | 3489/4250 [16:22<03:00, 4.21it/s] 82%|████████▏ | 3490/4250 [16:22<02:43, 4.64it/s] 82%|████████▏ | 3491/4250 [16:22<02:36, 4.84it/s] 82%|████████▏ | 3492/4250 [16:22<02:45, 4.59it/s] 82%|████████▏ | 3493/4250 [16:22<02:44, 4.59it/s] 82%|████████▏ | 3494/4250 [16:23<02:44, 4.60it/s] 82%|████████▏ | 3495/4250 [16:23<02:33, 4.91it/s] 82%|████████▏ | 3496/4250 [16:23<02:39, 4.72it/s] 82%|████████▏ | 3497/4250 [16:23<02:36, 4.82it/s] 82%|████████▏ | 3498/4250 [16:24<02:59, 4.20it/s] 82%|████████▏ | 3499/4250 [16:24<03:03, 4.10it/s] 82%|████████▏ | 3500/4250 [16:24<02:46, 4.49it/s] 82%|████████▏ | 3500/4250 [16:24<02:46, 4.49it/s] 82%|████████▏ | 3501/4250 [16:24<02:41, 4.62it/s] 82%|████████▏ | 3502/4250 [16:24<02:35, 4.81it/s] 82%|████████▏ | 3503/4250 [16:25<02:41, 4.61it/s] 82%|████████▏ | 3504/4250 [16:25<02:39, 4.67it/s] 82%|████████▏ | 3505/4250 [16:25<02:27, 5.05it/s] 82%|████████▏ | 3506/4250 [16:25<02:30, 4.94it/s] 83%|████████▎ | 3507/4250 [16:26<02:38, 4.70it/s] 83%|████████▎ | 3508/4250 [16:26<02:32, 4.86it/s] 83%|████████▎ | 3509/4250 [16:26<02:22, 5.21it/s] 83%|████████▎ | 3510/4250 [16:26<02:23, 5.16it/s] 83%|████████▎ | 3511/4250 [16:26<02:41, 4.58it/s] 83%|████████▎ | 3512/4250 [16:27<02:47, 4.40it/s] 83%|████████▎ | 3513/4250 [16:27<02:44, 4.48it/s] 83%|████████▎ | 3514/4250 [16:27<02:39, 4.61it/s] 83%|████████▎ | 3515/4250 [16:27<02:37, 4.67it/s] 83%|████████▎ | 3516/4250 [16:27<02:30, 4.87it/s] 83%|████████▎ | 3517/4250 [16:28<02:29, 4.90it/s] 83%|████████▎ | 3518/4250 [16:28<02:29, 4.89it/s] 83%|████████▎ | 3519/4250 [16:28<02:27, 4.97it/s] 83%|████████▎ | 3520/4250 [16:28<02:27, 4.95it/s] 83%|████████▎ | 3521/4250 [16:28<02:21, 5.15it/s] 83%|████████▎ | 3522/4250 [16:29<02:20, 5.19it/s] 83%|████████▎ | 3523/4250 [16:29<02:31, 4.81it/s] 83%|████████▎ | 3524/4250 [16:29<02:49, 4.28it/s] 83%|████████▎ | 3525/4250 [16:29<02:38, 4.58it/s] 83%|████████▎ | 3526/4250 [16:30<02:50, 4.25it/s] 83%|████████▎ | 3527/4250 [16:30<04:51, 2.48it/s] 83%|████████▎ | 3528/4250 [16:31<04:29, 2.68it/s] 83%|████████▎ | 3529/4250 [16:31<03:46, 3.18it/s] 83%|████████▎ | 3530/4250 [16:31<03:28, 3.45it/s] 83%|████████▎ | 3531/4250 [16:31<03:05, 3.87it/s] 83%|████████▎ | 3532/4250 [16:31<02:56, 4.06it/s] 83%|████████▎ | 3533/4250 [16:32<03:17, 3.63it/s] 83%|████████▎ | 3534/4250 [16:32<02:57, 4.04it/s] 83%|████████▎ | 3535/4250 [16:32<02:38, 4.51it/s] 83%|████████▎ | 3536/4250 [16:32<02:50, 4.18it/s] 83%|████████▎ | 3537/4250 [16:33<02:41, 4.42it/s] 83%|████████▎ | 3538/4250 [16:33<02:35, 4.59it/s] 83%|████████▎ | 3539/4250 [16:33<02:30, 4.72it/s] 83%|████████▎ | 3540/4250 [16:33<02:54, 4.06it/s] 83%|████████▎ | 3541/4250 [16:34<02:44, 4.32it/s] 83%|████████▎ | 3542/4250 [16:34<03:11, 3.69it/s] 83%|████████▎ | 3543/4250 [16:35<04:27, 2.64it/s] 83%|████████▎ | 3544/4250 [16:35<03:41, 3.18it/s] 83%|████████▎ | 3545/4250 [16:35<03:09, 3.73it/s] 83%|████████▎ | 3546/4250 [16:35<03:07, 3.76it/s] 83%|████████▎ | 3547/4250 [16:35<03:23, 3.46it/s] 83%|████████▎ | 3548/4250 [16:36<03:19, 3.52it/s] 84%|████████▎ | 3549/4250 [16:36<03:09, 3.69it/s] 84%|████████▎ | 3550/4250 [16:36<02:46, 4.22it/s] 84%|████████▎ | 3551/4250 [16:36<02:53, 4.03it/s] 84%|████████▎ | 3552/4250 [16:37<02:44, 4.25it/s] 84%|████████▎ | 3553/4250 [16:37<02:37, 4.42it/s] 84%|████████▎ | 3554/4250 [16:37<02:46, 4.18it/s] 84%|████████▎ | 3555/4250 [16:37<02:31, 4.60it/s] 84%|████████▎ | 3556/4250 [16:37<02:20, 4.95it/s] 84%|████████▎ | 3557/4250 [16:38<02:18, 5.02it/s] 84%|████████▎ | 3558/4250 [16:38<02:20, 4.92it/s] 84%|████████▎ | 3559/4250 [16:38<02:36, 4.41it/s] 84%|████████▍ | 3560/4250 [16:39<04:31, 2.54it/s] 84%|████████▍ | 3561/4250 [16:39<03:54, 2.93it/s] 84%|████████▍ | 3562/4250 [16:39<03:52, 2.96it/s] 84%|████████▍ | 3563/4250 [16:40<03:14, 3.54it/s] 84%|████████▍ | 3564/4250 [16:40<03:05, 3.71it/s] 84%|████████▍ | 3565/4250 [16:40<02:58, 3.84it/s] 84%|████████▍ | 3566/4250 [16:41<04:09, 2.75it/s] 84%|████████▍ | 3567/4250 [16:41<03:39, 3.11it/s] 84%|████████▍ | 3568/4250 [16:41<03:17, 3.45it/s] 84%|████████▍ | 3569/4250 [16:41<02:57, 3.84it/s] 84%|████████▍ | 3570/4250 [16:41<02:39, 4.25it/s] 84%|████████▍ | 3571/4250 [16:42<02:35, 4.37it/s] 84%|████████▍ | 3572/4250 [16:42<02:47, 4.05it/s] 84%|████████▍ | 3573/4250 [16:42<03:08, 3.60it/s] 84%|████████▍ | 3574/4250 [16:43<02:47, 4.03it/s] 84%|████████▍ | 3575/4250 [16:43<02:58, 3.79it/s] 84%|████████▍ | 3576/4250 [16:43<02:41, 4.17it/s] 84%|████████▍ | 3577/4250 [16:43<02:46, 4.04it/s] 84%|████████▍ | 3578/4250 [16:43<02:41, 4.16it/s] 84%|████████▍ | 3579/4250 [16:44<02:34, 4.35it/s] 84%|████████▍ | 3580/4250 [16:44<02:42, 4.13it/s] 84%|████████▍ | 3581/4250 [16:44<02:32, 4.39it/s] 84%|████████▍ | 3582/4250 [16:45<03:19, 3.34it/s] 84%|████████▍ | 3583/4250 [16:45<02:54, 3.83it/s] 84%|████████▍ | 3584/4250 [16:45<02:44, 4.05it/s] 84%|████████▍ | 3585/4250 [16:45<02:31, 4.39it/s] 84%|████████▍ | 3586/4250 [16:45<02:21, 4.71it/s] 84%|████████▍ | 3587/4250 [16:46<02:21, 4.70it/s] 84%|████████▍ | 3588/4250 [16:46<02:15, 4.90it/s] 84%|████████▍ | 3589/4250 [16:46<02:18, 4.77it/s] 84%|████████▍ | 3590/4250 [16:46<02:19, 4.73it/s] 84%|████████▍ | 3591/4250 [16:46<02:21, 4.66it/s] 85%|████████▍ | 3592/4250 [16:47<02:24, 4.56it/s] 85%|████████▍ | 3593/4250 [16:47<02:29, 4.41it/s] 85%|████████▍ | 3594/4250 [16:47<02:45, 3.97it/s] 85%|████████▍ | 3595/4250 [16:47<02:37, 4.15it/s] 85%|████████▍ | 3596/4250 [16:48<02:25, 4.50it/s] 85%|████████▍ | 3597/4250 [16:48<02:14, 4.86it/s] 85%|████████▍ | 3598/4250 [16:48<02:23, 4.55it/s] 85%|████████▍ | 3599/4250 [16:48<02:10, 4.98it/s] 85%|████████▍ | 3600/4250 [16:48<02:14, 4.85it/s] 85%|████████▍ | 3601/4250 [16:49<02:05, 5.18it/s] 85%|████████▍ | 3602/4250 [16:49<02:05, 5.17it/s] 85%|████████▍ | 3603/4250 [16:49<02:16, 4.75it/s] 85%|████████▍ | 3604/4250 [16:49<02:12, 4.87it/s] 85%|████████▍ | 3605/4250 [16:49<02:10, 4.95it/s] 85%|████████▍ | 3606/4250 [16:50<02:03, 5.21it/s] 85%|████████▍ | 3607/4250 [16:50<02:08, 5.02it/s] 85%|████████▍ | 3608/4250 [16:50<02:24, 4.45it/s] 85%|████████▍ | 3609/4250 [16:50<02:26, 4.37it/s] 85%|████████▍ | 3610/4250 [16:51<02:40, 3.99it/s] 85%|████████▍ | 3611/4250 [16:51<02:36, 4.08it/s] 85%|████████▍ | 3612/4250 [16:51<02:22, 4.47it/s] 85%|████████▌ | 3613/4250 [16:51<02:15, 4.70it/s] 85%|████████▌ | 3614/4250 [16:51<02:31, 4.20it/s] 85%|████████▌ | 3615/4250 [16:52<02:30, 4.23it/s] 85%|████████▌ | 3616/4250 [16:52<02:23, 4.43it/s] 85%|████████▌ | 3617/4250 [16:52<02:28, 4.28it/s] 85%|████████▌ | 3618/4250 [16:53<02:58, 3.54it/s] 85%|████████▌ | 3619/4250 [16:53<02:40, 3.92it/s] 85%|████████▌ | 3620/4250 [16:53<02:33, 4.11it/s] 85%|████████▌ | 3621/4250 [16:53<02:24, 4.36it/s] 85%|████████▌ | 3622/4250 [16:53<02:15, 4.63it/s] 85%|████████▌ | 3623/4250 [16:54<02:37, 3.99it/s] 85%|████████▌ | 3624/4250 [16:54<02:22, 4.38it/s] 85%|████████▌ | 3625/4250 [16:54<02:13, 4.68it/s] 85%|████████▌ | 3626/4250 [16:54<02:11, 4.76it/s] 85%|████████▌ | 3627/4250 [16:54<02:09, 4.80it/s] 85%|████████▌ | 3628/4250 [16:55<02:17, 4.52it/s] 85%|████████▌ | 3629/4250 [16:55<02:24, 4.30it/s] 85%|████████▌ | 3630/4250 [16:55<02:48, 3.69it/s] 85%|████████▌ | 3631/4250 [16:56<02:46, 3.71it/s] 85%|████████▌ | 3632/4250 [16:56<02:33, 4.02it/s] 85%|████████▌ | 3633/4250 [16:56<02:19, 4.43it/s] 86%|████████▌ | 3634/4250 [16:56<02:12, 4.67it/s] 86%|████████▌ | 3635/4250 [16:56<02:11, 4.69it/s] 86%|████████▌ | 3636/4250 [16:57<02:02, 5.00it/s] 86%|████████▌ | 3637/4250 [16:57<02:06, 4.85it/s] 86%|████████▌ | 3638/4250 [16:57<02:07, 4.78it/s] 86%|████████▌ | 3639/4250 [16:57<02:11, 4.65it/s] 86%|████████▌ | 3640/4250 [16:57<02:12, 4.60it/s] 86%|████████▌ | 3641/4250 [16:58<02:35, 3.91it/s] 86%|████████▌ | 3642/4250 [16:58<02:35, 3.92it/s] 86%|████████▌ | 3643/4250 [16:58<02:36, 3.88it/s] 86%|████████▌ | 3644/4250 [16:58<02:24, 4.19it/s] 86%|████████▌ | 3645/4250 [16:59<02:26, 4.14it/s] 86%|████████▌ | 3646/4250 [16:59<02:15, 4.45it/s] 86%|████████▌ | 3647/4250 [16:59<02:13, 4.52it/s] 86%|████████▌ | 3648/4250 [16:59<02:13, 4.52it/s] 86%|████████▌ | 3649/4250 [17:00<02:07, 4.70it/s] 86%|████████▌ | 3650/4250 [17:00<02:05, 4.80it/s] 86%|████████▌ | 3651/4250 [17:00<02:32, 3.93it/s] 86%|████████▌ | 3652/4250 [17:00<02:26, 4.08it/s] 86%|████████▌ | 3653/4250 [17:01<02:18, 4.32it/s] 86%|████████▌ | 3654/4250 [17:01<02:53, 3.43it/s] 86%|████████▌ | 3655/4250 [17:01<02:34, 3.86it/s] 86%|████████▌ | 3656/4250 [17:01<02:27, 4.02it/s] 86%|████████▌ | 3657/4250 [17:02<02:30, 3.95it/s] 86%|████████▌ | 3658/4250 [17:02<02:37, 3.76it/s] 86%|████████▌ | 3659/4250 [17:02<02:34, 3.82it/s] 86%|████████▌ | 3660/4250 [17:02<02:22, 4.15it/s] 86%|████████▌ | 3661/4250 [17:03<02:44, 3.59it/s] 86%|████████▌ | 3662/4250 [17:03<02:31, 3.87it/s] 86%|████████▌ | 3663/4250 [17:03<02:51, 3.41it/s] 86%|████████▌ | 3664/4250 [17:04<02:54, 3.36it/s] 86%|████████▌ | 3665/4250 [17:04<02:49, 3.45it/s] 86%|████████▋ | 3666/4250 [17:04<02:46, 3.50it/s] 86%|████████▋ | 3667/4250 [17:04<02:42, 3.59it/s] 86%|████████▋ | 3668/4250 [17:05<02:32, 3.82it/s] 86%|████████▋ | 3669/4250 [17:05<02:16, 4.24it/s] 86%|████████▋ | 3670/4250 [17:05<02:07, 4.56it/s] 86%|████████▋ | 3671/4250 [17:05<02:36, 3.71it/s] 86%|████████▋ | 3672/4250 [17:06<02:29, 3.87it/s] 86%|████████▋ | 3673/4250 [17:06<02:48, 3.42it/s] 86%|████████▋ | 3674/4250 [17:06<02:26, 3.93it/s] 86%|████████▋ | 3675/4250 [17:06<02:22, 4.05it/s] 86%|████████▋ | 3676/4250 [17:07<02:09, 4.44it/s] 87%|████████▋ | 3677/4250 [17:07<02:09, 4.43it/s] 87%|████████▋ | 3678/4250 [17:07<02:18, 4.12it/s] 87%|████████▋ | 3679/4250 [17:07<02:07, 4.47it/s] 87%|████████▋ | 3680/4250 [17:08<02:28, 3.85it/s] 87%|████████▋ | 3681/4250 [17:08<02:37, 3.61it/s] 87%|████████▋ | 3682/4250 [17:08<02:25, 3.91it/s] 87%|████████▋ | 3683/4250 [17:08<02:20, 4.03it/s] 87%|████████▋ | 3684/4250 [17:09<02:09, 4.38it/s] 87%|████████▋ | 3685/4250 [17:09<02:28, 3.79it/s] 87%|████████▋ | 3686/4250 [17:09<02:20, 4.01it/s] 87%|████████▋ | 3687/4250 [17:09<02:06, 4.43it/s] 87%|████████▋ | 3688/4250 [17:10<02:15, 4.13it/s] 87%|████████▋ | 3689/4250 [17:10<02:17, 4.09it/s] 87%|████████▋ | 3690/4250 [17:10<02:15, 4.15it/s] 87%|████████▋ | 3691/4250 [17:10<02:36, 3.58it/s] 87%|████████▋ | 3692/4250 [17:11<02:30, 3.72it/s] 87%|████████▋ | 3693/4250 [17:11<02:20, 3.97it/s] 87%|████████▋ | 3694/4250 [17:11<02:13, 4.17it/s] 87%|████████▋ | 3695/4250 [17:11<02:10, 4.26it/s] 87%|████████▋ | 3696/4250 [17:12<02:09, 4.26it/s] 87%|████████▋ | 3697/4250 [17:12<02:04, 4.45it/s] 87%|████████▋ | 3698/4250 [17:12<02:06, 4.37it/s] 87%|████████▋ | 3699/4250 [17:12<02:22, 3.86it/s] 87%|████████▋ | 3700/4250 [17:13<02:19, 3.95it/s] 87%|████████▋ | 3701/4250 [17:13<02:31, 3.63it/s] 87%|████████▋ | 3702/4250 [17:13<02:16, 4.01it/s] 87%|████████▋ | 3703/4250 [17:13<02:08, 4.26it/s] 87%|████████▋ | 3704/4250 [17:13<02:07, 4.29it/s] 87%|████████▋ | 3705/4250 [17:14<02:03, 4.41it/s] 87%|████████▋ | 3706/4250 [17:14<02:02, 4.44it/s] 87%|████████▋ | 3707/4250 [17:14<01:54, 4.74it/s] 87%|████████▋ | 3708/4250 [17:14<01:59, 4.52it/s] 87%|████████▋ | 3709/4250 [17:15<02:09, 4.17it/s] 87%|████████▋ | 3710/4250 [17:15<02:00, 4.48it/s] 87%|████████▋ | 3711/4250 [17:15<01:54, 4.69it/s] 87%|████████▋ | 3712/4250 [17:15<01:54, 4.72it/s] 87%|████████▋ | 3713/4250 [17:16<03:11, 2.81it/s] 87%|████████▋ | 3714/4250 [17:16<02:47, 3.19it/s] 87%|████████▋ | 3715/4250 [17:16<02:30, 3.55it/s] 87%|████████▋ | 3716/4250 [17:17<02:29, 3.57it/s] 87%|████████▋ | 3717/4250 [17:17<02:23, 3.71it/s] 87%|████████▋ | 3718/4250 [17:17<02:20, 3.78it/s] 88%|████████▊ | 3719/4250 [17:17<02:16, 3.90it/s] 88%|████████▊ | 3720/4250 [17:18<02:26, 3.61it/s] 88%|████████▊ | 3721/4250 [17:18<02:40, 3.31it/s] 88%|████████▊ | 3722/4250 [17:18<02:19, 3.80it/s] 88%|████████▊ | 3723/4250 [17:18<02:16, 3.87it/s] 88%|████████▊ | 3724/4250 [17:19<02:27, 3.56it/s] 88%|████████▊ | 3725/4250 [17:19<03:05, 2.83it/s] 88%|████████▊ | 3726/4250 [17:20<02:41, 3.24it/s] 88%|████████▊ | 3727/4250 [17:20<02:27, 3.54it/s] 88%|████████▊ | 3728/4250 [17:20<02:10, 4.01it/s] 88%|████████▊ | 3729/4250 [17:20<01:58, 4.41it/s] 88%|████████▊ | 3730/4250 [17:20<01:53, 4.60it/s] 88%|████████▊ | 3731/4250 [17:20<01:50, 4.68it/s] 88%|████████▊ | 3732/4250 [17:21<01:53, 4.55it/s] 88%|████████▊ | 3733/4250 [17:21<01:52, 4.60it/s] 88%|████████▊ | 3734/4250 [17:21<01:51, 4.64it/s] 88%|████████▊ | 3735/4250 [17:21<01:46, 4.83it/s] 88%|████████▊ | 3736/4250 [17:22<02:00, 4.28it/s] 88%|████████▊ | 3737/4250 [17:22<01:55, 4.44it/s] 88%|████████▊ | 3738/4250 [17:22<01:49, 4.66it/s] 88%|████████▊ | 3739/4250 [17:22<01:48, 4.71it/s] 88%|████████▊ | 3740/4250 [17:22<01:42, 4.98it/s] 88%|████████▊ | 3741/4250 [17:23<01:48, 4.69it/s] 88%|████████▊ | 3742/4250 [17:23<02:04, 4.09it/s] 88%|████████▊ | 3743/4250 [17:23<01:56, 4.36it/s] 88%|████████▊ | 3744/4250 [17:23<02:03, 4.09it/s] 88%|████████▊ | 3745/4250 [17:24<01:52, 4.47it/s] 88%|████████▊ | 3746/4250 [17:24<02:37, 3.19it/s] 88%|████████▊ | 3747/4250 [17:24<02:14, 3.74it/s] 88%|████████▊ | 3748/4250 [17:25<02:14, 3.72it/s] 88%|████████▊ | 3749/4250 [17:25<02:09, 3.88it/s] 88%|████████▊ | 3750/4250 [17:25<02:01, 4.13it/s] 88%|████████▊ | 3751/4250 [17:25<01:51, 4.49it/s] 88%|████████▊ | 3752/4250 [17:25<01:52, 4.43it/s] 88%|████████▊ | 3753/4250 [17:26<01:49, 4.54it/s] 88%|████████▊ | 3754/4250 [17:26<01:49, 4.53it/s] 88%|████████▊ | 3755/4250 [17:26<01:55, 4.27it/s] 88%|████████▊ | 3756/4250 [17:26<01:46, 4.62it/s] 88%|████████▊ | 3757/4250 [17:27<01:55, 4.25it/s] 88%|████████▊ | 3758/4250 [17:27<02:09, 3.80it/s] 88%|████████▊ | 3759/4250 [17:27<02:27, 3.33it/s] 88%|████████▊ | 3760/4250 [17:27<02:12, 3.70it/s] 88%|████████▊ | 3761/4250 [17:28<01:56, 4.19it/s] 89%|████████▊ | 3762/4250 [17:28<02:06, 3.85it/s] 89%|████████▊ | 3763/4250 [17:28<02:12, 3.67it/s] 89%|████████▊ | 3764/4250 [17:28<02:09, 3.75it/s] 89%|████████▊ | 3765/4250 [17:29<02:03, 3.92it/s] 89%|████████▊ | 3766/4250 [17:29<01:52, 4.29it/s] 89%|████████▊ | 3767/4250 [17:29<01:49, 4.41it/s] 89%|████████▊ | 3768/4250 [17:29<01:40, 4.80it/s] 89%|████████▊ | 3769/4250 [17:29<01:36, 4.96it/s] 89%|████████▊ | 3770/4250 [17:30<01:47, 4.48it/s] 89%|████████▊ | 3771/4250 [17:30<01:48, 4.40it/s] 89%|████████▉ | 3772/4250 [17:30<01:40, 4.75it/s] 89%|████████▉ | 3773/4250 [17:30<01:44, 4.56it/s] 89%|████████▉ | 3774/4250 [17:31<01:43, 4.61it/s] 89%|████████▉ | 3775/4250 [17:31<01:42, 4.64it/s] 89%|████████▉ | 3776/4250 [17:31<01:37, 4.84it/s] 89%|████████▉ | 3777/4250 [17:31<01:38, 4.81it/s] 89%|████████▉ | 3778/4250 [17:31<01:42, 4.62it/s] 89%|████████▉ | 3779/4250 [17:32<01:40, 4.71it/s] 89%|████████▉ | 3780/4250 [17:32<01:47, 4.39it/s] 89%|████████▉ | 3781/4250 [17:32<01:40, 4.65it/s] 89%|████████▉ | 3782/4250 [17:32<01:38, 4.73it/s] 89%|████████▉ | 3783/4250 [17:33<01:42, 4.56it/s] 89%|████████▉ | 3784/4250 [17:33<01:33, 4.97it/s] 89%|████████▉ | 3785/4250 [17:33<02:11, 3.53it/s] 89%|████████▉ | 3786/4250 [17:33<02:04, 3.74it/s] 89%|████████▉ | 3787/4250 [17:34<02:19, 3.31it/s] 89%|████████▉ | 3788/4250 [17:34<02:14, 3.43it/s] 89%|████████▉ | 3789/4250 [17:34<01:57, 3.93it/s] 89%|████████▉ | 3790/4250 [17:34<01:48, 4.26it/s] 89%|████████▉ | 3791/4250 [17:35<01:54, 4.01it/s] 89%|████████▉ | 3792/4250 [17:35<01:53, 4.03it/s] 89%|████████▉ | 3793/4250 [17:35<01:44, 4.35it/s] 89%|████████▉ | 3794/4250 [17:35<01:51, 4.09it/s] 89%|████████▉ | 3795/4250 [17:36<01:56, 3.92it/s] 89%|████████▉ | 3796/4250 [17:36<01:50, 4.12it/s] 89%|████████▉ | 3797/4250 [17:36<01:46, 4.24it/s] 89%|████████▉ | 3798/4250 [17:36<01:45, 4.30it/s] 89%|████████▉ | 3799/4250 [17:37<01:39, 4.53it/s] 89%|████████▉ | 3800/4250 [17:37<01:46, 4.24it/s] 89%|████████▉ | 3801/4250 [17:37<01:37, 4.58it/s] 89%|████████▉ | 3802/4250 [17:37<01:30, 4.95it/s] 89%|████████▉ | 3803/4250 [17:37<01:28, 5.04it/s] 90%|████████▉ | 3804/4250 [17:38<01:33, 4.76it/s] 90%|████████▉ | 3805/4250 [17:38<01:27, 5.11it/s] 90%|████████▉ | 3806/4250 [17:38<01:43, 4.29it/s] 90%|████████▉ | 3807/4250 [17:38<01:36, 4.60it/s] 90%|████████▉ | 3808/4250 [17:38<01:27, 5.05it/s] 90%|████████▉ | 3809/4250 [17:39<01:37, 4.50it/s] 90%|████████▉ | 3810/4250 [17:39<01:43, 4.25it/s] 90%|████████▉ | 3811/4250 [17:39<01:46, 4.11it/s] 90%|████████▉ | 3812/4250 [17:39<01:36, 4.55it/s] 90%|████████▉ | 3813/4250 [17:40<01:48, 4.03it/s] 90%|████████▉ | 3814/4250 [17:40<01:41, 4.29it/s] 90%|████████▉ | 3815/4250 [17:40<01:54, 3.81it/s] 90%|████████▉ | 3816/4250 [17:40<01:41, 4.26it/s] 90%|████████▉ | 3817/4250 [17:41<01:33, 4.65it/s] 90%|████████▉ | 3818/4250 [17:41<01:29, 4.84it/s] 90%|████████▉ | 3819/4250 [17:41<01:37, 4.42it/s] 90%|████████▉ | 3820/4250 [17:41<01:36, 4.46it/s] 90%|████████▉ | 3821/4250 [17:41<01:40, 4.28it/s] 90%|████████▉ | 3822/4250 [17:42<01:31, 4.69it/s] 90%|████████▉ | 3823/4250 [17:42<01:25, 5.00it/s] 90%|████████▉ | 3824/4250 [17:42<01:24, 5.03it/s] 90%|█████████ | 3825/4250 [17:42<01:31, 4.65it/s] 90%|█████████ | 3826/4250 [17:42<01:31, 4.63it/s] 90%|█████████ | 3827/4250 [17:43<01:29, 4.72it/s] 90%|█████████ | 3828/4250 [17:43<01:28, 4.78it/s] 90%|█████████ | 3829/4250 [17:43<01:42, 4.09it/s][INFO|trainer.py:805] 2024-08-30 20:43:32,652 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: tokens, ner_tags, id. If tokens, ner_tags, id are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3788] 2024-08-30 20:43:32,655 >> ***** Running Evaluation ***** [INFO|trainer.py:3790] 2024-08-30 20:43:32,655 >> Num examples = 6810 [INFO|trainer.py:3793] 2024-08-30 20:43:32,655 >> Batch size = 8 {'eval_loss': 0.1294233798980713, 'eval_precision': 0.7938948817994033, 'eval_recall': 0.8093121197941039, 'eval_f1': 0.8015293708724366, 'eval_accuracy': 0.9767668584453568, 'eval_runtime': 14.774, 'eval_samples_per_second': 460.946, 'eval_steps_per_second': 57.669, 'epoch': 8.0} {'loss': 0.0053, 'grad_norm': 0.11404519528150558, 'learning_rate': 8.823529411764707e-06, 'epoch': 8.23} 0%| | 0/852 [00:00> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-3829 [INFO|configuration_utils.py:472] 2024-08-30 20:43:47,101 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-3829/config.json [INFO|modeling_utils.py:2690] 2024-08-30 20:43:48,426 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-3829/model.safetensors [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:43:48,427 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-3829/tokenizer_config.json [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:43:48,428 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-3829/special_tokens_map.json [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:43:50,869 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:43:50,869 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json 90%|█████████ | 3830/4250 [18:02<40:12, 5.74s/it] 90%|█████████ | 3831/4250 [18:02<28:31, 4.08s/it] 90%|█████████ | 3832/4250 [18:02<20:17, 2.91s/it] 90%|█████████ | 3833/4250 [18:02<14:41, 2.11s/it] 90%|█████████ | 3834/4250 [18:03<10:39, 1.54s/it] 90%|█████████ | 3835/4250 [18:03<08:04, 1.17s/it] 90%|█████████ | 3836/4250 [18:03<06:02, 1.14it/s] 90%|█████████ | 3837/4250 [18:03<04:54, 1.40it/s] 90%|█████████ | 3838/4250 [18:04<03:47, 1.81it/s] 90%|█████████ | 3839/4250 [18:04<03:39, 1.87it/s] 90%|█████████ | 3840/4250 [18:04<02:53, 2.36it/s] 90%|█████████ | 3841/4250 [18:05<02:27, 2.77it/s] 90%|█████████ | 3842/4250 [18:05<02:22, 2.86it/s] 90%|█████████ | 3843/4250 [18:05<02:01, 3.34it/s] 90%|█████████ | 3844/4250 [18:05<02:03, 3.28it/s] 90%|█████████ | 3845/4250 [18:06<01:49, 3.71it/s] 90%|█████████ | 3846/4250 [18:06<01:41, 3.97it/s] 91%|█████████ | 3847/4250 [18:06<01:36, 4.17it/s] 91%|█████████ | 3848/4250 [18:06<01:27, 4.58it/s] 91%|█████████ | 3849/4250 [18:06<01:22, 4.87it/s] 91%|█████████ | 3850/4250 [18:07<01:37, 4.11it/s] 91%|█████████ | 3851/4250 [18:07<01:36, 4.15it/s] 91%|█████████ | 3852/4250 [18:07<01:28, 4.52it/s] 91%|█████████ | 3853/4250 [18:07<01:23, 4.75it/s] 91%|█████████ | 3854/4250 [18:07<01:30, 4.39it/s] 91%|█████████ | 3855/4250 [18:08<01:26, 4.56it/s] 91%|█████████ | 3856/4250 [18:08<01:28, 4.43it/s] 91%|█████████ | 3857/4250 [18:08<01:31, 4.29it/s] 91%|█████████ | 3858/4250 [18:08<01:31, 4.29it/s] 91%|█████████ | 3859/4250 [18:09<01:56, 3.36it/s] 91%|█████████ | 3860/4250 [18:09<01:49, 3.57it/s] 91%|█████████ | 3861/4250 [18:09<01:50, 3.52it/s] 91%|█████████ | 3862/4250 [18:10<01:38, 3.94it/s] 91%|█████████ | 3863/4250 [18:10<01:46, 3.62it/s] 91%|█████████ | 3864/4250 [18:10<01:46, 3.63it/s] 91%|█████████ | 3865/4250 [18:10<01:46, 3.60it/s] 91%|█████████ | 3866/4250 [18:11<01:40, 3.83it/s] 91%|█████████ | 3867/4250 [18:11<01:34, 4.07it/s] 91%|█████████ | 3868/4250 [18:11<01:34, 4.06it/s] 91%|█████████ | 3869/4250 [18:11<01:32, 4.14it/s] 91%|█████████ | 3870/4250 [18:12<01:30, 4.18it/s] 91%|█████████ | 3871/4250 [18:12<01:33, 4.06it/s] 91%|█████████ | 3872/4250 [18:12<01:28, 4.29it/s] 91%|█████████ | 3873/4250 [18:12<01:20, 4.70it/s] 91%|█████████ | 3874/4250 [18:13<01:35, 3.95it/s] 91%|█████████ | 3875/4250 [18:13<01:29, 4.19it/s] 91%|█████████ | 3876/4250 [18:13<01:22, 4.54it/s] 91%|█████████ | 3877/4250 [18:13<01:14, 4.98it/s] 91%|█████████ | 3878/4250 [18:13<01:26, 4.31it/s] 91%|█████████▏| 3879/4250 [18:14<01:21, 4.58it/s] 91%|█████████▏| 3880/4250 [18:14<01:22, 4.46it/s] 91%|█████████▏| 3881/4250 [18:14<01:17, 4.78it/s] 91%|█████████▏| 3882/4250 [18:14<01:24, 4.36it/s] 91%|█████████▏| 3883/4250 [18:15<01:51, 3.30it/s] 91%|█████████▏| 3884/4250 [18:15<01:50, 3.30it/s] 91%|█████████▏| 3885/4250 [18:15<01:49, 3.33it/s] 91%|█████████▏| 3886/4250 [18:16<01:36, 3.77it/s] 91%|█████████▏| 3887/4250 [18:16<01:30, 4.03it/s] 91%|█████████▏| 3888/4250 [18:16<01:26, 4.16it/s] 92%|█████████▏| 3889/4250 [18:16<01:24, 4.28it/s] 92%|█████████▏| 3890/4250 [18:16<01:22, 4.38it/s] 92%|█████████▏| 3891/4250 [18:17<01:16, 4.70it/s] 92%|█████████▏| 3892/4250 [18:17<01:12, 4.93it/s] 92%|█████████▏| 3893/4250 [18:17<01:09, 5.14it/s] 92%|█████████▏| 3894/4250 [18:17<01:15, 4.69it/s] 92%|█████████▏| 3895/4250 [18:17<01:20, 4.38it/s] 92%|█████████▏| 3896/4250 [18:18<01:16, 4.66it/s] 92%|█████████▏| 3897/4250 [18:18<01:13, 4.81it/s] 92%|█████████▏| 3898/4250 [18:18<01:18, 4.48it/s] 92%|█████████▏| 3899/4250 [18:18<01:18, 4.50it/s] 92%|█████████▏| 3900/4250 [18:19<01:28, 3.94it/s] 92%|█████████▏| 3901/4250 [18:19<01:25, 4.06it/s] 92%|█████████▏| 3902/4250 [18:19<01:15, 4.59it/s] 92%|█████████▏| 3903/4250 [18:19<01:14, 4.67it/s] 92%|█████████▏| 3904/4250 [18:19<01:11, 4.86it/s] 92%|█████████▏| 3905/4250 [18:20<01:28, 3.89it/s] 92%|█████████▏| 3906/4250 [18:20<01:24, 4.06it/s] 92%|█████████▏| 3907/4250 [18:20<01:34, 3.64it/s] 92%|█████████▏| 3908/4250 [18:21<01:28, 3.87it/s] 92%|█████████▏| 3909/4250 [18:21<01:21, 4.17it/s] 92%|█████████▏| 3910/4250 [18:21<01:24, 4.04it/s] 92%|█████████▏| 3911/4250 [18:21<01:16, 4.43it/s] 92%|█████████▏| 3912/4250 [18:21<01:11, 4.75it/s] 92%|█████████▏| 3913/4250 [18:22<01:11, 4.73it/s] 92%|█████████▏| 3914/4250 [18:22<01:12, 4.66it/s] 92%|█████████▏| 3915/4250 [18:22<01:17, 4.31it/s] 92%|█████████▏| 3916/4250 [18:22<01:18, 4.28it/s] 92%|█████████▏| 3917/4250 [18:23<01:16, 4.36it/s] 92%|█████████▏| 3918/4250 [18:23<01:15, 4.43it/s] 92%|█████████▏| 3919/4250 [18:23<01:33, 3.56it/s] 92%|█████████▏| 3920/4250 [18:23<01:24, 3.91it/s] 92%|█████████▏| 3921/4250 [18:24<01:17, 4.25it/s] 92%|█████████▏| 3922/4250 [18:24<01:27, 3.76it/s] 92%|█████████▏| 3923/4250 [18:24<01:25, 3.80it/s] 92%|█████████▏| 3924/4250 [18:24<01:27, 3.72it/s] 92%|█████████▏| 3925/4250 [18:25<01:23, 3.89it/s] 92%|█████████▏| 3926/4250 [18:25<01:16, 4.25it/s] 92%|█████████▏| 3927/4250 [18:25<01:09, 4.62it/s] 92%|█████████▏| 3928/4250 [18:25<01:11, 4.50it/s] 92%|█████████▏| 3929/4250 [18:25<01:07, 4.75it/s] 92%|█████████▏| 3930/4250 [18:26<01:10, 4.57it/s] 92%|█████████▏| 3931/4250 [18:26<01:09, 4.57it/s] 93%|█████████▎| 3932/4250 [18:26<01:11, 4.47it/s] 93%|█████████▎| 3933/4250 [18:26<01:09, 4.54it/s] 93%|█████████▎| 3934/4250 [18:27<01:08, 4.61it/s] 93%|█████████▎| 3935/4250 [18:27<01:05, 4.81it/s] 93%|█████████▎| 3936/4250 [18:27<01:13, 4.28it/s] 93%|█████████▎| 3937/4250 [18:27<01:07, 4.61it/s] 93%|█████████▎| 3938/4250 [18:27<01:04, 4.84it/s] 93%|█████████▎| 3939/4250 [18:28<01:09, 4.47it/s] 93%|█████████▎| 3940/4250 [18:28<01:06, 4.69it/s] 93%|█████████▎| 3941/4250 [18:29<01:48, 2.86it/s] 93%|█████████▎| 3942/4250 [18:29<01:39, 3.09it/s] 93%|█████████▎| 3943/4250 [18:29<01:34, 3.26it/s] 93%|█████████▎| 3944/4250 [18:29<01:20, 3.79it/s] 93%|█████████▎| 3945/4250 [18:29<01:13, 4.13it/s] 93%|█████████▎| 3946/4250 [18:30<01:21, 3.73it/s] 93%|█████████▎| 3947/4250 [18:30<01:17, 3.93it/s] 93%|█████████▎| 3948/4250 [18:30<01:13, 4.11it/s] 93%|█████████▎| 3949/4250 [18:30<01:09, 4.33it/s] 93%|█████████▎| 3950/4250 [18:31<01:08, 4.40it/s] 93%|█████████▎| 3951/4250 [18:31<01:07, 4.41it/s] 93%|█████████▎| 3952/4250 [18:31<01:03, 4.73it/s] 93%|█████████▎| 3953/4250 [18:31<01:04, 4.60it/s] 93%|█████████▎| 3954/4250 [18:31<01:06, 4.43it/s] 93%|█████████▎| 3955/4250 [18:32<01:01, 4.78it/s] 93%|█████████▎| 3956/4250 [18:32<01:16, 3.82it/s] 93%|█████████▎| 3957/4250 [18:32<01:12, 4.03it/s] 93%|█████████▎| 3958/4250 [18:32<01:11, 4.10it/s] 93%|█████████▎| 3959/4250 [18:33<01:05, 4.44it/s] 93%|█████████▎| 3960/4250 [18:33<01:01, 4.70it/s] 93%|█████████▎| 3961/4250 [18:33<00:59, 4.87it/s] 93%|█████████▎| 3962/4250 [18:33<01:02, 4.58it/s] 93%|█████████▎| 3963/4250 [18:33<01:01, 4.63it/s] 93%|█████████▎| 3964/4250 [18:34<01:01, 4.66it/s] 93%|█████████▎| 3965/4250 [18:34<00:59, 4.82it/s] 93%|█████████▎| 3966/4250 [18:34<00:57, 4.93it/s] 93%|█████████▎| 3967/4250 [18:34<01:04, 4.40it/s] 93%|█████████▎| 3968/4250 [18:35<00:58, 4.80it/s] 93%|█████████▎| 3969/4250 [18:35<01:00, 4.63it/s] 93%|█████████▎| 3970/4250 [18:35<01:00, 4.64it/s] 93%|█████████▎| 3971/4250 [18:35<00:59, 4.66it/s] 93%|█████████▎| 3972/4250 [18:35<00:57, 4.80it/s] 93%|█████████▎| 3973/4250 [18:36<00:59, 4.65it/s] 94%|█████████▎| 3974/4250 [18:36<00:56, 4.84it/s] 94%|█████████▎| 3975/4250 [18:36<01:01, 4.44it/s] 94%|█████████▎| 3976/4250 [18:36<00:57, 4.75it/s] 94%|█████████▎| 3977/4250 [18:36<00:54, 5.02it/s] 94%|█████████▎| 3978/4250 [18:37<00:55, 4.93it/s] 94%|█████████▎| 3979/4250 [18:37<01:05, 4.15it/s] 94%|█████████▎| 3980/4250 [18:38<01:37, 2.76it/s] 94%|█████████▎| 3981/4250 [18:38<01:27, 3.08it/s] 94%|█████████▎| 3982/4250 [18:38<01:22, 3.24it/s] 94%|█████████▎| 3983/4250 [18:38<01:17, 3.45it/s] 94%|█████████▎| 3984/4250 [18:39<01:12, 3.69it/s] 94%|█████████▍| 3985/4250 [18:39<01:09, 3.83it/s] 94%|█████████▍| 3986/4250 [18:39<01:04, 4.12it/s] 94%|█████████▍| 3987/4250 [18:39<01:18, 3.35it/s] 94%|█████████▍| 3988/4250 [18:40<01:15, 3.46it/s] 94%|█████████▍| 3989/4250 [18:40<01:11, 3.67it/s] 94%|█████████▍| 3990/4250 [18:40<01:07, 3.85it/s] 94%|█████████▍| 3991/4250 [18:40<01:00, 4.28it/s] 94%|█████████▍| 3992/4250 [18:41<01:01, 4.16it/s] 94%|█████████▍| 3993/4250 [18:41<00:57, 4.44it/s] 94%|█████████▍| 3994/4250 [18:41<01:18, 3.26it/s] 94%|█████████▍| 3995/4250 [18:42<01:10, 3.59it/s] 94%|█████████▍| 3996/4250 [18:42<01:02, 4.05it/s] 94%|█████████▍| 3997/4250 [18:42<00:55, 4.58it/s] 94%|█████████▍| 3998/4250 [18:42<01:02, 4.01it/s] 94%|█████████▍| 3999/4250 [18:42<00:54, 4.62it/s] 94%|█████████▍| 4000/4250 [18:43<00:56, 4.40it/s] 94%|█████████▍| 4000/4250 [18:43<00:56, 4.40it/s] 94%|█████████▍| 4001/4250 [18:43<01:03, 3.90it/s] 94%|█████████▍| 4002/4250 [18:43<00:58, 4.22it/s] 94%|█████████▍| 4003/4250 [18:43<00:58, 4.21it/s] 94%|█████████▍| 4004/4250 [18:44<00:58, 4.17it/s] 94%|█████████▍| 4005/4250 [18:44<00:55, 4.43it/s] 94%|█████████▍| 4006/4250 [18:44<00:51, 4.70it/s] 94%|█████████▍| 4007/4250 [18:44<00:53, 4.56it/s] 94%|█████████▍| 4008/4250 [18:44<00:48, 4.97it/s] 94%|█████████▍| 4009/4250 [18:45<00:51, 4.66it/s] 94%|█████████▍| 4010/4250 [18:45<00:53, 4.52it/s] 94%|█████████▍| 4011/4250 [18:45<00:51, 4.65it/s] 94%|█████████▍| 4012/4250 [18:45<00:53, 4.49it/s] 94%|█████████▍| 4013/4250 [18:45<00:49, 4.81it/s] 94%|█████████▍| 4014/4250 [18:46<00:52, 4.48it/s] 94%|█████████▍| 4015/4250 [18:46<00:49, 4.74it/s] 94%|█████████▍| 4016/4250 [18:46<00:52, 4.46it/s] 95%|█████████▍| 4017/4250 [18:46<00:55, 4.23it/s] 95%|█████████▍| 4018/4250 [18:47<00:56, 4.10it/s] 95%|█████████▍| 4019/4250 [18:47<00:58, 3.94it/s] 95%|█████████▍| 4020/4250 [18:47<00:56, 4.08it/s] 95%|█████████▍| 4021/4250 [18:47<00:53, 4.25it/s] 95%|█████████▍| 4022/4250 [18:48<00:51, 4.43it/s] 95%|█████████▍| 4023/4250 [18:48<00:46, 4.83it/s] 95%|█████████▍| 4024/4250 [18:48<00:48, 4.68it/s] 95%|█████████▍| 4025/4250 [18:48<00:47, 4.70it/s] 95%|█████████▍| 4026/4250 [18:48<00:56, 3.98it/s] 95%|█████████▍| 4027/4250 [18:49<00:52, 4.27it/s] 95%|█████████▍| 4028/4250 [18:49<00:51, 4.35it/s] 95%|█████████▍| 4029/4250 [18:49<00:49, 4.46it/s] 95%|█████████▍| 4030/4250 [18:49<00:55, 3.95it/s] 95%|█████████▍| 4031/4250 [18:50<00:53, 4.09it/s] 95%|█████████▍| 4032/4250 [18:50<00:51, 4.25it/s] 95%|█████████▍| 4033/4250 [18:50<01:01, 3.53it/s] 95%|█████████▍| 4034/4250 [18:50<00:56, 3.85it/s] 95%|█████████▍| 4035/4250 [18:51<00:49, 4.37it/s] 95%|█████████▍| 4036/4250 [18:51<00:50, 4.23it/s] 95%|█████████▍| 4037/4250 [18:51<00:50, 4.19it/s] 95%|█████████▌| 4038/4250 [18:51<00:58, 3.64it/s] 95%|█████████▌| 4039/4250 [18:52<00:58, 3.62it/s] 95%|█████████▌| 4040/4250 [18:52<01:00, 3.46it/s] 95%|█████████▌| 4041/4250 [18:52<01:01, 3.41it/s] 95%|█████████▌| 4042/4250 [18:53<00:54, 3.81it/s] 95%|█████████▌| 4043/4250 [18:53<00:50, 4.09it/s] 95%|█████████▌| 4044/4250 [18:53<00:45, 4.55it/s] 95%|█████████▌| 4045/4250 [18:53<00:43, 4.73it/s] 95%|█████████▌| 4046/4250 [18:53<00:43, 4.72it/s] 95%|█████████▌| 4047/4250 [18:54<00:45, 4.50it/s] 95%|█████████▌| 4048/4250 [18:54<00:42, 4.70it/s] 95%|█████████▌| 4049/4250 [18:54<00:41, 4.89it/s] 95%|█████████▌| 4050/4250 [18:54<00:42, 4.71it/s] 95%|█████████▌| 4051/4250 [18:55<00:50, 3.96it/s] 95%|█████████▌| 4052/4250 [18:55<00:54, 3.62it/s] 95%|█████████▌| 4053/4250 [18:55<00:48, 4.03it/s] 95%|█████████▌| 4054/4250 [18:55<00:46, 4.21it/s] 95%|█████████▌| 4055/4250 [18:56<00:58, 3.36it/s] 95%|█████████▌| 4056/4250 [18:56<00:53, 3.60it/s] 95%|█████████▌| 4057/4250 [18:56<00:46, 4.16it/s] 95%|█████████▌| 4058/4250 [18:56<00:44, 4.31it/s] 96%|█████████▌| 4059/4250 [18:57<00:44, 4.29it/s] 96%|█████████▌| 4060/4250 [18:57<00:43, 4.35it/s] 96%|█████████▌| 4061/4250 [18:57<00:42, 4.49it/s] 96%|█████████▌| 4062/4250 [18:57<00:42, 4.41it/s] 96%|█████████▌| 4063/4250 [18:57<00:41, 4.45it/s] 96%|█████████▌| 4064/4250 [18:58<00:40, 4.56it/s] 96%|█████████▌| 4065/4250 [18:58<00:43, 4.26it/s] 96%|█████████▌| 4066/4250 [18:58<00:45, 4.01it/s] 96%|█████████▌| 4067/4250 [18:58<00:44, 4.12it/s] 96%|█████████▌| 4068/4250 [18:59<00:42, 4.31it/s] 96%|█████████▌| 4069/4250 [18:59<00:57, 3.14it/s] 96%|█████████▌| 4070/4250 [18:59<00:51, 3.49it/s] 96%|█████████▌| 4071/4250 [19:00<00:51, 3.49it/s] 96%|█████████▌| 4072/4250 [19:00<01:01, 2.91it/s] 96%|█████████▌| 4073/4250 [19:00<00:53, 3.29it/s] 96%|█████████▌| 4074/4250 [19:01<00:47, 3.69it/s] 96%|█████████▌| 4075/4250 [19:01<00:48, 3.58it/s] 96%|█████████▌| 4076/4250 [19:01<00:47, 3.63it/s] 96%|█████████▌| 4077/4250 [19:01<00:42, 4.07it/s] 96%|█████████▌| 4078/4250 [19:01<00:40, 4.30it/s] 96%|█████████▌| 4079/4250 [19:02<00:37, 4.50it/s] 96%|█████████▌| 4080/4250 [19:02<00:36, 4.71it/s] 96%|█████████▌| 4081/4250 [19:02<00:36, 4.65it/s] 96%|█████████▌| 4082/4250 [19:02<00:34, 4.91it/s] 96%|█████████▌| 4083/4250 [19:03<00:41, 3.99it/s] 96%|█████████▌| 4084/4250 [19:03<00:41, 4.01it/s] 96%|█████████▌| 4085/4250 [19:03<00:37, 4.38it/s] 96%|█████████▌| 4086/4250 [19:03<00:35, 4.67it/s] 96%|█████████▌| 4087/4250 [19:03<00:35, 4.59it/s] 96%|█████████▌| 4088/4250 [19:04<00:33, 4.83it/s] 96%|█████████▌| 4089/4250 [19:04<00:35, 4.51it/s] 96%|█████████▌| 4090/4250 [19:04<00:33, 4.82it/s] 96%|█████████▋| 4091/4250 [19:04<00:31, 5.04it/s] 96%|█████████▋| 4092/4250 [19:05<00:35, 4.41it/s] 96%|█████████▋| 4093/4250 [19:05<00:36, 4.26it/s] 96%|█████████▋| 4094/4250 [19:05<00:38, 4.04it/s] 96%|█████████▋| 4095/4250 [19:05<00:35, 4.38it/s] 96%|█████████▋| 4096/4250 [19:05<00:33, 4.53it/s] 96%|█████████▋| 4097/4250 [19:06<00:35, 4.35it/s] 96%|█████████▋| 4098/4250 [19:06<00:37, 4.10it/s] 96%|█████████▋| 4099/4250 [19:06<00:39, 3.80it/s] 96%|█████████▋| 4100/4250 [19:07<00:37, 3.99it/s] 96%|█████████▋| 4101/4250 [19:07<00:35, 4.21it/s] 97%|█████████▋| 4102/4250 [19:07<00:38, 3.82it/s] 97%|█████████▋| 4103/4250 [19:07<00:38, 3.85it/s] 97%|█████████▋| 4104/4250 [19:08<00:35, 4.08it/s] 97%|█████████▋| 4105/4250 [19:08<00:34, 4.22it/s] 97%|█████████▋| 4106/4250 [19:08<00:39, 3.62it/s] 97%|█████████▋| 4107/4250 [19:08<00:39, 3.60it/s] 97%|█████████▋| 4108/4250 [19:09<00:36, 3.87it/s] 97%|█████████▋| 4109/4250 [19:09<00:38, 3.69it/s] 97%|█████████▋| 4110/4250 [19:09<00:35, 3.93it/s] 97%|█████████▋| 4111/4250 [19:09<00:35, 3.87it/s] 97%|█████████▋| 4112/4250 [19:10<00:33, 4.13it/s] 97%|█████████▋| 4113/4250 [19:10<00:32, 4.23it/s] 97%|█████████▋| 4114/4250 [19:10<00:29, 4.54it/s] 97%|█████████▋| 4115/4250 [19:10<00:28, 4.66it/s] 97%|█████████▋| 4116/4250 [19:10<00:29, 4.61it/s] 97%|█████████▋| 4117/4250 [19:11<00:29, 4.47it/s] 97%|█████████▋| 4118/4250 [19:11<00:27, 4.71it/s] 97%|█████████▋| 4119/4250 [19:11<00:34, 3.75it/s] 97%|█████████▋| 4120/4250 [19:11<00:33, 3.90it/s] 97%|█████████▋| 4121/4250 [19:12<00:32, 3.97it/s] 97%|█████████▋| 4122/4250 [19:12<00:29, 4.37it/s] 97%|█████████▋| 4123/4250 [19:12<00:29, 4.34it/s] 97%|█████████▋| 4124/4250 [19:12<00:26, 4.73it/s] 97%|█████████▋| 4125/4250 [19:13<00:34, 3.67it/s] 97%|█████████▋| 4126/4250 [19:13<00:30, 4.04it/s] 97%|█████████▋| 4127/4250 [19:13<00:28, 4.27it/s] 97%|█████████▋| 4128/4250 [19:13<00:29, 4.13it/s] 97%|█████████▋| 4129/4250 [19:14<00:34, 3.46it/s] 97%|█████████▋| 4130/4250 [19:14<00:31, 3.81it/s] 97%|█████████▋| 4131/4250 [19:14<00:28, 4.24it/s] 97%|█████████▋| 4132/4250 [19:14<00:28, 4.16it/s] 97%|█████████▋| 4133/4250 [19:15<00:30, 3.79it/s] 97%|█████████▋| 4134/4250 [19:15<00:27, 4.21it/s] 97%|█████████▋| 4135/4250 [19:15<00:26, 4.36it/s] 97%|█████████▋| 4136/4250 [19:15<00:24, 4.71it/s] 97%|█████████▋| 4137/4250 [19:15<00:24, 4.62it/s] 97%|█████████▋| 4138/4250 [19:16<00:24, 4.59it/s] 97%|█████████▋| 4139/4250 [19:16<00:39, 2.79it/s] 97%|█████████▋| 4140/4250 [19:17<00:35, 3.10it/s] 97%|█████████▋| 4141/4250 [19:17<00:30, 3.56it/s] 97%|█████████▋| 4142/4250 [19:17<00:30, 3.53it/s] 97%|█████████▋| 4143/4250 [19:17<00:28, 3.73it/s] 98%|█████████▊| 4144/4250 [19:18<00:27, 3.88it/s] 98%|█████████▊| 4145/4250 [19:18<00:24, 4.35it/s] 98%|█████████▊| 4146/4250 [19:18<00:22, 4.59it/s] 98%|█████████▊| 4147/4250 [19:18<00:21, 4.82it/s] 98%|█████████▊| 4148/4250 [19:18<00:20, 4.90it/s] 98%|█████████▊| 4149/4250 [19:18<00:19, 5.24it/s] 98%|█████████▊| 4150/4250 [19:19<00:20, 4.86it/s] 98%|█████████▊| 4151/4250 [19:19<00:19, 5.06it/s] 98%|█████████▊| 4152/4250 [19:19<00:22, 4.29it/s] 98%|█████████▊| 4153/4250 [19:20<00:38, 2.54it/s] 98%|█████████▊| 4154/4250 [19:20<00:31, 3.03it/s] 98%|█████████▊| 4155/4250 [19:20<00:27, 3.49it/s] 98%|█████████▊| 4156/4250 [19:21<00:25, 3.66it/s] 98%|█████████▊| 4157/4250 [19:21<00:24, 3.86it/s] 98%|█████████▊| 4158/4250 [19:21<00:23, 3.95it/s] 98%|█████████▊| 4159/4250 [19:21<00:21, 4.15it/s] 98%|█████████▊| 4160/4250 [19:21<00:21, 4.20it/s] 98%|█████████▊| 4161/4250 [19:22<00:21, 4.21it/s] 98%|█████████▊| 4162/4250 [19:22<00:20, 4.29it/s] 98%|█████████▊| 4163/4250 [19:22<00:19, 4.35it/s] 98%|█████████▊| 4164/4250 [19:22<00:18, 4.58it/s] 98%|█████████▊| 4165/4250 [19:23<00:19, 4.45it/s] 98%|█████████▊| 4166/4250 [19:23<00:21, 3.91it/s] 98%|█████████▊| 4167/4250 [19:23<00:19, 4.36it/s] 98%|█████████▊| 4168/4250 [19:23<00:17, 4.69it/s] 98%|█████████▊| 4169/4250 [19:24<00:20, 3.87it/s] 98%|█████████▊| 4170/4250 [19:24<00:18, 4.34it/s] 98%|█████████▊| 4171/4250 [19:24<00:16, 4.78it/s] 98%|█████████▊| 4172/4250 [19:24<00:17, 4.49it/s] 98%|█████████▊| 4173/4250 [19:24<00:18, 4.20it/s] 98%|█████████▊| 4174/4250 [19:25<00:18, 4.14it/s] 98%|█████████▊| 4175/4250 [19:25<00:17, 4.30it/s] 98%|█████████▊| 4176/4250 [19:25<00:19, 3.78it/s] 98%|█████████▊| 4177/4250 [19:25<00:17, 4.14it/s] 98%|█████████▊| 4178/4250 [19:26<00:16, 4.30it/s] 98%|█████████▊| 4179/4250 [19:26<00:14, 4.84it/s] 98%|█████████▊| 4180/4250 [19:26<00:14, 4.87it/s] 98%|█████████▊| 4181/4250 [19:26<00:13, 5.04it/s] 98%|█████████▊| 4182/4250 [19:26<00:13, 4.99it/s] 98%|█████████▊| 4183/4250 [19:27<00:14, 4.62it/s] 98%|█████████▊| 4184/4250 [19:27<00:15, 4.33it/s] 98%|█████████▊| 4185/4250 [19:27<00:17, 3.62it/s] 98%|█████████▊| 4186/4250 [19:28<00:16, 3.90it/s] 99%|█████████▊| 4187/4250 [19:28<00:14, 4.23it/s] 99%|█████████▊| 4188/4250 [19:28<00:14, 4.14it/s] 99%|█████████▊| 4189/4250 [19:28<00:14, 4.17it/s] 99%|█████████▊| 4190/4250 [19:28<00:13, 4.46it/s] 99%|█████████▊| 4191/4250 [19:29<00:12, 4.81it/s] 99%|█████████▊| 4192/4250 [19:29<00:11, 5.01it/s] 99%|█████████▊| 4193/4250 [19:29<00:10, 5.30it/s] 99%|█████████▊| 4194/4250 [19:29<00:11, 4.86it/s] 99%|█████████▊| 4195/4250 [19:29<00:12, 4.36it/s] 99%|█████████▊| 4196/4250 [19:30<00:12, 4.21it/s] 99%|█████████▉| 4197/4250 [19:30<00:12, 4.26it/s] 99%|█████████▉| 4198/4250 [19:30<00:12, 4.02it/s] 99%|█████████▉| 4199/4250 [19:30<00:12, 4.13it/s] 99%|█████████▉| 4200/4250 [19:31<00:13, 3.67it/s] 99%|█████████▉| 4201/4250 [19:31<00:12, 3.90it/s] 99%|█████████▉| 4202/4250 [19:31<00:12, 3.90it/s] 99%|█████████▉| 4203/4250 [19:31<00:10, 4.40it/s] 99%|█████████▉| 4204/4250 [19:32<00:10, 4.51it/s] 99%|█████████▉| 4205/4250 [19:32<00:09, 4.89it/s] 99%|█████████▉| 4206/4250 [19:32<00:09, 4.85it/s] 99%|█████████▉| 4207/4250 [19:32<00:08, 4.94it/s] 99%|█████████▉| 4208/4250 [19:32<00:08, 4.72it/s] 99%|█████████▉| 4209/4250 [19:33<00:08, 5.05it/s] 99%|█████████▉| 4210/4250 [19:33<00:08, 4.48it/s] 99%|█████████▉| 4211/4250 [19:33<00:08, 4.77it/s] 99%|█████████▉| 4212/4250 [19:33<00:08, 4.73it/s] 99%|█████████▉| 4213/4250 [19:33<00:07, 4.75it/s] 99%|█████████▉| 4214/4250 [19:34<00:07, 5.00it/s] 99%|█████████▉| 4215/4250 [19:34<00:06, 5.07it/s] 99%|█████████▉| 4216/4250 [19:34<00:06, 5.28it/s] 99%|█████████▉| 4217/4250 [19:34<00:06, 5.49it/s] 99%|█████████▉| 4218/4250 [19:34<00:06, 5.11it/s] 99%|█████████▉| 4219/4250 [19:35<00:07, 3.98it/s] 99%|█████████▉| 4220/4250 [19:35<00:07, 4.26it/s] 99%|█████████▉| 4221/4250 [19:35<00:07, 4.08it/s] 99%|█████████▉| 4222/4250 [19:35<00:06, 4.11it/s] 99%|█████████▉| 4223/4250 [19:36<00:06, 3.89it/s] 99%|█████████▉| 4224/4250 [19:36<00:06, 4.26it/s] 99%|█████████▉| 4225/4250 [19:36<00:05, 4.47it/s] 99%|█████████▉| 4226/4250 [19:36<00:05, 4.45it/s] 99%|█████████▉| 4227/4250 [19:37<00:04, 4.71it/s] 99%|█████████▉| 4228/4250 [19:37<00:04, 4.91it/s] 100%|█████████▉| 4229/4250 [19:37<00:04, 5.09it/s] 100%|█████████▉| 4230/4250 [19:37<00:04, 4.90it/s] 100%|█████████▉| 4231/4250 [19:37<00:03, 5.06it/s] 100%|█████████▉| 4232/4250 [19:38<00:04, 4.36it/s] 100%|█████████▉| 4233/4250 [19:38<00:03, 4.37it/s] 100%|█████████▉| 4234/4250 [19:38<00:03, 4.31it/s] 100%|█████████▉| 4235/4250 [19:38<00:03, 4.22it/s] 100%|█████████▉| 4236/4250 [19:39<00:03, 4.25it/s] 100%|█████████▉| 4237/4250 [19:39<00:03, 3.77it/s] 100%|█████████▉| 4238/4250 [19:39<00:03, 3.95it/s] 100%|█████████▉| 4239/4250 [19:39<00:02, 4.14it/s] 100%|█████████▉| 4240/4250 [19:40<00:02, 4.61it/s] 100%|█████████▉| 4241/4250 [19:40<00:01, 4.92it/s] 100%|█████████▉| 4242/4250 [19:40<00:01, 5.10it/s] 100%|█████████▉| 4243/4250 [19:40<00:01, 5.37it/s] 100%|█████████▉| 4244/4250 [19:40<00:01, 4.77it/s] 100%|█████████▉| 4245/4250 [19:41<00:01, 4.41it/s] 100%|█████████▉| 4246/4250 [19:41<00:00, 4.83it/s] 100%|█████████▉| 4247/4250 [19:41<00:00, 4.98it/s] 100%|█████████▉| 4248/4250 [19:41<00:00, 4.68it/s] 100%|█████████▉| 4249/4250 [19:41<00:00, 4.85it/s] 100%|██████████| 4250/4250 [19:42<00:00, 4.86it/s][INFO|trainer.py:3478] 2024-08-30 20:45:30,892 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-4250 [INFO|configuration_utils.py:472] 2024-08-30 20:45:30,894 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-4250/config.json [INFO|modeling_utils.py:2690] 2024-08-30 20:45:32,240 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-4250/model.safetensors [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:45:32,241 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-4250/tokenizer_config.json [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:45:32,241 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-4250/special_tokens_map.json [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:45:34,549 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:45:34,550 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json [INFO|trainer.py:805] 2024-08-30 20:45:34,601 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: tokens, ner_tags, id. If tokens, ner_tags, id are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. [INFO|trainer.py:3788] 2024-08-30 20:45:34,604 >> ***** Running Evaluation ***** [INFO|trainer.py:3790] 2024-08-30 20:45:34,604 >> Num examples = 6810 [INFO|trainer.py:3793] 2024-08-30 20:45:34,604 >> Batch size = 8 {'eval_loss': 0.13398884236812592, 'eval_precision': 0.787630741246021, 'eval_recall': 0.8104819840898456, 'eval_f1': 0.7988929889298894, 'eval_accuracy': 0.9766158155629093, 'eval_runtime': 14.4437, 'eval_samples_per_second': 471.487, 'eval_steps_per_second': 58.988, 'epoch': 9.0} {'loss': 0.0038, 'grad_norm': 0.5636719465255737, 'learning_rate': 2.9411764705882355e-06, 'epoch': 9.4} 0%| | 0/852 [00:00> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-4250 [INFO|configuration_utils.py:472] 2024-08-30 20:45:49,490 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-4250/config.json [INFO|modeling_utils.py:2690] 2024-08-30 20:45:50,835 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-4250/model.safetensors [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:45:50,838 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-4250/tokenizer_config.json [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:45:50,839 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-4250/special_tokens_map.json [INFO|trainer.py:2383] 2024-08-30 20:45:52,645 >> Training completed. Do not forget to share your model on huggingface.co/models =) [INFO|trainer.py:2621] 2024-08-30 20:45:52,646 >> Loading best model from /content/dissertation/scripts/ner/output/checkpoint-3404 (score: 0.8015293708724366). 100%|██████████| 4250/4250 [20:03<00:00, 4.86it/s] 100%|██████████| 4250/4250 [20:03<00:00, 3.53it/s] [INFO|trainer.py:4239] 2024-08-30 20:45:52,840 >> Waiting for the current checkpoint push to be finished, this might take a couple of minutes. [INFO|trainer.py:3478] 2024-08-30 20:45:55,484 >> Saving model checkpoint to /content/dissertation/scripts/ner/output [INFO|configuration_utils.py:472] 2024-08-30 20:45:55,486 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json [INFO|modeling_utils.py:2690] 2024-08-30 20:45:56,829 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:45:56,830 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:45:56,830 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json [INFO|trainer.py:3478] 2024-08-30 20:45:56,879 >> Saving model checkpoint to /content/dissertation/scripts/ner/output [INFO|configuration_utils.py:472] 2024-08-30 20:45:56,881 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json [INFO|modeling_utils.py:2690] 2024-08-30 20:45:58,218 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:45:58,219 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:45:58,219 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json {'eval_loss': 0.13674204051494598, 'eval_precision': 0.7882031427920747, 'eval_recall': 0.8097800655124006, 'eval_f1': 0.7988459319099828, 'eval_accuracy': 0.9766776058330014, 'eval_runtime': 14.8828, 'eval_samples_per_second': 457.575, 'eval_steps_per_second': 57.247, 'epoch': 9.99} {'train_runtime': 1203.9865, 'train_samples_per_second': 226.157, 'train_steps_per_second': 3.53, 'train_loss': 0.02590363489880281, 'epoch': 9.99} events.out.tfevents.1725049548.6b97e535edda.20735.0: 0%| | 0.00/11.9k [00:00