2024-09-05 22:43:35.221687: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2024-09-05 22:43:35.239699: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:485] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
2024-09-05 22:43:35.261393: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:8454] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
2024-09-05 22:43:35.267947: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1452] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
2024-09-05 22:43:35.283519: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2024-09-05 22:43:36.568969: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
/usr/local/lib/python3.10/dist-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
  warnings.warn(
09/05/2024 22:43:38 - WARNING - __main__ -   Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False
09/05/2024 22:43:38 - INFO - __main__ -   Training/evaluation parameters TrainingArguments(
_n_gpu=1,
accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None, 'use_configured_state': False},
adafactor=False,
adam_beta1=0.9,
adam_beta2=0.999,
adam_epsilon=1e-08,
auto_find_batch_size=False,
batch_eval_metrics=False,
bf16=False,
bf16_full_eval=False,
data_seed=None,
dataloader_drop_last=False,
dataloader_num_workers=0,
dataloader_persistent_workers=False,
dataloader_pin_memory=True,
dataloader_prefetch_factor=None,
ddp_backend=None,
ddp_broadcast_buffers=None,
ddp_bucket_cap_mb=None,
ddp_find_unused_parameters=None,
ddp_timeout=1800,
debug=[],
deepspeed=None,
disable_tqdm=False,
dispatch_batches=None,
do_eval=True,
do_predict=True,
do_train=True,
eval_accumulation_steps=None,
eval_delay=0,
eval_do_concat_batches=True,
eval_on_start=False,
eval_steps=None,
eval_strategy=epoch,
eval_use_gather_object=False,
evaluation_strategy=epoch,
fp16=False,
fp16_backend=auto,
fp16_full_eval=False,
fp16_opt_level=O1,
fsdp=[],
fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False},
fsdp_min_num_params=0,
fsdp_transformer_layer_cls_to_wrap=None,
full_determinism=False,
gradient_accumulation_steps=2,
gradient_checkpointing=False,
gradient_checkpointing_kwargs=None,
greater_is_better=True,
group_by_length=False,
half_precision_backend=auto,
hub_always_push=False,
hub_model_id=None,
hub_private_repo=False,
hub_strategy=every_save,
hub_token=<HUB_TOKEN>,
ignore_data_skip=False,
include_inputs_for_metrics=False,
include_num_input_tokens_seen=False,
include_tokens_per_second=False,
jit_mode_eval=False,
label_names=None,
label_smoothing_factor=0.0,
learning_rate=5e-05,
length_column_name=length,
load_best_model_at_end=True,
local_rank=0,
log_level=passive,
log_level_replica=warning,
log_on_each_node=True,
logging_dir=/content/dissertation/scripts/ner/output/tb,
logging_first_step=False,
logging_nan_inf_filter=True,
logging_steps=500,
logging_strategy=steps,
lr_scheduler_kwargs={},
lr_scheduler_type=linear,
max_grad_norm=1.0,
max_steps=-1,
metric_for_best_model=f1,
mp_parameters=,
neftune_noise_alpha=None,
no_cuda=False,
num_train_epochs=10.0,
optim=adamw_torch,
optim_args=None,
optim_target_modules=None,
output_dir=/content/dissertation/scripts/ner/output,
overwrite_output_dir=True,
past_index=-1,
per_device_eval_batch_size=8,
per_device_train_batch_size=32,
prediction_loss_only=False,
push_to_hub=True,
push_to_hub_model_id=None,
push_to_hub_organization=None,
push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
ray_scope=last,
remove_unused_columns=True,
report_to=['tensorboard'],
restore_callback_states_from_checkpoint=False,
resume_from_checkpoint=None,
run_name=/content/dissertation/scripts/ner/output,
save_on_each_node=False,
save_only_model=False,
save_safetensors=True,
save_steps=500,
save_strategy=epoch,
save_total_limit=None,
seed=42,
skip_memory_metrics=True,
split_batches=None,
tf32=None,
torch_compile=False,
torch_compile_backend=None,
torch_compile_mode=None,
torch_empty_cache_steps=None,
torchdynamo=None,
tpu_metrics_debug=False,
tpu_num_cores=None,
use_cpu=False,
use_ipex=False,
use_legacy_prediction_loop=False,
use_mps_device=False,
warmup_ratio=0.0,
warmup_steps=0,
weight_decay=0.0,
)

Downloading builder script:   0%|          | 0.00/3.54k [00:00<?, ?B/s]
Downloading builder script: 100%|██████████| 3.54k/3.54k [00:00<00:00, 15.0kB/s]
Downloading builder script: 100%|██████████| 3.54k/3.54k [00:00<00:00, 15.0kB/s]

Downloading data:   0%|          | 0.00/34.4M [00:00<?, ?B/s]
Downloading data:  30%|███       | 10.5M/34.4M [00:00<00:02, 11.3MB/s]
Downloading data:  61%|██████    | 21.0M/34.4M [00:01<00:00, 16.4MB/s]
Downloading data:  91%|█████████▏| 31.5M/34.4M [00:01<00:00, 19.3MB/s]
Downloading data: 100%|██████████| 34.4M/34.4M [00:01<00:00, 18.4MB/s]
Downloading data: 100%|██████████| 34.4M/34.4M [00:02<00:00, 17.0MB/s]

Downloading data:   0%|          | 0.00/6.96M [00:00<?, ?B/s]
Downloading data: 100%|██████████| 6.96M/6.96M [00:00<00:00, 9.66MB/s]
Downloading data: 100%|██████████| 6.96M/6.96M [00:00<00:00, 9.57MB/s]

Downloading data:   0%|          | 0.00/12.3M [00:00<?, ?B/s]
Downloading data:  85%|████████▌ | 10.5M/12.3M [00:00<00:00, 11.7MB/s]
Downloading data: 100%|██████████| 12.3M/12.3M [00:00<00:00, 13.4MB/s]

Generating train split: 0 examples [00:00, ? examples/s]
Generating train split: 617 examples [00:00, 6150.71 examples/s]
Generating train split: 1541 examples [00:00, 6145.46 examples/s]
Generating train split: 2451 examples [00:00, 6093.89 examples/s]
Generating train split: 3376 examples [00:00, 6119.13 examples/s]
Generating train split: 4000 examples [00:00, 6093.30 examples/s]
Generating train split: 4690 examples [00:00, 6321.68 examples/s]
Generating train split: 5330 examples [00:00, 6258.81 examples/s]
Generating train split: 6000 examples [00:00, 6279.89 examples/s]
Generating train split: 6674 examples [00:01, 6409.66 examples/s]
Generating train split: 7612 examples [00:01, 6338.10 examples/s]
Generating train split: 8575 examples [00:01, 6365.45 examples/s]
Generating train split: 9503 examples [00:01, 6295.80 examples/s]
Generating train split: 10409 examples [00:01, 6208.67 examples/s]
Generating train split: 11361 examples [00:01, 6247.79 examples/s]
Generating train split: 12000 examples [00:01, 6182.52 examples/s]
Generating train split: 12682 examples [00:02, 6335.72 examples/s]
Generating train split: 13339 examples [00:02, 6290.80 examples/s]
Generating train split: 14000 examples [00:02, 6233.63 examples/s]
Generating train split: 14692 examples [00:02, 6419.43 examples/s]
Generating train split: 15660 examples [00:02, 6395.32 examples/s]
Generating train split: 16520 examples [00:02, 6165.05 examples/s]
Generating train split: 17461 examples [00:02, 6198.47 examples/s]
Generating train split: 18385 examples [00:02, 6182.35 examples/s]
Generating train split: 19320 examples [00:03, 6194.99 examples/s]
Generating train split: 19984 examples [00:03, 6295.54 examples/s]
Generating train split: 20900 examples [00:03, 6222.76 examples/s]
Generating train split: 21806 examples [00:03, 6156.05 examples/s]
Generating train split: 22762 examples [00:03, 6219.92 examples/s]
Generating train split: 23698 examples [00:03, 6217.78 examples/s]
Generating train split: 24669 examples [00:03, 6190.70 examples/s]
Generating train split: 25566 examples [00:04, 6121.92 examples/s]
Generating train split: 26202 examples [00:04, 6169.45 examples/s]
Generating train split: 26882 examples [00:04, 6318.89 examples/s]
Generating train split: 27828 examples [00:04, 6311.08 examples/s]
Generating train split: 28766 examples [00:04, 6286.67 examples/s]
Generating train split: 29714 examples [00:04, 6293.32 examples/s]
Generating train split: 30576 examples [00:05, 4233.38 examples/s]
Generating train split: 31125 examples [00:05, 4445.75 examples/s]
Generating train split: 31770 examples [00:05, 4835.24 examples/s]
Generating train split: 31947 examples [00:05, 5962.85 examples/s]

Generating validation split: 0 examples [00:00, ? examples/s]
Generating validation split: 707 examples [00:00, 7041.45 examples/s]
Generating validation split: 1689 examples [00:00, 6594.13 examples/s]
Generating validation split: 2361 examples [00:00, 6490.83 examples/s]
Generating validation split: 3352 examples [00:00, 6489.44 examples/s]
Generating validation split: 4341 examples [00:00, 6476.95 examples/s]
Generating validation split: 5000 examples [00:00, 6383.23 examples/s]
Generating validation split: 5708 examples [00:00, 6572.22 examples/s]
Generating validation split: 6705 examples [00:01, 6594.95 examples/s]
Generating validation split: 6810 examples [00:01, 6504.53 examples/s]

Generating test split: 0 examples [00:00, ? examples/s]
Generating test split: 791 examples [00:00, 7886.60 examples/s]
Generating test split: 1890 examples [00:00, 7488.43 examples/s]
Generating test split: 3000 examples [00:00, 7375.84 examples/s]
Generating test split: 3771 examples [00:00, 7475.50 examples/s]
Generating test split: 4873 examples [00:00, 7418.70 examples/s]
Generating test split: 5633 examples [00:00, 7466.67 examples/s]
Generating test split: 6422 examples [00:00, 7585.10 examples/s]
Generating test split: 7605 examples [00:01, 7698.04 examples/s]
Generating test split: 8422 examples [00:01, 7708.73 examples/s]
Generating test split: 9599 examples [00:01, 7751.10 examples/s]
Generating test split: 10759 examples [00:01, 7742.01 examples/s]
Generating test split: 11924 examples [00:01, 7749.14 examples/s]
Generating test split: 12983 examples [00:01, 7518.55 examples/s]
Generating test split: 14046 examples [00:01, 7381.89 examples/s]
Generating test split: 14614 examples [00:01, 7520.46 examples/s]
[INFO|configuration_utils.py:733] 2024-09-05 22:43:57,301 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/config.json
[INFO|configuration_utils.py:800] 2024-09-05 22:43:57,310 >> Model config RobertaConfig {
  "_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es",
  "architectures": [
    "RobertaForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "bos_token_id": 0,
  "classifier_dropout": null,
  "eos_token_id": 2,
  "finetuning_task": "ner",
  "gradient_checkpointing": false,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "id2label": {
    "0": "O",
    "1": "B-ENFERMEDAD",
    "2": "I-ENFERMEDAD"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "B-ENFERMEDAD": 1,
    "I-ENFERMEDAD": 2,
    "O": 0
  },
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 514,
  "model_type": "roberta",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "transformers_version": "4.44.2",
  "type_vocab_size": 1,
  "use_cache": true,
  "vocab_size": 50262
}

[INFO|configuration_utils.py:733] 2024-09-05 22:43:57,806 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/config.json
[INFO|configuration_utils.py:800] 2024-09-05 22:43:57,808 >> Model config RobertaConfig {
  "_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es",
  "architectures": [
    "RobertaForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "bos_token_id": 0,
  "classifier_dropout": null,
  "eos_token_id": 2,
  "gradient_checkpointing": false,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 514,
  "model_type": "roberta",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "transformers_version": "4.44.2",
  "type_vocab_size": 1,
  "use_cache": true,
  "vocab_size": 50262
}

[INFO|tokenization_utils_base.py:2269] 2024-09-05 22:44:00,154 >> loading file vocab.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/vocab.json
[INFO|tokenization_utils_base.py:2269] 2024-09-05 22:44:00,154 >> loading file merges.txt from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/merges.txt
[INFO|tokenization_utils_base.py:2269] 2024-09-05 22:44:00,154 >> loading file tokenizer.json from cache at None
[INFO|tokenization_utils_base.py:2269] 2024-09-05 22:44:00,154 >> loading file added_tokens.json from cache at None
[INFO|tokenization_utils_base.py:2269] 2024-09-05 22:44:00,154 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/special_tokens_map.json
[INFO|tokenization_utils_base.py:2269] 2024-09-05 22:44:00,154 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/tokenizer_config.json
[INFO|configuration_utils.py:733] 2024-09-05 22:44:00,155 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/config.json
[INFO|configuration_utils.py:800] 2024-09-05 22:44:00,156 >> Model config RobertaConfig {
  "_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es",
  "architectures": [
    "RobertaForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "bos_token_id": 0,
  "classifier_dropout": null,
  "eos_token_id": 2,
  "gradient_checkpointing": false,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 514,
  "model_type": "roberta",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "transformers_version": "4.44.2",
  "type_vocab_size": 1,
  "use_cache": true,
  "vocab_size": 50262
}

/usr/local/lib/python3.10/dist-packages/transformers/tokenization_utils_base.py:1601: FutureWarning: `clean_up_tokenization_spaces` was not set. It will be set to `True` by default. This behavior will be depracted in transformers v4.45, and will be then set to `False` by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884
  warnings.warn(
[INFO|configuration_utils.py:733] 2024-09-05 22:44:00,243 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/config.json
[INFO|configuration_utils.py:800] 2024-09-05 22:44:00,244 >> Model config RobertaConfig {
  "_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es",
  "architectures": [
    "RobertaForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "bos_token_id": 0,
  "classifier_dropout": null,
  "eos_token_id": 2,
  "gradient_checkpointing": false,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 514,
  "model_type": "roberta",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "transformers_version": "4.44.2",
  "type_vocab_size": 1,
  "use_cache": true,
  "vocab_size": 50262
}

[INFO|modeling_utils.py:3678] 2024-09-05 22:44:31,232 >> loading weights file pytorch_model.bin from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/pytorch_model.bin
[INFO|modeling_utils.py:4497] 2024-09-05 22:44:31,384 >> Some weights of the model checkpoint at PlanTL-GOB-ES/bsc-bio-ehr-es were not used when initializing RobertaForTokenClassification: ['lm_head.bias', 'lm_head.decoder.bias', 'lm_head.decoder.weight', 'lm_head.dense.bias', 'lm_head.dense.weight', 'lm_head.layer_norm.bias', 'lm_head.layer_norm.weight']
- This IS expected if you are initializing RobertaForTokenClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing RobertaForTokenClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
[WARNING|modeling_utils.py:4509] 2024-09-05 22:44:31,384 >> Some weights of RobertaForTokenClassification were not initialized from the model checkpoint at PlanTL-GOB-ES/bsc-bio-ehr-es and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.

Map:   0%|          | 0/31947 [00:00<?, ? examples/s]
Map:   3%|▎         | 1000/31947 [00:00<00:03, 9158.31 examples/s]
Map:   9%|▉         | 3000/31947 [00:00<00:02, 10209.38 examples/s]
Map:  16%|█▌        | 5000/31947 [00:00<00:02, 10615.27 examples/s]
Map:  22%|██▏       | 7000/31947 [00:00<00:02, 10870.55 examples/s]
Map:  28%|██▊       | 9000/31947 [00:00<00:02, 11076.46 examples/s]
Map:  34%|███▍      | 11000/31947 [00:01<00:01, 11059.02 examples/s]
Map:  41%|████      | 13000/31947 [00:01<00:01, 11018.18 examples/s]
Map:  47%|████▋     | 15000/31947 [00:01<00:01, 11231.44 examples/s]
Map:  53%|█████▎    | 17000/31947 [00:01<00:01, 11046.82 examples/s]
Map:  59%|█████▉    | 19000/31947 [00:01<00:01, 11163.17 examples/s]
Map:  66%|██████▌   | 21000/31947 [00:01<00:00, 11103.32 examples/s]
Map:  72%|███████▏  | 23000/31947 [00:02<00:00, 11150.08 examples/s]
Map:  78%|███████▊  | 25000/31947 [00:02<00:00, 11126.48 examples/s]
Map:  85%|████████▍ | 27000/31947 [00:02<00:00, 11156.06 examples/s]
Map:  91%|█████████ | 29000/31947 [00:02<00:00, 11171.85 examples/s]
Map:  97%|█████████▋| 31000/31947 [00:02<00:00, 11147.45 examples/s]
Map: 100%|██████████| 31947/31947 [00:02<00:00, 10952.44 examples/s]

Map:   0%|          | 0/6810 [00:00<?, ? examples/s]
Map:  29%|██▉       | 2000/6810 [00:00<00:00, 11218.17 examples/s]
Map:  59%|█████▊    | 4000/6810 [00:00<00:00, 11344.49 examples/s]
Map:  88%|████████▊ | 6000/6810 [00:00<00:00, 7083.36 examples/s] 
Map: 100%|██████████| 6810/6810 [00:00<00:00, 8149.18 examples/s]

Map:   0%|          | 0/14614 [00:00<?, ? examples/s]
Map:  14%|█▎        | 2000/14614 [00:00<00:00, 13116.63 examples/s]
Map:  27%|██▋       | 4000/14614 [00:00<00:00, 13065.88 examples/s]
Map:  41%|████      | 6000/14614 [00:00<00:00, 13460.26 examples/s]
Map:  55%|█████▍    | 8000/14614 [00:00<00:00, 13794.05 examples/s]
Map:  68%|██████▊   | 10000/14614 [00:00<00:00, 13651.45 examples/s]
Map:  82%|████████▏ | 12000/14614 [00:00<00:00, 13688.96 examples/s]
Map:  96%|█████████▌| 14000/14614 [00:01<00:00, 13265.32 examples/s]
Map: 100%|██████████| 14614/14614 [00:01<00:00, 13315.87 examples/s]
/content/dissertation/scripts/ner/run_ner_train.py:397: FutureWarning: load_metric is deprecated and will be removed in the next major version of datasets. Use 'evaluate.load' instead, from the new library 🤗 Evaluate: https://huggingface.co/docs/evaluate
  metric = load_metric("seqeval", trust_remote_code=True)

Downloading builder script:   0%|          | 0.00/2.47k [00:00<?, ?B/s]
Downloading builder script: 6.33kB [00:00, 10.1MB/s]                   
[INFO|trainer.py:811] 2024-09-05 22:44:38,444 >> The following columns in the training set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: id, ner_tags, tokens. If id, ner_tags, tokens are not expected by `RobertaForTokenClassification.forward`,  you can safely ignore this message.
[INFO|trainer.py:2134] 2024-09-05 22:44:39,141 >> ***** Running training *****
[INFO|trainer.py:2135] 2024-09-05 22:44:39,141 >>   Num examples = 31,947
[INFO|trainer.py:2136] 2024-09-05 22:44:39,141 >>   Num Epochs = 10
[INFO|trainer.py:2137] 2024-09-05 22:44:39,141 >>   Instantaneous batch size per device = 32
[INFO|trainer.py:2140] 2024-09-05 22:44:39,141 >>   Total train batch size (w. parallel, distributed & accumulation) = 64
[INFO|trainer.py:2141] 2024-09-05 22:44:39,141 >>   Gradient Accumulation steps = 2
[INFO|trainer.py:2142] 2024-09-05 22:44:39,141 >>   Total optimization steps = 4,990
[INFO|trainer.py:2143] 2024-09-05 22:44:39,142 >>   Number of trainable parameters = 124,055,043

  0%|          | 0/4990 [00:00<?, ?it/s]
  0%|          | 1/4990 [00:01<2:30:16,  1.81s/it]
  0%|          | 2/4990 [00:02<1:13:06,  1.14it/s]
  0%|          | 3/4990 [00:02<54:01,  1.54it/s]  
  0%|          | 4/4990 [00:02<39:05,  2.13it/s]
  0%|          | 5/4990 [00:02<33:43,  2.46it/s]
  0%|          | 6/4990 [00:03<28:27,  2.92it/s]
  0%|          | 7/4990 [00:03<25:31,  3.25it/s]
  0%|          | 8/4990 [00:03<23:09,  3.58it/s]
  0%|          | 9/4990 [00:03<21:53,  3.79it/s]
  0%|          | 10/4990 [00:04<23:55,  3.47it/s]
  0%|          | 11/4990 [00:04<21:33,  3.85it/s]
  0%|          | 12/4990 [00:04<19:54,  4.17it/s]
  0%|          | 13/4990 [00:04<19:58,  4.15it/s]
  0%|          | 14/4990 [00:04<18:02,  4.60it/s]
  0%|          | 15/4990 [00:05<17:14,  4.81it/s]
  0%|          | 16/4990 [00:05<20:42,  4.00it/s]
  0%|          | 17/4990 [00:05<19:20,  4.28it/s]
  0%|          | 18/4990 [00:05<18:15,  4.54it/s]
  0%|          | 19/4990 [00:06<17:55,  4.62it/s]
  0%|          | 20/4990 [00:06<18:29,  4.48it/s]
  0%|          | 21/4990 [00:06<21:02,  3.94it/s]
  0%|          | 22/4990 [00:06<21:04,  3.93it/s]
  0%|          | 23/4990 [00:07<20:40,  4.00it/s]
  0%|          | 24/4990 [00:07<19:12,  4.31it/s]
  1%|          | 25/4990 [00:07<20:37,  4.01it/s]
  1%|          | 26/4990 [00:07<20:47,  3.98it/s]
  1%|          | 27/4990 [00:08<19:34,  4.23it/s]
  1%|          | 28/4990 [00:08<20:22,  4.06it/s]
  1%|          | 29/4990 [00:08<19:11,  4.31it/s]
  1%|          | 30/4990 [00:08<19:31,  4.23it/s]
  1%|          | 31/4990 [00:08<17:52,  4.63it/s]
  1%|          | 32/4990 [00:09<19:00,  4.35it/s]
  1%|          | 33/4990 [00:09<18:14,  4.53it/s]
  1%|          | 34/4990 [00:09<21:03,  3.92it/s]
  1%|          | 35/4990 [00:09<19:29,  4.24it/s]
  1%|          | 36/4990 [00:10<19:19,  4.27it/s]
  1%|          | 37/4990 [00:10<20:06,  4.10it/s]
  1%|          | 38/4990 [00:10<19:05,  4.32it/s]
  1%|          | 39/4990 [00:10<19:34,  4.21it/s]
  1%|          | 40/4990 [00:11<18:13,  4.53it/s]
  1%|          | 41/4990 [00:11<19:07,  4.31it/s]
  1%|          | 42/4990 [00:11<18:29,  4.46it/s]
  1%|          | 43/4990 [00:11<18:05,  4.56it/s]
  1%|          | 44/4990 [00:11<16:50,  4.89it/s]
  1%|          | 45/4990 [00:12<20:00,  4.12it/s]
  1%|          | 46/4990 [00:12<27:12,  3.03it/s]
  1%|          | 47/4990 [00:12<23:50,  3.45it/s]
  1%|          | 48/4990 [00:13<33:35,  2.45it/s]
  1%|          | 49/4990 [00:13<28:38,  2.88it/s]
  1%|          | 50/4990 [00:14<26:25,  3.12it/s]
  1%|          | 51/4990 [00:14<23:04,  3.57it/s]
  1%|          | 52/4990 [00:14<21:37,  3.81it/s]
  1%|          | 53/4990 [00:14<19:59,  4.12it/s]
  1%|          | 54/4990 [00:14<19:15,  4.27it/s]
  1%|          | 55/4990 [00:15<18:00,  4.57it/s]
  1%|          | 56/4990 [00:15<17:12,  4.78it/s]
  1%|          | 57/4990 [00:15<18:08,  4.53it/s]
  1%|          | 58/4990 [00:15<17:47,  4.62it/s]
  1%|          | 59/4990 [00:15<17:26,  4.71it/s]
  1%|          | 60/4990 [00:16<16:18,  5.04it/s]
  1%|          | 61/4990 [00:16<15:46,  5.21it/s]
  1%|          | 62/4990 [00:16<15:50,  5.18it/s]
  1%|▏         | 63/4990 [00:16<18:57,  4.33it/s]
  1%|▏         | 64/4990 [00:17<17:59,  4.56it/s]
  1%|▏         | 65/4990 [00:17<19:15,  4.26it/s]
  1%|▏         | 66/4990 [00:17<20:47,  3.95it/s]
  1%|▏         | 67/4990 [00:17<19:35,  4.19it/s]
  1%|▏         | 68/4990 [00:18<24:46,  3.31it/s]
  1%|▏         | 69/4990 [00:18<22:55,  3.58it/s]
  1%|▏         | 70/4990 [00:18<20:57,  3.91it/s]
  1%|▏         | 71/4990 [00:18<22:39,  3.62it/s]
  1%|▏         | 72/4990 [00:19<20:35,  3.98it/s]
  1%|▏         | 73/4990 [00:19<20:37,  3.97it/s]
  1%|▏         | 74/4990 [00:19<27:39,  2.96it/s]
  2%|▏         | 75/4990 [00:20<24:16,  3.37it/s]
  2%|▏         | 76/4990 [00:20<22:19,  3.67it/s]
  2%|▏         | 77/4990 [00:20<20:46,  3.94it/s]
  2%|▏         | 78/4990 [00:20<20:46,  3.94it/s]
  2%|▏         | 79/4990 [00:21<18:28,  4.43it/s]
  2%|▏         | 80/4990 [00:21<17:35,  4.65it/s]
  2%|▏         | 81/4990 [00:21<17:10,  4.77it/s]
  2%|▏         | 82/4990 [00:21<16:25,  4.98it/s]
  2%|▏         | 83/4990 [00:21<16:03,  5.09it/s]
  2%|▏         | 84/4990 [00:21<15:10,  5.39it/s]
  2%|▏         | 85/4990 [00:22<16:10,  5.06it/s]
  2%|▏         | 86/4990 [00:22<16:35,  4.93it/s]
  2%|▏         | 87/4990 [00:22<16:18,  5.01it/s]
  2%|▏         | 88/4990 [00:22<17:51,  4.57it/s]
  2%|▏         | 89/4990 [00:22<16:46,  4.87it/s]
  2%|▏         | 90/4990 [00:23<20:39,  3.95it/s]
  2%|▏         | 91/4990 [00:23<19:12,  4.25it/s]
  2%|▏         | 92/4990 [00:23<17:14,  4.73it/s]
  2%|▏         | 93/4990 [00:23<16:22,  4.99it/s]
  2%|▏         | 94/4990 [00:24<16:04,  5.07it/s]
  2%|▏         | 95/4990 [00:24<14:52,  5.49it/s]
  2%|▏         | 96/4990 [00:24<16:39,  4.90it/s]
  2%|▏         | 97/4990 [00:24<16:26,  4.96it/s]
  2%|▏         | 98/4990 [00:24<16:43,  4.87it/s]
  2%|▏         | 99/4990 [00:25<18:01,  4.52it/s]
  2%|▏         | 100/4990 [00:25<18:41,  4.36it/s]
  2%|▏         | 101/4990 [00:25<17:23,  4.69it/s]
  2%|▏         | 102/4990 [00:25<18:07,  4.50it/s]
  2%|▏         | 103/4990 [00:26<17:30,  4.65it/s]
  2%|▏         | 104/4990 [00:26<16:38,  4.89it/s]
  2%|▏         | 105/4990 [00:26<18:38,  4.37it/s]
  2%|▏         | 106/4990 [00:26<19:25,  4.19it/s]
  2%|▏         | 107/4990 [00:26<18:51,  4.31it/s]
  2%|▏         | 108/4990 [00:27<19:44,  4.12it/s]
  2%|▏         | 109/4990 [00:27<19:06,  4.26it/s]
  2%|▏         | 110/4990 [00:27<21:28,  3.79it/s]
  2%|▏         | 111/4990 [00:28<24:21,  3.34it/s]
  2%|▏         | 112/4990 [00:28<24:27,  3.32it/s]
  2%|▏         | 113/4990 [00:28<23:45,  3.42it/s]
  2%|▏         | 114/4990 [00:28<21:22,  3.80it/s]
  2%|▏         | 115/4990 [00:29<19:27,  4.18it/s]
  2%|▏         | 116/4990 [00:29<19:48,  4.10it/s]
  2%|▏         | 117/4990 [00:29<19:08,  4.24it/s]
  2%|▏         | 118/4990 [00:29<18:39,  4.35it/s]
  2%|▏         | 119/4990 [00:30<18:23,  4.42it/s]
  2%|▏         | 120/4990 [00:30<18:14,  4.45it/s]
  2%|▏         | 121/4990 [00:30<18:55,  4.29it/s]
  2%|▏         | 122/4990 [00:30<17:40,  4.59it/s]
  2%|▏         | 123/4990 [00:30<17:21,  4.67it/s]
  2%|▏         | 124/4990 [00:31<17:01,  4.76it/s]
  3%|▎         | 125/4990 [00:31<16:52,  4.80it/s]
  3%|▎         | 126/4990 [00:31<17:10,  4.72it/s]
  3%|▎         | 127/4990 [00:31<16:50,  4.81it/s]
  3%|▎         | 128/4990 [00:31<16:45,  4.83it/s]
  3%|▎         | 129/4990 [00:32<21:17,  3.81it/s]
  3%|▎         | 130/4990 [00:32<20:35,  3.94it/s]
  3%|▎         | 131/4990 [00:32<18:22,  4.41it/s]
  3%|▎         | 132/4990 [00:33<20:55,  3.87it/s]
  3%|▎         | 133/4990 [00:33<20:29,  3.95it/s]
  3%|▎         | 134/4990 [00:33<21:05,  3.84it/s]
  3%|▎         | 135/4990 [00:33<18:52,  4.29it/s]
  3%|▎         | 136/4990 [00:33<18:11,  4.45it/s]
  3%|▎         | 137/4990 [00:34<20:37,  3.92it/s]
  3%|▎         | 138/4990 [00:34<19:47,  4.09it/s]
  3%|▎         | 139/4990 [00:34<20:04,  4.03it/s]
  3%|▎         | 140/4990 [00:34<18:36,  4.35it/s]
  3%|▎         | 141/4990 [00:35<17:43,  4.56it/s]
  3%|▎         | 142/4990 [00:35<19:12,  4.21it/s]
  3%|▎         | 143/4990 [00:35<19:47,  4.08it/s]
  3%|▎         | 144/4990 [00:35<19:21,  4.17it/s]
  3%|▎         | 145/4990 [00:36<19:02,  4.24it/s]
  3%|▎         | 146/4990 [00:36<18:06,  4.46it/s]
  3%|▎         | 147/4990 [00:36<17:49,  4.53it/s]
  3%|▎         | 148/4990 [00:36<20:00,  4.03it/s]
  3%|▎         | 149/4990 [00:37<18:22,  4.39it/s]
  3%|▎         | 150/4990 [00:37<17:22,  4.64it/s]
  3%|▎         | 151/4990 [00:37<18:27,  4.37it/s]
  3%|▎         | 152/4990 [00:37<17:12,  4.69it/s]
  3%|▎         | 153/4990 [00:37<16:54,  4.77it/s]
  3%|▎         | 154/4990 [00:38<18:03,  4.46it/s]
  3%|▎         | 155/4990 [00:38<19:43,  4.09it/s]
  3%|▎         | 156/4990 [00:38<22:01,  3.66it/s]
  3%|▎         | 157/4990 [00:38<20:19,  3.96it/s]
  3%|▎         | 158/4990 [00:39<19:10,  4.20it/s]
  3%|▎         | 159/4990 [00:39<18:20,  4.39it/s]
  3%|▎         | 160/4990 [00:39<18:39,  4.32it/s]
  3%|▎         | 161/4990 [00:39<19:23,  4.15it/s]
  3%|▎         | 162/4990 [00:40<17:41,  4.55it/s]
  3%|▎         | 163/4990 [00:40<18:25,  4.37it/s]
  3%|▎         | 164/4990 [00:40<21:51,  3.68it/s]
  3%|▎         | 165/4990 [00:40<19:57,  4.03it/s]
  3%|▎         | 166/4990 [00:41<19:01,  4.23it/s]
  3%|▎         | 167/4990 [00:41<17:33,  4.58it/s]
  3%|▎         | 168/4990 [00:41<17:10,  4.68it/s]
  3%|▎         | 169/4990 [00:41<17:50,  4.50it/s]
  3%|▎         | 170/4990 [00:41<18:17,  4.39it/s]
  3%|▎         | 171/4990 [00:42<24:41,  3.25it/s]
  3%|▎         | 172/4990 [00:42<23:38,  3.40it/s]
  3%|▎         | 173/4990 [00:42<20:14,  3.97it/s]
  3%|▎         | 174/4990 [00:43<18:57,  4.23it/s]
  4%|▎         | 175/4990 [00:43<20:35,  3.90it/s]
  4%|▎         | 176/4990 [00:43<19:26,  4.13it/s]
  4%|▎         | 177/4990 [00:43<18:45,  4.28it/s]
  4%|▎         | 178/4990 [00:44<20:19,  3.95it/s]
  4%|▎         | 179/4990 [00:44<21:27,  3.74it/s]
  4%|▎         | 180/4990 [00:44<19:52,  4.03it/s]
  4%|▎         | 181/4990 [00:44<22:13,  3.61it/s]
  4%|▎         | 182/4990 [00:45<19:45,  4.06it/s]
  4%|▎         | 183/4990 [00:45<20:41,  3.87it/s]
  4%|▎         | 184/4990 [00:45<19:34,  4.09it/s]
  4%|▎         | 185/4990 [00:45<19:21,  4.14it/s]
  4%|▎         | 186/4990 [00:45<17:20,  4.62it/s]
  4%|▎         | 187/4990 [00:46<17:39,  4.53it/s]
  4%|▍         | 188/4990 [00:46<17:10,  4.66it/s]
  4%|▍         | 189/4990 [00:46<18:32,  4.32it/s]
  4%|▍         | 190/4990 [00:46<19:55,  4.01it/s]
  4%|▍         | 191/4990 [00:47<23:30,  3.40it/s]
  4%|▍         | 192/4990 [00:47<23:09,  3.45it/s]
  4%|▍         | 193/4990 [00:47<21:29,  3.72it/s]
  4%|▍         | 194/4990 [00:48<22:02,  3.63it/s]
  4%|▍         | 195/4990 [00:48<23:06,  3.46it/s]
  4%|▍         | 196/4990 [00:48<21:32,  3.71it/s]
  4%|▍         | 197/4990 [00:48<21:32,  3.71it/s]
  4%|▍         | 198/4990 [00:49<20:39,  3.87it/s]
  4%|▍         | 199/4990 [00:49<20:48,  3.84it/s]
  4%|▍         | 200/4990 [00:49<19:16,  4.14it/s]
  4%|▍         | 201/4990 [00:49<19:27,  4.10it/s]
  4%|▍         | 202/4990 [00:50<19:00,  4.20it/s]
  4%|▍         | 203/4990 [00:50<18:21,  4.35it/s]
  4%|▍         | 204/4990 [00:50<18:16,  4.36it/s]
  4%|▍         | 205/4990 [00:50<17:52,  4.46it/s]
  4%|▍         | 206/4990 [00:50<17:21,  4.59it/s]
  4%|▍         | 207/4990 [00:51<16:07,  4.94it/s]
  4%|▍         | 208/4990 [00:51<16:10,  4.93it/s]
  4%|▍         | 209/4990 [00:51<16:33,  4.81it/s]
  4%|▍         | 210/4990 [00:51<15:59,  4.98it/s]
  4%|▍         | 211/4990 [00:52<25:45,  3.09it/s]
  4%|▍         | 212/4990 [00:52<23:35,  3.38it/s]
  4%|▍         | 213/4990 [00:52<21:35,  3.69it/s]
  4%|▍         | 214/4990 [00:53<23:16,  3.42it/s]
  4%|▍         | 215/4990 [00:53<20:58,  3.79it/s]
  4%|▍         | 216/4990 [00:53<18:47,  4.24it/s]
  4%|▍         | 217/4990 [00:53<17:22,  4.58it/s]
  4%|▍         | 218/4990 [00:53<18:10,  4.37it/s]
  4%|▍         | 219/4990 [00:54<17:11,  4.63it/s]
  4%|▍         | 220/4990 [00:54<17:52,  4.45it/s]
  4%|▍         | 221/4990 [00:54<17:02,  4.66it/s]
  4%|▍         | 222/4990 [00:54<16:22,  4.85it/s]
  4%|▍         | 223/4990 [00:54<17:37,  4.51it/s]
  4%|▍         | 224/4990 [00:55<17:47,  4.46it/s]
  5%|▍         | 225/4990 [00:55<16:55,  4.69it/s]
  5%|▍         | 226/4990 [00:55<17:00,  4.67it/s]
  5%|▍         | 227/4990 [00:55<18:54,  4.20it/s]
  5%|▍         | 228/4990 [00:56<18:35,  4.27it/s]
  5%|▍         | 229/4990 [00:56<17:09,  4.63it/s]
  5%|▍         | 230/4990 [00:56<15:59,  4.96it/s]
  5%|▍         | 231/4990 [00:56<16:38,  4.77it/s]
  5%|▍         | 232/4990 [00:56<18:05,  4.38it/s]
  5%|▍         | 233/4990 [00:57<19:07,  4.15it/s]
  5%|▍         | 234/4990 [00:57<18:25,  4.30it/s]
  5%|▍         | 235/4990 [00:57<17:20,  4.57it/s]
  5%|▍         | 236/4990 [00:57<16:46,  4.72it/s]
  5%|▍         | 237/4990 [00:58<19:32,  4.06it/s]
  5%|▍         | 238/4990 [00:58<17:53,  4.43it/s]
  5%|▍         | 239/4990 [00:58<19:00,  4.17it/s]
  5%|▍         | 240/4990 [00:58<19:40,  4.02it/s]
  5%|▍         | 241/4990 [00:59<20:14,  3.91it/s]
  5%|▍         | 242/4990 [00:59<20:07,  3.93it/s]
  5%|▍         | 243/4990 [00:59<19:07,  4.14it/s]
  5%|▍         | 244/4990 [00:59<18:07,  4.37it/s]
  5%|▍         | 245/4990 [01:00<17:58,  4.40it/s]
  5%|▍         | 246/4990 [01:00<17:06,  4.62it/s]
  5%|▍         | 247/4990 [01:00<20:01,  3.95it/s]
  5%|▍         | 248/4990 [01:00<19:19,  4.09it/s]
  5%|▍         | 249/4990 [01:00<17:50,  4.43it/s]
  5%|▌         | 250/4990 [01:01<16:28,  4.80it/s]
  5%|▌         | 251/4990 [01:01<18:48,  4.20it/s]
  5%|▌         | 252/4990 [01:01<18:18,  4.31it/s]
  5%|▌         | 253/4990 [01:01<17:14,  4.58it/s]
  5%|▌         | 254/4990 [01:02<17:34,  4.49it/s]
  5%|▌         | 255/4990 [01:02<17:32,  4.50it/s]
  5%|▌         | 256/4990 [01:02<17:43,  4.45it/s]
  5%|▌         | 257/4990 [01:02<18:13,  4.33it/s]
  5%|▌         | 258/4990 [01:03<18:56,  4.16it/s]
  5%|▌         | 259/4990 [01:03<19:21,  4.07it/s]
  5%|▌         | 260/4990 [01:03<18:16,  4.32it/s]
  5%|▌         | 261/4990 [01:03<18:59,  4.15it/s]
  5%|▌         | 262/4990 [01:04<18:57,  4.16it/s]
  5%|▌         | 263/4990 [01:04<16:55,  4.66it/s]
  5%|▌         | 264/4990 [01:04<18:45,  4.20it/s]
  5%|▌         | 265/4990 [01:04<17:56,  4.39it/s]
  5%|▌         | 266/4990 [01:04<19:42,  3.99it/s]
  5%|▌         | 267/4990 [01:05<18:13,  4.32it/s]
  5%|▌         | 268/4990 [01:05<18:17,  4.30it/s]
  5%|▌         | 269/4990 [01:05<17:08,  4.59it/s]
  5%|▌         | 270/4990 [01:05<19:52,  3.96it/s]
  5%|▌         | 271/4990 [01:06<18:46,  4.19it/s]
  5%|▌         | 272/4990 [01:06<17:29,  4.50it/s]
  5%|▌         | 273/4990 [01:06<15:47,  4.98it/s]
  5%|▌         | 274/4990 [01:06<16:52,  4.66it/s]
  6%|▌         | 275/4990 [01:06<16:38,  4.72it/s]
  6%|▌         | 276/4990 [01:07<16:59,  4.63it/s]
  6%|▌         | 277/4990 [01:07<16:58,  4.63it/s]
  6%|▌         | 278/4990 [01:07<19:29,  4.03it/s]
  6%|▌         | 279/4990 [01:07<18:14,  4.31it/s]
  6%|▌         | 280/4990 [01:08<17:08,  4.58it/s]
  6%|▌         | 281/4990 [01:08<18:38,  4.21it/s]
  6%|▌         | 282/4990 [01:08<18:20,  4.28it/s]
  6%|▌         | 283/4990 [01:08<18:05,  4.34it/s]
  6%|▌         | 284/4990 [01:09<26:46,  2.93it/s]
  6%|▌         | 285/4990 [01:09<23:57,  3.27it/s]
  6%|▌         | 286/4990 [01:09<24:08,  3.25it/s]
  6%|▌         | 287/4990 [01:10<21:24,  3.66it/s]
  6%|▌         | 288/4990 [01:10<21:50,  3.59it/s]
  6%|▌         | 289/4990 [01:10<24:11,  3.24it/s]
  6%|▌         | 290/4990 [01:10<21:35,  3.63it/s]
  6%|▌         | 291/4990 [01:11<19:00,  4.12it/s]
  6%|▌         | 292/4990 [01:11<16:52,  4.64it/s]
  6%|▌         | 293/4990 [01:11<20:28,  3.82it/s]
  6%|▌         | 294/4990 [01:11<19:33,  4.00it/s]
  6%|▌         | 295/4990 [01:12<18:02,  4.34it/s]
  6%|▌         | 296/4990 [01:12<21:30,  3.64it/s]
  6%|▌         | 297/4990 [01:12<19:57,  3.92it/s]
  6%|▌         | 298/4990 [01:12<18:42,  4.18it/s]
  6%|▌         | 299/4990 [01:13<17:38,  4.43it/s]
  6%|▌         | 300/4990 [01:13<19:28,  4.01it/s]
  6%|▌         | 301/4990 [01:13<17:54,  4.36it/s]
  6%|▌         | 302/4990 [01:13<20:13,  3.86it/s]
  6%|▌         | 303/4990 [01:14<19:54,  3.92it/s]
  6%|▌         | 304/4990 [01:14<17:57,  4.35it/s]
  6%|▌         | 305/4990 [01:14<16:21,  4.77it/s]
  6%|▌         | 306/4990 [01:14<16:41,  4.68it/s]
  6%|▌         | 307/4990 [01:15<20:42,  3.77it/s]
  6%|▌         | 308/4990 [01:15<19:57,  3.91it/s]
  6%|▌         | 309/4990 [01:15<19:21,  4.03it/s]
  6%|▌         | 310/4990 [01:15<20:37,  3.78it/s]
  6%|▌         | 311/4990 [01:16<19:05,  4.08it/s]
  6%|▋         | 312/4990 [01:16<18:20,  4.25it/s]
  6%|▋         | 313/4990 [01:16<18:18,  4.26it/s]
  6%|▋         | 314/4990 [01:16<21:30,  3.62it/s]
  6%|▋         | 315/4990 [01:17<24:15,  3.21it/s]
  6%|▋         | 316/4990 [01:17<21:34,  3.61it/s]
  6%|▋         | 317/4990 [01:17<19:36,  3.97it/s]
  6%|▋         | 318/4990 [01:17<18:45,  4.15it/s]
  6%|▋         | 319/4990 [01:18<20:36,  3.78it/s]
  6%|▋         | 320/4990 [01:18<19:26,  4.00it/s]
  6%|▋         | 321/4990 [01:18<25:04,  3.10it/s]
  6%|▋         | 322/4990 [01:19<24:58,  3.11it/s]
  6%|▋         | 323/4990 [01:19<22:10,  3.51it/s]
  6%|▋         | 324/4990 [01:19<19:27,  4.00it/s]
  7%|▋         | 325/4990 [01:19<17:53,  4.35it/s]
  7%|▋         | 326/4990 [01:19<17:38,  4.41it/s]
  7%|▋         | 327/4990 [01:20<17:05,  4.55it/s]
  7%|▋         | 328/4990 [01:20<17:18,  4.49it/s]
  7%|▋         | 329/4990 [01:20<16:25,  4.73it/s]
  7%|▋         | 330/4990 [01:20<16:40,  4.66it/s]
  7%|▋         | 331/4990 [01:21<16:54,  4.59it/s]
  7%|▋         | 332/4990 [01:21<17:27,  4.45it/s]
  7%|▋         | 333/4990 [01:21<16:18,  4.76it/s]
  7%|▋         | 334/4990 [01:21<17:52,  4.34it/s]
  7%|▋         | 335/4990 [01:21<17:09,  4.52it/s]
  7%|▋         | 336/4990 [01:22<17:30,  4.43it/s]
  7%|▋         | 337/4990 [01:22<16:29,  4.70it/s]
  7%|▋         | 338/4990 [01:22<17:02,  4.55it/s]
  7%|▋         | 339/4990 [01:22<15:53,  4.88it/s]
  7%|▋         | 340/4990 [01:23<17:00,  4.56it/s]
  7%|▋         | 341/4990 [01:23<17:57,  4.32it/s]
  7%|▋         | 342/4990 [01:23<16:47,  4.61it/s]
  7%|▋         | 343/4990 [01:23<16:39,  4.65it/s]
  7%|▋         | 344/4990 [01:23<18:49,  4.11it/s]
  7%|▋         | 345/4990 [01:24<18:24,  4.21it/s]
  7%|▋         | 346/4990 [01:24<18:25,  4.20it/s]
  7%|▋         | 347/4990 [01:24<17:49,  4.34it/s]
  7%|▋         | 348/4990 [01:25<21:54,  3.53it/s]
  7%|▋         | 349/4990 [01:25<19:46,  3.91it/s]
  7%|▋         | 350/4990 [01:25<18:34,  4.16it/s]
  7%|▋         | 351/4990 [01:25<19:12,  4.02it/s]
  7%|▋         | 352/4990 [01:25<18:44,  4.13it/s]
  7%|▋         | 353/4990 [01:26<18:56,  4.08it/s]
  7%|▋         | 354/4990 [01:26<21:46,  3.55it/s]
  7%|▋         | 355/4990 [01:26<20:01,  3.86it/s]
  7%|▋         | 356/4990 [01:27<19:21,  3.99it/s]
  7%|▋         | 357/4990 [01:27<21:47,  3.54it/s]
  7%|▋         | 358/4990 [01:27<21:37,  3.57it/s]
  7%|▋         | 359/4990 [01:27<19:00,  4.06it/s]
  7%|▋         | 360/4990 [01:28<25:44,  3.00it/s]
  7%|▋         | 361/4990 [01:28<23:24,  3.29it/s]
  7%|▋         | 362/4990 [01:28<20:57,  3.68it/s]
  7%|▋         | 363/4990 [01:29<20:22,  3.78it/s]
  7%|▋         | 364/4990 [01:29<19:54,  3.87it/s]
  7%|▋         | 365/4990 [01:29<19:25,  3.97it/s]
  7%|▋         | 366/4990 [01:29<19:23,  3.97it/s]
  7%|▋         | 367/4990 [01:29<18:34,  4.15it/s]
  7%|▋         | 368/4990 [01:30<18:03,  4.27it/s]
  7%|▋         | 369/4990 [01:30<17:28,  4.41it/s]
  7%|▋         | 370/4990 [01:30<17:11,  4.48it/s]
  7%|▋         | 371/4990 [01:30<16:11,  4.75it/s]
  7%|▋         | 372/4990 [01:31<17:34,  4.38it/s]
  7%|▋         | 373/4990 [01:31<17:19,  4.44it/s]
  7%|▋         | 374/4990 [01:31<16:00,  4.81it/s]
  8%|▊         | 375/4990 [01:31<20:11,  3.81it/s]
  8%|▊         | 376/4990 [01:32<18:32,  4.15it/s]
  8%|▊         | 377/4990 [01:32<21:20,  3.60it/s]
  8%|▊         | 378/4990 [01:32<22:36,  3.40it/s]
  8%|▊         | 379/4990 [01:32<19:44,  3.89it/s]
  8%|▊         | 380/4990 [01:33<18:59,  4.04it/s]
  8%|▊         | 381/4990 [01:33<17:49,  4.31it/s]
  8%|▊         | 382/4990 [01:33<16:58,  4.52it/s]
  8%|▊         | 383/4990 [01:33<20:43,  3.70it/s]
  8%|▊         | 384/4990 [01:34<21:08,  3.63it/s]
  8%|▊         | 385/4990 [01:34<20:09,  3.81it/s]
  8%|▊         | 386/4990 [01:34<18:26,  4.16it/s]
  8%|▊         | 387/4990 [01:34<19:58,  3.84it/s]
  8%|▊         | 388/4990 [01:35<18:16,  4.20it/s]
  8%|▊         | 389/4990 [01:35<17:09,  4.47it/s]
  8%|▊         | 390/4990 [01:35<18:00,  4.26it/s]
  8%|▊         | 391/4990 [01:35<16:30,  4.64it/s]
  8%|▊         | 392/4990 [01:35<16:33,  4.63it/s]
  8%|▊         | 393/4990 [01:36<16:58,  4.51it/s]
  8%|▊         | 394/4990 [01:36<17:21,  4.41it/s]
  8%|▊         | 395/4990 [01:36<18:14,  4.20it/s]
  8%|▊         | 396/4990 [01:36<17:54,  4.28it/s]
  8%|▊         | 397/4990 [01:37<20:00,  3.83it/s]
  8%|▊         | 398/4990 [01:37<20:57,  3.65it/s]
  8%|▊         | 399/4990 [01:37<19:37,  3.90it/s]
  8%|▊         | 400/4990 [01:37<18:17,  4.18it/s]
  8%|▊         | 401/4990 [01:38<18:32,  4.13it/s]
  8%|▊         | 402/4990 [01:38<18:10,  4.21it/s]
  8%|▊         | 403/4990 [01:38<18:13,  4.19it/s]
  8%|▊         | 404/4990 [01:38<19:41,  3.88it/s]
  8%|▊         | 405/4990 [01:39<18:10,  4.20it/s]
  8%|▊         | 406/4990 [01:39<16:23,  4.66it/s]
  8%|▊         | 407/4990 [01:39<15:40,  4.87it/s]
  8%|▊         | 408/4990 [01:39<15:57,  4.78it/s]
  8%|▊         | 409/4990 [01:39<15:38,  4.88it/s]
  8%|▊         | 410/4990 [01:40<15:00,  5.09it/s]
  8%|▊         | 411/4990 [01:40<15:47,  4.83it/s]
  8%|▊         | 412/4990 [01:40<14:47,  5.16it/s]
  8%|▊         | 413/4990 [01:40<15:18,  4.98it/s]
  8%|▊         | 414/4990 [01:40<16:28,  4.63it/s]
  8%|▊         | 415/4990 [01:41<16:20,  4.67it/s]
  8%|▊         | 416/4990 [01:41<20:33,  3.71it/s]
  8%|▊         | 417/4990 [01:41<19:17,  3.95it/s]
  8%|▊         | 418/4990 [01:42<19:57,  3.82it/s]
  8%|▊         | 419/4990 [01:42<19:16,  3.95it/s]
  8%|▊         | 420/4990 [01:42<22:02,  3.46it/s]
  8%|▊         | 421/4990 [01:42<19:53,  3.83it/s]
  8%|▊         | 422/4990 [01:43<19:13,  3.96it/s]
  8%|▊         | 423/4990 [01:43<31:34,  2.41it/s]
  8%|▊         | 424/4990 [01:44<27:52,  2.73it/s]
  9%|▊         | 425/4990 [01:44<25:42,  2.96it/s]
  9%|▊         | 426/4990 [01:44<23:08,  3.29it/s]
  9%|▊         | 427/4990 [01:45<25:01,  3.04it/s]
  9%|▊         | 428/4990 [01:45<23:55,  3.18it/s]
  9%|▊         | 429/4990 [01:45<22:57,  3.31it/s]
  9%|▊         | 430/4990 [01:45<21:47,  3.49it/s]
  9%|▊         | 431/4990 [01:46<19:17,  3.94it/s]
  9%|▊         | 432/4990 [01:46<18:49,  4.03it/s]
  9%|▊         | 433/4990 [01:46<19:46,  3.84it/s]
  9%|▊         | 434/4990 [01:46<19:31,  3.89it/s]
  9%|▊         | 435/4990 [01:47<19:29,  3.90it/s]
  9%|▊         | 436/4990 [01:47<18:44,  4.05it/s]
  9%|▉         | 437/4990 [01:47<18:11,  4.17it/s]
  9%|▉         | 438/4990 [01:47<17:39,  4.30it/s]
  9%|▉         | 439/4990 [01:47<16:36,  4.57it/s]
  9%|▉         | 440/4990 [01:48<16:42,  4.54it/s]
  9%|▉         | 441/4990 [01:48<15:52,  4.78it/s]
  9%|▉         | 442/4990 [01:48<15:44,  4.82it/s]
  9%|▉         | 443/4990 [01:48<16:26,  4.61it/s]
  9%|▉         | 444/4990 [01:48<15:30,  4.88it/s]
  9%|▉         | 445/4990 [01:49<15:50,  4.78it/s]
  9%|▉         | 446/4990 [01:49<16:05,  4.71it/s]
  9%|▉         | 447/4990 [01:49<16:00,  4.73it/s]
  9%|▉         | 448/4990 [01:49<15:47,  4.80it/s]
  9%|▉         | 449/4990 [01:50<16:36,  4.56it/s]
  9%|▉         | 450/4990 [01:50<17:59,  4.20it/s]
  9%|▉         | 451/4990 [01:50<17:28,  4.33it/s]
  9%|▉         | 452/4990 [01:50<18:42,  4.04it/s]
  9%|▉         | 453/4990 [01:50<17:46,  4.25it/s]
  9%|▉         | 454/4990 [01:51<16:56,  4.46it/s]
  9%|▉         | 455/4990 [01:51<15:19,  4.93it/s]
  9%|▉         | 456/4990 [01:51<16:12,  4.66it/s]
  9%|▉         | 457/4990 [01:51<16:12,  4.66it/s]
  9%|▉         | 458/4990 [01:51<15:36,  4.84it/s]
  9%|▉         | 459/4990 [01:52<15:01,  5.03it/s]
  9%|▉         | 460/4990 [01:52<15:43,  4.80it/s]
  9%|▉         | 461/4990 [01:52<14:59,  5.04it/s]
  9%|▉         | 462/4990 [01:52<14:54,  5.06it/s]
  9%|▉         | 463/4990 [01:52<14:54,  5.06it/s]
  9%|▉         | 464/4990 [01:53<14:18,  5.27it/s]
  9%|▉         | 465/4990 [01:53<14:20,  5.26it/s]
  9%|▉         | 466/4990 [01:53<16:22,  4.61it/s]
  9%|▉         | 467/4990 [01:53<17:28,  4.31it/s]
  9%|▉         | 468/4990 [01:54<16:50,  4.48it/s]
  9%|▉         | 469/4990 [01:54<16:32,  4.56it/s]
  9%|▉         | 470/4990 [01:54<16:12,  4.65it/s]
  9%|▉         | 471/4990 [01:54<15:48,  4.77it/s]
  9%|▉         | 472/4990 [01:54<15:39,  4.81it/s]
  9%|▉         | 473/4990 [01:55<17:07,  4.40it/s]
  9%|▉         | 474/4990 [01:55<16:56,  4.44it/s]
 10%|▉         | 475/4990 [01:55<15:53,  4.73it/s]
 10%|▉         | 476/4990 [01:55<16:10,  4.65it/s]
 10%|▉         | 477/4990 [01:55<14:48,  5.08it/s]
 10%|▉         | 478/4990 [01:56<15:06,  4.98it/s]
 10%|▉         | 479/4990 [01:56<16:19,  4.60it/s]
 10%|▉         | 480/4990 [01:56<20:10,  3.73it/s]
 10%|▉         | 481/4990 [01:56<18:18,  4.10it/s]
 10%|▉         | 482/4990 [01:57<17:50,  4.21it/s]
 10%|▉         | 483/4990 [01:57<18:20,  4.09it/s]
 10%|▉         | 484/4990 [01:57<18:05,  4.15it/s]
 10%|▉         | 485/4990 [01:57<17:24,  4.32it/s]
 10%|▉         | 486/4990 [01:58<18:36,  4.03it/s]
 10%|▉         | 487/4990 [01:58<18:48,  3.99it/s]
 10%|▉         | 488/4990 [01:58<17:01,  4.41it/s]
 10%|▉         | 489/4990 [01:58<18:50,  3.98it/s]
 10%|▉         | 490/4990 [01:59<18:55,  3.96it/s]
 10%|▉         | 491/4990 [01:59<17:51,  4.20it/s]
 10%|▉         | 492/4990 [01:59<20:24,  3.67it/s]
 10%|▉         | 493/4990 [01:59<19:10,  3.91it/s]
 10%|▉         | 494/4990 [02:00<28:08,  2.66it/s]
 10%|▉         | 495/4990 [02:00<24:55,  3.01it/s]
 10%|▉         | 496/4990 [02:01<23:38,  3.17it/s]
 10%|▉         | 497/4990 [02:01<21:36,  3.47it/s]
 10%|▉         | 498/4990 [02:01<20:01,  3.74it/s]
 10%|█         | 499/4990 [02:01<18:19,  4.08it/s][INFO|trainer.py:811] 2024-09-05 22:46:40,950 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: id, ner_tags, tokens. If id, ner_tags, tokens are not expected by `RobertaForTokenClassification.forward`,  you can safely ignore this message.
[INFO|trainer.py:3819] 2024-09-05 22:46:40,953 >> 
***** Running Evaluation *****
[INFO|trainer.py:3821] 2024-09-05 22:46:40,953 >>   Num examples = 6810
[INFO|trainer.py:3824] 2024-09-05 22:46:40,953 >>   Batch size = 8


  0%|          | 0/852 [00:00<?, ?it/s]

  1%|          | 10/852 [00:00<00:09, 92.13it/s]

  2%|▏         | 20/852 [00:00<00:10, 83.09it/s]

  3%|▎         | 29/852 [00:00<00:10, 80.96it/s]

  4%|▍         | 38/852 [00:00<00:10, 79.95it/s]

  6%|▌         | 47/852 [00:00<00:09, 80.68it/s]

  7%|▋         | 56/852 [00:00<00:09, 82.11it/s]

  8%|▊         | 65/852 [00:00<00:09, 81.29it/s]

  9%|▊         | 74/852 [00:00<00:09, 80.27it/s]

 10%|▉         | 83/852 [00:01<00:09, 80.29it/s]

 11%|█         | 92/852 [00:01<00:09, 80.69it/s]

 12%|█▏        | 101/852 [00:01<00:09, 80.35it/s]

 13%|█▎        | 110/852 [00:01<00:09, 80.34it/s]

 14%|█▍        | 119/852 [00:01<00:09, 81.26it/s]

 15%|█▌        | 128/852 [00:01<00:09, 77.90it/s]

 16%|█▌        | 137/852 [00:01<00:09, 77.65it/s]

 17%|█▋        | 146/852 [00:01<00:08, 79.18it/s]

 18%|█▊        | 154/852 [00:01<00:08, 79.13it/s]

 19%|█▉        | 163/852 [00:02<00:08, 80.56it/s]

 20%|██        | 172/852 [00:02<00:08, 81.35it/s]

 21%|██        | 181/852 [00:02<00:08, 81.29it/s]

 22%|██▏       | 190/852 [00:02<00:08, 81.87it/s]

 23%|██▎       | 199/852 [00:02<00:08, 81.13it/s]

 24%|██▍       | 208/852 [00:02<00:08, 79.64it/s]

 25%|██▌       | 217/852 [00:02<00:07, 80.28it/s]

 27%|██▋       | 226/852 [00:02<00:07, 80.94it/s]

 28%|██▊       | 235/852 [00:02<00:07, 81.14it/s]

 29%|██▊       | 244/852 [00:03<00:07, 78.91it/s]

 30%|██▉       | 253/852 [00:03<00:07, 81.38it/s]

 31%|███       | 262/852 [00:03<00:07, 82.99it/s]

 32%|███▏      | 271/852 [00:03<00:07, 82.27it/s]

 33%|███▎      | 280/852 [00:03<00:07, 73.21it/s]

 34%|███▍      | 288/852 [00:03<00:07, 74.75it/s]

 35%|███▍      | 297/852 [00:03<00:07, 76.92it/s]

 36%|███▌      | 306/852 [00:03<00:06, 79.20it/s]

 37%|███▋      | 315/852 [00:03<00:06, 78.62it/s]

 38%|███▊      | 324/852 [00:04<00:06, 79.99it/s]

 39%|███▉      | 333/852 [00:04<00:06, 80.76it/s]

 40%|████      | 342/852 [00:04<00:06, 82.32it/s]

 41%|████      | 351/852 [00:04<00:06, 83.01it/s]

 42%|████▏     | 360/852 [00:04<00:06, 79.91it/s]

 43%|████▎     | 369/852 [00:04<00:06, 80.40it/s]

 44%|████▍     | 378/852 [00:04<00:05, 80.95it/s]

 45%|████▌     | 387/852 [00:04<00:05, 80.69it/s]

 46%|████▋     | 396/852 [00:04<00:05, 81.56it/s]

 48%|████▊     | 405/852 [00:05<00:05, 79.23it/s]

 49%|████▊     | 414/852 [00:05<00:05, 80.26it/s]

 50%|████▉     | 423/852 [00:05<00:05, 81.17it/s]

 51%|█████     | 432/852 [00:05<00:05, 80.47it/s]

 52%|█████▏    | 441/852 [00:05<00:04, 82.22it/s]

 53%|█████▎    | 450/852 [00:05<00:04, 82.08it/s]

 54%|█████▍    | 459/852 [00:05<00:04, 82.69it/s]

 55%|█████▍    | 468/852 [00:05<00:04, 79.57it/s]

 56%|█████▌    | 476/852 [00:05<00:04, 76.48it/s]

 57%|█████▋    | 484/852 [00:06<00:04, 76.69it/s]

 58%|█████▊    | 493/852 [00:06<00:04, 79.25it/s]

 59%|█████▉    | 502/852 [00:06<00:04, 81.12it/s]

 60%|█████▉    | 511/852 [00:06<00:04, 81.53it/s]

 61%|██████    | 520/852 [00:06<00:04, 82.38it/s]

 62%|██████▏   | 529/852 [00:06<00:04, 80.16it/s]

 63%|██████▎   | 538/852 [00:06<00:03, 81.91it/s]

 64%|██████▍   | 547/852 [00:06<00:03, 81.08it/s]

 65%|██████▌   | 556/852 [00:06<00:03, 78.18it/s]

 66%|██████▋   | 565/852 [00:07<00:03, 80.35it/s]

 67%|██████▋   | 574/852 [00:07<00:03, 81.19it/s]

 68%|██████▊   | 583/852 [00:07<00:03, 80.70it/s]

 69%|██████▉   | 592/852 [00:07<00:03, 80.43it/s]

 71%|███████   | 601/852 [00:07<00:03, 80.49it/s]

 72%|███████▏  | 610/852 [00:07<00:02, 80.86it/s]

 73%|███████▎  | 619/852 [00:07<00:02, 79.04it/s]

 74%|███████▎  | 627/852 [00:07<00:02, 78.94it/s]

 75%|███████▍  | 635/852 [00:07<00:02, 78.41it/s]

 75%|███████▌  | 643/852 [00:08<00:02, 76.41it/s]

 77%|███████▋  | 652/852 [00:08<00:02, 78.97it/s]

 78%|███████▊  | 661/852 [00:08<00:02, 80.15it/s]

 79%|███████▊  | 670/852 [00:08<00:02, 80.54it/s]

 80%|███████▉  | 679/852 [00:08<00:02, 80.46it/s]

 81%|████████  | 688/852 [00:08<00:02, 81.20it/s]

 82%|████████▏ | 697/852 [00:08<00:01, 81.93it/s]

 83%|████████▎ | 706/852 [00:08<00:01, 83.09it/s]

 84%|████████▍ | 715/852 [00:08<00:01, 83.40it/s]

 85%|████████▍ | 724/852 [00:09<00:01, 82.90it/s]

 86%|████████▌ | 733/852 [00:09<00:01, 83.77it/s]

 87%|████████▋ | 742/852 [00:09<00:01, 84.34it/s]

 88%|████████▊ | 751/852 [00:09<00:01, 83.18it/s]

 89%|████████▉ | 760/852 [00:09<00:01, 84.50it/s]

 90%|█████████ | 769/852 [00:09<00:01, 82.87it/s]

 91%|█████████▏| 778/852 [00:09<00:00, 82.40it/s]

 92%|█████████▏| 787/852 [00:09<00:00, 81.73it/s]

 93%|█████████▎| 796/852 [00:09<00:00, 82.64it/s]

 94%|█████████▍| 805/852 [00:09<00:00, 83.74it/s]

 96%|█████████▌| 814/852 [00:10<00:00, 82.67it/s]

 97%|█████████▋| 823/852 [00:10<00:00, 83.63it/s]

 98%|█████████▊| 832/852 [00:10<00:00, 84.37it/s]

 99%|█████████▊| 841/852 [00:10<00:00, 83.41it/s]

100%|█████████▉| 850/852 [00:10<00:00, 81.97it/s]
                                                  

                                                 

 10%|█         | 499/4990 [02:16<18:19,  4.08it/s]

100%|██████████| 852/852 [00:14<00:00, 81.97it/s]

                                                 [INFO|trainer.py:3503] 2024-09-05 22:46:55,159 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-499
[INFO|configuration_utils.py:472] 2024-09-05 22:46:55,160 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-499/config.json
[INFO|modeling_utils.py:2799] 2024-09-05 22:46:56,182 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-499/model.safetensors
[INFO|tokenization_utils_base.py:2684] 2024-09-05 22:46:56,183 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-499/tokenizer_config.json
[INFO|tokenization_utils_base.py:2693] 2024-09-05 22:46:56,183 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-499/special_tokens_map.json
[INFO|tokenization_utils_base.py:2684] 2024-09-05 22:46:58,215 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
[INFO|tokenization_utils_base.py:2693] 2024-09-05 22:46:58,215 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json

 10%|█         | 500/4990 [02:19<6:45:16,  5.42s/it]
                                                    

 10%|█         | 500/4990 [02:19<6:45:16,  5.42s/it]
 10%|█         | 501/4990 [02:19<4:48:18,  3.85s/it]
 10%|█         | 502/4990 [02:19<3:26:57,  2.77s/it]
 10%|█         | 503/4990 [02:19<2:30:05,  2.01s/it]
 10%|█         | 504/4990 [02:20<1:50:49,  1.48s/it]
 10%|█         | 505/4990 [02:20<1:24:52,  1.14s/it]
 10%|█         | 506/4990 [02:20<1:04:26,  1.16it/s]
 10%|█         | 507/4990 [02:20<49:53,  1.50it/s]  
 10%|█         | 508/4990 [02:21<41:00,  1.82it/s]
 10%|█         | 509/4990 [02:21<33:10,  2.25it/s]
 10%|█         | 510/4990 [02:21<27:07,  2.75it/s]
 10%|█         | 511/4990 [02:21<23:16,  3.21it/s]
 10%|█         | 512/4990 [02:21<21:02,  3.55it/s]
 10%|█         | 513/4990 [02:22<18:52,  3.95it/s]
 10%|█         | 514/4990 [02:22<22:26,  3.32it/s]
 10%|█         | 515/4990 [02:22<20:00,  3.73it/s]
 10%|█         | 516/4990 [02:22<18:22,  4.06it/s]
 10%|█         | 517/4990 [02:23<17:28,  4.27it/s]
 10%|█         | 518/4990 [02:23<16:30,  4.52it/s]
 10%|█         | 519/4990 [02:23<18:31,  4.02it/s]
 10%|█         | 520/4990 [02:23<16:33,  4.50it/s]
 10%|█         | 521/4990 [02:24<16:20,  4.56it/s]
 10%|█         | 522/4990 [02:24<16:24,  4.54it/s]
 10%|█         | 523/4990 [02:24<15:59,  4.65it/s]
 11%|█         | 524/4990 [02:24<19:35,  3.80it/s]
 11%|█         | 525/4990 [02:25<19:32,  3.81it/s]
 11%|█         | 526/4990 [02:25<18:10,  4.09it/s]
 11%|█         | 527/4990 [02:25<17:04,  4.36it/s]
 11%|█         | 528/4990 [02:25<17:16,  4.31it/s]
 11%|█         | 529/4990 [02:25<17:11,  4.33it/s]
 11%|█         | 530/4990 [02:26<16:46,  4.43it/s]
 11%|█         | 531/4990 [02:26<15:43,  4.73it/s]
 11%|█         | 532/4990 [02:26<15:18,  4.85it/s]
 11%|█         | 533/4990 [02:26<15:13,  4.88it/s]
 11%|█         | 534/4990 [02:27<28:20,  2.62it/s]
 11%|█         | 535/4990 [02:27<24:26,  3.04it/s]
 11%|█         | 536/4990 [02:28<22:16,  3.33it/s]
 11%|█         | 537/4990 [02:28<22:43,  3.27it/s]
 11%|█         | 538/4990 [02:28<22:19,  3.32it/s]
 11%|█         | 539/4990 [02:28<20:12,  3.67it/s]
 11%|█         | 540/4990 [02:29<21:08,  3.51it/s]
 11%|█         | 541/4990 [02:29<19:02,  3.89it/s]
 11%|█         | 542/4990 [02:29<17:45,  4.17it/s]
 11%|█         | 543/4990 [02:29<16:52,  4.39it/s]
 11%|█         | 544/4990 [02:29<15:30,  4.78it/s]
 11%|█         | 545/4990 [02:30<16:11,  4.58it/s]
 11%|█         | 546/4990 [02:30<16:42,  4.43it/s]
 11%|█         | 547/4990 [02:30<15:52,  4.66it/s]
 11%|█         | 548/4990 [02:30<16:27,  4.50it/s]
 11%|█         | 549/4990 [02:31<22:41,  3.26it/s]
 11%|█         | 550/4990 [02:31<22:32,  3.28it/s]
 11%|█         | 551/4990 [02:31<22:49,  3.24it/s]
 11%|█         | 552/4990 [02:32<19:56,  3.71it/s]
 11%|█         | 553/4990 [02:32<18:11,  4.06it/s]
 11%|█         | 554/4990 [02:32<19:06,  3.87it/s]
 11%|█         | 555/4990 [02:32<17:31,  4.22it/s]
 11%|█         | 556/4990 [02:32<16:52,  4.38it/s]
 11%|█         | 557/4990 [02:33<16:57,  4.36it/s]
 11%|█         | 558/4990 [02:33<16:32,  4.47it/s]
 11%|█         | 559/4990 [02:33<16:17,  4.53it/s]
 11%|█         | 560/4990 [02:33<17:38,  4.19it/s]
 11%|█         | 561/4990 [02:34<29:58,  2.46it/s]
 11%|█▏        | 562/4990 [02:34<26:44,  2.76it/s]
 11%|█▏        | 563/4990 [02:35<29:38,  2.49it/s]
 11%|█▏        | 564/4990 [02:35<24:19,  3.03it/s]
 11%|█▏        | 565/4990 [02:35<22:20,  3.30it/s]
 11%|█▏        | 566/4990 [02:36<19:36,  3.76it/s]
 11%|█▏        | 567/4990 [02:36<18:36,  3.96it/s]
 11%|█▏        | 568/4990 [02:36<18:25,  4.00it/s]
 11%|█▏        | 569/4990 [02:36<17:19,  4.25it/s]
 11%|█▏        | 570/4990 [02:37<18:45,  3.93it/s]
 11%|█▏        | 571/4990 [02:37<18:27,  3.99it/s]
 11%|█▏        | 572/4990 [02:37<21:34,  3.41it/s]
 11%|█▏        | 573/4990 [02:37<21:03,  3.50it/s]
 12%|█▏        | 574/4990 [02:38<19:30,  3.77it/s]
 12%|█▏        | 575/4990 [02:38<18:21,  4.01it/s]
 12%|█▏        | 576/4990 [02:38<17:29,  4.21it/s]
 12%|█▏        | 577/4990 [02:38<17:17,  4.25it/s]
 12%|█▏        | 578/4990 [02:38<16:36,  4.43it/s]
 12%|█▏        | 579/4990 [02:39<17:44,  4.14it/s]
 12%|█▏        | 580/4990 [02:39<18:01,  4.08it/s]
 12%|█▏        | 581/4990 [02:39<22:05,  3.33it/s]
 12%|█▏        | 582/4990 [02:40<20:32,  3.58it/s]
 12%|█▏        | 583/4990 [02:40<18:21,  4.00it/s]
 12%|█▏        | 584/4990 [02:40<17:22,  4.23it/s]
 12%|█▏        | 585/4990 [02:40<15:44,  4.66it/s]
 12%|█▏        | 586/4990 [02:40<14:56,  4.91it/s]
 12%|█▏        | 587/4990 [02:41<15:23,  4.77it/s]
 12%|█▏        | 588/4990 [02:41<15:02,  4.88it/s]
 12%|█▏        | 589/4990 [02:41<15:48,  4.64it/s]
 12%|█▏        | 590/4990 [02:41<16:13,  4.52it/s]
 12%|█▏        | 591/4990 [02:42<16:01,  4.58it/s]
 12%|█▏        | 592/4990 [02:42<16:48,  4.36it/s]
 12%|█▏        | 593/4990 [02:42<17:41,  4.14it/s]
 12%|█▏        | 594/4990 [02:42<18:45,  3.91it/s]
 12%|█▏        | 595/4990 [02:43<18:12,  4.02it/s]
 12%|█▏        | 596/4990 [02:43<16:06,  4.55it/s]
 12%|█▏        | 597/4990 [02:43<15:39,  4.67it/s]
 12%|█▏        | 598/4990 [02:43<17:10,  4.26it/s]
 12%|█▏        | 599/4990 [02:43<17:44,  4.12it/s]
 12%|█▏        | 600/4990 [02:44<17:03,  4.29it/s]
 12%|█▏        | 601/4990 [02:44<16:09,  4.53it/s]
 12%|█▏        | 602/4990 [02:44<15:17,  4.78it/s]
 12%|█▏        | 603/4990 [02:44<15:23,  4.75it/s]
 12%|█▏        | 604/4990 [02:44<14:31,  5.04it/s]
 12%|█▏        | 605/4990 [02:45<16:54,  4.32it/s]
 12%|█▏        | 606/4990 [02:45<17:54,  4.08it/s]
 12%|█▏        | 607/4990 [02:45<19:41,  3.71it/s]
 12%|█▏        | 608/4990 [02:46<17:59,  4.06it/s]
 12%|█▏        | 609/4990 [02:46<17:00,  4.29it/s]
 12%|█▏        | 610/4990 [02:46<15:46,  4.63it/s]
 12%|█▏        | 611/4990 [02:46<15:23,  4.74it/s]
 12%|█▏        | 612/4990 [02:46<14:48,  4.93it/s]
 12%|█▏        | 613/4990 [02:47<15:47,  4.62it/s]
 12%|█▏        | 614/4990 [02:47<14:57,  4.88it/s]
 12%|█▏        | 615/4990 [02:47<14:19,  5.09it/s]
 12%|█▏        | 616/4990 [02:47<14:04,  5.18it/s]
 12%|█▏        | 617/4990 [02:47<13:24,  5.44it/s]
 12%|█▏        | 618/4990 [02:47<14:28,  5.03it/s]
 12%|█▏        | 619/4990 [02:48<15:06,  4.82it/s]
 12%|█▏        | 620/4990 [02:48<15:07,  4.82it/s]
 12%|█▏        | 621/4990 [02:48<15:22,  4.73it/s]
 12%|█▏        | 622/4990 [02:48<15:06,  4.82it/s]
 12%|█▏        | 623/4990 [02:49<15:49,  4.60it/s]
 13%|█▎        | 624/4990 [02:49<14:46,  4.92it/s]
 13%|█▎        | 625/4990 [02:49<14:36,  4.98it/s]
 13%|█▎        | 626/4990 [02:49<14:10,  5.13it/s]
 13%|█▎        | 627/4990 [02:49<14:20,  5.07it/s]
 13%|█▎        | 628/4990 [02:50<18:54,  3.85it/s]