2024-08-30 21:54:12.390238: 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 21:54:12.408272: 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 21:54:12.429605: 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 21:54:12.436048: 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 21:54:12.451309: 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 21:54:13.743493: 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 21:54:15 - WARNING - __main__ -   Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False
08/30/2024 21:54:15 - 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=<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,
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%|          | 0.00/3.61k [00:00<?, ?B/s]
Downloading builder script: 100%|██████████| 3.61k/3.61k [00:00<00:00, 32.5kB/s]
Downloading builder script: 100%|██████████| 3.61k/3.61k [00:00<00:00, 32.4kB/s]

Downloading data:   0%|          | 0.00/28.4M [00:00<?, ?B/s]
Downloading data:  37%|███▋      | 10.5M/28.4M [00:00<00:01, 17.2MB/s]
Downloading data:  74%|███████▍  | 21.0M/28.4M [00:00<00:00, 27.1MB/s]
Downloading data: 100%|██████████| 28.4M/28.4M [00:00<00:00, 30.5MB/s]

Downloading data:   0%|          | 0.00/7.18M [00:00<?, ?B/s]
Downloading data: 100%|██████████| 7.18M/7.18M [00:00<00:00, 15.1MB/s]
Downloading data: 100%|██████████| 7.18M/7.18M [00:00<00:00, 14.9MB/s]

Downloading data:   0%|          | 0.00/12.7M [00:00<?, ?B/s]
Downloading data:  83%|████████▎ | 10.5M/12.7M [00:00<00:00, 13.6MB/s]
Downloading data: 100%|██████████| 12.7M/12.7M [00:00<00:00, 15.2MB/s]

Generating train split: 0 examples [00:00, ? examples/s]
Generating train split: 650 examples [00:00, 6479.58 examples/s]
Generating train split: 1570 examples [00:00, 6230.73 examples/s]
Generating train split: 2197 examples [00:00, 6243.84 examples/s]
Generating train split: 2876 examples [00:00, 6438.63 examples/s]
Generating train split: 3870 examples [00:00, 6516.72 examples/s]
Generating train split: 4836 examples [00:00, 6483.38 examples/s]
Generating train split: 5812 examples [00:00, 6483.37 examples/s]
Generating train split: 6748 examples [00:01, 6399.92 examples/s]
Generating train split: 7705 examples [00:01, 6390.99 examples/s]
Generating train split: 8677 examples [00:01, 6357.98 examples/s]
Generating train split: 9341 examples [00:01, 6309.55 examples/s]
Generating train split: 10000 examples [00:01, 6268.59 examples/s]
Generating train split: 10705 examples [00:01, 6466.53 examples/s]
Generating train split: 11689 examples [00:01, 6480.27 examples/s]
Generating train split: 12358 examples [00:01, 6436.83 examples/s]
Generating train split: 13326 examples [00:02, 6410.58 examples/s]
Generating train split: 14000 examples [00:02, 6434.42 examples/s]
Generating train split: 14683 examples [00:02, 6534.38 examples/s]
Generating train split: 15344 examples [00:02, 6420.69 examples/s]
Generating train split: 16000 examples [00:02, 6294.41 examples/s]
Generating train split: 16698 examples [00:02, 6482.52 examples/s]
Generating train split: 17710 examples [00:02, 6569.11 examples/s]
Generating train split: 18690 examples [00:02, 6530.42 examples/s]
Generating train split: 19357 examples [00:03, 6433.26 examples/s]
Generating train split: 20000 examples [00:03, 6315.16 examples/s]
Generating train split: 20701 examples [00:03, 6493.49 examples/s]
Generating train split: 21677 examples [00:03, 6406.63 examples/s]
Generating train split: 22333 examples [00:03, 6351.42 examples/s]
Generating train split: 23000 examples [00:03, 6378.96 examples/s]
Generating train split: 23682 examples [00:03, 6496.62 examples/s]
Generating train split: 24335 examples [00:03, 6415.76 examples/s]
Generating train split: 25000 examples [00:03, 6430.84 examples/s]
Generating train split: 25656 examples [00:03, 6465.37 examples/s]
Generating train split: 26589 examples [00:04, 6363.95 examples/s]
Generating train split: 27198 examples [00:04, 6406.41 examples/s]

Generating validation split: 0 examples [00:00, ? examples/s]
Generating validation split: 671 examples [00:00, 6676.09 examples/s]
Generating validation split: 1592 examples [00:00, 6295.62 examples/s]
Generating validation split: 2555 examples [00:00, 6350.38 examples/s]
Generating validation split: 3521 examples [00:00, 6384.09 examples/s]
Generating validation split: 4475 examples [00:00, 6369.31 examples/s]
Generating validation split: 5405 examples [00:00, 6305.44 examples/s]
Generating validation split: 6329 examples [00:01, 6214.54 examples/s]
Generating validation split: 6798 examples [00:01, 6281.30 examples/s]

Generating test split: 0 examples [00:00, ? examples/s]
Generating test split: 767 examples [00:00, 7644.75 examples/s]
Generating test split: 1833 examples [00:00, 7268.45 examples/s]
Generating test split: 2937 examples [00:00, 7302.00 examples/s]
Generating test split: 3985 examples [00:00, 7163.98 examples/s]
Generating test split: 4717 examples [00:00, 7206.82 examples/s]
Generating test split: 5833 examples [00:00, 7289.92 examples/s]
Generating test split: 6620 examples [00:00, 7440.45 examples/s]
Generating test split: 7767 examples [00:01, 7508.88 examples/s]
Generating test split: 8924 examples [00:01, 7571.24 examples/s]
Generating test split: 10000 examples [00:01, 7294.00 examples/s]
Generating test split: 10848 examples [00:01, 7569.77 examples/s]
Generating test split: 11961 examples [00:01, 5002.92 examples/s]
Generating test split: 12620 examples [00:01, 5277.89 examples/s]
Generating test split: 13274 examples [00:02, 5528.16 examples/s]
Generating test split: 14014 examples [00:02, 5941.72 examples/s]
Generating test split: 14605 examples [00:02, 6558.31 examples/s]
[INFO|configuration_utils.py:733] 2024-08-30 21:54:27,962 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--IVN-RIN--bioBIT/snapshots/83755ed79ee254c11854e9f54a53679557271018/config.json
[INFO|configuration_utils.py:800] 2024-08-30 21:54:27,966 >> Model config BertConfig {
  "_name_or_path": "IVN-RIN/bioBIT",
  "architectures": [
    "BertForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "classifier_dropout": null,
  "finetuning_task": "ner",
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "id2label": {
    "0": "O",
    "1": "B-FARMACO",
    "2": "I-FARMACO"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "B-FARMACO": 1,
    "I-FARMACO": 2,
    "O": 0
  },
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "bert",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 0,
  "position_embedding_type": "absolute",
  "torch_dtype": "float32",
  "transformers_version": "4.42.4",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 31102
}

[INFO|tokenization_utils_base.py:2161] 2024-08-30 21:54:29,333 >> loading file vocab.txt from cache at /root/.cache/huggingface/hub/models--IVN-RIN--bioBIT/snapshots/83755ed79ee254c11854e9f54a53679557271018/vocab.txt
[INFO|tokenization_utils_base.py:2161] 2024-08-30 21:54:29,334 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--IVN-RIN--bioBIT/snapshots/83755ed79ee254c11854e9f54a53679557271018/tokenizer.json
[INFO|tokenization_utils_base.py:2161] 2024-08-30 21:54:29,334 >> loading file added_tokens.json from cache at None
[INFO|tokenization_utils_base.py:2161] 2024-08-30 21:54:29,334 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--IVN-RIN--bioBIT/snapshots/83755ed79ee254c11854e9f54a53679557271018/special_tokens_map.json
[INFO|tokenization_utils_base.py:2161] 2024-08-30 21:54:29,334 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--IVN-RIN--bioBIT/snapshots/83755ed79ee254c11854e9f54a53679557271018/tokenizer_config.json
[INFO|modeling_utils.py:3556] 2024-08-30 21:54:40,888 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--IVN-RIN--bioBIT/snapshots/83755ed79ee254c11854e9f54a53679557271018/model.safetensors
[INFO|modeling_utils.py:4354] 2024-08-30 21:54:40,995 >> Some weights of the model checkpoint at IVN-RIN/bioBIT were not used when initializing BertForTokenClassification: ['cls.predictions.bias', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.dense.weight']
- This IS expected if you are initializing BertForTokenClassification 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 BertForTokenClassification 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 21:54:40,995 >> Some weights of BertForTokenClassification were not initialized from the model checkpoint at IVN-RIN/bioBIT 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%|          | 0/27198 [00:00<?, ? examples/s]
Map:   4%|▎         | 1000/27198 [00:00<00:02, 9695.97 examples/s]
Map:  11%|█         | 3000/27198 [00:00<00:02, 10181.51 examples/s]
Map:  18%|█▊        | 5000/27198 [00:00<00:02, 10348.11 examples/s]
Map:  26%|██▌       | 7000/27198 [00:00<00:01, 10323.24 examples/s]
Map:  33%|███▎      | 9000/27198 [00:00<00:01, 10072.54 examples/s]
Map:  40%|████      | 11000/27198 [00:01<00:01, 10242.18 examples/s]
Map:  48%|████▊     | 13000/27198 [00:01<00:01, 10318.43 examples/s]
Map:  55%|█████▌    | 15000/27198 [00:01<00:01, 10355.57 examples/s]
Map:  63%|██████▎   | 17000/27198 [00:01<00:00, 10360.62 examples/s]
Map:  70%|██████▉   | 19000/27198 [00:01<00:00, 10384.20 examples/s]
Map:  77%|███████▋  | 21000/27198 [00:02<00:00, 10434.32 examples/s]
Map:  85%|████████▍ | 23000/27198 [00:02<00:00, 10392.84 examples/s]
Map:  92%|█████████▏| 25000/27198 [00:02<00:00, 7635.68 examples/s] 
Map:  99%|█████████▉| 27000/27198 [00:02<00:00, 8272.86 examples/s]
Map: 100%|██████████| 27198/27198 [00:02<00:00, 9416.80 examples/s]

Map:   0%|          | 0/6798 [00:00<?, ? examples/s]
Map:  15%|█▍        | 1000/6798 [00:00<00:00, 9797.56 examples/s]
Map:  44%|████▍     | 3000/6798 [00:00<00:00, 10158.64 examples/s]
Map:  74%|███████▎  | 5000/6798 [00:00<00:00, 10229.27 examples/s]
Map: 100%|██████████| 6798/6798 [00:00<00:00, 10256.19 examples/s]
Map: 100%|██████████| 6798/6798 [00:00<00:00, 10116.89 examples/s]

Map:   0%|          | 0/14605 [00:00<?, ? examples/s]
Map:  14%|█▎        | 2000/14605 [00:00<00:01, 11674.32 examples/s]
Map:  27%|██▋       | 4000/14605 [00:00<00:00, 11547.74 examples/s]
Map:  41%|████      | 6000/14605 [00:00<00:00, 11939.80 examples/s]
Map:  55%|█████▍    | 8000/14605 [00:00<00:00, 12216.90 examples/s]
Map:  68%|██████▊   | 10000/14605 [00:00<00:00, 12206.52 examples/s]
Map:  82%|████████▏ | 12000/14605 [00:00<00:00, 12202.17 examples/s]
Map:  96%|█████████▌| 14000/14605 [00:01<00:00, 11909.07 examples/s]
Map: 100%|██████████| 14605/14605 [00:01<00:00, 11852.97 examples/s]
/content/dissertation/scripts/ner/run_ner_train.py:397: FutureWarning: load_metric is deprecated and will be removed in the next major version of datasets. Use 'evaluate.load' instead, from the new library 🤗 Evaluate: https://huggingface.co/docs/evaluate
  metric = load_metric("seqeval", trust_remote_code=True)
[INFO|trainer.py:805] 2024-08-30 21:54:47,484 >> The following columns in the training set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: id, tokens, ner_tags. If id, tokens, ner_tags are not expected by `BertForTokenClassification.forward`,  you can safely ignore this message.
[INFO|trainer.py:2128] 2024-08-30 21:54:48,041 >> ***** Running training *****
[INFO|trainer.py:2129] 2024-08-30 21:54:48,041 >>   Num examples = 27,198
[INFO|trainer.py:2130] 2024-08-30 21:54:48,041 >>   Num Epochs = 10
[INFO|trainer.py:2131] 2024-08-30 21:54:48,041 >>   Instantaneous batch size per device = 32
[INFO|trainer.py:2134] 2024-08-30 21:54:48,041 >>   Total train batch size (w. parallel, distributed & accumulation) = 64
[INFO|trainer.py:2135] 2024-08-30 21:54:48,041 >>   Gradient Accumulation steps = 2
[INFO|trainer.py:2136] 2024-08-30 21:54:48,041 >>   Total optimization steps = 4,250
[INFO|trainer.py:2137] 2024-08-30 21:54:48,042 >>   Number of trainable parameters = 109,339,395

  0%|          | 0/4250 [00:00<?, ?it/s]
  0%|          | 1/4250 [00:01<1:16:38,  1.08s/it]
  0%|          | 2/4250 [00:01<42:55,  1.65it/s]  
  0%|          | 3/4250 [00:01<31:14,  2.27it/s]
  0%|          | 4/4250 [00:01<27:28,  2.58it/s]
  0%|          | 5/4250 [00:02<22:59,  3.08it/s]
  0%|          | 6/4250 [00:02<20:46,  3.40it/s]
  0%|          | 7/4250 [00:02<19:37,  3.60it/s]
  0%|          | 8/4250 [00:02<19:26,  3.64it/s]
  0%|          | 9/4250 [00:03<19:00,  3.72it/s]
  0%|          | 10/4250 [00:03<18:07,  3.90it/s]
  0%|          | 11/4250 [00:03<19:02,  3.71it/s]
  0%|          | 12/4250 [00:04<24:46,  2.85it/s]
  0%|          | 13/4250 [00:04<21:06,  3.34it/s]
  0%|          | 14/4250 [00:04<20:00,  3.53it/s]
  0%|          | 15/4250 [00:04<18:30,  3.81it/s]
  0%|          | 16/4250 [00:05<18:06,  3.90it/s]
  0%|          | 17/4250 [00:05<17:34,  4.01it/s]
  0%|          | 18/4250 [00:05<18:38,  3.78it/s]
  0%|          | 19/4250 [00:05<17:09,  4.11it/s]
  0%|          | 20/4250 [00:06<19:46,  3.56it/s]
  0%|          | 21/4250 [00:06<18:46,  3.75it/s]
  1%|          | 22/4250 [00:06<17:49,  3.95it/s]
  1%|          | 23/4250 [00:06<16:35,  4.25it/s]
  1%|          | 24/4250 [00:07<16:31,  4.26it/s]
  1%|          | 25/4250 [00:07<16:19,  4.31it/s]
  1%|          | 26/4250 [00:07<17:22,  4.05it/s]
  1%|          | 27/4250 [00:07<17:01,  4.14it/s]
  1%|          | 28/4250 [00:08<17:18,  4.07it/s]
  1%|          | 29/4250 [00:08<17:59,  3.91it/s]
  1%|          | 30/4250 [00:08<17:04,  4.12it/s]
  1%|          | 31/4250 [00:08<16:47,  4.19it/s]
  1%|          | 32/4250 [00:08<16:27,  4.27it/s]
  1%|          | 33/4250 [00:09<17:11,  4.09it/s]
  1%|          | 34/4250 [00:09<15:30,  4.53it/s]
  1%|          | 35/4250 [00:09<15:15,  4.60it/s]
  1%|          | 36/4250 [00:09<15:39,  4.49it/s]
  1%|          | 37/4250 [00:10<15:49,  4.44it/s]
  1%|          | 38/4250 [00:10<16:11,  4.34it/s]
  1%|          | 39/4250 [00:10<15:41,  4.47it/s]
  1%|          | 40/4250 [00:10<15:55,  4.41it/s]
  1%|          | 41/4250 [00:10<15:07,  4.64it/s]
  1%|          | 42/4250 [00:11<14:56,  4.69it/s]
  1%|          | 43/4250 [00:11<15:59,  4.39it/s]
  1%|          | 44/4250 [00:11<15:40,  4.47it/s]
  1%|          | 45/4250 [00:11<15:41,  4.47it/s]
  1%|          | 46/4250 [00:12<17:35,  3.98it/s]
  1%|          | 47/4250 [00:12<17:45,  3.94it/s]
  1%|          | 48/4250 [00:12<16:40,  4.20it/s]
  1%|          | 49/4250 [00:12<15:58,  4.38it/s]
  1%|          | 50/4250 [00:13<17:10,  4.08it/s]
  1%|          | 51/4250 [00:13<18:57,  3.69it/s]
  1%|          | 52/4250 [00:13<19:58,  3.50it/s]
  1%|          | 53/4250 [00:14<18:49,  3.72it/s]
  1%|▏         | 54/4250 [00:14<17:34,  3.98it/s]
  1%|▏         | 55/4250 [00:14<16:51,  4.15it/s]
  1%|▏         | 56/4250 [00:14<17:23,  4.02it/s]
  1%|▏         | 57/4250 [00:15<21:46,  3.21it/s]
  1%|▏         | 58/4250 [00:15<20:01,  3.49it/s]
  1%|▏         | 59/4250 [00:15<18:11,  3.84it/s]
  1%|▏         | 60/4250 [00:15<20:27,  3.41it/s]
  1%|▏         | 61/4250 [00:16<18:31,  3.77it/s]
  1%|▏         | 62/4250 [00:16<19:20,  3.61it/s]
  1%|▏         | 63/4250 [00:16<18:01,  3.87it/s]
  2%|▏         | 64/4250 [00:16<18:11,  3.83it/s]
  2%|▏         | 65/4250 [00:17<16:45,  4.16it/s]
  2%|▏         | 66/4250 [00:17<17:26,  4.00it/s]
  2%|▏         | 67/4250 [00:17<17:29,  3.98it/s]
  2%|▏         | 68/4250 [00:17<16:14,  4.29it/s]
  2%|▏         | 69/4250 [00:18<16:41,  4.18it/s]
  2%|▏         | 70/4250 [00:18<15:52,  4.39it/s]
  2%|▏         | 71/4250 [00:18<15:10,  4.59it/s]
  2%|▏         | 72/4250 [00:18<15:05,  4.61it/s]
  2%|▏         | 73/4250 [00:19<16:51,  4.13it/s]
  2%|▏         | 74/4250 [00:19<17:50,  3.90it/s]
  2%|▏         | 75/4250 [00:19<16:49,  4.14it/s]
  2%|▏         | 76/4250 [00:19<16:36,  4.19it/s]
  2%|▏         | 77/4250 [00:19<16:32,  4.21it/s]
  2%|▏         | 78/4250 [00:20<16:37,  4.18it/s]
  2%|▏         | 79/4250 [00:20<20:19,  3.42it/s]
  2%|▏         | 80/4250 [00:21<21:51,  3.18it/s]
  2%|▏         | 81/4250 [00:21<20:01,  3.47it/s]
  2%|▏         | 82/4250 [00:21<18:23,  3.78it/s]
  2%|▏         | 83/4250 [00:21<17:42,  3.92it/s]
  2%|▏         | 84/4250 [00:21<17:39,  3.93it/s]
  2%|▏         | 85/4250 [00:22<20:45,  3.34it/s]
  2%|▏         | 86/4250 [00:22<20:38,  3.36it/s]
  2%|▏         | 87/4250 [00:22<19:30,  3.56it/s]
  2%|▏         | 88/4250 [00:23<18:15,  3.80it/s]
  2%|▏         | 89/4250 [00:23<21:52,  3.17it/s]
  2%|▏         | 90/4250 [00:23<19:46,  3.51it/s]
  2%|▏         | 91/4250 [00:24<20:54,  3.32it/s]
  2%|▏         | 92/4250 [00:24<19:20,  3.58it/s]
  2%|▏         | 93/4250 [00:24<19:18,  3.59it/s]
  2%|▏         | 94/4250 [00:24<18:39,  3.71it/s]
  2%|▏         | 95/4250 [00:25<18:39,  3.71it/s]
  2%|▏         | 96/4250 [00:25<18:11,  3.81it/s]
  2%|▏         | 97/4250 [00:25<17:50,  3.88it/s]
  2%|▏         | 98/4250 [00:25<17:37,  3.93it/s]
  2%|▏         | 99/4250 [00:26<15:45,  4.39it/s]
  2%|▏         | 100/4250 [00:26<18:10,  3.80it/s]
  2%|▏         | 101/4250 [00:26<17:23,  3.98it/s]
  2%|▏         | 102/4250 [00:26<17:23,  3.97it/s]
  2%|▏         | 103/4250 [00:27<18:38,  3.71it/s]
  2%|▏         | 104/4250 [00:27<17:19,  3.99it/s]
  2%|▏         | 105/4250 [00:27<17:35,  3.93it/s]
  2%|▏         | 106/4250 [00:27<16:50,  4.10it/s]
  3%|▎         | 107/4250 [00:28<19:37,  3.52it/s]
  3%|▎         | 108/4250 [00:28<17:52,  3.86it/s]
  3%|▎         | 109/4250 [00:28<17:14,  4.00it/s]
  3%|▎         | 110/4250 [00:28<17:47,  3.88it/s]
  3%|▎         | 111/4250 [00:29<16:36,  4.15it/s]
  3%|▎         | 112/4250 [00:29<17:14,  4.00it/s]
  3%|▎         | 113/4250 [00:29<18:29,  3.73it/s]
  3%|▎         | 114/4250 [00:29<17:31,  3.93it/s]
  3%|▎         | 115/4250 [00:30<19:28,  3.54it/s]
  3%|▎         | 116/4250 [00:30<17:27,  3.95it/s]
  3%|▎         | 117/4250 [00:30<16:28,  4.18it/s]
  3%|▎         | 118/4250 [00:30<16:04,  4.28it/s]
  3%|▎         | 119/4250 [00:31<16:06,  4.28it/s]
  3%|▎         | 120/4250 [00:31<16:11,  4.25it/s]
  3%|▎         | 121/4250 [00:31<16:50,  4.09it/s]
  3%|▎         | 122/4250 [00:31<16:30,  4.17it/s]
  3%|▎         | 123/4250 [00:32<15:33,  4.42it/s]
  3%|▎         | 124/4250 [00:32<16:36,  4.14it/s]
  3%|▎         | 125/4250 [00:32<16:22,  4.20it/s]
  3%|▎         | 126/4250 [00:32<15:56,  4.31it/s]
  3%|▎         | 127/4250 [00:33<17:35,  3.91it/s]
  3%|▎         | 128/4250 [00:33<17:48,  3.86it/s]
  3%|▎         | 129/4250 [00:33<18:55,  3.63it/s]
  3%|▎         | 130/4250 [00:33<19:53,  3.45it/s]
  3%|▎         | 131/4250 [00:34<21:30,  3.19it/s]
  3%|▎         | 132/4250 [00:34<18:47,  3.65it/s]
  3%|▎         | 133/4250 [00:34<19:03,  3.60it/s]
  3%|▎         | 134/4250 [00:35<18:17,  3.75it/s]
  3%|▎         | 135/4250 [00:35<18:36,  3.69it/s]
  3%|▎         | 136/4250 [00:35<17:18,  3.96it/s]
  3%|▎         | 137/4250 [00:35<17:23,  3.94it/s]
  3%|▎         | 138/4250 [00:36<16:21,  4.19it/s]
  3%|▎         | 139/4250 [00:36<18:04,  3.79it/s]
  3%|▎         | 140/4250 [00:36<17:20,  3.95it/s]
  3%|▎         | 141/4250 [00:36<17:03,  4.01it/s]
  3%|▎         | 142/4250 [00:37<16:21,  4.18it/s]
  3%|▎         | 143/4250 [00:37<17:08,  3.99it/s]
  3%|▎         | 144/4250 [00:37<16:12,  4.22it/s]
  3%|▎         | 145/4250 [00:37<16:06,  4.25it/s]
  3%|▎         | 146/4250 [00:37<16:05,  4.25it/s]
  3%|▎         | 147/4250 [00:38<16:17,  4.20it/s]
  3%|▎         | 148/4250 [00:38<15:01,  4.55it/s]
  4%|▎         | 149/4250 [00:38<14:40,  4.66it/s]
  4%|▎         | 150/4250 [00:38<15:20,  4.45it/s]
  4%|▎         | 151/4250 [00:39<15:14,  4.48it/s]
  4%|▎         | 152/4250 [00:39<14:33,  4.69it/s]
  4%|▎         | 153/4250 [00:39<14:51,  4.59it/s]
  4%|▎         | 154/4250 [00:39<15:37,  4.37it/s]
  4%|▎         | 155/4250 [00:39<15:52,  4.30it/s]
  4%|▎         | 156/4250 [00:40<16:36,  4.11it/s]
  4%|▎         | 157/4250 [00:40<18:32,  3.68it/s]
  4%|▎         | 158/4250 [00:40<19:13,  3.55it/s]
  4%|▎         | 159/4250 [00:41<18:27,  3.69it/s]
  4%|▍         | 160/4250 [00:41<20:59,  3.25it/s]
  4%|▍         | 161/4250 [00:41<20:13,  3.37it/s]
  4%|▍         | 162/4250 [00:42<18:44,  3.63it/s]
  4%|▍         | 163/4250 [00:42<17:18,  3.94it/s]
  4%|▍         | 164/4250 [00:42<16:43,  4.07it/s]
  4%|▍         | 165/4250 [00:42<17:07,  3.97it/s]
  4%|▍         | 166/4250 [00:42<15:52,  4.29it/s]
  4%|▍         | 167/4250 [00:43<15:46,  4.31it/s]
  4%|▍         | 168/4250 [00:43<15:42,  4.33it/s]
  4%|▍         | 169/4250 [00:43<15:19,  4.44it/s]
  4%|▍         | 170/4250 [00:43<15:05,  4.51it/s]
  4%|▍         | 171/4250 [00:43<14:22,  4.73it/s]
  4%|▍         | 172/4250 [00:44<17:40,  3.84it/s]
  4%|▍         | 173/4250 [00:44<17:04,  3.98it/s]
  4%|▍         | 174/4250 [00:44<16:34,  4.10it/s]
  4%|▍         | 175/4250 [00:45<16:43,  4.06it/s]
  4%|▍         | 176/4250 [00:45<17:02,  3.98it/s]
  4%|▍         | 177/4250 [00:45<15:29,  4.38it/s]
  4%|▍         | 178/4250 [00:45<16:23,  4.14it/s]
  4%|▍         | 179/4250 [00:46<22:29,  3.02it/s]
  4%|▍         | 180/4250 [00:46<21:27,  3.16it/s]
  4%|▍         | 181/4250 [00:46<21:39,  3.13it/s]
  4%|▍         | 182/4250 [00:47<19:25,  3.49it/s]
  4%|▍         | 183/4250 [00:47<17:34,  3.86it/s]
  4%|▍         | 184/4250 [00:47<15:59,  4.24it/s]
  4%|▍         | 185/4250 [00:47<17:30,  3.87it/s]
  4%|▍         | 186/4250 [00:48<16:32,  4.10it/s]
  4%|▍         | 187/4250 [00:48<15:54,  4.26it/s]
  4%|▍         | 188/4250 [00:48<15:03,  4.50it/s]
  4%|▍         | 189/4250 [00:48<16:32,  4.09it/s]
  4%|▍         | 190/4250 [00:48<16:20,  4.14it/s]
  4%|▍         | 191/4250 [00:49<16:00,  4.23it/s]
  5%|▍         | 192/4250 [00:49<20:25,  3.31it/s]
  5%|▍         | 193/4250 [00:49<19:38,  3.44it/s]
  5%|▍         | 194/4250 [00:50<19:04,  3.54it/s]
  5%|▍         | 195/4250 [00:50<19:26,  3.48it/s]
  5%|▍         | 196/4250 [00:50<19:43,  3.43it/s]
  5%|▍         | 197/4250 [00:51<22:32,  3.00it/s]
  5%|▍         | 198/4250 [00:51<20:17,  3.33it/s]
  5%|▍         | 199/4250 [00:51<19:04,  3.54it/s]
  5%|▍         | 200/4250 [00:51<19:10,  3.52it/s]
  5%|▍         | 201/4250 [00:52<17:57,  3.76it/s]
  5%|▍         | 202/4250 [00:52<16:58,  3.98it/s]
  5%|▍         | 203/4250 [00:52<17:50,  3.78it/s]
  5%|▍         | 204/4250 [00:53<18:23,  3.67it/s]
  5%|▍         | 205/4250 [00:53<20:11,  3.34it/s]
  5%|▍         | 206/4250 [00:54<29:04,  2.32it/s]
  5%|▍         | 207/4250 [00:54<25:49,  2.61it/s]
  5%|▍         | 208/4250 [00:54<23:49,  2.83it/s]
  5%|▍         | 209/4250 [00:54<20:34,  3.27it/s]
  5%|▍         | 210/4250 [00:55<22:38,  2.97it/s]
  5%|▍         | 211/4250 [00:55<20:50,  3.23it/s]
  5%|▍         | 212/4250 [00:56<27:58,  2.41it/s]
  5%|▌         | 213/4250 [00:56<23:54,  2.81it/s]
  5%|▌         | 214/4250 [00:56<21:29,  3.13it/s]
  5%|▌         | 215/4250 [00:56<19:16,  3.49it/s]
  5%|▌         | 216/4250 [00:57<17:35,  3.82it/s]
  5%|▌         | 217/4250 [00:57<17:54,  3.75it/s]
  5%|▌         | 218/4250 [00:57<17:15,  3.89it/s]
  5%|▌         | 219/4250 [00:57<21:03,  3.19it/s]
  5%|▌         | 220/4250 [00:58<21:20,  3.15it/s]
  5%|▌         | 221/4250 [00:58<19:17,  3.48it/s]
  5%|▌         | 222/4250 [00:58<18:58,  3.54it/s]
  5%|▌         | 223/4250 [00:59<18:23,  3.65it/s]
  5%|▌         | 224/4250 [00:59<19:19,  3.47it/s]
  5%|▌         | 225/4250 [00:59<17:44,  3.78it/s]
  5%|▌         | 226/4250 [00:59<16:41,  4.02it/s]
  5%|▌         | 227/4250 [00:59<14:48,  4.53it/s]
  5%|▌         | 228/4250 [01:00<14:53,  4.50it/s]
  5%|▌         | 229/4250 [01:00<15:46,  4.25it/s]
  5%|▌         | 230/4250 [01:00<16:31,  4.05it/s]
  5%|▌         | 231/4250 [01:00<15:56,  4.20it/s]
  5%|▌         | 232/4250 [01:01<16:04,  4.17it/s]
  5%|▌         | 233/4250 [01:01<17:08,  3.90it/s]
  6%|▌         | 234/4250 [01:01<16:18,  4.11it/s]
  6%|▌         | 235/4250 [01:01<15:32,  4.30it/s]
  6%|▌         | 236/4250 [01:02<18:03,  3.70it/s]
  6%|▌         | 237/4250 [01:02<17:39,  3.79it/s]
  6%|▌         | 238/4250 [01:02<17:04,  3.92it/s]
  6%|▌         | 239/4250 [01:02<16:28,  4.06it/s]
  6%|▌         | 240/4250 [01:03<16:27,  4.06it/s]
  6%|▌         | 241/4250 [01:03<15:43,  4.25it/s]
  6%|▌         | 242/4250 [01:03<15:13,  4.39it/s]
  6%|▌         | 243/4250 [01:03<16:49,  3.97it/s]
  6%|▌         | 244/4250 [01:04<16:32,  4.04it/s]
  6%|▌         | 245/4250 [01:04<15:08,  4.41it/s]
  6%|▌         | 246/4250 [01:04<15:58,  4.18it/s]
  6%|▌         | 247/4250 [01:05<18:58,  3.52it/s]
  6%|▌         | 248/4250 [01:05<17:18,  3.85it/s]
  6%|▌         | 249/4250 [01:05<17:01,  3.92it/s]
  6%|▌         | 250/4250 [01:05<17:03,  3.91it/s]
  6%|▌         | 251/4250 [01:05<17:23,  3.83it/s]
  6%|▌         | 252/4250 [01:06<16:16,  4.10it/s]
  6%|▌         | 253/4250 [01:06<16:01,  4.16it/s]
  6%|▌         | 254/4250 [01:06<18:43,  3.56it/s]
  6%|▌         | 255/4250 [01:07<17:11,  3.87it/s]
  6%|▌         | 256/4250 [01:07<15:48,  4.21it/s]
  6%|▌         | 257/4250 [01:07<15:45,  4.22it/s]
  6%|▌         | 258/4250 [01:07<15:28,  4.30it/s]
  6%|▌         | 259/4250 [01:07<15:16,  4.35it/s]
  6%|▌         | 260/4250 [01:08<15:46,  4.22it/s]
  6%|▌         | 261/4250 [01:08<16:22,  4.06it/s]
  6%|▌         | 262/4250 [01:08<16:58,  3.92it/s]
  6%|▌         | 263/4250 [01:08<16:51,  3.94it/s]
  6%|▌         | 264/4250 [01:09<17:22,  3.82it/s]
  6%|▌         | 265/4250 [01:09<18:33,  3.58it/s]
  6%|▋         | 266/4250 [01:09<17:10,  3.87it/s]
  6%|▋         | 267/4250 [01:09<16:28,  4.03it/s]
  6%|▋         | 268/4250 [01:10<15:55,  4.17it/s]
  6%|▋         | 269/4250 [01:10<15:05,  4.39it/s]
  6%|▋         | 270/4250 [01:10<15:59,  4.15it/s]
  6%|▋         | 271/4250 [01:10<15:23,  4.31it/s]
  6%|▋         | 272/4250 [01:11<17:34,  3.77it/s]
  6%|▋         | 273/4250 [01:11<17:16,  3.84it/s]
  6%|▋         | 274/4250 [01:11<16:56,  3.91it/s]
  6%|▋         | 275/4250 [01:11<17:35,  3.77it/s]
  6%|▋         | 276/4250 [01:12<16:27,  4.02it/s]
  7%|▋         | 277/4250 [01:12<16:17,  4.07it/s]
  7%|▋         | 278/4250 [01:12<15:37,  4.24it/s]
  7%|▋         | 279/4250 [01:12<14:53,  4.45it/s]
  7%|▋         | 280/4250 [01:13<14:28,  4.57it/s]
  7%|▋         | 281/4250 [01:13<16:13,  4.08it/s]
  7%|▋         | 282/4250 [01:13<15:35,  4.24it/s]
  7%|▋         | 283/4250 [01:13<18:01,  3.67it/s]
  7%|▋         | 284/4250 [01:14<17:47,  3.72it/s]
  7%|▋         | 285/4250 [01:14<15:44,  4.20it/s]
  7%|▋         | 286/4250 [01:14<14:33,  4.54it/s]
  7%|▋         | 287/4250 [01:14<13:57,  4.73it/s]
  7%|▋         | 288/4250 [01:14<14:34,  4.53it/s]
  7%|▋         | 289/4250 [01:15<14:38,  4.51it/s]
  7%|▋         | 290/4250 [01:15<16:00,  4.12it/s]
  7%|▋         | 291/4250 [01:15<16:28,  4.01it/s]
  7%|▋         | 292/4250 [01:15<16:07,  4.09it/s]
  7%|▋         | 293/4250 [01:16<15:33,  4.24it/s]
  7%|▋         | 294/4250 [01:16<17:41,  3.73it/s]
  7%|▋         | 295/4250 [01:16<18:00,  3.66it/s]
  7%|▋         | 296/4250 [01:17<18:14,  3.61it/s]
  7%|▋         | 297/4250 [01:17<16:55,  3.89it/s]
  7%|▋         | 298/4250 [01:17<16:34,  3.97it/s]
  7%|▋         | 299/4250 [01:17<16:28,  4.00it/s]
  7%|▋         | 300/4250 [01:18<16:29,  3.99it/s]
  7%|▋         | 301/4250 [01:18<15:50,  4.16it/s]
  7%|▋         | 302/4250 [01:18<17:24,  3.78it/s]
  7%|▋         | 303/4250 [01:18<16:36,  3.96it/s]
  7%|▋         | 304/4250 [01:19<16:51,  3.90it/s]
  7%|▋         | 305/4250 [01:19<15:48,  4.16it/s]
  7%|▋         | 306/4250 [01:19<16:32,  3.97it/s]
  7%|▋         | 307/4250 [01:19<16:51,  3.90it/s]
  7%|▋         | 308/4250 [01:20<15:55,  4.13it/s]
  7%|▋         | 309/4250 [01:20<17:03,  3.85it/s]
  7%|▋         | 310/4250 [01:20<15:39,  4.19it/s]
  7%|▋         | 311/4250 [01:20<17:13,  3.81it/s]
  7%|▋         | 312/4250 [01:21<16:25,  4.00it/s]
  7%|▋         | 313/4250 [01:21<15:07,  4.34it/s]
  7%|▋         | 314/4250 [01:21<14:13,  4.61it/s]
  7%|▋         | 315/4250 [01:21<14:42,  4.46it/s]
  7%|▋         | 316/4250 [01:21<14:47,  4.43it/s]
  7%|▋         | 317/4250 [01:22<17:53,  3.67it/s]
  7%|▋         | 318/4250 [01:22<16:43,  3.92it/s]
  8%|▊         | 319/4250 [01:22<16:30,  3.97it/s]
  8%|▊         | 320/4250 [01:23<17:33,  3.73it/s]
  8%|▊         | 321/4250 [01:23<16:49,  3.89it/s]
  8%|▊         | 322/4250 [01:23<19:39,  3.33it/s]
  8%|▊         | 323/4250 [01:23<19:31,  3.35it/s]
  8%|▊         | 324/4250 [01:24<20:40,  3.17it/s]
  8%|▊         | 325/4250 [01:24<18:45,  3.49it/s]
  8%|▊         | 326/4250 [01:24<16:12,  4.04it/s]
  8%|▊         | 327/4250 [01:24<15:22,  4.25it/s]
  8%|▊         | 328/4250 [01:25<14:59,  4.36it/s]
  8%|▊         | 329/4250 [01:25<16:05,  4.06it/s]
  8%|▊         | 330/4250 [01:25<15:15,  4.28it/s]
  8%|▊         | 331/4250 [01:25<15:50,  4.12it/s]
  8%|▊         | 332/4250 [01:26<15:59,  4.08it/s]
  8%|▊         | 333/4250 [01:26<15:12,  4.29it/s]
  8%|▊         | 334/4250 [01:26<15:06,  4.32it/s]
  8%|▊         | 335/4250 [01:26<15:42,  4.15it/s]
  8%|▊         | 336/4250 [01:27<16:53,  3.86it/s]
  8%|▊         | 337/4250 [01:27<16:14,  4.02it/s]
  8%|▊         | 338/4250 [01:27<16:49,  3.87it/s]
  8%|▊         | 339/4250 [01:27<16:21,  3.98it/s]
  8%|▊         | 340/4250 [01:28<16:10,  4.03it/s]
  8%|▊         | 341/4250 [01:28<15:41,  4.15it/s]
  8%|▊         | 342/4250 [01:28<14:19,  4.55it/s]
  8%|▊         | 343/4250 [01:28<14:23,  4.53it/s]
  8%|▊         | 344/4250 [01:28<14:04,  4.62it/s]
  8%|▊         | 345/4250 [01:29<14:13,  4.57it/s]
  8%|▊         | 346/4250 [01:29<13:44,  4.74it/s]
  8%|▊         | 347/4250 [01:29<15:11,  4.28it/s]
  8%|▊         | 348/4250 [01:29<15:11,  4.28it/s]
  8%|▊         | 349/4250 [01:30<15:11,  4.28it/s]
  8%|▊         | 350/4250 [01:30<16:12,  4.01it/s]
  8%|▊         | 351/4250 [01:30<15:47,  4.11it/s]
  8%|▊         | 352/4250 [01:30<14:58,  4.34it/s]
  8%|▊         | 353/4250 [01:31<15:26,  4.20it/s]
  8%|▊         | 354/4250 [01:31<15:15,  4.26it/s]
  8%|▊         | 355/4250 [01:31<15:28,  4.20it/s]
  8%|▊         | 356/4250 [01:31<14:47,  4.39it/s]
  8%|▊         | 357/4250 [01:32<15:03,  4.31it/s]
  8%|▊         | 358/4250 [01:32<14:13,  4.56it/s]
  8%|▊         | 359/4250 [01:32<13:48,  4.69it/s]
  8%|▊         | 360/4250 [01:32<17:16,  3.75it/s]
  8%|▊         | 361/4250 [01:33<16:19,  3.97it/s]
  9%|▊         | 362/4250 [01:33<14:31,  4.46it/s]
  9%|▊         | 363/4250 [01:33<13:47,  4.69it/s]
  9%|▊         | 364/4250 [01:33<16:00,  4.05it/s]
  9%|▊         | 365/4250 [01:33<17:03,  3.79it/s]
  9%|▊         | 366/4250 [01:34<15:39,  4.13it/s]
  9%|▊         | 367/4250 [01:34<14:24,  4.49it/s]
  9%|▊         | 368/4250 [01:34<13:35,  4.76it/s]
  9%|▊         | 369/4250 [01:34<14:18,  4.52it/s]
  9%|▊         | 370/4250 [01:35<16:38,  3.89it/s]
  9%|▊         | 371/4250 [01:35<15:10,  4.26it/s]
  9%|▉         | 372/4250 [01:35<14:18,  4.52it/s]
  9%|▉         | 373/4250 [01:35<15:04,  4.29it/s]
  9%|▉         | 374/4250 [01:35<14:30,  4.45it/s]
  9%|▉         | 375/4250 [01:36<17:11,  3.76it/s]
  9%|▉         | 376/4250 [01:36<16:01,  4.03it/s]
  9%|▉         | 377/4250 [01:36<16:17,  3.96it/s]
  9%|▉         | 378/4250 [01:36<14:37,  4.41it/s]
  9%|▉         | 379/4250 [01:37<14:14,  4.53it/s]
  9%|▉         | 380/4250 [01:37<15:00,  4.30it/s]
  9%|▉         | 381/4250 [01:37<15:22,  4.19it/s]
  9%|▉         | 382/4250 [01:37<16:12,  3.98it/s]
  9%|▉         | 383/4250 [01:38<16:00,  4.03it/s]
  9%|▉         | 384/4250 [01:38<15:05,  4.27it/s]
  9%|▉         | 385/4250 [01:38<15:35,  4.13it/s]
  9%|▉         | 386/4250 [01:38<15:09,  4.25it/s]
  9%|▉         | 387/4250 [01:39<14:50,  4.34it/s]
  9%|▉         | 388/4250 [01:39<15:02,  4.28it/s]
  9%|▉         | 389/4250 [01:39<14:20,  4.49it/s]
  9%|▉         | 390/4250 [01:39<13:57,  4.61it/s]
  9%|▉         | 391/4250 [01:39<14:27,  4.45it/s]
  9%|▉         | 392/4250 [01:40<13:49,  4.65it/s]
  9%|▉         | 393/4250 [01:40<13:18,  4.83it/s]
  9%|▉         | 394/4250 [01:40<12:53,  4.98it/s]
  9%|▉         | 395/4250 [01:40<13:55,  4.61it/s]
  9%|▉         | 396/4250 [01:41<15:28,  4.15it/s]
  9%|▉         | 397/4250 [01:41<16:24,  3.91it/s]
  9%|▉         | 398/4250 [01:41<15:34,  4.12it/s]
  9%|▉         | 399/4250 [01:41<16:41,  3.84it/s]
  9%|▉         | 400/4250 [01:42<15:57,  4.02it/s]
  9%|▉         | 401/4250 [01:42<15:42,  4.08it/s]
  9%|▉         | 402/4250 [01:42<14:43,  4.36it/s]
  9%|▉         | 403/4250 [01:42<15:24,  4.16it/s]
 10%|▉         | 404/4250 [01:43<15:47,  4.06it/s]
 10%|▉         | 405/4250 [01:43<15:24,  4.16it/s]
 10%|▉         | 406/4250 [01:43<15:58,  4.01it/s]
 10%|▉         | 407/4250 [01:43<15:39,  4.09it/s]
 10%|▉         | 408/4250 [01:44<14:33,  4.40it/s]
 10%|▉         | 409/4250 [01:44<17:09,  3.73it/s]
 10%|▉         | 410/4250 [01:44<16:43,  3.83it/s]
 10%|▉         | 411/4250 [01:44<17:14,  3.71it/s]
 10%|▉         | 412/4250 [01:45<17:18,  3.70it/s]
 10%|▉         | 413/4250 [01:45<17:05,  3.74it/s]
 10%|▉         | 414/4250 [01:45<17:29,  3.65it/s]
 10%|▉         | 415/4250 [01:46<18:02,  3.54it/s]
 10%|▉         | 416/4250 [01:46<19:17,  3.31it/s]
 10%|▉         | 417/4250 [01:46<20:16,  3.15it/s]
 10%|▉         | 418/4250 [01:46<17:55,  3.56it/s]
 10%|▉         | 419/4250 [01:47<19:14,  3.32it/s]
 10%|▉         | 420/4250 [01:47<18:01,  3.54it/s]
 10%|▉         | 421/4250 [01:47<16:54,  3.77it/s]
 10%|▉         | 422/4250 [01:47<16:11,  3.94it/s]
 10%|▉         | 423/4250 [01:48<16:08,  3.95it/s]
 10%|▉         | 424/4250 [01:48<14:54,  4.28it/s]
 10%|█         | 425/4250 [01:48<14:18,  4.46it/s][INFO|trainer.py:805] 2024-08-30 21:56:36,656 >> The following columns in the evaluation set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: id, tokens, ner_tags. If id, tokens, ner_tags are not expected by `BertForTokenClassification.forward`,  you can safely ignore this message.
[INFO|trainer.py:3788] 2024-08-30 21:56:36,658 >> 
***** Running Evaluation *****
[INFO|trainer.py:3790] 2024-08-30 21:56:36,658 >>   Num examples = 6798
[INFO|trainer.py:3793] 2024-08-30 21:56:36,658 >>   Batch size = 8


  0%|          | 0/850 [00:00<?, ?it/s]

  1%|          | 10/850 [00:00<00:08, 98.30it/s]

  2%|▏         | 20/850 [00:00<00:09, 85.95it/s]

  3%|▎         | 29/850 [00:00<00:09, 85.06it/s]

  4%|▍         | 38/850 [00:00<00:09, 85.47it/s]

  6%|▌         | 47/850 [00:00<00:09, 84.58it/s]

  7%|▋         | 56/850 [00:00<00:10, 78.37it/s]

  8%|▊         | 64/850 [00:00<00:10, 77.70it/s]

  8%|▊         | 72/850 [00:00<00:10, 74.39it/s]

  9%|▉         | 80/850 [00:01<00:10, 74.24it/s]

 10%|█         | 89/850 [00:01<00:09, 76.30it/s]

 12%|█▏        | 98/850 [00:01<00:09, 78.01it/s]

 13%|█▎        | 108/850 [00:01<00:09, 81.89it/s]

 14%|█▍        | 117/850 [00:01<00:08, 81.96it/s]

 15%|█▍        | 127/850 [00:01<00:08, 84.21it/s]

 16%|█▌        | 136/850 [00:01<00:08, 83.16it/s]

 17%|█▋        | 145/850 [00:01<00:08, 79.13it/s]

 18%|█▊        | 153/850 [00:01<00:08, 78.99it/s]

 19%|█▉        | 162/850 [00:02<00:08, 81.23it/s]

 20%|██        | 171/850 [00:02<00:08, 82.29it/s]

 21%|██        | 180/850 [00:02<00:07, 83.94it/s]

 22%|██▏       | 189/850 [00:02<00:08, 81.23it/s]

 23%|██▎       | 198/850 [00:02<00:07, 82.48it/s]

 24%|██▍       | 207/850 [00:02<00:07, 81.00it/s]

 25%|██▌       | 216/850 [00:02<00:08, 78.97it/s]

 26%|██▋       | 225/850 [00:02<00:07, 81.69it/s]

 28%|██▊       | 234/850 [00:02<00:07, 83.51it/s]

 29%|██▊       | 243/850 [00:02<00:07, 81.58it/s]

 30%|██▉       | 252/850 [00:03<00:07, 82.44it/s]

 31%|███       | 262/850 [00:03<00:07, 83.56it/s]

 32%|███▏      | 271/850 [00:03<00:06, 84.66it/s]

 33%|███▎      | 280/850 [00:03<00:06, 85.74it/s]

 34%|███▍      | 289/850 [00:03<00:06, 86.37it/s]

 35%|███▌      | 298/850 [00:03<00:06, 86.47it/s]

 36%|███▌      | 307/850 [00:03<00:06, 84.84it/s]

 37%|███▋      | 316/850 [00:03<00:06, 83.69it/s]

 38%|███▊      | 325/850 [00:03<00:06, 84.26it/s]

 39%|███▉      | 334/850 [00:04<00:06, 84.48it/s]

 40%|████      | 343/850 [00:04<00:06, 84.34it/s]

 42%|████▏     | 353/850 [00:04<00:05, 86.48it/s]

 43%|████▎     | 362/850 [00:04<00:05, 83.81it/s]

 44%|████▎     | 371/850 [00:04<00:05, 84.14it/s]

 45%|████▍     | 380/850 [00:04<00:05, 80.65it/s]

 46%|████▌     | 389/850 [00:04<00:05, 82.30it/s]

 47%|████▋     | 398/850 [00:04<00:05, 79.21it/s]

 48%|████▊     | 408/850 [00:04<00:05, 83.80it/s]

 49%|████▉     | 418/850 [00:05<00:04, 86.99it/s]

 50%|█████     | 428/850 [00:05<00:04, 88.54it/s]

 51%|█████▏    | 437/850 [00:05<00:04, 86.84it/s]

 52%|█████▏    | 446/850 [00:05<00:04, 84.38it/s]

 54%|█████▎    | 455/850 [00:05<00:04, 84.52it/s]

 55%|█████▍    | 465/850 [00:05<00:04, 87.83it/s]

 56%|█████▌    | 475/850 [00:05<00:04, 90.15it/s]

 57%|█████▋    | 485/850 [00:05<00:04, 88.56it/s]

 58%|█████▊    | 494/850 [00:05<00:04, 88.49it/s]

 59%|█████▉    | 504/850 [00:06<00:03, 90.91it/s]

 60%|██████    | 514/850 [00:06<00:03, 90.17it/s]

 62%|██████▏   | 524/850 [00:06<00:03, 90.41it/s]

 63%|██████▎   | 534/850 [00:06<00:03, 86.47it/s]

 64%|██████▍   | 543/850 [00:06<00:03, 84.59it/s]

 65%|██████▍   | 552/850 [00:06<00:03, 83.56it/s]

 66%|██████▌   | 561/850 [00:06<00:03, 82.10it/s]

 67%|██████▋   | 570/850 [00:06<00:03, 80.03it/s]

 68%|██████▊   | 579/850 [00:06<00:03, 77.55it/s]

 69%|██████▉   | 588/850 [00:07<00:03, 78.59it/s]

 70%|███████   | 597/850 [00:07<00:03, 80.01it/s]

 71%|███████▏  | 606/850 [00:07<00:02, 81.43it/s]

 72%|███████▏  | 615/850 [00:07<00:02, 83.13it/s]

 74%|███████▎  | 625/850 [00:07<00:02, 85.27it/s]

 75%|███████▍  | 634/850 [00:07<00:02, 84.44it/s]

 76%|███████▌  | 643/850 [00:07<00:02, 85.83it/s]

 77%|███████▋  | 653/850 [00:07<00:02, 89.01it/s]

 78%|███████▊  | 662/850 [00:07<00:02, 88.83it/s]

 79%|███████▉  | 671/850 [00:08<00:02, 86.72it/s]

 80%|████████  | 680/850 [00:08<00:01, 85.40it/s]

 81%|████████  | 689/850 [00:08<00:01, 84.31it/s]

 82%|████████▏ | 698/850 [00:08<00:01, 84.10it/s]

 83%|████████▎ | 707/850 [00:08<00:01, 82.22it/s]

 84%|████████▍ | 716/850 [00:08<00:01, 82.16it/s]

 85%|████████▌ | 725/850 [00:08<00:01, 79.13it/s]

 86%|████████▋ | 735/850 [00:08<00:01, 82.74it/s]

 88%|████████▊ | 744/850 [00:08<00:01, 80.60it/s]

 89%|████████▊ | 753/850 [00:09<00:01, 80.30it/s]

 90%|████████▉ | 762/850 [00:09<00:01, 82.27it/s]

 91%|█████████ | 771/850 [00:09<00:00, 81.44it/s]

 92%|█████████▏| 780/850 [00:09<00:00, 80.66it/s]

 93%|█████████▎| 789/850 [00:09<00:00, 78.52it/s]

 94%|█████████▍| 798/850 [00:09<00:00, 81.16it/s]

 95%|█████████▍| 807/850 [00:09<00:00, 81.60it/s]

 96%|█████████▌| 816/850 [00:09<00:00, 80.79it/s]

 97%|█████████▋| 826/850 [00:09<00:00, 81.84it/s]

 98%|█████████▊| 835/850 [00:10<00:00, 82.47it/s]

 99%|█████████▉| 844/850 [00:10<00:00, 83.17it/s]
                                                  

                                                 

 10%|█         | 425/4250 [02:02<14:18,  4.46it/s]

100%|██████████| 850/850 [00:14<00:00, 83.17it/s]

                                                 [INFO|trainer.py:3478] 2024-08-30 21:56:50,913 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-425
[INFO|configuration_utils.py:472] 2024-08-30 21:56:50,914 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-425/config.json
[INFO|modeling_utils.py:2690] 2024-08-30 21:56:52,125 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-425/model.safetensors
[INFO|tokenization_utils_base.py:2574] 2024-08-30 21:56:52,126 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-425/tokenizer_config.json
[INFO|tokenization_utils_base.py:2583] 2024-08-30 21:56:52,126 >> 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 21:56:54,071 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
[INFO|tokenization_utils_base.py:2583] 2024-08-30 21:56:54,071 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json

 10%|█         | 426/4250 [02:06<5:49:07,  5.48s/it]
 10%|█         | 427/4250 [02:06<4:08:55,  3.91s/it]
 10%|█         | 428/4250 [02:06<2:58:35,  2.80s/it]
 10%|█         | 429/4250 [02:07<2:09:47,  2.04s/it]
 10%|█         | 430/4250 [02:07<1:34:28,  1.48s/it]
 10%|█         | 431/4250 [02:07<1:10:13,  1.10s/it]
 10%|█         | 432/4250 [02:07<52:57,  1.20it/s]  
 10%|█         | 433/4250 [02:08<44:00,  1.45it/s]
 10%|█         | 434/4250 [02:08<35:08,  1.81it/s]
 10%|█         | 435/4250 [02:08<29:02,  2.19it/s]
 10%|█         | 436/4250 [02:08<24:36,  2.58it/s]
 10%|█         | 437/4250 [02:08<21:08,  3.01it/s]
 10%|█         | 438/4250 [02:09<18:48,  3.38it/s]
 10%|█         | 439/4250 [02:09<17:50,  3.56it/s]
 10%|█         | 440/4250 [02:09<16:07,  3.94it/s]
 10%|█         | 441/4250 [02:09<15:15,  4.16it/s]
 10%|█         | 442/4250 [02:10<15:13,  4.17it/s]
 10%|█         | 443/4250 [02:10<13:33,  4.68it/s]
 10%|█         | 444/4250 [02:10<13:28,  4.71it/s]
 10%|█         | 445/4250 [02:10<14:04,  4.50it/s]
 10%|█         | 446/4250 [02:10<15:40,  4.04it/s]
 11%|█         | 447/4250 [02:11<15:52,  3.99it/s]
 11%|█         | 448/4250 [02:11<14:48,  4.28it/s]
 11%|█         | 449/4250 [02:11<16:28,  3.85it/s]
 11%|█         | 450/4250 [02:11<15:36,  4.06it/s]
 11%|█         | 451/4250 [02:12<16:05,  3.93it/s]
 11%|█         | 452/4250 [02:12<14:50,  4.27it/s]
 11%|█         | 453/4250 [02:12<16:32,  3.83it/s]
 11%|█         | 454/4250 [02:12<15:02,  4.20it/s]
 11%|█         | 455/4250 [02:13<14:32,  4.35it/s]
 11%|█         | 456/4250 [02:13<14:43,  4.29it/s]
 11%|█         | 457/4250 [02:13<14:25,  4.38it/s]
 11%|█         | 458/4250 [02:13<14:56,  4.23it/s]
 11%|█         | 459/4250 [02:14<15:10,  4.16it/s]
 11%|█         | 460/4250 [02:14<15:13,  4.15it/s]
 11%|█         | 461/4250 [02:14<14:27,  4.37it/s]
 11%|█         | 462/4250 [02:14<14:50,  4.25it/s]
 11%|█         | 463/4250 [02:14<14:23,  4.38it/s]
 11%|█         | 464/4250 [02:15<15:27,  4.08it/s]
 11%|█         | 465/4250 [02:15<15:11,  4.15it/s]
 11%|█         | 466/4250 [02:15<13:40,  4.61it/s]
 11%|█         | 467/4250 [02:15<14:22,  4.39it/s]
 11%|█         | 468/4250 [02:16<15:43,  4.01it/s]
 11%|█         | 469/4250 [02:16<15:14,  4.14it/s]
 11%|█         | 470/4250 [02:16<15:34,  4.05it/s]
 11%|█         | 471/4250 [02:16<15:31,  4.06it/s]
 11%|█         | 472/4250 [02:17<16:26,  3.83it/s]
 11%|█         | 473/4250 [02:17<19:00,  3.31it/s]
 11%|█         | 474/4250 [02:17<18:14,  3.45it/s]
 11%|█         | 475/4250 [02:18<20:13,  3.11it/s]
 11%|█         | 476/4250 [02:18<18:00,  3.49it/s]
 11%|█         | 477/4250 [02:18<16:28,  3.82it/s]
 11%|█         | 478/4250 [02:18<17:09,  3.66it/s]
 11%|█▏        | 479/4250 [02:19<15:33,  4.04it/s]
 11%|█▏        | 480/4250 [02:19<14:39,  4.29it/s]
 11%|█▏        | 481/4250 [02:19<16:24,  3.83it/s]
 11%|█▏        | 482/4250 [02:19<16:23,  3.83it/s]
 11%|█▏        | 483/4250 [02:20<16:34,  3.79it/s]
 11%|█▏        | 484/4250 [02:20<16:50,  3.73it/s]
 11%|█▏        | 485/4250 [02:20<16:14,  3.86it/s]
 11%|█▏        | 486/4250 [02:20<14:51,  4.22it/s]
 11%|█▏        | 487/4250 [02:21<14:57,  4.19it/s]
 11%|█▏        | 488/4250 [02:21<15:03,  4.16it/s]