2024-09-05 13:34:48.258223: 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 13:34:48.275126: 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 13:34:48.295825: 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 13:34:48.302058: 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 13:34:48.316617: 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 13:34:49.554072: 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 13:34:51 - WARNING - __main__ -   Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False
09/05/2024 13:34:51 - 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%|          | 0.00/3.61k [00:00<?, ?B/s]
Downloading builder script: 100%|██████████| 3.61k/3.61k [00:00<00:00, 78.5kB/s]

Downloading data:   0%|          | 0.00/34.5M [00:00<?, ?B/s]
Downloading data:  30%|███       | 10.5M/34.5M [00:00<00:00, 27.4MB/s]
Downloading data:  91%|█████████ | 31.5M/34.5M [00:00<00:00, 68.8MB/s]
Downloading data: 100%|██████████| 34.5M/34.5M [00:00<00:00, 60.9MB/s]

Downloading data:   0%|          | 0.00/7.18M [00:00<?, ?B/s]
Downloading data: 100%|██████████| 7.18M/7.18M [00:00<00:00, 19.8MB/s]
Downloading data: 100%|██████████| 7.18M/7.18M [00:00<00:00, 19.5MB/s]

Downloading data:   0%|          | 0.00/12.7M [00:00<?, ?B/s]
Downloading data:  83%|████████▎ | 10.5M/12.7M [00:00<00:00, 37.4MB/s]
Downloading data: 100%|██████████| 12.7M/12.7M [00:00<00:00, 42.2MB/s]

Generating train split: 0 examples [00:00, ? examples/s]
Generating train split: 629 examples [00:00, 6265.46 examples/s]
Generating train split: 1556 examples [00:00, 6204.64 examples/s]
Generating train split: 2488 examples [00:00, 6205.95 examples/s]
Generating train split: 3406 examples [00:00, 6167.51 examples/s]
Generating train split: 4041 examples [00:00, 6213.89 examples/s]
Generating train split: 4694 examples [00:00, 6300.75 examples/s]
Generating train split: 5660 examples [00:00, 6223.79 examples/s]
Generating train split: 6591 examples [00:01, 6213.74 examples/s]
Generating train split: 7524 examples [00:01, 6214.38 examples/s]
Generating train split: 8150 examples [00:01, 6222.43 examples/s]
Generating train split: 8794 examples [00:01, 6276.86 examples/s]
Generating train split: 9718 examples [00:01, 6232.74 examples/s]
Generating train split: 10683 examples [00:01, 6278.76 examples/s]
Generating train split: 11320 examples [00:01, 6212.43 examples/s]
Generating train split: 11991 examples [00:01, 6336.29 examples/s]
Generating train split: 12937 examples [00:02, 6322.15 examples/s]
Generating train split: 13872 examples [00:02, 6287.58 examples/s]
Generating train split: 14779 examples [00:02, 6206.93 examples/s]
Generating train split: 15740 examples [00:02, 6267.13 examples/s]
Generating train split: 16655 examples [00:02, 6212.29 examples/s]
Generating train split: 17572 examples [00:02, 6178.55 examples/s]
Generating train split: 18496 examples [00:02, 6170.88 examples/s]
Generating train split: 19446 examples [00:03, 6215.86 examples/s]
Generating train split: 20393 examples [00:03, 6241.60 examples/s]
Generating train split: 21301 examples [00:03, 6143.32 examples/s]
Generating train split: 21969 examples [00:03, 6259.43 examples/s]
Generating train split: 22920 examples [00:03, 6282.76 examples/s]
Generating train split: 23802 examples [00:03, 6155.07 examples/s]
Generating train split: 24700 examples [00:03, 6097.66 examples/s]
Generating train split: 25324 examples [00:04, 6015.18 examples/s]
Generating train split: 25966 examples [00:04, 6110.40 examples/s]
Generating train split: 26860 examples [00:04, 6054.02 examples/s]
Generating train split: 27811 examples [00:04, 6144.38 examples/s]
Generating train split: 28686 examples [00:04, 6040.41 examples/s]
Generating train split: 29546 examples [00:04, 5939.45 examples/s]
Generating train split: 30200 examples [00:05, 3880.38 examples/s]
Generating train split: 30642 examples [00:05, 5887.40 examples/s]

Generating validation split: 0 examples [00:00, ? examples/s]
Generating validation split: 669 examples [00:00, 6669.57 examples/s]
Generating validation split: 1655 examples [00:00, 6291.68 examples/s]
Generating validation split: 2496 examples [00:00, 5956.66 examples/s]
Generating validation split: 3423 examples [00:00, 6043.91 examples/s]
Generating validation split: 4364 examples [00:00, 6121.84 examples/s]
Generating validation split: 5000 examples [00:00, 6039.18 examples/s]
Generating validation split: 5659 examples [00:00, 6184.58 examples/s]
Generating validation split: 6534 examples [00:01, 6056.08 examples/s]
Generating validation split: 6798 examples [00:01, 5980.17 examples/s]

Generating test split: 0 examples [00:00, ? examples/s]
Generating test split: 661 examples [00:00, 6589.02 examples/s]
Generating test split: 1355 examples [00:00, 6792.99 examples/s]
Generating test split: 2039 examples [00:00, 6809.84 examples/s]
Generating test split: 2808 examples [00:00, 7152.56 examples/s]
Generating test split: 3854 examples [00:00, 7067.95 examples/s]
Generating test split: 4567 examples [00:00, 7084.14 examples/s]
Generating test split: 5300 examples [00:00, 7156.26 examples/s]
Generating test split: 6078 examples [00:00, 7340.06 examples/s]
Generating test split: 6894 examples [00:00, 7582.90 examples/s]
Generating test split: 8000 examples [00:01, 7405.88 examples/s]
Generating test split: 8822 examples [00:01, 7620.84 examples/s]
Generating test split: 9898 examples [00:01, 7453.83 examples/s]
Generating test split: 11000 examples [00:01, 7326.21 examples/s]
Generating test split: 11833 examples [00:01, 7568.85 examples/s]
Generating test split: 12813 examples [00:01, 7209.43 examples/s]
Generating test split: 13913 examples [00:01, 7241.27 examples/s]
Generating test split: 14605 examples [00:02, 7213.79 examples/s]
[INFO|configuration_utils.py:733] 2024-09-05 13:35:02,046 >> 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] 2024-09-05 13:35:02,050 >> 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": "4.44.2",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 31102
}

[INFO|tokenization_utils_base.py:2269] 2024-09-05 13:35:02,109 >> loading file vocab.txt from cache at /root/.cache/huggingface/hub/models--IVN-RIN--bioBIT/snapshots/83755ed79ee254c11854e9f54a53679557271018/vocab.txt
[INFO|tokenization_utils_base.py:2269] 2024-09-05 13:35:02,109 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--IVN-RIN--bioBIT/snapshots/83755ed79ee254c11854e9f54a53679557271018/tokenizer.json
[INFO|tokenization_utils_base.py:2269] 2024-09-05 13:35:02,109 >> loading file added_tokens.json from cache at None
[INFO|tokenization_utils_base.py:2269] 2024-09-05 13:35:02,109 >> 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:2269] 2024-09-05 13:35:02,109 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--IVN-RIN--bioBIT/snapshots/83755ed79ee254c11854e9f54a53679557271018/tokenizer_config.json
/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|modeling_utils.py:3678] 2024-09-05 13:35:02,174 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--IVN-RIN--bioBIT/snapshots/83755ed79ee254c11854e9f54a53679557271018/model.safetensors
[INFO|modeling_utils.py:4497] 2024-09-05 13:35:02,231 >> 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:4509] 2024-09-05 13:35:02,231 >> 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%|          | 0/30642 [00:00<?, ? examples/s]
Map:   3%|▎         | 1000/30642 [00:00<00:03, 8169.45 examples/s]
Map:   7%|▋         | 2000/30642 [00:00<00:03, 8785.76 examples/s]
Map:  10%|▉         | 3000/30642 [00:00<00:03, 8977.75 examples/s]
Map:  13%|█▎        | 4000/30642 [00:00<00:03, 8751.64 examples/s]
Map:  16%|█▋        | 5000/30642 [00:00<00:03, 8345.11 examples/s]
Map:  20%|█▉        | 6000/30642 [00:00<00:02, 8334.77 examples/s]
Map:  23%|██▎       | 7000/30642 [00:00<00:02, 8612.88 examples/s]
Map:  26%|██▌       | 8000/30642 [00:00<00:02, 8927.73 examples/s]
Map:  29%|██▉       | 9000/30642 [00:01<00:02, 9082.34 examples/s]
Map:  33%|███▎      | 10000/30642 [00:01<00:02, 9177.53 examples/s]
Map:  39%|███▉      | 12000/30642 [00:01<00:01, 9509.77 examples/s]
Map:  46%|████▌     | 14000/30642 [00:01<00:01, 9728.49 examples/s]
Map:  49%|████▉     | 15000/30642 [00:01<00:01, 9655.08 examples/s]
Map:  55%|█████▌    | 17000/30642 [00:01<00:01, 9638.66 examples/s]
Map:  59%|█████▊    | 18000/30642 [00:01<00:01, 9561.14 examples/s]
Map:  65%|██████▌   | 20000/30642 [00:02<00:01, 9749.12 examples/s]
Map:  69%|██████▊   | 21000/30642 [00:02<00:00, 9704.18 examples/s]
Map:  72%|███████▏  | 22000/30642 [00:02<00:00, 9607.62 examples/s]
Map:  75%|███████▌  | 23000/30642 [00:02<00:00, 9693.36 examples/s]
Map:  78%|███████▊  | 24000/30642 [00:02<00:01, 5933.85 examples/s]
Map:  82%|████████▏ | 25000/30642 [00:02<00:00, 6544.96 examples/s]
Map:  85%|████████▍ | 26000/30642 [00:03<00:00, 6946.89 examples/s]
Map:  88%|████████▊ | 27000/30642 [00:03<00:00, 7453.27 examples/s]
Map:  91%|█████████▏| 28000/30642 [00:03<00:00, 8011.36 examples/s]
Map:  95%|█████████▍| 29000/30642 [00:03<00:00, 8395.26 examples/s]
Map:  98%|█████████▊| 30000/30642 [00:03<00:00, 8574.08 examples/s]
Map: 100%|██████████| 30642/30642 [00:03<00:00, 8582.41 examples/s]

Map:   0%|          | 0/6798 [00:00<?, ? examples/s]
Map:  15%|█▍        | 1000/6798 [00:00<00:00, 9831.13 examples/s]
Map:  29%|██▉       | 2000/6798 [00:00<00:00, 9753.45 examples/s]
Map:  59%|█████▉    | 4000/6798 [00:00<00:00, 10236.82 examples/s]
Map:  88%|████████▊ | 6000/6798 [00:00<00:00, 9421.82 examples/s] 
Map: 100%|██████████| 6798/6798 [00:00<00:00, 9492.30 examples/s]

Map:   0%|          | 0/14605 [00:00<?, ? examples/s]
Map:  14%|█▎        | 2000/14605 [00:00<00:01, 10766.18 examples/s]
Map:  27%|██▋       | 4000/14605 [00:00<00:01, 10245.05 examples/s]
Map:  41%|████      | 6000/14605 [00:00<00:00, 10485.63 examples/s]
Map:  55%|█████▍    | 8000/14605 [00:00<00:00, 10888.80 examples/s]
Map:  68%|██████▊   | 10000/14605 [00:00<00:00, 10982.67 examples/s]
Map:  82%|████████▏ | 12000/14605 [00:01<00:00, 11287.38 examples/s]
Map:  96%|█████████▌| 14000/14605 [00:01<00:00, 10907.87 examples/s]
Map: 100%|██████████| 14605/14605 [00:01<00:00, 10808.27 examples/s]
/content/dissertation/scripts/ner/run_ner_train.py:397: FutureWarning: load_metric is deprecated and will be removed in the next major version of datasets. Use 'evaluate.load' instead, from the new library 🤗 Evaluate: https://huggingface.co/docs/evaluate
  metric = load_metric("seqeval", trust_remote_code=True)
[INFO|trainer.py:811] 2024-09-05 13:35:08,966 >> The following columns in the training set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: ner_tags, id, tokens. If ner_tags, id, tokens are not expected by `BertForTokenClassification.forward`,  you can safely ignore this message.
[INFO|trainer.py:2134] 2024-09-05 13:35:09,528 >> ***** Running training *****
[INFO|trainer.py:2135] 2024-09-05 13:35:09,528 >>   Num examples = 30,642
[INFO|trainer.py:2136] 2024-09-05 13:35:09,528 >>   Num Epochs = 10
[INFO|trainer.py:2137] 2024-09-05 13:35:09,528 >>   Instantaneous batch size per device = 32
[INFO|trainer.py:2140] 2024-09-05 13:35:09,528 >>   Total train batch size (w. parallel, distributed & accumulation) = 64
[INFO|trainer.py:2141] 2024-09-05 13:35:09,528 >>   Gradient Accumulation steps = 2
[INFO|trainer.py:2142] 2024-09-05 13:35:09,528 >>   Total optimization steps = 4,790
[INFO|trainer.py:2143] 2024-09-05 13:35:09,529 >>   Number of trainable parameters = 109,339,395

  0%|          | 0/4790 [00:00<?, ?it/s]
  0%|          | 1/4790 [00:01<1:20:56,  1.01s/it]
  0%|          | 2/4790 [00:01<50:37,  1.58it/s]  
  0%|          | 3/4790 [00:01<37:18,  2.14it/s]
  0%|          | 4/4790 [00:01<29:46,  2.68it/s]
  0%|          | 5/4790 [00:02<25:48,  3.09it/s]
  0%|          | 6/4790 [00:02<26:14,  3.04it/s]
  0%|          | 7/4790 [00:02<24:55,  3.20it/s]
  0%|          | 8/4790 [00:02<22:17,  3.57it/s]
  0%|          | 9/4790 [00:03<21:39,  3.68it/s]
  0%|          | 10/4790 [00:03<22:52,  3.48it/s]
  0%|          | 11/4790 [00:03<21:15,  3.75it/s]
  0%|          | 12/4790 [00:04<22:03,  3.61it/s]
  0%|          | 13/4790 [00:04<20:44,  3.84it/s]
  0%|          | 14/4790 [00:04<19:51,  4.01it/s]
  0%|          | 15/4790 [00:04<18:24,  4.32it/s]
  0%|          | 16/4790 [00:04<18:34,  4.28it/s]
  0%|          | 17/4790 [00:05<18:30,  4.30it/s]
  0%|          | 18/4790 [00:05<18:13,  4.37it/s]
  0%|          | 19/4790 [00:05<20:34,  3.86it/s]
  0%|          | 20/4790 [00:05<19:30,  4.07it/s]
  0%|          | 21/4790 [00:06<19:47,  4.02it/s]
  0%|          | 22/4790 [00:06<19:42,  4.03it/s]
  0%|          | 23/4790 [00:06<19:29,  4.08it/s]
  1%|          | 24/4790 [00:06<20:18,  3.91it/s]
  1%|          | 25/4790 [00:07<20:17,  3.91it/s]
  1%|          | 26/4790 [00:07<19:08,  4.15it/s]
  1%|          | 27/4790 [00:07<18:37,  4.26it/s]
  1%|          | 28/4790 [00:07<20:30,  3.87it/s]
  1%|          | 29/4790 [00:08<20:31,  3.86it/s]
  1%|          | 30/4790 [00:08<21:02,  3.77it/s]
  1%|          | 31/4790 [00:08<20:09,  3.93it/s]
  1%|          | 32/4790 [00:09<22:20,  3.55it/s]
  1%|          | 33/4790 [00:09<20:31,  3.86it/s]
  1%|          | 34/4790 [00:09<21:36,  3.67it/s]
  1%|          | 35/4790 [00:09<22:11,  3.57it/s]
  1%|          | 36/4790 [00:10<20:46,  3.81it/s]
  1%|          | 37/4790 [00:10<23:52,  3.32it/s]
  1%|          | 38/4790 [00:10<21:50,  3.63it/s]
  1%|          | 39/4790 [00:10<22:49,  3.47it/s]
  1%|          | 40/4790 [00:11<23:36,  3.35it/s]
  1%|          | 41/4790 [00:11<21:06,  3.75it/s]
  1%|          | 42/4790 [00:11<20:37,  3.84it/s]
  1%|          | 43/4790 [00:12<20:36,  3.84it/s]
  1%|          | 44/4790 [00:12<30:21,  2.61it/s]
  1%|          | 45/4790 [00:12<26:51,  2.94it/s]
  1%|          | 46/4790 [00:13<24:36,  3.21it/s]
  1%|          | 47/4790 [00:13<26:25,  2.99it/s]
  1%|          | 48/4790 [00:13<24:41,  3.20it/s]
  1%|          | 49/4790 [00:14<23:30,  3.36it/s]
  1%|          | 50/4790 [00:14<23:01,  3.43it/s]
  1%|          | 51/4790 [00:14<22:17,  3.54it/s]
  1%|          | 52/4790 [00:14<21:00,  3.76it/s]
  1%|          | 53/4790 [00:15<19:53,  3.97it/s]
  1%|          | 54/4790 [00:15<19:08,  4.12it/s]
  1%|          | 55/4790 [00:15<21:09,  3.73it/s]
  1%|          | 56/4790 [00:15<19:04,  4.14it/s]
  1%|          | 57/4790 [00:16<20:34,  3.84it/s]
  1%|          | 58/4790 [00:16<20:14,  3.90it/s]
  1%|          | 59/4790 [00:16<19:47,  3.98it/s]
  1%|▏         | 60/4790 [00:16<22:20,  3.53it/s]
  1%|▏         | 61/4790 [00:17<21:23,  3.68it/s]
  1%|▏         | 62/4790 [00:17<21:38,  3.64it/s]
  1%|▏         | 63/4790 [00:17<22:00,  3.58it/s]
  1%|▏         | 64/4790 [00:18<21:29,  3.67it/s]
  1%|▏         | 65/4790 [00:18<21:47,  3.61it/s]
  1%|▏         | 66/4790 [00:18<20:36,  3.82it/s]
  1%|▏         | 67/4790 [00:19<27:23,  2.87it/s]
  1%|▏         | 68/4790 [00:19<26:32,  2.97it/s]
  1%|▏         | 69/4790 [00:19<24:31,  3.21it/s]
  1%|▏         | 70/4790 [00:19<23:00,  3.42it/s]
  1%|▏         | 71/4790 [00:20<23:36,  3.33it/s]
  2%|▏         | 72/4790 [00:20<22:01,  3.57it/s]
  2%|▏         | 73/4790 [00:20<20:12,  3.89it/s]
  2%|▏         | 74/4790 [00:20<18:49,  4.17it/s]
  2%|▏         | 75/4790 [00:21<20:11,  3.89it/s]
  2%|▏         | 76/4790 [00:21<19:23,  4.05it/s]
  2%|▏         | 77/4790 [00:21<21:03,  3.73it/s]
  2%|▏         | 78/4790 [00:21<20:42,  3.79it/s]
  2%|▏         | 79/4790 [00:22<20:11,  3.89it/s]
  2%|▏         | 80/4790 [00:22<20:50,  3.77it/s]
  2%|▏         | 81/4790 [00:22<19:14,  4.08it/s]
  2%|▏         | 82/4790 [00:22<21:12,  3.70it/s]
  2%|▏         | 83/4790 [00:23<20:43,  3.78it/s]
  2%|▏         | 84/4790 [00:23<21:25,  3.66it/s]
  2%|▏         | 85/4790 [00:23<22:19,  3.51it/s]
  2%|▏         | 86/4790 [00:24<21:02,  3.72it/s]
  2%|▏         | 87/4790 [00:24<19:44,  3.97it/s]
  2%|▏         | 88/4790 [00:24<18:39,  4.20it/s]
  2%|▏         | 89/4790 [00:24<19:58,  3.92it/s]
  2%|▏         | 90/4790 [00:25<20:11,  3.88it/s]
  2%|▏         | 91/4790 [00:25<22:09,  3.53it/s]
  2%|▏         | 92/4790 [00:25<21:43,  3.60it/s]
  2%|▏         | 93/4790 [00:25<20:35,  3.80it/s]
  2%|▏         | 94/4790 [00:26<20:45,  3.77it/s]
  2%|▏         | 95/4790 [00:26<18:51,  4.15it/s]
  2%|▏         | 96/4790 [00:26<23:08,  3.38it/s]
  2%|▏         | 97/4790 [00:26<21:22,  3.66it/s]
  2%|▏         | 98/4790 [00:27<21:11,  3.69it/s]
  2%|▏         | 99/4790 [00:27<23:06,  3.38it/s]
  2%|▏         | 100/4790 [00:27<22:34,  3.46it/s]
  2%|▏         | 101/4790 [00:28<22:19,  3.50it/s]
  2%|▏         | 102/4790 [00:28<22:22,  3.49it/s]
  2%|▏         | 103/4790 [00:28<21:22,  3.65it/s]
  2%|▏         | 104/4790 [00:28<20:50,  3.75it/s]
  2%|▏         | 105/4790 [00:29<19:16,  4.05it/s]
  2%|▏         | 106/4790 [00:29<19:27,  4.01it/s]
  2%|▏         | 107/4790 [00:29<20:03,  3.89it/s]
  2%|▏         | 108/4790 [00:29<21:03,  3.70it/s]
  2%|▏         | 109/4790 [00:30<19:57,  3.91it/s]
  2%|▏         | 110/4790 [00:30<18:51,  4.14it/s]
  2%|▏         | 111/4790 [00:30<19:09,  4.07it/s]
  2%|▏         | 112/4790 [00:30<19:05,  4.08it/s]
  2%|▏         | 113/4790 [00:31<18:14,  4.27it/s]
  2%|▏         | 114/4790 [00:31<18:41,  4.17it/s]
  2%|▏         | 115/4790 [00:31<17:37,  4.42it/s]
  2%|▏         | 116/4790 [00:31<18:21,  4.24it/s]
  2%|▏         | 117/4790 [00:32<20:53,  3.73it/s]
  2%|▏         | 118/4790 [00:32<20:04,  3.88it/s]
  2%|▏         | 119/4790 [00:32<21:01,  3.70it/s]
  3%|▎         | 120/4790 [00:32<19:06,  4.07it/s]
  3%|▎         | 121/4790 [00:33<20:35,  3.78it/s]
  3%|▎         | 122/4790 [00:33<21:02,  3.70it/s]
  3%|▎         | 123/4790 [00:33<24:04,  3.23it/s]
  3%|▎         | 124/4790 [00:34<21:34,  3.60it/s]
  3%|▎         | 125/4790 [00:34<21:45,  3.57it/s]
  3%|▎         | 126/4790 [00:34<21:13,  3.66it/s]
  3%|▎         | 127/4790 [00:34<22:31,  3.45it/s]
  3%|▎         | 128/4790 [00:35<21:58,  3.54it/s]
  3%|▎         | 129/4790 [00:35<21:51,  3.55it/s]
  3%|▎         | 130/4790 [00:35<22:45,  3.41it/s]
  3%|▎         | 131/4790 [00:36<21:18,  3.64it/s]
  3%|▎         | 132/4790 [00:36<20:34,  3.77it/s]
  3%|▎         | 133/4790 [00:36<20:01,  3.88it/s]
  3%|▎         | 134/4790 [00:36<22:14,  3.49it/s]
  3%|▎         | 135/4790 [00:37<21:41,  3.58it/s]
  3%|▎         | 136/4790 [00:37<25:05,  3.09it/s]
  3%|▎         | 137/4790 [00:37<23:27,  3.31it/s]
  3%|▎         | 138/4790 [00:38<24:07,  3.21it/s]
  3%|▎         | 139/4790 [00:38<24:49,  3.12it/s]
  3%|▎         | 140/4790 [00:38<22:58,  3.37it/s]
  3%|▎         | 141/4790 [00:38<21:06,  3.67it/s]
  3%|▎         | 142/4790 [00:39<20:26,  3.79it/s]
  3%|▎         | 143/4790 [00:39<21:11,  3.65it/s]
  3%|▎         | 144/4790 [00:39<19:58,  3.88it/s]
  3%|▎         | 145/4790 [00:39<18:59,  4.08it/s]
  3%|▎         | 146/4790 [00:40<18:44,  4.13it/s]
  3%|▎         | 147/4790 [00:40<20:34,  3.76it/s]
  3%|▎         | 148/4790 [00:40<19:30,  3.97it/s]
  3%|▎         | 149/4790 [00:41<21:12,  3.65it/s]
  3%|▎         | 150/4790 [00:41<21:36,  3.58it/s]
  3%|▎         | 151/4790 [00:41<20:19,  3.80it/s]
  3%|▎         | 152/4790 [00:41<20:08,  3.84it/s]
  3%|▎         | 153/4790 [00:42<21:57,  3.52it/s]
  3%|▎         | 154/4790 [00:42<22:08,  3.49it/s]
  3%|▎         | 155/4790 [00:42<20:34,  3.76it/s]
  3%|▎         | 156/4790 [00:42<22:06,  3.49it/s]
  3%|▎         | 157/4790 [00:43<20:52,  3.70it/s]
  3%|▎         | 158/4790 [00:43<19:31,  3.95it/s]
  3%|▎         | 159/4790 [00:43<21:04,  3.66it/s]
  3%|▎         | 160/4790 [00:44<22:25,  3.44it/s]
  3%|▎         | 161/4790 [00:44<21:51,  3.53it/s]
  3%|▎         | 162/4790 [00:44<20:32,  3.75it/s]
  3%|▎         | 163/4790 [00:44<19:43,  3.91it/s]
  3%|▎         | 164/4790 [00:45<20:41,  3.72it/s]
  3%|▎         | 165/4790 [00:45<19:02,  4.05it/s]
  3%|▎         | 166/4790 [00:45<20:47,  3.71it/s]
  3%|▎         | 167/4790 [00:45<22:56,  3.36it/s]
  4%|▎         | 168/4790 [00:46<23:05,  3.34it/s]
  4%|▎         | 169/4790 [00:46<21:23,  3.60it/s]
  4%|▎         | 170/4790 [00:46<21:05,  3.65it/s]
  4%|▎         | 171/4790 [00:47<20:26,  3.76it/s]
  4%|▎         | 172/4790 [00:47<19:43,  3.90it/s]
  4%|▎         | 173/4790 [00:47<21:36,  3.56it/s]
  4%|▎         | 174/4790 [00:47<21:23,  3.60it/s]
  4%|▎         | 175/4790 [00:48<20:53,  3.68it/s]
  4%|▎         | 176/4790 [00:48<20:12,  3.81it/s]
  4%|▎         | 177/4790 [00:48<19:38,  3.92it/s]
  4%|▎         | 178/4790 [00:48<19:02,  4.04it/s]
  4%|▎         | 179/4790 [00:49<18:51,  4.08it/s]
  4%|▍         | 180/4790 [00:49<17:55,  4.29it/s]
  4%|▍         | 181/4790 [00:49<20:31,  3.74it/s]
  4%|▍         | 182/4790 [00:49<19:12,  4.00it/s]
  4%|▍         | 183/4790 [00:50<19:09,  4.01it/s]
  4%|▍         | 184/4790 [00:50<17:15,  4.45it/s]
  4%|▍         | 185/4790 [00:50<21:16,  3.61it/s]
  4%|▍         | 186/4790 [00:50<21:56,  3.50it/s]
  4%|▍         | 187/4790 [00:51<21:13,  3.61it/s]
  4%|▍         | 188/4790 [00:51<19:37,  3.91it/s]
  4%|▍         | 189/4790 [00:51<19:49,  3.87it/s]
  4%|▍         | 190/4790 [00:51<19:27,  3.94it/s]
  4%|▍         | 191/4790 [00:52<18:22,  4.17it/s]
  4%|▍         | 192/4790 [00:52<19:45,  3.88it/s]
  4%|▍         | 193/4790 [00:52<19:55,  3.85it/s]
  4%|▍         | 194/4790 [00:52<19:56,  3.84it/s]
  4%|▍         | 195/4790 [00:53<19:34,  3.91it/s]
  4%|▍         | 196/4790 [00:53<18:31,  4.13it/s]
  4%|▍         | 197/4790 [00:53<17:44,  4.32it/s]
  4%|▍         | 198/4790 [00:53<19:39,  3.89it/s]
  4%|▍         | 199/4790 [00:54<19:52,  3.85it/s]
  4%|▍         | 200/4790 [00:54<19:50,  3.86it/s]
  4%|▍         | 201/4790 [00:54<20:10,  3.79it/s]
  4%|▍         | 202/4790 [00:54<18:09,  4.21it/s]
  4%|▍         | 203/4790 [00:55<18:39,  4.10it/s]
  4%|▍         | 204/4790 [00:55<23:44,  3.22it/s]
  4%|▍         | 205/4790 [00:55<21:02,  3.63it/s]
  4%|▍         | 206/4790 [00:56<20:28,  3.73it/s]
  4%|▍         | 207/4790 [00:56<19:35,  3.90it/s]
  4%|▍         | 208/4790 [00:56<19:23,  3.94it/s]
  4%|▍         | 209/4790 [00:56<20:38,  3.70it/s]
  4%|▍         | 210/4790 [00:57<20:28,  3.73it/s]
  4%|▍         | 211/4790 [00:57<21:45,  3.51it/s]
  4%|▍         | 212/4790 [00:57<19:52,  3.84it/s]
  4%|▍         | 213/4790 [00:57<19:25,  3.93it/s]
  4%|▍         | 214/4790 [00:58<18:19,  4.16it/s]
  4%|▍         | 215/4790 [00:58<19:07,  3.99it/s]
  5%|▍         | 216/4790 [00:58<19:16,  3.96it/s]
  5%|▍         | 217/4790 [00:58<20:18,  3.75it/s]
  5%|▍         | 218/4790 [00:59<21:08,  3.61it/s]
  5%|▍         | 219/4790 [00:59<19:39,  3.88it/s]
  5%|▍         | 220/4790 [00:59<19:09,  3.97it/s]
  5%|▍         | 221/4790 [00:59<18:31,  4.11it/s]
  5%|▍         | 222/4790 [01:00<17:59,  4.23it/s]
  5%|▍         | 223/4790 [01:00<18:22,  4.14it/s]
  5%|▍         | 224/4790 [01:00<18:34,  4.10it/s]
  5%|▍         | 225/4790 [01:00<18:29,  4.12it/s]
  5%|▍         | 226/4790 [01:01<22:07,  3.44it/s]
  5%|▍         | 227/4790 [01:01<21:26,  3.55it/s]
  5%|▍         | 228/4790 [01:01<20:48,  3.65it/s]
  5%|▍         | 229/4790 [01:02<20:04,  3.79it/s]
  5%|▍         | 230/4790 [01:02<19:58,  3.80it/s]
  5%|▍         | 231/4790 [01:02<23:39,  3.21it/s]
  5%|▍         | 232/4790 [01:02<22:14,  3.42it/s]
  5%|▍         | 233/4790 [01:03<22:43,  3.34it/s]
  5%|▍         | 234/4790 [01:03<22:02,  3.45it/s]
  5%|▍         | 235/4790 [01:03<20:39,  3.67it/s]
  5%|▍         | 236/4790 [01:04<23:49,  3.18it/s]
  5%|▍         | 237/4790 [01:04<24:54,  3.05it/s]
  5%|▍         | 238/4790 [01:04<24:56,  3.04it/s]
  5%|▍         | 239/4790 [01:05<24:16,  3.12it/s]
  5%|▌         | 240/4790 [01:05<22:37,  3.35it/s]
  5%|▌         | 241/4790 [01:05<26:11,  2.89it/s]
  5%|▌         | 242/4790 [01:06<23:40,  3.20it/s]
  5%|▌         | 243/4790 [01:06<24:51,  3.05it/s]
  5%|▌         | 244/4790 [01:06<24:47,  3.06it/s]
  5%|▌         | 245/4790 [01:07<22:59,  3.29it/s]
  5%|▌         | 246/4790 [01:07<22:32,  3.36it/s]
  5%|▌         | 247/4790 [01:07<20:16,  3.73it/s]
  5%|▌         | 248/4790 [01:07<19:43,  3.84it/s]
  5%|▌         | 249/4790 [01:08<21:41,  3.49it/s]
  5%|▌         | 250/4790 [01:08<25:08,  3.01it/s]
  5%|▌         | 251/4790 [01:08<25:17,  2.99it/s]
  5%|▌         | 252/4790 [01:09<22:38,  3.34it/s]
  5%|▌         | 253/4790 [01:09<20:45,  3.64it/s]
  5%|▌         | 254/4790 [01:09<19:55,  3.79it/s]
  5%|▌         | 255/4790 [01:09<19:58,  3.78it/s]
  5%|▌         | 256/4790 [01:10<20:54,  3.61it/s]
  5%|▌         | 257/4790 [01:10<22:47,  3.32it/s]
  5%|▌         | 258/4790 [01:10<20:47,  3.63it/s]
  5%|▌         | 259/4790 [01:10<18:58,  3.98it/s]
  5%|▌         | 260/4790 [01:11<21:14,  3.55it/s]
  5%|▌         | 261/4790 [01:11<20:03,  3.76it/s]
  5%|▌         | 262/4790 [01:11<21:05,  3.58it/s]
  5%|▌         | 263/4790 [01:12<21:12,  3.56it/s]
  6%|▌         | 264/4790 [01:12<20:51,  3.62it/s]
  6%|▌         | 265/4790 [01:12<22:23,  3.37it/s]
  6%|▌         | 266/4790 [01:13<21:56,  3.44it/s]
  6%|▌         | 267/4790 [01:13<22:31,  3.35it/s]
  6%|▌         | 268/4790 [01:13<21:57,  3.43it/s]
  6%|▌         | 269/4790 [01:13<22:48,  3.30it/s]
  6%|▌         | 270/4790 [01:14<22:38,  3.33it/s]
  6%|▌         | 271/4790 [01:14<21:37,  3.48it/s]
  6%|▌         | 272/4790 [01:14<19:41,  3.82it/s]
  6%|▌         | 273/4790 [01:14<18:42,  4.02it/s]
  6%|▌         | 274/4790 [01:15<18:50,  3.99it/s]
  6%|▌         | 275/4790 [01:15<19:49,  3.79it/s]
  6%|▌         | 276/4790 [01:15<17:32,  4.29it/s]
  6%|▌         | 277/4790 [01:15<16:46,  4.48it/s]
  6%|▌         | 278/4790 [01:16<16:39,  4.51it/s]
  6%|▌         | 279/4790 [01:16<18:49,  3.99it/s]
  6%|▌         | 280/4790 [01:16<17:38,  4.26it/s]
  6%|▌         | 281/4790 [01:16<16:33,  4.54it/s]
  6%|▌         | 282/4790 [01:17<20:05,  3.74it/s]
  6%|▌         | 283/4790 [01:17<18:27,  4.07it/s]
  6%|▌         | 284/4790 [01:17<18:32,  4.05it/s]
  6%|▌         | 285/4790 [01:17<18:28,  4.07it/s]
  6%|▌         | 286/4790 [01:18<18:14,  4.12it/s]
  6%|▌         | 287/4790 [01:18<21:27,  3.50it/s]
  6%|▌         | 288/4790 [01:18<21:52,  3.43it/s]
  6%|▌         | 289/4790 [01:18<20:33,  3.65it/s]
  6%|▌         | 290/4790 [01:19<21:24,  3.50it/s]
  6%|▌         | 291/4790 [01:19<20:36,  3.64it/s]
  6%|▌         | 292/4790 [01:19<19:57,  3.76it/s]
  6%|▌         | 293/4790 [01:20<24:15,  3.09it/s]
  6%|▌         | 294/4790 [01:20<22:18,  3.36it/s]
  6%|▌         | 295/4790 [01:20<23:18,  3.21it/s]
  6%|▌         | 296/4790 [01:21<25:14,  2.97it/s]
  6%|▌         | 297/4790 [01:21<24:18,  3.08it/s]
  6%|▌         | 298/4790 [01:21<21:32,  3.48it/s]
  6%|▌         | 299/4790 [01:21<20:51,  3.59it/s]
  6%|▋         | 300/4790 [01:22<19:20,  3.87it/s]
  6%|▋         | 301/4790 [01:22<19:39,  3.81it/s]
  6%|▋         | 302/4790 [01:22<19:31,  3.83it/s]
  6%|▋         | 303/4790 [01:22<20:12,  3.70it/s]
  6%|▋         | 304/4790 [01:23<19:28,  3.84it/s]
  6%|▋         | 305/4790 [01:23<19:17,  3.88it/s]
  6%|▋         | 306/4790 [01:23<17:51,  4.18it/s]
  6%|▋         | 307/4790 [01:23<18:10,  4.11it/s]
  6%|▋         | 308/4790 [01:24<23:32,  3.17it/s]
  6%|▋         | 309/4790 [01:24<21:51,  3.42it/s]
  6%|▋         | 310/4790 [01:24<20:53,  3.57it/s]
  6%|▋         | 311/4790 [01:25<20:05,  3.72it/s]
  7%|▋         | 312/4790 [01:25<19:17,  3.87it/s]
  7%|▋         | 313/4790 [01:25<19:03,  3.91it/s]
  7%|▋         | 314/4790 [01:25<21:26,  3.48it/s]
  7%|▋         | 315/4790 [01:26<20:37,  3.61it/s]
  7%|▋         | 316/4790 [01:26<20:04,  3.71it/s]
  7%|▋         | 317/4790 [01:26<19:26,  3.83it/s]
  7%|▋         | 318/4790 [01:27<20:44,  3.59it/s]
  7%|▋         | 319/4790 [01:27<19:54,  3.74it/s]
  7%|▋         | 320/4790 [01:27<22:32,  3.30it/s]
  7%|▋         | 321/4790 [01:27<21:02,  3.54it/s]
  7%|▋         | 322/4790 [01:28<21:39,  3.44it/s]
  7%|▋         | 323/4790 [01:28<21:36,  3.45it/s]
  7%|▋         | 324/4790 [01:28<20:08,  3.70it/s]
  7%|▋         | 325/4790 [01:29<20:12,  3.68it/s]
  7%|▋         | 326/4790 [01:29<18:55,  3.93it/s]
  7%|▋         | 327/4790 [01:29<18:47,  3.96it/s]
  7%|▋         | 328/4790 [01:29<17:11,  4.33it/s]
  7%|▋         | 329/4790 [01:29<19:41,  3.78it/s]
  7%|▋         | 330/4790 [01:30<19:27,  3.82it/s]
  7%|▋         | 331/4790 [01:30<19:14,  3.86it/s]
  7%|▋         | 332/4790 [01:30<19:45,  3.76it/s]
  7%|▋         | 333/4790 [01:31<19:15,  3.86it/s]
  7%|▋         | 334/4790 [01:31<19:12,  3.86it/s]
  7%|▋         | 335/4790 [01:31<19:52,  3.74it/s]
  7%|▋         | 336/4790 [01:31<21:35,  3.44it/s]
  7%|▋         | 337/4790 [01:32<25:21,  2.93it/s]
  7%|▋         | 338/4790 [01:32<24:09,  3.07it/s]
  7%|▋         | 339/4790 [01:32<21:21,  3.47it/s]
  7%|▋         | 340/4790 [01:33<21:04,  3.52it/s]
  7%|▋         | 341/4790 [01:33<21:03,  3.52it/s]
  7%|▋         | 342/4790 [01:33<18:26,  4.02it/s]
  7%|▋         | 343/4790 [01:33<17:48,  4.16it/s]
  7%|▋         | 344/4790 [01:34<16:38,  4.45it/s]
  7%|▋         | 345/4790 [01:34<18:20,  4.04it/s]
  7%|▋         | 346/4790 [01:34<18:51,  3.93it/s]
  7%|▋         | 347/4790 [01:34<18:24,  4.02it/s]
  7%|▋         | 348/4790 [01:35<18:23,  4.02it/s]
  7%|▋         | 349/4790 [01:35<19:05,  3.88it/s]
  7%|▋         | 350/4790 [01:35<18:45,  3.94it/s]
  7%|▋         | 351/4790 [01:35<19:40,  3.76it/s]
  7%|▋         | 352/4790 [01:36<20:27,  3.62it/s]
  7%|▋         | 353/4790 [01:36<20:13,  3.66it/s]
  7%|▋         | 354/4790 [01:36<21:46,  3.39it/s]
  7%|▋         | 355/4790 [01:37<20:23,  3.62it/s]
  7%|▋         | 356/4790 [01:37<20:12,  3.66it/s]
  7%|▋         | 357/4790 [01:37<20:34,  3.59it/s]
  7%|▋         | 358/4790 [01:37<20:09,  3.66it/s]
  7%|▋         | 359/4790 [01:38<21:14,  3.48it/s]
  8%|▊         | 360/4790 [01:38<20:40,  3.57it/s]
  8%|▊         | 361/4790 [01:38<19:59,  3.69it/s]
  8%|▊         | 362/4790 [01:39<23:39,  3.12it/s]
  8%|▊         | 363/4790 [01:39<23:06,  3.19it/s]
  8%|▊         | 364/4790 [01:39<21:44,  3.39it/s]
  8%|▊         | 365/4790 [01:39<20:51,  3.54it/s]
  8%|▊         | 366/4790 [01:40<20:37,  3.57it/s]
  8%|▊         | 367/4790 [01:40<20:49,  3.54it/s]
  8%|▊         | 368/4790 [01:40<19:58,  3.69it/s]
  8%|▊         | 369/4790 [01:41<23:59,  3.07it/s]
  8%|▊         | 370/4790 [01:41<24:54,  2.96it/s]
  8%|▊         | 371/4790 [01:41<23:32,  3.13it/s]
  8%|▊         | 372/4790 [01:42<24:14,  3.04it/s]
  8%|▊         | 373/4790 [01:42<21:57,  3.35it/s]
  8%|▊         | 374/4790 [01:42<20:08,  3.65it/s]
  8%|▊         | 375/4790 [01:43<23:55,  3.08it/s]
  8%|▊         | 376/4790 [01:43<23:20,  3.15it/s]
  8%|▊         | 377/4790 [01:43<20:48,  3.53it/s]
  8%|▊         | 378/4790 [01:43<20:24,  3.60it/s]
  8%|▊         | 379/4790 [01:44<19:31,  3.77it/s]
  8%|▊         | 380/4790 [01:44<19:40,  3.74it/s]
  8%|▊         | 381/4790 [01:44<18:52,  3.89it/s]
  8%|▊         | 382/4790 [01:44<17:12,  4.27it/s]
  8%|▊         | 383/4790 [01:44<16:23,  4.48it/s]
  8%|▊         | 384/4790 [01:45<16:58,  4.32it/s]
  8%|▊         | 385/4790 [01:45<19:00,  3.86it/s]
  8%|▊         | 386/4790 [01:45<20:09,  3.64it/s]
  8%|▊         | 387/4790 [01:46<21:31,  3.41it/s]
  8%|▊         | 388/4790 [01:46<20:03,  3.66it/s]
  8%|▊         | 389/4790 [01:46<22:50,  3.21it/s]
  8%|▊         | 390/4790 [01:46<20:16,  3.62it/s]
  8%|▊         | 391/4790 [01:47<21:09,  3.47it/s]
  8%|▊         | 392/4790 [01:47<19:30,  3.76it/s]
  8%|▊         | 393/4790 [01:47<17:51,  4.10it/s]
  8%|▊         | 394/4790 [01:47<17:49,  4.11it/s]
  8%|▊         | 395/4790 [01:48<18:08,  4.04it/s]
  8%|▊         | 396/4790 [01:48<17:36,  4.16it/s]
  8%|▊         | 397/4790 [01:48<19:35,  3.74it/s]
  8%|▊         | 398/4790 [01:49<20:26,  3.58it/s]
  8%|▊         | 399/4790 [01:49<20:14,  3.61it/s]
  8%|▊         | 400/4790 [01:49<18:53,  3.87it/s]
  8%|▊         | 401/4790 [01:49<19:57,  3.67it/s]
  8%|▊         | 402/4790 [01:50<18:32,  3.94it/s]
  8%|▊         | 403/4790 [01:50<18:04,  4.05it/s]
  8%|▊         | 404/4790 [01:50<17:58,  4.07it/s]
  8%|▊         | 405/4790 [01:50<18:34,  3.94it/s]
  8%|▊         | 406/4790 [01:51<19:41,  3.71it/s]
  8%|▊         | 407/4790 [01:51<18:06,  4.03it/s]
  9%|▊         | 408/4790 [01:51<19:27,  3.75it/s]
  9%|▊         | 409/4790 [01:51<18:26,  3.96it/s]
  9%|▊         | 410/4790 [01:52<18:19,  3.98it/s]
  9%|▊         | 411/4790 [01:52<19:04,  3.83it/s]
  9%|▊         | 412/4790 [01:52<22:31,  3.24it/s]
  9%|▊         | 413/4790 [01:53<22:04,  3.30it/s]
  9%|▊         | 414/4790 [01:53<20:44,  3.52it/s]
  9%|▊         | 415/4790 [01:53<19:50,  3.67it/s]
  9%|▊         | 416/4790 [01:53<20:30,  3.55it/s]
  9%|▊         | 417/4790 [01:54<19:17,  3.78it/s]
  9%|▊         | 418/4790 [01:54<17:48,  4.09it/s]
  9%|▊         | 419/4790 [01:54<17:43,  4.11it/s]
  9%|▉         | 420/4790 [01:54<17:57,  4.06it/s]
  9%|▉         | 421/4790 [01:55<18:55,  3.85it/s]
  9%|▉         | 422/4790 [01:55<18:49,  3.87it/s]
  9%|▉         | 423/4790 [01:55<18:09,  4.01it/s]
  9%|▉         | 424/4790 [01:55<18:01,  4.04it/s]
  9%|▉         | 425/4790 [01:56<18:29,  3.93it/s]
  9%|▉         | 426/4790 [01:56<18:20,  3.97it/s]
  9%|▉         | 427/4790 [01:56<17:21,  4.19it/s]
  9%|▉         | 428/4790 [01:56<17:53,  4.06it/s]
  9%|▉         | 429/4790 [01:57<17:32,  4.14it/s]
  9%|▉         | 430/4790 [01:57<16:50,  4.32it/s]
  9%|▉         | 431/4790 [01:57<16:49,  4.32it/s]
  9%|▉         | 432/4790 [01:57<16:52,  4.30it/s]
  9%|▉         | 433/4790 [01:57<16:16,  4.46it/s]
  9%|▉         | 434/4790 [01:58<17:52,  4.06it/s]
  9%|▉         | 435/4790 [01:58<17:23,  4.17it/s]
  9%|▉         | 436/4790 [01:58<16:56,  4.28it/s]
  9%|▉         | 437/4790 [01:58<19:06,  3.80it/s]
  9%|▉         | 438/4790 [01:59<19:18,  3.76it/s]
  9%|▉         | 439/4790 [01:59<18:51,  3.84it/s]
  9%|▉         | 440/4790 [01:59<19:20,  3.75it/s]
  9%|▉         | 441/4790 [02:00<20:58,  3.46it/s]
  9%|▉         | 442/4790 [02:00<20:20,  3.56it/s]
  9%|▉         | 443/4790 [02:00<20:12,  3.58it/s]
  9%|▉         | 444/4790 [02:00<18:59,  3.81it/s]
  9%|▉         | 445/4790 [02:01<17:37,  4.11it/s]
  9%|▉         | 446/4790 [02:01<19:02,  3.80it/s]
  9%|▉         | 447/4790 [02:01<17:38,  4.10it/s]
  9%|▉         | 448/4790 [02:01<17:54,  4.04it/s]
  9%|▉         | 449/4790 [02:02<16:45,  4.32it/s]
  9%|▉         | 450/4790 [02:02<17:07,  4.22it/s]
  9%|▉         | 451/4790 [02:02<16:06,  4.49it/s]
  9%|▉         | 452/4790 [02:02<19:32,  3.70it/s]
  9%|▉         | 453/4790 [02:03<19:30,  3.70it/s]
  9%|▉         | 454/4790 [02:03<18:34,  3.89it/s]
  9%|▉         | 455/4790 [02:03<17:23,  4.16it/s]
 10%|▉         | 456/4790 [02:03<18:24,  3.92it/s]
 10%|▉         | 457/4790 [02:04<25:31,  2.83it/s]
 10%|▉         | 458/4790 [02:04<23:07,  3.12it/s]
 10%|▉         | 459/4790 [02:05<23:20,  3.09it/s]
 10%|▉         | 460/4790 [02:05<22:18,  3.24it/s]
 10%|▉         | 461/4790 [02:05<21:41,  3.33it/s]
 10%|▉         | 462/4790 [02:05<20:15,  3.56it/s]
 10%|▉         | 463/4790 [02:06<24:21,  2.96it/s]
 10%|▉         | 464/4790 [02:06<21:39,  3.33it/s]
 10%|▉         | 465/4790 [02:06<19:06,  3.77it/s]
 10%|▉         | 466/4790 [02:06<18:17,  3.94it/s]
 10%|▉         | 467/4790 [02:07<18:49,  3.83it/s]
 10%|▉         | 468/4790 [02:07<18:49,  3.83it/s]
 10%|▉         | 469/4790 [02:07<18:00,  4.00it/s]
 10%|▉         | 470/4790 [02:07<18:25,  3.91it/s]
 10%|▉         | 471/4790 [02:08<20:39,  3.49it/s]
 10%|▉         | 472/4790 [02:08<20:58,  3.43it/s]
 10%|▉         | 473/4790 [02:08<20:46,  3.46it/s]
 10%|▉         | 474/4790 [02:09<19:24,  3.71it/s]
 10%|▉         | 475/4790 [02:09<17:54,  4.02it/s]
 10%|▉         | 476/4790 [02:09<18:35,  3.87it/s]
 10%|▉         | 477/4790 [02:09<17:33,  4.09it/s]
 10%|▉         | 478/4790 [02:10<20:27,  3.51it/s]
 10%|█         | 479/4790 [02:10<19:05,  3.76it/s][INFO|trainer.py:811] 2024-09-05 13:37:19,924 >> The following columns in the evaluation set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: ner_tags, id, tokens. If ner_tags, id, tokens are not expected by `BertForTokenClassification.forward`,  you can safely ignore this message.
[INFO|trainer.py:3819] 2024-09-05 13:37:19,927 >> 
***** Running Evaluation *****
[INFO|trainer.py:3821] 2024-09-05 13:37:19,927 >>   Num examples = 6798
[INFO|trainer.py:3824] 2024-09-05 13:37:19,927 >>   Batch size = 8


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

  1%|          | 9/850 [00:00<00:11, 75.89it/s]

  2%|▏         | 18/850 [00:00<00:10, 78.45it/s]

  3%|▎         | 27/850 [00:00<00:10, 80.37it/s]

  4%|▍         | 37/850 [00:00<00:09, 84.54it/s]

  5%|▌         | 46/850 [00:00<00:09, 85.60it/s]

  6%|▋         | 55/850 [00:00<00:10, 78.60it/s]

  8%|▊         | 64/850 [00:00<00:09, 79.44it/s]

  9%|▊         | 73/850 [00:00<00:10, 75.52it/s]

 10%|▉         | 81/850 [00:01<00:10, 76.28it/s]

 11%|█         | 90/850 [00:01<00:09, 80.04it/s]

 12%|█▏        | 99/850 [00:01<00:09, 82.32it/s]

 13%|█▎        | 109/850 [00:01<00:08, 84.86it/s]

 14%|█▍        | 118/850 [00:01<00:08, 85.25it/s]

 15%|█▍        | 127/850 [00:01<00:08, 86.48it/s]

 16%|█▌        | 136/850 [00:01<00:08, 85.42it/s]

 17%|█▋        | 145/850 [00:01<00:08, 81.53it/s]

 18%|█▊        | 154/850 [00:01<00:08, 82.60it/s]

 19%|█▉        | 163/850 [00:01<00:08, 84.65it/s]

 20%|██        | 172/850 [00:02<00:07, 85.43it/s]

 21%|██▏       | 181/850 [00:02<00:07, 85.66it/s]

 22%|██▏       | 190/850 [00:02<00:07, 84.23it/s]

 23%|██▎       | 199/850 [00:02<00:07, 85.01it/s]

 24%|██▍       | 208/850 [00:02<00:07, 83.44it/s]

 26%|██▌       | 217/850 [00:02<00:07, 81.88it/s]

 27%|██▋       | 227/850 [00:02<00:07, 84.16it/s]

 28%|██▊       | 237/850 [00:02<00:07, 86.15it/s]

 29%|██▉       | 246/850 [00:02<00:07, 84.46it/s]

 30%|███       | 256/850 [00:03<00:06, 88.24it/s]

 31%|███       | 265/850 [00:03<00:06, 87.70it/s]

 32%|███▏      | 275/850 [00:03<00:06, 88.16it/s]

 33%|███▎      | 284/850 [00:03<00:06, 87.65it/s]

 35%|███▍      | 294/850 [00:03<00:06, 88.09it/s]

 36%|███▌      | 303/850 [00:03<00:06, 86.09it/s]

 37%|███▋      | 313/850 [00:03<00:06, 87.89it/s]

 38%|███▊      | 322/850 [00:03<00:06, 87.79it/s]

 39%|███▉      | 331/850 [00:03<00:05, 87.25it/s]

 40%|████      | 340/850 [00:04<00:05, 87.67it/s]

 41%|████      | 349/850 [00:04<00:05, 86.98it/s]

 42%|████▏     | 358/850 [00:04<00:05, 85.62it/s]

 43%|████▎     | 367/850 [00:04<00:05, 85.83it/s]

 44%|████▍     | 376/850 [00:04<00:05, 84.60it/s]

 45%|████▌     | 385/850 [00:04<00:05, 82.20it/s]

 46%|████▋     | 394/850 [00:04<00:05, 80.28it/s]

 47%|████▋     | 403/850 [00:04<00:05, 81.93it/s]

 49%|████▊     | 413/850 [00:04<00:05, 85.88it/s]

 50%|████▉     | 423/850 [00:05<00:04, 87.54it/s]

 51%|█████     | 432/850 [00:05<00:04, 87.55it/s]

 52%|█████▏    | 441/850 [00:05<00:04, 86.85it/s]

 53%|█████▎    | 450/850 [00:05<00:04, 83.69it/s]

 54%|█████▍    | 460/850 [00:05<00:04, 86.80it/s]

 55%|█████▌    | 470/850 [00:05<00:04, 88.96it/s]

 56%|█████▋    | 480/850 [00:05<00:04, 90.23it/s]

 58%|█████▊    | 490/850 [00:05<00:04, 88.23it/s]

 59%|█████▉    | 500/850 [00:05<00:03, 89.90it/s]

 60%|██████    | 510/850 [00:05<00:03, 89.99it/s]

 61%|██████    | 520/850 [00:06<00:03, 90.30it/s]

 62%|██████▏   | 530/850 [00:06<00:03, 86.55it/s]

 63%|██████▎   | 539/850 [00:06<00:03, 85.36it/s]

 64%|██████▍   | 548/850 [00:06<00:03, 83.42it/s]

 66%|██████▌   | 557/850 [00:06<00:03, 83.02it/s]

 67%|██████▋   | 566/850 [00:06<00:03, 80.41it/s]

 68%|██████▊   | 575/850 [00:06<00:03, 82.97it/s]

 69%|██████▊   | 584/850 [00:06<00:03, 83.09it/s]

 70%|██████▉   | 593/850 [00:06<00:03, 84.13it/s]

 71%|███████   | 602/850 [00:07<00:02, 83.90it/s]

 72%|███████▏  | 611/850 [00:07<00:02, 84.78it/s]

 73%|███████▎  | 620/850 [00:07<00:02, 84.83it/s]

 74%|███████▍  | 629/850 [00:07<00:02, 84.00it/s]

 75%|███████▌  | 638/850 [00:07<00:02, 84.53it/s]

 76%|███████▌  | 647/850 [00:07<00:02, 85.90it/s]

 77%|███████▋  | 656/850 [00:07<00:02, 86.93it/s]

 78%|███████▊  | 666/850 [00:07<00:02, 88.25it/s]

 79%|███████▉  | 675/850 [00:07<00:02, 85.00it/s]

 80%|████████  | 684/850 [00:08<00:01, 85.36it/s]

 82%|████████▏ | 693/850 [00:08<00:01, 83.16it/s]

 83%|████████▎ | 702/850 [00:08<00:01, 83.49it/s]

 84%|████████▎ | 711/850 [00:08<00:01, 82.74it/s]

 85%|████████▍ | 720/850 [00:08<00:01, 83.13it/s]

 86%|████████▌ | 729/850 [00:08<00:01, 80.00it/s]

 87%|████████▋ | 738/850 [00:08<00:01, 80.48it/s]

 88%|████████▊ | 747/850 [00:08<00:01, 80.29it/s]

 89%|████████▉ | 756/850 [00:08<00:01, 80.87it/s]

 90%|█████████ | 765/850 [00:09<00:01, 82.87it/s]

 91%|█████████ | 774/850 [00:09<00:00, 82.26it/s]

 92%|█████████▏| 783/850 [00:09<00:00, 80.12it/s]

 93%|█████████▎| 792/850 [00:09<00:00, 79.96it/s]

 94%|█████████▍| 802/850 [00:09<00:00, 83.67it/s]

 95%|█████████▌| 811/850 [00:09<00:00, 81.61it/s]

 97%|█████████▋| 821/850 [00:09<00:00, 85.11it/s]

 98%|█████████▊| 830/850 [00:09<00:00, 84.40it/s]

 99%|█████████▊| 839/850 [00:09<00:00, 84.53it/s]

100%|█████████▉| 848/850 [00:10<00:00, 86.03it/s]
                                                  

                                                 

 10%|█         | 479/4790 [02:24<19:05,  3.76it/s]

100%|██████████| 850/850 [00:14<00:00, 86.03it/s]

                                                 [INFO|trainer.py:3503] 2024-09-05 13:37:33,956 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-479
[INFO|configuration_utils.py:472] 2024-09-05 13:37:33,957 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-479/config.json
[INFO|modeling_utils.py:2799] 2024-09-05 13:37:34,851 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-479/model.safetensors
[INFO|tokenization_utils_base.py:2684] 2024-09-05 13:37:34,852 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-479/tokenizer_config.json
[INFO|tokenization_utils_base.py:2693] 2024-09-05 13:37:34,852 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-479/special_tokens_map.json
[INFO|tokenization_utils_base.py:2684] 2024-09-05 13:37:36,650 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
[INFO|tokenization_utils_base.py:2693] 2024-09-05 13:37:36,650 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json

 10%|█         | 480/4790 [02:27<6:21:25,  5.31s/it]
 10%|█         | 481/4790 [02:27<4:31:30,  3.78s/it]
 10%|█         | 482/4790 [02:27<3:16:31,  2.74s/it]
 10%|█         | 483/4790 [02:28<2:25:49,  2.03s/it]
 10%|█         | 484/4790 [02:28<1:46:37,  1.49s/it]
 10%|█         | 485/4790 [02:28<1:22:39,  1.15s/it]
 10%|█         | 486/4790 [02:29<1:02:21,  1.15it/s]
 10%|█         | 487/4790 [02:29<50:31,  1.42it/s]  
 10%|█         | 488/4790 [02:29<41:55,  1.71it/s]
 10%|█         | 489/4790 [02:29<33:13,  2.16it/s]
 10%|█         | 490/4790 [02:30<29:22,  2.44it/s]
 10%|█         | 491/4790 [02:30<24:58,  2.87it/s]
 10%|█         | 492/4790 [02:30<22:15,  3.22it/s]
 10%|█         | 493/4790 [02:30<20:11,  3.55it/s]
 10%|█         | 494/4790 [02:31<20:24,  3.51it/s]
 10%|█         | 495/4790 [02:31<19:16,  3.71it/s]
 10%|█         | 496/4790 [02:31<19:33,  3.66it/s]
 10%|█         | 497/4790 [02:32<21:30,  3.33it/s]
 10%|█         | 498/4790 [02:32<22:35,  3.17it/s]
 10%|█         | 499/4790 [02:32<20:38,  3.46it/s]
 10%|█         | 500/4790 [02:32<19:03,  3.75it/s]
                                                  

 10%|█         | 500/4790 [02:32<19:03,  3.75it/s]
 10%|█         | 501/4790 [02:33<19:03,  3.75it/s]
 10%|█         | 502/4790 [02:33<19:37,  3.64it/s]
 11%|█         | 503/4790 [02:33<18:13,  3.92it/s]
 11%|█         | 504/4790 [02:34<21:59,  3.25it/s]
 11%|█         | 505/4790 [02:34<20:52,  3.42it/s]
 11%|█         | 506/4790 [02:34<20:21,  3.51it/s]
 11%|█         | 507/4790 [02:34<18:42,  3.82it/s]
 11%|█         | 508/4790 [02:35<22:26,  3.18it/s]
 11%|█         | 509/4790 [02:35<22:30,  3.17it/s]
 11%|█         | 510/4790 [02:35<21:05,  3.38it/s]
 11%|█         | 511/4790 [02:36<19:19,  3.69it/s]
 11%|█         | 512/4790 [02:36<19:44,  3.61it/s]
 11%|█         | 513/4790 [02:36<20:22,  3.50it/s]
 11%|█         | 514/4790 [02:36<19:52,  3.59it/s]
 11%|█         | 515/4790 [02:37<21:09,  3.37it/s]
 11%|█         | 516/4790 [02:37<20:38,  3.45it/s]
 11%|█         | 517/4790 [02:37<20:57,  3.40it/s]
 11%|█         | 518/4790 [02:38<19:47,  3.60it/s]
 11%|█         | 519/4790 [02:38<18:21,  3.88it/s]