Training in progress, epoch 1

README.md

@@ -0,0 +1,102 @@
+---
+library_name: transformers
+base_model: IVN-RIN/bioBIT
+tags:
+- token-classification
+- generated_from_trainer
+datasets:
+- Rodrigo1771/drugtemist-it-8-ner
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: output
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: Rodrigo1771/drugtemist-it-8-ner
+      type: Rodrigo1771/drugtemist-it-8-ner
+      config: DrugTEMIST Italian NER
+      split: validation
+      args: DrugTEMIST Italian NER
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.9122468659594986
+    - name: Recall
+      type: recall
+      value: 0.9157792836398838
+    - name: F1
+      type: f1
+      value: 0.9140096618357488
+    - name: Accuracy
+      type: accuracy
+      value: 0.9985198649701377
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# output
+
+This model is a fine-tuned version of [IVN-RIN/bioBIT](https://huggingface.co/IVN-RIN/bioBIT) on the Rodrigo1771/drugtemist-it-8-ner dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0085
+- Precision: 0.9122
+- Recall: 0.9158
+- F1: 0.9140
+- Accuracy: 0.9985
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 0.9990 | 494  | 0.0050          | 0.8807    | 0.9003 | 0.8904 | 0.9983   |
+| 0.0131        | 2.0    | 989  | 0.0046          | 0.9034    | 0.9148 | 0.9091 | 0.9985   |
+| 0.0037        | 2.9990 | 1483 | 0.0068          | 0.8972    | 0.9129 | 0.9050 | 0.9984   |
+| 0.0021        | 4.0    | 1978 | 0.0069          | 0.8807    | 0.9293 | 0.9044 | 0.9983   |
+| 0.0012        | 4.9990 | 2472 | 0.0073          | 0.8865    | 0.9226 | 0.9042 | 0.9984   |
+| 0.0006        | 6.0    | 2967 | 0.0077          | 0.8932    | 0.9313 | 0.9118 | 0.9984   |
+| 0.0004        | 6.9990 | 3461 | 0.0072          | 0.8978    | 0.9274 | 0.9124 | 0.9985   |
+| 0.0004        | 8.0    | 3956 | 0.0078          | 0.9138    | 0.9129 | 0.9133 | 0.9986   |
+| 0.0001        | 8.9990 | 4450 | 0.0084          | 0.9138    | 0.9138 | 0.9138 | 0.9986   |
+| 0.0001        | 9.9899 | 4940 | 0.0085          | 0.9122    | 0.9158 | 0.9140 | 0.9985   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,26 @@
+{
+    "epoch": 9.989888776541962,
+    "eval_accuracy": 0.9985198649701377,
+    "eval_f1": 0.9140096618357488,
+    "eval_loss": 0.008521749638020992,
+    "eval_precision": 0.9122468659594986,
+    "eval_recall": 0.9157792836398838,
+    "eval_runtime": 14.0315,
+    "eval_samples": 6798,
+    "eval_samples_per_second": 484.48,
+    "eval_steps_per_second": 60.578,
+    "predict_accuracy": 0.9982115932160268,
+    "predict_f1": 0.8982300884955752,
+    "predict_loss": 0.011793443001806736,
+    "predict_precision": 0.8874316939890711,
+    "predict_recall": 0.9092945128779395,
+    "predict_runtime": 27.4059,
+    "predict_samples_per_second": 532.915,
+    "predict_steps_per_second": 66.628,
+    "total_flos": 1.7928149517546354e+16,
+    "train_loss": 0.002201772875978276,
+    "train_runtime": 1511.1925,
+    "train_samples": 31619,
+    "train_samples_per_second": 209.232,
+    "train_steps_per_second": 3.269
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "IVN-RIN/bioBIT",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "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
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 9.989888776541962,
+    "eval_accuracy": 0.9985198649701377,
+    "eval_f1": 0.9140096618357488,
+    "eval_loss": 0.008521749638020992,
+    "eval_precision": 0.9122468659594986,
+    "eval_recall": 0.9157792836398838,
+    "eval_runtime": 14.0315,
+    "eval_samples": 6798,
+    "eval_samples_per_second": 484.48,
+    "eval_steps_per_second": 60.578
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3daec2c688aa0a46d9db382fbf86ed161eca7c49c159572a0d4bad0e523defb
+size 437380924

predict_results.json

@@ -0,0 +1,10 @@
+{
+    "predict_accuracy": 0.9982115932160268,
+    "predict_f1": 0.8982300884955752,
+    "predict_loss": 0.011793443001806736,
+    "predict_precision": 0.8874316939890711,
+    "predict_recall": 0.9092945128779395,
+    "predict_runtime": 27.4059,
+    "predict_samples_per_second": 532.915,
+    "predict_steps_per_second": 66.628
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tb/events.out.tfevents.1725539834.da2ff10c1388.1139.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7c63f332f72d5e8ce062a3570a23e513552485e35f9c3e717f676a61770d4de
+size 12077

tb/events.out.tfevents.1725541385.da2ff10c1388.1139.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a6b4673a2b54281137b214f6b38c5f460343279bcdc24f6bbcb40b41533804b
+size 560

tb/events.out.tfevents.1725541614.da2ff10c1388.8786.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4584b4d5777e5b7f96447a5414d6b2ef6ff8feef93772e32125e6e667e4a082c
+size 12077

tb/events.out.tfevents.1725543147.da2ff10c1388.8786.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:271b965f32982eddbd96116b6a0e21c0c303d7829ea9fa6ebdbd89621c357117
+size 560

tb/events.out.tfevents.1725543309.da2ff10c1388.16078.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15f77f4dbef1c3beb3875e5f7a213fc0182c8d07213f227ef8289a8f2a3570cf
+size 5576

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation": true,
+  "unk_token": "[UNK]"
+}

train.log

@@ -0,0 +1,320 @@
+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,
+)
+
+
+
+
+
+
+
+[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.
+
+
+
+/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]
+
                                                  
+
                                                 
 10%|█         | 479/4790 [02:24<19:05,  3.76it/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]

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.989888776541962,
+    "total_flos": 1.7928149517546354e+16,
+    "train_loss": 0.002201772875978276,
+    "train_runtime": 1511.1925,
+    "train_samples": 31619,
+    "train_samples_per_second": 209.232,
+    "train_steps_per_second": 3.269
+}

trainer_state.json

@@ -0,0 +1,225 @@
+{
+  "best_metric": 0.9140096618357488,
+  "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-4940",
+  "epoch": 9.989888776541962,
+  "eval_steps": 500,
+  "global_step": 4940,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9989888776541962,
+      "eval_accuracy": 0.9982926512594131,
+      "eval_f1": 0.8903781713738632,
+      "eval_loss": 0.004970682319253683,
+      "eval_precision": 0.8806818181818182,
+      "eval_recall": 0.9002904162633107,
+      "eval_runtime": 13.9779,
+      "eval_samples_per_second": 486.339,
+      "eval_steps_per_second": 60.81,
+      "step": 494
+    },
+    {
+      "epoch": 1.0111223458038423,
+      "grad_norm": 0.07247231900691986,
+      "learning_rate": 4.4939271255060735e-05,
+      "loss": 0.0131,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9985328486107504,
+      "eval_f1": 0.9090909090909091,
+      "eval_loss": 0.004644014406949282,
+      "eval_precision": 0.9034416826003824,
+      "eval_recall": 0.914811229428848,
+      "eval_runtime": 14.1023,
+      "eval_samples_per_second": 482.05,
+      "eval_steps_per_second": 60.274,
+      "step": 989
+    },
+    {
+      "epoch": 2.0222446916076846,
+      "grad_norm": 0.2395874410867691,
+      "learning_rate": 3.9878542510121455e-05,
+      "loss": 0.0037,
+      "step": 1000
+    },
+    {
+      "epoch": 2.998988877654196,
+      "eval_accuracy": 0.9983575694624772,
+      "eval_f1": 0.9049904030710172,
+      "eval_loss": 0.006752336397767067,
+      "eval_precision": 0.8972407231208372,
+      "eval_recall": 0.9128751210067764,
+      "eval_runtime": 13.9972,
+      "eval_samples_per_second": 485.67,
+      "eval_steps_per_second": 60.727,
+      "step": 1483
+    },
+    {
+      "epoch": 3.033367037411527,
+      "grad_norm": 0.0013774348190054297,
+      "learning_rate": 3.481781376518219e-05,
+      "loss": 0.0021,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.998338094001558,
+      "eval_f1": 0.9043805934997644,
+      "eval_loss": 0.006901361979544163,
+      "eval_precision": 0.8807339449541285,
+      "eval_recall": 0.9293320425943853,
+      "eval_runtime": 14.3886,
+      "eval_samples_per_second": 472.458,
+      "eval_steps_per_second": 59.075,
+      "step": 1978
+    },
+    {
+      "epoch": 4.044489383215369,
+      "grad_norm": 0.13544714450836182,
+      "learning_rate": 2.9757085020242914e-05,
+      "loss": 0.0012,
+      "step": 2000
+    },
+    {
+      "epoch": 4.998988877654196,
+      "eval_accuracy": 0.9984224876655414,
+      "eval_f1": 0.9041745730550285,
+      "eval_loss": 0.007279807701706886,
+      "eval_precision": 0.8865116279069768,
+      "eval_recall": 0.9225556631171346,
+      "eval_runtime": 14.0239,
+      "eval_samples_per_second": 484.743,
+      "eval_steps_per_second": 60.611,
+      "step": 2472
+    },
+    {
+      "epoch": 5.055611729019211,
+      "grad_norm": 0.001985458889976144,
+      "learning_rate": 2.4696356275303644e-05,
+      "loss": 0.0006,
+      "step": 2500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9984354713061543,
+      "eval_f1": 0.9118483412322275,
+      "eval_loss": 0.0077171181328594685,
+      "eval_precision": 0.89322191272052,
+      "eval_recall": 0.9312681510164569,
+      "eval_runtime": 14.0472,
+      "eval_samples_per_second": 483.939,
+      "eval_steps_per_second": 60.51,
+      "step": 2967
+    },
+    {
+      "epoch": 6.066734074823054,
+      "grad_norm": 0.015543761663138866,
+      "learning_rate": 1.9635627530364373e-05,
+      "loss": 0.0004,
+      "step": 3000
+    },
+    {
+      "epoch": 6.998988877654196,
+      "eval_accuracy": 0.998526356790444,
+      "eval_f1": 0.9123809523809524,
+      "eval_loss": 0.0071807485073804855,
+      "eval_precision": 0.8978444236176195,
+      "eval_recall": 0.9273959341723137,
+      "eval_runtime": 14.0553,
+      "eval_samples_per_second": 483.66,
+      "eval_steps_per_second": 60.475,
+      "step": 3461
+    },
+    {
+      "epoch": 7.077856420626896,
+      "grad_norm": 0.0003612766449805349,
+      "learning_rate": 1.4574898785425101e-05,
+      "loss": 0.0004,
+      "step": 3500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9985847831732018,
+      "eval_f1": 0.9133171912832929,
+      "eval_loss": 0.007767966017127037,
+      "eval_precision": 0.9137596899224806,
+      "eval_recall": 0.9128751210067764,
+      "eval_runtime": 14.0606,
+      "eval_samples_per_second": 483.479,
+      "eval_steps_per_second": 60.453,
+      "step": 3956
+    },
+    {
+      "epoch": 8.088978766430738,
+      "grad_norm": 0.0004361484607215971,
+      "learning_rate": 9.51417004048583e-06,
+      "loss": 0.0001,
+      "step": 4000
+    },
+    {
+      "epoch": 8.998988877654195,
+      "eval_accuracy": 0.9985523240716697,
+      "eval_f1": 0.9138431752178122,
+      "eval_loss": 0.00841750018298626,
+      "eval_precision": 0.9138431752178122,
+      "eval_recall": 0.9138431752178122,
+      "eval_runtime": 14.3137,
+      "eval_samples_per_second": 474.93,
+      "eval_steps_per_second": 59.384,
+      "step": 4450
+    },
+    {
+      "epoch": 9.100101112234581,
+      "grad_norm": 0.00019355813856236637,
+      "learning_rate": 4.453441295546559e-06,
+      "loss": 0.0001,
+      "step": 4500
+    },
+    {
+      "epoch": 9.989888776541962,
+      "eval_accuracy": 0.9985198649701377,
+      "eval_f1": 0.9140096618357488,
+      "eval_loss": 0.008521749638020992,
+      "eval_precision": 0.9122468659594986,
+      "eval_recall": 0.9157792836398838,
+      "eval_runtime": 14.4488,
+      "eval_samples_per_second": 470.491,
+      "eval_steps_per_second": 58.829,
+      "step": 4940
+    },
+    {
+      "epoch": 9.989888776541962,
+      "step": 4940,
+      "total_flos": 1.7928149517546354e+16,
+      "train_loss": 0.002201772875978276,
+      "train_runtime": 1511.1925,
+      "train_samples_per_second": 209.232,
+      "train_steps_per_second": 3.269
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4940,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.7928149517546354e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13556e6c97b2f39e25d5830ab0bc61ce81f807bcf643d150d23dd97c2f606c57
+size 5240