Training in progress, epoch 1

README.md

@@ -0,0 +1,103 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: PlanTL-GOB-ES/bsc-bio-ehr-es
+tags:
+- token-classification
+- generated_from_trainer
+datasets:
+- Rodrigo1771/distemist-85-ner
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: output
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: Rodrigo1771/distemist-85-ner
+      type: Rodrigo1771/distemist-85-ner
+      config: DisTEMIST NER
+      split: validation
+      args: DisTEMIST NER
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.803175344384777
+    - name: Recall
+      type: recall
+      value: 0.8048666354702855
+    - name: F1
+      type: f1
+      value: 0.8040201005025126
+    - name: Accuracy
+      type: accuracy
+      value: 0.9764853694371592
+---
+
+<!-- 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 [PlanTL-GOB-ES/bsc-bio-ehr-es](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es) on the Rodrigo1771/distemist-85-ner dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1424
+- Precision: 0.8032
+- Recall: 0.8049
+- F1: 0.8040
+- Accuracy: 0.9765
+
+## 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 | 499  | 0.0739          | 0.7271    | 0.7953 | 0.7596 | 0.9731   |
+| 0.105         | 2.0    | 999  | 0.0908          | 0.7436    | 0.7890 | 0.7656 | 0.9729   |
+| 0.0448        | 2.9990 | 1498 | 0.0930          | 0.7676    | 0.7990 | 0.7830 | 0.9744   |
+| 0.0255        | 4.0    | 1998 | 0.1052          | 0.7806    | 0.7983 | 0.7894 | 0.9757   |
+| 0.0164        | 4.9990 | 2497 | 0.1100          | 0.7756    | 0.8007 | 0.7879 | 0.9750   |
+| 0.0112        | 6.0    | 2997 | 0.1266          | 0.7869    | 0.8124 | 0.7994 | 0.9768   |
+| 0.0073        | 6.9990 | 3496 | 0.1288          | 0.7929    | 0.8009 | 0.7969 | 0.9763   |
+| 0.0054        | 8.0    | 3996 | 0.1424          | 0.8032    | 0.8049 | 0.8040 | 0.9765   |
+| 0.0038        | 8.9990 | 4495 | 0.1455          | 0.7901    | 0.8042 | 0.7971 | 0.9765   |
+| 0.0028        | 9.9900 | 4990 | 0.1497          | 0.7898    | 0.8072 | 0.7984 | 0.9768   |
+
+
+### 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": 9.98998998998999,
+    "eval_accuracy": 0.9764853694371592,
+    "eval_f1": 0.8040201005025126,
+    "eval_loss": 0.14244574308395386,
+    "eval_precision": 0.803175344384777,
+    "eval_recall": 0.8048666354702855,
+    "eval_runtime": 14.2417,
+    "eval_samples": 6810,
+    "eval_samples_per_second": 478.175,
+    "eval_steps_per_second": 59.825,
+    "predict_accuracy": 0.9760745138469196,
+    "predict_f1": 0.7984671441135821,
+    "predict_loss": 0.12913450598716736,
+    "predict_precision": 0.7908163265306123,
+    "predict_recall": 0.8062674448109617,
+    "predict_runtime": 28.8701,
+    "predict_samples_per_second": 506.199,
+    "predict_steps_per_second": 63.284,
+    "total_flos": 1.5071241212671032e+16,
+    "train_loss": 0.022475468706272407,
+    "train_runtime": 1385.1143,
+    "train_samples": 31947,
+    "train_samples_per_second": 230.645,
+    "train_steps_per_second": 3.603
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-FARMACO",
+    "2": "I-FARMACO"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-FARMACO": 1,
+    "I-FARMACO": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 9.98998998998999,
+    "eval_accuracy": 0.9764853694371592,
+    "eval_f1": 0.8040201005025126,
+    "eval_loss": 0.14244574308395386,
+    "eval_precision": 0.803175344384777,
+    "eval_recall": 0.8048666354702855,
+    "eval_runtime": 14.2417,
+    "eval_samples": 6810,
+    "eval_samples_per_second": 478.175,
+    "eval_steps_per_second": 59.825
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:411d5d3193996fda415850b6703d2f10e22a3e8288871b4ff25d76e44ac7ac11
+size 496244100

predict_results.json

@@ -0,0 +1,10 @@
+{
+    "predict_accuracy": 0.9760745138469196,
+    "predict_f1": 0.7984671441135821,
+    "predict_loss": 0.12913450598716736,
+    "predict_precision": 0.7908163265306123,
+    "predict_recall": 0.8062674448109617,
+    "predict_runtime": 28.8701,
+    "predict_samples_per_second": 506.199,
+    "predict_steps_per_second": 63.284
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tb/events.out.tfevents.1725576279.2a66098fac87.2185.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26ae516745ddff30692f4c665463f21acb32fb831f7fd631ed58c86455b7b8df
+size 12158

tb/events.out.tfevents.1725577702.2a66098fac87.2185.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99c4e72fbff46ff4f2f01e01ca635b888064333c67fbc1e31ea417bc542ae659
+size 560

tb/events.out.tfevents.1725577909.2a66098fac87.9264.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:819018489721b1569a2c7c0819b30388ca1b355762fd69229a7cdaaf57e06733
+size 5645

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50261": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_len": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

train.log

@@ -0,0 +1,413 @@
+2024-09-05 23:11:20.272577: 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 23:11:20.290773: 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 23:11:20.312338: 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 23:11:20.318778: 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 23:11:20.334427: 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 23:11:21.616309: 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 23:11:23 - WARNING - __main__ -   Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False
+09/05/2024 23:11:23 - 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 23:11:41,247 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/config.json
+[INFO|configuration_utils.py:800] 2024-09-05 23:11:41,251 >> Model config RobertaConfig {
+  "_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-FARMACO",
+    "2": "I-FARMACO"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-FARMACO": 1,
+    "I-FARMACO": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}
+
+[INFO|configuration_utils.py:733] 2024-09-05 23:11:41,488 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/config.json
+[INFO|configuration_utils.py:800] 2024-09-05 23:11:41,489 >> Model config RobertaConfig {
+  "_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}
+
+[INFO|tokenization_utils_base.py:2269] 2024-09-05 23:11:41,500 >> loading file vocab.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/vocab.json
+[INFO|tokenization_utils_base.py:2269] 2024-09-05 23:11:41,500 >> loading file merges.txt from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/merges.txt
+[INFO|tokenization_utils_base.py:2269] 2024-09-05 23:11:41,500 >> loading file tokenizer.json from cache at None
+[INFO|tokenization_utils_base.py:2269] 2024-09-05 23:11:41,500 >> loading file added_tokens.json from cache at None
+[INFO|tokenization_utils_base.py:2269] 2024-09-05 23:11:41,500 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/special_tokens_map.json
+[INFO|tokenization_utils_base.py:2269] 2024-09-05 23:11:41,500 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/tokenizer_config.json
+[INFO|configuration_utils.py:733] 2024-09-05 23:11:41,501 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/config.json
+[INFO|configuration_utils.py:800] 2024-09-05 23:11:41,501 >> Model config RobertaConfig {
+  "_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}
+
+/usr/local/lib/python3.10/dist-packages/transformers/tokenization_utils_base.py:1601: FutureWarning: `clean_up_tokenization_spaces` was not set. It will be set to `True` by default. This behavior will be depracted in transformers v4.45, and will be then set to `False` by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884
+  warnings.warn(
+[INFO|configuration_utils.py:733] 2024-09-05 23:11:41,588 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/config.json
+[INFO|configuration_utils.py:800] 2024-09-05 23:11:41,590 >> Model config RobertaConfig {
+  "_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}
+
+[INFO|modeling_utils.py:3678] 2024-09-05 23:11:41,949 >> loading weights file pytorch_model.bin from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/pytorch_model.bin
+[INFO|modeling_utils.py:4497] 2024-09-05 23:11:42,028 >> Some weights of the model checkpoint at PlanTL-GOB-ES/bsc-bio-ehr-es were not used when initializing RobertaForTokenClassification: ['lm_head.bias', 'lm_head.decoder.bias', 'lm_head.decoder.weight', 'lm_head.dense.bias', 'lm_head.dense.weight', 'lm_head.layer_norm.bias', 'lm_head.layer_norm.weight']
+- This IS expected if you are initializing RobertaForTokenClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
+- This IS NOT expected if you are initializing RobertaForTokenClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
+[WARNING|modeling_utils.py:4509] 2024-09-05 23:11:42,028 >> Some weights of RobertaForTokenClassification were not initialized from the model checkpoint at PlanTL-GOB-ES/bsc-bio-ehr-es and are newly initialized: ['classifier.bias', 'classifier.weight']
+You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
+
+
+
+/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 23:11:48,913 >> The following columns in the training set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: tokens, ner_tags, id. If tokens, ner_tags, id are not expected by `RobertaForTokenClassification.forward`,  you can safely ignore this message.
+[INFO|trainer.py:2134] 2024-09-05 23:11:49,475 >> ***** Running training *****
+[INFO|trainer.py:2135] 2024-09-05 23:11:49,475 >>   Num examples = 29,797
+[INFO|trainer.py:2136] 2024-09-05 23:11:49,475 >>   Num Epochs = 10
+[INFO|trainer.py:2137] 2024-09-05 23:11:49,475 >>   Instantaneous batch size per device = 32
+[INFO|trainer.py:2140] 2024-09-05 23:11:49,475 >>   Total train batch size (w. parallel, distributed & accumulation) = 64
+[INFO|trainer.py:2141] 2024-09-05 23:11:49,475 >>   Gradient Accumulation steps = 2
+[INFO|trainer.py:2142] 2024-09-05 23:11:49,475 >>   Total optimization steps = 4,660
+[INFO|trainer.py:2143] 2024-09-05 23:11:49,476 >>   Number of trainable parameters = 124,055,043
+
  0%|          | 0/4660 [00:00<?, ?it/s]
  0%|          | 1/4660 [00:01<1:34:24,  1.22s/it]
  0%|          | 2/4660 [00:01<51:16,  1.51it/s]  
  0%|          | 3/4660 [00:01<34:20,  2.26it/s]
  0%|          | 4/4660 [00:01<25:37,  3.03it/s]
  0%|          | 5/4660 [00:02<21:49,  3.55it/s]
  0%|          | 6/4660 [00:02<19:39,  3.94it/s]
  0%|          | 7/4660 [00:02<20:00,  3.87it/s]
  0%|          | 8/4660 [00:02<19:47,  3.92it/s]
  0%|          | 9/4660 [00:02<19:43,  3.93it/s]
  0%|          | 10/4660 [00:03<17:45,  4.36it/s]
  0%|          | 11/4660 [00:03<17:00,  4.55it/s]
  0%|          | 12/4660 [00:03<17:36,  4.40it/s]
  0%|          | 13/4660 [00:03<17:26,  4.44it/s]
  0%|          | 14/4660 [00:04<20:38,  3.75it/s]
  0%|          | 15/4660 [00:04<21:00,  3.69it/s]
  0%|          | 16/4660 [00:04<19:19,  4.00it/s]
  0%|          | 17/4660 [00:04<17:39,  4.38it/s]
  0%|          | 18/4660 [00:05<20:50,  3.71it/s]
  0%|          | 19/4660 [00:05<19:27,  3.97it/s]
  0%|          | 20/4660 [00:05<18:28,  4.19it/s]
  0%|          | 21/4660 [00:05<20:44,  3.73it/s]
  0%|          | 22/4660 [00:06<19:03,  4.06it/s]
  0%|          | 23/4660 [00:06<17:53,  4.32it/s]
  1%|          | 24/4660 [00:06<17:54,  4.32it/s]
  1%|          | 25/4660 [00:06<18:33,  4.16it/s]
  1%|          | 26/4660 [00:07<17:33,  4.40it/s]
  1%|          | 27/4660 [00:07<17:51,  4.32it/s]
  1%|          | 28/4660 [00:07<16:34,  4.66it/s]
  1%|          | 29/4660 [00:07<15:57,  4.83it/s]
  1%|          | 30/4660 [00:07<16:07,  4.78it/s]
  1%|          | 31/4660 [00:08<16:14,  4.75it/s]
  1%|          | 32/4660 [00:08<16:14,  4.75it/s]
  1%|          | 33/4660 [00:08<16:45,  4.60it/s]
  1%|          | 34/4660 [00:08<19:39,  3.92it/s]
  1%|          | 35/4660 [00:09<18:34,  4.15it/s]
  1%|          | 36/4660 [00:09<18:26,  4.18it/s]
  1%|          | 37/4660 [00:09<18:43,  4.12it/s]
  1%|          | 38/4660 [00:09<20:40,  3.72it/s]
  1%|          | 39/4660 [00:10<19:12,  4.01it/s]
  1%|          | 40/4660 [00:10<18:31,  4.16it/s]
  1%|          | 41/4660 [00:10<17:29,  4.40it/s]
  1%|          | 42/4660 [00:10<19:12,  4.01it/s]
  1%|          | 43/4660 [00:11<18:12,  4.23it/s]
  1%|          | 44/4660 [00:11<21:29,  3.58it/s]
  1%|          | 45/4660 [00:11<21:53,  3.51it/s]
  1%|          | 46/4660 [00:11<20:42,  3.71it/s]
  1%|          | 47/4660 [00:12<19:22,  3.97it/s]
  1%|          | 48/4660 [00:12<23:12,  3.31it/s]
  1%|          | 49/4660 [00:12<21:22,  3.60it/s]
  1%|          | 50/4660 [00:12<19:14,  3.99it/s]
  1%|          | 51/4660 [00:13<18:44,  4.10it/s]
  1%|          | 52/4660 [00:13<17:39,  4.35it/s]
  1%|          | 53/4660 [00:13<18:35,  4.13it/s]
  1%|          | 54/4660 [00:13<18:55,  4.05it/s]
  1%|          | 55/4660 [00:14<20:05,  3.82it/s]
  1%|          | 56/4660 [00:14<21:45,  3.53it/s]
  1%|          | 57/4660 [00:14<20:49,  3.68it/s]
  1%|          | 58/4660 [00:15<20:21,  3.77it/s]
  1%|▏         | 59/4660 [00:15<19:43,  3.89it/s]
  1%|▏         | 60/4660 [00:15<19:56,  3.84it/s]
  1%|▏         | 61/4660 [00:15<19:42,  3.89it/s]
  1%|▏         | 62/4660 [00:16<19:03,  4.02it/s]
  1%|▏         | 63/4660 [00:16<18:41,  4.10it/s]
  1%|▏         | 64/4660 [00:16<18:09,  4.22it/s]
  1%|▏         | 65/4660 [00:16<18:14,  4.20it/s]
  1%|▏         | 66/4660 [00:16<18:04,  4.23it/s]
  1%|▏         | 67/4660 [00:17<17:33,  4.36it/s]
  1%|▏         | 68/4660 [00:17<17:10,  4.46it/s]
  1%|▏         | 69/4660 [00:17<18:06,  4.23it/s]
  2%|▏         | 70/4660 [00:17<18:00,  4.25it/s]
  2%|▏         | 71/4660 [00:18<16:22,  4.67it/s]
  2%|▏         | 72/4660 [00:18<15:20,  4.98it/s]
  2%|▏         | 73/4660 [00:18<16:40,  4.58it/s]
  2%|▏         | 74/4660 [00:18<16:15,  4.70it/s]
  2%|▏         | 75/4660 [00:18<16:16,  4.69it/s]
  2%|▏         | 76/4660 [00:19<16:27,  4.64it/s]
  2%|▏         | 77/4660 [00:19<17:08,  4.46it/s]
  2%|▏         | 78/4660 [00:19<18:20,  4.16it/s]
  2%|▏         | 79/4660 [00:19<19:21,  3.94it/s]
  2%|▏         | 80/4660 [00:20<21:07,  3.61it/s]
  2%|▏         | 81/4660 [00:20<19:12,  3.97it/s]
  2%|▏         | 82/4660 [00:20<18:12,  4.19it/s]
  2%|▏         | 83/4660 [00:20<17:32,  4.35it/s]
  2%|▏         | 84/4660 [00:21<17:42,  4.31it/s]
  2%|▏         | 85/4660 [00:21<17:29,  4.36it/s]
  2%|▏         | 86/4660 [00:21<16:29,  4.62it/s]
  2%|▏         | 87/4660 [00:21<18:52,  4.04it/s]
  2%|▏         | 88/4660 [00:21<16:59,  4.49it/s]
  2%|▏         | 89/4660 [00:22<18:24,  4.14it/s]
  2%|▏         | 90/4660 [00:22<20:54,  3.64it/s]
  2%|▏         | 91/4660 [00:23<24:11,  3.15it/s]
  2%|▏         | 92/4660 [00:23<21:45,  3.50it/s]
  2%|▏         | 93/4660 [00:23<22:19,  3.41it/s]
  2%|▏         | 94/4660 [00:23<19:40,  3.87it/s]
  2%|▏         | 95/4660 [00:24<19:48,  3.84it/s]
  2%|▏         | 96/4660 [00:24<17:48,  4.27it/s]
  2%|▏         | 97/4660 [00:24<19:11,  3.96it/s]
  2%|▏         | 98/4660 [00:24<22:58,  3.31it/s]
  2%|▏         | 99/4660 [00:25<22:14,  3.42it/s]
  2%|▏         | 100/4660 [00:25<19:49,  3.83it/s]
  2%|▏         | 101/4660 [00:25<25:31,  2.98it/s]
  2%|▏         | 102/4660 [00:26<26:36,  2.86it/s]
  2%|▏         | 103/4660 [00:26<23:54,  3.18it/s]
  2%|▏         | 104/4660 [00:26<22:52,  3.32it/s]
  2%|▏         | 105/4660 [00:27<21:54,  3.46it/s]
  2%|▏         | 106/4660 [00:27<20:32,  3.70it/s]
  2%|▏         | 107/4660 [00:27<18:56,  4.01it/s]
  2%|▏         | 108/4660 [00:27<19:02,  3.98it/s]
  2%|▏         | 109/4660 [00:27<19:34,  3.87it/s]
  2%|▏         | 110/4660 [00:28<20:13,  3.75it/s]
  2%|▏         | 111/4660 [00:28<20:10,  3.76it/s]
  2%|▏         | 112/4660 [00:28<22:03,  3.44it/s]
  2%|▏         | 113/4660 [00:29<20:01,  3.79it/s]
  2%|▏         | 114/4660 [00:29<18:18,  4.14it/s]
  2%|▏         | 115/4660 [00:29<17:37,  4.30it/s]
  2%|▏         | 116/4660 [00:29<18:08,  4.17it/s]
  3%|▎         | 117/4660 [00:29<18:09,  4.17it/s]
  3%|▎         | 118/4660 [00:30<17:44,  4.27it/s]
  3%|▎         | 119/4660 [00:30<17:01,  4.45it/s]
  3%|▎         | 120/4660 [00:30<18:03,  4.19it/s]
  3%|▎         | 121/4660 [00:31<22:14,  3.40it/s]
  3%|▎         | 122/4660 [00:31<18:58,  3.99it/s]
  3%|▎         | 123/4660 [00:31<17:39,  4.28it/s]
  3%|▎         | 124/4660 [00:31<18:21,  4.12it/s]
  3%|▎         | 125/4660 [00:32<20:21,  3.71it/s]
  3%|▎         | 126/4660 [00:32<19:01,  3.97it/s]
  3%|▎         | 127/4660 [00:32<19:01,  3.97it/s]
  3%|▎         | 128/4660 [00:33<25:02,  3.02it/s]
  3%|▎         | 129/4660 [00:33<24:47,  3.05it/s]
  3%|▎         | 130/4660 [00:33<22:15,  3.39it/s]
  3%|▎         | 131/4660 [00:33<19:59,  3.78it/s]
  3%|▎         | 132/4660 [00:33<18:21,  4.11it/s]
  3%|▎         | 133/4660 [00:34<17:37,  4.28it/s]
  3%|▎         | 134/4660 [00:34<16:23,  4.60it/s]
  3%|▎         | 135/4660 [00:34<19:48,  3.81it/s]
  3%|▎         | 136/4660 [00:34<18:55,  3.98it/s]
  3%|▎         | 137/4660 [00:35<20:53,  3.61it/s]
  3%|▎         | 138/4660 [00:35<19:36,  3.84it/s]
  3%|▎         | 139/4660 [00:35<18:25,  4.09it/s]
  3%|▎         | 140/4660 [00:35<17:29,  4.31it/s]
  3%|▎         | 141/4660 [00:36<17:08,  4.39it/s]
  3%|▎         | 142/4660 [00:36<17:51,  4.22it/s]
  3%|▎         | 143/4660 [00:36<18:51,  3.99it/s]
  3%|▎         | 144/4660 [00:36<17:07,  4.40it/s]
  3%|▎         | 145/4660 [00:37<27:46,  2.71it/s]
  3%|▎         | 146/4660 [00:37<26:18,  2.86it/s]
  3%|▎         | 147/4660 [00:38<22:38,  3.32it/s]
  3%|▎         | 148/4660 [00:38<20:50,  3.61it/s]
  3%|▎         | 149/4660 [00:38<19:53,  3.78it/s]
  3%|▎         | 150/4660 [00:38<18:28,  4.07it/s]
  3%|▎         | 151/4660 [00:38<17:53,  4.20it/s]
  3%|▎         | 152/4660 [00:39<18:02,  4.16it/s]
  3%|▎         | 153/4660 [00:39<19:24,  3.87it/s]
  3%|▎         | 154/4660 [00:39<20:03,  3.75it/s]
  3%|▎         | 155/4660 [00:39<19:18,  3.89it/s]
  3%|▎         | 156/4660 [00:40<18:15,  4.11it/s]
  3%|▎         | 157/4660 [00:40<17:25,  4.31it/s]
  3%|▎         | 158/4660 [00:40<18:31,  4.05it/s]
  3%|▎         | 159/4660 [00:40<18:12,  4.12it/s]
  3%|▎         | 160/4660 [00:41<25:45,  2.91it/s]
  3%|▎         | 161/4660 [00:41<22:53,  3.28it/s]
  3%|▎         | 162/4660 [00:42<23:45,  3.16it/s]
  3%|▎         | 163/4660 [00:42<24:15,  3.09it/s]
  4%|▎         | 164/4660 [00:42<22:14,  3.37it/s]
  4%|▎         | 165/4660 [00:42<19:54,  3.76it/s]
  4%|▎         | 166/4660 [00:42<17:49,  4.20it/s]
  4%|▎         | 167/4660 [00:43<17:15,  4.34it/s]
  4%|▎         | 168/4660 [00:43<16:43,  4.48it/s]
  4%|▎         | 169/4660 [00:43<18:37,  4.02it/s]
  4%|▎         | 170/4660 [00:43<17:49,  4.20it/s]
  4%|▎         | 171/4660 [00:44<21:50,  3.42it/s]
  4%|▎         | 172/4660 [00:44<20:03,  3.73it/s]
  4%|▎         | 173/4660 [00:45<29:51,  2.50it/s]
  4%|▎         | 174/4660 [00:45<26:06,  2.86it/s]
  4%|▍         | 175/4660 [00:45<24:26,  3.06it/s]
  4%|▍         | 176/4660 [00:45<22:17,  3.35it/s]
  4%|▍         | 177/4660 [00:46<20:35,  3.63it/s]
  4%|▍         | 178/4660 [00:46<20:38,  3.62it/s]
  4%|▍         | 179/4660 [00:46<20:16,  3.68it/s]
  4%|▍         | 180/4660 [00:47<21:00,  3.55it/s]
  4%|▍         | 181/4660 [00:47<20:15,  3.68it/s]
  4%|▍         | 182/4660 [00:47<21:45,  3.43it/s]
  4%|▍         | 183/4660 [00:47<20:07,  3.71it/s]
  4%|▍         | 184/4660 [00:48<18:09,  4.11it/s]
  4%|▍         | 185/4660 [00:48<16:50,  4.43it/s]
  4%|▍         | 186/4660 [00:48<18:14,  4.09it/s]
  4%|▍         | 187/4660 [00:48<17:38,  4.23it/s]
  4%|▍         | 188/4660 [00:48<16:53,  4.41it/s]
  4%|▍         | 189/4660 [00:49<16:06,  4.63it/s]
  4%|▍         | 190/4660 [00:49<15:06,  4.93it/s]
  4%|▍         | 191/4660 [00:49<17:09,  4.34it/s]
  4%|▍         | 192/4660 [00:49<17:16,  4.31it/s]
  4%|▍         | 193/4660 [00:50<19:17,  3.86it/s]
  4%|▍         | 194/4660 [00:50<19:16,  3.86it/s]
  4%|▍         | 195/4660 [00:50<19:39,  3.79it/s]
  4%|▍         | 196/4660 [00:51<20:57,  3.55it/s]
  4%|▍         | 197/4660 [00:51<19:27,  3.82it/s]
  4%|▍         | 198/4660 [00:51<20:08,  3.69it/s]
  4%|▍         | 199/4660 [00:51<20:15,  3.67it/s]
  4%|▍         | 200/4660 [00:51<18:11,  4.08it/s]
  4%|▍         | 201/4660 [00:52<17:03,  4.36it/s]
  4%|▍         | 202/4660 [00:52<15:46,  4.71it/s]
  4%|▍         | 203/4660 [00:52<17:26,  4.26it/s]
  4%|▍         | 204/4660 [00:52<17:39,  4.21it/s]
  4%|▍         | 205/4660 [00:53<17:49,  4.17it/s]
  4%|▍         | 206/4660 [00:53<17:01,  4.36it/s]
  4%|▍         | 207/4660 [00:53<19:51,  3.74it/s]
  4%|▍         | 208/4660 [00:53<17:27,  4.25it/s]
  4%|▍         | 209/4660 [00:54<18:04,  4.10it/s]
  5%|▍         | 210/4660 [00:54<17:50,  4.16it/s]
  5%|▍         | 211/4660 [00:54<23:08,  3.20it/s]
  5%|▍         | 212/4660 [00:55<22:53,  3.24it/s]
  5%|▍         | 213/4660 [00:55<20:12,  3.67it/s]
  5%|▍         | 214/4660 [00:55<17:57,  4.12it/s]
  5%|▍         | 215/4660 [00:55<17:20,  4.27it/s]
  5%|▍         | 216/4660 [00:55<18:25,  4.02it/s]
  5%|▍         | 217/4660 [00:56<16:47,  4.41it/s]
  5%|▍         | 218/4660 [00:56<18:09,  4.08it/s]
  5%|▍         | 219/4660 [00:56<16:55,  4.37it/s]
  5%|▍         | 220/4660 [00:56<17:04,  4.33it/s]
  5%|▍         | 221/4660 [00:57<16:34,  4.46it/s]
  5%|▍         | 222/4660 [00:57<18:02,  4.10it/s]
  5%|▍         | 223/4660 [00:57<17:44,  4.17it/s]
  5%|▍         | 224/4660 [00:57<16:55,  4.37it/s]
  5%|▍         | 225/4660 [00:57<15:56,  4.64it/s]
  5%|▍         | 226/4660 [00:58<15:52,  4.66it/s]
  5%|▍         | 227/4660 [00:58<19:42,  3.75it/s]
  5%|▍         | 228/4660 [00:58<18:53,  3.91it/s]
  5%|▍         | 229/4660 [00:59<19:43,  3.74it/s]
  5%|▍         | 230/4660 [00:59<19:11,  3.85it/s]
  5%|▍         | 231/4660 [00:59<17:37,  4.19it/s]
  5%|▍         | 232/4660 [00:59<18:03,  4.09it/s]
  5%|▌         | 233/4660 [00:59<16:43,  4.41it/s]
  5%|▌         | 234/4660 [01:00<16:36,  4.44it/s]
  5%|▌         | 235/4660 [01:00<16:11,  4.56it/s]
  5%|▌         | 236/4660 [01:00<16:56,  4.35it/s]
  5%|▌         | 237/4660 [01:01<25:56,  2.84it/s]
  5%|▌         | 238/4660 [01:01<23:02,  3.20it/s]
  5%|▌         | 239/4660 [01:01<21:23,  3.44it/s]
  5%|▌         | 240/4660 [01:02<21:35,  3.41it/s]
  5%|▌         | 241/4660 [01:02<23:04,  3.19it/s]
  5%|▌         | 242/4660 [01:02<20:12,  3.64it/s]
  5%|▌         | 243/4660 [01:02<19:45,  3.72it/s]
  5%|▌         | 244/4660 [01:03<17:13,  4.27it/s]
  5%|▌         | 245/4660 [01:03<19:53,  3.70it/s]
  5%|▌         | 246/4660 [01:03<21:04,  3.49it/s]
  5%|▌         | 247/4660 [01:03<20:00,  3.68it/s]
  5%|▌         | 248/4660 [01:04<19:46,  3.72it/s]
  5%|▌         | 249/4660 [01:04<18:03,  4.07it/s]
  5%|▌         | 250/4660 [01:04<17:19,  4.24it/s]
  5%|▌         | 251/4660 [01:04<18:34,  3.96it/s]
  5%|▌         | 252/4660 [01:05<18:59,  3.87it/s]
  5%|▌         | 253/4660 [01:05<17:01,  4.31it/s]
  5%|▌         | 254/4660 [01:05<17:06,  4.29it/s]
  5%|▌         | 255/4660 [01:05<16:51,  4.35it/s]
  5%|▌         | 256/4660 [01:06<17:18,  4.24it/s]
  6%|▌         | 257/4660 [01:06<17:30,  4.19it/s]
  6%|▌         | 258/4660 [01:06<17:11,  4.27it/s]
  6%|▌         | 259/4660 [01:06<16:27,  4.46it/s]
  6%|▌         | 260/4660 [01:06<16:39,  4.40it/s]
  6%|▌         | 261/4660 [01:07<15:55,  4.60it/s]
  6%|▌         | 262/4660 [01:07<16:32,  4.43it/s]
  6%|▌         | 263/4660 [01:07<19:06,  3.83it/s]
  6%|▌         | 264/4660 [01:08<20:06,  3.64it/s]
  6%|▌         | 265/4660 [01:08<21:50,  3.35it/s]
  6%|▌         | 266/4660 [01:08<20:52,  3.51it/s]
  6%|▌         | 267/4660 [01:08<20:13,  3.62it/s]
  6%|▌         | 268/4660 [01:09<18:47,  3.90it/s]
  6%|▌         | 269/4660 [01:09<17:36,  4.15it/s]
  6%|▌         | 270/4660 [01:09<17:29,  4.18it/s]
  6%|▌         | 271/4660 [01:09<17:57,  4.07it/s]
  6%|▌         | 272/4660 [01:10<17:37,  4.15it/s]
  6%|▌         | 273/4660 [01:10<17:53,  4.09it/s]
  6%|▌         | 274/4660 [01:10<17:00,  4.30it/s]
  6%|▌         | 275/4660 [01:10<16:35,  4.40it/s]
  6%|▌         | 276/4660 [01:10<16:42,  4.37it/s]
  6%|▌         | 277/4660 [01:11<18:03,  4.05it/s]
  6%|▌         | 278/4660 [01:11<19:03,  3.83it/s]
  6%|▌         | 279/4660 [01:11<17:11,  4.25it/s]
  6%|▌         | 280/4660 [01:11<17:08,  4.26it/s]
  6%|▌         | 281/4660 [01:12<17:17,  4.22it/s]
  6%|▌         | 282/4660 [01:12<18:01,  4.05it/s]
  6%|▌         | 283/4660 [01:13<33:01,  2.21it/s]
  6%|▌         | 284/4660 [01:13<28:47,  2.53it/s]
  6%|▌         | 285/4660 [01:13<27:31,  2.65it/s]
  6%|▌         | 286/4660 [01:14<23:58,  3.04it/s]
  6%|▌         | 287/4660 [01:14<21:26,  3.40it/s]
  6%|▌         | 288/4660 [01:14<19:32,  3.73it/s]
  6%|▌         | 289/4660 [01:14<18:26,  3.95it/s]
  6%|▌         | 290/4660 [01:15<18:12,  4.00it/s]
  6%|▌         | 291/4660 [01:15<18:36,  3.91it/s]
  6%|▋         | 292/4660 [01:15<18:20,  3.97it/s]
  6%|▋         | 293/4660 [01:15<16:32,  4.40it/s]
  6%|▋         | 294/4660 [01:15<17:01,  4.28it/s]
  6%|▋         | 295/4660 [01:16<16:54,  4.30it/s]
  6%|▋         | 296/4660 [01:16<19:33,  3.72it/s]
  6%|▋         | 297/4660 [01:16<18:00,  4.04it/s]
  6%|▋         | 298/4660 [01:16<16:52,  4.31it/s]
  6%|▋         | 299/4660 [01:17<18:22,  3.95it/s]
  6%|▋         | 300/4660 [01:17<19:28,  3.73it/s]
  6%|▋         | 301/4660 [01:17<18:59,  3.82it/s]
  6%|▋         | 302/4660 [01:18<18:53,  3.84it/s]
  7%|▋         | 303/4660 [01:18<17:42,  4.10it/s]
  7%|▋         | 304/4660 [01:18<17:11,  4.22it/s]
  7%|▋         | 305/4660 [01:18<18:49,  3.86it/s]
  7%|▋         | 306/4660 [01:18<16:58,  4.27it/s]
  7%|▋         | 307/4660 [01:19<17:22,  4.17it/s]
  7%|▋         | 308/4660 [01:19<18:16,  3.97it/s]
  7%|▋         | 309/4660 [01:19<18:57,  3.83it/s]
  7%|▋         | 310/4660 [01:20<17:44,  4.09it/s]
  7%|▋         | 311/4660 [01:20<18:09,  3.99it/s]
  7%|▋         | 312/4660 [01:20<17:54,  4.05it/s]
  7%|▋         | 313/4660 [01:20<17:42,  4.09it/s]
  7%|▋         | 314/4660 [01:20<17:19,  4.18it/s]
  7%|▋         | 315/4660 [01:21<18:42,  3.87it/s]
  7%|▋         | 316/4660 [01:21<17:06,  4.23it/s]
  7%|▋         | 317/4660 [01:21<15:49,  4.58it/s]
  7%|▋         | 318/4660 [01:21<15:00,  4.82it/s]
  7%|▋         | 319/4660 [01:22<15:03,  4.80it/s]
  7%|▋         | 320/4660 [01:22<14:26,  5.01it/s]
  7%|▋         | 321/4660 [01:22<17:21,  4.17it/s]
  7%|▋         | 322/4660 [01:22<16:51,  4.29it/s]
  7%|▋         | 323/4660 [01:23<18:51,  3.83it/s]
  7%|▋         | 324/4660 [01:23<21:04,  3.43it/s]
  7%|▋         | 325/4660 [01:23<21:24,  3.37it/s]
  7%|▋         | 326/4660 [01:24<20:49,  3.47it/s]
  7%|▋         | 327/4660 [01:24<19:49,  3.64it/s]
  7%|▋         | 328/4660 [01:24<21:37,  3.34it/s]
  7%|▋         | 329/4660 [01:24<22:11,  3.25it/s]
  7%|▋         | 330/4660 [01:25<20:35,  3.51it/s]
  7%|▋         | 331/4660 [01:25<19:01,  3.79it/s]
  7%|▋         | 332/4660 [01:25<18:31,  3.90it/s]
  7%|▋         | 333/4660 [01:25<17:06,  4.22it/s]
  7%|▋         | 334/4660 [01:26<15:52,  4.54it/s]
  7%|▋         | 335/4660 [01:26<15:30,  4.65it/s]
  7%|▋         | 336/4660 [01:26<19:12,  3.75it/s]
  7%|▋         | 337/4660 [01:26<20:20,  3.54it/s]
  7%|▋         | 338/4660 [01:27<18:33,  3.88it/s]
  7%|▋         | 339/4660 [01:27<19:07,  3.77it/s]
  7%|▋         | 340/4660 [01:27<19:09,  3.76it/s]
  7%|▋         | 341/4660 [01:27<19:37,  3.67it/s]
  7%|▋         | 342/4660 [01:28<19:34,  3.68it/s]
  7%|▋         | 343/4660 [01:28<20:32,  3.50it/s]
  7%|▋         | 344/4660 [01:28<19:12,  3.74it/s]
  7%|▋         | 345/4660 [01:29<18:17,  3.93it/s]
  7%|▋         | 346/4660 [01:29<17:31,  4.10it/s]
  7%|▋         | 347/4660 [01:29<16:39,  4.32it/s]
  7%|▋         | 348/4660 [01:29<16:56,  4.24it/s]
  7%|▋         | 349/4660 [01:29<16:01,  4.48it/s]
  8%|▊         | 350/4660 [01:30<15:54,  4.52it/s]
  8%|▊         | 351/4660 [01:30<16:11,  4.44it/s]
  8%|▊         | 352/4660 [01:30<16:38,  4.31it/s]
  8%|▊         | 353/4660 [01:30<15:39,  4.58it/s]
  8%|▊         | 354/4660 [01:30<15:43,  4.56it/s]
  8%|▊         | 355/4660 [01:31<16:23,  4.38it/s]
  8%|▊         | 356/4660 [01:31<16:50,  4.26it/s]
  8%|▊         | 357/4660 [01:31<17:43,  4.05it/s]
  8%|▊         | 358/4660 [01:32<19:18,  3.71it/s]
  8%|▊         | 359/4660 [01:32<17:18,  4.14it/s]
  8%|▊         | 360/4660 [01:32<19:29,  3.68it/s]
  8%|▊         | 361/4660 [01:32<19:41,  3.64it/s]
  8%|▊         | 362/4660 [01:33<18:05,  3.96it/s]
  8%|▊         | 363/4660 [01:33<18:02,  3.97it/s]
  8%|▊         | 364/4660 [01:33<19:01,  3.76it/s]
  8%|▊         | 365/4660 [01:33<18:20,  3.90it/s]
  8%|▊         | 366/4660 [01:34<17:07,  4.18it/s]
  8%|▊         | 367/4660 [01:34<16:10,  4.42it/s]
  8%|▊         | 368/4660 [01:34<17:07,  4.18it/s]
  8%|▊         | 369/4660 [01:34<16:08,  4.43it/s]
  8%|▊         | 370/4660 [01:34<15:32,  4.60it/s]
  8%|▊         | 371/4660 [01:35<17:52,  4.00it/s]
  8%|▊         | 372/4660 [01:35<16:37,  4.30it/s]
  8%|▊         | 373/4660 [01:35<18:36,  3.84it/s]
  8%|▊         | 374/4660 [01:35<17:34,  4.06it/s]
  8%|▊         | 375/4660 [01:36<16:32,  4.32it/s]
  8%|▊         | 376/4660 [01:36<16:06,  4.43it/s]
  8%|▊         | 377/4660 [01:36<16:35,  4.30it/s]
  8%|▊         | 378/4660 [01:36<17:19,  4.12it/s]
  8%|▊         | 379/4660 [01:37<18:22,  3.88it/s]
  8%|▊         | 380/4660 [01:37<17:23,  4.10it/s]
  8%|▊         | 381/4660 [01:37<16:29,  4.32it/s]
  8%|▊         | 382/4660 [01:37<18:57,  3.76it/s]
  8%|▊         | 383/4660 [01:38<17:17,  4.12it/s]
  8%|▊         | 384/4660 [01:38<17:11,  4.15it/s]
  8%|▊         | 385/4660 [01:38<15:58,  4.46it/s]
  8%|▊         | 386/4660 [01:38<16:50,  4.23it/s]
  8%|▊         | 387/4660 [01:39<19:30,  3.65it/s]
  8%|▊         | 388/4660 [01:39<19:00,  3.74it/s]
  8%|▊         | 389/4660 [01:39<22:05,  3.22it/s]
  8%|▊         | 390/4660 [01:40<20:15,  3.51it/s]
  8%|▊         | 391/4660 [01:40<18:00,  3.95it/s]
  8%|▊         | 392/4660 [01:40<17:34,  4.05it/s]
  8%|▊         | 393/4660 [01:40<16:33,  4.29it/s]
  8%|▊         | 394/4660 [01:40<15:36,  4.56it/s]
  8%|▊         | 395/4660 [01:41<16:03,  4.43it/s]
  8%|▊         | 396/4660 [01:41<18:03,  3.94it/s]
  9%|▊         | 397/4660 [01:41<17:34,  4.04it/s]
  9%|▊         | 398/4660 [01:41<16:19,  4.35it/s]
  9%|▊         | 399/4660 [01:42<15:56,  4.46it/s]
  9%|▊         | 400/4660 [01:42<15:27,  4.59it/s]
  9%|▊         | 401/4660 [01:42<15:22,  4.62it/s]
  9%|▊         | 402/4660 [01:42<15:11,  4.67it/s]
  9%|▊         | 403/4660 [01:42<14:31,  4.88it/s]
  9%|▊         | 404/4660 [01:43<13:49,  5.13it/s]
  9%|▊         | 405/4660 [01:43<13:42,  5.18it/s]
  9%|▊         | 406/4660 [01:43<13:53,  5.11it/s]
  9%|▊         | 407/4660 [01:43<14:43,  4.82it/s]
  9%|▉         | 408/4660 [01:44<18:10,  3.90it/s]
  9%|▉         | 409/4660 [01:44<18:19,  3.87it/s]
  9%|▉         | 410/4660 [01:44<16:55,  4.19it/s]
  9%|▉         | 411/4660 [01:44<16:34,  4.27it/s]
  9%|▉         | 412/4660 [01:44<15:43,  4.50it/s]
  9%|▉         | 413/4660 [01:45<16:21,  4.33it/s]
  9%|▉         | 414/4660 [01:45<17:06,  4.13it/s]
  9%|▉         | 415/4660 [01:45<18:21,  3.85it/s]
  9%|▉         | 416/4660 [01:46<18:37,  3.80it/s]
  9%|▉         | 417/4660 [01:46<20:12,  3.50it/s]
  9%|▉         | 418/4660 [01:46<19:52,  3.56it/s]
  9%|▉         | 419/4660 [01:46<18:10,  3.89it/s]
  9%|▉         | 420/4660 [01:47<17:26,  4.05it/s]
  9%|▉         | 421/4660 [01:47<18:46,  3.76it/s]
  9%|▉         | 422/4660 [01:47<17:24,  4.06it/s]
  9%|▉         | 423/4660 [01:47<18:08,  3.89it/s]
  9%|▉         | 424/4660 [01:48<17:24,  4.06it/s]
  9%|▉         | 425/4660 [01:48<16:35,  4.26it/s]
  9%|▉         | 426/4660 [01:48<16:44,  4.21it/s]
  9%|▉         | 427/4660 [01:48<16:32,  4.26it/s]
  9%|▉         | 428/4660 [01:48<15:43,  4.49it/s]
  9%|▉         | 429/4660 [01:49<15:12,  4.64it/s]
  9%|▉         | 430/4660 [01:49<14:26,  4.88it/s]
  9%|▉         | 431/4660 [01:49<17:06,  4.12it/s]
  9%|▉         | 432/4660 [01:49<17:05,  4.12it/s]
  9%|▉         | 433/4660 [01:50<17:57,  3.92it/s]
  9%|▉         | 434/4660 [01:50<17:38,  3.99it/s]
  9%|▉         | 435/4660 [01:50<16:49,  4.19it/s]
  9%|▉         | 436/4660 [01:50<16:16,  4.33it/s]
  9%|▉         | 437/4660 [01:51<15:52,  4.43it/s]
  9%|▉         | 438/4660 [01:51<15:30,  4.54it/s]
  9%|▉         | 439/4660 [01:51<16:01,  4.39it/s]
  9%|▉         | 440/4660 [01:51<16:31,  4.26it/s]
  9%|▉         | 441/4660 [01:51<15:35,  4.51it/s]
  9%|▉         | 442/4660 [01:52<22:06,  3.18it/s]
 10%|▉         | 443/4660 [01:52<19:45,  3.56it/s]
 10%|▉         | 444/4660 [01:52<19:25,  3.62it/s]
 10%|▉         | 445/4660 [01:53<19:08,  3.67it/s]
 10%|▉         | 446/4660 [01:53<17:40,  3.97it/s]
 10%|▉         | 447/4660 [01:53<19:30,  3.60it/s]
 10%|▉         | 448/4660 [01:54<20:24,  3.44it/s]
 10%|▉         | 449/4660 [01:54<18:35,  3.78it/s]
 10%|▉         | 450/4660 [01:54<21:35,  3.25it/s]
 10%|▉         | 451/4660 [01:54<20:15,  3.46it/s]
 10%|▉         | 452/4660 [01:55<19:27,  3.60it/s]
 10%|▉         | 453/4660 [01:55<20:21,  3.44it/s]
 10%|▉         | 454/4660 [01:55<18:20,  3.82it/s]
 10%|▉         | 455/4660 [01:55<17:41,  3.96it/s]
 10%|▉         | 456/4660 [01:56<17:16,  4.06it/s]
 10%|▉         | 457/4660 [01:56<17:12,  4.07it/s]
 10%|▉         | 458/4660 [01:56<16:36,  4.22it/s]
 10%|▉         | 459/4660 [01:57<25:20,  2.76it/s]
 10%|▉         | 460/4660 [01:57<22:38,  3.09it/s]
 10%|▉         | 461/4660 [01:57<23:28,  2.98it/s]
 10%|▉         | 462/4660 [01:58<20:07,  3.48it/s]
 10%|▉         | 463/4660 [01:58<18:55,  3.69it/s]
 10%|▉         | 464/4660 [01:58<18:08,  3.85it/s]
 10%|▉         | 465/4660 [01:58<17:20,  4.03it/s]
 10%|█         | 466/4660 [01:58<16:28,  4.24it/s][INFO|trainer.py:811] 2024-09-05 23:13:48,410 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: tokens, ner_tags, id. If tokens, ner_tags, id are not expected by `RobertaForTokenClassification.forward`,  you can safely ignore this message.
+[INFO|trainer.py:3819] 2024-09-05 23:13:48,412 >> 
+***** Running Evaluation *****
+[INFO|trainer.py:3821] 2024-09-05 23:13:48,412 >>   Num examples = 6810
+[INFO|trainer.py:3824] 2024-09-05 23:13:48,412 >>   Batch size = 8
+
+
  0%|          | 0/852 [00:00<?, ?it/s]
+
  1%|          | 9/852 [00:00<00:09, 87.04it/s]
+
  2%|▏         | 18/852 [00:00<00:10, 78.62it/s]
+
  3%|▎         | 27/852 [00:00<00:10, 79.58it/s]
+
  4%|▍         | 35/852 [00:00<00:10, 78.85it/s]
+
  5%|▌         | 44/852 [00:00<00:10, 80.12it/s]
+
  6%|▌         | 53/852 [00:00<00:09, 81.95it/s]
+
  7%|▋         | 62/852 [00:00<00:09, 82.52it/s]
+
  8%|▊         | 71/852 [00:00<00:09, 78.94it/s]
+
  9%|▉         | 80/852 [00:01<00:09, 78.84it/s]
+
 10%|█         | 89/852 [00:01<00:09, 79.94it/s]
+
 12%|█▏        | 98/852 [00:01<00:09, 80.24it/s]
+
 13%|█▎        | 107/852 [00:01<00:09, 79.96it/s]
+
 14%|█▎        | 116/852 [00:01<00:09, 80.61it/s]
+
 15%|█▍        | 125/852 [00:01<00:08, 82.16it/s]
+
 16%|█▌        | 134/852 [00:01<00:09, 77.87it/s]
+
 17%|█▋        | 142/852 [00:01<00:09, 78.16it/s]
+
 18%|█▊        | 150/852 [00:01<00:09, 77.25it/s]
+
 19%|█▊        | 159/852 [00:01<00:08, 79.08it/s]
+
 20%|█▉        | 168/852 [00:02<00:08, 80.30it/s]
+
 21%|██        | 177/852 [00:02<00:08, 80.70it/s]
+
 22%|██▏       | 186/852 [00:02<00:08, 81.77it/s]
+
 23%|██▎       | 195/852 [00:02<00:08, 80.23it/s]
+
 24%|██▍       | 204/852 [00:02<00:07, 81.02it/s]
+
 25%|██▌       | 213/852 [00:02<00:07, 80.19it/s]
+
 26%|██▌       | 222/852 [00:02<00:07, 80.29it/s]
+
 27%|██▋       | 231/852 [00:02<00:07, 81.65it/s]
+
 28%|██▊       | 240/852 [00:02<00:07, 80.86it/s]
+
 29%|██▉       | 249/852 [00:03<00:07, 79.93it/s]
+
 30%|███       | 258/852 [00:03<00:07, 81.98it/s]
+
 31%|███▏      | 267/852 [00:03<00:07, 81.16it/s]
+
 32%|███▏      | 276/852 [00:03<00:07, 81.53it/s]
+
 33%|███▎      | 285/852 [00:03<00:06, 82.14it/s]
+
 35%|███▍      | 294/852 [00:03<00:06, 81.42it/s]
+
 36%|███▌      | 303/852 [00:03<00:06, 82.36it/s]
+
 37%|███▋      | 312/852 [00:03<00:06, 80.14it/s]
+
 38%|███▊      | 321/852 [00:03<00:06, 81.45it/s]
+
 39%|███▊      | 330/852 [00:04<00:06, 80.34it/s]
+
 40%|███▉      | 339/852 [00:04<00:06, 80.51it/s]
+
 41%|████      | 348/852 [00:04<00:06, 81.62it/s]
+
 42%|████▏     | 357/852 [00:04<00:06, 79.87it/s]
+
 43%|████▎     | 366/852 [00:04<00:05, 81.03it/s]
+
 44%|████▍     | 375/852 [00:04<00:05, 81.89it/s]
+
 45%|████▌     | 384/852 [00:04<00:05, 81.28it/s]
+
 46%|████▌     | 393/852 [00:04<00:05, 82.86it/s]
+
 47%|████▋     | 402/852 [00:04<00:05, 82.37it/s]
+
 48%|████▊     | 411/852 [00:05<00:05, 80.21it/s]
+
 49%|████▉     | 420/852 [00:05<00:05, 81.32it/s]
+
 50%|█████     | 429/852 [00:05<00:05, 80.36it/s]
+
 51%|█████▏    | 438/852 [00:05<00:05, 81.67it/s]
+
 52%|█████▏    | 447/852 [00:05<00:04, 81.84it/s]
+
 54%|█████▎    | 456/852 [00:05<00:04, 82.77it/s]
+
 55%|█████▍    | 465/852 [00:05<00:04, 81.67it/s]
+
 56%|█████▌    | 474/852 [00:05<00:04, 76.72it/s]
+
 57%|█████▋    | 483/852 [00:06<00:04, 77.86it/s]
+
 58%|█████▊    | 492/852 [00:06<00:04, 78.76it/s]
+
 59%|█████▉    | 501/852 [00:06<00:04, 80.94it/s]
+
 60%|█████▉    | 510/852 [00:06<00:04, 80.66it/s]
+
 61%|██████    | 519/852 [00:06<00:04, 81.83it/s]
+
 62%|██████▏   | 528/852 [00:06<00:04, 79.71it/s]
+
 63%|██████▎   | 537/852 [00:06<00:03, 81.93it/s]
+
 64%|██████▍   | 546/852 [00:06<00:03, 82.54it/s]
+
 65%|██████▌   | 555/852 [00:06<00:03, 79.93it/s]
+
 66%|██████▌   | 564/852 [00:06<00:03, 80.45it/s]
+
 67%|██████▋   | 573/852 [00:07<00:03, 81.11it/s]
+
 68%|██████▊   | 582/852 [00:07<00:03, 81.14it/s]
+
 69%|██████▉   | 591/852 [00:07<00:03, 80.29it/s]
+
 70%|███████   | 600/852 [00:07<00:03, 80.37it/s]
+
 71%|███████▏  | 609/852 [00:07<00:03, 80.96it/s]
+
 73%|███████▎  | 618/852 [00:07<00:02, 79.39it/s]
+
 73%|███████▎  | 626/852 [00:07<00:02, 79.48it/s]
+
 74%|███████▍  | 634/852 [00:07<00:02, 79.56it/s]
+
 75%|███████▌  | 642/852 [00:07<00:02, 76.70it/s]
+
 76%|███████▋  | 651/852 [00:08<00:02, 78.86it/s]
+
 77%|███████▋  | 660/852 [00:08<00:02, 80.53it/s]
+
 79%|███████▊  | 669/852 [00:08<00:02, 80.93it/s]
+
 80%|███████▉  | 678/852 [00:08<00:02, 81.23it/s]
+
 81%|████████  | 687/852 [00:08<00:02, 81.90it/s]
+
 82%|████████▏ | 696/852 [00:08<00:01, 82.92it/s]
+
 83%|████████▎ | 705/852 [00:08<00:01, 84.10it/s]
+
 84%|████████▍ | 714/852 [00:08<00:01, 84.78it/s]
+
 85%|████████▍ | 723/852 [00:08<00:01, 83.35it/s]
+
 86%|████████▌ | 732/852 [00:09<00:01, 84.47it/s]
+
 87%|████████▋ | 741/852 [00:09<00:01, 84.18it/s]
+
 88%|████████▊ | 750/852 [00:09<00:01, 84.46it/s]
+
 89%|████████▉ | 759/852 [00:09<00:01, 85.22it/s]
+
 90%|█████████ | 768/852 [00:09<00:01, 83.60it/s]
+
 91%|█████████ | 777/852 [00:09<00:00, 84.05it/s]
+
 92%|█████████▏| 786/852 [00:09<00:00, 82.48it/s]
+
 93%|█████████▎| 795/852 [00:09<00:00, 83.63it/s]
+
 94%|█████████▍| 804/852 [00:09<00:00, 84.80it/s]
+
 95%|█████████▌| 813/852 [00:10<00:00, 83.62it/s]
+
 96%|█████████▋| 822/852 [00:10<00:00, 83.96it/s]
+
 98%|█████████▊| 831/852 [00:10<00:00, 84.33it/s]
+
 99%|█████████▊| 840/852 [00:10<00:00, 82.98it/s]
+
                                                  
+
                                                 
 10%|█         | 466/4660 [02:12<16:28,  4.24it/s]
+
+
                                                 [INFO|trainer.py:3503] 2024-09-05 23:14:02,411 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-466
+[INFO|configuration_utils.py:472] 2024-09-05 23:14:02,412 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-466/config.json
+[INFO|modeling_utils.py:2799] 2024-09-05 23:14:03,437 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-466/model.safetensors
+[INFO|tokenization_utils_base.py:2684] 2024-09-05 23:14:03,438 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-466/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2693] 2024-09-05 23:14:03,439 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-466/special_tokens_map.json
+[INFO|tokenization_utils_base.py:2684] 2024-09-05 23:14:09,207 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2693] 2024-09-05 23:14:09,207 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+
 10%|█         | 467/4660 [02:20<7:35:00,  6.51s/it]
 10%|█         | 468/4660 [02:20<5:22:02,  4.61s/it]
 10%|█         | 469/4660 [02:20<3:50:09,  3.29s/it]
 10%|█         | 470/4660 [02:20<2:45:14,  2.37s/it]
 10%|█         | 471/4660 [02:20<2:01:55,  1.75s/it]
 10%|█         | 472/4660 [02:21<1:30:03,  1.29s/it]
 10%|█         | 473/4660 [02:21<1:07:44,  1.03it/s]
 10%|█         | 474/4660 [02:21<52:40,  1.32it/s]  
 10%|█         | 475/4660 [02:21<41:07,  1.70it/s]
 10%|█         | 476/4660 [02:22<33:13,  2.10it/s]
 10%|█         | 477/4660 [02:22<27:46,  2.51it/s]
 10%|█         | 478/4660 [02:22<23:22,  2.98it/s]
 10%|█         | 479/4660 [02:22<22:05,  3.15it/s]
 10%|█         | 480/4660 [02:23<20:19,  3.43it/s]
 10%|█         | 481/4660 [02:23<22:03,  3.16it/s]
 10%|█         | 482/4660 [02:23<19:59,  3.48it/s]
 10%|█         | 483/4660 [02:23<19:06,  3.64it/s]
 10%|█         | 484/4660 [02:24<17:17,  4.02it/s]
 10%|█         | 485/4660 [02:24<16:54,  4.11it/s]
 10%|█         | 486/4660 [02:24<16:30,  4.21it/s]
 10%|█         | 487/4660 [02:24<15:46,  4.41it/s]
 10%|█         | 488/4660 [02:25<18:07,  3.84it/s]
 10%|█         | 489/4660 [02:25<18:19,  3.79it/s]
 11%|█         | 490/4660 [02:25<18:28,  3.76it/s]
 11%|█         | 491/4660 [02:25<16:46,  4.14it/s]
 11%|█         | 492/4660 [02:25<16:33,  4.19it/s]
 11%|█         | 493/4660 [02:26<18:09,  3.82it/s]
 11%|█         | 494/4660 [02:26<17:24,  3.99it/s]
 11%|█         | 495/4660 [02:26<18:01,  3.85it/s]
 11%|█         | 496/4660 [02:27<16:58,  4.09it/s]
 11%|█         | 497/4660 [02:27<21:16,  3.26it/s]
 11%|█         | 498/4660 [02:27<19:03,  3.64it/s]
 11%|█         | 499/4660 [02:27<17:54,  3.87it/s]
 11%|█         | 500/4660 [02:28<17:15,  4.02it/s]
                                                  
 11%|█         | 500/4660 [02:28<17:15,  4.02it/s]
 11%|█         | 501/4660 [02:28<17:01,  4.07it/s]
 11%|█         | 502/4660 [02:28<17:04,  4.06it/s]
 11%|█         | 503/4660 [02:28<16:51,  4.11it/s]
 11%|█         | 504/4660 [02:29<17:04,  4.06it/s]
 11%|█         | 505/4660 [02:29<15:47,  4.39it/s]
 11%|█         | 506/4660 [02:29<16:57,  4.08it/s]
 11%|█         | 507/4660 [02:29<18:23,  3.76it/s]
 11%|█         | 508/4660 [02:30<17:09,  4.03it/s]
 11%|█         | 509/4660 [02:30<16:14,  4.26it/s]
 11%|█         | 510/4660 [02:30<21:31,  3.21it/s]
 11%|█         | 511/4660 [02:31<20:43,  3.34it/s]
 11%|█         | 512/4660 [02:31<19:25,  3.56it/s]
 11%|█         | 513/4660 [02:31<27:43,  2.49it/s]
 11%|█         | 514/4660 [02:32<23:53,  2.89it/s]
 11%|█         | 515/4660 [02:32<22:02,  3.13it/s]
 11%|█         | 516/4660 [02:32<19:16,  3.58it/s]
 11%|█         | 517/4660 [02:32<18:29,  3.73it/s]
 11%|█         | 518/4660 [02:33<18:28,  3.74it/s]
 11%|█         | 519/4660 [02:33<18:21,  3.76it/s]
 11%|█         | 520/4660 [02:33<18:38,  3.70it/s]
 11%|█         | 521/4660 [02:33<18:50,  3.66it/s]
 11%|█         | 522/4660 [02:34<16:46,  4.11it/s]
 11%|█         | 523/4660 [02:34<15:35,  4.42it/s]
 11%|█         | 524/4660 [02:34<16:18,  4.23it/s]
 11%|█▏        | 525/4660 [02:34<16:04,  4.29it/s]
 11%|█▏        | 526/4660 [02:35<15:49,  4.35it/s]
 11%|█▏        | 527/4660 [02:35<15:02,  4.58it/s]
 11%|█▏        | 528/4660 [02:35<14:13,  4.84it/s]
 11%|█▏        | 529/4660 [02:35<14:02,  4.90it/s]
 11%|█▏        | 530/4660 [02:35<14:10,  4.86it/s]
 11%|█▏        | 531/4660 [02:35<13:20,  5.16it/s]
 11%|█▏        | 532/4660 [02:36<13:18,  5.17it/s]
 11%|█▏        | 533/4660 [02:36<16:04,  4.28it/s]
 11%|█▏        | 534/4660 [02:36<17:23,  3.95it/s]
 11%|█▏        | 535/4660 [02:36<15:38,  4.40it/s]
 12%|█▏        | 536/4660 [02:37<15:29,  4.44it/s]
 12%|█▏        | 537/4660 [02:37<15:20,  4.48it/s]
 12%|█▏        | 538/4660 [02:37<18:06,  3.79it/s]
 12%|█▏        | 539/4660 [02:37<16:42,  4.11it/s]
 12%|█▏        | 540/4660 [02:38<17:15,  3.98it/s]
 12%|█▏        | 541/4660 [02:38<17:02,  4.03it/s]
 12%|█▏        | 542/4660 [02:38<15:54,  4.32it/s]
 12%|█▏        | 543/4660 [02:38<15:38,  4.39it/s]
 12%|█▏        | 544/4660 [02:39<15:53,  4.32it/s]
 12%|█▏        | 545/4660 [02:39<18:07,  3.78it/s]
 12%|█▏        | 546/4660 [02:39<17:14,  3.98it/s]
 12%|█▏        | 547/4660 [02:39<17:26,  3.93it/s]
 12%|█▏        | 548/4660 [02:40<17:39,  3.88it/s]
 12%|█▏        | 549/4660 [02:40<18:09,  3.77it/s]
 12%|█▏        | 550/4660 [02:40<17:44,  3.86it/s]
 12%|█▏        | 551/4660 [02:40<17:14,  3.97it/s]
 12%|█▏        | 552/4660 [02:41<16:05,  4.25it/s]
 12%|█▏        | 553/4660 [02:41<15:26,  4.43it/s]
 12%|█▏        | 554/4660 [02:41<17:23,  3.94it/s]
 12%|█▏        | 555/4660 [02:41<17:56,  3.81it/s]
 12%|█▏        | 556/4660 [02:42<17:54,  3.82it/s]
 12%|█▏        | 557/4660 [02:42<17:55,  3.81it/s]
 12%|█▏        | 558/4660 [02:42<18:21,  3.72it/s]
 12%|█▏        | 559/4660 [02:43<19:13,  3.55it/s]
 12%|█▏        | 560/4660 [02:43<18:18,  3.73it/s]
 12%|█▏        | 561/4660 [02:43<17:27,  3.91it/s]
 12%|█▏        | 562/4660 [02:43<16:04,  4.25it/s]
 12%|█▏        | 563/4660 [02:43<15:34,  4.38it/s]
 12%|█▏        | 564/4660 [02:44<16:03,  4.25it/s]
 12%|█▏        | 565/4660 [02:44<15:16,  4.47it/s]
 12%|█▏        | 566/4660 [02:44<15:56,  4.28it/s]
 12%|█▏        | 567/4660 [02:44<15:10,  4.50it/s]
 12%|█▏        | 568/4660 [02:45<13:54,  4.90it/s]
 12%|█▏        | 569/4660 [02:45<13:41,  4.98it/s]
 12%|█▏        | 570/4660 [02:45<14:06,  4.83it/s]
 12%|█▏        | 571/4660 [02:45<15:39,  4.35it/s]
 12%|█▏        | 572/4660 [02:46<18:05,  3.77it/s]
 12%|█▏        | 573/4660 [02:46<16:00,  4.25it/s]
 12%|█▏        | 574/4660 [02:46<17:30,  3.89it/s]
 12%|█▏        | 575/4660 [02:46<17:53,  3.80it/s]
 12%|█▏        | 576/4660 [02:47<17:00,  4.00it/s]
 12%|█▏        | 577/4660 [02:47<16:54,  4.03it/s]
 12%|█▏        | 578/4660 [02:47<17:03,  3.99it/s]
 12%|█▏        | 579/4660 [02:47<17:35,  3.87it/s]
 12%|█▏        | 580/4660 [02:48<16:52,  4.03it/s]
 12%|█▏        | 581/4660 [02:48<16:57,  4.01it/s]
 12%|█▏        | 582/4660 [02:48<16:52,  4.03it/s]
 13%|█▎        | 583/4660 [02:48<18:54,  3.59it/s]
 13%|█▎        | 584/4660 [02:49<17:09,  3.96it/s]
 13%|█▎        | 585/4660 [02:49<15:29,  4.39it/s]
 13%|█▎        | 586/4660 [02:49<14:32,  4.67it/s]
 13%|█▎        | 587/4660 [02:49<14:10,  4.79it/s]
 13%|█▎        | 588/4660 [02:50<27:18,  2.48it/s]
 13%|█▎        | 589/4660 [02:50<22:41,  2.99it/s]
 13%|█▎        | 590/4660 [02:50<21:23,  3.17it/s]
 13%|█▎        | 591/4660 [02:51<19:02,  3.56it/s]
 13%|█▎        | 592/4660 [02:51<20:57,  3.23it/s]
 13%|█▎        | 593/4660 [02:51<19:04,  3.55it/s]
 13%|█▎        | 594/4660 [02:51<18:27,  3.67it/s]
 13%|█▎        | 595/4660 [02:52<17:21,  3.90it/s]
 13%|█▎        | 596/4660 [02:52<16:18,  4.16it/s]
 13%|█▎        | 597/4660 [02:52<15:16,  4.43it/s]
 13%|█▎        | 598/4660 [02:52<14:25,  4.70it/s]
 13%|█▎        | 599/4660 [02:52<13:52,  4.88it/s]
 13%|█▎        | 600/4660 [02:53<15:59,  4.23it/s]
 13%|█▎        | 601/4660 [02:53<16:01,  4.22it/s]
 13%|█▎        | 602/4660 [02:53<16:54,  4.00it/s]
 13%|█▎        | 603/4660 [02:54<17:32,  3.86it/s]
 13%|█▎        | 604/4660 [02:54<25:52,  2.61it/s]
 13%|█▎        | 605/4660 [02:54<22:11,  3.04it/s]
 13%|█▎        | 606/4660 [02:55<19:45,  3.42it/s]
 13%|█▎        | 607/4660 [02:55<18:59,  3.56it/s]
 13%|█▎        | 608/4660 [02:55<17:46,  3.80it/s]
 13%|█▎        | 609/4660 [02:55<17:16,  3.91it/s]
 13%|█▎        | 610/4660 [02:56<16:17,  4.15it/s]
 13%|█▎        | 611/4660 [02:56<17:15,  3.91it/s]
 13%|█▎        | 612/4660 [02:56<19:37,  3.44it/s]
 13%|█▎        | 613/4660 [02:56<17:59,  3.75it/s]
 13%|█▎        | 614/4660 [02:57<17:30,  3.85it/s]
 13%|█▎        | 615/4660 [02:57<15:27,  4.36it/s]
 13%|█▎        | 616/4660 [02:57<15:41,  4.29it/s]
 13%|█▎        | 617/4660 [02:57<17:25,  3.87it/s]
 13%|█▎        | 618/4660 [02:58<21:15,  3.17it/s]
 13%|█▎        | 619/4660 [02:58<19:34,  3.44it/s]
 13%|█▎        | 620/4660 [02:58<19:02,  3.54it/s]
 13%|█▎        | 621/4660 [02:59<17:31,  3.84it/s]
 13%|█▎        | 622/4660 [02:59<15:26,  4.36it/s]
 13%|█▎        | 623/4660 [02:59<14:15,  4.72it/s]
 13%|█▎        | 624/4660 [02:59<14:07,  4.76it/s]
 13%|█▎        | 625/4660 [02:59<13:17,  5.06it/s]
 13%|█▎        | 626/4660 [02:59<12:33,  5.35it/s]
 13%|█▎        | 627/4660 [03:00<12:50,  5.24it/s]
 13%|█▎        | 628/4660 [03:00<13:23,  5.02it/s]
 13%|█▎        | 629/4660 [03:00<13:58,  4.81it/s]
 14%|█▎        | 630/4660 [03:00<14:43,  4.56it/s]
 14%|█▎        | 631/4660 [03:00<14:00,  4.79it/s]
 14%|█▎        | 632/4660 [03:01<14:29,  4.63it/s]
 14%|█▎        | 633/4660 [03:01<14:52,  4.51it/s]
 14%|█▎        | 634/4660 [03:01<16:16,  4.12it/s]
 14%|█▎        | 635/4660 [03:01<16:17,  4.12it/s]
 14%|█▎        | 636/4660 [03:02<15:11,  4.42it/s]
 14%|█▎        | 637/4660 [03:02<14:09,  4.74it/s]
 14%|█▎        | 638/4660 [03:02<13:27,  4.98it/s]
 14%|█▎        | 639/4660 [03:02<13:57,  4.80it/s]
 14%|█▎        | 640/4660 [03:03<14:51,  4.51it/s]
 14%|█▍        | 641/4660 [03:03<14:14,  4.70it/s]
 14%|█▍        | 642/4660 [03:03<13:55,  4.81it/s]
 14%|█▍        | 643/4660 [03:03<15:11,  4.40it/s]
 14%|█▍        | 644/4660 [03:03<15:38,  4.28it/s]
 14%|█▍        | 645/4660 [03:04<18:12,  3.68it/s]
 14%|█▍        | 646/4660 [03:04<16:32,  4.04it/s]
 14%|█▍        | 647/4660 [03:04<16:08,  4.14it/s]
 14%|█▍        | 648/4660 [03:05<18:37,  3.59it/s]
 14%|█▍        | 649/4660 [03:05<16:54,  3.95it/s]
 14%|█▍        | 650/4660 [03:05<17:13,  3.88it/s]
 14%|█▍        | 651/4660 [03:05<17:43,  3.77it/s]
 14%|█▍        | 652/4660 [03:05<16:06,  4.15it/s]
 14%|█▍        | 653/4660 [03:06<15:29,  4.31it/s]
 14%|█▍        | 654/4660 [03:06<15:24,  4.33it/s]
 14%|█▍        | 655/4660 [03:06<16:11,  4.12it/s]
 14%|█▍        | 656/4660 [03:06<15:04,  4.43it/s]
 14%|█▍        | 657/4660 [03:07<14:10,  4.71it/s]
 14%|█▍        | 658/4660 [03:07<14:31,  4.59it/s]
 14%|█▍        | 659/4660 [03:07<14:03,  4.74it/s]
 14%|█▍        | 660/4660 [03:07<15:13,  4.38it/s]
 14%|█▍        | 661/4660 [03:07<15:25,  4.32it/s]
 14%|█▍        | 662/4660 [03:08<14:18,  4.66it/s]
 14%|█▍        | 663/4660 [03:08<14:18,  4.66it/s]
 14%|█▍        | 664/4660 [03:08<15:55,  4.18it/s]
 14%|█▍        | 665/4660 [03:08<15:01,  4.43it/s]
 14%|█▍        | 666/4660 [03:09<14:22,  4.63it/s]
 14%|█▍        | 667/4660 [03:09<14:20,  4.64it/s]
 14%|█▍        | 668/4660 [03:09<15:44,  4.22it/s]
 14%|█▍        | 669/4660 [03:09<14:41,  4.53it/s]
 14%|█▍        | 670/4660 [03:09<14:17,  4.65it/s]
 14%|█▍        | 671/4660 [03:10<20:51,  3.19it/s]
 14%|█▍        | 672/4660 [03:10<19:12,  3.46it/s]
 14%|█▍        | 673/4660 [03:10<18:07,  3.67it/s]
 14%|█▍        | 674/4660 [03:11<16:17,  4.08it/s]
 14%|█▍        | 675/4660 [03:11<15:16,  4.35it/s]
 15%|█▍        | 676/4660 [03:11<15:56,  4.17it/s]
 15%|█▍        | 677/4660 [03:11<15:43,  4.22it/s]
 15%|█▍        | 678/4660 [03:11<14:08,  4.69it/s]
 15%|█▍        | 679/4660 [03:12<13:59,  4.74it/s]

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.98998998998999,
+    "total_flos": 1.5071241212671032e+16,
+    "train_loss": 0.022475468706272407,
+    "train_runtime": 1385.1143,
+    "train_samples": 31947,
+    "train_samples_per_second": 230.645,
+    "train_steps_per_second": 3.603
+}

trainer_state.json

@@ -0,0 +1,225 @@
+{
+  "best_metric": 0.8040201005025126,
+  "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-3996",
+  "epoch": 9.98998998998999,
+  "eval_steps": 500,
+  "global_step": 4990,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.998998998998999,
+      "eval_accuracy": 0.9730869045820918,
+      "eval_f1": 0.75963794837412,
+      "eval_loss": 0.07385822385549545,
+      "eval_precision": 0.7270588235294118,
+      "eval_recall": 0.7952737482452036,
+      "eval_runtime": 14.2023,
+      "eval_samples_per_second": 479.501,
+      "eval_steps_per_second": 59.99,
+      "step": 499
+    },
+    {
+      "epoch": 1.001001001001001,
+      "grad_norm": 0.8427119851112366,
+      "learning_rate": 4.4989979959919844e-05,
+      "loss": 0.105,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.972949592870776,
+      "eval_f1": 0.7655806561471223,
+      "eval_loss": 0.09075114130973816,
+      "eval_precision": 0.7435501653803749,
+      "eval_recall": 0.7889564810481984,
+      "eval_runtime": 14.1492,
+      "eval_samples_per_second": 481.299,
+      "eval_steps_per_second": 60.215,
+      "step": 999
+    },
+    {
+      "epoch": 2.002002002002002,
+      "grad_norm": 0.9121108651161194,
+      "learning_rate": 3.997995991983968e-05,
+      "loss": 0.0448,
+      "step": 1000
+    },
+    {
+      "epoch": 2.998998998998999,
+      "eval_accuracy": 0.9743913658395924,
+      "eval_f1": 0.7829875042989798,
+      "eval_loss": 0.09297410398721695,
+      "eval_precision": 0.7675882220723759,
+      "eval_recall": 0.7990173139915769,
+      "eval_runtime": 14.1376,
+      "eval_samples_per_second": 481.693,
+      "eval_steps_per_second": 60.265,
+      "step": 1498
+    },
+    {
+      "epoch": 3.003003003003003,
+      "grad_norm": 0.5380845069885254,
+      "learning_rate": 3.496993987975952e-05,
+      "loss": 0.0255,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9757438861960537,
+      "eval_f1": 0.789358010410642,
+      "eval_loss": 0.10520397126674652,
+      "eval_precision": 0.7805994051704416,
+      "eval_recall": 0.798315395414132,
+      "eval_runtime": 14.3621,
+      "eval_samples_per_second": 474.163,
+      "eval_steps_per_second": 59.323,
+      "step": 1998
+    },
+    {
+      "epoch": 4.004004004004004,
+      "grad_norm": 0.2705754339694977,
+      "learning_rate": 2.9959919839679363e-05,
+      "loss": 0.0164,
+      "step": 2000
+    },
+    {
+      "epoch": 4.998998998998999,
+      "eval_accuracy": 0.9750435964683428,
+      "eval_f1": 0.7879346074142298,
+      "eval_loss": 0.10997848957777023,
+      "eval_precision": 0.7756119673617408,
+      "eval_recall": 0.8006551240056153,
+      "eval_runtime": 14.2341,
+      "eval_samples_per_second": 478.428,
+      "eval_steps_per_second": 59.856,
+      "step": 2497
+    },
+    {
+      "epoch": 5.005005005005005,
+      "grad_norm": 0.27666428685188293,
+      "learning_rate": 2.49498997995992e-05,
+      "loss": 0.0112,
+      "step": 2500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9768011863731858,
+      "eval_f1": 0.799447386599125,
+      "eval_loss": 0.12663568556308746,
+      "eval_precision": 0.7869446962828649,
+      "eval_recall": 0.8123537669630323,
+      "eval_runtime": 14.5018,
+      "eval_samples_per_second": 469.597,
+      "eval_steps_per_second": 58.751,
+      "step": 2997
+    },
+    {
+      "epoch": 6.006006006006006,
+      "grad_norm": 0.24552026391029358,
+      "learning_rate": 1.993987975951904e-05,
+      "loss": 0.0073,
+      "step": 3000
+    },
+    {
+      "epoch": 6.998998998998999,
+      "eval_accuracy": 0.976293133041317,
+      "eval_f1": 0.7968804562914678,
+      "eval_loss": 0.12882493436336517,
+      "eval_precision": 0.792911744266852,
+      "eval_recall": 0.8008890968647637,
+      "eval_runtime": 14.3476,
+      "eval_samples_per_second": 474.643,
+      "eval_steps_per_second": 59.383,
+      "step": 3496
+    },
+    {
+      "epoch": 7.007007007007007,
+      "grad_norm": 0.2008085697889328,
+      "learning_rate": 1.492985971943888e-05,
+      "loss": 0.0054,
+      "step": 3500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9764853694371592,
+      "eval_f1": 0.8040201005025126,
+      "eval_loss": 0.14244574308395386,
+      "eval_precision": 0.803175344384777,
+      "eval_recall": 0.8048666354702855,
+      "eval_runtime": 14.514,
+      "eval_samples_per_second": 469.202,
+      "eval_steps_per_second": 58.702,
+      "step": 3996
+    },
+    {
+      "epoch": 8.008008008008009,
+      "grad_norm": 0.12597906589508057,
+      "learning_rate": 9.919839679358718e-06,
+      "loss": 0.0038,
+      "step": 4000
+    },
+    {
+      "epoch": 8.998998998999,
+      "eval_accuracy": 0.9765059661938567,
+      "eval_f1": 0.7970779220779219,
+      "eval_loss": 0.14552859961986542,
+      "eval_precision": 0.7901149425287356,
+      "eval_recall": 0.8041647168928404,
+      "eval_runtime": 14.2396,
+      "eval_samples_per_second": 478.242,
+      "eval_steps_per_second": 59.833,
+      "step": 4495
+    },
+    {
+      "epoch": 9.00900900900901,
+      "grad_norm": 0.2577208876609802,
+      "learning_rate": 4.9098196392785576e-06,
+      "loss": 0.0028,
+      "step": 4500
+    },
+    {
+      "epoch": 9.98998998998999,
+      "eval_accuracy": 0.9768286487154489,
+      "eval_f1": 0.7984262902105993,
+      "eval_loss": 0.14972682297229767,
+      "eval_precision": 0.7898351648351648,
+      "eval_recall": 0.8072063640617688,
+      "eval_runtime": 14.3927,
+      "eval_samples_per_second": 473.158,
+      "eval_steps_per_second": 59.197,
+      "step": 4990
+    },
+    {
+      "epoch": 9.98998998998999,
+      "step": 4990,
+      "total_flos": 1.5071241212671032e+16,
+      "train_loss": 0.022475468706272407,
+      "train_runtime": 1385.1143,
+      "train_samples_per_second": 230.645,
+      "train_steps_per_second": 3.603
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4990,
+  "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": 1.5071241212671032e+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