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/combined-train-distemist-dev-85-ner
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: output
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: Rodrigo1771/combined-train-distemist-dev-85-ner
+      type: Rodrigo1771/combined-train-distemist-dev-85-ner
+      config: CombinedTrainDisTEMISTDevNER
+      split: validation
+      args: CombinedTrainDisTEMISTDevNER
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.3152508603513856
+    - name: Recall
+      type: recall
+      value: 0.8144595226953674
+    - name: F1
+      type: f1
+      value: 0.45455732567249935
+    - name: Accuracy
+      type: accuracy
+      value: 0.8564886649182308
+---
+
+<!-- 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/combined-train-distemist-dev-85-ner dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7006
+- Precision: 0.3153
+- Recall: 0.8145
+- F1: 0.4546
+- Accuracy: 0.8565
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.3191        | 1.0   | 541  | 0.4772          | 0.2725    | 0.8074 | 0.4075 | 0.8443   |
+| 0.1619        | 2.0   | 1082 | 0.4584          | 0.3041    | 0.7941 | 0.4398 | 0.8553   |
+| 0.11          | 3.0   | 1623 | 0.6447          | 0.2976    | 0.8000 | 0.4338 | 0.8435   |
+| 0.0764        | 4.0   | 2164 | 0.7413          | 0.2896    | 0.7871 | 0.4234 | 0.8399   |
+| 0.0567        | 5.0   | 2705 | 0.7006          | 0.3153    | 0.8145 | 0.4546 | 0.8565   |
+| 0.0428        | 6.0   | 3246 | 0.8112          | 0.3071    | 0.8210 | 0.4470 | 0.8504   |
+| 0.0332        | 7.0   | 3787 | 0.9046          | 0.3114    | 0.8070 | 0.4494 | 0.8533   |
+| 0.0257        | 8.0   | 4328 | 0.9723          | 0.3060    | 0.8109 | 0.4444 | 0.8482   |
+| 0.022         | 9.0   | 4869 | 1.0028          | 0.3087    | 0.8077 | 0.4467 | 0.8502   |
+| 0.0181        | 10.0  | 5410 | 1.0023          | 0.3116    | 0.8119 | 0.4504 | 0.8533   |
+
+
+### 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": 10.0,
+    "eval_accuracy": 0.8564886649182308,
+    "eval_f1": 0.45455732567249935,
+    "eval_loss": 0.7005925178527832,
+    "eval_precision": 0.3152508603513856,
+    "eval_recall": 0.8144595226953674,
+    "eval_runtime": 14.2934,
+    "eval_samples": 6810,
+    "eval_samples_per_second": 476.445,
+    "eval_steps_per_second": 59.608,
+    "predict_accuracy": 0.9437946603149774,
+    "predict_f1": 0.6365870441364396,
+    "predict_loss": 0.22766011953353882,
+    "predict_precision": 0.519576379974326,
+    "predict_recall": 0.8216188784572444,
+    "predict_runtime": 29.1056,
+    "predict_samples_per_second": 502.103,
+    "predict_steps_per_second": 62.771,
+    "total_flos": 1.7176580067661056e+16,
+    "train_loss": 0.0812657987344287,
+    "train_runtime": 1549.44,
+    "train_samples": 34604,
+    "train_samples_per_second": 223.332,
+    "train_steps_per_second": 3.492
+}

config.json

@@ -0,0 +1,51 @@
+{
+  "_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-ENFERMEDAD",
+    "2": "I-ENFERMEDAD",
+    "3": "B-PROCEDIMIENTO",
+    "4": "I-PROCEDIMIENTO",
+    "5": "B-SINTOMA",
+    "6": "I-SINTOMA",
+    "7": "B-FARMACO",
+    "8": "I-FARMACO"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ENFERMEDAD": 1,
+    "B-FARMACO": 7,
+    "B-PROCEDIMIENTO": 3,
+    "B-SINTOMA": 5,
+    "I-ENFERMEDAD": 2,
+    "I-FARMACO": 8,
+    "I-PROCEDIMIENTO": 4,
+    "I-SINTOMA": 6,
+    "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": 10.0,
+    "eval_accuracy": 0.8564886649182308,
+    "eval_f1": 0.45455732567249935,
+    "eval_loss": 0.7005925178527832,
+    "eval_precision": 0.3152508603513856,
+    "eval_recall": 0.8144595226953674,
+    "eval_runtime": 14.2934,
+    "eval_samples": 6810,
+    "eval_samples_per_second": 476.445,
+    "eval_steps_per_second": 59.608
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a21a07cf22f5106fcfdb29d50447d952a26e139f2f64fcb6717e631952f598d5
+size 496262556

predict_results.json

@@ -0,0 +1,10 @@
+{
+    "predict_accuracy": 0.9437946603149774,
+    "predict_f1": 0.6365870441364396,
+    "predict_loss": 0.22766011953353882,
+    "predict_precision": 0.519576379974326,
+    "predict_recall": 0.8216188784572444,
+    "predict_runtime": 29.1056,
+    "predict_samples_per_second": 502.103,
+    "predict_steps_per_second": 62.771
+}

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 sha256:78b123fe2690b4ef8daee19df1596f88d3d9902ee0a7e2e67195ebf39fc38893
+size 12146

tb/events.out.tfevents.1725579302.2a66098fac87.9264.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ddb06f8e19acc3cfe83ba96582312f0eda7c54cb22293014a850cd5aff12d3d
+size 560

tb/events.out.tfevents.1725579443.2a66098fac87.15776.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c35cf63ce2a6e730611e5daee2288691541b634908c8c8e2a1a19a4eb706abe0
+size 12645

tb/events.out.tfevents.1725581040.2a66098fac87.15776.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35dfb83cada8fb681a65313600c2857481bd7212900b1573ca8d6ce9b64470bb
+size 560

tb/events.out.tfevents.1725581348.2a66098fac87.23851.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6677cd4d016bc7985db6c5208ed18accfe0e63ff244a077c77afa15603927ea2
+size 6144

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 +1,430 @@
+2024-09-06 00:08:37.934804: 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`.
+2024-09-06 00:08:37.953090: 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
+2024-09-06 00:08:37.974597: 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
+2024-09-06 00:08:37.981013: 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
+2024-09-06 00:08:37.996733: 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.
+2024-09-06 00:08:39.252831: 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(
+09/06/2024 00:08:40 - WARNING - __main__ -   Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False
+09/06/2024 00:08:40 - 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] 2024-09-06 00:08:59,880 >> 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] 2024-09-06 00:08:59,883 >> Model config RobertaConfig {
+  "_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-ENFERMEDAD",
+    "2": "I-ENFERMEDAD",
+    "3": "B-PROCEDIMIENTO",
+    "4": "I-PROCEDIMIENTO",
+    "5": "B-SINTOMA",
+    "6": "I-SINTOMA",
+    "7": "B-FARMACO",
+    "8": "I-FARMACO"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ENFERMEDAD": 1,
+    "B-FARMACO": 7,
+    "B-PROCEDIMIENTO": 3,
+    "B-SINTOMA": 5,
+    "I-ENFERMEDAD": 2,
+    "I-FARMACO": 8,
+    "I-PROCEDIMIENTO": 4,
+    "I-SINTOMA": 6,
+    "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] 2024-09-06 00:09:00,140 >> 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] 2024-09-06 00:09:00,140 >> 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] 2024-09-06 00:09:00,153 >> 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] 2024-09-06 00:09:00,153 >> 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] 2024-09-06 00:09:00,153 >> loading file tokenizer.json from cache at None
+[INFO|tokenization_utils_base.py:2269] 2024-09-06 00:09:00,153 >> loading file added_tokens.json from cache at None
+[INFO|tokenization_utils_base.py:2269] 2024-09-06 00:09:00,153 >> 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] 2024-09-06 00:09:00,153 >> 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] 2024-09-06 00:09:00,153 >> 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] 2024-09-06 00:09:00,154 >> 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] 2024-09-06 00:09:00,236 >> 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] 2024-09-06 00:09:00,238 >> 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] 2024-09-06 00:09:00,573 >> 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] 2024-09-06 00:09:00,651 >> 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] 2024-09-06 00:09:00,651 >> 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] 2024-09-06 00:09:07,817 >> 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] 2024-09-06 00:09:08,371 >> ***** Running training *****
+[INFO|trainer.py:2135] 2024-09-06 00:09:08,371 >>   Num examples = 34,604
+[INFO|trainer.py:2136] 2024-09-06 00:09:08,371 >>   Num Epochs = 10
+[INFO|trainer.py:2137] 2024-09-06 00:09:08,371 >>   Instantaneous batch size per device = 32
+[INFO|trainer.py:2140] 2024-09-06 00:09:08,371 >>   Total train batch size (w. parallel, distributed & accumulation) = 64
+[INFO|trainer.py:2141] 2024-09-06 00:09:08,371 >>   Gradient Accumulation steps = 2
+[INFO|trainer.py:2142] 2024-09-06 00:09:08,371 >>   Total optimization steps = 5,410
+[INFO|trainer.py:2143] 2024-09-06 00:09:08,372 >>   Number of trainable parameters = 124,059,657
+
  0%|          | 0/5410 [00:00<?, ?it/s]
  0%|          | 1/5410 [00:01<1:40:31,  1.12s/it]
  0%|          | 2/5410 [00:01<58:59,  1.53it/s]  
  0%|          | 3/5410 [00:01<43:24,  2.08it/s]
  0%|          | 4/5410 [00:01<34:13,  2.63it/s]
  0%|          | 5/5410 [00:02<29:11,  3.09it/s]
  0%|          | 6/5410 [00:02<25:31,  3.53it/s]
  0%|          | 7/5410 [00:02<23:30,  3.83it/s]
  0%|          | 8/5410 [00:02<25:15,  3.57it/s]
  0%|          | 9/5410 [00:03<22:25,  4.02it/s]
  0%|          | 10/5410 [00:03<21:21,  4.22it/s]
  0%|          | 11/5410 [00:03<20:43,  4.34it/s]
  0%|          | 12/5410 [00:03<19:48,  4.54it/s]
  0%|          | 13/5410 [00:03<20:51,  4.31it/s]
  0%|          | 14/5410 [00:04<22:33,  3.99it/s]
  0%|          | 15/5410 [00:04<22:51,  3.93it/s]
  0%|          | 16/5410 [00:04<22:45,  3.95it/s]
  0%|          | 17/5410 [00:04<21:37,  4.16it/s]
  0%|          | 18/5410 [00:05<21:15,  4.23it/s]
  0%|          | 19/5410 [00:05<21:17,  4.22it/s]
  0%|          | 20/5410 [00:05<22:33,  3.98it/s]
  0%|          | 21/5410 [00:05<21:27,  4.19it/s]
  0%|          | 22/5410 [00:06<19:54,  4.51it/s]
  0%|          | 23/5410 [00:06<21:05,  4.26it/s]
  0%|          | 24/5410 [00:06<22:13,  4.04it/s]
  0%|          | 25/5410 [00:06<22:20,  4.02it/s]
  0%|          | 26/5410 [00:07<22:12,  4.04it/s]
  0%|          | 27/5410 [00:07<22:20,  4.02it/s]
  1%|          | 28/5410 [00:07<27:25,  3.27it/s]
  1%|          | 29/5410 [00:08<28:15,  3.17it/s]
  1%|          | 30/5410 [00:08<29:25,  3.05it/s]
  1%|          | 31/5410 [00:08<28:51,  3.11it/s]
  1%|          | 32/5410 [00:09<26:54,  3.33it/s]
  1%|          | 33/5410 [00:09<29:44,  3.01it/s]
  1%|          | 34/5410 [00:09<26:00,  3.45it/s]
  1%|          | 35/5410 [00:09<24:56,  3.59it/s]
  1%|          | 36/5410 [00:10<22:37,  3.96it/s]
  1%|          | 37/5410 [00:10<23:34,  3.80it/s]
  1%|          | 38/5410 [00:10<21:40,  4.13it/s]
  1%|          | 39/5410 [00:10<23:12,  3.86it/s]
  1%|          | 40/5410 [00:11<23:32,  3.80it/s]
  1%|          | 41/5410 [00:11<22:26,  3.99it/s]
  1%|          | 42/5410 [00:11<22:45,  3.93it/s]
  1%|          | 43/5410 [00:11<23:43,  3.77it/s]
  1%|          | 44/5410 [00:12<22:05,  4.05it/s]
  1%|          | 45/5410 [00:12<20:37,  4.34it/s]
  1%|          | 46/5410 [00:12<20:31,  4.36it/s]
  1%|          | 47/5410 [00:13<25:28,  3.51it/s]
  1%|          | 48/5410 [00:13<25:50,  3.46it/s]
  1%|          | 49/5410 [00:13<23:45,  3.76it/s]
  1%|          | 50/5410 [00:13<22:52,  3.91it/s]
  1%|          | 51/5410 [00:14<24:47,  3.60it/s]
  1%|          | 52/5410 [00:14<23:28,  3.80it/s]
  1%|          | 53/5410 [00:14<23:00,  3.88it/s]
  1%|          | 54/5410 [00:14<24:12,  3.69it/s]
  1%|          | 55/5410 [00:15<23:36,  3.78it/s]
  1%|          | 56/5410 [00:15<21:37,  4.13it/s]
  1%|          | 57/5410 [00:15<21:49,  4.09it/s]
  1%|          | 58/5410 [00:15<20:27,  4.36it/s]
  1%|          | 59/5410 [00:16<21:47,  4.09it/s]
  1%|          | 60/5410 [00:16<20:40,  4.31it/s]
  1%|          | 61/5410 [00:16<21:26,  4.16it/s]
  1%|          | 62/5410 [00:16<20:04,  4.44it/s]
  1%|          | 63/5410 [00:16<20:16,  4.40it/s]
  1%|          | 64/5410 [00:17<22:58,  3.88it/s]
  1%|          | 65/5410 [00:17<27:23,  3.25it/s]
  1%|          | 66/5410 [00:17<27:00,  3.30it/s]
  1%|          | 67/5410 [00:18<25:55,  3.43it/s]
  1%|▏         | 68/5410 [00:18<23:46,  3.74it/s]
  1%|▏         | 69/5410 [00:18<22:40,  3.93it/s]
  1%|▏         | 70/5410 [00:18<21:51,  4.07it/s]
  1%|▏         | 71/5410 [00:19<33:07,  2.69it/s]
  1%|▏         | 72/5410 [00:19<28:19,  3.14it/s]
  1%|▏         | 73/5410 [00:20<28:30,  3.12it/s]
  1%|▏         | 74/5410 [00:20<26:17,  3.38it/s]
  1%|▏         | 75/5410 [00:20<23:47,  3.74it/s]
  1%|▏         | 76/5410 [00:20<21:30,  4.13it/s]
  1%|▏         | 77/5410 [00:20<23:01,  3.86it/s]
  1%|▏         | 78/5410 [00:21<21:45,  4.08it/s]
  1%|▏         | 79/5410 [00:21<22:11,  4.00it/s]
  1%|▏         | 80/5410 [00:21<23:38,  3.76it/s]
  1%|▏         | 81/5410 [00:21<22:22,  3.97it/s]
  2%|▏         | 82/5410 [00:22<21:28,  4.14it/s]
  2%|▏         | 83/5410 [00:22<21:06,  4.21it/s]
  2%|▏         | 84/5410 [00:22<22:05,  4.02it/s]
  2%|▏         | 85/5410 [00:23<23:22,  3.80it/s]
  2%|▏         | 86/5410 [00:23<20:59,  4.23it/s]
  2%|▏         | 87/5410 [00:23<19:42,  4.50it/s]
  2%|▏         | 88/5410 [00:23<21:51,  4.06it/s]
  2%|▏         | 89/5410 [00:23<20:32,  4.32it/s]
  2%|▏         | 90/5410 [00:24<20:06,  4.41it/s]
  2%|▏         | 91/5410 [00:24<24:33,  3.61it/s]
  2%|▏         | 92/5410 [00:24<22:44,  3.90it/s]
  2%|▏         | 93/5410 [00:24<21:26,  4.13it/s]
  2%|▏         | 94/5410 [00:25<22:10,  4.00it/s]
  2%|▏         | 95/5410 [00:25<21:57,  4.03it/s]
  2%|▏         | 96/5410 [00:25<21:22,  4.14it/s]
  2%|▏         | 97/5410 [00:25<21:05,  4.20it/s]
  2%|▏         | 98/5410 [00:26<20:12,  4.38it/s]
  2%|▏         | 99/5410 [00:26<22:49,  3.88it/s]
  2%|▏         | 100/5410 [00:26<23:27,  3.77it/s]
  2%|▏         | 101/5410 [00:26<22:45,  3.89it/s]
  2%|▏         | 102/5410 [00:27<20:54,  4.23it/s]
  2%|▏         | 103/5410 [00:27<19:02,  4.65it/s]
  2%|▏         | 104/5410 [00:27<17:33,  5.04it/s]
  2%|▏         | 105/5410 [00:27<16:34,  5.33it/s]
  2%|▏         | 106/5410 [00:27<18:00,  4.91it/s]
  2%|▏         | 107/5410 [00:28<18:40,  4.73it/s]
  2%|▏         | 108/5410 [00:28<20:57,  4.22it/s]
  2%|▏         | 109/5410 [00:28<19:29,  4.53it/s]
  2%|▏         | 110/5410 [00:28<22:31,  3.92it/s]
  2%|▏         | 111/5410 [00:29<22:22,  3.95it/s]
  2%|▏         | 112/5410 [00:29<20:19,  4.34it/s]
  2%|▏         | 113/5410 [00:29<22:55,  3.85it/s]
  2%|▏         | 114/5410 [00:29<21:57,  4.02it/s]
  2%|▏         | 115/5410 [00:30<21:22,  4.13it/s]
  2%|▏         | 116/5410 [00:30<28:02,  3.15it/s]
  2%|▏         | 117/5410 [00:30<25:04,  3.52it/s]
  2%|▏         | 118/5410 [00:31<23:46,  3.71it/s]
  2%|▏         | 119/5410 [00:31<22:11,  3.97it/s]
  2%|▏         | 120/5410 [00:31<21:54,  4.02it/s]
  2%|▏         | 121/5410 [00:31<20:23,  4.32it/s]
  2%|▏         | 122/5410 [00:32<23:15,  3.79it/s]
  2%|▏         | 123/5410 [00:32<21:18,  4.13it/s]
  2%|▏         | 124/5410 [00:32<21:21,  4.13it/s]
  2%|▏         | 125/5410 [00:32<21:33,  4.08it/s]
  2%|▏         | 126/5410 [00:32<20:09,  4.37it/s]
  2%|▏         | 127/5410 [00:33<20:09,  4.37it/s]
  2%|▏         | 128/5410 [00:33<24:00,  3.67it/s]
  2%|▏         | 129/5410 [00:33<23:09,  3.80it/s]
  2%|▏         | 130/5410 [00:33<21:16,  4.14it/s]
  2%|▏         | 131/5410 [00:34<20:26,  4.31it/s]
  2%|▏         | 132/5410 [00:34<23:28,  3.75it/s]
  2%|▏         | 133/5410 [00:34<21:11,  4.15it/s]
  2%|▏         | 134/5410 [00:34<20:25,  4.31it/s]
  2%|▏         | 135/5410 [00:35<19:41,  4.46it/s]
  3%|▎         | 136/5410 [00:35<26:01,  3.38it/s]
  3%|▎         | 137/5410 [00:35<26:07,  3.36it/s]
  3%|▎         | 138/5410 [00:36<23:27,  3.75it/s]
  3%|▎         | 139/5410 [00:36<24:01,  3.66it/s]
  3%|▎         | 140/5410 [00:36<23:02,  3.81it/s]
  3%|▎         | 141/5410 [00:36<20:31,  4.28it/s]
  3%|▎         | 142/5410 [00:36<20:58,  4.19it/s]
  3%|▎         | 143/5410 [00:37<21:31,  4.08it/s]
  3%|▎         | 144/5410 [00:37<21:51,  4.02it/s]
  3%|▎         | 145/5410 [00:37<20:44,  4.23it/s]
  3%|▎         | 146/5410 [00:37<20:40,  4.24it/s]
  3%|▎         | 147/5410 [00:38<19:45,  4.44it/s]
  3%|▎         | 148/5410 [00:38<19:53,  4.41it/s]
  3%|▎         | 149/5410 [00:38<21:47,  4.02it/s]
  3%|▎         | 150/5410 [00:38<20:19,  4.31it/s]
  3%|▎         | 151/5410 [00:39<19:15,  4.55it/s]
  3%|▎         | 152/5410 [00:39<19:58,  4.39it/s]
  3%|▎         | 153/5410 [00:39<20:11,  4.34it/s]
  3%|▎         | 154/5410 [00:39<20:53,  4.19it/s]
  3%|▎         | 155/5410 [00:40<20:22,  4.30it/s]
  3%|▎         | 156/5410 [00:40<21:26,  4.08it/s]
  3%|▎         | 157/5410 [00:40<21:19,  4.10it/s]
  3%|▎         | 158/5410 [00:40<21:22,  4.10it/s]
  3%|▎         | 159/5410 [00:40<20:22,  4.29it/s]
  3%|▎         | 160/5410 [00:41<20:28,  4.27it/s]
  3%|▎         | 161/5410 [00:41<20:38,  4.24it/s]
  3%|▎         | 162/5410 [00:41<21:29,  4.07it/s]
  3%|▎         | 163/5410 [00:41<21:16,  4.11it/s]
  3%|▎         | 164/5410 [00:42<25:12,  3.47it/s]
  3%|▎         | 165/5410 [00:42<23:45,  3.68it/s]
  3%|▎         | 166/5410 [00:42<21:04,  4.15it/s]
  3%|▎         | 167/5410 [00:42<20:29,  4.26it/s]
  3%|▎         | 168/5410 [00:43<21:13,  4.12it/s]
  3%|▎         | 169/5410 [00:43<20:22,  4.29it/s]
  3%|▎         | 170/5410 [00:43<18:20,  4.76it/s]
  3%|▎         | 171/5410 [00:43<20:23,  4.28it/s]
  3%|▎         | 172/5410 [00:44<20:23,  4.28it/s]
  3%|▎         | 173/5410 [00:44<24:14,  3.60it/s]
  3%|▎         | 174/5410 [00:44<24:04,  3.63it/s]
  3%|▎         | 175/5410 [00:45<26:36,  3.28it/s]
  3%|▎         | 176/5410 [00:45<24:13,  3.60it/s]
  3%|▎         | 177/5410 [00:45<23:54,  3.65it/s]
  3%|▎         | 178/5410 [00:45<24:15,  3.59it/s]
  3%|▎         | 179/5410 [00:46<23:26,  3.72it/s]
  3%|▎         | 180/5410 [00:46<21:59,  3.96it/s]
  3%|▎         | 181/5410 [00:46<20:21,  4.28it/s]
  3%|▎         | 182/5410 [00:46<19:25,  4.48it/s]
  3%|▎         | 183/5410 [00:46<18:48,  4.63it/s]
  3%|▎         | 184/5410 [00:47<20:39,  4.22it/s]
  3%|▎         | 185/5410 [00:47<21:26,  4.06it/s]
  3%|▎         | 186/5410 [00:47<20:39,  4.22it/s]
  3%|▎         | 187/5410 [00:48<21:25,  4.06it/s]
  3%|▎         | 188/5410 [00:48<20:00,  4.35it/s]
  3%|▎         | 189/5410 [00:48<19:15,  4.52it/s]
  4%|▎         | 190/5410 [00:48<18:03,  4.82it/s]
  4%|▎         | 191/5410 [00:48<19:03,  4.56it/s]
  4%|▎         | 192/5410 [00:49<22:49,  3.81it/s]
  4%|▎         | 193/5410 [00:49<21:59,  3.95it/s]
  4%|▎         | 194/5410 [00:49<21:51,  3.98it/s]
  4%|▎         | 195/5410 [00:49<21:56,  3.96it/s]
  4%|▎         | 196/5410 [00:50<21:15,  4.09it/s]
  4%|▎         | 197/5410 [00:50<25:23,  3.42it/s]
  4%|▎         | 198/5410 [00:50<25:06,  3.46it/s]
  4%|▎         | 199/5410 [00:51<24:18,  3.57it/s]
  4%|▎         | 200/5410 [00:51<25:39,  3.38it/s]
  4%|▎         | 201/5410 [00:51<24:03,  3.61it/s]
  4%|▎         | 202/5410 [00:52<33:15,  2.61it/s]
  4%|▍         | 203/5410 [00:52<29:17,  2.96it/s]
  4%|▍         | 204/5410 [00:52<27:28,  3.16it/s]
  4%|▍         | 205/5410 [00:52<24:16,  3.57it/s]
  4%|▍         | 206/5410 [00:53<21:32,  4.03it/s]
  4%|▍         | 207/5410 [00:53<20:50,  4.16it/s]
  4%|▍         | 208/5410 [00:53<20:18,  4.27it/s]
  4%|▍         | 209/5410 [00:53<19:47,  4.38it/s]
  4%|▍         | 210/5410 [00:54<20:15,  4.28it/s]
  4%|▍         | 211/5410 [00:54<21:13,  4.08it/s]
  4%|▍         | 212/5410 [00:54<20:20,  4.26it/s]
  4%|▍         | 213/5410 [00:54<19:38,  4.41it/s]
  4%|▍         | 214/5410 [00:54<18:28,  4.69it/s]
  4%|▍         | 215/5410 [00:55<19:12,  4.51it/s]
  4%|▍         | 216/5410 [00:55<18:21,  4.72it/s]
  4%|▍         | 217/5410 [00:55<17:43,  4.88it/s]
  4%|▍         | 218/5410 [00:55<18:01,  4.80it/s]
  4%|▍         | 219/5410 [00:56<25:27,  3.40it/s]
  4%|▍         | 220/5410 [00:56<24:12,  3.57it/s]
  4%|▍         | 221/5410 [00:56<21:48,  3.97it/s]
  4%|▍         | 222/5410 [00:56<20:57,  4.13it/s]
  4%|▍         | 223/5410 [00:57<19:16,  4.48it/s]
  4%|▍         | 224/5410 [00:57<18:11,  4.75it/s]
  4%|▍         | 225/5410 [00:57<18:08,  4.76it/s]
  4%|▍         | 226/5410 [00:57<18:19,  4.72it/s]
  4%|▍         | 227/5410 [00:57<18:07,  4.77it/s]
  4%|▍         | 228/5410 [00:58<19:53,  4.34it/s]
  4%|▍         | 229/5410 [00:58<20:59,  4.11it/s]
  4%|▍         | 230/5410 [00:58<20:43,  4.17it/s]
  4%|▍         | 231/5410 [00:58<19:19,  4.47it/s]
  4%|▍         | 232/5410 [00:59<20:24,  4.23it/s]
  4%|▍         | 233/5410 [00:59<19:32,  4.41it/s]
  4%|▍         | 234/5410 [00:59<20:52,  4.13it/s]
  4%|▍         | 235/5410 [00:59<19:19,  4.46it/s]
  4%|▍         | 236/5410 [01:00<20:38,  4.18it/s]
  4%|▍         | 237/5410 [01:00<20:05,  4.29it/s]
  4%|▍         | 238/5410 [01:00<21:14,  4.06it/s]
  4%|▍         | 239/5410 [01:00<20:24,  4.22it/s]
  4%|▍         | 240/5410 [01:01<20:00,  4.31it/s]
  4%|▍         | 241/5410 [01:01<32:09,  2.68it/s]
  4%|▍         | 242/5410 [01:02<30:23,  2.83it/s]
  4%|▍         | 243/5410 [01:02<30:24,  2.83it/s]
  5%|▍         | 244/5410 [01:02<27:11,  3.17it/s]
  5%|▍         | 245/5410 [01:02<25:58,  3.31it/s]
  5%|▍         | 246/5410 [01:03<25:30,  3.37it/s]
  5%|▍         | 247/5410 [01:03<26:02,  3.31it/s]
  5%|▍         | 248/5410 [01:03<27:39,  3.11it/s]
  5%|▍         | 249/5410 [01:04<24:09,  3.56it/s]
  5%|▍         | 250/5410 [01:04<21:10,  4.06it/s]
  5%|▍         | 251/5410 [01:04<21:25,  4.01it/s]
  5%|▍         | 252/5410 [01:04<20:45,  4.14it/s]
  5%|▍         | 253/5410 [01:04<21:34,  3.98it/s]
  5%|▍         | 254/5410 [01:05<20:53,  4.11it/s]
  5%|▍         | 255/5410 [01:05<20:27,  4.20it/s]
  5%|▍         | 256/5410 [01:05<20:24,  4.21it/s]
  5%|▍         | 257/5410 [01:05<20:09,  4.26it/s]
  5%|▍         | 258/5410 [01:06<19:00,  4.52it/s]
  5%|▍         | 259/5410 [01:06<18:36,  4.61it/s]
  5%|▍         | 260/5410 [01:06<20:09,  4.26it/s]
  5%|▍         | 261/5410 [01:06<22:16,  3.85it/s]
  5%|▍         | 262/5410 [01:07<21:29,  3.99it/s]
  5%|▍         | 263/5410 [01:07<22:15,  3.86it/s]
  5%|▍         | 264/5410 [01:07<22:15,  3.85it/s]
  5%|▍         | 265/5410 [01:07<22:25,  3.82it/s]
  5%|▍         | 266/5410 [01:08<21:33,  3.98it/s]
  5%|▍         | 267/5410 [01:08<20:28,  4.19it/s]
  5%|▍         | 268/5410 [01:08<20:06,  4.26it/s]
  5%|▍         | 269/5410 [01:08<22:14,  3.85it/s]
  5%|▍         | 270/5410 [01:09<21:09,  4.05it/s]
  5%|▌         | 271/5410 [01:09<19:16,  4.44it/s]
  5%|▌         | 272/5410 [01:09<22:35,  3.79it/s]
  5%|▌         | 273/5410 [01:09<20:40,  4.14it/s]
  5%|▌         | 274/5410 [01:09<19:25,  4.41it/s]
  5%|▌         | 275/5410 [01:10<18:52,  4.54it/s]
  5%|▌         | 276/5410 [01:10<18:20,  4.66it/s]
  5%|▌         | 277/5410 [01:10<17:55,  4.77it/s]
  5%|▌         | 278/5410 [01:10<19:54,  4.30it/s]
  5%|▌         | 279/5410 [01:11<19:16,  4.44it/s]
  5%|▌         | 280/5410 [01:11<21:40,  3.95it/s]
  5%|▌         | 281/5410 [01:11<21:06,  4.05it/s]
  5%|▌         | 282/5410 [01:12<24:46,  3.45it/s]
  5%|▌         | 283/5410 [01:12<23:25,  3.65it/s]
  5%|▌         | 284/5410 [01:12<21:42,  3.94it/s]
  5%|▌         | 285/5410 [01:12<22:28,  3.80it/s]
  5%|▌         | 286/5410 [01:12<20:07,  4.24it/s]
  5%|▌         | 287/5410 [01:13<21:38,  3.95it/s]
  5%|▌         | 288/5410 [01:13<21:41,  3.93it/s]
  5%|▌         | 289/5410 [01:13<21:05,  4.05it/s]
  5%|▌         | 290/5410 [01:13<21:43,  3.93it/s]
  5%|▌         | 291/5410 [01:14<21:16,  4.01it/s]
  5%|▌         | 292/5410 [01:14<22:53,  3.73it/s]
  5%|▌         | 293/5410 [01:14<23:09,  3.68it/s]
  5%|▌         | 294/5410 [01:15<22:52,  3.73it/s]
  5%|▌         | 295/5410 [01:15<22:31,  3.78it/s]
  5%|▌         | 296/5410 [01:15<21:38,  3.94it/s]
  5%|▌         | 297/5410 [01:15<20:29,  4.16it/s]
  6%|▌         | 298/5410 [01:15<19:46,  4.31it/s]
  6%|▌         | 299/5410 [01:16<18:59,  4.49it/s]
  6%|▌         | 300/5410 [01:16<19:43,  4.32it/s]
  6%|▌         | 301/5410 [01:16<18:43,  4.55it/s]
  6%|▌         | 302/5410 [01:16<18:59,  4.48it/s]
  6%|▌         | 303/5410 [01:17<18:09,  4.69it/s]
  6%|▌         | 304/5410 [01:17<20:55,  4.07it/s]
  6%|▌         | 305/5410 [01:17<20:44,  4.10it/s]
  6%|▌         | 306/5410 [01:17<23:57,  3.55it/s]
  6%|▌         | 307/5410 [01:18<26:56,  3.16it/s]
  6%|▌         | 308/5410 [01:18<24:56,  3.41it/s]
  6%|▌         | 309/5410 [01:18<23:01,  3.69it/s]
  6%|▌         | 310/5410 [01:19<24:04,  3.53it/s]
  6%|▌         | 311/5410 [01:19<21:55,  3.88it/s]
  6%|▌         | 312/5410 [01:19<21:11,  4.01it/s]
  6%|▌         | 313/5410 [01:19<19:58,  4.25it/s]
  6%|▌         | 314/5410 [01:20<20:12,  4.20it/s]
  6%|▌         | 315/5410 [01:20<24:21,  3.49it/s]
  6%|▌         | 316/5410 [01:20<22:59,  3.69it/s]
  6%|▌         | 317/5410 [01:20<20:56,  4.05it/s]
  6%|▌         | 318/5410 [01:21<20:36,  4.12it/s]
  6%|▌         | 319/5410 [01:21<20:12,  4.20it/s]
  6%|▌         | 320/5410 [01:21<19:45,  4.29it/s]
  6%|▌         | 321/5410 [01:21<19:08,  4.43it/s]
  6%|▌         | 322/5410 [01:21<19:37,  4.32it/s]
  6%|▌         | 323/5410 [01:22<20:25,  4.15it/s]
  6%|▌         | 324/5410 [01:22<20:05,  4.22it/s]
  6%|▌         | 325/5410 [01:22<18:12,  4.66it/s]
  6%|▌         | 326/5410 [01:22<18:52,  4.49it/s]
  6%|▌         | 327/5410 [01:23<19:50,  4.27it/s]
  6%|▌         | 328/5410 [01:23<18:32,  4.57it/s]
  6%|▌         | 329/5410 [01:23<18:52,  4.49it/s]
  6%|▌         | 330/5410 [01:23<18:56,  4.47it/s]
  6%|▌         | 331/5410 [01:24<20:49,  4.07it/s]
  6%|▌         | 332/5410 [01:24<20:11,  4.19it/s]
  6%|▌         | 333/5410 [01:24<20:41,  4.09it/s]
  6%|▌         | 334/5410 [01:24<20:59,  4.03it/s]
  6%|▌         | 335/5410 [01:25<21:19,  3.97it/s]
  6%|▌         | 336/5410 [01:25<20:56,  4.04it/s]
  6%|▌         | 337/5410 [01:25<21:43,  3.89it/s]
  6%|▌         | 338/5410 [01:25<24:03,  3.51it/s]
  6%|▋         | 339/5410 [01:26<24:53,  3.39it/s]
  6%|▋         | 340/5410 [01:26<24:13,  3.49it/s]
  6%|▋         | 341/5410 [01:26<23:02,  3.67it/s]
  6%|▋         | 342/5410 [01:27<23:50,  3.54it/s]
  6%|▋         | 343/5410 [01:27<26:01,  3.24it/s]
  6%|▋         | 344/5410 [01:27<22:43,  3.72it/s]
  6%|▋         | 345/5410 [01:27<24:18,  3.47it/s]
  6%|▋         | 346/5410 [01:28<23:45,  3.55it/s]
  6%|▋         | 347/5410 [01:28<21:22,  3.95it/s]
  6%|▋         | 348/5410 [01:28<20:16,  4.16it/s]
  6%|▋         | 349/5410 [01:28<21:42,  3.88it/s]
  6%|▋         | 350/5410 [01:29<20:03,  4.20it/s]
  6%|▋         | 351/5410 [01:29<22:11,  3.80it/s]
  7%|▋         | 352/5410 [01:29<21:50,  3.86it/s]
  7%|▋         | 353/5410 [01:29<20:18,  4.15it/s]
  7%|▋         | 354/5410 [01:30<20:35,  4.09it/s]
  7%|▋         | 355/5410 [01:30<22:38,  3.72it/s]
  7%|▋         | 356/5410 [01:30<24:41,  3.41it/s]
  7%|▋         | 357/5410 [01:31<23:58,  3.51it/s]
  7%|▋         | 358/5410 [01:31<25:43,  3.27it/s]
  7%|▋         | 359/5410 [01:31<24:02,  3.50it/s]
  7%|▋         | 360/5410 [01:31<23:11,  3.63it/s]
  7%|▋         | 361/5410 [01:32<22:19,  3.77it/s]
  7%|▋         | 362/5410 [01:32<23:53,  3.52it/s]
  7%|▋         | 363/5410 [01:32<22:17,  3.77it/s]
  7%|▋         | 364/5410 [01:32<21:41,  3.88it/s]
  7%|▋         | 365/5410 [01:33<21:30,  3.91it/s]
  7%|▋         | 366/5410 [01:33<19:34,  4.29it/s]
  7%|▋         | 367/5410 [01:33<19:13,  4.37it/s]
  7%|▋         | 368/5410 [01:33<19:50,  4.23it/s]
  7%|▋         | 369/5410 [01:34<18:53,  4.45it/s]
  7%|▋         | 370/5410 [01:34<18:06,  4.64it/s]
  7%|▋         | 371/5410 [01:34<20:18,  4.14it/s]
  7%|▋         | 372/5410 [01:34<18:59,  4.42it/s]
  7%|▋         | 373/5410 [01:34<17:29,  4.80it/s]
  7%|▋         | 374/5410 [01:35<16:23,  5.12it/s]
  7%|▋         | 375/5410 [01:35<22:14,  3.77it/s]
  7%|▋         | 376/5410 [01:35<22:14,  3.77it/s]
  7%|▋         | 377/5410 [01:36<22:01,  3.81it/s]
  7%|▋         | 378/5410 [01:36<21:05,  3.98it/s]
  7%|▋         | 379/5410 [01:36<21:24,  3.92it/s]
  7%|▋         | 380/5410 [01:36<24:42,  3.39it/s]
  7%|▋         | 381/5410 [01:37<22:33,  3.72it/s]
  7%|▋         | 382/5410 [01:37<25:11,  3.33it/s]
  7%|▋         | 383/5410 [01:37<23:03,  3.63it/s]
  7%|▋         | 384/5410 [01:37<23:26,  3.57it/s]
  7%|▋         | 385/5410 [01:38<21:39,  3.87it/s]
  7%|▋         | 386/5410 [01:38<21:21,  3.92it/s]
  7%|▋         | 387/5410 [01:38<19:38,  4.26it/s]
  7%|▋         | 388/5410 [01:38<18:59,  4.41it/s]
  7%|▋         | 389/5410 [01:39<17:55,  4.67it/s]
  7%|▋         | 390/5410 [01:39<21:16,  3.93it/s]
  7%|▋         | 391/5410 [01:39<21:05,  3.97it/s]
  7%|▋         | 392/5410 [01:39<22:07,  3.78it/s]
  7%|▋         | 393/5410 [01:40<21:48,  3.83it/s]
  7%|▋         | 394/5410 [01:40<19:48,  4.22it/s]
  7%|▋         | 395/5410 [01:40<18:36,  4.49it/s]
  7%|▋         | 396/5410 [01:40<18:17,  4.57it/s]
  7%|▋         | 397/5410 [01:40<17:26,  4.79it/s]
  7%|▋         | 398/5410 [01:41<18:24,  4.54it/s]
  7%|▋         | 399/5410 [01:41<21:28,  3.89it/s]
  7%|▋         | 400/5410 [01:41<20:26,  4.09it/s]
  7%|▋         | 401/5410 [01:42<22:30,  3.71it/s]
  7%|▋         | 402/5410 [01:42<20:05,  4.15it/s]
  7%|▋         | 403/5410 [01:42<19:20,  4.32it/s]
  7%|▋         | 404/5410 [01:42<23:50,  3.50it/s]
  7%|▋         | 405/5410 [01:43<22:24,  3.72it/s]
  8%|▊         | 406/5410 [01:43<21:34,  3.87it/s]
  8%|▊         | 407/5410 [01:43<26:44,  3.12it/s]
  8%|▊         | 408/5410 [01:43<24:04,  3.46it/s]
  8%|▊         | 409/5410 [01:44<29:51,  2.79it/s]
  8%|▊         | 410/5410 [01:44<27:08,  3.07it/s]
  8%|▊         | 411/5410 [01:44<24:27,  3.41it/s]
  8%|▊         | 412/5410 [01:45<21:55,  3.80it/s]
  8%|▊         | 413/5410 [01:45<22:05,  3.77it/s]
  8%|▊         | 414/5410 [01:45<22:19,  3.73it/s]
  8%|▊         | 415/5410 [01:45<21:01,  3.96it/s]
  8%|▊         | 416/5410 [01:46<20:28,  4.07it/s]
  8%|▊         | 417/5410 [01:46<21:59,  3.78it/s]
  8%|▊         | 418/5410 [01:46<21:16,  3.91it/s]
  8%|▊         | 419/5410 [01:46<20:46,  4.00it/s]
  8%|▊         | 420/5410 [01:47<20:30,  4.05it/s]
  8%|▊         | 421/5410 [01:47<22:46,  3.65it/s]
  8%|▊         | 422/5410 [01:47<19:57,  4.17it/s]
  8%|▊         | 423/5410 [01:47<18:42,  4.44it/s]
  8%|▊         | 424/5410 [01:48<17:53,  4.65it/s]
  8%|▊         | 425/5410 [01:48<17:43,  4.69it/s]
  8%|▊         | 426/5410 [01:48<18:12,  4.56it/s]
  8%|▊         | 427/5410 [01:48<17:29,  4.75it/s]
  8%|▊         | 428/5410 [01:48<18:22,  4.52it/s]
  8%|▊         | 429/5410 [01:49<21:50,  3.80it/s]
  8%|▊         | 430/5410 [01:49<23:28,  3.54it/s]
  8%|▊         | 431/5410 [01:49<23:45,  3.49it/s]
  8%|▊         | 432/5410 [01:50<21:21,  3.89it/s]
  8%|▊         | 433/5410 [01:50<22:22,  3.71it/s]
  8%|▊         | 434/5410 [01:50<20:57,  3.96it/s]
  8%|▊         | 435/5410 [01:50<20:26,  4.06it/s]
  8%|▊         | 436/5410 [01:51<20:08,  4.12it/s]
  8%|▊         | 437/5410 [01:51<18:59,  4.37it/s]
  8%|▊         | 438/5410 [01:51<20:03,  4.13it/s]
  8%|▊         | 439/5410 [01:51<20:14,  4.09it/s]
  8%|▊         | 440/5410 [01:52<26:54,  3.08it/s]
  8%|▊         | 441/5410 [01:52<24:06,  3.44it/s]
  8%|▊         | 442/5410 [01:52<23:37,  3.50it/s]
  8%|▊         | 443/5410 [01:52<21:10,  3.91it/s]
  8%|▊         | 444/5410 [01:53<20:28,  4.04it/s]
  8%|▊         | 445/5410 [01:53<20:39,  4.01it/s]
  8%|▊         | 446/5410 [01:53<18:55,  4.37it/s]
  8%|▊         | 447/5410 [01:53<18:48,  4.40it/s]
  8%|▊         | 448/5410 [01:54<17:53,  4.62it/s]
  8%|▊         | 449/5410 [01:54<18:59,  4.35it/s]
  8%|▊         | 450/5410 [01:54<17:45,  4.66it/s]
  8%|▊         | 451/5410 [01:54<18:05,  4.57it/s]
  8%|▊         | 452/5410 [01:54<18:26,  4.48it/s]
  8%|▊         | 453/5410 [01:55<18:09,  4.55it/s]
  8%|▊         | 454/5410 [01:55<19:59,  4.13it/s]
  8%|▊         | 455/5410 [01:55<18:57,  4.36it/s]
  8%|▊         | 456/5410 [01:55<19:55,  4.14it/s]
  8%|▊         | 457/5410 [01:56<19:56,  4.14it/s]
  8%|▊         | 458/5410 [01:56<20:43,  3.98it/s]
  8%|▊         | 459/5410 [01:56<20:32,  4.02it/s]
  9%|▊         | 460/5410 [01:56<19:30,  4.23it/s]
  9%|▊         | 461/5410 [01:57<20:35,  4.01it/s]
  9%|▊         | 462/5410 [01:57<19:14,  4.29it/s]
  9%|▊         | 463/5410 [01:57<20:20,  4.05it/s]
  9%|▊         | 464/5410 [01:57<20:06,  4.10it/s]
  9%|▊         | 465/5410 [01:58<18:18,  4.50it/s]
  9%|▊         | 466/5410 [01:58<19:26,  4.24it/s]
  9%|▊         | 467/5410 [01:58<19:22,  4.25it/s]
  9%|▊         | 468/5410 [01:58<18:21,  4.49it/s]
  9%|▊         | 469/5410 [01:59<19:02,  4.32it/s]
  9%|▊         | 470/5410 [01:59<18:01,  4.57it/s]
  9%|▊         | 471/5410 [01:59<18:19,  4.49it/s]
  9%|▊         | 472/5410 [01:59<18:22,  4.48it/s]
  9%|▊         | 473/5410 [01:59<19:14,  4.28it/s]
  9%|▉         | 474/5410 [02:00<17:52,  4.60it/s]
  9%|▉         | 475/5410 [02:00<17:45,  4.63it/s]
  9%|▉         | 476/5410 [02:00<16:43,  4.92it/s]
  9%|▉         | 477/5410 [02:00<15:59,  5.14it/s]
  9%|▉         | 478/5410 [02:00<17:10,  4.78it/s]
  9%|▉         | 479/5410 [02:01<21:36,  3.80it/s]
  9%|▉         | 480/5410 [02:01<19:27,  4.22it/s]
  9%|▉         | 481/5410 [02:01<18:47,  4.37it/s]
  9%|▉         | 482/5410 [02:01<20:52,  3.93it/s]
  9%|▉         | 483/5410 [02:02<19:55,  4.12it/s]
  9%|▉         | 484/5410 [02:02<20:17,  4.05it/s]
  9%|▉         | 485/5410 [02:02<22:35,  3.63it/s]
  9%|▉         | 486/5410 [02:03<20:42,  3.96it/s]
  9%|▉         | 487/5410 [02:03<18:48,  4.36it/s]
  9%|▉         | 488/5410 [02:03<17:18,  4.74it/s]
  9%|▉         | 489/5410 [02:03<18:11,  4.51it/s]
  9%|▉         | 490/5410 [02:03<17:36,  4.66it/s]
  9%|▉         | 491/5410 [02:03<17:10,  4.77it/s]
  9%|▉         | 492/5410 [02:04<17:35,  4.66it/s]
  9%|▉         | 493/5410 [02:04<19:26,  4.22it/s]
  9%|▉         | 494/5410 [02:04<18:42,  4.38it/s]
  9%|▉         | 495/5410 [02:05<21:45,  3.76it/s]
  9%|▉         | 496/5410 [02:05<22:22,  3.66it/s]
  9%|▉         | 497/5410 [02:05<20:36,  3.97it/s]
  9%|▉         | 498/5410 [02:05<21:18,  3.84it/s]
  9%|▉         | 499/5410 [02:06<19:06,  4.28it/s]
  9%|▉         | 500/5410 [02:06<18:29,  4.43it/s]
                                                  
  9%|▉         | 500/5410 [02:06<18:29,  4.43it/s]
  9%|▉         | 501/5410 [02:06<18:43,  4.37it/s]
  9%|▉         | 502/5410 [02:06<18:29,  4.42it/s]
  9%|▉         | 503/5410 [02:06<17:26,  4.69it/s]
  9%|▉         | 504/5410 [02:07<17:33,  4.66it/s]
  9%|▉         | 505/5410 [02:07<17:53,  4.57it/s]
  9%|▉         | 506/5410 [02:07<18:29,  4.42it/s]
  9%|▉         | 507/5410 [02:07<18:50,  4.34it/s]
  9%|▉         | 508/5410 [02:07<17:35,  4.64it/s]
  9%|▉         | 509/5410 [02:08<16:20,  5.00it/s]
  9%|▉         | 510/5410 [02:08<17:54,  4.56it/s]
  9%|▉         | 511/5410 [02:08<18:53,  4.32it/s]
  9%|▉         | 512/5410 [02:08<20:06,  4.06it/s]
  9%|▉         | 513/5410 [02:09<18:22,  4.44it/s]
 10%|▉         | 514/5410 [02:09<19:14,  4.24it/s]
 10%|▉         | 515/5410 [02:09<19:57,  4.09it/s]
 10%|▉         | 516/5410 [02:09<21:51,  3.73it/s]
 10%|▉         | 517/5410 [02:10<21:01,  3.88it/s]
 10%|▉         | 518/5410 [02:10<19:54,  4.10it/s]
 10%|▉         | 519/5410 [02:10<19:24,  4.20it/s]
 10%|▉         | 520/5410 [02:10<21:01,  3.88it/s]
 10%|▉         | 521/5410 [02:11<23:02,  3.54it/s]
 10%|▉         | 522/5410 [02:11<21:22,  3.81it/s]
 10%|▉         | 523/5410 [02:11<21:17,  3.83it/s]
 10%|▉         | 524/5410 [02:11<20:15,  4.02it/s]
 10%|▉         | 525/5410 [02:12<19:22,  4.20it/s]
 10%|▉         | 526/5410 [02:12<19:22,  4.20it/s]
 10%|▉         | 527/5410 [02:12<19:21,  4.21it/s]
 10%|▉         | 528/5410 [02:12<18:40,  4.36it/s]
 10%|▉         | 529/5410 [02:13<19:47,  4.11it/s]
 10%|▉         | 530/5410 [02:13<18:33,  4.38it/s]
 10%|▉         | 531/5410 [02:13<19:05,  4.26it/s]
 10%|▉         | 532/5410 [02:13<18:18,  4.44it/s]
 10%|▉         | 533/5410 [02:14<19:46,  4.11it/s]
 10%|▉         | 534/5410 [02:14<19:08,  4.25it/s]
 10%|▉         | 535/5410 [02:14<17:33,  4.63it/s]
 10%|▉         | 536/5410 [02:14<20:17,  4.00it/s]
 10%|▉         | 537/5410 [02:15<19:11,  4.23it/s]
 10%|▉         | 538/5410 [02:15<19:15,  4.22it/s]
 10%|▉         | 539/5410 [02:15<19:19,  4.20it/s]
 10%|▉         | 540/5410 [02:16<32:00,  2.54it/s]
 10%|█         | 541/5410 [02:16<25:28,  3.18it/s][INFO|trainer.py:811] 2024-09-06 00:11:24,745 >> 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] 2024-09-06 00:11:24,747 >> 
+***** Running Evaluation *****
+[INFO|trainer.py:3821] 2024-09-06 00:11:24,747 >>   Num examples = 6810
+[INFO|trainer.py:3824] 2024-09-06 00:11:24,747 >>   Batch size = 8
+{'loss': 0.3191, 'grad_norm': 1.4528056383132935, 'learning_rate': 4.537892791127542e-05, 'epoch': 0.92}
+
+
  0%|          | 0/852 [00:00<?, ?it/s]
+
  1%|          | 10/852 [00:00<00:08, 94.22it/s]
+
  2%|▏         | 20/852 [00:00<00:09, 84.30it/s]
+
  3%|▎         | 29/852 [00:00<00:09, 82.68it/s]
+
  4%|▍         | 38/852 [00:00<00:09, 81.67it/s]
+
  6%|▌         | 47/852 [00:00<00:09, 82.09it/s]
+
  7%|▋         | 56/852 [00:00<00:09, 83.32it/s]
+
  8%|▊         | 65/852 [00:00<00:09, 81.98it/s]
+
  9%|▊         | 74/852 [00:00<00:09, 80.45it/s]
+
 10%|▉         | 83/852 [00:01<00:09, 79.95it/s]
+
 11%|█         | 92/852 [00:01<00:09, 80.23it/s]
+
 12%|█▏        | 101/852 [00:01<00:09, 79.90it/s]
+
 13%|█▎        | 109/852 [00:01<00:09, 79.80it/s]
+
 14%|█▍        | 118/852 [00:01<00:09, 80.74it/s]
+
 15%|█▍        | 127/852 [00:01<00:09, 76.94it/s]
+
 16%|█▌        | 135/852 [00:01<00:09, 77.57it/s]
+
 17%|█▋        | 143/852 [00:01<00:09, 77.84it/s]
+
 18%|█▊        | 151/852 [00:01<00:09, 77.26it/s]
+
 19%|█▉        | 160/852 [00:01<00:08, 79.83it/s]
+
 20%|█▉        | 169/852 [00:02<00:08, 80.18it/s]
+
 21%|██        | 178/852 [00:02<00:08, 80.61it/s]
+
 22%|██▏       | 187/852 [00:02<00:08, 81.27it/s]
+
 23%|██▎       | 196/852 [00:02<00:08, 81.22it/s]
+
 24%|██▍       | 205/852 [00:02<00:07, 82.14it/s]
+
 25%|██▌       | 214/852 [00:02<00:08, 78.56it/s]
+
 26%|██▌       | 223/852 [00:02<00:07, 79.93it/s]
+
 27%|██▋       | 232/852 [00:02<00:07, 81.20it/s]
+
 28%|██▊       | 241/852 [00:03<00:07, 78.11it/s]
+
 29%|██▉       | 250/852 [00:03<00:07, 79.54it/s]
+
 30%|███       | 259/852 [00:03<00:07, 80.76it/s]
+
 31%|███▏      | 268/852 [00:03<00:07, 80.54it/s]
+
 33%|███▎      | 277/852 [00:03<00:07, 81.44it/s]
+
 34%|███▎      | 286/852 [00:03<00:06, 82.18it/s]
+
 35%|███▍      | 295/852 [00:03<00:06, 80.52it/s]
+
 36%|███▌      | 304/852 [00:03<00:06, 81.59it/s]
+
 37%|███▋      | 313/852 [00:03<00:06, 79.63it/s]
+
 38%|███▊      | 322/852 [00:03<00:06, 81.30it/s]
+
 39%|███▉      | 331/852 [00:04<00:06, 80.35it/s]
+
 40%|███▉      | 340/852 [00:04<00:06, 80.39it/s]
+
 41%|████      | 349/852 [00:04<00:06, 80.42it/s]
+
 42%|████▏     | 358/852 [00:04<00:06, 78.16it/s]
+
 43%|████▎     | 367/852 [00:04<00:06, 78.26it/s]
+
 44%|████▍     | 375/852 [00:04<00:06, 78.36it/s]
+
 45%|████▍     | 383/852 [00:04<00:06, 77.78it/s]
+
 46%|████▌     | 392/852 [00:04<00:05, 79.06it/s]
+
 47%|████▋     | 400/852 [00:04<00:05, 78.80it/s]
+
 48%|████▊     | 408/852 [00:05<00:05, 76.89it/s]
+
 49%|████▉     | 417/852 [00:05<00:05, 78.38it/s]
+
 50%|████▉     | 425/852 [00:05<00:05, 77.18it/s]
+
 51%|█████     | 434/852 [00:05<00:05, 78.90it/s]
+
 52%|█████▏    | 443/852 [00:05<00:05, 79.74it/s]
+
 53%|█████▎    | 452/852 [00:05<00:04, 80.60it/s]
+
 54%|█████▍    | 461/852 [00:05<00:04, 79.04it/s]
+
 55%|█████▌    | 469/852 [00:05<00:04, 78.87it/s]
+
 56%|█████▌    | 477/852 [00:05<00:04, 76.18it/s]
+
 57%|█████▋    | 485/852 [00:06<00:04, 76.30it/s]
+
 58%|█████▊    | 494/852 [00:06<00:04, 78.74it/s]
+
 59%|█████▉    | 503/852 [00:06<00:04, 80.84it/s]
+
 60%|██████    | 512/852 [00:06<00:04, 81.29it/s]
+
 61%|██████    | 521/852 [00:06<00:04, 81.02it/s]
+
 62%|██████▏   | 530/852 [00:06<00:04, 80.47it/s]
+
 63%|██████▎   | 539/852 [00:06<00:03, 81.51it/s]
+
 64%|██████▍   | 548/852 [00:06<00:03, 81.69it/s]
+
 65%|██████▌   | 557/852 [00:06<00:03, 78.97it/s]
+
 66%|██████▋   | 566/852 [00:07<00:03, 80.53it/s]
+
 67%|██████▋   | 575/852 [00:07<00:03, 80.72it/s]
+
 69%|██████▊   | 584/852 [00:07<00:03, 78.77it/s]
+
 69%|██████▉   | 592/852 [00:07<00:03, 78.82it/s]
+
 70%|███████   | 600/852 [00:07<00:03, 78.94it/s]
+
 71%|███████▏  | 608/852 [00:07<00:03, 79.16it/s]
+
 72%|███████▏  | 616/852 [00:07<00:03, 77.17it/s]
+
 73%|███████▎  | 625/852 [00:07<00:02, 78.54it/s]
+
 74%|███████▍  | 633/852 [00:07<00:02, 77.76it/s]
+
 75%|███████▌  | 641/852 [00:08<00:02, 73.90it/s]
+
 76%|███████▋  | 650/852 [00:08<00:02, 75.98it/s]
+
 77%|███████▋  | 658/852 [00:08<00:02, 77.10it/s]
+
 78%|███████▊  | 666/852 [00:08<00:02, 76.85it/s]
+
 79%|███████▉  | 674/852 [00:08<00:02, 76.57it/s]
+
 80%|████████  | 682/852 [00:08<00:02, 76.91it/s]
+
 81%|████████  | 690/852 [00:08<00:02, 77.56it/s]
+
 82%|████████▏ | 699/852 [00:08<00:01, 78.82it/s]
+
 83%|████████▎ | 707/852 [00:08<00:01, 78.02it/s]
+
 84%|████████▍ | 716/852 [00:09<00:01, 78.90it/s]
+
 85%|████████▌ | 725/852 [00:09<00:01, 79.76it/s]
+
 86%|████████▌ | 734/852 [00:09<00:01, 81.48it/s]
+
 87%|████████▋ | 743/852 [00:09<00:01, 81.95it/s]
+
 88%|████████▊ | 752/852 [00:09<00:01, 82.60it/s]
+
 89%|████████▉ | 761/852 [00:09<00:01, 83.75it/s]
+
 90%|█████████ | 770/852 [00:09<00:00, 82.01it/s]
+
 91%|█████████▏| 779/852 [00:09<00:00, 81.56it/s]
+
 92%|█████████▏| 788/852 [00:09<00:00, 80.52it/s]
+
 94%|█████████▎| 797/852 [00:10<00:00, 80.46it/s]
+
 95%|█████████▍| 806/852 [00:10<00:00, 81.77it/s]
+
 96%|█████████▌| 815/852 [00:10<00:00, 80.65it/s]
+
 97%|█████████▋| 824/852 [00:10<00:00, 81.60it/s]
+
 98%|█████████▊| 833/852 [00:10<00:00, 82.33it/s]
+
 99%|█████████▉| 842/852 [00:10<00:00, 80.74it/s]
+
+  _warn_prf(average, modifier, msg_start, len(result))
+
                                                  
+
                                                 
 10%|█         | 541/5410 [02:30<25:28,  3.18it/s]
+
+
                                                 [INFO|trainer.py:3503] 2024-09-06 00:11:39,040 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-541
+[INFO|configuration_utils.py:472] 2024-09-06 00:11:39,042 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-541/config.json
+[INFO|modeling_utils.py:2799] 2024-09-06 00:11:40,402 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-541/model.safetensors
+[INFO|tokenization_utils_base.py:2684] 2024-09-06 00:11:40,403 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-541/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2693] 2024-09-06 00:11:40,403 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-541/special_tokens_map.json
+[INFO|tokenization_utils_base.py:2684] 2024-09-06 00:11:43,153 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2693] 2024-09-06 00:11:43,153 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+
 10%|█         | 542/5410 [02:35<7:54:05,  5.84s/it]
 10%|█         | 543/5410 [02:35<5:37:39,  4.16s/it]
 10%|█         | 544/5410 [02:35<4:02:49,  2.99s/it]
 10%|█         | 545/5410 [02:35<2:55:18,  2.16s/it]
 10%|█         | 546/5410 [02:36<2:07:58,  1.58s/it]
 10%|█         | 547/5410 [02:36<1:35:06,  1.17s/it]
 10%|█         | 548/5410 [02:36<1:12:46,  1.11it/s]
 10%|█         | 549/5410 [02:36<55:36,  1.46it/s]  
 10%|█         | 550/5410 [02:37<46:04,  1.76it/s]
 10%|█         | 551/5410 [02:37<37:52,  2.14it/s]
 10%|█         | 552/5410 [02:37<37:27,  2.16it/s]
 10%|█         | 553/5410 [02:37<30:36,  2.65it/s]
 10%|█         | 554/5410 [02:38<28:47,  2.81it/s]
 10%|█         | 555/5410 [02:38<25:27,  3.18it/s]
 10%|█         | 556/5410 [02:38<23:10,  3.49it/s]
 10%|█         | 557/5410 [02:38<23:03,  3.51it/s]
 10%|█         | 558/5410 [02:39<24:37,  3.28it/s]
 10%|█         | 559/5410 [02:39<22:29,  3.59it/s]
 10%|█         | 560/5410 [02:39<20:36,  3.92it/s]
 10%|█         | 561/5410 [02:39<19:01,  4.25it/s]
 10%|█         | 562/5410 [02:40<18:26,  4.38it/s]
 10%|█         | 563/5410 [02:40<17:21,  4.65it/s]
 10%|█         | 564/5410 [02:40<18:23,  4.39it/s]
 10%|█         | 565/5410 [02:41<30:05,  2.68it/s]
 10%|█         | 566/5410 [02:41<25:51,  3.12it/s]
 10%|█         | 567/5410 [02:41<24:02,  3.36it/s]
 10%|█         | 568/5410 [02:41<21:56,  3.68it/s]
 11%|█         | 569/5410 [02:42<20:04,  4.02it/s]
 11%|█         | 570/5410 [02:42<20:34,  3.92it/s]
 11%|█         | 571/5410 [02:42<19:28,  4.14it/s]
 11%|█         | 572/5410 [02:42<21:29,  3.75it/s]
 11%|█         | 573/5410 [02:43<21:40,  3.72it/s]
 11%|█         | 574/5410 [02:43<21:01,  3.83it/s]
 11%|█         | 575/5410 [02:43<20:09,  4.00it/s]
 11%|█         | 576/5410 [02:43<20:28,  3.94it/s]
 11%|█         | 577/5410 [02:44<19:13,  4.19it/s]
 11%|█         | 578/5410 [02:44<20:41,  3.89it/s]
 11%|█         | 579/5410 [02:44<19:33,  4.12it/s]
 11%|█         | 580/5410 [02:44<20:54,  3.85it/s]
 11%|█         | 581/5410 [02:45<21:37,  3.72it/s]
 11%|█         | 582/5410 [02:45<20:32,  3.92it/s]
 11%|█         | 583/5410 [02:45<20:54,  3.85it/s]
 11%|█         | 584/5410 [02:45<19:27,  4.13it/s]
 11%|█         | 585/5410 [02:46<20:25,  3.94it/s]
 11%|█         | 586/5410 [02:46<22:31,  3.57it/s]
 11%|█         | 587/5410 [02:46<19:42,  4.08it/s]
 11%|█         | 588/5410 [02:46<19:24,  4.14it/s]
 11%|█         | 589/5410 [02:47<20:26,  3.93it/s]
 11%|█         | 590/5410 [02:47<22:02,  3.64it/s]
 11%|█         | 591/5410 [02:47<20:31,  3.91it/s]
 11%|█         | 592/5410 [02:47<20:25,  3.93it/s]
 11%|█         | 593/5410 [02:48<20:56,  3.84it/s]
 11%|█         | 594/5410 [02:48<19:38,  4.09it/s]
 11%|█         | 595/5410 [02:48<25:54,  3.10it/s]
 11%|█         | 596/5410 [02:49<23:08,  3.47it/s]
 11%|█         | 597/5410 [02:49<23:27,  3.42it/s]
 11%|█         | 598/5410 [02:49<21:04,  3.80it/s]
 11%|█         | 599/5410 [02:49<18:54,  4.24it/s]
 11%|█         | 600/5410 [02:50<18:03,  4.44it/s]
 11%|█         | 601/5410 [02:50<18:32,  4.32it/s]
 11%|█         | 602/5410 [02:50<19:35,  4.09it/s]
 11%|█         | 603/5410 [02:50<18:53,  4.24it/s]
 11%|█         | 604/5410 [02:50<17:06,  4.68it/s]
 11%|█         | 605/5410 [02:51<18:28,  4.34it/s]
 11%|█         | 606/5410 [02:51<18:37,  4.30it/s]
 11%|█         | 607/5410 [02:51<18:19,  4.37it/s]
 11%|█         | 608/5410 [02:51<19:04,  4.20it/s]
 11%|█▏        | 609/5410 [02:52<19:27,  4.11it/s]
 11%|█▏        | 610/5410 [02:52<21:04,  3.79it/s]
 11%|█▏        | 611/5410 [02:52<19:22,  4.13it/s]
 11%|█▏        | 612/5410 [02:53<21:53,  3.65it/s]
 11%|█▏        | 613/5410 [02:53<20:27,  3.91it/s]
 11%|█▏        | 614/5410 [02:53<18:38,  4.29it/s]
 11%|█▏        | 615/5410 [02:53<17:46,  4.50it/s]
 11%|█▏        | 616/5410 [02:53<17:53,  4.47it/s]
 11%|█▏        | 617/5410 [02:54<18:19,  4.36it/s]
 11%|█▏        | 618/5410 [02:54<18:31,  4.31it/s]
 11%|█▏        | 619/5410 [02:54<16:54,  4.72it/s]
 11%|█▏        | 620/5410 [02:54<16:57,  4.71it/s]
 11%|█▏        | 621/5410 [02:54<16:49,  4.74it/s]
 11%|█▏        | 622/5410 [02:55<15:59,  4.99it/s]
 12%|█▏        | 623/5410 [02:55<16:15,  4.91it/s]
 12%|█▏        | 624/5410 [02:55<15:58,  4.99it/s]
 12%|█▏        | 625/5410 [02:55<15:26,  5.16it/s]
 12%|█▏        | 626/5410 [02:55<16:42,  4.77it/s]
 12%|█▏        | 627/5410 [02:56<19:24,  4.11it/s]
 12%|█▏        | 628/5410 [02:56<20:09,  3.95it/s]
 12%|█▏        | 629/5410 [02:56<20:03,  3.97it/s]
 12%|█▏        | 630/5410 [02:57<19:47,  4.02it/s]
 12%|█▏        | 631/5410 [02:57<18:45,  4.25it/s]
 12%|█▏        | 632/5410 [02:57<19:36,  4.06it/s]
 12%|█▏        | 633/5410 [02:57<19:53,  4.00it/s]
 12%|█▏        | 634/5410 [02:57<18:21,  4.34it/s]
 12%|█▏        | 635/5410 [02:58<17:52,  4.45it/s]
 12%|█▏        | 636/5410 [02:58<17:08,  4.64it/s]
 12%|█▏        | 637/5410 [02:58<16:18,  4.88it/s]
 12%|█▏        | 638/5410 [02:58<16:09,  4.92it/s]
 12%|█▏        | 639/5410 [02:58<15:58,  4.98it/s]
 12%|█▏        | 640/5410 [02:59<23:17,  3.41it/s]
 12%|█▏        | 641/5410 [02:59<23:11,  3.43it/s]
 12%|█▏        | 642/5410 [02:59<22:25,  3.54it/s]
 12%|█▏        | 643/5410 [03:00<22:22,  3.55it/s]
 12%|█▏        | 644/5410 [03:00<21:11,  3.75it/s]
 12%|█▏        | 645/5410 [03:00<21:50,  3.64it/s]
 12%|█▏        | 646/5410 [03:00<20:21,  3.90it/s]
 12%|█▏        | 647/5410 [03:01<20:14,  3.92it/s]
 12%|█▏        | 648/5410 [03:01<19:24,  4.09it/s]
 12%|█▏        | 649/5410 [03:01<17:56,  4.42it/s]
 12%|█▏        | 650/5410 [03:01<17:49,  4.45it/s]
 12%|█▏        | 651/5410 [03:02<17:40,  4.49it/s]
 12%|█▏        | 652/5410 [03:02<17:13,  4.60it/s]
 12%|█▏        | 653/5410 [03:02<19:14,  4.12it/s]
 12%|█▏        | 654/5410 [03:02<19:30,  4.06it/s]
 12%|█▏        | 655/5410 [03:03<18:31,  4.28it/s]
 12%|█▏        | 656/5410 [03:03<18:31,  4.28it/s]
 12%|█▏        | 657/5410 [03:03<16:53,  4.69it/s]
 12%|█▏        | 658/5410 [03:03<16:36,  4.77it/s]
 12%|█▏        | 659/5410 [03:03<15:48,  5.01it/s]
 12%|█▏        | 660/5410 [03:04<15:56,  4.97it/s]
 12%|█▏        | 661/5410 [03:04<19:09,  4.13it/s]
 12%|█▏        | 662/5410 [03:04<20:22,  3.89it/s]
 12%|█▏        | 663/5410 [03:04<20:21,  3.89it/s]
 12%|█▏        | 664/5410 [03:05<18:44,  4.22it/s]
 12%|█▏        | 665/5410 [03:05<18:17,  4.32it/s]
 12%|█▏        | 666/5410 [03:05<18:15,  4.33it/s]
 12%|█▏        | 667/5410 [03:05<17:32,  4.50it/s]
 12%|█▏        | 668/5410 [03:06<20:56,  3.78it/s]
 12%|█▏        | 669/5410 [03:06<20:08,  3.92it/s]
 12%|█▏        | 670/5410 [03:06<20:21,  3.88it/s]
 12%|█▏        | 671/5410 [03:06<18:36,  4.24it/s]
 12%|█▏        | 672/5410 [03:07<18:06,  4.36it/s]
 12%|█▏        | 673/5410 [03:07<18:48,  4.20it/s]
 12%|█▏        | 674/5410 [03:07<17:31,  4.50it/s]
 12%|█▏        | 675/5410 [03:07<18:23,  4.29it/s]
 12%|█▏        | 676/5410 [03:07<18:22,  4.29it/s]
 13%|█▎        | 677/5410 [03:08<18:20,  4.30it/s]
 13%|█▎        | 678/5410 [03:08<18:53,  4.17it/s]
 13%|█▎        | 679/5410 [03:08<18:52,  4.18it/s]
 13%|█▎        | 680/5410 [03:08<19:15,  4.09it/s]
 13%|█▎        | 681/5410 [03:09<18:48,  4.19it/s]
 13%|█▎        | 682/5410 [03:09<18:21,  4.29it/s]
 13%|█▎        | 683/5410 [03:09<17:14,  4.57it/s]
 13%|█▎        | 684/5410 [03:09<15:57,  4.93it/s]
 13%|█▎        | 685/5410 [03:09<16:44,  4.70it/s]
 13%|█▎        | 686/5410 [03:10<19:59,  3.94it/s]
 13%|█▎        | 687/5410 [03:10<22:38,  3.48it/s]
 13%|█▎        | 688/5410 [03:10<20:49,  3.78it/s]
 13%|█▎        | 689/5410 [03:11<23:48,  3.31it/s]
 13%|█▎        | 690/5410 [03:11<21:11,  3.71it/s]
 13%|█▎        | 691/5410 [03:11<21:53,  3.59it/s]
 13%|█▎        | 692/5410 [03:12<21:16,  3.70it/s]
 13%|█▎        | 693/5410 [03:12<23:36,  3.33it/s]
 13%|█▎        | 694/5410 [03:12<22:56,  3.43it/s]
 13%|█▎        | 695/5410 [03:12<21:04,  3.73it/s]
 13%|█▎        | 696/5410 [03:13<19:28,  4.03it/s]
 13%|█▎        | 697/5410 [03:13<19:35,  4.01it/s]
 13%|█▎        | 698/5410 [03:13<22:04,  3.56it/s]
 13%|█▎        | 699/5410 [03:13<21:48,  3.60it/s]
 13%|█▎        | 700/5410 [03:14<21:12,  3.70it/s]
 13%|█▎        | 701/5410 [03:14<19:46,  3.97it/s]
 13%|█▎        | 702/5410 [03:14<19:39,  3.99it/s]
 13%|█▎        | 703/5410 [03:14<18:43,  4.19it/s]
 13%|█▎        | 704/5410 [03:15<18:05,  4.33it/s]
 13%|█▎        | 705/5410 [03:15<17:44,  4.42it/s]
 13%|█▎        | 706/5410 [03:15<17:09,  4.57it/s]
 13%|█▎        | 707/5410 [03:15<17:09,  4.57it/s]
 13%|█▎        | 708/5410 [03:16<19:23,  4.04it/s]
 13%|█▎        | 709/5410 [03:16<20:11,  3.88it/s]
 13%|█▎        | 710/5410 [03:16<19:34,  4.00it/s]
 13%|█▎        | 711/5410 [03:16<19:31,  4.01it/s]
 13%|█▎        | 712/5410 [03:17<21:13,  3.69it/s]
 13%|█▎        | 713/5410 [03:17<19:21,  4.05it/s]

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 1.7176580067661056e+16,
+    "train_loss": 0.0812657987344287,
+    "train_runtime": 1549.44,
+    "train_samples": 34604,
+    "train_samples_per_second": 223.332,
+    "train_steps_per_second": 3.492
+}

trainer_state.json

@@ -0,0 +1,232 @@
+{
+  "best_metric": 0.45455732567249935,
+  "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-2705",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 5410,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9242144177449169,
+      "grad_norm": 1.4528056383132935,
+      "learning_rate": 4.537892791127542e-05,
+      "loss": 0.3191,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8443022505389485,
+      "eval_f1": 0.407486125870823,
+      "eval_loss": 0.47723615169525146,
+      "eval_precision": 0.27250473783954515,
+      "eval_recall": 0.8074403369209172,
+      "eval_runtime": 14.3908,
+      "eval_samples_per_second": 473.218,
+      "eval_steps_per_second": 59.204,
+      "step": 541
+    },
+    {
+      "epoch": 1.8484288354898335,
+      "grad_norm": 1.5587466955184937,
+      "learning_rate": 4.075785582255083e-05,
+      "loss": 0.1619,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8552871874442172,
+      "eval_f1": 0.43975123088883133,
+      "eval_loss": 0.4583655595779419,
+      "eval_precision": 0.30406737143881024,
+      "eval_recall": 0.7941038839494619,
+      "eval_runtime": 14.212,
+      "eval_samples_per_second": 479.173,
+      "eval_steps_per_second": 59.949,
+      "step": 1082
+    },
+    {
+      "epoch": 2.7726432532347505,
+      "grad_norm": 0.9616082310676575,
+      "learning_rate": 3.613678373382625e-05,
+      "loss": 0.11,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8435470361267112,
+      "eval_f1": 0.4338006724608259,
+      "eval_loss": 0.6447410583496094,
+      "eval_precision": 0.29758899817216466,
+      "eval_recall": 0.7999532054281703,
+      "eval_runtime": 14.3233,
+      "eval_samples_per_second": 475.451,
+      "eval_steps_per_second": 59.484,
+      "step": 1623
+    },
+    {
+      "epoch": 3.6968576709796674,
+      "grad_norm": 1.4018645286560059,
+      "learning_rate": 3.1515711645101665e-05,
+      "loss": 0.0764,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8398602166778805,
+      "eval_f1": 0.42338430558177587,
+      "eval_loss": 0.7413247227668762,
+      "eval_precision": 0.2895756219333735,
+      "eval_recall": 0.7870846981750117,
+      "eval_runtime": 14.5396,
+      "eval_samples_per_second": 468.375,
+      "eval_steps_per_second": 58.598,
+      "step": 2164
+    },
+    {
+      "epoch": 4.621072088724584,
+      "grad_norm": 1.0904265642166138,
+      "learning_rate": 2.6894639556377083e-05,
+      "loss": 0.0567,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8564886649182308,
+      "eval_f1": 0.45455732567249935,
+      "eval_loss": 0.7005925178527832,
+      "eval_precision": 0.3152508603513856,
+      "eval_recall": 0.8144595226953674,
+      "eval_runtime": 14.2723,
+      "eval_samples_per_second": 477.148,
+      "eval_steps_per_second": 59.696,
+      "step": 2705
+    },
+    {
+      "epoch": 5.545286506469501,
+      "grad_norm": 1.240962028503418,
+      "learning_rate": 2.2273567467652497e-05,
+      "loss": 0.0428,
+      "step": 3000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8504057561069384,
+      "eval_f1": 0.44700636942675154,
+      "eval_loss": 0.8111857175827026,
+      "eval_precision": 0.30710659898477155,
+      "eval_recall": 0.8210107627515209,
+      "eval_runtime": 14.3991,
+      "eval_samples_per_second": 472.946,
+      "eval_steps_per_second": 59.17,
+      "step": 3246
+    },
+    {
+      "epoch": 6.469500924214418,
+      "grad_norm": 0.44737720489501953,
+      "learning_rate": 1.7652495378927914e-05,
+      "loss": 0.0332,
+      "step": 3500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8532961676301372,
+      "eval_f1": 0.4493518337567586,
+      "eval_loss": 0.904643714427948,
+      "eval_precision": 0.3113658932924077,
+      "eval_recall": 0.8069723912026205,
+      "eval_runtime": 14.3036,
+      "eval_samples_per_second": 476.105,
+      "eval_steps_per_second": 59.566,
+      "step": 3787
+    },
+    {
+      "epoch": 7.393715341959335,
+      "grad_norm": 0.7116318941116333,
+      "learning_rate": 1.3031423290203328e-05,
+      "loss": 0.0257,
+      "step": 4000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8481538440413583,
+      "eval_f1": 0.44435897435897437,
+      "eval_loss": 0.9722912907600403,
+      "eval_precision": 0.30602154335158044,
+      "eval_recall": 0.8109499298081423,
+      "eval_runtime": 14.4222,
+      "eval_samples_per_second": 472.19,
+      "eval_steps_per_second": 59.076,
+      "step": 4328
+    },
+    {
+      "epoch": 8.317929759704251,
+      "grad_norm": 0.9520462155342102,
+      "learning_rate": 8.410351201478742e-06,
+      "loss": 0.022,
+      "step": 4500
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.850186057368833,
+      "eval_f1": 0.44668737060041414,
+      "eval_loss": 1.002764105796814,
+      "eval_precision": 0.30871042747272404,
+      "eval_recall": 0.8076743097800655,
+      "eval_runtime": 14.2485,
+      "eval_samples_per_second": 477.944,
+      "eval_steps_per_second": 59.796,
+      "step": 4869
+    },
+    {
+      "epoch": 9.242144177449168,
+      "grad_norm": 0.6707109212875366,
+      "learning_rate": 3.789279112754159e-06,
+      "loss": 0.0181,
+      "step": 5000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8533304955579661,
+      "eval_f1": 0.45038613797131544,
+      "eval_loss": 1.0022608041763306,
+      "eval_precision": 0.31162999550965426,
+      "eval_recall": 0.8118858212447356,
+      "eval_runtime": 14.4559,
+      "eval_samples_per_second": 471.089,
+      "eval_steps_per_second": 58.938,
+      "step": 5410
+    },
+    {
+      "epoch": 10.0,
+      "step": 5410,
+      "total_flos": 1.7176580067661056e+16,
+      "train_loss": 0.0812657987344287,
+      "train_runtime": 1549.44,
+      "train_samples_per_second": 223.332,
+      "train_steps_per_second": 3.492
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5410,
+  "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": 1.7176580067661056e+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