Training in progress, epoch 0

README.md

@@ -0,0 +1,102 @@
+---
+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-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-ner
+      type: Rodrigo1771/combined-train-distemist-dev-ner
+      config: CombinedTrainDisTEMISTDevNER
+      split: validation
+      args: CombinedTrainDisTEMISTDevNER
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.32197630636422075
+    - name: Recall
+      type: recall
+      value: 0.8203088441740758
+    - name: F1
+      type: f1
+      value: 0.4624414693662204
+    - name: Accuracy
+      type: accuracy
+      value: 0.8601754843670617
+---
+
+<!-- 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-ner dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6266
+- Precision: 0.3220
+- Recall: 0.8203
+- F1: 0.4624
+- Accuracy: 0.8602
+
+## 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        | 0.9988 | 425  | 0.3834          | 0.2920    | 0.7819 | 0.4252 | 0.8517   |
+| 0.3349        | 2.0    | 851  | 0.5730          | 0.2681    | 0.8070 | 0.4025 | 0.8221   |
+| 0.1788        | 2.9988 | 1276 | 0.5796          | 0.2848    | 0.8009 | 0.4202 | 0.8338   |
+| 0.1227        | 4.0    | 1702 | 0.6591          | 0.2996    | 0.8109 | 0.4376 | 0.8388   |
+| 0.0856        | 4.9988 | 2127 | 0.6266          | 0.3220    | 0.8203 | 0.4624 | 0.8602   |
+| 0.0597        | 6.0    | 2553 | 0.7859          | 0.3075    | 0.8112 | 0.4460 | 0.8476   |
+| 0.0597        | 6.9988 | 2978 | 0.8297          | 0.3137    | 0.8166 | 0.4532 | 0.8508   |
+| 0.0458        | 8.0    | 3404 | 0.8468          | 0.3135    | 0.8205 | 0.4536 | 0.8532   |
+| 0.0343        | 8.9988 | 3829 | 0.9241          | 0.3085    | 0.8182 | 0.4481 | 0.8494   |
+| 0.0292        | 9.9882 | 4250 | 0.9384          | 0.3100    | 0.8163 | 0.4494 | 0.8499   |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,26 @@
+{
+    "epoch": 9.988249118683902,
+    "eval_accuracy": 0.8601754843670617,
+    "eval_f1": 0.4624414693662204,
+    "eval_loss": 0.6266195774078369,
+    "eval_precision": 0.32197630636422075,
+    "eval_recall": 0.8203088441740758,
+    "eval_runtime": 14.995,
+    "eval_samples": 6810,
+    "eval_samples_per_second": 454.15,
+    "eval_steps_per_second": 56.819,
+    "predict_accuracy": 0.9510588123763138,
+    "predict_f1": 0.6555634301913535,
+    "predict_loss": 0.18893657624721527,
+    "predict_precision": 0.5454009433962265,
+    "predict_recall": 0.8214920071047958,
+    "predict_runtime": 30.3218,
+    "predict_samples_per_second": 481.964,
+    "predict_steps_per_second": 60.254,
+    "total_flos": 1.2649810588547778e+16,
+    "train_loss": 0.10639642311544979,
+    "train_runtime": 1205.6346,
+    "train_samples": 27229,
+    "train_samples_per_second": 225.848,
+    "train_steps_per_second": 3.525
+}

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": "4.42.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 9.988249118683902,
+    "eval_accuracy": 0.8601754843670617,
+    "eval_f1": 0.4624414693662204,
+    "eval_loss": 0.6266195774078369,
+    "eval_precision": 0.32197630636422075,
+    "eval_recall": 0.8203088441740758,
+    "eval_runtime": 14.995,
+    "eval_samples": 6810,
+    "eval_samples_per_second": 454.15,
+    "eval_steps_per_second": 56.819
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:248b0b7048aa4d7483fba444efd0a93176b0ef8eb07838fef1140c669d738b7e
+size 496262556

predict_results.json

@@ -0,0 +1,10 @@
+{
+    "predict_accuracy": 0.9510588123763138,
+    "predict_f1": 0.6555634301913535,
+    "predict_loss": 0.18893657624721527,
+    "predict_precision": 0.5454009433962265,
+    "predict_recall": 0.8214920071047958,
+    "predict_runtime": 30.3218,
+    "predict_samples_per_second": 481.964,
+    "predict_steps_per_second": 60.254
+}

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.1725045346.6b97e535edda.2908.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e576d6fc5f437e9cdba3770a03c7980ab62c145def88b46a7b1d4e68f13bfde9
+size 6546

tb/events.out.tfevents.1725046129.6b97e535edda.6370.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9e94268d839c5a3c21781840b052643e729f1bd38c4ed1942a53d09ddd89bfc
+size 12153

tb/events.out.tfevents.1725047358.6b97e535edda.6370.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6babdcbcafd1e6dd843214457a56f608115a0ebceecc401a4e103c0ed26fb36d
+size 560

tb/events.out.tfevents.1725047806.6b97e535edda.13440.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98176e24292706b54fcd3566af82c1b540c139fe67c287bbedee399f56ea439a
+size 5863

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 +1,431 @@
+2024-08-30 19:56:24.380746: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
+2024-08-30 19:56:24.398707: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:485] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
+2024-08-30 19:56:24.420048: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:8454] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
+2024-08-30 19:56:24.426474: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1452] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
+2024-08-30 19:56:24.441801: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
+To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-08-30 19:56:25.730410: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
+/usr/local/lib/python3.10/dist-packages/transformers/training_args.py:1494: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
+  warnings.warn(
+08/30/2024 19:56:27 - WARNING - __main__ -   Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False
+08/30/2024 19:56:27 - INFO - __main__ -   Training/evaluation parameters TrainingArguments(
+_n_gpu=1,
+accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None, 'use_configured_state': False},
+adafactor=False,
+adam_beta1=0.9,
+adam_beta2=0.999,
+adam_epsilon=1e-08,
+auto_find_batch_size=False,
+batch_eval_metrics=False,
+bf16=False,
+bf16_full_eval=False,
+data_seed=None,
+dataloader_drop_last=False,
+dataloader_num_workers=0,
+dataloader_persistent_workers=False,
+dataloader_pin_memory=True,
+dataloader_prefetch_factor=None,
+ddp_backend=None,
+ddp_broadcast_buffers=None,
+ddp_bucket_cap_mb=None,
+ddp_find_unused_parameters=None,
+ddp_timeout=1800,
+debug=[],
+deepspeed=None,
+disable_tqdm=False,
+dispatch_batches=None,
+do_eval=True,
+do_predict=True,
+do_train=True,
+eval_accumulation_steps=None,
+eval_delay=0,
+eval_do_concat_batches=True,
+eval_on_start=False,
+eval_steps=None,
+eval_strategy=epoch,
+evaluation_strategy=epoch,
+fp16=False,
+fp16_backend=auto,
+fp16_full_eval=False,
+fp16_opt_level=O1,
+fsdp=[],
+fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False},
+fsdp_min_num_params=0,
+fsdp_transformer_layer_cls_to_wrap=None,
+full_determinism=False,
+gradient_accumulation_steps=2,
+gradient_checkpointing=False,
+gradient_checkpointing_kwargs=None,
+greater_is_better=True,
+group_by_length=False,
+half_precision_backend=auto,
+hub_always_push=False,
+hub_model_id=None,
+hub_private_repo=False,
+hub_strategy=every_save,
+hub_token=<HUB_TOKEN>,
+ignore_data_skip=False,
+include_inputs_for_metrics=False,
+include_num_input_tokens_seen=False,
+include_tokens_per_second=False,
+jit_mode_eval=False,
+label_names=None,
+label_smoothing_factor=0.0,
+learning_rate=5e-05,
+length_column_name=length,
+load_best_model_at_end=True,
+local_rank=0,
+log_level=passive,
+log_level_replica=warning,
+log_on_each_node=True,
+logging_dir=/content/dissertation/scripts/ner/output/tb,
+logging_first_step=False,
+logging_nan_inf_filter=True,
+logging_steps=500,
+logging_strategy=steps,
+lr_scheduler_kwargs={},
+lr_scheduler_type=linear,
+max_grad_norm=1.0,
+max_steps=-1,
+metric_for_best_model=f1,
+mp_parameters=,
+neftune_noise_alpha=None,
+no_cuda=False,
+num_train_epochs=10.0,
+optim=adamw_torch,
+optim_args=None,
+optim_target_modules=None,
+output_dir=/content/dissertation/scripts/ner/output,
+overwrite_output_dir=True,
+past_index=-1,
+per_device_eval_batch_size=8,
+per_device_train_batch_size=32,
+prediction_loss_only=False,
+push_to_hub=True,
+push_to_hub_model_id=None,
+push_to_hub_organization=None,
+push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
+ray_scope=last,
+remove_unused_columns=True,
+report_to=['tensorboard'],
+restore_callback_states_from_checkpoint=False,
+resume_from_checkpoint=None,
+run_name=/content/dissertation/scripts/ner/output,
+save_on_each_node=False,
+save_only_model=False,
+save_safetensors=True,
+save_steps=500,
+save_strategy=epoch,
+save_total_limit=None,
+seed=42,
+skip_memory_metrics=True,
+split_batches=None,
+tf32=None,
+torch_compile=False,
+torch_compile_backend=None,
+torch_compile_mode=None,
+torchdynamo=None,
+tpu_metrics_debug=False,
+tpu_num_cores=None,
+use_cpu=False,
+use_ipex=False,
+use_legacy_prediction_loop=False,
+use_mps_device=False,
+warmup_ratio=0.0,
+warmup_steps=0,
+weight_decay=0.0,
+)
+
+
+
+
+
+
+
+[INFO|configuration_utils.py:733] 2024-08-30 19:56:39,725 >> 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] 2024-08-30 19:56:39,729 >> 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": "4.42.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}
+
+[INFO|configuration_utils.py:733] 2024-08-30 19:56:39,829 >> 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] 2024-08-30 19:56:39,830 >> 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": "4.42.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}
+
+[INFO|tokenization_utils_base.py:2161] 2024-08-30 19:56:39,840 >> 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:2161] 2024-08-30 19:56:39,840 >> 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:2161] 2024-08-30 19:56:39,840 >> loading file tokenizer.json from cache at None
+[INFO|tokenization_utils_base.py:2161] 2024-08-30 19:56:39,840 >> loading file added_tokens.json from cache at None
+[INFO|tokenization_utils_base.py:2161] 2024-08-30 19:56:39,840 >> 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:2161] 2024-08-30 19:56:39,840 >> 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] 2024-08-30 19:56:39,841 >> 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] 2024-08-30 19:56:39,842 >> 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": "4.42.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}
+
+[INFO|configuration_utils.py:733] 2024-08-30 19:56:39,926 >> 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] 2024-08-30 19:56:39,927 >> 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": "4.42.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}
+
+[INFO|modeling_utils.py:3556] 2024-08-30 19:56:40,114 >> 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:4354] 2024-08-30 19:56:40,253 >> 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:4366] 2024-08-30 19:56:40,253 >> 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:805] 2024-08-30 19:56:46,202 >> The following columns in the training set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: id, ner_tags, tokens. If id, ner_tags, tokens are not expected by `RobertaForTokenClassification.forward`,  you can safely ignore this message.
+[INFO|trainer.py:2128] 2024-08-30 19:56:46,780 >> ***** Running training *****
+[INFO|trainer.py:2129] 2024-08-30 19:56:46,781 >>   Num examples = 27,229
+[INFO|trainer.py:2130] 2024-08-30 19:56:46,781 >>   Num Epochs = 10
+[INFO|trainer.py:2131] 2024-08-30 19:56:46,781 >>   Instantaneous batch size per device = 32
+[INFO|trainer.py:2134] 2024-08-30 19:56:46,781 >>   Total train batch size (w. parallel, distributed & accumulation) = 64
+[INFO|trainer.py:2135] 2024-08-30 19:56:46,781 >>   Gradient Accumulation steps = 2
+[INFO|trainer.py:2136] 2024-08-30 19:56:46,781 >>   Total optimization steps = 4,250
+[INFO|trainer.py:2137] 2024-08-30 19:56:46,781 >>   Number of trainable parameters = 124,059,657
+
  0%|          | 0/4250 [00:00<?, ?it/s]
  0%|          | 1/4250 [00:01<1:22:54,  1.17s/it]
  0%|          | 2/4250 [00:01<42:01,  1.68it/s]  
  0%|          | 3/4250 [00:01<29:22,  2.41it/s]
  0%|          | 4/4250 [00:01<23:09,  3.06it/s]
  0%|          | 5/4250 [00:02<21:02,  3.36it/s]
  0%|          | 6/4250 [00:02<18:48,  3.76it/s]
  0%|          | 7/4250 [00:02<18:03,  3.92it/s]
  0%|          | 8/4250 [00:02<17:04,  4.14it/s]
  0%|          | 9/4250 [00:02<17:57,  3.94it/s]
  0%|          | 10/4250 [00:03<17:19,  4.08it/s]
  0%|          | 11/4250 [00:03<16:45,  4.22it/s]
  0%|          | 12/4250 [00:03<15:21,  4.60it/s]
  0%|          | 13/4250 [00:03<17:21,  4.07it/s]
  0%|          | 14/4250 [00:04<16:55,  4.17it/s]
  0%|          | 15/4250 [00:04<16:34,  4.26it/s]
  0%|          | 16/4250 [00:04<15:42,  4.49it/s]
  0%|          | 17/4250 [00:04<14:41,  4.80it/s]
  0%|          | 18/4250 [00:04<14:23,  4.90it/s]
  0%|          | 19/4250 [00:05<15:11,  4.64it/s]
  0%|          | 20/4250 [00:05<14:17,  4.93it/s]
  0%|          | 21/4250 [00:05<16:33,  4.26it/s]
  1%|          | 22/4250 [00:05<15:53,  4.44it/s]
  1%|          | 23/4250 [00:06<15:25,  4.57it/s]
  1%|          | 24/4250 [00:06<15:15,  4.62it/s]
  1%|          | 25/4250 [00:06<16:44,  4.21it/s]
  1%|          | 26/4250 [00:06<15:11,  4.64it/s]
  1%|          | 27/4250 [00:06<15:12,  4.63it/s]
  1%|          | 28/4250 [00:07<13:58,  5.03it/s]
  1%|          | 29/4250 [00:07<13:39,  5.15it/s]
  1%|          | 30/4250 [00:07<16:45,  4.20it/s]
  1%|          | 31/4250 [00:07<15:42,  4.48it/s]
  1%|          | 32/4250 [00:08<16:49,  4.18it/s]
  1%|          | 33/4250 [00:08<16:15,  4.32it/s]
  1%|          | 34/4250 [00:08<16:30,  4.26it/s]
  1%|          | 35/4250 [00:08<15:50,  4.44it/s]
  1%|          | 36/4250 [00:08<16:12,  4.34it/s]
  1%|          | 37/4250 [00:09<15:15,  4.60it/s]
  1%|          | 38/4250 [00:09<15:04,  4.65it/s]
  1%|          | 39/4250 [00:09<16:26,  4.27it/s]
  1%|          | 40/4250 [00:09<15:17,  4.59it/s]
  1%|          | 41/4250 [00:09<14:58,  4.68it/s]
  1%|          | 42/4250 [00:10<15:05,  4.65it/s]
  1%|          | 43/4250 [00:10<17:31,  4.00it/s]
  1%|          | 44/4250 [00:11<27:49,  2.52it/s]
  1%|          | 45/4250 [00:11<23:40,  2.96it/s]
  1%|          | 46/4250 [00:11<22:36,  3.10it/s]
  1%|          | 47/4250 [00:11<19:55,  3.51it/s]
  1%|          | 48/4250 [00:12<18:43,  3.74it/s]
  1%|          | 49/4250 [00:12<16:10,  4.33it/s]
  1%|          | 50/4250 [00:12<16:42,  4.19it/s]
  1%|          | 51/4250 [00:12<16:56,  4.13it/s]
  1%|          | 52/4250 [00:13<16:31,  4.23it/s]
  1%|          | 53/4250 [00:13<17:15,  4.05it/s]
  1%|▏         | 54/4250 [00:13<20:55,  3.34it/s]
  1%|▏         | 55/4250 [00:13<19:02,  3.67it/s]
  1%|▏         | 56/4250 [00:14<18:24,  3.80it/s]
  1%|▏         | 57/4250 [00:14<17:03,  4.10it/s]
  1%|▏         | 58/4250 [00:14<15:38,  4.47it/s]
  1%|▏         | 59/4250 [00:14<15:03,  4.64it/s]
  1%|▏         | 60/4250 [00:14<14:48,  4.72it/s]
  1%|▏         | 61/4250 [00:15<15:50,  4.41it/s]
  1%|▏         | 62/4250 [00:15<15:56,  4.38it/s]
  1%|▏         | 63/4250 [00:15<15:00,  4.65it/s]
  2%|▏         | 64/4250 [00:15<14:46,  4.72it/s]
  2%|▏         | 65/4250 [00:16<15:31,  4.49it/s]
  2%|▏         | 66/4250 [00:16<16:36,  4.20it/s]
  2%|▏         | 67/4250 [00:16<16:31,  4.22it/s]
  2%|▏         | 68/4250 [00:17<20:45,  3.36it/s]
  2%|▏         | 69/4250 [00:17<18:33,  3.75it/s]
  2%|▏         | 70/4250 [00:17<19:56,  3.49it/s]
  2%|▏         | 71/4250 [00:17<18:58,  3.67it/s]
  2%|▏         | 72/4250 [00:18<17:43,  3.93it/s]
  2%|▏         | 73/4250 [00:18<17:15,  4.03it/s]
  2%|▏         | 74/4250 [00:18<17:31,  3.97it/s]
  2%|▏         | 75/4250 [00:18<15:34,  4.47it/s]
  2%|▏         | 76/4250 [00:18<16:08,  4.31it/s]
  2%|▏         | 77/4250 [00:19<15:14,  4.56it/s]
  2%|▏         | 78/4250 [00:19<16:02,  4.33it/s]
  2%|▏         | 79/4250 [00:19<16:08,  4.31it/s]
  2%|▏         | 80/4250 [00:19<16:04,  4.32it/s]
  2%|▏         | 81/4250 [00:20<16:05,  4.32it/s]
  2%|▏         | 82/4250 [00:20<15:07,  4.59it/s]
  2%|▏         | 83/4250 [00:20<17:05,  4.06it/s]
  2%|▏         | 84/4250 [00:20<15:34,  4.46it/s]
  2%|▏         | 85/4250 [00:20<15:15,  4.55it/s]
  2%|▏         | 86/4250 [00:21<15:04,  4.60it/s]
  2%|▏         | 87/4250 [00:21<15:05,  4.60it/s]
  2%|▏         | 88/4250 [00:21<13:41,  5.07it/s]
  2%|▏         | 89/4250 [00:21<13:52,  5.00it/s]
  2%|▏         | 90/4250 [00:22<16:13,  4.27it/s]
  2%|▏         | 91/4250 [00:22<14:34,  4.76it/s]
  2%|▏         | 92/4250 [00:22<14:02,  4.94it/s]
  2%|▏         | 93/4250 [00:22<13:17,  5.21it/s]
  2%|▏         | 94/4250 [00:22<13:54,  4.98it/s]
  2%|▏         | 95/4250 [00:23<15:06,  4.59it/s]
  2%|▏         | 96/4250 [00:23<16:55,  4.09it/s]
  2%|▏         | 97/4250 [00:23<15:53,  4.36it/s]
  2%|▏         | 98/4250 [00:23<14:45,  4.69it/s]
  2%|▏         | 99/4250 [00:23<14:08,  4.89it/s]
  2%|▏         | 100/4250 [00:24<14:28,  4.78it/s]
  2%|▏         | 101/4250 [00:24<18:01,  3.84it/s]
  2%|▏         | 102/4250 [00:24<20:25,  3.38it/s]
  2%|▏         | 103/4250 [00:25<18:29,  3.74it/s]
  2%|▏         | 104/4250 [00:25<16:58,  4.07it/s]
  2%|▏         | 105/4250 [00:25<16:37,  4.15it/s]
  2%|▏         | 106/4250 [00:25<16:08,  4.28it/s]
  3%|▎         | 107/4250 [00:25<15:55,  4.34it/s]
  3%|▎         | 108/4250 [00:26<19:06,  3.61it/s]
  3%|▎         | 109/4250 [00:26<18:34,  3.72it/s]
  3%|▎         | 110/4250 [00:26<17:11,  4.01it/s]
  3%|▎         | 111/4250 [00:26<15:34,  4.43it/s]
  3%|▎         | 112/4250 [00:27<16:09,  4.27it/s]
  3%|▎         | 113/4250 [00:27<15:47,  4.37it/s]
  3%|▎         | 114/4250 [00:27<14:36,  4.72it/s]
  3%|▎         | 115/4250 [00:27<14:04,  4.89it/s]
  3%|▎         | 116/4250 [00:28<15:35,  4.42it/s]
  3%|▎         | 117/4250 [00:28<15:07,  4.55it/s]
  3%|▎         | 118/4250 [00:28<14:42,  4.68it/s]
  3%|▎         | 119/4250 [00:28<15:06,  4.56it/s]
  3%|▎         | 120/4250 [00:28<14:14,  4.83it/s]
  3%|▎         | 121/4250 [00:29<14:18,  4.81it/s]
  3%|▎         | 122/4250 [00:29<20:13,  3.40it/s]
  3%|▎         | 123/4250 [00:29<18:31,  3.71it/s]
  3%|▎         | 124/4250 [00:30<16:53,  4.07it/s]
  3%|▎         | 125/4250 [00:30<17:05,  4.02it/s]
  3%|▎         | 126/4250 [00:30<15:30,  4.43it/s]
  3%|▎         | 127/4250 [00:30<14:48,  4.64it/s]
  3%|▎         | 128/4250 [00:30<14:12,  4.83it/s]
  3%|▎         | 129/4250 [00:31<17:31,  3.92it/s]
  3%|▎         | 130/4250 [00:31<16:58,  4.04it/s]
  3%|▎         | 131/4250 [00:31<15:29,  4.43it/s]
  3%|▎         | 132/4250 [00:31<14:37,  4.69it/s]
  3%|▎         | 133/4250 [00:32<15:37,  4.39it/s]
  3%|▎         | 134/4250 [00:32<15:17,  4.48it/s]
  3%|▎         | 135/4250 [00:32<15:06,  4.54it/s]
  3%|▎         | 136/4250 [00:32<15:10,  4.52it/s]
  3%|▎         | 137/4250 [00:32<14:56,  4.59it/s]
  3%|▎         | 138/4250 [00:33<14:26,  4.74it/s]
  3%|▎         | 139/4250 [00:33<14:55,  4.59it/s]
  3%|▎         | 140/4250 [00:33<15:52,  4.31it/s]
  3%|▎         | 141/4250 [00:33<15:57,  4.29it/s]
  3%|▎         | 142/4250 [00:33<14:58,  4.57it/s]
  3%|▎         | 143/4250 [00:34<14:36,  4.68it/s]
  3%|▎         | 144/4250 [00:34<14:25,  4.74it/s]
  3%|▎         | 145/4250 [00:34<16:56,  4.04it/s]
  3%|▎         | 146/4250 [00:35<22:12,  3.08it/s]
  3%|▎         | 147/4250 [00:35<19:47,  3.45it/s]
  3%|▎         | 148/4250 [00:35<19:39,  3.48it/s]
  4%|▎         | 149/4250 [00:35<18:55,  3.61it/s]
  4%|▎         | 150/4250 [00:36<17:36,  3.88it/s]
  4%|▎         | 151/4250 [00:36<16:08,  4.23it/s]
  4%|▎         | 152/4250 [00:36<17:00,  4.02it/s]
  4%|▎         | 153/4250 [00:36<16:21,  4.18it/s]
  4%|▎         | 154/4250 [00:37<15:19,  4.46it/s]
  4%|▎         | 155/4250 [00:37<14:26,  4.72it/s]
  4%|▎         | 156/4250 [00:37<14:44,  4.63it/s]
  4%|▎         | 157/4250 [00:37<14:24,  4.73it/s]
  4%|▎         | 158/4250 [00:38<17:32,  3.89it/s]
  4%|▎         | 159/4250 [00:38<18:32,  3.68it/s]
  4%|▍         | 160/4250 [00:38<16:57,  4.02it/s]
  4%|▍         | 161/4250 [00:38<16:00,  4.26it/s]
  4%|▍         | 162/4250 [00:38<14:56,  4.56it/s]
  4%|▍         | 163/4250 [00:39<14:48,  4.60it/s]
  4%|▍         | 164/4250 [00:39<18:40,  3.65it/s]
  4%|▍         | 165/4250 [00:39<18:13,  3.73it/s]
  4%|▍         | 166/4250 [00:40<18:24,  3.70it/s]
  4%|▍         | 167/4250 [00:40<17:28,  3.89it/s]
  4%|▍         | 168/4250 [00:40<15:55,  4.27it/s]
  4%|▍         | 169/4250 [00:40<15:32,  4.38it/s]
  4%|▍         | 170/4250 [00:40<15:28,  4.40it/s]
  4%|▍         | 171/4250 [00:41<15:59,  4.25it/s]
  4%|▍         | 172/4250 [00:41<15:11,  4.47it/s]
  4%|▍         | 173/4250 [00:41<18:21,  3.70it/s]
  4%|▍         | 174/4250 [00:41<16:38,  4.08it/s]
  4%|▍         | 175/4250 [00:42<19:24,  3.50it/s]
  4%|▍         | 176/4250 [00:42<19:20,  3.51it/s]
  4%|▍         | 177/4250 [00:42<17:03,  3.98it/s]
  4%|▍         | 178/4250 [00:42<16:06,  4.21it/s]
  4%|▍         | 179/4250 [00:43<15:38,  4.34it/s]
  4%|▍         | 180/4250 [00:43<14:25,  4.70it/s]
  4%|▍         | 181/4250 [00:43<14:35,  4.65it/s]
  4%|▍         | 182/4250 [00:43<17:09,  3.95it/s]
  4%|▍         | 183/4250 [00:44<16:33,  4.09it/s]
  4%|▍         | 184/4250 [00:44<16:26,  4.12it/s]
  4%|▍         | 185/4250 [00:44<15:05,  4.49it/s]
  4%|▍         | 186/4250 [00:44<14:37,  4.63it/s]
  4%|▍         | 187/4250 [00:44<13:45,  4.92it/s]
  4%|▍         | 188/4250 [00:45<14:40,  4.61it/s]
  4%|▍         | 189/4250 [00:45<14:11,  4.77it/s]
  4%|▍         | 190/4250 [00:45<13:43,  4.93it/s]
  4%|▍         | 191/4250 [00:45<14:21,  4.71it/s]
  5%|▍         | 192/4250 [00:46<14:09,  4.78it/s]
  5%|▍         | 193/4250 [00:46<13:53,  4.87it/s]
  5%|▍         | 194/4250 [00:46<16:40,  4.06it/s]
  5%|▍         | 195/4250 [00:46<15:35,  4.33it/s]
  5%|▍         | 196/4250 [00:46<14:25,  4.69it/s]
  5%|▍         | 197/4250 [00:47<14:55,  4.53it/s]
  5%|▍         | 198/4250 [00:47<15:18,  4.41it/s]
  5%|▍         | 199/4250 [00:47<15:25,  4.38it/s]
  5%|▍         | 200/4250 [00:47<15:34,  4.33it/s]
  5%|▍         | 201/4250 [00:48<15:13,  4.43it/s]
  5%|▍         | 202/4250 [00:48<15:31,  4.35it/s]
  5%|▍         | 203/4250 [00:48<14:25,  4.67it/s]
  5%|▍         | 204/4250 [00:48<13:45,  4.90it/s]
  5%|▍         | 205/4250 [00:48<14:42,  4.58it/s]
  5%|▍         | 206/4250 [00:49<14:27,  4.66it/s]
  5%|▍         | 207/4250 [00:49<16:42,  4.03it/s]
  5%|▍         | 208/4250 [00:49<15:16,  4.41it/s]
  5%|▍         | 209/4250 [00:49<15:09,  4.44it/s]
  5%|▍         | 210/4250 [00:50<13:59,  4.81it/s]
  5%|▍         | 211/4250 [00:50<15:05,  4.46it/s]
  5%|▍         | 212/4250 [00:50<14:22,  4.68it/s]
  5%|▌         | 213/4250 [00:50<17:28,  3.85it/s]
  5%|▌         | 214/4250 [00:50<15:20,  4.38it/s]
  5%|▌         | 215/4250 [00:51<15:14,  4.41it/s]
  5%|▌         | 216/4250 [00:51<19:02,  3.53it/s]
  5%|▌         | 217/4250 [00:51<17:01,  3.95it/s]
  5%|▌         | 218/4250 [00:52<15:54,  4.22it/s]
  5%|▌         | 219/4250 [00:52<16:32,  4.06it/s]
  5%|▌         | 220/4250 [00:52<16:39,  4.03it/s]
  5%|▌         | 221/4250 [00:52<18:42,  3.59it/s]
  5%|▌         | 222/4250 [00:53<20:01,  3.35it/s]
  5%|▌         | 223/4250 [00:53<18:25,  3.64it/s]
  5%|▌         | 224/4250 [00:53<16:30,  4.06it/s]
  5%|▌         | 225/4250 [00:53<15:06,  4.44it/s]
  5%|▌         | 226/4250 [00:53<14:23,  4.66it/s]
  5%|▌         | 227/4250 [00:54<14:00,  4.79it/s]
  5%|▌         | 228/4250 [00:54<13:46,  4.87it/s]
  5%|▌         | 229/4250 [00:54<12:57,  5.17it/s]
  5%|▌         | 230/4250 [00:54<14:21,  4.66it/s]
  5%|▌         | 231/4250 [00:54<13:45,  4.87it/s]
  5%|▌         | 232/4250 [00:55<13:36,  4.92it/s]
  5%|▌         | 233/4250 [00:55<13:25,  4.99it/s]
  6%|▌         | 234/4250 [00:55<15:43,  4.26it/s]
  6%|▌         | 235/4250 [00:56<20:40,  3.24it/s]
  6%|▌         | 236/4250 [00:56<21:54,  3.05it/s]
  6%|▌         | 237/4250 [00:56<19:46,  3.38it/s]
  6%|▌         | 238/4250 [00:56<17:28,  3.83it/s]
  6%|▌         | 239/4250 [00:57<17:32,  3.81it/s]
  6%|▌         | 240/4250 [00:57<20:00,  3.34it/s]
  6%|▌         | 241/4250 [00:57<18:01,  3.71it/s]
  6%|▌         | 242/4250 [00:58<16:32,  4.04it/s]
  6%|▌         | 243/4250 [00:58<16:03,  4.16it/s]
  6%|▌         | 244/4250 [00:58<16:03,  4.16it/s]
  6%|▌         | 245/4250 [00:58<16:00,  4.17it/s]
  6%|▌         | 246/4250 [00:59<24:58,  2.67it/s]
  6%|▌         | 247/4250 [00:59<22:20,  2.99it/s]
  6%|▌         | 248/4250 [00:59<19:39,  3.39it/s]
  6%|▌         | 249/4250 [01:00<23:51,  2.79it/s]
  6%|▌         | 250/4250 [01:00<25:16,  2.64it/s]
  6%|▌         | 251/4250 [01:01<22:47,  2.92it/s]
  6%|▌         | 252/4250 [01:01<19:31,  3.41it/s]
  6%|▌         | 253/4250 [01:01<17:12,  3.87it/s]
  6%|▌         | 254/4250 [01:01<17:52,  3.73it/s]
  6%|▌         | 255/4250 [01:01<18:09,  3.67it/s]
  6%|▌         | 256/4250 [01:02<17:54,  3.72it/s]
  6%|▌         | 257/4250 [01:02<16:41,  3.99it/s]
  6%|▌         | 258/4250 [01:02<15:34,  4.27it/s]
  6%|▌         | 259/4250 [01:02<14:26,  4.61it/s]
  6%|▌         | 260/4250 [01:03<15:43,  4.23it/s]
  6%|▌         | 261/4250 [01:03<15:00,  4.43it/s]
  6%|▌         | 262/4250 [01:03<13:51,  4.79it/s]
  6%|▌         | 263/4250 [01:03<12:53,  5.15it/s]
  6%|▌         | 264/4250 [01:03<14:52,  4.47it/s]
  6%|▌         | 265/4250 [01:04<15:49,  4.20it/s]
  6%|▋         | 266/4250 [01:04<15:45,  4.21it/s]
  6%|▋         | 267/4250 [01:04<15:43,  4.22it/s]
  6%|▋         | 268/4250 [01:04<14:46,  4.49it/s]
  6%|▋         | 269/4250 [01:05<14:19,  4.63it/s]
  6%|▋         | 270/4250 [01:05<16:42,  3.97it/s]
  6%|▋         | 271/4250 [01:05<15:07,  4.39it/s]
  6%|▋         | 272/4250 [01:05<14:36,  4.54it/s]
  6%|▋         | 273/4250 [01:05<14:08,  4.69it/s]
  6%|▋         | 274/4250 [01:06<13:43,  4.83it/s]
  6%|▋         | 275/4250 [01:06<13:31,  4.90it/s]
  6%|▋         | 276/4250 [01:06<12:57,  5.11it/s]
  7%|▋         | 277/4250 [01:06<13:38,  4.85it/s]
  7%|▋         | 278/4250 [01:06<13:30,  4.90it/s]
  7%|▋         | 279/4250 [01:07<14:07,  4.68it/s]
  7%|▋         | 280/4250 [01:07<17:31,  3.77it/s]
  7%|▋         | 281/4250 [01:07<16:05,  4.11it/s]
  7%|▋         | 282/4250 [01:07<15:57,  4.14it/s]
  7%|▋         | 283/4250 [01:08<14:59,  4.41it/s]
  7%|▋         | 284/4250 [01:08<14:31,  4.55it/s]
  7%|▋         | 285/4250 [01:08<14:42,  4.49it/s]
  7%|▋         | 286/4250 [01:08<14:16,  4.63it/s]
  7%|▋         | 287/4250 [01:09<15:52,  4.16it/s]
  7%|▋         | 288/4250 [01:09<14:43,  4.48it/s]
  7%|▋         | 289/4250 [01:09<14:54,  4.43it/s]
  7%|▋         | 290/4250 [01:09<14:03,  4.69it/s]
  7%|▋         | 291/4250 [01:09<14:55,  4.42it/s]
  7%|▋         | 292/4250 [01:10<14:00,  4.71it/s]
  7%|▋         | 293/4250 [01:10<13:17,  4.96it/s]
  7%|▋         | 294/4250 [01:10<12:52,  5.12it/s]
  7%|▋         | 295/4250 [01:10<14:15,  4.63it/s]
  7%|▋         | 296/4250 [01:10<13:24,  4.92it/s]
  7%|▋         | 297/4250 [01:11<13:06,  5.02it/s]
  7%|▋         | 298/4250 [01:11<13:03,  5.05it/s]
  7%|▋         | 299/4250 [01:11<13:42,  4.80it/s]
  7%|▋         | 300/4250 [01:11<15:32,  4.24it/s]
  7%|▋         | 301/4250 [01:12<14:54,  4.41it/s]
  7%|▋         | 302/4250 [01:12<16:06,  4.08it/s]
  7%|▋         | 303/4250 [01:12<17:16,  3.81it/s]
  7%|▋         | 304/4250 [01:12<16:34,  3.97it/s]
  7%|▋         | 305/4250 [01:13<16:19,  4.03it/s]
  7%|▋         | 306/4250 [01:13<18:08,  3.62it/s]
  7%|▋         | 307/4250 [01:13<16:02,  4.09it/s]
  7%|▋         | 308/4250 [01:13<15:13,  4.31it/s]
  7%|▋         | 309/4250 [01:14<15:00,  4.38it/s]
  7%|▋         | 310/4250 [01:14<14:22,  4.57it/s]
  7%|▋         | 311/4250 [01:14<13:57,  4.70it/s]
  7%|▋         | 312/4250 [01:14<16:54,  3.88it/s]
  7%|▋         | 313/4250 [01:15<16:11,  4.05it/s]
  7%|▋         | 314/4250 [01:15<16:16,  4.03it/s]
  7%|▋         | 315/4250 [01:15<15:12,  4.31it/s]
  7%|▋         | 316/4250 [01:15<14:32,  4.51it/s]
  7%|▋         | 317/4250 [01:15<15:42,  4.17it/s]
  7%|▋         | 318/4250 [01:16<15:25,  4.25it/s]
  8%|▊         | 319/4250 [01:16<15:46,  4.15it/s]
  8%|▊         | 320/4250 [01:16<16:24,  3.99it/s]
  8%|▊         | 321/4250 [01:16<15:02,  4.35it/s]
  8%|▊         | 322/4250 [01:17<14:34,  4.49it/s]
  8%|▊         | 323/4250 [01:17<13:27,  4.87it/s]
  8%|▊         | 324/4250 [01:17<13:12,  4.95it/s]
  8%|▊         | 325/4250 [01:17<13:20,  4.90it/s]
  8%|▊         | 326/4250 [01:17<12:56,  5.06it/s]
  8%|▊         | 327/4250 [01:18<12:33,  5.21it/s]
  8%|▊         | 328/4250 [01:18<16:34,  3.94it/s]
  8%|▊         | 329/4250 [01:18<17:43,  3.69it/s]
  8%|▊         | 330/4250 [01:18<16:38,  3.92it/s]
  8%|▊         | 331/4250 [01:19<16:14,  4.02it/s]
  8%|▊         | 332/4250 [01:19<15:09,  4.31it/s]
  8%|▊         | 333/4250 [01:19<14:14,  4.59it/s]
  8%|▊         | 334/4250 [01:19<14:32,  4.49it/s]
  8%|▊         | 335/4250 [01:20<15:50,  4.12it/s]
  8%|▊         | 336/4250 [01:20<15:37,  4.17it/s]
  8%|▊         | 337/4250 [01:20<14:28,  4.50it/s]
  8%|▊         | 338/4250 [01:20<13:49,  4.72it/s]
  8%|▊         | 339/4250 [01:21<17:39,  3.69it/s]
  8%|▊         | 340/4250 [01:21<16:23,  3.98it/s]
  8%|▊         | 341/4250 [01:21<17:22,  3.75it/s]
  8%|▊         | 342/4250 [01:21<15:44,  4.14it/s]
  8%|▊         | 343/4250 [01:22<16:07,  4.04it/s]
  8%|▊         | 344/4250 [01:22<15:55,  4.09it/s]
  8%|▊         | 345/4250 [01:22<17:27,  3.73it/s]
  8%|▊         | 346/4250 [01:22<18:31,  3.51it/s]
  8%|▊         | 347/4250 [01:23<17:10,  3.79it/s]
  8%|▊         | 348/4250 [01:23<18:02,  3.61it/s]
  8%|▊         | 349/4250 [01:23<16:20,  3.98it/s]
  8%|▊         | 350/4250 [01:23<16:04,  4.04it/s]
  8%|▊         | 351/4250 [01:24<15:27,  4.20it/s]
  8%|▊         | 352/4250 [01:24<15:43,  4.13it/s]
  8%|▊         | 353/4250 [01:24<14:03,  4.62it/s]
  8%|▊         | 354/4250 [01:24<14:09,  4.58it/s]
  8%|▊         | 355/4250 [01:25<15:16,  4.25it/s]
  8%|▊         | 356/4250 [01:25<14:47,  4.39it/s]
  8%|▊         | 357/4250 [01:25<13:58,  4.64it/s]
  8%|▊         | 358/4250 [01:25<13:27,  4.82it/s]
  8%|▊         | 359/4250 [01:25<12:49,  5.06it/s]
  8%|▊         | 360/4250 [01:26<14:44,  4.40it/s]
  8%|▊         | 361/4250 [01:26<14:12,  4.56it/s]
  9%|▊         | 362/4250 [01:26<13:27,  4.81it/s]
  9%|▊         | 363/4250 [01:26<14:20,  4.52it/s]
  9%|▊         | 364/4250 [01:27<20:33,  3.15it/s]
  9%|▊         | 365/4250 [01:27<19:16,  3.36it/s]
  9%|▊         | 366/4250 [01:27<18:53,  3.43it/s]
  9%|▊         | 367/4250 [01:27<17:08,  3.77it/s]
  9%|▊         | 368/4250 [01:28<15:11,  4.26it/s]
  9%|▊         | 369/4250 [01:28<16:08,  4.01it/s]
  9%|▊         | 370/4250 [01:28<15:07,  4.27it/s]
  9%|▊         | 371/4250 [01:28<14:16,  4.53it/s]
  9%|▉         | 372/4250 [01:29<13:49,  4.67it/s]
  9%|▉         | 373/4250 [01:29<15:45,  4.10it/s]
  9%|▉         | 374/4250 [01:29<15:17,  4.22it/s]
  9%|▉         | 375/4250 [01:30<25:49,  2.50it/s]
  9%|▉         | 376/4250 [01:30<22:04,  2.92it/s]
  9%|▉         | 377/4250 [01:30<19:35,  3.30it/s]
  9%|▉         | 378/4250 [01:30<17:28,  3.69it/s]
  9%|▉         | 379/4250 [01:31<15:53,  4.06it/s]
  9%|▉         | 380/4250 [01:31<15:12,  4.24it/s]
  9%|▉         | 381/4250 [01:31<14:26,  4.47it/s]
  9%|▉         | 382/4250 [01:31<13:56,  4.62it/s]
  9%|▉         | 383/4250 [01:32<15:15,  4.22it/s]
  9%|▉         | 384/4250 [01:32<14:11,  4.54it/s]
  9%|▉         | 385/4250 [01:32<16:37,  3.87it/s]
  9%|▉         | 386/4250 [01:32<18:49,  3.42it/s]
  9%|▉         | 387/4250 [01:33<16:38,  3.87it/s]
  9%|▉         | 388/4250 [01:33<15:53,  4.05it/s]
  9%|▉         | 389/4250 [01:33<15:09,  4.24it/s]
  9%|▉         | 390/4250 [01:33<15:50,  4.06it/s]
  9%|▉         | 391/4250 [01:33<14:30,  4.44it/s]
  9%|▉         | 392/4250 [01:34<14:35,  4.41it/s]
  9%|▉         | 393/4250 [01:34<13:41,  4.70it/s]
  9%|▉         | 394/4250 [01:34<13:40,  4.70it/s]
  9%|▉         | 395/4250 [01:34<13:01,  4.93it/s]
  9%|▉         | 396/4250 [01:34<12:48,  5.02it/s]
  9%|▉         | 397/4250 [01:35<13:29,  4.76it/s]
  9%|▉         | 398/4250 [01:35<14:09,  4.53it/s]
  9%|▉         | 399/4250 [01:35<13:17,  4.83it/s]
  9%|▉         | 400/4250 [01:35<14:40,  4.37it/s]
  9%|▉         | 401/4250 [01:36<14:07,  4.54it/s]
  9%|▉         | 402/4250 [01:36<15:53,  4.04it/s]
  9%|▉         | 403/4250 [01:36<15:28,  4.14it/s]
 10%|▉         | 404/4250 [01:36<14:42,  4.36it/s]
 10%|▉         | 405/4250 [01:37<15:18,  4.18it/s]
 10%|▉         | 406/4250 [01:37<15:58,  4.01it/s]
 10%|▉         | 407/4250 [01:38<23:05,  2.77it/s]
 10%|▉         | 408/4250 [01:38<21:24,  2.99it/s]
 10%|▉         | 409/4250 [01:38<18:33,  3.45it/s]
 10%|▉         | 410/4250 [01:38<17:36,  3.63it/s]
 10%|▉         | 411/4250 [01:38<17:20,  3.69it/s]
 10%|▉         | 412/4250 [01:39<18:25,  3.47it/s]
 10%|▉         | 413/4250 [01:39<17:11,  3.72it/s]
 10%|▉         | 414/4250 [01:39<16:35,  3.86it/s]
 10%|▉         | 415/4250 [01:39<15:19,  4.17it/s]
 10%|▉         | 416/4250 [01:40<14:55,  4.28it/s]
 10%|▉         | 417/4250 [01:40<14:53,  4.29it/s]
 10%|▉         | 418/4250 [01:40<13:45,  4.64it/s]
 10%|▉         | 419/4250 [01:40<14:57,  4.27it/s]
 10%|▉         | 420/4250 [01:41<15:01,  4.25it/s]
 10%|▉         | 421/4250 [01:41<15:29,  4.12it/s]
 10%|▉         | 422/4250 [01:41<15:00,  4.25it/s]
 10%|▉         | 423/4250 [01:41<13:52,  4.60it/s]
 10%|▉         | 424/4250 [01:42<14:35,  4.37it/s]
 10%|█         | 425/4250 [01:42<14:28,  4.40it/s][INFO|trainer.py:805] 2024-08-30 19:58:29,112 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: id, ner_tags, tokens. If id, ner_tags, tokens are not expected by `RobertaForTokenClassification.forward`,  you can safely ignore this message.
+[INFO|trainer.py:3788] 2024-08-30 19:58:29,114 >> 
+***** Running Evaluation *****
+[INFO|trainer.py:3790] 2024-08-30 19:58:29,114 >>   Num examples = 6810
+[INFO|trainer.py:3793] 2024-08-30 19:58:29,114 >>   Batch size = 8
+
+
  0%|          | 0/852 [00:00<?, ?it/s]
+
  1%|          | 10/852 [00:00<00:09, 89.20it/s]
+
  2%|▏         | 19/852 [00:00<00:10, 78.42it/s]
+
  3%|▎         | 27/852 [00:00<00:10, 78.13it/s]
+
  4%|▍         | 35/852 [00:00<00:10, 77.05it/s]
+
  5%|▌         | 43/852 [00:00<00:10, 77.06it/s]
+
  6%|▌         | 51/852 [00:00<00:10, 77.66it/s]
+
  7%|▋         | 60/852 [00:00<00:10, 78.68it/s]
+
  8%|▊         | 68/852 [00:00<00:10, 76.32it/s]
+
  9%|▉         | 76/852 [00:00<00:10, 76.81it/s]
+
 10%|▉         | 84/852 [00:01<00:10, 76.39it/s]
+
 11%|█         | 92/852 [00:01<00:09, 76.10it/s]
+
 12%|█▏        | 100/852 [00:01<00:09, 75.52it/s]
+
 13%|█▎        | 108/852 [00:01<00:09, 75.37it/s]
+
 14%|█▎        | 116/852 [00:01<00:09, 75.61it/s]
+
 15%|█▍        | 125/852 [00:01<00:09, 77.44it/s]
+
 16%|█▌        | 133/852 [00:01<00:09, 74.02it/s]
+
 17%|█▋        | 141/852 [00:01<00:09, 74.52it/s]
+
 17%|█▋        | 149/852 [00:01<00:09, 74.17it/s]
+
 19%|█▊        | 158/852 [00:02<00:09, 76.52it/s]
+
 19%|█▉        | 166/852 [00:02<00:08, 76.93it/s]
+
 20%|██        | 174/852 [00:02<00:08, 77.40it/s]
+
 21%|██▏       | 182/852 [00:02<00:08, 77.81it/s]
+
 22%|██▏       | 191/852 [00:02<00:08, 78.32it/s]
+
 23%|██▎       | 199/852 [00:02<00:08, 78.40it/s]
+
 24%|██▍       | 207/852 [00:02<00:08, 77.19it/s]
+
 25%|██▌       | 215/852 [00:02<00:08, 76.20it/s]
+
 26%|██▌       | 223/852 [00:02<00:08, 77.17it/s]
+
 27%|██▋       | 231/852 [00:03<00:07, 77.72it/s]
+
 28%|██▊       | 239/852 [00:03<00:07, 76.96it/s]
+
 29%|██▉       | 247/852 [00:03<00:08, 75.20it/s]
+
 30%|███       | 256/852 [00:03<00:07, 77.34it/s]
+
 31%|███       | 264/852 [00:03<00:07, 76.46it/s]
+
 32%|███▏      | 272/852 [00:03<00:07, 73.76it/s]
+
 33%|███▎      | 280/852 [00:03<00:07, 74.90it/s]
+
 34%|███▍      | 288/852 [00:03<00:07, 74.86it/s]
+
 35%|███▍      | 296/852 [00:03<00:07, 76.06it/s]
+
 36%|███▌      | 305/852 [00:03<00:07, 77.75it/s]
+
 37%|███▋      | 313/852 [00:04<00:07, 75.79it/s]
+
 38%|███▊      | 321/852 [00:04<00:06, 76.62it/s]
+
 39%|███▊      | 329/852 [00:04<00:06, 76.40it/s]
+
 40%|███▉      | 337/852 [00:04<00:06, 76.71it/s]
+
 41%|████      | 346/852 [00:04<00:06, 77.07it/s]
+
 42%|████▏     | 354/852 [00:04<00:06, 76.21it/s]
+
 42%|████▏     | 362/852 [00:04<00:06, 76.53it/s]
+
 43%|████▎     | 370/852 [00:04<00:06, 76.40it/s]
+
 44%|████▍     | 378/852 [00:04<00:06, 76.51it/s]
+
 45%|████▌     | 386/852 [00:05<00:06, 75.64it/s]
+
 46%|████▌     | 394/852 [00:05<00:05, 76.44it/s]
+
 47%|████▋     | 402/852 [00:05<00:05, 76.42it/s]
+
 48%|████▊     | 410/852 [00:05<00:06, 72.56it/s]
+
 49%|████▉     | 418/852 [00:05<00:05, 74.22it/s]
+
 50%|█████     | 426/852 [00:05<00:05, 73.15it/s]
+
 51%|█████     | 435/852 [00:05<00:05, 74.99it/s]
+
 52%|█████▏    | 443/852 [00:05<00:05, 76.20it/s]
+
 53%|█████▎    | 451/852 [00:05<00:05, 76.98it/s]
+
 54%|█████▍    | 459/852 [00:06<00:05, 77.54it/s]
+
 55%|█████▍    | 467/852 [00:06<00:05, 74.54it/s]
+
 56%|█████▌    | 475/852 [00:06<00:05, 71.46it/s]
+
 57%|█████▋    | 483/852 [00:06<00:05, 72.27it/s]
+
 58%|█████▊    | 491/852 [00:06<00:04, 72.68it/s]
+
 59%|█████▊    | 499/852 [00:06<00:04, 73.96it/s]
+
 60%|█████▉    | 507/852 [00:06<00:04, 73.71it/s]
+
 60%|██████    | 515/852 [00:06<00:04, 74.07it/s]
+
 61%|██████▏   | 523/852 [00:06<00:04, 73.58it/s]
+
 62%|██████▏   | 531/852 [00:06<00:04, 74.92it/s]
+
 63%|██████▎   | 540/852 [00:07<00:04, 76.68it/s]
+
 64%|██████▍   | 548/852 [00:07<00:03, 77.09it/s]
+
 65%|██████▌   | 556/852 [00:07<00:03, 74.59it/s]
+
 66%|██████▌   | 564/852 [00:07<00:03, 75.78it/s]
+
 67%|██████▋   | 572/852 [00:07<00:03, 76.36it/s]
+
 68%|██████▊   | 580/852 [00:07<00:03, 77.03it/s]
+
 69%|██████▉   | 588/852 [00:07<00:03, 76.20it/s]
+
 70%|███████   | 597/852 [00:07<00:03, 77.37it/s]
+
 71%|███████   | 605/852 [00:07<00:03, 77.54it/s]
+
 72%|███████▏  | 613/852 [00:08<00:03, 77.35it/s]
+
 73%|███████▎  | 621/852 [00:08<00:03, 76.88it/s]
+
 74%|███████▍  | 629/852 [00:08<00:02, 75.44it/s]
+
 75%|███████▍  | 637/852 [00:08<00:02, 76.45it/s]
+
 76%|███████▌  | 645/852 [00:08<00:02, 74.01it/s]
+
 77%|███████▋  | 654/852 [00:08<00:02, 76.16it/s]
+
 78%|███████▊  | 662/852 [00:08<00:02, 76.57it/s]
+
 79%|███████▊  | 670/852 [00:08<00:02, 77.05it/s]
+
 80%|███████▉  | 678/852 [00:08<00:02, 77.66it/s]
+
 81%|████████  | 686/852 [00:09<00:02, 78.20it/s]
+
 81%|████████▏ | 694/852 [00:09<00:02, 78.37it/s]
+
 83%|████████▎ | 703/852 [00:09<00:01, 79.27it/s]
+
 84%|████████▎ | 712/852 [00:09<00:01, 80.17it/s]
+
 85%|████████▍ | 721/852 [00:09<00:01, 79.07it/s]
+
 86%|████████▌ | 730/852 [00:09<00:01, 79.67it/s]
+
 87%|████████▋ | 738/852 [00:09<00:01, 79.74it/s]
+
 88%|████████▊ | 746/852 [00:09<00:01, 79.62it/s]
+
 88%|████████▊ | 754/852 [00:09<00:01, 79.63it/s]
+
 90%|████████▉ | 763/852 [00:09<00:01, 79.84it/s]
+
 90%|█████████ | 771/852 [00:10<00:01, 78.47it/s]
+
 91%|█████████▏| 779/852 [00:10<00:00, 77.58it/s]
+
 92%|█████████▏| 787/852 [00:10<00:00, 76.86it/s]
+
 93%|█████████▎| 796/852 [00:10<00:00, 77.54it/s]
+
 94%|█████████▍| 805/852 [00:10<00:00, 78.72it/s]
+
 95%|█████████▌| 813/852 [00:10<00:00, 77.73it/s]
+
 96%|█████████▋| 822/852 [00:10<00:00, 78.66it/s]
+
 98%|█████████▊| 831/852 [00:10<00:00, 79.83it/s]
+
 98%|█████████▊| 839/852 [00:10<00:00, 79.61it/s]
+
 99%|█████████▉| 847/852 [00:11<00:00, 77.55it/s]/usr/local/lib/python3.10/dist-packages/seqeval/metrics/v1.py:57: UndefinedMetricWarning: Recall and F-score are ill-defined and being set to 0.0 in labels with no true samples. Use `zero_division` parameter to control this behavior.
+  _warn_prf(average, modifier, msg_start, len(result))
+
                                                  
+
                                                 
 10%|█         | 425/4250 [01:57<14:28,  4.40it/s]
+
+
                                                 [INFO|trainer.py:3478] 2024-08-30 19:58:43,890 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-425
+[INFO|configuration_utils.py:472] 2024-08-30 19:58:43,892 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-425/config.json
+[INFO|modeling_utils.py:2690] 2024-08-30 19:58:45,270 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-425/model.safetensors
+[INFO|tokenization_utils_base.py:2574] 2024-08-30 19:58:45,271 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-425/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2583] 2024-08-30 19:58:45,271 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-425/special_tokens_map.json
+[INFO|tokenization_utils_base.py:2574] 2024-08-30 19:58:47,606 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2583] 2024-08-30 19:58:47,607 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+
 10%|█         | 426/4250 [02:01<6:11:12,  5.82s/it]
 10%|█         | 427/4250 [02:01<4:23:04,  4.13s/it]
 10%|█         | 428/4250 [02:01<3:08:07,  2.95s/it]
 10%|█         | 429/4250 [02:01<2:17:52,  2.17s/it]
 10%|█         | 430/4250 [02:01<1:39:43,  1.57s/it]
 10%|█         | 431/4250 [02:02<1:14:51,  1.18s/it]
 10%|█         | 432/4250 [02:02<56:05,  1.13it/s]  
 10%|█         | 433/4250 [02:02<42:36,  1.49it/s]
 10%|█         | 434/4250 [02:02<35:09,  1.81it/s]
 10%|█         | 435/4250 [02:03<27:53,  2.28it/s]
 10%|█         | 436/4250 [02:03<23:52,  2.66it/s]
 10%|█         | 437/4250 [02:03<20:33,  3.09it/s]
 10%|█         | 438/4250 [02:03<18:19,  3.47it/s]
 10%|█         | 439/4250 [02:03<16:56,  3.75it/s]
 10%|█         | 440/4250 [02:04<15:28,  4.10it/s]
 10%|█         | 441/4250 [02:04<14:40,  4.33it/s]
 10%|█         | 442/4250 [02:04<14:39,  4.33it/s]
 10%|█         | 443/4250 [02:04<16:18,  3.89it/s]
 10%|█         | 444/4250 [02:05<15:50,  4.01it/s]
 10%|█         | 445/4250 [02:05<14:21,  4.42it/s]
 10%|█         | 446/4250 [02:05<15:17,  4.15it/s]
 11%|█         | 447/4250 [02:05<14:24,  4.40it/s]
 11%|█         | 448/4250 [02:05<13:17,  4.77it/s]
 11%|█         | 449/4250 [02:06<13:08,  4.82it/s]
 11%|█         | 450/4250 [02:06<15:05,  4.20it/s]
 11%|█         | 451/4250 [02:06<15:49,  4.00it/s]
 11%|█         | 452/4250 [02:06<14:51,  4.26it/s]
 11%|█         | 453/4250 [02:07<15:37,  4.05it/s]
 11%|█         | 454/4250 [02:07<15:38,  4.04it/s]
 11%|█         | 455/4250 [02:07<15:50,  3.99it/s]
 11%|█         | 456/4250 [02:07<14:25,  4.38it/s]
 11%|█         | 457/4250 [02:08<13:17,  4.76it/s]
 11%|█         | 458/4250 [02:08<14:22,  4.40it/s]
 11%|█         | 459/4250 [02:09<24:54,  2.54it/s]
 11%|█         | 460/4250 [02:09<25:12,  2.51it/s]
 11%|█         | 461/4250 [02:09<23:10,  2.73it/s]
 11%|█         | 462/4250 [02:09<20:15,  3.12it/s]
 11%|█         | 463/4250 [02:10<17:57,  3.52it/s]
 11%|█         | 464/4250 [02:10<16:49,  3.75it/s]
 11%|█         | 465/4250 [02:10<15:28,  4.08it/s]
 11%|█         | 466/4250 [02:10<14:54,  4.23it/s]
 11%|█         | 467/4250 [02:11<15:20,  4.11it/s]
 11%|█         | 468/4250 [02:11<15:20,  4.11it/s]
 11%|█         | 469/4250 [02:11<14:55,  4.22it/s]
 11%|█         | 470/4250 [02:11<14:12,  4.44it/s]
 11%|█         | 471/4250 [02:11<13:01,  4.84it/s]
 11%|█         | 472/4250 [02:12<14:33,  4.33it/s]
 11%|█         | 473/4250 [02:12<14:12,  4.43it/s]
 11%|█         | 474/4250 [02:12<15:29,  4.06it/s]
 11%|█         | 475/4250 [02:13<19:41,  3.20it/s]
 11%|█         | 476/4250 [02:13<19:02,  3.30it/s]
 11%|█         | 477/4250 [02:13<18:12,  3.45it/s]
 11%|█         | 478/4250 [02:14<18:30,  3.40it/s]
 11%|█▏        | 479/4250 [02:14<17:11,  3.66it/s]
 11%|█▏        | 480/4250 [02:14<15:16,  4.11it/s]
 11%|█▏        | 481/4250 [02:14<16:04,  3.91it/s]
 11%|█▏        | 482/4250 [02:15<17:51,  3.52it/s]
 11%|█▏        | 483/4250 [02:15<16:15,  3.86it/s]
 11%|█▏        | 484/4250 [02:15<14:37,  4.29it/s]
 11%|█▏        | 485/4250 [02:15<14:49,  4.23it/s]
 11%|█▏        | 486/4250 [02:15<15:41,  4.00it/s]
 11%|█▏        | 487/4250 [02:16<14:31,  4.32it/s]
 11%|█▏        | 488/4250 [02:16<14:11,  4.42it/s]
 12%|█▏        | 489/4250 [02:16<18:02,  3.48it/s]
 12%|█▏        | 490/4250 [02:17<16:37,  3.77it/s]
 12%|█▏        | 491/4250 [02:17<16:43,  3.74it/s]
 12%|█▏        | 492/4250 [02:17<15:55,  3.93it/s]
 12%|█▏        | 493/4250 [02:17<14:34,  4.30it/s]
 12%|█▏        | 494/4250 [02:17<15:06,  4.14it/s]
 12%|█▏        | 495/4250 [02:18<17:03,  3.67it/s]
 12%|█▏        | 496/4250 [02:18<16:05,  3.89it/s]
 12%|█▏        | 497/4250 [02:18<14:37,  4.28it/s]
 12%|█▏        | 498/4250 [02:18<13:21,  4.68it/s]
 12%|█▏        | 499/4250 [02:19<14:14,  4.39it/s]
 12%|█▏        | 500/4250 [02:19<13:55,  4.49it/s]
                                                  
 12%|█▏        | 500/4250 [02:19<13:55,  4.49it/s]
 12%|█▏        | 501/4250 [02:19<16:34,  3.77it/s]

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.988249118683902,
+    "total_flos": 1.2649810588547778e+16,
+    "train_loss": 0.10639642311544979,
+    "train_runtime": 1205.6346,
+    "train_samples": 27229,
+    "train_samples_per_second": 225.848,
+    "train_steps_per_second": 3.525
+}

trainer_state.json

@@ -0,0 +1,218 @@
+{
+  "best_metric": 0.4624414693662204,
+  "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-2127",
+  "epoch": 9.988249118683902,
+  "eval_steps": 500,
+  "global_step": 4250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9988249118683902,
+      "eval_accuracy": 0.8517239485355707,
+      "eval_f1": 0.4251637936518033,
+      "eval_loss": 0.3833567500114441,
+      "eval_precision": 0.29195422381409974,
+      "eval_recall": 0.7819372952737482,
+      "eval_runtime": 14.7317,
+      "eval_samples_per_second": 462.27,
+      "eval_steps_per_second": 57.835,
+      "step": 425
+    },
+    {
+      "epoch": 1.1750881316098707,
+      "grad_norm": 1.4406206607818604,
+      "learning_rate": 4.411764705882353e-05,
+      "loss": 0.3349,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.822140140332569,
+      "eval_f1": 0.40249737425603915,
+      "eval_loss": 0.5730458498001099,
+      "eval_precision": 0.2681125621890547,
+      "eval_recall": 0.8069723912026205,
+      "eval_runtime": 14.9036,
+      "eval_samples_per_second": 456.937,
+      "eval_steps_per_second": 57.167,
+      "step": 851
+    },
+    {
+      "epoch": 2.3501762632197414,
+      "grad_norm": 2.988006591796875,
+      "learning_rate": 3.8235294117647055e-05,
+      "loss": 0.1788,
+      "step": 1000
+    },
+    {
+      "epoch": 2.99882491186839,
+      "eval_accuracy": 0.8338185013799827,
+      "eval_f1": 0.42018044559013074,
+      "eval_loss": 0.5796028971672058,
+      "eval_precision": 0.2847990681421083,
+      "eval_recall": 0.8008890968647637,
+      "eval_runtime": 14.7541,
+      "eval_samples_per_second": 461.567,
+      "eval_steps_per_second": 57.747,
+      "step": 1276
+    },
+    {
+      "epoch": 3.525264394829612,
+      "grad_norm": 1.1645787954330444,
+      "learning_rate": 3.235294117647059e-05,
+      "loss": 0.1227,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8388097820863142,
+      "eval_f1": 0.43759863644971914,
+      "eval_loss": 0.6590859889984131,
+      "eval_precision": 0.2996455433560993,
+      "eval_recall": 0.8109499298081423,
+      "eval_runtime": 14.8634,
+      "eval_samples_per_second": 458.172,
+      "eval_steps_per_second": 57.322,
+      "step": 1702
+    },
+    {
+      "epoch": 4.700352526439483,
+      "grad_norm": 1.1214195489883423,
+      "learning_rate": 2.647058823529412e-05,
+      "loss": 0.0856,
+      "step": 2000
+    },
+    {
+      "epoch": 4.9988249118683905,
+      "eval_accuracy": 0.8601754843670617,
+      "eval_f1": 0.4624414693662204,
+      "eval_loss": 0.6266195774078369,
+      "eval_precision": 0.32197630636422075,
+      "eval_recall": 0.8203088441740758,
+      "eval_runtime": 14.7766,
+      "eval_samples_per_second": 460.863,
+      "eval_steps_per_second": 57.659,
+      "step": 2127
+    },
+    {
+      "epoch": 5.875440658049354,
+      "grad_norm": 1.1390776634216309,
+      "learning_rate": 2.058823529411765e-05,
+      "loss": 0.0597,
+      "step": 2500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8475977316105291,
+      "eval_f1": 0.44600244420145363,
+      "eval_loss": 0.7858611941337585,
+      "eval_precision": 0.3075490109110263,
+      "eval_recall": 0.8111839026672906,
+      "eval_runtime": 14.8163,
+      "eval_samples_per_second": 459.628,
+      "eval_steps_per_second": 57.504,
+      "step": 2553
+    },
+    {
+      "epoch": 6.9988249118683905,
+      "eval_accuracy": 0.8507970944841886,
+      "eval_f1": 0.45324675324675323,
+      "eval_loss": 0.829707145690918,
+      "eval_precision": 0.3136796692432141,
+      "eval_recall": 0.8165652784277024,
+      "eval_runtime": 14.8867,
+      "eval_samples_per_second": 457.456,
+      "eval_steps_per_second": 57.232,
+      "step": 2978
+    },
+    {
+      "epoch": 7.050528789659224,
+      "grad_norm": 0.5195357799530029,
+      "learning_rate": 1.4705882352941177e-05,
+      "loss": 0.0458,
+      "step": 3000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8532206461889135,
+      "eval_f1": 0.453628249902988,
+      "eval_loss": 0.8468152284622192,
+      "eval_precision": 0.3134608509116911,
+      "eval_recall": 0.8205428170332242,
+      "eval_runtime": 15.05,
+      "eval_samples_per_second": 452.493,
+      "eval_steps_per_second": 56.611,
+      "step": 3404
+    },
+    {
+      "epoch": 8.225616921269095,
+      "grad_norm": 0.8723571300506592,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 0.0343,
+      "step": 3500
+    },
+    {
+      "epoch": 8.99882491186839,
+      "eval_accuracy": 0.8493827838576352,
+      "eval_f1": 0.44807482862451153,
+      "eval_loss": 0.9241161346435547,
+      "eval_precision": 0.30851345390383766,
+      "eval_recall": 0.8182030884417407,
+      "eval_runtime": 14.662,
+      "eval_samples_per_second": 464.465,
+      "eval_steps_per_second": 58.109,
+      "step": 3829
+    },
+    {
+      "epoch": 9.400705052878966,
+      "grad_norm": 0.6075822710990906,
+      "learning_rate": 2.9411764705882355e-06,
+      "loss": 0.0292,
+      "step": 4000
+    },
+    {
+      "epoch": 9.988249118683902,
+      "eval_accuracy": 0.8498565092616749,
+      "eval_f1": 0.44938176197836166,
+      "eval_loss": 0.938378632068634,
+      "eval_precision": 0.31002310289674784,
+      "eval_recall": 0.816331305568554,
+      "eval_runtime": 15.4697,
+      "eval_samples_per_second": 440.215,
+      "eval_steps_per_second": 55.075,
+      "step": 4250
+    },
+    {
+      "epoch": 9.988249118683902,
+      "step": 4250,
+      "total_flos": 1.2649810588547778e+16,
+      "train_loss": 0.10639642311544979,
+      "train_runtime": 1205.6346,
+      "train_samples_per_second": 225.848,
+      "train_steps_per_second": 3.525
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4250,
+  "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": 1.2649810588547778e+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 sha256:3a7fb15010252c8cbc6a884d820aedc076e55d4b9641d17f55264378c0fcf155
+size 5176