Training in progress, epoch 0

README.md

@@ -0,0 +1,103 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: michiyasunaga/BioLinkBERT-base
+tags:
+- token-classification
+- generated_from_trainer
+datasets:
+- Rodrigo1771/drugtemist-en-fasttext-85-ner
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: output
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: Rodrigo1771/drugtemist-en-fasttext-85-ner
+      type: Rodrigo1771/drugtemist-en-fasttext-85-ner
+      config: DrugTEMIST English NER
+      split: validation
+      args: DrugTEMIST English NER
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.925
+    - name: Recall
+      type: recall
+      value: 0.9310344827586207
+    - name: F1
+      type: f1
+      value: 0.9280074314909428
+    - name: Accuracy
+      type: accuracy
+      value: 0.9986883598917199
+---
+
+<!-- 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 [michiyasunaga/BioLinkBERT-base](https://huggingface.co/michiyasunaga/BioLinkBERT-base) on the Rodrigo1771/drugtemist-en-fasttext-85-ner dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0077
+- Precision: 0.925
+- Recall: 0.9310
+- F1: 0.9280
+- Accuracy: 0.9987
+
+## 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        | 1.0   | 448  | 0.0054          | 0.9404    | 0.8975 | 0.9185 | 0.9986   |
+| 0.016         | 2.0   | 896  | 0.0045          | 0.9162    | 0.9171 | 0.9166 | 0.9986   |
+| 0.0039        | 3.0   | 1344 | 0.0058          | 0.9064    | 0.9385 | 0.9222 | 0.9985   |
+| 0.0022        | 4.0   | 1792 | 0.0057          | 0.8963    | 0.9348 | 0.9151 | 0.9985   |
+| 0.0017        | 5.0   | 2240 | 0.0060          | 0.9178    | 0.9366 | 0.9271 | 0.9987   |
+| 0.0012        | 6.0   | 2688 | 0.0063          | 0.9254    | 0.9254 | 0.9254 | 0.9987   |
+| 0.0008        | 7.0   | 3136 | 0.0069          | 0.9130    | 0.9394 | 0.9260 | 0.9986   |
+| 0.0005        | 8.0   | 3584 | 0.0069          | 0.9214    | 0.9292 | 0.9253 | 0.9986   |
+| 0.0004        | 9.0   | 4032 | 0.0077          | 0.9249    | 0.9292 | 0.9270 | 0.9987   |
+| 0.0004        | 10.0  | 4480 | 0.0077          | 0.925     | 0.9310 | 0.9280 | 0.9987   |
+
+
+### 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": 0.9986883598917199,
+    "eval_f1": 0.9280074314909428,
+    "eval_loss": 0.007708101533353329,
+    "eval_precision": 0.925,
+    "eval_recall": 0.9310344827586207,
+    "eval_runtime": 15.1013,
+    "eval_samples": 6946,
+    "eval_samples_per_second": 459.961,
+    "eval_steps_per_second": 57.545,
+    "predict_accuracy": 0.9986842934577083,
+    "predict_f1": 0.9187817258883249,
+    "predict_loss": 0.007964327931404114,
+    "predict_precision": 0.8930921052631579,
+    "predict_recall": 0.945993031358885,
+    "predict_runtime": 28.3853,
+    "predict_samples_per_second": 518.402,
+    "predict_steps_per_second": 64.822,
+    "total_flos": 1.178126279062056e+16,
+    "train_loss": 0.0030171065125614406,
+    "train_runtime": 1889.6824,
+    "train_samples": 28668,
+    "train_samples_per_second": 151.708,
+    "train_steps_per_second": 2.371
+}

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "michiyasunaga/BioLinkBERT-base",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-FARMACO",
+    "2": "I-FARMACO"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-FARMACO": 1,
+    "I-FARMACO": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28895
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9986883598917199,
+    "eval_f1": 0.9280074314909428,
+    "eval_loss": 0.007708101533353329,
+    "eval_precision": 0.925,
+    "eval_recall": 0.9310344827586207,
+    "eval_runtime": 15.1013,
+    "eval_samples": 6946,
+    "eval_samples_per_second": 459.961,
+    "eval_steps_per_second": 57.545
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40611e818e2049888ec8971082e2927ce2ade5b2fe28c152dda7ca60aee8e8c8
+size 430601004

predict_results.json

@@ -0,0 +1,10 @@
+{
+    "predict_accuracy": 0.9986842934577083,
+    "predict_f1": 0.9187817258883249,
+    "predict_loss": 0.007964327931404114,
+    "predict_precision": 0.8930921052631579,
+    "predict_recall": 0.945993031358885,
+    "predict_runtime": 28.3853,
+    "predict_samples_per_second": 518.402,
+    "predict_steps_per_second": 64.822
+}

special_tokens_map.json

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

tb/events.out.tfevents.1725881335.0a1c9bec2a53.3232.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:593e737686a00ae0f64a94f2ef02389ad7dff30c0ba6a6f2b1c65ac31e873867
+size 11302

tb/events.out.tfevents.1725882696.0a1c9bec2a53.3232.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ecdc6d00855fb66deb25a7b5be160aa0ebb2ebe07a43beb7d88fb0430fb141
+size 560

tb/events.out.tfevents.1725882852.0a1c9bec2a53.9893.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:543df15001da008ba822f9c1ebf4f77259f803cbf1c5758f2da70bdbf003d86f
+size 11091

tb/events.out.tfevents.1725883955.0a1c9bec2a53.9893.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b842d84c89f0d88706e31e98b113fae6b45879220115930147db648f848a8c24
+size 560

tb/events.out.tfevents.1725884095.0a1c9bec2a53.15221.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a5eb73def06ef281d6c5abe9cbb6a47c633f2d7191b334dbe5cbead1c284e80
+size 10880

tb/events.out.tfevents.1725885059.0a1c9bec2a53.15221.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c793a2eec8072a81c25e2f78d3ef7bcf74abbe37e32354df7dcda008aa71eda
+size 560

tb/events.out.tfevents.1725885168.0a1c9bec2a53.19825.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0f9a2adaf22b0a47090405af62255c59f8c395faf6fe62ec62fa970d9063713
+size 10880

tb/events.out.tfevents.1725886061.0a1c9bec2a53.19825.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa09451db71ecc3a737f5726105cdc310a150c4cd36e427e1f2dad13956046fd
+size 560

tb/events.out.tfevents.1725886210.0a1c9bec2a53.24273.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a173893ab6ea4bae83ba8f7d43d877ca16a06c53d30cb7f414ae20737d881888
+size 12305

tb/events.out.tfevents.1725888457.0a1c9bec2a53.24273.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bb5583c37fdbd9ea659142a09fba0fae95a78d6f0eaac64a0292bc00e64215d
+size 560

tb/events.out.tfevents.1725888716.0a1c9bec2a53.34821.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90e8e7961730149c6c235f6c85cd7c14fbfd2b133f0d765a77e4ff36d922e037
+size 12094

tb/events.out.tfevents.1725890856.0a1c9bec2a53.34821.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e48c8b756097d535fb92e12d532058c15666eb7d5fe08ece1421f853f8616afe
+size 560

tb/events.out.tfevents.1725891307.0a1c9bec2a53.45801.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b59ea71e16013960515c0ea3aec0462f8d6295f502eaf0ddccffb7136d4244c
+size 11883

tb/events.out.tfevents.1725893247.0a1c9bec2a53.45801.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eb0ea5376593c677f9f45e198627a38538984ad7f53adc631503b0e4a5e2fee
+size 560

tb/events.out.tfevents.1725893713.0a1c9bec2a53.55811.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65b143233c7e274fae4af7647d01071caef7613f9ad0ff20f0e66bf331518c3d
+size 5593

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train.log

@@ -0,0 +1,329 @@
+2024-09-09 14:54:26.533883: 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`.
+2024-09-09 14:54:26.551972: 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
+2024-09-09 14:54:26.573854: 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
+2024-09-09 14:54:26.580465: 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
+2024-09-09 14:54:26.595903: 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.
+2024-09-09 14:54:27.853402: 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(
+09/09/2024 14:54:29 - WARNING - __main__ -   Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False
+09/09/2024 14:54:29 - 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] 2024-09-09 14:55:04,800 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--michiyasunaga--BioLinkBERT-base/snapshots/b71f5d70f063d1c8f1124070ce86f1ee463ca1fe/config.json
+[INFO|configuration_utils.py:800] 2024-09-09 14:55:04,803 >> Model config BertConfig {
+  "_name_or_path": "michiyasunaga/BioLinkBERT-base",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-FARMACO",
+    "2": "I-FARMACO"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-FARMACO": 1,
+    "I-FARMACO": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28895
+}
+
+[INFO|tokenization_utils_base.py:2269] 2024-09-09 14:55:05,041 >> loading file vocab.txt from cache at /root/.cache/huggingface/hub/models--michiyasunaga--BioLinkBERT-base/snapshots/b71f5d70f063d1c8f1124070ce86f1ee463ca1fe/vocab.txt
+[INFO|tokenization_utils_base.py:2269] 2024-09-09 14:55:05,041 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--michiyasunaga--BioLinkBERT-base/snapshots/b71f5d70f063d1c8f1124070ce86f1ee463ca1fe/tokenizer.json
+[INFO|tokenization_utils_base.py:2269] 2024-09-09 14:55:05,041 >> loading file added_tokens.json from cache at None
+[INFO|tokenization_utils_base.py:2269] 2024-09-09 14:55:05,041 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--michiyasunaga--BioLinkBERT-base/snapshots/b71f5d70f063d1c8f1124070ce86f1ee463ca1fe/special_tokens_map.json
+[INFO|tokenization_utils_base.py:2269] 2024-09-09 14:55:05,041 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--michiyasunaga--BioLinkBERT-base/snapshots/b71f5d70f063d1c8f1124070ce86f1ee463ca1fe/tokenizer_config.json
+/usr/local/lib/python3.10/dist-packages/transformers/tokenization_utils_base.py:1601: FutureWarning: `clean_up_tokenization_spaces` was not set. It will be set to `True` by default. This behavior will be depracted in transformers v4.45, and will be then set to `False` by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884
+  warnings.warn(
+[INFO|modeling_utils.py:3678] 2024-09-09 14:55:05,351 >> loading weights file pytorch_model.bin from cache at /root/.cache/huggingface/hub/models--michiyasunaga--BioLinkBERT-base/snapshots/b71f5d70f063d1c8f1124070ce86f1ee463ca1fe/pytorch_model.bin
+[INFO|modeling_utils.py:4497] 2024-09-09 14:55:05,431 >> Some weights of the model checkpoint at michiyasunaga/BioLinkBERT-base were not used when initializing BertForTokenClassification: ['bert.pooler.dense.bias', 'bert.pooler.dense.weight']
+- This IS expected if you are initializing BertForTokenClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
+- This IS NOT expected if you are initializing BertForTokenClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
+[WARNING|modeling_utils.py:4509] 2024-09-09 14:55:05,431 >> Some weights of BertForTokenClassification were not initialized from the model checkpoint at michiyasunaga/BioLinkBERT-base 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] 2024-09-09 14:55:12,756 >> The following columns in the training set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: id, ner_tags, tokens. If id, ner_tags, tokens are not expected by `BertForTokenClassification.forward`,  you can safely ignore this message.
+[INFO|trainer.py:2134] 2024-09-09 14:55:13,341 >> ***** Running training *****
+[INFO|trainer.py:2135] 2024-09-09 14:55:13,341 >>   Num examples = 27,841
+[INFO|trainer.py:2136] 2024-09-09 14:55:13,341 >>   Num Epochs = 10
+[INFO|trainer.py:2137] 2024-09-09 14:55:13,341 >>   Instantaneous batch size per device = 32
+[INFO|trainer.py:2140] 2024-09-09 14:55:13,341 >>   Total train batch size (w. parallel, distributed & accumulation) = 64
+[INFO|trainer.py:2141] 2024-09-09 14:55:13,341 >>   Gradient Accumulation steps = 2
+[INFO|trainer.py:2142] 2024-09-09 14:55:13,341 >>   Total optimization steps = 4,350
+[INFO|trainer.py:2143] 2024-09-09 14:55:13,342 >>   Number of trainable parameters = 107,644,419
+
  0%|          | 0/4350 [00:00<?, ?it/s]
  0%|          | 1/4350 [00:01<1:26:47,  1.20s/it]
  0%|          | 2/4350 [00:01<48:19,  1.50it/s]  
  0%|          | 3/4350 [00:01<35:09,  2.06it/s]
  0%|          | 4/4350 [00:02<34:11,  2.12it/s]
  0%|          | 5/4350 [00:02<32:13,  2.25it/s]
  0%|          | 6/4350 [00:03<31:07,  2.33it/s]
  0%|          | 7/4350 [00:03<27:29,  2.63it/s]
  0%|          | 8/4350 [00:03<29:39,  2.44it/s]
  0%|          | 9/4350 [00:04<29:25,  2.46it/s]
  0%|          | 10/4350 [00:04<28:28,  2.54it/s]
  0%|          | 11/4350 [00:05<30:37,  2.36it/s]
  0%|          | 12/4350 [00:05<29:55,  2.42it/s]
  0%|          | 13/4350 [00:05<28:12,  2.56it/s]
  0%|          | 14/4350 [00:06<25:29,  2.84it/s]
  0%|          | 15/4350 [00:06<25:23,  2.84it/s]
  0%|          | 16/4350 [00:06<26:41,  2.71it/s]
  0%|          | 17/4350 [00:07<25:02,  2.88it/s]
  0%|          | 18/4350 [00:07<27:48,  2.60it/s]
  0%|          | 19/4350 [00:07<24:49,  2.91it/s]
  0%|          | 20/4350 [00:08<24:27,  2.95it/s]
  0%|          | 21/4350 [00:08<31:17,  2.31it/s]
  1%|          | 22/4350 [00:09<28:58,  2.49it/s]
  1%|          | 23/4350 [00:09<28:39,  2.52it/s]
  1%|          | 24/4350 [00:09<27:03,  2.66it/s]
  1%|          | 25/4350 [00:10<27:26,  2.63it/s]
  1%|          | 26/4350 [00:10<27:22,  2.63it/s]
  1%|          | 27/4350 [00:10<24:40,  2.92it/s]
  1%|          | 28/4350 [00:11<24:44,  2.91it/s]
  1%|          | 29/4350 [00:11<24:42,  2.92it/s]
  1%|          | 30/4350 [00:11<24:17,  2.96it/s]
  1%|          | 31/4350 [00:12<24:57,  2.88it/s]
  1%|          | 32/4350 [00:12<24:02,  2.99it/s]
  1%|          | 33/4350 [00:12<25:04,  2.87it/s]
  1%|          | 34/4350 [00:13<24:17,  2.96it/s]
  1%|          | 35/4350 [00:13<24:21,  2.95it/s]
  1%|          | 36/4350 [00:13<25:29,  2.82it/s]
  1%|          | 37/4350 [00:14<24:33,  2.93it/s]
  1%|          | 38/4350 [00:14<23:11,  3.10it/s]
  1%|          | 39/4350 [00:14<25:50,  2.78it/s]
  1%|          | 40/4350 [00:15<29:44,  2.42it/s]
  1%|          | 41/4350 [00:15<29:19,  2.45it/s]
  1%|          | 42/4350 [00:16<28:55,  2.48it/s]
  1%|          | 43/4350 [00:16<30:34,  2.35it/s]
  1%|          | 44/4350 [00:17<28:24,  2.53it/s]
  1%|          | 45/4350 [00:17<28:44,  2.50it/s]
  1%|          | 46/4350 [00:17<28:03,  2.56it/s]
  1%|          | 47/4350 [00:18<28:46,  2.49it/s]
  1%|          | 48/4350 [00:18<27:34,  2.60it/s]
  1%|          | 49/4350 [00:18<25:37,  2.80it/s]
  1%|          | 50/4350 [00:19<25:17,  2.83it/s]
  1%|          | 51/4350 [00:19<26:12,  2.73it/s]
  1%|          | 52/4350 [00:20<25:24,  2.82it/s]
  1%|          | 53/4350 [00:20<24:51,  2.88it/s]
  1%|          | 54/4350 [00:20<28:45,  2.49it/s]
  1%|▏         | 55/4350 [00:21<26:33,  2.70it/s]
  1%|▏         | 56/4350 [00:21<23:51,  3.00it/s]
  1%|▏         | 57/4350 [00:21<26:54,  2.66it/s]
  1%|▏         | 58/4350 [00:22<28:44,  2.49it/s]
  1%|▏         | 59/4350 [00:22<30:49,  2.32it/s]
  1%|▏         | 60/4350 [00:23<29:21,  2.44it/s]
  1%|▏         | 61/4350 [00:23<27:50,  2.57it/s]
  1%|▏         | 62/4350 [00:23<26:32,  2.69it/s]
  1%|▏         | 63/4350 [00:24<27:12,  2.63it/s]
  1%|▏         | 64/4350 [00:24<29:29,  2.42it/s]
  1%|▏         | 65/4350 [00:25<26:34,  2.69it/s]
  2%|▏         | 66/4350 [00:25<25:51,  2.76it/s]
  2%|▏         | 67/4350 [00:25<25:44,  2.77it/s]
  2%|▏         | 68/4350 [00:26<28:14,  2.53it/s]
  2%|▏         | 69/4350 [00:26<26:22,  2.71it/s]
  2%|▏         | 70/4350 [00:26<25:55,  2.75it/s]
  2%|▏         | 71/4350 [00:27<25:53,  2.75it/s]
  2%|▏         | 72/4350 [00:27<24:28,  2.91it/s]
  2%|▏         | 73/4350 [00:27<23:34,  3.02it/s]
  2%|▏         | 74/4350 [00:28<28:47,  2.48it/s]
  2%|▏         | 75/4350 [00:28<27:12,  2.62it/s]
  2%|▏         | 76/4350 [00:29<26:36,  2.68it/s]
  2%|▏         | 77/4350 [00:29<25:00,  2.85it/s]
  2%|▏         | 78/4350 [00:29<25:03,  2.84it/s]
  2%|▏         | 79/4350 [00:30<24:07,  2.95it/s]
  2%|▏         | 80/4350 [00:30<28:37,  2.49it/s]
  2%|▏         | 81/4350 [00:31<28:27,  2.50it/s]
  2%|▏         | 82/4350 [00:31<26:29,  2.68it/s]
  2%|▏         | 83/4350 [00:31<25:48,  2.75it/s]
  2%|▏         | 84/4350 [00:32<29:21,  2.42it/s]
  2%|▏         | 85/4350 [00:32<28:18,  2.51it/s]
  2%|▏         | 86/4350 [00:32<27:17,  2.60it/s]
  2%|▏         | 87/4350 [00:33<24:25,  2.91it/s]
  2%|▏         | 88/4350 [00:33<23:17,  3.05it/s]
  2%|▏         | 89/4350 [00:33<22:39,  3.14it/s]
  2%|▏         | 90/4350 [00:34<23:57,  2.96it/s]
  2%|▏         | 91/4350 [00:34<24:14,  2.93it/s]
  2%|▏         | 92/4350 [00:34<25:34,  2.77it/s]
  2%|▏         | 93/4350 [00:35<25:50,  2.75it/s]
  2%|▏         | 94/4350 [00:35<25:12,  2.81it/s]
  2%|▏         | 95/4350 [00:35<25:13,  2.81it/s]
  2%|▏         | 96/4350 [00:36<26:06,  2.72it/s]
  2%|▏         | 97/4350 [00:36<26:14,  2.70it/s]
  2%|▏         | 98/4350 [00:37<25:29,  2.78it/s]
  2%|▏         | 99/4350 [00:37<23:56,  2.96it/s]
  2%|▏         | 100/4350 [00:37<25:47,  2.75it/s]
  2%|▏         | 101/4350 [00:38<25:40,  2.76it/s]
  2%|▏         | 102/4350 [00:38<26:57,  2.63it/s]
  2%|▏         | 103/4350 [00:38<25:28,  2.78it/s]
  2%|▏         | 104/4350 [00:39<25:48,  2.74it/s]
  2%|▏         | 105/4350 [00:39<24:48,  2.85it/s]
  2%|▏         | 106/4350 [00:39<23:25,  3.02it/s]
  2%|▏         | 107/4350 [00:40<21:57,  3.22it/s]
  2%|▏         | 108/4350 [00:40<22:23,  3.16it/s]
  3%|▎         | 109/4350 [00:40<21:53,  3.23it/s]
  3%|▎         | 110/4350 [00:41<22:42,  3.11it/s]
  3%|▎         | 111/4350 [00:41<23:09,  3.05it/s]
  3%|▎         | 112/4350 [00:41<22:32,  3.13it/s]
  3%|▎         | 113/4350 [00:42<24:23,  2.90it/s]
  3%|▎         | 114/4350 [00:42<27:08,  2.60it/s]
  3%|▎         | 115/4350 [00:42<25:08,  2.81it/s]
  3%|▎         | 116/4350 [00:43<23:52,  2.96it/s]
  3%|▎         | 117/4350 [00:43<23:58,  2.94it/s]
  3%|▎         | 118/4350 [00:43<23:30,  3.00it/s]
  3%|▎         | 119/4350 [00:44<24:10,  2.92it/s]
  3%|▎         | 120/4350 [00:44<22:06,  3.19it/s]
  3%|▎         | 121/4350 [00:44<23:01,  3.06it/s]
  3%|▎         | 122/4350 [00:45<24:28,  2.88it/s]
  3%|▎         | 123/4350 [00:45<23:25,  3.01it/s]
  3%|▎         | 124/4350 [00:45<24:26,  2.88it/s]
  3%|▎         | 125/4350 [00:46<23:50,  2.95it/s]
  3%|▎         | 126/4350 [00:46<23:31,  2.99it/s]
  3%|▎         | 127/4350 [00:46<25:08,  2.80it/s]
  3%|▎         | 128/4350 [00:47<28:37,  2.46it/s]
  3%|▎         | 129/4350 [00:47<27:30,  2.56it/s]
  3%|▎         | 130/4350 [00:48<28:05,  2.50it/s]
  3%|▎         | 131/4350 [00:48<26:05,  2.69it/s]
  3%|▎         | 132/4350 [00:48<26:28,  2.66it/s]
  3%|▎         | 133/4350 [00:49<30:00,  2.34it/s]
  3%|▎         | 134/4350 [00:49<30:42,  2.29it/s]
  3%|▎         | 135/4350 [00:50<32:31,  2.16it/s]
  3%|▎         | 136/4350 [00:50<31:18,  2.24it/s]
  3%|▎         | 137/4350 [00:51<28:02,  2.50it/s]
  3%|▎         | 138/4350 [00:51<26:29,  2.65it/s]
  3%|▎         | 139/4350 [00:51<26:52,  2.61it/s]
  3%|▎         | 140/4350 [00:52<24:46,  2.83it/s]
  3%|▎         | 141/4350 [00:52<24:21,  2.88it/s]
  3%|▎         | 142/4350 [00:52<22:53,  3.06it/s]
  3%|▎         | 143/4350 [00:53<22:50,  3.07it/s]
  3%|▎         | 144/4350 [00:53<22:02,  3.18it/s]
  3%|▎         | 145/4350 [00:53<24:49,  2.82it/s]
  3%|▎         | 146/4350 [00:54<22:41,  3.09it/s]
  3%|▎         | 147/4350 [00:54<21:48,  3.21it/s]
  3%|▎         | 148/4350 [00:54<21:27,  3.26it/s]
  3%|▎         | 149/4350 [00:55<24:15,  2.89it/s]
  3%|▎         | 150/4350 [00:55<24:44,  2.83it/s]
  3%|▎         | 151/4350 [00:55<26:30,  2.64it/s]
  3%|▎         | 152/4350 [00:56<25:07,  2.78it/s]
  4%|▎         | 153/4350 [00:56<26:45,  2.61it/s]
  4%|▎         | 154/4350 [00:56<25:22,  2.76it/s]
  4%|▎         | 155/4350 [00:57<25:16,  2.77it/s]
  4%|▎         | 156/4350 [00:57<24:03,  2.91it/s]
  4%|▎         | 157/4350 [00:58<26:08,  2.67it/s]
  4%|▎         | 158/4350 [00:58<25:24,  2.75it/s]
  4%|▎         | 159/4350 [00:58<24:39,  2.83it/s]
  4%|▎         | 160/4350 [00:59<23:24,  2.98it/s]
  4%|▎         | 161/4350 [00:59<22:40,  3.08it/s]
  4%|▎         | 162/4350 [00:59<23:26,  2.98it/s]
  4%|▎         | 163/4350 [01:00<27:26,  2.54it/s]
  4%|▍         | 164/4350 [01:00<26:22,  2.65it/s]
  4%|▍         | 165/4350 [01:00<26:08,  2.67it/s]
  4%|▍         | 166/4350 [01:01<27:07,  2.57it/s]
  4%|▍         | 167/4350 [01:01<25:08,  2.77it/s]
  4%|▍         | 168/4350 [01:01<24:15,  2.87it/s]
  4%|▍         | 169/4350 [01:02<22:37,  3.08it/s]
  4%|▍         | 170/4350 [01:02<23:54,  2.91it/s]
  4%|▍         | 171/4350 [01:03<25:48,  2.70it/s]
  4%|▍         | 172/4350 [01:03<26:05,  2.67it/s]
  4%|▍         | 173/4350 [01:03<25:06,  2.77it/s]
  4%|▍         | 174/4350 [01:04<24:17,  2.86it/s]
  4%|▍         | 175/4350 [01:04<26:11,  2.66it/s]
  4%|▍         | 176/4350 [01:05<29:55,  2.32it/s]
  4%|▍         | 177/4350 [01:05<26:45,  2.60it/s]
  4%|▍         | 178/4350 [01:05<25:36,  2.72it/s]
  4%|▍         | 179/4350 [01:06<27:32,  2.52it/s]
  4%|▍         | 180/4350 [01:06<26:09,  2.66it/s]
  4%|▍         | 181/4350 [01:07<31:31,  2.20it/s]
  4%|▍         | 182/4350 [01:07<28:29,  2.44it/s]
  4%|▍         | 183/4350 [01:07<25:00,  2.78it/s]
  4%|▍         | 184/4350 [01:08<23:57,  2.90it/s]
  4%|▍         | 185/4350 [01:08<23:22,  2.97it/s]
  4%|▍         | 186/4350 [01:08<23:55,  2.90it/s]
  4%|▍         | 187/4350 [01:09<24:13,  2.86it/s]
  4%|▍         | 188/4350 [01:09<23:14,  2.98it/s]
  4%|▍         | 189/4350 [01:09<23:19,  2.97it/s]
  4%|▍         | 190/4350 [01:10<23:50,  2.91it/s]
  4%|▍         | 191/4350 [01:10<24:13,  2.86it/s]
  4%|▍         | 192/4350 [01:10<26:16,  2.64it/s]
  4%|▍         | 193/4350 [01:11<25:08,  2.76it/s]
  4%|▍         | 194/4350 [01:11<23:10,  2.99it/s]
  4%|▍         | 195/4350 [01:11<27:00,  2.56it/s]
  5%|▍         | 196/4350 [01:12<26:52,  2.58it/s]
  5%|▍         | 197/4350 [01:12<25:28,  2.72it/s]
  5%|▍         | 198/4350 [01:12<23:30,  2.94it/s]
  5%|▍         | 199/4350 [01:13<23:27,  2.95it/s]
  5%|▍         | 200/4350 [01:13<26:11,  2.64it/s]
  5%|▍         | 201/4350 [01:14<24:40,  2.80it/s]
  5%|▍         | 202/4350 [01:14<24:16,  2.85it/s]
  5%|▍         | 203/4350 [01:14<23:57,  2.88it/s]
  5%|▍         | 204/4350 [01:15<24:49,  2.78it/s]
  5%|▍         | 205/4350 [01:15<24:27,  2.82it/s]
  5%|▍         | 206/4350 [01:15<23:23,  2.95it/s]
  5%|▍         | 207/4350 [01:16<23:43,  2.91it/s]
  5%|▍         | 208/4350 [01:16<26:45,  2.58it/s]
  5%|▍         | 209/4350 [01:16<25:14,  2.73it/s]
  5%|▍         | 210/4350 [01:17<23:13,  2.97it/s]
  5%|▍         | 211/4350 [01:17<24:28,  2.82it/s]
  5%|▍         | 212/4350 [01:17<22:58,  3.00it/s]
  5%|▍         | 213/4350 [01:18<23:16,  2.96it/s]
  5%|▍         | 214/4350 [01:18<29:27,  2.34it/s]
  5%|▍         | 215/4350 [01:19<28:01,  2.46it/s]
  5%|▍         | 216/4350 [01:19<27:45,  2.48it/s]
  5%|▍         | 217/4350 [01:19<26:16,  2.62it/s]
  5%|▌         | 218/4350 [01:20<24:58,  2.76it/s]
  5%|▌         | 219/4350 [01:20<27:32,  2.50it/s]
  5%|▌         | 220/4350 [01:21<27:51,  2.47it/s]
  5%|▌         | 221/4350 [01:21<28:22,  2.43it/s]
  5%|▌         | 222/4350 [01:21<26:42,  2.58it/s]
  5%|▌         | 223/4350 [01:22<28:07,  2.45it/s]
  5%|▌         | 224/4350 [01:22<28:55,  2.38it/s]
  5%|▌         | 225/4350 [01:23<29:23,  2.34it/s]
  5%|▌         | 226/4350 [01:23<27:54,  2.46it/s]
  5%|▌         | 227/4350 [01:24<27:01,  2.54it/s]
  5%|▌         | 228/4350 [01:24<25:31,  2.69it/s]
  5%|▌         | 229/4350 [01:24<23:13,  2.96it/s]
  5%|▌         | 230/4350 [01:24<22:18,  3.08it/s]
  5%|▌         | 231/4350 [01:25<23:07,  2.97it/s]
  5%|▌         | 232/4350 [01:25<23:03,  2.98it/s]
  5%|▌         | 233/4350 [01:25<22:13,  3.09it/s]
  5%|▌         | 234/4350 [01:26<23:11,  2.96it/s]
  5%|▌         | 235/4350 [01:26<23:18,  2.94it/s]
  5%|▌         | 236/4350 [01:26<23:14,  2.95it/s]
  5%|▌         | 237/4350 [01:27<22:26,  3.05it/s]
  5%|▌         | 238/4350 [01:27<21:03,  3.25it/s]
  5%|▌         | 239/4350 [01:28<27:48,  2.46it/s]
  6%|▌         | 240/4350 [01:28<25:49,  2.65it/s]
  6%|▌         | 241/4350 [01:28<23:33,  2.91it/s]
  6%|▌         | 242/4350 [01:29<26:27,  2.59it/s]
  6%|▌         | 243/4350 [01:29<25:11,  2.72it/s]
  6%|▌         | 244/4350 [01:30<28:43,  2.38it/s]
  6%|▌         | 245/4350 [01:30<28:35,  2.39it/s]
  6%|▌         | 246/4350 [01:30<29:18,  2.33it/s]
  6%|▌         | 247/4350 [01:31<27:55,  2.45it/s]
  6%|▌         | 248/4350 [01:31<26:52,  2.54it/s]
  6%|▌         | 249/4350 [01:32<27:30,  2.48it/s]
  6%|▌         | 250/4350 [01:32<26:22,  2.59it/s]
  6%|▌         | 251/4350 [01:32<26:03,  2.62it/s]
  6%|▌         | 252/4350 [01:33<26:25,  2.59it/s]
  6%|▌         | 253/4350 [01:33<23:55,  2.85it/s]
  6%|▌         | 254/4350 [01:33<22:18,  3.06it/s]
  6%|▌         | 255/4350 [01:34<22:37,  3.02it/s]
  6%|▌         | 256/4350 [01:34<22:50,  2.99it/s]
  6%|▌         | 257/4350 [01:34<25:25,  2.68it/s]
  6%|▌         | 258/4350 [01:35<29:19,  2.33it/s]
  6%|▌         | 259/4350 [01:35<26:57,  2.53it/s]
  6%|▌         | 260/4350 [01:36<27:54,  2.44it/s]
  6%|▌         | 261/4350 [01:36<27:11,  2.51it/s]
  6%|▌         | 262/4350 [01:36<25:56,  2.63it/s]
  6%|▌         | 263/4350 [01:37<26:06,  2.61it/s]
  6%|▌         | 264/4350 [01:37<23:41,  2.87it/s]
  6%|▌         | 265/4350 [01:37<23:16,  2.93it/s]
  6%|▌         | 266/4350 [01:38<22:48,  2.98it/s]
  6%|▌         | 267/4350 [01:38<22:39,  3.00it/s]
  6%|▌         | 268/4350 [01:38<22:43,  2.99it/s]
  6%|▌         | 269/4350 [01:39<20:40,  3.29it/s]
  6%|▌         | 270/4350 [01:39<21:46,  3.12it/s]
  6%|▌         | 271/4350 [01:39<22:54,  2.97it/s]
  6%|▋         | 272/4350 [01:40<21:55,  3.10it/s]
  6%|▋         | 273/4350 [01:40<21:52,  3.11it/s]
  6%|▋         | 274/4350 [01:40<21:41,  3.13it/s]
  6%|▋         | 275/4350 [01:41<22:50,  2.97it/s]
  6%|▋         | 276/4350 [01:41<22:06,  3.07it/s]
  6%|▋         | 277/4350 [01:41<21:06,  3.22it/s]
  6%|▋         | 278/4350 [01:42<23:57,  2.83it/s]
  6%|▋         | 279/4350 [01:42<23:08,  2.93it/s]
  6%|▋         | 280/4350 [01:42<21:59,  3.09it/s]
  6%|▋         | 281/4350 [01:43<22:16,  3.04it/s]
  6%|▋         | 282/4350 [01:43<21:12,  3.20it/s]
  7%|▋         | 283/4350 [01:43<20:40,  3.28it/s]
  7%|▋         | 284/4350 [01:43<20:46,  3.26it/s]
  7%|▋         | 285/4350 [01:44<21:23,  3.17it/s]
  7%|▋         | 286/4350 [01:44<24:38,  2.75it/s]
  7%|▋         | 287/4350 [01:45<24:59,  2.71it/s]
  7%|▋         | 288/4350 [01:45<25:30,  2.65it/s]
  7%|▋         | 289/4350 [01:45<24:13,  2.79it/s]
  7%|▋         | 290/4350 [01:46<25:40,  2.64it/s]
  7%|▋         | 291/4350 [01:46<26:55,  2.51it/s]
  7%|▋         | 292/4350 [01:47<25:25,  2.66it/s]
  7%|▋         | 293/4350 [01:47<27:43,  2.44it/s]
  7%|▋         | 294/4350 [01:47<25:27,  2.66it/s]
  7%|▋         | 295/4350 [01:48<24:33,  2.75it/s]
  7%|▋         | 296/4350 [01:48<23:55,  2.82it/s]
  7%|▋         | 297/4350 [01:48<24:34,  2.75it/s]
  7%|▋         | 298/4350 [01:49<23:14,  2.91it/s]
  7%|▋         | 299/4350 [01:49<25:06,  2.69it/s]
  7%|▋         | 300/4350 [01:50<26:48,  2.52it/s]
  7%|▋         | 301/4350 [01:50<26:58,  2.50it/s]
  7%|▋         | 302/4350 [01:50<27:08,  2.49it/s]
  7%|▋         | 303/4350 [01:51<25:10,  2.68it/s]
  7%|▋         | 304/4350 [01:51<24:23,  2.76it/s]
  7%|▋         | 305/4350 [01:51<24:40,  2.73it/s]
  7%|▋         | 306/4350 [01:52<24:02,  2.80it/s]
  7%|▋         | 307/4350 [01:52<26:31,  2.54it/s]
  7%|▋         | 308/4350 [01:53<24:54,  2.70it/s]
  7%|▋         | 309/4350 [01:53<25:25,  2.65it/s]
  7%|▋         | 310/4350 [01:53<25:02,  2.69it/s]
  7%|▋         | 311/4350 [01:54<23:09,  2.91it/s]
  7%|▋         | 312/4350 [01:54<22:55,  2.94it/s]
  7%|▋         | 313/4350 [01:54<24:20,  2.76it/s]
  7%|▋         | 314/4350 [01:55<22:33,  2.98it/s]
  7%|▋         | 315/4350 [01:55<22:21,  3.01it/s]
  7%|▋         | 316/4350 [01:55<22:25,  3.00it/s]
  7%|▋         | 317/4350 [01:56<21:16,  3.16it/s]
  7%|▋         | 318/4350 [01:56<22:06,  3.04it/s]
  7%|▋         | 319/4350 [01:56<21:16,  3.16it/s]
  7%|▋         | 320/4350 [01:57<21:17,  3.15it/s]
  7%|▋         | 321/4350 [01:57<23:11,  2.89it/s]
  7%|▋         | 322/4350 [01:57<21:07,  3.18it/s]
  7%|▋         | 323/4350 [01:58<23:11,  2.89it/s]
  7%|▋         | 324/4350 [01:58<22:59,  2.92it/s]
  7%|▋         | 325/4350 [01:58<22:27,  2.99it/s]
  7%|▋         | 326/4350 [01:59<23:08,  2.90it/s]
  8%|▊         | 327/4350 [01:59<22:01,  3.04it/s]
  8%|▊         | 328/4350 [01:59<21:22,  3.14it/s]
  8%|▊         | 329/4350 [02:00<23:25,  2.86it/s]
  8%|▊         | 330/4350 [02:00<23:12,  2.89it/s]
  8%|▊         | 331/4350 [02:00<26:42,  2.51it/s]
  8%|▊         | 332/4350 [02:01<27:41,  2.42it/s]
  8%|▊         | 333/4350 [02:01<26:58,  2.48it/s]
  8%|▊         | 334/4350 [02:02<30:37,  2.19it/s]
  8%|▊         | 335/4350 [02:02<28:58,  2.31it/s]
  8%|▊         | 336/4350 [02:03<27:32,  2.43it/s]
  8%|▊         | 337/4350 [02:03<25:56,  2.58it/s]
  8%|▊         | 338/4350 [02:03<24:05,  2.77it/s]
  8%|▊         | 339/4350 [02:04<23:12,  2.88it/s]
  8%|▊         | 340/4350 [02:04<22:21,  2.99it/s]
  8%|▊         | 341/4350 [02:04<21:00,  3.18it/s]
  8%|▊         | 342/4350 [02:04<20:41,  3.23it/s]
  8%|▊         | 343/4350 [02:05<21:35,  3.09it/s]
  8%|▊         | 344/4350 [02:05<23:45,  2.81it/s]
  8%|▊         | 345/4350 [02:06<28:22,  2.35it/s]
  8%|▊         | 346/4350 [02:06<25:33,  2.61it/s]
  8%|▊         | 347/4350 [02:07<27:08,  2.46it/s]
  8%|▊         | 348/4350 [02:07<25:48,  2.58it/s]
  8%|▊         | 349/4350 [02:07<23:48,  2.80it/s]
  8%|▊         | 350/4350 [02:08<23:04,  2.89it/s]
  8%|▊         | 351/4350 [02:08<22:56,  2.91it/s]
  8%|▊         | 352/4350 [02:08<21:51,  3.05it/s]
  8%|▊         | 353/4350 [02:08<22:07,  3.01it/s]
  8%|▊         | 354/4350 [02:09<35:32,  1.87it/s]
  8%|▊         | 355/4350 [02:10<30:32,  2.18it/s]
  8%|▊         | 356/4350 [02:10<30:17,  2.20it/s]
  8%|▊         | 357/4350 [02:11<28:50,  2.31it/s]
  8%|▊         | 358/4350 [02:11<25:47,  2.58it/s]
  8%|▊         | 359/4350 [02:11<24:42,  2.69it/s]
  8%|▊         | 360/4350 [02:12<25:10,  2.64it/s]
  8%|▊         | 361/4350 [02:12<24:15,  2.74it/s]
  8%|▊         | 362/4350 [02:12<21:49,  3.04it/s]
  8%|▊         | 363/4350 [02:12<20:14,  3.28it/s]
  8%|▊         | 364/4350 [02:13<19:53,  3.34it/s]
  8%|▊         | 365/4350 [02:13<20:56,  3.17it/s]
  8%|▊         | 366/4350 [02:13<23:17,  2.85it/s]
  8%|▊         | 367/4350 [02:14<22:06,  3.00it/s]
  8%|▊         | 368/4350 [02:14<23:28,  2.83it/s]
  8%|▊         | 369/4350 [02:15<22:59,  2.89it/s]
  9%|▊         | 370/4350 [02:15<22:03,  3.01it/s]
  9%|▊         | 371/4350 [02:15<22:02,  3.01it/s]
  9%|▊         | 372/4350 [02:16<22:35,  2.94it/s]
  9%|▊         | 373/4350 [02:16<21:48,  3.04it/s]
  9%|▊         | 374/4350 [02:16<21:50,  3.03it/s]
  9%|▊         | 375/4350 [02:17<24:57,  2.65it/s]
  9%|▊         | 376/4350 [02:17<24:08,  2.74it/s]
  9%|▊         | 377/4350 [02:17<23:25,  2.83it/s]
  9%|▊         | 378/4350 [02:18<24:48,  2.67it/s]
  9%|▊         | 379/4350 [02:18<23:59,  2.76it/s]
  9%|▊         | 380/4350 [02:18<23:10,  2.86it/s]
  9%|▉         | 381/4350 [02:19<23:11,  2.85it/s]
  9%|▉         | 382/4350 [02:19<29:29,  2.24it/s]
  9%|▉         | 383/4350 [02:20<26:05,  2.53it/s]
  9%|▉         | 384/4350 [02:20<24:06,  2.74it/s]
  9%|▉         | 385/4350 [02:20<23:35,  2.80it/s]
  9%|▉         | 386/4350 [02:21<23:38,  2.79it/s]
  9%|▉         | 387/4350 [02:21<22:25,  2.95it/s]
  9%|▉         | 388/4350 [02:21<24:05,  2.74it/s]
  9%|▉         | 389/4350 [02:22<23:36,  2.80it/s]
  9%|▉         | 390/4350 [02:22<23:04,  2.86it/s]
  9%|▉         | 391/4350 [02:22<22:44,  2.90it/s]
  9%|▉         | 392/4350 [02:23<25:19,  2.60it/s]
  9%|▉         | 393/4350 [02:23<25:05,  2.63it/s]
  9%|▉         | 394/4350 [02:24<28:22,  2.32it/s]
  9%|▉         | 395/4350 [02:24<25:17,  2.61it/s]
  9%|▉         | 396/4350 [02:24<24:49,  2.65it/s]
  9%|▉         | 397/4350 [02:25<22:40,  2.91it/s]
  9%|▉         | 398/4350 [02:25<22:51,  2.88it/s]
  9%|▉         | 399/4350 [02:25<21:20,  3.08it/s]
  9%|▉         | 400/4350 [02:26<23:42,  2.78it/s]
  9%|▉         | 401/4350 [02:26<23:52,  2.76it/s]
  9%|▉         | 402/4350 [02:27<25:18,  2.60it/s]
  9%|▉         | 403/4350 [02:27<24:41,  2.66it/s]
  9%|▉         | 404/4350 [02:27<25:02,  2.63it/s]
  9%|▉         | 405/4350 [02:28<24:03,  2.73it/s]
  9%|▉         | 406/4350 [02:28<27:48,  2.36it/s]
  9%|▉         | 407/4350 [02:29<28:03,  2.34it/s]
  9%|▉         | 408/4350 [02:29<25:54,  2.54it/s]
  9%|▉         | 409/4350 [02:29<24:35,  2.67it/s]
  9%|▉         | 410/4350 [02:30<22:41,  2.89it/s]
  9%|▉         | 411/4350 [02:30<23:52,  2.75it/s]
  9%|▉         | 412/4350 [02:30<25:11,  2.60it/s]
  9%|▉         | 413/4350 [02:31<24:47,  2.65it/s]
 10%|▉         | 414/4350 [02:31<26:37,  2.46it/s]
 10%|▉         | 415/4350 [02:32<25:33,  2.57it/s]
 10%|▉         | 416/4350 [02:32<24:17,  2.70it/s]
 10%|▉         | 417/4350 [02:32<23:41,  2.77it/s]
 10%|▉         | 418/4350 [02:33<22:35,  2.90it/s]
 10%|▉         | 419/4350 [02:33<21:32,  3.04it/s]
 10%|▉         | 420/4350 [02:33<20:14,  3.24it/s]
 10%|▉         | 421/4350 [02:34<23:00,  2.85it/s]
 10%|▉         | 422/4350 [02:34<22:45,  2.88it/s]
 10%|▉         | 423/4350 [02:34<21:47,  3.00it/s]
 10%|▉         | 424/4350 [02:35<21:44,  3.01it/s]
 10%|▉         | 425/4350 [02:35<22:25,  2.92it/s]
 10%|▉         | 426/4350 [02:35<23:36,  2.77it/s]
 10%|▉         | 427/4350 [02:36<23:06,  2.83it/s]
 10%|▉         | 428/4350 [02:36<22:40,  2.88it/s]
 10%|▉         | 429/4350 [02:36<22:37,  2.89it/s]
 10%|▉         | 430/4350 [02:37<21:50,  2.99it/s]
 10%|▉         | 431/4350 [02:37<21:18,  3.07it/s]
 10%|▉         | 432/4350 [02:37<21:59,  2.97it/s]
 10%|▉         | 433/4350 [02:38<21:34,  3.03it/s]
 10%|▉         | 434/4350 [02:38<20:35,  3.17it/s]
 10%|█         | 435/4350 [02:38<23:44,  2.75it/s][INFO|trainer.py:811] 2024-09-09 14:57:52,268 >> The following columns in the evaluation set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: id, ner_tags, tokens. If id, ner_tags, tokens are not expected by `BertForTokenClassification.forward`,  you can safely ignore this message.
+[INFO|trainer.py:3819] 2024-09-09 14:57:52,271 >> 
+***** Running Evaluation *****
+[INFO|trainer.py:3821] 2024-09-09 14:57:52,271 >>   Num examples = 6946
+[INFO|trainer.py:3824] 2024-09-09 14:57:52,271 >>   Batch size = 8
+
+
  0%|          | 0/869 [00:00<?, ?it/s]
+
  1%|          | 10/869 [00:00<00:09, 94.38it/s]
+
  2%|▏         | 20/869 [00:00<00:10, 80.53it/s]
+
  3%|▎         | 29/869 [00:00<00:10, 78.84it/s]
+
  4%|▍         | 37/869 [00:00<00:10, 75.92it/s]
+
  5%|▌         | 46/869 [00:00<00:10, 79.35it/s]
+
  6%|▋         | 55/869 [00:00<00:09, 81.86it/s]
+
  7%|▋         | 64/869 [00:00<00:10, 77.60it/s]
+
  8%|▊         | 72/869 [00:00<00:10, 76.90it/s]
+
  9%|▉         | 82/869 [00:01<00:09, 81.12it/s]
+
 10%|█         | 91/869 [00:01<00:09, 83.34it/s]
+
 12%|█▏        | 101/869 [00:01<00:08, 86.18it/s]
+
 13%|█▎        | 110/869 [00:01<00:09, 82.44it/s]
+
 14%|█▎        | 119/869 [00:01<00:09, 81.44it/s]
+
 15%|█▍        | 128/869 [00:01<00:09, 79.58it/s]
+
 16%|█▌        | 137/869 [00:01<00:09, 80.83it/s]
+
 17%|█▋        | 146/869 [00:01<00:09, 76.19it/s]
+
 18%|█▊        | 155/869 [00:01<00:09, 78.46it/s]
+
 19%|█▉        | 163/869 [00:02<00:08, 78.50it/s]
+
 20%|█▉        | 171/869 [00:02<00:09, 76.56it/s]
+
 21%|██        | 179/869 [00:02<00:09, 75.51it/s]
+
 22%|██▏       | 188/869 [00:02<00:08, 77.69it/s]
+
 23%|██▎       | 196/869 [00:02<00:08, 75.43it/s]
+
 24%|██▎       | 205/869 [00:02<00:08, 78.09it/s]
+
 25%|██▍       | 214/869 [00:02<00:08, 79.78it/s]
+
 26%|██▌       | 223/869 [00:02<00:07, 81.12it/s]
+
 27%|██▋       | 232/869 [00:02<00:08, 77.58it/s]
+
 28%|██▊       | 240/869 [00:03<00:08, 77.81it/s]
+
 29%|██▊       | 248/869 [00:03<00:08, 72.44it/s]
+
 30%|██▉       | 257/869 [00:03<00:08, 75.03it/s]
+
 30%|███       | 265/869 [00:03<00:08, 74.16it/s]
+
 31%|███▏      | 273/869 [00:03<00:08, 74.49it/s]
+
 32%|███▏      | 281/869 [00:03<00:07, 73.94it/s]
+
 33%|███▎      | 289/869 [00:03<00:07, 73.45it/s]
+
 34%|███▍      | 297/869 [00:03<00:07, 74.28it/s]
+
 35%|███▌      | 305/869 [00:03<00:07, 71.04it/s]
+
 36%|███▌      | 313/869 [00:04<00:07, 72.51it/s]
+
 37%|███▋      | 321/869 [00:04<00:07, 72.04it/s]
+
 38%|███▊      | 330/869 [00:04<00:07, 76.27it/s]
+
 39%|███▉      | 339/869 [00:04<00:06, 77.90it/s]
+
 40%|███▉      | 347/869 [00:04<00:07, 72.34it/s]
+
 41%|████      | 355/869 [00:04<00:07, 73.40it/s]
+
 42%|████▏     | 364/869 [00:04<00:06, 77.35it/s]
+
 43%|████▎     | 373/869 [00:04<00:06, 75.47it/s]
+
 44%|████▍     | 381/869 [00:04<00:06, 76.61it/s]
+
 45%|████▍     | 389/869 [00:05<00:06, 71.19it/s]
+
 46%|████▌     | 398/869 [00:05<00:06, 73.53it/s]
+
 47%|████▋     | 407/869 [00:05<00:06, 75.94it/s]
+
 48%|████▊     | 416/869 [00:05<00:05, 78.73it/s]
+
 49%|████▉     | 425/869 [00:05<00:05, 79.97it/s]
+
 50%|████▉     | 434/869 [00:05<00:05, 79.87it/s]
+
 51%|█████     | 443/869 [00:05<00:05, 75.05it/s]
+
 52%|█████▏    | 452/869 [00:05<00:05, 78.30it/s]
+
 53%|█████▎    | 460/869 [00:05<00:05, 77.46it/s]
+
 54%|█████▍    | 468/869 [00:06<00:05, 77.51it/s]
+
 55%|█████▌    | 478/869 [00:06<00:04, 82.12it/s]
+
 56%|█████▌    | 487/869 [00:06<00:04, 82.39it/s]
+
 57%|█████▋    | 496/869 [00:06<00:04, 77.76it/s]
+
 58%|█████▊    | 504/869 [00:06<00:04, 75.48it/s]
+
 59%|█████▉    | 513/869 [00:06<00:04, 77.10it/s]
+
 60%|██████    | 522/869 [00:06<00:04, 72.55it/s]
+
 61%|██████    | 531/869 [00:06<00:04, 74.98it/s]
+
 62%|██████▏   | 539/869 [00:07<00:04, 73.62it/s]
+
 63%|██████▎   | 547/869 [00:07<00:04, 72.80it/s]
+
 64%|██████▍   | 556/869 [00:07<00:04, 75.57it/s]
+
 65%|██████▍   | 564/869 [00:07<00:04, 76.14it/s]
+
 66%|██████▌   | 572/869 [00:07<00:03, 75.16it/s]
+
 67%|██████▋   | 580/869 [00:07<00:03, 75.56it/s]
+
 68%|██████▊   | 588/869 [00:07<00:03, 74.55it/s]
+
 69%|██████▊   | 597/869 [00:07<00:03, 76.58it/s]
+
 70%|██████▉   | 606/869 [00:07<00:03, 78.76it/s]
+
 71%|███████   | 614/869 [00:07<00:03, 77.83it/s]
+
 72%|███████▏  | 622/869 [00:08<00:03, 76.62it/s]
+
 72%|███████▏  | 630/869 [00:08<00:03, 75.57it/s]
+
 73%|███████▎  | 638/869 [00:08<00:03, 74.86it/s]
+
 74%|███████▍  | 647/869 [00:08<00:02, 78.56it/s]
+
 75%|███████▌  | 656/869 [00:08<00:02, 80.46it/s]
+
 77%|███████▋  | 665/869 [00:08<00:02, 78.96it/s]
+
 78%|███████▊  | 674/869 [00:08<00:02, 81.43it/s]
+
 79%|███████▊  | 683/869 [00:08<00:02, 71.20it/s]
+
 80%|███████▉  | 692/869 [00:09<00:02, 74.89it/s]
+
 81%|████████  | 700/869 [00:09<00:02, 74.84it/s]
+
 81%|████████▏ | 708/869 [00:09<00:02, 74.65it/s]
+
 83%|████████▎ | 717/869 [00:09<00:01, 76.79it/s]
+
 84%|████████▎ | 726/869 [00:09<00:01, 78.45it/s]
+
 84%|████████▍ | 734/869 [00:09<00:01, 78.58it/s]
+
 86%|████████▌ | 743/869 [00:09<00:01, 79.37it/s]
+
 86%|████████▋ | 751/869 [00:09<00:01, 76.29it/s]
+
 87%|████████▋ | 759/869 [00:09<00:01, 77.08it/s]
+
 88%|████████▊ | 767/869 [00:09<00:01, 73.70it/s]
+
 89%|████████▉ | 776/869 [00:10<00:01, 70.08it/s]
+
 90%|█████████ | 784/869 [00:10<00:01, 66.90it/s]
+
 91%|█████████▏| 793/869 [00:10<00:01, 71.36it/s]
+
 92%|█████████▏| 801/869 [00:10<00:00, 73.31it/s]
+
 93%|█████████▎| 809/869 [00:10<00:00, 75.05it/s]
+
 94%|█████████▍| 817/869 [00:10<00:00, 75.70it/s]
+
 95%|█████████▍| 825/869 [00:10<00:00, 76.54it/s]
+
 96%|█████████▌| 833/869 [00:10<00:00, 76.46it/s]
+
 97%|█████████▋| 842/869 [00:10<00:00, 79.79it/s]
+
 98%|█████████▊| 851/869 [00:11<00:00, 80.97it/s]
+
 99%|█████████▉| 860/869 [00:11<00:00, 76.49it/s]
+
                                                  
+
                                                 
 10%|█         | 435/4350 [02:53<23:44,  2.75it/s]
+
+
                                                 [INFO|trainer.py:3503] 2024-09-09 14:58:07,323 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-435
+[INFO|configuration_utils.py:472] 2024-09-09 14:58:07,324 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-435/config.json
+[INFO|modeling_utils.py:2799] 2024-09-09 14:58:08,210 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-435/model.safetensors
+[INFO|tokenization_utils_base.py:2684] 2024-09-09 14:58:08,211 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-435/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2693] 2024-09-09 14:58:08,211 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-435/special_tokens_map.json
+[INFO|tokenization_utils_base.py:2684] 2024-09-09 14:58:15,350 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2693] 2024-09-09 14:58:15,350 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+
 10%|█         | 436/4350 [03:02<7:54:02,  7.27s/it]
 10%|█         | 437/4350 [03:02<5:38:17,  5.19s/it]
 10%|█         | 438/4350 [03:02<4:03:46,  3.74s/it]
 10%|█         | 439/4350 [03:03<2:58:39,  2.74s/it]
 10%|█         | 440/4350 [03:03<2:10:48,  2.01s/it]
 10%|█         | 441/4350 [03:04<1:39:18,  1.52s/it]
 10%|█         | 442/4350 [03:04<1:19:11,  1.22s/it]
 10%|█         | 443/4350 [03:04<1:01:40,  1.06it/s]
 10%|█         | 444/4350 [03:05<50:27,  1.29it/s]  
 10%|█         | 445/4350 [03:05<41:06,  1.58it/s]
 10%|█         | 446/4350 [03:05<35:42,  1.82it/s]
 10%|█         | 447/4350 [03:06<33:41,  1.93it/s]
 10%|█         | 448/4350 [03:06<29:20,  2.22it/s]
 10%|█         | 449/4350 [03:07<28:09,  2.31it/s]
 10%|█         | 450/4350 [03:07<27:36,  2.35it/s]
 10%|█         | 451/4350 [03:07<24:39,  2.64it/s]
 10%|█         | 452/4350 [03:08<25:44,  2.52it/s]
 10%|█         | 453/4350 [03:08<24:33,  2.64it/s]
 10%|█         | 454/4350 [03:08<23:33,  2.76it/s]
 10%|█         | 455/4350 [03:09<22:58,  2.83it/s]
 10%|█         | 456/4350 [03:09<22:12,  2.92it/s]
 11%|█         | 457/4350 [03:09<22:10,  2.93it/s]
 11%|█         | 458/4350 [03:10<24:28,  2.65it/s]
 11%|█         | 459/4350 [03:10<23:59,  2.70it/s]
 11%|█         | 460/4350 [03:10<21:44,  2.98it/s]
 11%|█         | 461/4350 [03:11<21:22,  3.03it/s]
 11%|█         | 462/4350 [03:11<19:33,  3.31it/s]
 11%|█         | 463/4350 [03:11<23:42,  2.73it/s]
 11%|█         | 464/4350 [03:12<23:46,  2.72it/s]
 11%|█         | 465/4350 [03:12<21:40,  2.99it/s]
 11%|█         | 466/4350 [03:12<24:07,  2.68it/s]
 11%|█         | 467/4350 [03:13<24:06,  2.69it/s]
 11%|█         | 468/4350 [03:14<31:52,  2.03it/s]
 11%|█         | 469/4350 [03:14<28:11,  2.29it/s]
 11%|█         | 470/4350 [03:14<27:41,  2.33it/s]
 11%|█         | 471/4350 [03:15<27:16,  2.37it/s]
 11%|█         | 472/4350 [03:15<25:24,  2.54it/s]
 11%|█         | 473/4350 [03:15<24:43,  2.61it/s]
 11%|█         | 474/4350 [03:16<24:10,  2.67it/s]
 11%|█         | 475/4350 [03:16<24:12,  2.67it/s]
 11%|█         | 476/4350 [03:17<23:17,  2.77it/s]
 11%|█         | 477/4350 [03:17<24:06,  2.68it/s]
 11%|█         | 478/4350 [03:17<22:57,  2.81it/s]
 11%|█         | 479/4350 [03:18<24:02,  2.68it/s]
 11%|█         | 480/4350 [03:18<24:15,  2.66it/s]
 11%|█         | 481/4350 [03:18<23:12,  2.78it/s]
 11%|█         | 482/4350 [03:19<23:58,  2.69it/s]
 11%|█         | 483/4350 [03:19<23:27,  2.75it/s]
 11%|█         | 484/4350 [03:19<21:37,  2.98it/s]
 11%|█         | 485/4350 [03:20<21:17,  3.03it/s]
 11%|█         | 486/4350 [03:20<24:09,  2.67it/s]
 11%|█         | 487/4350 [03:20<23:24,  2.75it/s]
 11%|█         | 488/4350 [03:21<24:25,  2.63it/s]
 11%|█         | 489/4350 [03:21<24:16,  2.65it/s]
 11%|█▏        | 490/4350 [03:22<24:30,  2.62it/s]
 11%|█▏        | 491/4350 [03:22<22:52,  2.81it/s]
 11%|█▏        | 492/4350 [03:22<22:31,  2.85it/s]
 11%|█▏        | 493/4350 [03:23<22:25,  2.87it/s]
 11%|█▏        | 494/4350 [03:23<22:51,  2.81it/s]
 11%|█▏        | 495/4350 [03:23<20:55,  3.07it/s]
 11%|█▏        | 496/4350 [03:24<22:34,  2.84it/s]
 11%|█▏        | 497/4350 [03:24<22:38,  2.84it/s]
 11%|█▏        | 498/4350 [03:24<22:48,  2.81it/s]
 11%|█▏        | 499/4350 [03:25<22:06,  2.90it/s]
 11%|█▏        | 500/4350 [03:25<22:27,  2.86it/s]
                                                  
 11%|█▏        | 500/4350 [03:25<22:27,  2.86it/s]
 12%|█▏        | 501/4350 [03:26<23:40,  2.71it/s]
 12%|█▏        | 502/4350 [03:26<22:58,  2.79it/s]
 12%|█▏        | 503/4350 [03:26<23:33,  2.72it/s]
 12%|█▏        | 504/4350 [03:27<23:08,  2.77it/s]
 12%|█▏        | 505/4350 [03:27<20:31,  3.12it/s]
 12%|█▏        | 506/4350 [03:27<20:39,  3.10it/s]
 12%|█▏        | 507/4350 [03:27<19:56,  3.21it/s]
 12%|█▏        | 508/4350 [03:28<21:15,  3.01it/s]
 12%|█▏        | 509/4350 [03:28<23:12,  2.76it/s]
 12%|█▏        | 510/4350 [03:29<21:47,  2.94it/s]
 12%|█▏        | 511/4350 [03:29<21:15,  3.01it/s]
 12%|█▏        | 512/4350 [03:29<23:18,  2.75it/s]
 12%|█▏        | 513/4350 [03:30<22:50,  2.80it/s]
 12%|█▏        | 514/4350 [03:30<22:21,  2.86it/s]
 12%|█▏        | 515/4350 [03:30<21:47,  2.93it/s]
 12%|█▏        | 516/4350 [03:31<22:27,  2.84it/s]
 12%|█▏        | 517/4350 [03:31<24:53,  2.57it/s]
 12%|█▏        | 518/4350 [03:31<22:41,  2.82it/s]
 12%|█▏        | 519/4350 [03:32<21:59,  2.90it/s]
 12%|█▏        | 520/4350 [03:32<23:16,  2.74it/s]
 12%|█▏        | 521/4350 [03:32<22:21,  2.85it/s]
 12%|█▏        | 522/4350 [03:33<21:01,  3.03it/s]
 12%|█▏        | 523/4350 [03:33<22:59,  2.77it/s]
 12%|█▏        | 524/4350 [03:33<22:42,  2.81it/s]
 12%|█▏        | 525/4350 [03:34<24:14,  2.63it/s]
 12%|█▏        | 526/4350 [03:34<24:17,  2.62it/s]
 12%|█▏        | 527/4350 [03:35<23:08,  2.75it/s]
 12%|█▏        | 528/4350 [03:35<23:07,  2.75it/s]
 12%|█▏        | 529/4350 [03:35<25:05,  2.54it/s]
 12%|█▏        | 530/4350 [03:36<31:57,  1.99it/s]
 12%|█▏        | 531/4350 [03:37<28:16,  2.25it/s]
 12%|█▏        | 532/4350 [03:37<25:28,  2.50it/s]
 12%|█▏        | 533/4350 [03:37<22:38,  2.81it/s]
 12%|█▏        | 534/4350 [03:37<23:49,  2.67it/s]
 12%|█▏        | 535/4350 [03:38<24:28,  2.60it/s]
 12%|█▏        | 536/4350 [03:38<23:41,  2.68it/s]
 12%|█▏        | 537/4350 [03:39<25:30,  2.49it/s]
 12%|█▏        | 538/4350 [03:39<24:18,  2.61it/s]
 12%|█▏        | 539/4350 [03:40<28:25,  2.23it/s]
 12%|█▏        | 540/4350 [03:40<26:16,  2.42it/s]
 12%|█▏        | 541/4350 [03:40<25:23,  2.50it/s]
 12%|█▏        | 542/4350 [03:41<23:06,  2.75it/s]
 12%|█▏        | 543/4350 [03:41<24:11,  2.62it/s]
 13%|█▎        | 544/4350 [03:41<22:10,  2.86it/s]
 13%|█▎        | 545/4350 [03:42<22:36,  2.80it/s]
 13%|█▎        | 546/4350 [03:42<23:00,  2.76it/s]
 13%|█▎        | 547/4350 [03:43<24:28,  2.59it/s]
 13%|█▎        | 548/4350 [03:43<24:01,  2.64it/s]
 13%|█▎        | 549/4350 [03:43<24:11,  2.62it/s]
 13%|█▎        | 550/4350 [03:44<23:04,  2.74it/s]
 13%|█▎        | 551/4350 [03:44<22:02,  2.87it/s]
 13%|█▎        | 552/4350 [03:44<21:14,  2.98it/s]
 13%|█▎        | 553/4350 [03:45<24:03,  2.63it/s]
 13%|█▎        | 554/4350 [03:45<22:22,  2.83it/s]
 13%|█▎        | 555/4350 [03:45<21:26,  2.95it/s]
 13%|█▎        | 556/4350 [03:46<19:42,  3.21it/s]
 13%|█▎        | 557/4350 [03:46<20:31,  3.08it/s]
 13%|█▎        | 558/4350 [03:46<21:34,  2.93it/s]
 13%|█▎        | 559/4350 [03:47<21:25,  2.95it/s]
 13%|█▎        | 560/4350 [03:47<21:19,  2.96it/s]
 13%|█▎        | 561/4350 [03:47<22:03,  2.86it/s]
 13%|█▎        | 562/4350 [03:48<23:13,  2.72it/s]
 13%|█▎        | 563/4350 [03:48<24:07,  2.62it/s]
 13%|█▎        | 564/4350 [03:48<21:46,  2.90it/s]
 13%|█▎        | 565/4350 [03:49<22:41,  2.78it/s]
 13%|█▎        | 566/4350 [03:49<24:25,  2.58it/s]
 13%|█▎        | 567/4350 [03:50<29:30,  2.14it/s]
 13%|█▎        | 568/4350 [03:50<29:34,  2.13it/s]
 13%|█▎        | 569/4350 [03:51<27:34,  2.28it/s]
 13%|█▎        | 570/4350 [03:51<25:34,  2.46it/s]
 13%|█▎        | 571/4350 [03:52<26:52,  2.34it/s]
 13%|█▎        | 572/4350 [03:52<24:30,  2.57it/s]
 13%|█▎        | 573/4350 [03:52<25:08,  2.50it/s]

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 1.178126279062056e+16,
+    "train_loss": 0.0030171065125614406,
+    "train_runtime": 1889.6824,
+    "train_samples": 28668,
+    "train_samples_per_second": 151.708,
+    "train_steps_per_second": 2.371
+}

trainer_state.json

@@ -0,0 +1,218 @@
+{
+  "best_metric": 0.9280074314909428,
+  "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-4480",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 4480,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9985976613735942,
+      "eval_f1": 0.9184549356223176,
+      "eval_loss": 0.005405870731920004,
+      "eval_precision": 0.9404296875,
+      "eval_recall": 0.8974836905871388,
+      "eval_runtime": 15.084,
+      "eval_samples_per_second": 460.487,
+      "eval_steps_per_second": 57.611,
+      "step": 448
+    },
+    {
+      "epoch": 1.1160714285714286,
+      "grad_norm": 0.0893813744187355,
+      "learning_rate": 4.4419642857142854e-05,
+      "loss": 0.016,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9985627773281612,
+      "eval_f1": 0.9166278528178854,
+      "eval_loss": 0.004539168905466795,
+      "eval_precision": 0.9162011173184358,
+      "eval_recall": 0.9170549860205033,
+      "eval_runtime": 15.2132,
+      "eval_samples_per_second": 456.577,
+      "eval_steps_per_second": 57.121,
+      "step": 896
+    },
+    {
+      "epoch": 2.232142857142857,
+      "grad_norm": 0.01820996217429638,
+      "learning_rate": 3.883928571428572e-05,
+      "loss": 0.0039,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.998548823709988,
+      "eval_f1": 0.9221611721611722,
+      "eval_loss": 0.005798548460006714,
+      "eval_precision": 0.9063906390639064,
+      "eval_recall": 0.9384902143522833,
+      "eval_runtime": 15.0713,
+      "eval_samples_per_second": 460.875,
+      "eval_steps_per_second": 57.659,
+      "step": 1344
+    },
+    {
+      "epoch": 3.3482142857142856,
+      "grad_norm": 0.09450385719537735,
+      "learning_rate": 3.325892857142857e-05,
+      "loss": 0.0022,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.998513939664555,
+      "eval_f1": 0.9151459854014599,
+      "eval_loss": 0.005682563409209251,
+      "eval_precision": 0.8963360142984808,
+      "eval_recall": 0.934762348555452,
+      "eval_runtime": 15.3704,
+      "eval_samples_per_second": 451.907,
+      "eval_steps_per_second": 56.537,
+      "step": 1792
+    },
+    {
+      "epoch": 4.464285714285714,
+      "grad_norm": 0.08753237873315811,
+      "learning_rate": 2.767857142857143e-05,
+      "loss": 0.0017,
+      "step": 2000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9987023135098931,
+      "eval_f1": 0.9271217712177122,
+      "eval_loss": 0.005979395937174559,
+      "eval_precision": 0.9178082191780822,
+      "eval_recall": 0.9366262814538676,
+      "eval_runtime": 15.1424,
+      "eval_samples_per_second": 458.713,
+      "eval_steps_per_second": 57.389,
+      "step": 2240
+    },
+    {
+      "epoch": 5.580357142857143,
+      "grad_norm": 0.010990791022777557,
+      "learning_rate": 2.2098214285714286e-05,
+      "loss": 0.0012,
+      "step": 2500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9987092903189797,
+      "eval_f1": 0.9254426840633737,
+      "eval_loss": 0.006339639890938997,
+      "eval_precision": 0.9254426840633737,
+      "eval_recall": 0.9254426840633737,
+      "eval_runtime": 15.1172,
+      "eval_samples_per_second": 459.478,
+      "eval_steps_per_second": 57.484,
+      "step": 2688
+    },
+    {
+      "epoch": 6.696428571428571,
+      "grad_norm": 0.0010647091548889875,
+      "learning_rate": 1.6517857142857144e-05,
+      "loss": 0.0008,
+      "step": 3000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9986116149917673,
+      "eval_f1": 0.9260450160771704,
+      "eval_loss": 0.0069307987578213215,
+      "eval_precision": 0.9130434782608695,
+      "eval_recall": 0.9394221808014911,
+      "eval_runtime": 15.1162,
+      "eval_samples_per_second": 459.508,
+      "eval_steps_per_second": 57.488,
+      "step": 3136
+    },
+    {
+      "epoch": 7.8125,
+      "grad_norm": 0.0007633898057974875,
+      "learning_rate": 1.09375e-05,
+      "loss": 0.0005,
+      "step": 3500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9986395222281137,
+      "eval_f1": 0.9252900232018563,
+      "eval_loss": 0.006891186349093914,
+      "eval_precision": 0.9214417744916821,
+      "eval_recall": 0.9291705498602051,
+      "eval_runtime": 15.1611,
+      "eval_samples_per_second": 458.146,
+      "eval_steps_per_second": 57.318,
+      "step": 3584
+    },
+    {
+      "epoch": 8.928571428571429,
+      "grad_norm": 0.0015532037941738963,
+      "learning_rate": 5.357142857142857e-06,
+      "loss": 0.0004,
+      "step": 4000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9986534758462869,
+      "eval_f1": 0.9270106927010694,
+      "eval_loss": 0.0076610674150288105,
+      "eval_precision": 0.924860853432282,
+      "eval_recall": 0.9291705498602051,
+      "eval_runtime": 15.344,
+      "eval_samples_per_second": 452.684,
+      "eval_steps_per_second": 56.634,
+      "step": 4032
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9986883598917199,
+      "eval_f1": 0.9280074314909428,
+      "eval_loss": 0.007708101533353329,
+      "eval_precision": 0.925,
+      "eval_recall": 0.9310344827586207,
+      "eval_runtime": 15.1825,
+      "eval_samples_per_second": 457.501,
+      "eval_steps_per_second": 57.237,
+      "step": 4480
+    },
+    {
+      "epoch": 10.0,
+      "step": 4480,
+      "total_flos": 1.178126279062056e+16,
+      "train_loss": 0.0030171065125614406,
+      "train_runtime": 1889.6824,
+      "train_samples_per_second": 151.708,
+      "train_steps_per_second": 2.371
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4480,
+  "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": 1.178126279062056e+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