Training in progress, epoch 1

README.md

@@ -0,0 +1,103 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: PlanTL-GOB-ES/bsc-bio-ehr-es
+tags:
+- token-classification
+- generated_from_trainer
+datasets:
+- Rodrigo1771/symptemist-fasttext-9-ner
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: output
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: Rodrigo1771/symptemist-fasttext-9-ner
+      type: Rodrigo1771/symptemist-fasttext-9-ner
+      config: SympTEMIST NER
+      split: validation
+      args: SympTEMIST NER
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.6659969864389754
+    - name: Recall
+      type: recall
+      value: 0.7257799671592775
+    - name: F1
+      type: f1
+      value: 0.6946045049764275
+    - name: Accuracy
+      type: accuracy
+      value: 0.9496615226667522
+---
+
+<!-- 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/symptemist-fasttext-9-ner dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2450
+- Precision: 0.6660
+- Recall: 0.7258
+- F1: 0.6946
+- Accuracy: 0.9497
+
+## 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        | 0.9968 | 155  | 0.1485          | 0.5669    | 0.6218 | 0.5931 | 0.9436   |
+| No log        | 2.0    | 311  | 0.1609          | 0.5623    | 0.7159 | 0.6299 | 0.9409   |
+| No log        | 2.9968 | 466  | 0.1635          | 0.6210    | 0.7219 | 0.6677 | 0.9487   |
+| 0.1246        | 4.0    | 622  | 0.2047          | 0.6659    | 0.6765 | 0.6712 | 0.9493   |
+| 0.1246        | 4.9968 | 777  | 0.2134          | 0.6562    | 0.7115 | 0.6828 | 0.9480   |
+| 0.1246        | 6.0    | 933  | 0.2259          | 0.6518    | 0.7099 | 0.6796 | 0.9494   |
+| 0.0242        | 6.9968 | 1088 | 0.2450          | 0.6660    | 0.7258 | 0.6946 | 0.9497   |
+| 0.0242        | 8.0    | 1244 | 0.2650          | 0.6491    | 0.7230 | 0.6841 | 0.9491   |
+| 0.0242        | 8.9968 | 1399 | 0.2745          | 0.6646    | 0.7126 | 0.6878 | 0.9498   |
+| 0.0083        | 9.9678 | 1550 | 0.2774          | 0.6628    | 0.7187 | 0.6896 | 0.9503   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,26 @@
+{
+    "epoch": 9.967845659163988,
+    "eval_accuracy": 0.9496615226667522,
+    "eval_f1": 0.6946045049764275,
+    "eval_loss": 0.24502409994602203,
+    "eval_precision": 0.6659969864389754,
+    "eval_recall": 0.7257799671592775,
+    "eval_runtime": 5.9273,
+    "eval_samples": 2519,
+    "eval_samples_per_second": 424.981,
+    "eval_steps_per_second": 53.144,
+    "predict_accuracy": 0.9468015056363083,
+    "predict_f1": 0.6798307475317349,
+    "predict_loss": 0.26582667231559753,
+    "predict_precision": 0.6624923640806353,
+    "predict_recall": 0.6981010621177985,
+    "predict_runtime": 9.8107,
+    "predict_samples_per_second": 412.509,
+    "predict_steps_per_second": 51.576,
+    "total_flos": 4644619911314910.0,
+    "train_loss": 0.050868147861573,
+    "train_runtime": 855.1929,
+    "train_samples": 9929,
+    "train_samples_per_second": 116.102,
+    "train_steps_per_second": 1.812
+}

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": 9.967845659163988,
+    "eval_accuracy": 0.9496615226667522,
+    "eval_f1": 0.6946045049764275,
+    "eval_loss": 0.24502409994602203,
+    "eval_precision": 0.6659969864389754,
+    "eval_recall": 0.7257799671592775,
+    "eval_runtime": 5.9273,
+    "eval_samples": 2519,
+    "eval_samples_per_second": 424.981,
+    "eval_steps_per_second": 53.144
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de24de8a8a2140ef151720c762b9aa1baa91d13e71b9e69e71c8fea44eb7f992
+size 430601004

predict_results.json

@@ -0,0 +1,10 @@
+{
+    "predict_accuracy": 0.9468015056363083,
+    "predict_f1": 0.6798307475317349,
+    "predict_loss": 0.26582667231559753,
+    "predict_precision": 0.6624923640806353,
+    "predict_recall": 0.6981010621177985,
+    "predict_runtime": 9.8107,
+    "predict_samples_per_second": 412.509,
+    "predict_steps_per_second": 51.576
+}

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:e06bd26a7e6ecde5d6a27f3da6adb8e716555d4d754eaa26c925bf2c2b62de08
+size 5804

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 +1,330 @@
+2024-09-09 12:49:35.169739: 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 12:49:35.188435: 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 12:49:35.210470: 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 12:49:35.217107: 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 12:49:35.233109: 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 12:49:36.523400: 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 12:49:38 - WARNING - __main__ -   Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False
+09/09/2024 12:49:38 - 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 12:49:56,508 >> 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 12:49:56,512 >> 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 12:49:58,923 >> 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 12:49:58,923 >> 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 12:49:58,923 >> loading file added_tokens.json from cache at None
+[INFO|tokenization_utils_base.py:2269] 2024-09-09 12:49:58,923 >> 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 12:49:58,923 >> 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 12:50:02,660 >> 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 12:50:02,740 >> 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 12:50:02,740 >> 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 12:50:10,148 >> The following columns in the training set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: id, tokens, ner_tags. If id, tokens, ner_tags are not expected by `BertForTokenClassification.forward`,  you can safely ignore this message.
+[INFO|trainer.py:2134] 2024-09-09 12:50:10,704 >> ***** Running training *****
+[INFO|trainer.py:2135] 2024-09-09 12:50:10,704 >>   Num examples = 32,447
+[INFO|trainer.py:2136] 2024-09-09 12:50:10,704 >>   Num Epochs = 10
+[INFO|trainer.py:2137] 2024-09-09 12:50:10,704 >>   Instantaneous batch size per device = 32
+[INFO|trainer.py:2140] 2024-09-09 12:50:10,704 >>   Total train batch size (w. parallel, distributed & accumulation) = 64
+[INFO|trainer.py:2141] 2024-09-09 12:50:10,704 >>   Gradient Accumulation steps = 2
+[INFO|trainer.py:2142] 2024-09-09 12:50:10,704 >>   Total optimization steps = 5,070
+[INFO|trainer.py:2143] 2024-09-09 12:50:10,705 >>   Number of trainable parameters = 107,644,419
+
  0%|          | 0/5070 [00:00<?, ?it/s]
  0%|          | 1/5070 [00:01<1:55:56,  1.37s/it]
  0%|          | 2/5070 [00:01<1:01:02,  1.38it/s]
  0%|          | 3/5070 [00:01<43:59,  1.92it/s]  
  0%|          | 4/5070 [00:02<37:03,  2.28it/s]
  0%|          | 5/5070 [00:02<33:54,  2.49it/s]
  0%|          | 6/5070 [00:02<29:56,  2.82it/s]
  0%|          | 7/5070 [00:03<29:13,  2.89it/s]
  0%|          | 8/5070 [00:03<29:19,  2.88it/s]
  0%|          | 9/5070 [00:03<28:01,  3.01it/s]
  0%|          | 10/5070 [00:04<29:27,  2.86it/s]
  0%|          | 11/5070 [00:04<31:52,  2.65it/s]
  0%|          | 12/5070 [00:04<31:16,  2.70it/s]
  0%|          | 13/5070 [00:05<30:19,  2.78it/s]
  0%|          | 14/5070 [00:05<32:35,  2.59it/s]
  0%|          | 15/5070 [00:06<29:33,  2.85it/s]
  0%|          | 16/5070 [00:06<29:08,  2.89it/s]
  0%|          | 17/5070 [00:06<32:23,  2.60it/s]
  0%|          | 18/5070 [00:07<32:56,  2.56it/s]
  0%|          | 19/5070 [00:07<30:14,  2.78it/s]
  0%|          | 20/5070 [00:07<31:25,  2.68it/s]
  0%|          | 21/5070 [00:08<28:05,  3.00it/s]
  0%|          | 22/5070 [00:08<27:40,  3.04it/s]
  0%|          | 23/5070 [00:08<29:31,  2.85it/s]
  0%|          | 24/5070 [00:09<27:57,  3.01it/s]
  0%|          | 25/5070 [00:09<29:57,  2.81it/s]
  1%|          | 26/5070 [00:09<30:14,  2.78it/s]
  1%|          | 27/5070 [00:10<31:00,  2.71it/s]
  1%|          | 28/5070 [00:10<33:13,  2.53it/s]
  1%|          | 29/5070 [00:11<31:44,  2.65it/s]
  1%|          | 30/5070 [00:11<34:06,  2.46it/s]
  1%|          | 31/5070 [00:11<31:33,  2.66it/s]
  1%|          | 32/5070 [00:12<30:32,  2.75it/s]
  1%|          | 33/5070 [00:12<32:34,  2.58it/s]
  1%|          | 34/5070 [00:13<33:22,  2.51it/s]
  1%|          | 35/5070 [00:13<32:11,  2.61it/s]
  1%|          | 36/5070 [00:13<29:47,  2.82it/s]
  1%|          | 37/5070 [00:14<34:03,  2.46it/s]
  1%|          | 38/5070 [00:14<33:12,  2.53it/s]
  1%|          | 39/5070 [00:15<32:01,  2.62it/s]
  1%|          | 40/5070 [00:15<32:04,  2.61it/s]
  1%|          | 41/5070 [00:15<31:28,  2.66it/s]
  1%|          | 42/5070 [00:16<29:43,  2.82it/s]
  1%|          | 43/5070 [00:16<29:54,  2.80it/s]
  1%|          | 44/5070 [00:16<30:08,  2.78it/s]
  1%|          | 45/5070 [00:17<28:16,  2.96it/s]
  1%|          | 46/5070 [00:17<28:34,  2.93it/s]
  1%|          | 47/5070 [00:17<29:04,  2.88it/s]
  1%|          | 48/5070 [00:18<30:31,  2.74it/s]
  1%|          | 49/5070 [00:18<29:37,  2.82it/s]
  1%|          | 50/5070 [00:19<33:53,  2.47it/s]
  1%|          | 51/5070 [00:19<34:07,  2.45it/s]
  1%|          | 52/5070 [00:19<34:08,  2.45it/s]
  1%|          | 53/5070 [00:20<31:49,  2.63it/s]
  1%|          | 54/5070 [00:20<31:13,  2.68it/s]
  1%|          | 55/5070 [00:20<31:05,  2.69it/s]
  1%|          | 56/5070 [00:21<30:58,  2.70it/s]
  1%|          | 57/5070 [00:21<29:45,  2.81it/s]
  1%|          | 58/5070 [00:21<30:11,  2.77it/s]
  1%|          | 59/5070 [00:22<30:56,  2.70it/s]
  1%|          | 60/5070 [00:22<31:45,  2.63it/s]
  1%|          | 61/5070 [00:23<31:48,  2.63it/s]
  1%|          | 62/5070 [00:23<31:35,  2.64it/s]
  1%|          | 63/5070 [00:23<31:04,  2.69it/s]
  1%|▏         | 64/5070 [00:24<28:24,  2.94it/s]
  1%|▏         | 65/5070 [00:24<27:01,  3.09it/s]
  1%|▏         | 66/5070 [00:24<30:56,  2.70it/s]
  1%|▏         | 67/5070 [00:25<33:25,  2.50it/s]
  1%|▏         | 68/5070 [00:25<37:18,  2.23it/s]
  1%|▏         | 69/5070 [00:26<39:18,  2.12it/s]
  1%|▏         | 70/5070 [00:26<35:57,  2.32it/s]
  1%|▏         | 71/5070 [00:27<35:19,  2.36it/s]
  1%|▏         | 72/5070 [00:27<36:17,  2.30it/s]
  1%|▏         | 73/5070 [00:28<38:25,  2.17it/s]
  1%|▏         | 74/5070 [00:28<35:23,  2.35it/s]
  1%|▏         | 75/5070 [00:28<35:34,  2.34it/s]
  1%|▏         | 76/5070 [00:29<35:16,  2.36it/s]
  2%|▏         | 77/5070 [00:29<37:14,  2.23it/s]
  2%|▏         | 78/5070 [00:30<36:13,  2.30it/s]
  2%|▏         | 79/5070 [00:30<37:43,  2.20it/s]
  2%|▏         | 80/5070 [00:31<35:44,  2.33it/s]
  2%|▏         | 81/5070 [00:31<35:40,  2.33it/s]
  2%|▏         | 82/5070 [00:31<32:56,  2.52it/s]
  2%|▏         | 83/5070 [00:32<32:34,  2.55it/s]
  2%|▏         | 84/5070 [00:32<36:48,  2.26it/s]
  2%|▏         | 85/5070 [00:33<34:40,  2.40it/s]
  2%|▏         | 86/5070 [00:33<35:53,  2.31it/s]
  2%|▏         | 87/5070 [00:34<38:14,  2.17it/s]
  2%|▏         | 88/5070 [00:34<37:25,  2.22it/s]
  2%|▏         | 89/5070 [00:34<33:37,  2.47it/s]
  2%|▏         | 90/5070 [00:35<32:47,  2.53it/s]
  2%|▏         | 91/5070 [00:35<30:14,  2.74it/s]
  2%|▏         | 92/5070 [00:36<34:18,  2.42it/s]
  2%|▏         | 93/5070 [00:36<33:53,  2.45it/s]
  2%|▏         | 94/5070 [00:36<34:27,  2.41it/s]
  2%|▏         | 95/5070 [00:37<32:28,  2.55it/s]
  2%|▏         | 96/5070 [00:37<31:05,  2.67it/s]
  2%|▏         | 97/5070 [00:37<28:50,  2.87it/s]
  2%|▏         | 98/5070 [00:38<32:59,  2.51it/s]
  2%|▏         | 99/5070 [00:38<31:29,  2.63it/s]
  2%|▏         | 100/5070 [00:39<31:13,  2.65it/s]
  2%|▏         | 101/5070 [00:39<34:40,  2.39it/s]
  2%|▏         | 102/5070 [00:39<31:42,  2.61it/s]
  2%|▏         | 103/5070 [00:40<32:17,  2.56it/s]
  2%|▏         | 104/5070 [00:40<30:58,  2.67it/s]
  2%|▏         | 105/5070 [00:41<29:59,  2.76it/s]
  2%|▏         | 106/5070 [00:41<36:53,  2.24it/s]
  2%|▏         | 107/5070 [00:42<34:40,  2.39it/s]
  2%|▏         | 108/5070 [00:42<33:38,  2.46it/s]
  2%|▏         | 109/5070 [00:42<33:31,  2.47it/s]
  2%|▏         | 110/5070 [00:43<31:03,  2.66it/s]
  2%|▏         | 111/5070 [00:43<31:56,  2.59it/s]
  2%|▏         | 112/5070 [00:43<31:17,  2.64it/s]
  2%|▏         | 113/5070 [00:44<31:57,  2.58it/s]
  2%|▏         | 114/5070 [00:44<29:33,  2.80it/s]
  2%|▏         | 115/5070 [00:45<31:12,  2.65it/s]
  2%|▏         | 116/5070 [00:45<31:17,  2.64it/s]
  2%|▏         | 117/5070 [00:45<33:04,  2.50it/s]
  2%|▏         | 118/5070 [00:46<36:26,  2.26it/s]
  2%|▏         | 119/5070 [00:47<42:31,  1.94it/s]
  2%|▏         | 120/5070 [00:47<37:20,  2.21it/s]
  2%|▏         | 121/5070 [00:47<35:21,  2.33it/s]
  2%|▏         | 122/5070 [00:48<34:00,  2.43it/s]
  2%|▏         | 123/5070 [00:48<32:01,  2.57it/s]
  2%|▏         | 124/5070 [00:48<31:24,  2.62it/s]
  2%|▏         | 125/5070 [00:49<29:14,  2.82it/s]
  2%|▏         | 126/5070 [00:49<31:42,  2.60it/s]
  3%|▎         | 127/5070 [00:50<36:51,  2.24it/s]
  3%|▎         | 128/5070 [00:50<35:05,  2.35it/s]
  3%|▎         | 129/5070 [00:50<32:31,  2.53it/s]
  3%|▎         | 130/5070 [00:51<33:29,  2.46it/s]
  3%|▎         | 131/5070 [00:51<34:54,  2.36it/s]
  3%|▎         | 132/5070 [00:52<32:01,  2.57it/s]
  3%|▎         | 133/5070 [00:52<30:11,  2.73it/s]
  3%|▎         | 134/5070 [00:52<27:55,  2.95it/s]
  3%|▎         | 135/5070 [00:53<27:47,  2.96it/s]
  3%|▎         | 136/5070 [00:53<34:07,  2.41it/s]
  3%|▎         | 137/5070 [00:54<36:48,  2.23it/s]
  3%|▎         | 138/5070 [00:54<34:08,  2.41it/s]
  3%|▎         | 139/5070 [00:54<32:28,  2.53it/s]
  3%|▎         | 140/5070 [00:55<32:32,  2.53it/s]
  3%|▎         | 141/5070 [00:55<34:10,  2.40it/s]
  3%|▎         | 142/5070 [00:56<33:01,  2.49it/s]
  3%|▎         | 143/5070 [00:56<34:43,  2.36it/s]
  3%|▎         | 144/5070 [00:56<32:40,  2.51it/s]
  3%|▎         | 145/5070 [00:57<34:42,  2.37it/s]
  3%|▎         | 146/5070 [00:57<33:20,  2.46it/s]
  3%|▎         | 147/5070 [00:58<38:03,  2.16it/s]
  3%|▎         | 148/5070 [00:58<38:10,  2.15it/s]
  3%|▎         | 149/5070 [00:59<39:25,  2.08it/s]
  3%|▎         | 150/5070 [00:59<37:15,  2.20it/s]
  3%|▎         | 151/5070 [01:00<35:10,  2.33it/s]
  3%|▎         | 152/5070 [01:00<35:57,  2.28it/s]
  3%|▎         | 153/5070 [01:00<32:39,  2.51it/s]
  3%|▎         | 154/5070 [01:01<31:50,  2.57it/s]
  3%|▎         | 155/5070 [01:01<30:24,  2.69it/s]
  3%|▎         | 156/5070 [01:01<29:07,  2.81it/s]
  3%|▎         | 157/5070 [01:02<27:52,  2.94it/s]
  3%|▎         | 158/5070 [01:02<26:45,  3.06it/s]
  3%|▎         | 159/5070 [01:02<27:09,  3.01it/s]
  3%|▎         | 160/5070 [01:03<28:05,  2.91it/s]
  3%|▎         | 161/5070 [01:03<28:55,  2.83it/s]
  3%|▎         | 162/5070 [01:04<32:05,  2.55it/s]
  3%|▎         | 163/5070 [01:04<32:59,  2.48it/s]
  3%|▎         | 164/5070 [01:04<33:29,  2.44it/s]
  3%|▎         | 165/5070 [01:05<38:00,  2.15it/s]
  3%|▎         | 166/5070 [01:05<37:31,  2.18it/s]
  3%|▎         | 167/5070 [01:06<34:33,  2.36it/s]
  3%|▎         | 168/5070 [01:06<30:48,  2.65it/s]
  3%|▎         | 169/5070 [01:06<29:41,  2.75it/s]
  3%|▎         | 170/5070 [01:07<28:36,  2.85it/s]
  3%|▎         | 171/5070 [01:07<29:44,  2.74it/s]
  3%|▎         | 172/5070 [01:07<29:24,  2.78it/s]
  3%|▎         | 173/5070 [01:08<30:28,  2.68it/s]
  3%|▎         | 174/5070 [01:08<31:08,  2.62it/s]
  3%|▎         | 175/5070 [01:09<30:05,  2.71it/s]
  3%|▎         | 176/5070 [01:09<31:47,  2.57it/s]
  3%|▎         | 177/5070 [01:09<30:57,  2.63it/s]
  4%|▎         | 178/5070 [01:10<30:51,  2.64it/s]
  4%|▎         | 179/5070 [01:10<32:25,  2.51it/s]
  4%|▎         | 180/5070 [01:11<32:40,  2.49it/s]
  4%|▎         | 181/5070 [01:11<30:53,  2.64it/s]
  4%|▎         | 182/5070 [01:11<29:51,  2.73it/s]
  4%|▎         | 183/5070 [01:12<30:08,  2.70it/s]
  4%|▎         | 184/5070 [01:12<29:08,  2.79it/s]
  4%|▎         | 185/5070 [01:12<27:38,  2.95it/s]
  4%|▎         | 186/5070 [01:13<29:08,  2.79it/s]
  4%|▎         | 187/5070 [01:13<30:50,  2.64it/s]
  4%|▎         | 188/5070 [01:13<29:46,  2.73it/s]
  4%|▎         | 189/5070 [01:14<27:02,  3.01it/s]
  4%|▎         | 190/5070 [01:14<32:28,  2.50it/s]
  4%|▍         | 191/5070 [01:15<33:35,  2.42it/s]
  4%|▍         | 192/5070 [01:15<33:34,  2.42it/s]
  4%|▍         | 193/5070 [01:16<39:01,  2.08it/s]
  4%|▍         | 194/5070 [01:16<38:27,  2.11it/s]
  4%|▍         | 195/5070 [01:17<35:38,  2.28it/s]
  4%|▍         | 196/5070 [01:17<33:20,  2.44it/s]
  4%|▍         | 197/5070 [01:17<31:14,  2.60it/s]
  4%|▍         | 198/5070 [01:18<32:57,  2.46it/s]
  4%|▍         | 199/5070 [01:18<30:26,  2.67it/s]
  4%|▍         | 200/5070 [01:19<34:45,  2.34it/s]
  4%|▍         | 201/5070 [01:19<31:49,  2.55it/s]
  4%|▍         | 202/5070 [01:19<32:15,  2.52it/s]
  4%|▍         | 203/5070 [01:20<36:02,  2.25it/s]
  4%|▍         | 204/5070 [01:20<36:30,  2.22it/s]
  4%|▍         | 205/5070 [01:21<39:03,  2.08it/s]
  4%|▍         | 206/5070 [01:21<36:32,  2.22it/s]
  4%|▍         | 207/5070 [01:22<34:56,  2.32it/s]
  4%|▍         | 208/5070 [01:22<34:18,  2.36it/s]
  4%|▍         | 209/5070 [01:22<32:08,  2.52it/s]
  4%|▍         | 210/5070 [01:23<31:17,  2.59it/s]
  4%|▍         | 211/5070 [01:23<29:35,  2.74it/s]
  4%|▍         | 212/5070 [01:23<33:09,  2.44it/s]
  4%|▍         | 213/5070 [01:24<32:48,  2.47it/s]
  4%|▍         | 214/5070 [01:24<36:04,  2.24it/s]
  4%|▍         | 215/5070 [01:25<33:15,  2.43it/s]
  4%|▍         | 216/5070 [01:25<32:15,  2.51it/s]
  4%|▍         | 217/5070 [01:26<32:45,  2.47it/s]
  4%|▍         | 218/5070 [01:26<32:25,  2.49it/s]
  4%|▍         | 219/5070 [01:26<34:45,  2.33it/s]
  4%|▍         | 220/5070 [01:27<37:32,  2.15it/s]
  4%|▍         | 221/5070 [01:27<38:50,  2.08it/s]
  4%|▍         | 222/5070 [01:28<34:44,  2.33it/s]
  4%|▍         | 223/5070 [01:28<34:06,  2.37it/s]
  4%|▍         | 224/5070 [01:29<34:41,  2.33it/s]
  4%|▍         | 225/5070 [01:29<34:43,  2.33it/s]
  4%|▍         | 226/5070 [01:30<34:36,  2.33it/s]
  4%|▍         | 227/5070 [01:30<35:31,  2.27it/s]
  4%|▍         | 228/5070 [01:30<35:10,  2.29it/s]
  5%|▍         | 229/5070 [01:31<31:33,  2.56it/s]
  5%|▍         | 230/5070 [01:31<29:53,  2.70it/s]
  5%|▍         | 231/5070 [01:31<27:03,  2.98it/s]
  5%|▍         | 232/5070 [01:32<27:04,  2.98it/s]
  5%|▍         | 233/5070 [01:32<28:05,  2.87it/s]
  5%|▍         | 234/5070 [01:32<27:50,  2.90it/s]
  5%|▍         | 235/5070 [01:33<29:12,  2.76it/s]
  5%|▍         | 236/5070 [01:33<29:10,  2.76it/s]
  5%|▍         | 237/5070 [01:33<29:14,  2.75it/s]
  5%|▍         | 238/5070 [01:34<28:12,  2.85it/s]
  5%|▍         | 239/5070 [01:34<28:52,  2.79it/s]
  5%|▍         | 240/5070 [01:35<28:58,  2.78it/s]
  5%|▍         | 241/5070 [01:35<30:33,  2.63it/s]
  5%|▍         | 242/5070 [01:35<27:48,  2.89it/s]
  5%|▍         | 243/5070 [01:36<27:25,  2.93it/s]
  5%|▍         | 244/5070 [01:36<26:48,  3.00it/s]
  5%|▍         | 245/5070 [01:36<29:15,  2.75it/s]
  5%|▍         | 246/5070 [01:37<27:55,  2.88it/s]
  5%|▍         | 247/5070 [01:37<28:18,  2.84it/s]
  5%|▍         | 248/5070 [01:37<30:50,  2.61it/s]
  5%|▍         | 249/5070 [01:38<31:34,  2.54it/s]
  5%|▍         | 250/5070 [01:38<30:21,  2.65it/s]
  5%|▍         | 251/5070 [01:39<29:52,  2.69it/s]
  5%|▍         | 252/5070 [01:39<32:46,  2.45it/s]
  5%|▍         | 253/5070 [01:39<31:44,  2.53it/s]
  5%|▌         | 254/5070 [01:40<31:13,  2.57it/s]
  5%|▌         | 255/5070 [01:40<31:48,  2.52it/s]
  5%|▌         | 256/5070 [01:41<31:07,  2.58it/s]
  5%|▌         | 257/5070 [01:41<31:06,  2.58it/s]
  5%|▌         | 258/5070 [01:41<30:15,  2.65it/s]
  5%|▌         | 259/5070 [01:42<29:15,  2.74it/s]
  5%|▌         | 260/5070 [01:42<31:19,  2.56it/s]
  5%|▌         | 261/5070 [01:43<36:08,  2.22it/s]
  5%|▌         | 262/5070 [01:43<33:22,  2.40it/s]
  5%|▌         | 263/5070 [01:43<32:11,  2.49it/s]
  5%|▌         | 264/5070 [01:44<29:48,  2.69it/s]
  5%|▌         | 265/5070 [01:44<28:33,  2.80it/s]
  5%|▌         | 266/5070 [01:44<28:52,  2.77it/s]
  5%|▌         | 267/5070 [01:45<32:16,  2.48it/s]
  5%|▌         | 268/5070 [01:45<33:51,  2.36it/s]
  5%|▌         | 269/5070 [01:46<33:57,  2.36it/s]
  5%|▌         | 270/5070 [01:46<31:25,  2.55it/s]
  5%|▌         | 271/5070 [01:46<31:23,  2.55it/s]
  5%|▌         | 272/5070 [01:47<32:46,  2.44it/s]
  5%|▌         | 273/5070 [01:47<32:44,  2.44it/s]
  5%|▌         | 274/5070 [01:48<33:13,  2.41it/s]
  5%|▌         | 275/5070 [01:48<32:30,  2.46it/s]
  5%|▌         | 276/5070 [01:49<32:22,  2.47it/s]
  5%|▌         | 277/5070 [01:49<31:44,  2.52it/s]
  5%|▌         | 278/5070 [01:49<31:56,  2.50it/s]
  6%|▌         | 279/5070 [01:50<31:59,  2.50it/s]
  6%|▌         | 280/5070 [01:50<30:52,  2.59it/s]
  6%|▌         | 281/5070 [01:50<29:44,  2.68it/s]
  6%|▌         | 282/5070 [01:51<31:30,  2.53it/s]
  6%|▌         | 283/5070 [01:51<33:37,  2.37it/s]
  6%|▌         | 284/5070 [01:52<32:58,  2.42it/s]
  6%|▌         | 285/5070 [01:52<32:31,  2.45it/s]
  6%|▌         | 286/5070 [01:53<31:45,  2.51it/s]
  6%|▌         | 287/5070 [01:53<30:22,  2.63it/s]
  6%|▌         | 288/5070 [01:53<28:53,  2.76it/s]
  6%|▌         | 289/5070 [01:54<29:05,  2.74it/s]
  6%|▌         | 290/5070 [01:54<29:51,  2.67it/s]
  6%|▌         | 291/5070 [01:54<29:46,  2.67it/s]
  6%|▌         | 292/5070 [01:55<28:56,  2.75it/s]
  6%|▌         | 293/5070 [01:55<27:36,  2.88it/s]
  6%|▌         | 294/5070 [01:55<27:28,  2.90it/s]
  6%|▌         | 295/5070 [01:56<29:02,  2.74it/s]
  6%|▌         | 296/5070 [01:56<34:38,  2.30it/s]
  6%|▌         | 297/5070 [01:57<33:12,  2.40it/s]
  6%|▌         | 298/5070 [01:57<30:01,  2.65it/s]
  6%|▌         | 299/5070 [01:58<35:52,  2.22it/s]
  6%|▌         | 300/5070 [01:58<32:11,  2.47it/s]
  6%|▌         | 301/5070 [01:58<30:00,  2.65it/s]
  6%|▌         | 302/5070 [01:59<32:15,  2.46it/s]
  6%|▌         | 303/5070 [01:59<36:24,  2.18it/s]
  6%|▌         | 304/5070 [02:00<32:07,  2.47it/s]
  6%|▌         | 305/5070 [02:00<33:30,  2.37it/s]
  6%|▌         | 306/5070 [02:00<33:06,  2.40it/s]
  6%|▌         | 307/5070 [02:01<29:43,  2.67it/s]
  6%|▌         | 308/5070 [02:01<34:19,  2.31it/s]
  6%|▌         | 309/5070 [02:02<31:41,  2.50it/s]
  6%|▌         | 310/5070 [02:02<32:56,  2.41it/s]
  6%|▌         | 311/5070 [02:02<29:29,  2.69it/s]
  6%|▌         | 312/5070 [02:03<33:51,  2.34it/s]
  6%|▌         | 313/5070 [02:03<31:25,  2.52it/s]
  6%|▌         | 314/5070 [02:04<33:19,  2.38it/s]
  6%|▌         | 315/5070 [02:04<32:28,  2.44it/s]
  6%|▌         | 316/5070 [02:04<31:52,  2.49it/s]
  6%|▋         | 317/5070 [02:05<30:42,  2.58it/s]
  6%|▋         | 318/5070 [02:05<29:19,  2.70it/s]
  6%|▋         | 319/5070 [02:05<28:40,  2.76it/s]
  6%|▋         | 320/5070 [02:06<27:29,  2.88it/s]
  6%|▋         | 321/5070 [02:06<29:14,  2.71it/s]
  6%|▋         | 322/5070 [02:07<28:11,  2.81it/s]
  6%|▋         | 323/5070 [02:07<27:18,  2.90it/s]
  6%|▋         | 324/5070 [02:07<29:24,  2.69it/s]
  6%|▋         | 325/5070 [02:08<28:57,  2.73it/s]
  6%|▋         | 326/5070 [02:08<28:15,  2.80it/s]
  6%|▋         | 327/5070 [02:08<27:16,  2.90it/s]
  6%|▋         | 328/5070 [02:09<28:10,  2.81it/s]
  6%|▋         | 329/5070 [02:09<25:59,  3.04it/s]
  7%|▋         | 330/5070 [02:09<26:56,  2.93it/s]
  7%|▋         | 331/5070 [02:10<41:18,  1.91it/s]
  7%|▋         | 332/5070 [02:11<37:36,  2.10it/s]
  7%|▋         | 333/5070 [02:11<35:17,  2.24it/s]
  7%|▋         | 334/5070 [02:11<30:48,  2.56it/s]
  7%|▋         | 335/5070 [02:12<32:01,  2.46it/s]
  7%|▋         | 336/5070 [02:12<30:39,  2.57it/s]
  7%|▋         | 337/5070 [02:12<31:04,  2.54it/s]
  7%|▋         | 338/5070 [02:13<31:22,  2.51it/s]
  7%|▋         | 339/5070 [02:13<29:31,  2.67it/s]
  7%|▋         | 340/5070 [02:14<32:09,  2.45it/s]
  7%|▋         | 341/5070 [02:14<32:00,  2.46it/s]
  7%|▋         | 342/5070 [02:14<31:12,  2.53it/s]
  7%|▋         | 343/5070 [02:15<31:17,  2.52it/s]
  7%|▋         | 344/5070 [02:15<31:32,  2.50it/s]
  7%|▋         | 345/5070 [02:16<34:21,  2.29it/s]
  7%|▋         | 346/5070 [02:16<31:52,  2.47it/s]
  7%|▋         | 347/5070 [02:16<30:24,  2.59it/s]
  7%|▋         | 348/5070 [02:17<29:56,  2.63it/s]
  7%|▋         | 349/5070 [02:17<32:38,  2.41it/s]
  7%|▋         | 350/5070 [02:18<31:33,  2.49it/s]
  7%|▋         | 351/5070 [02:18<29:10,  2.70it/s]
  7%|▋         | 352/5070 [02:18<29:07,  2.70it/s]
  7%|▋         | 353/5070 [02:19<29:14,  2.69it/s]
  7%|▋         | 354/5070 [02:19<31:25,  2.50it/s]
  7%|▋         | 355/5070 [02:19<29:31,  2.66it/s]
  7%|▋         | 356/5070 [02:20<27:26,  2.86it/s]
  7%|▋         | 357/5070 [02:20<25:35,  3.07it/s]
  7%|▋         | 358/5070 [02:20<27:36,  2.84it/s]
  7%|▋         | 359/5070 [02:21<28:06,  2.79it/s]
  7%|▋         | 360/5070 [02:21<28:07,  2.79it/s]
  7%|▋         | 361/5070 [02:21<26:24,  2.97it/s]
  7%|▋         | 362/5070 [02:22<28:17,  2.77it/s]
  7%|▋         | 363/5070 [02:22<29:25,  2.67it/s]
  7%|▋         | 364/5070 [02:23<26:55,  2.91it/s]
  7%|▋         | 365/5070 [02:23<32:24,  2.42it/s]
  7%|▋         | 366/5070 [02:24<31:13,  2.51it/s]
  7%|▋         | 367/5070 [02:24<29:52,  2.62it/s]
  7%|▋         | 368/5070 [02:24<28:41,  2.73it/s]
  7%|▋         | 369/5070 [02:25<27:59,  2.80it/s]
  7%|▋         | 370/5070 [02:25<28:45,  2.72it/s]
  7%|▋         | 371/5070 [02:25<31:32,  2.48it/s]
  7%|▋         | 372/5070 [02:26<28:45,  2.72it/s]
  7%|▋         | 373/5070 [02:26<28:16,  2.77it/s]
  7%|▋         | 374/5070 [02:26<29:23,  2.66it/s]
  7%|▋         | 375/5070 [02:27<32:17,  2.42it/s]
  7%|▋         | 376/5070 [02:27<30:05,  2.60it/s]
  7%|▋         | 377/5070 [02:28<32:03,  2.44it/s]
  7%|▋         | 378/5070 [02:28<31:05,  2.52it/s]
  7%|▋         | 379/5070 [02:28<30:05,  2.60it/s]
  7%|▋         | 380/5070 [02:29<32:30,  2.40it/s]
  8%|▊         | 381/5070 [02:29<31:32,  2.48it/s]
  8%|▊         | 382/5070 [02:30<34:09,  2.29it/s]
  8%|▊         | 383/5070 [02:30<33:53,  2.30it/s]
  8%|▊         | 384/5070 [02:31<32:36,  2.40it/s]
  8%|▊         | 385/5070 [02:31<32:58,  2.37it/s]
  8%|▊         | 386/5070 [02:32<33:49,  2.31it/s]
  8%|▊         | 387/5070 [02:32<34:36,  2.26it/s]
  8%|▊         | 388/5070 [02:32<30:40,  2.54it/s]
  8%|▊         | 389/5070 [02:33<33:50,  2.30it/s]
  8%|▊         | 390/5070 [02:33<34:57,  2.23it/s]
  8%|▊         | 391/5070 [02:34<31:32,  2.47it/s]
  8%|▊         | 392/5070 [02:34<29:57,  2.60it/s]
  8%|▊         | 393/5070 [02:34<28:23,  2.75it/s]
  8%|▊         | 394/5070 [02:35<28:33,  2.73it/s]
  8%|▊         | 395/5070 [02:35<29:05,  2.68it/s]
  8%|▊         | 396/5070 [02:35<29:46,  2.62it/s]
  8%|▊         | 397/5070 [02:36<27:19,  2.85it/s]
  8%|▊         | 398/5070 [02:36<28:19,  2.75it/s]
  8%|▊         | 399/5070 [02:36<28:51,  2.70it/s]
  8%|▊         | 400/5070 [02:37<28:11,  2.76it/s]
  8%|▊         | 401/5070 [02:37<29:33,  2.63it/s]
  8%|▊         | 402/5070 [02:38<31:49,  2.44it/s]
  8%|▊         | 403/5070 [02:38<31:43,  2.45it/s]
  8%|▊         | 404/5070 [02:39<31:30,  2.47it/s]
  8%|▊         | 405/5070 [02:39<29:03,  2.68it/s]
  8%|▊         | 406/5070 [02:39<29:03,  2.67it/s]
  8%|▊         | 407/5070 [02:40<30:11,  2.57it/s]
  8%|▊         | 408/5070 [02:40<30:14,  2.57it/s]
  8%|▊         | 409/5070 [02:41<33:16,  2.33it/s]
  8%|▊         | 410/5070 [02:41<30:50,  2.52it/s]
  8%|▊         | 411/5070 [02:41<30:26,  2.55it/s]
  8%|▊         | 412/5070 [02:42<30:50,  2.52it/s]
  8%|▊         | 413/5070 [02:42<33:27,  2.32it/s]
  8%|▊         | 414/5070 [02:43<32:54,  2.36it/s]
  8%|▊         | 415/5070 [02:43<30:43,  2.53it/s]
  8%|▊         | 416/5070 [02:43<27:35,  2.81it/s]
  8%|▊         | 417/5070 [02:43<27:18,  2.84it/s]
  8%|▊         | 418/5070 [02:44<28:26,  2.73it/s]
  8%|▊         | 419/5070 [02:44<28:17,  2.74it/s]
  8%|▊         | 420/5070 [02:45<27:58,  2.77it/s]
  8%|▊         | 421/5070 [02:45<26:19,  2.94it/s]
  8%|▊         | 422/5070 [02:45<24:50,  3.12it/s]
  8%|▊         | 423/5070 [02:46<26:30,  2.92it/s]
  8%|▊         | 424/5070 [02:46<26:57,  2.87it/s]
  8%|▊         | 425/5070 [02:46<29:17,  2.64it/s]
  8%|▊         | 426/5070 [02:47<29:36,  2.61it/s]
  8%|▊         | 427/5070 [02:47<30:52,  2.51it/s]
  8%|▊         | 428/5070 [02:48<29:51,  2.59it/s]
  8%|▊         | 429/5070 [02:48<28:39,  2.70it/s]
  8%|▊         | 430/5070 [02:48<28:36,  2.70it/s]
  9%|▊         | 431/5070 [02:49<28:34,  2.71it/s]
  9%|▊         | 432/5070 [02:49<28:04,  2.75it/s]
  9%|▊         | 433/5070 [02:49<27:33,  2.80it/s]
  9%|▊         | 434/5070 [02:50<26:46,  2.89it/s]
  9%|▊         | 435/5070 [02:50<30:11,  2.56it/s]
  9%|▊         | 436/5070 [02:50<27:57,  2.76it/s]
  9%|▊         | 437/5070 [02:51<27:25,  2.82it/s]
  9%|▊         | 438/5070 [02:51<28:27,  2.71it/s]
  9%|▊         | 439/5070 [02:52<29:18,  2.63it/s]
  9%|▊         | 440/5070 [02:52<29:07,  2.65it/s]
  9%|▊         | 441/5070 [02:52<29:23,  2.63it/s]
  9%|▊         | 442/5070 [02:53<28:21,  2.72it/s]
  9%|▊         | 443/5070 [02:53<26:46,  2.88it/s]
  9%|▉         | 444/5070 [02:53<27:21,  2.82it/s]
  9%|▉         | 445/5070 [02:54<27:35,  2.79it/s]
  9%|▉         | 446/5070 [02:54<31:53,  2.42it/s]
  9%|▉         | 447/5070 [02:55<29:38,  2.60it/s]
  9%|▉         | 448/5070 [02:55<32:06,  2.40it/s]
  9%|▉         | 449/5070 [02:55<30:18,  2.54it/s]
  9%|▉         | 450/5070 [02:56<30:30,  2.52it/s]
  9%|▉         | 451/5070 [02:56<35:58,  2.14it/s]
  9%|▉         | 452/5070 [02:57<31:53,  2.41it/s]
  9%|▉         | 453/5070 [02:57<30:16,  2.54it/s]
  9%|▉         | 454/5070 [02:58<32:03,  2.40it/s]
  9%|▉         | 455/5070 [02:58<32:14,  2.39it/s]
  9%|▉         | 456/5070 [02:58<30:19,  2.54it/s]
  9%|▉         | 457/5070 [02:59<29:53,  2.57it/s]
  9%|▉         | 458/5070 [02:59<29:59,  2.56it/s]
  9%|▉         | 459/5070 [02:59<29:36,  2.60it/s]
  9%|▉         | 460/5070 [03:00<32:30,  2.36it/s]
  9%|▉         | 461/5070 [03:00<31:48,  2.42it/s]
  9%|▉         | 462/5070 [03:01<30:53,  2.49it/s]
  9%|▉         | 463/5070 [03:01<29:15,  2.62it/s]
  9%|▉         | 464/5070 [03:01<26:44,  2.87it/s]
  9%|▉         | 465/5070 [03:02<28:36,  2.68it/s]
  9%|▉         | 466/5070 [03:02<28:37,  2.68it/s]
  9%|▉         | 467/5070 [03:02<27:06,  2.83it/s]
  9%|▉         | 468/5070 [03:03<26:37,  2.88it/s]
  9%|▉         | 469/5070 [03:03<26:46,  2.86it/s]
  9%|▉         | 470/5070 [03:03<27:13,  2.82it/s]
  9%|▉         | 471/5070 [03:04<27:24,  2.80it/s]
  9%|▉         | 472/5070 [03:04<27:36,  2.78it/s]
  9%|▉         | 473/5070 [03:05<26:50,  2.86it/s]
  9%|▉         | 474/5070 [03:05<28:13,  2.71it/s]
  9%|▉         | 475/5070 [03:05<28:49,  2.66it/s]
  9%|▉         | 476/5070 [03:06<29:09,  2.63it/s]
  9%|▉         | 477/5070 [03:06<27:36,  2.77it/s]
  9%|▉         | 478/5070 [03:07<29:31,  2.59it/s]
  9%|▉         | 479/5070 [03:07<27:13,  2.81it/s]
  9%|▉         | 480/5070 [03:07<27:09,  2.82it/s]
  9%|▉         | 481/5070 [03:07<24:54,  3.07it/s]
 10%|▉         | 482/5070 [03:08<28:23,  2.69it/s]
 10%|▉         | 483/5070 [03:08<27:57,  2.73it/s]
 10%|▉         | 484/5070 [03:08<25:38,  2.98it/s]
 10%|▉         | 485/5070 [03:09<25:07,  3.04it/s]
 10%|▉         | 486/5070 [03:09<26:52,  2.84it/s]
 10%|▉         | 487/5070 [03:10<29:34,  2.58it/s]
 10%|▉         | 488/5070 [03:10<30:52,  2.47it/s]
 10%|▉         | 489/5070 [03:10<28:52,  2.64it/s]
 10%|▉         | 490/5070 [03:11<28:11,  2.71it/s]
 10%|▉         | 491/5070 [03:11<28:24,  2.69it/s]
 10%|▉         | 492/5070 [03:12<30:32,  2.50it/s]
 10%|▉         | 493/5070 [03:12<30:43,  2.48it/s]
 10%|▉         | 494/5070 [03:12<29:25,  2.59it/s]
 10%|▉         | 495/5070 [03:13<26:43,  2.85it/s]
 10%|▉         | 496/5070 [03:13<27:07,  2.81it/s]
 10%|▉         | 497/5070 [03:13<29:10,  2.61it/s]
 10%|▉         | 498/5070 [03:14<30:41,  2.48it/s]
 10%|▉         | 499/5070 [03:14<29:46,  2.56it/s]
 10%|▉         | 500/5070 [03:15<29:14,  2.60it/s]
                                                  
 10%|▉         | 500/5070 [03:15<29:14,  2.60it/s]
 10%|▉         | 501/5070 [03:15<31:12,  2.44it/s]
 10%|▉         | 502/5070 [03:16<31:45,  2.40it/s]
 10%|▉         | 503/5070 [03:16<34:48,  2.19it/s]
 10%|▉         | 504/5070 [03:17<35:06,  2.17it/s]
 10%|▉         | 505/5070 [03:17<34:39,  2.20it/s]
 10%|▉         | 506/5070 [03:17<31:02,  2.45it/s]
 10%|█         | 507/5070 [03:18<27:23,  2.78it/s][INFO|trainer.py:811] 2024-09-09 12:53:28,785 >> The following columns in the evaluation set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: id, tokens, ner_tags. If id, tokens, ner_tags are not expected by `BertForTokenClassification.forward`,  you can safely ignore this message.
+[INFO|trainer.py:3819] 2024-09-09 12:53:28,787 >> 
+***** Running Evaluation *****
+[INFO|trainer.py:3821] 2024-09-09 12:53:28,787 >>   Num examples = 6946
+[INFO|trainer.py:3824] 2024-09-09 12:53:28,787 >>   Batch size = 8
+{'loss': 0.0183, 'grad_norm': 0.16175590455532074, 'learning_rate': 4.5069033530571994e-05, 'epoch': 0.99}
+
+
  0%|          | 0/869 [00:00<?, ?it/s]
+
  1%|          | 10/869 [00:00<00:09, 91.31it/s]
+
  2%|▏         | 20/869 [00:00<00:10, 79.28it/s]
+
  3%|▎         | 29/869 [00:00<00:10, 77.60it/s]
+
  4%|▍         | 37/869 [00:00<00:11, 74.43it/s]
+
  5%|▌         | 46/869 [00:00<00:10, 78.18it/s]
+
  6%|▋         | 55/869 [00:00<00:10, 80.86it/s]
+
  7%|▋         | 64/869 [00:00<00:10, 77.08it/s]
+
  8%|▊         | 72/869 [00:00<00:10, 76.17it/s]
+
  9%|▉         | 82/869 [00:01<00:09, 80.57it/s]
+
 11%|█         | 92/869 [00:01<00:09, 83.71it/s]
+
 12%|█▏        | 102/869 [00:01<00:09, 84.98it/s]
+
 13%|█▎        | 111/869 [00:01<00:09, 82.02it/s]
+
 14%|█▍        | 120/869 [00:01<00:09, 80.94it/s]
+
 15%|█▍        | 129/869 [00:01<00:09, 78.76it/s]
+
 16%|█▌        | 138/869 [00:01<00:08, 81.75it/s]
+
 17%|█▋        | 147/869 [00:01<00:09, 77.19it/s]
+
 18%|█▊        | 156/869 [00:01<00:09, 78.39it/s]
+
 19%|█▉        | 164/869 [00:02<00:08, 78.36it/s]
+
 20%|█▉        | 172/869 [00:02<00:09, 76.45it/s]
+
 21%|██        | 180/869 [00:02<00:09, 75.56it/s]
+
 22%|██▏       | 189/869 [00:02<00:08, 77.85it/s]
+
 23%|██▎       | 197/869 [00:02<00:08, 74.92it/s]
+
 24%|██▎       | 206/869 [00:02<00:08, 77.53it/s]
+
 25%|██▍       | 215/869 [00:02<00:08, 79.20it/s]
+
 26%|██▌       | 224/869 [00:02<00:08, 80.25it/s]
+
 27%|██▋       | 233/869 [00:02<00:08, 76.55it/s]
+
 28%|██▊       | 241/869 [00:03<00:08, 71.54it/s]
+
 29%|██▉       | 250/869 [00:03<00:08, 74.36it/s]
+
 30%|██▉       | 259/869 [00:03<00:07, 76.53it/s]
+
 31%|███       | 267/869 [00:03<00:07, 75.31it/s]
+
 32%|███▏      | 275/869 [00:03<00:07, 74.63it/s]
+
 33%|███▎      | 283/869 [00:03<00:07, 73.75it/s]
+
 33%|███▎      | 291/869 [00:03<00:07, 74.15it/s]
+
 34%|███▍      | 299/869 [00:03<00:07, 71.68it/s]
+
 35%|███▌      | 307/869 [00:03<00:07, 72.22it/s]
+
 36%|███▌      | 315/869 [00:04<00:07, 72.79it/s]
+
 37%|███▋      | 323/869 [00:04<00:07, 72.47it/s]
+
 38%|███▊      | 333/869 [00:04<00:06, 78.26it/s]
+
 39%|███▉      | 341/869 [00:04<00:06, 77.41it/s]
+
 40%|████      | 349/869 [00:04<00:07, 71.93it/s]
+
 41%|████      | 358/869 [00:04<00:06, 74.83it/s]
+
 42%|████▏     | 367/869 [00:04<00:06, 78.08it/s]
+
 43%|████▎     | 375/869 [00:04<00:06, 74.02it/s]
+
 44%|████▍     | 383/869 [00:04<00:06, 74.40it/s]
+
 45%|████▍     | 391/869 [00:05<00:06, 71.69it/s]
+
 46%|████▌     | 399/869 [00:05<00:06, 73.08it/s]
+
 47%|████▋     | 408/869 [00:05<00:06, 76.09it/s]
+
 48%|████▊     | 417/869 [00:05<00:05, 78.91it/s]
+
 49%|████▉     | 425/869 [00:05<00:05, 79.05it/s]
+
 50%|████▉     | 434/869 [00:05<00:05, 79.59it/s]
+
 51%|█████     | 442/869 [00:05<00:05, 76.14it/s]
+
 52%|█████▏    | 450/869 [00:05<00:05, 77.00it/s]
+
 53%|█████▎    | 459/869 [00:05<00:05, 77.04it/s]
+
 54%|█████▎    | 467/869 [00:06<00:05, 76.09it/s]
+
 55%|█████▍    | 477/869 [00:06<00:04, 81.01it/s]
+
 56%|█████▌    | 486/869 [00:06<00:04, 82.35it/s]
+
 57%|█████▋    | 495/869 [00:06<00:04, 76.40it/s]
+
 58%|█████▊    | 503/869 [00:06<00:04, 74.27it/s]
+
 59%|█████▉    | 511/869 [00:06<00:04, 75.21it/s]
+
 60%|█████▉    | 520/869 [00:06<00:04, 78.71it/s]
+
 61%|██████    | 528/869 [00:06<00:04, 72.74it/s]
+
 62%|██████▏   | 536/869 [00:06<00:04, 73.74it/s]
+
 63%|██████▎   | 544/869 [00:07<00:04, 70.86it/s]
+
 64%|██████▎   | 553/869 [00:07<00:04, 73.98it/s]
+
 65%|██████▍   | 561/869 [00:07<00:04, 75.50it/s]
+
 65%|██████▌   | 569/869 [00:07<00:04, 73.18it/s]
+
 67%|██████▋   | 578/869 [00:07<00:03, 75.98it/s]
+
 67%|██████▋   | 586/869 [00:07<00:03, 73.37it/s]
+
 68%|██████▊   | 594/869 [00:07<00:03, 74.99it/s]
+
 69%|██████▉   | 603/869 [00:07<00:03, 78.26it/s]
+
 70%|███████   | 611/869 [00:07<00:03, 77.04it/s]
+
 71%|███████   | 619/869 [00:08<00:03, 77.37it/s]
+
 72%|███████▏  | 627/869 [00:08<00:03, 75.86it/s]
+
 73%|███████▎  | 635/869 [00:08<00:03, 73.79it/s]
+
 74%|███████▍  | 644/869 [00:08<00:02, 77.27it/s]
+
 75%|███████▌  | 653/869 [00:08<00:02, 79.43it/s]
+
 76%|███████▌  | 661/869 [00:08<00:02, 76.75it/s]
+
 77%|███████▋  | 670/869 [00:08<00:02, 79.36it/s]
+
 78%|███████▊  | 679/869 [00:08<00:02, 82.14it/s]
+
 79%|███████▉  | 688/869 [00:09<00:02, 70.58it/s]
+
 80%|████████  | 696/869 [00:09<00:02, 72.95it/s]
+
 81%|████████  | 704/869 [00:09<00:02, 72.45it/s]
+
 82%|████████▏ | 713/869 [00:09<00:02, 76.22it/s]
+
 83%|████████▎ | 721/869 [00:09<00:01, 76.48it/s]
+
 84%|████████▍ | 730/869 [00:09<00:01, 78.48it/s]
+
 85%|████████▍ | 738/869 [00:09<00:01, 77.62it/s]
+
 86%|████████▌ | 746/869 [00:09<00:01, 78.12it/s]
+
 87%|████████▋ | 754/869 [00:09<00:01, 75.65it/s]
+
 88%|████████▊ | 763/869 [00:09<00:01, 78.80it/s]
+
 89%|████████▊ | 771/869 [00:10<00:01, 73.95it/s]
+
 90%|████████▉ | 779/869 [00:10<00:01, 65.06it/s]
+
 91%|█████████ | 788/869 [00:10<00:01, 69.56it/s]
+
 92%|█████████▏| 797/869 [00:10<00:00, 73.01it/s]
+
 93%|█████████▎| 805/869 [00:10<00:00, 73.73it/s]
+
 94%|█████████▎| 814/869 [00:10<00:00, 75.79it/s]
+
 95%|█████████▍| 822/869 [00:10<00:00, 75.50it/s]
+
 96%|█████████▌| 831/869 [00:10<00:00, 75.78it/s]
+
 97%|█████████▋| 840/869 [00:11<00:00, 77.68it/s]
+
 98%|█████████▊| 849/869 [00:11<00:00, 79.00it/s]
+
 99%|█████████▊| 857/869 [00:11<00:00, 79.09it/s]
+
                                                  
+
                                                 
 10%|█         | 507/5070 [03:33<27:23,  2.78it/s]
+
+
                                                 [INFO|trainer.py:3503] 2024-09-09 12:53:44,013 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-507
+[INFO|configuration_utils.py:472] 2024-09-09 12:53:44,015 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-507/config.json
+[INFO|modeling_utils.py:2799] 2024-09-09 12:53:44,902 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-507/model.safetensors
+[INFO|tokenization_utils_base.py:2684] 2024-09-09 12:53:44,903 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-507/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2693] 2024-09-09 12:53:44,903 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-507/special_tokens_map.json
+[INFO|tokenization_utils_base.py:2684] 2024-09-09 12:53:48,529 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2693] 2024-09-09 12:53:48,529 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+
 10%|█         | 508/5070 [03:38<7:59:31,  6.31s/it]
 10%|█         | 509/5070 [03:38<5:43:00,  4.51s/it]
 10%|█         | 510/5070 [03:39<4:09:49,  3.29s/it]
 10%|█         | 511/5070 [03:39<3:02:23,  2.40s/it]
 10%|█         | 512/5070 [03:39<2:14:43,  1.77s/it]
 10%|█         | 513/5070 [03:40<1:43:58,  1.37s/it]
 10%|█         | 514/5070 [03:40<1:22:41,  1.09s/it]
 10%|█         | 515/5070 [03:40<1:04:22,  1.18it/s]
 10%|█         | 516/5070 [03:41<52:24,  1.45it/s]  
 10%|█         | 517/5070 [03:41<48:49,  1.55it/s]
 10%|█         | 518/5070 [03:42<46:44,  1.62it/s]
 10%|█         | 519/5070 [03:42<39:54,  1.90it/s]
 10%|█         | 520/5070 [03:42<34:40,  2.19it/s]
 10%|█         | 521/5070 [03:43<32:48,  2.31it/s]
 10%|█         | 522/5070 [03:43<31:00,  2.44it/s]
 10%|█         | 523/5070 [03:43<27:25,  2.76it/s]
 10%|█         | 524/5070 [03:44<26:38,  2.84it/s]
 10%|█         | 525/5070 [03:44<27:04,  2.80it/s]
 10%|█         | 526/5070 [03:44<27:18,  2.77it/s]
 10%|█         | 527/5070 [03:45<27:06,  2.79it/s]
 10%|█         | 528/5070 [03:45<27:34,  2.75it/s]
 10%|█         | 529/5070 [03:45<25:33,  2.96it/s]
 10%|█         | 530/5070 [03:46<27:32,  2.75it/s]
 10%|█         | 531/5070 [03:46<28:24,  2.66it/s]
 10%|█         | 532/5070 [03:47<26:56,  2.81it/s]
 11%|█         | 533/5070 [03:47<26:50,  2.82it/s]
 11%|█         | 534/5070 [03:47<25:43,  2.94it/s]
 11%|█         | 535/5070 [03:48<27:07,  2.79it/s]
 11%|█         | 536/5070 [03:48<27:33,  2.74it/s]
 11%|█         | 537/5070 [03:48<29:37,  2.55it/s]
 11%|█         | 538/5070 [03:49<32:00,  2.36it/s]
 11%|█         | 539/5070 [03:49<29:10,  2.59it/s]
 11%|█         | 540/5070 [03:50<28:23,  2.66it/s]
 11%|█         | 541/5070 [03:50<28:24,  2.66it/s]
 11%|█         | 542/5070 [03:50<29:45,  2.54it/s]
 11%|█         | 543/5070 [03:51<32:20,  2.33it/s]
 11%|█         | 544/5070 [03:51<32:47,  2.30it/s]
 11%|█         | 545/5070 [03:52<32:17,  2.34it/s]
 11%|█         | 546/5070 [03:52<29:43,  2.54it/s]
 11%|█         | 547/5070 [03:52<29:53,  2.52it/s]
 11%|█         | 548/5070 [03:53<28:05,  2.68it/s]
 11%|█         | 549/5070 [03:53<27:40,  2.72it/s]
 11%|█         | 550/5070 [03:53<25:17,  2.98it/s]
 11%|█         | 551/5070 [03:54<26:11,  2.87it/s]
 11%|█         | 552/5070 [03:54<26:47,  2.81it/s]
 11%|█         | 553/5070 [03:55<27:54,  2.70it/s]
 11%|█         | 554/5070 [03:55<31:30,  2.39it/s]
 11%|█         | 555/5070 [03:55<31:08,  2.42it/s]
 11%|█         | 556/5070 [03:56<28:54,  2.60it/s]
 11%|█         | 557/5070 [03:56<28:31,  2.64it/s]
 11%|█         | 558/5070 [03:56<27:29,  2.74it/s]
 11%|█         | 559/5070 [03:57<30:01,  2.50it/s]
 11%|█         | 560/5070 [03:57<28:51,  2.60it/s]
 11%|█         | 561/5070 [03:58<27:48,  2.70it/s]
 11%|█         | 562/5070 [03:58<27:04,  2.78it/s]
 11%|█         | 563/5070 [03:58<28:37,  2.62it/s]
 11%|█         | 564/5070 [03:59<32:25,  2.32it/s]
 11%|█         | 565/5070 [03:59<32:00,  2.35it/s]
 11%|█         | 566/5070 [04:00<32:54,  2.28it/s]
 11%|█         | 567/5070 [04:00<32:14,  2.33it/s]
 11%|█         | 568/5070 [04:01<31:07,  2.41it/s]
 11%|█         | 569/5070 [04:01<30:28,  2.46it/s]
 11%|█         | 570/5070 [04:01<28:51,  2.60it/s]
 11%|█▏        | 571/5070 [04:02<27:02,  2.77it/s]
 11%|█▏        | 572/5070 [04:02<27:49,  2.69it/s]
 11%|█▏        | 573/5070 [04:03<29:30,  2.54it/s]
 11%|█▏        | 574/5070 [04:03<29:06,  2.57it/s]
 11%|█▏        | 575/5070 [04:03<27:59,  2.68it/s]
 11%|█▏        | 576/5070 [04:04<27:40,  2.71it/s]
 11%|█▏        | 577/5070 [04:04<26:59,  2.78it/s]
 11%|█▏        | 578/5070 [04:04<27:13,  2.75it/s]
 11%|█▏        | 579/5070 [04:05<27:11,  2.75it/s]
 11%|█▏        | 580/5070 [04:05<27:55,  2.68it/s]
 11%|█▏        | 581/5070 [04:05<27:12,  2.75it/s]
 11%|█▏        | 582/5070 [04:06<25:46,  2.90it/s]
 11%|█▏        | 583/5070 [04:06<26:23,  2.83it/s]
 12%|█▏        | 584/5070 [04:06<26:58,  2.77it/s]
 12%|█▏        | 585/5070 [04:07<28:33,  2.62it/s]
 12%|█▏        | 586/5070 [04:07<28:31,  2.62it/s]
 12%|█▏        | 587/5070 [04:08<26:37,  2.81it/s]
 12%|█▏        | 588/5070 [04:08<26:51,  2.78it/s]
 12%|█▏        | 589/5070 [04:08<28:01,  2.66it/s]
 12%|█▏        | 590/5070 [04:09<31:48,  2.35it/s]
 12%|█▏        | 591/5070 [04:09<28:30,  2.62it/s]
 12%|█▏        | 592/5070 [04:10<29:37,  2.52it/s]
 12%|█▏        | 593/5070 [04:10<28:26,  2.62it/s]
 12%|█▏        | 594/5070 [04:10<28:30,  2.62it/s]
 12%|█▏        | 595/5070 [04:11<26:28,  2.82it/s]
 12%|█▏        | 596/5070 [04:11<24:56,  2.99it/s]
 12%|█▏        | 597/5070 [04:11<26:43,  2.79it/s]
 12%|█▏        | 598/5070 [04:12<26:47,  2.78it/s]
 12%|█▏        | 599/5070 [04:12<28:46,  2.59it/s]
 12%|█▏        | 600/5070 [04:12<28:04,  2.65it/s]
 12%|█▏        | 601/5070 [04:13<27:50,  2.68it/s]
 12%|█▏        | 602/5070 [04:13<28:36,  2.60it/s]
 12%|█▏        | 603/5070 [04:14<31:30,  2.36it/s]
 12%|█▏        | 604/5070 [04:14<30:04,  2.48it/s]
 12%|█▏        | 605/5070 [04:15<29:27,  2.53it/s]
 12%|█▏        | 606/5070 [04:15<27:32,  2.70it/s]
 12%|█▏        | 607/5070 [04:15<26:02,  2.86it/s]
 12%|█▏        | 608/5070 [04:15<24:33,  3.03it/s]
 12%|█▏        | 609/5070 [04:16<27:46,  2.68it/s]
 12%|█▏        | 610/5070 [04:16<27:02,  2.75it/s]
 12%|█▏        | 611/5070 [04:17<27:23,  2.71it/s]
 12%|█▏        | 612/5070 [04:17<26:46,  2.78it/s]
 12%|█▏        | 613/5070 [04:17<27:05,  2.74it/s]
 12%|█▏        | 614/5070 [04:18<27:24,  2.71it/s]
 12%|█▏        | 615/5070 [04:18<27:54,  2.66it/s]
 12%|█▏        | 616/5070 [04:18<28:24,  2.61it/s]
 12%|█▏        | 617/5070 [04:19<27:37,  2.69it/s]
 12%|█▏        | 618/5070 [04:19<27:37,  2.69it/s]
 12%|█▏        | 619/5070 [04:20<27:19,  2.71it/s]
 12%|█▏        | 620/5070 [04:20<32:19,  2.29it/s]
 12%|█▏        | 621/5070 [04:21<33:26,  2.22it/s]

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.967845659163988,
+    "total_flos": 4644619911314910.0,
+    "train_loss": 0.050868147861573,
+    "train_runtime": 855.1929,
+    "train_samples": 9929,
+    "train_samples_per_second": 116.102,
+    "train_steps_per_second": 1.812
+}

trainer_state.json

@@ -0,0 +1,183 @@
+{
+  "best_metric": 0.6946045049764275,
+  "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-1088",
+  "epoch": 9.967845659163988,
+  "eval_steps": 500,
+  "global_step": 1550,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9967845659163987,
+      "eval_accuracy": 0.9435978055118868,
+      "eval_f1": 0.593056643174106,
+      "eval_loss": 0.14849668741226196,
+      "eval_precision": 0.5668662674650699,
+      "eval_recall": 0.6217843459222769,
+      "eval_runtime": 5.8633,
+      "eval_samples_per_second": 429.618,
+      "eval_steps_per_second": 53.724,
+      "step": 155
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9408546953704001,
+      "eval_f1": 0.6299060919817,
+      "eval_loss": 0.16094118356704712,
+      "eval_precision": 0.5623387790197765,
+      "eval_recall": 0.715927750410509,
+      "eval_runtime": 5.9155,
+      "eval_samples_per_second": 425.831,
+      "eval_steps_per_second": 53.25,
+      "step": 311
+    },
+    {
+      "epoch": 2.996784565916399,
+      "eval_accuracy": 0.9486669447207161,
+      "eval_f1": 0.6676790685902303,
+      "eval_loss": 0.1634686440229416,
+      "eval_precision": 0.6209981167608286,
+      "eval_recall": 0.7219485495347564,
+      "eval_runtime": 5.9009,
+      "eval_samples_per_second": 426.884,
+      "eval_steps_per_second": 53.382,
+      "step": 466
+    },
+    {
+      "epoch": 3.215434083601286,
+      "grad_norm": 0.9288749098777771,
+      "learning_rate": 3.387096774193548e-05,
+      "loss": 0.1246,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9492604831723828,
+      "eval_f1": 0.6711919630735812,
+      "eval_loss": 0.20466655492782593,
+      "eval_precision": 0.665948275862069,
+      "eval_recall": 0.6765188834154351,
+      "eval_runtime": 5.9155,
+      "eval_samples_per_second": 425.831,
+      "eval_steps_per_second": 53.25,
+      "step": 622
+    },
+    {
+      "epoch": 4.996784565916399,
+      "eval_accuracy": 0.9479771567904007,
+      "eval_f1": 0.6827731092436975,
+      "eval_loss": 0.2133806049823761,
+      "eval_precision": 0.6562342251388188,
+      "eval_recall": 0.7115489874110563,
+      "eval_runtime": 5.8759,
+      "eval_samples_per_second": 428.701,
+      "eval_steps_per_second": 53.609,
+      "step": 777
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.949388815810581,
+      "eval_f1": 0.6795913020696882,
+      "eval_loss": 0.2258971482515335,
+      "eval_precision": 0.6517587939698493,
+      "eval_recall": 0.7099069512862616,
+      "eval_runtime": 5.9106,
+      "eval_samples_per_second": 426.187,
+      "eval_steps_per_second": 53.294,
+      "step": 933
+    },
+    {
+      "epoch": 6.430868167202572,
+      "grad_norm": 0.18494442105293274,
+      "learning_rate": 1.774193548387097e-05,
+      "loss": 0.0242,
+      "step": 1000
+    },
+    {
+      "epoch": 6.996784565916399,
+      "eval_accuracy": 0.9496615226667522,
+      "eval_f1": 0.6946045049764275,
+      "eval_loss": 0.24502409994602203,
+      "eval_precision": 0.6659969864389754,
+      "eval_recall": 0.7257799671592775,
+      "eval_runtime": 5.8918,
+      "eval_samples_per_second": 427.542,
+      "eval_steps_per_second": 53.464,
+      "step": 1088
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9490679842150855,
+      "eval_f1": 0.6841015018125324,
+      "eval_loss": 0.26501980423927307,
+      "eval_precision": 0.6491400491400492,
+      "eval_recall": 0.7230432402846196,
+      "eval_runtime": 5.9184,
+      "eval_samples_per_second": 425.624,
+      "eval_steps_per_second": 53.224,
+      "step": 1244
+    },
+    {
+      "epoch": 8.996784565916398,
+      "eval_accuracy": 0.9497577721454009,
+      "eval_f1": 0.687797147385103,
+      "eval_loss": 0.27453720569610596,
+      "eval_precision": 0.664624808575804,
+      "eval_recall": 0.7126436781609196,
+      "eval_runtime": 5.9283,
+      "eval_samples_per_second": 424.913,
+      "eval_steps_per_second": 53.135,
+      "step": 1399
+    },
+    {
+      "epoch": 9.646302250803858,
+      "grad_norm": 0.35425594449043274,
+      "learning_rate": 1.6129032258064516e-06,
+      "loss": 0.0083,
+      "step": 1500
+    },
+    {
+      "epoch": 9.967845659163988,
+      "eval_accuracy": 0.950255061118419,
+      "eval_f1": 0.6896008403361344,
+      "eval_loss": 0.27744925022125244,
+      "eval_precision": 0.662796567390207,
+      "eval_recall": 0.7186644772851669,
+      "eval_runtime": 6.1493,
+      "eval_samples_per_second": 409.643,
+      "eval_steps_per_second": 51.226,
+      "step": 1550
+    },
+    {
+      "epoch": 9.967845659163988,
+      "step": 1550,
+      "total_flos": 4644619911314910.0,
+      "train_loss": 0.050868147861573,
+      "train_runtime": 855.1929,
+      "train_samples_per_second": 116.102,
+      "train_steps_per_second": 1.812
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1550,
+  "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": 4644619911314910.0,
+  "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