Pushing fine-tuned model to Hugging Face Hub

README.md

@@ -0,0 +1,48 @@
+
+---
+language:
+- pt
+- en
+tags:
+- aes
+datasets:
+- kamel-usp/aes_enem_dataset
+base_model: ricardoz/BERTugues-base-portuguese-cased
+metrics:
+- accuracy
+- qwk
+library_name: transformers
+model-index:
+  - name: BERTugues-base-portuguese-cased-encoder_classification-C4-essay_only
+    results:
+      - task:
+          type: text-classification
+          name: Automated Essay Score
+        dataset:
+          name: Automated Essay Score ENEM Dataset
+          type: kamel-usp/aes_enem_dataset
+          config: JBCS2025
+          split: test
+        metrics:
+          - name: Macro F1
+            type: f1
+            value: 0.2885197389992787
+          - name: QWK
+            type: qwk
+            value: 0.5408745247148289
+          - name: Weighted Macro F1
+            type: f1
+            value: 0.5051079377027337
+---
+# Model ID: BERTugues-base-portuguese-cased-encoder_classification-C4-essay_only
+## Results
+|                  |   test_data |
+|:-----------------|------------:|
+| eval_accuracy    |  0.492754   |
+| eval_RMSE        | 31.2076     |
+| eval_QWK         |  0.540875   |
+| eval_Macro_F1    |  0.28852    |
+| eval_Weighted_F1 |  0.505108   |
+| eval_Micro_F1    |  0.492754   |
+| eval_HDIV        |  0.00724638 |
+        

config.json

@@ -0,0 +1,40 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": 0,
+    "1": 40,
+    "2": 80,
+    "3": 120,
+    "4": 160,
+    "5": 200
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "40": 1,
+    "80": 2,
+    "120": 3,
+    "160": 4,
+    "200": 5
+  },
+  "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": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

emissions.csv

@@ -0,0 +1,2 @@
+timestamp,project_name,run_id,experiment_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
+2025-07-09T17:08:23,jbcs2025,c0944ce8-a1c4-4f61-b7c1-e8c230270aae,BERTugues-base-portuguese-cased-encoder_classification-C4-essay_only,124.09483157697832,0.00258094138718514,2.0798137637054887e-05,54.6325,144.3331460987135,58.0,0.0014930500536145782,0.007276071376407955,0.0019587412501549505,0.010727862680177487,Romania,ROU,gorj county,,,Linux-5.15.0-143-generic-x86_64-with-glibc2.35,3.12.11,3.0.2,36,Intel(R) Xeon(R) Gold 6248R CPU @ 3.00GHz,1,1 x NVIDIA RTX A6000,23.2904,45.0489,393.6063117980957,machine,N,1.0

evaluation_results.csv

@@ -0,0 +1,4 @@
+eval_loss,eval_model_preparation_time,eval_accuracy,eval_RMSE,eval_QWK,eval_HDIV,eval_Macro_F1,eval_Micro_F1,eval_Weighted_F1,eval_TP_0,eval_TN_0,eval_FP_0,eval_FN_0,eval_TP_1,eval_TN_1,eval_FP_1,eval_FN_1,eval_TP_2,eval_TN_2,eval_FP_2,eval_FN_2,eval_TP_3,eval_TN_3,eval_FP_3,eval_FN_3,eval_TP_4,eval_TN_4,eval_FP_4,eval_FN_4,eval_TP_5,eval_TN_5,eval_FP_5,eval_FN_5,eval_runtime,eval_samples_per_second,eval_steps_per_second,epoch,reference,timestamp,id
+1.7812554836273193,0.0022,0.3181818181818182,49.11335065052284,0.014999250037498024,0.06060606060606055,0.10120481927710842,0.3181818181818182,0.1840087623220153,0,125,6,1,0,132,0,0,0,120,8,4,0,68,0,64,42,8,76,6,0,117,0,15,0.7413,178.059,12.14,-1,validation_before_training,2025-07-09 17:06:28,BERTugues-base-portuguese-cased-encoder_classification-C4-essay_only
+1.7043002843856812,0.0022,0.5,32.47376563543955,0.5530126109294722,0.0,0.3471042547949657,0.5,0.5155880326753562,0,131,0,1,0,132,0,0,2,116,12,2,31,53,15,33,24,62,22,24,9,100,17,6,0.3934,335.544,22.878,16.0,validation_after_training,2025-07-09 17:06:28,BERTugues-base-portuguese-cased-encoder_classification-C4-essay_only
+1.6317094564437866,0.0022,0.4927536231884058,31.20757990421976,0.5408745247148289,0.007246376811594235,0.2885197389992787,0.4927536231884058,0.5051079377027337,0,137,0,1,0,137,0,1,7,106,23,2,41,41,21,35,17,75,17,29,3,124,9,2,0.3914,352.571,22.994,16.0,test_results,2025-07-09 17:06:28,BERTugues-base-portuguese-cased-encoder_classification-C4-essay_only

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09640891f9f0ce6d2d580776c853cbf8333f13b21f5c618680c639fb6204ca84
+size 437970952

run_experiment.log

@@ -0,0 +1,417 @@
+[2025-07-09 17:06:16,012][__main__][INFO] - cache_dir: /tmp/
+dataset:
+  name: kamel-usp/aes_enem_dataset
+  split: JBCS2025
+training_params:
+  seed: 42
+  num_train_epochs: 20
+  logging_steps: 100
+  metric_for_best_model: QWK
+  bf16: true
+bootstrap:
+  enabled: true
+  n_bootstrap: 10000
+  bootstrap_seed: 42
+  metrics:
+  - QWK
+  - Macro_F1
+  - Weighted_F1
+post_training_results:
+  model_path: /workspace/jbcs2025/outputs/2025-03-24/20-42-59
+experiments:
+  model:
+    name: ricardoz/BERTugues-base-portuguese-cased
+    type: encoder_classification
+    num_labels: 6
+    output_dir: ./results/
+    logging_dir: ./logs/
+    best_model_dir: ./results/best_model
+  tokenizer:
+    name: ricardoz/BERTugues-base-portuguese-cased
+  dataset:
+    grade_index: 3
+    use_full_context: false
+  training_params:
+    weight_decay: 0.01
+    warmup_ratio: 0.1
+    learning_rate: 5.0e-05
+    train_batch_size: 16
+    eval_batch_size: 16
+    gradient_accumulation_steps: 1
+    gradient_checkpointing: false
+
+[2025-07-09 17:06:19,861][__main__][INFO] - GPU 0: NVIDIA RTX A6000 | TDP ≈ 300 W
+[2025-07-09 17:06:19,861][__main__][INFO] - Starting the Fine Tuning training process.
+[2025-07-09 17:06:24,826][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--ricardoz--BERTugues-base-portuguese-cased/snapshots/76022866e209716d673e144cc9186f7b20830967/config.json
+[2025-07-09 17:06:24,827][transformers.configuration_utils][INFO] - Model config BertConfig {
+  "architectures": [
+    "BertForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}
+
+[2025-07-09 17:06:25,030][transformers.models.auto.tokenization_auto][INFO] - Could not locate the tokenizer configuration file, will try to use the model config instead.
+[2025-07-09 17:06:25,241][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--ricardoz--BERTugues-base-portuguese-cased/snapshots/76022866e209716d673e144cc9186f7b20830967/config.json
+[2025-07-09 17:06:25,242][transformers.configuration_utils][INFO] - Model config BertConfig {
+  "architectures": [
+    "BertForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}
+
+[2025-07-09 17:06:25,880][transformers.tokenization_utils_base][INFO] - loading file vocab.txt from cache at /tmp/models--ricardoz--BERTugues-base-portuguese-cased/snapshots/76022866e209716d673e144cc9186f7b20830967/vocab.txt
+[2025-07-09 17:06:25,880][transformers.tokenization_utils_base][INFO] - loading file tokenizer.json from cache at None
+[2025-07-09 17:06:25,880][transformers.tokenization_utils_base][INFO] - loading file added_tokens.json from cache at None
+[2025-07-09 17:06:25,880][transformers.tokenization_utils_base][INFO] - loading file special_tokens_map.json from cache at None
+[2025-07-09 17:06:25,880][transformers.tokenization_utils_base][INFO] - loading file tokenizer_config.json from cache at None
+[2025-07-09 17:06:25,880][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None
+[2025-07-09 17:06:25,880][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--ricardoz--BERTugues-base-portuguese-cased/snapshots/76022866e209716d673e144cc9186f7b20830967/config.json
+[2025-07-09 17:06:25,881][transformers.configuration_utils][INFO] - Model config BertConfig {
+  "architectures": [
+    "BertForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}
+
+[2025-07-09 17:06:25,912][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--ricardoz--BERTugues-base-portuguese-cased/snapshots/76022866e209716d673e144cc9186f7b20830967/config.json
+[2025-07-09 17:06:25,913][transformers.configuration_utils][INFO] - Model config BertConfig {
+  "architectures": [
+    "BertForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}
+
+[2025-07-09 17:06:25,933][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: True; Use Full Context: False
+[2025-07-09 17:06:26,599][__main__][INFO] - 
+Token statistics for 'train' split:
+[2025-07-09 17:06:26,599][__main__][INFO] -   Total examples: 500
+[2025-07-09 17:06:26,599][__main__][INFO] -   Min tokens: 512
+[2025-07-09 17:06:26,599][__main__][INFO] -   Max tokens: 512
+[2025-07-09 17:06:26,599][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-09 17:06:26,599][__main__][INFO] -   Std tokens: 0.00
+[2025-07-09 17:06:26,696][__main__][INFO] - 
+Token statistics for 'validation' split:
+[2025-07-09 17:06:26,696][__main__][INFO] -   Total examples: 132
+[2025-07-09 17:06:26,696][__main__][INFO] -   Min tokens: 512
+[2025-07-09 17:06:26,696][__main__][INFO] -   Max tokens: 512
+[2025-07-09 17:06:26,696][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-09 17:06:26,696][__main__][INFO] -   Std tokens: 0.00
+[2025-07-09 17:06:26,798][__main__][INFO] - 
+Token statistics for 'test' split:
+[2025-07-09 17:06:26,798][__main__][INFO] -   Total examples: 138
+[2025-07-09 17:06:26,798][__main__][INFO] -   Min tokens: 512
+[2025-07-09 17:06:26,798][__main__][INFO] -   Max tokens: 512
+[2025-07-09 17:06:26,798][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-09 17:06:26,798][__main__][INFO] -   Std tokens: 0.00
+[2025-07-09 17:06:26,798][__main__][INFO] - If token statistics are the same (max, avg, min) keep in mind that this is due to batched tokenization and padding.
+[2025-07-09 17:06:26,798][__main__][INFO] - Model max length: 512. If it is the same as stats, then there is a high chance that sequences are being truncated.
+[2025-07-09 17:06:27,018][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--ricardoz--BERTugues-base-portuguese-cased/snapshots/76022866e209716d673e144cc9186f7b20830967/config.json
+[2025-07-09 17:06:27,018][transformers.configuration_utils][INFO] - Model config BertConfig {
+  "architectures": [
+    "BertForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": 0,
+    "1": 40,
+    "2": 80,
+    "3": 120,
+    "4": 160,
+    "5": 200
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "40": 1,
+    "80": 2,
+    "120": 3,
+    "160": 4,
+    "200": 5
+  },
+  "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": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}
+
+[2025-07-09 17:06:27,214][transformers.modeling_utils][INFO] - loading weights file model.safetensors from cache at /tmp/models--ricardoz--BERTugues-base-portuguese-cased/snapshots/76022866e209716d673e144cc9186f7b20830967/model.safetensors
+[2025-07-09 17:06:27,215][transformers.modeling_utils][INFO] - Will use torch_dtype=torch.float32 as defined in model's config object
+[2025-07-09 17:06:27,215][transformers.modeling_utils][INFO] - Instantiating BertForSequenceClassification model under default dtype torch.float32.
+[2025-07-09 17:06:28,002][transformers.modeling_utils][INFO] - Some weights of the model checkpoint at ricardoz/BERTugues-base-portuguese-cased were not used when initializing BertForSequenceClassification: ['cls.predictions.bias', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.dense.weight', 'cls.seq_relationship.bias', 'cls.seq_relationship.weight']
+- This IS expected if you are initializing BertForSequenceClassification 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 BertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
+[2025-07-09 17:06:28,002][transformers.modeling_utils][WARNING] - Some weights of BertForSequenceClassification were not initialized from the model checkpoint at ricardoz/BERTugues-base-portuguese-cased 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.
+[2025-07-09 17:06:28,008][transformers.training_args][INFO] - PyTorch: setting up devices
+[2025-07-09 17:06:28,033][__main__][INFO] - Total steps: 620. Number of warmup steps: 62
+[2025-07-09 17:06:28,041][transformers.trainer][INFO] - You have loaded a model on multiple GPUs. `is_model_parallel` attribute will be force-set to `True` to avoid any unexpected behavior such as device placement mismatching.
+[2025-07-09 17:06:28,063][transformers.trainer][INFO] - Using auto half precision backend
+[2025-07-09 17:06:28,065][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:06:28,070][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:06:28,071][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:06:28,071][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:06:29,180][transformers.trainer][INFO] - The following columns in the Training set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:06:29,190][transformers.trainer][INFO] - ***** Running training *****
+[2025-07-09 17:06:29,190][transformers.trainer][INFO] -   Num examples = 500
+[2025-07-09 17:06:29,190][transformers.trainer][INFO] -   Num Epochs = 20
+[2025-07-09 17:06:29,190][transformers.trainer][INFO] -   Instantaneous batch size per device = 16
+[2025-07-09 17:06:29,190][transformers.trainer][INFO] -   Total train batch size (w. parallel, distributed & accumulation) = 16
+[2025-07-09 17:06:29,190][transformers.trainer][INFO] -   Gradient Accumulation steps = 1
+[2025-07-09 17:06:29,190][transformers.trainer][INFO] -   Total optimization steps = 640
+[2025-07-09 17:06:29,190][transformers.trainer][INFO] -   Number of trainable parameters = 109,486,854
+[2025-07-09 17:06:34,013][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:06:34,016][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:06:34,016][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:06:34,016][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:06:34,411][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-32
+[2025-07-09 17:06:34,413][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-32/config.json
+[2025-07-09 17:06:35,388][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-32/model.safetensors
+[2025-07-09 17:06:41,012][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:06:41,014][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:06:41,015][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:06:41,015][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:06:41,409][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-64
+[2025-07-09 17:06:41,411][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-64/config.json
+[2025-07-09 17:06:42,414][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-64/model.safetensors
+[2025-07-09 17:06:43,902][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-32] due to args.save_total_limit
+[2025-07-09 17:06:48,508][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:06:48,511][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:06:48,512][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:06:48,512][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:06:48,905][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-96
+[2025-07-09 17:06:48,906][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-96/config.json
+[2025-07-09 17:06:49,840][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-96/model.safetensors
+[2025-07-09 17:06:50,703][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-64] due to args.save_total_limit
+[2025-07-09 17:06:55,362][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:06:55,365][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:06:55,365][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:06:55,365][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:06:55,757][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-128
+[2025-07-09 17:06:55,759][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-128/config.json
+[2025-07-09 17:06:56,597][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-128/model.safetensors
+[2025-07-09 17:07:01,972][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:07:01,975][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:07:01,975][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:07:01,975][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:07:02,367][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-160
+[2025-07-09 17:07:02,368][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-160/config.json
+[2025-07-09 17:07:03,428][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-160/model.safetensors
+[2025-07-09 17:07:04,269][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-128] due to args.save_total_limit
+[2025-07-09 17:07:08,895][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:07:08,897][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:07:08,898][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:07:08,898][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:07:09,288][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-192
+[2025-07-09 17:07:09,289][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-192/config.json
+[2025-07-09 17:07:10,206][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-192/model.safetensors
+[2025-07-09 17:07:11,160][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-160] due to args.save_total_limit
+[2025-07-09 17:07:15,856][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:07:15,859][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:07:15,859][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:07:15,859][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:07:16,282][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-224
+[2025-07-09 17:07:16,283][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-224/config.json
+[2025-07-09 17:07:17,131][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-224/model.safetensors
+[2025-07-09 17:07:18,022][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-192] due to args.save_total_limit
+[2025-07-09 17:07:22,789][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:07:22,792][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:07:22,792][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:07:22,792][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:07:23,201][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-256
+[2025-07-09 17:07:23,203][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-256/config.json
+[2025-07-09 17:07:24,424][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-256/model.safetensors
+[2025-07-09 17:07:25,309][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-96] due to args.save_total_limit
+[2025-07-09 17:07:25,432][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-224] due to args.save_total_limit
+[2025-07-09 17:07:30,129][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:07:30,131][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:07:30,131][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:07:30,131][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:07:30,520][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-288
+[2025-07-09 17:07:30,521][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-288/config.json
+[2025-07-09 17:07:31,349][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-288/model.safetensors
+[2025-07-09 17:07:36,863][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:07:36,866][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:07:36,866][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:07:36,866][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:07:37,257][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-320
+[2025-07-09 17:07:37,258][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-320/config.json
+[2025-07-09 17:07:38,110][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-320/model.safetensors
+[2025-07-09 17:07:38,960][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-256] due to args.save_total_limit
+[2025-07-09 17:07:39,067][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-288] due to args.save_total_limit
+[2025-07-09 17:07:43,736][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:07:43,739][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:07:43,739][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:07:43,739][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:07:44,147][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-352
+[2025-07-09 17:07:44,148][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-352/config.json
+[2025-07-09 17:07:45,170][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-352/model.safetensors
+[2025-07-09 17:07:46,159][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-320] due to args.save_total_limit
+[2025-07-09 17:07:50,840][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:07:50,843][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:07:50,843][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:07:50,843][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:07:51,241][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-384
+[2025-07-09 17:07:51,242][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-384/config.json
+[2025-07-09 17:07:52,176][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-384/model.safetensors
+[2025-07-09 17:07:57,717][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:07:57,720][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:07:57,720][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:07:57,720][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:07:58,119][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-416
+[2025-07-09 17:07:58,121][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-416/config.json
+[2025-07-09 17:07:59,069][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-416/model.safetensors
+[2025-07-09 17:08:00,007][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-384] due to args.save_total_limit
+[2025-07-09 17:08:04,702][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:08:04,705][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:08:04,706][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:08:04,706][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:08:05,096][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-448
+[2025-07-09 17:08:05,097][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-448/config.json
+[2025-07-09 17:08:05,906][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-448/model.safetensors
+[2025-07-09 17:08:06,837][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-416] due to args.save_total_limit
+[2025-07-09 17:08:11,545][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:08:11,548][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:08:11,548][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:08:11,548][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:08:11,937][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-480
+[2025-07-09 17:08:11,938][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-480/config.json
+[2025-07-09 17:08:12,811][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-480/model.safetensors
+[2025-07-09 17:08:13,705][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-448] due to args.save_total_limit
+[2025-07-09 17:08:18,361][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:08:18,363][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:08:18,364][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:08:18,364][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:08:18,754][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-512
+[2025-07-09 17:08:18,756][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-512/config.json
+[2025-07-09 17:08:19,574][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-512/model.safetensors
+[2025-07-09 17:08:20,476][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-480] due to args.save_total_limit
+[2025-07-09 17:08:20,590][transformers.trainer][INFO] - 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+[2025-07-09 17:08:20,590][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-352 (score: 0.5530126109294722).
+[2025-07-09 17:08:20,826][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-512] due to args.save_total_limit
+[2025-07-09 17:08:20,953][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:08:20,957][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:08:20,957][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:08:20,957][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:08:21,357][__main__][INFO] - Training completed successfully.
+[2025-07-09 17:08:21,357][__main__][INFO] - Running on Test
+[2025-07-09 17:08:21,357][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:08:21,359][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:08:21,359][transformers.trainer][INFO] -   Num examples = 138
+[2025-07-09 17:08:21,359][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:08:21,755][__main__][INFO] - Test metrics: {'eval_loss': 1.6317094564437866, 'eval_model_preparation_time': 0.0022, 'eval_accuracy': 0.4927536231884058, 'eval_RMSE': 31.20757990421976, 'eval_QWK': 0.5408745247148289, 'eval_HDIV': 0.007246376811594235, 'eval_Macro_F1': 0.2885197389992787, 'eval_Micro_F1': 0.4927536231884058, 'eval_Weighted_F1': 0.5051079377027337, 'eval_TP_0': 0, 'eval_TN_0': 137, 'eval_FP_0': 0, 'eval_FN_0': 1, 'eval_TP_1': 0, 'eval_TN_1': 137, 'eval_FP_1': 0, 'eval_FN_1': 1, 'eval_TP_2': 7, 'eval_TN_2': 106, 'eval_FP_2': 23, 'eval_FN_2': 2, 'eval_TP_3': 41, 'eval_TN_3': 41, 'eval_FP_3': 21, 'eval_FN_3': 35, 'eval_TP_4': 17, 'eval_TN_4': 75, 'eval_FP_4': 17, 'eval_FN_4': 29, 'eval_TP_5': 3, 'eval_TN_5': 124, 'eval_FP_5': 9, 'eval_FN_5': 2, 'eval_runtime': 0.3914, 'eval_samples_per_second': 352.571, 'eval_steps_per_second': 22.994, 'epoch': 16.0}
+[2025-07-09 17:08:21,755][transformers.trainer][INFO] - Saving model checkpoint to ./results/best_model
+[2025-07-09 17:08:21,757][transformers.configuration_utils][INFO] - Configuration saved in ./results/best_model/config.json
+[2025-07-09 17:08:22,927][transformers.modeling_utils][INFO] - Model weights saved in ./results/best_model/model.safetensors
+[2025-07-09 17:08:22,929][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/best_model/tokenizer_config.json
+[2025-07-09 17:08:22,929][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/best_model/special_tokens_map.json
+[2025-07-09 17:08:22,941][__main__][INFO] - Model and tokenizer saved to ./results/best_model
+[2025-07-09 17:08:22,945][__main__][INFO] - Fine Tuning Finished.
+[2025-07-09 17:08:23,454][__main__][INFO] - Total emissions: 0.0026 kg CO2eq

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e17d2cf5818eeb3796caceeb049dff425aa1ed7693c852da5dfcbebeafdcac86
+size 5777