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: google-bert/bert-base-multilingual-cased
+metrics:
+- accuracy
+- qwk
+library_name: transformers
+model-index:
+  - name: bert-base-multilingual-cased-encoder_classification-C1-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: 0.3541902345442168
+          - name: QWK
+            type: qwk
+            value: 0.5069416088199266
+          - name: Weighted Macro F1
+            type: f1
+            value: 0.5913421963441202
+---
+# Model ID: bert-base-multilingual-cased-encoder_classification-C1-essay_only
+## Results
+|                  |   test_data |
+|:-----------------|------------:|
+| eval_accuracy    |  0.615942   |
+| eval_RMSE        | 28.4885     |
+| eval_QWK         |  0.506942   |
+| eval_Macro_F1    |  0.35419    |
+| eval_Weighted_F1 |  0.591342   |
+| eval_Micro_F1    |  0.615942   |
+| eval_HDIV        |  0.00724638 |
+        

config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "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,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

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
+2025-07-09T17:12:10,jbcs2025,97e50830-3795-415a-a8a3-7263fb59ab62,bert-base-multilingual-cased-encoder_classification-C1-essay_only,113.5037816510303,0.00223454427924116,1.968695885491562e-05,42.45363636363637,190.20433069788172,58.0,0.0013511013389485957,0.0061414413020379754,0.0017954963278564457,0.009288038968843018,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
+1.768218994140625,0.0021,0.42424242424242425,40.45199174779452,0.10542168674698782,0.015151515151515138,0.1779020979020979,0.42424242424242425,0.32896800169527446,0,131,0,1,0,132,0,0,0,125,0,7,0,93,0,39,48,15,54,15,8,88,22,14,0.5915,223.162,15.216,-1,validation_before_training,2025-07-09 17:10:25,bert-base-multilingual-cased-encoder_classification-C1-essay_only
+1.5438644886016846,0.0021,0.5151515151515151,32.47376563543955,0.49077687123093305,0.007575757575757569,0.3540979909948699,0.5151515151515151,0.5093727755026494,0,131,0,1,0,132,0,0,2,121,4,5,22,71,22,17,37,42,27,26,7,99,11,15,0.4008,329.37,22.457,12.0,validation_after_training,2025-07-09 17:10:25,bert-base-multilingual-cased-encoder_classification-C1-essay_only
+1.3753403425216675,0.0021,0.6159420289855072,28.48849246447679,0.5069416088199266,0.007246376811594235,0.35419023454421683,0.6159420289855072,0.5913421963441202,0,137,0,1,0,138,0,0,5,121,7,5,43,51,21,23,37,62,25,14,0,128,0,10,0.3866,356.924,23.278,12.0,test_results,2025-07-09 17:10:25,bert-base-multilingual-cased-encoder_classification-C1-essay_only

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92cc81f3d5f1b9ea6a1cee23e9b89eba64c3c6852c13763fb4d4e8d13d8beb3e
+size 711455760

run_experiment.log

@@ -0,0 +1,378 @@
+[2025-07-09 17:10:13,702][__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: google-bert/bert-base-multilingual-cased
+    type: encoder_classification
+    num_labels: 6
+    output_dir: ./results/
+    logging_dir: ./logs/
+    best_model_dir: ./results/best_model
+  tokenizer:
+    name: google-bert/bert-base-multilingual-cased
+  dataset:
+    grade_index: 0
+    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 17:10:17,535][__main__][INFO] - GPU 0: NVIDIA RTX A6000 | TDP ≈ 300 W
+[2025-07-09 17:10:17,535][__main__][INFO] - Starting the Fine Tuning training process.
+[2025-07-09 17:10:21,995][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--google-bert--bert-base-multilingual-cased/snapshots/3f076fdb1ab68d5b2880cb87a0886f315b8146f8/config.json
+[2025-07-09 17:10:21,996][transformers.configuration_utils][INFO] - Model config BertConfig {
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "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,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}
+
+[2025-07-09 17:10:22,196][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--google-bert--bert-base-multilingual-cased/snapshots/3f076fdb1ab68d5b2880cb87a0886f315b8146f8/config.json
+[2025-07-09 17:10:22,196][transformers.configuration_utils][INFO] - Model config BertConfig {
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "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,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}
+
+[2025-07-09 17:10:22,385][transformers.tokenization_utils_base][INFO] - loading file vocab.txt from cache at /tmp/models--google-bert--bert-base-multilingual-cased/snapshots/3f076fdb1ab68d5b2880cb87a0886f315b8146f8/vocab.txt
+[2025-07-09 17:10:22,386][transformers.tokenization_utils_base][INFO] - loading file tokenizer.json from cache at /tmp/models--google-bert--bert-base-multilingual-cased/snapshots/3f076fdb1ab68d5b2880cb87a0886f315b8146f8/tokenizer.json
+[2025-07-09 17:10:22,386][transformers.tokenization_utils_base][INFO] - loading file added_tokens.json from cache at None
+[2025-07-09 17:10:22,386][transformers.tokenization_utils_base][INFO] - loading file special_tokens_map.json from cache at None
+[2025-07-09 17:10:22,386][transformers.tokenization_utils_base][INFO] - loading file tokenizer_config.json from cache at /tmp/models--google-bert--bert-base-multilingual-cased/snapshots/3f076fdb1ab68d5b2880cb87a0886f315b8146f8/tokenizer_config.json
+[2025-07-09 17:10:22,386][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None
+[2025-07-09 17:10:22,386][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--google-bert--bert-base-multilingual-cased/snapshots/3f076fdb1ab68d5b2880cb87a0886f315b8146f8/config.json
+[2025-07-09 17:10:22,387][transformers.configuration_utils][INFO] - Model config BertConfig {
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "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,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}
+
+[2025-07-09 17:10:22,653][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: True; Use Full Context: False
+[2025-07-09 17:10:23,368][__main__][INFO] - 
+Token statistics for 'train' split:
+[2025-07-09 17:10:23,368][__main__][INFO] -   Total examples: 500
+[2025-07-09 17:10:23,368][__main__][INFO] -   Min tokens: 512
+[2025-07-09 17:10:23,368][__main__][INFO] -   Max tokens: 512
+[2025-07-09 17:10:23,368][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-09 17:10:23,368][__main__][INFO] -   Std tokens: 0.00
+[2025-07-09 17:10:23,468][__main__][INFO] - 
+Token statistics for 'validation' split:
+[2025-07-09 17:10:23,468][__main__][INFO] -   Total examples: 132
+[2025-07-09 17:10:23,468][__main__][INFO] -   Min tokens: 512
+[2025-07-09 17:10:23,468][__main__][INFO] -   Max tokens: 512
+[2025-07-09 17:10:23,468][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-09 17:10:23,468][__main__][INFO] -   Std tokens: 0.00
+[2025-07-09 17:10:23,575][__main__][INFO] - 
+Token statistics for 'test' split:
+[2025-07-09 17:10:23,575][__main__][INFO] -   Total examples: 138
+[2025-07-09 17:10:23,575][__main__][INFO] -   Min tokens: 512
+[2025-07-09 17:10:23,575][__main__][INFO] -   Max tokens: 512
+[2025-07-09 17:10:23,575][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-09 17:10:23,575][__main__][INFO] -   Std tokens: 0.00
+[2025-07-09 17:10:23,575][__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 17:10:23,575][__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 17:10:23,775][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--google-bert--bert-base-multilingual-cased/snapshots/3f076fdb1ab68d5b2880cb87a0886f315b8146f8/config.json
+[2025-07-09 17:10:23,776][transformers.configuration_utils][INFO] - Model config BertConfig {
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "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,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}
+
+[2025-07-09 17:10:23,957][transformers.modeling_utils][INFO] - loading weights file model.safetensors from cache at /tmp/models--google-bert--bert-base-multilingual-cased/snapshots/3f076fdb1ab68d5b2880cb87a0886f315b8146f8/model.safetensors
+[2025-07-09 17:10:23,965][transformers.modeling_utils][INFO] - Since the `torch_dtype` attribute can't be found in model's config object, will use torch_dtype={torch_dtype} as derived from model's weights
+[2025-07-09 17:10:23,965][transformers.modeling_utils][INFO] - Instantiating BertForSequenceClassification model under default dtype torch.float32.
+[2025-07-09 17:10:24,194][transformers.modeling_utils][INFO] - A pretrained model of type `BertForSequenceClassification` contains parameters that have been renamed internally (a few are listed below but more are present in the model):
+* `cls.predictions.transform.LayerNorm.beta` -> `cls.predictions.transform.LayerNorm.bias`
+* `cls.predictions.transform.LayerNorm.gamma` -> `cls.predictions.transform.LayerNorm.weight`
+If you are using a model from the Hub, consider submitting a PR to adjust these weights and help future users.
+[2025-07-09 17:10:25,084][transformers.modeling_utils][INFO] - Some weights of the model checkpoint at google-bert/bert-base-multilingual-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 17:10:25,084][transformers.modeling_utils][WARNING] - Some weights of BertForSequenceClassification were not initialized from the model checkpoint at google-bert/bert-base-multilingual-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 17:10:25,090][transformers.training_args][INFO] - PyTorch: setting up devices
+[2025-07-09 17:10:25,112][__main__][INFO] - Total steps: 620. Number of warmup steps: 62
+[2025-07-09 17:10:25,121][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 17:10:25,146][transformers.trainer][INFO] - Using auto half precision backend
+[2025-07-09 17:10:25,148][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text. If id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:10:25,153][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:10:25,153][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:10:25,153][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:10:26,049][transformers.trainer][INFO] - The following columns in the Training set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text. If id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:10:26,058][transformers.trainer][INFO] - ***** Running training *****
+[2025-07-09 17:10:26,058][transformers.trainer][INFO] -   Num examples = 500
+[2025-07-09 17:10:26,058][transformers.trainer][INFO] -   Num Epochs = 20
+[2025-07-09 17:10:26,058][transformers.trainer][INFO] -   Instantaneous batch size per device = 16
+[2025-07-09 17:10:26,058][transformers.trainer][INFO] -   Total train batch size (w. parallel, distributed & accumulation) = 16
+[2025-07-09 17:10:26,058][transformers.trainer][INFO] -   Gradient Accumulation steps = 1
+[2025-07-09 17:10:26,058][transformers.trainer][INFO] -   Total optimization steps = 640
+[2025-07-09 17:10:26,059][transformers.trainer][INFO] -   Number of trainable parameters = 177,858,054
+[2025-07-09 17:10:30,991][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text. If id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:10:30,993][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:10:30,993][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:10:30,993][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:10:31,380][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-32
+[2025-07-09 17:10:31,381][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-32/config.json
+[2025-07-09 17:10:32,662][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-32/model.safetensors
+[2025-07-09 17:10:39,168][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text. If id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:10:39,171][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:10:39,171][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:10:39,171][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:10:39,557][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-64
+[2025-07-09 17:10:39,559][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-64/config.json
+[2025-07-09 17:10:40,871][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-64/model.safetensors
+[2025-07-09 17:10:42,956][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-32] due to args.save_total_limit
+[2025-07-09 17:10:47,966][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text. If id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:10:47,969][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:10:47,969][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:10:47,969][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:10:48,364][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-96
+[2025-07-09 17:10:48,365][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-96/config.json
+[2025-07-09 17:10:50,370][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-96/model.safetensors
+[2025-07-09 17:10:52,138][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-64] due to args.save_total_limit
+[2025-07-09 17:10:57,123][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text. If id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:10:57,128][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:10:57,128][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:10:57,128][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:10:57,523][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-128
+[2025-07-09 17:10:57,525][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-128/config.json
+[2025-07-09 17:10:58,970][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-128/model.safetensors
+[2025-07-09 17:11:00,598][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-96] due to args.save_total_limit
+[2025-07-09 17:11:05,572][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text. If id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:11:05,575][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:11:05,575][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:11:05,575][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:11:05,962][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-160
+[2025-07-09 17:11:05,963][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-160/config.json
+[2025-07-09 17:11:07,174][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-160/model.safetensors
+[2025-07-09 17:11:13,628][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text. If id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:11:13,631][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:11:13,631][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:11:13,631][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:11:14,021][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-192
+[2025-07-09 17:11:14,022][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-192/config.json
+[2025-07-09 17:11:15,830][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-192/model.safetensors
+[2025-07-09 17:11:17,403][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-160] due to args.save_total_limit
+[2025-07-09 17:11:22,426][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text. If id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:11:22,429][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:11:22,429][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:11:22,429][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:11:22,816][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-224
+[2025-07-09 17:11:22,818][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-224/config.json
+[2025-07-09 17:11:24,074][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-224/model.safetensors
+[2025-07-09 17:11:25,720][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-128] due to args.save_total_limit
+[2025-07-09 17:11:25,913][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-192] due to args.save_total_limit
+[2025-07-09 17:11:30,963][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text. If id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:11:30,965][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:11:30,966][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:11:30,966][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:11:31,356][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-256
+[2025-07-09 17:11:31,357][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-256/config.json
+[2025-07-09 17:11:32,518][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-256/model.safetensors
+[2025-07-09 17:11:38,890][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text. If id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:11:38,893][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:11:38,893][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:11:38,893][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:11:39,286][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-288
+[2025-07-09 17:11:39,287][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-288/config.json
+[2025-07-09 17:11:40,416][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-288/model.safetensors
+[2025-07-09 17:11:42,013][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-256] due to args.save_total_limit
+[2025-07-09 17:11:47,014][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text. If id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:11:47,017][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:11:47,017][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:11:47,017][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:11:47,431][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-320
+[2025-07-09 17:11:47,433][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-320/config.json
+[2025-07-09 17:11:48,738][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-320/model.safetensors
+[2025-07-09 17:11:50,331][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-288] due to args.save_total_limit
+[2025-07-09 17:11:55,293][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text. If id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:11:55,296][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:11:55,296][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:11:55,296][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:11:55,683][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-352
+[2025-07-09 17:11:55,685][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-352/config.json
+[2025-07-09 17:11:56,871][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-352/model.safetensors
+[2025-07-09 17:11:58,761][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-320] due to args.save_total_limit
+[2025-07-09 17:12:03,735][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text. If id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:12:03,739][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:12:03,739][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:12:03,739][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:12:04,127][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-384
+[2025-07-09 17:12:04,129][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-384/config.json
+[2025-07-09 17:12:05,323][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-384/model.safetensors
+[2025-07-09 17:12:06,909][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-352] due to args.save_total_limit
+[2025-07-09 17:12:07,072][transformers.trainer][INFO] - 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+[2025-07-09 17:12:07,072][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-224 (score: 0.49077687123093305).
+[2025-07-09 17:12:07,502][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-10-13/results/checkpoint-384] due to args.save_total_limit
+[2025-07-09 17:12:07,671][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text. If id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:12:07,674][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:12:07,674][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:12:07,674][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:12:08,081][__main__][INFO] - Training completed successfully.
+[2025-07-09 17:12:08,082][__main__][INFO] - Running on Test
+[2025-07-09 17:12:08,082][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text. If id, reference, id_prompt, prompt, grades, essay_year, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:12:08,084][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:12:08,084][transformers.trainer][INFO] -   Num examples = 138
+[2025-07-09 17:12:08,084][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:12:08,476][__main__][INFO] - Test metrics: {'eval_loss': 1.3753403425216675, 'eval_model_preparation_time': 0.0021, 'eval_accuracy': 0.6159420289855072, 'eval_RMSE': 28.48849246447679, 'eval_QWK': 0.5069416088199266, 'eval_HDIV': 0.007246376811594235, 'eval_Macro_F1': 0.35419023454421683, 'eval_Micro_F1': 0.6159420289855072, 'eval_Weighted_F1': 0.5913421963441202, 'eval_TP_0': 0, 'eval_TN_0': 137, 'eval_FP_0': 0, 'eval_FN_0': 1, 'eval_TP_1': 0, 'eval_TN_1': 138, 'eval_FP_1': 0, 'eval_FN_1': 0, 'eval_TP_2': 5, 'eval_TN_2': 121, 'eval_FP_2': 7, 'eval_FN_2': 5, 'eval_TP_3': 43, 'eval_TN_3': 51, 'eval_FP_3': 21, 'eval_FN_3': 23, 'eval_TP_4': 37, 'eval_TN_4': 62, 'eval_FP_4': 25, 'eval_FN_4': 14, 'eval_TP_5': 0, 'eval_TN_5': 128, 'eval_FP_5': 0, 'eval_FN_5': 10, 'eval_runtime': 0.3866, 'eval_samples_per_second': 356.924, 'eval_steps_per_second': 23.278, 'epoch': 12.0}
+[2025-07-09 17:12:08,476][transformers.trainer][INFO] - Saving model checkpoint to ./results/best_model
+[2025-07-09 17:12:08,478][transformers.configuration_utils][INFO] - Configuration saved in ./results/best_model/config.json
+[2025-07-09 17:12:09,900][transformers.modeling_utils][INFO] - Model weights saved in ./results/best_model/model.safetensors
+[2025-07-09 17:12:09,902][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/best_model/tokenizer_config.json
+[2025-07-09 17:12:09,902][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/best_model/special_tokens_map.json
+[2025-07-09 17:12:09,993][__main__][INFO] - Model and tokenizer saved to ./results/best_model
+[2025-07-09 17:12:10,025][__main__][INFO] - Fine Tuning Finished.
+[2025-07-09 17:12:10,544][__main__][INFO] - Total emissions: 0.0022 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 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "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 sha256:89ca4cf42e2295e2bc738c7e06a8bae467bd78ec70dd3b2281b4616641a98930
+size 5777