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-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: 0.2949925820893562
+          - name: QWK
+            type: qwk
+            value: 0.4965296316070473
+          - name: Weighted Macro F1
+            type: f1
+            value: 0.5487262828076291
+---
+# Model ID: bert-base-multilingual-cased-encoder_classification-C4-essay_only
+## Results
+|                  |   test_data |
+|:-----------------|------------:|
+| eval_accuracy    |  0.536232   |
+| eval_RMSE        | 30.8338     |
+| eval_QWK         |  0.49653    |
+| eval_Macro_F1    |  0.294993   |
+| eval_Weighted_F1 |  0.548726   |
+| eval_Micro_F1    |  0.536232   |
+| 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
+2025-07-09T17:18:11,jbcs2025,f7043fb1-83d9-4f39-bc50-37d83ab1dd5a,bert-base-multilingual-cased-encoder_classification-C4-essay_only,92.52555080497405,0.0017463849133527085,1.8874623259836084e-05,41.0,109.55187753175237,58.0,0.0010732017221398305,0.004728838783067069,0.0014569300511196423,0.007258970556326542,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
+1.7804791927337646,0.0021,0.30303030303030304,42.78204097869841,0.1050646551724137,0.015151515151515138,0.144,0.30303030303030304,0.19515151515151513,0,131,0,1,0,132,0,0,0,128,0,4,0,68,0,64,34,16,68,14,6,93,24,9,0.6355,207.699,14.161,-1,validation_before_training,2025-07-09 17:16:48,bert-base-multilingual-cased-encoder_classification-C4-essay_only
+1.272457480430603,0.0021,0.5378787878787878,30.15113445777636,0.5589021564783461,0.007575757575757569,0.33328870666331967,0.5378787878787878,0.5431462985642552,0,131,0,1,0,132,0,0,0,122,6,4,34,52,16,30,27,57,27,21,10,105,12,5,0.3963,333.044,22.708,9.0,validation_after_training,2025-07-09 17:16:48,bert-base-multilingual-cased-encoder_classification-C4-essay_only
+1.3231467008590698,0.0021,0.5362318840579711,30.833822949500753,0.49652963160704733,0.007246376811594235,0.29499258208935625,0.5362318840579711,0.5487262828076291,0,137,0,1,0,137,0,1,5,112,17,4,44,42,20,32,23,71,21,23,2,127,6,3,0.3847,358.675,23.392,9.0,test_results,2025-07-09 17:16:48,bert-base-multilingual-cased-encoder_classification-C4-essay_only

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41792349f09db4e47ded8c1f9f5e6a93eff3a7c4c194eef8179085a8117109de
+size 711455760

run_experiment.log

@@ -0,0 +1,351 @@
+[2025-07-09 17:16:35,620][__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: 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 17:16:39,482][__main__][INFO] - GPU 0: NVIDIA RTX A6000 | TDP ≈ 300 W
+[2025-07-09 17:16:39,482][__main__][INFO] - Starting the Fine Tuning training process.
+[2025-07-09 17:16:45,186][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 17:16:45,187][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 17:16:45,391][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 17:16:45,392][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 17:16:46,066][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 17:16:46,067][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 17:16:46,067][transformers.tokenization_utils_base][INFO] - loading file added_tokens.json from cache at None
+[2025-07-09 17:16:46,067][transformers.tokenization_utils_base][INFO] - loading file special_tokens_map.json from cache at None
+[2025-07-09 17:16:46,067][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 17:16:46,067][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None
+[2025-07-09 17:16:46,067][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 17:16:46,068][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 17:16:46,311][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: True; Use Full Context: False
+[2025-07-09 17:16:47,007][__main__][INFO] - 
+Token statistics for 'train' split:
+[2025-07-09 17:16:47,008][__main__][INFO] -   Total examples: 500
+[2025-07-09 17:16:47,008][__main__][INFO] -   Min tokens: 512
+[2025-07-09 17:16:47,008][__main__][INFO] -   Max tokens: 512
+[2025-07-09 17:16:47,008][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-09 17:16:47,008][__main__][INFO] -   Std tokens: 0.00
+[2025-07-09 17:16:47,103][__main__][INFO] - 
+Token statistics for 'validation' split:
+[2025-07-09 17:16:47,103][__main__][INFO] -   Total examples: 132
+[2025-07-09 17:16:47,103][__main__][INFO] -   Min tokens: 512
+[2025-07-09 17:16:47,103][__main__][INFO] -   Max tokens: 512
+[2025-07-09 17:16:47,103][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-09 17:16:47,103][__main__][INFO] -   Std tokens: 0.00
+[2025-07-09 17:16:47,203][__main__][INFO] - 
+Token statistics for 'test' split:
+[2025-07-09 17:16:47,203][__main__][INFO] -   Total examples: 138
+[2025-07-09 17:16:47,203][__main__][INFO] -   Min tokens: 512
+[2025-07-09 17:16:47,203][__main__][INFO] -   Max tokens: 512
+[2025-07-09 17:16:47,203][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-09 17:16:47,203][__main__][INFO] -   Std tokens: 0.00
+[2025-07-09 17:16:47,204][__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 17:16:47,204][__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 17:16:47,419][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 17:16:47,420][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 17:16:47,598][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 17:16:47,605][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 17:16:47,605][transformers.modeling_utils][INFO] - Instantiating BertForSequenceClassification model under default dtype torch.float32.
+[2025-07-09 17:16:47,773][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 17:16:48,508][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 17:16:48,508][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 17:16:48,514][transformers.training_args][INFO] - PyTorch: setting up devices
+[2025-07-09 17:16:48,577][__main__][INFO] - Total steps: 620. Number of warmup steps: 62
+[2025-07-09 17:16:48,585][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 17:16:48,610][transformers.trainer][INFO] - Using auto half precision backend
+[2025-07-09 17:16:48,612][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:16:48,618][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:16:48,618][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:16:48,618][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:16:49,574][transformers.trainer][INFO] - The following columns in the Training set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:16:49,583][transformers.trainer][INFO] - ***** Running training *****
+[2025-07-09 17:16:49,584][transformers.trainer][INFO] -   Num examples = 500
+[2025-07-09 17:16:49,584][transformers.trainer][INFO] -   Num Epochs = 20
+[2025-07-09 17:16:49,584][transformers.trainer][INFO] -   Instantaneous batch size per device = 16
+[2025-07-09 17:16:49,584][transformers.trainer][INFO] -   Total train batch size (w. parallel, distributed & accumulation) = 16
+[2025-07-09 17:16:49,584][transformers.trainer][INFO] -   Gradient Accumulation steps = 1
+[2025-07-09 17:16:49,584][transformers.trainer][INFO] -   Total optimization steps = 640
+[2025-07-09 17:16:49,584][transformers.trainer][INFO] -   Number of trainable parameters = 177,858,054
+[2025-07-09 17:16:54,598][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:16:54,600][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:16:54,600][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:16:54,600][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:16:54,990][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-32
+[2025-07-09 17:16:54,991][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-32/config.json
+[2025-07-09 17:16:56,420][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-32/model.safetensors
+[2025-07-09 17:17:02,794][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:17:02,796][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:17:02,796][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:17:02,796][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:17:03,180][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-64
+[2025-07-09 17:17:03,181][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-64/config.json
+[2025-07-09 17:17:04,499][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-64/model.safetensors
+[2025-07-09 17:17:06,619][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-32] due to args.save_total_limit
+[2025-07-09 17:17:11,599][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:17:11,601][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:17:11,601][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:17:11,601][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:17:11,990][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-96
+[2025-07-09 17:17:11,991][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-96/config.json
+[2025-07-09 17:17:13,340][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-96/model.safetensors
+[2025-07-09 17:17:15,231][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-64] due to args.save_total_limit
+[2025-07-09 17:17:20,161][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:17:20,164][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:17:20,164][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:17:20,164][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:17:20,551][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-128
+[2025-07-09 17:17:20,552][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-128/config.json
+[2025-07-09 17:17:22,038][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-128/model.safetensors
+[2025-07-09 17:17:24,130][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-96] due to args.save_total_limit
+[2025-07-09 17:17:29,080][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:17:29,082][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:17:29,083][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:17:29,083][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:17:29,474][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-160
+[2025-07-09 17:17:29,476][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-160/config.json
+[2025-07-09 17:17:30,903][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-160/model.safetensors
+[2025-07-09 17:17:37,833][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:17:37,835][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:17:37,835][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:17:37,835][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:17:38,223][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-192
+[2025-07-09 17:17:38,224][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-192/config.json
+[2025-07-09 17:17:39,538][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-192/model.safetensors
+[2025-07-09 17:17:41,709][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-160] due to args.save_total_limit
+[2025-07-09 17:17:46,670][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:17:46,672][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:17:46,673][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:17:46,673][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:17:47,064][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-224
+[2025-07-09 17:17:47,066][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-224/config.json
+[2025-07-09 17:17:48,459][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-224/model.safetensors
+[2025-07-09 17:17:50,566][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-192] due to args.save_total_limit
+[2025-07-09 17:17:55,524][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:17:55,527][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:17:55,527][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:17:55,527][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:17:55,918][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-256
+[2025-07-09 17:17:55,920][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-256/config.json
+[2025-07-09 17:17:57,309][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-256/model.safetensors
+[2025-07-09 17:17:59,425][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-224] due to args.save_total_limit
+[2025-07-09 17:18:04,384][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:18:04,387][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:18:04,387][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:18:04,387][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:18:04,777][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-288
+[2025-07-09 17:18:04,778][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-288/config.json
+[2025-07-09 17:18:06,261][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-288/model.safetensors
+[2025-07-09 17:18:08,369][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-256] due to args.save_total_limit
+[2025-07-09 17:18:08,507][transformers.trainer][INFO] - 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+[2025-07-09 17:18:08,507][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-128 (score: 0.5589021564783461).
+[2025-07-09 17:18:08,871][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-288] due to args.save_total_limit
+[2025-07-09 17:18:09,010][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:18:09,013][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:18:09,013][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:18:09,013][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:18:09,416][__main__][INFO] - Training completed successfully.
+[2025-07-09 17:18:09,416][__main__][INFO] - Running on Test
+[2025-07-09 17:18:09,417][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:18:09,419][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:18:09,419][transformers.trainer][INFO] -   Num examples = 138
+[2025-07-09 17:18:09,419][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:18:09,810][__main__][INFO] - Test metrics: {'eval_loss': 1.3231467008590698, 'eval_model_preparation_time': 0.0021, 'eval_accuracy': 0.5362318840579711, 'eval_RMSE': 30.833822949500753, 'eval_QWK': 0.49652963160704733, 'eval_HDIV': 0.007246376811594235, 'eval_Macro_F1': 0.29499258208935625, 'eval_Micro_F1': 0.5362318840579711, 'eval_Weighted_F1': 0.5487262828076291, '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': 5, 'eval_TN_2': 112, 'eval_FP_2': 17, 'eval_FN_2': 4, 'eval_TP_3': 44, 'eval_TN_3': 42, 'eval_FP_3': 20, 'eval_FN_3': 32, 'eval_TP_4': 23, 'eval_TN_4': 71, 'eval_FP_4': 21, 'eval_FN_4': 23, 'eval_TP_5': 2, 'eval_TN_5': 127, 'eval_FP_5': 6, 'eval_FN_5': 3, 'eval_runtime': 0.3847, 'eval_samples_per_second': 358.675, 'eval_steps_per_second': 23.392, 'epoch': 9.0}
+[2025-07-09 17:18:09,810][transformers.trainer][INFO] - Saving model checkpoint to ./results/best_model
+[2025-07-09 17:18:09,812][transformers.configuration_utils][INFO] - Configuration saved in ./results/best_model/config.json
+[2025-07-09 17:18:10,908][transformers.modeling_utils][INFO] - Model weights saved in ./results/best_model/model.safetensors
+[2025-07-09 17:18:10,910][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/best_model/tokenizer_config.json
+[2025-07-09 17:18:10,910][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/best_model/special_tokens_map.json
+[2025-07-09 17:18:10,975][__main__][INFO] - Model and tokenizer saved to ./results/best_model
+[2025-07-09 17:18:10,997][__main__][INFO] - Fine Tuning Finished.
+[2025-07-09 17:18:11,507][__main__][INFO] - Total emissions: 0.0017 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 sha256:4e8ca4052f2bbb8925daf9b957acae4217086431184dd4d46c4b83ad1d2370df
+size 5777