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-C3-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: 0.2245231652826589
+          - name: QWK
+            type: qwk
+            value: 0.3586046018449793
+          - name: Weighted Macro F1
+            type: f1
+            value: 0.3210121894546771
+---
+# Model ID: bert-base-multilingual-cased-encoder_classification-C3-essay_only
+## Results
+|                  |   test_data |
+|:-----------------|------------:|
+| eval_accuracy    |   0.318841  |
+| eval_RMSE        |  55.2202    |
+| eval_QWK         |   0.358605  |
+| eval_Macro_F1    |   0.224523  |
+| eval_Weighted_F1 |   0.321012  |
+| eval_Micro_F1    |   0.318841  |
+| eval_HDIV        |   0.0869565 |
+        

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
+2025-07-09T17:16:25,jbcs2025,08774bae-90bc-487d-a94a-31fab5a1acd3,bert-base-multilingual-cased-encoder_classification-C3-essay_only,128.87568475597072,0.002477183599012129,1.9221497086147297e-05,47.09875,122.32799163750946,58.0,0.0015115457615074949,0.006749469010682851,0.0020355714330366594,0.010296586205227007,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
+1.796027660369873,0.0021,0.22727272727272727,67.23995925944722,0.08456046407853635,0.19696969696969702,0.09612058314801086,0.22727272727272727,0.12372801401711706,0,131,0,1,0,108,0,24,0,126,0,6,0,79,0,53,26,16,76,14,4,98,26,4,0.6133,215.236,14.675,-1,validation_before_training,2025-07-09 17:14:26,bert-base-multilingual-cased-encoder_classification-C3-essay_only
+1.781539797782898,0.0021,0.3409090909090909,50.572480239511265,0.43200913614487313,0.06818181818181823,0.25636222910216716,0.3409090909090909,0.32550520686743595,0,131,0,1,2,100,8,22,4,98,28,2,11,68,11,42,23,63,29,17,5,113,11,3,0.4169,316.605,21.587,13.0,validation_after_training,2025-07-09 17:14:26,bert-base-multilingual-cased-encoder_classification-C3-essay_only
+1.8821938037872314,0.0021,0.3188405797101449,55.22024413490799,0.35860460184497933,0.08695652173913049,0.22452316528265895,0.3188405797101449,0.3210121894546771,0,137,0,1,8,91,18,21,8,96,24,10,12,71,22,33,16,80,20,22,0,121,10,7,0.4153,332.255,21.669,13.0,test_results,2025-07-09 17:14:26,bert-base-multilingual-cased-encoder_classification-C3-essay_only

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c99a221910443740e4d949a46c7b824962e5a6a93f4c40f3b0152f2ef41147b
+size 711455760

run_experiment.log

@@ -0,0 +1,387 @@
+[2025-07-09 17:14:13,621][__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: 2
+    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 17:14:17,504][__main__][INFO] - GPU 0: NVIDIA RTX A6000 | TDP ≈ 300 W
+[2025-07-09 17:14:17,504][__main__][INFO] - Starting the Fine Tuning training process.
+[2025-07-09 17:14:23,069][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 17:14:23,070][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 17:14:23,265][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 17:14:23,265][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 17:14:23,456][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 17:14:23,456][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 17:14:23,456][transformers.tokenization_utils_base][INFO] - loading file added_tokens.json from cache at None
+[2025-07-09 17:14:23,456][transformers.tokenization_utils_base][INFO] - loading file special_tokens_map.json from cache at None
+[2025-07-09 17:14:23,456][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 17:14:23,456][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None
+[2025-07-09 17:14:23,456][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 17:14:23,457][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 17:14:23,736][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: True; Use Full Context: False
+[2025-07-09 17:14:24,512][__main__][INFO] - 
+Token statistics for 'train' split:
+[2025-07-09 17:14:24,512][__main__][INFO] -   Total examples: 500
+[2025-07-09 17:14:24,513][__main__][INFO] -   Min tokens: 512
+[2025-07-09 17:14:24,513][__main__][INFO] -   Max tokens: 512
+[2025-07-09 17:14:24,513][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-09 17:14:24,513][__main__][INFO] -   Std tokens: 0.00
+[2025-07-09 17:14:24,629][__main__][INFO] - 
+Token statistics for 'validation' split:
+[2025-07-09 17:14:24,630][__main__][INFO] -   Total examples: 132
+[2025-07-09 17:14:24,630][__main__][INFO] -   Min tokens: 512
+[2025-07-09 17:14:24,630][__main__][INFO] -   Max tokens: 512
+[2025-07-09 17:14:24,630][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-09 17:14:24,630][__main__][INFO] -   Std tokens: 0.00
+[2025-07-09 17:14:24,746][__main__][INFO] - 
+Token statistics for 'test' split:
+[2025-07-09 17:14:24,747][__main__][INFO] -   Total examples: 138
+[2025-07-09 17:14:24,747][__main__][INFO] -   Min tokens: 512
+[2025-07-09 17:14:24,747][__main__][INFO] -   Max tokens: 512
+[2025-07-09 17:14:24,747][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-09 17:14:24,747][__main__][INFO] -   Std tokens: 0.00
+[2025-07-09 17:14:24,747][__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 17:14:24,747][__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 17:14:24,973][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 17:14:24,974][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 17:14:25,166][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 17:14:25,174][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 17:14:25,175][transformers.modeling_utils][INFO] - Instantiating BertForSequenceClassification model under default dtype torch.float32.
+[2025-07-09 17:14:25,371][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 17:14:26,303][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 17:14:26,303][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 17:14:26,309][transformers.training_args][INFO] - PyTorch: setting up devices
+[2025-07-09 17:14:26,331][__main__][INFO] - Total steps: 620. Number of warmup steps: 62
+[2025-07-09 17:14:26,339][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 17:14:26,364][transformers.trainer][INFO] - Using auto half precision backend
+[2025-07-09 17:14:26,367][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:14:26,372][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:14:26,372][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:14:26,372][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:14:27,295][transformers.trainer][INFO] - The following columns in the Training set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:14:27,305][transformers.trainer][INFO] - ***** Running training *****
+[2025-07-09 17:14:27,305][transformers.trainer][INFO] -   Num examples = 500
+[2025-07-09 17:14:27,305][transformers.trainer][INFO] -   Num Epochs = 20
+[2025-07-09 17:14:27,305][transformers.trainer][INFO] -   Instantaneous batch size per device = 16
+[2025-07-09 17:14:27,305][transformers.trainer][INFO] -   Total train batch size (w. parallel, distributed & accumulation) = 16
+[2025-07-09 17:14:27,305][transformers.trainer][INFO] -   Gradient Accumulation steps = 1
+[2025-07-09 17:14:27,305][transformers.trainer][INFO] -   Total optimization steps = 640
+[2025-07-09 17:14:27,305][transformers.trainer][INFO] -   Number of trainable parameters = 177,858,054
+[2025-07-09 17:14:32,297][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:14:32,300][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:14:32,300][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:14:32,300][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:14:32,694][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-32
+[2025-07-09 17:14:32,695][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-32/config.json
+[2025-07-09 17:14:33,919][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-32/model.safetensors
+[2025-07-09 17:14:40,425][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:14:40,429][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:14:40,429][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:14:40,429][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:14:40,820][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-64
+[2025-07-09 17:14:40,821][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-64/config.json
+[2025-07-09 17:14:42,135][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-64/model.safetensors
+[2025-07-09 17:14:43,757][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-32] due to args.save_total_limit
+[2025-07-09 17:14:48,774][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:14:48,777][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:14:48,777][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:14:48,777][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:14:49,177][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-96
+[2025-07-09 17:14:49,179][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-96/config.json
+[2025-07-09 17:14:50,716][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-96/model.safetensors
+[2025-07-09 17:14:57,646][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:14:57,649][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:14:57,649][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:14:57,649][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:14:58,049][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-128
+[2025-07-09 17:14:58,050][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-128/config.json
+[2025-07-09 17:14:59,457][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-128/model.safetensors
+[2025-07-09 17:15:01,555][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-96] due to args.save_total_limit
+[2025-07-09 17:15:06,640][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:15:06,643][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:15:06,643][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:15:06,643][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:15:07,046][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-160
+[2025-07-09 17:15:07,048][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-160/config.json
+[2025-07-09 17:15:08,445][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-160/model.safetensors
+[2025-07-09 17:15:10,671][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-64] due to args.save_total_limit
+[2025-07-09 17:15:10,793][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-128] due to args.save_total_limit
+[2025-07-09 17:15:15,813][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:15:15,817][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:15:15,817][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:15:15,817][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:15:16,219][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-192
+[2025-07-09 17:15:16,221][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-192/config.json
+[2025-07-09 17:15:17,720][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-192/model.safetensors
+[2025-07-09 17:15:25,077][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:15:25,080][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:15:25,081][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:15:25,081][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:15:25,478][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-224
+[2025-07-09 17:15:25,479][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-224/config.json
+[2025-07-09 17:15:26,845][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-224/model.safetensors
+[2025-07-09 17:15:29,329][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-192] due to args.save_total_limit
+[2025-07-09 17:15:34,302][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:15:34,305][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:15:34,305][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:15:34,305][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:15:34,698][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-256
+[2025-07-09 17:15:34,699][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-256/config.json
+[2025-07-09 17:15:35,873][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-256/model.safetensors
+[2025-07-09 17:15:37,772][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-160] due to args.save_total_limit
+[2025-07-09 17:15:37,945][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-224] due to args.save_total_limit
+[2025-07-09 17:15:42,919][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:15:42,922][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:15:42,922][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:15:42,922][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:15:43,317][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-288
+[2025-07-09 17:15:43,319][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-288/config.json
+[2025-07-09 17:15:44,554][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-288/model.safetensors
+[2025-07-09 17:15:51,406][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:15:51,408][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:15:51,408][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:15:51,408][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:15:51,805][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-320
+[2025-07-09 17:15:51,806][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-320/config.json
+[2025-07-09 17:15:53,422][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-320/model.safetensors
+[2025-07-09 17:15:55,534][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-288] due to args.save_total_limit
+[2025-07-09 17:16:00,487][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:16:00,491][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:16:00,491][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:16:00,491][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:16:00,885][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-352
+[2025-07-09 17:16:00,886][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-352/config.json
+[2025-07-09 17:16:02,213][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-352/model.safetensors
+[2025-07-09 17:16:04,259][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-320] due to args.save_total_limit
+[2025-07-09 17:16:09,238][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:16:09,242][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:16:09,242][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:16:09,242][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:16:09,639][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-384
+[2025-07-09 17:16:09,641][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-384/config.json
+[2025-07-09 17:16:11,042][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-384/model.safetensors
+[2025-07-09 17:16:13,060][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-352] due to args.save_total_limit
+[2025-07-09 17:16:18,036][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:16:18,039][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:16:18,039][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:16:18,039][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:16:18,434][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-416
+[2025-07-09 17:16:18,435][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-416/config.json
+[2025-07-09 17:16:20,168][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-416/model.safetensors
+[2025-07-09 17:16:22,058][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-384] due to args.save_total_limit
+[2025-07-09 17:16:22,176][transformers.trainer][INFO] - 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+[2025-07-09 17:16:22,176][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-256 (score: 0.43200913614487313).
+[2025-07-09 17:16:22,534][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-416] due to args.save_total_limit
+[2025-07-09 17:16:22,692][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:16:22,695][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:16:22,695][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:16:22,695][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:16:23,118][__main__][INFO] - Training completed successfully.
+[2025-07-09 17:16:23,118][__main__][INFO] - Running on Test
+[2025-07-09 17:16:23,119][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:16:23,121][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:16:23,121][transformers.trainer][INFO] -   Num examples = 138
+[2025-07-09 17:16:23,121][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:16:23,542][__main__][INFO] - Test metrics: {'eval_loss': 1.8821938037872314, 'eval_model_preparation_time': 0.0021, 'eval_accuracy': 0.3188405797101449, 'eval_RMSE': 55.22024413490799, 'eval_QWK': 0.35860460184497933, 'eval_HDIV': 0.08695652173913049, 'eval_Macro_F1': 0.22452316528265895, 'eval_Micro_F1': 0.3188405797101449, 'eval_Weighted_F1': 0.3210121894546771, 'eval_TP_0': 0, 'eval_TN_0': 137, 'eval_FP_0': 0, 'eval_FN_0': 1, 'eval_TP_1': 8, 'eval_TN_1': 91, 'eval_FP_1': 18, 'eval_FN_1': 21, 'eval_TP_2': 8, 'eval_TN_2': 96, 'eval_FP_2': 24, 'eval_FN_2': 10, 'eval_TP_3': 12, 'eval_TN_3': 71, 'eval_FP_3': 22, 'eval_FN_3': 33, 'eval_TP_4': 16, 'eval_TN_4': 80, 'eval_FP_4': 20, 'eval_FN_4': 22, 'eval_TP_5': 0, 'eval_TN_5': 121, 'eval_FP_5': 10, 'eval_FN_5': 7, 'eval_runtime': 0.4153, 'eval_samples_per_second': 332.255, 'eval_steps_per_second': 21.669, 'epoch': 13.0}
+[2025-07-09 17:16:23,543][transformers.trainer][INFO] - Saving model checkpoint to ./results/best_model
+[2025-07-09 17:16:23,545][transformers.configuration_utils][INFO] - Configuration saved in ./results/best_model/config.json
+[2025-07-09 17:16:25,266][transformers.modeling_utils][INFO] - Model weights saved in ./results/best_model/model.safetensors
+[2025-07-09 17:16:25,268][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/best_model/tokenizer_config.json
+[2025-07-09 17:16:25,269][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/best_model/special_tokens_map.json
+[2025-07-09 17:16:25,342][__main__][INFO] - Model and tokenizer saved to ./results/best_model
+[2025-07-09 17:16:25,368][__main__][INFO] - Fine Tuning Finished.
+[2025-07-09 17:16:25,879][__main__][INFO] - Total emissions: 0.0025 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 sha256:39ac0ba33512fe2ae794238aca83bc4979e74cb71175b5481d987b702e4e8753
+size 5777