Pushing fine-tuned model to Hugging Face Hub

README.md

@@ -0,0 +1,48 @@
+
+---
+language:
+- pt
+- en
+tags:
+- aes
+datasets:
+- kamel-usp/aes_enem_dataset
+base_model: ricardoz/BERTugues-base-portuguese-cased
+metrics:
+- accuracy
+- qwk
+library_name: transformers
+model-index:
+  - name: BERTugues-base-portuguese-cased-encoder_classification-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: 0.3873376623376623
+          - name: QWK
+            type: qwk
+            value: 0.6139860139860139
+          - name: Weighted Macro F1
+            type: f1
+            value: 0.5620203065855239
+---
+# Model ID: BERTugues-base-portuguese-cased-encoder_classification-C1-essay_only
+## Results
+|                  |   test_data |
+|:-----------------|------------:|
+| eval_accuracy    |  0.543478   |
+| eval_RMSE        | 30.4555     |
+| eval_QWK         |  0.613986   |
+| eval_Macro_F1    |  0.387338   |
+| eval_Weighted_F1 |  0.56202    |
+| eval_Micro_F1    |  0.543478   |
+| eval_HDIV        |  0.00724638 |
+        

config.json

@@ -0,0 +1,40 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": 0,
+    "1": 40,
+    "2": 80,
+    "3": 120,
+    "4": 160,
+    "5": 200
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "40": 1,
+    "80": 2,
+    "120": 3,
+    "160": 4,
+    "200": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

emissions.csv

@@ -0,0 +1,2 @@
+timestamp,project_name,run_id,experiment_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
+2025-07-09T17:02:55,jbcs2025,95d1c6d6-6591-4a90-a0f8-7b597d9e768e,BERTugues-base-portuguese-cased-encoder_classification-C1-essay_only,76.78956367401406,0.0015437702652992163,2.010390724256238e-05,49.199999999999996,210.83072035434986,58.0,0.0009759866625364993,0.004228010604628629,0.0012127913891373382,0.006416788656302467,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
+1.7795836925506592,0.0025,0.4166666666666667,54.9379815626841,-0.17570467878094131,0.06818181818181823,0.12154696132596685,0.4166666666666667,0.2900552486187845,0,125,6,1,0,132,0,0,0,117,8,7,0,93,0,39,55,6,63,8,0,110,0,22,0.7633,172.929,11.791,-1,validation_before_training,2025-07-09 17:01:48,BERTugues-base-portuguese-cased-encoder_classification-C1-essay_only
+1.4637502431869507,0.0025,0.44696969696969696,37.335497772755005,0.5213772228528187,0.0,0.355808371275661,0.44696969696969696,0.4545482079360584,0,131,0,1,0,132,0,0,6,111,14,1,16,83,10,23,25,50,19,38,12,80,30,10,0.4211,313.471,21.373,9.0,validation_after_training,2025-07-09 17:01:48,BERTugues-base-portuguese-cased-encoder_classification-C1-essay_only
+1.247100830078125,0.0025,0.5434782608695652,30.45547950507524,0.6139860139860139,0.007246376811594235,0.38733766233766237,0.5434782608695652,0.5620203065855239,0,137,0,1,0,138,0,0,7,109,19,3,35,61,11,31,28,67,20,23,5,115,13,5,0.42,328.555,21.427,9.0,test_results,2025-07-09 17:01:48,BERTugues-base-portuguese-cased-encoder_classification-C1-essay_only

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64259312cfc1470926a6fc2d19809fe7f3812d38cf2fa96690278d9bb26ff5ae
+size 437970952

run_experiment.log

@@ -0,0 +1,354 @@
+[2025-07-09 17:01:35,568][__main__][INFO] - cache_dir: /tmp/
+dataset:
+  name: kamel-usp/aes_enem_dataset
+  split: JBCS2025
+training_params:
+  seed: 42
+  num_train_epochs: 20
+  logging_steps: 100
+  metric_for_best_model: QWK
+  bf16: true
+bootstrap:
+  enabled: true
+  n_bootstrap: 10000
+  bootstrap_seed: 42
+  metrics:
+  - QWK
+  - Macro_F1
+  - Weighted_F1
+post_training_results:
+  model_path: /workspace/jbcs2025/outputs/2025-03-24/20-42-59
+experiments:
+  model:
+    name: ricardoz/BERTugues-base-portuguese-cased
+    type: encoder_classification
+    num_labels: 6
+    output_dir: ./results/
+    logging_dir: ./logs/
+    best_model_dir: ./results/best_model
+  tokenizer:
+    name: ricardoz/BERTugues-base-portuguese-cased
+  dataset:
+    grade_index: 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 17:01:39,460][__main__][INFO] - GPU 0: NVIDIA RTX A6000 | TDP ≈ 300 W
+[2025-07-09 17:01:39,460][__main__][INFO] - Starting the Fine Tuning training process.
+[2025-07-09 17:01:44,526][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--ricardoz--BERTugues-base-portuguese-cased/snapshots/76022866e209716d673e144cc9186f7b20830967/config.json
+[2025-07-09 17:01:44,528][transformers.configuration_utils][INFO] - Model config BertConfig {
+  "architectures": [
+    "BertForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}
+
+[2025-07-09 17:01:44,746][transformers.models.auto.tokenization_auto][INFO] - Could not locate the tokenizer configuration file, will try to use the model config instead.
+[2025-07-09 17:01:44,949][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--ricardoz--BERTugues-base-portuguese-cased/snapshots/76022866e209716d673e144cc9186f7b20830967/config.json
+[2025-07-09 17:01:44,950][transformers.configuration_utils][INFO] - Model config BertConfig {
+  "architectures": [
+    "BertForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}
+
+[2025-07-09 17:01:45,587][transformers.tokenization_utils_base][INFO] - loading file vocab.txt from cache at /tmp/models--ricardoz--BERTugues-base-portuguese-cased/snapshots/76022866e209716d673e144cc9186f7b20830967/vocab.txt
+[2025-07-09 17:01:45,587][transformers.tokenization_utils_base][INFO] - loading file tokenizer.json from cache at None
+[2025-07-09 17:01:45,587][transformers.tokenization_utils_base][INFO] - loading file added_tokens.json from cache at None
+[2025-07-09 17:01:45,587][transformers.tokenization_utils_base][INFO] - loading file special_tokens_map.json from cache at None
+[2025-07-09 17:01:45,587][transformers.tokenization_utils_base][INFO] - loading file tokenizer_config.json from cache at None
+[2025-07-09 17:01:45,587][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None
+[2025-07-09 17:01:45,588][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--ricardoz--BERTugues-base-portuguese-cased/snapshots/76022866e209716d673e144cc9186f7b20830967/config.json
+[2025-07-09 17:01:45,588][transformers.configuration_utils][INFO] - Model config BertConfig {
+  "architectures": [
+    "BertForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}
+
+[2025-07-09 17:01:45,622][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--ricardoz--BERTugues-base-portuguese-cased/snapshots/76022866e209716d673e144cc9186f7b20830967/config.json
+[2025-07-09 17:01:45,622][transformers.configuration_utils][INFO] - Model config BertConfig {
+  "architectures": [
+    "BertForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}
+
+[2025-07-09 17:01:45,641][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: True; Use Full Context: False
+[2025-07-09 17:01:46,310][__main__][INFO] - 
+Token statistics for 'train' split:
+[2025-07-09 17:01:46,310][__main__][INFO] -   Total examples: 500
+[2025-07-09 17:01:46,310][__main__][INFO] -   Min tokens: 512
+[2025-07-09 17:01:46,310][__main__][INFO] -   Max tokens: 512
+[2025-07-09 17:01:46,310][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-09 17:01:46,310][__main__][INFO] -   Std tokens: 0.00
+[2025-07-09 17:01:46,406][__main__][INFO] - 
+Token statistics for 'validation' split:
+[2025-07-09 17:01:46,407][__main__][INFO] -   Total examples: 132
+[2025-07-09 17:01:46,407][__main__][INFO] -   Min tokens: 512
+[2025-07-09 17:01:46,407][__main__][INFO] -   Max tokens: 512
+[2025-07-09 17:01:46,407][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-09 17:01:46,407][__main__][INFO] -   Std tokens: 0.00
+[2025-07-09 17:01:46,506][__main__][INFO] - 
+Token statistics for 'test' split:
+[2025-07-09 17:01:46,506][__main__][INFO] -   Total examples: 138
+[2025-07-09 17:01:46,506][__main__][INFO] -   Min tokens: 512
+[2025-07-09 17:01:46,506][__main__][INFO] -   Max tokens: 512
+[2025-07-09 17:01:46,506][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-09 17:01:46,506][__main__][INFO] -   Std tokens: 0.00
+[2025-07-09 17:01:46,506][__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 17:01:46,506][__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 17:01:46,719][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--ricardoz--BERTugues-base-portuguese-cased/snapshots/76022866e209716d673e144cc9186f7b20830967/config.json
+[2025-07-09 17:01:46,720][transformers.configuration_utils][INFO] - Model config BertConfig {
+  "architectures": [
+    "BertForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": 0,
+    "1": 40,
+    "2": 80,
+    "3": 120,
+    "4": 160,
+    "5": 200
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "40": 1,
+    "80": 2,
+    "120": 3,
+    "160": 4,
+    "200": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}
+
+[2025-07-09 17:01:46,911][transformers.modeling_utils][INFO] - loading weights file model.safetensors from cache at /tmp/models--ricardoz--BERTugues-base-portuguese-cased/snapshots/76022866e209716d673e144cc9186f7b20830967/model.safetensors
+[2025-07-09 17:01:46,911][transformers.modeling_utils][INFO] - Will use torch_dtype=torch.float32 as defined in model's config object
+[2025-07-09 17:01:46,911][transformers.modeling_utils][INFO] - Instantiating BertForSequenceClassification model under default dtype torch.float32.
+[2025-07-09 17:01:48,083][transformers.modeling_utils][INFO] - Some weights of the model checkpoint at ricardoz/BERTugues-base-portuguese-cased were not used when initializing BertForSequenceClassification: ['cls.predictions.bias', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.dense.weight', 'cls.seq_relationship.bias', 'cls.seq_relationship.weight']
+- This IS expected if you are initializing BertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
+- This IS NOT expected if you are initializing BertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
+[2025-07-09 17:01:48,084][transformers.modeling_utils][WARNING] - Some weights of BertForSequenceClassification were not initialized from the model checkpoint at ricardoz/BERTugues-base-portuguese-cased and are newly initialized: ['classifier.bias', 'classifier.weight']
+You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
+[2025-07-09 17:01:48,090][transformers.training_args][INFO] - PyTorch: setting up devices
+[2025-07-09 17:01:48,113][__main__][INFO] - Total steps: 620. Number of warmup steps: 62
+[2025-07-09 17:01:48,121][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 17:01:48,144][transformers.trainer][INFO] - Using auto half precision backend
+[2025-07-09 17:01:48,147][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, prompt, essay_year, reference, id, id_prompt. If essay_text, supporting_text, grades, prompt, essay_year, reference, id, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:01:48,152][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:01:48,152][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:01:48,152][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:01:49,260][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, prompt, essay_year, reference, id, id_prompt. If essay_text, supporting_text, grades, prompt, essay_year, reference, id, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:01:49,270][transformers.trainer][INFO] - ***** Running training *****
+[2025-07-09 17:01:49,270][transformers.trainer][INFO] -   Num examples = 500
+[2025-07-09 17:01:49,270][transformers.trainer][INFO] -   Num Epochs = 20
+[2025-07-09 17:01:49,270][transformers.trainer][INFO] -   Instantaneous batch size per device = 16
+[2025-07-09 17:01:49,270][transformers.trainer][INFO] -   Total train batch size (w. parallel, distributed & accumulation) = 16
+[2025-07-09 17:01:49,270][transformers.trainer][INFO] -   Gradient Accumulation steps = 1
+[2025-07-09 17:01:49,270][transformers.trainer][INFO] -   Total optimization steps = 640
+[2025-07-09 17:01:49,271][transformers.trainer][INFO] -   Number of trainable parameters = 109,486,854
+[2025-07-09 17:01:54,149][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, prompt, essay_year, reference, id, id_prompt. If essay_text, supporting_text, grades, prompt, essay_year, reference, id, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:01:54,152][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:01:54,152][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:01:54,152][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:01:54,570][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-32
+[2025-07-09 17:01:54,572][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-32/config.json
+[2025-07-09 17:01:55,547][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-32/model.safetensors
+[2025-07-09 17:02:01,078][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, prompt, essay_year, reference, id, id_prompt. If essay_text, supporting_text, grades, prompt, essay_year, reference, id, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:02:01,081][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:02:01,081][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:02:01,081][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:02:01,499][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-64
+[2025-07-09 17:02:01,501][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-64/config.json
+[2025-07-09 17:02:02,401][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-64/model.safetensors
+[2025-07-09 17:02:03,876][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-32] due to args.save_total_limit
+[2025-07-09 17:02:08,594][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, prompt, essay_year, reference, id, id_prompt. If essay_text, supporting_text, grades, prompt, essay_year, reference, id, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:02:08,597][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:02:08,597][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:02:08,598][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:02:09,021][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-96
+[2025-07-09 17:02:09,022][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-96/config.json
+[2025-07-09 17:02:10,284][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-96/model.safetensors
+[2025-07-09 17:02:15,880][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, prompt, essay_year, reference, id, id_prompt. If essay_text, supporting_text, grades, prompt, essay_year, reference, id, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:02:15,883][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:02:15,883][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:02:15,883][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:02:16,290][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-128
+[2025-07-09 17:02:16,291][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-128/config.json
+[2025-07-09 17:02:17,310][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-128/model.safetensors
+[2025-07-09 17:02:18,246][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-64] due to args.save_total_limit
+[2025-07-09 17:02:18,313][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-96] due to args.save_total_limit
+[2025-07-09 17:02:22,925][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, prompt, essay_year, reference, id, id_prompt. If essay_text, supporting_text, grades, prompt, essay_year, reference, id, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:02:22,927][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:02:22,927][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:02:22,927][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:02:23,315][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-160
+[2025-07-09 17:02:23,316][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-160/config.json
+[2025-07-09 17:02:24,123][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-160/model.safetensors
+[2025-07-09 17:02:29,422][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, prompt, essay_year, reference, id, id_prompt. If essay_text, supporting_text, grades, prompt, essay_year, reference, id, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:02:29,424][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:02:29,425][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:02:29,425][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:02:29,814][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-192
+[2025-07-09 17:02:29,815][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-192/config.json
+[2025-07-09 17:02:30,704][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-192/model.safetensors
+[2025-07-09 17:02:32,183][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-160] due to args.save_total_limit
+[2025-07-09 17:02:36,833][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, prompt, essay_year, reference, id, id_prompt. If essay_text, supporting_text, grades, prompt, essay_year, reference, id, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:02:36,836][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:02:36,836][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:02:36,836][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:02:37,229][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-224
+[2025-07-09 17:02:37,230][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-224/config.json
+[2025-07-09 17:02:38,109][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-224/model.safetensors
+[2025-07-09 17:02:38,912][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-192] due to args.save_total_limit
+[2025-07-09 17:02:43,498][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, prompt, essay_year, reference, id, id_prompt. If essay_text, supporting_text, grades, prompt, essay_year, reference, id, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:02:43,501][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:02:43,501][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:02:43,501][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:02:43,887][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-256
+[2025-07-09 17:02:43,889][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-256/config.json
+[2025-07-09 17:02:44,876][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-256/model.safetensors
+[2025-07-09 17:02:45,756][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-224] due to args.save_total_limit
+[2025-07-09 17:02:50,418][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, prompt, essay_year, reference, id, id_prompt. If essay_text, supporting_text, grades, prompt, essay_year, reference, id, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:02:50,420][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:02:50,420][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:02:50,421][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:02:50,818][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-288
+[2025-07-09 17:02:50,819][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-288/config.json
+[2025-07-09 17:02:51,840][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-288/model.safetensors
+[2025-07-09 17:02:52,719][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-256] due to args.save_total_limit
+[2025-07-09 17:02:52,800][transformers.trainer][INFO] - 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+[2025-07-09 17:02:52,801][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-128 (score: 0.5213772228528187).
+[2025-07-09 17:02:53,045][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-01-35/results/checkpoint-288] due to args.save_total_limit
+[2025-07-09 17:02:53,175][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, prompt, essay_year, reference, id, id_prompt. If essay_text, supporting_text, grades, prompt, essay_year, reference, id, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:02:53,178][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:02:53,178][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:02:53,178][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:02:53,607][__main__][INFO] - Training completed successfully.
+[2025-07-09 17:02:53,607][__main__][INFO] - Running on Test
+[2025-07-09 17:02:53,607][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, prompt, essay_year, reference, id, id_prompt. If essay_text, supporting_text, grades, prompt, essay_year, reference, id, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:02:53,610][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:02:53,610][transformers.trainer][INFO] -   Num examples = 138
+[2025-07-09 17:02:53,610][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:02:54,035][__main__][INFO] - Test metrics: {'eval_loss': 1.247100830078125, 'eval_model_preparation_time': 0.0025, 'eval_accuracy': 0.5434782608695652, 'eval_RMSE': 30.45547950507524, 'eval_QWK': 0.6139860139860139, 'eval_HDIV': 0.007246376811594235, 'eval_Macro_F1': 0.38733766233766237, 'eval_Micro_F1': 0.5434782608695652, 'eval_Weighted_F1': 0.5620203065855239, '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': 7, 'eval_TN_2': 109, 'eval_FP_2': 19, 'eval_FN_2': 3, 'eval_TP_3': 35, 'eval_TN_3': 61, 'eval_FP_3': 11, 'eval_FN_3': 31, 'eval_TP_4': 28, 'eval_TN_4': 67, 'eval_FP_4': 20, 'eval_FN_4': 23, 'eval_TP_5': 5, 'eval_TN_5': 115, 'eval_FP_5': 13, 'eval_FN_5': 5, 'eval_runtime': 0.42, 'eval_samples_per_second': 328.555, 'eval_steps_per_second': 21.427, 'epoch': 9.0}
+[2025-07-09 17:02:54,036][transformers.trainer][INFO] - Saving model checkpoint to ./results/best_model
+[2025-07-09 17:02:54,038][transformers.configuration_utils][INFO] - Configuration saved in ./results/best_model/config.json
+[2025-07-09 17:02:55,219][transformers.modeling_utils][INFO] - Model weights saved in ./results/best_model/model.safetensors
+[2025-07-09 17:02:55,221][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/best_model/tokenizer_config.json
+[2025-07-09 17:02:55,221][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/best_model/special_tokens_map.json
+[2025-07-09 17:02:55,234][__main__][INFO] - Model and tokenizer saved to ./results/best_model
+[2025-07-09 17:02:55,238][__main__][INFO] - Fine Tuning Finished.
+[2025-07-09 17:02:55,748][__main__][INFO] - Total emissions: 0.0015 kg CO2eq

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86df43a6e3e587411c325a3b7c2d1597d795466c11ad95b9347154103e2fb21e
+size 5777