abarbosa's picture
Pushing fine-tuned model to Hugging Face Hub
c1a5a3c verified
[2025-07-09 17:04:19,126][__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: 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 17:04:22,994][__main__][INFO] - GPU 0: NVIDIA RTX A6000 | TDP ≈ 300 W
[2025-07-09 17:04:22,994][__main__][INFO] - Starting the Fine Tuning training process.
[2025-07-09 17:04:29,107][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 17:04:29,109][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 17:04:29,314][transformers.models.auto.tokenization_auto][INFO] - Could not locate the tokenizer configuration file, will try to use the model config instead.
[2025-07-09 17:04:29,519][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 17:04:29,520][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 17:04:30,137][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 17:04:30,137][transformers.tokenization_utils_base][INFO] - loading file tokenizer.json from cache at None
[2025-07-09 17:04:30,137][transformers.tokenization_utils_base][INFO] - loading file added_tokens.json from cache at None
[2025-07-09 17:04:30,137][transformers.tokenization_utils_base][INFO] - loading file special_tokens_map.json from cache at None
[2025-07-09 17:04:30,137][transformers.tokenization_utils_base][INFO] - loading file tokenizer_config.json from cache at None
[2025-07-09 17:04:30,137][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None
[2025-07-09 17:04:30,137][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 17:04:30,138][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 17:04:30,170][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 17:04:30,171][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 17:04:30,190][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: True; Use Full Context: False
[2025-07-09 17:04:30,954][__main__][INFO] -
Token statistics for 'train' split:
[2025-07-09 17:04:30,954][__main__][INFO] - Total examples: 500
[2025-07-09 17:04:30,954][__main__][INFO] - Min tokens: 512
[2025-07-09 17:04:30,954][__main__][INFO] - Max tokens: 512
[2025-07-09 17:04:30,954][__main__][INFO] - Avg tokens: 512.00
[2025-07-09 17:04:30,954][__main__][INFO] - Std tokens: 0.00
[2025-07-09 17:04:31,058][__main__][INFO] -
Token statistics for 'validation' split:
[2025-07-09 17:04:31,058][__main__][INFO] - Total examples: 132
[2025-07-09 17:04:31,058][__main__][INFO] - Min tokens: 512
[2025-07-09 17:04:31,058][__main__][INFO] - Max tokens: 512
[2025-07-09 17:04:31,058][__main__][INFO] - Avg tokens: 512.00
[2025-07-09 17:04:31,058][__main__][INFO] - Std tokens: 0.00
[2025-07-09 17:04:31,159][__main__][INFO] -
Token statistics for 'test' split:
[2025-07-09 17:04:31,159][__main__][INFO] - Total examples: 138
[2025-07-09 17:04:31,159][__main__][INFO] - Min tokens: 512
[2025-07-09 17:04:31,159][__main__][INFO] - Max tokens: 512
[2025-07-09 17:04:31,159][__main__][INFO] - Avg tokens: 512.00
[2025-07-09 17:04:31,159][__main__][INFO] - Std tokens: 0.00
[2025-07-09 17:04:31,160][__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 17:04:31,160][__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 17:04:31,375][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 17:04:31,375][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 17:04:31,577][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 17:04:31,577][transformers.modeling_utils][INFO] - Will use torch_dtype=torch.float32 as defined in model's config object
[2025-07-09 17:04:31,577][transformers.modeling_utils][INFO] - Instantiating BertForSequenceClassification model under default dtype torch.float32.
[2025-07-09 17:04:32,380][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 17:04:32,380][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 17:04:32,385][transformers.training_args][INFO] - PyTorch: setting up devices
[2025-07-09 17:04:32,408][__main__][INFO] - Total steps: 620. Number of warmup steps: 62
[2025-07-09 17:04:32,414][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 17:04:32,436][transformers.trainer][INFO] - Using auto half precision backend
[2025-07-09 17:04:32,438][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year. If id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:04:32,442][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:04:32,442][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:04:32,442][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:04:33,464][transformers.trainer][INFO] - The following columns in the Training set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year. If id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:04:33,473][transformers.trainer][INFO] - ***** Running training *****
[2025-07-09 17:04:33,473][transformers.trainer][INFO] - Num examples = 500
[2025-07-09 17:04:33,473][transformers.trainer][INFO] - Num Epochs = 20
[2025-07-09 17:04:33,473][transformers.trainer][INFO] - Instantaneous batch size per device = 16
[2025-07-09 17:04:33,473][transformers.trainer][INFO] - Total train batch size (w. parallel, distributed & accumulation) = 16
[2025-07-09 17:04:33,473][transformers.trainer][INFO] - Gradient Accumulation steps = 1
[2025-07-09 17:04:33,473][transformers.trainer][INFO] - Total optimization steps = 640
[2025-07-09 17:04:33,474][transformers.trainer][INFO] - Number of trainable parameters = 109,486,854
[2025-07-09 17:04:38,107][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year. If id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:04:38,110][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:04:38,110][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:04:38,110][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:04:38,498][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-32
[2025-07-09 17:04:38,499][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-32/config.json
[2025-07-09 17:04:39,433][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-32/model.safetensors
[2025-07-09 17:04:44,704][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year. If id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:04:44,706][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:04:44,707][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:04:44,707][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:04:45,096][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-64
[2025-07-09 17:04:45,098][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-64/config.json
[2025-07-09 17:04:46,269][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-64/model.safetensors
[2025-07-09 17:04:47,530][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-32] due to args.save_total_limit
[2025-07-09 17:04:52,228][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year. If id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:04:52,231][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:04:52,232][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:04:52,232][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:04:52,653][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-96
[2025-07-09 17:04:52,655][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-96/config.json
[2025-07-09 17:04:53,627][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-96/model.safetensors
[2025-07-09 17:04:59,027][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year. If id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:04:59,029][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:04:59,030][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:04:59,030][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:04:59,419][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-128
[2025-07-09 17:04:59,420][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-128/config.json
[2025-07-09 17:05:00,311][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-128/model.safetensors
[2025-07-09 17:05:01,114][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-96] due to args.save_total_limit
[2025-07-09 17:05:05,758][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year. If id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:05:05,761][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:05:05,761][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:05:05,761][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:05:06,149][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-160
[2025-07-09 17:05:06,151][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-160/config.json
[2025-07-09 17:05:07,172][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-160/model.safetensors
[2025-07-09 17:05:08,394][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-64] due to args.save_total_limit
[2025-07-09 17:05:08,510][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-128] due to args.save_total_limit
[2025-07-09 17:05:13,284][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year. If id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:05:13,287][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:05:13,288][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:05:13,288][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:05:13,710][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-192
[2025-07-09 17:05:13,712][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-192/config.json
[2025-07-09 17:05:14,721][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-192/model.safetensors
[2025-07-09 17:05:20,283][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year. If id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:05:20,290][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:05:20,290][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:05:20,290][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:05:20,684][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-224
[2025-07-09 17:05:20,686][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-224/config.json
[2025-07-09 17:05:21,697][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-224/model.safetensors
[2025-07-09 17:05:23,064][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-160] due to args.save_total_limit
[2025-07-09 17:05:23,196][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-192] due to args.save_total_limit
[2025-07-09 17:05:27,855][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year. If id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:05:27,861][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:05:27,861][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:05:27,861][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:05:28,258][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-256
[2025-07-09 17:05:28,259][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-256/config.json
[2025-07-09 17:05:29,461][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-256/model.safetensors
[2025-07-09 17:05:30,496][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-224] due to args.save_total_limit
[2025-07-09 17:05:35,212][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year. If id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:05:35,216][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:05:35,216][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:05:35,216][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:05:35,644][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-288
[2025-07-09 17:05:35,646][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-288/config.json
[2025-07-09 17:05:36,831][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-288/model.safetensors
[2025-07-09 17:05:42,600][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year. If id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:05:42,605][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:05:42,605][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:05:42,605][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:05:43,003][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-320
[2025-07-09 17:05:43,005][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-320/config.json
[2025-07-09 17:05:43,926][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-320/model.safetensors
[2025-07-09 17:05:44,704][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-288] due to args.save_total_limit
[2025-07-09 17:05:49,345][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year. If id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:05:49,348][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:05:49,348][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:05:49,348][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:05:49,741][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-352
[2025-07-09 17:05:49,743][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-352/config.json
[2025-07-09 17:05:50,571][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-352/model.safetensors
[2025-07-09 17:05:51,384][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-320] due to args.save_total_limit
[2025-07-09 17:05:56,030][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year. If id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:05:56,033][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:05:56,033][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:05:56,033][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:05:56,424][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-384
[2025-07-09 17:05:56,425][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-384/config.json
[2025-07-09 17:05:57,204][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-384/model.safetensors
[2025-07-09 17:05:57,996][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-352] due to args.save_total_limit
[2025-07-09 17:06:02,695][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year. If id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:06:02,698][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:06:02,698][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:06:02,698][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:06:03,088][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-416
[2025-07-09 17:06:03,090][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-416/config.json
[2025-07-09 17:06:03,995][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-416/model.safetensors
[2025-07-09 17:06:04,799][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-384] due to args.save_total_limit
[2025-07-09 17:06:04,912][transformers.trainer][INFO] -
Training completed. Do not forget to share your model on huggingface.co/models =)
[2025-07-09 17:06:04,913][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-256 (score: 0.5384823603717406).
[2025-07-09 17:06:05,136][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-04-19/results/checkpoint-416] due to args.save_total_limit
[2025-07-09 17:06:05,256][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year. If id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:06:05,260][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:06:05,260][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:06:05,260][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:06:05,661][__main__][INFO] - Training completed successfully.
[2025-07-09 17:06:05,661][__main__][INFO] - Running on Test
[2025-07-09 17:06:05,662][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year. If id, grades, essay_text, prompt, reference, id_prompt, supporting_text, essay_year are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:06:05,664][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:06:05,664][transformers.trainer][INFO] - Num examples = 138
[2025-07-09 17:06:05,664][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:06:06,060][__main__][INFO] - Test metrics: {'eval_loss': 2.0192933082580566, 'eval_model_preparation_time': 0.0019, 'eval_accuracy': 0.36231884057971014, 'eval_RMSE': 55.638585297552666, 'eval_QWK': 0.2865109794353433, 'eval_HDIV': 0.09420289855072461, 'eval_Macro_F1': 0.26051544019593825, 'eval_Micro_F1': 0.36231884057971014, 'eval_Weighted_F1': 0.34754448627572954, 'eval_TP_0': 0, 'eval_TN_0': 135, 'eval_FP_0': 2, 'eval_FN_0': 1, 'eval_TP_1': 3, 'eval_TN_1': 100, 'eval_FP_1': 9, 'eval_FN_1': 26, 'eval_TP_2': 10, 'eval_TN_2': 102, 'eval_FP_2': 18, 'eval_FN_2': 8, 'eval_TP_3': 18, 'eval_TN_3': 63, 'eval_FP_3': 30, 'eval_FN_3': 27, 'eval_TP_4': 18, 'eval_TN_4': 78, 'eval_FP_4': 22, 'eval_FN_4': 20, 'eval_TP_5': 1, 'eval_TN_5': 124, 'eval_FP_5': 7, 'eval_FN_5': 6, 'eval_runtime': 0.3908, 'eval_samples_per_second': 353.12, 'eval_steps_per_second': 23.03, 'epoch': 13.0}
[2025-07-09 17:06:06,061][transformers.trainer][INFO] - Saving model checkpoint to ./results/best_model
[2025-07-09 17:06:06,062][transformers.configuration_utils][INFO] - Configuration saved in ./results/best_model/config.json
[2025-07-09 17:06:07,003][transformers.modeling_utils][INFO] - Model weights saved in ./results/best_model/model.safetensors
[2025-07-09 17:06:07,005][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/best_model/tokenizer_config.json
[2025-07-09 17:06:07,006][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/best_model/special_tokens_map.json
[2025-07-09 17:06:07,018][__main__][INFO] - Model and tokenizer saved to ./results/best_model
[2025-07-09 17:06:07,023][__main__][INFO] - Fine Tuning Finished.
[2025-07-09 17:06:07,532][__main__][INFO] - Total emissions: 0.0021 kg CO2eq