abarbosa's picture
Pushing fine-tuned model to Hugging Face Hub
9ae740e verified
[2025-07-09 17:06:16,012][__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: 3
use_full_context: false
training_params:
weight_decay: 0.01
warmup_ratio: 0.1
learning_rate: 5.0e-05
train_batch_size: 16
eval_batch_size: 16
gradient_accumulation_steps: 1
gradient_checkpointing: false
[2025-07-09 17:06:19,861][__main__][INFO] - GPU 0: NVIDIA RTX A6000 | TDP ≈ 300 W
[2025-07-09 17:06:19,861][__main__][INFO] - Starting the Fine Tuning training process.
[2025-07-09 17:06:24,826][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 17:06:24,827][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 17:06:25,030][transformers.models.auto.tokenization_auto][INFO] - Could not locate the tokenizer configuration file, will try to use the model config instead.
[2025-07-09 17:06:25,241][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 17:06:25,242][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 17:06:25,880][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 17:06:25,880][transformers.tokenization_utils_base][INFO] - loading file tokenizer.json from cache at None
[2025-07-09 17:06:25,880][transformers.tokenization_utils_base][INFO] - loading file added_tokens.json from cache at None
[2025-07-09 17:06:25,880][transformers.tokenization_utils_base][INFO] - loading file special_tokens_map.json from cache at None
[2025-07-09 17:06:25,880][transformers.tokenization_utils_base][INFO] - loading file tokenizer_config.json from cache at None
[2025-07-09 17:06:25,880][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None
[2025-07-09 17:06:25,880][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 17:06:25,881][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 17:06:25,912][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 17:06:25,913][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 17:06:25,933][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: True; Use Full Context: False
[2025-07-09 17:06:26,599][__main__][INFO] -
Token statistics for 'train' split:
[2025-07-09 17:06:26,599][__main__][INFO] - Total examples: 500
[2025-07-09 17:06:26,599][__main__][INFO] - Min tokens: 512
[2025-07-09 17:06:26,599][__main__][INFO] - Max tokens: 512
[2025-07-09 17:06:26,599][__main__][INFO] - Avg tokens: 512.00
[2025-07-09 17:06:26,599][__main__][INFO] - Std tokens: 0.00
[2025-07-09 17:06:26,696][__main__][INFO] -
Token statistics for 'validation' split:
[2025-07-09 17:06:26,696][__main__][INFO] - Total examples: 132
[2025-07-09 17:06:26,696][__main__][INFO] - Min tokens: 512
[2025-07-09 17:06:26,696][__main__][INFO] - Max tokens: 512
[2025-07-09 17:06:26,696][__main__][INFO] - Avg tokens: 512.00
[2025-07-09 17:06:26,696][__main__][INFO] - Std tokens: 0.00
[2025-07-09 17:06:26,798][__main__][INFO] -
Token statistics for 'test' split:
[2025-07-09 17:06:26,798][__main__][INFO] - Total examples: 138
[2025-07-09 17:06:26,798][__main__][INFO] - Min tokens: 512
[2025-07-09 17:06:26,798][__main__][INFO] - Max tokens: 512
[2025-07-09 17:06:26,798][__main__][INFO] - Avg tokens: 512.00
[2025-07-09 17:06:26,798][__main__][INFO] - Std tokens: 0.00
[2025-07-09 17:06:26,798][__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 17:06:26,798][__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 17:06:27,018][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 17:06:27,018][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 17:06:27,214][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 17:06:27,215][transformers.modeling_utils][INFO] - Will use torch_dtype=torch.float32 as defined in model's config object
[2025-07-09 17:06:27,215][transformers.modeling_utils][INFO] - Instantiating BertForSequenceClassification model under default dtype torch.float32.
[2025-07-09 17:06:28,002][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 17:06:28,002][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 17:06:28,008][transformers.training_args][INFO] - PyTorch: setting up devices
[2025-07-09 17:06:28,033][__main__][INFO] - Total steps: 620. Number of warmup steps: 62
[2025-07-09 17:06:28,041][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 17:06:28,063][transformers.trainer][INFO] - Using auto half precision backend
[2025-07-09 17:06:28,065][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:06:28,070][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:06:28,071][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:06:28,071][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:06:29,180][transformers.trainer][INFO] - The following columns in the Training set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:06:29,190][transformers.trainer][INFO] - ***** Running training *****
[2025-07-09 17:06:29,190][transformers.trainer][INFO] - Num examples = 500
[2025-07-09 17:06:29,190][transformers.trainer][INFO] - Num Epochs = 20
[2025-07-09 17:06:29,190][transformers.trainer][INFO] - Instantaneous batch size per device = 16
[2025-07-09 17:06:29,190][transformers.trainer][INFO] - Total train batch size (w. parallel, distributed & accumulation) = 16
[2025-07-09 17:06:29,190][transformers.trainer][INFO] - Gradient Accumulation steps = 1
[2025-07-09 17:06:29,190][transformers.trainer][INFO] - Total optimization steps = 640
[2025-07-09 17:06:29,190][transformers.trainer][INFO] - Number of trainable parameters = 109,486,854
[2025-07-09 17:06:34,013][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:06:34,016][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:06:34,016][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:06:34,016][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:06:34,411][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-32
[2025-07-09 17:06:34,413][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-32/config.json
[2025-07-09 17:06:35,388][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-32/model.safetensors
[2025-07-09 17:06:41,012][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:06:41,014][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:06:41,015][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:06:41,015][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:06:41,409][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-64
[2025-07-09 17:06:41,411][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-64/config.json
[2025-07-09 17:06:42,414][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-64/model.safetensors
[2025-07-09 17:06:43,902][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-32] due to args.save_total_limit
[2025-07-09 17:06:48,508][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:06:48,511][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:06:48,512][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:06:48,512][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:06:48,905][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-96
[2025-07-09 17:06:48,906][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-96/config.json
[2025-07-09 17:06:49,840][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-96/model.safetensors
[2025-07-09 17:06:50,703][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-64] due to args.save_total_limit
[2025-07-09 17:06:55,362][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:06:55,365][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:06:55,365][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:06:55,365][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:06:55,757][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-128
[2025-07-09 17:06:55,759][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-128/config.json
[2025-07-09 17:06:56,597][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-128/model.safetensors
[2025-07-09 17:07:01,972][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:07:01,975][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:07:01,975][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:07:01,975][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:07:02,367][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-160
[2025-07-09 17:07:02,368][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-160/config.json
[2025-07-09 17:07:03,428][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-160/model.safetensors
[2025-07-09 17:07:04,269][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-128] due to args.save_total_limit
[2025-07-09 17:07:08,895][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:07:08,897][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:07:08,898][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:07:08,898][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:07:09,288][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-192
[2025-07-09 17:07:09,289][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-192/config.json
[2025-07-09 17:07:10,206][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-192/model.safetensors
[2025-07-09 17:07:11,160][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-160] due to args.save_total_limit
[2025-07-09 17:07:15,856][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:07:15,859][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:07:15,859][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:07:15,859][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:07:16,282][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-224
[2025-07-09 17:07:16,283][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-224/config.json
[2025-07-09 17:07:17,131][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-224/model.safetensors
[2025-07-09 17:07:18,022][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-192] due to args.save_total_limit
[2025-07-09 17:07:22,789][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:07:22,792][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:07:22,792][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:07:22,792][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:07:23,201][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-256
[2025-07-09 17:07:23,203][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-256/config.json
[2025-07-09 17:07:24,424][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-256/model.safetensors
[2025-07-09 17:07:25,309][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-96] due to args.save_total_limit
[2025-07-09 17:07:25,432][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-224] due to args.save_total_limit
[2025-07-09 17:07:30,129][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:07:30,131][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:07:30,131][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:07:30,131][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:07:30,520][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-288
[2025-07-09 17:07:30,521][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-288/config.json
[2025-07-09 17:07:31,349][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-288/model.safetensors
[2025-07-09 17:07:36,863][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:07:36,866][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:07:36,866][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:07:36,866][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:07:37,257][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-320
[2025-07-09 17:07:37,258][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-320/config.json
[2025-07-09 17:07:38,110][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-320/model.safetensors
[2025-07-09 17:07:38,960][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-256] due to args.save_total_limit
[2025-07-09 17:07:39,067][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-288] due to args.save_total_limit
[2025-07-09 17:07:43,736][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:07:43,739][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:07:43,739][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:07:43,739][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:07:44,147][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-352
[2025-07-09 17:07:44,148][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-352/config.json
[2025-07-09 17:07:45,170][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-352/model.safetensors
[2025-07-09 17:07:46,159][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-320] due to args.save_total_limit
[2025-07-09 17:07:50,840][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:07:50,843][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:07:50,843][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:07:50,843][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:07:51,241][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-384
[2025-07-09 17:07:51,242][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-384/config.json
[2025-07-09 17:07:52,176][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-384/model.safetensors
[2025-07-09 17:07:57,717][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:07:57,720][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:07:57,720][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:07:57,720][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:07:58,119][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-416
[2025-07-09 17:07:58,121][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-416/config.json
[2025-07-09 17:07:59,069][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-416/model.safetensors
[2025-07-09 17:08:00,007][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-384] due to args.save_total_limit
[2025-07-09 17:08:04,702][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:08:04,705][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:08:04,706][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:08:04,706][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:08:05,096][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-448
[2025-07-09 17:08:05,097][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-448/config.json
[2025-07-09 17:08:05,906][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-448/model.safetensors
[2025-07-09 17:08:06,837][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-416] due to args.save_total_limit
[2025-07-09 17:08:11,545][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:08:11,548][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:08:11,548][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:08:11,548][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:08:11,937][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-480
[2025-07-09 17:08:11,938][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-480/config.json
[2025-07-09 17:08:12,811][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-480/model.safetensors
[2025-07-09 17:08:13,705][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-448] due to args.save_total_limit
[2025-07-09 17:08:18,361][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:08:18,363][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:08:18,364][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:08:18,364][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:08:18,754][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-512
[2025-07-09 17:08:18,756][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-512/config.json
[2025-07-09 17:08:19,574][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-512/model.safetensors
[2025-07-09 17:08:20,476][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-480] due to args.save_total_limit
[2025-07-09 17:08:20,590][transformers.trainer][INFO] -
Training completed. Do not forget to share your model on huggingface.co/models =)
[2025-07-09 17:08:20,590][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-352 (score: 0.5530126109294722).
[2025-07-09 17:08:20,826][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-06-15/results/checkpoint-512] due to args.save_total_limit
[2025-07-09 17:08:20,953][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:08:20,957][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:08:20,957][transformers.trainer][INFO] - Num examples = 132
[2025-07-09 17:08:20,957][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:08:21,357][__main__][INFO] - Training completed successfully.
[2025-07-09 17:08:21,357][__main__][INFO] - Running on Test
[2025-07-09 17:08:21,357][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades. If id_prompt, prompt, essay_text, supporting_text, essay_year, reference, id, grades are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message.
[2025-07-09 17:08:21,359][transformers.trainer][INFO] -
***** Running Evaluation *****
[2025-07-09 17:08:21,359][transformers.trainer][INFO] - Num examples = 138
[2025-07-09 17:08:21,359][transformers.trainer][INFO] - Batch size = 16
[2025-07-09 17:08:21,755][__main__][INFO] - Test metrics: {'eval_loss': 1.6317094564437866, 'eval_model_preparation_time': 0.0022, 'eval_accuracy': 0.4927536231884058, 'eval_RMSE': 31.20757990421976, 'eval_QWK': 0.5408745247148289, 'eval_HDIV': 0.007246376811594235, 'eval_Macro_F1': 0.2885197389992787, 'eval_Micro_F1': 0.4927536231884058, 'eval_Weighted_F1': 0.5051079377027337, 'eval_TP_0': 0, 'eval_TN_0': 137, 'eval_FP_0': 0, 'eval_FN_0': 1, 'eval_TP_1': 0, 'eval_TN_1': 137, 'eval_FP_1': 0, 'eval_FN_1': 1, 'eval_TP_2': 7, 'eval_TN_2': 106, 'eval_FP_2': 23, 'eval_FN_2': 2, 'eval_TP_3': 41, 'eval_TN_3': 41, 'eval_FP_3': 21, 'eval_FN_3': 35, 'eval_TP_4': 17, 'eval_TN_4': 75, 'eval_FP_4': 17, 'eval_FN_4': 29, 'eval_TP_5': 3, 'eval_TN_5': 124, 'eval_FP_5': 9, 'eval_FN_5': 2, 'eval_runtime': 0.3914, 'eval_samples_per_second': 352.571, 'eval_steps_per_second': 22.994, 'epoch': 16.0}
[2025-07-09 17:08:21,755][transformers.trainer][INFO] - Saving model checkpoint to ./results/best_model
[2025-07-09 17:08:21,757][transformers.configuration_utils][INFO] - Configuration saved in ./results/best_model/config.json
[2025-07-09 17:08:22,927][transformers.modeling_utils][INFO] - Model weights saved in ./results/best_model/model.safetensors
[2025-07-09 17:08:22,929][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/best_model/tokenizer_config.json
[2025-07-09 17:08:22,929][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/best_model/special_tokens_map.json
[2025-07-09 17:08:22,941][__main__][INFO] - Model and tokenizer saved to ./results/best_model
[2025-07-09 17:08:22,945][__main__][INFO] - Fine Tuning Finished.
[2025-07-09 17:08:23,454][__main__][INFO] - Total emissions: 0.0026 kg CO2eq