| [2025-07-09 16:33:25,901][__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: neuralmind/bert-base-portuguese-cased |
| type: encoder_classification |
| num_labels: 6 |
| output_dir: ./results/ |
| logging_dir: ./logs/ |
| best_model_dir: ./results/best_model |
| tokenizer: |
| name: neuralmind/bert-base-portuguese-cased |
| dataset: |
| grade_index: 1 |
| 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 16:33:29,741][__main__][INFO] - GPU 0: NVIDIA RTX A6000 | TDP ≈ 300 W |
| [2025-07-09 16:33:29,741][__main__][INFO] - Starting the Fine Tuning training process. |
| [2025-07-09 16:33:34,824][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/config.json |
| [2025-07-09 16:33:34,825][transformers.configuration_utils][INFO] - Model config BertConfig { |
| "architectures": [ |
| "BertForMaskedLM" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "classifier_dropout": null, |
| "directionality": "bidi", |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 768, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "layer_norm_eps": 1e-12, |
| "max_position_embeddings": 512, |
| "model_type": "bert", |
| "num_attention_heads": 12, |
| "num_hidden_layers": 12, |
| "output_past": true, |
| "pad_token_id": 0, |
| "pooler_fc_size": 768, |
| "pooler_num_attention_heads": 12, |
| "pooler_num_fc_layers": 3, |
| "pooler_size_per_head": 128, |
| "pooler_type": "first_token_transform", |
| "position_embedding_type": "absolute", |
| "transformers_version": "4.53.1", |
| "type_vocab_size": 2, |
| "use_cache": true, |
| "vocab_size": 29794 |
| } |
|
|
| [2025-07-09 16:33:35,020][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/config.json |
| [2025-07-09 16:33:35,021][transformers.configuration_utils][INFO] - Model config BertConfig { |
| "architectures": [ |
| "BertForMaskedLM" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "classifier_dropout": null, |
| "directionality": "bidi", |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 768, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "layer_norm_eps": 1e-12, |
| "max_position_embeddings": 512, |
| "model_type": "bert", |
| "num_attention_heads": 12, |
| "num_hidden_layers": 12, |
| "output_past": true, |
| "pad_token_id": 0, |
| "pooler_fc_size": 768, |
| "pooler_num_attention_heads": 12, |
| "pooler_num_fc_layers": 3, |
| "pooler_size_per_head": 128, |
| "pooler_type": "first_token_transform", |
| "position_embedding_type": "absolute", |
| "transformers_version": "4.53.1", |
| "type_vocab_size": 2, |
| "use_cache": true, |
| "vocab_size": 29794 |
| } |
|
|
| [2025-07-09 16:33:35,219][transformers.tokenization_utils_base][INFO] - loading file vocab.txt from cache at /tmp/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/vocab.txt |
| [2025-07-09 16:33:35,219][transformers.tokenization_utils_base][INFO] - loading file tokenizer.json from cache at None |
| [2025-07-09 16:33:35,219][transformers.tokenization_utils_base][INFO] - loading file added_tokens.json from cache at /tmp/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/added_tokens.json |
| [2025-07-09 16:33:35,219][transformers.tokenization_utils_base][INFO] - loading file special_tokens_map.json from cache at /tmp/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/special_tokens_map.json |
| [2025-07-09 16:33:35,219][transformers.tokenization_utils_base][INFO] - loading file tokenizer_config.json from cache at /tmp/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/tokenizer_config.json |
| [2025-07-09 16:33:35,219][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None |
| [2025-07-09 16:33:35,219][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/config.json |
| [2025-07-09 16:33:35,220][transformers.configuration_utils][INFO] - Model config BertConfig { |
| "architectures": [ |
| "BertForMaskedLM" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "classifier_dropout": null, |
| "directionality": "bidi", |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 768, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "layer_norm_eps": 1e-12, |
| "max_position_embeddings": 512, |
| "model_type": "bert", |
| "num_attention_heads": 12, |
| "num_hidden_layers": 12, |
| "output_past": true, |
| "pad_token_id": 0, |
| "pooler_fc_size": 768, |
| "pooler_num_attention_heads": 12, |
| "pooler_num_fc_layers": 3, |
| "pooler_size_per_head": 128, |
| "pooler_type": "first_token_transform", |
| "position_embedding_type": "absolute", |
| "transformers_version": "4.53.1", |
| "type_vocab_size": 2, |
| "use_cache": true, |
| "vocab_size": 29794 |
| } |
|
|
| [2025-07-09 16:33:35,250][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/config.json |
| [2025-07-09 16:33:35,250][transformers.configuration_utils][INFO] - Model config BertConfig { |
| "architectures": [ |
| "BertForMaskedLM" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "classifier_dropout": null, |
| "directionality": "bidi", |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 768, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "layer_norm_eps": 1e-12, |
| "max_position_embeddings": 512, |
| "model_type": "bert", |
| "num_attention_heads": 12, |
| "num_hidden_layers": 12, |
| "output_past": true, |
| "pad_token_id": 0, |
| "pooler_fc_size": 768, |
| "pooler_num_attention_heads": 12, |
| "pooler_num_fc_layers": 3, |
| "pooler_size_per_head": 128, |
| "pooler_type": "first_token_transform", |
| "position_embedding_type": "absolute", |
| "transformers_version": "4.53.1", |
| "type_vocab_size": 2, |
| "use_cache": true, |
| "vocab_size": 29794 |
| } |
|
|
| [2025-07-09 16:33:35,268][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: True; Use Full Context: False |
| [2025-07-09 16:33:35,890][__main__][INFO] - |
| Token statistics for 'train' split: |
| [2025-07-09 16:33:35,890][__main__][INFO] - Total examples: 500 |
| [2025-07-09 16:33:35,890][__main__][INFO] - Min tokens: 512 |
| [2025-07-09 16:33:35,890][__main__][INFO] - Max tokens: 512 |
| [2025-07-09 16:33:35,891][__main__][INFO] - Avg tokens: 512.00 |
| [2025-07-09 16:33:35,891][__main__][INFO] - Std tokens: 0.00 |
| [2025-07-09 16:33:35,983][__main__][INFO] - |
| Token statistics for 'validation' split: |
| [2025-07-09 16:33:35,983][__main__][INFO] - Total examples: 132 |
| [2025-07-09 16:33:35,983][__main__][INFO] - Min tokens: 512 |
| [2025-07-09 16:33:35,983][__main__][INFO] - Max tokens: 512 |
| [2025-07-09 16:33:35,983][__main__][INFO] - Avg tokens: 512.00 |
| [2025-07-09 16:33:35,983][__main__][INFO] - Std tokens: 0.00 |
| [2025-07-09 16:33:36,082][__main__][INFO] - |
| Token statistics for 'test' split: |
| [2025-07-09 16:33:36,083][__main__][INFO] - Total examples: 138 |
| [2025-07-09 16:33:36,083][__main__][INFO] - Min tokens: 512 |
| [2025-07-09 16:33:36,083][__main__][INFO] - Max tokens: 512 |
| [2025-07-09 16:33:36,083][__main__][INFO] - Avg tokens: 512.00 |
| [2025-07-09 16:33:36,083][__main__][INFO] - Std tokens: 0.00 |
| [2025-07-09 16:33:36,083][__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 16:33:36,083][__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 16:33:36,300][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/config.json |
| [2025-07-09 16:33:36,301][transformers.configuration_utils][INFO] - Model config BertConfig { |
| "architectures": [ |
| "BertForMaskedLM" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "classifier_dropout": null, |
| "directionality": "bidi", |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 768, |
| "id2label": { |
| "0": 0, |
| "1": 40, |
| "2": 80, |
| "3": 120, |
| "4": 160, |
| "5": 200 |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "label2id": { |
| "0": 0, |
| "40": 1, |
| "80": 2, |
| "120": 3, |
| "160": 4, |
| "200": 5 |
| }, |
| "layer_norm_eps": 1e-12, |
| "max_position_embeddings": 512, |
| "model_type": "bert", |
| "num_attention_heads": 12, |
| "num_hidden_layers": 12, |
| "output_past": true, |
| "pad_token_id": 0, |
| "pooler_fc_size": 768, |
| "pooler_num_attention_heads": 12, |
| "pooler_num_fc_layers": 3, |
| "pooler_size_per_head": 128, |
| "pooler_type": "first_token_transform", |
| "position_embedding_type": "absolute", |
| "transformers_version": "4.53.1", |
| "type_vocab_size": 2, |
| "use_cache": true, |
| "vocab_size": 29794 |
| } |
|
|
| [2025-07-09 16:33:36,719][transformers.modeling_utils][INFO] - loading weights file pytorch_model.bin from cache at /tmp/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/pytorch_model.bin |
| [2025-07-09 16:33:36,846][transformers.modeling_utils][INFO] - Since the `torch_dtype` attribute can't be found in model's config object, will use torch_dtype={torch_dtype} as derived from model's weights |
| [2025-07-09 16:33:36,846][transformers.modeling_utils][INFO] - Instantiating BertForSequenceClassification model under default dtype torch.float32. |
| [2025-07-09 16:33:36,911][transformers.safetensors_conversion][INFO] - Attempting to create safetensors variant |
| [2025-07-09 16:33:37,672][transformers.safetensors_conversion][INFO] - Safetensors PR exists |
| [2025-07-09 16:33:37,900][transformers.modeling_utils][INFO] - Some weights of the model checkpoint at neuralmind/bert-base-portuguese-cased were not used when initializing BertForSequenceClassification: ['cls.predictions.bias', 'cls.predictions.decoder.weight', '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 16:33:37,901][transformers.modeling_utils][WARNING] - Some weights of BertForSequenceClassification were not initialized from the model checkpoint at neuralmind/bert-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 16:33:37,907][transformers.training_args][INFO] - PyTorch: setting up devices |
| [2025-07-09 16:33:37,929][__main__][INFO] - Total steps: 620. Number of warmup steps: 62 |
| [2025-07-09 16:33:37,937][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 16:33:37,961][transformers.trainer][INFO] - Using auto half precision backend |
| [2025-07-09 16:33:37,964][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, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-09 16:33:37,969][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-09 16:33:37,969][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-09 16:33:37,969][transformers.trainer][INFO] - Batch size = 16 |
| [2025-07-09 16:33:39,133][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, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-09 16:33:39,143][transformers.trainer][INFO] - ***** Running training ***** |
| [2025-07-09 16:33:39,143][transformers.trainer][INFO] - Num examples = 500 |
| [2025-07-09 16:33:39,143][transformers.trainer][INFO] - Num Epochs = 20 |
| [2025-07-09 16:33:39,143][transformers.trainer][INFO] - Instantaneous batch size per device = 16 |
| [2025-07-09 16:33:39,143][transformers.trainer][INFO] - Total train batch size (w. parallel, distributed & accumulation) = 16 |
| [2025-07-09 16:33:39,143][transformers.trainer][INFO] - Gradient Accumulation steps = 1 |
| [2025-07-09 16:33:39,143][transformers.trainer][INFO] - Total optimization steps = 640 |
| [2025-07-09 16:33:39,143][transformers.trainer][INFO] - Number of trainable parameters = 108,927,750 |
| [2025-07-09 16:33:43,844][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, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-09 16:33:43,847][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-09 16:33:43,847][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-09 16:33:43,847][transformers.trainer][INFO] - Batch size = 16 |
| [2025-07-09 16:33:44,238][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-32 |
| [2025-07-09 16:33:44,240][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-32/config.json |
| [2025-07-09 16:33:45,191][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-32/model.safetensors |
| [2025-07-09 16:33:50,697][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, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-09 16:33:50,700][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-09 16:33:50,701][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-09 16:33:50,701][transformers.trainer][INFO] - Batch size = 16 |
| [2025-07-09 16:33:51,122][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-64 |
| [2025-07-09 16:33:51,123][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-64/config.json |
| [2025-07-09 16:33:51,996][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-64/model.safetensors |
| [2025-07-09 16:33:53,125][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-32] due to args.save_total_limit |
| [2025-07-09 16:33:57,709][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, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-09 16:33:57,711][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-09 16:33:57,712][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-09 16:33:57,712][transformers.trainer][INFO] - Batch size = 16 |
| [2025-07-09 16:33:58,097][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-96 |
| [2025-07-09 16:33:58,098][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-96/config.json |
| [2025-07-09 16:33:58,892][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-96/model.safetensors |
| [2025-07-09 16:34:04,225][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, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-09 16:34:04,229][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-09 16:34:04,229][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-09 16:34:04,229][transformers.trainer][INFO] - Batch size = 16 |
| [2025-07-09 16:34:04,615][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-128 |
| [2025-07-09 16:34:04,616][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-128/config.json |
| [2025-07-09 16:34:05,587][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-128/model.safetensors |
| [2025-07-09 16:34:06,570][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-64] due to args.save_total_limit |
| [2025-07-09 16:34:06,664][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-96] due to args.save_total_limit |
| [2025-07-09 16:34:11,268][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, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-09 16:34:11,271][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-09 16:34:11,271][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-09 16:34:11,271][transformers.trainer][INFO] - Batch size = 16 |
| [2025-07-09 16:34:11,660][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-160 |
| [2025-07-09 16:34:11,662][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-160/config.json |
| [2025-07-09 16:34:12,471][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-160/model.safetensors |
| [2025-07-09 16:34:13,431][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-128] due to args.save_total_limit |
| [2025-07-09 16:34:18,058][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, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-09 16:34:18,060][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-09 16:34:18,060][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-09 16:34:18,060][transformers.trainer][INFO] - Batch size = 16 |
| [2025-07-09 16:34:18,451][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-192 |
| [2025-07-09 16:34:18,453][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-192/config.json |
| [2025-07-09 16:34:19,471][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-192/model.safetensors |
| [2025-07-09 16:34:25,567][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, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-09 16:34:25,570][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-09 16:34:25,570][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-09 16:34:25,570][transformers.trainer][INFO] - Batch size = 16 |
| [2025-07-09 16:34:25,964][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-224 |
| [2025-07-09 16:34:25,966][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-224/config.json |
| [2025-07-09 16:34:27,025][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-224/model.safetensors |
| [2025-07-09 16:34:27,806][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-192] due to args.save_total_limit |
| [2025-07-09 16:34:32,442][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, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-09 16:34:32,445][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-09 16:34:32,445][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-09 16:34:32,445][transformers.trainer][INFO] - Batch size = 16 |
| [2025-07-09 16:34:32,834][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-256 |
| [2025-07-09 16:34:32,835][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-256/config.json |
| [2025-07-09 16:34:33,763][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-256/model.safetensors |
| [2025-07-09 16:34:34,710][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-224] due to args.save_total_limit |
| [2025-07-09 16:34:39,399][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, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-09 16:34:39,401][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-09 16:34:39,402][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-09 16:34:39,402][transformers.trainer][INFO] - Batch size = 16 |
| [2025-07-09 16:34:39,809][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-288 |
| [2025-07-09 16:34:39,810][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-288/config.json |
| [2025-07-09 16:34:40,771][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-288/model.safetensors |
| [2025-07-09 16:34:41,710][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-256] due to args.save_total_limit |
| [2025-07-09 16:34:46,344][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, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-09 16:34:46,347][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-09 16:34:46,347][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-09 16:34:46,347][transformers.trainer][INFO] - Batch size = 16 |
| [2025-07-09 16:34:46,736][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-320 |
| [2025-07-09 16:34:46,737][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-320/config.json |
| [2025-07-09 16:34:47,962][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-320/model.safetensors |
| [2025-07-09 16:34:48,900][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-288] due to args.save_total_limit |
| [2025-07-09 16:34:49,006][transformers.trainer][INFO] - |
|
|
| Training completed. Do not forget to share your model on huggingface.co/models =) |
|
|
|
|
| [2025-07-09 16:34:49,006][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-160 (score: 0.397729353598242). |
| [2025-07-09 16:34:49,183][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-320] due to args.save_total_limit |
| [2025-07-09 16:34:49,284][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, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-09 16:34:49,287][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-09 16:34:49,287][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-09 16:34:49,287][transformers.trainer][INFO] - Batch size = 16 |
| [2025-07-09 16:34:49,688][__main__][INFO] - Training completed successfully. |
| [2025-07-09 16:34:49,688][__main__][INFO] - Running on Test |
| [2025-07-09 16:34:49,688][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, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-09 16:34:49,690][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-09 16:34:49,690][transformers.trainer][INFO] - Num examples = 138 |
| [2025-07-09 16:34:49,690][transformers.trainer][INFO] - Batch size = 16 |
| [2025-07-09 16:34:50,088][__main__][INFO] - Test metrics: {'eval_loss': 1.7175557613372803, 'eval_model_preparation_time': 0.0022, 'eval_accuracy': 0.34782608695652173, 'eval_RMSE': 63.519938670433646, 'eval_QWK': 0.3477835723598436, 'eval_HDIV': 0.1159420289855072, 'eval_Macro_F1': 0.24903083028083028, 'eval_Micro_F1': 0.34782608695652173, 'eval_Weighted_F1': 0.34937224611137657, 'eval_TP_0': 0, 'eval_TN_0': 137, 'eval_FP_0': 0, 'eval_FN_0': 1, 'eval_TP_1': 17, 'eval_TN_1': 70, 'eval_FP_1': 33, 'eval_FN_1': 18, 'eval_TP_2': 1, 'eval_TN_2': 124, 'eval_FP_2': 9, 'eval_FN_2': 4, 'eval_TP_3': 19, 'eval_TN_3': 66, 'eval_FP_3': 21, 'eval_FN_3': 32, 'eval_TP_4': 6, 'eval_TN_4': 92, 'eval_FP_4': 20, 'eval_FN_4': 20, 'eval_TP_5': 5, 'eval_TN_5': 111, 'eval_FP_5': 7, 'eval_FN_5': 15, 'eval_runtime': 0.3923, 'eval_samples_per_second': 351.73, 'eval_steps_per_second': 22.939, 'epoch': 10.0} |
| [2025-07-09 16:34:50,089][transformers.trainer][INFO] - Saving model checkpoint to ./results/best_model |
| [2025-07-09 16:34:50,091][transformers.configuration_utils][INFO] - Configuration saved in ./results/best_model/config.json |
| [2025-07-09 16:34:50,968][transformers.modeling_utils][INFO] - Model weights saved in ./results/best_model/model.safetensors |
| [2025-07-09 16:34:50,970][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/best_model/tokenizer_config.json |
| [2025-07-09 16:34:50,970][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/best_model/special_tokens_map.json |
| [2025-07-09 16:34:50,982][__main__][INFO] - Model and tokenizer saved to ./results/best_model |
| [2025-07-09 16:34:50,986][__main__][INFO] - Fine Tuning Finished. |
| [2025-07-09 16:34:51,496][__main__][INFO] - Total emissions: 0.0016 kg CO2eq |
|
|
