[2025-07-09 16:34:59,575][__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: 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 16:35:03,416][__main__][INFO] - GPU 0: NVIDIA RTX A6000 | TDP ≈ 300 W [2025-07-09 16:35:03,417][__main__][INFO] - Starting the Fine Tuning training process. [2025-07-09 16:35:08,634][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 16:35:08,636][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 16:35:08,841][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 16:35:08,842][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 16:35:09,027][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 16:35:09,027][transformers.tokenization_utils_base][INFO] - loading file tokenizer.json from cache at None [2025-07-09 16:35:09,027][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 16:35:09,027][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 16:35:09,028][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 16:35:09,028][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None [2025-07-09 16:35:09,028][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 16:35:09,029][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 16:35:09,064][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 16:35:09,065][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 16:35:09,085][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: True; Use Full Context: False [2025-07-09 16:35:09,804][__main__][INFO] - Token statistics for 'train' split: [2025-07-09 16:35:09,804][__main__][INFO] - Total examples: 500 [2025-07-09 16:35:09,804][__main__][INFO] - Min tokens: 512 [2025-07-09 16:35:09,804][__main__][INFO] - Max tokens: 512 [2025-07-09 16:35:09,804][__main__][INFO] - Avg tokens: 512.00 [2025-07-09 16:35:09,804][__main__][INFO] - Std tokens: 0.00 [2025-07-09 16:35:09,897][__main__][INFO] - Token statistics for 'validation' split: [2025-07-09 16:35:09,897][__main__][INFO] - Total examples: 132 [2025-07-09 16:35:09,897][__main__][INFO] - Min tokens: 512 [2025-07-09 16:35:09,897][__main__][INFO] - Max tokens: 512 [2025-07-09 16:35:09,897][__main__][INFO] - Avg tokens: 512.00 [2025-07-09 16:35:09,897][__main__][INFO] - Std tokens: 0.00 [2025-07-09 16:35:09,997][__main__][INFO] - Token statistics for 'test' split: [2025-07-09 16:35:09,997][__main__][INFO] - Total examples: 138 [2025-07-09 16:35:09,997][__main__][INFO] - Min tokens: 512 [2025-07-09 16:35:09,997][__main__][INFO] - Max tokens: 512 [2025-07-09 16:35:09,997][__main__][INFO] - Avg tokens: 512.00 [2025-07-09 16:35:09,997][__main__][INFO] - Std tokens: 0.00 [2025-07-09 16:35:09,997][__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 16:35:09,997][__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 16:35:10,203][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 16:35:10,204][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 16:35:10,602][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 16:35:10,772][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 16:35:10,772][transformers.modeling_utils][INFO] - Instantiating BertForSequenceClassification model under default dtype torch.float32. [2025-07-09 16:35:10,836][transformers.safetensors_conversion][INFO] - Attempting to create safetensors variant [2025-07-09 16:35:11,566][transformers.safetensors_conversion][INFO] - Safetensors PR exists [2025-07-09 16:35:11,644][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 16:35:11,644][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 16:35:11,649][transformers.training_args][INFO] - PyTorch: setting up devices [2025-07-09 16:35:11,673][__main__][INFO] - Total steps: 620. Number of warmup steps: 62 [2025-07-09 16:35:11,681][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 16:35:11,705][transformers.trainer][INFO] - Using auto half precision backend [2025-07-09 16:35:11,708][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text. If id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:35:11,712][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:35:11,712][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:35:11,712][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:35:12,692][transformers.trainer][INFO] - The following columns in the Training set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text. If id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:35:12,701][transformers.trainer][INFO] - ***** Running training ***** [2025-07-09 16:35:12,702][transformers.trainer][INFO] - Num examples = 500 [2025-07-09 16:35:12,702][transformers.trainer][INFO] - Num Epochs = 20 [2025-07-09 16:35:12,702][transformers.trainer][INFO] - Instantaneous batch size per device = 16 [2025-07-09 16:35:12,702][transformers.trainer][INFO] - Total train batch size (w. parallel, distributed & accumulation) = 16 [2025-07-09 16:35:12,702][transformers.trainer][INFO] - Gradient Accumulation steps = 1 [2025-07-09 16:35:12,702][transformers.trainer][INFO] - Total optimization steps = 640 [2025-07-09 16:35:12,702][transformers.trainer][INFO] - Number of trainable parameters = 108,927,750 [2025-07-09 16:35:17,362][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text. If id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:35:17,365][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:35:17,365][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:35:17,365][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:35:17,754][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-32 [2025-07-09 16:35:17,756][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-32/config.json [2025-07-09 16:35:18,660][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-32/model.safetensors [2025-07-09 16:35:24,067][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text. If id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:35:24,070][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:35:24,070][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:35:24,070][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:35:24,459][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-64 [2025-07-09 16:35:24,461][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-64/config.json [2025-07-09 16:35:25,430][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-64/model.safetensors [2025-07-09 16:35:26,382][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-32] due to args.save_total_limit [2025-07-09 16:35:30,977][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text. If id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:35:30,979][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:35:30,979][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:35:30,979][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:35:31,368][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-96 [2025-07-09 16:35:31,369][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-96/config.json [2025-07-09 16:35:32,255][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-96/model.safetensors [2025-07-09 16:35:33,185][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-64] due to args.save_total_limit [2025-07-09 16:35:37,797][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text. If id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:35:37,799][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:35:37,799][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:35:37,799][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:35:38,190][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-128 [2025-07-09 16:35:38,191][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-128/config.json [2025-07-09 16:35:39,076][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-128/model.safetensors [2025-07-09 16:35:40,014][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-96] due to args.save_total_limit [2025-07-09 16:35:44,625][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text. If id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:35:44,627][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:35:44,628][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:35:44,628][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:35:45,014][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-160 [2025-07-09 16:35:45,015][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-160/config.json [2025-07-09 16:35:45,870][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-160/model.safetensors [2025-07-09 16:35:51,343][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text. If id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:35:51,346][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:35:51,346][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:35:51,346][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:35:51,746][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-192 [2025-07-09 16:35:51,747][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-192/config.json [2025-07-09 16:35:52,712][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-192/model.safetensors [2025-07-09 16:35:53,727][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-160] due to args.save_total_limit [2025-07-09 16:35:58,347][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text. If id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:35:58,350][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:35:58,350][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:35:58,350][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:35:58,743][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-224 [2025-07-09 16:35:58,744][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-224/config.json [2025-07-09 16:35:59,854][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-224/model.safetensors [2025-07-09 16:36:00,794][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-128] due to args.save_total_limit [2025-07-09 16:36:00,867][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-192] due to args.save_total_limit [2025-07-09 16:36:05,477][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text. If id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:36:05,479][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:36:05,479][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:36:05,479][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:36:05,869][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-256 [2025-07-09 16:36:05,871][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-256/config.json [2025-07-09 16:36:06,914][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-256/model.safetensors [2025-07-09 16:36:12,561][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text. If id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:36:12,564][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:36:12,564][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:36:12,564][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:36:12,957][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-288 [2025-07-09 16:36:12,959][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-288/config.json [2025-07-09 16:36:13,858][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-288/model.safetensors [2025-07-09 16:36:14,781][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-256] due to args.save_total_limit [2025-07-09 16:36:19,417][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text. If id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:36:19,420][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:36:19,420][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:36:19,420][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:36:19,814][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-320 [2025-07-09 16:36:19,815][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-320/config.json [2025-07-09 16:36:20,855][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-320/model.safetensors [2025-07-09 16:36:21,776][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-288] due to args.save_total_limit [2025-07-09 16:36:26,423][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text. If id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:36:26,426][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:36:26,426][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:36:26,426][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:36:26,863][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-352 [2025-07-09 16:36:26,865][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-352/config.json [2025-07-09 16:36:27,838][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-352/model.safetensors [2025-07-09 16:36:28,778][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-320] due to args.save_total_limit [2025-07-09 16:36:33,427][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text. If id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:36:33,430][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:36:33,430][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:36:33,430][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:36:33,822][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-384 [2025-07-09 16:36:33,824][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-384/config.json [2025-07-09 16:36:34,855][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-384/model.safetensors [2025-07-09 16:36:35,890][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-352] due to args.save_total_limit [2025-07-09 16:36:35,974][transformers.trainer][INFO] - Training completed. Do not forget to share your model on huggingface.co/models =) [2025-07-09 16:36:35,975][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-224 (score: 0.47031922525107606). [2025-07-09 16:36:36,115][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-34-59/results/checkpoint-384] due to args.save_total_limit [2025-07-09 16:36:36,203][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text. If id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:36:36,206][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:36:36,206][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:36:36,206][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:36:36,624][__main__][INFO] - Training completed successfully. [2025-07-09 16:36:36,625][__main__][INFO] - Running on Test [2025-07-09 16:36:36,625][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text. If id, essay_year, id_prompt, reference, grades, prompt, essay_text, supporting_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:36:36,627][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:36:36,627][transformers.trainer][INFO] - Num examples = 138 [2025-07-09 16:36:36,627][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:36:37,039][__main__][INFO] - Test metrics: {'eval_loss': 1.9964232444763184, 'eval_model_preparation_time': 0.0021, 'eval_accuracy': 0.3115942028985507, 'eval_RMSE': 51.07539184552491, 'eval_QWK': 0.3491384731480316, 'eval_HDIV': 0.050724637681159424, 'eval_Macro_F1': 0.21826640792158034, 'eval_Micro_F1': 0.3115942028985507, 'eval_Weighted_F1': 0.26630624081898446, 'eval_TP_0': 0, 'eval_TN_0': 137, 'eval_FP_0': 0, 'eval_FN_0': 1, 'eval_TP_1': 0, 'eval_TN_1': 107, 'eval_FP_1': 2, 'eval_FN_1': 29, 'eval_TP_2': 14, 'eval_TN_2': 94, 'eval_FP_2': 26, 'eval_FN_2': 4, 'eval_TP_3': 18, 'eval_TN_3': 57, 'eval_FP_3': 36, 'eval_FN_3': 27, 'eval_TP_4': 9, 'eval_TN_4': 81, 'eval_FP_4': 19, 'eval_FN_4': 29, 'eval_TP_5': 2, 'eval_TN_5': 119, 'eval_FP_5': 12, 'eval_FN_5': 5, 'eval_runtime': 0.4065, 'eval_samples_per_second': 339.468, 'eval_steps_per_second': 22.139, 'epoch': 12.0} [2025-07-09 16:36:37,040][transformers.trainer][INFO] - Saving model checkpoint to ./results/best_model [2025-07-09 16:36:37,041][transformers.configuration_utils][INFO] - Configuration saved in ./results/best_model/config.json [2025-07-09 16:36:37,950][transformers.modeling_utils][INFO] - Model weights saved in ./results/best_model/model.safetensors [2025-07-09 16:36:37,952][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/best_model/tokenizer_config.json [2025-07-09 16:36:37,953][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/best_model/special_tokens_map.json [2025-07-09 16:36:37,966][__main__][INFO] - Model and tokenizer saved to ./results/best_model [2025-07-09 16:36:37,970][__main__][INFO] - Fine Tuning Finished. [2025-07-09 16:36:38,483][__main__][INFO] - Total emissions: 0.0020 kg CO2eq