[2025-07-09 16:53:54,191][__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-large-portuguese-cased type: encoder_classification num_labels: 6 output_dir: ./results/bertimbau_large/C4 logging_dir: ./logs/bertimbau_large/C4 best_model_dir: ./results/bertimbau_large/C4/best_model tokenizer: name: neuralmind/bert-large-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 16:53:58,044][__main__][INFO] - GPU 0: NVIDIA RTX A6000 | TDP ≈ 300 W [2025-07-09 16:53:58,044][__main__][INFO] - Starting the Fine Tuning training process. [2025-07-09 16:54:05,028][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/config.json [2025-07-09 16:54:05,030][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": 1024, "initializer_range": 0.02, "intermediate_size": 4096, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "num_attention_heads": 16, "num_hidden_layers": 24, "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 16:54:05,245][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/config.json [2025-07-09 16:54:05,246][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": 1024, "initializer_range": 0.02, "intermediate_size": 4096, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "num_attention_heads": 16, "num_hidden_layers": 24, "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 16:54:05,442][transformers.tokenization_utils_base][INFO] - loading file vocab.txt from cache at /tmp/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/vocab.txt [2025-07-09 16:54:05,442][transformers.tokenization_utils_base][INFO] - loading file tokenizer.json from cache at None [2025-07-09 16:54:05,442][transformers.tokenization_utils_base][INFO] - loading file added_tokens.json from cache at /tmp/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/added_tokens.json [2025-07-09 16:54:05,442][transformers.tokenization_utils_base][INFO] - loading file special_tokens_map.json from cache at /tmp/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/special_tokens_map.json [2025-07-09 16:54:05,442][transformers.tokenization_utils_base][INFO] - loading file tokenizer_config.json from cache at /tmp/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/tokenizer_config.json [2025-07-09 16:54:05,442][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None [2025-07-09 16:54:05,442][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/config.json [2025-07-09 16:54:05,443][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": 1024, "initializer_range": 0.02, "intermediate_size": 4096, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "num_attention_heads": 16, "num_hidden_layers": 24, "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 16:54:05,483][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/config.json [2025-07-09 16:54:05,484][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": 1024, "initializer_range": 0.02, "intermediate_size": 4096, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "num_attention_heads": 16, "num_hidden_layers": 24, "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 16:54:05,506][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: True; Use Full Context: False [2025-07-09 16:54:06,320][__main__][INFO] - Token statistics for 'train' split: [2025-07-09 16:54:06,320][__main__][INFO] - Total examples: 500 [2025-07-09 16:54:06,320][__main__][INFO] - Min tokens: 512 [2025-07-09 16:54:06,320][__main__][INFO] - Max tokens: 512 [2025-07-09 16:54:06,320][__main__][INFO] - Avg tokens: 512.00 [2025-07-09 16:54:06,320][__main__][INFO] - Std tokens: 0.00 [2025-07-09 16:54:06,437][__main__][INFO] - Token statistics for 'validation' split: [2025-07-09 16:54:06,438][__main__][INFO] - Total examples: 132 [2025-07-09 16:54:06,438][__main__][INFO] - Min tokens: 512 [2025-07-09 16:54:06,438][__main__][INFO] - Max tokens: 512 [2025-07-09 16:54:06,438][__main__][INFO] - Avg tokens: 512.00 [2025-07-09 16:54:06,438][__main__][INFO] - Std tokens: 0.00 [2025-07-09 16:54:06,550][__main__][INFO] - Token statistics for 'test' split: [2025-07-09 16:54:06,550][__main__][INFO] - Total examples: 138 [2025-07-09 16:54:06,550][__main__][INFO] - Min tokens: 512 [2025-07-09 16:54:06,550][__main__][INFO] - Max tokens: 512 [2025-07-09 16:54:06,550][__main__][INFO] - Avg tokens: 512.00 [2025-07-09 16:54:06,550][__main__][INFO] - Std tokens: 0.00 [2025-07-09 16:54:06,550][__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 16:54:06,550][__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 16:54:06,771][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/config.json [2025-07-09 16:54:06,773][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": 1024, "id2label": { "0": 0, "1": 40, "2": 80, "3": 120, "4": 160, "5": 200 }, "initializer_range": 0.02, "intermediate_size": 4096, "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": 16, "num_hidden_layers": 24, "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 16:54:07,183][transformers.modeling_utils][INFO] - loading weights file pytorch_model.bin from cache at /tmp/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/pytorch_model.bin [2025-07-09 16:54:07,422][transformers.safetensors_conversion][INFO] - Attempting to create safetensors variant [2025-07-09 16:54:07,589][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 16:54:07,589][transformers.modeling_utils][INFO] - Instantiating BertForSequenceClassification model under default dtype torch.float32. [2025-07-09 16:54:08,078][transformers.safetensors_conversion][INFO] - Safetensors PR exists [2025-07-09 16:54:09,909][transformers.modeling_utils][INFO] - Some weights of the model checkpoint at neuralmind/bert-large-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 16:54:09,910][transformers.modeling_utils][WARNING] - Some weights of BertForSequenceClassification were not initialized from the model checkpoint at neuralmind/bert-large-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 16:54:09,918][transformers.training_args][INFO] - PyTorch: setting up devices [2025-07-09 16:54:09,939][__main__][INFO] - Total steps: 620. Number of warmup steps: 62 [2025-07-09 16:54:09,947][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 16:54:09,970][transformers.trainer][INFO] - Using auto half precision backend [2025-07-09 16:54:09,972][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, id_prompt, essay_year, reference, grades, supporting_text, essay_text. If id, prompt, id_prompt, essay_year, reference, grades, supporting_text, essay_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:54:09,979][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:54:09,979][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:54:09,979][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:54:11,341][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, id_prompt, essay_year, reference, grades, supporting_text, essay_text. If id, prompt, id_prompt, essay_year, reference, grades, supporting_text, essay_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:54:11,356][transformers.trainer][INFO] - ***** Running training ***** [2025-07-09 16:54:11,356][transformers.trainer][INFO] - Num examples = 500 [2025-07-09 16:54:11,356][transformers.trainer][INFO] - Num Epochs = 20 [2025-07-09 16:54:11,356][transformers.trainer][INFO] - Instantaneous batch size per device = 16 [2025-07-09 16:54:11,356][transformers.trainer][INFO] - Total train batch size (w. parallel, distributed & accumulation) = 16 [2025-07-09 16:54:11,356][transformers.trainer][INFO] - Gradient Accumulation steps = 1 [2025-07-09 16:54:11,356][transformers.trainer][INFO] - Total optimization steps = 640 [2025-07-09 16:54:11,357][transformers.trainer][INFO] - Number of trainable parameters = 334,402,566 [2025-07-09 16:54:28,115][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, id_prompt, essay_year, reference, grades, supporting_text, essay_text. If id, prompt, id_prompt, essay_year, reference, grades, supporting_text, essay_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:54:28,118][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:54:28,118][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:54:28,119][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:54:29,030][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-32 [2025-07-09 16:54:29,031][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-32/config.json [2025-07-09 16:54:31,350][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-32/model.safetensors [2025-07-09 16:54:52,432][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, id_prompt, essay_year, reference, grades, supporting_text, essay_text. If id, prompt, id_prompt, essay_year, reference, grades, supporting_text, essay_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:54:52,435][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:54:52,435][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:54:52,435][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:54:53,404][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-64 [2025-07-09 16:54:53,406][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-64/config.json [2025-07-09 16:54:55,613][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-64/model.safetensors [2025-07-09 16:55:10,328][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, id_prompt, essay_year, reference, grades, supporting_text, essay_text. If id, prompt, id_prompt, essay_year, reference, grades, supporting_text, essay_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:55:10,331][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:55:10,331][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:55:10,331][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:55:11,245][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-96 [2025-07-09 16:55:11,247][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-96/config.json [2025-07-09 16:55:13,769][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-96/model.safetensors [2025-07-09 16:55:16,613][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-64] due to args.save_total_limit [2025-07-09 16:55:29,236][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, id_prompt, essay_year, reference, grades, supporting_text, essay_text. If id, prompt, id_prompt, essay_year, reference, grades, supporting_text, essay_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:55:29,240][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:55:29,240][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:55:29,240][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:55:30,191][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-128 [2025-07-09 16:55:30,193][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-128/config.json [2025-07-09 16:55:32,526][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-128/model.safetensors [2025-07-09 16:55:34,980][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-32] due to args.save_total_limit [2025-07-09 16:55:35,242][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-96] due to args.save_total_limit [2025-07-09 16:55:47,812][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, id_prompt, essay_year, reference, grades, supporting_text, essay_text. If id, prompt, id_prompt, essay_year, reference, grades, supporting_text, essay_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:55:47,815][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:55:47,815][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:55:47,815][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:55:48,732][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-160 [2025-07-09 16:55:48,734][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-160/config.json [2025-07-09 16:55:51,184][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-160/model.safetensors [2025-07-09 16:55:54,022][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-128] due to args.save_total_limit [2025-07-09 16:56:06,659][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, id_prompt, essay_year, reference, grades, supporting_text, essay_text. If id, prompt, id_prompt, essay_year, reference, grades, supporting_text, essay_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:56:06,663][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:56:06,663][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:56:06,663][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:56:07,584][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-192 [2025-07-09 16:56:07,585][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-192/config.json [2025-07-09 16:56:09,835][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-192/model.safetensors [2025-07-09 16:56:24,827][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, id_prompt, essay_year, reference, grades, supporting_text, essay_text. If id, prompt, id_prompt, essay_year, reference, grades, supporting_text, essay_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:56:24,831][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:56:24,831][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:56:24,831][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:56:25,790][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-224 [2025-07-09 16:56:25,792][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-224/config.json [2025-07-09 16:56:27,918][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-224/model.safetensors [2025-07-09 16:56:30,615][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-192] due to args.save_total_limit [2025-07-09 16:56:43,124][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, id_prompt, essay_year, reference, grades, supporting_text, essay_text. If id, prompt, id_prompt, essay_year, reference, grades, supporting_text, essay_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:56:43,127][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:56:43,127][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:56:43,127][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:56:44,044][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-256 [2025-07-09 16:56:44,046][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-256/config.json [2025-07-09 16:56:46,321][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-256/model.safetensors [2025-07-09 16:56:48,768][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-224] due to args.save_total_limit [2025-07-09 16:57:01,389][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, id_prompt, essay_year, reference, grades, supporting_text, essay_text. If id, prompt, id_prompt, essay_year, reference, grades, supporting_text, essay_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:57:01,395][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:57:01,395][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:57:01,395][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:57:02,344][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-288 [2025-07-09 16:57:02,346][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-288/config.json [2025-07-09 16:57:04,823][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-288/model.safetensors [2025-07-09 16:57:07,652][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-256] due to args.save_total_limit [2025-07-09 16:57:20,291][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, id_prompt, essay_year, reference, grades, supporting_text, essay_text. If id, prompt, id_prompt, essay_year, reference, grades, supporting_text, essay_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:57:20,294][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:57:20,294][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:57:20,294][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:57:21,235][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-320 [2025-07-09 16:57:21,237][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-320/config.json [2025-07-09 16:57:23,711][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-320/model.safetensors [2025-07-09 16:57:26,609][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-288] due to args.save_total_limit [2025-07-09 16:57:26,868][transformers.trainer][INFO] - Training completed. Do not forget to share your model on huggingface.co/models =) [2025-07-09 16:57:26,868][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-160 (score: 0.5419023136246788). [2025-07-09 16:57:27,635][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-53-54/results/bertimbau_large/C4/checkpoint-320] due to args.save_total_limit [2025-07-09 16:57:27,895][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, id_prompt, essay_year, reference, grades, supporting_text, essay_text. If id, prompt, id_prompt, essay_year, reference, grades, supporting_text, essay_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:57:27,900][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:57:27,900][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:57:27,900][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:57:28,812][__main__][INFO] - Training completed successfully. [2025-07-09 16:57:28,812][__main__][INFO] - Running on Test [2025-07-09 16:57:28,812][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, id_prompt, essay_year, reference, grades, supporting_text, essay_text. If id, prompt, id_prompt, essay_year, reference, grades, supporting_text, essay_text are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:57:28,816][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:57:28,816][transformers.trainer][INFO] - Num examples = 138 [2025-07-09 16:57:28,816][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:57:29,741][__main__][INFO] - Test metrics: {'eval_loss': 1.184962272644043, 'eval_model_preparation_time': 0.0037, 'eval_accuracy': 0.5869565217391305, 'eval_RMSE': 29.29114225312413, 'eval_QWK': 0.5985849056603774, 'eval_HDIV': 0.007246376811594235, 'eval_Macro_F1': 0.45502820381025977, 'eval_Micro_F1': 0.5869565217391305, 'eval_Weighted_F1': 0.6030619269196934, 'eval_TP_0': 0, 'eval_TN_0': 137, 'eval_FP_0': 0, 'eval_FN_0': 1, 'eval_TP_1': 1, 'eval_TN_1': 136, 'eval_FP_1': 1, 'eval_FN_1': 0, 'eval_TP_2': 5, 'eval_TN_2': 114, 'eval_FP_2': 15, 'eval_FN_2': 4, 'eval_TP_3': 42, 'eval_TN_3': 52, 'eval_FP_3': 10, 'eval_FN_3': 34, 'eval_TP_4': 29, 'eval_TN_4': 69, 'eval_FP_4': 23, 'eval_FN_4': 17, 'eval_TP_5': 4, 'eval_TN_5': 125, 'eval_FP_5': 8, 'eval_FN_5': 1, 'eval_runtime': 0.9188, 'eval_samples_per_second': 150.196, 'eval_steps_per_second': 9.795, 'epoch': 10.0} [2025-07-09 16:57:29,741][transformers.trainer][INFO] - Saving model checkpoint to ./results/bertimbau_large/C4/best_model [2025-07-09 16:57:29,743][transformers.configuration_utils][INFO] - Configuration saved in ./results/bertimbau_large/C4/best_model/config.json [2025-07-09 16:57:31,824][transformers.modeling_utils][INFO] - Model weights saved in ./results/bertimbau_large/C4/best_model/model.safetensors [2025-07-09 16:57:31,827][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/bertimbau_large/C4/best_model/tokenizer_config.json [2025-07-09 16:57:31,827][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/bertimbau_large/C4/best_model/special_tokens_map.json [2025-07-09 16:57:31,838][__main__][INFO] - Model and tokenizer saved to ./results/bertimbau_large/C4/best_model [2025-07-09 16:57:31,842][__main__][INFO] - Fine Tuning Finished. [2025-07-09 16:57:32,353][__main__][INFO] - Total emissions: 0.0045 kg CO2eq