[2025-07-09 16:57:42,869][__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/C5 logging_dir: ./logs/bertimbau_large/C5 best_model_dir: ./results/bertimbau_large/C5/best_model tokenizer: name: neuralmind/bert-large-portuguese-cased dataset: grade_index: 4 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 16:57:46,732][__main__][INFO] - GPU 0: NVIDIA RTX A6000 | TDP ≈ 300 W [2025-07-09 16:57:46,733][__main__][INFO] - Starting the Fine Tuning training process. [2025-07-09 16:57:52,183][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 16:57:52,184][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 16:57:52,386][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 16:57:52,387][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 16:57:52,630][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 16:57:52,631][transformers.tokenization_utils_base][INFO] - loading file tokenizer.json from cache at None [2025-07-09 16:57:52,631][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 16:57:52,631][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 16:57:52,631][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 16:57:52,631][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None [2025-07-09 16:57:52,631][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 16:57:52,632][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 16:57:52,662][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 16:57:52,663][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 16:57:52,682][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: True; Use Full Context: False [2025-07-09 16:57:53,334][__main__][INFO] - Token statistics for 'train' split: [2025-07-09 16:57:53,334][__main__][INFO] - Total examples: 500 [2025-07-09 16:57:53,334][__main__][INFO] - Min tokens: 512 [2025-07-09 16:57:53,334][__main__][INFO] - Max tokens: 512 [2025-07-09 16:57:53,334][__main__][INFO] - Avg tokens: 512.00 [2025-07-09 16:57:53,335][__main__][INFO] - Std tokens: 0.00 [2025-07-09 16:57:53,430][__main__][INFO] - Token statistics for 'validation' split: [2025-07-09 16:57:53,431][__main__][INFO] - Total examples: 132 [2025-07-09 16:57:53,431][__main__][INFO] - Min tokens: 512 [2025-07-09 16:57:53,431][__main__][INFO] - Max tokens: 512 [2025-07-09 16:57:53,431][__main__][INFO] - Avg tokens: 512.00 [2025-07-09 16:57:53,431][__main__][INFO] - Std tokens: 0.00 [2025-07-09 16:57:53,529][__main__][INFO] - Token statistics for 'test' split: [2025-07-09 16:57:53,529][__main__][INFO] - Total examples: 138 [2025-07-09 16:57:53,529][__main__][INFO] - Min tokens: 512 [2025-07-09 16:57:53,529][__main__][INFO] - Max tokens: 512 [2025-07-09 16:57:53,529][__main__][INFO] - Avg tokens: 512.00 [2025-07-09 16:57:53,529][__main__][INFO] - Std tokens: 0.00 [2025-07-09 16:57:53,529][__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 16:57:53,529][__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 16:57:53,738][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 16:57:53,738][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 16:57:54,136][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 16:57:54,377][transformers.safetensors_conversion][INFO] - Attempting to create safetensors variant [2025-07-09 16:57:55,046][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 16:57:55,046][transformers.modeling_utils][INFO] - Instantiating BertForSequenceClassification model under default dtype torch.float32. [2025-07-09 16:57:55,324][transformers.safetensors_conversion][INFO] - Safetensors PR exists [2025-07-09 16:57:56,969][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 16:57:56,970][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 16:57:56,979][transformers.training_args][INFO] - PyTorch: setting up devices [2025-07-09 16:57:57,001][__main__][INFO] - Total steps: 620. Number of warmup steps: 62 [2025-07-09 16:57:57,009][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 16:57:57,035][transformers.trainer][INFO] - Using auto half precision backend [2025-07-09 16:57:57,038][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:57:57,044][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:57:57,044][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:57:57,045][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:57:58,469][transformers.trainer][INFO] - The following columns in the Training set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:57:58,484][transformers.trainer][INFO] - ***** Running training ***** [2025-07-09 16:57:58,484][transformers.trainer][INFO] - Num examples = 500 [2025-07-09 16:57:58,484][transformers.trainer][INFO] - Num Epochs = 20 [2025-07-09 16:57:58,484][transformers.trainer][INFO] - Instantaneous batch size per device = 16 [2025-07-09 16:57:58,484][transformers.trainer][INFO] - Total train batch size (w. parallel, distributed & accumulation) = 16 [2025-07-09 16:57:58,484][transformers.trainer][INFO] - Gradient Accumulation steps = 1 [2025-07-09 16:57:58,484][transformers.trainer][INFO] - Total optimization steps = 640 [2025-07-09 16:57:58,485][transformers.trainer][INFO] - Number of trainable parameters = 334,402,566 [2025-07-09 16:58:10,840][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:58:10,842][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:58:10,843][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:58:10,843][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:58:11,763][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-32 [2025-07-09 16:58:11,765][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-32/config.json [2025-07-09 16:58:14,552][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-32/model.safetensors [2025-07-09 16:58:29,916][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:58:29,920][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:58:29,920][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:58:29,920][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:58:30,836][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-64 [2025-07-09 16:58:30,837][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-64/config.json [2025-07-09 16:58:33,080][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-64/model.safetensors [2025-07-09 16:58:48,106][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:58:48,110][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:58:48,110][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:58:48,110][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:58:49,026][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-96 [2025-07-09 16:58:49,028][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-96/config.json [2025-07-09 16:58:50,997][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-96/model.safetensors [2025-07-09 16:58:53,331][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-32] due to args.save_total_limit [2025-07-09 16:58:53,540][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-64] due to args.save_total_limit [2025-07-09 16:59:06,189][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:59:06,193][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:59:06,193][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:59:06,193][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:59:07,110][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-128 [2025-07-09 16:59:07,112][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-128/config.json [2025-07-09 16:59:09,263][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-128/model.safetensors [2025-07-09 16:59:23,878][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:59:23,880][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:59:23,881][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:59:23,881][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:59:24,800][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-160 [2025-07-09 16:59:24,801][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-160/config.json [2025-07-09 16:59:27,049][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-160/model.safetensors [2025-07-09 16:59:29,822][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-128] due to args.save_total_limit [2025-07-09 16:59:42,490][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 16:59:42,494][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 16:59:42,494][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 16:59:42,494][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 16:59:43,446][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-192 [2025-07-09 16:59:43,448][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-192/config.json [2025-07-09 16:59:45,659][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-192/model.safetensors [2025-07-09 16:59:47,967][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-96] due to args.save_total_limit [2025-07-09 16:59:48,167][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-160] due to args.save_total_limit [2025-07-09 17:00:00,675][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:00:00,679][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:00:00,679][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:00:00,679][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:00:01,594][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-224 [2025-07-09 17:00:01,596][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-224/config.json [2025-07-09 17:00:04,095][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-224/model.safetensors [2025-07-09 17:00:18,859][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:00:18,863][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:00:18,863][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:00:18,863][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:00:19,813][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-256 [2025-07-09 17:00:19,816][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-256/config.json [2025-07-09 17:00:22,407][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-256/model.safetensors [2025-07-09 17:00:25,011][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-224] due to args.save_total_limit [2025-07-09 17:00:37,587][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:00:37,589][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:00:37,589][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:00:37,589][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:00:38,507][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-288 [2025-07-09 17:00:38,509][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-288/config.json [2025-07-09 17:00:40,642][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-288/model.safetensors [2025-07-09 17:00:42,927][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-256] due to args.save_total_limit [2025-07-09 17:00:55,513][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:00:55,516][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:00:55,516][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:00:55,516][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:00:56,443][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-320 [2025-07-09 17:00:56,445][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-320/config.json [2025-07-09 17:00:58,820][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-320/model.safetensors [2025-07-09 17:01:01,234][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-288] due to args.save_total_limit [2025-07-09 17:01:13,788][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:01:13,791][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:01:13,792][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:01:13,792][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:01:14,713][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-352 [2025-07-09 17:01:14,715][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-352/config.json [2025-07-09 17:01:16,746][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-352/model.safetensors [2025-07-09 17:01:19,071][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-320] due to args.save_total_limit [2025-07-09 17:01:19,334][transformers.trainer][INFO] - Training completed. Do not forget to share your model on huggingface.co/models =) [2025-07-09 17:01:19,334][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-192 (score: 0.5028286803591193). [2025-07-09 17:01:19,785][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-352] due to args.save_total_limit [2025-07-09 17:01:20,049][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:01:20,052][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:01:20,052][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:01:20,052][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:01:20,950][__main__][INFO] - Training completed successfully. [2025-07-09 17:01:20,950][__main__][INFO] - Running on Test [2025-07-09 17:01:20,951][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:01:20,953][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:01:20,953][transformers.trainer][INFO] - Num examples = 138 [2025-07-09 17:01:20,953][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:01:21,879][__main__][INFO] - Test metrics: {'eval_loss': 1.5725419521331787, 'eval_model_preparation_time': 0.0037, 'eval_accuracy': 0.41304347826086957, 'eval_RMSE': 59.75796593554388, 'eval_QWK': 0.45915406932356084, 'eval_HDIV': 0.14492753623188404, 'eval_Macro_F1': 0.3013676792556103, 'eval_Micro_F1': 0.41304347826086957, 'eval_Weighted_F1': 0.3597310868375336, 'eval_TP_0': 5, 'eval_TN_0': 115, 'eval_FP_0': 1, 'eval_FN_0': 17, 'eval_TP_1': 6, 'eval_TN_1': 94, 'eval_FP_1': 12, 'eval_FN_1': 26, 'eval_TP_2': 14, 'eval_TN_2': 82, 'eval_FP_2': 32, 'eval_FN_2': 10, 'eval_TP_3': 3, 'eval_TN_3': 112, 'eval_FP_3': 1, 'eval_FN_3': 22, 'eval_TP_4': 29, 'eval_TN_4': 71, 'eval_FP_4': 35, 'eval_FN_4': 3, 'eval_TP_5': 0, 'eval_TN_5': 135, 'eval_FP_5': 0, 'eval_FN_5': 3, 'eval_runtime': 0.9202, 'eval_samples_per_second': 149.972, 'eval_steps_per_second': 9.781, 'epoch': 11.0} [2025-07-09 17:01:21,880][transformers.trainer][INFO] - Saving model checkpoint to ./results/bertimbau_large/C5/best_model [2025-07-09 17:01:21,881][transformers.configuration_utils][INFO] - Configuration saved in ./results/bertimbau_large/C5/best_model/config.json [2025-07-09 17:01:23,984][transformers.modeling_utils][INFO] - Model weights saved in ./results/bertimbau_large/C5/best_model/model.safetensors [2025-07-09 17:01:23,987][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/bertimbau_large/C5/best_model/tokenizer_config.json [2025-07-09 17:01:23,987][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/bertimbau_large/C5/best_model/special_tokens_map.json [2025-07-09 17:01:23,999][__main__][INFO] - Model and tokenizer saved to ./results/bertimbau_large/C5/best_model [2025-07-09 17:01:24,003][__main__][INFO] - Fine Tuning Finished. [2025-07-09 17:01:24,515][__main__][INFO] - Total emissions: 0.0048 kg CO2eq