[2025-07-09 17:14:13,621][__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: google-bert/bert-base-multilingual-cased type: encoder_classification num_labels: 6 output_dir: ./results/ logging_dir: ./logs/ best_model_dir: ./results/best_model tokenizer: name: google-bert/bert-base-multilingual-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 17:14:17,504][__main__][INFO] - GPU 0: NVIDIA RTX A6000 | TDP ≈ 300 W [2025-07-09 17:14:17,504][__main__][INFO] - Starting the Fine Tuning training process. [2025-07-09 17:14:23,069][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--google-bert--bert-base-multilingual-cased/snapshots/3f076fdb1ab68d5b2880cb87a0886f315b8146f8/config.json [2025-07-09 17:14:23,070][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, "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": 119547 } [2025-07-09 17:14:23,265][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--google-bert--bert-base-multilingual-cased/snapshots/3f076fdb1ab68d5b2880cb87a0886f315b8146f8/config.json [2025-07-09 17:14:23,265][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, "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": 119547 } [2025-07-09 17:14:23,456][transformers.tokenization_utils_base][INFO] - loading file vocab.txt from cache at /tmp/models--google-bert--bert-base-multilingual-cased/snapshots/3f076fdb1ab68d5b2880cb87a0886f315b8146f8/vocab.txt [2025-07-09 17:14:23,456][transformers.tokenization_utils_base][INFO] - loading file tokenizer.json from cache at /tmp/models--google-bert--bert-base-multilingual-cased/snapshots/3f076fdb1ab68d5b2880cb87a0886f315b8146f8/tokenizer.json [2025-07-09 17:14:23,456][transformers.tokenization_utils_base][INFO] - loading file added_tokens.json from cache at None [2025-07-09 17:14:23,456][transformers.tokenization_utils_base][INFO] - loading file special_tokens_map.json from cache at None [2025-07-09 17:14:23,456][transformers.tokenization_utils_base][INFO] - loading file tokenizer_config.json from cache at /tmp/models--google-bert--bert-base-multilingual-cased/snapshots/3f076fdb1ab68d5b2880cb87a0886f315b8146f8/tokenizer_config.json [2025-07-09 17:14:23,456][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None [2025-07-09 17:14:23,456][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--google-bert--bert-base-multilingual-cased/snapshots/3f076fdb1ab68d5b2880cb87a0886f315b8146f8/config.json [2025-07-09 17:14:23,457][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, "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": 119547 } [2025-07-09 17:14:23,736][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: True; Use Full Context: False [2025-07-09 17:14:24,512][__main__][INFO] - Token statistics for 'train' split: [2025-07-09 17:14:24,512][__main__][INFO] - Total examples: 500 [2025-07-09 17:14:24,513][__main__][INFO] - Min tokens: 512 [2025-07-09 17:14:24,513][__main__][INFO] - Max tokens: 512 [2025-07-09 17:14:24,513][__main__][INFO] - Avg tokens: 512.00 [2025-07-09 17:14:24,513][__main__][INFO] - Std tokens: 0.00 [2025-07-09 17:14:24,629][__main__][INFO] - Token statistics for 'validation' split: [2025-07-09 17:14:24,630][__main__][INFO] - Total examples: 132 [2025-07-09 17:14:24,630][__main__][INFO] - Min tokens: 512 [2025-07-09 17:14:24,630][__main__][INFO] - Max tokens: 512 [2025-07-09 17:14:24,630][__main__][INFO] - Avg tokens: 512.00 [2025-07-09 17:14:24,630][__main__][INFO] - Std tokens: 0.00 [2025-07-09 17:14:24,746][__main__][INFO] - Token statistics for 'test' split: [2025-07-09 17:14:24,747][__main__][INFO] - Total examples: 138 [2025-07-09 17:14:24,747][__main__][INFO] - Min tokens: 512 [2025-07-09 17:14:24,747][__main__][INFO] - Max tokens: 512 [2025-07-09 17:14:24,747][__main__][INFO] - Avg tokens: 512.00 [2025-07-09 17:14:24,747][__main__][INFO] - Std tokens: 0.00 [2025-07-09 17:14:24,747][__main__][INFO] - If token statistics are the same (max, avg, min) keep in mind that this is due to batched tokenization and padding. [2025-07-09 17:14:24,747][__main__][INFO] - Model max length: 512. If it is the same as stats, then there is a high chance that sequences are being truncated. [2025-07-09 17:14:24,973][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--google-bert--bert-base-multilingual-cased/snapshots/3f076fdb1ab68d5b2880cb87a0886f315b8146f8/config.json [2025-07-09 17:14:24,974][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, "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": 119547 } [2025-07-09 17:14:25,166][transformers.modeling_utils][INFO] - loading weights file model.safetensors from cache at /tmp/models--google-bert--bert-base-multilingual-cased/snapshots/3f076fdb1ab68d5b2880cb87a0886f315b8146f8/model.safetensors [2025-07-09 17:14:25,174][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 17:14:25,175][transformers.modeling_utils][INFO] - Instantiating BertForSequenceClassification model under default dtype torch.float32. [2025-07-09 17:14:25,371][transformers.modeling_utils][INFO] - A pretrained model of type `BertForSequenceClassification` contains parameters that have been renamed internally (a few are listed below but more are present in the model): * `cls.predictions.transform.LayerNorm.beta` -> `cls.predictions.transform.LayerNorm.bias` * `cls.predictions.transform.LayerNorm.gamma` -> `cls.predictions.transform.LayerNorm.weight` If you are using a model from the Hub, consider submitting a PR to adjust these weights and help future users. [2025-07-09 17:14:26,303][transformers.modeling_utils][INFO] - Some weights of the model checkpoint at google-bert/bert-base-multilingual-cased were not used when initializing BertForSequenceClassification: ['cls.predictions.bias', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.dense.weight', 'cls.seq_relationship.bias', 'cls.seq_relationship.weight'] - This IS expected if you are initializing BertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). [2025-07-09 17:14:26,303][transformers.modeling_utils][WARNING] - Some weights of BertForSequenceClassification were not initialized from the model checkpoint at google-bert/bert-base-multilingual-cased and are newly initialized: ['classifier.bias', 'classifier.weight'] You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. [2025-07-09 17:14:26,309][transformers.training_args][INFO] - PyTorch: setting up devices [2025-07-09 17:14:26,331][__main__][INFO] - Total steps: 620. Number of warmup steps: 62 [2025-07-09 17:14:26,339][transformers.trainer][INFO] - You have loaded a model on multiple GPUs. `is_model_parallel` attribute will be force-set to `True` to avoid any unexpected behavior such as device placement mismatching. [2025-07-09 17:14:26,364][transformers.trainer][INFO] - Using auto half precision backend [2025-07-09 17:14:26,367][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:14:26,372][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:14:26,372][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:14:26,372][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:14:27,295][transformers.trainer][INFO] - The following columns in the Training set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:14:27,305][transformers.trainer][INFO] - ***** Running training ***** [2025-07-09 17:14:27,305][transformers.trainer][INFO] - Num examples = 500 [2025-07-09 17:14:27,305][transformers.trainer][INFO] - Num Epochs = 20 [2025-07-09 17:14:27,305][transformers.trainer][INFO] - Instantaneous batch size per device = 16 [2025-07-09 17:14:27,305][transformers.trainer][INFO] - Total train batch size (w. parallel, distributed & accumulation) = 16 [2025-07-09 17:14:27,305][transformers.trainer][INFO] - Gradient Accumulation steps = 1 [2025-07-09 17:14:27,305][transformers.trainer][INFO] - Total optimization steps = 640 [2025-07-09 17:14:27,305][transformers.trainer][INFO] - Number of trainable parameters = 177,858,054 [2025-07-09 17:14:32,297][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:14:32,300][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:14:32,300][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:14:32,300][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:14:32,694][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-32 [2025-07-09 17:14:32,695][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-32/config.json [2025-07-09 17:14:33,919][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-32/model.safetensors [2025-07-09 17:14:40,425][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:14:40,429][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:14:40,429][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:14:40,429][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:14:40,820][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-64 [2025-07-09 17:14:40,821][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-64/config.json [2025-07-09 17:14:42,135][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-64/model.safetensors [2025-07-09 17:14:43,757][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-32] due to args.save_total_limit [2025-07-09 17:14:48,774][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:14:48,777][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:14:48,777][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:14:48,777][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:14:49,177][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-96 [2025-07-09 17:14:49,179][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-96/config.json [2025-07-09 17:14:50,716][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-96/model.safetensors [2025-07-09 17:14:57,646][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:14:57,649][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:14:57,649][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:14:57,649][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:14:58,049][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-128 [2025-07-09 17:14:58,050][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-128/config.json [2025-07-09 17:14:59,457][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-128/model.safetensors [2025-07-09 17:15:01,555][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-96] due to args.save_total_limit [2025-07-09 17:15:06,640][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:15:06,643][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:15:06,643][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:15:06,643][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:15:07,046][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-160 [2025-07-09 17:15:07,048][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-160/config.json [2025-07-09 17:15:08,445][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-160/model.safetensors [2025-07-09 17:15:10,671][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-64] due to args.save_total_limit [2025-07-09 17:15:10,793][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-128] due to args.save_total_limit [2025-07-09 17:15:15,813][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:15:15,817][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:15:15,817][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:15:15,817][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:15:16,219][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-192 [2025-07-09 17:15:16,221][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-192/config.json [2025-07-09 17:15:17,720][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-192/model.safetensors [2025-07-09 17:15:25,077][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:15:25,080][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:15:25,081][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:15:25,081][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:15:25,478][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-224 [2025-07-09 17:15:25,479][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-224/config.json [2025-07-09 17:15:26,845][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-224/model.safetensors [2025-07-09 17:15:29,329][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-192] due to args.save_total_limit [2025-07-09 17:15:34,302][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:15:34,305][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:15:34,305][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:15:34,305][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:15:34,698][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-256 [2025-07-09 17:15:34,699][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-256/config.json [2025-07-09 17:15:35,873][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-256/model.safetensors [2025-07-09 17:15:37,772][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-160] due to args.save_total_limit [2025-07-09 17:15:37,945][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-224] due to args.save_total_limit [2025-07-09 17:15:42,919][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:15:42,922][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:15:42,922][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:15:42,922][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:15:43,317][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-288 [2025-07-09 17:15:43,319][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-288/config.json [2025-07-09 17:15:44,554][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-288/model.safetensors [2025-07-09 17:15:51,406][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:15:51,408][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:15:51,408][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:15:51,408][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:15:51,805][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-320 [2025-07-09 17:15:51,806][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-320/config.json [2025-07-09 17:15:53,422][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-320/model.safetensors [2025-07-09 17:15:55,534][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-288] due to args.save_total_limit [2025-07-09 17:16:00,487][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:16:00,491][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:16:00,491][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:16:00,491][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:16:00,885][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-352 [2025-07-09 17:16:00,886][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-352/config.json [2025-07-09 17:16:02,213][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-352/model.safetensors [2025-07-09 17:16:04,259][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-320] due to args.save_total_limit [2025-07-09 17:16:09,238][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:16:09,242][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:16:09,242][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:16:09,242][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:16:09,639][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-384 [2025-07-09 17:16:09,641][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-384/config.json [2025-07-09 17:16:11,042][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-384/model.safetensors [2025-07-09 17:16:13,060][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-352] due to args.save_total_limit [2025-07-09 17:16:18,036][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:16:18,039][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:16:18,039][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:16:18,039][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:16:18,434][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-416 [2025-07-09 17:16:18,435][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-416/config.json [2025-07-09 17:16:20,168][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-416/model.safetensors [2025-07-09 17:16:22,058][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-384] due to args.save_total_limit [2025-07-09 17:16:22,176][transformers.trainer][INFO] - Training completed. Do not forget to share your model on huggingface.co/models =) [2025-07-09 17:16:22,176][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-256 (score: 0.43200913614487313). [2025-07-09 17:16:22,534][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-14-13/results/checkpoint-416] due to args.save_total_limit [2025-07-09 17:16:22,692][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:16:22,695][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:16:22,695][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:16:22,695][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:16:23,118][__main__][INFO] - Training completed successfully. [2025-07-09 17:16:23,118][__main__][INFO] - Running on Test [2025-07-09 17:16:23,119][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference. If prompt, id, grades, supporting_text, essay_year, essay_text, id_prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:16:23,121][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:16:23,121][transformers.trainer][INFO] - Num examples = 138 [2025-07-09 17:16:23,121][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:16:23,542][__main__][INFO] - Test metrics: {'eval_loss': 1.8821938037872314, 'eval_model_preparation_time': 0.0021, 'eval_accuracy': 0.3188405797101449, 'eval_RMSE': 55.22024413490799, 'eval_QWK': 0.35860460184497933, 'eval_HDIV': 0.08695652173913049, 'eval_Macro_F1': 0.22452316528265895, 'eval_Micro_F1': 0.3188405797101449, 'eval_Weighted_F1': 0.3210121894546771, 'eval_TP_0': 0, 'eval_TN_0': 137, 'eval_FP_0': 0, 'eval_FN_0': 1, 'eval_TP_1': 8, 'eval_TN_1': 91, 'eval_FP_1': 18, 'eval_FN_1': 21, 'eval_TP_2': 8, 'eval_TN_2': 96, 'eval_FP_2': 24, 'eval_FN_2': 10, 'eval_TP_3': 12, 'eval_TN_3': 71, 'eval_FP_3': 22, 'eval_FN_3': 33, 'eval_TP_4': 16, 'eval_TN_4': 80, 'eval_FP_4': 20, 'eval_FN_4': 22, 'eval_TP_5': 0, 'eval_TN_5': 121, 'eval_FP_5': 10, 'eval_FN_5': 7, 'eval_runtime': 0.4153, 'eval_samples_per_second': 332.255, 'eval_steps_per_second': 21.669, 'epoch': 13.0} [2025-07-09 17:16:23,543][transformers.trainer][INFO] - Saving model checkpoint to ./results/best_model [2025-07-09 17:16:23,545][transformers.configuration_utils][INFO] - Configuration saved in ./results/best_model/config.json [2025-07-09 17:16:25,266][transformers.modeling_utils][INFO] - Model weights saved in ./results/best_model/model.safetensors [2025-07-09 17:16:25,268][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/best_model/tokenizer_config.json [2025-07-09 17:16:25,269][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/best_model/special_tokens_map.json [2025-07-09 17:16:25,342][__main__][INFO] - Model and tokenizer saved to ./results/best_model [2025-07-09 17:16:25,368][__main__][INFO] - Fine Tuning Finished. [2025-07-09 17:16:25,879][__main__][INFO] - Total emissions: 0.0025 kg CO2eq