[2025-07-09 17:16:35,620][__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: 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 17:16:39,482][__main__][INFO] - GPU 0: NVIDIA RTX A6000 | TDP ≈ 300 W [2025-07-09 17:16:39,482][__main__][INFO] - Starting the Fine Tuning training process. [2025-07-09 17:16:45,186][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 17:16:45,187][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 17:16:45,391][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 17:16:45,392][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 17:16:46,066][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 17:16:46,067][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 17:16:46,067][transformers.tokenization_utils_base][INFO] - loading file added_tokens.json from cache at None [2025-07-09 17:16:46,067][transformers.tokenization_utils_base][INFO] - loading file special_tokens_map.json from cache at None [2025-07-09 17:16:46,067][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 17:16:46,067][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None [2025-07-09 17:16:46,067][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 17:16:46,068][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 17:16:46,311][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: True; Use Full Context: False [2025-07-09 17:16:47,007][__main__][INFO] - Token statistics for 'train' split: [2025-07-09 17:16:47,008][__main__][INFO] - Total examples: 500 [2025-07-09 17:16:47,008][__main__][INFO] - Min tokens: 512 [2025-07-09 17:16:47,008][__main__][INFO] - Max tokens: 512 [2025-07-09 17:16:47,008][__main__][INFO] - Avg tokens: 512.00 [2025-07-09 17:16:47,008][__main__][INFO] - Std tokens: 0.00 [2025-07-09 17:16:47,103][__main__][INFO] - Token statistics for 'validation' split: [2025-07-09 17:16:47,103][__main__][INFO] - Total examples: 132 [2025-07-09 17:16:47,103][__main__][INFO] - Min tokens: 512 [2025-07-09 17:16:47,103][__main__][INFO] - Max tokens: 512 [2025-07-09 17:16:47,103][__main__][INFO] - Avg tokens: 512.00 [2025-07-09 17:16:47,103][__main__][INFO] - Std tokens: 0.00 [2025-07-09 17:16:47,203][__main__][INFO] - Token statistics for 'test' split: [2025-07-09 17:16:47,203][__main__][INFO] - Total examples: 138 [2025-07-09 17:16:47,203][__main__][INFO] - Min tokens: 512 [2025-07-09 17:16:47,203][__main__][INFO] - Max tokens: 512 [2025-07-09 17:16:47,203][__main__][INFO] - Avg tokens: 512.00 [2025-07-09 17:16:47,203][__main__][INFO] - Std tokens: 0.00 [2025-07-09 17:16:47,204][__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 17:16:47,204][__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 17:16:47,419][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 17:16:47,420][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 17:16:47,598][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 17:16:47,605][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 17:16:47,605][transformers.modeling_utils][INFO] - Instantiating BertForSequenceClassification model under default dtype torch.float32. [2025-07-09 17:16:47,773][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 17:16:48,508][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 17:16:48,508][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 17:16:48,514][transformers.training_args][INFO] - PyTorch: setting up devices [2025-07-09 17:16:48,577][__main__][INFO] - Total steps: 620. Number of warmup steps: 62 [2025-07-09 17:16:48,585][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 17:16:48,610][transformers.trainer][INFO] - Using auto half precision backend [2025-07-09 17:16:48,612][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:16:48,618][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:16:48,618][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:16:48,618][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:16:49,574][transformers.trainer][INFO] - The following columns in the Training set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:16:49,583][transformers.trainer][INFO] - ***** Running training ***** [2025-07-09 17:16:49,584][transformers.trainer][INFO] - Num examples = 500 [2025-07-09 17:16:49,584][transformers.trainer][INFO] - Num Epochs = 20 [2025-07-09 17:16:49,584][transformers.trainer][INFO] - Instantaneous batch size per device = 16 [2025-07-09 17:16:49,584][transformers.trainer][INFO] - Total train batch size (w. parallel, distributed & accumulation) = 16 [2025-07-09 17:16:49,584][transformers.trainer][INFO] - Gradient Accumulation steps = 1 [2025-07-09 17:16:49,584][transformers.trainer][INFO] - Total optimization steps = 640 [2025-07-09 17:16:49,584][transformers.trainer][INFO] - Number of trainable parameters = 177,858,054 [2025-07-09 17:16:54,598][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:16:54,600][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:16:54,600][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:16:54,600][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:16:54,990][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-32 [2025-07-09 17:16:54,991][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-32/config.json [2025-07-09 17:16:56,420][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-32/model.safetensors [2025-07-09 17:17:02,794][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:17:02,796][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:17:02,796][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:17:02,796][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:17:03,180][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-64 [2025-07-09 17:17:03,181][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-64/config.json [2025-07-09 17:17:04,499][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-64/model.safetensors [2025-07-09 17:17:06,619][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-32] due to args.save_total_limit [2025-07-09 17:17:11,599][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:17:11,601][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:17:11,601][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:17:11,601][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:17:11,990][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-96 [2025-07-09 17:17:11,991][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-96/config.json [2025-07-09 17:17:13,340][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-96/model.safetensors [2025-07-09 17:17:15,231][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-64] due to args.save_total_limit [2025-07-09 17:17:20,161][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:17:20,164][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:17:20,164][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:17:20,164][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:17:20,551][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-128 [2025-07-09 17:17:20,552][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-128/config.json [2025-07-09 17:17:22,038][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-128/model.safetensors [2025-07-09 17:17:24,130][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-96] due to args.save_total_limit [2025-07-09 17:17:29,080][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:17:29,082][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:17:29,083][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:17:29,083][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:17:29,474][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-160 [2025-07-09 17:17:29,476][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-160/config.json [2025-07-09 17:17:30,903][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-160/model.safetensors [2025-07-09 17:17:37,833][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:17:37,835][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:17:37,835][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:17:37,835][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:17:38,223][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-192 [2025-07-09 17:17:38,224][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-192/config.json [2025-07-09 17:17:39,538][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-192/model.safetensors [2025-07-09 17:17:41,709][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-160] due to args.save_total_limit [2025-07-09 17:17:46,670][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:17:46,672][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:17:46,673][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:17:46,673][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:17:47,064][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-224 [2025-07-09 17:17:47,066][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-224/config.json [2025-07-09 17:17:48,459][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-224/model.safetensors [2025-07-09 17:17:50,566][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-192] due to args.save_total_limit [2025-07-09 17:17:55,524][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:17:55,527][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:17:55,527][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:17:55,527][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:17:55,918][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-256 [2025-07-09 17:17:55,920][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-256/config.json [2025-07-09 17:17:57,309][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-256/model.safetensors [2025-07-09 17:17:59,425][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-224] due to args.save_total_limit [2025-07-09 17:18:04,384][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:18:04,387][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:18:04,387][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:18:04,387][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:18:04,777][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-288 [2025-07-09 17:18:04,778][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-288/config.json [2025-07-09 17:18:06,261][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-288/model.safetensors [2025-07-09 17:18:08,369][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-256] due to args.save_total_limit [2025-07-09 17:18:08,507][transformers.trainer][INFO] - Training completed. Do not forget to share your model on huggingface.co/models =) [2025-07-09 17:18:08,507][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-128 (score: 0.5589021564783461). [2025-07-09 17:18:08,871][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/17-16-35/results/checkpoint-288] due to args.save_total_limit [2025-07-09 17:18:09,010][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:18:09,013][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:18:09,013][transformers.trainer][INFO] - Num examples = 132 [2025-07-09 17:18:09,013][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:18:09,416][__main__][INFO] - Training completed successfully. [2025-07-09 17:18:09,416][__main__][INFO] - Running on Test [2025-07-09 17:18:09,417][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference. If essay_text, supporting_text, grades, id, id_prompt, essay_year, prompt, reference are not expected by `BertForSequenceClassification.forward`, you can safely ignore this message. [2025-07-09 17:18:09,419][transformers.trainer][INFO] - ***** Running Evaluation ***** [2025-07-09 17:18:09,419][transformers.trainer][INFO] - Num examples = 138 [2025-07-09 17:18:09,419][transformers.trainer][INFO] - Batch size = 16 [2025-07-09 17:18:09,810][__main__][INFO] - Test metrics: {'eval_loss': 1.3231467008590698, 'eval_model_preparation_time': 0.0021, 'eval_accuracy': 0.5362318840579711, 'eval_RMSE': 30.833822949500753, 'eval_QWK': 0.49652963160704733, 'eval_HDIV': 0.007246376811594235, 'eval_Macro_F1': 0.29499258208935625, 'eval_Micro_F1': 0.5362318840579711, 'eval_Weighted_F1': 0.5487262828076291, 'eval_TP_0': 0, 'eval_TN_0': 137, 'eval_FP_0': 0, 'eval_FN_0': 1, 'eval_TP_1': 0, 'eval_TN_1': 137, 'eval_FP_1': 0, 'eval_FN_1': 1, 'eval_TP_2': 5, 'eval_TN_2': 112, 'eval_FP_2': 17, 'eval_FN_2': 4, 'eval_TP_3': 44, 'eval_TN_3': 42, 'eval_FP_3': 20, 'eval_FN_3': 32, 'eval_TP_4': 23, 'eval_TN_4': 71, 'eval_FP_4': 21, 'eval_FN_4': 23, 'eval_TP_5': 2, 'eval_TN_5': 127, 'eval_FP_5': 6, 'eval_FN_5': 3, 'eval_runtime': 0.3847, 'eval_samples_per_second': 358.675, 'eval_steps_per_second': 23.392, 'epoch': 9.0} [2025-07-09 17:18:09,810][transformers.trainer][INFO] - Saving model checkpoint to ./results/best_model [2025-07-09 17:18:09,812][transformers.configuration_utils][INFO] - Configuration saved in ./results/best_model/config.json [2025-07-09 17:18:10,908][transformers.modeling_utils][INFO] - Model weights saved in ./results/best_model/model.safetensors [2025-07-09 17:18:10,910][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/best_model/tokenizer_config.json [2025-07-09 17:18:10,910][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/best_model/special_tokens_map.json [2025-07-09 17:18:10,975][__main__][INFO] - Model and tokenizer saved to ./results/best_model [2025-07-09 17:18:10,997][__main__][INFO] - Fine Tuning Finished. [2025-07-09 17:18:11,507][__main__][INFO] - Total emissions: 0.0017 kg CO2eq