--- tags: - generated_from_trainer metrics: - accuracy model-index: - name: GPT2_more_function_42 results: [] --- # GPT2_more_function_42 This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 4.3530 - Accuracy: 0.2670 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 10000 - num_epochs: 10 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:| | 5.6351 | 1.0 | 6417 | 5.4097 | 0.1894 | | 4.9863 | 2.0 | 12834 | 4.8426 | 0.2244 | | 4.7136 | 3.0 | 19251 | 4.6423 | 0.2405 | | 4.584 | 4.0 | 25668 | 4.5398 | 0.2492 | | 4.4834 | 5.0 | 32085 | 4.4778 | 0.2548 | | 4.4098 | 6.0 | 38502 | 4.4340 | 0.2588 | | 4.3491 | 7.0 | 44919 | 4.4003 | 0.2622 | | 4.2949 | 8.0 | 51336 | 4.3788 | 0.2642 | | 4.2459 | 9.0 | 57753 | 4.3607 | 0.2667 | | 4.2045 | 10.0 | 64170 | 4.3530 | 0.2670 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.9.1+cu128 - Datasets 4.1.1 - Tokenizers 0.13.3