| license: mit | |
| base_model: roberta-base | |
| tags: | |
| - generated_from_trainer | |
| metrics: | |
| - f1 | |
| - accuracy | |
| model-index: | |
| - name: RewardModel_RobertaBase_GPT_Data | |
| results: [] | |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You | |
| should probably proofread and complete it, then remove this comment. --> | |
| # RewardModel_RobertaBase_GPT_Data | |
| This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 0.2827 | |
| - F1: 0.9076 | |
| - Roc Auc: 0.9420 | |
| - Accuracy: 0.8393 | |
| ## 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: 2e-05 | |
| - train_batch_size: 16 | |
| - eval_batch_size: 16 | |
| - seed: 42 | |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 | |
| - lr_scheduler_type: linear | |
| - num_epochs: 5 | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy | | |
| |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:| | |
| | No log | 1.0 | 16 | 0.6224 | 0.0 | 0.5 | 0.0 | | |
| | No log | 2.0 | 32 | 0.5112 | 0.4658 | 0.6518 | 0.3036 | | |
| | No log | 3.0 | 48 | 0.3407 | 0.8235 | 0.8571 | 0.75 | | |
| | No log | 4.0 | 64 | 0.3243 | 0.85 | 0.8973 | 0.7679 | | |
| | No log | 5.0 | 80 | 0.2827 | 0.9076 | 0.9420 | 0.8393 | | |
| ### Framework versions | |
| - Transformers 4.41.2 | |
| - Pytorch 2.3.0+cu121 | |
| - Datasets 2.19.2 | |
| - Tokenizers 0.19.1 | |