| --- |
| license: mit |
| tags: |
| - trl |
| - reward-trainer |
| - generated_from_trainer |
| base_model: OpenAssistant/reward-model-deberta-v3-base |
| metrics: |
| - accuracy |
| model-index: |
| - name: Reward_model |
| results: [] |
| datasets: |
| - Anthropic/hh-rlhf |
| --- |
| |
| <!-- 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. --> |
|
|
| # Reward_model |
| |
| This model is a fine-tuned version of [OpenAssistant/reward-model-deberta-v3-base](https://huggingface.co/OpenAssistant/reward-model-deberta-v3-base) on [Anthropic/hh-rlhf](https://huggingface.co/datasets/Anthropic/hh-rlhf) dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.6931 |
| - Accuracy: 1.0 |
| |
| ### Training hyperparameters |
| |
| The following hyperparameters were used during training: |
| - learning_rate: 5e-05 |
| - train_batch_size: 12 |
| - eval_batch_size: 2 |
| - seed: 42 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - num_epochs: 1 |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | |
| |:-------------:|:-----:|:-----:|:---------------:|:--------:| |
| | 0.6936 | 1.0 | 13400 | 0.6931 | 1.0 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.39.3 |
| - Pytorch 2.1.2 |
| - Datasets 2.18.0 |
| - Tokenizers 0.15.2 |
