Reward_model

This model is a fine-tuned version of OpenAssistant/reward-model-deberta-v3-base on 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