reward-model

This model is a fine-tuned version of ChaiML/reward_models_100_170000000_cp_498032 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5080

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: 1e-05
• train_batch_size: 3
• eval_batch_size: 3
• seed: 7
• gradient_accumulation_steps: 16
• total_train_batch_size: 48
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 200
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.5245	1.0	388	0.5152
0.5334	2.0	776	0.5080

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.15.0
• Tokenizers 0.15.0