zephyr-7b-dpo-lora-timedial

This model is a fine-tuned version of EllieS/zephyr-7b-sft-lora-timedial on the EllieS/timedial_dpo dataset. It achieves the following results on the evaluation set:

• Loss: 0.0056
• Rewards/chosen: -0.5375
• Rewards/rejected: -5.7320
• Rewards/accuracies: 1.0
• Rewards/margins: 5.1945
• Logps/rejected: -611.0701
• Logps/chosen: -80.2486
• Logits/rejected: -2.2508
• Logits/chosen: -2.4113

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: 5e-06
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 2
• total_train_batch_size: 2
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Framework versions

• PEFT 0.7.1
• Transformers 4.36.2
• Pytorch 2.1.2+cu121
• Datasets 2.14.6
• Tokenizers 0.15.2