zephyr-7b-dpo-lora

This model is a fine-tuned version of HuggingFaceH4/zephyr-7b-beta on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.6931
• eval_runtime: 817.0722
• eval_samples_per_second: 2.448
• eval_steps_per_second: 0.153
• eval_rewards/chosen: 0.0
• eval_rewards/rejected: 0.0
• eval_rewards/accuracies: 0.0
• eval_rewards/margins: 0.0
• eval_logps/rejected: -311.3714
• eval_logps/chosen: -319.0738
• eval_logits/rejected: -2.3541
• eval_logits/chosen: -2.4051
• step: 0

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-07
• train_batch_size: 8
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• total_eval_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 0

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.1+cu121
• Datasets 2.14.6
• Tokenizers 0.14.1