README.md

metadata

library_name: peft
tags:
  - trl
  - dpo
  - generated_from_trainer
base_model: Yaxin1992/zephyr-beta-llama2-7b-ties
model-index:
  - name: zephyr-llama-merge-7b-dpo-multi
    results: []

zephyr-llama-merge-7b-dpo-multi

This model is a fine-tuned version of Yaxin1992/zephyr-beta-llama2-7b-ties on an unknown dataset.

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: 2e-06
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 1200

Training results

Framework versions

• PEFT 0.9.0
• Transformers 4.38.1
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2