README.md

metadata

license: other
base_model: lewtun/gemma-7b-sft-full-deita-10k-v0
tags:
  - alignment-handbook
  - trl
  - dpo
  - generated_from_trainer
  - trl
  - dpo
  - generated_from_trainer
datasets:
  - argilla/dpo-mix-7k
model-index:
  - name: gemma-7b-dpo-full-mix1-beta-0.2
    results: []

gemma-7b-dpo-full-mix1-beta-0.2

This model is a fine-tuned version of lewtun/gemma-7b-sft-full-deita-10k-v0 on the argilla/dpo-mix-7k dataset. It achieves the following results on the evaluation set:

• Loss: 0.7715
• Rewards/chosen: -1.9769
• Rewards/rejected: -4.0284
• Rewards/accuracies: 0.6562
• Rewards/margins: 2.0516
• Logps/rejected: -471.6917
• Logps/chosen: -463.2887
• Logits/rejected: 100.9810
• Logits/chosen: 107.1974

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: 2
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 8
• total_train_batch_size: 128
• total_eval_batch_size: 32
• 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

• Transformers 4.39.0.dev0
• Pytorch 2.1.2+cu121
• Datasets 2.14.6
• Tokenizers 0.15.1