README.md

metadata

license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
  - alignment-handbook
  - trl
  - dpo
  - generated_from_trainer
  - trl
  - dpo
  - generated_from_trainer
datasets:
  - HuggingFaceH4/ultrafeedback_binarized
model-index:
  - name: mistral-7b-dpo-full-wo-healthsearch_qa-ep3
    results: []

mistral-7b-dpo-full-wo-healthsearch_qa-ep3

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:

• Loss: 0.2680
• Rewards/chosen: -0.5188
• Rewards/rejected: -3.1722
• Rewards/accuracies: 0.8909
• Rewards/margins: 2.6534
• Logps/rejected: -1410.1324
• Logps/chosen: -651.1674
• Logits/rejected: -3.3100
• Logits/chosen: -3.2034

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: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• 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
• Datasets 2.14.6
• Tokenizers 0.15.2