Mistral-7B-DFT2

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the siqi00/mistral_ultrafeedback_unhelpful_chatprompt_0.7_1.0_50_320 dataset.

This model was trained using Discriminative Fine-tuning (DFT), as described in the paper Discriminative Finetuning of Generative Large Language Models without Reward Models and Preference Data. The code is available at PenGuln/DFT.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-06
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• 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: 2

Framework versions

• Transformers 4.45.2
• Pytorch 2.1.2+cu121
• Datasets 3.0.1
• Tokenizers 0.20.1