README.md

metadata

license: apache-2.0
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.1
model-index:
  - name: Mistral-7B-Medical-Finetune_V2
    results: []

Mistral-7B-Medical-Finetune_V2

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6807

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: 0.00025
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.7727	1.05	300	0.6943
0.5476	2.1	600	0.6807

Framework versions

• PEFT 0.8.2
• Transformers 4.36.2
• Pytorch 2.2.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.1