Mistral-7B-Medical-Finetune_QA_Choices_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: 0.6574

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: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.7911	0.2	300	0.7404
0.7311	0.39	600	0.7118
0.7015	0.59	900	0.6815
0.6824	0.78	1200	0.6623
0.6686	0.98	1500	0.6574

Framework versions

• PEFT 0.9.0
• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2