mistral-7b-mmlu-v1

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the medical_meadow_mmmlu dataset.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0005
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 20
• num_epochs: 1.0
• mixed_precision_training: Native AMP

Framework versions

• PEFT 0.8.2
• Transformers 4.37.2
• Pytorch 2.1.1+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1

Performance

hf (pretrained=mistralai/Mistral-7B-v0.1,parallelize=True,load_in_4bit=True,peft=chenhugging/mistral-7b-mmlu-v1), gen_kwargs: (None), limit: 100.0, num_fewshot: None, batch_size: 1

Tasks	Version	Filter	n-shot	Metric	Value		Stderr
pubmedqa	1	none	0	acc	0.98	±	0.0141
medmcqa	Yaml	none	0	acc	0.47	±	0.0502
professional_medicine	0	none	0	acc	0.79	±	0.0409
college_medicine	0	none	0	acc	0.72	±	0.0451
clinical_knowledge	0	none	0	acc	0.72	±	0.0451
aocnp	Yaml	none	0	acc	0.56	±	0.0499
ocn	Yaml	none	0	acc	0.66	±	0.0476