|
--- |
|
license: other |
|
library_name: peft |
|
tags: |
|
- llama-factory |
|
- lora |
|
- generated_from_trainer |
|
base_model: mistralai/Mistral-7B-v0.1 |
|
model-index: |
|
- name: mistral-7b-medqa-v1 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# mistral-7b-medqa-v1 |
|
|
|
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the medical_meadow_medqa 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-medqa-v1), gen_kwargs: (None), limit: 100.0, num_fewshot: None |
|
|
|
| Tasks |Version|Filter|n-shot| Metric |Value| |Stderr| |
|
|---------------------|-------|------|-----:|--------|----:|---|-----:| |
|
|pubmedqa | 1|none | 0|acc | 0.98|± |0.0141| |
|
|ocn |Yaml |none | 0|acc | 0.71|± |0.0456| |
|
|professional_medicine| 0|none | 0|acc | 0.69|± |0.0465| |
|
|college_medicine | 0|none | 0|acc | 0.61|± |0.0490| |
|
|clinical_knowledge | 0|none | 0|acc | 0.63|± |0.0485| |
|
|medmcqa |Yaml |none | 0|acc | 0.41|± |0.0494| |
|
|aocnp |Yaml |none | 0|acc | 0.61|± |0.0490| |
|
|
|
|
|
### Appendix (original performance before lora-finetune) |
|
|
|
hf (pretrained=mistralai/Mistral-7B-v0.1,parallelize=True,load_in_4bit=True), 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| |
|
|ocn |Yaml |none | 0|acc | 0.62|± |0.0488| |
|
|professional_medicine| 0|none | 0|acc | 0.64|± |0.0482| |
|
|college_medicine | 0|none | 0|acc | 0.65|± |0.0479| |
|
|clinical_knowledge | 0|none | 0|acc | 0.68|± |0.0469| |
|
|medmcqa |Yaml |none | 0|acc | 0.45|± |0.0500| |
|
|aocnp |Yaml |none | 0|acc | 0.47|± |0.0502| |
|
|