|
--- |
|
language: |
|
- en |
|
license: apache-2.0 |
|
tags: |
|
- text-generation-inference |
|
- transformers |
|
- unsloth |
|
- mistral |
|
- trl |
|
- medical |
|
datasets: |
|
- Shekswess/medical_mistral_instruct_dataset_short |
|
base_model: unsloth/mistral-7b-instruct-v0.2-bnb-4bit |
|
--- |
|
|
|
- **Developed by:** Shekswess |
|
- **License:** apache-2.0 |
|
- **Finetuned from model :** unsloth/mistral-7b-instruct-v0.2-bnb-4bit |
|
|
|
To utilize the fine-tuning of the model, you need to use the mistral instruction prompt template for this medical version of the model : |
|
``` |
|
[INST] Answer the question truthfully, you are a medical professional. This is the question: {question} [/INST] |
|
``` |
|
|
|
Metrics: |
|
|
|
- train_runtime: 2362.0602 |
|
- train_samples_per_second: 0.847 |
|
- train_steps_per_second: 0.106 |
|
- total_flos: 3.160426333342925e+16 |
|
- train_loss: 1.0993178739547729 |
|
- steps: 250 |
|
- epoch: 1.0 |
|
|
|
 |
|
|
|
|
