metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
- medical
base_model: mistralai/Mixtral-8x7B-v0.1
model-index:
- name: Thealth_Mixtral-8x7B
results: []
datasets:
- medalpaca/medical_meadow_medqa
- medalpaca/medical_meadow_medical_flashcards
- medalpaca/medical_meadow_pubmed_causal
- medalpaca/medical_meadow_wikidoc
language:
- en
pipeline_tag: text2text-generation
results_Thealth_Mixtral-8x7B
This model is a fine-tuned version of mistralai/Mixtral-8x7B-v0.1 on medical dataset . It achieves the following results on the evaluation set:
- Loss: 1.2772
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 30
- training_steps: 300
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5369 | 0.01 | 50 | 1.4087 |
| 1.3005 | 0.03 | 100 | 1.2964 |
| 1.2934 | 0.04 | 150 | 1.2727 |
| 1.2727 | 0.05 | 200 | 1.2744 |
| 1.2563 | 0.06 | 250 | 1.2763 |
| 1.2816 | 0.08 | 300 | 1.2772 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0