Mistral-8x7b-Medical-Finetune_QA_MCQ
This model is a fine-tuned version of mistralai/Mixtral-8x7B-Instruct-v0.1 on the None dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.9575
- eval_runtime: 539.2458
- eval_samples_per_second: 9.009
- eval_steps_per_second: 0.282
- epoch: 4.13
- step: 62000
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1
- num_epochs: 5
Framework versions
- PEFT 0.9.0
- Transformers 4.38.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 12
Model tree for TachyHealth/Mistral-8x7b-Medical-Finetune_QA_MCQ_Gazal_Ai
Base model
mistralai/Mixtral-8x7B-v0.1
Finetuned
mistralai/Mixtral-8x7B-Instruct-v0.1