biomistral-gptq-ft
This model is a fine-tuned version of LoneStriker/BioMistral-7B-SLERP-GPTQ on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3391
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.9096 | 1.0 | 62 | 1.3700 |
1.3713 | 1.99 | 124 | 1.3455 |
1.3253 | 2.99 | 186 | 1.3391 |
Framework versions
- PEFT 0.11.1
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 2
Model tree for amasi/biomistral-gptq-ft
Base model
LoneStriker/BioMistral-7B-SLERP-GPTQ
Adapter
this model