Mistral-7B-Instruct-v0.2-GPTQ_finetune
This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6337
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: 4
- eval_batch_size: 4
- 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: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
3.2048 | 0.5714 | 1 | 1.8649 |
1.559 | 1.7143 | 3 | 1.7810 |
1.3635 | 2.8571 | 5 | 1.7115 |
1.3561 | 4.0 | 7 | 1.6645 |
2.7801 | 4.5714 | 8 | 1.6496 |
0.898 | 5.7143 | 10 | 1.6337 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 0
Model tree for vjvk/Mistral-7B-Instruct-v0.2-GPTQ_finetune
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ