Configuration Parsing
Warning:
In adapter_config.json: "peft.base_model_name_or_path" must be a string
result
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: 0.4904
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 |
|---|---|---|---|
| 1.8013 | 0.9912 | 28 | 0.7742 |
| 0.7042 | 1.9823 | 56 | 0.5279 |
| 0.5777 | 2.9735 | 84 | 0.4869 |
| 0.5117 | 4.0 | 113 | 0.4764 |
| 0.503 | 4.9912 | 141 | 0.4750 |
| 0.4824 | 5.9823 | 169 | 0.4781 |
| 0.4634 | 6.9735 | 197 | 0.4782 |
| 0.4288 | 8.0 | 226 | 0.4851 |
| 0.4327 | 8.9912 | 254 | 0.4886 |
| 0.4123 | 9.9115 | 280 | 0.4904 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 2
Model tree for vjvk/result
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ