ft-mistral-with-customize-ds-with-QLoRA
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2127
- F1 Micro: 0.7762
- F1 Macro: 0.5914
- F1 Weighted: 0.7707
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 5
- total_train_batch_size: 40
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | F1 Weighted |
|---|---|---|---|---|---|---|
| No log | 1.0 | 25 | 0.3648 | 0.6954 | 0.4375 | 0.6497 |
| No log | 2.0 | 50 | 0.2530 | 0.7298 | 0.5400 | 0.7228 |
| No log | 3.0 | 75 | 0.2202 | 0.7470 | 0.5385 | 0.7400 |
| 0.4222 | 4.0 | 100 | 0.2127 | 0.7762 | 0.5914 | 0.7707 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.2
- Datasets 2.15.0
- Tokenizers 0.15.1