Mistral-7B_final_MT_2
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: 0.6772
- Accuracy: 0.8117
- Precision: 0.8213
- Recall: 0.7967
- F1 score: 0.8088
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 score |
|---|---|---|---|---|---|---|---|
| 1.3277 | 0.5 | 200 | 1.1873 | 0.6883 | 0.7839 | 0.52 | 0.6253 |
| 0.8667 | 1.0 | 400 | 1.0207 | 0.675 | 0.7665 | 0.5033 | 0.6076 |
| 0.5318 | 1.5 | 600 | 0.6518 | 0.7733 | 0.7697 | 0.78 | 0.7748 |
| 0.5096 | 2.0 | 800 | 0.6387 | 0.7833 | 0.8320 | 0.71 | 0.7662 |
| 0.3206 | 2.5 | 1000 | 0.6011 | 0.805 | 0.8560 | 0.7333 | 0.7899 |
| 0.3049 | 3.0 | 1200 | 0.5818 | 0.8017 | 0.8291 | 0.76 | 0.7930 |
| 0.1994 | 3.5 | 1400 | 0.6459 | 0.8117 | 0.8148 | 0.8067 | 0.8107 |
| 0.1792 | 4.0 | 1600 | 0.6293 | 0.8083 | 0.8157 | 0.7967 | 0.8061 |
| 0.0904 | 4.5 | 1800 | 0.6960 | 0.8167 | 0.8467 | 0.7733 | 0.8084 |
| 0.0868 | 5.0 | 2000 | 0.6772 | 0.8117 | 0.8213 | 0.7967 | 0.8088 |
Framework versions
- PEFT 0.11.1
- Transformers 4.44.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 5
Model tree for rishavranaut/Mistral-7B_final_MT_2
Base model
mistralai/Mistral-7B-v0.1