<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
vietcuna-7b-test-exam-12
This model is a fine-tuned version of vilm/vietcuna-7b-v3 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.7656
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: 0.0005
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 14.3516 | 0.15 | 300 | 13.9922 |
| 10.0687 | 0.31 | 600 | 9.3828 |
| 7.2003 | 0.46 | 900 | 6.9414 |
| 6.0928 | 0.61 | 1200 | 5.9883 |
| 5.6407 | 0.77 | 1500 | 5.6133 |
| 5.4097 | 0.92 | 1800 | 5.375 |
| 5.2841 | 1.07 | 2100 | 5.2305 |
| 5.1691 | 1.23 | 2400 | 5.1875 |
| 5.0585 | 1.38 | 2700 | 5.0664 |
| 4.9741 | 1.53 | 3000 | 5.0078 |
| 4.9581 | 1.69 | 3300 | 4.9531 |
| 4.9653 | 1.84 | 3600 | 4.9102 |
| 4.8763 | 1.99 | 3900 | 4.8711 |
| 4.8308 | 2.15 | 4200 | 4.8281 |
| 4.7993 | 2.3 | 4500 | 4.8125 |
| 4.8228 | 2.46 | 4800 | 4.8047 |
| 4.789 | 2.61 | 5100 | 4.7852 |
| 4.8048 | 2.76 | 5400 | 4.7734 |
| 4.7566 | 2.92 | 5700 | 4.7656 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.14.1
