vietnamese-news-summarization-vistral-7b
This model is a fine-tuned version of Viet-Mistral/Vistral-7B-Chat on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.8576
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: 2e-06
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.0431 | 0.0060 | 20 | 2.0914 |
| 2.0513 | 0.0119 | 40 | 2.0405 |
| 2.0366 | 0.0179 | 60 | 1.9899 |
| 1.946 | 0.0238 | 80 | 1.9301 |
| 1.9324 | 0.0298 | 100 | 1.8576 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.1.2
- Datasets 2.16.0
- Tokenizers 0.19.1
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for anhvu2501/vietnamese-news-summarization-vistral-7b
Base model
Viet-Mistral/Vistral-7B-Chat