kancilgpt
This model is a fine-tuned version of indobenchmark/indogpt on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.8174
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-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3408 | 1.0 | 2189 | 2.8174 |
| 0.5612 | 2.0 | 4378 | 3.1873 |
| 0.2904 | 3.0 | 6567 | 3.5123 |
| 0.1836 | 4.0 | 8756 | 3.7073 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0