chilenoGPT
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.3921
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 30414
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.4985 | 1.0 | 3802 | 4.3106 |
| 4.1063 | 2.0 | 7604 | 3.9798 |
| 3.8797 | 3.0 | 11406 | 3.7886 |
| 3.7554 | 4.0 | 15208 | 3.6645 |
| 3.616 | 5.0 | 19010 | 3.5792 |
| 3.534 | 6.0 | 22812 | 3.5152 |
| 3.4631 | 7.0 | 26614 | 3.4632 |
| 3.3867 | 8.0 | 30416 | 3.4330 |
| 3.2781 | 9.0 | 34218 | 3.3975 |
| 3.2074 | 10.0 | 38020 | 3.3921 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Tokenizers 0.13.3