gpt2-small-spanish-disco-poetry
This model is a fine-tuned version of datificate/gpt2-small-spanish on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.2471
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: 6
- eval_batch_size: 6
- 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 |
|---|---|---|---|
| 4.7329 | 1.0 | 750 | 4.4635 |
| 4.4445 | 2.0 | 1500 | 4.3703 |
| 4.3344 | 3.0 | 2250 | 4.3262 |
| 4.2352 | 4.0 | 3000 | 4.3045 |
| 4.1714 | 5.0 | 3750 | 4.2821 |
| 4.1034 | 6.0 | 4500 | 4.2619 |
| 4.0668 | 7.0 | 5250 | 4.2554 |
| 4.0322 | 8.0 | 6000 | 4.2515 |
| 4.0163 | 9.0 | 6750 | 4.2489 |
| 4.0011 | 10.0 | 7500 | 4.2471 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6