metadata
license: mit
base_model: DeepESP/gpt2-spanish
tags:
- generated_from_trainer
model-index:
- name: Julio-Cortazar
results: []
Julio-Cortazar
This model is a fine-tuned version of DeepESP/gpt2-spanish on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4635
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.625 | 1.0 | 177 | 2.5849 |
| 2.5334 | 2.0 | 354 | 2.5254 |
| 2.4463 | 3.0 | 531 | 2.4991 |
| 2.2868 | 4.0 | 708 | 2.4825 |
| 2.198 | 5.0 | 885 | 2.4753 |
| 2.1981 | 6.0 | 1062 | 2.4707 |
| 2.096 | 7.0 | 1239 | 2.4655 |
| 1.9984 | 8.0 | 1416 | 2.4642 |
| 1.9602 | 9.0 | 1593 | 2.4631 |
| 2.0752 | 10.0 | 1770 | 2.4636 |
| 2.0311 | 11.0 | 1947 | 2.4635 |
| 2.0731 | 12.0 | 2124 | 2.4635 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3