<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->
dico97/distilgpt2-finetuned-wikitext2-datos-propios
This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 2.1457
- Validation Loss: 2.4673
- Epoch: 14
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:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 3.2488 | 2.9547 | 0 |
| 2.9889 | 2.8030 | 1 |
| 2.8373 | 2.7189 | 2 |
| 2.7251 | 2.6685 | 3 |
| 2.6403 | 2.6278 | 4 |
| 2.5661 | 2.6034 | 5 |
| 2.5023 | 2.5710 | 6 |
| 2.4410 | 2.5560 | 7 |
| 2.3893 | 2.5280 | 8 |
| 2.3409 | 2.5150 | 9 |
| 2.2976 | 2.5084 | 10 |
| 2.2565 | 2.4861 | 11 |
| 2.2148 | 2.4663 | 12 |
| 2.1813 | 2.4622 | 13 |
| 2.1457 | 2.4673 | 14 |
Framework versions
- Transformers 4.28.0
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
