<!-- 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. -->
distilgpt_new_0020
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 3.1904
- Validation Loss: 3.0689
- Epoch: 19
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 |
---|---|---|
5.6632 | 4.5153 | 0 |
4.4292 | 4.0923 | 1 |
4.1169 | 3.8723 | 2 |
3.9326 | 3.7260 | 3 |
3.8026 | 3.6281 | 4 |
3.7045 | 3.5355 | 5 |
3.6254 | 3.4645 | 6 |
3.5604 | 3.4093 | 7 |
3.5048 | 3.3587 | 8 |
3.4569 | 3.3136 | 9 |
3.4155 | 3.2778 | 10 |
3.3791 | 3.2443 | 11 |
3.3470 | 3.2157 | 12 |
3.3183 | 3.1854 | 13 |
3.2922 | 3.1642 | 14 |
3.2685 | 3.1400 | 15 |
3.2467 | 3.1193 | 16 |
3.2267 | 3.1009 | 17 |
3.2078 | 3.0838 | 18 |
3.1904 | 3.0689 | 19 |
Framework versions
- Transformers 4.20.1
- TensorFlow 2.8.2
- Datasets 2.3.2
- Tokenizers 0.12.1