montelnewsspeaker
This model is a fine-tuned version of distilgpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8843
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8369 | 1.0 | 1090 | 0.8848 |
| 0.8257 | 2.0 | 2180 | 0.8879 |
| 0.8085 | 3.0 | 3270 | 0.8750 |
| 0.7996 | 4.0 | 4360 | 0.8720 |
| 0.7861 | 5.0 | 5450 | 0.8789 |
| 0.7781 | 6.0 | 6540 | 0.8777 |
| 0.768 | 7.0 | 7630 | 0.8798 |
| 0.7585 | 8.0 | 8720 | 0.8789 |
| 0.7475 | 9.0 | 9810 | 0.8774 |
| 0.739 | 10.0 | 10900 | 0.8828 |
| 0.7285 | 11.0 | 11990 | 0.8817 |
| 0.7269 | 12.0 | 13080 | 0.8813 |
| 0.7202 | 13.0 | 14170 | 0.8801 |
| 0.7156 | 14.0 | 15260 | 0.8839 |
| 0.7106 | 15.0 | 16350 | 0.8843 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.15.0