<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
distilgpt2-finetuned-wikitext2
This model is a fine-tuned version of distilgpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.4740
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: 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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.0767 | 1.0 | 794 | 3.7406 |
| 3.8158 | 2.0 | 1588 | 3.6718 |
| 3.7557 | 3.0 | 2382 | 3.6302 |
| 3.6758 | 4.0 | 3176 | 3.5968 |
| 3.6383 | 5.0 | 3970 | 3.5704 |
| 3.5762 | 6.0 | 4764 | 3.5524 |
| 3.5415 | 7.0 | 5558 | 3.5360 |
| 3.5116 | 8.0 | 6352 | 3.5195 |
| 3.485 | 9.0 | 7146 | 3.5116 |
| 3.4587 | 10.0 | 7940 | 3.5033 |
| 3.429 | 11.0 | 8734 | 3.4950 |
| 3.4179 | 12.0 | 9528 | 3.4882 |
| 3.3985 | 13.0 | 10322 | 3.4845 |
| 3.3812 | 14.0 | 11116 | 3.4825 |
| 3.3671 | 15.0 | 11910 | 3.4795 |
| 3.3547 | 16.0 | 12704 | 3.4751 |
| 3.3472 | 17.0 | 13498 | 3.4744 |
| 3.3393 | 18.0 | 14292 | 3.4743 |
| 3.3334 | 19.0 | 15086 | 3.4740 |
| 3.3309 | 20.0 | 15880 | 3.4740 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
