<!-- 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-love2
This model is a fine-tuned version of glenn2/distilgpt2-finetuned-love2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2861
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: 20.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 45 | 0.2777 |
| No log | 2.0 | 90 | 0.2796 |
| No log | 3.0 | 135 | 0.2838 |
| No log | 4.0 | 180 | 0.2740 |
| No log | 5.0 | 225 | 0.2796 |
| No log | 6.0 | 270 | 0.2795 |
| No log | 7.0 | 315 | 0.2815 |
| No log | 8.0 | 360 | 0.2814 |
| No log | 9.0 | 405 | 0.2791 |
| No log | 10.0 | 450 | 0.2796 |
| No log | 11.0 | 495 | 0.2829 |
| 0.0735 | 12.0 | 540 | 0.2859 |
| 0.0735 | 13.0 | 585 | 0.2864 |
| 0.0735 | 14.0 | 630 | 0.2870 |
| 0.0735 | 15.0 | 675 | 0.2861 |
| 0.0735 | 16.0 | 720 | 0.2848 |
| 0.0735 | 17.0 | 765 | 0.2863 |
| 0.0735 | 18.0 | 810 | 0.2865 |
| 0.0735 | 19.0 | 855 | 0.2862 |
| 0.0735 | 20.0 | 900 | 0.2861 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
