<!-- 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-poet
This model is a fine-tuned version of distilgpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.5041
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 | 156 | 4.0149 |
| No log | 2.0 | 312 | 3.7999 |
| No log | 3.0 | 468 | 3.7235 |
| 4.4263 | 4.0 | 624 | 3.6806 |
| 4.4263 | 5.0 | 780 | 3.6501 |
| 4.4263 | 6.0 | 936 | 3.6179 |
| 3.951 | 7.0 | 1092 | 3.6038 |
| 3.951 | 8.0 | 1248 | 3.5823 |
| 3.951 | 9.0 | 1404 | 3.5644 |
| 3.787 | 10.0 | 1560 | 3.5492 |
| 3.787 | 11.0 | 1716 | 3.5452 |
| 3.787 | 12.0 | 1872 | 3.5312 |
| 3.6901 | 13.0 | 2028 | 3.5259 |
| 3.6901 | 14.0 | 2184 | 3.5181 |
| 3.6901 | 15.0 | 2340 | 3.5108 |
| 3.6901 | 16.0 | 2496 | 3.5109 |
| 3.6212 | 17.0 | 2652 | 3.5074 |
| 3.6212 | 18.0 | 2808 | 3.5043 |
| 3.6212 | 19.0 | 2964 | 3.5041 |
| 3.5786 | 20.0 | 3120 | 3.5041 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
