<!-- 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. -->
gpt2-simpsons
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.3643
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 6877
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.319 | 1.0 | 860 | 3.4223 |
| 3.1458 | 2.0 | 1720 | 3.3075 |
| 3.0161 | 3.0 | 2580 | 3.2596 |
| 2.9279 | 4.0 | 3440 | 3.2313 |
| 2.8508 | 5.0 | 4300 | 3.2176 |
| 2.7454 | 6.0 | 5160 | 3.2237 |
| 2.6928 | 7.0 | 6020 | 3.2381 |
| 2.5962 | 8.0 | 6880 | 3.2617 |
| 2.4645 | 9.0 | 7740 | 3.3105 |
| 2.3415 | 10.0 | 8600 | 3.3643 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Tokenizers 0.13.2
