<!-- 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-dp-gutenberg-fixed
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 3.1394
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: 0.0005
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.7114 | 0.27 | 500 | 5.6575 |
| 5.3632 | 0.54 | 1000 | 5.2280 |
| 5.0215 | 0.81 | 1500 | 4.9772 |
| 4.7647 | 1.08 | 2000 | 4.8238 |
| 4.5742 | 1.35 | 2500 | 4.7096 |
| 4.4883 | 1.62 | 3000 | 4.6098 |
| 4.4004 | 1.89 | 3500 | 4.5143 |
| 4.207 | 2.16 | 4000 | 4.4732 |
| 4.1128 | 2.43 | 4500 | 4.4205 |
| 4.0827 | 2.7 | 5000 | 4.3622 |
| 4.0505 | 2.97 | 5500 | 4.3114 |
| 3.8066 | 3.24 | 6000 | 4.3173 |
| 3.7866 | 3.51 | 6500 | 4.2872 |
| 3.7701 | 3.78 | 7000 | 4.2562 |
| 3.7022 | 4.05 | 7500 | 4.2455 |
| 3.4888 | 4.32 | 8000 | 4.2468 |
| 3.4902 | 4.59 | 8500 | 4.2348 |
| 3.4834 | 4.86 | 9000 | 4.2222 |
| 3.3882 | 5.13 | 9500 | 4.2306 |
| 3.2957 | 5.4 | 10000 | 4.2306 |
| 3.2966 | 5.67 | 10500 | 4.2293 |
| 3.2954 | 5.94 | 11000 | 4.2286 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
