<!-- 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-concat-simple-wiki-mod-rarity-all-no-cut
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3462
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 |
|---|---|---|---|
| 6.6774 | 0.29 | 500 | 5.6364 |
| 5.3296 | 0.59 | 1000 | 5.2066 |
| 4.9846 | 0.88 | 1500 | 4.9630 |
| 4.7143 | 1.17 | 2000 | 4.8166 |
| 4.5671 | 1.47 | 2500 | 4.6964 |
| 4.4602 | 1.76 | 3000 | 4.6054 |
| 4.3491 | 2.06 | 3500 | 4.5378 |
| 4.1571 | 2.35 | 4000 | 4.4850 |
| 4.1355 | 2.64 | 4500 | 4.4260 |
| 4.0891 | 2.94 | 5000 | 4.3742 |
| 3.8782 | 3.23 | 5500 | 4.3681 |
| 3.8308 | 3.52 | 6000 | 4.3389 |
| 3.8143 | 3.82 | 6500 | 4.2994 |
| 3.6943 | 4.11 | 7000 | 4.3005 |
| 3.5497 | 4.4 | 7500 | 4.2925 |
| 3.5336 | 4.7 | 8000 | 4.2784 |
| 3.5253 | 4.99 | 8500 | 4.2637 |
| 3.357 | 5.28 | 9000 | 4.2795 |
| 3.3454 | 5.58 | 9500 | 4.2779 |
| 3.3495 | 5.87 | 10000 | 4.2771 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
