<!-- 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. -->
guten-rarity-all-2p5k-plus-wiki-syn-2-14k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3262
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 |
|---|---|---|---|
| 6.7039 | 0.28 | 500 | 5.6292 |
| 5.317 | 0.56 | 1000 | 5.1996 |
| 4.965 | 0.84 | 1500 | 4.9486 |
| 4.6889 | 1.12 | 2000 | 4.8034 |
| 4.5184 | 1.4 | 2500 | 4.6831 |
| 4.4048 | 1.68 | 3000 | 4.5851 |
| 4.3153 | 1.96 | 3500 | 4.4936 |
| 4.0978 | 2.23 | 4000 | 4.4584 |
| 4.0527 | 2.51 | 4500 | 4.4060 |
| 4.0205 | 2.79 | 5000 | 4.3531 |
| 3.9215 | 3.07 | 5500 | 4.3385 |
| 3.7414 | 3.35 | 6000 | 4.3158 |
| 3.741 | 3.63 | 6500 | 4.2861 |
| 3.7226 | 3.91 | 7000 | 4.2584 |
| 3.5373 | 4.19 | 7500 | 4.2741 |
| 3.4612 | 4.47 | 8000 | 4.2627 |
| 3.462 | 4.75 | 8500 | 4.2509 |
| 3.4281 | 5.03 | 9000 | 4.2514 |
| 3.2731 | 5.31 | 9500 | 4.2551 |
| 3.2696 | 5.59 | 10000 | 4.2549 |
| 3.2714 | 5.87 | 10500 | 4.2542 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
