<!-- 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. -->
simple_wikipedia-rarity-seed
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1526
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 |
|---|---|---|---|
| 6.3353 | 0.29 | 500 | 5.3432 |
| 5.0331 | 0.58 | 1000 | 4.9248 |
| 4.7045 | 0.87 | 1500 | 4.6995 |
| 4.4613 | 1.17 | 2000 | 4.5660 |
| 4.3127 | 1.46 | 2500 | 4.4566 |
| 4.2095 | 1.75 | 3000 | 4.3611 |
| 4.1096 | 2.04 | 3500 | 4.3006 |
| 3.9248 | 2.33 | 4000 | 4.2579 |
| 3.8938 | 2.62 | 4500 | 4.2018 |
| 3.8576 | 2.91 | 5000 | 4.1488 |
| 3.6767 | 3.21 | 5500 | 4.1456 |
| 3.6134 | 3.5 | 6000 | 4.1125 |
| 3.5925 | 3.79 | 6500 | 4.0849 |
| 3.5138 | 4.08 | 7000 | 4.0796 |
| 3.3429 | 4.37 | 7500 | 4.0750 |
| 3.3382 | 4.66 | 8000 | 4.0624 |
| 3.328 | 4.95 | 8500 | 4.0507 |
| 3.1885 | 5.24 | 9000 | 4.0623 |
| 3.1615 | 5.54 | 9500 | 4.0621 |
| 3.1534 | 5.83 | 10000 | 4.0617 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
