<!-- 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-log-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: 4.1528
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 |
---|---|---|---|
6.3397 | 0.29 | 500 | 5.3500 |
5.0305 | 0.58 | 1000 | 4.9322 |
4.7176 | 0.87 | 1500 | 4.7007 |
4.4695 | 1.17 | 2000 | 4.5715 |
4.3034 | 1.46 | 2500 | 4.4625 |
4.2247 | 1.75 | 3000 | 4.3657 |
4.1027 | 2.04 | 3500 | 4.3050 |
3.9238 | 2.33 | 4000 | 4.2594 |
3.8913 | 2.62 | 4500 | 4.2022 |
3.8633 | 2.91 | 5000 | 4.1553 |
3.6726 | 3.21 | 5500 | 4.1434 |
3.6113 | 3.5 | 6000 | 4.1167 |
3.6006 | 3.79 | 6500 | 4.0839 |
3.5168 | 4.08 | 7000 | 4.0827 |
3.3434 | 4.37 | 7500 | 4.0770 |
3.3399 | 4.66 | 8000 | 4.0610 |
3.3254 | 4.95 | 8500 | 4.0501 |
3.1918 | 5.24 | 9000 | 4.0638 |
3.1599 | 5.54 | 9500 | 4.0629 |
3.1599 | 5.83 | 10000 | 4.0621 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3