<!-- 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. -->
gutenberg_fixed-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: 4.1027
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 |
---|---|---|---|
6.3464 | 0.29 | 500 | 5.3385 |
5.0325 | 0.58 | 1000 | 4.9275 |
4.7015 | 0.87 | 1500 | 4.6813 |
4.4439 | 1.16 | 2000 | 4.5384 |
4.2877 | 1.46 | 2500 | 4.4265 |
4.1914 | 1.75 | 3000 | 4.3221 |
4.0739 | 2.04 | 3500 | 4.2465 |
3.8852 | 2.33 | 4000 | 4.2009 |
3.8675 | 2.62 | 4500 | 4.1497 |
3.8215 | 2.91 | 5000 | 4.0969 |
3.6454 | 3.2 | 5500 | 4.0917 |
3.5847 | 3.49 | 6000 | 4.0672 |
3.5639 | 3.79 | 6500 | 4.0323 |
3.4775 | 4.08 | 7000 | 4.0319 |
3.3099 | 4.37 | 7500 | 4.0274 |
3.3121 | 4.66 | 8000 | 4.0128 |
3.2957 | 4.95 | 8500 | 4.0009 |
3.1585 | 5.24 | 9000 | 4.0134 |
3.1319 | 5.53 | 9500 | 4.0121 |
3.1272 | 5.82 | 10000 | 4.0113 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3