<!-- 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. -->
aochildes-log-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: 4.3494
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 |
---|---|---|---|
6.7012 | 0.29 | 500 | 5.6318 |
5.3412 | 0.59 | 1000 | 5.2043 |
4.9942 | 0.88 | 1500 | 4.9555 |
4.7162 | 1.17 | 2000 | 4.8127 |
4.5637 | 1.47 | 2500 | 4.6882 |
4.4549 | 1.76 | 3000 | 4.5863 |
4.3244 | 2.05 | 3500 | 4.5156 |
4.1353 | 2.35 | 4000 | 4.4659 |
4.0987 | 2.64 | 4500 | 4.4137 |
4.0704 | 2.93 | 5000 | 4.3586 |
3.8584 | 3.23 | 5500 | 4.3513 |
3.8035 | 3.52 | 6000 | 4.3279 |
3.7832 | 3.81 | 6500 | 4.2999 |
3.6738 | 4.11 | 7000 | 4.3075 |
3.5158 | 4.4 | 7500 | 4.2989 |
3.5108 | 4.69 | 8000 | 4.2880 |
3.4999 | 4.99 | 8500 | 4.2787 |
3.3285 | 5.28 | 9000 | 4.2964 |
3.3229 | 5.57 | 9500 | 4.2965 |
3.3189 | 5.87 | 10000 | 4.2951 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3