<!-- 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. -->
qed-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: 4.1244
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 |
---|---|---|---|
6.3525 | 0.29 | 500 | 5.3404 |
5.0484 | 0.58 | 1000 | 4.9249 |
4.7092 | 0.88 | 1500 | 4.6891 |
4.4658 | 1.17 | 2000 | 4.5610 |
4.3116 | 1.46 | 2500 | 4.4365 |
4.2167 | 1.75 | 3000 | 4.3382 |
4.092 | 2.04 | 3500 | 4.2635 |
3.9184 | 2.34 | 4000 | 4.2181 |
3.8863 | 2.63 | 4500 | 4.1659 |
3.8503 | 2.92 | 5000 | 4.1157 |
3.6638 | 3.21 | 5500 | 4.1080 |
3.609 | 3.5 | 6000 | 4.0860 |
3.593 | 3.8 | 6500 | 4.0527 |
3.4993 | 4.09 | 7000 | 4.0485 |
3.3413 | 4.38 | 7500 | 4.0433 |
3.3309 | 4.67 | 8000 | 4.0289 |
3.3234 | 4.96 | 8500 | 4.0165 |
3.1789 | 5.26 | 9000 | 4.0305 |
3.1552 | 5.55 | 9500 | 4.0301 |
3.1529 | 5.84 | 10000 | 4.0296 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3