<!-- 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. -->
guten-log-rarity
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1085
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 |
---|---|---|---|
6.3399 | 0.29 | 500 | 5.3371 |
5.0398 | 0.58 | 1000 | 4.9192 |
4.6956 | 0.87 | 1500 | 4.6871 |
4.4399 | 1.16 | 2000 | 4.5482 |
4.2944 | 1.46 | 2500 | 4.4250 |
4.1926 | 1.75 | 3000 | 4.3221 |
4.0782 | 2.04 | 3500 | 4.2542 |
3.8913 | 2.33 | 4000 | 4.2078 |
3.8644 | 2.62 | 4500 | 4.1535 |
3.8283 | 2.91 | 5000 | 4.1029 |
3.6399 | 3.2 | 5500 | 4.1006 |
3.5829 | 3.49 | 6000 | 4.0681 |
3.5631 | 3.79 | 6500 | 4.0411 |
3.4868 | 4.08 | 7000 | 4.0380 |
3.3087 | 4.37 | 7500 | 4.0326 |
3.3097 | 4.66 | 8000 | 4.0188 |
3.3016 | 4.95 | 8500 | 4.0055 |
3.1531 | 5.24 | 9000 | 4.0191 |
3.1275 | 5.53 | 9500 | 4.0183 |
3.126 | 5.82 | 10000 | 4.0171 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3