<!-- 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. -->
gpt2-cl-rarity-modified-datasets
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.7776
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: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.6195 | 0.05 | 500 | 5.8643 |
| 5.3457 | 0.1 | 1000 | 5.4503 |
| 5.0121 | 0.15 | 1500 | 5.2455 |
| 4.7787 | 0.2 | 2000 | 5.1007 |
| 4.615 | 0.26 | 2500 | 5.0312 |
| 4.488 | 0.31 | 3000 | 4.9546 |
| 4.3734 | 0.36 | 3500 | 4.9068 |
| 4.259 | 0.41 | 4000 | 4.8614 |
| 4.1719 | 0.46 | 4500 | 4.8338 |
| 4.0864 | 0.51 | 5000 | 4.8095 |
| 3.9943 | 0.56 | 5500 | 4.7851 |
| 3.9112 | 0.61 | 6000 | 4.7684 |
| 3.8242 | 0.67 | 6500 | 4.7537 |
| 3.7503 | 0.72 | 7000 | 4.7429 |
| 3.686 | 0.77 | 7500 | 4.7318 |
| 3.6406 | 0.82 | 8000 | 4.7279 |
| 3.5975 | 0.87 | 8500 | 4.7238 |
| 3.5778 | 0.92 | 9000 | 4.7213 |
| 3.5637 | 0.97 | 9500 | 4.7194 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
