<!-- 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-dp-cl-rarity-2
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.8538
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: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.8154 | 0.29 | 500 | 5.8625 |
| 5.5131 | 0.58 | 1000 | 5.4712 |
| 5.1777 | 0.87 | 1500 | 5.2785 |
| 4.9215 | 1.15 | 2000 | 5.1669 |
| 4.771 | 1.44 | 2500 | 5.0527 |
| 4.6814 | 1.73 | 3000 | 4.9900 |
| 4.5856 | 2.02 | 3500 | 4.9580 |
| 4.3933 | 2.31 | 4000 | 4.9329 |
| 4.3697 | 2.6 | 4500 | 4.8822 |
| 4.336 | 2.89 | 5000 | 4.8406 |
| 4.1637 | 3.18 | 5500 | 4.8717 |
| 4.0936 | 3.46 | 6000 | 4.8500 |
| 4.0831 | 3.75 | 6500 | 4.8168 |
| 4.028 | 4.04 | 7000 | 4.8076 |
| 3.8111 | 4.33 | 7500 | 4.8192 |
| 3.8157 | 4.62 | 8000 | 4.8051 |
| 3.8032 | 4.91 | 8500 | 4.7920 |
| 3.6328 | 5.2 | 9000 | 4.8242 |
| 3.5632 | 5.48 | 9500 | 4.8342 |
| 3.5601 | 5.77 | 10000 | 4.8337 |
| 3.5208 | 6.06 | 10500 | 4.8434 |
| 3.4092 | 6.35 | 11000 | 4.8511 |
| 3.4088 | 6.64 | 11500 | 4.8524 |
| 3.4029 | 6.93 | 12000 | 4.8538 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
