<!-- 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-8-276k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 5.0899
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 |
|---|---|---|---|
| 6.3323 | 0.05 | 500 | 5.9421 |
| 5.032 | 0.1 | 1000 | 5.5886 |
| 4.7579 | 0.15 | 1500 | 5.3936 |
| 4.5703 | 0.2 | 2000 | 5.2874 |
| 4.4393 | 0.25 | 2500 | 5.2097 |
| 4.3401 | 0.3 | 3000 | 5.1646 |
| 4.2459 | 0.35 | 3500 | 5.1279 |
| 4.1527 | 0.4 | 4000 | 5.1053 |
| 4.069 | 0.45 | 4500 | 5.0732 |
| 3.9905 | 0.5 | 5000 | 5.0548 |
| 3.9063 | 0.55 | 5500 | 5.0423 |
| 3.8291 | 0.6 | 6000 | 5.0330 |
| 3.7463 | 0.65 | 6500 | 5.0260 |
| 3.6706 | 0.7 | 7000 | 5.0294 |
| 3.6096 | 0.75 | 7500 | 5.0213 |
| 3.5477 | 0.8 | 8000 | 5.0179 |
| 3.5038 | 0.85 | 8500 | 5.0168 |
| 3.4811 | 0.9 | 9000 | 5.0151 |
| 3.4619 | 0.95 | 9500 | 5.0138 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
