<!-- 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-9-210k-mod-datasets
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 5.0528
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 |
|---|---|---|---|
| 6.3046 | 0.06 | 500 | 5.9519 |
| 5.0135 | 0.13 | 1000 | 5.5816 |
| 4.7368 | 0.19 | 1500 | 5.3952 |
| 4.5486 | 0.26 | 2000 | 5.2773 |
| 4.412 | 0.32 | 2500 | 5.2062 |
| 4.3027 | 0.39 | 3000 | 5.1514 |
| 4.1991 | 0.45 | 3500 | 5.1160 |
| 4.1058 | 0.52 | 4000 | 5.0827 |
| 4.0144 | 0.58 | 4500 | 5.0443 |
| 3.9241 | 0.65 | 5000 | 5.0280 |
| 3.8441 | 0.71 | 5500 | 5.0056 |
| 3.7614 | 0.78 | 6000 | 4.9986 |
| 3.7094 | 0.84 | 6500 | 4.9807 |
| 3.6717 | 0.91 | 7000 | 4.9782 |
| 3.6519 | 0.97 | 7500 | 4.9763 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
