<!-- 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-mod-datasets-rarity1-rerun
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 2.9787
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 |
|---|---|---|---|
| 6.7084 | 0.28 | 500 | 5.6576 |
| 5.3752 | 0.55 | 1000 | 5.2425 |
| 5.0307 | 0.83 | 1500 | 4.9836 |
| 4.7909 | 1.1 | 2000 | 4.8439 |
| 4.5953 | 1.38 | 2500 | 4.7316 |
| 4.5122 | 1.65 | 3000 | 4.6381 |
| 4.427 | 1.93 | 3500 | 4.5558 |
| 4.2204 | 2.2 | 4000 | 4.5216 |
| 4.1628 | 2.48 | 4500 | 4.4629 |
| 4.1262 | 2.75 | 5000 | 4.4110 |
| 4.0687 | 3.03 | 5500 | 4.3795 |
| 3.844 | 3.3 | 6000 | 4.3767 |
| 3.8487 | 3.58 | 6500 | 4.3454 |
| 3.839 | 3.85 | 7000 | 4.3102 |
| 3.6914 | 4.13 | 7500 | 4.3299 |
| 3.5631 | 4.4 | 8000 | 4.3255 |
| 3.5612 | 4.68 | 8500 | 4.3048 |
| 3.5508 | 4.95 | 9000 | 4.2833 |
| 3.3422 | 5.23 | 9500 | 4.3169 |
| 3.3036 | 5.5 | 10000 | 4.3117 |
| 3.3052 | 5.78 | 10500 | 4.3068 |
| 3.267 | 6.05 | 11000 | 4.3145 |
| 3.1427 | 6.33 | 11500 | 4.3211 |
| 3.1445 | 6.6 | 12000 | 4.3209 |
| 3.1484 | 6.88 | 12500 | 4.3213 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
