guten-rarity
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1076
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: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.3463 | 0.29 | 500 | 5.3398 |
| 5.0313 | 0.58 | 1000 | 4.9287 |
| 4.7042 | 0.87 | 1500 | 4.6884 |
| 4.4385 | 1.16 | 2000 | 4.5427 |
| 4.294 | 1.46 | 2500 | 4.4285 |
| 4.1966 | 1.75 | 3000 | 4.3204 |
| 4.0779 | 2.04 | 3500 | 4.2444 |
| 3.8836 | 2.33 | 4000 | 4.2115 |
| 3.8596 | 2.62 | 4500 | 4.1536 |
| 3.8337 | 2.91 | 5000 | 4.1065 |
| 3.6462 | 3.2 | 5500 | 4.1009 |
| 3.5855 | 3.49 | 6000 | 4.0714 |
| 3.5628 | 3.79 | 6500 | 4.0399 |
| 3.4858 | 4.08 | 7000 | 4.0352 |
| 3.3143 | 4.37 | 7500 | 4.0331 |
| 3.3117 | 4.66 | 8000 | 4.0203 |
| 3.2978 | 4.95 | 8500 | 4.0062 |
| 3.1643 | 5.24 | 9000 | 4.0186 |
| 3.135 | 5.53 | 9500 | 4.0163 |
| 3.1265 | 5.82 | 10000 | 4.0157 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
- Downloads last month
- 10