bnc-rarity
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1160
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 |
|---|---|---|---|
| 6.3515 | 0.29 | 500 | 5.3315 |
| 5.0415 | 0.58 | 1000 | 4.9224 |
| 4.7148 | 0.88 | 1500 | 4.6897 |
| 4.4508 | 1.17 | 2000 | 4.5523 |
| 4.3075 | 1.46 | 2500 | 4.4324 |
| 4.1932 | 1.75 | 3000 | 4.3257 |
| 4.0881 | 2.05 | 3500 | 4.2605 |
| 3.8959 | 2.34 | 4000 | 4.2136 |
| 3.8716 | 2.63 | 4500 | 4.1591 |
| 3.841 | 2.92 | 5000 | 4.1098 |
| 3.6473 | 3.22 | 5500 | 4.1034 |
| 3.5978 | 3.51 | 6000 | 4.0793 |
| 3.5733 | 3.8 | 6500 | 4.0456 |
| 3.4778 | 4.09 | 7000 | 4.0478 |
| 3.3229 | 4.39 | 7500 | 4.0395 |
| 3.3188 | 4.68 | 8000 | 4.0262 |
| 3.3082 | 4.97 | 8500 | 4.0132 |
| 3.1558 | 5.26 | 9000 | 4.0267 |
| 3.1411 | 5.56 | 9500 | 4.0268 |
| 3.1377 | 5.85 | 10000 | 4.0257 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
- Downloads last month
- 4