gpt2_small_ZH_superbpe_65536_parallel3-100_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 5.2058
- Accuracy: 0.2259
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: 5e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|
| 6.7902 | 1.0 | 4878 | 6.4050 | 0.1555 |
| 6.007 | 2.0 | 9756 | 5.8338 | 0.1838 |
| 5.6839 | 3.0 | 14634 | 5.5847 | 0.1989 |
| 5.499 | 4.0 | 19512 | 5.4491 | 0.2067 |
| 5.3781 | 5.0 | 24390 | 5.3617 | 0.2135 |
| 5.2894 | 6.0 | 29268 | 5.3044 | 0.2177 |
| 5.222 | 7.0 | 34146 | 5.2628 | 0.2207 |
| 5.1681 | 8.0 | 39024 | 5.2334 | 0.2233 |
| 5.1283 | 9.0 | 43902 | 5.2147 | 0.2251 |
| 5.0942 | 10.0 | 48780 | 5.2058 | 0.2259 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
