gpt2_small_DE_superbpe_65536_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 5.1407
- Accuracy: 0.2504
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 |
|---|
| 7.8942 | 1.0 | 1123 | 6.7411 | 0.1782 |
| 6.4338 | 2.0 | 2246 | 5.9303 | 0.2091 |
| 5.8858 | 3.0 | 3369 | 5.6179 | 0.2225 |
| 5.6219 | 4.0 | 4492 | 5.4511 | 0.2304 |
| 5.4539 | 5.0 | 5615 | 5.3375 | 0.2371 |
| 5.3365 | 6.0 | 6738 | 5.2627 | 0.2406 |
| 5.2477 | 7.0 | 7861 | 5.2093 | 0.2452 |
| 5.1762 | 8.0 | 8984 | 5.1732 | 0.2483 |
| 5.0748 | 9.0 | 10107 | 5.1500 | 0.2501 |
| 5.045 | 10.0 | 11230 | 5.1407 | 0.2504 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
