gpt2_small_KO_superbpe_8192_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 4.2945
- Accuracy: 0.2689
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 |
|---|
| 6.8215 | 1.0 | 1449 | 5.3616 | 0.1846 |
| 5.4234 | 2.0 | 2898 | 4.8575 | 0.2172 |
| 4.7989 | 3.0 | 4347 | 4.6462 | 0.2353 |
| 4.6624 | 4.0 | 5796 | 4.5198 | 0.2472 |
| 4.4904 | 5.0 | 7245 | 4.4448 | 0.2540 |
| 4.4246 | 6.0 | 8694 | 4.3853 | 0.2601 |
| 4.3397 | 7.0 | 10143 | 4.3473 | 0.2637 |
| 4.296 | 8.0 | 11592 | 4.3197 | 0.2662 |
| 4.2495 | 9.0 | 13041 | 4.3026 | 0.2679 |
| 4.2228 | 10.0 | 14490 | 4.2945 | 0.2689 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
