GPTuz-finetuned-uzwikitext
Bu spaceda text generation modelni test(o'rganish maqsadida) fine-tuned qilingan.
Model asosan 50 MB dataset bilan 1.30 minut oralig'ida bajarildi, Agarda modelga fine-tuning qilmoqchi bo'lsangiz, sizdan kamida 10GB va Google colab Pro version foydalanishni tafsiya qilaman, natia zo'rchiqdi.
It achieves the following results on the evaluation set:
- Loss: 2.8346
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.4436 | 1.0 | 3206 | 2.9914 |
| 2.2235 | 2.0 | 6412 | 2.8723 |
| 2.1544 | 3.0 | 9618 | 2.8346 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Tokenizers 0.15.1
- Downloads last month
- 1