Turkish-GPT2-mini-ModelA
This model is a fine-tuned version of eminAydin/turkish-gpt2-mini-M1-cleaned-sports720k-20ep on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.4487
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
4.577 | 1.0 | 92 | 4.5116 |
4.0771 | 1.99 | 184 | 4.4504 |
3.833 | 2.99 | 276 | 4.4489 |
3.6125 | 4.0 | 369 | 4.4436 |
3.5061 | 5.0 | 461 | 4.4475 |
3.393 | 5.99 | 553 | 4.4394 |
3.3029 | 6.99 | 645 | 4.4413 |
3.2109 | 8.0 | 738 | 4.4477 |
3.2136 | 9.0 | 830 | 4.4487 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 0