Turkish-GPT2-mini-ModelB
This model is a fine-tuned version of eminAydin/turkish-gpt2-mini-M2-cleaned-politics720k-20ep on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.0370
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 |
---|---|---|---|
4.4407 | 1.0 | 105 | 4.3549 |
3.7151 | 2.0 | 211 | 4.2113 |
3.4445 | 3.0 | 316 | 4.1424 |
3.1961 | 4.0 | 422 | 4.0877 |
3.063 | 5.0 | 527 | 4.0599 |
2.9136 | 6.0 | 633 | 4.0505 |
2.8495 | 7.0 | 738 | 4.0388 |
2.7652 | 8.0 | 844 | 4.0370 |
2.7571 | 9.0 | 949 | 4.0367 |
2.7437 | 9.95 | 1050 | 4.0370 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 2