Turkish-GPT2-mini-ModelB-v2
This model is a fine-tuned version of eminAydin/turkish-gpt2-mini-M2-cleaned-politics720k-10ep on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.0013
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 |
|---|---|---|---|
| 4.4557 | 1.0 | 105 | 4.2953 |
| 3.6895 | 2.0 | 211 | 4.1427 |
| 3.4175 | 3.0 | 316 | 4.0737 |
| 3.1772 | 4.0 | 422 | 4.0387 |
| 3.0538 | 5.0 | 527 | 4.0180 |
| 2.9085 | 6.0 | 633 | 4.0103 |
| 2.8535 | 7.0 | 738 | 4.0035 |
| 2.7727 | 8.0 | 844 | 4.0013 |
| 2.7713 | 9.0 | 949 | 4.0013 |
| 2.7571 | 9.95 | 1050 | 4.0013 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 10
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.