<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
ayla_ozetler200_bertuncased
This model is a fine-tuned version of dbmdz/bert-base-turkish-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3311
- Accuracy: 0.9
Model description
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.89 | 6 | 1.6870 | 0.4278 |
| 1.7467 | 1.93 | 13 | 1.1508 | 0.6972 |
| 1.0982 | 2.96 | 20 | 0.7106 | 0.8028 |
| 1.0982 | 4.0 | 27 | 0.5116 | 0.85 |
| 0.5588 | 4.89 | 33 | 0.4031 | 0.8694 |
| 0.3365 | 5.93 | 40 | 0.3696 | 0.8778 |
| 0.3365 | 6.96 | 47 | 0.3394 | 0.8806 |
| 0.2345 | 8.0 | 54 | 0.3397 | 0.9 |
| 0.1791 | 8.89 | 60 | 0.3311 | 0.9 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.11.0
