checkpoints_berturk
This model is a fine-tuned version of dbmdz/bert-base-turkish-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1264
- Accuracy: 0.9633
- Macro F1: 0.9595
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
|---|---|---|---|---|---|
| 1.4009 | 1.0 | 32 | 1.1257 | 0.5413 | 0.5372 |
| 0.9029 | 2.0 | 64 | 0.6056 | 0.8257 | 0.8242 |
| 0.5490 | 3.0 | 96 | 0.1996 | 0.9725 | 0.9704 |
| 0.1897 | 4.0 | 128 | 0.1376 | 0.9633 | 0.9595 |
| 0.1026 | 5.0 | 160 | 0.1264 | 0.9633 | 0.9595 |
Framework versions
- Transformers 5.10.2
- Pytorch 2.11.0+cpu
- Datasets 4.0.0
- Tokenizers 0.22.2