metadata
library_name: transformers
license: mit
base_model: dbmdz/bert-base-turkish-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-turkish-cased2
results: []
bert-base-turkish-cased2
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: 0.1156
- Precision: 0.6818
- Recall: 0.6034
- F1: 0.6402
- Accuracy: 0.9651
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
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.127 | 1.0 | 298 | 0.1456 | 0.8619 | 0.2063 | 0.3330 | 0.9567 |
| 0.0795 | 2.0 | 596 | 0.1171 | 0.7381 | 0.5741 | 0.6458 | 0.9670 |
| 0.0434 | 3.0 | 894 | 0.1624 | 0.7921 | 0.4233 | 0.5517 | 0.9639 |
| 0.0195 | 4.0 | 1192 | 0.1800 | 0.7534 | 0.5093 | 0.6077 | 0.9655 |
| 0.0097 | 5.0 | 1490 | 0.1936 | 0.7682 | 0.5437 | 0.6367 | 0.9675 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0