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: irem_5e-05_4_10_categorize
results: []
irem_5e-05_4_10_categorize
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: 0.8459
- Precision: 0.2556
- Recall: 0.2403
- F1: 0.2477
- Accuracy: 0.8883
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: 4
- eval_batch_size: 4
- 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2701 | 1.0 | 672 | 0.1902 | 0.125 | 0.0926 | 0.1064 | 0.9460 |
| 0.2016 | 2.0 | 1344 | 0.1750 | 0.1173 | 0.1759 | 0.1407 | 0.9453 |
| 0.1195 | 3.0 | 2016 | 0.2107 | 0.1880 | 0.2315 | 0.2075 | 0.9476 |
| 0.0776 | 4.0 | 2688 | 0.2238 | 0.1397 | 0.1759 | 0.1557 | 0.9473 |
| 0.0314 | 5.0 | 3360 | 0.2438 | 0.2057 | 0.2685 | 0.2329 | 0.9506 |
| 0.022 | 6.0 | 4032 | 0.3185 | 0.2231 | 0.25 | 0.2358 | 0.9498 |
| 0.0165 | 7.0 | 4704 | 0.3448 | 0.2177 | 0.25 | 0.2328 | 0.9494 |
| 0.0078 | 8.0 | 5376 | 0.3405 | 0.2308 | 0.2778 | 0.2521 | 0.9501 |
| 0.0035 | 9.0 | 6048 | 0.3445 | 0.2121 | 0.2593 | 0.2333 | 0.9484 |
| 0.0035 | 10.0 | 6720 | 0.3680 | 0.2273 | 0.2778 | 0.25 | 0.9489 |
Framework versions
- Transformers 4.48.2
- Pytorch 2.6.0+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0