<!-- 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. -->
bert-base-turkish-cased-product-names-classification
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: 0.2877
- Accuracy: 0.9513
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 1.0 | 416 | 1.6794 | 0.7308 |
3.0588 | 2.0 | 832 | 0.7715 | 0.8660 |
0.9503 | 3.0 | 1248 | 0.5145 | 0.9026 |
0.4787 | 4.0 | 1664 | 0.3971 | 0.9243 |
0.2869 | 5.0 | 2080 | 0.3472 | 0.9285 |
0.2869 | 6.0 | 2496 | 0.3312 | 0.9345 |
0.1842 | 7.0 | 2912 | 0.3000 | 0.9393 |
0.1287 | 8.0 | 3328 | 0.2924 | 0.9447 |
0.0952 | 9.0 | 3744 | 0.2838 | 0.9471 |
0.0723 | 10.0 | 4160 | 0.2936 | 0.9489 |
0.0598 | 11.0 | 4576 | 0.2907 | 0.9495 |
0.0598 | 12.0 | 4992 | 0.2908 | 0.9507 |
0.0432 | 13.0 | 5408 | 0.2844 | 0.9495 |
0.0402 | 14.0 | 5824 | 0.2891 | 0.9507 |
0.031 | 15.0 | 6240 | 0.2877 | 0.9513 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3