<!-- 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-128k-cased-product-names
This model is a fine-tuned version of dbmdz/bert-base-turkish-128k-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0667
- Accuracy: 0.9904
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 364 | 0.0598 | 0.9810 |
| 0.1386 | 2.0 | 728 | 0.0570 | 0.9872 |
| 0.056 | 3.0 | 1092 | 0.0594 | 0.9880 |
| 0.056 | 4.0 | 1456 | 0.0559 | 0.9896 |
| 0.0346 | 5.0 | 1820 | 0.0565 | 0.9892 |
| 0.0173 | 6.0 | 2184 | 0.0667 | 0.9904 |
| 0.0083 | 7.0 | 2548 | 0.0686 | 0.9894 |
| 0.0083 | 8.0 | 2912 | 0.0725 | 0.9894 |
| 0.0091 | 9.0 | 3276 | 0.0716 | 0.9902 |
| 0.0047 | 10.0 | 3640 | 0.0762 | 0.9894 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.0
- Datasets 2.14.5
- Tokenizers 0.13.3
