model_TrainTestSplit_berturk_v2_24Feb
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: 0.0003
- Precision: 0.9999
- Recall: 0.9999
- F1: 0.9999
- Accuracy: 0.9999
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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 196 | 0.0058 | 0.9982 | 0.9980 | 0.9981 | 0.9986 |
| No log | 2.0 | 392 | 0.0042 | 0.9987 | 0.9986 | 0.9986 | 0.9990 |
| 0.0132 | 3.0 | 588 | 0.0042 | 0.9985 | 0.9988 | 0.9986 | 0.9990 |
| 0.0132 | 4.0 | 784 | 0.0022 | 0.9993 | 0.9992 | 0.9992 | 0.9993 |
| 0.0132 | 5.0 | 980 | 0.0020 | 0.9993 | 0.9992 | 0.9993 | 0.9995 |
| 0.0069 | 6.0 | 1176 | 0.0013 | 0.9994 | 0.9994 | 0.9994 | 0.9995 |
| 0.0069 | 7.0 | 1372 | 0.0008 | 0.9997 | 0.9997 | 0.9997 | 0.9998 |
| 0.0035 | 8.0 | 1568 | 0.0008 | 0.9997 | 0.9997 | 0.9997 | 0.9998 |
| 0.0035 | 9.0 | 1764 | 0.0006 | 0.9996 | 0.9997 | 0.9996 | 0.9997 |
| 0.0035 | 10.0 | 1960 | 0.0004 | 0.9998 | 0.9999 | 0.9998 | 0.9999 |
| 0.0019 | 11.0 | 2156 | 0.0003 | 0.9999 | 0.9999 | 0.9999 | 0.9999 |
| 0.0019 | 12.0 | 2352 | 0.0003 | 0.9999 | 0.9999 | 0.9999 | 0.9999 |
| 0.0012 | 13.0 | 2548 | 0.0004 | 0.9999 | 0.9999 | 0.9999 | 0.9999 |
| 0.0012 | 14.0 | 2744 | 0.0003 | 0.9999 | 0.9999 | 0.9999 | 0.9999 |
| 0.0012 | 15.0 | 2940 | 0.0003 | 0.9999 | 0.9999 | 0.9999 | 0.9999 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.0
- Tokenizers 0.13.2
- Downloads last month
- 0
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.