metadata
license: mit
base_model: dbmdz/bert-base-turkish-cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert-duygua15
results: []
bert-duygua15
This model is a fine-tuned version of dbmdz/bert-base-turkish-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3342
- Accuracy: 0.9433
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: 64
- eval_batch_size: 64
- 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 | 75 | 0.1786 | 0.9383 |
| No log | 2.0 | 150 | 0.1796 | 0.945 |
| No log | 3.0 | 225 | 0.2770 | 0.9233 |
| No log | 4.0 | 300 | 0.2481 | 0.9383 |
| No log | 5.0 | 375 | 0.2703 | 0.9408 |
| No log | 6.0 | 450 | 0.2989 | 0.94 |
| 0.0994 | 7.0 | 525 | 0.3262 | 0.9433 |
| 0.0994 | 8.0 | 600 | 0.3299 | 0.9408 |
| 0.0994 | 9.0 | 675 | 0.3213 | 0.9442 |
| 0.0994 | 10.0 | 750 | 0.3342 | 0.9433 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1