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: 5e-05_64_10_detect
results: []
5e-05_64_10_detect
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: 0.5204
- Precision: 0.4302
- Recall: 0.4619
- F1: 0.4455
- Accuracy: 0.8994
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 62 | 0.4949 | 0.4191 | 0.5473 | 0.4747 | 0.8857 |
| 0.0228 | 2.0 | 124 | 0.4641 | 0.4825 | 0.5206 | 0.5008 | 0.9054 |
| 0.0228 | 3.0 | 186 | 0.5234 | 0.4415 | 0.5328 | 0.4829 | 0.8997 |
| 0.0188 | 4.0 | 248 | 0.5468 | 0.5196 | 0.5006 | 0.5099 | 0.9059 |
| 0.0144 | 5.0 | 310 | 0.5661 | 0.4424 | 0.5339 | 0.4839 | 0.8961 |
Framework versions
- Transformers 4.48.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0