metadata
license: mit
base_model: dbmdz/bert-base-turkish-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: BERTurk_hate_span_all
results: []
BERTurk_hate_span_all
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: 0.1292
- Precision: 0.6325
- Recall: 0.5175
- F1: 0.5692
- Accuracy: 0.9700
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: 8
- eval_batch_size: 8
- 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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1724 | 1.0 | 230 | 0.1273 | 0.2477 | 0.4907 | 0.3292 | 0.9597 |
| 0.1228 | 2.0 | 460 | 0.1410 | 0.3866 | 0.4259 | 0.4053 | 0.9684 |
| 0.0564 | 3.0 | 690 | 0.1094 | 0.3955 | 0.4907 | 0.4380 | 0.9719 |
| 0.0414 | 4.0 | 920 | 0.1226 | 0.5192 | 0.5 | 0.5094 | 0.9739 |
| 0.0165 | 5.0 | 1150 | 0.1548 | 0.4359 | 0.4722 | 0.4533 | 0.9713 |
| 0.0069 | 6.0 | 1380 | 0.1959 | 0.5604 | 0.4722 | 0.5126 | 0.9749 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1