metadata
library_name: transformers
license: mit
base_model: VRLLab/TurkishBERTweet
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: TurkishBERTweet_with_categories
results: []
TurkishBERTweet_with_categories
This model is a fine-tuned version of VRLLab/TurkishBERTweet on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1821
- Precision: 0.2178
- Recall: 0.2136
- F1: 0.2157
- Accuracy: 0.9595
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: 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 |
|---|---|---|---|---|---|---|---|
| 0.2417 | 1.0 | 298 | 0.2246 | 0.1184 | 0.0874 | 0.1006 | 0.9489 |
| 0.1675 | 2.0 | 596 | 0.2198 | 0.18 | 0.1748 | 0.1773 | 0.9537 |
| 0.1071 | 3.0 | 894 | 0.2781 | 0.2703 | 0.1942 | 0.2260 | 0.9539 |
| 0.0622 | 4.0 | 1192 | 0.2997 | 0.1771 | 0.1650 | 0.1709 | 0.9504 |
| 0.0374 | 5.0 | 1490 | 0.3237 | 0.2785 | 0.2136 | 0.2418 | 0.9537 |
Framework versions
- Transformers 4.48.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0