metadata
library_name: transformers
license: mit
base_model: VRLLab/TurkishBERTweet
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: TurkishBERTweet2
results: []
TurkishBERTweet2
This model is a fine-tuned version of VRLLab/TurkishBERTweet on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1225
- Precision: 0.8357
- Recall: 0.6374
- F1: 0.7232
- Accuracy: 0.9609
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 |
|---|---|---|---|---|---|---|---|
| 0.1648 | 1.0 | 298 | 0.1416 | 0.8091 | 0.6586 | 0.7261 | 0.9535 |
| 0.1114 | 2.0 | 596 | 0.1698 | 0.8431 | 0.7888 | 0.8151 | 0.9642 |
| 0.064 | 3.0 | 894 | 0.1908 | 0.8459 | 0.7500 | 0.7951 | 0.9622 |
| 0.0331 | 4.0 | 1192 | 0.3295 | 0.8624 | 0.7073 | 0.7772 | 0.9608 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0