metadata
library_name: transformers
license: mit
base_model: VRLLab/TurkishBERTweet
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: TurkishBERTweet
results: []
TurkishBERTweet
This model is a fine-tuned version of VRLLab/TurkishBERTweet on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1966
- Precision: 0.4301
- Recall: 0.3604
- F1: 0.3922
- Accuracy: 0.9591
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 |
|---|---|---|---|---|---|---|---|
| 0.1734 | 1.0 | 230 | 0.1177 | 0.1495 | 0.1818 | 0.1641 | 0.9667 |
| 0.1235 | 2.0 | 460 | 0.1159 | 0.4394 | 0.3295 | 0.3766 | 0.9699 |
| 0.0779 | 3.0 | 690 | 0.1331 | 0.3483 | 0.3523 | 0.3503 | 0.9715 |
| 0.0564 | 4.0 | 920 | 0.1152 | 0.4286 | 0.375 | 0.4000 | 0.9756 |
| 0.0302 | 5.0 | 1150 | 0.1620 | 0.3830 | 0.4091 | 0.3956 | 0.9722 |
| 0.0226 | 6.0 | 1380 | 0.1654 | 0.3786 | 0.4432 | 0.4084 | 0.9749 |
| 0.0087 | 7.0 | 1610 | 0.1906 | 0.4875 | 0.4432 | 0.4643 | 0.9750 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3