metadata
library_name: transformers
license: mit
base_model: VRLLab/TurkishBERTweet
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: TurkishBERTweet2_with_categories
results: []
TurkishBERTweet2_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: 0.1788
- Precision: 0.3611
- Recall: 0.2006
- F1: 0.2579
- Accuracy: 0.9585
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 |
|---|---|---|---|---|---|---|---|
| 0.279 | 1.0 | 298 | 0.2864 | 0.0 | 0.0 | 0.0 | 0.9420 |
| 0.2286 | 2.0 | 596 | 0.2713 | 0.25 | 0.0588 | 0.0952 | 0.9472 |
| 0.1702 | 3.0 | 894 | 0.2439 | 0.3130 | 0.1148 | 0.1680 | 0.9517 |
| 0.1181 | 4.0 | 1192 | 0.2775 | 0.2473 | 0.1261 | 0.1670 | 0.9496 |
| 0.0852 | 5.0 | 1490 | 0.3034 | 0.3274 | 0.1541 | 0.2095 | 0.9510 |
| 0.0502 | 6.0 | 1788 | 0.3130 | 0.3605 | 0.2353 | 0.2847 | 0.9532 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0