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: 0.5271
- Precision: 0.4533
- Recall: 0.4378
- F1: 0.4454
- Accuracy: 0.8407
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 |
|---|---|---|---|---|---|---|---|
| 0.7102 | 1.0 | 105 | 0.5722 | 0.6 | 0.1720 | 0.2673 | 0.8499 |
| 0.4812 | 2.0 | 210 | 0.4792 | 0.5023 | 0.3439 | 0.4083 | 0.8645 |
| 0.3025 | 3.0 | 315 | 0.5154 | 0.3987 | 0.4013 | 0.4 | 0.8523 |
| 0.1848 | 4.0 | 420 | 0.6540 | 0.4181 | 0.5446 | 0.4730 | 0.8327 |
| 0.1135 | 5.0 | 525 | 0.6031 | 0.4959 | 0.5828 | 0.5359 | 0.8587 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0