metadata
license: other
base_model: boun-tabi-LMG/TURNA
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: TURNA_emotion_single
results: []
TURNA_emotion_single
This model is a fine-tuned version of boun-tabi-LMG/TURNA on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5223
- Accuracy: 0.908
- Precision: 0.9133
- Recall: 0.908
- F1: 0.9065
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 0.4 | 50 | 1.5118 | 0.48 | 0.4815 | 0.48 | 0.3654 |
| No log | 0.8 | 100 | 0.9884 | 0.655 | 0.8127 | 0.655 | 0.5878 |
| 1.1187 | 1.2 | 150 | 1.2171 | 0.66 | 0.7893 | 0.66 | 0.6006 |
| 1.1187 | 1.6 | 200 | 1.2756 | 0.68 | 0.8250 | 0.68 | 0.6289 |
| 0.1624 | 2.0 | 250 | 1.3194 | 0.715 | 0.8334 | 0.715 | 0.6729 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
Citation Information
Uludoğan, G., Balal, Z. Y., Akkurt, F., Türker, M., Güngör, O., & Üsküdarlı, S. (2024).
Turna: A turkish encoder-decoder language model for enhanced understanding and generation. arXiv preprint arXiv:2401.14373.