metadata
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
base_model: dbmdz/bert-base-turkish-cased
model-index:
- name: BERTurk_emotion_multi
results: []
BERTurk_emotion_multi
This model is a fine-tuned version of dbmdz/bert-base-turkish-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3919
- Accuracy: 0.859
- Precision: 0.8671
- Recall: 0.859
- F1: 0.8541
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 | 1.6478 | 0.23 | 0.0529 | 0.23 | 0.0860 |
| No log | 0.8 | 100 | 0.6822 | 0.77 | 0.8494 | 0.77 | 0.7556 |
| 1.163 | 1.2 | 150 | 0.7381 | 0.745 | 0.7713 | 0.745 | 0.7431 |
| 1.163 | 1.6 | 200 | 1.2519 | 0.75 | 0.8436 | 0.75 | 0.7028 |
| 0.1426 | 2.0 | 250 | 1.2671 | 0.72 | 0.7730 | 0.72 | 0.6964 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2