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: 0.1457
- Precision: 0.5116
- Recall: 0.3964
- F1: 0.4467
- Accuracy: 0.9618
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 |
|---|---|---|---|---|---|---|---|
| 0.1975 | 1.0 | 230 | 0.1641 | 0.6471 | 0.25 | 0.3607 | 0.9667 |
| 0.1939 | 2.0 | 460 | 0.1492 | 0.4912 | 0.3182 | 0.3862 | 0.9673 |
| 0.1543 | 3.0 | 690 | 0.1448 | 0.3103 | 0.3068 | 0.3086 | 0.9680 |
| 0.1571 | 4.0 | 920 | 0.1173 | 0.2105 | 0.1818 | 0.1951 | 0.9729 |
| 0.1401 | 5.0 | 1150 | 0.1095 | 0.3140 | 0.3068 | 0.3103 | 0.9732 |
| 0.1101 | 6.0 | 1380 | 0.1175 | 0.3896 | 0.3409 | 0.3636 | 0.9741 |
| 0.0639 | 7.0 | 1610 | 0.1138 | 0.3364 | 0.4091 | 0.3692 | 0.9707 |
| 0.0589 | 8.0 | 1840 | 0.1195 | 0.3838 | 0.4318 | 0.4064 | 0.9719 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3