metadata
license: mit
base_model: burakaytan/roberta-base-turkish-uncased
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: laptop_kriter
results: []
laptop_kriter
This model is a fine-tuned version of burakaytan/roberta-base-turkish-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2151
- F1: 0.7709
- Roc Auc: 0.8574
- Accuracy: 0.7344
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: 2e-05
- train_batch_size: 2
- eval_batch_size: 2
- 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 | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.3066 | 1.0 | 1151 | 0.2457 | 0.5688 | 0.7257 | 0.6484 |
| 0.2325 | 2.0 | 2302 | 0.2088 | 0.6630 | 0.7908 | 0.6719 |
| 0.1723 | 3.0 | 3453 | 0.2023 | 0.6933 | 0.8174 | 0.6875 |
| 0.159 | 4.0 | 4604 | 0.2004 | 0.7312 | 0.8363 | 0.7188 |
| 0.1306 | 5.0 | 5755 | 0.2138 | 0.7168 | 0.8104 | 0.7148 |
| 0.1034 | 6.0 | 6906 | 0.2103 | 0.7745 | 0.8641 | 0.7539 |
| 0.0865 | 7.0 | 8057 | 0.2107 | 0.7684 | 0.8530 | 0.75 |
| 0.0733 | 8.0 | 9208 | 0.2099 | 0.7757 | 0.8663 | 0.7383 |
| 0.0643 | 9.0 | 10359 | 0.2130 | 0.7772 | 0.8586 | 0.7539 |
| 0.0617 | 10.0 | 11510 | 0.2151 | 0.7709 | 0.8574 | 0.7344 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0