<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
umit_42000news_convbert_uncased
This model is a fine-tuned version of dbmdz/convbert-base-turkish-mc4-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0049
- Accuracy: 0.6654
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.1237 | 1.0 | 1584 | 1.1773 | 0.5974 |
1.1288 | 2.0 | 3168 | 1.0300 | 0.6521 |
0.6861 | 3.0 | 4752 | 1.0049 | 0.6654 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.10.1
- Tokenizers 0.13.2