bert-base-turkish-cased-D-E

This model is a fine-tuned version of dbmdz/bert-base-turkish-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0375

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.4926	1.0	2404	1.2238
1.1193	2.0	4808	1.0637
0.8506	3.0	7212	1.0375

Framework versions

• Transformers 4.26.0
• Pytorch 2.2.1+cu121
• Datasets 2.9.0
• Tokenizers 0.13.3