eraydikyologlu/bert_kazanim_model_20

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:

• Train Loss: 0.0119
• Epoch: 19

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:

• optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 8340, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Epoch
0.3839	0
0.2565	1
0.1910	2
0.1553	3
0.1412	4
0.1205	5
0.0937	6
0.0762	7
0.0622	8
0.0569	9
0.0490	10
0.0378	11
0.0348	12
0.0317	13
0.0249	14
0.0206	15
0.0172	16
0.0154	17
0.0140	18
0.0119	19

Framework versions

• Transformers 4.47.1
• TensorFlow 2.17.1
• Datasets 3.2.0
• Tokenizers 0.21.0