umutarpayy/bert_sos_6

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: 0.1148
• Train Accuracy: 0.9770
• Validation Loss: 0.0771
• Validation Accuracy: 0.9801
• Epoch: 11

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': 5280, '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	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
2.0415	0.4693	1.1491	0.7021	0
1.0934	0.7011	0.8941	0.7447	1
0.8658	0.7534	0.7142	0.7915	2
0.6968	0.8018	0.5239	0.8553	3
0.5517	0.8419	0.4126	0.8936	4
0.4201	0.8862	0.3014	0.9234	5
0.3271	0.9141	0.2085	0.9461	6
0.2483	0.9411	0.1461	0.9617	7
0.1912	0.9564	0.1246	0.9660	8
0.1575	0.9668	0.0950	0.9730	9
0.1265	0.9744	0.0806	0.9801	10
0.1148	0.9770	0.0771	0.9801	11

Framework versions

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