umutarpayy/tarih11_bert

umutarpayy/tarih11v_bert

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: 0.3840
• Train Accuracy: 0.8680
• Validation Loss: 0.2637
• Validation Accuracy: 0.9058
• 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': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 3e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 3856, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 428, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, '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
2.8081	0.1691	2.0039	0.4014	0
1.8655	0.4074	1.4399	0.5428	1
1.4976	0.5100	1.1151	0.6475	2
1.2692	0.5821	0.9070	0.7068	3
1.0687	0.6476	0.6802	0.7976	4
0.9017	0.6984	0.5772	0.8185	5
0.7475	0.7511	0.4778	0.8639	6
0.6290	0.7934	0.3831	0.8778	7
0.5501	0.8141	0.3291	0.9005	8
0.4693	0.8363	0.2908	0.9023	9
0.4157	0.8598	0.2763	0.9040	10
0.3840	0.8680	0.2637	0.9058	11

Framework versions

• Transformers 4.48.3
• TensorFlow 2.18.0
• Datasets 3.4.1
• Tokenizers 0.21.1