umutarpayy/zorluk_duzeyi_tespit_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: 0.0412
• Train Accuracy: 0.9850
• Validation Loss: 0.0169
• Validation Accuracy: 0.9935
• Epoch: 12

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': 106365, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 11818, '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
1.3161	0.4321	1.1777	0.5137	0
1.1633	0.5191	0.9971	0.6030	1
0.9911	0.6005	0.7380	0.7232	2
0.7800	0.6967	0.5147	0.8194	3
0.5823	0.7785	0.3435	0.8829	4
0.4247	0.8421	0.2016	0.9359	5
0.3047	0.8891	0.1348	0.9578	6
0.2179	0.9221	0.0790	0.9762	7
0.1566	0.9451	0.0561	0.9821	8
0.1103	0.9622	0.0386	0.9871	9
0.0806	0.9719	0.0239	0.9923	10
0.0572	0.9797	0.0212	0.9921	11
0.0412	0.9850	0.0169	0.9935	12

Framework versions

• Transformers 4.51.3
• TensorFlow 2.18.0
• Datasets 3.5.1
• Tokenizers 0.21.1