umutarpayy/Fen7_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: 0.1235
• Train Accuracy: 0.9801
• Validation Loss: 0.0685
• Validation Accuracy: 0.9916
• 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': 4817, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 535, '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
3.4524	0.1990	1.7841	0.5706	0
1.4544	0.5916	1.0376	0.6993	1
1.0550	0.6798	0.8457	0.7538	2
0.8618	0.7353	0.6681	0.8056	3
0.6971	0.7867	0.4979	0.8420	4
0.5355	0.8412	0.3540	0.9049	5
0.4035	0.8910	0.2237	0.9343	6
0.3004	0.9224	0.1559	0.9622	7
0.2211	0.9524	0.1146	0.9790	8
0.1767	0.9651	0.0943	0.9804	9
0.1424	0.9739	0.0746	0.9874	10
0.1235	0.9801	0.0685	0.9916	11

Framework versions

• Transformers 4.49.0
• TensorFlow 2.18.0
• Datasets 3.4.1
• Tokenizers 0.21.1