umutarpayy/kimya11_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: 0.1622
• Train Accuracy: 0.9420
• Validation Loss: 0.1268
• Validation Accuracy: 0.9541
• 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': 6318, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 702, '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
2.5503	0.3053	1.1854	0.6154	0
1.0395	0.6669	0.7700	0.7340	1
0.7644	0.7450	0.6048	0.7853	2
0.6294	0.7893	0.5001	0.8269	3
0.5274	0.8217	0.4076	0.8526	4
0.4479	0.8491	0.3462	0.8857	5
0.3747	0.8693	0.2588	0.9167	6
0.3143	0.8908	0.2174	0.9274	7
0.2631	0.9072	0.1678	0.9412	8
0.2238	0.9209	0.1431	0.9530	9
0.1859	0.9344	0.1373	0.9487	10
0.1622	0.9420	0.1268	0.9541	11

Framework versions

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