umutarpayy/bersos_turkce_6_v6

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: 0.0602
• Train Accuracy: 0.9886
• Validation Loss: 0.0337
• Validation Accuracy: 0.9929
• 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': 4752, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 528, '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
2.7646	0.2619	1.3859	0.6525	0
1.2234	0.6646	0.8642	0.7504	1
0.9232	0.7325	0.6745	0.8071	2
0.7210	0.7911	0.5282	0.8482	3
0.5421	0.8470	0.3159	0.9121	4
0.3950	0.8916	0.2143	0.9461	5
0.2825	0.9271	0.1455	0.9574	6
0.1980	0.9526	0.1037	0.9745	7
0.1476	0.9631	0.0575	0.9858	8
0.1004	0.9783	0.0430	0.9901	9
0.0761	0.9835	0.0346	0.9943	10
0.0602	0.9886	0.0337	0.9929	11

Framework versions

• Transformers 4.47.1
• TensorFlow 2.18.0
• Datasets 3.2.0
• Tokenizers 0.21.0