YSKartal/bert-base-cased-finetuned-ref_disam

This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 5.2706
• Validation Loss: 6.4898
• Train Accuracy: 0.0484
• Epoch: 5

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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 10352, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Accuracy	Epoch
7.0987	7.2119	0.0133	0
6.2071	6.8066	0.0271	1
5.6562	6.5590	0.0410	2
5.3508	6.4898	0.0484	3
5.2693	6.4898	0.0484	4
5.2706	6.4898	0.0484	5

Framework versions

• Transformers 4.27.3
• TensorFlow 2.11.0
• Datasets 2.10.1
• Tokenizers 0.13.2