Alex034/typo_classifier_2023

This model is a fine-tuned version of cahya/bert-base-indonesian-1.5G on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.2560
• Validation Loss: 0.2439
• Train Accuracy: 0.9079
• Epoch: 9

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': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 12930, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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
0.5254	0.4244	0.8645	0
0.3893	0.3439	0.8841	1
0.3352	0.3051	0.8900	2
0.3048	0.2825	0.8947	3
0.2858	0.2677	0.8993	4
0.2736	0.2580	0.9021	5
0.2671	0.2519	0.9044	6
0.2617	0.2475	0.9066	7
0.2586	0.2447	0.9079	8
0.2560	0.2439	0.9079	9

Framework versions

• Transformers 4.35.0
• TensorFlow 2.13.0
• Datasets 2.1.0
• Tokenizers 0.14.1