vanhuyen/demo

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

• Train Loss: 0.1698
• Train Accuracy: 0.9359
• Validation Loss: 0.0592
• Validation Accuracy: 0.9877
• Epoch: 7

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': 5e-06, 'decay_steps': 24350, '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	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
1.1965	0.5073	0.6710	0.8000	0
0.7393	0.7065	0.2841	0.9377	1
0.4082	0.8426	0.1169	0.9762	2
0.2412	0.9114	0.0674	0.9877	3
0.1738	0.9385	0.0592	0.9877	4
0.1661	0.9405	0.0592	0.9877	5
0.1646	0.9395	0.0590	0.9877	6
0.1698	0.9359	0.0592	0.9877	7

Framework versions

• Transformers 4.44.2
• TensorFlow 2.17.0
• Datasets 3.0.2
• Tokenizers 0.19.1