metadata

base_model: bert-base-chinese
tags:
  - generated_from_keras_callback
model-index:
  - name: Hzmin9/my_awesome_model
    results: []

Hzmin9/my_awesome_model

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

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

optimizer: {'name': 'Adam', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2250, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
training_precision: float32

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
2.0541	0.595	1.5183	0.5950	0
1.3021	0.6125	1.2977	0.6125	1
0.9285	0.6625	1.2059	0.6625	2
0.7071	0.6625	1.1796	0.6625	3
0.5354	0.6525	1.2179	0.6525	4
0.4165	0.6825	1.1801	0.6825	5
0.3302	0.6675	1.3224	0.6675	6
0.2655	0.6725	1.3056	0.6725	7
0.2195	0.6675	1.3366	0.6675	8
0.1928	0.6725	1.3273	0.6725	9