metadata

license: mit
base_model: indobenchmark/indobert-base-p1
tags:
  - generated_from_keras_callback
model-index:
  - name: aditnnda/gacoanReviewer
    results: []

aditnnda/gacoanReviewer

This model is a fine-tuned version of indobenchmark/indobert-base-p1 on an unknown dataset. It achieves the following results on the evaluation set:

Train Loss: 0.0001
Validation Loss: 0.5471
Train Accuracy: 0.9163
Epoch: 24

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': 3550, '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
0.2751	0.2043	0.9107	0
0.1202	0.2077	0.9177	1
0.0583	0.2770	0.9079	2
0.0435	0.3412	0.9066	3
0.0251	0.3762	0.9079	4
0.0208	0.2241	0.9303	5
0.0070	0.2794	0.9317	6
0.0151	0.3823	0.9219	7
0.0088	0.3740	0.9261	8
0.0019	0.4286	0.9261	9
0.0030	0.6086	0.8912	10
0.0052	0.4023	0.9344	11
0.0005	0.5193	0.9121	12
0.0002	0.5171	0.9135	13
0.0002	0.5276	0.9163	14
0.0002	0.5344	0.9135	15
0.0002	0.5362	0.9163	16
0.0001	0.5407	0.9163	17
0.0001	0.5406	0.9163	18
0.0001	0.5484	0.9149	19
0.0001	0.5406	0.9177	20
0.0001	0.5431	0.9177	21
0.0001	0.5453	0.9163	22
0.0001	0.5466	0.9163	23
0.0001	0.5471	0.9163	24

Framework versions

Transformers 4.35.2
TensorFlow 2.15.0
Datasets 2.15.0
Tokenizers 0.15.0