damand2061/innermore-x-indobert-base-p1

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: 0.0007
• Validation Loss: 0.2387
• Validation Precision: 0.7583
• Validation Recall: 0.6987
• Validation F1: 0.7273
• Validation Accuracy: 0.9535
• Epoch: 14

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': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0002, 'decay_steps': 420, '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, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Validation Loss	Validation Precision	Validation Recall	Validation F1	Validation Accuracy	Epoch
0.5438	0.2878	0.5065	0.5109	0.5087	0.9161	0
0.1798	0.1890	0.6416	0.6332	0.6374	0.9425	1
0.0764	0.2122	0.5833	0.5502	0.5663	0.9338	2
0.0491	0.1986	0.7729	0.6987	0.7339	0.9545	3
0.0333	0.2071	0.75	0.6812	0.7140	0.9545	4
0.0252	0.1806	0.7456	0.7424	0.7440	0.9530	5
0.0138	0.2283	0.7018	0.6987	0.7002	0.9497	6
0.0073	0.2202	0.7318	0.7031	0.7171	0.9530	7
0.0065	0.2174	0.7762	0.7118	0.7426	0.9540	8
0.0037	0.2373	0.7619	0.6987	0.7289	0.9516	9
0.0021	0.2343	0.7594	0.7031	0.7302	0.9535	10
0.0015	0.2478	0.7546	0.7118	0.7326	0.9530	11
0.0011	0.2405	0.7630	0.7031	0.7318	0.9540	12
0.0006	0.2388	0.7583	0.6987	0.7273	0.9535	13
0.0007	0.2387	0.7583	0.6987	0.7273	0.9535	14

Framework versions

• Transformers 4.38.2
• TensorFlow 2.15.0
• Tokenizers 0.15.2