Labira/LabiraPJOK_1_50

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

• Train Loss: 0.1065
• Validation Loss: 7.1445
• Epoch: 45

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': 150, '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	Epoch
1.6494	4.1520	0
1.6128	4.3365	1
1.2043	4.6166	2
1.1480	4.5769	3
1.0336	5.1587	4
0.8954	5.2969	5
0.7306	5.4294	6
0.7589	5.2671	7
0.5728	5.2392	8
0.6026	5.6260	9
0.3001	6.3308	10
0.3688	6.4235	11
0.2650	5.8635	12
0.3598	5.5841	13
0.2204	5.8293	14
0.2078	6.1692	15
0.1080	6.4491	16
0.1985	6.4271	17
0.0852	6.2699	18
0.1295	6.3012	19
0.0857	6.6709	20
0.0957	7.0530	21
0.0843	7.2611	22
0.2785	7.1146	23
0.0894	6.9268	24
0.1080	7.1326	25
0.0535	7.5213	26
0.3044	7.5237	27
0.1145	7.3478	28
0.0558	7.2094	29
0.1047	7.0415	30
0.0498	7.0443	31
0.1680	7.0692	32
0.1997	7.1370	33
0.0362	7.1806	34
0.0332	7.2268	35
0.0596	7.2691	36
0.0537	7.2544	37
0.0422	7.1536	38
0.0460	7.1102	39
0.0542	7.0963	40
0.0390	7.1052	41
0.2518	7.1087	42
0.1056	7.1267	43
0.0403	7.1337	44
0.1065	7.1445	45

Framework versions

• Transformers 4.44.2
• TensorFlow 2.17.0
• Datasets 3.0.1
• Tokenizers 0.19.1