metadata

library_name: transformers
license: mit
base_model: indolem/indobert-base-uncased
tags:
  - generated_from_keras_callback
model-index:
  - name: Labira/LabiraPJOK_1_500
    results: []

Labira/LabiraPJOK_1_500

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: 0.0005
Validation Loss: 7.9553
Epoch: 137

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': 1500, '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
0.0054	8.3302	0
0.0108	7.8442	1
0.0114	7.0958	2
0.0284	6.6490	3
0.0179	7.3034	4
0.0044	8.1785	5
0.0070	8.4039	6
0.0038	8.2728	7
0.0028	8.1154	8
0.0140	8.1207	9
0.0160	8.1384	10
0.0029	8.2978	11
0.0112	8.6940	12
0.0100	8.7433	13
0.0062	8.6486	14
0.0059	8.4821	15
0.0055	8.4559	16
0.0039	8.5136	17
0.0044	8.2783	18
0.0016	8.0974	19
0.0094	7.9739	20
0.0020	8.2513	21
0.0008	8.4637	22
0.0039	8.2813	23
0.0017	8.2027	24
0.0018	8.2722	25
0.0015	8.3875	26
0.0013	8.4975	27
0.0013	8.6171	28
0.0009	8.7272	29
0.0010	8.8335	30
0.0007	8.9168	31
0.0007	8.9992	32
0.0006	9.0661	33
0.0007	9.1103	34
0.0004	9.1424	35
0.0008	9.1573	36
0.0006	9.1666	37
0.0008	9.1732	38
0.0004	9.1781	39
0.0006	9.1867	40
0.0005	9.1986	41
0.0005	9.2203	42
0.0005	9.2512	43
0.0006	9.2889	44
0.0005	9.3360	45
0.0007	9.3759	46
0.0004	9.4144	47
0.0006	9.4461	48
0.0004	9.4718	49
0.0005	9.5113	50
0.0004	9.5425	51
0.0003	9.5667	52
0.0015	9.5468	53
0.0003	9.4515	54
0.0005	9.3881	55
0.0006	9.3797	56
0.0006	9.3887	57
0.0003	9.4038	58
0.0004	9.4206	59
0.0003	9.4417	60
0.0003	9.4627	61
0.0003	9.4775	62
0.0004	9.4930	63
0.0009	9.5593	64
0.0003	9.6068	65
0.0003	9.6416	66
0.0003	9.6715	67
0.0003	9.6956	68
0.0004	9.7146	69
0.0010	9.7344	70
0.0002	9.7946	71
0.0003	9.7965	72
0.0034	9.7113	73
0.0004	9.5730	74
0.0005	9.4858	75
0.0009	9.5826	76
0.0006	9.6923	77
0.0005	9.8243	78
0.0005	9.9368	79
0.0007	10.0514	80
0.0006	10.1386	81
0.0010	10.1427	82
0.0005	9.9261	83
0.0011	9.8122	84
0.0003	9.8724	85
0.0081	9.5494	86
0.0151	8.3043	87
0.0425	9.1449	88
0.0076	8.8560	89
0.0113	8.2403	90
0.0446	7.5457	91
0.0264	7.4204	92
0.1545	8.0820	93
0.3878	8.2238	94
0.4155	6.1718	95
0.0410	5.0625	96
0.0768	4.8214	97
0.0514	4.8477	98
0.0150	5.2002	99
0.0328	5.6224	100
0.0260	5.9887	101
0.0040	6.2793	102
0.0076	6.3696	103
0.0013	6.3642	104
0.0075	6.4379	105
0.0015	6.6379	106
0.0010	6.7736	107
0.0023	6.8582	108
0.0056	6.8884	109
0.0011	6.9125	110
0.0014	6.9437	111
0.0014	6.9807	112
0.0010	7.0239	113
0.0006	7.0602	114
0.0006	7.0919	115
0.0005	7.1213	116
0.0008	7.1457	117
0.0006	7.1679	118
0.0009	7.1871	119
0.0288	7.3166	120
0.0007	7.1397	121
0.0033	6.9025	122
0.0020	6.8509	123
0.0068	6.9533	124
0.0066	7.2446	125
0.0035	7.5351	126
0.0019	7.7354	127
0.0021	7.8376	128
0.0007	7.9071	129
0.0012	7.9566	130
0.0009	8.0014	131
0.0013	8.0186	132
0.0015	8.0123	133
0.0009	7.9870	134
0.0008	7.9685	135
0.0005	7.9599	136
0.0005	7.9553	137

Framework versions

Transformers 4.44.2
TensorFlow 2.17.0
Datasets 3.0.1
Tokenizers 0.19.1