LabiraPJOK_123_100_Full

Labira/LabiraPJOK_123_100_Full

LabiraPJOK_123_100_Full is a question answering model from Labira. Use it when the input is a question plus a passage. It is set up for transformers. The card lists the license as mit.

probably proofread and complete it, then remove this comment. --

Downloads · 30 days

25% of all-time downloads

All-time downloads

Public

Repo size

440 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.h5440 MB · 100%

At a glance

Task: Question Answering
Library: transformers
License: mit
Model type: bert
Access: Public
Created: Sep 21, 2025
Updated: Sep 21, 2025
SHA: 1d406c81

Try a prompt

Base models

indolem/indobert-base-uncased

Model card

From the Hugging Face model README

Labira/LabiraPJOK_123_100_Full

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: 0.0108
Validation Loss: 0.0014
Epoch: 99

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': False, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2200, '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
4.8014	3.8239	0
3.5330	3.0989	1
3.0273	2.6526	2
2.6530	2.0593	3
2.2572	1.6401	4
1.7060	1.0829	5
1.2904	0.6494	6
0.9646	0.4921	7
0.6371	0.2708	8
0.4612	0.2947	9
0.4154	0.2030	10
0.4027	0.1670	11
0.2759	0.1051	12
0.2515	0.1313	13
0.1759	0.0651	14
0.1293	0.0732	15
0.1595	0.0472	16
0.0989	0.0647	17
0.0797	0.0566	18
0.1292	0.0351	19
0.1098	0.0743	20
0.1490	0.0591	21
0.0934	0.0558	22
0.0720	0.0330	23
0.0502	0.0265	24
0.0598	0.0235	25
0.0589	0.0272	26
0.0409	0.0243	27
0.0445	0.0199	28
0.0425	0.0395	29
0.0420	0.0252	30
0.0332	0.0194	31
0.0286	0.0178	32
0.0480	0.0184	33
0.0361	0.0279	34
0.0529	0.0195	35
0.0296	0.0194	36
0.0346	0.0143	37
0.0256	0.0177	38
0.0331	0.0098	39
0.0386	0.0086	40
0.0303	0.0053	41
0.0310	0.0154	42
0.0193	0.0024	43
0.1070	0.0090	44
0.0937	0.0123	45
0.0766	0.0112	46
0.0698	0.0057	47
0.0297	0.0043	48
0.0385	0.0117	49
0.0802	0.0181	50
0.1040	0.0072	51
0.0836	0.0163	52
0.0861	0.0060	53
0.0867	0.0079	54
0.1242	0.0041	55
0.1090	0.0070	56
0.0394	0.0042	57
0.0312	0.0041	58
0.0391	0.0020	59
0.0320	0.0023	60
0.0479	0.0135	61
0.0403	0.0017	62
0.0352	0.0019	63
0.0314	0.0030	64
0.0254	0.0020	65
0.0243	0.0013	66
0.0504	0.0022	67
0.0474	0.0023	68
0.0430	0.0036	69
0.0142	0.0021	70
0.0169	0.0014	71
0.0110	0.0013	72
0.0229	0.0011	73
0.0476	0.0008	74
0.0461	0.0012	75
0.0170	0.0013	76
0.0210	0.0020	77
0.0146	0.0021	78
0.0206	0.0019	79
0.0137	0.0021	80
0.0125	0.0015	81
0.0303	0.0026	82
0.0100	0.0019	83
0.0088	0.0015	84
0.0128	0.0016	85
0.0153	0.0018	86
0.0141	0.0018	87
0.0163	0.0017	88
0.0104	0.0014	89
0.0098	0.0014	90
0.0116	0.0013	91
0.0160	0.0015	92
0.0161	0.0016	93
0.0088	0.0015	94
0.0101	0.0015	95
0.0105	0.0015	96
0.0110	0.0015	97
0.0049	0.0014	98
0.0108	0.0014	99

Framework versions

Transformers 4.45.2
TensorFlow 2.17.0
Datasets 2.20.0
Tokenizers 0.20.1

Task: Question Answering
Library: transformers
Type: bert
License: mit
Created: Sep 21, 2025
Updated: Sep 21, 2025