Labira/LabiraPJOK_4_100_Group

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: 0.0923
• Validation Loss: 0.0207
• 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': 300, '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
6.0143	5.4097	0
5.4107	4.8137	1
5.1199	4.2679	2
4.4588	3.8174	3
4.0979	4.1675	4
3.7043	3.8359	5
4.2631	3.4466	6
3.3397	2.9869	7
3.3407	2.4810	8
2.7209	1.9936	9
2.2011	1.6508	10
1.8231	1.4160	11
1.7967	1.2276	12
1.4320	0.9688	13
1.4783	0.7902	14
1.6968	0.7241	15
0.9957	0.6687	16
1.1000	0.6334	17
0.7929	0.5741	18
0.7711	0.5164	19
1.1769	0.4778	20
0.7386	0.4681	21
0.4486	0.4709	22
0.6128	0.4349	23
0.3976	0.3977	24
0.4388	0.3597	25
0.4466	0.3300	26
0.9996	0.3130	27
0.3339	0.3061	28
0.4258	0.3022	29
0.2798	0.3007	30
0.2566	0.3003	31
0.2680	0.2996	32
0.3876	0.2983	33
0.2534	0.2970	34
0.3045	0.2967	35
0.3094	0.2963	36
0.2417	0.2950	37
0.3368	0.2934	38
0.2831	0.2919	39
0.1785	0.2909	40
0.2789	0.2899	41
0.3243	0.2896	42
0.3355	0.2892	43
0.2775	0.2893	44
0.3313	0.2890	45
0.3249	0.2887	46
0.2887	0.2890	47
0.1869	0.2902	48
0.3599	0.2910	49
0.3157	0.2905	50
0.2670	0.2885	51
0.3326	0.2868	52
0.1986	0.1883	53
0.4806	0.1881	54
0.3620	0.2858	55
0.1411	0.2882	56
0.1301	0.2905	57
0.3283	0.2426	58
0.2434	0.2314	59
0.2115	0.2232	60
0.1430	0.2136	61
0.2704	0.2055	62
0.2001	0.1985	63
0.1271	0.1936	64
0.1162	0.1913	65
0.0990	0.1893	66
0.1776	0.1880	67
0.1269	0.1870	68
0.2546	0.1867	69
0.1521	0.1863	70
0.0998	0.1860	71
0.0989	0.1856	72
0.1166	0.1853	73
0.1331	0.1850	74
0.1571	0.1846	75
0.1997	0.1858	76
0.1514	0.1866	77
0.1626	0.0152	78
0.2198	0.0153	79
0.2598	0.0165	80
0.2675	0.0177	81
0.1063	0.0185	82
0.1424	0.0193	83
0.1639	0.0197	84
0.1225	0.0201	85
0.1899	0.0203	86
0.1857	0.0209	87
0.0887	0.0214	88
0.0980	0.0218	89
0.1236	0.0223	90
0.0868	0.0224	91
0.0661	0.0222	92
0.0701	0.0216	93
0.0699	0.0212	94
0.1249	0.0209	95
0.1155	0.0208	96
0.0651	0.0208	97
0.0646	0.0207	98
0.0923	0.0207	99

Framework versions

• Transformers 4.45.2
• TensorFlow 2.17.0
• Datasets 2.20.0
• Tokenizers 0.20.1