Labira/LabiraPJOK_6_100_Group

This model is a fine-tuned version of Labira/LabiraPJOK_5_100_Group on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0384
• Validation Loss: 0.0017
• 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': 400, '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
3.2140	2.5795	0
1.5796	1.6377	1
1.2599	1.1880	2
1.0232	0.9323	3
0.7286	0.7767	4
0.6644	0.6911	5
0.5911	0.6071	6
0.4856	0.5126	7
0.4193	0.4042	8
0.3771	0.3472	9
0.2351	0.3399	10
0.3774	0.2887	11
0.3694	0.2545	12
0.2110	0.2572	13
0.2303	0.2229	14
0.1635	0.1686	15
0.1560	0.1591	16
0.2134	0.1437	17
0.1097	0.1447	18
0.1041	0.1354	19
0.1667	0.1058	20
0.0982	0.0677	21
0.0717	0.0470	22
0.0966	0.0506	23
0.1553	0.0578	24
0.1038	0.0798	25
0.1154	0.0802	26
0.0830	0.0559	27
0.0554	0.0403	28
0.0856	0.0337	29
0.0638	0.0296	30
0.0671	0.0228	31
0.0666	0.0162	32
0.0787	0.0114	33
0.0704	0.0115	34
0.0476	0.0117	35
0.0451	0.0099	36
0.0600	0.0077	37
0.0932	0.0056	38
0.0483	0.0045	39
0.0841	0.0052	40
0.0584	0.0062	41
0.0403	0.0080	42
0.1138	0.0052	43
0.0494	0.0043	44
0.0592	0.0040	45
0.0639	0.0036	46
0.0481	0.0036	47
0.0485	0.0041	48
0.0590	0.0044	49
0.0271	0.0040	50
0.0426	0.0036	51
0.0463	0.0035	52
0.0468	0.0035	53
0.1085	0.0035	54
0.0487	0.0035	55
0.0271	0.0035	56
0.0278	0.0034	57
0.0291	0.0031	58
0.0496	0.0028	59
0.0642	0.0030	60
0.0467	0.0029	61
0.0449	0.0030	62
0.0509	0.0030	63
0.0622	0.0028	64
0.0709	0.0037	65
0.0566	0.0047	66
0.0701	0.0048	67
0.0510	0.0040	68
0.0404	0.0032	69
0.0189	0.0027	70
0.0369	0.0025	71
0.0595	0.0021	72
0.0736	0.0022	73
0.0554	0.0025	74
0.0432	0.0026	75
0.0180	0.0027	76
0.0415	0.0027	77
0.0391	0.0026	78
0.0276	0.0026	79
0.0426	0.0025	80
0.0757	0.0025	81
0.0331	0.0024	82
0.0595	0.0025	83
0.0371	0.0023	84
0.0419	0.0022	85
0.0509	0.0022	86
0.0459	0.0021	87
0.0574	0.0020	88
0.0233	0.0022	89
0.0195	0.0020	90
0.0515	0.0019	91
0.0348	0.0019	92
0.0790	0.0018	93
0.0533	0.0018	94
0.0408	0.0018	95
0.0609	0.0017	96
0.0442	0.0017	97
0.0427	0.0017	98
0.0384	0.0017	99

Framework versions

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