Labira/LabiraPJOK_4_100_Full

This model is a fine-tuned version of Labira/LabiraPJOK_3_100_Full on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0114
• Validation Loss: 0.0019
• 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
4.7082	1.0888	0
2.1015	0.9187	1
1.6691	0.7789	2
1.6319	0.6115	3
1.0958	0.5354	4
1.0045	0.4263	5
0.5512	0.2684	6
0.4544	0.2098	7
0.3825	0.1910	8
0.1953	0.1831	9
0.1976	0.1801	10
0.8616	0.1791	11
1.5897	2.3429	12
2.1748	2.0662	13
2.4636	1.7558	14
1.6550	1.4900	15
1.5978	1.3461	16
1.4202	1.2605	17
1.7664	1.1584	18
1.2947	1.0410	19
1.0935	0.9207	20
1.2261	0.7981	21
0.7240	0.6023	22
0.6482	0.4366	23
0.7506	0.3078	24
0.5547	0.2124	25
0.4757	0.1207	26
0.2835	0.0586	27
0.2399	0.0283	28
0.1450	0.0172	29
0.1593	0.0128	30
0.0375	0.0101	31
0.1237	0.0085	32
0.0495	0.0076	33
0.0962	0.0072	34
0.0260	0.0067	35
0.1116	0.0063	36
0.0955	0.0061	37
0.0384	0.0060	38
0.0141	0.0059	39
0.0106	0.0057	40
0.0565	0.0055	41
0.0118	0.0053	42
0.0166	0.0051	43
0.0240	0.0048	44
0.0127	0.0046	45
0.0323	0.0043	46
0.0109	0.0040	47
0.0164	0.0036	48
0.0268	0.0033	49
0.0268	0.0031	50
0.0127	0.0030	51
0.0090	0.0029	52
0.1247	0.0028	53
0.0192	0.0028	54
0.0093	0.0028	55
0.1175	0.0031	56
0.0146	0.0035	57
0.0101	0.0037	58
0.0116	0.0039	59
0.0085	0.0040	60
0.0095	0.0039	61
0.0252	0.0039	62
0.0539	0.0039	63
0.0112	0.0038	64
0.0254	0.0037	65
0.0130	0.0035	66
0.0128	0.0034	67
0.0071	0.0033	68
0.0101	0.0032	69
0.0107	0.0031	70
0.0093	0.0030	71
0.3929	0.0029	72
0.0199	0.0028	73
0.0072	0.0028	74
0.0147	0.0027	75
0.0116	0.0026	76
0.0151	0.0025	77
0.0094	0.0024	78
0.0135	0.0023	79
0.0122	0.0023	80
0.0116	0.0023	81
0.0120	0.0022	82
0.0167	0.0022	83
0.0092	0.0022	84
0.0096	0.0021	85
0.0127	0.0021	86
0.0168	0.0021	87
0.0171	0.0021	88
0.0287	0.0020	89
0.0120	0.0020	90
0.0181	0.0020	91
0.0137	0.0019	92
0.0198	0.0019	93
0.0120	0.0019	94
0.0095	0.0019	95
0.0144	0.0019	96
0.0070	0.0019	97
0.0057	0.0019	98
0.0114	0.0019	99

Framework versions

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