Labira/LabiraPJOK_5_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: 0.0022
• Validation Loss: 0.0008
• Epoch: 96

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': 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
3.5586	1.9568	0
1.7698	1.4494	1
1.2758	1.1921	2
0.9196	0.8832	3
0.9555	0.6157	4
0.6439	0.4235	5
0.4805	0.3079	6
0.2379	0.2399	7
0.2184	0.0946	8
0.1195	0.0436	9
0.0914	0.0233	10
0.0457	0.0143	11
0.0791	0.0107	12
0.0615	0.0084	13
0.0728	0.0071	14
0.0147	0.0061	15
0.0417	0.0058	16
0.0208	0.0064	17
0.0116	0.0074	18
0.0223	0.0055	19
0.0372	0.0046	20
0.0381	0.0046	21
0.0065	0.0049	22
0.0142	0.0048	23
0.0199	0.0036	24
0.0129	0.0025	25
0.0273	0.0019	26
0.0075	0.0016	27
0.0157	0.0015	28
0.0100	0.0015	29
0.0063	0.0015	30
0.0068	0.0015	31
0.0057	0.0015	32
0.0039	0.0015	33
0.0044	0.0015	34
0.0062	0.0014	35
0.0118	0.0013	36
0.0035	0.0011	37
0.0064	0.0009	38
0.0049	0.0008	39
0.0106	0.0008	40
0.0070	0.0009	41
0.0030	0.0010	42
0.0061	0.0011	43
0.0058	0.0011	44
0.0083	0.0012	45
0.0064	0.0014	46
0.0045	0.0014	47
0.0521	0.0014	48
0.0031	0.0015	49
0.0094	0.0014	50
0.0060	0.0012	51
0.0052	0.0010	52
0.0160	0.0008	53
0.0125	0.0007	54
0.0186	0.0007	55
0.0093	0.0011	56
0.0023	0.0019	57
0.0059	0.0023	58
0.0033	0.0022	59
0.0033	0.0020	60
0.0047	0.0017	61
0.0049	0.0015	62
0.0021	0.0013	63
0.0134	0.0012	64
0.0049	0.0012	65
0.0674	0.0013	66
0.0284	0.0013	67
0.0035	0.0012	68
0.0074	0.0011	69
0.0072	0.0010	70
0.0035	0.0010	71
0.0038	0.0009	72
0.0040	0.0009	73
0.0017	0.0008	74
0.0183	0.0008	75
0.0178	0.0007	76
0.0043	0.0007	77
0.0081	0.0007	78
0.0046	0.0007	79
0.0035	0.0007	80
0.0097	0.0007	81
0.0095	0.0007	82
0.0040	0.0008	83
0.0036	0.0008	84
0.0073	0.0008	85
0.0174	0.0008	86
0.0034	0.0009	87
0.0035	0.0009	88
0.0038	0.0009	89
0.0025	0.0008	90
0.0024	0.0008	91
0.0101	0.0008	92
0.0027	0.0008	93
0.0016	0.0008	94
0.0075	0.0008	95
0.0022	0.0008	96

Framework versions

• Transformers 4.46.2
• TensorFlow 2.17.0
• Datasets 3.1.0
• Tokenizers 0.20.3