Labira/LabiraPJOK_5A_100_Full

This model is a fine-tuned version of Labira/LabiraPJOK_4_100_Full on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0022
• Validation Loss: 0.0010
• 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
3.8867	2.3827	0
1.9836	1.5612	1
1.3760	0.9002	2
0.9254	0.4459	3
0.6740	0.1479	4
0.3874	0.0864	5
0.3355	0.0557	6
0.1929	0.0374	7
0.2133	0.0230	8
0.1516	0.0164	9
0.1120	0.0123	10
0.1013	0.0091	11
0.0750	0.0084	12
0.0947	0.0094	13
0.0406	0.0119	14
0.0335	0.0130	15
0.0219	0.0094	16
0.0223	0.0074	17
0.0186	0.0056	18
0.0225	0.0044	19
0.0157	0.0035	20
0.0070	0.0029	21
0.0360	0.0028	22
0.0210	0.0025	23
0.0342	0.0027	24
0.0097	0.0032	25
0.0158	0.0031	26
0.0096	0.0030	27
0.0205	0.0028	28
0.0084	0.0024	29
0.0178	0.0024	30
0.0061	0.0023	31
0.0035	0.0022	32
0.0088	0.0022	33
0.0156	0.0024	34
0.0036	0.0024	35
0.0059	0.0024	36
0.0138	0.0030	37
0.0079	0.0045	38
0.0045	0.0053	39
0.0085	0.0045	40
0.0060	0.0040	41
0.0041	0.0035	42
0.0090	0.0018	43
0.0044	0.0010	44
0.0036	0.0007	45
0.0048	0.0006	46
0.0039	0.0005	47
0.0037	0.0005	48
0.0017	0.0005	49
0.0096	0.0006	50
0.0047	0.0008	51
0.0030	0.0009	52
0.0030	0.0011	53
0.1695	0.0012	54
0.0044	0.0014	55
0.0037	0.0012	56
0.0033	0.0011	57
0.0018	0.0010	58
0.0026	0.0009	59
0.0062	0.0009	60
0.0041	0.0009	61
0.0030	0.0009	62
0.0048	0.0009	63
0.0017	0.0008	64
0.0031	0.0008	65
0.0027	0.0008	66
0.0025	0.0007	67
0.0018	0.0007	68
0.0016	0.0006	69
0.0043	0.0007	70
0.0129	0.0007	71
0.0036	0.0007	72
0.0033	0.0007	73
0.0036	0.0007	74
0.0036	0.0007	75
0.0033	0.0007	76
0.0040	0.0007	77
0.0058	0.0007	78
0.0263	0.0008	79
0.0024	0.0014	80
0.0161	0.0023	81
0.0024	0.0032	82
0.0091	0.0036	83
0.0031	0.0034	84
0.0033	0.0032	85
0.0042	0.0028	86
0.0018	0.0024	87
0.0022	0.0022	88
0.0015	0.0020	89
0.0036	0.0018	90
0.0029	0.0016	91
0.0064	0.0013	92
0.0015	0.0012	93
0.0059	0.0011	94
0.0044	0.0011	95
0.0031	0.0011	96
0.0071	0.0011	97
0.1268	0.0010	98
0.0022	0.0010	99

Framework versions

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