Labira/LabiraPJOK_5_100_Group

This model is a fine-tuned version of Labira/LabiraPJOK_4_100_Group on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0245
• Validation Loss: 0.0048
• 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
5.0299	4.2579	0
3.9993	3.2863	1
3.5084	2.8872	2
3.1257	2.4304	3
2.6719	1.8348	4
2.0749	1.2511	5
1.8650	0.8881	6
1.2486	0.6654	7
1.1500	0.5810	8
0.8070	0.4871	9
0.6750	0.3621	10
0.5653	0.3742	11
0.4448	0.3147	12
0.3255	0.1682	13
0.2929	0.1691	14
0.2513	0.1638	15
0.2130	0.1555	16
0.2244	0.0776	17
0.1301	0.0292	18
0.1741	0.0287	19
0.1357	0.0739	20
0.1466	0.0305	21
0.1158	0.0236	22
0.2801	0.0214	23
0.0510	0.0284	24
0.1506	0.0392	25
0.1013	0.0402	26
0.0567	0.0399	27
0.0801	0.0260	28
0.1379	0.0202	29
0.0538	0.0241	30
0.0698	0.0216	31
0.0695	0.0186	32
0.0481	0.0122	33
0.0647	0.0108	34
0.0686	0.0087	35
0.0741	0.0088	36
0.0460	0.0095	37
0.0575	0.0128	38
0.1026	0.0207	39
0.0333	0.0315	40
0.0367	0.0299	41
0.0731	0.0215	42
0.0989	0.0162	43
0.0231	0.0125	44
0.0309	0.0095	45
0.0217	0.0087	46
0.0235	0.0086	47
0.0239	0.0102	48
0.0346	0.0117	49
0.0327	0.0118	50
0.0217	0.0101	51
0.0153	0.0080	52
0.0372	0.0066	53
0.0321	0.0069	54
0.0610	0.0076	55
0.0159	0.0117	56
0.0378	0.0137	57
0.0278	0.0118	58
0.0176	0.0101	59
0.0233	0.0083	60
0.0268	0.0081	61
0.0140	0.0083	62
0.0130	0.0077	63
0.0218	0.0072	64
0.0205	0.0071	65
0.0177	0.0074	66
0.0201	0.0078	67
0.0787	0.0108	68
0.0193	0.0120	69
0.0144	0.0115	70
0.0254	0.0098	71
0.0195	0.0082	72
0.0254	0.0069	73
0.0134	0.0057	74
0.0176	0.0050	75
0.0156	0.0048	76
0.0112	0.0048	77
0.0181	0.0047	78
0.0321	0.0046	79
0.0145	0.0048	80
0.0148	0.0053	81
0.0191	0.0059	82
0.0373	0.0066	83
0.0128	0.0072	84
0.0270	0.0073	85
0.0217	0.0071	86
0.0119	0.0067	87
0.0123	0.0063	88
0.0116	0.0059	89
0.0107	0.0056	90
0.0233	0.0054	91
0.0109	0.0053	92
0.0145	0.0051	93
0.0113	0.0050	94
0.0137	0.0049	95
0.0127	0.0049	96
0.0124	0.0048	97
0.0098	0.0048	98
0.0245	0.0048	99

Framework versions

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