Keisyahsq/BC2GM_BERT

This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0031
• Validation Loss: 0.1601
• Train Precision: 0.8543
• Train Recall: 0.8713
• Train F1: 0.8627
• Train Accuracy: 0.9712
• 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': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 15620, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Precision	Train Recall	Train F1	Train Accuracy	Epoch
0.1462	0.0941	0.7837	0.8515	0.8162	0.9639	0
0.0726	0.0885	0.8363	0.8419	0.8391	0.9680	1
0.0452	0.1000	0.8402	0.8563	0.8482	0.9689	2
0.0275	0.1060	0.8357	0.8658	0.8505	0.9689	3
0.0187	0.1246	0.8471	0.8662	0.8566	0.9691	4
0.0127	0.1268	0.8460	0.8725	0.8590	0.9703	5
0.0089	0.1451	0.8400	0.8780	0.8586	0.9702	6
0.0060	0.1555	0.8611	0.8558	0.8584	0.9713	7
0.0046	0.1541	0.8560	0.8732	0.8645	0.9713	8
0.0034	0.1601	0.8543	0.8713	0.8627	0.9712	9
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	10
0.0032	0.1601	0.8543	0.8713	0.8627	0.9712	11
0.0029	0.1601	0.8543	0.8713	0.8627	0.9712	12
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	13
0.0031	0.1601	0.8543	0.8713	0.8627	0.9712	14
0.0027	0.1601	0.8543	0.8713	0.8627	0.9712	15
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	16
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	17
0.0029	0.1601	0.8543	0.8713	0.8627	0.9712	18
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	19
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	20
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	21
0.0031	0.1601	0.8543	0.8713	0.8627	0.9712	22
0.0031	0.1601	0.8543	0.8713	0.8627	0.9712	23
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	24
0.0031	0.1601	0.8543	0.8713	0.8627	0.9712	25
0.0029	0.1601	0.8543	0.8713	0.8627	0.9712	26
0.0028	0.1601	0.8543	0.8713	0.8627	0.9712	27
0.0032	0.1601	0.8543	0.8713	0.8627	0.9712	28
0.0031	0.1601	0.8543	0.8713	0.8627	0.9712	29
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	30
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	31
0.0029	0.1601	0.8543	0.8713	0.8627	0.9712	32
0.0029	0.1601	0.8543	0.8713	0.8627	0.9712	33
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	34
0.0031	0.1601	0.8543	0.8713	0.8627	0.9712	35
0.0032	0.1601	0.8543	0.8713	0.8627	0.9712	36
0.0029	0.1601	0.8543	0.8713	0.8627	0.9712	37
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	38
0.0031	0.1601	0.8543	0.8713	0.8627	0.9712	39
0.0032	0.1601	0.8543	0.8713	0.8627	0.9712	40
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	41
0.0029	0.1601	0.8543	0.8713	0.8627	0.9712	42
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	43
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	44
0.0031	0.1601	0.8543	0.8713	0.8627	0.9712	45
0.0029	0.1601	0.8543	0.8713	0.8627	0.9712	46
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	47
0.0029	0.1601	0.8543	0.8713	0.8627	0.9712	48
0.0029	0.1601	0.8543	0.8713	0.8627	0.9712	49
0.0029	0.1601	0.8543	0.8713	0.8627	0.9712	50
0.0032	0.1601	0.8543	0.8713	0.8627	0.9712	51
0.0031	0.1601	0.8543	0.8713	0.8627	0.9712	52
0.0029	0.1601	0.8543	0.8713	0.8627	0.9712	53
0.0028	0.1601	0.8543	0.8713	0.8627	0.9712	54
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	55
0.0027	0.1601	0.8543	0.8713	0.8627	0.9712	56
0.0029	0.1601	0.8543	0.8713	0.8627	0.9712	57
0.0028	0.1601	0.8543	0.8713	0.8627	0.9712	58
0.0029	0.1601	0.8543	0.8713	0.8627	0.9712	59
0.0029	0.1601	0.8543	0.8713	0.8627	0.9712	60
0.0031	0.1601	0.8543	0.8713	0.8627	0.9712	61
0.0029	0.1601	0.8543	0.8713	0.8627	0.9712	62
0.0032	0.1601	0.8543	0.8713	0.8627	0.9712	63
0.0031	0.1601	0.8543	0.8713	0.8627	0.9712	64
0.0029	0.1601	0.8543	0.8713	0.8627	0.9712	65
0.0027	0.1601	0.8543	0.8713	0.8627	0.9712	66
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	67
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	68
0.0031	0.1601	0.8543	0.8713	0.8627	0.9712	69
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	70
0.0031	0.1601	0.8543	0.8713	0.8627	0.9712	71
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	72
0.0031	0.1601	0.8543	0.8713	0.8627	0.9712	73
0.0032	0.1601	0.8543	0.8713	0.8627	0.9712	74
0.0028	0.1601	0.8543	0.8713	0.8627	0.9712	75
0.0031	0.1601	0.8543	0.8713	0.8627	0.9712	76
0.0029	0.1601	0.8543	0.8713	0.8627	0.9712	77
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	78
0.0031	0.1601	0.8543	0.8713	0.8627	0.9712	79
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	80
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	81
0.0029	0.1601	0.8543	0.8713	0.8627	0.9712	82
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	83
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	84
0.0031	0.1601	0.8543	0.8713	0.8627	0.9712	85
0.0028	0.1601	0.8543	0.8713	0.8627	0.9712	86
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	87
0.0028	0.1601	0.8543	0.8713	0.8627	0.9712	88
0.0029	0.1601	0.8543	0.8713	0.8627	0.9712	89
0.0029	0.1601	0.8543	0.8713	0.8627	0.9712	90
0.0028	0.1601	0.8543	0.8713	0.8627	0.9712	91
0.0029	0.1601	0.8543	0.8713	0.8627	0.9712	92
0.0028	0.1601	0.8543	0.8713	0.8627	0.9712	93
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	94
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	95
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	96
0.0029	0.1601	0.8543	0.8713	0.8627	0.9712	97
0.0030	0.1601	0.8543	0.8713	0.8627	0.9712	98
0.0031	0.1601	0.8543	0.8713	0.8627	0.9712	99

Framework versions

• Transformers 4.31.0
• TensorFlow 2.10.1
• Datasets 3.0.0
• Tokenizers 0.13.3