roberta-large-ner-ghtk-gam-7-label-new-data-3090-11Sep-1

This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3028
• Hiều cao khách hàng: {'precision': 0.8695652173913043, 'recall': 1.0, 'f1': 0.9302325581395349, 'number': 20}
• Oại da: {'precision': 0.9047619047619048, 'recall': 0.8260869565217391, 'f1': 0.8636363636363636, 'number': 23}
• Àu da: {'precision': 0.78125, 'recall': 0.6578947368421053, 'f1': 0.7142857142857143, 'number': 38}
• Áng khuôn mặt: {'precision': 0.7368421052631579, 'recall': 0.875, 'f1': 0.7999999999999999, 'number': 16}
• Áng người: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 13}
• Ân nặng khách hàng: {'precision': 0.9, 'recall': 0.8709677419354839, 'f1': 0.8852459016393444, 'number': 31}
• Ặc điểm khác của da: {'precision': 0.8620689655172413, 'recall': 0.8928571428571429, 'f1': 0.8771929824561403, 'number': 28}
• Overall Precision: 0.8563
• Overall Recall: 0.8462
• Overall F1: 0.8512
• Overall Accuracy: 0.9619

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:

• learning_rate: 2.5e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Hiều cao khách hàng	Oại da	Àu da	Áng khuôn mặt	Áng người	Ân nặng khách hàng	Ặc điểm khác của da	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
No log	1.0	141	0.2795	{'precision': 0.9473684210526315, 'recall': 0.9, 'f1': 0.9230769230769231, 'number': 20}	{'precision': 0.5161290322580645, 'recall': 0.6956521739130435, 'f1': 0.5925925925925926, 'number': 23}	{'precision': 0.6666666666666666, 'recall': 0.5789473684210527, 'f1': 0.619718309859155, 'number': 38}	{'precision': 0.625, 'recall': 0.625, 'f1': 0.625, 'number': 16}	{'precision': 0.6666666666666666, 'recall': 0.7692307692307693, 'f1': 0.7142857142857142, 'number': 13}	{'precision': 0.8888888888888888, 'recall': 0.7741935483870968, 'f1': 0.8275862068965517, 'number': 31}	{'precision': 0.5161290322580645, 'recall': 0.5714285714285714, 'f1': 0.5423728813559322, 'number': 28}	0.6744	0.6864	0.6804	0.9196
No log	2.0	282	0.2887	{'precision': 0.8695652173913043, 'recall': 1.0, 'f1': 0.9302325581395349, 'number': 20}	{'precision': 0.7727272727272727, 'recall': 0.7391304347826086, 'f1': 0.7555555555555555, 'number': 23}	{'precision': 0.6363636363636364, 'recall': 0.5526315789473685, 'f1': 0.5915492957746479, 'number': 38}	{'precision': 0.6, 'recall': 0.75, 'f1': 0.6666666666666665, 'number': 16}	{'precision': 0.7058823529411765, 'recall': 0.9230769230769231, 'f1': 0.8000000000000002, 'number': 13}	{'precision': 0.90625, 'recall': 0.9354838709677419, 'f1': 0.9206349206349206, 'number': 31}	{'precision': 0.6571428571428571, 'recall': 0.8214285714285714, 'f1': 0.73015873015873, 'number': 28}	0.7363	0.7929	0.7635	0.9262
No log	3.0	423	0.2731	{'precision': 0.9523809523809523, 'recall': 1.0, 'f1': 0.975609756097561, 'number': 20}	{'precision': 0.8095238095238095, 'recall': 0.7391304347826086, 'f1': 0.7727272727272727, 'number': 23}	{'precision': 0.7419354838709677, 'recall': 0.6052631578947368, 'f1': 0.6666666666666666, 'number': 38}	{'precision': 0.7368421052631579, 'recall': 0.875, 'f1': 0.7999999999999999, 'number': 16}	{'precision': 0.8571428571428571, 'recall': 0.9230769230769231, 'f1': 0.888888888888889, 'number': 13}	{'precision': 0.9655172413793104, 'recall': 0.9032258064516129, 'f1': 0.9333333333333333, 'number': 31}	{'precision': 0.5121951219512195, 'recall': 0.75, 'f1': 0.6086956521739131, 'number': 28}	0.7670	0.7988	0.7826	0.9328
0.4116	4.0	564	0.2516	{'precision': 0.8695652173913043, 'recall': 1.0, 'f1': 0.9302325581395349, 'number': 20}	{'precision': 0.8636363636363636, 'recall': 0.8260869565217391, 'f1': 0.8444444444444444, 'number': 23}	{'precision': 0.7241379310344828, 'recall': 0.5526315789473685, 'f1': 0.6268656716417911, 'number': 38}	{'precision': 0.7777777777777778, 'recall': 0.875, 'f1': 0.823529411764706, 'number': 16}	{'precision': 0.9230769230769231, 'recall': 0.9230769230769231, 'f1': 0.9230769230769231, 'number': 13}	{'precision': 0.9354838709677419, 'recall': 0.9354838709677419, 'f1': 0.9354838709677419, 'number': 31}	{'precision': 0.78125, 'recall': 0.8928571428571429, 'f1': 0.8333333333333334, 'number': 28}	0.8333	0.8284	0.8309	0.9502
0.4116	5.0	705	0.2274	{'precision': 0.8695652173913043, 'recall': 1.0, 'f1': 0.9302325581395349, 'number': 20}	{'precision': 0.8181818181818182, 'recall': 0.782608695652174, 'f1': 0.8, 'number': 23}	{'precision': 0.8064516129032258, 'recall': 0.6578947368421053, 'f1': 0.7246376811594202, 'number': 38}	{'precision': 0.7647058823529411, 'recall': 0.8125, 'f1': 0.787878787878788, 'number': 16}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 13}	{'precision': 0.9285714285714286, 'recall': 0.8387096774193549, 'f1': 0.8813559322033899, 'number': 31}	{'precision': 0.8275862068965517, 'recall': 0.8571428571428571, 'f1': 0.8421052631578947, 'number': 28}	0.8528	0.8225	0.8373	0.9594
0.4116	6.0	846	0.2420	{'precision': 0.8333333333333334, 'recall': 1.0, 'f1': 0.9090909090909091, 'number': 20}	{'precision': 0.6666666666666666, 'recall': 0.6956521739130435, 'f1': 0.6808510638297872, 'number': 23}	{'precision': 0.7878787878787878, 'recall': 0.6842105263157895, 'f1': 0.732394366197183, 'number': 38}	{'precision': 0.8235294117647058, 'recall': 0.875, 'f1': 0.8484848484848485, 'number': 16}	{'precision': 0.9230769230769231, 'recall': 0.9230769230769231, 'f1': 0.9230769230769231, 'number': 13}	{'precision': 0.9354838709677419, 'recall': 0.9354838709677419, 'f1': 0.9354838709677419, 'number': 31}	{'precision': 0.7666666666666667, 'recall': 0.8214285714285714, 'f1': 0.793103448275862, 'number': 28}	0.8140	0.8284	0.8211	0.9527
0.4116	7.0	987	0.2390	{'precision': 0.8695652173913043, 'recall': 1.0, 'f1': 0.9302325581395349, 'number': 20}	{'precision': 0.8636363636363636, 'recall': 0.8260869565217391, 'f1': 0.8444444444444444, 'number': 23}	{'precision': 0.7419354838709677, 'recall': 0.6052631578947368, 'f1': 0.6666666666666666, 'number': 38}	{'precision': 0.8421052631578947, 'recall': 1.0, 'f1': 0.9142857142857143, 'number': 16}	{'precision': 0.9230769230769231, 'recall': 0.9230769230769231, 'f1': 0.9230769230769231, 'number': 13}	{'precision': 0.9032258064516129, 'recall': 0.9032258064516129, 'f1': 0.9032258064516129, 'number': 31}	{'precision': 0.896551724137931, 'recall': 0.9285714285714286, 'f1': 0.912280701754386, 'number': 28}	0.8571	0.8521	0.8546	0.9619
0.1291	8.0	1128	0.2731	{'precision': 0.8695652173913043, 'recall': 1.0, 'f1': 0.9302325581395349, 'number': 20}	{'precision': 0.9047619047619048, 'recall': 0.8260869565217391, 'f1': 0.8636363636363636, 'number': 23}	{'precision': 0.75, 'recall': 0.631578947368421, 'f1': 0.6857142857142857, 'number': 38}	{'precision': 0.7894736842105263, 'recall': 0.9375, 'f1': 0.8571428571428572, 'number': 16}	{'precision': 0.9230769230769231, 'recall': 0.9230769230769231, 'f1': 0.9230769230769231, 'number': 13}	{'precision': 0.9333333333333333, 'recall': 0.9032258064516129, 'f1': 0.9180327868852459, 'number': 31}	{'precision': 0.896551724137931, 'recall': 0.9285714285714286, 'f1': 0.912280701754386, 'number': 28}	0.8623	0.8521	0.8571	0.9602
0.1291	9.0	1269	0.2968	{'precision': 0.8695652173913043, 'recall': 1.0, 'f1': 0.9302325581395349, 'number': 20}	{'precision': 0.9047619047619048, 'recall': 0.8260869565217391, 'f1': 0.8636363636363636, 'number': 23}	{'precision': 0.7741935483870968, 'recall': 0.631578947368421, 'f1': 0.6956521739130435, 'number': 38}	{'precision': 0.7647058823529411, 'recall': 0.8125, 'f1': 0.787878787878788, 'number': 16}	{'precision': 0.9230769230769231, 'recall': 0.9230769230769231, 'f1': 0.9230769230769231, 'number': 13}	{'precision': 0.9, 'recall': 0.8709677419354839, 'f1': 0.8852459016393444, 'number': 31}	{'precision': 0.8620689655172413, 'recall': 0.8928571428571429, 'f1': 0.8771929824561403, 'number': 28}	0.8537	0.8284	0.8408	0.9610
0.1291	10.0	1410	0.3028	{'precision': 0.8695652173913043, 'recall': 1.0, 'f1': 0.9302325581395349, 'number': 20}	{'precision': 0.9047619047619048, 'recall': 0.8260869565217391, 'f1': 0.8636363636363636, 'number': 23}	{'precision': 0.78125, 'recall': 0.6578947368421053, 'f1': 0.7142857142857143, 'number': 38}	{'precision': 0.7368421052631579, 'recall': 0.875, 'f1': 0.7999999999999999, 'number': 16}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 13}	{'precision': 0.9, 'recall': 0.8709677419354839, 'f1': 0.8852459016393444, 'number': 31}	{'precision': 0.8620689655172413, 'recall': 0.8928571428571429, 'f1': 0.8771929824561403, 'number': 28}	0.8563	0.8462	0.8512	0.9619

Framework versions

• Transformers 4.44.0
• Pytorch 2.3.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1