roberta-large-ner-ghtk-cs-add-2label-new-data-3090-11Sep-1

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3034
• Tk: {'precision': 0.8552631578947368, 'recall': 0.5603448275862069, 'f1': 0.6770833333333334, 'number': 116}
• A: {'precision': 0.9509345794392523, 'recall': 0.9443155452436195, 'f1': 0.9476135040745051, 'number': 431}
• Gày: {'precision': 0.7560975609756098, 'recall': 0.9117647058823529, 'f1': 0.8266666666666665, 'number': 34}
• Gày trừu tượng: {'precision': 0.9087221095334685, 'recall': 0.9180327868852459, 'f1': 0.9133537206931702, 'number': 488}
• Iờ: {'precision': 0.6585365853658537, 'recall': 0.7105263157894737, 'f1': 0.6835443037974684, 'number': 38}
• Ã đơn: {'precision': 0.8712871287128713, 'recall': 0.8669950738916257, 'f1': 0.8691358024691358, 'number': 203}
• Đt: {'precision': 0.9171038824763903, 'recall': 0.9954441913439636, 'f1': 0.9546695794647734, 'number': 878}
• Đt trừu tượng: {'precision': 0.8438818565400844, 'recall': 0.8583690987124464, 'f1': 0.8510638297872342, 'number': 233}
• Overall Precision: 0.9017
• Overall Recall: 0.9203
• Overall F1: 0.9109
• Overall Accuracy: 0.9635

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: 8
• eval_batch_size: 8
• 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	Tk	A	Gày	Gày trừu tượng	Iờ	Ã đơn	Đt	Đt trừu tượng	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
No log	1.0	487	0.2055	{'precision': 0.7586206896551724, 'recall': 0.5689655172413793, 'f1': 0.6502463054187193, 'number': 116}	{'precision': 0.9370629370629371, 'recall': 0.9327146171693735, 'f1': 0.9348837209302325, 'number': 431}	{'precision': 0.7878787878787878, 'recall': 0.7647058823529411, 'f1': 0.7761194029850745, 'number': 34}	{'precision': 0.8915187376725838, 'recall': 0.9262295081967213, 'f1': 0.9085427135678392, 'number': 488}	{'precision': 0.8, 'recall': 0.21052631578947367, 'f1': 0.3333333333333333, 'number': 38}	{'precision': 0.8909090909090909, 'recall': 0.7241379310344828, 'f1': 0.7989130434782608, 'number': 203}	{'precision': 0.9588431590656284, 'recall': 0.9817767653758542, 'f1': 0.9701744513224535, 'number': 878}	{'precision': 0.84375, 'recall': 0.8111587982832618, 'f1': 0.8271334792122538, 'number': 233}	0.9142	0.8889	0.9014	0.9575
0.087	2.0	974	0.1863	{'precision': 0.872093023255814, 'recall': 0.646551724137931, 'f1': 0.7425742574257427, 'number': 116}	{'precision': 0.9846153846153847, 'recall': 0.8909512761020881, 'f1': 0.9354445797807551, 'number': 431}	{'precision': 0.7073170731707317, 'recall': 0.8529411764705882, 'f1': 0.7733333333333334, 'number': 34}	{'precision': 0.9420935412026726, 'recall': 0.8668032786885246, 'f1': 0.9028815368196371, 'number': 488}	{'precision': 0.8181818181818182, 'recall': 0.47368421052631576, 'f1': 0.6, 'number': 38}	{'precision': 0.8317757009345794, 'recall': 0.8768472906403941, 'f1': 0.8537170263788968, 'number': 203}	{'precision': 0.9311827956989247, 'recall': 0.9863325740318907, 'f1': 0.9579646017699115, 'number': 878}	{'precision': 0.8611111111111112, 'recall': 0.7982832618025751, 'f1': 0.8285077951002228, 'number': 233}	0.9195	0.8918	0.9054	0.9605
0.0437	3.0	1461	0.1873	{'precision': 0.8279569892473119, 'recall': 0.6637931034482759, 'f1': 0.736842105263158, 'number': 116}	{'precision': 0.9315673289183223, 'recall': 0.9791183294663574, 'f1': 0.9547511312217195, 'number': 431}	{'precision': 0.725, 'recall': 0.8529411764705882, 'f1': 0.7837837837837837, 'number': 34}	{'precision': 0.9072164948453608, 'recall': 0.9016393442622951, 'f1': 0.9044193216855086, 'number': 488}	{'precision': 0.6458333333333334, 'recall': 0.8157894736842105, 'f1': 0.7209302325581395, 'number': 38}	{'precision': 0.8557213930348259, 'recall': 0.8472906403940886, 'f1': 0.8514851485148515, 'number': 203}	{'precision': 0.9320388349514563, 'recall': 0.9840546697038725, 'f1': 0.9573407202216068, 'number': 878}	{'precision': 0.8739495798319328, 'recall': 0.8927038626609443, 'f1': 0.8832271762208068, 'number': 233}	0.9026	0.9265	0.9144	0.9628
0.0346	4.0	1948	0.2300	{'precision': 0.7792207792207793, 'recall': 0.5172413793103449, 'f1': 0.6217616580310881, 'number': 116}	{'precision': 0.9601873536299765, 'recall': 0.951276102088167, 'f1': 0.9557109557109557, 'number': 431}	{'precision': 0.7837837837837838, 'recall': 0.8529411764705882, 'f1': 0.8169014084507041, 'number': 34}	{'precision': 0.8840864440078585, 'recall': 0.9221311475409836, 'f1': 0.9027081243731194, 'number': 488}	{'precision': 0.6296296296296297, 'recall': 0.8947368421052632, 'f1': 0.7391304347826088, 'number': 38}	{'precision': 0.8704663212435233, 'recall': 0.8275862068965517, 'f1': 0.8484848484848485, 'number': 203}	{'precision': 0.9216101694915254, 'recall': 0.9908883826879271, 'f1': 0.9549945115257958, 'number': 878}	{'precision': 0.8809523809523809, 'recall': 0.7939914163090128, 'f1': 0.835214446952596, 'number': 233}	0.9000	0.9112	0.9056	0.9603
0.0266	5.0	2435	0.2330	{'precision': 0.788235294117647, 'recall': 0.5775862068965517, 'f1': 0.6666666666666666, 'number': 116}	{'precision': 0.9419642857142857, 'recall': 0.9791183294663574, 'f1': 0.9601820250284414, 'number': 431}	{'precision': 0.7209302325581395, 'recall': 0.9117647058823529, 'f1': 0.8051948051948051, 'number': 34}	{'precision': 0.8986083499005965, 'recall': 0.9262295081967213, 'f1': 0.9122098890010091, 'number': 488}	{'precision': 0.5961538461538461, 'recall': 0.8157894736842105, 'f1': 0.6888888888888889, 'number': 38}	{'precision': 0.7510204081632653, 'recall': 0.9064039408866995, 'f1': 0.8214285714285714, 'number': 203}	{'precision': 0.9180672268907563, 'recall': 0.9954441913439636, 'f1': 0.955191256830601, 'number': 878}	{'precision': 0.7709923664122137, 'recall': 0.8669527896995708, 'f1': 0.8161616161616161, 'number': 233}	0.8737	0.9347	0.9032	0.9580
0.0193	6.0	2922	0.2854	{'precision': 0.7777777777777778, 'recall': 0.4224137931034483, 'f1': 0.547486033519553, 'number': 116}	{'precision': 0.9430523917995444, 'recall': 0.9605568445475638, 'f1': 0.9517241379310345, 'number': 431}	{'precision': 0.7560975609756098, 'recall': 0.9117647058823529, 'f1': 0.8266666666666665, 'number': 34}	{'precision': 0.8853754940711462, 'recall': 0.9180327868852459, 'f1': 0.9014084507042255, 'number': 488}	{'precision': 0.5777777777777777, 'recall': 0.6842105263157895, 'f1': 0.6265060240963854, 'number': 38}	{'precision': 0.8936170212765957, 'recall': 0.8275862068965517, 'f1': 0.8593350383631713, 'number': 203}	{'precision': 0.9023883696780893, 'recall': 0.989749430523918, 'f1': 0.9440521455730582, 'number': 878}	{'precision': 0.8290598290598291, 'recall': 0.8326180257510729, 'f1': 0.8308351177730192, 'number': 233}	0.8871	0.9083	0.8976	0.9595
0.0138	7.0	3409	0.2634	{'precision': 0.7380952380952381, 'recall': 0.5344827586206896, 'f1': 0.62, 'number': 116}	{'precision': 0.9578454332552693, 'recall': 0.9489559164733179, 'f1': 0.9533799533799533, 'number': 431}	{'precision': 0.7380952380952381, 'recall': 0.9117647058823529, 'f1': 0.8157894736842106, 'number': 34}	{'precision': 0.9098360655737705, 'recall': 0.9098360655737705, 'f1': 0.9098360655737705, 'number': 488}	{'precision': 0.6444444444444445, 'recall': 0.7631578947368421, 'f1': 0.6987951807228916, 'number': 38}	{'precision': 0.8613861386138614, 'recall': 0.8571428571428571, 'f1': 0.8592592592592593, 'number': 203}	{'precision': 0.9202975557917109, 'recall': 0.9863325740318907, 'f1': 0.9521715228147334, 'number': 878}	{'precision': 0.8648648648648649, 'recall': 0.8240343347639485, 'f1': 0.8439560439560441, 'number': 233}	0.9004	0.9116	0.9060	0.9623
0.0084	8.0	3896	0.2786	{'precision': 0.8043478260869565, 'recall': 0.6379310344827587, 'f1': 0.7115384615384616, 'number': 116}	{'precision': 0.9618138424821002, 'recall': 0.9350348027842227, 'f1': 0.9482352941176471, 'number': 431}	{'precision': 0.7380952380952381, 'recall': 0.9117647058823529, 'f1': 0.8157894736842106, 'number': 34}	{'precision': 0.9056224899598394, 'recall': 0.9241803278688525, 'f1': 0.9148073022312374, 'number': 488}	{'precision': 0.627906976744186, 'recall': 0.7105263157894737, 'f1': 0.6666666666666666, 'number': 38}	{'precision': 0.8088888888888889, 'recall': 0.896551724137931, 'f1': 0.8504672897196263, 'number': 203}	{'precision': 0.9209694415173867, 'recall': 0.9954441913439636, 'f1': 0.9567597153804049, 'number': 878}	{'precision': 0.8954545454545455, 'recall': 0.8454935622317596, 'f1': 0.869757174392936, 'number': 233}	0.8999	0.9248	0.9122	0.9617
0.004	9.0	4383	0.3020	{'precision': 0.8571428571428571, 'recall': 0.5172413793103449, 'f1': 0.6451612903225806, 'number': 116}	{'precision': 0.9551886792452831, 'recall': 0.9396751740139211, 'f1': 0.9473684210526315, 'number': 431}	{'precision': 0.7560975609756098, 'recall': 0.9117647058823529, 'f1': 0.8266666666666665, 'number': 34}	{'precision': 0.9190871369294605, 'recall': 0.9077868852459017, 'f1': 0.9134020618556701, 'number': 488}	{'precision': 0.65, 'recall': 0.6842105263157895, 'f1': 0.6666666666666667, 'number': 38}	{'precision': 0.8911917098445595, 'recall': 0.8472906403940886, 'f1': 0.8686868686868686, 'number': 203}	{'precision': 0.9171038824763903, 'recall': 0.9954441913439636, 'f1': 0.9546695794647734, 'number': 878}	{'precision': 0.8504273504273504, 'recall': 0.8540772532188842, 'f1': 0.8522483940042828, 'number': 233}	0.9069	0.9128	0.9098	0.9630
0.0033	10.0	4870	0.3034	{'precision': 0.8552631578947368, 'recall': 0.5603448275862069, 'f1': 0.6770833333333334, 'number': 116}	{'precision': 0.9509345794392523, 'recall': 0.9443155452436195, 'f1': 0.9476135040745051, 'number': 431}	{'precision': 0.7560975609756098, 'recall': 0.9117647058823529, 'f1': 0.8266666666666665, 'number': 34}	{'precision': 0.9087221095334685, 'recall': 0.9180327868852459, 'f1': 0.9133537206931702, 'number': 488}	{'precision': 0.6585365853658537, 'recall': 0.7105263157894737, 'f1': 0.6835443037974684, 'number': 38}	{'precision': 0.8712871287128713, 'recall': 0.8669950738916257, 'f1': 0.8691358024691358, 'number': 203}	{'precision': 0.9171038824763903, 'recall': 0.9954441913439636, 'f1': 0.9546695794647734, 'number': 878}	{'precision': 0.8438818565400844, 'recall': 0.8583690987124464, 'f1': 0.8510638297872342, 'number': 233}	0.9017	0.9203	0.9109	0.9635

Framework versions

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