roberta-large-ner-ghtk-cs-add-2label-50-new-data-3090-14Sep-1

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

• Loss: 0.2865
• Tk: {'precision': 0.7570093457943925, 'recall': 0.6982758620689655, 'f1': 0.726457399103139, 'number': 116}
• A: {'precision': 0.9559164733178654, 'recall': 0.9559164733178654, 'f1': 0.9559164733178654, 'number': 431}
• Gày: {'precision': 0.7209302325581395, 'recall': 0.9117647058823529, 'f1': 0.8051948051948051, 'number': 34}
• Gày trừu tượng: {'precision': 0.9004065040650406, 'recall': 0.9077868852459017, 'f1': 0.9040816326530612, 'number': 488}
• Iờ: {'precision': 0.6136363636363636, 'recall': 0.7105263157894737, 'f1': 0.6585365853658537, 'number': 38}
• Ã đơn: {'precision': 0.8860103626943006, 'recall': 0.8423645320197044, 'f1': 0.8636363636363636, 'number': 203}
• Đt: {'precision': 0.9453551912568307, 'recall': 0.9851936218678815, 'f1': 0.9648633575013943, 'number': 878}
• Đt trừu tượng: {'precision': 0.7896825396825397, 'recall': 0.8540772532188842, 'f1': 0.820618556701031, 'number': 233}
• Overall Precision: 0.8999
• Overall Recall: 0.9207
• Overall F1: 0.9102
• Overall Accuracy: 0.9616

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	396	0.1707	{'precision': 0.7684210526315789, 'recall': 0.6293103448275862, 'f1': 0.6919431279620853, 'number': 116}	{'precision': 0.9210526315789473, 'recall': 0.974477958236659, 'f1': 0.9470124013528748, 'number': 431}	{'precision': 0.75, 'recall': 0.8823529411764706, 'f1': 0.8108108108108107, 'number': 34}	{'precision': 0.8651252408477842, 'recall': 0.9200819672131147, 'f1': 0.8917576961271102, 'number': 488}	{'precision': 0.4827586206896552, 'recall': 0.7368421052631579, 'f1': 0.5833333333333334, 'number': 38}	{'precision': 0.8722222222222222, 'recall': 0.7733990147783252, 'f1': 0.8198433420365536, 'number': 203}	{'precision': 0.9314775160599572, 'recall': 0.9908883826879271, 'f1': 0.9602649006622518, 'number': 878}	{'precision': 0.691358024691358, 'recall': 0.9613733905579399, 'f1': 0.8043087971274685, 'number': 233}	0.8638	0.9298	0.8956	0.9557
0.0853	2.0	792	0.1964	{'precision': 0.8131868131868132, 'recall': 0.6379310344827587, 'f1': 0.714975845410628, 'number': 116}	{'precision': 0.9727722772277227, 'recall': 0.9118329466357309, 'f1': 0.9413173652694611, 'number': 431}	{'precision': 0.6829268292682927, 'recall': 0.8235294117647058, 'f1': 0.7466666666666667, 'number': 34}	{'precision': 0.9620853080568721, 'recall': 0.8319672131147541, 'f1': 0.8923076923076924, 'number': 488}	{'precision': 0.5818181818181818, 'recall': 0.8421052631578947, 'f1': 0.6881720430107526, 'number': 38}	{'precision': 0.7613168724279835, 'recall': 0.9113300492610837, 'f1': 0.8295964125560539, 'number': 203}	{'precision': 0.927427961579509, 'recall': 0.989749430523918, 'f1': 0.9575757575757575, 'number': 878}	{'precision': 0.8245614035087719, 'recall': 0.8068669527896996, 'f1': 0.8156182212581344, 'number': 233}	0.8984	0.8984	0.8984	0.9563
0.0429	3.0	1188	0.2005	{'precision': 0.7604166666666666, 'recall': 0.6293103448275862, 'f1': 0.6886792452830188, 'number': 116}	{'precision': 0.9213973799126638, 'recall': 0.9791183294663574, 'f1': 0.9493813273340832, 'number': 431}	{'precision': 0.7380952380952381, 'recall': 0.9117647058823529, 'f1': 0.8157894736842106, 'number': 34}	{'precision': 0.9216101694915254, 'recall': 0.8913934426229508, 'f1': 0.90625, 'number': 488}	{'precision': 0.8461538461538461, 'recall': 0.2894736842105263, 'f1': 0.4313725490196079, 'number': 38}	{'precision': 0.8729281767955801, 'recall': 0.7783251231527094, 'f1': 0.8229166666666666, 'number': 203}	{'precision': 0.9331175836030206, 'recall': 0.9851936218678815, 'f1': 0.9584487534626038, 'number': 878}	{'precision': 0.7395833333333334, 'recall': 0.9141630901287554, 'f1': 0.817658349328215, 'number': 233}	0.8914	0.9120	0.9016	0.9582
0.0343	4.0	1584	0.1970	{'precision': 0.7391304347826086, 'recall': 0.7327586206896551, 'f1': 0.735930735930736, 'number': 116}	{'precision': 0.9343891402714932, 'recall': 0.9582366589327146, 'f1': 0.9461626575028637, 'number': 431}	{'precision': 0.6521739130434783, 'recall': 0.8823529411764706, 'f1': 0.75, 'number': 34}	{'precision': 0.8701550387596899, 'recall': 0.9200819672131147, 'f1': 0.894422310756972, 'number': 488}	{'precision': 0.6304347826086957, 'recall': 0.7631578947368421, 'f1': 0.6904761904761905, 'number': 38}	{'precision': 0.7822222222222223, 'recall': 0.8669950738916257, 'f1': 0.8224299065420562, 'number': 203}	{'precision': 0.946448087431694, 'recall': 0.9863325740318907, 'f1': 0.9659788064696041, 'number': 878}	{'precision': 0.7491039426523297, 'recall': 0.8969957081545065, 'f1': 0.8164062499999999, 'number': 233}	0.8735	0.9323	0.9019	0.9578
0.0343	5.0	1980	0.2266	{'precision': 0.7570093457943925, 'recall': 0.6982758620689655, 'f1': 0.726457399103139, 'number': 116}	{'precision': 0.9621749408983451, 'recall': 0.9443155452436195, 'f1': 0.9531615925058547, 'number': 431}	{'precision': 0.7045454545454546, 'recall': 0.9117647058823529, 'f1': 0.794871794871795, 'number': 34}	{'precision': 0.9066937119675457, 'recall': 0.9159836065573771, 'f1': 0.9113149847094801, 'number': 488}	{'precision': 0.6458333333333334, 'recall': 0.8157894736842105, 'f1': 0.7209302325581395, 'number': 38}	{'precision': 0.786046511627907, 'recall': 0.8325123152709359, 'f1': 0.8086124401913874, 'number': 203}	{'precision': 0.9466230936819172, 'recall': 0.989749430523918, 'f1': 0.9677060133630289, 'number': 878}	{'precision': 0.8285714285714286, 'recall': 0.871244635193133, 'f1': 0.8493723849372384, 'number': 233}	0.8977	0.9244	0.9109	0.9592
0.0238	6.0	2376	0.2266	{'precision': 0.75, 'recall': 0.75, 'f1': 0.75, 'number': 116}	{'precision': 0.9426605504587156, 'recall': 0.9535962877030162, 'f1': 0.9480968858131487, 'number': 431}	{'precision': 0.7142857142857143, 'recall': 0.8823529411764706, 'f1': 0.7894736842105262, 'number': 34}	{'precision': 0.9182389937106918, 'recall': 0.8975409836065574, 'f1': 0.9077720207253885, 'number': 488}	{'precision': 0.6363636363636364, 'recall': 0.7368421052631579, 'f1': 0.6829268292682926, 'number': 38}	{'precision': 0.9047619047619048, 'recall': 0.8423645320197044, 'f1': 0.8724489795918366, 'number': 203}	{'precision': 0.9558011049723757, 'recall': 0.9851936218678815, 'f1': 0.9702748177229389, 'number': 878}	{'precision': 0.7649253731343284, 'recall': 0.8798283261802575, 'f1': 0.8183632734530938, 'number': 233}	0.9023	0.9232	0.9126	0.9624
0.014	7.0	2772	0.2611	{'precision': 0.7340425531914894, 'recall': 0.5948275862068966, 'f1': 0.6571428571428571, 'number': 116}	{'precision': 0.9732360097323601, 'recall': 0.9280742459396751, 'f1': 0.9501187648456058, 'number': 431}	{'precision': 0.7272727272727273, 'recall': 0.9411764705882353, 'f1': 0.8205128205128205, 'number': 34}	{'precision': 0.9046653144016227, 'recall': 0.9139344262295082, 'f1': 0.9092762487257898, 'number': 488}	{'precision': 0.6444444444444445, 'recall': 0.7631578947368421, 'f1': 0.6987951807228916, 'number': 38}	{'precision': 0.8947368421052632, 'recall': 0.8374384236453202, 'f1': 0.8651399491094148, 'number': 203}	{'precision': 0.9192348565356004, 'recall': 0.9851936218678815, 'f1': 0.9510720175920835, 'number': 878}	{'precision': 0.7829457364341085, 'recall': 0.8669527896995708, 'f1': 0.8228105906313645, 'number': 233}	0.8938	0.9141	0.9038	0.9607
0.0094	8.0	3168	0.2767	{'precision': 0.7422680412371134, 'recall': 0.6206896551724138, 'f1': 0.6760563380281691, 'number': 116}	{'precision': 0.9564220183486238, 'recall': 0.9675174013921114, 'f1': 0.9619377162629758, 'number': 431}	{'precision': 0.6818181818181818, 'recall': 0.8823529411764706, 'f1': 0.7692307692307693, 'number': 34}	{'precision': 0.9014373716632443, 'recall': 0.8995901639344263, 'f1': 0.9005128205128204, 'number': 488}	{'precision': 0.6444444444444445, 'recall': 0.7631578947368421, 'f1': 0.6987951807228916, 'number': 38}	{'precision': 0.8769230769230769, 'recall': 0.8423645320197044, 'f1': 0.8592964824120604, 'number': 203}	{'precision': 0.938177874186551, 'recall': 0.9851936218678815, 'f1': 0.961111111111111, 'number': 878}	{'precision': 0.7509157509157509, 'recall': 0.8798283261802575, 'f1': 0.8102766798418972, 'number': 233}	0.8916	0.9203	0.9057	0.9608
0.0041	9.0	3564	0.2789	{'precision': 0.7450980392156863, 'recall': 0.6551724137931034, 'f1': 0.6972477064220184, 'number': 116}	{'precision': 0.9518348623853211, 'recall': 0.962877030162413, 'f1': 0.9573241061130334, 'number': 431}	{'precision': 0.7209302325581395, 'recall': 0.9117647058823529, 'f1': 0.8051948051948051, 'number': 34}	{'precision': 0.9004065040650406, 'recall': 0.9077868852459017, 'f1': 0.9040816326530612, 'number': 488}	{'precision': 0.6341463414634146, 'recall': 0.6842105263157895, 'f1': 0.6582278481012659, 'number': 38}	{'precision': 0.890625, 'recall': 0.8423645320197044, 'f1': 0.8658227848101266, 'number': 203}	{'precision': 0.9402173913043478, 'recall': 0.9851936218678815, 'f1': 0.9621802002224694, 'number': 878}	{'precision': 0.7803921568627451, 'recall': 0.8540772532188842, 'f1': 0.8155737704918034, 'number': 233}	0.8972	0.9195	0.9082	0.9620
0.0041	10.0	3960	0.2865	{'precision': 0.7570093457943925, 'recall': 0.6982758620689655, 'f1': 0.726457399103139, 'number': 116}	{'precision': 0.9559164733178654, 'recall': 0.9559164733178654, 'f1': 0.9559164733178654, 'number': 431}	{'precision': 0.7209302325581395, 'recall': 0.9117647058823529, 'f1': 0.8051948051948051, 'number': 34}	{'precision': 0.9004065040650406, 'recall': 0.9077868852459017, 'f1': 0.9040816326530612, 'number': 488}	{'precision': 0.6136363636363636, 'recall': 0.7105263157894737, 'f1': 0.6585365853658537, 'number': 38}	{'precision': 0.8860103626943006, 'recall': 0.8423645320197044, 'f1': 0.8636363636363636, 'number': 203}	{'precision': 0.9453551912568307, 'recall': 0.9851936218678815, 'f1': 0.9648633575013943, 'number': 878}	{'precision': 0.7896825396825397, 'recall': 0.8540772532188842, 'f1': 0.820618556701031, 'number': 233}	0.8999	0.9207	0.9102	0.9616

Framework versions

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