roberta-large-ner-ghtk-cs-add-2label-16-new-data-3090-16Sep-1

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

• Loss: 0.2797
• Tk: {'precision': 0.8, 'recall': 0.7586206896551724, 'f1': 0.7787610619469026, 'number': 116}
• A: {'precision': 0.9242761692650334, 'recall': 0.962877030162413, 'f1': 0.9431818181818182, 'number': 431}
• Gày: {'precision': 0.7111111111111111, 'recall': 0.9411764705882353, 'f1': 0.8101265822784811, 'number': 34}
• Gày trừu tượng: {'precision': 0.9047619047619048, 'recall': 0.8954918032786885, 'f1': 0.9001029866117404, 'number': 488}
• Iờ: {'precision': 0.675, 'recall': 0.7105263157894737, 'f1': 0.6923076923076923, 'number': 38}
• Ã đơn: {'precision': 0.8300970873786407, 'recall': 0.8423645320197044, 'f1': 0.8361858190709045, 'number': 203}
• Đt: {'precision': 0.9442013129102844, 'recall': 0.9829157175398633, 'f1': 0.9631696428571428, 'number': 878}
• Đt trừu tượng: {'precision': 0.7364864864864865, 'recall': 0.9356223175965666, 'f1': 0.8241965973534972, 'number': 233}
• Overall Precision: 0.8852
• Overall Recall: 0.9298
• Overall F1: 0.9069
• Overall Accuracy: 0.9585

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	298	0.2560	{'precision': 0.640625, 'recall': 0.35344827586206895, 'f1': 0.45555555555555555, 'number': 116}	{'precision': 0.918141592920354, 'recall': 0.962877030162413, 'f1': 0.9399773499433748, 'number': 431}	{'precision': 0.45161290322580644, 'recall': 0.8235294117647058, 'f1': 0.5833333333333333, 'number': 34}	{'precision': 0.8821218074656189, 'recall': 0.9200819672131147, 'f1': 0.9007021063189569, 'number': 488}	{'precision': 0.5283018867924528, 'recall': 0.7368421052631579, 'f1': 0.6153846153846154, 'number': 38}	{'precision': 0.68359375, 'recall': 0.8620689655172413, 'f1': 0.7625272331154684, 'number': 203}	{'precision': 0.889348500517063, 'recall': 0.979498861047836, 'f1': 0.9322493224932249, 'number': 878}	{'precision': 0.5658914728682171, 'recall': 0.9399141630901288, 'f1': 0.7064516129032258, 'number': 233}	0.8055	0.9149	0.8567	0.9384
0.0856	2.0	596	0.1970	{'precision': 0.7951807228915663, 'recall': 0.5689655172413793, 'f1': 0.6633165829145728, 'number': 116}	{'precision': 0.9399538106235565, 'recall': 0.9443155452436195, 'f1': 0.9421296296296297, 'number': 431}	{'precision': 0.6530612244897959, 'recall': 0.9411764705882353, 'f1': 0.7710843373493975, 'number': 34}	{'precision': 0.9102296450939458, 'recall': 0.8934426229508197, 'f1': 0.9017580144777663, 'number': 488}	{'precision': 0.5901639344262295, 'recall': 0.9473684210526315, 'f1': 0.7272727272727273, 'number': 38}	{'precision': 0.8142857142857143, 'recall': 0.8423645320197044, 'f1': 0.828087167070218, 'number': 203}	{'precision': 0.9053069719042663, 'recall': 0.9908883826879271, 'f1': 0.9461663947797716, 'number': 878}	{'precision': 0.6380368098159509, 'recall': 0.8927038626609443, 'f1': 0.7441860465116278, 'number': 233}	0.8555	0.9195	0.8863	0.9537
0.0856	3.0	894	0.2256	{'precision': 0.8426966292134831, 'recall': 0.646551724137931, 'f1': 0.7317073170731707, 'number': 116}	{'precision': 0.9351230425055929, 'recall': 0.9698375870069605, 'f1': 0.9521640091116174, 'number': 431}	{'precision': 0.7435897435897436, 'recall': 0.8529411764705882, 'f1': 0.7945205479452054, 'number': 34}	{'precision': 0.8660194174757282, 'recall': 0.9139344262295082, 'f1': 0.8893320039880359, 'number': 488}	{'precision': 0.6382978723404256, 'recall': 0.7894736842105263, 'f1': 0.7058823529411764, 'number': 38}	{'precision': 0.9259259259259259, 'recall': 0.7389162561576355, 'f1': 0.8219178082191781, 'number': 203}	{'precision': 0.9369565217391305, 'recall': 0.9817767653758542, 'f1': 0.9588431590656284, 'number': 878}	{'precision': 0.6735395189003437, 'recall': 0.8412017167381974, 'f1': 0.7480916030534353, 'number': 233}	0.8789	0.9112	0.8947	0.9565
0.0382	4.0	1192	0.2189	{'precision': 0.7923076923076923, 'recall': 0.8879310344827587, 'f1': 0.8373983739837397, 'number': 116}	{'precision': 0.9682926829268292, 'recall': 0.9211136890951276, 'f1': 0.9441141498216409, 'number': 431}	{'precision': 0.625, 'recall': 0.7352941176470589, 'f1': 0.6756756756756757, 'number': 34}	{'precision': 0.8771929824561403, 'recall': 0.9221311475409836, 'f1': 0.899100899100899, 'number': 488}	{'precision': 0.5409836065573771, 'recall': 0.868421052631579, 'f1': 0.6666666666666666, 'number': 38}	{'precision': 0.8756476683937824, 'recall': 0.8325123152709359, 'f1': 0.8535353535353536, 'number': 203}	{'precision': 0.9674523007856342, 'recall': 0.9817767653758542, 'f1': 0.9745618993781798, 'number': 878}	{'precision': 0.6488095238095238, 'recall': 0.9356223175965666, 'f1': 0.7662565905096661, 'number': 233}	0.8768	0.9323	0.9037	0.9575
0.0382	5.0	1490	0.2290	{'precision': 0.7747747747747747, 'recall': 0.7413793103448276, 'f1': 0.7577092511013217, 'number': 116}	{'precision': 0.9312638580931264, 'recall': 0.974477958236659, 'f1': 0.9523809523809523, 'number': 431}	{'precision': 0.7441860465116279, 'recall': 0.9411764705882353, 'f1': 0.8311688311688312, 'number': 34}	{'precision': 0.8997955010224948, 'recall': 0.9016393442622951, 'f1': 0.9007164790174003, 'number': 488}	{'precision': 0.7857142857142857, 'recall': 0.5789473684210527, 'f1': 0.6666666666666667, 'number': 38}	{'precision': 0.9106145251396648, 'recall': 0.8029556650246306, 'f1': 0.8534031413612566, 'number': 203}	{'precision': 0.9614512471655329, 'recall': 0.9658314350797267, 'f1': 0.9636363636363636, 'number': 878}	{'precision': 0.7768924302788844, 'recall': 0.8369098712446352, 'f1': 0.8057851239669422, 'number': 233}	0.9063	0.9112	0.9088	0.9616
0.025	6.0	1788	0.2494	{'precision': 0.7338709677419355, 'recall': 0.7844827586206896, 'f1': 0.7583333333333333, 'number': 116}	{'precision': 0.9154013015184381, 'recall': 0.9791183294663574, 'f1': 0.946188340807175, 'number': 431}	{'precision': 0.7209302325581395, 'recall': 0.9117647058823529, 'f1': 0.8051948051948051, 'number': 34}	{'precision': 0.893574297188755, 'recall': 0.9118852459016393, 'f1': 0.9026369168356998, 'number': 488}	{'precision': 0.65, 'recall': 0.6842105263157895, 'f1': 0.6666666666666667, 'number': 38}	{'precision': 0.8608247422680413, 'recall': 0.8226600985221675, 'f1': 0.8413098236775819, 'number': 203}	{'precision': 0.9474260679079957, 'recall': 0.9851936218678815, 'f1': 0.9659408151870463, 'number': 878}	{'precision': 0.7709923664122137, 'recall': 0.8669527896995708, 'f1': 0.8161616161616161, 'number': 233}	0.8872	0.9290	0.9076	0.9596
0.0136	7.0	2086	0.2645	{'precision': 0.8, 'recall': 0.7586206896551724, 'f1': 0.7787610619469026, 'number': 116}	{'precision': 0.9321266968325792, 'recall': 0.9559164733178654, 'f1': 0.9438717067583048, 'number': 431}	{'precision': 0.7333333333333333, 'recall': 0.9705882352941176, 'f1': 0.8354430379746834, 'number': 34}	{'precision': 0.9036885245901639, 'recall': 0.9036885245901639, 'f1': 0.9036885245901639, 'number': 488}	{'precision': 0.6829268292682927, 'recall': 0.7368421052631579, 'f1': 0.7088607594936709, 'number': 38}	{'precision': 0.8877005347593583, 'recall': 0.8177339901477833, 'f1': 0.8512820512820511, 'number': 203}	{'precision': 0.9551569506726457, 'recall': 0.9703872437357631, 'f1': 0.9627118644067797, 'number': 878}	{'precision': 0.7233333333333334, 'recall': 0.9313304721030042, 'f1': 0.8142589118198874, 'number': 233}	0.8930	0.9240	0.9082	0.9598
0.0136	8.0	2384	0.2769	{'precision': 0.7857142857142857, 'recall': 0.7586206896551724, 'f1': 0.7719298245614034, 'number': 116}	{'precision': 0.9193899782135077, 'recall': 0.9791183294663574, 'f1': 0.9483146067415731, 'number': 431}	{'precision': 0.7333333333333333, 'recall': 0.9705882352941176, 'f1': 0.8354430379746834, 'number': 34}	{'precision': 0.9016393442622951, 'recall': 0.9016393442622951, 'f1': 0.9016393442622952, 'number': 488}	{'precision': 0.6078431372549019, 'recall': 0.8157894736842105, 'f1': 0.6966292134831461, 'number': 38}	{'precision': 0.7882882882882883, 'recall': 0.8620689655172413, 'f1': 0.823529411764706, 'number': 203}	{'precision': 0.9495060373216246, 'recall': 0.9851936218678815, 'f1': 0.9670206819452208, 'number': 878}	{'precision': 0.7147540983606557, 'recall': 0.9356223175965666, 'f1': 0.8104089219330856, 'number': 233}	0.8762	0.9385	0.9063	0.9562
0.0086	9.0	2682	0.2666	{'precision': 0.8, 'recall': 0.7586206896551724, 'f1': 0.7787610619469026, 'number': 116}	{'precision': 0.9285714285714286, 'recall': 0.9651972157772621, 'f1': 0.9465301478953356, 'number': 431}	{'precision': 0.7380952380952381, 'recall': 0.9117647058823529, 'f1': 0.8157894736842106, 'number': 34}	{'precision': 0.9070247933884298, 'recall': 0.8995901639344263, 'f1': 0.9032921810699589, 'number': 488}	{'precision': 0.625, 'recall': 0.6578947368421053, 'f1': 0.6410256410256411, 'number': 38}	{'precision': 0.8808290155440415, 'recall': 0.8374384236453202, 'f1': 0.8585858585858585, 'number': 203}	{'precision': 0.944994499449945, 'recall': 0.9783599088838268, 'f1': 0.9613878007834359, 'number': 878}	{'precision': 0.776173285198556, 'recall': 0.9227467811158798, 'f1': 0.8431372549019608, 'number': 233}	0.8961	0.9265	0.9110	0.9607
0.0086	10.0	2980	0.2797	{'precision': 0.8, 'recall': 0.7586206896551724, 'f1': 0.7787610619469026, 'number': 116}	{'precision': 0.9242761692650334, 'recall': 0.962877030162413, 'f1': 0.9431818181818182, 'number': 431}	{'precision': 0.7111111111111111, 'recall': 0.9411764705882353, 'f1': 0.8101265822784811, 'number': 34}	{'precision': 0.9047619047619048, 'recall': 0.8954918032786885, 'f1': 0.9001029866117404, 'number': 488}	{'precision': 0.675, 'recall': 0.7105263157894737, 'f1': 0.6923076923076923, 'number': 38}	{'precision': 0.8300970873786407, 'recall': 0.8423645320197044, 'f1': 0.8361858190709045, 'number': 203}	{'precision': 0.9442013129102844, 'recall': 0.9829157175398633, 'f1': 0.9631696428571428, 'number': 878}	{'precision': 0.7364864864864865, 'recall': 0.9356223175965666, 'f1': 0.8241965973534972, 'number': 233}	0.8852	0.9298	0.9069	0.9585

Framework versions

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