roberta-large-ner-ghtk-cs-add-2label-16-new-data-3090-18Sep-1

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

• Loss: 0.3080
• Tk: {'precision': 0.7252747252747253, 'recall': 0.5689655172413793, 'f1': 0.6376811594202899, 'number': 116}
• A: {'precision': 0.9198218262806236, 'recall': 0.9582366589327146, 'f1': 0.9386363636363636, 'number': 431}
• Gày: {'precision': 0.6976744186046512, 'recall': 0.8823529411764706, 'f1': 0.7792207792207793, 'number': 34}
• Gày trừu tượng: {'precision': 0.8882235528942116, 'recall': 0.9118852459016393, 'f1': 0.8998988877654196, 'number': 488}
• Iền: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 39}
• Iờ: {'precision': 0.5833333333333334, 'recall': 0.7368421052631579, 'f1': 0.6511627906976745, 'number': 38}
• Ã đơn: {'precision': 0.8564102564102564, 'recall': 0.8226600985221675, 'f1': 0.8391959798994976, 'number': 203}
• Đt: {'precision': 0.928495197438634, 'recall': 0.9908883826879271, 'f1': 0.9586776859504132, 'number': 878}
• Đt trừu tượng: {'precision': 0.7331081081081081, 'recall': 0.9313304721030042, 'f1': 0.8204158790170132, 'number': 233}
• Overall Precision: 0.8734
• Overall Recall: 0.9089
• Overall F1: 0.8908
• Overall Accuracy: 0.9527

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	Iền	Iờ	Ã đơn	Đt	Đt trừu tượng	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
No log	1.0	298	0.2209	{'precision': 0.7027027027027027, 'recall': 0.22413793103448276, 'f1': 0.33986928104575165, 'number': 116}	{'precision': 0.9098712446351931, 'recall': 0.9837587006960556, 'f1': 0.9453734671125976, 'number': 431}	{'precision': 0.6739130434782609, 'recall': 0.9117647058823529, 'f1': 0.775, 'number': 34}	{'precision': 0.8674463937621832, 'recall': 0.9118852459016393, 'f1': 0.8891108891108892, 'number': 488}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 39}	{'precision': 0.5517241379310345, 'recall': 0.8421052631578947, 'f1': 0.6666666666666666, 'number': 38}	{'precision': 0.674074074074074, 'recall': 0.896551724137931, 'f1': 0.7695560253699789, 'number': 203}	{'precision': 0.893223819301848, 'recall': 0.9908883826879271, 'f1': 0.9395248380129589, 'number': 878}	{'precision': 0.672782874617737, 'recall': 0.944206008583691, 'f1': 0.7857142857142857, 'number': 233}	0.8287	0.9065	0.8659	0.9421
0.0927	2.0	596	0.1942	{'precision': 0.7281553398058253, 'recall': 0.646551724137931, 'f1': 0.684931506849315, 'number': 116}	{'precision': 0.9177489177489178, 'recall': 0.9837587006960556, 'f1': 0.9496080627099663, 'number': 431}	{'precision': 0.7105263157894737, 'recall': 0.7941176470588235, 'f1': 0.7499999999999999, 'number': 34}	{'precision': 0.8505747126436781, 'recall': 0.9098360655737705, 'f1': 0.8792079207920792, 'number': 488}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 39}	{'precision': 0.6415094339622641, 'recall': 0.8947368421052632, 'f1': 0.7472527472527473, 'number': 38}	{'precision': 0.8104265402843602, 'recall': 0.8423645320197044, 'f1': 0.8260869565217391, 'number': 203}	{'precision': 0.9303322615219721, 'recall': 0.9886104783599089, 'f1': 0.9585864163445611, 'number': 878}	{'precision': 0.6949685534591195, 'recall': 0.9484978540772532, 'f1': 0.8021778584392014, 'number': 233}	0.8576	0.9203	0.8878	0.9519
0.0927	3.0	894	0.2122	{'precision': 0.8734177215189873, 'recall': 0.5948275862068966, 'f1': 0.7076923076923076, 'number': 116}	{'precision': 0.9004237288135594, 'recall': 0.9860788863109049, 'f1': 0.9413067552602437, 'number': 431}	{'precision': 0.7317073170731707, 'recall': 0.8823529411764706, 'f1': 0.8, 'number': 34}	{'precision': 0.867816091954023, 'recall': 0.9282786885245902, 'f1': 0.8970297029702969, 'number': 488}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 39}	{'precision': 0.5714285714285714, 'recall': 0.9473684210526315, 'f1': 0.7128712871287128, 'number': 38}	{'precision': 0.9012345679012346, 'recall': 0.7192118226600985, 'f1': 0.8, 'number': 203}	{'precision': 0.9539842873176206, 'recall': 0.9681093394077449, 'f1': 0.9609949123798757, 'number': 878}	{'precision': 0.8125, 'recall': 0.8369098712446352, 'f1': 0.8245243128964059, 'number': 233}	0.8923	0.8959	0.8941	0.9541
0.0388	4.0	1192	0.2409	{'precision': 0.8648648648648649, 'recall': 0.5517241379310345, 'f1': 0.6736842105263158, 'number': 116}	{'precision': 0.9217002237136466, 'recall': 0.9559164733178654, 'f1': 0.938496583143508, 'number': 431}	{'precision': 0.6818181818181818, 'recall': 0.8823529411764706, 'f1': 0.7692307692307693, 'number': 34}	{'precision': 0.8708414872798435, 'recall': 0.9118852459016393, 'f1': 0.8908908908908908, 'number': 488}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 39}	{'precision': 0.4927536231884058, 'recall': 0.8947368421052632, 'f1': 0.6355140186915887, 'number': 38}	{'precision': 0.9244186046511628, 'recall': 0.7832512315270936, 'f1': 0.8479999999999999, 'number': 203}	{'precision': 0.9414951245937161, 'recall': 0.989749430523918, 'f1': 0.9650194336479733, 'number': 878}	{'precision': 0.6268656716417911, 'recall': 0.9012875536480687, 'f1': 0.7394366197183099, 'number': 233}	0.8633	0.9037	0.8830	0.9513
0.0388	5.0	1490	0.2519	{'precision': 0.7619047619047619, 'recall': 0.5517241379310345, 'f1': 0.64, 'number': 116}	{'precision': 0.922566371681416, 'recall': 0.9675174013921114, 'f1': 0.9445073612684032, 'number': 431}	{'precision': 0.6976744186046512, 'recall': 0.8823529411764706, 'f1': 0.7792207792207793, 'number': 34}	{'precision': 0.858508604206501, 'recall': 0.9200819672131147, 'f1': 0.8882294757665679, 'number': 488}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 39}	{'precision': 0.631578947368421, 'recall': 0.631578947368421, 'f1': 0.631578947368421, 'number': 38}	{'precision': 0.8477157360406091, 'recall': 0.8226600985221675, 'f1': 0.8350000000000001, 'number': 203}	{'precision': 0.9219409282700421, 'recall': 0.9954441913439636, 'f1': 0.9572836801752465, 'number': 878}	{'precision': 0.6964856230031949, 'recall': 0.9356223175965666, 'f1': 0.7985347985347986, 'number': 233}	0.8634	0.9118	0.8869	0.9538
0.0272	6.0	1788	0.2670	{'precision': 0.7303370786516854, 'recall': 0.5603448275862069, 'f1': 0.6341463414634146, 'number': 116}	{'precision': 0.9271523178807947, 'recall': 0.974477958236659, 'f1': 0.9502262443438914, 'number': 431}	{'precision': 0.6744186046511628, 'recall': 0.8529411764705882, 'f1': 0.7532467532467532, 'number': 34}	{'precision': 0.8708414872798435, 'recall': 0.9118852459016393, 'f1': 0.8908908908908908, 'number': 488}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 39}	{'precision': 0.6744186046511628, 'recall': 0.7631578947368421, 'f1': 0.7160493827160495, 'number': 38}	{'precision': 0.8791208791208791, 'recall': 0.7881773399014779, 'f1': 0.8311688311688312, 'number': 203}	{'precision': 0.9357601713062098, 'recall': 0.9954441913439636, 'f1': 0.9646799116997792, 'number': 878}	{'precision': 0.7181208053691275, 'recall': 0.9184549356223176, 'f1': 0.8060263653483992, 'number': 233}	0.8758	0.9089	0.8921	0.9553
0.0137	7.0	2086	0.2894	{'precision': 0.7849462365591398, 'recall': 0.6293103448275862, 'f1': 0.6985645933014354, 'number': 116}	{'precision': 0.9237668161434978, 'recall': 0.9559164733178654, 'f1': 0.9395667046750285, 'number': 431}	{'precision': 0.7142857142857143, 'recall': 0.8823529411764706, 'f1': 0.7894736842105262, 'number': 34}	{'precision': 0.8920570264765784, 'recall': 0.8975409836065574, 'f1': 0.8947906026557712, 'number': 488}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 39}	{'precision': 0.5686274509803921, 'recall': 0.7631578947368421, 'f1': 0.651685393258427, 'number': 38}	{'precision': 0.8522167487684729, 'recall': 0.8522167487684729, 'f1': 0.852216748768473, 'number': 203}	{'precision': 0.9248677248677248, 'recall': 0.9954441913439636, 'f1': 0.9588590235874931, 'number': 878}	{'precision': 0.7437722419928826, 'recall': 0.8969957081545065, 'f1': 0.8132295719844358, 'number': 233}	0.8770	0.9098	0.8931	0.9537
0.0137	8.0	2384	0.2868	{'precision': 0.7368421052631579, 'recall': 0.603448275862069, 'f1': 0.6635071090047393, 'number': 116}	{'precision': 0.9137168141592921, 'recall': 0.9582366589327146, 'f1': 0.9354473386183466, 'number': 431}	{'precision': 0.7272727272727273, 'recall': 0.9411764705882353, 'f1': 0.8205128205128205, 'number': 34}	{'precision': 0.8904665314401623, 'recall': 0.8995901639344263, 'f1': 0.8950050968399593, 'number': 488}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 39}	{'precision': 0.5882352941176471, 'recall': 0.7894736842105263, 'f1': 0.6741573033707866, 'number': 38}	{'precision': 0.8542713567839196, 'recall': 0.8374384236453202, 'f1': 0.845771144278607, 'number': 203}	{'precision': 0.9375, 'recall': 0.9908883826879271, 'f1': 0.9634551495016611, 'number': 878}	{'precision': 0.7700729927007299, 'recall': 0.9055793991416309, 'f1': 0.8323471400394478, 'number': 233}	0.8813	0.9085	0.8947	0.9533
0.007	9.0	2682	0.3053	{'precision': 0.7368421052631579, 'recall': 0.603448275862069, 'f1': 0.6635071090047393, 'number': 116}	{'precision': 0.9177777777777778, 'recall': 0.9582366589327146, 'f1': 0.9375709421112373, 'number': 431}	{'precision': 0.7111111111111111, 'recall': 0.9411764705882353, 'f1': 0.8101265822784811, 'number': 34}	{'precision': 0.8774703557312253, 'recall': 0.9098360655737705, 'f1': 0.8933601609657947, 'number': 488}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 39}	{'precision': 0.5957446808510638, 'recall': 0.7368421052631579, 'f1': 0.6588235294117647, 'number': 38}	{'precision': 0.8527918781725888, 'recall': 0.8275862068965517, 'f1': 0.84, 'number': 203}	{'precision': 0.932475884244373, 'recall': 0.9908883826879271, 'f1': 0.9607951408061844, 'number': 878}	{'precision': 0.7448275862068966, 'recall': 0.927038626609442, 'f1': 0.8260038240917782, 'number': 233}	0.8744	0.9110	0.8923	0.9524
0.007	10.0	2980	0.3080	{'precision': 0.7252747252747253, 'recall': 0.5689655172413793, 'f1': 0.6376811594202899, 'number': 116}	{'precision': 0.9198218262806236, 'recall': 0.9582366589327146, 'f1': 0.9386363636363636, 'number': 431}	{'precision': 0.6976744186046512, 'recall': 0.8823529411764706, 'f1': 0.7792207792207793, 'number': 34}	{'precision': 0.8882235528942116, 'recall': 0.9118852459016393, 'f1': 0.8998988877654196, 'number': 488}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 39}	{'precision': 0.5833333333333334, 'recall': 0.7368421052631579, 'f1': 0.6511627906976745, 'number': 38}	{'precision': 0.8564102564102564, 'recall': 0.8226600985221675, 'f1': 0.8391959798994976, 'number': 203}	{'precision': 0.928495197438634, 'recall': 0.9908883826879271, 'f1': 0.9586776859504132, 'number': 878}	{'precision': 0.7331081081081081, 'recall': 0.9313304721030042, 'f1': 0.8204158790170132, 'number': 233}	0.8734	0.9089	0.8908	0.9527

Framework versions

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