roberta-large-ner-ghtk-cs-add-3label-16-new-data-3090-19Sep-1

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

• Loss: 0.2826
• Tk: {'precision': 0.7669902912621359, 'recall': 0.6810344827586207, 'f1': 0.7214611872146118, 'number': 116}
• A: {'precision': 0.9321266968325792, 'recall': 0.9559164733178654, 'f1': 0.9438717067583048, 'number': 431}
• Gày: {'precision': 0.717948717948718, 'recall': 0.8235294117647058, 'f1': 0.767123287671233, 'number': 34}
• Gày trừu tượng: {'precision': 0.8864097363083164, 'recall': 0.8954918032786885, 'f1': 0.890927624872579, 'number': 488}
• Iền: {'precision': 0.76, 'recall': 0.9743589743589743, 'f1': 0.853932584269663, 'number': 39}
• Iờ: {'precision': 0.6904761904761905, 'recall': 0.7631578947368421, 'f1': 0.725, 'number': 38}
• Ã đơn: {'precision': 0.8677248677248677, 'recall': 0.8078817733990148, 'f1': 0.836734693877551, 'number': 203}
• Đt: {'precision': 0.9456521739130435, 'recall': 0.9908883826879271, 'f1': 0.967741935483871, 'number': 878}
• Đt trừu tượng: {'precision': 0.7562724014336918, 'recall': 0.9055793991416309, 'f1': 0.82421875, 'number': 233}
• Overall Precision: 0.8870
• Overall Recall: 0.9220
• Overall F1: 0.9041
• Overall Accuracy: 0.9589

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	315	0.1648	{'precision': 0.7755102040816326, 'recall': 0.3275862068965517, 'f1': 0.46060606060606063, 'number': 116}	{'precision': 0.9075268817204301, 'recall': 0.9791183294663574, 'f1': 0.9419642857142858, 'number': 431}	{'precision': 0.5961538461538461, 'recall': 0.9117647058823529, 'f1': 0.7209302325581395, 'number': 34}	{'precision': 0.8640776699029126, 'recall': 0.9118852459016393, 'f1': 0.8873379860418743, 'number': 488}	{'precision': 0.7727272727272727, 'recall': 0.8717948717948718, 'f1': 0.8192771084337349, 'number': 39}	{'precision': 0.8235294117647058, 'recall': 0.3684210526315789, 'f1': 0.509090909090909, 'number': 38}	{'precision': 0.8816568047337278, 'recall': 0.7339901477832512, 'f1': 0.8010752688172043, 'number': 203}	{'precision': 0.891260162601626, 'recall': 0.9988610478359908, 'f1': 0.9419978517722878, 'number': 878}	{'precision': 0.8382978723404255, 'recall': 0.8454935622317596, 'f1': 0.8418803418803419, 'number': 233}	0.8723	0.8972	0.8846	0.9548
0.1057	2.0	630	0.1924	{'precision': 0.7752808988764045, 'recall': 0.5948275862068966, 'f1': 0.673170731707317, 'number': 116}	{'precision': 0.9373549883990719, 'recall': 0.9373549883990719, 'f1': 0.9373549883990719, 'number': 431}	{'precision': 0.7142857142857143, 'recall': 0.8823529411764706, 'f1': 0.7894736842105262, 'number': 34}	{'precision': 0.8433962264150944, 'recall': 0.9159836065573771, 'f1': 0.8781925343811395, 'number': 488}	{'precision': 0.7450980392156863, 'recall': 0.9743589743589743, 'f1': 0.8444444444444443, 'number': 39}	{'precision': 0.5737704918032787, 'recall': 0.9210526315789473, 'f1': 0.7070707070707071, 'number': 38}	{'precision': 0.8932584269662921, 'recall': 0.7832512315270936, 'f1': 0.8346456692913385, 'number': 203}	{'precision': 0.9234856535600425, 'recall': 0.989749430523918, 'f1': 0.9554700384826827, 'number': 878}	{'precision': 0.68125, 'recall': 0.9356223175965666, 'f1': 0.7884267631103075, 'number': 233}	0.8585	0.9224	0.8893	0.9563
0.1057	3.0	945	0.2188	{'precision': 0.7345132743362832, 'recall': 0.7155172413793104, 'f1': 0.7248908296943231, 'number': 116}	{'precision': 0.9461358313817331, 'recall': 0.9373549883990719, 'f1': 0.9417249417249417, 'number': 431}	{'precision': 0.6904761904761905, 'recall': 0.8529411764705882, 'f1': 0.7631578947368423, 'number': 34}	{'precision': 0.8423005565862709, 'recall': 0.930327868852459, 'f1': 0.8841285296981499, 'number': 488}	{'precision': 0.74, 'recall': 0.9487179487179487, 'f1': 0.8314606741573033, 'number': 39}	{'precision': 0.576271186440678, 'recall': 0.8947368421052632, 'f1': 0.7010309278350517, 'number': 38}	{'precision': 0.9022988505747126, 'recall': 0.7733990147783252, 'f1': 0.8328912466843502, 'number': 203}	{'precision': 0.927061310782241, 'recall': 0.9988610478359908, 'f1': 0.9616228070175438, 'number': 878}	{'precision': 0.7840909090909091, 'recall': 0.8884120171673819, 'f1': 0.8329979879275653, 'number': 233}	0.8730	0.9276	0.8995	0.9563
0.0502	4.0	1260	0.2143	{'precision': 0.7692307692307693, 'recall': 0.6896551724137931, 'f1': 0.7272727272727274, 'number': 116}	{'precision': 0.918859649122807, 'recall': 0.9721577726218097, 'f1': 0.9447576099210823, 'number': 431}	{'precision': 0.6904761904761905, 'recall': 0.8529411764705882, 'f1': 0.7631578947368423, 'number': 34}	{'precision': 0.8670520231213873, 'recall': 0.9221311475409836, 'f1': 0.8937437934458788, 'number': 488}	{'precision': 0.7169811320754716, 'recall': 0.9743589743589743, 'f1': 0.8260869565217391, 'number': 39}	{'precision': 0.6129032258064516, 'recall': 1.0, 'f1': 0.76, 'number': 38}	{'precision': 0.9027027027027027, 'recall': 0.8226600985221675, 'f1': 0.8608247422680413, 'number': 203}	{'precision': 0.9321851453175457, 'recall': 0.9863325740318907, 'f1': 0.9584947426674045, 'number': 878}	{'precision': 0.7448275862068966, 'recall': 0.927038626609442, 'f1': 0.8260038240917782, 'number': 233}	0.8723	0.9362	0.9031	0.9595
0.0298	5.0	1575	0.2116	{'precision': 0.765625, 'recall': 0.8448275862068966, 'f1': 0.8032786885245901, 'number': 116}	{'precision': 0.9439252336448598, 'recall': 0.9373549883990719, 'f1': 0.940628637951106, 'number': 431}	{'precision': 0.7435897435897436, 'recall': 0.8529411764705882, 'f1': 0.7945205479452054, 'number': 34}	{'precision': 0.8667953667953668, 'recall': 0.9200819672131147, 'f1': 0.8926441351888668, 'number': 488}	{'precision': 0.7307692307692307, 'recall': 0.9743589743589743, 'f1': 0.8351648351648352, 'number': 39}	{'precision': 0.725, 'recall': 0.7631578947368421, 'f1': 0.7435897435897436, 'number': 38}	{'precision': 0.9090909090909091, 'recall': 0.7881773399014779, 'f1': 0.8443271767810027, 'number': 203}	{'precision': 0.9590254706533776, 'recall': 0.9863325740318907, 'f1': 0.9724873666479507, 'number': 878}	{'precision': 0.7508650519031141, 'recall': 0.9313304721030042, 'f1': 0.8314176245210727, 'number': 233}	0.8900	0.9309	0.9100	0.9609
0.0298	6.0	1890	0.2537	{'precision': 0.7909090909090909, 'recall': 0.75, 'f1': 0.7699115044247786, 'number': 116}	{'precision': 0.9362186788154897, 'recall': 0.9535962877030162, 'f1': 0.9448275862068964, 'number': 431}	{'precision': 0.6829268292682927, 'recall': 0.8235294117647058, 'f1': 0.7466666666666667, 'number': 34}	{'precision': 0.8987854251012146, 'recall': 0.9098360655737705, 'f1': 0.9042769857433809, 'number': 488}	{'precision': 0.7307692307692307, 'recall': 0.9743589743589743, 'f1': 0.8351648351648352, 'number': 39}	{'precision': 0.6304347826086957, 'recall': 0.7631578947368421, 'f1': 0.6904761904761905, 'number': 38}	{'precision': 0.9, 'recall': 0.7980295566502463, 'f1': 0.8459530026109661, 'number': 203}	{'precision': 0.9576837416481069, 'recall': 0.979498861047836, 'f1': 0.9684684684684685, 'number': 878}	{'precision': 0.7672727272727272, 'recall': 0.9055793991416309, 'f1': 0.8307086614173227, 'number': 233}	0.8955	0.9228	0.9089	0.9608
0.0173	7.0	2205	0.2857	{'precision': 0.782608695652174, 'recall': 0.6206896551724138, 'f1': 0.6923076923076923, 'number': 116}	{'precision': 0.9342403628117913, 'recall': 0.9559164733178654, 'f1': 0.9449541284403669, 'number': 431}	{'precision': 0.717948717948718, 'recall': 0.8235294117647058, 'f1': 0.767123287671233, 'number': 34}	{'precision': 0.8897795591182365, 'recall': 0.9098360655737705, 'f1': 0.8996960486322187, 'number': 488}	{'precision': 0.7755102040816326, 'recall': 0.9743589743589743, 'f1': 0.8636363636363635, 'number': 39}	{'precision': 0.6744186046511628, 'recall': 0.7631578947368421, 'f1': 0.7160493827160495, 'number': 38}	{'precision': 0.8852459016393442, 'recall': 0.7980295566502463, 'f1': 0.839378238341969, 'number': 203}	{'precision': 0.9351351351351351, 'recall': 0.9851936218678815, 'f1': 0.9595119245701608, 'number': 878}	{'precision': 0.6656346749226006, 'recall': 0.9227467811158798, 'f1': 0.7733812949640289, 'number': 233}	0.8732	0.9207	0.8963	0.9575
0.0105	8.0	2520	0.2864	{'precision': 0.7959183673469388, 'recall': 0.6724137931034483, 'f1': 0.7289719626168225, 'number': 116}	{'precision': 0.9403669724770642, 'recall': 0.951276102088167, 'f1': 0.9457900807381776, 'number': 431}	{'precision': 0.6904761904761905, 'recall': 0.8529411764705882, 'f1': 0.7631578947368423, 'number': 34}	{'precision': 0.8946280991735537, 'recall': 0.8872950819672131, 'f1': 0.8909465020576132, 'number': 488}	{'precision': 0.7450980392156863, 'recall': 0.9743589743589743, 'f1': 0.8444444444444443, 'number': 39}	{'precision': 0.75, 'recall': 0.7105263157894737, 'f1': 0.7297297297297298, 'number': 38}	{'precision': 0.8704663212435233, 'recall': 0.8275862068965517, 'f1': 0.8484848484848485, 'number': 203}	{'precision': 0.9493392070484582, 'recall': 0.9817767653758542, 'f1': 0.9652855543113102, 'number': 878}	{'precision': 0.7210884353741497, 'recall': 0.9098712446351931, 'f1': 0.8045540796963946, 'number': 233}	0.8879	0.9175	0.9024	0.9595
0.0105	9.0	2835	0.2858	{'precision': 0.7938144329896907, 'recall': 0.6637931034482759, 'f1': 0.7230046948356809, 'number': 116}	{'precision': 0.9399538106235565, 'recall': 0.9443155452436195, 'f1': 0.9421296296296297, 'number': 431}	{'precision': 0.7, 'recall': 0.8235294117647058, 'f1': 0.7567567567567567, 'number': 34}	{'precision': 0.8752475247524752, 'recall': 0.9057377049180327, 'f1': 0.8902316213494461, 'number': 488}	{'precision': 0.7254901960784313, 'recall': 0.9487179487179487, 'f1': 0.8222222222222223, 'number': 39}	{'precision': 0.6521739130434783, 'recall': 0.7894736842105263, 'f1': 0.7142857142857143, 'number': 38}	{'precision': 0.8534031413612565, 'recall': 0.8029556650246306, 'f1': 0.8274111675126904, 'number': 203}	{'precision': 0.942578548212351, 'recall': 0.9908883826879271, 'f1': 0.9661299278178789, 'number': 878}	{'precision': 0.7924528301886793, 'recall': 0.9012875536480687, 'f1': 0.8433734939759037, 'number': 233}	0.8875	0.9203	0.9036	0.9587
0.0052	10.0	3150	0.2826	{'precision': 0.7669902912621359, 'recall': 0.6810344827586207, 'f1': 0.7214611872146118, 'number': 116}	{'precision': 0.9321266968325792, 'recall': 0.9559164733178654, 'f1': 0.9438717067583048, 'number': 431}	{'precision': 0.717948717948718, 'recall': 0.8235294117647058, 'f1': 0.767123287671233, 'number': 34}	{'precision': 0.8864097363083164, 'recall': 0.8954918032786885, 'f1': 0.890927624872579, 'number': 488}	{'precision': 0.76, 'recall': 0.9743589743589743, 'f1': 0.853932584269663, 'number': 39}	{'precision': 0.6904761904761905, 'recall': 0.7631578947368421, 'f1': 0.725, 'number': 38}	{'precision': 0.8677248677248677, 'recall': 0.8078817733990148, 'f1': 0.836734693877551, 'number': 203}	{'precision': 0.9456521739130435, 'recall': 0.9908883826879271, 'f1': 0.967741935483871, 'number': 878}	{'precision': 0.7562724014336918, 'recall': 0.9055793991416309, 'f1': 0.82421875, 'number': 233}	0.8870	0.9220	0.9041	0.9589

Framework versions

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