roberta-large-ner-ghtk-cs-add-6label-5-new-data-3090-24Sep-1

Kudod/roberta-large-ner-ghtk-cs-add-6label-5-new-data-3090-24Sep-1

roberta-large-ner-ghtk-cs-add-6label-5-new-data-3090-24Sep-1 is a machine learning model from Kudod. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

4% of all-time downloads

All-time downloads

Public

Parameters

559M

13.4 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors2.2 GB · 99%

At a glance

Model type: xlm-roberta
Access: Public
Created: Sep 24, 2024
Updated: Sep 24, 2024
SHA: 5f649bf2

Model card

From the Hugging Face model README

roberta-large-ner-ghtk-cs-add-6label-5-new-data-3090-24Sep-1

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

Loss: 0.3298
Tk: {'precision': 0.6448598130841121, 'recall': 0.5948275862068966, 'f1': 0.6188340807174888, 'number': 116}
A: {'precision': 0.9324324324324325, 'recall': 0.9605568445475638, 'f1': 0.9462857142857144, 'number': 431}
Gày: {'precision': 0.7380952380952381, 'recall': 0.9117647058823529, 'f1': 0.8157894736842106, 'number': 34}
Gày trừu tượng: {'precision': 0.906054279749478, 'recall': 0.889344262295082, 'f1': 0.8976215098241986, 'number': 488}
Gân hàng: {'precision': 0.8421052631578947, 'recall': 0.8648648648648649, 'f1': 0.8533333333333334, 'number': 37}
Iền: {'precision': 0.6851851851851852, 'recall': 0.9487179487179487, 'f1': 0.7956989247311828, 'number': 39}
Iờ: {'precision': 0.6382978723404256, 'recall': 0.7894736842105263, 'f1': 0.7058823529411764, 'number': 38}
Ã đơn: {'precision': 0.8631578947368421, 'recall': 0.8078817733990148, 'f1': 0.8346055979643766, 'number': 203}
Đt: {'precision': 0.9299781181619255, 'recall': 0.9681093394077449, 'f1': 0.9486607142857143, 'number': 878}
Đt trừu tượng: {'precision': 0.8211382113821138, 'recall': 0.8669527896995708, 'f1': 0.8434237995824635, 'number': 233}
Ịa chỉ cụ thể: {'precision': 0.52, 'recall': 0.6046511627906976, 'f1': 0.5591397849462365, 'number': 43}
Ịa chỉ trừu tượng: {'precision': 0.6626506024096386, 'recall': 0.7236842105263158, 'f1': 0.6918238993710693, 'number': 76}
Overall Precision: 0.8701
Overall Recall: 0.8960
Overall F1: 0.8829
Overall Accuracy: 0.9480

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	Gân hàng	Iền	Iờ	Ã đơn	Đt	Đt trừu tượng	Ịa chỉ cụ thể	Ịa chỉ trừu tượng	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
No log	1.0	350	0.2079	{'precision': 0.5987654320987654, 'recall': 0.8362068965517241, 'f1': 0.6978417266187049, 'number': 116}	{'precision': 0.9391100702576113, 'recall': 0.9303944315545244, 'f1': 0.9347319347319347, 'number': 431}	{'precision': 0.625, 'recall': 0.7352941176470589, 'f1': 0.6756756756756757, 'number': 34}	{'precision': 0.9588688946015425, 'recall': 0.764344262295082, 'f1': 0.8506271379703535, 'number': 488}	{'precision': 0.8205128205128205, 'recall': 0.8648648648648649, 'f1': 0.8421052631578947, 'number': 37}	{'precision': 0.8148148148148148, 'recall': 0.5641025641025641, 'f1': 0.6666666666666667, 'number': 39}	{'precision': 0.8214285714285714, 'recall': 0.6052631578947368, 'f1': 0.6969696969696969, 'number': 38}	{'precision': 0.8932584269662921, 'recall': 0.7832512315270936, 'f1': 0.8346456692913385, 'number': 203}	{'precision': 0.9631696428571429, 'recall': 0.9829157175398633, 'f1': 0.9729425028184894, 'number': 878}	{'precision': 0.8347826086956521, 'recall': 0.8240343347639485, 'f1': 0.8293736501079914, 'number': 233}	{'precision': 0.1951219512195122, 'recall': 0.18604651162790697, 'f1': 0.1904761904761905, 'number': 43}	{'precision': 0.7966101694915254, 'recall': 0.618421052631579, 'f1': 0.6962962962962964, 'number': 76}	0.8911	0.8570	0.8737	0.9424
0.2068	2.0	700	0.2081	{'precision': 0.5632183908045977, 'recall': 0.4224137931034483, 'f1': 0.48275862068965514, 'number': 116}	{'precision': 0.906183368869936, 'recall': 0.9860788863109049, 'f1': 0.9444444444444443, 'number': 431}	{'precision': 0.7435897435897436, 'recall': 0.8529411764705882, 'f1': 0.7945205479452054, 'number': 34}	{'precision': 0.8968421052631579, 'recall': 0.8729508196721312, 'f1': 0.8847352024922119, 'number': 488}	{'precision': 0.7906976744186046, 'recall': 0.918918918918919, 'f1': 0.85, 'number': 37}	{'precision': 0.6862745098039216, 'recall': 0.8974358974358975, 'f1': 0.7777777777777778, 'number': 39}	{'precision': 0.5967741935483871, 'recall': 0.9736842105263158, 'f1': 0.74, 'number': 38}	{'precision': 0.729957805907173, 'recall': 0.8522167487684729, 'f1': 0.7863636363636363, 'number': 203}	{'precision': 0.8322211630123928, 'recall': 0.9943052391799544, 'f1': 0.9060716139076284, 'number': 878}	{'precision': 0.8140495867768595, 'recall': 0.8454935622317596, 'f1': 0.8294736842105264, 'number': 233}	{'precision': 0.46296296296296297, 'recall': 0.5813953488372093, 'f1': 0.5154639175257731, 'number': 43}	{'precision': 0.7121212121212122, 'recall': 0.618421052631579, 'f1': 0.6619718309859155, 'number': 76}	0.8177	0.8983	0.8561	0.9389
0.1006	3.0	1050	0.2243	{'precision': 0.5816326530612245, 'recall': 0.49137931034482757, 'f1': 0.5327102803738317, 'number': 116}	{'precision': 0.9363636363636364, 'recall': 0.9559164733178654, 'f1': 0.9460390355912743, 'number': 431}	{'precision': 0.8181818181818182, 'recall': 0.5294117647058824, 'f1': 0.6428571428571428, 'number': 34}	{'precision': 0.9173728813559322, 'recall': 0.8872950819672131, 'f1': 0.9020833333333333, 'number': 488}	{'precision': 0.875, 'recall': 0.9459459459459459, 'f1': 0.9090909090909091, 'number': 37}	{'precision': 0.7916666666666666, 'recall': 0.9743589743589743, 'f1': 0.8735632183908045, 'number': 39}	{'precision': 0.6341463414634146, 'recall': 0.6842105263157895, 'f1': 0.6582278481012659, 'number': 38}	{'precision': 0.8404255319148937, 'recall': 0.7783251231527094, 'f1': 0.8081841432225063, 'number': 203}	{'precision': 0.8924508790072389, 'recall': 0.9829157175398633, 'f1': 0.9355013550135501, 'number': 878}	{'precision': 0.9210526315789473, 'recall': 0.7510729613733905, 'f1': 0.8274231678486997, 'number': 233}	{'precision': 0.4117647058823529, 'recall': 0.4883720930232558, 'f1': 0.44680851063829785, 'number': 43}	{'precision': 0.5555555555555556, 'recall': 0.6578947368421053, 'f1': 0.6024096385542169, 'number': 76}	0.8636	0.8739	0.8687	0.9433
0.1006	4.0	1400	0.2313	{'precision': 0.5797101449275363, 'recall': 0.3448275862068966, 'f1': 0.43243243243243246, 'number': 116}	{'precision': 0.9118942731277533, 'recall': 0.9605568445475638, 'f1': 0.9355932203389831, 'number': 431}	{'precision': 0.775, 'recall': 0.9117647058823529, 'f1': 0.8378378378378379, 'number': 34}	{'precision': 0.8846918489065606, 'recall': 0.9118852459016393, 'f1': 0.8980827447023207, 'number': 488}	{'precision': 0.8, 'recall': 0.8648648648648649, 'f1': 0.8311688311688312, 'number': 37}	{'precision': 0.7755102040816326, 'recall': 0.9743589743589743, 'f1': 0.8636363636363635, 'number': 39}	{'precision': 0.6136363636363636, 'recall': 0.7105263157894737, 'f1': 0.6585365853658537, 'number': 38}	{'precision': 0.8645833333333334, 'recall': 0.8177339901477833, 'f1': 0.8405063291139241, 'number': 203}	{'precision': 0.906610703043022, 'recall': 0.9840546697038725, 'f1': 0.9437465865647188, 'number': 878}	{'precision': 0.79296875, 'recall': 0.871244635193133, 'f1': 0.8302658486707566, 'number': 233}	{'precision': 0.2647058823529412, 'recall': 0.4186046511627907, 'f1': 0.32432432432432434, 'number': 43}	{'precision': 0.7285714285714285, 'recall': 0.6710526315789473, 'f1': 0.6986301369863013, 'number': 76}	0.8506	0.8903	0.8700	0.9441
0.0625	5.0	1750	0.2365	{'precision': 0.6666666666666666, 'recall': 0.41379310344827586, 'f1': 0.5106382978723404, 'number': 116}	{'precision': 0.9356321839080459, 'recall': 0.9443155452436195, 'f1': 0.9399538106235567, 'number': 431}	{'precision': 0.7692307692307693, 'recall': 0.8823529411764706, 'f1': 0.8219178082191781, 'number': 34}	{'precision': 0.9157894736842105, 'recall': 0.8913934426229508, 'f1': 0.9034267912772587, 'number': 488}	{'precision': 0.868421052631579, 'recall': 0.8918918918918919, 'f1': 0.88, 'number': 37}	{'precision': 0.6481481481481481, 'recall': 0.8974358974358975, 'f1': 0.7526881720430108, 'number': 39}	{'precision': 0.5471698113207547, 'recall': 0.7631578947368421, 'f1': 0.6373626373626373, 'number': 38}	{'precision': 0.8055555555555556, 'recall': 0.8571428571428571, 'f1': 0.8305489260143198, 'number': 203}	{'precision': 0.9645308924485125, 'recall': 0.9601366742596811, 'f1': 0.9623287671232876, 'number': 878}	{'precision': 0.8122448979591836, 'recall': 0.8540772532188842, 'f1': 0.8326359832635983, 'number': 233}	{'precision': 0.4583333333333333, 'recall': 0.5116279069767442, 'f1': 0.4835164835164835, 'number': 43}	{'precision': 0.6538461538461539, 'recall': 0.6710526315789473, 'f1': 0.6623376623376623, 'number': 76}	0.8778	0.8815	0.8796	0.9475
0.0398	6.0	2100	0.2782	{'precision': 0.6057692307692307, 'recall': 0.5431034482758621, 'f1': 0.5727272727272726, 'number': 116}	{'precision': 0.9346846846846847, 'recall': 0.962877030162413, 'f1': 0.9485714285714286, 'number': 431}	{'precision': 0.7380952380952381, 'recall': 0.9117647058823529, 'f1': 0.8157894736842106, 'number': 34}	{'precision': 0.9022403258655805, 'recall': 0.9077868852459017, 'f1': 0.9050051072522983, 'number': 488}	{'precision': 0.8205128205128205, 'recall': 0.8648648648648649, 'f1': 0.8421052631578947, 'number': 37}	{'precision': 0.76, 'recall': 0.9743589743589743, 'f1': 0.853932584269663, 'number': 39}	{'precision': 0.5573770491803278, 'recall': 0.8947368421052632, 'f1': 0.686868686868687, 'number': 38}	{'precision': 0.8076923076923077, 'recall': 0.8275862068965517, 'f1': 0.8175182481751824, 'number': 203}	{'precision': 0.9393605292171996, 'recall': 0.9703872437357631, 'f1': 0.9546218487394957, 'number': 878}	{'precision': 0.7700729927007299, 'recall': 0.9055793991416309, 'f1': 0.8323471400394478, 'number': 233}	{'precision': 0.42857142857142855, 'recall': 0.5581395348837209, 'f1': 0.48484848484848486, 'number': 43}	{'precision': 0.7027027027027027, 'recall': 0.6842105263157895, 'f1': 0.6933333333333334, 'number': 76}	0.8593	0.9033	0.8807	0.9463
0.0398	7.0	2450	0.2983	{'precision': 0.6336633663366337, 'recall': 0.5517241379310345, 'f1': 0.5898617511520738, 'number': 116}	{'precision': 0.9242761692650334, 'recall': 0.962877030162413, 'f1': 0.9431818181818182, 'number': 431}	{'precision': 0.7560975609756098, 'recall': 0.9117647058823529, 'f1': 0.8266666666666665, 'number': 34}	{'precision': 0.9075975359342916, 'recall': 0.9057377049180327, 'f1': 0.9066666666666666, 'number': 488}	{'precision': 0.8, 'recall': 0.8648648648648649, 'f1': 0.8311688311688312, 'number': 37}	{'precision': 0.7755102040816326, 'recall': 0.9743589743589743, 'f1': 0.8636363636363635, 'number': 39}	{'precision': 0.5714285714285714, 'recall': 0.8421052631578947, 'f1': 0.6808510638297872, 'number': 38}	{'precision': 0.85, 'recall': 0.8374384236453202, 'f1': 0.8436724565756824, 'number': 203}	{'precision': 0.9316702819956616, 'recall': 0.9783599088838268, 'f1': 0.9544444444444444, 'number': 878}	{'precision': 0.7777777777777778, 'recall': 0.9012875536480687, 'f1': 0.8349900596421471, 'number': 233}	{'precision': 0.5681818181818182, 'recall': 0.5813953488372093, 'f1': 0.5747126436781609, 'number': 43}	{'precision': 0.6470588235294118, 'recall': 0.7236842105263158, 'f1': 0.6832298136645962, 'number': 76}	0.8648	0.9071	0.8854	0.9488
0.0232	8.0	2800	0.3239	{'precision': 0.652542372881356, 'recall': 0.6637931034482759, 'f1': 0.6581196581196582, 'number': 116}	{'precision': 0.9186813186813186, 'recall': 0.9698375870069605, 'f1': 0.943566591422122, 'number': 431}	{'precision': 0.7333333333333333, 'recall': 0.9705882352941176, 'f1': 0.8354430379746834, 'number': 34}	{'precision': 0.9014373716632443, 'recall': 0.8995901639344263, 'f1': 0.9005128205128204, 'number': 488}	{'precision': 0.8205128205128205, 'recall': 0.8648648648648649, 'f1': 0.8421052631578947, 'number': 37}	{'precision': 0.7755102040816326, 'recall': 0.9743589743589743, 'f1': 0.8636363636363635, 'number': 39}	{'precision': 0.6346153846153846, 'recall': 0.868421052631579, 'f1': 0.7333333333333333, 'number': 38}	{'precision': 0.8199052132701422, 'recall': 0.8522167487684729, 'f1': 0.8357487922705314, 'number': 203}	{'precision': 0.9163987138263665, 'recall': 0.9738041002277904, 'f1': 0.9442297073440088, 'number': 878}	{'precision': 0.8110236220472441, 'recall': 0.8841201716738197, 'f1': 0.8459958932238193, 'number': 233}	{'precision': 0.4262295081967213, 'recall': 0.6046511627906976, 'f1': 0.4999999999999999, 'number': 43}	{'precision': 0.6206896551724138, 'recall': 0.7105263157894737, 'f1': 0.6625766871165644, 'number': 76}	0.8542	0.9113	0.8818	0.9459
0.013	9.0	3150	0.3279	{'precision': 0.6363636363636364, 'recall': 0.603448275862069, 'f1': 0.6194690265486726, 'number': 116}	{'precision': 0.9321266968325792, 'recall': 0.9559164733178654, 'f1': 0.9438717067583048, 'number': 431}	{'precision': 0.7560975609756098, 'recall': 0.9117647058823529, 'f1': 0.8266666666666665, 'number': 34}	{'precision': 0.9049586776859504, 'recall': 0.8975409836065574, 'f1': 0.9012345679012345, 'number': 488}	{'precision': 0.8205128205128205, 'recall': 0.8648648648648649, 'f1': 0.8421052631578947, 'number': 37}	{'precision': 0.7307692307692307, 'recall': 0.9743589743589743, 'f1': 0.8351648351648352, 'number': 39}	{'precision': 0.6444444444444445, 'recall': 0.7631578947368421, 'f1': 0.6987951807228916, 'number': 38}	{'precision': 0.837696335078534, 'recall': 0.7881773399014779, 'f1': 0.8121827411167513, 'number': 203}	{'precision': 0.9482564679415073, 'recall': 0.9601366742596811, 'f1': 0.9541595925297114, 'number': 878}	{'precision': 0.8204081632653061, 'recall': 0.8626609442060086, 'f1': 0.8410041841004183, 'number': 233}	{'precision': 0.5098039215686274, 'recall': 0.6046511627906976, 'f1': 0.553191489361702, 'number': 43}	{'precision': 0.675, 'recall': 0.7105263157894737, 'f1': 0.6923076923076923, 'number': 76}	0.8745	0.8922	0.8833	0.9483
0.0078	10.0	3500	0.3298	{'precision': 0.6448598130841121, 'recall': 0.5948275862068966, 'f1': 0.6188340807174888, 'number': 116}	{'precision': 0.9324324324324325, 'recall': 0.9605568445475638, 'f1': 0.9462857142857144, 'number': 431}	{'precision': 0.7380952380952381, 'recall': 0.9117647058823529, 'f1': 0.8157894736842106, 'number': 34}	{'precision': 0.906054279749478, 'recall': 0.889344262295082, 'f1': 0.8976215098241986, 'number': 488}	{'precision': 0.8421052631578947, 'recall': 0.8648648648648649, 'f1': 0.8533333333333334, 'number': 37}	{'precision': 0.6851851851851852, 'recall': 0.9487179487179487, 'f1': 0.7956989247311828, 'number': 39}	{'precision': 0.6382978723404256, 'recall': 0.7894736842105263, 'f1': 0.7058823529411764, 'number': 38}	{'precision': 0.8631578947368421, 'recall': 0.8078817733990148, 'f1': 0.8346055979643766, 'number': 203}	{'precision': 0.9299781181619255, 'recall': 0.9681093394077449, 'f1': 0.9486607142857143, 'number': 878}	{'precision': 0.8211382113821138, 'recall': 0.8669527896995708, 'f1': 0.8434237995824635, 'number': 233}	{'precision': 0.52, 'recall': 0.6046511627906976, 'f1': 0.5591397849462365, 'number': 43}	{'precision': 0.6626506024096386, 'recall': 0.7236842105263158, 'f1': 0.6918238993710693, 'number': 76}	0.8701	0.8960	0.8829	0.9480

Framework versions

Transformers 4.44.0
Pytorch 2.3.1+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Type: xlm-roberta
Created: Sep 24, 2024
Updated: Sep 24, 2024