roberta-large-ner-ghtk-cs-6-labelold-data-3090-12Aug-2

Kudod/roberta-large-ner-ghtk-cs-6-labelold-data-3090-12Aug-2

roberta-large-ner-ghtk-cs-6-labelold-data-3090-12Aug-2 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. The card lists the license as mit.

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

Downloads · 30 days

31% of all-time downloads

All-time downloads

Public

Parameters

559M

11.2 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors2.2 GB · 99%

At a glance

License: mit
Model type: xlm-roberta
Access: Public
Created: Aug 12, 2024
Updated: Aug 12, 2024
SHA: f9dab6b4

Base models

FacebookAI/xlm-roberta-large

Model card

From the Hugging Face model README

roberta-large-ner-ghtk-cs-6-labelold-data-3090-12Aug-2

This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1987
Tk: {'precision': 0.9069767441860465, 'recall': 0.6724137931034483, 'f1': 0.7722772277227723, 'number': 116}
Gày: {'precision': 0.6578947368421053, 'recall': 0.7575757575757576, 'f1': 0.704225352112676, 'number': 33}
Gày trừu tượng: {'precision': 0.9209401709401709, 'recall': 0.9229122055674518, 'f1': 0.9219251336898395, 'number': 467}
Ã đơn: {'precision': 0.9128205128205128, 'recall': 0.8944723618090452, 'f1': 0.9035532994923858, 'number': 199}
Đt: {'precision': 0.9442013129102844, 'recall': 0.9829157175398633, 'f1': 0.9631696428571428, 'number': 878}
Đt trừu tượng: {'precision': 0.8095238095238095, 'recall': 0.8738317757009346, 'f1': 0.8404494382022472, 'number': 214}
Overall Precision: 0.9120
Overall Recall: 0.9240
Overall F1: 0.9179
Overall Accuracy: 0.9709

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	Gày	Gày trừu tượng	Ã đơn	Đt	Đt trừu tượng	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
No log	1.0	454	0.1742	{'precision': 0.375, 'recall': 0.05172413793103448, 'f1': 0.09090909090909091, 'number': 116}	{'precision': 0.5306122448979592, 'recall': 0.7878787878787878, 'f1': 0.6341463414634148, 'number': 33}	{'precision': 0.8404040404040404, 'recall': 0.8907922912205567, 'f1': 0.8648648648648648, 'number': 467}	{'precision': 0.7699530516431925, 'recall': 0.8241206030150754, 'f1': 0.7961165048543689, 'number': 199}	{'precision': 0.8424124513618677, 'recall': 0.9863325740318907, 'f1': 0.9087093389296957, 'number': 878}	{'precision': 0.6772908366533864, 'recall': 0.794392523364486, 'f1': 0.7311827956989246, 'number': 214}	0.8031	0.8642	0.8325	0.9353
0.2313	2.0	908	0.1278	{'precision': 0.8041237113402062, 'recall': 0.6724137931034483, 'f1': 0.7323943661971831, 'number': 116}	{'precision': 0.6756756756756757, 'recall': 0.7575757575757576, 'f1': 0.7142857142857142, 'number': 33}	{'precision': 0.9311926605504587, 'recall': 0.8693790149892934, 'f1': 0.8992248062015504, 'number': 467}	{'precision': 0.7951219512195122, 'recall': 0.8190954773869347, 'f1': 0.806930693069307, 'number': 199}	{'precision': 0.9318423855165069, 'recall': 0.9965831435079726, 'f1': 0.9631260319207484, 'number': 878}	{'precision': 0.8357142857142857, 'recall': 0.5467289719626168, 'f1': 0.6610169491525424, 'number': 214}	0.8975	0.8726	0.8849	0.9611
0.0909	3.0	1362	0.1366	{'precision': 0.8252427184466019, 'recall': 0.7327586206896551, 'f1': 0.776255707762557, 'number': 116}	{'precision': 0.5849056603773585, 'recall': 0.9393939393939394, 'f1': 0.7209302325581395, 'number': 33}	{'precision': 0.8685831622176592, 'recall': 0.9057815845824411, 'f1': 0.8867924528301887, 'number': 467}	{'precision': 0.7647058823529411, 'recall': 0.914572864321608, 'f1': 0.8329519450800914, 'number': 199}	{'precision': 0.9497267759562842, 'recall': 0.989749430523918, 'f1': 0.9693251533742331, 'number': 878}	{'precision': 0.7630331753554502, 'recall': 0.7523364485981309, 'f1': 0.7576470588235295, 'number': 214}	0.8724	0.9182	0.8947	0.9583
0.0644	4.0	1816	0.1713	{'precision': 0.8133333333333334, 'recall': 0.5258620689655172, 'f1': 0.6387434554973822, 'number': 116}	{'precision': 0.7352941176470589, 'recall': 0.7575757575757576, 'f1': 0.746268656716418, 'number': 33}	{'precision': 0.8678861788617886, 'recall': 0.9143468950749465, 'f1': 0.8905109489051095, 'number': 467}	{'precision': 0.9269662921348315, 'recall': 0.8291457286432161, 'f1': 0.8753315649867375, 'number': 199}	{'precision': 0.9242105263157895, 'recall': 1.0, 'f1': 0.9606126914660831, 'number': 878}	{'precision': 0.48931116389548696, 'recall': 0.9626168224299065, 'f1': 0.6488188976377952, 'number': 214}	0.8195	0.9240	0.8686	0.9586
0.0486	5.0	2270	0.1590	{'precision': 0.8494623655913979, 'recall': 0.6810344827586207, 'f1': 0.7559808612440192, 'number': 116}	{'precision': 0.71875, 'recall': 0.696969696969697, 'f1': 0.7076923076923077, 'number': 33}	{'precision': 0.933184855233853, 'recall': 0.8972162740899358, 'f1': 0.9148471615720524, 'number': 467}	{'precision': 0.8578431372549019, 'recall': 0.8793969849246231, 'f1': 0.8684863523573201, 'number': 199}	{'precision': 0.9474260679079957, 'recall': 0.9851936218678815, 'f1': 0.9659408151870463, 'number': 878}	{'precision': 0.6931818181818182, 'recall': 0.8551401869158879, 'f1': 0.7656903765690377, 'number': 214}	0.8921	0.9145	0.9032	0.9642
0.0319	6.0	2724	0.1608	{'precision': 0.8514851485148515, 'recall': 0.7413793103448276, 'f1': 0.792626728110599, 'number': 116}	{'precision': 0.6666666666666666, 'recall': 0.7272727272727273, 'f1': 0.6956521739130435, 'number': 33}	{'precision': 0.9069767441860465, 'recall': 0.9186295503211992, 'f1': 0.9127659574468084, 'number': 467}	{'precision': 0.9297297297297298, 'recall': 0.864321608040201, 'f1': 0.8958333333333334, 'number': 199}	{'precision': 0.9473684210526315, 'recall': 0.9840546697038725, 'f1': 0.9653631284916201, 'number': 878}	{'precision': 0.8936170212765957, 'recall': 0.7850467289719626, 'f1': 0.8358208955223881, 'number': 214}	0.9198	0.9140	0.9169	0.9696
0.0214	7.0	3178	0.1753	{'precision': 0.8181818181818182, 'recall': 0.6206896551724138, 'f1': 0.7058823529411765, 'number': 116}	{'precision': 0.65, 'recall': 0.7878787878787878, 'f1': 0.7123287671232875, 'number': 33}	{'precision': 0.9232456140350878, 'recall': 0.9014989293361885, 'f1': 0.9122426868905742, 'number': 467}	{'precision': 0.895, 'recall': 0.8994974874371859, 'f1': 0.8972431077694235, 'number': 199}	{'precision': 0.9288025889967637, 'recall': 0.9806378132118451, 'f1': 0.954016620498615, 'number': 878}	{'precision': 0.8070175438596491, 'recall': 0.8598130841121495, 'f1': 0.832579185520362, 'number': 214}	0.8989	0.9140	0.9064	0.9687
0.0147	8.0	3632	0.1762	{'precision': 0.8817204301075269, 'recall': 0.7068965517241379, 'f1': 0.7846889952153109, 'number': 116}	{'precision': 0.6578947368421053, 'recall': 0.7575757575757576, 'f1': 0.704225352112676, 'number': 33}	{'precision': 0.9189765458422174, 'recall': 0.9229122055674518, 'f1': 0.920940170940171, 'number': 467}	{'precision': 0.8254716981132075, 'recall': 0.8793969849246231, 'f1': 0.8515815085158152, 'number': 199}	{'precision': 0.9372294372294372, 'recall': 0.9863325740318907, 'f1': 0.9611542730299667, 'number': 878}	{'precision': 0.8181818181818182, 'recall': 0.883177570093458, 'f1': 0.849438202247191, 'number': 214}	0.8988	0.9271	0.9128	0.9674
0.0096	9.0	4086	0.1923	{'precision': 0.9102564102564102, 'recall': 0.6120689655172413, 'f1': 0.7319587628865979, 'number': 116}	{'precision': 0.6756756756756757, 'recall': 0.7575757575757576, 'f1': 0.7142857142857142, 'number': 33}	{'precision': 0.9129511677282378, 'recall': 0.9207708779443254, 'f1': 0.9168443496801706, 'number': 467}	{'precision': 0.9132653061224489, 'recall': 0.8994974874371859, 'f1': 0.9063291139240507, 'number': 199}	{'precision': 0.9370932754880694, 'recall': 0.9840546697038725, 'f1': 0.96, 'number': 878}	{'precision': 0.85, 'recall': 0.8738317757009346, 'f1': 0.8617511520737327, 'number': 214}	0.9127	0.9208	0.9167	0.9722
0.0053	10.0	4540	0.1987	{'precision': 0.9069767441860465, 'recall': 0.6724137931034483, 'f1': 0.7722772277227723, 'number': 116}	{'precision': 0.6578947368421053, 'recall': 0.7575757575757576, 'f1': 0.704225352112676, 'number': 33}	{'precision': 0.9209401709401709, 'recall': 0.9229122055674518, 'f1': 0.9219251336898395, 'number': 467}	{'precision': 0.9128205128205128, 'recall': 0.8944723618090452, 'f1': 0.9035532994923858, 'number': 199}	{'precision': 0.9442013129102844, 'recall': 0.9829157175398633, 'f1': 0.9631696428571428, 'number': 878}	{'precision': 0.8095238095238095, 'recall': 0.8738317757009346, 'f1': 0.8404494382022472, 'number': 214}	0.9120	0.9240	0.9179	0.9709

Framework versions

Transformers 4.44.0
Pytorch 2.3.1+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Type: xlm-roberta
License: mit
Created: Aug 12, 2024
Updated: Aug 12, 2024