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

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

roberta-large-ner-ghtk-cs-6-label-new-data-3090-6Sep-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. The card lists the license as mit.

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

Downloads · 30 days

6% 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

License: mit
Model type: xlm-roberta
Access: Public
Created: Sep 6, 2024
Updated: Sep 6, 2024
SHA: 20f922a6

Base models

FacebookAI/xlm-roberta-large

Model card

From the Hugging Face model README

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

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: 0.1725
Tk: {'precision': 0.8651685393258427, 'recall': 0.6637931034482759, 'f1': 0.751219512195122, 'number': 116}
Gày: {'precision': 0.75, 'recall': 0.8823529411764706, 'f1': 0.8108108108108107, 'number': 34}
Gày trừu tượng: {'precision': 0.9111111111111111, 'recall': 0.9241803278688525, 'f1': 0.9175991861648015, 'number': 488}
Ã đơn: {'precision': 0.8958333333333334, 'recall': 0.8472906403940886, 'f1': 0.8708860759493672, 'number': 203}
Đt: {'precision': 0.9220917822838848, 'recall': 0.9840546697038725, 'f1': 0.9520661157024795, 'number': 878}
Đt trừu tượng: {'precision': 0.8170731707317073, 'recall': 0.8626609442060086, 'f1': 0.8392484342379958, 'number': 233}
Overall Precision: 0.8979
Overall Recall: 0.9196
Overall F1: 0.9086
Overall Accuracy: 0.9685

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	467	0.1594	{'precision': 0.75, 'recall': 0.07758620689655173, 'f1': 0.14062500000000003, 'number': 116}	{'precision': 0.30120481927710846, 'recall': 0.7352941176470589, 'f1': 0.4273504273504274, 'number': 34}	{'precision': 0.8500986193293886, 'recall': 0.8831967213114754, 'f1': 0.8663316582914573, 'number': 488}	{'precision': 0.777292576419214, 'recall': 0.8768472906403941, 'f1': 0.8240740740740742, 'number': 203}	{'precision': 0.8541666666666666, 'recall': 0.9806378132118451, 'f1': 0.9130434782608696, 'number': 878}	{'precision': 0.755868544600939, 'recall': 0.6909871244635193, 'f1': 0.7219730941704036, 'number': 233}	0.8114	0.8530	0.8317	0.9466
0.2588	2.0	934	0.1616	{'precision': 0.578125, 'recall': 0.31896551724137934, 'f1': 0.41111111111111115, 'number': 116}	{'precision': 0.5918367346938775, 'recall': 0.8529411764705882, 'f1': 0.6987951807228915, 'number': 34}	{'precision': 0.8096947935368043, 'recall': 0.9241803278688525, 'f1': 0.8631578947368421, 'number': 488}	{'precision': 0.9083969465648855, 'recall': 0.5862068965517241, 'f1': 0.7125748502994012, 'number': 203}	{'precision': 0.8858307849133538, 'recall': 0.989749430523918, 'f1': 0.9349112426035503, 'number': 878}	{'precision': 0.5903614457831325, 'recall': 0.8412017167381974, 'f1': 0.6938053097345134, 'number': 233}	0.8046	0.8714	0.8367	0.9465
0.1107	3.0	1401	0.1661	{'precision': 0.8070175438596491, 'recall': 0.7931034482758621, 'f1': 0.8, 'number': 116}	{'precision': 0.5370370370370371, 'recall': 0.8529411764705882, 'f1': 0.6590909090909091, 'number': 34}	{'precision': 0.8352272727272727, 'recall': 0.9036885245901639, 'f1': 0.8681102362204726, 'number': 488}	{'precision': 0.9352941176470588, 'recall': 0.7832512315270936, 'f1': 0.8525469168900804, 'number': 203}	{'precision': 0.9374325782092773, 'recall': 0.989749430523918, 'f1': 0.9628808864265929, 'number': 878}	{'precision': 0.6057692307692307, 'recall': 0.8111587982832618, 'f1': 0.6935779816513762, 'number': 233}	0.8451	0.9114	0.8770	0.9562
0.0835	4.0	1868	0.1308	{'precision': 0.8243243243243243, 'recall': 0.5258620689655172, 'f1': 0.6421052631578947, 'number': 116}	{'precision': 0.7741935483870968, 'recall': 0.7058823529411765, 'f1': 0.7384615384615385, 'number': 34}	{'precision': 0.8868686868686869, 'recall': 0.8995901639344263, 'f1': 0.8931841302136317, 'number': 488}	{'precision': 0.8695652173913043, 'recall': 0.7881773399014779, 'f1': 0.82687338501292, 'number': 203}	{'precision': 0.9097586568730325, 'recall': 0.9874715261958997, 'f1': 0.947023484434735, 'number': 878}	{'precision': 0.684931506849315, 'recall': 0.8583690987124464, 'f1': 0.7619047619047619, 'number': 233}	0.8630	0.8970	0.8797	0.9594
0.0594	5.0	2335	0.1368	{'precision': 0.6888888888888889, 'recall': 0.8017241379310345, 'f1': 0.7410358565737052, 'number': 116}	{'precision': 0.75, 'recall': 0.7058823529411765, 'f1': 0.7272727272727272, 'number': 34}	{'precision': 0.9032258064516129, 'recall': 0.9180327868852459, 'f1': 0.9105691056910569, 'number': 488}	{'precision': 0.9090909090909091, 'recall': 0.7881773399014779, 'f1': 0.8443271767810027, 'number': 203}	{'precision': 0.935659760087241, 'recall': 0.9772209567198178, 'f1': 0.9559888579387186, 'number': 878}	{'precision': 0.7751937984496124, 'recall': 0.8583690987124464, 'f1': 0.814663951120163, 'number': 233}	0.8853	0.9134	0.8991	0.9647
0.044	6.0	2802	0.1338	{'precision': 0.9333333333333333, 'recall': 0.603448275862069, 'f1': 0.7329842931937173, 'number': 116}	{'precision': 0.6744186046511628, 'recall': 0.8529411764705882, 'f1': 0.7532467532467532, 'number': 34}	{'precision': 0.9276595744680851, 'recall': 0.8934426229508197, 'f1': 0.9102296450939458, 'number': 488}	{'precision': 0.875, 'recall': 0.8275862068965517, 'f1': 0.8506329113924052, 'number': 203}	{'precision': 0.924468085106383, 'recall': 0.989749430523918, 'f1': 0.955995599559956, 'number': 878}	{'precision': 0.7807692307692308, 'recall': 0.871244635193133, 'f1': 0.8235294117647058, 'number': 233}	0.8965	0.9093	0.9028	0.9658
0.0264	7.0	3269	0.1551	{'precision': 0.7857142857142857, 'recall': 0.6637931034482759, 'f1': 0.719626168224299, 'number': 116}	{'precision': 0.6041666666666666, 'recall': 0.8529411764705882, 'f1': 0.7073170731707317, 'number': 34}	{'precision': 0.888015717092338, 'recall': 0.9262295081967213, 'f1': 0.9067201604814443, 'number': 488}	{'precision': 0.848780487804878, 'recall': 0.8571428571428571, 'f1': 0.8529411764705881, 'number': 203}	{'precision': 0.924468085106383, 'recall': 0.989749430523918, 'f1': 0.955995599559956, 'number': 878}	{'precision': 0.8253275109170306, 'recall': 0.8111587982832618, 'f1': 0.8181818181818181, 'number': 233}	0.8822	0.9170	0.8993	0.9641
0.02	8.0	3736	0.1654	{'precision': 0.9240506329113924, 'recall': 0.6293103448275862, 'f1': 0.7487179487179487, 'number': 116}	{'precision': 0.7142857142857143, 'recall': 0.8823529411764706, 'f1': 0.7894736842105262, 'number': 34}	{'precision': 0.9001996007984032, 'recall': 0.9241803278688525, 'f1': 0.9120323559150658, 'number': 488}	{'precision': 0.9, 'recall': 0.8423645320197044, 'f1': 0.8702290076335878, 'number': 203}	{'precision': 0.9234913793103449, 'recall': 0.9760820045558086, 'f1': 0.9490586932447398, 'number': 878}	{'precision': 0.8031496062992126, 'recall': 0.8755364806866953, 'f1': 0.837782340862423, 'number': 233}	0.8957	0.9150	0.9052	0.9676
0.0107	9.0	4203	0.1804	{'precision': 0.8390804597701149, 'recall': 0.6293103448275862, 'f1': 0.7192118226600984, 'number': 116}	{'precision': 0.725, 'recall': 0.8529411764705882, 'f1': 0.7837837837837837, 'number': 34}	{'precision': 0.907258064516129, 'recall': 0.9221311475409836, 'f1': 0.9146341463414632, 'number': 488}	{'precision': 0.8693467336683417, 'recall': 0.8522167487684729, 'f1': 0.8606965174129352, 'number': 203}	{'precision': 0.917558886509636, 'recall': 0.9760820045558086, 'f1': 0.945916114790287, 'number': 878}	{'precision': 0.8355555555555556, 'recall': 0.8068669527896996, 'f1': 0.8209606986899564, 'number': 233}	0.8935	0.9068	0.9001	0.9661
0.009	10.0	4670	0.1725	{'precision': 0.8651685393258427, 'recall': 0.6637931034482759, 'f1': 0.751219512195122, 'number': 116}	{'precision': 0.75, 'recall': 0.8823529411764706, 'f1': 0.8108108108108107, 'number': 34}	{'precision': 0.9111111111111111, 'recall': 0.9241803278688525, 'f1': 0.9175991861648015, 'number': 488}	{'precision': 0.8958333333333334, 'recall': 0.8472906403940886, 'f1': 0.8708860759493672, 'number': 203}	{'precision': 0.9220917822838848, 'recall': 0.9840546697038725, 'f1': 0.9520661157024795, 'number': 878}	{'precision': 0.8170731707317073, 'recall': 0.8626609442060086, 'f1': 0.8392484342379958, 'number': 233}	0.8979	0.9196	0.9086	0.9685

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: Sep 6, 2024
Updated: Sep 6, 2024