Linguistic Acceptability on CoLA

Metric: Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	Accuracy▼	Extra Data	Paper	Date↕	Code
1	LTG-BERT-base 98M	82.7	No	Not all layers are equally as important: Every L...	2023-11-03	-
2	ELC-BERT-base 98M	82.6	No	Not all layers are equally as important: Every L...	2023-11-03	-
3	LTG-BERT-small 24M	77.6	No	Not all layers are equally as important: Every L...	2023-11-03	-
4	ELC-BERT-small 24M	76.1	No	Not all layers are equally as important: Every L...	2023-11-03	-
5	PSQ (Chen et al., 2020)	67.5	No	A Statistical Framework for Low-bitwidth Trainin...	2020-10-27	Code
6	Q-BERT (Shen et al., 2020)	65.1	No	Q-BERT: Hessian Based Ultra Low Precision Quanti...	2019-09-12	-
7	Q8BERT (Zafrir et al., 2019)	65	No	Q8BERT: Quantized 8Bit BERT	2019-10-14	Code
8	24hBERT	57.1	No	How to Train BERT with an Academic Budget	2021-04-15	Code

#1LTG-BERT-base 98MSOTA
82.7
Accuracy· 2023-11-03
Not all layers are equally as important: Every Layer Counts BERT
#2ELC-BERT-base 98M
82.6
Accuracy· 2023-11-03
Not all layers are equally as important: Every Layer Counts BERT
#3LTG-BERT-small 24M
77.6
Accuracy· 2023-11-03
Not all layers are equally as important: Every Layer Counts BERT
#4ELC-BERT-small 24M
76.1
Accuracy· 2023-11-03
Not all layers are equally as important: Every Layer Counts BERT
#5PSQ (Chen et al., 2020)SOTA
67.5
Accuracy· 2020-10-27
A Statistical Framework for Low-bitwidth Training of Deep Neural Networks Code
#6Q-BERT (Shen et al., 2020)SOTA
65.1
Accuracy· 2019-09-12
Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT
#7Q8BERT (Zafrir et al., 2019)
65
Accuracy· 2019-10-14
Q8BERT: Quantized 8Bit BERT Code
#824hBERT
57.1
Accuracy· 2021-04-15
How to Train BERT with an Academic Budget Code