anliR3-bert-base-uncased-alum – AI Model by asun17904 | AlphaNeural AI

You can deploy this model and start earning money today!

asun17904/
anliR3-bert-base-uncased-alum

like

0

Views

No views yet

Knowledge Continuity Regularized Network

Dataset: ANLI Round: None

Trainer Hyperparameters:

lr = 5e-05
per_device_batch_size = 16
gradient_accumulation_steps = 1
weight_decay = 1e-09
seed = 42

Regularization Hyperparameters

numerical stability denominator constant = 1.0
lambda = 1.0
alpha = 1.0
beta = 1.0

Extended Logs:

eval_loss	eval_accuracy	epoch
1.096	0.427	1.0
1.090	0.432	2.0
1.077	0.455	3.0
1.087	0.443	4.0
1.082	0.453	5.0
1.085	0.444	6.0
1.082	0.448	7.0
1.084	0.446	8.0
1.088	0.448	9.0
1.091	0.444	10.0
1.089	0.455	11.0
1.084	0.461	12.0
1.082	0.458	13.0
1.080	0.461	14.0
1.080	0.461	15.0
1.081	0.454	16.0
1.078	0.463	17.0
1.078	0.461	18.0
1.076	0.469	19.0

Test Accuracy: 0.463