glue-cola-bert-base-uncased-regularized-l2

asun17904/glue-cola-bert-base-uncased-regularized-l2

glue-cola-bert-base-uncased-regularized-l2 is a machine learning model from asun17904. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as mit.

Downloads · 30 days

Access

Public

Updated Jan 24, 2024

Repo size

1.3 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin438 MB · 100%

At a glance

Library: pytorch
License: mit
Access: Public
Created: Jan 24, 2024
Updated: Jan 24, 2024
SHA: f192dda8

Model card

From the Hugging Face model README

Knowledge Continuity Regularized Network

Dataset: GLUE

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 = 0.01
lambda = 0.02
alpha = 2.0
beta = 1.0

Extended Logs:

eval_loss	eval_accuracy	epoch
16.556	0.800	1.0
16.658	0.794	2.0
16.329	0.804	3.0
16.252	0.816	4.0
16.386	0.808	5.0
16.747	0.802	6.0
16.614	0.807	7.0
16.641	0.808	8.0
16.362	0.814	9.0
16.559	0.805	10.0
16.639	0.802	11.0
16.819	0.796	12.0
16.648	0.803	13.0
17.400	0.780	14.0
16.121	0.818	15.0
16.481	0.808	16.0
16.644	0.801	17.0
16.747	0.806	18.0
16.386	0.808	19.0
16.684	0.802	20.0
16.766	0.803	21.0
16.543	0.803	22.0
16.636	0.803	23.0
16.468	0.813	24.0
16.653	0.800	25.0
17.070	0.788	26.0
17.067	0.796	27.0
16.857	0.796	28.0
16.925	0.795	29.0
16.890	0.798	30.0
16.594	0.801	31.0
16.578	0.800	32.0
16.517	0.802	33.0
16.529	0.802	34.0
16.674	0.803	35.0
16.543	0.809	36.0
16.659	0.803	37.0
16.723	0.803	38.0
16.480	0.808	39.0
16.410	0.804	40.0
16.641	0.803	41.0
16.328	0.811	42.0
16.270	0.813	43.0
16.291	0.812	44.0
16.522	0.812	45.0
16.395	0.810	46.0
16.385	0.811	47.0
16.392	0.812	48.0
16.401	0.811	49.0

Library: pytorch
License: mit
Languages: en
Created: Jan 24, 2024
Updated: Jan 24, 2024