anliR2-bert-base-uncased-alum

asun17904/anliR2-bert-base-uncased-alum

anliR2-bert-base-uncased-alum 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 30, 2024

Repo size

3.9 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 29, 2024
Updated: Jan 30, 2024
SHA: 4345ae21

Model card

From the Hugging Face model README

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
1.117	0.391	1.0
1.106	0.418	2.0
1.093	0.434	3.0
1.072	0.464	4.0
1.098	0.434	5.0
1.084	0.453	6.0
1.088	0.447	7.0
1.080	0.459	8.0
1.099	0.440	9.0
1.075	0.468	10.0
1.078	0.460	11.0
1.079	0.465	12.0
1.082	0.463	13.0
1.091	0.449	14.0
1.082	0.458	15.0
1.086	0.456	16.0
1.089	0.450	17.0
1.082	0.467	18.0

Library: pytorch
License: mit
Languages: en
Created: Jan 29, 2024
Updated: Jan 30, 2024