MAE

Circularmachines/MAE

MAE is a machine learning model from Circularmachines. 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 transformers. The card lists the license as apache-2.0.

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

Downloads · 30 days

3% of all-time downloads

All-time downloads

306

Public

Repo size

5.4 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin448 MB · 99%

At a glance

Library: transformers
License: apache-2.0
Model type: vit_mae
Access: Public
Created: May 9, 2023
Updated: May 9, 2023
SHA: 550eae80

Model card

From the Hugging Face model README

MAE

This model is a fine-tuned version of facebook/vit-mae-base on the Circularmachines/batch_indexing_machine_224x224_images dataset. It achieves the following results on the evaluation set:

Loss: 0.2263

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: 4.6875e-06
train_batch_size: 8
eval_batch_size: 8
seed: 1337
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.249	1.0	7705	0.2445
0.2269	2.0	15410	0.2373
0.2401	3.0	23115	0.2334
0.2202	4.0	30820	0.2305
0.2173	5.0	38525	0.2283
0.2347	6.0	46230	0.2282
0.2304	7.0	53935	0.2268
0.2267	8.0	61640	0.2262
0.2177	9.0	69345	0.2254
0.2175	10.0	77050	0.2262

Framework versions

Transformers 4.29.0.dev0
Pytorch 2.0.0+cu118
Datasets 2.12.0
Tokenizers 0.13.3

Library: transformers
Type: vit_mae
License: apache-2.0
Created: May 9, 2023
Updated: May 9, 2023