videomae-base-finetuned-isl-numbers_2

latif98/videomae-base-finetuned-isl-numbers_2

videomae-base-finetuned-isl-numbers_2 is a video classification model from latif98. Use it for the video classification 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 cc-by-nc-4.0.

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

Downloads · 30 days

6% of all-time downloads

All-time downloads

283

Public

Parameters

86.3M

17.3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors345 MB · 100%

At a glance

Task: Video Classification
Library: transformers
License: cc-by-nc-4.0
Model type: videomae
Access: Public
Created: Apr 21, 2024
Updated: Apr 22, 2024
SHA: a34d1b0b

Base models

latif98/videomae-base-finetuned-isl-numbers

Spaces

Model card

From the Hugging Face model README

videomae-base-finetuned-isl-numbers_2

This model is a fine-tuned version of latif98/videomae-base-finetuned-isl-numbers on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.2759
Accuracy: 0.6839

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: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
training_steps: 3800

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.5502	0.02	76	3.4251	0.0945
3.1152	1.02	152	3.0364	0.2756
2.6365	2.02	228	2.6197	0.3780
2.3879	3.02	304	2.1519	0.4646
1.9396	4.02	380	2.0804	0.4173
1.9285	5.02	456	1.9335	0.4488
1.5843	6.02	532	1.7907	0.4803
1.2387	7.02	608	1.8962	0.3858
1.2578	8.02	684	1.7191	0.4488
0.9611	9.02	760	1.7362	0.4882
0.9247	10.02	836	1.3898	0.5906
0.8107	11.02	912	1.9588	0.4094
0.7618	12.02	988	1.1416	0.6614
0.7083	13.02	1064	1.2812	0.6614
0.7098	14.02	1140	1.4601	0.5197
0.4601	15.02	1216	1.1276	0.6693
0.5684	16.02	1292	1.4792	0.5591
0.5044	17.02	1368	1.1236	0.6614
0.4551	18.02	1444	1.3894	0.6063
0.3488	19.02	1520	1.2918	0.6614
0.4711	20.02	1596	1.2510	0.6299
0.3451	21.02	1672	1.1265	0.6693
0.394	22.02	1748	1.1676	0.6378
0.234	23.02	1824	1.0714	0.7087
0.2318	24.02	1900	1.2647	0.6378
0.4294	25.02	1976	1.0250	0.7480
0.2084	26.02	2052	1.1361	0.6850
0.1724	27.02	2128	0.8791	0.7402
0.1715	28.02	2204	0.7549	0.7559
0.2719	29.02	2280	0.7708	0.7717
0.2021	30.02	2356	1.1394	0.7165
0.0999	31.02	2432	0.7838	0.7717
0.1473	32.02	2508	1.3809	0.6457
0.0939	33.02	2584	0.7839	0.7874
0.0952	34.02	2660	1.0636	0.7008
0.2684	35.02	2736	0.9194	0.7323
0.1628	36.02	2812	0.7346	0.8031
0.0584	37.02	2888	1.0112	0.7323
0.0567	38.02	2964	1.0584	0.7323
0.1358	39.02	3040	1.0566	0.7323
0.0796	40.02	3116	0.9323	0.7480
0.0828	41.02	3192	0.7611	0.7953
0.0661	42.02	3268	0.7284	0.7874
0.0882	43.02	3344	0.6982	0.7953
0.0398	44.02	3420	0.8586	0.7717
0.2085	45.02	3496	0.7990	0.7717
0.0509	46.02	3572	0.7134	0.8268
0.0791	47.02	3648	0.6887	0.8189
0.0469	48.02	3724	0.7159	0.8031
0.0621	49.02	3800	0.7062	0.8031

Framework versions

Transformers 4.40.0
Pytorch 2.1.0+cu121
Datasets 2.18.0
Tokenizers 0.19.1

Task: Video Classification
Library: transformers
Type: videomae
License: cc-by-nc-4.0
Created: Apr 21, 2024
Updated: Apr 22, 2024