videomae-base-finetuned-ImageTBAD_NewTBAD

AymanAbaid25/videomae-base-finetuned-ImageTBAD_NewTBAD

videomae-base-finetuned-ImageTBAD_NewTBAD is a video classification model from AymanAbaid25. 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

4% of all-time downloads

All-time downloads

114

Public

Parameters

86.2M

32.4 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: Jan 29, 2025
Updated: Aug 4, 2025
SHA: 3b3e25bb

Base models

MCG-NJU/videomae-base

Model card

From the Hugging Face model README

videomae-base-finetuned-ImageTBAD_NewTBAD

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

Loss: 0.8677
Accuracy: 0.6786

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: 4
eval_batch_size: 4
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: 1060

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.9916	0.0255	27	0.7363	0.6429
0.6555	1.0255	54	0.8760	0.5357
0.7784	2.0255	81	0.8665	0.6429
0.7095	3.0255	108	0.9988	0.6429
0.7878	4.0255	135	0.7762	0.6429
0.6338	5.0255	162	0.7192	0.6429
0.9695	6.0255	189	0.9186	0.6429
0.6448	7.0255	216	0.9459	0.6429
0.5396	8.0255	243	0.7403	0.6429
0.5527	9.0255	270	0.7731	0.6429
0.7133	10.0255	297	0.8257	0.6429
0.7189	11.0255	324	0.7138	0.6429
0.6111	12.0255	351	0.5883	0.75
0.6318	13.0255	378	0.7667	0.7143
0.5604	14.0255	405	0.6575	0.6786
0.4851	15.0255	432	0.6212	0.75
0.4557	16.0255	459	0.6888	0.6429
0.5065	17.0255	486	0.6488	0.75
0.6024	18.0255	513	0.6337	0.7857
0.5913	19.0255	540	0.5965	0.6786
0.5557	20.0255	567	0.5556	0.7143
0.8652	21.0255	594	0.7864	0.6429
0.4589	22.0255	621	0.6316	0.6071
0.5287	23.0255	648	0.7389	0.6429
0.4386	24.0255	675	0.7870	0.5714
0.4477	25.0255	702	0.6795	0.6786
0.6338	26.0255	729	0.5635	0.7143
0.5666	27.0255	756	0.7130	0.7143
0.4704	28.0255	783	0.6144	0.6429
0.3877	29.0255	810	0.7417	0.75
0.6096	30.0255	837	0.7972	0.6071
0.594	31.0255	864	0.8041	0.5714
0.6546	32.0255	891	0.8819	0.5714
0.3474	33.0255	918	0.7812	0.6786
0.6284	34.0255	945	0.8726	0.6429
0.3378	35.0255	972	0.8990	0.75
0.3506	36.0255	999	0.9164	0.5714
0.4684	37.0255	1026	0.8540	0.6429
0.3758	38.0255	1053	0.8673	0.6786
0.358	39.0066	1060	0.8677	0.6786

Framework versions

Transformers 4.45.0.dev0
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1

Task: Video Classification
Library: transformers
Type: videomae
License: cc-by-nc-4.0
Created: Jan 29, 2025
Updated: Aug 4, 2025