videomae-base-finetuned-yt_short_classification

Kartikeya/videomae-base-finetuned-yt_short_classification

videomae-base-finetuned-yt_short_classification is a video classification model from Kartikeya. 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

13% of all-time downloads

All-time downloads

Public

Parameters

86.2M

1.7 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: Aug 20, 2025
Updated: Aug 21, 2025
SHA: 9d8200c0

Base models

MCG-NJU/videomae-base

Model card

From the Hugging Face model README

videomae-base-finetuned-yt_short_classification

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: 0.4704
Accuracy: 0.7815
0 Precision: 0.7484
0 Recall: 0.8149
0 F1-score: 0.7803
0 Support: 6322.0
1 Precision: 0.8170
1 Recall: 0.7510
1 F1-score: 0.7827
1 Support: 6957.0
Accuracy F1-score: 0.7815
Macro avg Precision: 0.7827
Macro avg Recall: 0.7830
Macro avg F1-score: 0.7815
Macro avg Support: 13279.0
Weighted avg Precision: 0.7844
Weighted avg Recall: 0.7815
Weighted avg F1-score: 0.7815
Weighted avg Support: 13279.0

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: 16
eval_batch_size: 16
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
training_steps: 2060

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	0 Precision	0 Recall	0 F1-score	0 Support	1 Precision	1 Recall	1 F1-score	1 Support	Accuracy F1-score	Macro avg Precision	Macro avg Recall	Macro avg F1-score	Macro avg Support	Weighted avg Precision	Weighted avg Recall	Weighted avg F1-score	Weighted avg Support
0.6282	0.2005	413	0.6101	0.6848	0.7561	0.4991	0.6012	6322.0	0.6522	0.8537	0.7395	6957.0	0.6848	0.7041	0.6764	0.6704	13279.0	0.7016	0.6848	0.6737	13279.0
0.6569	1.2005	826	0.5357	0.7290	0.7392	0.6655	0.7004	6322.0	0.7213	0.7867	0.7526	6957.0	0.7290	0.7303	0.7261	0.7265	13279.0	0.7298	0.7290	0.7277	13279.0
0.5064	2.2005	1239	0.4839	0.7687	0.7517	0.7680	0.7597	6322.0	0.7849	0.7694	0.7771	6957.0	0.7687	0.7683	0.7687	0.7684	13279.0	0.7691	0.7687	0.7688	13279.0
0.4293	3.2005	1652	0.5120	0.7518	0.6850	0.8861	0.7727	6322.0	0.8589	0.6297	0.7267	6957.0	0.7518	0.7719	0.7579	0.7497	13279.0	0.7761	0.7518	0.7486	13279.0
0.421	4.1981	2060	0.4704	0.7815	0.7484	0.8149	0.7803	6322.0	0.8170	0.7510	0.7827	6957.0	0.7815	0.7827	0.7830	0.7815	13279.0	0.7844	0.7815	0.7815	13279.0

Framework versions

Transformers 4.46.3
Pytorch 2.0.0+cu117
Datasets 3.1.0
Tokenizers 0.20.3

Task: Video Classification
Library: transformers
Type: videomae
License: cc-by-nc-4.0
Created: Aug 20, 2025
Updated: Aug 21, 2025