videomae-base-finetuned-ucf101-subset

Sunilkt/videomae-base-finetuned-ucf101-subset

videomae-base-finetuned-ucf101-subset is a machine learning model from Sunilkt. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as cc-by-nc-4.0.

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

Downloads · 30 days

11% of all-time downloads

All-time downloads

105

Public

Parameters

86.2M

3.4 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin345 MB · 50%

At a glance

License: cc-by-nc-4.0
Model type: videomae
Access: Public
Created: Sep 23, 2024
Updated: Sep 23, 2024
SHA: dde9c5ad

Model card

From the Hugging Face model README

videomae-base-finetuned-ucf101-subset

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: 0.7890
Accuracy: 0.2297

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: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.25	2	0.7797	0.2807
No log	1.25	4	0.8898	0.2807
No log	2.25	6	0.9445	0.2807
No log	3.25	8	0.9488	0.2807

Framework versions

Transformers 4.28.0
Pytorch 2.4.1+cpu
Datasets 3.0.0
Tokenizers 0.13.3

Type: videomae
License: cc-by-nc-4.0
Created: Sep 23, 2024
Updated: Sep 23, 2024