videomae-base-finetuned-ucf101-subset

hansenling/videomae-base-finetuned-ucf101-subset

videomae-base-finetuned-ucf101-subset is a machine learning model from hansenling. 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

17% of all-time downloads

All-time downloads

Public

Parameters

86.2M

4.1 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors345 MB · 100%

At a glance

License: cc-by-nc-4.0
Model type: videomae
Access: Public
Created: Sep 20, 2024
Updated: Oct 10, 2024
SHA: 96f84f24

Base models

MCG-NJU/videomae-base

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: 0.4127
Accuracy: 0.8857

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: 148

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.158	0.2568	38	1.8710	0.4143
0.9003	1.2568	76	0.9266	0.7
0.45	2.2568	114	0.4982	0.8
0.3354	3.2297	148	0.4127	0.8857

Framework versions

Transformers 4.44.0
Pytorch 2.4.0+cpu
Datasets 3.0.1
Tokenizers 0.19.1

Type: videomae
License: cc-by-nc-4.0
Created: Sep 20, 2024
Updated: Oct 10, 2024