videomae-base-finetuned-ucf101-subset-frequency – AI Model by yangboyuan | AlphaNeural AI

You can deploy this model and start earning money today!

yangboyuan/
videomae-base-finetuned-ucf101-subset-frequency

like

0

video-classification

generated_from_trainer

MCG-NJU/videomae-base

endpoints_compatible

Views

No views yet

videomae-base-finetuned-ucf101-subset-frequency

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: 0.5657
Accuracy: 0.7726

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: 1480

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8818	0.1	148	0.5919	0.7111
0.6337	1.1	296	0.5929	0.7111
0.6245	2.1	444	0.7150	0.6085
0.6549	3.1	592	0.6096	0.7556
0.658	4.1	740	0.7169	0.6735
0.6981	5.1	888	0.6050	0.7726
0.619	6.1	1036	0.5278	0.7709
0.6163	7.1	1184	0.5167	0.7778
0.3778	8.1	1332	0.5298	0.7812
0.5459	9.1	1480	0.5657	0.7726

Framework versions

Transformers 4.42.4
Pytorch 2.0.1+cu117
Datasets 2.20.0
Tokenizers 0.19.1