Modelpublic

Shawon16/ViViT_BDSLW60_U5_20_coR

sourceHugging Facemitupdated 10mo agoView on Hugging Face

0likes27downloads

Model Card

ViViTBDSLW60U520coR

This model is a fine-tuned version of google/vivit-b-16x2-kinetics400 on an unknown dataset. It achieves the following results on the evaluation set:

—Loss: 0.5355
—Accuracy: 0.8717

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
—trainbatchsize: 2
—evalbatchsize: 2
—seed: 42
—gradientaccumulationsteps: 4
—totaltrainbatch_size: 8
—optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
—lrschedulertype: linear
—lrschedulerwarmup_ratio: 0.1
—training_steps: 18560
—mixedprecisiontraining: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
11.1492	0.0501	929	1.4489	0.7117
1.051	1.0501	1858	0.6573	0.7883
0.1849	2.0501	2787	0.7059	0.8117
0.1169	3.0501	3716	0.6554	0.8233
0.1042	4.0501	4645	0.8616	0.79
0.1028	5.0501	5574	0.8305	0.8267
0.0464	6.0501	6503	0.9667	0.8083
0.068	7.0501	7432	1.0300	0.7767
0.0957	8.0501	8361	0.8642	0.81
0.0562	9.0501	9290	1.0133	0.83
0.023	10.0501	10219	0.8639	0.8367
0.0526	11.0501	11148	0.6815	0.86
0.0445	12.0501	12077	0.6488	0.8633
0.0112	13.0501	13006	0.5026	0.8833
0.0028	14.0501	13935	0.8986	0.8367
0.0534	15.0501	14864	0.5898	0.8567
0.009	16.0501	15793	0.6852	0.8233
0.0086	17.0501	16722	0.4841	0.8683
0.0108	18.0501	17651	0.5355	0.8717

Framework versions

—Transformers 4.46.1
—Pytorch 2.5.1+cu124
—Datasets 3.1.0
—Tokenizers 0.20.1