Modelpublic

esmaelehab/videomae-base-finetuned-kinetics-finetuned-Accident-dataset

sourceHugging Facecc-by-nc-4.0updated 8mo agoView on Hugging Face

0likes13downloads

Model Card

videomae-base-finetuned-kinetics-finetuned-Accident-dataset

This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set:

—Loss: 0.0077
—Accuracy: 1.0

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: 2e-05
—trainbatchsize: 8
—evalbatchsize: 8
—seed: 42
—optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
—lrschedulertype: linear
—lrschedulerwarmup_ratio: 0.1
—training_steps: 392
—mixedprecisiontraining: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5675	0.1276	50	0.2509	0.9126
0.1471	1.1276	100	0.2354	0.9126
0.022	2.1276	150	0.1293	0.9515
0.0013	3.1276	200	0.0422	0.9806
0.0009	4.1276	250	0.0173	0.9903
0.0024	5.1276	300	0.0544	0.9806
0.0376	6.1276	350	0.0447	0.9806
0.0007	7.1071	392	0.0317	0.9806

Framework versions

—Transformers 4.57.1
—Pytorch 2.8.0+cu126
—Datasets 4.4.2
—Tokenizers 0.22.1