CoolFace
Modelpublic

mohamedsaeed823/VideoMAEF-finetuned-ARSL-diverse-dataset

sourceHugging Facecc-by-nc-4.0updated 2y agoView on Hugging Face
0likes13downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

VideoMAEF-finetuned-ARSL-diverse-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: 0.0012
  • —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: 2.5e-05
  • —trainbatchsize: 2
  • —evalbatchsize: 2
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_ratio: 0.1
  • —training_steps: 2395

Training results

Training LossEpochStepValidation LossAccuracy
1.04850.122981.11480.6854
0.72561.125960.10321.0
0.20522.128940.00571.0
0.04513.1211920.00281.0
0.18214.1214900.00201.0
0.09655.1217880.00151.0
0.08736.1220860.00121.0
0.00277.1223840.00111.0
0.12228.023950.00121.0

Framework versions

  • —Transformers 4.39.3
  • —Pytorch 2.1.2
  • —Datasets 2.18.0
  • —Tokenizers 0.15.2