CoolFace
Modelpublic

kkumtori/vivit-b-16x2-kinetics400-0513-O_M

sourceHugging Facemitupdated 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. -->

vivit-b-16x2-kinetics400-0513-O_M

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: 1.0697
  • —Accuracy: 0.805

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
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_ratio: 0.1
  • —training_steps: 2900

Training results

Training LossEpochStepValidation LossAccuracy
1.59510.12901.58560.45
1.14841.15800.98890.65
0.4362.18700.72300.77
0.10113.111601.02180.78
0.06314.114501.05620.805
0.00055.117401.08550.805
0.00046.120301.20530.785
0.00057.123201.11310.8
0.14838.126101.04470.81
0.00139.129001.06970.805

Framework versions

  • —Transformers 4.40.2
  • —Pytorch 2.2.1+cu121
  • —Datasets 2.19.1
  • —Tokenizers 0.19.1