CoolFace
Modelpublic

yangboyuan/vivit-b-16x2-kinetics400-finetuned-vivit-severity

sourceHugging Facemitupdated 2y agoView on Hugging Face
0likes8downloads
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-finetuned-vivit-severity

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: 1.0088
  • —Accuracy: 0.8530

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: 1
  • —evalbatchsize: 1
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_ratio: 0.1
  • —training_steps: 5210

Training results

Training LossEpochStepValidation LossAccuracy
2.05040.15210.92790.8280
1.16171.110420.98900.8280
0.50882.115630.84130.8172
0.79473.120840.76310.8423
0.00284.126050.87180.8459
0.75025.131260.90220.8495
0.8146.136470.84670.8423
0.52517.141680.89140.8602
0.99778.146890.95990.8530
0.00079.152101.00880.8530

Framework versions

  • —Transformers 4.42.4
  • —Pytorch 2.0.1+cu117
  • —Datasets 2.20.0
  • —Tokenizers 0.19.1