CoolFace
Modelpublic

yangboyuan/videomae-base-finetuned-ucf101-subset-frequency

sourceHugging Facecc-by-nc-4.0updated 2y agoView on Hugging Face
0likes12downloads
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. -->

videomae-base-finetuned-ucf101-subset-frequency

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

  • —Loss: 0.5657
  • —Accuracy: 0.7726

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: 4
  • —evalbatchsize: 4
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_ratio: 0.1
  • —training_steps: 1480

Training results

Training LossEpochStepValidation LossAccuracy
0.88180.11480.59190.7111
0.63371.12960.59290.7111
0.62452.14440.71500.6085
0.65493.15920.60960.7556
0.6584.17400.71690.6735
0.69815.18880.60500.7726
0.6196.110360.52780.7709
0.61637.111840.51670.7778
0.37788.113320.52980.7812
0.54599.114800.56570.7726

Framework versions

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