CoolFace
Modelpublic

pavitemple/finetuned-Accident-Video-subset

sourceHugging Facecc-by-nc-4.0updated 3y agoView on Hugging Face
0likes5downloads
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. -->

finetuned-Accident-Video-subset

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: 1.0765
  • —Accuracy: 0.5161

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: 90

Training results

Training LossEpochStepValidation LossAccuracy
1.58980.13121.31730.48
1.21041.13241.21570.4
1.4182.13361.16170.52
1.12023.13481.12790.52
1.22264.13601.11110.48
1.18865.13721.07280.48
1.01776.13841.04530.56
1.04437.07901.03780.56

Framework versions

  • —Transformers 4.35.0
  • —Pytorch 2.1.0
  • —Datasets 2.14.6
  • —Tokenizers 0.14.1