CoolFace
Modelpublic

pavitemple/finetuned-Accident-MultipleLabels-Video-subset-v2-new

sourceHugging Facecc-by-nc-4.0updated 3y agoView on Hugging Face
0likes7downloads
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-MultipleLabels-Video-subset-v2-new

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: 1.7905
  • —Accuracy: 0.3333

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
  • —gradientaccumulationsteps: 4
  • —totaltrainbatch_size: 16
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_ratio: 0.1
  • —training_steps: 20

Training results

Training LossEpochStepValidation LossAccuracy
No log0.241.97530.1406
No log1.281.97650.0938
1.74052.2122.09650.0938
1.74053.2162.11520.0469
1.46914.2202.11300.0469

Framework versions

  • —Transformers 4.35.2
  • —Pytorch 2.2.0.dev20231202+cu121
  • —Datasets 2.15.0
  • —Tokenizers 0.15.0