CoolFace
Modelpublic

ivensamdh/genderage2

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face
3likes317downloads
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. -->

genderage2

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.2771

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: 0.0001
  • —trainbatchsize: 11
  • —evalbatchsize: 8
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 8
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
0.37370.891000.3702
0.32081.792000.3308
0.26812.683000.2977
0.23343.574000.2875
0.20934.465000.2840
0.19895.366000.2798
0.18016.257000.2785
0.17077.148000.2771

Framework versions

  • —Transformers 4.25.1
  • —Pytorch 1.13.1+cu117
  • —Datasets 2.8.0
  • —Tokenizers 0.13.2