CoolFace
Modelpublic

Geohunterr/workspace

sourceHugging Facegemmaupdated 2y agoView on Hugging Face
0likes25downloads
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. -->

workspace

This model is a fine-tuned version of google/paligemma-3b-pt-224 on the ecgt_vision dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.0009

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: 2e-05
  • —trainbatchsize: 16
  • —evalbatchsize: 8
  • —seed: 42
  • —gradientaccumulationsteps: 4
  • —totaltrainbatch_size: 64
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 2
  • —num_epochs: 5

Training results

Training LossEpochStepValidation Loss
3.35570.99611290.0054
0.00392.02590.0015
0.00082.99613880.0011
0.00034.05180.0010
0.00024.98076450.0009

Framework versions

  • —PEFT 0.11.1
  • —Transformers 4.41.0
  • —Pytorch 2.0.1+cu118
  • —Datasets 2.19.1
  • —Tokenizers 0.19.1