CoolFace
Modelpublic

jesusgs01/results_solo_good_fold_5_pt

sourceHugging Facegemmaupdated 1y agoView on Hugging Face
0likes6downloads
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. -->

resultssologoodfold5_pt

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

  • —Loss: 0.1692

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: 1e-05
  • —trainbatchsize: 8
  • —evalbatchsize: 8
  • —seed: 42
  • —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: linear
  • —num_epochs: 10

Training results

Training LossEpochStepValidation Loss
0.20091.020910.1753
0.19692.041820.1692
0.18333.062730.1785
0.19234.083640.1724
0.18145.0104550.1761
0.1856.0125460.1716
0.18397.0146370.1729
0.1918.0167280.1720
0.18819.0188190.1714
0.18710.0209100.1719

Framework versions

  • —Transformers 4.48.3
  • —Pytorch 2.1.2+cu121
  • —Tokenizers 0.21.0