Team Ai
Modelpublic

ChiJuiChen/GenerativeImage2Text-naruto

sourceHugging Facemitupdated 2y agoView on Hugging Face
0likes26downloads
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. -->

GenerativeImage2Text-naruto

This model is a fine-tuned version of microsoft/git-base on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.0544
  • —Wer Score: 2.6810

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: 2
  • —evalbatchsize: 2
  • —seed: 42
  • —gradientaccumulationsteps: 2
  • —totaltrainbatch_size: 4
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 30
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer Score
7.28291.8182504.433311.5086
2.21183.63641000.36551.1034
0.10895.45451500.04281.0259
0.02237.27272000.04210.4655
0.01629.09092500.04300.4224
0.013910.90913000.04340.9569
0.012612.72733500.04550.8534
0.011514.54554000.04573.2845
0.010616.36364500.04902.3190
0.009618.18185000.05152.2241
0.009420.05500.05201.9569
0.008721.81826000.05404.2328
0.008423.63646500.05391.8448
0.00825.45457000.05462.5431
0.007727.27277500.05422.7672
0.007229.09098000.05442.6810

Framework versions

  • —Transformers 4.40.2
  • —Pytorch 2.3.0+cu121
  • —Datasets 2.19.1
  • —Tokenizers 0.19.1