CoolFace
Modelpublic

cyttic/heb-verifier17-connected

sourceHugging Faceupdated 2mo 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. -->

heb-verifier17-connected

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.0546
  • —Cer: 0.0209
  • —Exact: 0.9619

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: 16
  • —evalbatchsize: 32
  • —seed: 42
  • —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 0.05
  • —num_epochs: 3
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossCerExact
0.13570.37295000.12820.05030.9104
0.10840.745710000.08560.03620.9384
0.04781.118615000.07320.02600.9518
0.06251.491420000.05420.02150.9630
0.05671.864325000.05670.02200.9597
0.03362.237130000.04730.02090.9619
0.04272.610035000.03340.01640.9720
0.03542.982840000.03700.01530.9709
0.03543.040230.05460.02090.9619

Framework versions

  • —Transformers 5.13.1
  • —Pytorch 2.11.0+cu128
  • —Datasets 5.0.0
  • —Tokenizers 0.22.2