CoolFace
Modelpublic

DanSarm/receipt-operations-model

sourceHugging Faceapache-2.0updated 1y 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. -->

receipt-operations-model

This model is a fine-tuned version of DanSarm/receipt-core-model on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.0971

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: 4
  • —evalbatchsize: 4
  • —seed: 42
  • —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: linear
  • —num_epochs: 300

Training results

Training LossEpochStepValidation Loss
0.35321.0290.2037
0.13082.0580.1489
0.09373.0870.1171
0.0734.01160.1048
0.05555.01450.1018
0.04986.01740.1001
0.03777.02030.1025
0.03058.02320.1047
0.02779.02610.0971
0.025810.02900.0977
0.019911.03190.0978
0.018412.03480.1008
0.014413.03770.1051
0.012914.04060.1076
0.013915.04350.1072
0.012316.04640.1100
0.010817.04930.1086
0.008718.05220.1124
0.008119.05510.1212
0.006920.05800.1219
0.006321.06090.1131
0.00422.06380.1173
0.005323.06670.1175
0.005824.06960.1228

Framework versions

  • —Transformers 4.49.0
  • —Pytorch 2.6.0+cu124
  • —Datasets 3.4.1
  • —Tokenizers 0.21.1