CoolFace
Modelpublic

Thenghuy/cropwiz_qa_model

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes5downloads
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. -->

cropwizqamodel

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

  • —Loss: 2.9531

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: 16
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 27

Training results

Training LossEpochStepValidation Loss
No log1.065.5539
No log2.0124.8899
No log3.0184.0865
No log4.0243.6266
No log5.0303.3544
No log6.0363.1559
No log7.0422.9612
No log8.0482.9628
No log9.0542.9661
No log10.0602.9657
No log11.0662.9469
No log12.0722.9327
No log13.0782.9189
No log14.0842.9100
No log15.0902.9095
No log16.0962.9215
No log17.01022.9453
No log18.01082.9371
No log19.01142.9247
No log20.01202.9409
No log21.01262.9985
No log22.01322.9990
No log23.01382.9988
No log24.01442.9857
No log25.01502.9716
No log26.01562.9567
No log27.01622.9531

Framework versions

  • —Transformers 4.42.4
  • —Pytorch 2.3.0+cu121
  • —Datasets 2.20.0
  • —Tokenizers 0.19.1