CoolFace
Modelpublic

paola-md/recipe-distilbert-s

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face
0likes52downloads
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. -->

recipe-distilbert-s

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 1.0321

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: 256
  • —evalbatchsize: 256
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 20
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
1.85941.08441.4751
1.47632.016881.3282
1.36643.025321.2553
1.29754.033761.2093
1.25435.042201.1667
1.21896.050641.1472
1.19447.059081.1251
1.17378.067521.1018
1.15499.075961.0950
1.138710.084401.0796
1.129511.092841.0713
1.116612.0101281.0639
1.107813.0109721.0485
1.09914.0118161.0431
1.095115.0126601.0425
1.087416.0135041.0323
1.082817.0143481.0368
1.080218.0151921.0339
1.079819.0160361.0247
1.075820.0168801.0321

Framework versions

  • —Transformers 4.19.0.dev0
  • —Pytorch 1.11.0+cu102
  • —Datasets 2.3.2
  • —Tokenizers 0.12.1