CoolFace
Modelpublic

paola-md/recipe-distilbert-tis

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face
0likes57downloads
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-tis

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: 0.9886

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
1.87921.010381.4680
1.46912.020761.3122
1.34713.031141.2343
1.27984.041521.1829
1.22845.051901.1437
1.19566.062281.1120
1.16837.072661.0905
1.14588.083041.0731
1.1269.093421.0645
1.11310.0103801.0471
1.096211.0114181.0348
1.086412.0124561.0256
1.077213.0134941.0173
1.069214.0145321.0130
1.062215.0155701.0111
1.057716.0166081.0021
1.053717.0176461.0001
1.047418.0186840.9928
1.047119.0197220.9908
1.045820.0207600.9886

Framework versions

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