CoolFace
Modelpublic

paola-md/recipe-distilbert-upper-tIs

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face
0likes124downloads
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-upper-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: 0.8746

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
1.671.013531.2945
1.29652.027061.1547
1.19043.040591.0846
1.12724.054121.0407
1.08575.067651.0039
1.05496.081180.9802
1.037.094710.9660
1.018.0108240.9474
0.99319.0121770.9365
0.980710.0135300.9252
0.969111.0148830.9105
0.960112.0162360.9079
0.950313.0175890.8979
0.943614.0189420.8930
0.937115.0202950.8875
0.932216.0216480.8851
0.927917.0230010.8801
0.925418.0243540.8812
0.922719.0257070.8768
0.923220.0270600.8746

Framework versions

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