CoolFace
Modelpublic

paola-md/recipe-distilbert-upper-Is

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face
0likes250downloads
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-Is

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: 0.8565

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
1.63091.013051.2607
1.26392.026101.1291
1.15923.039151.0605
1.09874.052201.0128
1.05695.065250.9796
1.02626.078300.9592
1.00327.091350.9352
0.98158.0104400.9186
0.9679.0117450.9086
0.953210.0130500.8973
0.943611.0143550.8888
0.931812.0156600.8835
0.924313.0169650.8748
0.916914.0182700.8673
0.911715.0195750.8610
0.906616.0208800.8562
0.902817.0221850.8566
0.90118.0234900.8583
0.898819.0247950.8557
0.895820.0261000.8565

Framework versions

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