CoolFace
Modelpublic

paola-md/recipe-roberta-is

sourceHugging Facemitupdated 4y agoView on Hugging Face
0likes170downloads
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-roberta-is

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

  • —Loss: 0.8382

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
1.3341.09611.1217
1.16382.019221.0369
1.09363.028830.9922
1.05034.038440.9606
1.01885.048050.9314
0.99536.057660.9256
0.97697.067270.9109
0.95998.076880.8978
0.94619.086490.8813
0.937710.096100.8777
0.925311.0105710.8755
0.91812.0115320.8601
0.911213.0124930.8541
0.904314.0134540.8548
0.898415.0144150.8470
0.895816.0153760.8412
0.891417.0163370.8345
0.888218.0172980.8353
0.887119.0182590.8344
0.883920.0192200.8382

Framework versions

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