CoolFace
Modelpublic

paola-md/recipe-roberta-upper-tIs

sourceHugging Facemitupdated 4y agoView on Hugging Face
0likes234downloads
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-upper-tIs

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

  • —Loss: 0.7904

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
1.26711.012811.0554
1.09952.025620.9832
1.03393.038430.9389
0.99254.051240.9095
0.9645.064050.8914
0.94266.076860.8708
0.92277.089670.8590
0.90828.0102480.8448
0.89639.0115290.8361
0.884710.0128100.8249
0.875611.0140910.8204
0.867212.0153720.8105
0.861213.0166530.8106
0.856114.0179340.8041
0.848515.0192150.7979
0.845216.0204960.7910
0.840317.0217770.7991
0.838918.0230580.7928
0.837119.0243390.7926
0.834120.0256200.7904

Framework versions

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