CoolFace
Modelpublic

irfanamal/distilroberta_multiple_choice

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes17downloads
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. -->

distilrobertamultiplechoice

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

  • —Loss: 1.1925
  • —Accuracy: 0.58

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: 5e-06
  • —trainbatchsize: 16
  • —evalbatchsize: 16
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 100

Training results

Training LossEpochStepValidation LossAccuracy
1.45961.032071.29850.45
1.35012.064141.24200.49
1.27533.096211.18920.49
1.20694.0128281.19540.525
1.13195.0160351.17630.52
1.06336.0192421.19300.535
0.99117.0224491.18450.535
0.92348.0256561.18660.565
0.86229.0288631.20620.55
0.797810.0320701.19250.58

Framework versions

  • —Transformers 4.31.0
  • —Pytorch 2.0.1+cu117
  • —Datasets 2.14.4
  • —Tokenizers 0.13.3