CoolFace
Modelpublic

irfanamal/electra_multiple_choice

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes14downloads
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. -->

electramultiplechoice

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

  • —Loss: 1.2639
  • —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
1.42231.032071.18650.54
1.21312.064141.08170.555
1.07543.096211.00160.61
0.94024.0128280.98410.595
0.82075.0160350.99120.63
0.71636.0192421.08080.58
0.61877.0224491.09560.6
0.54258.0256561.15260.63
0.47639.0288631.26390.58

Framework versions

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