CoolFace
Modelpublic

Shaier/BERT_MC_OpenBookQA_w_wrong_context

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face
0likes52downloads
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. -->

BERTMCOpenBookQAwwrong_context

This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.7450
  • —Accuracy: 0.922

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-05
  • —trainbatchsize: 16
  • —evalbatchsize: 16
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 11

Training results

Training LossEpochStepValidation LossAccuracy
0.35251.018590.26960.906
0.20842.037180.32840.9143
0.12633.055770.42050.9143
0.07344.074360.46880.9203
0.04375.092950.62660.9173
0.03576.0111540.69340.9207
0.02647.0130130.69470.92
0.00988.0148720.68000.9197
0.01049.0167310.73930.923
0.006710.0185900.78460.9217
0.003411.0204490.74500.922

Framework versions

  • —Transformers 4.21.3
  • —Pytorch 1.12.1
  • —Datasets 2.5.1
  • —Tokenizers 0.11.0