CoolFace
Modelpublic

gokuls/mobilebert_add_GLUE_Experiment_logit_kd_qnli_256

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face
0likes24downloads
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. -->

mobilebertaddGLUEExperimentlogitkdqnli_256

This model is a fine-tuned version of google/mobilebert-uncased on the GLUE QNLI dataset. It achieves the following results on the evaluation set:

  • —Loss: 1.0610
  • —Accuracy: 0.5054

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: 128
  • —evalbatchsize: 128
  • —seed: 10
  • —distributed_type: multi-GPU
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 50

Training results

Training LossEpochStepValidation LossAccuracy
1.13961.08191.06120.5054
1.13932.016381.06110.5054
1.13933.024571.06170.5054
1.13934.032761.06100.5054
1.13945.040951.06120.5054
1.13936.049141.06130.5054
1.13937.057331.06140.5054
1.13938.065521.06150.5054
1.13929.073711.06110.5054

Framework versions

  • —Transformers 4.26.0
  • —Pytorch 1.14.0a0+410ce96
  • —Datasets 2.9.0
  • —Tokenizers 0.13.2