CoolFace
Modelpublic

gokuls/mobilebert_add_GLUE_Experiment_logit_kd_sst2_128

sourceHugging Faceapache-2.0updated 4y 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. -->

mobilebertaddGLUEExperimentlogitkdsst2_128

This model is a fine-tuned version of google/mobilebert-uncased on the GLUE SST2 dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.7282
  • —Accuracy: 0.8073

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
1.54871.05271.39290.5780
1.36292.010541.49790.5505
1.13973.015811.39270.6755
0.56494.021080.72890.8073
0.41125.026350.72820.8073
0.34626.031620.76540.8050
0.30697.036890.83030.7970
0.28338.042160.88060.7924
0.26629.047430.92970.7959
0.252110.052701.09790.7718

Framework versions

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