CoolFace
Modelpublic

gokuls/mobilebert_add_GLUE_Experiment_logit_kd_cola_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. -->

mobilebertaddGLUEExperimentlogitkdcola_128

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

  • —Loss: 0.6833
  • —Matthews Correlation: 0.0

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 LossMatthews Correlation
0.8271.0670.68690.0
0.79712.01340.68720.0
0.79683.02010.68370.0
0.79564.02680.68430.0
0.79575.03350.68330.0
0.79346.04020.68340.0
0.78227.04690.70140.0
0.76368.05360.68350.0
0.75099.06030.68790.0
0.748210.06700.68420.0

Framework versions

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