CoolFace
Modelpublic

gokuls/mobilebert_sa_GLUE_Experiment_logit_kd_rte_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. -->

mobilebertsaGLUEExperimentlogitkdrte_128

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

  • —Loss: 0.3915
  • —Accuracy: 0.5271

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
0.40931.0200.39170.5271
0.40772.0400.39220.5271
0.40763.0600.39160.5271
0.40754.0800.39210.5271
0.40755.01000.39250.5271
0.40736.01200.39150.5271
0.40667.01400.39160.5271
0.40438.01600.39370.5271
0.39029.01800.44400.5054
0.354510.02000.45750.4801
0.311611.02200.47700.4440

Framework versions

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