CoolFace
Modelpublic

gokuls/mobilebert_add_GLUE_Experiment_logit_kd_stsb_128

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face
0likes15downloads
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. -->

mobilebertaddGLUEExperimentlogitkdstsb_128

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

  • —Loss: 1.1505
  • —Pearson: 0.0470
  • —Spearmanr: 0.0414
  • —Combined Score: 0.0442

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 LossPearsonSpearmanrCombined Score
2.5241.0451.3607-0.0066-0.0281-0.0174
1.08772.0901.17290.04460.04970.0472
1.06483.01351.15050.04700.04140.0442
1.07374.01801.15640.04720.04640.0468
1.04455.02251.19710.05290.05750.0552
1.02966.02701.17230.05780.07270.0652
1.0267.03151.27350.06210.06060.0614
1.02168.03601.22140.06660.07000.0683

Framework versions

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