CoolFace
Modelpublic

muhtasham/small-mlm-glue-cola-target-glue-stsb

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face
0likes20downloads
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. -->

small-mlm-glue-cola-target-glue-stsb

This model is a fine-tuned version of muhtasham/small-mlm-glue-cola on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.5924
  • —Pearson: 0.8702
  • —Spearmanr: 0.8670

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: 3e-05
  • —trainbatchsize: 32
  • —evalbatchsize: 32
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: constant
  • —training_steps: 5000

Training results

Training LossEpochStepValidation LossPearsonSpearmanr
0.84652.785000.63850.86290.8640
0.30575.5610000.60680.86720.8660
0.18328.3315000.64590.86050.8577
0.129111.1120000.61580.86750.8646
0.102313.8925000.60530.86920.8664
0.084216.6730000.60380.87030.8667
0.071519.4435000.58540.87180.8686
0.063122.2240000.56950.87290.8692
0.057525.045000.58680.87160.8685
0.052527.7850000.59240.87020.8670

Framework versions

  • —Transformers 4.26.0.dev0
  • —Pytorch 1.13.0+cu116
  • —Datasets 2.8.1.dev0
  • —Tokenizers 0.13.2