CoolFace
Modelpublic

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

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face
0likes19downloads
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-mnli-target-glue-stsb

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

  • —Loss: 0.5787
  • —Pearson: 0.8713
  • —Spearmanr: 0.8682

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
0.84092.785000.62230.86390.8635
0.29245.5610000.58940.86780.8657
0.17348.3315000.60290.86530.8628
0.125211.1120000.61900.87020.8670
0.100913.8925000.58010.87080.8681
0.083116.6730000.63740.86890.8652
0.069819.4435000.58010.87160.8683
0.060922.2240000.56410.87410.8706
0.056925.045000.54910.87280.8697
0.051227.7850000.57870.87130.8682

Framework versions

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