CoolFace
Modelpublic

muhtasham/tiny-mlm-glue-rte-from-scratch-custom-tokenizer-target-glue-stsb

sourceHugging Faceupdated 4y agoView on Hugging Face
0likes28downloads
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. -->

tiny-mlm-glue-rte-from-scratch-custom-tokenizer-target-glue-stsb

This model is a fine-tuned version of muhtasham/tiny-mlm-glue-rte-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 3.1300
  • —Pearson: 0.1749
  • —Spearmanr: 0.1759

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
3.51192.785002.36040.04210.0353
2.02415.5610002.46880.09230.0872
1.77998.3315002.63170.13530.1453
1.379811.1120002.76820.16470.1754
1.09313.8925002.80720.17880.1810
0.891816.6730003.10680.17240.1745
0.757819.4435003.10690.17190.1741
0.66822.2240003.13000.17490.1759

Framework versions

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