CoolFace
Modelpublic

muhtasham/tiny-mlm-glue-mnli-from-scratch-custom-tokenizer-target-glue-mnli

sourceHugging Faceupdated 4y agoView on Hugging Face
0likes29downloads
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-mnli-from-scratch-custom-tokenizer-target-glue-mnli

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

  • —Loss: 1.0101
  • —Accuracy: 0.4803

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 LossAccuracy
1.09830.045001.09590.3689
1.09110.0810001.08720.3711
1.08440.1215001.07660.3948
1.06470.1620001.05680.4272
1.04820.225001.03640.4501
1.03850.2430001.02740.4595
1.02980.2935001.02870.4501
1.02090.3340001.02150.4656
1.01440.3745001.01390.4786
1.01110.4150001.01010.4803

Framework versions

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