CoolFace
Modelpublic

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

sourceHugging Faceupdated 4y agoView on Hugging Face
0likes33downloads
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-cola-from-scratch-custom-tokenizer-target-glue-mnli

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

  • —Loss: 1.0222
  • —Accuracy: 0.4694

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
1.09830.045001.09590.3677
1.09240.0810001.08830.3622
1.08640.1215001.07880.3862
1.07070.1620001.06700.4131
1.0630.225001.06070.4223
1.05460.2430001.04250.4354
1.04240.2935001.04210.4367
1.03260.3340001.03670.4410
1.0270.3745001.02690.4630
1.02130.4150001.02220.4694

Framework versions

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