CoolFace
Modelpublic

gokuls/hBERTv1_no_pretrain_mnli

sourceHugging Faceupdated 3y agoView on Hugging Face
0likes21downloads
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. -->

hBERTv1nopretrain_mnli

This model is a fine-tuned version of [](https://huggingface.co/) on the GLUE MNLI dataset. It achieves the following results on the evaluation set:

  • —Loss: 1.0986
  • —Accuracy: 0.3522

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: 4e-05
  • —trainbatchsize: 96
  • —evalbatchsize: 96
  • —seed: 10
  • —distributed_type: multi-GPU
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 50

Training results

Training LossEpochStepValidation LossAccuracy
1.10371.040911.09940.3182
1.09882.081821.09860.3182
1.09873.0122731.09890.3274
1.09874.0163641.09860.3545
1.09875.0204551.09860.3545
1.09876.0245461.09860.3274
1.09867.0286371.09860.3182
1.09868.0327281.09860.3274
1.09869.0368191.09860.3274

Framework versions

  • —Transformers 4.30.2
  • —Pytorch 1.14.0a0+410ce96
  • —Datasets 2.12.0
  • —Tokenizers 0.13.3