CoolFace
Modelpublic

gokuls/hBERTv2_new_no_pretrain_qnli

sourceHugging Faceupdated 3y 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. -->

hBERTv2newnopretrainqnli

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

  • —Loss: 0.6386
  • —Accuracy: 0.6352

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: 128
  • —evalbatchsize: 128
  • —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
0.68661.08190.67700.5570
0.6522.016380.64680.6264
0.59863.024570.63860.6352
0.51444.032760.69300.6590
0.42725.040950.70340.6548
0.35586.049140.81710.6637
0.28747.057330.90570.6601
0.23918.065521.00900.6445

Framework versions

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