CoolFace
Modelpublic

gokuls/hBERTv1_new_pretrain_w_init__rte

sourceHugging Faceupdated 3y agoView on Hugging Face
0likes16downloads
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. -->

hBERTv1newpretrainwinit__rte

This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_wt_init on the GLUE RTE dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.6916
  • —Accuracy: 0.5271

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
0.74781.0200.69210.5271
0.71952.0400.69160.5271
0.70873.0600.69450.5271
0.70254.0800.69170.5379
0.7215.01000.69240.5379
0.69926.01200.73020.4621
0.6857.01400.71240.5379

Framework versions

  • —Transformers 4.29.2
  • —Pytorch 1.14.0a0+410ce96
  • —Datasets 2.12.0
  • —Tokenizers 0.13.3