Edit model card

hBERTv2_new_no_pretrain_qqp

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

  • Loss: 0.4537
  • Accuracy: 0.7856
  • F1: 0.6931
  • Combined Score: 0.7393

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
  • train_batch_size: 128
  • eval_batch_size: 128
  • seed: 10
  • distributed_type: multi-GPU
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 50

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Combined Score
0.5037 1.0 2843 0.4537 0.7856 0.6931 0.7393
0.4066 2.0 5686 0.4549 0.7946 0.6758 0.7352
0.3367 3.0 8529 0.4630 0.7950 0.6650 0.7300
0.2876 4.0 11372 0.5279 0.8180 0.7598 0.7889
0.2498 5.0 14215 0.4857 0.8217 0.7650 0.7933
0.2371 6.0 17058 0.5113 0.8216 0.7376 0.7796

Framework versions

  • Transformers 4.30.2
  • Pytorch 1.14.0a0+410ce96
  • Datasets 2.12.0
  • Tokenizers 0.13.3
Downloads last month
2

Dataset used to train gokuls/hBERTv2_new_no_pretrain_qqp

Evaluation results