Edit model card

mobilebert_sa_GLUE_Experiment_logit_kd_pretrain_wnli

This model is a fine-tuned version of gokuls/mobilebert_sa_pre-training-complete on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3677
  • Accuracy: 0.2958

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: 5e-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
0.3708 1.0 5 0.3927 0.3944
0.3555 2.0 10 0.3715 0.4225
0.3493 3.0 15 0.3677 0.2958
0.3485 4.0 20 0.3704 0.3803
0.3454 5.0 25 0.3815 0.2394
0.3461 6.0 30 0.3878 0.2394
0.3432 7.0 35 0.3962 0.2535
0.3427 8.0 40 0.4050 0.1972

Framework versions

  • Transformers 4.26.0
  • Pytorch 1.14.0a0+410ce96
  • Datasets 2.9.0
  • Tokenizers 0.13.2
Downloads last month
8

Dataset used to train gokuls/mobilebert_sa_GLUE_Experiment_logit_kd_pretrain_wnli

Evaluation results