Edit model card

mobilebert_sa_GLUE_Experiment_stsb_256

This model is a fine-tuned version of google/mobilebert-uncased on the GLUE STSB dataset. It achieves the following results on the evaluation set:

  • Loss: 2.2966
  • Pearson: 0.0077
  • Spearmanr: 0.0083
  • Combined Score: 0.0080

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 Pearson Spearmanr Combined Score
4.155 1.0 45 2.2966 0.0077 0.0083 0.0080
2.1654 2.0 90 2.3384 0.0600 0.0633 0.0616
2.0822 3.0 135 2.3583 0.0625 0.0718 0.0671
2.0017 4.0 180 2.7680 0.0721 0.0753 0.0737
1.9379 5.0 225 2.7330 0.0963 0.0919 0.0941
1.785 6.0 270 2.3938 0.1605 0.1497 0.1551

Framework versions

  • Transformers 4.26.0
  • Pytorch 1.14.0a0+410ce96
  • Datasets 2.8.0
  • Tokenizers 0.13.2
Downloads last month
7
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train gokuls/mobilebert_sa_GLUE_Experiment_stsb_256

Evaluation results