Edit model card

bert-base-uncased-stsb

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

  • Loss: 0.5144
  • Pearson: 0.8875
  • Spearmanr: 0.8843
  • Combined Score: 0.8859

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: 2e-05
  • train_batch_size: 32
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0

Training results

Training Loss Epoch Step Validation Loss Pearson Spearmanr Combined Score
No log 1.0 180 0.5179 0.8806 0.8735 0.8771
No log 2.0 360 0.5145 0.8850 0.8820 0.8835
0.7868 3.0 540 0.5144 0.8875 0.8843 0.8859

Framework versions

  • Transformers 4.20.0.dev0
  • Pytorch 1.11.0+cu113
  • Datasets 2.1.0
  • Tokenizers 0.12.1
Downloads last month
307
Safetensors
Model size
109M params
Tensor type
I64
·
F32
·
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.

Model tree for JeremiahZ/bert-base-uncased-stsb

Finetuned
(2176)
this model

Dataset used to train JeremiahZ/bert-base-uncased-stsb

Evaluation results