keikofujii's picture
End of training
22e9ebd
metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - spearmanr
model-index:
  - name: distilbert-base-uncased-finetuned-stsb
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: glue
          type: glue
          config: stsb
          split: validation
          args: stsb
        metrics:
          - name: Spearmanr
            type: spearmanr
            value: 0.8679004942016133

distilbert-base-uncased-finetuned-stsb

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

  • Loss: 0.5563
  • Pearson: 0.8708
  • Spearmanr: 0.8679

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Pearson Spearmanr
No log 1.0 360 0.6167 0.8601 0.8577
1.0026 2.0 720 0.6175 0.8670 0.8653
0.3862 3.0 1080 0.6439 0.8703 0.8675
0.3862 4.0 1440 0.5563 0.8708 0.8679
0.2514 5.0 1800 0.5616 0.8694 0.8659

Framework versions

  • Transformers 4.33.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3