Hugging Face's logo

navsad
/
navid_test_bert

Text Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
4
navid_test_bert / README.md
lewtun's picture
lewtun HF staff
Add evaluation results on the cola config and validation split of glue
982b82e
preview code
|
raw
history blame
2.5 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - matthews_correlation
model-index:
  - name: navid_test_bert
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: glue
          type: glue
          args: cola
        metrics:
          - name: Matthews Correlation
            type: matthews_correlation
            value: 0.5834463254140851
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: glue
          type: glue
          config: cola
          split: validation
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8312559923298178
            verified: true
          - name: Precision
            type: precision
            value: 0.8376703841387856
            verified: true
          - name: Recall
            type: recall
            value: 0.9375866851595007
            verified: true
          - name: AUC
            type: auc
            value: 0.8870185473936304
            verified: true
          - name: F1
            type: f1
            value: 0.8848167539267016
            verified: true
          - name: loss
            type: loss
            value: 0.815069854259491
            verified: true

navid_test_bert

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

  • Loss: 0.8149
  • Matthews Correlation: 0.5834

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: 8
  • 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

Training results

Training Loss Epoch Step Validation Loss Matthews Correlation
0.4598 1.0 1069 0.4919 0.5314
0.3228 2.0 2138 0.6362 0.5701
0.17 3.0 3207 0.8149 0.5834

Framework versions

  • Transformers 4.16.2
  • Pytorch 1.10.0+cu111
  • Datasets 1.18.2
  • Tokenizers 0.11.0