finetuned-bert-mrpc / README.md
oumeima's picture
add model
63d0302
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
  - f1
model_index:
  - name: finetuned-bert-mrpc
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: glue
          type: glue
          args: mrpc
        metric:
          name: F1
          type: f1
          value: 0.9003322259136212

finetuned-bert-mrpc

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: 0.5280
  • Accuracy: 0.8529
  • F1: 0.9003

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: 3.0

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
0.5704 1.0 230 0.4204 0.7917 0.8542
0.3391 2.0 460 0.4157 0.8456 0.8955
0.1923 3.0 690 0.5280 0.8529 0.9003

Framework versions

  • Transformers 4.9.2
  • Pytorch 1.9.0+cu102
  • Datasets 1.11.0
  • Tokenizers 0.10.3