README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
  - f1
widget:
  - text:
      - >-
        Yucaipa owned Dominick 's before selling the chain to Safeway in 1998
        for $ 2.5 billion.
      - >-
        Yucaipa bought Dominick's in 1995 for $ 693 million and sold it to
        Safeway for $ 1.8 billion in 1998.
    example_title: Not Equivalent
  - text:
      - >-
        In a statement , Mr. Rowland said :  As is the case with all appointees
        , Commissioner Anson is accountable to me .
      - >-
        As is the case with all appointees, Commissioner Anson is accountable to
        me, Rowland said .
    example_title: Equivalent
model-index:
  - name: platzi-distilroberta-base-mrpc-glue-franco-medina
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: glue
          type: glue
          config: mrpc
          split: validation
          args: mrpc
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8357843137254902
          - name: F1
            type: f1
            value: 0.8718929254302105

platzi-distilroberta-base-mrpc-glue-franco-medina

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

• Loss: 0.5966
• Accuracy: 0.8358
• F1: 0.8719

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: 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	Accuracy	F1
0.5343	1.09	500	0.4880	0.8309	0.8752
0.4025	2.18	1000	0.5966	0.8358	0.8719

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3