Eje2 / README.md
IsraelRam's picture
Model save
f802c49
metadata
license: apache-2.0
base_model: distilroberta-base
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
  - f1
model-index:
  - name: Eje2
    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: 0.8862478777589134

Eje2

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

  • Loss: 0.7123
  • Accuracy: 0.8358
  • F1: 0.8862

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
0.5337 1.09 500 0.3729 0.8480 0.8877
0.3434 2.18 1000 0.7123 0.8358 0.8862

Framework versions

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