vickt's picture
End of training
cc5d478
metadata
base_model: google/pegasus-cnn_dailymail
tags:
  - generated_from_trainer
metrics:
  - rouge
  - precision
  - recall
  - f1
model-index:
  - name: PEGASUS_CNNDM_ORIGIN
    results: []

PEGASUS_CNNDM_ORIGIN

This model is a fine-tuned version of google/pegasus-cnn_dailymail on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.7525
  • Rouge1: 0.3585
  • Rouge2: 0.1596
  • Rougel: 0.2651
  • Rougelsum: 0.2651
  • Gen Len: 57.9427
  • Precision: 0.8769
  • Recall: 0.8915
  • F1: 0.884

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: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len Precision Recall F1
1.0026 1.0 625 1.7480 0.3556 0.1565 0.2627 0.2629 57.9482 0.8764 0.8909 0.8835
0.9045 2.0 1250 1.7525 0.3585 0.1596 0.2651 0.2651 57.9427 0.8769 0.8915 0.884

Framework versions

  • Transformers 4.36.0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.5
  • Tokenizers 0.15.0