pegasus-reviews / README.md
ravinderbrai's picture
Training complete
3131d4e
metadata
base_model: google/pegasus-cnn_dailymail
tags:
  - summarization
  - generated_from_trainer
model-index:
  - name: pegasus-reviews
    results: []

pegasus-reviews

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: 4.3085

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: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 6

Training results

Training Loss Epoch Step Validation Loss
0.8541 1.0 1 4.3114
0.8178 2.0 2 4.3112
0.9366 3.0 3 4.3108
0.831 4.0 4 4.3102
0.8294 5.0 5 4.3094
0.2781 5.33 6 4.3085

Framework versions

  • Transformers 4.34.1
  • Pytorch 2.1.0
  • Datasets 2.12.0
  • Tokenizers 0.14.1