cleaned_ds / README.md
Musab-Bin-Nadeem's picture
End of training
8f52932 verified
metadata
library_name: transformers
license: apache-2.0
base_model: sshleifer/distilbart-cnn-12-6
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: cleaned_ds
    results: []

cleaned_ds

This model is a fine-tuned version of sshleifer/distilbart-cnn-12-6 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 4.2803
  • Rouge1: 0.2705
  • Rouge2: 0.0363
  • Rougel: 0.1609
  • Rougelsum: 0.1609
  • Generated Length: 113.0

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
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Generated Length
No log 1.0 1 4.5060 0.2826 0.0384 0.1694 0.1694 95.0
No log 2.0 2 4.3368 0.2832 0.0333 0.1701 0.1701 82.0
No log 3.0 3 4.2803 0.2705 0.0363 0.1609 0.1609 113.0

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.0
  • Tokenizers 0.19.1