Edit model card

bart-base-cnn-xsum-cite-swe

This model is a fine-tuned version of Gabriel/bart-base-cnn-xsum-swe on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.4203
  • Rouge1: 29.6279
  • Rouge2: 11.5697
  • Rougel: 24.2429
  • Rougelsum: 24.4557
  • Gen Len: 19.9371

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
  • gradient_accumulation_steps: 2
  • 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: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
2.4833 1.0 2558 2.4203 29.6279 11.5697 24.2429 24.4557 19.9371

Framework versions

  • Transformers 4.22.2
  • Pytorch 1.12.1+cu113
  • Datasets 2.5.1
  • Tokenizers 0.12.1
Downloads last month
13

Dataset used to train Gabriel/bart-base-cnn-xsum-cite-swe

Evaluation results