Edit model card

bart-large-cnn-finetuned-roundup-4-4

This model is a fine-tuned version of facebook/bart-large-cnn on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7912
  • Rouge1: 53.8175
  • Rouge2: 35.1335
  • Rougel: 38.0823
  • Rougelsum: 51.2925
  • Gen Len: 142.0

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

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
No log 1.0 398 0.9455 52.8137 33.4924 35.5866 50.7208 142.0
1.1309 2.0 796 0.8397 54.0923 35.0799 37.4609 51.5914 142.0
0.6902 3.0 1194 0.7932 53.5752 35.0842 37.9295 51.0356 142.0
0.4951 4.0 1592 0.7912 53.8175 35.1335 38.0823 51.2925 142.0

Framework versions

  • Transformers 4.18.0
  • Pytorch 1.11.0+cu113
  • Datasets 2.1.0
  • Tokenizers 0.12.1
Downloads last month
2