GuysTrans's picture
End of training
4958f2e
metadata
license: apache-2.0
base_model: GuysTrans/bart-base-finetuned-xsum
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: bart-base-generation
    results: []

bart-base-generation

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

  • Loss: 1.0932
  • Rouge1: 17.1543
  • Rouge2: 12.9074
  • Rougel: 16.512
  • Rougelsum: 16.9278
  • Bleu-1: 0.0079
  • Bleu-2: 0.0073
  • Bleu-3: 0.007
  • Bleu-4: 0.0068
  • Gen Len: 20.0

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Bleu-1 Bleu-2 Bleu-3 Bleu-4 Gen Len
2.1136 1.0 28600 1.0932 17.1543 12.9074 16.512 16.9278 0.0079 0.0073 0.007 0.0068 20.0

Framework versions

  • Transformers 4.33.0
  • Pytorch 2.0.0
  • Datasets 2.1.0
  • Tokenizers 0.13.3