bart_summarisation / README.md
MeetK's picture
bart_summarisation
2e8164a
|
raw
history blame
1.66 kB
metadata
license: apache-2.0
base_model: MeetK/bart_summarisation
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: bart_summarisation
    results: []

bart_summarisation

This model is a fine-tuned version of MeetK/bart_summarisation on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.8662
  • Rouge1: 0.3202
  • Rouge2: 0.1186
  • Rougel: 0.2291
  • Rougelsum: 0.229
  • Gen Len: 63.321

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

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
No log 1.0 313 1.8355 0.3173 0.1175 0.2289 0.2288 63.492
1.5858 2.0 626 1.8662 0.3202 0.1186 0.2291 0.229 63.321

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.1+cpu
  • Datasets 2.15.0
  • Tokenizers 0.15.0