metadata

license: apache-2.0
base_model: facebook/bart-base
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: bart-base-re-attention-mini-seq-512
    results: []

bart-base-re-attention-mini-seq-512

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

Loss: 10.8199
Rouge1: 0.6673
Rouge2: 0.0021
Rougel: 0.6475
Rougelsum: 0.6688
Gen Len: 15.0368

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	Gen Len
5.9784	1.0	2920	10.8199	0.6673	0.0021	0.6475	0.6688	15.0368

Framework versions

Transformers 4.34.1
Pytorch 2.1.0+cu118
Datasets 2.14.5
Tokenizers 0.14.1