metadata

license: apache-2.0
base_model: GuysTrans/bart-base-mini
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: bart-base-mini
    results: []

bart-base-mini

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

Loss: 2.5668
Rouge1: 7.0742
Rouge2: 1.8925
Rougel: 6.1211
Rougelsum: 6.976
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	Gen Len
1.9847	1.0	22880	2.5668	7.0742	1.8925	6.1211	6.976	20.0

Framework versions

Transformers 4.33.0
Pytorch 2.0.0
Datasets 2.1.0
Tokenizers 0.13.3