dhivyeshrk/bart-large-cnn-samsum

pegasus-samsum

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

• Loss: 1.4963

Model description

Original bart (Bidirectional Auto Regressive Transformers) paper : https://arxiv.org/abs/1910.13461

Training and evaluation data

Fine-Tuned over 1 epoch. The improvements over facebook/bart-large-cnn over the rouge benchmark is as follows :
Rouge1 : 30.6 %
Rouge2 : 103 %
RougeL : 33.18 %
RougeLSum : 33.18 %

Training procedure

Please refer to https://github.com/dhivyeshrk/FineTuning-Facebook-bart-large-cnn

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.3689	0.54	500	1.4963

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.13.3