thesis-bart-finetuned-on-original-wcep

This model is a fine-tuned version of sshleifer/distilbart-cnn-6-6 on the wcep-10 dataset. It achieves the following results on the evaluation set:

• Loss: 1.9981
• Rouge1: 37.2224
• Rouge2: 16.5575
• Rougel: 26.7904
• Rougelsum: 30.3497
• Gen Len: 67.5627

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: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.0801	1.0	510	2.0119	36.4915	16.0165	26.3565	29.7397	67.9882
1.7597	2.0	1020	1.9868	36.9513	16.3776	26.4974	30.1234	68.3961
1.5997	3.0	1530	1.9981	37.2224	16.5575	26.7904	30.3497	67.5627

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2