nor-sum

This model is a fine-tuned version of sshleifer/distilbart-cnn-6-6 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.1812
• Rouge1: 0.2552
• Rouge2: 0.0679
• Rougel: 0.1884
• Rougelsum: 0.1886
• Gen Len: 65.3086

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.6231	1.0	3188	2.4652	0.2359	0.0563	0.1732	0.1733	66.1928
2.3062	2.0	6377	2.2798	0.2524	0.0653	0.1864	0.1864	66.3107
2.0817	3.0	9565	2.1973	0.2529	0.0675	0.189	0.1893	65.077
1.9776	4.0	12752	2.1812	0.2552	0.0679	0.1884	0.1886	65.3086

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.1
• Tokenizers 0.13.3