distilbart-cnn-12-6-finetuned-roundup-4-4

This model is a fine-tuned version of sshleifer/distilbart-cnn-12-6 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.9444
• Rouge1: 53.2401
• Rouge2: 33.8737
• Rougel: 36.4695
• Rougelsum: 50.8979
• Gen Len: 141.5185

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

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	398	1.1590	52.4465	33.664	35.2295	50.0326	141.6852
1.4068	2.0	796	1.0174	53.3143	34.1363	35.8354	51.2277	141.8889
0.9247	3.0	1194	0.9575	52.7672	33.1797	35.9617	50.3643	142.0
0.731	4.0	1592	0.9444	53.2401	33.8737	36.4695	50.8979	141.5185

Framework versions

• Transformers 4.18.0
• Pytorch 1.11.0+cu113
• Datasets 2.1.0
• Tokenizers 0.12.1