distilbart-cnn-12-6-rate-prof

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: 1.0922
• Rouge1: 0.3041
• Rouge2: 0.1196
• Rougel: 0.2229
• Rougelsum: 0.2241
• Gen Len: 66.9333

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: 1e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	68	1.1530	0.2844	0.0943	0.204	0.2027	67.8
No log	2.0	136	1.0948	0.2614	0.0498	0.1672	0.168	67.8
No log	3.0	204	1.0797	0.3042	0.0983	0.2068	0.2082	66.6667
No log	4.0	272	1.0808	0.2932	0.0914	0.2012	0.2024	67.1333
No log	5.0	340	1.0922	0.3041	0.1196	0.2229	0.2241	66.9333

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3