pegasus-multi_news_wires_hdwriter42k

This model is a fine-tuned version of google/pegasus-multi_news on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.6427
• Rouge1: 37.3045
• Rouge2: 17.2478
• Rougel: 30.7768
• Rougelsum: 31.3514
• Gen Len: 34.6955

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: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.7914	1.0	16875	1.6849	36.6608	17.005	30.4166	30.9289	35.4077
1.6658	2.0	33750	1.6452	37.2837	17.3162	30.8358	31.3382	34.7757
1.5478	3.0	50625	1.6427	37.3045	17.2478	30.7768	31.3514	34.6955

Framework versions

• Transformers 4.23.1
• Pytorch 1.12.1+cu113
• Datasets 2.6.1
• Tokenizers 0.13.1