pegasus-newsroom_wires_hdwriter42k

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

• Loss: 1.5521
• Rouge1: 37.5311
• Rouge2: 17.6638
• Rougel: 31.2287
• Rougelsum: 31.7152
• Gen Len: 35.1639

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
1.662	1.0	16875	1.5702	36.8068	17.3179	30.6952	31.1331	36.4668
1.5071	2.0	33750	1.5503	37.5627	17.6519	31.2538	31.7985	35.3514
1.4512	3.0	50625	1.5521	37.5311	17.6638	31.2287	31.7152	35.1639

Framework versions

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