pegasus-newsroom-summarizer_30216

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: 0.9637
• Rouge1: 52.0929
• Rouge2: 34.6709
• Rougel: 41.1615
• Rougelsum: 48.4141
• Gen Len: 102.017

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
1.0592	1.0	12086	0.9743	51.6187	34.1687	40.5959	47.9305	104.3352
0.9742	2.0	24172	0.9647	52.1837	34.7301	41.2599	48.4955	101.2771
0.9371	3.0	36258	0.9637	52.0929	34.6709	41.1615	48.4141	102.017

Framework versions

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