t5-small-finetuned-xsum-xlsum

This model is a fine-tuned version of t5-small on the scientific_papers dataset. It achieves the following results on the evaluation set:

• Loss: 1.9963
• Rouge1: 14.3541
• Rouge2: 6.1674
• Rougel: 12.2975
• Rougelsum: 13.2515
• Gen Len: 19.0

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: 16
• eval_batch_size: 16
• 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
2.3055	1.0	7496	2.0773	14.3312	6.153	12.2551	13.2033	19.0
2.2512	2.0	14992	2.0330	14.3048	6.1346	12.2343	13.1992	19.0
2.2034	3.0	22488	2.0106	14.3866	6.1752	12.3205	13.2743	19.0
2.2054	4.0	29984	2.0004	14.3629	6.167	12.2928	13.2506	19.0
2.1944	5.0	37480	1.9963	14.3541	6.1674	12.2975	13.2515	19.0

Framework versions

• Transformers 4.24.0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1
• Tokenizers 0.13.2