my_awesome_xlsum_model

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

• Loss: 2.5400
• Rouge1: 0.3969
• Rouge2: 0.1692
• Rougel: 0.2607
• Gen Len: 92.422

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: 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: 6
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Gen Len
1.6518	1.0	1185	2.5537	0.394	0.1661	0.2582	93.3638
1.6179	2.0	2370	2.5472	0.396	0.1683	0.2605	93.2167
1.6244	3.0	3555	2.5424	0.3976	0.1697	0.2616	92.9717
1.6094	4.0	4740	2.5427	0.3964	0.1687	0.2605	92.612
1.6191	5.0	5925	2.5421	0.3971	0.1688	0.2603	92.6815
1.6063	6.0	7110	2.5400	0.3969	0.1692	0.2607	92.422

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.2+cu118
• Datasets 2.18.0
• Tokenizers 0.15.2