t5-small-finetuned-mlsum-de

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

• Loss: 1.6917
• Rouge1: 25.924
• Rouge2: 17.2398
• Rougel: 24.0239
• Rougelsum: 24.6845
• Gen Len: 18.9879

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: 32
• eval_batch_size: 32
• 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
0.9987	1.0	6899	1.7184	25.6352	17.0364	23.7635	24.4065	18.9903
0.9624	2.0	13798	1.6996	25.8132	17.1732	23.9131	24.5744	18.9885
0.9902	3.0	20697	1.6917	25.924	17.2398	24.0239	24.6845	18.9879

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1