nort5-large-finetuned-norwegian

This model is a fine-tuned version of ltg/nort5-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.9237
• Rouge1: 23.7487
• Rouge2: 6.7301
• Rougel: 14.8509
• Rougelsum: 15.4894

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: 5.6e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
2.9348	1.0	18	2.6112	17.8464	3.5066	11.3712	11.5183
1.2006	2.0	36	2.4548	21.4194	5.3028	14.875	14.5553
0.7799	3.0	54	2.2980	24.4265	7.6063	17.1996	17.2811
0.5767	4.0	72	2.3304	29.6421	10.5432	21.2022	21.4957
0.4624	5.0	90	2.3195	28.8043	8.9197	19.7301	19.9298
0.4133	6.0	108	2.3266	29.6	9.4969	19.7972	19.8279

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1