mt5-base-cnn_then_norsumm

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.8705
• Rouge1: 30.0222
• Rouge2: 12.8189
• Rougel: 22.7383
• Rougelsum: 26.5718

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: 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
2.5087	1.0	18	3.0861	27.0039	9.4951	19.8448	24.6014
2.5952	2.0	36	3.0623	28.0269	9.9808	20.5307	25.5142
2.6155	3.0	54	3.0309	28.7776	9.5968	20.5973	25.3272
2.6171	4.0	72	3.0298	28.458	10.1857	20.6671	25.4602
2.5156	5.0	90	3.0293	29.1667	11.0558	21.6151	26.3694

Framework versions

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