mt5-base-finetuned-cnn-dm

This model is a fine-tuned version of google/mt5-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.9004
• Rouge1: 22.89
• Rouge2: 9.473
• Rougel: 19.8849
• Rougelsum: 20.5077

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: 5e-05
• train_batch_size: 16
• eval_batch_size: 16
• 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
• lr_scheduler_warmup_steps: 500
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
2.6876	1.4526	5000	2.3189	21.7323	8.9826	19.4447	20.3889
2.5444	2.9053	10000	2.2517	22.2631	9.3492	19.8828	20.8966

Framework versions

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