mt5-small-finetuned-amazon-en-es

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

• Loss: 2.7039
• Rouge1: 18.8926
• Rouge2: 9.9716
• Rougel: 18.0984
• Rougelsum: 17.9782

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 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: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
4.018	1.0	611	2.8602	16.5049	7.8577	16.0553	15.8568
3.6801	2.0	1222	2.8070	14.4434	6.6539	14.122	13.817
3.4617	3.0	1833	2.7783	16.0718	7.8726	15.359	15.1215
3.3465	4.0	2444	2.7362	17.127	8.8774	16.4322	16.2438
3.2436	5.0	3055	2.7196	18.8253	9.9968	17.9656	17.9366
3.1844	6.0	3666	2.7137	18.8923	10.3424	18.215	18.1285
3.1241	7.0	4277	2.7102	18.3392	9.795	17.6282	17.4866
3.1074	8.0	4888	2.7039	18.8926	9.9716	18.0984	17.9782

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3