mt5-small-finetuned-amazon-en-es

This model is a fine-tuned version of google/mt5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.0328
• Rouge1: 16.4389
• Rouge2: 8.0419
• Rougel: 16.2131
• Rougelsum: 16.0484

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_fused 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
7.1842	1.0	1209	3.3246	15.0089	6.5237	14.4095	14.2924
3.9146	2.0	2418	3.1735	16.7976	8.3402	16.3224	16.0651
3.6022	3.0	3627	3.1338	17.795	9.0478	17.2897	17.1568
3.4148	4.0	4836	3.0935	18.0448	9.1484	17.525	17.3333
3.3189	5.0	6045	3.0602	16.6951	7.8279	16.1867	15.9983
3.2451	6.0	7254	3.0384	16.1576	7.7209	15.9061	15.6342
3.2012	7.0	8463	3.0337	16.3761	8.0505	16.1882	16.0124
3.1719	8.0	9672	3.0328	16.4389	8.0419	16.2131	16.0484

Framework versions

• Transformers 4.57.1
• Pytorch 2.8.0+cu128
• Datasets 3.5.0
• Tokenizers 0.22.1