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: 3.0361
• Rouge1: 16.5633
• Rouge2: 7.8215
• Rougel: 16.1196
• Rougelsum: 16.1733

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_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
7.2216	1.0	1209	3.2970	13.3481	5.5941	13.1485	13.1056
3.9167	2.0	2418	3.1679	16.1864	7.5841	15.64	15.829
3.5934	3.0	3627	3.1141	17.8204	8.7044	17.1378	17.2288
3.4304	4.0	4836	3.0893	17.0632	8.4519	16.3722	16.4902
3.3234	5.0	6045	3.0502	17.6037	8.5541	17.0038	17.1642
3.2554	6.0	7254	3.0455	17.5434	8.4389	17.0173	17.0904
3.2126	7.0	8463	3.0374	17.0439	8.0657	16.5776	16.6909
3.1864	8.0	9672	3.0361	16.5633	7.8215	16.1196	16.1733

Framework versions

• Transformers 4.57.3
• Pytorch 2.9.1+cu130
• Datasets 3.6.0
• Tokenizers 0.22.1