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: 3.0314
• Rouge1: 12.1887
• Rouge2: 5.0349
• Rougel: 11.9609
• Rougelsum: 11.9035

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 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
6.5509	1.0	1209	3.2944	10.1651	2.3944	9.8582	9.904
3.9082	2.0	2418	3.1770	12.5331	5.3519	12.3313	12.386
3.5985	3.0	3627	3.1019	12.6027	5.5032	12.4595	12.4211
3.4283	4.0	4836	3.0808	12.6623	5.6897	12.505	12.421
3.3176	5.0	6045	3.0667	12.9332	5.3428	12.6202	12.5254
3.2425	6.0	7254	3.0449	11.891	4.7626	11.622	11.5941
3.205	7.0	8463	3.0273	11.9972	5.1009	11.8661	11.7716
3.1671	8.0	9672	3.0314	12.1887	5.0349	11.9609	11.9035

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu126
• Datasets 3.3.2
• Tokenizers 0.21.1