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: 3.0357
• Rouge1: 17.1269
• Rouge2: 8.2287
• Rougel: 16.5766
• Rougelsum: 16.5551

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
6.5252	1.0	1209	3.3096	13.9556	5.7543	13.5465	13.5156
3.9131	2.0	2418	3.1712	16.6317	8.4008	16.1719	16.0248
3.5892	3.0	3627	3.1078	16.9908	8.8871	16.4323	16.4496
3.4227	4.0	4836	3.0850	17.6382	9.2124	17.0876	16.9337
3.3185	5.0	6045	3.0580	17.3244	8.7532	16.7803	16.746
3.251	6.0	7254	3.0404	16.9059	7.9694	16.2362	16.1888
3.2086	7.0	8463	3.0362	17.2803	8.1514	16.6794	16.6264
3.1737	8.0	9672	3.0357	17.1269	8.2287	16.5766	16.5551

Framework versions

• Transformers 4.57.3
• Pytorch 2.9.0+cu128
• Datasets 4.4.1
• Tokenizers 0.22.1