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: 2.7874
• Rouge1: 18.5523
• Rouge2: 10.0675
• Rougel: 17.5229
• Rougelsum: 17.5494

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
4.1365	1.0	611	3.0261	17.3417	8.0201	17.0052	17.1328
3.8953	2.0	1222	2.8934	17.6971	8.8023	16.726	16.9165
3.6211	3.0	1833	2.8633	19.8278	10.349	18.782	18.9807
3.4721	4.0	2444	2.8363	17.9441	9.9183	16.9501	16.9501
3.3561	5.0	3055	2.8246	17.5136	9.1469	16.4998	16.5171
3.2596	6.0	3666	2.8041	18.4253	10.0062	17.4766	17.5163
3.2331	7.0	4277	2.7885	18.2069	10.3961	17.2279	17.2918
3.1979	8.0	4888	2.7874	18.5523	10.0675	17.5229	17.5494

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu126
• Datasets 3.6.0
• Tokenizers 0.22.1