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: 3.0056
• Rouge1: 16.1556
• Rouge2: 8.8085
• Rougel: 15.8019
• Rougelsum: 15.7787

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
6.9474	1.0	1399	3.3187	11.4251	4.57	10.9308	10.7649
3.892	2.0	2798	3.1469	13.4445	6.2409	13.013	12.9006
3.5863	3.0	4197	3.0734	15.1812	8.3203	14.7922	14.7632
3.4229	4.0	5596	3.0587	16.1014	8.4524	15.8047	15.7134
3.326	5.0	6995	3.0234	17.153	9.3495	16.6487	16.564
3.2622	6.0	8394	3.0144	15.5588	8.1691	15.275	15.2065
3.2163	7.0	9793	3.0139	15.8487	8.6641	15.548	15.511
3.1948	8.0	11192	3.0056	16.1556	8.8085	15.8019	15.7787

Framework versions

• Transformers 4.55.4
• Pytorch 2.8.0+cu128
• Datasets 4.0.0
• Tokenizers 0.21.4