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: 3.0150
• Rouge1: 16.6244
• Rouge2: 7.4737
• Rougel: 16.2514
• Rougelsum: 16.3475

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 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
3.3536	1.0	1209	3.1069	17.673	8.5372	17.1607	17.1184
3.3641	2.0	2418	3.0533	17.2312	8.728	16.7626	16.7101
3.2384	3.0	3627	3.0481	15.9593	7.8483	15.7221	15.8227
3.1555	4.0	4836	3.0504	16.3465	7.9873	15.9367	15.9714
3.0826	5.0	6045	3.0267	16.285	7.4032	15.7749	15.8915
3.0396	6.0	7254	3.0217	16.5194	7.6637	16.1961	16.214
3.0181	7.0	8463	3.0122	16.068	7.2738	15.7885	15.8982
2.9965	8.0	9672	3.0150	16.6244	7.4737	16.2514	16.3475

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3