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: 3.1419
• Rouge1: 15.5934
• Rouge2: 5.6761
• Rougel: 14.9619
• Rougelsum: 14.9916

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: 32
• eval_batch_size: 32
• 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
No log	1.0	303	4.1931	5.7223	1.2656	5.5538	5.5575
No log	2.0	606	3.3284	10.6092	2.2017	10.4709	10.4227
No log	3.0	909	3.2566	13.6575	4.6938	13.3543	13.3219
5.92	4.0	1212	3.1976	13.9965	4.9638	13.4642	13.4203
5.92	5.0	1515	3.1850	15.6112	5.0982	14.8932	14.8245
5.92	6.0	1818	3.1602	14.9109	5.2255	14.4425	14.3098
5.92	7.0	2121	3.1454	15.5771	5.8869	15.006	15.002
3.7023	8.0	2424	3.1419	15.5934	5.6761	14.9619	14.9916

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3