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: 3.0303
• Rouge1: 16.5852
• Rouge2: 7.6579
• Rougel: 16.124
• Rougelsum: 15.9936

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
6.9675	1.0	1209	3.2986	15.4048	6.9451	14.8606	14.7973
3.8997	2.0	2418	3.1665	16.3162	7.7266	15.7977	15.7097
3.5826	3.0	3627	3.1106	17.1709	8.5204	16.4245	16.3642
3.421	4.0	4836	3.0963	17.3478	8.785	16.7929	16.6929
3.3089	5.0	6045	3.0490	16.7208	7.6362	16.1295	16.0292
3.2437	6.0	7254	3.0401	16.6134	7.9347	16.0422	15.8593
3.2133	7.0	8463	3.0292	16.2514	7.6585	15.9708	15.8423
3.1851	8.0	9672	3.0303	16.5852	7.6579	16.124	15.9936

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Tokenizers 0.20.3