mt5-small-google-finetuned-amazon-en-es

This model is a fine-tuned version of akahana/mt5-small-google on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 6.3094
• Model Preparation Time: 0.0043
• Rouge1: 3.9907
• Rouge2: 0.0
• Rougel: 3.728
• Rougelsum: 3.7451

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	Model Preparation Time	Rouge1	Rouge2	Rougel	Rougelsum
36.3235	1.0	1209	10.4603	0.0043	1.9526	0.0	1.9645	1.9549
10.1253	2.0	2418	7.8354	0.0043	2.7987	0.0	2.738	2.7197
8.2571	3.0	3627	7.1225	0.0043	2.7838	0.0	2.7297	2.7215
7.5278	4.0	4836	6.7621	0.0043	3.6597	0.0	3.4788	3.4724
7.1356	5.0	6045	6.5444	0.0043	3.8173	0.0	3.5713	3.5866
6.8907	6.0	7254	6.3968	0.0043	3.8173	0.0	3.5334	3.5352
6.753	7.0	8463	6.3399	0.0043	3.9907	0.0	3.728	3.7451
6.6743	8.0	9672	6.3094	0.0043	3.9907	0.0	3.728	3.7451

Framework versions

• Transformers 4.54.1
• Pytorch 2.5.1+cu121
• Datasets 4.0.0
• Tokenizers 0.21.4