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: 13.0523
• Rouge1: 0.6901
• Rouge2: 0.0
• Rougel: 0.7131
• Rougelsum: 0.6901

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
20.4138	1.0	11	17.0350	0.3221	0.0	0.3221	0.3221
20.9666	2.0	22	15.8389	0.3221	0.0	0.3221	0.3221
20.3285	3.0	33	14.7984	0.6901	0.0	0.7131	0.6901
20.2575	4.0	44	13.7555	0.6901	0.0	0.7131	0.6901
19.3567	5.0	55	13.0846	0.6901	0.0	0.7131	0.6901
19.568	6.0	66	13.0045	0.6901	0.0	0.7131	0.6901
18.6292	7.0	77	13.0753	0.3221	0.0	0.3221	0.3221
18.4457	8.0	88	13.0523	0.6901	0.0	0.7131	0.6901

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3