mt5-small-RecetasdelaAbuela-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: 0.1833
• Rouge1: 80.0
• Rouge2: 61.5385
• Rougel: 80.0
• Rougelsum: 80.0

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 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
1.4237	1.0	2024	0.2535	80.0	61.5385	80.0	80.0
0.2757	2.0	4048	0.2099	80.0	61.5385	80.0	80.0
0.2417	3.0	6072	0.1991	80.0	61.5385	80.0	80.0
0.224	4.0	8096	0.1927	80.0	61.5385	80.0	80.0
0.2165	5.0	10120	0.1875	80.0	61.5385	80.0	80.0
0.2076	6.0	12144	0.1858	80.0	61.5385	80.0	80.0
0.2042	7.0	14168	0.1837	80.0	61.5385	80.0	80.0
0.2005	8.0	16192	0.1833	80.0	61.5385	80.0	80.0

Framework versions

• Transformers 4.50.2
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1