mt5-small-finetuned-amazon-en-es

This model is a fine-tuned version of google/mt5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.0656
• Rouge1: 15.6444
• Rouge2: 7.1213
• Rougel: 15.1199
• Rougelsum: 15.1977

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
7.1956	1.0	1209	3.3170	14.3233	5.9058	14.2101	14.1479
3.8992	2.0	2418	3.2469	17.2106	8.2802	16.5694	16.6279
3.6016	3.0	3627	3.1369	16.6585	8.3859	16.0162	16.0873
3.4161	4.0	4836	3.1090	16.4091	7.9873	15.9314	15.9518
3.3189	5.0	6045	3.0682	15.9424	7.1211	15.4668	15.4841
3.2496	6.0	7254	3.0482	15.8669	7.273	15.3226	15.363
3.1971	7.0	8463	3.0712	15.9518	7.2165	15.3741	15.4616
3.1778	8.0	9672	3.0656	15.6444	7.1213	15.1199	15.1977

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1