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: 3.1185
• Rouge1: 17.2081
• Rouge2: 8.8374
• Rougel: 16.8033
• Rougelsum: 16.663

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: 32
• eval_batch_size: 32
• 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
No log	1.0	303	3.9821	8.3993	2.0894	8.1427	8.135
No log	2.0	606	3.3511	13.1381	5.7193	12.8494	12.8375
No log	3.0	909	3.2235	15.2502	6.5903	14.728	14.612
5.8943	4.0	1212	3.1695	16.1725	8.1638	15.7655	15.6068
5.8943	5.0	1515	3.1579	16.3126	7.9727	15.8308	15.7236
5.8943	6.0	1818	3.1346	16.8323	8.088	16.3863	16.3343
5.8943	7.0	2121	3.1181	16.965	8.5799	16.6418	16.5064
3.7097	8.0	2424	3.1185	17.2081	8.8374	16.8033	16.663

Framework versions

• Transformers 4.15.0
• Pytorch 1.10.1
• Datasets 1.17.0
• Tokenizers 0.10.3