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: 3.0301
• Rouge1: 17.4531
• Rouge2: 9.0091
• Rougel: 17.0836
• Rougelsum: 17.1528

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
3.6834	1.0	1209	3.2483	15.494	7.8022	15.1402	15.2041
3.6689	2.0	2418	3.1014	16.6941	8.9493	15.9414	16.1157
3.4493	3.0	3627	3.0640	16.5731	8.2808	16.0156	16.1514
3.3175	4.0	4836	3.0375	16.8245	8.6021	16.2052	16.3956
3.2303	5.0	6045	3.0312	17.8902	9.7012	17.3184	17.5092
3.1693	6.0	7254	3.0255	16.985	8.7225	16.6058	16.7549
3.1357	7.0	8463	3.0235	17.015	9.0093	16.7306	16.9061
3.1073	8.0	9672	3.0301	17.4531	9.0091	17.0836	17.1528

Framework versions

• Transformers 4.32.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3