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: 2.9624
• Rouge1: 13.5483
• Rouge2: 5.8705
• Rougel: 13.4874
• Rougelsum: 13.5096

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
6.0643	1.0	2201	3.1809	9.7343	3.3747	9.618	9.5626
3.6469	2.0	4402	3.0471	10.6825	3.6312	10.6077	10.6607
3.3978	3.0	6603	2.9941	11.3078	4.3662	11.2585	11.1503
3.2626	4.0	8804	2.9708	12.0216	4.1979	11.8896	11.8944
3.1728	5.0	11005	2.9692	12.905	4.8062	12.8674	12.8577
3.1046	6.0	13206	2.9618	13.3125	5.7428	13.2373	13.223
3.069	7.0	15407	2.9644	13.8965	6.0565	13.9164	13.8888
3.0409	8.0	17608	2.9624	13.5483	5.8705	13.4874	13.5096

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3