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: 3.0132
• Rouge1: 16.4719
• Rouge2: 7.9366
• Rougel: 16.2123
• Rougelsum: 16.2853

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
• distributed_type: multi-GPU
• 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
3.9249	1.0	1209	3.1904	15.8207	8.0555	15.4584	15.648
3.5688	2.0	2418	3.0812	16.3271	8.1479	15.9001	16.0134
3.3905	3.0	3627	3.0442	15.9864	7.295	15.4247	15.5848
3.2728	4.0	4836	3.0304	16.2893	7.5851	15.9494	16.0117
3.1958	5.0	6045	3.0169	15.4888	7.4495	15.2244	15.2326
3.1359	6.0	7254	3.0158	16.3866	8.2218	16.0625	16.0953
3.1059	7.0	8463	3.0075	15.9134	7.8387	15.626	15.6499
3.0852	8.0	9672	3.0132	16.4719	7.9366	16.2123	16.2853

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu117
• Datasets 2.12.0
• Tokenizers 0.13.2