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: 3.0135
• Rouge1: 16.5421
• Rouge2: 7.9012
• Rougel: 16.2574
• Rougelsum: 16.1537

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
3.4509	1.0	1209	3.1308	17.5055	8.164	16.9714	16.8977
3.4226	2.0	2418	3.0489	16.7302	8.1598	16.3268	16.3168
3.286	3.0	3627	3.0366	16.7244	7.9017	16.3893	16.3728
3.1859	4.0	4836	3.0219	16.9671	8.0508	16.6206	16.5261
3.1249	5.0	6045	3.0353	17.3032	8.0195	16.9664	16.972
3.0665	6.0	7254	3.0272	17.0115	7.88	16.7424	16.7476
3.0407	7.0	8463	3.0122	17.3339	8.0171	16.9919	16.9449
3.0248	8.0	9672	3.0135	16.5421	7.9012	16.2574	16.1537

Framework versions

• Transformers 4.29.1
• Pytorch 1.13.1
• Datasets 2.12.0
• Tokenizers 0.13.3