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: 3.0329
• Rouge1: 16.3034
• Rouge2: 7.8192
• Rougel: 16.0316
• Rougelsum: 15.9173

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
7.0891	1.0	1209	3.2989	13.8686	6.1132	13.3657	13.3454
3.9283	2.0	2418	3.1443	16.3537	7.9374	15.8565	15.7281
3.5985	3.0	3627	3.1004	17.9042	9.1908	17.5268	17.385
3.4285	4.0	4836	3.0578	16.3118	8.4563	15.9252	15.9109
3.3222	5.0	6045	3.0587	17.5106	8.6579	17.2096	17.1079
3.2554	6.0	7254	3.0497	16.9153	8.0973	16.5874	16.4807
3.2085	7.0	8463	3.0309	16.3789	7.9306	16.1233	16.0097
3.1856	8.0	9672	3.0329	16.3034	7.8192	16.0316	15.9173

Framework versions

• Transformers 4.24.0
• Pytorch 1.12.1+cu113
• Datasets 2.7.1
• Tokenizers 0.13.2