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: 3.0348
• Rouge1: 17.5116
• Rouge2: 8.5034
• Rougel: 17.2199
• Rougelsum: 17.0937

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
6.6706	1.0	1209	3.3114	13.1025	4.546	12.6485	12.5756
3.9103	2.0	2418	3.1923	16.1192	8.3043	15.7004	15.6132
3.5937	3.0	3627	3.0927	17.9684	9.2115	17.5115	17.4098
3.4088	4.0	4836	3.0605	17.8543	8.4785	17.2866	17.1586
3.3178	5.0	6045	3.0501	16.029	7.6078	15.5929	15.4296
3.2438	6.0	7254	3.0422	16.645	8.345	16.3489	16.1929
3.2005	7.0	8463	3.0404	16.6148	7.5599	16.2553	16.1232
3.1792	8.0	9672	3.0348	17.5116	8.5034	17.2199	17.0937

Framework versions

• Transformers 4.33.0.dev0
• Pytorch 2.0.0+cu117
• Datasets 2.14.4
• Tokenizers 0.13.3