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: 3.0229
• Rouge1: 17.552
• Rouge2: 8.6159
• Rougel: 17.3207
• Rougelsum: 17.1968

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
3.6836	1.0	1209	3.2362	17.2827	8.6322	16.7811	16.7223
3.6489	2.0	2418	3.0808	17.7206	8.7236	17.0749	16.9989
3.4263	3.0	3627	3.0574	17.9532	9.55	17.604	17.4782
3.3129	4.0	4836	3.0444	16.8908	8.1947	16.3227	16.2468
3.2353	5.0	6045	3.0449	17.0334	8.1498	16.8367	16.6738
3.1678	6.0	7254	3.0326	18.197	9.3959	18.0328	17.86
3.1365	7.0	8463	3.0276	17.8769	9.1995	17.5326	17.4261
3.1118	8.0	9672	3.0229	17.552	8.6159	17.3207	17.1968

Framework versions

• Transformers 4.26.0
• Pytorch 1.13.1+cu116
• Datasets 2.8.0
• Tokenizers 0.13.2