mt5-small-finetuned-amazon-en-es

This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.7408
• Rouge1: 11.6009
• Rouge2: 2.8728
• Rougel: 11.8004
• Rougelsum: 11.9188

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
12.338	1.0	300	5.2256	4.1224	1.2022	4.1645	4.2077
5.5954	2.0	600	3.9721	9.005	2.1934	9.133	9.2792
4.5559	3.0	900	3.8552	9.5807	2.6302	9.511	9.5471
4.1858	4.0	1200	3.8014	10.8843	2.9462	10.9298	11.1352
3.9963	5.0	1500	3.7575	13.0171	4.7986	13.0233	12.9146
3.884	6.0	1800	3.7491	11.6897	2.8728	11.8886	12.0365
3.8293	7.0	2100	3.7408	11.4003	2.8728	11.5425	11.6537
3.7902	8.0	2400	3.7408	11.6009	2.8728	11.8004	11.9188

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Tokenizers 0.20.3