ptt5-base-portuguese-vocab-finetuned-xlsum-pt

This model is a fine-tuned version of unicamp-dl/ptt5-base-portuguese-vocab on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0394
• Rouge1: 17.6273
• Rouge2: 16.731
• Rougel: 17.6255
• Rougelsum: 17.629

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
0.0596	1.0	125	0.0352	17.6273	16.731	17.6255	17.629
0.0314	2.0	250	0.0324	17.6273	16.731	17.6255	17.629
0.0248	3.0	375	0.0312	17.6273	16.731	17.6255	17.629
0.0213	4.0	500	0.0328	17.6273	16.731	17.6255	17.629
0.0177	5.0	625	0.0322	17.6273	16.731	17.6255	17.629
0.0153	6.0	750	0.0346	17.6273	16.731	17.6255	17.629
0.0139	7.0	875	0.0379	17.6273	16.731	17.6255	17.629
0.0125	8.0	1000	0.0360	17.6273	16.731	17.6255	17.629
0.0113	9.0	1125	0.0372	17.6273	16.731	17.6255	17.629
0.0112	10.0	1250	0.0394	17.6273	16.731	17.6255	17.629

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2