ptt5-small-portuguese-vocab-finetuned-xlsum-pt

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

• Loss: 0.0360
• 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
0.0787	1.0	125	0.0457	17.6273	16.731	17.6255	17.629
0.0428	2.0	250	0.0401	17.6273	16.731	17.6255	17.629
0.0367	3.0	375	0.0374	17.6273	16.731	17.6255	17.629
0.0336	4.0	500	0.0360	17.6273	16.731	17.6255	17.629
0.0316	5.0	625	0.0365	17.6273	16.731	17.6255	17.629
0.0299	6.0	750	0.0361	17.6273	16.731	17.6255	17.629
0.0293	7.0	875	0.0353	17.6273	16.731	17.6255	17.629
0.0283	8.0	1000	0.0362	17.6273	16.731	17.6255	17.629
0.0275	9.0	1125	0.0357	17.6273	16.731	17.6255	17.629
0.0274	10.0	1250	0.0360	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