punctuation-nilc-t5-base

This model is a fine-tuned version of unicamp-dl/ptt5-base-portuguese-vocab on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0432
• Bleu: 26.0973
• Gen Len: 18.8694

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: 5e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
0.0544	1.0	4686	0.0442	25.989	18.8655
0.0367	2.0	9372	0.0371	25.9358	18.8713
0.0222	3.0	14058	0.0374	25.8976	18.8694
0.0152	4.0	18744	0.0409	26.1575	18.8694
0.0147	5.0	23430	0.0432	26.0973	18.8694

Framework versions

• Transformers 4.24.0
• Pytorch 1.12.1+cu113
• Datasets 2.6.1
• Tokenizers 0.13.2