Edit model card

t5_base-qg-af-oficial

This model is a fine-tuned version of unicamp-dl/ptt5-base-portuguese-vocab on the tiagoblima/preprocessed-du-qg-squadv1_pt dataset. It achieves the following results on the evaluation set:

  • Loss: 1.9312

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: 0.0001
  • train_batch_size: 32
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
  • lr_scheduler_type: linear
  • num_epochs: 5.0

Training results

Training Loss Epoch Step Validation Loss
2.0526 1.0 1386 1.9887
1.9076 2.0 2772 1.9484
1.7999 3.0 4158 1.9368
1.7721 4.0 5544 1.9312
1.7238 5.0 6930 1.9366

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.15.0
  • Tokenizers 0.15.1
Downloads last month
6
Safetensors
Model size
223M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for tiagoblima/t5_base-qg-af-oficial

Finetuned
(18)
this model

Dataset used to train tiagoblima/t5_base-qg-af-oficial