fix_punct_uncased_t5_small
This model is a fine-tuned version of google/t5-v1_1-small on the NPR utterances dataset.
Dataset
The model was trained on 80k rows from the above dataset consisting of NPR radio transcripts. Commans, periods, and semicolons were removed from the text and then random commas, periods, and semicolons were added. The model was trained to place those three punctuation marks in the correct location. All texts were lowercase during training.
It achieves the following results on the evaluation set:
- Loss: 0.3050
- Rouge1: 92.8762
- Rouge2: 90.4805
- Rougel: 92.8662
- Rougelsum: 92.7068
- Gen Len: 48.6130
Model description
The purpose of this model is to correct the punctuation in a sentence. For example, the phrase "this is, a sentence. with odd punctuation to show off what, the model. can do" gets changed to "this is a sentence with odd punctuation to show off what the model can do."
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 8e-05
- train_batch_size: 128
- eval_batch_size: 256
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.3066 | 1.0 | 600 | 0.4347 | 59.0002 | 54.7692 | 58.7112 | 58.7856 | 16.3808 |
| 0.8192 | 2.0 | 1200 | 0.3154 | 62.4672 | 59.0199 | 62.4096 | 62.3667 | 16.5158 |
| 0.7208 | 3.0 | 1800 | 0.3050 | 62.701 | 59.3201 | 62.6739 | 62.6165 | 16.5471 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.11.0a0+17540c5
- Datasets 2.5.1
- Tokenizers 0.12.1