Downloads · 30 days
3
14% of all-time downloads
t5_disfluent_cleaner
abdulbaseermohammedkhan/t5_disfluent_cleaner
t5_disfluent_cleaner is a machine learning model from abdulbaseermohammedkhan. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
22
Public
Parameters
223M
893 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors892 MB · 100%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- t5
- Access
- Public
- Created
- Aug 2, 2025
- Updated
- Aug 2, 2025
- SHA
- 29c75de6
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
t5_disfluent_cleaner
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6394
- Bleu: 0.9088
- Rougel: 0.9584
- Exact Match: 0.7342
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Rougel | Exact Match |
|---|---|---|---|---|---|---|
| 1.652 | 1.0 | 896 | 1.6790 | 0.8989 | 0.9530 | 0.7031 |
| 1.6164 | 2.0 | 1792 | 1.6544 | 0.9039 | 0.9554 | 0.7182 |
| 1.5844 | 3.0 | 2688 | 1.6443 | 0.9055 | 0.9566 | 0.7252 |
| 1.5963 | 4.0 | 3584 | 1.6394 | 0.9088 | 0.9584 | 0.7342 |
| 1.6005 | 5.0 | 4480 | 1.6375 | 0.9077 | 0.9580 | 0.7342 |
Framework versions
- Transformers 4.54.1
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.2
- Library
- transformers
- Type
- t5
- License
- apache-2.0
- Created
- Aug 2, 2025
- Updated
- Aug 2, 2025