Downloads · 30 days
3
6% of all-time downloads
bart-with-woz-noise-data-0.1-v2
gayanin/bart-with-woz-noise-data-0.1-v2
bart-with-woz-noise-data-0.1-v2 is a machine learning model from gayanin. 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
53
Public
Parameters
139M
11.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors558 MB · 100%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- bart
- Access
- Public
- Created
- Feb 12, 2024
- Updated
- Feb 12, 2024
- SHA
- e5f1c4dd
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. -->
bart-with-woz-noise-data-0.1-v2
This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0845
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2188 | 0.13 | 500 | 0.1794 |
| 0.1741 | 0.26 | 1000 | 0.1518 |
| 0.1631 | 0.39 | 1500 | 0.1327 |
| 0.1318 | 0.53 | 2000 | 0.1272 |
| 0.1238 | 0.66 | 2500 | 0.1168 |
| 0.1451 | 0.79 | 3000 | 0.1103 |
| 0.1166 | 0.92 | 3500 | 0.1068 |
| 0.0833 | 1.05 | 4000 | 0.1054 |
| 0.1029 | 1.18 | 4500 | 0.1017 |
| 0.1174 | 1.31 | 5000 | 0.0971 |
| 0.0786 | 1.44 | 5500 | 0.0956 |
| 0.1184 | 1.58 | 6000 | 0.0951 |
| 0.0984 | 1.71 | 6500 | 0.0926 |
| 0.0959 | 1.84 | 7000 | 0.0893 |
| 0.093 | 1.97 | 7500 | 0.0893 |
| 0.0783 | 2.1 | 8000 | 0.0910 |
| 0.0678 | 2.23 | 8500 | 0.0927 |
| 0.0756 | 2.36 | 9000 | 0.0889 |
| 0.0684 | 2.5 | 9500 | 0.0877 |
| 0.0573 | 2.63 | 10000 | 0.0872 |
| 0.0544 | 2.76 | 10500 | 0.0855 |
| 0.0579 | 2.89 | 11000 | 0.0845 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.2+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1
- Library
- transformers
- Type
- bart
- License
- apache-2.0
- Created
- Feb 12, 2024
- Updated
- Feb 12, 2024