MU-Bench: Benchmarking Machine Unlearning
Collection
Benchmark machine unlearning (MU) in a wide range of tasks, domains, modalities.
•
18 items
•
Updated
•
1
superb_ks_42
This model is a fine-tuned version of facebook/hubert-large-ll60k on the superb dataset. It achieves the following results on the evaluation set:
- Loss: 0.0464
- Accuracy: 0.9887
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: 32
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6086 | 1.0 | 1597 | 0.0966 | 0.9826 |
| 0.2065 | 2.0 | 3194 | 0.0611 | 0.9862 |
| 0.1822 | 3.0 | 4791 | 0.0541 | 0.9879 |
| 0.1529 | 4.0 | 6388 | 0.0540 | 0.9869 |
| 0.1392 | 5.0 | 7985 | 0.0534 | 0.9865 |
| 0.1307 | 6.0 | 9582 | 0.0464 | 0.9887 |
| 0.1171 | 7.0 | 11179 | 0.0498 | 0.9873 |
| 0.1144 | 8.0 | 12776 | 0.0471 | 0.9884 |
| 0.1104 | 9.0 | 14373 | 0.0455 | 0.9879 |
| 0.1079 | 10.0 | 15970 | 0.0464 | 0.9885 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 13
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 jialicheng/hubert-large-speech_commands
Base model
facebook/hubert-large-ll60k