<!-- 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. -->
hubert-base-ls960-finetuned-ks
This model is a fine-tuned version of facebook/hubert-base-ls960 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0485
- Accuracy: 0.9952
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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 |
|---|---|---|---|---|
| 1.8588 | 1.0 | 62 | 1.5145 | 0.7962 |
| 0.874 | 2.0 | 124 | 0.5052 | 0.9846 |
| 0.44 | 3.0 | 186 | 0.2257 | 0.9904 |
| 0.3184 | 4.0 | 248 | 0.1315 | 0.9913 |
| 0.1445 | 5.0 | 310 | 0.0898 | 0.9933 |
| 0.129 | 6.0 | 372 | 0.0717 | 0.9933 |
| 0.1263 | 7.0 | 434 | 0.0611 | 0.9933 |
| 0.0908 | 8.0 | 496 | 0.0515 | 0.9942 |
| 0.0804 | 9.0 | 558 | 0.0514 | 0.9942 |
| 0.0959 | 10.0 | 620 | 0.0485 | 0.9952 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.3
- Tokenizers 0.13.3
