metadata
library_name: transformers
license: apache-2.0
base_model: facebook/hubert-base-ls960
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: hubert-base-ls960-finetuned-eos_poc5_ge-di-v5
results: []
hubert-base-ls960-finetuned-eos_poc5_ge-di-v5
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: 0.8936
- Accuracy: 0.6772
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use 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_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.0044 | 1.0 | 302 | 1.0290 | 0.5622 |
| 0.7936 | 2.0 | 604 | 1.0197 | 0.5640 |
| 0.9923 | 3.0 | 906 | 0.9170 | 0.6122 |
| 0.9078 | 4.0 | 1208 | 0.9016 | 0.6160 |
| 0.8268 | 5.0 | 1510 | 0.9285 | 0.6345 |
| 0.7044 | 6.0 | 1812 | 0.8985 | 0.6494 |
| 0.6689 | 7.0 | 2114 | 0.9121 | 0.6549 |
| 0.7087 | 8.0 | 2416 | 0.8722 | 0.6735 |
| 0.6809 | 9.0 | 2718 | 0.8894 | 0.6735 |
| 0.7639 | 10.0 | 3020 | 0.8936 | 0.6772 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0