hubert-base-ls960-finetuned-bmd-V1-20241110_105846-LOSO-section-out1
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: 1.0359
- Accuracy: 0.5172
- F1: 0.4927
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 1968
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 0.8571 | 3 | 1.0949 | 0.3793 | 0.2086 |
| No log | 2.0 | 7 | 1.0894 | 0.4828 | 0.4039 |
| 1.0912 | 2.8571 | 10 | 1.0769 | 0.4483 | 0.4099 |
| 1.0912 | 4.0 | 14 | 1.0269 | 0.4828 | 0.4815 |
| 1.0912 | 4.8571 | 17 | 1.0563 | 0.4483 | 0.4118 |
| 0.9968 | 6.0 | 21 | 1.1175 | 0.3448 | 0.3237 |
| 0.9968 | 6.8571 | 24 | 1.1136 | 0.4138 | 0.4015 |
| 0.9968 | 8.0 | 28 | 1.0389 | 0.4828 | 0.4652 |
| 0.8896 | 8.5714 | 30 | 1.0359 | 0.5172 | 0.4927 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3