metadata
library_name: transformers
license: apache-2.0
base_model: facebook/hubert-base-ls960
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bs16-lr2e-5-epoch10-seqlen10
results: []
bs16-lr2e-5-epoch10-seqlen10
This model is a fine-tuned version of facebook/hubert-base-ls960 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6936
- Accuracy: 0.6167
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 1
- seed: 1016
- 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: 10.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 6.1254 | 1.0 | 8648 | 6.3700 | 0.0055 |
| 4.5846 | 2.0 | 17296 | 5.1543 | 0.0521 |
| 3.6412 | 3.0 | 25944 | 4.2039 | 0.1302 |
| 2.6422 | 4.0 | 34592 | 3.4738 | 0.2416 |
| 1.9601 | 5.0 | 43240 | 2.7758 | 0.3746 |
| 1.564 | 6.0 | 51888 | 2.3559 | 0.4623 |
| 1.2376 | 7.0 | 60536 | 2.0383 | 0.5352 |
| 1.0652 | 8.0 | 69184 | 1.8766 | 0.5666 |
| 0.9146 | 9.0 | 77832 | 1.7436 | 0.6059 |
| 0.8688 | 10.0 | 86480 | 1.6936 | 0.6167 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.0.0+cu117
- Datasets 3.1.0
- Tokenizers 0.20.3