|
--- |
|
license: apache-2.0 |
|
base_model: facebook/hubert-base-ls960 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- recall |
|
- precision |
|
model-index: |
|
- name: hubert-base-ls960-finetuned-common_voice |
|
results: [] |
|
--- |
|
|
|
<!-- 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-common_voice |
|
|
|
This model is a fine-tuned version of [facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0451 |
|
- Accuracy: 0.99 |
|
- F1: 0.9900 |
|
- Recall: 0.99 |
|
- Precision: 0.9900 |
|
- Mcc: 0.9875 |
|
- Auc: 0.9994 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- 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 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision | Mcc | Auc | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|:------:|:------:| |
|
| 0.2557 | 1.0 | 200 | 0.1431 | 0.965 | 0.9647 | 0.9650 | 0.9676 | 0.9570 | 0.9965 | |
|
| 0.1858 | 2.0 | 400 | 0.0567 | 0.985 | 0.9849 | 0.985 | 0.9854 | 0.9814 | 0.9994 | |
|
| 0.0626 | 3.0 | 600 | 0.0612 | 0.9875 | 0.9875 | 0.9875 | 0.9876 | 0.9844 | 0.9996 | |
|
| 0.2167 | 4.0 | 800 | 0.0340 | 0.995 | 0.9950 | 0.9950 | 0.9950 | 0.9938 | 0.9999 | |
|
| 0.0217 | 5.0 | 1000 | 0.0454 | 0.9925 | 0.9925 | 0.9925 | 0.9925 | 0.9906 | 0.9997 | |
|
| 0.1366 | 6.0 | 1200 | 0.0659 | 0.985 | 0.9850 | 0.985 | 0.9852 | 0.9813 | 0.9992 | |
|
| 0.0167 | 7.0 | 1400 | 0.0515 | 0.9925 | 0.9925 | 0.9925 | 0.9927 | 0.9907 | 0.9991 | |
|
| 0.015 | 8.0 | 1600 | 0.0414 | 0.9925 | 0.9925 | 0.9925 | 0.9927 | 0.9907 | 0.9993 | |
|
| 0.0312 | 9.0 | 1800 | 0.0432 | 0.9925 | 0.9925 | 0.9925 | 0.9926 | 0.9906 | 0.9993 | |
|
| 0.0091 | 10.0 | 2000 | 0.0451 | 0.99 | 0.9900 | 0.99 | 0.9900 | 0.9875 | 0.9994 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.0 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
