|
--- |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: model_result |
|
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. --> |
|
|
|
# model_result |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6132 |
|
- Accuracy: 0.9038 |
|
|
|
## 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: 30 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-------:|:----:|:---------------:|:--------:| |
|
| No log | 0.9231 | 3 | 1.6081 | 0.1538 | |
|
| No log | 1.8462 | 6 | 1.5995 | 0.1731 | |
|
| No log | 2.7692 | 9 | 1.5848 | 0.25 | |
|
| 1.598 | 4.0 | 13 | 1.5500 | 0.3365 | |
|
| 1.598 | 4.9231 | 16 | 1.5076 | 0.4904 | |
|
| 1.598 | 5.8462 | 19 | 1.4453 | 0.6827 | |
|
| 1.5052 | 6.7692 | 22 | 1.3662 | 0.6731 | |
|
| 1.5052 | 8.0 | 26 | 1.2518 | 0.7212 | |
|
| 1.5052 | 8.9231 | 29 | 1.1767 | 0.7308 | |
|
| 1.2847 | 9.8462 | 32 | 1.1189 | 0.6923 | |
|
| 1.2847 | 10.7692 | 35 | 1.0484 | 0.7596 | |
|
| 1.2847 | 12.0 | 39 | 1.0011 | 0.7115 | |
|
| 1.081 | 12.9231 | 42 | 0.9297 | 0.7692 | |
|
| 1.081 | 13.8462 | 45 | 0.9014 | 0.7404 | |
|
| 1.081 | 14.7692 | 48 | 0.8527 | 0.7692 | |
|
| 0.9228 | 16.0 | 52 | 0.7915 | 0.8462 | |
|
| 0.9228 | 16.9231 | 55 | 0.8105 | 0.75 | |
|
| 0.9228 | 17.8462 | 58 | 0.7530 | 0.7885 | |
|
| 0.7978 | 18.7692 | 61 | 0.7055 | 0.8558 | |
|
| 0.7978 | 20.0 | 65 | 0.6827 | 0.8846 | |
|
| 0.7978 | 20.9231 | 68 | 0.6725 | 0.8654 | |
|
| 0.6996 | 21.8462 | 71 | 0.6646 | 0.875 | |
|
| 0.6996 | 22.7692 | 74 | 0.6351 | 0.9038 | |
|
| 0.6996 | 24.0 | 78 | 0.6202 | 0.9135 | |
|
| 0.6471 | 24.9231 | 81 | 0.6186 | 0.9038 | |
|
| 0.6471 | 25.8462 | 84 | 0.6157 | 0.8942 | |
|
| 0.6471 | 26.7692 | 87 | 0.6148 | 0.8942 | |
|
| 0.6172 | 27.6923 | 90 | 0.6132 | 0.9038 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
