|
--- |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: mood_box |
|
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. --> |
|
|
|
# mood_box |
|
|
|
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: 1.5115 |
|
- Accuracy: 0.3802 |
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 4 | 1.6030 | 0.2231 | |
|
| No log | 2.0 | 8 | 1.5976 | 0.3223 | |
|
| 1.6018 | 3.0 | 12 | 1.5936 | 0.2893 | |
|
| 1.6018 | 4.0 | 16 | 1.5849 | 0.2810 | |
|
| 1.5765 | 5.0 | 20 | 1.5733 | 0.3636 | |
|
| 1.5765 | 6.0 | 24 | 1.5557 | 0.3884 | |
|
| 1.5765 | 7.0 | 28 | 1.5360 | 0.3719 | |
|
| 1.5323 | 8.0 | 32 | 1.5246 | 0.3554 | |
|
| 1.5323 | 9.0 | 36 | 1.5152 | 0.3719 | |
|
| 1.4909 | 10.0 | 40 | 1.5115 | 0.3802 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.1 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.17.1 |
|
- Tokenizers 0.15.2 |
|
|