|
--- |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: CS337_finetune_wav2vec_base |
|
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. --> |
|
|
|
# CS337_finetune_wav2vec_base |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9254 |
|
- Accuracy: 0.6485 |
|
|
|
## 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: 0.0005 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.2727 | 0.97 | 28 | 1.2536 | 0.5520 | |
|
| 1.2855 | 1.98 | 57 | 1.1553 | 0.5520 | |
|
| 1.2834 | 2.99 | 86 | 1.1334 | 0.5305 | |
|
| 1.127 | 4.0 | 115 | 0.9970 | 0.5799 | |
|
| 1.1262 | 4.97 | 143 | 0.9905 | 0.6168 | |
|
| 1.2568 | 5.98 | 172 | 0.9853 | 0.6155 | |
|
| 1.1343 | 6.99 | 201 | 0.9947 | 0.6218 | |
|
| 1.0321 | 8.0 | 230 | 0.9495 | 0.6294 | |
|
| 1.0019 | 8.97 | 258 | 0.9227 | 0.6548 | |
|
| 0.9676 | 9.74 | 280 | 0.9254 | 0.6485 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|