metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: wav2vec2-base-one-shot-hip-hop-drums-clf
results: []
wav2vec2-base-one-shot-hip-hop-drums-clf
This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5567
- Accuracy: 0.475
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 | 3 | 1.9203 | 0.4 |
| No log | 2.0 | 6 | 1.8357 | 0.45 |
| No log | 3.0 | 9 | 1.7626 | 0.45 |
| 1.8485 | 4.0 | 12 | 1.7037 | 0.425 |
| 1.8485 | 5.0 | 15 | 1.6605 | 0.45 |
| 1.8485 | 6.0 | 18 | 1.6233 | 0.45 |
| 1.5876 | 7.0 | 21 | 1.5963 | 0.475 |
| 1.5876 | 8.0 | 24 | 1.5776 | 0.475 |
| 1.5876 | 9.0 | 27 | 1.5634 | 0.475 |
| 1.491 | 10.0 | 30 | 1.5567 | 0.475 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1