metadata
license: apache-2.0
tags:
- audio-classification
- generated_from_trainer
datasets:
- mir_st500
metrics:
- accuracy
model-index:
- name: wav2vec2-base-mirst500
results: []
wav2vec2-base-mirst500
This model is a fine-tuned version of facebook/wav2vec2-base on the /workspace/datasets/datasets/MIR_ST500/MIR_ST500_AUDIO_CLASSIFICATION.py dataset. It achieves the following results on the evaluation set:
- Loss: 0.8678
- Accuracy: 0.7017
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: 16
- eval_batch_size: 1
- seed: 0
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- total_eval_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1999 | 1.0 | 1304 | 1.1029 | 0.5877 |
| 1.0779 | 2.0 | 2608 | 0.9455 | 0.6555 |
| 0.9775 | 3.0 | 3912 | 0.9670 | 0.6523 |
| 0.9542 | 4.0 | 5216 | 0.8810 | 0.6946 |
| 0.9403 | 5.0 | 6520 | 0.8678 | 0.7017 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.9.1+cu102
- Datasets 2.0.0
- Tokenizers 0.10.3