metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- accuracy
model-index:
- name: my_birdcall_model
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: audiofolder
type: audiofolder
config: rb
split: train[:5000]
args: rb
metrics:
- name: Accuracy
type: accuracy
value: 0.26
my_birdcall_model
This model is a fine-tuned version of facebook/wav2vec2-base on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 3.1584
- Accuracy: 0.26
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 |
---|---|---|---|---|
4.9434 | 0.99 | 31 | 4.8016 | 0.108 |
4.5209 | 1.98 | 62 | 4.3832 | 0.108 |
4.1573 | 2.98 | 93 | 3.9995 | 0.108 |
3.8211 | 4.0 | 125 | 3.6762 | 0.108 |
3.5876 | 4.99 | 156 | 3.4586 | 0.152 |
3.4453 | 5.98 | 187 | 3.3284 | 0.191 |
3.313 | 6.98 | 218 | 3.2432 | 0.21 |
3.2369 | 8.0 | 250 | 3.1993 | 0.223 |
3.2286 | 8.99 | 281 | 3.1712 | 0.23 |
3.1867 | 9.92 | 310 | 3.1584 | 0.26 |
Framework versions
- Transformers 4.38.0
- Pytorch 2.3.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0