metadata
license: cc-by-nc-sa-4.0
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: wav2vec2-large-robust-12-ft-emotion-msp-dim-finetuned-gtzan
results: []
wav2vec2-large-robust-12-ft-emotion-msp-dim-finetuned-gtzan
This model is a fine-tuned version of audeering/wav2vec2-large-robust-12-ft-emotion-msp-dim on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.7711
- Accuracy: 0.83
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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 |
|---|---|---|---|---|
| 2.186 | 1.0 | 112 | 2.1638 | 0.3 |
| 1.655 | 2.0 | 225 | 1.7677 | 0.48 |
| 1.5148 | 3.0 | 337 | 1.3746 | 0.54 |
| 1.2349 | 4.0 | 450 | 1.1218 | 0.64 |
| 0.9702 | 5.0 | 562 | 1.0244 | 0.69 |
| 0.9191 | 6.0 | 675 | 0.9180 | 0.75 |
| 0.6891 | 7.0 | 787 | 0.8959 | 0.76 |
| 0.628 | 8.0 | 900 | 0.8084 | 0.81 |
| 0.7337 | 9.0 | 1012 | 0.7742 | 0.83 |
| 0.5573 | 9.96 | 1120 | 0.7711 | 0.83 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3