metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Arousal-wav2vec2-base-EMOPIA
results: []
Arousal-wav2vec2-base-EMOPIA
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: 0.4207
- Accuracy: 0.9014
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: 1e-06
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 3
- total_train_batch_size: 3
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6871 | 1.0 | 269 | 0.6601 | 0.6761 |
| 0.6071 | 2.0 | 538 | 0.5375 | 0.8451 |
| 0.4312 | 3.0 | 807 | 0.3544 | 0.8873 |
| 0.306 | 4.0 | 1076 | 0.3780 | 0.8592 |
| 0.3052 | 5.0 | 1345 | 0.4133 | 0.8873 |
| 0.3099 | 6.0 | 1614 | 0.4112 | 0.8873 |
| 0.2965 | 7.0 | 1883 | 0.4241 | 0.8873 |
| 0.2954 | 8.0 | 2152 | 0.4381 | 0.8873 |
| 0.2905 | 9.0 | 2421 | 0.4294 | 0.9014 |
| 0.2868 | 10.0 | 2690 | 0.4208 | 0.9014 |
| 0.284 | 11.0 | 2959 | 0.4077 | 0.9014 |
| 0.2666 | 12.0 | 3228 | 0.4149 | 0.9014 |
| 0.2697 | 13.0 | 3497 | 0.4108 | 0.9014 |
| 0.2622 | 14.0 | 3766 | 0.4187 | 0.9014 |
| 0.2648 | 15.0 | 4035 | 0.4207 | 0.9014 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1