VoxSentinel-finetuned-IEMOCAP
This model is a fine-tuned version of JesseHuang922/VoxSentinel_Emotion_Base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3814
- Accuracy: 0.5271
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 6.0955 | 1.0 | 402 | 1.4687 | 0.4549 |
| 5.4630 | 2.0 | 804 | 1.4093 | 0.4816 |
| 4.8706 | 3.0 | 1206 | 1.3848 | 0.4785 |
| 4.2373 | 4.0 | 1608 | 1.4118 | 0.5121 |
| 3.2957 | 5.0 | 2010 | 1.3814 | 0.5271 |
Framework versions
- Transformers 5.10.2
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2