Qwen-RAVDESS-Emotional-Analysis
This model is a fine-tuned version of Qwen/Qwen2-Audio-7B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0852
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: 2e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.7491 | 0.0476 | 2 | 3.6261 |
| 2.8532 | 0.0952 | 4 | 1.2801 |
| 1.0146 | 0.1429 | 6 | 0.8481 |
| 0.8266 | 0.1905 | 8 | 0.5289 |
| 0.3213 | 0.2381 | 10 | 0.2054 |
| 0.224 | 0.2857 | 12 | 0.1256 |
| 0.104 | 0.3333 | 14 | 0.0932 |
| 0.1328 | 0.3810 | 16 | 0.0805 |
| 0.0972 | 0.4286 | 18 | 0.0977 |
| 0.109 | 0.4762 | 20 | 0.0852 |
Framework versions
- PEFT 0.14.0
- Transformers 4.50.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0
- Downloads last month
- 0
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for cenk10combr/Qwen-RAVDESS-Emotional-Analysis
Base model
Qwen/Qwen2-Audio-7B-Instruct