Configuration Parsing Warning:In adapter_config.json: "peft.task_type" must be a string
musicgen-synths-test
This model is a fine-tuned version of facebook/musicgen-small on the TRULYSENYA/SYNTH-SOUNDS-SLICE - DEFAULT dataset. It achieves the following results on the evaluation set:
- Loss: 2.4152
- Clap: 0.0540
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 2
- seed: 456
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Clap |
|---|---|---|---|---|
| 3.6 | 1.3333 | 25 | 2.5249 | 0.0917 |
| 3.5431 | 2.6667 | 50 | 2.3253 | 0.0774 |
Framework versions
- PEFT 0.10.0
- Transformers 4.41.0
- Pytorch 2.9.0+cu128
- Datasets 4.3.0
- Tokenizers 0.19.1
- Downloads last month
- 9
Model tree for TrulySenya/musicgen-synths-test
Base model
facebook/musicgen-small