Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
musicgen-large
This model is a fine-tuned version of facebook/musicgen-melody on the YLACOMBE/TINY-PUNK - DEFAULT dataset. It achieves the following results on the evaluation set:
- Loss: 4.5011
- Clap: -0.0131
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 1
- seed: 123
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Clap |
|---|---|---|---|---|
| 9.4039 | 0.8571 | 3 | 4.4428 | -0.0070 |
| 8.8992 | 2.0 | 7 | 4.4435 | 0.0117 |
| 8.5373 | 2.8571 | 10 | 4.4463 | -0.0288 |
| 8.0105 | 4.0 | 14 | 4.4552 | -0.0111 |
| 7.8068 | 4.8571 | 17 | 4.4682 | -0.0194 |
| 7.6881 | 6.0 | 21 | 4.4913 | 0.0071 |
| 7.6672 | 6.8571 | 24 | 4.5011 | -0.0222 |
Framework versions
- PEFT 0.11.1
- Transformers 4.42.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 3
Inference API (serverless) does not yet support peft models for this pipeline type.
Model tree for Z3K3/musicgen-large
Base model
facebook/musicgen-melody