Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
black-eyed-peas-v1-autotuned
This model is a fine-tuned version of facebook/musicgen-melody-large on the SWEET-DREAMBOOTHS/BLACK-EYED-PEAS-V1-AUTOTUNED - DEFAULT dataset. It achieves the following results on the evaluation set:
- Loss: 5.1025
- Clap: 0.0905
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: 8
- eval_batch_size: 1
- seed: 456
- optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Clap |
|---|---|---|---|---|
| 8.2705 | 0.3125 | 5 | 3.0109 | 0.3172 |
| 6.4565 | 0.625 | 10 | 3.3557 | 0.2050 |
| 6.0972 | 0.9375 | 15 | 4.5204 | 0.1229 |
| 6.3825 | 1.25 | 20 | 4.9794 | 0.1119 |
| 6.3178 | 1.5625 | 25 | 5.1081 | 0.0916 |
| 6.1301 | 1.875 | 30 | 5.1036 | 0.0850 |
Framework versions
- PEFT 0.10.0
- Transformers 4.41.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.18.1.dev0
- Tokenizers 0.19.1
- Downloads last month
- 8
Inference API (serverless) does not yet support peft models for this pipeline type.
Model tree for sweet-dreambooths/black-eyed-peas-v1-autotuned
Base model
facebook/musicgen-melody-large