|
--- |
|
license: cc-by-nc-4.0 |
|
library_name: peft |
|
tags: |
|
- text-to-audio |
|
- ylacombe/tiny-punk |
|
- generated_from_trainer |
|
base_model: facebook/musicgen-melody |
|
model-index: |
|
- name: musicgen-melody-lora-punk |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# musicgen-melody-lora-punk |
|
|
|
This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on the YLACOMBE/TINY-PUNK - DEFAULT dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 6.2333 |
|
- Clap: -0.0021 |
|
|
|
## 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: 4 |
|
- seed: 456 |
|
- optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4.0 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Clap | |
|
|:-------------:|:------:|:----:|:---------------:|:-------:| |
|
| 7.1679 | 2.7778 | 25 | 6.2244 | -0.0018 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.41.2 |
|
- Pytorch 2.0.0+cu117 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
