metadata
base_model: facebook/musicgen-melody
library_name: peft
license: cc-by-nc-4.0
tags:
- text-to-audio
- ogbanugot/musicgen
- generated_from_trainer
model-index:
- name: musicgen-melody-lora-afrobeats-with-vocals-long
results: []
musicgen-melody-lora-afrobeats-with-vocals-long
This model is a fine-tuned version of facebook/musicgen-melody on the OGBANUGOT/MUSICGEN - DEFAULT dataset. It achieves the following results on the evaluation set:
- Loss: 4.9616
- Clap: 0.0882
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: 2
- eval_batch_size: 1
- seed: 456
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Clap |
|---|---|---|---|---|
| 3.2006 | 25.0 | 25 | 4.9824 | 0.0558 |
| 3.0919 | 50.0 | 50 | 4.9616 | 0.0974 |
Framework versions
- PEFT 0.11.1
- Transformers 4.42.1
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1