Hugging Face's logo

jihong008
/
musicgen-melody-lora-punk3

Text-to-Audio
PEFT
Safetensors
musicgen_melody
ylacombe/tiny-punk
Generated from Trainer
Model card Files Community
musicgen-melody-lora-punk3 / README.md
jihong008's picture
jihong008
End of training
1940a04 verified
preview code
|
raw
history blame contribute delete
1.78 kB
metadata
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-punk3
    results: []

Visualize in Weights & Biases

musicgen-melody-lora-punk3

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: 7.9297
  • Clap: -0.0094

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: 4.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Clap
6.5295 3.2787 25 7.8930 0.0111

Framework versions

  • PEFT 0.11.1
  • Transformers 4.42.0.dev0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1