Hugging Face's logo

heboya8
/
facebook-musicgen-small-not-lora-310

Safetensors
musicgen
Model card Files Community
facebook-musicgen-small-not-lora-310 / README.md
heboya8's picture
heboya8
Create README.md
5a6f4de verified
preview code
|
raw
history blame contribute delete
1.27 kB

GenCaps-finetune-Musicgen-small

This model is a fine-tuned version of ./GenCaps-finetune-Musicgen-small on the CLAPV2/MUSICCAPS - DEFAULT dataset. It achieves the following results on the evaluation set:

  • Loss: 4.7031
  • Clap: 0.1730

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: 1e-05
  • train_batch_size: 16
  • eval_batch_size: 1
  • seed: 456
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 128
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.99) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 310.0
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • PEFT 0.14.0
  • Transformers 4.54.0.dev0
  • Pytorch 2.6.0+cu124
  • Datasets 3.6.0
  • Tokenizers 0.21.1