Hugging Face's logo

sweet-dreambooths
/
black-eyed-peas-v1-crafted-prompt-3-epochs-piano-prompts

Text-to-Audio
PEFT
Safetensors
musicgen_melody
sweet-dreambooths/black-eyed-peas-v1-piano-prompts
Generated from Trainer
Model card Files Community
black-eyed-peas-v1-crafted-prompt-3-epochs-piano-prompts / README.md
sanchit-gandhi's picture
sanchit-gandhi HF staff
End of training
10bf770 verified
preview code
|
raw
history blame
2 kB
metadata
license: cc-by-nc-4.0
library_name: peft
tags:
  - text-to-audio
  - sweet-dreambooths/black-eyed-peas-v1-piano-prompts
  - generated_from_trainer
base_model: facebook/musicgen-melody-large
model-index:
  - name: black-eyed-peas-v1-crafted-prompt-3-epochs-piano-prompts
    results: []

Visualize in Weights & Biases Visualize in Weights & Biases

black-eyed-peas-v1-crafted-prompt-3-epochs-piano-prompts

This model is a fine-tuned version of facebook/musicgen-melody-large on the SWEET-DREAMBOOTHS/BLACK-EYED-PEAS-V1-PIANO-PROMPTS - DEFAULT dataset. It achieves the following results on the evaluation set:

  • Loss: 3.0910
  • Text Cosine Sim: 0.4804
  • Audio Cosine Sim: 0.5601

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: 3e-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 456
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • PEFT 0.10.0
  • Transformers 4.41.0.dev0
  • Pytorch 2.1.0+cu121
  • Datasets 2.18.1.dev0
  • Tokenizers 0.19.1