sanchit-gandhi's picture
End of training
467af1f verified
metadata
license: cc-by-nc-4.0
library_name: peft
tags:
  - text-to-audio
  - sweet-dreambooths/combined-artists-v1
  - generated_from_trainer
base_model: facebook/musicgen-melody-large
model-index:
  - name: combined-artists-text-only-3-epochs
    results: []

Visualize in Weights & Biases Visualize in Weights & Biases

combined-artists-text-only-3-epochs

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

  • Loss: 5.1016
  • Text Cosine Sim: 0.0961
  • Audio Cosine Sim: 0.3267

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: 16
  • eval_batch_size: 4
  • seed: 456
  • 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

Training Loss Epoch Step Validation Loss Text Cosine Sim Audio Cosine Sim
7.174 1.0 99 4.9214 0.1636 0.3831
6.7947 2.0 198 5.0773 0.1509 0.3747
7.1508 3.0 297 5.1016 0.1181 0.3217

Framework versions

  • PEFT 0.10.0
  • Transformers 4.41.0.dev0
  • Pytorch 2.1.2+cu121
  • Datasets 2.19.2.dev0
  • Tokenizers 0.19.1