facebook-musicgen-small-not-lora-440

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

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: 3.2387
• Clap: 0.2978

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: 440.0
• mixed_precision_training: Native AMP

Training results

Framework versions

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