---
library_name: transformers
tags:
- text-to-audio
- CLAPv2/MusicCaps
- generated_from_trainer
model-index:
- name: GenCaps-finetune-Musicgen-small
  results: []
license: mit
datasets:
- CLAPv2/MusicCaps
language:
- en
base_model:
- facebook/musicgen-small
pipeline_tag: text-to-audio
---

<!-- 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 [facebook/musicgen-smalll](https://huggingface.co/facebook/musicgen-small) on the CLAPV2/MUSICCAPS - DEFAULT dataset.
It achieves the following results on the evaluation set:
- Loss: 2.2189
- Clap: 0.3387

## 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: 8
- 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: 700.0
- 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