metadata
library_name: peft
license: cc-by-nc-4.0
base_model: facebook/musicgen-small
tags:
- text-to-audio
- taufiqsyed/salami_cleaned_sampled
- generated_from_trainer
model-index:
- name: salami_truncsplit_finetune_model_16
results: []
salami_truncsplit_finetune_model_16
This model is a fine-tuned version of facebook/musicgen-small on the TAUFIQSYED/SALAMI_CLEANED_SAMPLED - DEFAULT dataset. It achieves the following results on the evaluation set:
- Loss: 3.7649
- Clap: 0.1988
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: 1
- eval_batch_size: 1
- seed: 456
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Use adamw_torch with betas=(0.9,0.99) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 1.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Clap |
|---|---|---|---|---|
| 9.2964 | 0.2407 | 25 | 3.6824 | 0.2393 |
| 8.452 | 0.4813 | 50 | 3.7090 | 0.2203 |
| 8.2681 | 0.7220 | 75 | 3.7505 | 0.1934 |
| 8.0758 | 0.9627 | 100 | 3.7648 | 0.2037 |
Framework versions
- PEFT 0.13.2
- Transformers 4.47.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3