Model save

README.md

@@ -1,10 +1,8 @@
 ---
-base_model: facebook/musicgen-melody
 library_name: peft
 license: cc-by-nc-4.0
+base_model: facebook/musicgen-melody
 tags:
-- text-to-audio
-- DevPanda004/demucsmetadata
 - generated_from_trainer
 model-index:
 - name: musicgen-melody-indian
@@ -16,10 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # musicgen-melody-indian
 
-This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on the DEVPANDA004/DEMUCSMETADATA - DEFAULT dataset.
-It achieves the following results on the evaluation set:
-- Loss: 2.9599
-- Clap: 0.2567
+This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on an unknown dataset.
 
 ## Model description
 
@@ -39,14 +34,14 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 2
-- eval_batch_size: 1
-- seed: 456
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
 - gradient_accumulation_steps: 8
-- total_train_batch_size: 16
+- total_train_batch_size: 32
 - optimizer: Use 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: 2.0
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -55,8 +50,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.13.2
-- Transformers 4.47.0.dev0
-- Pytorch 2.5.0+cu121
-- Datasets 3.0.2
-- Tokenizers 0.20.1
+- PEFT 0.14.0
+- Transformers 4.48.0.dev0
+- Pytorch 2.1.2+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0