Model save

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: facebook/musicgen-large
-library_name: peft
+library_name: transformers
 license: cc-by-nc-4.0
+base_model: facebook/musicgen-small
 tags:
 - generated_from_trainer
 model-index:
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # musicgen-finetune-aav
 
-This model is a fine-tuned version of [facebook/musicgen-large](https://huggingface.co/facebook/musicgen-large) on an unknown dataset.
+This model is a fine-tuned version of [facebook/musicgen-small](https://huggingface.co/facebook/musicgen-small) on an unknown dataset.
 
 ## Model description
 
@@ -33,7 +33,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
+- learning_rate: 0.0001
 - train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 16
 - 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
+- num_epochs: 4
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -50,8 +50,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.13.2
 - Transformers 4.47.0.dev0
 - Pytorch 2.1.2+cu121
 - Datasets 3.1.0
-- Tokenizers 0.20.1
+- Tokenizers 0.20.2

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2048,
+  "decoder_start_token_id": 2048,
+  "do_sample": true,
+  "guidance_scale": 3.0,
+  "max_length": 1500,
+  "pad_token_id": 2048,
+  "transformers_version": "4.47.0.dev0"
+}