Training in progress - step 500

asr_modeling.py

@@ -827,8 +827,10 @@ class ASRModel(PreTrainedModel, GenerationMixin):
         self.feature_extractor.save_pretrained(save_dir)
 
         # Save LoRA adapters if present (creates adapter_model.safetensors and adapter_config.json)
+        # Don't save embedding layers - the <audio> token embedding is never used
+        # (it's replaced with projected audio embeddings before the LLM sees it)
         if hasattr(self.language_model, "peft_config"):
-            self.language_model.save_pretrained(save_dir)
+            self.language_model.save_pretrained(save_dir, save_embedding_layers=False)
 
         # Add processor auto_map to preprocessor_config.json
         config_path = save_dir / "preprocessor_config.json"