burtenshaw
/

Qwen3-30B-A3B-python-coder

Text Generation

Generated from Trainer

Model card Files Files and versions Community

burtenshaw HF Staff commited on 2 days ago

Commit

b50538b

·

verified ·

1 Parent(s): bce8c2b

Upload train.py with huggingface_hub

Files changed (1) hide show

train.py +1 -2

train.py CHANGED Viewed

@@ -61,7 +61,7 @@ model_name = "Qwen/Qwen3-30B-A3B"  # You can change this to any model you want t
 # model_name = "Qwen/Qwen3-0.6B"
 # Training configuration
-output_dir = "./output/sft-model"
 num_train_epochs = 1
 per_device_train_batch_size = 1
 gradient_accumulation_steps = 1
@@ -122,7 +122,6 @@ training_args = SFTConfig(
     fp16=False,
     max_steps=1000,
     report_to="wandb",  # Disable reporting to avoid wandb prompts
-    output_dir="./tmp/sft-model",
 )
 """## Initialize and run the SFT Trainer"""

 # model_name = "Qwen/Qwen3-0.6B"
 # Training configuration
+output_dir = "./tmp/sft-model"
 num_train_epochs = 1
 per_device_train_batch_size = 1
 gradient_accumulation_steps = 1
     fp16=False,
     max_steps=1000,
     report_to="wandb",  # Disable reporting to avoid wandb prompts
 )
 """## Initialize and run the SFT Trainer"""