初始化项目，由ModelHub XC社区提供模型

Model: Alienpenguin10/M3PO-GRPO-trial1-seed123
Source: Original Platform

training_config.json

@@ -0,0 +1,23 @@
+{
+  "num_iterations": 1,
+  "num_steps": 467,
+  "batch_size": 4,
+  "num_generations": 4,
+  "max_completion_length": 400,
+  "beta": 0.005,
+  "learning_rate": 5e-06,
+  "mu": 1,
+  "epsilon": 0.1,
+  "lambda_blend": 0.1,
+  "temperature_m3po": 0.1,
+  "use_m3po": false,
+  "gating_type": "bhattacharyya",
+  "gating_warmup_steps": 50,
+  "gating_lr": 0.0005,
+  "gating_grad_clip": 1.0,
+  "gradient_accumulation_steps": 4,
+  "warmup_ratio": 0.1,
+  "seed": 123,
+  "trial_number": 1,
+  "model_name": "Qwen/Qwen2.5-1.5B-Instruct"
+}