初始化项目，由ModelHub XC社区提供模型

Model: abharadwaj123/sqlstorm-grpo-plan8192
Source: Original Platform

checkpoint-12/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.48,
+  "eval_steps": 500,
+  "global_step": 12,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.175,
+      "completions/max_length": 6298.7,
+      "completions/max_terminated_length": 4670.0,
+      "completions/mean_length": 3769.95,
+      "completions/mean_terminated_length": 2954.4666748046875,
+      "completions/min_length": 1554.8,
+      "completions/min_terminated_length": 1554.8,
+      "entropy": 4.061883237212896,
+      "epoch": 0.4,
+      "frac_reward_zero_std": 0.05,
+      "grad_norm": 0.3359375,
+      "learning_rate": 2.5e-06,
+      "loss": -0.07856913208961487,
+      "num_tokens": 166764.0,
+      "reward": 0.6544295579195023,
+      "reward_std": 0.040438423810701354,
+      "rewards/reward_func/mean": 0.6544295579195023,
+      "rewards/reward_func/std": 0.04043842608807609,
+      "step": 10,
+      "step_time": 292.8999413277721
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 12,
+  "num_input_tokens_seen": 210353,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}