{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.35557132718239887,
  "eval_steps": 500,
  "global_step": 501,
  "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": 0.873046875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1965.146484375,
      "completions/mean_terminated_length": 1395.3692626953125,
      "completions/min_length": 331.0,
      "completions/min_terminated_length": 331.0,
      "epoch": 0.0007097232079489,
      "frac_reward_zero_std": 0.5625,
      "grad_norm": 14.304986953735352,
      "learning_rate": 1e-06,
      "loss": 0.0173,
      "num_tokens": 1537484.0,
      "reward": 0.078125,
      "reward_std": 0.15549317002296448,
      "rewards/simpleverify_reward/mean": 0.078125,
      "rewards/simpleverify_reward/std": 0.26863065361976624,
      "step": 1,
      "tools/generated_tokens": 1989.998046875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.041015625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.779296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1849.0625,
      "completions/mean_terminated_length": 1146.6195068359375,
      "completions/min_length": 248.0,
      "completions/min_terminated_length": 248.0,
      "epoch": 0.0014194464158978,
      "frac_reward_zero_std": 0.59375,
      "grad_norm": 47.43809127807617,
      "learning_rate": 9.98e-07,
      "loss": 0.0461,
      "num_tokens": 3051969.0,
      "reward": 0.1640625,
      "reward_std": 0.17151758074760437,
      "rewards/simpleverify_reward/mean": 0.1640625,
      "rewards/simpleverify_reward/std": 0.37069445848464966,
      "step": 2,
      "tools/generated_tokens": 1800.697265625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.099609375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.759765625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2041.0,
      "completions/mean_length": 1863.205078125,
      "completions/mean_terminated_length": 1278.7723388671875,
      "completions/min_length": 291.0,
      "completions/min_terminated_length": 291.0,
      "epoch": 0.0021291696238466998,
      "frac_reward_zero_std": 0.59375,
      "grad_norm": 41.36878204345703,
      "learning_rate": 9.959999999999999e-07,
      "loss": 0.0338,
      "num_tokens": 4541413.0,
      "reward": 0.16015625,
      "reward_std": 0.1565784215927124,
      "rewards/simpleverify_reward/mean": 0.16015625,
      "rewards/simpleverify_reward/std": 0.3671095669269562,
      "step": 3,
      "tools/generated_tokens": 1890.875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.046875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.802734375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1893.7890625,
      "completions/mean_terminated_length": 1266.2574462890625,
      "completions/min_length": 428.0,
      "completions/min_terminated_length": 428.0,
      "epoch": 0.0028388928317956,
      "frac_reward_zero_std": 0.625,
      "grad_norm": 37.67452621459961,
      "learning_rate": 9.94e-07,
      "loss": 0.0173,
      "num_tokens": 6102121.0,
      "reward": 0.1015625,
      "reward_std": 0.13856959342956543,
      "rewards/simpleverify_reward/mean": 0.1015625,
      "rewards/simpleverify_reward/std": 0.30236753821372986,
      "step": 4,
      "tools/generated_tokens": 1967.853515625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.09375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.74609375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2029.0,
      "completions/mean_length": 1818.810546875,
      "completions/mean_terminated_length": 1145.34619140625,
      "completions/min_length": 356.0,
      "completions/min_terminated_length": 356.0,
      "epoch": 0.0035486160397444995,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 47.504051208496094,
      "learning_rate": 9.92e-07,
      "loss": 0.0492,
      "num_tokens": 7614582.0,
      "reward": 0.169921875,
      "reward_std": 0.1773129403591156,
      "rewards/simpleverify_reward/mean": 0.169921875,
      "rewards/simpleverify_reward/std": 0.3759314715862274,
      "step": 5,
      "tools/generated_tokens": 1822.982421875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.09765625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.765625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2038.0,
      "completions/mean_length": 1875.056640625,
      "completions/mean_terminated_length": 1310.1083984375,
      "completions/min_length": 481.0,
      "completions/min_terminated_length": 481.0,
      "epoch": 0.0042583392476933995,
      "frac_reward_zero_std": 0.65625,
      "grad_norm": 33.492862701416016,
      "learning_rate": 9.9e-07,
      "loss": 0.0327,
      "num_tokens": 9159907.0,
      "reward": 0.11328125,
      "reward_std": 0.14166401326656342,
      "rewards/simpleverify_reward/mean": 0.11328125,
      "rewards/simpleverify_reward/std": 0.3172462284564972,
      "step": 6,
      "tools/generated_tokens": 1900.66796875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.095703125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.69921875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2038.0,
      "completions/mean_length": 1730.548828125,
      "completions/mean_terminated_length": 992.5779418945312,
      "completions/min_length": 376.0,
      "completions/min_terminated_length": 376.0,
      "epoch": 0.0049680624556423,
      "frac_reward_zero_std": 0.625,
      "grad_norm": 14.8273286819458,
      "learning_rate": 9.88e-07,
      "loss": 0.0175,
      "num_tokens": 10648762.0,
      "reward": 0.15234375,
      "reward_std": 0.1556403934955597,
      "rewards/simpleverify_reward/mean": 0.15234375,
      "rewards/simpleverify_reward/std": 0.35970520973205566,
      "step": 7,
      "tools/generated_tokens": 1791.275390625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.11328125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.796875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2025.0,
      "completions/mean_length": 1855.94921875,
      "completions/mean_terminated_length": 1102.519287109375,
      "completions/min_length": 382.0,
      "completions/min_terminated_length": 382.0,
      "epoch": 0.0056777856635912,
      "frac_reward_zero_std": 0.625,
      "grad_norm": 58.01800537109375,
      "learning_rate": 9.86e-07,
      "loss": 0.0336,
      "num_tokens": 12201242.0,
      "reward": 0.173828125,
      "reward_std": 0.14475050568580627,
      "rewards/simpleverify_reward/mean": 0.173828125,
      "rewards/simpleverify_reward/std": 0.3793322443962097,
      "step": 8,
      "tools/generated_tokens": 1901.150390625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.11328125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.7890625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1848.333984375,
      "completions/mean_terminated_length": 1101.4351806640625,
      "completions/min_length": 215.0,
      "completions/min_terminated_length": 215.0,
      "epoch": 0.0063875088715401,
      "frac_reward_zero_std": 0.53125,
      "grad_norm": 26.3413028717041,
      "learning_rate": 9.84e-07,
      "loss": 0.0504,
      "num_tokens": 13730620.0,
      "reward": 0.189453125,
      "reward_std": 0.16553467512130737,
      "rewards/simpleverify_reward/mean": 0.189453125,
      "rewards/simpleverify_reward/std": 0.3922513723373413,
      "step": 9,
      "tools/generated_tokens": 1835.49609375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.1171875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.728515625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2021.0,
      "completions/mean_length": 1802.70703125,
      "completions/mean_terminated_length": 1144.474853515625,
      "completions/min_length": 189.0,
      "completions/min_terminated_length": 189.0,
      "epoch": 0.007097232079488999,
      "frac_reward_zero_std": 0.53125,
      "grad_norm": 53.488285064697266,
      "learning_rate": 9.819999999999999e-07,
      "loss": 0.0339,
      "num_tokens": 15258675.0,
      "reward": 0.173828125,
      "reward_std": 0.20586776733398438,
      "rewards/simpleverify_reward/mean": 0.173828125,
      "rewards/simpleverify_reward/std": 0.3793322443962097,
      "step": 10,
      "tools/generated_tokens": 1869.17578125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.111328125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.72265625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2035.0,
      "completions/mean_length": 1864.38671875,
      "completions/mean_terminated_length": 1385.957763671875,
      "completions/min_length": 147.0,
      "completions/min_terminated_length": 147.0,
      "epoch": 0.007806955287437899,
      "frac_reward_zero_std": 0.59375,
      "grad_norm": 8.392992973327637,
      "learning_rate": 9.8e-07,
      "loss": 0.0088,
      "num_tokens": 16790232.0,
      "reward": 0.19921875,
      "reward_std": 0.17950454354286194,
      "rewards/simpleverify_reward/mean": 0.19921875,
      "rewards/simpleverify_reward/std": 0.39980348944664,
      "step": 11,
      "tools/generated_tokens": 1909.103515625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.076171875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.85546875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1949.419921875,
      "completions/mean_terminated_length": 1365.9324951171875,
      "completions/min_length": 196.0,
      "completions/min_terminated_length": 196.0,
      "epoch": 0.008516678495386799,
      "frac_reward_zero_std": 0.625,
      "grad_norm": 17.738483428955078,
      "learning_rate": 9.78e-07,
      "loss": 0.0231,
      "num_tokens": 18314217.0,
      "reward": 0.109375,
      "reward_std": 0.1523444950580597,
      "rewards/simpleverify_reward/mean": 0.109375,
      "rewards/simpleverify_reward/std": 0.31241437792778015,
      "step": 12,
      "tools/generated_tokens": 1951.6171875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.046875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.724609375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2016.0,
      "completions/mean_length": 1782.244140625,
      "completions/mean_terminated_length": 1082.98583984375,
      "completions/min_length": 322.0,
      "completions/min_terminated_length": 322.0,
      "epoch": 0.009226401703335699,
      "frac_reward_zero_std": 0.625,
      "grad_norm": 15.494470596313477,
      "learning_rate": 9.759999999999998e-07,
      "loss": 0.018,
      "num_tokens": 19848120.0,
      "reward": 0.1640625,
      "reward_std": 0.14909161627292633,
      "rewards/simpleverify_reward/mean": 0.1640625,
      "rewards/simpleverify_reward/std": 0.37069445848464966,
      "step": 13,
      "tools/generated_tokens": 1879.98046875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.126953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.607421875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2021.0,
      "completions/mean_length": 1726.068359375,
      "completions/mean_terminated_length": 1227.9552001953125,
      "completions/min_length": 259.0,
      "completions/min_terminated_length": 259.0,
      "epoch": 0.0099361249112846,
      "frac_reward_zero_std": 0.4375,
      "grad_norm": 41.79543685913086,
      "learning_rate": 9.74e-07,
      "loss": 0.0703,
      "num_tokens": 21333382.0,
      "reward": 0.275390625,
      "reward_std": 0.2432900071144104,
      "rewards/simpleverify_reward/mean": 0.275390625,
      "rewards/simpleverify_reward/std": 0.44714778661727905,
      "step": 14,
      "tools/generated_tokens": 1796.00390625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.1171875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.71875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2000.0,
      "completions/mean_length": 1750.638671875,
      "completions/mean_terminated_length": 990.7152709960938,
      "completions/min_length": 333.0,
      "completions/min_terminated_length": 333.0,
      "epoch": 0.0106458481192335,
      "frac_reward_zero_std": 0.5625,
      "grad_norm": 39.885501861572266,
      "learning_rate": 9.72e-07,
      "loss": 0.0313,
      "num_tokens": 22795072.0,
      "reward": 0.1875,
      "reward_std": 0.1740870624780655,
      "rewards/simpleverify_reward/mean": 0.1875,
      "rewards/simpleverify_reward/std": 0.39069411158561707,
      "step": 15,
      "tools/generated_tokens": 1783.083984375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.66015625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2033.0,
      "completions/mean_length": 1717.16796875,
      "completions/mean_terminated_length": 1074.5172119140625,
      "completions/min_length": 343.0,
      "completions/min_terminated_length": 343.0,
      "epoch": 0.0113555713271824,
      "frac_reward_zero_std": 0.40625,
      "grad_norm": 19.833545684814453,
      "learning_rate": 9.7e-07,
      "loss": 0.0364,
      "num_tokens": 24247709.0,
      "reward": 0.197265625,
      "reward_std": 0.23469552397727966,
      "rewards/simpleverify_reward/mean": 0.197265625,
      "rewards/simpleverify_reward/std": 0.3983237147331238,
      "step": 16,
      "tools/generated_tokens": 1785.98046875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.087890625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.86328125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2039.0,
      "completions/mean_length": 1971.453125,
      "completions/mean_terminated_length": 1488.1142578125,
      "completions/min_length": 543.0,
      "completions/min_terminated_length": 543.0,
      "epoch": 0.0120652945351313,
      "frac_reward_zero_std": 0.6875,
      "grad_norm": 8.582590103149414,
      "learning_rate": 9.679999999999999e-07,
      "loss": 0.008,
      "num_tokens": 25787050.0,
      "reward": 0.0703125,
      "reward_std": 0.12418891489505768,
      "rewards/simpleverify_reward/mean": 0.0703125,
      "rewards/simpleverify_reward/std": 0.25592297315597534,
      "step": 17,
      "tools/generated_tokens": 2008.291015625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.03125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.76171875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2032.0,
      "completions/mean_length": 1834.615234375,
      "completions/mean_terminated_length": 1152.4835205078125,
      "completions/min_length": 283.0,
      "completions/min_terminated_length": 283.0,
      "epoch": 0.0127750177430802,
      "frac_reward_zero_std": 0.5625,
      "grad_norm": 69.20243072509766,
      "learning_rate": 9.66e-07,
      "loss": 0.0479,
      "num_tokens": 27327956.0,
      "reward": 0.1484375,
      "reward_std": 0.18281693756580353,
      "rewards/simpleverify_reward/mean": 0.1484375,
      "rewards/simpleverify_reward/std": 0.35588082671165466,
      "step": 18,
      "tools/generated_tokens": 1892.3359375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.107421875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.759765625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 1996.0,
      "completions/mean_length": 1836.240234375,
      "completions/mean_terminated_length": 1166.5284423828125,
      "completions/min_length": 242.0,
      "completions/min_terminated_length": 242.0,
      "epoch": 0.0134847409510291,
      "frac_reward_zero_std": 0.71875,
      "grad_norm": 20.689762115478516,
      "learning_rate": 9.64e-07,
      "loss": 0.0157,
      "num_tokens": 28807323.0,
      "reward": 0.13671875,
      "reward_std": 0.11257697641849518,
      "rewards/simpleverify_reward/mean": 0.13671875,
      "rewards/simpleverify_reward/std": 0.3438861668109894,
      "step": 19,
      "tools/generated_tokens": 1861.337890625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0546875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.861328125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2030.0,
      "completions/mean_length": 1922.796875,
      "completions/mean_terminated_length": 1145.126708984375,
      "completions/min_length": 357.0,
      "completions/min_terminated_length": 357.0,
      "epoch": 0.014194464158977998,
      "frac_reward_zero_std": 0.75,
      "grad_norm": 8.300631523132324,
      "learning_rate": 9.619999999999999e-07,
      "loss": 0.0075,
      "num_tokens": 30324785.0,
      "reward": 0.04296875,
      "reward_std": 0.08714932948350906,
      "rewards/simpleverify_reward/mean": 0.04296875,
      "rewards/simpleverify_reward/std": 0.2029850035905838,
      "step": 20,
      "tools/generated_tokens": 1948.033203125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.046875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.73046875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2016.0,
      "completions/mean_length": 1746.912109375,
      "completions/mean_terminated_length": 930.9202880859375,
      "completions/min_length": 327.0,
      "completions/min_terminated_length": 327.0,
      "epoch": 0.014904187366926898,
      "frac_reward_zero_std": 0.59375,
      "grad_norm": 85.41146087646484,
      "learning_rate": 9.6e-07,
      "loss": 0.0434,
      "num_tokens": 31783166.0,
      "reward": 0.20703125,
      "reward_std": 0.179582417011261,
      "rewards/simpleverify_reward/mean": 0.20703125,
      "rewards/simpleverify_reward/std": 0.40557438135147095,
      "step": 21,
      "tools/generated_tokens": 1747.951171875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.091796875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.671875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2012.0,
      "completions/mean_length": 1741.681640625,
      "completions/mean_terminated_length": 1114.4583740234375,
      "completions/min_length": 390.0,
      "completions/min_terminated_length": 390.0,
      "epoch": 0.015613910574875798,
      "frac_reward_zero_std": 0.625,
      "grad_norm": 14.292308807373047,
      "learning_rate": 9.58e-07,
      "loss": 0.0358,
      "num_tokens": 33209278.0,
      "reward": 0.18359375,
      "reward_std": 0.17547637224197388,
      "rewards/simpleverify_reward/mean": 0.18359375,
      "rewards/simpleverify_reward/std": 0.3875311613082886,
      "step": 22,
      "tools/generated_tokens": 1770.9765625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.04296875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.736328125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1814.4453125,
      "completions/mean_terminated_length": 1162.22216796875,
      "completions/min_length": 346.0,
      "completions/min_terminated_length": 346.0,
      "epoch": 0.016323633782824698,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 42.15079116821289,
      "learning_rate": 9.559999999999998e-07,
      "loss": 0.0415,
      "num_tokens": 34717288.0,
      "reward": 0.197265625,
      "reward_std": 0.19772270321846008,
      "rewards/simpleverify_reward/mean": 0.197265625,
      "rewards/simpleverify_reward/std": 0.3983237147331238,
      "step": 23,
      "tools/generated_tokens": 1808.04296875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.11328125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.740234375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2038.0,
      "completions/mean_length": 1832.916015625,
      "completions/mean_terminated_length": 1220.007568359375,
      "completions/min_length": 438.0,
      "completions/min_terminated_length": 438.0,
      "epoch": 0.017033356990773598,
      "frac_reward_zero_std": 0.46875,
      "grad_norm": 24.988969802856445,
      "learning_rate": 9.539999999999999e-07,
      "loss": 0.0388,
      "num_tokens": 36205714.0,
      "reward": 0.18359375,
      "reward_std": 0.19503545761108398,
      "rewards/simpleverify_reward/mean": 0.18359375,
      "rewards/simpleverify_reward/std": 0.3875311613082886,
      "step": 24,
      "tools/generated_tokens": 1894.955078125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.052734375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.798828125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2029.0,
      "completions/mean_length": 1851.29296875,
      "completions/mean_terminated_length": 1070.1942138671875,
      "completions/min_length": 234.0,
      "completions/min_terminated_length": 234.0,
      "epoch": 0.017743080198722498,
      "frac_reward_zero_std": 0.65625,
      "grad_norm": 18.4696044921875,
      "learning_rate": 9.52e-07,
      "loss": 0.021,
      "num_tokens": 37685716.0,
      "reward": 0.123046875,
      "reward_std": 0.1331951916217804,
      "rewards/simpleverify_reward/mean": 0.123046875,
      "rewards/simpleverify_reward/std": 0.32881227135658264,
      "step": 25,
      "tools/generated_tokens": 1857.87109375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.05078125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.76953125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2041.0,
      "completions/mean_length": 1840.154296875,
      "completions/mean_terminated_length": 1146.1610107421875,
      "completions/min_length": 181.0,
      "completions/min_terminated_length": 181.0,
      "epoch": 0.018452803406671398,
      "frac_reward_zero_std": 0.625,
      "grad_norm": 24.909900665283203,
      "learning_rate": 9.499999999999999e-07,
      "loss": 0.0281,
      "num_tokens": 39184649.0,
      "reward": 0.13671875,
      "reward_std": 0.15538014471530914,
      "rewards/simpleverify_reward/mean": 0.13671875,
      "rewards/simpleverify_reward/std": 0.3438861668109894,
      "step": 26,
      "tools/generated_tokens": 1856.806640625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.080078125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.8125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2038.0,
      "completions/mean_length": 1859.94140625,
      "completions/mean_terminated_length": 1045.0208740234375,
      "completions/min_length": 257.0,
      "completions/min_terminated_length": 257.0,
      "epoch": 0.0191625266146203,
      "frac_reward_zero_std": 0.65625,
      "grad_norm": 30.26369857788086,
      "learning_rate": 9.479999999999999e-07,
      "loss": 0.0279,
      "num_tokens": 40668405.0,
      "reward": 0.138671875,
      "reward_std": 0.14079925417900085,
      "rewards/simpleverify_reward/mean": 0.138671875,
      "rewards/simpleverify_reward/std": 0.34594178199768066,
      "step": 27,
      "tools/generated_tokens": 1890.923828125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.046875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.7890625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2028.0,
      "completions/mean_length": 1818.103515625,
      "completions/mean_terminated_length": 958.120361328125,
      "completions/min_length": 236.0,
      "completions/min_terminated_length": 236.0,
      "epoch": 0.0198722498225692,
      "frac_reward_zero_std": 0.65625,
      "grad_norm": 12.765514373779297,
      "learning_rate": 9.459999999999999e-07,
      "loss": 0.0132,
      "num_tokens": 42123534.0,
      "reward": 0.11328125,
      "reward_std": 0.12384280562400818,
      "rewards/simpleverify_reward/mean": 0.11328125,
      "rewards/simpleverify_reward/std": 0.3172462284564972,
      "step": 28,
      "tools/generated_tokens": 1846.5,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.029296875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.728515625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2037.0,
      "completions/mean_length": 1843.615234375,
      "completions/mean_terminated_length": 1295.1583251953125,
      "completions/min_length": 321.0,
      "completions/min_terminated_length": 321.0,
      "epoch": 0.0205819730305181,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 21.552108764648438,
      "learning_rate": 9.439999999999999e-07,
      "loss": 0.0635,
      "num_tokens": 43593417.0,
      "reward": 0.23046875,
      "reward_std": 0.23923486471176147,
      "rewards/simpleverify_reward/mean": 0.23046875,
      "rewards/simpleverify_reward/std": 0.42154473066329956,
      "step": 29,
      "tools/generated_tokens": 1877.82421875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.03515625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.79296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2026.0,
      "completions/mean_length": 1880.07421875,
      "completions/mean_terminated_length": 1236.8868408203125,
      "completions/min_length": 443.0,
      "completions/min_terminated_length": 443.0,
      "epoch": 0.021291696238467,
      "frac_reward_zero_std": 0.65625,
      "grad_norm": 14.616175651550293,
      "learning_rate": 9.419999999999999e-07,
      "loss": 0.0197,
      "num_tokens": 45095058.0,
      "reward": 0.12109375,
      "reward_std": 0.12615203857421875,
      "rewards/simpleverify_reward/mean": 0.12109375,
      "rewards/simpleverify_reward/std": 0.3265552520751953,
      "step": 30,
      "tools/generated_tokens": 1914.46875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.048828125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.79296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2038.0,
      "completions/mean_length": 1867.53125,
      "completions/mean_terminated_length": 1176.3018798828125,
      "completions/min_length": 431.0,
      "completions/min_terminated_length": 431.0,
      "epoch": 0.0220014194464159,
      "frac_reward_zero_std": 0.59375,
      "grad_norm": 7.746190071105957,
      "learning_rate": 9.399999999999999e-07,
      "loss": 0.0313,
      "num_tokens": 46557868.0,
      "reward": 0.16796875,
      "reward_std": 0.16081562638282776,
      "rewards/simpleverify_reward/mean": 0.16796875,
      "rewards/simpleverify_reward/std": 0.374204158782959,
      "step": 31,
      "tools/generated_tokens": 1892.236328125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.02734375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.80859375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2035.0,
      "completions/mean_length": 1920.58203125,
      "completions/mean_terminated_length": 1382.30615234375,
      "completions/min_length": 775.0,
      "completions/min_terminated_length": 775.0,
      "epoch": 0.0227111426543648,
      "frac_reward_zero_std": 0.78125,
      "grad_norm": 1.3792033195495605,
      "learning_rate": 9.379999999999998e-07,
      "loss": 0.015,
      "num_tokens": 48050730.0,
      "reward": 0.1015625,
      "reward_std": 0.0932510495185852,
      "rewards/simpleverify_reward/mean": 0.1015625,
      "rewards/simpleverify_reward/std": 0.30236753821372986,
      "step": 32,
      "tools/generated_tokens": 1943.91796875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.017578125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.73046875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1814.498046875,
      "completions/mean_terminated_length": 1181.6739501953125,
      "completions/min_length": 305.0,
      "completions/min_terminated_length": 305.0,
      "epoch": 0.0234208658623137,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 53.03191375732422,
      "learning_rate": 9.36e-07,
      "loss": 0.0555,
      "num_tokens": 49552140.0,
      "reward": 0.20703125,
      "reward_std": 0.2064279466867447,
      "rewards/simpleverify_reward/mean": 0.20703125,
      "rewards/simpleverify_reward/std": 0.40557438135147095,
      "step": 33,
      "tools/generated_tokens": 1840.412109375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.08984375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.693359375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2032.0,
      "completions/mean_length": 1787.427734375,
      "completions/mean_terminated_length": 1198.2357177734375,
      "completions/min_length": 363.0,
      "completions/min_terminated_length": 363.0,
      "epoch": 0.0241305890702626,
      "frac_reward_zero_std": 0.59375,
      "grad_norm": 26.05194854736328,
      "learning_rate": 9.34e-07,
      "loss": 0.0432,
      "num_tokens": 51030975.0,
      "reward": 0.18359375,
      "reward_std": 0.18866002559661865,
      "rewards/simpleverify_reward/mean": 0.18359375,
      "rewards/simpleverify_reward/std": 0.3875311613082886,
      "step": 34,
      "tools/generated_tokens": 1831.388671875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.056640625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.751953125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2032.0,
      "completions/mean_length": 1867.685546875,
      "completions/mean_terminated_length": 1321.06298828125,
      "completions/min_length": 351.0,
      "completions/min_terminated_length": 351.0,
      "epoch": 0.0248403122782115,
      "frac_reward_zero_std": 0.53125,
      "grad_norm": 3.4410009384155273,
      "learning_rate": 9.32e-07,
      "loss": 0.0305,
      "num_tokens": 52495952.0,
      "reward": 0.173828125,
      "reward_std": 0.2005443572998047,
      "rewards/simpleverify_reward/mean": 0.173828125,
      "rewards/simpleverify_reward/std": 0.3793322443962097,
      "step": 35,
      "tools/generated_tokens": 1893.0,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.021484375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.708984375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1821.4921875,
      "completions/mean_terminated_length": 1269.6644287109375,
      "completions/min_length": 240.0,
      "completions/min_terminated_length": 240.0,
      "epoch": 0.0255500354861604,
      "frac_reward_zero_std": 0.59375,
      "grad_norm": 46.663509368896484,
      "learning_rate": 9.3e-07,
      "loss": 0.0409,
      "num_tokens": 53988033.0,
      "reward": 0.177734375,
      "reward_std": 0.1667589247226715,
      "rewards/simpleverify_reward/mean": 0.177734375,
      "rewards/simpleverify_reward/std": 0.3826628625392914,
      "step": 36,
      "tools/generated_tokens": 1839.337890625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.07421875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.765625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2039.0,
      "completions/mean_length": 1839.720703125,
      "completions/mean_terminated_length": 1159.3416748046875,
      "completions/min_length": 268.0,
      "completions/min_terminated_length": 268.0,
      "epoch": 0.0262597586941093,
      "frac_reward_zero_std": 0.65625,
      "grad_norm": 21.043195724487305,
      "learning_rate": 9.28e-07,
      "loss": 0.0215,
      "num_tokens": 55450933.0,
      "reward": 0.169921875,
      "reward_std": 0.1355608105659485,
      "rewards/simpleverify_reward/mean": 0.169921875,
      "rewards/simpleverify_reward/std": 0.3759314715862274,
      "step": 37,
      "tools/generated_tokens": 1869.822265625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.037109375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.63671875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2035.0,
      "completions/mean_length": 1681.87109375,
      "completions/mean_terminated_length": 1040.1612548828125,
      "completions/min_length": 245.0,
      "completions/min_terminated_length": 245.0,
      "epoch": 0.0269694819020582,
      "frac_reward_zero_std": 0.5625,
      "grad_norm": 30.15522003173828,
      "learning_rate": 9.26e-07,
      "loss": 0.0169,
      "num_tokens": 56844186.0,
      "reward": 0.30078125,
      "reward_std": 0.17884942889213562,
      "rewards/simpleverify_reward/mean": 0.30078125,
      "rewards/simpleverify_reward/std": 0.45904624462127686,
      "step": 38,
      "tools/generated_tokens": 1704.990234375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.046875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.794921875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2024.0,
      "completions/mean_length": 1878.779296875,
      "completions/mean_terminated_length": 1222.84765625,
      "completions/min_length": 317.0,
      "completions/min_terminated_length": 317.0,
      "epoch": 0.027679205110007096,
      "frac_reward_zero_std": 0.59375,
      "grad_norm": 6.172724723815918,
      "learning_rate": 9.24e-07,
      "loss": 0.0258,
      "num_tokens": 58305698.0,
      "reward": 0.162109375,
      "reward_std": 0.15479376912117004,
      "rewards/simpleverify_reward/mean": 0.162109375,
      "rewards/simpleverify_reward/std": 0.3689115643501282,
      "step": 39,
      "tools/generated_tokens": 1886.451171875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0078125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.802734375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2040.0,
      "completions/mean_length": 1937.404296875,
      "completions/mean_terminated_length": 1487.3564453125,
      "completions/min_length": 419.0,
      "completions/min_terminated_length": 419.0,
      "epoch": 0.028388928317955996,
      "frac_reward_zero_std": 0.59375,
      "grad_norm": 10.753429412841797,
      "learning_rate": 9.22e-07,
      "loss": 0.0174,
      "num_tokens": 59833936.0,
      "reward": 0.12109375,
      "reward_std": 0.1767607480287552,
      "rewards/simpleverify_reward/mean": 0.12109375,
      "rewards/simpleverify_reward/std": 0.3265552520751953,
      "step": 40,
      "tools/generated_tokens": 1979.751953125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.04296875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.740234375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2030.0,
      "completions/mean_length": 1829.111328125,
      "completions/mean_terminated_length": 1205.3609619140625,
      "completions/min_length": 348.0,
      "completions/min_terminated_length": 348.0,
      "epoch": 0.029098651525904896,
      "frac_reward_zero_std": 0.625,
      "grad_norm": 10.790342330932617,
      "learning_rate": 9.2e-07,
      "loss": 0.0154,
      "num_tokens": 61294420.0,
      "reward": 0.109375,
      "reward_std": 0.15080136060714722,
      "rewards/simpleverify_reward/mean": 0.109375,
      "rewards/simpleverify_reward/std": 0.31241437792778015,
      "step": 41,
      "tools/generated_tokens": 1840.908203125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.048828125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.748046875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2040.0,
      "completions/mean_length": 1854.2421875,
      "completions/mean_terminated_length": 1278.9766845703125,
      "completions/min_length": 458.0,
      "completions/min_terminated_length": 458.0,
      "epoch": 0.029808374733853796,
      "frac_reward_zero_std": 0.625,
      "grad_norm": 0.21703369915485382,
      "learning_rate": 9.18e-07,
      "loss": 0.0217,
      "num_tokens": 62760115.0,
      "reward": 0.130859375,
      "reward_std": 0.13282598555088043,
      "rewards/simpleverify_reward/mean": 0.130859375,
      "rewards/simpleverify_reward/std": 0.33757632970809937,
      "step": 42,
      "tools/generated_tokens": 1882.2421875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0234375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.802734375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2030.0,
      "completions/mean_length": 1878.4296875,
      "completions/mean_terminated_length": 1188.39599609375,
      "completions/min_length": 346.0,
      "completions/min_terminated_length": 346.0,
      "epoch": 0.030518097941802696,
      "frac_reward_zero_std": 0.625,
      "grad_norm": 5.473078727722168,
      "learning_rate": 9.16e-07,
      "loss": 0.0123,
      "num_tokens": 64235546.0,
      "reward": 0.134765625,
      "reward_std": 0.13188038766384125,
      "rewards/simpleverify_reward/mean": 0.134765625,
      "rewards/simpleverify_reward/std": 0.3418070077896118,
      "step": 43,
      "tools/generated_tokens": 1904.396484375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.029296875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.818359375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1942.9921875,
      "completions/mean_terminated_length": 1469.8924560546875,
      "completions/min_length": 464.0,
      "completions/min_terminated_length": 464.0,
      "epoch": 0.031227821149751596,
      "frac_reward_zero_std": 0.6875,
      "grad_norm": 2.0192646980285645,
      "learning_rate": 9.14e-07,
      "loss": 0.0289,
      "num_tokens": 65722118.0,
      "reward": 0.103515625,
      "reward_std": 0.1321677267551422,
      "rewards/simpleverify_reward/mean": 0.103515625,
      "rewards/simpleverify_reward/std": 0.30492907762527466,
      "step": 44,
      "tools/generated_tokens": 1950.16796875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0078125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.6171875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1736.53515625,
      "completions/mean_terminated_length": 1234.3775634765625,
      "completions/min_length": 380.0,
      "completions/min_terminated_length": 380.0,
      "epoch": 0.0319375443577005,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 0.3154919445514679,
      "learning_rate": 9.12e-07,
      "loss": 0.0222,
      "num_tokens": 67115625.0,
      "reward": 0.2421875,
      "reward_std": 0.1919400990009308,
      "rewards/simpleverify_reward/mean": 0.2421875,
      "rewards/simpleverify_reward/std": 0.42882615327835083,
      "step": 45,
      "tools/generated_tokens": 1760.548828125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.025390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.767578125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1907.576171875,
      "completions/mean_terminated_length": 1443.8236083984375,
      "completions/min_length": 616.0,
      "completions/min_terminated_length": 616.0,
      "epoch": 0.032647267565649396,
      "frac_reward_zero_std": 0.5625,
      "grad_norm": 0.23441001772880554,
      "learning_rate": 9.1e-07,
      "loss": 0.0163,
      "num_tokens": 68601601.0,
      "reward": 0.15625,
      "reward_std": 0.1701846569776535,
      "rewards/simpleverify_reward/mean": 0.15625,
      "rewards/simpleverify_reward/std": 0.36344730854034424,
      "step": 46,
      "tools/generated_tokens": 1935.0078125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.021484375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.640625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1781.044921875,
      "completions/mean_terminated_length": 1305.16845703125,
      "completions/min_length": 256.0,
      "completions/min_terminated_length": 256.0,
      "epoch": 0.0333569907735983,
      "frac_reward_zero_std": 0.4375,
      "grad_norm": 4.0652875900268555,
      "learning_rate": 9.08e-07,
      "loss": 0.036,
      "num_tokens": 70023445.0,
      "reward": 0.251953125,
      "reward_std": 0.2161707878112793,
      "rewards/simpleverify_reward/mean": 0.251953125,
      "rewards/simpleverify_reward/std": 0.43455907702445984,
      "step": 47,
      "tools/generated_tokens": 1804.349609375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.02734375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.6875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2029.0,
      "completions/mean_length": 1815.947265625,
      "completions/mean_terminated_length": 1305.4312744140625,
      "completions/min_length": 333.0,
      "completions/min_terminated_length": 333.0,
      "epoch": 0.034066713981547196,
      "frac_reward_zero_std": 0.5625,
      "grad_norm": 10.052021026611328,
      "learning_rate": 9.06e-07,
      "loss": 0.0004,
      "num_tokens": 71485618.0,
      "reward": 0.158203125,
      "reward_std": 0.1630263328552246,
      "rewards/simpleverify_reward/mean": 0.158203125,
      "rewards/simpleverify_reward/std": 0.36528825759887695,
      "step": 48,
      "tools/generated_tokens": 1851.4453125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.7421875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2031.0,
      "completions/mean_length": 1798.822265625,
      "completions/mean_terminated_length": 1081.492431640625,
      "completions/min_length": 314.0,
      "completions/min_terminated_length": 314.0,
      "epoch": 0.0347764371894961,
      "frac_reward_zero_std": 0.65625,
      "grad_norm": 0.5334547758102417,
      "learning_rate": 9.039999999999999e-07,
      "loss": 0.0102,
      "num_tokens": 72903778.0,
      "reward": 0.125,
      "reward_std": 0.13401323556900024,
      "rewards/simpleverify_reward/mean": 0.125,
      "rewards/simpleverify_reward/std": 0.3310423493385315,
      "step": 49,
      "tools/generated_tokens": 1807.587890625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.009765625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.71875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2034.0,
      "completions/mean_length": 1811.291015625,
      "completions/mean_terminated_length": 1206.3680419921875,
      "completions/min_length": 344.0,
      "completions/min_terminated_length": 344.0,
      "epoch": 0.035486160397444996,
      "frac_reward_zero_std": 0.59375,
      "grad_norm": 23.335891723632812,
      "learning_rate": 9.02e-07,
      "loss": 0.025,
      "num_tokens": 74357888.0,
      "reward": 0.2109375,
      "reward_std": 0.14200212061405182,
      "rewards/simpleverify_reward/mean": 0.2109375,
      "rewards/simpleverify_reward/std": 0.4083731174468994,
      "step": 50,
      "tools/generated_tokens": 1824.443359375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.05078125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.66015625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2034.0,
      "completions/mean_length": 1727.701171875,
      "completions/mean_terminated_length": 1105.511474609375,
      "completions/min_length": 262.0,
      "completions/min_terminated_length": 262.0,
      "epoch": 0.0361958836053939,
      "frac_reward_zero_std": 0.59375,
      "grad_norm": 5.091102123260498,
      "learning_rate": 9e-07,
      "loss": 0.0141,
      "num_tokens": 75775001.0,
      "reward": 0.197265625,
      "reward_std": 0.1867963969707489,
      "rewards/simpleverify_reward/mean": 0.197265625,
      "rewards/simpleverify_reward/std": 0.3983237147331238,
      "step": 51,
      "tools/generated_tokens": 1763.9453125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0546875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.009765625
    },
    {
      "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": 0.681640625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2032.0,
      "completions/mean_length": 1759.84765625,
      "completions/mean_terminated_length": 1142.8834228515625,
      "completions/min_length": 329.0,
      "completions/min_terminated_length": 329.0,
      "epoch": 0.036905606813342796,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 36.26031494140625,
      "learning_rate": 8.98e-07,
      "loss": 0.0436,
      "num_tokens": 77193536.0,
      "reward": 0.240234375,
      "reward_std": 0.18864649534225464,
      "rewards/simpleverify_reward/mean": 0.240234375,
      "rewards/simpleverify_reward/std": 0.4276435375213623,
      "step": 52,
      "tools/generated_tokens": 1783.0,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.033203125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.669921875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 1942.0,
      "completions/mean_length": 1681.578125,
      "completions/mean_terminated_length": 937.8934936523438,
      "completions/min_length": 236.0,
      "completions/min_terminated_length": 236.0,
      "epoch": 0.03761533002129169,
      "frac_reward_zero_std": 0.53125,
      "grad_norm": 7.171099662780762,
      "learning_rate": 8.96e-07,
      "loss": 0.0363,
      "num_tokens": 78556367.0,
      "reward": 0.205078125,
      "reward_std": 0.17623455822467804,
      "rewards/simpleverify_reward/mean": 0.205078125,
      "rewards/simpleverify_reward/std": 0.4041535556316376,
      "step": 53,
      "tools/generated_tokens": 1690.765625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.021484375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.6875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2020.0,
      "completions/mean_length": 1765.03125,
      "completions/mean_terminated_length": 1142.5,
      "completions/min_length": 303.0,
      "completions/min_terminated_length": 303.0,
      "epoch": 0.0383250532292406,
      "frac_reward_zero_std": 0.5625,
      "grad_norm": 16.39349365234375,
      "learning_rate": 8.939999999999999e-07,
      "loss": 0.0326,
      "num_tokens": 80022171.0,
      "reward": 0.234375,
      "reward_std": 0.20781400799751282,
      "rewards/simpleverify_reward/mean": 0.234375,
      "rewards/simpleverify_reward/std": 0.42402184009552,
      "step": 54,
      "tools/generated_tokens": 1837.24609375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.078125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.7421875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1844.994140625,
      "completions/mean_terminated_length": 1260.5833740234375,
      "completions/min_length": 691.0,
      "completions/min_terminated_length": 691.0,
      "epoch": 0.03903477643718949,
      "frac_reward_zero_std": 0.6875,
      "grad_norm": 19.338659286499023,
      "learning_rate": 8.92e-07,
      "loss": 0.0251,
      "num_tokens": 81470788.0,
      "reward": 0.208984375,
      "reward_std": 0.11990302801132202,
      "rewards/simpleverify_reward/mean": 0.208984375,
      "rewards/simpleverify_reward/std": 0.40698084235191345,
      "step": 55,
      "tools/generated_tokens": 1850.98828125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0078125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.740234375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2020.0,
      "completions/mean_length": 1777.115234375,
      "completions/mean_terminated_length": 1005.1954956054688,
      "completions/min_length": 245.0,
      "completions/min_terminated_length": 245.0,
      "epoch": 0.0397444996451384,
      "frac_reward_zero_std": 0.625,
      "grad_norm": 0.2824317216873169,
      "learning_rate": 8.9e-07,
      "loss": 0.0253,
      "num_tokens": 82872151.0,
      "reward": 0.1953125,
      "reward_std": 0.14667484164237976,
      "rewards/simpleverify_reward/mean": 0.1953125,
      "rewards/simpleverify_reward/std": 0.3968288004398346,
      "step": 56,
      "tools/generated_tokens": 1787.671875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0078125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.837890625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2025.0,
      "completions/mean_length": 1949.140625,
      "completions/mean_terminated_length": 1438.1685791015625,
      "completions/min_length": 521.0,
      "completions/min_terminated_length": 521.0,
      "epoch": 0.04045422285308729,
      "frac_reward_zero_std": 0.71875,
      "grad_norm": 0.2156990021467209,
      "learning_rate": 8.88e-07,
      "loss": 0.0183,
      "num_tokens": 84357951.0,
      "reward": 0.1328125,
      "reward_std": 0.12000264972448349,
      "rewards/simpleverify_reward/mean": 0.1328125,
      "rewards/simpleverify_reward/std": 0.33970388770103455,
      "step": 57,
      "tools/generated_tokens": 1949.140625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.76953125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2021.0,
      "completions/mean_length": 1829.18359375,
      "completions/mean_terminated_length": 1098.559326171875,
      "completions/min_length": 422.0,
      "completions/min_terminated_length": 422.0,
      "epoch": 0.0411639460610362,
      "frac_reward_zero_std": 0.75,
      "grad_norm": 0.22395376861095428,
      "learning_rate": 8.86e-07,
      "loss": 0.0081,
      "num_tokens": 85783005.0,
      "reward": 0.158203125,
      "reward_std": 0.1014629602432251,
      "rewards/simpleverify_reward/mean": 0.158203125,
      "rewards/simpleverify_reward/std": 0.36528825759887695,
      "step": 58,
      "tools/generated_tokens": 1829.18359375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.8125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2039.0,
      "completions/mean_length": 1888.857421875,
      "completions/mean_terminated_length": 1199.2396240234375,
      "completions/min_length": 355.0,
      "completions/min_terminated_length": 355.0,
      "epoch": 0.04187366926898509,
      "frac_reward_zero_std": 0.75,
      "grad_norm": 8.763437271118164,
      "learning_rate": 8.839999999999999e-07,
      "loss": 0.0073,
      "num_tokens": 87265499.0,
      "reward": 0.138671875,
      "reward_std": 0.08444078266620636,
      "rewards/simpleverify_reward/mean": 0.138671875,
      "rewards/simpleverify_reward/std": 0.34594178199768066,
      "step": 59,
      "tools/generated_tokens": 1903.90234375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0234375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.75390625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1858.107421875,
      "completions/mean_terminated_length": 1276.373046875,
      "completions/min_length": 454.0,
      "completions/min_terminated_length": 454.0,
      "epoch": 0.042583392476934,
      "frac_reward_zero_std": 0.46875,
      "grad_norm": 18.061670303344727,
      "learning_rate": 8.82e-07,
      "loss": 0.0248,
      "num_tokens": 88749385.0,
      "reward": 0.19921875,
      "reward_std": 0.20891696214675903,
      "rewards/simpleverify_reward/mean": 0.19921875,
      "rewards/simpleverify_reward/std": 0.39980348944664,
      "step": 60,
      "tools/generated_tokens": 1884.408203125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.03125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.685546875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1849.626953125,
      "completions/mean_terminated_length": 1417.1490478515625,
      "completions/min_length": 397.0,
      "completions/min_terminated_length": 397.0,
      "epoch": 0.043293115684882894,
      "frac_reward_zero_std": 0.65625,
      "grad_norm": 0.2572893798351288,
      "learning_rate": 8.799999999999999e-07,
      "loss": 0.0165,
      "num_tokens": 90187996.0,
      "reward": 0.1953125,
      "reward_std": 0.15167921781539917,
      "rewards/simpleverify_reward/mean": 0.1953125,
      "rewards/simpleverify_reward/std": 0.3968288004398346,
      "step": 61,
      "tools/generated_tokens": 1856.0,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.765625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2009.0,
      "completions/mean_length": 1904.228515625,
      "completions/mean_terminated_length": 1434.5750732421875,
      "completions/min_length": 362.0,
      "completions/min_terminated_length": 362.0,
      "epoch": 0.0440028388928318,
      "frac_reward_zero_std": 0.65625,
      "grad_norm": 0.6352214813232422,
      "learning_rate": 8.78e-07,
      "loss": 0.0278,
      "num_tokens": 91670743.0,
      "reward": 0.123046875,
      "reward_std": 0.14053335785865784,
      "rewards/simpleverify_reward/mean": 0.123046875,
      "rewards/simpleverify_reward/std": 0.32881227135658264,
      "step": 62,
      "tools/generated_tokens": 1923.494140625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.017578125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.65234375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1702.21484375,
      "completions/mean_terminated_length": 1053.382080078125,
      "completions/min_length": 291.0,
      "completions/min_terminated_length": 291.0,
      "epoch": 0.044712562100780694,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 54.840675354003906,
      "learning_rate": 8.76e-07,
      "loss": 0.0438,
      "num_tokens": 93070074.0,
      "reward": 0.2578125,
      "reward_std": 0.20937609672546387,
      "rewards/simpleverify_reward/mean": 0.2578125,
      "rewards/simpleverify_reward/std": 0.43785804510116577,
      "step": 63,
      "tools/generated_tokens": 1707.8203125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.06640625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.828125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2035.0,
      "completions/mean_length": 1907.884765625,
      "completions/mean_terminated_length": 1232.7841796875,
      "completions/min_length": 257.0,
      "completions/min_terminated_length": 257.0,
      "epoch": 0.0454222853087296,
      "frac_reward_zero_std": 0.625,
      "grad_norm": 14.823603630065918,
      "learning_rate": 8.739999999999999e-07,
      "loss": 0.0117,
      "num_tokens": 94556814.0,
      "reward": 0.1171875,
      "reward_std": 0.14722147583961487,
      "rewards/simpleverify_reward/mean": 0.1171875,
      "rewards/simpleverify_reward/std": 0.32195815443992615,
      "step": 64,
      "tools/generated_tokens": 1914.541015625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.025390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.6640625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2040.0,
      "completions/mean_length": 1801.744140625,
      "completions/mean_terminated_length": 1314.9593505859375,
      "completions/min_length": 418.0,
      "completions/min_terminated_length": 418.0,
      "epoch": 0.046132008516678494,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 8.701075553894043,
      "learning_rate": 8.72e-07,
      "loss": 0.0288,
      "num_tokens": 95998077.0,
      "reward": 0.234375,
      "reward_std": 0.21684160828590393,
      "rewards/simpleverify_reward/mean": 0.234375,
      "rewards/simpleverify_reward/std": 0.42402184009552,
      "step": 65,
      "tools/generated_tokens": 1830.9375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.04296875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.724609375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1781.724609375,
      "completions/mean_terminated_length": 1081.0992431640625,
      "completions/min_length": 447.0,
      "completions/min_terminated_length": 447.0,
      "epoch": 0.0468417317246274,
      "frac_reward_zero_std": 0.71875,
      "grad_norm": 21.933923721313477,
      "learning_rate": 8.699999999999999e-07,
      "loss": 0.0187,
      "num_tokens": 97416203.0,
      "reward": 0.234375,
      "reward_std": 0.11563194543123245,
      "rewards/simpleverify_reward/mean": 0.234375,
      "rewards/simpleverify_reward/std": 0.42402184009552,
      "step": 66,
      "tools/generated_tokens": 1785.359375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0234375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.7734375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2037.0,
      "completions/mean_length": 1867.197265625,
      "completions/mean_terminated_length": 1249.97412109375,
      "completions/min_length": 345.0,
      "completions/min_terminated_length": 345.0,
      "epoch": 0.047551454932576294,
      "frac_reward_zero_std": 0.5625,
      "grad_norm": 1.883864402770996,
      "learning_rate": 8.68e-07,
      "loss": 0.0128,
      "num_tokens": 98887093.0,
      "reward": 0.158203125,
      "reward_std": 0.16653147339820862,
      "rewards/simpleverify_reward/mean": 0.158203125,
      "rewards/simpleverify_reward/std": 0.36528825759887695,
      "step": 67,
      "tools/generated_tokens": 1884.66796875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0234375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.7109375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2035.0,
      "completions/mean_length": 1897.841796875,
      "completions/mean_terminated_length": 1528.5338134765625,
      "completions/min_length": 701.0,
      "completions/min_terminated_length": 701.0,
      "epoch": 0.0482611781405252,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 4.292568206787109,
      "learning_rate": 8.659999999999999e-07,
      "loss": 0.0291,
      "num_tokens": 100365972.0,
      "reward": 0.21875,
      "reward_std": 0.2511081397533417,
      "rewards/simpleverify_reward/mean": 0.21875,
      "rewards/simpleverify_reward/std": 0.41380295157432556,
      "step": 68,
      "tools/generated_tokens": 1918.853515625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.017578125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.841796875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1933.568359375,
      "completions/mean_terminated_length": 1324.6790771484375,
      "completions/min_length": 525.0,
      "completions/min_terminated_length": 525.0,
      "epoch": 0.048970901348474094,
      "frac_reward_zero_std": 0.53125,
      "grad_norm": 5.0049214363098145,
      "learning_rate": 8.639999999999999e-07,
      "loss": 0.0238,
      "num_tokens": 101890713.0,
      "reward": 0.09375,
      "reward_std": 0.17109671235084534,
      "rewards/simpleverify_reward/mean": 0.09375,
      "rewards/simpleverify_reward/std": 0.29176566004753113,
      "step": 69,
      "tools/generated_tokens": 1979.40234375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.048828125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.658203125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2037.0,
      "completions/mean_length": 1793.9765625,
      "completions/mean_terminated_length": 1304.7999267578125,
      "completions/min_length": 432.0,
      "completions/min_terminated_length": 432.0,
      "epoch": 0.049680624556423,
      "frac_reward_zero_std": 0.46875,
      "grad_norm": 2.8965625762939453,
      "learning_rate": 8.62e-07,
      "loss": 0.0315,
      "num_tokens": 103339897.0,
      "reward": 0.201171875,
      "reward_std": 0.20484378933906555,
      "rewards/simpleverify_reward/mean": 0.201171875,
      "rewards/simpleverify_reward/std": 0.4012683033943176,
      "step": 70,
      "tools/generated_tokens": 1821.13671875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.02734375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.703125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1776.544921875,
      "completions/mean_terminated_length": 1133.625,
      "completions/min_length": 288.0,
      "completions/min_terminated_length": 288.0,
      "epoch": 0.050390347764371894,
      "frac_reward_zero_std": 0.53125,
      "grad_norm": 0.3445601463317871,
      "learning_rate": 8.599999999999999e-07,
      "loss": 0.0203,
      "num_tokens": 104760178.0,
      "reward": 0.19140625,
      "reward_std": 0.1847543716430664,
      "rewards/simpleverify_reward/mean": 0.19140625,
      "rewards/simpleverify_reward/std": 0.3937928080558777,
      "step": 71,
      "tools/generated_tokens": 1797.9921875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0234375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.7578125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2032.0,
      "completions/mean_length": 1873.455078125,
      "completions/mean_terminated_length": 1327.29833984375,
      "completions/min_length": 339.0,
      "completions/min_terminated_length": 339.0,
      "epoch": 0.0511000709723208,
      "frac_reward_zero_std": 0.5625,
      "grad_norm": 0.2811175584793091,
      "learning_rate": 8.58e-07,
      "loss": 0.0263,
      "num_tokens": 106208807.0,
      "reward": 0.208984375,
      "reward_std": 0.1785447597503662,
      "rewards/simpleverify_reward/mean": 0.208984375,
      "rewards/simpleverify_reward/std": 0.40698084235191345,
      "step": 72,
      "tools/generated_tokens": 1875.328125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.615234375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2023.0,
      "completions/mean_length": 1709.6640625,
      "completions/mean_terminated_length": 1168.6700439453125,
      "completions/min_length": 312.0,
      "completions/min_terminated_length": 312.0,
      "epoch": 0.051809794180269694,
      "frac_reward_zero_std": 0.5625,
      "grad_norm": 20.53804588317871,
      "learning_rate": 8.559999999999999e-07,
      "loss": 0.0274,
      "num_tokens": 107580590.0,
      "reward": 0.255859375,
      "reward_std": 0.16501638293266296,
      "rewards/simpleverify_reward/mean": 0.255859375,
      "rewards/simpleverify_reward/std": 0.43676990270614624,
      "step": 73,
      "tools/generated_tokens": 1718.234375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.015625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.703125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1823.33984375,
      "completions/mean_terminated_length": 1291.25,
      "completions/min_length": 432.0,
      "completions/min_terminated_length": 432.0,
      "epoch": 0.0525195173882186,
      "frac_reward_zero_std": 0.46875,
      "grad_norm": 0.43003737926483154,
      "learning_rate": 8.539999999999999e-07,
      "loss": 0.0146,
      "num_tokens": 109013391.0,
      "reward": 0.12109375,
      "reward_std": 0.19613981246948242,
      "rewards/simpleverify_reward/mean": 0.12109375,
      "rewards/simpleverify_reward/std": 0.3265552520751953,
      "step": 74,
      "tools/generated_tokens": 1835.0703125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.01171875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.67578125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2038.0,
      "completions/mean_length": 1748.568359375,
      "completions/mean_terminated_length": 1124.4517822265625,
      "completions/min_length": 226.0,
      "completions/min_terminated_length": 226.0,
      "epoch": 0.053229240596167494,
      "frac_reward_zero_std": 0.46875,
      "grad_norm": 19.066383361816406,
      "learning_rate": 8.52e-07,
      "loss": 0.0476,
      "num_tokens": 110453357.0,
      "reward": 0.24609375,
      "reward_std": 0.22384248673915863,
      "rewards/simpleverify_reward/mean": 0.24609375,
      "rewards/simpleverify_reward/std": 0.4311550557613373,
      "step": 75,
      "tools/generated_tokens": 1775.681640625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0703125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.69921875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2038.0,
      "completions/mean_length": 1767.37109375,
      "completions/mean_terminated_length": 1115.0,
      "completions/min_length": 340.0,
      "completions/min_terminated_length": 340.0,
      "epoch": 0.0539389638041164,
      "frac_reward_zero_std": 0.6875,
      "grad_norm": 0.23244716227054596,
      "learning_rate": 8.499999999999999e-07,
      "loss": 0.0299,
      "num_tokens": 111865312.0,
      "reward": 0.19921875,
      "reward_std": 0.10332095623016357,
      "rewards/simpleverify_reward/mean": 0.19921875,
      "rewards/simpleverify_reward/std": 0.39980348944664,
      "step": 76,
      "tools/generated_tokens": 1784.12890625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.01953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.626953125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2038.0,
      "completions/mean_length": 1671.2109375,
      "completions/mean_terminated_length": 1037.9686279296875,
      "completions/min_length": 155.0,
      "completions/min_terminated_length": 155.0,
      "epoch": 0.054648687012065295,
      "frac_reward_zero_std": 0.59375,
      "grad_norm": 0.28951776027679443,
      "learning_rate": 8.48e-07,
      "loss": 0.0216,
      "num_tokens": 113237334.0,
      "reward": 0.171875,
      "reward_std": 0.16008372604846954,
      "rewards/simpleverify_reward/mean": 0.171875,
      "rewards/simpleverify_reward/std": 0.3776407241821289,
      "step": 77,
      "tools/generated_tokens": 1680.10546875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.03515625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.67578125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1798.1015625,
      "completions/mean_terminated_length": 1277.2288818359375,
      "completions/min_length": 390.0,
      "completions/min_terminated_length": 390.0,
      "epoch": 0.05535841022001419,
      "frac_reward_zero_std": 0.40625,
      "grad_norm": 0.3478720486164093,
      "learning_rate": 8.459999999999999e-07,
      "loss": 0.0404,
      "num_tokens": 114648634.0,
      "reward": 0.25390625,
      "reward_std": 0.2499440759420395,
      "rewards/simpleverify_reward/mean": 0.25390625,
      "rewards/simpleverify_reward/std": 0.43567025661468506,
      "step": 78,
      "tools/generated_tokens": 1803.927734375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0078125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.5859375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2013.0,
      "completions/mean_length": 1673.763671875,
      "completions/mean_terminated_length": 1144.1839599609375,
      "completions/min_length": 395.0,
      "completions/min_terminated_length": 395.0,
      "epoch": 0.056068133427963095,
      "frac_reward_zero_std": 0.53125,
      "grad_norm": 4.278706073760986,
      "learning_rate": 8.439999999999999e-07,
      "loss": 0.0303,
      "num_tokens": 116026868.0,
      "reward": 0.302734375,
      "reward_std": 0.1883329451084137,
      "rewards/simpleverify_reward/mean": 0.302734375,
      "rewards/simpleverify_reward/std": 0.45989060401916504,
      "step": 79,
      "tools/generated_tokens": 1698.427734375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.73046875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1818.078125,
      "completions/mean_terminated_length": 1194.95654296875,
      "completions/min_length": 422.0,
      "completions/min_terminated_length": 422.0,
      "epoch": 0.05677785663591199,
      "frac_reward_zero_std": 0.625,
      "grad_norm": 7.619236946105957,
      "learning_rate": 8.419999999999999e-07,
      "loss": 0.0294,
      "num_tokens": 117463694.0,
      "reward": 0.201171875,
      "reward_std": 0.15295642614364624,
      "rewards/simpleverify_reward/mean": 0.201171875,
      "rewards/simpleverify_reward/std": 0.4012683033943176,
      "step": 80,
      "tools/generated_tokens": 1829.6875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.015625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.671875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1786.125,
      "completions/mean_terminated_length": 1249.90478515625,
      "completions/min_length": 353.0,
      "completions/min_terminated_length": 353.0,
      "epoch": 0.057487579843860895,
      "frac_reward_zero_std": 0.53125,
      "grad_norm": 6.234090805053711,
      "learning_rate": 8.399999999999999e-07,
      "loss": 0.0356,
      "num_tokens": 118882513.0,
      "reward": 0.25390625,
      "reward_std": 0.18712444603443146,
      "rewards/simpleverify_reward/mean": 0.25390625,
      "rewards/simpleverify_reward/std": 0.43567025661468506,
      "step": 81,
      "tools/generated_tokens": 1795.7265625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.01953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.77734375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1904.87109375,
      "completions/mean_terminated_length": 1405.1754150390625,
      "completions/min_length": 654.0,
      "completions/min_terminated_length": 654.0,
      "epoch": 0.05819730305180979,
      "frac_reward_zero_std": 0.625,
      "grad_norm": 1.654779314994812,
      "learning_rate": 8.38e-07,
      "loss": 0.0299,
      "num_tokens": 120368597.0,
      "reward": 0.123046875,
      "reward_std": 0.15443308651447296,
      "rewards/simpleverify_reward/mean": 0.123046875,
      "rewards/simpleverify_reward/std": 0.32881227135658264,
      "step": 82,
      "tools/generated_tokens": 1920.388671875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.015625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.001953125
    },
    {
      "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": 0.677734375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1765.00390625,
      "completions/mean_terminated_length": 1169.8544921875,
      "completions/min_length": 276.0,
      "completions/min_terminated_length": 276.0,
      "epoch": 0.058907026259758695,
      "frac_reward_zero_std": 0.4375,
      "grad_norm": 0.3756980895996094,
      "learning_rate": 8.359999999999999e-07,
      "loss": 0.0469,
      "num_tokens": 121769801.0,
      "reward": 0.2421875,
      "reward_std": 0.21928317844867706,
      "rewards/simpleverify_reward/mean": 0.2421875,
      "rewards/simpleverify_reward/std": 0.42882615327835083,
      "step": 83,
      "tools/generated_tokens": 1782.310546875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.013671875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.546875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1603.783203125,
      "completions/mean_terminated_length": 1067.659423828125,
      "completions/min_length": 192.0,
      "completions/min_terminated_length": 192.0,
      "epoch": 0.05961674946770759,
      "frac_reward_zero_std": 0.40625,
      "grad_norm": 0.35295289754867554,
      "learning_rate": 8.34e-07,
      "loss": 0.0293,
      "num_tokens": 123109400.0,
      "reward": 0.28125,
      "reward_std": 0.22112740576267242,
      "rewards/simpleverify_reward/mean": 0.28125,
      "rewards/simpleverify_reward/std": 0.45004892349243164,
      "step": 84,
      "tools/generated_tokens": 1631.49609375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.037109375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.798828125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1855.482421875,
      "completions/mean_terminated_length": 1091.0194091796875,
      "completions/min_length": 275.0,
      "completions/min_terminated_length": 275.0,
      "epoch": 0.060326472675656495,
      "frac_reward_zero_std": 0.65625,
      "grad_norm": 0.25946611166000366,
      "learning_rate": 8.319999999999999e-07,
      "loss": 0.0194,
      "num_tokens": 124562001.0,
      "reward": 0.12890625,
      "reward_std": 0.12825526297092438,
      "rewards/simpleverify_reward/mean": 0.12890625,
      "rewards/simpleverify_reward/std": 0.33542385697364807,
      "step": 85,
      "tools/generated_tokens": 1871.583984375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.013671875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.736328125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2034.0,
      "completions/mean_length": 1743.841796875,
      "completions/mean_terminated_length": 894.4518432617188,
      "completions/min_length": 214.0,
      "completions/min_terminated_length": 214.0,
      "epoch": 0.06103619588360539,
      "frac_reward_zero_std": 0.625,
      "grad_norm": 50.28761672973633,
      "learning_rate": 8.299999999999999e-07,
      "loss": 0.0262,
      "num_tokens": 125960520.0,
      "reward": 0.1875,
      "reward_std": 0.1424909383058548,
      "rewards/simpleverify_reward/mean": 0.1875,
      "rewards/simpleverify_reward/std": 0.39069411158561707,
      "step": 86,
      "tools/generated_tokens": 1747.744140625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.03125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.640625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2024.0,
      "completions/mean_length": 1745.390625,
      "completions/mean_terminated_length": 1205.95654296875,
      "completions/min_length": 303.0,
      "completions/min_terminated_length": 303.0,
      "epoch": 0.061745919091554295,
      "frac_reward_zero_std": 0.46875,
      "grad_norm": 37.87419891357422,
      "learning_rate": 8.28e-07,
      "loss": 0.0214,
      "num_tokens": 127387929.0,
      "reward": 0.21484375,
      "reward_std": 0.1921243965625763,
      "rewards/simpleverify_reward/mean": 0.21484375,
      "rewards/simpleverify_reward/std": 0.4111155867576599,
      "step": 87,
      "tools/generated_tokens": 1773.06640625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.03515625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.5234375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1579.421875,
      "completions/mean_terminated_length": 1064.7540283203125,
      "completions/min_length": 260.0,
      "completions/min_terminated_length": 260.0,
      "epoch": 0.06245564229950319,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 61.75159454345703,
      "learning_rate": 8.259999999999999e-07,
      "loss": 0.0531,
      "num_tokens": 128757950.0,
      "reward": 0.341796875,
      "reward_std": 0.20200853049755096,
      "rewards/simpleverify_reward/mean": 0.341796875,
      "rewards/simpleverify_reward/std": 0.4747757613658905,
      "step": 88,
      "tools/generated_tokens": 1600.693359375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.07421875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.6875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2037.0,
      "completions/mean_length": 1768.837890625,
      "completions/mean_terminated_length": 1154.6812744140625,
      "completions/min_length": 466.0,
      "completions/min_terminated_length": 466.0,
      "epoch": 0.0631653655074521,
      "frac_reward_zero_std": 0.59375,
      "grad_norm": 0.26727408170700073,
      "learning_rate": 8.24e-07,
      "loss": 0.0232,
      "num_tokens": 130175727.0,
      "reward": 0.244140625,
      "reward_std": 0.14233016967773438,
      "rewards/simpleverify_reward/mean": 0.244140625,
      "rewards/simpleverify_reward/std": 0.42999663949012756,
      "step": 89,
      "tools/generated_tokens": 1777.759765625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0234375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.611328125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1622.990234375,
      "completions/mean_terminated_length": 954.5075073242188,
      "completions/min_length": 242.0,
      "completions/min_terminated_length": 242.0,
      "epoch": 0.063875088715401,
      "frac_reward_zero_std": 0.5625,
      "grad_norm": 16.603391647338867,
      "learning_rate": 8.219999999999999e-07,
      "loss": 0.0402,
      "num_tokens": 131514749.0,
      "reward": 0.306640625,
      "reward_std": 0.15167227387428284,
      "rewards/simpleverify_reward/mean": 0.306640625,
      "rewards/simpleverify_reward/std": 0.4615498185157776,
      "step": 90,
      "tools/generated_tokens": 1634.154296875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0234375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.638671875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1726.927734375,
      "completions/mean_terminated_length": 1159.410888671875,
      "completions/min_length": 381.0,
      "completions/min_terminated_length": 381.0,
      "epoch": 0.06458481192334989,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 40.104278564453125,
      "learning_rate": 8.199999999999999e-07,
      "loss": 0.0519,
      "num_tokens": 132931787.0,
      "reward": 0.2265625,
      "reward_std": 0.22074052691459656,
      "rewards/simpleverify_reward/mean": 0.2265625,
      "rewards/simpleverify_reward/std": 0.4190165400505066,
      "step": 91,
      "tools/generated_tokens": 1732.62890625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.037109375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.72265625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2021.0,
      "completions/mean_length": 1824.234375,
      "completions/mean_terminated_length": 1241.18310546875,
      "completions/min_length": 351.0,
      "completions/min_terminated_length": 351.0,
      "epoch": 0.06529453513129879,
      "frac_reward_zero_std": 0.59375,
      "grad_norm": 7.339715957641602,
      "learning_rate": 8.179999999999999e-07,
      "loss": 0.0388,
      "num_tokens": 134375795.0,
      "reward": 0.21484375,
      "reward_std": 0.14914941787719727,
      "rewards/simpleverify_reward/mean": 0.21484375,
      "rewards/simpleverify_reward/std": 0.4111155867576599,
      "step": 92,
      "tools/generated_tokens": 1834.05859375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.02734375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.587890625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2037.0,
      "completions/mean_length": 1630.68359375,
      "completions/mean_terminated_length": 1035.364990234375,
      "completions/min_length": 194.0,
      "completions/min_terminated_length": 194.0,
      "epoch": 0.0660042583392477,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 0.37413114309310913,
      "learning_rate": 8.159999999999999e-07,
      "loss": 0.0386,
      "num_tokens": 135700660.0,
      "reward": 0.30859375,
      "reward_std": 0.21342378854751587,
      "rewards/simpleverify_reward/mean": 0.30859375,
      "rewards/simpleverify_reward/std": 0.4623647928237915,
      "step": 93,
      "tools/generated_tokens": 1626.095703125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.013671875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.642578125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2039.0,
      "completions/mean_length": 1725.345703125,
      "completions/mean_terminated_length": 1145.273193359375,
      "completions/min_length": 309.0,
      "completions/min_terminated_length": 309.0,
      "epoch": 0.0667139815471966,
      "frac_reward_zero_std": 0.46875,
      "grad_norm": 4.32207727432251,
      "learning_rate": 8.14e-07,
      "loss": 0.0306,
      "num_tokens": 137099890.0,
      "reward": 0.22265625,
      "reward_std": 0.22497963905334473,
      "rewards/simpleverify_reward/mean": 0.22265625,
      "rewards/simpleverify_reward/std": 0.41643625497817993,
      "step": 94,
      "tools/generated_tokens": 1762.46875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.03515625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.658203125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2041.0,
      "completions/mean_length": 1726.966796875,
      "completions/mean_terminated_length": 1108.74853515625,
      "completions/min_length": 340.0,
      "completions/min_terminated_length": 340.0,
      "epoch": 0.06742370475514549,
      "frac_reward_zero_std": 0.5625,
      "grad_norm": 0.3213869631290436,
      "learning_rate": 8.12e-07,
      "loss": 0.0112,
      "num_tokens": 138469954.0,
      "reward": 0.2109375,
      "reward_std": 0.17169174551963806,
      "rewards/simpleverify_reward/mean": 0.2109375,
      "rewards/simpleverify_reward/std": 0.4083731174468994,
      "step": 95,
      "tools/generated_tokens": 1728.015625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.623046875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1759.44921875,
      "completions/mean_terminated_length": 1282.51806640625,
      "completions/min_length": 315.0,
      "completions/min_terminated_length": 315.0,
      "epoch": 0.06813342796309439,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 0.30484744906425476,
      "learning_rate": 8.1e-07,
      "loss": 0.0263,
      "num_tokens": 139892809.0,
      "reward": 0.240234375,
      "reward_std": 0.22333574295043945,
      "rewards/simpleverify_reward/mean": 0.240234375,
      "rewards/simpleverify_reward/std": 0.4276435375213623,
      "step": 96,
      "tools/generated_tokens": 1783.13671875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.021484375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.59765625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1627.517578125,
      "completions/mean_terminated_length": 1002.91748046875,
      "completions/min_length": 235.0,
      "completions/min_terminated_length": 235.0,
      "epoch": 0.0688431511710433,
      "frac_reward_zero_std": 0.59375,
      "grad_norm": 6.74561071395874,
      "learning_rate": 8.08e-07,
      "loss": 0.0249,
      "num_tokens": 141237503.0,
      "reward": 0.21875,
      "reward_std": 0.13747870922088623,
      "rewards/simpleverify_reward/mean": 0.21875,
      "rewards/simpleverify_reward/std": 0.41380295157432556,
      "step": 97,
      "tools/generated_tokens": 1651.546875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.033203125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.591796875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2001.0,
      "completions/mean_length": 1602.88671875,
      "completions/mean_terminated_length": 957.5789184570312,
      "completions/min_length": 298.0,
      "completions/min_terminated_length": 298.0,
      "epoch": 0.0695528743789922,
      "frac_reward_zero_std": 0.625,
      "grad_norm": 5.7436418533325195,
      "learning_rate": 8.06e-07,
      "loss": 0.0206,
      "num_tokens": 142565247.0,
      "reward": 0.220703125,
      "reward_std": 0.14993564784526825,
      "rewards/simpleverify_reward/mean": 0.220703125,
      "rewards/simpleverify_reward/std": 0.4151262938976288,
      "step": 98,
      "tools/generated_tokens": 1612.44921875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.03125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.666015625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2026.0,
      "completions/mean_length": 1776.146484375,
      "completions/mean_terminated_length": 1234.029296875,
      "completions/min_length": 93.0,
      "completions/min_terminated_length": 93.0,
      "epoch": 0.07026259758694109,
      "frac_reward_zero_std": 0.4375,
      "grad_norm": 30.303165435791016,
      "learning_rate": 8.04e-07,
      "loss": 0.042,
      "num_tokens": 144009437.0,
      "reward": 0.232421875,
      "reward_std": 0.22925907373428345,
      "rewards/simpleverify_reward/mean": 0.232421875,
      "rewards/simpleverify_reward/std": 0.42278963327407837,
      "step": 99,
      "tools/generated_tokens": 1772.95703125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.05859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.490234375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2015.0,
      "completions/mean_length": 1524.27734375,
      "completions/mean_terminated_length": 1020.6206665039062,
      "completions/min_length": 267.0,
      "completions/min_terminated_length": 267.0,
      "epoch": 0.07097232079488999,
      "frac_reward_zero_std": 0.5625,
      "grad_norm": 0.3421337902545929,
      "learning_rate": 8.02e-07,
      "loss": 0.0083,
      "num_tokens": 145275158.0,
      "reward": 0.23828125,
      "reward_std": 0.14954319596290588,
      "rewards/simpleverify_reward/mean": 0.23828125,
      "rewards/simpleverify_reward/std": 0.42644867300987244,
      "step": 100,
      "tools/generated_tokens": 1527.06640625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.64453125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1739.3046875,
      "completions/mean_terminated_length": 1179.5823974609375,
      "completions/min_length": 98.0,
      "completions/min_terminated_length": 98.0,
      "epoch": 0.0716820440028389,
      "frac_reward_zero_std": 0.46875,
      "grad_norm": 0.3271843194961548,
      "learning_rate": 8e-07,
      "loss": 0.0417,
      "num_tokens": 146672115.0,
      "reward": 0.265625,
      "reward_std": 0.20727300643920898,
      "rewards/simpleverify_reward/mean": 0.265625,
      "rewards/simpleverify_reward/std": 0.44209739565849304,
      "step": 101,
      "tools/generated_tokens": 1751.025390625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.015625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.59375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2028.0,
      "completions/mean_length": 1651.693359375,
      "completions/mean_terminated_length": 1072.4759521484375,
      "completions/min_length": 264.0,
      "completions/min_terminated_length": 264.0,
      "epoch": 0.0723917672107878,
      "frac_reward_zero_std": 0.59375,
      "grad_norm": 0.27534782886505127,
      "learning_rate": 7.98e-07,
      "loss": 0.0184,
      "num_tokens": 148002814.0,
      "reward": 0.33203125,
      "reward_std": 0.1581159383058548,
      "rewards/simpleverify_reward/mean": 0.33203125,
      "rewards/simpleverify_reward/std": 0.47140273451805115,
      "step": 102,
      "tools/generated_tokens": 1653.359375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.513671875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2019.0,
      "completions/mean_length": 1533.64453125,
      "completions/mean_terminated_length": 990.3694458007812,
      "completions/min_length": 241.0,
      "completions/min_terminated_length": 241.0,
      "epoch": 0.07310149041873669,
      "frac_reward_zero_std": 0.4375,
      "grad_norm": 17.060688018798828,
      "learning_rate": 7.96e-07,
      "loss": 0.0682,
      "num_tokens": 149276398.0,
      "reward": 0.37109375,
      "reward_std": 0.22413049638271332,
      "rewards/simpleverify_reward/mean": 0.37109375,
      "rewards/simpleverify_reward/std": 0.4835699498653412,
      "step": 103,
      "tools/generated_tokens": 1540.478515625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.013671875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.6328125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2040.0,
      "completions/mean_length": 1711.0625,
      "completions/mean_terminated_length": 1130.3829345703125,
      "completions/min_length": 189.0,
      "completions/min_terminated_length": 189.0,
      "epoch": 0.07381121362668559,
      "frac_reward_zero_std": 0.53125,
      "grad_norm": 0.31140822172164917,
      "learning_rate": 7.94e-07,
      "loss": 0.0243,
      "num_tokens": 150638968.0,
      "reward": 0.255859375,
      "reward_std": 0.18560537695884705,
      "rewards/simpleverify_reward/mean": 0.255859375,
      "rewards/simpleverify_reward/std": 0.43676990270614624,
      "step": 104,
      "tools/generated_tokens": 1713.98828125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.552734375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2034.0,
      "completions/mean_length": 1652.908203125,
      "completions/mean_terminated_length": 1164.650634765625,
      "completions/min_length": 286.0,
      "completions/min_terminated_length": 286.0,
      "epoch": 0.0745209368346345,
      "frac_reward_zero_std": 0.53125,
      "grad_norm": 3.1037306785583496,
      "learning_rate": 7.92e-07,
      "loss": 0.0173,
      "num_tokens": 152001058.0,
      "reward": 0.302734375,
      "reward_std": 0.19064217805862427,
      "rewards/simpleverify_reward/mean": 0.302734375,
      "rewards/simpleverify_reward/std": 0.45989060401916504,
      "step": 105,
      "tools/generated_tokens": 1678.212890625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0234375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.6875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1733.609375,
      "completions/mean_terminated_length": 1041.9500732421875,
      "completions/min_length": 329.0,
      "completions/min_terminated_length": 329.0,
      "epoch": 0.07523066004258339,
      "frac_reward_zero_std": 0.53125,
      "grad_norm": 0.29409074783325195,
      "learning_rate": 7.9e-07,
      "loss": 0.0292,
      "num_tokens": 153390716.0,
      "reward": 0.228515625,
      "reward_std": 0.1800159215927124,
      "rewards/simpleverify_reward/mean": 0.228515625,
      "rewards/simpleverify_reward/std": 0.4202871024608612,
      "step": 106,
      "tools/generated_tokens": 1750.78125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.01953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.509765625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1633.59375,
      "completions/mean_terminated_length": 1202.6773681640625,
      "completions/min_length": 397.0,
      "completions/min_terminated_length": 397.0,
      "epoch": 0.07594038325053229,
      "frac_reward_zero_std": 0.40625,
      "grad_norm": 1.6234400272369385,
      "learning_rate": 7.88e-07,
      "loss": 0.0412,
      "num_tokens": 154725951.0,
      "reward": 0.376953125,
      "reward_std": 0.24580302834510803,
      "rewards/simpleverify_reward/mean": 0.376953125,
      "rewards/simpleverify_reward/std": 0.4850969910621643,
      "step": 107,
      "tools/generated_tokens": 1645.640625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.009765625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.654296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1767.9765625,
      "completions/mean_terminated_length": 1237.9886474609375,
      "completions/min_length": 345.0,
      "completions/min_terminated_length": 345.0,
      "epoch": 0.0766501064584812,
      "frac_reward_zero_std": 0.5625,
      "grad_norm": 14.223878860473633,
      "learning_rate": 7.86e-07,
      "loss": 0.0247,
      "num_tokens": 156124076.0,
      "reward": 0.212890625,
      "reward_std": 0.1921730935573578,
      "rewards/simpleverify_reward/mean": 0.212890625,
      "rewards/simpleverify_reward/std": 0.409751296043396,
      "step": 108,
      "tools/generated_tokens": 1772.998046875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.009765625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.6953125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2017.0,
      "completions/mean_length": 1792.0703125,
      "completions/mean_terminated_length": 1208.025634765625,
      "completions/min_length": 357.0,
      "completions/min_terminated_length": 357.0,
      "epoch": 0.0773598296664301,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 0.3179459571838379,
      "learning_rate": 7.84e-07,
      "loss": 0.0294,
      "num_tokens": 157526848.0,
      "reward": 0.232421875,
      "reward_std": 0.19037629663944244,
      "rewards/simpleverify_reward/mean": 0.232421875,
      "rewards/simpleverify_reward/std": 0.42278963327407837,
      "step": 109,
      "tools/generated_tokens": 1792.0703125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.69140625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1822.841796875,
      "completions/mean_terminated_length": 1318.3734130859375,
      "completions/min_length": 319.0,
      "completions/min_terminated_length": 319.0,
      "epoch": 0.07806955287437899,
      "frac_reward_zero_std": 0.40625,
      "grad_norm": 30.463953018188477,
      "learning_rate": 7.82e-07,
      "loss": 0.0336,
      "num_tokens": 158980418.0,
      "reward": 0.197265625,
      "reward_std": 0.23504400253295898,
      "rewards/simpleverify_reward/mean": 0.197265625,
      "rewards/simpleverify_reward/std": 0.3983237147331238,
      "step": 110,
      "tools/generated_tokens": 1829.3984375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.03125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.57421875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1722.11328125,
      "completions/mean_terminated_length": 1282.6146240234375,
      "completions/min_length": 363.0,
      "completions/min_terminated_length": 363.0,
      "epoch": 0.07877927608232789,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 4.885906219482422,
      "learning_rate": 7.799999999999999e-07,
      "loss": 0.0643,
      "num_tokens": 160354343.0,
      "reward": 0.318359375,
      "reward_std": 0.31701478362083435,
      "rewards/simpleverify_reward/mean": 0.318359375,
      "rewards/simpleverify_reward/std": 0.46629536151885986,
      "step": 111,
      "tools/generated_tokens": 1727.580078125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0078125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.5859375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1691.30078125,
      "completions/mean_terminated_length": 1186.5377197265625,
      "completions/min_length": 243.0,
      "completions/min_terminated_length": 243.0,
      "epoch": 0.0794889992902768,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 0.3375658690929413,
      "learning_rate": 7.78e-07,
      "loss": 0.0377,
      "num_tokens": 161708996.0,
      "reward": 0.263671875,
      "reward_std": 0.21555078029632568,
      "rewards/simpleverify_reward/mean": 0.263671875,
      "rewards/simpleverify_reward/std": 0.4410543739795685,
      "step": 112,
      "tools/generated_tokens": 1698.783203125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.515625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1611.458984375,
      "completions/mean_terminated_length": 1146.7540283203125,
      "completions/min_length": 412.0,
      "completions/min_terminated_length": 412.0,
      "epoch": 0.0801987224982257,
      "frac_reward_zero_std": 0.53125,
      "grad_norm": 2.748366594314575,
      "learning_rate": 7.76e-07,
      "loss": 0.0339,
      "num_tokens": 163060349.0,
      "reward": 0.35546875,
      "reward_std": 0.17348617315292358,
      "rewards/simpleverify_reward/mean": 0.35546875,
      "rewards/simpleverify_reward/std": 0.47912323474884033,
      "step": 113,
      "tools/generated_tokens": 1638.3828125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.025390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.673828125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1811.28515625,
      "completions/mean_terminated_length": 1322.2635498046875,
      "completions/min_length": 334.0,
      "completions/min_terminated_length": 334.0,
      "epoch": 0.08090844570617459,
      "frac_reward_zero_std": 0.46875,
      "grad_norm": 11.043597221374512,
      "learning_rate": 7.74e-07,
      "loss": 0.0264,
      "num_tokens": 164490373.0,
      "reward": 0.22265625,
      "reward_std": 0.21327516436576843,
      "rewards/simpleverify_reward/mean": 0.22265625,
      "rewards/simpleverify_reward/std": 0.41643625497817993,
      "step": 114,
      "tools/generated_tokens": 1817.12890625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.021484375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.5546875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1682.029296875,
      "completions/mean_terminated_length": 1226.1710205078125,
      "completions/min_length": 400.0,
      "completions/min_terminated_length": 400.0,
      "epoch": 0.08161816891412349,
      "frac_reward_zero_std": 0.46875,
      "grad_norm": 0.4902113378047943,
      "learning_rate": 7.72e-07,
      "loss": 0.043,
      "num_tokens": 165840845.0,
      "reward": 0.341796875,
      "reward_std": 0.19596010446548462,
      "rewards/simpleverify_reward/mean": 0.341796875,
      "rewards/simpleverify_reward/std": 0.4747757613658905,
      "step": 115,
      "tools/generated_tokens": 1685.44140625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.48828125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1523.50390625,
      "completions/mean_terminated_length": 1023.030517578125,
      "completions/min_length": 195.0,
      "completions/min_terminated_length": 195.0,
      "epoch": 0.0823278921220724,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 13.916735649108887,
      "learning_rate": 7.699999999999999e-07,
      "loss": 0.0209,
      "num_tokens": 167139778.0,
      "reward": 0.39453125,
      "reward_std": 0.21060168743133545,
      "rewards/simpleverify_reward/mean": 0.39453125,
      "rewards/simpleverify_reward/std": 0.4892277717590332,
      "step": 116,
      "tools/generated_tokens": 1542.822265625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.044921875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.646484375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1812.064453125,
      "completions/mean_terminated_length": 1380.602294921875,
      "completions/min_length": 435.0,
      "completions/min_terminated_length": 435.0,
      "epoch": 0.0830376153300213,
      "frac_reward_zero_std": 0.4375,
      "grad_norm": 2.1903862953186035,
      "learning_rate": 7.68e-07,
      "loss": 0.024,
      "num_tokens": 168565096.0,
      "reward": 0.2421875,
      "reward_std": 0.24411246180534363,
      "rewards/simpleverify_reward/mean": 0.2421875,
      "rewards/simpleverify_reward/std": 0.42882615327835083,
      "step": 117,
      "tools/generated_tokens": 1825.6875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.013671875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.603515625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2039.0,
      "completions/mean_length": 1702.634765625,
      "completions/mean_terminated_length": 1176.9310302734375,
      "completions/min_length": 337.0,
      "completions/min_terminated_length": 337.0,
      "epoch": 0.08374733853797019,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 0.3545679748058319,
      "learning_rate": 7.66e-07,
      "loss": 0.0262,
      "num_tokens": 169916605.0,
      "reward": 0.271484375,
      "reward_std": 0.2131485939025879,
      "rewards/simpleverify_reward/mean": 0.271484375,
      "rewards/simpleverify_reward/std": 0.44516023993492126,
      "step": 118,
      "tools/generated_tokens": 1702.640625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.486328125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1585.205078125,
      "completions/mean_terminated_length": 1147.045654296875,
      "completions/min_length": 234.0,
      "completions/min_terminated_length": 234.0,
      "epoch": 0.08445706174591909,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 0.4309438467025757,
      "learning_rate": 7.64e-07,
      "loss": 0.0516,
      "num_tokens": 171220326.0,
      "reward": 0.29296875,
      "reward_std": 0.23924238979816437,
      "rewards/simpleverify_reward/mean": 0.29296875,
      "rewards/simpleverify_reward/std": 0.455569326877594,
      "step": 119,
      "tools/generated_tokens": 1590.837890625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0078125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.64453125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1806.681640625,
      "completions/mean_terminated_length": 1369.12646484375,
      "completions/min_length": 517.0,
      "completions/min_terminated_length": 517.0,
      "epoch": 0.085166784953868,
      "frac_reward_zero_std": 0.40625,
      "grad_norm": 0.3674212098121643,
      "learning_rate": 7.62e-07,
      "loss": 0.0236,
      "num_tokens": 172631900.0,
      "reward": 0.244140625,
      "reward_std": 0.22864244878292084,
      "rewards/simpleverify_reward/mean": 0.244140625,
      "rewards/simpleverify_reward/std": 0.42999663949012756,
      "step": 120,
      "tools/generated_tokens": 1809.2734375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.607421875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2036.0,
      "completions/mean_length": 1684.7890625,
      "completions/mean_terminated_length": 1122.805908203125,
      "completions/min_length": 184.0,
      "completions/min_terminated_length": 184.0,
      "epoch": 0.0858765081618169,
      "frac_reward_zero_std": 0.46875,
      "grad_norm": 0.33565211296081543,
      "learning_rate": 7.599999999999999e-07,
      "loss": 0.0329,
      "num_tokens": 173976677.0,
      "reward": 0.298828125,
      "reward_std": 0.21012642979621887,
      "rewards/simpleverify_reward/mean": 0.298828125,
      "rewards/simpleverify_reward/std": 0.45819199085235596,
      "step": 121,
      "tools/generated_tokens": 1685.359375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.515625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1602.865234375,
      "completions/mean_terminated_length": 1129.0120849609375,
      "completions/min_length": 243.0,
      "completions/min_terminated_length": 243.0,
      "epoch": 0.08658623136976579,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 0.4335751533508301,
      "learning_rate": 7.58e-07,
      "loss": 0.0153,
      "num_tokens": 175279712.0,
      "reward": 0.318359375,
      "reward_std": 0.2559392750263214,
      "rewards/simpleverify_reward/mean": 0.318359375,
      "rewards/simpleverify_reward/std": 0.46629536151885986,
      "step": 122,
      "tools/generated_tokens": 1602.904296875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.47265625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2041.0,
      "completions/mean_length": 1627.857421875,
      "completions/mean_terminated_length": 1251.28515625,
      "completions/min_length": 445.0,
      "completions/min_terminated_length": 445.0,
      "epoch": 0.08729595457771469,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 1.346057653427124,
      "learning_rate": 7.559999999999999e-07,
      "loss": 0.0322,
      "num_tokens": 176627063.0,
      "reward": 0.271484375,
      "reward_std": 0.3070718050003052,
      "rewards/simpleverify_reward/mean": 0.271484375,
      "rewards/simpleverify_reward/std": 0.44516023993492126,
      "step": 123,
      "tools/generated_tokens": 1642.064453125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.015625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.431640625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1501.837890625,
      "completions/mean_terminated_length": 1087.0550537109375,
      "completions/min_length": 205.0,
      "completions/min_terminated_length": 205.0,
      "epoch": 0.0880056777856636,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.6639207601547241,
      "learning_rate": 7.54e-07,
      "loss": 0.0486,
      "num_tokens": 177907892.0,
      "reward": 0.427734375,
      "reward_std": 0.3197053074836731,
      "rewards/simpleverify_reward/mean": 0.427734375,
      "rewards/simpleverify_reward/std": 0.4952339828014374,
      "step": 124,
      "tools/generated_tokens": 1524.998046875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.03515625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.59765625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1751.8515625,
      "completions/mean_terminated_length": 1311.9417724609375,
      "completions/min_length": 440.0,
      "completions/min_terminated_length": 440.0,
      "epoch": 0.0887154009936125,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 3.8040530681610107,
      "learning_rate": 7.52e-07,
      "loss": 0.0473,
      "num_tokens": 179300099.0,
      "reward": 0.25,
      "reward_std": 0.2969130277633667,
      "rewards/simpleverify_reward/mean": 0.25,
      "rewards/simpleverify_reward/std": 0.43343618512153625,
      "step": 125,
      "tools/generated_tokens": 1760.41015625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.01171875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.46875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1569.341796875,
      "completions/mean_terminated_length": 1146.996337890625,
      "completions/min_length": 339.0,
      "completions/min_terminated_length": 339.0,
      "epoch": 0.08942512420156139,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 7.0698137283325195,
      "learning_rate": 7.5e-07,
      "loss": 0.0238,
      "num_tokens": 180605177.0,
      "reward": 0.400390625,
      "reward_std": 0.2691951394081116,
      "rewards/simpleverify_reward/mean": 0.400390625,
      "rewards/simpleverify_reward/std": 0.4904567301273346,
      "step": 126,
      "tools/generated_tokens": 1584.13671875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.021484375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.439453125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2041.0,
      "completions/mean_length": 1510.841796875,
      "completions/mean_terminated_length": 1089.7247314453125,
      "completions/min_length": 353.0,
      "completions/min_terminated_length": 353.0,
      "epoch": 0.09013484740951029,
      "frac_reward_zero_std": 0.4375,
      "grad_norm": 1.4712598323822021,
      "learning_rate": 7.48e-07,
      "loss": 0.0335,
      "num_tokens": 181893220.0,
      "reward": 0.25390625,
      "reward_std": 0.23402543365955353,
      "rewards/simpleverify_reward/mean": 0.25390625,
      "rewards/simpleverify_reward/std": 0.43567025661468506,
      "step": 127,
      "tools/generated_tokens": 1527.57421875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.017578125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.515625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1564.904296875,
      "completions/mean_terminated_length": 1050.64111328125,
      "completions/min_length": 261.0,
      "completions/min_terminated_length": 261.0,
      "epoch": 0.0908445706174592,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.39145684242248535,
      "learning_rate": 7.459999999999999e-07,
      "loss": 0.0419,
      "num_tokens": 183180213.0,
      "reward": 0.39453125,
      "reward_std": 0.2801550626754761,
      "rewards/simpleverify_reward/mean": 0.39453125,
      "rewards/simpleverify_reward/std": 0.4892277717590332,
      "step": 128,
      "tools/generated_tokens": 1566.708984375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.58984375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1641.3046875,
      "completions/mean_terminated_length": 1056.4381103515625,
      "completions/min_length": 288.0,
      "completions/min_terminated_length": 288.0,
      "epoch": 0.09155429382540808,
      "frac_reward_zero_std": 0.46875,
      "grad_norm": 0.3946840465068817,
      "learning_rate": 7.44e-07,
      "loss": 0.0154,
      "num_tokens": 184514575.0,
      "reward": 0.236328125,
      "reward_std": 0.1958683729171753,
      "rewards/simpleverify_reward/mean": 0.236328125,
      "rewards/simpleverify_reward/std": 0.42524150013923645,
      "step": 129,
      "tools/generated_tokens": 1643.3515625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.43359375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1549.361328125,
      "completions/mean_terminated_length": 1167.644775390625,
      "completions/min_length": 299.0,
      "completions/min_terminated_length": 299.0,
      "epoch": 0.09226401703335699,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.406906396150589,
      "learning_rate": 7.42e-07,
      "loss": 0.0262,
      "num_tokens": 185807898.0,
      "reward": 0.328125,
      "reward_std": 0.2794487774372101,
      "rewards/simpleverify_reward/mean": 0.328125,
      "rewards/simpleverify_reward/std": 0.4699897766113281,
      "step": 130,
      "tools/generated_tokens": 1564.890625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.015625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.396484375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1570.583984375,
      "completions/mean_terminated_length": 1256.9417724609375,
      "completions/min_length": 181.0,
      "completions/min_terminated_length": 181.0,
      "epoch": 0.09297374024130589,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.408595472574234,
      "learning_rate": 7.4e-07,
      "loss": 0.0565,
      "num_tokens": 187100017.0,
      "reward": 0.3125,
      "reward_std": 0.30801182985305786,
      "rewards/simpleverify_reward/mean": 0.3125,
      "rewards/simpleverify_reward/std": 0.4639657139778137,
      "step": 131,
      "tools/generated_tokens": 1577.1640625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.009765625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.4765625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2003.0,
      "completions/mean_length": 1562.9453125,
      "completions/mean_terminated_length": 1121.328369140625,
      "completions/min_length": 351.0,
      "completions/min_terminated_length": 351.0,
      "epoch": 0.0936834634492548,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.42142218351364136,
      "learning_rate": 7.38e-07,
      "loss": 0.0437,
      "num_tokens": 188400037.0,
      "reward": 0.400390625,
      "reward_std": 0.2871820032596588,
      "rewards/simpleverify_reward/mean": 0.400390625,
      "rewards/simpleverify_reward/std": 0.4904567301273346,
      "step": 132,
      "tools/generated_tokens": 1572.49609375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.015625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.529296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1615.59765625,
      "completions/mean_terminated_length": 1129.369384765625,
      "completions/min_length": 205.0,
      "completions/min_terminated_length": 205.0,
      "epoch": 0.09439318665720368,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 0.37718144059181213,
      "learning_rate": 7.359999999999999e-07,
      "loss": 0.0499,
      "num_tokens": 189720271.0,
      "reward": 0.294921875,
      "reward_std": 0.2517799437046051,
      "rewards/simpleverify_reward/mean": 0.294921875,
      "rewards/simpleverify_reward/std": 0.4564536213874817,
      "step": 133,
      "tools/generated_tokens": 1618.5859375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.46875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1579.271484375,
      "completions/mean_terminated_length": 1165.6875,
      "completions/min_length": 298.0,
      "completions/min_terminated_length": 298.0,
      "epoch": 0.09510290986515259,
      "frac_reward_zero_std": 0.4375,
      "grad_norm": 0.39622676372528076,
      "learning_rate": 7.34e-07,
      "loss": 0.0223,
      "num_tokens": 191033811.0,
      "reward": 0.291015625,
      "reward_std": 0.22681047022342682,
      "rewards/simpleverify_reward/mean": 0.291015625,
      "rewards/simpleverify_reward/std": 0.45467492938041687,
      "step": 134,
      "tools/generated_tokens": 1590.349609375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.01171875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.533203125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1638.09375,
      "completions/mean_terminated_length": 1169.8743896484375,
      "completions/min_length": 314.0,
      "completions/min_terminated_length": 314.0,
      "epoch": 0.09581263307310149,
      "frac_reward_zero_std": 0.4375,
      "grad_norm": 0.3372923731803894,
      "learning_rate": 7.319999999999999e-07,
      "loss": 0.0449,
      "num_tokens": 192369669.0,
      "reward": 0.28125,
      "reward_std": 0.23482444882392883,
      "rewards/simpleverify_reward/mean": 0.28125,
      "rewards/simpleverify_reward/std": 0.45004892349243164,
      "step": 135,
      "tools/generated_tokens": 1642.751953125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.001953125
    },
    {
      "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": 0.6875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2033.0,
      "completions/mean_length": 1806.759765625,
      "completions/mean_terminated_length": 1276.03125,
      "completions/min_length": 310.0,
      "completions/min_terminated_length": 310.0,
      "epoch": 0.0965223562810504,
      "frac_reward_zero_std": 0.53125,
      "grad_norm": 0.4272914230823517,
      "learning_rate": 7.3e-07,
      "loss": 0.0204,
      "num_tokens": 193784623.0,
      "reward": 0.185546875,
      "reward_std": 0.19658556580543518,
      "rewards/simpleverify_reward/mean": 0.185546875,
      "rewards/simpleverify_reward/std": 0.38912075757980347,
      "step": 136,
      "tools/generated_tokens": 1810.951171875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.650390625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1717.419921875,
      "completions/mean_terminated_length": 1102.43017578125,
      "completions/min_length": 238.0,
      "completions/min_terminated_length": 238.0,
      "epoch": 0.09723207948899928,
      "frac_reward_zero_std": 0.4375,
      "grad_norm": 0.3212464451789856,
      "learning_rate": 7.28e-07,
      "loss": 0.0362,
      "num_tokens": 195161208.0,
      "reward": 0.21484375,
      "reward_std": 0.22619745135307312,
      "rewards/simpleverify_reward/mean": 0.21484375,
      "rewards/simpleverify_reward/std": 0.4111155867576599,
      "step": 137,
      "tools/generated_tokens": 1721.775390625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.609375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2026.0,
      "completions/mean_length": 1786.421875,
      "completions/mean_terminated_length": 1378.3599853515625,
      "completions/min_length": 331.0,
      "completions/min_terminated_length": 331.0,
      "epoch": 0.09794180269694819,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 0.3559974133968353,
      "learning_rate": 7.259999999999999e-07,
      "loss": 0.0457,
      "num_tokens": 196564768.0,
      "reward": 0.271484375,
      "reward_std": 0.26387032866477966,
      "rewards/simpleverify_reward/mean": 0.271484375,
      "rewards/simpleverify_reward/std": 0.44516023993492126,
      "step": 138,
      "tools/generated_tokens": 1786.427734375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.580078125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1715.75390625,
      "completions/mean_terminated_length": 1256.7906494140625,
      "completions/min_length": 461.0,
      "completions/min_terminated_length": 461.0,
      "epoch": 0.09865152590489709,
      "frac_reward_zero_std": 0.46875,
      "grad_norm": 0.36598193645477295,
      "learning_rate": 7.24e-07,
      "loss": 0.0082,
      "num_tokens": 197936185.0,
      "reward": 0.185546875,
      "reward_std": 0.20441049337387085,
      "rewards/simpleverify_reward/mean": 0.185546875,
      "rewards/simpleverify_reward/std": 0.38912075757980347,
      "step": 139,
      "tools/generated_tokens": 1720.125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.458984375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2040.0,
      "completions/mean_length": 1558.99609375,
      "completions/mean_terminated_length": 1144.13720703125,
      "completions/min_length": 34.0,
      "completions/min_terminated_length": 34.0,
      "epoch": 0.099361249112846,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.43565794825553894,
      "learning_rate": 7.219999999999999e-07,
      "loss": 0.0307,
      "num_tokens": 199226416.0,
      "reward": 0.32421875,
      "reward_std": 0.28462696075439453,
      "rewards/simpleverify_reward/mean": 0.32421875,
      "rewards/simpleverify_reward/std": 0.4685399830341339,
      "step": 140,
      "tools/generated_tokens": 1560.0234375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.6015625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1756.060546875,
      "completions/mean_terminated_length": 1315.289306640625,
      "completions/min_length": 224.0,
      "completions/min_terminated_length": 224.0,
      "epoch": 0.10007097232079488,
      "frac_reward_zero_std": 0.4375,
      "grad_norm": 0.31730177998542786,
      "learning_rate": 7.2e-07,
      "loss": 0.0184,
      "num_tokens": 200617512.0,
      "reward": 0.279296875,
      "reward_std": 0.2331317961215973,
      "rewards/simpleverify_reward/mean": 0.279296875,
      "rewards/simpleverify_reward/std": 0.44909247756004333,
      "step": 141,
      "tools/generated_tokens": 1760.5859375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.51953125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1566.1640625,
      "completions/mean_terminated_length": 1045.1544189453125,
      "completions/min_length": 191.0,
      "completions/min_terminated_length": 191.0,
      "epoch": 0.10078069552874379,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 8.894607543945312,
      "learning_rate": 7.179999999999999e-07,
      "loss": 0.0461,
      "num_tokens": 201929131.0,
      "reward": 0.31640625,
      "reward_std": 0.24319365620613098,
      "rewards/simpleverify_reward/mean": 0.31640625,
      "rewards/simpleverify_reward/std": 0.46552830934524536,
      "step": 142,
      "tools/generated_tokens": 1577.32421875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.033203125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.51953125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1583.357421875,
      "completions/mean_terminated_length": 1080.93896484375,
      "completions/min_length": 266.0,
      "completions/min_terminated_length": 266.0,
      "epoch": 0.10149041873669269,
      "frac_reward_zero_std": 0.40625,
      "grad_norm": 0.3868037760257721,
      "learning_rate": 7.159999999999999e-07,
      "loss": 0.03,
      "num_tokens": 203228983.0,
      "reward": 0.33984375,
      "reward_std": 0.23849496245384216,
      "rewards/simpleverify_reward/mean": 0.33984375,
      "rewards/simpleverify_reward/std": 0.4741191864013672,
      "step": 143,
      "tools/generated_tokens": 1586.708984375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.40234375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1387.171875,
      "completions/mean_terminated_length": 942.3006591796875,
      "completions/min_length": 262.0,
      "completions/min_terminated_length": 262.0,
      "epoch": 0.1022001419446416,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 0.442498117685318,
      "learning_rate": 7.14e-07,
      "loss": 0.0447,
      "num_tokens": 204421375.0,
      "reward": 0.375,
      "reward_std": 0.23963943123817444,
      "rewards/simpleverify_reward/mean": 0.375,
      "rewards/simpleverify_reward/std": 0.4845963716506958,
      "step": 144,
      "tools/generated_tokens": 1387.181640625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1476.2421875,
      "completions/mean_terminated_length": 1133.1875,
      "completions/min_length": 319.0,
      "completions/min_terminated_length": 319.0,
      "epoch": 0.10290986515259049,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.4894505739212036,
      "learning_rate": 7.119999999999999e-07,
      "loss": 0.045,
      "num_tokens": 205665802.0,
      "reward": 0.396484375,
      "reward_std": 0.2925666868686676,
      "rewards/simpleverify_reward/mean": 0.396484375,
      "rewards/simpleverify_reward/std": 0.4896455705165863,
      "step": 145,
      "tools/generated_tokens": 1482.59375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.470703125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1522.3984375,
      "completions/mean_terminated_length": 1054.9815673828125,
      "completions/min_length": 199.0,
      "completions/min_terminated_length": 199.0,
      "epoch": 0.10361958836053939,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.390195369720459,
      "learning_rate": 7.1e-07,
      "loss": 0.0458,
      "num_tokens": 206969949.0,
      "reward": 0.296875,
      "reward_std": 0.28526005148887634,
      "rewards/simpleverify_reward/mean": 0.296875,
      "rewards/simpleverify_reward/std": 0.45732781291007996,
      "step": 146,
      "tools/generated_tokens": 1546.111328125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.046875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.470703125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2033.0,
      "completions/mean_length": 1598.685546875,
      "completions/mean_terminated_length": 1199.1107177734375,
      "completions/min_length": 384.0,
      "completions/min_terminated_length": 384.0,
      "epoch": 0.10432931156848829,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.42708995938301086,
      "learning_rate": 7.079999999999999e-07,
      "loss": 0.04,
      "num_tokens": 208288788.0,
      "reward": 0.375,
      "reward_std": 0.3073047399520874,
      "rewards/simpleverify_reward/mean": 0.375,
      "rewards/simpleverify_reward/std": 0.4845963716506958,
      "step": 147,
      "tools/generated_tokens": 1600.197265625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.4765625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1594.525390625,
      "completions/mean_terminated_length": 1181.660400390625,
      "completions/min_length": 375.0,
      "completions/min_terminated_length": 375.0,
      "epoch": 0.1050390347764372,
      "frac_reward_zero_std": 0.40625,
      "grad_norm": 14.579595565795898,
      "learning_rate": 7.059999999999999e-07,
      "loss": 0.0384,
      "num_tokens": 209608637.0,
      "reward": 0.28515625,
      "reward_std": 0.22221127152442932,
      "rewards/simpleverify_reward/mean": 0.28515625,
      "rewards/simpleverify_reward/std": 0.45193037390708923,
      "step": 148,
      "tools/generated_tokens": 1608.1953125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.017578125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.494140625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1504.138671875,
      "completions/mean_terminated_length": 972.8764038085938,
      "completions/min_length": 287.0,
      "completions/min_terminated_length": 287.0,
      "epoch": 0.10574875798438609,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.8280407190322876,
      "learning_rate": 7.04e-07,
      "loss": 0.0287,
      "num_tokens": 210872997.0,
      "reward": 0.322265625,
      "reward_std": 0.27162301540374756,
      "rewards/simpleverify_reward/mean": 0.322265625,
      "rewards/simpleverify_reward/std": 0.46780112385749817,
      "step": 149,
      "tools/generated_tokens": 1512.05078125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.01171875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.478515625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2037.0,
      "completions/mean_length": 1550.28515625,
      "completions/mean_terminated_length": 1093.58056640625,
      "completions/min_length": 295.0,
      "completions/min_terminated_length": 295.0,
      "epoch": 0.10645848119233499,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.3765493631362915,
      "learning_rate": 7.019999999999999e-07,
      "loss": 0.021,
      "num_tokens": 212169863.0,
      "reward": 0.275390625,
      "reward_std": 0.240533709526062,
      "rewards/simpleverify_reward/mean": 0.275390625,
      "rewards/simpleverify_reward/std": 0.44714778661727905,
      "step": 150,
      "tools/generated_tokens": 1564.41015625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.017578125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.546875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2031.0,
      "completions/mean_length": 1605.541015625,
      "completions/mean_terminated_length": 1071.538818359375,
      "completions/min_length": 296.0,
      "completions/min_terminated_length": 296.0,
      "epoch": 0.10716820440028389,
      "frac_reward_zero_std": 0.53125,
      "grad_norm": 0.34773552417755127,
      "learning_rate": 7e-07,
      "loss": 0.0223,
      "num_tokens": 213483532.0,
      "reward": 0.275390625,
      "reward_std": 0.1801806092262268,
      "rewards/simpleverify_reward/mean": 0.275390625,
      "rewards/simpleverify_reward/std": 0.44714778661727905,
      "step": 151,
      "tools/generated_tokens": 1605.55078125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.595703125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2006.0,
      "completions/mean_length": 1632.658203125,
      "completions/mean_terminated_length": 1020.68115234375,
      "completions/min_length": 295.0,
      "completions/min_terminated_length": 295.0,
      "epoch": 0.1078779276082328,
      "frac_reward_zero_std": 0.40625,
      "grad_norm": 0.4107280969619751,
      "learning_rate": 6.979999999999999e-07,
      "loss": 0.0318,
      "num_tokens": 214801217.0,
      "reward": 0.28515625,
      "reward_std": 0.24837331473827362,
      "rewards/simpleverify_reward/mean": 0.28515625,
      "rewards/simpleverify_reward/std": 0.45193037390708923,
      "step": 152,
      "tools/generated_tokens": 1633.685546875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.515625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1657.69140625,
      "completions/mean_terminated_length": 1242.2015380859375,
      "completions/min_length": 354.0,
      "completions/min_terminated_length": 354.0,
      "epoch": 0.10858765081618169,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.4095619022846222,
      "learning_rate": 6.959999999999999e-07,
      "loss": 0.0263,
      "num_tokens": 216141619.0,
      "reward": 0.29296875,
      "reward_std": 0.2855563759803772,
      "rewards/simpleverify_reward/mean": 0.29296875,
      "rewards/simpleverify_reward/std": 0.455569326877594,
      "step": 153,
      "tools/generated_tokens": 1657.705078125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.546875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2039.0,
      "completions/mean_length": 1615.833984375,
      "completions/mean_terminated_length": 1094.2542724609375,
      "completions/min_length": 248.0,
      "completions/min_terminated_length": 248.0,
      "epoch": 0.10929737402413059,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.3636707067489624,
      "learning_rate": 6.939999999999999e-07,
      "loss": 0.0362,
      "num_tokens": 217476549.0,
      "reward": 0.248046875,
      "reward_std": 0.2677682936191559,
      "rewards/simpleverify_reward/mean": 0.248046875,
      "rewards/simpleverify_reward/std": 0.4323015511035919,
      "step": 154,
      "tools/generated_tokens": 1626.234375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.02734375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.564453125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1645.85546875,
      "completions/mean_terminated_length": 1124.690673828125,
      "completions/min_length": 199.0,
      "completions/min_terminated_length": 199.0,
      "epoch": 0.11000709723207949,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 14.394134521484375,
      "learning_rate": 6.919999999999999e-07,
      "loss": 0.0728,
      "num_tokens": 218816261.0,
      "reward": 0.328125,
      "reward_std": 0.2647358179092407,
      "rewards/simpleverify_reward/mean": 0.328125,
      "rewards/simpleverify_reward/std": 0.4699897766113281,
      "step": 155,
      "tools/generated_tokens": 1646.92578125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0078125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.5078125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1632.826171875,
      "completions/mean_terminated_length": 1204.4722900390625,
      "completions/min_length": 368.0,
      "completions/min_terminated_length": 368.0,
      "epoch": 0.11071682044002838,
      "frac_reward_zero_std": 0.40625,
      "grad_norm": 0.3400692045688629,
      "learning_rate": 6.9e-07,
      "loss": 0.0377,
      "num_tokens": 220164849.0,
      "reward": 0.365234375,
      "reward_std": 0.256111204624176,
      "rewards/simpleverify_reward/mean": 0.365234375,
      "rewards/simpleverify_reward/std": 0.4819667339324951,
      "step": 156,
      "tools/generated_tokens": 1640.810546875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.556640625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1659.701171875,
      "completions/mean_terminated_length": 1172.1893310546875,
      "completions/min_length": 207.0,
      "completions/min_terminated_length": 207.0,
      "epoch": 0.11142654364797729,
      "frac_reward_zero_std": 0.4375,
      "grad_norm": 0.3191794157028198,
      "learning_rate": 6.879999999999999e-07,
      "loss": 0.0135,
      "num_tokens": 221505768.0,
      "reward": 0.283203125,
      "reward_std": 0.23686885833740234,
      "rewards/simpleverify_reward/mean": 0.283203125,
      "rewards/simpleverify_reward/std": 0.4509948492050171,
      "step": 157,
      "tools/generated_tokens": 1659.705078125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.419921875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2033.0,
      "completions/mean_length": 1526.345703125,
      "completions/mean_terminated_length": 1148.7171630859375,
      "completions/min_length": 220.0,
      "completions/min_terminated_length": 220.0,
      "epoch": 0.11213626685592619,
      "frac_reward_zero_std": 0.4375,
      "grad_norm": 0.4618627727031708,
      "learning_rate": 6.86e-07,
      "loss": 0.0396,
      "num_tokens": 222775474.0,
      "reward": 0.34375,
      "reward_std": 0.2455572783946991,
      "rewards/simpleverify_reward/mean": 0.34375,
      "rewards/simpleverify_reward/std": 0.4754233956336975,
      "step": 158,
      "tools/generated_tokens": 1529.05078125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.482421875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1478.064453125,
      "completions/mean_terminated_length": 946.841552734375,
      "completions/min_length": 184.0,
      "completions/min_terminated_length": 184.0,
      "epoch": 0.11284599006387509,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.4622233510017395,
      "learning_rate": 6.84e-07,
      "loss": 0.0385,
      "num_tokens": 224015043.0,
      "reward": 0.26953125,
      "reward_std": 0.2626599073410034,
      "rewards/simpleverify_reward/mean": 0.26953125,
      "rewards/simpleverify_reward/std": 0.44415023922920227,
      "step": 159,
      "tools/generated_tokens": 1478.072265625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.43359375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2019.0,
      "completions/mean_length": 1476.166015625,
      "completions/mean_terminated_length": 1038.417236328125,
      "completions/min_length": 222.0,
      "completions/min_terminated_length": 222.0,
      "epoch": 0.11355571327182398,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.49046239256858826,
      "learning_rate": 6.82e-07,
      "loss": 0.0541,
      "num_tokens": 225257695.0,
      "reward": 0.33984375,
      "reward_std": 0.29554182291030884,
      "rewards/simpleverify_reward/mean": 0.33984375,
      "rewards/simpleverify_reward/std": 0.4741191864013672,
      "step": 160,
      "tools/generated_tokens": 1477.904296875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.51171875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1528.375,
      "completions/mean_terminated_length": 983.8080444335938,
      "completions/min_length": 293.0,
      "completions/min_terminated_length": 293.0,
      "epoch": 0.11426543647977289,
      "frac_reward_zero_std": 0.46875,
      "grad_norm": 4.738332271575928,
      "learning_rate": 6.800000000000001e-07,
      "loss": 0.0305,
      "num_tokens": 226532528.0,
      "reward": 0.29296875,
      "reward_std": 0.2199622094631195,
      "rewards/simpleverify_reward/mean": 0.29296875,
      "rewards/simpleverify_reward/std": 0.455569326877594,
      "step": 161,
      "tools/generated_tokens": 1531.546875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.01171875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.568359375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2041.0,
      "completions/mean_length": 1659.380859375,
      "completions/mean_terminated_length": 1147.669677734375,
      "completions/min_length": 202.0,
      "completions/min_terminated_length": 202.0,
      "epoch": 0.11497515968772179,
      "frac_reward_zero_std": 0.53125,
      "grad_norm": 0.3620808720588684,
      "learning_rate": 6.78e-07,
      "loss": 0.0418,
      "num_tokens": 227872285.0,
      "reward": 0.2890625,
      "reward_std": 0.21254311501979828,
      "rewards/simpleverify_reward/mean": 0.2890625,
      "rewards/simpleverify_reward/std": 0.45377036929130554,
      "step": 162,
      "tools/generated_tokens": 1661.26171875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.392578125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1484.060546875,
      "completions/mean_terminated_length": 1119.585205078125,
      "completions/min_length": 349.0,
      "completions/min_terminated_length": 349.0,
      "epoch": 0.1156848828956707,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.8598911762237549,
      "learning_rate": 6.76e-07,
      "loss": 0.0389,
      "num_tokens": 229122183.0,
      "reward": 0.34765625,
      "reward_std": 0.29164037108421326,
      "rewards/simpleverify_reward/mean": 0.34765625,
      "rewards/simpleverify_reward/std": 0.47669193148612976,
      "step": 163,
      "tools/generated_tokens": 1484.123046875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.494140625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2021.0,
      "completions/mean_length": 1567.001953125,
      "completions/mean_terminated_length": 1097.146728515625,
      "completions/min_length": 320.0,
      "completions/min_terminated_length": 320.0,
      "epoch": 0.11639460610361958,
      "frac_reward_zero_std": 0.46875,
      "grad_norm": 5.106903553009033,
      "learning_rate": 6.74e-07,
      "loss": 0.0294,
      "num_tokens": 230426929.0,
      "reward": 0.234375,
      "reward_std": 0.21356724202632904,
      "rewards/simpleverify_reward/mean": 0.234375,
      "rewards/simpleverify_reward/std": 0.42402184009552,
      "step": 164,
      "tools/generated_tokens": 1575.0,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0234375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.529296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2033.0,
      "completions/mean_length": 1577.470703125,
      "completions/mean_terminated_length": 1048.369384765625,
      "completions/min_length": 308.0,
      "completions/min_terminated_length": 308.0,
      "epoch": 0.11710432931156849,
      "frac_reward_zero_std": 0.46875,
      "grad_norm": 0.3818837106227875,
      "learning_rate": 6.72e-07,
      "loss": 0.0296,
      "num_tokens": 231737924.0,
      "reward": 0.259765625,
      "reward_std": 0.2131882905960083,
      "rewards/simpleverify_reward/mean": 0.259765625,
      "rewards/simpleverify_reward/std": 0.4389347732067108,
      "step": 165,
      "tools/generated_tokens": 1584.46484375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.009765625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.47265625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2039.0,
      "completions/mean_length": 1528.861328125,
      "completions/mean_terminated_length": 1063.5592041015625,
      "completions/min_length": 394.0,
      "completions/min_terminated_length": 394.0,
      "epoch": 0.11781405251951739,
      "frac_reward_zero_std": 0.40625,
      "grad_norm": 3.3341245651245117,
      "learning_rate": 6.7e-07,
      "loss": 0.0524,
      "num_tokens": 233012592.0,
      "reward": 0.296875,
      "reward_std": 0.24561606347560883,
      "rewards/simpleverify_reward/mean": 0.296875,
      "rewards/simpleverify_reward/std": 0.45732781291007996,
      "step": 166,
      "tools/generated_tokens": 1531.05859375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.37109375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1475.251953125,
      "completions/mean_terminated_length": 1137.2950439453125,
      "completions/min_length": 165.0,
      "completions/min_terminated_length": 165.0,
      "epoch": 0.1185237757274663,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.4514034390449524,
      "learning_rate": 6.68e-07,
      "loss": 0.0279,
      "num_tokens": 234258523.0,
      "reward": 0.400390625,
      "reward_std": 0.2839597463607788,
      "rewards/simpleverify_reward/mean": 0.400390625,
      "rewards/simpleverify_reward/std": 0.4904567301273346,
      "step": 167,
      "tools/generated_tokens": 1482.224609375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.013671875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.376953125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2041.0,
      "completions/mean_length": 1405.888671875,
      "completions/mean_terminated_length": 1017.4012451171875,
      "completions/min_length": 288.0,
      "completions/min_terminated_length": 288.0,
      "epoch": 0.11923349893541518,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.5383172035217285,
      "learning_rate": 6.66e-07,
      "loss": 0.0195,
      "num_tokens": 235473631.0,
      "reward": 0.435546875,
      "reward_std": 0.2723279893398285,
      "rewards/simpleverify_reward/mean": 0.435546875,
      "rewards/simpleverify_reward/std": 0.49631330370903015,
      "step": 168,
      "tools/generated_tokens": 1407.7578125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.416015625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2030.0,
      "completions/mean_length": 1387.3125,
      "completions/mean_terminated_length": 917.301025390625,
      "completions/min_length": 228.0,
      "completions/min_terminated_length": 228.0,
      "epoch": 0.11994322214336409,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 3.8666043281555176,
      "learning_rate": 6.64e-07,
      "loss": 0.0343,
      "num_tokens": 236668015.0,
      "reward": 0.35546875,
      "reward_std": 0.23585405945777893,
      "rewards/simpleverify_reward/mean": 0.35546875,
      "rewards/simpleverify_reward/std": 0.47912323474884033,
      "step": 169,
      "tools/generated_tokens": 1385.380859375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.42578125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1512.083984375,
      "completions/mean_terminated_length": 1114.7041015625,
      "completions/min_length": 441.0,
      "completions/min_terminated_length": 441.0,
      "epoch": 0.12065294535131299,
      "frac_reward_zero_std": 0.40625,
      "grad_norm": 0.42591357231140137,
      "learning_rate": 6.62e-07,
      "loss": 0.0347,
      "num_tokens": 237931620.0,
      "reward": 0.3046875,
      "reward_std": 0.23904018104076385,
      "rewards/simpleverify_reward/mean": 0.3046875,
      "rewards/simpleverify_reward/std": 0.4607250988483429,
      "step": 170,
      "tools/generated_tokens": 1514.310546875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.6015625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1666.26171875,
      "completions/mean_terminated_length": 1089.9117431640625,
      "completions/min_length": 293.0,
      "completions/min_terminated_length": 293.0,
      "epoch": 0.1213626685592619,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 0.42307814955711365,
      "learning_rate": 6.6e-07,
      "loss": 0.03,
      "num_tokens": 239276541.0,
      "reward": 0.240234375,
      "reward_std": 0.2187921404838562,
      "rewards/simpleverify_reward/mean": 0.240234375,
      "rewards/simpleverify_reward/std": 0.4276435375213623,
      "step": 171,
      "tools/generated_tokens": 1668.90234375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.376953125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2032.0,
      "completions/mean_length": 1493.05859375,
      "completions/mean_terminated_length": 1157.310302734375,
      "completions/min_length": 1.0,
      "completions/min_terminated_length": 1.0,
      "epoch": 0.12207239176721078,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.49157026410102844,
      "learning_rate": 6.58e-07,
      "loss": 0.0436,
      "num_tokens": 240537819.0,
      "reward": 0.443359375,
      "reward_std": 0.29585689306259155,
      "rewards/simpleverify_reward/mean": 0.443359375,
      "rewards/simpleverify_reward/std": 0.49726733565330505,
      "step": 172,
      "tools/generated_tokens": 1493.078125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.482421875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1593.255859375,
      "completions/mean_terminated_length": 1169.4000244140625,
      "completions/min_length": 422.0,
      "completions/min_terminated_length": 422.0,
      "epoch": 0.12278211497515969,
      "frac_reward_zero_std": 0.46875,
      "grad_norm": 0.4006853699684143,
      "learning_rate": 6.56e-07,
      "loss": 0.0368,
      "num_tokens": 241840766.0,
      "reward": 0.240234375,
      "reward_std": 0.2065807282924652,
      "rewards/simpleverify_reward/mean": 0.240234375,
      "rewards/simpleverify_reward/std": 0.4276435375213623,
      "step": 173,
      "tools/generated_tokens": 1593.283203125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.353515625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1427.611328125,
      "completions/mean_terminated_length": 1088.3656005859375,
      "completions/min_length": 263.0,
      "completions/min_terminated_length": 263.0,
      "epoch": 0.12349183818310859,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.5583156943321228,
      "learning_rate": 6.54e-07,
      "loss": 0.0479,
      "num_tokens": 243062119.0,
      "reward": 0.4453125,
      "reward_std": 0.3368067741394043,
      "rewards/simpleverify_reward/mean": 0.4453125,
      "rewards/simpleverify_reward/std": 0.49748632311820984,
      "step": 174,
      "tools/generated_tokens": 1427.63671875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2041.0,
      "completions/mean_length": 1487.78125,
      "completions/mean_terminated_length": 1151.6500244140625,
      "completions/min_length": 213.0,
      "completions/min_terminated_length": 213.0,
      "epoch": 0.1242015613910575,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.495913028717041,
      "learning_rate": 6.52e-07,
      "loss": 0.0406,
      "num_tokens": 244309031.0,
      "reward": 0.337890625,
      "reward_std": 0.30493783950805664,
      "rewards/simpleverify_reward/mean": 0.337890625,
      "rewards/simpleverify_reward/std": 0.4734536409378052,
      "step": 175,
      "tools/generated_tokens": 1487.818359375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.44921875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2039.0,
      "completions/mean_length": 1539.017578125,
      "completions/mean_terminated_length": 1123.8900146484375,
      "completions/min_length": 337.0,
      "completions/min_terminated_length": 337.0,
      "epoch": 0.12491128459900638,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.48639461398124695,
      "learning_rate": 6.5e-07,
      "loss": 0.0274,
      "num_tokens": 245583942.0,
      "reward": 0.279296875,
      "reward_std": 0.2824642062187195,
      "rewards/simpleverify_reward/mean": 0.279296875,
      "rewards/simpleverify_reward/std": 0.44909247756004333,
      "step": 176,
      "tools/generated_tokens": 1542.59765625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.419921875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1498.015625,
      "completions/mean_terminated_length": 1099.8787841796875,
      "completions/min_length": 287.0,
      "completions/min_terminated_length": 287.0,
      "epoch": 0.1256210078069553,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.5057523846626282,
      "learning_rate": 6.48e-07,
      "loss": 0.0572,
      "num_tokens": 246831166.0,
      "reward": 0.384765625,
      "reward_std": 0.3200225830078125,
      "rewards/simpleverify_reward/mean": 0.384765625,
      "rewards/simpleverify_reward/std": 0.4870156943798065,
      "step": 177,
      "tools/generated_tokens": 1498.03515625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.341796875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1335.09375,
      "completions/mean_terminated_length": 964.8901977539062,
      "completions/min_length": 131.0,
      "completions/min_terminated_length": 131.0,
      "epoch": 0.1263307310149042,
      "frac_reward_zero_std": 0.40625,
      "grad_norm": 0.46459251642227173,
      "learning_rate": 6.46e-07,
      "loss": 0.0478,
      "num_tokens": 248014606.0,
      "reward": 0.3984375,
      "reward_std": 0.23882928490638733,
      "rewards/simpleverify_reward/mean": 0.3984375,
      "rewards/simpleverify_reward/std": 0.4900552034378052,
      "step": 178,
      "tools/generated_tokens": 1335.123046875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.396484375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1348.11328125,
      "completions/mean_terminated_length": 888.3171997070312,
      "completions/min_length": 211.0,
      "completions/min_terminated_length": 211.0,
      "epoch": 0.1270404542228531,
      "frac_reward_zero_std": 0.40625,
      "grad_norm": 11.390530586242676,
      "learning_rate": 6.44e-07,
      "loss": 0.0424,
      "num_tokens": 249202739.0,
      "reward": 0.365234375,
      "reward_std": 0.2573038935661316,
      "rewards/simpleverify_reward/mean": 0.365234375,
      "rewards/simpleverify_reward/std": 0.4819667339324951,
      "step": 179,
      "tools/generated_tokens": 1352.76171875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.017578125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.548828125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2035.0,
      "completions/mean_length": 1652.64453125,
      "completions/mean_terminated_length": 1171.7142333984375,
      "completions/min_length": 185.0,
      "completions/min_terminated_length": 185.0,
      "epoch": 0.127750177430802,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 0.41326630115509033,
      "learning_rate": 6.42e-07,
      "loss": 0.0406,
      "num_tokens": 250535293.0,
      "reward": 0.255859375,
      "reward_std": 0.2597251534461975,
      "rewards/simpleverify_reward/mean": 0.255859375,
      "rewards/simpleverify_reward/std": 0.43676990270614624,
      "step": 180,
      "tools/generated_tokens": 1652.662109375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.640625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2036.0,
      "completions/mean_length": 1734.658203125,
      "completions/mean_terminated_length": 1176.0924072265625,
      "completions/min_length": 302.0,
      "completions/min_terminated_length": 302.0,
      "epoch": 0.12845990063875087,
      "frac_reward_zero_std": 0.4375,
      "grad_norm": 0.39128628373146057,
      "learning_rate": 6.4e-07,
      "loss": 0.0272,
      "num_tokens": 251910238.0,
      "reward": 0.208984375,
      "reward_std": 0.2384585440158844,
      "rewards/simpleverify_reward/mean": 0.208984375,
      "rewards/simpleverify_reward/std": 0.40698084235191345,
      "step": 181,
      "tools/generated_tokens": 1734.662109375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.455078125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1557.271484375,
      "completions/mean_terminated_length": 1147.45166015625,
      "completions/min_length": 242.0,
      "completions/min_terminated_length": 242.0,
      "epoch": 0.12916962384669978,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.4420749843120575,
      "learning_rate": 6.38e-07,
      "loss": 0.056,
      "num_tokens": 253194102.0,
      "reward": 0.34375,
      "reward_std": 0.3182061016559601,
      "rewards/simpleverify_reward/mean": 0.34375,
      "rewards/simpleverify_reward/std": 0.4754233956336975,
      "step": 182,
      "tools/generated_tokens": 1558.595703125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.427734375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1433.48828125,
      "completions/mean_terminated_length": 974.1774291992188,
      "completions/min_length": 183.0,
      "completions/min_terminated_length": 183.0,
      "epoch": 0.12987934705464868,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.5740164518356323,
      "learning_rate": 6.36e-07,
      "loss": 0.058,
      "num_tokens": 254408656.0,
      "reward": 0.322265625,
      "reward_std": 0.29086214303970337,
      "rewards/simpleverify_reward/mean": 0.322265625,
      "rewards/simpleverify_reward/std": 0.46780112385749817,
      "step": 183,
      "tools/generated_tokens": 1433.521484375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.326171875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2038.0,
      "completions/mean_length": 1386.619140625,
      "completions/mean_terminated_length": 1066.4725341796875,
      "completions/min_length": 161.0,
      "completions/min_terminated_length": 161.0,
      "epoch": 0.13058907026259758,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 11.693355560302734,
      "learning_rate": 6.34e-07,
      "loss": 0.087,
      "num_tokens": 255622422.0,
      "reward": 0.4609375,
      "reward_std": 0.3279082179069519,
      "rewards/simpleverify_reward/mean": 0.4609375,
      "rewards/simpleverify_reward/std": 0.4989593029022217,
      "step": 184,
      "tools/generated_tokens": 1386.376953125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.029296875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.435546875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2012.0,
      "completions/mean_length": 1455.181640625,
      "completions/mean_terminated_length": 997.7474365234375,
      "completions/min_length": 306.0,
      "completions/min_terminated_length": 306.0,
      "epoch": 0.1312987934705465,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.5669927597045898,
      "learning_rate": 6.319999999999999e-07,
      "loss": 0.049,
      "num_tokens": 256859771.0,
      "reward": 0.359375,
      "reward_std": 0.3022531270980835,
      "rewards/simpleverify_reward/mean": 0.359375,
      "rewards/simpleverify_reward/std": 0.48028653860092163,
      "step": 185,
      "tools/generated_tokens": 1461.21484375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.40625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2036.0,
      "completions/mean_length": 1447.982421875,
      "completions/mean_terminated_length": 1037.444091796875,
      "completions/min_length": 283.0,
      "completions/min_terminated_length": 283.0,
      "epoch": 0.1320085166784954,
      "frac_reward_zero_std": 0.40625,
      "grad_norm": 0.5091459155082703,
      "learning_rate": 6.3e-07,
      "loss": 0.0247,
      "num_tokens": 258091328.0,
      "reward": 0.3203125,
      "reward_std": 0.24345500767230988,
      "rewards/simpleverify_reward/mean": 0.3203125,
      "rewards/simpleverify_reward/std": 0.4670529365539551,
      "step": 186,
      "tools/generated_tokens": 1450.478515625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.47265625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2039.0,
      "completions/mean_length": 1609.232421875,
      "completions/mean_terminated_length": 1215.9666748046875,
      "completions/min_length": 268.0,
      "completions/min_terminated_length": 268.0,
      "epoch": 0.1327182398864443,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.4609977900981903,
      "learning_rate": 6.28e-07,
      "loss": 0.0529,
      "num_tokens": 259413510.0,
      "reward": 0.328125,
      "reward_std": 0.29442471265792847,
      "rewards/simpleverify_reward/mean": 0.328125,
      "rewards/simpleverify_reward/std": 0.4699897766113281,
      "step": 187,
      "tools/generated_tokens": 1610.298828125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.525390625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1603.646484375,
      "completions/mean_terminated_length": 1111.7489013671875,
      "completions/min_length": 304.0,
      "completions/min_terminated_length": 304.0,
      "epoch": 0.1334279630943932,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.48466944694519043,
      "learning_rate": 6.26e-07,
      "loss": 0.0423,
      "num_tokens": 260718685.0,
      "reward": 0.296875,
      "reward_std": 0.2620850205421448,
      "rewards/simpleverify_reward/mean": 0.296875,
      "rewards/simpleverify_reward/std": 0.45732781291007996,
      "step": 188,
      "tools/generated_tokens": 1604.88671875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.326171875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2022.0,
      "completions/mean_length": 1331.8359375,
      "completions/mean_terminated_length": 985.1710205078125,
      "completions/min_length": 201.0,
      "completions/min_terminated_length": 201.0,
      "epoch": 0.13413768630234207,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.6402611136436462,
      "learning_rate": 6.24e-07,
      "loss": 0.0173,
      "num_tokens": 261881186.0,
      "reward": 0.353515625,
      "reward_std": 0.30631446838378906,
      "rewards/simpleverify_reward/mean": 0.353515625,
      "rewards/simpleverify_reward/std": 0.47852855920791626,
      "step": 189,
      "tools/generated_tokens": 1335.56640625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.328125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2039.0,
      "completions/mean_length": 1338.669921875,
      "completions/mean_terminated_length": 992.2529296875,
      "completions/min_length": 174.0,
      "completions/min_terminated_length": 174.0,
      "epoch": 0.13484740951029098,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.5538321733474731,
      "learning_rate": 6.219999999999999e-07,
      "loss": 0.0623,
      "num_tokens": 263057815.0,
      "reward": 0.3984375,
      "reward_std": 0.31173911690711975,
      "rewards/simpleverify_reward/mean": 0.3984375,
      "rewards/simpleverify_reward/std": 0.4900552034378052,
      "step": 190,
      "tools/generated_tokens": 1339.92578125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.42578125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1449.65625,
      "completions/mean_terminated_length": 1005.9863891601562,
      "completions/min_length": 171.0,
      "completions/min_terminated_length": 171.0,
      "epoch": 0.13555713271823988,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.5269685387611389,
      "learning_rate": 6.2e-07,
      "loss": 0.0565,
      "num_tokens": 264278770.0,
      "reward": 0.349609375,
      "reward_std": 0.2954065799713135,
      "rewards/simpleverify_reward/mean": 0.349609375,
      "rewards/simpleverify_reward/std": 0.47731292247772217,
      "step": 191,
      "tools/generated_tokens": 1451.8359375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.435546875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2028.0,
      "completions/mean_length": 1440.94921875,
      "completions/mean_terminated_length": 972.5328979492188,
      "completions/min_length": 232.0,
      "completions/min_terminated_length": 232.0,
      "epoch": 0.13626685592618878,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.631152868270874,
      "learning_rate": 6.18e-07,
      "loss": 0.0127,
      "num_tokens": 265514533.0,
      "reward": 0.345703125,
      "reward_std": 0.2569291591644287,
      "rewards/simpleverify_reward/mean": 0.345703125,
      "rewards/simpleverify_reward/std": 0.4760620892047882,
      "step": 192,
      "tools/generated_tokens": 1444.890625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.41796875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2022.0,
      "completions/mean_length": 1538.513671875,
      "completions/mean_terminated_length": 1172.6409912109375,
      "completions/min_length": 301.0,
      "completions/min_terminated_length": 301.0,
      "epoch": 0.1369765791341377,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.5391044616699219,
      "learning_rate": 6.16e-07,
      "loss": 0.0316,
      "num_tokens": 266797404.0,
      "reward": 0.322265625,
      "reward_std": 0.3167951703071594,
      "rewards/simpleverify_reward/mean": 0.322265625,
      "rewards/simpleverify_reward/std": 0.46780112385749817,
      "step": 193,
      "tools/generated_tokens": 1538.560546875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.404296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2036.0,
      "completions/mean_length": 1411.80859375,
      "completions/mean_terminated_length": 980.0327758789062,
      "completions/min_length": 230.0,
      "completions/min_terminated_length": 230.0,
      "epoch": 0.1376863023420866,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 1.9424054622650146,
      "learning_rate": 6.14e-07,
      "loss": 0.0353,
      "num_tokens": 268017514.0,
      "reward": 0.310546875,
      "reward_std": 0.2834952473640442,
      "rewards/simpleverify_reward/mean": 0.310546875,
      "rewards/simpleverify_reward/std": 0.46317005157470703,
      "step": 194,
      "tools/generated_tokens": 1416.12109375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.01171875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.30078125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2015.0,
      "completions/mean_length": 1291.0,
      "completions/mean_terminated_length": 965.3630981445312,
      "completions/min_length": 214.0,
      "completions/min_terminated_length": 214.0,
      "epoch": 0.1383960255500355,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.5140926837921143,
      "learning_rate": 6.119999999999999e-07,
      "loss": 0.0321,
      "num_tokens": 269188075.0,
      "reward": 0.396484375,
      "reward_std": 0.29288023710250854,
      "rewards/simpleverify_reward/mean": 0.396484375,
      "rewards/simpleverify_reward/std": 0.4896455705165863,
      "step": 195,
      "tools/generated_tokens": 1297.953125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.021484375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.494140625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2027.0,
      "completions/mean_length": 1609.544921875,
      "completions/mean_terminated_length": 1181.2470703125,
      "completions/min_length": 247.0,
      "completions/min_terminated_length": 247.0,
      "epoch": 0.1391057487579844,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.4680353105068207,
      "learning_rate": 6.1e-07,
      "loss": 0.0557,
      "num_tokens": 270498946.0,
      "reward": 0.30078125,
      "reward_std": 0.2930728793144226,
      "rewards/simpleverify_reward/mean": 0.30078125,
      "rewards/simpleverify_reward/std": 0.45904624462127686,
      "step": 196,
      "tools/generated_tokens": 1609.56640625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.388671875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1394.96484375,
      "completions/mean_terminated_length": 979.7763671875,
      "completions/min_length": 209.0,
      "completions/min_terminated_length": 209.0,
      "epoch": 0.13981547196593327,
      "frac_reward_zero_std": 0.40625,
      "grad_norm": 0.4783429503440857,
      "learning_rate": 6.079999999999999e-07,
      "loss": 0.0324,
      "num_tokens": 271717074.0,
      "reward": 0.400390625,
      "reward_std": 0.25021058320999146,
      "rewards/simpleverify_reward/mean": 0.400390625,
      "rewards/simpleverify_reward/std": 0.4904567301273346,
      "step": 197,
      "tools/generated_tokens": 1410.7265625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.017578125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.5390625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1583.04296875,
      "completions/mean_terminated_length": 1039.2796630859375,
      "completions/min_length": 308.0,
      "completions/min_terminated_length": 308.0,
      "epoch": 0.14052519517388218,
      "frac_reward_zero_std": 0.4375,
      "grad_norm": 0.44527584314346313,
      "learning_rate": 6.06e-07,
      "loss": 0.0102,
      "num_tokens": 273016040.0,
      "reward": 0.302734375,
      "reward_std": 0.23765070736408234,
      "rewards/simpleverify_reward/mean": 0.302734375,
      "rewards/simpleverify_reward/std": 0.45989060401916504,
      "step": 198,
      "tools/generated_tokens": 1583.17578125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2039.0,
      "completions/mean_length": 1369.0546875,
      "completions/mean_terminated_length": 1082.388916015625,
      "completions/min_length": 281.0,
      "completions/min_terminated_length": 281.0,
      "epoch": 0.14123491838183108,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.5894403457641602,
      "learning_rate": 6.04e-07,
      "loss": 0.0499,
      "num_tokens": 274210430.0,
      "reward": 0.435546875,
      "reward_std": 0.3200957179069519,
      "rewards/simpleverify_reward/mean": 0.435546875,
      "rewards/simpleverify_reward/std": 0.49631330370903015,
      "step": 199,
      "tools/generated_tokens": 1373.01171875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.4140625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2033.0,
      "completions/mean_length": 1431.63671875,
      "completions/mean_terminated_length": 996.0733642578125,
      "completions/min_length": 199.0,
      "completions/min_terminated_length": 199.0,
      "epoch": 0.14194464158977999,
      "frac_reward_zero_std": 0.4375,
      "grad_norm": 0.4364069998264313,
      "learning_rate": 6.019999999999999e-07,
      "loss": 0.0246,
      "num_tokens": 275425172.0,
      "reward": 0.31640625,
      "reward_std": 0.23172909021377563,
      "rewards/simpleverify_reward/mean": 0.31640625,
      "rewards/simpleverify_reward/std": 0.46552830934524536,
      "step": 200,
      "tools/generated_tokens": 1431.662109375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.333984375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1343.51171875,
      "completions/mean_terminated_length": 990.234619140625,
      "completions/min_length": 259.0,
      "completions/min_terminated_length": 259.0,
      "epoch": 0.1426543647977289,
      "frac_reward_zero_std": 0.46875,
      "grad_norm": 0.4648093283176422,
      "learning_rate": 6e-07,
      "loss": 0.0631,
      "num_tokens": 276611708.0,
      "reward": 0.47265625,
      "reward_std": 0.22101986408233643,
      "rewards/simpleverify_reward/mean": 0.47265625,
      "rewards/simpleverify_reward/std": 0.49974003434181213,
      "step": 201,
      "tools/generated_tokens": 1348.701171875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0078125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.451171875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1526.509765625,
      "completions/mean_terminated_length": 1097.8114013671875,
      "completions/min_length": 301.0,
      "completions/min_terminated_length": 301.0,
      "epoch": 0.1433640880056778,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.5087636113166809,
      "learning_rate": 5.979999999999999e-07,
      "loss": 0.0221,
      "num_tokens": 277879866.0,
      "reward": 0.361328125,
      "reward_std": 0.2898038327693939,
      "rewards/simpleverify_reward/mean": 0.361328125,
      "rewards/simpleverify_reward/std": 0.48085519671440125,
      "step": 202,
      "tools/generated_tokens": 1529.951171875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.33203125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1399.08984375,
      "completions/mean_terminated_length": 1076.5322265625,
      "completions/min_length": 186.0,
      "completions/min_terminated_length": 186.0,
      "epoch": 0.1440738112136267,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.5622513294219971,
      "learning_rate": 5.96e-07,
      "loss": 0.0364,
      "num_tokens": 279106445.0,
      "reward": 0.404296875,
      "reward_std": 0.32092171907424927,
      "rewards/simpleverify_reward/mean": 0.404296875,
      "rewards/simpleverify_reward/std": 0.4912354052066803,
      "step": 203,
      "tools/generated_tokens": 1410.986328125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.025390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.373046875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1399.146484375,
      "completions/mean_terminated_length": 1013.0684814453125,
      "completions/min_length": 253.0,
      "completions/min_terminated_length": 253.0,
      "epoch": 0.1447835344215756,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 16.918113708496094,
      "learning_rate": 5.939999999999999e-07,
      "loss": 0.0721,
      "num_tokens": 280328826.0,
      "reward": 0.44140625,
      "reward_std": 0.3008366525173187,
      "rewards/simpleverify_reward/mean": 0.44140625,
      "rewards/simpleverify_reward/std": 0.4970405399799347,
      "step": 204,
      "tools/generated_tokens": 1409.76171875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.01953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.28515625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2011.0,
      "completions/mean_length": 1294.615234375,
      "completions/mean_terminated_length": 994.0846557617188,
      "completions/min_length": 258.0,
      "completions/min_terminated_length": 258.0,
      "epoch": 0.14549325762952448,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.7149117588996887,
      "learning_rate": 5.919999999999999e-07,
      "loss": 0.0258,
      "num_tokens": 281488759.0,
      "reward": 0.453125,
      "reward_std": 0.34695887565612793,
      "rewards/simpleverify_reward/mean": 0.453125,
      "rewards/simpleverify_reward/std": 0.4982847273349762,
      "step": 205,
      "tools/generated_tokens": 1298.134765625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1476.06640625,
      "completions/mean_terminated_length": 1132.90625,
      "completions/min_length": 232.0,
      "completions/min_terminated_length": 232.0,
      "epoch": 0.14620298083747338,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 0.48339390754699707,
      "learning_rate": 5.9e-07,
      "loss": 0.0274,
      "num_tokens": 282729167.0,
      "reward": 0.376953125,
      "reward_std": 0.2586422562599182,
      "rewards/simpleverify_reward/mean": 0.376953125,
      "rewards/simpleverify_reward/std": 0.4850969910621643,
      "step": 206,
      "tools/generated_tokens": 1478.009765625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.396484375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2017.0,
      "completions/mean_length": 1413.107421875,
      "completions/mean_terminated_length": 996.009765625,
      "completions/min_length": 50.0,
      "completions/min_terminated_length": 50.0,
      "epoch": 0.14691270404542228,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.52320796251297,
      "learning_rate": 5.879999999999999e-07,
      "loss": 0.0525,
      "num_tokens": 283945610.0,
      "reward": 0.380859375,
      "reward_std": 0.3087293803691864,
      "rewards/simpleverify_reward/mean": 0.380859375,
      "rewards/simpleverify_reward/std": 0.48607301712036133,
      "step": 207,
      "tools/generated_tokens": 1418.796875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.009765625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.513671875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2041.0,
      "completions/mean_length": 1626.595703125,
      "completions/mean_terminated_length": 1181.4979248046875,
      "completions/min_length": 204.0,
      "completions/min_terminated_length": 204.0,
      "epoch": 0.14762242725337119,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.4202703833580017,
      "learning_rate": 5.86e-07,
      "loss": 0.0438,
      "num_tokens": 285258154.0,
      "reward": 0.28125,
      "reward_std": 0.28131818771362305,
      "rewards/simpleverify_reward/mean": 0.28125,
      "rewards/simpleverify_reward/std": 0.45004892349243164,
      "step": 208,
      "tools/generated_tokens": 1627.75,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.369140625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1430.08984375,
      "completions/mean_terminated_length": 1068.5262451171875,
      "completions/min_length": 256.0,
      "completions/min_terminated_length": 256.0,
      "epoch": 0.1483321504613201,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.5146494507789612,
      "learning_rate": 5.839999999999999e-07,
      "loss": 0.0392,
      "num_tokens": 286479720.0,
      "reward": 0.43359375,
      "reward_std": 0.3149046301841736,
      "rewards/simpleverify_reward/mean": 0.43359375,
      "rewards/simpleverify_reward/std": 0.4960552453994751,
      "step": 209,
      "tools/generated_tokens": 1430.1171875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.3984375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2036.0,
      "completions/mean_length": 1494.216796875,
      "completions/mean_terminated_length": 1127.42529296875,
      "completions/min_length": 163.0,
      "completions/min_terminated_length": 163.0,
      "epoch": 0.149041873669269,
      "frac_reward_zero_std": 0.40625,
      "grad_norm": 0.5937039852142334,
      "learning_rate": 5.819999999999999e-07,
      "loss": 0.0089,
      "num_tokens": 287752569.0,
      "reward": 0.25390625,
      "reward_std": 0.24453411996364594,
      "rewards/simpleverify_reward/mean": 0.25390625,
      "rewards/simpleverify_reward/std": 0.43567025661468506,
      "step": 210,
      "tools/generated_tokens": 1498.4453125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0234375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.00390625
    },
    {
      "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": 0.412109375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2040.0,
      "completions/mean_length": 1451.333984375,
      "completions/mean_terminated_length": 1033.0731201171875,
      "completions/min_length": 178.0,
      "completions/min_terminated_length": 178.0,
      "epoch": 0.1497515968772179,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 7.312984466552734,
      "learning_rate": 5.8e-07,
      "loss": 0.0459,
      "num_tokens": 289004261.0,
      "reward": 0.330078125,
      "reward_std": 0.26880234479904175,
      "rewards/simpleverify_reward/mean": 0.330078125,
      "rewards/simpleverify_reward/std": 0.47070086002349854,
      "step": 211,
      "tools/generated_tokens": 1456.408203125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.025390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.01953125
    },
    {
      "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": 0.330078125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2032.0,
      "completions/mean_length": 1390.099609375,
      "completions/mean_terminated_length": 1065.9447021484375,
      "completions/min_length": 274.0,
      "completions/min_terminated_length": 274.0,
      "epoch": 0.15046132008516677,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 0.5733084678649902,
      "learning_rate": 5.779999999999999e-07,
      "loss": 0.0444,
      "num_tokens": 290204104.0,
      "reward": 0.412109375,
      "reward_std": 0.2694815397262573,
      "rewards/simpleverify_reward/mean": 0.412109375,
      "rewards/simpleverify_reward/std": 0.49269601702690125,
      "step": 212,
      "tools/generated_tokens": 1390.130859375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.45703125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2037.0,
      "completions/mean_length": 1559.466796875,
      "completions/mean_terminated_length": 1148.25537109375,
      "completions/min_length": 168.0,
      "completions/min_terminated_length": 168.0,
      "epoch": 0.15117104329311568,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.5228673219680786,
      "learning_rate": 5.76e-07,
      "loss": 0.0542,
      "num_tokens": 291492679.0,
      "reward": 0.365234375,
      "reward_std": 0.2867896556854248,
      "rewards/simpleverify_reward/mean": 0.365234375,
      "rewards/simpleverify_reward/std": 0.4819667339324951,
      "step": 213,
      "tools/generated_tokens": 1559.5234375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.3671875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2033.0,
      "completions/mean_length": 1482.2421875,
      "completions/mean_terminated_length": 1153.9630126953125,
      "completions/min_length": 173.0,
      "completions/min_terminated_length": 173.0,
      "epoch": 0.15188076650106458,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.494219571352005,
      "learning_rate": 5.739999999999999e-07,
      "loss": 0.0572,
      "num_tokens": 292736995.0,
      "reward": 0.283203125,
      "reward_std": 0.3024464547634125,
      "rewards/simpleverify_reward/mean": 0.283203125,
      "rewards/simpleverify_reward/std": 0.4509948492050171,
      "step": 214,
      "tools/generated_tokens": 1482.267578125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.322265625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1360.130859375,
      "completions/mean_terminated_length": 1033.0460205078125,
      "completions/min_length": 280.0,
      "completions/min_terminated_length": 280.0,
      "epoch": 0.15259048970901348,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.5642914175987244,
      "learning_rate": 5.719999999999999e-07,
      "loss": 0.0515,
      "num_tokens": 293912630.0,
      "reward": 0.4453125,
      "reward_std": 0.3157520294189453,
      "rewards/simpleverify_reward/mean": 0.4453125,
      "rewards/simpleverify_reward/std": 0.49748632311820984,
      "step": 215,
      "tools/generated_tokens": 1360.1640625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.40625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2035.0,
      "completions/mean_length": 1429.306640625,
      "completions/mean_terminated_length": 1005.9901123046875,
      "completions/min_length": 1.0,
      "completions/min_terminated_length": 1.0,
      "epoch": 0.1533002129169624,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.5976746082305908,
      "learning_rate": 5.699999999999999e-07,
      "loss": 0.0563,
      "num_tokens": 295125347.0,
      "reward": 0.36328125,
      "reward_std": 0.2989523410797119,
      "rewards/simpleverify_reward/mean": 0.36328125,
      "rewards/simpleverify_reward/std": 0.4814152419567108,
      "step": 216,
      "tools/generated_tokens": 1429.376953125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.435546875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1492.66015625,
      "completions/mean_terminated_length": 1064.1453857421875,
      "completions/min_length": 135.0,
      "completions/min_terminated_length": 135.0,
      "epoch": 0.1540099361249113,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.5782800912857056,
      "learning_rate": 5.679999999999999e-07,
      "loss": 0.0368,
      "num_tokens": 296385320.0,
      "reward": 0.341796875,
      "reward_std": 0.3323614299297333,
      "rewards/simpleverify_reward/mean": 0.341796875,
      "rewards/simpleverify_reward/std": 0.4747757613658905,
      "step": 217,
      "tools/generated_tokens": 1495.232421875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.009765625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.23046875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1266.169921875,
      "completions/mean_terminated_length": 1032.0177001953125,
      "completions/min_length": 263.0,
      "completions/min_terminated_length": 263.0,
      "epoch": 0.1547196593328602,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.6306391954421997,
      "learning_rate": 5.66e-07,
      "loss": 0.0561,
      "num_tokens": 297522440.0,
      "reward": 0.615234375,
      "reward_std": 0.3178749680519104,
      "rewards/simpleverify_reward/mean": 0.615234375,
      "rewards/simpleverify_reward/std": 0.4870156943798065,
      "step": 218,
      "tools/generated_tokens": 1275.51171875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.32421875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1369.603515625,
      "completions/mean_terminated_length": 1044.1300048828125,
      "completions/min_length": 223.0,
      "completions/min_terminated_length": 223.0,
      "epoch": 0.1554293825408091,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.6182549595832825,
      "learning_rate": 5.639999999999999e-07,
      "loss": 0.0345,
      "num_tokens": 298705469.0,
      "reward": 0.451171875,
      "reward_std": 0.2972636818885803,
      "rewards/simpleverify_reward/mean": 0.451171875,
      "rewards/simpleverify_reward/std": 0.498096764087677,
      "step": 219,
      "tools/generated_tokens": 1369.66015625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.373046875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1397.669921875,
      "completions/mean_terminated_length": 1010.71337890625,
      "completions/min_length": 274.0,
      "completions/min_terminated_length": 274.0,
      "epoch": 0.15613910574875797,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.5839889645576477,
      "learning_rate": 5.620000000000001e-07,
      "loss": 0.0618,
      "num_tokens": 299921056.0,
      "reward": 0.439453125,
      "reward_std": 0.3186393976211548,
      "rewards/simpleverify_reward/mean": 0.439453125,
      "rewards/simpleverify_reward/std": 0.49680593609809875,
      "step": 220,
      "tools/generated_tokens": 1407.921875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.009765625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.37109375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2031.0,
      "completions/mean_length": 1393.890625,
      "completions/mean_terminated_length": 1007.9254760742188,
      "completions/min_length": 235.0,
      "completions/min_terminated_length": 235.0,
      "epoch": 0.15684882895670688,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.52753084897995,
      "learning_rate": 5.6e-07,
      "loss": 0.0273,
      "num_tokens": 301126356.0,
      "reward": 0.3671875,
      "reward_std": 0.2859557271003723,
      "rewards/simpleverify_reward/mean": 0.3671875,
      "rewards/simpleverify_reward/std": 0.48250964283943176,
      "step": 221,
      "tools/generated_tokens": 1395.826171875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.37890625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2040.0,
      "completions/mean_length": 1431.96875,
      "completions/mean_terminated_length": 1056.15087890625,
      "completions/min_length": 267.0,
      "completions/min_terminated_length": 267.0,
      "epoch": 0.15755855216465578,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.583171546459198,
      "learning_rate": 5.58e-07,
      "loss": 0.0498,
      "num_tokens": 302348196.0,
      "reward": 0.36328125,
      "reward_std": 0.31380563974380493,
      "rewards/simpleverify_reward/mean": 0.36328125,
      "rewards/simpleverify_reward/std": 0.4814152419567108,
      "step": 222,
      "tools/generated_tokens": 1431.98828125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.291015625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2040.0,
      "completions/mean_length": 1308.46484375,
      "completions/mean_terminated_length": 1004.9091186523438,
      "completions/min_length": 39.0,
      "completions/min_terminated_length": 39.0,
      "epoch": 0.15826827537260468,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 17.87936782836914,
      "learning_rate": 5.560000000000001e-07,
      "loss": 0.0626,
      "num_tokens": 303510613.0,
      "reward": 0.369140625,
      "reward_std": 0.38441938161849976,
      "rewards/simpleverify_reward/mean": 0.369140625,
      "rewards/simpleverify_reward/std": 0.4830440282821655,
      "step": 223,
      "tools/generated_tokens": 1308.94140625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.462890625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2034.0,
      "completions/mean_length": 1533.009765625,
      "completions/mean_terminated_length": 1089.181884765625,
      "completions/min_length": 238.0,
      "completions/min_terminated_length": 238.0,
      "epoch": 0.1589779985805536,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.4689052402973175,
      "learning_rate": 5.54e-07,
      "loss": 0.0426,
      "num_tokens": 304782442.0,
      "reward": 0.33203125,
      "reward_std": 0.2940274477005005,
      "rewards/simpleverify_reward/mean": 0.33203125,
      "rewards/simpleverify_reward/std": 0.47140273451805115,
      "step": 224,
      "tools/generated_tokens": 1533.03125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.265625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1250.9921875,
      "completions/mean_terminated_length": 962.7127075195312,
      "completions/min_length": 283.0,
      "completions/min_terminated_length": 283.0,
      "epoch": 0.1596877217885025,
      "frac_reward_zero_std": 0.09375,
      "grad_norm": 0.7160318493843079,
      "learning_rate": 5.520000000000001e-07,
      "loss": 0.0824,
      "num_tokens": 305907635.0,
      "reward": 0.466796875,
      "reward_std": 0.3645517826080322,
      "rewards/simpleverify_reward/mean": 0.466796875,
      "rewards/simpleverify_reward/std": 0.4993842542171478,
      "step": 225,
      "tools/generated_tokens": 1254.359375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.44140625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1536.984375,
      "completions/mean_terminated_length": 1133.1748046875,
      "completions/min_length": 371.0,
      "completions/min_terminated_length": 371.0,
      "epoch": 0.1603974449964514,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.5075684189796448,
      "learning_rate": 5.5e-07,
      "loss": 0.0301,
      "num_tokens": 307184574.0,
      "reward": 0.33203125,
      "reward_std": 0.2898435592651367,
      "rewards/simpleverify_reward/mean": 0.33203125,
      "rewards/simpleverify_reward/std": 0.47140273451805115,
      "step": 226,
      "tools/generated_tokens": 1544.0390625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.24609375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2041.0,
      "completions/mean_length": 1256.21484375,
      "completions/mean_terminated_length": 997.7564697265625,
      "completions/min_length": 170.0,
      "completions/min_terminated_length": 170.0,
      "epoch": 0.1611071682044003,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.9388975501060486,
      "learning_rate": 5.48e-07,
      "loss": 0.0372,
      "num_tokens": 308313608.0,
      "reward": 0.416015625,
      "reward_std": 0.26389631628990173,
      "rewards/simpleverify_reward/mean": 0.416015625,
      "rewards/simpleverify_reward/std": 0.493378221988678,
      "step": 227,
      "tools/generated_tokens": 1256.794921875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.373046875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2037.0,
      "completions/mean_length": 1343.794921875,
      "completions/mean_terminated_length": 924.7819213867188,
      "completions/min_length": 166.0,
      "completions/min_terminated_length": 166.0,
      "epoch": 0.16181689141234917,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 0.4860675036907196,
      "learning_rate": 5.46e-07,
      "loss": 0.0292,
      "num_tokens": 309487423.0,
      "reward": 0.396484375,
      "reward_std": 0.25909245014190674,
      "rewards/simpleverify_reward/mean": 0.396484375,
      "rewards/simpleverify_reward/std": 0.4896455705165863,
      "step": 228,
      "tools/generated_tokens": 1343.8203125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.373046875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1433.302734375,
      "completions/mean_terminated_length": 1067.5482177734375,
      "completions/min_length": 250.0,
      "completions/min_terminated_length": 250.0,
      "epoch": 0.16252661462029808,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.5392472743988037,
      "learning_rate": 5.44e-07,
      "loss": 0.0592,
      "num_tokens": 310706238.0,
      "reward": 0.4921875,
      "reward_std": 0.28324806690216064,
      "rewards/simpleverify_reward/mean": 0.4921875,
      "rewards/simpleverify_reward/std": 0.5004279017448425,
      "step": 229,
      "tools/generated_tokens": 1436.373046875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.310546875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2007.0,
      "completions/mean_length": 1228.3515625,
      "completions/mean_terminated_length": 859.1614379882812,
      "completions/min_length": 233.0,
      "completions/min_terminated_length": 233.0,
      "epoch": 0.16323633782824698,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.715187132358551,
      "learning_rate": 5.420000000000001e-07,
      "loss": 0.0632,
      "num_tokens": 311819906.0,
      "reward": 0.44140625,
      "reward_std": 0.25748780369758606,
      "rewards/simpleverify_reward/mean": 0.44140625,
      "rewards/simpleverify_reward/std": 0.4970405399799347,
      "step": 230,
      "tools/generated_tokens": 1228.43359375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.423828125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1522.552734375,
      "completions/mean_terminated_length": 1136.0372314453125,
      "completions/min_length": 416.0,
      "completions/min_terminated_length": 416.0,
      "epoch": 0.16394606103619588,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.6242817640304565,
      "learning_rate": 5.4e-07,
      "loss": 0.0853,
      "num_tokens": 313081981.0,
      "reward": 0.37890625,
      "reward_std": 0.3475643992424011,
      "rewards/simpleverify_reward/mean": 0.37890625,
      "rewards/simpleverify_reward/std": 0.4855891764163971,
      "step": 231,
      "tools/generated_tokens": 1522.591796875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.361328125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 1975.0,
      "completions/mean_length": 1345.6328125,
      "completions/mean_terminated_length": 948.2691650390625,
      "completions/min_length": 234.0,
      "completions/min_terminated_length": 234.0,
      "epoch": 0.1646557842441448,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.6576735973358154,
      "learning_rate": 5.38e-07,
      "loss": 0.0346,
      "num_tokens": 314271102.0,
      "reward": 0.3984375,
      "reward_std": 0.2397531270980835,
      "rewards/simpleverify_reward/mean": 0.3984375,
      "rewards/simpleverify_reward/std": 0.4900552034378052,
      "step": 232,
      "tools/generated_tokens": 1347.5703125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.3359375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2016.0,
      "completions/mean_length": 1380.49609375,
      "completions/mean_terminated_length": 1042.817626953125,
      "completions/min_length": 238.0,
      "completions/min_terminated_length": 238.0,
      "epoch": 0.1653655074520937,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 1.771489143371582,
      "learning_rate": 5.36e-07,
      "loss": 0.0326,
      "num_tokens": 315473557.0,
      "reward": 0.404296875,
      "reward_std": 0.33762484788894653,
      "rewards/simpleverify_reward/mean": 0.404296875,
      "rewards/simpleverify_reward/std": 0.4912354052066803,
      "step": 233,
      "tools/generated_tokens": 1387.240234375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.259765625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 1989.0,
      "completions/mean_length": 1260.865234375,
      "completions/mean_terminated_length": 984.6411743164062,
      "completions/min_length": 43.0,
      "completions/min_terminated_length": 43.0,
      "epoch": 0.1660752306600426,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.6351748108863831,
      "learning_rate": 5.34e-07,
      "loss": 0.0156,
      "num_tokens": 316601232.0,
      "reward": 0.47265625,
      "reward_std": 0.30422520637512207,
      "rewards/simpleverify_reward/mean": 0.47265625,
      "rewards/simpleverify_reward/std": 0.49974003434181213,
      "step": 234,
      "tools/generated_tokens": 1260.90234375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.330078125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1397.95703125,
      "completions/mean_terminated_length": 1077.6734619140625,
      "completions/min_length": 233.0,
      "completions/min_terminated_length": 233.0,
      "epoch": 0.16678495386799147,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.5346411466598511,
      "learning_rate": 5.32e-07,
      "loss": 0.0397,
      "num_tokens": 317810817.0,
      "reward": 0.39453125,
      "reward_std": 0.32192516326904297,
      "rewards/simpleverify_reward/mean": 0.39453125,
      "rewards/simpleverify_reward/std": 0.4892277717590332,
      "step": 235,
      "tools/generated_tokens": 1398.720703125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.24609375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1272.865234375,
      "completions/mean_terminated_length": 1019.8419189453125,
      "completions/min_length": 197.0,
      "completions/min_terminated_length": 197.0,
      "epoch": 0.16749467707594037,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.6538094878196716,
      "learning_rate": 5.3e-07,
      "loss": 0.0332,
      "num_tokens": 318945644.0,
      "reward": 0.447265625,
      "reward_std": 0.3570775091648102,
      "rewards/simpleverify_reward/mean": 0.447265625,
      "rewards/simpleverify_reward/std": 0.4976975917816162,
      "step": 236,
      "tools/generated_tokens": 1273.1640625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.333984375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1397.390625,
      "completions/mean_terminated_length": 1071.1319580078125,
      "completions/min_length": 231.0,
      "completions/min_terminated_length": 231.0,
      "epoch": 0.16820440028388928,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.5986636281013489,
      "learning_rate": 5.28e-07,
      "loss": 0.0516,
      "num_tokens": 320150099.0,
      "reward": 0.41796875,
      "reward_std": 0.3584598898887634,
      "rewards/simpleverify_reward/mean": 0.41796875,
      "rewards/simpleverify_reward/std": 0.4937073290348053,
      "step": 237,
      "tools/generated_tokens": 1398.638671875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.361328125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1361.90234375,
      "completions/mean_terminated_length": 973.7431640625,
      "completions/min_length": 252.0,
      "completions/min_terminated_length": 252.0,
      "epoch": 0.16891412349183818,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.6070579290390015,
      "learning_rate": 5.26e-07,
      "loss": 0.0503,
      "num_tokens": 321331008.0,
      "reward": 0.380859375,
      "reward_std": 0.2928847670555115,
      "rewards/simpleverify_reward/mean": 0.380859375,
      "rewards/simpleverify_reward/std": 0.48607301712036133,
      "step": 238,
      "tools/generated_tokens": 1363.7265625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.283203125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1239.697265625,
      "completions/mean_terminated_length": 920.340576171875,
      "completions/min_length": 176.0,
      "completions/min_terminated_length": 176.0,
      "epoch": 0.16962384669978708,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.6365195512771606,
      "learning_rate": 5.24e-07,
      "loss": 0.0498,
      "num_tokens": 322449941.0,
      "reward": 0.4609375,
      "reward_std": 0.32901355624198914,
      "rewards/simpleverify_reward/mean": 0.4609375,
      "rewards/simpleverify_reward/std": 0.4989593029022217,
      "step": 239,
      "tools/generated_tokens": 1239.7734375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.30859375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1275.50390625,
      "completions/mean_terminated_length": 930.717529296875,
      "completions/min_length": 194.0,
      "completions/min_terminated_length": 194.0,
      "epoch": 0.170333569907736,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.6822172403335571,
      "learning_rate": 5.22e-07,
      "loss": 0.0475,
      "num_tokens": 323599785.0,
      "reward": 0.451171875,
      "reward_std": 0.31717967987060547,
      "rewards/simpleverify_reward/mean": 0.451171875,
      "rewards/simpleverify_reward/std": 0.498096764087677,
      "step": 240,
      "tools/generated_tokens": 1284.462890625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0078125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.34765625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1352.7578125,
      "completions/mean_terminated_length": 982.2395629882812,
      "completions/min_length": 158.0,
      "completions/min_terminated_length": 158.0,
      "epoch": 0.1710432931156849,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.5963873863220215,
      "learning_rate": 5.2e-07,
      "loss": 0.0401,
      "num_tokens": 324784865.0,
      "reward": 0.40234375,
      "reward_std": 0.30037921667099,
      "rewards/simpleverify_reward/mean": 0.40234375,
      "rewards/simpleverify_reward/std": 0.4908501207828522,
      "step": 241,
      "tools/generated_tokens": 1355.04296875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.279296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1230.896484375,
      "completions/mean_terminated_length": 914.2412109375,
      "completions/min_length": 217.0,
      "completions/min_terminated_length": 217.0,
      "epoch": 0.1717530163236338,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.6322327852249146,
      "learning_rate": 5.18e-07,
      "loss": 0.0374,
      "num_tokens": 325895244.0,
      "reward": 0.458984375,
      "reward_std": 0.3352106809616089,
      "rewards/simpleverify_reward/mean": 0.458984375,
      "rewards/simpleverify_reward/std": 0.49880221486091614,
      "step": 242,
      "tools/generated_tokens": 1230.935546875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.3671875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1441.7421875,
      "completions/mean_terminated_length": 1089.9630126953125,
      "completions/min_length": 337.0,
      "completions/min_terminated_length": 337.0,
      "epoch": 0.17246273953158267,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.5796099305152893,
      "learning_rate": 5.16e-07,
      "loss": 0.008,
      "num_tokens": 327117752.0,
      "reward": 0.36328125,
      "reward_std": 0.31451743841171265,
      "rewards/simpleverify_reward/mean": 0.36328125,
      "rewards/simpleverify_reward/std": 0.4814152419567108,
      "step": 243,
      "tools/generated_tokens": 1441.845703125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.400390625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1404.41015625,
      "completions/mean_terminated_length": 974.6514282226562,
      "completions/min_length": 245.0,
      "completions/min_terminated_length": 245.0,
      "epoch": 0.17317246273953157,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.5231593251228333,
      "learning_rate": 5.14e-07,
      "loss": 0.0344,
      "num_tokens": 328327285.0,
      "reward": 0.337890625,
      "reward_std": 0.3096126914024353,
      "rewards/simpleverify_reward/mean": 0.337890625,
      "rewards/simpleverify_reward/std": 0.4734536409378052,
      "step": 244,
      "tools/generated_tokens": 1406.2890625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.443359375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2033.0,
      "completions/mean_length": 1458.349609375,
      "completions/mean_terminated_length": 988.6982421875,
      "completions/min_length": 185.0,
      "completions/min_terminated_length": 185.0,
      "epoch": 0.17388218594748048,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.5477619171142578,
      "learning_rate": 5.12e-07,
      "loss": 0.0682,
      "num_tokens": 329563037.0,
      "reward": 0.294921875,
      "reward_std": 0.2743849754333496,
      "rewards/simpleverify_reward/mean": 0.294921875,
      "rewards/simpleverify_reward/std": 0.4564536213874817,
      "step": 245,
      "tools/generated_tokens": 1459.162109375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.41015625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1371.693359375,
      "completions/mean_terminated_length": 901.4138793945312,
      "completions/min_length": 194.0,
      "completions/min_terminated_length": 194.0,
      "epoch": 0.17459190915542938,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.6315802335739136,
      "learning_rate": 5.1e-07,
      "loss": 0.0407,
      "num_tokens": 330749568.0,
      "reward": 0.365234375,
      "reward_std": 0.26947450637817383,
      "rewards/simpleverify_reward/mean": 0.365234375,
      "rewards/simpleverify_reward/std": 0.4819667339324951,
      "step": 246,
      "tools/generated_tokens": 1371.7890625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.138671875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2015.0,
      "completions/mean_length": 1019.748046875,
      "completions/mean_terminated_length": 854.2041015625,
      "completions/min_length": 134.0,
      "completions/min_terminated_length": 134.0,
      "epoch": 0.17530163236337828,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.7383608818054199,
      "learning_rate": 5.079999999999999e-07,
      "loss": 0.0647,
      "num_tokens": 331755263.0,
      "reward": 0.5625,
      "reward_std": 0.3399468660354614,
      "rewards/simpleverify_reward/mean": 0.5625,
      "rewards/simpleverify_reward/std": 0.49656352400779724,
      "step": 247,
      "tools/generated_tokens": 1019.7890625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.240234375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1130.384765625,
      "completions/mean_terminated_length": 840.2390747070312,
      "completions/min_length": 253.0,
      "completions/min_terminated_length": 253.0,
      "epoch": 0.1760113555713272,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.6927427053451538,
      "learning_rate": 5.06e-07,
      "loss": 0.035,
      "num_tokens": 332809764.0,
      "reward": 0.51171875,
      "reward_std": 0.30499789118766785,
      "rewards/simpleverify_reward/mean": 0.51171875,
      "rewards/simpleverify_reward/std": 0.5003514885902405,
      "step": 248,
      "tools/generated_tokens": 1130.439453125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.337890625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2030.0,
      "completions/mean_length": 1286.341796875,
      "completions/mean_terminated_length": 897.6489868164062,
      "completions/min_length": 207.0,
      "completions/min_terminated_length": 207.0,
      "epoch": 0.1767210787792761,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.7188593149185181,
      "learning_rate": 5.04e-07,
      "loss": 0.0768,
      "num_tokens": 333962127.0,
      "reward": 0.423828125,
      "reward_std": 0.34203383326530457,
      "rewards/simpleverify_reward/mean": 0.423828125,
      "rewards/simpleverify_reward/std": 0.4946470856666565,
      "step": 249,
      "tools/generated_tokens": 1294.431640625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.013671875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.244140625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1224.140625,
      "completions/mean_terminated_length": 958.0361938476562,
      "completions/min_length": 149.0,
      "completions/min_terminated_length": 149.0,
      "epoch": 0.177430801987225,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 1.1489200592041016,
      "learning_rate": 5.02e-07,
      "loss": 0.0561,
      "num_tokens": 335076768.0,
      "reward": 0.431640625,
      "reward_std": 0.2638174891471863,
      "rewards/simpleverify_reward/mean": 0.431640625,
      "rewards/simpleverify_reward/std": 0.4957893490791321,
      "step": 250,
      "tools/generated_tokens": 1229.025390625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.263671875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2014.0,
      "completions/mean_length": 1193.462890625,
      "completions/mean_terminated_length": 887.4615478515625,
      "completions/min_length": 243.0,
      "completions/min_terminated_length": 243.0,
      "epoch": 0.17814052519517387,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.5607917308807373,
      "learning_rate": 5e-07,
      "loss": 0.0173,
      "num_tokens": 336173149.0,
      "reward": 0.453125,
      "reward_std": 0.3089769780635834,
      "rewards/simpleverify_reward/mean": 0.453125,
      "rewards/simpleverify_reward/std": 0.4982847273349762,
      "step": 251,
      "tools/generated_tokens": 1193.53125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.267578125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 1993.0,
      "completions/mean_length": 1299.916015625,
      "completions/mean_terminated_length": 1026.615966796875,
      "completions/min_length": 228.0,
      "completions/min_terminated_length": 228.0,
      "epoch": 0.17885024840312277,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.766234278678894,
      "learning_rate": 4.979999999999999e-07,
      "loss": 0.0461,
      "num_tokens": 337324235.0,
      "reward": 0.388671875,
      "reward_std": 0.2685081660747528,
      "rewards/simpleverify_reward/mean": 0.388671875,
      "rewards/simpleverify_reward/std": 0.4879252314567566,
      "step": 252,
      "tools/generated_tokens": 1303.080078125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.21484375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1259.505859375,
      "completions/mean_terminated_length": 1043.748779296875,
      "completions/min_length": 87.0,
      "completions/min_terminated_length": 87.0,
      "epoch": 0.17955997161107168,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 5.994595527648926,
      "learning_rate": 4.96e-07,
      "loss": -0.0006,
      "num_tokens": 338461358.0,
      "reward": 0.37890625,
      "reward_std": 0.3450518250465393,
      "rewards/simpleverify_reward/mean": 0.37890625,
      "rewards/simpleverify_reward/std": 0.4855891764163971,
      "step": 253,
      "tools/generated_tokens": 1261.7578125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.013671875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.306640625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1342.34375,
      "completions/mean_terminated_length": 1030.2647705078125,
      "completions/min_length": 225.0,
      "completions/min_terminated_length": 225.0,
      "epoch": 0.18026969481902058,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.6243718862533569,
      "learning_rate": 4.94e-07,
      "loss": 0.0231,
      "num_tokens": 339635622.0,
      "reward": 0.349609375,
      "reward_std": 0.3102465271949768,
      "rewards/simpleverify_reward/mean": 0.349609375,
      "rewards/simpleverify_reward/std": 0.47731292247772217,
      "step": 254,
      "tools/generated_tokens": 1344.78125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.298828125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2038.0,
      "completions/mean_length": 1337.400390625,
      "completions/mean_terminated_length": 1034.5543212890625,
      "completions/min_length": 226.0,
      "completions/min_terminated_length": 226.0,
      "epoch": 0.18097941802696949,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.7035239934921265,
      "learning_rate": 4.92e-07,
      "loss": 0.0115,
      "num_tokens": 340817485.0,
      "reward": 0.32421875,
      "reward_std": 0.2626042366027832,
      "rewards/simpleverify_reward/mean": 0.32421875,
      "rewards/simpleverify_reward/std": 0.4685399830341339,
      "step": 255,
      "tools/generated_tokens": 1343.7734375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.283203125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1353.115234375,
      "completions/mean_terminated_length": 1078.5694580078125,
      "completions/min_length": 286.0,
      "completions/min_terminated_length": 286.0,
      "epoch": 0.1816891412349184,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.5653458833694458,
      "learning_rate": 4.9e-07,
      "loss": 0.049,
      "num_tokens": 341999896.0,
      "reward": 0.4296875,
      "reward_std": 0.2921462059020996,
      "rewards/simpleverify_reward/mean": 0.4296875,
      "rewards/simpleverify_reward/std": 0.4955156147480011,
      "step": 256,
      "tools/generated_tokens": 1353.1796875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.37890625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2039.0,
      "completions/mean_length": 1485.955078125,
      "completions/mean_terminated_length": 1143.072265625,
      "completions/min_length": 295.0,
      "completions/min_terminated_length": 295.0,
      "epoch": 0.1823988644428673,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.581987202167511,
      "learning_rate": 4.879999999999999e-07,
      "loss": 0.0475,
      "num_tokens": 343262705.0,
      "reward": 0.341796875,
      "reward_std": 0.2982213497161865,
      "rewards/simpleverify_reward/mean": 0.341796875,
      "rewards/simpleverify_reward/std": 0.4747757613658905,
      "step": 257,
      "tools/generated_tokens": 1485.984375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.234375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1212.74609375,
      "completions/mean_terminated_length": 957.0560913085938,
      "completions/min_length": 188.0,
      "completions/min_terminated_length": 188.0,
      "epoch": 0.18310858765081617,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.7033218741416931,
      "learning_rate": 4.86e-07,
      "loss": 0.037,
      "num_tokens": 344373071.0,
      "reward": 0.4296875,
      "reward_std": 0.29866501688957214,
      "rewards/simpleverify_reward/mean": 0.4296875,
      "rewards/simpleverify_reward/std": 0.4955156147480011,
      "step": 258,
      "tools/generated_tokens": 1212.794921875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.369140625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2025.0,
      "completions/mean_length": 1419.201171875,
      "completions/mean_terminated_length": 1051.2662353515625,
      "completions/min_length": 138.0,
      "completions/min_terminated_length": 138.0,
      "epoch": 0.18381831085876507,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.5521474480628967,
      "learning_rate": 4.839999999999999e-07,
      "loss": 0.0513,
      "num_tokens": 345601581.0,
      "reward": 0.291015625,
      "reward_std": 0.2740667462348938,
      "rewards/simpleverify_reward/mean": 0.291015625,
      "rewards/simpleverify_reward/std": 0.45467492938041687,
      "step": 259,
      "tools/generated_tokens": 1424.841796875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.248046875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2035.0,
      "completions/mean_length": 1219.16015625,
      "completions/mean_terminated_length": 945.7506103515625,
      "completions/min_length": 232.0,
      "completions/min_terminated_length": 232.0,
      "epoch": 0.18452803406671398,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.6541528701782227,
      "learning_rate": 4.82e-07,
      "loss": 0.0457,
      "num_tokens": 346711295.0,
      "reward": 0.533203125,
      "reward_std": 0.3350181579589844,
      "rewards/simpleverify_reward/mean": 0.533203125,
      "rewards/simpleverify_reward/std": 0.4993842542171478,
      "step": 260,
      "tools/generated_tokens": 1219.19921875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.365234375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1436.12109375,
      "completions/mean_terminated_length": 1084.055419921875,
      "completions/min_length": 255.0,
      "completions/min_terminated_length": 255.0,
      "epoch": 0.18523775727466288,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.5888699889183044,
      "learning_rate": 4.8e-07,
      "loss": 0.0627,
      "num_tokens": 347927373.0,
      "reward": 0.384765625,
      "reward_std": 0.3195419907569885,
      "rewards/simpleverify_reward/mean": 0.384765625,
      "rewards/simpleverify_reward/std": 0.4870156943798065,
      "step": 261,
      "tools/generated_tokens": 1436.265625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.2109375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2018.0,
      "completions/mean_length": 1095.40234375,
      "completions/mean_terminated_length": 840.7474975585938,
      "completions/min_length": 163.0,
      "completions/min_terminated_length": 163.0,
      "epoch": 0.18594748048261178,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 0.6816576719284058,
      "learning_rate": 4.779999999999999e-07,
      "loss": 0.01,
      "num_tokens": 348970334.0,
      "reward": 0.40234375,
      "reward_std": 0.2647759020328522,
      "rewards/simpleverify_reward/mean": 0.40234375,
      "rewards/simpleverify_reward/std": 0.4908501207828522,
      "step": 262,
      "tools/generated_tokens": 1097.2265625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.310546875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1245.9140625,
      "completions/mean_terminated_length": 884.634521484375,
      "completions/min_length": 113.0,
      "completions/min_terminated_length": 113.0,
      "epoch": 0.18665720369056069,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.6039858460426331,
      "learning_rate": 4.76e-07,
      "loss": 0.0488,
      "num_tokens": 350094501.0,
      "reward": 0.353515625,
      "reward_std": 0.3159897029399872,
      "rewards/simpleverify_reward/mean": 0.353515625,
      "rewards/simpleverify_reward/std": 0.47852855920791626,
      "step": 263,
      "tools/generated_tokens": 1248.1796875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.001953125
    },
    {
      "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": 0.296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 1986.0,
      "completions/mean_length": 1238.677734375,
      "completions/mean_terminated_length": 896.9639282226562,
      "completions/min_length": 116.0,
      "completions/min_terminated_length": 116.0,
      "epoch": 0.1873669268985096,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 2.7133028507232666,
      "learning_rate": 4.7399999999999993e-07,
      "loss": 0.0203,
      "num_tokens": 351233850.0,
      "reward": 0.359375,
      "reward_std": 0.28686124086380005,
      "rewards/simpleverify_reward/mean": 0.359375,
      "rewards/simpleverify_reward/std": 0.48028653860092163,
      "step": 264,
      "tools/generated_tokens": 1249.25,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.02734375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.3125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2041.0,
      "completions/mean_length": 1246.6484375,
      "completions/mean_terminated_length": 882.3977661132812,
      "completions/min_length": 170.0,
      "completions/min_terminated_length": 170.0,
      "epoch": 0.1880766501064585,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.6047411561012268,
      "learning_rate": 4.7199999999999994e-07,
      "loss": 0.0125,
      "num_tokens": 352356216.0,
      "reward": 0.30078125,
      "reward_std": 0.2849799394607544,
      "rewards/simpleverify_reward/mean": 0.30078125,
      "rewards/simpleverify_reward/std": 0.45904624462127686,
      "step": 265,
      "tools/generated_tokens": 1244.19921875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.001953125
    },
    {
      "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": 0.330078125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2041.0,
      "completions/mean_length": 1288.2265625,
      "completions/mean_terminated_length": 913.8775634765625,
      "completions/min_length": 219.0,
      "completions/min_terminated_length": 219.0,
      "epoch": 0.18878637331440737,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.5851951241493225,
      "learning_rate": 4.6999999999999995e-07,
      "loss": 0.0417,
      "num_tokens": 353501708.0,
      "reward": 0.34375,
      "reward_std": 0.28555071353912354,
      "rewards/simpleverify_reward/mean": 0.34375,
      "rewards/simpleverify_reward/std": 0.4754233956336975,
      "step": 266,
      "tools/generated_tokens": 1288.26953125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.36328125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2039.0,
      "completions/mean_length": 1398.181640625,
      "completions/mean_terminated_length": 1027.4263916015625,
      "completions/min_length": 199.0,
      "completions/min_terminated_length": 199.0,
      "epoch": 0.18949609652235627,
      "frac_reward_zero_std": 0.09375,
      "grad_norm": 0.9684135913848877,
      "learning_rate": 4.68e-07,
      "loss": 0.0652,
      "num_tokens": 354708813.0,
      "reward": 0.39453125,
      "reward_std": 0.37343472242355347,
      "rewards/simpleverify_reward/mean": 0.39453125,
      "rewards/simpleverify_reward/std": 0.4892277717590332,
      "step": 267,
      "tools/generated_tokens": 1402.244140625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.34765625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2001.0,
      "completions/mean_length": 1332.251953125,
      "completions/mean_terminated_length": 950.805419921875,
      "completions/min_length": 195.0,
      "completions/min_terminated_length": 195.0,
      "epoch": 0.19020581973030518,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.6549555659294128,
      "learning_rate": 4.66e-07,
      "loss": 0.0467,
      "num_tokens": 355888322.0,
      "reward": 0.439453125,
      "reward_std": 0.2617330551147461,
      "rewards/simpleverify_reward/mean": 0.439453125,
      "rewards/simpleverify_reward/std": 0.49680593609809875,
      "step": 268,
      "tools/generated_tokens": 1341.060546875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.01171875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.251953125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2035.0,
      "completions/mean_length": 1267.0234375,
      "completions/mean_terminated_length": 1003.9791259765625,
      "completions/min_length": 197.0,
      "completions/min_terminated_length": 197.0,
      "epoch": 0.19091554293825408,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.7348724603652954,
      "learning_rate": 4.64e-07,
      "loss": 0.0489,
      "num_tokens": 357024062.0,
      "reward": 0.46484375,
      "reward_std": 0.34802281856536865,
      "rewards/simpleverify_reward/mean": 0.46484375,
      "rewards/simpleverify_reward/std": 0.49925029277801514,
      "step": 269,
      "tools/generated_tokens": 1267.130859375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.228515625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2036.0,
      "completions/mean_length": 1140.083984375,
      "completions/mean_terminated_length": 873.69873046875,
      "completions/min_length": 1.0,
      "completions/min_terminated_length": 1.0,
      "epoch": 0.19162526614620298,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 13.841625213623047,
      "learning_rate": 4.62e-07,
      "loss": 0.0604,
      "num_tokens": 358103133.0,
      "reward": 0.52734375,
      "reward_std": 0.36365818977355957,
      "rewards/simpleverify_reward/mean": 0.52734375,
      "rewards/simpleverify_reward/std": 0.49974003434181213,
      "step": 270,
      "tools/generated_tokens": 1139.865234375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.013671875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.240234375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1246.130859375,
      "completions/mean_terminated_length": 992.5835571289062,
      "completions/min_length": 4.0,
      "completions/min_terminated_length": 4.0,
      "epoch": 0.1923349893541519,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 1.4622390270233154,
      "learning_rate": 4.6e-07,
      "loss": 0.0446,
      "num_tokens": 359227269.0,
      "reward": 0.423828125,
      "reward_std": 0.3422025144100189,
      "rewards/simpleverify_reward/mean": 0.423828125,
      "rewards/simpleverify_reward/std": 0.4946470856666565,
      "step": 271,
      "tools/generated_tokens": 1245.228515625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.36328125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1430.390625,
      "completions/mean_terminated_length": 1078.01220703125,
      "completions/min_length": 351.0,
      "completions/min_terminated_length": 351.0,
      "epoch": 0.1930447125621008,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 0.5269935727119446,
      "learning_rate": 4.58e-07,
      "loss": 0.0304,
      "num_tokens": 360447141.0,
      "reward": 0.36328125,
      "reward_std": 0.24897731840610504,
      "rewards/simpleverify_reward/mean": 0.36328125,
      "rewards/simpleverify_reward/std": 0.4814152419567108,
      "step": 272,
      "tools/generated_tokens": 1431.31640625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.255859375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2036.0,
      "completions/mean_length": 1157.244140625,
      "completions/mean_terminated_length": 850.9737548828125,
      "completions/min_length": 173.0,
      "completions/min_terminated_length": 173.0,
      "epoch": 0.1937544357700497,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.7677679657936096,
      "learning_rate": 4.56e-07,
      "loss": 0.0327,
      "num_tokens": 361532200.0,
      "reward": 0.349609375,
      "reward_std": 0.2921416163444519,
      "rewards/simpleverify_reward/mean": 0.349609375,
      "rewards/simpleverify_reward/std": 0.47731292247772217,
      "step": 273,
      "tools/generated_tokens": 1162.681640625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.2421875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1188.013671875,
      "completions/mean_terminated_length": 913.1726684570312,
      "completions/min_length": 198.0,
      "completions/min_terminated_length": 198.0,
      "epoch": 0.19446415897799857,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.6195986270904541,
      "learning_rate": 4.54e-07,
      "loss": 0.0201,
      "num_tokens": 362630015.0,
      "reward": 0.451171875,
      "reward_std": 0.28672775626182556,
      "rewards/simpleverify_reward/mean": 0.451171875,
      "rewards/simpleverify_reward/std": 0.498096764087677,
      "step": 274,
      "tools/generated_tokens": 1188.05859375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.25,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2036.0,
      "completions/mean_length": 1218.134765625,
      "completions/mean_terminated_length": 941.5130615234375,
      "completions/min_length": 202.0,
      "completions/min_terminated_length": 202.0,
      "epoch": 0.19517388218594747,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.6688512563705444,
      "learning_rate": 4.5199999999999997e-07,
      "loss": 0.0235,
      "num_tokens": 363744707.0,
      "reward": 0.396484375,
      "reward_std": 0.312208354473114,
      "rewards/simpleverify_reward/mean": 0.396484375,
      "rewards/simpleverify_reward/std": 0.4896455705165863,
      "step": 275,
      "tools/generated_tokens": 1222.87890625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.01171875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.3203125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2040.0,
      "completions/mean_length": 1389.150390625,
      "completions/mean_terminated_length": 1078.6580810546875,
      "completions/min_length": 244.0,
      "completions/min_terminated_length": 244.0,
      "epoch": 0.19588360539389638,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.5727658867835999,
      "learning_rate": 4.5e-07,
      "loss": 0.0451,
      "num_tokens": 364954714.0,
      "reward": 0.359375,
      "reward_std": 0.29986441135406494,
      "rewards/simpleverify_reward/mean": 0.359375,
      "rewards/simpleverify_reward/std": 0.48028653860092163,
      "step": 276,
      "tools/generated_tokens": 1394.087890625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.328125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2025.0,
      "completions/mean_length": 1232.40234375,
      "completions/mean_terminated_length": 834.0872192382812,
      "completions/min_length": 210.0,
      "completions/min_terminated_length": 210.0,
      "epoch": 0.19659332860184528,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 0.5912299156188965,
      "learning_rate": 4.48e-07,
      "loss": 0.0406,
      "num_tokens": 366072056.0,
      "reward": 0.380859375,
      "reward_std": 0.24972200393676758,
      "rewards/simpleverify_reward/mean": 0.380859375,
      "rewards/simpleverify_reward/std": 0.48607301712036133,
      "step": 277,
      "tools/generated_tokens": 1232.451171875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.34375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1314.33984375,
      "completions/mean_terminated_length": 930.0416870117188,
      "completions/min_length": 87.0,
      "completions/min_terminated_length": 87.0,
      "epoch": 0.19730305180979418,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.661057710647583,
      "learning_rate": 4.46e-07,
      "loss": 0.0289,
      "num_tokens": 367232102.0,
      "reward": 0.35546875,
      "reward_std": 0.31484484672546387,
      "rewards/simpleverify_reward/mean": 0.35546875,
      "rewards/simpleverify_reward/std": 0.47912323474884033,
      "step": 278,
      "tools/generated_tokens": 1314.392578125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.287109375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1272.978515625,
      "completions/mean_terminated_length": 960.8466186523438,
      "completions/min_length": 196.0,
      "completions/min_terminated_length": 196.0,
      "epoch": 0.1980127750177431,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.6543398499488831,
      "learning_rate": 4.44e-07,
      "loss": 0.0003,
      "num_tokens": 368381171.0,
      "reward": 0.455078125,
      "reward_std": 0.30583643913269043,
      "rewards/simpleverify_reward/mean": 0.455078125,
      "rewards/simpleverify_reward/std": 0.4984649419784546,
      "step": 279,
      "tools/generated_tokens": 1277.349609375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0078125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.33203125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1329.32421875,
      "completions/mean_terminated_length": 972.0877075195312,
      "completions/min_length": 246.0,
      "completions/min_terminated_length": 246.0,
      "epoch": 0.198722498225692,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.597754180431366,
      "learning_rate": 4.4199999999999996e-07,
      "loss": 0.0452,
      "num_tokens": 369545029.0,
      "reward": 0.4375,
      "reward_std": 0.27106988430023193,
      "rewards/simpleverify_reward/mean": 0.4375,
      "rewards/simpleverify_reward/std": 0.49656352400779724,
      "step": 280,
      "tools/generated_tokens": 1330.06640625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.41796875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2035.0,
      "completions/mean_length": 1498.76171875,
      "completions/mean_terminated_length": 1104.34228515625,
      "completions/min_length": 297.0,
      "completions/min_terminated_length": 297.0,
      "epoch": 0.1994322214336409,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.5574524998664856,
      "learning_rate": 4.3999999999999997e-07,
      "loss": 0.041,
      "num_tokens": 370801634.0,
      "reward": 0.3359375,
      "reward_std": 0.327461302280426,
      "rewards/simpleverify_reward/mean": 0.3359375,
      "rewards/simpleverify_reward/std": 0.4727790653705597,
      "step": 281,
      "tools/generated_tokens": 1499.76171875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.3125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2030.0,
      "completions/mean_length": 1391.119140625,
      "completions/mean_terminated_length": 1092.5369873046875,
      "completions/min_length": 187.0,
      "completions/min_terminated_length": 187.0,
      "epoch": 0.20014194464158977,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.5833698511123657,
      "learning_rate": 4.38e-07,
      "loss": 0.0596,
      "num_tokens": 372008166.0,
      "reward": 0.453125,
      "reward_std": 0.2840961813926697,
      "rewards/simpleverify_reward/mean": 0.453125,
      "rewards/simpleverify_reward/std": 0.4982847273349762,
      "step": 282,
      "tools/generated_tokens": 1395.861328125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.013671875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.166015625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2041.0,
      "completions/mean_length": 1074.638671875,
      "completions/mean_terminated_length": 880.878173828125,
      "completions/min_length": 61.0,
      "completions/min_terminated_length": 61.0,
      "epoch": 0.20085166784953867,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.7128947973251343,
      "learning_rate": 4.36e-07,
      "loss": 0.0367,
      "num_tokens": 373039134.0,
      "reward": 0.53125,
      "reward_std": 0.34224194288253784,
      "rewards/simpleverify_reward/mean": 0.53125,
      "rewards/simpleverify_reward/std": 0.4995105266571045,
      "step": 283,
      "tools/generated_tokens": 1081.89453125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.009765625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.333984375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2029.0,
      "completions/mean_length": 1369.69921875,
      "completions/mean_terminated_length": 1029.55419921875,
      "completions/min_length": 244.0,
      "completions/min_terminated_length": 244.0,
      "epoch": 0.20156139105748758,
      "frac_reward_zero_std": 0.125,
      "grad_norm": 0.6266929507255554,
      "learning_rate": 4.34e-07,
      "loss": 0.0577,
      "num_tokens": 374226788.0,
      "reward": 0.388671875,
      "reward_std": 0.37397414445877075,
      "rewards/simpleverify_reward/mean": 0.388671875,
      "rewards/simpleverify_reward/std": 0.4879252314567566,
      "step": 284,
      "tools/generated_tokens": 1369.697265625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.26171875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2033.0,
      "completions/mean_length": 1296.958984375,
      "completions/mean_terminated_length": 1030.7169189453125,
      "completions/min_length": 1.0,
      "completions/min_terminated_length": 1.0,
      "epoch": 0.20227111426543648,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.6627830266952515,
      "learning_rate": 4.3199999999999995e-07,
      "loss": 0.0484,
      "num_tokens": 375378687.0,
      "reward": 0.341796875,
      "reward_std": 0.36087656021118164,
      "rewards/simpleverify_reward/mean": 0.341796875,
      "rewards/simpleverify_reward/std": 0.4747757613658905,
      "step": 285,
      "tools/generated_tokens": 1297.009765625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.423828125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2038.0,
      "completions/mean_length": 1411.63671875,
      "completions/mean_terminated_length": 943.5321655273438,
      "completions/min_length": 206.0,
      "completions/min_terminated_length": 206.0,
      "epoch": 0.20298083747338538,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.5783690214157104,
      "learning_rate": 4.2999999999999996e-07,
      "loss": 0.0361,
      "num_tokens": 376584694.0,
      "reward": 0.28515625,
      "reward_std": 0.30192285776138306,
      "rewards/simpleverify_reward/mean": 0.28515625,
      "rewards/simpleverify_reward/std": 0.45193037390708923,
      "step": 286,
      "tools/generated_tokens": 1413.421875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.240234375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2034.0,
      "completions/mean_length": 1204.36328125,
      "completions/mean_terminated_length": 937.6092529296875,
      "completions/min_length": 265.0,
      "completions/min_terminated_length": 265.0,
      "epoch": 0.2036905606813343,
      "frac_reward_zero_std": 0.125,
      "grad_norm": 0.7862333655357361,
      "learning_rate": 4.2799999999999997e-07,
      "loss": 0.0923,
      "num_tokens": 377683920.0,
      "reward": 0.462890625,
      "reward_std": 0.3667975068092346,
      "rewards/simpleverify_reward/mean": 0.462890625,
      "rewards/simpleverify_reward/std": 0.4991086423397064,
      "step": 287,
      "tools/generated_tokens": 1204.41796875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.341796875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2009.0,
      "completions/mean_length": 1317.615234375,
      "completions/mean_terminated_length": 938.3353271484375,
      "completions/min_length": 145.0,
      "completions/min_terminated_length": 145.0,
      "epoch": 0.2044002838892832,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.5510988235473633,
      "learning_rate": 4.26e-07,
      "loss": 0.0224,
      "num_tokens": 378842288.0,
      "reward": 0.357421875,
      "reward_std": 0.2860950231552124,
      "rewards/simpleverify_reward/mean": 0.357421875,
      "rewards/simpleverify_reward/std": 0.4797092080116272,
      "step": 288,
      "tools/generated_tokens": 1320.65625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.251953125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2024.0,
      "completions/mean_length": 1274.6796875,
      "completions/mean_terminated_length": 1014.214111328125,
      "completions/min_length": 263.0,
      "completions/min_terminated_length": 263.0,
      "epoch": 0.20511000709723207,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.6020498871803284,
      "learning_rate": 4.24e-07,
      "loss": 0.0479,
      "num_tokens": 379985436.0,
      "reward": 0.501953125,
      "reward_std": 0.29777711629867554,
      "rewards/simpleverify_reward/mean": 0.501953125,
      "rewards/simpleverify_reward/std": 0.5004851818084717,
      "step": 289,
      "tools/generated_tokens": 1274.72265625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.3359375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1328.0859375,
      "completions/mean_terminated_length": 963.8941650390625,
      "completions/min_length": 171.0,
      "completions/min_terminated_length": 171.0,
      "epoch": 0.20581973030518097,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.5988476276397705,
      "learning_rate": 4.2199999999999994e-07,
      "loss": 0.0375,
      "num_tokens": 381155320.0,
      "reward": 0.34375,
      "reward_std": 0.2836172878742218,
      "rewards/simpleverify_reward/mean": 0.34375,
      "rewards/simpleverify_reward/std": 0.4754233956336975,
      "step": 290,
      "tools/generated_tokens": 1328.1796875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.306640625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1304.603515625,
      "completions/mean_terminated_length": 975.833740234375,
      "completions/min_length": 336.0,
      "completions/min_terminated_length": 336.0,
      "epoch": 0.20652945351312987,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.6669707298278809,
      "learning_rate": 4.1999999999999995e-07,
      "loss": 0.0832,
      "num_tokens": 382309597.0,
      "reward": 0.3828125,
      "reward_std": 0.29345768690109253,
      "rewards/simpleverify_reward/mean": 0.3828125,
      "rewards/simpleverify_reward/std": 0.486548513174057,
      "step": 291,
      "tools/generated_tokens": 1304.658203125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.326171875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1432.986328125,
      "completions/mean_terminated_length": 1135.2840576171875,
      "completions/min_length": 285.0,
      "completions/min_terminated_length": 285.0,
      "epoch": 0.20723917672107878,
      "frac_reward_zero_std": 0.125,
      "grad_norm": 0.6444351673126221,
      "learning_rate": 4.1799999999999996e-07,
      "loss": 0.0616,
      "num_tokens": 383533156.0,
      "reward": 0.3359375,
      "reward_std": 0.3674302101135254,
      "rewards/simpleverify_reward/mean": 0.3359375,
      "rewards/simpleverify_reward/std": 0.4727790653705597,
      "step": 292,
      "tools/generated_tokens": 1434.236328125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.234375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2024.0,
      "completions/mean_length": 1180.296875,
      "completions/mean_terminated_length": 914.6785278320312,
      "completions/min_length": 257.0,
      "completions/min_terminated_length": 257.0,
      "epoch": 0.20794889992902768,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.6060939431190491,
      "learning_rate": 4.1599999999999997e-07,
      "loss": 0.0659,
      "num_tokens": 384624668.0,
      "reward": 0.443359375,
      "reward_std": 0.33243972063064575,
      "rewards/simpleverify_reward/mean": 0.443359375,
      "rewards/simpleverify_reward/std": 0.49726733565330505,
      "step": 293,
      "tools/generated_tokens": 1180.330078125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.2734375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1175.228515625,
      "completions/mean_terminated_length": 846.76611328125,
      "completions/min_length": 248.0,
      "completions/min_terminated_length": 248.0,
      "epoch": 0.20865862313697658,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.624791145324707,
      "learning_rate": 4.14e-07,
      "loss": 0.0311,
      "num_tokens": 385713941.0,
      "reward": 0.341796875,
      "reward_std": 0.31254255771636963,
      "rewards/simpleverify_reward/mean": 0.341796875,
      "rewards/simpleverify_reward/std": 0.4747757613658905,
      "step": 294,
      "tools/generated_tokens": 1179.134765625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.28125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2033.0,
      "completions/mean_length": 1248.271484375,
      "completions/mean_terminated_length": 935.334228515625,
      "completions/min_length": 155.0,
      "completions/min_terminated_length": 155.0,
      "epoch": 0.2093683463449255,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.8347308039665222,
      "learning_rate": 4.12e-07,
      "loss": 0.0596,
      "num_tokens": 386839952.0,
      "reward": 0.498046875,
      "reward_std": 0.33648228645324707,
      "rewards/simpleverify_reward/mean": 0.498046875,
      "rewards/simpleverify_reward/std": 0.5004851818084717,
      "step": 295,
      "tools/generated_tokens": 1248.330078125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.3046875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1303.24609375,
      "completions/mean_terminated_length": 976.9185791015625,
      "completions/min_length": 82.0,
      "completions/min_terminated_length": 82.0,
      "epoch": 0.2100780695528744,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 34.90583038330078,
      "learning_rate": 4.0999999999999994e-07,
      "loss": 0.0534,
      "num_tokens": 387998331.0,
      "reward": 0.384765625,
      "reward_std": 0.28232425451278687,
      "rewards/simpleverify_reward/mean": 0.384765625,
      "rewards/simpleverify_reward/std": 0.4870156943798065,
      "step": 296,
      "tools/generated_tokens": 1303.625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.009765625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.3515625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1359.70703125,
      "completions/mean_terminated_length": 986.5361328125,
      "completions/min_length": 127.0,
      "completions/min_terminated_length": 127.0,
      "epoch": 0.21078779276082327,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.7117847204208374,
      "learning_rate": 4.0799999999999995e-07,
      "loss": 0.0597,
      "num_tokens": 389180890.0,
      "reward": 0.443359375,
      "reward_std": 0.31109943985939026,
      "rewards/simpleverify_reward/mean": 0.443359375,
      "rewards/simpleverify_reward/std": 0.49726733565330505,
      "step": 297,
      "tools/generated_tokens": 1361.970703125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.271484375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2030.0,
      "completions/mean_length": 1213.560546875,
      "completions/mean_terminated_length": 902.603271484375,
      "completions/min_length": 171.0,
      "completions/min_terminated_length": 171.0,
      "epoch": 0.21149751596877217,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.7926952838897705,
      "learning_rate": 4.06e-07,
      "loss": 0.0367,
      "num_tokens": 390285938.0,
      "reward": 0.359375,
      "reward_std": 0.2875227928161621,
      "rewards/simpleverify_reward/mean": 0.359375,
      "rewards/simpleverify_reward/std": 0.48028653860092163,
      "step": 298,
      "tools/generated_tokens": 1214.44140625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.24609375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1201.330078125,
      "completions/mean_terminated_length": 924.9559326171875,
      "completions/min_length": 213.0,
      "completions/min_terminated_length": 213.0,
      "epoch": 0.21220723917672107,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.743270218372345,
      "learning_rate": 4.04e-07,
      "loss": 0.0418,
      "num_tokens": 391391460.0,
      "reward": 0.505859375,
      "reward_std": 0.3214261531829834,
      "rewards/simpleverify_reward/mean": 0.505859375,
      "rewards/simpleverify_reward/std": 0.5004546642303467,
      "step": 299,
      "tools/generated_tokens": 1203.845703125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.255859375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1255.779296875,
      "completions/mean_terminated_length": 983.388427734375,
      "completions/min_length": 218.0,
      "completions/min_terminated_length": 218.0,
      "epoch": 0.21291696238466998,
      "frac_reward_zero_std": 0.40625,
      "grad_norm": 0.5910018682479858,
      "learning_rate": 4.02e-07,
      "loss": 0.0222,
      "num_tokens": 392520212.0,
      "reward": 0.341796875,
      "reward_std": 0.24363473057746887,
      "rewards/simpleverify_reward/mean": 0.341796875,
      "rewards/simpleverify_reward/std": 0.4747757613658905,
      "step": 300,
      "tools/generated_tokens": 1260.98046875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.470703125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2041.0,
      "completions/mean_length": 1459.244140625,
      "completions/mean_terminated_length": 935.6642456054688,
      "completions/min_length": 299.0,
      "completions/min_terminated_length": 299.0,
      "epoch": 0.21362668559261888,
      "frac_reward_zero_std": 0.4375,
      "grad_norm": 0.4871727228164673,
      "learning_rate": 4e-07,
      "loss": 0.0313,
      "num_tokens": 393754033.0,
      "reward": 0.3046875,
      "reward_std": 0.21711531281471252,
      "rewards/simpleverify_reward/mean": 0.3046875,
      "rewards/simpleverify_reward/std": 0.4607250988483429,
      "step": 301,
      "tools/generated_tokens": 1459.2734375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.279296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2029.0,
      "completions/mean_length": 1230.40625,
      "completions/mean_terminated_length": 913.5609741210938,
      "completions/min_length": 164.0,
      "completions/min_terminated_length": 164.0,
      "epoch": 0.21433640880056778,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.6048601269721985,
      "learning_rate": 3.98e-07,
      "loss": 0.0493,
      "num_tokens": 394878284.0,
      "reward": 0.431640625,
      "reward_std": 0.30478525161743164,
      "rewards/simpleverify_reward/mean": 0.431640625,
      "rewards/simpleverify_reward/std": 0.4957893490791321,
      "step": 302,
      "tools/generated_tokens": 1231.373046875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.330078125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1341.013671875,
      "completions/mean_terminated_length": 992.6735229492188,
      "completions/min_length": 245.0,
      "completions/min_terminated_length": 245.0,
      "epoch": 0.2150461320085167,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.6917058229446411,
      "learning_rate": 3.96e-07,
      "loss": 0.0701,
      "num_tokens": 396045263.0,
      "reward": 0.466796875,
      "reward_std": 0.3610159754753113,
      "rewards/simpleverify_reward/mean": 0.466796875,
      "rewards/simpleverify_reward/std": 0.4993842542171478,
      "step": 303,
      "tools/generated_tokens": 1341.845703125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.259765625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2036.0,
      "completions/mean_length": 1285.109375,
      "completions/mean_terminated_length": 1017.3931884765625,
      "completions/min_length": 116.0,
      "completions/min_terminated_length": 116.0,
      "epoch": 0.2157558552164656,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.6624124050140381,
      "learning_rate": 3.94e-07,
      "loss": 0.0482,
      "num_tokens": 397187895.0,
      "reward": 0.44140625,
      "reward_std": 0.30899518728256226,
      "rewards/simpleverify_reward/mean": 0.44140625,
      "rewards/simpleverify_reward/std": 0.4970405399799347,
      "step": 304,
      "tools/generated_tokens": 1285.234375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.353515625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2040.0,
      "completions/mean_length": 1340.916015625,
      "completions/mean_terminated_length": 954.2628173828125,
      "completions/min_length": 175.0,
      "completions/min_terminated_length": 175.0,
      "epoch": 0.21646557842441447,
      "frac_reward_zero_std": 0.40625,
      "grad_norm": 0.5474103093147278,
      "learning_rate": 3.92e-07,
      "loss": 0.0162,
      "num_tokens": 398357362.0,
      "reward": 0.306640625,
      "reward_std": 0.2384233921766281,
      "rewards/simpleverify_reward/mean": 0.306640625,
      "rewards/simpleverify_reward/std": 0.4615498185157776,
      "step": 305,
      "tools/generated_tokens": 1342.58203125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.3046875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2025.0,
      "completions/mean_length": 1260.97265625,
      "completions/mean_terminated_length": 916.0955200195312,
      "completions/min_length": 141.0,
      "completions/min_terminated_length": 141.0,
      "epoch": 0.21717530163236337,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.6779371500015259,
      "learning_rate": 3.8999999999999997e-07,
      "loss": 0.0434,
      "num_tokens": 399493236.0,
      "reward": 0.44140625,
      "reward_std": 0.3262137174606323,
      "rewards/simpleverify_reward/mean": 0.44140625,
      "rewards/simpleverify_reward/std": 0.4970405399799347,
      "step": 306,
      "tools/generated_tokens": 1261.052734375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.32421875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2034.0,
      "completions/mean_length": 1231.064453125,
      "completions/mean_terminated_length": 839.124267578125,
      "completions/min_length": 196.0,
      "completions/min_terminated_length": 196.0,
      "epoch": 0.21788502484031227,
      "frac_reward_zero_std": 0.46875,
      "grad_norm": 0.5752106308937073,
      "learning_rate": 3.88e-07,
      "loss": 0.0427,
      "num_tokens": 400620565.0,
      "reward": 0.322265625,
      "reward_std": 0.21192461252212524,
      "rewards/simpleverify_reward/mean": 0.322265625,
      "rewards/simpleverify_reward/std": 0.46780112385749817,
      "step": 307,
      "tools/generated_tokens": 1231.130859375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.19140625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2036.0,
      "completions/mean_length": 1090.302734375,
      "completions/mean_terminated_length": 863.6014404296875,
      "completions/min_length": 189.0,
      "completions/min_terminated_length": 189.0,
      "epoch": 0.21859474804826118,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 1.8041062355041504,
      "learning_rate": 3.86e-07,
      "loss": 0.0537,
      "num_tokens": 401671408.0,
      "reward": 0.39453125,
      "reward_std": 0.3237219750881195,
      "rewards/simpleverify_reward/mean": 0.39453125,
      "rewards/simpleverify_reward/std": 0.4892277717590332,
      "step": 308,
      "tools/generated_tokens": 1097.00390625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0078125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.001953125
    },
    {
      "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": 0.251953125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2037.0,
      "completions/mean_length": 1211.4453125,
      "completions/mean_terminated_length": 929.6814575195312,
      "completions/min_length": 152.0,
      "completions/min_terminated_length": 152.0,
      "epoch": 0.21930447125621008,
      "frac_reward_zero_std": 0.125,
      "grad_norm": 19.02752113342285,
      "learning_rate": 3.84e-07,
      "loss": 0.0925,
      "num_tokens": 402791825.0,
      "reward": 0.462890625,
      "reward_std": 0.34798216819763184,
      "rewards/simpleverify_reward/mean": 0.462890625,
      "rewards/simpleverify_reward/std": 0.4991086423397064,
      "step": 309,
      "tools/generated_tokens": 1211.208984375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.015625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.33203125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1328.375,
      "completions/mean_terminated_length": 970.6666870117188,
      "completions/min_length": 166.0,
      "completions/min_terminated_length": 166.0,
      "epoch": 0.22001419446415899,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.6793827414512634,
      "learning_rate": 3.82e-07,
      "loss": 0.0266,
      "num_tokens": 403965658.0,
      "reward": 0.396484375,
      "reward_std": 0.32008957862854004,
      "rewards/simpleverify_reward/mean": 0.396484375,
      "rewards/simpleverify_reward/std": 0.4896455705165863,
      "step": 310,
      "tools/generated_tokens": 1331.25390625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.3046875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1245.361328125,
      "completions/mean_terminated_length": 893.6432495117188,
      "completions/min_length": 207.0,
      "completions/min_terminated_length": 207.0,
      "epoch": 0.2207239176721079,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.6477154493331909,
      "learning_rate": 3.7999999999999996e-07,
      "loss": 0.034,
      "num_tokens": 405097879.0,
      "reward": 0.400390625,
      "reward_std": 0.32350480556488037,
      "rewards/simpleverify_reward/mean": 0.400390625,
      "rewards/simpleverify_reward/std": 0.4904567301273346,
      "step": 311,
      "tools/generated_tokens": 1251.275390625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.423828125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2037.0,
      "completions/mean_length": 1446.564453125,
      "completions/mean_terminated_length": 1004.1525268554688,
      "completions/min_length": 167.0,
      "completions/min_terminated_length": 167.0,
      "epoch": 0.22143364088005676,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.591532289981842,
      "learning_rate": 3.7799999999999997e-07,
      "loss": 0.0655,
      "num_tokens": 406332636.0,
      "reward": 0.388671875,
      "reward_std": 0.26711997389793396,
      "rewards/simpleverify_reward/mean": 0.388671875,
      "rewards/simpleverify_reward/std": 0.4879252314567566,
      "step": 312,
      "tools/generated_tokens": 1447.8515625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.19921875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1084.826171875,
      "completions/mean_terminated_length": 845.2073364257812,
      "completions/min_length": 225.0,
      "completions/min_terminated_length": 225.0,
      "epoch": 0.22214336408800567,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.8163130283355713,
      "learning_rate": 3.76e-07,
      "loss": 0.017,
      "num_tokens": 407374771.0,
      "reward": 0.384765625,
      "reward_std": 0.3182097375392914,
      "rewards/simpleverify_reward/mean": 0.384765625,
      "rewards/simpleverify_reward/std": 0.4870156943798065,
      "step": 313,
      "tools/generated_tokens": 1084.900390625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.34375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2041.0,
      "completions/mean_length": 1258.46484375,
      "completions/mean_terminated_length": 844.8988037109375,
      "completions/min_length": 157.0,
      "completions/min_terminated_length": 157.0,
      "epoch": 0.22285308729595457,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 2.9996449947357178,
      "learning_rate": 3.74e-07,
      "loss": 0.0131,
      "num_tokens": 408512537.0,
      "reward": 0.35546875,
      "reward_std": 0.19506019353866577,
      "rewards/simpleverify_reward/mean": 0.35546875,
      "rewards/simpleverify_reward/std": 0.47912323474884033,
      "step": 314,
      "tools/generated_tokens": 1261.451171875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.009765625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.275390625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2038.0,
      "completions/mean_length": 1240.69140625,
      "completions/mean_terminated_length": 933.87060546875,
      "completions/min_length": 163.0,
      "completions/min_terminated_length": 163.0,
      "epoch": 0.22356281050390348,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.5609243512153625,
      "learning_rate": 3.72e-07,
      "loss": 0.018,
      "num_tokens": 409632955.0,
      "reward": 0.404296875,
      "reward_std": 0.3010219931602478,
      "rewards/simpleverify_reward/mean": 0.404296875,
      "rewards/simpleverify_reward/std": 0.4912354052066803,
      "step": 315,
      "tools/generated_tokens": 1240.72265625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.240234375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1249.294921875,
      "completions/mean_terminated_length": 996.748046875,
      "completions/min_length": 207.0,
      "completions/min_terminated_length": 207.0,
      "epoch": 0.22427253371185238,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.7543084621429443,
      "learning_rate": 3.7e-07,
      "loss": 0.0732,
      "num_tokens": 410765971.0,
      "reward": 0.525390625,
      "reward_std": 0.3165287673473358,
      "rewards/simpleverify_reward/mean": 0.525390625,
      "rewards/simpleverify_reward/std": 0.4998432695865631,
      "step": 316,
      "tools/generated_tokens": 1255.857421875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.216796875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2036.0,
      "completions/mean_length": 1154.25,
      "completions/mean_terminated_length": 906.8529052734375,
      "completions/min_length": 170.0,
      "completions/min_terminated_length": 170.0,
      "epoch": 0.22498225691980128,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.7145474553108215,
      "learning_rate": 3.6799999999999996e-07,
      "loss": 0.0562,
      "num_tokens": 411845651.0,
      "reward": 0.482421875,
      "reward_std": 0.3194028437137604,
      "rewards/simpleverify_reward/mean": 0.482421875,
      "rewards/simpleverify_reward/std": 0.5001795887947083,
      "step": 317,
      "tools/generated_tokens": 1154.373046875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.3515625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1425.26171875,
      "completions/mean_terminated_length": 1087.6324462890625,
      "completions/min_length": 190.0,
      "completions/min_terminated_length": 190.0,
      "epoch": 0.22569198012775019,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.6387969851493835,
      "learning_rate": 3.6599999999999997e-07,
      "loss": 0.0626,
      "num_tokens": 413062089.0,
      "reward": 0.38671875,
      "reward_std": 0.3609073758125305,
      "rewards/simpleverify_reward/mean": 0.38671875,
      "rewards/simpleverify_reward/std": 0.48747459053993225,
      "step": 318,
      "tools/generated_tokens": 1425.359375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.259765625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1238.384765625,
      "completions/mean_terminated_length": 954.2717895507812,
      "completions/min_length": 179.0,
      "completions/min_terminated_length": 179.0,
      "epoch": 0.2264017033356991,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.627472460269928,
      "learning_rate": 3.64e-07,
      "loss": 0.0251,
      "num_tokens": 414183566.0,
      "reward": 0.44921875,
      "reward_std": 0.33357226848602295,
      "rewards/simpleverify_reward/mean": 0.44921875,
      "rewards/simpleverify_reward/std": 0.497901052236557,
      "step": 319,
      "tools/generated_tokens": 1238.44921875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.24609375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1187.5078125,
      "completions/mean_terminated_length": 906.6217651367188,
      "completions/min_length": 204.0,
      "completions/min_terminated_length": 204.0,
      "epoch": 0.22711142654364797,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.7704684138298035,
      "learning_rate": 3.62e-07,
      "loss": 0.0534,
      "num_tokens": 415274386.0,
      "reward": 0.453125,
      "reward_std": 0.30459073185920715,
      "rewards/simpleverify_reward/mean": 0.453125,
      "rewards/simpleverify_reward/std": 0.4982847273349762,
      "step": 320,
      "tools/generated_tokens": 1187.5859375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.197265625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1169.9609375,
      "completions/mean_terminated_length": 954.1897583007812,
      "completions/min_length": 224.0,
      "completions/min_terminated_length": 224.0,
      "epoch": 0.22782114975159687,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.6537746787071228,
      "learning_rate": 3.6e-07,
      "loss": 0.0498,
      "num_tokens": 416350126.0,
      "reward": 0.466796875,
      "reward_std": 0.28875067830085754,
      "rewards/simpleverify_reward/mean": 0.466796875,
      "rewards/simpleverify_reward/std": 0.4993842542171478,
      "step": 321,
      "tools/generated_tokens": 1170.0703125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.404296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2040.0,
      "completions/mean_length": 1511.0546875,
      "completions/mean_terminated_length": 1146.6361083984375,
      "completions/min_length": 294.0,
      "completions/min_terminated_length": 294.0,
      "epoch": 0.22853087295954577,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.6450453996658325,
      "learning_rate": 3.5799999999999995e-07,
      "loss": 0.035,
      "num_tokens": 417619907.0,
      "reward": 0.30859375,
      "reward_std": 0.2801062762737274,
      "rewards/simpleverify_reward/mean": 0.30859375,
      "rewards/simpleverify_reward/std": 0.4623647928237915,
      "step": 322,
      "tools/generated_tokens": 1516.533203125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0078125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.345703125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2034.0,
      "completions/mean_length": 1320.93359375,
      "completions/mean_terminated_length": 936.7821044921875,
      "completions/min_length": 222.0,
      "completions/min_terminated_length": 222.0,
      "epoch": 0.22924059616749468,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.5721625685691833,
      "learning_rate": 3.5599999999999996e-07,
      "loss": 0.0611,
      "num_tokens": 418785681.0,
      "reward": 0.310546875,
      "reward_std": 0.2801467776298523,
      "rewards/simpleverify_reward/mean": 0.310546875,
      "rewards/simpleverify_reward/std": 0.46317005157470703,
      "step": 323,
      "tools/generated_tokens": 1321.0078125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.345703125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2034.0,
      "completions/mean_length": 1335.587890625,
      "completions/mean_terminated_length": 959.1791381835938,
      "completions/min_length": 250.0,
      "completions/min_terminated_length": 250.0,
      "epoch": 0.22995031937544358,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.5795235633850098,
      "learning_rate": 3.5399999999999997e-07,
      "loss": 0.049,
      "num_tokens": 419959566.0,
      "reward": 0.392578125,
      "reward_std": 0.32217440009117126,
      "rewards/simpleverify_reward/mean": 0.392578125,
      "rewards/simpleverify_reward/std": 0.4888018071651459,
      "step": 324,
      "tools/generated_tokens": 1335.64453125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.283203125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1349.623046875,
      "completions/mean_terminated_length": 1073.697509765625,
      "completions/min_length": 228.0,
      "completions/min_terminated_length": 228.0,
      "epoch": 0.23066004258339248,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.731829822063446,
      "learning_rate": 3.52e-07,
      "loss": 0.0742,
      "num_tokens": 421134538.0,
      "reward": 0.357421875,
      "reward_std": 0.3590441644191742,
      "rewards/simpleverify_reward/mean": 0.357421875,
      "rewards/simpleverify_reward/std": 0.4797092080116272,
      "step": 325,
      "tools/generated_tokens": 1350.42578125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.37109375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1435.158203125,
      "completions/mean_terminated_length": 1073.54345703125,
      "completions/min_length": 213.0,
      "completions/min_terminated_length": 213.0,
      "epoch": 0.2313697657913414,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.6450489163398743,
      "learning_rate": 3.5e-07,
      "loss": 0.0589,
      "num_tokens": 422356779.0,
      "reward": 0.326171875,
      "reward_std": 0.36344391107559204,
      "rewards/simpleverify_reward/mean": 0.326171875,
      "rewards/simpleverify_reward/std": 0.4692695140838623,
      "step": 326,
      "tools/generated_tokens": 1435.236328125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.244140625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2022.0,
      "completions/mean_length": 1103.837890625,
      "completions/mean_terminated_length": 798.8759765625,
      "completions/min_length": 184.0,
      "completions/min_terminated_length": 184.0,
      "epoch": 0.2320794889992903,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.8069353103637695,
      "learning_rate": 3.4799999999999994e-07,
      "loss": 0.0618,
      "num_tokens": 423409671.0,
      "reward": 0.5234375,
      "reward_std": 0.3126524090766907,
      "rewards/simpleverify_reward/mean": 0.5234375,
      "rewards/simpleverify_reward/std": 0.49993884563446045,
      "step": 327,
      "tools/generated_tokens": 1105.546875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.255859375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2013.0,
      "completions/mean_length": 1211.927734375,
      "completions/mean_terminated_length": 924.4592895507812,
      "completions/min_length": 232.0,
      "completions/min_terminated_length": 232.0,
      "epoch": 0.23278921220723917,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.6202053427696228,
      "learning_rate": 3.4599999999999995e-07,
      "loss": 0.0325,
      "num_tokens": 424519842.0,
      "reward": 0.40625,
      "reward_std": 0.29183927178382874,
      "rewards/simpleverify_reward/mean": 0.40625,
      "rewards/simpleverify_reward/std": 0.49161264300346375,
      "step": 328,
      "tools/generated_tokens": 1212.04296875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.302734375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1260.81640625,
      "completions/mean_terminated_length": 919.0420532226562,
      "completions/min_length": 192.0,
      "completions/min_terminated_length": 192.0,
      "epoch": 0.23349893541518807,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.7488528490066528,
      "learning_rate": 3.4399999999999996e-07,
      "loss": 0.0247,
      "num_tokens": 425653743.0,
      "reward": 0.400390625,
      "reward_std": 0.31649649143218994,
      "rewards/simpleverify_reward/mean": 0.400390625,
      "rewards/simpleverify_reward/std": 0.4904567301273346,
      "step": 329,
      "tools/generated_tokens": 1264.169921875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.40234375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2037.0,
      "completions/mean_length": 1418.716796875,
      "completions/mean_terminated_length": 995.0817260742188,
      "completions/min_length": 289.0,
      "completions/min_terminated_length": 289.0,
      "epoch": 0.23420865862313697,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.6870012879371643,
      "learning_rate": 3.42e-07,
      "loss": 0.0733,
      "num_tokens": 426864094.0,
      "reward": 0.326171875,
      "reward_std": 0.3028716444969177,
      "rewards/simpleverify_reward/mean": 0.326171875,
      "rewards/simpleverify_reward/std": 0.4692695140838623,
      "step": 330,
      "tools/generated_tokens": 1418.794921875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.4375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2040.0,
      "completions/mean_length": 1452.220703125,
      "completions/mean_terminated_length": 988.8367919921875,
      "completions/min_length": 200.0,
      "completions/min_terminated_length": 200.0,
      "epoch": 0.23491838183108588,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.6392552852630615,
      "learning_rate": 3.4000000000000003e-07,
      "loss": 0.0258,
      "num_tokens": 428108127.0,
      "reward": 0.326171875,
      "reward_std": 0.2873068153858185,
      "rewards/simpleverify_reward/mean": 0.326171875,
      "rewards/simpleverify_reward/std": 0.4692695140838623,
      "step": 331,
      "tools/generated_tokens": 1452.28515625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.291015625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1259.1484375,
      "completions/mean_terminated_length": 935.349853515625,
      "completions/min_length": 194.0,
      "completions/min_terminated_length": 194.0,
      "epoch": 0.23562810503903478,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.5846631526947021,
      "learning_rate": 3.38e-07,
      "loss": 0.0357,
      "num_tokens": 429245143.0,
      "reward": 0.390625,
      "reward_std": 0.3238213062286377,
      "rewards/simpleverify_reward/mean": 0.390625,
      "rewards/simpleverify_reward/std": 0.48836761713027954,
      "step": 332,
      "tools/generated_tokens": 1259.947265625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.3046875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2035.0,
      "completions/mean_length": 1251.27734375,
      "completions/mean_terminated_length": 902.1516723632812,
      "completions/min_length": 251.0,
      "completions/min_terminated_length": 251.0,
      "epoch": 0.23633782824698368,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.6075937747955322,
      "learning_rate": 3.36e-07,
      "loss": 0.0123,
      "num_tokens": 430386307.0,
      "reward": 0.43359375,
      "reward_std": 0.30695292353630066,
      "rewards/simpleverify_reward/mean": 0.43359375,
      "rewards/simpleverify_reward/std": 0.4960552453994751,
      "step": 333,
      "tools/generated_tokens": 1254.0546875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.244140625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1241.11328125,
      "completions/mean_terminated_length": 980.490966796875,
      "completions/min_length": 178.0,
      "completions/min_terminated_length": 178.0,
      "epoch": 0.2370475514549326,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 3.165816307067871,
      "learning_rate": 3.34e-07,
      "loss": 0.0297,
      "num_tokens": 431530817.0,
      "reward": 0.3984375,
      "reward_std": 0.31547266244888306,
      "rewards/simpleverify_reward/mean": 0.3984375,
      "rewards/simpleverify_reward/std": 0.4900552034378052,
      "step": 334,
      "tools/generated_tokens": 1262.751953125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.017578125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.349609375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2011.0,
      "completions/mean_length": 1325.138671875,
      "completions/mean_terminated_length": 936.5736083984375,
      "completions/min_length": 304.0,
      "completions/min_terminated_length": 304.0,
      "epoch": 0.23775727466288146,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.6655516624450684,
      "learning_rate": 3.32e-07,
      "loss": 0.0469,
      "num_tokens": 432706337.0,
      "reward": 0.408203125,
      "reward_std": 0.2931326627731323,
      "rewards/simpleverify_reward/mean": 0.408203125,
      "rewards/simpleverify_reward/std": 0.49198177456855774,
      "step": 335,
      "tools/generated_tokens": 1331.466796875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.013671875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.314453125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2038.0,
      "completions/mean_length": 1318.166015625,
      "completions/mean_terminated_length": 983.3988647460938,
      "completions/min_length": 143.0,
      "completions/min_terminated_length": 143.0,
      "epoch": 0.23846699787083037,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.6423631906509399,
      "learning_rate": 3.3e-07,
      "loss": 0.0374,
      "num_tokens": 433872342.0,
      "reward": 0.3984375,
      "reward_std": 0.304781973361969,
      "rewards/simpleverify_reward/mean": 0.3984375,
      "rewards/simpleverify_reward/std": 0.4900552034378052,
      "step": 336,
      "tools/generated_tokens": 1318.23046875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.326171875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2037.0,
      "completions/mean_length": 1404.7265625,
      "completions/mean_terminated_length": 1093.344970703125,
      "completions/min_length": 252.0,
      "completions/min_terminated_length": 252.0,
      "epoch": 0.23917672107877927,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.6284003853797913,
      "learning_rate": 3.28e-07,
      "loss": 0.0362,
      "num_tokens": 435074154.0,
      "reward": 0.322265625,
      "reward_std": 0.29802384972572327,
      "rewards/simpleverify_reward/mean": 0.322265625,
      "rewards/simpleverify_reward/std": 0.46780112385749817,
      "step": 337,
      "tools/generated_tokens": 1404.818359375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.36328125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1422.15234375,
      "completions/mean_terminated_length": 1065.0736083984375,
      "completions/min_length": 120.0,
      "completions/min_terminated_length": 120.0,
      "epoch": 0.23988644428672817,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.6327836513519287,
      "learning_rate": 3.26e-07,
      "loss": 0.0629,
      "num_tokens": 436295286.0,
      "reward": 0.326171875,
      "reward_std": 0.35279715061187744,
      "rewards/simpleverify_reward/mean": 0.326171875,
      "rewards/simpleverify_reward/std": 0.4692695140838623,
      "step": 338,
      "tools/generated_tokens": 1428.728515625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.009765625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.33984375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1347.775390625,
      "completions/mean_terminated_length": 987.3047485351562,
      "completions/min_length": 229.0,
      "completions/min_terminated_length": 229.0,
      "epoch": 0.24059616749467708,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.6107127666473389,
      "learning_rate": 3.24e-07,
      "loss": 0.0656,
      "num_tokens": 437468338.0,
      "reward": 0.357421875,
      "reward_std": 0.31983643770217896,
      "rewards/simpleverify_reward/mean": 0.357421875,
      "rewards/simpleverify_reward/std": 0.4797092080116272,
      "step": 339,
      "tools/generated_tokens": 1350.080078125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.3125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1301.767578125,
      "completions/mean_terminated_length": 962.571044921875,
      "completions/min_length": 268.0,
      "completions/min_terminated_length": 268.0,
      "epoch": 0.24130589070262598,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.6607086062431335,
      "learning_rate": 3.22e-07,
      "loss": 0.0367,
      "num_tokens": 438625081.0,
      "reward": 0.3828125,
      "reward_std": 0.3230574131011963,
      "rewards/simpleverify_reward/mean": 0.3828125,
      "rewards/simpleverify_reward/std": 0.486548513174057,
      "step": 340,
      "tools/generated_tokens": 1303.6953125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.263671875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2014.0,
      "completions/mean_length": 1258.255859375,
      "completions/mean_terminated_length": 975.4562377929688,
      "completions/min_length": 213.0,
      "completions/min_terminated_length": 213.0,
      "epoch": 0.24201561391057488,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.7276241779327393,
      "learning_rate": 3.2e-07,
      "loss": 0.0311,
      "num_tokens": 439751644.0,
      "reward": 0.3515625,
      "reward_std": 0.2960313558578491,
      "rewards/simpleverify_reward/mean": 0.3515625,
      "rewards/simpleverify_reward/std": 0.4779251217842102,
      "step": 341,
      "tools/generated_tokens": 1258.296875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.248046875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2039.0,
      "completions/mean_length": 1217.71484375,
      "completions/mean_terminated_length": 943.8285522460938,
      "completions/min_length": 210.0,
      "completions/min_terminated_length": 210.0,
      "epoch": 0.2427253371185238,
      "frac_reward_zero_std": 0.09375,
      "grad_norm": 0.7113949060440063,
      "learning_rate": 3.18e-07,
      "loss": 0.0616,
      "num_tokens": 440859546.0,
      "reward": 0.421875,
      "reward_std": 0.388104647397995,
      "rewards/simpleverify_reward/mean": 0.421875,
      "rewards/simpleverify_reward/std": 0.49434176087379456,
      "step": 342,
      "tools/generated_tokens": 1217.787109375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.38671875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2027.0,
      "completions/mean_length": 1359.94921875,
      "completions/mean_terminated_length": 926.0828247070312,
      "completions/min_length": 167.0,
      "completions/min_terminated_length": 167.0,
      "epoch": 0.24343506032647266,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 2.5205166339874268,
      "learning_rate": 3.1599999999999997e-07,
      "loss": 0.0644,
      "num_tokens": 442062495.0,
      "reward": 0.439453125,
      "reward_std": 0.29959845542907715,
      "rewards/simpleverify_reward/mean": 0.439453125,
      "rewards/simpleverify_reward/std": 0.49680593609809875,
      "step": 343,
      "tools/generated_tokens": 1367.275390625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.02734375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.009765625
    },
    {
      "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": 0.27734375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1277.025390625,
      "completions/mean_terminated_length": 981.1378784179688,
      "completions/min_length": 241.0,
      "completions/min_terminated_length": 241.0,
      "epoch": 0.24414478353442157,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.6804311871528625,
      "learning_rate": 3.14e-07,
      "loss": 0.0491,
      "num_tokens": 443212523.0,
      "reward": 0.44140625,
      "reward_std": 0.33071640133857727,
      "rewards/simpleverify_reward/mean": 0.44140625,
      "rewards/simpleverify_reward/std": 0.4970405399799347,
      "step": 344,
      "tools/generated_tokens": 1279.380859375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.330078125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2018.0,
      "completions/mean_length": 1323.126953125,
      "completions/mean_terminated_length": 965.9738159179688,
      "completions/min_length": 241.0,
      "completions/min_terminated_length": 241.0,
      "epoch": 0.24485450674237047,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.7062215209007263,
      "learning_rate": 3.12e-07,
      "loss": 0.0229,
      "num_tokens": 444374220.0,
      "reward": 0.37890625,
      "reward_std": 0.32367104291915894,
      "rewards/simpleverify_reward/mean": 0.37890625,
      "rewards/simpleverify_reward/std": 0.4855891764163971,
      "step": 345,
      "tools/generated_tokens": 1323.15625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.234375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2039.0,
      "completions/mean_length": 1293.248046875,
      "completions/mean_terminated_length": 1062.2015380859375,
      "completions/min_length": 180.0,
      "completions/min_terminated_length": 180.0,
      "epoch": 0.24556422995031937,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.7053819298744202,
      "learning_rate": 3.1e-07,
      "loss": 0.0667,
      "num_tokens": 445526283.0,
      "reward": 0.3203125,
      "reward_std": 0.35928022861480713,
      "rewards/simpleverify_reward/mean": 0.3203125,
      "rewards/simpleverify_reward/std": 0.4670529365539551,
      "step": 346,
      "tools/generated_tokens": 1293.330078125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.2109375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1150.072265625,
      "completions/mean_terminated_length": 910.0321655273438,
      "completions/min_length": 199.0,
      "completions/min_terminated_length": 199.0,
      "epoch": 0.24627395315826828,
      "frac_reward_zero_std": 0.125,
      "grad_norm": 0.7500547766685486,
      "learning_rate": 3.08e-07,
      "loss": 0.041,
      "num_tokens": 446597456.0,
      "reward": 0.474609375,
      "reward_std": 0.3582080602645874,
      "rewards/simpleverify_reward/mean": 0.474609375,
      "rewards/simpleverify_reward/std": 0.4998432695865631,
      "step": 347,
      "tools/generated_tokens": 1150.19140625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.001953125
    },
    {
      "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": 0.35546875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2013.0,
      "completions/mean_length": 1390.576171875,
      "completions/mean_terminated_length": 1027.9969482421875,
      "completions/min_length": 214.0,
      "completions/min_terminated_length": 214.0,
      "epoch": 0.24698367636621718,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 0.5302176475524902,
      "learning_rate": 3.0599999999999996e-07,
      "loss": 0.0402,
      "num_tokens": 447801817.0,
      "reward": 0.33984375,
      "reward_std": 0.2533029317855835,
      "rewards/simpleverify_reward/mean": 0.33984375,
      "rewards/simpleverify_reward/std": 0.4741191864013672,
      "step": 348,
      "tools/generated_tokens": 1391.345703125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.337890625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1359.59765625,
      "completions/mean_terminated_length": 1008.2890625,
      "completions/min_length": 196.0,
      "completions/min_terminated_length": 196.0,
      "epoch": 0.24769339957416608,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.5506761074066162,
      "learning_rate": 3.0399999999999997e-07,
      "loss": 0.0486,
      "num_tokens": 448983403.0,
      "reward": 0.384765625,
      "reward_std": 0.2690545320510864,
      "rewards/simpleverify_reward/mean": 0.384765625,
      "rewards/simpleverify_reward/std": 0.4870156943798065,
      "step": 349,
      "tools/generated_tokens": 1359.673828125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.3828125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2034.0,
      "completions/mean_length": 1426.984375,
      "completions/mean_terminated_length": 1041.7974853515625,
      "completions/min_length": 268.0,
      "completions/min_terminated_length": 268.0,
      "epoch": 0.248403122782115,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.5980308055877686,
      "learning_rate": 3.02e-07,
      "loss": 0.025,
      "num_tokens": 450198179.0,
      "reward": 0.29296875,
      "reward_std": 0.2858304977416992,
      "rewards/simpleverify_reward/mean": 0.29296875,
      "rewards/simpleverify_reward/std": 0.455569326877594,
      "step": 350,
      "tools/generated_tokens": 1427.04296875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.240234375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2039.0,
      "completions/mean_length": 1105.541015625,
      "completions/mean_terminated_length": 807.5398559570312,
      "completions/min_length": 186.0,
      "completions/min_terminated_length": 186.0,
      "epoch": 0.24911284599006386,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.6942192316055298,
      "learning_rate": 3e-07,
      "loss": 0.0513,
      "num_tokens": 451248851.0,
      "reward": 0.509765625,
      "reward_std": 0.2933964729309082,
      "rewards/simpleverify_reward/mean": 0.509765625,
      "rewards/simpleverify_reward/std": 0.5003935098648071,
      "step": 351,
      "tools/generated_tokens": 1106.30078125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.271484375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1153.974609375,
      "completions/mean_terminated_length": 820.8123779296875,
      "completions/min_length": 148.0,
      "completions/min_terminated_length": 148.0,
      "epoch": 0.24982256919801277,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.6195289492607117,
      "learning_rate": 2.98e-07,
      "loss": 0.0738,
      "num_tokens": 452323558.0,
      "reward": 0.392578125,
      "reward_std": 0.28559958934783936,
      "rewards/simpleverify_reward/mean": 0.392578125,
      "rewards/simpleverify_reward/std": 0.4888018071651459,
      "step": 352,
      "tools/generated_tokens": 1154.005859375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.373046875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1413.33984375,
      "completions/mean_terminated_length": 1035.7071533203125,
      "completions/min_length": 145.0,
      "completions/min_terminated_length": 145.0,
      "epoch": 0.2505322924059617,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.6473001837730408,
      "learning_rate": 2.9599999999999995e-07,
      "loss": 0.0601,
      "num_tokens": 453528553.0,
      "reward": 0.37109375,
      "reward_std": 0.33391135931015015,
      "rewards/simpleverify_reward/mean": 0.37109375,
      "rewards/simpleverify_reward/std": 0.4835699498653412,
      "step": 353,
      "tools/generated_tokens": 1413.8828125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.2109375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2024.0,
      "completions/mean_length": 1140.505859375,
      "completions/mean_terminated_length": 897.9083862304688,
      "completions/min_length": 275.0,
      "completions/min_terminated_length": 275.0,
      "epoch": 0.2512420156139106,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.695559024810791,
      "learning_rate": 2.9399999999999996e-07,
      "loss": 0.0582,
      "num_tokens": 454594940.0,
      "reward": 0.5390625,
      "reward_std": 0.3390277922153473,
      "rewards/simpleverify_reward/mean": 0.5390625,
      "rewards/simpleverify_reward/std": 0.4989593029022217,
      "step": 354,
      "tools/generated_tokens": 1140.55859375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.333984375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2031.0,
      "completions/mean_length": 1327.7734375,
      "completions/mean_terminated_length": 966.6041259765625,
      "completions/min_length": 221.0,
      "completions/min_terminated_length": 221.0,
      "epoch": 0.25195173882185945,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.7467368841171265,
      "learning_rate": 2.9199999999999997e-07,
      "loss": 0.0399,
      "num_tokens": 455756193.0,
      "reward": 0.35546875,
      "reward_std": 0.3158992528915405,
      "rewards/simpleverify_reward/mean": 0.35546875,
      "rewards/simpleverify_reward/std": 0.47912323474884033,
      "step": 355,
      "tools/generated_tokens": 1329.091796875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.30078125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2022.0,
      "completions/mean_length": 1244.650390625,
      "completions/mean_terminated_length": 899.0753784179688,
      "completions/min_length": 155.0,
      "completions/min_terminated_length": 155.0,
      "epoch": 0.2526614620298084,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.6393960118293762,
      "learning_rate": 2.9e-07,
      "loss": 0.0454,
      "num_tokens": 456876366.0,
      "reward": 0.38671875,
      "reward_std": 0.30661919713020325,
      "rewards/simpleverify_reward/mean": 0.38671875,
      "rewards/simpleverify_reward/std": 0.48747459053993225,
      "step": 356,
      "tools/generated_tokens": 1244.7734375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.361328125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1408.763671875,
      "completions/mean_terminated_length": 1047.1162109375,
      "completions/min_length": 188.0,
      "completions/min_terminated_length": 188.0,
      "epoch": 0.25337118523775726,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.5758090615272522,
      "learning_rate": 2.88e-07,
      "loss": 0.044,
      "num_tokens": 458087469.0,
      "reward": 0.33984375,
      "reward_std": 0.29832786321640015,
      "rewards/simpleverify_reward/mean": 0.33984375,
      "rewards/simpleverify_reward/std": 0.4741191864013672,
      "step": 357,
      "tools/generated_tokens": 1417.55859375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0078125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.298828125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2040.0,
      "completions/mean_length": 1348.091796875,
      "completions/mean_terminated_length": 1049.80224609375,
      "completions/min_length": 192.0,
      "completions/min_terminated_length": 192.0,
      "epoch": 0.2540809084457062,
      "frac_reward_zero_std": 0.125,
      "grad_norm": 0.6754249334335327,
      "learning_rate": 2.8599999999999994e-07,
      "loss": 0.0553,
      "num_tokens": 459268890.0,
      "reward": 0.439453125,
      "reward_std": 0.34164124727249146,
      "rewards/simpleverify_reward/mean": 0.439453125,
      "rewards/simpleverify_reward/std": 0.49680593609809875,
      "step": 358,
      "tools/generated_tokens": 1353.98828125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.255859375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2035.0,
      "completions/mean_length": 1202.189453125,
      "completions/mean_terminated_length": 911.3753051757812,
      "completions/min_length": 200.0,
      "completions/min_terminated_length": 200.0,
      "epoch": 0.25479063165365506,
      "frac_reward_zero_std": 0.125,
      "grad_norm": 0.7031462788581848,
      "learning_rate": 2.8399999999999995e-07,
      "loss": 0.0581,
      "num_tokens": 460374267.0,
      "reward": 0.48828125,
      "reward_std": 0.38914695382118225,
      "rewards/simpleverify_reward/mean": 0.48828125,
      "rewards/simpleverify_reward/std": 0.5003514885902405,
      "step": 359,
      "tools/generated_tokens": 1202.244140625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.302734375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2040.0,
      "completions/mean_length": 1234.04296875,
      "completions/mean_terminated_length": 880.644287109375,
      "completions/min_length": 1.0,
      "completions/min_terminated_length": 1.0,
      "epoch": 0.255500354861604,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.6721753478050232,
      "learning_rate": 2.8199999999999996e-07,
      "loss": 0.0103,
      "num_tokens": 461485778.0,
      "reward": 0.310546875,
      "reward_std": 0.2735599875450134,
      "rewards/simpleverify_reward/mean": 0.310546875,
      "rewards/simpleverify_reward/std": 0.46317005157470703,
      "step": 360,
      "tools/generated_tokens": 1235.123046875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.2890625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2023.0,
      "completions/mean_length": 1147.40234375,
      "completions/mean_terminated_length": 781.2252807617188,
      "completions/min_length": 217.0,
      "completions/min_terminated_length": 217.0,
      "epoch": 0.25621007806955287,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.6766145825386047,
      "learning_rate": 2.8e-07,
      "loss": 0.0509,
      "num_tokens": 462569069.0,
      "reward": 0.38671875,
      "reward_std": 0.3148774206638336,
      "rewards/simpleverify_reward/mean": 0.38671875,
      "rewards/simpleverify_reward/std": 0.48747459053993225,
      "step": 361,
      "tools/generated_tokens": 1151.576171875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.009765625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.224609375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2024.0,
      "completions/mean_length": 1184.7421875,
      "completions/mean_terminated_length": 934.6800537109375,
      "completions/min_length": 146.0,
      "completions/min_terminated_length": 146.0,
      "epoch": 0.25691980127750175,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.6532149314880371,
      "learning_rate": 2.7800000000000003e-07,
      "loss": 0.0547,
      "num_tokens": 463670486.0,
      "reward": 0.41015625,
      "reward_std": 0.3096548318862915,
      "rewards/simpleverify_reward/mean": 0.41015625,
      "rewards/simpleverify_reward/std": 0.49234291911125183,
      "step": 362,
      "tools/generated_tokens": 1188.095703125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.220703125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1157.3828125,
      "completions/mean_terminated_length": 905.1528930664062,
      "completions/min_length": 128.0,
      "completions/min_terminated_length": 128.0,
      "epoch": 0.2576295244854507,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.8286237716674805,
      "learning_rate": 2.7600000000000004e-07,
      "loss": 0.0557,
      "num_tokens": 464746284.0,
      "reward": 0.431640625,
      "reward_std": 0.323504775762558,
      "rewards/simpleverify_reward/mean": 0.431640625,
      "rewards/simpleverify_reward/std": 0.4957893490791321,
      "step": 363,
      "tools/generated_tokens": 1160.5390625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.00390625
    },
    {
      "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": 0.240234375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1261.052734375,
      "completions/mean_terminated_length": 1012.2236328125,
      "completions/min_length": 182.0,
      "completions/min_terminated_length": 182.0,
      "epoch": 0.25833924769339955,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.7166011333465576,
      "learning_rate": 2.74e-07,
      "loss": 0.0439,
      "num_tokens": 465902913.0,
      "reward": 0.359375,
      "reward_std": 0.32318317890167236,
      "rewards/simpleverify_reward/mean": 0.359375,
      "rewards/simpleverify_reward/std": 0.48028653860092163,
      "step": 364,
      "tools/generated_tokens": 1246.298828125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.03515625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.181640625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1123.255859375,
      "completions/mean_terminated_length": 918.00244140625,
      "completions/min_length": 118.0,
      "completions/min_terminated_length": 118.0,
      "epoch": 0.2590489709013485,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.8048588633537292,
      "learning_rate": 2.72e-07,
      "loss": 0.0293,
      "num_tokens": 466963851.0,
      "reward": 0.376953125,
      "reward_std": 0.3425540328025818,
      "rewards/simpleverify_reward/mean": 0.376953125,
      "rewards/simpleverify_reward/std": 0.4850969910621643,
      "step": 365,
      "tools/generated_tokens": 1124.53125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.208984375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2034.0,
      "completions/mean_length": 1146.4921875,
      "completions/mean_terminated_length": 908.3161010742188,
      "completions/min_length": 254.0,
      "completions/min_terminated_length": 254.0,
      "epoch": 0.25975869410929736,
      "frac_reward_zero_std": 0.09375,
      "grad_norm": 0.764937698841095,
      "learning_rate": 2.7e-07,
      "loss": 0.0437,
      "num_tokens": 468035447.0,
      "reward": 0.49609375,
      "reward_std": 0.3268173336982727,
      "rewards/simpleverify_reward/mean": 0.49609375,
      "rewards/simpleverify_reward/std": 0.5004737377166748,
      "step": 366,
      "tools/generated_tokens": 1146.556640625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.275390625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1337.48046875,
      "completions/mean_terminated_length": 1067.4447021484375,
      "completions/min_length": 184.0,
      "completions/min_terminated_length": 184.0,
      "epoch": 0.2604684173172463,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.6203275918960571,
      "learning_rate": 2.68e-07,
      "loss": 0.0449,
      "num_tokens": 469209277.0,
      "reward": 0.458984375,
      "reward_std": 0.31374257802963257,
      "rewards/simpleverify_reward/mean": 0.458984375,
      "rewards/simpleverify_reward/std": 0.49880221486091614,
      "step": 367,
      "tools/generated_tokens": 1337.568359375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.392578125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2041.0,
      "completions/mean_length": 1409.142578125,
      "completions/mean_terminated_length": 996.24755859375,
      "completions/min_length": 189.0,
      "completions/min_terminated_length": 189.0,
      "epoch": 0.26117814052519517,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.6325060725212097,
      "learning_rate": 2.66e-07,
      "loss": 0.0594,
      "num_tokens": 470414662.0,
      "reward": 0.35546875,
      "reward_std": 0.30289798974990845,
      "rewards/simpleverify_reward/mean": 0.35546875,
      "rewards/simpleverify_reward/std": 0.47912323474884033,
      "step": 368,
      "tools/generated_tokens": 1409.21484375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.302734375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1396.20703125,
      "completions/mean_terminated_length": 1113.2156982421875,
      "completions/min_length": 1.0,
      "completions/min_terminated_length": 1.0,
      "epoch": 0.2618878637331441,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.6155630946159363,
      "learning_rate": 2.64e-07,
      "loss": 0.0421,
      "num_tokens": 471621152.0,
      "reward": 0.42578125,
      "reward_std": 0.3427072763442993,
      "rewards/simpleverify_reward/mean": 0.42578125,
      "rewards/simpleverify_reward/std": 0.4949444830417633,
      "step": 369,
      "tools/generated_tokens": 1396.310546875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.3515625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2036.0,
      "completions/mean_length": 1389.11328125,
      "completions/mean_terminated_length": 1031.885498046875,
      "completions/min_length": 120.0,
      "completions/min_terminated_length": 120.0,
      "epoch": 0.262597586941093,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.6010565757751465,
      "learning_rate": 2.62e-07,
      "loss": 0.0588,
      "num_tokens": 472824298.0,
      "reward": 0.3125,
      "reward_std": 0.2748309373855591,
      "rewards/simpleverify_reward/mean": 0.3125,
      "rewards/simpleverify_reward/std": 0.4639657139778137,
      "step": 370,
      "tools/generated_tokens": 1389.28125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.15234375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2022.0,
      "completions/mean_length": 964.123046875,
      "completions/mean_terminated_length": 769.331787109375,
      "completions/min_length": 1.0,
      "completions/min_terminated_length": 1.0,
      "epoch": 0.26330731014904185,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.6946766972541809,
      "learning_rate": 2.6e-07,
      "loss": 0.0207,
      "num_tokens": 473802262.0,
      "reward": 0.529296875,
      "reward_std": 0.2616007924079895,
      "rewards/simpleverify_reward/mean": 0.529296875,
      "rewards/simpleverify_reward/std": 0.49962911009788513,
      "step": 371,
      "tools/generated_tokens": 965.3671875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.28125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2024.0,
      "completions/mean_length": 1241.697265625,
      "completions/mean_terminated_length": 926.1875,
      "completions/min_length": 226.0,
      "completions/min_terminated_length": 226.0,
      "epoch": 0.2640170333569908,
      "frac_reward_zero_std": 0.40625,
      "grad_norm": 0.5640001893043518,
      "learning_rate": 2.58e-07,
      "loss": 0.0539,
      "num_tokens": 474926507.0,
      "reward": 0.337890625,
      "reward_std": 0.2517799139022827,
      "rewards/simpleverify_reward/mean": 0.337890625,
      "rewards/simpleverify_reward/std": 0.4734536409378052,
      "step": 372,
      "tools/generated_tokens": 1241.970703125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.298828125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2029.0,
      "completions/mean_length": 1240.833984375,
      "completions/mean_terminated_length": 896.8328247070312,
      "completions/min_length": 119.0,
      "completions/min_terminated_length": 119.0,
      "epoch": 0.26472675656493966,
      "frac_reward_zero_std": 0.125,
      "grad_norm": 0.8219614624977112,
      "learning_rate": 2.56e-07,
      "loss": 0.0849,
      "num_tokens": 476067523.0,
      "reward": 0.427734375,
      "reward_std": 0.36377912759780884,
      "rewards/simpleverify_reward/mean": 0.427734375,
      "rewards/simpleverify_reward/std": 0.4952339828014374,
      "step": 373,
      "tools/generated_tokens": 1246.11328125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.23828125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2037.0,
      "completions/mean_length": 1140.72265625,
      "completions/mean_terminated_length": 856.90771484375,
      "completions/min_length": 213.0,
      "completions/min_terminated_length": 213.0,
      "epoch": 0.2654364797728886,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 1.852407455444336,
      "learning_rate": 2.5399999999999997e-07,
      "loss": 0.0596,
      "num_tokens": 477135573.0,
      "reward": 0.443359375,
      "reward_std": 0.310013085603714,
      "rewards/simpleverify_reward/mean": 0.443359375,
      "rewards/simpleverify_reward/std": 0.49726733565330505,
      "step": 374,
      "tools/generated_tokens": 1140.79296875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.29296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1320.62890625,
      "completions/mean_terminated_length": 1019.2320556640625,
      "completions/min_length": 219.0,
      "completions/min_terminated_length": 219.0,
      "epoch": 0.26614620298083747,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.6187204122543335,
      "learning_rate": 2.52e-07,
      "loss": 0.0355,
      "num_tokens": 478302692.0,
      "reward": 0.40625,
      "reward_std": 0.2970767021179199,
      "rewards/simpleverify_reward/mean": 0.40625,
      "rewards/simpleverify_reward/std": 0.49161264300346375,
      "step": 375,
      "tools/generated_tokens": 1325.619140625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.009765625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.216796875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1176.529296875,
      "completions/mean_terminated_length": 935.2992553710938,
      "completions/min_length": 286.0,
      "completions/min_terminated_length": 286.0,
      "epoch": 0.2668559261887864,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.6812962889671326,
      "learning_rate": 2.5e-07,
      "loss": 0.0502,
      "num_tokens": 479394707.0,
      "reward": 0.4453125,
      "reward_std": 0.28951048851013184,
      "rewards/simpleverify_reward/mean": 0.4453125,
      "rewards/simpleverify_reward/std": 0.49748632311820984,
      "step": 376,
      "tools/generated_tokens": 1176.6171875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.279296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2035.0,
      "completions/mean_length": 1256.630859375,
      "completions/mean_terminated_length": 949.9485473632812,
      "completions/min_length": 43.0,
      "completions/min_terminated_length": 43.0,
      "epoch": 0.2675656493967353,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.6673181653022766,
      "learning_rate": 2.48e-07,
      "loss": 0.0243,
      "num_tokens": 480526086.0,
      "reward": 0.33984375,
      "reward_std": 0.32239681482315063,
      "rewards/simpleverify_reward/mean": 0.33984375,
      "rewards/simpleverify_reward/std": 0.4741191864013672,
      "step": 377,
      "tools/generated_tokens": 1256.6875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.330078125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2038.0,
      "completions/mean_length": 1387.1875,
      "completions/mean_terminated_length": 1061.59765625,
      "completions/min_length": 258.0,
      "completions/min_terminated_length": 258.0,
      "epoch": 0.26827537260468415,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.6397454142570496,
      "learning_rate": 2.46e-07,
      "loss": 0.0736,
      "num_tokens": 481723718.0,
      "reward": 0.39453125,
      "reward_std": 0.30578774213790894,
      "rewards/simpleverify_reward/mean": 0.39453125,
      "rewards/simpleverify_reward/std": 0.4892277717590332,
      "step": 378,
      "tools/generated_tokens": 1387.291015625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.2109375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2041.0,
      "completions/mean_length": 1160.076171875,
      "completions/mean_terminated_length": 922.7103881835938,
      "completions/min_length": 153.0,
      "completions/min_terminated_length": 153.0,
      "epoch": 0.2689850958126331,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.6766166090965271,
      "learning_rate": 2.4399999999999996e-07,
      "loss": 0.048,
      "num_tokens": 482803059.0,
      "reward": 0.4921875,
      "reward_std": 0.3281271755695343,
      "rewards/simpleverify_reward/mean": 0.4921875,
      "rewards/simpleverify_reward/std": 0.5004279017448425,
      "step": 379,
      "tools/generated_tokens": 1161.390625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.287109375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1200.048828125,
      "completions/mean_terminated_length": 858.5479736328125,
      "completions/min_length": 146.0,
      "completions/min_terminated_length": 146.0,
      "epoch": 0.26969481902058196,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.6695575714111328,
      "learning_rate": 2.4199999999999997e-07,
      "loss": 0.038,
      "num_tokens": 483903604.0,
      "reward": 0.474609375,
      "reward_std": 0.2772991359233856,
      "rewards/simpleverify_reward/mean": 0.474609375,
      "rewards/simpleverify_reward/std": 0.4998432695865631,
      "step": 380,
      "tools/generated_tokens": 1201.419921875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.30859375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2032.0,
      "completions/mean_length": 1266.982421875,
      "completions/mean_terminated_length": 918.3926391601562,
      "completions/min_length": 167.0,
      "completions/min_terminated_length": 167.0,
      "epoch": 0.2704045422285309,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.6021305918693542,
      "learning_rate": 2.4e-07,
      "loss": 0.0245,
      "num_tokens": 485039595.0,
      "reward": 0.40234375,
      "reward_std": 0.2551799714565277,
      "rewards/simpleverify_reward/mean": 0.40234375,
      "rewards/simpleverify_reward/std": 0.4908501207828522,
      "step": 381,
      "tools/generated_tokens": 1267.236328125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.232421875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2039.0,
      "completions/mean_length": 1167.8671875,
      "completions/mean_terminated_length": 901.3638916015625,
      "completions/min_length": 216.0,
      "completions/min_terminated_length": 216.0,
      "epoch": 0.27111426543647976,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.7280493378639221,
      "learning_rate": 2.38e-07,
      "loss": 0.027,
      "num_tokens": 486122359.0,
      "reward": 0.427734375,
      "reward_std": 0.29272642731666565,
      "rewards/simpleverify_reward/mean": 0.427734375,
      "rewards/simpleverify_reward/std": 0.4952339828014374,
      "step": 382,
      "tools/generated_tokens": 1167.982421875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.34765625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2033.0,
      "completions/mean_length": 1427.1640625,
      "completions/mean_terminated_length": 1096.2994384765625,
      "completions/min_length": 281.0,
      "completions/min_terminated_length": 281.0,
      "epoch": 0.2718239886444287,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.6256048679351807,
      "learning_rate": 2.3599999999999997e-07,
      "loss": 0.0237,
      "num_tokens": 487342347.0,
      "reward": 0.353515625,
      "reward_std": 0.2980824112892151,
      "rewards/simpleverify_reward/mean": 0.353515625,
      "rewards/simpleverify_reward/std": 0.47852855920791626,
      "step": 383,
      "tools/generated_tokens": 1427.25390625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.265625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1382.33984375,
      "completions/mean_terminated_length": 1141.569091796875,
      "completions/min_length": 385.0,
      "completions/min_terminated_length": 385.0,
      "epoch": 0.27253371185237757,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.6692814230918884,
      "learning_rate": 2.34e-07,
      "loss": 0.0846,
      "num_tokens": 488535047.0,
      "reward": 0.4296875,
      "reward_std": 0.3399724066257477,
      "rewards/simpleverify_reward/mean": 0.4296875,
      "rewards/simpleverify_reward/std": 0.4955156147480011,
      "step": 384,
      "tools/generated_tokens": 1385.74609375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.28125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1279.947265625,
      "completions/mean_terminated_length": 979.4049072265625,
      "completions/min_length": 165.0,
      "completions/min_terminated_length": 165.0,
      "epoch": 0.27324343506032645,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.7357189059257507,
      "learning_rate": 2.32e-07,
      "loss": 0.0551,
      "num_tokens": 489677980.0,
      "reward": 0.4375,
      "reward_std": 0.33020398020744324,
      "rewards/simpleverify_reward/mean": 0.4375,
      "rewards/simpleverify_reward/std": 0.49656352400779724,
      "step": 385,
      "tools/generated_tokens": 1280.0234375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.310546875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1352.125,
      "completions/mean_terminated_length": 1038.685546875,
      "completions/min_length": 180.0,
      "completions/min_terminated_length": 180.0,
      "epoch": 0.2739531582682754,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 22.788246154785156,
      "learning_rate": 2.3e-07,
      "loss": 0.0217,
      "num_tokens": 490885111.0,
      "reward": 0.3515625,
      "reward_std": 0.27165788412094116,
      "rewards/simpleverify_reward/mean": 0.3515625,
      "rewards/simpleverify_reward/std": 0.4779251217842102,
      "step": 386,
      "tools/generated_tokens": 1344.6796875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.021484375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.00390625
    },
    {
      "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": 0.32421875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2041.0,
      "completions/mean_length": 1322.56640625,
      "completions/mean_terminated_length": 974.5260009765625,
      "completions/min_length": 216.0,
      "completions/min_terminated_length": 216.0,
      "epoch": 0.27466288147622425,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.6160613894462585,
      "learning_rate": 2.28e-07,
      "loss": 0.0557,
      "num_tokens": 492044761.0,
      "reward": 0.40234375,
      "reward_std": 0.32096806168556213,
      "rewards/simpleverify_reward/mean": 0.40234375,
      "rewards/simpleverify_reward/std": 0.4908501207828522,
      "step": 387,
      "tools/generated_tokens": 1322.6796875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.2890625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1248.8671875,
      "completions/mean_terminated_length": 923.945068359375,
      "completions/min_length": 196.0,
      "completions/min_terminated_length": 196.0,
      "epoch": 0.2753726046841732,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.6579756736755371,
      "learning_rate": 2.2599999999999999e-07,
      "loss": 0.0474,
      "num_tokens": 493175429.0,
      "reward": 0.44921875,
      "reward_std": 0.33170169591903687,
      "rewards/simpleverify_reward/mean": 0.44921875,
      "rewards/simpleverify_reward/std": 0.497901052236557,
      "step": 388,
      "tools/generated_tokens": 1253.119140625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.01171875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.359375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1358.93359375,
      "completions/mean_terminated_length": 972.3840942382812,
      "completions/min_length": 206.0,
      "completions/min_terminated_length": 206.0,
      "epoch": 0.27608232789212206,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 0.6040433645248413,
      "learning_rate": 2.24e-07,
      "loss": 0.0325,
      "num_tokens": 494352387.0,
      "reward": 0.357421875,
      "reward_std": 0.2569561302661896,
      "rewards/simpleverify_reward/mean": 0.357421875,
      "rewards/simpleverify_reward/std": 0.4797092080116272,
      "step": 389,
      "tools/generated_tokens": 1358.9609375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.341796875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1291.34375,
      "completions/mean_terminated_length": 898.42138671875,
      "completions/min_length": 195.0,
      "completions/min_terminated_length": 195.0,
      "epoch": 0.276792051100071,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.5689383745193481,
      "learning_rate": 2.22e-07,
      "loss": 0.043,
      "num_tokens": 495499363.0,
      "reward": 0.390625,
      "reward_std": 0.26429039239883423,
      "rewards/simpleverify_reward/mean": 0.390625,
      "rewards/simpleverify_reward/std": 0.48836761713027954,
      "step": 390,
      "tools/generated_tokens": 1291.47265625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.369140625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1377.71484375,
      "completions/mean_terminated_length": 985.504638671875,
      "completions/min_length": 169.0,
      "completions/min_terminated_length": 169.0,
      "epoch": 0.27750177430801987,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.7342774868011475,
      "learning_rate": 2.1999999999999998e-07,
      "loss": 0.0662,
      "num_tokens": 496696177.0,
      "reward": 0.39453125,
      "reward_std": 0.3232579231262207,
      "rewards/simpleverify_reward/mean": 0.39453125,
      "rewards/simpleverify_reward/std": 0.4892277717590332,
      "step": 391,
      "tools/generated_tokens": 1377.828125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.28125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2036.0,
      "completions/mean_length": 1203.916015625,
      "completions/mean_terminated_length": 873.622314453125,
      "completions/min_length": 192.0,
      "completions/min_terminated_length": 192.0,
      "epoch": 0.2782114975159688,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.5903851985931396,
      "learning_rate": 2.18e-07,
      "loss": 0.034,
      "num_tokens": 497800694.0,
      "reward": 0.40234375,
      "reward_std": 0.25922486186027527,
      "rewards/simpleverify_reward/mean": 0.40234375,
      "rewards/simpleverify_reward/std": 0.4908501207828522,
      "step": 392,
      "tools/generated_tokens": 1203.986328125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.306640625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1267.634765625,
      "completions/mean_terminated_length": 922.5154418945312,
      "completions/min_length": 163.0,
      "completions/min_terminated_length": 163.0,
      "epoch": 0.2789212207239177,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.7402511835098267,
      "learning_rate": 2.1599999999999998e-07,
      "loss": 0.0594,
      "num_tokens": 498930443.0,
      "reward": 0.49609375,
      "reward_std": 0.31898653507232666,
      "rewards/simpleverify_reward/mean": 0.49609375,
      "rewards/simpleverify_reward/std": 0.5004737377166748,
      "step": 393,
      "tools/generated_tokens": 1267.689453125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.380859375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2039.0,
      "completions/mean_length": 1365.646484375,
      "completions/mean_terminated_length": 945.9022216796875,
      "completions/min_length": 211.0,
      "completions/min_terminated_length": 211.0,
      "epoch": 0.27963094393186655,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.7135945558547974,
      "learning_rate": 2.1399999999999998e-07,
      "loss": 0.0631,
      "num_tokens": 500112310.0,
      "reward": 0.328125,
      "reward_std": 0.32366305589675903,
      "rewards/simpleverify_reward/mean": 0.328125,
      "rewards/simpleverify_reward/std": 0.4699897766113281,
      "step": 394,
      "tools/generated_tokens": 1365.734375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.359375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2041.0,
      "completions/mean_length": 1300.4140625,
      "completions/mean_terminated_length": 881.0365600585938,
      "completions/min_length": 1.0,
      "completions/min_terminated_length": 1.0,
      "epoch": 0.2803406671398155,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.647331178188324,
      "learning_rate": 2.12e-07,
      "loss": 0.0502,
      "num_tokens": 501265434.0,
      "reward": 0.3359375,
      "reward_std": 0.2713969051837921,
      "rewards/simpleverify_reward/mean": 0.3359375,
      "rewards/simpleverify_reward/std": 0.4727790653705597,
      "step": 395,
      "tools/generated_tokens": 1300.5703125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.1640625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 996.9765625,
      "completions/mean_terminated_length": 790.700927734375,
      "completions/min_length": 113.0,
      "completions/min_terminated_length": 113.0,
      "epoch": 0.28105039034776436,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.7739845514297485,
      "learning_rate": 2.0999999999999997e-07,
      "loss": 0.0607,
      "num_tokens": 502262296.0,
      "reward": 0.412109375,
      "reward_std": 0.3054564297199249,
      "rewards/simpleverify_reward/mean": 0.412109375,
      "rewards/simpleverify_reward/std": 0.49269601702690125,
      "step": 396,
      "tools/generated_tokens": 998.6640625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.263671875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2020.0,
      "completions/mean_length": 1270.259765625,
      "completions/mean_terminated_length": 991.7586059570312,
      "completions/min_length": 221.0,
      "completions/min_terminated_length": 221.0,
      "epoch": 0.2817601135557133,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.6564942598342896,
      "learning_rate": 2.0799999999999998e-07,
      "loss": 0.0618,
      "num_tokens": 503407581.0,
      "reward": 0.4453125,
      "reward_std": 0.35241031646728516,
      "rewards/simpleverify_reward/mean": 0.4453125,
      "rewards/simpleverify_reward/std": 0.49748632311820984,
      "step": 397,
      "tools/generated_tokens": 1270.498046875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.29296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2031.0,
      "completions/mean_length": 1237.642578125,
      "completions/mean_terminated_length": 901.859130859375,
      "completions/min_length": 219.0,
      "completions/min_terminated_length": 219.0,
      "epoch": 0.28246983676366216,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.698727011680603,
      "learning_rate": 2.06e-07,
      "loss": 0.0592,
      "num_tokens": 504521014.0,
      "reward": 0.421875,
      "reward_std": 0.2939755916595459,
      "rewards/simpleverify_reward/mean": 0.421875,
      "rewards/simpleverify_reward/std": 0.49434176087379456,
      "step": 398,
      "tools/generated_tokens": 1237.78515625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.23046875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2027.0,
      "completions/mean_length": 1289.72265625,
      "completions/mean_terminated_length": 1062.6243896484375,
      "completions/min_length": 274.0,
      "completions/min_terminated_length": 274.0,
      "epoch": 0.2831795599716111,
      "frac_reward_zero_std": 0.0625,
      "grad_norm": 0.7721478939056396,
      "learning_rate": 2.0399999999999997e-07,
      "loss": 0.0561,
      "num_tokens": 505669744.0,
      "reward": 0.423828125,
      "reward_std": 0.38662952184677124,
      "rewards/simpleverify_reward/mean": 0.423828125,
      "rewards/simpleverify_reward/std": 0.4946470856666565,
      "step": 399,
      "tools/generated_tokens": 1294.330078125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.00390625
    },
    {
      "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": 0.349609375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2038.0,
      "completions/mean_length": 1349.689453125,
      "completions/mean_terminated_length": 974.3213500976562,
      "completions/min_length": 231.0,
      "completions/min_terminated_length": 231.0,
      "epoch": 0.28388928317955997,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.5860941410064697,
      "learning_rate": 2.02e-07,
      "loss": 0.0311,
      "num_tokens": 506847268.0,
      "reward": 0.259765625,
      "reward_std": 0.2570491135120392,
      "rewards/simpleverify_reward/mean": 0.259765625,
      "rewards/simpleverify_reward/std": 0.4389347732067108,
      "step": 400,
      "tools/generated_tokens": 1354.93359375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.330078125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2032.0,
      "completions/mean_length": 1388.380859375,
      "completions/mean_terminated_length": 1063.3790283203125,
      "completions/min_length": 284.0,
      "completions/min_terminated_length": 284.0,
      "epoch": 0.28459900638750885,
      "frac_reward_zero_std": 0.09375,
      "grad_norm": 6.295687675476074,
      "learning_rate": 2e-07,
      "loss": 0.0614,
      "num_tokens": 508055946.0,
      "reward": 0.306640625,
      "reward_std": 0.3533630967140198,
      "rewards/simpleverify_reward/mean": 0.306640625,
      "rewards/simpleverify_reward/std": 0.4615498185157776,
      "step": 401,
      "tools/generated_tokens": 1396.439453125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.013671875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.30859375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1374.58984375,
      "completions/mean_terminated_length": 1074.0281982421875,
      "completions/min_length": 157.0,
      "completions/min_terminated_length": 157.0,
      "epoch": 0.2853087295954578,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.5921972393989563,
      "learning_rate": 1.98e-07,
      "loss": 0.0647,
      "num_tokens": 509253680.0,
      "reward": 0.294921875,
      "reward_std": 0.30614081025123596,
      "rewards/simpleverify_reward/mean": 0.294921875,
      "rewards/simpleverify_reward/std": 0.4564536213874817,
      "step": 402,
      "tools/generated_tokens": 1375.25390625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.212890625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2038.0,
      "completions/mean_length": 1173.8984375,
      "completions/mean_terminated_length": 937.4788818359375,
      "completions/min_length": 165.0,
      "completions/min_terminated_length": 165.0,
      "epoch": 0.28601845280340665,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.6621772050857544,
      "learning_rate": 1.96e-07,
      "loss": 0.0512,
      "num_tokens": 510344560.0,
      "reward": 0.302734375,
      "reward_std": 0.3198366165161133,
      "rewards/simpleverify_reward/mean": 0.302734375,
      "rewards/simpleverify_reward/std": 0.45989060401916504,
      "step": 403,
      "tools/generated_tokens": 1174.994140625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.2421875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1117.890625,
      "completions/mean_terminated_length": 820.644287109375,
      "completions/min_length": 199.0,
      "completions/min_terminated_length": 199.0,
      "epoch": 0.2867281760113556,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.8605492115020752,
      "learning_rate": 1.94e-07,
      "loss": 0.033,
      "num_tokens": 511407561.0,
      "reward": 0.390625,
      "reward_std": 0.3527781367301941,
      "rewards/simpleverify_reward/mean": 0.390625,
      "rewards/simpleverify_reward/std": 0.48836761713027954,
      "step": 404,
      "tools/generated_tokens": 1118.763671875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.22265625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1213.783203125,
      "completions/mean_terminated_length": 974.836669921875,
      "completions/min_length": 219.0,
      "completions/min_terminated_length": 219.0,
      "epoch": 0.28743789921930446,
      "frac_reward_zero_std": 0.09375,
      "grad_norm": 0.7969029545783997,
      "learning_rate": 1.92e-07,
      "loss": 0.0795,
      "num_tokens": 512523930.0,
      "reward": 0.455078125,
      "reward_std": 0.4014338254928589,
      "rewards/simpleverify_reward/mean": 0.455078125,
      "rewards/simpleverify_reward/std": 0.4984649419784546,
      "step": 405,
      "tools/generated_tokens": 1213.9140625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.380859375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1438.638671875,
      "completions/mean_terminated_length": 1063.794921875,
      "completions/min_length": 209.0,
      "completions/min_terminated_length": 209.0,
      "epoch": 0.2881476224272534,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.7239100933074951,
      "learning_rate": 1.8999999999999998e-07,
      "loss": 0.0463,
      "num_tokens": 513743361.0,
      "reward": 0.2890625,
      "reward_std": 0.3026997745037079,
      "rewards/simpleverify_reward/mean": 0.2890625,
      "rewards/simpleverify_reward/std": 0.45377036929130554,
      "step": 406,
      "tools/generated_tokens": 1438.798828125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.392578125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2040.0,
      "completions/mean_length": 1430.755859375,
      "completions/mean_terminated_length": 1031.82958984375,
      "completions/min_length": 312.0,
      "completions/min_terminated_length": 312.0,
      "epoch": 0.28885734563520227,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.591381311416626,
      "learning_rate": 1.88e-07,
      "loss": 0.0462,
      "num_tokens": 514960196.0,
      "reward": 0.330078125,
      "reward_std": 0.3073534667491913,
      "rewards/simpleverify_reward/mean": 0.330078125,
      "rewards/simpleverify_reward/std": 0.47070086002349854,
      "step": 407,
      "tools/generated_tokens": 1430.859375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.158203125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2037.0,
      "completions/mean_length": 1112.625,
      "completions/mean_terminated_length": 936.835205078125,
      "completions/min_length": 266.0,
      "completions/min_terminated_length": 266.0,
      "epoch": 0.2895670688431512,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.7954338192939758,
      "learning_rate": 1.86e-07,
      "loss": 0.0369,
      "num_tokens": 516021956.0,
      "reward": 0.4921875,
      "reward_std": 0.3528083264827728,
      "rewards/simpleverify_reward/mean": 0.4921875,
      "rewards/simpleverify_reward/std": 0.5004279017448425,
      "step": 408,
      "tools/generated_tokens": 1112.6953125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.302734375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1309.173828125,
      "completions/mean_terminated_length": 988.3949584960938,
      "completions/min_length": 153.0,
      "completions/min_terminated_length": 153.0,
      "epoch": 0.2902767920511001,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 0.5457648038864136,
      "learning_rate": 1.8399999999999998e-07,
      "loss": 0.0412,
      "num_tokens": 517184199.0,
      "reward": 0.302734375,
      "reward_std": 0.2620815336704254,
      "rewards/simpleverify_reward/mean": 0.302734375,
      "rewards/simpleverify_reward/std": 0.45989060401916504,
      "step": 409,
      "tools/generated_tokens": 1311.677734375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.216796875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1171.06640625,
      "completions/mean_terminated_length": 928.32421875,
      "completions/min_length": 104.0,
      "completions/min_terminated_length": 104.0,
      "epoch": 0.29098651525904895,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.6583137512207031,
      "learning_rate": 1.82e-07,
      "loss": 0.0656,
      "num_tokens": 518273609.0,
      "reward": 0.43359375,
      "reward_std": 0.3208349943161011,
      "rewards/simpleverify_reward/mean": 0.43359375,
      "rewards/simpleverify_reward/std": 0.4960552453994751,
      "step": 410,
      "tools/generated_tokens": 1171.162109375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.322265625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2038.0,
      "completions/mean_length": 1298.9765625,
      "completions/mean_terminated_length": 942.8126220703125,
      "completions/min_length": 145.0,
      "completions/min_terminated_length": 145.0,
      "epoch": 0.2916962384669979,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 1.140650749206543,
      "learning_rate": 1.8e-07,
      "loss": 0.0398,
      "num_tokens": 519431405.0,
      "reward": 0.353515625,
      "reward_std": 0.3374301791191101,
      "rewards/simpleverify_reward/mean": 0.353515625,
      "rewards/simpleverify_reward/std": 0.47852855920791626,
      "step": 411,
      "tools/generated_tokens": 1300.896484375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.236328125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2031.0,
      "completions/mean_length": 1175.66796875,
      "completions/mean_terminated_length": 905.7135620117188,
      "completions/min_length": 246.0,
      "completions/min_terminated_length": 246.0,
      "epoch": 0.29240596167494676,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.7362069487571716,
      "learning_rate": 1.7799999999999998e-07,
      "loss": 0.0551,
      "num_tokens": 520518911.0,
      "reward": 0.484375,
      "reward_std": 0.35414251685142517,
      "rewards/simpleverify_reward/mean": 0.484375,
      "rewards/simpleverify_reward/std": 0.5002445578575134,
      "step": 412,
      "tools/generated_tokens": 1178.462890625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.173828125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2037.0,
      "completions/mean_length": 1169.921875,
      "completions/mean_terminated_length": 985.172607421875,
      "completions/min_length": 311.0,
      "completions/min_terminated_length": 311.0,
      "epoch": 0.2931156848828957,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.6351224780082703,
      "learning_rate": 1.76e-07,
      "loss": 0.0175,
      "num_tokens": 521604337.0,
      "reward": 0.390625,
      "reward_std": 0.2914080023765564,
      "rewards/simpleverify_reward/mean": 0.390625,
      "rewards/simpleverify_reward/std": 0.48836761713027954,
      "step": 413,
      "tools/generated_tokens": 1170.1796875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.26171875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2036.0,
      "completions/mean_length": 1173.81640625,
      "completions/mean_terminated_length": 863.9205932617188,
      "completions/min_length": 72.0,
      "completions/min_terminated_length": 72.0,
      "epoch": 0.29382540809084456,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.7182329893112183,
      "learning_rate": 1.7399999999999997e-07,
      "loss": 0.0546,
      "num_tokens": 522697711.0,
      "reward": 0.373046875,
      "reward_std": 0.3029216527938843,
      "rewards/simpleverify_reward/mean": 0.373046875,
      "rewards/simpleverify_reward/std": 0.48408737778663635,
      "step": 414,
      "tools/generated_tokens": 1174.162109375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.212890625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2036.0,
      "completions/mean_length": 1143.34765625,
      "completions/mean_terminated_length": 898.6649780273438,
      "completions/min_length": 270.0,
      "completions/min_terminated_length": 270.0,
      "epoch": 0.2945351312987935,
      "frac_reward_zero_std": 0.125,
      "grad_norm": 0.7987658977508545,
      "learning_rate": 1.7199999999999998e-07,
      "loss": 0.0706,
      "num_tokens": 523772177.0,
      "reward": 0.46875,
      "reward_std": 0.3934553265571594,
      "rewards/simpleverify_reward/mean": 0.46875,
      "rewards/simpleverify_reward/std": 0.4995105266571045,
      "step": 415,
      "tools/generated_tokens": 1143.4296875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.318359375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2035.0,
      "completions/mean_length": 1329.2265625,
      "completions/mean_terminated_length": 993.5244140625,
      "completions/min_length": 209.0,
      "completions/min_terminated_length": 209.0,
      "epoch": 0.29524485450674237,
      "frac_reward_zero_std": 0.4375,
      "grad_norm": 0.6266219019889832,
      "learning_rate": 1.7000000000000001e-07,
      "loss": 0.0375,
      "num_tokens": 524947253.0,
      "reward": 0.376953125,
      "reward_std": 0.24642425775527954,
      "rewards/simpleverify_reward/mean": 0.376953125,
      "rewards/simpleverify_reward/std": 0.4850969910621643,
      "step": 416,
      "tools/generated_tokens": 1329.46875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.20703125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2002.0,
      "completions/mean_length": 1041.603515625,
      "completions/mean_terminated_length": 778.8546752929688,
      "completions/min_length": 198.0,
      "completions/min_terminated_length": 198.0,
      "epoch": 0.29595457771469125,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.8554182052612305,
      "learning_rate": 1.68e-07,
      "loss": 0.0128,
      "num_tokens": 525968009.0,
      "reward": 0.4609375,
      "reward_std": 0.2844626307487488,
      "rewards/simpleverify_reward/mean": 0.4609375,
      "rewards/simpleverify_reward/std": 0.4989593029022217,
      "step": 417,
      "tools/generated_tokens": 1044.634765625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.009765625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.23828125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2038.0,
      "completions/mean_length": 1167.412109375,
      "completions/mean_terminated_length": 891.9461669921875,
      "completions/min_length": 218.0,
      "completions/min_terminated_length": 218.0,
      "epoch": 0.2966643009226402,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 1.041237473487854,
      "learning_rate": 1.66e-07,
      "loss": 0.0499,
      "num_tokens": 527055013.0,
      "reward": 0.3515625,
      "reward_std": 0.27507874369621277,
      "rewards/simpleverify_reward/mean": 0.3515625,
      "rewards/simpleverify_reward/std": 0.4779251217842102,
      "step": 418,
      "tools/generated_tokens": 1168.498046875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.318359375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1289.0703125,
      "completions/mean_terminated_length": 934.6132202148438,
      "completions/min_length": 208.0,
      "completions/min_terminated_length": 208.0,
      "epoch": 0.29737402413058905,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.6660295724868774,
      "learning_rate": 1.64e-07,
      "loss": 0.0463,
      "num_tokens": 528208657.0,
      "reward": 0.341796875,
      "reward_std": 0.2558779716491699,
      "rewards/simpleverify_reward/mean": 0.341796875,
      "rewards/simpleverify_reward/std": 0.4747757613658905,
      "step": 419,
      "tools/generated_tokens": 1291.103515625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.001953125
    },
    {
      "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": 0.265625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1269.568359375,
      "completions/mean_terminated_length": 988.0079345703125,
      "completions/min_length": 146.0,
      "completions/min_terminated_length": 146.0,
      "epoch": 0.298083747338538,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.6993208527565002,
      "learning_rate": 1.62e-07,
      "loss": 0.0542,
      "num_tokens": 529340388.0,
      "reward": 0.373046875,
      "reward_std": 0.3554404377937317,
      "rewards/simpleverify_reward/mean": 0.373046875,
      "rewards/simpleverify_reward/std": 0.48408737778663635,
      "step": 420,
      "tools/generated_tokens": 1269.673828125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.26171875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1265.421875,
      "completions/mean_terminated_length": 988.0,
      "completions/min_length": 122.0,
      "completions/min_terminated_length": 122.0,
      "epoch": 0.29879347054648686,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.7926800847053528,
      "learning_rate": 1.6e-07,
      "loss": 0.0587,
      "num_tokens": 530471596.0,
      "reward": 0.396484375,
      "reward_std": 0.3082372546195984,
      "rewards/simpleverify_reward/mean": 0.396484375,
      "rewards/simpleverify_reward/std": 0.4896455705165863,
      "step": 421,
      "tools/generated_tokens": 1265.51953125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.25390625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2020.0,
      "completions/mean_length": 1144.283203125,
      "completions/mean_terminated_length": 836.735595703125,
      "completions/min_length": 218.0,
      "completions/min_terminated_length": 218.0,
      "epoch": 0.2995031937544358,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.6528905034065247,
      "learning_rate": 1.5799999999999999e-07,
      "loss": 0.0642,
      "num_tokens": 531544869.0,
      "reward": 0.416015625,
      "reward_std": 0.2973790764808655,
      "rewards/simpleverify_reward/mean": 0.416015625,
      "rewards/simpleverify_reward/std": 0.493378221988678,
      "step": 422,
      "tools/generated_tokens": 1145.529296875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.275390625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2027.0,
      "completions/mean_length": 1199.36328125,
      "completions/mean_terminated_length": 876.8355712890625,
      "completions/min_length": 167.0,
      "completions/min_terminated_length": 167.0,
      "epoch": 0.30021291696238467,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.6907066106796265,
      "learning_rate": 1.56e-07,
      "loss": 0.049,
      "num_tokens": 532650994.0,
      "reward": 0.388671875,
      "reward_std": 0.303730845451355,
      "rewards/simpleverify_reward/mean": 0.388671875,
      "rewards/simpleverify_reward/std": 0.4879252314567566,
      "step": 423,
      "tools/generated_tokens": 1201.12890625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0078125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2030.0,
      "completions/mean_length": 1243.09375,
      "completions/mean_terminated_length": 903.2444458007812,
      "completions/min_length": 188.0,
      "completions/min_terminated_length": 188.0,
      "epoch": 0.30092264017033354,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.6291918754577637,
      "learning_rate": 1.54e-07,
      "loss": 0.0654,
      "num_tokens": 533781329.0,
      "reward": 0.376953125,
      "reward_std": 0.3115488886833191,
      "rewards/simpleverify_reward/mean": 0.376953125,
      "rewards/simpleverify_reward/std": 0.4850969910621643,
      "step": 424,
      "tools/generated_tokens": 1244.431640625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.318359375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2032.0,
      "completions/mean_length": 1429.369140625,
      "completions/mean_terminated_length": 1140.4384765625,
      "completions/min_length": 328.0,
      "completions/min_terminated_length": 328.0,
      "epoch": 0.3016323633782825,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.6000931262969971,
      "learning_rate": 1.5199999999999998e-07,
      "loss": 0.0297,
      "num_tokens": 535004110.0,
      "reward": 0.38671875,
      "reward_std": 0.34190401434898376,
      "rewards/simpleverify_reward/mean": 0.38671875,
      "rewards/simpleverify_reward/std": 0.48747459053993225,
      "step": 425,
      "tools/generated_tokens": 1429.529296875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.291015625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1273.5625,
      "completions/mean_terminated_length": 955.6804809570312,
      "completions/min_length": 216.0,
      "completions/min_terminated_length": 216.0,
      "epoch": 0.30234208658623135,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 7.326871871948242,
      "learning_rate": 1.5e-07,
      "loss": 0.0596,
      "num_tokens": 536144122.0,
      "reward": 0.451171875,
      "reward_std": 0.3173927068710327,
      "rewards/simpleverify_reward/mean": 0.451171875,
      "rewards/simpleverify_reward/std": 0.498096764087677,
      "step": 426,
      "tools/generated_tokens": 1272.123046875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.00390625
    },
    {
      "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": 0.279296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1271.421875,
      "completions/mean_terminated_length": 970.4715576171875,
      "completions/min_length": 181.0,
      "completions/min_terminated_length": 181.0,
      "epoch": 0.3030518097941803,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.6980746984481812,
      "learning_rate": 1.4799999999999998e-07,
      "loss": 0.0371,
      "num_tokens": 537281762.0,
      "reward": 0.4140625,
      "reward_std": 0.33930712938308716,
      "rewards/simpleverify_reward/mean": 0.4140625,
      "rewards/simpleverify_reward/std": 0.49304109811782837,
      "step": 427,
      "tools/generated_tokens": 1271.5390625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.314453125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2038.0,
      "completions/mean_length": 1305.5,
      "completions/mean_terminated_length": 964.923095703125,
      "completions/min_length": 226.0,
      "completions/min_terminated_length": 226.0,
      "epoch": 0.30376153300212916,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.6822951436042786,
      "learning_rate": 1.4599999999999998e-07,
      "loss": 0.0361,
      "num_tokens": 538433000.0,
      "reward": 0.46875,
      "reward_std": 0.29888269305229187,
      "rewards/simpleverify_reward/mean": 0.46875,
      "rewards/simpleverify_reward/std": 0.4995105266571045,
      "step": 428,
      "tools/generated_tokens": 1305.73046875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.23046875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2039.0,
      "completions/mean_length": 1207.9296875,
      "completions/mean_terminated_length": 956.3350219726562,
      "completions/min_length": 251.0,
      "completions/min_terminated_length": 251.0,
      "epoch": 0.3044712562100781,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.7300967574119568,
      "learning_rate": 1.44e-07,
      "loss": 0.0359,
      "num_tokens": 539541704.0,
      "reward": 0.4140625,
      "reward_std": 0.35101553797721863,
      "rewards/simpleverify_reward/mean": 0.4140625,
      "rewards/simpleverify_reward/std": 0.49304109811782837,
      "step": 429,
      "tools/generated_tokens": 1210.775390625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.41015625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2029.0,
      "completions/mean_length": 1430.708984375,
      "completions/mean_terminated_length": 1001.4668579101562,
      "completions/min_length": 185.0,
      "completions/min_terminated_length": 185.0,
      "epoch": 0.30518097941802697,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.6016764640808105,
      "learning_rate": 1.4199999999999997e-07,
      "loss": 0.057,
      "num_tokens": 540772947.0,
      "reward": 0.3828125,
      "reward_std": 0.2952210009098053,
      "rewards/simpleverify_reward/mean": 0.3828125,
      "rewards/simpleverify_reward/std": 0.486548513174057,
      "step": 430,
      "tools/generated_tokens": 1430.841796875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.2734375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1203.65234375,
      "completions/mean_terminated_length": 885.8870849609375,
      "completions/min_length": 284.0,
      "completions/min_terminated_length": 284.0,
      "epoch": 0.3058907026259759,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.6592767834663391,
      "learning_rate": 1.4e-07,
      "loss": 0.0415,
      "num_tokens": 541873009.0,
      "reward": 0.318359375,
      "reward_std": 0.27588266134262085,
      "rewards/simpleverify_reward/mean": 0.318359375,
      "rewards/simpleverify_reward/std": 0.46629536151885986,
      "step": 431,
      "tools/generated_tokens": 1203.830078125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1299.943359375,
      "completions/mean_terminated_length": 984.0972290039062,
      "completions/min_length": 186.0,
      "completions/min_terminated_length": 186.0,
      "epoch": 0.3066004258339248,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.7302961945533752,
      "learning_rate": 1.3800000000000002e-07,
      "loss": 0.0414,
      "num_tokens": 543035361.0,
      "reward": 0.33984375,
      "reward_std": 0.3077436089515686,
      "rewards/simpleverify_reward/mean": 0.33984375,
      "rewards/simpleverify_reward/std": 0.4741191864013672,
      "step": 432,
      "tools/generated_tokens": 1302.052734375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.197265625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2035.0,
      "completions/mean_length": 1108.2265625,
      "completions/mean_terminated_length": 877.28466796875,
      "completions/min_length": 175.0,
      "completions/min_terminated_length": 175.0,
      "epoch": 0.30731014904187365,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.725911021232605,
      "learning_rate": 1.36e-07,
      "loss": 0.0424,
      "num_tokens": 544085221.0,
      "reward": 0.54296875,
      "reward_std": 0.2770131230354309,
      "rewards/simpleverify_reward/mean": 0.54296875,
      "rewards/simpleverify_reward/std": 0.49863746762275696,
      "step": 433,
      "tools/generated_tokens": 1108.3203125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.310546875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2035.0,
      "completions/mean_length": 1269.900390625,
      "completions/mean_terminated_length": 919.4249267578125,
      "completions/min_length": 172.0,
      "completions/min_terminated_length": 172.0,
      "epoch": 0.3080198722498226,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.742814302444458,
      "learning_rate": 1.34e-07,
      "loss": 0.0827,
      "num_tokens": 545217714.0,
      "reward": 0.400390625,
      "reward_std": 0.33378589153289795,
      "rewards/simpleverify_reward/mean": 0.400390625,
      "rewards/simpleverify_reward/std": 0.4904567301273346,
      "step": 434,
      "tools/generated_tokens": 1269.9765625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.2265625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2037.0,
      "completions/mean_length": 1234.173828125,
      "completions/mean_terminated_length": 995.7802734375,
      "completions/min_length": 199.0,
      "completions/min_terminated_length": 199.0,
      "epoch": 0.30872959545777146,
      "frac_reward_zero_std": 0.09375,
      "grad_norm": 0.7725135087966919,
      "learning_rate": 1.32e-07,
      "loss": 0.0697,
      "num_tokens": 546339675.0,
      "reward": 0.435546875,
      "reward_std": 0.37313446402549744,
      "rewards/simpleverify_reward/mean": 0.435546875,
      "rewards/simpleverify_reward/std": 0.49631330370903015,
      "step": 435,
      "tools/generated_tokens": 1234.328125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.279296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1266.224609375,
      "completions/mean_terminated_length": 963.2601928710938,
      "completions/min_length": 204.0,
      "completions/min_terminated_length": 204.0,
      "epoch": 0.3094393186657204,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.6177472472190857,
      "learning_rate": 1.3e-07,
      "loss": 0.0481,
      "num_tokens": 547472206.0,
      "reward": 0.439453125,
      "reward_std": 0.29626578092575073,
      "rewards/simpleverify_reward/mean": 0.439453125,
      "rewards/simpleverify_reward/std": 0.49680593609809875,
      "step": 436,
      "tools/generated_tokens": 1266.359375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.19921875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2025.0,
      "completions/mean_length": 1155.3125,
      "completions/mean_terminated_length": 933.231689453125,
      "completions/min_length": 182.0,
      "completions/min_terminated_length": 182.0,
      "epoch": 0.31014904187366926,
      "frac_reward_zero_std": 0.125,
      "grad_norm": 0.807860791683197,
      "learning_rate": 1.28e-07,
      "loss": 0.0764,
      "num_tokens": 548551982.0,
      "reward": 0.419921875,
      "reward_std": 0.35567137598991394,
      "rewards/simpleverify_reward/mean": 0.419921875,
      "rewards/simpleverify_reward/std": 0.4940285086631775,
      "step": 437,
      "tools/generated_tokens": 1155.427734375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.310546875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1303.818359375,
      "completions/mean_terminated_length": 968.620361328125,
      "completions/min_length": 279.0,
      "completions/min_terminated_length": 279.0,
      "epoch": 0.3108587650816182,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.7790530920028687,
      "learning_rate": 1.26e-07,
      "loss": 0.0376,
      "num_tokens": 549699905.0,
      "reward": 0.427734375,
      "reward_std": 0.33594679832458496,
      "rewards/simpleverify_reward/mean": 0.427734375,
      "rewards/simpleverify_reward/std": 0.4952339828014374,
      "step": 438,
      "tools/generated_tokens": 1303.9609375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.28125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2023.0,
      "completions/mean_length": 1230.748046875,
      "completions/mean_terminated_length": 910.9537963867188,
      "completions/min_length": 246.0,
      "completions/min_terminated_length": 246.0,
      "epoch": 0.31156848828956707,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.6871810555458069,
      "learning_rate": 1.24e-07,
      "loss": 0.0605,
      "num_tokens": 550824282.0,
      "reward": 0.361328125,
      "reward_std": 0.3441922962665558,
      "rewards/simpleverify_reward/mean": 0.361328125,
      "rewards/simpleverify_reward/std": 0.48085519671440125,
      "step": 439,
      "tools/generated_tokens": 1235.84765625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.009765625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.22265625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2038.0,
      "completions/mean_length": 1091.513671875,
      "completions/mean_terminated_length": 817.5452270507812,
      "completions/min_length": 151.0,
      "completions/min_terminated_length": 151.0,
      "epoch": 0.31227821149751595,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.7541882991790771,
      "learning_rate": 1.2199999999999998e-07,
      "loss": 0.0348,
      "num_tokens": 551872922.0,
      "reward": 0.427734375,
      "reward_std": 0.2846006751060486,
      "rewards/simpleverify_reward/mean": 0.427734375,
      "rewards/simpleverify_reward/std": 0.4952339828014374,
      "step": 440,
      "tools/generated_tokens": 1092.44921875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.37890625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2031.0,
      "completions/mean_length": 1393.935546875,
      "completions/mean_terminated_length": 994.9150390625,
      "completions/min_length": 163.0,
      "completions/min_terminated_length": 163.0,
      "epoch": 0.3129879347054649,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 0.5526400208473206,
      "learning_rate": 1.2e-07,
      "loss": 0.0445,
      "num_tokens": 553092067.0,
      "reward": 0.30078125,
      "reward_std": 0.25675168633461,
      "rewards/simpleverify_reward/mean": 0.30078125,
      "rewards/simpleverify_reward/std": 0.45904624462127686,
      "step": 441,
      "tools/generated_tokens": 1398.017578125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.025390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.001953125
    },
    {
      "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": 0.306640625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1311.18359375,
      "completions/mean_terminated_length": 985.3239135742188,
      "completions/min_length": 171.0,
      "completions/min_terminated_length": 171.0,
      "epoch": 0.31369765791341375,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.6232791543006897,
      "learning_rate": 1.1799999999999998e-07,
      "loss": 0.0442,
      "num_tokens": 554252225.0,
      "reward": 0.275390625,
      "reward_std": 0.29165229201316833,
      "rewards/simpleverify_reward/mean": 0.275390625,
      "rewards/simpleverify_reward/std": 0.44714778661727905,
      "step": 442,
      "tools/generated_tokens": 1311.3203125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.1796875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2013.0,
      "completions/mean_length": 1140.326171875,
      "completions/mean_terminated_length": 941.5048217773438,
      "completions/min_length": 242.0,
      "completions/min_terminated_length": 242.0,
      "epoch": 0.3144073811213627,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.7834530472755432,
      "learning_rate": 1.16e-07,
      "loss": 0.0361,
      "num_tokens": 555332184.0,
      "reward": 0.451171875,
      "reward_std": 0.3605419993400574,
      "rewards/simpleverify_reward/mean": 0.451171875,
      "rewards/simpleverify_reward/std": 0.498096764087677,
      "step": 443,
      "tools/generated_tokens": 1140.5234375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.1875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2035.0,
      "completions/mean_length": 1104.4921875,
      "completions/mean_terminated_length": 886.7740478515625,
      "completions/min_length": 204.0,
      "completions/min_terminated_length": 204.0,
      "epoch": 0.31511710432931156,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.7379464507102966,
      "learning_rate": 1.14e-07,
      "loss": 0.0214,
      "num_tokens": 556385012.0,
      "reward": 0.46875,
      "reward_std": 0.3311811685562134,
      "rewards/simpleverify_reward/mean": 0.46875,
      "rewards/simpleverify_reward/std": 0.4995105266571045,
      "step": 444,
      "tools/generated_tokens": 1107.47265625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.314453125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2034.0,
      "completions/mean_length": 1370.72265625,
      "completions/mean_terminated_length": 1060.0626220703125,
      "completions/min_length": 242.0,
      "completions/min_terminated_length": 242.0,
      "epoch": 0.3158268275372605,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.6513476371765137,
      "learning_rate": 1.12e-07,
      "loss": 0.0429,
      "num_tokens": 557577635.0,
      "reward": 0.365234375,
      "reward_std": 0.35505953431129456,
      "rewards/simpleverify_reward/mean": 0.365234375,
      "rewards/simpleverify_reward/std": 0.4819667339324951,
      "step": 445,
      "tools/generated_tokens": 1375.34375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.27734375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2031.0,
      "completions/mean_length": 1237.794921875,
      "completions/mean_terminated_length": 926.8513793945312,
      "completions/min_length": 184.0,
      "completions/min_terminated_length": 184.0,
      "epoch": 0.31653655074520937,
      "frac_reward_zero_std": 0.40625,
      "grad_norm": 0.6375740766525269,
      "learning_rate": 1.0999999999999999e-07,
      "loss": 0.0452,
      "num_tokens": 558704434.0,
      "reward": 0.4296875,
      "reward_std": 0.2690756320953369,
      "rewards/simpleverify_reward/mean": 0.4296875,
      "rewards/simpleverify_reward/std": 0.4955156147480011,
      "step": 446,
      "tools/generated_tokens": 1240.2109375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.259765625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2040.0,
      "completions/mean_length": 1153.935546875,
      "completions/mean_terminated_length": 840.1873779296875,
      "completions/min_length": 192.0,
      "completions/min_terminated_length": 192.0,
      "epoch": 0.31724627395315824,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.685998260974884,
      "learning_rate": 1.0799999999999999e-07,
      "loss": 0.0684,
      "num_tokens": 559781873.0,
      "reward": 0.48046875,
      "reward_std": 0.2746238112449646,
      "rewards/simpleverify_reward/mean": 0.48046875,
      "rewards/simpleverify_reward/std": 0.5001069903373718,
      "step": 447,
      "tools/generated_tokens": 1154.94921875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.26171875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2037.0,
      "completions/mean_length": 1256.146484375,
      "completions/mean_terminated_length": 975.4364624023438,
      "completions/min_length": 172.0,
      "completions/min_terminated_length": 172.0,
      "epoch": 0.3179559971611072,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.6786825656890869,
      "learning_rate": 1.06e-07,
      "loss": 0.0363,
      "num_tokens": 560916537.0,
      "reward": 0.373046875,
      "reward_std": 0.2889110743999481,
      "rewards/simpleverify_reward/mean": 0.373046875,
      "rewards/simpleverify_reward/std": 0.48408737778663635,
      "step": 448,
      "tools/generated_tokens": 1257.16015625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.28515625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1200.603515625,
      "completions/mean_terminated_length": 862.571044921875,
      "completions/min_length": 75.0,
      "completions/min_terminated_length": 75.0,
      "epoch": 0.31866572036905605,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.7856035828590393,
      "learning_rate": 1.0399999999999999e-07,
      "loss": 0.037,
      "num_tokens": 562019198.0,
      "reward": 0.353515625,
      "reward_std": 0.36861681938171387,
      "rewards/simpleverify_reward/mean": 0.353515625,
      "rewards/simpleverify_reward/std": 0.47852855920791626,
      "step": 449,
      "tools/generated_tokens": 1200.69140625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.390625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1433.099609375,
      "completions/mean_terminated_length": 1038.9327392578125,
      "completions/min_length": 233.0,
      "completions/min_terminated_length": 233.0,
      "epoch": 0.319375443577005,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 4.611087799072266,
      "learning_rate": 1.0199999999999999e-07,
      "loss": 0.0662,
      "num_tokens": 563246250.0,
      "reward": 0.314453125,
      "reward_std": 0.340899258852005,
      "rewards/simpleverify_reward/mean": 0.314453125,
      "rewards/simpleverify_reward/std": 0.4647517800331116,
      "step": 450,
      "tools/generated_tokens": 1431.771484375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.24609375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1214.107421875,
      "completions/mean_terminated_length": 941.9041137695312,
      "completions/min_length": 183.0,
      "completions/min_terminated_length": 183.0,
      "epoch": 0.32008516678495386,
      "frac_reward_zero_std": 0.09375,
      "grad_norm": 0.7868542671203613,
      "learning_rate": 1e-07,
      "loss": 0.0657,
      "num_tokens": 564350449.0,
      "reward": 0.3984375,
      "reward_std": 0.36811816692352295,
      "rewards/simpleverify_reward/mean": 0.3984375,
      "rewards/simpleverify_reward/std": 0.4900552034378052,
      "step": 451,
      "tools/generated_tokens": 1214.326171875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.212890625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1146.498046875,
      "completions/mean_terminated_length": 902.66748046875,
      "completions/min_length": 267.0,
      "completions/min_terminated_length": 267.0,
      "epoch": 0.3207948899929028,
      "frac_reward_zero_std": 0.125,
      "grad_norm": 0.8436964750289917,
      "learning_rate": 9.8e-08,
      "loss": 0.0543,
      "num_tokens": 565426720.0,
      "reward": 0.435546875,
      "reward_std": 0.3603372573852539,
      "rewards/simpleverify_reward/mean": 0.435546875,
      "rewards/simpleverify_reward/std": 0.49631330370903015,
      "step": 452,
      "tools/generated_tokens": 1146.68359375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.224609375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1176.166015625,
      "completions/mean_terminated_length": 923.61962890625,
      "completions/min_length": 172.0,
      "completions/min_terminated_length": 172.0,
      "epoch": 0.32150461320085166,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.7844744920730591,
      "learning_rate": 9.6e-08,
      "loss": 0.0404,
      "num_tokens": 566507525.0,
      "reward": 0.447265625,
      "reward_std": 0.31512391567230225,
      "rewards/simpleverify_reward/mean": 0.447265625,
      "rewards/simpleverify_reward/std": 0.4976975917816162,
      "step": 453,
      "tools/generated_tokens": 1176.2578125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.21875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2041.0,
      "completions/mean_length": 1158.916015625,
      "completions/mean_terminated_length": 909.9724731445312,
      "completions/min_length": 216.0,
      "completions/min_terminated_length": 216.0,
      "epoch": 0.3222143364088006,
      "frac_reward_zero_std": 0.125,
      "grad_norm": 1.0917400121688843,
      "learning_rate": 9.4e-08,
      "loss": 0.0793,
      "num_tokens": 567592392.0,
      "reward": 0.451171875,
      "reward_std": 0.35600733757019043,
      "rewards/simpleverify_reward/mean": 0.451171875,
      "rewards/simpleverify_reward/std": 0.498096764087677,
      "step": 454,
      "tools/generated_tokens": 1162.146484375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.1640625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2039.0,
      "completions/mean_length": 1016.833984375,
      "completions/mean_terminated_length": 814.45556640625,
      "completions/min_length": 153.0,
      "completions/min_terminated_length": 153.0,
      "epoch": 0.32292405961674947,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.715778648853302,
      "learning_rate": 9.199999999999999e-08,
      "loss": 0.0133,
      "num_tokens": 568606826.0,
      "reward": 0.5078125,
      "reward_std": 0.29565417766571045,
      "rewards/simpleverify_reward/mean": 0.5078125,
      "rewards/simpleverify_reward/std": 0.5004279017448425,
      "step": 455,
      "tools/generated_tokens": 1025.078125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0078125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.328125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2000.0,
      "completions/mean_length": 1325.80078125,
      "completions/mean_terminated_length": 973.0988159179688,
      "completions/min_length": 319.0,
      "completions/min_terminated_length": 319.0,
      "epoch": 0.32363378282469835,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.6652244925498962,
      "learning_rate": 9e-08,
      "loss": 0.0563,
      "num_tokens": 569790496.0,
      "reward": 0.373046875,
      "reward_std": 0.35577401518821716,
      "rewards/simpleverify_reward/mean": 0.373046875,
      "rewards/simpleverify_reward/std": 0.48408737778663635,
      "step": 456,
      "tools/generated_tokens": 1334.474609375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.005859375
    },
    {
      "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": 0.31640625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1292.794921875,
      "completions/mean_terminated_length": 943.2428588867188,
      "completions/min_length": 192.0,
      "completions/min_terminated_length": 192.0,
      "epoch": 0.3243435060326473,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.6290222406387329,
      "learning_rate": 8.8e-08,
      "loss": 0.0737,
      "num_tokens": 570945127.0,
      "reward": 0.32421875,
      "reward_std": 0.32689106464385986,
      "rewards/simpleverify_reward/mean": 0.32421875,
      "rewards/simpleverify_reward/std": 0.4685399830341339,
      "step": 457,
      "tools/generated_tokens": 1292.947265625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.318359375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2001.0,
      "completions/mean_length": 1218.984375,
      "completions/mean_terminated_length": 831.793701171875,
      "completions/min_length": 261.0,
      "completions/min_terminated_length": 261.0,
      "epoch": 0.32505322924059615,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.7029735445976257,
      "learning_rate": 8.599999999999999e-08,
      "loss": 0.0548,
      "num_tokens": 572053688.0,
      "reward": 0.421875,
      "reward_std": 0.30872493982315063,
      "rewards/simpleverify_reward/mean": 0.421875,
      "rewards/simpleverify_reward/std": 0.49434176087379456,
      "step": 458,
      "tools/generated_tokens": 1221.34375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.21484375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2017.0,
      "completions/mean_length": 1160.21875,
      "completions/mean_terminated_length": 917.2984619140625,
      "completions/min_length": 203.0,
      "completions/min_terminated_length": 203.0,
      "epoch": 0.3257629524485451,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 8.137350082397461,
      "learning_rate": 8.4e-08,
      "loss": 0.0331,
      "num_tokens": 573152886.0,
      "reward": 0.3671875,
      "reward_std": 0.33988797664642334,
      "rewards/simpleverify_reward/mean": 0.3671875,
      "rewards/simpleverify_reward/std": 0.48250964283943176,
      "step": 459,
      "tools/generated_tokens": 1164.46484375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.01171875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.216796875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2019.0,
      "completions/mean_length": 1171.75,
      "completions/mean_terminated_length": 929.197021484375,
      "completions/min_length": 242.0,
      "completions/min_terminated_length": 242.0,
      "epoch": 0.32647267565649396,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.7571688890457153,
      "learning_rate": 8.2e-08,
      "loss": 0.0345,
      "num_tokens": 574234182.0,
      "reward": 0.3515625,
      "reward_std": 0.3163956105709076,
      "rewards/simpleverify_reward/mean": 0.3515625,
      "rewards/simpleverify_reward/std": 0.4779251217842102,
      "step": 460,
      "tools/generated_tokens": 1171.912109375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.279296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2038.0,
      "completions/mean_length": 1236.38671875,
      "completions/mean_terminated_length": 921.8590698242188,
      "completions/min_length": 197.0,
      "completions/min_terminated_length": 197.0,
      "epoch": 0.3271823988644429,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 0.6279066205024719,
      "learning_rate": 8e-08,
      "loss": 0.0393,
      "num_tokens": 575347356.0,
      "reward": 0.3828125,
      "reward_std": 0.2475813925266266,
      "rewards/simpleverify_reward/mean": 0.3828125,
      "rewards/simpleverify_reward/std": 0.486548513174057,
      "step": 461,
      "tools/generated_tokens": 1236.5234375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.259765625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1185.552734375,
      "completions/mean_terminated_length": 882.8997802734375,
      "completions/min_length": 157.0,
      "completions/min_terminated_length": 157.0,
      "epoch": 0.32789212207239177,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.7574703693389893,
      "learning_rate": 7.8e-08,
      "loss": 0.0314,
      "num_tokens": 576436102.0,
      "reward": 0.47265625,
      "reward_std": 0.3092268705368042,
      "rewards/simpleverify_reward/mean": 0.47265625,
      "rewards/simpleverify_reward/std": 0.49974003434181213,
      "step": 462,
      "tools/generated_tokens": 1187.8984375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2031.0,
      "completions/mean_length": 1243.6328125,
      "completions/mean_terminated_length": 904.013916015625,
      "completions/min_length": 22.0,
      "completions/min_terminated_length": 22.0,
      "epoch": 0.32860184528034064,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.6601927876472473,
      "learning_rate": 7.599999999999999e-08,
      "loss": 0.0356,
      "num_tokens": 577562536.0,
      "reward": 0.298828125,
      "reward_std": 0.2965189218521118,
      "rewards/simpleverify_reward/mean": 0.298828125,
      "rewards/simpleverify_reward/std": 0.45819199085235596,
      "step": 463,
      "tools/generated_tokens": 1244.53125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.25390625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2014.0,
      "completions/mean_length": 1163.708984375,
      "completions/mean_terminated_length": 862.7722778320312,
      "completions/min_length": 1.0,
      "completions/min_terminated_length": 1.0,
      "epoch": 0.3293115684882896,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.7537508606910706,
      "learning_rate": 7.399999999999999e-08,
      "loss": 0.0256,
      "num_tokens": 578654902.0,
      "reward": 0.48046875,
      "reward_std": 0.2643716037273407,
      "rewards/simpleverify_reward/mean": 0.48046875,
      "rewards/simpleverify_reward/std": 0.5001069903373718,
      "step": 464,
      "tools/generated_tokens": 1164.888671875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.318359375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1179.8046875,
      "completions/mean_terminated_length": 774.315185546875,
      "completions/min_length": 97.0,
      "completions/min_terminated_length": 97.0,
      "epoch": 0.33002129169623845,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.6534639596939087,
      "learning_rate": 7.2e-08,
      "loss": 0.0309,
      "num_tokens": 579752242.0,
      "reward": 0.37890625,
      "reward_std": 0.23508894443511963,
      "rewards/simpleverify_reward/mean": 0.37890625,
      "rewards/simpleverify_reward/std": 0.4855891764163971,
      "step": 465,
      "tools/generated_tokens": 1179.8828125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.279296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2040.0,
      "completions/mean_length": 1285.98828125,
      "completions/mean_terminated_length": 990.6829223632812,
      "completions/min_length": 160.0,
      "completions/min_terminated_length": 160.0,
      "epoch": 0.3307310149041874,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.7492855191230774,
      "learning_rate": 7e-08,
      "loss": 0.0268,
      "num_tokens": 580902335.0,
      "reward": 0.3515625,
      "reward_std": 0.36798202991485596,
      "rewards/simpleverify_reward/mean": 0.3515625,
      "rewards/simpleverify_reward/std": 0.4779251217842102,
      "step": 466,
      "tools/generated_tokens": 1287.521484375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.333984375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1335.279296875,
      "completions/mean_terminated_length": 977.8739013671875,
      "completions/min_length": 184.0,
      "completions/min_terminated_length": 184.0,
      "epoch": 0.33144073811213626,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.7209360003471375,
      "learning_rate": 6.8e-08,
      "loss": 0.079,
      "num_tokens": 582070121.0,
      "reward": 0.404296875,
      "reward_std": 0.3230496644973755,
      "rewards/simpleverify_reward/mean": 0.404296875,
      "rewards/simpleverify_reward/std": 0.4912354052066803,
      "step": 467,
      "tools/generated_tokens": 1337.791015625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.30078125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1322.900390625,
      "completions/mean_terminated_length": 1010.9860229492188,
      "completions/min_length": 146.0,
      "completions/min_terminated_length": 146.0,
      "epoch": 0.3321504613200852,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.738075852394104,
      "learning_rate": 6.6e-08,
      "loss": 0.0427,
      "num_tokens": 583237190.0,
      "reward": 0.373046875,
      "reward_std": 0.322451651096344,
      "rewards/simpleverify_reward/mean": 0.373046875,
      "rewards/simpleverify_reward/std": 0.48408737778663635,
      "step": 468,
      "tools/generated_tokens": 1323.052734375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.21875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1149.7109375,
      "completions/mean_terminated_length": 898.1900024414062,
      "completions/min_length": 172.0,
      "completions/min_terminated_length": 172.0,
      "epoch": 0.33286018452803406,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.8020686507225037,
      "learning_rate": 6.4e-08,
      "loss": 0.0554,
      "num_tokens": 584318130.0,
      "reward": 0.435546875,
      "reward_std": 0.35014182329177856,
      "rewards/simpleverify_reward/mean": 0.435546875,
      "rewards/simpleverify_reward/std": 0.49631330370903015,
      "step": 469,
      "tools/generated_tokens": 1149.919921875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.380859375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2036.0,
      "completions/mean_length": 1411.353515625,
      "completions/mean_terminated_length": 1019.7255859375,
      "completions/min_length": 197.0,
      "completions/min_terminated_length": 197.0,
      "epoch": 0.33356990773598294,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.5665439367294312,
      "learning_rate": 6.2e-08,
      "loss": 0.0315,
      "num_tokens": 585536963.0,
      "reward": 0.30859375,
      "reward_std": 0.2557433247566223,
      "rewards/simpleverify_reward/mean": 0.30859375,
      "rewards/simpleverify_reward/std": 0.4623647928237915,
      "step": 470,
      "tools/generated_tokens": 1412.29296875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.26171875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1259.83203125,
      "completions/mean_terminated_length": 980.4285278320312,
      "completions/min_length": 225.0,
      "completions/min_terminated_length": 225.0,
      "epoch": 0.33427963094393187,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.7590119242668152,
      "learning_rate": 6e-08,
      "loss": 0.0303,
      "num_tokens": 586674168.0,
      "reward": 0.390625,
      "reward_std": 0.3632587790489197,
      "rewards/simpleverify_reward/mean": 0.390625,
      "rewards/simpleverify_reward/std": 0.48836761713027954,
      "step": 471,
      "tools/generated_tokens": 1260.732421875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.279296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2041.0,
      "completions/mean_length": 1274.787109375,
      "completions/mean_terminated_length": 975.1409301757812,
      "completions/min_length": 198.0,
      "completions/min_terminated_length": 198.0,
      "epoch": 0.33498935415188075,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.6527867317199707,
      "learning_rate": 5.8e-08,
      "loss": 0.027,
      "num_tokens": 587812283.0,
      "reward": 0.3515625,
      "reward_std": 0.28547048568725586,
      "rewards/simpleverify_reward/mean": 0.3515625,
      "rewards/simpleverify_reward/std": 0.4779251217842102,
      "step": 472,
      "tools/generated_tokens": 1274.921875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.26171875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2035.0,
      "completions/mean_length": 1202.18359375,
      "completions/mean_terminated_length": 902.3491821289062,
      "completions/min_length": 246.0,
      "completions/min_terminated_length": 246.0,
      "epoch": 0.3356990773598297,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.6650018095970154,
      "learning_rate": 5.6e-08,
      "loss": 0.0112,
      "num_tokens": 588914138.0,
      "reward": 0.357421875,
      "reward_std": 0.294342041015625,
      "rewards/simpleverify_reward/mean": 0.357421875,
      "rewards/simpleverify_reward/std": 0.4797092080116272,
      "step": 473,
      "tools/generated_tokens": 1205.849609375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.18359375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2042.0,
      "completions/mean_length": 1140.482421875,
      "completions/mean_terminated_length": 936.3994750976562,
      "completions/min_length": 199.0,
      "completions/min_terminated_length": 199.0,
      "epoch": 0.33640880056777855,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.7834558486938477,
      "learning_rate": 5.3999999999999994e-08,
      "loss": 0.049,
      "num_tokens": 589978433.0,
      "reward": 0.470703125,
      "reward_std": 0.3193378448486328,
      "rewards/simpleverify_reward/mean": 0.470703125,
      "rewards/simpleverify_reward/std": 0.49962911009788513,
      "step": 474,
      "tools/generated_tokens": 1140.677734375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.302734375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2029.0,
      "completions/mean_length": 1281.373046875,
      "completions/mean_terminated_length": 948.5406494140625,
      "completions/min_length": 126.0,
      "completions/min_terminated_length": 126.0,
      "epoch": 0.3371185237757275,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 2.444260597229004,
      "learning_rate": 5.1999999999999996e-08,
      "loss": 0.051,
      "num_tokens": 591126171.0,
      "reward": 0.369140625,
      "reward_std": 0.2803192138671875,
      "rewards/simpleverify_reward/mean": 0.369140625,
      "rewards/simpleverify_reward/std": 0.4830440282821655,
      "step": 475,
      "tools/generated_tokens": 1279.880859375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.009765625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.181640625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2037.0,
      "completions/mean_length": 974.8828125,
      "completions/mean_terminated_length": 736.6993408203125,
      "completions/min_length": 130.0,
      "completions/min_terminated_length": 130.0,
      "epoch": 0.33782824698367636,
      "frac_reward_zero_std": 0.40625,
      "grad_norm": 0.8360289931297302,
      "learning_rate": 5e-08,
      "loss": 0.0344,
      "num_tokens": 592109183.0,
      "reward": 0.45703125,
      "reward_std": 0.2039102017879486,
      "rewards/simpleverify_reward/mean": 0.45703125,
      "rewards/simpleverify_reward/std": 0.49863746762275696,
      "step": 476,
      "tools/generated_tokens": 975.087890625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.28125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2035.0,
      "completions/mean_length": 1243.5,
      "completions/mean_terminated_length": 928.6956787109375,
      "completions/min_length": 174.0,
      "completions/min_terminated_length": 174.0,
      "epoch": 0.3385379701916253,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.8137232065200806,
      "learning_rate": 4.8e-08,
      "loss": 0.0596,
      "num_tokens": 593242877.0,
      "reward": 0.41796875,
      "reward_std": 0.3309957683086395,
      "rewards/simpleverify_reward/mean": 0.41796875,
      "rewards/simpleverify_reward/std": 0.4937073290348053,
      "step": 477,
      "tools/generated_tokens": 1244.5703125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.267578125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2029.0,
      "completions/mean_length": 1198.3359375,
      "completions/mean_terminated_length": 887.927978515625,
      "completions/min_length": 202.0,
      "completions/min_terminated_length": 202.0,
      "epoch": 0.33924769339957417,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.7721689939498901,
      "learning_rate": 4.5999999999999995e-08,
      "loss": 0.0286,
      "num_tokens": 594344809.0,
      "reward": 0.330078125,
      "reward_std": 0.30406349897384644,
      "rewards/simpleverify_reward/mean": 0.330078125,
      "rewards/simpleverify_reward/std": 0.47070086002349854,
      "step": 478,
      "tools/generated_tokens": 1198.40234375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.3046875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2016.0,
      "completions/mean_length": 1244.890625,
      "completions/mean_terminated_length": 892.96630859375,
      "completions/min_length": 256.0,
      "completions/min_terminated_length": 256.0,
      "epoch": 0.33995741660752304,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.6058586239814758,
      "learning_rate": 4.4e-08,
      "loss": 0.0487,
      "num_tokens": 595470037.0,
      "reward": 0.328125,
      "reward_std": 0.29110032320022583,
      "rewards/simpleverify_reward/mean": 0.328125,
      "rewards/simpleverify_reward/std": 0.4699897766113281,
      "step": 479,
      "tools/generated_tokens": 1245.609375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.255859375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2036.0,
      "completions/mean_length": 1188.08203125,
      "completions/mean_terminated_length": 892.4146728515625,
      "completions/min_length": 125.0,
      "completions/min_terminated_length": 125.0,
      "epoch": 0.340667139815472,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.7383036613464355,
      "learning_rate": 4.2e-08,
      "loss": 0.0531,
      "num_tokens": 596559535.0,
      "reward": 0.41015625,
      "reward_std": 0.3195435404777527,
      "rewards/simpleverify_reward/mean": 0.41015625,
      "rewards/simpleverify_reward/std": 0.49234291911125183,
      "step": 480,
      "tools/generated_tokens": 1188.224609375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.236328125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1177.24609375,
      "completions/mean_terminated_length": 907.780029296875,
      "completions/min_length": 212.0,
      "completions/min_terminated_length": 212.0,
      "epoch": 0.34137686302342085,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.7642154693603516,
      "learning_rate": 4e-08,
      "loss": 0.049,
      "num_tokens": 597644749.0,
      "reward": 0.412109375,
      "reward_std": 0.35182395577430725,
      "rewards/simpleverify_reward/mean": 0.412109375,
      "rewards/simpleverify_reward/std": 0.49269601702690125,
      "step": 481,
      "tools/generated_tokens": 1177.322265625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.2734375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2033.0,
      "completions/mean_length": 1249.80859375,
      "completions/mean_terminated_length": 949.4140014648438,
      "completions/min_length": 188.0,
      "completions/min_terminated_length": 188.0,
      "epoch": 0.3420865862313698,
      "frac_reward_zero_std": 0.15625,
      "grad_norm": 0.744307816028595,
      "learning_rate": 3.7999999999999996e-08,
      "loss": 0.0341,
      "num_tokens": 598767739.0,
      "reward": 0.26953125,
      "reward_std": 0.3366055488586426,
      "rewards/simpleverify_reward/mean": 0.26953125,
      "rewards/simpleverify_reward/std": 0.44415023922920227,
      "step": 482,
      "tools/generated_tokens": 1249.896484375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.212890625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2031.0,
      "completions/mean_length": 1137.330078125,
      "completions/mean_terminated_length": 891.0198364257812,
      "completions/min_length": 1.0,
      "completions/min_terminated_length": 1.0,
      "epoch": 0.34279630943931866,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.7181747555732727,
      "learning_rate": 3.6e-08,
      "loss": 0.0487,
      "num_tokens": 599831758.0,
      "reward": 0.33203125,
      "reward_std": 0.3370566964149475,
      "rewards/simpleverify_reward/mean": 0.33203125,
      "rewards/simpleverify_reward/std": 0.47140273451805115,
      "step": 483,
      "tools/generated_tokens": 1141.1015625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.00390625,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.314453125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1300.79296875,
      "completions/mean_terminated_length": 958.0569458007812,
      "completions/min_length": 197.0,
      "completions/min_terminated_length": 197.0,
      "epoch": 0.3435060326472676,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.6568207740783691,
      "learning_rate": 3.4e-08,
      "loss": 0.0267,
      "num_tokens": 600986644.0,
      "reward": 0.2890625,
      "reward_std": 0.24453887343406677,
      "rewards/simpleverify_reward/mean": 0.2890625,
      "rewards/simpleverify_reward/std": 0.45377036929130554,
      "step": 484,
      "tools/generated_tokens": 1300.900390625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.25,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1125.740234375,
      "completions/mean_terminated_length": 818.3203125,
      "completions/min_length": 156.0,
      "completions/min_terminated_length": 156.0,
      "epoch": 0.34421575585521647,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.8363790512084961,
      "learning_rate": 3.2e-08,
      "loss": 0.0388,
      "num_tokens": 602048671.0,
      "reward": 0.369140625,
      "reward_std": 0.3437926769256592,
      "rewards/simpleverify_reward/mean": 0.369140625,
      "rewards/simpleverify_reward/std": 0.4830440282821655,
      "step": 485,
      "tools/generated_tokens": 1125.84765625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.27734375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2046.0,
      "completions/mean_length": 1169.583984375,
      "completions/mean_terminated_length": 832.462158203125,
      "completions/min_length": 188.0,
      "completions/min_terminated_length": 188.0,
      "epoch": 0.34492547906316534,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.7112640142440796,
      "learning_rate": 3e-08,
      "loss": 0.058,
      "num_tokens": 603132701.0,
      "reward": 0.443359375,
      "reward_std": 0.266493558883667,
      "rewards/simpleverify_reward/mean": 0.443359375,
      "rewards/simpleverify_reward/std": 0.49726733565330505,
      "step": 486,
      "tools/generated_tokens": 1170.25,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.287109375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2039.0,
      "completions/mean_length": 1218.328125,
      "completions/mean_terminated_length": 884.1863403320312,
      "completions/min_length": 162.0,
      "completions/min_terminated_length": 162.0,
      "epoch": 0.3456352022711143,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.8249945044517517,
      "learning_rate": 2.8e-08,
      "loss": 0.0737,
      "num_tokens": 604250709.0,
      "reward": 0.400390625,
      "reward_std": 0.3163902759552002,
      "rewards/simpleverify_reward/mean": 0.400390625,
      "rewards/simpleverify_reward/std": 0.4904567301273346,
      "step": 487,
      "tools/generated_tokens": 1219.810546875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.255859375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2047.0,
      "completions/mean_length": 1314.576171875,
      "completions/mean_terminated_length": 1062.401611328125,
      "completions/min_length": 1.0,
      "completions/min_terminated_length": 1.0,
      "epoch": 0.34634492547906315,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.6430212259292603,
      "learning_rate": 2.5999999999999998e-08,
      "loss": 0.0317,
      "num_tokens": 605410044.0,
      "reward": 0.353515625,
      "reward_std": 0.34115731716156006,
      "rewards/simpleverify_reward/mean": 0.353515625,
      "rewards/simpleverify_reward/std": 0.47852855920791626,
      "step": 488,
      "tools/generated_tokens": 1314.712890625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.330078125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2041.0,
      "completions/mean_length": 1296.150390625,
      "completions/mean_terminated_length": 925.70556640625,
      "completions/min_length": 148.0,
      "completions/min_terminated_length": 148.0,
      "epoch": 0.3470546486870121,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.6434535980224609,
      "learning_rate": 2.4e-08,
      "loss": 0.0376,
      "num_tokens": 606569207.0,
      "reward": 0.3359375,
      "reward_std": 0.27647560834884644,
      "rewards/simpleverify_reward/mean": 0.3359375,
      "rewards/simpleverify_reward/std": 0.4727790653705597,
      "step": 489,
      "tools/generated_tokens": 1301.6484375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.013671875,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.35546875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1357.75390625,
      "completions/mean_terminated_length": 977.0726928710938,
      "completions/min_length": 185.0,
      "completions/min_terminated_length": 185.0,
      "epoch": 0.34776437189496096,
      "frac_reward_zero_std": 0.40625,
      "grad_norm": 0.5409228801727295,
      "learning_rate": 2.2e-08,
      "loss": 0.0332,
      "num_tokens": 607763433.0,
      "reward": 0.25,
      "reward_std": 0.2382165789604187,
      "rewards/simpleverify_reward/mean": 0.25,
      "rewards/simpleverify_reward/std": 0.43343618512153625,
      "step": 490,
      "tools/generated_tokens": 1357.82421875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.2734375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1157.728515625,
      "completions/mean_terminated_length": 822.6801147460938,
      "completions/min_length": 1.0,
      "completions/min_terminated_length": 1.0,
      "epoch": 0.3484740951029099,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.7284823060035706,
      "learning_rate": 2e-08,
      "loss": 0.0586,
      "num_tokens": 608848025.0,
      "reward": 0.46484375,
      "reward_std": 0.3199349641799927,
      "rewards/simpleverify_reward/mean": 0.46484375,
      "rewards/simpleverify_reward/std": 0.49925029277801514,
      "step": 491,
      "tools/generated_tokens": 1163.232421875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0078125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.26953125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1156.9140625,
      "completions/mean_terminated_length": 828.11767578125,
      "completions/min_length": 138.0,
      "completions/min_terminated_length": 138.0,
      "epoch": 0.34918381831085876,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.7355701327323914,
      "learning_rate": 1.8e-08,
      "loss": 0.0537,
      "num_tokens": 609927469.0,
      "reward": 0.390625,
      "reward_std": 0.29354336857795715,
      "rewards/simpleverify_reward/mean": 0.390625,
      "rewards/simpleverify_reward/std": 0.48836761713027954,
      "step": 492,
      "tools/generated_tokens": 1156.9921875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.265625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1185.603515625,
      "completions/mean_terminated_length": 873.6754760742188,
      "completions/min_length": 139.0,
      "completions/min_terminated_length": 139.0,
      "epoch": 0.34989354151880764,
      "frac_reward_zero_std": 0.3125,
      "grad_norm": 0.7573776841163635,
      "learning_rate": 1.6e-08,
      "loss": 0.0449,
      "num_tokens": 611020242.0,
      "reward": 0.533203125,
      "reward_std": 0.29014208912849426,
      "rewards/simpleverify_reward/mean": 0.533203125,
      "rewards/simpleverify_reward/std": 0.4993842542171478,
      "step": 493,
      "tools/generated_tokens": 1185.763671875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.291015625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2044.0,
      "completions/mean_length": 1365.546875,
      "completions/mean_terminated_length": 1085.4215087890625,
      "completions/min_length": 205.0,
      "completions/min_terminated_length": 205.0,
      "epoch": 0.35060326472675657,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.5987696647644043,
      "learning_rate": 1.4e-08,
      "loss": 0.0704,
      "num_tokens": 612205546.0,
      "reward": 0.333984375,
      "reward_std": 0.3418103754520416,
      "rewards/simpleverify_reward/mean": 0.333984375,
      "rewards/simpleverify_reward/std": 0.47209542989730835,
      "step": 494,
      "tools/generated_tokens": 1365.654296875,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.23046875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2023.0,
      "completions/mean_length": 1287.515625,
      "completions/mean_terminated_length": 1059.75634765625,
      "completions/min_length": 153.0,
      "completions/min_terminated_length": 153.0,
      "epoch": 0.35131298793470545,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.8309851288795471,
      "learning_rate": 1.2e-08,
      "loss": 0.0725,
      "num_tokens": 613352338.0,
      "reward": 0.474609375,
      "reward_std": 0.33154866099357605,
      "rewards/simpleverify_reward/mean": 0.474609375,
      "rewards/simpleverify_reward/std": 0.4998432695865631,
      "step": 495,
      "tools/generated_tokens": 1287.6015625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.19140625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2028.0,
      "completions/mean_length": 1105.4375,
      "completions/mean_terminated_length": 882.31884765625,
      "completions/min_length": 179.0,
      "completions/min_terminated_length": 179.0,
      "epoch": 0.3520227111426544,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.6914606094360352,
      "learning_rate": 1e-08,
      "loss": 0.0677,
      "num_tokens": 614407869.0,
      "reward": 0.494140625,
      "reward_std": 0.3392329812049866,
      "rewards/simpleverify_reward/mean": 0.494140625,
      "rewards/simpleverify_reward/std": 0.5004546642303467,
      "step": 496,
      "tools/generated_tokens": 1108.5,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.267578125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2045.0,
      "completions/mean_length": 1232.513671875,
      "completions/mean_terminated_length": 934.5892944335938,
      "completions/min_length": 168.0,
      "completions/min_terminated_length": 168.0,
      "epoch": 0.35273243435060325,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.742068886756897,
      "learning_rate": 8e-09,
      "loss": 0.0699,
      "num_tokens": 615519549.0,
      "reward": 0.4609375,
      "reward_std": 0.3483656644821167,
      "rewards/simpleverify_reward/mean": 0.4609375,
      "rewards/simpleverify_reward/std": 0.4989593029022217,
      "step": 497,
      "tools/generated_tokens": 1234.009765625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.001953125,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.2109375,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2029.0,
      "completions/mean_length": 1099.57421875,
      "completions/mean_terminated_length": 846.03466796875,
      "completions/min_length": 178.0,
      "completions/min_terminated_length": 178.0,
      "epoch": 0.3534421575585522,
      "frac_reward_zero_std": 0.1875,
      "grad_norm": 0.8446533679962158,
      "learning_rate": 6e-09,
      "loss": 0.0829,
      "num_tokens": 616570786.0,
      "reward": 0.40234375,
      "reward_std": 0.3462895154953003,
      "rewards/simpleverify_reward/mean": 0.40234375,
      "rewards/simpleverify_reward/std": 0.4908501207828522,
      "step": 498,
      "tools/generated_tokens": 1101.783203125,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.005859375,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.220703125,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 1160.13671875,
      "completions/mean_terminated_length": 908.6867065429688,
      "completions/min_length": 191.0,
      "completions/min_terminated_length": 191.0,
      "epoch": 0.35415188076650106,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.7965478301048279,
      "learning_rate": 4e-09,
      "loss": 0.0616,
      "num_tokens": 617660024.0,
      "reward": 0.380859375,
      "reward_std": 0.3263852298259735,
      "rewards/simpleverify_reward/mean": 0.380859375,
      "rewards/simpleverify_reward/std": 0.48607301712036133,
      "step": 499,
      "tools/generated_tokens": 1160.287109375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.291015625,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2031.0,
      "completions/mean_length": 1249.6640625,
      "completions/mean_terminated_length": 921.9724731445312,
      "completions/min_length": 200.0,
      "completions/min_terminated_length": 200.0,
      "epoch": 0.35486160397445,
      "frac_reward_zero_std": 0.34375,
      "grad_norm": 0.7206050157546997,
      "learning_rate": 2e-09,
      "loss": 0.0331,
      "num_tokens": 618786892.0,
      "reward": 0.37890625,
      "reward_std": 0.24709367752075195,
      "rewards/simpleverify_reward/mean": 0.37890625,
      "rewards/simpleverify_reward/std": 0.4855891764163971,
      "step": 500,
      "tools/generated_tokens": 1249.81640625,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "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": 0.29296875,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2048.0,
      "completions/mean_length": 1309.669921875,
      "completions/mean_terminated_length": 1003.7320556640625,
      "completions/min_length": 62.0,
      "completions/min_terminated_length": 62.0,
      "epoch": 0.35557132718239887,
      "frac_reward_zero_std": 0.21875,
      "grad_norm": 0.6422320604324341,
      "learning_rate": 0.0,
      "loss": 0.0494,
      "num_tokens": 619944467.0,
      "reward": 0.396484375,
      "reward_std": 0.29910749197006226,
      "rewards/simpleverify_reward/mean": 0.396484375,
      "rewards/simpleverify_reward/std": 0.4896455705165863,
      "step": 501,
      "tools/generated_tokens": 1309.80859375,
      "tools/num_python": 0.0,
      "tools/num_python_exec_error": 0.0,
      "tools/num_retrieval": 0.0,
      "tools/num_retriever_exec_error": 0.0,
      "tools/num_saving": 0.0,
      "tools/num_saving_exec_error": 0.0,
      "tools/num_tool_detect_error": 0.0
    },
    {
      "epoch": 0.35557132718239887,
      "step": 501,
      "total_flos": 0.0,
      "train_loss": 9.857557580142677e-05,
      "train_runtime": 96.6022,
      "train_samples_per_second": 2650.043,
      "train_steps_per_second": 5.176
    }
  ],
  "logging_steps": 1,
  "max_steps": 500,
  "num_input_tokens_seen": 619944467,
  "num_train_epochs": 1,
  "save_steps": 100,
  "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": 8,
  "trial_name": null,
  "trial_params": null
}