{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.32,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 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": 1504.0,
      "completions/max_terminated_length": 1504.0,
      "completions/mean_length": 303.0,
      "completions/mean_terminated_length": 410.4126892089844,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.0016,
      "grad_norm": 0.005749928764998913,
      "learning_rate": 5.000000000000001e-07,
      "loss": -0.0217,
      "num_tokens": 392512.0,
      "reward": 0.04026263207197189,
      "reward_std": 0.09501844644546509,
      "rewards/accuracy_reward": 0.0,
      "rewards/brier_reward": 0.018024610355496407,
      "rewards/confidence_one_or_zero": 0.0625,
      "rewards/format_reward": 0.0625,
      "rewards/mean_confidence_reward": 0.26346302032470703,
      "step": 1
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 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": 1514.0,
      "completions/max_terminated_length": 1514.0,
      "completions/mean_length": 341.23828125,
      "completions/mean_terminated_length": 493.5423889160156,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.0032,
      "grad_norm": 0.006314713973551989,
      "learning_rate": 1.0000000000000002e-06,
      "loss": -0.0254,
      "num_tokens": 816933.0,
      "reward": 0.07134318351745605,
      "reward_std": 0.16403131186962128,
      "rewards/accuracy_reward": 0.0,
      "rewards/brier_reward": 0.029404297471046448,
      "rewards/confidence_one_or_zero": 0.07421875,
      "rewards/format_reward": 0.11328125,
      "rewards/mean_confidence_reward": 0.3325389623641968,
      "step": 2
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 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": 1443.0,
      "completions/max_terminated_length": 1443.0,
      "completions/mean_length": 312.1015625,
      "completions/mean_terminated_length": 459.18389892578125,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.0048,
      "grad_norm": 0.005154214799404144,
      "learning_rate": 1.5e-06,
      "loss": -0.0184,
      "num_tokens": 1227311.0,
      "reward": 0.044827938079833984,
      "reward_std": 0.10091917961835861,
      "rewards/accuracy_reward": 0.0,
      "rewards/brier_reward": 0.015436407178640366,
      "rewards/confidence_one_or_zero": 0.078125,
      "rewards/format_reward": 0.07421875,
      "rewards/mean_confidence_reward": 0.2802625000476837,
      "step": 3
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 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": 1513.0,
      "completions/max_terminated_length": 1513.0,
      "completions/mean_length": 313.24609375,
      "completions/mean_terminated_length": 424.2909851074219,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.0064,
      "grad_norm": 0.005596967414021492,
      "learning_rate": 2.0000000000000003e-06,
      "loss": -0.0349,
      "num_tokens": 1650278.0,
      "reward": 0.044450514018535614,
      "reward_std": 0.1127510517835617,
      "rewards/accuracy_reward": 0.0,
      "rewards/brier_reward": 0.018587836995720863,
      "rewards/confidence_one_or_zero": 0.07421875,
      "rewards/format_reward": 0.0703125,
      "rewards/mean_confidence_reward": 0.2687794864177704,
      "step": 4
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 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": 1526.0,
      "completions/max_terminated_length": 1526.0,
      "completions/mean_length": 306.84765625,
      "completions/mean_terminated_length": 431.6098937988281,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.008,
      "grad_norm": 0.006082500796765089,
      "learning_rate": 2.5e-06,
      "loss": -0.0153,
      "num_tokens": 2080167.0,
      "reward": 0.05005643144249916,
      "reward_std": 0.11759157478809357,
      "rewards/accuracy_reward": 0.0,
      "rewards/brier_reward": 0.018080823123455048,
      "rewards/confidence_one_or_zero": 0.09375,
      "rewards/format_reward": 0.08203125,
      "rewards/mean_confidence_reward": 0.30190616846084595,
      "step": 5
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 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": 1526.0,
      "completions/max_terminated_length": 1526.0,
      "completions/mean_length": 323.73828125,
      "completions/mean_terminated_length": 499.2590026855469,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.0096,
      "grad_norm": 0.006878445390611887,
      "learning_rate": 3e-06,
      "loss": -0.0257,
      "num_tokens": 2506484.0,
      "reward": 0.06703364849090576,
      "reward_std": 0.15876701474189758,
      "rewards/accuracy_reward": 0.0,
      "rewards/brier_reward": 0.036410294473171234,
      "rewards/confidence_one_or_zero": 0.07421875,
      "rewards/format_reward": 0.09765625,
      "rewards/mean_confidence_reward": 0.2985377311706543,
      "step": 6
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 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": 1509.0,
      "completions/max_terminated_length": 1509.0,
      "completions/mean_length": 326.8046875,
      "completions/mean_terminated_length": 462.22100830078125,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.0112,
      "grad_norm": 0.009645157493650913,
      "learning_rate": 3.5e-06,
      "loss": -0.0403,
      "num_tokens": 2925402.0,
      "reward": 0.07675451785326004,
      "reward_std": 0.17086508870124817,
      "rewards/accuracy_reward": 0.0,
      "rewards/brier_reward": 0.028508201241493225,
      "rewards/confidence_one_or_zero": 0.0859375,
      "rewards/format_reward": 0.125,
      "rewards/mean_confidence_reward": 0.3304399251937866,
      "step": 7
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 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": 1528.0,
      "completions/max_terminated_length": 1528.0,
      "completions/mean_length": 363.6953125,
      "completions/mean_terminated_length": 495.2446594238281,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.0128,
      "grad_norm": 0.007638865616172552,
      "learning_rate": 4.000000000000001e-06,
      "loss": -0.0562,
      "num_tokens": 3338884.0,
      "reward": 0.10420513153076172,
      "reward_std": 0.2052772045135498,
      "rewards/accuracy_reward": 0.0,
      "rewards/brier_reward": 0.044346779584884644,
      "rewards/confidence_one_or_zero": 0.1015625,
      "rewards/format_reward": 0.1640625,
      "rewards/mean_confidence_reward": 0.3951185345649719,
      "step": 8
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 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": 1490.0,
      "completions/max_terminated_length": 1490.0,
      "completions/mean_length": 314.37890625,
      "completions/mean_terminated_length": 444.64642333984375,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.0144,
      "grad_norm": 0.011798583902418613,
      "learning_rate": 4.5e-06,
      "loss": -0.0687,
      "num_tokens": 3768333.0,
      "reward": 0.17055284976959229,
      "reward_std": 0.2825161814689636,
      "rewards/accuracy_reward": 0.00390625,
      "rewards/brier_reward": 0.06376074254512787,
      "rewards/confidence_one_or_zero": 0.11328125,
      "rewards/format_reward": 0.26953125,
      "rewards/mean_confidence_reward": 0.4795473515987396,
      "step": 9
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 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": 1530.0,
      "completions/max_terminated_length": 1530.0,
      "completions/mean_length": 357.54296875,
      "completions/mean_terminated_length": 492.1021423339844,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.016,
      "grad_norm": 0.008803842589259148,
      "learning_rate": 5e-06,
      "loss": -0.0374,
      "num_tokens": 4195512.0,
      "reward": 0.20917564630508423,
      "reward_std": 0.29108554124832153,
      "rewards/accuracy_reward": 0.0,
      "rewards/brier_reward": 0.09413106739521027,
      "rewards/confidence_one_or_zero": 0.17578125,
      "rewards/format_reward": 0.32421875,
      "rewards/mean_confidence_reward": 0.5659036636352539,
      "step": 10
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.14453125,
      "completions/max_length": 1535.0,
      "completions/max_terminated_length": 1535.0,
      "completions/mean_length": 364.484375,
      "completions/mean_terminated_length": 426.06390380859375,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.0176,
      "grad_norm": 0.010400340892374516,
      "learning_rate": 5e-06,
      "loss": -0.0757,
      "num_tokens": 4636212.0,
      "reward": 0.4166101813316345,
      "reward_std": 0.3802958130836487,
      "rewards/accuracy_reward": 0.01171875,
      "rewards/brier_reward": 0.20821861922740936,
      "rewards/confidence_one_or_zero": 0.171875,
      "rewards/format_reward": 0.6015625,
      "rewards/mean_confidence_reward": 0.7054708003997803,
      "step": 11
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.05859375,
      "completions/max_length": 1516.0,
      "completions/max_terminated_length": 1516.0,
      "completions/mean_length": 374.7265625,
      "completions/mean_terminated_length": 398.0498046875,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.0192,
      "grad_norm": 0.009152157232165337,
      "learning_rate": 5e-06,
      "loss": -0.0242,
      "num_tokens": 5070462.0,
      "reward": 0.5529123544692993,
      "reward_std": 0.3406127095222473,
      "rewards/accuracy_reward": 0.0078125,
      "rewards/brier_reward": 0.32066667079925537,
      "rewards/confidence_one_or_zero": 0.19921875,
      "rewards/format_reward": 0.76953125,
      "rewards/mean_confidence_reward": 0.6666077971458435,
      "step": 12
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.04296875,
      "completions/max_length": 1533.0,
      "completions/max_terminated_length": 1533.0,
      "completions/mean_length": 305.55859375,
      "completions/mean_terminated_length": 319.27752685546875,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 7.0,
      "epoch": 0.0208,
      "grad_norm": 0.008684230037033558,
      "learning_rate": 5e-06,
      "loss": -0.0189,
      "num_tokens": 5497389.0,
      "reward": 0.5994592905044556,
      "reward_std": 0.30771589279174805,
      "rewards/accuracy_reward": 0.00390625,
      "rewards/brier_reward": 0.3629792332649231,
      "rewards/confidence_one_or_zero": 0.25390625,
      "rewards/format_reward": 0.828125,
      "rewards/mean_confidence_reward": 0.6504890322685242,
      "step": 13
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.01171875,
      "completions/max_length": 1512.0,
      "completions/max_terminated_length": 1512.0,
      "completions/mean_length": 255.3515625,
      "completions/mean_terminated_length": 258.37945556640625,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 9.0,
      "epoch": 0.0224,
      "grad_norm": 0.010425634682178497,
      "learning_rate": 5e-06,
      "loss": 0.0136,
      "num_tokens": 5909999.0,
      "reward": 0.699076771736145,
      "reward_std": 0.3184015154838562,
      "rewards/accuracy_reward": 0.01953125,
      "rewards/brier_reward": 0.460651695728302,
      "rewards/confidence_one_or_zero": 0.33203125,
      "rewards/format_reward": 0.8984375,
      "rewards/mean_confidence_reward": 0.5886218547821045,
      "step": 14
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 1228.0,
      "completions/max_terminated_length": 1228.0,
      "completions/mean_length": 228.60546875,
      "completions/mean_terminated_length": 228.60546875,
      "completions/min_length": 15.0,
      "completions/min_terminated_length": 15.0,
      "epoch": 0.024,
      "grad_norm": 0.008485889993607998,
      "learning_rate": 5e-06,
      "loss": 0.0061,
      "num_tokens": 6312106.0,
      "reward": 0.8145014047622681,
      "reward_std": 0.23522086441516876,
      "rewards/accuracy_reward": 0.015625,
      "rewards/brier_reward": 0.6211885213851929,
      "rewards/confidence_one_or_zero": 0.41796875,
      "rewards/format_reward": 0.9765625,
      "rewards/mean_confidence_reward": 0.4547516405582428,
      "step": 15
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.00390625,
      "completions/max_length": 1415.0,
      "completions/max_terminated_length": 1415.0,
      "completions/mean_length": 169.3046875,
      "completions/mean_terminated_length": 169.96864318847656,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 29.0,
      "epoch": 0.0256,
      "grad_norm": 0.010844497941434383,
      "learning_rate": 5e-06,
      "loss": 0.0199,
      "num_tokens": 6714200.0,
      "reward": 0.8929893374443054,
      "reward_std": 0.23516574501991272,
      "rewards/accuracy_reward": 0.046875,
      "rewards/brier_reward": 0.7234768271446228,
      "rewards/confidence_one_or_zero": 0.71484375,
      "rewards/format_reward": 0.96875,
      "rewards/mean_confidence_reward": 0.2515939474105835,
      "step": 16
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.00390625,
      "completions/max_length": 945.0,
      "completions/max_terminated_length": 945.0,
      "completions/mean_length": 99.51171875,
      "completions/mean_terminated_length": 99.90196990966797,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 30.0,
      "epoch": 0.0272,
      "grad_norm": 0.010410776361823082,
      "learning_rate": 5e-06,
      "loss": 0.0293,
      "num_tokens": 7052771.0,
      "reward": 0.9686627388000488,
      "reward_std": 0.1116916686296463,
      "rewards/accuracy_reward": 0.01171875,
      "rewards/brier_reward": 0.9295110702514648,
      "rewards/confidence_one_or_zero": 0.91015625,
      "rewards/format_reward": 0.984375,
      "rewards/mean_confidence_reward": 0.07008671760559082,
      "step": 17
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 1332.0,
      "completions/max_terminated_length": 1332.0,
      "completions/mean_length": 69.91015625,
      "completions/mean_terminated_length": 69.91015625,
      "completions/min_length": 30.0,
      "completions/min_terminated_length": 30.0,
      "epoch": 0.0288,
      "grad_norm": 0.007693614345043898,
      "learning_rate": 5e-06,
      "loss": 0.0155,
      "num_tokens": 7410788.0,
      "reward": 1.0056359767913818,
      "reward_std": 0.054224878549575806,
      "rewards/accuracy_reward": 0.03515625,
      "rewards/brier_reward": 0.9526762366294861,
      "rewards/confidence_one_or_zero": 0.98828125,
      "rewards/format_reward": 0.98828125,
      "rewards/mean_confidence_reward": 0.001613281317986548,
      "step": 18
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 315.0,
      "completions/max_terminated_length": 315.0,
      "completions/mean_length": 54.0859375,
      "completions/mean_terminated_length": 54.0859375,
      "completions/min_length": 30.0,
      "completions/min_terminated_length": 30.0,
      "epoch": 0.0304,
      "grad_norm": 0.011272546835243702,
      "learning_rate": 5e-06,
      "loss": -0.0014,
      "num_tokens": 7768314.0,
      "reward": 1.0253913402557373,
      "reward_std": 0.06518790125846863,
      "rewards/accuracy_reward": 0.06640625,
      "rewards/brier_reward": 0.9257808923721313,
      "rewards/confidence_one_or_zero": 0.99609375,
      "rewards/format_reward": 0.9921875,
      "rewards/mean_confidence_reward": 3.9062499126885086e-05,
      "step": 19
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 259.0,
      "completions/max_terminated_length": 259.0,
      "completions/mean_length": 49.15625,
      "completions/mean_terminated_length": 49.15625,
      "completions/min_length": 26.0,
      "completions/min_terminated_length": 26.0,
      "epoch": 0.032,
      "grad_norm": 0.00929289497435093,
      "learning_rate": 5e-06,
      "loss": 0.01,
      "num_tokens": 8124378.0,
      "reward": 1.0371103286743164,
      "reward_std": 0.04432518407702446,
      "rewards/accuracy_reward": 0.08984375,
      "rewards/brier_reward": 0.90234375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.9921875,
      "rewards/mean_confidence_reward": 0.0,
      "step": 20
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 97.0,
      "completions/max_terminated_length": 97.0,
      "completions/mean_length": 49.47265625,
      "completions/mean_terminated_length": 49.47265625,
      "completions/min_length": 28.0,
      "completions/min_terminated_length": 28.0,
      "epoch": 0.0336,
      "grad_norm": 0.007096223067492247,
      "learning_rate": 5e-06,
      "loss": -0.0009,
      "num_tokens": 8479995.0,
      "reward": 1.0410165786743164,
      "reward_std": 0.05655324086546898,
      "rewards/accuracy_reward": 0.08203125,
      "rewards/brier_reward": 0.91796875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 21
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 141.0,
      "completions/max_terminated_length": 141.0,
      "completions/mean_length": 51.7890625,
      "completions/mean_terminated_length": 51.7890625,
      "completions/min_length": 28.0,
      "completions/min_terminated_length": 28.0,
      "epoch": 0.0352,
      "grad_norm": 0.005252554547041655,
      "learning_rate": 5e-06,
      "loss": -0.0012,
      "num_tokens": 8832877.0,
      "reward": 1.0546884536743164,
      "reward_std": 0.0483323335647583,
      "rewards/accuracy_reward": 0.109375,
      "rewards/brier_reward": 0.890625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 22
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 213.0,
      "completions/max_terminated_length": 213.0,
      "completions/mean_length": 54.7578125,
      "completions/mean_terminated_length": 54.7578125,
      "completions/min_length": 29.0,
      "completions/min_terminated_length": 29.0,
      "epoch": 0.0368,
      "grad_norm": 0.011090493761003017,
      "learning_rate": 5e-06,
      "loss": -0.0004,
      "num_tokens": 9192591.0,
      "reward": 1.0605478286743164,
      "reward_std": 0.0958084836602211,
      "rewards/accuracy_reward": 0.13671875,
      "rewards/brier_reward": 0.85546875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.9921875,
      "rewards/mean_confidence_reward": 0.0,
      "step": 23
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 220.0,
      "completions/max_terminated_length": 220.0,
      "completions/mean_length": 55.78515625,
      "completions/mean_terminated_length": 55.78515625,
      "completions/min_length": 32.0,
      "completions/min_terminated_length": 32.0,
      "epoch": 0.0384,
      "grad_norm": 0.008098751306533813,
      "learning_rate": 5e-06,
      "loss": -0.0023,
      "num_tokens": 9541448.0,
      "reward": 1.0644540786743164,
      "reward_std": 0.08022359758615494,
      "rewards/accuracy_reward": 0.13671875,
      "rewards/brier_reward": 0.859375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.99609375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 24
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 193.0,
      "completions/max_terminated_length": 193.0,
      "completions/mean_length": 62.41796875,
      "completions/mean_terminated_length": 62.41796875,
      "completions/min_length": 23.0,
      "completions/min_terminated_length": 23.0,
      "epoch": 0.04,
      "grad_norm": 0.007593750022351742,
      "learning_rate": 5e-06,
      "loss": -0.0014,
      "num_tokens": 9905859.0,
      "reward": 1.0566415786743164,
      "reward_std": 0.08320242166519165,
      "rewards/accuracy_reward": 0.13671875,
      "rewards/brier_reward": 0.8515625,
      "rewards/confidence_one_or_zero": 0.99609375,
      "rewards/format_reward": 0.98828125,
      "rewards/mean_confidence_reward": 0.0,
      "step": 25
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 161.0,
      "completions/max_terminated_length": 161.0,
      "completions/mean_length": 61.703125,
      "completions/mean_terminated_length": 61.703125,
      "completions/min_length": 32.0,
      "completions/min_terminated_length": 32.0,
      "epoch": 0.0416,
      "grad_norm": 0.006790656130760908,
      "learning_rate": 5e-06,
      "loss": 0.0022,
      "num_tokens": 10275231.0,
      "reward": 1.0703134536743164,
      "reward_std": 0.07213689386844635,
      "rewards/accuracy_reward": 0.1484375,
      "rewards/brier_reward": 0.84765625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.99609375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 26
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 195.0,
      "completions/max_terminated_length": 195.0,
      "completions/mean_length": 65.6328125,
      "completions/mean_terminated_length": 65.6328125,
      "completions/min_length": 27.0,
      "completions/min_terminated_length": 27.0,
      "epoch": 0.0432,
      "grad_norm": 0.0061500584706664085,
      "learning_rate": 5e-06,
      "loss": -0.0004,
      "num_tokens": 10624729.0,
      "reward": 1.0585947036743164,
      "reward_std": 0.06575888395309448,
      "rewards/accuracy_reward": 0.1328125,
      "rewards/brier_reward": 0.859375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.9921875,
      "rewards/mean_confidence_reward": 0.0,
      "step": 27
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 801.0,
      "completions/max_terminated_length": 801.0,
      "completions/mean_length": 66.05078125,
      "completions/mean_terminated_length": 66.05078125,
      "completions/min_length": 25.0,
      "completions/min_terminated_length": 25.0,
      "epoch": 0.0448,
      "grad_norm": 0.006998259574174881,
      "learning_rate": 5e-06,
      "loss": -0.0088,
      "num_tokens": 10976326.0,
      "reward": 1.0878915786743164,
      "reward_std": 0.07318098098039627,
      "rewards/accuracy_reward": 0.17578125,
      "rewards/brier_reward": 0.82421875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 28
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 253.0,
      "completions/max_terminated_length": 253.0,
      "completions/mean_length": 64.43359375,
      "completions/mean_terminated_length": 64.43359375,
      "completions/min_length": 26.0,
      "completions/min_terminated_length": 26.0,
      "epoch": 0.0464,
      "grad_norm": 0.006655920296907425,
      "learning_rate": 5e-06,
      "loss": -0.0008,
      "num_tokens": 11341973.0,
      "reward": 1.0820322036743164,
      "reward_std": 0.08318543434143066,
      "rewards/accuracy_reward": 0.1640625,
      "rewards/brier_reward": 0.8359375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 29
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 170.0,
      "completions/max_terminated_length": 170.0,
      "completions/mean_length": 64.484375,
      "completions/mean_terminated_length": 64.484375,
      "completions/min_length": 32.0,
      "completions/min_terminated_length": 32.0,
      "epoch": 0.048,
      "grad_norm": 0.006319932173937559,
      "learning_rate": 5e-06,
      "loss": 0.0018,
      "num_tokens": 11688553.0,
      "reward": 1.0957040786743164,
      "reward_std": 0.08278603851795197,
      "rewards/accuracy_reward": 0.19140625,
      "rewards/brier_reward": 0.80859375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 30
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 221.0,
      "completions/max_terminated_length": 221.0,
      "completions/mean_length": 62.36328125,
      "completions/mean_terminated_length": 62.36328125,
      "completions/min_length": 32.0,
      "completions/min_terminated_length": 32.0,
      "epoch": 0.0496,
      "grad_norm": 0.007409350946545601,
      "learning_rate": 5e-06,
      "loss": -0.0039,
      "num_tokens": 12039830.0,
      "reward": 1.0976572036743164,
      "reward_std": 0.08574788272380829,
      "rewards/accuracy_reward": 0.203125,
      "rewards/brier_reward": 0.79296875,
      "rewards/confidence_one_or_zero": 0.99609375,
      "rewards/format_reward": 0.99609375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 31
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 168.0,
      "completions/max_terminated_length": 168.0,
      "completions/mean_length": 68.796875,
      "completions/mean_terminated_length": 68.796875,
      "completions/min_length": 34.0,
      "completions/min_terminated_length": 34.0,
      "epoch": 0.0512,
      "grad_norm": 0.006146772764623165,
      "learning_rate": 5e-06,
      "loss": 0.0011,
      "num_tokens": 12383978.0,
      "reward": 1.1308603286743164,
      "reward_std": 0.0666126236319542,
      "rewards/accuracy_reward": 0.26171875,
      "rewards/brier_reward": 0.73828125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 32
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 215.0,
      "completions/max_terminated_length": 215.0,
      "completions/mean_length": 69.16796875,
      "completions/mean_terminated_length": 69.16796875,
      "completions/min_length": 36.0,
      "completions/min_terminated_length": 36.0,
      "epoch": 0.0528,
      "grad_norm": 0.006563497707247734,
      "learning_rate": 5e-06,
      "loss": 0.0025,
      "num_tokens": 12742837.0,
      "reward": 1.0664072036743164,
      "reward_std": 0.06365078687667847,
      "rewards/accuracy_reward": 0.1328125,
      "rewards/brier_reward": 0.8671875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 33
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 438.0,
      "completions/max_terminated_length": 438.0,
      "completions/mean_length": 71.05859375,
      "completions/mean_terminated_length": 71.05859375,
      "completions/min_length": 34.0,
      "completions/min_terminated_length": 34.0,
      "epoch": 0.0544,
      "grad_norm": 0.006254891399294138,
      "learning_rate": 5e-06,
      "loss": 0.0011,
      "num_tokens": 13102620.0,
      "reward": 1.0917978286743164,
      "reward_std": 0.06332746148109436,
      "rewards/accuracy_reward": 0.18359375,
      "rewards/brier_reward": 0.81640625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 34
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 153.0,
      "completions/max_terminated_length": 153.0,
      "completions/mean_length": 70.12890625,
      "completions/mean_terminated_length": 70.12890625,
      "completions/min_length": 32.0,
      "completions/min_terminated_length": 32.0,
      "epoch": 0.056,
      "grad_norm": 0.006259838584810495,
      "learning_rate": 5e-06,
      "loss": 0.0057,
      "num_tokens": 13465429.0,
      "reward": 1.1992197036743164,
      "reward_std": 0.06970866024494171,
      "rewards/accuracy_reward": 0.3984375,
      "rewards/brier_reward": 0.6015625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 35
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 184.0,
      "completions/max_terminated_length": 184.0,
      "completions/mean_length": 63.85546875,
      "completions/mean_terminated_length": 63.85546875,
      "completions/min_length": 33.0,
      "completions/min_terminated_length": 33.0,
      "epoch": 0.0576,
      "grad_norm": 0.006907327566295862,
      "learning_rate": 5e-06,
      "loss": -0.0026,
      "num_tokens": 13815680.0,
      "reward": 1.1582040786743164,
      "reward_std": 0.08081457763910294,
      "rewards/accuracy_reward": 0.31640625,
      "rewards/brier_reward": 0.68359375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 36
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 228.0,
      "completions/max_terminated_length": 228.0,
      "completions/mean_length": 65.3828125,
      "completions/mean_terminated_length": 65.3828125,
      "completions/min_length": 34.0,
      "completions/min_terminated_length": 34.0,
      "epoch": 0.0592,
      "grad_norm": 0.007342278026044369,
      "learning_rate": 5e-06,
      "loss": -0.0008,
      "num_tokens": 14174674.0,
      "reward": 1.1699228286743164,
      "reward_std": 0.09639701247215271,
      "rewards/accuracy_reward": 0.33984375,
      "rewards/brier_reward": 0.66015625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 37
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 231.0,
      "completions/max_terminated_length": 231.0,
      "completions/mean_length": 63.69921875,
      "completions/mean_terminated_length": 63.69921875,
      "completions/min_length": 32.0,
      "completions/min_terminated_length": 32.0,
      "epoch": 0.0608,
      "grad_norm": 0.005854626186192036,
      "learning_rate": 5e-06,
      "loss": -0.0005,
      "num_tokens": 14536365.0,
      "reward": 1.1015634536743164,
      "reward_std": 0.05129294842481613,
      "rewards/accuracy_reward": 0.203125,
      "rewards/brier_reward": 0.796875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 38
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 241.0,
      "completions/max_terminated_length": 241.0,
      "completions/mean_length": 63.9453125,
      "completions/mean_terminated_length": 63.9453125,
      "completions/min_length": 33.0,
      "completions/min_terminated_length": 33.0,
      "epoch": 0.0624,
      "grad_norm": 0.007452231831848621,
      "learning_rate": 5e-06,
      "loss": -0.0017,
      "num_tokens": 14888983.0,
      "reward": 1.1113290786743164,
      "reward_std": 0.05937965214252472,
      "rewards/accuracy_reward": 0.22265625,
      "rewards/brier_reward": 0.77734375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 39
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 184.0,
      "completions/max_terminated_length": 184.0,
      "completions/mean_length": 62.33984375,
      "completions/mean_terminated_length": 62.33984375,
      "completions/min_length": 31.0,
      "completions/min_terminated_length": 31.0,
      "epoch": 0.064,
      "grad_norm": 0.005153173580765724,
      "learning_rate": 5e-06,
      "loss": -0.0016,
      "num_tokens": 15236582.0,
      "reward": 1.2089853286743164,
      "reward_std": 0.053135842084884644,
      "rewards/accuracy_reward": 0.41796875,
      "rewards/brier_reward": 0.58203125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 40
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 145.0,
      "completions/max_terminated_length": 145.0,
      "completions/mean_length": 64.19140625,
      "completions/mean_terminated_length": 64.19140625,
      "completions/min_length": 33.0,
      "completions/min_terminated_length": 33.0,
      "epoch": 0.0656,
      "grad_norm": 0.008204660378396511,
      "learning_rate": 5e-06,
      "loss": -0.0013,
      "num_tokens": 15602439.0,
      "reward": 1.0898447036743164,
      "reward_std": 0.0676315501332283,
      "rewards/accuracy_reward": 0.1875,
      "rewards/brier_reward": 0.80859375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.99609375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 41
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 186.0,
      "completions/max_terminated_length": 186.0,
      "completions/mean_length": 65.29296875,
      "completions/mean_terminated_length": 65.29296875,
      "completions/min_length": 31.0,
      "completions/min_terminated_length": 31.0,
      "epoch": 0.0672,
      "grad_norm": 0.007392301224172115,
      "learning_rate": 5e-06,
      "loss": 0.0023,
      "num_tokens": 15951946.0,
      "reward": 1.2500009536743164,
      "reward_std": 0.07779218256473541,
      "rewards/accuracy_reward": 0.5,
      "rewards/brier_reward": 0.5,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 42
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 223.0,
      "completions/max_terminated_length": 223.0,
      "completions/mean_length": 65.9296875,
      "completions/mean_terminated_length": 65.9296875,
      "completions/min_length": 27.0,
      "completions/min_terminated_length": 27.0,
      "epoch": 0.0688,
      "grad_norm": 0.025153739377856255,
      "learning_rate": 5e-06,
      "loss": -0.0024,
      "num_tokens": 16317912.0,
      "reward": 1.1640634536743164,
      "reward_std": 0.08529357612133026,
      "rewards/accuracy_reward": 0.3515625,
      "rewards/brier_reward": 0.63671875,
      "rewards/confidence_one_or_zero": 0.98828125,
      "rewards/format_reward": 0.98828125,
      "rewards/mean_confidence_reward": 0.0,
      "step": 43
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 625.0,
      "completions/max_terminated_length": 625.0,
      "completions/mean_length": 66.828125,
      "completions/mean_terminated_length": 66.828125,
      "completions/min_length": 30.0,
      "completions/min_terminated_length": 30.0,
      "epoch": 0.0704,
      "grad_norm": 0.006532193627208471,
      "learning_rate": 5e-06,
      "loss": -0.0012,
      "num_tokens": 16686652.0,
      "reward": 1.1914072036743164,
      "reward_std": 0.047477371990680695,
      "rewards/accuracy_reward": 0.3828125,
      "rewards/brier_reward": 0.6171875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 44
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 197.0,
      "completions/max_terminated_length": 197.0,
      "completions/mean_length": 62.3515625,
      "completions/mean_terminated_length": 62.3515625,
      "completions/min_length": 31.0,
      "completions/min_terminated_length": 31.0,
      "epoch": 0.072,
      "grad_norm": 0.00799117423593998,
      "learning_rate": 5e-06,
      "loss": -0.0028,
      "num_tokens": 17040462.0,
      "reward": 1.1582040786743164,
      "reward_std": 0.06818589568138123,
      "rewards/accuracy_reward": 0.31640625,
      "rewards/brier_reward": 0.68359375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 45
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 274.0,
      "completions/max_terminated_length": 274.0,
      "completions/mean_length": 66.0234375,
      "completions/mean_terminated_length": 66.0234375,
      "completions/min_length": 34.0,
      "completions/min_terminated_length": 34.0,
      "epoch": 0.0736,
      "grad_norm": 0.00791685376316309,
      "learning_rate": 5e-06,
      "loss": -0.0003,
      "num_tokens": 17375468.0,
      "reward": 1.1464853286743164,
      "reward_std": 0.06194208562374115,
      "rewards/accuracy_reward": 0.29296875,
      "rewards/brier_reward": 0.70703125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 46
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 439.0,
      "completions/max_terminated_length": 439.0,
      "completions/mean_length": 73.671875,
      "completions/mean_terminated_length": 73.671875,
      "completions/min_length": 32.0,
      "completions/min_terminated_length": 32.0,
      "epoch": 0.0752,
      "grad_norm": 0.006725848186761141,
      "learning_rate": 5e-06,
      "loss": 0.0033,
      "num_tokens": 17720488.0,
      "reward": 1.1425790786743164,
      "reward_std": 0.054445136338472366,
      "rewards/accuracy_reward": 0.28515625,
      "rewards/brier_reward": 0.71484375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 47
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0078125,
      "completions/max_length": 1332.0,
      "completions/max_terminated_length": 1332.0,
      "completions/mean_length": 131.52734375,
      "completions/mean_terminated_length": 132.56298828125,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 31.0,
      "epoch": 0.0768,
      "grad_norm": 0.015706874430179596,
      "learning_rate": 5e-06,
      "loss": 0.0124,
      "num_tokens": 18080463.0,
      "reward": 1.1503915786743164,
      "reward_std": 0.14131194353103638,
      "rewards/accuracy_reward": 0.33984375,
      "rewards/brier_reward": 0.640625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.98046875,
      "rewards/mean_confidence_reward": 0.0,
      "step": 48
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 200.0,
      "completions/max_terminated_length": 200.0,
      "completions/mean_length": 60.30078125,
      "completions/mean_terminated_length": 60.30078125,
      "completions/min_length": 27.0,
      "completions/min_terminated_length": 27.0,
      "epoch": 0.0784,
      "grad_norm": 0.008152630180120468,
      "learning_rate": 5e-06,
      "loss": 0.001,
      "num_tokens": 18446988.0,
      "reward": 1.1640634536743164,
      "reward_std": 0.0668778270483017,
      "rewards/accuracy_reward": 0.328125,
      "rewards/brier_reward": 0.671875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 49
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 203.0,
      "completions/max_terminated_length": 203.0,
      "completions/mean_length": 60.88671875,
      "completions/mean_terminated_length": 60.88671875,
      "completions/min_length": 31.0,
      "completions/min_terminated_length": 31.0,
      "epoch": 0.08,
      "grad_norm": 0.007156162057071924,
      "learning_rate": 5e-06,
      "loss": 0.0012,
      "num_tokens": 18802703.0,
      "reward": 1.1269540786743164,
      "reward_std": 0.05102774128317833,
      "rewards/accuracy_reward": 0.25390625,
      "rewards/brier_reward": 0.74609375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 50
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 405.0,
      "completions/max_terminated_length": 405.0,
      "completions/mean_length": 63.71484375,
      "completions/mean_terminated_length": 63.71484375,
      "completions/min_length": 29.0,
      "completions/min_terminated_length": 29.0,
      "epoch": 0.0816,
      "grad_norm": 0.009628606028854847,
      "learning_rate": 5e-06,
      "loss": 0.0056,
      "num_tokens": 19158862.0,
      "reward": 1.1347665786743164,
      "reward_std": 0.08870971202850342,
      "rewards/accuracy_reward": 0.27734375,
      "rewards/brier_reward": 0.71875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.99609375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 51
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 259.0,
      "completions/max_terminated_length": 259.0,
      "completions/mean_length": 69.57421875,
      "completions/mean_terminated_length": 69.57421875,
      "completions/min_length": 33.0,
      "completions/min_terminated_length": 33.0,
      "epoch": 0.0832,
      "grad_norm": 0.006935023702681065,
      "learning_rate": 5e-06,
      "loss": 0.0003,
      "num_tokens": 19524057.0,
      "reward": 1.1562509536743164,
      "reward_std": 0.06509427726268768,
      "rewards/accuracy_reward": 0.3125,
      "rewards/brier_reward": 0.6875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 52
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 284.0,
      "completions/max_terminated_length": 284.0,
      "completions/mean_length": 69.5,
      "completions/mean_terminated_length": 69.5,
      "completions/min_length": 33.0,
      "completions/min_terminated_length": 33.0,
      "epoch": 0.0848,
      "grad_norm": 0.008871861733496189,
      "learning_rate": 5e-06,
      "loss": -0.0007,
      "num_tokens": 19880473.0,
      "reward": 1.1132822036743164,
      "reward_std": 0.08120957016944885,
      "rewards/accuracy_reward": 0.2265625,
      "rewards/brier_reward": 0.7734375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 53
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 353.0,
      "completions/max_terminated_length": 353.0,
      "completions/mean_length": 73.41796875,
      "completions/mean_terminated_length": 73.41796875,
      "completions/min_length": 32.0,
      "completions/min_terminated_length": 32.0,
      "epoch": 0.0864,
      "grad_norm": 0.006425413303077221,
      "learning_rate": 5e-06,
      "loss": 0.0004,
      "num_tokens": 20234380.0,
      "reward": 1.1562509536743164,
      "reward_std": 0.07101795077323914,
      "rewards/accuracy_reward": 0.3125,
      "rewards/brier_reward": 0.6875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 54
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 391.0,
      "completions/max_terminated_length": 391.0,
      "completions/mean_length": 73.94140625,
      "completions/mean_terminated_length": 73.94140625,
      "completions/min_length": 38.0,
      "completions/min_terminated_length": 38.0,
      "epoch": 0.088,
      "grad_norm": 0.007403024472296238,
      "learning_rate": 5e-06,
      "loss": -0.0011,
      "num_tokens": 20605917.0,
      "reward": 1.1269540786743164,
      "reward_std": 0.06135355681180954,
      "rewards/accuracy_reward": 0.25390625,
      "rewards/brier_reward": 0.74609375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 55
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 252.0,
      "completions/max_terminated_length": 252.0,
      "completions/mean_length": 83.75390625,
      "completions/mean_terminated_length": 83.75390625,
      "completions/min_length": 34.0,
      "completions/min_terminated_length": 34.0,
      "epoch": 0.0896,
      "grad_norm": 0.006885427515953779,
      "learning_rate": 5e-06,
      "loss": 0.0013,
      "num_tokens": 20974542.0,
      "reward": 1.2363290786743164,
      "reward_std": 0.056094493716955185,
      "rewards/accuracy_reward": 0.48046875,
      "rewards/brier_reward": 0.515625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.99609375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 56
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 1186.0,
      "completions/max_terminated_length": 1186.0,
      "completions/mean_length": 89.47265625,
      "completions/mean_terminated_length": 89.47265625,
      "completions/min_length": 37.0,
      "completions/min_terminated_length": 37.0,
      "epoch": 0.0912,
      "grad_norm": 0.004320678301155567,
      "learning_rate": 5e-06,
      "loss": -0.0057,
      "num_tokens": 21326775.0,
      "reward": 1.1132822036743164,
      "reward_std": 0.045503467321395874,
      "rewards/accuracy_reward": 0.2265625,
      "rewards/brier_reward": 0.7734375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 57
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 400.0,
      "completions/max_terminated_length": 400.0,
      "completions/mean_length": 95.81640625,
      "completions/mean_terminated_length": 95.81640625,
      "completions/min_length": 38.0,
      "completions/min_terminated_length": 38.0,
      "epoch": 0.0928,
      "grad_norm": 0.008047458715736866,
      "learning_rate": 5e-06,
      "loss": 0.0063,
      "num_tokens": 21692672.0,
      "reward": 1.1503915786743164,
      "reward_std": 0.09199290722608566,
      "rewards/accuracy_reward": 0.30859375,
      "rewards/brier_reward": 0.6875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.99609375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 58
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 547.0,
      "completions/max_terminated_length": 547.0,
      "completions/mean_length": 95.40234375,
      "completions/mean_terminated_length": 95.40234375,
      "completions/min_length": 38.0,
      "completions/min_terminated_length": 38.0,
      "epoch": 0.0944,
      "grad_norm": 0.00607341481372714,
      "learning_rate": 5e-06,
      "loss": 0.0066,
      "num_tokens": 22062023.0,
      "reward": 1.1796884536743164,
      "reward_std": 0.0662132203578949,
      "rewards/accuracy_reward": 0.359375,
      "rewards/brier_reward": 0.640625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 59
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 1083.0,
      "completions/max_terminated_length": 1083.0,
      "completions/mean_length": 108.17578125,
      "completions/mean_terminated_length": 108.17578125,
      "completions/min_length": 39.0,
      "completions/min_terminated_length": 39.0,
      "epoch": 0.096,
      "grad_norm": 0.005692021455615759,
      "learning_rate": 5e-06,
      "loss": 0.0085,
      "num_tokens": 22423764.0,
      "reward": 1.1269540786743164,
      "reward_std": 0.05983643978834152,
      "rewards/accuracy_reward": 0.25390625,
      "rewards/brier_reward": 0.74609375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 60
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 518.0,
      "completions/max_terminated_length": 518.0,
      "completions/mean_length": 93.9921875,
      "completions/mean_terminated_length": 93.9921875,
      "completions/min_length": 37.0,
      "completions/min_terminated_length": 37.0,
      "epoch": 0.0976,
      "grad_norm": 0.004186698235571384,
      "learning_rate": 5e-06,
      "loss": -0.002,
      "num_tokens": 22794730.0,
      "reward": 1.1777353286743164,
      "reward_std": 0.037416763603687286,
      "rewards/accuracy_reward": 0.35546875,
      "rewards/brier_reward": 0.64453125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 61
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 883.0,
      "completions/max_terminated_length": 883.0,
      "completions/mean_length": 103.70703125,
      "completions/mean_terminated_length": 103.70703125,
      "completions/min_length": 36.0,
      "completions/min_terminated_length": 36.0,
      "epoch": 0.0992,
      "grad_norm": 0.004728452768176794,
      "learning_rate": 5e-06,
      "loss": -0.0016,
      "num_tokens": 23156191.0,
      "reward": 1.1816415786743164,
      "reward_std": 0.055698275566101074,
      "rewards/accuracy_reward": 0.36328125,
      "rewards/brier_reward": 0.63671875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 62
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.00390625,
      "completions/max_length": 683.0,
      "completions/max_terminated_length": 683.0,
      "completions/mean_length": 117.2421875,
      "completions/mean_terminated_length": 117.70196533203125,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 37.0,
      "epoch": 0.1008,
      "grad_norm": 0.006030679680407047,
      "learning_rate": 5e-06,
      "loss": 0.0127,
      "num_tokens": 23528725.0,
      "reward": 1.1171884536743164,
      "reward_std": 0.05655202269554138,
      "rewards/accuracy_reward": 0.25,
      "rewards/brier_reward": 0.7421875,
      "rewards/confidence_one_or_zero": 0.99609375,
      "rewards/format_reward": 0.9921875,
      "rewards/mean_confidence_reward": 0.0,
      "step": 63
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 469.0,
      "completions/max_terminated_length": 469.0,
      "completions/mean_length": 109.6171875,
      "completions/mean_terminated_length": 109.6171875,
      "completions/min_length": 34.0,
      "completions/min_terminated_length": 34.0,
      "epoch": 0.1024,
      "grad_norm": 0.00417441688477993,
      "learning_rate": 5e-06,
      "loss": 0.0078,
      "num_tokens": 23910147.0,
      "reward": 1.1582040786743164,
      "reward_std": 0.03827172517776489,
      "rewards/accuracy_reward": 0.31640625,
      "rewards/brier_reward": 0.68359375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 64
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 1274.0,
      "completions/max_terminated_length": 1274.0,
      "completions/mean_length": 113.59765625,
      "completions/mean_terminated_length": 113.59765625,
      "completions/min_length": 34.0,
      "completions/min_terminated_length": 34.0,
      "epoch": 0.104,
      "grad_norm": 0.004523205570876598,
      "learning_rate": 5e-06,
      "loss": 0.0082,
      "num_tokens": 24283652.0,
      "reward": 1.1464853286743164,
      "reward_std": 0.034854330122470856,
      "rewards/accuracy_reward": 0.30078125,
      "rewards/brier_reward": 0.6953125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.99609375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 65
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.00390625,
      "completions/max_length": 1219.0,
      "completions/max_terminated_length": 1219.0,
      "completions/mean_length": 109.6328125,
      "completions/mean_terminated_length": 110.06275177001953,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 33.0,
      "epoch": 0.1056,
      "grad_norm": 0.0046501909382641315,
      "learning_rate": 5e-06,
      "loss": -0.0153,
      "num_tokens": 24661446.0,
      "reward": 1.1210947036743164,
      "reward_std": 0.04635843634605408,
      "rewards/accuracy_reward": 0.25,
      "rewards/brier_reward": 0.74609375,
      "rewards/confidence_one_or_zero": 0.99609375,
      "rewards/format_reward": 0.99609375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 66
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0078125,
      "completions/max_length": 1018.0,
      "completions/max_terminated_length": 1018.0,
      "completions/mean_length": 131.8515625,
      "completions/mean_terminated_length": 132.8897705078125,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 36.0,
      "epoch": 0.1072,
      "grad_norm": 0.0051050446927547455,
      "learning_rate": 5e-06,
      "loss": -0.0071,
      "num_tokens": 25046312.0,
      "reward": 1.2031259536743164,
      "reward_std": 0.08831032365560532,
      "rewards/accuracy_reward": 0.421875,
      "rewards/brier_reward": 0.5703125,
      "rewards/confidence_one_or_zero": 0.9921875,
      "rewards/format_reward": 0.9921875,
      "rewards/mean_confidence_reward": 0.0,
      "step": 67
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0078125,
      "completions/max_length": 1495.0,
      "completions/max_terminated_length": 1495.0,
      "completions/mean_length": 175.33203125,
      "completions/mean_terminated_length": 176.7126007080078,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 35.0,
      "epoch": 0.1088,
      "grad_norm": 0.00740397721529007,
      "learning_rate": 5e-06,
      "loss": -0.0033,
      "num_tokens": 25432013.0,
      "reward": 1.1660165786743164,
      "reward_std": 0.1343783736228943,
      "rewards/accuracy_reward": 0.37109375,
      "rewards/brier_reward": 0.609375,
      "rewards/confidence_one_or_zero": 0.9921875,
      "rewards/format_reward": 0.98046875,
      "rewards/mean_confidence_reward": 0.0,
      "step": 68
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.01171875,
      "completions/max_length": 915.0,
      "completions/max_terminated_length": 915.0,
      "completions/mean_length": 183.25,
      "completions/mean_terminated_length": 185.4229278564453,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 33.0,
      "epoch": 0.1104,
      "grad_norm": 0.0071678152307868,
      "learning_rate": 5e-06,
      "loss": 0.0051,
      "num_tokens": 25798581.0,
      "reward": 1.2304697036743164,
      "reward_std": 0.14793682098388672,
      "rewards/accuracy_reward": 0.515625,
      "rewards/brier_reward": 0.45703125,
      "rewards/confidence_one_or_zero": 0.98828125,
      "rewards/format_reward": 0.97265625,
      "rewards/mean_confidence_reward": 0.0,
      "step": 69
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.00390625,
      "completions/max_length": 1007.0,
      "completions/max_terminated_length": 1007.0,
      "completions/mean_length": 185.08984375,
      "completions/mean_terminated_length": 185.81570434570312,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 37.0,
      "epoch": 0.112,
      "grad_norm": 0.006619483698159456,
      "learning_rate": 5e-06,
      "loss": 0.015,
      "num_tokens": 26189180.0,
      "reward": 1.1679697036743164,
      "reward_std": 0.09055261313915253,
      "rewards/accuracy_reward": 0.3515625,
      "rewards/brier_reward": 0.640625,
      "rewards/confidence_one_or_zero": 0.99609375,
      "rewards/format_reward": 0.9921875,
      "rewards/mean_confidence_reward": 0.0,
      "step": 70
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 1036.0,
      "completions/max_terminated_length": 1036.0,
      "completions/mean_length": 165.5703125,
      "completions/mean_terminated_length": 165.5703125,
      "completions/min_length": 36.0,
      "completions/min_terminated_length": 36.0,
      "epoch": 0.1136,
      "grad_norm": 0.005290019791573286,
      "learning_rate": 5e-06,
      "loss": 0.0114,
      "num_tokens": 26565902.0,
      "reward": 1.2070322036743164,
      "reward_std": 0.10731258988380432,
      "rewards/accuracy_reward": 0.4140625,
      "rewards/brier_reward": 0.5859375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 71
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 488.0,
      "completions/max_terminated_length": 488.0,
      "completions/mean_length": 123.67578125,
      "completions/mean_terminated_length": 123.67578125,
      "completions/min_length": 37.0,
      "completions/min_terminated_length": 37.0,
      "epoch": 0.1152,
      "grad_norm": 0.006431462708860636,
      "learning_rate": 5e-06,
      "loss": -0.0074,
      "num_tokens": 26926955.0,
      "reward": 1.2207040786743164,
      "reward_std": 0.07384559512138367,
      "rewards/accuracy_reward": 0.44140625,
      "rewards/brier_reward": 0.55859375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 72
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 560.0,
      "completions/max_terminated_length": 560.0,
      "completions/mean_length": 131.01171875,
      "completions/mean_terminated_length": 131.01171875,
      "completions/min_length": 37.0,
      "completions/min_terminated_length": 37.0,
      "epoch": 0.1168,
      "grad_norm": 0.009269109927117825,
      "learning_rate": 5e-06,
      "loss": -0.0066,
      "num_tokens": 27304238.0,
      "reward": 1.0742197036743164,
      "reward_std": 0.07411082088947296,
      "rewards/accuracy_reward": 0.1875,
      "rewards/brier_reward": 0.79296875,
      "rewards/confidence_one_or_zero": 0.984375,
      "rewards/format_reward": 0.98046875,
      "rewards/mean_confidence_reward": 0.0,
      "step": 73
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 861.0,
      "completions/max_terminated_length": 861.0,
      "completions/mean_length": 122.14453125,
      "completions/mean_terminated_length": 122.14453125,
      "completions/min_length": 35.0,
      "completions/min_terminated_length": 35.0,
      "epoch": 0.1184,
      "grad_norm": 0.006270912941545248,
      "learning_rate": 5e-06,
      "loss": 0.0044,
      "num_tokens": 27661051.0,
      "reward": 1.2031259536743164,
      "reward_std": 0.09482251107692719,
      "rewards/accuracy_reward": 0.40625,
      "rewards/brier_reward": 0.59375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 74
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 652.0,
      "completions/max_terminated_length": 652.0,
      "completions/mean_length": 135.33984375,
      "completions/mean_terminated_length": 135.33984375,
      "completions/min_length": 35.0,
      "completions/min_terminated_length": 35.0,
      "epoch": 0.12,
      "grad_norm": 0.004971709102392197,
      "learning_rate": 5e-06,
      "loss": 0.0012,
      "num_tokens": 28045506.0,
      "reward": 1.1523447036743164,
      "reward_std": 0.0780605673789978,
      "rewards/accuracy_reward": 0.3125,
      "rewards/brier_reward": 0.68359375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.99609375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 75
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 695.0,
      "completions/max_terminated_length": 695.0,
      "completions/mean_length": 112.8828125,
      "completions/mean_terminated_length": 112.8828125,
      "completions/min_length": 33.0,
      "completions/min_terminated_length": 33.0,
      "epoch": 0.1216,
      "grad_norm": 0.0035235807299613953,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "num_tokens": 28410428.0,
      "reward": 1.1894540786743164,
      "reward_std": 0.034720130264759064,
      "rewards/accuracy_reward": 0.37890625,
      "rewards/brier_reward": 0.62109375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 76
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 555.0,
      "completions/max_terminated_length": 555.0,
      "completions/mean_length": 125.0078125,
      "completions/mean_terminated_length": 125.0078125,
      "completions/min_length": 37.0,
      "completions/min_terminated_length": 37.0,
      "epoch": 0.1232,
      "grad_norm": 0.003428579308092594,
      "learning_rate": 5e-06,
      "loss": -0.0027,
      "num_tokens": 28783238.0,
      "reward": 1.2128915786743164,
      "reward_std": 0.01913524977862835,
      "rewards/accuracy_reward": 0.42578125,
      "rewards/brier_reward": 0.57421875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 77
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 366.0,
      "completions/max_terminated_length": 366.0,
      "completions/mean_length": 123.5546875,
      "completions/mean_terminated_length": 123.5546875,
      "completions/min_length": 36.0,
      "completions/min_terminated_length": 36.0,
      "epoch": 0.1248,
      "grad_norm": 0.005758420564234257,
      "learning_rate": 5e-06,
      "loss": 0.0033,
      "num_tokens": 29151548.0,
      "reward": 1.2011728286743164,
      "reward_std": 0.08107856661081314,
      "rewards/accuracy_reward": 0.40234375,
      "rewards/brier_reward": 0.59765625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 78
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 475.0,
      "completions/max_terminated_length": 475.0,
      "completions/mean_length": 131.78125,
      "completions/mean_terminated_length": 131.78125,
      "completions/min_length": 37.0,
      "completions/min_terminated_length": 37.0,
      "epoch": 0.1264,
      "grad_norm": 0.006008731666952372,
      "learning_rate": 5e-06,
      "loss": -0.0007,
      "num_tokens": 29525276.0,
      "reward": 1.0976572036743164,
      "reward_std": 0.0864686369895935,
      "rewards/accuracy_reward": 0.1953125,
      "rewards/brier_reward": 0.8046875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 79
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 426.0,
      "completions/max_terminated_length": 426.0,
      "completions/mean_length": 134.1484375,
      "completions/mean_terminated_length": 134.1484375,
      "completions/min_length": 40.0,
      "completions/min_terminated_length": 40.0,
      "epoch": 0.128,
      "grad_norm": 0.006112709175795317,
      "learning_rate": 5e-06,
      "loss": 0.0037,
      "num_tokens": 29901738.0,
      "reward": 1.1035165786743164,
      "reward_std": 0.07299062609672546,
      "rewards/accuracy_reward": 0.21484375,
      "rewards/brier_reward": 0.78125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.99609375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 80
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 412.0,
      "completions/max_terminated_length": 412.0,
      "completions/mean_length": 127.109375,
      "completions/mean_terminated_length": 127.109375,
      "completions/min_length": 39.0,
      "completions/min_terminated_length": 39.0,
      "epoch": 0.1296,
      "grad_norm": 0.005416556261479855,
      "learning_rate": 5e-06,
      "loss": -0.002,
      "num_tokens": 30274126.0,
      "reward": 1.1484384536743164,
      "reward_std": 0.07536393404006958,
      "rewards/accuracy_reward": 0.296875,
      "rewards/brier_reward": 0.703125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 81
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 368.0,
      "completions/max_terminated_length": 368.0,
      "completions/mean_length": 130.44140625,
      "completions/mean_terminated_length": 130.44140625,
      "completions/min_length": 43.0,
      "completions/min_terminated_length": 43.0,
      "epoch": 0.1312,
      "grad_norm": 0.00545592000707984,
      "learning_rate": 5e-06,
      "loss": -0.0001,
      "num_tokens": 30650839.0,
      "reward": 1.1855478286743164,
      "reward_std": 0.08252204954624176,
      "rewards/accuracy_reward": 0.37109375,
      "rewards/brier_reward": 0.62890625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 82
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 368.0,
      "completions/max_terminated_length": 368.0,
      "completions/mean_length": 124.1796875,
      "completions/mean_terminated_length": 124.1796875,
      "completions/min_length": 42.0,
      "completions/min_terminated_length": 42.0,
      "epoch": 0.1328,
      "grad_norm": 0.0041496846824884415,
      "learning_rate": 5e-06,
      "loss": 0.0035,
      "num_tokens": 31020485.0,
      "reward": 1.2207040786743164,
      "reward_std": 0.053135842084884644,
      "rewards/accuracy_reward": 0.44140625,
      "rewards/brier_reward": 0.55859375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 83
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 399.0,
      "completions/max_terminated_length": 399.0,
      "completions/mean_length": 125.25390625,
      "completions/mean_terminated_length": 125.25390625,
      "completions/min_length": 42.0,
      "completions/min_terminated_length": 42.0,
      "epoch": 0.1344,
      "grad_norm": 0.0039185709320008755,
      "learning_rate": 5e-06,
      "loss": 0.0012,
      "num_tokens": 31402606.0,
      "reward": 1.2519540786743164,
      "reward_std": 0.043794769793748856,
      "rewards/accuracy_reward": 0.50390625,
      "rewards/brier_reward": 0.49609375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 84
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 516.0,
      "completions/max_terminated_length": 516.0,
      "completions/mean_length": 120.93359375,
      "completions/mean_terminated_length": 120.93359375,
      "completions/min_length": 43.0,
      "completions/min_terminated_length": 43.0,
      "epoch": 0.136,
      "grad_norm": 0.007022375240921974,
      "learning_rate": 5e-06,
      "loss": 0.0042,
      "num_tokens": 31768261.0,
      "reward": 1.2324228286743164,
      "reward_std": 0.07595369219779968,
      "rewards/accuracy_reward": 0.47265625,
      "rewards/brier_reward": 0.5234375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.99609375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 85
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 366.0,
      "completions/max_terminated_length": 366.0,
      "completions/mean_length": 103.8671875,
      "completions/mean_terminated_length": 103.8671875,
      "completions/min_length": 36.0,
      "completions/min_terminated_length": 36.0,
      "epoch": 0.1376,
      "grad_norm": 0.0054367585107684135,
      "learning_rate": 5e-06,
      "loss": 0.0036,
      "num_tokens": 32125435.0,
      "reward": 1.2050790786743164,
      "reward_std": 0.048331111669540405,
      "rewards/accuracy_reward": 0.41015625,
      "rewards/brier_reward": 0.58984375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 86
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 382.0,
      "completions/max_terminated_length": 382.0,
      "completions/mean_length": 95.42578125,
      "completions/mean_terminated_length": 95.42578125,
      "completions/min_length": 36.0,
      "completions/min_terminated_length": 36.0,
      "epoch": 0.1392,
      "grad_norm": 0.005786779802292585,
      "learning_rate": 5e-06,
      "loss": -0.007,
      "num_tokens": 32488520.0,
      "reward": 1.2714853286743164,
      "reward_std": 0.058260709047317505,
      "rewards/accuracy_reward": 0.54296875,
      "rewards/brier_reward": 0.45703125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 87
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 252.0,
      "completions/max_terminated_length": 252.0,
      "completions/mean_length": 94.78515625,
      "completions/mean_terminated_length": 94.78515625,
      "completions/min_length": 39.0,
      "completions/min_terminated_length": 39.0,
      "epoch": 0.1408,
      "grad_norm": 0.005196675658226013,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "num_tokens": 32844833.0,
      "reward": 1.1835947036743164,
      "reward_std": 0.045503467321395874,
      "rewards/accuracy_reward": 0.3671875,
      "rewards/brier_reward": 0.6328125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 88
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 318.0,
      "completions/max_terminated_length": 318.0,
      "completions/mean_length": 87.51953125,
      "completions/mean_terminated_length": 87.51953125,
      "completions/min_length": 41.0,
      "completions/min_terminated_length": 41.0,
      "epoch": 0.1424,
      "grad_norm": 0.0070787761360406876,
      "learning_rate": 5e-06,
      "loss": 0.0041,
      "num_tokens": 33212142.0,
      "reward": 1.1835947036743164,
      "reward_std": 0.04294103384017944,
      "rewards/accuracy_reward": 0.3671875,
      "rewards/brier_reward": 0.6328125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 89
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 191.0,
      "completions/max_terminated_length": 191.0,
      "completions/mean_length": 77.0390625,
      "completions/mean_terminated_length": 77.0390625,
      "completions/min_length": 38.0,
      "completions/min_terminated_length": 38.0,
      "epoch": 0.144,
      "grad_norm": 0.0065049161203205585,
      "learning_rate": 5e-06,
      "loss": -0.0026,
      "num_tokens": 33566784.0,
      "reward": 1.1757822036743164,
      "reward_std": 0.026633426547050476,
      "rewards/accuracy_reward": 0.3515625,
      "rewards/brier_reward": 0.6484375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 90
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 198.0,
      "completions/max_terminated_length": 198.0,
      "completions/mean_length": 74.1328125,
      "completions/mean_terminated_length": 74.1328125,
      "completions/min_length": 39.0,
      "completions/min_terminated_length": 39.0,
      "epoch": 0.1456,
      "grad_norm": 0.005245994310826063,
      "learning_rate": 5e-06,
      "loss": 0.0043,
      "num_tokens": 33911994.0,
      "reward": 1.2363290786743164,
      "reward_std": 0.03360118716955185,
      "rewards/accuracy_reward": 0.47265625,
      "rewards/brier_reward": 0.52734375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 91
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 192.0,
      "completions/max_terminated_length": 192.0,
      "completions/mean_length": 67.546875,
      "completions/mean_terminated_length": 67.546875,
      "completions/min_length": 40.0,
      "completions/min_terminated_length": 40.0,
      "epoch": 0.1472,
      "grad_norm": 0.007916582748293877,
      "learning_rate": 5e-06,
      "loss": -0.0011,
      "num_tokens": 34267734.0,
      "reward": 1.2011728286743164,
      "reward_std": 0.06917505711317062,
      "rewards/accuracy_reward": 0.40234375,
      "rewards/brier_reward": 0.59765625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 92
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 204.0,
      "completions/max_terminated_length": 204.0,
      "completions/mean_length": 66.01953125,
      "completions/mean_terminated_length": 66.01953125,
      "completions/min_length": 41.0,
      "completions/min_terminated_length": 41.0,
      "epoch": 0.1488,
      "grad_norm": 0.0072298673912882805,
      "learning_rate": 5e-06,
      "loss": -0.0054,
      "num_tokens": 34623507.0,
      "reward": 1.1621103286743164,
      "reward_std": 0.051558155566453934,
      "rewards/accuracy_reward": 0.32421875,
      "rewards/brier_reward": 0.67578125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 93
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 145.0,
      "completions/max_terminated_length": 145.0,
      "completions/mean_length": 63.97265625,
      "completions/mean_terminated_length": 63.97265625,
      "completions/min_length": 40.0,
      "completions/min_terminated_length": 40.0,
      "epoch": 0.1504,
      "grad_norm": 0.007007594686001539,
      "learning_rate": 5e-06,
      "loss": -0.0011,
      "num_tokens": 34973988.0,
      "reward": 1.1953134536743164,
      "reward_std": 0.05214790999889374,
      "rewards/accuracy_reward": 0.390625,
      "rewards/brier_reward": 0.609375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 94
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 147.0,
      "completions/max_terminated_length": 147.0,
      "completions/mean_length": 65.8203125,
      "completions/mean_terminated_length": 65.8203125,
      "completions/min_length": 41.0,
      "completions/min_terminated_length": 41.0,
      "epoch": 0.152,
      "grad_norm": 0.007378693204373121,
      "learning_rate": 5e-06,
      "loss": -0.0021,
      "num_tokens": 35338446.0,
      "reward": 1.1894540786743164,
      "reward_std": 0.043396592140197754,
      "rewards/accuracy_reward": 0.37890625,
      "rewards/brier_reward": 0.62109375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 95
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 136.0,
      "completions/max_terminated_length": 136.0,
      "completions/mean_length": 62.55859375,
      "completions/mean_terminated_length": 62.55859375,
      "completions/min_length": 39.0,
      "completions/min_terminated_length": 39.0,
      "epoch": 0.1536,
      "grad_norm": 0.0066678086295723915,
      "learning_rate": 5e-06,
      "loss": -0.0008,
      "num_tokens": 35707853.0,
      "reward": 1.1699228286743164,
      "reward_std": 0.03360118716955185,
      "rewards/accuracy_reward": 0.33984375,
      "rewards/brier_reward": 0.66015625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 96
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 204.0,
      "completions/max_terminated_length": 204.0,
      "completions/mean_length": 64.35546875,
      "completions/mean_terminated_length": 64.35546875,
      "completions/min_length": 39.0,
      "completions/min_terminated_length": 39.0,
      "epoch": 0.1552,
      "grad_norm": 0.004400665406137705,
      "learning_rate": 5e-06,
      "loss": 0.0016,
      "num_tokens": 36057144.0,
      "reward": 1.2226572036743164,
      "reward_std": 0.03189248964190483,
      "rewards/accuracy_reward": 0.4453125,
      "rewards/brier_reward": 0.5546875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 97
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 307.0,
      "completions/max_terminated_length": 307.0,
      "completions/mean_length": 66.6015625,
      "completions/mean_terminated_length": 66.6015625,
      "completions/min_length": 40.0,
      "completions/min_terminated_length": 40.0,
      "epoch": 0.1568,
      "grad_norm": 0.005063364747911692,
      "learning_rate": 5e-06,
      "loss": 0.0011,
      "num_tokens": 36401298.0,
      "reward": 1.1718759536743164,
      "reward_std": 0.026633426547050476,
      "rewards/accuracy_reward": 0.34375,
      "rewards/brier_reward": 0.65625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 98
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 186.0,
      "completions/max_terminated_length": 186.0,
      "completions/mean_length": 61.29296875,
      "completions/mean_terminated_length": 61.29296875,
      "completions/min_length": 39.0,
      "completions/min_terminated_length": 39.0,
      "epoch": 0.1584,
      "grad_norm": 0.005123145878314972,
      "learning_rate": 5e-06,
      "loss": 0.0015,
      "num_tokens": 36764013.0,
      "reward": 1.1933603286743164,
      "reward_std": 0.024924729019403458,
      "rewards/accuracy_reward": 0.38671875,
      "rewards/brier_reward": 0.61328125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 99
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 102.0,
      "completions/max_terminated_length": 102.0,
      "completions/mean_length": 57.15234375,
      "completions/mean_terminated_length": 57.15234375,
      "completions/min_length": 35.0,
      "completions/min_terminated_length": 35.0,
      "epoch": 0.16,
      "grad_norm": 0.005492492578923702,
      "learning_rate": 5e-06,
      "loss": 0.0008,
      "num_tokens": 37137556.0,
      "reward": 1.1953134536743164,
      "reward_std": 0.024659521877765656,
      "rewards/accuracy_reward": 0.390625,
      "rewards/brier_reward": 0.609375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 100
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 131.0,
      "completions/max_terminated_length": 131.0,
      "completions/mean_length": 56.99609375,
      "completions/mean_terminated_length": 56.99609375,
      "completions/min_length": 38.0,
      "completions/min_terminated_length": 38.0,
      "epoch": 0.1616,
      "grad_norm": 0.005264037288725376,
      "learning_rate": 5e-06,
      "loss": -0.0012,
      "num_tokens": 37502395.0,
      "reward": 1.1660165786743164,
      "reward_std": 0.02380579523742199,
      "rewards/accuracy_reward": 0.33984375,
      "rewards/brier_reward": 0.65625,
      "rewards/confidence_one_or_zero": 0.99609375,
      "rewards/format_reward": 0.99609375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 101
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 128.0,
      "completions/max_terminated_length": 128.0,
      "completions/mean_length": 53.05859375,
      "completions/mean_terminated_length": 53.05859375,
      "completions/min_length": 34.0,
      "completions/min_terminated_length": 34.0,
      "epoch": 0.1632,
      "grad_norm": 0.0073048085905611515,
      "learning_rate": 5e-06,
      "loss": 0.0006,
      "num_tokens": 37854850.0,
      "reward": 1.1425790786743164,
      "reward_std": 0.02169768325984478,
      "rewards/accuracy_reward": 0.28515625,
      "rewards/brier_reward": 0.71484375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 102
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 143.0,
      "completions/max_terminated_length": 143.0,
      "completions/mean_length": 55.15234375,
      "completions/mean_terminated_length": 55.15234375,
      "completions/min_length": 34.0,
      "completions/min_terminated_length": 34.0,
      "epoch": 0.1648,
      "grad_norm": 0.0033208683598786592,
      "learning_rate": 5e-06,
      "loss": -0.0001,
      "num_tokens": 38223889.0,
      "reward": 1.1660165786743164,
      "reward_std": 0.01657281443476677,
      "rewards/accuracy_reward": 0.33203125,
      "rewards/brier_reward": 0.66796875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 103
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 142.0,
      "completions/max_terminated_length": 142.0,
      "completions/mean_length": 53.171875,
      "completions/mean_terminated_length": 53.171875,
      "completions/min_length": 36.0,
      "completions/min_terminated_length": 36.0,
      "epoch": 0.1664,
      "grad_norm": 0.005567228887230158,
      "learning_rate": 5e-06,
      "loss": -0.0006,
      "num_tokens": 38574245.0,
      "reward": 1.1699228286743164,
      "reward_std": 0.028930652886629105,
      "rewards/accuracy_reward": 0.33984375,
      "rewards/brier_reward": 0.66015625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 104
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 117.0,
      "completions/max_terminated_length": 117.0,
      "completions/mean_length": 51.65234375,
      "completions/mean_terminated_length": 51.65234375,
      "completions/min_length": 35.0,
      "completions/min_terminated_length": 35.0,
      "epoch": 0.168,
      "grad_norm": 0.010346847586333752,
      "learning_rate": 5e-06,
      "loss": 0.0025,
      "num_tokens": 38937908.0,
      "reward": 1.2265634536743164,
      "reward_std": 0.05017400532960892,
      "rewards/accuracy_reward": 0.453125,
      "rewards/brier_reward": 0.546875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 105
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 108.0,
      "completions/max_terminated_length": 108.0,
      "completions/mean_length": 50.90234375,
      "completions/mean_terminated_length": 50.90234375,
      "completions/min_length": 35.0,
      "completions/min_terminated_length": 35.0,
      "epoch": 0.1696,
      "grad_norm": 0.009891422465443611,
      "learning_rate": 5e-06,
      "loss": -0.0006,
      "num_tokens": 39307219.0,
      "reward": 1.1503915786743164,
      "reward_std": 0.04464973136782646,
      "rewards/accuracy_reward": 0.30078125,
      "rewards/brier_reward": 0.69921875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 106
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 100.0,
      "completions/max_terminated_length": 100.0,
      "completions/mean_length": 52.31640625,
      "completions/mean_terminated_length": 52.31640625,
      "completions/min_length": 34.0,
      "completions/min_terminated_length": 34.0,
      "epoch": 0.1712,
      "grad_norm": 0.006135431118309498,
      "learning_rate": 5e-06,
      "loss": -0.001,
      "num_tokens": 39671956.0,
      "reward": 1.1972665786743164,
      "reward_std": 0.03215769678354263,
      "rewards/accuracy_reward": 0.39453125,
      "rewards/brier_reward": 0.60546875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 107
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 88.0,
      "completions/max_terminated_length": 88.0,
      "completions/mean_length": 48.3828125,
      "completions/mean_terminated_length": 48.3828125,
      "completions/min_length": 35.0,
      "completions/min_terminated_length": 35.0,
      "epoch": 0.1728,
      "grad_norm": 0.006157853174954653,
      "learning_rate": 5e-06,
      "loss": -0.0006,
      "num_tokens": 40026910.0,
      "reward": 1.1972665786743164,
      "reward_std": 0.022552644833922386,
      "rewards/accuracy_reward": 0.39453125,
      "rewards/brier_reward": 0.60546875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 108
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 76.0,
      "completions/max_terminated_length": 76.0,
      "completions/mean_length": 47.84375,
      "completions/mean_terminated_length": 47.84375,
      "completions/min_length": 35.0,
      "completions/min_terminated_length": 35.0,
      "epoch": 0.1744,
      "grad_norm": 0.009094290435314178,
      "learning_rate": 5e-06,
      "loss": -0.0005,
      "num_tokens": 40372246.0,
      "reward": 1.1757822036743164,
      "reward_std": 0.03998042270541191,
      "rewards/accuracy_reward": 0.3515625,
      "rewards/brier_reward": 0.6484375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 109
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 70.0,
      "completions/max_terminated_length": 70.0,
      "completions/mean_length": 46.38671875,
      "completions/mean_terminated_length": 46.38671875,
      "completions/min_length": 34.0,
      "completions/min_terminated_length": 34.0,
      "epoch": 0.176,
      "grad_norm": 0.007714184932410717,
      "learning_rate": 5e-06,
      "loss": -0.0005,
      "num_tokens": 40728177.0,
      "reward": 1.1464853286743164,
      "reward_std": 0.04083415865898132,
      "rewards/accuracy_reward": 0.29296875,
      "rewards/brier_reward": 0.70703125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 110
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 84.0,
      "completions/max_terminated_length": 84.0,
      "completions/mean_length": 46.9453125,
      "completions/mean_terminated_length": 46.9453125,
      "completions/min_length": 35.0,
      "completions/min_terminated_length": 35.0,
      "epoch": 0.1776,
      "grad_norm": 0.007513863034546375,
      "learning_rate": 5e-06,
      "loss": 0.0019,
      "num_tokens": 41081603.0,
      "reward": 1.1660165786743164,
      "reward_std": 0.01913524977862835,
      "rewards/accuracy_reward": 0.33203125,
      "rewards/brier_reward": 0.66796875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 111
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 68.0,
      "completions/max_terminated_length": 68.0,
      "completions/mean_length": 45.87890625,
      "completions/mean_terminated_length": 45.87890625,
      "completions/min_length": 33.0,
      "completions/min_terminated_length": 33.0,
      "epoch": 0.1792,
      "grad_norm": 0.005671597085893154,
      "learning_rate": 5e-06,
      "loss": 0.0003,
      "num_tokens": 41441476.0,
      "reward": 1.1503915786743164,
      "reward_std": 0.022552644833922386,
      "rewards/accuracy_reward": 0.30078125,
      "rewards/brier_reward": 0.69921875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 112
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 81.0,
      "completions/max_terminated_length": 81.0,
      "completions/mean_length": 46.2265625,
      "completions/mean_terminated_length": 46.2265625,
      "completions/min_length": 33.0,
      "completions/min_terminated_length": 33.0,
      "epoch": 0.1808,
      "grad_norm": 0.0054357945919036865,
      "learning_rate": 5e-06,
      "loss": -0.0007,
      "num_tokens": 41776358.0,
      "reward": 1.2968759536743164,
      "reward_std": 0.03189249336719513,
      "rewards/accuracy_reward": 0.59375,
      "rewards/brier_reward": 0.40625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 113
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 66.0,
      "completions/max_terminated_length": 66.0,
      "completions/mean_length": 46.6484375,
      "completions/mean_terminated_length": 46.6484375,
      "completions/min_length": 35.0,
      "completions/min_terminated_length": 35.0,
      "epoch": 0.1824,
      "grad_norm": 0.009192634373903275,
      "learning_rate": 5e-06,
      "loss": -0.0013,
      "num_tokens": 42121340.0,
      "reward": 1.1933603286743164,
      "reward_std": 0.06535948067903519,
      "rewards/accuracy_reward": 0.38671875,
      "rewards/brier_reward": 0.61328125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 114
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 82.0,
      "completions/max_terminated_length": 82.0,
      "completions/mean_length": 46.59765625,
      "completions/mean_terminated_length": 46.59765625,
      "completions/min_length": 33.0,
      "completions/min_terminated_length": 33.0,
      "epoch": 0.184,
      "grad_norm": 0.00554991140961647,
      "learning_rate": 5e-06,
      "loss": -0.0004,
      "num_tokens": 42475581.0,
      "reward": 1.1445322036743164,
      "reward_std": 0.03189248964190483,
      "rewards/accuracy_reward": 0.3515625,
      "rewards/brier_reward": 0.6171875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.96875,
      "rewards/mean_confidence_reward": 0.0,
      "step": 115
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 77.0,
      "completions/max_terminated_length": 77.0,
      "completions/mean_length": 47.359375,
      "completions/mean_terminated_length": 47.359375,
      "completions/min_length": 34.0,
      "completions/min_terminated_length": 34.0,
      "epoch": 0.1856,
      "grad_norm": 0.046929169446229935,
      "learning_rate": 5e-06,
      "loss": -0.0028,
      "num_tokens": 42829713.0,
      "reward": 1.1660165786743164,
      "reward_std": 0.12684404850006104,
      "rewards/accuracy_reward": 0.41796875,
      "rewards/brier_reward": 0.5390625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.95703125,
      "rewards/mean_confidence_reward": 0.0,
      "step": 116
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 85.0,
      "completions/max_terminated_length": 85.0,
      "completions/mean_length": 49.31640625,
      "completions/mean_terminated_length": 49.31640625,
      "completions/min_length": 36.0,
      "completions/min_terminated_length": 36.0,
      "epoch": 0.1872,
      "grad_norm": 0.00579815125092864,
      "learning_rate": 5e-06,
      "loss": -0.0,
      "num_tokens": 43172258.0,
      "reward": 1.1621103286743164,
      "reward_std": 0.01275724172592163,
      "rewards/accuracy_reward": 0.32421875,
      "rewards/brier_reward": 0.67578125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 117
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 99.0,
      "completions/max_terminated_length": 99.0,
      "completions/mean_length": 50.3984375,
      "completions/mean_terminated_length": 50.3984375,
      "completions/min_length": 36.0,
      "completions/min_terminated_length": 36.0,
      "epoch": 0.1888,
      "grad_norm": 0.005210595671087503,
      "learning_rate": 5e-06,
      "loss": 0.0009,
      "num_tokens": 43517144.0,
      "reward": 1.1601572036743164,
      "reward_std": 0.043661803007125854,
      "rewards/accuracy_reward": 0.3203125,
      "rewards/brier_reward": 0.6796875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 118
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 108.0,
      "completions/max_terminated_length": 108.0,
      "completions/mean_length": 52.4453125,
      "completions/mean_terminated_length": 52.4453125,
      "completions/min_length": 35.0,
      "completions/min_terminated_length": 35.0,
      "epoch": 0.1904,
      "grad_norm": 0.007191211450845003,
      "learning_rate": 5e-06,
      "loss": 0.0008,
      "num_tokens": 43867754.0,
      "reward": 1.1621103286743164,
      "reward_std": 0.037416763603687286,
      "rewards/accuracy_reward": 0.32421875,
      "rewards/brier_reward": 0.67578125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 119
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 109.0,
      "completions/max_terminated_length": 109.0,
      "completions/mean_length": 51.90234375,
      "completions/mean_terminated_length": 51.90234375,
      "completions/min_length": 34.0,
      "completions/min_terminated_length": 34.0,
      "epoch": 0.192,
      "grad_norm": 0.007046000100672245,
      "learning_rate": 5e-06,
      "loss": -0.0008,
      "num_tokens": 44204993.0,
      "reward": 1.2402353286743164,
      "reward_std": 0.05695141479372978,
      "rewards/accuracy_reward": 0.48046875,
      "rewards/brier_reward": 0.51953125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 120
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 149.0,
      "completions/max_terminated_length": 149.0,
      "completions/mean_length": 53.69921875,
      "completions/mean_terminated_length": 53.69921875,
      "completions/min_length": 35.0,
      "completions/min_terminated_length": 35.0,
      "epoch": 0.1936,
      "grad_norm": 0.009322714060544968,
      "learning_rate": 5e-06,
      "loss": 0.0004,
      "num_tokens": 44537516.0,
      "reward": 1.2539072036743164,
      "reward_std": 0.0672023743391037,
      "rewards/accuracy_reward": 0.5078125,
      "rewards/brier_reward": 0.4921875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 121
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 113.0,
      "completions/max_terminated_length": 113.0,
      "completions/mean_length": 54.3984375,
      "completions/mean_terminated_length": 54.3984375,
      "completions/min_length": 36.0,
      "completions/min_terminated_length": 36.0,
      "epoch": 0.1952,
      "grad_norm": 0.007987559773027897,
      "learning_rate": 5e-06,
      "loss": -0.0028,
      "num_tokens": 44894378.0,
      "reward": 1.1679697036743164,
      "reward_std": 0.0674663633108139,
      "rewards/accuracy_reward": 0.34375,
      "rewards/brier_reward": 0.65234375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.99609375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 122
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 105.0,
      "completions/max_terminated_length": 105.0,
      "completions/mean_length": 53.44921875,
      "completions/mean_terminated_length": 53.44921875,
      "completions/min_length": 36.0,
      "completions/min_terminated_length": 36.0,
      "epoch": 0.1968,
      "grad_norm": 0.005494001787155867,
      "learning_rate": 5e-06,
      "loss": -0.0012,
      "num_tokens": 45252013.0,
      "reward": 1.2617197036743164,
      "reward_std": 0.044914938509464264,
      "rewards/accuracy_reward": 0.5234375,
      "rewards/brier_reward": 0.4765625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 123
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 191.0,
      "completions/max_terminated_length": 191.0,
      "completions/mean_length": 55.171875,
      "completions/mean_terminated_length": 55.171875,
      "completions/min_length": 36.0,
      "completions/min_terminated_length": 36.0,
      "epoch": 0.1984,
      "grad_norm": 0.007676423992961645,
      "learning_rate": 5e-06,
      "loss": 0.0046,
      "num_tokens": 45605305.0,
      "reward": 1.1679697036743164,
      "reward_std": 0.039125457406044006,
      "rewards/accuracy_reward": 0.3359375,
      "rewards/brier_reward": 0.6640625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 124
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 120.0,
      "completions/max_terminated_length": 120.0,
      "completions/mean_length": 54.44921875,
      "completions/mean_terminated_length": 54.44921875,
      "completions/min_length": 37.0,
      "completions/min_terminated_length": 37.0,
      "epoch": 0.2,
      "grad_norm": 0.008286594413220882,
      "learning_rate": 5e-06,
      "loss": -0.0016,
      "num_tokens": 45965436.0,
      "reward": 1.1406259536743164,
      "reward_std": 0.04635842889547348,
      "rewards/accuracy_reward": 0.2890625,
      "rewards/brier_reward": 0.70703125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.99609375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 125
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 126.0,
      "completions/max_terminated_length": 126.0,
      "completions/mean_length": 56.96484375,
      "completions/mean_terminated_length": 56.96484375,
      "completions/min_length": 36.0,
      "completions/min_terminated_length": 36.0,
      "epoch": 0.2016,
      "grad_norm": 0.0051973238587379456,
      "learning_rate": 5e-06,
      "loss": 0.002,
      "num_tokens": 46328467.0,
      "reward": 1.2343759536743164,
      "reward_std": 0.03998042270541191,
      "rewards/accuracy_reward": 0.46875,
      "rewards/brier_reward": 0.53125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 126
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 118.0,
      "completions/max_terminated_length": 118.0,
      "completions/mean_length": 55.6640625,
      "completions/mean_terminated_length": 55.6640625,
      "completions/min_length": 37.0,
      "completions/min_terminated_length": 37.0,
      "epoch": 0.2032,
      "grad_norm": 0.002425758633762598,
      "learning_rate": 5e-06,
      "loss": -0.001,
      "num_tokens": 46691533.0,
      "reward": 1.1601572036743164,
      "reward_std": 0.011048543266952038,
      "rewards/accuracy_reward": 0.3203125,
      "rewards/brier_reward": 0.6796875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 127
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 102.0,
      "completions/max_terminated_length": 102.0,
      "completions/mean_length": 54.59765625,
      "completions/mean_terminated_length": 54.59765625,
      "completions/min_length": 36.0,
      "completions/min_terminated_length": 36.0,
      "epoch": 0.2048,
      "grad_norm": 0.014877156354486942,
      "learning_rate": 5e-06,
      "loss": -0.0003,
      "num_tokens": 47053270.0,
      "reward": 1.2460947036743164,
      "reward_std": 0.07285766303539276,
      "rewards/accuracy_reward": 0.4921875,
      "rewards/brier_reward": 0.5078125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 128
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 179.0,
      "completions/max_terminated_length": 179.0,
      "completions/mean_length": 55.13671875,
      "completions/mean_terminated_length": 55.13671875,
      "completions/min_length": 28.0,
      "completions/min_terminated_length": 28.0,
      "epoch": 0.2064,
      "grad_norm": 0.006909608840942383,
      "learning_rate": 5e-06,
      "loss": 0.0005,
      "num_tokens": 47414457.0,
      "reward": 1.2070322036743164,
      "reward_std": 0.036563023924827576,
      "rewards/accuracy_reward": 0.4140625,
      "rewards/brier_reward": 0.5859375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 129
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 167.0,
      "completions/max_terminated_length": 167.0,
      "completions/mean_length": 53.84375,
      "completions/mean_terminated_length": 53.84375,
      "completions/min_length": 25.0,
      "completions/min_terminated_length": 25.0,
      "epoch": 0.208,
      "grad_norm": 0.003339196555316448,
      "learning_rate": 5e-06,
      "loss": 0.0002,
      "num_tokens": 47752457.0,
      "reward": 1.1464853286743164,
      "reward_std": 0.0191352479159832,
      "rewards/accuracy_reward": 0.29296875,
      "rewards/brier_reward": 0.70703125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 130
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 179.0,
      "completions/max_terminated_length": 179.0,
      "completions/mean_length": 55.34765625,
      "completions/mean_terminated_length": 55.34765625,
      "completions/min_length": 27.0,
      "completions/min_terminated_length": 27.0,
      "epoch": 0.2096,
      "grad_norm": 0.004676603712141514,
      "learning_rate": 5e-06,
      "loss": 0.0018,
      "num_tokens": 48113242.0,
      "reward": 1.2128915786743164,
      "reward_std": 0.03597327321767807,
      "rewards/accuracy_reward": 0.42578125,
      "rewards/brier_reward": 0.57421875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 131
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 168.0,
      "completions/max_terminated_length": 168.0,
      "completions/mean_length": 53.95703125,
      "completions/mean_terminated_length": 53.95703125,
      "completions/min_length": 26.0,
      "completions/min_terminated_length": 26.0,
      "epoch": 0.2112,
      "grad_norm": 0.003998136613518,
      "learning_rate": 5e-06,
      "loss": 0.0012,
      "num_tokens": 48471623.0,
      "reward": 1.1308603286743164,
      "reward_std": 0.0191352479159832,
      "rewards/accuracy_reward": 0.26171875,
      "rewards/brier_reward": 0.73828125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 132
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 177.0,
      "completions/max_terminated_length": 177.0,
      "completions/mean_length": 52.5625,
      "completions/mean_terminated_length": 52.5625,
      "completions/min_length": 35.0,
      "completions/min_terminated_length": 35.0,
      "epoch": 0.2128,
      "grad_norm": 0.0053713698871433735,
      "learning_rate": 5e-06,
      "loss": -0.002,
      "num_tokens": 48821807.0,
      "reward": 1.1210947036743164,
      "reward_std": 0.04024440422654152,
      "rewards/accuracy_reward": 0.2421875,
      "rewards/brier_reward": 0.7578125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 133
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 112.0,
      "completions/max_terminated_length": 112.0,
      "completions/mean_length": 51.9765625,
      "completions/mean_terminated_length": 51.9765625,
      "completions/min_length": 32.0,
      "completions/min_terminated_length": 32.0,
      "epoch": 0.2144,
      "grad_norm": 0.005026605445891619,
      "learning_rate": 5e-06,
      "loss": -0.0006,
      "num_tokens": 49169657.0,
      "reward": 1.1835947036743164,
      "reward_std": 0.020843947306275368,
      "rewards/accuracy_reward": 0.3671875,
      "rewards/brier_reward": 0.6328125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 134
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 122.0,
      "completions/max_terminated_length": 122.0,
      "completions/mean_length": 53.65625,
      "completions/mean_terminated_length": 53.65625,
      "completions/min_length": 33.0,
      "completions/min_terminated_length": 33.0,
      "epoch": 0.216,
      "grad_norm": 0.010881892405450344,
      "learning_rate": 5e-06,
      "loss": -0.0006,
      "num_tokens": 49516481.0,
      "reward": 1.2324228286743164,
      "reward_std": 0.03360118716955185,
      "rewards/accuracy_reward": 0.46484375,
      "rewards/brier_reward": 0.53515625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 135
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 135.0,
      "completions/max_terminated_length": 135.0,
      "completions/mean_length": 56.70703125,
      "completions/mean_terminated_length": 56.70703125,
      "completions/min_length": 37.0,
      "completions/min_terminated_length": 37.0,
      "epoch": 0.2176,
      "grad_norm": 0.00886172242462635,
      "learning_rate": 5e-06,
      "loss": 0.0028,
      "num_tokens": 49888774.0,
      "reward": 1.2050790786743164,
      "reward_std": 0.030904557555913925,
      "rewards/accuracy_reward": 0.41015625,
      "rewards/brier_reward": 0.58984375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 136
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 107.0,
      "completions/max_terminated_length": 107.0,
      "completions/mean_length": 52.28125,
      "completions/mean_terminated_length": 52.28125,
      "completions/min_length": 26.0,
      "completions/min_terminated_length": 26.0,
      "epoch": 0.2192,
      "grad_norm": 0.004887416493147612,
      "learning_rate": 5e-06,
      "loss": -0.0013,
      "num_tokens": 50247878.0,
      "reward": 1.2304697036743164,
      "reward_std": 0.03642883151769638,
      "rewards/accuracy_reward": 0.4609375,
      "rewards/brier_reward": 0.5390625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 137
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 133.0,
      "completions/max_terminated_length": 133.0,
      "completions/mean_length": 55.6171875,
      "completions/mean_terminated_length": 55.6171875,
      "completions/min_length": 37.0,
      "completions/min_terminated_length": 37.0,
      "epoch": 0.2208,
      "grad_norm": 0.00412516575306654,
      "learning_rate": 5e-06,
      "loss": 0.0006,
      "num_tokens": 50610956.0,
      "reward": 1.2421884536743164,
      "reward_std": 0.024659521877765656,
      "rewards/accuracy_reward": 0.484375,
      "rewards/brier_reward": 0.515625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 138
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 253.0,
      "completions/max_terminated_length": 253.0,
      "completions/mean_length": 58.73046875,
      "completions/mean_terminated_length": 58.73046875,
      "completions/min_length": 31.0,
      "completions/min_terminated_length": 31.0,
      "epoch": 0.2224,
      "grad_norm": 0.002713292371481657,
      "learning_rate": 5e-06,
      "loss": -0.0005,
      "num_tokens": 50967759.0,
      "reward": 1.1269540786743164,
      "reward_std": 0.01275724172592163,
      "rewards/accuracy_reward": 0.25390625,
      "rewards/brier_reward": 0.74609375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 139
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 174.0,
      "completions/max_terminated_length": 174.0,
      "completions/mean_length": 54.40625,
      "completions/mean_terminated_length": 54.40625,
      "completions/min_length": 27.0,
      "completions/min_terminated_length": 27.0,
      "epoch": 0.224,
      "grad_norm": 0.007535545155405998,
      "learning_rate": 5e-06,
      "loss": -0.002,
      "num_tokens": 51329615.0,
      "reward": 1.2421884536743164,
      "reward_std": 0.04379599541425705,
      "rewards/accuracy_reward": 0.4921875,
      "rewards/brier_reward": 0.50390625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.99609375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 140
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 191.0,
      "completions/max_terminated_length": 191.0,
      "completions/mean_length": 59.91796875,
      "completions/mean_terminated_length": 59.91796875,
      "completions/min_length": 26.0,
      "completions/min_terminated_length": 26.0,
      "epoch": 0.2256,
      "grad_norm": 0.005773982498794794,
      "learning_rate": 5e-06,
      "loss": -0.0002,
      "num_tokens": 51693218.0,
      "reward": 1.1855478286743164,
      "reward_std": 0.05615260452032089,
      "rewards/accuracy_reward": 0.37109375,
      "rewards/brier_reward": 0.62890625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 141
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 223.0,
      "completions/max_terminated_length": 223.0,
      "completions/mean_length": 62.546875,
      "completions/mean_terminated_length": 62.546875,
      "completions/min_length": 23.0,
      "completions/min_terminated_length": 23.0,
      "epoch": 0.2272,
      "grad_norm": 0.007854162715375423,
      "learning_rate": 5e-06,
      "loss": 0.0023,
      "num_tokens": 52067630.0,
      "reward": 1.2011728286743164,
      "reward_std": 0.08844131231307983,
      "rewards/accuracy_reward": 0.41796875,
      "rewards/brier_reward": 0.57421875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.9921875,
      "rewards/mean_confidence_reward": 0.0,
      "step": 142
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 182.0,
      "completions/max_terminated_length": 182.0,
      "completions/mean_length": 58.87890625,
      "completions/mean_terminated_length": 58.87890625,
      "completions/min_length": 31.0,
      "completions/min_terminated_length": 31.0,
      "epoch": 0.2288,
      "grad_norm": 0.006240553688257933,
      "learning_rate": 5e-06,
      "loss": -0.0005,
      "num_tokens": 52440703.0,
      "reward": 1.1914072036743164,
      "reward_std": 0.05740697309374809,
      "rewards/accuracy_reward": 0.390625,
      "rewards/brier_reward": 0.60546875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.99609375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 143
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 180.0,
      "completions/max_terminated_length": 180.0,
      "completions/mean_length": 53.40234375,
      "completions/mean_terminated_length": 53.40234375,
      "completions/min_length": 25.0,
      "completions/min_terminated_length": 25.0,
      "epoch": 0.2304,
      "grad_norm": 0.004978107754141092,
      "learning_rate": 5e-06,
      "loss": 0.0008,
      "num_tokens": 52792606.0,
      "reward": 1.1933603286743164,
      "reward_std": 0.04208730161190033,
      "rewards/accuracy_reward": 0.38671875,
      "rewards/brier_reward": 0.61328125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 144
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 120.0,
      "completions/max_terminated_length": 120.0,
      "completions/mean_length": 53.58984375,
      "completions/mean_terminated_length": 53.58984375,
      "completions/min_length": 27.0,
      "completions/min_terminated_length": 27.0,
      "epoch": 0.232,
      "grad_norm": 0.003977401647716761,
      "learning_rate": 5e-06,
      "loss": 0.0014,
      "num_tokens": 53163565.0,
      "reward": 1.1914072036743164,
      "reward_std": 0.03445492684841156,
      "rewards/accuracy_reward": 0.3828125,
      "rewards/brier_reward": 0.6171875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 145
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 127.0,
      "completions/max_terminated_length": 127.0,
      "completions/mean_length": 51.46484375,
      "completions/mean_terminated_length": 51.46484375,
      "completions/min_length": 29.0,
      "completions/min_terminated_length": 29.0,
      "epoch": 0.2336,
      "grad_norm": 0.003525414504110813,
      "learning_rate": 5e-06,
      "loss": -0.0004,
      "num_tokens": 53525860.0,
      "reward": 1.2343759536743164,
      "reward_std": 0.020843947306275368,
      "rewards/accuracy_reward": 0.46875,
      "rewards/brier_reward": 0.53125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 146
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 107.0,
      "completions/max_terminated_length": 107.0,
      "completions/mean_length": 49.3125,
      "completions/mean_terminated_length": 49.3125,
      "completions/min_length": 25.0,
      "completions/min_terminated_length": 25.0,
      "epoch": 0.2352,
      "grad_norm": 0.0049398792907595634,
      "learning_rate": 5e-06,
      "loss": -0.0,
      "num_tokens": 53873428.0,
      "reward": 1.2675790786743164,
      "reward_std": 0.04662363603711128,
      "rewards/accuracy_reward": 0.53515625,
      "rewards/brier_reward": 0.46484375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 147
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 154.0,
      "completions/max_terminated_length": 154.0,
      "completions/mean_length": 50.09375,
      "completions/mean_terminated_length": 50.09375,
      "completions/min_length": 25.0,
      "completions/min_terminated_length": 25.0,
      "epoch": 0.2368,
      "grad_norm": 0.0061876606196165085,
      "learning_rate": 5e-06,
      "loss": -0.0018,
      "num_tokens": 54229540.0,
      "reward": 1.2695322036743164,
      "reward_std": 0.0388009138405323,
      "rewards/accuracy_reward": 0.5390625,
      "rewards/brier_reward": 0.4609375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 148
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 91.0,
      "completions/max_terminated_length": 91.0,
      "completions/mean_length": 50.296875,
      "completions/mean_terminated_length": 50.296875,
      "completions/min_length": 29.0,
      "completions/min_terminated_length": 29.0,
      "epoch": 0.2384,
      "grad_norm": 0.009590424597263336,
      "learning_rate": 5e-06,
      "loss": 0.0004,
      "num_tokens": 54591136.0,
      "reward": 1.1875009536743164,
      "reward_std": 0.05582928657531738,
      "rewards/accuracy_reward": 0.375,
      "rewards/brier_reward": 0.625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 149
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 114.0,
      "completions/max_terminated_length": 114.0,
      "completions/mean_length": 50.74609375,
      "completions/mean_terminated_length": 50.74609375,
      "completions/min_length": 27.0,
      "completions/min_terminated_length": 27.0,
      "epoch": 0.24,
      "grad_norm": 0.006619809195399284,
      "learning_rate": 5e-06,
      "loss": -0.0013,
      "num_tokens": 54930119.0,
      "reward": 1.1210947036743164,
      "reward_std": 0.04024440422654152,
      "rewards/accuracy_reward": 0.2421875,
      "rewards/brier_reward": 0.7578125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 150
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 110.0,
      "completions/max_terminated_length": 110.0,
      "completions/mean_length": 49.984375,
      "completions/mean_terminated_length": 49.984375,
      "completions/min_length": 26.0,
      "completions/min_terminated_length": 26.0,
      "epoch": 0.2416,
      "grad_norm": 0.005861316341906786,
      "learning_rate": 5e-06,
      "loss": -0.0006,
      "num_tokens": 55283315.0,
      "reward": 1.2558603286743164,
      "reward_std": 0.03616362065076828,
      "rewards/accuracy_reward": 0.51171875,
      "rewards/brier_reward": 0.48828125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 151
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 122.0,
      "completions/max_terminated_length": 122.0,
      "completions/mean_length": 49.63671875,
      "completions/mean_terminated_length": 49.63671875,
      "completions/min_length": 25.0,
      "completions/min_terminated_length": 25.0,
      "epoch": 0.2432,
      "grad_norm": 0.00885644182562828,
      "learning_rate": 5e-06,
      "loss": 0.0005,
      "num_tokens": 55623406.0,
      "reward": 1.1523447036743164,
      "reward_std": 0.04294103384017944,
      "rewards/accuracy_reward": 0.3125,
      "rewards/brier_reward": 0.68359375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.99609375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 152
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 153.0,
      "completions/max_terminated_length": 153.0,
      "completions/mean_length": 51.5,
      "completions/mean_terminated_length": 51.5,
      "completions/min_length": 26.0,
      "completions/min_terminated_length": 26.0,
      "epoch": 0.2448,
      "grad_norm": 0.007674382999539375,
      "learning_rate": 5e-06,
      "loss": -0.0001,
      "num_tokens": 55979030.0,
      "reward": 1.2070322036743164,
      "reward_std": 0.047477371990680695,
      "rewards/accuracy_reward": 0.4140625,
      "rewards/brier_reward": 0.5859375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 153
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 156.0,
      "completions/max_terminated_length": 156.0,
      "completions/mean_length": 50.91796875,
      "completions/mean_terminated_length": 50.91796875,
      "completions/min_length": 34.0,
      "completions/min_terminated_length": 34.0,
      "epoch": 0.2464,
      "grad_norm": 0.005602710880339146,
      "learning_rate": 5e-06,
      "loss": 0.0005,
      "num_tokens": 56334569.0,
      "reward": 1.2578134536743164,
      "reward_std": 0.04037860035896301,
      "rewards/accuracy_reward": 0.5234375,
      "rewards/brier_reward": 0.47265625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.99609375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 154
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.00390625,
      "completions/max_length": 98.0,
      "completions/max_terminated_length": 98.0,
      "completions/mean_length": 50.79296875,
      "completions/mean_terminated_length": 50.99216079711914,
      "completions/min_length": 0.0,
      "completions/min_terminated_length": 37.0,
      "epoch": 0.248,
      "grad_norm": 0.007848069071769714,
      "learning_rate": 5e-06,
      "loss": -0.0042,
      "num_tokens": 56695340.0,
      "reward": 1.1523447036743164,
      "reward_std": 0.04892086982727051,
      "rewards/accuracy_reward": 0.3203125,
      "rewards/brier_reward": 0.671875,
      "rewards/confidence_one_or_zero": 0.99609375,
      "rewards/format_reward": 0.9921875,
      "rewards/mean_confidence_reward": 0.0,
      "step": 155
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 140.0,
      "completions/max_terminated_length": 140.0,
      "completions/mean_length": 52.45703125,
      "completions/mean_terminated_length": 52.45703125,
      "completions/min_length": 33.0,
      "completions/min_terminated_length": 33.0,
      "epoch": 0.2496,
      "grad_norm": 0.005280786659568548,
      "learning_rate": 5e-06,
      "loss": -0.0015,
      "num_tokens": 57050241.0,
      "reward": 1.2246103286743164,
      "reward_std": 0.03741675987839699,
      "rewards/accuracy_reward": 0.44921875,
      "rewards/brier_reward": 0.55078125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 156
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 110.0,
      "completions/max_terminated_length": 110.0,
      "completions/mean_length": 50.06640625,
      "completions/mean_terminated_length": 50.06640625,
      "completions/min_length": 27.0,
      "completions/min_terminated_length": 27.0,
      "epoch": 0.2512,
      "grad_norm": 0.006250562611967325,
      "learning_rate": 5e-06,
      "loss": 0.0014,
      "num_tokens": 57398938.0,
      "reward": 1.2070322036743164,
      "reward_std": 0.04747737571597099,
      "rewards/accuracy_reward": 0.4140625,
      "rewards/brier_reward": 0.5859375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 157
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 111.0,
      "completions/max_terminated_length": 111.0,
      "completions/mean_length": 51.06640625,
      "completions/mean_terminated_length": 51.06640625,
      "completions/min_length": 34.0,
      "completions/min_terminated_length": 34.0,
      "epoch": 0.2528,
      "grad_norm": 0.011759904213249683,
      "learning_rate": 5e-06,
      "loss": 0.0034,
      "num_tokens": 57770347.0,
      "reward": 1.2226572036743164,
      "reward_std": 0.06490392982959747,
      "rewards/accuracy_reward": 0.4453125,
      "rewards/brier_reward": 0.5546875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 158
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 113.0,
      "completions/max_terminated_length": 113.0,
      "completions/mean_length": 51.4765625,
      "completions/mean_terminated_length": 51.4765625,
      "completions/min_length": 35.0,
      "completions/min_terminated_length": 35.0,
      "epoch": 0.2544,
      "grad_norm": 0.006999201141297817,
      "learning_rate": 5e-06,
      "loss": 0.0002,
      "num_tokens": 58126709.0,
      "reward": 1.1386728286743164,
      "reward_std": 0.037416763603687286,
      "rewards/accuracy_reward": 0.28515625,
      "rewards/brier_reward": 0.7109375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.99609375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 159
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 76.0,
      "completions/max_terminated_length": 76.0,
      "completions/mean_length": 47.21484375,
      "completions/mean_terminated_length": 47.21484375,
      "completions/min_length": 30.0,
      "completions/min_terminated_length": 30.0,
      "epoch": 0.256,
      "grad_norm": 0.0068825832568109035,
      "learning_rate": 5e-06,
      "loss": 0.0004,
      "num_tokens": 58472412.0,
      "reward": 1.2031259536743164,
      "reward_std": 0.038136303424835205,
      "rewards/accuracy_reward": 0.40625,
      "rewards/brier_reward": 0.59375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 160
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 98.0,
      "completions/max_terminated_length": 98.0,
      "completions/mean_length": 48.1953125,
      "completions/mean_terminated_length": 48.1953125,
      "completions/min_length": 33.0,
      "completions/min_terminated_length": 33.0,
      "epoch": 0.2576,
      "grad_norm": 0.006445925682783127,
      "learning_rate": 5e-06,
      "loss": 0.0005,
      "num_tokens": 58823382.0,
      "reward": 1.2050790786743164,
      "reward_std": 0.0236715879291296,
      "rewards/accuracy_reward": 0.41015625,
      "rewards/brier_reward": 0.58984375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 161
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 133.0,
      "completions/max_terminated_length": 133.0,
      "completions/mean_length": 46.9453125,
      "completions/mean_terminated_length": 46.9453125,
      "completions/min_length": 33.0,
      "completions/min_terminated_length": 33.0,
      "epoch": 0.2592,
      "grad_norm": 0.005022743251174688,
      "learning_rate": 5e-06,
      "loss": 0.0006,
      "num_tokens": 59166184.0,
      "reward": 1.1855478286743164,
      "reward_std": 0.03103875368833542,
      "rewards/accuracy_reward": 0.37109375,
      "rewards/brier_reward": 0.62890625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 162
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 82.0,
      "completions/max_terminated_length": 82.0,
      "completions/mean_length": 46.54296875,
      "completions/mean_terminated_length": 46.54296875,
      "completions/min_length": 31.0,
      "completions/min_terminated_length": 31.0,
      "epoch": 0.2608,
      "grad_norm": 0.008230634965002537,
      "learning_rate": 5e-06,
      "loss": -0.0005,
      "num_tokens": 59516459.0,
      "reward": 1.2578134536743164,
      "reward_std": 0.05529887229204178,
      "rewards/accuracy_reward": 0.515625,
      "rewards/brier_reward": 0.484375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 163
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 73.0,
      "completions/max_terminated_length": 73.0,
      "completions/mean_length": 45.5859375,
      "completions/mean_terminated_length": 45.5859375,
      "completions/min_length": 32.0,
      "completions/min_terminated_length": 32.0,
      "epoch": 0.2624,
      "grad_norm": 0.00862080603837967,
      "learning_rate": 5e-06,
      "loss": 0.0006,
      "num_tokens": 59875753.0,
      "reward": 1.2792978286743164,
      "reward_std": 0.03360118716955185,
      "rewards/accuracy_reward": 0.55859375,
      "rewards/brier_reward": 0.44140625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 164
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 72.0,
      "completions/max_terminated_length": 72.0,
      "completions/mean_length": 45.5390625,
      "completions/mean_terminated_length": 45.5390625,
      "completions/min_length": 34.0,
      "completions/min_terminated_length": 34.0,
      "epoch": 0.264,
      "grad_norm": 0.0062230536714196205,
      "learning_rate": 5e-06,
      "loss": 0.0013,
      "num_tokens": 60217323.0,
      "reward": 1.1796884536743164,
      "reward_std": 0.05273643881082535,
      "rewards/accuracy_reward": 0.359375,
      "rewards/brier_reward": 0.640625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 165
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 97.0,
      "completions/max_terminated_length": 97.0,
      "completions/mean_length": 44.92578125,
      "completions/mean_terminated_length": 44.92578125,
      "completions/min_length": 33.0,
      "completions/min_terminated_length": 33.0,
      "epoch": 0.2656,
      "grad_norm": 0.00558104133233428,
      "learning_rate": 5e-06,
      "loss": 0.0004,
      "num_tokens": 60570864.0,
      "reward": 1.1738290786743164,
      "reward_std": 0.022228099405765533,
      "rewards/accuracy_reward": 0.34765625,
      "rewards/brier_reward": 0.65234375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 166
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 73.0,
      "completions/max_terminated_length": 73.0,
      "completions/mean_length": 43.72265625,
      "completions/mean_terminated_length": 43.72265625,
      "completions/min_length": 32.0,
      "completions/min_terminated_length": 32.0,
      "epoch": 0.2672,
      "grad_norm": 0.009653366170823574,
      "learning_rate": 5e-06,
      "loss": -0.0004,
      "num_tokens": 60938281.0,
      "reward": 1.1933603286743164,
      "reward_std": 0.04254163056612015,
      "rewards/accuracy_reward": 0.38671875,
      "rewards/brier_reward": 0.61328125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 167
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 92.0,
      "completions/max_terminated_length": 92.0,
      "completions/mean_length": 44.7421875,
      "completions/mean_terminated_length": 44.7421875,
      "completions/min_length": 33.0,
      "completions/min_terminated_length": 33.0,
      "epoch": 0.2688,
      "grad_norm": 0.005720548797398806,
      "learning_rate": 5e-06,
      "loss": -0.0001,
      "num_tokens": 61289079.0,
      "reward": 1.1308603286743164,
      "reward_std": 0.0191352479159832,
      "rewards/accuracy_reward": 0.26171875,
      "rewards/brier_reward": 0.73828125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 168
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 117.0,
      "completions/max_terminated_length": 117.0,
      "completions/mean_length": 45.4453125,
      "completions/mean_terminated_length": 45.4453125,
      "completions/min_length": 29.0,
      "completions/min_terminated_length": 29.0,
      "epoch": 0.2704,
      "grad_norm": 0.007109296508133411,
      "learning_rate": 5e-06,
      "loss": 0.0009,
      "num_tokens": 61647617.0,
      "reward": 1.1582040786743164,
      "reward_std": 0.04451553523540497,
      "rewards/accuracy_reward": 0.31640625,
      "rewards/brier_reward": 0.68359375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 169
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 117.0,
      "completions/max_terminated_length": 117.0,
      "completions/mean_length": 45.26171875,
      "completions/mean_terminated_length": 45.26171875,
      "completions/min_length": 32.0,
      "completions/min_terminated_length": 32.0,
      "epoch": 0.272,
      "grad_norm": 0.008910843171179295,
      "learning_rate": 5e-06,
      "loss": -0.001,
      "num_tokens": 61980084.0,
      "reward": 1.1621103286743164,
      "reward_std": 0.019990211352705956,
      "rewards/accuracy_reward": 0.32421875,
      "rewards/brier_reward": 0.67578125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 170
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 76.0,
      "completions/max_terminated_length": 76.0,
      "completions/mean_length": 44.41796875,
      "completions/mean_terminated_length": 44.41796875,
      "completions/min_length": 33.0,
      "completions/min_terminated_length": 33.0,
      "epoch": 0.2736,
      "grad_norm": 0.0,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "num_tokens": 62333263.0,
      "reward": 1.2500009536743164,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.5,
      "rewards/brier_reward": 0.5,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 171
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 85.0,
      "completions/max_terminated_length": 85.0,
      "completions/mean_length": 43.0859375,
      "completions/mean_terminated_length": 43.0859375,
      "completions/min_length": 33.0,
      "completions/min_terminated_length": 33.0,
      "epoch": 0.2752,
      "grad_norm": 0.0074557592160999775,
      "learning_rate": 5e-06,
      "loss": 0.0002,
      "num_tokens": 62696221.0,
      "reward": 1.1191415786743164,
      "reward_std": 0.03360118716955185,
      "rewards/accuracy_reward": 0.23828125,
      "rewards/brier_reward": 0.76171875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 172
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 81.0,
      "completions/max_terminated_length": 81.0,
      "completions/mean_length": 42.8203125,
      "completions/mean_terminated_length": 42.8203125,
      "completions/min_length": 31.0,
      "completions/min_terminated_length": 31.0,
      "epoch": 0.2768,
      "grad_norm": 0.005095581524074078,
      "learning_rate": 5e-06,
      "loss": 0.001,
      "num_tokens": 63049559.0,
      "reward": 1.1328134536743164,
      "reward_std": 0.039125461131334305,
      "rewards/accuracy_reward": 0.265625,
      "rewards/brier_reward": 0.734375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 173
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 69.0,
      "completions/max_terminated_length": 69.0,
      "completions/mean_length": 42.484375,
      "completions/mean_terminated_length": 42.484375,
      "completions/min_length": 32.0,
      "completions/min_terminated_length": 32.0,
      "epoch": 0.2784,
      "grad_norm": 0.010611972771584988,
      "learning_rate": 5e-06,
      "loss": 0.0007,
      "num_tokens": 63408899.0,
      "reward": 1.1875009536743164,
      "reward_std": 0.02551448345184326,
      "rewards/accuracy_reward": 0.375,
      "rewards/brier_reward": 0.625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 174
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 92.0,
      "completions/max_terminated_length": 92.0,
      "completions/mean_length": 41.0546875,
      "completions/mean_terminated_length": 41.0546875,
      "completions/min_length": 31.0,
      "completions/min_terminated_length": 31.0,
      "epoch": 0.28,
      "grad_norm": 0.006971416063606739,
      "learning_rate": 5e-06,
      "loss": 0.0005,
      "num_tokens": 63749625.0,
      "reward": 1.2402353286743164,
      "reward_std": 0.048331111669540405,
      "rewards/accuracy_reward": 0.48046875,
      "rewards/brier_reward": 0.51953125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 175
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 75.0,
      "completions/max_terminated_length": 75.0,
      "completions/mean_length": 40.8515625,
      "completions/mean_terminated_length": 40.8515625,
      "completions/min_length": 31.0,
      "completions/min_terminated_length": 31.0,
      "epoch": 0.2816,
      "grad_norm": 0.008722545579075813,
      "learning_rate": 5e-06,
      "loss": -0.0005,
      "num_tokens": 64088787.0,
      "reward": 1.1914072036743164,
      "reward_std": 0.036563027650117874,
      "rewards/accuracy_reward": 0.3828125,
      "rewards/brier_reward": 0.6171875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 176
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 182.0,
      "completions/max_terminated_length": 182.0,
      "completions/mean_length": 40.27734375,
      "completions/mean_terminated_length": 40.27734375,
      "completions/min_length": 31.0,
      "completions/min_terminated_length": 31.0,
      "epoch": 0.2832,
      "grad_norm": 0.010323431342840195,
      "learning_rate": 5e-06,
      "loss": 0.0013,
      "num_tokens": 64443402.0,
      "reward": 1.2148447036743164,
      "reward_std": 0.0384027361869812,
      "rewards/accuracy_reward": 0.4296875,
      "rewards/brier_reward": 0.5703125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 177
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 57.0,
      "completions/max_terminated_length": 57.0,
      "completions/mean_length": 39.2734375,
      "completions/mean_terminated_length": 39.2734375,
      "completions/min_length": 31.0,
      "completions/min_terminated_length": 31.0,
      "epoch": 0.2848,
      "grad_norm": 0.005445533897727728,
      "learning_rate": 5e-06,
      "loss": -0.0,
      "num_tokens": 64787016.0,
      "reward": 1.2011728286743164,
      "reward_std": 0.026368219405412674,
      "rewards/accuracy_reward": 0.40234375,
      "rewards/brier_reward": 0.59765625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 178
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 58.0,
      "completions/max_terminated_length": 58.0,
      "completions/mean_length": 38.3203125,
      "completions/mean_terminated_length": 38.3203125,
      "completions/min_length": 30.0,
      "completions/min_terminated_length": 30.0,
      "epoch": 0.2864,
      "grad_norm": 0.005081367213279009,
      "learning_rate": 5e-06,
      "loss": -0.0001,
      "num_tokens": 65137202.0,
      "reward": 1.2402353286743164,
      "reward_std": 0.023805785924196243,
      "rewards/accuracy_reward": 0.48046875,
      "rewards/brier_reward": 0.51953125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 179
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 58.0,
      "completions/max_terminated_length": 58.0,
      "completions/mean_length": 36.71875,
      "completions/mean_terminated_length": 36.71875,
      "completions/min_length": 30.0,
      "completions/min_terminated_length": 30.0,
      "epoch": 0.288,
      "grad_norm": 0.009812582284212112,
      "learning_rate": 5e-06,
      "loss": 0.0015,
      "num_tokens": 65473690.0,
      "reward": 1.2636728286743164,
      "reward_std": 0.06135355681180954,
      "rewards/accuracy_reward": 0.52734375,
      "rewards/brier_reward": 0.47265625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 180
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 53.0,
      "completions/max_terminated_length": 53.0,
      "completions/mean_length": 36.46875,
      "completions/mean_terminated_length": 36.46875,
      "completions/min_length": 30.0,
      "completions/min_terminated_length": 30.0,
      "epoch": 0.2896,
      "grad_norm": 0.004110858775675297,
      "learning_rate": 5e-06,
      "loss": 0.0002,
      "num_tokens": 65823274.0,
      "reward": 1.1855478286743164,
      "reward_std": 0.005524271633476019,
      "rewards/accuracy_reward": 0.37109375,
      "rewards/brier_reward": 0.62890625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 181
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 66.0,
      "completions/max_terminated_length": 66.0,
      "completions/mean_length": 35.16015625,
      "completions/mean_terminated_length": 35.16015625,
      "completions/min_length": 29.0,
      "completions/min_terminated_length": 29.0,
      "epoch": 0.2912,
      "grad_norm": 0.013062373735010624,
      "learning_rate": 5e-06,
      "loss": -0.0003,
      "num_tokens": 66166363.0,
      "reward": 1.1464853286743164,
      "reward_std": 0.04254163056612015,
      "rewards/accuracy_reward": 0.30078125,
      "rewards/brier_reward": 0.6953125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 0.99609375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 182
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 57.0,
      "completions/max_terminated_length": 57.0,
      "completions/mean_length": 35.27734375,
      "completions/mean_terminated_length": 35.27734375,
      "completions/min_length": 30.0,
      "completions/min_terminated_length": 30.0,
      "epoch": 0.2928,
      "grad_norm": 0.004537950269877911,
      "learning_rate": 5e-06,
      "loss": 0.0002,
      "num_tokens": 66505130.0,
      "reward": 1.2167978286743164,
      "reward_std": 0.015319675207138062,
      "rewards/accuracy_reward": 0.43359375,
      "rewards/brier_reward": 0.56640625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 183
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 48.0,
      "completions/max_terminated_length": 48.0,
      "completions/mean_length": 35.56640625,
      "completions/mean_terminated_length": 35.56640625,
      "completions/min_length": 30.0,
      "completions/min_terminated_length": 30.0,
      "epoch": 0.2944,
      "grad_norm": 0.013359584845602512,
      "learning_rate": 5e-06,
      "loss": 0.0004,
      "num_tokens": 66854059.0,
      "reward": 1.2207040786743164,
      "reward_std": 0.03103875368833542,
      "rewards/accuracy_reward": 0.44140625,
      "rewards/brier_reward": 0.55859375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 184
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 46.0,
      "completions/max_terminated_length": 46.0,
      "completions/mean_length": 35.4140625,
      "completions/mean_terminated_length": 35.4140625,
      "completions/min_length": 30.0,
      "completions/min_terminated_length": 30.0,
      "epoch": 0.296,
      "grad_norm": 0.004776604939252138,
      "learning_rate": 5e-06,
      "loss": 0.0002,
      "num_tokens": 67204125.0,
      "reward": 1.2128915786743164,
      "reward_std": 0.01657281443476677,
      "rewards/accuracy_reward": 0.42578125,
      "rewards/brier_reward": 0.57421875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 185
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 48.0,
      "completions/max_terminated_length": 48.0,
      "completions/mean_length": 34.16015625,
      "completions/mean_terminated_length": 34.16015625,
      "completions/min_length": 30.0,
      "completions/min_terminated_length": 30.0,
      "epoch": 0.2976,
      "grad_norm": 0.004593758378177881,
      "learning_rate": 5e-06,
      "loss": -0.0001,
      "num_tokens": 67545518.0,
      "reward": 1.2753915786743164,
      "reward_std": 0.01657281443476677,
      "rewards/accuracy_reward": 0.55078125,
      "rewards/brier_reward": 0.44921875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 186
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 48.0,
      "completions/max_terminated_length": 48.0,
      "completions/mean_length": 34.578125,
      "completions/mean_terminated_length": 34.578125,
      "completions/min_length": 30.0,
      "completions/min_terminated_length": 30.0,
      "epoch": 0.2992,
      "grad_norm": 0.004609708674252033,
      "learning_rate": 5e-06,
      "loss": -0.0,
      "num_tokens": 67891474.0,
      "reward": 1.1855478286743164,
      "reward_std": 0.02110915631055832,
      "rewards/accuracy_reward": 0.37109375,
      "rewards/brier_reward": 0.62890625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 187
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 51.0,
      "completions/max_terminated_length": 51.0,
      "completions/mean_length": 34.76171875,
      "completions/mean_terminated_length": 34.76171875,
      "completions/min_length": 30.0,
      "completions/min_terminated_length": 30.0,
      "epoch": 0.3008,
      "grad_norm": 0.005076521076261997,
      "learning_rate": 5e-06,
      "loss": -0.0001,
      "num_tokens": 68255949.0,
      "reward": 1.2167978286743164,
      "reward_std": 0.019990211352705956,
      "rewards/accuracy_reward": 0.43359375,
      "rewards/brier_reward": 0.56640625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 188
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 47.0,
      "completions/max_terminated_length": 47.0,
      "completions/mean_length": 34.65234375,
      "completions/mean_terminated_length": 34.65234375,
      "completions/min_length": 30.0,
      "completions/min_terminated_length": 30.0,
      "epoch": 0.3024,
      "grad_norm": 0.015296814031898975,
      "learning_rate": 5e-06,
      "loss": 0.0007,
      "num_tokens": 68597300.0,
      "reward": 1.1777353286743164,
      "reward_std": 0.028930652886629105,
      "rewards/accuracy_reward": 0.35546875,
      "rewards/brier_reward": 0.64453125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 189
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 55.0,
      "completions/max_terminated_length": 55.0,
      "completions/mean_length": 34.6015625,
      "completions/mean_terminated_length": 34.6015625,
      "completions/min_length": 30.0,
      "completions/min_terminated_length": 30.0,
      "epoch": 0.304,
      "grad_norm": 0.007346505299210548,
      "learning_rate": 5e-06,
      "loss": 0.0007,
      "num_tokens": 68945222.0,
      "reward": 1.1308603286743164,
      "reward_std": 0.01913524977862835,
      "rewards/accuracy_reward": 0.26171875,
      "rewards/brier_reward": 0.73828125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 190
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 45.0,
      "completions/max_terminated_length": 45.0,
      "completions/mean_length": 34.1875,
      "completions/mean_terminated_length": 34.1875,
      "completions/min_length": 30.0,
      "completions/min_terminated_length": 30.0,
      "epoch": 0.3056,
      "grad_norm": 0.005888568237423897,
      "learning_rate": 5e-06,
      "loss": -0.0002,
      "num_tokens": 69298710.0,
      "reward": 1.1992197036743164,
      "reward_std": 0.018281511962413788,
      "rewards/accuracy_reward": 0.3984375,
      "rewards/brier_reward": 0.6015625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 191
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 46.0,
      "completions/max_terminated_length": 46.0,
      "completions/mean_length": 33.23828125,
      "completions/mean_terminated_length": 33.23828125,
      "completions/min_length": 30.0,
      "completions/min_terminated_length": 30.0,
      "epoch": 0.3072,
      "grad_norm": 0.004927255213260651,
      "learning_rate": 5e-06,
      "loss": -0.0,
      "num_tokens": 69655875.0,
      "reward": 1.1074228286743164,
      "reward_std": 0.01275724172592163,
      "rewards/accuracy_reward": 0.21484375,
      "rewards/brier_reward": 0.78515625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 192
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 43.0,
      "completions/max_terminated_length": 43.0,
      "completions/mean_length": 33.46484375,
      "completions/mean_terminated_length": 33.46484375,
      "completions/min_length": 29.0,
      "completions/min_terminated_length": 29.0,
      "epoch": 0.3088,
      "grad_norm": 0.002895692829042673,
      "learning_rate": 5e-06,
      "loss": -0.0001,
      "num_tokens": 70013034.0,
      "reward": 1.2148447036743164,
      "reward_std": 0.011048543266952038,
      "rewards/accuracy_reward": 0.4296875,
      "rewards/brier_reward": 0.5703125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 193
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 45.0,
      "completions/max_terminated_length": 45.0,
      "completions/mean_length": 32.80078125,
      "completions/mean_terminated_length": 32.80078125,
      "completions/min_length": 30.0,
      "completions/min_terminated_length": 30.0,
      "epoch": 0.3104,
      "grad_norm": 0.01532782893627882,
      "learning_rate": 5e-06,
      "loss": 0.0003,
      "num_tokens": 70367679.0,
      "reward": 1.1679697036743164,
      "reward_std": 0.06292805820703506,
      "rewards/accuracy_reward": 0.3359375,
      "rewards/brier_reward": 0.6640625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 194
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 45.0,
      "completions/max_terminated_length": 45.0,
      "completions/mean_length": 33.89453125,
      "completions/mean_terminated_length": 33.89453125,
      "completions/min_length": 29.0,
      "completions/min_terminated_length": 29.0,
      "epoch": 0.312,
      "grad_norm": 0.014220437966287136,
      "learning_rate": 5e-06,
      "loss": -0.0,
      "num_tokens": 70717156.0,
      "reward": 1.1386728286743164,
      "reward_std": 0.048331111669540405,
      "rewards/accuracy_reward": 0.27734375,
      "rewards/brier_reward": 0.72265625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 195
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 44.0,
      "completions/max_terminated_length": 44.0,
      "completions/mean_length": 33.41015625,
      "completions/mean_terminated_length": 33.41015625,
      "completions/min_length": 29.0,
      "completions/min_terminated_length": 29.0,
      "epoch": 0.3136,
      "grad_norm": 0.05932420864701271,
      "learning_rate": 5e-06,
      "loss": -0.0,
      "num_tokens": 71069909.0,
      "reward": 1.3300790786743164,
      "reward_std": 0.023805784061551094,
      "rewards/accuracy_reward": 0.66015625,
      "rewards/brier_reward": 0.33984375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 196
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 44.0,
      "completions/max_terminated_length": 44.0,
      "completions/mean_length": 32.6875,
      "completions/mean_terminated_length": 32.6875,
      "completions/min_length": 29.0,
      "completions/min_terminated_length": 29.0,
      "epoch": 0.3152,
      "grad_norm": 0.014617173001170158,
      "learning_rate": 5e-06,
      "loss": -0.0002,
      "num_tokens": 71421901.0,
      "reward": 1.2246103286743164,
      "reward_std": 0.03616362065076828,
      "rewards/accuracy_reward": 0.44921875,
      "rewards/brier_reward": 0.55078125,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 197
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 61.0,
      "completions/max_terminated_length": 61.0,
      "completions/mean_length": 32.6875,
      "completions/mean_terminated_length": 32.6875,
      "completions/min_length": 28.0,
      "completions/min_terminated_length": 28.0,
      "epoch": 0.3168,
      "grad_norm": 0.010734383016824722,
      "learning_rate": 5e-06,
      "loss": -0.0,
      "num_tokens": 71774381.0,
      "reward": 1.1953134536743164,
      "reward_std": 0.058980248868465424,
      "rewards/accuracy_reward": 0.390625,
      "rewards/brier_reward": 0.609375,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 198
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 42.0,
      "completions/max_terminated_length": 42.0,
      "completions/mean_length": 33.453125,
      "completions/mean_terminated_length": 33.453125,
      "completions/min_length": 30.0,
      "completions/min_terminated_length": 30.0,
      "epoch": 0.3184,
      "grad_norm": 0.007351653650403023,
      "learning_rate": 5e-06,
      "loss": 0.0003,
      "num_tokens": 72128153.0,
      "reward": 1.2285165786743164,
      "reward_std": 0.030183792114257812,
      "rewards/accuracy_reward": 0.45703125,
      "rewards/brier_reward": 0.54296875,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 199
    },
    {
      "calib/answer_extract_rate": 0.0,
      "calib/avg_num_step_conf": 0.0,
      "calib/final_conf_rate": 0.0,
      "calib/format_rate": 0.0,
      "calib/nonempty_final_conf_rate": 0.0,
      "calib/nonempty_reasoning_rate": 0.0,
      "calib/nonempty_step_conf_rate": 0.0,
      "calib/step_conf_rate": 0.0,
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 41.0,
      "completions/max_terminated_length": 41.0,
      "completions/mean_length": 32.83984375,
      "completions/mean_terminated_length": 32.83984375,
      "completions/min_length": 29.0,
      "completions/min_terminated_length": 29.0,
      "epoch": 0.32,
      "grad_norm": 0.011516711674630642,
      "learning_rate": 5e-06,
      "loss": -0.0002,
      "num_tokens": 72451840.0,
      "reward": 1.1875009536743164,
      "reward_std": 0.020843947306275368,
      "rewards/accuracy_reward": 0.375,
      "rewards/brier_reward": 0.625,
      "rewards/confidence_one_or_zero": 1.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 200
    },
    {
      "epoch": 0.32,
      "step": 200,
      "total_flos": 0.0,
      "train_loss": -0.0015666725028131623,
      "train_runtime": 6054.4549,
      "train_samples_per_second": 8.457,
      "train_steps_per_second": 0.033
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 72451840,
  "num_train_epochs": 1,
  "save_steps": 20,
  "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
}