{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.35486947457138424, "eval_steps": 500, "global_step": 2000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1858.0, "completions/mean_length": 2025.765625, "completions/mean_terminated_length": 1478.800048828125, "completions/min_length": 814.0, "completions/min_terminated_length": 814.0, "epoch": 0.00035486160397445, "frac_reward_zero_std": 0.9375, "grad_norm": 0.11000830680131912, "learning_rate": 1e-06, "loss": 0.005, "num_tokens": 270738.0, "reward": 0.0390625, "reward_std": 0.03234682232141495, "rewards/simpleverify_reward/mean": 0.0390625, "rewards/simpleverify_reward/std": 0.194504976272583, "step": 1 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9765625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1938.0, "completions/mean_length": 2045.234375, "completions/mean_terminated_length": 1930.0, "completions/min_length": 1921.0, "completions/min_terminated_length": 1921.0, "epoch": 0.0007097232079489, "frac_reward_zero_std": 0.9375, "grad_norm": 0.1009114682674408, "learning_rate": 9.995e-07, "loss": 0.0012, "num_tokens": 543992.0, "reward": 0.0234375, "reward_std": 0.03234682232141495, "rewards/simpleverify_reward/mean": 0.0234375, "rewards/simpleverify_reward/std": 0.15188287198543549, "step": 2 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 2041.34375, "completions/mean_terminated_length": 1906.0, "completions/min_length": 1560.0, "completions/min_terminated_length": 1560.0, "epoch": 0.0010645848119233499, "frac_reward_zero_std": 0.875, "grad_norm": 0.13870732486248016, "learning_rate": 9.989999999999999e-07, "loss": 0.0025, "num_tokens": 817212.0, "reward": 0.0546875, "reward_std": 0.05102896690368652, "rewards/simpleverify_reward/mean": 0.0546875, "rewards/simpleverify_reward/std": 0.22826264798641205, "step": 3 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1700.0, "completions/mean_length": 1885.0546875, "completions/mean_terminated_length": 1178.9583740234375, "completions/min_length": 791.0, "completions/min_terminated_length": 791.0, "epoch": 0.0014194464158978, "frac_reward_zero_std": 0.9375, "grad_norm": 0.10237956792116165, "learning_rate": 9.985e-07, "loss": -0.0014, "num_tokens": 1070091.0, "reward": 0.0390625, "reward_std": 0.03234682232141495, "rewards/simpleverify_reward/mean": 0.0390625, "rewards/simpleverify_reward/std": 0.194504976272583, "step": 4 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1899.0, "completions/mean_length": 2015.90625, "completions/mean_terminated_length": 1637.2000732421875, "completions/min_length": 1398.0, "completions/min_terminated_length": 1398.0, "epoch": 0.0017743080198722497, "frac_reward_zero_std": 0.75, "grad_norm": 0.2162560224533081, "learning_rate": 9.98e-07, "loss": 0.0032, "num_tokens": 1338335.0, "reward": 0.109375, "reward_std": 0.10205792635679245, "rewards/simpleverify_reward/mean": 0.109375, "rewards/simpleverify_reward/std": 0.31333550810813904, "step": 5 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2023.0, "completions/mean_length": 2047.8046875, "completions/mean_terminated_length": 2023.0, "completions/min_length": 2023.0, "completions/min_terminated_length": 2023.0, "epoch": 0.0021291696238466998, "frac_reward_zero_std": 0.9375, "grad_norm": 0.09901043772697449, "learning_rate": 9.975e-07, "loss": 0.0001, "num_tokens": 1613558.0, "reward": 0.0078125, "reward_std": 0.022097086533904076, "rewards/simpleverify_reward/mean": 0.0078125, "rewards/simpleverify_reward/std": 0.0883883461356163, "step": 6 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1950.0, "completions/mean_length": 2036.734375, "completions/mean_terminated_length": 1759.5999755859375, "completions/min_length": 1460.0, "completions/min_terminated_length": 1460.0, "epoch": 0.00248403122782115, "frac_reward_zero_std": 1.0, "grad_norm": 0.0, "learning_rate": 9.97e-07, "loss": 0.0, "num_tokens": 1885004.0, "reward": 0.0, "reward_std": 0.0, "rewards/simpleverify_reward/mean": 0.0, "rewards/simpleverify_reward/std": 0.0, "step": 7 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 1.0, "completions/max_length": 2048.0, "completions/max_terminated_length": 0.0, "completions/mean_length": 2048.0, "completions/mean_terminated_length": 0.0, "completions/min_length": 2048.0, "completions/min_terminated_length": 0.0, "epoch": 0.0028388928317956, "frac_reward_zero_std": 0.75, "grad_norm": 0.21043376624584198, "learning_rate": 9.965e-07, "loss": -0.0, "num_tokens": 2157004.0, "reward": 0.03125, "reward_std": 0.0883883461356163, "rewards/simpleverify_reward/mean": 0.03125, "rewards/simpleverify_reward/std": 0.1746762990951538, "step": 8 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 2033.3515625, "completions/mean_terminated_length": 1813.625, "completions/min_length": 1538.0, "completions/min_terminated_length": 1538.0, "epoch": 0.00319375443577005, "frac_reward_zero_std": 1.0, "grad_norm": 0.0, "learning_rate": 9.959999999999999e-07, "loss": 0.0, "num_tokens": 2428961.0, "reward": 0.0, "reward_std": 0.0, "rewards/simpleverify_reward/mean": 0.0, "rewards/simpleverify_reward/std": 0.0, "step": 9 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1937.0, "completions/mean_length": 2021.9765625, "completions/mean_terminated_length": 1631.625, "completions/min_length": 1281.0, "completions/min_terminated_length": 1281.0, "epoch": 0.0035486160397444995, "frac_reward_zero_std": 1.0, "grad_norm": 0.0, "learning_rate": 9.955e-07, "loss": 0.0, "num_tokens": 2701886.0, "reward": 0.0, "reward_std": 0.0, "rewards/simpleverify_reward/mean": 0.0, "rewards/simpleverify_reward/std": 0.0, "step": 10 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1739.0, "completions/mean_length": 2008.171875, "completions/mean_terminated_length": 1410.75, "completions/min_length": 1210.0, "completions/min_terminated_length": 1210.0, "epoch": 0.0039034776437189495, "frac_reward_zero_std": 0.9375, "grad_norm": 0.10884974896907806, "learning_rate": 9.95e-07, "loss": 0.0048, "num_tokens": 2970052.0, "reward": 0.0390625, "reward_std": 0.03234682232141495, "rewards/simpleverify_reward/mean": 0.0390625, "rewards/simpleverify_reward/std": 0.194504976272583, "step": 11 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1951.0, "completions/mean_length": 2036.234375, "completions/mean_terminated_length": 1797.0, "completions/min_length": 1595.0, "completions/min_terminated_length": 1595.0, "epoch": 0.0042583392476933995, "frac_reward_zero_std": 0.9375, "grad_norm": 0.11947102099657059, "learning_rate": 9.945e-07, "loss": 0.0011, "num_tokens": 3240778.0, "reward": 0.046875, "reward_std": 0.0289318785071373, "rewards/simpleverify_reward/mean": 0.046875, "rewards/simpleverify_reward/std": 0.21220162510871887, "step": 12 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 2028.6796875, "completions/mean_terminated_length": 1553.4000244140625, "completions/min_length": 1126.0, "completions/min_terminated_length": 1126.0, "epoch": 0.0046132008516678496, "frac_reward_zero_std": 0.875, "grad_norm": 0.17723293602466583, "learning_rate": 9.94e-07, "loss": 0.0042, "num_tokens": 3513849.0, "reward": 0.03125, "reward_std": 0.05444391071796417, "rewards/simpleverify_reward/mean": 0.03125, "rewards/simpleverify_reward/std": 0.1746762990951538, "step": 13 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 2007.34375, "completions/mean_terminated_length": 1647.6923828125, "completions/min_length": 1356.0, "completions/min_terminated_length": 1356.0, "epoch": 0.0049680624556423, "frac_reward_zero_std": 0.8125, "grad_norm": 0.18125641345977783, "learning_rate": 9.935e-07, "loss": 0.0027, "num_tokens": 3781565.0, "reward": 0.046875, "reward_std": 0.08337578922510147, "rewards/simpleverify_reward/mean": 0.046875, "rewards/simpleverify_reward/std": 0.21220162510871887, "step": 14 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1956.0, "completions/mean_length": 2038.84375, "completions/mean_terminated_length": 1813.5999755859375, "completions/min_length": 1614.0, "completions/min_terminated_length": 1614.0, "epoch": 0.00532292405961675, "frac_reward_zero_std": 1.0, "grad_norm": 0.0, "learning_rate": 9.929999999999999e-07, "loss": 0.0, "num_tokens": 4053977.0, "reward": 0.0, "reward_std": 0.0, "rewards/simpleverify_reward/mean": 0.0, "rewards/simpleverify_reward/std": 0.0, "step": 15 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1956.0, "completions/mean_length": 2046.03125, "completions/mean_terminated_length": 1922.0, "completions/min_length": 1888.0, "completions/min_terminated_length": 1888.0, "epoch": 0.0056777856635912, "frac_reward_zero_std": 0.9375, "grad_norm": 0.12818536162376404, "learning_rate": 9.925e-07, "loss": 0.0009, "num_tokens": 4326109.0, "reward": 0.015625, "reward_std": 0.0289318785071373, "rewards/simpleverify_reward/mean": 0.015625, "rewards/simpleverify_reward/std": 0.12450689822435379, "step": 16 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 2038.4453125, "completions/mean_terminated_length": 1873.2857666015625, "completions/min_length": 1628.0, "completions/min_terminated_length": 1628.0, "epoch": 0.00603264726756565, "frac_reward_zero_std": 0.9375, "grad_norm": 0.10090091824531555, "learning_rate": 9.92e-07, "loss": 0.0009, "num_tokens": 4596886.0, "reward": 0.015625, "reward_std": 0.0289318785071373, "rewards/simpleverify_reward/mean": 0.015625, "rewards/simpleverify_reward/std": 0.12450689822435379, "step": 17 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1564.0, "completions/mean_length": 2005.484375, "completions/mean_terminated_length": 1367.75, "completions/min_length": 1206.0, "completions/min_terminated_length": 1206.0, "epoch": 0.0063875088715401, "frac_reward_zero_std": 0.9375, "grad_norm": 0.1060536727309227, "learning_rate": 9.915e-07, "loss": -0.0, "num_tokens": 4863852.0, "reward": 0.0703125, "reward_std": 0.022097086533904076, "rewards/simpleverify_reward/mean": 0.0703125, "rewards/simpleverify_reward/std": 0.2566775679588318, "step": 18 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.90625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1939.0, "completions/mean_length": 2011.984375, "completions/mean_terminated_length": 1663.8333740234375, "completions/min_length": 1313.0, "completions/min_terminated_length": 1313.0, "epoch": 0.00674237047551455, "frac_reward_zero_std": 0.8125, "grad_norm": 0.18270161747932434, "learning_rate": 9.91e-07, "loss": 0.0034, "num_tokens": 5136858.0, "reward": 0.1171875, "reward_std": 0.08443661779165268, "rewards/simpleverify_reward/mean": 0.1171875, "rewards/simpleverify_reward/std": 0.322907418012619, "step": 19 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1835.0, "completions/mean_length": 2013.8984375, "completions/mean_terminated_length": 1651.181884765625, "completions/min_length": 1425.0, "completions/min_terminated_length": 1425.0, "epoch": 0.007097232079488999, "frac_reward_zero_std": 0.875, "grad_norm": 0.13983409106731415, "learning_rate": 9.905e-07, "loss": 0.0006, "num_tokens": 5405805.0, "reward": 0.0625, "reward_std": 0.04419417306780815, "rewards/simpleverify_reward/mean": 0.0625, "rewards/simpleverify_reward/std": 0.24301259219646454, "step": 20 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 1.0, "completions/max_length": 2048.0, "completions/max_terminated_length": 0.0, "completions/mean_length": 2048.0, "completions/mean_terminated_length": 0.0, "completions/min_length": 2048.0, "completions/min_terminated_length": 0.0, "epoch": 0.007452093683463449, "frac_reward_zero_std": 1.0, "grad_norm": 0.0, "learning_rate": 9.9e-07, "loss": 0.0, "num_tokens": 5682653.0, "reward": 0.0, "reward_std": 0.0, "rewards/simpleverify_reward/mean": 0.0, "rewards/simpleverify_reward/std": 0.0, "step": 21 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2013.0, "completions/mean_length": 2032.453125, "completions/mean_terminated_length": 1650.0, "completions/min_length": 1323.0, "completions/min_terminated_length": 1323.0, "epoch": 0.007806955287437899, "frac_reward_zero_std": 0.9375, "grad_norm": 0.12088192254304886, "learning_rate": 9.895e-07, "loss": 0.0051, "num_tokens": 5953911.0, "reward": 0.03125, "reward_std": 0.033407654613256454, "rewards/simpleverify_reward/mean": 0.03125, "rewards/simpleverify_reward/std": 0.1746762990951538, "step": 22 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1242.0, "completions/mean_length": 1998.9296875, "completions/mean_terminated_length": 1001.1666870117188, "completions/min_length": 610.0, "completions/min_terminated_length": 610.0, "epoch": 0.008161816891412349, "frac_reward_zero_std": 0.9375, "grad_norm": 0.15355144441127777, "learning_rate": 9.89e-07, "loss": -0.0016, "num_tokens": 6219454.0, "reward": 0.0078125, "reward_std": 0.022097086533904076, "rewards/simpleverify_reward/mean": 0.0078125, "rewards/simpleverify_reward/std": 0.0883883461356163, "step": 23 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 1.0, "completions/max_length": 2048.0, "completions/max_terminated_length": 0.0, "completions/mean_length": 2048.0, "completions/mean_terminated_length": 0.0, "completions/min_length": 2048.0, "completions/min_terminated_length": 0.0, "epoch": 0.008516678495386799, "frac_reward_zero_std": 1.0, "grad_norm": 0.0, "learning_rate": 9.885e-07, "loss": 0.0, "num_tokens": 6492342.0, "reward": 0.0, "reward_std": 0.0, "rewards/simpleverify_reward/mean": 0.0, "rewards/simpleverify_reward/std": 0.0, "step": 24 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 2031.7109375, "completions/mean_terminated_length": 1787.375, "completions/min_length": 1407.0, "completions/min_terminated_length": 1407.0, "epoch": 0.008871540099361249, "frac_reward_zero_std": 0.875, "grad_norm": 0.1470993608236313, "learning_rate": 9.88e-07, "loss": 0.0019, "num_tokens": 6764753.0, "reward": 0.046875, "reward_std": 0.06233953312039375, "rewards/simpleverify_reward/mean": 0.046875, "rewards/simpleverify_reward/std": 0.21220162510871887, "step": 25 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1966.0, "completions/mean_length": 2025.0703125, "completions/mean_terminated_length": 1558.8333740234375, "completions/min_length": 1081.0, "completions/min_terminated_length": 1081.0, "epoch": 0.009226401703335699, "frac_reward_zero_std": 0.875, "grad_norm": 0.1570315659046173, "learning_rate": 9.875e-07, "loss": 0.0037, "num_tokens": 7035594.0, "reward": 0.0390625, "reward_std": 0.05550473928451538, "rewards/simpleverify_reward/mean": 0.0390625, "rewards/simpleverify_reward/std": 0.194504976272583, "step": 26 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 2034.1328125, "completions/mean_terminated_length": 1826.125, "completions/min_length": 1537.0, "completions/min_terminated_length": 1537.0, "epoch": 0.00958126330731015, "frac_reward_zero_std": 0.6875, "grad_norm": 0.23265095055103302, "learning_rate": 9.87e-07, "loss": 0.0007, "num_tokens": 7305827.0, "reward": 0.0703125, "reward_std": 0.1344047486782074, "rewards/simpleverify_reward/mean": 0.0703125, "rewards/simpleverify_reward/std": 0.2566775679588318, "step": 27 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9765625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1937.0, "completions/mean_length": 2044.4140625, "completions/mean_terminated_length": 1895.0, "completions/min_length": 1849.0, "completions/min_terminated_length": 1849.0, "epoch": 0.0099361249112846, "frac_reward_zero_std": 0.8125, "grad_norm": 0.1934260129928589, "learning_rate": 9.865e-07, "loss": 0.0016, "num_tokens": 7577416.0, "reward": 0.0390625, "reward_std": 0.0765409991145134, "rewards/simpleverify_reward/mean": 0.0390625, "rewards/simpleverify_reward/std": 0.194504976272583, "step": 28 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.96875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2006.0, "completions/mean_length": 2037.8984375, "completions/mean_terminated_length": 1724.75, "completions/min_length": 1604.0, "completions/min_terminated_length": 1604.0, "epoch": 0.01029098651525905, "frac_reward_zero_std": 0.875, "grad_norm": 0.15636993944644928, "learning_rate": 9.86e-07, "loss": 0.0033, "num_tokens": 7846987.0, "reward": 0.0390625, "reward_std": 0.05550473928451538, "rewards/simpleverify_reward/mean": 0.0390625, "rewards/simpleverify_reward/std": 0.194504976272583, "step": 29 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1944.0, "completions/mean_length": 2012.7421875, "completions/mean_terminated_length": 1700.84619140625, "completions/min_length": 1394.0, "completions/min_terminated_length": 1394.0, "epoch": 0.0106458481192335, "frac_reward_zero_std": 0.8125, "grad_norm": 0.16549935936927795, "learning_rate": 9.855e-07, "loss": 0.003, "num_tokens": 8118010.0, "reward": 0.09375, "reward_std": 0.07312605530023575, "rewards/simpleverify_reward/mean": 0.09375, "rewards/simpleverify_reward/std": 0.29262590408325195, "step": 30 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.90625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1989.46875, "completions/mean_terminated_length": 1423.666748046875, "completions/min_length": 1004.0, "completions/min_terminated_length": 1004.0, "epoch": 0.01100070972320795, "frac_reward_zero_std": 0.875, "grad_norm": 0.14854446053504944, "learning_rate": 9.849999999999999e-07, "loss": 0.0024, "num_tokens": 8383318.0, "reward": 0.0859375, "reward_std": 0.05550473928451538, "rewards/simpleverify_reward/mean": 0.0859375, "rewards/simpleverify_reward/std": 0.2813730239868164, "step": 31 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 2019.1015625, "completions/mean_terminated_length": 1678.0999755859375, "completions/min_length": 1227.0, "completions/min_terminated_length": 1227.0, "epoch": 0.0113555713271824, "frac_reward_zero_std": 0.8125, "grad_norm": 0.17601685225963593, "learning_rate": 9.845e-07, "loss": 0.004, "num_tokens": 8651939.0, "reward": 0.0546875, "reward_std": 0.0765409916639328, "rewards/simpleverify_reward/mean": 0.0546875, "rewards/simpleverify_reward/std": 0.22826264798641205, "step": 32 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 1.0, "completions/max_length": 2048.0, "completions/max_terminated_length": 0.0, "completions/mean_length": 2048.0, "completions/mean_terminated_length": 0.0, "completions/min_length": 2048.0, "completions/min_terminated_length": 0.0, "epoch": 0.01171043293115685, "frac_reward_zero_std": 1.0, "grad_norm": 0.0, "learning_rate": 9.84e-07, "loss": 0.0, "num_tokens": 8926027.0, "reward": 0.0, "reward_std": 0.0, "rewards/simpleverify_reward/mean": 0.0, "rewards/simpleverify_reward/std": 0.0, "step": 33 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 1.0, "completions/max_length": 2048.0, "completions/max_terminated_length": 0.0, "completions/mean_length": 2048.0, "completions/mean_terminated_length": 0.0, "completions/min_length": 2048.0, "completions/min_terminated_length": 0.0, "epoch": 0.0120652945351313, "frac_reward_zero_std": 0.9375, "grad_norm": 0.11012071371078491, "learning_rate": 9.835e-07, "loss": -0.0, "num_tokens": 9201411.0, "reward": 0.0078125, "reward_std": 0.022097086533904076, "rewards/simpleverify_reward/mean": 0.0078125, "rewards/simpleverify_reward/std": 0.0883883461356163, "step": 34 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2014.0, "completions/mean_length": 2023.8046875, "completions/mean_terminated_length": 1703.888916015625, "completions/min_length": 958.0, "completions/min_terminated_length": 958.0, "epoch": 0.01242015613910575, "frac_reward_zero_std": 0.8125, "grad_norm": 0.17891617119312286, "learning_rate": 9.83e-07, "loss": 0.0089, "num_tokens": 9472610.0, "reward": 0.078125, "reward_std": 0.08337578922510147, "rewards/simpleverify_reward/mean": 0.078125, "rewards/simpleverify_reward/std": 0.2694226801395416, "step": 35 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.96875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 2041.046875, "completions/mean_terminated_length": 1825.5, "completions/min_length": 1303.0, "completions/min_terminated_length": 1303.0, "epoch": 0.0127750177430802, "frac_reward_zero_std": 0.875, "grad_norm": 0.16117160022258759, "learning_rate": 9.825e-07, "loss": 0.0049, "num_tokens": 9745680.0, "reward": 0.015625, "reward_std": 0.04419417306780815, "rewards/simpleverify_reward/mean": 0.015625, "rewards/simpleverify_reward/std": 0.12450689822435379, "step": 36 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1841.0, "completions/mean_length": 2036.6796875, "completions/mean_terminated_length": 1758.2000732421875, "completions/min_length": 1686.0, "completions/min_terminated_length": 1686.0, "epoch": 0.01312987934705465, "frac_reward_zero_std": 0.9375, "grad_norm": 0.09306556731462479, "learning_rate": 9.819999999999999e-07, "loss": 0.001, "num_tokens": 10017871.0, "reward": 0.0078125, "reward_std": 0.022097086533904076, "rewards/simpleverify_reward/mean": 0.0078125, "rewards/simpleverify_reward/std": 0.0883883461356163, "step": 37 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1891.0, "completions/mean_length": 2012.0703125, "completions/mean_terminated_length": 1629.9091796875, "completions/min_length": 1379.0, "completions/min_terminated_length": 1379.0, "epoch": 0.0134847409510291, "frac_reward_zero_std": 0.75, "grad_norm": 0.2062092125415802, "learning_rate": 9.815e-07, "loss": 0.0037, "num_tokens": 10288304.0, "reward": 0.046875, "reward_std": 0.09863808006048203, "rewards/simpleverify_reward/mean": 0.046875, "rewards/simpleverify_reward/std": 0.21220162510871887, "step": 38 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 1.0, "completions/max_length": 2048.0, "completions/max_terminated_length": 0.0, "completions/mean_length": 2048.0, "completions/mean_terminated_length": 0.0, "completions/min_length": 2048.0, "completions/min_terminated_length": 0.0, "epoch": 0.013839602555003548, "frac_reward_zero_std": 1.0, "grad_norm": 0.0, "learning_rate": 9.81e-07, "loss": 0.0, "num_tokens": 10564192.0, "reward": 0.0, "reward_std": 0.0, "rewards/simpleverify_reward/mean": 0.0, "rewards/simpleverify_reward/std": 0.0, "step": 39 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1996.0, "completions/mean_length": 2012.4296875, "completions/mean_terminated_length": 1592.7000732421875, "completions/min_length": 1111.0, "completions/min_terminated_length": 1111.0, "epoch": 0.014194464158977998, "frac_reward_zero_std": 0.875, "grad_norm": 0.14161746203899384, "learning_rate": 9.805e-07, "loss": 0.0025, "num_tokens": 10832255.0, "reward": 0.0625, "reward_std": 0.0578637570142746, "rewards/simpleverify_reward/mean": 0.0625, "rewards/simpleverify_reward/std": 0.24301259219646454, "step": 40 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2000.0, "completions/mean_length": 2028.9375, "completions/mean_terminated_length": 1743.0, "completions/min_length": 1576.0, "completions/min_terminated_length": 1576.0, "epoch": 0.014549325762952448, "frac_reward_zero_std": 0.875, "grad_norm": 0.1618345081806183, "learning_rate": 9.8e-07, "loss": 0.0033, "num_tokens": 11104407.0, "reward": 0.0703125, "reward_std": 0.05102896690368652, "rewards/simpleverify_reward/mean": 0.0703125, "rewards/simpleverify_reward/std": 0.2566775679588318, "step": 41 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1991.0, "completions/mean_length": 2018.796875, "completions/mean_terminated_length": 1781.0001220703125, "completions/min_length": 1321.0, "completions/min_terminated_length": 1321.0, "epoch": 0.014904187366926898, "frac_reward_zero_std": 0.75, "grad_norm": 0.212400421500206, "learning_rate": 9.795e-07, "loss": 0.0044, "num_tokens": 11371957.0, "reward": 0.125, "reward_std": 0.11678344756364822, "rewards/simpleverify_reward/mean": 0.125, "rewards/simpleverify_reward/std": 0.3320184051990509, "step": 42 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2010.0, "completions/mean_length": 1909.0390625, "completions/mean_terminated_length": 1001.7058715820312, "completions/min_length": 730.0, "completions/min_terminated_length": 730.0, "epoch": 0.015259048970901348, "frac_reward_zero_std": 0.9375, "grad_norm": 0.13048599660396576, "learning_rate": 9.789999999999999e-07, "loss": 0.0, "num_tokens": 11629650.0, "reward": 0.0078125, "reward_std": 0.022097086533904076, "rewards/simpleverify_reward/mean": 0.0078125, "rewards/simpleverify_reward/std": 0.0883883461356163, "step": 43 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.90625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1956.0, "completions/mean_length": 2007.046875, "completions/mean_terminated_length": 1611.166748046875, "completions/min_length": 1290.0, "completions/min_terminated_length": 1290.0, "epoch": 0.015613910574875798, "frac_reward_zero_std": 0.75, "grad_norm": 0.21283991634845734, "learning_rate": 9.785e-07, "loss": 0.0083, "num_tokens": 11898488.0, "reward": 0.0859375, "reward_std": 0.1054728776216507, "rewards/simpleverify_reward/mean": 0.0859375, "rewards/simpleverify_reward/std": 0.2813730239868164, "step": 44 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 2000.0078125, "completions/mean_terminated_length": 1433.7000732421875, "completions/min_length": 908.0, "completions/min_terminated_length": 908.0, "epoch": 0.01596877217885025, "frac_reward_zero_std": 0.9375, "grad_norm": 0.10860895365476608, "learning_rate": 9.78e-07, "loss": -0.0, "num_tokens": 12166033.0, "reward": 0.0078125, "reward_std": 0.022097086533904076, "rewards/simpleverify_reward/mean": 0.0078125, "rewards/simpleverify_reward/std": 0.0883883461356163, "step": 45 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 2009.5234375, "completions/mean_terminated_length": 1740.1875, "completions/min_length": 1476.0, "completions/min_terminated_length": 1476.0, "epoch": 0.016323633782824698, "frac_reward_zero_std": 0.8125, "grad_norm": 0.18546663224697113, "learning_rate": 9.775e-07, "loss": 0.0075, "num_tokens": 12431964.0, "reward": 0.1015625, "reward_std": 0.07996084541082382, "rewards/simpleverify_reward/mean": 0.1015625, "rewards/simpleverify_reward/std": 0.3032590448856354, "step": 46 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.90625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 2020.4609375, "completions/mean_terminated_length": 1754.25, "completions/min_length": 1517.0, "completions/min_terminated_length": 1517.0, "epoch": 0.01667849538679915, "frac_reward_zero_std": 0.8125, "grad_norm": 0.1879655122756958, "learning_rate": 9.77e-07, "loss": -0.0004, "num_tokens": 12702103.0, "reward": 0.046875, "reward_std": 0.08337578922510147, "rewards/simpleverify_reward/mean": 0.046875, "rewards/simpleverify_reward/std": 0.21220162510871887, "step": 47 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 1.0, "completions/max_length": 2048.0, "completions/max_terminated_length": 0.0, "completions/mean_length": 2048.0, "completions/mean_terminated_length": 0.0, "completions/min_length": 2048.0, "completions/min_terminated_length": 0.0, "epoch": 0.017033356990773598, "frac_reward_zero_std": 1.0, "grad_norm": 0.0, "learning_rate": 9.765e-07, "loss": 0.0, "num_tokens": 12974175.0, "reward": 0.0, "reward_std": 0.0, "rewards/simpleverify_reward/mean": 0.0, "rewards/simpleverify_reward/std": 0.0, "step": 48 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1975.0390625, "completions/mean_terminated_length": 1329.615478515625, "completions/min_length": 914.0, "completions/min_terminated_length": 914.0, "epoch": 0.01738821859474805, "frac_reward_zero_std": 0.75, "grad_norm": 0.25256940722465515, "learning_rate": 9.759999999999998e-07, "loss": -0.0032, "num_tokens": 13237204.0, "reward": 0.0625, "reward_std": 0.1065337061882019, "rewards/simpleverify_reward/mean": 0.0625, "rewards/simpleverify_reward/std": 0.24301259219646454, "step": 49 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1851.0, "completions/mean_length": 2017.7421875, "completions/mean_terminated_length": 1494.71435546875, "completions/min_length": 960.0, "completions/min_terminated_length": 960.0, "epoch": 0.017743080198722498, "frac_reward_zero_std": 1.0, "grad_norm": 0.0, "learning_rate": 9.755e-07, "loss": 0.0, "num_tokens": 13507963.0, "reward": 0.0, "reward_std": 0.0, "rewards/simpleverify_reward/mean": 0.0, "rewards/simpleverify_reward/std": 0.0, "step": 50 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1974.0, "completions/mean_length": 2013.0546875, "completions/mean_terminated_length": 1488.875, "completions/min_length": 949.0, "completions/min_terminated_length": 949.0, "epoch": 0.01809794180269695, "frac_reward_zero_std": 0.9375, "grad_norm": 0.10639584064483643, "learning_rate": 9.75e-07, "loss": 0.0, "num_tokens": 13776978.0, "reward": 0.0078125, "reward_std": 0.022097086533904076, "rewards/simpleverify_reward/mean": 0.0078125, "rewards/simpleverify_reward/std": 0.0883883461356163, "step": 51 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1533.0, "completions/mean_length": 2043.9765625, "completions/mean_terminated_length": 1533.0, "completions/min_length": 1533.0, "completions/min_terminated_length": 1533.0, "epoch": 0.018452803406671398, "frac_reward_zero_std": 0.9375, "grad_norm": 0.10344074666500092, "learning_rate": 9.745e-07, "loss": 0.0032, "num_tokens": 14049279.0, "reward": 0.0078125, "reward_std": 0.022097086533904076, "rewards/simpleverify_reward/mean": 0.0078125, "rewards/simpleverify_reward/std": 0.0883883461356163, "step": 52 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 1.0, "completions/max_length": 2048.0, "completions/max_terminated_length": 0.0, "completions/mean_length": 2048.0, "completions/mean_terminated_length": 0.0, "completions/min_length": 2048.0, "completions/min_terminated_length": 0.0, "epoch": 0.018807665010645847, "frac_reward_zero_std": 1.0, "grad_norm": 0.0, "learning_rate": 9.74e-07, "loss": 0.0, "num_tokens": 14323383.0, "reward": 0.0, "reward_std": 0.0, "rewards/simpleverify_reward/mean": 0.0, "rewards/simpleverify_reward/std": 0.0, "step": 53 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9765625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1971.0, "completions/mean_length": 2045.78125, "completions/mean_terminated_length": 1953.3333740234375, "completions/min_length": 1926.0, "completions/min_terminated_length": 1926.0, "epoch": 0.0191625266146203, "frac_reward_zero_std": 0.9375, "grad_norm": 0.08971650153398514, "learning_rate": 9.735e-07, "loss": 0.0006, "num_tokens": 14593907.0, "reward": 0.0078125, "reward_std": 0.022097086533904076, "rewards/simpleverify_reward/mean": 0.0078125, "rewards/simpleverify_reward/std": 0.0883883461356163, "step": 54 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1921.359375, "completions/mean_terminated_length": 1343.2174072265625, "completions/min_length": 865.0, "completions/min_terminated_length": 865.0, "epoch": 0.019517388218594747, "frac_reward_zero_std": 0.875, "grad_norm": 0.1606256365776062, "learning_rate": 9.729999999999998e-07, "loss": 0.0061, "num_tokens": 14851521.0, "reward": 0.03125, "reward_std": 0.05444391071796417, "rewards/simpleverify_reward/mean": 0.03125, "rewards/simpleverify_reward/std": 0.1746762990951538, "step": 55 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1985.0, "completions/mean_length": 2026.390625, "completions/mean_terminated_length": 1702.25, "completions/min_length": 1328.0, "completions/min_terminated_length": 1328.0, "epoch": 0.0198722498225692, "frac_reward_zero_std": 0.875, "grad_norm": 0.14034079015254974, "learning_rate": 9.725e-07, "loss": 0.0064, "num_tokens": 15124787.0, "reward": 0.0546875, "reward_std": 0.061278700828552246, "rewards/simpleverify_reward/mean": 0.0546875, "rewards/simpleverify_reward/std": 0.22826264798641205, "step": 56 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 2045.375, "completions/mean_terminated_length": 1980.800048828125, "completions/min_length": 1888.0, "completions/min_terminated_length": 1888.0, "epoch": 0.020227111426543647, "frac_reward_zero_std": 0.875, "grad_norm": 0.1382763683795929, "learning_rate": 9.72e-07, "loss": 0.0011, "num_tokens": 15399515.0, "reward": 0.046875, "reward_std": 0.06233953312039375, "rewards/simpleverify_reward/mean": 0.046875, "rewards/simpleverify_reward/std": 0.21220162510871887, "step": 57 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1824.0, "completions/mean_length": 2008.9765625, "completions/mean_terminated_length": 1423.625, "completions/min_length": 1102.0, "completions/min_terminated_length": 1102.0, "epoch": 0.0205819730305181, "frac_reward_zero_std": 0.9375, "grad_norm": 0.10122266411781311, "learning_rate": 9.715e-07, "loss": -0.0, "num_tokens": 15667088.0, "reward": 0.078125, "reward_std": 0.0289318785071373, "rewards/simpleverify_reward/mean": 0.078125, "rewards/simpleverify_reward/std": 0.2694226801395416, "step": 58 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1961.0, "completions/mean_length": 2006.9140625, "completions/mean_terminated_length": 1643.4615478515625, "completions/min_length": 1297.0, "completions/min_terminated_length": 1297.0, "epoch": 0.020936834634492547, "frac_reward_zero_std": 0.875, "grad_norm": 0.14492473006248474, "learning_rate": 9.709999999999999e-07, "loss": 0.0072, "num_tokens": 15935829.0, "reward": 0.1015625, "reward_std": 0.05102896690368652, "rewards/simpleverify_reward/mean": 0.1015625, "rewards/simpleverify_reward/std": 0.3032590448856354, "step": 59 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 1.0, "completions/max_length": 2048.0, "completions/max_terminated_length": 0.0, "completions/mean_length": 2048.0, "completions/mean_terminated_length": 0.0, "completions/min_length": 2048.0, "completions/min_terminated_length": 0.0, "epoch": 0.021291696238467, "frac_reward_zero_std": 0.9375, "grad_norm": 0.1017904058098793, "learning_rate": 9.705e-07, "loss": -0.0, "num_tokens": 16210069.0, "reward": 0.015625, "reward_std": 0.0289318785071373, "rewards/simpleverify_reward/mean": 0.015625, "rewards/simpleverify_reward/std": 0.12450689822435379, "step": 60 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.90625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2003.0, "completions/mean_length": 2008.4375, "completions/mean_terminated_length": 1626.0, "completions/min_length": 1247.0, "completions/min_terminated_length": 1247.0, "epoch": 0.021646557842441447, "frac_reward_zero_std": 0.75, "grad_norm": 0.20772631466388702, "learning_rate": 9.7e-07, "loss": 0.0026, "num_tokens": 16476253.0, "reward": 0.1171875, "reward_std": 0.1054728701710701, "rewards/simpleverify_reward/mean": 0.1171875, "rewards/simpleverify_reward/std": 0.322907418012619, "step": 61 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1491.0, "completions/mean_length": 2002.5546875, "completions/mean_terminated_length": 1320.875, "completions/min_length": 1113.0, "completions/min_terminated_length": 1113.0, "epoch": 0.0220014194464159, "frac_reward_zero_std": 1.0, "grad_norm": 0.0, "learning_rate": 9.695e-07, "loss": 0.0, "num_tokens": 16742532.0, "reward": 0.0625, "reward_std": 0.0, "rewards/simpleverify_reward/mean": 0.0625, "rewards/simpleverify_reward/std": 0.24301259219646454, "step": 62 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 1.0, "completions/max_length": 2048.0, "completions/max_terminated_length": 0.0, "completions/mean_length": 2048.0, "completions/mean_terminated_length": 0.0, "completions/min_length": 2048.0, "completions/min_terminated_length": 0.0, "epoch": 0.022356281050390347, "frac_reward_zero_std": 1.0, "grad_norm": 0.0, "learning_rate": 9.69e-07, "loss": 0.0, "num_tokens": 17016476.0, "reward": 0.0, "reward_std": 0.0, "rewards/simpleverify_reward/mean": 0.0, "rewards/simpleverify_reward/std": 0.0, "step": 63 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 2035.75, "completions/mean_terminated_length": 1824.0001220703125, "completions/min_length": 1318.0, "completions/min_terminated_length": 1318.0, "epoch": 0.0227111426543648, "frac_reward_zero_std": 0.875, "grad_norm": 0.15132854878902435, "learning_rate": 9.685e-07, "loss": 0.0028, "num_tokens": 17289428.0, "reward": 0.0546875, "reward_std": 0.0657544732093811, "rewards/simpleverify_reward/mean": 0.0546875, "rewards/simpleverify_reward/std": 0.22826264798641205, "step": 64 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2009.0, "completions/mean_length": 2025.7421875, "completions/mean_terminated_length": 1763.0999755859375, "completions/min_length": 1489.0, "completions/min_terminated_length": 1489.0, "epoch": 0.023066004258339247, "frac_reward_zero_std": 0.8125, "grad_norm": 0.1790650337934494, "learning_rate": 9.679999999999999e-07, "loss": 0.0035, "num_tokens": 17561283.0, "reward": 0.0859375, "reward_std": 0.06629125773906708, "rewards/simpleverify_reward/mean": 0.0859375, "rewards/simpleverify_reward/std": 0.2813730239868164, "step": 65 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1995.0, "completions/mean_length": 2005.453125, "completions/mean_terminated_length": 1503.4000244140625, "completions/min_length": 840.0, "completions/min_terminated_length": 840.0, "epoch": 0.0234208658623137, "frac_reward_zero_std": 0.75, "grad_norm": 0.2163587212562561, "learning_rate": 9.675e-07, "loss": 0.009, "num_tokens": 17829501.0, "reward": 0.0703125, "reward_std": 0.11336849629878998, "rewards/simpleverify_reward/mean": 0.0703125, "rewards/simpleverify_reward/std": 0.2566775679588318, "step": 66 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1637.0, "completions/mean_length": 2044.7890625, "completions/mean_terminated_length": 1637.0, "completions/min_length": 1637.0, "completions/min_terminated_length": 1637.0, "epoch": 0.023775727466288147, "frac_reward_zero_std": 0.9375, "grad_norm": 0.08992587774991989, "learning_rate": 9.67e-07, "loss": 0.0022, "num_tokens": 18104658.0, "reward": 0.0078125, "reward_std": 0.022097086533904076, "rewards/simpleverify_reward/mean": 0.0078125, "rewards/simpleverify_reward/std": 0.0883883461356163, "step": 67 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1810.0, "completions/mean_length": 1949.0859375, "completions/mean_terminated_length": 1344.611083984375, "completions/min_length": 969.0, "completions/min_terminated_length": 969.0, "epoch": 0.0241305890702626, "frac_reward_zero_std": 0.875, "grad_norm": 0.15729287266731262, "learning_rate": 9.665e-07, "loss": -0.0015, "num_tokens": 18371629.0, "reward": 0.109375, "reward_std": 0.0646936446428299, "rewards/simpleverify_reward/mean": 0.109375, "rewards/simpleverify_reward/std": 0.31333550810813904, "step": 68 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1913.0, "completions/mean_length": 2036.6484375, "completions/mean_terminated_length": 1757.4000244140625, "completions/min_length": 1638.0, "completions/min_terminated_length": 1638.0, "epoch": 0.024485450674237047, "frac_reward_zero_std": 0.8125, "grad_norm": 0.18401813507080078, "learning_rate": 9.66e-07, "loss": 0.0047, "num_tokens": 18641992.0, "reward": 0.078125, "reward_std": 0.09810130298137665, "rewards/simpleverify_reward/mean": 0.078125, "rewards/simpleverify_reward/std": 0.2694226801395416, "step": 69 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1650.0, "completions/mean_length": 2044.890625, "completions/mean_terminated_length": 1650.0, "completions/min_length": 1650.0, "completions/min_terminated_length": 1650.0, "epoch": 0.0248403122782115, "frac_reward_zero_std": 0.8125, "grad_norm": 0.2005736082792282, "learning_rate": 9.655e-07, "loss": 0.0024, "num_tokens": 18915626.0, "reward": 0.0390625, "reward_std": 0.0765409916639328, "rewards/simpleverify_reward/mean": 0.0390625, "rewards/simpleverify_reward/std": 0.194504976272583, "step": 70 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 2033.4453125, "completions/mean_terminated_length": 1861.7000732421875, "completions/min_length": 1536.0, "completions/min_terminated_length": 1536.0, "epoch": 0.025195173882185947, "frac_reward_zero_std": 0.9375, "grad_norm": 0.09403716772794724, "learning_rate": 9.649999999999999e-07, "loss": 0.0025, "num_tokens": 19186771.0, "reward": 0.0546875, "reward_std": 0.022097086533904076, "rewards/simpleverify_reward/mean": 0.0546875, "rewards/simpleverify_reward/std": 0.22826264798641205, "step": 71 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.96875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1964.0, "completions/mean_length": 2034.7421875, "completions/mean_terminated_length": 1623.75, "completions/min_length": 1260.0, "completions/min_terminated_length": 1260.0, "epoch": 0.0255500354861604, "frac_reward_zero_std": 0.8125, "grad_norm": 0.18101583421230316, "learning_rate": 9.645e-07, "loss": 0.0077, "num_tokens": 19460818.0, "reward": 0.046875, "reward_std": 0.08337578922510147, "rewards/simpleverify_reward/mean": 0.046875, "rewards/simpleverify_reward/std": 0.21220162510871887, "step": 72 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9765625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2001.0, "completions/mean_length": 2044.75, "completions/mean_terminated_length": 1909.3333740234375, "completions/min_length": 1750.0, "completions/min_terminated_length": 1750.0, "epoch": 0.025904897090134847, "frac_reward_zero_std": 0.875, "grad_norm": 0.13758188486099243, "learning_rate": 9.64e-07, "loss": 0.0018, "num_tokens": 19732650.0, "reward": 0.0234375, "reward_std": 0.05102896690368652, "rewards/simpleverify_reward/mean": 0.0234375, "rewards/simpleverify_reward/std": 0.15188287198543549, "step": 73 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1972.0, "completions/mean_length": 2027.6328125, "completions/mean_terminated_length": 1758.3333740234375, "completions/min_length": 1413.0, "completions/min_terminated_length": 1413.0, "epoch": 0.0262597586941093, "frac_reward_zero_std": 0.875, "grad_norm": 0.14039738476276398, "learning_rate": 9.635e-07, "loss": 0.0013, "num_tokens": 20004603.0, "reward": 0.0859375, "reward_std": 0.05102896690368652, "rewards/simpleverify_reward/mean": 0.0859375, "rewards/simpleverify_reward/std": 0.2813730239868164, "step": 74 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1966.9765625, "completions/mean_terminated_length": 1554.1429443359375, "completions/min_length": 944.0, "completions/min_terminated_length": 944.0, "epoch": 0.026614620298083747, "frac_reward_zero_std": 0.75, "grad_norm": 0.2064376175403595, "learning_rate": 9.63e-07, "loss": 0.006, "num_tokens": 20270048.0, "reward": 0.1640625, "reward_std": 0.11336850374937057, "rewards/simpleverify_reward/mean": 0.1640625, "rewards/simpleverify_reward/std": 0.371787428855896, "step": 75 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1946.875, "completions/mean_terminated_length": 1530.239990234375, "completions/min_length": 787.0, "completions/min_terminated_length": 787.0, "epoch": 0.0269694819020582, "frac_reward_zero_std": 0.75, "grad_norm": 0.21116983890533447, "learning_rate": 9.624999999999999e-07, "loss": 0.007, "num_tokens": 20529760.0, "reward": 0.1875, "reward_std": 0.11678344011306763, "rewards/simpleverify_reward/mean": 0.1875, "rewards/simpleverify_reward/std": 0.39184603095054626, "step": 76 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 1.0, "completions/max_length": 2048.0, "completions/max_terminated_length": 0.0, "completions/mean_length": 2048.0, "completions/mean_terminated_length": 0.0, "completions/min_length": 2048.0, "completions/min_terminated_length": 0.0, "epoch": 0.027324343506032647, "frac_reward_zero_std": 1.0, "grad_norm": 0.0, "learning_rate": 9.619999999999999e-07, "loss": 0.0, "num_tokens": 20805568.0, "reward": 0.0, "reward_std": 0.0, "rewards/simpleverify_reward/mean": 0.0, "rewards/simpleverify_reward/std": 0.0, "step": 77 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2019.0, "completions/mean_length": 1946.828125, "completions/mean_terminated_length": 1286.2353515625, "completions/min_length": 690.0, "completions/min_terminated_length": 690.0, "epoch": 0.027679205110007096, "frac_reward_zero_std": 0.9375, "grad_norm": 0.10632627457380295, "learning_rate": 9.615e-07, "loss": 0.0004, "num_tokens": 21066274.0, "reward": 0.1328125, "reward_std": 0.022097086533904076, "rewards/simpleverify_reward/mean": 0.1328125, "rewards/simpleverify_reward/std": 0.3407054841518402, "step": 78 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1763.0, "completions/mean_length": 2021.703125, "completions/mean_terminated_length": 1487.0, "completions/min_length": 1341.0, "completions/min_terminated_length": 1341.0, "epoch": 0.028034066713981547, "frac_reward_zero_std": 0.875, "grad_norm": 0.16673973202705383, "learning_rate": 9.61e-07, "loss": 0.0053, "num_tokens": 21336380.0, "reward": 0.0703125, "reward_std": 0.05102896690368652, "rewards/simpleverify_reward/mean": 0.0703125, "rewards/simpleverify_reward/std": 0.2566775679588318, "step": 79 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 1.0, "completions/max_length": 2048.0, "completions/max_terminated_length": 0.0, "completions/mean_length": 2048.0, "completions/mean_terminated_length": 0.0, "completions/min_length": 2048.0, "completions/min_terminated_length": 0.0, "epoch": 0.028388928317955996, "frac_reward_zero_std": 0.875, "grad_norm": 0.174808531999588, "learning_rate": 9.605e-07, "loss": -0.0, "num_tokens": 21609876.0, "reward": 0.015625, "reward_std": 0.04419417306780815, "rewards/simpleverify_reward/mean": 0.015625, "rewards/simpleverify_reward/std": 0.12450689822435379, "step": 80 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 1.0, "completions/max_length": 2048.0, "completions/max_terminated_length": 0.0, "completions/mean_length": 2048.0, "completions/mean_terminated_length": 0.0, "completions/min_length": 2048.0, "completions/min_terminated_length": 0.0, "epoch": 0.028743789921930447, "frac_reward_zero_std": 1.0, "grad_norm": 0.0, "learning_rate": 9.6e-07, "loss": 0.0, "num_tokens": 21883196.0, "reward": 0.0, "reward_std": 0.0, "rewards/simpleverify_reward/mean": 0.0, "rewards/simpleverify_reward/std": 0.0, "step": 81 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1897.0, "completions/mean_length": 1916.265625, "completions/mean_terminated_length": 1373.52001953125, "completions/min_length": 852.0, "completions/min_terminated_length": 852.0, "epoch": 0.029098651525904896, "frac_reward_zero_std": 0.75, "grad_norm": 0.2497006058692932, "learning_rate": 9.594999999999999e-07, "loss": 0.0111, "num_tokens": 22137694.0, "reward": 0.203125, "reward_std": 0.10205793380737305, "rewards/simpleverify_reward/mean": 0.203125, "rewards/simpleverify_reward/std": 0.40390563011169434, "step": 82 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1648.0, "completions/mean_length": 2044.875, "completions/mean_terminated_length": 1648.0, "completions/min_length": 1648.0, "completions/min_terminated_length": 1648.0, "epoch": 0.029453513129879347, "frac_reward_zero_std": 0.875, "grad_norm": 0.13509400188922882, "learning_rate": 9.589999999999998e-07, "loss": 0.0024, "num_tokens": 22412078.0, "reward": 0.015625, "reward_std": 0.04419417306780815, "rewards/simpleverify_reward/mean": 0.015625, "rewards/simpleverify_reward/std": 0.12450689822435379, "step": 83 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 2028.9140625, "completions/mean_terminated_length": 1803.7000732421875, "completions/min_length": 1414.0, "completions/min_terminated_length": 1414.0, "epoch": 0.029808374733853796, "frac_reward_zero_std": 0.75, "grad_norm": 0.21675287187099457, "learning_rate": 9.585e-07, "loss": 0.0043, "num_tokens": 22684211.0, "reward": 0.0703125, "reward_std": 0.11336849629878998, "rewards/simpleverify_reward/mean": 0.0703125, "rewards/simpleverify_reward/std": 0.2566775679588318, "step": 84 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2002.0, "completions/mean_length": 2002.8671875, "completions/mean_terminated_length": 1662.86669921875, "completions/min_length": 826.0, "completions/min_terminated_length": 826.0, "epoch": 0.030163236337828248, "frac_reward_zero_std": 0.8125, "grad_norm": 0.18612781167030334, "learning_rate": 9.58e-07, "loss": 0.0052, "num_tokens": 22950506.0, "reward": 0.125, "reward_std": 0.08785156160593033, "rewards/simpleverify_reward/mean": 0.125, "rewards/simpleverify_reward/std": 0.3320184051990509, "step": 85 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 2046.828125, "completions/mean_terminated_length": 1973.0, "completions/min_length": 1912.0, "completions/min_terminated_length": 1912.0, "epoch": 0.030518097941802696, "frac_reward_zero_std": 0.875, "grad_norm": 0.1479736715555191, "learning_rate": 9.575e-07, "loss": 0.0001, "num_tokens": 23224460.0, "reward": 0.0234375, "reward_std": 0.05102896690368652, "rewards/simpleverify_reward/mean": 0.0234375, "rewards/simpleverify_reward/std": 0.15188287198543549, "step": 86 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1899.0, "completions/mean_length": 1991.03125, "completions/mean_terminated_length": 1237.77783203125, "completions/min_length": 847.0, "completions/min_terminated_length": 847.0, "epoch": 0.030872959545777148, "frac_reward_zero_std": 0.9375, "grad_norm": 0.11066299676895142, "learning_rate": 9.57e-07, "loss": 0.0062, "num_tokens": 23489584.0, "reward": 0.078125, "reward_std": 0.0289318785071373, "rewards/simpleverify_reward/mean": 0.078125, "rewards/simpleverify_reward/std": 0.2694226801395416, "step": 87 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 2041.203125, "completions/mean_terminated_length": 1874.0, "completions/min_length": 1561.0, "completions/min_terminated_length": 1561.0, "epoch": 0.031227821149751596, "frac_reward_zero_std": 0.875, "grad_norm": 0.17076733708381653, "learning_rate": 9.565e-07, "loss": 0.0029, "num_tokens": 23761818.0, "reward": 0.046875, "reward_std": 0.05444391071796417, "rewards/simpleverify_reward/mean": 0.046875, "rewards/simpleverify_reward/std": 0.21220162510871887, "step": 88 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1997.9765625, "completions/mean_terminated_length": 1671.3529052734375, "completions/min_length": 1275.0, "completions/min_terminated_length": 1275.0, "epoch": 0.03158268275372605, "frac_reward_zero_std": 0.8125, "grad_norm": 0.18252821266651154, "learning_rate": 9.559999999999998e-07, "loss": 0.007, "num_tokens": 24027271.0, "reward": 0.0703125, "reward_std": 0.07996084541082382, "rewards/simpleverify_reward/mean": 0.0703125, "rewards/simpleverify_reward/std": 0.2566775679588318, "step": 89 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1977.0, "completions/mean_length": 2026.546875, "completions/mean_terminated_length": 1836.769287109375, "completions/min_length": 1508.0, "completions/min_terminated_length": 1508.0, "epoch": 0.0319375443577005, "frac_reward_zero_std": 0.6875, "grad_norm": 0.21926119923591614, "learning_rate": 9.555e-07, "loss": 0.0051, "num_tokens": 24296453.0, "reward": 0.078125, "reward_std": 0.1354655921459198, "rewards/simpleverify_reward/mean": 0.078125, "rewards/simpleverify_reward/std": 0.2694226801395416, "step": 90 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1758.0, "completions/mean_length": 2032.2734375, "completions/mean_terminated_length": 1645.4000244140625, "completions/min_length": 1489.0, "completions/min_terminated_length": 1489.0, "epoch": 0.032292405961674944, "frac_reward_zero_std": 0.875, "grad_norm": 0.1501067578792572, "learning_rate": 9.55e-07, "loss": 0.0035, "num_tokens": 24568840.0, "reward": 0.046875, "reward_std": 0.05444391071796417, "rewards/simpleverify_reward/mean": 0.046875, "rewards/simpleverify_reward/std": 0.21220162510871887, "step": 91 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1986.0, "completions/mean_length": 2045.1171875, "completions/mean_terminated_length": 1863.5, "completions/min_length": 1741.0, "completions/min_terminated_length": 1741.0, "epoch": 0.032647267565649396, "frac_reward_zero_std": 0.8125, "grad_norm": 0.18133777379989624, "learning_rate": 9.545e-07, "loss": 0.0013, "num_tokens": 24840631.0, "reward": 0.03125, "reward_std": 0.07312605530023575, "rewards/simpleverify_reward/mean": 0.03125, "rewards/simpleverify_reward/std": 0.1746762990951538, "step": 92 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2023.0, "completions/mean_length": 2045.3046875, "completions/mean_terminated_length": 1979.0, "completions/min_length": 1941.0, "completions/min_terminated_length": 1941.0, "epoch": 0.03300212916962385, "frac_reward_zero_std": 0.8125, "grad_norm": 0.17109790444374084, "learning_rate": 9.539999999999999e-07, "loss": 0.0011, "num_tokens": 25112822.0, "reward": 0.046875, "reward_std": 0.08337578922510147, "rewards/simpleverify_reward/mean": 0.046875, "rewards/simpleverify_reward/std": 0.21220162510871887, "step": 93 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1947.0, "completions/mean_length": 1976.625, "completions/mean_terminated_length": 1540.4444580078125, "completions/min_length": 1054.0, "completions/min_terminated_length": 1054.0, "epoch": 0.0333569907735983, "frac_reward_zero_std": 0.8125, "grad_norm": 0.1924932301044464, "learning_rate": 9.535e-07, "loss": 0.0068, "num_tokens": 25377030.0, "reward": 0.0859375, "reward_std": 0.0765409916639328, "rewards/simpleverify_reward/mean": 0.0859375, "rewards/simpleverify_reward/std": 0.2813730239868164, "step": 94 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1912.0, "completions/mean_length": 2044.890625, "completions/mean_terminated_length": 1849.0, "completions/min_length": 1786.0, "completions/min_terminated_length": 1786.0, "epoch": 0.033711852377572744, "frac_reward_zero_std": 0.875, "grad_norm": 0.12767784297466278, "learning_rate": 9.529999999999999e-07, "loss": 0.0021, "num_tokens": 25652480.0, "reward": 0.015625, "reward_std": 0.04419417306780815, "rewards/simpleverify_reward/mean": 0.015625, "rewards/simpleverify_reward/std": 0.12450689822435379, "step": 95 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1818.0, "completions/mean_length": 1928.1875, "completions/mean_terminated_length": 1025.60009765625, "completions/min_length": 539.0, "completions/min_terminated_length": 539.0, "epoch": 0.034066713981547196, "frac_reward_zero_std": 0.875, "grad_norm": 0.22118103504180908, "learning_rate": 9.525e-07, "loss": 0.0114, "num_tokens": 25911064.0, "reward": 0.0703125, "reward_std": 0.05102896690368652, "rewards/simpleverify_reward/mean": 0.0703125, "rewards/simpleverify_reward/std": 0.2566775679588318, "step": 96 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2015.0, "completions/mean_length": 1874.0, "completions/mean_terminated_length": 1191.3846435546875, "completions/min_length": 815.0, "completions/min_terminated_length": 815.0, "epoch": 0.03442157558552165, "frac_reward_zero_std": 0.75, "grad_norm": 0.24148720502853394, "learning_rate": 9.52e-07, "loss": 0.0054, "num_tokens": 26162264.0, "reward": 0.0703125, "reward_std": 0.10994865000247955, "rewards/simpleverify_reward/mean": 0.0703125, "rewards/simpleverify_reward/std": 0.2566775679588318, "step": 97 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1918.0, "completions/mean_length": 2031.609375, "completions/mean_terminated_length": 1785.75, "completions/min_length": 1602.0, "completions/min_terminated_length": 1602.0, "epoch": 0.0347764371894961, "frac_reward_zero_std": 1.0, "grad_norm": 0.0, "learning_rate": 9.515e-07, "loss": 0.0, "num_tokens": 26434846.0, "reward": 0.0625, "reward_std": 0.0, "rewards/simpleverify_reward/mean": 0.0625, "rewards/simpleverify_reward/std": 0.24301259219646454, "step": 98 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 2000.828125, "completions/mean_terminated_length": 1712.5555419921875, "completions/min_length": 1439.0, "completions/min_terminated_length": 1439.0, "epoch": 0.035131298793470545, "frac_reward_zero_std": 0.75, "grad_norm": 0.2180820107460022, "learning_rate": 9.509999999999999e-07, "loss": 0.0013, "num_tokens": 26699536.0, "reward": 0.125, "reward_std": 0.10888782143592834, "rewards/simpleverify_reward/mean": 0.125, "rewards/simpleverify_reward/std": 0.3320184051990509, "step": 99 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1982.7890625, "completions/mean_terminated_length": 1289.181884765625, "completions/min_length": 799.0, "completions/min_terminated_length": 799.0, "epoch": 0.035486160397444996, "frac_reward_zero_std": 0.875, "grad_norm": 0.15329216420650482, "learning_rate": 9.504999999999999e-07, "loss": 0.008, "num_tokens": 26965981.0, "reward": 0.0859375, "reward_std": 0.05550473928451538, "rewards/simpleverify_reward/mean": 0.0859375, "rewards/simpleverify_reward/std": 0.2813730239868164, "step": 100 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1828.0, "completions/mean_length": 1909.25, "completions/mean_terminated_length": 1390.2222900390625, "completions/min_length": 988.0, "completions/min_terminated_length": 988.0, "epoch": 0.03584102200141945, "frac_reward_zero_std": 0.6875, "grad_norm": 0.25106897950172424, "learning_rate": 9.499999999999999e-07, "loss": 0.0023, "num_tokens": 27222821.0, "reward": 0.1953125, "reward_std": 0.12415502220392227, "rewards/simpleverify_reward/mean": 0.1953125, "rewards/simpleverify_reward/std": 0.3979988098144531, "step": 101 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1958.0, "completions/mean_length": 1950.140625, "completions/mean_terminated_length": 1212.933349609375, "completions/min_length": 568.0, "completions/min_terminated_length": 568.0, "epoch": 0.0361958836053939, "frac_reward_zero_std": 0.8125, "grad_norm": 0.1870078295469284, "learning_rate": 9.495e-07, "loss": -0.0009, "num_tokens": 27483047.0, "reward": 0.125, "reward_std": 0.08785156160593033, "rewards/simpleverify_reward/mean": 0.125, "rewards/simpleverify_reward/std": 0.3320184051990509, "step": 102 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1859.0, "completions/mean_length": 1948.390625, "completions/mean_terminated_length": 1251.125, "completions/min_length": 810.0, "completions/min_terminated_length": 810.0, "epoch": 0.036550745209368345, "frac_reward_zero_std": 0.75, "grad_norm": 0.22619827091693878, "learning_rate": 9.489999999999999e-07, "loss": 0.0063, "num_tokens": 27742857.0, "reward": 0.125, "reward_std": 0.10888782143592834, "rewards/simpleverify_reward/mean": 0.125, "rewards/simpleverify_reward/std": 0.3320184051990509, "step": 103 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1975.8203125, "completions/mean_terminated_length": 1646.3043212890625, "completions/min_length": 1091.0, "completions/min_terminated_length": 1091.0, "epoch": 0.036905606813342796, "frac_reward_zero_std": 0.625, "grad_norm": 0.2571430504322052, "learning_rate": 9.485e-07, "loss": 0.006, "num_tokens": 28007634.0, "reward": 0.171875, "reward_std": 0.16333173215389252, "rewards/simpleverify_reward/mean": 0.171875, "rewards/simpleverify_reward/std": 0.3787541687488556, "step": 104 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.84375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2013.0, "completions/mean_length": 1922.2109375, "completions/mean_terminated_length": 1242.9500732421875, "completions/min_length": 519.0, "completions/min_terminated_length": 519.0, "epoch": 0.03726046841731725, "frac_reward_zero_std": 0.75, "grad_norm": 0.20960628986358643, "learning_rate": 9.479999999999999e-07, "loss": 0.004, "num_tokens": 28265413.0, "reward": 0.1484375, "reward_std": 0.10994865000247955, "rewards/simpleverify_reward/mean": 0.1484375, "rewards/simpleverify_reward/std": 0.356930136680603, "step": 105 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1922.3984375, "completions/mean_terminated_length": 1452.5555419921875, "completions/min_length": 808.0, "completions/min_terminated_length": 808.0, "epoch": 0.03761533002129169, "frac_reward_zero_std": 0.625, "grad_norm": 0.25948667526245117, "learning_rate": 9.474999999999999e-07, "loss": 0.0167, "num_tokens": 28521936.0, "reward": 0.15625, "reward_std": 0.15650182962417603, "rewards/simpleverify_reward/mean": 0.15625, "rewards/simpleverify_reward/std": 0.3645188808441162, "step": 106 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1811.0, "completions/mean_length": 1992.0078125, "completions/mean_terminated_length": 1496.6923828125, "completions/min_length": 1174.0, "completions/min_terminated_length": 1174.0, "epoch": 0.037970191625266145, "frac_reward_zero_std": 0.75, "grad_norm": 0.23777250945568085, "learning_rate": 9.469999999999999e-07, "loss": 0.0025, "num_tokens": 28786545.0, "reward": 0.15625, "reward_std": 0.11913755536079407, "rewards/simpleverify_reward/mean": 0.15625, "rewards/simpleverify_reward/std": 0.3645188808441162, "step": 107 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2010.0, "completions/mean_length": 1932.390625, "completions/mean_terminated_length": 1404.6087646484375, "completions/min_length": 699.0, "completions/min_terminated_length": 699.0, "epoch": 0.0383250532292406, "frac_reward_zero_std": 0.875, "grad_norm": 0.14967875182628632, "learning_rate": 9.465e-07, "loss": 0.0058, "num_tokens": 29044451.0, "reward": 0.109375, "reward_std": 0.05444391071796417, "rewards/simpleverify_reward/mean": 0.109375, "rewards/simpleverify_reward/std": 0.31333550810813904, "step": 108 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 2044.546875, "completions/mean_terminated_length": 1974.3333740234375, "completions/min_length": 1919.0, "completions/min_terminated_length": 1919.0, "epoch": 0.03867991483321505, "frac_reward_zero_std": 0.875, "grad_norm": 0.15848353505134583, "learning_rate": 9.459999999999999e-07, "loss": 0.0007, "num_tokens": 29320673.0, "reward": 0.046875, "reward_std": 0.05444391071796417, "rewards/simpleverify_reward/mean": 0.046875, "rewards/simpleverify_reward/std": 0.21220162510871887, "step": 109 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1756.0, "completions/mean_length": 2006.546875, "completions/mean_terminated_length": 1458.4444580078125, "completions/min_length": 1274.0, "completions/min_terminated_length": 1274.0, "epoch": 0.03903477643718949, "frac_reward_zero_std": 0.75, "grad_norm": 0.1988353282213211, "learning_rate": 9.455e-07, "loss": 0.0003, "num_tokens": 29590663.0, "reward": 0.0859375, "reward_std": 0.09522314369678497, "rewards/simpleverify_reward/mean": 0.0859375, "rewards/simpleverify_reward/std": 0.2813730239868164, "step": 110 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1845.328125, "completions/mean_terminated_length": 1382.820556640625, "completions/min_length": 621.0, "completions/min_terminated_length": 621.0, "epoch": 0.039389638041163945, "frac_reward_zero_std": 0.625, "grad_norm": 0.2873983085155487, "learning_rate": 9.45e-07, "loss": 0.0118, "num_tokens": 29838401.0, "reward": 0.203125, "reward_std": 0.16097761690616608, "rewards/simpleverify_reward/mean": 0.203125, "rewards/simpleverify_reward/std": 0.40390563011169434, "step": 111 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1782.0, "completions/mean_length": 2019.640625, "completions/mean_terminated_length": 1443.0, "completions/min_length": 1061.0, "completions/min_terminated_length": 1061.0, "epoch": 0.0397444996451384, "frac_reward_zero_std": 0.875, "grad_norm": 0.15921390056610107, "learning_rate": 9.444999999999999e-07, "loss": 0.0036, "num_tokens": 30106403.0, "reward": 0.0546875, "reward_std": 0.05102896690368652, "rewards/simpleverify_reward/mean": 0.0546875, "rewards/simpleverify_reward/std": 0.22826264798641205, "step": 112 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1698.0, "completions/mean_length": 2042.234375, "completions/mean_terminated_length": 1679.0, "completions/min_length": 1660.0, "completions/min_terminated_length": 1660.0, "epoch": 0.04009936124911285, "frac_reward_zero_std": 0.875, "grad_norm": 0.17053626477718353, "learning_rate": 9.439999999999999e-07, "loss": 0.0029, "num_tokens": 30380529.0, "reward": 0.0234375, "reward_std": 0.05102896690368652, "rewards/simpleverify_reward/mean": 0.0234375, "rewards/simpleverify_reward/std": 0.15188287198543549, "step": 113 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1973.0, "completions/mean_length": 2039.4453125, "completions/mean_terminated_length": 1829.0, "completions/min_length": 1616.0, "completions/min_terminated_length": 1616.0, "epoch": 0.04045422285308729, "frac_reward_zero_std": 0.8125, "grad_norm": 0.19428665935993195, "learning_rate": 9.434999999999999e-07, "loss": 0.0017, "num_tokens": 30652874.0, "reward": 0.046875, "reward_std": 0.08337578922510147, "rewards/simpleverify_reward/mean": 0.046875, "rewards/simpleverify_reward/std": 0.21220162510871887, "step": 114 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.78125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1997.0, "completions/mean_length": 1924.109375, "completions/mean_terminated_length": 1481.6429443359375, "completions/min_length": 1095.0, "completions/min_terminated_length": 1095.0, "epoch": 0.040809084457061745, "frac_reward_zero_std": 0.875, "grad_norm": 0.14166906476020813, "learning_rate": 9.429999999999999e-07, "loss": 0.0033, "num_tokens": 30910352.0, "reward": 0.1796875, "reward_std": 0.061278700828552246, "rewards/simpleverify_reward/mean": 0.1796875, "rewards/simpleverify_reward/std": 0.3854354918003082, "step": 115 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2006.0, "completions/mean_length": 2044.375, "completions/mean_terminated_length": 1816.0, "completions/min_length": 1626.0, "completions/min_terminated_length": 1626.0, "epoch": 0.0411639460610362, "frac_reward_zero_std": 0.9375, "grad_norm": 0.11061698943376541, "learning_rate": 9.425e-07, "loss": 0.0021, "num_tokens": 31185192.0, "reward": 0.015625, "reward_std": 0.0289318785071373, "rewards/simpleverify_reward/mean": 0.015625, "rewards/simpleverify_reward/std": 0.12450689822435379, "step": 116 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1908.0, "completions/mean_length": 1894.5078125, "completions/mean_terminated_length": 1013.9473876953125, "completions/min_length": 36.0, "completions/min_terminated_length": 36.0, "epoch": 0.04151880766501065, "frac_reward_zero_std": 0.875, "grad_norm": 0.16402512788772583, "learning_rate": 9.419999999999999e-07, "loss": 0.0092, "num_tokens": 31441201.0, "reward": 0.078125, "reward_std": 0.06233953312039375, "rewards/simpleverify_reward/mean": 0.078125, "rewards/simpleverify_reward/std": 0.2694226801395416, "step": 117 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1991.0, "completions/mean_length": 2019.484375, "completions/mean_terminated_length": 1716.181884765625, "completions/min_length": 1009.0, "completions/min_terminated_length": 1009.0, "epoch": 0.04187366926898509, "frac_reward_zero_std": 0.9375, "grad_norm": 0.10785388201475143, "learning_rate": 9.415e-07, "loss": 0.003, "num_tokens": 31712487.0, "reward": 0.0546875, "reward_std": 0.022097086533904076, "rewards/simpleverify_reward/mean": 0.0546875, "rewards/simpleverify_reward/std": 0.22826264798641205, "step": 118 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1982.0, "completions/mean_length": 2045.765625, "completions/mean_terminated_length": 1905.0, "completions/min_length": 1828.0, "completions/min_terminated_length": 1828.0, "epoch": 0.042228530872959545, "frac_reward_zero_std": 0.8125, "grad_norm": 0.18608415126800537, "learning_rate": 9.409999999999999e-07, "loss": 0.0013, "num_tokens": 31989601.0, "reward": 0.0390625, "reward_std": 0.0765409991145134, "rewards/simpleverify_reward/mean": 0.0390625, "rewards/simpleverify_reward/std": 0.194504976272583, "step": 119 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1926.9453125, "completions/mean_terminated_length": 1629.21630859375, "completions/min_length": 1073.0, "completions/min_terminated_length": 1073.0, "epoch": 0.042583392476934, "frac_reward_zero_std": 0.5625, "grad_norm": 0.2868794798851013, "learning_rate": 9.404999999999999e-07, "loss": 0.0127, "num_tokens": 32250498.0, "reward": 0.25, "reward_std": 0.2001592218875885, "rewards/simpleverify_reward/mean": 0.25, "rewards/simpleverify_reward/std": 0.434714138507843, "step": 120 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1966.0, "completions/mean_length": 2021.9921875, "completions/mean_terminated_length": 1791.923095703125, "completions/min_length": 1523.0, "completions/min_terminated_length": 1523.0, "epoch": 0.04293825408090845, "frac_reward_zero_std": 0.8125, "grad_norm": 0.20643247663974762, "learning_rate": 9.399999999999999e-07, "loss": 0.004, "num_tokens": 32520753.0, "reward": 0.0859375, "reward_std": 0.094686359167099, "rewards/simpleverify_reward/mean": 0.0859375, "rewards/simpleverify_reward/std": 0.2813730239868164, "step": 121 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.90625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2005.0, "completions/mean_length": 1975.9140625, "completions/mean_terminated_length": 1279.0833740234375, "completions/min_length": 764.0, "completions/min_terminated_length": 764.0, "epoch": 0.043293115684882894, "frac_reward_zero_std": 0.6875, "grad_norm": 0.21788254380226135, "learning_rate": 9.395e-07, "loss": 0.0048, "num_tokens": 32784878.0, "reward": 0.0546875, "reward_std": 0.12415501475334167, "rewards/simpleverify_reward/mean": 0.0546875, "rewards/simpleverify_reward/std": 0.22826264798641205, "step": 122 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1999.4921875, "completions/mean_terminated_length": 1659.9375, "completions/min_length": 1119.0, "completions/min_terminated_length": 1119.0, "epoch": 0.043647977288857345, "frac_reward_zero_std": 0.875, "grad_norm": 0.1471034437417984, "learning_rate": 9.389999999999999e-07, "loss": 0.0048, "num_tokens": 33052301.0, "reward": 0.078125, "reward_std": 0.05444391071796417, "rewards/simpleverify_reward/mean": 0.078125, "rewards/simpleverify_reward/std": 0.2694226801395416, "step": 123 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 2037.8125, "completions/mean_terminated_length": 1830.666748046875, "completions/min_length": 1663.0, "completions/min_terminated_length": 1663.0, "epoch": 0.0440028388928318, "frac_reward_zero_std": 0.6875, "grad_norm": 0.24567624926567078, "learning_rate": 9.385e-07, "loss": 0.0054, "num_tokens": 33326197.0, "reward": 0.078125, "reward_std": 0.13781970739364624, "rewards/simpleverify_reward/mean": 0.078125, "rewards/simpleverify_reward/std": 0.2694226801395416, "step": 124 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1962.0, "completions/mean_length": 1929.1484375, "completions/mean_terminated_length": 1462.8846435546875, "completions/min_length": 1138.0, "completions/min_terminated_length": 1138.0, "epoch": 0.04435770049680625, "frac_reward_zero_std": 0.5625, "grad_norm": 0.30356013774871826, "learning_rate": 9.379999999999998e-07, "loss": 0.0129, "num_tokens": 33582760.0, "reward": 0.2265625, "reward_std": 0.18649455904960632, "rewards/simpleverify_reward/mean": 0.2265625, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 125 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2000.0, "completions/mean_length": 1855.765625, "completions/mean_terminated_length": 1417.076904296875, "completions/min_length": 796.0, "completions/min_terminated_length": 796.0, "epoch": 0.044712562100780694, "frac_reward_zero_std": 0.625, "grad_norm": 0.2940121591091156, "learning_rate": 9.374999999999999e-07, "loss": 0.0186, "num_tokens": 33828442.0, "reward": 0.2578125, "reward_std": 0.1633366346359253, "rewards/simpleverify_reward/mean": 0.2578125, "rewards/simpleverify_reward/std": 0.43914902210235596, "step": 126 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1438.0, "completions/mean_length": 1982.484375, "completions/mean_terminated_length": 999.75, "completions/min_length": 500.0, "completions/min_terminated_length": 500.0, "epoch": 0.045067423704755145, "frac_reward_zero_std": 1.0, "grad_norm": 0.0, "learning_rate": 9.37e-07, "loss": 0.0, "num_tokens": 34094896.0, "reward": 0.0, "reward_std": 0.0, "rewards/simpleverify_reward/mean": 0.0, "rewards/simpleverify_reward/std": 0.0, "step": 127 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1942.0, "completions/mean_length": 1964.1796875, "completions/mean_terminated_length": 1560.3182373046875, "completions/min_length": 1018.0, "completions/min_terminated_length": 1018.0, "epoch": 0.0454222853087296, "frac_reward_zero_std": 0.875, "grad_norm": 0.13257147371768951, "learning_rate": 9.365e-07, "loss": 0.003, "num_tokens": 34357607.0, "reward": 0.171875, "reward_std": 0.05444391071796417, "rewards/simpleverify_reward/mean": 0.171875, "rewards/simpleverify_reward/std": 0.3787541687488556, "step": 128 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1992.9375, "completions/mean_terminated_length": 1607.5, "completions/min_length": 1251.0, "completions/min_terminated_length": 1251.0, "epoch": 0.04577714691270404, "frac_reward_zero_std": 0.8125, "grad_norm": 0.18217991292476654, "learning_rate": 9.36e-07, "loss": 0.0079, "num_tokens": 34621303.0, "reward": 0.1015625, "reward_std": 0.09021057933568954, "rewards/simpleverify_reward/mean": 0.1015625, "rewards/simpleverify_reward/std": 0.3032590448856354, "step": 129 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.90625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1996.9140625, "completions/mean_terminated_length": 1503.0833740234375, "completions/min_length": 1012.0, "completions/min_terminated_length": 1012.0, "epoch": 0.046132008516678494, "frac_reward_zero_std": 0.8125, "grad_norm": 0.17857706546783447, "learning_rate": 9.355e-07, "loss": 0.0041, "num_tokens": 34886660.0, "reward": 0.0859375, "reward_std": 0.06629125773906708, "rewards/simpleverify_reward/mean": 0.0859375, "rewards/simpleverify_reward/std": 0.2813730239868164, "step": 130 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1977.0, "completions/mean_length": 1893.3828125, "completions/mean_terminated_length": 1365.5517578125, "completions/min_length": 697.0, "completions/min_terminated_length": 697.0, "epoch": 0.046486870120652946, "frac_reward_zero_std": 0.875, "grad_norm": 0.15010495483875275, "learning_rate": 9.35e-07, "loss": 0.0009, "num_tokens": 35141157.0, "reward": 0.1484375, "reward_std": 0.05550473928451538, "rewards/simpleverify_reward/mean": 0.1484375, "rewards/simpleverify_reward/std": 0.356930136680603, "step": 131 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2009.0, "completions/mean_length": 1950.828125, "completions/mean_terminated_length": 1316.3529052734375, "completions/min_length": 776.0, "completions/min_terminated_length": 776.0, "epoch": 0.0468417317246274, "frac_reward_zero_std": 0.8125, "grad_norm": 0.200405091047287, "learning_rate": 9.344999999999999e-07, "loss": 0.0013, "num_tokens": 35402375.0, "reward": 0.0703125, "reward_std": 0.08679073303937912, "rewards/simpleverify_reward/mean": 0.0703125, "rewards/simpleverify_reward/std": 0.2566775679588318, "step": 132 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1996.0, "completions/mean_length": 2028.46875, "completions/mean_terminated_length": 1735.5, "completions/min_length": 1277.0, "completions/min_terminated_length": 1277.0, "epoch": 0.04719659332860184, "frac_reward_zero_std": 0.75, "grad_norm": 0.20619356632232666, "learning_rate": 9.34e-07, "loss": 0.0065, "num_tokens": 35675531.0, "reward": 0.0625, "reward_std": 0.11230766773223877, "rewards/simpleverify_reward/mean": 0.0625, "rewards/simpleverify_reward/std": 0.24301259219646454, "step": 133 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.84375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1940.2265625, "completions/mean_terminated_length": 1358.25, "completions/min_length": 762.0, "completions/min_terminated_length": 762.0, "epoch": 0.047551454932576294, "frac_reward_zero_std": 0.75, "grad_norm": 0.23402857780456543, "learning_rate": 9.334999999999999e-07, "loss": 0.0048, "num_tokens": 35935336.0, "reward": 0.1015625, "reward_std": 0.09969891607761383, "rewards/simpleverify_reward/mean": 0.1015625, "rewards/simpleverify_reward/std": 0.3032590448856354, "step": 134 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2016.0, "completions/mean_length": 2019.8046875, "completions/mean_terminated_length": 1596.875, "completions/min_length": 1251.0, "completions/min_terminated_length": 1251.0, "epoch": 0.047906316536550746, "frac_reward_zero_std": 0.875, "grad_norm": 0.20180900394916534, "learning_rate": 9.33e-07, "loss": -0.0055, "num_tokens": 36204183.0, "reward": 0.0234375, "reward_std": 0.05102896690368652, "rewards/simpleverify_reward/mean": 0.0234375, "rewards/simpleverify_reward/std": 0.15188287198543549, "step": 135 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 2044.171875, "completions/mean_terminated_length": 1950.0, "completions/min_length": 1771.0, "completions/min_terminated_length": 1771.0, "epoch": 0.0482611781405252, "frac_reward_zero_std": 0.8125, "grad_norm": 0.19126732647418976, "learning_rate": 9.325e-07, "loss": 0.002, "num_tokens": 36477517.0, "reward": 0.0390625, "reward_std": 0.0765409991145134, "rewards/simpleverify_reward/mean": 0.0390625, "rewards/simpleverify_reward/std": 0.194504976272583, "step": 136 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1940.0, "completions/mean_length": 1958.140625, "completions/mean_terminated_length": 1442.631591796875, "completions/min_length": 709.0, "completions/min_terminated_length": 709.0, "epoch": 0.04861603974449964, "frac_reward_zero_std": 0.9375, "grad_norm": 0.10327829420566559, "learning_rate": 9.32e-07, "loss": 0.0017, "num_tokens": 36736951.0, "reward": 0.03125, "reward_std": 0.033407654613256454, "rewards/simpleverify_reward/mean": 0.03125, "rewards/simpleverify_reward/std": 0.1746762990951538, "step": 137 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1402.0, "completions/mean_length": 2042.953125, "completions/mean_terminated_length": 1402.0, "completions/min_length": 1402.0, "completions/min_terminated_length": 1402.0, "epoch": 0.048970901348474094, "frac_reward_zero_std": 0.875, "grad_norm": 0.17296747863292694, "learning_rate": 9.315e-07, "loss": 0.0036, "num_tokens": 37008529.0, "reward": 0.015625, "reward_std": 0.04419417306780815, "rewards/simpleverify_reward/mean": 0.015625, "rewards/simpleverify_reward/std": 0.12450689822435379, "step": 138 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 2035.7890625, "completions/mean_terminated_length": 1891.7000732421875, "completions/min_length": 1713.0, "completions/min_terminated_length": 1713.0, "epoch": 0.049325762952448546, "frac_reward_zero_std": 0.6875, "grad_norm": 0.24224716424942017, "learning_rate": 9.31e-07, "loss": 0.0016, "num_tokens": 37280334.0, "reward": 0.09375, "reward_std": 0.1173202246427536, "rewards/simpleverify_reward/mean": 0.09375, "rewards/simpleverify_reward/std": 0.29262590408325195, "step": 139 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1938.984375, "completions/mean_terminated_length": 1466.5833740234375, "completions/min_length": 956.0, "completions/min_terminated_length": 956.0, "epoch": 0.049680624556423, "frac_reward_zero_std": 0.8125, "grad_norm": 0.21501393616199493, "learning_rate": 9.304999999999999e-07, "loss": 0.0124, "num_tokens": 37544564.0, "reward": 0.1875, "reward_std": 0.08337578922510147, "rewards/simpleverify_reward/mean": 0.1875, "rewards/simpleverify_reward/std": 0.39184603095054626, "step": 140 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1987.0, "completions/mean_length": 2041.734375, "completions/mean_terminated_length": 1914.3333740234375, "completions/min_length": 1749.0, "completions/min_terminated_length": 1749.0, "epoch": 0.05003548616039744, "frac_reward_zero_std": 0.8125, "grad_norm": 0.2074357122182846, "learning_rate": 9.3e-07, "loss": 0.0006, "num_tokens": 37820074.0, "reward": 0.0703125, "reward_std": 0.07996084541082382, "rewards/simpleverify_reward/mean": 0.0703125, "rewards/simpleverify_reward/std": 0.2566775679588318, "step": 141 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1774.6875, "completions/mean_terminated_length": 1287.478271484375, "completions/min_length": 606.0, "completions/min_terminated_length": 606.0, "epoch": 0.050390347764371894, "frac_reward_zero_std": 0.625, "grad_norm": 0.3174847960472107, "learning_rate": 9.295e-07, "loss": 0.0062, "num_tokens": 38057058.0, "reward": 0.3046875, "reward_std": 0.15991678833961487, "rewards/simpleverify_reward/mean": 0.3046875, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 142 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1877.0, "completions/mean_length": 1967.578125, "completions/mean_terminated_length": 1018.6000366210938, "completions/min_length": 691.0, "completions/min_terminated_length": 691.0, "epoch": 0.050745209368346346, "frac_reward_zero_std": 0.9375, "grad_norm": 0.10959112644195557, "learning_rate": 9.29e-07, "loss": 0.0, "num_tokens": 38320236.0, "reward": 0.0703125, "reward_std": 0.022097086533904076, "rewards/simpleverify_reward/mean": 0.0703125, "rewards/simpleverify_reward/std": 0.2566775679588318, "step": 143 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1978.0625, "completions/mean_terminated_length": 1408.571533203125, "completions/min_length": 815.0, "completions/min_terminated_length": 815.0, "epoch": 0.0511000709723208, "frac_reward_zero_std": 0.875, "grad_norm": 0.1680544763803482, "learning_rate": 9.285e-07, "loss": 0.008, "num_tokens": 38585396.0, "reward": 0.1015625, "reward_std": 0.061278700828552246, "rewards/simpleverify_reward/mean": 0.1015625, "rewards/simpleverify_reward/std": 0.3032590448856354, "step": 144 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.65625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2000.0, "completions/mean_length": 1828.640625, "completions/mean_terminated_length": 1409.8636474609375, "completions/min_length": 564.0, "completions/min_terminated_length": 564.0, "epoch": 0.05145493257629524, "frac_reward_zero_std": 0.625, "grad_norm": 0.3061962425708771, "learning_rate": 9.28e-07, "loss": 0.0119, "num_tokens": 38828590.0, "reward": 0.2265625, "reward_std": 0.16439256072044373, "rewards/simpleverify_reward/mean": 0.2265625, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 145 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.84375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1984.0, "completions/mean_length": 1978.140625, "completions/mean_terminated_length": 1600.9000244140625, "completions/min_length": 1064.0, "completions/min_terminated_length": 1064.0, "epoch": 0.051809794180269694, "frac_reward_zero_std": 0.625, "grad_norm": 0.274245947599411, "learning_rate": 9.274999999999999e-07, "loss": 0.0122, "num_tokens": 39093920.0, "reward": 0.203125, "reward_std": 0.15650182962417603, "rewards/simpleverify_reward/mean": 0.203125, "rewards/simpleverify_reward/std": 0.40390563011169434, "step": 146 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2013.0, "completions/mean_length": 1921.7109375, "completions/mean_terminated_length": 1278.2381591796875, "completions/min_length": 679.0, "completions/min_terminated_length": 679.0, "epoch": 0.052164655784244146, "frac_reward_zero_std": 0.8125, "grad_norm": 0.18410632014274597, "learning_rate": 9.27e-07, "loss": -0.0007, "num_tokens": 39350571.0, "reward": 0.0859375, "reward_std": 0.0946863517165184, "rewards/simpleverify_reward/mean": 0.0859375, "rewards/simpleverify_reward/std": 0.2813730239868164, "step": 147 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1890.0, "completions/mean_length": 1944.0625, "completions/mean_terminated_length": 1265.4117431640625, "completions/min_length": 1039.0, "completions/min_terminated_length": 1039.0, "epoch": 0.0525195173882186, "frac_reward_zero_std": 0.6875, "grad_norm": 0.25119152665138245, "learning_rate": 9.264999999999999e-07, "loss": 0.003, "num_tokens": 39612371.0, "reward": 0.1015625, "reward_std": 0.13888052105903625, "rewards/simpleverify_reward/mean": 0.1015625, "rewards/simpleverify_reward/std": 0.3032590448856354, "step": 148 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1964.0, "completions/mean_length": 1892.59375, "completions/mean_terminated_length": 1219.166748046875, "completions/min_length": 805.0, "completions/min_terminated_length": 805.0, "epoch": 0.05287437899219304, "frac_reward_zero_std": 0.625, "grad_norm": 0.2648962736129761, "learning_rate": 9.26e-07, "loss": 0.0058, "num_tokens": 39866039.0, "reward": 0.1484375, "reward_std": 0.15991678833961487, "rewards/simpleverify_reward/mean": 0.1484375, "rewards/simpleverify_reward/std": 0.356930136680603, "step": 149 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1942.4375, "completions/mean_terminated_length": 1547.5555419921875, "completions/min_length": 857.0, "completions/min_terminated_length": 857.0, "epoch": 0.053229240596167494, "frac_reward_zero_std": 0.5625, "grad_norm": 0.29754072427749634, "learning_rate": 9.255e-07, "loss": 0.0099, "num_tokens": 40123687.0, "reward": 0.1796875, "reward_std": 0.21276798844337463, "rewards/simpleverify_reward/mean": 0.1796875, "rewards/simpleverify_reward/std": 0.3854354918003082, "step": 150 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2010.0, "completions/mean_length": 1904.75, "completions/mean_terminated_length": 1492.3636474609375, "completions/min_length": 752.0, "completions/min_terminated_length": 752.0, "epoch": 0.053584102200141946, "frac_reward_zero_std": 0.75, "grad_norm": 0.20326314866542816, "learning_rate": 9.25e-07, "loss": 0.0059, "num_tokens": 40382263.0, "reward": 0.171875, "reward_std": 0.11100947856903076, "rewards/simpleverify_reward/mean": 0.171875, "rewards/simpleverify_reward/std": 0.3787541687488556, "step": 151 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1986.0, "completions/mean_length": 2000.9609375, "completions/mean_terminated_length": 1671.6875, "completions/min_length": 1144.0, "completions/min_terminated_length": 1144.0, "epoch": 0.0539389638041164, "frac_reward_zero_std": 0.8125, "grad_norm": 0.18641862273216248, "learning_rate": 9.244999999999999e-07, "loss": -0.0005, "num_tokens": 40647978.0, "reward": 0.09375, "reward_std": 0.07312605530023575, "rewards/simpleverify_reward/mean": 0.09375, "rewards/simpleverify_reward/std": 0.29262590408325195, "step": 152 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.765625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1954.0, "completions/mean_length": 1908.640625, "completions/mean_terminated_length": 1453.4000244140625, "completions/min_length": 1080.0, "completions/min_terminated_length": 1080.0, "epoch": 0.05429382540809084, "frac_reward_zero_std": 0.875, "grad_norm": 0.14640246331691742, "learning_rate": 9.24e-07, "loss": 0.0045, "num_tokens": 40901964.0, "reward": 0.1953125, "reward_std": 0.05102896690368652, "rewards/simpleverify_reward/mean": 0.1953125, "rewards/simpleverify_reward/std": 0.3979988098144531, "step": 153 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1892.4140625, "completions/mean_terminated_length": 1462.2647705078125, "completions/min_length": 793.0, "completions/min_terminated_length": 793.0, "epoch": 0.054648687012065295, "frac_reward_zero_std": 0.6875, "grad_norm": 0.23988117277622223, "learning_rate": 9.234999999999999e-07, "loss": -0.001, "num_tokens": 41159345.0, "reward": 0.1171875, "reward_std": 0.14913025498390198, "rewards/simpleverify_reward/mean": 0.1171875, "rewards/simpleverify_reward/std": 0.322907418012619, "step": 154 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2014.0, "completions/mean_length": 2015.609375, "completions/mean_terminated_length": 1455.71435546875, "completions/min_length": 1092.0, "completions/min_terminated_length": 1092.0, "epoch": 0.055003548616039746, "frac_reward_zero_std": 0.75, "grad_norm": 0.24103501439094543, "learning_rate": 9.23e-07, "loss": -0.0022, "num_tokens": 41427239.0, "reward": 0.0546875, "reward_std": 0.09969891607761383, "rewards/simpleverify_reward/mean": 0.0546875, "rewards/simpleverify_reward/std": 0.22826264798641205, "step": 155 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1966.0, "completions/mean_length": 1838.5234375, "completions/mean_terminated_length": 1281.914306640625, "completions/min_length": 625.0, "completions/min_terminated_length": 625.0, "epoch": 0.05535841022001419, "frac_reward_zero_std": 0.75, "grad_norm": 0.21790824830532074, "learning_rate": 9.225e-07, "loss": 0.0041, "num_tokens": 41674578.0, "reward": 0.25, "reward_std": 0.10205793380737305, "rewards/simpleverify_reward/mean": 0.25, "rewards/simpleverify_reward/std": 0.434714138507843, "step": 156 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.78125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1953.4296875, "completions/mean_terminated_length": 1615.6785888671875, "completions/min_length": 1161.0, "completions/min_terminated_length": 1161.0, "epoch": 0.05571327182398864, "frac_reward_zero_std": 0.6875, "grad_norm": 0.2287120372056961, "learning_rate": 9.22e-07, "loss": 0.0055, "num_tokens": 41936457.0, "reward": 0.1640625, "reward_std": 0.1344047486782074, "rewards/simpleverify_reward/mean": 0.1640625, "rewards/simpleverify_reward/std": 0.371787428855896, "step": 157 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.65625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2022.0, "completions/mean_length": 1832.6015625, "completions/mean_terminated_length": 1421.3863525390625, "completions/min_length": 704.0, "completions/min_terminated_length": 704.0, "epoch": 0.056068133427963095, "frac_reward_zero_std": 0.5625, "grad_norm": 0.30966436862945557, "learning_rate": 9.215e-07, "loss": 0.0109, "num_tokens": 42182582.0, "reward": 0.265625, "reward_std": 0.17965975403785706, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 158 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1975.1953125, "completions/mean_terminated_length": 1530.27783203125, "completions/min_length": 677.0, "completions/min_terminated_length": 677.0, "epoch": 0.056422995031937546, "frac_reward_zero_std": 0.875, "grad_norm": 0.16462011635303497, "learning_rate": 9.21e-07, "loss": 0.0032, "num_tokens": 42448615.0, "reward": 0.09375, "reward_std": 0.05444391071796417, "rewards/simpleverify_reward/mean": 0.09375, "rewards/simpleverify_reward/std": 0.29262590408325195, "step": 159 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1987.0, "completions/mean_length": 1913.90625, "completions/mean_terminated_length": 1387.84619140625, "completions/min_length": 592.0, "completions/min_terminated_length": 592.0, "epoch": 0.05677785663591199, "frac_reward_zero_std": 0.75, "grad_norm": 0.19266045093536377, "learning_rate": 9.204999999999999e-07, "loss": 0.0157, "num_tokens": 42704939.0, "reward": 0.1875, "reward_std": 0.1065337061882019, "rewards/simpleverify_reward/mean": 0.1875, "rewards/simpleverify_reward/std": 0.39184603095054626, "step": 160 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1936.7421875, "completions/mean_terminated_length": 1500.269287109375, "completions/min_length": 1059.0, "completions/min_terminated_length": 1059.0, "epoch": 0.05713271823988644, "frac_reward_zero_std": 0.6875, "grad_norm": 0.25348079204559326, "learning_rate": 9.2e-07, "loss": -0.0007, "num_tokens": 42964178.0, "reward": 0.25, "reward_std": 0.15466687083244324, "rewards/simpleverify_reward/mean": 0.25, "rewards/simpleverify_reward/std": 0.434714138507843, "step": 161 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1731.0, "completions/mean_length": 1900.9375, "completions/mean_terminated_length": 1263.666748046875, "completions/min_length": 489.0, "completions/min_terminated_length": 489.0, "epoch": 0.057487579843860895, "frac_reward_zero_std": 0.75, "grad_norm": 0.25043025612831116, "learning_rate": 9.194999999999999e-07, "loss": 0.0051, "num_tokens": 43219506.0, "reward": 0.1171875, "reward_std": 0.11336849629878998, "rewards/simpleverify_reward/mean": 0.1171875, "rewards/simpleverify_reward/std": 0.322907418012619, "step": 162 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1904.0, "completions/mean_length": 2015.6015625, "completions/mean_terminated_length": 1671.0, "completions/min_length": 1376.0, "completions/min_terminated_length": 1376.0, "epoch": 0.05784244144783535, "frac_reward_zero_std": 0.9375, "grad_norm": 0.11453405022621155, "learning_rate": 9.19e-07, "loss": 0.0036, "num_tokens": 43492431.0, "reward": 0.0546875, "reward_std": 0.022097086533904076, "rewards/simpleverify_reward/mean": 0.0546875, "rewards/simpleverify_reward/std": 0.22826264798641205, "step": 163 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1997.0, "completions/mean_length": 1965.4453125, "completions/mean_terminated_length": 1491.8421630859375, "completions/min_length": 1020.0, "completions/min_terminated_length": 1020.0, "epoch": 0.05819730305180979, "frac_reward_zero_std": 0.75, "grad_norm": 0.23644348978996277, "learning_rate": 9.185e-07, "loss": 0.01, "num_tokens": 43755992.0, "reward": 0.109375, "reward_std": 0.09863808751106262, "rewards/simpleverify_reward/mean": 0.109375, "rewards/simpleverify_reward/std": 0.31333550810813904, "step": 164 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1994.0, "completions/mean_length": 1958.046875, "completions/mean_terminated_length": 1408.3333740234375, "completions/min_length": 648.0, "completions/min_terminated_length": 648.0, "epoch": 0.05855216465578424, "frac_reward_zero_std": 0.6875, "grad_norm": 0.22757942974567413, "learning_rate": 9.18e-07, "loss": 0.0107, "num_tokens": 44016478.0, "reward": 0.15625, "reward_std": 0.13781969249248505, "rewards/simpleverify_reward/mean": 0.15625, "rewards/simpleverify_reward/std": 0.3645188808441162, "step": 165 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2019.0, "completions/mean_length": 1868.0859375, "completions/mean_terminated_length": 1305.1290283203125, "completions/min_length": 702.0, "completions/min_terminated_length": 702.0, "epoch": 0.058907026259758695, "frac_reward_zero_std": 0.75, "grad_norm": 0.21873225271701813, "learning_rate": 9.174999999999999e-07, "loss": 0.0115, "num_tokens": 44266281.0, "reward": 0.15625, "reward_std": 0.11913755536079407, "rewards/simpleverify_reward/mean": 0.15625, "rewards/simpleverify_reward/std": 0.3645188808441162, "step": 166 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2004.0, "completions/mean_length": 1897.609375, "completions/mean_terminated_length": 1173.0, "completions/min_length": 431.0, "completions/min_terminated_length": 431.0, "epoch": 0.05926188786373315, "frac_reward_zero_std": 0.8125, "grad_norm": 0.22603987157344818, "learning_rate": 9.17e-07, "loss": 0.0145, "num_tokens": 44522247.0, "reward": 0.1015625, "reward_std": 0.0765409991145134, "rewards/simpleverify_reward/mean": 0.1015625, "rewards/simpleverify_reward/std": 0.3032590448856354, "step": 167 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1764.1171875, "completions/mean_terminated_length": 1335.5098876953125, "completions/min_length": 612.0, "completions/min_terminated_length": 612.0, "epoch": 0.05961674946770759, "frac_reward_zero_std": 0.6875, "grad_norm": 0.2754305303096771, "learning_rate": 9.164999999999999e-07, "loss": 0.0009, "num_tokens": 44757830.0, "reward": 0.2265625, "reward_std": 0.14913025498390198, "rewards/simpleverify_reward/mean": 0.2265625, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 168 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1994.0, "completions/mean_length": 1954.2734375, "completions/mean_terminated_length": 1476.71435546875, "completions/min_length": 851.0, "completions/min_terminated_length": 851.0, "epoch": 0.05997161107168204, "frac_reward_zero_std": 0.75, "grad_norm": 0.22915028035640717, "learning_rate": 9.16e-07, "loss": 0.0191, "num_tokens": 45018985.0, "reward": 0.1640625, "reward_std": 0.11572261154651642, "rewards/simpleverify_reward/mean": 0.1640625, "rewards/simpleverify_reward/std": 0.371787428855896, "step": 169 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.84375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1891.0, "completions/mean_length": 1947.0, "completions/mean_terminated_length": 1401.5999755859375, "completions/min_length": 795.0, "completions/min_terminated_length": 795.0, "epoch": 0.060326472675656495, "frac_reward_zero_std": 0.625, "grad_norm": 0.28283485770225525, "learning_rate": 9.155e-07, "loss": 0.0112, "num_tokens": 45281017.0, "reward": 0.109375, "reward_std": 0.16675156354904175, "rewards/simpleverify_reward/mean": 0.109375, "rewards/simpleverify_reward/std": 0.31333550810813904, "step": 170 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.78125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2000.0, "completions/mean_length": 1841.125, "completions/mean_terminated_length": 1102.2857666015625, "completions/min_length": 351.0, "completions/min_terminated_length": 351.0, "epoch": 0.06068133427963095, "frac_reward_zero_std": 0.75, "grad_norm": 0.24894912540912628, "learning_rate": 9.15e-07, "loss": 0.0122, "num_tokens": 45527065.0, "reward": 0.1796875, "reward_std": 0.10889272391796112, "rewards/simpleverify_reward/mean": 0.1796875, "rewards/simpleverify_reward/std": 0.3854354918003082, "step": 171 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2010.0, "completions/mean_length": 1918.875, "completions/mean_terminated_length": 1260.952392578125, "completions/min_length": 550.0, "completions/min_terminated_length": 550.0, "epoch": 0.06103619588360539, "frac_reward_zero_std": 0.6875, "grad_norm": 0.21681544184684753, "learning_rate": 9.145e-07, "loss": 0.005, "num_tokens": 45782865.0, "reward": 0.140625, "reward_std": 0.1173202320933342, "rewards/simpleverify_reward/mean": 0.140625, "rewards/simpleverify_reward/std": 0.3490002751350403, "step": 172 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 2021.2890625, "completions/mean_terminated_length": 1803.7857666015625, "completions/min_length": 1294.0, "completions/min_terminated_length": 1294.0, "epoch": 0.06139105748757984, "frac_reward_zero_std": 0.75, "grad_norm": 0.21752753853797913, "learning_rate": 9.14e-07, "loss": 0.0093, "num_tokens": 46058550.0, "reward": 0.0859375, "reward_std": 0.12019838392734528, "rewards/simpleverify_reward/mean": 0.0859375, "rewards/simpleverify_reward/std": 0.2813730239868164, "step": 173 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1852.5234375, "completions/mean_terminated_length": 1333.1142578125, "completions/min_length": 703.0, "completions/min_terminated_length": 703.0, "epoch": 0.061745919091554295, "frac_reward_zero_std": 0.8125, "grad_norm": 0.16616222262382507, "learning_rate": 9.134999999999999e-07, "loss": 0.0007, "num_tokens": 46307033.0, "reward": 0.2265625, "reward_std": 0.0765409991145134, "rewards/simpleverify_reward/mean": 0.2265625, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 174 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.59375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2019.0, "completions/mean_length": 1706.1953125, "completions/mean_terminated_length": 1206.6346435546875, "completions/min_length": 357.0, "completions/min_terminated_length": 357.0, "epoch": 0.06210078069552875, "frac_reward_zero_std": 0.6875, "grad_norm": 0.307117223739624, "learning_rate": 9.13e-07, "loss": 0.0018, "num_tokens": 46539826.0, "reward": 0.265625, "reward_std": 0.13781970739364624, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 175 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2015.0, "completions/mean_length": 1875.8984375, "completions/mean_terminated_length": 1598.4285888671875, "completions/min_length": 838.0, "completions/min_terminated_length": 838.0, "epoch": 0.06245564229950319, "frac_reward_zero_std": 0.5, "grad_norm": 0.3874506652355194, "learning_rate": 9.124999999999999e-07, "loss": 0.0091, "num_tokens": 46792533.0, "reward": 0.328125, "reward_std": 0.2109457552433014, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 176 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1984.0, "completions/mean_length": 1857.8828125, "completions/mean_terminated_length": 1332.2647705078125, "completions/min_length": 728.0, "completions/min_terminated_length": 728.0, "epoch": 0.06281050390347764, "frac_reward_zero_std": 0.6875, "grad_norm": 0.2699841260910034, "learning_rate": 9.12e-07, "loss": 0.0098, "num_tokens": 47042390.0, "reward": 0.25, "reward_std": 0.12756997346878052, "rewards/simpleverify_reward/mean": 0.25, "rewards/simpleverify_reward/std": 0.434714138507843, "step": 177 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1958.0, "completions/mean_length": 1908.71875, "completions/mean_terminated_length": 1272.86962890625, "completions/min_length": 97.0, "completions/min_terminated_length": 97.0, "epoch": 0.0631653655074521, "frac_reward_zero_std": 0.8125, "grad_norm": 0.20633496344089508, "learning_rate": 9.115e-07, "loss": 0.0028, "num_tokens": 47298122.0, "reward": 0.09375, "reward_std": 0.07312604784965515, "rewards/simpleverify_reward/mean": 0.09375, "rewards/simpleverify_reward/std": 0.29262590408325195, "step": 178 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1938.0, "completions/mean_length": 1656.15625, "completions/mean_terminated_length": 1197.8983154296875, "completions/min_length": 734.0, "completions/min_terminated_length": 734.0, "epoch": 0.06352022711142655, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3872126340866089, "learning_rate": 9.109999999999999e-07, "loss": 0.0121, "num_tokens": 47519766.0, "reward": 0.40625, "reward_std": 0.19226360321044922, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 179 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1970.1171875, "completions/mean_terminated_length": 1573.2857666015625, "completions/min_length": 1208.0, "completions/min_terminated_length": 1208.0, "epoch": 0.063875088715401, "frac_reward_zero_std": 0.75, "grad_norm": 0.2036694586277008, "learning_rate": 9.104999999999999e-07, "loss": -0.0004, "num_tokens": 47785901.0, "reward": 0.1484375, "reward_std": 0.1054728776216507, "rewards/simpleverify_reward/mean": 0.1484375, "rewards/simpleverify_reward/std": 0.356930136680603, "step": 180 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1780.578125, "completions/mean_terminated_length": 1122.8648681640625, "completions/min_length": 454.0, "completions/min_terminated_length": 454.0, "epoch": 0.06422995031937544, "frac_reward_zero_std": 0.75, "grad_norm": 0.2026248425245285, "learning_rate": 9.1e-07, "loss": 0.0122, "num_tokens": 48027415.0, "reward": 0.140625, "reward_std": 0.11678344011306763, "rewards/simpleverify_reward/mean": 0.140625, "rewards/simpleverify_reward/std": 0.3490002751350403, "step": 181 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2021.0, "completions/mean_length": 1963.1328125, "completions/mean_terminated_length": 1575.6956787109375, "completions/min_length": 1061.0, "completions/min_terminated_length": 1061.0, "epoch": 0.06458481192334989, "frac_reward_zero_std": 0.625, "grad_norm": 0.29536622762680054, "learning_rate": 9.094999999999999e-07, "loss": 0.0055, "num_tokens": 48293024.0, "reward": 0.1328125, "reward_std": 0.15756267309188843, "rewards/simpleverify_reward/mean": 0.1328125, "rewards/simpleverify_reward/std": 0.3407054841518402, "step": 182 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1926.0234375, "completions/mean_terminated_length": 1338.3182373046875, "completions/min_length": 668.0, "completions/min_terminated_length": 668.0, "epoch": 0.06493967352732434, "frac_reward_zero_std": 0.6875, "grad_norm": 0.2782774865627289, "learning_rate": 9.09e-07, "loss": 0.0017, "num_tokens": 48554011.0, "reward": 0.1484375, "reward_std": 0.1331065595149994, "rewards/simpleverify_reward/mean": 0.1484375, "rewards/simpleverify_reward/std": 0.356930136680603, "step": 183 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.9296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1758.0, "completions/mean_length": 1981.265625, "completions/mean_terminated_length": 1098.888916015625, "completions/min_length": 908.0, "completions/min_terminated_length": 908.0, "epoch": 0.06529453513129879, "frac_reward_zero_std": 1.0, "grad_norm": 0.0, "learning_rate": 9.085e-07, "loss": 0.0, "num_tokens": 48818229.0, "reward": 0.0625, "reward_std": 0.0, "rewards/simpleverify_reward/mean": 0.0625, "rewards/simpleverify_reward/std": 0.24301259219646454, "step": 184 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2007.0, "completions/mean_length": 1884.7265625, "completions/mean_terminated_length": 1414.697021484375, "completions/min_length": 977.0, "completions/min_terminated_length": 977.0, "epoch": 0.06564939673527324, "frac_reward_zero_std": 0.625, "grad_norm": 0.24678251147270203, "learning_rate": 9.08e-07, "loss": 0.0022, "num_tokens": 49070746.0, "reward": 0.2734375, "reward_std": 0.1633366346359253, "rewards/simpleverify_reward/mean": 0.2734375, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 185 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2015.0, "completions/mean_length": 1718.921875, "completions/mean_terminated_length": 1170.4583740234375, "completions/min_length": 464.0, "completions/min_terminated_length": 464.0, "epoch": 0.0660042583392477, "frac_reward_zero_std": 0.6875, "grad_norm": 0.2577919661998749, "learning_rate": 9.074999999999999e-07, "loss": 0.005, "num_tokens": 49299848.0, "reward": 0.25, "reward_std": 0.14913517236709595, "rewards/simpleverify_reward/mean": 0.25, "rewards/simpleverify_reward/std": 0.434714138507843, "step": 186 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1878.796875, "completions/mean_terminated_length": 1411.0, "completions/min_length": 942.0, "completions/min_terminated_length": 942.0, "epoch": 0.06635911994322215, "frac_reward_zero_std": 0.75, "grad_norm": 0.22841861844062805, "learning_rate": 9.07e-07, "loss": -0.002, "num_tokens": 49547974.0, "reward": 0.2109375, "reward_std": 0.09522313624620438, "rewards/simpleverify_reward/mean": 0.2109375, "rewards/simpleverify_reward/std": 0.4095771610736847, "step": 187 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.703125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1895.6875, "completions/mean_terminated_length": 1534.9473876953125, "completions/min_length": 966.0, "completions/min_terminated_length": 966.0, "epoch": 0.0667139815471966, "frac_reward_zero_std": 0.75, "grad_norm": 0.23691679537296295, "learning_rate": 9.064999999999999e-07, "loss": 0.0005, "num_tokens": 49801662.0, "reward": 0.1640625, "reward_std": 0.11572261154651642, "rewards/simpleverify_reward/mean": 0.1640625, "rewards/simpleverify_reward/std": 0.371787428855896, "step": 188 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1968.0, "completions/mean_length": 1794.8359375, "completions/mean_terminated_length": 1327.888916015625, "completions/min_length": 774.0, "completions/min_terminated_length": 774.0, "epoch": 0.06706884315117104, "frac_reward_zero_std": 0.8125, "grad_norm": 0.16908808052539825, "learning_rate": 9.06e-07, "loss": 0.0015, "num_tokens": 50042185.0, "reward": 0.296875, "reward_std": 0.08337578922510147, "rewards/simpleverify_reward/mean": 0.296875, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 189 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1912.046875, "completions/mean_terminated_length": 1378.6923828125, "completions/min_length": 707.0, "completions/min_terminated_length": 707.0, "epoch": 0.06742370475514549, "frac_reward_zero_std": 0.8125, "grad_norm": 0.24108128249645233, "learning_rate": 9.055e-07, "loss": -0.008, "num_tokens": 50298399.0, "reward": 0.109375, "reward_std": 0.08337578922510147, "rewards/simpleverify_reward/mean": 0.109375, "rewards/simpleverify_reward/std": 0.31333550810813904, "step": 190 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.765625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1994.0, "completions/mean_length": 1869.0703125, "completions/mean_terminated_length": 1284.5667724609375, "completions/min_length": 693.0, "completions/min_terminated_length": 693.0, "epoch": 0.06777856635911994, "frac_reward_zero_std": 0.8125, "grad_norm": 0.20033231377601624, "learning_rate": 9.05e-07, "loss": 0.013, "num_tokens": 50550536.0, "reward": 0.15625, "reward_std": 0.09810129553079605, "rewards/simpleverify_reward/mean": 0.15625, "rewards/simpleverify_reward/std": 0.3645188808441162, "step": 191 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1989.2734375, "completions/mean_terminated_length": 1758.8846435546875, "completions/min_length": 1332.0, "completions/min_terminated_length": 1332.0, "epoch": 0.06813342796309439, "frac_reward_zero_std": 0.6875, "grad_norm": 0.2520403265953064, "learning_rate": 9.045e-07, "loss": 0.0053, "num_tokens": 50819835.0, "reward": 0.203125, "reward_std": 0.14571532607078552, "rewards/simpleverify_reward/mean": 0.203125, "rewards/simpleverify_reward/std": 0.40390563011169434, "step": 192 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1984.1328125, "completions/mean_terminated_length": 1676.4091796875, "completions/min_length": 1251.0, "completions/min_terminated_length": 1251.0, "epoch": 0.06848828956706884, "frac_reward_zero_std": 0.8125, "grad_norm": 0.17692260444164276, "learning_rate": 9.039999999999999e-07, "loss": -0.0042, "num_tokens": 51085276.0, "reward": 0.1328125, "reward_std": 0.08891239762306213, "rewards/simpleverify_reward/mean": 0.1328125, "rewards/simpleverify_reward/std": 0.3407054841518402, "step": 193 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1687.3671875, "completions/mean_terminated_length": 1177.0377197265625, "completions/min_length": 576.0, "completions/min_terminated_length": 576.0, "epoch": 0.0688431511710433, "frac_reward_zero_std": 0.75, "grad_norm": 0.2691556513309479, "learning_rate": 9.034999999999999e-07, "loss": 0.0063, "num_tokens": 51310763.0, "reward": 0.2890625, "reward_std": 0.1054728776216507, "rewards/simpleverify_reward/mean": 0.2890625, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 194 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1770.734375, "completions/mean_terminated_length": 1259.3333740234375, "completions/min_length": 556.0, "completions/min_terminated_length": 556.0, "epoch": 0.06919801277501775, "frac_reward_zero_std": 0.6875, "grad_norm": 0.26433828473091125, "learning_rate": 9.03e-07, "loss": 0.005, "num_tokens": 51547081.0, "reward": 0.15625, "reward_std": 0.12756997346878052, "rewards/simpleverify_reward/mean": 0.15625, "rewards/simpleverify_reward/std": 0.3645188808441162, "step": 195 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1845.0625, "completions/mean_terminated_length": 1305.82861328125, "completions/min_length": 481.0, "completions/min_terminated_length": 481.0, "epoch": 0.0695528743789922, "frac_reward_zero_std": 0.75, "grad_norm": 0.22566500306129456, "learning_rate": 9.024999999999999e-07, "loss": 0.0074, "num_tokens": 51794273.0, "reward": 0.1484375, "reward_std": 0.11336850374937057, "rewards/simpleverify_reward/mean": 0.1484375, "rewards/simpleverify_reward/std": 0.356930136680603, "step": 196 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1988.0, "completions/mean_length": 1953.8203125, "completions/mean_terminated_length": 1338.88232421875, "completions/min_length": 748.0, "completions/min_terminated_length": 748.0, "epoch": 0.06990773598296664, "frac_reward_zero_std": 0.6875, "grad_norm": 0.26399531960487366, "learning_rate": 9.02e-07, "loss": 0.0028, "num_tokens": 52052954.0, "reward": 0.125, "reward_std": 0.1514892876148224, "rewards/simpleverify_reward/mean": 0.125, "rewards/simpleverify_reward/std": 0.3320184051990509, "step": 197 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1985.0, "completions/mean_length": 1909.8046875, "completions/mean_terminated_length": 1542.5999755859375, "completions/min_length": 761.0, "completions/min_terminated_length": 761.0, "epoch": 0.07026259758694109, "frac_reward_zero_std": 0.5625, "grad_norm": 0.30374157428741455, "learning_rate": 9.015e-07, "loss": 0.0112, "num_tokens": 52307337.0, "reward": 0.2421875, "reward_std": 0.20016413927078247, "rewards/simpleverify_reward/mean": 0.2421875, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 198 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1991.0, "completions/mean_length": 1700.375, "completions/mean_terminated_length": 1139.9183349609375, "completions/min_length": 516.0, "completions/min_terminated_length": 516.0, "epoch": 0.07061745919091554, "frac_reward_zero_std": 0.8125, "grad_norm": 0.21707706153392792, "learning_rate": 9.01e-07, "loss": 0.0018, "num_tokens": 52534617.0, "reward": 0.25, "reward_std": 0.09127141535282135, "rewards/simpleverify_reward/mean": 0.25, "rewards/simpleverify_reward/std": 0.434714138507843, "step": 199 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1977.0, "completions/mean_length": 1765.328125, "completions/mean_terminated_length": 1338.549072265625, "completions/min_length": 726.0, "completions/min_terminated_length": 726.0, "epoch": 0.07097232079488999, "frac_reward_zero_std": 0.5625, "grad_norm": 0.2907353937625885, "learning_rate": 9.004999999999999e-07, "loss": 0.0201, "num_tokens": 52772011.0, "reward": 0.2265625, "reward_std": 0.20699402689933777, "rewards/simpleverify_reward/mean": 0.2265625, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 200 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1958.0, "completions/mean_length": 1927.90625, "completions/mean_terminated_length": 1194.0, "completions/min_length": 590.0, "completions/min_terminated_length": 590.0, "epoch": 0.07132718239886444, "frac_reward_zero_std": 0.75, "grad_norm": 0.23527830839157104, "learning_rate": 9e-07, "loss": -0.0032, "num_tokens": 53033327.0, "reward": 0.0703125, "reward_std": 0.1054728776216507, "rewards/simpleverify_reward/mean": 0.0703125, "rewards/simpleverify_reward/std": 0.2566775679588318, "step": 201 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2023.0, "completions/mean_length": 1795.28125, "completions/mean_terminated_length": 1239.300048828125, "completions/min_length": 229.0, "completions/min_terminated_length": 229.0, "epoch": 0.0716820440028389, "frac_reward_zero_std": 0.5625, "grad_norm": 0.28900274634361267, "learning_rate": 8.994999999999999e-07, "loss": 0.018, "num_tokens": 53274891.0, "reward": 0.28125, "reward_std": 0.19568344950675964, "rewards/simpleverify_reward/mean": 0.28125, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 202 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.59375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1969.0, "completions/mean_length": 1680.6015625, "completions/mean_terminated_length": 1143.6346435546875, "completions/min_length": 61.0, "completions/min_terminated_length": 61.0, "epoch": 0.07203690560681335, "frac_reward_zero_std": 0.625, "grad_norm": 0.32915744185447693, "learning_rate": 8.99e-07, "loss": 0.0116, "num_tokens": 53498520.0, "reward": 0.3359375, "reward_std": 0.154142826795578, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 203 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1962.0, "completions/mean_length": 1945.4140625, "completions/mean_terminated_length": 1318.5, "completions/min_length": 819.0, "completions/min_terminated_length": 819.0, "epoch": 0.0723917672107878, "frac_reward_zero_std": 0.6875, "grad_norm": 0.23899303376674652, "learning_rate": 8.985e-07, "loss": -0.0026, "num_tokens": 53760725.0, "reward": 0.1328125, "reward_std": 0.1344047486782074, "rewards/simpleverify_reward/mean": 0.1328125, "rewards/simpleverify_reward/std": 0.3407054841518402, "step": 204 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.53125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1745.09375, "completions/mean_terminated_length": 1401.800048828125, "completions/min_length": 873.0, "completions/min_terminated_length": 873.0, "epoch": 0.07274662881476224, "frac_reward_zero_std": 0.5, "grad_norm": 0.3135543763637543, "learning_rate": 8.98e-07, "loss": -0.0024, "num_tokens": 53994841.0, "reward": 0.421875, "reward_std": 0.21542152762413025, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 205 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1848.0, "completions/mean_length": 1768.78125, "completions/mean_terminated_length": 1347.2156982421875, "completions/min_length": 637.0, "completions/min_terminated_length": 637.0, "epoch": 0.07310149041873669, "frac_reward_zero_std": 0.4375, "grad_norm": 0.33511820435523987, "learning_rate": 8.974999999999999e-07, "loss": 0.0252, "num_tokens": 54228853.0, "reward": 0.359375, "reward_std": 0.2569572329521179, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 206 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.765625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2012.0, "completions/mean_length": 1919.9296875, "completions/mean_terminated_length": 1501.5667724609375, "completions/min_length": 980.0, "completions/min_terminated_length": 980.0, "epoch": 0.07345635202271114, "frac_reward_zero_std": 0.625, "grad_norm": 0.27520033717155457, "learning_rate": 8.969999999999999e-07, "loss": 0.0066, "num_tokens": 54486028.0, "reward": 0.2265625, "reward_std": 0.17700621485710144, "rewards/simpleverify_reward/mean": 0.2265625, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 207 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.703125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1999.0, "completions/mean_length": 1774.5859375, "completions/mean_terminated_length": 1127.0263671875, "completions/min_length": 464.0, "completions/min_terminated_length": 464.0, "epoch": 0.07381121362668559, "frac_reward_zero_std": 0.8125, "grad_norm": 0.2688887417316437, "learning_rate": 8.964999999999999e-07, "loss": 0.0018, "num_tokens": 54723343.0, "reward": 0.1875, "reward_std": 0.08337578922510147, "rewards/simpleverify_reward/mean": 0.1875, "rewards/simpleverify_reward/std": 0.39184603095054626, "step": 208 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5703125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1975.0, "completions/mean_length": 1791.7109375, "completions/mean_terminated_length": 1451.54541015625, "completions/min_length": 963.0, "completions/min_terminated_length": 963.0, "epoch": 0.07416607523066004, "frac_reward_zero_std": 0.625, "grad_norm": 0.307596355676651, "learning_rate": 8.96e-07, "loss": 0.0119, "num_tokens": 54966458.0, "reward": 0.390625, "reward_std": 0.1462521106004715, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 209 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1860.65625, "completions/mean_terminated_length": 1321.3333740234375, "completions/min_length": 468.0, "completions/min_terminated_length": 468.0, "epoch": 0.0745209368346345, "frac_reward_zero_std": 0.75, "grad_norm": 0.2759498357772827, "learning_rate": 8.954999999999999e-07, "loss": -0.0045, "num_tokens": 55215622.0, "reward": 0.234375, "reward_std": 0.11678344011306763, "rewards/simpleverify_reward/mean": 0.234375, "rewards/simpleverify_reward/std": 0.42527204751968384, "step": 210 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1929.0, "completions/mean_length": 1781.5, "completions/mean_terminated_length": 1173.3333740234375, "completions/min_length": 739.0, "completions/min_terminated_length": 739.0, "epoch": 0.07487579843860895, "frac_reward_zero_std": 0.6875, "grad_norm": 0.29184937477111816, "learning_rate": 8.95e-07, "loss": 0.0152, "num_tokens": 55453598.0, "reward": 0.2265625, "reward_std": 0.1412346363067627, "rewards/simpleverify_reward/mean": 0.2265625, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 211 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1912.9765625, "completions/mean_terminated_length": 1452.034423828125, "completions/min_length": 791.0, "completions/min_terminated_length": 791.0, "epoch": 0.07523066004258339, "frac_reward_zero_std": 0.6875, "grad_norm": 0.24279329180717468, "learning_rate": 8.945e-07, "loss": 0.0022, "num_tokens": 55709291.0, "reward": 0.2265625, "reward_std": 0.12073516845703125, "rewards/simpleverify_reward/mean": 0.2265625, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 212 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.703125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1891.7421875, "completions/mean_terminated_length": 1521.657958984375, "completions/min_length": 809.0, "completions/min_terminated_length": 809.0, "epoch": 0.07558552164655784, "frac_reward_zero_std": 0.5625, "grad_norm": 0.326217383146286, "learning_rate": 8.939999999999999e-07, "loss": 0.0025, "num_tokens": 55963770.0, "reward": 0.21875, "reward_std": 0.20463499426841736, "rewards/simpleverify_reward/mean": 0.21875, "rewards/simpleverify_reward/std": 0.41502299904823303, "step": 213 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1996.0, "completions/mean_length": 1718.453125, "completions/mean_terminated_length": 1399.046142578125, "completions/min_length": 914.0, "completions/min_terminated_length": 914.0, "epoch": 0.07594038325053229, "frac_reward_zero_std": 0.5, "grad_norm": 0.316698282957077, "learning_rate": 8.934999999999999e-07, "loss": 0.0116, "num_tokens": 56194860.0, "reward": 0.359375, "reward_std": 0.2359209954738617, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 214 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.765625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1803.140625, "completions/mean_terminated_length": 1003.2667236328125, "completions/min_length": 574.0, "completions/min_terminated_length": 574.0, "epoch": 0.07629524485450674, "frac_reward_zero_std": 0.625, "grad_norm": 0.278921514749527, "learning_rate": 8.93e-07, "loss": 0.006, "num_tokens": 56435214.0, "reward": 0.09375, "reward_std": 0.1462521106004715, "rewards/simpleverify_reward/mean": 0.09375, "rewards/simpleverify_reward/std": 0.29262590408325195, "step": 215 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1980.0, "completions/mean_length": 1938.546875, "completions/mean_terminated_length": 1464.25, "completions/min_length": 849.0, "completions/min_terminated_length": 849.0, "epoch": 0.0766501064584812, "frac_reward_zero_std": 0.8125, "grad_norm": 0.18918476998806, "learning_rate": 8.924999999999999e-07, "loss": 0.0043, "num_tokens": 56695804.0, "reward": 0.15625, "reward_std": 0.09127141535282135, "rewards/simpleverify_reward/mean": 0.15625, "rewards/simpleverify_reward/std": 0.3645188808441162, "step": 216 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2005.0, "completions/mean_length": 1952.3046875, "completions/mean_terminated_length": 1327.4705810546875, "completions/min_length": 660.0, "completions/min_terminated_length": 660.0, "epoch": 0.07700496806245564, "frac_reward_zero_std": 0.6875, "grad_norm": 0.2406197190284729, "learning_rate": 8.92e-07, "loss": 0.006, "num_tokens": 56956387.0, "reward": 0.140625, "reward_std": 0.12756995856761932, "rewards/simpleverify_reward/mean": 0.140625, "rewards/simpleverify_reward/std": 0.3490002751350403, "step": 217 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1900.7421875, "completions/mean_terminated_length": 1476.8182373046875, "completions/min_length": 937.0, "completions/min_terminated_length": 937.0, "epoch": 0.0773598296664301, "frac_reward_zero_std": 0.75, "grad_norm": 0.21085521578788757, "learning_rate": 8.915e-07, "loss": 0.0084, "num_tokens": 57211706.0, "reward": 0.234375, "reward_std": 0.11678344011306763, "rewards/simpleverify_reward/mean": 0.234375, "rewards/simpleverify_reward/std": 0.42527204751968384, "step": 218 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.765625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2009.0, "completions/mean_length": 1923.3984375, "completions/mean_terminated_length": 1516.36669921875, "completions/min_length": 691.0, "completions/min_terminated_length": 691.0, "epoch": 0.07771469127040455, "frac_reward_zero_std": 0.5, "grad_norm": 0.35193341970443726, "learning_rate": 8.91e-07, "loss": 0.0019, "num_tokens": 57470149.0, "reward": 0.1640625, "reward_std": 0.21542641520500183, "rewards/simpleverify_reward/mean": 0.1640625, "rewards/simpleverify_reward/std": 0.371787428855896, "step": 219 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1916.0, "completions/mean_length": 1921.765625, "completions/mean_terminated_length": 1449.5555419921875, "completions/min_length": 793.0, "completions/min_terminated_length": 793.0, "epoch": 0.07806955287437899, "frac_reward_zero_std": 0.625, "grad_norm": 0.27400675415992737, "learning_rate": 8.904999999999999e-07, "loss": 0.0132, "num_tokens": 57727383.0, "reward": 0.1875, "reward_std": 0.16097761690616608, "rewards/simpleverify_reward/mean": 0.1875, "rewards/simpleverify_reward/std": 0.39184603095054626, "step": 220 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1869.0390625, "completions/mean_terminated_length": 1489.2926025390625, "completions/min_length": 702.0, "completions/min_terminated_length": 702.0, "epoch": 0.07842441447835344, "frac_reward_zero_std": 0.6875, "grad_norm": 0.2413613349199295, "learning_rate": 8.9e-07, "loss": 0.0127, "num_tokens": 57977620.0, "reward": 0.2578125, "reward_std": 0.14913025498390198, "rewards/simpleverify_reward/mean": 0.2578125, "rewards/simpleverify_reward/std": 0.43914902210235596, "step": 221 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.71875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1954.9140625, "completions/mean_terminated_length": 1717.02783203125, "completions/min_length": 1258.0, "completions/min_terminated_length": 1258.0, "epoch": 0.07877927608232789, "frac_reward_zero_std": 0.5625, "grad_norm": 0.2796337604522705, "learning_rate": 8.894999999999999e-07, "loss": 0.0123, "num_tokens": 58239001.0, "reward": 0.234375, "reward_std": 0.19226360321044922, "rewards/simpleverify_reward/mean": 0.234375, "rewards/simpleverify_reward/std": 0.42527204751968384, "step": 222 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1740.9765625, "completions/mean_terminated_length": 1245.9796142578125, "completions/min_length": 823.0, "completions/min_terminated_length": 823.0, "epoch": 0.07913413768630234, "frac_reward_zero_std": 0.4375, "grad_norm": 0.4209553301334381, "learning_rate": 8.89e-07, "loss": 0.0009, "num_tokens": 58472254.0, "reward": 0.265625, "reward_std": 0.26827272772789, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 223 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1865.796875, "completions/mean_terminated_length": 1505.6279296875, "completions/min_length": 525.0, "completions/min_terminated_length": 525.0, "epoch": 0.0794889992902768, "frac_reward_zero_std": 0.6875, "grad_norm": 0.27262482047080994, "learning_rate": 8.884999999999999e-07, "loss": -0.0037, "num_tokens": 58721692.0, "reward": 0.2578125, "reward_std": 0.14913025498390198, "rewards/simpleverify_reward/mean": 0.2578125, "rewards/simpleverify_reward/std": 0.43914902210235596, "step": 224 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1955.0, "completions/mean_length": 1732.0546875, "completions/mean_terminated_length": 1205.479248046875, "completions/min_length": 107.0, "completions/min_terminated_length": 107.0, "epoch": 0.07984386089425125, "frac_reward_zero_std": 0.6875, "grad_norm": 0.25603750348091125, "learning_rate": 8.88e-07, "loss": 0.0199, "num_tokens": 58960067.0, "reward": 0.21875, "reward_std": 0.1354655921459198, "rewards/simpleverify_reward/mean": 0.21875, "rewards/simpleverify_reward/std": 0.41502299904823303, "step": 225 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1847.7890625, "completions/mean_terminated_length": 1294.2647705078125, "completions/min_length": 686.0, "completions/min_terminated_length": 686.0, "epoch": 0.0801987224982257, "frac_reward_zero_std": 0.875, "grad_norm": 0.18311823904514313, "learning_rate": 8.874999999999999e-07, "loss": 0.0108, "num_tokens": 59206992.0, "reward": 0.265625, "reward_std": 0.05444391071796417, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 226 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1908.4609375, "completions/mean_terminated_length": 1432.1033935546875, "completions/min_length": 817.0, "completions/min_terminated_length": 817.0, "epoch": 0.08055358410220015, "frac_reward_zero_std": 0.625, "grad_norm": 0.26252424716949463, "learning_rate": 8.869999999999999e-07, "loss": 0.0172, "num_tokens": 59463955.0, "reward": 0.1953125, "reward_std": 0.15308690071105957, "rewards/simpleverify_reward/mean": 0.1953125, "rewards/simpleverify_reward/std": 0.3979988098144531, "step": 227 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.78125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1926.3984375, "completions/mean_terminated_length": 1492.107177734375, "completions/min_length": 783.0, "completions/min_terminated_length": 783.0, "epoch": 0.08090844570617459, "frac_reward_zero_std": 0.5625, "grad_norm": 0.30648136138916016, "learning_rate": 8.864999999999999e-07, "loss": 0.0088, "num_tokens": 59720262.0, "reward": 0.1640625, "reward_std": 0.16834919154644012, "rewards/simpleverify_reward/mean": 0.1640625, "rewards/simpleverify_reward/std": 0.371787428855896, "step": 228 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1796.4921875, "completions/mean_terminated_length": 1440.5849609375, "completions/min_length": 692.0, "completions/min_terminated_length": 692.0, "epoch": 0.08126330731014904, "frac_reward_zero_std": 0.5, "grad_norm": 0.29749175906181335, "learning_rate": 8.86e-07, "loss": 0.0118, "num_tokens": 59959693.0, "reward": 0.2734375, "reward_std": 0.2288537621498108, "rewards/simpleverify_reward/mean": 0.2734375, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 229 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1855.6328125, "completions/mean_terminated_length": 1535.0208740234375, "completions/min_length": 1056.0, "completions/min_terminated_length": 1056.0, "epoch": 0.08161816891412349, "frac_reward_zero_std": 0.6875, "grad_norm": 0.23472841084003448, "learning_rate": 8.854999999999999e-07, "loss": 0.0046, "num_tokens": 60210038.0, "reward": 0.328125, "reward_std": 0.14123955368995667, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 230 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1635.2734375, "completions/mean_terminated_length": 1152.59326171875, "completions/min_length": 655.0, "completions/min_terminated_length": 655.0, "epoch": 0.08197303051809794, "frac_reward_zero_std": 0.6875, "grad_norm": 0.26652026176452637, "learning_rate": 8.85e-07, "loss": 0.0034, "num_tokens": 60428841.0, "reward": 0.3359375, "reward_std": 0.13888053596019745, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 231 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1750.0703125, "completions/mean_terminated_length": 1253.5208740234375, "completions/min_length": 440.0, "completions/min_terminated_length": 440.0, "epoch": 0.0823278921220724, "frac_reward_zero_std": 0.6875, "grad_norm": 0.2430071234703064, "learning_rate": 8.845e-07, "loss": 0.0006, "num_tokens": 60664322.0, "reward": 0.3046875, "reward_std": 0.13888052105903625, "rewards/simpleverify_reward/mean": 0.3046875, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 232 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.765625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1933.734375, "completions/mean_terminated_length": 1560.466796875, "completions/min_length": 813.0, "completions/min_terminated_length": 813.0, "epoch": 0.08268275372604685, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3426039218902588, "learning_rate": 8.839999999999999e-07, "loss": 0.0011, "num_tokens": 60921840.0, "reward": 0.171875, "reward_std": 0.18861129879951477, "rewards/simpleverify_reward/mean": 0.171875, "rewards/simpleverify_reward/std": 0.3787541687488556, "step": 233 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2015.0, "completions/mean_length": 1880.8515625, "completions/mean_terminated_length": 1513.125, "completions/min_length": 797.0, "completions/min_terminated_length": 797.0, "epoch": 0.0830376153300213, "frac_reward_zero_std": 0.6875, "grad_norm": 0.26999470591545105, "learning_rate": 8.834999999999999e-07, "loss": 0.009, "num_tokens": 61173349.0, "reward": 0.28125, "reward_std": 0.1604408323764801, "rewards/simpleverify_reward/mean": 0.28125, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 234 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1855.3203125, "completions/mean_terminated_length": 1460.7857666015625, "completions/min_length": 604.0, "completions/min_terminated_length": 604.0, "epoch": 0.08339247693399574, "frac_reward_zero_std": 0.625, "grad_norm": 0.3119662404060364, "learning_rate": 8.83e-07, "loss": 0.004, "num_tokens": 61419734.0, "reward": 0.2109375, "reward_std": 0.172288179397583, "rewards/simpleverify_reward/mean": 0.2109375, "rewards/simpleverify_reward/std": 0.4095771610736847, "step": 235 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1891.890625, "completions/mean_terminated_length": 1548.4500732421875, "completions/min_length": 1120.0, "completions/min_terminated_length": 1120.0, "epoch": 0.08374733853797019, "frac_reward_zero_std": 0.6875, "grad_norm": 0.25925731658935547, "learning_rate": 8.824999999999999e-07, "loss": -0.0004, "num_tokens": 61672968.0, "reward": 0.2578125, "reward_std": 0.12415501475334167, "rewards/simpleverify_reward/mean": 0.2578125, "rewards/simpleverify_reward/std": 0.43914902210235596, "step": 236 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1944.0, "completions/mean_length": 1829.4609375, "completions/mean_terminated_length": 1291.9730224609375, "completions/min_length": 536.0, "completions/min_terminated_length": 536.0, "epoch": 0.08410220014194464, "frac_reward_zero_std": 0.5, "grad_norm": 0.3176504373550415, "learning_rate": 8.82e-07, "loss": 0.015, "num_tokens": 61917043.0, "reward": 0.1875, "reward_std": 0.22567126154899597, "rewards/simpleverify_reward/mean": 0.1875, "rewards/simpleverify_reward/std": 0.39184603095054626, "step": 237 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1640.1171875, "completions/mean_terminated_length": 1244.78466796875, "completions/min_length": 485.0, "completions/min_terminated_length": 485.0, "epoch": 0.08445706174591909, "frac_reward_zero_std": 0.4375, "grad_norm": 0.3944616913795471, "learning_rate": 8.814999999999999e-07, "loss": 0.0135, "num_tokens": 62139818.0, "reward": 0.390625, "reward_std": 0.2522490322589874, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 238 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1994.0, "completions/mean_length": 1852.0625, "completions/mean_terminated_length": 1370.1622314453125, "completions/min_length": 807.0, "completions/min_terminated_length": 807.0, "epoch": 0.08481192334989354, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3631586730480194, "learning_rate": 8.81e-07, "loss": 0.0039, "num_tokens": 62386122.0, "reward": 0.2265625, "reward_std": 0.2080499529838562, "rewards/simpleverify_reward/mean": 0.2265625, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 239 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1990.71875, "completions/mean_terminated_length": 1698.857177734375, "completions/min_length": 1156.0, "completions/min_terminated_length": 1156.0, "epoch": 0.085166784953868, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3029223084449768, "learning_rate": 8.804999999999999e-07, "loss": 0.0062, "num_tokens": 62653878.0, "reward": 0.125, "reward_std": 0.18990950286388397, "rewards/simpleverify_reward/mean": 0.125, "rewards/simpleverify_reward/std": 0.3320184051990509, "step": 240 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.703125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2020.0, "completions/mean_length": 1793.28125, "completions/mean_terminated_length": 1190.0, "completions/min_length": 491.0, "completions/min_terminated_length": 491.0, "epoch": 0.08552164655784245, "frac_reward_zero_std": 0.6875, "grad_norm": 0.2498152256011963, "learning_rate": 8.799999999999999e-07, "loss": 0.014, "num_tokens": 62894002.0, "reward": 0.28125, "reward_std": 0.13098981976509094, "rewards/simpleverify_reward/mean": 0.28125, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 241 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1776.4921875, "completions/mean_terminated_length": 1179.175048828125, "completions/min_length": 432.0, "completions/min_terminated_length": 432.0, "epoch": 0.0858765081618169, "frac_reward_zero_std": 0.5, "grad_norm": 0.37262967228889465, "learning_rate": 8.794999999999999e-07, "loss": 0.0274, "num_tokens": 63131361.0, "reward": 0.25, "reward_std": 0.22119548916816711, "rewards/simpleverify_reward/mean": 0.25, "rewards/simpleverify_reward/std": 0.434714138507843, "step": 242 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1647.2421875, "completions/mean_terminated_length": 1270.772705078125, "completions/min_length": 491.0, "completions/min_terminated_length": 491.0, "epoch": 0.08623136976579134, "frac_reward_zero_std": 0.375, "grad_norm": 0.4241889715194702, "learning_rate": 8.79e-07, "loss": 0.0173, "num_tokens": 63352192.0, "reward": 0.4453125, "reward_std": 0.2664504945278168, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 243 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.703125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1836.984375, "completions/mean_terminated_length": 1337.2105712890625, "completions/min_length": 877.0, "completions/min_terminated_length": 877.0, "epoch": 0.08658623136976579, "frac_reward_zero_std": 0.6875, "grad_norm": 0.25614264607429504, "learning_rate": 8.784999999999999e-07, "loss": -0.0001, "num_tokens": 63598622.0, "reward": 0.1796875, "reward_std": 0.13888052105903625, "rewards/simpleverify_reward/mean": 0.1796875, "rewards/simpleverify_reward/std": 0.3854354918003082, "step": 244 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4765625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2014.0, "completions/mean_length": 1662.3125, "completions/mean_terminated_length": 1311.1641845703125, "completions/min_length": 634.0, "completions/min_terminated_length": 634.0, "epoch": 0.08694109297374024, "frac_reward_zero_std": 0.3125, "grad_norm": 0.4223305284976959, "learning_rate": 8.78e-07, "loss": 0.0123, "num_tokens": 63824342.0, "reward": 0.4296875, "reward_std": 0.3148258924484253, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 245 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1848.6328125, "completions/mean_terminated_length": 1393.6666259765625, "completions/min_length": 812.0, "completions/min_terminated_length": 812.0, "epoch": 0.08729595457771469, "frac_reward_zero_std": 0.75, "grad_norm": 0.23571975529193878, "learning_rate": 8.774999999999999e-07, "loss": 0.0107, "num_tokens": 64076135.0, "reward": 0.1796875, "reward_std": 0.10994865000247955, "rewards/simpleverify_reward/mean": 0.1796875, "rewards/simpleverify_reward/std": 0.3854354918003082, "step": 246 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.546875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2023.0, "completions/mean_length": 1672.6640625, "completions/mean_terminated_length": 1219.67236328125, "completions/min_length": 402.0, "completions/min_terminated_length": 402.0, "epoch": 0.08765081618168914, "frac_reward_zero_std": 0.4375, "grad_norm": 0.36376047134399414, "learning_rate": 8.769999999999999e-07, "loss": 0.0297, "num_tokens": 64302116.0, "reward": 0.328125, "reward_std": 0.25460314750671387, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 247 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1992.0, "completions/mean_length": 1608.921875, "completions/mean_terminated_length": 1245.1142578125, "completions/min_length": 617.0, "completions/min_terminated_length": 617.0, "epoch": 0.0880056777856636, "frac_reward_zero_std": 0.4375, "grad_norm": 0.41628313064575195, "learning_rate": 8.764999999999999e-07, "loss": 0.0283, "num_tokens": 64517378.0, "reward": 0.3671875, "reward_std": 0.2569621503353119, "rewards/simpleverify_reward/mean": 0.3671875, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 248 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.75, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1929.8671875, "completions/mean_terminated_length": 1575.46875, "completions/min_length": 778.0, "completions/min_terminated_length": 778.0, "epoch": 0.08836053938963805, "frac_reward_zero_std": 0.5625, "grad_norm": 0.33727893233299255, "learning_rate": 8.76e-07, "loss": 0.0132, "num_tokens": 64775897.0, "reward": 0.1796875, "reward_std": 0.20569583773612976, "rewards/simpleverify_reward/mean": 0.1796875, "rewards/simpleverify_reward/std": 0.3854354918003082, "step": 249 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1777.9296875, "completions/mean_terminated_length": 1370.176513671875, "completions/min_length": 654.0, "completions/min_terminated_length": 654.0, "epoch": 0.0887154009936125, "frac_reward_zero_std": 0.5, "grad_norm": 0.3391297459602356, "learning_rate": 8.754999999999999e-07, "loss": 0.0093, "num_tokens": 65014112.0, "reward": 0.265625, "reward_std": 0.21884137392044067, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 250 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.65625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1815.0078125, "completions/mean_terminated_length": 1370.20458984375, "completions/min_length": 515.0, "completions/min_terminated_length": 515.0, "epoch": 0.08907026259758694, "frac_reward_zero_std": 0.5, "grad_norm": 0.3305000960826874, "learning_rate": 8.75e-07, "loss": 0.0243, "num_tokens": 65256937.0, "reward": 0.234375, "reward_std": 0.22567124664783478, "rewards/simpleverify_reward/mean": 0.234375, "rewards/simpleverify_reward/std": 0.42527204751968384, "step": 251 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4765625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1676.3828125, "completions/mean_terminated_length": 1338.0447998046875, "completions/min_length": 699.0, "completions/min_terminated_length": 699.0, "epoch": 0.08942512420156139, "frac_reward_zero_std": 0.5, "grad_norm": 0.3274216055870056, "learning_rate": 8.745000000000001e-07, "loss": -0.0029, "num_tokens": 65481786.0, "reward": 0.3671875, "reward_std": 0.24145761132240295, "rewards/simpleverify_reward/mean": 0.3671875, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 252 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1823.7421875, "completions/mean_terminated_length": 1423.978271484375, "completions/min_length": 619.0, "completions/min_terminated_length": 619.0, "epoch": 0.08977998580553584, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3100050389766693, "learning_rate": 8.739999999999999e-07, "loss": 0.0029, "num_tokens": 65728705.0, "reward": 0.203125, "reward_std": 0.18543373048305511, "rewards/simpleverify_reward/mean": 0.203125, "rewards/simpleverify_reward/std": 0.40390563011169434, "step": 253 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1996.0, "completions/mean_length": 1532.21875, "completions/mean_terminated_length": 1167.7333984375, "completions/min_length": 559.0, "completions/min_terminated_length": 559.0, "epoch": 0.09013484740951029, "frac_reward_zero_std": 0.4375, "grad_norm": 0.4018900394439697, "learning_rate": 8.735e-07, "loss": 0.0064, "num_tokens": 65938437.0, "reward": 0.328125, "reward_std": 0.2567248046398163, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 254 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2019.0, "completions/mean_length": 1748.375, "completions/mean_terminated_length": 1363.1429443359375, "completions/min_length": 396.0, "completions/min_terminated_length": 396.0, "epoch": 0.09048970901348474, "frac_reward_zero_std": 0.4375, "grad_norm": 0.3234691023826599, "learning_rate": 8.729999999999999e-07, "loss": 0.0308, "num_tokens": 66172485.0, "reward": 0.375, "reward_std": 0.250127375125885, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 255 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1886.0, "completions/mean_length": 1656.3359375, "completions/mean_terminated_length": 1119.611083984375, "completions/min_length": 492.0, "completions/min_terminated_length": 492.0, "epoch": 0.0908445706174592, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3458096981048584, "learning_rate": 8.725e-07, "loss": 0.002, "num_tokens": 66395776.0, "reward": 0.2890625, "reward_std": 0.20251823961734772, "rewards/simpleverify_reward/mean": 0.2890625, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 256 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2015.0, "completions/mean_length": 1900.5859375, "completions/mean_terminated_length": 1397.3448486328125, "completions/min_length": 730.0, "completions/min_terminated_length": 730.0, "epoch": 0.09119943222143365, "frac_reward_zero_std": 0.6875, "grad_norm": 0.2679227292537689, "learning_rate": 8.72e-07, "loss": -0.0073, "num_tokens": 66652739.0, "reward": 0.1328125, "reward_std": 0.12863080203533173, "rewards/simpleverify_reward/mean": 0.1328125, "rewards/simpleverify_reward/std": 0.3407054841518402, "step": 257 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.546875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1965.0, "completions/mean_length": 1652.0703125, "completions/mean_terminated_length": 1174.22412109375, "completions/min_length": 512.0, "completions/min_terminated_length": 512.0, "epoch": 0.09155429382540808, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3826090395450592, "learning_rate": 8.715e-07, "loss": -0.0, "num_tokens": 66876068.0, "reward": 0.2890625, "reward_std": 0.2012200653553009, "rewards/simpleverify_reward/mean": 0.2890625, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 258 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1753.328125, "completions/mean_terminated_length": 1501.3623046875, "completions/min_length": 976.0, "completions/min_terminated_length": 976.0, "epoch": 0.09190915542938254, "frac_reward_zero_std": 0.5, "grad_norm": 0.3702980577945709, "learning_rate": 8.71e-07, "loss": 0.0209, "num_tokens": 67111334.0, "reward": 0.4453125, "reward_std": 0.21778054535388947, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 259 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1727.53125, "completions/mean_terminated_length": 1315.5, "completions/min_length": 527.0, "completions/min_terminated_length": 527.0, "epoch": 0.09226401703335699, "frac_reward_zero_std": 0.3125, "grad_norm": 0.4095343053340912, "learning_rate": 8.705e-07, "loss": 0.0323, "num_tokens": 67343698.0, "reward": 0.2890625, "reward_std": 0.3385029733181, "rewards/simpleverify_reward/mean": 0.2890625, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 260 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1572.0546875, "completions/mean_terminated_length": 1276.84814453125, "completions/min_length": 388.0, "completions/min_terminated_length": 388.0, "epoch": 0.09261887863733144, "frac_reward_zero_std": 0.375, "grad_norm": 0.44901567697525024, "learning_rate": 8.699999999999999e-07, "loss": -0.0197, "num_tokens": 67553945.0, "reward": 0.359375, "reward_std": 0.3027362823486328, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 261 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1799.8828125, "completions/mean_terminated_length": 1425.2745361328125, "completions/min_length": 758.0, "completions/min_terminated_length": 758.0, "epoch": 0.09297374024130589, "frac_reward_zero_std": 0.5, "grad_norm": 0.35093817114830017, "learning_rate": 8.695e-07, "loss": 0.0284, "num_tokens": 67795226.0, "reward": 0.21875, "reward_std": 0.2290911078453064, "rewards/simpleverify_reward/mean": 0.21875, "rewards/simpleverify_reward/std": 0.41502299904823303, "step": 262 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2000.0, "completions/mean_length": 1721.5703125, "completions/mean_terminated_length": 1301.875, "completions/min_length": 537.0, "completions/min_terminated_length": 537.0, "epoch": 0.09332860184528034, "frac_reward_zero_std": 0.5, "grad_norm": 0.3443338871002197, "learning_rate": 8.69e-07, "loss": 0.0107, "num_tokens": 68025875.0, "reward": 0.375, "reward_std": 0.21542152762413025, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 263 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1783.5234375, "completions/mean_terminated_length": 1201.675048828125, "completions/min_length": 569.0, "completions/min_terminated_length": 569.0, "epoch": 0.0936834634492548, "frac_reward_zero_std": 0.625, "grad_norm": 0.31576135754585266, "learning_rate": 8.685e-07, "loss": 0.0085, "num_tokens": 68267558.0, "reward": 0.1796875, "reward_std": 0.1633366346359253, "rewards/simpleverify_reward/mean": 0.1796875, "rewards/simpleverify_reward/std": 0.3854354918003082, "step": 264 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1984.0, "completions/mean_length": 1825.9296875, "completions/mean_terminated_length": 1186.6363525390625, "completions/min_length": 522.0, "completions/min_terminated_length": 522.0, "epoch": 0.09403832505322925, "frac_reward_zero_std": 0.5, "grad_norm": 0.35720208287239075, "learning_rate": 8.68e-07, "loss": 0.0023, "num_tokens": 68512277.0, "reward": 0.1875, "reward_std": 0.21542152762413025, "rewards/simpleverify_reward/mean": 0.1875, "rewards/simpleverify_reward/std": 0.39184603095054626, "step": 265 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5546875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1687.9140625, "completions/mean_terminated_length": 1239.385986328125, "completions/min_length": 252.0, "completions/min_terminated_length": 252.0, "epoch": 0.09439318665720368, "frac_reward_zero_std": 0.4375, "grad_norm": 0.4161880314350128, "learning_rate": 8.675000000000001e-07, "loss": 0.013, "num_tokens": 68742666.0, "reward": 0.234375, "reward_std": 0.230683833360672, "rewards/simpleverify_reward/mean": 0.234375, "rewards/simpleverify_reward/std": 0.42527204751968384, "step": 266 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2009.0, "completions/mean_length": 1799.125, "completions/mean_terminated_length": 1458.0740966796875, "completions/min_length": 569.0, "completions/min_terminated_length": 569.0, "epoch": 0.09474804826117814, "frac_reward_zero_std": 0.625, "grad_norm": 0.32704517245292664, "learning_rate": 8.669999999999999e-07, "loss": -0.0055, "num_tokens": 68986202.0, "reward": 0.2421875, "reward_std": 0.18595777451992035, "rewards/simpleverify_reward/mean": 0.2421875, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 267 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1921.0, "completions/mean_length": 1754.4453125, "completions/mean_terminated_length": 1281.1632080078125, "completions/min_length": 524.0, "completions/min_terminated_length": 524.0, "epoch": 0.09510290986515259, "frac_reward_zero_std": 0.625, "grad_norm": 0.2826489806175232, "learning_rate": 8.665e-07, "loss": 0.0047, "num_tokens": 69224163.0, "reward": 0.28125, "reward_std": 0.16545338928699493, "rewards/simpleverify_reward/mean": 0.28125, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 268 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1868.2421875, "completions/mean_terminated_length": 1547.8043212890625, "completions/min_length": 870.0, "completions/min_terminated_length": 870.0, "epoch": 0.09545777146912704, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3244038224220276, "learning_rate": 8.659999999999999e-07, "loss": 0.0171, "num_tokens": 69475866.0, "reward": 0.203125, "reward_std": 0.20357908308506012, "rewards/simpleverify_reward/mean": 0.203125, "rewards/simpleverify_reward/std": 0.40390563011169434, "step": 269 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1630.0390625, "completions/mean_terminated_length": 1237.4091796875, "completions/min_length": 600.0, "completions/min_terminated_length": 600.0, "epoch": 0.09581263307310149, "frac_reward_zero_std": 0.375, "grad_norm": 0.42587682604789734, "learning_rate": 8.655e-07, "loss": -0.0039, "num_tokens": 69698407.0, "reward": 0.375, "reward_std": 0.27328526973724365, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 270 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1858.0, "completions/mean_length": 1886.1015625, "completions/mean_terminated_length": 1106.0455322265625, "completions/min_length": 727.0, "completions/min_terminated_length": 727.0, "epoch": 0.09616749467707594, "frac_reward_zero_std": 0.75, "grad_norm": 0.25026461482048035, "learning_rate": 8.65e-07, "loss": 0.0148, "num_tokens": 69951092.0, "reward": 0.140625, "reward_std": 0.11678344756364822, "rewards/simpleverify_reward/mean": 0.140625, "rewards/simpleverify_reward/std": 0.3490002751350403, "step": 271 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1943.1171875, "completions/mean_terminated_length": 1641.181884765625, "completions/min_length": 1000.0, "completions/min_terminated_length": 1000.0, "epoch": 0.0965223562810504, "frac_reward_zero_std": 0.4375, "grad_norm": 0.3182675242424011, "learning_rate": 8.645e-07, "loss": 0.0078, "num_tokens": 70211395.0, "reward": 0.234375, "reward_std": 0.233047753572464, "rewards/simpleverify_reward/mean": 0.234375, "rewards/simpleverify_reward/std": 0.42527204751968384, "step": 272 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1806.2734375, "completions/mean_terminated_length": 1293.3414306640625, "completions/min_length": 498.0, "completions/min_terminated_length": 498.0, "epoch": 0.09687721788502485, "frac_reward_zero_std": 0.4375, "grad_norm": 0.3774825930595398, "learning_rate": 8.639999999999999e-07, "loss": -0.0013, "num_tokens": 70454526.0, "reward": 0.234375, "reward_std": 0.23410366475582123, "rewards/simpleverify_reward/mean": 0.234375, "rewards/simpleverify_reward/std": 0.42527204751968384, "step": 273 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1711.0, "completions/mean_length": 1840.1484375, "completions/mean_terminated_length": 1265.5, "completions/min_length": 970.0, "completions/min_terminated_length": 970.0, "epoch": 0.09723207948899928, "frac_reward_zero_std": 0.8125, "grad_norm": 0.24680854380130768, "learning_rate": 8.635e-07, "loss": 0.006, "num_tokens": 70704305.0, "reward": 0.171875, "reward_std": 0.08785156160593033, "rewards/simpleverify_reward/mean": 0.171875, "rewards/simpleverify_reward/std": 0.3787541687488556, "step": 274 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1845.5234375, "completions/mean_terminated_length": 1445.279052734375, "completions/min_length": 522.0, "completions/min_terminated_length": 522.0, "epoch": 0.09758694109297374, "frac_reward_zero_std": 0.625, "grad_norm": 0.2943173050880432, "learning_rate": 8.629999999999999e-07, "loss": 0.0102, "num_tokens": 70952596.0, "reward": 0.2421875, "reward_std": 0.17358636856079102, "rewards/simpleverify_reward/mean": 0.2421875, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 275 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1974.375, "completions/mean_terminated_length": 1685.53857421875, "completions/min_length": 1136.0, "completions/min_terminated_length": 1136.0, "epoch": 0.09794180269694819, "frac_reward_zero_std": 0.6875, "grad_norm": 0.21844615042209625, "learning_rate": 8.625e-07, "loss": 0.0058, "num_tokens": 71217804.0, "reward": 0.1953125, "reward_std": 0.14913025498390198, "rewards/simpleverify_reward/mean": 0.1953125, "rewards/simpleverify_reward/std": 0.3979988098144531, "step": 276 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1907.7578125, "completions/mean_terminated_length": 1267.521728515625, "completions/min_length": 750.0, "completions/min_terminated_length": 750.0, "epoch": 0.09829666430092264, "frac_reward_zero_std": 0.75, "grad_norm": 0.2231844961643219, "learning_rate": 8.62e-07, "loss": 0.0004, "num_tokens": 71472277.0, "reward": 0.109375, "reward_std": 0.09863808751106262, "rewards/simpleverify_reward/mean": 0.109375, "rewards/simpleverify_reward/std": 0.31333550810813904, "step": 277 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2022.0, "completions/mean_length": 1654.9375, "completions/mean_terminated_length": 1285.697021484375, "completions/min_length": 516.0, "completions/min_terminated_length": 516.0, "epoch": 0.09865152590489709, "frac_reward_zero_std": 0.4375, "grad_norm": 0.41331398487091064, "learning_rate": 8.615e-07, "loss": -0.0166, "num_tokens": 71697677.0, "reward": 0.1875, "reward_std": 0.2648528814315796, "rewards/simpleverify_reward/mean": 0.1875, "rewards/simpleverify_reward/std": 0.39184603095054626, "step": 278 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.46875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1616.8359375, "completions/mean_terminated_length": 1236.3970947265625, "completions/min_length": 34.0, "completions/min_terminated_length": 34.0, "epoch": 0.09900638750887154, "frac_reward_zero_std": 0.4375, "grad_norm": 0.4317677319049835, "learning_rate": 8.61e-07, "loss": 0.0058, "num_tokens": 71920096.0, "reward": 0.3515625, "reward_std": 0.23068872094154358, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 279 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1778.2578125, "completions/mean_terminated_length": 1462.796630859375, "completions/min_length": 999.0, "completions/min_terminated_length": 999.0, "epoch": 0.099361249112846, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3374361991882324, "learning_rate": 8.605e-07, "loss": 0.0267, "num_tokens": 72157609.0, "reward": 0.375, "reward_std": 0.19438526034355164, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 280 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1919.0390625, "completions/mean_terminated_length": 1547.7879638671875, "completions/min_length": 1015.0, "completions/min_terminated_length": 1015.0, "epoch": 0.09971611071682045, "frac_reward_zero_std": 0.625, "grad_norm": 0.2865069806575775, "learning_rate": 8.599999999999999e-07, "loss": 0.0238, "num_tokens": 72415670.0, "reward": 0.203125, "reward_std": 0.18383118510246277, "rewards/simpleverify_reward/mean": 0.203125, "rewards/simpleverify_reward/std": 0.40390563011169434, "step": 281 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2020.0, "completions/mean_length": 1865.015625, "completions/mean_terminated_length": 1292.4515380859375, "completions/min_length": 580.0, "completions/min_terminated_length": 580.0, "epoch": 0.10007097232079488, "frac_reward_zero_std": 0.625, "grad_norm": 0.31854158639907837, "learning_rate": 8.595e-07, "loss": -0.01, "num_tokens": 72665928.0, "reward": 0.140625, "reward_std": 0.15650184452533722, "rewards/simpleverify_reward/mean": 0.140625, "rewards/simpleverify_reward/std": 0.3490002751350403, "step": 282 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.53125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1641.2265625, "completions/mean_terminated_length": 1180.2166748046875, "completions/min_length": 417.0, "completions/min_terminated_length": 417.0, "epoch": 0.10042583392476934, "frac_reward_zero_std": 0.5625, "grad_norm": 0.34172025322914124, "learning_rate": 8.59e-07, "loss": 0.0108, "num_tokens": 72888037.0, "reward": 0.296875, "reward_std": 0.17623990774154663, "rewards/simpleverify_reward/mean": 0.296875, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 283 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.53125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1706.3046875, "completions/mean_terminated_length": 1319.050048828125, "completions/min_length": 477.0, "completions/min_terminated_length": 477.0, "epoch": 0.10078069552874379, "frac_reward_zero_std": 0.625, "grad_norm": 0.28643742203712463, "learning_rate": 8.585e-07, "loss": 0.0079, "num_tokens": 73117012.0, "reward": 0.3359375, "reward_std": 0.18253791332244873, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 284 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1977.0, "completions/mean_length": 1798.9375, "completions/mean_terminated_length": 1081.939453125, "completions/min_length": 557.0, "completions/min_terminated_length": 557.0, "epoch": 0.10113555713271824, "frac_reward_zero_std": 0.6875, "grad_norm": 0.24156221747398376, "learning_rate": 8.58e-07, "loss": 0.0043, "num_tokens": 73359996.0, "reward": 0.125, "reward_std": 0.13994136452674866, "rewards/simpleverify_reward/mean": 0.125, "rewards/simpleverify_reward/std": 0.3320184051990509, "step": 285 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1964.0, "completions/mean_length": 1657.2109375, "completions/mean_terminated_length": 1353.263916015625, "completions/min_length": 778.0, "completions/min_terminated_length": 778.0, "epoch": 0.10149041873669269, "frac_reward_zero_std": 0.625, "grad_norm": 0.282728374004364, "learning_rate": 8.575e-07, "loss": 0.0099, "num_tokens": 73582735.0, "reward": 0.3984375, "reward_std": 0.17806214094161987, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 286 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5546875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1969.0, "completions/mean_length": 1677.296875, "completions/mean_terminated_length": 1215.5438232421875, "completions/min_length": 570.0, "completions/min_terminated_length": 570.0, "epoch": 0.10184528034066714, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3453022837638855, "learning_rate": 8.569999999999999e-07, "loss": 0.0172, "num_tokens": 73806901.0, "reward": 0.25, "reward_std": 0.1841355413198471, "rewards/simpleverify_reward/mean": 0.25, "rewards/simpleverify_reward/std": 0.434714138507843, "step": 287 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2018.0, "completions/mean_length": 1482.1953125, "completions/mean_terminated_length": 1119.5, "completions/min_length": 432.0, "completions/min_terminated_length": 432.0, "epoch": 0.1022001419446416, "frac_reward_zero_std": 0.5625, "grad_norm": 0.35024091601371765, "learning_rate": 8.565e-07, "loss": -0.0063, "num_tokens": 74008326.0, "reward": 0.40625, "reward_std": 0.18648964166641235, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 288 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2021.0, "completions/mean_length": 1704.4140625, "completions/mean_terminated_length": 1327.03271484375, "completions/min_length": 489.0, "completions/min_terminated_length": 489.0, "epoch": 0.10255500354861603, "frac_reward_zero_std": 0.625, "grad_norm": 0.2877115309238434, "learning_rate": 8.559999999999999e-07, "loss": -0.0005, "num_tokens": 74237787.0, "reward": 0.3125, "reward_std": 0.1643974632024765, "rewards/simpleverify_reward/mean": 0.3125, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 289 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1631.3984375, "completions/mean_terminated_length": 1498.2576904296875, "completions/min_length": 725.0, "completions/min_terminated_length": 725.0, "epoch": 0.10290986515259049, "frac_reward_zero_std": 0.1875, "grad_norm": 0.5798021554946899, "learning_rate": 8.555e-07, "loss": 0.0259, "num_tokens": 74456510.0, "reward": 0.5859375, "reward_std": 0.36584997177124023, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 290 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1731.84375, "completions/mean_terminated_length": 1395.290283203125, "completions/min_length": 630.0, "completions/min_terminated_length": 630.0, "epoch": 0.10326472675656494, "frac_reward_zero_std": 0.375, "grad_norm": 0.38101959228515625, "learning_rate": 8.55e-07, "loss": -0.0132, "num_tokens": 74689202.0, "reward": 0.3515625, "reward_std": 0.282474160194397, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 291 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1672.8515625, "completions/mean_terminated_length": 1297.703125, "completions/min_length": 469.0, "completions/min_terminated_length": 469.0, "epoch": 0.10361958836053939, "frac_reward_zero_std": 0.375, "grad_norm": 0.42847225069999695, "learning_rate": 8.545e-07, "loss": 0.0236, "num_tokens": 74917039.0, "reward": 0.3828125, "reward_std": 0.2767002284526825, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 292 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1705.046875, "completions/mean_terminated_length": 1303.966064453125, "completions/min_length": 543.0, "completions/min_terminated_length": 543.0, "epoch": 0.10397444996451384, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3052312731742859, "learning_rate": 8.539999999999999e-07, "loss": 0.0072, "num_tokens": 75151165.0, "reward": 0.3359375, "reward_std": 0.18649455904960632, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 293 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1782.484375, "completions/mean_terminated_length": 1339.9583740234375, "completions/min_length": 339.0, "completions/min_terminated_length": 339.0, "epoch": 0.10432931156848829, "frac_reward_zero_std": 0.625, "grad_norm": 0.27749380469322205, "learning_rate": 8.535e-07, "loss": 0.0145, "num_tokens": 75392803.0, "reward": 0.265625, "reward_std": 0.1712273508310318, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 294 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1599.75, "completions/mean_terminated_length": 1417.4945068359375, "completions/min_length": 901.0, "completions/min_terminated_length": 901.0, "epoch": 0.10468417317246274, "frac_reward_zero_std": 0.5, "grad_norm": 0.3388848602771759, "learning_rate": 8.529999999999999e-07, "loss": 0.0027, "num_tokens": 75606155.0, "reward": 0.4296875, "reward_std": 0.22461043298244476, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 295 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1984.0, "completions/mean_length": 1921.625, "completions/mean_terminated_length": 1572.2353515625, "completions/min_length": 965.0, "completions/min_terminated_length": 965.0, "epoch": 0.1050390347764372, "frac_reward_zero_std": 0.5, "grad_norm": 0.31512829661369324, "learning_rate": 8.525e-07, "loss": 0.0037, "num_tokens": 75864979.0, "reward": 0.171875, "reward_std": 0.20859163999557495, "rewards/simpleverify_reward/mean": 0.171875, "rewards/simpleverify_reward/std": 0.3787541687488556, "step": 296 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1797.0546875, "completions/mean_terminated_length": 1392.4693603515625, "completions/min_length": 723.0, "completions/min_terminated_length": 723.0, "epoch": 0.10539389638041163, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3239031434059143, "learning_rate": 8.52e-07, "loss": -0.0042, "num_tokens": 76106330.0, "reward": 0.28125, "reward_std": 0.2001592218875885, "rewards/simpleverify_reward/mean": 0.28125, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 297 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2019.0, "completions/mean_length": 1515.1484375, "completions/mean_terminated_length": 1059.521728515625, "completions/min_length": 570.0, "completions/min_terminated_length": 570.0, "epoch": 0.10574875798438609, "frac_reward_zero_std": 0.5, "grad_norm": 0.3899322748184204, "learning_rate": 8.515e-07, "loss": -0.0029, "num_tokens": 76310469.0, "reward": 0.3828125, "reward_std": 0.20411096513271332, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 298 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5546875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2018.0, "completions/mean_length": 1710.8125, "completions/mean_terminated_length": 1290.8070068359375, "completions/min_length": 603.0, "completions/min_terminated_length": 603.0, "epoch": 0.10610361958836054, "frac_reward_zero_std": 0.375, "grad_norm": 0.3830328583717346, "learning_rate": 8.51e-07, "loss": -0.0028, "num_tokens": 76541429.0, "reward": 0.2421875, "reward_std": 0.2619746923446655, "rewards/simpleverify_reward/mean": 0.2421875, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 299 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.59375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1703.6328125, "completions/mean_terminated_length": 1200.3270263671875, "completions/min_length": 647.0, "completions/min_terminated_length": 647.0, "epoch": 0.10645848119233499, "frac_reward_zero_std": 0.4375, "grad_norm": 0.3598440885543823, "learning_rate": 8.504999999999999e-07, "loss": 0.0108, "num_tokens": 76771174.0, "reward": 0.28125, "reward_std": 0.2580229938030243, "rewards/simpleverify_reward/mean": 0.28125, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 300 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1951.0, "completions/mean_length": 1796.7734375, "completions/mean_terminated_length": 1263.682861328125, "completions/min_length": 452.0, "completions/min_terminated_length": 452.0, "epoch": 0.10681334279630944, "frac_reward_zero_std": 0.75, "grad_norm": 0.2310454547405243, "learning_rate": 8.499999999999999e-07, "loss": -0.0024, "num_tokens": 77015057.0, "reward": 0.2734375, "reward_std": 0.10994865000247955, "rewards/simpleverify_reward/mean": 0.2734375, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 301 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2010.0, "completions/mean_length": 1576.7421875, "completions/mean_terminated_length": 1090.52392578125, "completions/min_length": 55.0, "completions/min_terminated_length": 55.0, "epoch": 0.10716820440028389, "frac_reward_zero_std": 0.5, "grad_norm": 0.3604891300201416, "learning_rate": 8.495e-07, "loss": 0.0072, "num_tokens": 77228896.0, "reward": 0.2734375, "reward_std": 0.20411096513271332, "rewards/simpleverify_reward/mean": 0.2734375, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 302 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1877.1953125, "completions/mean_terminated_length": 1404.9705810546875, "completions/min_length": 917.0, "completions/min_terminated_length": 917.0, "epoch": 0.10752306600425834, "frac_reward_zero_std": 0.5, "grad_norm": 0.31112736463546753, "learning_rate": 8.489999999999999e-07, "loss": -0.0016, "num_tokens": 77479593.0, "reward": 0.171875, "reward_std": 0.21436560153961182, "rewards/simpleverify_reward/mean": 0.171875, "rewards/simpleverify_reward/std": 0.3787541687488556, "step": 303 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.546875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1635.0078125, "completions/mean_terminated_length": 1136.5689697265625, "completions/min_length": 601.0, "completions/min_terminated_length": 601.0, "epoch": 0.1078779276082328, "frac_reward_zero_std": 0.5625, "grad_norm": 0.399704247713089, "learning_rate": 8.485e-07, "loss": 0.0154, "num_tokens": 77698666.0, "reward": 0.3203125, "reward_std": 0.17282496392726898, "rewards/simpleverify_reward/mean": 0.3203125, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 304 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1942.0, "completions/mean_length": 1647.21875, "completions/mean_terminated_length": 1207.016357421875, "completions/min_length": 448.0, "completions/min_terminated_length": 448.0, "epoch": 0.10823278921220723, "frac_reward_zero_std": 0.5, "grad_norm": 0.32526618242263794, "learning_rate": 8.48e-07, "loss": 0.0098, "num_tokens": 77919942.0, "reward": 0.390625, "reward_std": 0.23356688022613525, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 305 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1977.0, "completions/mean_length": 1885.765625, "completions/mean_terminated_length": 1486.7568359375, "completions/min_length": 993.0, "completions/min_terminated_length": 993.0, "epoch": 0.10858765081618169, "frac_reward_zero_std": 0.6875, "grad_norm": 0.25484248995780945, "learning_rate": 8.475e-07, "loss": 0.0062, "num_tokens": 78176816.0, "reward": 0.265625, "reward_std": 0.1536109447479248, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 306 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.59375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1979.0, "completions/mean_length": 1689.2578125, "completions/mean_terminated_length": 1164.9423828125, "completions/min_length": 164.0, "completions/min_terminated_length": 164.0, "epoch": 0.10894251242015614, "frac_reward_zero_std": 0.5, "grad_norm": 0.33575284481048584, "learning_rate": 8.469999999999999e-07, "loss": 0.0345, "num_tokens": 78405057.0, "reward": 0.2734375, "reward_std": 0.2301519364118576, "rewards/simpleverify_reward/mean": 0.2734375, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 307 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2010.0, "completions/mean_length": 1806.1640625, "completions/mean_terminated_length": 1403.104248046875, "completions/min_length": 648.0, "completions/min_terminated_length": 648.0, "epoch": 0.10929737402413059, "frac_reward_zero_std": 0.5, "grad_norm": 0.42161011695861816, "learning_rate": 8.465e-07, "loss": 0.0093, "num_tokens": 78647742.0, "reward": 0.1875, "reward_std": 0.22461532056331635, "rewards/simpleverify_reward/mean": 0.1875, "rewards/simpleverify_reward/std": 0.39184603095054626, "step": 308 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1787.2578125, "completions/mean_terminated_length": 1418.2830810546875, "completions/min_length": 728.0, "completions/min_terminated_length": 728.0, "epoch": 0.10965223562810504, "frac_reward_zero_std": 0.5, "grad_norm": 0.3221695125102997, "learning_rate": 8.459999999999999e-07, "loss": 0.0032, "num_tokens": 78888951.0, "reward": 0.34375, "reward_std": 0.22567126154899597, "rewards/simpleverify_reward/mean": 0.34375, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 309 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1700.2890625, "completions/mean_terminated_length": 1330.1451416015625, "completions/min_length": 514.0, "completions/min_terminated_length": 514.0, "epoch": 0.11000709723207949, "frac_reward_zero_std": 0.375, "grad_norm": 0.40381288528442383, "learning_rate": 8.455e-07, "loss": 0.0196, "num_tokens": 79118564.0, "reward": 0.359375, "reward_std": 0.2869548797607422, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 310 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5703125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1803.75, "completions/mean_terminated_length": 1479.5635986328125, "completions/min_length": 785.0, "completions/min_terminated_length": 785.0, "epoch": 0.11036195883605394, "frac_reward_zero_std": 0.5625, "grad_norm": 0.346367746591568, "learning_rate": 8.45e-07, "loss": 0.0089, "num_tokens": 79368500.0, "reward": 0.265625, "reward_std": 0.21488472819328308, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 311 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2020.0, "completions/mean_length": 1752.734375, "completions/mean_terminated_length": 1466.5538330078125, "completions/min_length": 730.0, "completions/min_terminated_length": 730.0, "epoch": 0.11071682044002838, "frac_reward_zero_std": 0.3125, "grad_norm": 0.44547805190086365, "learning_rate": 8.445e-07, "loss": 0.0175, "num_tokens": 79606618.0, "reward": 0.3984375, "reward_std": 0.2964382767677307, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 312 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.59375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1651.59375, "completions/mean_terminated_length": 1072.2308349609375, "completions/min_length": 253.0, "completions/min_terminated_length": 253.0, "epoch": 0.11107168204400283, "frac_reward_zero_std": 0.75, "grad_norm": 0.2185051292181015, "learning_rate": 8.439999999999999e-07, "loss": 0.0068, "num_tokens": 79831126.0, "reward": 0.2421875, "reward_std": 0.12019839137792587, "rewards/simpleverify_reward/mean": 0.2421875, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 313 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.8046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1984.0, "completions/mean_length": 1905.671875, "completions/mean_terminated_length": 1319.280029296875, "completions/min_length": 314.0, "completions/min_terminated_length": 314.0, "epoch": 0.11142654364797729, "frac_reward_zero_std": 0.6875, "grad_norm": 0.24224166572093964, "learning_rate": 8.435e-07, "loss": -0.005, "num_tokens": 80087620.0, "reward": 0.1328125, "reward_std": 0.1344047486782074, "rewards/simpleverify_reward/mean": 0.1328125, "rewards/simpleverify_reward/std": 0.3407054841518402, "step": 314 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1719.578125, "completions/mean_terminated_length": 1380.730224609375, "completions/min_length": 643.0, "completions/min_terminated_length": 643.0, "epoch": 0.11178140525195174, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3218618631362915, "learning_rate": 8.429999999999999e-07, "loss": 0.0077, "num_tokens": 80319974.0, "reward": 0.265625, "reward_std": 0.1820138692855835, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 315 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2012.0, "completions/mean_length": 1591.5859375, "completions/mean_terminated_length": 1279.3026123046875, "completions/min_length": 473.0, "completions/min_terminated_length": 473.0, "epoch": 0.11213626685592619, "frac_reward_zero_std": 0.375, "grad_norm": 0.39656782150268555, "learning_rate": 8.425e-07, "loss": 0.0141, "num_tokens": 80533825.0, "reward": 0.3359375, "reward_std": 0.29932135343551636, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 316 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1928.0, "completions/mean_length": 1662.421875, "completions/mean_terminated_length": 1300.212158203125, "completions/min_length": 409.0, "completions/min_terminated_length": 409.0, "epoch": 0.11249112845990064, "frac_reward_zero_std": 0.4375, "grad_norm": 0.3831337094306946, "learning_rate": 8.419999999999999e-07, "loss": 0.0169, "num_tokens": 80756919.0, "reward": 0.3359375, "reward_std": 0.25354230403900146, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 317 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1483.28125, "completions/mean_terminated_length": 1044.0555419921875, "completions/min_length": 411.0, "completions/min_terminated_length": 411.0, "epoch": 0.11284599006387509, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3351518511772156, "learning_rate": 8.415e-07, "loss": 0.0076, "num_tokens": 80957971.0, "reward": 0.3671875, "reward_std": 0.1990984082221985, "rewards/simpleverify_reward/mean": 0.3671875, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 318 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1760.140625, "completions/mean_terminated_length": 1280.375, "completions/min_length": 457.0, "completions/min_terminated_length": 457.0, "epoch": 0.11320085166784954, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3081319332122803, "learning_rate": 8.41e-07, "loss": 0.0016, "num_tokens": 81195893.0, "reward": 0.171875, "reward_std": 0.19568344950675964, "rewards/simpleverify_reward/mean": 0.171875, "rewards/simpleverify_reward/std": 0.3787541687488556, "step": 319 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1913.0, "completions/mean_length": 1467.34375, "completions/mean_terminated_length": 1107.18994140625, "completions/min_length": 460.0, "completions/min_terminated_length": 460.0, "epoch": 0.11355571327182398, "frac_reward_zero_std": 0.3125, "grad_norm": 0.46082353591918945, "learning_rate": 8.404999999999999e-07, "loss": 0.0012, "num_tokens": 81393681.0, "reward": 0.484375, "reward_std": 0.2885475754737854, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 320 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1967.0, "completions/mean_length": 1546.2734375, "completions/mean_terminated_length": 1130.55712890625, "completions/min_length": 626.0, "completions/min_terminated_length": 626.0, "epoch": 0.11391057487579843, "frac_reward_zero_std": 0.5625, "grad_norm": 0.36904653906822205, "learning_rate": 8.399999999999999e-07, "loss": 0.0051, "num_tokens": 81600620.0, "reward": 0.34375, "reward_std": 0.2001592218875885, "rewards/simpleverify_reward/mean": 0.34375, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 321 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1726.6640625, "completions/mean_terminated_length": 1225.3800048828125, "completions/min_length": 468.0, "completions/min_terminated_length": 468.0, "epoch": 0.11426543647977289, "frac_reward_zero_std": 0.5625, "grad_norm": 0.34477853775024414, "learning_rate": 8.395e-07, "loss": 0.0109, "num_tokens": 81832825.0, "reward": 0.296875, "reward_std": 0.1841355413198471, "rewards/simpleverify_reward/mean": 0.296875, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 322 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1578.8984375, "completions/mean_terminated_length": 1124.230712890625, "completions/min_length": 543.0, "completions/min_terminated_length": 543.0, "epoch": 0.11462029808374734, "frac_reward_zero_std": 0.5, "grad_norm": 0.3494102954864502, "learning_rate": 8.389999999999999e-07, "loss": 0.0152, "num_tokens": 82047244.0, "reward": 0.390625, "reward_std": 0.2109457552433014, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 323 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1893.0625, "completions/mean_terminated_length": 1364.137939453125, "completions/min_length": 830.0, "completions/min_terminated_length": 830.0, "epoch": 0.11497515968772179, "frac_reward_zero_std": 0.75, "grad_norm": 0.21600313484668732, "learning_rate": 8.385e-07, "loss": 0.0201, "num_tokens": 82300924.0, "reward": 0.1875, "reward_std": 0.11230766773223877, "rewards/simpleverify_reward/mean": 0.1875, "rewards/simpleverify_reward/std": 0.39184603095054626, "step": 324 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1590.4609375, "completions/mean_terminated_length": 1256.5810546875, "completions/min_length": 552.0, "completions/min_terminated_length": 552.0, "epoch": 0.11533002129169624, "frac_reward_zero_std": 0.375, "grad_norm": 0.3563880920410156, "learning_rate": 8.38e-07, "loss": 0.0107, "num_tokens": 82515863.0, "reward": 0.390625, "reward_std": 0.28930896520614624, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 325 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1755.78125, "completions/mean_terminated_length": 1454.2857666015625, "completions/min_length": 536.0, "completions/min_terminated_length": 536.0, "epoch": 0.1156848828956707, "frac_reward_zero_std": 0.5, "grad_norm": 0.32081276178359985, "learning_rate": 8.375e-07, "loss": 0.0156, "num_tokens": 82753331.0, "reward": 0.3359375, "reward_std": 0.21778056025505066, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 326 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.546875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1742.0234375, "completions/mean_terminated_length": 1372.7413330078125, "completions/min_length": 552.0, "completions/min_terminated_length": 552.0, "epoch": 0.11603974449964514, "frac_reward_zero_std": 0.5, "grad_norm": 0.31785449385643005, "learning_rate": 8.369999999999999e-07, "loss": 0.0182, "num_tokens": 82988486.0, "reward": 0.2265625, "reward_std": 0.2314501255750656, "rewards/simpleverify_reward/mean": 0.2265625, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 327 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.546875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1719.5703125, "completions/mean_terminated_length": 1323.189697265625, "completions/min_length": 810.0, "completions/min_terminated_length": 810.0, "epoch": 0.11639460610361958, "frac_reward_zero_std": 0.625, "grad_norm": 0.2804138958454132, "learning_rate": 8.365e-07, "loss": -0.0047, "num_tokens": 83219007.0, "reward": 0.296875, "reward_std": 0.16675157845020294, "rewards/simpleverify_reward/mean": 0.296875, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 328 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5703125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2008.0, "completions/mean_length": 1653.375, "completions/mean_terminated_length": 1129.5999755859375, "completions/min_length": 466.0, "completions/min_terminated_length": 466.0, "epoch": 0.11674946770759403, "frac_reward_zero_std": 0.4375, "grad_norm": 0.39414918422698975, "learning_rate": 8.359999999999999e-07, "loss": 0.0168, "num_tokens": 83448623.0, "reward": 0.2734375, "reward_std": 0.23751860857009888, "rewards/simpleverify_reward/mean": 0.2734375, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 329 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1800.84375, "completions/mean_terminated_length": 1415.280029296875, "completions/min_length": 980.0, "completions/min_terminated_length": 980.0, "epoch": 0.11710432931156849, "frac_reward_zero_std": 0.5, "grad_norm": 0.33043357729911804, "learning_rate": 8.355e-07, "loss": 0.0048, "num_tokens": 83688187.0, "reward": 0.296875, "reward_std": 0.20517179369926453, "rewards/simpleverify_reward/mean": 0.296875, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 330 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2018.0, "completions/mean_length": 1708.7421875, "completions/mean_terminated_length": 1311.9830322265625, "completions/min_length": 707.0, "completions/min_terminated_length": 707.0, "epoch": 0.11745919091554294, "frac_reward_zero_std": 0.4375, "grad_norm": 0.3889828622341156, "learning_rate": 8.349999999999999e-07, "loss": 0.0131, "num_tokens": 83917690.0, "reward": 0.2421875, "reward_std": 0.2511882185935974, "rewards/simpleverify_reward/mean": 0.2421875, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 331 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1551.3203125, "completions/mean_terminated_length": 1211.48681640625, "completions/min_length": 656.0, "completions/min_terminated_length": 656.0, "epoch": 0.11781405251951739, "frac_reward_zero_std": 0.6875, "grad_norm": 0.2919055223464966, "learning_rate": 8.345e-07, "loss": 0.0062, "num_tokens": 84128747.0, "reward": 0.453125, "reward_std": 0.13781970739364624, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 332 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2023.0, "completions/mean_length": 1632.140625, "completions/mean_terminated_length": 1347.605224609375, "completions/min_length": 600.0, "completions/min_terminated_length": 600.0, "epoch": 0.11816891412349184, "frac_reward_zero_std": 0.6875, "grad_norm": 0.24284008145332336, "learning_rate": 8.34e-07, "loss": 0.001, "num_tokens": 84348901.0, "reward": 0.40625, "reward_std": 0.1514892876148224, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 333 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1995.0, "completions/mean_length": 1565.859375, "completions/mean_terminated_length": 1166.3714599609375, "completions/min_length": 43.0, "completions/min_terminated_length": 43.0, "epoch": 0.1185237757274663, "frac_reward_zero_std": 0.5625, "grad_norm": 0.33688002824783325, "learning_rate": 8.334999999999999e-07, "loss": 0.0261, "num_tokens": 84558083.0, "reward": 0.28125, "reward_std": 0.20463500916957855, "rewards/simpleverify_reward/mean": 0.28125, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 334 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1986.0, "completions/mean_length": 1777.515625, "completions/mean_terminated_length": 1406.851806640625, "completions/min_length": 737.0, "completions/min_terminated_length": 737.0, "epoch": 0.11887863733144073, "frac_reward_zero_std": 0.6875, "grad_norm": 0.24259230494499207, "learning_rate": 8.329999999999999e-07, "loss": 0.0062, "num_tokens": 84800629.0, "reward": 0.296875, "reward_std": 0.13781969249248505, "rewards/simpleverify_reward/mean": 0.296875, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 335 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1952.0, "completions/mean_length": 1341.1484375, "completions/mean_terminated_length": 1031.404541015625, "completions/min_length": 502.0, "completions/min_terminated_length": 502.0, "epoch": 0.11923349893541518, "frac_reward_zero_std": 0.4375, "grad_norm": 0.47636544704437256, "learning_rate": 8.325e-07, "loss": 0.0153, "num_tokens": 84983528.0, "reward": 0.5234375, "reward_std": 0.22621294856071472, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 336 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2020.0, "completions/mean_length": 1439.71875, "completions/mean_terminated_length": 1074.75, "completions/min_length": 419.0, "completions/min_terminated_length": 419.0, "epoch": 0.11958836053938963, "frac_reward_zero_std": 0.5, "grad_norm": 0.3617617189884186, "learning_rate": 8.319999999999999e-07, "loss": 0.0187, "num_tokens": 85178996.0, "reward": 0.40625, "reward_std": 0.23014703392982483, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 337 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2018.0, "completions/mean_length": 1611.84375, "completions/mean_terminated_length": 1051.071533203125, "completions/min_length": 360.0, "completions/min_terminated_length": 360.0, "epoch": 0.11994322214336409, "frac_reward_zero_std": 0.4375, "grad_norm": 0.48093491792678833, "learning_rate": 8.315e-07, "loss": 0.0114, "num_tokens": 85395592.0, "reward": 0.328125, "reward_std": 0.21937815845012665, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 338 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.546875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1838.90625, "completions/mean_terminated_length": 1586.5517578125, "completions/min_length": 809.0, "completions/min_terminated_length": 809.0, "epoch": 0.12029808374733854, "frac_reward_zero_std": 0.375, "grad_norm": 0.35707253217697144, "learning_rate": 8.31e-07, "loss": 0.0106, "num_tokens": 85641364.0, "reward": 0.2890625, "reward_std": 0.3119252026081085, "rewards/simpleverify_reward/mean": 0.2890625, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 339 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1994.0, "completions/mean_length": 1631.7421875, "completions/mean_terminated_length": 1364.9102783203125, "completions/min_length": 758.0, "completions/min_terminated_length": 758.0, "epoch": 0.12065294535131299, "frac_reward_zero_std": 0.5625, "grad_norm": 0.33931824564933777, "learning_rate": 8.304999999999999e-07, "loss": -0.0127, "num_tokens": 85863067.0, "reward": 0.3359375, "reward_std": 0.19332444667816162, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 340 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1759.3984375, "completions/mean_terminated_length": 1294.10205078125, "completions/min_length": 676.0, "completions/min_terminated_length": 676.0, "epoch": 0.12100780695528744, "frac_reward_zero_std": 0.625, "grad_norm": 0.33075857162475586, "learning_rate": 8.299999999999999e-07, "loss": 0.0089, "num_tokens": 86100134.0, "reward": 0.296875, "reward_std": 0.18359875679016113, "rewards/simpleverify_reward/mean": 0.296875, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 341 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.546875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1711.6640625, "completions/mean_terminated_length": 1305.7413330078125, "completions/min_length": 423.0, "completions/min_terminated_length": 423.0, "epoch": 0.1213626685592619, "frac_reward_zero_std": 0.5, "grad_norm": 0.34114184975624084, "learning_rate": 8.295e-07, "loss": 0.0058, "num_tokens": 86331219.0, "reward": 0.203125, "reward_std": 0.21542152762413025, "rewards/simpleverify_reward/mean": 0.203125, "rewards/simpleverify_reward/std": 0.40390563011169434, "step": 342 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1987.0, "completions/mean_length": 1729.078125, "completions/mean_terminated_length": 1389.58056640625, "completions/min_length": 648.0, "completions/min_terminated_length": 648.0, "epoch": 0.12171753016323633, "frac_reward_zero_std": 0.625, "grad_norm": 0.3108656704425812, "learning_rate": 8.289999999999999e-07, "loss": 0.0191, "num_tokens": 86568853.0, "reward": 0.3125, "reward_std": 0.18147706985473633, "rewards/simpleverify_reward/mean": 0.3125, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 343 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1629.6875, "completions/mean_terminated_length": 1224.2462158203125, "completions/min_length": 345.0, "completions/min_terminated_length": 345.0, "epoch": 0.12207239176721078, "frac_reward_zero_std": 0.375, "grad_norm": 0.38700857758522034, "learning_rate": 8.285e-07, "loss": 0.0144, "num_tokens": 86789653.0, "reward": 0.40625, "reward_std": 0.2777610719203949, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 344 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2002.0, "completions/mean_length": 1822.0234375, "completions/mean_terminated_length": 1419.1956787109375, "completions/min_length": 684.0, "completions/min_terminated_length": 684.0, "epoch": 0.12242725337118524, "frac_reward_zero_std": 0.625, "grad_norm": 0.274078905582428, "learning_rate": 8.28e-07, "loss": 0.0059, "num_tokens": 87036192.0, "reward": 0.1328125, "reward_std": 0.14966705441474915, "rewards/simpleverify_reward/mean": 0.1328125, "rewards/simpleverify_reward/std": 0.3407054841518402, "step": 345 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1587.5078125, "completions/mean_terminated_length": 1240.5616455078125, "completions/min_length": 768.0, "completions/min_terminated_length": 768.0, "epoch": 0.12278211497515969, "frac_reward_zero_std": 0.4375, "grad_norm": 0.37767553329467773, "learning_rate": 8.275e-07, "loss": 0.0103, "num_tokens": 87249769.0, "reward": 0.3984375, "reward_std": 0.26355957984924316, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 346 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1670.5625, "completions/mean_terminated_length": 1304.7384033203125, "completions/min_length": 588.0, "completions/min_terminated_length": 588.0, "epoch": 0.12313697657913414, "frac_reward_zero_std": 0.5, "grad_norm": 0.36224254965782166, "learning_rate": 8.269999999999999e-07, "loss": 0.0097, "num_tokens": 87474921.0, "reward": 0.2265625, "reward_std": 0.21778053045272827, "rewards/simpleverify_reward/mean": 0.2265625, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 347 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1581.6015625, "completions/mean_terminated_length": 1361.8045654296875, "completions/min_length": 868.0, "completions/min_terminated_length": 868.0, "epoch": 0.12349183818310859, "frac_reward_zero_std": 0.25, "grad_norm": 0.48073309659957886, "learning_rate": 8.264999999999999e-07, "loss": 0.0268, "num_tokens": 87691350.0, "reward": 0.53125, "reward_std": 0.3253750801086426, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 348 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1754.6171875, "completions/mean_terminated_length": 1411.5084228515625, "completions/min_length": 664.0, "completions/min_terminated_length": 664.0, "epoch": 0.12384669978708304, "frac_reward_zero_std": 0.3125, "grad_norm": 0.37202122807502747, "learning_rate": 8.259999999999999e-07, "loss": 0.0263, "num_tokens": 87926653.0, "reward": 0.2734375, "reward_std": 0.29538238048553467, "rewards/simpleverify_reward/mean": 0.2734375, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 349 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1655.90625, "completions/mean_terminated_length": 1238.51611328125, "completions/min_length": 363.0, "completions/min_terminated_length": 363.0, "epoch": 0.1242015613910575, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3404761552810669, "learning_rate": 8.255e-07, "loss": 0.0393, "num_tokens": 88150577.0, "reward": 0.265625, "reward_std": 0.1933293342590332, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 350 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1632.546875, "completions/mean_terminated_length": 1309.4166259765625, "completions/min_length": 632.0, "completions/min_terminated_length": 632.0, "epoch": 0.12455642299503193, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3334108293056488, "learning_rate": 8.249999999999999e-07, "loss": 0.009, "num_tokens": 88370519.0, "reward": 0.359375, "reward_std": 0.19438526034355164, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 351 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2015.0, "completions/mean_length": 1749.3828125, "completions/mean_terminated_length": 1340.1666259765625, "completions/min_length": 796.0, "completions/min_terminated_length": 796.0, "epoch": 0.12491128459900638, "frac_reward_zero_std": 0.625, "grad_norm": 0.31186622381210327, "learning_rate": 8.245e-07, "loss": 0.0065, "num_tokens": 88605616.0, "reward": 0.296875, "reward_std": 0.15992167592048645, "rewards/simpleverify_reward/mean": 0.296875, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 352 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1985.0, "completions/mean_length": 1739.234375, "completions/mean_terminated_length": 1316.111083984375, "completions/min_length": 540.0, "completions/min_terminated_length": 540.0, "epoch": 0.12526614620298085, "frac_reward_zero_std": 0.4375, "grad_norm": 0.4165165424346924, "learning_rate": 8.24e-07, "loss": 0.0105, "num_tokens": 88838542.0, "reward": 0.2734375, "reward_std": 0.2601397633552551, "rewards/simpleverify_reward/mean": 0.2734375, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 353 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1575.65625, "completions/mean_terminated_length": 1252.4736328125, "completions/min_length": 626.0, "completions/min_terminated_length": 626.0, "epoch": 0.1256210078069553, "frac_reward_zero_std": 0.4375, "grad_norm": 0.4168197810649872, "learning_rate": 8.234999999999999e-07, "loss": 0.012, "num_tokens": 89050138.0, "reward": 0.4296875, "reward_std": 0.2603819966316223, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 354 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1560.0546875, "completions/mean_terminated_length": 1257.4051513671875, "completions/min_length": 210.0, "completions/min_terminated_length": 210.0, "epoch": 0.12597586941092973, "frac_reward_zero_std": 0.25, "grad_norm": 0.41451025009155273, "learning_rate": 8.229999999999999e-07, "loss": 0.0347, "num_tokens": 89269041.0, "reward": 0.4296875, "reward_std": 0.33008819818496704, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 355 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4765625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2012.0, "completions/mean_length": 1515.9140625, "completions/mean_terminated_length": 1031.4775390625, "completions/min_length": 616.0, "completions/min_terminated_length": 616.0, "epoch": 0.1263307310149042, "frac_reward_zero_std": 0.8125, "grad_norm": 0.24746844172477722, "learning_rate": 8.225e-07, "loss": 0.0087, "num_tokens": 89473894.0, "reward": 0.4375, "reward_std": 0.07312604784965515, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 356 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1537.2578125, "completions/mean_terminated_length": 1209.8590087890625, "completions/min_length": 382.0, "completions/min_terminated_length": 382.0, "epoch": 0.12668559261887863, "frac_reward_zero_std": 0.375, "grad_norm": 0.383741557598114, "learning_rate": 8.219999999999999e-07, "loss": 0.0048, "num_tokens": 89682127.0, "reward": 0.4453125, "reward_std": 0.2845958471298218, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 357 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1983.0, "completions/mean_length": 1621.21875, "completions/mean_terminated_length": 1299.6712646484375, "completions/min_length": 451.0, "completions/min_terminated_length": 451.0, "epoch": 0.1270404542228531, "frac_reward_zero_std": 0.375, "grad_norm": 0.41173288226127625, "learning_rate": 8.215e-07, "loss": -0.0078, "num_tokens": 89900715.0, "reward": 0.265625, "reward_std": 0.28930896520614624, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 358 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1898.0, "completions/mean_length": 1853.3671875, "completions/mean_terminated_length": 1440.3658447265625, "completions/min_length": 951.0, "completions/min_terminated_length": 951.0, "epoch": 0.12739531582682753, "frac_reward_zero_std": 0.6875, "grad_norm": 0.27068012952804565, "learning_rate": 8.21e-07, "loss": 0.0198, "num_tokens": 90149386.0, "reward": 0.265625, "reward_std": 0.15596505999565125, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 359 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1973.0, "completions/mean_length": 1695.2109375, "completions/mean_terminated_length": 1144.8599853515625, "completions/min_length": 363.0, "completions/min_terminated_length": 363.0, "epoch": 0.127750177430802, "frac_reward_zero_std": 0.6875, "grad_norm": 0.39065778255462646, "learning_rate": 8.205e-07, "loss": 0.0064, "num_tokens": 90378229.0, "reward": 0.2265625, "reward_std": 0.1593799889087677, "rewards/simpleverify_reward/mean": 0.2265625, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 360 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1859.0859375, "completions/mean_terminated_length": 1472.261962890625, "completions/min_length": 863.0, "completions/min_terminated_length": 863.0, "epoch": 0.12810503903477644, "frac_reward_zero_std": 0.5, "grad_norm": 0.3598393499851227, "learning_rate": 8.199999999999999e-07, "loss": 0.0036, "num_tokens": 90626600.0, "reward": 0.2109375, "reward_std": 0.2120065689086914, "rewards/simpleverify_reward/mean": 0.2109375, "rewards/simpleverify_reward/std": 0.4095771610736847, "step": 361 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.765625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1976.0, "completions/mean_length": 1860.796875, "completions/mean_terminated_length": 1249.2667236328125, "completions/min_length": 473.0, "completions/min_terminated_length": 473.0, "epoch": 0.12845990063875087, "frac_reward_zero_std": 0.8125, "grad_norm": 0.2104821354150772, "learning_rate": 8.194999999999999e-07, "loss": -0.0018, "num_tokens": 90877870.0, "reward": 0.1015625, "reward_std": 0.0765409916639328, "rewards/simpleverify_reward/mean": 0.1015625, "rewards/simpleverify_reward/std": 0.3032590448856354, "step": 362 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2012.0, "completions/mean_length": 1728.6640625, "completions/mean_terminated_length": 1510.1710205078125, "completions/min_length": 826.0, "completions/min_terminated_length": 826.0, "epoch": 0.12881476224272534, "frac_reward_zero_std": 0.375, "grad_norm": 0.36217764019966125, "learning_rate": 8.189999999999999e-07, "loss": 0.0067, "num_tokens": 91111035.0, "reward": 0.2890625, "reward_std": 0.2801200747489929, "rewards/simpleverify_reward/mean": 0.2890625, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 363 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5703125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1707.8125, "completions/mean_terminated_length": 1256.2908935546875, "completions/min_length": 441.0, "completions/min_terminated_length": 441.0, "epoch": 0.12916962384669978, "frac_reward_zero_std": 0.5, "grad_norm": 0.3259200155735016, "learning_rate": 8.185e-07, "loss": 0.0052, "num_tokens": 91340275.0, "reward": 0.2265625, "reward_std": 0.2451099008321762, "rewards/simpleverify_reward/mean": 0.2265625, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 364 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1967.0, "completions/mean_length": 1503.3671875, "completions/mean_terminated_length": 1052.0999755859375, "completions/min_length": 374.0, "completions/min_terminated_length": 374.0, "epoch": 0.12952448545067424, "frac_reward_zero_std": 0.5625, "grad_norm": 0.4014933407306671, "learning_rate": 8.179999999999999e-07, "loss": 0.0088, "num_tokens": 91543474.0, "reward": 0.28125, "reward_std": 0.21040897071361542, "rewards/simpleverify_reward/mean": 0.28125, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 365 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1715.765625, "completions/mean_terminated_length": 1288.607177734375, "completions/min_length": 592.0, "completions/min_terminated_length": 592.0, "epoch": 0.12987934705464868, "frac_reward_zero_std": 0.4375, "grad_norm": 0.3815619647502899, "learning_rate": 8.175e-07, "loss": 0.0152, "num_tokens": 91772724.0, "reward": 0.2109375, "reward_std": 0.27275338768959045, "rewards/simpleverify_reward/mean": 0.2109375, "rewards/simpleverify_reward/std": 0.4095771610736847, "step": 366 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1533.6796875, "completions/mean_terminated_length": 1340.1182861328125, "completions/min_length": 541.0, "completions/min_terminated_length": 541.0, "epoch": 0.13023420865862315, "frac_reward_zero_std": 0.25, "grad_norm": 0.4437546730041504, "learning_rate": 8.169999999999999e-07, "loss": 0.0043, "num_tokens": 91979387.0, "reward": 0.4609375, "reward_std": 0.3379838466644287, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 367 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1719.0859375, "completions/mean_terminated_length": 1253.6414794921875, "completions/min_length": 570.0, "completions/min_terminated_length": 570.0, "epoch": 0.13058907026259758, "frac_reward_zero_std": 0.5, "grad_norm": 0.32243016362190247, "learning_rate": 8.164999999999999e-07, "loss": 0.0188, "num_tokens": 92211022.0, "reward": 0.34375, "reward_std": 0.24381661415100098, "rewards/simpleverify_reward/mean": 0.34375, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 368 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1587.4765625, "completions/mean_terminated_length": 1229.2916259765625, "completions/min_length": 504.0, "completions/min_terminated_length": 504.0, "epoch": 0.13094393186657205, "frac_reward_zero_std": 0.3125, "grad_norm": 0.4453756809234619, "learning_rate": 8.159999999999999e-07, "loss": 0.0343, "num_tokens": 92424947.0, "reward": 0.4375, "reward_std": 0.30327308177948, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 369 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1548.0546875, "completions/mean_terminated_length": 1120.565185546875, "completions/min_length": 451.0, "completions/min_terminated_length": 451.0, "epoch": 0.1312987934705465, "frac_reward_zero_std": 0.6875, "grad_norm": 0.28283506631851196, "learning_rate": 8.155e-07, "loss": 0.0033, "num_tokens": 92635570.0, "reward": 0.390625, "reward_std": 0.12756997346878052, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 370 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1695.59375, "completions/mean_terminated_length": 1354.03076171875, "completions/min_length": 408.0, "completions/min_terminated_length": 408.0, "epoch": 0.13165365507452093, "frac_reward_zero_std": 0.375, "grad_norm": 0.3999881446361542, "learning_rate": 8.149999999999999e-07, "loss": 0.0244, "num_tokens": 92865294.0, "reward": 0.3203125, "reward_std": 0.2869499623775482, "rewards/simpleverify_reward/mean": 0.3203125, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 371 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2004.0, "completions/mean_length": 1575.7109375, "completions/mean_terminated_length": 1241.9600830078125, "completions/min_length": 586.0, "completions/min_terminated_length": 586.0, "epoch": 0.1320085166784954, "frac_reward_zero_std": 0.625, "grad_norm": 0.34113720059394836, "learning_rate": 8.145e-07, "loss": 0.0098, "num_tokens": 93078345.0, "reward": 0.25, "reward_std": 0.18359875679016113, "rewards/simpleverify_reward/mean": 0.25, "rewards/simpleverify_reward/std": 0.434714138507843, "step": 372 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1825.8125, "completions/mean_terminated_length": 1479.199951171875, "completions/min_length": 637.0, "completions/min_terminated_length": 637.0, "epoch": 0.13236337828246983, "frac_reward_zero_std": 0.625, "grad_norm": 0.31132739782333374, "learning_rate": 8.14e-07, "loss": -0.0051, "num_tokens": 93327913.0, "reward": 0.21875, "reward_std": 0.16545340418815613, "rewards/simpleverify_reward/mean": 0.21875, "rewards/simpleverify_reward/std": 0.41502299904823303, "step": 373 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1762.5859375, "completions/mean_terminated_length": 1198.3953857421875, "completions/min_length": 461.0, "completions/min_terminated_length": 461.0, "epoch": 0.1327182398864443, "frac_reward_zero_std": 0.5, "grad_norm": 0.3465563952922821, "learning_rate": 8.134999999999999e-07, "loss": 0.0259, "num_tokens": 93566132.0, "reward": 0.296875, "reward_std": 0.20517179369926453, "rewards/simpleverify_reward/mean": 0.296875, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 374 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1714.3515625, "completions/mean_terminated_length": 1359.1773681640625, "completions/min_length": 439.0, "completions/min_terminated_length": 439.0, "epoch": 0.13307310149041873, "frac_reward_zero_std": 0.4375, "grad_norm": 0.336162805557251, "learning_rate": 8.129999999999999e-07, "loss": 0.0179, "num_tokens": 93795457.0, "reward": 0.2890625, "reward_std": 0.2556639611721039, "rewards/simpleverify_reward/mean": 0.2890625, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 375 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1847.65625, "completions/mean_terminated_length": 1422.5364990234375, "completions/min_length": 916.0, "completions/min_terminated_length": 916.0, "epoch": 0.1334279630943932, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3068615794181824, "learning_rate": 8.125e-07, "loss": 0.0156, "num_tokens": 94043421.0, "reward": 0.2578125, "reward_std": 0.21146979928016663, "rewards/simpleverify_reward/mean": 0.2578125, "rewards/simpleverify_reward/std": 0.43914902210235596, "step": 376 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1572.375, "completions/mean_terminated_length": 1225.29736328125, "completions/min_length": 523.0, "completions/min_terminated_length": 523.0, "epoch": 0.13378282469836764, "frac_reward_zero_std": 0.4375, "grad_norm": 0.3763822019100189, "learning_rate": 8.12e-07, "loss": 0.0191, "num_tokens": 94254013.0, "reward": 0.4453125, "reward_std": 0.251188188791275, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 377 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1557.0859375, "completions/mean_terminated_length": 1299.9405517578125, "completions/min_length": 369.0, "completions/min_terminated_length": 369.0, "epoch": 0.13413768630234207, "frac_reward_zero_std": 0.3125, "grad_norm": 0.44133850932121277, "learning_rate": 8.115e-07, "loss": 0.0042, "num_tokens": 94462392.0, "reward": 0.46875, "reward_std": 0.3135228157043457, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 378 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1553.65625, "completions/mean_terminated_length": 1181.2054443359375, "completions/min_length": 250.0, "completions/min_terminated_length": 250.0, "epoch": 0.13449254790631654, "frac_reward_zero_std": 0.625, "grad_norm": 0.293014794588089, "learning_rate": 8.11e-07, "loss": 0.0171, "num_tokens": 94672220.0, "reward": 0.34375, "reward_std": 0.17700131237506866, "rewards/simpleverify_reward/mean": 0.34375, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 379 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2013.0, "completions/mean_length": 1521.0078125, "completions/mean_terminated_length": 1314.79345703125, "completions/min_length": 581.0, "completions/min_terminated_length": 581.0, "epoch": 0.13484740951029098, "frac_reward_zero_std": 0.1875, "grad_norm": 0.4553318917751312, "learning_rate": 8.105e-07, "loss": 0.0318, "num_tokens": 94880861.0, "reward": 0.4765625, "reward_std": 0.3895270526409149, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 380 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1565.484375, "completions/mean_terminated_length": 1224.5067138671875, "completions/min_length": 381.0, "completions/min_terminated_length": 381.0, "epoch": 0.13520227111426544, "frac_reward_zero_std": 0.3125, "grad_norm": 0.41930896043777466, "learning_rate": 8.1e-07, "loss": 0.0292, "num_tokens": 95089579.0, "reward": 0.4140625, "reward_std": 0.31140607595443726, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 381 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2012.0, "completions/mean_length": 1705.296875, "completions/mean_terminated_length": 1373.138427734375, "completions/min_length": 665.0, "completions/min_terminated_length": 665.0, "epoch": 0.13555713271823988, "frac_reward_zero_std": 0.625, "grad_norm": 0.2677071690559387, "learning_rate": 8.094999999999999e-07, "loss": 0.0023, "num_tokens": 95317393.0, "reward": 0.3203125, "reward_std": 0.13941730558872223, "rewards/simpleverify_reward/mean": 0.3203125, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 382 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5703125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1662.0703125, "completions/mean_terminated_length": 1149.8363037109375, "completions/min_length": 441.0, "completions/min_terminated_length": 441.0, "epoch": 0.13591199432221435, "frac_reward_zero_std": 0.75, "grad_norm": 0.2755357027053833, "learning_rate": 8.09e-07, "loss": 0.0111, "num_tokens": 95544282.0, "reward": 0.265625, "reward_std": 0.11230766773223877, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 383 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5546875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1717.890625, "completions/mean_terminated_length": 1306.7017822265625, "completions/min_length": 694.0, "completions/min_terminated_length": 694.0, "epoch": 0.13626685592618878, "frac_reward_zero_std": 0.625, "grad_norm": 0.27980145812034607, "learning_rate": 8.085e-07, "loss": 0.0146, "num_tokens": 95776980.0, "reward": 0.34375, "reward_std": 0.16097761690616608, "rewards/simpleverify_reward/mean": 0.34375, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 384 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1678.7734375, "completions/mean_terminated_length": 1417.8533935546875, "completions/min_length": 756.0, "completions/min_terminated_length": 756.0, "epoch": 0.13662171753016322, "frac_reward_zero_std": 0.1875, "grad_norm": 0.49462372064590454, "learning_rate": 8.08e-07, "loss": 0.0141, "num_tokens": 96008175.0, "reward": 0.4296875, "reward_std": 0.3656175136566162, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 385 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4765625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1723.140625, "completions/mean_terminated_length": 1427.373046875, "completions/min_length": 587.0, "completions/min_terminated_length": 587.0, "epoch": 0.1369765791341377, "frac_reward_zero_std": 0.25, "grad_norm": 0.43258920311927795, "learning_rate": 8.075e-07, "loss": 0.0084, "num_tokens": 96240097.0, "reward": 0.375, "reward_std": 0.3424547016620636, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 386 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1515.4453125, "completions/mean_terminated_length": 1101.236083984375, "completions/min_length": 572.0, "completions/min_terminated_length": 572.0, "epoch": 0.13733144073811213, "frac_reward_zero_std": 0.5, "grad_norm": 0.3283170759677887, "learning_rate": 8.070000000000001e-07, "loss": 0.0062, "num_tokens": 96444914.0, "reward": 0.3515625, "reward_std": 0.21990220248699188, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 387 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.53125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2000.0, "completions/mean_length": 1703.6796875, "completions/mean_terminated_length": 1313.4500732421875, "completions/min_length": 554.0, "completions/min_terminated_length": 554.0, "epoch": 0.1376863023420866, "frac_reward_zero_std": 0.5, "grad_norm": 0.3350697159767151, "learning_rate": 8.064999999999999e-07, "loss": 0.0003, "num_tokens": 96675977.0, "reward": 0.265625, "reward_std": 0.23356689512729645, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 388 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1619.6640625, "completions/mean_terminated_length": 1264.7572021484375, "completions/min_length": 623.0, "completions/min_terminated_length": 623.0, "epoch": 0.13804116394606103, "frac_reward_zero_std": 0.375, "grad_norm": 0.38728225231170654, "learning_rate": 8.06e-07, "loss": 0.023, "num_tokens": 96895150.0, "reward": 0.328125, "reward_std": 0.2698654234409332, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 389 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1432.859375, "completions/mean_terminated_length": 1201.3548583984375, "completions/min_length": 556.0, "completions/min_terminated_length": 556.0, "epoch": 0.1383960255500355, "frac_reward_zero_std": 0.4375, "grad_norm": 0.397167831659317, "learning_rate": 8.055e-07, "loss": -0.0032, "num_tokens": 97091860.0, "reward": 0.484375, "reward_std": 0.25566887855529785, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 390 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1966.0, "completions/mean_length": 1721.59375, "completions/mean_terminated_length": 1301.9285888671875, "completions/min_length": 625.0, "completions/min_terminated_length": 625.0, "epoch": 0.13875088715400993, "frac_reward_zero_std": 0.4375, "grad_norm": 0.4167414903640747, "learning_rate": 8.05e-07, "loss": 0.0102, "num_tokens": 97323000.0, "reward": 0.25, "reward_std": 0.2740466892719269, "rewards/simpleverify_reward/mean": 0.25, "rewards/simpleverify_reward/std": 0.434714138507843, "step": 391 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1999.0, "completions/mean_length": 1742.1015625, "completions/mean_terminated_length": 1196.8043212890625, "completions/min_length": 605.0, "completions/min_terminated_length": 605.0, "epoch": 0.1391057487579844, "frac_reward_zero_std": 0.625, "grad_norm": 0.3362621068954468, "learning_rate": 8.045e-07, "loss": 0.0024, "num_tokens": 97558701.0, "reward": 0.234375, "reward_std": 0.18725106120109558, "rewards/simpleverify_reward/mean": 0.234375, "rewards/simpleverify_reward/std": 0.42527204751968384, "step": 392 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1616.109375, "completions/mean_terminated_length": 1210.3939208984375, "completions/min_length": 624.0, "completions/min_terminated_length": 624.0, "epoch": 0.13946061036195884, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3119211792945862, "learning_rate": 8.04e-07, "loss": 0.0156, "num_tokens": 97778547.0, "reward": 0.390625, "reward_std": 0.19226360321044922, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 393 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1528.4375, "completions/mean_terminated_length": 1149.29736328125, "completions/min_length": 462.0, "completions/min_terminated_length": 462.0, "epoch": 0.13981547196593327, "frac_reward_zero_std": 0.4375, "grad_norm": 0.39737579226493835, "learning_rate": 8.034999999999999e-07, "loss": 0.0018, "num_tokens": 97984643.0, "reward": 0.34375, "reward_std": 0.23645778000354767, "rewards/simpleverify_reward/mean": 0.34375, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 394 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1999.0, "completions/mean_length": 1549.125, "completions/mean_terminated_length": 1207.7894287109375, "completions/min_length": 658.0, "completions/min_terminated_length": 658.0, "epoch": 0.14017033356990774, "frac_reward_zero_std": 0.5, "grad_norm": 0.32970213890075684, "learning_rate": 8.03e-07, "loss": 0.0142, "num_tokens": 98195427.0, "reward": 0.375, "reward_std": 0.21436560153961182, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 395 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.703125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2022.0, "completions/mean_length": 1760.4609375, "completions/mean_terminated_length": 1079.4473876953125, "completions/min_length": 460.0, "completions/min_terminated_length": 460.0, "epoch": 0.14052519517388218, "frac_reward_zero_std": 0.6875, "grad_norm": 0.26566675305366516, "learning_rate": 8.024999999999999e-07, "loss": -0.0053, "num_tokens": 98432590.0, "reward": 0.171875, "reward_std": 0.12756997346878052, "rewards/simpleverify_reward/mean": 0.171875, "rewards/simpleverify_reward/std": 0.3787541687488556, "step": 396 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5, "completions/max_length": 2048.0, "completions/max_terminated_length": 1997.0, "completions/mean_length": 1651.2109375, "completions/mean_terminated_length": 1254.421875, "completions/min_length": 820.0, "completions/min_terminated_length": 820.0, "epoch": 0.14088005677785664, "frac_reward_zero_std": 0.375, "grad_norm": 0.4477979242801666, "learning_rate": 8.02e-07, "loss": 0.0158, "num_tokens": 98654257.0, "reward": 0.3671875, "reward_std": 0.27222445607185364, "rewards/simpleverify_reward/mean": 0.3671875, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 397 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2011.0, "completions/mean_length": 1571.015625, "completions/mean_terminated_length": 1362.0, "completions/min_length": 584.0, "completions/min_terminated_length": 584.0, "epoch": 0.14123491838183108, "frac_reward_zero_std": 0.3125, "grad_norm": 0.42701542377471924, "learning_rate": 8.015e-07, "loss": 0.0336, "num_tokens": 98869347.0, "reward": 0.4609375, "reward_std": 0.3224793076515198, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 398 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1712.8828125, "completions/mean_terminated_length": 1344.80322265625, "completions/min_length": 654.0, "completions/min_terminated_length": 654.0, "epoch": 0.14158977998580555, "frac_reward_zero_std": 0.5, "grad_norm": 0.3441160023212433, "learning_rate": 8.01e-07, "loss": 0.0046, "num_tokens": 99098052.0, "reward": 0.28125, "reward_std": 0.23934084177017212, "rewards/simpleverify_reward/mean": 0.28125, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 399 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1520.046875, "completions/mean_terminated_length": 1213.7037353515625, "completions/min_length": 451.0, "completions/min_terminated_length": 451.0, "epoch": 0.14194464158977999, "frac_reward_zero_std": 0.4375, "grad_norm": 0.38593432307243347, "learning_rate": 8.005e-07, "loss": 0.0137, "num_tokens": 99304130.0, "reward": 0.4296875, "reward_std": 0.24329257011413574, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 400 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1580.609375, "completions/mean_terminated_length": 1239.54052734375, "completions/min_length": 543.0, "completions/min_terminated_length": 543.0, "epoch": 0.14229950319375442, "frac_reward_zero_std": 0.5625, "grad_norm": 0.37898221611976624, "learning_rate": 8e-07, "loss": -0.0007, "num_tokens": 99521600.0, "reward": 0.3125, "reward_std": 0.1841355413198471, "rewards/simpleverify_reward/mean": 0.3125, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 401 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1982.0, "completions/mean_length": 1476.234375, "completions/mean_terminated_length": 1225.6854248046875, "completions/min_length": 580.0, "completions/min_terminated_length": 580.0, "epoch": 0.1426543647977289, "frac_reward_zero_std": 0.5, "grad_norm": 0.36896049976348877, "learning_rate": 7.994999999999999e-07, "loss": -0.0084, "num_tokens": 99721478.0, "reward": 0.515625, "reward_std": 0.24381661415100098, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 402 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2020.0, "completions/mean_length": 1648.234375, "completions/mean_terminated_length": 1222.6773681640625, "completions/min_length": 636.0, "completions/min_terminated_length": 636.0, "epoch": 0.14300922640170333, "frac_reward_zero_std": 0.5, "grad_norm": 0.34463030099868774, "learning_rate": 7.99e-07, "loss": 0.0203, "num_tokens": 99941836.0, "reward": 0.3125, "reward_std": 0.24381661415100098, "rewards/simpleverify_reward/mean": 0.3125, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 403 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2020.0, "completions/mean_length": 1738.2265625, "completions/mean_terminated_length": 1397.9835205078125, "completions/min_length": 584.0, "completions/min_terminated_length": 584.0, "epoch": 0.1433640880056778, "frac_reward_zero_std": 0.4375, "grad_norm": 0.33979734778404236, "learning_rate": 7.985e-07, "loss": -0.0088, "num_tokens": 100176977.0, "reward": 0.296875, "reward_std": 0.26249876618385315, "rewards/simpleverify_reward/mean": 0.296875, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 404 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1475.140625, "completions/mean_terminated_length": 1205.17236328125, "completions/min_length": 587.0, "completions/min_terminated_length": 587.0, "epoch": 0.14371894960965223, "frac_reward_zero_std": 0.25, "grad_norm": 0.46085888147354126, "learning_rate": 7.98e-07, "loss": 0.0036, "num_tokens": 100377491.0, "reward": 0.3515625, "reward_std": 0.325370192527771, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 405 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1692.4765625, "completions/mean_terminated_length": 1407.0562744140625, "completions/min_length": 663.0, "completions/min_terminated_length": 663.0, "epoch": 0.1440738112136267, "frac_reward_zero_std": 0.25, "grad_norm": 0.4188992381095886, "learning_rate": 7.975e-07, "loss": 0.023, "num_tokens": 100608296.0, "reward": 0.3984375, "reward_std": 0.331153929233551, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 406 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1758.4296875, "completions/mean_terminated_length": 1510.826171875, "completions/min_length": 750.0, "completions/min_terminated_length": 750.0, "epoch": 0.14442867281760113, "frac_reward_zero_std": 0.25, "grad_norm": 0.4223903715610504, "learning_rate": 7.970000000000001e-07, "loss": -0.0006, "num_tokens": 100844639.0, "reward": 0.4296875, "reward_std": 0.3311441242694855, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 407 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1393.7578125, "completions/mean_terminated_length": 1107.0673828125, "completions/min_length": 374.0, "completions/min_terminated_length": 374.0, "epoch": 0.1447835344215756, "frac_reward_zero_std": 0.625, "grad_norm": 0.2960067689418793, "learning_rate": 7.964999999999999e-07, "loss": -0.0024, "num_tokens": 101034936.0, "reward": 0.5390625, "reward_std": 0.1701665222644806, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 408 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2001.0, "completions/mean_length": 1381.3515625, "completions/mean_terminated_length": 1159.135498046875, "completions/min_length": 552.0, "completions/min_terminated_length": 552.0, "epoch": 0.14513839602555004, "frac_reward_zero_std": 0.375, "grad_norm": 0.47950854897499084, "learning_rate": 7.96e-07, "loss": 0.0439, "num_tokens": 101224421.0, "reward": 0.46875, "reward_std": 0.2961388826370239, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 409 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2006.0, "completions/mean_length": 1458.015625, "completions/mean_terminated_length": 1115.6790771484375, "completions/min_length": 505.0, "completions/min_terminated_length": 505.0, "epoch": 0.14549325762952448, "frac_reward_zero_std": 0.5625, "grad_norm": 0.32937830686569214, "learning_rate": 7.954999999999999e-07, "loss": 0.0073, "num_tokens": 101424615.0, "reward": 0.375, "reward_std": 0.18543371558189392, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 410 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1966.0, "completions/mean_length": 1651.3203125, "completions/mean_terminated_length": 1312.1304931640625, "completions/min_length": 398.0, "completions/min_terminated_length": 398.0, "epoch": 0.14584811923349894, "frac_reward_zero_std": 0.3125, "grad_norm": 0.46722593903541565, "learning_rate": 7.95e-07, "loss": 0.011, "num_tokens": 101644864.0, "reward": 0.3984375, "reward_std": 0.287486732006073, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 411 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.46875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1612.859375, "completions/mean_terminated_length": 1228.9117431640625, "completions/min_length": 372.0, "completions/min_terminated_length": 372.0, "epoch": 0.14620298083747338, "frac_reward_zero_std": 0.5625, "grad_norm": 0.36611199378967285, "learning_rate": 7.945e-07, "loss": 0.0034, "num_tokens": 101863886.0, "reward": 0.2734375, "reward_std": 0.19567856192588806, "rewards/simpleverify_reward/mean": 0.2734375, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 412 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1417.546875, "completions/mean_terminated_length": 1198.54736328125, "completions/min_length": 358.0, "completions/min_terminated_length": 358.0, "epoch": 0.14655784244144784, "frac_reward_zero_std": 0.5, "grad_norm": 0.3523828685283661, "learning_rate": 7.94e-07, "loss": 0.0035, "num_tokens": 102056556.0, "reward": 0.4609375, "reward_std": 0.23250606656074524, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 413 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2008.0, "completions/mean_length": 1729.3203125, "completions/mean_terminated_length": 1278.3585205078125, "completions/min_length": 507.0, "completions/min_terminated_length": 507.0, "epoch": 0.14691270404542228, "frac_reward_zero_std": 0.625, "grad_norm": 0.2786339223384857, "learning_rate": 7.934999999999999e-07, "loss": 0.0173, "num_tokens": 102289333.0, "reward": 0.359375, "reward_std": 0.1893727034330368, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 414 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.59375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1802.1953125, "completions/mean_terminated_length": 1442.9423828125, "completions/min_length": 474.0, "completions/min_terminated_length": 474.0, "epoch": 0.14726756564939675, "frac_reward_zero_std": 0.5, "grad_norm": 0.3441077172756195, "learning_rate": 7.93e-07, "loss": 0.0145, "num_tokens": 102529310.0, "reward": 0.21875, "reward_std": 0.22567126154899597, "rewards/simpleverify_reward/mean": 0.21875, "rewards/simpleverify_reward/std": 0.41502299904823303, "step": 415 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2015.0, "completions/mean_length": 1719.984375, "completions/mean_terminated_length": 1154.6807861328125, "completions/min_length": 623.0, "completions/min_terminated_length": 623.0, "epoch": 0.14762242725337119, "frac_reward_zero_std": 0.625, "grad_norm": 0.32400697469711304, "learning_rate": 7.924999999999999e-07, "loss": 0.0078, "num_tokens": 102759364.0, "reward": 0.25, "reward_std": 0.1530819833278656, "rewards/simpleverify_reward/mean": 0.25, "rewards/simpleverify_reward/std": 0.434714138507843, "step": 416 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1567.8125, "completions/mean_terminated_length": 1269.9747314453125, "completions/min_length": 437.0, "completions/min_terminated_length": 437.0, "epoch": 0.14797728885734562, "frac_reward_zero_std": 0.3125, "grad_norm": 0.4601669907569885, "learning_rate": 7.92e-07, "loss": 0.0197, "num_tokens": 102974028.0, "reward": 0.484375, "reward_std": 0.30221718549728394, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 417 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1971.0, "completions/mean_length": 1579.6796875, "completions/mean_terminated_length": 1139.742431640625, "completions/min_length": 466.0, "completions/min_terminated_length": 466.0, "epoch": 0.1483321504613201, "frac_reward_zero_std": 0.625, "grad_norm": 0.3124106824398041, "learning_rate": 7.915e-07, "loss": 0.0054, "num_tokens": 103187019.0, "reward": 0.359375, "reward_std": 0.1893727034330368, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 418 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1600.2109375, "completions/mean_terminated_length": 1152.421875, "completions/min_length": 365.0, "completions/min_terminated_length": 365.0, "epoch": 0.14868701206529453, "frac_reward_zero_std": 0.625, "grad_norm": 0.3654753267765045, "learning_rate": 7.91e-07, "loss": -0.0023, "num_tokens": 103405598.0, "reward": 0.3046875, "reward_std": 0.14966705441474915, "rewards/simpleverify_reward/mean": 0.3046875, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 419 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2013.0, "completions/mean_length": 1684.2890625, "completions/mean_terminated_length": 1435.4342041015625, "completions/min_length": 460.0, "completions/min_terminated_length": 460.0, "epoch": 0.149041873669269, "frac_reward_zero_std": 0.3125, "grad_norm": 0.39443063735961914, "learning_rate": 7.905e-07, "loss": 0.0343, "num_tokens": 103631715.0, "reward": 0.3671875, "reward_std": 0.31800350546836853, "rewards/simpleverify_reward/mean": 0.3671875, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 420 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1487.46875, "completions/mean_terminated_length": 1223.310302734375, "completions/min_length": 618.0, "completions/min_terminated_length": 618.0, "epoch": 0.14939673527324343, "frac_reward_zero_std": 0.3125, "grad_norm": 0.45436015725135803, "learning_rate": 7.9e-07, "loss": 0.0163, "num_tokens": 103836023.0, "reward": 0.484375, "reward_std": 0.3066929578781128, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 421 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1752.40625, "completions/mean_terminated_length": 1275.836669921875, "completions/min_length": 433.0, "completions/min_terminated_length": 433.0, "epoch": 0.1497515968772179, "frac_reward_zero_std": 0.5625, "grad_norm": 0.30419668555259705, "learning_rate": 7.894999999999999e-07, "loss": 0.0089, "num_tokens": 104071347.0, "reward": 0.2890625, "reward_std": 0.19332444667816162, "rewards/simpleverify_reward/mean": 0.2890625, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 422 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4765625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2023.0, "completions/mean_length": 1672.03125, "completions/mean_terminated_length": 1329.7313232421875, "completions/min_length": 417.0, "completions/min_terminated_length": 417.0, "epoch": 0.15010645848119233, "frac_reward_zero_std": 0.625, "grad_norm": 0.28032252192497253, "learning_rate": 7.89e-07, "loss": 0.0092, "num_tokens": 104297095.0, "reward": 0.1953125, "reward_std": 0.14966705441474915, "rewards/simpleverify_reward/mean": 0.1953125, "rewards/simpleverify_reward/std": 0.3979988098144531, "step": 423 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1497.1328125, "completions/mean_terminated_length": 1289.8172607421875, "completions/min_length": 804.0, "completions/min_terminated_length": 804.0, "epoch": 0.15046132008516677, "frac_reward_zero_std": 0.4375, "grad_norm": 0.3899635672569275, "learning_rate": 7.884999999999999e-07, "loss": 0.023, "num_tokens": 104501152.0, "reward": 0.4921875, "reward_std": 0.2498900294303894, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 424 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.59375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1764.2578125, "completions/mean_terminated_length": 1349.5577392578125, "completions/min_length": 734.0, "completions/min_terminated_length": 734.0, "epoch": 0.15081618168914124, "frac_reward_zero_std": 0.4375, "grad_norm": 0.3870023488998413, "learning_rate": 7.88e-07, "loss": 0.0167, "num_tokens": 104740393.0, "reward": 0.265625, "reward_std": 0.2580229938030243, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 425 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1606.109375, "completions/mean_terminated_length": 1332.025390625, "completions/min_length": 351.0, "completions/min_terminated_length": 351.0, "epoch": 0.15117104329311568, "frac_reward_zero_std": 0.5625, "grad_norm": 0.308543860912323, "learning_rate": 7.875e-07, "loss": -0.0025, "num_tokens": 104957719.0, "reward": 0.515625, "reward_std": 0.2001592367887497, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 426 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1671.984375, "completions/mean_terminated_length": 1475.0238037109375, "completions/min_length": 393.0, "completions/min_terminated_length": 393.0, "epoch": 0.15152590489709014, "frac_reward_zero_std": 0.4375, "grad_norm": 0.37979206442832947, "learning_rate": 7.87e-07, "loss": -0.0021, "num_tokens": 105184413.0, "reward": 0.3515625, "reward_std": 0.2738093435764313, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 427 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1965.0, "completions/mean_length": 1544.8125, "completions/mean_terminated_length": 1242.9000244140625, "completions/min_length": 305.0, "completions/min_terminated_length": 305.0, "epoch": 0.15188076650106458, "frac_reward_zero_std": 0.4375, "grad_norm": 0.4167653024196625, "learning_rate": 7.864999999999999e-07, "loss": 0.016, "num_tokens": 105392269.0, "reward": 0.25, "reward_std": 0.2738044261932373, "rewards/simpleverify_reward/mean": 0.25, "rewards/simpleverify_reward/std": 0.434714138507843, "step": 428 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1955.0, "completions/mean_length": 1582.75, "completions/mean_terminated_length": 1264.4210205078125, "completions/min_length": 463.0, "completions/min_terminated_length": 463.0, "epoch": 0.15223562810503904, "frac_reward_zero_std": 0.3125, "grad_norm": 0.4351480007171631, "learning_rate": 7.86e-07, "loss": 0.0054, "num_tokens": 105602741.0, "reward": 0.4375, "reward_std": 0.3169426918029785, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 429 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1994.0, "completions/mean_length": 1556.6171875, "completions/mean_terminated_length": 1174.4305419921875, "completions/min_length": 479.0, "completions/min_terminated_length": 479.0, "epoch": 0.15259048970901348, "frac_reward_zero_std": 0.5, "grad_norm": 0.37416553497314453, "learning_rate": 7.854999999999999e-07, "loss": 0.0289, "num_tokens": 105813828.0, "reward": 0.3515625, "reward_std": 0.22225631773471832, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 430 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1460.8828125, "completions/mean_terminated_length": 1174.151123046875, "completions/min_length": 343.0, "completions/min_terminated_length": 343.0, "epoch": 0.15294535131298795, "frac_reward_zero_std": 0.375, "grad_norm": 0.475296288728714, "learning_rate": 7.85e-07, "loss": 0.0128, "num_tokens": 106010645.0, "reward": 0.4375, "reward_std": 0.2961388826370239, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 431 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5546875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1628.2265625, "completions/mean_terminated_length": 1105.350830078125, "completions/min_length": 236.0, "completions/min_terminated_length": 236.0, "epoch": 0.1533002129169624, "frac_reward_zero_std": 0.5, "grad_norm": 0.39187586307525635, "learning_rate": 7.845e-07, "loss": -0.0029, "num_tokens": 106229786.0, "reward": 0.234375, "reward_std": 0.22567126154899597, "rewards/simpleverify_reward/mean": 0.234375, "rewards/simpleverify_reward/std": 0.42527204751968384, "step": 432 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2018.0, "completions/mean_length": 1666.1015625, "completions/mean_terminated_length": 1175.08935546875, "completions/min_length": 391.0, "completions/min_terminated_length": 391.0, "epoch": 0.15365507452093682, "frac_reward_zero_std": 0.4375, "grad_norm": 0.3520200848579407, "learning_rate": 7.84e-07, "loss": 0.0349, "num_tokens": 106456495.0, "reward": 0.1953125, "reward_std": 0.2409384548664093, "rewards/simpleverify_reward/mean": 0.1953125, "rewards/simpleverify_reward/std": 0.3979988098144531, "step": 433 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1978.0, "completions/mean_length": 1517.5859375, "completions/mean_terminated_length": 1230.011962890625, "completions/min_length": 673.0, "completions/min_terminated_length": 673.0, "epoch": 0.1540099361249113, "frac_reward_zero_std": 0.25, "grad_norm": 0.4508194029331207, "learning_rate": 7.834999999999999e-07, "loss": 0.0279, "num_tokens": 106662258.0, "reward": 0.3828125, "reward_std": 0.3185402750968933, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 434 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1341.1484375, "completions/mean_terminated_length": 1152.1881103515625, "completions/min_length": 500.0, "completions/min_terminated_length": 500.0, "epoch": 0.15436479772888573, "frac_reward_zero_std": 0.1875, "grad_norm": 0.48595529794692993, "learning_rate": 7.83e-07, "loss": -0.0021, "num_tokens": 106843501.0, "reward": 0.5546875, "reward_std": 0.37009328603744507, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 435 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1910.0, "completions/mean_length": 1488.7265625, "completions/mean_terminated_length": 1286.4361572265625, "completions/min_length": 532.0, "completions/min_terminated_length": 532.0, "epoch": 0.1547196593328602, "frac_reward_zero_std": 0.375, "grad_norm": 0.42271578311920166, "learning_rate": 7.824999999999999e-07, "loss": 0.0268, "num_tokens": 107045114.0, "reward": 0.515625, "reward_std": 0.3027362823486328, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 436 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2015.0, "completions/mean_length": 1545.6015625, "completions/mean_terminated_length": 1263.7681884765625, "completions/min_length": 501.0, "completions/min_terminated_length": 501.0, "epoch": 0.15507452093683463, "frac_reward_zero_std": 0.3125, "grad_norm": 0.5125712156295776, "learning_rate": 7.82e-07, "loss": 0.031, "num_tokens": 107253567.0, "reward": 0.4296875, "reward_std": 0.2998581528663635, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 437 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1408.21875, "completions/mean_terminated_length": 1167.44091796875, "completions/min_length": 384.0, "completions/min_terminated_length": 384.0, "epoch": 0.1554293825408091, "frac_reward_zero_std": 0.25, "grad_norm": 0.49060505628585815, "learning_rate": 7.815e-07, "loss": 0.0156, "num_tokens": 107444195.0, "reward": 0.4375, "reward_std": 0.327729195356369, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 438 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1963.0, "completions/mean_length": 1365.8515625, "completions/mean_terminated_length": 1119.116943359375, "completions/min_length": 620.0, "completions/min_terminated_length": 620.0, "epoch": 0.15578424414478353, "frac_reward_zero_std": 0.3125, "grad_norm": 0.4787510335445404, "learning_rate": 7.81e-07, "loss": 0.0099, "num_tokens": 107630272.0, "reward": 0.5, "reward_std": 0.32719239592552185, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 439 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4765625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2005.0, "completions/mean_length": 1692.5, "completions/mean_terminated_length": 1368.8358154296875, "completions/min_length": 622.0, "completions/min_terminated_length": 622.0, "epoch": 0.15613910574875797, "frac_reward_zero_std": 0.375, "grad_norm": 0.4030400812625885, "learning_rate": 7.805e-07, "loss": 0.0099, "num_tokens": 107860632.0, "reward": 0.328125, "reward_std": 0.27328529953956604, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 440 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1976.0, "completions/mean_length": 1416.875, "completions/mean_terminated_length": 1223.6734619140625, "completions/min_length": 387.0, "completions/min_terminated_length": 387.0, "epoch": 0.15649396735273244, "frac_reward_zero_std": 0.375, "grad_norm": 0.41757169365882874, "learning_rate": 7.799999999999999e-07, "loss": 0.015, "num_tokens": 108055744.0, "reward": 0.453125, "reward_std": 0.28801077604293823, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 441 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1813.90625, "completions/mean_terminated_length": 1482.6414794921875, "completions/min_length": 621.0, "completions/min_terminated_length": 621.0, "epoch": 0.15684882895670688, "frac_reward_zero_std": 0.625, "grad_norm": 0.28534433245658875, "learning_rate": 7.794999999999999e-07, "loss": 0.0005, "num_tokens": 108299108.0, "reward": 0.2109375, "reward_std": 0.18383610248565674, "rewards/simpleverify_reward/mean": 0.2109375, "rewards/simpleverify_reward/std": 0.4095771610736847, "step": 442 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1619.5703125, "completions/mean_terminated_length": 1402.8353271484375, "completions/min_length": 677.0, "completions/min_terminated_length": 677.0, "epoch": 0.15720369056068134, "frac_reward_zero_std": 0.4375, "grad_norm": 0.37640032172203064, "learning_rate": 7.79e-07, "loss": 0.0052, "num_tokens": 108519421.0, "reward": 0.21875, "reward_std": 0.250127375125885, "rewards/simpleverify_reward/mean": 0.21875, "rewards/simpleverify_reward/std": 0.41502299904823303, "step": 443 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1655.109375, "completions/mean_terminated_length": 1223.57373046875, "completions/min_length": 517.0, "completions/min_terminated_length": 517.0, "epoch": 0.15755855216465578, "frac_reward_zero_std": 0.4375, "grad_norm": 0.4165063202381134, "learning_rate": 7.784999999999999e-07, "loss": 0.0114, "num_tokens": 108742699.0, "reward": 0.2421875, "reward_std": 0.2601397633552551, "rewards/simpleverify_reward/mean": 0.2421875, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 444 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1977.0, "completions/mean_length": 1424.2890625, "completions/mean_terminated_length": 1180.228271484375, "completions/min_length": 509.0, "completions/min_terminated_length": 509.0, "epoch": 0.15791341376863025, "frac_reward_zero_std": 0.375, "grad_norm": 0.40322747826576233, "learning_rate": 7.78e-07, "loss": 0.0326, "num_tokens": 108935344.0, "reward": 0.515625, "reward_std": 0.2959064245223999, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 445 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2007.0, "completions/mean_length": 1694.3828125, "completions/mean_terminated_length": 1351.6461181640625, "completions/min_length": 714.0, "completions/min_terminated_length": 714.0, "epoch": 0.15826827537260468, "frac_reward_zero_std": 0.3125, "grad_norm": 0.39566361904144287, "learning_rate": 7.775e-07, "loss": -0.0012, "num_tokens": 109165761.0, "reward": 0.2890625, "reward_std": 0.3237774670124054, "rewards/simpleverify_reward/mean": 0.2890625, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 446 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1714.703125, "completions/mean_terminated_length": 1324.915283203125, "completions/min_length": 717.0, "completions/min_terminated_length": 717.0, "epoch": 0.15862313697657912, "frac_reward_zero_std": 0.5625, "grad_norm": 0.32143139839172363, "learning_rate": 7.77e-07, "loss": 0.012, "num_tokens": 109397443.0, "reward": 0.359375, "reward_std": 0.17965975403785706, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 447 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1898.0, "completions/mean_length": 1564.59375, "completions/mean_terminated_length": 1222.9866943359375, "completions/min_length": 555.0, "completions/min_terminated_length": 555.0, "epoch": 0.1589779985805536, "frac_reward_zero_std": 0.4375, "grad_norm": 0.4040890336036682, "learning_rate": 7.764999999999999e-07, "loss": 0.0195, "num_tokens": 109609071.0, "reward": 0.359375, "reward_std": 0.27722427248954773, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 448 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2010.0, "completions/mean_length": 1585.7890625, "completions/mean_terminated_length": 1317.5926513671875, "completions/min_length": 649.0, "completions/min_terminated_length": 649.0, "epoch": 0.15933286018452802, "frac_reward_zero_std": 0.375, "grad_norm": 0.37511393427848816, "learning_rate": 7.76e-07, "loss": 0.0278, "num_tokens": 109822700.0, "reward": 0.4140625, "reward_std": 0.2869499623775482, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 449 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1999.0, "completions/mean_length": 1260.484375, "completions/mean_terminated_length": 1078.75, "completions/min_length": 241.0, "completions/min_terminated_length": 241.0, "epoch": 0.1596877217885025, "frac_reward_zero_std": 0.375, "grad_norm": 0.6030889749526978, "learning_rate": 7.754999999999999e-07, "loss": 0.0145, "num_tokens": 109994490.0, "reward": 0.5625, "reward_std": 0.2585597634315491, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 450 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2000.0, "completions/mean_length": 1639.5546875, "completions/mean_terminated_length": 1331.8218994140625, "completions/min_length": 643.0, "completions/min_terminated_length": 643.0, "epoch": 0.16004258339247693, "frac_reward_zero_std": 0.375, "grad_norm": 0.42923861742019653, "learning_rate": 7.75e-07, "loss": -0.0055, "num_tokens": 110214977.0, "reward": 0.3203125, "reward_std": 0.28247418999671936, "rewards/simpleverify_reward/mean": 0.3203125, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 451 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5, "completions/max_length": 2048.0, "completions/max_terminated_length": 2006.0, "completions/mean_length": 1722.4609375, "completions/mean_terminated_length": 1396.921875, "completions/min_length": 557.0, "completions/min_terminated_length": 557.0, "epoch": 0.1603974449964514, "frac_reward_zero_std": 0.3125, "grad_norm": 0.37717944383621216, "learning_rate": 7.745e-07, "loss": 0.0286, "num_tokens": 110447124.0, "reward": 0.3515625, "reward_std": 0.30115634202957153, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 452 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1477.1015625, "completions/mean_terminated_length": 1123.0, "completions/min_length": 306.0, "completions/min_terminated_length": 306.0, "epoch": 0.16075230660042583, "frac_reward_zero_std": 0.625, "grad_norm": 0.40610337257385254, "learning_rate": 7.74e-07, "loss": 0.0081, "num_tokens": 110649001.0, "reward": 0.2421875, "reward_std": 0.1814819872379303, "rewards/simpleverify_reward/mean": 0.2421875, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 453 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1329.21875, "completions/mean_terminated_length": 1233.8052978515625, "completions/min_length": 478.0, "completions/min_terminated_length": 478.0, "epoch": 0.1611071682044003, "frac_reward_zero_std": 0.25, "grad_norm": 0.47952648997306824, "learning_rate": 7.734999999999999e-07, "loss": 0.0039, "num_tokens": 110828741.0, "reward": 0.390625, "reward_std": 0.33797892928123474, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 454 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1618.71875, "completions/mean_terminated_length": 1263.028564453125, "completions/min_length": 582.0, "completions/min_terminated_length": 582.0, "epoch": 0.16146202980837474, "frac_reward_zero_std": 0.5, "grad_norm": 0.4021058678627014, "learning_rate": 7.729999999999999e-07, "loss": 0.0063, "num_tokens": 111048745.0, "reward": 0.3203125, "reward_std": 0.2280302792787552, "rewards/simpleverify_reward/mean": 0.3203125, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 455 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1932.0, "completions/mean_length": 1510.40625, "completions/mean_terminated_length": 1005.3939819335938, "completions/min_length": 468.0, "completions/min_terminated_length": 468.0, "epoch": 0.16181689141234917, "frac_reward_zero_std": 0.5, "grad_norm": 0.4265432357788086, "learning_rate": 7.724999999999999e-07, "loss": -0.0099, "num_tokens": 111252261.0, "reward": 0.3515625, "reward_std": 0.20858673751354218, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 456 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2021.0, "completions/mean_length": 1618.9765625, "completions/mean_terminated_length": 1263.5, "completions/min_length": 428.0, "completions/min_terminated_length": 428.0, "epoch": 0.16217175301632364, "frac_reward_zero_std": 0.25, "grad_norm": 0.4886038303375244, "learning_rate": 7.72e-07, "loss": 0.0168, "num_tokens": 111469498.0, "reward": 0.5, "reward_std": 0.33008331060409546, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 457 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2018.0, "completions/mean_length": 1685.4765625, "completions/mean_terminated_length": 1375.4927978515625, "completions/min_length": 716.0, "completions/min_terminated_length": 716.0, "epoch": 0.16252661462029808, "frac_reward_zero_std": 0.375, "grad_norm": 0.35268843173980713, "learning_rate": 7.714999999999999e-07, "loss": 0.0311, "num_tokens": 111696503.0, "reward": 0.34375, "reward_std": 0.30168038606643677, "rewards/simpleverify_reward/mean": 0.34375, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 458 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1489.28125, "completions/mean_terminated_length": 1225.97705078125, "completions/min_length": 414.0, "completions/min_terminated_length": 414.0, "epoch": 0.16288147622427254, "frac_reward_zero_std": 0.4375, "grad_norm": 0.44222548604011536, "learning_rate": 7.71e-07, "loss": 0.0224, "num_tokens": 111898139.0, "reward": 0.3515625, "reward_std": 0.2396402657032013, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 459 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1392.65625, "completions/mean_terminated_length": 1105.483154296875, "completions/min_length": 453.0, "completions/min_terminated_length": 453.0, "epoch": 0.16323633782824698, "frac_reward_zero_std": 0.5, "grad_norm": 0.40310531854629517, "learning_rate": 7.705e-07, "loss": 0.0147, "num_tokens": 112087863.0, "reward": 0.5859375, "reward_std": 0.228030264377594, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 460 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1749.359375, "completions/mean_terminated_length": 1450.71875, "completions/min_length": 827.0, "completions/min_terminated_length": 827.0, "epoch": 0.16359119943222145, "frac_reward_zero_std": 0.375, "grad_norm": 0.37669849395751953, "learning_rate": 7.699999999999999e-07, "loss": 0.0202, "num_tokens": 112321853.0, "reward": 0.3359375, "reward_std": 0.2969672679901123, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 461 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.53125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1940.0, "completions/mean_length": 1689.828125, "completions/mean_terminated_length": 1283.9000244140625, "completions/min_length": 653.0, "completions/min_terminated_length": 653.0, "epoch": 0.16394606103619588, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3216113746166229, "learning_rate": 7.694999999999999e-07, "loss": 0.0015, "num_tokens": 112549439.0, "reward": 0.3046875, "reward_std": 0.19332444667816162, "rewards/simpleverify_reward/mean": 0.3046875, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 462 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.59375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1702.3515625, "completions/mean_terminated_length": 1197.173095703125, "completions/min_length": 524.0, "completions/min_terminated_length": 524.0, "epoch": 0.16430092264017032, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3634297847747803, "learning_rate": 7.69e-07, "loss": 0.0156, "num_tokens": 112777876.0, "reward": 0.25, "reward_std": 0.18990948796272278, "rewards/simpleverify_reward/mean": 0.25, "rewards/simpleverify_reward/std": 0.434714138507843, "step": 463 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1404.9921875, "completions/mean_terminated_length": 1068.1785888671875, "completions/min_length": 450.0, "completions/min_terminated_length": 450.0, "epoch": 0.1646557842441448, "frac_reward_zero_std": 0.5625, "grad_norm": 0.43694406747817993, "learning_rate": 7.684999999999999e-07, "loss": -0.007, "num_tokens": 112976347.0, "reward": 0.5234375, "reward_std": 0.21276798844337463, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 464 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1882.0, "completions/mean_length": 1529.6015625, "completions/mean_terminated_length": 1197.294921875, "completions/min_length": 524.0, "completions/min_terminated_length": 524.0, "epoch": 0.16501064584811923, "frac_reward_zero_std": 0.5, "grad_norm": 0.4123513400554657, "learning_rate": 7.68e-07, "loss": -0.0004, "num_tokens": 113184760.0, "reward": 0.421875, "reward_std": 0.20517179369926453, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 465 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1708.703125, "completions/mean_terminated_length": 1389.9697265625, "completions/min_length": 494.0, "completions/min_terminated_length": 494.0, "epoch": 0.1653655074520937, "frac_reward_zero_std": 0.375, "grad_norm": 0.42042210698127747, "learning_rate": 7.675e-07, "loss": 0.0086, "num_tokens": 113414898.0, "reward": 0.3984375, "reward_std": 0.3050953149795532, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 466 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1628.484375, "completions/mean_terminated_length": 1291.6900634765625, "completions/min_length": 422.0, "completions/min_terminated_length": 422.0, "epoch": 0.16572036905606813, "frac_reward_zero_std": 0.625, "grad_norm": 0.3597731292247772, "learning_rate": 7.67e-07, "loss": 0.0053, "num_tokens": 113634064.0, "reward": 0.46875, "reward_std": 0.17464719712734222, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 467 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1355.359375, "completions/mean_terminated_length": 1187.24267578125, "completions/min_length": 475.0, "completions/min_terminated_length": 475.0, "epoch": 0.1660752306600426, "frac_reward_zero_std": 0.3125, "grad_norm": 0.4909055531024933, "learning_rate": 7.664999999999999e-07, "loss": 0.0215, "num_tokens": 113817982.0, "reward": 0.4921875, "reward_std": 0.30798622965812683, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 468 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1555.5859375, "completions/mean_terminated_length": 1279.3536376953125, "completions/min_length": 684.0, "completions/min_terminated_length": 684.0, "epoch": 0.16643009226401703, "frac_reward_zero_std": 0.5, "grad_norm": 0.3711403012275696, "learning_rate": 7.66e-07, "loss": 0.0129, "num_tokens": 114028865.0, "reward": 0.3125, "reward_std": 0.22803518176078796, "rewards/simpleverify_reward/mean": 0.3125, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 469 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1671.9140625, "completions/mean_terminated_length": 1379.40283203125, "completions/min_length": 574.0, "completions/min_terminated_length": 574.0, "epoch": 0.16678495386799147, "frac_reward_zero_std": 0.375, "grad_norm": 0.41401010751724243, "learning_rate": 7.654999999999999e-07, "loss": 0.0169, "num_tokens": 114257414.0, "reward": 0.3828125, "reward_std": 0.2935473918914795, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 470 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1516.328125, "completions/mean_terminated_length": 1218.0731201171875, "completions/min_length": 328.0, "completions/min_terminated_length": 328.0, "epoch": 0.16713981547196594, "frac_reward_zero_std": 0.5, "grad_norm": 0.43500375747680664, "learning_rate": 7.65e-07, "loss": 0.0049, "num_tokens": 114460112.0, "reward": 0.3671875, "reward_std": 0.19728106260299683, "rewards/simpleverify_reward/mean": 0.3671875, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 471 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1959.0, "completions/mean_length": 1494.75, "completions/mean_terminated_length": 1162.800048828125, "completions/min_length": 543.0, "completions/min_terminated_length": 543.0, "epoch": 0.16749467707594037, "frac_reward_zero_std": 0.3125, "grad_norm": 0.48275867104530334, "learning_rate": 7.644999999999999e-07, "loss": -0.0162, "num_tokens": 114664488.0, "reward": 0.3359375, "reward_std": 0.2896084189414978, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 472 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1916.0, "completions/mean_length": 1472.6484375, "completions/mean_terminated_length": 1138.802490234375, "completions/min_length": 660.0, "completions/min_terminated_length": 660.0, "epoch": 0.16784953867991484, "frac_reward_zero_std": 0.5, "grad_norm": 0.45186132192611694, "learning_rate": 7.64e-07, "loss": 0.0219, "num_tokens": 114865803.0, "reward": 0.515625, "reward_std": 0.2109457552433014, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 473 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1619.625, "completions/mean_terminated_length": 1353.924072265625, "completions/min_length": 699.0, "completions/min_terminated_length": 699.0, "epoch": 0.16820440028388928, "frac_reward_zero_std": 0.1875, "grad_norm": 0.41866376996040344, "learning_rate": 7.635e-07, "loss": 0.0082, "num_tokens": 115084099.0, "reward": 0.40625, "reward_std": 0.36113685369491577, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 474 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1674.8828125, "completions/mean_terminated_length": 1324.3787841796875, "completions/min_length": 518.0, "completions/min_terminated_length": 518.0, "epoch": 0.16855926188786374, "frac_reward_zero_std": 0.3125, "grad_norm": 0.412737637758255, "learning_rate": 7.629999999999999e-07, "loss": 0.0291, "num_tokens": 115308500.0, "reward": 0.4296875, "reward_std": 0.2909066081047058, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 475 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1463.3125, "completions/mean_terminated_length": 1088.5128173828125, "completions/min_length": 401.0, "completions/min_terminated_length": 401.0, "epoch": 0.16891412349183818, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3758375346660614, "learning_rate": 7.624999999999999e-07, "loss": 0.0117, "num_tokens": 115506676.0, "reward": 0.3671875, "reward_std": 0.19674429297447205, "rewards/simpleverify_reward/mean": 0.3671875, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 476 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1564.5078125, "completions/mean_terminated_length": 1283.9630126953125, "completions/min_length": 547.0, "completions/min_terminated_length": 547.0, "epoch": 0.16926898509581265, "frac_reward_zero_std": 0.4375, "grad_norm": 0.47250643372535706, "learning_rate": 7.62e-07, "loss": 0.0303, "num_tokens": 115719125.0, "reward": 0.4609375, "reward_std": 0.22621294856071472, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 477 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1386.1171875, "completions/mean_terminated_length": 1137.021484375, "completions/min_length": 264.0, "completions/min_terminated_length": 264.0, "epoch": 0.16962384669978708, "frac_reward_zero_std": 0.4375, "grad_norm": 0.4140004813671112, "learning_rate": 7.614999999999999e-07, "loss": 0.0269, "num_tokens": 115906556.0, "reward": 0.4453125, "reward_std": 0.2672119140625, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 478 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2005.0, "completions/mean_length": 1563.7265625, "completions/mean_terminated_length": 1343.602294921875, "completions/min_length": 601.0, "completions/min_terminated_length": 601.0, "epoch": 0.16997870830376152, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3180043399333954, "learning_rate": 7.61e-07, "loss": -0.011, "num_tokens": 116117953.0, "reward": 0.4375, "reward_std": 0.18990948796272278, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 479 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1494.390625, "completions/mean_terminated_length": 1151.0126953125, "completions/min_length": 531.0, "completions/min_terminated_length": 531.0, "epoch": 0.170333569907736, "frac_reward_zero_std": 0.4375, "grad_norm": 0.39127129316329956, "learning_rate": 7.605e-07, "loss": 0.0378, "num_tokens": 116322067.0, "reward": 0.4765625, "reward_std": 0.21937325596809387, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 480 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1535.6953125, "completions/mean_terminated_length": 1217.936767578125, "completions/min_length": 392.0, "completions/min_terminated_length": 392.0, "epoch": 0.17068843151171043, "frac_reward_zero_std": 0.5, "grad_norm": 0.43266892433166504, "learning_rate": 7.599999999999999e-07, "loss": 0.0001, "num_tokens": 116529772.0, "reward": 0.3984375, "reward_std": 0.23250606656074524, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 481 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1614.0546875, "completions/mean_terminated_length": 1166.3333740234375, "completions/min_length": 419.0, "completions/min_terminated_length": 419.0, "epoch": 0.1710432931156849, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3307344913482666, "learning_rate": 7.594999999999999e-07, "loss": 0.0032, "num_tokens": 116749987.0, "reward": 0.3671875, "reward_std": 0.20357416570186615, "rewards/simpleverify_reward/mean": 0.3671875, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 482 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1417.6015625, "completions/mean_terminated_length": 1170.9239501953125, "completions/min_length": 643.0, "completions/min_terminated_length": 643.0, "epoch": 0.17139815471965933, "frac_reward_zero_std": 0.3125, "grad_norm": 0.4515925645828247, "learning_rate": 7.59e-07, "loss": 0.011, "num_tokens": 116942048.0, "reward": 0.3125, "reward_std": 0.30221715569496155, "rewards/simpleverify_reward/mean": 0.3125, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 483 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1989.0, "completions/mean_length": 1494.0859375, "completions/mean_terminated_length": 1115.0921630859375, "completions/min_length": 397.0, "completions/min_terminated_length": 397.0, "epoch": 0.1717530163236338, "frac_reward_zero_std": 0.4375, "grad_norm": 0.4055440127849579, "learning_rate": 7.584999999999999e-07, "loss": -0.0132, "num_tokens": 117142859.0, "reward": 0.328125, "reward_std": 0.2432974874973297, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 484 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5, "completions/max_length": 2048.0, "completions/max_terminated_length": 2007.0, "completions/mean_length": 1681.8046875, "completions/mean_terminated_length": 1315.609375, "completions/min_length": 585.0, "completions/min_terminated_length": 585.0, "epoch": 0.17210787792760823, "frac_reward_zero_std": 0.4375, "grad_norm": 0.43010595440864563, "learning_rate": 7.58e-07, "loss": 0.0174, "num_tokens": 117369890.0, "reward": 0.203125, "reward_std": 0.250127375125885, "rewards/simpleverify_reward/mean": 0.203125, "rewards/simpleverify_reward/std": 0.40390563011169434, "step": 485 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1612.7109375, "completions/mean_terminated_length": 1376.7108154296875, "completions/min_length": 727.0, "completions/min_terminated_length": 727.0, "epoch": 0.17246273953158267, "frac_reward_zero_std": 0.1875, "grad_norm": 0.437628835439682, "learning_rate": 7.575e-07, "loss": 0.0152, "num_tokens": 117586821.0, "reward": 0.3671875, "reward_std": 0.3771556317806244, "rewards/simpleverify_reward/mean": 0.3671875, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 486 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1894.0, "completions/mean_length": 1730.890625, "completions/mean_terminated_length": 1184.3829345703125, "completions/min_length": 634.0, "completions/min_terminated_length": 634.0, "epoch": 0.17281760113555714, "frac_reward_zero_std": 0.5625, "grad_norm": 0.31768760085105896, "learning_rate": 7.57e-07, "loss": 0.0169, "num_tokens": 117819487.0, "reward": 0.2734375, "reward_std": 0.1922685205936432, "rewards/simpleverify_reward/mean": 0.2734375, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 487 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1995.0, "completions/mean_length": 1476.265625, "completions/mean_terminated_length": 1216.3863525390625, "completions/min_length": 459.0, "completions/min_terminated_length": 459.0, "epoch": 0.17317246273953157, "frac_reward_zero_std": 0.25, "grad_norm": 0.4826831519603729, "learning_rate": 7.564999999999999e-07, "loss": 0.0148, "num_tokens": 118021233.0, "reward": 0.421875, "reward_std": 0.3606000542640686, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 488 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.59375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1812.9375, "completions/mean_terminated_length": 1469.3846435546875, "completions/min_length": 743.0, "completions/min_terminated_length": 743.0, "epoch": 0.17352732434350604, "frac_reward_zero_std": 0.25, "grad_norm": 0.4291941225528717, "learning_rate": 7.559999999999999e-07, "loss": 0.0288, "num_tokens": 118267097.0, "reward": 0.2421875, "reward_std": 0.3527093529701233, "rewards/simpleverify_reward/mean": 0.2421875, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 489 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1962.0, "completions/mean_length": 1538.8359375, "completions/mean_terminated_length": 1142.8194580078125, "completions/min_length": 480.0, "completions/min_terminated_length": 480.0, "epoch": 0.17388218594748048, "frac_reward_zero_std": 0.5, "grad_norm": 0.42561638355255127, "learning_rate": 7.554999999999999e-07, "loss": 0.0001, "num_tokens": 118474196.0, "reward": 0.234375, "reward_std": 0.2380426526069641, "rewards/simpleverify_reward/mean": 0.234375, "rewards/simpleverify_reward/std": 0.42527204751968384, "step": 490 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1642.796875, "completions/mean_terminated_length": 1237.59375, "completions/min_length": 545.0, "completions/min_terminated_length": 545.0, "epoch": 0.17423704755145494, "frac_reward_zero_std": 0.4375, "grad_norm": 0.40740466117858887, "learning_rate": 7.55e-07, "loss": 0.0185, "num_tokens": 118696626.0, "reward": 0.34375, "reward_std": 0.22962787747383118, "rewards/simpleverify_reward/mean": 0.34375, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 491 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1419.390625, "completions/mean_terminated_length": 989.2894897460938, "completions/min_length": 505.0, "completions/min_terminated_length": 505.0, "epoch": 0.17459190915542938, "frac_reward_zero_std": 0.625, "grad_norm": 0.3353428542613983, "learning_rate": 7.544999999999999e-07, "loss": 0.0017, "num_tokens": 118888364.0, "reward": 0.421875, "reward_std": 0.16097761690616608, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 492 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1355.5703125, "completions/mean_terminated_length": 1170.46533203125, "completions/min_length": 489.0, "completions/min_terminated_length": 489.0, "epoch": 0.17494677075940382, "frac_reward_zero_std": 0.4375, "grad_norm": 0.4684803783893585, "learning_rate": 7.54e-07, "loss": 0.0053, "num_tokens": 119071557.0, "reward": 0.59375, "reward_std": 0.250127375125885, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 493 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2021.0, "completions/mean_length": 1256.1796875, "completions/mean_terminated_length": 992.2396240234375, "completions/min_length": 550.0, "completions/min_terminated_length": 550.0, "epoch": 0.17530163236337828, "frac_reward_zero_std": 0.5625, "grad_norm": 0.3778371214866638, "learning_rate": 7.535e-07, "loss": 0.0023, "num_tokens": 119244556.0, "reward": 0.609375, "reward_std": 0.19568344950675964, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 494 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1964.0, "completions/mean_length": 1381.4453125, "completions/mean_terminated_length": 1110.4285888671875, "completions/min_length": 415.0, "completions/min_terminated_length": 415.0, "epoch": 0.17565649396735272, "frac_reward_zero_std": 0.4375, "grad_norm": 0.4325321614742279, "learning_rate": 7.529999999999999e-07, "loss": -0.0019, "num_tokens": 119431133.0, "reward": 0.59375, "reward_std": 0.23752352595329285, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 495 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2022.0, "completions/mean_length": 1381.8515625, "completions/mean_terminated_length": 1067.9195556640625, "completions/min_length": 523.0, "completions/min_terminated_length": 523.0, "epoch": 0.1760113555713272, "frac_reward_zero_std": 0.4375, "grad_norm": 0.42573803663253784, "learning_rate": 7.524999999999999e-07, "loss": -0.004, "num_tokens": 119616226.0, "reward": 0.4375, "reward_std": 0.25460314750671387, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 496 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1530.8125, "completions/mean_terminated_length": 1141.150634765625, "completions/min_length": 450.0, "completions/min_terminated_length": 450.0, "epoch": 0.17636621717530163, "frac_reward_zero_std": 0.5, "grad_norm": 0.4494895339012146, "learning_rate": 7.52e-07, "loss": 0.0282, "num_tokens": 119823450.0, "reward": 0.28125, "reward_std": 0.22119548916816711, "rewards/simpleverify_reward/mean": 0.28125, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 497 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1396.6953125, "completions/mean_terminated_length": 1100.647705078125, "completions/min_length": 482.0, "completions/min_terminated_length": 482.0, "epoch": 0.1767210787792761, "frac_reward_zero_std": 0.5, "grad_norm": 0.41927075386047363, "learning_rate": 7.514999999999999e-07, "loss": -0.0049, "num_tokens": 120012451.0, "reward": 0.4140625, "reward_std": 0.22225633263587952, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 498 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1412.359375, "completions/mean_terminated_length": 1191.5579833984375, "completions/min_length": 481.0, "completions/min_terminated_length": 481.0, "epoch": 0.17707594038325053, "frac_reward_zero_std": 0.375, "grad_norm": 0.46326249837875366, "learning_rate": 7.51e-07, "loss": 0.0669, "num_tokens": 120203921.0, "reward": 0.5, "reward_std": 0.3040344715118408, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 499 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2003.0, "completions/mean_length": 1541.546875, "completions/mean_terminated_length": 1276.261962890625, "completions/min_length": 396.0, "completions/min_terminated_length": 396.0, "epoch": 0.177430801987225, "frac_reward_zero_std": 0.375, "grad_norm": 0.47457200288772583, "learning_rate": 7.505e-07, "loss": 0.0145, "num_tokens": 120411887.0, "reward": 0.3359375, "reward_std": 0.2948455810546875, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 500 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1391.1328125, "completions/mean_terminated_length": 1207.2099609375, "completions/min_length": 486.0, "completions/min_terminated_length": 486.0, "epoch": 0.08889480338013174, "frac_reward_zero_std": 0.25, "grad_norm": 0.5155197381973267, "learning_rate": 7.5e-07, "loss": 0.0027, "num_tokens": 120600272.0, "reward": 0.5234375, "reward_std": 0.3416230380535126, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 501 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1382.171875, "completions/mean_terminated_length": 1228.519287109375, "completions/min_length": 484.0, "completions/min_terminated_length": 484.0, "epoch": 0.08907223811741743, "frac_reward_zero_std": 0.125, "grad_norm": 0.6141640543937683, "learning_rate": 7.495e-07, "loss": 0.0061, "num_tokens": 120787510.0, "reward": 0.5078125, "reward_std": 0.37305837869644165, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 502 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2007.0, "completions/mean_length": 1386.5703125, "completions/mean_terminated_length": 1156.810546875, "completions/min_length": 434.0, "completions/min_terminated_length": 434.0, "epoch": 0.08924967285470313, "frac_reward_zero_std": 0.125, "grad_norm": 0.630131721496582, "learning_rate": 7.489999999999999e-07, "loss": 0.0021, "num_tokens": 120975311.0, "reward": 0.4765625, "reward_std": 0.35232165455818176, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 503 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2006.0, "completions/mean_length": 1403.3984375, "completions/mean_terminated_length": 1206.0714111328125, "completions/min_length": 520.0, "completions/min_terminated_length": 520.0, "epoch": 0.08942710759198882, "frac_reward_zero_std": 0.125, "grad_norm": 0.5015130639076233, "learning_rate": 7.485e-07, "loss": -0.0097, "num_tokens": 121165266.0, "reward": 0.5625, "reward_std": 0.34351080656051636, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 504 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1382.53125, "completions/mean_terminated_length": 1178.8162841796875, "completions/min_length": 460.0, "completions/min_terminated_length": 460.0, "epoch": 0.08960454232927452, "frac_reward_zero_std": 0.125, "grad_norm": 0.5133466720581055, "learning_rate": 7.48e-07, "loss": 0.0025, "num_tokens": 121351702.0, "reward": 0.4453125, "reward_std": 0.3576752543449402, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 505 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1378.515625, "completions/mean_terminated_length": 1126.55908203125, "completions/min_length": 457.0, "completions/min_terminated_length": 457.0, "epoch": 0.0897819770665602, "frac_reward_zero_std": 0.125, "grad_norm": 0.5015819072723389, "learning_rate": 7.475e-07, "loss": 0.0184, "num_tokens": 121537624.0, "reward": 0.546875, "reward_std": 0.345456600189209, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 506 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1379.2578125, "completions/mean_terminated_length": 1137.372314453125, "completions/min_length": 473.0, "completions/min_terminated_length": 473.0, "epoch": 0.0899594118038459, "frac_reward_zero_std": 0.125, "grad_norm": 0.5481694340705872, "learning_rate": 7.47e-07, "loss": 0.0073, "num_tokens": 121723641.0, "reward": 0.4609375, "reward_std": 0.35892558097839355, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 507 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1365.15625, "completions/mean_terminated_length": 1156.1224365234375, "completions/min_length": 418.0, "completions/min_terminated_length": 418.0, "epoch": 0.09013684654113159, "frac_reward_zero_std": 0.125, "grad_norm": 0.5568780899047852, "learning_rate": 7.465e-07, "loss": 0.014, "num_tokens": 121907853.0, "reward": 0.5546875, "reward_std": 0.3703433871269226, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 508 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1957.0, "completions/mean_length": 1268.4453125, "completions/mean_terminated_length": 963.4022216796875, "completions/min_length": 332.0, "completions/min_terminated_length": 332.0, "epoch": 0.09031428127841729, "frac_reward_zero_std": 0.375, "grad_norm": 0.5088124871253967, "learning_rate": 7.459999999999999e-07, "loss": 0.025, "num_tokens": 122079334.0, "reward": 0.5859375, "reward_std": 0.27707332372665405, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 509 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1216.1875, "completions/mean_terminated_length": 961.551025390625, "completions/min_length": 306.0, "completions/min_terminated_length": 306.0, "epoch": 0.09049171601570298, "frac_reward_zero_std": 0.5, "grad_norm": 0.5786054134368896, "learning_rate": 7.455e-07, "loss": 0.0121, "num_tokens": 122244126.0, "reward": 0.609375, "reward_std": 0.20868882536888123, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 510 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1969.0, "completions/mean_length": 1220.3359375, "completions/mean_terminated_length": 977.888916015625, "completions/min_length": 297.0, "completions/min_terminated_length": 297.0, "epoch": 0.09066915075298866, "frac_reward_zero_std": 0.5, "grad_norm": 0.39323121309280396, "learning_rate": 7.45e-07, "loss": 0.0188, "num_tokens": 122409449.0, "reward": 0.6171875, "reward_std": 0.20555339753627777, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 511 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2007.0, "completions/mean_length": 1219.484375, "completions/mean_terminated_length": 976.7879028320312, "completions/min_length": 310.0, "completions/min_terminated_length": 310.0, "epoch": 0.09084658549027436, "frac_reward_zero_std": 0.5, "grad_norm": 0.3840543031692505, "learning_rate": 7.445e-07, "loss": 0.0119, "num_tokens": 122574663.0, "reward": 0.6171875, "reward_std": 0.21547812223434448, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 512 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1775.328125, "completions/mean_terminated_length": 1401.6666259765625, "completions/min_length": 697.0, "completions/min_terminated_length": 697.0, "epoch": 0.09102402022756005, "frac_reward_zero_std": 0.25, "grad_norm": 0.44411173462867737, "learning_rate": 7.44e-07, "loss": -0.0106, "num_tokens": 122815921.0, "reward": 0.2109375, "reward_std": 0.3034759759902954, "rewards/simpleverify_reward/mean": 0.2109375, "rewards/simpleverify_reward/std": 0.4095771610736847, "step": 513 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1690.984375, "completions/mean_terminated_length": 1344.953857421875, "completions/min_length": 673.0, "completions/min_terminated_length": 673.0, "epoch": 0.09120145496484575, "frac_reward_zero_std": 0.375, "grad_norm": 0.40744781494140625, "learning_rate": 7.435000000000001e-07, "loss": -0.0039, "num_tokens": 123046383.0, "reward": 0.2265625, "reward_std": 0.26115670800209045, "rewards/simpleverify_reward/mean": 0.2265625, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 514 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5546875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1722.2265625, "completions/mean_terminated_length": 1316.4385986328125, "completions/min_length": 731.0, "completions/min_terminated_length": 731.0, "epoch": 0.09137888970213144, "frac_reward_zero_std": 0.375, "grad_norm": 0.48088568449020386, "learning_rate": 7.429999999999999e-07, "loss": -0.004, "num_tokens": 123280844.0, "reward": 0.2578125, "reward_std": 0.27946737408638, "rewards/simpleverify_reward/mean": 0.2578125, "rewards/simpleverify_reward/std": 0.43914902210235596, "step": 515 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1770.328125, "completions/mean_terminated_length": 1351.09814453125, "completions/min_length": 846.0, "completions/min_terminated_length": 846.0, "epoch": 0.09155632443941712, "frac_reward_zero_std": 0.375, "grad_norm": 0.43115273118019104, "learning_rate": 7.425e-07, "loss": -0.0067, "num_tokens": 123521462.0, "reward": 0.2421875, "reward_std": 0.26613396406173706, "rewards/simpleverify_reward/mean": 0.2421875, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 516 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1825.0, "completions/mean_length": 1374.921875, "completions/mean_terminated_length": 1057.72412109375, "completions/min_length": 514.0, "completions/min_terminated_length": 514.0, "epoch": 0.09173375917670282, "frac_reward_zero_std": 0.25, "grad_norm": 0.5580482482910156, "learning_rate": 7.42e-07, "loss": 0.0014, "num_tokens": 123708716.0, "reward": 0.46875, "reward_std": 0.3255210816860199, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 517 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1363.1484375, "completions/mean_terminated_length": 1084.6923828125, "completions/min_length": 586.0, "completions/min_terminated_length": 586.0, "epoch": 0.09191119391398851, "frac_reward_zero_std": 0.25, "grad_norm": 0.5148314833641052, "learning_rate": 7.415e-07, "loss": 0.014, "num_tokens": 123894463.0, "reward": 0.46875, "reward_std": 0.2849799394607544, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 518 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2013.0, "completions/mean_length": 1332.3984375, "completions/mean_terminated_length": 1073.5638427734375, "completions/min_length": 595.0, "completions/min_terminated_length": 595.0, "epoch": 0.0920886286512742, "frac_reward_zero_std": 0.25, "grad_norm": 0.939701497554779, "learning_rate": 7.41e-07, "loss": 0.0169, "num_tokens": 124076274.0, "reward": 0.4453125, "reward_std": 0.28548625111579895, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 519 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1982.0, "completions/mean_length": 1362.4453125, "completions/mean_terminated_length": 1083.703369140625, "completions/min_length": 464.0, "completions/min_terminated_length": 464.0, "epoch": 0.0922660633885599, "frac_reward_zero_std": 0.125, "grad_norm": 0.5659785270690918, "learning_rate": 7.405e-07, "loss": 0.0067, "num_tokens": 124261931.0, "reward": 0.4453125, "reward_std": 0.3320651650428772, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 520 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1096.46875, "completions/mean_terminated_length": 940.7636108398438, "completions/min_length": 318.0, "completions/min_terminated_length": 318.0, "epoch": 0.09244349812584558, "frac_reward_zero_std": 0.0, "grad_norm": 0.789027750492096, "learning_rate": 7.4e-07, "loss": -0.0049, "num_tokens": 124411575.0, "reward": 0.5859375, "reward_std": 0.4208405315876007, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 521 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2022.0, "completions/mean_length": 1146.2265625, "completions/mean_terminated_length": 959.0660400390625, "completions/min_length": 341.0, "completions/min_terminated_length": 341.0, "epoch": 0.09262093286313128, "frac_reward_zero_std": 0.0, "grad_norm": 0.7315119504928589, "learning_rate": 7.395e-07, "loss": 0.0156, "num_tokens": 124567588.0, "reward": 0.6171875, "reward_std": 0.40665391087532043, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 522 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1116.65625, "completions/mean_terminated_length": 933.869140625, "completions/min_length": 334.0, "completions/min_terminated_length": 334.0, "epoch": 0.09279836760041697, "frac_reward_zero_std": 0.0, "grad_norm": 0.683813750743866, "learning_rate": 7.389999999999999e-07, "loss": -0.004, "num_tokens": 124719816.0, "reward": 0.6015625, "reward_std": 0.3501671254634857, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 523 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1105.96875, "completions/mean_terminated_length": 941.7614135742188, "completions/min_length": 340.0, "completions/min_terminated_length": 340.0, "epoch": 0.09297580233770267, "frac_reward_zero_std": 0.125, "grad_norm": 0.6708394885063171, "learning_rate": 7.385e-07, "loss": 0.0121, "num_tokens": 124870676.0, "reward": 0.6171875, "reward_std": 0.3281818628311157, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 524 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1959.0, "completions/mean_length": 1419.34375, "completions/mean_terminated_length": 1101.317626953125, "completions/min_length": 403.0, "completions/min_terminated_length": 403.0, "epoch": 0.09315323707498836, "frac_reward_zero_std": 0.375, "grad_norm": 0.5037345290184021, "learning_rate": 7.38e-07, "loss": 0.0248, "num_tokens": 125063520.0, "reward": 0.5078125, "reward_std": 0.3149757981300354, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 525 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1430.0078125, "completions/mean_terminated_length": 1169.0777587890625, "completions/min_length": 398.0, "completions/min_terminated_length": 398.0, "epoch": 0.09333067181227404, "frac_reward_zero_std": 0.125, "grad_norm": 0.5477482080459595, "learning_rate": 7.375e-07, "loss": 0.0313, "num_tokens": 125257729.0, "reward": 0.515625, "reward_std": 0.3805084824562073, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 526 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1995.0, "completions/mean_length": 1423.203125, "completions/mean_terminated_length": 1107.12939453125, "completions/min_length": 370.0, "completions/min_terminated_length": 370.0, "epoch": 0.09350810654955974, "frac_reward_zero_std": 0.25, "grad_norm": 0.4826931357383728, "learning_rate": 7.37e-07, "loss": 0.0161, "num_tokens": 125451067.0, "reward": 0.5, "reward_std": 0.3474799394607544, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 527 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1985.0, "completions/mean_length": 1429.984375, "completions/mean_terminated_length": 1117.3411865234375, "completions/min_length": 382.0, "completions/min_terminated_length": 382.0, "epoch": 0.09368554128684543, "frac_reward_zero_std": 0.125, "grad_norm": 0.5008958578109741, "learning_rate": 7.365e-07, "loss": 0.0241, "num_tokens": 125645273.0, "reward": 0.4765625, "reward_std": 0.38751477003097534, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 528 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1944.0, "completions/mean_length": 1656.0078125, "completions/mean_terminated_length": 1152.0179443359375, "completions/min_length": 343.0, "completions/min_terminated_length": 343.0, "epoch": 0.09386297602413113, "frac_reward_zero_std": 0.5, "grad_norm": 0.4440796375274658, "learning_rate": 7.359999999999999e-07, "loss": 0.0071, "num_tokens": 125869994.0, "reward": 0.2421875, "reward_std": 0.21023227274417877, "rewards/simpleverify_reward/mean": 0.2421875, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 529 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1650.7890625, "completions/mean_terminated_length": 1186.2542724609375, "completions/min_length": 369.0, "completions/min_terminated_length": 369.0, "epoch": 0.09404041076141682, "frac_reward_zero_std": 0.5, "grad_norm": 0.43429824709892273, "learning_rate": 7.355e-07, "loss": 0.0201, "num_tokens": 126094047.0, "reward": 0.25, "reward_std": 0.22045661509037018, "rewards/simpleverify_reward/mean": 0.25, "rewards/simpleverify_reward/std": 0.434714138507843, "step": 530 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1669.7421875, "completions/mean_terminated_length": 1183.4107666015625, "completions/min_length": 321.0, "completions/min_terminated_length": 321.0, "epoch": 0.0942178454987025, "frac_reward_zero_std": 0.5, "grad_norm": 0.5173701047897339, "learning_rate": 7.35e-07, "loss": 0.0052, "num_tokens": 126320526.0, "reward": 0.203125, "reward_std": 0.20552174746990204, "rewards/simpleverify_reward/mean": 0.203125, "rewards/simpleverify_reward/std": 0.40390563011169434, "step": 531 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1999.0, "completions/mean_length": 1652.4765625, "completions/mean_terminated_length": 1189.915283203125, "completions/min_length": 389.0, "completions/min_terminated_length": 389.0, "epoch": 0.0943952802359882, "frac_reward_zero_std": 0.375, "grad_norm": 0.4869205057621002, "learning_rate": 7.345e-07, "loss": -0.0093, "num_tokens": 126544795.0, "reward": 0.3125, "reward_std": 0.25218653678894043, "rewards/simpleverify_reward/mean": 0.3125, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 532 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1313.15625, "completions/mean_terminated_length": 1168.9345703125, "completions/min_length": 444.0, "completions/min_terminated_length": 444.0, "epoch": 0.0945727149732739, "frac_reward_zero_std": 0.25, "grad_norm": 0.6011422872543335, "learning_rate": 7.34e-07, "loss": 0.0231, "num_tokens": 126724399.0, "reward": 0.390625, "reward_std": 0.32767558097839355, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 533 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1372.1328125, "completions/mean_terminated_length": 1174.1514892578125, "completions/min_length": 373.0, "completions/min_terminated_length": 373.0, "epoch": 0.09475014971055959, "frac_reward_zero_std": 0.25, "grad_norm": 0.535778820514679, "learning_rate": 7.335e-07, "loss": 0.0044, "num_tokens": 126911552.0, "reward": 0.3359375, "reward_std": 0.30949485301971436, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 534 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1984.0, "completions/mean_length": 1334.8125, "completions/mean_terminated_length": 1178.590576171875, "completions/min_length": 406.0, "completions/min_terminated_length": 406.0, "epoch": 0.09492758444784527, "frac_reward_zero_std": 0.5, "grad_norm": 0.5272184014320374, "learning_rate": 7.329999999999999e-07, "loss": 0.0252, "num_tokens": 127093928.0, "reward": 0.359375, "reward_std": 0.19937554001808167, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 535 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1986.0, "completions/mean_length": 1326.8203125, "completions/mean_terminated_length": 1124.8900146484375, "completions/min_length": 376.0, "completions/min_terminated_length": 376.0, "epoch": 0.09510501918513097, "frac_reward_zero_std": 0.25, "grad_norm": 0.5738640427589417, "learning_rate": 7.325e-07, "loss": 0.0138, "num_tokens": 127275281.0, "reward": 0.3984375, "reward_std": 0.2958405315876007, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 536 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1955.0, "completions/mean_length": 1595.3671875, "completions/mean_terminated_length": 1341.451171875, "completions/min_length": 585.0, "completions/min_terminated_length": 585.0, "epoch": 0.09528245392241666, "frac_reward_zero_std": 0.375, "grad_norm": 0.40674030780792236, "learning_rate": 7.319999999999999e-07, "loss": 0.0116, "num_tokens": 127493152.0, "reward": 0.2265625, "reward_std": 0.21808473765850067, "rewards/simpleverify_reward/mean": 0.2265625, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 537 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2023.0, "completions/mean_length": 1626.1171875, "completions/mean_terminated_length": 1308.26025390625, "completions/min_length": 596.0, "completions/min_terminated_length": 596.0, "epoch": 0.09545988865970235, "frac_reward_zero_std": 0.5, "grad_norm": 0.3684297502040863, "learning_rate": 7.315e-07, "loss": 0.0122, "num_tokens": 127714959.0, "reward": 0.2265625, "reward_std": 0.18837818503379822, "rewards/simpleverify_reward/mean": 0.2265625, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 538 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2002.0, "completions/mean_length": 1560.5859375, "completions/mean_terminated_length": 1339.0341796875, "completions/min_length": 649.0, "completions/min_terminated_length": 649.0, "epoch": 0.09563732339698805, "frac_reward_zero_std": 0.5, "grad_norm": 0.3920265734195709, "learning_rate": 7.31e-07, "loss": 0.0136, "num_tokens": 127928378.0, "reward": 0.328125, "reward_std": 0.2181389182806015, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 539 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1885.0, "completions/mean_length": 1568.8671875, "completions/mean_terminated_length": 1309.0963134765625, "completions/min_length": 744.0, "completions/min_terminated_length": 744.0, "epoch": 0.09581475813427373, "frac_reward_zero_std": 0.5, "grad_norm": 0.34448105096817017, "learning_rate": 7.305e-07, "loss": 0.0029, "num_tokens": 128142857.0, "reward": 0.2734375, "reward_std": 0.20818254351615906, "rewards/simpleverify_reward/mean": 0.2734375, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 540 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1682.5234375, "completions/mean_terminated_length": 1293.4676513671875, "completions/min_length": 657.0, "completions/min_terminated_length": 657.0, "epoch": 0.09599219287155943, "frac_reward_zero_std": 0.25, "grad_norm": 0.5379966497421265, "learning_rate": 7.3e-07, "loss": -0.0061, "num_tokens": 128372380.0, "reward": 0.1875, "reward_std": 0.2948821485042572, "rewards/simpleverify_reward/mean": 0.1875, "rewards/simpleverify_reward/std": 0.39184603095054626, "step": 541 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1998.0, "completions/mean_length": 1682.890625, "completions/mean_terminated_length": 1166.2264404296875, "completions/min_length": 617.0, "completions/min_terminated_length": 617.0, "epoch": 0.09616962760884512, "frac_reward_zero_std": 0.25, "grad_norm": 0.5107181668281555, "learning_rate": 7.295e-07, "loss": -0.002, "num_tokens": 128601950.0, "reward": 0.1640625, "reward_std": 0.2764844298362732, "rewards/simpleverify_reward/mean": 0.1640625, "rewards/simpleverify_reward/std": 0.371787428855896, "step": 542 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5703125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1718.546875, "completions/mean_terminated_length": 1281.272705078125, "completions/min_length": 592.0, "completions/min_terminated_length": 592.0, "epoch": 0.09634706234613082, "frac_reward_zero_std": 0.125, "grad_norm": 0.5181966423988342, "learning_rate": 7.289999999999999e-07, "loss": 0.0024, "num_tokens": 128836084.0, "reward": 0.2109375, "reward_std": 0.32523179054260254, "rewards/simpleverify_reward/mean": 0.2109375, "rewards/simpleverify_reward/std": 0.4095771610736847, "step": 543 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1704.3515625, "completions/mean_terminated_length": 1218.056640625, "completions/min_length": 675.0, "completions/min_terminated_length": 675.0, "epoch": 0.09652449708341651, "frac_reward_zero_std": 0.25, "grad_norm": 0.5132919549942017, "learning_rate": 7.285e-07, "loss": -0.0036, "num_tokens": 129068401.0, "reward": 0.1796875, "reward_std": 0.27332115173339844, "rewards/simpleverify_reward/mean": 0.1796875, "rewards/simpleverify_reward/std": 0.3854354918003082, "step": 544 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1384.65625, "completions/mean_terminated_length": 1093.9775390625, "completions/min_length": 387.0, "completions/min_terminated_length": 387.0, "epoch": 0.09670193182070219, "frac_reward_zero_std": 0.125, "grad_norm": 0.6473442912101746, "learning_rate": 7.28e-07, "loss": 0.0394, "num_tokens": 129257077.0, "reward": 0.4765625, "reward_std": 0.39305341243743896, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 545 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1930.0, "completions/mean_length": 1372.90625, "completions/mean_terminated_length": 1031.3883056640625, "completions/min_length": 388.0, "completions/min_terminated_length": 388.0, "epoch": 0.09687936655798789, "frac_reward_zero_std": 0.25, "grad_norm": 0.5191752314567566, "learning_rate": 7.275e-07, "loss": 0.0368, "num_tokens": 129444249.0, "reward": 0.3515625, "reward_std": 0.3435424566268921, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 546 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1389.53125, "completions/mean_terminated_length": 1090.227294921875, "completions/min_length": 382.0, "completions/min_terminated_length": 382.0, "epoch": 0.09705680129527358, "frac_reward_zero_std": 0.25, "grad_norm": 0.5528131723403931, "learning_rate": 7.27e-07, "loss": 0.0144, "num_tokens": 129633549.0, "reward": 0.4453125, "reward_std": 0.33822086453437805, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 547 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1973.0, "completions/mean_length": 1359.5546875, "completions/mean_terminated_length": 1068.8778076171875, "completions/min_length": 385.0, "completions/min_terminated_length": 385.0, "epoch": 0.09723423603255928, "frac_reward_zero_std": 0.125, "grad_norm": 0.5850695967674255, "learning_rate": 7.265000000000001e-07, "loss": 0.0354, "num_tokens": 129819012.0, "reward": 0.421875, "reward_std": 0.37718653678894043, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 548 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1560.7734375, "completions/mean_terminated_length": 1314.294189453125, "completions/min_length": 602.0, "completions/min_terminated_length": 602.0, "epoch": 0.09741167076984497, "frac_reward_zero_std": 0.25, "grad_norm": 0.5953626036643982, "learning_rate": 7.259999999999999e-07, "loss": 0.0118, "num_tokens": 130030871.0, "reward": 0.5234375, "reward_std": 0.3232898414134979, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 549 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2020.0, "completions/mean_length": 1571.4375, "completions/mean_terminated_length": 1304.0975341796875, "completions/min_length": 545.0, "completions/min_terminated_length": 545.0, "epoch": 0.09758910550713065, "frac_reward_zero_std": 0.25, "grad_norm": 0.5556616187095642, "learning_rate": 7.255e-07, "loss": 0.0006, "num_tokens": 130244095.0, "reward": 0.453125, "reward_std": 0.29533424973487854, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 550 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1983.0, "completions/mean_length": 1588.921875, "completions/mean_terminated_length": 1284.857177734375, "completions/min_length": 579.0, "completions/min_terminated_length": 579.0, "epoch": 0.09776654024441635, "frac_reward_zero_std": 0.375, "grad_norm": 0.4970830976963043, "learning_rate": 7.249999999999999e-07, "loss": 0.0079, "num_tokens": 130459557.0, "reward": 0.4453125, "reward_std": 0.2685280442237854, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 551 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1977.0, "completions/mean_length": 1565.953125, "completions/mean_terminated_length": 1304.6024169921875, "completions/min_length": 523.0, "completions/min_terminated_length": 523.0, "epoch": 0.09794397498170204, "frac_reward_zero_std": 0.375, "grad_norm": 0.5727196931838989, "learning_rate": 7.245e-07, "loss": 0.0114, "num_tokens": 130672079.0, "reward": 0.4453125, "reward_std": 0.26408424973487854, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 552 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2015.0, "completions/mean_length": 1702.296875, "completions/mean_terminated_length": 1322.590087890625, "completions/min_length": 674.0, "completions/min_terminated_length": 674.0, "epoch": 0.09812140971898774, "frac_reward_zero_std": 0.5, "grad_norm": 0.4272399842739105, "learning_rate": 7.24e-07, "loss": 0.0048, "num_tokens": 130900949.0, "reward": 0.1015625, "reward_std": 0.19828036427497864, "rewards/simpleverify_reward/mean": 0.1015625, "rewards/simpleverify_reward/std": 0.3032590448856354, "step": 553 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1724.59375, "completions/mean_terminated_length": 1401.1875, "completions/min_length": 636.0, "completions/min_terminated_length": 636.0, "epoch": 0.09829884445627343, "frac_reward_zero_std": 0.375, "grad_norm": 0.45110565423965454, "learning_rate": 7.235e-07, "loss": 0.0085, "num_tokens": 131132673.0, "reward": 0.171875, "reward_std": 0.2576674520969391, "rewards/simpleverify_reward/mean": 0.171875, "rewards/simpleverify_reward/std": 0.3787541687488556, "step": 554 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1724.125, "completions/mean_terminated_length": 1389.9683837890625, "completions/min_length": 583.0, "completions/min_terminated_length": 583.0, "epoch": 0.09847627919355911, "frac_reward_zero_std": 0.25, "grad_norm": 0.4846172034740448, "learning_rate": 7.229999999999999e-07, "loss": -0.0026, "num_tokens": 131364337.0, "reward": 0.1796875, "reward_std": 0.26933008432388306, "rewards/simpleverify_reward/mean": 0.1796875, "rewards/simpleverify_reward/std": 0.3854354918003082, "step": 555 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5, "completions/max_length": 2048.0, "completions/max_terminated_length": 1948.0, "completions/mean_length": 1699.3984375, "completions/mean_terminated_length": 1350.796875, "completions/min_length": 686.0, "completions/min_terminated_length": 686.0, "epoch": 0.09865371393084481, "frac_reward_zero_std": 0.375, "grad_norm": 0.4325043261051178, "learning_rate": 7.225e-07, "loss": 0.0209, "num_tokens": 131592836.0, "reward": 0.203125, "reward_std": 0.23283424973487854, "rewards/simpleverify_reward/mean": 0.203125, "rewards/simpleverify_reward/std": 0.40390563011169434, "step": 556 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1362.65625, "completions/mean_terminated_length": 1073.2889404296875, "completions/min_length": 34.0, "completions/min_terminated_length": 34.0, "epoch": 0.0988311486681305, "frac_reward_zero_std": 0.375, "grad_norm": 0.41760048270225525, "learning_rate": 7.219999999999999e-07, "loss": 0.0066, "num_tokens": 131779624.0, "reward": 0.3515625, "reward_std": 0.28367161750793457, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 557 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1993.0, "completions/mean_length": 1333.5546875, "completions/mean_terminated_length": 1043.06591796875, "completions/min_length": 34.0, "completions/min_terminated_length": 34.0, "epoch": 0.0990085834054162, "frac_reward_zero_std": 0.5, "grad_norm": 0.38868775963783264, "learning_rate": 7.215e-07, "loss": 0.0143, "num_tokens": 131962687.0, "reward": 0.328125, "reward_std": 0.22045661509037018, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 558 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1984.0, "completions/mean_length": 1333.34375, "completions/mean_terminated_length": 1074.85107421875, "completions/min_length": 34.0, "completions/min_terminated_length": 34.0, "epoch": 0.09918601814270189, "frac_reward_zero_std": 0.5, "grad_norm": 0.352913498878479, "learning_rate": 7.21e-07, "loss": 0.0139, "num_tokens": 132145723.0, "reward": 0.3515625, "reward_std": 0.24406731128692627, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 559 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1358.625, "completions/mean_terminated_length": 1147.591796875, "completions/min_length": 34.0, "completions/min_terminated_length": 34.0, "epoch": 0.09936345287998757, "frac_reward_zero_std": 0.25, "grad_norm": 0.47009870409965515, "learning_rate": 7.205e-07, "loss": -0.0217, "num_tokens": 132331995.0, "reward": 0.40625, "reward_std": 0.3169713318347931, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 560 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1995.0, "completions/mean_length": 1499.3359375, "completions/mean_terminated_length": 1123.9342041015625, "completions/min_length": 639.0, "completions/min_terminated_length": 639.0, "epoch": 0.09954088761727327, "frac_reward_zero_std": 0.375, "grad_norm": 0.46925586462020874, "learning_rate": 7.2e-07, "loss": 0.0138, "num_tokens": 132536022.0, "reward": 0.4609375, "reward_std": 0.21741947531700134, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 561 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1959.0, "completions/mean_length": 1454.8515625, "completions/mean_terminated_length": 1110.6790771484375, "completions/min_length": 521.0, "completions/min_terminated_length": 521.0, "epoch": 0.09971832235455896, "frac_reward_zero_std": 0.375, "grad_norm": 0.5841662883758545, "learning_rate": 7.195e-07, "loss": -0.0074, "num_tokens": 132734355.0, "reward": 0.4140625, "reward_std": 0.2442798912525177, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 562 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2012.0, "completions/mean_length": 1508.140625, "completions/mean_terminated_length": 1150.5714111328125, "completions/min_length": 605.0, "completions/min_terminated_length": 605.0, "epoch": 0.09989575709184466, "frac_reward_zero_std": 0.5, "grad_norm": 0.5518825054168701, "learning_rate": 7.189999999999999e-07, "loss": 0.0319, "num_tokens": 132939509.0, "reward": 0.40625, "reward_std": 0.2000408172607422, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 563 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1992.0, "completions/mean_length": 1480.859375, "completions/mean_terminated_length": 1193.9530029296875, "completions/min_length": 593.0, "completions/min_terminated_length": 593.0, "epoch": 0.10007319182913035, "frac_reward_zero_std": 0.375, "grad_norm": 0.5726907849311829, "learning_rate": 7.185e-07, "loss": 0.0173, "num_tokens": 133141171.0, "reward": 0.453125, "reward_std": 0.2640564441680908, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 564 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1490.3828125, "completions/mean_terminated_length": 1121.052001953125, "completions/min_length": 502.0, "completions/min_terminated_length": 502.0, "epoch": 0.10025062656641603, "frac_reward_zero_std": 0.5, "grad_norm": 0.34521567821502686, "learning_rate": 7.179999999999999e-07, "loss": 0.0229, "num_tokens": 133345268.0, "reward": 0.359375, "reward_std": 0.23411095142364502, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 565 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1994.0, "completions/mean_length": 1516.4921875, "completions/mean_terminated_length": 1140.893310546875, "completions/min_length": 454.0, "completions/min_terminated_length": 454.0, "epoch": 0.10042806130370173, "frac_reward_zero_std": 0.5, "grad_norm": 0.33621713519096375, "learning_rate": 7.175e-07, "loss": 0.0048, "num_tokens": 133552707.0, "reward": 0.375, "reward_std": 0.22668421268463135, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 566 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1483.5625, "completions/mean_terminated_length": 1058.3013916015625, "completions/min_length": 505.0, "completions/min_terminated_length": 505.0, "epoch": 0.10060549604098742, "frac_reward_zero_std": 0.5, "grad_norm": 0.34661731123924255, "learning_rate": 7.17e-07, "loss": 0.0113, "num_tokens": 133755931.0, "reward": 0.359375, "reward_std": 0.21904873847961426, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 567 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1502.8046875, "completions/mean_terminated_length": 1141.7012939453125, "completions/min_length": 490.0, "completions/min_terminated_length": 490.0, "epoch": 0.10078293077827312, "frac_reward_zero_std": 0.5, "grad_norm": 0.3602941930294037, "learning_rate": 7.165e-07, "loss": 0.0112, "num_tokens": 133961618.0, "reward": 0.359375, "reward_std": 0.2288651019334793, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 568 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.46875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1697.9375, "completions/mean_terminated_length": 1389.058837890625, "completions/min_length": 584.0, "completions/min_terminated_length": 584.0, "epoch": 0.10096036551555881, "frac_reward_zero_std": 0.375, "grad_norm": 0.427600622177124, "learning_rate": 7.159999999999999e-07, "loss": 0.0325, "num_tokens": 134191834.0, "reward": 0.421875, "reward_std": 0.25423625111579895, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 569 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1733.8125, "completions/mean_terminated_length": 1399.354736328125, "completions/min_length": 602.0, "completions/min_terminated_length": 602.0, "epoch": 0.1011378002528445, "frac_reward_zero_std": 0.375, "grad_norm": 0.43299490213394165, "learning_rate": 7.155e-07, "loss": 0.0465, "num_tokens": 134426642.0, "reward": 0.375, "reward_std": 0.2726023197174072, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 570 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1714.21875, "completions/mean_terminated_length": 1358.9031982421875, "completions/min_length": 592.0, "completions/min_terminated_length": 592.0, "epoch": 0.10131523499013019, "frac_reward_zero_std": 0.25, "grad_norm": 0.4400845170021057, "learning_rate": 7.149999999999999e-07, "loss": 0.0329, "num_tokens": 134658942.0, "reward": 0.375, "reward_std": 0.29398179054260254, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 571 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1689.4765625, "completions/mean_terminated_length": 1382.9130859375, "completions/min_length": 659.0, "completions/min_terminated_length": 659.0, "epoch": 0.10149266972741589, "frac_reward_zero_std": 0.25, "grad_norm": 0.42452412843704224, "learning_rate": 7.145e-07, "loss": 0.0316, "num_tokens": 134888075.0, "reward": 0.421875, "reward_std": 0.2931797206401825, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 572 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1319.7578125, "completions/mean_terminated_length": 964.1046752929688, "completions/min_length": 438.0, "completions/min_terminated_length": 438.0, "epoch": 0.10167010446470158, "frac_reward_zero_std": 0.25, "grad_norm": 0.6485141515731812, "learning_rate": 7.14e-07, "loss": 0.0207, "num_tokens": 135065580.0, "reward": 0.390625, "reward_std": 0.3318798542022705, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 573 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1318.9140625, "completions/mean_terminated_length": 975.3218383789062, "completions/min_length": 390.0, "completions/min_terminated_length": 390.0, "epoch": 0.10184753920198727, "frac_reward_zero_std": 0.375, "grad_norm": 0.5359305143356323, "learning_rate": 7.135e-07, "loss": 0.0195, "num_tokens": 135242977.0, "reward": 0.4140625, "reward_std": 0.2926734387874603, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 574 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1935.0, "completions/mean_length": 1333.9453125, "completions/mean_terminated_length": 972.7176513671875, "completions/min_length": 334.0, "completions/min_terminated_length": 334.0, "epoch": 0.10202497393927296, "frac_reward_zero_std": 0.25, "grad_norm": 0.6098996996879578, "learning_rate": 7.129999999999999e-07, "loss": 0.0114, "num_tokens": 135422298.0, "reward": 0.4609375, "reward_std": 0.28846919536590576, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 575 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1301.1015625, "completions/mean_terminated_length": 936.3372192382812, "completions/min_length": 422.0, "completions/min_terminated_length": 422.0, "epoch": 0.10220240867655865, "frac_reward_zero_std": 0.25, "grad_norm": 0.6013754606246948, "learning_rate": 7.125e-07, "loss": 0.0358, "num_tokens": 135597415.0, "reward": 0.4375, "reward_std": 0.2774718403816223, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 576 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1414.8671875, "completions/mean_terminated_length": 1261.1942138671875, "completions/min_length": 514.0, "completions/min_terminated_length": 514.0, "epoch": 0.10237984341384435, "frac_reward_zero_std": 0.375, "grad_norm": 0.4309338629245758, "learning_rate": 7.119999999999999e-07, "loss": -0.0078, "num_tokens": 135790438.0, "reward": 0.328125, "reward_std": 0.25218653678894043, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 577 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1437.8203125, "completions/mean_terminated_length": 1282.2843017578125, "completions/min_length": 551.0, "completions/min_terminated_length": 551.0, "epoch": 0.10255727815113004, "frac_reward_zero_std": 0.5, "grad_norm": 0.34503498673439026, "learning_rate": 7.115e-07, "loss": -0.0051, "num_tokens": 135986399.0, "reward": 0.3984375, "reward_std": 0.2251671403646469, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 578 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1434.3671875, "completions/mean_terminated_length": 1254.6162109375, "completions/min_length": 527.0, "completions/min_terminated_length": 527.0, "epoch": 0.10273471288841574, "frac_reward_zero_std": 0.375, "grad_norm": 0.39890745282173157, "learning_rate": 7.11e-07, "loss": 0.004, "num_tokens": 136181918.0, "reward": 0.421875, "reward_std": 0.19628483057022095, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 579 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1424.125, "completions/mean_terminated_length": 1287.4666748046875, "completions/min_length": 521.0, "completions/min_terminated_length": 521.0, "epoch": 0.10291214762570142, "frac_reward_zero_std": 0.25, "grad_norm": 0.4717305600643158, "learning_rate": 7.105e-07, "loss": 0.0133, "num_tokens": 136376126.0, "reward": 0.4296875, "reward_std": 0.2918713688850403, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 580 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1588.21875, "completions/mean_terminated_length": 1441.2783203125, "completions/min_length": 655.0, "completions/min_terminated_length": 655.0, "epoch": 0.10308958236298711, "frac_reward_zero_std": 0.125, "grad_norm": 0.4948972165584564, "learning_rate": 7.1e-07, "loss": 0.009, "num_tokens": 136591178.0, "reward": 0.359375, "reward_std": 0.3728730380535126, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 581 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1550.265625, "completions/mean_terminated_length": 1417.2078857421875, "completions/min_length": 750.0, "completions/min_terminated_length": 750.0, "epoch": 0.1032670171002728, "frac_reward_zero_std": 0.125, "grad_norm": 0.4937152862548828, "learning_rate": 7.094999999999999e-07, "loss": 0.0137, "num_tokens": 136801372.0, "reward": 0.375, "reward_std": 0.3856213688850403, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 582 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1571.890625, "completions/mean_terminated_length": 1399.6807861328125, "completions/min_length": 732.0, "completions/min_terminated_length": 732.0, "epoch": 0.1034444518375585, "frac_reward_zero_std": 0.0, "grad_norm": 0.5509287714958191, "learning_rate": 7.089999999999999e-07, "loss": 0.0339, "num_tokens": 137014334.0, "reward": 0.421875, "reward_std": 0.4437096118927002, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 583 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2006.0, "completions/mean_length": 1583.0078125, "completions/mean_terminated_length": 1386.6778564453125, "completions/min_length": 744.0, "completions/min_terminated_length": 744.0, "epoch": 0.1036218865748442, "frac_reward_zero_std": 0.125, "grad_norm": 0.5613638758659363, "learning_rate": 7.085e-07, "loss": 0.0606, "num_tokens": 137228719.0, "reward": 0.421875, "reward_std": 0.3714885711669922, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 584 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2021.0, "completions/mean_length": 1361.8046875, "completions/mean_terminated_length": 1142.505126953125, "completions/min_length": 410.0, "completions/min_terminated_length": 410.0, "epoch": 0.10379932131212988, "frac_reward_zero_std": 0.0, "grad_norm": 0.8396710157394409, "learning_rate": 7.079999999999999e-07, "loss": 0.013, "num_tokens": 137419110.0, "reward": 0.4453125, "reward_std": 0.3644103705883026, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 585 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1339.9375, "completions/mean_terminated_length": 1176.5384521484375, "completions/min_length": 390.0, "completions/min_terminated_length": 390.0, "epoch": 0.10397675604941557, "frac_reward_zero_std": 0.0, "grad_norm": 0.7400331497192383, "learning_rate": 7.075e-07, "loss": 0.0223, "num_tokens": 137606702.0, "reward": 0.546875, "reward_std": 0.4049736559391022, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 586 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1279.8046875, "completions/mean_terminated_length": 1170.0625, "completions/min_length": 398.0, "completions/min_terminated_length": 398.0, "epoch": 0.10415419078670127, "frac_reward_zero_std": 0.125, "grad_norm": 3.4402709007263184, "learning_rate": 7.07e-07, "loss": -0.0029, "num_tokens": 137786597.0, "reward": 0.5859375, "reward_std": 0.4113866090774536, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 587 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1360.0, "completions/mean_terminated_length": 1149.3876953125, "completions/min_length": 414.0, "completions/min_terminated_length": 414.0, "epoch": 0.10433162552398696, "frac_reward_zero_std": 0.125, "grad_norm": 0.5823692083358765, "learning_rate": 7.065e-07, "loss": 0.0091, "num_tokens": 137976757.0, "reward": 0.4375, "reward_std": 0.35011857748031616, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 588 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1929.0, "completions/mean_length": 1261.0859375, "completions/mean_terminated_length": 1248.5953369140625, "completions/min_length": 553.0, "completions/min_terminated_length": 553.0, "epoch": 0.10450906026127266, "frac_reward_zero_std": 0.25, "grad_norm": 0.4727173149585724, "learning_rate": 7.059999999999999e-07, "loss": -0.0027, "num_tokens": 138145248.0, "reward": 0.2578125, "reward_std": 0.28652724623680115, "rewards/simpleverify_reward/mean": 0.2578125, "rewards/simpleverify_reward/std": 0.43914902210235596, "step": 589 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1235.7890625, "completions/mean_terminated_length": 1222.8968505859375, "completions/min_length": 644.0, "completions/min_terminated_length": 644.0, "epoch": 0.10468649499855834, "frac_reward_zero_std": 0.25, "grad_norm": 0.5180861949920654, "learning_rate": 7.055e-07, "loss": 0.0144, "num_tokens": 138310501.0, "reward": 0.234375, "reward_std": 0.2729007303714752, "rewards/simpleverify_reward/mean": 0.234375, "rewards/simpleverify_reward/std": 0.42527204751968384, "step": 590 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.03125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1291.6875, "completions/mean_terminated_length": 1267.290283203125, "completions/min_length": 779.0, "completions/min_terminated_length": 779.0, "epoch": 0.10486392973584403, "frac_reward_zero_std": 0.125, "grad_norm": 0.5557597875595093, "learning_rate": 7.049999999999999e-07, "loss": -0.0107, "num_tokens": 138482909.0, "reward": 0.234375, "reward_std": 0.339093416929245, "rewards/simpleverify_reward/mean": 0.234375, "rewards/simpleverify_reward/std": 0.42527204751968384, "step": 591 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2012.0, "completions/mean_length": 1273.4921875, "completions/mean_terminated_length": 1221.8583984375, "completions/min_length": 621.0, "completions/min_terminated_length": 621.0, "epoch": 0.10504136447312973, "frac_reward_zero_std": 0.125, "grad_norm": 0.6139190196990967, "learning_rate": 7.045e-07, "loss": -0.0058, "num_tokens": 138652988.0, "reward": 0.2265625, "reward_std": 0.3055257201194763, "rewards/simpleverify_reward/mean": 0.2265625, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 592 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1406.140625, "completions/mean_terminated_length": 1145.1649169921875, "completions/min_length": 415.0, "completions/min_terminated_length": 415.0, "epoch": 0.10521879921041542, "frac_reward_zero_std": 0.25, "grad_norm": 0.5972158908843994, "learning_rate": 7.04e-07, "loss": -0.0149, "num_tokens": 138842670.0, "reward": 0.5078125, "reward_std": 0.31705838441848755, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 593 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1402.5546875, "completions/mean_terminated_length": 1130.0333251953125, "completions/min_length": 463.0, "completions/min_terminated_length": 463.0, "epoch": 0.10539623394770112, "frac_reward_zero_std": 0.125, "grad_norm": 0.5981178283691406, "learning_rate": 7.035e-07, "loss": -0.0001, "num_tokens": 139031893.0, "reward": 0.53125, "reward_std": 0.3636361062526703, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 594 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1407.84375, "completions/mean_terminated_length": 1176.2978515625, "completions/min_length": 488.0, "completions/min_terminated_length": 488.0, "epoch": 0.1055736686849868, "frac_reward_zero_std": 0.375, "grad_norm": 0.515367865562439, "learning_rate": 7.029999999999999e-07, "loss": 0.0136, "num_tokens": 139221793.0, "reward": 0.4921875, "reward_std": 0.2896904945373535, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 595 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2003.0, "completions/mean_length": 1404.6796875, "completions/mean_terminated_length": 1171.9893798828125, "completions/min_length": 493.0, "completions/min_terminated_length": 493.0, "epoch": 0.1057511034222725, "frac_reward_zero_std": 0.375, "grad_norm": 0.4822327196598053, "learning_rate": 7.024999999999999e-07, "loss": -0.0048, "num_tokens": 139411288.0, "reward": 0.53125, "reward_std": 0.279760479927063, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 596 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1956.0, "completions/mean_length": 1233.0546875, "completions/mean_terminated_length": 1015.197998046875, "completions/min_length": 470.0, "completions/min_terminated_length": 470.0, "epoch": 0.10592853815955819, "frac_reward_zero_std": 0.375, "grad_norm": 0.4897841811180115, "learning_rate": 7.019999999999999e-07, "loss": 0.0184, "num_tokens": 139579471.0, "reward": 0.5078125, "reward_std": 0.27068254351615906, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 597 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1921.0, "completions/mean_length": 1229.375, "completions/mean_terminated_length": 1000.1599731445312, "completions/min_length": 438.0, "completions/min_terminated_length": 438.0, "epoch": 0.10610597289684388, "frac_reward_zero_std": 0.25, "grad_norm": 0.5531035661697388, "learning_rate": 7.015e-07, "loss": 0.0067, "num_tokens": 139747183.0, "reward": 0.546875, "reward_std": 0.30193254351615906, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 598 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1758.0, "completions/mean_length": 1182.3046875, "completions/mean_terminated_length": 1012.40185546875, "completions/min_length": 454.0, "completions/min_terminated_length": 454.0, "epoch": 0.10628340763412958, "frac_reward_zero_std": 0.25, "grad_norm": 0.538284182548523, "learning_rate": 7.009999999999999e-07, "loss": 0.0267, "num_tokens": 139908870.0, "reward": 0.6015625, "reward_std": 0.30132144689559937, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 599 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2009.0, "completions/mean_length": 1218.5703125, "completions/mean_terminated_length": 996.841552734375, "completions/min_length": 458.0, "completions/min_terminated_length": 458.0, "epoch": 0.10646084237141526, "frac_reward_zero_std": 0.25, "grad_norm": 0.5021139979362488, "learning_rate": 7.005e-07, "loss": 0.0177, "num_tokens": 140075199.0, "reward": 0.5625, "reward_std": 0.2788337469100952, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 600 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2009.0, "completions/mean_length": 1299.9765625, "completions/mean_terminated_length": 1060.91748046875, "completions/min_length": 373.0, "completions/min_terminated_length": 373.0, "epoch": 0.10663827710870095, "frac_reward_zero_std": 0.25, "grad_norm": 0.47349512577056885, "learning_rate": 7e-07, "loss": 0.031, "num_tokens": 140254092.0, "reward": 0.4609375, "reward_std": 0.30917394161224365, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 601 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2004.0, "completions/mean_length": 1281.0859375, "completions/mean_terminated_length": 1056.434326171875, "completions/min_length": 413.0, "completions/min_terminated_length": 413.0, "epoch": 0.10681571184598665, "frac_reward_zero_std": 0.25, "grad_norm": 0.4751918911933899, "learning_rate": 6.994999999999999e-07, "loss": 0.038, "num_tokens": 140430567.0, "reward": 0.4375, "reward_std": 0.2755298912525177, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 602 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2014.0, "completions/mean_length": 1296.03125, "completions/mean_terminated_length": 1034.821044921875, "completions/min_length": 376.0, "completions/min_terminated_length": 376.0, "epoch": 0.10699314658327234, "frac_reward_zero_std": 0.25, "grad_norm": 0.48732075095176697, "learning_rate": 6.989999999999999e-07, "loss": 0.0122, "num_tokens": 140608955.0, "reward": 0.4453125, "reward_std": 0.29312556982040405, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 603 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1266.4765625, "completions/mean_terminated_length": 1067.2647705078125, "completions/min_length": 374.0, "completions/min_terminated_length": 374.0, "epoch": 0.10717058132055803, "frac_reward_zero_std": 0.25, "grad_norm": 0.5745494961738586, "learning_rate": 6.985e-07, "loss": 0.0227, "num_tokens": 140783560.0, "reward": 0.515625, "reward_std": 0.32266926765441895, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 604 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1516.1875, "completions/mean_terminated_length": 1283.1461181640625, "completions/min_length": 646.0, "completions/min_terminated_length": 646.0, "epoch": 0.10734801605784372, "frac_reward_zero_std": 0.5, "grad_norm": 0.32983097434043884, "learning_rate": 6.979999999999999e-07, "loss": 0.0098, "num_tokens": 140987296.0, "reward": 0.4296875, "reward_std": 0.1978282630443573, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 605 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1533.953125, "completions/mean_terminated_length": 1255.2529296875, "completions/min_length": 604.0, "completions/min_terminated_length": 604.0, "epoch": 0.10752545079512942, "frac_reward_zero_std": 0.375, "grad_norm": 0.4551124572753906, "learning_rate": 6.975e-07, "loss": 0.0011, "num_tokens": 141193306.0, "reward": 0.421875, "reward_std": 0.2290782630443573, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 606 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2014.0, "completions/mean_length": 1537.2265625, "completions/mean_terminated_length": 1230.7625732421875, "completions/min_length": 648.0, "completions/min_terminated_length": 648.0, "epoch": 0.10770288553241511, "frac_reward_zero_std": 0.25, "grad_norm": 0.4369035065174103, "learning_rate": 6.97e-07, "loss": 0.0085, "num_tokens": 141399735.0, "reward": 0.390625, "reward_std": 0.2629890441894531, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 607 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1996.0, "completions/mean_length": 1509.75, "completions/mean_terminated_length": 1207.8048095703125, "completions/min_length": 610.0, "completions/min_terminated_length": 610.0, "epoch": 0.1078803202697008, "frac_reward_zero_std": 0.625, "grad_norm": 0.31802651286125183, "learning_rate": 6.965e-07, "loss": 0.0028, "num_tokens": 141602647.0, "reward": 0.40625, "reward_std": 0.15712818503379822, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 608 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1977.0, "completions/mean_length": 1238.640625, "completions/mean_terminated_length": 843.3720703125, "completions/min_length": 414.0, "completions/min_terminated_length": 414.0, "epoch": 0.10805775500698649, "frac_reward_zero_std": 0.5, "grad_norm": 0.5359482169151306, "learning_rate": 6.959999999999999e-07, "loss": 0.0026, "num_tokens": 141770153.0, "reward": 0.6484375, "reward_std": 0.14965170621871948, "rewards/simpleverify_reward/mean": 0.6484375, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 609 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1841.0, "completions/mean_length": 1238.796875, "completions/mean_terminated_length": 857.4482421875, "completions/min_length": 369.0, "completions/min_terminated_length": 369.0, "epoch": 0.10823518974427218, "frac_reward_zero_std": 0.375, "grad_norm": 0.512330949306488, "learning_rate": 6.955e-07, "loss": 0.0243, "num_tokens": 141937679.0, "reward": 0.6171875, "reward_std": 0.1945282220840454, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 610 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1914.0, "completions/mean_length": 1250.34375, "completions/mean_terminated_length": 860.7907104492188, "completions/min_length": 386.0, "completions/min_terminated_length": 386.0, "epoch": 0.10841262448155788, "frac_reward_zero_std": 0.375, "grad_norm": 0.5266452431678772, "learning_rate": 6.949999999999999e-07, "loss": 0.0229, "num_tokens": 142106683.0, "reward": 0.6015625, "reward_std": 0.21366733312606812, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 611 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2000.0, "completions/mean_length": 1255.6796875, "completions/mean_terminated_length": 882.287353515625, "completions/min_length": 420.0, "completions/min_terminated_length": 420.0, "epoch": 0.10859005921884357, "frac_reward_zero_std": 0.375, "grad_norm": 0.5677009224891663, "learning_rate": 6.945e-07, "loss": 0.0356, "num_tokens": 142276370.0, "reward": 0.59375, "reward_std": 0.2000408172607422, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 612 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2023.0, "completions/mean_length": 1523.328125, "completions/mean_terminated_length": 1301.800048828125, "completions/min_length": 596.0, "completions/min_terminated_length": 596.0, "epoch": 0.10876749395612927, "frac_reward_zero_std": 0.125, "grad_norm": 0.5515462756156921, "learning_rate": 6.939999999999999e-07, "loss": 0.0096, "num_tokens": 142486460.0, "reward": 0.4765625, "reward_std": 0.3545043468475342, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 613 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1550.421875, "completions/mean_terminated_length": 1315.9310302734375, "completions/min_length": 588.0, "completions/min_terminated_length": 588.0, "epoch": 0.10894492869341495, "frac_reward_zero_std": 0.25, "grad_norm": 0.44883790612220764, "learning_rate": 6.935e-07, "loss": 0.0188, "num_tokens": 142700018.0, "reward": 0.4765625, "reward_std": 0.3502710461616516, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 614 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1943.0, "completions/mean_length": 1503.484375, "completions/mean_terminated_length": 1273.5777587890625, "completions/min_length": 525.0, "completions/min_terminated_length": 525.0, "epoch": 0.10912236343070064, "frac_reward_zero_std": 0.125, "grad_norm": 0.5222975611686707, "learning_rate": 6.929999999999999e-07, "loss": 0.0359, "num_tokens": 142907568.0, "reward": 0.46875, "reward_std": 0.38064974546432495, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 615 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1476.9375, "completions/mean_terminated_length": 1317.0399169921875, "completions/min_length": 572.0, "completions/min_terminated_length": 572.0, "epoch": 0.10929979816798634, "frac_reward_zero_std": 0.125, "grad_norm": 0.5258731245994568, "learning_rate": 6.924999999999999e-07, "loss": 0.0343, "num_tokens": 143111720.0, "reward": 0.5078125, "reward_std": 0.3959232568740845, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 616 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1499.2421875, "completions/mean_terminated_length": 1072.4305419921875, "completions/min_length": 551.0, "completions/min_terminated_length": 551.0, "epoch": 0.10947723290527203, "frac_reward_zero_std": 0.5, "grad_norm": 0.407659113407135, "learning_rate": 6.919999999999999e-07, "loss": 0.007, "num_tokens": 143316535.0, "reward": 0.4375, "reward_std": 0.23488396406173706, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 617 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1489.140625, "completions/mean_terminated_length": 1054.4722900390625, "completions/min_length": 574.0, "completions/min_terminated_length": 574.0, "epoch": 0.10965466764255773, "frac_reward_zero_std": 0.375, "grad_norm": 0.42338764667510986, "learning_rate": 6.915e-07, "loss": 0.0064, "num_tokens": 143520057.0, "reward": 0.4921875, "reward_std": 0.2504299283027649, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 618 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1992.0, "completions/mean_length": 1484.4921875, "completions/mean_terminated_length": 1059.9315185546875, "completions/min_length": 577.0, "completions/min_terminated_length": 577.0, "epoch": 0.10983210237984341, "frac_reward_zero_std": 0.375, "grad_norm": 0.4918474853038788, "learning_rate": 6.909999999999999e-07, "loss": 0.0154, "num_tokens": 143722984.0, "reward": 0.484375, "reward_std": 0.23283424973487854, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 619 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1969.0, "completions/mean_length": 1473.3125, "completions/mean_terminated_length": 1067.2000732421875, "completions/min_length": 523.0, "completions/min_terminated_length": 523.0, "epoch": 0.1100095371171291, "frac_reward_zero_std": 0.5, "grad_norm": 0.42690733075141907, "learning_rate": 6.905e-07, "loss": 0.0039, "num_tokens": 143924480.0, "reward": 0.53125, "reward_std": 0.2464885711669922, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 620 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2009.0, "completions/mean_length": 1596.9765625, "completions/mean_terminated_length": 1101.590087890625, "completions/min_length": 414.0, "completions/min_terminated_length": 414.0, "epoch": 0.1101869718544148, "frac_reward_zero_std": 0.625, "grad_norm": 0.4287160634994507, "learning_rate": 6.9e-07, "loss": -0.0063, "num_tokens": 144151789.0, "reward": 0.2578125, "reward_std": 0.17584684491157532, "rewards/simpleverify_reward/mean": 0.2578125, "rewards/simpleverify_reward/std": 0.43914902210235596, "step": 621 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4765625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1554.71875, "completions/mean_terminated_length": 1105.6119384765625, "completions/min_length": 404.0, "completions/min_terminated_length": 404.0, "epoch": 0.11036440659170049, "frac_reward_zero_std": 0.625, "grad_norm": 0.4008740484714508, "learning_rate": 6.894999999999999e-07, "loss": 0.0005, "num_tokens": 144373689.0, "reward": 0.234375, "reward_std": 0.15119513869285583, "rewards/simpleverify_reward/mean": 0.234375, "rewards/simpleverify_reward/std": 0.42527204751968384, "step": 622 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2016.0, "completions/mean_length": 1544.5625, "completions/mean_terminated_length": 1056.6153564453125, "completions/min_length": 348.0, "completions/min_terminated_length": 348.0, "epoch": 0.11054184132898619, "frac_reward_zero_std": 0.375, "grad_norm": 0.5386563539505005, "learning_rate": 6.889999999999999e-07, "loss": -0.0142, "num_tokens": 144594289.0, "reward": 0.2890625, "reward_std": 0.24667394161224365, "rewards/simpleverify_reward/mean": 0.2890625, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 623 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1531.4765625, "completions/mean_terminated_length": 1046.257568359375, "completions/min_length": 375.0, "completions/min_terminated_length": 375.0, "epoch": 0.11071927606627187, "frac_reward_zero_std": 0.5, "grad_norm": 0.5871000289916992, "learning_rate": 6.885e-07, "loss": -0.0011, "num_tokens": 144813214.0, "reward": 0.25, "reward_std": 0.2097259759902954, "rewards/simpleverify_reward/mean": 0.25, "rewards/simpleverify_reward/std": 0.434714138507843, "step": 624 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1380.484375, "completions/mean_terminated_length": 952.5897827148438, "completions/min_length": 344.0, "completions/min_terminated_length": 344.0, "epoch": 0.11089671080355756, "frac_reward_zero_std": 0.375, "grad_norm": 0.37613430619239807, "learning_rate": 6.879999999999999e-07, "loss": 0.0064, "num_tokens": 145004220.0, "reward": 0.4375, "reward_std": 0.24467839300632477, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 625 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1356.875, "completions/mean_terminated_length": 1019.3488159179688, "completions/min_length": 388.0, "completions/min_terminated_length": 388.0, "epoch": 0.11107414554084326, "frac_reward_zero_std": 0.5, "grad_norm": 0.41033676266670227, "learning_rate": 6.875e-07, "loss": 0.003, "num_tokens": 145192204.0, "reward": 0.4140625, "reward_std": 0.2070690393447876, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 626 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1374.0859375, "completions/mean_terminated_length": 1021.0833740234375, "completions/min_length": 403.0, "completions/min_terminated_length": 403.0, "epoch": 0.11125158027812895, "frac_reward_zero_std": 0.375, "grad_norm": 0.3870909810066223, "learning_rate": 6.87e-07, "loss": 0.0076, "num_tokens": 145382391.0, "reward": 0.4375, "reward_std": 0.27132564783096313, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 627 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1367.4921875, "completions/mean_terminated_length": 959.1875, "completions/min_length": 374.0, "completions/min_terminated_length": 374.0, "epoch": 0.11142901501541465, "frac_reward_zero_std": 0.5, "grad_norm": 0.39628660678863525, "learning_rate": 6.865e-07, "loss": 0.012, "num_tokens": 145571734.0, "reward": 0.4375, "reward_std": 0.18888446688652039, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 628 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1361.7890625, "completions/mean_terminated_length": 1142.4844970703125, "completions/min_length": 444.0, "completions/min_terminated_length": 444.0, "epoch": 0.11160644975270033, "frac_reward_zero_std": 0.125, "grad_norm": 0.5374038219451904, "learning_rate": 6.86e-07, "loss": 0.0116, "num_tokens": 145755787.0, "reward": 0.3359375, "reward_std": 0.31578171253204346, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 629 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1340.4375, "completions/mean_terminated_length": 1123.836669921875, "completions/min_length": 442.0, "completions/min_terminated_length": 442.0, "epoch": 0.11178388448998602, "frac_reward_zero_std": 0.375, "grad_norm": 0.4786739647388458, "learning_rate": 6.854999999999999e-07, "loss": 0.0041, "num_tokens": 145937107.0, "reward": 0.3828125, "reward_std": 0.27707332372665405, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 630 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1346.3125, "completions/mean_terminated_length": 1122.061767578125, "completions/min_length": 484.0, "completions/min_terminated_length": 484.0, "epoch": 0.11196131922727172, "frac_reward_zero_std": 0.25, "grad_norm": 0.5285488367080688, "learning_rate": 6.85e-07, "loss": 0.0097, "num_tokens": 146119179.0, "reward": 0.4140625, "reward_std": 0.3271957039833069, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 631 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1978.0, "completions/mean_length": 1382.140625, "completions/mean_terminated_length": 1169.3402099609375, "completions/min_length": 431.0, "completions/min_terminated_length": 431.0, "epoch": 0.11213875396455741, "frac_reward_zero_std": 0.25, "grad_norm": 0.5178000926971436, "learning_rate": 6.845e-07, "loss": 0.0024, "num_tokens": 146305837.0, "reward": 0.375, "reward_std": 0.32437169551849365, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 632 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1428.078125, "completions/mean_terminated_length": 1080.3170166015625, "completions/min_length": 396.0, "completions/min_terminated_length": 396.0, "epoch": 0.11231618870184311, "frac_reward_zero_std": 0.25, "grad_norm": 0.5870347619056702, "learning_rate": 6.84e-07, "loss": 0.0486, "num_tokens": 146496807.0, "reward": 0.6015625, "reward_std": 0.3112236559391022, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 633 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1440.3125, "completions/mean_terminated_length": 1075.7000732421875, "completions/min_length": 372.0, "completions/min_terminated_length": 372.0, "epoch": 0.11249362343912879, "frac_reward_zero_std": 0.375, "grad_norm": 0.41642412543296814, "learning_rate": 6.835e-07, "loss": 0.027, "num_tokens": 146689343.0, "reward": 0.5625, "reward_std": 0.27164655923843384, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 634 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1981.0, "completions/mean_length": 1474.078125, "completions/mean_terminated_length": 1041.6712646484375, "completions/min_length": 366.0, "completions/min_terminated_length": 366.0, "epoch": 0.11267105817641448, "frac_reward_zero_std": 0.375, "grad_norm": 0.46392470598220825, "learning_rate": 6.830000000000001e-07, "loss": 0.0303, "num_tokens": 146886201.0, "reward": 0.546875, "reward_std": 0.26834267377853394, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 635 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1440.0234375, "completions/mean_terminated_length": 1010.38671875, "completions/min_length": 356.0, "completions/min_terminated_length": 356.0, "epoch": 0.11284849291370018, "frac_reward_zero_std": 0.5, "grad_norm": 0.3243767321109772, "learning_rate": 6.824999999999999e-07, "loss": 0.013, "num_tokens": 147078700.0, "reward": 0.5546875, "reward_std": 0.2218368649482727, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 636 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1947.0, "completions/mean_length": 1506.8515625, "completions/mean_terminated_length": 1251.82763671875, "completions/min_length": 436.0, "completions/min_terminated_length": 436.0, "epoch": 0.11302592765098587, "frac_reward_zero_std": 0.5, "grad_norm": 0.426695317029953, "learning_rate": 6.82e-07, "loss": 0.012, "num_tokens": 147288409.0, "reward": 0.390625, "reward_std": 0.20927388966083527, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 637 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1529.7109375, "completions/mean_terminated_length": 1248.7108154296875, "completions/min_length": 397.0, "completions/min_terminated_length": 397.0, "epoch": 0.11320336238827157, "frac_reward_zero_std": 0.5, "grad_norm": 0.4359927773475647, "learning_rate": 6.815e-07, "loss": -0.0037, "num_tokens": 147501044.0, "reward": 0.3125, "reward_std": 0.2130298763513565, "rewards/simpleverify_reward/mean": 0.3125, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 638 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1509.65625, "completions/mean_terminated_length": 1217.7830810546875, "completions/min_length": 446.0, "completions/min_terminated_length": 446.0, "epoch": 0.11338079712555725, "frac_reward_zero_std": 0.375, "grad_norm": 0.48437148332595825, "learning_rate": 6.81e-07, "loss": 0.0108, "num_tokens": 147711112.0, "reward": 0.3515625, "reward_std": 0.26943784952163696, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 639 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2016.0, "completions/mean_length": 1526.5390625, "completions/mean_terminated_length": 1243.8192138671875, "completions/min_length": 384.0, "completions/min_terminated_length": 384.0, "epoch": 0.11355823186284295, "frac_reward_zero_std": 0.375, "grad_norm": 0.4358665347099304, "learning_rate": 6.805e-07, "loss": 0.009, "num_tokens": 147923341.0, "reward": 0.34375, "reward_std": 0.21244096755981445, "rewards/simpleverify_reward/mean": 0.34375, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 640 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1303.40625, "completions/mean_terminated_length": 1044.7579345703125, "completions/min_length": 432.0, "completions/min_terminated_length": 432.0, "epoch": 0.11373566660012864, "frac_reward_zero_std": 0.375, "grad_norm": 0.4979339838027954, "learning_rate": 6.800000000000001e-07, "loss": -0.0042, "num_tokens": 148098497.0, "reward": 0.453125, "reward_std": 0.26187554001808167, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 641 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1274.171875, "completions/mean_terminated_length": 1005.3684692382812, "completions/min_length": 414.0, "completions/min_terminated_length": 414.0, "epoch": 0.11391310133741434, "frac_reward_zero_std": 0.375, "grad_norm": 0.5266083478927612, "learning_rate": 6.794999999999999e-07, "loss": 0.0085, "num_tokens": 148269911.0, "reward": 0.4453125, "reward_std": 0.22686956822872162, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 642 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1281.984375, "completions/mean_terminated_length": 982.2391357421875, "completions/min_length": 435.0, "completions/min_terminated_length": 435.0, "epoch": 0.11409053607470003, "frac_reward_zero_std": 0.5, "grad_norm": 0.4987327754497528, "learning_rate": 6.79e-07, "loss": 0.0168, "num_tokens": 148442325.0, "reward": 0.4609375, "reward_std": 0.17472384870052338, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 643 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2005.0, "completions/mean_length": 1309.4140625, "completions/mean_terminated_length": 961.3448486328125, "completions/min_length": 467.0, "completions/min_terminated_length": 467.0, "epoch": 0.11426797081198571, "frac_reward_zero_std": 0.625, "grad_norm": 0.3358268141746521, "learning_rate": 6.784999999999999e-07, "loss": 0.0169, "num_tokens": 148618250.0, "reward": 0.453125, "reward_std": 0.16613000631332397, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 644 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1373.15625, "completions/mean_terminated_length": 1192.75244140625, "completions/min_length": 378.0, "completions/min_terminated_length": 378.0, "epoch": 0.1144454055492714, "frac_reward_zero_std": 0.25, "grad_norm": 0.4570358097553253, "learning_rate": 6.78e-07, "loss": 0.017, "num_tokens": 148806142.0, "reward": 0.5859375, "reward_std": 0.34196737408638, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 645 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1390.21875, "completions/mean_terminated_length": 1188.857177734375, "completions/min_length": 471.0, "completions/min_terminated_length": 471.0, "epoch": 0.1146228402865571, "frac_reward_zero_std": 0.125, "grad_norm": 0.5515322685241699, "learning_rate": 6.775e-07, "loss": 0.0162, "num_tokens": 148996218.0, "reward": 0.546875, "reward_std": 0.40646854043006897, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 646 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1353.8359375, "completions/mean_terminated_length": 1150.4949951171875, "completions/min_length": 425.0, "completions/min_terminated_length": 425.0, "epoch": 0.1148002750238428, "frac_reward_zero_std": 0.125, "grad_norm": 0.5503378510475159, "learning_rate": 6.77e-07, "loss": -0.0033, "num_tokens": 149181637.0, "reward": 0.625, "reward_std": 0.33084267377853394, "rewards/simpleverify_reward/mean": 0.625, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 647 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1342.2109375, "completions/mean_terminated_length": 1126.153076171875, "completions/min_length": 394.0, "completions/min_terminated_length": 394.0, "epoch": 0.11497770976112849, "frac_reward_zero_std": 0.125, "grad_norm": 0.6044089198112488, "learning_rate": 6.765e-07, "loss": 0.0179, "num_tokens": 149365568.0, "reward": 0.53125, "reward_std": 0.34178200364112854, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 648 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2016.0, "completions/mean_length": 1346.2890625, "completions/mean_terminated_length": 1149.8099365234375, "completions/min_length": 553.0, "completions/min_terminated_length": 553.0, "epoch": 0.11515514449841417, "frac_reward_zero_std": 0.125, "grad_norm": 0.5514361262321472, "learning_rate": 6.76e-07, "loss": 0.0034, "num_tokens": 149549861.0, "reward": 0.4921875, "reward_std": 0.3917190432548523, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 649 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1874.0, "completions/mean_length": 1342.546875, "completions/mean_terminated_length": 1077.0537109375, "completions/min_length": 539.0, "completions/min_terminated_length": 539.0, "epoch": 0.11533257923569987, "frac_reward_zero_std": 0.0, "grad_norm": 0.5922033786773682, "learning_rate": 6.754999999999999e-07, "loss": -0.0099, "num_tokens": 149733675.0, "reward": 0.4609375, "reward_std": 0.39706701040267944, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 650 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1311.4609375, "completions/mean_terminated_length": 1095.70703125, "completions/min_length": 583.0, "completions/min_terminated_length": 583.0, "epoch": 0.11551001397298556, "frac_reward_zero_std": 0.125, "grad_norm": 0.5737316608428955, "learning_rate": 6.75e-07, "loss": -0.001, "num_tokens": 149913510.0, "reward": 0.4765625, "reward_std": 0.37997761368751526, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 651 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1344.578125, "completions/mean_terminated_length": 1165.2745361328125, "completions/min_length": 544.0, "completions/min_terminated_length": 544.0, "epoch": 0.11568744871027126, "frac_reward_zero_std": 0.0, "grad_norm": 0.5658794045448303, "learning_rate": 6.745e-07, "loss": -0.0113, "num_tokens": 150097584.0, "reward": 0.4921875, "reward_std": 0.43193918466567993, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 652 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1219.2734375, "completions/mean_terminated_length": 1047.2735595703125, "completions/min_length": 416.0, "completions/min_terminated_length": 416.0, "epoch": 0.11586488344755695, "frac_reward_zero_std": 0.25, "grad_norm": 0.5225741863250732, "learning_rate": 6.74e-07, "loss": 0.0379, "num_tokens": 150266003.0, "reward": 0.4375, "reward_std": 0.32746243476867676, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 653 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1191.5859375, "completions/mean_terminated_length": 1042.302734375, "completions/min_length": 427.0, "completions/min_terminated_length": 427.0, "epoch": 0.11604231818484263, "frac_reward_zero_std": 0.25, "grad_norm": 0.5269824266433716, "learning_rate": 6.735e-07, "loss": 0.0207, "num_tokens": 150430878.0, "reward": 0.4921875, "reward_std": 0.3395996689796448, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 654 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1956.0, "completions/mean_length": 1242.578125, "completions/mean_terminated_length": 1006.646484375, "completions/min_length": 425.0, "completions/min_terminated_length": 425.0, "epoch": 0.11621975292212833, "frac_reward_zero_std": 0.125, "grad_norm": 0.6160121560096741, "learning_rate": 6.730000000000001e-07, "loss": 0.0051, "num_tokens": 150602280.0, "reward": 0.4296875, "reward_std": 0.3353690803050995, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 655 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1251.2421875, "completions/mean_terminated_length": 1038.24755859375, "completions/min_length": 423.0, "completions/min_terminated_length": 423.0, "epoch": 0.11639718765941402, "frac_reward_zero_std": 0.0, "grad_norm": 0.6680843830108643, "learning_rate": 6.724999999999999e-07, "loss": 0.0423, "num_tokens": 150774791.0, "reward": 0.5, "reward_std": 0.36956915259361267, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 656 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1961.0, "completions/mean_length": 1334.5625, "completions/mean_terminated_length": 1116.1632080078125, "completions/min_length": 374.0, "completions/min_terminated_length": 374.0, "epoch": 0.11657462239669972, "frac_reward_zero_std": 0.375, "grad_norm": 0.4802338480949402, "learning_rate": 6.72e-07, "loss": 0.0041, "num_tokens": 150964319.0, "reward": 0.5625, "reward_std": 0.3039822578430176, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 657 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2000.0, "completions/mean_length": 1338.15625, "completions/mean_terminated_length": 1101.541748046875, "completions/min_length": 358.0, "completions/min_terminated_length": 358.0, "epoch": 0.11675205713398541, "frac_reward_zero_std": 0.25, "grad_norm": 0.5679851770401001, "learning_rate": 6.714999999999999e-07, "loss": 0.0102, "num_tokens": 151154307.0, "reward": 0.546875, "reward_std": 0.33573853969573975, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 658 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1375.65625, "completions/mean_terminated_length": 1122.6236572265625, "completions/min_length": 368.0, "completions/min_terminated_length": 368.0, "epoch": 0.1169294918712711, "frac_reward_zero_std": 0.25, "grad_norm": 0.6236666440963745, "learning_rate": 6.71e-07, "loss": 0.0338, "num_tokens": 151349095.0, "reward": 0.578125, "reward_std": 0.3540782630443573, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 659 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1365.640625, "completions/mean_terminated_length": 1200.0194091796875, "completions/min_length": 391.0, "completions/min_terminated_length": 391.0, "epoch": 0.11710692660855679, "frac_reward_zero_std": 0.25, "grad_norm": 0.6060218214988708, "learning_rate": 6.705e-07, "loss": 0.0241, "num_tokens": 151542601.0, "reward": 0.6171875, "reward_std": 0.29972386360168457, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 660 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2023.0, "completions/mean_length": 1312.0234375, "completions/mean_terminated_length": 1167.579345703125, "completions/min_length": 465.0, "completions/min_terminated_length": 465.0, "epoch": 0.11728436134584248, "frac_reward_zero_std": 0.0, "grad_norm": 0.5927854776382446, "learning_rate": 6.7e-07, "loss": 0.0091, "num_tokens": 151720284.0, "reward": 0.5078125, "reward_std": 0.49039655923843384, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 661 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1326.0234375, "completions/mean_terminated_length": 1159.4134521484375, "completions/min_length": 476.0, "completions/min_terminated_length": 476.0, "epoch": 0.11746179608312818, "frac_reward_zero_std": 0.0, "grad_norm": 0.6286494135856628, "learning_rate": 6.695e-07, "loss": -0.0029, "num_tokens": 151899759.0, "reward": 0.453125, "reward_std": 0.4680625796318054, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 662 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1312.96875, "completions/mean_terminated_length": 1143.34619140625, "completions/min_length": 492.0, "completions/min_terminated_length": 492.0, "epoch": 0.11763923082041387, "frac_reward_zero_std": 0.0, "grad_norm": 0.6656221151351929, "learning_rate": 6.69e-07, "loss": 0.0053, "num_tokens": 152077563.0, "reward": 0.4296875, "reward_std": 0.4848354160785675, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 663 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1286.8359375, "completions/mean_terminated_length": 1162.28173828125, "completions/min_length": 464.0, "completions/min_terminated_length": 464.0, "epoch": 0.11781666555769955, "frac_reward_zero_std": 0.0, "grad_norm": 0.6065910458564758, "learning_rate": 6.684999999999999e-07, "loss": 0.0018, "num_tokens": 152252022.0, "reward": 0.453125, "reward_std": 0.48924756050109863, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 664 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1312.1796875, "completions/mean_terminated_length": 1077.0206298828125, "completions/min_length": 398.0, "completions/min_terminated_length": 398.0, "epoch": 0.11799410029498525, "frac_reward_zero_std": 0.375, "grad_norm": 0.4219629764556885, "learning_rate": 6.68e-07, "loss": 0.0004, "num_tokens": 152430125.0, "reward": 0.546875, "reward_std": 0.24933473765850067, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 665 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1915.0, "completions/mean_length": 1278.609375, "completions/mean_terminated_length": 1000.319091796875, "completions/min_length": 397.0, "completions/min_terminated_length": 397.0, "epoch": 0.11817153503227094, "frac_reward_zero_std": 0.375, "grad_norm": 0.5777439475059509, "learning_rate": 6.675e-07, "loss": -0.0003, "num_tokens": 152603931.0, "reward": 0.4921875, "reward_std": 0.251706600189209, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 666 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1317.9609375, "completions/mean_terminated_length": 1064.368408203125, "completions/min_length": 406.0, "completions/min_terminated_length": 406.0, "epoch": 0.11834896976955664, "frac_reward_zero_std": 0.25, "grad_norm": 0.5671809911727905, "learning_rate": 6.67e-07, "loss": 0.0124, "num_tokens": 152782774.0, "reward": 0.5390625, "reward_std": 0.2968776822090149, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 667 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2004.0, "completions/mean_length": 1279.953125, "completions/mean_terminated_length": 1034.494873046875, "completions/min_length": 450.0, "completions/min_terminated_length": 450.0, "epoch": 0.11852640450684233, "frac_reward_zero_std": 0.375, "grad_norm": 0.4439055919647217, "learning_rate": 6.665e-07, "loss": -0.012, "num_tokens": 152956752.0, "reward": 0.5078125, "reward_std": 0.2728690803050995, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 668 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1984.0, "completions/mean_length": 1618.6640625, "completions/mean_terminated_length": 1430.528076171875, "completions/min_length": 702.0, "completions/min_terminated_length": 702.0, "epoch": 0.11870383924412801, "frac_reward_zero_std": 0.0, "grad_norm": 0.5615836381912231, "learning_rate": 6.66e-07, "loss": 0.0283, "num_tokens": 153180421.0, "reward": 0.4296875, "reward_std": 0.43103885650634766, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 669 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1630.296875, "completions/mean_terminated_length": 1379.675048828125, "completions/min_length": 752.0, "completions/min_terminated_length": 752.0, "epoch": 0.11888127398141371, "frac_reward_zero_std": 0.125, "grad_norm": 0.580673098564148, "learning_rate": 6.654999999999999e-07, "loss": 0.0098, "num_tokens": 153405579.0, "reward": 0.3515625, "reward_std": 0.35722315311431885, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 670 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1641.53125, "completions/mean_terminated_length": 1405.6790771484375, "completions/min_length": 778.0, "completions/min_terminated_length": 778.0, "epoch": 0.1190587087186994, "frac_reward_zero_std": 0.125, "grad_norm": 0.5207106471061707, "learning_rate": 6.65e-07, "loss": 0.0253, "num_tokens": 153632175.0, "reward": 0.328125, "reward_std": 0.34966084361076355, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 671 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2021.0, "completions/mean_length": 1656.9453125, "completions/mean_terminated_length": 1380.5999755859375, "completions/min_length": 759.0, "completions/min_terminated_length": 759.0, "epoch": 0.1192361434559851, "frac_reward_zero_std": 0.125, "grad_norm": 0.5258269309997559, "learning_rate": 6.645e-07, "loss": 0.0255, "num_tokens": 153860744.0, "reward": 0.3203125, "reward_std": 0.33491697907447815, "rewards/simpleverify_reward/mean": 0.3203125, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 672 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1421.1796875, "completions/mean_terminated_length": 1045.0875244140625, "completions/min_length": 589.0, "completions/min_terminated_length": 589.0, "epoch": 0.11941357819327078, "frac_reward_zero_std": 0.5, "grad_norm": 0.415617972612381, "learning_rate": 6.64e-07, "loss": -0.0026, "num_tokens": 154053711.0, "reward": 0.265625, "reward_std": 0.21962818503379822, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 673 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1457.578125, "completions/mean_terminated_length": 1137.4698486328125, "completions/min_length": 533.0, "completions/min_terminated_length": 533.0, "epoch": 0.11959101293055648, "frac_reward_zero_std": 0.375, "grad_norm": 0.449864000082016, "learning_rate": 6.635e-07, "loss": 0.0094, "num_tokens": 154251337.0, "reward": 0.34375, "reward_std": 0.26802176237106323, "rewards/simpleverify_reward/mean": 0.34375, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 674 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1462.625, "completions/mean_terminated_length": 1176.744140625, "completions/min_length": 607.0, "completions/min_terminated_length": 607.0, "epoch": 0.11976844766784217, "frac_reward_zero_std": 0.25, "grad_norm": 0.5100752711296082, "learning_rate": 6.63e-07, "loss": -0.0208, "num_tokens": 154449609.0, "reward": 0.328125, "reward_std": 0.27792394161224365, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 675 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1438.125, "completions/mean_terminated_length": 1150.712646484375, "completions/min_length": 568.0, "completions/min_terminated_length": 568.0, "epoch": 0.11994588240512787, "frac_reward_zero_std": 0.125, "grad_norm": 0.5546215176582336, "learning_rate": 6.624999999999999e-07, "loss": -0.0103, "num_tokens": 154644745.0, "reward": 0.34375, "reward_std": 0.36489027738571167, "rewards/simpleverify_reward/mean": 0.34375, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 676 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1386.875, "completions/mean_terminated_length": 1138.0645751953125, "completions/min_length": 529.0, "completions/min_terminated_length": 529.0, "epoch": 0.12012331714241356, "frac_reward_zero_std": 0.25, "grad_norm": 0.5159702897071838, "learning_rate": 6.62e-07, "loss": 0.0051, "num_tokens": 154832553.0, "reward": 0.34375, "reward_std": 0.2792820334434509, "rewards/simpleverify_reward/mean": 0.34375, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 677 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1999.0, "completions/mean_length": 1421.984375, "completions/mean_terminated_length": 1147.6629638671875, "completions/min_length": 538.0, "completions/min_terminated_length": 538.0, "epoch": 0.12030075187969924, "frac_reward_zero_std": 0.25, "grad_norm": 0.5556815266609192, "learning_rate": 6.614999999999999e-07, "loss": 0.0092, "num_tokens": 155024855.0, "reward": 0.3828125, "reward_std": 0.3034759759902954, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 678 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1971.0, "completions/mean_length": 1418.4609375, "completions/mean_terminated_length": 1162.4945068359375, "completions/min_length": 535.0, "completions/min_terminated_length": 535.0, "epoch": 0.12047818661698494, "frac_reward_zero_std": 0.25, "grad_norm": 0.518841028213501, "learning_rate": 6.61e-07, "loss": -0.0064, "num_tokens": 155216706.0, "reward": 0.4453125, "reward_std": 0.29642558097839355, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 679 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1969.0, "completions/mean_length": 1450.9296875, "completions/mean_terminated_length": 1198.8333740234375, "completions/min_length": 569.0, "completions/min_terminated_length": 569.0, "epoch": 0.12065562135427063, "frac_reward_zero_std": 0.125, "grad_norm": 0.5401055216789246, "learning_rate": 6.605e-07, "loss": 0.0041, "num_tokens": 155412713.0, "reward": 0.40625, "reward_std": 0.32107165455818176, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 680 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1567.4453125, "completions/mean_terminated_length": 1116.01513671875, "completions/min_length": 533.0, "completions/min_terminated_length": 533.0, "epoch": 0.12083305609155633, "frac_reward_zero_std": 0.5, "grad_norm": 0.3501947224140167, "learning_rate": 6.6e-07, "loss": 0.0294, "num_tokens": 155623298.0, "reward": 0.453125, "reward_std": 0.2160891890525818, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 681 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2013.0, "completions/mean_length": 1573.2421875, "completions/mean_terminated_length": 1083.4127197265625, "completions/min_length": 494.0, "completions/min_terminated_length": 494.0, "epoch": 0.12101049082884202, "frac_reward_zero_std": 0.375, "grad_norm": 0.3801238536834717, "learning_rate": 6.595e-07, "loss": 0.0085, "num_tokens": 155834625.0, "reward": 0.421875, "reward_std": 0.25242161750793457, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 682 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1577.078125, "completions/mean_terminated_length": 1091.2064208984375, "completions/min_length": 545.0, "completions/min_terminated_length": 545.0, "epoch": 0.1211879255661277, "frac_reward_zero_std": 0.5, "grad_norm": 0.33345821499824524, "learning_rate": 6.59e-07, "loss": 0.0144, "num_tokens": 156046443.0, "reward": 0.4296875, "reward_std": 0.1848391890525818, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 683 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.46875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1566.5625, "completions/mean_terminated_length": 1141.7647705078125, "completions/min_length": 524.0, "completions/min_terminated_length": 524.0, "epoch": 0.1213653603034134, "frac_reward_zero_std": 0.5, "grad_norm": 0.36717525124549866, "learning_rate": 6.584999999999999e-07, "loss": 0.0091, "num_tokens": 156256915.0, "reward": 0.5, "reward_std": 0.1971946656703949, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 684 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1175.8046875, "completions/mean_terminated_length": 1068.6929931640625, "completions/min_length": 462.0, "completions/min_terminated_length": 462.0, "epoch": 0.12154279504069909, "frac_reward_zero_std": 0.5, "grad_norm": 0.49501776695251465, "learning_rate": 6.58e-07, "loss": 0.0046, "num_tokens": 156419738.0, "reward": 0.59375, "reward_std": 0.22668421268463135, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 685 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1142.640625, "completions/mean_terminated_length": 1065.915283203125, "completions/min_length": 430.0, "completions/min_terminated_length": 430.0, "epoch": 0.12172022977798479, "frac_reward_zero_std": 0.375, "grad_norm": 0.5402448177337646, "learning_rate": 6.575e-07, "loss": 0.0256, "num_tokens": 156578316.0, "reward": 0.65625, "reward_std": 0.2915782630443573, "rewards/simpleverify_reward/mean": 0.65625, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 686 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.09375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1979.0, "completions/mean_length": 1163.3984375, "completions/mean_terminated_length": 1071.887939453125, "completions/min_length": 473.0, "completions/min_terminated_length": 473.0, "epoch": 0.12189766451527048, "frac_reward_zero_std": 0.25, "grad_norm": 0.5292155146598816, "learning_rate": 6.57e-07, "loss": 0.0391, "num_tokens": 156739551.0, "reward": 0.6171875, "reward_std": 0.32967114448547363, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 687 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2021.0, "completions/mean_length": 1158.6171875, "completions/mean_terminated_length": 1058.0782470703125, "completions/min_length": 452.0, "completions/min_terminated_length": 452.0, "epoch": 0.12207509925255616, "frac_reward_zero_std": 0.25, "grad_norm": 0.5565047860145569, "learning_rate": 6.565e-07, "loss": 0.0423, "num_tokens": 156900174.0, "reward": 0.6171875, "reward_std": 0.29664260149002075, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 688 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1483.90625, "completions/mean_terminated_length": 1236.7191162109375, "completions/min_length": 490.0, "completions/min_terminated_length": 490.0, "epoch": 0.12225253398984186, "frac_reward_zero_std": 0.375, "grad_norm": 0.3914908468723297, "learning_rate": 6.56e-07, "loss": 0.0115, "num_tokens": 157102338.0, "reward": 0.2421875, "reward_std": 0.21763263642787933, "rewards/simpleverify_reward/mean": 0.2421875, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 689 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2014.0, "completions/mean_length": 1459.3203125, "completions/mean_terminated_length": 1161.5177001953125, "completions/min_length": 508.0, "completions/min_terminated_length": 508.0, "epoch": 0.12242996872712755, "frac_reward_zero_std": 0.25, "grad_norm": 0.45787641406059265, "learning_rate": 6.554999999999999e-07, "loss": 0.0141, "num_tokens": 157301355.0, "reward": 0.2265625, "reward_std": 0.259880006313324, "rewards/simpleverify_reward/mean": 0.2265625, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 690 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1440.8828125, "completions/mean_terminated_length": 1174.8426513671875, "completions/min_length": 508.0, "completions/min_terminated_length": 508.0, "epoch": 0.12260740346441325, "frac_reward_zero_std": 0.5, "grad_norm": 0.33934512734413147, "learning_rate": 6.55e-07, "loss": 0.0153, "num_tokens": 157498012.0, "reward": 0.2890625, "reward_std": 0.21342839300632477, "rewards/simpleverify_reward/mean": 0.2890625, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 691 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1478.9609375, "completions/mean_terminated_length": 1229.6068115234375, "completions/min_length": 479.0, "completions/min_terminated_length": 479.0, "epoch": 0.12278483820169894, "frac_reward_zero_std": 0.125, "grad_norm": 0.5112743377685547, "learning_rate": 6.544999999999999e-07, "loss": 0.0053, "num_tokens": 157699543.0, "reward": 0.28125, "reward_std": 0.3047843277454376, "rewards/simpleverify_reward/mean": 0.28125, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 692 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2007.0, "completions/mean_length": 1424.5625, "completions/mean_terminated_length": 1225.319580078125, "completions/min_length": 659.0, "completions/min_terminated_length": 659.0, "epoch": 0.12296227293898462, "frac_reward_zero_std": 0.25, "grad_norm": 0.5509973168373108, "learning_rate": 6.54e-07, "loss": 0.0021, "num_tokens": 157893343.0, "reward": 0.2890625, "reward_std": 0.2601150870323181, "rewards/simpleverify_reward/mean": 0.2890625, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 693 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2019.0, "completions/mean_length": 1421.171875, "completions/mean_terminated_length": 1175.891357421875, "completions/min_length": 589.0, "completions/min_terminated_length": 589.0, "epoch": 0.12313970767627032, "frac_reward_zero_std": 0.25, "grad_norm": 0.6326795220375061, "learning_rate": 6.535e-07, "loss": 0.0164, "num_tokens": 158086709.0, "reward": 0.296875, "reward_std": 0.3237064480781555, "rewards/simpleverify_reward/mean": 0.296875, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 694 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1953.0, "completions/mean_length": 1403.0078125, "completions/mean_terminated_length": 1150.61962890625, "completions/min_length": 517.0, "completions/min_terminated_length": 517.0, "epoch": 0.12331714241355601, "frac_reward_zero_std": 0.125, "grad_norm": 0.5781369805335999, "learning_rate": 6.53e-07, "loss": 0.0144, "num_tokens": 158277750.0, "reward": 0.265625, "reward_std": 0.30457115173339844, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 695 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1935.0, "completions/mean_length": 1392.421875, "completions/mean_terminated_length": 1182.9072265625, "completions/min_length": 593.0, "completions/min_terminated_length": 593.0, "epoch": 0.12349457715084171, "frac_reward_zero_std": 0.25, "grad_norm": 0.5873992443084717, "learning_rate": 6.524999999999999e-07, "loss": 0.0057, "num_tokens": 158467436.0, "reward": 0.3203125, "reward_std": 0.30257564783096313, "rewards/simpleverify_reward/mean": 0.3203125, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 696 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1928.0, "completions/mean_length": 1366.8203125, "completions/mean_terminated_length": 1167.2828369140625, "completions/min_length": 572.0, "completions/min_terminated_length": 572.0, "epoch": 0.1236720118881274, "frac_reward_zero_std": 0.125, "grad_norm": 0.5907487273216248, "learning_rate": 6.52e-07, "loss": 0.0367, "num_tokens": 158652533.0, "reward": 0.5703125, "reward_std": 0.3613291084766388, "rewards/simpleverify_reward/mean": 0.5703125, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 697 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2018.0, "completions/mean_length": 1437.703125, "completions/mean_terminated_length": 1234.2708740234375, "completions/min_length": 637.0, "completions/min_terminated_length": 637.0, "epoch": 0.12384944662541308, "frac_reward_zero_std": 0.125, "grad_norm": 0.5493257641792297, "learning_rate": 6.514999999999999e-07, "loss": 0.0409, "num_tokens": 158846703.0, "reward": 0.5546875, "reward_std": 0.33808407187461853, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 698 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1979.0, "completions/mean_length": 1379.0625, "completions/mean_terminated_length": 1174.28564453125, "completions/min_length": 515.0, "completions/min_terminated_length": 515.0, "epoch": 0.12402688136269878, "frac_reward_zero_std": 0.25, "grad_norm": 0.4814161956310272, "learning_rate": 6.51e-07, "loss": 0.0432, "num_tokens": 159033367.0, "reward": 0.5234375, "reward_std": 0.33981287479400635, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 699 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1413.9453125, "completions/mean_terminated_length": 1228.212158203125, "completions/min_length": 617.0, "completions/min_terminated_length": 617.0, "epoch": 0.12420431609998447, "frac_reward_zero_std": 0.0, "grad_norm": 0.6322165727615356, "learning_rate": 6.505e-07, "loss": 0.0443, "num_tokens": 159224496.0, "reward": 0.5625, "reward_std": 0.44173622131347656, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 700 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1461.265625, "completions/mean_terminated_length": 1174.720947265625, "completions/min_length": 597.0, "completions/min_terminated_length": 597.0, "epoch": 0.12438175083727017, "frac_reward_zero_std": 0.125, "grad_norm": 0.49925708770751953, "learning_rate": 6.5e-07, "loss": 0.0281, "num_tokens": 159423282.0, "reward": 0.4609375, "reward_std": 0.36690834164619446, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 701 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1459.2265625, "completions/mean_terminated_length": 1191.602294921875, "completions/min_length": 527.0, "completions/min_terminated_length": 527.0, "epoch": 0.12455918557455586, "frac_reward_zero_std": 0.125, "grad_norm": 0.475635826587677, "learning_rate": 6.495e-07, "loss": 0.0224, "num_tokens": 159621807.0, "reward": 0.453125, "reward_std": 0.38516929745674133, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 702 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1966.0, "completions/mean_length": 1464.8359375, "completions/mean_terminated_length": 1190.011474609375, "completions/min_length": 537.0, "completions/min_terminated_length": 537.0, "epoch": 0.12473662031184155, "frac_reward_zero_std": 0.25, "grad_norm": 0.41582390666007996, "learning_rate": 6.49e-07, "loss": 0.0146, "num_tokens": 159821050.0, "reward": 0.515625, "reward_std": 0.3267752528190613, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 703 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1990.0, "completions/mean_length": 1461.8359375, "completions/mean_terminated_length": 1195.397705078125, "completions/min_length": 653.0, "completions/min_terminated_length": 653.0, "epoch": 0.12491405504912724, "frac_reward_zero_std": 0.25, "grad_norm": 0.40553364157676697, "learning_rate": 6.484999999999999e-07, "loss": 0.0187, "num_tokens": 160019909.0, "reward": 0.5, "reward_std": 0.31971919536590576, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 704 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1644.78125, "completions/mean_terminated_length": 1310.6856689453125, "completions/min_length": 610.0, "completions/min_terminated_length": 610.0, "epoch": 0.12509148978641293, "frac_reward_zero_std": 0.25, "grad_norm": 0.5030779838562012, "learning_rate": 6.48e-07, "loss": 0.0242, "num_tokens": 160241081.0, "reward": 0.4140625, "reward_std": 0.28915637731552124, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 705 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1627.1484375, "completions/mean_terminated_length": 1329.7467041015625, "completions/min_length": 870.0, "completions/min_terminated_length": 870.0, "epoch": 0.12526892452369862, "frac_reward_zero_std": 0.25, "grad_norm": 0.5119894742965698, "learning_rate": 6.474999999999999e-07, "loss": 0.0019, "num_tokens": 160459996.0, "reward": 0.3984375, "reward_std": 0.25907793641090393, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 706 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2001.0, "completions/mean_length": 1622.4140625, "completions/mean_terminated_length": 1331.2237548828125, "completions/min_length": 607.0, "completions/min_terminated_length": 607.0, "epoch": 0.12544635926098432, "frac_reward_zero_std": 0.125, "grad_norm": 0.556277871131897, "learning_rate": 6.47e-07, "loss": 0.0272, "num_tokens": 160678305.0, "reward": 0.4296875, "reward_std": 0.3238956332206726, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 707 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1644.171875, "completions/mean_terminated_length": 1349.486572265625, "completions/min_length": 587.0, "completions/min_terminated_length": 587.0, "epoch": 0.12562379399827, "frac_reward_zero_std": 0.375, "grad_norm": 0.4379242956638336, "learning_rate": 6.465e-07, "loss": 0.0247, "num_tokens": 160899399.0, "reward": 0.421875, "reward_std": 0.24491733312606812, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 708 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1998.0, "completions/mean_length": 1202.734375, "completions/mean_terminated_length": 1064.4180908203125, "completions/min_length": 399.0, "completions/min_terminated_length": 399.0, "epoch": 0.12580122873555571, "frac_reward_zero_std": 0.125, "grad_norm": 0.5764206647872925, "learning_rate": 6.46e-07, "loss": 0.0303, "num_tokens": 161078965.0, "reward": 0.59375, "reward_std": 0.39678335189819336, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 709 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1969.0, "completions/mean_length": 1144.2421875, "completions/mean_terminated_length": 1033.25439453125, "completions/min_length": 435.0, "completions/min_terminated_length": 435.0, "epoch": 0.1259786634728414, "frac_reward_zero_std": 0.125, "grad_norm": 0.5937316417694092, "learning_rate": 6.454999999999999e-07, "loss": 0.013, "num_tokens": 161251044.0, "reward": 0.6875, "reward_std": 0.35373392701148987, "rewards/simpleverify_reward/mean": 0.6875, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 710 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2009.0, "completions/mean_length": 1183.8046875, "completions/mean_terminated_length": 1060.3482666015625, "completions/min_length": 421.0, "completions/min_terminated_length": 421.0, "epoch": 0.12615609821012708, "frac_reward_zero_std": 0.125, "grad_norm": 0.591524600982666, "learning_rate": 6.45e-07, "loss": 0.0345, "num_tokens": 161428187.0, "reward": 0.6484375, "reward_std": 0.38296055793762207, "rewards/simpleverify_reward/mean": 0.6484375, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 711 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1893.0, "completions/mean_length": 1166.3828125, "completions/mean_terminated_length": 1058.114013671875, "completions/min_length": 425.0, "completions/min_terminated_length": 425.0, "epoch": 0.12633353294741279, "frac_reward_zero_std": 0.0, "grad_norm": 0.6330700516700745, "learning_rate": 6.444999999999999e-07, "loss": 0.0328, "num_tokens": 161603100.0, "reward": 0.6640625, "reward_std": 0.40558475255966187, "rewards/simpleverify_reward/mean": 0.6640625, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 712 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2006.0, "completions/mean_length": 1233.46875, "completions/mean_terminated_length": 1025.8431396484375, "completions/min_length": 521.0, "completions/min_terminated_length": 521.0, "epoch": 0.12651096768469847, "frac_reward_zero_std": 0.25, "grad_norm": 0.5709378123283386, "learning_rate": 6.44e-07, "loss": 0.0028, "num_tokens": 161771704.0, "reward": 0.5390625, "reward_std": 0.32831305265426636, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 713 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2008.0, "completions/mean_length": 1234.46875, "completions/mean_terminated_length": 1037.009765625, "completions/min_length": 523.0, "completions/min_terminated_length": 523.0, "epoch": 0.12668840242198418, "frac_reward_zero_std": 0.25, "grad_norm": 0.5613293051719666, "learning_rate": 6.435e-07, "loss": 0.0027, "num_tokens": 161940436.0, "reward": 0.5703125, "reward_std": 0.31181254982948303, "rewards/simpleverify_reward/mean": 0.5703125, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 714 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1220.1640625, "completions/mean_terminated_length": 1029.125, "completions/min_length": 492.0, "completions/min_terminated_length": 492.0, "epoch": 0.12686583715926986, "frac_reward_zero_std": 0.0, "grad_norm": 0.6471117734909058, "learning_rate": 6.43e-07, "loss": 0.0015, "num_tokens": 162107337.0, "reward": 0.5546875, "reward_std": 0.3554943799972534, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 715 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1950.0, "completions/mean_length": 1238.34375, "completions/mean_terminated_length": 1001.1716918945312, "completions/min_length": 539.0, "completions/min_terminated_length": 539.0, "epoch": 0.12704327189655554, "frac_reward_zero_std": 0.25, "grad_norm": 0.5445898771286011, "learning_rate": 6.424999999999999e-07, "loss": 0.0069, "num_tokens": 162276565.0, "reward": 0.5234375, "reward_std": 0.28321951627731323, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 716 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.53125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1717.5078125, "completions/mean_terminated_length": 1342.9500732421875, "completions/min_length": 782.0, "completions/min_terminated_length": 782.0, "epoch": 0.12722070663384125, "frac_reward_zero_std": 0.375, "grad_norm": 0.48787906765937805, "learning_rate": 6.42e-07, "loss": 0.0234, "num_tokens": 162508374.0, "reward": 0.21875, "reward_std": 0.26802173256874084, "rewards/simpleverify_reward/mean": 0.21875, "rewards/simpleverify_reward/std": 0.41502299904823303, "step": 717 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1717.3671875, "completions/mean_terminated_length": 1376.2381591796875, "completions/min_length": 837.0, "completions/min_terminated_length": 837.0, "epoch": 0.12739814137112693, "frac_reward_zero_std": 0.25, "grad_norm": 0.5229278802871704, "learning_rate": 6.414999999999999e-07, "loss": 0.0187, "num_tokens": 162740165.0, "reward": 0.265625, "reward_std": 0.31447336077690125, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 718 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.46875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2021.0, "completions/mean_length": 1673.59375, "completions/mean_terminated_length": 1343.2353515625, "completions/min_length": 764.0, "completions/min_terminated_length": 764.0, "epoch": 0.12757557610841264, "frac_reward_zero_std": 0.125, "grad_norm": 0.5324886441230774, "learning_rate": 6.41e-07, "loss": 0.0339, "num_tokens": 162966353.0, "reward": 0.3046875, "reward_std": 0.3440170884132385, "rewards/simpleverify_reward/mean": 0.3046875, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 719 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1685.0546875, "completions/mean_terminated_length": 1393.676025390625, "completions/min_length": 889.0, "completions/min_terminated_length": 889.0, "epoch": 0.12775301084569832, "frac_reward_zero_std": 0.25, "grad_norm": 0.49155956506729126, "learning_rate": 6.404999999999999e-07, "loss": 0.036, "num_tokens": 163194008.0, "reward": 0.28125, "reward_std": 0.34351080656051636, "rewards/simpleverify_reward/mean": 0.28125, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 720 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1496.1484375, "completions/mean_terminated_length": 1271.769287109375, "completions/min_length": 659.0, "completions/min_terminated_length": 659.0, "epoch": 0.127930445582984, "frac_reward_zero_std": 0.125, "grad_norm": 0.5539267063140869, "learning_rate": 6.4e-07, "loss": 0.0084, "num_tokens": 163394939.0, "reward": 0.4140625, "reward_std": 0.3805665373802185, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 721 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2003.0, "completions/mean_length": 1497.3828125, "completions/mean_terminated_length": 1247.102294921875, "completions/min_length": 675.0, "completions/min_terminated_length": 675.0, "epoch": 0.1281078803202697, "frac_reward_zero_std": 0.25, "grad_norm": 0.48030364513397217, "learning_rate": 6.395e-07, "loss": 0.0079, "num_tokens": 163596028.0, "reward": 0.4296875, "reward_std": 0.3193970322608948, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 722 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1978.0, "completions/mean_length": 1506.6953125, "completions/mean_terminated_length": 1242.337158203125, "completions/min_length": 717.0, "completions/min_terminated_length": 717.0, "epoch": 0.1282853150575554, "frac_reward_zero_std": 0.125, "grad_norm": 0.5329502820968628, "learning_rate": 6.389999999999999e-07, "loss": 0.0267, "num_tokens": 163798309.0, "reward": 0.390625, "reward_std": 0.39177703857421875, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 723 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1977.0, "completions/mean_length": 1497.390625, "completions/mean_terminated_length": 1264.9111328125, "completions/min_length": 678.0, "completions/min_terminated_length": 678.0, "epoch": 0.1284627497948411, "frac_reward_zero_std": 0.125, "grad_norm": 0.5378173589706421, "learning_rate": 6.384999999999999e-07, "loss": 0.0138, "num_tokens": 163999399.0, "reward": 0.453125, "reward_std": 0.37321737408638, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 724 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2021.0, "completions/mean_length": 1554.90625, "completions/mean_terminated_length": 1346.711181640625, "completions/min_length": 719.0, "completions/min_terminated_length": 719.0, "epoch": 0.12864018453212678, "frac_reward_zero_std": 0.25, "grad_norm": 0.4654092490673065, "learning_rate": 6.38e-07, "loss": 0.0035, "num_tokens": 164209675.0, "reward": 0.25, "reward_std": 0.2977283000946045, "rewards/simpleverify_reward/mean": 0.25, "rewards/simpleverify_reward/std": 0.434714138507843, "step": 725 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1996.0, "completions/mean_length": 1553.0546875, "completions/mean_terminated_length": 1319.8045654296875, "completions/min_length": 724.0, "completions/min_terminated_length": 724.0, "epoch": 0.12881761926941246, "frac_reward_zero_std": 0.25, "grad_norm": 0.47914764285087585, "learning_rate": 6.374999999999999e-07, "loss": 0.004, "num_tokens": 164419714.0, "reward": 0.21875, "reward_std": 0.3209668695926666, "rewards/simpleverify_reward/mean": 0.21875, "rewards/simpleverify_reward/std": 0.41502299904823303, "step": 726 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1551.0, "completions/mean_terminated_length": 1299.5765380859375, "completions/min_length": 716.0, "completions/min_terminated_length": 716.0, "epoch": 0.12899505400669817, "frac_reward_zero_std": 0.25, "grad_norm": 0.4713367521762848, "learning_rate": 6.37e-07, "loss": 0.0088, "num_tokens": 164629490.0, "reward": 0.265625, "reward_std": 0.3047843277454376, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 727 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1536.375, "completions/mean_terminated_length": 1336.1739501953125, "completions/min_length": 639.0, "completions/min_terminated_length": 639.0, "epoch": 0.12917248874398385, "frac_reward_zero_std": 0.375, "grad_norm": 0.45485958456993103, "learning_rate": 6.365e-07, "loss": 0.01, "num_tokens": 164837394.0, "reward": 0.2578125, "reward_std": 0.2815170884132385, "rewards/simpleverify_reward/mean": 0.2578125, "rewards/simpleverify_reward/std": 0.43914902210235596, "step": 728 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1962.0, "completions/mean_length": 1265.4609375, "completions/mean_terminated_length": 1065.990234375, "completions/min_length": 387.0, "completions/min_terminated_length": 387.0, "epoch": 0.12934992348126956, "frac_reward_zero_std": 0.0, "grad_norm": 0.6924700736999512, "learning_rate": 6.36e-07, "loss": 0.0223, "num_tokens": 165010157.0, "reward": 0.4765625, "reward_std": 0.40103617310523987, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 729 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1981.0, "completions/mean_length": 1287.7421875, "completions/mean_terminated_length": 1044.773193359375, "completions/min_length": 416.0, "completions/min_terminated_length": 416.0, "epoch": 0.12952735821855524, "frac_reward_zero_std": 0.25, "grad_norm": 0.6440111994743347, "learning_rate": 6.354999999999999e-07, "loss": 0.0262, "num_tokens": 165185772.0, "reward": 0.484375, "reward_std": 0.35799360275268555, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 730 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2019.0, "completions/mean_length": 1259.4765625, "completions/mean_terminated_length": 1095.82080078125, "completions/min_length": 396.0, "completions/min_terminated_length": 396.0, "epoch": 0.12970479295584092, "frac_reward_zero_std": 0.125, "grad_norm": 0.6612324118614197, "learning_rate": 6.35e-07, "loss": 0.0275, "num_tokens": 165357769.0, "reward": 0.5078125, "reward_std": 0.37305837869644165, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 731 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2006.0, "completions/mean_length": 1237.7109375, "completions/mean_terminated_length": 1041.038818359375, "completions/min_length": 412.0, "completions/min_terminated_length": 412.0, "epoch": 0.12988222769312663, "frac_reward_zero_std": 0.125, "grad_norm": 0.7175538539886475, "learning_rate": 6.344999999999999e-07, "loss": 0.0167, "num_tokens": 165526980.0, "reward": 0.53125, "reward_std": 0.3330235481262207, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 732 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1962.0, "completions/mean_length": 1142.9296875, "completions/mean_terminated_length": 1106.13818359375, "completions/min_length": 420.0, "completions/min_terminated_length": 420.0, "epoch": 0.1300596624304123, "frac_reward_zero_std": 0.125, "grad_norm": 0.7073763608932495, "learning_rate": 6.34e-07, "loss": -0.0005, "num_tokens": 165683035.0, "reward": 0.6640625, "reward_std": 0.3978690803050995, "rewards/simpleverify_reward/mean": 0.6640625, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 733 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1994.0, "completions/mean_length": 1165.1171875, "completions/mean_terminated_length": 1106.2584228515625, "completions/min_length": 423.0, "completions/min_terminated_length": 423.0, "epoch": 0.13023709716769802, "frac_reward_zero_std": 0.125, "grad_norm": 0.7688567042350769, "learning_rate": 6.335e-07, "loss": 0.0066, "num_tokens": 165841930.0, "reward": 0.65625, "reward_std": 0.3827752470970154, "rewards/simpleverify_reward/mean": 0.65625, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 734 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1892.0, "completions/mean_length": 1115.4921875, "completions/mean_terminated_length": 1093.112060546875, "completions/min_length": 412.0, "completions/min_terminated_length": 412.0, "epoch": 0.1304145319049837, "frac_reward_zero_std": 0.125, "grad_norm": 0.7328159213066101, "learning_rate": 6.33e-07, "loss": 0.0186, "num_tokens": 165994473.0, "reward": 0.6875, "reward_std": 0.38094252347946167, "rewards/simpleverify_reward/mean": 0.6875, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 735 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1971.0, "completions/mean_length": 1113.40625, "completions/mean_terminated_length": 1090.97607421875, "completions/min_length": 444.0, "completions/min_terminated_length": 444.0, "epoch": 0.13059196664226938, "frac_reward_zero_std": 0.125, "grad_norm": 0.7545661330223083, "learning_rate": 6.324999999999999e-07, "loss": 0.0164, "num_tokens": 166146749.0, "reward": 0.734375, "reward_std": 0.3314315676689148, "rewards/simpleverify_reward/mean": 0.734375, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 736 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1935.0, "completions/mean_length": 1423.2890625, "completions/mean_terminated_length": 1178.8370361328125, "completions/min_length": 540.0, "completions/min_terminated_length": 540.0, "epoch": 0.1307694013795551, "frac_reward_zero_std": 0.375, "grad_norm": 0.5029528737068176, "learning_rate": 6.319999999999999e-07, "loss": 0.0189, "num_tokens": 166340034.0, "reward": 0.515625, "reward_std": 0.2530868649482727, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 737 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1442.7578125, "completions/mean_terminated_length": 1196.67041015625, "completions/min_length": 564.0, "completions/min_terminated_length": 564.0, "epoch": 0.13094683611684077, "frac_reward_zero_std": 0.25, "grad_norm": 0.5149990320205688, "learning_rate": 6.314999999999999e-07, "loss": 0.0492, "num_tokens": 166535811.0, "reward": 0.5625, "reward_std": 0.3441760540008545, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 738 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2010.0, "completions/mean_length": 1402.78125, "completions/mean_terminated_length": 1169.4041748046875, "completions/min_length": 552.0, "completions/min_terminated_length": 552.0, "epoch": 0.13112427085412648, "frac_reward_zero_std": 0.5, "grad_norm": 0.44429707527160645, "learning_rate": 6.31e-07, "loss": 0.0246, "num_tokens": 166726471.0, "reward": 0.59375, "reward_std": 0.2342950701713562, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 739 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1890.0, "completions/mean_length": 1411.859375, "completions/mean_terminated_length": 1208.556640625, "completions/min_length": 545.0, "completions/min_terminated_length": 545.0, "epoch": 0.13130170559141216, "frac_reward_zero_std": 0.375, "grad_norm": 0.4736509323120117, "learning_rate": 6.304999999999999e-07, "loss": 0.0172, "num_tokens": 166918293.0, "reward": 0.578125, "reward_std": 0.26834267377853394, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 740 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1999.0, "completions/mean_length": 1292.6171875, "completions/mean_terminated_length": 985.4835205078125, "completions/min_length": 360.0, "completions/min_terminated_length": 360.0, "epoch": 0.13147914032869784, "frac_reward_zero_std": 0.25, "grad_norm": 0.667048454284668, "learning_rate": 6.3e-07, "loss": 0.0033, "num_tokens": 167095140.0, "reward": 0.3828125, "reward_std": 0.282634437084198, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 741 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1891.0, "completions/mean_length": 1249.171875, "completions/mean_terminated_length": 971.6842651367188, "completions/min_length": 373.0, "completions/min_terminated_length": 373.0, "epoch": 0.13165657506598355, "frac_reward_zero_std": 0.5, "grad_norm": 0.6542120575904846, "learning_rate": 6.295e-07, "loss": 0.0112, "num_tokens": 167266426.0, "reward": 0.4296875, "reward_std": 0.2312908172607422, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 742 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1294.9921875, "completions/mean_terminated_length": 1022.6276245117188, "completions/min_length": 345.0, "completions/min_terminated_length": 345.0, "epoch": 0.13183400980326923, "frac_reward_zero_std": 0.375, "grad_norm": 0.5650685429573059, "learning_rate": 6.289999999999999e-07, "loss": 0.0145, "num_tokens": 167443577.0, "reward": 0.453125, "reward_std": 0.3044399917125702, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 743 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1822.0, "completions/mean_length": 1282.2421875, "completions/mean_terminated_length": 1016.2421264648438, "completions/min_length": 348.0, "completions/min_terminated_length": 348.0, "epoch": 0.13201144454055494, "frac_reward_zero_std": 0.25, "grad_norm": 0.6115204095840454, "learning_rate": 6.284999999999999e-07, "loss": 0.0396, "num_tokens": 167619096.0, "reward": 0.4609375, "reward_std": 0.3181428909301758, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 744 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1986.0, "completions/mean_length": 1577.71875, "completions/mean_terminated_length": 1348.0465087890625, "completions/min_length": 580.0, "completions/min_terminated_length": 580.0, "epoch": 0.13218887927784062, "frac_reward_zero_std": 0.375, "grad_norm": 0.4915173053741455, "learning_rate": 6.28e-07, "loss": 0.0141, "num_tokens": 167839380.0, "reward": 0.4140625, "reward_std": 0.24667394161224365, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 745 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1992.0, "completions/mean_length": 1593.1953125, "completions/mean_terminated_length": 1363.11767578125, "completions/min_length": 597.0, "completions/min_terminated_length": 597.0, "epoch": 0.1323663140151263, "frac_reward_zero_std": 0.375, "grad_norm": 0.48459357023239136, "learning_rate": 6.274999999999999e-07, "loss": 0.0049, "num_tokens": 168061645.0, "reward": 0.390625, "reward_std": 0.2191799283027649, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 746 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1992.0, "completions/mean_length": 1576.8203125, "completions/mean_terminated_length": 1362.6478271484375, "completions/min_length": 618.0, "completions/min_terminated_length": 618.0, "epoch": 0.132543748752412, "frac_reward_zero_std": 0.25, "grad_norm": 0.49250495433807373, "learning_rate": 6.27e-07, "loss": 0.0193, "num_tokens": 168281814.0, "reward": 0.40625, "reward_std": 0.27507779002189636, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 747 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1559.984375, "completions/mean_terminated_length": 1346.1348876953125, "completions/min_length": 630.0, "completions/min_terminated_length": 630.0, "epoch": 0.1327211834896977, "frac_reward_zero_std": 0.25, "grad_norm": 1.020601511001587, "learning_rate": 6.265e-07, "loss": 0.0128, "num_tokens": 168499828.0, "reward": 0.4296875, "reward_std": 0.2777385711669922, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 748 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2011.0, "completions/mean_length": 1360.640625, "completions/mean_terminated_length": 1185.431396484375, "completions/min_length": 370.0, "completions/min_terminated_length": 370.0, "epoch": 0.1328986182269834, "frac_reward_zero_std": 0.25, "grad_norm": 0.5449454188346863, "learning_rate": 6.26e-07, "loss": 0.0276, "num_tokens": 168684726.0, "reward": 0.515625, "reward_std": 0.3160709738731384, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 749 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2013.0, "completions/mean_length": 1279.1796875, "completions/mean_terminated_length": 1119.61328125, "completions/min_length": 330.0, "completions/min_terminated_length": 330.0, "epoch": 0.13307605296426908, "frac_reward_zero_std": 0.5, "grad_norm": 0.471177875995636, "learning_rate": 6.254999999999999e-07, "loss": 0.0329, "num_tokens": 168859197.0, "reward": 0.4765625, "reward_std": 0.24622182548046112, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 750 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1291.296875, "completions/mean_terminated_length": 1116.673095703125, "completions/min_length": 400.0, "completions/min_terminated_length": 400.0, "epoch": 0.13325348770155476, "frac_reward_zero_std": 0.375, "grad_norm": 0.523776650428772, "learning_rate": 6.249999999999999e-07, "loss": 0.0445, "num_tokens": 169035219.0, "reward": 0.4609375, "reward_std": 0.25966301560401917, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 751 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1985.0, "completions/mean_length": 1283.78125, "completions/mean_terminated_length": 1166.73876953125, "completions/min_length": 397.0, "completions/min_terminated_length": 397.0, "epoch": 0.13343092243884047, "frac_reward_zero_std": 0.25, "grad_norm": 0.5659192800521851, "learning_rate": 6.245e-07, "loss": 0.0058, "num_tokens": 169210279.0, "reward": 0.453125, "reward_std": 0.3100011348724365, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 752 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1242.8359375, "completions/mean_terminated_length": 890.01123046875, "completions/min_length": 322.0, "completions/min_terminated_length": 322.0, "epoch": 0.13360835717612615, "frac_reward_zero_std": 0.375, "grad_norm": 0.7069109678268433, "learning_rate": 6.24e-07, "loss": 0.0008, "num_tokens": 169377826.0, "reward": 0.453125, "reward_std": 0.24776911735534668, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 753 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1250.890625, "completions/mean_terminated_length": 901.5955200195312, "completions/min_length": 344.0, "completions/min_terminated_length": 344.0, "epoch": 0.13378579191341186, "frac_reward_zero_std": 0.25, "grad_norm": 0.6472541689872742, "learning_rate": 6.235e-07, "loss": 0.002, "num_tokens": 169546404.0, "reward": 0.5390625, "reward_std": 0.27398645877838135, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 754 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1801.0, "completions/mean_length": 1237.953125, "completions/mean_terminated_length": 895.933349609375, "completions/min_length": 427.0, "completions/min_terminated_length": 427.0, "epoch": 0.13396322665069754, "frac_reward_zero_std": 0.25, "grad_norm": 0.7350425720214844, "learning_rate": 6.23e-07, "loss": 0.0199, "num_tokens": 169713326.0, "reward": 0.5078125, "reward_std": 0.2902793884277344, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 755 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2006.0, "completions/mean_length": 1260.234375, "completions/mean_terminated_length": 875.5115966796875, "completions/min_length": 358.0, "completions/min_terminated_length": 358.0, "epoch": 0.13414066138798322, "frac_reward_zero_std": 0.375, "grad_norm": 0.6750327944755554, "learning_rate": 6.225000000000001e-07, "loss": 0.0232, "num_tokens": 169883100.0, "reward": 0.4453125, "reward_std": 0.2876671254634857, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 756 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1967.0, "completions/mean_length": 1573.0234375, "completions/mean_terminated_length": 1297.4197998046875, "completions/min_length": 456.0, "completions/min_terminated_length": 456.0, "epoch": 0.13431809612526893, "frac_reward_zero_std": 0.625, "grad_norm": 0.33026203513145447, "learning_rate": 6.219999999999999e-07, "loss": 0.0138, "num_tokens": 170097455.0, "reward": 0.1953125, "reward_std": 0.14305339753627777, "rewards/simpleverify_reward/mean": 0.1953125, "rewards/simpleverify_reward/std": 0.3979988098144531, "step": 757 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1583.1796875, "completions/mean_terminated_length": 1339.702392578125, "completions/min_length": 493.0, "completions/min_terminated_length": 493.0, "epoch": 0.1344955308625546, "frac_reward_zero_std": 0.625, "grad_norm": 0.35756292939186096, "learning_rate": 6.215e-07, "loss": 0.0149, "num_tokens": 170313110.0, "reward": 0.2109375, "reward_std": 0.1606174111366272, "rewards/simpleverify_reward/mean": 0.2109375, "rewards/simpleverify_reward/std": 0.4095771610736847, "step": 758 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1583.4921875, "completions/mean_terminated_length": 1372.352294921875, "completions/min_length": 459.0, "completions/min_terminated_length": 459.0, "epoch": 0.13467296559984032, "frac_reward_zero_std": 0.5, "grad_norm": 0.37917274236679077, "learning_rate": 6.21e-07, "loss": 0.0019, "num_tokens": 170528805.0, "reward": 0.2265625, "reward_std": 0.20331305265426636, "rewards/simpleverify_reward/mean": 0.2265625, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 759 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1575.84375, "completions/mean_terminated_length": 1292.550048828125, "completions/min_length": 443.0, "completions/min_terminated_length": 443.0, "epoch": 0.134850400337126, "frac_reward_zero_std": 0.5, "grad_norm": 0.4125700891017914, "learning_rate": 6.205e-07, "loss": 0.0109, "num_tokens": 170743521.0, "reward": 0.203125, "reward_std": 0.16769562661647797, "rewards/simpleverify_reward/mean": 0.203125, "rewards/simpleverify_reward/std": 0.40390563011169434, "step": 760 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1274.9765625, "completions/mean_terminated_length": 972.4891357421875, "completions/min_length": 364.0, "completions/min_terminated_length": 364.0, "epoch": 0.13502783507441168, "frac_reward_zero_std": 0.125, "grad_norm": 0.7809562087059021, "learning_rate": 6.2e-07, "loss": 0.0008, "num_tokens": 170914462.0, "reward": 0.5546875, "reward_std": 0.3823811411857605, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 761 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1972.0, "completions/mean_length": 1281.6171875, "completions/mean_terminated_length": 981.728271484375, "completions/min_length": 322.0, "completions/min_terminated_length": 322.0, "epoch": 0.1352052698116974, "frac_reward_zero_std": 0.0, "grad_norm": 0.6561772227287292, "learning_rate": 6.195000000000001e-07, "loss": 0.0164, "num_tokens": 171086253.0, "reward": 0.5859375, "reward_std": 0.41303902864456177, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 762 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1947.0, "completions/mean_length": 1239.640625, "completions/mean_terminated_length": 1002.8485107421875, "completions/min_length": 313.0, "completions/min_terminated_length": 313.0, "epoch": 0.13538270454898307, "frac_reward_zero_std": 0.0, "grad_norm": 0.7437065243721008, "learning_rate": 6.189999999999999e-07, "loss": 0.022, "num_tokens": 171252671.0, "reward": 0.609375, "reward_std": 0.4149797558784485, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 763 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1964.0, "completions/mean_length": 1269.6953125, "completions/mean_terminated_length": 976.7849731445312, "completions/min_length": 322.0, "completions/min_terminated_length": 322.0, "epoch": 0.13556013928626878, "frac_reward_zero_std": 0.25, "grad_norm": 0.5353446006774902, "learning_rate": 6.185e-07, "loss": 0.0134, "num_tokens": 171422936.0, "reward": 0.609375, "reward_std": 0.336323618888855, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 764 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2007.0, "completions/mean_length": 1685.65625, "completions/mean_terminated_length": 1261.8983154296875, "completions/min_length": 735.0, "completions/min_terminated_length": 735.0, "epoch": 0.13573757402355446, "frac_reward_zero_std": 0.375, "grad_norm": 0.3970658481121063, "learning_rate": 6.18e-07, "loss": 0.008, "num_tokens": 171654956.0, "reward": 0.2421875, "reward_std": 0.19828036427497864, "rewards/simpleverify_reward/mean": 0.2421875, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 765 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1672.4765625, "completions/mean_terminated_length": 1308.5076904296875, "completions/min_length": 763.0, "completions/min_terminated_length": 763.0, "epoch": 0.13591500876084014, "frac_reward_zero_std": 0.625, "grad_norm": 0.3328665494918823, "learning_rate": 6.175e-07, "loss": 0.0005, "num_tokens": 171885289.0, "reward": 0.2265625, "reward_std": 0.14943468570709229, "rewards/simpleverify_reward/mean": 0.2265625, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 766 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2020.0, "completions/mean_length": 1671.15625, "completions/mean_terminated_length": 1270.0, "completions/min_length": 754.0, "completions/min_terminated_length": 754.0, "epoch": 0.13609244349812585, "frac_reward_zero_std": 0.625, "grad_norm": 0.3130190074443817, "learning_rate": 6.17e-07, "loss": 0.0011, "num_tokens": 172115453.0, "reward": 0.2734375, "reward_std": 0.12984731793403625, "rewards/simpleverify_reward/mean": 0.2734375, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 767 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5546875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1699.109375, "completions/mean_terminated_length": 1264.5263671875, "completions/min_length": 784.0, "completions/min_terminated_length": 784.0, "epoch": 0.13626987823541153, "frac_reward_zero_std": 0.25, "grad_norm": 0.447031170129776, "learning_rate": 6.165e-07, "loss": 0.0158, "num_tokens": 172349195.0, "reward": 0.2421875, "reward_std": 0.2504299283027649, "rewards/simpleverify_reward/mean": 0.2421875, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 768 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1887.0, "completions/mean_length": 1304.484375, "completions/mean_terminated_length": 1158.5606689453125, "completions/min_length": 607.0, "completions/min_terminated_length": 607.0, "epoch": 0.13644731297269724, "frac_reward_zero_std": 0.125, "grad_norm": 0.6327698230743408, "learning_rate": 6.16e-07, "loss": 0.0265, "num_tokens": 172530217.0, "reward": 0.6015625, "reward_std": 0.3501671254634857, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 769 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1925.0, "completions/mean_length": 1309.546875, "completions/mean_terminated_length": 1156.2830810546875, "completions/min_length": 582.0, "completions/min_terminated_length": 582.0, "epoch": 0.13662474770998292, "frac_reward_zero_std": 0.25, "grad_norm": 0.4802011251449585, "learning_rate": 6.155e-07, "loss": 0.0312, "num_tokens": 172711887.0, "reward": 0.6484375, "reward_std": 0.33364027738571167, "rewards/simpleverify_reward/mean": 0.6484375, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 770 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1923.0, "completions/mean_length": 1274.53125, "completions/mean_terminated_length": 1139.7064208984375, "completions/min_length": 595.0, "completions/min_terminated_length": 595.0, "epoch": 0.1368021824472686, "frac_reward_zero_std": 0.25, "grad_norm": 0.5211946368217468, "learning_rate": 6.149999999999999e-07, "loss": 0.0229, "num_tokens": 172889075.0, "reward": 0.65625, "reward_std": 0.3366774320602417, "rewards/simpleverify_reward/mean": 0.65625, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 771 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1298.4140625, "completions/mean_terminated_length": 1198.9114990234375, "completions/min_length": 589.0, "completions/min_terminated_length": 589.0, "epoch": 0.13697961718455431, "frac_reward_zero_std": 0.125, "grad_norm": 0.5557469129562378, "learning_rate": 6.145e-07, "loss": 0.0147, "num_tokens": 173069320.0, "reward": 0.609375, "reward_std": 0.3321193754673004, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 772 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1991.0, "completions/mean_length": 1225.7890625, "completions/mean_terminated_length": 1099.8648681640625, "completions/min_length": 471.0, "completions/min_terminated_length": 471.0, "epoch": 0.13715705192184, "frac_reward_zero_std": 0.5, "grad_norm": 0.39187368750572205, "learning_rate": 6.14e-07, "loss": 0.0183, "num_tokens": 173236285.0, "reward": 0.5703125, "reward_std": 0.2185424566268921, "rewards/simpleverify_reward/mean": 0.5703125, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 773 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1239.6640625, "completions/mean_terminated_length": 1062.60009765625, "completions/min_length": 481.0, "completions/min_terminated_length": 481.0, "epoch": 0.1373344866591257, "frac_reward_zero_std": 0.375, "grad_norm": 0.4627130627632141, "learning_rate": 6.135e-07, "loss": 0.0066, "num_tokens": 173405026.0, "reward": 0.484375, "reward_std": 0.23456305265426636, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 774 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1291.8671875, "completions/mean_terminated_length": 1070.373779296875, "completions/min_length": 479.0, "completions/min_terminated_length": 479.0, "epoch": 0.13751192139641139, "frac_reward_zero_std": 0.375, "grad_norm": 0.4416593015193939, "learning_rate": 6.13e-07, "loss": 0.0101, "num_tokens": 173580449.0, "reward": 0.484375, "reward_std": 0.2066391110420227, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 775 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2004.0, "completions/mean_length": 1245.6328125, "completions/mean_terminated_length": 1060.47119140625, "completions/min_length": 443.0, "completions/min_terminated_length": 443.0, "epoch": 0.13768935613369707, "frac_reward_zero_std": 0.375, "grad_norm": 0.46934592723846436, "learning_rate": 6.125000000000001e-07, "loss": 0.02, "num_tokens": 173749954.0, "reward": 0.546875, "reward_std": 0.24228432774543762, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 776 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1310.4765625, "completions/mean_terminated_length": 1074.773193359375, "completions/min_length": 452.0, "completions/min_terminated_length": 452.0, "epoch": 0.13786679087098277, "frac_reward_zero_std": 0.5, "grad_norm": 0.43048590421676636, "learning_rate": 6.119999999999999e-07, "loss": -0.0034, "num_tokens": 173927343.0, "reward": 0.375, "reward_std": 0.20709684491157532, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 777 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1322.6875, "completions/mean_terminated_length": 1049.720458984375, "completions/min_length": 505.0, "completions/min_terminated_length": 505.0, "epoch": 0.13804422560826846, "frac_reward_zero_std": 0.5, "grad_norm": 0.34339818358421326, "learning_rate": 6.115e-07, "loss": 0.0106, "num_tokens": 174106295.0, "reward": 0.3515625, "reward_std": 0.18119096755981445, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 778 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1332.7421875, "completions/mean_terminated_length": 1063.55908203125, "completions/min_length": 470.0, "completions/min_terminated_length": 470.0, "epoch": 0.13822166034555414, "frac_reward_zero_std": 0.5, "grad_norm": 0.3460698127746582, "learning_rate": 6.11e-07, "loss": 0.015, "num_tokens": 174286534.0, "reward": 0.3515625, "reward_std": 0.17743882536888123, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 779 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1997.0, "completions/mean_length": 1344.6484375, "completions/mean_terminated_length": 1129.336669921875, "completions/min_length": 473.0, "completions/min_terminated_length": 473.0, "epoch": 0.13839909508283985, "frac_reward_zero_std": 0.5, "grad_norm": 0.4472050070762634, "learning_rate": 6.105e-07, "loss": 0.0037, "num_tokens": 174468297.0, "reward": 0.390625, "reward_std": 0.2066391110420227, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 780 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1817.734375, "completions/mean_terminated_length": 1548.440673828125, "completions/min_length": 874.0, "completions/min_terminated_length": 874.0, "epoch": 0.13857652982012553, "frac_reward_zero_std": 0.125, "grad_norm": 0.5566094517707825, "learning_rate": 6.1e-07, "loss": 0.0101, "num_tokens": 174713335.0, "reward": 0.3359375, "reward_std": 0.35075217485427856, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 781 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2004.0, "completions/mean_length": 1814.0703125, "completions/mean_terminated_length": 1587.3385009765625, "completions/min_length": 883.0, "completions/min_terminated_length": 883.0, "epoch": 0.13875396455741124, "frac_reward_zero_std": 0.0, "grad_norm": 0.5495970249176025, "learning_rate": 6.095e-07, "loss": 0.0096, "num_tokens": 174957904.0, "reward": 0.328125, "reward_std": 0.3631020188331604, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 782 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1781.5, "completions/mean_terminated_length": 1531.151611328125, "completions/min_length": 787.0, "completions/min_terminated_length": 787.0, "epoch": 0.13893139929469692, "frac_reward_zero_std": 0.125, "grad_norm": 0.5564880967140198, "learning_rate": 6.089999999999999e-07, "loss": 0.0177, "num_tokens": 175198304.0, "reward": 0.4140625, "reward_std": 0.37806469202041626, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 783 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1768.2734375, "completions/mean_terminated_length": 1529.0870361328125, "completions/min_length": 860.0, "completions/min_terminated_length": 860.0, "epoch": 0.1391088340319826, "frac_reward_zero_std": 0.375, "grad_norm": 0.45983508229255676, "learning_rate": 6.085e-07, "loss": 0.0137, "num_tokens": 175437011.0, "reward": 0.328125, "reward_std": 0.29930341243743896, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 784 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1549.5078125, "completions/mean_terminated_length": 1173.9315185546875, "completions/min_length": 635.0, "completions/min_terminated_length": 635.0, "epoch": 0.1392862687692683, "frac_reward_zero_std": 0.5, "grad_norm": 0.5041157007217407, "learning_rate": 6.079999999999999e-07, "loss": 0.0031, "num_tokens": 175650004.0, "reward": 0.4375, "reward_std": 0.21497184038162231, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 785 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1552.015625, "completions/mean_terminated_length": 1212.657958984375, "completions/min_length": 614.0, "completions/min_terminated_length": 614.0, "epoch": 0.139463703506554, "frac_reward_zero_std": 0.25, "grad_norm": 0.594780445098877, "learning_rate": 6.075e-07, "loss": 0.0155, "num_tokens": 175863318.0, "reward": 0.375, "reward_std": 0.2997780442237854, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 786 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1544.078125, "completions/mean_terminated_length": 1221.05126953125, "completions/min_length": 554.0, "completions/min_terminated_length": 554.0, "epoch": 0.1396411382438397, "frac_reward_zero_std": 0.25, "grad_norm": 0.5163488984107971, "learning_rate": 6.07e-07, "loss": 0.0055, "num_tokens": 176075616.0, "reward": 0.4375, "reward_std": 0.3122924566268921, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 787 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2007.0, "completions/mean_length": 1530.9765625, "completions/mean_terminated_length": 1141.4383544921875, "completions/min_length": 589.0, "completions/min_terminated_length": 589.0, "epoch": 0.13981857298112538, "frac_reward_zero_std": 0.5, "grad_norm": 0.46399638056755066, "learning_rate": 6.065e-07, "loss": 0.0139, "num_tokens": 176286237.0, "reward": 0.453125, "reward_std": 0.237278014421463, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 788 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1339.6171875, "completions/mean_terminated_length": 981.2588500976562, "completions/min_length": 526.0, "completions/min_terminated_length": 526.0, "epoch": 0.13999600771841106, "frac_reward_zero_std": 0.5, "grad_norm": 0.53806471824646, "learning_rate": 6.06e-07, "loss": 0.0027, "num_tokens": 176468636.0, "reward": 0.5234375, "reward_std": 0.2039783000946045, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 789 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1326.0234375, "completions/mean_terminated_length": 934.59033203125, "completions/min_length": 551.0, "completions/min_terminated_length": 551.0, "epoch": 0.14017344245569677, "frac_reward_zero_std": 0.5, "grad_norm": 0.5614297986030579, "learning_rate": 6.055e-07, "loss": 0.0118, "num_tokens": 176649295.0, "reward": 0.5546875, "reward_std": 0.19362401962280273, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 790 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1314.09375, "completions/mean_terminated_length": 888.2469482421875, "completions/min_length": 495.0, "completions/min_terminated_length": 495.0, "epoch": 0.14035087719298245, "frac_reward_zero_std": 0.375, "grad_norm": 0.5882228016853333, "learning_rate": 6.049999999999999e-07, "loss": 0.002, "num_tokens": 176828427.0, "reward": 0.5234375, "reward_std": 0.21763263642787933, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 791 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2012.0, "completions/mean_length": 1333.453125, "completions/mean_terminated_length": 904.7250366210938, "completions/min_length": 508.0, "completions/min_terminated_length": 508.0, "epoch": 0.14052831193026816, "frac_reward_zero_std": 0.5, "grad_norm": 0.5218134522438049, "learning_rate": 6.045e-07, "loss": 0.0104, "num_tokens": 177010037.0, "reward": 0.5390625, "reward_std": 0.18837818503379822, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 792 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1958.0, "completions/mean_length": 1538.3359375, "completions/mean_terminated_length": 1166.4189453125, "completions/min_length": 623.0, "completions/min_terminated_length": 623.0, "epoch": 0.14070574666755384, "frac_reward_zero_std": 0.375, "grad_norm": 0.5167847871780396, "learning_rate": 6.04e-07, "loss": -0.0004, "num_tokens": 177216848.0, "reward": 0.3984375, "reward_std": 0.26408424973487854, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 793 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1527.625, "completions/mean_terminated_length": 1171.5789794921875, "completions/min_length": 659.0, "completions/min_terminated_length": 659.0, "epoch": 0.14088318140483952, "frac_reward_zero_std": 0.25, "grad_norm": 0.6068069338798523, "learning_rate": 6.035e-07, "loss": 0.0044, "num_tokens": 177422288.0, "reward": 0.40625, "reward_std": 0.30832332372665405, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 794 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1554.2421875, "completions/mean_terminated_length": 1205.320068359375, "completions/min_length": 649.0, "completions/min_terminated_length": 649.0, "epoch": 0.14106061614212523, "frac_reward_zero_std": 0.375, "grad_norm": 0.5525851249694824, "learning_rate": 6.03e-07, "loss": 0.0196, "num_tokens": 177631135.0, "reward": 0.453125, "reward_std": 0.27824485301971436, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 795 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2002.0, "completions/mean_length": 1537.3046875, "completions/mean_terminated_length": 1209.9359130859375, "completions/min_length": 617.0, "completions/min_terminated_length": 617.0, "epoch": 0.1412380508794109, "frac_reward_zero_std": 0.25, "grad_norm": 0.5112963914871216, "learning_rate": 6.025000000000001e-07, "loss": 0.0107, "num_tokens": 177837814.0, "reward": 0.4609375, "reward_std": 0.3133876323699951, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 796 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1463.1796875, "completions/mean_terminated_length": 1049.90673828125, "completions/min_length": 556.0, "completions/min_terminated_length": 556.0, "epoch": 0.14141548561669662, "frac_reward_zero_std": 0.375, "grad_norm": 0.5590913891792297, "learning_rate": 6.019999999999999e-07, "loss": 0.0019, "num_tokens": 178034445.0, "reward": 0.3828125, "reward_std": 0.2392735779285431, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 797 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2022.0, "completions/mean_length": 1482.875, "completions/mean_terminated_length": 1132.3544921875, "completions/min_length": 573.0, "completions/min_terminated_length": 573.0, "epoch": 0.1415929203539823, "frac_reward_zero_std": 0.5, "grad_norm": 0.5370381474494934, "learning_rate": 6.015e-07, "loss": 0.0015, "num_tokens": 178233597.0, "reward": 0.453125, "reward_std": 0.2290782630443573, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 798 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1471.96875, "completions/mean_terminated_length": 1102.718017578125, "completions/min_length": 546.0, "completions/min_terminated_length": 546.0, "epoch": 0.14177035509126798, "frac_reward_zero_std": 0.5, "grad_norm": 0.508191704750061, "learning_rate": 6.009999999999999e-07, "loss": 0.013, "num_tokens": 178431353.0, "reward": 0.421875, "reward_std": 0.22234314680099487, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 799 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2016.0, "completions/mean_length": 1503.015625, "completions/mean_terminated_length": 1142.052001953125, "completions/min_length": 542.0, "completions/min_terminated_length": 542.0, "epoch": 0.1419477898285537, "frac_reward_zero_std": 0.5, "grad_norm": 0.5308178663253784, "learning_rate": 6.005e-07, "loss": 0.0012, "num_tokens": 178633083.0, "reward": 0.421875, "reward_std": 0.24228432774543762, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 800 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1916.0, "completions/mean_length": 1459.171875, "completions/mean_terminated_length": 1191.522705078125, "completions/min_length": 522.0, "completions/min_terminated_length": 522.0, "epoch": 0.14212522456583937, "frac_reward_zero_std": 0.5, "grad_norm": 0.4173080623149872, "learning_rate": 6e-07, "loss": 0.0073, "num_tokens": 178836241.0, "reward": 0.4140625, "reward_std": 0.17743882536888123, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 801 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1456.921875, "completions/mean_terminated_length": 1197.91015625, "completions/min_length": 424.0, "completions/min_terminated_length": 424.0, "epoch": 0.14230265930312508, "frac_reward_zero_std": 0.375, "grad_norm": 0.5077956318855286, "learning_rate": 5.995e-07, "loss": 0.0095, "num_tokens": 179039111.0, "reward": 0.453125, "reward_std": 0.22359731793403625, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 802 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1472.2109375, "completions/mean_terminated_length": 1246.9022216796875, "completions/min_length": 460.0, "completions/min_terminated_length": 460.0, "epoch": 0.14248009404041076, "frac_reward_zero_std": 0.625, "grad_norm": 0.4251132309436798, "learning_rate": 5.989999999999999e-07, "loss": 0.0095, "num_tokens": 179243938.0, "reward": 0.453125, "reward_std": 0.16613000631332397, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 803 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1469.8359375, "completions/mean_terminated_length": 1225.7222900390625, "completions/min_length": 484.0, "completions/min_terminated_length": 484.0, "epoch": 0.14265752877769644, "frac_reward_zero_std": 0.5, "grad_norm": 0.43637123703956604, "learning_rate": 5.985e-07, "loss": 0.0168, "num_tokens": 179448461.0, "reward": 0.421875, "reward_std": 0.18090170621871948, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 804 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1514.1171875, "completions/mean_terminated_length": 1234.46435546875, "completions/min_length": 502.0, "completions/min_terminated_length": 502.0, "epoch": 0.14283496351498215, "frac_reward_zero_std": 0.375, "grad_norm": 0.4362834095954895, "learning_rate": 5.979999999999999e-07, "loss": 0.0334, "num_tokens": 179650396.0, "reward": 0.4765625, "reward_std": 0.2942485213279724, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 805 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1927.0, "completions/mean_length": 1486.640625, "completions/mean_terminated_length": 1202.6588134765625, "completions/min_length": 480.0, "completions/min_terminated_length": 480.0, "epoch": 0.14301239825226783, "frac_reward_zero_std": 0.25, "grad_norm": 0.6600541472434998, "learning_rate": 5.975e-07, "loss": 0.0426, "num_tokens": 179848814.0, "reward": 0.4453125, "reward_std": 0.2827712595462799, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 806 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1448.8671875, "completions/mean_terminated_length": 1223.3870849609375, "completions/min_length": 501.0, "completions/min_terminated_length": 501.0, "epoch": 0.14318983298955354, "frac_reward_zero_std": 0.375, "grad_norm": 0.5034757256507874, "learning_rate": 5.97e-07, "loss": 0.0401, "num_tokens": 180042397.0, "reward": 0.4921875, "reward_std": 0.2926734387874603, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 807 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2022.0, "completions/mean_length": 1494.5859375, "completions/mean_terminated_length": 1243.0341796875, "completions/min_length": 500.0, "completions/min_terminated_length": 500.0, "epoch": 0.14336726772683922, "frac_reward_zero_std": 0.25, "grad_norm": 0.5049775242805481, "learning_rate": 5.965e-07, "loss": 0.0186, "num_tokens": 180241832.0, "reward": 0.453125, "reward_std": 0.3304169476032257, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 808 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1333.3046875, "completions/mean_terminated_length": 1151.12744140625, "completions/min_length": 518.0, "completions/min_terminated_length": 518.0, "epoch": 0.1435447024641249, "frac_reward_zero_std": 0.25, "grad_norm": 0.5306967496871948, "learning_rate": 5.96e-07, "loss": 0.0543, "num_tokens": 180423215.0, "reward": 0.4296875, "reward_std": 0.3658711910247803, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 809 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1355.234375, "completions/mean_terminated_length": 1211.452880859375, "completions/min_length": 530.0, "completions/min_terminated_length": 530.0, "epoch": 0.1437221372014106, "frac_reward_zero_std": 0.125, "grad_norm": 0.5671568512916565, "learning_rate": 5.955e-07, "loss": 0.0555, "num_tokens": 180607405.0, "reward": 0.4375, "reward_std": 0.3937145471572876, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 810 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1328.40625, "completions/mean_terminated_length": 1202.972412109375, "completions/min_length": 427.0, "completions/min_terminated_length": 427.0, "epoch": 0.1438995719386963, "frac_reward_zero_std": 0.25, "grad_norm": 0.7333787679672241, "learning_rate": 5.949999999999999e-07, "loss": 0.022, "num_tokens": 180788161.0, "reward": 0.390625, "reward_std": 0.3285759389400482, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 811 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1328.1953125, "completions/mean_terminated_length": 1225.3660888671875, "completions/min_length": 504.0, "completions/min_terminated_length": 504.0, "epoch": 0.144077006675982, "frac_reward_zero_std": 0.125, "grad_norm": 0.8419047594070435, "learning_rate": 5.945e-07, "loss": 0.0369, "num_tokens": 180968890.0, "reward": 0.453125, "reward_std": 0.3768421709537506, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 812 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.46875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2015.0, "completions/mean_length": 1668.265625, "completions/mean_terminated_length": 1333.2059326171875, "completions/min_length": 665.0, "completions/min_terminated_length": 665.0, "epoch": 0.14425444141326768, "frac_reward_zero_std": 0.125, "grad_norm": 0.5588064789772034, "learning_rate": 5.939999999999999e-07, "loss": 0.0226, "num_tokens": 181193948.0, "reward": 0.484375, "reward_std": 0.3616127669811249, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 813 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1952.0, "completions/mean_length": 1652.9765625, "completions/mean_terminated_length": 1355.356201171875, "completions/min_length": 701.0, "completions/min_terminated_length": 701.0, "epoch": 0.14443187615055336, "frac_reward_zero_std": 0.125, "grad_norm": 0.5255189538002014, "learning_rate": 5.935e-07, "loss": 0.0248, "num_tokens": 181417049.0, "reward": 0.5546875, "reward_std": 0.32533007860183716, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 814 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1649.90625, "completions/mean_terminated_length": 1359.4053955078125, "completions/min_length": 743.0, "completions/min_terminated_length": 743.0, "epoch": 0.14460931088783907, "frac_reward_zero_std": 0.375, "grad_norm": 0.4366391599178314, "learning_rate": 5.93e-07, "loss": 0.0143, "num_tokens": 181639757.0, "reward": 0.515625, "reward_std": 0.2913650870323181, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 815 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1981.0, "completions/mean_length": 1611.2578125, "completions/mean_terminated_length": 1349.2125244140625, "completions/min_length": 691.0, "completions/min_terminated_length": 691.0, "epoch": 0.14478674562512475, "frac_reward_zero_std": 0.125, "grad_norm": 0.567513108253479, "learning_rate": 5.925e-07, "loss": 0.0116, "num_tokens": 181857518.0, "reward": 0.53125, "reward_std": 0.38029977679252625, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 816 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1286.6875, "completions/mean_terminated_length": 1162.1090087890625, "completions/min_length": 460.0, "completions/min_terminated_length": 460.0, "epoch": 0.14496418036241046, "frac_reward_zero_std": 0.125, "grad_norm": 0.6743841171264648, "learning_rate": 5.919999999999999e-07, "loss": 0.0055, "num_tokens": 182031350.0, "reward": 0.453125, "reward_std": 0.4165877401828766, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 817 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1888.0, "completions/mean_length": 1291.5390625, "completions/mean_terminated_length": 1134.5377197265625, "completions/min_length": 441.0, "completions/min_terminated_length": 441.0, "epoch": 0.14514161509969614, "frac_reward_zero_std": 0.125, "grad_norm": 0.703214168548584, "learning_rate": 5.915e-07, "loss": 0.0156, "num_tokens": 182205803.0, "reward": 0.5, "reward_std": 0.39476001262664795, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 818 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1991.0, "completions/mean_length": 1207.2109375, "completions/mean_terminated_length": 1095.601806640625, "completions/min_length": 446.0, "completions/min_terminated_length": 446.0, "epoch": 0.14531904983698182, "frac_reward_zero_std": 0.125, "grad_norm": 0.7005196213722229, "learning_rate": 5.909999999999999e-07, "loss": -0.0175, "num_tokens": 182369462.0, "reward": 0.4921875, "reward_std": 0.3900166153907776, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 819 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1999.0, "completions/mean_length": 1263.2578125, "completions/mean_terminated_length": 1117.9351806640625, "completions/min_length": 465.0, "completions/min_terminated_length": 465.0, "epoch": 0.14549648457426753, "frac_reward_zero_std": 0.125, "grad_norm": 0.6704800724983215, "learning_rate": 5.905e-07, "loss": 0.0205, "num_tokens": 182540295.0, "reward": 0.515625, "reward_std": 0.3624148368835449, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 820 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1363.640625, "completions/mean_terminated_length": 1116.1063232421875, "completions/min_length": 370.0, "completions/min_terminated_length": 370.0, "epoch": 0.1456739193115532, "frac_reward_zero_std": 0.25, "grad_norm": 0.5194501876831055, "learning_rate": 5.9e-07, "loss": -0.0124, "num_tokens": 182724857.0, "reward": 0.4140625, "reward_std": 0.31407544016838074, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 821 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1387.484375, "completions/mean_terminated_length": 1176.3917236328125, "completions/min_length": 374.0, "completions/min_terminated_length": 374.0, "epoch": 0.14585135404883892, "frac_reward_zero_std": 0.25, "grad_norm": 0.515429675579071, "learning_rate": 5.895e-07, "loss": -0.0358, "num_tokens": 182912471.0, "reward": 0.4296875, "reward_std": 0.31181254982948303, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 822 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1987.0, "completions/mean_length": 1364.1484375, "completions/mean_terminated_length": 1126.60009765625, "completions/min_length": 361.0, "completions/min_terminated_length": 361.0, "epoch": 0.1460287887861246, "frac_reward_zero_std": 0.375, "grad_norm": 0.5013579726219177, "learning_rate": 5.89e-07, "loss": -0.0208, "num_tokens": 183097098.0, "reward": 0.4296875, "reward_std": 0.278114914894104, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 823 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1958.0, "completions/mean_length": 1374.65625, "completions/mean_terminated_length": 1159.4638671875, "completions/min_length": 352.0, "completions/min_terminated_length": 352.0, "epoch": 0.14620622352341028, "frac_reward_zero_std": 0.125, "grad_norm": 0.5136587619781494, "learning_rate": 5.885e-07, "loss": 0.0035, "num_tokens": 183283070.0, "reward": 0.484375, "reward_std": 0.3571651577949524, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 824 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1234.828125, "completions/mean_terminated_length": 1017.445556640625, "completions/min_length": 557.0, "completions/min_terminated_length": 557.0, "epoch": 0.146383658260696, "frac_reward_zero_std": 0.375, "grad_norm": 0.5327492952346802, "learning_rate": 5.879999999999999e-07, "loss": 0.0309, "num_tokens": 183450648.0, "reward": 0.59375, "reward_std": 0.25857165455818176, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 825 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1909.0, "completions/mean_length": 1230.5703125, "completions/mean_terminated_length": 1001.6900024414062, "completions/min_length": 496.0, "completions/min_terminated_length": 496.0, "epoch": 0.14656109299798167, "frac_reward_zero_std": 0.5, "grad_norm": 0.46311548352241516, "learning_rate": 5.875e-07, "loss": 0.0236, "num_tokens": 183617681.0, "reward": 0.59375, "reward_std": 0.21497184038162231, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 826 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1960.0, "completions/mean_length": 1245.015625, "completions/mean_terminated_length": 1020.1799926757812, "completions/min_length": 543.0, "completions/min_terminated_length": 543.0, "epoch": 0.14673852773526738, "frac_reward_zero_std": 0.625, "grad_norm": 0.4449942111968994, "learning_rate": 5.87e-07, "loss": 0.0197, "num_tokens": 183786563.0, "reward": 0.578125, "reward_std": 0.1926366090774536, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 827 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1963.0, "completions/mean_length": 1262.0859375, "completions/mean_terminated_length": 1031.86865234375, "completions/min_length": 544.0, "completions/min_terminated_length": 544.0, "epoch": 0.14691596247255306, "frac_reward_zero_std": 0.375, "grad_norm": 0.52968430519104, "learning_rate": 5.865e-07, "loss": 0.0115, "num_tokens": 183957630.0, "reward": 0.59375, "reward_std": 0.2464885711669922, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 828 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1526.859375, "completions/mean_terminated_length": 1314.967041015625, "completions/min_length": 304.0, "completions/min_terminated_length": 304.0, "epoch": 0.14709339720983874, "frac_reward_zero_std": 0.125, "grad_norm": 0.5312326550483704, "learning_rate": 5.86e-07, "loss": 0.016, "num_tokens": 184163068.0, "reward": 0.5234375, "reward_std": 0.34902340173721313, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 829 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1901.0, "completions/mean_length": 1553.46875, "completions/mean_terminated_length": 1328.681884765625, "completions/min_length": 369.0, "completions/min_terminated_length": 369.0, "epoch": 0.14727083194712445, "frac_reward_zero_std": 0.125, "grad_norm": 0.47524404525756836, "learning_rate": 5.854999999999999e-07, "loss": 0.0129, "num_tokens": 184371912.0, "reward": 0.4765625, "reward_std": 0.3162299394607544, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 830 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1505.1484375, "completions/mean_terminated_length": 1292.728271484375, "completions/min_length": 353.0, "completions/min_terminated_length": 353.0, "epoch": 0.14744826668441013, "frac_reward_zero_std": 0.125, "grad_norm": 0.5071495175361633, "learning_rate": 5.849999999999999e-07, "loss": 0.0331, "num_tokens": 184574571.0, "reward": 0.484375, "reward_std": 0.3446376323699951, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 831 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1578.0234375, "completions/mean_terminated_length": 1364.3978271484375, "completions/min_length": 335.0, "completions/min_terminated_length": 335.0, "epoch": 0.14762570142169584, "frac_reward_zero_std": 0.125, "grad_norm": 0.4811771512031555, "learning_rate": 5.845e-07, "loss": 0.0069, "num_tokens": 184786558.0, "reward": 0.4453125, "reward_std": 0.385010302066803, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 832 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1468.625, "completions/mean_terminated_length": 1328.0, "completions/min_length": 697.0, "completions/min_terminated_length": 697.0, "epoch": 0.14780313615898152, "frac_reward_zero_std": 0.25, "grad_norm": 0.46074819564819336, "learning_rate": 5.839999999999999e-07, "loss": 0.0243, "num_tokens": 184987566.0, "reward": 0.703125, "reward_std": 0.3011361062526703, "rewards/simpleverify_reward/mean": 0.703125, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 833 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1950.0, "completions/mean_length": 1484.75, "completions/mean_terminated_length": 1304.7421875, "completions/min_length": 737.0, "completions/min_terminated_length": 737.0, "epoch": 0.1479805708962672, "frac_reward_zero_std": 0.375, "grad_norm": 0.46329936385154724, "learning_rate": 5.835e-07, "loss": 0.0211, "num_tokens": 185190638.0, "reward": 0.703125, "reward_std": 0.2290782630443573, "rewards/simpleverify_reward/mean": 0.703125, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 834 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1528.8984375, "completions/mean_terminated_length": 1333.53759765625, "completions/min_length": 515.0, "completions/min_terminated_length": 515.0, "epoch": 0.1481580056335529, "frac_reward_zero_std": 0.25, "grad_norm": 0.3900422751903534, "learning_rate": 5.83e-07, "loss": -0.005, "num_tokens": 185399361.0, "reward": 0.6640625, "reward_std": 0.2827712595462799, "rewards/simpleverify_reward/mean": 0.6640625, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 835 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1482.21875, "completions/mean_terminated_length": 1316.48486328125, "completions/min_length": 770.0, "completions/min_terminated_length": 770.0, "epoch": 0.1483354403708386, "frac_reward_zero_std": 0.125, "grad_norm": 0.5237165093421936, "learning_rate": 5.825e-07, "loss": 0.0206, "num_tokens": 185602109.0, "reward": 0.6875, "reward_std": 0.3607085645198822, "rewards/simpleverify_reward/mean": 0.6875, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 836 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1388.40625, "completions/mean_terminated_length": 1066.279052734375, "completions/min_length": 249.0, "completions/min_terminated_length": 249.0, "epoch": 0.1485128751081243, "frac_reward_zero_std": 0.25, "grad_norm": 0.5434783101081848, "learning_rate": 5.819999999999999e-07, "loss": -0.0007, "num_tokens": 185793105.0, "reward": 0.4296875, "reward_std": 0.28321951627731323, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 837 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1378.359375, "completions/mean_terminated_length": 1116.3260498046875, "completions/min_length": 258.0, "completions/min_terminated_length": 258.0, "epoch": 0.14869030984540998, "frac_reward_zero_std": 0.375, "grad_norm": 0.4663015604019165, "learning_rate": 5.815e-07, "loss": -0.0008, "num_tokens": 185982815.0, "reward": 0.46875, "reward_std": 0.24558821320533752, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 838 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2006.0, "completions/mean_length": 1399.9453125, "completions/mean_terminated_length": 1083.4534912109375, "completions/min_length": 244.0, "completions/min_terminated_length": 244.0, "epoch": 0.14886774458269567, "frac_reward_zero_std": 0.25, "grad_norm": 0.5074353218078613, "learning_rate": 5.809999999999999e-07, "loss": -0.0013, "num_tokens": 186175288.0, "reward": 0.4375, "reward_std": 0.27132561802864075, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 839 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1379.2421875, "completions/mean_terminated_length": 1117.5543212890625, "completions/min_length": 245.0, "completions/min_terminated_length": 245.0, "epoch": 0.14904517931998137, "frac_reward_zero_std": 0.375, "grad_norm": 0.5238502621650696, "learning_rate": 5.805e-07, "loss": -0.0052, "num_tokens": 186365111.0, "reward": 0.4921875, "reward_std": 0.2504299283027649, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 840 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1995.0, "completions/mean_length": 1296.875, "completions/mean_terminated_length": 991.4725341796875, "completions/min_length": 559.0, "completions/min_terminated_length": 559.0, "epoch": 0.14922261405726706, "frac_reward_zero_std": 0.375, "grad_norm": 0.5376987457275391, "learning_rate": 5.8e-07, "loss": 0.0311, "num_tokens": 186542631.0, "reward": 0.484375, "reward_std": 0.2530868649482727, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 841 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1294.15625, "completions/mean_terminated_length": 1063.3876953125, "completions/min_length": 547.0, "completions/min_terminated_length": 547.0, "epoch": 0.14940004879455276, "frac_reward_zero_std": 0.375, "grad_norm": 0.4228079915046692, "learning_rate": 5.795e-07, "loss": 0.0178, "num_tokens": 186719803.0, "reward": 0.578125, "reward_std": 0.2614234387874603, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 842 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1299.859375, "completions/mean_terminated_length": 1018.3010864257812, "completions/min_length": 533.0, "completions/min_terminated_length": 533.0, "epoch": 0.14957748353183845, "frac_reward_zero_std": 0.5, "grad_norm": 0.3710361123085022, "learning_rate": 5.79e-07, "loss": 0.0217, "num_tokens": 186897705.0, "reward": 0.546875, "reward_std": 0.22769677639007568, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 843 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1282.65625, "completions/mean_terminated_length": 1058.464599609375, "completions/min_length": 541.0, "completions/min_terminated_length": 541.0, "epoch": 0.14975491826912413, "frac_reward_zero_std": 0.25, "grad_norm": 0.6053426265716553, "learning_rate": 5.784999999999999e-07, "loss": 0.0328, "num_tokens": 187073405.0, "reward": 0.5703125, "reward_std": 0.3067798912525177, "rewards/simpleverify_reward/mean": 0.5703125, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 844 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1460.546875, "completions/mean_terminated_length": 1264.729248046875, "completions/min_length": 416.0, "completions/min_terminated_length": 416.0, "epoch": 0.14993235300640984, "frac_reward_zero_std": 0.375, "grad_norm": 0.4940608739852905, "learning_rate": 5.779999999999999e-07, "loss": 0.0036, "num_tokens": 187272243.0, "reward": 0.3671875, "reward_std": 0.2508781850337982, "rewards/simpleverify_reward/mean": 0.3671875, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 845 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1984.0, "completions/mean_length": 1464.265625, "completions/mean_terminated_length": 1168.9647216796875, "completions/min_length": 394.0, "completions/min_terminated_length": 394.0, "epoch": 0.15010978774369552, "frac_reward_zero_std": 0.375, "grad_norm": 0.5307592749595642, "learning_rate": 5.775e-07, "loss": -0.0014, "num_tokens": 187471557.0, "reward": 0.2890625, "reward_std": 0.2378891110420227, "rewards/simpleverify_reward/mean": 0.2890625, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 846 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1450.9921875, "completions/mean_terminated_length": 1198.9222412109375, "completions/min_length": 424.0, "completions/min_terminated_length": 424.0, "epoch": 0.15028722248098123, "frac_reward_zero_std": 0.5, "grad_norm": 0.42816439270973206, "learning_rate": 5.769999999999999e-07, "loss": 0.0032, "num_tokens": 187669172.0, "reward": 0.28125, "reward_std": 0.21347813308238983, "rewards/simpleverify_reward/mean": 0.28125, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 847 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 1993.0, "completions/mean_length": 1454.40625, "completions/mean_terminated_length": 1256.541748046875, "completions/min_length": 432.0, "completions/min_terminated_length": 432.0, "epoch": 0.1504646572182669, "frac_reward_zero_std": 0.25, "grad_norm": 0.6301708221435547, "learning_rate": 5.765e-07, "loss": 0.0137, "num_tokens": 187867224.0, "reward": 0.328125, "reward_std": 0.31071737408638, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 848 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2015.0, "completions/mean_length": 1478.5859375, "completions/mean_terminated_length": 1210.2413330078125, "completions/min_length": 623.0, "completions/min_terminated_length": 623.0, "epoch": 0.1506420919555526, "frac_reward_zero_std": 0.5, "grad_norm": 0.42136645317077637, "learning_rate": 5.76e-07, "loss": 0.0149, "num_tokens": 188069379.0, "reward": 0.484375, "reward_std": 0.2020905315876007, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 849 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1984.0, "completions/mean_length": 1500.65625, "completions/mean_terminated_length": 1172.25, "completions/min_length": 598.0, "completions/min_terminated_length": 598.0, "epoch": 0.1508195266928383, "frac_reward_zero_std": 0.375, "grad_norm": 0.5091667175292969, "learning_rate": 5.755e-07, "loss": 0.034, "num_tokens": 188274359.0, "reward": 0.4140625, "reward_std": 0.23107381165027618, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 850 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1474.03125, "completions/mean_terminated_length": 1173.3809814453125, "completions/min_length": 623.0, "completions/min_terminated_length": 623.0, "epoch": 0.15099696143012398, "frac_reward_zero_std": 0.5, "grad_norm": 0.39358586072921753, "learning_rate": 5.749999999999999e-07, "loss": 0.0215, "num_tokens": 188475931.0, "reward": 0.4609375, "reward_std": 0.18837818503379822, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 851 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1972.0, "completions/mean_length": 1449.40625, "completions/mean_terminated_length": 1187.1011962890625, "completions/min_length": 621.0, "completions/min_terminated_length": 621.0, "epoch": 0.15117439616740969, "frac_reward_zero_std": 0.25, "grad_norm": 0.5644955635070801, "learning_rate": 5.745e-07, "loss": 0.0361, "num_tokens": 188674351.0, "reward": 0.4765625, "reward_std": 0.26581305265426636, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 852 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2002.0, "completions/mean_length": 1381.765625, "completions/mean_terminated_length": 1177.8162841796875, "completions/min_length": 330.0, "completions/min_terminated_length": 330.0, "epoch": 0.15135183090469537, "frac_reward_zero_std": 0.5, "grad_norm": 0.4135335683822632, "learning_rate": 5.739999999999999e-07, "loss": 0.008, "num_tokens": 188861569.0, "reward": 0.421875, "reward_std": 0.17693254351615906, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 853 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1390.4296875, "completions/mean_terminated_length": 1180.2783203125, "completions/min_length": 323.0, "completions/min_terminated_length": 323.0, "epoch": 0.15152926564198105, "frac_reward_zero_std": 0.375, "grad_norm": 0.6436745524406433, "learning_rate": 5.735e-07, "loss": 0.0105, "num_tokens": 189049896.0, "reward": 0.421875, "reward_std": 0.2563907504081726, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 854 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1368.8046875, "completions/mean_terminated_length": 1203.951416015625, "completions/min_length": 327.0, "completions/min_terminated_length": 327.0, "epoch": 0.15170670037926676, "frac_reward_zero_std": 0.25, "grad_norm": 0.5862742066383362, "learning_rate": 5.73e-07, "loss": 0.0057, "num_tokens": 189235455.0, "reward": 0.4765625, "reward_std": 0.23993882536888123, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 855 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1362.1484375, "completions/mean_terminated_length": 1178.802001953125, "completions/min_length": 316.0, "completions/min_terminated_length": 316.0, "epoch": 0.15188413511655244, "frac_reward_zero_std": 0.375, "grad_norm": 0.5157927870750427, "learning_rate": 5.725e-07, "loss": 0.0206, "num_tokens": 189420162.0, "reward": 0.4765625, "reward_std": 0.2728690803050995, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 856 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1370.3984375, "completions/mean_terminated_length": 1252.2843017578125, "completions/min_length": 522.0, "completions/min_terminated_length": 522.0, "epoch": 0.15206156985383815, "frac_reward_zero_std": 0.125, "grad_norm": 0.5813551545143127, "learning_rate": 5.719999999999999e-07, "loss": 0.0166, "num_tokens": 189604933.0, "reward": 0.6640625, "reward_std": 0.3900166153907776, "rewards/simpleverify_reward/mean": 0.6640625, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 857 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1425.109375, "completions/mean_terminated_length": 1316.5321044921875, "completions/min_length": 576.0, "completions/min_terminated_length": 576.0, "epoch": 0.15223900459112383, "frac_reward_zero_std": 0.125, "grad_norm": 0.5741039514541626, "learning_rate": 5.715e-07, "loss": 0.0107, "num_tokens": 189796707.0, "reward": 0.5625, "reward_std": 0.3842689096927643, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 858 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1375.9453125, "completions/mean_terminated_length": 1244.046630859375, "completions/min_length": 543.0, "completions/min_terminated_length": 543.0, "epoch": 0.1524164393284095, "frac_reward_zero_std": 0.25, "grad_norm": 0.4996434450149536, "learning_rate": 5.709999999999999e-07, "loss": 0.0205, "num_tokens": 189982188.0, "reward": 0.6171875, "reward_std": 0.374308705329895, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 859 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1361.5625, "completions/mean_terminated_length": 1234.4444580078125, "completions/min_length": 550.0, "completions/min_terminated_length": 550.0, "epoch": 0.15259387406569522, "frac_reward_zero_std": 0.25, "grad_norm": 0.5631534457206726, "learning_rate": 5.705e-07, "loss": 0.0149, "num_tokens": 190165828.0, "reward": 0.5703125, "reward_std": 0.3426326513290405, "rewards/simpleverify_reward/mean": 0.5703125, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 860 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2012.0, "completions/mean_length": 1307.421875, "completions/mean_terminated_length": 1017.6304321289062, "completions/min_length": 255.0, "completions/min_terminated_length": 255.0, "epoch": 0.1527713088029809, "frac_reward_zero_std": 0.25, "grad_norm": 0.7804224491119385, "learning_rate": 5.699999999999999e-07, "loss": -0.0048, "num_tokens": 190344618.0, "reward": 0.40625, "reward_std": 0.2717738747596741, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 861 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1297.875, "completions/mean_terminated_length": 1058.144287109375, "completions/min_length": 266.0, "completions/min_terminated_length": 266.0, "epoch": 0.1529487435402666, "frac_reward_zero_std": 0.25, "grad_norm": 0.8373832702636719, "learning_rate": 5.695e-07, "loss": 0.0093, "num_tokens": 190522186.0, "reward": 0.4296875, "reward_std": 0.3001815676689148, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 862 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1314.4375, "completions/mean_terminated_length": 1069.916748046875, "completions/min_length": 276.0, "completions/min_terminated_length": 276.0, "epoch": 0.1531261782775523, "frac_reward_zero_std": 0.125, "grad_norm": 0.6871925592422485, "learning_rate": 5.69e-07, "loss": 0.0269, "num_tokens": 190701874.0, "reward": 0.3984375, "reward_std": 0.35165637731552124, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 863 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1962.0, "completions/mean_length": 1331.453125, "completions/mean_terminated_length": 1082.54736328125, "completions/min_length": 253.0, "completions/min_terminated_length": 253.0, "epoch": 0.15330361301483797, "frac_reward_zero_std": 0.0, "grad_norm": 0.8241652846336365, "learning_rate": 5.684999999999999e-07, "loss": 0.0136, "num_tokens": 190883740.0, "reward": 0.421875, "reward_std": 0.4003128409385681, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 864 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1538.1328125, "completions/mean_terminated_length": 1166.067626953125, "completions/min_length": 317.0, "completions/min_terminated_length": 317.0, "epoch": 0.15348104775212368, "frac_reward_zero_std": 0.375, "grad_norm": 0.478306382894516, "learning_rate": 5.679999999999999e-07, "loss": 0.0165, "num_tokens": 191093181.0, "reward": 0.4296875, "reward_std": 0.263418972492218, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 865 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1540.7890625, "completions/mean_terminated_length": 1158.643798828125, "completions/min_length": 303.0, "completions/min_terminated_length": 303.0, "epoch": 0.15365848248940936, "frac_reward_zero_std": 0.5, "grad_norm": 0.42513418197631836, "learning_rate": 5.675e-07, "loss": -0.0027, "num_tokens": 191302962.0, "reward": 0.3515625, "reward_std": 0.22079971432685852, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 866 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.46875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1553.84375, "completions/mean_terminated_length": 1117.823486328125, "completions/min_length": 288.0, "completions/min_terminated_length": 288.0, "epoch": 0.15383591722669507, "frac_reward_zero_std": 0.625, "grad_norm": 0.377957820892334, "learning_rate": 5.669999999999999e-07, "loss": -0.0003, "num_tokens": 191514414.0, "reward": 0.34375, "reward_std": 0.1839885711669922, "rewards/simpleverify_reward/mean": 0.34375, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 867 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1555.0234375, "completions/mean_terminated_length": 1133.4927978515625, "completions/min_length": 263.0, "completions/min_terminated_length": 263.0, "epoch": 0.15401335196398075, "frac_reward_zero_std": 0.5, "grad_norm": 0.44965848326683044, "learning_rate": 5.665e-07, "loss": 0.0239, "num_tokens": 191726017.0, "reward": 0.3515625, "reward_std": 0.21968236565589905, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 868 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1154.203125, "completions/mean_terminated_length": 1035.5574951171875, "completions/min_length": 551.0, "completions/min_terminated_length": 551.0, "epoch": 0.15419078670126643, "frac_reward_zero_std": 0.5, "grad_norm": 0.47335925698280334, "learning_rate": 5.66e-07, "loss": 0.034, "num_tokens": 191882923.0, "reward": 0.7265625, "reward_std": 0.19738000631332397, "rewards/simpleverify_reward/mean": 0.7265625, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 869 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2012.0, "completions/mean_length": 1104.921875, "completions/mean_terminated_length": 989.1052856445312, "completions/min_length": 557.0, "completions/min_terminated_length": 557.0, "epoch": 0.15436822143855214, "frac_reward_zero_std": 0.5, "grad_norm": 0.4651593863964081, "learning_rate": 5.655e-07, "loss": -0.0017, "num_tokens": 192033521.0, "reward": 0.75, "reward_std": 0.19628483057022095, "rewards/simpleverify_reward/mean": 0.75, "rewards/simpleverify_reward/std": 0.434714138507843, "step": 870 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1820.0, "completions/mean_length": 1133.0703125, "completions/mean_terminated_length": 963.638916015625, "completions/min_length": 499.0, "completions/min_terminated_length": 499.0, "epoch": 0.15454565617583782, "frac_reward_zero_std": 0.25, "grad_norm": 0.5530648231506348, "learning_rate": 5.649999999999999e-07, "loss": 0.0227, "num_tokens": 192187722.0, "reward": 0.71875, "reward_std": 0.29863813519477844, "rewards/simpleverify_reward/mean": 0.71875, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 871 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1983.0, "completions/mean_length": 1140.046875, "completions/mean_terminated_length": 1000.9910278320312, "completions/min_length": 550.0, "completions/min_terminated_length": 550.0, "epoch": 0.15472309091312353, "frac_reward_zero_std": 0.5, "grad_norm": 0.4448218047618866, "learning_rate": 5.645e-07, "loss": 0.0266, "num_tokens": 192342816.0, "reward": 0.78125, "reward_std": 0.18968652188777924, "rewards/simpleverify_reward/mean": 0.78125, "rewards/simpleverify_reward/std": 0.41502299904823303, "step": 872 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1096.765625, "completions/mean_terminated_length": 920.6111450195312, "completions/min_length": 414.0, "completions/min_terminated_length": 414.0, "epoch": 0.1549005256504092, "frac_reward_zero_std": 0.375, "grad_norm": 0.5843942761421204, "learning_rate": 5.639999999999999e-07, "loss": 0.0052, "num_tokens": 192494194.0, "reward": 0.59375, "reward_std": 0.26472732424736023, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 873 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1992.0, "completions/mean_length": 1167.3984375, "completions/mean_terminated_length": 994.570068359375, "completions/min_length": 376.0, "completions/min_terminated_length": 376.0, "epoch": 0.1550779603876949, "frac_reward_zero_std": 0.25, "grad_norm": 0.6805791854858398, "learning_rate": 5.635e-07, "loss": -0.0094, "num_tokens": 192654613.0, "reward": 0.6171875, "reward_std": 0.26581305265426636, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 874 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1135.75, "completions/mean_terminated_length": 996.0360717773438, "completions/min_length": 389.0, "completions/min_terminated_length": 389.0, "epoch": 0.1552553951249806, "frac_reward_zero_std": 0.125, "grad_norm": 0.6306915283203125, "learning_rate": 5.629999999999999e-07, "loss": 0.0054, "num_tokens": 192810981.0, "reward": 0.6875, "reward_std": 0.27619513869285583, "rewards/simpleverify_reward/mean": 0.6875, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 875 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1856.0, "completions/mean_length": 1150.4609375, "completions/mean_terminated_length": 984.25, "completions/min_length": 379.0, "completions/min_terminated_length": 379.0, "epoch": 0.15543282986226628, "frac_reward_zero_std": 0.375, "grad_norm": 0.649768590927124, "learning_rate": 5.625e-07, "loss": 0.017, "num_tokens": 192969232.0, "reward": 0.671875, "reward_std": 0.2004890739917755, "rewards/simpleverify_reward/mean": 0.671875, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 876 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1101.546875, "completions/mean_terminated_length": 946.6726684570312, "completions/min_length": 526.0, "completions/min_terminated_length": 526.0, "epoch": 0.155610264599552, "frac_reward_zero_std": 0.125, "grad_norm": 0.683748722076416, "learning_rate": 5.620000000000001e-07, "loss": 0.0193, "num_tokens": 193120294.0, "reward": 0.6484375, "reward_std": 0.36222946643829346, "rewards/simpleverify_reward/mean": 0.6484375, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 877 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2012.0, "completions/mean_length": 1129.1328125, "completions/mean_terminated_length": 927.857177734375, "completions/min_length": 478.0, "completions/min_terminated_length": 478.0, "epoch": 0.15578769933683767, "frac_reward_zero_std": 0.125, "grad_norm": 0.6264920234680176, "learning_rate": 5.614999999999999e-07, "loss": 0.0087, "num_tokens": 193274887.0, "reward": 0.65625, "reward_std": 0.37209999561309814, "rewards/simpleverify_reward/mean": 0.65625, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 878 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1112.6484375, "completions/mean_terminated_length": 979.02685546875, "completions/min_length": 491.0, "completions/min_terminated_length": 491.0, "epoch": 0.15596513407412335, "frac_reward_zero_std": 0.125, "grad_norm": 0.6430924534797668, "learning_rate": 5.61e-07, "loss": 0.0165, "num_tokens": 193427370.0, "reward": 0.71875, "reward_std": 0.3561279773712158, "rewards/simpleverify_reward/mean": 0.71875, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 879 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1880.0, "completions/mean_length": 1085.8359375, "completions/mean_terminated_length": 897.0, "completions/min_length": 479.0, "completions/min_terminated_length": 479.0, "epoch": 0.15614256881140906, "frac_reward_zero_std": 0.125, "grad_norm": 0.9642370343208313, "learning_rate": 5.605e-07, "loss": 0.0058, "num_tokens": 193576421.0, "reward": 0.671875, "reward_std": 0.3716517686843872, "rewards/simpleverify_reward/mean": 0.671875, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 880 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2012.0, "completions/mean_length": 1235.9140625, "completions/mean_terminated_length": 1058.028564453125, "completions/min_length": 595.0, "completions/min_terminated_length": 595.0, "epoch": 0.15632000354869474, "frac_reward_zero_std": 0.375, "grad_norm": 0.4682198166847229, "learning_rate": 5.6e-07, "loss": -0.0038, "num_tokens": 193745002.0, "reward": 0.5625, "reward_std": 0.2551366090774536, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 881 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2011.0, "completions/mean_length": 1236.6015625, "completions/mean_terminated_length": 1095.1650390625, "completions/min_length": 544.0, "completions/min_terminated_length": 544.0, "epoch": 0.15649743828598045, "frac_reward_zero_std": 0.5, "grad_norm": 0.43142199516296387, "learning_rate": 5.595e-07, "loss": 0.0, "num_tokens": 193913671.0, "reward": 0.546875, "reward_std": 0.23283424973487854, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 882 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1798.0, "completions/mean_length": 1233.4375, "completions/mean_terminated_length": 1100.1453857421875, "completions/min_length": 551.0, "completions/min_terminated_length": 551.0, "epoch": 0.15667487302326613, "frac_reward_zero_std": 0.5, "grad_norm": 0.402783066034317, "learning_rate": 5.590000000000001e-07, "loss": -0.0066, "num_tokens": 194081935.0, "reward": 0.5390625, "reward_std": 0.24494513869285583, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 883 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1982.0, "completions/mean_length": 1250.4921875, "completions/mean_terminated_length": 1075.800048828125, "completions/min_length": 589.0, "completions/min_terminated_length": 589.0, "epoch": 0.1568523077605518, "frac_reward_zero_std": 0.5, "grad_norm": 0.41928139328956604, "learning_rate": 5.584999999999999e-07, "loss": -0.0028, "num_tokens": 194252382.0, "reward": 0.46875, "reward_std": 0.24888262152671814, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 884 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0703125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1247.0, "completions/mean_terminated_length": 1186.4202880859375, "completions/min_length": 445.0, "completions/min_terminated_length": 445.0, "epoch": 0.15702974249783752, "frac_reward_zero_std": 0.0, "grad_norm": 0.6118391156196594, "learning_rate": 5.58e-07, "loss": -0.0101, "num_tokens": 194423582.0, "reward": 0.4609375, "reward_std": 0.42120859026908875, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 885 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1259.1171875, "completions/mean_terminated_length": 1184.94873046875, "completions/min_length": 548.0, "completions/min_terminated_length": 548.0, "epoch": 0.1572071772351232, "frac_reward_zero_std": 0.125, "grad_norm": 0.5648077130317688, "learning_rate": 5.575e-07, "loss": -0.0014, "num_tokens": 194596333.0, "reward": 0.46875, "reward_std": 0.40146225690841675, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 886 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1953.0, "completions/mean_length": 1253.8203125, "completions/mean_terminated_length": 1200.8751220703125, "completions/min_length": 492.0, "completions/min_terminated_length": 492.0, "epoch": 0.1573846119724089, "frac_reward_zero_std": 0.125, "grad_norm": 0.582021176815033, "learning_rate": 5.57e-07, "loss": 0.0003, "num_tokens": 194768406.0, "reward": 0.5234375, "reward_std": 0.36065438389778137, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 887 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2000.0, "completions/mean_length": 1244.421875, "completions/mean_terminated_length": 1204.901611328125, "completions/min_length": 480.0, "completions/min_terminated_length": 480.0, "epoch": 0.1575620467096946, "frac_reward_zero_std": 0.0, "grad_norm": 0.5632320642471313, "learning_rate": 5.565e-07, "loss": -0.0063, "num_tokens": 194939276.0, "reward": 0.46875, "reward_std": 0.38221919536590576, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 888 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1574.5390625, "completions/mean_terminated_length": 1308.93896484375, "completions/min_length": 517.0, "completions/min_terminated_length": 517.0, "epoch": 0.15773948144698027, "frac_reward_zero_std": 0.375, "grad_norm": 0.4047718346118927, "learning_rate": 5.560000000000001e-07, "loss": 0.0334, "num_tokens": 195153393.0, "reward": 0.4140625, "reward_std": 0.2846841812133789, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 889 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1573.890625, "completions/mean_terminated_length": 1316.8433837890625, "completions/min_length": 441.0, "completions/min_terminated_length": 441.0, "epoch": 0.15791691618426598, "frac_reward_zero_std": 0.375, "grad_norm": 0.3787659704685211, "learning_rate": 5.555e-07, "loss": 0.0478, "num_tokens": 195367427.0, "reward": 0.46875, "reward_std": 0.2715607285499573, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 890 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2023.0, "completions/mean_length": 1556.84375, "completions/mean_terminated_length": 1308.37646484375, "completions/min_length": 405.0, "completions/min_terminated_length": 405.0, "epoch": 0.15809435092155166, "frac_reward_zero_std": 0.375, "grad_norm": 0.3901714086532593, "learning_rate": 5.55e-07, "loss": 0.0338, "num_tokens": 195579279.0, "reward": 0.4453125, "reward_std": 0.2815170884132385, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 891 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1555.90625, "completions/mean_terminated_length": 1324.0, "completions/min_length": 678.0, "completions/min_terminated_length": 678.0, "epoch": 0.15827178565883737, "frac_reward_zero_std": 0.25, "grad_norm": 0.5386247634887695, "learning_rate": 5.544999999999999e-07, "loss": 0.0029, "num_tokens": 195791011.0, "reward": 0.4453125, "reward_std": 0.2735343277454376, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 892 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2005.0, "completions/mean_length": 1661.109375, "completions/mean_terminated_length": 1360.1944580078125, "completions/min_length": 584.0, "completions/min_terminated_length": 584.0, "epoch": 0.15844922039612305, "frac_reward_zero_std": 0.125, "grad_norm": 0.5129647850990295, "learning_rate": 5.54e-07, "loss": 0.0133, "num_tokens": 196017537.0, "reward": 0.34375, "reward_std": 0.3380298614501953, "rewards/simpleverify_reward/mean": 0.34375, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 893 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1707.1484375, "completions/mean_terminated_length": 1442.0416259765625, "completions/min_length": 800.0, "completions/min_terminated_length": 800.0, "epoch": 0.15862665513340873, "frac_reward_zero_std": 0.125, "grad_norm": 0.5228179097175598, "learning_rate": 5.535e-07, "loss": 0.0135, "num_tokens": 196249956.0, "reward": 0.3203125, "reward_std": 0.3578120768070221, "rewards/simpleverify_reward/mean": 0.3203125, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 894 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1705.3359375, "completions/mean_terminated_length": 1373.21533203125, "completions/min_length": 455.0, "completions/min_terminated_length": 455.0, "epoch": 0.15880408987069444, "frac_reward_zero_std": 0.125, "grad_norm": 0.48048269748687744, "learning_rate": 5.53e-07, "loss": 0.0267, "num_tokens": 196482143.0, "reward": 0.3046875, "reward_std": 0.36041927337646484, "rewards/simpleverify_reward/mean": 0.3046875, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 895 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1668.34375, "completions/mean_terminated_length": 1382.3013916015625, "completions/min_length": 506.0, "completions/min_terminated_length": 506.0, "epoch": 0.15898152460798012, "frac_reward_zero_std": 0.125, "grad_norm": 0.5205445885658264, "learning_rate": 5.525e-07, "loss": 0.0261, "num_tokens": 196709595.0, "reward": 0.3828125, "reward_std": 0.39728015661239624, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 896 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1977.0, "completions/mean_length": 1331.1796875, "completions/mean_terminated_length": 1198.4351806640625, "completions/min_length": 488.0, "completions/min_terminated_length": 488.0, "epoch": 0.15915895934526583, "frac_reward_zero_std": 0.0, "grad_norm": 0.6482744216918945, "learning_rate": 5.520000000000001e-07, "loss": 0.0352, "num_tokens": 196889010.0, "reward": 0.5234375, "reward_std": 0.41634291410446167, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 897 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1372.71875, "completions/mean_terminated_length": 1174.9090576171875, "completions/min_length": 563.0, "completions/min_terminated_length": 563.0, "epoch": 0.1593363940825515, "frac_reward_zero_std": 0.0, "grad_norm": 0.6085941195487976, "learning_rate": 5.514999999999999e-07, "loss": 0.0217, "num_tokens": 197073742.0, "reward": 0.515625, "reward_std": 0.39994096755981445, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 898 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1342.6640625, "completions/mean_terminated_length": 1171.466064453125, "completions/min_length": 545.0, "completions/min_terminated_length": 545.0, "epoch": 0.1595138288198372, "frac_reward_zero_std": 0.0, "grad_norm": 0.6367630362510681, "learning_rate": 5.51e-07, "loss": 0.018, "num_tokens": 197254627.0, "reward": 0.484375, "reward_std": 0.4135189652442932, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 899 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1316.9140625, "completions/mean_terminated_length": 1165.1793212890625, "completions/min_length": 505.0, "completions/min_terminated_length": 505.0, "epoch": 0.1596912635571229, "frac_reward_zero_std": 0.125, "grad_norm": 0.6152228713035583, "learning_rate": 5.505e-07, "loss": 0.0071, "num_tokens": 197432216.0, "reward": 0.515625, "reward_std": 0.3485434949398041, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 900 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1568.765625, "completions/mean_terminated_length": 1207.6986083984375, "completions/min_length": 596.0, "completions/min_terminated_length": 596.0, "epoch": 0.15986869829440858, "frac_reward_zero_std": 0.625, "grad_norm": 0.4216940701007843, "learning_rate": 5.5e-07, "loss": -0.0043, "num_tokens": 197646810.0, "reward": 0.28125, "reward_std": 0.16109731793403625, "rewards/simpleverify_reward/mean": 0.28125, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 901 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2009.0, "completions/mean_length": 1560.03125, "completions/mean_terminated_length": 1142.7825927734375, "completions/min_length": 535.0, "completions/min_terminated_length": 535.0, "epoch": 0.1600461330316943, "frac_reward_zero_std": 0.375, "grad_norm": 0.5560011267662048, "learning_rate": 5.495e-07, "loss": -0.0059, "num_tokens": 197860286.0, "reward": 0.2734375, "reward_std": 0.2378891110420227, "rewards/simpleverify_reward/mean": 0.2734375, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 902 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1977.0, "completions/mean_length": 1588.078125, "completions/mean_terminated_length": 1156.0303955078125, "completions/min_length": 583.0, "completions/min_terminated_length": 583.0, "epoch": 0.16022356776897997, "frac_reward_zero_std": 0.5, "grad_norm": 0.4858543574810028, "learning_rate": 5.490000000000001e-07, "loss": 0.0049, "num_tokens": 198077352.0, "reward": 0.265625, "reward_std": 0.20048905909061432, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 903 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1595.4609375, "completions/mean_terminated_length": 1208.50732421875, "completions/min_length": 670.0, "completions/min_terminated_length": 670.0, "epoch": 0.16040100250626566, "frac_reward_zero_std": 0.625, "grad_norm": 0.39520567655563354, "learning_rate": 5.484999999999999e-07, "loss": 0.0174, "num_tokens": 198295363.0, "reward": 0.3203125, "reward_std": 0.13644562661647797, "rewards/simpleverify_reward/mean": 0.3203125, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 904 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1994.0, "completions/mean_length": 1218.515625, "completions/mean_terminated_length": 1091.4775390625, "completions/min_length": 181.0, "completions/min_terminated_length": 181.0, "epoch": 0.16057843724355136, "frac_reward_zero_std": 0.375, "grad_norm": 0.5528967976570129, "learning_rate": 5.48e-07, "loss": -0.003, "num_tokens": 198463909.0, "reward": 0.2578125, "reward_std": 0.1753891110420227, "rewards/simpleverify_reward/mean": 0.2578125, "rewards/simpleverify_reward/std": 0.43914902210235596, "step": 905 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1234.265625, "completions/mean_terminated_length": 1092.4219970703125, "completions/min_length": 189.0, "completions/min_terminated_length": 189.0, "epoch": 0.16075587198083705, "frac_reward_zero_std": 0.5, "grad_norm": 0.7102707624435425, "learning_rate": 5.474999999999999e-07, "loss": -0.0036, "num_tokens": 198634471.0, "reward": 0.25, "reward_std": 0.1441391110420227, "rewards/simpleverify_reward/mean": 0.25, "rewards/simpleverify_reward/std": 0.434714138507843, "step": 906 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1221.0078125, "completions/mean_terminated_length": 1058.700927734375, "completions/min_length": 184.0, "completions/min_terminated_length": 184.0, "epoch": 0.16093330671812275, "frac_reward_zero_std": 0.375, "grad_norm": 0.5471065640449524, "learning_rate": 5.47e-07, "loss": 0.0093, "num_tokens": 198803336.0, "reward": 0.2890625, "reward_std": 0.23256750404834747, "rewards/simpleverify_reward/mean": 0.2890625, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 907 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1196.6875, "completions/mean_terminated_length": 1048.2935791015625, "completions/min_length": 200.0, "completions/min_terminated_length": 200.0, "epoch": 0.16111074145540843, "frac_reward_zero_std": 0.25, "grad_norm": 0.6793535351753235, "learning_rate": 5.465e-07, "loss": -0.0104, "num_tokens": 198969088.0, "reward": 0.2890625, "reward_std": 0.2504299283027649, "rewards/simpleverify_reward/mean": 0.2890625, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 908 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1324.578125, "completions/mean_terminated_length": 1073.2843017578125, "completions/min_length": 462.0, "completions/min_terminated_length": 462.0, "epoch": 0.16128817619269412, "frac_reward_zero_std": 0.375, "grad_norm": 0.6227533221244812, "learning_rate": 5.46e-07, "loss": -0.0175, "num_tokens": 199152250.0, "reward": 0.484375, "reward_std": 0.2579922080039978, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 909 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1882.0, "completions/mean_length": 1354.9765625, "completions/mean_terminated_length": 1073.1978759765625, "completions/min_length": 457.0, "completions/min_terminated_length": 457.0, "epoch": 0.16146561092997982, "frac_reward_zero_std": 0.375, "grad_norm": 0.5740654468536377, "learning_rate": 5.455e-07, "loss": -0.0106, "num_tokens": 199339303.0, "reward": 0.4296875, "reward_std": 0.30289655923843384, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 910 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1973.0, "completions/mean_length": 1365.7109375, "completions/mean_terminated_length": 1055.57958984375, "completions/min_length": 466.0, "completions/min_terminated_length": 466.0, "epoch": 0.1616430456672655, "frac_reward_zero_std": 0.375, "grad_norm": 0.5676875710487366, "learning_rate": 5.45e-07, "loss": 0.0183, "num_tokens": 199527730.0, "reward": 0.4453125, "reward_std": 0.29472315311431885, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 911 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1341.859375, "completions/mean_terminated_length": 1054.747314453125, "completions/min_length": 396.0, "completions/min_terminated_length": 396.0, "epoch": 0.16182048040455121, "frac_reward_zero_std": 0.375, "grad_norm": 0.5853471159934998, "learning_rate": 5.444999999999999e-07, "loss": 0.0128, "num_tokens": 199713104.0, "reward": 0.46875, "reward_std": 0.27494096755981445, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 912 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1616.78125, "completions/mean_terminated_length": 1312.0533447265625, "completions/min_length": 387.0, "completions/min_terminated_length": 387.0, "epoch": 0.1619979151418369, "frac_reward_zero_std": 0.375, "grad_norm": 0.4467117488384247, "learning_rate": 5.44e-07, "loss": 0.003, "num_tokens": 199929636.0, "reward": 0.5, "reward_std": 0.2563907504081726, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 913 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1596.9765625, "completions/mean_terminated_length": 1288.381591796875, "completions/min_length": 374.0, "completions/min_terminated_length": 374.0, "epoch": 0.16217534987912258, "frac_reward_zero_std": 0.375, "grad_norm": 0.4547715485095978, "learning_rate": 5.435e-07, "loss": 0.0144, "num_tokens": 200143633.0, "reward": 0.5, "reward_std": 0.23898044228553772, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 914 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1641.796875, "completions/mean_terminated_length": 1294.4637451171875, "completions/min_length": 375.0, "completions/min_terminated_length": 375.0, "epoch": 0.16235278461640829, "frac_reward_zero_std": 0.375, "grad_norm": 0.4510555565357208, "learning_rate": 5.43e-07, "loss": 0.0227, "num_tokens": 200363367.0, "reward": 0.421875, "reward_std": 0.23456305265426636, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 915 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1616.0546875, "completions/mean_terminated_length": 1300.8514404296875, "completions/min_length": 380.0, "completions/min_terminated_length": 380.0, "epoch": 0.16253021935369397, "frac_reward_zero_std": 0.25, "grad_norm": 0.5152022838592529, "learning_rate": 5.425e-07, "loss": 0.0007, "num_tokens": 200579806.0, "reward": 0.4765625, "reward_std": 0.30917394161224365, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 916 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2014.0, "completions/mean_length": 1399.65625, "completions/mean_terminated_length": 1136.0439453125, "completions/min_length": 534.0, "completions/min_terminated_length": 534.0, "epoch": 0.16270765409097968, "frac_reward_zero_std": 0.375, "grad_norm": 0.5058249831199646, "learning_rate": 5.420000000000001e-07, "loss": -0.0119, "num_tokens": 200772082.0, "reward": 0.328125, "reward_std": 0.26187556982040405, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 917 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1985.0, "completions/mean_length": 1425.5703125, "completions/mean_terminated_length": 1142.647705078125, "completions/min_length": 572.0, "completions/min_terminated_length": 572.0, "epoch": 0.16288508882826536, "frac_reward_zero_std": 0.125, "grad_norm": 0.581295371055603, "learning_rate": 5.414999999999999e-07, "loss": 0.0087, "num_tokens": 200967675.0, "reward": 0.296875, "reward_std": 0.3347259759902954, "rewards/simpleverify_reward/mean": 0.296875, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 918 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2005.0, "completions/mean_length": 1417.3671875, "completions/mean_terminated_length": 1141.0224609375, "completions/min_length": 576.0, "completions/min_terminated_length": 576.0, "epoch": 0.16306252356555104, "frac_reward_zero_std": 0.25, "grad_norm": 0.5382856130599976, "learning_rate": 5.41e-07, "loss": 0.0101, "num_tokens": 201162218.0, "reward": 0.3359375, "reward_std": 0.28059419989585876, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 919 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1950.0, "completions/mean_length": 1413.1796875, "completions/mean_terminated_length": 1192.6632080078125, "completions/min_length": 576.0, "completions/min_terminated_length": 576.0, "epoch": 0.16323995830283675, "frac_reward_zero_std": 0.25, "grad_norm": 0.5566451549530029, "learning_rate": 5.405e-07, "loss": 0.014, "num_tokens": 201356225.0, "reward": 0.3828125, "reward_std": 0.3067798614501953, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 920 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1928.0, "completions/mean_length": 1421.7109375, "completions/mean_terminated_length": 1269.6990966796875, "completions/min_length": 734.0, "completions/min_terminated_length": 734.0, "epoch": 0.16341739304012243, "frac_reward_zero_std": 0.375, "grad_norm": 0.5047520399093628, "learning_rate": 5.4e-07, "loss": 0.0159, "num_tokens": 201548204.0, "reward": 0.4453125, "reward_std": 0.2907276451587677, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 921 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2021.0, "completions/mean_length": 1422.4453125, "completions/mean_terminated_length": 1270.6116943359375, "completions/min_length": 638.0, "completions/min_terminated_length": 638.0, "epoch": 0.1635948277774081, "frac_reward_zero_std": 0.25, "grad_norm": 0.5967679023742676, "learning_rate": 5.395e-07, "loss": 0.0522, "num_tokens": 201740277.0, "reward": 0.46875, "reward_std": 0.3561279773712158, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 922 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1478.34375, "completions/mean_terminated_length": 1340.07763671875, "completions/min_length": 665.0, "completions/min_terminated_length": 665.0, "epoch": 0.16377226251469382, "frac_reward_zero_std": 0.25, "grad_norm": 0.5635038018226624, "learning_rate": 5.39e-07, "loss": 0.0217, "num_tokens": 201939505.0, "reward": 0.453125, "reward_std": 0.32128483057022095, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 923 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1422.6015625, "completions/mean_terminated_length": 1270.8057861328125, "completions/min_length": 664.0, "completions/min_terminated_length": 664.0, "epoch": 0.1639496972519795, "frac_reward_zero_std": 0.375, "grad_norm": 0.5530535578727722, "learning_rate": 5.384999999999999e-07, "loss": 0.0303, "num_tokens": 202131598.0, "reward": 0.3984375, "reward_std": 0.3021235466003418, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 924 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1544.84375, "completions/mean_terminated_length": 1377.125, "completions/min_length": 428.0, "completions/min_terminated_length": 428.0, "epoch": 0.1641271319892652, "frac_reward_zero_std": 0.0, "grad_norm": 0.6084845662117004, "learning_rate": 5.38e-07, "loss": 0.0262, "num_tokens": 202340042.0, "reward": 0.40625, "reward_std": 0.4305035471916199, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 925 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1540.65625, "completions/mean_terminated_length": 1342.1304931640625, "completions/min_length": 469.0, "completions/min_terminated_length": 469.0, "epoch": 0.1643045667265509, "frac_reward_zero_std": 0.0, "grad_norm": 0.5969578623771667, "learning_rate": 5.374999999999999e-07, "loss": 0.0191, "num_tokens": 202547950.0, "reward": 0.3515625, "reward_std": 0.462418794631958, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 926 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1518.328125, "completions/mean_terminated_length": 1231.1566162109375, "completions/min_length": 386.0, "completions/min_terminated_length": 386.0, "epoch": 0.16448200146383657, "frac_reward_zero_std": 0.0, "grad_norm": 0.6379212737083435, "learning_rate": 5.37e-07, "loss": 0.0274, "num_tokens": 202753000.0, "reward": 0.3359375, "reward_std": 0.448764443397522, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 927 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1489.2265625, "completions/mean_terminated_length": 1295.1263427734375, "completions/min_length": 474.0, "completions/min_terminated_length": 474.0, "epoch": 0.16465943620112228, "frac_reward_zero_std": 0.0, "grad_norm": 0.5939204692840576, "learning_rate": 5.365e-07, "loss": 0.012, "num_tokens": 202954325.0, "reward": 0.421875, "reward_std": 0.45395228266716003, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 928 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1492.671875, "completions/mean_terminated_length": 1201.7857666015625, "completions/min_length": 609.0, "completions/min_terminated_length": 609.0, "epoch": 0.16483687093840796, "frac_reward_zero_std": 0.375, "grad_norm": 0.3920523524284363, "learning_rate": 5.36e-07, "loss": 0.0125, "num_tokens": 203159755.0, "reward": 0.546875, "reward_std": 0.27132564783096313, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 929 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1509.46875, "completions/mean_terminated_length": 1196.9876708984375, "completions/min_length": 594.0, "completions/min_terminated_length": 594.0, "epoch": 0.16501430567569367, "frac_reward_zero_std": 0.25, "grad_norm": 0.4900974929332733, "learning_rate": 5.355e-07, "loss": 0.0042, "num_tokens": 203367335.0, "reward": 0.515625, "reward_std": 0.2755298614501953, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 930 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1493.765625, "completions/mean_terminated_length": 1182.8536376953125, "completions/min_length": 606.0, "completions/min_terminated_length": 606.0, "epoch": 0.16519174041297935, "frac_reward_zero_std": 0.25, "grad_norm": 0.4887286126613617, "learning_rate": 5.35e-07, "loss": 0.0166, "num_tokens": 203572905.0, "reward": 0.53125, "reward_std": 0.28748178482055664, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 931 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1481.828125, "completions/mean_terminated_length": 1224.477294921875, "completions/min_length": 598.0, "completions/min_terminated_length": 598.0, "epoch": 0.16536917515026503, "frac_reward_zero_std": 0.375, "grad_norm": 0.38009515404701233, "learning_rate": 5.344999999999999e-07, "loss": 0.0233, "num_tokens": 203776947.0, "reward": 0.578125, "reward_std": 0.27289125323295593, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 932 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2012.0, "completions/mean_length": 1519.40625, "completions/mean_terminated_length": 1191.5443115234375, "completions/min_length": 687.0, "completions/min_terminated_length": 687.0, "epoch": 0.16554660988755074, "frac_reward_zero_std": 0.375, "grad_norm": 0.547688364982605, "learning_rate": 5.34e-07, "loss": 0.0013, "num_tokens": 203983063.0, "reward": 0.34375, "reward_std": 0.28921058773994446, "rewards/simpleverify_reward/mean": 0.34375, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 933 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2006.0, "completions/mean_length": 1558.4375, "completions/mean_terminated_length": 1244.6153564453125, "completions/min_length": 702.0, "completions/min_terminated_length": 702.0, "epoch": 0.16572404462483642, "frac_reward_zero_std": 0.25, "grad_norm": 0.5471159815788269, "learning_rate": 5.335e-07, "loss": 0.0175, "num_tokens": 204194175.0, "reward": 0.40625, "reward_std": 0.3248332738876343, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 934 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1924.0, "completions/mean_length": 1529.1015625, "completions/mean_terminated_length": 1196.474365234375, "completions/min_length": 703.0, "completions/min_terminated_length": 703.0, "epoch": 0.16590147936212213, "frac_reward_zero_std": 0.125, "grad_norm": 0.627537727355957, "learning_rate": 5.33e-07, "loss": 0.02, "num_tokens": 204401532.0, "reward": 0.3828125, "reward_std": 0.3705565631389618, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 935 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1544.2265625, "completions/mean_terminated_length": 1251.91357421875, "completions/min_length": 678.0, "completions/min_terminated_length": 678.0, "epoch": 0.1660789140994078, "frac_reward_zero_std": 0.375, "grad_norm": 0.5578209161758423, "learning_rate": 5.325e-07, "loss": 0.0117, "num_tokens": 204610825.0, "reward": 0.3359375, "reward_std": 0.2926734387874603, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 936 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1409.953125, "completions/mean_terminated_length": 1197.2708740234375, "completions/min_length": 475.0, "completions/min_terminated_length": 475.0, "epoch": 0.1662563488366935, "frac_reward_zero_std": 0.125, "grad_norm": 0.6242923140525818, "learning_rate": 5.32e-07, "loss": 0.018, "num_tokens": 204803667.0, "reward": 0.4296875, "reward_std": 0.3481174111366272, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 937 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2003.0, "completions/mean_length": 1394.1875, "completions/mean_terminated_length": 1167.07373046875, "completions/min_length": 501.0, "completions/min_terminated_length": 501.0, "epoch": 0.1664337835739792, "frac_reward_zero_std": 0.25, "grad_norm": 0.5825689435005188, "learning_rate": 5.314999999999999e-07, "loss": 0.0182, "num_tokens": 204994491.0, "reward": 0.40625, "reward_std": 0.34703171253204346, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 938 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1415.8203125, "completions/mean_terminated_length": 1177.9031982421875, "completions/min_length": 604.0, "completions/min_terminated_length": 604.0, "epoch": 0.16661121831126488, "frac_reward_zero_std": 0.25, "grad_norm": 0.5366015434265137, "learning_rate": 5.31e-07, "loss": 0.0053, "num_tokens": 205188084.0, "reward": 0.3515625, "reward_std": 0.314206600189209, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 939 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1986.0, "completions/mean_length": 1396.21875, "completions/mean_terminated_length": 1169.810546875, "completions/min_length": 474.0, "completions/min_terminated_length": 474.0, "epoch": 0.1667886530485506, "frac_reward_zero_std": 0.125, "grad_norm": 0.6257774233818054, "learning_rate": 5.304999999999999e-07, "loss": 0.0134, "num_tokens": 205379168.0, "reward": 0.421875, "reward_std": 0.34998178482055664, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 940 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1464.8359375, "completions/mean_terminated_length": 1253.9041748046875, "completions/min_length": 285.0, "completions/min_terminated_length": 285.0, "epoch": 0.16696608778583627, "frac_reward_zero_std": 0.375, "grad_norm": 0.3703712522983551, "learning_rate": 5.3e-07, "loss": 0.0112, "num_tokens": 205576523.0, "reward": 0.671875, "reward_std": 0.2900126576423645, "rewards/simpleverify_reward/mean": 0.671875, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 941 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1982.0, "completions/mean_length": 1483.859375, "completions/mean_terminated_length": 1227.431884765625, "completions/min_length": 278.0, "completions/min_terminated_length": 278.0, "epoch": 0.16714352252312195, "frac_reward_zero_std": 0.25, "grad_norm": 0.425913006067276, "learning_rate": 5.295e-07, "loss": 0.0329, "num_tokens": 205776313.0, "reward": 0.609375, "reward_std": 0.3272273540496826, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 942 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 1987.0, "completions/mean_length": 1424.9921875, "completions/mean_terminated_length": 1217.322998046875, "completions/min_length": 272.0, "completions/min_terminated_length": 272.0, "epoch": 0.16732095726040766, "frac_reward_zero_std": 0.375, "grad_norm": 0.35563141107559204, "learning_rate": 5.29e-07, "loss": 0.0078, "num_tokens": 205968568.0, "reward": 0.6484375, "reward_std": 0.21808473765850067, "rewards/simpleverify_reward/mean": 0.6484375, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 943 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1482.421875, "completions/mean_terminated_length": 1277.85107421875, "completions/min_length": 278.0, "completions/min_terminated_length": 278.0, "epoch": 0.16749839199769334, "frac_reward_zero_std": 0.375, "grad_norm": 0.3774588704109192, "learning_rate": 5.284999999999999e-07, "loss": 0.005, "num_tokens": 206168174.0, "reward": 0.6328125, "reward_std": 0.25029873847961426, "rewards/simpleverify_reward/mean": 0.6328125, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 944 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2016.0, "completions/mean_length": 1368.3359375, "completions/mean_terminated_length": 1048.034423828125, "completions/min_length": 510.0, "completions/min_terminated_length": 510.0, "epoch": 0.16767582673497905, "frac_reward_zero_std": 0.25, "grad_norm": 0.4950558543205261, "learning_rate": 5.28e-07, "loss": 0.0055, "num_tokens": 206357801.0, "reward": 0.6015625, "reward_std": 0.28322336077690125, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 945 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1988.0, "completions/mean_length": 1381.6484375, "completions/mean_terminated_length": 1044.552978515625, "completions/min_length": 575.0, "completions/min_terminated_length": 575.0, "epoch": 0.16785326147226473, "frac_reward_zero_std": 0.625, "grad_norm": 0.322849839925766, "learning_rate": 5.274999999999999e-07, "loss": 0.0054, "num_tokens": 206549132.0, "reward": 0.59375, "reward_std": 0.1379890739917755, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 946 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2008.0, "completions/mean_length": 1364.125, "completions/mean_terminated_length": 1041.839111328125, "completions/min_length": 530.0, "completions/min_terminated_length": 530.0, "epoch": 0.1680306962095504, "frac_reward_zero_std": 0.375, "grad_norm": 0.428290992975235, "learning_rate": 5.27e-07, "loss": 0.0193, "num_tokens": 206738220.0, "reward": 0.6171875, "reward_std": 0.21808473765850067, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 947 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1381.0625, "completions/mean_terminated_length": 1066.7586669921875, "completions/min_length": 538.0, "completions/min_terminated_length": 538.0, "epoch": 0.16820813094683612, "frac_reward_zero_std": 0.25, "grad_norm": 0.5484077334403992, "learning_rate": 5.265e-07, "loss": 0.019, "num_tokens": 206929476.0, "reward": 0.5625, "reward_std": 0.24933473765850067, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 948 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1434.34375, "completions/mean_terminated_length": 1175.2445068359375, "completions/min_length": 412.0, "completions/min_terminated_length": 412.0, "epoch": 0.1683855656841218, "frac_reward_zero_std": 0.375, "grad_norm": 0.43803176283836365, "learning_rate": 5.26e-07, "loss": 0.0236, "num_tokens": 207122992.0, "reward": 0.5625, "reward_std": 0.2000408172607422, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 949 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2018.0, "completions/mean_length": 1444.515625, "completions/mean_terminated_length": 1243.354248046875, "completions/min_length": 427.0, "completions/min_terminated_length": 427.0, "epoch": 0.1685630004214075, "frac_reward_zero_std": 0.375, "grad_norm": 0.4317778944969177, "learning_rate": 5.255e-07, "loss": 0.0373, "num_tokens": 207317810.0, "reward": 0.6015625, "reward_std": 0.23107381165027618, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 950 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2005.0, "completions/mean_length": 1466.8203125, "completions/mean_terminated_length": 1248.0968017578125, "completions/min_length": 440.0, "completions/min_terminated_length": 440.0, "epoch": 0.1687404351586932, "frac_reward_zero_std": 0.125, "grad_norm": 0.58296799659729, "learning_rate": 5.25e-07, "loss": 0.0149, "num_tokens": 207515483.0, "reward": 0.53125, "reward_std": 0.3390933871269226, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 951 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1445.734375, "completions/mean_terminated_length": 1292.2156982421875, "completions/min_length": 459.0, "completions/min_terminated_length": 459.0, "epoch": 0.16891786989597887, "frac_reward_zero_std": 0.125, "grad_norm": 0.5844834446907043, "learning_rate": 5.244999999999999e-07, "loss": 0.0278, "num_tokens": 207710457.0, "reward": 0.59375, "reward_std": 0.33062565326690674, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 952 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1803.0, "completions/mean_length": 1487.6484375, "completions/mean_terminated_length": 1173.3048095703125, "completions/min_length": 626.0, "completions/min_terminated_length": 626.0, "epoch": 0.16909530463326458, "frac_reward_zero_std": 0.375, "grad_norm": 0.5118170380592346, "learning_rate": 5.24e-07, "loss": 0.0277, "num_tokens": 207912588.0, "reward": 0.5078125, "reward_std": 0.23062554001808167, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 953 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1525.0625, "completions/mean_terminated_length": 1211.300048828125, "completions/min_length": 643.0, "completions/min_terminated_length": 643.0, "epoch": 0.16927273937055026, "frac_reward_zero_std": 0.375, "grad_norm": 0.4943774938583374, "learning_rate": 5.234999999999999e-07, "loss": 0.01, "num_tokens": 208119508.0, "reward": 0.515625, "reward_std": 0.19628481566905975, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 954 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1964.0, "completions/mean_length": 1524.515625, "completions/mean_terminated_length": 1188.94873046875, "completions/min_length": 671.0, "completions/min_terminated_length": 671.0, "epoch": 0.16945017410783597, "frac_reward_zero_std": 0.5, "grad_norm": 0.41272351145744324, "learning_rate": 5.23e-07, "loss": 0.0244, "num_tokens": 208326358.0, "reward": 0.5, "reward_std": 0.17430339753627777, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 955 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1496.5234375, "completions/mean_terminated_length": 1245.852294921875, "completions/min_length": 620.0, "completions/min_terminated_length": 620.0, "epoch": 0.16962760884512165, "frac_reward_zero_std": 0.375, "grad_norm": 0.423787921667099, "learning_rate": 5.225e-07, "loss": 0.0144, "num_tokens": 208529625.0, "reward": 0.578125, "reward_std": 0.22953036427497864, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 956 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1201.75, "completions/mean_terminated_length": 1045.0369873046875, "completions/min_length": 389.0, "completions/min_terminated_length": 389.0, "epoch": 0.16980504358240733, "frac_reward_zero_std": 0.625, "grad_norm": 0.414927214384079, "learning_rate": 5.22e-07, "loss": 0.0093, "num_tokens": 208694137.0, "reward": 0.6328125, "reward_std": 0.1320282220840454, "rewards/simpleverify_reward/mean": 0.6328125, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 957 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1993.0, "completions/mean_length": 1197.3828125, "completions/mean_terminated_length": 1049.110107421875, "completions/min_length": 457.0, "completions/min_terminated_length": 457.0, "epoch": 0.16998247831969304, "frac_reward_zero_std": 0.5, "grad_norm": 0.4794359803199768, "learning_rate": 5.214999999999999e-07, "loss": 0.011, "num_tokens": 208858090.0, "reward": 0.6484375, "reward_std": 0.18574902415275574, "rewards/simpleverify_reward/mean": 0.6484375, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 958 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1926.0, "completions/mean_length": 1221.2421875, "completions/mean_terminated_length": 1020.5728149414062, "completions/min_length": 501.0, "completions/min_terminated_length": 501.0, "epoch": 0.17015991305697872, "frac_reward_zero_std": 0.5, "grad_norm": 0.4714824855327606, "learning_rate": 5.21e-07, "loss": 0.0287, "num_tokens": 209025097.0, "reward": 0.59375, "reward_std": 0.22863000631332397, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 959 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2003.0, "completions/mean_length": 1176.46875, "completions/mean_terminated_length": 1051.96435546875, "completions/min_length": 420.0, "completions/min_terminated_length": 420.0, "epoch": 0.17033734779426443, "frac_reward_zero_std": 0.375, "grad_norm": 0.5730910897254944, "learning_rate": 5.204999999999999e-07, "loss": 0.0325, "num_tokens": 209186373.0, "reward": 0.6484375, "reward_std": 0.23256748914718628, "rewards/simpleverify_reward/mean": 0.6484375, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 960 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1241.9296875, "completions/mean_terminated_length": 1092.657470703125, "completions/min_length": 368.0, "completions/min_terminated_length": 368.0, "epoch": 0.1705147825315501, "frac_reward_zero_std": 0.25, "grad_norm": 0.5543794631958008, "learning_rate": 5.2e-07, "loss": 0.0039, "num_tokens": 209356108.0, "reward": 0.625, "reward_std": 0.3202752470970154, "rewards/simpleverify_reward/mean": 0.625, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 961 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1961.0, "completions/mean_length": 1232.3046875, "completions/mean_terminated_length": 1063.0093994140625, "completions/min_length": 395.0, "completions/min_terminated_length": 395.0, "epoch": 0.1706922172688358, "frac_reward_zero_std": 0.25, "grad_norm": 0.57602459192276, "learning_rate": 5.195e-07, "loss": -0.0002, "num_tokens": 209524611.0, "reward": 0.625, "reward_std": 0.2909129858016968, "rewards/simpleverify_reward/mean": 0.625, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 962 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1199.9765625, "completions/mean_terminated_length": 1014.2191162109375, "completions/min_length": 384.0, "completions/min_terminated_length": 384.0, "epoch": 0.1708696520061215, "frac_reward_zero_std": 0.375, "grad_norm": 0.5108728408813477, "learning_rate": 5.19e-07, "loss": 0.0242, "num_tokens": 209688976.0, "reward": 0.6171875, "reward_std": 0.26783639192581177, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 963 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1935.0, "completions/mean_length": 1132.46875, "completions/mean_terminated_length": 1001.6785888671875, "completions/min_length": 404.0, "completions/min_terminated_length": 404.0, "epoch": 0.17104708674340718, "frac_reward_zero_std": 0.375, "grad_norm": 0.5079631805419922, "learning_rate": 5.184999999999999e-07, "loss": 0.009, "num_tokens": 209844700.0, "reward": 0.6640625, "reward_std": 0.2409759908914566, "rewards/simpleverify_reward/mean": 0.6640625, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 964 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1294.8984375, "completions/mean_terminated_length": 1187.3125, "completions/min_length": 544.0, "completions/min_terminated_length": 544.0, "epoch": 0.1712245214806929, "frac_reward_zero_std": 0.0, "grad_norm": 0.6892680525779724, "learning_rate": 5.18e-07, "loss": 0.0204, "num_tokens": 210022255.0, "reward": 0.375, "reward_std": 0.4377765655517578, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 965 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2003.0, "completions/mean_length": 1291.5546875, "completions/mean_terminated_length": 1143.0933837890625, "completions/min_length": 514.0, "completions/min_terminated_length": 514.0, "epoch": 0.17140195621797857, "frac_reward_zero_std": 0.0, "grad_norm": 0.6186103224754333, "learning_rate": 5.174999999999999e-07, "loss": 0.0102, "num_tokens": 210199382.0, "reward": 0.3515625, "reward_std": 0.45302411913871765, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 966 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1270.125, "completions/mean_terminated_length": 1159.0, "completions/min_length": 520.0, "completions/min_terminated_length": 520.0, "epoch": 0.17157939095526425, "frac_reward_zero_std": 0.0, "grad_norm": 0.6076728701591492, "learning_rate": 5.17e-07, "loss": 0.0066, "num_tokens": 210373766.0, "reward": 0.390625, "reward_std": 0.47213560342788696, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 967 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1314.3984375, "completions/mean_terminated_length": 1170.4205322265625, "completions/min_length": 567.0, "completions/min_terminated_length": 567.0, "epoch": 0.17175682569254996, "frac_reward_zero_std": 0.0, "grad_norm": 0.6525442600250244, "learning_rate": 5.164999999999999e-07, "loss": 0.0068, "num_tokens": 210553817.0, "reward": 0.40625, "reward_std": 0.4614642560482025, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 968 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1499.7421875, "completions/mean_terminated_length": 1124.618408203125, "completions/min_length": 607.0, "completions/min_terminated_length": 607.0, "epoch": 0.17193426042983564, "frac_reward_zero_std": 0.125, "grad_norm": 0.65024334192276, "learning_rate": 5.16e-07, "loss": 0.0311, "num_tokens": 210759032.0, "reward": 0.5, "reward_std": 0.3397586941719055, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 969 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1920.0, "completions/mean_length": 1516.046875, "completions/mean_terminated_length": 1102.3055419921875, "completions/min_length": 530.0, "completions/min_terminated_length": 530.0, "epoch": 0.17211169516712135, "frac_reward_zero_std": 0.125, "grad_norm": 0.6391782760620117, "learning_rate": 5.155e-07, "loss": 0.0111, "num_tokens": 210966334.0, "reward": 0.46875, "reward_std": 0.3221946358680725, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 970 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1998.0, "completions/mean_length": 1497.7421875, "completions/mean_terminated_length": 1189.0609130859375, "completions/min_length": 622.0, "completions/min_terminated_length": 622.0, "epoch": 0.17228912990440703, "frac_reward_zero_std": 0.125, "grad_norm": 0.6841428875923157, "learning_rate": 5.149999999999999e-07, "loss": 0.0149, "num_tokens": 211171293.0, "reward": 0.515625, "reward_std": 0.3719726800918579, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 971 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2001.0, "completions/mean_length": 1483.703125, "completions/mean_terminated_length": 1121.974365234375, "completions/min_length": 602.0, "completions/min_terminated_length": 602.0, "epoch": 0.17246656464169272, "frac_reward_zero_std": 0.125, "grad_norm": 0.665371835231781, "learning_rate": 5.144999999999999e-07, "loss": 0.0155, "num_tokens": 211374455.0, "reward": 0.5390625, "reward_std": 0.32171475887298584, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 972 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2016.0, "completions/mean_length": 1545.4765625, "completions/mean_terminated_length": 1201.644775390625, "completions/min_length": 542.0, "completions/min_terminated_length": 542.0, "epoch": 0.17264399937897842, "frac_reward_zero_std": 0.25, "grad_norm": 0.508702278137207, "learning_rate": 5.14e-07, "loss": 0.027, "num_tokens": 211583540.0, "reward": 0.40625, "reward_std": 0.3493928909301758, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 973 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1516.515625, "completions/mean_terminated_length": 1175.820556640625, "completions/min_length": 526.0, "completions/min_terminated_length": 526.0, "epoch": 0.1728214341162641, "frac_reward_zero_std": 0.125, "grad_norm": 0.5247697234153748, "learning_rate": 5.134999999999999e-07, "loss": 0.0395, "num_tokens": 211788918.0, "reward": 0.453125, "reward_std": 0.35783424973487854, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 974 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1498.0390625, "completions/mean_terminated_length": 1257.044921875, "completions/min_length": 548.0, "completions/min_terminated_length": 548.0, "epoch": 0.17299886885354981, "frac_reward_zero_std": 0.125, "grad_norm": 0.5658259987831116, "learning_rate": 5.13e-07, "loss": 0.0246, "num_tokens": 211991931.0, "reward": 0.4765625, "reward_std": 0.40263378620147705, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 975 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2013.0, "completions/mean_length": 1548.5625, "completions/mean_terminated_length": 1184.108154296875, "completions/min_length": 579.0, "completions/min_terminated_length": 579.0, "epoch": 0.1731763035908355, "frac_reward_zero_std": 0.125, "grad_norm": 0.5298219323158264, "learning_rate": 5.125e-07, "loss": 0.0365, "num_tokens": 212201411.0, "reward": 0.4609375, "reward_std": 0.38421088457107544, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 976 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1423.5078125, "completions/mean_terminated_length": 1286.71435546875, "completions/min_length": 544.0, "completions/min_terminated_length": 544.0, "epoch": 0.17335373832812118, "frac_reward_zero_std": 0.0, "grad_norm": 0.6154323220252991, "learning_rate": 5.12e-07, "loss": 0.0112, "num_tokens": 212397780.0, "reward": 0.5546875, "reward_std": 0.45459920167922974, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 977 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1419.15625, "completions/mean_terminated_length": 1266.5242919921875, "completions/min_length": 560.0, "completions/min_terminated_length": 560.0, "epoch": 0.17353117306540689, "frac_reward_zero_std": 0.0, "grad_norm": 0.6390635967254639, "learning_rate": 5.114999999999999e-07, "loss": 0.048, "num_tokens": 212593592.0, "reward": 0.5859375, "reward_std": 0.38136857748031616, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 978 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1391.671875, "completions/mean_terminated_length": 1262.8597412109375, "completions/min_length": 568.0, "completions/min_terminated_length": 568.0, "epoch": 0.17370860780269257, "frac_reward_zero_std": 0.125, "grad_norm": 0.5816176533699036, "learning_rate": 5.11e-07, "loss": 0.001, "num_tokens": 212785886.0, "reward": 0.625, "reward_std": 0.345456600189209, "rewards/simpleverify_reward/mean": 0.625, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 979 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1373.5703125, "completions/mean_terminated_length": 1297.330322265625, "completions/min_length": 582.0, "completions/min_terminated_length": 582.0, "epoch": 0.17388604253997827, "frac_reward_zero_std": 0.0, "grad_norm": 0.6792082786560059, "learning_rate": 5.104999999999999e-07, "loss": 0.0088, "num_tokens": 212975863.0, "reward": 0.65625, "reward_std": 0.3474799394607544, "rewards/simpleverify_reward/mean": 0.65625, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 980 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1858.0, "completions/mean_length": 1488.4296875, "completions/mean_terminated_length": 962.7727661132812, "completions/min_length": 477.0, "completions/min_terminated_length": 477.0, "epoch": 0.17406347727726396, "frac_reward_zero_std": 0.5, "grad_norm": 0.42808935046195984, "learning_rate": 5.1e-07, "loss": 0.0119, "num_tokens": 213179246.0, "reward": 0.3828125, "reward_std": 0.1593368798494339, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 981 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2011.0, "completions/mean_length": 1515.421875, "completions/mean_terminated_length": 1015.1212158203125, "completions/min_length": 473.0, "completions/min_terminated_length": 473.0, "epoch": 0.17424091201454964, "frac_reward_zero_std": 0.375, "grad_norm": 0.4686397612094879, "learning_rate": 5.095e-07, "loss": 0.0162, "num_tokens": 213386084.0, "reward": 0.3984375, "reward_std": 0.19828036427497864, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 982 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1915.0, "completions/mean_length": 1498.9140625, "completions/mean_terminated_length": 932.3968505859375, "completions/min_length": 459.0, "completions/min_terminated_length": 459.0, "epoch": 0.17441834675183535, "frac_reward_zero_std": 0.625, "grad_norm": 0.43036434054374695, "learning_rate": 5.09e-07, "loss": -0.009, "num_tokens": 213590809.0, "reward": 0.34375, "reward_std": 0.11840169876813889, "rewards/simpleverify_reward/mean": 0.34375, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 983 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.46875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1988.0, "completions/mean_length": 1472.5546875, "completions/mean_terminated_length": 964.808837890625, "completions/min_length": 457.0, "completions/min_terminated_length": 457.0, "epoch": 0.17459578148912103, "frac_reward_zero_std": 0.5, "grad_norm": 0.42754849791526794, "learning_rate": 5.085e-07, "loss": -0.0092, "num_tokens": 213792160.0, "reward": 0.3671875, "reward_std": 0.15558473765850067, "rewards/simpleverify_reward/mean": 0.3671875, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 984 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1854.0, "completions/mean_length": 1140.4375, "completions/mean_terminated_length": 991.92724609375, "completions/min_length": 450.0, "completions/min_terminated_length": 450.0, "epoch": 0.17477321622640674, "frac_reward_zero_std": 0.5, "grad_norm": 0.47246477007865906, "learning_rate": 5.079999999999999e-07, "loss": 0.0085, "num_tokens": 213946872.0, "reward": 0.703125, "reward_std": 0.19937554001808167, "rewards/simpleverify_reward/mean": 0.703125, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 985 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1102.2421875, "completions/mean_terminated_length": 957.3964233398438, "completions/min_length": 441.0, "completions/min_terminated_length": 441.0, "epoch": 0.17495065096369242, "frac_reward_zero_std": 0.5, "grad_norm": 0.520001232624054, "learning_rate": 5.074999999999999e-07, "loss": -0.0048, "num_tokens": 214096695.0, "reward": 0.640625, "reward_std": 0.21347813308238983, "rewards/simpleverify_reward/mean": 0.640625, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 986 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1842.0, "completions/mean_length": 1093.890625, "completions/mean_terminated_length": 947.7658081054688, "completions/min_length": 439.0, "completions/min_terminated_length": 439.0, "epoch": 0.1751280857009781, "frac_reward_zero_std": 0.5, "grad_norm": 0.5031280517578125, "learning_rate": 5.07e-07, "loss": 0.0043, "num_tokens": 214245449.0, "reward": 0.6953125, "reward_std": 0.20978017151355743, "rewards/simpleverify_reward/mean": 0.6953125, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 987 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1126.75, "completions/mean_terminated_length": 995.1428833007812, "completions/min_length": 455.0, "completions/min_terminated_length": 455.0, "epoch": 0.1753055204382638, "frac_reward_zero_std": 0.5, "grad_norm": 0.4571584165096283, "learning_rate": 5.064999999999999e-07, "loss": -0.0009, "num_tokens": 214398409.0, "reward": 0.6796875, "reward_std": 0.21103432774543762, "rewards/simpleverify_reward/mean": 0.6796875, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 988 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1901.0, "completions/mean_length": 1130.0546875, "completions/mean_terminated_length": 896.0686645507812, "completions/min_length": 420.0, "completions/min_terminated_length": 420.0, "epoch": 0.1754829551755495, "frac_reward_zero_std": 0.125, "grad_norm": 0.756882905960083, "learning_rate": 5.06e-07, "loss": 0.0111, "num_tokens": 214554048.0, "reward": 0.546875, "reward_std": 0.3411167562007904, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 989 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1174.734375, "completions/mean_terminated_length": 962.7767333984375, "completions/min_length": 415.0, "completions/min_terminated_length": 415.0, "epoch": 0.1756603899128352, "frac_reward_zero_std": 0.125, "grad_norm": 0.6771344542503357, "learning_rate": 5.055e-07, "loss": 0.0408, "num_tokens": 214715406.0, "reward": 0.640625, "reward_std": 0.3424736559391022, "rewards/simpleverify_reward/mean": 0.640625, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 990 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1177.2890625, "completions/mean_terminated_length": 944.5247192382812, "completions/min_length": 394.0, "completions/min_terminated_length": 394.0, "epoch": 0.17583782465012088, "frac_reward_zero_std": 0.375, "grad_norm": 0.5563556551933289, "learning_rate": 5.049999999999999e-07, "loss": 0.0231, "num_tokens": 214877091.0, "reward": 0.625, "reward_std": 0.2614234387874603, "rewards/simpleverify_reward/mean": 0.625, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 991 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2012.0, "completions/mean_length": 1157.1640625, "completions/mean_terminated_length": 940.9417724609375, "completions/min_length": 397.0, "completions/min_terminated_length": 397.0, "epoch": 0.17601525938740656, "frac_reward_zero_std": 0.125, "grad_norm": 0.6816340684890747, "learning_rate": 5.044999999999999e-07, "loss": 0.0219, "num_tokens": 215036200.0, "reward": 0.578125, "reward_std": 0.34042394161224365, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 992 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2022.0, "completions/mean_length": 1242.3984375, "completions/mean_terminated_length": 902.2555541992188, "completions/min_length": 324.0, "completions/min_terminated_length": 324.0, "epoch": 0.17619269412469227, "frac_reward_zero_std": 0.5, "grad_norm": 0.4131840169429779, "learning_rate": 5.04e-07, "loss": 0.0147, "num_tokens": 215206459.0, "reward": 0.28125, "reward_std": 0.21369513869285583, "rewards/simpleverify_reward/mean": 0.28125, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 993 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1218.7890625, "completions/mean_terminated_length": 975.888916015625, "completions/min_length": 347.0, "completions/min_terminated_length": 347.0, "epoch": 0.17637012886197795, "frac_reward_zero_std": 0.5, "grad_norm": 0.6375681757926941, "learning_rate": 5.034999999999999e-07, "loss": 0.002, "num_tokens": 215373696.0, "reward": 0.265625, "reward_std": 0.21574485301971436, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 994 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1920.0, "completions/mean_length": 1190.4375, "completions/mean_terminated_length": 867.6989135742188, "completions/min_length": 353.0, "completions/min_terminated_length": 353.0, "epoch": 0.17654756359926366, "frac_reward_zero_std": 0.625, "grad_norm": 0.41238731145858765, "learning_rate": 5.03e-07, "loss": 0.0142, "num_tokens": 215537304.0, "reward": 0.2734375, "reward_std": 0.1784759908914566, "rewards/simpleverify_reward/mean": 0.2734375, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 995 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2022.0, "completions/mean_length": 1235.7890625, "completions/mean_terminated_length": 905.5494995117188, "completions/min_length": 349.0, "completions/min_terminated_length": 349.0, "epoch": 0.17672499833654934, "frac_reward_zero_std": 0.625, "grad_norm": 0.35919642448425293, "learning_rate": 5.025e-07, "loss": -0.0057, "num_tokens": 215706717.0, "reward": 0.2734375, "reward_std": 0.18449485301971436, "rewards/simpleverify_reward/mean": 0.2734375, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 996 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1191.125, "completions/mean_terminated_length": 1022.9532470703125, "completions/min_length": 357.0, "completions/min_terminated_length": 357.0, "epoch": 0.17690243307383502, "frac_reward_zero_std": 0.25, "grad_norm": 0.5857241153717041, "learning_rate": 5.02e-07, "loss": 0.0076, "num_tokens": 215867261.0, "reward": 0.5390625, "reward_std": 0.3358173370361328, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 997 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1949.0, "completions/mean_length": 1188.640625, "completions/mean_terminated_length": 1038.843994140625, "completions/min_length": 336.0, "completions/min_terminated_length": 336.0, "epoch": 0.17707986781112073, "frac_reward_zero_std": 0.375, "grad_norm": 0.5156708359718323, "learning_rate": 5.014999999999999e-07, "loss": 0.0184, "num_tokens": 216027487.0, "reward": 0.578125, "reward_std": 0.2656276822090149, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 998 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1915.0, "completions/mean_length": 1194.578125, "completions/mean_terminated_length": 1017.4528198242188, "completions/min_length": 322.0, "completions/min_terminated_length": 322.0, "epoch": 0.1772573025484064, "frac_reward_zero_std": 0.375, "grad_norm": 0.5377020835876465, "learning_rate": 5.009999999999999e-07, "loss": 0.003, "num_tokens": 216188473.0, "reward": 0.5859375, "reward_std": 0.2768382132053375, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 999 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2004.0, "completions/mean_length": 1173.0703125, "completions/mean_terminated_length": 981.4190673828125, "completions/min_length": 395.0, "completions/min_terminated_length": 395.0, "epoch": 0.17743473728569212, "frac_reward_zero_std": 0.375, "grad_norm": 0.49568939208984375, "learning_rate": 5.004999999999999e-07, "loss": 0.0024, "num_tokens": 216346706.0, "reward": 0.6640625, "reward_std": 0.22013446688652039, "rewards/simpleverify_reward/mean": 0.6640625, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1000 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1295.921875, "completions/mean_terminated_length": 1055.5670166015625, "completions/min_length": 608.0, "completions/min_terminated_length": 608.0, "epoch": 0.1776121720229778, "frac_reward_zero_std": 1.0, "grad_norm": 0.0, "learning_rate": 5e-07, "loss": 0.0, "num_tokens": 216526520.0, "reward": 0.625, "reward_std": 0.0, "rewards/simpleverify_reward/mean": 0.625, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 1001 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1312.6328125, "completions/mean_terminated_length": 1067.510498046875, "completions/min_length": 567.0, "completions/min_terminated_length": 567.0, "epoch": 0.17778960676026348, "frac_reward_zero_std": 0.5, "grad_norm": 0.46639081835746765, "learning_rate": 4.994999999999999e-07, "loss": 0.0092, "num_tokens": 216708473.0, "reward": 0.6171875, "reward_std": 0.1593368798494339, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1002 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1850.0, "completions/mean_length": 1311.484375, "completions/mean_terminated_length": 1045.0850830078125, "completions/min_length": 657.0, "completions/min_terminated_length": 657.0, "epoch": 0.1779670414975492, "frac_reward_zero_std": 0.375, "grad_norm": 0.48045510053634644, "learning_rate": 4.99e-07, "loss": 0.0163, "num_tokens": 216890279.0, "reward": 0.6015625, "reward_std": 0.17914125323295593, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1003 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1969.0, "completions/mean_length": 1312.9921875, "completions/mean_terminated_length": 1057.6737060546875, "completions/min_length": 616.0, "completions/min_terminated_length": 616.0, "epoch": 0.17814447623483487, "frac_reward_zero_std": 0.375, "grad_norm": 0.6237868666648865, "learning_rate": 4.985e-07, "loss": 0.0155, "num_tokens": 217072278.0, "reward": 0.578125, "reward_std": 0.20379294455051422, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1004 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1917.0, "completions/mean_length": 1184.2734375, "completions/mean_terminated_length": 1103.0684814453125, "completions/min_length": 453.0, "completions/min_terminated_length": 453.0, "epoch": 0.17832191097212058, "frac_reward_zero_std": 0.25, "grad_norm": 0.6631577610969543, "learning_rate": 4.979999999999999e-07, "loss": 0.0402, "num_tokens": 217233801.0, "reward": 0.4375, "reward_std": 0.28212815523147583, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1005 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1168.359375, "completions/mean_terminated_length": 1125.0982666015625, "completions/min_length": 485.0, "completions/min_terminated_length": 485.0, "epoch": 0.17849934570940626, "frac_reward_zero_std": 0.375, "grad_norm": 0.5686766505241394, "learning_rate": 4.975e-07, "loss": 0.0121, "num_tokens": 217393287.0, "reward": 0.4765625, "reward_std": 0.26805341243743896, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1006 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1960.0, "completions/mean_length": 1192.71875, "completions/mean_terminated_length": 1087.6842041015625, "completions/min_length": 478.0, "completions/min_terminated_length": 478.0, "epoch": 0.17867678044669194, "frac_reward_zero_std": 0.375, "grad_norm": 0.5407971143722534, "learning_rate": 4.97e-07, "loss": 0.0242, "num_tokens": 217555891.0, "reward": 0.40625, "reward_std": 0.2520497143268585, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1007 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.09375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2020.0, "completions/mean_length": 1224.4765625, "completions/mean_terminated_length": 1139.284423828125, "completions/min_length": 474.0, "completions/min_terminated_length": 474.0, "epoch": 0.17885421518397765, "frac_reward_zero_std": 0.375, "grad_norm": 0.4752250611782074, "learning_rate": 4.964999999999999e-07, "loss": 0.0378, "num_tokens": 217722560.0, "reward": 0.453125, "reward_std": 0.25878483057022095, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1008 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.09375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2019.0, "completions/mean_length": 1068.8828125, "completions/mean_terminated_length": 967.5948486328125, "completions/min_length": 373.0, "completions/min_terminated_length": 373.0, "epoch": 0.17903164992126333, "frac_reward_zero_std": 0.25, "grad_norm": 0.5981407165527344, "learning_rate": 4.96e-07, "loss": 0.0241, "num_tokens": 217866449.0, "reward": 0.6171875, "reward_std": 0.27901527285575867, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1009 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1960.0, "completions/mean_length": 1046.2890625, "completions/mean_terminated_length": 923.2719116210938, "completions/min_length": 303.0, "completions/min_terminated_length": 303.0, "epoch": 0.17920908465854904, "frac_reward_zero_std": 0.5, "grad_norm": 0.5867880582809448, "learning_rate": 4.955e-07, "loss": 0.0206, "num_tokens": 218007446.0, "reward": 0.546875, "reward_std": 0.21521076560020447, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1010 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1981.0, "completions/mean_length": 1055.3046875, "completions/mean_terminated_length": 903.270263671875, "completions/min_length": 349.0, "completions/min_terminated_length": 349.0, "epoch": 0.17938651939583472, "frac_reward_zero_std": 0.125, "grad_norm": 0.7393320202827454, "learning_rate": 4.95e-07, "loss": 0.0276, "num_tokens": 218149597.0, "reward": 0.6015625, "reward_std": 0.33033639192581177, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1011 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2006.0, "completions/mean_length": 1044.578125, "completions/mean_terminated_length": 911.3805541992188, "completions/min_length": 355.0, "completions/min_terminated_length": 355.0, "epoch": 0.1795639541331204, "frac_reward_zero_std": 0.25, "grad_norm": 0.7118883728981018, "learning_rate": 4.945e-07, "loss": 0.0045, "num_tokens": 218290375.0, "reward": 0.578125, "reward_std": 0.28737401962280273, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1012 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2007.0, "completions/mean_length": 1464.8671875, "completions/mean_terminated_length": 1301.5899658203125, "completions/min_length": 603.0, "completions/min_terminated_length": 603.0, "epoch": 0.1797413888704061, "frac_reward_zero_std": 0.125, "grad_norm": 0.5528715252876282, "learning_rate": 4.94e-07, "loss": 0.0435, "num_tokens": 218489782.0, "reward": 0.5859375, "reward_std": 0.36222946643829346, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1013 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1450.546875, "completions/mean_terminated_length": 1326.5472412109375, "completions/min_length": 639.0, "completions/min_terminated_length": 639.0, "epoch": 0.1799188236076918, "frac_reward_zero_std": 0.125, "grad_norm": 0.5382867455482483, "learning_rate": 4.935e-07, "loss": 0.0061, "num_tokens": 218687356.0, "reward": 0.53125, "reward_std": 0.39145228266716003, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1014 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1494.890625, "completions/mean_terminated_length": 1353.9019775390625, "completions/min_length": 653.0, "completions/min_terminated_length": 653.0, "epoch": 0.1800962583449775, "frac_reward_zero_std": 0.25, "grad_norm": 0.5384383797645569, "learning_rate": 4.93e-07, "loss": 0.0249, "num_tokens": 218890606.0, "reward": 0.5703125, "reward_std": 0.3160167932510376, "rewards/simpleverify_reward/mean": 0.5703125, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1015 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1470.1640625, "completions/mean_terminated_length": 1329.91259765625, "completions/min_length": 609.0, "completions/min_terminated_length": 609.0, "epoch": 0.18027369308226318, "frac_reward_zero_std": 0.125, "grad_norm": 0.5660786628723145, "learning_rate": 4.924999999999999e-07, "loss": 0.0252, "num_tokens": 219090691.0, "reward": 0.578125, "reward_std": 0.3551456332206726, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1016 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1407.34375, "completions/mean_terminated_length": 1211.2244873046875, "completions/min_length": 572.0, "completions/min_terminated_length": 572.0, "epoch": 0.18045112781954886, "frac_reward_zero_std": 0.125, "grad_norm": 0.5297269821166992, "learning_rate": 4.92e-07, "loss": 0.0003, "num_tokens": 219284239.0, "reward": 0.4140625, "reward_std": 0.3515252470970154, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1017 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1432.4921875, "completions/mean_terminated_length": 1275.59814453125, "completions/min_length": 552.0, "completions/min_terminated_length": 552.0, "epoch": 0.18062856255683457, "frac_reward_zero_std": 0.125, "grad_norm": 0.535946786403656, "learning_rate": 4.915e-07, "loss": 0.009, "num_tokens": 219481006.0, "reward": 0.4609375, "reward_std": 0.38730162382125854, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1018 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1437.1953125, "completions/mean_terminated_length": 1317.3177490234375, "completions/min_length": 555.0, "completions/min_terminated_length": 555.0, "epoch": 0.18080599729412025, "frac_reward_zero_std": 0.125, "grad_norm": 0.5877459049224854, "learning_rate": 4.909999999999999e-07, "loss": -0.0106, "num_tokens": 219678375.0, "reward": 0.515625, "reward_std": 0.3685610294342041, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1019 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1399.421875, "completions/mean_terminated_length": 1286.366943359375, "completions/min_length": 426.0, "completions/min_terminated_length": 426.0, "epoch": 0.18098343203140596, "frac_reward_zero_std": 0.0, "grad_norm": 0.6307836771011353, "learning_rate": 4.905e-07, "loss": -0.0078, "num_tokens": 219870909.0, "reward": 0.484375, "reward_std": 0.4404057264328003, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1020 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2007.0, "completions/mean_length": 1403.75, "completions/mean_terminated_length": 1161.290283203125, "completions/min_length": 620.0, "completions/min_terminated_length": 620.0, "epoch": 0.18116086676869164, "frac_reward_zero_std": 0.25, "grad_norm": 0.5016013383865356, "learning_rate": 4.9e-07, "loss": 0.0279, "num_tokens": 220060861.0, "reward": 0.53125, "reward_std": 0.32040640711784363, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1021 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1405.96875, "completions/mean_terminated_length": 1134.888916015625, "completions/min_length": 635.0, "completions/min_terminated_length": 635.0, "epoch": 0.18133830150597732, "frac_reward_zero_std": 0.25, "grad_norm": 0.540497362613678, "learning_rate": 4.894999999999999e-07, "loss": 0.0242, "num_tokens": 220251097.0, "reward": 0.5390625, "reward_std": 0.30896076560020447, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1022 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1415.546875, "completions/mean_terminated_length": 1177.52685546875, "completions/min_length": 629.0, "completions/min_terminated_length": 629.0, "epoch": 0.18151573624326303, "frac_reward_zero_std": 0.25, "grad_norm": 0.49823129177093506, "learning_rate": 4.89e-07, "loss": 0.0399, "num_tokens": 220442559.0, "reward": 0.5390625, "reward_std": 0.3289783000946045, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1023 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2000.0, "completions/mean_length": 1394.046875, "completions/mean_terminated_length": 1138.1522216796875, "completions/min_length": 709.0, "completions/min_terminated_length": 709.0, "epoch": 0.1816931709805487, "frac_reward_zero_std": 0.25, "grad_norm": 0.5517503023147583, "learning_rate": 4.885e-07, "loss": 0.019, "num_tokens": 220631269.0, "reward": 0.5546875, "reward_std": 0.32171475887298584, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1024 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1543.2890625, "completions/mean_terminated_length": 1260.158447265625, "completions/min_length": 559.0, "completions/min_terminated_length": 559.0, "epoch": 0.18187060571783442, "frac_reward_zero_std": 0.125, "grad_norm": 0.6850502490997314, "learning_rate": 4.879999999999999e-07, "loss": 0.0227, "num_tokens": 220846794.0, "reward": 0.4296875, "reward_std": 0.3470000624656677, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1025 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1561.2421875, "completions/mean_terminated_length": 1306.2738037109375, "completions/min_length": 556.0, "completions/min_terminated_length": 556.0, "epoch": 0.1820480404551201, "frac_reward_zero_std": 0.25, "grad_norm": 0.6196487545967102, "learning_rate": 4.875e-07, "loss": 0.0121, "num_tokens": 221064617.0, "reward": 0.3203125, "reward_std": 0.28013262152671814, "rewards/simpleverify_reward/mean": 0.3203125, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 1026 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1528.3046875, "completions/mean_terminated_length": 1300.572998046875, "completions/min_length": 555.0, "completions/min_terminated_length": 555.0, "epoch": 0.18222547519240578, "frac_reward_zero_std": 0.0, "grad_norm": 0.7546705007553101, "learning_rate": 4.87e-07, "loss": 0.0239, "num_tokens": 221278224.0, "reward": 0.4453125, "reward_std": 0.41152340173721313, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1027 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1503.0, "completions/mean_terminated_length": 1281.4066162109375, "completions/min_length": 541.0, "completions/min_terminated_length": 541.0, "epoch": 0.1824029099296915, "frac_reward_zero_std": 0.125, "grad_norm": 0.5372587442398071, "learning_rate": 4.864999999999999e-07, "loss": 0.0201, "num_tokens": 221488592.0, "reward": 0.40625, "reward_std": 0.34703171253204346, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1028 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1334.2109375, "completions/mean_terminated_length": 1054.9022216796875, "completions/min_length": 294.0, "completions/min_terminated_length": 294.0, "epoch": 0.18258034466697717, "frac_reward_zero_std": 0.125, "grad_norm": 0.7249754667282104, "learning_rate": 4.86e-07, "loss": 0.0023, "num_tokens": 221672219.0, "reward": 0.3515625, "reward_std": 0.38444983959198, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1029 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1367.0703125, "completions/mean_terminated_length": 1130.536865234375, "completions/min_length": 321.0, "completions/min_terminated_length": 321.0, "epoch": 0.18275777940426288, "frac_reward_zero_std": 0.125, "grad_norm": 0.667853832244873, "learning_rate": 4.854999999999999e-07, "loss": 0.0132, "num_tokens": 221860052.0, "reward": 0.40625, "reward_std": 0.37675637006759644, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1030 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1326.5234375, "completions/mean_terminated_length": 1075.9052734375, "completions/min_length": 297.0, "completions/min_terminated_length": 297.0, "epoch": 0.18293521414154856, "frac_reward_zero_std": 0.0, "grad_norm": 0.7542763352394104, "learning_rate": 4.85e-07, "loss": -0.0026, "num_tokens": 222042695.0, "reward": 0.4296875, "reward_std": 0.40207332372665405, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1031 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1382.140625, "completions/mean_terminated_length": 1121.5870361328125, "completions/min_length": 291.0, "completions/min_terminated_length": 291.0, "epoch": 0.18311264887883424, "frac_reward_zero_std": 0.0, "grad_norm": 0.7086990475654602, "learning_rate": 4.845e-07, "loss": 0.0259, "num_tokens": 222232457.0, "reward": 0.3828125, "reward_std": 0.42347532510757446, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1032 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1998.0, "completions/mean_length": 1289.6484375, "completions/mean_terminated_length": 906.0117797851562, "completions/min_length": 361.0, "completions/min_terminated_length": 361.0, "epoch": 0.18329008361611995, "frac_reward_zero_std": 0.25, "grad_norm": 0.7179805636405945, "learning_rate": 4.839999999999999e-07, "loss": 0.0017, "num_tokens": 222408428.0, "reward": 0.484375, "reward_std": 0.3122924566268921, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1033 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1246.609375, "completions/mean_terminated_length": 1001.2857055664062, "completions/min_length": 369.0, "completions/min_terminated_length": 369.0, "epoch": 0.18346751835340563, "frac_reward_zero_std": 0.25, "grad_norm": 0.7298426628112793, "learning_rate": 4.835e-07, "loss": 0.0109, "num_tokens": 222578890.0, "reward": 0.5546875, "reward_std": 0.28652724623680115, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1034 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1282.8671875, "completions/mean_terminated_length": 1038.3402099609375, "completions/min_length": 382.0, "completions/min_terminated_length": 382.0, "epoch": 0.18364495309069134, "frac_reward_zero_std": 0.25, "grad_norm": 0.73063063621521, "learning_rate": 4.83e-07, "loss": 0.0156, "num_tokens": 222753993.0, "reward": 0.53125, "reward_std": 0.3093358874320984, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1035 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1260.734375, "completions/mean_terminated_length": 964.4515991210938, "completions/min_length": 355.0, "completions/min_terminated_length": 355.0, "epoch": 0.18382238782797702, "frac_reward_zero_std": 0.25, "grad_norm": 0.6609231233596802, "learning_rate": 4.824999999999999e-07, "loss": 0.0276, "num_tokens": 222926263.0, "reward": 0.5546875, "reward_std": 0.2986064851284027, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1036 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2005.0, "completions/mean_length": 1368.9375, "completions/mean_terminated_length": 1113.3763427734375, "completions/min_length": 657.0, "completions/min_terminated_length": 657.0, "epoch": 0.1839998225652627, "frac_reward_zero_std": 0.375, "grad_norm": 0.4602085053920746, "learning_rate": 4.82e-07, "loss": 0.0215, "num_tokens": 223113615.0, "reward": 0.6640625, "reward_std": 0.24952572584152222, "rewards/simpleverify_reward/mean": 0.6640625, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1037 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1985.0, "completions/mean_length": 1387.5234375, "completions/mean_terminated_length": 1108.6556396484375, "completions/min_length": 615.0, "completions/min_terminated_length": 615.0, "epoch": 0.1841772573025484, "frac_reward_zero_std": 0.25, "grad_norm": 0.5030209422111511, "learning_rate": 4.815e-07, "loss": 0.0218, "num_tokens": 223303346.0, "reward": 0.6484375, "reward_std": 0.27991947531700134, "rewards/simpleverify_reward/mean": 0.6484375, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1038 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2023.0, "completions/mean_length": 1362.3203125, "completions/mean_terminated_length": 1152.4183349609375, "completions/min_length": 518.0, "completions/min_terminated_length": 518.0, "epoch": 0.1843546920398341, "frac_reward_zero_std": 0.25, "grad_norm": 0.581887423992157, "learning_rate": 4.809999999999999e-07, "loss": 0.0393, "num_tokens": 223489851.0, "reward": 0.7265625, "reward_std": 0.3227234482765198, "rewards/simpleverify_reward/mean": 0.7265625, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 1039 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1383.828125, "completions/mean_terminated_length": 1123.934814453125, "completions/min_length": 507.0, "completions/min_terminated_length": 507.0, "epoch": 0.1845321267771198, "frac_reward_zero_std": 0.375, "grad_norm": 0.4906255900859833, "learning_rate": 4.805e-07, "loss": 0.0253, "num_tokens": 223679109.0, "reward": 0.6640625, "reward_std": 0.28548622131347656, "rewards/simpleverify_reward/mean": 0.6640625, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1040 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1517.890625, "completions/mean_terminated_length": 1259.0, "completions/min_length": 335.0, "completions/min_terminated_length": 335.0, "epoch": 0.18470956151440548, "frac_reward_zero_std": 0.125, "grad_norm": 0.7133379578590393, "learning_rate": 4.8e-07, "loss": -0.0017, "num_tokens": 223882135.0, "reward": 0.34375, "reward_std": 0.3542124032974243, "rewards/simpleverify_reward/mean": 0.34375, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 1041 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1518.5859375, "completions/mean_terminated_length": 1295.0555419921875, "completions/min_length": 334.0, "completions/min_terminated_length": 334.0, "epoch": 0.18488699625169117, "frac_reward_zero_std": 0.25, "grad_norm": 0.6428630948066711, "learning_rate": 4.794999999999999e-07, "loss": 0.0134, "num_tokens": 224085250.0, "reward": 0.390625, "reward_std": 0.31138262152671814, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1042 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1529.2421875, "completions/mean_terminated_length": 1284.7701416015625, "completions/min_length": 349.0, "completions/min_terminated_length": 349.0, "epoch": 0.18506443098897687, "frac_reward_zero_std": 0.375, "grad_norm": 0.5716790556907654, "learning_rate": 4.79e-07, "loss": 0.0065, "num_tokens": 224289729.0, "reward": 0.3359375, "reward_std": 0.27526313066482544, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1043 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1502.6875, "completions/mean_terminated_length": 1280.967041015625, "completions/min_length": 313.0, "completions/min_terminated_length": 313.0, "epoch": 0.18524186572626256, "frac_reward_zero_std": 0.125, "grad_norm": 0.764651894569397, "learning_rate": 4.785e-07, "loss": 0.0057, "num_tokens": 224490809.0, "reward": 0.390625, "reward_std": 0.3462296426296234, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1044 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1116.9765625, "completions/mean_terminated_length": 1011.7304077148438, "completions/min_length": 388.0, "completions/min_terminated_length": 388.0, "epoch": 0.18541930046354826, "frac_reward_zero_std": 0.125, "grad_norm": 0.6323384046554565, "learning_rate": 4.779999999999999e-07, "loss": 0.0097, "num_tokens": 224643286.0, "reward": 0.625, "reward_std": 0.3561279773712158, "rewards/simpleverify_reward/mean": 0.625, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 1045 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1130.4140625, "completions/mean_terminated_length": 939.9717407226562, "completions/min_length": 431.0, "completions/min_terminated_length": 431.0, "epoch": 0.18559673520083395, "frac_reward_zero_std": 0.125, "grad_norm": 0.7481417059898376, "learning_rate": 4.775e-07, "loss": 0.0068, "num_tokens": 224797483.0, "reward": 0.6328125, "reward_std": 0.33478015661239624, "rewards/simpleverify_reward/mean": 0.6328125, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1046 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2002.0, "completions/mean_length": 1136.53125, "completions/mean_terminated_length": 987.3817749023438, "completions/min_length": 427.0, "completions/min_terminated_length": 427.0, "epoch": 0.18577416993811963, "frac_reward_zero_std": 0.25, "grad_norm": 0.6656091213226318, "learning_rate": 4.769999999999999e-07, "loss": 0.0107, "num_tokens": 224952463.0, "reward": 0.65625, "reward_std": 0.3072861433029175, "rewards/simpleverify_reward/mean": 0.65625, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 1047 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1961.0, "completions/mean_length": 1129.4453125, "completions/mean_terminated_length": 928.2381591796875, "completions/min_length": 442.0, "completions/min_terminated_length": 442.0, "epoch": 0.18595160467540534, "frac_reward_zero_std": 0.25, "grad_norm": 0.6349508166313171, "learning_rate": 4.7649999999999996e-07, "loss": -0.0079, "num_tokens": 225106536.0, "reward": 0.59375, "reward_std": 0.28258588910102844, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1048 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1605.078125, "completions/mean_terminated_length": 1175.78466796875, "completions/min_length": 424.0, "completions/min_terminated_length": 424.0, "epoch": 0.18612903941269102, "frac_reward_zero_std": 0.25, "grad_norm": 0.5121270418167114, "learning_rate": 4.76e-07, "loss": 0.0104, "num_tokens": 225323906.0, "reward": 0.265625, "reward_std": 0.303402841091156, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 1049 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1584.0546875, "completions/mean_terminated_length": 1223.2083740234375, "completions/min_length": 437.0, "completions/min_terminated_length": 437.0, "epoch": 0.18630647414997673, "frac_reward_zero_std": 0.25, "grad_norm": 0.5502735376358032, "learning_rate": 4.7549999999999994e-07, "loss": 0.0094, "num_tokens": 225538585.0, "reward": 0.3359375, "reward_std": 0.3440170884132385, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1050 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1574.453125, "completions/mean_terminated_length": 1194.2816162109375, "completions/min_length": 476.0, "completions/min_terminated_length": 476.0, "epoch": 0.1864839088872624, "frac_reward_zero_std": 0.25, "grad_norm": 0.5606426000595093, "learning_rate": 4.7499999999999995e-07, "loss": 0.0228, "num_tokens": 225752035.0, "reward": 0.34375, "reward_std": 0.2915782630443573, "rewards/simpleverify_reward/mean": 0.34375, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 1051 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1594.21875, "completions/mean_terminated_length": 1126.0318603515625, "completions/min_length": 462.0, "completions/min_terminated_length": 462.0, "epoch": 0.1866613436245481, "frac_reward_zero_std": 0.25, "grad_norm": 0.5859506130218506, "learning_rate": 4.7449999999999997e-07, "loss": 0.0319, "num_tokens": 225968015.0, "reward": 0.28125, "reward_std": 0.3176366090774536, "rewards/simpleverify_reward/mean": 0.28125, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 1052 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.09375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1152.640625, "completions/mean_terminated_length": 1060.0172119140625, "completions/min_length": 352.0, "completions/min_terminated_length": 352.0, "epoch": 0.1868387783618338, "frac_reward_zero_std": 0.375, "grad_norm": 0.6465532183647156, "learning_rate": 4.7399999999999993e-07, "loss": 0.0066, "num_tokens": 226127041.0, "reward": 0.5546875, "reward_std": 0.306327760219574, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1053 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1147.90625, "completions/mean_terminated_length": 1046.156494140625, "completions/min_length": 401.0, "completions/min_terminated_length": 401.0, "epoch": 0.18701621309911948, "frac_reward_zero_std": 0.25, "grad_norm": 0.7096079587936401, "learning_rate": 4.7349999999999995e-07, "loss": -0.0037, "num_tokens": 226285461.0, "reward": 0.546875, "reward_std": 0.3379541039466858, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1054 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1153.1953125, "completions/mean_terminated_length": 987.49072265625, "completions/min_length": 338.0, "completions/min_terminated_length": 338.0, "epoch": 0.18719364783640519, "frac_reward_zero_std": 0.25, "grad_norm": 0.7344784736633301, "learning_rate": 4.7299999999999996e-07, "loss": -0.0022, "num_tokens": 226444558.0, "reward": 0.6015625, "reward_std": 0.2843368649482727, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1055 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2012.0, "completions/mean_length": 1142.4375, "completions/mean_terminated_length": 1013.0714721679688, "completions/min_length": 400.0, "completions/min_terminated_length": 400.0, "epoch": 0.18737108257369087, "frac_reward_zero_std": 0.375, "grad_norm": 0.6879386305809021, "learning_rate": 4.725e-07, "loss": 0.0054, "num_tokens": 226602278.0, "reward": 0.6015625, "reward_std": 0.24198853969573975, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1056 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1768.0, "completions/mean_length": 1442.375, "completions/mean_terminated_length": 1014.4000244140625, "completions/min_length": 297.0, "completions/min_terminated_length": 297.0, "epoch": 0.18754851731097655, "frac_reward_zero_std": 0.5, "grad_norm": 0.6176565885543823, "learning_rate": 4.7199999999999994e-07, "loss": 0.0098, "num_tokens": 226796086.0, "reward": 0.265625, "reward_std": 0.2066391110420227, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 1057 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2008.0, "completions/mean_length": 1494.7421875, "completions/mean_terminated_length": 1077.904052734375, "completions/min_length": 316.0, "completions/min_terminated_length": 316.0, "epoch": 0.18772595204826226, "frac_reward_zero_std": 0.25, "grad_norm": 0.6302356719970703, "learning_rate": 4.7149999999999995e-07, "loss": 0.0263, "num_tokens": 226996597.0, "reward": 0.359375, "reward_std": 0.2948821485042572, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 1058 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1888.0, "completions/mean_length": 1429.359375, "completions/mean_terminated_length": 1006.0789794921875, "completions/min_length": 290.0, "completions/min_terminated_length": 290.0, "epoch": 0.18790338678554794, "frac_reward_zero_std": 0.625, "grad_norm": 0.5753463506698608, "learning_rate": 4.7099999999999997e-07, "loss": 0.0123, "num_tokens": 227188739.0, "reward": 0.2890625, "reward_std": 0.15558473765850067, "rewards/simpleverify_reward/mean": 0.2890625, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 1059 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2016.0, "completions/mean_length": 1470.3515625, "completions/mean_terminated_length": 1087.7532958984375, "completions/min_length": 291.0, "completions/min_terminated_length": 291.0, "epoch": 0.18808082152283365, "frac_reward_zero_std": 0.5, "grad_norm": 0.6285086870193481, "learning_rate": 4.7049999999999993e-07, "loss": 0.018, "num_tokens": 227386128.0, "reward": 0.3046875, "reward_std": 0.17914125323295593, "rewards/simpleverify_reward/mean": 0.3046875, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 1060 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.53125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1770.109375, "completions/mean_terminated_length": 1455.166748046875, "completions/min_length": 922.0, "completions/min_terminated_length": 922.0, "epoch": 0.18825825626011933, "frac_reward_zero_std": 0.625, "grad_norm": 0.33815133571624756, "learning_rate": 4.6999999999999995e-07, "loss": -0.0016, "num_tokens": 227623774.0, "reward": 0.125, "reward_std": 0.10519562661647797, "rewards/simpleverify_reward/mean": 0.125, "rewards/simpleverify_reward/std": 0.3320184051990509, "step": 1061 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1771.765625, "completions/mean_terminated_length": 1504.03076171875, "completions/min_length": 780.0, "completions/min_terminated_length": 780.0, "epoch": 0.188435690997405, "frac_reward_zero_std": 0.25, "grad_norm": 0.43570926785469055, "learning_rate": 4.6949999999999996e-07, "loss": 0.0112, "num_tokens": 227861632.0, "reward": 0.234375, "reward_std": 0.266292929649353, "rewards/simpleverify_reward/mean": 0.234375, "rewards/simpleverify_reward/std": 0.42527204751968384, "step": 1062 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1770.625, "completions/mean_terminated_length": 1475.354736328125, "completions/min_length": 938.0, "completions/min_terminated_length": 938.0, "epoch": 0.18861312573469072, "frac_reward_zero_std": 0.375, "grad_norm": 0.3967943787574768, "learning_rate": 4.689999999999999e-07, "loss": 0.0181, "num_tokens": 228099344.0, "reward": 0.234375, "reward_std": 0.23283424973487854, "rewards/simpleverify_reward/mean": 0.234375, "rewards/simpleverify_reward/std": 0.42527204751968384, "step": 1063 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1756.65625, "completions/mean_terminated_length": 1474.2769775390625, "completions/min_length": 949.0, "completions/min_terminated_length": 949.0, "epoch": 0.1887905604719764, "frac_reward_zero_std": 0.375, "grad_norm": 0.37584245204925537, "learning_rate": 4.685e-07, "loss": 0.0196, "num_tokens": 228335268.0, "reward": 0.234375, "reward_std": 0.22359731793403625, "rewards/simpleverify_reward/mean": 0.234375, "rewards/simpleverify_reward/std": 0.42527204751968384, "step": 1064 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1713.4609375, "completions/mean_terminated_length": 1389.21533203125, "completions/min_length": 548.0, "completions/min_terminated_length": 548.0, "epoch": 0.18896799520926208, "frac_reward_zero_std": 0.125, "grad_norm": 0.5722981095314026, "learning_rate": 4.68e-07, "loss": 0.0109, "num_tokens": 228569119.0, "reward": 0.4296875, "reward_std": 0.3402385711669922, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1065 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1688.2421875, "completions/mean_terminated_length": 1317.0635986328125, "completions/min_length": 477.0, "completions/min_terminated_length": 477.0, "epoch": 0.1891454299465478, "frac_reward_zero_std": 0.25, "grad_norm": 0.47598323225975037, "learning_rate": 4.675e-07, "loss": 0.0033, "num_tokens": 228799742.0, "reward": 0.3828125, "reward_std": 0.2918713688850403, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1066 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.46875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1737.078125, "completions/mean_terminated_length": 1462.7353515625, "completions/min_length": 463.0, "completions/min_terminated_length": 463.0, "epoch": 0.18932286468383347, "frac_reward_zero_std": 0.125, "grad_norm": 0.5356374382972717, "learning_rate": 4.67e-07, "loss": 0.0024, "num_tokens": 229036616.0, "reward": 0.3984375, "reward_std": 0.3726062774658203, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1067 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1723.734375, "completions/mean_terminated_length": 1409.4461669921875, "completions/min_length": 475.0, "completions/min_terminated_length": 475.0, "epoch": 0.18950029942111918, "frac_reward_zero_std": 0.25, "grad_norm": 0.5172515511512756, "learning_rate": 4.665e-07, "loss": 0.0093, "num_tokens": 229271782.0, "reward": 0.4140625, "reward_std": 0.32203567028045654, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1068 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1249.046875, "completions/mean_terminated_length": 1064.673095703125, "completions/min_length": 346.0, "completions/min_terminated_length": 346.0, "epoch": 0.18967773415840486, "frac_reward_zero_std": 0.25, "grad_norm": 0.6347262263298035, "learning_rate": 4.66e-07, "loss": -0.0092, "num_tokens": 229442524.0, "reward": 0.6171875, "reward_std": 0.2951752543449402, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1069 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1300.9296875, "completions/mean_terminated_length": 1062.1751708984375, "completions/min_length": 354.0, "completions/min_terminated_length": 354.0, "epoch": 0.18985516889569054, "frac_reward_zero_std": 0.25, "grad_norm": 0.7280873656272888, "learning_rate": 4.655e-07, "loss": 0.0009, "num_tokens": 229619907.0, "reward": 0.5546875, "reward_std": 0.31841084361076355, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1070 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2013.0, "completions/mean_length": 1266.6640625, "completions/mean_terminated_length": 1067.5, "completions/min_length": 363.0, "completions/min_terminated_length": 363.0, "epoch": 0.19003260363297625, "frac_reward_zero_std": 0.375, "grad_norm": 0.6086215376853943, "learning_rate": 4.65e-07, "loss": 0.0096, "num_tokens": 229792904.0, "reward": 0.65625, "reward_std": 0.25423622131347656, "rewards/simpleverify_reward/mean": 0.65625, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 1071 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1259.4609375, "completions/mean_terminated_length": 1068.0679931640625, "completions/min_length": 368.0, "completions/min_terminated_length": 368.0, "epoch": 0.19021003837026193, "frac_reward_zero_std": 0.25, "grad_norm": 0.6923936605453491, "learning_rate": 4.645e-07, "loss": -0.008, "num_tokens": 229964979.0, "reward": 0.5625, "reward_std": 0.29203036427497864, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1072 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1915.0, "completions/mean_length": 1388.9140625, "completions/mean_terminated_length": 1204.3699951171875, "completions/min_length": 638.0, "completions/min_terminated_length": 638.0, "epoch": 0.19038747310754764, "frac_reward_zero_std": 0.375, "grad_norm": 0.48746809363365173, "learning_rate": 4.64e-07, "loss": 0.0261, "num_tokens": 230158312.0, "reward": 0.65625, "reward_std": 0.25423625111579895, "rewards/simpleverify_reward/mean": 0.65625, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 1073 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1398.203125, "completions/mean_terminated_length": 1240.4854736328125, "completions/min_length": 564.0, "completions/min_terminated_length": 564.0, "epoch": 0.19056490784483332, "frac_reward_zero_std": 0.375, "grad_norm": 0.46528929471969604, "learning_rate": 4.635e-07, "loss": 0.0133, "num_tokens": 230352834.0, "reward": 0.6484375, "reward_std": 0.26581305265426636, "rewards/simpleverify_reward/mean": 0.6484375, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1074 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1904.0, "completions/mean_length": 1411.2421875, "completions/mean_terminated_length": 1180.925537109375, "completions/min_length": 557.0, "completions/min_terminated_length": 557.0, "epoch": 0.190742342582119, "frac_reward_zero_std": 0.25, "grad_norm": 0.5415490865707397, "learning_rate": 4.63e-07, "loss": 0.0341, "num_tokens": 230549025.0, "reward": 0.578125, "reward_std": 0.31950217485427856, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1075 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1394.28125, "completions/mean_terminated_length": 1211.239990234375, "completions/min_length": 562.0, "completions/min_terminated_length": 562.0, "epoch": 0.1909197773194047, "frac_reward_zero_std": 0.25, "grad_norm": 0.5757480263710022, "learning_rate": 4.625e-07, "loss": 0.0162, "num_tokens": 230743045.0, "reward": 0.640625, "reward_std": 0.3157500624656677, "rewards/simpleverify_reward/mean": 0.640625, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 1076 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1413.8671875, "completions/mean_terminated_length": 1135.98876953125, "completions/min_length": 579.0, "completions/min_terminated_length": 579.0, "epoch": 0.1910972120566904, "frac_reward_zero_std": 0.125, "grad_norm": 0.5788071155548096, "learning_rate": 4.62e-07, "loss": 0.0251, "num_tokens": 230933908.0, "reward": 0.5078125, "reward_std": 0.36315619945526123, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1077 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2013.0, "completions/mean_length": 1424.703125, "completions/mean_terminated_length": 1180.8043212890625, "completions/min_length": 559.0, "completions/min_terminated_length": 559.0, "epoch": 0.1912746467939761, "frac_reward_zero_std": 0.125, "grad_norm": 0.59950190782547, "learning_rate": 4.615e-07, "loss": 0.0304, "num_tokens": 231126158.0, "reward": 0.5859375, "reward_std": 0.3385361433029175, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1078 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1974.0, "completions/mean_length": 1405.5859375, "completions/mean_terminated_length": 1144.3846435546875, "completions/min_length": 621.0, "completions/min_terminated_length": 621.0, "epoch": 0.19145208153126178, "frac_reward_zero_std": 0.25, "grad_norm": 0.5702386498451233, "learning_rate": 4.61e-07, "loss": 0.0299, "num_tokens": 231315961.0, "reward": 0.5625, "reward_std": 0.32565224170684814, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1079 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1410.234375, "completions/mean_terminated_length": 1170.215087890625, "completions/min_length": 670.0, "completions/min_terminated_length": 670.0, "epoch": 0.19162951626854746, "frac_reward_zero_std": 0.125, "grad_norm": 0.5890116095542908, "learning_rate": 4.605e-07, "loss": 0.0303, "num_tokens": 231506359.0, "reward": 0.578125, "reward_std": 0.3474799394607544, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1080 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1219.828125, "completions/mean_terminated_length": 1141.9658203125, "completions/min_length": 727.0, "completions/min_terminated_length": 727.0, "epoch": 0.19180695100583317, "frac_reward_zero_std": 0.125, "grad_norm": 0.6588760018348694, "learning_rate": 4.6e-07, "loss": 0.0085, "num_tokens": 231677457.0, "reward": 0.59375, "reward_std": 0.36489027738571167, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1081 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1229.7734375, "completions/mean_terminated_length": 1152.84619140625, "completions/min_length": 650.0, "completions/min_terminated_length": 650.0, "epoch": 0.19198438574311885, "frac_reward_zero_std": 0.125, "grad_norm": 0.6078976392745972, "learning_rate": 4.595e-07, "loss": 0.017, "num_tokens": 231849828.0, "reward": 0.5625, "reward_std": 0.4025038182735443, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1082 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1998.0, "completions/mean_length": 1219.8359375, "completions/mean_terminated_length": 1149.652587890625, "completions/min_length": 693.0, "completions/min_terminated_length": 693.0, "epoch": 0.19216182048040456, "frac_reward_zero_std": 0.0, "grad_norm": 0.692095160484314, "learning_rate": 4.59e-07, "loss": -0.0071, "num_tokens": 232020927.0, "reward": 0.5703125, "reward_std": 0.4264582693576813, "rewards/simpleverify_reward/mean": 0.5703125, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1083 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1959.0, "completions/mean_length": 1234.640625, "completions/mean_terminated_length": 1142.695556640625, "completions/min_length": 686.0, "completions/min_terminated_length": 686.0, "epoch": 0.19233925521769024, "frac_reward_zero_std": 0.0, "grad_norm": 0.6708630323410034, "learning_rate": 4.585e-07, "loss": 0.0216, "num_tokens": 232193921.0, "reward": 0.5078125, "reward_std": 0.44034770131111145, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1084 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1533.1484375, "completions/mean_terminated_length": 1299.125, "completions/min_length": 668.0, "completions/min_terminated_length": 668.0, "epoch": 0.19251668995497592, "frac_reward_zero_std": 0.125, "grad_norm": 0.6143676042556763, "learning_rate": 4.58e-07, "loss": 0.0313, "num_tokens": 232400340.0, "reward": 0.390625, "reward_std": 0.400077760219574, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1085 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1994.0, "completions/mean_length": 1492.8828125, "completions/mean_terminated_length": 1240.556884765625, "completions/min_length": 605.0, "completions/min_terminated_length": 605.0, "epoch": 0.19269412469226163, "frac_reward_zero_std": 0.0, "grad_norm": 0.6499711871147156, "learning_rate": 4.575e-07, "loss": 0.009, "num_tokens": 232601605.0, "reward": 0.4609375, "reward_std": 0.401860773563385, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1086 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1972.0, "completions/mean_length": 1574.171875, "completions/mean_terminated_length": 1342.7674560546875, "completions/min_length": 629.0, "completions/min_terminated_length": 629.0, "epoch": 0.1928715594295473, "frac_reward_zero_std": 0.25, "grad_norm": 0.6195365786552429, "learning_rate": 4.57e-07, "loss": 0.0191, "num_tokens": 232813275.0, "reward": 0.3203125, "reward_std": 0.37199485301971436, "rewards/simpleverify_reward/mean": 0.3203125, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 1087 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2014.0, "completions/mean_length": 1509.7265625, "completions/mean_terminated_length": 1256.0574951171875, "completions/min_length": 691.0, "completions/min_terminated_length": 691.0, "epoch": 0.19304899416683302, "frac_reward_zero_std": 0.25, "grad_norm": 0.559878945350647, "learning_rate": 4.565e-07, "loss": 0.0133, "num_tokens": 233016696.0, "reward": 0.3828125, "reward_std": 0.3584998846054077, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1088 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1085.78125, "completions/mean_terminated_length": 995.3162841796875, "completions/min_length": 414.0, "completions/min_terminated_length": 414.0, "epoch": 0.1932264289041187, "frac_reward_zero_std": 0.25, "grad_norm": 0.6938900947570801, "learning_rate": 4.56e-07, "loss": 0.0118, "num_tokens": 233165564.0, "reward": 0.515625, "reward_std": 0.29706305265426636, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1089 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2016.0, "completions/mean_length": 1101.1875, "completions/mean_terminated_length": 984.9122924804688, "completions/min_length": 442.0, "completions/min_terminated_length": 442.0, "epoch": 0.19340386364140438, "frac_reward_zero_std": 0.25, "grad_norm": 0.603276252746582, "learning_rate": 4.5549999999999997e-07, "loss": 0.0034, "num_tokens": 233316404.0, "reward": 0.5234375, "reward_std": 0.27228015661239624, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1090 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1086.5546875, "completions/mean_terminated_length": 1005.0762939453125, "completions/min_length": 424.0, "completions/min_terminated_length": 424.0, "epoch": 0.1935812983786901, "frac_reward_zero_std": 0.125, "grad_norm": 0.7328097820281982, "learning_rate": 4.55e-07, "loss": 0.0133, "num_tokens": 233465371.0, "reward": 0.5078125, "reward_std": 0.35221683979034424, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1091 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.09375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1089.75, "completions/mean_terminated_length": 990.6206665039062, "completions/min_length": 400.0, "completions/min_terminated_length": 400.0, "epoch": 0.19375873311597577, "frac_reward_zero_std": 0.375, "grad_norm": 0.6901548504829407, "learning_rate": 4.545e-07, "loss": 0.0034, "num_tokens": 233614747.0, "reward": 0.6484375, "reward_std": 0.23722384870052338, "rewards/simpleverify_reward/mean": 0.6484375, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1092 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2014.0, "completions/mean_length": 1256.875, "completions/mean_terminated_length": 935.2088012695312, "completions/min_length": 428.0, "completions/min_terminated_length": 428.0, "epoch": 0.19393616785326148, "frac_reward_zero_std": 0.25, "grad_norm": 0.6217597126960754, "learning_rate": 4.54e-07, "loss": 0.0263, "num_tokens": 233791339.0, "reward": 0.5625, "reward_std": 0.25857165455818176, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1093 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1940.0, "completions/mean_length": 1255.96875, "completions/mean_terminated_length": 933.93408203125, "completions/min_length": 431.0, "completions/min_terminated_length": 431.0, "epoch": 0.19411360259054716, "frac_reward_zero_std": 0.375, "grad_norm": 0.5146581530570984, "learning_rate": 4.535e-07, "loss": 0.0136, "num_tokens": 233967815.0, "reward": 0.609375, "reward_std": 0.2783816456794739, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1094 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1953.0, "completions/mean_length": 1245.5546875, "completions/mean_terminated_length": 943.5591430664062, "completions/min_length": 440.0, "completions/min_terminated_length": 440.0, "epoch": 0.19429103732783284, "frac_reward_zero_std": 0.25, "grad_norm": 0.6996644139289856, "learning_rate": 4.53e-07, "loss": 0.0265, "num_tokens": 234142958.0, "reward": 0.6015625, "reward_std": 0.2603282630443573, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1095 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1289.6875, "completions/mean_terminated_length": 945.0, "completions/min_length": 435.0, "completions/min_terminated_length": 435.0, "epoch": 0.19446847206511855, "frac_reward_zero_std": 0.125, "grad_norm": 0.679388165473938, "learning_rate": 4.525e-07, "loss": 0.0237, "num_tokens": 234323750.0, "reward": 0.53125, "reward_std": 0.31971919536590576, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1096 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1294.3203125, "completions/mean_terminated_length": 1111.3883056640625, "completions/min_length": 415.0, "completions/min_terminated_length": 415.0, "epoch": 0.19464590680240423, "frac_reward_zero_std": 0.25, "grad_norm": 0.7092629075050354, "learning_rate": 4.5199999999999997e-07, "loss": -0.001, "num_tokens": 234500991.0, "reward": 0.2890625, "reward_std": 0.3034854531288147, "rewards/simpleverify_reward/mean": 0.2890625, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 1097 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2003.0, "completions/mean_length": 1322.5859375, "completions/mean_terminated_length": 1119.469970703125, "completions/min_length": 555.0, "completions/min_terminated_length": 555.0, "epoch": 0.19482334153968994, "frac_reward_zero_std": 0.25, "grad_norm": 0.671562135219574, "learning_rate": 4.515e-07, "loss": -0.0177, "num_tokens": 234681850.0, "reward": 0.3046875, "reward_std": 0.31337815523147583, "rewards/simpleverify_reward/mean": 0.3046875, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 1098 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1307.4375, "completions/mean_terminated_length": 1090.5050048828125, "completions/min_length": 464.0, "completions/min_terminated_length": 464.0, "epoch": 0.19500077627697562, "frac_reward_zero_std": 0.25, "grad_norm": 0.7398974895477295, "learning_rate": 4.51e-07, "loss": 0.0003, "num_tokens": 234860770.0, "reward": 0.3203125, "reward_std": 0.28322336077690125, "rewards/simpleverify_reward/mean": 0.3203125, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 1099 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1338.265625, "completions/mean_terminated_length": 1148.53466796875, "completions/min_length": 549.0, "completions/min_terminated_length": 549.0, "epoch": 0.1951782110142613, "frac_reward_zero_std": 0.25, "grad_norm": 0.670694887638092, "learning_rate": 4.505e-07, "loss": -0.0111, "num_tokens": 235043636.0, "reward": 0.3359375, "reward_std": 0.30917394161224365, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1100 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2019.0, "completions/mean_length": 1521.9375, "completions/mean_terminated_length": 1274.02294921875, "completions/min_length": 746.0, "completions/min_terminated_length": 746.0, "epoch": 0.195355645751547, "frac_reward_zero_std": 0.0, "grad_norm": 0.5646795034408569, "learning_rate": 4.5e-07, "loss": 0.0264, "num_tokens": 235254972.0, "reward": 0.5078125, "reward_std": 0.38317376375198364, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1101 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1995.0, "completions/mean_length": 1530.5390625, "completions/mean_terminated_length": 1209.582275390625, "completions/min_length": 738.0, "completions/min_terminated_length": 738.0, "epoch": 0.1955330804888327, "frac_reward_zero_std": 0.125, "grad_norm": 0.5721580982208252, "learning_rate": 4.495e-07, "loss": 0.0127, "num_tokens": 235467409.0, "reward": 0.3828125, "reward_std": 0.3195282220840454, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1102 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1518.859375, "completions/mean_terminated_length": 1222.0242919921875, "completions/min_length": 615.0, "completions/min_terminated_length": 615.0, "epoch": 0.1957105152261184, "frac_reward_zero_std": 0.375, "grad_norm": 0.4656810760498047, "learning_rate": 4.49e-07, "loss": 0.0012, "num_tokens": 235678351.0, "reward": 0.453125, "reward_std": 0.27928200364112854, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1103 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1522.3125, "completions/mean_terminated_length": 1246.952392578125, "completions/min_length": 705.0, "completions/min_terminated_length": 705.0, "epoch": 0.19588794996340408, "frac_reward_zero_std": 0.375, "grad_norm": 0.4617553651332855, "learning_rate": 4.4849999999999997e-07, "loss": 0.0031, "num_tokens": 235889735.0, "reward": 0.4921875, "reward_std": 0.2918713688850403, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1104 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1324.0, "completions/mean_terminated_length": 1018.3111572265625, "completions/min_length": 434.0, "completions/min_terminated_length": 434.0, "epoch": 0.19606538470068977, "frac_reward_zero_std": 0.375, "grad_norm": 0.5893492102622986, "learning_rate": 4.48e-07, "loss": 0.031, "num_tokens": 236071271.0, "reward": 0.515625, "reward_std": 0.28588032722473145, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1105 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1998.0, "completions/mean_length": 1325.8046875, "completions/mean_terminated_length": 1054.0107421875, "completions/min_length": 433.0, "completions/min_terminated_length": 433.0, "epoch": 0.19624281943797547, "frac_reward_zero_std": 0.375, "grad_norm": 0.6003866195678711, "learning_rate": 4.475e-07, "loss": 0.0157, "num_tokens": 236253038.0, "reward": 0.4921875, "reward_std": 0.28719252347946167, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1106 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1322.9296875, "completions/mean_terminated_length": 1060.670166015625, "completions/min_length": 399.0, "completions/min_terminated_length": 399.0, "epoch": 0.19642025417526116, "frac_reward_zero_std": 0.375, "grad_norm": 0.5446386337280273, "learning_rate": 4.4699999999999997e-07, "loss": 0.0195, "num_tokens": 236434437.0, "reward": 0.546875, "reward_std": 0.28258591890335083, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1107 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1337.234375, "completions/mean_terminated_length": 1069.741943359375, "completions/min_length": 458.0, "completions/min_terminated_length": 458.0, "epoch": 0.19659768891254686, "frac_reward_zero_std": 0.375, "grad_norm": 0.5126391649246216, "learning_rate": 4.465e-07, "loss": 0.0199, "num_tokens": 236617667.0, "reward": 0.5078125, "reward_std": 0.30653828382492065, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1108 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1943.0, "completions/mean_length": 1073.390625, "completions/mean_terminated_length": 761.91748046875, "completions/min_length": 384.0, "completions/min_terminated_length": 384.0, "epoch": 0.19677512364983255, "frac_reward_zero_std": 0.25, "grad_norm": 0.7146598100662231, "learning_rate": 4.46e-07, "loss": 0.01, "num_tokens": 236766485.0, "reward": 0.3671875, "reward_std": 0.25418204069137573, "rewards/simpleverify_reward/mean": 0.3671875, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1109 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1994.0, "completions/mean_length": 1079.6875, "completions/mean_terminated_length": 808.5599975585938, "completions/min_length": 365.0, "completions/min_terminated_length": 365.0, "epoch": 0.19695255838711823, "frac_reward_zero_std": 0.25, "grad_norm": 0.6025139093399048, "learning_rate": 4.455e-07, "loss": 0.0314, "num_tokens": 236916109.0, "reward": 0.3515625, "reward_std": 0.30760830640792847, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1110 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2006.0, "completions/mean_length": 1077.7890625, "completions/mean_terminated_length": 793.5858764648438, "completions/min_length": 361.0, "completions/min_terminated_length": 361.0, "epoch": 0.19712999312440393, "frac_reward_zero_std": 0.25, "grad_norm": 0.6872496604919434, "learning_rate": 4.45e-07, "loss": 0.0214, "num_tokens": 237065490.0, "reward": 0.328125, "reward_std": 0.2913650870323181, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1111 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1991.0, "completions/mean_length": 1091.625, "completions/mean_terminated_length": 798.8571166992188, "completions/min_length": 373.0, "completions/min_terminated_length": 373.0, "epoch": 0.19730742786168962, "frac_reward_zero_std": 0.375, "grad_norm": 0.5632882714271545, "learning_rate": 4.445e-07, "loss": 0.0116, "num_tokens": 237216642.0, "reward": 0.3828125, "reward_std": 0.24600867927074432, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1112 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.03125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1888.0, "completions/mean_length": 1003.96875, "completions/mean_terminated_length": 970.290283203125, "completions/min_length": 339.0, "completions/min_terminated_length": 339.0, "epoch": 0.19748486259897532, "frac_reward_zero_std": 0.25, "grad_norm": 0.6289524435997009, "learning_rate": 4.44e-07, "loss": -0.0174, "num_tokens": 237354622.0, "reward": 0.6796875, "reward_std": 0.292221337556839, "rewards/simpleverify_reward/mean": 0.6796875, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 1113 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 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": 2048.0, "completions/max_terminated_length": 1980.0, "completions/mean_length": 951.484375, "completions/mean_terminated_length": 942.8504028320312, "completions/min_length": 341.0, "completions/min_terminated_length": 341.0, "epoch": 0.197662297336261, "frac_reward_zero_std": 0.25, "grad_norm": 0.5902702808380127, "learning_rate": 4.4349999999999997e-07, "loss": -0.0027, "num_tokens": 237485884.0, "reward": 0.671875, "reward_std": 0.301489919424057, "rewards/simpleverify_reward/mean": 0.671875, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1114 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1015.5234375, "completions/mean_terminated_length": 973.5527954101562, "completions/min_length": 322.0, "completions/min_terminated_length": 322.0, "epoch": 0.1978397320735467, "frac_reward_zero_std": 0.375, "grad_norm": 0.5599170923233032, "learning_rate": 4.43e-07, "loss": -0.0078, "num_tokens": 237625343.0, "reward": 0.6640625, "reward_std": 0.2634190022945404, "rewards/simpleverify_reward/mean": 0.6640625, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1115 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1979.0, "completions/mean_length": 971.15625, "completions/mean_terminated_length": 954.0635375976562, "completions/min_length": 346.0, "completions/min_terminated_length": 346.0, "epoch": 0.1980171668108324, "frac_reward_zero_std": 0.125, "grad_norm": 0.6744949817657471, "learning_rate": 4.425e-07, "loss": 0.0079, "num_tokens": 237759123.0, "reward": 0.6171875, "reward_std": 0.31337815523147583, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1116 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1423.8203125, "completions/mean_terminated_length": 1108.058837890625, "completions/min_length": 435.0, "completions/min_terminated_length": 435.0, "epoch": 0.19819460154811808, "frac_reward_zero_std": 0.375, "grad_norm": 0.5458399653434753, "learning_rate": 4.4199999999999996e-07, "loss": 0.0043, "num_tokens": 237950972.0, "reward": 0.4609375, "reward_std": 0.20773044228553772, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1117 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1403.953125, "completions/mean_terminated_length": 1066.59521484375, "completions/min_length": 395.0, "completions/min_terminated_length": 395.0, "epoch": 0.19837203628540379, "frac_reward_zero_std": 0.375, "grad_norm": 0.5115838050842285, "learning_rate": 4.415e-07, "loss": -0.0007, "num_tokens": 238140278.0, "reward": 0.40625, "reward_std": 0.23456305265426636, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1118 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1993.0, "completions/mean_length": 1413.4453125, "completions/mean_terminated_length": 1081.0595703125, "completions/min_length": 400.0, "completions/min_terminated_length": 400.0, "epoch": 0.19854947102268947, "frac_reward_zero_std": 0.25, "grad_norm": 0.5635474324226379, "learning_rate": 4.41e-07, "loss": 0.0039, "num_tokens": 238330799.0, "reward": 0.421875, "reward_std": 0.25594252347946167, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1119 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1411.9453125, "completions/mean_terminated_length": 1055.1341552734375, "completions/min_length": 409.0, "completions/min_terminated_length": 409.0, "epoch": 0.19872690575997515, "frac_reward_zero_std": 0.375, "grad_norm": 0.5395488739013672, "learning_rate": 4.405e-07, "loss": 0.0064, "num_tokens": 238521128.0, "reward": 0.4609375, "reward_std": 0.19234731793403625, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1120 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1418.9765625, "completions/mean_terminated_length": 1242.8499755859375, "completions/min_length": 544.0, "completions/min_terminated_length": 544.0, "epoch": 0.19890434049726086, "frac_reward_zero_std": 0.125, "grad_norm": 0.6708294749259949, "learning_rate": 4.3999999999999997e-07, "loss": 0.0016, "num_tokens": 238713493.0, "reward": 0.609375, "reward_std": 0.37562090158462524, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1121 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2004.0, "completions/mean_length": 1415.359375, "completions/mean_terminated_length": 1276.781005859375, "completions/min_length": 479.0, "completions/min_terminated_length": 479.0, "epoch": 0.19908177523454654, "frac_reward_zero_std": 0.25, "grad_norm": 0.6349936723709106, "learning_rate": 4.395e-07, "loss": -0.0036, "num_tokens": 238905395.0, "reward": 0.6484375, "reward_std": 0.31747764348983765, "rewards/simpleverify_reward/mean": 0.6484375, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1122 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1400.171875, "completions/mean_terminated_length": 1235.039306640625, "completions/min_length": 521.0, "completions/min_terminated_length": 521.0, "epoch": 0.19925920997183225, "frac_reward_zero_std": 0.125, "grad_norm": 0.6833613514900208, "learning_rate": 4.39e-07, "loss": 0.0133, "num_tokens": 239095353.0, "reward": 0.5703125, "reward_std": 0.3851150870323181, "rewards/simpleverify_reward/mean": 0.5703125, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1123 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2009.0, "completions/mean_length": 1405.8671875, "completions/mean_terminated_length": 1257.6827392578125, "completions/min_length": 531.0, "completions/min_terminated_length": 531.0, "epoch": 0.19943664470911793, "frac_reward_zero_std": 0.125, "grad_norm": 0.6510134339332581, "learning_rate": 4.3849999999999996e-07, "loss": -0.0017, "num_tokens": 239286040.0, "reward": 0.5390625, "reward_std": 0.4060688316822052, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1124 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1630.03125, "completions/mean_terminated_length": 1370.7847900390625, "completions/min_length": 617.0, "completions/min_terminated_length": 617.0, "epoch": 0.1996140794464036, "frac_reward_zero_std": 0.375, "grad_norm": 0.47368910908699036, "learning_rate": 4.38e-07, "loss": 0.0408, "num_tokens": 239506076.0, "reward": 0.359375, "reward_std": 0.26802173256874084, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 1125 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1641.7265625, "completions/mean_terminated_length": 1470.18896484375, "completions/min_length": 708.0, "completions/min_terminated_length": 708.0, "epoch": 0.19979151418368932, "frac_reward_zero_std": 0.25, "grad_norm": 0.5028244256973267, "learning_rate": 4.375e-07, "loss": 0.0238, "num_tokens": 239727609.0, "reward": 0.328125, "reward_std": 0.31446951627731323, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1126 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1685.1640625, "completions/mean_terminated_length": 1444.8441162109375, "completions/min_length": 717.0, "completions/min_terminated_length": 717.0, "epoch": 0.199968948920975, "frac_reward_zero_std": 0.25, "grad_norm": 0.4450012743473053, "learning_rate": 4.3699999999999996e-07, "loss": 0.0067, "num_tokens": 239954702.0, "reward": 0.3125, "reward_std": 0.29046475887298584, "rewards/simpleverify_reward/mean": 0.3125, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 1127 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1693.609375, "completions/mean_terminated_length": 1466.4359130859375, "completions/min_length": 714.0, "completions/min_terminated_length": 714.0, "epoch": 0.2001463836582607, "frac_reward_zero_std": 0.125, "grad_norm": 0.514642596244812, "learning_rate": 4.3649999999999997e-07, "loss": 0.0102, "num_tokens": 240182876.0, "reward": 0.296875, "reward_std": 0.3455643653869629, "rewards/simpleverify_reward/mean": 0.296875, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 1128 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1988.0, "completions/mean_length": 1128.6328125, "completions/mean_terminated_length": 1006.5928955078125, "completions/min_length": 290.0, "completions/min_terminated_length": 290.0, "epoch": 0.2003238183955464, "frac_reward_zero_std": 0.125, "grad_norm": 0.6078024506568909, "learning_rate": 4.36e-07, "loss": 0.0256, "num_tokens": 240335101.0, "reward": 0.7265625, "reward_std": 0.364279180765152, "rewards/simpleverify_reward/mean": 0.7265625, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 1129 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.09375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1961.0, "completions/mean_length": 1114.578125, "completions/mean_terminated_length": 1018.0172119140625, "completions/min_length": 305.0, "completions/min_terminated_length": 305.0, "epoch": 0.20050125313283207, "frac_reward_zero_std": 0.25, "grad_norm": 0.5678122043609619, "learning_rate": 4.355e-07, "loss": 0.0242, "num_tokens": 240485527.0, "reward": 0.703125, "reward_std": 0.3472667932510376, "rewards/simpleverify_reward/mean": 0.703125, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 1130 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0546875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1104.578125, "completions/mean_terminated_length": 1050.0, "completions/min_length": 287.0, "completions/min_terminated_length": 287.0, "epoch": 0.20067868787011778, "frac_reward_zero_std": 0.125, "grad_norm": 0.626523494720459, "learning_rate": 4.3499999999999996e-07, "loss": 0.0054, "num_tokens": 240634673.0, "reward": 0.75, "reward_std": 0.3878079056739807, "rewards/simpleverify_reward/mean": 0.75, "rewards/simpleverify_reward/std": 0.434714138507843, "step": 1131 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1138.71875, "completions/mean_terminated_length": 1035.930419921875, "completions/min_length": 273.0, "completions/min_terminated_length": 273.0, "epoch": 0.20085612260740346, "frac_reward_zero_std": 0.125, "grad_norm": 0.5891764163970947, "learning_rate": 4.345e-07, "loss": 0.01, "num_tokens": 240788189.0, "reward": 0.765625, "reward_std": 0.34202155470848083, "rewards/simpleverify_reward/mean": 0.765625, "rewards/simpleverify_reward/std": 0.42527204751968384, "step": 1132 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2009.0, "completions/mean_length": 1356.875, "completions/mean_terminated_length": 1136.0, "completions/min_length": 588.0, "completions/min_terminated_length": 588.0, "epoch": 0.20103355734468917, "frac_reward_zero_std": 0.125, "grad_norm": 0.7051650285720825, "learning_rate": 4.34e-07, "loss": 0.0066, "num_tokens": 240972589.0, "reward": 0.5859375, "reward_std": 0.3677142560482025, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1133 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1969.0, "completions/mean_length": 1432.5546875, "completions/mean_terminated_length": 1200.9354248046875, "completions/min_length": 647.0, "completions/min_terminated_length": 647.0, "epoch": 0.20121099208197485, "frac_reward_zero_std": 0.125, "grad_norm": 0.6804752349853516, "learning_rate": 4.3349999999999996e-07, "loss": 0.0381, "num_tokens": 241166676.0, "reward": 0.6015625, "reward_std": 0.3692798912525177, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1134 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1369.65625, "completions/mean_terminated_length": 1124.2978515625, "completions/min_length": 608.0, "completions/min_terminated_length": 608.0, "epoch": 0.20138842681926053, "frac_reward_zero_std": 0.25, "grad_norm": 0.5849790573120117, "learning_rate": 4.3299999999999997e-07, "loss": 0.0188, "num_tokens": 241352712.0, "reward": 0.609375, "reward_std": 0.28101465106010437, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1135 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 1993.0, "completions/mean_length": 1343.890625, "completions/mean_terminated_length": 1109.1875, "completions/min_length": 616.0, "completions/min_terminated_length": 616.0, "epoch": 0.20156586155654624, "frac_reward_zero_std": 0.25, "grad_norm": 0.6455153822898865, "learning_rate": 4.325e-07, "loss": 0.0195, "num_tokens": 241535450.0, "reward": 0.59375, "reward_std": 0.3281276822090149, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1136 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2001.0, "completions/mean_length": 1457.9765625, "completions/mean_terminated_length": 1169.8255615234375, "completions/min_length": 470.0, "completions/min_terminated_length": 470.0, "epoch": 0.20174329629383192, "frac_reward_zero_std": 0.375, "grad_norm": 0.4709451198577881, "learning_rate": 4.3199999999999995e-07, "loss": 0.0073, "num_tokens": 241732871.0, "reward": 0.375, "reward_std": 0.2464885711669922, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 1137 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1398.96875, "completions/mean_terminated_length": 1124.933349609375, "completions/min_length": 429.0, "completions/min_terminated_length": 429.0, "epoch": 0.20192073103111763, "frac_reward_zero_std": 0.375, "grad_norm": 0.5403620004653931, "learning_rate": 4.3149999999999997e-07, "loss": 0.0348, "num_tokens": 241922739.0, "reward": 0.3828125, "reward_std": 0.22093653678894043, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1138 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2007.0, "completions/mean_length": 1383.65625, "completions/mean_terminated_length": 1171.3402099609375, "completions/min_length": 480.0, "completions/min_terminated_length": 480.0, "epoch": 0.2020981657684033, "frac_reward_zero_std": 0.625, "grad_norm": 0.407431960105896, "learning_rate": 4.31e-07, "loss": 0.0075, "num_tokens": 242110647.0, "reward": 0.4375, "reward_std": 0.1379890739917755, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1139 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1404.1015625, "completions/mean_terminated_length": 1171.2021484375, "completions/min_length": 524.0, "completions/min_terminated_length": 524.0, "epoch": 0.202275600505689, "frac_reward_zero_std": 0.5, "grad_norm": 0.4302029609680176, "learning_rate": 4.305e-07, "loss": 0.02, "num_tokens": 242301172.0, "reward": 0.421875, "reward_std": 0.20597384870052338, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1140 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1736.4375, "completions/mean_terminated_length": 1394.2293701171875, "completions/min_length": 596.0, "completions/min_terminated_length": 596.0, "epoch": 0.2024530352429747, "frac_reward_zero_std": 0.25, "grad_norm": 0.6214062571525574, "learning_rate": 4.2999999999999996e-07, "loss": 0.0487, "num_tokens": 242536796.0, "reward": 0.3515625, "reward_std": 0.36065438389778137, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1141 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1966.0, "completions/mean_length": 1760.953125, "completions/mean_terminated_length": 1354.7547607421875, "completions/min_length": 626.0, "completions/min_terminated_length": 626.0, "epoch": 0.20263046998026038, "frac_reward_zero_std": 0.25, "grad_norm": 0.5639274716377258, "learning_rate": 4.295e-07, "loss": 0.0581, "num_tokens": 242775558.0, "reward": 0.3203125, "reward_std": 0.30235862731933594, "rewards/simpleverify_reward/mean": 0.3203125, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 1142 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.546875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1776.0859375, "completions/mean_terminated_length": 1447.913818359375, "completions/min_length": 642.0, "completions/min_terminated_length": 642.0, "epoch": 0.2028079047175461, "frac_reward_zero_std": 0.125, "grad_norm": 0.5991226434707642, "learning_rate": 4.29e-07, "loss": 0.0513, "num_tokens": 243016257.0, "reward": 0.34375, "reward_std": 0.3752670884132385, "rewards/simpleverify_reward/mean": 0.34375, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 1143 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1745.1171875, "completions/mean_terminated_length": 1451.5538330078125, "completions/min_length": 648.0, "completions/min_terminated_length": 648.0, "epoch": 0.20298533945483177, "frac_reward_zero_std": 0.25, "grad_norm": 0.573157787322998, "learning_rate": 4.2849999999999995e-07, "loss": 0.0341, "num_tokens": 243252992.0, "reward": 0.328125, "reward_std": 0.3189171254634857, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1144 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1999.0, "completions/mean_length": 1381.703125, "completions/mean_terminated_length": 1100.3778076171875, "completions/min_length": 446.0, "completions/min_terminated_length": 446.0, "epoch": 0.20316277419211745, "frac_reward_zero_std": 0.25, "grad_norm": 0.5705953240394592, "learning_rate": 4.2799999999999997e-07, "loss": 0.0368, "num_tokens": 243442314.0, "reward": 0.3828125, "reward_std": 0.3400215804576874, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1145 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1352.5546875, "completions/mean_terminated_length": 1036.4432373046875, "completions/min_length": 384.0, "completions/min_terminated_length": 384.0, "epoch": 0.20334020892940316, "frac_reward_zero_std": 0.0, "grad_norm": 0.7186987400054932, "learning_rate": 4.275e-07, "loss": 0.0426, "num_tokens": 243627905.0, "reward": 0.3828125, "reward_std": 0.4170081913471222, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1146 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1979.0, "completions/mean_length": 1281.984375, "completions/mean_terminated_length": 1004.9148559570312, "completions/min_length": 463.0, "completions/min_terminated_length": 463.0, "epoch": 0.20351764366668884, "frac_reward_zero_std": 0.25, "grad_norm": 0.6162980794906616, "learning_rate": 4.2699999999999995e-07, "loss": -0.0019, "num_tokens": 243804463.0, "reward": 0.4296875, "reward_std": 0.31873178482055664, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1147 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1990.0, "completions/mean_length": 1342.359375, "completions/mean_terminated_length": 1087.127685546875, "completions/min_length": 406.0, "completions/min_terminated_length": 406.0, "epoch": 0.20369507840397455, "frac_reward_zero_std": 0.125, "grad_norm": 0.6231982707977295, "learning_rate": 4.2649999999999996e-07, "loss": 0.0173, "num_tokens": 243988749.0, "reward": 0.421875, "reward_std": 0.3670673370361328, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1148 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1394.7109375, "completions/mean_terminated_length": 1118.8778076171875, "completions/min_length": 461.0, "completions/min_terminated_length": 461.0, "epoch": 0.20387251314126023, "frac_reward_zero_std": 0.25, "grad_norm": 0.6753664016723633, "learning_rate": 4.26e-07, "loss": 0.0191, "num_tokens": 244177064.0, "reward": 0.46875, "reward_std": 0.3347259759902954, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1149 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1385.4375, "completions/mean_terminated_length": 1136.0860595703125, "completions/min_length": 440.0, "completions/min_terminated_length": 440.0, "epoch": 0.2040499478785459, "frac_reward_zero_std": 0.125, "grad_norm": 0.6455181241035461, "learning_rate": 4.255e-07, "loss": 0.0008, "num_tokens": 244364192.0, "reward": 0.484375, "reward_std": 0.3603322505950928, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1150 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1435.28125, "completions/mean_terminated_length": 1114.3333740234375, "completions/min_length": 397.0, "completions/min_terminated_length": 397.0, "epoch": 0.20422738261583162, "frac_reward_zero_std": 0.375, "grad_norm": 0.6123635768890381, "learning_rate": 4.2499999999999995e-07, "loss": -0.0128, "num_tokens": 244557700.0, "reward": 0.4609375, "reward_std": 0.2685280442237854, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1151 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1358.1484375, "completions/mean_terminated_length": 1088.20654296875, "completions/min_length": 418.0, "completions/min_terminated_length": 418.0, "epoch": 0.2044048173531173, "frac_reward_zero_std": 0.375, "grad_norm": 0.6570711731910706, "learning_rate": 4.2449999999999997e-07, "loss": 0.0066, "num_tokens": 244741335.0, "reward": 0.4609375, "reward_std": 0.3041732609272003, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1152 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1352.609375, "completions/mean_terminated_length": 1175.35302734375, "completions/min_length": 423.0, "completions/min_terminated_length": 423.0, "epoch": 0.204582252090403, "frac_reward_zero_std": 0.25, "grad_norm": 0.5103778839111328, "learning_rate": 4.24e-07, "loss": 0.0137, "num_tokens": 244925733.0, "reward": 0.4921875, "reward_std": 0.2768382132053375, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1153 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1389.5859375, "completions/mean_terminated_length": 1131.9456787109375, "completions/min_length": 384.0, "completions/min_terminated_length": 384.0, "epoch": 0.2047596868276887, "frac_reward_zero_std": 0.25, "grad_norm": 0.4845430254936218, "learning_rate": 4.2349999999999995e-07, "loss": 0.0148, "num_tokens": 245114864.0, "reward": 0.5, "reward_std": 0.30457115173339844, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 1154 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1400.703125, "completions/mean_terminated_length": 1137.5164794921875, "completions/min_length": 364.0, "completions/min_terminated_length": 364.0, "epoch": 0.20493712156497437, "frac_reward_zero_std": 0.25, "grad_norm": 0.45717376470565796, "learning_rate": 4.2299999999999996e-07, "loss": 0.0157, "num_tokens": 245305418.0, "reward": 0.4609375, "reward_std": 0.2541820704936981, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1155 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1384.859375, "completions/mean_terminated_length": 1145.0, "completions/min_length": 386.0, "completions/min_terminated_length": 386.0, "epoch": 0.20511455630226008, "frac_reward_zero_std": 0.25, "grad_norm": 0.48311397433280945, "learning_rate": 4.225e-07, "loss": 0.0264, "num_tokens": 245493944.0, "reward": 0.453125, "reward_std": 0.26780858635902405, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1156 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1994.0, "completions/mean_length": 1261.5390625, "completions/mean_terminated_length": 953.7935180664062, "completions/min_length": 351.0, "completions/min_terminated_length": 351.0, "epoch": 0.20529199103954576, "frac_reward_zero_std": 0.5, "grad_norm": 0.4708237946033478, "learning_rate": 4.2199999999999994e-07, "loss": 0.0126, "num_tokens": 245669389.0, "reward": 0.3828125, "reward_std": 0.22937136888504028, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1157 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1265.578125, "completions/mean_terminated_length": 935.2222290039062, "completions/min_length": 351.0, "completions/min_terminated_length": 351.0, "epoch": 0.20546942577683147, "frac_reward_zero_std": 0.375, "grad_norm": 0.5678210854530334, "learning_rate": 4.2149999999999996e-07, "loss": 0.0027, "num_tokens": 245845351.0, "reward": 0.4140625, "reward_std": 0.24472814798355103, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1158 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1252.203125, "completions/mean_terminated_length": 928.6373901367188, "completions/min_length": 350.0, "completions/min_terminated_length": 350.0, "epoch": 0.20564686051411715, "frac_reward_zero_std": 0.5, "grad_norm": 0.46063563227653503, "learning_rate": 4.2099999999999997e-07, "loss": 0.009, "num_tokens": 246019601.0, "reward": 0.375, "reward_std": 0.20253878831863403, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 1159 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1266.7578125, "completions/mean_terminated_length": 898.586181640625, "completions/min_length": 342.0, "completions/min_terminated_length": 342.0, "epoch": 0.20582429525140283, "frac_reward_zero_std": 0.5, "grad_norm": 0.5462067127227783, "learning_rate": 4.205e-07, "loss": 0.0034, "num_tokens": 246195714.0, "reward": 0.40625, "reward_std": 0.2130298614501953, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1160 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1946.0, "completions/mean_length": 1154.9765625, "completions/mean_terminated_length": 1036.43359375, "completions/min_length": 484.0, "completions/min_terminated_length": 484.0, "epoch": 0.20600172998868854, "frac_reward_zero_std": 0.5, "grad_norm": 0.4711664617061615, "learning_rate": 4.1999999999999995e-07, "loss": 0.0018, "num_tokens": 246354079.0, "reward": 0.6640625, "reward_std": 0.19894562661647797, "rewards/simpleverify_reward/mean": 0.6640625, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1161 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1191.09375, "completions/mean_terminated_length": 1085.859619140625, "completions/min_length": 501.0, "completions/min_terminated_length": 501.0, "epoch": 0.20617916472597422, "frac_reward_zero_std": 0.25, "grad_norm": 0.5853299498558044, "learning_rate": 4.1949999999999996e-07, "loss": -0.0126, "num_tokens": 246517067.0, "reward": 0.6875, "reward_std": 0.27132564783096313, "rewards/simpleverify_reward/mean": 0.6875, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 1162 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1217.3671875, "completions/mean_terminated_length": 1090.1531982421875, "completions/min_length": 500.0, "completions/min_terminated_length": 500.0, "epoch": 0.20635659946325993, "frac_reward_zero_std": 0.125, "grad_norm": 0.6863648295402527, "learning_rate": 4.19e-07, "loss": 0.0118, "num_tokens": 246683418.0, "reward": 0.59375, "reward_std": 0.33361247181892395, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1163 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1969.0, "completions/mean_length": 1162.1640625, "completions/mean_terminated_length": 1035.6160888671875, "completions/min_length": 452.0, "completions/min_terminated_length": 452.0, "epoch": 0.2065340342005456, "frac_reward_zero_std": 0.25, "grad_norm": 0.5901791453361511, "learning_rate": 4.1849999999999994e-07, "loss": 0.0106, "num_tokens": 246842703.0, "reward": 0.5859375, "reward_std": 0.33754998445510864, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1164 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1596.734375, "completions/mean_terminated_length": 1426.9031982421875, "completions/min_length": 621.0, "completions/min_terminated_length": 621.0, "epoch": 0.2067114689378313, "frac_reward_zero_std": 0.125, "grad_norm": 0.5751940011978149, "learning_rate": 4.1799999999999996e-07, "loss": 0.0295, "num_tokens": 247058589.0, "reward": 0.390625, "reward_std": 0.40862101316452026, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1165 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1590.015625, "completions/mean_terminated_length": 1389.3258056640625, "completions/min_length": 566.0, "completions/min_terminated_length": 566.0, "epoch": 0.206888903675117, "frac_reward_zero_std": 0.125, "grad_norm": 0.5764418840408325, "learning_rate": 4.1749999999999997e-07, "loss": 0.0205, "num_tokens": 247273615.0, "reward": 0.4296875, "reward_std": 0.40731915831565857, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1166 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1554.359375, "completions/mean_terminated_length": 1353.6484375, "completions/min_length": 584.0, "completions/min_terminated_length": 584.0, "epoch": 0.20706633841240268, "frac_reward_zero_std": 0.125, "grad_norm": 0.568045973777771, "learning_rate": 4.17e-07, "loss": 0.0134, "num_tokens": 247484077.0, "reward": 0.421875, "reward_std": 0.4033816456794739, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1167 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2008.0, "completions/mean_length": 1528.4296875, "completions/mean_terminated_length": 1362.38134765625, "completions/min_length": 484.0, "completions/min_terminated_length": 484.0, "epoch": 0.2072437731496884, "frac_reward_zero_std": 0.125, "grad_norm": 0.5920391082763672, "learning_rate": 4.1649999999999995e-07, "loss": 0.0067, "num_tokens": 247691220.0, "reward": 0.3984375, "reward_std": 0.4009559452533722, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1168 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1218.046875, "completions/mean_terminated_length": 996.17822265625, "completions/min_length": 416.0, "completions/min_terminated_length": 416.0, "epoch": 0.20742120788697407, "frac_reward_zero_std": 0.375, "grad_norm": 0.7261437177658081, "learning_rate": 4.1599999999999997e-07, "loss": 0.0247, "num_tokens": 247859610.0, "reward": 0.609375, "reward_std": 0.2638174891471863, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1169 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1929.0, "completions/mean_length": 1258.703125, "completions/mean_terminated_length": 973.2127075195312, "completions/min_length": 483.0, "completions/min_terminated_length": 483.0, "epoch": 0.20759864262425975, "frac_reward_zero_std": 0.375, "grad_norm": 0.6072814464569092, "learning_rate": 4.155e-07, "loss": 0.0216, "num_tokens": 248033204.0, "reward": 0.5546875, "reward_std": 0.2568970322608948, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1170 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1932.0, "completions/mean_length": 1251.046875, "completions/mean_terminated_length": 1027.9000244140625, "completions/min_length": 414.0, "completions/min_terminated_length": 414.0, "epoch": 0.20777607736154546, "frac_reward_zero_std": 0.375, "grad_norm": 0.5311263799667358, "learning_rate": 4.1499999999999994e-07, "loss": 0.0379, "num_tokens": 248205818.0, "reward": 0.546875, "reward_std": 0.28716087341308594, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1171 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1985.0, "completions/mean_length": 1226.6328125, "completions/mean_terminated_length": 941.3158569335938, "completions/min_length": 430.0, "completions/min_terminated_length": 430.0, "epoch": 0.20795351209883114, "frac_reward_zero_std": 0.375, "grad_norm": 0.6682702898979187, "learning_rate": 4.1449999999999996e-07, "loss": 0.0397, "num_tokens": 248375307.0, "reward": 0.515625, "reward_std": 0.2656276822090149, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1172 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1393.203125, "completions/mean_terminated_length": 1146.774169921875, "completions/min_length": 449.0, "completions/min_terminated_length": 449.0, "epoch": 0.20813094683611685, "frac_reward_zero_std": 0.25, "grad_norm": 0.5924772620201111, "learning_rate": 4.14e-07, "loss": 0.0072, "num_tokens": 248567221.0, "reward": 0.4296875, "reward_std": 0.3162299692630768, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1173 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1960.0, "completions/mean_length": 1410.03125, "completions/mean_terminated_length": 1150.637451171875, "completions/min_length": 587.0, "completions/min_terminated_length": 587.0, "epoch": 0.20830838157340253, "frac_reward_zero_std": 0.25, "grad_norm": 0.5483768582344055, "learning_rate": 4.1349999999999994e-07, "loss": 0.0135, "num_tokens": 248761289.0, "reward": 0.3828125, "reward_std": 0.28982165455818176, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1174 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1443.203125, "completions/mean_terminated_length": 1137.2470703125, "completions/min_length": 512.0, "completions/min_terminated_length": 512.0, "epoch": 0.20848581631068822, "frac_reward_zero_std": 0.125, "grad_norm": 0.7255544066429138, "learning_rate": 4.1299999999999995e-07, "loss": 0.018, "num_tokens": 248959603.0, "reward": 0.3984375, "reward_std": 0.3900166153907776, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1175 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1356.3203125, "completions/mean_terminated_length": 1125.760498046875, "completions/min_length": 490.0, "completions/min_terminated_length": 490.0, "epoch": 0.20866325104797392, "frac_reward_zero_std": 0.25, "grad_norm": 0.6288854479789734, "learning_rate": 4.1249999999999997e-07, "loss": 0.0079, "num_tokens": 249146796.0, "reward": 0.4140625, "reward_std": 0.3193970322608948, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1176 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1427.09375, "completions/mean_terminated_length": 1134.4827880859375, "completions/min_length": 381.0, "completions/min_terminated_length": 381.0, "epoch": 0.2088406857852596, "frac_reward_zero_std": 0.125, "grad_norm": 0.7646661996841431, "learning_rate": 4.12e-07, "loss": 0.0411, "num_tokens": 249341560.0, "reward": 0.3359375, "reward_std": 0.38431864976882935, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1177 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1431.109375, "completions/mean_terminated_length": 1170.64453125, "completions/min_length": 351.0, "completions/min_terminated_length": 351.0, "epoch": 0.20901812052254531, "frac_reward_zero_std": 0.125, "grad_norm": 0.7023695707321167, "learning_rate": 4.1149999999999995e-07, "loss": 0.0439, "num_tokens": 249536838.0, "reward": 0.3203125, "reward_std": 0.3776125907897949, "rewards/simpleverify_reward/mean": 0.3203125, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 1178 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2023.0, "completions/mean_length": 1419.7421875, "completions/mean_terminated_length": 1183.301025390625, "completions/min_length": 349.0, "completions/min_terminated_length": 349.0, "epoch": 0.209195555259831, "frac_reward_zero_std": 0.125, "grad_norm": 0.6820915937423706, "learning_rate": 4.1099999999999996e-07, "loss": 0.02, "num_tokens": 249730661.0, "reward": 0.3359375, "reward_std": 0.3705565631389618, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1179 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1423.2421875, "completions/mean_terminated_length": 1188.1182861328125, "completions/min_length": 332.0, "completions/min_terminated_length": 332.0, "epoch": 0.20937298999711668, "frac_reward_zero_std": 0.125, "grad_norm": 0.6987996697425842, "learning_rate": 4.105e-07, "loss": 0.0415, "num_tokens": 249924932.0, "reward": 0.40625, "reward_std": 0.3893830180168152, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1180 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1977.0, "completions/mean_length": 1239.3671875, "completions/mean_terminated_length": 1043.0970458984375, "completions/min_length": 212.0, "completions/min_terminated_length": 212.0, "epoch": 0.20955042473440239, "frac_reward_zero_std": 0.375, "grad_norm": 0.514895498752594, "learning_rate": 4.0999999999999994e-07, "loss": 0.0129, "num_tokens": 250094387.0, "reward": 0.390625, "reward_std": 0.29738396406173706, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1181 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1291.9375, "completions/mean_terminated_length": 1070.464599609375, "completions/min_length": 217.0, "completions/min_terminated_length": 217.0, "epoch": 0.20972785947168807, "frac_reward_zero_std": 0.375, "grad_norm": 0.4940984845161438, "learning_rate": 4.0949999999999995e-07, "loss": 0.0092, "num_tokens": 250270571.0, "reward": 0.3828125, "reward_std": 0.2685280442237854, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1182 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1220.8515625, "completions/mean_terminated_length": 1029.97119140625, "completions/min_length": 203.0, "completions/min_terminated_length": 203.0, "epoch": 0.20990529420897377, "frac_reward_zero_std": 0.375, "grad_norm": 0.540010392665863, "learning_rate": 4.0899999999999997e-07, "loss": -0.0095, "num_tokens": 250437656.0, "reward": 0.4296875, "reward_std": 0.2790191173553467, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1183 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1266.5859375, "completions/mean_terminated_length": 1095.4190673828125, "completions/min_length": 245.0, "completions/min_terminated_length": 245.0, "epoch": 0.21008272894625946, "frac_reward_zero_std": 0.375, "grad_norm": 0.5316308736801147, "learning_rate": 4.0849999999999993e-07, "loss": 0.0251, "num_tokens": 250610595.0, "reward": 0.375, "reward_std": 0.26664024591445923, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 1184 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1444.6484375, "completions/mean_terminated_length": 1235.063232421875, "completions/min_length": 541.0, "completions/min_terminated_length": 541.0, "epoch": 0.21026016368354514, "frac_reward_zero_std": 0.375, "grad_norm": 0.5037848949432373, "learning_rate": 4.0799999999999995e-07, "loss": 0.0191, "num_tokens": 250806006.0, "reward": 0.5859375, "reward_std": 0.26350483298301697, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1185 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1996.0, "completions/mean_length": 1464.9921875, "completions/mean_terminated_length": 1209.516845703125, "completions/min_length": 516.0, "completions/min_terminated_length": 516.0, "epoch": 0.21043759842083085, "frac_reward_zero_std": 0.5, "grad_norm": 0.4340427815914154, "learning_rate": 4.0749999999999996e-07, "loss": 0.0289, "num_tokens": 251004021.0, "reward": 0.5234375, "reward_std": 0.2427906095981598, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1186 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1970.0, "completions/mean_length": 1423.671875, "completions/mean_terminated_length": 1179.36962890625, "completions/min_length": 528.0, "completions/min_terminated_length": 528.0, "epoch": 0.21061503315811653, "frac_reward_zero_std": 0.5, "grad_norm": 0.46559152007102966, "learning_rate": 4.07e-07, "loss": 0.0188, "num_tokens": 251196747.0, "reward": 0.53125, "reward_std": 0.22466084361076355, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1187 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2004.0, "completions/mean_length": 1432.875, "completions/mean_terminated_length": 1219.2000732421875, "completions/min_length": 463.0, "completions/min_terminated_length": 463.0, "epoch": 0.21079246789540224, "frac_reward_zero_std": 0.375, "grad_norm": 0.5643739700317383, "learning_rate": 4.0649999999999994e-07, "loss": 0.0092, "num_tokens": 251390651.0, "reward": 0.546875, "reward_std": 0.24478615820407867, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1188 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2019.0, "completions/mean_length": 1038.921875, "completions/mean_terminated_length": 781.7059326171875, "completions/min_length": 253.0, "completions/min_terminated_length": 253.0, "epoch": 0.21096990263268792, "frac_reward_zero_std": 0.5, "grad_norm": 0.8087849617004395, "learning_rate": 4.06e-07, "loss": 0.0012, "num_tokens": 251534449.0, "reward": 0.6171875, "reward_std": 0.17824089527130127, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1189 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1997.0, "completions/mean_length": 1047.921875, "completions/mean_terminated_length": 767.8999633789062, "completions/min_length": 275.0, "completions/min_terminated_length": 275.0, "epoch": 0.2111473373699736, "frac_reward_zero_std": 0.5, "grad_norm": 0.5676496624946594, "learning_rate": 4.055e-07, "loss": 0.0072, "num_tokens": 251679399.0, "reward": 0.609375, "reward_std": 0.18968652188777924, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1190 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2021.0, "completions/mean_length": 1045.640625, "completions/mean_terminated_length": 826.0762329101562, "completions/min_length": 267.0, "completions/min_terminated_length": 267.0, "epoch": 0.2113247721072593, "frac_reward_zero_std": 0.5, "grad_norm": 0.604439914226532, "learning_rate": 4.05e-07, "loss": 0.0036, "num_tokens": 251824057.0, "reward": 0.609375, "reward_std": 0.1441391110420227, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1191 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1995.0, "completions/mean_length": 1044.5, "completions/mean_terminated_length": 824.6857299804688, "completions/min_length": 269.0, "completions/min_terminated_length": 269.0, "epoch": 0.211502206844545, "frac_reward_zero_std": 0.625, "grad_norm": 0.5432741641998291, "learning_rate": 4.045e-07, "loss": 0.0036, "num_tokens": 251968569.0, "reward": 0.609375, "reward_std": 0.10519562661647797, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1192 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2009.0, "completions/mean_length": 1433.4921875, "completions/mean_terminated_length": 1154.1705322265625, "completions/min_length": 597.0, "completions/min_terminated_length": 597.0, "epoch": 0.2116796415818307, "frac_reward_zero_std": 0.25, "grad_norm": 0.5126451849937439, "learning_rate": 4.04e-07, "loss": 0.0115, "num_tokens": 252163192.0, "reward": 0.5078125, "reward_std": 0.3248779773712158, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1193 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1435.65625, "completions/mean_terminated_length": 1214.170166015625, "completions/min_length": 691.0, "completions/min_terminated_length": 691.0, "epoch": 0.21185707631911638, "frac_reward_zero_std": 0.125, "grad_norm": 0.6448184847831726, "learning_rate": 4.0350000000000003e-07, "loss": 0.0227, "num_tokens": 252358092.0, "reward": 0.5546875, "reward_std": 0.3690628409385681, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1194 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1468.2265625, "completions/mean_terminated_length": 1223.433349609375, "completions/min_length": 582.0, "completions/min_terminated_length": 582.0, "epoch": 0.21203451105640206, "frac_reward_zero_std": 0.25, "grad_norm": 0.566381573677063, "learning_rate": 4.03e-07, "loss": 0.0246, "num_tokens": 252557161.0, "reward": 0.5390625, "reward_std": 0.3466293513774872, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1195 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2023.0, "completions/mean_length": 1435.65625, "completions/mean_terminated_length": 1231.541748046875, "completions/min_length": 638.0, "completions/min_terminated_length": 638.0, "epoch": 0.21221194579368777, "frac_reward_zero_std": 0.125, "grad_norm": 0.6075947284698486, "learning_rate": 4.025e-07, "loss": 0.0193, "num_tokens": 252752061.0, "reward": 0.578125, "reward_std": 0.36318784952163696, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1196 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1987.0, "completions/mean_length": 1144.625, "completions/mean_terminated_length": 914.3529663085938, "completions/min_length": 324.0, "completions/min_terminated_length": 324.0, "epoch": 0.21238938053097345, "frac_reward_zero_std": 0.25, "grad_norm": 0.5224564671516418, "learning_rate": 4.02e-07, "loss": 0.0219, "num_tokens": 252909597.0, "reward": 0.328125, "reward_std": 0.2909129858016968, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1197 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1943.0, "completions/mean_length": 1156.515625, "completions/mean_terminated_length": 871.6082153320312, "completions/min_length": 327.0, "completions/min_terminated_length": 327.0, "epoch": 0.21256681526825916, "frac_reward_zero_std": 0.375, "grad_norm": 0.4729352593421936, "learning_rate": 4.015e-07, "loss": 0.0037, "num_tokens": 253068655.0, "reward": 0.3359375, "reward_std": 0.2442798763513565, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1198 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1879.0, "completions/mean_length": 1133.5390625, "completions/mean_terminated_length": 900.4412231445312, "completions/min_length": 299.0, "completions/min_terminated_length": 299.0, "epoch": 0.21274425000554484, "frac_reward_zero_std": 0.25, "grad_norm": 0.5524249076843262, "learning_rate": 4.01e-07, "loss": -0.0005, "num_tokens": 253224772.0, "reward": 0.359375, "reward_std": 0.27132561802864075, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 1199 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1980.0, "completions/mean_length": 1153.7265625, "completions/mean_terminated_length": 925.7745361328125, "completions/min_length": 317.0, "completions/min_terminated_length": 317.0, "epoch": 0.21292168474283052, "frac_reward_zero_std": 0.125, "grad_norm": 0.664505660533905, "learning_rate": 4.005e-07, "loss": 0.0246, "num_tokens": 253383473.0, "reward": 0.3671875, "reward_std": 0.29312556982040405, "rewards/simpleverify_reward/mean": 0.3671875, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1200 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1998.0, "completions/mean_length": 1292.0859375, "completions/mean_terminated_length": 960.8427124023438, "completions/min_length": 502.0, "completions/min_terminated_length": 502.0, "epoch": 0.21309911948011623, "frac_reward_zero_std": 0.5, "grad_norm": 0.4892268478870392, "learning_rate": 4e-07, "loss": 0.0173, "num_tokens": 253560236.0, "reward": 0.625, "reward_std": 0.18954971432685852, "rewards/simpleverify_reward/mean": 0.625, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 1201 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1278.8671875, "completions/mean_terminated_length": 1022.4896240234375, "completions/min_length": 473.0, "completions/min_terminated_length": 473.0, "epoch": 0.2132765542174019, "frac_reward_zero_std": 0.375, "grad_norm": 0.550573468208313, "learning_rate": 3.995e-07, "loss": 0.026, "num_tokens": 253735307.0, "reward": 0.6796875, "reward_std": 0.22753483057022095, "rewards/simpleverify_reward/mean": 0.6796875, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 1202 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1927.0, "completions/mean_length": 1263.9140625, "completions/mean_terminated_length": 991.5474243164062, "completions/min_length": 495.0, "completions/min_terminated_length": 495.0, "epoch": 0.2134539889546876, "frac_reward_zero_std": 0.625, "grad_norm": 0.40699246525764465, "learning_rate": 3.99e-07, "loss": 0.023, "num_tokens": 253908464.0, "reward": 0.6875, "reward_std": 0.14699089527130127, "rewards/simpleverify_reward/mean": 0.6875, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 1203 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1967.0, "completions/mean_length": 1282.5859375, "completions/mean_terminated_length": 994.52685546875, "completions/min_length": 489.0, "completions/min_terminated_length": 489.0, "epoch": 0.2136314236919733, "frac_reward_zero_std": 0.5, "grad_norm": 0.40226835012435913, "learning_rate": 3.9850000000000003e-07, "loss": 0.034, "num_tokens": 254084011.0, "reward": 0.6796875, "reward_std": 0.17824089527130127, "rewards/simpleverify_reward/mean": 0.6796875, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 1204 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2002.0, "completions/mean_length": 1228.2734375, "completions/mean_terminated_length": 1039.1058349609375, "completions/min_length": 430.0, "completions/min_terminated_length": 430.0, "epoch": 0.21380885842925898, "frac_reward_zero_std": 0.5, "grad_norm": 0.4937935769557953, "learning_rate": 3.98e-07, "loss": 0.0001, "num_tokens": 254254078.0, "reward": 0.609375, "reward_std": 0.2066391110420227, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1205 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1961.0, "completions/mean_length": 1231.109375, "completions/mean_terminated_length": 991.8181762695312, "completions/min_length": 485.0, "completions/min_terminated_length": 485.0, "epoch": 0.2139862931665447, "frac_reward_zero_std": 0.375, "grad_norm": 0.60837721824646, "learning_rate": 3.975e-07, "loss": 0.0077, "num_tokens": 254424508.0, "reward": 0.5859375, "reward_std": 0.25591087341308594, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1206 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1246.3125, "completions/mean_terminated_length": 1021.8399658203125, "completions/min_length": 440.0, "completions/min_terminated_length": 440.0, "epoch": 0.21416372790383037, "frac_reward_zero_std": 0.375, "grad_norm": 0.5783274173736572, "learning_rate": 3.97e-07, "loss": 0.0255, "num_tokens": 254596884.0, "reward": 0.59375, "reward_std": 0.262323796749115, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1207 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1190.6875, "completions/mean_terminated_length": 950.6399536132812, "completions/min_length": 457.0, "completions/min_terminated_length": 457.0, "epoch": 0.21434116264111605, "frac_reward_zero_std": 0.375, "grad_norm": 0.5683014392852783, "learning_rate": 3.965e-07, "loss": 0.0182, "num_tokens": 254762140.0, "reward": 0.546875, "reward_std": 0.2497924566268921, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1208 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1968.0, "completions/mean_length": 1286.3359375, "completions/mean_terminated_length": 1128.2547607421875, "completions/min_length": 425.0, "completions/min_terminated_length": 425.0, "epoch": 0.21451859737840176, "frac_reward_zero_std": 0.125, "grad_norm": 0.6758663058280945, "learning_rate": 3.96e-07, "loss": 0.0211, "num_tokens": 254936151.0, "reward": 0.5625, "reward_std": 0.3746018409729004, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1209 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1278.90625, "completions/mean_terminated_length": 1136.4814453125, "completions/min_length": 417.0, "completions/min_terminated_length": 417.0, "epoch": 0.21469603211568744, "frac_reward_zero_std": 0.125, "grad_norm": 0.6176310181617737, "learning_rate": 3.955e-07, "loss": 0.0034, "num_tokens": 255109211.0, "reward": 0.6484375, "reward_std": 0.34902340173721313, "rewards/simpleverify_reward/mean": 0.6484375, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1210 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2019.0, "completions/mean_length": 1278.4453125, "completions/mean_terminated_length": 1152.5181884765625, "completions/min_length": 406.0, "completions/min_terminated_length": 406.0, "epoch": 0.21487346685297315, "frac_reward_zero_std": 0.25, "grad_norm": 0.5558910369873047, "learning_rate": 3.95e-07, "loss": 0.0124, "num_tokens": 255282212.0, "reward": 0.6796875, "reward_std": 0.29972386360168457, "rewards/simpleverify_reward/mean": 0.6796875, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 1211 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1279.5546875, "completions/mean_terminated_length": 1111.2286376953125, "completions/min_length": 449.0, "completions/min_terminated_length": 449.0, "epoch": 0.21505090159025883, "frac_reward_zero_std": 0.25, "grad_norm": 0.5683709383010864, "learning_rate": 3.945e-07, "loss": 0.0194, "num_tokens": 255455355.0, "reward": 0.6015625, "reward_std": 0.3587982654571533, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1212 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1579.265625, "completions/mean_terminated_length": 1416.442138671875, "completions/min_length": 893.0, "completions/min_terminated_length": 893.0, "epoch": 0.2152283363275445, "frac_reward_zero_std": 0.125, "grad_norm": 0.5426621437072754, "learning_rate": 3.94e-07, "loss": 0.0083, "num_tokens": 255670141.0, "reward": 0.3359375, "reward_std": 0.3721316456794739, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1213 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1559.1015625, "completions/mean_terminated_length": 1428.4058837890625, "completions/min_length": 914.0, "completions/min_terminated_length": 914.0, "epoch": 0.21540577106483022, "frac_reward_zero_std": 0.125, "grad_norm": 0.52616947889328, "learning_rate": 3.935e-07, "loss": 0.0246, "num_tokens": 255882346.0, "reward": 0.4609375, "reward_std": 0.4252040982246399, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1214 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2009.0, "completions/mean_length": 1638.2109375, "completions/mean_terminated_length": 1458.6405029296875, "completions/min_length": 892.0, "completions/min_terminated_length": 892.0, "epoch": 0.2155832058021159, "frac_reward_zero_std": 0.25, "grad_norm": 0.4572106897830963, "learning_rate": 3.93e-07, "loss": 0.0098, "num_tokens": 256104677.0, "reward": 0.296875, "reward_std": 0.34838029742240906, "rewards/simpleverify_reward/mean": 0.296875, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 1215 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2014.0, "completions/mean_length": 1607.1796875, "completions/mean_terminated_length": 1454.052734375, "completions/min_length": 870.0, "completions/min_terminated_length": 870.0, "epoch": 0.2157606405394016, "frac_reward_zero_std": 0.125, "grad_norm": 0.5855644345283508, "learning_rate": 3.925e-07, "loss": 0.0195, "num_tokens": 256323036.0, "reward": 0.390625, "reward_std": 0.41751062870025635, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1216 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2016.0, "completions/mean_length": 1410.921875, "completions/mean_terminated_length": 1263.9039306640625, "completions/min_length": 630.0, "completions/min_terminated_length": 630.0, "epoch": 0.2159380752766873, "frac_reward_zero_std": 0.5, "grad_norm": 0.4750804007053375, "learning_rate": 3.92e-07, "loss": 0.0281, "num_tokens": 256514402.0, "reward": 0.578125, "reward_std": 0.21076759696006775, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1217 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1437.1953125, "completions/mean_terminated_length": 1288.9417724609375, "completions/min_length": 663.0, "completions/min_terminated_length": 663.0, "epoch": 0.21611551001397297, "frac_reward_zero_std": 0.375, "grad_norm": 0.508647620677948, "learning_rate": 3.915e-07, "loss": 0.003, "num_tokens": 256709131.0, "reward": 0.5546875, "reward_std": 0.22686956822872162, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1218 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1401.703125, "completions/mean_terminated_length": 1252.5577392578125, "completions/min_length": 675.0, "completions/min_terminated_length": 675.0, "epoch": 0.21629294475125868, "frac_reward_zero_std": 0.375, "grad_norm": 0.49016737937927246, "learning_rate": 3.91e-07, "loss": 0.0089, "num_tokens": 256899317.0, "reward": 0.59375, "reward_std": 0.20597384870052338, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1219 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1411.6796875, "completions/mean_terminated_length": 1272.2952880859375, "completions/min_length": 598.0, "completions/min_terminated_length": 598.0, "epoch": 0.21647037948854436, "frac_reward_zero_std": 0.375, "grad_norm": 0.4481828808784485, "learning_rate": 3.905e-07, "loss": 0.0188, "num_tokens": 257090780.0, "reward": 0.53125, "reward_std": 0.24478614330291748, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1220 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1946.0, "completions/mean_length": 1367.6875, "completions/mean_terminated_length": 902.2105102539062, "completions/min_length": 443.0, "completions/min_terminated_length": 443.0, "epoch": 0.21664781422583007, "frac_reward_zero_std": 0.625, "grad_norm": 0.45308998227119446, "learning_rate": 3.8999999999999997e-07, "loss": -0.0051, "num_tokens": 257280868.0, "reward": 0.484375, "reward_std": 0.14789125323295593, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1221 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1963.0, "completions/mean_length": 1351.8046875, "completions/mean_terminated_length": 974.349365234375, "completions/min_length": 411.0, "completions/min_terminated_length": 411.0, "epoch": 0.21682524896311575, "frac_reward_zero_std": 0.375, "grad_norm": 0.5251091122627258, "learning_rate": 3.895e-07, "loss": 0.009, "num_tokens": 257468923.0, "reward": 0.5234375, "reward_std": 0.2343776822090149, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1222 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2022.0, "completions/mean_length": 1338.375, "completions/mean_terminated_length": 926.6173095703125, "completions/min_length": 407.0, "completions/min_terminated_length": 407.0, "epoch": 0.21700268370040143, "frac_reward_zero_std": 0.5, "grad_norm": 0.5631048083305359, "learning_rate": 3.89e-07, "loss": 0.0049, "num_tokens": 257655259.0, "reward": 0.4609375, "reward_std": 0.1687908172607422, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1223 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1356.4765625, "completions/mean_terminated_length": 913.1923217773438, "completions/min_length": 434.0, "completions/min_terminated_length": 434.0, "epoch": 0.21718011843768714, "frac_reward_zero_std": 0.5, "grad_norm": 0.5701531767845154, "learning_rate": 3.885e-07, "loss": -0.005, "num_tokens": 257843912.0, "reward": 0.4453125, "reward_std": 0.17824089527130127, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1224 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1999.0, "completions/mean_length": 1471.8671875, "completions/mean_terminated_length": 858.5645141601562, "completions/min_length": 223.0, "completions/min_terminated_length": 223.0, "epoch": 0.21735755317497282, "frac_reward_zero_std": 0.625, "grad_norm": 0.5712953805923462, "learning_rate": 3.88e-07, "loss": -0.0025, "num_tokens": 258047975.0, "reward": 0.390625, "reward_std": 0.11840169876813889, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1225 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1453.8203125, "completions/mean_terminated_length": 821.3064575195312, "completions/min_length": 227.0, "completions/min_terminated_length": 227.0, "epoch": 0.21753498791225853, "frac_reward_zero_std": 0.625, "grad_norm": 0.5842037200927734, "learning_rate": 3.875e-07, "loss": 0.0342, "num_tokens": 258249728.0, "reward": 0.359375, "reward_std": 0.14347384870052338, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 1226 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1854.0, "completions/mean_length": 1457.765625, "completions/mean_terminated_length": 848.793701171875, "completions/min_length": 256.0, "completions/min_terminated_length": 256.0, "epoch": 0.2177124226495442, "frac_reward_zero_std": 0.5, "grad_norm": 0.5849073529243469, "learning_rate": 3.87e-07, "loss": 0.0213, "num_tokens": 258451986.0, "reward": 0.375, "reward_std": 0.18683473765850067, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 1227 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1927.0, "completions/mean_length": 1452.453125, "completions/mean_terminated_length": 838.0000610351562, "completions/min_length": 238.0, "completions/min_terminated_length": 238.0, "epoch": 0.2178898573868299, "frac_reward_zero_std": 0.625, "grad_norm": 0.727906346321106, "learning_rate": 3.8649999999999997e-07, "loss": 0.0107, "num_tokens": 258653564.0, "reward": 0.421875, "reward_std": 0.12704971432685852, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1228 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1173.2578125, "completions/mean_terminated_length": 1020.77978515625, "completions/min_length": 231.0, "completions/min_terminated_length": 231.0, "epoch": 0.2180672921241156, "frac_reward_zero_std": 0.0, "grad_norm": 0.9016913771629333, "learning_rate": 3.86e-07, "loss": 0.0118, "num_tokens": 258813037.0, "reward": 0.6328125, "reward_std": 0.38773179054260254, "rewards/simpleverify_reward/mean": 0.6328125, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1229 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1202.8203125, "completions/mean_terminated_length": 1046.3055419921875, "completions/min_length": 222.0, "completions/min_terminated_length": 222.0, "epoch": 0.21824472686140128, "frac_reward_zero_std": 0.25, "grad_norm": 0.7052378058433533, "learning_rate": 3.855e-07, "loss": 0.0068, "num_tokens": 258976294.0, "reward": 0.5546875, "reward_std": 0.2896904945373535, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1230 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1223.3671875, "completions/mean_terminated_length": 1033.0673828125, "completions/min_length": 231.0, "completions/min_terminated_length": 231.0, "epoch": 0.218422161598687, "frac_reward_zero_std": 0.125, "grad_norm": 0.9514174461364746, "learning_rate": 3.8499999999999997e-07, "loss": 0.0191, "num_tokens": 259142181.0, "reward": 0.484375, "reward_std": 0.38996240496635437, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1231 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2018.0, "completions/mean_length": 1219.8515625, "completions/mean_terminated_length": 987.969970703125, "completions/min_length": 253.0, "completions/min_terminated_length": 253.0, "epoch": 0.21859959633597267, "frac_reward_zero_std": 0.125, "grad_norm": 0.844750702381134, "learning_rate": 3.845e-07, "loss": 0.0101, "num_tokens": 259307618.0, "reward": 0.5859375, "reward_std": 0.3530189096927643, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1232 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1529.8828125, "completions/mean_terminated_length": 1311.122314453125, "completions/min_length": 753.0, "completions/min_terminated_length": 753.0, "epoch": 0.21877703107325835, "frac_reward_zero_std": 0.25, "grad_norm": 0.5316745638847351, "learning_rate": 3.84e-07, "loss": 0.0337, "num_tokens": 259521043.0, "reward": 0.5, "reward_std": 0.32770198583602905, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 1233 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1487.4765625, "completions/mean_terminated_length": 1330.530029296875, "completions/min_length": 715.0, "completions/min_terminated_length": 715.0, "epoch": 0.21895446581054406, "frac_reward_zero_std": 0.125, "grad_norm": 0.5868287682533264, "learning_rate": 3.835e-07, "loss": 0.0288, "num_tokens": 259729040.0, "reward": 0.5859375, "reward_std": 0.33456701040267944, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1234 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2004.0, "completions/mean_length": 1473.875, "completions/mean_terminated_length": 1266.2127685546875, "completions/min_length": 770.0, "completions/min_terminated_length": 770.0, "epoch": 0.21913190054782974, "frac_reward_zero_std": 0.25, "grad_norm": 0.5081027746200562, "learning_rate": 3.83e-07, "loss": 0.0252, "num_tokens": 259935296.0, "reward": 0.5546875, "reward_std": 0.2760361433029175, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1235 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1497.2265625, "completions/mean_terminated_length": 1305.9052734375, "completions/min_length": 743.0, "completions/min_terminated_length": 743.0, "epoch": 0.21930933528511545, "frac_reward_zero_std": 0.25, "grad_norm": 0.49711325764656067, "learning_rate": 3.825e-07, "loss": 0.0238, "num_tokens": 260144541.0, "reward": 0.546875, "reward_std": 0.266292929649353, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1236 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1944.0, "completions/mean_length": 1054.0859375, "completions/mean_terminated_length": 969.85595703125, "completions/min_length": 294.0, "completions/min_terminated_length": 294.0, "epoch": 0.21948677002240113, "frac_reward_zero_std": 0.125, "grad_norm": 0.7586798667907715, "learning_rate": 3.82e-07, "loss": 0.0636, "num_tokens": 260288280.0, "reward": 0.8046875, "reward_std": 0.3098391890525818, "rewards/simpleverify_reward/mean": 0.8046875, "rewards/simpleverify_reward/std": 0.3979988098144531, "step": 1237 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1968.0, "completions/mean_length": 1019.703125, "completions/mean_terminated_length": 977.9024047851562, "completions/min_length": 306.0, "completions/min_terminated_length": 306.0, "epoch": 0.21966420475968682, "frac_reward_zero_std": 0.375, "grad_norm": 0.8302742838859558, "learning_rate": 3.8149999999999997e-07, "loss": 0.0256, "num_tokens": 260427618.0, "reward": 0.7890625, "reward_std": 0.23504294455051422, "rewards/simpleverify_reward/mean": 0.7890625, "rewards/simpleverify_reward/std": 0.4095771610736847, "step": 1238 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1046.109375, "completions/mean_terminated_length": 996.8359985351562, "completions/min_length": 323.0, "completions/min_terminated_length": 323.0, "epoch": 0.21984163949697252, "frac_reward_zero_std": 0.375, "grad_norm": 0.7723889946937561, "learning_rate": 3.81e-07, "loss": 0.0337, "num_tokens": 260570336.0, "reward": 0.8046875, "reward_std": 0.2218368798494339, "rewards/simpleverify_reward/mean": 0.8046875, "rewards/simpleverify_reward/std": 0.3979988098144531, "step": 1239 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.03125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1926.0, "completions/mean_length": 1001.90625, "completions/mean_terminated_length": 968.1612548828125, "completions/min_length": 331.0, "completions/min_terminated_length": 331.0, "epoch": 0.2200190742342582, "frac_reward_zero_std": 0.375, "grad_norm": 0.5413018465042114, "learning_rate": 3.805e-07, "loss": 0.0337, "num_tokens": 260707396.0, "reward": 0.8125, "reward_std": 0.21917608380317688, "rewards/simpleverify_reward/mean": 0.8125, "rewards/simpleverify_reward/std": 0.39184603095054626, "step": 1240 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1403.0390625, "completions/mean_terminated_length": 1140.80224609375, "completions/min_length": 465.0, "completions/min_terminated_length": 465.0, "epoch": 0.22019650897154391, "frac_reward_zero_std": 0.125, "grad_norm": 0.6064037084579468, "learning_rate": 3.7999999999999996e-07, "loss": 0.0132, "num_tokens": 260904089.0, "reward": 0.515625, "reward_std": 0.3330235481262207, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1241 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1987.0, "completions/mean_length": 1381.3828125, "completions/mean_terminated_length": 1089.2696533203125, "completions/min_length": 460.0, "completions/min_terminated_length": 460.0, "epoch": 0.2203739437088296, "frac_reward_zero_std": 0.25, "grad_norm": 0.6045839190483093, "learning_rate": 3.795e-07, "loss": 0.0103, "num_tokens": 261098010.0, "reward": 0.515625, "reward_std": 0.27699071168899536, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1242 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2013.0, "completions/mean_length": 1388.953125, "completions/mean_terminated_length": 1110.68896484375, "completions/min_length": 399.0, "completions/min_terminated_length": 399.0, "epoch": 0.22055137844611528, "frac_reward_zero_std": 0.25, "grad_norm": 0.609367847442627, "learning_rate": 3.79e-07, "loss": 0.0356, "num_tokens": 261292900.0, "reward": 0.453125, "reward_std": 0.291130006313324, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1243 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1387.65625, "completions/mean_terminated_length": 1065.162841796875, "completions/min_length": 455.0, "completions/min_terminated_length": 455.0, "epoch": 0.22072881318340098, "frac_reward_zero_std": 0.375, "grad_norm": 0.5013318657875061, "learning_rate": 3.785e-07, "loss": -0.0016, "num_tokens": 261487624.0, "reward": 0.4921875, "reward_std": 0.25087815523147583, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1244 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1828.0, "completions/mean_length": 1292.21875, "completions/mean_terminated_length": 936.0459594726562, "completions/min_length": 277.0, "completions/min_terminated_length": 277.0, "epoch": 0.22090624792068667, "frac_reward_zero_std": 0.625, "grad_norm": 0.4630362093448639, "learning_rate": 3.7799999999999997e-07, "loss": 0.0152, "num_tokens": 261663636.0, "reward": 0.328125, "reward_std": 0.1566799283027649, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1245 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1831.0, "completions/mean_length": 1290.1640625, "completions/mean_terminated_length": 970.1889038085938, "completions/min_length": 255.0, "completions/min_terminated_length": 255.0, "epoch": 0.22108368265797237, "frac_reward_zero_std": 0.375, "grad_norm": 0.5633994340896606, "learning_rate": 3.775e-07, "loss": 0.0091, "num_tokens": 261839385.0, "reward": 0.390625, "reward_std": 0.24821737408638, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1246 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1986.0, "completions/mean_length": 1295.3203125, "completions/mean_terminated_length": 989.2857666015625, "completions/min_length": 272.0, "completions/min_terminated_length": 272.0, "epoch": 0.22126111739525806, "frac_reward_zero_std": 0.25, "grad_norm": 0.6398330330848694, "learning_rate": 3.77e-07, "loss": 0.0135, "num_tokens": 262015794.0, "reward": 0.375, "reward_std": 0.294668972492218, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 1247 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1288.765625, "completions/mean_terminated_length": 1003.0322875976562, "completions/min_length": 261.0, "completions/min_terminated_length": 261.0, "epoch": 0.22143855213254374, "frac_reward_zero_std": 0.25, "grad_norm": 0.6415656208992004, "learning_rate": 3.7649999999999996e-07, "loss": 0.0164, "num_tokens": 262191364.0, "reward": 0.3671875, "reward_std": 0.30257561802864075, "rewards/simpleverify_reward/mean": 0.3671875, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1248 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2003.0, "completions/mean_length": 1300.765625, "completions/mean_terminated_length": 985.2666625976562, "completions/min_length": 417.0, "completions/min_terminated_length": 417.0, "epoch": 0.22161598686982945, "frac_reward_zero_std": 0.25, "grad_norm": 0.5933798551559448, "learning_rate": 3.76e-07, "loss": 0.0223, "num_tokens": 262373222.0, "reward": 0.4296875, "reward_std": 0.27603617310523987, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1249 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1991.0, "completions/mean_length": 1327.8359375, "completions/mean_terminated_length": 988.4482421875, "completions/min_length": 395.0, "completions/min_terminated_length": 395.0, "epoch": 0.22179342160711513, "frac_reward_zero_std": 0.25, "grad_norm": 0.6656382083892822, "learning_rate": 3.755e-07, "loss": 0.0102, "num_tokens": 262558545.0, "reward": 0.4453125, "reward_std": 0.27376943826675415, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1250 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2014.0, "completions/mean_length": 1305.671875, "completions/mean_terminated_length": 992.2444458007812, "completions/min_length": 410.0, "completions/min_terminated_length": 410.0, "epoch": 0.22197085634440084, "frac_reward_zero_std": 0.125, "grad_norm": 0.6511300206184387, "learning_rate": 3.75e-07, "loss": 0.0543, "num_tokens": 262741031.0, "reward": 0.4609375, "reward_std": 0.30917394161224365, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1251 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1326.421875, "completions/mean_terminated_length": 986.3677978515625, "completions/min_length": 383.0, "completions/min_terminated_length": 383.0, "epoch": 0.22214829108168652, "frac_reward_zero_std": 0.375, "grad_norm": 0.5146708488464355, "learning_rate": 3.7449999999999997e-07, "loss": 0.0086, "num_tokens": 262926173.0, "reward": 0.4375, "reward_std": 0.21542394161224365, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1252 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1338.65625, "completions/mean_terminated_length": 1121.5101318359375, "completions/min_length": 428.0, "completions/min_terminated_length": 428.0, "epoch": 0.2223257258189722, "frac_reward_zero_std": 0.25, "grad_norm": 0.6780998706817627, "learning_rate": 3.74e-07, "loss": -0.013, "num_tokens": 263110513.0, "reward": 0.3125, "reward_std": 0.3561374545097351, "rewards/simpleverify_reward/mean": 0.3125, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 1253 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1336.1015625, "completions/mean_terminated_length": 1145.7921142578125, "completions/min_length": 452.0, "completions/min_terminated_length": 452.0, "epoch": 0.2225031605562579, "frac_reward_zero_std": 0.25, "grad_norm": 0.6746789813041687, "learning_rate": 3.735e-07, "loss": -0.0101, "num_tokens": 263294526.0, "reward": 0.3125, "reward_std": 0.3592950701713562, "rewards/simpleverify_reward/mean": 0.3125, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 1254 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2022.0, "completions/mean_length": 1339.296875, "completions/mean_terminated_length": 1131.697021484375, "completions/min_length": 460.0, "completions/min_terminated_length": 460.0, "epoch": 0.2226805952935436, "frac_reward_zero_std": 0.25, "grad_norm": 0.6388943195343018, "learning_rate": 3.7299999999999997e-07, "loss": -0.0024, "num_tokens": 263478948.0, "reward": 0.34375, "reward_std": 0.3592148721218109, "rewards/simpleverify_reward/mean": 0.34375, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 1255 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1355.7109375, "completions/mean_terminated_length": 1124.947998046875, "completions/min_length": 432.0, "completions/min_terminated_length": 432.0, "epoch": 0.2228580300308293, "frac_reward_zero_std": 0.125, "grad_norm": 0.6940591335296631, "learning_rate": 3.725e-07, "loss": 0.0148, "num_tokens": 263665471.0, "reward": 0.3359375, "reward_std": 0.3900166153907776, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1256 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1991.0, "completions/mean_length": 1477.15625, "completions/mean_terminated_length": 1134.6500244140625, "completions/min_length": 512.0, "completions/min_terminated_length": 512.0, "epoch": 0.22303546476811498, "frac_reward_zero_std": 0.625, "grad_norm": 0.4232292175292969, "learning_rate": 3.72e-07, "loss": 0.0081, "num_tokens": 263865091.0, "reward": 0.5, "reward_std": 0.12433473765850067, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 1257 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1459.6015625, "completions/mean_terminated_length": 1182.310302734375, "completions/min_length": 517.0, "completions/min_terminated_length": 517.0, "epoch": 0.22321289950540066, "frac_reward_zero_std": 0.125, "grad_norm": 0.5452167391777039, "learning_rate": 3.7149999999999996e-07, "loss": 0.009, "num_tokens": 264062464.0, "reward": 0.53125, "reward_std": 0.29408007860183716, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1258 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1458.765625, "completions/mean_terminated_length": 1209.977783203125, "completions/min_length": 410.0, "completions/min_terminated_length": 410.0, "epoch": 0.22339033424268637, "frac_reward_zero_std": 0.125, "grad_norm": 0.5450909733772278, "learning_rate": 3.71e-07, "loss": 0.0072, "num_tokens": 264259730.0, "reward": 0.546875, "reward_std": 0.30523642897605896, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1259 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1459.2109375, "completions/mean_terminated_length": 1139.9879150390625, "completions/min_length": 510.0, "completions/min_terminated_length": 510.0, "epoch": 0.22356776897997205, "frac_reward_zero_std": 0.375, "grad_norm": 0.527843713760376, "learning_rate": 3.705e-07, "loss": 0.0062, "num_tokens": 264457053.0, "reward": 0.5078125, "reward_std": 0.22686955332756042, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1260 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1446.90625, "completions/mean_terminated_length": 1335.5926513671875, "completions/min_length": 745.0, "completions/min_terminated_length": 745.0, "epoch": 0.22374520371725776, "frac_reward_zero_std": 0.375, "grad_norm": 0.48065224289894104, "learning_rate": 3.7e-07, "loss": 0.0322, "num_tokens": 264654865.0, "reward": 0.625, "reward_std": 0.23328250646591187, "rewards/simpleverify_reward/mean": 0.625, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 1261 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1968.0, "completions/mean_length": 1435.9375, "completions/mean_terminated_length": 1322.5926513671875, "completions/min_length": 633.0, "completions/min_terminated_length": 633.0, "epoch": 0.22392263845454344, "frac_reward_zero_std": 0.375, "grad_norm": 0.5221258401870728, "learning_rate": 3.6949999999999997e-07, "loss": 0.0076, "num_tokens": 264851273.0, "reward": 0.578125, "reward_std": 0.2563907504081726, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1262 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2013.0, "completions/mean_length": 1411.9609375, "completions/mean_terminated_length": 1358.059326171875, "completions/min_length": 683.0, "completions/min_terminated_length": 683.0, "epoch": 0.22410007319182912, "frac_reward_zero_std": 0.25, "grad_norm": 0.5533108711242676, "learning_rate": 3.69e-07, "loss": 0.0135, "num_tokens": 265044612.0, "reward": 0.625, "reward_std": 0.30662089586257935, "rewards/simpleverify_reward/mean": 0.625, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 1263 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2022.0, "completions/mean_length": 1415.15625, "completions/mean_terminated_length": 1337.4385986328125, "completions/min_length": 701.0, "completions/min_terminated_length": 701.0, "epoch": 0.22427750792911483, "frac_reward_zero_std": 0.25, "grad_norm": 0.5346993803977966, "learning_rate": 3.685e-07, "loss": 0.0313, "num_tokens": 265238360.0, "reward": 0.640625, "reward_std": 0.3008190393447876, "rewards/simpleverify_reward/mean": 0.640625, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 1264 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1998.0, "completions/mean_length": 1549.7890625, "completions/mean_terminated_length": 1219.80517578125, "completions/min_length": 545.0, "completions/min_terminated_length": 545.0, "epoch": 0.2244549426664005, "frac_reward_zero_std": 0.375, "grad_norm": 0.5864889621734619, "learning_rate": 3.6799999999999996e-07, "loss": 0.0158, "num_tokens": 265450077.0, "reward": 0.3359375, "reward_std": 0.2942485511302948, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1265 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1997.0, "completions/mean_length": 1540.65625, "completions/mean_terminated_length": 1274.90478515625, "completions/min_length": 565.0, "completions/min_terminated_length": 565.0, "epoch": 0.22463237740368622, "frac_reward_zero_std": 0.25, "grad_norm": 0.6257895827293396, "learning_rate": 3.675e-07, "loss": 0.0112, "num_tokens": 265660625.0, "reward": 0.375, "reward_std": 0.3396275043487549, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 1266 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2014.0, "completions/mean_length": 1523.921875, "completions/mean_terminated_length": 1229.9267578125, "completions/min_length": 505.0, "completions/min_terminated_length": 505.0, "epoch": 0.2248098121409719, "frac_reward_zero_std": 0.25, "grad_norm": 0.6647021770477295, "learning_rate": 3.67e-07, "loss": 0.0073, "num_tokens": 265869031.0, "reward": 0.359375, "reward_std": 0.3263174891471863, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 1267 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2015.0, "completions/mean_length": 1560.4765625, "completions/mean_terminated_length": 1267.9625244140625, "completions/min_length": 540.0, "completions/min_terminated_length": 540.0, "epoch": 0.22498724687825758, "frac_reward_zero_std": 0.375, "grad_norm": 0.5589057207107544, "learning_rate": 3.6649999999999995e-07, "loss": -0.0046, "num_tokens": 266082116.0, "reward": 0.359375, "reward_std": 0.3092281222343445, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 1268 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1688.3671875, "completions/mean_terminated_length": 1434.2266845703125, "completions/min_length": 732.0, "completions/min_terminated_length": 732.0, "epoch": 0.2251646816155433, "frac_reward_zero_std": 0.125, "grad_norm": 0.5639638304710388, "learning_rate": 3.6599999999999997e-07, "loss": 0.0185, "num_tokens": 266309603.0, "reward": 0.3515625, "reward_std": 0.3085086941719055, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1269 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1963.0, "completions/mean_length": 1736.2734375, "completions/mean_terminated_length": 1414.65087890625, "completions/min_length": 819.0, "completions/min_terminated_length": 819.0, "epoch": 0.22534211635282897, "frac_reward_zero_std": 0.375, "grad_norm": 0.466474324464798, "learning_rate": 3.655e-07, "loss": 0.0148, "num_tokens": 266543222.0, "reward": 0.2421875, "reward_std": 0.2777385711669922, "rewards/simpleverify_reward/mean": 0.2421875, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 1270 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1672.375, "completions/mean_terminated_length": 1361.142822265625, "completions/min_length": 618.0, "completions/min_terminated_length": 618.0, "epoch": 0.22551955109011468, "frac_reward_zero_std": 0.25, "grad_norm": 0.5701966881752014, "learning_rate": 3.65e-07, "loss": 0.0339, "num_tokens": 266768662.0, "reward": 0.296875, "reward_std": 0.3047843277454376, "rewards/simpleverify_reward/mean": 0.296875, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 1271 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2012.0, "completions/mean_length": 1678.1796875, "completions/mean_terminated_length": 1425.144775390625, "completions/min_length": 778.0, "completions/min_terminated_length": 778.0, "epoch": 0.22569698582740036, "frac_reward_zero_std": 0.375, "grad_norm": 0.5041601061820984, "learning_rate": 3.6449999999999996e-07, "loss": 0.035, "num_tokens": 266994845.0, "reward": 0.265625, "reward_std": 0.2755298614501953, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 1272 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1877.0, "completions/mean_length": 1214.921875, "completions/mean_terminated_length": 970.888916015625, "completions/min_length": 440.0, "completions/min_terminated_length": 440.0, "epoch": 0.22587442056468604, "frac_reward_zero_std": 0.25, "grad_norm": 0.8095243573188782, "learning_rate": 3.64e-07, "loss": 0.0122, "num_tokens": 267163395.0, "reward": 0.3671875, "reward_std": 0.2889174520969391, "rewards/simpleverify_reward/mean": 0.3671875, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1273 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2003.0, "completions/mean_length": 1235.5546875, "completions/mean_terminated_length": 997.565673828125, "completions/min_length": 453.0, "completions/min_terminated_length": 453.0, "epoch": 0.22605185530197175, "frac_reward_zero_std": 0.25, "grad_norm": 0.6859294176101685, "learning_rate": 3.635e-07, "loss": 0.0027, "num_tokens": 267334586.0, "reward": 0.4375, "reward_std": 0.32927703857421875, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1274 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1942.0, "completions/mean_length": 1231.6796875, "completions/mean_terminated_length": 1013.4554443359375, "completions/min_length": 411.0, "completions/min_terminated_length": 411.0, "epoch": 0.22622929003925743, "frac_reward_zero_std": 0.375, "grad_norm": 0.7315773367881775, "learning_rate": 3.6299999999999995e-07, "loss": 0.0143, "num_tokens": 267505281.0, "reward": 0.4765625, "reward_std": 0.2991669476032257, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1275 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1900.0, "completions/mean_length": 1220.1484375, "completions/mean_terminated_length": 966.7244873046875, "completions/min_length": 405.0, "completions/min_terminated_length": 405.0, "epoch": 0.22640672477654314, "frac_reward_zero_std": 0.375, "grad_norm": 0.8462421298027039, "learning_rate": 3.6249999999999997e-07, "loss": 0.0157, "num_tokens": 267674500.0, "reward": 0.3984375, "reward_std": 0.25921475887298584, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1276 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1288.09375, "completions/mean_terminated_length": 955.1011352539062, "completions/min_length": 407.0, "completions/min_terminated_length": 407.0, "epoch": 0.22658415951382882, "frac_reward_zero_std": 0.25, "grad_norm": 0.6704915165901184, "learning_rate": 3.62e-07, "loss": -0.0043, "num_tokens": 267852304.0, "reward": 0.3515625, "reward_std": 0.27001726627349854, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1277 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2000.0, "completions/mean_length": 1277.921875, "completions/mean_terminated_length": 952.7777709960938, "completions/min_length": 359.0, "completions/min_terminated_length": 359.0, "epoch": 0.2267615942511145, "frac_reward_zero_std": 0.5, "grad_norm": 0.5009145140647888, "learning_rate": 3.6149999999999995e-07, "loss": 0.0046, "num_tokens": 268028806.0, "reward": 0.4609375, "reward_std": 0.21353617310523987, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1278 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1991.0, "completions/mean_length": 1283.8671875, "completions/mean_terminated_length": 961.2333374023438, "completions/min_length": 372.0, "completions/min_terminated_length": 372.0, "epoch": 0.2269390289884002, "frac_reward_zero_std": 0.5, "grad_norm": 0.5617305636405945, "learning_rate": 3.6099999999999996e-07, "loss": -0.0042, "num_tokens": 268206069.0, "reward": 0.3984375, "reward_std": 0.22596919536590576, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1279 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1293.703125, "completions/mean_terminated_length": 987.010986328125, "completions/min_length": 383.0, "completions/min_terminated_length": 383.0, "epoch": 0.2271164637256859, "frac_reward_zero_std": 0.375, "grad_norm": 0.5918540954589844, "learning_rate": 3.605e-07, "loss": -0.0106, "num_tokens": 268384591.0, "reward": 0.390625, "reward_std": 0.22863000631332397, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1280 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1316.1328125, "completions/mean_terminated_length": 1120.485107421875, "completions/min_length": 557.0, "completions/min_terminated_length": 557.0, "epoch": 0.2272938984629716, "frac_reward_zero_std": 0.25, "grad_norm": 0.6741766929626465, "learning_rate": 3.6e-07, "loss": 0.0098, "num_tokens": 268563104.0, "reward": 0.578125, "reward_std": 0.29578250646591187, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1281 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2011.0, "completions/mean_length": 1341.203125, "completions/mean_terminated_length": 1152.2574462890625, "completions/min_length": 620.0, "completions/min_terminated_length": 620.0, "epoch": 0.22747133320025728, "frac_reward_zero_std": 0.25, "grad_norm": 0.5348829030990601, "learning_rate": 3.5949999999999996e-07, "loss": 0.0226, "num_tokens": 268744826.0, "reward": 0.5078125, "reward_std": 0.28548622131347656, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1282 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1342.3125, "completions/mean_terminated_length": 1135.595947265625, "completions/min_length": 576.0, "completions/min_terminated_length": 576.0, "epoch": 0.22764876793754296, "frac_reward_zero_std": 0.25, "grad_norm": 0.6081008911132812, "learning_rate": 3.5899999999999997e-07, "loss": 0.0112, "num_tokens": 268926690.0, "reward": 0.53125, "reward_std": 0.29578250646591187, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1283 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1892.0, "completions/mean_length": 1324.0625, "completions/mean_terminated_length": 1121.3599853515625, "completions/min_length": 561.0, "completions/min_terminated_length": 561.0, "epoch": 0.22782620267482867, "frac_reward_zero_std": 0.375, "grad_norm": 0.4827655553817749, "learning_rate": 3.585e-07, "loss": 0.0218, "num_tokens": 269106218.0, "reward": 0.5546875, "reward_std": 0.24074089527130127, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1284 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2018.0, "completions/mean_length": 1506.34375, "completions/mean_terminated_length": 1192.0494384765625, "completions/min_length": 638.0, "completions/min_terminated_length": 638.0, "epoch": 0.22800363741211435, "frac_reward_zero_std": 0.375, "grad_norm": 0.5148894190788269, "learning_rate": 3.5799999999999995e-07, "loss": 0.0251, "num_tokens": 269309958.0, "reward": 0.3828125, "reward_std": 0.3021235466003418, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1285 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1517.9765625, "completions/mean_terminated_length": 1240.34521484375, "completions/min_length": 616.0, "completions/min_terminated_length": 616.0, "epoch": 0.22818107214940006, "frac_reward_zero_std": 0.375, "grad_norm": 0.5108408331871033, "learning_rate": 3.5749999999999997e-07, "loss": 0.0239, "num_tokens": 269515187.0, "reward": 0.4375, "reward_std": 0.3071783781051636, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1286 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1935.0, "completions/mean_length": 1477.875, "completions/mean_terminated_length": 1209.1954345703125, "completions/min_length": 589.0, "completions/min_terminated_length": 589.0, "epoch": 0.22835850688668574, "frac_reward_zero_std": 0.375, "grad_norm": 0.5261794924736023, "learning_rate": 3.57e-07, "loss": 0.0002, "num_tokens": 269715283.0, "reward": 0.40625, "reward_std": 0.28282544016838074, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1287 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1989.0, "completions/mean_length": 1516.1796875, "completions/mean_terminated_length": 1237.607177734375, "completions/min_length": 614.0, "completions/min_terminated_length": 614.0, "epoch": 0.22853594162397142, "frac_reward_zero_std": 0.375, "grad_norm": 0.5215900540351868, "learning_rate": 3.5649999999999994e-07, "loss": 0.0292, "num_tokens": 269920282.0, "reward": 0.4453125, "reward_std": 0.2845000624656677, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1288 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1919.0, "completions/mean_length": 1265.6640625, "completions/mean_terminated_length": 1066.2451171875, "completions/min_length": 223.0, "completions/min_terminated_length": 223.0, "epoch": 0.22871337636125713, "frac_reward_zero_std": 0.125, "grad_norm": 0.7240816354751587, "learning_rate": 3.5599999999999996e-07, "loss": 0.0175, "num_tokens": 270093471.0, "reward": 0.546875, "reward_std": 0.3748188614845276, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1289 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1956.0, "completions/mean_length": 1282.3671875, "completions/mean_terminated_length": 1067.989990234375, "completions/min_length": 268.0, "completions/min_terminated_length": 268.0, "epoch": 0.2288908110985428, "frac_reward_zero_std": 0.125, "grad_norm": 0.7476657629013062, "learning_rate": 3.555e-07, "loss": 0.0335, "num_tokens": 270268798.0, "reward": 0.5234375, "reward_std": 0.40036705136299133, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1290 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1262.71875, "completions/mean_terminated_length": 1022.3265380859375, "completions/min_length": 261.0, "completions/min_terminated_length": 261.0, "epoch": 0.22906824583582852, "frac_reward_zero_std": 0.125, "grad_norm": 0.7854456901550293, "learning_rate": 3.55e-07, "loss": 0.0157, "num_tokens": 270441610.0, "reward": 0.5703125, "reward_std": 0.38908424973487854, "rewards/simpleverify_reward/mean": 0.5703125, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1291 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1285.0625, "completions/mean_terminated_length": 1009.1063232421875, "completions/min_length": 227.0, "completions/min_terminated_length": 227.0, "epoch": 0.2292456805731142, "frac_reward_zero_std": 0.25, "grad_norm": 0.611349880695343, "learning_rate": 3.5449999999999995e-07, "loss": 0.0059, "num_tokens": 270617282.0, "reward": 0.4921875, "reward_std": 0.3580252230167389, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1292 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1226.0703125, "completions/mean_terminated_length": 1108.65185546875, "completions/min_length": 436.0, "completions/min_terminated_length": 436.0, "epoch": 0.22942311531039988, "frac_reward_zero_std": 0.25, "grad_norm": 0.5487425327301025, "learning_rate": 3.5399999999999997e-07, "loss": 0.0039, "num_tokens": 270786395.0, "reward": 0.6015625, "reward_std": 0.3324124813079834, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1293 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2020.0, "completions/mean_length": 1235.71875, "completions/mean_terminated_length": 1102.7999267578125, "completions/min_length": 488.0, "completions/min_terminated_length": 488.0, "epoch": 0.2296005500476856, "frac_reward_zero_std": 0.25, "grad_norm": 0.5663857460021973, "learning_rate": 3.535e-07, "loss": 0.0067, "num_tokens": 270956743.0, "reward": 0.578125, "reward_std": 0.33052173256874084, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1294 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.09375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1960.0, "completions/mean_length": 1208.8125, "completions/mean_terminated_length": 1122.0, "completions/min_length": 496.0, "completions/min_terminated_length": 496.0, "epoch": 0.22977798478497127, "frac_reward_zero_std": 0.375, "grad_norm": 0.49327409267425537, "learning_rate": 3.5299999999999994e-07, "loss": -0.0065, "num_tokens": 271123647.0, "reward": 0.578125, "reward_std": 0.3044400215148926, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1295 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1230.8046875, "completions/mean_terminated_length": 1042.22119140625, "completions/min_length": 447.0, "completions/min_terminated_length": 447.0, "epoch": 0.22995541952225698, "frac_reward_zero_std": 0.25, "grad_norm": 0.5341302752494812, "learning_rate": 3.5249999999999996e-07, "loss": 0.0288, "num_tokens": 271293366.0, "reward": 0.578125, "reward_std": 0.3561279773712158, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1296 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1288.6875, "completions/mean_terminated_length": 1046.0206298828125, "completions/min_length": 580.0, "completions/min_terminated_length": 580.0, "epoch": 0.23013285425954266, "frac_reward_zero_std": 0.375, "grad_norm": 0.5345629453659058, "learning_rate": 3.52e-07, "loss": 0.0296, "num_tokens": 271468046.0, "reward": 0.3359375, "reward_std": 0.29208454489707947, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1297 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1981.0, "completions/mean_length": 1339.0703125, "completions/mean_terminated_length": 992.8488159179688, "completions/min_length": 608.0, "completions/min_terminated_length": 608.0, "epoch": 0.23031028899682834, "frac_reward_zero_std": 0.375, "grad_norm": 0.5078356266021729, "learning_rate": 3.5149999999999994e-07, "loss": 0.0219, "num_tokens": 271649175.0, "reward": 0.328125, "reward_std": 0.2543674111366272, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1298 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2008.0, "completions/mean_length": 1343.4140625, "completions/mean_terminated_length": 1045.9222412109375, "completions/min_length": 571.0, "completions/min_terminated_length": 571.0, "epoch": 0.23048772373411405, "frac_reward_zero_std": 0.5, "grad_norm": 0.46228960156440735, "learning_rate": 3.5099999999999995e-07, "loss": 0.0077, "num_tokens": 271830860.0, "reward": 0.3203125, "reward_std": 0.21433821320533752, "rewards/simpleverify_reward/mean": 0.3203125, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 1299 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2003.0, "completions/mean_length": 1358.7734375, "completions/mean_terminated_length": 1089.0760498046875, "completions/min_length": 597.0, "completions/min_terminated_length": 597.0, "epoch": 0.23066515847139973, "frac_reward_zero_std": 0.5, "grad_norm": 0.46858835220336914, "learning_rate": 3.5049999999999997e-07, "loss": 0.0067, "num_tokens": 272014511.0, "reward": 0.359375, "reward_std": 0.2004890739917755, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 1300 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1974.0, "completions/mean_length": 1195.421875, "completions/mean_terminated_length": 1018.4717407226562, "completions/min_length": 581.0, "completions/min_terminated_length": 581.0, "epoch": 0.23084259320868544, "frac_reward_zero_std": 0.0, "grad_norm": 0.7129612565040588, "learning_rate": 3.5e-07, "loss": 0.0187, "num_tokens": 272179253.0, "reward": 0.53125, "reward_std": 0.39632561802864075, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1301 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1988.0, "completions/mean_length": 1223.984375, "completions/mean_terminated_length": 1003.7029418945312, "completions/min_length": 485.0, "completions/min_terminated_length": 485.0, "epoch": 0.23102002794597112, "frac_reward_zero_std": 0.125, "grad_norm": 0.6816868185997009, "learning_rate": 3.4949999999999995e-07, "loss": 0.025, "num_tokens": 272347651.0, "reward": 0.5078125, "reward_std": 0.3473209738731384, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1302 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1979.0, "completions/mean_length": 1198.765625, "completions/mean_terminated_length": 992.6408081054688, "completions/min_length": 519.0, "completions/min_terminated_length": 519.0, "epoch": 0.2311974626832568, "frac_reward_zero_std": 0.0, "grad_norm": 0.7475446462631226, "learning_rate": 3.4899999999999996e-07, "loss": 0.035, "num_tokens": 272512821.0, "reward": 0.546875, "reward_std": 0.36092111468315125, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1303 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1941.0, "completions/mean_length": 1248.875, "completions/mean_terminated_length": 1014.7879028320312, "completions/min_length": 539.0, "completions/min_terminated_length": 539.0, "epoch": 0.2313748974205425, "frac_reward_zero_std": 0.125, "grad_norm": 0.6542615294456482, "learning_rate": 3.485e-07, "loss": 0.0286, "num_tokens": 272684405.0, "reward": 0.5703125, "reward_std": 0.37146639823913574, "rewards/simpleverify_reward/mean": 0.5703125, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1304 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2008.0, "completions/mean_length": 1561.3984375, "completions/mean_terminated_length": 1170.7464599609375, "completions/min_length": 448.0, "completions/min_terminated_length": 448.0, "epoch": 0.2315523321578282, "frac_reward_zero_std": 0.375, "grad_norm": 0.46741050481796265, "learning_rate": 3.4799999999999994e-07, "loss": 0.0205, "num_tokens": 272897432.0, "reward": 0.3828125, "reward_std": 0.29312169551849365, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1305 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2003.0, "completions/mean_length": 1593.890625, "completions/mean_terminated_length": 1321.425048828125, "completions/min_length": 429.0, "completions/min_terminated_length": 429.0, "epoch": 0.2317297668951139, "frac_reward_zero_std": 0.375, "grad_norm": 0.519931435585022, "learning_rate": 3.4749999999999996e-07, "loss": 0.0364, "num_tokens": 273114618.0, "reward": 0.3984375, "reward_std": 0.2955252230167389, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1306 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2008.0, "completions/mean_length": 1566.6171875, "completions/mean_terminated_length": 1247.7791748046875, "completions/min_length": 401.0, "completions/min_terminated_length": 401.0, "epoch": 0.23190720163239958, "frac_reward_zero_std": 0.375, "grad_norm": 0.4748646914958954, "learning_rate": 3.4699999999999997e-07, "loss": 0.0332, "num_tokens": 273328313.0, "reward": 0.453125, "reward_std": 0.2870296835899353, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1307 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1571.34375, "completions/mean_terminated_length": 1245.2105712890625, "completions/min_length": 396.0, "completions/min_terminated_length": 396.0, "epoch": 0.23208463636968527, "frac_reward_zero_std": 0.375, "grad_norm": 0.5175181031227112, "learning_rate": 3.4649999999999993e-07, "loss": 0.0433, "num_tokens": 273542613.0, "reward": 0.46875, "reward_std": 0.31651926040649414, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1308 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1952.0, "completions/mean_length": 1256.140625, "completions/mean_terminated_length": 1134.8648681640625, "completions/min_length": 512.0, "completions/min_terminated_length": 512.0, "epoch": 0.23226207110697097, "frac_reward_zero_std": 0.25, "grad_norm": 0.639200747013092, "learning_rate": 3.4599999999999995e-07, "loss": 0.0226, "num_tokens": 273719575.0, "reward": 0.5234375, "reward_std": 0.32067376375198364, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1309 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1996.0, "completions/mean_length": 1242.546875, "completions/mean_terminated_length": 1166.820556640625, "completions/min_length": 507.0, "completions/min_terminated_length": 507.0, "epoch": 0.23243950584425666, "frac_reward_zero_std": 0.25, "grad_norm": 0.649411678314209, "learning_rate": 3.4549999999999996e-07, "loss": 0.0212, "num_tokens": 273894797.0, "reward": 0.4921875, "reward_std": 0.33776313066482544, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1310 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1269.40625, "completions/mean_terminated_length": 1116.59814453125, "completions/min_length": 538.0, "completions/min_terminated_length": 538.0, "epoch": 0.23261694058154236, "frac_reward_zero_std": 0.25, "grad_norm": 0.6241251826286316, "learning_rate": 3.45e-07, "loss": 0.0282, "num_tokens": 274073457.0, "reward": 0.46875, "reward_std": 0.3525126576423645, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1311 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0703125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1229.1171875, "completions/mean_terminated_length": 1167.1849365234375, "completions/min_length": 549.0, "completions/min_terminated_length": 549.0, "epoch": 0.23279437531882805, "frac_reward_zero_std": 0.125, "grad_norm": 0.6491435766220093, "learning_rate": 3.4449999999999994e-07, "loss": 0.0208, "num_tokens": 274246960.0, "reward": 0.5390625, "reward_std": 0.382485955953598, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1312 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1399.890625, "completions/mean_terminated_length": 1192.7628173828125, "completions/min_length": 476.0, "completions/min_terminated_length": 476.0, "epoch": 0.23297181005611373, "frac_reward_zero_std": 0.0, "grad_norm": 0.6626121401786804, "learning_rate": 3.4399999999999996e-07, "loss": 0.0117, "num_tokens": 274437522.0, "reward": 0.53125, "reward_std": 0.37082332372665405, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1313 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1995.0, "completions/mean_length": 1361.6015625, "completions/mean_terminated_length": 1178.10888671875, "completions/min_length": 450.0, "completions/min_terminated_length": 450.0, "epoch": 0.23314924479339943, "frac_reward_zero_std": 0.125, "grad_norm": 0.6664382219314575, "learning_rate": 3.435e-07, "loss": 0.0176, "num_tokens": 274623183.0, "reward": 0.5078125, "reward_std": 0.3886321485042572, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1314 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1385.3203125, "completions/mean_terminated_length": 1224.4757080078125, "completions/min_length": 427.0, "completions/min_terminated_length": 427.0, "epoch": 0.23332667953068512, "frac_reward_zero_std": 0.0, "grad_norm": 0.7015066146850586, "learning_rate": 3.43e-07, "loss": 0.0185, "num_tokens": 274811880.0, "reward": 0.515625, "reward_std": 0.426489919424057, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1315 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1358.8828125, "completions/mean_terminated_length": 1174.663330078125, "completions/min_length": 448.0, "completions/min_terminated_length": 448.0, "epoch": 0.23350411426797082, "frac_reward_zero_std": 0.0, "grad_norm": 0.6384735703468323, "learning_rate": 3.425e-07, "loss": 0.0266, "num_tokens": 274997193.0, "reward": 0.5078125, "reward_std": 0.43590834736824036, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1316 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1266.3046875, "completions/mean_terminated_length": 1005.7396240234375, "completions/min_length": 292.0, "completions/min_terminated_length": 292.0, "epoch": 0.2336815490052565, "frac_reward_zero_std": 0.25, "grad_norm": 0.6289550065994263, "learning_rate": 3.42e-07, "loss": 0.0355, "num_tokens": 275169312.0, "reward": 0.3359375, "reward_std": 0.28343653678894043, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1317 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1294.2265625, "completions/mean_terminated_length": 1010.5484008789062, "completions/min_length": 375.0, "completions/min_terminated_length": 375.0, "epoch": 0.2338589837425422, "frac_reward_zero_std": 0.0, "grad_norm": 0.6574151515960693, "learning_rate": 3.4150000000000003e-07, "loss": 0.0407, "num_tokens": 275345005.0, "reward": 0.359375, "reward_std": 0.36376726627349854, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 1318 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1252.8203125, "completions/mean_terminated_length": 1030.169921875, "completions/min_length": 391.0, "completions/min_terminated_length": 391.0, "epoch": 0.2340364184798279, "frac_reward_zero_std": 0.125, "grad_norm": 0.5312092900276184, "learning_rate": 3.41e-07, "loss": 0.0175, "num_tokens": 275515398.0, "reward": 0.40625, "reward_std": 0.34998178482055664, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1319 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1275.3125, "completions/mean_terminated_length": 1097.0, "completions/min_length": 404.0, "completions/min_terminated_length": 404.0, "epoch": 0.23421385321711358, "frac_reward_zero_std": 0.25, "grad_norm": 0.6018688082695007, "learning_rate": 3.405e-07, "loss": 0.0454, "num_tokens": 275688670.0, "reward": 0.3671875, "reward_std": 0.2843368649482727, "rewards/simpleverify_reward/mean": 0.3671875, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1320 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.53125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2020.0, "completions/mean_length": 1669.7265625, "completions/mean_terminated_length": 1241.0167236328125, "completions/min_length": 563.0, "completions/min_terminated_length": 563.0, "epoch": 0.23439128795439929, "frac_reward_zero_std": 0.125, "grad_norm": 0.5266081094741821, "learning_rate": 3.4000000000000003e-07, "loss": -0.0062, "num_tokens": 275917419.0, "reward": 0.2421875, "reward_std": 0.327860951423645, "rewards/simpleverify_reward/mean": 0.2421875, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 1321 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1682.4296875, "completions/mean_terminated_length": 1316.859375, "completions/min_length": 551.0, "completions/min_terminated_length": 551.0, "epoch": 0.23456872269168497, "frac_reward_zero_std": 0.375, "grad_norm": 0.4508037269115448, "learning_rate": 3.395e-07, "loss": 0.0041, "num_tokens": 276147794.0, "reward": 0.28125, "reward_std": 0.27132564783096313, "rewards/simpleverify_reward/mean": 0.28125, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 1322 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.546875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1688.1953125, "completions/mean_terminated_length": 1253.9482421875, "completions/min_length": 497.0, "completions/min_terminated_length": 497.0, "epoch": 0.23474615742897065, "frac_reward_zero_std": 0.25, "grad_norm": 0.4926084578037262, "learning_rate": 3.39e-07, "loss": -0.0108, "num_tokens": 276378907.0, "reward": 0.21875, "reward_std": 0.2978322207927704, "rewards/simpleverify_reward/mean": 0.21875, "rewards/simpleverify_reward/std": 0.41502299904823303, "step": 1323 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1686.2578125, "completions/mean_terminated_length": 1263.203369140625, "completions/min_length": 620.0, "completions/min_terminated_length": 620.0, "epoch": 0.23492359216625636, "frac_reward_zero_std": 0.375, "grad_norm": 0.4908566474914551, "learning_rate": 3.385e-07, "loss": -0.0009, "num_tokens": 276609772.0, "reward": 0.25, "reward_std": 0.25594252347946167, "rewards/simpleverify_reward/mean": 0.25, "rewards/simpleverify_reward/std": 0.434714138507843, "step": 1324 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1418.359375, "completions/mean_terminated_length": 1250.03955078125, "completions/min_length": 727.0, "completions/min_terminated_length": 727.0, "epoch": 0.23510102690354204, "frac_reward_zero_std": 0.5, "grad_norm": 0.3994861841201782, "learning_rate": 3.38e-07, "loss": 0.0222, "num_tokens": 276803082.0, "reward": 0.6875, "reward_std": 0.2110065221786499, "rewards/simpleverify_reward/mean": 0.6875, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 1325 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1982.0, "completions/mean_length": 1420.484375, "completions/mean_terminated_length": 1283.028564453125, "completions/min_length": 653.0, "completions/min_terminated_length": 653.0, "epoch": 0.23527846164082775, "frac_reward_zero_std": 0.375, "grad_norm": 0.48038092255592346, "learning_rate": 3.375e-07, "loss": 0.0191, "num_tokens": 276996664.0, "reward": 0.6328125, "reward_std": 0.2669360339641571, "rewards/simpleverify_reward/mean": 0.6328125, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1326 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1428.265625, "completions/mean_terminated_length": 1254.739990234375, "completions/min_length": 686.0, "completions/min_terminated_length": 686.0, "epoch": 0.23545589637811343, "frac_reward_zero_std": 0.375, "grad_norm": 0.530302107334137, "learning_rate": 3.37e-07, "loss": 0.0408, "num_tokens": 277191242.0, "reward": 0.6796875, "reward_std": 0.24622182548046112, "rewards/simpleverify_reward/mean": 0.6796875, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 1327 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1408.9375, "completions/mean_terminated_length": 1297.541259765625, "completions/min_length": 675.0, "completions/min_terminated_length": 675.0, "epoch": 0.2356333311153991, "frac_reward_zero_std": 0.25, "grad_norm": 0.5197821855545044, "learning_rate": 3.3650000000000003e-07, "loss": 0.0098, "num_tokens": 277383346.0, "reward": 0.7109375, "reward_std": 0.3083813488483429, "rewards/simpleverify_reward/mean": 0.7109375, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 1328 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1327.1484375, "completions/mean_terminated_length": 1066.4149169921875, "completions/min_length": 434.0, "completions/min_terminated_length": 434.0, "epoch": 0.23581076585268482, "frac_reward_zero_std": 0.125, "grad_norm": 0.7193008661270142, "learning_rate": 3.36e-07, "loss": -0.0039, "num_tokens": 277572069.0, "reward": 0.46875, "reward_std": 0.29270508885383606, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1329 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1345.8359375, "completions/mean_terminated_length": 1149.22998046875, "completions/min_length": 527.0, "completions/min_terminated_length": 527.0, "epoch": 0.2359882005899705, "frac_reward_zero_std": 0.25, "grad_norm": 0.5984018445014954, "learning_rate": 3.355e-07, "loss": 0.0213, "num_tokens": 277763184.0, "reward": 0.46875, "reward_std": 0.24933473765850067, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1330 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1332.7578125, "completions/mean_terminated_length": 1052.8804931640625, "completions/min_length": 480.0, "completions/min_terminated_length": 480.0, "epoch": 0.2361656353272562, "frac_reward_zero_std": 0.375, "grad_norm": 0.5263649821281433, "learning_rate": 3.35e-07, "loss": 0.0154, "num_tokens": 277952625.0, "reward": 0.46875, "reward_std": 0.21542394161224365, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1331 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1994.0, "completions/mean_length": 1325.5703125, "completions/mean_terminated_length": 1158.8558349609375, "completions/min_length": 514.0, "completions/min_terminated_length": 514.0, "epoch": 0.2363430700645419, "frac_reward_zero_std": 0.375, "grad_norm": 0.5391342043876648, "learning_rate": 3.345e-07, "loss": 0.0157, "num_tokens": 278141146.0, "reward": 0.5234375, "reward_std": 0.24600867927074432, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1332 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1335.65625, "completions/mean_terminated_length": 1162.75732421875, "completions/min_length": 76.0, "completions/min_terminated_length": 76.0, "epoch": 0.23652050480182757, "frac_reward_zero_std": 0.125, "grad_norm": 0.7081823348999023, "learning_rate": 3.34e-07, "loss": -0.0052, "num_tokens": 278324158.0, "reward": 0.4453125, "reward_std": 0.36382144689559937, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1333 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1335.421875, "completions/mean_terminated_length": 1170.9808349609375, "completions/min_length": 76.0, "completions/min_terminated_length": 76.0, "epoch": 0.23669793953911328, "frac_reward_zero_std": 0.0, "grad_norm": 0.7030953764915466, "learning_rate": 3.335e-07, "loss": 0.0096, "num_tokens": 278507140.0, "reward": 0.4609375, "reward_std": 0.40036705136299133, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1334 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1963.0, "completions/mean_length": 1303.328125, "completions/mean_terminated_length": 1157.177490234375, "completions/min_length": 409.0, "completions/min_terminated_length": 409.0, "epoch": 0.23687537427639896, "frac_reward_zero_std": 0.0, "grad_norm": 0.7522503733634949, "learning_rate": 3.33e-07, "loss": 0.0001, "num_tokens": 278686014.0, "reward": 0.5859375, "reward_std": 0.3886321485042572, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1335 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1974.0, "completions/mean_length": 1331.2421875, "completions/mean_terminated_length": 1190.570068359375, "completions/min_length": 423.0, "completions/min_terminated_length": 423.0, "epoch": 0.23705280901368467, "frac_reward_zero_std": 0.0, "grad_norm": 0.6641578078269958, "learning_rate": 3.325e-07, "loss": 0.0113, "num_tokens": 278868461.0, "reward": 0.6015625, "reward_std": 0.38421475887298584, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1336 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.46875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1609.7421875, "completions/mean_terminated_length": 1223.0440673828125, "completions/min_length": 639.0, "completions/min_terminated_length": 639.0, "epoch": 0.23723024375097035, "frac_reward_zero_std": 0.375, "grad_norm": 0.6277766823768616, "learning_rate": 3.32e-07, "loss": 0.0125, "num_tokens": 279086540.0, "reward": 0.34375, "reward_std": 0.24933473765850067, "rewards/simpleverify_reward/mean": 0.34375, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 1337 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4765625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1971.0, "completions/mean_length": 1583.9296875, "completions/mean_terminated_length": 1161.4178466796875, "completions/min_length": 560.0, "completions/min_terminated_length": 560.0, "epoch": 0.23740767848825603, "frac_reward_zero_std": 0.5, "grad_norm": 0.4500449597835541, "learning_rate": 3.315e-07, "loss": 0.0189, "num_tokens": 279301315.0, "reward": 0.3515625, "reward_std": 0.19738000631332397, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1338 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1576.828125, "completions/mean_terminated_length": 1210.361083984375, "completions/min_length": 571.0, "completions/min_terminated_length": 571.0, "epoch": 0.23758511322554174, "frac_reward_zero_std": 0.375, "grad_norm": 0.5788394212722778, "learning_rate": 3.31e-07, "loss": 0.0057, "num_tokens": 279515181.0, "reward": 0.390625, "reward_std": 0.26083454489707947, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1339 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1547.9296875, "completions/mean_terminated_length": 1171.1644287109375, "completions/min_length": 566.0, "completions/min_terminated_length": 566.0, "epoch": 0.23776254796282742, "frac_reward_zero_std": 0.125, "grad_norm": 0.6508961319923401, "learning_rate": 3.305e-07, "loss": 0.0322, "num_tokens": 279725348.0, "reward": 0.3515625, "reward_std": 0.3133781850337982, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1340 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1475.6015625, "completions/mean_terminated_length": 1215.4205322265625, "completions/min_length": 605.0, "completions/min_terminated_length": 605.0, "epoch": 0.23793998270011313, "frac_reward_zero_std": 0.0, "grad_norm": 0.662151575088501, "learning_rate": 3.3e-07, "loss": 0.027, "num_tokens": 279930049.0, "reward": 0.4296875, "reward_std": 0.4082289934158325, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1341 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1485.125, "completions/mean_terminated_length": 1219.862060546875, "completions/min_length": 623.0, "completions/min_terminated_length": 623.0, "epoch": 0.2381174174373988, "frac_reward_zero_std": 0.0, "grad_norm": 0.5927581191062927, "learning_rate": 3.295e-07, "loss": 0.0319, "num_tokens": 280135969.0, "reward": 0.4609375, "reward_std": 0.3896957039833069, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1342 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1499.8125, "completions/mean_terminated_length": 1301.5318603515625, "completions/min_length": 632.0, "completions/min_terminated_length": 632.0, "epoch": 0.2382948521746845, "frac_reward_zero_std": 0.125, "grad_norm": 0.5909737348556519, "learning_rate": 3.29e-07, "loss": 0.0307, "num_tokens": 280343769.0, "reward": 0.4453125, "reward_std": 0.3978690505027771, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1343 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1531.3359375, "completions/mean_terminated_length": 1251.216796875, "completions/min_length": 661.0, "completions/min_terminated_length": 661.0, "epoch": 0.2384722869119702, "frac_reward_zero_std": 0.25, "grad_norm": 0.5410571694374084, "learning_rate": 3.285e-07, "loss": 0.0391, "num_tokens": 280555604.0, "reward": 0.390625, "reward_std": 0.37901920080184937, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1344 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1982.0, "completions/mean_length": 1419.4296875, "completions/mean_terminated_length": 1309.8623046875, "completions/min_length": 470.0, "completions/min_terminated_length": 470.0, "epoch": 0.23864972164925588, "frac_reward_zero_std": 0.0, "grad_norm": 0.641847550868988, "learning_rate": 3.28e-07, "loss": 0.0137, "num_tokens": 280746923.0, "reward": 0.5859375, "reward_std": 0.40380212664604187, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1345 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1429.0390625, "completions/mean_terminated_length": 1334.2432861328125, "completions/min_length": 493.0, "completions/min_terminated_length": 493.0, "epoch": 0.23882715638654156, "frac_reward_zero_std": 0.0, "grad_norm": 0.5651304721832275, "learning_rate": 3.275e-07, "loss": 0.0077, "num_tokens": 280939472.0, "reward": 0.5703125, "reward_std": 0.38328149914741516, "rewards/simpleverify_reward/mean": 0.5703125, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1346 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1985.0, "completions/mean_length": 1472.0390625, "completions/mean_terminated_length": 1359.0, "completions/min_length": 460.0, "completions/min_terminated_length": 460.0, "epoch": 0.23900459112382727, "frac_reward_zero_std": 0.125, "grad_norm": 0.5837796926498413, "learning_rate": 3.27e-07, "loss": 0.0187, "num_tokens": 281137525.0, "reward": 0.6015625, "reward_std": 0.3677142560482025, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1347 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1960.0, "completions/mean_length": 1452.0703125, "completions/mean_terminated_length": 1285.2099609375, "completions/min_length": 487.0, "completions/min_terminated_length": 487.0, "epoch": 0.23918202586111295, "frac_reward_zero_std": 0.125, "grad_norm": 0.5409320592880249, "learning_rate": 3.265e-07, "loss": 0.0181, "num_tokens": 281333022.0, "reward": 0.546875, "reward_std": 0.37562090158462524, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1348 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1502.1015625, "completions/mean_terminated_length": 1128.5921630859375, "completions/min_length": 280.0, "completions/min_terminated_length": 280.0, "epoch": 0.23935946059839866, "frac_reward_zero_std": 0.375, "grad_norm": 0.625049352645874, "learning_rate": 3.26e-07, "loss": 0.0281, "num_tokens": 281541131.0, "reward": 0.4765625, "reward_std": 0.259880006313324, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1349 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1487.0625, "completions/mean_terminated_length": 1150.5, "completions/min_length": 1.0, "completions/min_terminated_length": 1.0, "epoch": 0.23953689533568434, "frac_reward_zero_std": 0.375, "grad_norm": 0.6807450652122498, "learning_rate": 3.255e-07, "loss": 0.0257, "num_tokens": 281747315.0, "reward": 0.53125, "reward_std": 0.23456303775310516, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1350 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1929.0, "completions/mean_length": 1503.8203125, "completions/mean_terminated_length": 1093.8218994140625, "completions/min_length": 292.0, "completions/min_terminated_length": 292.0, "epoch": 0.23971433007297002, "frac_reward_zero_std": 0.375, "grad_norm": 0.5976566672325134, "learning_rate": 3.25e-07, "loss": 0.0161, "num_tokens": 281955644.0, "reward": 0.4921875, "reward_std": 0.25328171253204346, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1351 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1472.4609375, "completions/mean_terminated_length": 1149.5975341796875, "completions/min_length": 266.0, "completions/min_terminated_length": 266.0, "epoch": 0.23989176481025573, "frac_reward_zero_std": 0.375, "grad_norm": 0.46662718057632446, "learning_rate": 3.245e-07, "loss": 0.0134, "num_tokens": 282159959.0, "reward": 0.5625, "reward_std": 0.2288651019334793, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1352 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1385.9921875, "completions/mean_terminated_length": 1106.477783203125, "completions/min_length": 465.0, "completions/min_terminated_length": 465.0, "epoch": 0.2400691995475414, "frac_reward_zero_std": 0.5, "grad_norm": 0.44167831540107727, "learning_rate": 3.24e-07, "loss": 0.0294, "num_tokens": 282344966.0, "reward": 0.5234375, "reward_std": 0.24803203344345093, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1353 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1400.7421875, "completions/mean_terminated_length": 1184.9896240234375, "completions/min_length": 427.0, "completions/min_terminated_length": 427.0, "epoch": 0.24024663428482712, "frac_reward_zero_std": 0.5, "grad_norm": 0.45962584018707275, "learning_rate": 3.235e-07, "loss": 0.0277, "num_tokens": 282531861.0, "reward": 0.546875, "reward_std": 0.24433404207229614, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1354 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1401.5, "completions/mean_terminated_length": 1167.6595458984375, "completions/min_length": 428.0, "completions/min_terminated_length": 428.0, "epoch": 0.2404240690221128, "frac_reward_zero_std": 0.25, "grad_norm": 0.521867036819458, "learning_rate": 3.23e-07, "loss": 0.0298, "num_tokens": 282718853.0, "reward": 0.515625, "reward_std": 0.3393065631389618, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1355 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1353.1328125, "completions/mean_terminated_length": 1121.510498046875, "completions/min_length": 450.0, "completions/min_terminated_length": 450.0, "epoch": 0.24060150375939848, "frac_reward_zero_std": 0.375, "grad_norm": 0.5153634548187256, "learning_rate": 3.225e-07, "loss": 0.0225, "num_tokens": 282899654.0, "reward": 0.5625, "reward_std": 0.286581426858902, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1356 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1991.0, "completions/mean_length": 1363.9765625, "completions/mean_terminated_length": 1075.166748046875, "completions/min_length": 355.0, "completions/min_terminated_length": 355.0, "epoch": 0.2407789384966842, "frac_reward_zero_std": 0.25, "grad_norm": 0.6134834885597229, "learning_rate": 3.22e-07, "loss": 0.0248, "num_tokens": 283089651.0, "reward": 0.4453125, "reward_std": 0.3391212224960327, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1357 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1345.234375, "completions/mean_terminated_length": 1048.5111083984375, "completions/min_length": 330.0, "completions/min_terminated_length": 330.0, "epoch": 0.24095637323396987, "frac_reward_zero_std": 0.25, "grad_norm": 0.6810173988342285, "learning_rate": 3.215e-07, "loss": 0.018, "num_tokens": 283277249.0, "reward": 0.484375, "reward_std": 0.3155868649482727, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1358 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1341.0390625, "completions/mean_terminated_length": 1095.4632568359375, "completions/min_length": 379.0, "completions/min_terminated_length": 379.0, "epoch": 0.24113380797125558, "frac_reward_zero_std": 0.25, "grad_norm": 0.7088934779167175, "learning_rate": 3.21e-07, "loss": 0.0203, "num_tokens": 283464310.0, "reward": 0.484375, "reward_std": 0.3127670884132385, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1359 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2010.0, "completions/mean_length": 1359.921875, "completions/mean_terminated_length": 1047.1591796875, "completions/min_length": 383.0, "completions/min_terminated_length": 383.0, "epoch": 0.24131124270854126, "frac_reward_zero_std": 0.25, "grad_norm": 0.6295799016952515, "learning_rate": 3.205e-07, "loss": 0.0159, "num_tokens": 283653788.0, "reward": 0.4765625, "reward_std": 0.3290822207927704, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1360 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1574.4453125, "completions/mean_terminated_length": 1194.267578125, "completions/min_length": 512.0, "completions/min_terminated_length": 512.0, "epoch": 0.24148867744582694, "frac_reward_zero_std": 0.25, "grad_norm": 0.5877003073692322, "learning_rate": 3.2e-07, "loss": 0.0382, "num_tokens": 283865701.0, "reward": 0.3359375, "reward_std": 0.3369705379009247, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1361 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1524.9765625, "completions/mean_terminated_length": 1200.5697021484375, "completions/min_length": 562.0, "completions/min_terminated_length": 562.0, "epoch": 0.24166611218311265, "frac_reward_zero_std": 0.25, "grad_norm": 0.6098566651344299, "learning_rate": 3.1949999999999997e-07, "loss": 0.034, "num_tokens": 284071282.0, "reward": 0.328125, "reward_std": 0.3463625907897949, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1362 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1997.0, "completions/mean_length": 1520.859375, "completions/mean_terminated_length": 1136.189208984375, "completions/min_length": 507.0, "completions/min_terminated_length": 507.0, "epoch": 0.24184354692039833, "frac_reward_zero_std": 0.25, "grad_norm": 0.5682264566421509, "learning_rate": 3.19e-07, "loss": 0.0139, "num_tokens": 284276336.0, "reward": 0.390625, "reward_std": 0.31673625111579895, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1363 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2004.0, "completions/mean_length": 1502.9375, "completions/mean_terminated_length": 1153.5384521484375, "completions/min_length": 567.0, "completions/min_terminated_length": 567.0, "epoch": 0.24202098165768404, "frac_reward_zero_std": 0.25, "grad_norm": 0.5855401158332825, "learning_rate": 3.185e-07, "loss": 0.0312, "num_tokens": 284479096.0, "reward": 0.3359375, "reward_std": 0.3311648368835449, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1364 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1245.4921875, "completions/mean_terminated_length": 1096.879638671875, "completions/min_length": 609.0, "completions/min_terminated_length": 609.0, "epoch": 0.24219841639496972, "frac_reward_zero_std": 0.25, "grad_norm": 0.5341880321502686, "learning_rate": 3.18e-07, "loss": 0.0272, "num_tokens": 284649095.0, "reward": 0.6015625, "reward_std": 0.3248779773712158, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1365 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2001.0, "completions/mean_length": 1224.9921875, "completions/mean_terminated_length": 1081.5321044921875, "completions/min_length": 623.0, "completions/min_terminated_length": 623.0, "epoch": 0.2423758511322554, "frac_reward_zero_std": 0.125, "grad_norm": 0.6780824065208435, "learning_rate": 3.175e-07, "loss": 0.03, "num_tokens": 284816470.0, "reward": 0.6015625, "reward_std": 0.32171472907066345, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1366 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1257.6640625, "completions/mean_terminated_length": 1160.605224609375, "completions/min_length": 619.0, "completions/min_terminated_length": 619.0, "epoch": 0.2425532858695411, "frac_reward_zero_std": 0.125, "grad_norm": 0.612825870513916, "learning_rate": 3.17e-07, "loss": 0.0456, "num_tokens": 284988027.0, "reward": 0.578125, "reward_std": 0.3758559823036194, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1367 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2010.0, "completions/mean_length": 1219.6796875, "completions/mean_terminated_length": 1126.04345703125, "completions/min_length": 619.0, "completions/min_terminated_length": 619.0, "epoch": 0.2427307206068268, "frac_reward_zero_std": 0.25, "grad_norm": 0.5536546111106873, "learning_rate": 3.165e-07, "loss": 0.02, "num_tokens": 285154722.0, "reward": 0.703125, "reward_std": 0.2997780442237854, "rewards/simpleverify_reward/mean": 0.703125, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 1368 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1702.4375, "completions/mean_terminated_length": 1377.8182373046875, "completions/min_length": 874.0, "completions/min_terminated_length": 874.0, "epoch": 0.2429081553441125, "frac_reward_zero_std": 0.25, "grad_norm": 0.5324143171310425, "learning_rate": 3.1599999999999997e-07, "loss": 0.0338, "num_tokens": 285383610.0, "reward": 0.4375, "reward_std": 0.2837296426296234, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1369 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1687.7109375, "completions/mean_terminated_length": 1379.6376953125, "completions/min_length": 865.0, "completions/min_terminated_length": 865.0, "epoch": 0.24308559008139818, "frac_reward_zero_std": 0.25, "grad_norm": 0.5336506366729736, "learning_rate": 3.155e-07, "loss": 0.0388, "num_tokens": 285610613.0, "reward": 0.3984375, "reward_std": 0.32171475887298584, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1370 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2016.0, "completions/mean_length": 1704.09375, "completions/mean_terminated_length": 1410.029052734375, "completions/min_length": 720.0, "completions/min_terminated_length": 720.0, "epoch": 0.24326302481868387, "frac_reward_zero_std": 0.25, "grad_norm": 0.5261699557304382, "learning_rate": 3.15e-07, "loss": 0.0122, "num_tokens": 285839713.0, "reward": 0.4375, "reward_std": 0.2948821485042572, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1371 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1667.734375, "completions/mean_terminated_length": 1381.23291015625, "completions/min_length": 819.0, "completions/min_terminated_length": 819.0, "epoch": 0.24344045955596957, "frac_reward_zero_std": 0.375, "grad_norm": 0.4553759694099426, "learning_rate": 3.1449999999999996e-07, "loss": 0.0112, "num_tokens": 286064159.0, "reward": 0.4375, "reward_std": 0.2576674520969391, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1372 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1223.578125, "completions/mean_terminated_length": 1033.326904296875, "completions/min_length": 396.0, "completions/min_terminated_length": 396.0, "epoch": 0.24361789429325525, "frac_reward_zero_std": 0.375, "grad_norm": 0.49309903383255005, "learning_rate": 3.14e-07, "loss": -0.0012, "num_tokens": 286234953.0, "reward": 0.5859375, "reward_std": 0.24052387475967407, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1373 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1987.0, "completions/mean_length": 1249.5625, "completions/mean_terminated_length": 1055.7669677734375, "completions/min_length": 448.0, "completions/min_terminated_length": 448.0, "epoch": 0.24379532903054096, "frac_reward_zero_std": 0.375, "grad_norm": 0.4869302213191986, "learning_rate": 3.135e-07, "loss": 0.0006, "num_tokens": 286409073.0, "reward": 0.5546875, "reward_std": 0.23677173256874084, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1374 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1235.9296875, "completions/mean_terminated_length": 1076.5513916015625, "completions/min_length": 400.0, "completions/min_terminated_length": 400.0, "epoch": 0.24397276376782664, "frac_reward_zero_std": 0.25, "grad_norm": 0.5722882747650146, "learning_rate": 3.13e-07, "loss": 0.0032, "num_tokens": 286581448.0, "reward": 0.5625, "reward_std": 0.2920398414134979, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1375 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1237.5390625, "completions/mean_terminated_length": 1087.4537353515625, "completions/min_length": 433.0, "completions/min_terminated_length": 433.0, "epoch": 0.24415019850511233, "frac_reward_zero_std": 0.25, "grad_norm": 0.5421512722969055, "learning_rate": 3.1249999999999997e-07, "loss": 0.0099, "num_tokens": 286754029.0, "reward": 0.59375, "reward_std": 0.3182518780231476, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1376 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1437.875, "completions/mean_terminated_length": 1160.5455322265625, "completions/min_length": 544.0, "completions/min_terminated_length": 544.0, "epoch": 0.24432763324239803, "frac_reward_zero_std": 0.25, "grad_norm": 0.5168169736862183, "learning_rate": 3.12e-07, "loss": 0.0094, "num_tokens": 286948813.0, "reward": 0.4765625, "reward_std": 0.33492082357406616, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1377 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1499.0703125, "completions/mean_terminated_length": 1085.4931640625, "completions/min_length": 565.0, "completions/min_terminated_length": 565.0, "epoch": 0.24450506797968372, "frac_reward_zero_std": 0.125, "grad_norm": 0.5744701027870178, "learning_rate": 3.115e-07, "loss": 0.0176, "num_tokens": 287151430.0, "reward": 0.4453125, "reward_std": 0.34902724623680115, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1378 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1424.0, "completions/mean_terminated_length": 1160.5333251953125, "completions/min_length": 554.0, "completions/min_terminated_length": 554.0, "epoch": 0.24468250271696942, "frac_reward_zero_std": 0.25, "grad_norm": 0.5250328779220581, "learning_rate": 3.1099999999999997e-07, "loss": 0.0197, "num_tokens": 287344438.0, "reward": 0.5078125, "reward_std": 0.32501479983329773, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1379 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2009.0, "completions/mean_length": 1454.4765625, "completions/mean_terminated_length": 1143.5833740234375, "completions/min_length": 538.0, "completions/min_terminated_length": 538.0, "epoch": 0.2448599374542551, "frac_reward_zero_std": 0.375, "grad_norm": 0.47696250677108765, "learning_rate": 3.105e-07, "loss": 0.0233, "num_tokens": 287541347.0, "reward": 0.4453125, "reward_std": 0.28322336077690125, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1380 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2004.0, "completions/mean_length": 1285.28125, "completions/mean_terminated_length": 1090.86279296875, "completions/min_length": 355.0, "completions/min_terminated_length": 355.0, "epoch": 0.2450373721915408, "frac_reward_zero_std": 0.125, "grad_norm": 0.8504617810249329, "learning_rate": 3.1e-07, "loss": 0.0193, "num_tokens": 287721591.0, "reward": 0.46875, "reward_std": 0.31116947531700134, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1381 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1293.2890625, "completions/mean_terminated_length": 1081.969970703125, "completions/min_length": 383.0, "completions/min_terminated_length": 383.0, "epoch": 0.2452148069288265, "frac_reward_zero_std": 0.5, "grad_norm": 0.511267364025116, "learning_rate": 3.0949999999999996e-07, "loss": 0.0129, "num_tokens": 287902860.0, "reward": 0.4921875, "reward_std": 0.21809419989585876, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1382 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2018.0, "completions/mean_length": 1320.9609375, "completions/mean_terminated_length": 1098.39794921875, "completions/min_length": 386.0, "completions/min_terminated_length": 386.0, "epoch": 0.24539224166611218, "frac_reward_zero_std": 0.25, "grad_norm": 0.590827226638794, "learning_rate": 3.09e-07, "loss": 0.0049, "num_tokens": 288087671.0, "reward": 0.4296875, "reward_std": 0.28367161750793457, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1383 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1975.0, "completions/mean_length": 1277.9921875, "completions/mean_terminated_length": 1062.3900146484375, "completions/min_length": 369.0, "completions/min_terminated_length": 369.0, "epoch": 0.24556967640339789, "frac_reward_zero_std": 0.375, "grad_norm": 0.6758449077606201, "learning_rate": 3.085e-07, "loss": -0.0104, "num_tokens": 288266982.0, "reward": 0.4296875, "reward_std": 0.2664783000946045, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1384 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1458.0703125, "completions/mean_terminated_length": 1253.1474609375, "completions/min_length": 419.0, "completions/min_terminated_length": 419.0, "epoch": 0.24574711114068357, "frac_reward_zero_std": 0.25, "grad_norm": 0.5578358769416809, "learning_rate": 3.08e-07, "loss": 0.0053, "num_tokens": 288465743.0, "reward": 0.5859375, "reward_std": 0.311010479927063, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1385 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2020.0, "completions/mean_length": 1498.875, "completions/mean_terminated_length": 1275.6043701171875, "completions/min_length": 431.0, "completions/min_terminated_length": 431.0, "epoch": 0.24592454587796925, "frac_reward_zero_std": 0.125, "grad_norm": 0.6483157277107239, "learning_rate": 3.0749999999999997e-07, "loss": 0.0115, "num_tokens": 288669727.0, "reward": 0.578125, "reward_std": 0.3746018409729004, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1386 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1505.0546875, "completions/mean_terminated_length": 1300.720458984375, "completions/min_length": 425.0, "completions/min_terminated_length": 425.0, "epoch": 0.24610198061525496, "frac_reward_zero_std": 0.125, "grad_norm": 0.602230429649353, "learning_rate": 3.07e-07, "loss": 0.0238, "num_tokens": 288874502.0, "reward": 0.5859375, "reward_std": 0.3512042760848999, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1387 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1499.609375, "completions/mean_terminated_length": 1276.637451171875, "completions/min_length": 421.0, "completions/min_terminated_length": 421.0, "epoch": 0.24627941535254064, "frac_reward_zero_std": 0.125, "grad_norm": 0.6273670792579651, "learning_rate": 3.065e-07, "loss": 0.0284, "num_tokens": 289078580.0, "reward": 0.578125, "reward_std": 0.3873332738876343, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1388 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1554.8671875, "completions/mean_terminated_length": 1228.2467041015625, "completions/min_length": 506.0, "completions/min_terminated_length": 506.0, "epoch": 0.24645685008982635, "frac_reward_zero_std": 0.5, "grad_norm": 0.43503493070602417, "learning_rate": 3.0599999999999996e-07, "loss": -0.002, "num_tokens": 289291811.0, "reward": 0.3359375, "reward_std": 0.23017343878746033, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1389 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1998.0, "completions/mean_length": 1519.734375, "completions/mean_terminated_length": 1202.7750244140625, "completions/min_length": 492.0, "completions/min_terminated_length": 492.0, "epoch": 0.24663428482711203, "frac_reward_zero_std": 0.5, "grad_norm": 0.4613286554813385, "learning_rate": 3.055e-07, "loss": -0.0076, "num_tokens": 289500545.0, "reward": 0.3046875, "reward_std": 0.21103432774543762, "rewards/simpleverify_reward/mean": 0.3046875, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 1390 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2003.0, "completions/mean_length": 1552.46875, "completions/mean_terminated_length": 1202.2933349609375, "completions/min_length": 546.0, "completions/min_terminated_length": 546.0, "epoch": 0.2468117195643977, "frac_reward_zero_std": 0.5, "grad_norm": 0.43656453490257263, "learning_rate": 3.05e-07, "loss": 0.0163, "num_tokens": 289713469.0, "reward": 0.3046875, "reward_std": 0.2343776822090149, "rewards/simpleverify_reward/mean": 0.3046875, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 1391 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1992.0, "completions/mean_length": 1522.1328125, "completions/mean_terminated_length": 1274.310302734375, "completions/min_length": 499.0, "completions/min_terminated_length": 499.0, "epoch": 0.24698915430168342, "frac_reward_zero_std": 0.25, "grad_norm": 0.6185822486877441, "learning_rate": 3.0449999999999995e-07, "loss": 0.0064, "num_tokens": 289922510.0, "reward": 0.3359375, "reward_std": 0.2971172332763672, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1392 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1825.0, "completions/mean_length": 1413.8359375, "completions/mean_terminated_length": 1007.3204956054688, "completions/min_length": 505.0, "completions/min_terminated_length": 505.0, "epoch": 0.2471665890389691, "frac_reward_zero_std": 0.625, "grad_norm": 0.3996567130088806, "learning_rate": 3.0399999999999997e-07, "loss": -0.0045, "num_tokens": 290115001.0, "reward": 0.203125, "reward_std": 0.1379890739917755, "rewards/simpleverify_reward/mean": 0.203125, "rewards/simpleverify_reward/std": 0.40390563011169434, "step": 1393 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1969.0, "completions/mean_length": 1398.9609375, "completions/mean_terminated_length": 1009.5375366210938, "completions/min_length": 499.0, "completions/min_terminated_length": 499.0, "epoch": 0.2473440237762548, "frac_reward_zero_std": 0.625, "grad_norm": 0.36569809913635254, "learning_rate": 3.035e-07, "loss": -0.0006, "num_tokens": 290305588.0, "reward": 0.21875, "reward_std": 0.11840169876813889, "rewards/simpleverify_reward/mean": 0.21875, "rewards/simpleverify_reward/std": 0.41502299904823303, "step": 1394 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1403.5546875, "completions/mean_terminated_length": 1016.8875122070312, "completions/min_length": 505.0, "completions/min_terminated_length": 505.0, "epoch": 0.2475214585135405, "frac_reward_zero_std": 0.625, "grad_norm": 0.46881771087646484, "learning_rate": 3.03e-07, "loss": 0.0083, "num_tokens": 290496763.0, "reward": 0.2421875, "reward_std": 0.12984731793403625, "rewards/simpleverify_reward/mean": 0.2421875, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 1395 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1952.0, "completions/mean_length": 1428.234375, "completions/mean_terminated_length": 1030.94873046875, "completions/min_length": 449.0, "completions/min_terminated_length": 449.0, "epoch": 0.24769889325082617, "frac_reward_zero_std": 0.625, "grad_norm": 0.4852975010871887, "learning_rate": 3.0249999999999996e-07, "loss": 0.0069, "num_tokens": 290691097.0, "reward": 0.21875, "reward_std": 0.1379890739917755, "rewards/simpleverify_reward/mean": 0.21875, "rewards/simpleverify_reward/std": 0.41502299904823303, "step": 1396 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1433.296875, "completions/mean_terminated_length": 1153.8863525390625, "completions/min_length": 648.0, "completions/min_terminated_length": 648.0, "epoch": 0.24787632798811188, "frac_reward_zero_std": 0.25, "grad_norm": 0.596284806728363, "learning_rate": 3.02e-07, "loss": 0.0102, "num_tokens": 290882495.0, "reward": 0.3671875, "reward_std": 0.3182796835899353, "rewards/simpleverify_reward/mean": 0.3671875, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1397 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1973.0, "completions/mean_length": 1399.015625, "completions/mean_terminated_length": 1104.022705078125, "completions/min_length": 625.0, "completions/min_terminated_length": 625.0, "epoch": 0.24805376272539756, "frac_reward_zero_std": 0.375, "grad_norm": 0.5524886250495911, "learning_rate": 3.015e-07, "loss": -0.015, "num_tokens": 291069505.0, "reward": 0.40625, "reward_std": 0.2978322207927704, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1398 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1408.640625, "completions/mean_terminated_length": 1128.471923828125, "completions/min_length": 644.0, "completions/min_terminated_length": 644.0, "epoch": 0.24823119746268327, "frac_reward_zero_std": 0.375, "grad_norm": 0.5441040396690369, "learning_rate": 3.0099999999999996e-07, "loss": 0.0115, "num_tokens": 291257747.0, "reward": 0.375, "reward_std": 0.2806389033794403, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 1399 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1370.03125, "completions/mean_terminated_length": 1124.8084716796875, "completions/min_length": 602.0, "completions/min_terminated_length": 602.0, "epoch": 0.24840863219996895, "frac_reward_zero_std": 0.25, "grad_norm": 0.6409869194030762, "learning_rate": 3.0049999999999997e-07, "loss": 0.0176, "num_tokens": 291441047.0, "reward": 0.421875, "reward_std": 0.31071737408638, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1400 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1910.0, "completions/mean_length": 1094.4140625, "completions/mean_terminated_length": 938.3726806640625, "completions/min_length": 348.0, "completions/min_terminated_length": 348.0, "epoch": 0.24858606693725463, "frac_reward_zero_std": 0.125, "grad_norm": 0.5826771259307861, "learning_rate": 3e-07, "loss": 0.017, "num_tokens": 291591084.0, "reward": 0.671875, "reward_std": 0.2977283000946045, "rewards/simpleverify_reward/mean": 0.671875, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1401 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1074.9921875, "completions/mean_terminated_length": 935.9910888671875, "completions/min_length": 347.0, "completions/min_terminated_length": 347.0, "epoch": 0.24876350167454034, "frac_reward_zero_std": 0.375, "grad_norm": 0.6725035309791565, "learning_rate": 2.9949999999999995e-07, "loss": 0.015, "num_tokens": 291738635.0, "reward": 0.6484375, "reward_std": 0.2568970322608948, "rewards/simpleverify_reward/mean": 0.6484375, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1402 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1088.59375, "completions/mean_terminated_length": 970.7719116210938, "completions/min_length": 317.0, "completions/min_terminated_length": 317.0, "epoch": 0.24894093641182602, "frac_reward_zero_std": 0.375, "grad_norm": 0.5698011517524719, "learning_rate": 2.9899999999999996e-07, "loss": -0.0033, "num_tokens": 291887927.0, "reward": 0.6875, "reward_std": 0.22359731793403625, "rewards/simpleverify_reward/mean": 0.6875, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 1403 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2012.0, "completions/mean_length": 1064.8125, "completions/mean_terminated_length": 934.3009033203125, "completions/min_length": 367.0, "completions/min_terminated_length": 367.0, "epoch": 0.24911837114911173, "frac_reward_zero_std": 0.375, "grad_norm": 0.5422430634498596, "learning_rate": 2.985e-07, "loss": 0.0159, "num_tokens": 292034175.0, "reward": 0.6328125, "reward_std": 0.2664783000946045, "rewards/simpleverify_reward/mean": 0.6328125, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1404 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1414.859375, "completions/mean_terminated_length": 1059.682861328125, "completions/min_length": 302.0, "completions/min_terminated_length": 302.0, "epoch": 0.2492958058863974, "frac_reward_zero_std": 0.375, "grad_norm": 0.7280596494674683, "learning_rate": 2.98e-07, "loss": 0.0399, "num_tokens": 292225789.0, "reward": 0.5, "reward_std": 0.288735955953598, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 1405 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1999.0, "completions/mean_length": 1394.0390625, "completions/mean_terminated_length": 1085.8505859375, "completions/min_length": 306.0, "completions/min_terminated_length": 306.0, "epoch": 0.2494732406236831, "frac_reward_zero_std": 0.25, "grad_norm": 0.7182281017303467, "learning_rate": 2.9749999999999996e-07, "loss": 0.0422, "num_tokens": 292414738.0, "reward": 0.515625, "reward_std": 0.3354007303714752, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1406 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1451.7109375, "completions/mean_terminated_length": 1069.474365234375, "completions/min_length": 332.0, "completions/min_terminated_length": 332.0, "epoch": 0.2496506753609688, "frac_reward_zero_std": 0.25, "grad_norm": 0.7223165035247803, "learning_rate": 2.9699999999999997e-07, "loss": 0.0228, "num_tokens": 292611069.0, "reward": 0.40625, "reward_std": 0.3380298614501953, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1407 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1969.0, "completions/mean_length": 1391.9609375, "completions/mean_terminated_length": 1071.56982421875, "completions/min_length": 334.0, "completions/min_terminated_length": 334.0, "epoch": 0.24982811009825448, "frac_reward_zero_std": 0.25, "grad_norm": 0.6658913493156433, "learning_rate": 2.965e-07, "loss": 0.0343, "num_tokens": 292799752.0, "reward": 0.546875, "reward_std": 0.291130006313324, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1408 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1560.8984375, "completions/mean_terminated_length": 1216.6800537109375, "completions/min_length": 369.0, "completions/min_terminated_length": 369.0, "epoch": 0.25000554483554016, "frac_reward_zero_std": 0.0, "grad_norm": 0.8266129493713379, "learning_rate": 2.9599999999999995e-07, "loss": 0.038, "num_tokens": 293011323.0, "reward": 0.4296875, "reward_std": 0.41985994577407837, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1409 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1513.0390625, "completions/mean_terminated_length": 1251.779052734375, "completions/min_length": 336.0, "completions/min_terminated_length": 336.0, "epoch": 0.25018297957282587, "frac_reward_zero_std": 0.125, "grad_norm": 0.7195338010787964, "learning_rate": 2.9549999999999997e-07, "loss": 0.0415, "num_tokens": 293216768.0, "reward": 0.5234375, "reward_std": 0.4025310277938843, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1410 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1523.9921875, "completions/mean_terminated_length": 1209.5875244140625, "completions/min_length": 376.0, "completions/min_terminated_length": 376.0, "epoch": 0.2503604143101116, "frac_reward_zero_std": 0.0, "grad_norm": 0.7136026620864868, "learning_rate": 2.95e-07, "loss": 0.0529, "num_tokens": 293423615.0, "reward": 0.46875, "reward_std": 0.44450217485427856, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1411 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2011.0, "completions/mean_length": 1586.15625, "completions/mean_terminated_length": 1290.1025390625, "completions/min_length": 388.0, "completions/min_terminated_length": 388.0, "epoch": 0.25053784904739723, "frac_reward_zero_std": 0.125, "grad_norm": 0.6957118511199951, "learning_rate": 2.945e-07, "loss": 0.0285, "num_tokens": 293638419.0, "reward": 0.4765625, "reward_std": 0.39550137519836426, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1412 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1464.3984375, "completions/mean_terminated_length": 1169.1646728515625, "completions/min_length": 399.0, "completions/min_terminated_length": 399.0, "epoch": 0.25071528378468294, "frac_reward_zero_std": 0.0, "grad_norm": 0.5941152572631836, "learning_rate": 2.9399999999999996e-07, "loss": 0.0211, "num_tokens": 293838774.0, "reward": 0.5078125, "reward_std": 0.4264582693576813, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1413 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1446.5078125, "completions/mean_terminated_length": 1182.9326171875, "completions/min_length": 415.0, "completions/min_terminated_length": 415.0, "epoch": 0.25089271852196865, "frac_reward_zero_std": 0.125, "grad_norm": 0.5986711382865906, "learning_rate": 2.935e-07, "loss": 0.0127, "num_tokens": 294036839.0, "reward": 0.484375, "reward_std": 0.39055192470550537, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1414 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1449.0390625, "completions/mean_terminated_length": 1135.297607421875, "completions/min_length": 437.0, "completions/min_terminated_length": 437.0, "epoch": 0.2510701532592543, "frac_reward_zero_std": 0.125, "grad_norm": 0.7279865145683289, "learning_rate": 2.93e-07, "loss": 0.0048, "num_tokens": 294235228.0, "reward": 0.4609375, "reward_std": 0.3771643340587616, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1415 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2005.0, "completions/mean_length": 1446.6875, "completions/mean_terminated_length": 1142.494140625, "completions/min_length": 428.0, "completions/min_terminated_length": 428.0, "epoch": 0.25124758799654, "frac_reward_zero_std": 0.125, "grad_norm": 0.6383588314056396, "learning_rate": 2.9249999999999995e-07, "loss": 0.0143, "num_tokens": 294433316.0, "reward": 0.40625, "reward_std": 0.355816513299942, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1416 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1540.6640625, "completions/mean_terminated_length": 1064.0758056640625, "completions/min_length": 414.0, "completions/min_terminated_length": 414.0, "epoch": 0.2514250227338257, "frac_reward_zero_std": 0.25, "grad_norm": 0.662296712398529, "learning_rate": 2.9199999999999997e-07, "loss": 0.0374, "num_tokens": 294640889.0, "reward": 0.40625, "reward_std": 0.28543204069137573, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1417 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1548.8125, "completions/mean_terminated_length": 1033.77783203125, "completions/min_length": 501.0, "completions/min_terminated_length": 501.0, "epoch": 0.25160245747111143, "frac_reward_zero_std": 0.375, "grad_norm": 0.6432082056999207, "learning_rate": 2.915e-07, "loss": 0.0174, "num_tokens": 294849505.0, "reward": 0.34375, "reward_std": 0.2515212595462799, "rewards/simpleverify_reward/mean": 0.34375, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 1418 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2018.0, "completions/mean_length": 1572.7109375, "completions/mean_terminated_length": 1066.758056640625, "completions/min_length": 476.0, "completions/min_terminated_length": 476.0, "epoch": 0.2517798922083971, "frac_reward_zero_std": 0.25, "grad_norm": 0.6507839560508728, "learning_rate": 2.9099999999999995e-07, "loss": -0.0034, "num_tokens": 295061180.0, "reward": 0.3359375, "reward_std": 0.2759283781051636, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1419 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1970.0, "completions/mean_length": 1507.84375, "completions/mean_terminated_length": 1045.9710693359375, "completions/min_length": 488.0, "completions/min_terminated_length": 488.0, "epoch": 0.2519573269456828, "frac_reward_zero_std": 0.375, "grad_norm": 0.6539142727851868, "learning_rate": 2.9049999999999996e-07, "loss": 0.0251, "num_tokens": 295264552.0, "reward": 0.3203125, "reward_std": 0.26123809814453125, "rewards/simpleverify_reward/mean": 0.3203125, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 1420 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2004.0, "completions/mean_length": 1351.1796875, "completions/mean_terminated_length": 1128.4844970703125, "completions/min_length": 534.0, "completions/min_terminated_length": 534.0, "epoch": 0.2521347616829685, "frac_reward_zero_std": 0.25, "grad_norm": 0.5707922577857971, "learning_rate": 2.9e-07, "loss": 0.0053, "num_tokens": 295448607.0, "reward": 0.4765625, "reward_std": 0.2504260838031769, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1421 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1366.75, "completions/mean_terminated_length": 1120.34033203125, "completions/min_length": 535.0, "completions/min_terminated_length": 535.0, "epoch": 0.25231219642025415, "frac_reward_zero_std": 0.375, "grad_norm": 0.5584607124328613, "learning_rate": 2.895e-07, "loss": 0.0034, "num_tokens": 295634655.0, "reward": 0.4296875, "reward_std": 0.23677173256874084, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1422 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1345.109375, "completions/mean_terminated_length": 1148.2999267578125, "completions/min_length": 504.0, "completions/min_terminated_length": 504.0, "epoch": 0.25248963115753986, "frac_reward_zero_std": 0.25, "grad_norm": 0.6362887024879456, "learning_rate": 2.8899999999999995e-07, "loss": 0.0146, "num_tokens": 295817933.0, "reward": 0.4453125, "reward_std": 0.28367161750793457, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1423 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2004.0, "completions/mean_length": 1332.9609375, "completions/mean_terminated_length": 1104.4432373046875, "completions/min_length": 526.0, "completions/min_terminated_length": 526.0, "epoch": 0.25266706589482557, "frac_reward_zero_std": 0.25, "grad_norm": 0.6713374853134155, "learning_rate": 2.8849999999999997e-07, "loss": 0.0139, "num_tokens": 295999656.0, "reward": 0.53125, "reward_std": 0.28417789936065674, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1424 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2016.0, "completions/mean_length": 1259.15625, "completions/mean_terminated_length": 996.2083740234375, "completions/min_length": 452.0, "completions/min_terminated_length": 452.0, "epoch": 0.2528445006321112, "frac_reward_zero_std": 0.25, "grad_norm": 0.6287244558334351, "learning_rate": 2.88e-07, "loss": 0.0327, "num_tokens": 296170364.0, "reward": 0.59375, "reward_std": 0.34351080656051636, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1425 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1961.0, "completions/mean_length": 1219.1640625, "completions/mean_terminated_length": 931.252685546875, "completions/min_length": 420.0, "completions/min_terminated_length": 420.0, "epoch": 0.25302193536939693, "frac_reward_zero_std": 0.375, "grad_norm": 0.6123759150505066, "learning_rate": 2.8749999999999995e-07, "loss": 0.0204, "num_tokens": 296335953.0, "reward": 0.59375, "reward_std": 0.291130006313324, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1426 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2021.0, "completions/mean_length": 1180.703125, "completions/mean_terminated_length": 915.2040405273438, "completions/min_length": 429.0, "completions/min_terminated_length": 429.0, "epoch": 0.25319937010668264, "frac_reward_zero_std": 0.25, "grad_norm": 0.785445511341095, "learning_rate": 2.8699999999999996e-07, "loss": 0.0505, "num_tokens": 296496619.0, "reward": 0.6015625, "reward_std": 0.36382147669792175, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1427 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1174.2734375, "completions/mean_terminated_length": 929.6300048828125, "completions/min_length": 454.0, "completions/min_terminated_length": 454.0, "epoch": 0.25337680484396835, "frac_reward_zero_std": 0.25, "grad_norm": 0.6619685888290405, "learning_rate": 2.865e-07, "loss": 0.0164, "num_tokens": 296656462.0, "reward": 0.59375, "reward_std": 0.3254890441894531, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1428 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1364.046875, "completions/mean_terminated_length": 1106.6451416015625, "completions/min_length": 514.0, "completions/min_terminated_length": 514.0, "epoch": 0.253554239581254, "frac_reward_zero_std": 0.25, "grad_norm": 0.5962027311325073, "learning_rate": 2.8599999999999994e-07, "loss": 0.0069, "num_tokens": 296842372.0, "reward": 0.5546875, "reward_std": 0.30257564783096313, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1429 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1390.9296875, "completions/mean_terminated_length": 1113.5, "completions/min_length": 554.0, "completions/min_terminated_length": 554.0, "epoch": 0.2537316743185397, "frac_reward_zero_std": 0.25, "grad_norm": 0.6782481074333191, "learning_rate": 2.8549999999999996e-07, "loss": 0.0174, "num_tokens": 297031723.0, "reward": 0.484375, "reward_std": 0.31548207998275757, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1430 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1975.0, "completions/mean_length": 1354.703125, "completions/mean_terminated_length": 1083.4130859375, "completions/min_length": 516.0, "completions/min_terminated_length": 516.0, "epoch": 0.2539091090558254, "frac_reward_zero_std": 0.25, "grad_norm": 0.6232447624206543, "learning_rate": 2.8499999999999997e-07, "loss": 0.0185, "num_tokens": 297216437.0, "reward": 0.5625, "reward_std": 0.29240670800209045, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1431 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2015.0, "completions/mean_length": 1416.09375, "completions/mean_terminated_length": 1118.298828125, "completions/min_length": 562.0, "completions/min_terminated_length": 562.0, "epoch": 0.2540865437931111, "frac_reward_zero_std": 0.25, "grad_norm": 0.6912521123886108, "learning_rate": 2.845e-07, "loss": 0.0473, "num_tokens": 297409009.0, "reward": 0.5390625, "reward_std": 0.32216301560401917, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1432 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1576.546875, "completions/mean_terminated_length": 1284.1265869140625, "completions/min_length": 626.0, "completions/min_terminated_length": 626.0, "epoch": 0.2542639785303968, "frac_reward_zero_std": 0.125, "grad_norm": 0.6212739944458008, "learning_rate": 2.8399999999999995e-07, "loss": 0.0307, "num_tokens": 297625127.0, "reward": 0.421875, "reward_std": 0.3748149871826172, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1433 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1577.234375, "completions/mean_terminated_length": 1285.240478515625, "completions/min_length": 611.0, "completions/min_terminated_length": 611.0, "epoch": 0.2544414132676825, "frac_reward_zero_std": 0.375, "grad_norm": 0.49226054549217224, "learning_rate": 2.8349999999999996e-07, "loss": 0.0378, "num_tokens": 297841333.0, "reward": 0.421875, "reward_std": 0.31968629360198975, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1434 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2014.0, "completions/mean_length": 1602.625, "completions/mean_terminated_length": 1267.0684814453125, "completions/min_length": 631.0, "completions/min_terminated_length": 631.0, "epoch": 0.25461884800496815, "frac_reward_zero_std": 0.375, "grad_norm": 0.49993664026260376, "learning_rate": 2.83e-07, "loss": 0.0346, "num_tokens": 298060789.0, "reward": 0.4765625, "reward_std": 0.311808705329895, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1435 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1605.5703125, "completions/mean_terminated_length": 1312.532470703125, "completions/min_length": 635.0, "completions/min_terminated_length": 635.0, "epoch": 0.25479628274225385, "frac_reward_zero_std": 0.125, "grad_norm": 0.6381776332855225, "learning_rate": 2.8249999999999994e-07, "loss": 0.0264, "num_tokens": 298280622.0, "reward": 0.4453125, "reward_std": 0.3795255422592163, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1436 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1954.0, "completions/mean_length": 796.6953125, "completions/mean_terminated_length": 766.6640625, "completions/min_length": 325.0, "completions/min_terminated_length": 325.0, "epoch": 0.25497371747953956, "frac_reward_zero_std": 0.625, "grad_norm": 0.5166403651237488, "learning_rate": 2.8199999999999996e-07, "loss": 0.0063, "num_tokens": 298391015.0, "reward": 0.7265625, "reward_std": 0.151701420545578, "rewards/simpleverify_reward/mean": 0.7265625, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 1437 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 780.7109375, "completions/mean_terminated_length": 750.2960205078125, "completions/min_length": 311.0, "completions/min_terminated_length": 311.0, "epoch": 0.25515115221682527, "frac_reward_zero_std": 0.375, "grad_norm": 0.7800284028053284, "learning_rate": 2.8149999999999997e-07, "loss": 0.007, "num_tokens": 298499362.0, "reward": 0.7578125, "reward_std": 0.23414260149002075, "rewards/simpleverify_reward/mean": 0.7578125, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 1438 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 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": 2000.0, "completions/max_terminated_length": 2000.0, "completions/mean_length": 756.7578125, "completions/mean_terminated_length": 756.7578125, "completions/min_length": 334.0, "completions/min_terminated_length": 334.0, "epoch": 0.2553285869541109, "frac_reward_zero_std": 0.5, "grad_norm": 0.6522235870361328, "learning_rate": 2.8100000000000004e-07, "loss": 0.0204, "num_tokens": 298604643.0, "reward": 0.71875, "reward_std": 0.16769562661647797, "rewards/simpleverify_reward/mean": 0.71875, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 1439 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.03125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2001.0, "completions/mean_length": 776.4375, "completions/mean_terminated_length": 735.4193115234375, "completions/min_length": 278.0, "completions/min_terminated_length": 278.0, "epoch": 0.25550602169139663, "frac_reward_zero_std": 0.625, "grad_norm": 0.4678557813167572, "learning_rate": 2.805e-07, "loss": 0.0093, "num_tokens": 298712443.0, "reward": 0.765625, "reward_std": 0.16613000631332397, "rewards/simpleverify_reward/mean": 0.765625, "rewards/simpleverify_reward/std": 0.42527204751968384, "step": 1440 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1874.0, "completions/mean_length": 1130.65625, "completions/mean_terminated_length": 980.54541015625, "completions/min_length": 436.0, "completions/min_terminated_length": 436.0, "epoch": 0.25568345642868234, "frac_reward_zero_std": 0.5, "grad_norm": 0.47018495202064514, "learning_rate": 2.8e-07, "loss": -0.0057, "num_tokens": 298868847.0, "reward": 0.609375, "reward_std": 0.20927388966083527, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1441 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1923.0, "completions/mean_length": 1126.40625, "completions/mean_terminated_length": 985.2612915039062, "completions/min_length": 352.0, "completions/min_terminated_length": 352.0, "epoch": 0.255860891165968, "frac_reward_zero_std": 0.5, "grad_norm": 0.5117943286895752, "learning_rate": 2.7950000000000003e-07, "loss": 0.0036, "num_tokens": 299024707.0, "reward": 0.5859375, "reward_std": 0.20773044228553772, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1442 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1863.0, "completions/mean_length": 1126.0546875, "completions/mean_terminated_length": 994.3482666015625, "completions/min_length": 436.0, "completions/min_terminated_length": 436.0, "epoch": 0.2560383259032537, "frac_reward_zero_std": 0.5, "grad_norm": 0.4498876929283142, "learning_rate": 2.79e-07, "loss": -0.0, "num_tokens": 299180522.0, "reward": 0.6015625, "reward_std": 0.20818254351615906, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1443 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1161.859375, "completions/mean_terminated_length": 1016.8544921875, "completions/min_length": 390.0, "completions/min_terminated_length": 390.0, "epoch": 0.2562157606405394, "frac_reward_zero_std": 0.25, "grad_norm": 0.5618749260902405, "learning_rate": 2.785e-07, "loss": 0.0152, "num_tokens": 299340920.0, "reward": 0.578125, "reward_std": 0.27323853969573975, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1444 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1212.828125, "completions/mean_terminated_length": 1142.0509033203125, "completions/min_length": 578.0, "completions/min_terminated_length": 578.0, "epoch": 0.25639319537782507, "frac_reward_zero_std": 0.25, "grad_norm": 0.5708720684051514, "learning_rate": 2.7800000000000003e-07, "loss": 0.0217, "num_tokens": 299508274.0, "reward": 0.7890625, "reward_std": 0.2810424566268921, "rewards/simpleverify_reward/mean": 0.7890625, "rewards/simpleverify_reward/std": 0.4095771610736847, "step": 1445 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1229.640625, "completions/mean_terminated_length": 1137.13037109375, "completions/min_length": 564.0, "completions/min_terminated_length": 564.0, "epoch": 0.2565706301151108, "frac_reward_zero_std": 0.375, "grad_norm": 0.5349525809288025, "learning_rate": 2.775e-07, "loss": 0.021, "num_tokens": 299677780.0, "reward": 0.796875, "reward_std": 0.2563907504081726, "rewards/simpleverify_reward/mean": 0.796875, "rewards/simpleverify_reward/std": 0.40390563011169434, "step": 1446 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1248.0625, "completions/mean_terminated_length": 1180.271240234375, "completions/min_length": 565.0, "completions/min_terminated_length": 565.0, "epoch": 0.2567480648523965, "frac_reward_zero_std": 0.25, "grad_norm": 0.588538408279419, "learning_rate": 2.77e-07, "loss": 0.0407, "num_tokens": 299849644.0, "reward": 0.7734375, "reward_std": 0.29642558097839355, "rewards/simpleverify_reward/mean": 0.7734375, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 1447 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2014.0, "completions/mean_length": 1234.6484375, "completions/mean_terminated_length": 1142.704345703125, "completions/min_length": 490.0, "completions/min_terminated_length": 490.0, "epoch": 0.2569254995896822, "frac_reward_zero_std": 0.375, "grad_norm": 0.6354647278785706, "learning_rate": 2.765e-07, "loss": 0.0398, "num_tokens": 300019791.0, "reward": 0.7578125, "reward_std": 0.23722384870052338, "rewards/simpleverify_reward/mean": 0.7578125, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 1448 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1970.0, "completions/mean_length": 1356.4921875, "completions/mean_terminated_length": 1171.6336669921875, "completions/min_length": 371.0, "completions/min_terminated_length": 371.0, "epoch": 0.25710293432696785, "frac_reward_zero_std": 0.5, "grad_norm": 0.4538154900074005, "learning_rate": 2.7600000000000004e-07, "loss": 0.0199, "num_tokens": 300203918.0, "reward": 0.4609375, "reward_std": 0.21763263642787933, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1449 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1270.0234375, "completions/mean_terminated_length": 1090.490478515625, "completions/min_length": 307.0, "completions/min_terminated_length": 307.0, "epoch": 0.25728036906425356, "frac_reward_zero_std": 0.375, "grad_norm": 0.5183801651000977, "learning_rate": 2.755e-07, "loss": 0.0404, "num_tokens": 300376977.0, "reward": 0.5234375, "reward_std": 0.22013446688652039, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1450 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1304.1875, "completions/mean_terminated_length": 1141.2572021484375, "completions/min_length": 335.0, "completions/min_terminated_length": 335.0, "epoch": 0.25745780380153926, "frac_reward_zero_std": 0.25, "grad_norm": 0.823459804058075, "learning_rate": 2.75e-07, "loss": 0.0017, "num_tokens": 300554409.0, "reward": 0.4765625, "reward_std": 0.28367161750793457, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1451 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1295.7109375, "completions/mean_terminated_length": 1085.0699462890625, "completions/min_length": 309.0, "completions/min_terminated_length": 309.0, "epoch": 0.2576352385388249, "frac_reward_zero_std": 0.375, "grad_norm": 1.1448743343353271, "learning_rate": 2.7450000000000003e-07, "loss": 0.0142, "num_tokens": 300730756.0, "reward": 0.4921875, "reward_std": 0.24574071168899536, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1452 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2014.0, "completions/mean_length": 1272.0234375, "completions/mean_terminated_length": 1044.7171630859375, "completions/min_length": 443.0, "completions/min_terminated_length": 443.0, "epoch": 0.2578126732761106, "frac_reward_zero_std": 0.375, "grad_norm": 0.5523427724838257, "learning_rate": 2.74e-07, "loss": -0.0031, "num_tokens": 300907463.0, "reward": 0.6171875, "reward_std": 0.1945282220840454, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1453 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1962.0, "completions/mean_length": 1258.5546875, "completions/mean_terminated_length": 1037.510009765625, "completions/min_length": 437.0, "completions/min_terminated_length": 437.0, "epoch": 0.25799010801339634, "frac_reward_zero_std": 0.5, "grad_norm": 0.459684282541275, "learning_rate": 2.735e-07, "loss": 0.0179, "num_tokens": 301082446.0, "reward": 0.6171875, "reward_std": 0.18574902415275574, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1454 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1234.53125, "completions/mean_terminated_length": 1056.3428955078125, "completions/min_length": 422.0, "completions/min_terminated_length": 422.0, "epoch": 0.258167542750682, "frac_reward_zero_std": 0.125, "grad_norm": 0.6722079515457153, "learning_rate": 2.73e-07, "loss": 0.0021, "num_tokens": 301254354.0, "reward": 0.6328125, "reward_std": 0.25484731793403625, "rewards/simpleverify_reward/mean": 0.6328125, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1455 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1261.234375, "completions/mean_terminated_length": 1030.7677001953125, "completions/min_length": 455.0, "completions/min_terminated_length": 455.0, "epoch": 0.2583449774879677, "frac_reward_zero_std": 0.25, "grad_norm": 0.5914202928543091, "learning_rate": 2.725e-07, "loss": 0.0126, "num_tokens": 301429680.0, "reward": 0.6015625, "reward_std": 0.23722384870052338, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1456 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2009.0, "completions/mean_length": 1431.0, "completions/mean_terminated_length": 1295.84765625, "completions/min_length": 561.0, "completions/min_terminated_length": 561.0, "epoch": 0.2585224122252534, "frac_reward_zero_std": 0.375, "grad_norm": 0.555696964263916, "learning_rate": 2.72e-07, "loss": 0.0109, "num_tokens": 301626256.0, "reward": 0.484375, "reward_std": 0.28580838441848755, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1457 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1984.0, "completions/mean_length": 1444.2265625, "completions/mean_terminated_length": 1297.6795654296875, "completions/min_length": 587.0, "completions/min_terminated_length": 587.0, "epoch": 0.2586998469625391, "frac_reward_zero_std": 0.25, "grad_norm": 0.5867753624916077, "learning_rate": 2.715e-07, "loss": 0.0062, "num_tokens": 301824525.0, "reward": 0.5, "reward_std": 0.3285759389400482, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 1458 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1442.5390625, "completions/mean_terminated_length": 1337.0, "completions/min_length": 577.0, "completions/min_terminated_length": 577.0, "epoch": 0.25887728169982477, "frac_reward_zero_std": 0.25, "grad_norm": 0.5624083876609802, "learning_rate": 2.7100000000000003e-07, "loss": -0.0013, "num_tokens": 302022578.0, "reward": 0.546875, "reward_std": 0.30946704745292664, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1459 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1996.0, "completions/mean_length": 1447.3046875, "completions/mean_terminated_length": 1322.632080078125, "completions/min_length": 512.0, "completions/min_terminated_length": 512.0, "epoch": 0.2590547164371105, "frac_reward_zero_std": 0.125, "grad_norm": 0.658726692199707, "learning_rate": 2.705e-07, "loss": 0.0104, "num_tokens": 302221241.0, "reward": 0.46875, "reward_std": 0.37734586000442505, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1460 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1111.5078125, "completions/mean_terminated_length": 996.5, "completions/min_length": 429.0, "completions/min_terminated_length": 429.0, "epoch": 0.2592321511743962, "frac_reward_zero_std": 0.0, "grad_norm": 0.7514787912368774, "learning_rate": 2.7e-07, "loss": 0.0276, "num_tokens": 302373082.0, "reward": 0.7265625, "reward_std": 0.3768143653869629, "rewards/simpleverify_reward/mean": 0.7265625, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 1461 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1901.0, "completions/mean_length": 1093.390625, "completions/mean_terminated_length": 1012.4915161132812, "completions/min_length": 469.0, "completions/min_terminated_length": 469.0, "epoch": 0.25940958591168184, "frac_reward_zero_std": 0.0, "grad_norm": 0.8073225021362305, "learning_rate": 2.695e-07, "loss": 0.0159, "num_tokens": 302522604.0, "reward": 0.734375, "reward_std": 0.37082332372665405, "rewards/simpleverify_reward/mean": 0.734375, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 1462 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.09375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1689.0, "completions/mean_length": 1092.6796875, "completions/mean_terminated_length": 993.8534545898438, "completions/min_length": 441.0, "completions/min_terminated_length": 441.0, "epoch": 0.25958702064896755, "frac_reward_zero_std": 0.125, "grad_norm": 0.7144867181777954, "learning_rate": 2.69e-07, "loss": 0.0227, "num_tokens": 302672035.0, "reward": 0.6953125, "reward_std": 0.3578120768070221, "rewards/simpleverify_reward/mean": 0.6953125, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 1463 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.09375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1119.6484375, "completions/mean_terminated_length": 1023.612060546875, "completions/min_length": 424.0, "completions/min_terminated_length": 424.0, "epoch": 0.25976445538625326, "frac_reward_zero_std": 0.25, "grad_norm": 0.5719031095504761, "learning_rate": 2.685e-07, "loss": -0.0023, "num_tokens": 302824918.0, "reward": 0.7265625, "reward_std": 0.3197689652442932, "rewards/simpleverify_reward/mean": 0.7265625, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 1464 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2012.0, "completions/mean_length": 1510.0, "completions/mean_terminated_length": 1352.404052734375, "completions/min_length": 633.0, "completions/min_terminated_length": 633.0, "epoch": 0.2599418901235389, "frac_reward_zero_std": 0.25, "grad_norm": 0.5871142148971558, "learning_rate": 2.68e-07, "loss": 0.0411, "num_tokens": 303034582.0, "reward": 0.7265625, "reward_std": 0.28196918964385986, "rewards/simpleverify_reward/mean": 0.7265625, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 1465 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2013.0, "completions/mean_length": 1461.1796875, "completions/mean_terminated_length": 1332.63818359375, "completions/min_length": 637.0, "completions/min_terminated_length": 637.0, "epoch": 0.2601193248608246, "frac_reward_zero_std": 0.25, "grad_norm": 0.5250039100646973, "learning_rate": 2.675e-07, "loss": 0.0382, "num_tokens": 303237997.0, "reward": 0.703125, "reward_std": 0.3041190803050995, "rewards/simpleverify_reward/mean": 0.703125, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 1466 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2015.0, "completions/mean_length": 1528.515625, "completions/mean_terminated_length": 1362.4947509765625, "completions/min_length": 592.0, "completions/min_terminated_length": 592.0, "epoch": 0.2602967595981103, "frac_reward_zero_std": 0.25, "grad_norm": 0.5342966914176941, "learning_rate": 2.67e-07, "loss": 0.0261, "num_tokens": 303450031.0, "reward": 0.6875, "reward_std": 0.3078750669956207, "rewards/simpleverify_reward/mean": 0.6875, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 1467 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1471.3671875, "completions/mean_terminated_length": 1338.298095703125, "completions/min_length": 648.0, "completions/min_terminated_length": 648.0, "epoch": 0.26047419433539604, "frac_reward_zero_std": 0.375, "grad_norm": 0.484921932220459, "learning_rate": 2.665e-07, "loss": 0.0401, "num_tokens": 303654750.0, "reward": 0.7265625, "reward_std": 0.25623178482055664, "rewards/simpleverify_reward/mean": 0.7265625, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 1468 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1945.0, "completions/mean_length": 1301.46875, "completions/mean_terminated_length": 1111.176513671875, "completions/min_length": 427.0, "completions/min_terminated_length": 427.0, "epoch": 0.2606516290726817, "frac_reward_zero_std": 0.25, "grad_norm": 0.5779603123664856, "learning_rate": 2.66e-07, "loss": 0.0331, "num_tokens": 303834954.0, "reward": 0.609375, "reward_std": 0.3056941628456116, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1469 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1271.9140625, "completions/mean_terminated_length": 1101.914306640625, "completions/min_length": 445.0, "completions/min_terminated_length": 445.0, "epoch": 0.2608290638099674, "frac_reward_zero_std": 0.25, "grad_norm": 0.5638324618339539, "learning_rate": 2.655e-07, "loss": 0.02, "num_tokens": 304011375.0, "reward": 0.7109375, "reward_std": 0.3400215804576874, "rewards/simpleverify_reward/mean": 0.7109375, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 1470 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1281.890625, "completions/mean_terminated_length": 1140.0185546875, "completions/min_length": 393.0, "completions/min_terminated_length": 393.0, "epoch": 0.2610064985472531, "frac_reward_zero_std": 0.0, "grad_norm": 0.692988932132721, "learning_rate": 2.65e-07, "loss": 0.0602, "num_tokens": 304189073.0, "reward": 0.671875, "reward_std": 0.4022681415081024, "rewards/simpleverify_reward/mean": 0.671875, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1471 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1231.3515625, "completions/mean_terminated_length": 1052.4666748046875, "completions/min_length": 436.0, "completions/min_terminated_length": 436.0, "epoch": 0.26118393328453876, "frac_reward_zero_std": 0.125, "grad_norm": 0.6269715428352356, "learning_rate": 2.645e-07, "loss": 0.0326, "num_tokens": 304360302.0, "reward": 0.6328125, "reward_std": 0.3341149091720581, "rewards/simpleverify_reward/mean": 0.6328125, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1472 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2004.0, "completions/mean_length": 1362.9140625, "completions/mean_terminated_length": 1153.19384765625, "completions/min_length": 209.0, "completions/min_terminated_length": 209.0, "epoch": 0.26136136802182447, "frac_reward_zero_std": 0.0, "grad_norm": 0.7209065556526184, "learning_rate": 2.64e-07, "loss": 0.0405, "num_tokens": 304546515.0, "reward": 0.421875, "reward_std": 0.39816218614578247, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1473 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1325.84375, "completions/mean_terminated_length": 1132.7921142578125, "completions/min_length": 236.0, "completions/min_terminated_length": 236.0, "epoch": 0.2615388027591102, "frac_reward_zero_std": 0.25, "grad_norm": 0.6265503764152527, "learning_rate": 2.635e-07, "loss": -0.0047, "num_tokens": 304727983.0, "reward": 0.4453125, "reward_std": 0.31279873847961426, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1474 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1361.3828125, "completions/mean_terminated_length": 1169.1300048828125, "completions/min_length": 222.0, "completions/min_terminated_length": 222.0, "epoch": 0.26171623749639583, "frac_reward_zero_std": 0.125, "grad_norm": 0.6188717484474182, "learning_rate": 2.63e-07, "loss": -0.0053, "num_tokens": 304914000.0, "reward": 0.4375, "reward_std": 0.3584457039833069, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1475 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1894.0, "completions/mean_length": 1333.9609375, "completions/mean_terminated_length": 1134.030029296875, "completions/min_length": 228.0, "completions/min_terminated_length": 228.0, "epoch": 0.26189367223368154, "frac_reward_zero_std": 0.125, "grad_norm": 0.6117385029792786, "learning_rate": 2.625e-07, "loss": -0.0037, "num_tokens": 305096507.0, "reward": 0.484375, "reward_std": 0.3873332738876343, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1476 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1963.0, "completions/mean_length": 1211.1484375, "completions/mean_terminated_length": 1037.4622802734375, "completions/min_length": 191.0, "completions/min_terminated_length": 191.0, "epoch": 0.26207110697096725, "frac_reward_zero_std": 0.25, "grad_norm": 0.5457273125648499, "learning_rate": 2.62e-07, "loss": 0.0379, "num_tokens": 305261118.0, "reward": 0.6953125, "reward_std": 0.3481174111366272, "rewards/simpleverify_reward/mean": 0.6953125, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 1477 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2003.0, "completions/mean_length": 1220.140625, "completions/mean_terminated_length": 1029.09619140625, "completions/min_length": 192.0, "completions/min_terminated_length": 192.0, "epoch": 0.26224854170825296, "frac_reward_zero_std": 0.25, "grad_norm": 0.5459546446800232, "learning_rate": 2.615e-07, "loss": 0.0564, "num_tokens": 305426880.0, "reward": 0.6953125, "reward_std": 0.34468233585357666, "rewards/simpleverify_reward/mean": 0.6953125, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 1478 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1159.4609375, "completions/mean_terminated_length": 1023.37841796875, "completions/min_length": 192.0, "completions/min_terminated_length": 192.0, "epoch": 0.2624259764455386, "frac_reward_zero_std": 0.125, "grad_norm": 0.6215841174125671, "learning_rate": 2.61e-07, "loss": 0.0636, "num_tokens": 305584875.0, "reward": 0.7421875, "reward_std": 0.3551734387874603, "rewards/simpleverify_reward/mean": 0.7421875, "rewards/simpleverify_reward/std": 0.43914902210235596, "step": 1479 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1890.0, "completions/mean_length": 1184.4453125, "completions/mean_terminated_length": 995.2857666015625, "completions/min_length": 191.0, "completions/min_terminated_length": 191.0, "epoch": 0.2626034111828243, "frac_reward_zero_std": 0.125, "grad_norm": 0.6094849705696106, "learning_rate": 2.605e-07, "loss": 0.064, "num_tokens": 305746068.0, "reward": 0.71875, "reward_std": 0.3900482654571533, "rewards/simpleverify_reward/mean": 0.71875, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 1480 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1948.0, "completions/mean_length": 1483.1328125, "completions/mean_terminated_length": 1083.9600830078125, "completions/min_length": 365.0, "completions/min_terminated_length": 365.0, "epoch": 0.26278084592011003, "frac_reward_zero_std": 0.5, "grad_norm": 0.482914000749588, "learning_rate": 2.6e-07, "loss": 0.0082, "num_tokens": 305943925.0, "reward": 0.328125, "reward_std": 0.22466085851192474, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1481 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1441.7890625, "completions/mean_terminated_length": 1135.11767578125, "completions/min_length": 414.0, "completions/min_terminated_length": 414.0, "epoch": 0.2629582806573957, "frac_reward_zero_std": 0.25, "grad_norm": 0.5187057852745056, "learning_rate": 2.595e-07, "loss": 0.0047, "num_tokens": 306136490.0, "reward": 0.3984375, "reward_std": 0.27946737408638, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1482 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1983.0, "completions/mean_length": 1453.625, "completions/mean_terminated_length": 1152.941162109375, "completions/min_length": 508.0, "completions/min_terminated_length": 508.0, "epoch": 0.2631357153946814, "frac_reward_zero_std": 0.125, "grad_norm": 0.6092787384986877, "learning_rate": 2.59e-07, "loss": 0.0327, "num_tokens": 306330570.0, "reward": 0.359375, "reward_std": 0.3705882132053375, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 1483 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1494.3984375, "completions/mean_terminated_length": 1183.8414306640625, "completions/min_length": 492.0, "completions/min_terminated_length": 492.0, "epoch": 0.2633131501319671, "frac_reward_zero_std": 0.5, "grad_norm": 0.42754289507865906, "learning_rate": 2.585e-07, "loss": 0.0357, "num_tokens": 306529869.0, "reward": 0.3359375, "reward_std": 0.22641746699810028, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1484 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1838.0, "completions/mean_length": 1363.0546875, "completions/mean_terminated_length": 978.8170166015625, "completions/min_length": 349.0, "completions/min_terminated_length": 349.0, "epoch": 0.26349058486925275, "frac_reward_zero_std": 0.75, "grad_norm": 0.4197446405887604, "learning_rate": 2.58e-07, "loss": 0.0071, "num_tokens": 306716676.0, "reward": 0.3828125, "reward_std": 0.09308473765850067, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1485 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1749.0, "completions/mean_length": 1314.046875, "completions/mean_terminated_length": 942.7529296875, "completions/min_length": 292.0, "completions/min_terminated_length": 292.0, "epoch": 0.26366801960653846, "frac_reward_zero_std": 0.5, "grad_norm": 0.49350211024284363, "learning_rate": 2.5749999999999997e-07, "loss": 0.0134, "num_tokens": 306897210.0, "reward": 0.3828125, "reward_std": 0.13644562661647797, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1486 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1857.0, "completions/mean_length": 1365.75, "completions/mean_terminated_length": 1008.3809814453125, "completions/min_length": 329.0, "completions/min_terminated_length": 329.0, "epoch": 0.26384545434382417, "frac_reward_zero_std": 0.625, "grad_norm": 0.5415734052658081, "learning_rate": 2.57e-07, "loss": 0.0086, "num_tokens": 307084362.0, "reward": 0.3984375, "reward_std": 0.1128891110420227, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1487 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2005.0, "completions/mean_length": 1357.8203125, "completions/mean_terminated_length": 1020.7557983398438, "completions/min_length": 328.0, "completions/min_terminated_length": 328.0, "epoch": 0.2640228890811099, "frac_reward_zero_std": 0.625, "grad_norm": 0.42941200733184814, "learning_rate": 2.565e-07, "loss": 0.0203, "num_tokens": 307270499.0, "reward": 0.3828125, "reward_std": 0.1414783000946045, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1488 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1002.265625, "completions/mean_terminated_length": 722.7128295898438, "completions/min_length": 243.0, "completions/min_terminated_length": 243.0, "epoch": 0.26420032381839553, "frac_reward_zero_std": 0.375, "grad_norm": 0.7429630160331726, "learning_rate": 2.56e-07, "loss": -0.0014, "num_tokens": 307409717.0, "reward": 0.59375, "reward_std": 0.2645905315876007, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1489 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1601.0, "completions/mean_length": 1011.5078125, "completions/mean_terminated_length": 680.2576904296875, "completions/min_length": 252.0, "completions/min_terminated_length": 252.0, "epoch": 0.26437775855568124, "frac_reward_zero_std": 0.5, "grad_norm": 0.6643014550209045, "learning_rate": 2.555e-07, "loss": -0.0154, "num_tokens": 307550118.0, "reward": 0.5859375, "reward_std": 0.225140780210495, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1490 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1538.0, "completions/mean_length": 1020.8671875, "completions/mean_terminated_length": 706.4387817382812, "completions/min_length": 244.0, "completions/min_terminated_length": 244.0, "epoch": 0.26455519329296695, "frac_reward_zero_std": 0.5, "grad_norm": 0.5987410545349121, "learning_rate": 2.55e-07, "loss": -0.0083, "num_tokens": 307691717.0, "reward": 0.5859375, "reward_std": 0.21148642897605896, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1491 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1760.0, "completions/mean_length": 1024.921875, "completions/mean_terminated_length": 738.4599609375, "completions/min_length": 242.0, "completions/min_terminated_length": 242.0, "epoch": 0.2647326280302526, "frac_reward_zero_std": 0.375, "grad_norm": 0.7155737280845642, "learning_rate": 2.545e-07, "loss": 0.0082, "num_tokens": 307833835.0, "reward": 0.625, "reward_std": 0.23613813519477844, "rewards/simpleverify_reward/mean": 0.625, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 1492 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2007.0, "completions/mean_length": 1472.65625, "completions/mean_terminated_length": 1201.5172119140625, "completions/min_length": 535.0, "completions/min_terminated_length": 535.0, "epoch": 0.2649100627675383, "frac_reward_zero_std": 0.375, "grad_norm": 0.46735572814941406, "learning_rate": 2.5399999999999997e-07, "loss": 0.0133, "num_tokens": 308033983.0, "reward": 0.59375, "reward_std": 0.24318468570709229, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1493 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1412.1171875, "completions/mean_terminated_length": 1163.29345703125, "completions/min_length": 436.0, "completions/min_terminated_length": 436.0, "epoch": 0.265087497504824, "frac_reward_zero_std": 0.25, "grad_norm": 0.7027925252914429, "learning_rate": 2.535e-07, "loss": 0.025, "num_tokens": 308226382.0, "reward": 0.59375, "reward_std": 0.28279343247413635, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1494 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1937.0, "completions/mean_length": 1411.234375, "completions/mean_terminated_length": 1089.10595703125, "completions/min_length": 423.0, "completions/min_terminated_length": 423.0, "epoch": 0.2652649322421097, "frac_reward_zero_std": 0.375, "grad_norm": 0.513909101486206, "learning_rate": 2.53e-07, "loss": 0.0402, "num_tokens": 308418668.0, "reward": 0.5625, "reward_std": 0.26187169551849365, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1495 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1463.90625, "completions/mean_terminated_length": 1198.4091796875, "completions/min_length": 418.0, "completions/min_terminated_length": 418.0, "epoch": 0.2654423669793954, "frac_reward_zero_std": 0.375, "grad_norm": 0.534683883190155, "learning_rate": 2.5249999999999996e-07, "loss": 0.0327, "num_tokens": 308617696.0, "reward": 0.5859375, "reward_std": 0.25591084361076355, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1496 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1493.5859375, "completions/mean_terminated_length": 1293.0531005859375, "completions/min_length": 415.0, "completions/min_terminated_length": 415.0, "epoch": 0.2656198017166811, "frac_reward_zero_std": 0.25, "grad_norm": 0.524583637714386, "learning_rate": 2.52e-07, "loss": 0.0282, "num_tokens": 308822859.0, "reward": 0.3828125, "reward_std": 0.3008693754673004, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1497 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1976.0, "completions/mean_length": 1474.3984375, "completions/mean_terminated_length": 1275.1474609375, "completions/min_length": 461.0, "completions/min_terminated_length": 461.0, "epoch": 0.2657972364539668, "frac_reward_zero_std": 0.25, "grad_norm": 0.5238807797431946, "learning_rate": 2.515e-07, "loss": 0.0119, "num_tokens": 309025566.0, "reward": 0.359375, "reward_std": 0.2946690022945404, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 1498 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1447.3828125, "completions/mean_terminated_length": 1271.4444580078125, "completions/min_length": 428.0, "completions/min_terminated_length": 428.0, "epoch": 0.26597467119125245, "frac_reward_zero_std": 0.25, "grad_norm": 0.5263134837150574, "learning_rate": 2.51e-07, "loss": 0.0161, "num_tokens": 309224815.0, "reward": 0.3359375, "reward_std": 0.3113604784011841, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1499 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1487.5234375, "completions/mean_terminated_length": 1323.3433837890625, "completions/min_length": 450.0, "completions/min_terminated_length": 450.0, "epoch": 0.26615210592853816, "frac_reward_zero_std": 0.25, "grad_norm": 0.5105469226837158, "learning_rate": 2.5049999999999997e-07, "loss": 0.0088, "num_tokens": 309429202.0, "reward": 0.3671875, "reward_std": 0.3527793884277344, "rewards/simpleverify_reward/mean": 0.3671875, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1500 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1269.8515625, "completions/mean_terminated_length": 1010.46875, "completions/min_length": 452.0, "completions/min_terminated_length": 452.0, "epoch": 0.26632954066582387, "frac_reward_zero_std": 0.375, "grad_norm": 0.4867743253707886, "learning_rate": 2.5e-07, "loss": 0.0011, "num_tokens": 309603071.0, "reward": 0.53125, "reward_std": 0.24558822810649872, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1501 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1263.109375, "completions/mean_terminated_length": 1022.8367309570312, "completions/min_length": 461.0, "completions/min_terminated_length": 461.0, "epoch": 0.2665069754031095, "frac_reward_zero_std": 0.25, "grad_norm": 0.5343323945999146, "learning_rate": 2.495e-07, "loss": 0.0215, "num_tokens": 309776077.0, "reward": 0.5390625, "reward_std": 0.30324089527130127, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1502 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1287.3203125, "completions/mean_terminated_length": 1033.760498046875, "completions/min_length": 453.0, "completions/min_terminated_length": 453.0, "epoch": 0.26668441014039523, "frac_reward_zero_std": 0.5, "grad_norm": 0.4029009938240051, "learning_rate": 2.4899999999999997e-07, "loss": 0.0176, "num_tokens": 309952182.0, "reward": 0.5234375, "reward_std": 0.20978017151355743, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1503 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1279.703125, "completions/mean_terminated_length": 1054.646484375, "completions/min_length": 472.0, "completions/min_terminated_length": 472.0, "epoch": 0.26686184487768094, "frac_reward_zero_std": 0.5, "grad_norm": 0.423321396112442, "learning_rate": 2.485e-07, "loss": -0.0013, "num_tokens": 310127312.0, "reward": 0.5078125, "reward_std": 0.2493889033794403, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1504 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1386.1484375, "completions/mean_terminated_length": 1127.1630859375, "completions/min_length": 437.0, "completions/min_terminated_length": 437.0, "epoch": 0.2670392796149666, "frac_reward_zero_std": 0.125, "grad_norm": 0.7069523930549622, "learning_rate": 2.48e-07, "loss": 0.041, "num_tokens": 310316915.0, "reward": 0.4296875, "reward_std": 0.3567485213279724, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1505 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1399.03125, "completions/mean_terminated_length": 1104.0455322265625, "completions/min_length": 513.0, "completions/min_terminated_length": 513.0, "epoch": 0.2672167143522523, "frac_reward_zero_std": 0.25, "grad_norm": 0.5958172678947449, "learning_rate": 2.475e-07, "loss": 0.0342, "num_tokens": 310508167.0, "reward": 0.4140625, "reward_std": 0.3100837469100952, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1506 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2008.0, "completions/mean_length": 1337.5, "completions/mean_terminated_length": 1080.5106201171875, "completions/min_length": 433.0, "completions/min_terminated_length": 433.0, "epoch": 0.267394149089538, "frac_reward_zero_std": 0.25, "grad_norm": 0.6590302586555481, "learning_rate": 2.47e-07, "loss": 0.0498, "num_tokens": 310691543.0, "reward": 0.3984375, "reward_std": 0.33193784952163696, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1507 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1999.0, "completions/mean_length": 1359.1796875, "completions/mean_terminated_length": 1068.344482421875, "completions/min_length": 402.0, "completions/min_terminated_length": 402.0, "epoch": 0.2675715838268237, "frac_reward_zero_std": 0.25, "grad_norm": 0.6336004734039307, "learning_rate": 2.465e-07, "loss": 0.033, "num_tokens": 310877694.0, "reward": 0.453125, "reward_std": 0.2961588501930237, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1508 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2018.0, "completions/mean_length": 1404.3828125, "completions/mean_terminated_length": 964.01318359375, "completions/min_length": 583.0, "completions/min_terminated_length": 583.0, "epoch": 0.2677490185641094, "frac_reward_zero_std": 0.5, "grad_norm": 0.4366950988769531, "learning_rate": 2.46e-07, "loss": 0.0108, "num_tokens": 311070879.0, "reward": 0.515625, "reward_std": 0.1727283000946045, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1509 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1403.8671875, "completions/mean_terminated_length": 1042.5242919921875, "completions/min_length": 588.0, "completions/min_terminated_length": 588.0, "epoch": 0.2679264533013951, "frac_reward_zero_std": 0.875, "grad_norm": 0.17908354103565216, "learning_rate": 2.4549999999999997e-07, "loss": 0.0023, "num_tokens": 311263998.0, "reward": 0.5390625, "reward_std": 0.059839196503162384, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1510 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1996.0, "completions/mean_length": 1405.75, "completions/mean_terminated_length": 994.05126953125, "completions/min_length": 585.0, "completions/min_terminated_length": 585.0, "epoch": 0.2681038880386808, "frac_reward_zero_std": 0.5, "grad_norm": 0.49044132232666016, "learning_rate": 2.45e-07, "loss": 0.0183, "num_tokens": 311457358.0, "reward": 0.4921875, "reward_std": 0.13644562661647797, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1511 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1409.2265625, "completions/mean_terminated_length": 1038.5802001953125, "completions/min_length": 599.0, "completions/min_terminated_length": 599.0, "epoch": 0.26828132277596645, "frac_reward_zero_std": 0.625, "grad_norm": 0.3429792523384094, "learning_rate": 2.445e-07, "loss": 0.0066, "num_tokens": 311651163.0, "reward": 0.53125, "reward_std": 0.11840169876813889, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1512 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1544.328125, "completions/mean_terminated_length": 1354.774169921875, "completions/min_length": 403.0, "completions/min_terminated_length": 403.0, "epoch": 0.26845875751325216, "frac_reward_zero_std": 0.125, "grad_norm": 0.530754804611206, "learning_rate": 2.4399999999999996e-07, "loss": 0.0323, "num_tokens": 311858533.0, "reward": 0.5859375, "reward_std": 0.38730162382125854, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1513 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2012.0, "completions/mean_length": 1500.875, "completions/mean_terminated_length": 1294.9677734375, "completions/min_length": 434.0, "completions/min_terminated_length": 434.0, "epoch": 0.26863619225053786, "frac_reward_zero_std": 0.125, "grad_norm": 0.5467333793640137, "learning_rate": 2.435e-07, "loss": 0.0262, "num_tokens": 312060341.0, "reward": 0.609375, "reward_std": 0.4000816345214844, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1514 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1521.84375, "completions/mean_terminated_length": 1299.68896484375, "completions/min_length": 438.0, "completions/min_terminated_length": 438.0, "epoch": 0.2688136269878235, "frac_reward_zero_std": 0.125, "grad_norm": 0.49508267641067505, "learning_rate": 2.43e-07, "loss": 0.0222, "num_tokens": 312264833.0, "reward": 0.640625, "reward_std": 0.3413337469100952, "rewards/simpleverify_reward/mean": 0.640625, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 1515 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1496.5625, "completions/mean_terminated_length": 1280.7825927734375, "completions/min_length": 437.0, "completions/min_terminated_length": 437.0, "epoch": 0.2689910617251092, "frac_reward_zero_std": 0.125, "grad_norm": 0.5428900122642517, "learning_rate": 2.425e-07, "loss": 0.0001, "num_tokens": 312466089.0, "reward": 0.609375, "reward_std": 0.3417820334434509, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1516 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1253.9609375, "completions/mean_terminated_length": 1186.66943359375, "completions/min_length": 463.0, "completions/min_terminated_length": 463.0, "epoch": 0.26916849646239493, "frac_reward_zero_std": 0.375, "grad_norm": 0.4823312759399414, "learning_rate": 2.4199999999999997e-07, "loss": -0.0039, "num_tokens": 312637012.0, "reward": 0.71875, "reward_std": 0.18683473765850067, "rewards/simpleverify_reward/mean": 0.71875, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 1517 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2018.0, "completions/mean_length": 1243.09375, "completions/mean_terminated_length": 1144.24560546875, "completions/min_length": 395.0, "completions/min_terminated_length": 395.0, "epoch": 0.26934593119968064, "frac_reward_zero_std": 0.5, "grad_norm": 0.42256560921669006, "learning_rate": 2.415e-07, "loss": 0.01, "num_tokens": 312806544.0, "reward": 0.7265625, "reward_std": 0.1687908172607422, "rewards/simpleverify_reward/mean": 0.7265625, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 1518 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2006.0, "completions/mean_length": 1263.1875, "completions/mean_terminated_length": 1134.7635498046875, "completions/min_length": 446.0, "completions/min_terminated_length": 446.0, "epoch": 0.2695233659369663, "frac_reward_zero_std": 0.5, "grad_norm": 0.46011748909950256, "learning_rate": 2.41e-07, "loss": 0.0121, "num_tokens": 312978648.0, "reward": 0.7265625, "reward_std": 0.1593368798494339, "rewards/simpleverify_reward/mean": 0.7265625, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 1519 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.09375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1269.0, "completions/mean_terminated_length": 1188.413818359375, "completions/min_length": 444.0, "completions/min_terminated_length": 444.0, "epoch": 0.269700800674252, "frac_reward_zero_std": 0.5, "grad_norm": 0.35996007919311523, "learning_rate": 2.4049999999999996e-07, "loss": -0.001, "num_tokens": 313151496.0, "reward": 0.734375, "reward_std": 0.14789125323295593, "rewards/simpleverify_reward/mean": 0.734375, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 1520 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0703125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1918.0, "completions/mean_length": 1015.8515625, "completions/mean_terminated_length": 937.7899780273438, "completions/min_length": 312.0, "completions/min_terminated_length": 312.0, "epoch": 0.2698782354115377, "frac_reward_zero_std": 0.375, "grad_norm": 0.6126433610916138, "learning_rate": 2.4e-07, "loss": -0.0, "num_tokens": 313294053.0, "reward": 0.7265625, "reward_std": 0.2312908172607422, "rewards/simpleverify_reward/mean": 0.7265625, "rewards/simpleverify_reward/std": 0.447474867105484, "step": 1521 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1011.5859375, "completions/mean_terminated_length": 942.49169921875, "completions/min_length": 355.0, "completions/min_terminated_length": 355.0, "epoch": 0.27005567014882337, "frac_reward_zero_std": 0.625, "grad_norm": 0.4124051034450531, "learning_rate": 2.395e-07, "loss": 0.0031, "num_tokens": 313436064.0, "reward": 0.7734375, "reward_std": 0.16503483057022095, "rewards/simpleverify_reward/mean": 0.7734375, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 1522 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1943.0, "completions/mean_length": 1029.78125, "completions/mean_terminated_length": 943.4915161132812, "completions/min_length": 356.0, "completions/min_terminated_length": 356.0, "epoch": 0.2702331048861091, "frac_reward_zero_std": 0.5, "grad_norm": 0.6240484118461609, "learning_rate": 2.3899999999999996e-07, "loss": 0.0148, "num_tokens": 313580404.0, "reward": 0.75, "reward_std": 0.2020905315876007, "rewards/simpleverify_reward/mean": 0.75, "rewards/simpleverify_reward/std": 0.434714138507843, "step": 1523 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1932.0, "completions/mean_length": 1007.2890625, "completions/mean_terminated_length": 919.0932006835938, "completions/min_length": 396.0, "completions/min_terminated_length": 396.0, "epoch": 0.2704105396233948, "frac_reward_zero_std": 0.25, "grad_norm": 0.6516265273094177, "learning_rate": 2.3849999999999997e-07, "loss": 0.0036, "num_tokens": 313721865.0, "reward": 0.7421875, "reward_std": 0.2473391890525818, "rewards/simpleverify_reward/mean": 0.7421875, "rewards/simpleverify_reward/std": 0.43914902210235596, "step": 1524 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 1994.0, "completions/mean_length": 1325.1640625, "completions/mean_terminated_length": 1084.21875, "completions/min_length": 369.0, "completions/min_terminated_length": 369.0, "epoch": 0.27058797436068044, "frac_reward_zero_std": 0.0, "grad_norm": 0.6647433638572693, "learning_rate": 2.38e-07, "loss": 0.0144, "num_tokens": 313901582.0, "reward": 0.4296875, "reward_std": 0.39091694355010986, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1525 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1322.6640625, "completions/mean_terminated_length": 1137.7745361328125, "completions/min_length": 379.0, "completions/min_terminated_length": 379.0, "epoch": 0.27076540909796615, "frac_reward_zero_std": 0.25, "grad_norm": 0.6442816257476807, "learning_rate": 2.3749999999999998e-07, "loss": -0.0258, "num_tokens": 314080979.0, "reward": 0.453125, "reward_std": 0.31777340173721313, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1526 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1313.9609375, "completions/mean_terminated_length": 1089.255126953125, "completions/min_length": 383.0, "completions/min_terminated_length": 383.0, "epoch": 0.27094284383525186, "frac_reward_zero_std": 0.125, "grad_norm": 0.7874903082847595, "learning_rate": 2.3699999999999996e-07, "loss": 0.0002, "num_tokens": 314259262.0, "reward": 0.4140625, "reward_std": 0.40072083473205566, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1527 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2013.0, "completions/mean_length": 1333.890625, "completions/mean_terminated_length": 1105.6700439453125, "completions/min_length": 354.0, "completions/min_terminated_length": 354.0, "epoch": 0.27112027857253757, "frac_reward_zero_std": 0.25, "grad_norm": 0.5938149690628052, "learning_rate": 2.3649999999999998e-07, "loss": 0.0121, "num_tokens": 314440096.0, "reward": 0.5234375, "reward_std": 0.3021235167980194, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1528 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1427.4296875, "completions/mean_terminated_length": 1193.8817138671875, "completions/min_length": 546.0, "completions/min_terminated_length": 546.0, "epoch": 0.2712977133098232, "frac_reward_zero_std": 0.375, "grad_norm": 0.5182876586914062, "learning_rate": 2.3599999999999997e-07, "loss": 0.0026, "num_tokens": 314633031.0, "reward": 0.5390625, "reward_std": 0.2695651650428772, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1529 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2000.0, "completions/mean_length": 1461.5546875, "completions/mean_terminated_length": 1143.6024169921875, "completions/min_length": 573.0, "completions/min_terminated_length": 573.0, "epoch": 0.2714751480471089, "frac_reward_zero_std": 0.25, "grad_norm": 0.5350605845451355, "learning_rate": 2.3549999999999998e-07, "loss": 0.0283, "num_tokens": 314830334.0, "reward": 0.4453125, "reward_std": 0.31226465106010437, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1530 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1466.9765625, "completions/mean_terminated_length": 1193.160888671875, "completions/min_length": 517.0, "completions/min_terminated_length": 517.0, "epoch": 0.27165258278439464, "frac_reward_zero_std": 0.25, "grad_norm": 0.5414671301841736, "learning_rate": 2.3499999999999997e-07, "loss": 0.0049, "num_tokens": 315028331.0, "reward": 0.4921875, "reward_std": 0.3118125796318054, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1531 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2021.0, "completions/mean_length": 1459.890625, "completions/mean_terminated_length": 1141.0361328125, "completions/min_length": 562.0, "completions/min_terminated_length": 562.0, "epoch": 0.2718300175216803, "frac_reward_zero_std": 0.25, "grad_norm": 0.5536431670188904, "learning_rate": 2.3449999999999996e-07, "loss": 0.0128, "num_tokens": 315225421.0, "reward": 0.4140625, "reward_std": 0.2893695533275604, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1532 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2023.0, "completions/mean_length": 1276.703125, "completions/mean_terminated_length": 1107.75244140625, "completions/min_length": 413.0, "completions/min_terminated_length": 413.0, "epoch": 0.272007452258966, "frac_reward_zero_std": 0.125, "grad_norm": 0.6039083003997803, "learning_rate": 2.34e-07, "loss": 0.0101, "num_tokens": 315396343.0, "reward": 0.4765625, "reward_std": 0.3917190432548523, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1533 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1279.2421875, "completions/mean_terminated_length": 1083.2843017578125, "completions/min_length": 484.0, "completions/min_terminated_length": 484.0, "epoch": 0.2721848869962517, "frac_reward_zero_std": 0.25, "grad_norm": 0.5486680865287781, "learning_rate": 2.335e-07, "loss": -0.0079, "num_tokens": 315567590.0, "reward": 0.40625, "reward_std": 0.28417789936065674, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1534 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1270.4453125, "completions/mean_terminated_length": 1109.0660400390625, "completions/min_length": 418.0, "completions/min_terminated_length": 418.0, "epoch": 0.27236232173353736, "frac_reward_zero_std": 0.0, "grad_norm": 0.7663577198982239, "learning_rate": 2.33e-07, "loss": -0.0077, "num_tokens": 315737711.0, "reward": 0.4609375, "reward_std": 0.4236064851284027, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1535 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1277.6015625, "completions/mean_terminated_length": 1081.2255859375, "completions/min_length": 424.0, "completions/min_terminated_length": 424.0, "epoch": 0.27253975647082307, "frac_reward_zero_std": 0.25, "grad_norm": 0.5368286967277527, "learning_rate": 2.325e-07, "loss": 0.0338, "num_tokens": 315908748.0, "reward": 0.4453125, "reward_std": 0.3311648368835449, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1536 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1129.6796875, "completions/mean_terminated_length": 949.4485473632812, "completions/min_length": 348.0, "completions/min_terminated_length": 348.0, "epoch": 0.2727171912081088, "frac_reward_zero_std": 0.25, "grad_norm": 0.8199437856674194, "learning_rate": 2.32e-07, "loss": 0.0144, "num_tokens": 316065299.0, "reward": 0.71875, "reward_std": 0.29248809814453125, "rewards/simpleverify_reward/mean": 0.71875, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 1537 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1936.0, "completions/mean_length": 1109.546875, "completions/mean_terminated_length": 914.7736206054688, "completions/min_length": 328.0, "completions/min_terminated_length": 328.0, "epoch": 0.2728946259453945, "frac_reward_zero_std": 0.625, "grad_norm": 0.4644268751144409, "learning_rate": 2.315e-07, "loss": 0.0064, "num_tokens": 316219273.0, "reward": 0.7578125, "reward_std": 0.17584684491157532, "rewards/simpleverify_reward/mean": 0.7578125, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 1538 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1877.0, "completions/mean_length": 1148.984375, "completions/mean_terminated_length": 982.5, "completions/min_length": 363.0, "completions/min_terminated_length": 363.0, "epoch": 0.27307206068268014, "frac_reward_zero_std": 0.375, "grad_norm": 0.7115219235420227, "learning_rate": 2.31e-07, "loss": 0.0166, "num_tokens": 316378295.0, "reward": 0.7578125, "reward_std": 0.24600867927074432, "rewards/simpleverify_reward/mean": 0.7578125, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 1539 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1965.0, "completions/mean_length": 1127.3828125, "completions/mean_terminated_length": 914.9327392578125, "completions/min_length": 349.0, "completions/min_terminated_length": 349.0, "epoch": 0.27324949541996585, "frac_reward_zero_std": 0.375, "grad_norm": 0.6862944960594177, "learning_rate": 2.305e-07, "loss": 0.0241, "num_tokens": 316534552.0, "reward": 0.703125, "reward_std": 0.25718632340431213, "rewards/simpleverify_reward/mean": 0.703125, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 1540 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1856.0, "completions/mean_length": 1195.765625, "completions/mean_terminated_length": 934.8775024414062, "completions/min_length": 563.0, "completions/min_terminated_length": 563.0, "epoch": 0.27342693015725156, "frac_reward_zero_std": 0.5, "grad_norm": 0.49189430475234985, "learning_rate": 2.3e-07, "loss": -0.0007, "num_tokens": 316702858.0, "reward": 0.5, "reward_std": 0.125, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 1541 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2010.0, "completions/mean_length": 1235.296875, "completions/mean_terminated_length": 1018.0396118164062, "completions/min_length": 536.0, "completions/min_terminated_length": 536.0, "epoch": 0.2736043648945372, "frac_reward_zero_std": 0.25, "grad_norm": 0.7656846046447754, "learning_rate": 2.295e-07, "loss": 0.0043, "num_tokens": 316876224.0, "reward": 0.5078125, "reward_std": 0.26581305265426636, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1542 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2021.0, "completions/mean_length": 1228.3984375, "completions/mean_terminated_length": 966.4638671875, "completions/min_length": 539.0, "completions/min_terminated_length": 539.0, "epoch": 0.2737817996318229, "frac_reward_zero_std": 0.625, "grad_norm": 0.5174285173416138, "learning_rate": 2.29e-07, "loss": 0.0097, "num_tokens": 317048707.0, "reward": 0.5078125, "reward_std": 0.13578036427497864, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1543 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1244.234375, "completions/mean_terminated_length": 998.1836547851562, "completions/min_length": 512.0, "completions/min_terminated_length": 512.0, "epoch": 0.27395923436910863, "frac_reward_zero_std": 0.375, "grad_norm": 0.5738860964775085, "learning_rate": 2.285e-07, "loss": 0.0167, "num_tokens": 317223217.0, "reward": 0.46875, "reward_std": 0.18683473765850067, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1544 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2011.0, "completions/mean_length": 1363.4765625, "completions/mean_terminated_length": 1205.5096435546875, "completions/min_length": 471.0, "completions/min_terminated_length": 471.0, "epoch": 0.2741366691063943, "frac_reward_zero_std": 0.125, "grad_norm": 0.6500445604324341, "learning_rate": 2.28e-07, "loss": 0.0207, "num_tokens": 317407982.0, "reward": 0.609375, "reward_std": 0.38027340173721313, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1545 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1356.9765625, "completions/mean_terminated_length": 1197.5096435546875, "completions/min_length": 488.0, "completions/min_terminated_length": 488.0, "epoch": 0.27431410384368, "frac_reward_zero_std": 0.0, "grad_norm": 0.6333335041999817, "learning_rate": 2.275e-07, "loss": 0.0195, "num_tokens": 317591915.0, "reward": 0.546875, "reward_std": 0.42832648754119873, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1546 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1971.0, "completions/mean_length": 1357.8203125, "completions/mean_terminated_length": 1222.364501953125, "completions/min_length": 545.0, "completions/min_terminated_length": 545.0, "epoch": 0.2744915385809657, "frac_reward_zero_std": 0.375, "grad_norm": 0.4860689043998718, "learning_rate": 2.27e-07, "loss": 0.0113, "num_tokens": 317775956.0, "reward": 0.59375, "reward_std": 0.3008151650428772, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1547 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2002.0, "completions/mean_length": 1361.3515625, "completions/mean_terminated_length": 1186.3236083984375, "completions/min_length": 440.0, "completions/min_terminated_length": 440.0, "epoch": 0.2746689733182514, "frac_reward_zero_std": 0.375, "grad_norm": 0.469070702791214, "learning_rate": 2.265e-07, "loss": 0.0214, "num_tokens": 317960449.0, "reward": 0.609375, "reward_std": 0.31308799982070923, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1548 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1447.375, "completions/mean_terminated_length": 1308.769287109375, "completions/min_length": 548.0, "completions/min_terminated_length": 548.0, "epoch": 0.27484640805553706, "frac_reward_zero_std": 0.125, "grad_norm": 0.7080373764038086, "learning_rate": 2.2599999999999999e-07, "loss": -0.011, "num_tokens": 318156449.0, "reward": 0.4375, "reward_std": 0.36933404207229614, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1549 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1437.1171875, "completions/mean_terminated_length": 1323.99072265625, "completions/min_length": 496.0, "completions/min_terminated_length": 496.0, "epoch": 0.27502384279282277, "frac_reward_zero_std": 0.125, "grad_norm": 0.6507850885391235, "learning_rate": 2.255e-07, "loss": -0.0202, "num_tokens": 318351136.0, "reward": 0.4140625, "reward_std": 0.34437090158462524, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1550 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2021.0, "completions/mean_length": 1432.8359375, "completions/mean_terminated_length": 1283.5242919921875, "completions/min_length": 486.0, "completions/min_terminated_length": 486.0, "epoch": 0.2752012775301085, "frac_reward_zero_std": 0.125, "grad_norm": 0.7437512278556824, "learning_rate": 2.25e-07, "loss": 0.0141, "num_tokens": 318545275.0, "reward": 0.484375, "reward_std": 0.357168972492218, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1551 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1417.78125, "completions/mean_terminated_length": 1279.7333984375, "completions/min_length": 478.0, "completions/min_terminated_length": 478.0, "epoch": 0.27537871226739413, "frac_reward_zero_std": 0.25, "grad_norm": 0.5532950162887573, "learning_rate": 2.245e-07, "loss": 0.0172, "num_tokens": 318737487.0, "reward": 0.4453125, "reward_std": 0.31181254982948303, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1552 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1540.2890625, "completions/mean_terminated_length": 1309.5113525390625, "completions/min_length": 381.0, "completions/min_terminated_length": 381.0, "epoch": 0.27555614700467984, "frac_reward_zero_std": 0.125, "grad_norm": 0.6335256099700928, "learning_rate": 2.24e-07, "loss": 0.0202, "num_tokens": 318946196.0, "reward": 0.4609375, "reward_std": 0.34437090158462524, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1553 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1571.5703125, "completions/mean_terminated_length": 1355.0113525390625, "completions/min_length": 619.0, "completions/min_terminated_length": 619.0, "epoch": 0.27573358174196555, "frac_reward_zero_std": 0.125, "grad_norm": 0.6449365019798279, "learning_rate": 2.2349999999999998e-07, "loss": 0.0287, "num_tokens": 319158909.0, "reward": 0.3984375, "reward_std": 0.3820338547229767, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1554 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2013.0, "completions/mean_length": 1534.703125, "completions/mean_terminated_length": 1333.847900390625, "completions/min_length": 453.0, "completions/min_terminated_length": 453.0, "epoch": 0.2759110164792512, "frac_reward_zero_std": 0.125, "grad_norm": 0.6980355381965637, "learning_rate": 2.23e-07, "loss": 0.0096, "num_tokens": 319366903.0, "reward": 0.3671875, "reward_std": 0.36020228266716003, "rewards/simpleverify_reward/mean": 0.3671875, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1555 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1519.4609375, "completions/mean_terminated_length": 1320.54833984375, "completions/min_length": 396.0, "completions/min_terminated_length": 396.0, "epoch": 0.2760884512165369, "frac_reward_zero_std": 0.0, "grad_norm": 0.6587293148040771, "learning_rate": 2.225e-07, "loss": 0.0091, "num_tokens": 319572946.0, "reward": 0.46875, "reward_std": 0.38621029257774353, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1556 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2010.0, "completions/mean_length": 1354.4140625, "completions/mean_terminated_length": 1061.566650390625, "completions/min_length": 417.0, "completions/min_terminated_length": 417.0, "epoch": 0.2762658859538226, "frac_reward_zero_std": 0.25, "grad_norm": 0.6609447002410889, "learning_rate": 2.22e-07, "loss": 0.0213, "num_tokens": 319758759.0, "reward": 0.484375, "reward_std": 0.2520497143268585, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1557 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1336.578125, "completions/mean_terminated_length": 1079.2552490234375, "completions/min_length": 472.0, "completions/min_terminated_length": 472.0, "epoch": 0.2764433206911083, "frac_reward_zero_std": 0.5, "grad_norm": 0.44456326961517334, "learning_rate": 2.215e-07, "loss": 0.0167, "num_tokens": 319942289.0, "reward": 0.5078125, "reward_std": 0.21696737408638, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1558 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1342.765625, "completions/mean_terminated_length": 1056.02197265625, "completions/min_length": 432.0, "completions/min_terminated_length": 432.0, "epoch": 0.276620755428394, "frac_reward_zero_std": 0.375, "grad_norm": 0.7075988054275513, "learning_rate": 2.2099999999999998e-07, "loss": 0.0326, "num_tokens": 320126611.0, "reward": 0.4765625, "reward_std": 0.23173905909061432, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1559 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1354.5546875, "completions/mean_terminated_length": 1083.20654296875, "completions/min_length": 438.0, "completions/min_terminated_length": 438.0, "epoch": 0.2767981901656797, "frac_reward_zero_std": 0.375, "grad_norm": 0.5073733925819397, "learning_rate": 2.205e-07, "loss": 0.0164, "num_tokens": 320312442.0, "reward": 0.46875, "reward_std": 0.23020508885383606, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1560 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1736.1640625, "completions/mean_terminated_length": 1536.269287109375, "completions/min_length": 828.0, "completions/min_terminated_length": 828.0, "epoch": 0.2769756249029654, "frac_reward_zero_std": 0.25, "grad_norm": 0.5365615487098694, "learning_rate": 2.1999999999999998e-07, "loss": 0.0015, "num_tokens": 320548319.0, "reward": 0.296875, "reward_std": 0.29533424973487854, "rewards/simpleverify_reward/mean": 0.296875, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 1561 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1778.734375, "completions/mean_terminated_length": 1569.3055419921875, "completions/min_length": 882.0, "completions/min_terminated_length": 882.0, "epoch": 0.27715305964025105, "frac_reward_zero_std": 0.25, "grad_norm": 0.5511105060577393, "learning_rate": 2.195e-07, "loss": 0.0185, "num_tokens": 320789645.0, "reward": 0.328125, "reward_std": 0.3219776451587677, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1562 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2014.0, "completions/mean_length": 1779.46875, "completions/mean_terminated_length": 1570.611083984375, "completions/min_length": 943.0, "completions/min_terminated_length": 943.0, "epoch": 0.27733049437753676, "frac_reward_zero_std": 0.5, "grad_norm": 0.4374215602874756, "learning_rate": 2.19e-07, "loss": 0.0145, "num_tokens": 321031065.0, "reward": 0.328125, "reward_std": 0.23411095142364502, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1563 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1755.703125, "completions/mean_terminated_length": 1549.146728515625, "completions/min_length": 981.0, "completions/min_terminated_length": 981.0, "epoch": 0.27750792911482247, "frac_reward_zero_std": 0.375, "grad_norm": 0.524825930595398, "learning_rate": 2.1849999999999998e-07, "loss": 0.022, "num_tokens": 321269443.0, "reward": 0.3515625, "reward_std": 0.26350483298301697, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1564 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1176.7265625, "completions/mean_terminated_length": 921.5050659179688, "completions/min_length": 221.0, "completions/min_terminated_length": 221.0, "epoch": 0.2776853638521081, "frac_reward_zero_std": 0.125, "grad_norm": 0.6949015855789185, "learning_rate": 2.18e-07, "loss": 0.0359, "num_tokens": 321429152.0, "reward": 0.375, "reward_std": 0.345456600189209, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 1565 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2011.0, "completions/mean_length": 1168.8828125, "completions/mean_terminated_length": 875.84375, "completions/min_length": 270.0, "completions/min_terminated_length": 270.0, "epoch": 0.27786279858939383, "frac_reward_zero_std": 0.375, "grad_norm": 0.8069576621055603, "learning_rate": 2.1749999999999998e-07, "loss": 0.0301, "num_tokens": 321587857.0, "reward": 0.4140625, "reward_std": 0.27001726627349854, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1566 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1904.0, "completions/mean_length": 1126.3125, "completions/mean_terminated_length": 831.7525634765625, "completions/min_length": 264.0, "completions/min_terminated_length": 264.0, "epoch": 0.27804023332667954, "frac_reward_zero_std": 0.25, "grad_norm": 0.7140054702758789, "learning_rate": 2.17e-07, "loss": 0.0189, "num_tokens": 321741113.0, "reward": 0.4140625, "reward_std": 0.27901527285575867, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1567 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1176.9140625, "completions/mean_terminated_length": 861.8403930664062, "completions/min_length": 305.0, "completions/min_terminated_length": 305.0, "epoch": 0.2782176680639652, "frac_reward_zero_std": 0.375, "grad_norm": 0.7029414772987366, "learning_rate": 2.1649999999999999e-07, "loss": 0.025, "num_tokens": 321900846.0, "reward": 0.4375, "reward_std": 0.27337536215782166, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1568 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1519.734375, "completions/mean_terminated_length": 1202.7750244140625, "completions/min_length": 497.0, "completions/min_terminated_length": 497.0, "epoch": 0.2783951028012509, "frac_reward_zero_std": 0.5, "grad_norm": 0.4664854407310486, "learning_rate": 2.1599999999999998e-07, "loss": 0.0134, "num_tokens": 322105356.0, "reward": 0.4453125, "reward_std": 0.23677173256874084, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1569 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1988.0, "completions/mean_length": 1539.3828125, "completions/mean_terminated_length": 1254.0609130859375, "completions/min_length": 539.0, "completions/min_terminated_length": 539.0, "epoch": 0.2785725375385366, "frac_reward_zero_std": 0.25, "grad_norm": 0.5441316366195679, "learning_rate": 2.155e-07, "loss": 0.0215, "num_tokens": 322312381.0, "reward": 0.375, "reward_std": 0.3122924566268921, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 1570 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1490.0859375, "completions/mean_terminated_length": 1245.6068115234375, "completions/min_length": 524.0, "completions/min_terminated_length": 524.0, "epoch": 0.2787499722758223, "frac_reward_zero_std": 0.375, "grad_norm": 0.5210974216461182, "learning_rate": 2.1499999999999998e-07, "loss": 0.0118, "num_tokens": 322513096.0, "reward": 0.4375, "reward_std": 0.27199089527130127, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1571 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1520.921875, "completions/mean_terminated_length": 1298.3778076171875, "completions/min_length": 526.0, "completions/min_terminated_length": 526.0, "epoch": 0.278927407013108, "frac_reward_zero_std": 0.25, "grad_norm": 0.5555667281150818, "learning_rate": 2.145e-07, "loss": 0.0151, "num_tokens": 322717758.0, "reward": 0.46875, "reward_std": 0.3209404945373535, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1572 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2001.0, "completions/mean_length": 1479.7734375, "completions/mean_terminated_length": 1282.3895263671875, "completions/min_length": 507.0, "completions/min_terminated_length": 507.0, "epoch": 0.2791048417503937, "frac_reward_zero_std": 0.0, "grad_norm": 0.7457099556922913, "learning_rate": 2.1399999999999998e-07, "loss": 0.0239, "num_tokens": 322916241.0, "reward": 0.5, "reward_std": 0.42036622762680054, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 1573 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1949.0, "completions/mean_length": 1511.390625, "completions/mean_terminated_length": 1230.3095703125, "completions/min_length": 584.0, "completions/min_terminated_length": 584.0, "epoch": 0.2792822764876794, "frac_reward_zero_std": 0.0, "grad_norm": 0.693416953086853, "learning_rate": 2.1349999999999997e-07, "loss": 0.0319, "num_tokens": 323118771.0, "reward": 0.46875, "reward_std": 0.37719598412513733, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1574 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1531.53125, "completions/mean_terminated_length": 1251.51806640625, "completions/min_length": 629.0, "completions/min_terminated_length": 629.0, "epoch": 0.27945971122496505, "frac_reward_zero_std": 0.125, "grad_norm": 0.6497524976730347, "learning_rate": 2.13e-07, "loss": 0.0269, "num_tokens": 323323879.0, "reward": 0.453125, "reward_std": 0.3716517388820648, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1575 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1477.375, "completions/mean_terminated_length": 1208.459716796875, "completions/min_length": 407.0, "completions/min_terminated_length": 407.0, "epoch": 0.27963714596225075, "frac_reward_zero_std": 0.0, "grad_norm": 0.73150634765625, "learning_rate": 2.1249999999999998e-07, "loss": 0.0471, "num_tokens": 323522055.0, "reward": 0.4609375, "reward_std": 0.39547502994537354, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1576 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1990.0, "completions/mean_length": 1732.6328125, "completions/mean_terminated_length": 1012.94873046875, "completions/min_length": 555.0, "completions/min_terminated_length": 555.0, "epoch": 0.27981458069953646, "frac_reward_zero_std": 0.375, "grad_norm": 0.5034419298171997, "learning_rate": 2.12e-07, "loss": 0.0197, "num_tokens": 323759048.0, "reward": 0.28125, "reward_std": 0.20597384870052338, "rewards/simpleverify_reward/mean": 0.28125, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 1577 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.7109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1743.8203125, "completions/mean_terminated_length": 995.7026977539062, "completions/min_length": 508.0, "completions/min_terminated_length": 508.0, "epoch": 0.2799920154368221, "frac_reward_zero_std": 0.375, "grad_norm": 0.5124056339263916, "learning_rate": 2.1149999999999998e-07, "loss": 0.0323, "num_tokens": 323997473.0, "reward": 0.265625, "reward_std": 0.20597384870052338, "rewards/simpleverify_reward/mean": 0.265625, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 1578 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1924.0, "completions/mean_length": 1720.3046875, "completions/mean_terminated_length": 1049.3095703125, "completions/min_length": 546.0, "completions/min_terminated_length": 546.0, "epoch": 0.2801694501741078, "frac_reward_zero_std": 0.375, "grad_norm": 0.507365882396698, "learning_rate": 2.1099999999999997e-07, "loss": 0.0199, "num_tokens": 324232888.0, "reward": 0.2890625, "reward_std": 0.21148642897605896, "rewards/simpleverify_reward/mean": 0.2890625, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 1579 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.65625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1937.0, "completions/mean_length": 1692.5625, "completions/mean_terminated_length": 1014.0, "completions/min_length": 515.0, "completions/min_terminated_length": 515.0, "epoch": 0.28034688491139353, "frac_reward_zero_std": 0.5, "grad_norm": 0.49377891421318054, "learning_rate": 2.1049999999999999e-07, "loss": 0.0115, "num_tokens": 324464752.0, "reward": 0.3125, "reward_std": 0.18090170621871948, "rewards/simpleverify_reward/mean": 0.3125, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 1580 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1027.90625, "completions/mean_terminated_length": 986.43896484375, "completions/min_length": 403.0, "completions/min_terminated_length": 403.0, "epoch": 0.28052431964867924, "frac_reward_zero_std": 0.5, "grad_norm": 0.4959375858306885, "learning_rate": 2.0999999999999997e-07, "loss": 0.0099, "num_tokens": 324606212.0, "reward": 0.609375, "reward_std": 0.21073855459690094, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1581 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.03125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1988.0, "completions/mean_length": 1015.59375, "completions/mean_terminated_length": 982.290283203125, "completions/min_length": 402.0, "completions/min_terminated_length": 402.0, "epoch": 0.2807017543859649, "frac_reward_zero_std": 0.5, "grad_norm": 0.5077772736549377, "learning_rate": 2.095e-07, "loss": 0.0241, "num_tokens": 324746096.0, "reward": 0.59375, "reward_std": 0.22167789936065674, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1582 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1966.0, "completions/mean_length": 1063.2734375, "completions/mean_terminated_length": 997.6250610351562, "completions/min_length": 410.0, "completions/min_terminated_length": 410.0, "epoch": 0.2808791891232506, "frac_reward_zero_std": 0.5, "grad_norm": 0.43885448575019836, "learning_rate": 2.0899999999999998e-07, "loss": 0.0221, "num_tokens": 324892083.0, "reward": 0.59375, "reward_std": 0.19628483057022095, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1583 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.03125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2009.0, "completions/mean_length": 1018.1015625, "completions/mean_terminated_length": 984.8790283203125, "completions/min_length": 395.0, "completions/min_terminated_length": 395.0, "epoch": 0.2810566238605363, "frac_reward_zero_std": 0.375, "grad_norm": 0.5133162140846252, "learning_rate": 2.085e-07, "loss": 0.0089, "num_tokens": 325032288.0, "reward": 0.6484375, "reward_std": 0.22013446688652039, "rewards/simpleverify_reward/mean": 0.6484375, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1584 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1963.0, "completions/mean_length": 1497.859375, "completions/mean_terminated_length": 1282.5870361328125, "completions/min_length": 770.0, "completions/min_terminated_length": 770.0, "epoch": 0.28123405859782197, "frac_reward_zero_std": 0.125, "grad_norm": 0.6191809177398682, "learning_rate": 2.0799999999999998e-07, "loss": 0.0102, "num_tokens": 325234686.0, "reward": 0.3671875, "reward_std": 0.3188629746437073, "rewards/simpleverify_reward/mean": 0.3671875, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1585 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1505.140625, "completions/mean_terminated_length": 1346.1212158203125, "completions/min_length": 562.0, "completions/min_terminated_length": 562.0, "epoch": 0.2814114933351077, "frac_reward_zero_std": 0.375, "grad_norm": 0.5144892334938049, "learning_rate": 2.0749999999999997e-07, "loss": 0.0334, "num_tokens": 325438016.0, "reward": 0.3984375, "reward_std": 0.22753483057022095, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1586 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1485.75, "completions/mean_terminated_length": 1298.3333740234375, "completions/min_length": 542.0, "completions/min_terminated_length": 542.0, "epoch": 0.2815889280723934, "frac_reward_zero_std": 0.25, "grad_norm": 0.5768429636955261, "learning_rate": 2.07e-07, "loss": 0.0321, "num_tokens": 325638864.0, "reward": 0.46875, "reward_std": 0.2711888253688812, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1587 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1520.8359375, "completions/mean_terminated_length": 1330.1595458984375, "completions/min_length": 580.0, "completions/min_terminated_length": 580.0, "epoch": 0.28176636280967904, "frac_reward_zero_std": 0.125, "grad_norm": 0.6082057356834412, "learning_rate": 2.0649999999999998e-07, "loss": 0.0182, "num_tokens": 325844203.0, "reward": 0.421875, "reward_std": 0.3074173331260681, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1588 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1963.0, "completions/mean_length": 1376.015625, "completions/mean_terminated_length": 1092.2889404296875, "completions/min_length": 461.0, "completions/min_terminated_length": 461.0, "epoch": 0.28194379754696475, "frac_reward_zero_std": 0.375, "grad_norm": 0.48313039541244507, "learning_rate": 2.06e-07, "loss": 0.0277, "num_tokens": 326030637.0, "reward": 0.5234375, "reward_std": 0.2905189096927643, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1589 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1355.75, "completions/mean_terminated_length": 1196.0, "completions/min_length": 506.0, "completions/min_terminated_length": 506.0, "epoch": 0.28212123228425046, "frac_reward_zero_std": 0.25, "grad_norm": 0.5902231931686401, "learning_rate": 2.0549999999999998e-07, "loss": 0.0194, "num_tokens": 326214477.0, "reward": 0.578125, "reward_std": 0.2999148368835449, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1590 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1391.1171875, "completions/mean_terminated_length": 1162.9368896484375, "completions/min_length": 424.0, "completions/min_terminated_length": 424.0, "epoch": 0.28229866702153616, "frac_reward_zero_std": 0.25, "grad_norm": 0.5950605869293213, "learning_rate": 2.0499999999999997e-07, "loss": 0.02, "num_tokens": 326402844.0, "reward": 0.5234375, "reward_std": 0.32831305265426636, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1591 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1388.390625, "completions/mean_terminated_length": 1195.1717529296875, "completions/min_length": 498.0, "completions/min_terminated_length": 498.0, "epoch": 0.2824761017588218, "frac_reward_zero_std": 0.125, "grad_norm": 0.616370677947998, "learning_rate": 2.0449999999999998e-07, "loss": 0.0235, "num_tokens": 326590862.0, "reward": 0.5703125, "reward_std": 0.3545081913471222, "rewards/simpleverify_reward/mean": 0.5703125, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1592 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1926.0, "completions/mean_length": 1327.9765625, "completions/mean_terminated_length": 1239.5526123046875, "completions/min_length": 391.0, "completions/min_terminated_length": 391.0, "epoch": 0.2826535364961075, "frac_reward_zero_std": 0.25, "grad_norm": 0.6040993332862854, "learning_rate": 2.0399999999999997e-07, "loss": 0.0402, "num_tokens": 326770203.0, "reward": 0.5859375, "reward_std": 0.3096316456794739, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1593 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1990.0, "completions/mean_length": 1389.6796875, "completions/mean_terminated_length": 1327.786376953125, "completions/min_length": 456.0, "completions/min_terminated_length": 456.0, "epoch": 0.28283097123339324, "frac_reward_zero_std": 0.125, "grad_norm": 0.5878868103027344, "learning_rate": 2.035e-07, "loss": 0.0269, "num_tokens": 326957442.0, "reward": 0.5625, "reward_std": 0.3431389033794403, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1594 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.09375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1372.28125, "completions/mean_terminated_length": 1302.3792724609375, "completions/min_length": 413.0, "completions/min_terminated_length": 413.0, "epoch": 0.2830084059706789, "frac_reward_zero_std": 0.375, "grad_norm": 0.567361056804657, "learning_rate": 2.03e-07, "loss": 0.0133, "num_tokens": 327142454.0, "reward": 0.5546875, "reward_std": 0.26805341243743896, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1595 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.09375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2007.0, "completions/mean_length": 1338.21875, "completions/mean_terminated_length": 1264.7930908203125, "completions/min_length": 371.0, "completions/min_terminated_length": 371.0, "epoch": 0.2831858407079646, "frac_reward_zero_std": 0.125, "grad_norm": 0.7040905952453613, "learning_rate": 2.025e-07, "loss": 0.0185, "num_tokens": 327323106.0, "reward": 0.5234375, "reward_std": 0.339201420545578, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1596 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1924.0, "completions/mean_length": 1412.65625, "completions/mean_terminated_length": 1091.2470703125, "completions/min_length": 501.0, "completions/min_terminated_length": 501.0, "epoch": 0.2833632754452503, "frac_reward_zero_std": 0.625, "grad_norm": 0.4183664917945862, "learning_rate": 2.02e-07, "loss": 0.0074, "num_tokens": 327512022.0, "reward": 0.4609375, "reward_std": 0.19109314680099487, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1597 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1385.484375, "completions/mean_terminated_length": 1095.1685791015625, "completions/min_length": 546.0, "completions/min_terminated_length": 546.0, "epoch": 0.28354071018253596, "frac_reward_zero_std": 0.375, "grad_norm": 0.6132733225822449, "learning_rate": 2.015e-07, "loss": 0.001, "num_tokens": 327697460.0, "reward": 0.4375, "reward_std": 0.23283424973487854, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1598 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1427.390625, "completions/mean_terminated_length": 1102.3095703125, "completions/min_length": 487.0, "completions/min_terminated_length": 487.0, "epoch": 0.28371814491982167, "frac_reward_zero_std": 0.25, "grad_norm": 0.5835340619087219, "learning_rate": 2.01e-07, "loss": 0.0094, "num_tokens": 327888262.0, "reward": 0.4140625, "reward_std": 0.29927176237106323, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1599 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1419.0546875, "completions/mean_terminated_length": 1122.6551513671875, "completions/min_length": 459.0, "completions/min_terminated_length": 459.0, "epoch": 0.2838955796571074, "frac_reward_zero_std": 0.375, "grad_norm": 0.5394343137741089, "learning_rate": 2.005e-07, "loss": 0.0071, "num_tokens": 328077997.0, "reward": 0.40625, "reward_std": 0.2323821485042572, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1600 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2009.0, "completions/mean_length": 909.7890625, "completions/mean_terminated_length": 802.77783203125, "completions/min_length": 392.0, "completions/min_terminated_length": 392.0, "epoch": 0.2840730143943931, "frac_reward_zero_std": 0.5, "grad_norm": 0.6259103417396545, "learning_rate": 2e-07, "loss": 0.0059, "num_tokens": 328206002.0, "reward": 0.6640625, "reward_std": 0.21342839300632477, "rewards/simpleverify_reward/mean": 0.6640625, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1601 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.09375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1918.0, "completions/mean_length": 899.4296875, "completions/mean_terminated_length": 780.612060546875, "completions/min_length": 342.0, "completions/min_terminated_length": 342.0, "epoch": 0.28425044913167874, "frac_reward_zero_std": 0.375, "grad_norm": 0.6901051998138428, "learning_rate": 1.995e-07, "loss": 0.021, "num_tokens": 328332681.0, "reward": 0.6484375, "reward_std": 0.2312908172607422, "rewards/simpleverify_reward/mean": 0.6484375, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1602 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 907.6640625, "completions/mean_terminated_length": 800.4530029296875, "completions/min_length": 374.0, "completions/min_terminated_length": 374.0, "epoch": 0.28442788386896445, "frac_reward_zero_std": 0.375, "grad_norm": 0.7740325927734375, "learning_rate": 1.99e-07, "loss": 0.0083, "num_tokens": 328460414.0, "reward": 0.671875, "reward_std": 0.25423625111579895, "rewards/simpleverify_reward/mean": 0.671875, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1603 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.09375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1902.0, "completions/mean_length": 933.8125, "completions/mean_terminated_length": 818.5516967773438, "completions/min_length": 338.0, "completions/min_terminated_length": 338.0, "epoch": 0.28460531860625016, "frac_reward_zero_std": 0.375, "grad_norm": 0.7991352081298828, "learning_rate": 1.985e-07, "loss": 0.0111, "num_tokens": 328591494.0, "reward": 0.671875, "reward_std": 0.2352283000946045, "rewards/simpleverify_reward/mean": 0.671875, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1604 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1549.421875, "completions/mean_terminated_length": 1338.9111328125, "completions/min_length": 541.0, "completions/min_terminated_length": 541.0, "epoch": 0.2847827533435358, "frac_reward_zero_std": 0.375, "grad_norm": 0.4578897953033447, "learning_rate": 1.98e-07, "loss": -0.0011, "num_tokens": 328799980.0, "reward": 0.484375, "reward_std": 0.2750816345214844, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1605 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1577.3515625, "completions/mean_terminated_length": 1330.8214111328125, "completions/min_length": 686.0, "completions/min_terminated_length": 686.0, "epoch": 0.2849601880808215, "frac_reward_zero_std": 0.125, "grad_norm": 0.6698722839355469, "learning_rate": 1.975e-07, "loss": 0.015, "num_tokens": 329012041.0, "reward": 0.4296875, "reward_std": 0.34380394220352173, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1606 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1573.5390625, "completions/mean_terminated_length": 1357.875, "completions/min_length": 685.0, "completions/min_terminated_length": 685.0, "epoch": 0.28513762281810723, "frac_reward_zero_std": 0.125, "grad_norm": 0.685056209564209, "learning_rate": 1.97e-07, "loss": 0.0072, "num_tokens": 329223614.0, "reward": 0.453125, "reward_std": 0.34043341875076294, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1607 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1560.6640625, "completions/mean_terminated_length": 1296.4456787109375, "completions/min_length": 660.0, "completions/min_terminated_length": 660.0, "epoch": 0.2853150575553929, "frac_reward_zero_std": 0.25, "grad_norm": 0.577598512172699, "learning_rate": 1.965e-07, "loss": -0.011, "num_tokens": 329433539.0, "reward": 0.4609375, "reward_std": 0.30235862731933594, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1608 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1406.859375, "completions/mean_terminated_length": 1201.958740234375, "completions/min_length": 542.0, "completions/min_terminated_length": 542.0, "epoch": 0.2854924922926786, "frac_reward_zero_std": 0.25, "grad_norm": 0.558723509311676, "learning_rate": 1.96e-07, "loss": 0.0172, "num_tokens": 329624785.0, "reward": 0.5625, "reward_std": 0.3365406095981598, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1609 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1976.0, "completions/mean_length": 1333.546875, "completions/mean_terminated_length": 1193.3270263671875, "completions/min_length": 551.0, "completions/min_terminated_length": 551.0, "epoch": 0.2856699270299643, "frac_reward_zero_std": 0.125, "grad_norm": 0.6344190239906311, "learning_rate": 1.955e-07, "loss": 0.0212, "num_tokens": 329806647.0, "reward": 0.5859375, "reward_std": 0.40058404207229614, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1610 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1332.4296875, "completions/mean_terminated_length": 1207.6971435546875, "completions/min_length": 545.0, "completions/min_terminated_length": 545.0, "epoch": 0.28584736176725, "frac_reward_zero_std": 0.25, "grad_norm": 0.5214484930038452, "learning_rate": 1.9499999999999999e-07, "loss": 0.0285, "num_tokens": 329988366.0, "reward": 0.6015625, "reward_std": 0.368827760219574, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1611 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1389.71875, "completions/mean_terminated_length": 1170.291748046875, "completions/min_length": 538.0, "completions/min_terminated_length": 538.0, "epoch": 0.28602479650453566, "frac_reward_zero_std": 0.125, "grad_norm": 0.6231695413589478, "learning_rate": 1.945e-07, "loss": 0.0019, "num_tokens": 330177418.0, "reward": 0.5625, "reward_std": 0.38996243476867676, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1612 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1251.5546875, "completions/mean_terminated_length": 1018.2525024414062, "completions/min_length": 556.0, "completions/min_terminated_length": 556.0, "epoch": 0.28620223124182137, "frac_reward_zero_std": 0.25, "grad_norm": 0.6796825528144836, "learning_rate": 1.94e-07, "loss": 0.0237, "num_tokens": 330350561.0, "reward": 0.5390625, "reward_std": 0.27068254351615906, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1613 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2007.0, "completions/mean_length": 1227.2109375, "completions/mean_terminated_length": 986.7777709960938, "completions/min_length": 474.0, "completions/min_terminated_length": 474.0, "epoch": 0.2863796659791071, "frac_reward_zero_std": 0.25, "grad_norm": 0.725692629814148, "learning_rate": 1.935e-07, "loss": 0.0334, "num_tokens": 330520588.0, "reward": 0.53125, "reward_std": 0.2821281850337982, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1614 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2002.0, "completions/mean_length": 1301.4765625, "completions/mean_terminated_length": 986.27783203125, "completions/min_length": 515.0, "completions/min_terminated_length": 515.0, "epoch": 0.28655710071639273, "frac_reward_zero_std": 0.25, "grad_norm": 0.7107068300247192, "learning_rate": 1.93e-07, "loss": 0.0147, "num_tokens": 330700121.0, "reward": 0.5, "reward_std": 0.30501943826675415, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 1615 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1260.7890625, "completions/mean_terminated_length": 998.3854370117188, "completions/min_length": 568.0, "completions/min_terminated_length": 568.0, "epoch": 0.28673453545367844, "frac_reward_zero_std": 0.25, "grad_norm": 0.641274094581604, "learning_rate": 1.9249999999999998e-07, "loss": 0.0214, "num_tokens": 330874446.0, "reward": 0.5234375, "reward_std": 0.29312169551849365, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1616 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1300.921875, "completions/mean_terminated_length": 1110.490234375, "completions/min_length": 540.0, "completions/min_terminated_length": 540.0, "epoch": 0.28691197019096415, "frac_reward_zero_std": 0.125, "grad_norm": 0.6710767149925232, "learning_rate": 1.92e-07, "loss": 0.0503, "num_tokens": 331056868.0, "reward": 0.671875, "reward_std": 0.3939540982246399, "rewards/simpleverify_reward/mean": 0.671875, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1617 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1972.0, "completions/mean_length": 1256.3984375, "completions/mean_terminated_length": 1101.037353515625, "completions/min_length": 521.0, "completions/min_terminated_length": 521.0, "epoch": 0.2870894049282498, "frac_reward_zero_std": 0.125, "grad_norm": 0.7601807117462158, "learning_rate": 1.915e-07, "loss": 0.0047, "num_tokens": 331233591.0, "reward": 0.671875, "reward_std": 0.3495296835899353, "rewards/simpleverify_reward/mean": 0.671875, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1618 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1285.5078125, "completions/mean_terminated_length": 1118.4857177734375, "completions/min_length": 519.0, "completions/min_terminated_length": 519.0, "epoch": 0.2872668396655355, "frac_reward_zero_std": 0.25, "grad_norm": 0.59100341796875, "learning_rate": 1.91e-07, "loss": 0.0349, "num_tokens": 331414040.0, "reward": 0.671875, "reward_std": 0.3399718403816223, "rewards/simpleverify_reward/mean": 0.671875, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1619 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1271.3046875, "completions/mean_terminated_length": 1082.786376953125, "completions/min_length": 517.0, "completions/min_terminated_length": 517.0, "epoch": 0.2874442744028212, "frac_reward_zero_std": 0.125, "grad_norm": 0.6181972622871399, "learning_rate": 1.905e-07, "loss": 0.0199, "num_tokens": 331592671.0, "reward": 0.6875, "reward_std": 0.34998178482055664, "rewards/simpleverify_reward/mean": 0.6875, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 1620 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2014.0, "completions/mean_length": 1473.6796875, "completions/mean_terminated_length": 1231.18896484375, "completions/min_length": 654.0, "completions/min_terminated_length": 654.0, "epoch": 0.28762170914010693, "frac_reward_zero_std": 0.375, "grad_norm": 0.5768668055534363, "learning_rate": 1.8999999999999998e-07, "loss": 0.0168, "num_tokens": 331792214.0, "reward": 0.546875, "reward_std": 0.2816799283027649, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1621 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2007.0, "completions/mean_length": 1520.6015625, "completions/mean_terminated_length": 1244.34521484375, "completions/min_length": 660.0, "completions/min_terminated_length": 660.0, "epoch": 0.2877991438773926, "frac_reward_zero_std": 0.375, "grad_norm": 0.5381739139556885, "learning_rate": 1.895e-07, "loss": 0.0375, "num_tokens": 331997763.0, "reward": 0.484375, "reward_std": 0.3089885711669922, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1622 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1471.859375, "completions/mean_terminated_length": 1180.4000244140625, "completions/min_length": 676.0, "completions/min_terminated_length": 676.0, "epoch": 0.2879765786146783, "frac_reward_zero_std": 0.375, "grad_norm": 0.5435426235198975, "learning_rate": 1.8899999999999999e-07, "loss": 0.0259, "num_tokens": 332197073.0, "reward": 0.5703125, "reward_std": 0.28343653678894043, "rewards/simpleverify_reward/mean": 0.5703125, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1623 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1955.0, "completions/mean_length": 1487.84375, "completions/mean_terminated_length": 1204.4705810546875, "completions/min_length": 686.0, "completions/min_terminated_length": 686.0, "epoch": 0.288154013351964, "frac_reward_zero_std": 0.25, "grad_norm": 0.6248264908790588, "learning_rate": 1.885e-07, "loss": 0.0149, "num_tokens": 332398429.0, "reward": 0.5, "reward_std": 0.346225768327713, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 1624 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1493.9765625, "completions/mean_terminated_length": 1063.0694580078125, "completions/min_length": 427.0, "completions/min_terminated_length": 427.0, "epoch": 0.28833144808924965, "frac_reward_zero_std": 0.125, "grad_norm": 0.6293219327926636, "learning_rate": 1.88e-07, "loss": 0.0123, "num_tokens": 332604330.0, "reward": 0.375, "reward_std": 0.3432757258415222, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 1625 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1482.984375, "completions/mean_terminated_length": 1108.7532958984375, "completions/min_length": 511.0, "completions/min_terminated_length": 511.0, "epoch": 0.28850888282653536, "frac_reward_zero_std": 0.25, "grad_norm": 0.5535520911216736, "learning_rate": 1.875e-07, "loss": 0.0119, "num_tokens": 332808824.0, "reward": 0.390625, "reward_std": 0.34171009063720703, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1626 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2011.0, "completions/mean_length": 1475.421875, "completions/mean_terminated_length": 1175.5, "completions/min_length": 505.0, "completions/min_terminated_length": 505.0, "epoch": 0.28868631756382107, "frac_reward_zero_std": 0.375, "grad_norm": 0.5120573043823242, "learning_rate": 1.87e-07, "loss": 0.0043, "num_tokens": 333012350.0, "reward": 0.3828125, "reward_std": 0.2759283781051636, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1627 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1995.0, "completions/mean_length": 1504.0703125, "completions/mean_terminated_length": 1107.148681640625, "completions/min_length": 526.0, "completions/min_terminated_length": 526.0, "epoch": 0.2888637523011067, "frac_reward_zero_std": 0.25, "grad_norm": 0.5450478196144104, "learning_rate": 1.8649999999999998e-07, "loss": 0.0212, "num_tokens": 333219543.0, "reward": 0.2890625, "reward_std": 0.3244297206401825, "rewards/simpleverify_reward/mean": 0.2890625, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 1628 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1122.8984375, "completions/mean_terminated_length": 1108.21435546875, "completions/min_length": 472.0, "completions/min_terminated_length": 472.0, "epoch": 0.28904118703839243, "frac_reward_zero_std": 0.375, "grad_norm": 0.5418780446052551, "learning_rate": 1.86e-07, "loss": -0.0054, "num_tokens": 333371226.0, "reward": 0.765625, "reward_std": 0.27619513869285583, "rewards/simpleverify_reward/mean": 0.765625, "rewards/simpleverify_reward/std": 0.42527204751968384, "step": 1629 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2022.0, "completions/mean_length": 1095.2421875, "completions/mean_terminated_length": 1080.119140625, "completions/min_length": 461.0, "completions/min_terminated_length": 461.0, "epoch": 0.28921862177567814, "frac_reward_zero_std": 0.25, "grad_norm": 0.6927297711372375, "learning_rate": 1.855e-07, "loss": -0.005, "num_tokens": 333519369.0, "reward": 0.7578125, "reward_std": 0.32636725902557373, "rewards/simpleverify_reward/mean": 0.7578125, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 1630 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1074.375, "completions/mean_terminated_length": 1051.008056640625, "completions/min_length": 426.0, "completions/min_terminated_length": 426.0, "epoch": 0.28939605651296385, "frac_reward_zero_std": 0.25, "grad_norm": 0.6820957660675049, "learning_rate": 1.85e-07, "loss": -0.0266, "num_tokens": 333664841.0, "reward": 0.71875, "reward_std": 0.3041190803050995, "rewards/simpleverify_reward/mean": 0.71875, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 1631 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1993.0, "completions/mean_length": 1067.90625, "completions/mean_terminated_length": 1052.3492431640625, "completions/min_length": 400.0, "completions/min_terminated_length": 400.0, "epoch": 0.2895734912502495, "frac_reward_zero_std": 0.25, "grad_norm": 0.5843555927276611, "learning_rate": 1.845e-07, "loss": -0.0123, "num_tokens": 333809485.0, "reward": 0.75, "reward_std": 0.2901967763900757, "rewards/simpleverify_reward/mean": 0.75, "rewards/simpleverify_reward/std": 0.434714138507843, "step": 1632 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2019.0, "completions/mean_length": 1358.390625, "completions/mean_terminated_length": 1215.26416015625, "completions/min_length": 659.0, "completions/min_terminated_length": 659.0, "epoch": 0.2897509259875352, "frac_reward_zero_std": 0.375, "grad_norm": 0.49597713351249695, "learning_rate": 1.8399999999999998e-07, "loss": 0.0241, "num_tokens": 333994271.0, "reward": 0.4296875, "reward_std": 0.2845000624656677, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1633 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2011.0, "completions/mean_length": 1352.90625, "completions/mean_terminated_length": 1184.1942138671875, "completions/min_length": 583.0, "completions/min_terminated_length": 583.0, "epoch": 0.2899283607248209, "frac_reward_zero_std": 0.125, "grad_norm": 0.697268545627594, "learning_rate": 1.835e-07, "loss": -0.0034, "num_tokens": 334178355.0, "reward": 0.5078125, "reward_std": 0.3105320334434509, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1634 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1352.0, "completions/mean_terminated_length": 1215.40185546875, "completions/min_length": 422.0, "completions/min_terminated_length": 422.0, "epoch": 0.2901057954621066, "frac_reward_zero_std": 0.5, "grad_norm": 0.4687853455543518, "learning_rate": 1.8299999999999998e-07, "loss": 0.0074, "num_tokens": 334362323.0, "reward": 0.4765625, "reward_std": 0.20818254351615906, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1635 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1364.3359375, "completions/mean_terminated_length": 1214.5810546875, "completions/min_length": 610.0, "completions/min_terminated_length": 610.0, "epoch": 0.2902832301993923, "frac_reward_zero_std": 0.25, "grad_norm": 0.6099880933761597, "learning_rate": 1.825e-07, "loss": 0.0013, "num_tokens": 334547870.0, "reward": 0.46875, "reward_std": 0.2849799692630768, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1636 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1380.265625, "completions/mean_terminated_length": 1118.978271484375, "completions/min_length": 467.0, "completions/min_terminated_length": 467.0, "epoch": 0.290460664936678, "frac_reward_zero_std": 0.25, "grad_norm": 0.6416499614715576, "learning_rate": 1.82e-07, "loss": 0.0274, "num_tokens": 334738288.0, "reward": 0.4921875, "reward_std": 0.3017735779285431, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1637 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1372.2421875, "completions/mean_terminated_length": 1117.9246826171875, "completions/min_length": 524.0, "completions/min_terminated_length": 524.0, "epoch": 0.29063809967396365, "frac_reward_zero_std": 0.0, "grad_norm": 0.7075250744819641, "learning_rate": 1.8149999999999998e-07, "loss": 0.0445, "num_tokens": 334927679.0, "reward": 0.5, "reward_std": 0.41578567028045654, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 1638 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2018.0, "completions/mean_length": 1378.109375, "completions/mean_terminated_length": 1135.8084716796875, "completions/min_length": 523.0, "completions/min_terminated_length": 523.0, "epoch": 0.29081553441124935, "frac_reward_zero_std": 0.25, "grad_norm": 0.5859790444374084, "learning_rate": 1.81e-07, "loss": 0.0367, "num_tokens": 335117821.0, "reward": 0.4765625, "reward_std": 0.3242127299308777, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1639 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1392.8515625, "completions/mean_terminated_length": 1174.46875, "completions/min_length": 548.0, "completions/min_terminated_length": 548.0, "epoch": 0.29099296914853506, "frac_reward_zero_std": 0.125, "grad_norm": 0.6112595796585083, "learning_rate": 1.8049999999999998e-07, "loss": 0.0366, "num_tokens": 335309850.0, "reward": 0.4609375, "reward_std": 0.3228282630443573, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1640 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1325.8828125, "completions/mean_terminated_length": 997.6477661132812, "completions/min_length": 506.0, "completions/min_terminated_length": 506.0, "epoch": 0.29117040388582077, "frac_reward_zero_std": 0.5, "grad_norm": 0.5462923645973206, "learning_rate": 1.8e-07, "loss": 0.0088, "num_tokens": 335492363.0, "reward": 0.5234375, "reward_std": 0.21353617310523987, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1641 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1354.4140625, "completions/mean_terminated_length": 1039.147705078125, "completions/min_length": 484.0, "completions/min_terminated_length": 484.0, "epoch": 0.2913478386231064, "frac_reward_zero_std": 0.25, "grad_norm": 0.6191162467002869, "learning_rate": 1.7949999999999999e-07, "loss": 0.0373, "num_tokens": 335678528.0, "reward": 0.5390625, "reward_std": 0.31383588910102844, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1642 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1348.4375, "completions/mean_terminated_length": 1018.7586059570312, "completions/min_length": 490.0, "completions/min_terminated_length": 490.0, "epoch": 0.29152527336039213, "frac_reward_zero_std": 0.125, "grad_norm": 0.6425727009773254, "learning_rate": 1.7899999999999997e-07, "loss": 0.005, "num_tokens": 335863928.0, "reward": 0.515625, "reward_std": 0.2947453558444977, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1643 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1327.828125, "completions/mean_terminated_length": 1023.7555541992188, "completions/min_length": 499.0, "completions/min_terminated_length": 499.0, "epoch": 0.29170270809767784, "frac_reward_zero_std": 0.5, "grad_norm": 0.46548891067504883, "learning_rate": 1.785e-07, "loss": 0.017, "num_tokens": 336046690.0, "reward": 0.59375, "reward_std": 0.199823796749115, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1644 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1527.578125, "completions/mean_terminated_length": 1235.6341552734375, "completions/min_length": 440.0, "completions/min_terminated_length": 440.0, "epoch": 0.2918801428349635, "frac_reward_zero_std": 0.25, "grad_norm": 0.510766327381134, "learning_rate": 1.7799999999999998e-07, "loss": 0.0271, "num_tokens": 336251916.0, "reward": 0.5234375, "reward_std": 0.29927173256874084, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1645 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1505.2890625, "completions/mean_terminated_length": 1240.244140625, "completions/min_length": 626.0, "completions/min_terminated_length": 626.0, "epoch": 0.2920575775722492, "frac_reward_zero_std": 0.625, "grad_norm": 0.4232046902179718, "learning_rate": 1.775e-07, "loss": 0.0068, "num_tokens": 336454289.0, "reward": 0.6328125, "reward_std": 0.16708454489707947, "rewards/simpleverify_reward/mean": 0.6328125, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1646 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2006.0, "completions/mean_length": 1522.578125, "completions/mean_terminated_length": 1300.7333984375, "completions/min_length": 583.0, "completions/min_terminated_length": 583.0, "epoch": 0.2922350123095349, "frac_reward_zero_std": 0.375, "grad_norm": 0.5076855421066284, "learning_rate": 1.7699999999999998e-07, "loss": 0.0092, "num_tokens": 336658875.0, "reward": 0.59375, "reward_std": 0.24148227274417877, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1647 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1510.828125, "completions/mean_terminated_length": 1275.438232421875, "completions/min_length": 649.0, "completions/min_terminated_length": 649.0, "epoch": 0.29241244704682057, "frac_reward_zero_std": 0.375, "grad_norm": 0.5586110949516296, "learning_rate": 1.7649999999999997e-07, "loss": 0.027, "num_tokens": 336861957.0, "reward": 0.5625, "reward_std": 0.26472732424736023, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1648 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1968.0, "completions/mean_length": 1338.34375, "completions/mean_terminated_length": 1130.464599609375, "completions/min_length": 392.0, "completions/min_terminated_length": 392.0, "epoch": 0.2925898817841063, "frac_reward_zero_std": 0.0, "grad_norm": 0.72336745262146, "learning_rate": 1.76e-07, "loss": 0.0159, "num_tokens": 337044225.0, "reward": 0.7109375, "reward_std": 0.4347948431968689, "rewards/simpleverify_reward/mean": 0.7109375, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 1649 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1913.0, "completions/mean_length": 1317.15625, "completions/mean_terminated_length": 1103.0706787109375, "completions/min_length": 470.0, "completions/min_terminated_length": 470.0, "epoch": 0.292767316521392, "frac_reward_zero_std": 0.0, "grad_norm": 0.7600106596946716, "learning_rate": 1.7549999999999998e-07, "loss": 0.0402, "num_tokens": 337223781.0, "reward": 0.703125, "reward_std": 0.41091614961624146, "rewards/simpleverify_reward/mean": 0.703125, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 1650 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2022.0, "completions/mean_length": 1302.890625, "completions/mean_terminated_length": 1103.7030029296875, "completions/min_length": 372.0, "completions/min_terminated_length": 372.0, "epoch": 0.2929447512586777, "frac_reward_zero_std": 0.125, "grad_norm": 0.7825155854225159, "learning_rate": 1.75e-07, "loss": 0.0327, "num_tokens": 337401511.0, "reward": 0.7421875, "reward_std": 0.36883723735809326, "rewards/simpleverify_reward/mean": 0.7421875, "rewards/simpleverify_reward/std": 0.43914902210235596, "step": 1651 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1314.84375, "completions/mean_terminated_length": 1100.080810546875, "completions/min_length": 375.0, "completions/min_terminated_length": 375.0, "epoch": 0.29312218599596335, "frac_reward_zero_std": 0.0, "grad_norm": 0.7196303606033325, "learning_rate": 1.7449999999999998e-07, "loss": 0.0291, "num_tokens": 337580771.0, "reward": 0.6875, "reward_std": 0.4289020895957947, "rewards/simpleverify_reward/mean": 0.6875, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 1652 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1099.1796875, "completions/mean_terminated_length": 982.6578979492188, "completions/min_length": 322.0, "completions/min_terminated_length": 322.0, "epoch": 0.29329962073324906, "frac_reward_zero_std": 0.0, "grad_norm": 0.8575593829154968, "learning_rate": 1.7399999999999997e-07, "loss": -0.0035, "num_tokens": 337733642.0, "reward": 0.5078125, "reward_std": 0.414585679769516, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1653 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1092.0234375, "completions/mean_terminated_length": 974.622802734375, "completions/min_length": 305.0, "completions/min_terminated_length": 305.0, "epoch": 0.29347705547053476, "frac_reward_zero_std": 0.125, "grad_norm": 0.8427969813346863, "learning_rate": 1.7349999999999999e-07, "loss": -0.0056, "num_tokens": 337885597.0, "reward": 0.453125, "reward_std": 0.33084267377853394, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1654 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1983.0, "completions/mean_length": 1116.234375, "completions/mean_terminated_length": 973.5315551757812, "completions/min_length": 291.0, "completions/min_terminated_length": 291.0, "epoch": 0.2936544902078204, "frac_reward_zero_std": 0.125, "grad_norm": 0.7952362298965454, "learning_rate": 1.7299999999999997e-07, "loss": 0.0306, "num_tokens": 338040651.0, "reward": 0.53125, "reward_std": 0.3793674111366272, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1655 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2005.0, "completions/mean_length": 1124.875, "completions/mean_terminated_length": 973.8181762695312, "completions/min_length": 345.0, "completions/min_terminated_length": 345.0, "epoch": 0.2938319249451061, "frac_reward_zero_std": 0.125, "grad_norm": 0.7248344421386719, "learning_rate": 1.725e-07, "loss": 0.012, "num_tokens": 338196811.0, "reward": 0.5078125, "reward_std": 0.37146639823913574, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1656 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1556.2578125, "completions/mean_terminated_length": 1412.212158203125, "completions/min_length": 649.0, "completions/min_terminated_length": 649.0, "epoch": 0.29400935968239184, "frac_reward_zero_std": 0.125, "grad_norm": 0.6096704602241516, "learning_rate": 1.7199999999999998e-07, "loss": 0.0277, "num_tokens": 338406108.0, "reward": 0.3359375, "reward_std": 0.4186058044433594, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1657 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1578.046875, "completions/mean_terminated_length": 1331.8809814453125, "completions/min_length": 665.0, "completions/min_terminated_length": 665.0, "epoch": 0.2941867944196775, "frac_reward_zero_std": 0.25, "grad_norm": 0.6251875162124634, "learning_rate": 1.715e-07, "loss": 0.0218, "num_tokens": 338618194.0, "reward": 0.28125, "reward_std": 0.32940438389778137, "rewards/simpleverify_reward/mean": 0.28125, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 1658 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1578.1796875, "completions/mean_terminated_length": 1387.1539306640625, "completions/min_length": 672.0, "completions/min_terminated_length": 672.0, "epoch": 0.2943642291569632, "frac_reward_zero_std": 0.125, "grad_norm": 0.598021924495697, "learning_rate": 1.71e-07, "loss": 0.0209, "num_tokens": 338830297.0, "reward": 0.328125, "reward_std": 0.39190438389778137, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1659 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1553.234375, "completions/mean_terminated_length": 1374.276611328125, "completions/min_length": 731.0, "completions/min_terminated_length": 731.0, "epoch": 0.2945416638942489, "frac_reward_zero_std": 0.25, "grad_norm": 0.5330653786659241, "learning_rate": 1.705e-07, "loss": 0.0185, "num_tokens": 339039207.0, "reward": 0.3046875, "reward_std": 0.3323861360549927, "rewards/simpleverify_reward/mean": 0.3046875, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 1660 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1936.0, "completions/mean_length": 1441.859375, "completions/mean_terminated_length": 1078.175048828125, "completions/min_length": 364.0, "completions/min_terminated_length": 364.0, "epoch": 0.2947190986315346, "frac_reward_zero_std": 0.625, "grad_norm": 0.46293768286705017, "learning_rate": 1.7000000000000001e-07, "loss": 0.0107, "num_tokens": 339238709.0, "reward": 0.4453125, "reward_std": 0.1414783000946045, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1661 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1909.0, "completions/mean_length": 1402.71875, "completions/mean_terminated_length": 1040.731689453125, "completions/min_length": 354.0, "completions/min_terminated_length": 354.0, "epoch": 0.29489653336882027, "frac_reward_zero_std": 0.5, "grad_norm": 0.4968985915184021, "learning_rate": 1.695e-07, "loss": 0.0135, "num_tokens": 339433201.0, "reward": 0.4453125, "reward_std": 0.18837818503379822, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1662 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1982.0, "completions/mean_length": 1401.875, "completions/mean_terminated_length": 1014.2000122070312, "completions/min_length": 380.0, "completions/min_terminated_length": 380.0, "epoch": 0.295073968106106, "frac_reward_zero_std": 0.75, "grad_norm": 0.4104657471179962, "learning_rate": 1.69e-07, "loss": 0.0017, "num_tokens": 339627585.0, "reward": 0.421875, "reward_std": 0.10724534839391708, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1663 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2001.0, "completions/mean_length": 1423.6328125, "completions/mean_terminated_length": 1073.3780517578125, "completions/min_length": 372.0, "completions/min_terminated_length": 372.0, "epoch": 0.2952514028433917, "frac_reward_zero_std": 0.5, "grad_norm": 0.5187285542488098, "learning_rate": 1.685e-07, "loss": 0.003, "num_tokens": 339824754.0, "reward": 0.4453125, "reward_std": 0.19738000631332397, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1664 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2001.0, "completions/mean_length": 1119.15625, "completions/mean_terminated_length": 926.3773803710938, "completions/min_length": 469.0, "completions/min_terminated_length": 469.0, "epoch": 0.29542883758067734, "frac_reward_zero_std": 0.25, "grad_norm": 0.6334227919578552, "learning_rate": 1.68e-07, "loss": -0.0161, "num_tokens": 339978310.0, "reward": 0.625, "reward_std": 0.3334813117980957, "rewards/simpleverify_reward/mean": 0.625, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 1665 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1130.75, "completions/mean_terminated_length": 940.3773803710938, "completions/min_length": 401.0, "completions/min_terminated_length": 401.0, "epoch": 0.29560627231796305, "frac_reward_zero_std": 0.375, "grad_norm": 0.5845961570739746, "learning_rate": 1.675e-07, "loss": -0.0067, "num_tokens": 340133350.0, "reward": 0.6484375, "reward_std": 0.28343650698661804, "rewards/simpleverify_reward/mean": 0.6484375, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1666 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1159.828125, "completions/mean_terminated_length": 954.8654174804688, "completions/min_length": 495.0, "completions/min_terminated_length": 495.0, "epoch": 0.29578370705524876, "frac_reward_zero_std": 0.25, "grad_norm": 0.6015773415565491, "learning_rate": 1.67e-07, "loss": -0.0307, "num_tokens": 340292112.0, "reward": 0.609375, "reward_std": 0.3267752230167389, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1667 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1140.328125, "completions/mean_terminated_length": 920.0194091796875, "completions/min_length": 489.0, "completions/min_terminated_length": 489.0, "epoch": 0.2959611417925344, "frac_reward_zero_std": 0.125, "grad_norm": 0.8211484551429749, "learning_rate": 1.665e-07, "loss": -0.015, "num_tokens": 340448378.0, "reward": 0.5859375, "reward_std": 0.3294360339641571, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1668 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2019.0, "completions/mean_length": 1323.2421875, "completions/mean_terminated_length": 1039.641357421875, "completions/min_length": 424.0, "completions/min_terminated_length": 424.0, "epoch": 0.2961385765298201, "frac_reward_zero_std": 0.5, "grad_norm": 0.6693331599235535, "learning_rate": 1.66e-07, "loss": 0.0063, "num_tokens": 340629657.0, "reward": 0.3046875, "reward_std": 0.23256748914718628, "rewards/simpleverify_reward/mean": 0.3046875, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 1669 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2010.0, "completions/mean_length": 1292.7421875, "completions/mean_terminated_length": 1008.50537109375, "completions/min_length": 417.0, "completions/min_terminated_length": 417.0, "epoch": 0.2963160112671058, "frac_reward_zero_std": 0.625, "grad_norm": 0.5424920320510864, "learning_rate": 1.655e-07, "loss": -0.0041, "num_tokens": 340807032.0, "reward": 0.3203125, "reward_std": 0.15763446688652039, "rewards/simpleverify_reward/mean": 0.3203125, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 1670 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2012.0, "completions/mean_length": 1329.0859375, "completions/mean_terminated_length": 1014.0562133789062, "completions/min_length": 357.0, "completions/min_terminated_length": 357.0, "epoch": 0.29649344600439154, "frac_reward_zero_std": 0.375, "grad_norm": 0.6429799199104309, "learning_rate": 1.65e-07, "loss": 0.0138, "num_tokens": 340989059.0, "reward": 0.3515625, "reward_std": 0.257485955953598, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1671 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1990.0, "completions/mean_length": 1349.8203125, "completions/mean_terminated_length": 996.62353515625, "completions/min_length": 378.0, "completions/min_terminated_length": 378.0, "epoch": 0.2966708807416772, "frac_reward_zero_std": 0.625, "grad_norm": 0.5206194519996643, "learning_rate": 1.645e-07, "loss": 0.0063, "num_tokens": 341173740.0, "reward": 0.3125, "reward_std": 0.18954971432685852, "rewards/simpleverify_reward/mean": 0.3125, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 1672 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2007.0, "completions/mean_length": 1357.6171875, "completions/mean_terminated_length": 995.9880981445312, "completions/min_length": 610.0, "completions/min_terminated_length": 610.0, "epoch": 0.2968483154789629, "frac_reward_zero_std": 0.5, "grad_norm": 0.5070126056671143, "learning_rate": 1.64e-07, "loss": 0.0137, "num_tokens": 341360443.0, "reward": 0.3984375, "reward_std": 0.22753483057022095, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1673 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1376.09375, "completions/mean_terminated_length": 972.9500122070312, "completions/min_length": 511.0, "completions/min_terminated_length": 511.0, "epoch": 0.2970257502162486, "frac_reward_zero_std": 0.375, "grad_norm": 0.6461871266365051, "learning_rate": 1.635e-07, "loss": 0.036, "num_tokens": 341549511.0, "reward": 0.3203125, "reward_std": 0.24667392671108246, "rewards/simpleverify_reward/mean": 0.3203125, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 1674 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2013.0, "completions/mean_length": 1354.171875, "completions/mean_terminated_length": 990.7380981445312, "completions/min_length": 630.0, "completions/min_terminated_length": 630.0, "epoch": 0.29720318495353426, "frac_reward_zero_std": 0.5, "grad_norm": 0.49362051486968994, "learning_rate": 1.63e-07, "loss": 0.0175, "num_tokens": 341735773.0, "reward": 0.421875, "reward_std": 0.20709684491157532, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1675 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1967.0, "completions/mean_length": 1368.59375, "completions/mean_terminated_length": 1000.2409057617188, "completions/min_length": 585.0, "completions/min_terminated_length": 585.0, "epoch": 0.29738061969081997, "frac_reward_zero_std": 0.625, "grad_norm": 0.4246383309364319, "learning_rate": 1.625e-07, "loss": 0.0002, "num_tokens": 341923881.0, "reward": 0.40625, "reward_std": 0.18638263642787933, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1676 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.46875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1637.84375, "completions/mean_terminated_length": 1275.941162109375, "completions/min_length": 575.0, "completions/min_terminated_length": 575.0, "epoch": 0.2975580544281057, "frac_reward_zero_std": 0.375, "grad_norm": 0.45815303921699524, "learning_rate": 1.62e-07, "loss": 0.0132, "num_tokens": 342149285.0, "reward": 0.3984375, "reward_std": 0.259880006313324, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1677 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.53125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1646.453125, "completions/mean_terminated_length": 1191.36669921875, "completions/min_length": 490.0, "completions/min_terminated_length": 490.0, "epoch": 0.29773548916539133, "frac_reward_zero_std": 0.5, "grad_norm": 0.410282701253891, "learning_rate": 1.615e-07, "loss": 0.0044, "num_tokens": 342375791.0, "reward": 0.359375, "reward_std": 0.19628481566905975, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 1678 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1678.78125, "completions/mean_terminated_length": 1285.741943359375, "completions/min_length": 541.0, "completions/min_terminated_length": 541.0, "epoch": 0.29791292390267704, "frac_reward_zero_std": 0.375, "grad_norm": 0.4491287171840668, "learning_rate": 1.61e-07, "loss": -0.0016, "num_tokens": 342606435.0, "reward": 0.40625, "reward_std": 0.2464885711669922, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1679 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1665.3828125, "completions/mean_terminated_length": 1294.5384521484375, "completions/min_length": 588.0, "completions/min_terminated_length": 588.0, "epoch": 0.29809035863996275, "frac_reward_zero_std": 0.5, "grad_norm": 0.3970786929130554, "learning_rate": 1.605e-07, "loss": 0.0171, "num_tokens": 342835364.0, "reward": 0.390625, "reward_std": 0.22466085851192474, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1680 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2022.0, "completions/mean_length": 1180.9921875, "completions/mean_terminated_length": 1145.7479248046875, "completions/min_length": 390.0, "completions/min_terminated_length": 390.0, "epoch": 0.29826779337724846, "frac_reward_zero_std": 0.375, "grad_norm": 0.5731014013290405, "learning_rate": 1.6e-07, "loss": 0.0445, "num_tokens": 342996547.0, "reward": 0.6953125, "reward_std": 0.28343653678894043, "rewards/simpleverify_reward/mean": 0.6953125, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 1681 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1247.171875, "completions/mean_terminated_length": 1148.8245849609375, "completions/min_length": 360.0, "completions/min_terminated_length": 360.0, "epoch": 0.2984452281145341, "frac_reward_zero_std": 0.25, "grad_norm": 0.6650973558425903, "learning_rate": 1.595e-07, "loss": 0.0362, "num_tokens": 343166201.0, "reward": 0.6171875, "reward_std": 0.33603435754776, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1682 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0546875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1201.0, "completions/mean_terminated_length": 1152.0, "completions/min_length": 388.0, "completions/min_terminated_length": 388.0, "epoch": 0.2986226628518198, "frac_reward_zero_std": 0.25, "grad_norm": 0.5670868158340454, "learning_rate": 1.59e-07, "loss": 0.0334, "num_tokens": 343329945.0, "reward": 0.625, "reward_std": 0.32642143964767456, "rewards/simpleverify_reward/mean": 0.625, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 1683 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.09375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1246.9921875, "completions/mean_terminated_length": 1164.1292724609375, "completions/min_length": 423.0, "completions/min_terminated_length": 423.0, "epoch": 0.29880009758910553, "frac_reward_zero_std": 0.25, "grad_norm": 0.5593337416648865, "learning_rate": 1.585e-07, "loss": 0.0232, "num_tokens": 343499576.0, "reward": 0.6328125, "reward_std": 0.33808404207229614, "rewards/simpleverify_reward/mean": 0.6328125, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1684 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1974.0, "completions/mean_length": 1392.9453125, "completions/mean_terminated_length": 1165.4000244140625, "completions/min_length": 612.0, "completions/min_terminated_length": 612.0, "epoch": 0.2989775323263912, "frac_reward_zero_std": 0.125, "grad_norm": 0.651786744594574, "learning_rate": 1.5799999999999999e-07, "loss": 0.0231, "num_tokens": 343689825.0, "reward": 0.4921875, "reward_std": 0.3785129487514496, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1685 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1999.0, "completions/mean_length": 1394.25, "completions/mean_terminated_length": 1157.7872314453125, "completions/min_length": 661.0, "completions/min_terminated_length": 661.0, "epoch": 0.2991549670636769, "frac_reward_zero_std": 0.25, "grad_norm": 0.5417504906654358, "learning_rate": 1.575e-07, "loss": 0.0372, "num_tokens": 343880241.0, "reward": 0.5234375, "reward_std": 0.2956235110759735, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1686 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2009.0, "completions/mean_length": 1466.2109375, "completions/mean_terminated_length": 1201.7613525390625, "completions/min_length": 645.0, "completions/min_terminated_length": 645.0, "epoch": 0.2993324018009626, "frac_reward_zero_std": 0.125, "grad_norm": 0.6399005651473999, "learning_rate": 1.57e-07, "loss": 0.0113, "num_tokens": 344079868.0, "reward": 0.3984375, "reward_std": 0.36222946643829346, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1687 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1985.0, "completions/mean_length": 1439.6953125, "completions/mean_terminated_length": 1201.6630859375, "completions/min_length": 605.0, "completions/min_terminated_length": 605.0, "epoch": 0.29950983653824825, "frac_reward_zero_std": 0.125, "grad_norm": 0.609180748462677, "learning_rate": 1.565e-07, "loss": 0.0136, "num_tokens": 344276101.0, "reward": 0.4140625, "reward_std": 0.37761643528938293, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1688 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1789.0, "completions/mean_length": 1163.7109375, "completions/mean_terminated_length": 999.9537353515625, "completions/min_length": 450.0, "completions/min_terminated_length": 450.0, "epoch": 0.29968727127553396, "frac_reward_zero_std": 0.25, "grad_norm": 0.7547073364257812, "learning_rate": 1.56e-07, "loss": 0.0127, "num_tokens": 344436544.0, "reward": 0.6328125, "reward_std": 0.3149757981300354, "rewards/simpleverify_reward/mean": 0.6328125, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1689 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1971.0, "completions/mean_length": 1171.8359375, "completions/mean_terminated_length": 1028.463623046875, "completions/min_length": 341.0, "completions/min_terminated_length": 341.0, "epoch": 0.29986470601281967, "frac_reward_zero_std": 0.375, "grad_norm": 0.6516780257225037, "learning_rate": 1.5549999999999998e-07, "loss": 0.0154, "num_tokens": 344598027.0, "reward": 0.6328125, "reward_std": 0.2801326513290405, "rewards/simpleverify_reward/mean": 0.6328125, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1690 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1192.4609375, "completions/mean_terminated_length": 1024.5513916015625, "completions/min_length": 382.0, "completions/min_terminated_length": 382.0, "epoch": 0.3000421407501054, "frac_reward_zero_std": 0.25, "grad_norm": 0.7509438395500183, "learning_rate": 1.55e-07, "loss": -0.0032, "num_tokens": 344762150.0, "reward": 0.5546875, "reward_std": 0.3532540202140808, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1691 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1769.0, "completions/mean_length": 1175.203125, "completions/mean_terminated_length": 1003.906494140625, "completions/min_length": 401.0, "completions/min_terminated_length": 401.0, "epoch": 0.30021957548739103, "frac_reward_zero_std": 0.375, "grad_norm": 0.6437941789627075, "learning_rate": 1.545e-07, "loss": 0.0133, "num_tokens": 344924064.0, "reward": 0.6171875, "reward_std": 0.29833850264549255, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1692 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1077.3828125, "completions/mean_terminated_length": 1037.9267578125, "completions/min_length": 441.0, "completions/min_terminated_length": 441.0, "epoch": 0.30039701022467674, "frac_reward_zero_std": 0.25, "grad_norm": 0.6549848914146423, "learning_rate": 1.54e-07, "loss": 0.0067, "num_tokens": 345073873.0, "reward": 0.6953125, "reward_std": 0.29141926765441895, "rewards/simpleverify_reward/mean": 0.6953125, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 1693 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1939.0, "completions/mean_length": 1093.6953125, "completions/mean_terminated_length": 1070.7919921875, "completions/min_length": 464.0, "completions/min_terminated_length": 464.0, "epoch": 0.30057444496196245, "frac_reward_zero_std": 0.25, "grad_norm": 0.6319935917854309, "learning_rate": 1.535e-07, "loss": 0.0265, "num_tokens": 345225770.0, "reward": 0.703125, "reward_std": 0.2788337469100952, "rewards/simpleverify_reward/mean": 0.703125, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 1694 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1892.0, "completions/mean_length": 1077.15625, "completions/mean_terminated_length": 1029.4097900390625, "completions/min_length": 411.0, "completions/min_terminated_length": 411.0, "epoch": 0.3007518796992481, "frac_reward_zero_std": 0.5, "grad_norm": 0.5794487595558167, "learning_rate": 1.5299999999999998e-07, "loss": 0.0278, "num_tokens": 345375550.0, "reward": 0.609375, "reward_std": 0.20927387475967407, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1695 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2011.0, "completions/mean_length": 1059.203125, "completions/mean_terminated_length": 1035.4720458984375, "completions/min_length": 437.0, "completions/min_terminated_length": 437.0, "epoch": 0.3009293144365338, "frac_reward_zero_std": 0.375, "grad_norm": 0.5946463346481323, "learning_rate": 1.525e-07, "loss": -0.0002, "num_tokens": 345523032.0, "reward": 0.6953125, "reward_std": 0.2201344519853592, "rewards/simpleverify_reward/mean": 0.6953125, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 1696 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1935.0, "completions/mean_length": 1713.6015625, "completions/mean_terminated_length": 1346.3114013671875, "completions/min_length": 764.0, "completions/min_terminated_length": 764.0, "epoch": 0.3011067491738195, "frac_reward_zero_std": 0.5, "grad_norm": 0.4687768518924713, "learning_rate": 1.5199999999999998e-07, "loss": 0.0219, "num_tokens": 345752373.0, "reward": 0.375, "reward_std": 0.1727283000946045, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 1697 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1738.90625, "completions/mean_terminated_length": 1399.4097900390625, "completions/min_length": 816.0, "completions/min_terminated_length": 816.0, "epoch": 0.3012841839111052, "frac_reward_zero_std": 0.375, "grad_norm": 0.4596710801124573, "learning_rate": 1.515e-07, "loss": 0.0119, "num_tokens": 345984953.0, "reward": 0.3515625, "reward_std": 0.23062554001808167, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1698 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1709.7421875, "completions/mean_terminated_length": 1338.2130126953125, "completions/min_length": 714.0, "completions/min_terminated_length": 714.0, "epoch": 0.3014616186483909, "frac_reward_zero_std": 0.625, "grad_norm": 0.37623223662376404, "learning_rate": 1.51e-07, "loss": 0.0199, "num_tokens": 346213800.0, "reward": 0.4296875, "reward_std": 0.14943468570709229, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1699 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1709.53125, "completions/mean_terminated_length": 1349.2257080078125, "completions/min_length": 807.0, "completions/min_terminated_length": 807.0, "epoch": 0.3016390533856766, "frac_reward_zero_std": 0.625, "grad_norm": 0.3187052011489868, "learning_rate": 1.5049999999999998e-07, "loss": 0.0106, "num_tokens": 346442620.0, "reward": 0.421875, "reward_std": 0.125, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1700 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1343.7421875, "completions/mean_terminated_length": 1137.4444580078125, "completions/min_length": 460.0, "completions/min_terminated_length": 460.0, "epoch": 0.30181648812296225, "frac_reward_zero_std": 0.125, "grad_norm": 0.7350690960884094, "learning_rate": 1.5e-07, "loss": 0.0085, "num_tokens": 346628315.0, "reward": 0.46875, "reward_std": 0.38972732424736023, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1701 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2003.0, "completions/mean_length": 1348.6328125, "completions/mean_terminated_length": 1125.1236572265625, "completions/min_length": 481.0, "completions/min_terminated_length": 481.0, "epoch": 0.30199392286024795, "frac_reward_zero_std": 0.125, "grad_norm": 0.6902365684509277, "learning_rate": 1.4949999999999998e-07, "loss": 0.0137, "num_tokens": 346814636.0, "reward": 0.484375, "reward_std": 0.34042394161224365, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1702 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1335.6875, "completions/mean_terminated_length": 1162.796142578125, "completions/min_length": 479.0, "completions/min_terminated_length": 479.0, "epoch": 0.30217135759753366, "frac_reward_zero_std": 0.125, "grad_norm": 0.7413514256477356, "learning_rate": 1.49e-07, "loss": 0.0181, "num_tokens": 346999300.0, "reward": 0.4765625, "reward_std": 0.3567710816860199, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1703 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2021.0, "completions/mean_length": 1371.9140625, "completions/mean_terminated_length": 1191.17822265625, "completions/min_length": 493.0, "completions/min_terminated_length": 493.0, "epoch": 0.30234879233481937, "frac_reward_zero_std": 0.125, "grad_norm": 0.6847198605537415, "learning_rate": 1.4849999999999999e-07, "loss": 0.0105, "num_tokens": 347188601.0, "reward": 0.453125, "reward_std": 0.35296088457107544, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1704 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1473.953125, "completions/mean_terminated_length": 1162.722900390625, "completions/min_length": 591.0, "completions/min_terminated_length": 591.0, "epoch": 0.302526227072105, "frac_reward_zero_std": 0.375, "grad_norm": 0.5733334422111511, "learning_rate": 1.4799999999999998e-07, "loss": 0.0052, "num_tokens": 347387955.0, "reward": 0.5234375, "reward_std": 0.231073796749115, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1705 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1471.8125, "completions/mean_terminated_length": 1209.9091796875, "completions/min_length": 602.0, "completions/min_terminated_length": 602.0, "epoch": 0.30270366180939073, "frac_reward_zero_std": 0.0, "grad_norm": 0.6887063384056091, "learning_rate": 1.475e-07, "loss": 0.012, "num_tokens": 347587035.0, "reward": 0.4765625, "reward_std": 0.3719184994697571, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1706 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1862.0, "completions/mean_length": 1450.109375, "completions/mean_terminated_length": 1114.707275390625, "completions/min_length": 712.0, "completions/min_terminated_length": 712.0, "epoch": 0.30288109654667644, "frac_reward_zero_std": 0.25, "grad_norm": 0.5793241262435913, "learning_rate": 1.4699999999999998e-07, "loss": 0.0092, "num_tokens": 347783337.0, "reward": 0.546875, "reward_std": 0.24933473765850067, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1707 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1506.1953125, "completions/mean_terminated_length": 1241.593017578125, "completions/min_length": 531.0, "completions/min_terminated_length": 531.0, "epoch": 0.3030585312839621, "frac_reward_zero_std": 0.125, "grad_norm": 0.6119737029075623, "learning_rate": 1.465e-07, "loss": 0.004, "num_tokens": 347986818.0, "reward": 0.4765625, "reward_std": 0.34812304377555847, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1708 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1600.453125, "completions/mean_terminated_length": 1304.0260009765625, "completions/min_length": 332.0, "completions/min_terminated_length": 332.0, "epoch": 0.3032359660212478, "frac_reward_zero_std": 0.375, "grad_norm": 0.45017489790916443, "learning_rate": 1.4599999999999998e-07, "loss": 0.0326, "num_tokens": 348201948.0, "reward": 0.453125, "reward_std": 0.2658672332763672, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1709 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1606.171875, "completions/mean_terminated_length": 1251.4647216796875, "completions/min_length": 344.0, "completions/min_terminated_length": 344.0, "epoch": 0.3034134007585335, "frac_reward_zero_std": 0.25, "grad_norm": 0.5102473497390747, "learning_rate": 1.4549999999999997e-07, "loss": 0.0322, "num_tokens": 348417810.0, "reward": 0.4375, "reward_std": 0.3366774320602417, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1710 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1644.5390625, "completions/mean_terminated_length": 1265.5303955078125, "completions/min_length": 334.0, "completions/min_terminated_length": 334.0, "epoch": 0.30359083549581917, "frac_reward_zero_std": 0.375, "grad_norm": 0.45076078176498413, "learning_rate": 1.45e-07, "loss": 0.013, "num_tokens": 348638583.0, "reward": 0.4296875, "reward_std": 0.2926734387874603, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1711 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1636.2265625, "completions/mean_terminated_length": 1315.9583740234375, "completions/min_length": 373.0, "completions/min_terminated_length": 373.0, "epoch": 0.3037682702331049, "frac_reward_zero_std": 0.25, "grad_norm": 0.49469754099845886, "learning_rate": 1.4449999999999998e-07, "loss": 0.0294, "num_tokens": 348858292.0, "reward": 0.4296875, "reward_std": 0.3244297206401825, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1712 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1285.2890625, "completions/mean_terminated_length": 1191.622802734375, "completions/min_length": 397.0, "completions/min_terminated_length": 397.0, "epoch": 0.3039457049703906, "frac_reward_zero_std": 0.125, "grad_norm": 0.7113436460494995, "learning_rate": 1.44e-07, "loss": 0.007, "num_tokens": 349034105.0, "reward": 0.578125, "reward_std": 0.3834404945373535, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1713 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2015.0, "completions/mean_length": 1255.578125, "completions/mean_terminated_length": 1142.375, "completions/min_length": 379.0, "completions/min_terminated_length": 379.0, "epoch": 0.3041231397076763, "frac_reward_zero_std": 0.125, "grad_norm": 0.5945358276367188, "learning_rate": 1.4349999999999998e-07, "loss": 0.0264, "num_tokens": 349206115.0, "reward": 0.5234375, "reward_std": 0.3703433871269226, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1714 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.09375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2012.0, "completions/mean_length": 1271.921875, "completions/mean_terminated_length": 1191.637939453125, "completions/min_length": 390.0, "completions/min_terminated_length": 390.0, "epoch": 0.30430057444496195, "frac_reward_zero_std": 0.125, "grad_norm": 0.5928698182106018, "learning_rate": 1.4299999999999997e-07, "loss": 0.0185, "num_tokens": 349380217.0, "reward": 0.6171875, "reward_std": 0.382485955953598, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1715 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1283.5234375, "completions/mean_terminated_length": 1174.3125, "completions/min_length": 374.0, "completions/min_terminated_length": 374.0, "epoch": 0.30447800918224766, "frac_reward_zero_std": 0.125, "grad_norm": 0.7064175605773926, "learning_rate": 1.4249999999999999e-07, "loss": 0.0198, "num_tokens": 349555804.0, "reward": 0.53125, "reward_std": 0.3873332738876343, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1716 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1985.0, "completions/mean_length": 1540.53125, "completions/mean_terminated_length": 1215.2308349609375, "completions/min_length": 467.0, "completions/min_terminated_length": 467.0, "epoch": 0.30465544391953336, "frac_reward_zero_std": 0.5, "grad_norm": 0.42939555644989014, "learning_rate": 1.4199999999999997e-07, "loss": 0.0102, "num_tokens": 349769648.0, "reward": 0.5703125, "reward_std": 0.21763263642787933, "rewards/simpleverify_reward/mean": 0.5703125, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1717 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1531.28125, "completions/mean_terminated_length": 1189.0389404296875, "completions/min_length": 495.0, "completions/min_terminated_length": 495.0, "epoch": 0.304832878656819, "frac_reward_zero_std": 0.5, "grad_norm": 0.38701534271240234, "learning_rate": 1.415e-07, "loss": 0.0048, "num_tokens": 349982308.0, "reward": 0.53125, "reward_std": 0.22564704716205597, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1718 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1998.0, "completions/mean_length": 1531.2890625, "completions/mean_terminated_length": 1129.40283203125, "completions/min_length": 527.0, "completions/min_terminated_length": 527.0, "epoch": 0.3050103133941047, "frac_reward_zero_std": 0.375, "grad_norm": 0.46957504749298096, "learning_rate": 1.4099999999999998e-07, "loss": 0.0266, "num_tokens": 350194969.0, "reward": 0.5234375, "reward_std": 0.24494513869285583, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1719 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1985.0, "completions/mean_length": 1512.359375, "completions/mean_terminated_length": 1157.58447265625, "completions/min_length": 510.0, "completions/min_terminated_length": 510.0, "epoch": 0.30518774813139044, "frac_reward_zero_std": 0.375, "grad_norm": 0.6072459816932678, "learning_rate": 1.4050000000000002e-07, "loss": 0.0124, "num_tokens": 350405207.0, "reward": 0.5390625, "reward_std": 0.2603282630443573, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1720 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1214.96875, "completions/mean_terminated_length": 981.719970703125, "completions/min_length": 473.0, "completions/min_terminated_length": 473.0, "epoch": 0.3053651828686761, "frac_reward_zero_std": 0.375, "grad_norm": 0.6419132947921753, "learning_rate": 1.4e-07, "loss": 0.0265, "num_tokens": 350571123.0, "reward": 0.5234375, "reward_std": 0.24872365593910217, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1721 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1977.0, "completions/mean_length": 1221.90625, "completions/mean_terminated_length": 1001.0692749023438, "completions/min_length": 462.0, "completions/min_terminated_length": 462.0, "epoch": 0.3055426176059618, "frac_reward_zero_std": 0.5, "grad_norm": 0.5325756072998047, "learning_rate": 1.395e-07, "loss": 0.0207, "num_tokens": 350737927.0, "reward": 0.5546875, "reward_std": 0.17472384870052338, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1722 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1224.25, "completions/mean_terminated_length": 1004.0396118164062, "completions/min_length": 425.0, "completions/min_terminated_length": 425.0, "epoch": 0.3057200523432475, "frac_reward_zero_std": 0.25, "grad_norm": 0.7526895999908447, "learning_rate": 1.3900000000000001e-07, "loss": 0.01, "num_tokens": 350905031.0, "reward": 0.5546875, "reward_std": 0.23722384870052338, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1723 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2015.0, "completions/mean_length": 1255.8515625, "completions/mean_terminated_length": 991.8021240234375, "completions/min_length": 471.0, "completions/min_terminated_length": 471.0, "epoch": 0.3058974870805332, "frac_reward_zero_std": 0.375, "grad_norm": 0.6623892784118652, "learning_rate": 1.385e-07, "loss": 0.0156, "num_tokens": 351076180.0, "reward": 0.4921875, "reward_std": 0.24302572011947632, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1724 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2014.0, "completions/mean_length": 1702.6953125, "completions/mean_terminated_length": 1378.3182373046875, "completions/min_length": 678.0, "completions/min_terminated_length": 678.0, "epoch": 0.30607492181781887, "frac_reward_zero_std": 0.25, "grad_norm": 0.5886374115943909, "learning_rate": 1.3800000000000002e-07, "loss": 0.0193, "num_tokens": 351309005.0, "reward": 0.3359375, "reward_std": 0.29927173256874084, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1725 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.46875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1684.3984375, "completions/mean_terminated_length": 1363.573486328125, "completions/min_length": 653.0, "completions/min_terminated_length": 653.0, "epoch": 0.3062523565551046, "frac_reward_zero_std": 0.25, "grad_norm": 0.6287007927894592, "learning_rate": 1.375e-07, "loss": 0.0193, "num_tokens": 351539488.0, "reward": 0.3359375, "reward_std": 0.28495216369628906, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1726 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1960.0, "completions/mean_length": 1689.6171875, "completions/mean_terminated_length": 1352.95458984375, "completions/min_length": 664.0, "completions/min_terminated_length": 664.0, "epoch": 0.3064297912923903, "frac_reward_zero_std": 0.25, "grad_norm": 0.5787681341171265, "learning_rate": 1.37e-07, "loss": 0.0205, "num_tokens": 351770639.0, "reward": 0.3515625, "reward_std": 0.3112236559391022, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1727 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1663.40625, "completions/mean_terminated_length": 1334.55078125, "completions/min_length": 620.0, "completions/min_terminated_length": 620.0, "epoch": 0.30660722602967594, "frac_reward_zero_std": 0.125, "grad_norm": 0.6440557837486267, "learning_rate": 1.365e-07, "loss": 0.0248, "num_tokens": 351998435.0, "reward": 0.390625, "reward_std": 0.35828250646591187, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1728 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1160.703125, "completions/mean_terminated_length": 1006.0366821289062, "completions/min_length": 365.0, "completions/min_terminated_length": 365.0, "epoch": 0.30678466076696165, "frac_reward_zero_std": 0.5, "grad_norm": 0.5095906257629395, "learning_rate": 1.36e-07, "loss": 0.025, "num_tokens": 352161181.0, "reward": 0.765625, "reward_std": 0.20552174746990204, "rewards/simpleverify_reward/mean": 0.765625, "rewards/simpleverify_reward/std": 0.42527204751968384, "step": 1729 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1189.4609375, "completions/mean_terminated_length": 1001.4000244140625, "completions/min_length": 371.0, "completions/min_terminated_length": 371.0, "epoch": 0.30696209550424736, "frac_reward_zero_std": 0.25, "grad_norm": 0.5659407377243042, "learning_rate": 1.3550000000000002e-07, "loss": 0.0013, "num_tokens": 352327608.0, "reward": 0.7421875, "reward_std": 0.26783639192581177, "rewards/simpleverify_reward/mean": 0.7421875, "rewards/simpleverify_reward/std": 0.43914902210235596, "step": 1730 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1190.3359375, "completions/mean_terminated_length": 1012.3302001953125, "completions/min_length": 382.0, "completions/min_terminated_length": 382.0, "epoch": 0.307139530241533, "frac_reward_zero_std": 0.375, "grad_norm": 0.6718946695327759, "learning_rate": 1.35e-07, "loss": 0.0415, "num_tokens": 352494147.0, "reward": 0.734375, "reward_std": 0.23328250646591187, "rewards/simpleverify_reward/mean": 0.734375, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 1731 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1978.0, "completions/mean_length": 1183.703125, "completions/mean_terminated_length": 1004.3207397460938, "completions/min_length": 340.0, "completions/min_terminated_length": 340.0, "epoch": 0.3073169649788187, "frac_reward_zero_std": 0.5, "grad_norm": 0.5653723478317261, "learning_rate": 1.345e-07, "loss": 0.0084, "num_tokens": 352659837.0, "reward": 0.6875, "reward_std": 0.23831519484519958, "rewards/simpleverify_reward/mean": 0.6875, "rewards/simpleverify_reward/std": 0.4653336703777313, "step": 1732 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1277.578125, "completions/mean_terminated_length": 1031.36083984375, "completions/min_length": 339.0, "completions/min_terminated_length": 339.0, "epoch": 0.3074943997161044, "frac_reward_zero_std": 0.125, "grad_norm": 0.6964938044548035, "learning_rate": 1.34e-07, "loss": 0.0527, "num_tokens": 352834407.0, "reward": 0.59375, "reward_std": 0.35817772150039673, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1733 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1996.0, "completions/mean_length": 1325.15625, "completions/mean_terminated_length": 1063.7021484375, "completions/min_length": 335.0, "completions/min_terminated_length": 335.0, "epoch": 0.30767183445339014, "frac_reward_zero_std": 0.125, "grad_norm": 0.739679753780365, "learning_rate": 1.335e-07, "loss": 0.0372, "num_tokens": 353015067.0, "reward": 0.484375, "reward_std": 0.32040637731552124, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1734 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1307.8671875, "completions/mean_terminated_length": 995.36669921875, "completions/min_length": 327.0, "completions/min_terminated_length": 327.0, "epoch": 0.3078492691906758, "frac_reward_zero_std": 0.25, "grad_norm": 0.6089053153991699, "learning_rate": 1.33e-07, "loss": 0.035, "num_tokens": 353193514.0, "reward": 0.515625, "reward_std": 0.2849799692630768, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1735 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2009.0, "completions/mean_length": 1263.4296875, "completions/mean_terminated_length": 1053.6929931640625, "completions/min_length": 339.0, "completions/min_terminated_length": 339.0, "epoch": 0.3080267039279615, "frac_reward_zero_std": 0.0, "grad_norm": 1.0357939004898071, "learning_rate": 1.325e-07, "loss": 0.0433, "num_tokens": 353366273.0, "reward": 0.5703125, "reward_std": 0.3680257201194763, "rewards/simpleverify_reward/mean": 0.5703125, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1736 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2022.0, "completions/mean_length": 1412.5703125, "completions/mean_terminated_length": 1163.9239501953125, "completions/min_length": 560.0, "completions/min_terminated_length": 560.0, "epoch": 0.3082041386652472, "frac_reward_zero_std": 0.125, "grad_norm": 0.5754034519195557, "learning_rate": 1.32e-07, "loss": 0.0174, "num_tokens": 353560842.0, "reward": 0.515625, "reward_std": 0.36947083473205566, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1737 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2019.0, "completions/mean_length": 1404.515625, "completions/mean_terminated_length": 1152.7174072265625, "completions/min_length": 597.0, "completions/min_terminated_length": 597.0, "epoch": 0.30838157340253286, "frac_reward_zero_std": 0.125, "grad_norm": 0.6236006617546082, "learning_rate": 1.315e-07, "loss": 0.0123, "num_tokens": 353754380.0, "reward": 0.515625, "reward_std": 0.36193370819091797, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1738 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1975.0, "completions/mean_length": 1395.25, "completions/mean_terminated_length": 1139.8260498046875, "completions/min_length": 590.0, "completions/min_terminated_length": 590.0, "epoch": 0.30855900813981857, "frac_reward_zero_std": 0.125, "grad_norm": 0.6424726843833923, "learning_rate": 1.31e-07, "loss": 0.0413, "num_tokens": 353946732.0, "reward": 0.4140625, "reward_std": 0.3879668712615967, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1739 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2011.0, "completions/mean_length": 1377.1015625, "completions/mean_terminated_length": 1124.6129150390625, "completions/min_length": 618.0, "completions/min_terminated_length": 618.0, "epoch": 0.3087364428771043, "frac_reward_zero_std": 0.125, "grad_norm": 0.5924379229545593, "learning_rate": 1.305e-07, "loss": 0.01, "num_tokens": 354136761.0, "reward": 0.484375, "reward_std": 0.3512584865093231, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1740 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1493.6640625, "completions/mean_terminated_length": 1250.7528076171875, "completions/min_length": 471.0, "completions/min_terminated_length": 471.0, "epoch": 0.30891387761438993, "frac_reward_zero_std": 0.25, "grad_norm": 0.6038674116134644, "learning_rate": 1.3e-07, "loss": 0.0359, "num_tokens": 354338462.0, "reward": 0.3515625, "reward_std": 0.27376943826675415, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1741 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1461.1484375, "completions/mean_terminated_length": 1281.5, "completions/min_length": 568.0, "completions/min_terminated_length": 568.0, "epoch": 0.30909131235167564, "frac_reward_zero_std": 0.25, "grad_norm": 0.6234077215194702, "learning_rate": 1.295e-07, "loss": 0.0229, "num_tokens": 354536001.0, "reward": 0.40625, "reward_std": 0.29248809814453125, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1742 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1469.4296875, "completions/mean_terminated_length": 1215.89892578125, "completions/min_length": 565.0, "completions/min_terminated_length": 565.0, "epoch": 0.30926874708896135, "frac_reward_zero_std": 0.5, "grad_norm": 0.4552809000015259, "learning_rate": 1.29e-07, "loss": 0.0432, "num_tokens": 354734600.0, "reward": 0.359375, "reward_std": 0.20709684491157532, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 1743 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2023.0, "completions/mean_length": 1477.1171875, "completions/mean_terminated_length": 1208.0804443359375, "completions/min_length": 534.0, "completions/min_terminated_length": 534.0, "epoch": 0.30944618182624706, "frac_reward_zero_std": 0.375, "grad_norm": 0.5469423532485962, "learning_rate": 1.285e-07, "loss": 0.0248, "num_tokens": 354934183.0, "reward": 0.359375, "reward_std": 0.2383151799440384, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 1744 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1182.46875, "completions/mean_terminated_length": 1031.5963134765625, "completions/min_length": 288.0, "completions/min_terminated_length": 288.0, "epoch": 0.3096236165635327, "frac_reward_zero_std": 0.125, "grad_norm": 0.7102411389350891, "learning_rate": 1.28e-07, "loss": 0.018, "num_tokens": 355098883.0, "reward": 0.59375, "reward_std": 0.3333735167980194, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1745 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1969.0, "completions/mean_length": 1155.6640625, "completions/mean_terminated_length": 1019.0, "completions/min_length": 295.0, "completions/min_terminated_length": 295.0, "epoch": 0.3098010513008184, "frac_reward_zero_std": 0.125, "grad_norm": 0.7365615367889404, "learning_rate": 1.275e-07, "loss": 0.0213, "num_tokens": 355260152.0, "reward": 0.6171875, "reward_std": 0.34308475255966187, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1746 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1992.0, "completions/mean_length": 1171.3984375, "completions/mean_terminated_length": 1027.9544677734375, "completions/min_length": 294.0, "completions/min_terminated_length": 294.0, "epoch": 0.30997848603810413, "frac_reward_zero_std": 0.125, "grad_norm": 0.7916591167449951, "learning_rate": 1.2699999999999999e-07, "loss": 0.0372, "num_tokens": 355423435.0, "reward": 0.671875, "reward_std": 0.35011857748031616, "rewards/simpleverify_reward/mean": 0.671875, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1747 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1177.921875, "completions/mean_terminated_length": 1071.0701904296875, "completions/min_length": 283.0, "completions/min_terminated_length": 283.0, "epoch": 0.3101559207753898, "frac_reward_zero_std": 0.125, "grad_norm": 0.7288697361946106, "learning_rate": 1.265e-07, "loss": 0.0461, "num_tokens": 355587553.0, "reward": 0.6328125, "reward_std": 0.3604412078857422, "rewards/simpleverify_reward/mean": 0.6328125, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1748 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1387.6015625, "completions/mean_terminated_length": 1176.54638671875, "completions/min_length": 343.0, "completions/min_terminated_length": 343.0, "epoch": 0.3103333555126755, "frac_reward_zero_std": 0.0, "grad_norm": 0.6697434782981873, "learning_rate": 1.26e-07, "loss": 0.0247, "num_tokens": 355774126.0, "reward": 0.546875, "reward_std": 0.4219318628311157, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1749 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2031.0, "completions/mean_length": 1431.21875, "completions/mean_terminated_length": 1180.4395751953125, "completions/min_length": 414.0, "completions/min_terminated_length": 414.0, "epoch": 0.3105107902499612, "frac_reward_zero_std": 0.125, "grad_norm": 0.6051805019378662, "learning_rate": 1.255e-07, "loss": 0.0285, "num_tokens": 355966282.0, "reward": 0.6171875, "reward_std": 0.38136857748031616, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1750 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2010.0, "completions/mean_length": 1411.3671875, "completions/mean_terminated_length": 1181.095703125, "completions/min_length": 387.0, "completions/min_terminated_length": 387.0, "epoch": 0.31068822498724685, "frac_reward_zero_std": 0.125, "grad_norm": 0.6228799819946289, "learning_rate": 1.25e-07, "loss": 0.0262, "num_tokens": 356155897.0, "reward": 0.6171875, "reward_std": 0.3870665431022644, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1751 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1428.234375, "completions/mean_terminated_length": 1156.6517333984375, "completions/min_length": 400.0, "completions/min_terminated_length": 400.0, "epoch": 0.31086565972453256, "frac_reward_zero_std": 0.125, "grad_norm": 0.6913759708404541, "learning_rate": 1.2449999999999998e-07, "loss": 0.0415, "num_tokens": 356347671.0, "reward": 0.5625, "reward_std": 0.38005638122558594, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1752 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2009.0, "completions/mean_length": 1389.9140625, "completions/mean_terminated_length": 954.0389404296875, "completions/min_length": 439.0, "completions/min_terminated_length": 439.0, "epoch": 0.31104309446181827, "frac_reward_zero_std": 0.25, "grad_norm": 0.612645149230957, "learning_rate": 1.24e-07, "loss": -0.0015, "num_tokens": 356533548.0, "reward": 0.4453125, "reward_std": 0.2975429594516754, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1753 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1346.109375, "completions/mean_terminated_length": 952.3658447265625, "completions/min_length": 436.0, "completions/min_terminated_length": 436.0, "epoch": 0.311220529199104, "frac_reward_zero_std": 0.125, "grad_norm": 0.6233890056610107, "learning_rate": 1.235e-07, "loss": 0.008, "num_tokens": 356713818.0, "reward": 0.4921875, "reward_std": 0.30415070056915283, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1754 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2022.0, "completions/mean_length": 1370.640625, "completions/mean_terminated_length": 977.6049194335938, "completions/min_length": 447.0, "completions/min_terminated_length": 447.0, "epoch": 0.31139796393638963, "frac_reward_zero_std": 0.25, "grad_norm": 0.6385501623153687, "learning_rate": 1.23e-07, "loss": 0.0043, "num_tokens": 356897228.0, "reward": 0.484375, "reward_std": 0.3140212595462799, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1755 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1694.0, "completions/mean_length": 1346.09375, "completions/mean_terminated_length": 881.19482421875, "completions/min_length": 438.0, "completions/min_terminated_length": 438.0, "epoch": 0.31157539867367534, "frac_reward_zero_std": 0.375, "grad_norm": 0.5379707217216492, "learning_rate": 1.225e-07, "loss": -0.0032, "num_tokens": 357077496.0, "reward": 0.4453125, "reward_std": 0.2785341441631317, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1756 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1993.0, "completions/mean_length": 1397.9375, "completions/mean_terminated_length": 1057.4285888671875, "completions/min_length": 494.0, "completions/min_terminated_length": 494.0, "epoch": 0.31175283341096105, "frac_reward_zero_std": 0.375, "grad_norm": 0.5482233166694641, "learning_rate": 1.2199999999999998e-07, "loss": 0.0089, "num_tokens": 357266384.0, "reward": 0.4765625, "reward_std": 0.2524796426296234, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1757 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1394.3046875, "completions/mean_terminated_length": 1039.8914794921875, "completions/min_length": 485.0, "completions/min_terminated_length": 485.0, "epoch": 0.3119302681482467, "frac_reward_zero_std": 0.5, "grad_norm": 0.5036266446113586, "learning_rate": 1.215e-07, "loss": 0.0137, "num_tokens": 357454807.0, "reward": 0.421875, "reward_std": 0.2000408172607422, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1758 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1422.140625, "completions/mean_terminated_length": 1071.0487060546875, "completions/min_length": 480.0, "completions/min_terminated_length": 480.0, "epoch": 0.3121077028855324, "frac_reward_zero_std": 0.625, "grad_norm": 0.4367346465587616, "learning_rate": 1.2099999999999998e-07, "loss": 0.0016, "num_tokens": 357646793.0, "reward": 0.46875, "reward_std": 0.17558008432388306, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1759 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1408.265625, "completions/mean_terminated_length": 1049.3902587890625, "completions/min_length": 450.0, "completions/min_terminated_length": 450.0, "epoch": 0.3122851376228181, "frac_reward_zero_std": 0.5, "grad_norm": 0.47620704770088196, "learning_rate": 1.205e-07, "loss": 0.0266, "num_tokens": 357837003.0, "reward": 0.40625, "reward_std": 0.18023642897605896, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1760 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1959.0, "completions/mean_length": 1600.953125, "completions/mean_terminated_length": 1374.800048828125, "completions/min_length": 558.0, "completions/min_terminated_length": 558.0, "epoch": 0.3124625723601038, "frac_reward_zero_std": 0.125, "grad_norm": 0.601508378982544, "learning_rate": 1.2e-07, "loss": 0.0376, "num_tokens": 358060693.0, "reward": 0.40625, "reward_std": 0.379608154296875, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1761 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1631.046875, "completions/mean_terminated_length": 1380.875, "completions/min_length": 604.0, "completions/min_terminated_length": 604.0, "epoch": 0.3126400070973895, "frac_reward_zero_std": 0.25, "grad_norm": 0.5535143613815308, "learning_rate": 1.1949999999999998e-07, "loss": 0.0434, "num_tokens": 358288235.0, "reward": 0.390625, "reward_std": 0.36616697907447815, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1762 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2020.0, "completions/mean_length": 1634.53125, "completions/mean_terminated_length": 1386.4500732421875, "completions/min_length": 668.0, "completions/min_terminated_length": 668.0, "epoch": 0.3128174418346752, "frac_reward_zero_std": 0.25, "grad_norm": 0.5628781914710999, "learning_rate": 1.19e-07, "loss": 0.0535, "num_tokens": 358516223.0, "reward": 0.3984375, "reward_std": 0.3816800117492676, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1763 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1627.375, "completions/mean_terminated_length": 1414.5882568359375, "completions/min_length": 613.0, "completions/min_terminated_length": 613.0, "epoch": 0.3129948765719609, "frac_reward_zero_std": 0.125, "grad_norm": 0.55907142162323, "learning_rate": 1.1849999999999998e-07, "loss": 0.0371, "num_tokens": 358743295.0, "reward": 0.359375, "reward_std": 0.39997297525405884, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 1764 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2011.0, "completions/mean_length": 1579.0234375, "completions/mean_terminated_length": 1225.6849365234375, "completions/min_length": 527.0, "completions/min_terminated_length": 527.0, "epoch": 0.31317231130924655, "frac_reward_zero_std": 0.5, "grad_norm": 0.4628675878047943, "learning_rate": 1.1799999999999998e-07, "loss": 0.0184, "num_tokens": 358956786.0, "reward": 0.1875, "reward_std": 0.2352283000946045, "rewards/simpleverify_reward/mean": 0.1875, "rewards/simpleverify_reward/std": 0.39184603095054626, "step": 1765 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1562.1875, "completions/mean_terminated_length": 1280.2962646484375, "completions/min_length": 570.0, "completions/min_terminated_length": 570.0, "epoch": 0.31334974604653226, "frac_reward_zero_std": 0.25, "grad_norm": 0.6446439027786255, "learning_rate": 1.1749999999999999e-07, "loss": -0.0019, "num_tokens": 359168122.0, "reward": 0.2265625, "reward_std": 0.27398645877838135, "rewards/simpleverify_reward/mean": 0.2265625, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 1766 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1984.0, "completions/mean_length": 1600.921875, "completions/mean_terminated_length": 1284.9866943359375, "completions/min_length": 655.0, "completions/min_terminated_length": 655.0, "epoch": 0.31352718078381797, "frac_reward_zero_std": 0.375, "grad_norm": 0.5139790773391724, "learning_rate": 1.17e-07, "loss": 0.0113, "num_tokens": 359384416.0, "reward": 0.2109375, "reward_std": 0.2701031267642975, "rewards/simpleverify_reward/mean": 0.2109375, "rewards/simpleverify_reward/std": 0.4095771610736847, "step": 1767 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1596.34375, "completions/mean_terminated_length": 1316.2025146484375, "completions/min_length": 646.0, "completions/min_terminated_length": 646.0, "epoch": 0.3137046155211036, "frac_reward_zero_std": 0.375, "grad_norm": 0.4910896122455597, "learning_rate": 1.165e-07, "loss": 0.0295, "num_tokens": 359600124.0, "reward": 0.21875, "reward_std": 0.2708735466003418, "rewards/simpleverify_reward/mean": 0.21875, "rewards/simpleverify_reward/std": 0.41502299904823303, "step": 1768 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1342.5625, "completions/mean_terminated_length": 1135.919189453125, "completions/min_length": 498.0, "completions/min_terminated_length": 498.0, "epoch": 0.31388205025838933, "frac_reward_zero_std": 0.25, "grad_norm": 0.5864795446395874, "learning_rate": 1.16e-07, "loss": -0.0103, "num_tokens": 359784052.0, "reward": 0.546875, "reward_std": 0.34202152490615845, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1769 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1332.5625, "completions/mean_terminated_length": 1158.91259765625, "completions/min_length": 459.0, "completions/min_terminated_length": 459.0, "epoch": 0.31405948499567504, "frac_reward_zero_std": 0.125, "grad_norm": 0.612471342086792, "learning_rate": 1.155e-07, "loss": -0.0024, "num_tokens": 359966700.0, "reward": 0.5703125, "reward_std": 0.3580252230167389, "rewards/simpleverify_reward/mean": 0.5703125, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1770 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1306.3828125, "completions/mean_terminated_length": 1126.378662109375, "completions/min_length": 481.0, "completions/min_terminated_length": 481.0, "epoch": 0.3142369197329607, "frac_reward_zero_std": 0.25, "grad_norm": 0.5896564722061157, "learning_rate": 1.15e-07, "loss": -0.0226, "num_tokens": 360145997.0, "reward": 0.5390625, "reward_std": 0.3294360339641571, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1771 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2013.0, "completions/mean_length": 1337.1640625, "completions/mean_terminated_length": 1173.125, "completions/min_length": 506.0, "completions/min_terminated_length": 506.0, "epoch": 0.3144143544702464, "frac_reward_zero_std": 0.25, "grad_norm": 0.5526965260505676, "learning_rate": 1.145e-07, "loss": 0.01, "num_tokens": 360329234.0, "reward": 0.4765625, "reward_std": 0.3195338547229767, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1772 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2006.0, "completions/mean_length": 1228.4765625, "completions/mean_terminated_length": 1094.3726806640625, "completions/min_length": 536.0, "completions/min_terminated_length": 536.0, "epoch": 0.3145917892075321, "frac_reward_zero_std": 0.125, "grad_norm": 0.717369556427002, "learning_rate": 1.14e-07, "loss": 0.0232, "num_tokens": 360496543.0, "reward": 0.734375, "reward_std": 0.3182255029678345, "rewards/simpleverify_reward/mean": 0.734375, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 1773 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1242.109375, "completions/mean_terminated_length": 1110.236328125, "completions/min_length": 537.0, "completions/min_terminated_length": 537.0, "epoch": 0.3147692239448178, "frac_reward_zero_std": 0.375, "grad_norm": 0.6038191318511963, "learning_rate": 1.135e-07, "loss": 0.0297, "num_tokens": 360665597.0, "reward": 0.75, "reward_std": 0.2497924566268921, "rewards/simpleverify_reward/mean": 0.75, "rewards/simpleverify_reward/std": 0.434714138507843, "step": 1774 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1973.0, "completions/mean_length": 1245.1328125, "completions/mean_terminated_length": 1113.7545166015625, "completions/min_length": 506.0, "completions/min_terminated_length": 506.0, "epoch": 0.3149466586821035, "frac_reward_zero_std": 0.25, "grad_norm": 0.6479100584983826, "learning_rate": 1.1299999999999999e-07, "loss": 0.0315, "num_tokens": 360835038.0, "reward": 0.71875, "reward_std": 0.3018277585506439, "rewards/simpleverify_reward/mean": 0.71875, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 1775 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1236.125, "completions/mean_terminated_length": 1085.77783203125, "completions/min_length": 601.0, "completions/min_terminated_length": 601.0, "epoch": 0.3151240934193892, "frac_reward_zero_std": 0.25, "grad_norm": 0.6221591234207153, "learning_rate": 1.125e-07, "loss": 0.0092, "num_tokens": 361003326.0, "reward": 0.765625, "reward_std": 0.3089885711669922, "rewards/simpleverify_reward/mean": 0.765625, "rewards/simpleverify_reward/std": 0.42527204751968384, "step": 1776 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1477.25, "completions/mean_terminated_length": 1134.800048828125, "completions/min_length": 63.0, "completions/min_terminated_length": 63.0, "epoch": 0.3153015281566749, "frac_reward_zero_std": 0.25, "grad_norm": 0.7063202857971191, "learning_rate": 1.12e-07, "loss": 0.0085, "num_tokens": 361205326.0, "reward": 0.5, "reward_std": 0.2645905315876007, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 1777 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1499.9296875, "completions/mean_terminated_length": 1148.6025390625, "completions/min_length": 63.0, "completions/min_terminated_length": 63.0, "epoch": 0.31547896289396055, "frac_reward_zero_std": 0.25, "grad_norm": 0.7319376468658447, "learning_rate": 1.115e-07, "loss": -0.0388, "num_tokens": 361410229.0, "reward": 0.4453125, "reward_std": 0.2601150870323181, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1778 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2019.0, "completions/mean_length": 1497.375, "completions/mean_terminated_length": 1188.48779296875, "completions/min_length": 520.0, "completions/min_terminated_length": 520.0, "epoch": 0.31565639763124625, "frac_reward_zero_std": 0.25, "grad_norm": 0.6203946471214294, "learning_rate": 1.11e-07, "loss": 0.0206, "num_tokens": 361614805.0, "reward": 0.5078125, "reward_std": 0.2409759908914566, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1779 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1498.65625, "completions/mean_terminated_length": 1146.5128173828125, "completions/min_length": 620.0, "completions/min_terminated_length": 620.0, "epoch": 0.31583383236853196, "frac_reward_zero_std": 0.375, "grad_norm": 0.5527229309082031, "learning_rate": 1.1049999999999999e-07, "loss": 0.0198, "num_tokens": 361819545.0, "reward": 0.53125, "reward_std": 0.2066391110420227, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1780 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1451.1875, "completions/mean_terminated_length": 1353.5272216796875, "completions/min_length": 588.0, "completions/min_terminated_length": 588.0, "epoch": 0.3160112671058176, "frac_reward_zero_std": 0.125, "grad_norm": 0.6085858345031738, "learning_rate": 1.0999999999999999e-07, "loss": 0.0303, "num_tokens": 362019761.0, "reward": 0.421875, "reward_std": 0.36616694927215576, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1781 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1475.6015625, "completions/mean_terminated_length": 1350.2191162109375, "completions/min_length": 730.0, "completions/min_terminated_length": 730.0, "epoch": 0.3161887018431033, "frac_reward_zero_std": 0.125, "grad_norm": 0.6508769989013672, "learning_rate": 1.095e-07, "loss": 0.0358, "num_tokens": 362223102.0, "reward": 0.4140625, "reward_std": 0.38956451416015625, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1782 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2022.0, "completions/mean_length": 1463.0859375, "completions/mean_terminated_length": 1348.2896728515625, "completions/min_length": 741.0, "completions/min_terminated_length": 741.0, "epoch": 0.31636613658038903, "frac_reward_zero_std": 0.125, "grad_norm": 0.624975323677063, "learning_rate": 1.09e-07, "loss": 0.0348, "num_tokens": 362424841.0, "reward": 0.4921875, "reward_std": 0.3966149091720581, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1783 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1449.203125, "completions/mean_terminated_length": 1351.2181396484375, "completions/min_length": 729.0, "completions/min_terminated_length": 729.0, "epoch": 0.31654357131767474, "frac_reward_zero_std": 0.375, "grad_norm": 0.4854550361633301, "learning_rate": 1.085e-07, "loss": 0.0153, "num_tokens": 362624803.0, "reward": 0.4765625, "reward_std": 0.30132144689559937, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1784 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2005.0, "completions/mean_length": 1328.1640625, "completions/mean_terminated_length": 1078.1158447265625, "completions/min_length": 510.0, "completions/min_terminated_length": 510.0, "epoch": 0.3167210060549604, "frac_reward_zero_std": 0.125, "grad_norm": 0.6878235936164856, "learning_rate": 1.0799999999999999e-07, "loss": 0.03, "num_tokens": 362805848.0, "reward": 0.53125, "reward_std": 0.38094252347946167, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1785 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2003.0, "completions/mean_length": 1363.203125, "completions/mean_terminated_length": 1115.5106201171875, "completions/min_length": 497.0, "completions/min_terminated_length": 497.0, "epoch": 0.3168984407922461, "frac_reward_zero_std": 0.25, "grad_norm": 0.5959640145301819, "learning_rate": 1.0749999999999999e-07, "loss": 0.0113, "num_tokens": 362991378.0, "reward": 0.5234375, "reward_std": 0.28915637731552124, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1786 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1356.125, "completions/mean_terminated_length": 1085.391357421875, "completions/min_length": 507.0, "completions/min_terminated_length": 507.0, "epoch": 0.3170758755295318, "frac_reward_zero_std": 0.25, "grad_norm": 0.6488312482833862, "learning_rate": 1.0699999999999999e-07, "loss": 0.0277, "num_tokens": 363176002.0, "reward": 0.4765625, "reward_std": 0.31841084361076355, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1787 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1994.0, "completions/mean_length": 1295.5625, "completions/mean_terminated_length": 1084.8800048828125, "completions/min_length": 338.0, "completions/min_terminated_length": 338.0, "epoch": 0.31725331026681747, "frac_reward_zero_std": 0.25, "grad_norm": 0.6501026153564453, "learning_rate": 1.065e-07, "loss": 0.0353, "num_tokens": 363352874.0, "reward": 0.5078125, "reward_std": 0.34481915831565857, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1788 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2023.0, "completions/mean_length": 1130.0625, "completions/mean_terminated_length": 1017.3333129882812, "completions/min_length": 363.0, "completions/min_terminated_length": 363.0, "epoch": 0.3174307450041032, "frac_reward_zero_std": 0.125, "grad_norm": 0.7393320798873901, "learning_rate": 1.06e-07, "loss": -0.0045, "num_tokens": 363508594.0, "reward": 0.6796875, "reward_std": 0.34287720918655396, "rewards/simpleverify_reward/mean": 0.6796875, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 1789 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1954.0, "completions/mean_length": 1141.09375, "completions/mean_terminated_length": 1038.5738525390625, "completions/min_length": 415.0, "completions/min_terminated_length": 415.0, "epoch": 0.3176081797413889, "frac_reward_zero_std": 0.25, "grad_norm": 0.6807360649108887, "learning_rate": 1.0549999999999999e-07, "loss": 0.0125, "num_tokens": 363665726.0, "reward": 0.703125, "reward_std": 0.29091301560401917, "rewards/simpleverify_reward/mean": 0.703125, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 1790 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1156.1015625, "completions/mean_terminated_length": 1037.7080078125, "completions/min_length": 410.0, "completions/min_terminated_length": 410.0, "epoch": 0.31778561447867454, "frac_reward_zero_std": 0.25, "grad_norm": 0.6859392523765564, "learning_rate": 1.0499999999999999e-07, "loss": 0.0122, "num_tokens": 363824779.0, "reward": 0.671875, "reward_std": 0.31071737408638, "rewards/simpleverify_reward/mean": 0.671875, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1791 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1967.0, "completions/mean_length": 1134.28125, "completions/mean_terminated_length": 1030.9912109375, "completions/min_length": 354.0, "completions/min_terminated_length": 354.0, "epoch": 0.31796304921596025, "frac_reward_zero_std": 0.25, "grad_norm": 0.6859744191169739, "learning_rate": 1.0449999999999999e-07, "loss": 0.0178, "num_tokens": 363981039.0, "reward": 0.6484375, "reward_std": 0.3359295427799225, "rewards/simpleverify_reward/mean": 0.6484375, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1792 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1492.59375, "completions/mean_terminated_length": 1046.7042236328125, "completions/min_length": 457.0, "completions/min_terminated_length": 457.0, "epoch": 0.31814048395324596, "frac_reward_zero_std": 0.25, "grad_norm": 0.5538215041160583, "learning_rate": 1.0399999999999999e-07, "loss": 0.0224, "num_tokens": 364187851.0, "reward": 0.2578125, "reward_std": 0.3294360339641571, "rewards/simpleverify_reward/mean": 0.2578125, "rewards/simpleverify_reward/std": 0.43914902210235596, "step": 1793 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1427.4375, "completions/mean_terminated_length": 944.7777709960938, "completions/min_length": 458.0, "completions/min_terminated_length": 458.0, "epoch": 0.31831791869053166, "frac_reward_zero_std": 0.375, "grad_norm": 0.5585764050483704, "learning_rate": 1.035e-07, "loss": 0.0095, "num_tokens": 364386323.0, "reward": 0.2265625, "reward_std": 0.28846919536590576, "rewards/simpleverify_reward/mean": 0.2265625, "rewards/simpleverify_reward/std": 0.4202519655227661, "step": 1794 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4609375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1481.875, "completions/mean_terminated_length": 997.797119140625, "completions/min_length": 457.0, "completions/min_terminated_length": 457.0, "epoch": 0.3184953534278173, "frac_reward_zero_std": 0.25, "grad_norm": 0.5372487306594849, "learning_rate": 1.03e-07, "loss": 0.0158, "num_tokens": 364591763.0, "reward": 0.2421875, "reward_std": 0.3162299394607544, "rewards/simpleverify_reward/mean": 0.2421875, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 1795 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1468.109375, "completions/mean_terminated_length": 987.6286010742188, "completions/min_length": 395.0, "completions/min_terminated_length": 395.0, "epoch": 0.318672788165103, "frac_reward_zero_std": 0.25, "grad_norm": 0.5397871732711792, "learning_rate": 1.0249999999999998e-07, "loss": 0.0051, "num_tokens": 364795441.0, "reward": 0.21875, "reward_std": 0.3072861433029175, "rewards/simpleverify_reward/mean": 0.21875, "rewards/simpleverify_reward/std": 0.41502299904823303, "step": 1796 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1978.0, "completions/mean_length": 1608.6171875, "completions/mean_terminated_length": 1326.9615478515625, "completions/min_length": 817.0, "completions/min_terminated_length": 817.0, "epoch": 0.31885022290238874, "frac_reward_zero_std": 0.25, "grad_norm": 0.5313739776611328, "learning_rate": 1.0199999999999999e-07, "loss": 0.0134, "num_tokens": 365014672.0, "reward": 0.5, "reward_std": 0.2948821485042572, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 1797 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2006.0, "completions/mean_length": 1600.8203125, "completions/mean_terminated_length": 1382.43017578125, "completions/min_length": 811.0, "completions/min_terminated_length": 811.0, "epoch": 0.3190276576396744, "frac_reward_zero_std": 0.0, "grad_norm": 0.562907338142395, "learning_rate": 1.015e-07, "loss": 0.0168, "num_tokens": 365232905.0, "reward": 0.59375, "reward_std": 0.37696951627731323, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1798 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1629.640625, "completions/mean_terminated_length": 1394.951171875, "completions/min_length": 704.0, "completions/min_terminated_length": 704.0, "epoch": 0.3192050923769601, "frac_reward_zero_std": 0.125, "grad_norm": 0.5627999901771545, "learning_rate": 1.01e-07, "loss": 0.008, "num_tokens": 365454827.0, "reward": 0.5078125, "reward_std": 0.3534446358680725, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1799 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1599.9453125, "completions/mean_terminated_length": 1348.5975341796875, "completions/min_length": 780.0, "completions/min_terminated_length": 780.0, "epoch": 0.3193825271142458, "frac_reward_zero_std": 0.125, "grad_norm": 0.5614757537841797, "learning_rate": 1.005e-07, "loss": 0.0291, "num_tokens": 365672948.0, "reward": 0.5546875, "reward_std": 0.3545081615447998, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1800 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1558.3984375, "completions/mean_terminated_length": 1343.85400390625, "completions/min_length": 739.0, "completions/min_terminated_length": 739.0, "epoch": 0.31955996185153146, "frac_reward_zero_std": 0.375, "grad_norm": 0.4586736857891083, "learning_rate": 1e-07, "loss": 0.0319, "num_tokens": 365882247.0, "reward": 0.5234375, "reward_std": 0.29664260149002075, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1801 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1600.5, "completions/mean_terminated_length": 1349.46337890625, "completions/min_length": 621.0, "completions/min_terminated_length": 621.0, "epoch": 0.31973739658881717, "frac_reward_zero_std": 0.25, "grad_norm": 0.4889685809612274, "learning_rate": 9.95e-08, "loss": 0.0239, "num_tokens": 366096935.0, "reward": 0.46875, "reward_std": 0.3432757258415222, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1802 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2015.0, "completions/mean_length": 1568.21875, "completions/mean_terminated_length": 1299.0731201171875, "completions/min_length": 705.0, "completions/min_terminated_length": 705.0, "epoch": 0.3199148313261029, "frac_reward_zero_std": 0.125, "grad_norm": 0.5668044686317444, "learning_rate": 9.9e-08, "loss": 0.0392, "num_tokens": 366307491.0, "reward": 0.46875, "reward_std": 0.35296475887298584, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1803 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1596.984375, "completions/mean_terminated_length": 1391.977294921875, "completions/min_length": 646.0, "completions/min_terminated_length": 646.0, "epoch": 0.3200922660633886, "frac_reward_zero_std": 0.25, "grad_norm": 0.49503573775291443, "learning_rate": 9.85e-08, "loss": 0.0311, "num_tokens": 366521729.0, "reward": 0.5078125, "reward_std": 0.2975429594516754, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1804 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1921.0, "completions/mean_length": 1222.0, "completions/mean_terminated_length": 1069.0369873046875, "completions/min_length": 452.0, "completions/min_terminated_length": 452.0, "epoch": 0.32026970080067424, "frac_reward_zero_std": 0.25, "grad_norm": 0.5925901532173157, "learning_rate": 9.8e-08, "loss": 0.0343, "num_tokens": 366691569.0, "reward": 0.640625, "reward_std": 0.29842114448547363, "rewards/simpleverify_reward/mean": 0.640625, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 1805 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1816.0, "completions/mean_length": 1234.390625, "completions/mean_terminated_length": 1092.5687255859375, "completions/min_length": 465.0, "completions/min_terminated_length": 465.0, "epoch": 0.32044713553795995, "frac_reward_zero_std": 0.25, "grad_norm": 0.7303621768951416, "learning_rate": 9.749999999999999e-08, "loss": 0.0264, "num_tokens": 366862995.0, "reward": 0.5703125, "reward_std": 0.2603282630443573, "rewards/simpleverify_reward/mean": 0.5703125, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1806 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1968.0, "completions/mean_length": 1206.90625, "completions/mean_terminated_length": 1051.148193359375, "completions/min_length": 522.0, "completions/min_terminated_length": 522.0, "epoch": 0.32062457027524566, "frac_reward_zero_std": 0.25, "grad_norm": 0.6719720959663391, "learning_rate": 9.7e-08, "loss": 0.0285, "num_tokens": 367030903.0, "reward": 0.6328125, "reward_std": 0.24164125323295593, "rewards/simpleverify_reward/mean": 0.6328125, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1807 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1918.0, "completions/mean_length": 1257.671875, "completions/mean_terminated_length": 1128.345458984375, "completions/min_length": 495.0, "completions/min_terminated_length": 495.0, "epoch": 0.3208020050125313, "frac_reward_zero_std": 0.375, "grad_norm": 0.5795762538909912, "learning_rate": 9.65e-08, "loss": 0.0136, "num_tokens": 367205309.0, "reward": 0.6328125, "reward_std": 0.2541820704936981, "rewards/simpleverify_reward/mean": 0.6328125, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1808 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1355.0390625, "completions/mean_terminated_length": 1186.8447265625, "completions/min_length": 442.0, "completions/min_terminated_length": 442.0, "epoch": 0.320979439749817, "frac_reward_zero_std": 0.25, "grad_norm": 0.6234398484230042, "learning_rate": 9.6e-08, "loss": 0.0176, "num_tokens": 367390402.0, "reward": 0.578125, "reward_std": 0.3188907504081726, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1809 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1949.0, "completions/mean_length": 1324.625, "completions/mean_terminated_length": 1157.6923828125, "completions/min_length": 469.0, "completions/min_terminated_length": 469.0, "epoch": 0.32115687448710273, "frac_reward_zero_std": 0.25, "grad_norm": 0.5924640893936157, "learning_rate": 9.55e-08, "loss": 0.0094, "num_tokens": 367571602.0, "reward": 0.5546875, "reward_std": 0.3259190022945404, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1810 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2015.0, "completions/mean_length": 1325.28125, "completions/mean_terminated_length": 1141.058837890625, "completions/min_length": 449.0, "completions/min_terminated_length": 449.0, "epoch": 0.3213343092243884, "frac_reward_zero_std": 0.375, "grad_norm": 0.5998307466506958, "learning_rate": 9.499999999999999e-08, "loss": 0.0038, "num_tokens": 367752886.0, "reward": 0.5859375, "reward_std": 0.3055257201194763, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1811 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2020.0, "completions/mean_length": 1353.59375, "completions/mean_terminated_length": 1150.1817626953125, "completions/min_length": 457.0, "completions/min_terminated_length": 457.0, "epoch": 0.3215117439616741, "frac_reward_zero_std": 0.375, "grad_norm": 0.5854908227920532, "learning_rate": 9.449999999999999e-08, "loss": 0.0123, "num_tokens": 367937794.0, "reward": 0.5859375, "reward_std": 0.2876407504081726, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1812 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2007.0, "completions/mean_length": 1509.9765625, "completions/mean_terminated_length": 1187.1624755859375, "completions/min_length": 364.0, "completions/min_terminated_length": 364.0, "epoch": 0.3216891786989598, "frac_reward_zero_std": 0.125, "grad_norm": 0.5646727681159973, "learning_rate": 9.4e-08, "loss": 0.0184, "num_tokens": 368143039.0, "reward": 0.3828125, "reward_std": 0.3373110294342041, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1813 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3984375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1500.578125, "completions/mean_terminated_length": 1138.0, "completions/min_length": 416.0, "completions/min_terminated_length": 416.0, "epoch": 0.3218666134362455, "frac_reward_zero_std": 0.125, "grad_norm": 0.554463803768158, "learning_rate": 9.35e-08, "loss": 0.028, "num_tokens": 368347081.0, "reward": 0.4375, "reward_std": 0.3696783781051636, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1814 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1469.1953125, "completions/mean_terminated_length": 1186.523193359375, "completions/min_length": 359.0, "completions/min_terminated_length": 359.0, "epoch": 0.32204404817353116, "frac_reward_zero_std": 0.375, "grad_norm": 0.5229028463363647, "learning_rate": 9.3e-08, "loss": 0.0239, "num_tokens": 368547106.0, "reward": 0.4296875, "reward_std": 0.3083775043487549, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1815 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2015.0, "completions/mean_length": 1470.4375, "completions/mean_terminated_length": 1198.2529296875, "completions/min_length": 390.0, "completions/min_terminated_length": 390.0, "epoch": 0.32222148291081687, "frac_reward_zero_std": 0.0, "grad_norm": 0.6636422872543335, "learning_rate": 9.25e-08, "loss": 0.0176, "num_tokens": 368747290.0, "reward": 0.3984375, "reward_std": 0.36222386360168457, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1816 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.03125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1799.0, "completions/mean_length": 948.8671875, "completions/mean_terminated_length": 913.4112548828125, "completions/min_length": 224.0, "completions/min_terminated_length": 224.0, "epoch": 0.3223989176481026, "frac_reward_zero_std": 0.25, "grad_norm": 0.8019546270370483, "learning_rate": 9.199999999999999e-08, "loss": -0.0004, "num_tokens": 368877497.0, "reward": 0.5390625, "reward_std": 0.303933709859848, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1817 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 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": 1727.0, "completions/max_terminated_length": 1727.0, "completions/mean_length": 926.984375, "completions/mean_terminated_length": 926.984375, "completions/min_length": 268.0, "completions/min_terminated_length": 268.0, "epoch": 0.32257635238538823, "frac_reward_zero_std": 0.125, "grad_norm": 0.773457407951355, "learning_rate": 9.149999999999999e-08, "loss": 0.0005, "num_tokens": 369004903.0, "reward": 0.59375, "reward_std": 0.31468650698661804, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1818 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 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": 2048.0, "completions/max_terminated_length": 1949.0, "completions/mean_length": 968.4921875, "completions/mean_terminated_length": 959.9921264648438, "completions/min_length": 257.0, "completions/min_terminated_length": 257.0, "epoch": 0.32275378712267394, "frac_reward_zero_std": 0.125, "grad_norm": 0.8815913796424866, "learning_rate": 9.1e-08, "loss": -0.0222, "num_tokens": 369137622.0, "reward": 0.546875, "reward_std": 0.3182255029678345, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1819 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 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": 2020.0, "completions/max_terminated_length": 2020.0, "completions/mean_length": 948.3359375, "completions/mean_terminated_length": 948.3359375, "completions/min_length": 314.0, "completions/min_terminated_length": 314.0, "epoch": 0.32293122185995965, "frac_reward_zero_std": 0.125, "grad_norm": 0.9375982880592346, "learning_rate": 9.05e-08, "loss": 0.0074, "num_tokens": 369267761.0, "reward": 0.546875, "reward_std": 0.3493165373802185, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1820 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1259.015625, "completions/mean_terminated_length": 1076.9423828125, "completions/min_length": 424.0, "completions/min_terminated_length": 424.0, "epoch": 0.3231086565972453, "frac_reward_zero_std": 0.0, "grad_norm": 0.8494004607200623, "learning_rate": 9e-08, "loss": -0.0081, "num_tokens": 369439683.0, "reward": 0.40625, "reward_std": 0.4168228209018707, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1821 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2006.0, "completions/mean_length": 1229.0078125, "completions/mean_terminated_length": 1030.2232666015625, "completions/min_length": 517.0, "completions/min_terminated_length": 517.0, "epoch": 0.323286091334531, "frac_reward_zero_std": 0.125, "grad_norm": 0.7107903957366943, "learning_rate": 8.949999999999999e-08, "loss": -0.0143, "num_tokens": 369607764.0, "reward": 0.421875, "reward_std": 0.3318798542022705, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1822 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1220.8671875, "completions/mean_terminated_length": 1049.1981201171875, "completions/min_length": 461.0, "completions/min_terminated_length": 461.0, "epoch": 0.3234635260718167, "frac_reward_zero_std": 0.125, "grad_norm": 0.7141254544258118, "learning_rate": 8.899999999999999e-08, "loss": -0.0032, "num_tokens": 369774803.0, "reward": 0.4140625, "reward_std": 0.37146639823913574, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1823 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1260.75, "completions/mean_terminated_length": 1009.1546020507812, "completions/min_length": 413.0, "completions/min_terminated_length": 413.0, "epoch": 0.32364096080910243, "frac_reward_zero_std": 0.0, "grad_norm": 0.8488349914550781, "learning_rate": 8.849999999999999e-08, "loss": 0.0179, "num_tokens": 369946947.0, "reward": 0.3515625, "reward_std": 0.40402472019195557, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1824 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1538.390625, "completions/mean_terminated_length": 1154.4383544921875, "completions/min_length": 483.0, "completions/min_terminated_length": 483.0, "epoch": 0.3238183955463881, "frac_reward_zero_std": 0.25, "grad_norm": 0.5954626798629761, "learning_rate": 8.8e-08, "loss": 0.0153, "num_tokens": 370156373.0, "reward": 0.2890625, "reward_std": 0.3088296055793762, "rewards/simpleverify_reward/mean": 0.2890625, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 1825 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4921875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1891.0, "completions/mean_length": 1552.1015625, "completions/mean_terminated_length": 1071.4615478515625, "completions/min_length": 638.0, "completions/min_terminated_length": 638.0, "epoch": 0.3239958302836738, "frac_reward_zero_std": 0.25, "grad_norm": 0.7211251258850098, "learning_rate": 8.75e-08, "loss": 0.0327, "num_tokens": 370367554.0, "reward": 0.203125, "reward_std": 0.26847386360168457, "rewards/simpleverify_reward/mean": 0.203125, "rewards/simpleverify_reward/std": 0.40390563011169434, "step": 1826 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2003.0, "completions/mean_length": 1499.3046875, "completions/mean_terminated_length": 1123.881591796875, "completions/min_length": 550.0, "completions/min_terminated_length": 550.0, "epoch": 0.3241732650209595, "frac_reward_zero_std": 0.25, "grad_norm": 0.7914566993713379, "learning_rate": 8.699999999999998e-08, "loss": 0.0444, "num_tokens": 370571977.0, "reward": 0.2578125, "reward_std": 0.2856174111366272, "rewards/simpleverify_reward/mean": 0.2578125, "rewards/simpleverify_reward/std": 0.43914902210235596, "step": 1827 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1480.9765625, "completions/mean_terminated_length": 1067.2027587890625, "completions/min_length": 432.0, "completions/min_terminated_length": 432.0, "epoch": 0.32435069975824515, "frac_reward_zero_std": 0.375, "grad_norm": 1.0252747535705566, "learning_rate": 8.649999999999999e-08, "loss": 0.0135, "num_tokens": 370774054.0, "reward": 0.2890625, "reward_std": 0.265360951423645, "rewards/simpleverify_reward/mean": 0.2890625, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 1828 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2003.0, "completions/mean_length": 1298.8359375, "completions/mean_terminated_length": 1184.09912109375, "completions/min_length": 606.0, "completions/min_terminated_length": 606.0, "epoch": 0.32452813449553086, "frac_reward_zero_std": 0.125, "grad_norm": 0.6478581428527832, "learning_rate": 8.599999999999999e-08, "loss": 0.0269, "num_tokens": 370951265.0, "reward": 0.71875, "reward_std": 0.375, "rewards/simpleverify_reward/mean": 0.71875, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 1829 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1324.234375, "completions/mean_terminated_length": 1198.0733642578125, "completions/min_length": 599.0, "completions/min_terminated_length": 599.0, "epoch": 0.32470556923281657, "frac_reward_zero_std": 0.25, "grad_norm": 0.5781984329223633, "learning_rate": 8.55e-08, "loss": 0.0292, "num_tokens": 371131727.0, "reward": 0.7109375, "reward_std": 0.34572336077690125, "rewards/simpleverify_reward/mean": 0.7109375, "rewards/simpleverify_reward/std": 0.45510825514793396, "step": 1830 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2003.0, "completions/mean_length": 1311.5, "completions/mean_terminated_length": 1183.1192626953125, "completions/min_length": 581.0, "completions/min_terminated_length": 581.0, "epoch": 0.3248830039701022, "frac_reward_zero_std": 0.125, "grad_norm": 0.6362768411636353, "learning_rate": 8.500000000000001e-08, "loss": 0.0227, "num_tokens": 371310559.0, "reward": 0.7421875, "reward_std": 0.35232728719711304, "rewards/simpleverify_reward/mean": 0.7421875, "rewards/simpleverify_reward/std": 0.43914902210235596, "step": 1831 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1292.7421875, "completions/mean_terminated_length": 1199.9912109375, "completions/min_length": 629.0, "completions/min_terminated_length": 629.0, "epoch": 0.32506043870738793, "frac_reward_zero_std": 0.375, "grad_norm": 0.48291173577308655, "learning_rate": 8.45e-08, "loss": 0.0152, "num_tokens": 371486990.0, "reward": 0.7890625, "reward_std": 0.2686648368835449, "rewards/simpleverify_reward/mean": 0.7890625, "rewards/simpleverify_reward/std": 0.4095771610736847, "step": 1832 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1974.0, "completions/mean_length": 1138.6796875, "completions/mean_terminated_length": 949.9528198242188, "completions/min_length": 439.0, "completions/min_terminated_length": 439.0, "epoch": 0.32523787344467364, "frac_reward_zero_std": 0.375, "grad_norm": 0.7181811928749084, "learning_rate": 8.4e-08, "loss": 0.0247, "num_tokens": 371651237.0, "reward": 0.6015625, "reward_std": 0.24007563292980194, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1833 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1929.0, "completions/mean_length": 1113.4453125, "completions/mean_terminated_length": 930.0280151367188, "completions/min_length": 415.0, "completions/min_terminated_length": 415.0, "epoch": 0.32541530818195935, "frac_reward_zero_std": 0.25, "grad_norm": 0.8692100048065186, "learning_rate": 8.35e-08, "loss": -0.005, "num_tokens": 371812254.0, "reward": 0.6328125, "reward_std": 0.2541820704936981, "rewards/simpleverify_reward/mean": 0.6328125, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1834 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2034.0, "completions/mean_length": 1121.1953125, "completions/mean_terminated_length": 939.2990112304688, "completions/min_length": 466.0, "completions/min_terminated_length": 466.0, "epoch": 0.325592742919245, "frac_reward_zero_std": 0.375, "grad_norm": 0.7731946706771851, "learning_rate": 8.3e-08, "loss": 0.0134, "num_tokens": 371974263.0, "reward": 0.609375, "reward_std": 0.27337533235549927, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1835 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1129.0703125, "completions/mean_terminated_length": 978.699951171875, "completions/min_length": 449.0, "completions/min_terminated_length": 449.0, "epoch": 0.3257701776565307, "frac_reward_zero_std": 0.25, "grad_norm": 0.7814953327178955, "learning_rate": 8.25e-08, "loss": 0.0003, "num_tokens": 372137280.0, "reward": 0.5390625, "reward_std": 0.30324089527130127, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1836 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2002.0, "completions/mean_length": 1140.515625, "completions/mean_terminated_length": 920.25244140625, "completions/min_length": 319.0, "completions/min_terminated_length": 319.0, "epoch": 0.3259476123938164, "frac_reward_zero_std": 0.375, "grad_norm": 0.6458981037139893, "learning_rate": 8.2e-08, "loss": 0.0006, "num_tokens": 372291970.0, "reward": 0.5625, "reward_std": 0.21962818503379822, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1837 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1151.4375, "completions/mean_terminated_length": 1032.4248046875, "completions/min_length": 299.0, "completions/min_terminated_length": 299.0, "epoch": 0.3261250471311021, "frac_reward_zero_std": 0.625, "grad_norm": 0.3827361464500427, "learning_rate": 8.15e-08, "loss": -0.0005, "num_tokens": 372448058.0, "reward": 0.609375, "reward_std": 0.14699089527130127, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1838 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1123.078125, "completions/mean_terminated_length": 1009.4912109375, "completions/min_length": 315.0, "completions/min_terminated_length": 315.0, "epoch": 0.3263024818683878, "frac_reward_zero_std": 0.625, "grad_norm": 0.43035393953323364, "learning_rate": 8.1e-08, "loss": 0.0075, "num_tokens": 372600516.0, "reward": 0.6015625, "reward_std": 0.15513263642787933, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1839 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1146.59375, "completions/mean_terminated_length": 979.6666870117188, "completions/min_length": 345.0, "completions/min_terminated_length": 345.0, "epoch": 0.3264799166056735, "frac_reward_zero_std": 0.375, "grad_norm": 0.5989941358566284, "learning_rate": 8.05e-08, "loss": -0.0022, "num_tokens": 372755984.0, "reward": 0.5703125, "reward_std": 0.20818254351615906, "rewards/simpleverify_reward/mean": 0.5703125, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1840 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1485.5, "completions/mean_terminated_length": 1180.530029296875, "completions/min_length": 486.0, "completions/min_terminated_length": 486.0, "epoch": 0.32665735134295915, "frac_reward_zero_std": 0.25, "grad_norm": 0.5033450126647949, "learning_rate": 8e-08, "loss": 0.0195, "num_tokens": 372956192.0, "reward": 0.390625, "reward_std": 0.2662929594516754, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1841 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1486.59375, "completions/mean_terminated_length": 1160.8394775390625, "completions/min_length": 515.0, "completions/min_terminated_length": 515.0, "epoch": 0.32683478608024485, "frac_reward_zero_std": 0.5, "grad_norm": 0.4286954402923584, "learning_rate": 7.95e-08, "loss": 0.0285, "num_tokens": 373156540.0, "reward": 0.3984375, "reward_std": 0.17472384870052338, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1842 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1496.953125, "completions/mean_terminated_length": 1155.16455078125, "completions/min_length": 460.0, "completions/min_terminated_length": 460.0, "epoch": 0.32701222081753056, "frac_reward_zero_std": 0.625, "grad_norm": 0.3369769752025604, "learning_rate": 7.899999999999999e-08, "loss": 0.0107, "num_tokens": 373358214.0, "reward": 0.3515625, "reward_std": 0.13644562661647797, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1843 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1487.2890625, "completions/mean_terminated_length": 1193.5833740234375, "completions/min_length": 508.0, "completions/min_terminated_length": 508.0, "epoch": 0.3271896555548162, "frac_reward_zero_std": 0.5, "grad_norm": 0.5441376566886902, "learning_rate": 7.85e-08, "loss": 0.0143, "num_tokens": 373558651.0, "reward": 0.375, "reward_std": 0.18968652188777924, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 1844 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1988.0, "completions/mean_length": 1352.171875, "completions/mean_terminated_length": 1139.1632080078125, "completions/min_length": 373.0, "completions/min_terminated_length": 373.0, "epoch": 0.3273670902921019, "frac_reward_zero_std": 0.375, "grad_norm": 0.4631456732749939, "learning_rate": 7.8e-08, "loss": 0.0318, "num_tokens": 373741361.0, "reward": 0.734375, "reward_std": 0.2543674111366272, "rewards/simpleverify_reward/mean": 0.734375, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 1845 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 1994.0, "completions/mean_length": 1365.484375, "completions/mean_terminated_length": 1137.979248046875, "completions/min_length": 409.0, "completions/min_terminated_length": 409.0, "epoch": 0.32754452502938763, "frac_reward_zero_std": 0.375, "grad_norm": 0.4359433948993683, "learning_rate": 7.75e-08, "loss": 0.0231, "num_tokens": 373925775.0, "reward": 0.671875, "reward_std": 0.27792394161224365, "rewards/simpleverify_reward/mean": 0.671875, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1846 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1980.0, "completions/mean_length": 1346.1953125, "completions/mean_terminated_length": 1149.68994140625, "completions/min_length": 428.0, "completions/min_terminated_length": 428.0, "epoch": 0.32772195976667334, "frac_reward_zero_std": 0.5, "grad_norm": 0.4288485646247864, "learning_rate": 7.7e-08, "loss": 0.0293, "num_tokens": 374107720.0, "reward": 0.734375, "reward_std": 0.20927388966083527, "rewards/simpleverify_reward/mean": 0.734375, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 1847 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1392.1171875, "completions/mean_terminated_length": 1135.4674072265625, "completions/min_length": 390.0, "completions/min_terminated_length": 390.0, "epoch": 0.327899394503959, "frac_reward_zero_std": 0.5, "grad_norm": 0.41701191663742065, "learning_rate": 7.649999999999999e-08, "loss": 0.0234, "num_tokens": 374295543.0, "reward": 0.671875, "reward_std": 0.22359731793403625, "rewards/simpleverify_reward/mean": 0.671875, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1848 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1974.0, "completions/mean_length": 1400.84375, "completions/mean_terminated_length": 1202.734619140625, "completions/min_length": 550.0, "completions/min_terminated_length": 550.0, "epoch": 0.3280768292412447, "frac_reward_zero_std": 0.375, "grad_norm": 0.5285943150520325, "learning_rate": 7.599999999999999e-08, "loss": 0.0094, "num_tokens": 374485411.0, "reward": 0.453125, "reward_std": 0.22293207049369812, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1849 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1380.4921875, "completions/mean_terminated_length": 1184.9595947265625, "completions/min_length": 536.0, "completions/min_terminated_length": 536.0, "epoch": 0.3282542639785304, "frac_reward_zero_std": 0.5, "grad_norm": 0.47812801599502563, "learning_rate": 7.55e-08, "loss": 0.0101, "num_tokens": 374672674.0, "reward": 0.421875, "reward_std": 0.18023642897605896, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1850 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1971.0, "completions/mean_length": 1378.421875, "completions/mean_terminated_length": 1190.93994140625, "completions/min_length": 519.0, "completions/min_terminated_length": 519.0, "epoch": 0.32843169871581607, "frac_reward_zero_std": 0.375, "grad_norm": 0.5240035057067871, "learning_rate": 7.5e-08, "loss": 0.0258, "num_tokens": 374859672.0, "reward": 0.4375, "reward_std": 0.24273642897605896, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1851 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1340.234375, "completions/mean_terminated_length": 1168.4466552734375, "completions/min_length": 527.0, "completions/min_terminated_length": 527.0, "epoch": 0.3286091334531018, "frac_reward_zero_std": 0.375, "grad_norm": 0.5369052290916443, "learning_rate": 7.45e-08, "loss": 0.0048, "num_tokens": 375041782.0, "reward": 0.4453125, "reward_std": 0.2077304571866989, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1852 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1881.0, "completions/mean_length": 993.8828125, "completions/mean_terminated_length": 968.5840454101562, "completions/min_length": 461.0, "completions/min_terminated_length": 461.0, "epoch": 0.3287865681903875, "frac_reward_zero_std": 0.5, "grad_norm": 0.6629040241241455, "learning_rate": 7.399999999999999e-08, "loss": 0.0051, "num_tokens": 375176183.0, "reward": 0.796875, "reward_std": 0.19628483057022095, "rewards/simpleverify_reward/mean": 0.796875, "rewards/simpleverify_reward/std": 0.40390563011169434, "step": 1853 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1947.0, "completions/mean_length": 989.4921875, "completions/mean_terminated_length": 918.925048828125, "completions/min_length": 450.0, "completions/min_terminated_length": 450.0, "epoch": 0.32896400292767314, "frac_reward_zero_std": 0.5, "grad_norm": 0.7137410640716553, "learning_rate": 7.349999999999999e-08, "loss": -0.0062, "num_tokens": 375310022.0, "reward": 0.765625, "reward_std": 0.20709684491157532, "rewards/simpleverify_reward/mean": 0.765625, "rewards/simpleverify_reward/std": 0.42527204751968384, "step": 1854 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1978.0, "completions/mean_length": 993.8984375, "completions/mean_terminated_length": 977.166748046875, "completions/min_length": 415.0, "completions/min_terminated_length": 415.0, "epoch": 0.32914143766495885, "frac_reward_zero_std": 0.5, "grad_norm": 0.5960044860839844, "learning_rate": 7.299999999999999e-08, "loss": 0.0119, "num_tokens": 375444425.0, "reward": 0.8359375, "reward_std": 0.21215170621871948, "rewards/simpleverify_reward/mean": 0.8359375, "rewards/simpleverify_reward/std": 0.371787428855896, "step": 1855 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.03125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1016.90625, "completions/mean_terminated_length": 983.6451416015625, "completions/min_length": 430.0, "completions/min_terminated_length": 430.0, "epoch": 0.32931887240224456, "frac_reward_zero_std": 0.5, "grad_norm": 0.6117632985115051, "learning_rate": 7.25e-08, "loss": -0.0013, "num_tokens": 375581773.0, "reward": 0.796875, "reward_std": 0.2115406095981598, "rewards/simpleverify_reward/mean": 0.796875, "rewards/simpleverify_reward/std": 0.40390563011169434, "step": 1856 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4765625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1299.9453125, "completions/mean_terminated_length": 618.8805541992188, "completions/min_length": 355.0, "completions/min_terminated_length": 355.0, "epoch": 0.32949630713953026, "frac_reward_zero_std": 0.625, "grad_norm": 0.47664153575897217, "learning_rate": 7.2e-08, "loss": -0.0016, "num_tokens": 375767798.0, "reward": 0.5, "reward_std": 0.12433473765850067, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 1857 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1293.7421875, "completions/mean_terminated_length": 688.2112426757812, "completions/min_length": 361.0, "completions/min_terminated_length": 361.0, "epoch": 0.3296737418768159, "frac_reward_zero_std": 0.625, "grad_norm": 0.5130541324615479, "learning_rate": 7.149999999999999e-08, "loss": -0.0059, "num_tokens": 375953029.0, "reward": 0.46875, "reward_std": 0.16109731793403625, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1858 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1304.09375, "completions/mean_terminated_length": 706.8732299804688, "completions/min_length": 381.0, "completions/min_terminated_length": 381.0, "epoch": 0.3298511766141016, "frac_reward_zero_std": 0.375, "grad_norm": 0.7497277855873108, "learning_rate": 7.099999999999999e-08, "loss": 0.0057, "num_tokens": 376139585.0, "reward": 0.4609375, "reward_std": 0.20818254351615906, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1859 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.453125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1290.2734375, "completions/mean_terminated_length": 662.44287109375, "completions/min_length": 357.0, "completions/min_terminated_length": 357.0, "epoch": 0.33002861135138734, "frac_reward_zero_std": 0.75, "grad_norm": 0.3761014938354492, "learning_rate": 7.049999999999999e-08, "loss": -0.0002, "num_tokens": 376324372.0, "reward": 0.4609375, "reward_std": 0.11493883281946182, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1860 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1749.625, "completions/mean_terminated_length": 1299.1373291015625, "completions/min_length": 832.0, "completions/min_terminated_length": 832.0, "epoch": 0.330206046088673, "frac_reward_zero_std": 0.375, "grad_norm": 0.44837048649787903, "learning_rate": 7e-08, "loss": 0.0301, "num_tokens": 376561556.0, "reward": 0.328125, "reward_std": 0.2614234387874603, "rewards/simpleverify_reward/mean": 0.328125, "rewards/simpleverify_reward/std": 0.4713755249977112, "step": 1861 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1753.875, "completions/mean_terminated_length": 1375.71435546875, "completions/min_length": 766.0, "completions/min_terminated_length": 766.0, "epoch": 0.3303834808259587, "frac_reward_zero_std": 0.375, "grad_norm": 0.44296371936798096, "learning_rate": 6.950000000000001e-08, "loss": 0.0225, "num_tokens": 376799284.0, "reward": 0.3515625, "reward_std": 0.2847132086753845, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1862 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5703125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1731.453125, "completions/mean_terminated_length": 1311.30908203125, "completions/min_length": 741.0, "completions/min_terminated_length": 741.0, "epoch": 0.3305609155632444, "frac_reward_zero_std": 0.375, "grad_norm": 0.5759620666503906, "learning_rate": 6.900000000000001e-08, "loss": 0.0281, "num_tokens": 377034142.0, "reward": 0.3828125, "reward_std": 0.2537299692630768, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1863 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1873.0, "completions/mean_length": 1743.5625, "completions/mean_terminated_length": 1312.7547607421875, "completions/min_length": 826.0, "completions/min_terminated_length": 826.0, "epoch": 0.33073835030053006, "frac_reward_zero_std": 0.25, "grad_norm": 0.5275439023971558, "learning_rate": 6.85e-08, "loss": 0.0325, "num_tokens": 377270550.0, "reward": 0.3359375, "reward_std": 0.30963167548179626, "rewards/simpleverify_reward/mean": 0.3359375, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1864 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1143.3046875, "completions/mean_terminated_length": 1041.0347900390625, "completions/min_length": 512.0, "completions/min_terminated_length": 512.0, "epoch": 0.33091578503781577, "frac_reward_zero_std": 0.75, "grad_norm": 0.28659698367118835, "learning_rate": 6.8e-08, "loss": 0.0127, "num_tokens": 377425709.0, "reward": 0.734375, "reward_std": 0.1280868798494339, "rewards/simpleverify_reward/mean": 0.734375, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 1865 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0703125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1118.7578125, "completions/mean_terminated_length": 1048.47900390625, "completions/min_length": 508.0, "completions/min_terminated_length": 508.0, "epoch": 0.3310932197751015, "frac_reward_zero_std": 0.5, "grad_norm": 0.5092146992683411, "learning_rate": 6.75e-08, "loss": 0.033, "num_tokens": 377577726.0, "reward": 0.7578125, "reward_std": 0.18244513869285583, "rewards/simpleverify_reward/mean": 0.7578125, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 1866 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1110.3984375, "completions/mean_terminated_length": 1030.940673828125, "completions/min_length": 537.0, "completions/min_terminated_length": 537.0, "epoch": 0.3312706545123872, "frac_reward_zero_std": 0.625, "grad_norm": 0.36527925729751587, "learning_rate": 6.7e-08, "loss": 0.0303, "num_tokens": 377728673.0, "reward": 0.765625, "reward_std": 0.1556389182806015, "rewards/simpleverify_reward/mean": 0.765625, "rewards/simpleverify_reward/std": 0.42527204751968384, "step": 1867 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1977.0, "completions/mean_length": 1097.3125, "completions/mean_terminated_length": 1016.7457885742188, "completions/min_length": 495.0, "completions/min_terminated_length": 495.0, "epoch": 0.33144808924967284, "frac_reward_zero_std": 0.625, "grad_norm": 0.4258614480495453, "learning_rate": 6.65e-08, "loss": 0.0157, "num_tokens": 377877945.0, "reward": 0.7578125, "reward_std": 0.1692390739917755, "rewards/simpleverify_reward/mean": 0.7578125, "rewards/simpleverify_reward/std": 0.4300905168056488, "step": 1868 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2021.0, "completions/mean_length": 1507.5390625, "completions/mean_terminated_length": 1296.0543212890625, "completions/min_length": 621.0, "completions/min_terminated_length": 621.0, "epoch": 0.33162552398695855, "frac_reward_zero_std": 0.375, "grad_norm": 0.5361859798431396, "learning_rate": 6.6e-08, "loss": 0.0126, "num_tokens": 378082206.0, "reward": 0.5390625, "reward_std": 0.29791927337646484, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1869 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2013.0, "completions/mean_length": 1479.828125, "completions/mean_terminated_length": 1221.5682373046875, "completions/min_length": 622.0, "completions/min_terminated_length": 622.0, "epoch": 0.33180295872424426, "frac_reward_zero_std": 0.375, "grad_norm": 0.5821510553359985, "learning_rate": 6.55e-08, "loss": 0.0293, "num_tokens": 378282920.0, "reward": 0.4921875, "reward_std": 0.2777385711669922, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1870 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1490.140625, "completions/mean_terminated_length": 1254.5999755859375, "completions/min_length": 659.0, "completions/min_terminated_length": 659.0, "epoch": 0.3319803934615299, "frac_reward_zero_std": 0.5, "grad_norm": 0.5245599746704102, "learning_rate": 6.5e-08, "loss": 0.0123, "num_tokens": 378484954.0, "reward": 0.53125, "reward_std": 0.2551366090774536, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1871 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2015.0, "completions/mean_length": 1476.1953125, "completions/mean_terminated_length": 1243.703369140625, "completions/min_length": 696.0, "completions/min_terminated_length": 696.0, "epoch": 0.3321578281988156, "frac_reward_zero_std": 0.25, "grad_norm": 0.5846651196479797, "learning_rate": 6.45e-08, "loss": 0.0251, "num_tokens": 378685203.0, "reward": 0.5390625, "reward_std": 0.32043421268463135, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1872 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1971.0, "completions/mean_length": 1194.5546875, "completions/mean_terminated_length": 944.5555419921875, "completions/min_length": 263.0, "completions/min_terminated_length": 263.0, "epoch": 0.3323352629361013, "frac_reward_zero_std": 0.375, "grad_norm": 0.7260473966598511, "learning_rate": 6.4e-08, "loss": 0.0006, "num_tokens": 378846906.0, "reward": 0.5390625, "reward_std": 0.25623178482055664, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1873 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1177.5859375, "completions/mean_terminated_length": 933.8699951171875, "completions/min_length": 264.0, "completions/min_terminated_length": 264.0, "epoch": 0.332512697673387, "frac_reward_zero_std": 0.375, "grad_norm": 0.6654760837554932, "learning_rate": 6.349999999999999e-08, "loss": 0.0375, "num_tokens": 379006437.0, "reward": 0.5234375, "reward_std": 0.259880006313324, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1874 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1955.0, "completions/mean_length": 1186.4140625, "completions/mean_terminated_length": 911.0618286132812, "completions/min_length": 247.0, "completions/min_terminated_length": 247.0, "epoch": 0.3326901324106727, "frac_reward_zero_std": 0.25, "grad_norm": 0.7884858250617981, "learning_rate": 6.3e-08, "loss": 0.0306, "num_tokens": 379167098.0, "reward": 0.5, "reward_std": 0.31343233585357666, "rewards/simpleverify_reward/mean": 0.5, "rewards/simpleverify_reward/std": 0.5019646286964417, "step": 1875 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1983.0, "completions/mean_length": 1156.453125, "completions/mean_terminated_length": 906.8200073242188, "completions/min_length": 267.0, "completions/min_terminated_length": 267.0, "epoch": 0.3328675671479584, "frac_reward_zero_std": 0.375, "grad_norm": 0.7164013385772705, "learning_rate": 6.25e-08, "loss": 0.0242, "num_tokens": 379323924.0, "reward": 0.6015625, "reward_std": 0.26408424973487854, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1876 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2009.0, "completions/mean_length": 1279.2734375, "completions/mean_terminated_length": 1177.2301025390625, "completions/min_length": 528.0, "completions/min_terminated_length": 528.0, "epoch": 0.3330450018852441, "frac_reward_zero_std": 0.25, "grad_norm": 0.6289778351783752, "learning_rate": 6.2e-08, "loss": 0.0274, "num_tokens": 379505367.0, "reward": 0.4140625, "reward_std": 0.27946737408638, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1877 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2035.0, "completions/mean_length": 1271.6953125, "completions/mean_terminated_length": 1168.64599609375, "completions/min_length": 533.0, "completions/min_terminated_length": 533.0, "epoch": 0.33322243662252976, "frac_reward_zero_std": 0.125, "grad_norm": 0.8298846483230591, "learning_rate": 6.15e-08, "loss": 0.0159, "num_tokens": 379685840.0, "reward": 0.4140625, "reward_std": 0.3221629858016968, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1878 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1934.0, "completions/mean_length": 1212.453125, "completions/mean_terminated_length": 1101.539794921875, "completions/min_length": 495.0, "completions/min_terminated_length": 495.0, "epoch": 0.33339987135981547, "frac_reward_zero_std": 0.125, "grad_norm": 0.7027313113212585, "learning_rate": 6.099999999999999e-08, "loss": 0.0297, "num_tokens": 379858730.0, "reward": 0.3828125, "reward_std": 0.29927173256874084, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1879 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.078125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1231.5234375, "completions/mean_terminated_length": 1162.33056640625, "completions/min_length": 499.0, "completions/min_terminated_length": 499.0, "epoch": 0.3335773060971012, "frac_reward_zero_std": 0.125, "grad_norm": 0.7388859987258911, "learning_rate": 6.049999999999999e-08, "loss": -0.0011, "num_tokens": 380034061.0, "reward": 0.4375, "reward_std": 0.34532544016838074, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1880 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1978.0, "completions/mean_length": 1158.34375, "completions/mean_terminated_length": 849.3052978515625, "completions/min_length": 325.0, "completions/min_terminated_length": 325.0, "epoch": 0.33375474083438683, "frac_reward_zero_std": 0.375, "grad_norm": 0.7102561593055725, "learning_rate": 6e-08, "loss": -0.0062, "num_tokens": 380194905.0, "reward": 0.4921875, "reward_std": 0.28548622131347656, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1881 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1134.90625, "completions/mean_terminated_length": 843.0927734375, "completions/min_length": 320.0, "completions/min_terminated_length": 320.0, "epoch": 0.33393217557167254, "frac_reward_zero_std": 0.25, "grad_norm": 0.7659732699394226, "learning_rate": 5.95e-08, "loss": -0.0083, "num_tokens": 380352749.0, "reward": 0.5390625, "reward_std": 0.2958405315876007, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1882 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1134.1015625, "completions/mean_terminated_length": 816.6421508789062, "completions/min_length": 329.0, "completions/min_terminated_length": 329.0, "epoch": 0.33410961030895825, "frac_reward_zero_std": 0.375, "grad_norm": 0.7015123963356018, "learning_rate": 5.899999999999999e-08, "loss": -0.0163, "num_tokens": 380510490.0, "reward": 0.4765625, "reward_std": 0.2665822207927704, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1883 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1965.0, "completions/mean_length": 1190.328125, "completions/mean_terminated_length": 916.2267456054688, "completions/min_length": 339.0, "completions/min_terminated_length": 339.0, "epoch": 0.3342870450462439, "frac_reward_zero_std": 0.375, "grad_norm": 0.7836437821388245, "learning_rate": 5.85e-08, "loss": -0.0119, "num_tokens": 380675428.0, "reward": 0.546875, "reward_std": 0.24888263642787933, "rewards/simpleverify_reward/mean": 0.546875, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1884 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.40625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2024.0, "completions/mean_length": 1525.8828125, "completions/mean_terminated_length": 1168.644775390625, "completions/min_length": 403.0, "completions/min_terminated_length": 403.0, "epoch": 0.3344644797835296, "frac_reward_zero_std": 0.25, "grad_norm": 0.5432262420654297, "learning_rate": 5.8e-08, "loss": 0.02, "num_tokens": 380884933.0, "reward": 0.4765625, "reward_std": 0.2702304720878601, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1885 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2014.0, "completions/mean_length": 1493.46875, "completions/mean_terminated_length": 1138.0, "completions/min_length": 424.0, "completions/min_terminated_length": 424.0, "epoch": 0.3346419145208153, "frac_reward_zero_std": 0.375, "grad_norm": 0.5389989018440247, "learning_rate": 5.75e-08, "loss": 0.0172, "num_tokens": 381090289.0, "reward": 0.4765625, "reward_std": 0.23378878831863403, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1886 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2016.0, "completions/mean_length": 1503.296875, "completions/mean_terminated_length": 1197.731689453125, "completions/min_length": 400.0, "completions/min_terminated_length": 400.0, "epoch": 0.33481934925810103, "frac_reward_zero_std": 0.375, "grad_norm": 0.503272533416748, "learning_rate": 5.7e-08, "loss": 0.0197, "num_tokens": 381296903.0, "reward": 0.484375, "reward_std": 0.25197336077690125, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1887 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3828125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1951.0, "completions/mean_length": 1503.71875, "completions/mean_terminated_length": 1166.1265869140625, "completions/min_length": 386.0, "completions/min_terminated_length": 386.0, "epoch": 0.3349967839953867, "frac_reward_zero_std": 0.375, "grad_norm": 0.49680444598197937, "learning_rate": 5.6499999999999996e-08, "loss": 0.02, "num_tokens": 381503571.0, "reward": 0.515625, "reward_std": 0.21369513869285583, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1888 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1997.0, "completions/mean_length": 1254.2265625, "completions/mean_terminated_length": 1080.3524169921875, "completions/min_length": 561.0, "completions/min_terminated_length": 561.0, "epoch": 0.3351742187326724, "frac_reward_zero_std": 0.25, "grad_norm": 0.6560686230659485, "learning_rate": 5.6e-08, "loss": 0.0225, "num_tokens": 381675312.0, "reward": 0.4453125, "reward_std": 0.27946737408638, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1889 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2011.0, "completions/mean_length": 1253.75, "completions/mean_terminated_length": 1106.6666259765625, "completions/min_length": 560.0, "completions/min_terminated_length": 560.0, "epoch": 0.3353516534699581, "frac_reward_zero_std": 0.125, "grad_norm": 0.6787051558494568, "learning_rate": 5.55e-08, "loss": -0.0118, "num_tokens": 381846992.0, "reward": 0.4765625, "reward_std": 0.3393382430076599, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1890 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1269.0859375, "completions/mean_terminated_length": 1116.2149658203125, "completions/min_length": 555.0, "completions/min_terminated_length": 555.0, "epoch": 0.33552908820724375, "frac_reward_zero_std": 0.25, "grad_norm": 0.6635191440582275, "learning_rate": 5.4999999999999996e-08, "loss": -0.0, "num_tokens": 382020635.0, "reward": 0.46875, "reward_std": 0.29203981161117554, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1891 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1990.0, "completions/mean_length": 1264.53125, "completions/mean_terminated_length": 1101.924560546875, "completions/min_length": 545.0, "completions/min_terminated_length": 545.0, "epoch": 0.33570652294452946, "frac_reward_zero_std": 0.375, "grad_norm": 0.6561899781227112, "learning_rate": 5.45e-08, "loss": -0.0093, "num_tokens": 382193695.0, "reward": 0.46875, "reward_std": 0.260971337556839, "rewards/simpleverify_reward/mean": 0.46875, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1892 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1157.7578125, "completions/mean_terminated_length": 919.7722778320312, "completions/min_length": 464.0, "completions/min_terminated_length": 464.0, "epoch": 0.33588395768181517, "frac_reward_zero_std": 0.375, "grad_norm": 0.6224446296691895, "learning_rate": 5.3999999999999994e-08, "loss": 0.0073, "num_tokens": 382351200.0, "reward": 0.578125, "reward_std": 0.2290782630443573, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1893 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2016.0, "completions/mean_length": 1147.75, "completions/mean_terminated_length": 918.2745361328125, "completions/min_length": 417.0, "completions/min_terminated_length": 417.0, "epoch": 0.3360613924191008, "frac_reward_zero_std": 0.375, "grad_norm": 0.545708179473877, "learning_rate": 5.3499999999999996e-08, "loss": 0.0036, "num_tokens": 382507424.0, "reward": 0.5546875, "reward_std": 0.22093650698661804, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1894 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1988.0, "completions/mean_length": 1153.8046875, "completions/mean_terminated_length": 914.7623901367188, "completions/min_length": 431.0, "completions/min_terminated_length": 431.0, "epoch": 0.33623882715638653, "frac_reward_zero_std": 0.625, "grad_norm": 0.4119203984737396, "learning_rate": 5.3e-08, "loss": -0.0013, "num_tokens": 382664423.0, "reward": 0.5703125, "reward_std": 0.1802906095981598, "rewards/simpleverify_reward/mean": 0.5703125, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1895 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2023.0, "completions/mean_length": 1131.359375, "completions/mean_terminated_length": 908.873779296875, "completions/min_length": 376.0, "completions/min_terminated_length": 376.0, "epoch": 0.33641626189367224, "frac_reward_zero_std": 0.5, "grad_norm": 0.4792971611022949, "learning_rate": 5.2499999999999994e-08, "loss": 0.0038, "num_tokens": 382818549.0, "reward": 0.5390625, "reward_std": 0.18244513869285583, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1896 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1585.6328125, "completions/mean_terminated_length": 1383.0224609375, "completions/min_length": 662.0, "completions/min_terminated_length": 662.0, "epoch": 0.33659369663095795, "frac_reward_zero_std": 0.125, "grad_norm": 0.6243671178817749, "learning_rate": 5.1999999999999996e-08, "loss": 0.0253, "num_tokens": 383034950.0, "reward": 0.4765625, "reward_std": 0.39706701040267944, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1897 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2043.0, "completions/mean_length": 1593.171875, "completions/mean_terminated_length": 1453.938720703125, "completions/min_length": 676.0, "completions/min_terminated_length": 676.0, "epoch": 0.3367711313682436, "frac_reward_zero_std": 0.125, "grad_norm": 0.5571836233139038, "learning_rate": 5.15e-08, "loss": 0.0074, "num_tokens": 383252316.0, "reward": 0.5078125, "reward_std": 0.3221629858016968, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1898 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1575.8046875, "completions/mean_terminated_length": 1405.0106201171875, "completions/min_length": 626.0, "completions/min_terminated_length": 626.0, "epoch": 0.3369485661055293, "frac_reward_zero_std": 0.125, "grad_norm": 0.581660270690918, "learning_rate": 5.0999999999999993e-08, "loss": 0.0049, "num_tokens": 383467459.0, "reward": 0.5390625, "reward_std": 0.36882779002189636, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1899 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1982.0, "completions/mean_length": 1563.5, "completions/mean_terminated_length": 1358.933349609375, "completions/min_length": 615.0, "completions/min_terminated_length": 615.0, "epoch": 0.337126000842815, "frac_reward_zero_std": 0.25, "grad_norm": 0.5561313629150391, "learning_rate": 5.05e-08, "loss": 0.0046, "num_tokens": 383681027.0, "reward": 0.4765625, "reward_std": 0.32863396406173706, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1900 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2022.0, "completions/mean_length": 1184.1953125, "completions/mean_terminated_length": 1051.90087890625, "completions/min_length": 429.0, "completions/min_terminated_length": 429.0, "epoch": 0.3373034355801007, "frac_reward_zero_std": 0.5, "grad_norm": 0.5415223836898804, "learning_rate": 5e-08, "loss": 0.0091, "num_tokens": 383842108.0, "reward": 0.515625, "reward_std": 0.20882563292980194, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1901 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1181.734375, "completions/mean_terminated_length": 1057.982177734375, "completions/min_length": 455.0, "completions/min_terminated_length": 455.0, "epoch": 0.3374808703173864, "frac_reward_zero_std": 0.625, "grad_norm": 0.46520721912384033, "learning_rate": 4.95e-08, "loss": -0.0012, "num_tokens": 384002874.0, "reward": 0.5234375, "reward_std": 0.16503483057022095, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1902 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1168.453125, "completions/mean_terminated_length": 1033.747802734375, "completions/min_length": 374.0, "completions/min_terminated_length": 374.0, "epoch": 0.3376583050546721, "frac_reward_zero_std": 0.5, "grad_norm": 0.5722686052322388, "learning_rate": 4.9e-08, "loss": -0.0003, "num_tokens": 384161940.0, "reward": 0.5234375, "reward_std": 0.19234731793403625, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1903 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1170.796875, "completions/mean_terminated_length": 1017.889892578125, "completions/min_length": 440.0, "completions/min_terminated_length": 440.0, "epoch": 0.33783573979195775, "frac_reward_zero_std": 0.625, "grad_norm": 0.4834861755371094, "learning_rate": 4.85e-08, "loss": 0.0047, "num_tokens": 384321306.0, "reward": 0.484375, "reward_std": 0.17693254351615906, "rewards/simpleverify_reward/mean": 0.484375, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1904 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 1922.0, "completions/mean_length": 1238.8515625, "completions/mean_terminated_length": 969.1354370117188, "completions/min_length": 324.0, "completions/min_terminated_length": 324.0, "epoch": 0.33801317452924345, "frac_reward_zero_std": 0.375, "grad_norm": 0.5904597640037537, "learning_rate": 4.8e-08, "loss": 0.0293, "num_tokens": 384491447.0, "reward": 0.6484375, "reward_std": 0.24872365593910217, "rewards/simpleverify_reward/mean": 0.6484375, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1905 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2015.0, "completions/mean_length": 1258.4765625, "completions/mean_terminated_length": 1027.2020263671875, "completions/min_length": 312.0, "completions/min_terminated_length": 312.0, "epoch": 0.33819060926652916, "frac_reward_zero_std": 0.5, "grad_norm": 0.5041691660881042, "learning_rate": 4.7499999999999995e-08, "loss": 0.0356, "num_tokens": 384664100.0, "reward": 0.640625, "reward_std": 0.2306797206401825, "rewards/simpleverify_reward/mean": 0.640625, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 1906 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1970.0, "completions/mean_length": 1229.546875, "completions/mean_terminated_length": 945.2421264648438, "completions/min_length": 297.0, "completions/min_terminated_length": 297.0, "epoch": 0.33836804400381487, "frac_reward_zero_std": 0.25, "grad_norm": 0.5857300758361816, "learning_rate": 4.7e-08, "loss": 0.0384, "num_tokens": 384833050.0, "reward": 0.6640625, "reward_std": 0.2760361433029175, "rewards/simpleverify_reward/mean": 0.6640625, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1907 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1986.0, "completions/mean_length": 1246.7890625, "completions/mean_terminated_length": 990.73193359375, "completions/min_length": 313.0, "completions/min_terminated_length": 313.0, "epoch": 0.3385454787411005, "frac_reward_zero_std": 0.5, "grad_norm": 0.484236478805542, "learning_rate": 4.65e-08, "loss": 0.0316, "num_tokens": 385004207.0, "reward": 0.6640625, "reward_std": 0.1945282220840454, "rewards/simpleverify_reward/mean": 0.6640625, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1908 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3359375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2022.0, "completions/mean_length": 1659.1328125, "completions/mean_terminated_length": 1462.4117431640625, "completions/min_length": 709.0, "completions/min_terminated_length": 709.0, "epoch": 0.33872291347838623, "frac_reward_zero_std": 0.375, "grad_norm": 0.49865350127220154, "learning_rate": 4.5999999999999995e-08, "loss": 0.0227, "num_tokens": 385234128.0, "reward": 0.5078125, "reward_std": 0.24052390456199646, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1909 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1612.6640625, "completions/mean_terminated_length": 1428.8555908203125, "completions/min_length": 645.0, "completions/min_terminated_length": 645.0, "epoch": 0.33890034821567194, "frac_reward_zero_std": 0.125, "grad_norm": 0.629196286201477, "learning_rate": 4.55e-08, "loss": 0.0224, "num_tokens": 385458101.0, "reward": 0.5625, "reward_std": 0.3182255029678345, "rewards/simpleverify_reward/mean": 0.5625, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1910 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.34375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1668.5625, "completions/mean_terminated_length": 1469.8095703125, "completions/min_length": 722.0, "completions/min_terminated_length": 722.0, "epoch": 0.3390777829529576, "frac_reward_zero_std": 0.25, "grad_norm": 0.5455185174942017, "learning_rate": 4.5e-08, "loss": 0.0075, "num_tokens": 385689229.0, "reward": 0.5234375, "reward_std": 0.22753483057022095, "rewards/simpleverify_reward/mean": 0.5234375, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1911 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2041.0, "completions/mean_length": 1650.765625, "completions/mean_terminated_length": 1463.563232421875, "completions/min_length": 708.0, "completions/min_terminated_length": 708.0, "epoch": 0.3392552176902433, "frac_reward_zero_std": 0.25, "grad_norm": 0.5264582633972168, "learning_rate": 4.4499999999999995e-08, "loss": 0.0175, "num_tokens": 385918079.0, "reward": 0.53125, "reward_std": 0.2792820334434509, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1912 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2030.0, "completions/mean_length": 1509.3984375, "completions/mean_terminated_length": 1103.602783203125, "completions/min_length": 462.0, "completions/min_terminated_length": 462.0, "epoch": 0.339432652427529, "frac_reward_zero_std": 0.625, "grad_norm": 0.4311012029647827, "learning_rate": 4.4e-08, "loss": 0.0003, "num_tokens": 386126914.0, "reward": 0.3203125, "reward_std": 0.18372184038162231, "rewards/simpleverify_reward/mean": 0.3203125, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 1913 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4296875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1486.8125, "completions/mean_terminated_length": 1064.0, "completions/min_length": 479.0, "completions/min_terminated_length": 479.0, "epoch": 0.33961008716481467, "frac_reward_zero_std": 0.5, "grad_norm": 0.5335213541984558, "learning_rate": 4.349999999999999e-08, "loss": -0.0064, "num_tokens": 386332858.0, "reward": 0.3046875, "reward_std": 0.2152385711669922, "rewards/simpleverify_reward/mean": 0.3046875, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 1914 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.4375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1522.453125, "completions/mean_terminated_length": 1113.6944580078125, "completions/min_length": 455.0, "completions/min_terminated_length": 455.0, "epoch": 0.3397875219021004, "frac_reward_zero_std": 0.5, "grad_norm": 0.5333724617958069, "learning_rate": 4.2999999999999995e-08, "loss": 0.0114, "num_tokens": 386543364.0, "reward": 0.3515625, "reward_std": 0.21433821320533752, "rewards/simpleverify_reward/mean": 0.3515625, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1915 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2014.0, "completions/mean_length": 1505.5, "completions/mean_terminated_length": 1157.74365234375, "completions/min_length": 443.0, "completions/min_terminated_length": 443.0, "epoch": 0.3399649566393861, "frac_reward_zero_std": 0.375, "grad_norm": 0.5212669372558594, "learning_rate": 4.2500000000000003e-08, "loss": 0.0053, "num_tokens": 386751700.0, "reward": 0.34375, "reward_std": 0.23680341243743896, "rewards/simpleverify_reward/mean": 0.34375, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 1916 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2020.0, "completions/mean_length": 1340.5859375, "completions/mean_terminated_length": 1063.771728515625, "completions/min_length": 608.0, "completions/min_terminated_length": 608.0, "epoch": 0.3401423913766718, "frac_reward_zero_std": 0.375, "grad_norm": 0.535800576210022, "learning_rate": 4.2e-08, "loss": 0.0255, "num_tokens": 386934783.0, "reward": 0.5390625, "reward_std": 0.28527307510375977, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1917 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1329.6875, "completions/mean_terminated_length": 1100.1236572265625, "completions/min_length": 558.0, "completions/min_terminated_length": 558.0, "epoch": 0.34031982611395745, "frac_reward_zero_std": 0.25, "grad_norm": 0.6228834986686707, "learning_rate": 4.15e-08, "loss": 0.0252, "num_tokens": 387116471.0, "reward": 0.5859375, "reward_std": 0.32043421268463135, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1918 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2027.0, "completions/mean_length": 1330.1796875, "completions/mean_terminated_length": 1060.0322265625, "completions/min_length": 500.0, "completions/min_terminated_length": 500.0, "epoch": 0.34049726085124316, "frac_reward_zero_std": 0.25, "grad_norm": 0.5756497383117676, "learning_rate": 4.1e-08, "loss": 0.0067, "num_tokens": 387298222.0, "reward": 0.5390625, "reward_std": 0.27398645877838135, "rewards/simpleverify_reward/mean": 0.5390625, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1919 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1334.8828125, "completions/mean_terminated_length": 1010.7386474609375, "completions/min_length": 615.0, "completions/min_terminated_length": 615.0, "epoch": 0.34067469558852886, "frac_reward_zero_std": 0.375, "grad_norm": 0.5467122793197632, "learning_rate": 4.05e-08, "loss": 0.0204, "num_tokens": 387480575.0, "reward": 0.515625, "reward_std": 0.23019562661647797, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1920 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1412.5234375, "completions/mean_terminated_length": 1102.1744384765625, "completions/min_length": 364.0, "completions/min_terminated_length": 364.0, "epoch": 0.3408521303258145, "frac_reward_zero_std": 0.375, "grad_norm": 0.4767427444458008, "learning_rate": 4e-08, "loss": 0.0036, "num_tokens": 387670274.0, "reward": 0.4609375, "reward_std": 0.231073796749115, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1921 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2890625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2046.0, "completions/mean_length": 1392.75, "completions/mean_terminated_length": 1126.3297119140625, "completions/min_length": 391.0, "completions/min_terminated_length": 391.0, "epoch": 0.3410295650631002, "frac_reward_zero_std": 0.375, "grad_norm": 0.6366061568260193, "learning_rate": 3.9499999999999996e-08, "loss": 0.0061, "num_tokens": 387857442.0, "reward": 0.4453125, "reward_std": 0.21808473765850067, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1922 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2008.0, "completions/mean_length": 1401.0, "completions/mean_terminated_length": 1106.9091796875, "completions/min_length": 372.0, "completions/min_terminated_length": 372.0, "epoch": 0.34120699980038594, "frac_reward_zero_std": 0.5, "grad_norm": 0.5471360683441162, "learning_rate": 3.9e-08, "loss": -0.0044, "num_tokens": 388045666.0, "reward": 0.453125, "reward_std": 0.17693254351615906, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1923 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1439.640625, "completions/mean_terminated_length": 1049.6666259765625, "completions/min_length": 393.0, "completions/min_terminated_length": 393.0, "epoch": 0.3413844345376716, "frac_reward_zero_std": 0.375, "grad_norm": 0.5794419646263123, "learning_rate": 3.85e-08, "loss": 0.0111, "num_tokens": 388238836.0, "reward": 0.4296875, "reward_std": 0.20099535584449768, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1924 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1984.0, "completions/mean_length": 1177.7890625, "completions/mean_terminated_length": 1035.390869140625, "completions/min_length": 536.0, "completions/min_terminated_length": 536.0, "epoch": 0.3415618692749573, "frac_reward_zero_std": 0.125, "grad_norm": 0.796055257320404, "learning_rate": 3.7999999999999996e-08, "loss": 0.0271, "num_tokens": 388399497.0, "reward": 0.578125, "reward_std": 0.34404873847961426, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1925 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2016.0, "completions/mean_length": 1207.3203125, "completions/mean_terminated_length": 1078.567626953125, "completions/min_length": 489.0, "completions/min_terminated_length": 489.0, "epoch": 0.341739304012243, "frac_reward_zero_std": 0.125, "grad_norm": 0.8305366635322571, "learning_rate": 3.75e-08, "loss": 0.0269, "num_tokens": 388563938.0, "reward": 0.5703125, "reward_std": 0.35003596544265747, "rewards/simpleverify_reward/mean": 0.5703125, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1926 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1984.0, "completions/mean_length": 1198.625, "completions/mean_terminated_length": 1085.8760986328125, "completions/min_length": 497.0, "completions/min_terminated_length": 497.0, "epoch": 0.3419167387495287, "frac_reward_zero_std": 0.125, "grad_norm": 0.6577127575874329, "learning_rate": 3.6999999999999994e-08, "loss": 0.0108, "num_tokens": 388727266.0, "reward": 0.6015625, "reward_std": 0.368827760219574, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1927 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.15625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1207.7109375, "completions/mean_terminated_length": 1052.101806640625, "completions/min_length": 485.0, "completions/min_terminated_length": 485.0, "epoch": 0.34209417348681437, "frac_reward_zero_std": 0.125, "grad_norm": 0.7692504525184631, "learning_rate": 3.6499999999999996e-08, "loss": 0.0081, "num_tokens": 388891757.0, "reward": 0.6015625, "reward_std": 0.36382144689559937, "rewards/simpleverify_reward/mean": 0.6015625, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1928 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2012.0, "completions/mean_length": 1241.921875, "completions/mean_terminated_length": 1142.9298095703125, "completions/min_length": 512.0, "completions/min_terminated_length": 512.0, "epoch": 0.3422716082241001, "frac_reward_zero_std": 0.125, "grad_norm": 0.629965603351593, "learning_rate": 3.6e-08, "loss": -0.0135, "num_tokens": 389061027.0, "reward": 0.4609375, "reward_std": 0.3292228579521179, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1929 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1296.3515625, "completions/mean_terminated_length": 1188.9732666015625, "completions/min_length": 513.0, "completions/min_terminated_length": 513.0, "epoch": 0.3424490429613858, "frac_reward_zero_std": 0.25, "grad_norm": 0.6086907386779785, "learning_rate": 3.5499999999999994e-08, "loss": -0.02, "num_tokens": 389237264.0, "reward": 0.4765625, "reward_std": 0.29905858635902405, "rewards/simpleverify_reward/mean": 0.4765625, "rewards/simpleverify_reward/std": 0.5014128684997559, "step": 1930 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1986.0, "completions/mean_length": 1283.09375, "completions/mean_terminated_length": 1115.5428466796875, "completions/min_length": 514.0, "completions/min_terminated_length": 514.0, "epoch": 0.34262647769867144, "frac_reward_zero_std": 0.125, "grad_norm": 0.6849652528762817, "learning_rate": 3.5e-08, "loss": -0.0095, "num_tokens": 389411804.0, "reward": 0.4453125, "reward_std": 0.3593776822090149, "rewards/simpleverify_reward/mean": 0.4453125, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1931 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2045.0, "completions/mean_length": 1259.3203125, "completions/mean_terminated_length": 1146.65185546875, "completions/min_length": 530.0, "completions/min_terminated_length": 530.0, "epoch": 0.34280391243595715, "frac_reward_zero_std": 0.125, "grad_norm": 0.6932358741760254, "learning_rate": 3.4500000000000005e-08, "loss": -0.0158, "num_tokens": 389583301.0, "reward": 0.515625, "reward_std": 0.3479320704936981, "rewards/simpleverify_reward/mean": 0.515625, "rewards/simpleverify_reward/std": 0.5017194747924805, "step": 1932 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 1813.0, "completions/mean_length": 1198.015625, "completions/mean_terminated_length": 914.6875, "completions/min_length": 319.0, "completions/min_terminated_length": 319.0, "epoch": 0.34298134717324286, "frac_reward_zero_std": 0.5, "grad_norm": 0.5176469683647156, "learning_rate": 3.4e-08, "loss": 0.0032, "num_tokens": 389747575.0, "reward": 0.6953125, "reward_std": 0.17254295945167542, "rewards/simpleverify_reward/mean": 0.6953125, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 1933 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2019.0, "completions/mean_length": 1165.6796875, "completions/mean_terminated_length": 907.2222290039062, "completions/min_length": 313.0, "completions/min_terminated_length": 313.0, "epoch": 0.3431587819105285, "frac_reward_zero_std": 0.625, "grad_norm": 0.41512778401374817, "learning_rate": 3.35e-08, "loss": 0.0089, "num_tokens": 389907710.0, "reward": 0.734375, "reward_std": 0.1375408172607422, "rewards/simpleverify_reward/mean": 0.734375, "rewards/simpleverify_reward/std": 0.44340085983276367, "step": 1934 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2109375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1923.0, "completions/mean_length": 1152.7109375, "completions/mean_terminated_length": 913.376220703125, "completions/min_length": 293.0, "completions/min_terminated_length": 293.0, "epoch": 0.3433362166478142, "frac_reward_zero_std": 0.5, "grad_norm": 0.558982789516449, "learning_rate": 3.3e-08, "loss": 0.0009, "num_tokens": 390066185.0, "reward": 0.71875, "reward_std": 0.18241733312606812, "rewards/simpleverify_reward/mean": 0.71875, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 1935 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1907.0, "completions/mean_length": 1191.3125, "completions/mean_terminated_length": 929.0612182617188, "completions/min_length": 303.0, "completions/min_terminated_length": 303.0, "epoch": 0.3435136513850999, "frac_reward_zero_std": 0.625, "grad_norm": 0.45571938157081604, "learning_rate": 3.25e-08, "loss": 0.0066, "num_tokens": 390229601.0, "reward": 0.703125, "reward_std": 0.1379890739917755, "rewards/simpleverify_reward/mean": 0.703125, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 1936 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2022.0, "completions/mean_length": 1273.953125, "completions/mean_terminated_length": 1095.326904296875, "completions/min_length": 435.0, "completions/min_terminated_length": 435.0, "epoch": 0.34369108612238564, "frac_reward_zero_std": 0.125, "grad_norm": 0.7422348260879517, "learning_rate": 3.2e-08, "loss": 0.0151, "num_tokens": 390405547.0, "reward": 0.6328125, "reward_std": 0.3552773594856262, "rewards/simpleverify_reward/mean": 0.6328125, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1937 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2003.0, "completions/mean_length": 1273.9375, "completions/mean_terminated_length": 1095.3077392578125, "completions/min_length": 415.0, "completions/min_terminated_length": 415.0, "epoch": 0.3438685208596713, "frac_reward_zero_std": 0.125, "grad_norm": 0.7524957656860352, "learning_rate": 3.15e-08, "loss": 0.0052, "num_tokens": 390581491.0, "reward": 0.59375, "reward_std": 0.34479135274887085, "rewards/simpleverify_reward/mean": 0.59375, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1938 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1289.453125, "completions/mean_terminated_length": 1077.0599365234375, "completions/min_length": 439.0, "completions/min_terminated_length": 439.0, "epoch": 0.344045955596957, "frac_reward_zero_std": 0.375, "grad_norm": 0.6606844663619995, "learning_rate": 3.1e-08, "loss": 0.0045, "num_tokens": 390759421.0, "reward": 0.6171875, "reward_std": 0.2508781850337982, "rewards/simpleverify_reward/mean": 0.6171875, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1939 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1273.046875, "completions/mean_terminated_length": 1112.20751953125, "completions/min_length": 444.0, "completions/min_terminated_length": 444.0, "epoch": 0.3442233903342427, "frac_reward_zero_std": 0.125, "grad_norm": 0.6956670880317688, "learning_rate": 3.0499999999999995e-08, "loss": 0.024, "num_tokens": 390935251.0, "reward": 0.5703125, "reward_std": 0.3604412078857422, "rewards/simpleverify_reward/mean": 0.5703125, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1940 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1257.484375, "completions/mean_terminated_length": 1065.6116943359375, "completions/min_length": 434.0, "completions/min_terminated_length": 434.0, "epoch": 0.34440082507152836, "frac_reward_zero_std": 0.25, "grad_norm": 0.6983596086502075, "learning_rate": 3e-08, "loss": 0.0443, "num_tokens": 391108353.0, "reward": 0.5546875, "reward_std": 0.29642558097839355, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1941 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1246.7265625, "completions/mean_terminated_length": 1052.24267578125, "completions/min_length": 460.0, "completions/min_terminated_length": 460.0, "epoch": 0.34457825980881407, "frac_reward_zero_std": 0.375, "grad_norm": 0.5987433791160583, "learning_rate": 2.9499999999999996e-08, "loss": 0.0395, "num_tokens": 391280078.0, "reward": 0.578125, "reward_std": 0.21542394161224365, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1942 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.25, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1288.9609375, "completions/mean_terminated_length": 1035.947998046875, "completions/min_length": 451.0, "completions/min_terminated_length": 451.0, "epoch": 0.3447556945460998, "frac_reward_zero_std": 0.375, "grad_norm": 0.4820862412452698, "learning_rate": 2.9e-08, "loss": 0.0336, "num_tokens": 391457209.0, "reward": 0.53125, "reward_std": 0.2352283000946045, "rewards/simpleverify_reward/mean": 0.53125, "rewards/simpleverify_reward/std": 0.5009832978248596, "step": 1943 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1993.0, "completions/mean_length": 1266.7265625, "completions/mean_terminated_length": 1067.5784912109375, "completions/min_length": 408.0, "completions/min_terminated_length": 408.0, "epoch": 0.34493312928338543, "frac_reward_zero_std": 0.375, "grad_norm": 0.6117426753044128, "learning_rate": 2.85e-08, "loss": 0.0293, "num_tokens": 391631494.0, "reward": 0.5546875, "reward_std": 0.2333405315876007, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1944 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.578125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1747.9609375, "completions/mean_terminated_length": 1336.7962646484375, "completions/min_length": 626.0, "completions/min_terminated_length": 626.0, "epoch": 0.34511056402067114, "frac_reward_zero_std": 0.625, "grad_norm": 0.37476012110710144, "learning_rate": 2.8e-08, "loss": 0.0183, "num_tokens": 391871489.0, "reward": 0.375, "reward_std": 0.15984316170215607, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 1945 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1764.84375, "completions/mean_terminated_length": 1337.3333740234375, "completions/min_length": 660.0, "completions/min_terminated_length": 660.0, "epoch": 0.34528799875795685, "frac_reward_zero_std": 0.375, "grad_norm": 0.48514458537101746, "learning_rate": 2.7499999999999998e-08, "loss": 0.0242, "num_tokens": 392113645.0, "reward": 0.3203125, "reward_std": 0.21148642897605896, "rewards/simpleverify_reward/mean": 0.3203125, "rewards/simpleverify_reward/std": 0.4684300124645233, "step": 1946 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1730.6328125, "completions/mean_terminated_length": 1382.049072265625, "completions/min_length": 699.0, "completions/min_terminated_length": 699.0, "epoch": 0.34546543349524256, "frac_reward_zero_std": 0.25, "grad_norm": 0.4982852041721344, "learning_rate": 2.6999999999999997e-08, "loss": 0.0253, "num_tokens": 392351422.0, "reward": 0.390625, "reward_std": 0.2785891890525818, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1947 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5546875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2019.0, "completions/mean_length": 1721.5, "completions/mean_terminated_length": 1314.8070068359375, "completions/min_length": 566.0, "completions/min_terminated_length": 566.0, "epoch": 0.3456428682325282, "frac_reward_zero_std": 0.5, "grad_norm": 0.3777994215488434, "learning_rate": 2.65e-08, "loss": 0.0159, "num_tokens": 392588030.0, "reward": 0.375, "reward_std": 0.18954971432685852, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 1948 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2032.0, "completions/mean_length": 1157.4296875, "completions/mean_terminated_length": 1073.700927734375, "completions/min_length": 291.0, "completions/min_terminated_length": 291.0, "epoch": 0.3458203029698139, "frac_reward_zero_std": 0.25, "grad_norm": 0.5941503047943115, "learning_rate": 2.5999999999999998e-08, "loss": 0.0329, "num_tokens": 392747205.0, "reward": 0.3671875, "reward_std": 0.3195338547229767, "rewards/simpleverify_reward/mean": 0.3671875, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1949 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1945.0, "completions/mean_length": 1102.2421875, "completions/mean_terminated_length": 1055.7294921875, "completions/min_length": 282.0, "completions/min_terminated_length": 282.0, "epoch": 0.34599773770709963, "frac_reward_zero_std": 0.5, "grad_norm": 0.5038989782333374, "learning_rate": 2.5499999999999997e-08, "loss": 0.0185, "num_tokens": 392899316.0, "reward": 0.375, "reward_std": 0.2000408172607422, "rewards/simpleverify_reward/mean": 0.375, "rewards/simpleverify_reward/std": 0.4860251843929291, "step": 1950 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2014.0, "completions/mean_length": 1182.8984375, "completions/mean_terminated_length": 1085.104248046875, "completions/min_length": 303.0, "completions/min_terminated_length": 303.0, "epoch": 0.3461751724443853, "frac_reward_zero_std": 0.25, "grad_norm": 0.6003223657608032, "learning_rate": 2.5e-08, "loss": 0.0281, "num_tokens": 393061751.0, "reward": 0.3671875, "reward_std": 0.31750667095184326, "rewards/simpleverify_reward/mean": 0.3671875, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1951 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.046875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1072.921875, "completions/mean_terminated_length": 1024.9671630859375, "completions/min_length": 302.0, "completions/min_terminated_length": 302.0, "epoch": 0.346352607181671, "frac_reward_zero_std": 0.125, "grad_norm": 0.7447670698165894, "learning_rate": 2.45e-08, "loss": 0.0192, "num_tokens": 393210109.0, "reward": 0.3984375, "reward_std": 0.31337815523147583, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1952 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2039.0, "completions/mean_length": 1436.0234375, "completions/mean_terminated_length": 1280.0294189453125, "completions/min_length": 353.0, "completions/min_terminated_length": 353.0, "epoch": 0.3465300419189567, "frac_reward_zero_std": 0.25, "grad_norm": 0.5469094514846802, "learning_rate": 2.4e-08, "loss": 0.0097, "num_tokens": 393407056.0, "reward": 0.3984375, "reward_std": 0.30917394161224365, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1953 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2036.0, "completions/mean_length": 1459.609375, "completions/mean_terminated_length": 1323.8270263671875, "completions/min_length": 347.0, "completions/min_terminated_length": 347.0, "epoch": 0.34670747665624235, "frac_reward_zero_std": 0.25, "grad_norm": 0.575575053691864, "learning_rate": 2.35e-08, "loss": 0.0075, "num_tokens": 393607022.0, "reward": 0.4296875, "reward_std": 0.3303627669811249, "rewards/simpleverify_reward/mean": 0.4296875, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1954 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.21875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2016.0, "completions/mean_length": 1448.34375, "completions/mean_terminated_length": 1280.43994140625, "completions/min_length": 341.0, "completions/min_terminated_length": 341.0, "epoch": 0.34688491139352806, "frac_reward_zero_std": 0.25, "grad_norm": 0.49505555629730225, "learning_rate": 2.2999999999999998e-08, "loss": -0.0005, "num_tokens": 393805546.0, "reward": 0.4140625, "reward_std": 0.2909446358680725, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1955 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1796875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1439.5546875, "completions/mean_terminated_length": 1306.2762451171875, "completions/min_length": 358.0, "completions/min_terminated_length": 358.0, "epoch": 0.34706234613081377, "frac_reward_zero_std": 0.25, "grad_norm": 0.523328423500061, "learning_rate": 2.25e-08, "loss": 0.0214, "num_tokens": 394002945.0, "reward": 0.40625, "reward_std": 0.2963978052139282, "rewards/simpleverify_reward/mean": 0.40625, "rewards/simpleverify_reward/std": 0.4930621087551117, "step": 1956 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2048.0, "completions/mean_length": 1789.1171875, "completions/mean_terminated_length": 1398.2550048828125, "completions/min_length": 861.0, "completions/min_terminated_length": 861.0, "epoch": 0.3472397808680995, "frac_reward_zero_std": 0.375, "grad_norm": 0.4781237244606018, "learning_rate": 2.2e-08, "loss": 0.032, "num_tokens": 394250016.0, "reward": 0.1640625, "reward_std": 0.25591087341308594, "rewards/simpleverify_reward/mean": 0.1640625, "rewards/simpleverify_reward/std": 0.371787428855896, "step": 1957 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5546875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1750.3203125, "completions/mean_terminated_length": 1379.5263671875, "completions/min_length": 869.0, "completions/min_terminated_length": 869.0, "epoch": 0.34741721560538513, "frac_reward_zero_std": 0.5, "grad_norm": 0.6083716154098511, "learning_rate": 2.1499999999999997e-08, "loss": 0.0061, "num_tokens": 394492121.0, "reward": 0.140625, "reward_std": 0.18968652188777924, "rewards/simpleverify_reward/mean": 0.140625, "rewards/simpleverify_reward/std": 0.3490002751350403, "step": 1958 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2037.0, "completions/mean_length": 1755.1171875, "completions/mean_terminated_length": 1312.921630859375, "completions/min_length": 899.0, "completions/min_terminated_length": 899.0, "epoch": 0.34759465034267084, "frac_reward_zero_std": 0.5, "grad_norm": 0.4063025116920471, "learning_rate": 2.1e-08, "loss": 0.0227, "num_tokens": 394734840.0, "reward": 0.1640625, "reward_std": 0.15558473765850067, "rewards/simpleverify_reward/mean": 0.1640625, "rewards/simpleverify_reward/std": 0.371787428855896, "step": 1959 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.59375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1996.0, "completions/mean_length": 1766.203125, "completions/mean_terminated_length": 1354.34619140625, "completions/min_length": 854.0, "completions/min_terminated_length": 854.0, "epoch": 0.34777208507995655, "frac_reward_zero_std": 0.5, "grad_norm": 0.46952202916145325, "learning_rate": 2.05e-08, "loss": 0.0471, "num_tokens": 394978978.0, "reward": 0.1328125, "reward_std": 0.2060280293226242, "rewards/simpleverify_reward/mean": 0.1328125, "rewards/simpleverify_reward/std": 0.3407054841518402, "step": 1960 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2020.0, "completions/mean_length": 1503.71875, "completions/mean_terminated_length": 905.901611328125, "completions/min_length": 440.0, "completions/min_terminated_length": 440.0, "epoch": 0.3479495198172422, "frac_reward_zero_std": 0.625, "grad_norm": 0.41465359926223755, "learning_rate": 2e-08, "loss": 0.0078, "num_tokens": 395184782.0, "reward": 0.4375, "reward_std": 0.15712818503379822, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1961 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.546875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2047.0, "completions/mean_length": 1530.5625, "completions/mean_terminated_length": 906.0689697265625, "completions/min_length": 399.0, "completions/min_terminated_length": 399.0, "epoch": 0.3481269545545279, "frac_reward_zero_std": 0.75, "grad_norm": 0.3469390571117401, "learning_rate": 1.95e-08, "loss": 0.0006, "num_tokens": 395394022.0, "reward": 0.3984375, "reward_std": 0.08715169876813889, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1962 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.46875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2025.0, "completions/mean_length": 1483.0859375, "completions/mean_terminated_length": 984.6323852539062, "completions/min_length": 431.0, "completions/min_terminated_length": 431.0, "epoch": 0.3483043892918136, "frac_reward_zero_std": 0.625, "grad_norm": 0.4725486934185028, "learning_rate": 1.8999999999999998e-08, "loss": 0.0064, "num_tokens": 395597185.0, "reward": 0.4921875, "reward_std": 0.14305339753627777, "rewards/simpleverify_reward/mean": 0.4921875, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1963 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.546875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1912.0, "completions/mean_length": 1529.5625, "completions/mean_terminated_length": 903.862060546875, "completions/min_length": 471.0, "completions/min_terminated_length": 471.0, "epoch": 0.3484818240290993, "frac_reward_zero_std": 0.75, "grad_norm": 0.2877945303916931, "learning_rate": 1.8499999999999997e-08, "loss": 0.009, "num_tokens": 395806297.0, "reward": 0.453125, "reward_std": 0.09529343992471695, "rewards/simpleverify_reward/mean": 0.453125, "rewards/simpleverify_reward/std": 0.4997538626194, "step": 1964 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2009.0, "completions/mean_length": 1250.984375, "completions/mean_terminated_length": 818.867431640625, "completions/min_length": 256.0, "completions/min_terminated_length": 256.0, "epoch": 0.348659258766385, "frac_reward_zero_std": 0.375, "grad_norm": 0.5866318941116333, "learning_rate": 1.8e-08, "loss": -0.0008, "num_tokens": 395982103.0, "reward": 0.421875, "reward_std": 0.22511295974254608, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1965 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1650.0, "completions/mean_length": 1247.578125, "completions/mean_terminated_length": 783.1358032226562, "completions/min_length": 279.0, "completions/min_terminated_length": 279.0, "epoch": 0.3488366935036707, "frac_reward_zero_std": 0.5, "grad_norm": 0.5786519646644592, "learning_rate": 1.75e-08, "loss": 0.01, "num_tokens": 396157473.0, "reward": 0.4140625, "reward_std": 0.1868889182806015, "rewards/simpleverify_reward/mean": 0.4140625, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1966 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3671875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1617.0, "completions/mean_length": 1232.9609375, "completions/mean_terminated_length": 760.0370483398438, "completions/min_length": 296.0, "completions/min_terminated_length": 296.0, "epoch": 0.3490141282409564, "frac_reward_zero_std": 0.625, "grad_norm": 0.4387436807155609, "learning_rate": 1.7e-08, "loss": 0.0129, "num_tokens": 396330972.0, "reward": 0.3984375, "reward_std": 0.1414783000946045, "rewards/simpleverify_reward/mean": 0.3984375, "rewards/simpleverify_reward/std": 0.4915000796318054, "step": 1967 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1415.0, "completions/mean_length": 1240.796875, "completions/mean_terminated_length": 756.4750366210938, "completions/min_length": 272.0, "completions/min_terminated_length": 272.0, "epoch": 0.34919156297824205, "frac_reward_zero_std": 0.625, "grad_norm": 0.4676709771156311, "learning_rate": 1.65e-08, "loss": 0.0149, "num_tokens": 396505474.0, "reward": 0.390625, "reward_std": 0.1535891890525818, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1968 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.6015625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2009.0, "completions/mean_length": 1735.546875, "completions/mean_terminated_length": 1263.803955078125, "completions/min_length": 456.0, "completions/min_terminated_length": 456.0, "epoch": 0.34936899771552776, "frac_reward_zero_std": 0.375, "grad_norm": 0.4533047676086426, "learning_rate": 1.6e-08, "loss": 0.0191, "num_tokens": 396741352.0, "reward": 0.390625, "reward_std": 0.262323796749115, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1969 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1963.0, "completions/mean_length": 1681.046875, "completions/mean_terminated_length": 1251.8983154296875, "completions/min_length": 561.0, "completions/min_terminated_length": 561.0, "epoch": 0.34954643245281347, "frac_reward_zero_std": 0.5, "grad_norm": 0.4519512355327606, "learning_rate": 1.55e-08, "loss": 0.0192, "num_tokens": 396970254.0, "reward": 0.3828125, "reward_std": 0.2556428909301758, "rewards/simpleverify_reward/mean": 0.3828125, "rewards/simpleverify_reward/std": 0.4879830479621887, "step": 1970 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.515625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1669.9453125, "completions/mean_terminated_length": 1267.5, "completions/min_length": 502.0, "completions/min_terminated_length": 502.0, "epoch": 0.3497238671900991, "frac_reward_zero_std": 0.25, "grad_norm": 0.5518940687179565, "learning_rate": 1.5e-08, "loss": 0.0249, "num_tokens": 397197735.0, "reward": 0.4609375, "reward_std": 0.31407544016838074, "rewards/simpleverify_reward/mean": 0.4609375, "rewards/simpleverify_reward/std": 0.5004304051399231, "step": 1971 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.5859375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2006.0, "completions/mean_length": 1719.359375, "completions/mean_terminated_length": 1254.3018798828125, "completions/min_length": 485.0, "completions/min_terminated_length": 485.0, "epoch": 0.34990130192738483, "frac_reward_zero_std": 0.375, "grad_norm": 0.4673527181148529, "learning_rate": 1.45e-08, "loss": 0.0165, "num_tokens": 397431541.0, "reward": 0.296875, "reward_std": 0.24148225784301758, "rewards/simpleverify_reward/mean": 0.296875, "rewards/simpleverify_reward/std": 0.45867621898651123, "step": 1972 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2020.0, "completions/mean_length": 1104.8671875, "completions/mean_terminated_length": 1066.5284423828125, "completions/min_length": 330.0, "completions/min_terminated_length": 330.0, "epoch": 0.35007873666467054, "frac_reward_zero_std": 0.0, "grad_norm": 0.8222348093986511, "learning_rate": 1.4e-08, "loss": 0.0015, "num_tokens": 397585428.0, "reward": 0.5546875, "reward_std": 0.4351062774658203, "rewards/simpleverify_reward/mean": 0.5546875, "rewards/simpleverify_reward/std": 0.4989531338214874, "step": 1973 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0390625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1102.8828125, "completions/mean_terminated_length": 1064.46337890625, "completions/min_length": 324.0, "completions/min_terminated_length": 324.0, "epoch": 0.3502561714019562, "frac_reward_zero_std": 0.0, "grad_norm": 0.8188478350639343, "learning_rate": 1.3499999999999998e-08, "loss": 0.0231, "num_tokens": 397739061.0, "reward": 0.578125, "reward_std": 0.3857581913471222, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1974 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.0546875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1133.8515625, "completions/mean_terminated_length": 1080.9669189453125, "completions/min_length": 329.0, "completions/min_terminated_length": 329.0, "epoch": 0.3504336061392419, "frac_reward_zero_std": 0.0, "grad_norm": 0.8087294697761536, "learning_rate": 1.2999999999999999e-08, "loss": 0.0433, "num_tokens": 397896658.0, "reward": 0.609375, "reward_std": 0.43470776081085205, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1975 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.03125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1937.0, "completions/mean_length": 1107.03125, "completions/mean_terminated_length": 1076.6773681640625, "completions/min_length": 342.0, "completions/min_terminated_length": 342.0, "epoch": 0.3506110408765276, "frac_reward_zero_std": 0.125, "grad_norm": 0.6584596633911133, "learning_rate": 1.25e-08, "loss": -0.0106, "num_tokens": 398050822.0, "reward": 0.5859375, "reward_std": 0.356073796749115, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1976 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2042.0, "completions/mean_length": 1270.96875, "completions/mean_terminated_length": 1043.353515625, "completions/min_length": 562.0, "completions/min_terminated_length": 562.0, "epoch": 0.3507884756138133, "frac_reward_zero_std": 0.375, "grad_norm": 0.48491594195365906, "learning_rate": 1.2e-08, "loss": 0.0515, "num_tokens": 398226402.0, "reward": 0.609375, "reward_std": 0.24273642897605896, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1977 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2007.0, "completions/mean_length": 1286.6640625, "completions/mean_terminated_length": 1063.646484375, "completions/min_length": 545.0, "completions/min_terminated_length": 545.0, "epoch": 0.350965910351099, "frac_reward_zero_std": 0.25, "grad_norm": 0.5356215834617615, "learning_rate": 1.1499999999999999e-08, "loss": 0.0488, "num_tokens": 398403991.0, "reward": 0.578125, "reward_std": 0.2816799283027649, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1978 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2038.0, "completions/mean_length": 1263.3203125, "completions/mean_terminated_length": 1109.3177490234375, "completions/min_length": 581.0, "completions/min_terminated_length": 581.0, "epoch": 0.3511433450883847, "frac_reward_zero_std": 0.25, "grad_norm": 0.5896720290184021, "learning_rate": 1.1e-08, "loss": 0.0427, "num_tokens": 398578592.0, "reward": 0.6484375, "reward_std": 0.2603282630443573, "rewards/simpleverify_reward/mean": 0.6484375, "rewards/simpleverify_reward/std": 0.4793342351913452, "step": 1979 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2005.0, "completions/mean_length": 1286.0078125, "completions/mean_terminated_length": 1101.0582275390625, "completions/min_length": 587.0, "completions/min_terminated_length": 587.0, "epoch": 0.3513207798256704, "frac_reward_zero_std": 0.25, "grad_norm": 0.5601932406425476, "learning_rate": 1.05e-08, "loss": 0.0392, "num_tokens": 398756097.0, "reward": 0.6328125, "reward_std": 0.2504299283027649, "rewards/simpleverify_reward/mean": 0.6328125, "rewards/simpleverify_reward/std": 0.4839322865009308, "step": 1980 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1899.0, "completions/mean_length": 1191.484375, "completions/mean_terminated_length": 940.5858764648438, "completions/min_length": 484.0, "completions/min_terminated_length": 484.0, "epoch": 0.35149821456295605, "frac_reward_zero_std": 0.375, "grad_norm": 0.6141852736473083, "learning_rate": 1e-08, "loss": 0.0208, "num_tokens": 398920607.0, "reward": 0.5703125, "reward_std": 0.24165073037147522, "rewards/simpleverify_reward/mean": 0.5703125, "rewards/simpleverify_reward/std": 0.4969765841960907, "step": 1981 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1977.0, "completions/mean_length": 1197.9765625, "completions/mean_terminated_length": 937.7652587890625, "completions/min_length": 454.0, "completions/min_terminated_length": 454.0, "epoch": 0.35167564930024175, "frac_reward_zero_std": 0.5, "grad_norm": 0.4331953525543213, "learning_rate": 9.499999999999999e-09, "loss": 0.0077, "num_tokens": 399085948.0, "reward": 0.609375, "reward_std": 0.16703036427497864, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1982 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1953125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1179.46875, "completions/mean_terminated_length": 968.6602172851562, "completions/min_length": 497.0, "completions/min_terminated_length": 497.0, "epoch": 0.35185308403752746, "frac_reward_zero_std": 0.5, "grad_norm": 0.5827615857124329, "learning_rate": 9e-09, "loss": -0.0004, "num_tokens": 399248920.0, "reward": 0.609375, "reward_std": 0.2000408172607422, "rewards/simpleverify_reward/mean": 0.609375, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1983 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 1851.0, "completions/mean_length": 1203.078125, "completions/mean_terminated_length": 933.051513671875, "completions/min_length": 490.0, "completions/min_terminated_length": 490.0, "epoch": 0.3520305187748131, "frac_reward_zero_std": 0.375, "grad_norm": 0.5460608601570129, "learning_rate": 8.5e-09, "loss": 0.0221, "num_tokens": 399414914.0, "reward": 0.578125, "reward_std": 0.22511295974254608, "rewards/simpleverify_reward/mean": 0.578125, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1984 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1888.0, "completions/mean_length": 1258.6328125, "completions/mean_terminated_length": 1057.421630859375, "completions/min_length": 290.0, "completions/min_terminated_length": 290.0, "epoch": 0.3522079535120988, "frac_reward_zero_std": 0.5, "grad_norm": 0.4601600170135498, "learning_rate": 8e-09, "loss": 0.0192, "num_tokens": 399586675.0, "reward": 0.71875, "reward_std": 0.21497184038162231, "rewards/simpleverify_reward/mean": 0.71875, "rewards/simpleverify_reward/std": 0.4513758420944214, "step": 1985 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2421875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2029.0, "completions/mean_length": 1298.4140625, "completions/mean_terminated_length": 1058.8555908203125, "completions/min_length": 287.0, "completions/min_terminated_length": 287.0, "epoch": 0.35238538824938453, "frac_reward_zero_std": 0.25, "grad_norm": 0.5851021409034729, "learning_rate": 7.5e-09, "loss": 0.0198, "num_tokens": 399763528.0, "reward": 0.640625, "reward_std": 0.315596342086792, "rewards/simpleverify_reward/mean": 0.640625, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 1986 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.234375, "completions/max_length": 2048.0, "completions/max_terminated_length": 1972.0, "completions/mean_length": 1331.5703125, "completions/mean_terminated_length": 1112.255126953125, "completions/min_length": 304.0, "completions/min_terminated_length": 304.0, "epoch": 0.3525628229866702, "frac_reward_zero_std": 0.5, "grad_norm": 0.48594731092453003, "learning_rate": 7e-09, "loss": 0.0238, "num_tokens": 399944625.0, "reward": 0.6953125, "reward_std": 0.21148642897605896, "rewards/simpleverify_reward/mean": 0.6953125, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 1987 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1917.0, "completions/mean_length": 1288.0, "completions/mean_terminated_length": 1065.373779296875, "completions/min_length": 311.0, "completions/min_terminated_length": 311.0, "epoch": 0.3527402577239559, "frac_reward_zero_std": 0.5, "grad_norm": 0.4607448875904083, "learning_rate": 6.4999999999999995e-09, "loss": 0.0141, "num_tokens": 400120145.0, "reward": 0.6953125, "reward_std": 0.20158424973487854, "rewards/simpleverify_reward/mean": 0.6953125, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 1988 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1328125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2003.0, "completions/mean_length": 1316.78125, "completions/mean_terminated_length": 1204.7928466796875, "completions/min_length": 484.0, "completions/min_terminated_length": 484.0, "epoch": 0.3529176924612416, "frac_reward_zero_std": 0.5, "grad_norm": 0.48536795377731323, "learning_rate": 6e-09, "loss": 0.0089, "num_tokens": 400298821.0, "reward": 0.6640625, "reward_std": 0.20818254351615906, "rewards/simpleverify_reward/mean": 0.6640625, "rewards/simpleverify_reward/std": 0.47417303919792175, "step": 1989 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1966.0, "completions/mean_length": 1297.1796875, "completions/mean_terminated_length": 1174.318115234375, "completions/min_length": 488.0, "completions/min_terminated_length": 488.0, "epoch": 0.3530951271985273, "frac_reward_zero_std": 0.125, "grad_norm": 0.5960118770599365, "learning_rate": 5.5e-09, "loss": 0.0196, "num_tokens": 400474988.0, "reward": 0.65625, "reward_std": 0.29203036427497864, "rewards/simpleverify_reward/mean": 0.65625, "rewards/simpleverify_reward/std": 0.47682511806488037, "step": 1990 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2033.0, "completions/mean_length": 1272.0390625, "completions/mean_terminated_length": 1169.035400390625, "completions/min_length": 468.0, "completions/min_terminated_length": 468.0, "epoch": 0.35327256193581297, "frac_reward_zero_std": 0.5, "grad_norm": 0.3778776526451111, "learning_rate": 5e-09, "loss": -0.0034, "num_tokens": 400647937.0, "reward": 0.6953125, "reward_std": 0.1692390739917755, "rewards/simpleverify_reward/mean": 0.6953125, "rewards/simpleverify_reward/std": 0.46208351850509644, "step": 1991 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.140625, "completions/max_length": 2048.0, "completions/max_terminated_length": 1980.0, "completions/mean_length": 1273.203125, "completions/mean_terminated_length": 1146.4180908203125, "completions/min_length": 483.0, "completions/min_terminated_length": 483.0, "epoch": 0.3534499966730987, "frac_reward_zero_std": 0.125, "grad_norm": 0.6797174215316772, "learning_rate": 4.5e-09, "loss": 0.0272, "num_tokens": 400821035.0, "reward": 0.5859375, "reward_std": 0.3259190022945404, "rewards/simpleverify_reward/mean": 0.5859375, "rewards/simpleverify_reward/std": 0.49449479579925537, "step": 1992 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.28125, "completions/max_length": 2048.0, "completions/max_terminated_length": 2017.0, "completions/mean_length": 1520.5078125, "completions/mean_terminated_length": 1314.097900390625, "completions/min_length": 697.0, "completions/min_terminated_length": 697.0, "epoch": 0.3536274314103844, "frac_reward_zero_std": 0.25, "grad_norm": 0.6136237382888794, "learning_rate": 4e-09, "loss": -0.0007, "num_tokens": 401026588.0, "reward": 0.421875, "reward_std": 0.3375816345214844, "rewards/simpleverify_reward/mean": 0.421875, "rewards/simpleverify_reward/std": 0.4957992732524872, "step": 1993 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.265625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2044.0, "completions/mean_length": 1555.7109375, "completions/mean_terminated_length": 1377.64892578125, "completions/min_length": 630.0, "completions/min_terminated_length": 630.0, "epoch": 0.35380486614767004, "frac_reward_zero_std": 0.25, "grad_norm": 0.6325065493583679, "learning_rate": 3.5e-09, "loss": 0.0301, "num_tokens": 401236647.0, "reward": 0.4375, "reward_std": 0.3285759389400482, "rewards/simpleverify_reward/mean": 0.4375, "rewards/simpleverify_reward/std": 0.49802759289741516, "step": 1994 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.3203125, "completions/max_length": 2048.0, "completions/max_terminated_length": 1981.0, "completions/mean_length": 1536.1328125, "completions/mean_terminated_length": 1294.9080810546875, "completions/min_length": 691.0, "completions/min_terminated_length": 691.0, "epoch": 0.35398230088495575, "frac_reward_zero_std": 0.25, "grad_norm": 0.5843533277511597, "learning_rate": 3e-09, "loss": -0.0178, "num_tokens": 401444200.0, "reward": 0.359375, "reward_std": 0.3364642560482025, "rewards/simpleverify_reward/mean": 0.359375, "rewards/simpleverify_reward/std": 0.481702595949173, "step": 1995 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.2734375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2026.0, "completions/mean_length": 1572.8515625, "completions/mean_terminated_length": 1394.0322265625, "completions/min_length": 728.0, "completions/min_terminated_length": 728.0, "epoch": 0.35415973562224146, "frac_reward_zero_std": 0.25, "grad_norm": 0.642387866973877, "learning_rate": 2.5e-09, "loss": -0.0034, "num_tokens": 401656453.0, "reward": 0.390625, "reward_std": 0.337577760219574, "rewards/simpleverify_reward/mean": 0.390625, "rewards/simpleverify_reward/std": 0.4898075461387634, "step": 1996 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2023.0, "completions/mean_length": 1311.8046875, "completions/mean_terminated_length": 1167.3177490234375, "completions/min_length": 434.0, "completions/min_terminated_length": 434.0, "epoch": 0.3543371703595271, "frac_reward_zero_std": 0.375, "grad_norm": 0.5222218632698059, "learning_rate": 2e-09, "loss": 0.0458, "num_tokens": 401833484.0, "reward": 0.5078125, "reward_std": 0.24052388966083527, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1997 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1640625, "completions/max_length": 2048.0, "completions/max_terminated_length": 2028.0, "completions/mean_length": 1305.703125, "completions/mean_terminated_length": 1160.0186767578125, "completions/min_length": 457.0, "completions/min_terminated_length": 457.0, "epoch": 0.3545146050968128, "frac_reward_zero_std": 0.5, "grad_norm": 0.42975109815597534, "learning_rate": 1.5e-09, "loss": 0.0145, "num_tokens": 402009734.0, "reward": 0.5078125, "reward_std": 0.2251407653093338, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1998 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.1484375, "completions/max_length": 2048.0, "completions/max_terminated_length": 2000.0, "completions/mean_length": 1290.9296875, "completions/mean_terminated_length": 1158.9632568359375, "completions/min_length": 477.0, "completions/min_terminated_length": 477.0, "epoch": 0.3546920398340985, "frac_reward_zero_std": 0.375, "grad_norm": 0.47858738899230957, "learning_rate": 1e-09, "loss": 0.0122, "num_tokens": 402184093.0, "reward": 0.5078125, "reward_std": 0.268528014421463, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 1999 }, { "clip_ratio/high_max": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/region_mean": 0.0, "completions/clipped_ratio": 0.171875, "completions/max_length": 2048.0, "completions/max_terminated_length": 2040.0, "completions/mean_length": 1307.109375, "completions/mean_terminated_length": 1153.339599609375, "completions/min_length": 452.0, "completions/min_terminated_length": 452.0, "epoch": 0.35486947457138424, "frac_reward_zero_std": 0.5, "grad_norm": 0.4051937758922577, "learning_rate": 5e-10, "loss": 0.0015, "num_tokens": 402360523.0, "reward": 0.5078125, "reward_std": 0.2427906095981598, "rewards/simpleverify_reward/mean": 0.5078125, "rewards/simpleverify_reward/std": 0.5019033551216125, "step": 2000 }, { "epoch": 0.35486947457138424, "step": 2000, "total_flos": 0.0, "train_loss": 0.011338358580396744, "train_runtime": 25427.0604, "train_samples_per_second": 10.068, "train_steps_per_second": 0.079 } ], "logging_steps": 1, "max_steps": 2000, "num_input_tokens_seen": 402360523, "num_train_epochs": 1, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }