[ { "step": 1, "loss": 0.2423, "grad_norm": 0.24541568756103516, "learning_rate": 0.0, "num_tokens": 5422.0, "completions/mean_length": 1243.5, "completions/min_length": 1019.0, "completions/max_length": 1846.0, "completions/clipped_ratio": 0.25, "completions/mean_terminated_length": 1042.666748046875, "completions/min_terminated_length": 1019.0, "completions/max_terminated_length": 1089.0, "rewards/match_format_exactly/mean": 2.25, "rewards/match_format_exactly/std": 1.5, "rewards/match_format_approximately/mean": 0.75, "rewards/match_format_approximately/std": 1.5, "rewards/check_answer/mean": -2.375, "rewards/check_answer/std": 0.25, "rewards/check_numbers/mean": -1.5, "rewards/check_numbers/std": 0.0, "reward": -0.875, "reward_std": 2.75, "frac_reward_zero_std": 0.0, "completion_length": 1243.5, "kl": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/high_max": 0.0, "clip_ratio/region_mean": 0.0, "epoch": 7.868439688409789e-05, "time_ms": 60626.65366800502, "memory_mb": 162696.66357421875, "memory_gb": 158.883460521698 }, { "step": 2, "loss": 0.1559, "grad_norm": 0.7674608826637268, "learning_rate": 5e-06, "num_tokens": 7690.0, "completions/mean_length": 478.0, "completions/min_length": 329.0, "completions/max_length": 553.0, "completions/clipped_ratio": 0.0, "completions/mean_terminated_length": 478.0, "completions/min_terminated_length": 329.0, "completions/max_terminated_length": 553.0, "rewards/match_format_exactly/mean": 0.75, "rewards/match_format_exactly/std": 1.5, "rewards/match_format_approximately/mean": -1.875, "rewards/match_format_approximately/std": 2.25, "rewards/check_answer/mean": -2.125, "rewards/check_answer/std": 0.25, "rewards/check_numbers/mean": -2.25, "rewards/check_numbers/std": 0.5, "reward": -5.5, "reward_std": 4.0, "frac_reward_zero_std": 0.0, "completion_length": 478.0, "kl": 0.0, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/high_max": 0.0, "clip_ratio/region_mean": 0.0, "epoch": 0.00015736879376819577, "time_ms": 3893.7715340289287, "memory_mb": 160786.34130859375, "memory_gb": 157.01791143417358 }, { "step": 3, "loss": -0.165, "grad_norm": 0.47987309098243713, "learning_rate": 4.444444444444444e-06, "num_tokens": 12437.0, "completions/mean_length": 1009.75, "completions/min_length": 745.0, "completions/max_length": 1319.0, "completions/clipped_ratio": 0.0, "completions/mean_terminated_length": 1009.75, "completions/min_terminated_length": 745.0, "completions/max_terminated_length": 1319.0, "rewards/match_format_exactly/mean": 2.25, "rewards/match_format_exactly/std": 1.5, "rewards/match_format_approximately/mean": 0.375, "rewards/match_format_approximately/std": 2.25, "rewards/check_answer/mean": -1.375, "rewards/check_answer/std": 1.9311050176620483, "rewards/check_numbers/mean": -1.75, "rewards/check_numbers/std": 0.5, "reward": -0.5, "reward_std": 5.0332231521606445, "frac_reward_zero_std": 0.0, "completion_length": 1009.75, "kl": 0.0038291513919830322, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/high_max": 0.0, "clip_ratio/region_mean": 0.0, "epoch": 0.00023605319065229366, "time_ms": 7929.127738985699, "memory_mb": 161959.54833984375, "memory_gb": 158.16362142562866 }, { "step": 4, "loss": 0.3177, "grad_norm": 0.37925368547439575, "learning_rate": 3.88888888888889e-06, "num_tokens": 17403.0, "completions/mean_length": 1076.5, "completions/min_length": 546.0, "completions/max_length": 1846.0, "completions/clipped_ratio": 0.25, "completions/mean_terminated_length": 820.0, "completions/min_terminated_length": 546.0, "completions/max_terminated_length": 1192.0, "rewards/match_format_exactly/mean": 0.75, "rewards/match_format_exactly/std": 1.5, "rewards/match_format_approximately/mean": -0.75, "rewards/match_format_approximately/std": 1.9364917278289795, "rewards/check_answer/mean": -2.125, "rewards/check_answer/std": 0.25, "rewards/check_numbers/mean": -2.0, "rewards/check_numbers/std": 0.5773502588272095, "reward": -4.125, "reward_std": 3.4970226287841797, "frac_reward_zero_std": 0.0, "completion_length": 1076.5, "kl": 0.005913741886615753, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/high_max": 0.0, "clip_ratio/region_mean": 0.0, "epoch": 0.00031473758753639155, "time_ms": 11084.477900003549, "memory_mb": 162749.5458984375, "memory_gb": 158.93510341644287 }, { "step": 5, "loss": -0.02, "grad_norm": 0.6089861989021301, "learning_rate": 3.3333333333333333e-06, "num_tokens": 19235.0, "completions/mean_length": 302.0, "completions/min_length": 256.0, "completions/max_length": 334.0, "completions/clipped_ratio": 0.0, "completions/mean_terminated_length": 302.0, "completions/min_terminated_length": 256.0, "completions/max_terminated_length": 334.0, "rewards/match_format_exactly/mean": 3.0, "rewards/match_format_exactly/std": 0.0, "rewards/match_format_approximately/mean": 1.5, "rewards/match_format_approximately/std": 0.0, "rewards/check_answer/mean": -1.125, "rewards/check_answer/std": 4.190763473510742, "rewards/check_numbers/mean": -0.25, "rewards/check_numbers/std": 2.5, "reward": 3.125, "reward_std": 6.650501251220703, "frac_reward_zero_std": 0.0, "completion_length": 302.0, "kl": 0.015983864665031433, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/high_max": 0.0, "clip_ratio/region_mean": 0.0, "epoch": 0.00039342198442048943, "time_ms": 2679.084858042188, "memory_mb": 160465.05859375, "memory_gb": 156.70415878295898 }, { "step": 6, "loss": 0.0, "grad_norm": 0.002889552852138877, "learning_rate": 2.7777777777777783e-06, "num_tokens": 26958.0, "completions/mean_length": 1833.75, "completions/min_length": 1797.0, "completions/max_length": 1846.0, "completions/clipped_ratio": 0.75, "completions/mean_terminated_length": 1797.0, "completions/min_terminated_length": 1797.0, "completions/max_terminated_length": 1797.0, "rewards/match_format_exactly/mean": 0.0, "rewards/match_format_exactly/std": 0.0, "rewards/match_format_approximately/mean": -3.0, "rewards/match_format_approximately/std": 0.0, "rewards/check_answer/mean": -2.0, "rewards/check_answer/std": 0.0, "rewards/check_numbers/mean": -2.5, "rewards/check_numbers/std": 0.0, "reward": -7.5, "reward_std": 0.0, "frac_reward_zero_std": 1.0, "completion_length": 1833.75, "kl": 0.003961368463933468, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/high_max": 0.0, "clip_ratio/region_mean": 0.0, "epoch": 0.0004721063813045873, "time_ms": 10652.5042289868, "memory_mb": 162744.833984375, "memory_gb": 158.9305019378662 }, { "step": 7, "loss": 0.0, "grad_norm": 0.003148352960124612, "learning_rate": 2.222222222222222e-06, "num_tokens": 29616.0, "completions/mean_length": 521.5, "completions/min_length": 452.0, "completions/max_length": 675.0, "completions/clipped_ratio": 0.0, "completions/mean_terminated_length": 521.5, "completions/min_terminated_length": 452.0, "completions/max_terminated_length": 675.0, "rewards/match_format_exactly/mean": 0.0, "rewards/match_format_exactly/std": 0.0, "rewards/match_format_approximately/mean": -3.0, "rewards/match_format_approximately/std": 0.0, "rewards/check_answer/mean": -2.0, "rewards/check_answer/std": 0.0, "rewards/check_numbers/mean": -2.5, "rewards/check_numbers/std": 0.0, "reward": -7.5, "reward_std": 0.0, "frac_reward_zero_std": 1.0, "completion_length": 521.5, "kl": 0.009647021070122719, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/high_max": 0.0, "clip_ratio/region_mean": 0.0, "epoch": 0.0005507907781886852, "time_ms": 4468.553012993652, "memory_mb": 160983.70361328125, "memory_gb": 157.21064805984497 }, { "step": 8, "loss": 0.0613, "grad_norm": 0.4861072301864624, "learning_rate": 1.6666666666666667e-06, "num_tokens": 32984.0, "completions/mean_length": 775.0, "completions/min_length": 671.0, "completions/max_length": 933.0, "completions/clipped_ratio": 0.0, "completions/mean_terminated_length": 775.0, "completions/min_terminated_length": 671.0, "completions/max_terminated_length": 933.0, "rewards/match_format_exactly/mean": 0.0, "rewards/match_format_exactly/std": 0.0, "rewards/match_format_approximately/mean": -2.25, "rewards/match_format_approximately/std": 1.5, "rewards/check_answer/mean": -2.0, "rewards/check_answer/std": 0.0, "rewards/check_numbers/mean": -2.25, "rewards/check_numbers/std": 0.5, "reward": -6.5, "reward_std": 2.0, "frac_reward_zero_std": 0.0, "completion_length": 775.0, "kl": 0.003189136739820242, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/high_max": 0.0, "clip_ratio/region_mean": 0.0, "epoch": 0.0006294751750727831, "time_ms": 5805.1959190052, "memory_mb": 161361.3447265625, "memory_gb": 157.5794382095337 }, { "step": 9, "loss": 0.006, "grad_norm": 0.5726504921913147, "learning_rate": 1.111111111111111e-06, "num_tokens": 35116.0, "completions/mean_length": 436.0, "completions/min_length": 237.0, "completions/max_length": 635.0, "completions/clipped_ratio": 0.0, "completions/mean_terminated_length": 436.0, "completions/min_terminated_length": 237.0, "completions/max_terminated_length": 635.0, "rewards/match_format_exactly/mean": 1.5, "rewards/match_format_exactly/std": 1.7320507764816284, "rewards/match_format_approximately/mean": 0.75, "rewards/match_format_approximately/std": 0.8660253882408142, "rewards/check_answer/mean": -1.25, "rewards/check_answer/std": 1.8484227657318115, "rewards/check_numbers/mean": -1.5, "rewards/check_numbers/std": 0.0, "reward": -0.5, "reward_std": 3.8297085762023926, "frac_reward_zero_std": 0.0, "completion_length": 436.0, "kl": 0.0023976736702024937, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/high_max": 0.0, "clip_ratio/region_mean": 0.0, "epoch": 0.0007081595719568809, "time_ms": 4304.089896031655, "memory_mb": 160920.1044921875, "memory_gb": 157.14853954315186 }, { "step": 10, "loss": 0.1582, "grad_norm": 0.3651980459690094, "learning_rate": 5.555555555555555e-07, "num_tokens": 39155.0, "completions/mean_length": 841.75, "completions/min_length": 729.0, "completions/max_length": 1108.0, "completions/clipped_ratio": 0.0, "completions/mean_terminated_length": 841.75, "completions/min_terminated_length": 729.0, "completions/max_terminated_length": 1108.0, "rewards/match_format_exactly/mean": 2.25, "rewards/match_format_exactly/std": 1.5, "rewards/match_format_approximately/mean": 0.375, "rewards/match_format_approximately/std": 2.25, "rewards/check_answer/mean": -2.375, "rewards/check_answer/std": 0.25, "rewards/check_numbers/mean": -1.75, "rewards/check_numbers/std": 0.5, "reward": -1.5, "reward_std": 4.0, "frac_reward_zero_std": 0.0, "completion_length": 841.75, "kl": 0.00485160993412137, "clip_ratio/low_mean": 0.0, "clip_ratio/low_min": 0.0, "clip_ratio/high_mean": 0.0, "clip_ratio/high_max": 0.0, "clip_ratio/region_mean": 0.0, "epoch": 0.0007868439688409789, "time_ms": 6777.490795007907, "memory_mb": 161641.44970703125, "memory_gb": 157.8529782295227 } ]