{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 10,
  "global_step": 965,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 426.8250160217285,
      "epoch": 0.0010368066355624676,
      "grad_norm": 14.147396087646484,
      "kl": 0.0,
      "learning_rate": 1.0344827586206896e-08,
      "loss": 0.1143,
      "reward": 0.30000000447034836,
      "reward_std": 0.353316530585289,
      "rewards/accuracy_reward": 0.22500000894069672,
      "rewards/format_reward": 0.07500000111758709,
      "step": 1
    },
    {
      "completion_length": 345.9749946594238,
      "epoch": 0.002073613271124935,
      "grad_norm": 0.5298608541488647,
      "kl": 0.0,
      "learning_rate": 2.0689655172413793e-08,
      "loss": 0.0471,
      "reward": 0.3000000026077032,
      "reward_std": 0.34968600049614906,
      "rewards/accuracy_reward": 0.27500000409781933,
      "rewards/format_reward": 0.02500000037252903,
      "step": 2
    },
    {
      "completion_length": 321.2000045776367,
      "epoch": 0.003110419906687403,
      "grad_norm": 3.317950487136841,
      "kl": 0.00021088123321533203,
      "learning_rate": 3.103448275862069e-08,
      "loss": 0.0899,
      "reward": 0.4750000014901161,
      "reward_std": 0.42900275811553,
      "rewards/accuracy_reward": 0.45000001043081284,
      "rewards/format_reward": 0.02500000037252903,
      "step": 3
    },
    {
      "completion_length": 283.5250053405762,
      "epoch": 0.00414722654224987,
      "grad_norm": 0.7831366062164307,
      "kl": 0.0001735687255859375,
      "learning_rate": 4.1379310344827585e-08,
      "loss": -0.0534,
      "reward": 0.5250000096857548,
      "reward_std": 0.4415663778781891,
      "rewards/accuracy_reward": 0.5250000096857548,
      "rewards/format_reward": 0.0,
      "step": 4
    },
    {
      "completion_length": 311.0750045776367,
      "epoch": 0.005184033177812338,
      "grad_norm": 0.6258169412612915,
      "kl": 0.00017344951629638672,
      "learning_rate": 5.172413793103448e-08,
      "loss": -0.0563,
      "reward": 0.24999999813735485,
      "reward_std": 0.23617041483521461,
      "rewards/accuracy_reward": 0.20000000670552254,
      "rewards/format_reward": 0.05000000074505806,
      "step": 5
    },
    {
      "completion_length": 363.50000381469727,
      "epoch": 0.006220839813374806,
      "grad_norm": 3.521343946456909,
      "kl": 0.0002512931823730469,
      "learning_rate": 6.206896551724137e-08,
      "loss": 0.1373,
      "reward": 0.550000011920929,
      "reward_std": 0.517391100525856,
      "rewards/accuracy_reward": 0.4750000163912773,
      "rewards/format_reward": 0.07500000111758709,
      "step": 6
    },
    {
      "completion_length": 387.9500045776367,
      "epoch": 0.007257646448937273,
      "grad_norm": 3.267216205596924,
      "kl": 0.0003764629364013672,
      "learning_rate": 7.241379310344827e-08,
      "loss": 0.0081,
      "reward": 0.2750000059604645,
      "reward_std": 0.36053743213415146,
      "rewards/accuracy_reward": 0.20000000670552254,
      "rewards/format_reward": 0.07500000111758709,
      "step": 7
    },
    {
      "completion_length": 340.6500053405762,
      "epoch": 0.00829445308449974,
      "grad_norm": 2.6857998371124268,
      "kl": 0.0002391338348388672,
      "learning_rate": 8.275862068965517e-08,
      "loss": 0.055,
      "reward": 0.375,
      "reward_std": 0.39822831004858017,
      "rewards/accuracy_reward": 0.34999999962747097,
      "rewards/format_reward": 0.02500000037252903,
      "step": 8
    },
    {
      "completion_length": 488.42501068115234,
      "epoch": 0.00933125972006221,
      "grad_norm": 0.6219092607498169,
      "kl": 0.00023365020751953125,
      "learning_rate": 9.310344827586207e-08,
      "loss": -0.011,
      "reward": 0.22500000521540642,
      "reward_std": 0.3297629803419113,
      "rewards/accuracy_reward": 0.22500000521540642,
      "rewards/format_reward": 0.0,
      "step": 9
    },
    {
      "completion_length": 360.625,
      "epoch": 0.010368066355624676,
      "grad_norm": 0.5460860133171082,
      "kl": 0.000164031982421875,
      "learning_rate": 1.0344827586206897e-07,
      "loss": 0.0558,
      "reward": 0.25000000558793545,
      "reward_std": 0.3856646828353405,
      "rewards/accuracy_reward": 0.22500000335276127,
      "rewards/format_reward": 0.02500000037252903,
      "step": 10
    },
    {
      "completion_length": 341.00000762939453,
      "epoch": 0.011404872991187144,
      "grad_norm": 1.1156655550003052,
      "kl": 0.00022840499877929688,
      "learning_rate": 1.1379310344827586e-07,
      "loss": 0.0461,
      "reward": 0.4000000059604645,
      "reward_std": 0.497468076646328,
      "rewards/accuracy_reward": 0.4000000059604645,
      "rewards/format_reward": 0.0,
      "step": 11
    },
    {
      "completion_length": 354.0999984741211,
      "epoch": 0.012441679626749611,
      "grad_norm": 0.694392740726471,
      "kl": 0.00033974647521972656,
      "learning_rate": 1.2413793103448275e-07,
      "loss": 0.0749,
      "reward": 0.3250000011175871,
      "reward_std": 0.3046357296407223,
      "rewards/accuracy_reward": 0.3250000011175871,
      "rewards/format_reward": 0.0,
      "step": 12
    },
    {
      "completion_length": 371.7750015258789,
      "epoch": 0.01347848626231208,
      "grad_norm": 1.2974847555160522,
      "kl": 0.0002536773681640625,
      "learning_rate": 1.3448275862068965e-07,
      "loss": 0.0034,
      "reward": 0.42500000447034836,
      "reward_std": 0.5263643711805344,
      "rewards/accuracy_reward": 0.3750000074505806,
      "rewards/format_reward": 0.05000000074505806,
      "step": 13
    },
    {
      "completion_length": 377.55001068115234,
      "epoch": 0.014515292897874546,
      "grad_norm": 0.8971682786941528,
      "kl": 0.0002269744873046875,
      "learning_rate": 1.4482758620689654e-07,
      "loss": 0.0266,
      "reward": 0.4000000078231096,
      "reward_std": 0.4415663816034794,
      "rewards/accuracy_reward": 0.4000000078231096,
      "rewards/format_reward": 0.0,
      "step": 14
    },
    {
      "completion_length": 382.6500053405762,
      "epoch": 0.015552099533437015,
      "grad_norm": 1.676780104637146,
      "kl": 0.00034689903259277344,
      "learning_rate": 1.5517241379310344e-07,
      "loss": 0.0303,
      "reward": 0.25000000558793545,
      "reward_std": 0.2920721098780632,
      "rewards/accuracy_reward": 0.22500000335276127,
      "rewards/format_reward": 0.02500000037252903,
      "step": 15
    },
    {
      "completion_length": 237.32500457763672,
      "epoch": 0.01658890616899948,
      "grad_norm": 0.6732295155525208,
      "kl": 0.0001780986785888672,
      "learning_rate": 1.6551724137931034e-07,
      "loss": 0.0088,
      "reward": 0.2000000048428774,
      "reward_std": 0.31719936057925224,
      "rewards/accuracy_reward": 0.1750000026077032,
      "rewards/format_reward": 0.02500000037252903,
      "step": 16
    },
    {
      "completion_length": 246.77500343322754,
      "epoch": 0.01762571280456195,
      "grad_norm": 0.8578572273254395,
      "kl": 0.00020766258239746094,
      "learning_rate": 1.7586206896551724e-07,
      "loss": -0.0679,
      "reward": 0.2500000037252903,
      "reward_std": 0.23617041110992432,
      "rewards/accuracy_reward": 0.2500000037252903,
      "rewards/format_reward": 0.0,
      "step": 17
    },
    {
      "completion_length": 287.7250061035156,
      "epoch": 0.01866251944012442,
      "grad_norm": 1.177450180053711,
      "kl": 0.0002694129943847656,
      "learning_rate": 1.8620689655172414e-07,
      "loss": 0.1109,
      "reward": 0.5750000178813934,
      "reward_std": 0.5335852541029453,
      "rewards/accuracy_reward": 0.5000000149011612,
      "rewards/format_reward": 0.07500000111758709,
      "step": 18
    },
    {
      "completion_length": 276.7000045776367,
      "epoch": 0.019699326075686883,
      "grad_norm": 0.9230583906173706,
      "kl": 0.0002455711364746094,
      "learning_rate": 1.9655172413793106e-07,
      "loss": -0.0118,
      "reward": 0.6000000163912773,
      "reward_std": 0.3731010667979717,
      "rewards/accuracy_reward": 0.6000000163912773,
      "rewards/format_reward": 0.0,
      "step": 19
    },
    {
      "completion_length": 389.7750015258789,
      "epoch": 0.020736132711249352,
      "grad_norm": 0.8271303772926331,
      "kl": 0.000316619873046875,
      "learning_rate": 2.0689655172413793e-07,
      "loss": -0.0191,
      "reward": 0.450000012293458,
      "reward_std": 0.25609347224235535,
      "rewards/accuracy_reward": 0.40000000037252903,
      "rewards/format_reward": 0.05000000074505806,
      "step": 20
    },
    {
      "completion_length": 313.29999923706055,
      "epoch": 0.02177293934681182,
      "grad_norm": 3.3089773654937744,
      "kl": 0.0006225109100341797,
      "learning_rate": 2.1724137931034486e-07,
      "loss": -0.0103,
      "reward": 0.4000000096857548,
      "reward_std": 0.26129765808582306,
      "rewards/accuracy_reward": 0.4000000096857548,
      "rewards/format_reward": 0.0,
      "step": 21
    },
    {
      "completion_length": 342.8750114440918,
      "epoch": 0.02280974598237429,
      "grad_norm": 0.981069803237915,
      "kl": 0.0006477832794189453,
      "learning_rate": 2.2758620689655173e-07,
      "loss": 0.0766,
      "reward": 0.5250000059604645,
      "reward_std": 0.44892579317092896,
      "rewards/accuracy_reward": 0.44999999925494194,
      "rewards/format_reward": 0.07500000111758709,
      "step": 22
    },
    {
      "completion_length": 429.30001068115234,
      "epoch": 0.023846552617936754,
      "grad_norm": 0.4381193518638611,
      "kl": 0.0002999305725097656,
      "learning_rate": 2.3793103448275865e-07,
      "loss": -0.018,
      "reward": 0.3750000037252903,
      "reward_std": 0.2361704222857952,
      "rewards/accuracy_reward": 0.3750000037252903,
      "rewards/format_reward": 0.0,
      "step": 23
    },
    {
      "completion_length": 341.90000915527344,
      "epoch": 0.024883359253499222,
      "grad_norm": 0.8023965954780579,
      "kl": 0.0002903938293457031,
      "learning_rate": 2.482758620689655e-07,
      "loss": 0.0741,
      "reward": 0.5750000048428774,
      "reward_std": 0.36053744703531265,
      "rewards/accuracy_reward": 0.5000000167638063,
      "rewards/format_reward": 0.07500000111758709,
      "step": 24
    },
    {
      "completion_length": 414.6750183105469,
      "epoch": 0.02592016588906169,
      "grad_norm": 1.5727014541625977,
      "kl": 0.00022554397583007812,
      "learning_rate": 2.5862068965517245e-07,
      "loss": -0.0566,
      "reward": 0.42500000819563866,
      "reward_std": 0.5225953236222267,
      "rewards/accuracy_reward": 0.42500000819563866,
      "rewards/format_reward": 0.0,
      "step": 25
    },
    {
      "completion_length": 285.1750030517578,
      "epoch": 0.02695697252462416,
      "grad_norm": 0.7682381272315979,
      "kl": 0.0005116462707519531,
      "learning_rate": 2.689655172413793e-07,
      "loss": -0.0143,
      "reward": 0.35000000335276127,
      "reward_std": 0.45413001254200935,
      "rewards/accuracy_reward": 0.3250000048428774,
      "rewards/format_reward": 0.02500000037252903,
      "step": 26
    },
    {
      "completion_length": 340.00000762939453,
      "epoch": 0.027993779160186624,
      "grad_norm": 0.6389257907867432,
      "kl": 0.00046062469482421875,
      "learning_rate": 2.7931034482758624e-07,
      "loss": -0.0795,
      "reward": 0.20000000670552254,
      "reward_std": 0.31719936430454254,
      "rewards/accuracy_reward": 0.20000000670552254,
      "rewards/format_reward": 0.0,
      "step": 27
    },
    {
      "completion_length": 273.35000228881836,
      "epoch": 0.029030585795749093,
      "grad_norm": 1.1553552150726318,
      "kl": 0.00037384033203125,
      "learning_rate": 2.896551724137931e-07,
      "loss": -0.035,
      "reward": 0.30000000447034836,
      "reward_std": 0.3046357333660126,
      "rewards/accuracy_reward": 0.30000000447034836,
      "rewards/format_reward": 0.0,
      "step": 28
    },
    {
      "completion_length": 294.79999923706055,
      "epoch": 0.03006739243131156,
      "grad_norm": 2.068281650543213,
      "kl": 0.0003008842468261719,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 0.0542,
      "reward": 0.8250000029802322,
      "reward_std": 0.3371223881840706,
      "rewards/accuracy_reward": 0.7750000208616257,
      "rewards/format_reward": 0.05000000074505806,
      "step": 29
    },
    {
      "completion_length": 307.32500076293945,
      "epoch": 0.03110419906687403,
      "grad_norm": 4348.3486328125,
      "kl": 6.1257734298706055,
      "learning_rate": 3.103448275862069e-07,
      "loss": 0.1656,
      "reward": 0.4750000163912773,
      "reward_std": 0.39822830632328987,
      "rewards/accuracy_reward": 0.4750000163912773,
      "rewards/format_reward": 0.0,
      "step": 30
    },
    {
      "completion_length": 387.575008392334,
      "epoch": 0.0321410057024365,
      "grad_norm": 1.4455534219741821,
      "kl": 0.00043702125549316406,
      "learning_rate": 3.2068965517241384e-07,
      "loss": 0.0563,
      "reward": 0.32500000298023224,
      "reward_std": 0.3966545984148979,
      "rewards/accuracy_reward": 0.30000000447034836,
      "rewards/format_reward": 0.02500000037252903,
      "step": 31
    },
    {
      "completion_length": 281.0250015258789,
      "epoch": 0.03317781233799896,
      "grad_norm": 1.362587332725525,
      "kl": 0.0006682872772216797,
      "learning_rate": 3.310344827586207e-07,
      "loss": -0.0157,
      "reward": 0.5750000104308128,
      "reward_std": 0.5587125271558762,
      "rewards/accuracy_reward": 0.5500000044703484,
      "rewards/format_reward": 0.02500000037252903,
      "step": 32
    },
    {
      "completion_length": 451.30001068115234,
      "epoch": 0.03421461897356143,
      "grad_norm": 0.9912571310997009,
      "kl": 0.0003376007080078125,
      "learning_rate": 3.4137931034482763e-07,
      "loss": 0.0678,
      "reward": 0.5000000074505806,
      "reward_std": 0.45413000881671906,
      "rewards/accuracy_reward": 0.4750000014901161,
      "rewards/format_reward": 0.02500000037252903,
      "step": 33
    },
    {
      "completion_length": 398.0,
      "epoch": 0.0352514256091239,
      "grad_norm": 2.6609644889831543,
      "kl": 0.0003285408020019531,
      "learning_rate": 3.517241379310345e-07,
      "loss": 0.0505,
      "reward": 0.3500000089406967,
      "reward_std": 0.37310105934739113,
      "rewards/accuracy_reward": 0.32500001043081284,
      "rewards/format_reward": 0.02500000037252903,
      "step": 34
    },
    {
      "completion_length": 316.0250015258789,
      "epoch": 0.036288232244686365,
      "grad_norm": 0.6625248193740845,
      "kl": 0.000457763671875,
      "learning_rate": 3.6206896551724143e-07,
      "loss": 0.0455,
      "reward": 0.5500000007450581,
      "reward_std": 0.3856646716594696,
      "rewards/accuracy_reward": 0.47499999590218067,
      "rewards/format_reward": 0.07500000111758709,
      "step": 35
    },
    {
      "completion_length": 335.325008392334,
      "epoch": 0.03732503888024884,
      "grad_norm": 9.054551124572754,
      "kl": 0.0006432533264160156,
      "learning_rate": 3.7241379310344827e-07,
      "loss": 0.0427,
      "reward": 0.40000000037252903,
      "reward_std": 0.32818928733468056,
      "rewards/accuracy_reward": 0.3500000014901161,
      "rewards/format_reward": 0.05000000074505806,
      "step": 36
    },
    {
      "completion_length": 380.825008392334,
      "epoch": 0.0383618455158113,
      "grad_norm": 0.7966611385345459,
      "kl": 0.0003523826599121094,
      "learning_rate": 3.827586206896552e-07,
      "loss": -0.0201,
      "reward": 0.3250000085681677,
      "reward_std": 0.3856646828353405,
      "rewards/accuracy_reward": 0.25000000931322575,
      "rewards/format_reward": 0.07500000111758709,
      "step": 37
    },
    {
      "completion_length": 338.87500381469727,
      "epoch": 0.03939865215137377,
      "grad_norm": 0.723584771156311,
      "kl": 0.00029540061950683594,
      "learning_rate": 3.931034482758621e-07,
      "loss": 0.0589,
      "reward": 0.4000000059604645,
      "reward_std": 0.553369790315628,
      "rewards/accuracy_reward": 0.32500000670552254,
      "rewards/format_reward": 0.07500000111758709,
      "step": 38
    },
    {
      "completion_length": 285.6000061035156,
      "epoch": 0.04043545878693624,
      "grad_norm": 1.385939121246338,
      "kl": 0.0009665489196777344,
      "learning_rate": 4.0344827586206897e-07,
      "loss": 0.0266,
      "reward": 0.3000000063329935,
      "reward_std": 0.3731010630726814,
      "rewards/accuracy_reward": 0.3000000063329935,
      "rewards/format_reward": 0.0,
      "step": 39
    },
    {
      "completion_length": 342.0750045776367,
      "epoch": 0.041472265422498704,
      "grad_norm": 1.392383098602295,
      "kl": 0.0010743141174316406,
      "learning_rate": 4.1379310344827586e-07,
      "loss": 0.037,
      "reward": 0.42500001564621925,
      "reward_std": 0.4469091147184372,
      "rewards/accuracy_reward": 0.4000000096857548,
      "rewards/format_reward": 0.02500000037252903,
      "step": 40
    },
    {
      "completion_length": 321.325008392334,
      "epoch": 0.04250907205806117,
      "grad_norm": 0.7412877678871155,
      "kl": 0.0005884170532226562,
      "learning_rate": 4.2413793103448276e-07,
      "loss": 0.0443,
      "reward": 0.6000000014901161,
      "reward_std": 0.3856646791100502,
      "rewards/accuracy_reward": 0.5,
      "rewards/format_reward": 0.10000000335276127,
      "step": 41
    },
    {
      "completion_length": 302.37500762939453,
      "epoch": 0.04354587869362364,
      "grad_norm": 0.8022830486297607,
      "kl": 0.0013997554779052734,
      "learning_rate": 4.344827586206897e-07,
      "loss": 0.1065,
      "reward": 0.20000000670552254,
      "reward_std": 0.2487340345978737,
      "rewards/accuracy_reward": 0.1750000063329935,
      "rewards/format_reward": 0.02500000037252903,
      "step": 42
    },
    {
      "completion_length": 348.3499984741211,
      "epoch": 0.044582685329186106,
      "grad_norm": 0.5473265647888184,
      "kl": 0.0008740425109863281,
      "learning_rate": 4.4482758620689656e-07,
      "loss": -0.0136,
      "reward": 0.6000000089406967,
      "reward_std": 0.3297629877924919,
      "rewards/accuracy_reward": 0.5500000044703484,
      "rewards/format_reward": 0.05000000074505806,
      "step": 43
    },
    {
      "completion_length": 475.4000015258789,
      "epoch": 0.04561949196474858,
      "grad_norm": 0.7117322683334351,
      "kl": 0.0007257461547851562,
      "learning_rate": 4.5517241379310346e-07,
      "loss": 0.0024,
      "reward": 0.25000000558793545,
      "reward_std": 0.31719936057925224,
      "rewards/accuracy_reward": 0.25000000558793545,
      "rewards/format_reward": 0.0,
      "step": 44
    },
    {
      "completion_length": 364.4750099182129,
      "epoch": 0.04665629860031104,
      "grad_norm": 0.810202419757843,
      "kl": 0.0007882118225097656,
      "learning_rate": 4.6551724137931035e-07,
      "loss": 0.0617,
      "reward": 0.22500000335276127,
      "reward_std": 0.3479738272726536,
      "rewards/accuracy_reward": 0.2000000048428774,
      "rewards/format_reward": 0.02500000037252903,
      "step": 45
    },
    {
      "completion_length": 276.65000915527344,
      "epoch": 0.04769310523587351,
      "grad_norm": 0.6206042766571045,
      "kl": 0.0006685256958007812,
      "learning_rate": 4.758620689655173e-07,
      "loss": 0.0294,
      "reward": 0.2750000022351742,
      "reward_std": 0.41643913090229034,
      "rewards/accuracy_reward": 0.2500000037252903,
      "rewards/format_reward": 0.02500000037252903,
      "step": 46
    },
    {
      "completion_length": 358.450008392334,
      "epoch": 0.04872991187143598,
      "grad_norm": 3.410537004470825,
      "kl": 0.002124786376953125,
      "learning_rate": 4.862068965517241e-07,
      "loss": 0.0181,
      "reward": 0.3500000052154064,
      "reward_std": 0.4415663778781891,
      "rewards/accuracy_reward": 0.30000000819563866,
      "rewards/format_reward": 0.05000000074505806,
      "step": 47
    },
    {
      "completion_length": 307.2500114440918,
      "epoch": 0.049766718506998445,
      "grad_norm": 2.8998336791992188,
      "kl": 0.0014314651489257812,
      "learning_rate": 4.96551724137931e-07,
      "loss": 0.0167,
      "reward": 0.6250000074505806,
      "reward_std": 0.558712512254715,
      "rewards/accuracy_reward": 0.5250000059604645,
      "rewards/format_reward": 0.10000000149011612,
      "step": 48
    },
    {
      "completion_length": 303.54999923706055,
      "epoch": 0.05080352514256091,
      "grad_norm": 0.7844371199607849,
      "kl": 0.0009660720825195312,
      "learning_rate": 5.068965517241379e-07,
      "loss": 0.0628,
      "reward": 0.42500001192092896,
      "reward_std": 0.47768356651067734,
      "rewards/accuracy_reward": 0.4000000134110451,
      "rewards/format_reward": 0.02500000037252903,
      "step": 49
    },
    {
      "completion_length": 461.3499984741211,
      "epoch": 0.05184033177812338,
      "grad_norm": 0.5534600615501404,
      "kl": 0.002307891845703125,
      "learning_rate": 5.172413793103449e-07,
      "loss": -0.0613,
      "reward": 0.3750000037252903,
      "reward_std": 0.35704541951417923,
      "rewards/accuracy_reward": 0.32500000670552254,
      "rewards/format_reward": 0.05000000074505806,
      "step": 50
    },
    {
      "completion_length": 301.3500061035156,
      "epoch": 0.05287713841368585,
      "grad_norm": 0.9939333200454712,
      "kl": 0.0011472702026367188,
      "learning_rate": 5.275862068965517e-07,
      "loss": -0.0638,
      "reward": 0.5500000081956387,
      "reward_std": 0.38409100100398064,
      "rewards/accuracy_reward": 0.5000000037252903,
      "rewards/format_reward": 0.05000000074505806,
      "step": 51
    },
    {
      "completion_length": 293.6750030517578,
      "epoch": 0.05391394504924832,
      "grad_norm": 0.6740232110023499,
      "kl": 0.0012159347534179688,
      "learning_rate": 5.379310344827586e-07,
      "loss": 0.0925,
      "reward": 0.5250000152736902,
      "reward_std": 0.5210216604173183,
      "rewards/accuracy_reward": 0.4500000048428774,
      "rewards/format_reward": 0.07500000111758709,
      "step": 52
    },
    {
      "completion_length": 326.12500762939453,
      "epoch": 0.054950751684810784,
      "grad_norm": 0.8232463002204895,
      "kl": 0.0014095306396484375,
      "learning_rate": 5.482758620689655e-07,
      "loss": 0.0658,
      "reward": 0.5250000171363354,
      "reward_std": 0.4415663816034794,
      "rewards/accuracy_reward": 0.45000001415610313,
      "rewards/format_reward": 0.07500000298023224,
      "step": 53
    },
    {
      "completion_length": 285.4000053405762,
      "epoch": 0.05598755832037325,
      "grad_norm": 1.9464935064315796,
      "kl": 0.002483367919921875,
      "learning_rate": 5.586206896551725e-07,
      "loss": -0.1223,
      "reward": 0.32500000670552254,
      "reward_std": 0.4723408371210098,
      "rewards/accuracy_reward": 0.2500000037252903,
      "rewards/format_reward": 0.07500000111758709,
      "step": 54
    },
    {
      "completion_length": 331.77500915527344,
      "epoch": 0.05702436495593572,
      "grad_norm": 3.9341742992401123,
      "kl": 0.0035686492919921875,
      "learning_rate": 5.689655172413793e-07,
      "loss": 0.0667,
      "reward": 0.4750000163912773,
      "reward_std": 0.36053743213415146,
      "rewards/accuracy_reward": 0.42500000819563866,
      "rewards/format_reward": 0.05000000074505806,
      "step": 55
    },
    {
      "completion_length": 326.8500099182129,
      "epoch": 0.058061171591498185,
      "grad_norm": 1.525079369544983,
      "kl": 0.0031280517578125,
      "learning_rate": 5.793103448275862e-07,
      "loss": -0.0055,
      "reward": 0.37500000186264515,
      "reward_std": 0.37310105934739113,
      "rewards/accuracy_reward": 0.35000000335276127,
      "rewards/format_reward": 0.02500000037252903,
      "step": 56
    },
    {
      "completion_length": 267.37500762939453,
      "epoch": 0.05909797822706065,
      "grad_norm": 0.823444128036499,
      "kl": 0.002056121826171875,
      "learning_rate": 5.896551724137931e-07,
      "loss": 0.0713,
      "reward": 0.6500000059604645,
      "reward_std": 0.46669362485408783,
      "rewards/accuracy_reward": 0.5500000044703484,
      "rewards/format_reward": 0.10000000149011612,
      "step": 57
    },
    {
      "completion_length": 222.75,
      "epoch": 0.06013478486262312,
      "grad_norm": 1.267547845840454,
      "kl": 0.0028076171875,
      "learning_rate": 6.000000000000001e-07,
      "loss": 0.0757,
      "reward": 0.600000012665987,
      "reward_std": 0.4092182368040085,
      "rewards/accuracy_reward": 0.5000000167638063,
      "rewards/format_reward": 0.10000000149011612,
      "step": 58
    },
    {
      "completion_length": 252.62500762939453,
      "epoch": 0.06117159149818559,
      "grad_norm": 1.6207536458969116,
      "kl": 0.0028018951416015625,
      "learning_rate": 6.103448275862069e-07,
      "loss": 0.0935,
      "reward": 0.3750000074505806,
      "reward_std": 0.4614894315600395,
      "rewards/accuracy_reward": 0.3000000026077032,
      "rewards/format_reward": 0.07500000111758709,
      "step": 59
    },
    {
      "completion_length": 295.5250053405762,
      "epoch": 0.06220839813374806,
      "grad_norm": 1.536206603050232,
      "kl": 0.010120391845703125,
      "learning_rate": 6.206896551724138e-07,
      "loss": 0.0602,
      "reward": 0.6750000156462193,
      "reward_std": 0.30463574454188347,
      "rewards/accuracy_reward": 0.6250000093132257,
      "rewards/format_reward": 0.05000000074505806,
      "step": 60
    },
    {
      "completion_length": 265.5250015258789,
      "epoch": 0.06324520476931052,
      "grad_norm": 14.682554244995117,
      "kl": 0.020404815673828125,
      "learning_rate": 6.310344827586207e-07,
      "loss": -0.0303,
      "reward": 0.6000000089406967,
      "reward_std": 0.5896254852414131,
      "rewards/accuracy_reward": 0.4750000052154064,
      "rewards/format_reward": 0.12500000186264515,
      "step": 61
    },
    {
      "completion_length": 288.37500762939453,
      "epoch": 0.064282011404873,
      "grad_norm": 5.919084548950195,
      "kl": 0.006771087646484375,
      "learning_rate": 6.413793103448277e-07,
      "loss": 0.0497,
      "reward": 0.5500000044703484,
      "reward_std": 0.4704626724123955,
      "rewards/accuracy_reward": 0.45000000670552254,
      "rewards/format_reward": 0.10000000149011612,
      "step": 62
    },
    {
      "completion_length": 301.6250114440918,
      "epoch": 0.06531881804043546,
      "grad_norm": 16.421817779541016,
      "kl": 0.005756378173828125,
      "learning_rate": 6.517241379310345e-07,
      "loss": 0.1564,
      "reward": 0.6250000149011612,
      "reward_std": 0.5894869714975357,
      "rewards/accuracy_reward": 0.45000000298023224,
      "rewards/format_reward": 0.17500000447034836,
      "step": 63
    },
    {
      "completion_length": 284.77500915527344,
      "epoch": 0.06635562467599793,
      "grad_norm": 7.291428565979004,
      "kl": 0.0056972503662109375,
      "learning_rate": 6.620689655172414e-07,
      "loss": 0.0605,
      "reward": 0.5250000022351742,
      "reward_std": 0.46148940920829773,
      "rewards/accuracy_reward": 0.37499999813735485,
      "rewards/format_reward": 0.15000000223517418,
      "step": 64
    },
    {
      "completion_length": 343.8000030517578,
      "epoch": 0.06739243131156039,
      "grad_norm": 6.103272914886475,
      "kl": 0.004486083984375,
      "learning_rate": 6.724137931034483e-07,
      "loss": -0.0342,
      "reward": 0.4750000089406967,
      "reward_std": 0.5461488887667656,
      "rewards/accuracy_reward": 0.45000000298023224,
      "rewards/format_reward": 0.02500000037252903,
      "step": 65
    },
    {
      "completion_length": 276.20001220703125,
      "epoch": 0.06842923794712286,
      "grad_norm": 0.6578114032745361,
      "kl": 0.004322052001953125,
      "learning_rate": 6.827586206896553e-07,
      "loss": 0.1695,
      "reward": 0.3000000063329935,
      "reward_std": 0.47234082594513893,
      "rewards/accuracy_reward": 0.15000000409781933,
      "rewards/format_reward": 0.15000000223517418,
      "step": 66
    },
    {
      "completion_length": 246.37500381469727,
      "epoch": 0.06946604458268534,
      "grad_norm": 7.143874645233154,
      "kl": 0.004947662353515625,
      "learning_rate": 6.931034482758621e-07,
      "loss": 0.0603,
      "reward": 0.45000001043081284,
      "reward_std": 0.4902471899986267,
      "rewards/accuracy_reward": 0.35000000335276127,
      "rewards/format_reward": 0.10000000149011612,
      "step": 67
    },
    {
      "completion_length": 179.375,
      "epoch": 0.0705028512182478,
      "grad_norm": 0.9650272727012634,
      "kl": 0.00789642333984375,
      "learning_rate": 7.03448275862069e-07,
      "loss": 0.1452,
      "reward": 0.75,
      "reward_std": 0.5985585674643517,
      "rewards/accuracy_reward": 0.4750000052154064,
      "rewards/format_reward": 0.27500000409781933,
      "step": 68
    },
    {
      "completion_length": 284.3250045776367,
      "epoch": 0.07153965785381027,
      "grad_norm": 1.4530069828033447,
      "kl": 0.0058746337890625,
      "learning_rate": 7.137931034482759e-07,
      "loss": -0.0084,
      "reward": 0.775000024586916,
      "reward_std": 0.5697024464607239,
      "rewards/accuracy_reward": 0.5750000067055225,
      "rewards/format_reward": 0.2000000048428774,
      "step": 69
    },
    {
      "completion_length": 290.325008392334,
      "epoch": 0.07257646448937273,
      "grad_norm": 0.7363834381103516,
      "kl": 0.01473236083984375,
      "learning_rate": 7.241379310344829e-07,
      "loss": -0.0061,
      "reward": 0.4000000078231096,
      "reward_std": 0.41643914952874184,
      "rewards/accuracy_reward": 0.3250000011175871,
      "rewards/format_reward": 0.07500000111758709,
      "step": 70
    },
    {
      "completion_length": 194.20000076293945,
      "epoch": 0.0736132711249352,
      "grad_norm": 1.855769395828247,
      "kl": 0.01556396484375,
      "learning_rate": 7.344827586206896e-07,
      "loss": 0.0088,
      "reward": 0.8250000216066837,
      "reward_std": 0.5607292056083679,
      "rewards/accuracy_reward": 0.47500000335276127,
      "rewards/format_reward": 0.35000001080334187,
      "step": 71
    },
    {
      "completion_length": 244.00000381469727,
      "epoch": 0.07465007776049767,
      "grad_norm": 1.9801136255264282,
      "kl": 0.0140533447265625,
      "learning_rate": 7.448275862068965e-07,
      "loss": 0.0587,
      "reward": 0.9500000327825546,
      "reward_std": 0.5624414160847664,
      "rewards/accuracy_reward": 0.6500000208616257,
      "rewards/format_reward": 0.30000000819563866,
      "step": 72
    },
    {
      "completion_length": 223.0250015258789,
      "epoch": 0.07568688439606014,
      "grad_norm": 0.857162594795227,
      "kl": 0.01824951171875,
      "learning_rate": 7.551724137931035e-07,
      "loss": 0.0944,
      "reward": 0.7750000059604645,
      "reward_std": 0.5263643562793732,
      "rewards/accuracy_reward": 0.42500001192092896,
      "rewards/format_reward": 0.350000012665987,
      "step": 73
    },
    {
      "completion_length": 267.02500915527344,
      "epoch": 0.0767236910316226,
      "grad_norm": 1.467808723449707,
      "kl": 0.0139923095703125,
      "learning_rate": 7.655172413793104e-07,
      "loss": 0.0959,
      "reward": 0.8000000268220901,
      "reward_std": 0.4850429780781269,
      "rewards/accuracy_reward": 0.4000000059604645,
      "rewards/format_reward": 0.4000000096857548,
      "step": 74
    },
    {
      "completion_length": 222.25000381469727,
      "epoch": 0.07776049766718507,
      "grad_norm": 1.6067920923233032,
      "kl": 0.0166168212890625,
      "learning_rate": 7.758620689655173e-07,
      "loss": 0.1242,
      "reward": 0.7500000037252903,
      "reward_std": 0.6815058067440987,
      "rewards/accuracy_reward": 0.4000000059604645,
      "rewards/format_reward": 0.3500000014901161,
      "step": 75
    },
    {
      "completion_length": 199.7750015258789,
      "epoch": 0.07879730430274753,
      "grad_norm": 1.2611151933670044,
      "kl": 0.03570556640625,
      "learning_rate": 7.862068965517242e-07,
      "loss": 0.0485,
      "reward": 0.8250000178813934,
      "reward_std": 0.582266092300415,
      "rewards/accuracy_reward": 0.42500000447034836,
      "rewards/format_reward": 0.4000000134110451,
      "step": 76
    },
    {
      "completion_length": 173.07500457763672,
      "epoch": 0.07983411093831,
      "grad_norm": 3.898858070373535,
      "kl": 0.02545166015625,
      "learning_rate": 7.96551724137931e-07,
      "loss": 0.2017,
      "reward": 1.0250000208616257,
      "reward_std": 0.5948297046124935,
      "rewards/accuracy_reward": 0.45000001043081284,
      "rewards/format_reward": 0.5750000029802322,
      "step": 77
    },
    {
      "completion_length": 187.725004196167,
      "epoch": 0.08087091757387248,
      "grad_norm": 0.8916759490966797,
      "kl": 0.040130615234375,
      "learning_rate": 8.068965517241379e-07,
      "loss": 0.0355,
      "reward": 1.1250000149011612,
      "reward_std": 0.6099044531583786,
      "rewards/accuracy_reward": 0.675000011920929,
      "rewards/format_reward": 0.45000000670552254,
      "step": 78
    },
    {
      "completion_length": 177.35000610351562,
      "epoch": 0.08190772420943494,
      "grad_norm": 1.327777624130249,
      "kl": 0.04638671875,
      "learning_rate": 8.172413793103448e-07,
      "loss": 0.0438,
      "reward": 0.9500000178813934,
      "reward_std": 0.7595372572541237,
      "rewards/accuracy_reward": 0.3500000089406967,
      "rewards/format_reward": 0.6000000089406967,
      "step": 79
    },
    {
      "completion_length": 183.1750030517578,
      "epoch": 0.08294453084499741,
      "grad_norm": 1.4906061887741089,
      "kl": 0.054718017578125,
      "learning_rate": 8.275862068965517e-07,
      "loss": 0.1092,
      "reward": 0.8500000089406967,
      "reward_std": 0.6130405142903328,
      "rewards/accuracy_reward": 0.15000000223517418,
      "rewards/format_reward": 0.7000000029802322,
      "step": 80
    },
    {
      "completion_length": 199.35000228881836,
      "epoch": 0.08398133748055987,
      "grad_norm": 3.892275333404541,
      "kl": 0.0404052734375,
      "learning_rate": 8.379310344827587e-07,
      "loss": 0.1296,
      "reward": 1.175000011920929,
      "reward_std": 0.6471008583903313,
      "rewards/accuracy_reward": 0.45000000298023224,
      "rewards/format_reward": 0.7250000089406967,
      "step": 81
    },
    {
      "completion_length": 141.80000114440918,
      "epoch": 0.08501814411612234,
      "grad_norm": 0.9681069254875183,
      "kl": 0.091522216796875,
      "learning_rate": 8.482758620689655e-07,
      "loss": 0.0576,
      "reward": 1.0500000417232513,
      "reward_std": 0.5101702138781548,
      "rewards/accuracy_reward": 0.32500000670552254,
      "rewards/format_reward": 0.7249999940395355,
      "step": 82
    },
    {
      "completion_length": 141.00000190734863,
      "epoch": 0.08605495075168482,
      "grad_norm": 1.6170580387115479,
      "kl": 0.0736083984375,
      "learning_rate": 8.586206896551725e-07,
      "loss": 0.091,
      "reward": 1.1250000149011612,
      "reward_std": 0.5112976878881454,
      "rewards/accuracy_reward": 0.3500000052154064,
      "rewards/format_reward": 0.7750000059604645,
      "step": 83
    },
    {
      "completion_length": 226.37499809265137,
      "epoch": 0.08709175738724728,
      "grad_norm": 2.232787847518921,
      "kl": 0.05548095703125,
      "learning_rate": 8.689655172413794e-07,
      "loss": 0.1663,
      "reward": 1.2000000327825546,
      "reward_std": 0.5984200611710548,
      "rewards/accuracy_reward": 0.450000012293458,
      "rewards/format_reward": 0.7500000149011612,
      "step": 84
    },
    {
      "completion_length": 137.9500026702881,
      "epoch": 0.08812856402280975,
      "grad_norm": 1.994882583618164,
      "kl": 0.058135986328125,
      "learning_rate": 8.793103448275862e-07,
      "loss": 0.0491,
      "reward": 1.4500000029802322,
      "reward_std": 0.44892580062150955,
      "rewards/accuracy_reward": 0.6500000059604645,
      "rewards/format_reward": 0.800000011920929,
      "step": 85
    },
    {
      "completion_length": 121.20000076293945,
      "epoch": 0.08916537065837221,
      "grad_norm": 1.0910072326660156,
      "kl": 0.056640625,
      "learning_rate": 8.896551724137931e-07,
      "loss": 0.054,
      "reward": 1.175000011920929,
      "reward_std": 0.40558772534132004,
      "rewards/accuracy_reward": 0.3750000074505806,
      "rewards/format_reward": 0.800000011920929,
      "step": 86
    },
    {
      "completion_length": 148.9000015258789,
      "epoch": 0.09020217729393468,
      "grad_norm": 2.2213571071624756,
      "kl": 0.220458984375,
      "learning_rate": 9e-07,
      "loss": 0.0789,
      "reward": 1.3250000327825546,
      "reward_std": 0.5624815374612808,
      "rewards/accuracy_reward": 0.5500000007450581,
      "rewards/format_reward": 0.7750000059604645,
      "step": 87
    },
    {
      "completion_length": 157.7750015258789,
      "epoch": 0.09123898392949716,
      "grad_norm": 1.2787593603134155,
      "kl": 0.067138671875,
      "learning_rate": 9.103448275862069e-07,
      "loss": 0.0193,
      "reward": 1.2250000536441803,
      "reward_std": 0.510664701461792,
      "rewards/accuracy_reward": 0.4750000052154064,
      "rewards/format_reward": 0.7500000149011612,
      "step": 88
    },
    {
      "completion_length": 141.32500076293945,
      "epoch": 0.09227579056505962,
      "grad_norm": 1.5759501457214355,
      "kl": 0.109130859375,
      "learning_rate": 9.206896551724139e-07,
      "loss": 0.1089,
      "reward": 1.4500000476837158,
      "reward_std": 0.3804604858160019,
      "rewards/accuracy_reward": 0.6000000089406967,
      "rewards/format_reward": 0.8500000238418579,
      "step": 89
    },
    {
      "completion_length": 142.72500228881836,
      "epoch": 0.09331259720062209,
      "grad_norm": 0.9323010444641113,
      "kl": 0.079803466796875,
      "learning_rate": 9.310344827586207e-07,
      "loss": 0.0734,
      "reward": 1.3000000417232513,
      "reward_std": 0.4657529257237911,
      "rewards/accuracy_reward": 0.45000000670552254,
      "rewards/format_reward": 0.8500000238418579,
      "step": 90
    },
    {
      "completion_length": 122.37500190734863,
      "epoch": 0.09434940383618455,
      "grad_norm": 1.3933780193328857,
      "kl": 0.1185302734375,
      "learning_rate": 9.413793103448277e-07,
      "loss": 0.0271,
      "reward": 1.2000000476837158,
      "reward_std": 0.6617213189601898,
      "rewards/accuracy_reward": 0.3500000052154064,
      "rewards/format_reward": 0.8500000238418579,
      "step": 91
    },
    {
      "completion_length": 126.70000457763672,
      "epoch": 0.09538621047174702,
      "grad_norm": 7.927647113800049,
      "kl": 0.4715576171875,
      "learning_rate": 9.517241379310346e-07,
      "loss": 0.0897,
      "reward": 1.2000000178813934,
      "reward_std": 0.6092714741826057,
      "rewards/accuracy_reward": 0.450000012293458,
      "rewards/format_reward": 0.75,
      "step": 92
    },
    {
      "completion_length": 172.30000114440918,
      "epoch": 0.09642301710730948,
      "grad_norm": 1.3404741287231445,
      "kl": 0.078857421875,
      "learning_rate": 9.620689655172413e-07,
      "loss": 0.0283,
      "reward": 1.3750000298023224,
      "reward_std": 0.46511995419859886,
      "rewards/accuracy_reward": 0.4750000089406967,
      "rewards/format_reward": 0.9000000208616257,
      "step": 93
    },
    {
      "completion_length": 113.35000038146973,
      "epoch": 0.09745982374287196,
      "grad_norm": 7.312382221221924,
      "kl": 0.0780029296875,
      "learning_rate": 9.724137931034483e-07,
      "loss": 0.0145,
      "reward": 1.4000000059604645,
      "reward_std": 0.4092182442545891,
      "rewards/accuracy_reward": 0.4750000089406967,
      "rewards/format_reward": 0.925000011920929,
      "step": 94
    },
    {
      "completion_length": 109.42500114440918,
      "epoch": 0.09849663037843442,
      "grad_norm": 1.404718041419983,
      "kl": 0.08563232421875,
      "learning_rate": 9.827586206896552e-07,
      "loss": 0.072,
      "reward": 1.4250000417232513,
      "reward_std": 0.4740530401468277,
      "rewards/accuracy_reward": 0.45000001788139343,
      "rewards/format_reward": 0.9750000089406967,
      "step": 95
    },
    {
      "completion_length": 117.55000305175781,
      "epoch": 0.09953343701399689,
      "grad_norm": 1.4174925088882446,
      "kl": 0.1512451171875,
      "learning_rate": 9.93103448275862e-07,
      "loss": -0.0339,
      "reward": 1.4000000357627869,
      "reward_std": 0.578635536134243,
      "rewards/accuracy_reward": 0.5750000178813934,
      "rewards/format_reward": 0.8250000178813934,
      "step": 96
    },
    {
      "completion_length": 105.30000114440918,
      "epoch": 0.10057024364955935,
      "grad_norm": 6.377532005310059,
      "kl": 0.1229248046875,
      "learning_rate": 1.003448275862069e-06,
      "loss": -0.0262,
      "reward": 1.3500000536441803,
      "reward_std": 0.4958944097161293,
      "rewards/accuracy_reward": 0.5000000074505806,
      "rewards/format_reward": 0.8500000238418579,
      "step": 97
    },
    {
      "completion_length": 122.80000114440918,
      "epoch": 0.10160705028512182,
      "grad_norm": 3.010532855987549,
      "kl": 0.09405517578125,
      "learning_rate": 1.0137931034482759e-06,
      "loss": 0.0275,
      "reward": 1.3250000178813934,
      "reward_std": 0.2795085050165653,
      "rewards/accuracy_reward": 0.40000000037252903,
      "rewards/format_reward": 0.9250000268220901,
      "step": 98
    },
    {
      "completion_length": 117.97500038146973,
      "epoch": 0.1026438569206843,
      "grad_norm": 1.6175012588500977,
      "kl": 0.09100341796875,
      "learning_rate": 1.0241379310344828e-06,
      "loss": 0.0431,
      "reward": 1.2500000447034836,
      "reward_std": 0.5535082966089249,
      "rewards/accuracy_reward": 0.3750000111758709,
      "rewards/format_reward": 0.875,
      "step": 99
    },
    {
      "completion_length": 123.85000419616699,
      "epoch": 0.10368066355624676,
      "grad_norm": 1.486450433731079,
      "kl": 0.08172607421875,
      "learning_rate": 1.0344827586206898e-06,
      "loss": 0.0611,
      "reward": 1.475000023841858,
      "reward_std": 0.4525563009083271,
      "rewards/accuracy_reward": 0.6250000074505806,
      "rewards/format_reward": 0.8500000089406967,
      "step": 100
    },
    {
      "completion_length": 118.80000114440918,
      "epoch": 0.10471747019180923,
      "grad_norm": 1.8546826839447021,
      "kl": 0.07427978515625,
      "learning_rate": 1.0448275862068965e-06,
      "loss": -0.0648,
      "reward": 1.2500000298023224,
      "reward_std": 0.45412999391555786,
      "rewards/accuracy_reward": 0.4000000134110451,
      "rewards/format_reward": 0.8500000089406967,
      "step": 101
    },
    {
      "completion_length": 107.62500190734863,
      "epoch": 0.1057542768273717,
      "grad_norm": 1.0969343185424805,
      "kl": 0.1190185546875,
      "learning_rate": 1.0551724137931035e-06,
      "loss": 0.0655,
      "reward": 1.4000000059604645,
      "reward_std": 0.3804604709148407,
      "rewards/accuracy_reward": 0.45000000670552254,
      "rewards/format_reward": 0.9500000178813934,
      "step": 102
    },
    {
      "completion_length": 125.30000114440918,
      "epoch": 0.10679108346293416,
      "grad_norm": 2.0286576747894287,
      "kl": 0.1263427734375,
      "learning_rate": 1.0655172413793104e-06,
      "loss": 0.1098,
      "reward": 1.350000023841858,
      "reward_std": 0.44156638905406,
      "rewards/accuracy_reward": 0.45000001043081284,
      "rewards/format_reward": 0.9000000357627869,
      "step": 103
    },
    {
      "completion_length": 115.07500076293945,
      "epoch": 0.10782789009849664,
      "grad_norm": 2.2312369346618652,
      "kl": 0.1448974609375,
      "learning_rate": 1.0758620689655172e-06,
      "loss": 0.0629,
      "reward": 1.3250000178813934,
      "reward_std": 0.47234081476926804,
      "rewards/accuracy_reward": 0.37500000931322575,
      "rewards/format_reward": 0.9500000178813934,
      "step": 104
    },
    {
      "completion_length": 119.22500228881836,
      "epoch": 0.1088646967340591,
      "grad_norm": 0.6519957184791565,
      "kl": 0.0863037109375,
      "learning_rate": 1.0862068965517241e-06,
      "loss": -0.0487,
      "reward": 1.3500000089406967,
      "reward_std": 0.33353203162550926,
      "rewards/accuracy_reward": 0.4500000011175871,
      "rewards/format_reward": 0.9000000059604645,
      "step": 105
    },
    {
      "completion_length": 123.47500228881836,
      "epoch": 0.10990150336962157,
      "grad_norm": 1.1476188898086548,
      "kl": 0.10223388671875,
      "learning_rate": 1.096551724137931e-06,
      "loss": 0.0576,
      "reward": 1.2500000149011612,
      "reward_std": 0.3533165417611599,
      "rewards/accuracy_reward": 0.3499999977648258,
      "rewards/format_reward": 0.9000000208616257,
      "step": 106
    },
    {
      "completion_length": 113.65000343322754,
      "epoch": 0.11093831000518403,
      "grad_norm": 1.9051084518432617,
      "kl": 0.08203125,
      "learning_rate": 1.106896551724138e-06,
      "loss": 0.0674,
      "reward": 1.4000000357627869,
      "reward_std": 0.5806522481143475,
      "rewards/accuracy_reward": 0.6000000089406967,
      "rewards/format_reward": 0.800000011920929,
      "step": 107
    },
    {
      "completion_length": 123.80000305175781,
      "epoch": 0.1119751166407465,
      "grad_norm": 1.0134373903274536,
      "kl": 0.1263427734375,
      "learning_rate": 1.117241379310345e-06,
      "loss": 0.1178,
      "reward": 1.6500000357627869,
      "reward_std": 0.47234082967042923,
      "rewards/accuracy_reward": 0.7750000208616257,
      "rewards/format_reward": 0.8750000298023224,
      "step": 108
    },
    {
      "completion_length": 189.0250072479248,
      "epoch": 0.11301192327630896,
      "grad_norm": 2.021437883377075,
      "kl": 0.06475830078125,
      "learning_rate": 1.1275862068965517e-06,
      "loss": 0.046,
      "reward": 1.2750000357627869,
      "reward_std": 0.6544602662324905,
      "rewards/accuracy_reward": 0.4750000089406967,
      "rewards/format_reward": 0.8000000268220901,
      "step": 109
    },
    {
      "completion_length": 125.30000495910645,
      "epoch": 0.11404872991187144,
      "grad_norm": 1.5949187278747559,
      "kl": 0.07537841796875,
      "learning_rate": 1.1379310344827587e-06,
      "loss": 0.1211,
      "reward": 1.2750000059604645,
      "reward_std": 0.5409446507692337,
      "rewards/accuracy_reward": 0.4750000089406967,
      "rewards/format_reward": 0.800000011920929,
      "step": 110
    },
    {
      "completion_length": 112.60000228881836,
      "epoch": 0.1150855365474339,
      "grad_norm": 0.9887787103652954,
      "kl": 0.09454345703125,
      "learning_rate": 1.1482758620689656e-06,
      "loss": 0.0565,
      "reward": 1.225000023841858,
      "reward_std": 0.5337237864732742,
      "rewards/accuracy_reward": 0.35000000335276127,
      "rewards/format_reward": 0.8750000298023224,
      "step": 111
    },
    {
      "completion_length": 113.90000534057617,
      "epoch": 0.11612234318299637,
      "grad_norm": 1.2379708290100098,
      "kl": 0.1116943359375,
      "learning_rate": 1.1586206896551724e-06,
      "loss": 0.0541,
      "reward": 1.225000023841858,
      "reward_std": 0.5572371743619442,
      "rewards/accuracy_reward": 0.45000000670552254,
      "rewards/format_reward": 0.7750000208616257,
      "step": 112
    },
    {
      "completion_length": 140.9500026702881,
      "epoch": 0.11715914981855884,
      "grad_norm": 2.4870309829711914,
      "kl": 0.076171875,
      "learning_rate": 1.1689655172413793e-06,
      "loss": 0.0255,
      "reward": 1.4750000536441803,
      "reward_std": 0.4415663853287697,
      "rewards/accuracy_reward": 0.6500000134110451,
      "rewards/format_reward": 0.8250000178813934,
      "step": 113
    },
    {
      "completion_length": 143.625,
      "epoch": 0.1181959564541213,
      "grad_norm": 2.575742721557617,
      "kl": 0.05718994140625,
      "learning_rate": 1.1793103448275863e-06,
      "loss": 0.071,
      "reward": 1.225000023841858,
      "reward_std": 0.562441386282444,
      "rewards/accuracy_reward": 0.42500001192092896,
      "rewards/format_reward": 0.800000011920929,
      "step": 114
    },
    {
      "completion_length": 150.72500228881836,
      "epoch": 0.11923276308968378,
      "grad_norm": 4.119329929351807,
      "kl": 0.07586669921875,
      "learning_rate": 1.1896551724137932e-06,
      "loss": 0.0335,
      "reward": 1.2000000178813934,
      "reward_std": 0.5210216380655766,
      "rewards/accuracy_reward": 0.40000000037252903,
      "rewards/format_reward": 0.800000011920929,
      "step": 115
    },
    {
      "completion_length": 129.87500190734863,
      "epoch": 0.12026956972524624,
      "grad_norm": 0.9842166304588318,
      "kl": 0.0792236328125,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.0267,
      "reward": 1.3750000298023224,
      "reward_std": 0.6417581215500832,
      "rewards/accuracy_reward": 0.5500000044703484,
      "rewards/format_reward": 0.8250000178813934,
      "step": 116
    },
    {
      "completion_length": 125.87500381469727,
      "epoch": 0.12130637636080871,
      "grad_norm": 1.5760966539382935,
      "kl": 0.0994873046875,
      "learning_rate": 1.210344827586207e-06,
      "loss": 0.0867,
      "reward": 1.2000000029802322,
      "reward_std": 0.6293330267071724,
      "rewards/accuracy_reward": 0.4500000011175871,
      "rewards/format_reward": 0.75,
      "step": 117
    },
    {
      "completion_length": 144.975004196167,
      "epoch": 0.12234318299637117,
      "grad_norm": 0.8227043747901917,
      "kl": 0.0821533203125,
      "learning_rate": 1.2206896551724138e-06,
      "loss": 0.0002,
      "reward": 1.3500000089406967,
      "reward_std": 0.472973819822073,
      "rewards/accuracy_reward": 0.5500000007450581,
      "rewards/format_reward": 0.800000011920929,
      "step": 118
    },
    {
      "completion_length": 151.1500015258789,
      "epoch": 0.12337998963193364,
      "grad_norm": 3.4477927684783936,
      "kl": 0.11090087890625,
      "learning_rate": 1.2310344827586206e-06,
      "loss": 0.057,
      "reward": 1.5000000596046448,
      "reward_std": 0.5665664002299309,
      "rewards/accuracy_reward": 0.7250000089406967,
      "rewards/format_reward": 0.7750000059604645,
      "step": 119
    },
    {
      "completion_length": 133.72500228881836,
      "epoch": 0.12441679626749612,
      "grad_norm": 1.916924238204956,
      "kl": 0.14306640625,
      "learning_rate": 1.2413793103448275e-06,
      "loss": 0.1373,
      "reward": 1.4749999940395355,
      "reward_std": 0.41643914580345154,
      "rewards/accuracy_reward": 0.6749999970197678,
      "rewards/format_reward": 0.800000011920929,
      "step": 120
    },
    {
      "completion_length": 144.70000457763672,
      "epoch": 0.12545360290305857,
      "grad_norm": 1.4124659299850464,
      "kl": 0.11669921875,
      "learning_rate": 1.2517241379310345e-06,
      "loss": 0.0701,
      "reward": 1.600000023841858,
      "reward_std": 0.5210216268897057,
      "rewards/accuracy_reward": 0.7500000298023224,
      "rewards/format_reward": 0.8500000238418579,
      "step": 121
    },
    {
      "completion_length": 143.50000381469727,
      "epoch": 0.12649040953862103,
      "grad_norm": 2.2720749378204346,
      "kl": 0.09759521484375,
      "learning_rate": 1.2620689655172414e-06,
      "loss": 0.0201,
      "reward": 1.449999988079071,
      "reward_std": 0.5462873950600624,
      "rewards/accuracy_reward": 0.675000011920929,
      "rewards/format_reward": 0.7750000059604645,
      "step": 122
    },
    {
      "completion_length": 125.87500190734863,
      "epoch": 0.12752721617418353,
      "grad_norm": 1.0222535133361816,
      "kl": 0.07147216796875,
      "learning_rate": 1.2724137931034484e-06,
      "loss": 0.0006,
      "reward": 1.4500000476837158,
      "reward_std": 0.3856646865606308,
      "rewards/accuracy_reward": 0.5000000149011612,
      "rewards/format_reward": 0.9500000029802322,
      "step": 123
    },
    {
      "completion_length": 145.07500648498535,
      "epoch": 0.128564022809746,
      "grad_norm": 4.159966945648193,
      "kl": 0.08453369140625,
      "learning_rate": 1.2827586206896553e-06,
      "loss": 0.0968,
      "reward": 1.300000011920929,
      "reward_std": 0.5659333989024162,
      "rewards/accuracy_reward": 0.5250000096857548,
      "rewards/format_reward": 0.7750000208616257,
      "step": 124
    },
    {
      "completion_length": 118.10000038146973,
      "epoch": 0.12960082944530846,
      "grad_norm": 1.1424363851547241,
      "kl": 0.0953369140625,
      "learning_rate": 1.293103448275862e-06,
      "loss": -0.0023,
      "reward": 1.3250000178813934,
      "reward_std": 0.3245587684214115,
      "rewards/accuracy_reward": 0.3999999985098839,
      "rewards/format_reward": 0.925000011920929,
      "step": 125
    },
    {
      "completion_length": 108.20000076293945,
      "epoch": 0.13063763608087092,
      "grad_norm": 3.2891056537628174,
      "kl": 0.100830078125,
      "learning_rate": 1.303448275862069e-06,
      "loss": -0.036,
      "reward": 1.2750000208616257,
      "reward_std": 0.37323955446481705,
      "rewards/accuracy_reward": 0.40000000409781933,
      "rewards/format_reward": 0.8750000149011612,
      "step": 126
    },
    {
      "completion_length": 128.57500457763672,
      "epoch": 0.1316744427164334,
      "grad_norm": 1.2664824724197388,
      "kl": 0.07080078125,
      "learning_rate": 1.3137931034482758e-06,
      "loss": 0.0349,
      "reward": 1.6750000417232513,
      "reward_std": 0.36053745076060295,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 0.925000011920929,
      "step": 127
    },
    {
      "completion_length": 145.00000190734863,
      "epoch": 0.13271124935199585,
      "grad_norm": 1.661323070526123,
      "kl": 0.08135986328125,
      "learning_rate": 1.3241379310344827e-06,
      "loss": 0.0568,
      "reward": 1.5000000298023224,
      "reward_std": 0.4850430078804493,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 0.8750000298023224,
      "step": 128
    },
    {
      "completion_length": 129.42500114440918,
      "epoch": 0.13374805598755832,
      "grad_norm": 1.649943232536316,
      "kl": 0.0888671875,
      "learning_rate": 1.3344827586206897e-06,
      "loss": -0.0105,
      "reward": 1.3750000298023224,
      "reward_std": 0.36053745076060295,
      "rewards/accuracy_reward": 0.42500000074505806,
      "rewards/format_reward": 0.9500000178813934,
      "step": 129
    },
    {
      "completion_length": 119.15000343322754,
      "epoch": 0.13478486262312078,
      "grad_norm": 6.876035690307617,
      "kl": 0.19091796875,
      "learning_rate": 1.3448275862068966e-06,
      "loss": -0.0036,
      "reward": 1.475000023841858,
      "reward_std": 0.4849044345319271,
      "rewards/accuracy_reward": 0.6500000059604645,
      "rewards/format_reward": 0.8250000178813934,
      "step": 130
    },
    {
      "completion_length": 108.72500038146973,
      "epoch": 0.13582166925868325,
      "grad_norm": 1.3705264329910278,
      "kl": 0.1119384765625,
      "learning_rate": 1.3551724137931036e-06,
      "loss": 0.0473,
      "reward": 1.1250000149011612,
      "reward_std": 0.31719935685396194,
      "rewards/accuracy_reward": 0.17500000074505806,
      "rewards/format_reward": 0.9500000029802322,
      "step": 131
    },
    {
      "completion_length": 132.72500038146973,
      "epoch": 0.1368584758942457,
      "grad_norm": 9.587868690490723,
      "kl": 0.10333251953125,
      "learning_rate": 1.3655172413793105e-06,
      "loss": 0.1013,
      "reward": 1.3750000596046448,
      "reward_std": 0.5335852727293968,
      "rewards/accuracy_reward": 0.5000000149011612,
      "rewards/format_reward": 0.8750000298023224,
      "step": 132
    },
    {
      "completion_length": 122.40000343322754,
      "epoch": 0.13789528252980818,
      "grad_norm": 5.267590045928955,
      "kl": 0.120849609375,
      "learning_rate": 1.3758620689655173e-06,
      "loss": -0.0325,
      "reward": 1.475000023841858,
      "reward_std": 0.49746808409690857,
      "rewards/accuracy_reward": 0.5000000037252903,
      "rewards/format_reward": 0.9750000089406967,
      "step": 133
    },
    {
      "completion_length": 121.22500228881836,
      "epoch": 0.13893208916537067,
      "grad_norm": 2.1384124755859375,
      "kl": 0.184814453125,
      "learning_rate": 1.3862068965517242e-06,
      "loss": 0.0501,
      "reward": 1.2750000357627869,
      "reward_std": 0.4291412718594074,
      "rewards/accuracy_reward": 0.4250000137835741,
      "rewards/format_reward": 0.8500000089406967,
      "step": 134
    },
    {
      "completion_length": 108.37500381469727,
      "epoch": 0.13996889580093314,
      "grad_norm": 4.733362674713135,
      "kl": 0.0623779296875,
      "learning_rate": 1.396551724137931e-06,
      "loss": 0.0074,
      "reward": 1.550000011920929,
      "reward_std": 0.23617041110992432,
      "rewards/accuracy_reward": 0.5749999973922968,
      "rewards/format_reward": 0.9750000089406967,
      "step": 135
    },
    {
      "completion_length": 133.85000038146973,
      "epoch": 0.1410057024364956,
      "grad_norm": 1.9882097244262695,
      "kl": 0.07232666015625,
      "learning_rate": 1.406896551724138e-06,
      "loss": 0.048,
      "reward": 1.574999988079071,
      "reward_std": 0.4290027506649494,
      "rewards/accuracy_reward": 0.6000000089406967,
      "rewards/format_reward": 0.9750000089406967,
      "step": 136
    },
    {
      "completion_length": 142.67500114440918,
      "epoch": 0.14204250907205807,
      "grad_norm": 2.703753709793091,
      "kl": 0.1512451171875,
      "learning_rate": 1.4172413793103449e-06,
      "loss": 0.0586,
      "reward": 1.375,
      "reward_std": 0.4578990526497364,
      "rewards/accuracy_reward": 0.5750000178813934,
      "rewards/format_reward": 0.800000011920929,
      "step": 137
    },
    {
      "completion_length": 119.35000228881836,
      "epoch": 0.14307931570762053,
      "grad_norm": 2.8184866905212402,
      "kl": 0.10125732421875,
      "learning_rate": 1.4275862068965518e-06,
      "loss": -0.0393,
      "reward": 1.5000000298023224,
      "reward_std": 0.4290027655661106,
      "rewards/accuracy_reward": 0.5250000208616257,
      "rewards/format_reward": 0.9750000089406967,
      "step": 138
    },
    {
      "completion_length": 111.85000228881836,
      "epoch": 0.144116122343183,
      "grad_norm": 4.2106242179870605,
      "kl": 0.1044921875,
      "learning_rate": 1.4379310344827588e-06,
      "loss": 0.0386,
      "reward": 1.0750000178813934,
      "reward_std": 0.3479738309979439,
      "rewards/accuracy_reward": 0.25000000186264515,
      "rewards/format_reward": 0.8250000178813934,
      "step": 139
    },
    {
      "completion_length": 117.80000305175781,
      "epoch": 0.14515292897874546,
      "grad_norm": 4.182285785675049,
      "kl": 0.0821533203125,
      "learning_rate": 1.4482758620689657e-06,
      "loss": -0.0056,
      "reward": 1.3500000536441803,
      "reward_std": 0.5786355212330818,
      "rewards/accuracy_reward": 0.42500001192092896,
      "rewards/format_reward": 0.925000011920929,
      "step": 140
    },
    {
      "completion_length": 135.22500228881836,
      "epoch": 0.14618973561430793,
      "grad_norm": 1.8042055368423462,
      "kl": 0.1070556640625,
      "learning_rate": 1.4586206896551724e-06,
      "loss": 0.0296,
      "reward": 1.5,
      "reward_std": 0.3856646940112114,
      "rewards/accuracy_reward": 0.5500000063329935,
      "rewards/format_reward": 0.9500000178813934,
      "step": 141
    },
    {
      "completion_length": 126.97500228881836,
      "epoch": 0.1472265422498704,
      "grad_norm": 4.371006011962891,
      "kl": 0.09185791015625,
      "learning_rate": 1.4689655172413792e-06,
      "loss": 0.0361,
      "reward": 1.75,
      "reward_std": 0.24873404949903488,
      "rewards/accuracy_reward": 0.7750000059604645,
      "rewards/format_reward": 0.9750000089406967,
      "step": 142
    },
    {
      "completion_length": 131.6750030517578,
      "epoch": 0.14826334888543286,
      "grad_norm": 17.638200759887695,
      "kl": 0.11883544921875,
      "learning_rate": 1.4793103448275861e-06,
      "loss": 0.0239,
      "reward": 1.375,
      "reward_std": 0.24873404577374458,
      "rewards/accuracy_reward": 0.42500000447034836,
      "rewards/format_reward": 0.9500000178813934,
      "step": 143
    },
    {
      "completion_length": 135.87500381469727,
      "epoch": 0.14930015552099535,
      "grad_norm": 10.907958984375,
      "kl": 0.119384765625,
      "learning_rate": 1.489655172413793e-06,
      "loss": 0.0428,
      "reward": 1.2250000089406967,
      "reward_std": 0.3930240869522095,
      "rewards/accuracy_reward": 0.37500000931322575,
      "rewards/format_reward": 0.8500000089406967,
      "step": 144
    },
    {
      "completion_length": 147.6250057220459,
      "epoch": 0.1503369621565578,
      "grad_norm": 921.281005859375,
      "kl": 3.2681884765625,
      "learning_rate": 1.5e-06,
      "loss": 0.2005,
      "reward": 1.225000038743019,
      "reward_std": 0.30463574081659317,
      "rewards/accuracy_reward": 0.2750000059604645,
      "rewards/format_reward": 0.9500000178813934,
      "step": 145
    },
    {
      "completion_length": 148.72500228881836,
      "epoch": 0.15137376879212028,
      "grad_norm": 14.504183769226074,
      "kl": 0.0855712890625,
      "learning_rate": 1.510344827586207e-06,
      "loss": 0.0652,
      "reward": 1.675000011920929,
      "reward_std": 0.34448179230093956,
      "rewards/accuracy_reward": 0.7500000149011612,
      "rewards/format_reward": 0.9250000268220901,
      "step": 146
    },
    {
      "completion_length": 173.975004196167,
      "epoch": 0.15241057542768274,
      "grad_norm": 251.97561645507812,
      "kl": 0.8280029296875,
      "learning_rate": 1.520689655172414e-06,
      "loss": 0.0497,
      "reward": 1.5250000059604645,
      "reward_std": 0.4343454875051975,
      "rewards/accuracy_reward": 0.6500000059604645,
      "rewards/format_reward": 0.8750000149011612,
      "step": 147
    },
    {
      "completion_length": 180.57500457763672,
      "epoch": 0.1534473820632452,
      "grad_norm": 206.3589630126953,
      "kl": 0.494384765625,
      "learning_rate": 1.5310344827586209e-06,
      "loss": 0.1159,
      "reward": 1.2500000149011612,
      "reward_std": 0.37310104444622993,
      "rewards/accuracy_reward": 0.45000000298023224,
      "rewards/format_reward": 0.800000011920929,
      "step": 148
    },
    {
      "completion_length": 170.9250030517578,
      "epoch": 0.15448418869880767,
      "grad_norm": 61797.4140625,
      "kl": 1144.1375732421875,
      "learning_rate": 1.5413793103448276e-06,
      "loss": 27.6538,
      "reward": 0.9000000208616257,
      "reward_std": 0.5481655634939671,
      "rewards/accuracy_reward": 0.1750000026077032,
      "rewards/format_reward": 0.7250000089406967,
      "step": 149
    },
    {
      "completion_length": 165.55000495910645,
      "epoch": 0.15552099533437014,
      "grad_norm": 886645.125,
      "kl": 669.49169921875,
      "learning_rate": 1.5517241379310346e-06,
      "loss": 31.4775,
      "reward": 1.2750000208616257,
      "reward_std": 0.49226387962698936,
      "rewards/accuracy_reward": 0.475000012665987,
      "rewards/format_reward": 0.800000011920929,
      "step": 150
    },
    {
      "completion_length": 118.1500015258789,
      "epoch": 0.1565578019699326,
      "grad_norm": 120.34538269042969,
      "kl": 1.54296875,
      "learning_rate": 1.5620689655172415e-06,
      "loss": 0.0637,
      "reward": 1.425000011920929,
      "reward_std": 0.26865706592798233,
      "rewards/accuracy_reward": 0.475000012665987,
      "rewards/format_reward": 0.9500000178813934,
      "step": 151
    },
    {
      "completion_length": 126.35000419616699,
      "epoch": 0.15759460860549507,
      "grad_norm": 93.3667984008789,
      "kl": 1.257568359375,
      "learning_rate": 1.5724137931034485e-06,
      "loss": -0.0012,
      "reward": 1.5,
      "reward_std": 0.4291412904858589,
      "rewards/accuracy_reward": 0.5750000104308128,
      "rewards/format_reward": 0.925000011920929,
      "step": 152
    },
    {
      "completion_length": 185.10000610351562,
      "epoch": 0.15863141524105753,
      "grad_norm": 607.76611328125,
      "kl": 1.4993896484375,
      "learning_rate": 1.5827586206896554e-06,
      "loss": 0.1878,
      "reward": 1.5500000417232513,
      "reward_std": 0.4902471825480461,
      "rewards/accuracy_reward": 0.675000011920929,
      "rewards/format_reward": 0.8750000149011612,
      "step": 153
    },
    {
      "completion_length": 150.1500015258789,
      "epoch": 0.15966822187662,
      "grad_norm": 621.0995483398438,
      "kl": 0.4017333984375,
      "learning_rate": 1.593103448275862e-06,
      "loss": 0.0861,
      "reward": 1.5750000178813934,
      "reward_std": 0.27228758856654167,
      "rewards/accuracy_reward": 0.6750000007450581,
      "rewards/format_reward": 0.9000000208616257,
      "step": 154
    },
    {
      "completion_length": 148.475004196167,
      "epoch": 0.1607050285121825,
      "grad_norm": 1060.59033203125,
      "kl": 5.067626953125,
      "learning_rate": 1.603448275862069e-06,
      "loss": 0.3634,
      "reward": 1.2999999970197678,
      "reward_std": 0.48553744331002235,
      "rewards/accuracy_reward": 0.4500000011175871,
      "rewards/format_reward": 0.8500000238418579,
      "step": 155
    },
    {
      "completion_length": 134.1500015258789,
      "epoch": 0.16174183514774496,
      "grad_norm": 100.48238372802734,
      "kl": 0.8262939453125,
      "learning_rate": 1.6137931034482759e-06,
      "loss": 0.0642,
      "reward": 1.2750000059604645,
      "reward_std": 0.248734038323164,
      "rewards/accuracy_reward": 0.42500001192092896,
      "rewards/format_reward": 0.8500000089406967,
      "step": 156
    },
    {
      "completion_length": 147.5750026702881,
      "epoch": 0.16277864178330742,
      "grad_norm": 62.48579788208008,
      "kl": 0.651611328125,
      "learning_rate": 1.6241379310344828e-06,
      "loss": 0.151,
      "reward": 1.25,
      "reward_std": 0.41643912717700005,
      "rewards/accuracy_reward": 0.4000000078231096,
      "rewards/format_reward": 0.8500000238418579,
      "step": 157
    },
    {
      "completion_length": 220.97500610351562,
      "epoch": 0.16381544841886989,
      "grad_norm": 575.1019287109375,
      "kl": 2.5919189453125,
      "learning_rate": 1.6344827586206896e-06,
      "loss": 0.2918,
      "reward": 1.4000000357627869,
      "reward_std": 0.36053742468357086,
      "rewards/accuracy_reward": 0.5000000149011612,
      "rewards/format_reward": 0.9000000059604645,
      "step": 158
    },
    {
      "completion_length": 144.225004196167,
      "epoch": 0.16485225505443235,
      "grad_norm": 7.095518112182617,
      "kl": 0.1251220703125,
      "learning_rate": 1.6448275862068965e-06,
      "loss": 0.0249,
      "reward": 1.5,
      "reward_std": 0.39728759601712227,
      "rewards/accuracy_reward": 0.6000000014901161,
      "rewards/format_reward": 0.9000000059604645,
      "step": 159
    },
    {
      "completion_length": 142.92500114440918,
      "epoch": 0.16588906168999482,
      "grad_norm": 33.05251693725586,
      "kl": 0.8707275390625,
      "learning_rate": 1.6551724137931035e-06,
      "loss": 0.0677,
      "reward": 1.2750000357627869,
      "reward_std": 0.3371223881840706,
      "rewards/accuracy_reward": 0.3500000014901161,
      "rewards/format_reward": 0.925000011920929,
      "step": 160
    },
    {
      "completion_length": 154.0750026702881,
      "epoch": 0.16692586832555728,
      "grad_norm": 65645.4609375,
      "kl": 342.103515625,
      "learning_rate": 1.6655172413793104e-06,
      "loss": 13.3002,
      "reward": 1.5000000149011612,
      "reward_std": 0.41643913090229034,
      "rewards/accuracy_reward": 0.6000000089406967,
      "rewards/format_reward": 0.9000000208616257,
      "step": 161
    },
    {
      "completion_length": 143.15000534057617,
      "epoch": 0.16796267496111975,
      "grad_norm": 230979.875,
      "kl": 1004.058837890625,
      "learning_rate": 1.6758620689655174e-06,
      "loss": 41.8463,
      "reward": 1.4500000476837158,
      "reward_std": 0.3099784553050995,
      "rewards/accuracy_reward": 0.5500000044703484,
      "rewards/format_reward": 0.9000000059604645,
      "step": 162
    },
    {
      "completion_length": 162.97500228881836,
      "epoch": 0.1689994815966822,
      "grad_norm": 104.41748809814453,
      "kl": 0.559814453125,
      "learning_rate": 1.6862068965517243e-06,
      "loss": 0.0662,
      "reward": 1.2750000208616257,
      "reward_std": 0.45977721735835075,
      "rewards/accuracy_reward": 0.4750000014901161,
      "rewards/format_reward": 0.800000011920929,
      "step": 163
    },
    {
      "completion_length": 125.02500534057617,
      "epoch": 0.17003628823224468,
      "grad_norm": 422910.1875,
      "kl": 7556.533203125,
      "learning_rate": 1.696551724137931e-06,
      "loss": 274.9914,
      "reward": 1.4500000178813934,
      "reward_std": 0.39302410185337067,
      "rewards/accuracy_reward": 0.5500000081956387,
      "rewards/format_reward": 0.9000000208616257,
      "step": 164
    },
    {
      "completion_length": 136.90000534057617,
      "epoch": 0.17107309486780714,
      "grad_norm": 39.6871452331543,
      "kl": 0.236572265625,
      "learning_rate": 1.706896551724138e-06,
      "loss": 0.0168,
      "reward": 1.324999988079071,
      "reward_std": 0.2920721285045147,
      "rewards/accuracy_reward": 0.3750000074505806,
      "rewards/format_reward": 0.9500000178813934,
      "step": 165
    },
    {
      "completion_length": 190.02500343322754,
      "epoch": 0.17210990150336963,
      "grad_norm": 2343.3095703125,
      "kl": 3.414794921875,
      "learning_rate": 1.717241379310345e-06,
      "loss": 0.3358,
      "reward": 1.4000000357627869,
      "reward_std": 0.5968463532626629,
      "rewards/accuracy_reward": 0.5750000178813934,
      "rewards/format_reward": 0.8250000178813934,
      "step": 166
    },
    {
      "completion_length": 123.57500267028809,
      "epoch": 0.1731467081389321,
      "grad_norm": 1024.3455810546875,
      "kl": 4.07666015625,
      "learning_rate": 1.727586206896552e-06,
      "loss": 0.2434,
      "reward": 1.550000011920929,
      "reward_std": 0.39665462449193,
      "rewards/accuracy_reward": 0.7000000178813934,
      "rewards/format_reward": 0.8500000238418579,
      "step": 167
    },
    {
      "completion_length": 127.15000343322754,
      "epoch": 0.17418351477449456,
      "grad_norm": 11.419363021850586,
      "kl": 0.1678466796875,
      "learning_rate": 1.7379310344827588e-06,
      "loss": 0.0772,
      "reward": 1.475000023841858,
      "reward_std": 0.5659334138035774,
      "rewards/accuracy_reward": 0.6250000149011612,
      "rewards/format_reward": 0.8500000238418579,
      "step": 168
    },
    {
      "completion_length": 158.8250026702881,
      "epoch": 0.17522032141005703,
      "grad_norm": 812.2886962890625,
      "kl": 10.5908203125,
      "learning_rate": 1.7482758620689658e-06,
      "loss": 0.3363,
      "reward": 1.7500000298023224,
      "reward_std": 0.1928323283791542,
      "rewards/accuracy_reward": 0.7750000059604645,
      "rewards/format_reward": 0.9750000089406967,
      "step": 169
    },
    {
      "completion_length": 142.80000114440918,
      "epoch": 0.1762571280456195,
      "grad_norm": 114.91448974609375,
      "kl": 0.28302001953125,
      "learning_rate": 1.7586206896551723e-06,
      "loss": 0.0374,
      "reward": 1.5000000596046448,
      "reward_std": 0.373101070523262,
      "rewards/accuracy_reward": 0.5750000104308128,
      "rewards/format_reward": 0.925000011920929,
      "step": 170
    },
    {
      "completion_length": 175.60000038146973,
      "epoch": 0.17729393468118196,
      "grad_norm": 19.830774307250977,
      "kl": 0.1810302734375,
      "learning_rate": 1.7689655172413793e-06,
      "loss": 0.0822,
      "reward": 1.5250000059604645,
      "reward_std": 0.324558787047863,
      "rewards/accuracy_reward": 0.5500000044703484,
      "rewards/format_reward": 0.9750000089406967,
      "step": 171
    },
    {
      "completion_length": 159.2500057220459,
      "epoch": 0.17833074131674442,
      "grad_norm": 154360.703125,
      "kl": 380.17138671875,
      "learning_rate": 1.7793103448275862e-06,
      "loss": 27.3536,
      "reward": 1.4000000655651093,
      "reward_std": 0.6183832511305809,
      "rewards/accuracy_reward": 0.5750000104308128,
      "rewards/format_reward": 0.8250000178813934,
      "step": 172
    },
    {
      "completion_length": 135.850004196167,
      "epoch": 0.1793675479523069,
      "grad_norm": 10.023521423339844,
      "kl": 0.11395263671875,
      "learning_rate": 1.789655172413793e-06,
      "loss": 0.0159,
      "reward": 1.4500000178813934,
      "reward_std": 0.22894952446222305,
      "rewards/accuracy_reward": 0.4749999977648258,
      "rewards/format_reward": 0.9750000089406967,
      "step": 173
    },
    {
      "completion_length": 179.9250030517578,
      "epoch": 0.18040435458786935,
      "grad_norm": 25.44389533996582,
      "kl": 0.44427490234375,
      "learning_rate": 1.8e-06,
      "loss": 0.0691,
      "reward": 1.350000023841858,
      "reward_std": 0.5138007514178753,
      "rewards/accuracy_reward": 0.550000011920929,
      "rewards/format_reward": 0.8000000268220901,
      "step": 174
    },
    {
      "completion_length": 157.3000030517578,
      "epoch": 0.18144116122343182,
      "grad_norm": 648.756103515625,
      "kl": 1.504638671875,
      "learning_rate": 1.8103448275862069e-06,
      "loss": 0.1569,
      "reward": 1.4500000476837158,
      "reward_std": 0.5697024464607239,
      "rewards/accuracy_reward": 0.5750000104308128,
      "rewards/format_reward": 0.8750000298023224,
      "step": 175
    },
    {
      "completion_length": 140.4250030517578,
      "epoch": 0.1824779678589943,
      "grad_norm": 16.518726348876953,
      "kl": 0.1947021484375,
      "learning_rate": 1.8206896551724138e-06,
      "loss": 0.0508,
      "reward": 1.3499999940395355,
      "reward_std": 0.30463574081659317,
      "rewards/accuracy_reward": 0.3750000037252903,
      "rewards/format_reward": 0.9750000089406967,
      "step": 176
    },
    {
      "completion_length": 168.4000015258789,
      "epoch": 0.18351477449455678,
      "grad_norm": 12.404158592224121,
      "kl": 0.2431640625,
      "learning_rate": 1.8310344827586208e-06,
      "loss": -0.0125,
      "reward": 1.4250000417232513,
      "reward_std": 0.26129765436053276,
      "rewards/accuracy_reward": 0.42500000447034836,
      "rewards/format_reward": 1.0,
      "step": 177
    },
    {
      "completion_length": 164.92500114440918,
      "epoch": 0.18455158113011924,
      "grad_norm": 29.254444122314453,
      "kl": 0.3502197265625,
      "learning_rate": 1.8413793103448277e-06,
      "loss": 0.1379,
      "reward": 1.4000000357627869,
      "reward_std": 0.5660719126462936,
      "rewards/accuracy_reward": 0.5250000096857548,
      "rewards/format_reward": 0.8750000149011612,
      "step": 178
    },
    {
      "completion_length": 149.7750015258789,
      "epoch": 0.1855883877656817,
      "grad_norm": 6.365128517150879,
      "kl": 0.097900390625,
      "learning_rate": 1.8517241379310345e-06,
      "loss": 0.0811,
      "reward": 1.2750000208616257,
      "reward_std": 0.39302409440279007,
      "rewards/accuracy_reward": 0.32500001043081284,
      "rewards/format_reward": 0.9500000178813934,
      "step": 179
    },
    {
      "completion_length": 123.5,
      "epoch": 0.18662519440124417,
      "grad_norm": 19.429393768310547,
      "kl": 0.1754150390625,
      "learning_rate": 1.8620689655172414e-06,
      "loss": 0.0367,
      "reward": 1.4500000327825546,
      "reward_std": 0.3804604858160019,
      "rewards/accuracy_reward": 0.5500000063329935,
      "rewards/format_reward": 0.9000000208616257,
      "step": 180
    },
    {
      "completion_length": 149.12500381469727,
      "epoch": 0.18766200103680664,
      "grad_norm": 14.26073932647705,
      "kl": 0.134765625,
      "learning_rate": 1.8724137931034484e-06,
      "loss": 0.0374,
      "reward": 1.5750000178813934,
      "reward_std": 0.2920721210539341,
      "rewards/accuracy_reward": 0.6000000182539225,
      "rewards/format_reward": 0.9750000089406967,
      "step": 181
    },
    {
      "completion_length": 144.2750072479248,
      "epoch": 0.1886988076723691,
      "grad_norm": 4.313653945922852,
      "kl": 0.19671630859375,
      "learning_rate": 1.8827586206896553e-06,
      "loss": 0.0236,
      "reward": 1.4000000208616257,
      "reward_std": 0.28485122695565224,
      "rewards/accuracy_reward": 0.4749999940395355,
      "rewards/format_reward": 0.925000011920929,
      "step": 182
    },
    {
      "completion_length": 132.47500228881836,
      "epoch": 0.18973561430793157,
      "grad_norm": 4.134154796600342,
      "kl": 0.1151123046875,
      "learning_rate": 1.8931034482758623e-06,
      "loss": 0.0525,
      "reward": 1.4250000417232513,
      "reward_std": 0.37310105189681053,
      "rewards/accuracy_reward": 0.5500000044703484,
      "rewards/format_reward": 0.8750000298023224,
      "step": 183
    },
    {
      "completion_length": 171.25000381469727,
      "epoch": 0.19077242094349403,
      "grad_norm": 7.449805736541748,
      "kl": 0.124755859375,
      "learning_rate": 1.9034482758620692e-06,
      "loss": 0.0377,
      "reward": 1.1250000447034836,
      "reward_std": 0.4688488021492958,
      "rewards/accuracy_reward": 0.2750000022351742,
      "rewards/format_reward": 0.8500000238418579,
      "step": 184
    },
    {
      "completion_length": 134.2750015258789,
      "epoch": 0.1918092275790565,
      "grad_norm": 4.306768417358398,
      "kl": 0.11016845703125,
      "learning_rate": 1.913793103448276e-06,
      "loss": 0.0353,
      "reward": 1.4000000059604645,
      "reward_std": 0.36053743958473206,
      "rewards/accuracy_reward": 0.4499999973922968,
      "rewards/format_reward": 0.9500000178813934,
      "step": 185
    },
    {
      "completion_length": 162.60000610351562,
      "epoch": 0.19284603421461896,
      "grad_norm": 4.144135475158691,
      "kl": 0.0718994140625,
      "learning_rate": 1.9241379310344827e-06,
      "loss": 0.0482,
      "reward": 1.4250000417232513,
      "reward_std": 0.31719936802983284,
      "rewards/accuracy_reward": 0.5000000037252903,
      "rewards/format_reward": 0.925000011920929,
      "step": 186
    },
    {
      "completion_length": 168.5,
      "epoch": 0.19388284085018145,
      "grad_norm": 2.6224422454833984,
      "kl": 0.1402587890625,
      "learning_rate": 1.9344827586206894e-06,
      "loss": -0.0576,
      "reward": 1.4500000476837158,
      "reward_std": 0.5263643860816956,
      "rewards/accuracy_reward": 0.5750000029802322,
      "rewards/format_reward": 0.8750000149011612,
      "step": 187
    },
    {
      "completion_length": 155.87500190734863,
      "epoch": 0.19491964748574392,
      "grad_norm": 2.5991694927215576,
      "kl": 0.1173095703125,
      "learning_rate": 1.9448275862068966e-06,
      "loss": 0.0525,
      "reward": 1.425000011920929,
      "reward_std": 0.4129471443593502,
      "rewards/accuracy_reward": 0.5250000040978193,
      "rewards/format_reward": 0.9000000357627869,
      "step": 188
    },
    {
      "completion_length": 157.60000228881836,
      "epoch": 0.19595645412130638,
      "grad_norm": 11.603816986083984,
      "kl": 0.08740234375,
      "learning_rate": 1.9551724137931033e-06,
      "loss": 0.0086,
      "reward": 1.5999999940395355,
      "reward_std": 0.4525563307106495,
      "rewards/accuracy_reward": 0.7250000089406967,
      "rewards/format_reward": 0.8750000149011612,
      "step": 189
    },
    {
      "completion_length": 163.6750030517578,
      "epoch": 0.19699326075686885,
      "grad_norm": 2.4964864253997803,
      "kl": 0.08258056640625,
      "learning_rate": 1.9655172413793105e-06,
      "loss": 0.007,
      "reward": 1.5250000357627869,
      "reward_std": 0.329762976616621,
      "rewards/accuracy_reward": 0.5500000063329935,
      "rewards/format_reward": 0.9750000089406967,
      "step": 190
    },
    {
      "completion_length": 163.37500381469727,
      "epoch": 0.1980300673924313,
      "grad_norm": 2.807250499725342,
      "kl": 0.0880126953125,
      "learning_rate": 1.9758620689655172e-06,
      "loss": -0.0182,
      "reward": 1.3000000417232513,
      "reward_std": 0.4849044606089592,
      "rewards/accuracy_reward": 0.45000000670552254,
      "rewards/format_reward": 0.8499999940395355,
      "step": 191
    },
    {
      "completion_length": 113.47500228881836,
      "epoch": 0.19906687402799378,
      "grad_norm": 0.9696298241615295,
      "kl": 0.1170654296875,
      "learning_rate": 1.986206896551724e-06,
      "loss": -0.0394,
      "reward": 1.725000023841858,
      "reward_std": 0.12436702474951744,
      "rewards/accuracy_reward": 0.7250000089406967,
      "rewards/format_reward": 1.0,
      "step": 192
    },
    {
      "completion_length": 139.8250026702881,
      "epoch": 0.20010368066355624,
      "grad_norm": 1.4813657999038696,
      "kl": 0.0897216796875,
      "learning_rate": 1.996551724137931e-06,
      "loss": 0.0159,
      "reward": 1.3750000298023224,
      "reward_std": 0.41643912717700005,
      "rewards/accuracy_reward": 0.45000000670552254,
      "rewards/format_reward": 0.9250000268220901,
      "step": 193
    },
    {
      "completion_length": 186.35000228881836,
      "epoch": 0.2011404872991187,
      "grad_norm": 2.646305561065674,
      "kl": 0.1492919921875,
      "learning_rate": 2.006896551724138e-06,
      "loss": 0.0906,
      "reward": 1.5250000357627869,
      "reward_std": 0.40387552604079247,
      "rewards/accuracy_reward": 0.6250000074505806,
      "rewards/format_reward": 0.9000000357627869,
      "step": 194
    },
    {
      "completion_length": 178.600004196167,
      "epoch": 0.20217729393468117,
      "grad_norm": 3.9357028007507324,
      "kl": 0.1038818359375,
      "learning_rate": 2.017241379310345e-06,
      "loss": 0.013,
      "reward": 1.2750000059604645,
      "reward_std": 0.3966546133160591,
      "rewards/accuracy_reward": 0.40000000037252903,
      "rewards/format_reward": 0.8750000149011612,
      "step": 195
    },
    {
      "completion_length": 175.0500030517578,
      "epoch": 0.20321410057024364,
      "grad_norm": 6.768120288848877,
      "kl": 0.12518310546875,
      "learning_rate": 2.0275862068965518e-06,
      "loss": 0.0436,
      "reward": 1.4749999940395355,
      "reward_std": 0.472340852022171,
      "rewards/accuracy_reward": 0.6250000223517418,
      "rewards/format_reward": 0.8499999940395355,
      "step": 196
    },
    {
      "completion_length": 145.22500038146973,
      "epoch": 0.2042509072058061,
      "grad_norm": 2.82489275932312,
      "kl": 0.0924072265625,
      "learning_rate": 2.037931034482759e-06,
      "loss": 0.0287,
      "reward": 1.475000023841858,
      "reward_std": 0.4290027730166912,
      "rewards/accuracy_reward": 0.6000000089406967,
      "rewards/format_reward": 0.8750000298023224,
      "step": 197
    },
    {
      "completion_length": 186.82500076293945,
      "epoch": 0.2052877138413686,
      "grad_norm": 6.81854772567749,
      "kl": 0.0621337890625,
      "learning_rate": 2.0482758620689657e-06,
      "loss": -0.1108,
      "reward": 1.225000038743019,
      "reward_std": 0.373101070523262,
      "rewards/accuracy_reward": 0.32500001043081284,
      "rewards/format_reward": 0.9000000059604645,
      "step": 198
    },
    {
      "completion_length": 160.30000114440918,
      "epoch": 0.20632452047693106,
      "grad_norm": 3.4426076412200928,
      "kl": 0.06744384765625,
      "learning_rate": 2.0586206896551724e-06,
      "loss": 0.0542,
      "reward": 1.1750000268220901,
      "reward_std": 0.4614894203841686,
      "rewards/accuracy_reward": 0.3500000089406967,
      "rewards/format_reward": 0.8250000178813934,
      "step": 199
    },
    {
      "completion_length": 190.45000457763672,
      "epoch": 0.20736132711249353,
      "grad_norm": 2.7901272773742676,
      "kl": 0.095458984375,
      "learning_rate": 2.0689655172413796e-06,
      "loss": 0.0244,
      "reward": 1.5000000298023224,
      "reward_std": 0.5173911228775978,
      "rewards/accuracy_reward": 0.5750000104308128,
      "rewards/format_reward": 0.925000011920929,
      "step": 200
    },
    {
      "completion_length": 175.1500015258789,
      "epoch": 0.208398133748056,
      "grad_norm": 5.208185195922852,
      "kl": 0.0733642578125,
      "learning_rate": 2.0793103448275863e-06,
      "loss": 0.0926,
      "reward": 1.449999988079071,
      "reward_std": 0.4525563232600689,
      "rewards/accuracy_reward": 0.5250000059604645,
      "rewards/format_reward": 0.925000011920929,
      "step": 201
    },
    {
      "completion_length": 162.62500190734863,
      "epoch": 0.20943494038361846,
      "grad_norm": 1.4480936527252197,
      "kl": 0.1016845703125,
      "learning_rate": 2.089655172413793e-06,
      "loss": 0.0509,
      "reward": 1.4000000059604645,
      "reward_std": 0.45977722853422165,
      "rewards/accuracy_reward": 0.4750000089406967,
      "rewards/format_reward": 0.9250000268220901,
      "step": 202
    },
    {
      "completion_length": 164.6750030517578,
      "epoch": 0.21047174701918092,
      "grad_norm": 4.689480304718018,
      "kl": 0.0806884765625,
      "learning_rate": 2.1e-06,
      "loss": 0.0337,
      "reward": 1.425000011920929,
      "reward_std": 0.37310105934739113,
      "rewards/accuracy_reward": 0.5750000029802322,
      "rewards/format_reward": 0.8500000238418579,
      "step": 203
    },
    {
      "completion_length": 165.60000228881836,
      "epoch": 0.2115085536547434,
      "grad_norm": 5.075602054595947,
      "kl": 0.078369140625,
      "learning_rate": 2.110344827586207e-06,
      "loss": 0.0524,
      "reward": 1.3250000327825546,
      "reward_std": 0.3407529257237911,
      "rewards/accuracy_reward": 0.4500000011175871,
      "rewards/format_reward": 0.875,
      "step": 204
    },
    {
      "completion_length": 155.70000457763672,
      "epoch": 0.21254536029030585,
      "grad_norm": 1.853857398033142,
      "kl": 0.09381103515625,
      "learning_rate": 2.1206896551724137e-06,
      "loss": -0.0339,
      "reward": 1.2250000089406967,
      "reward_std": 0.5588510297238827,
      "rewards/accuracy_reward": 0.4000000078231096,
      "rewards/format_reward": 0.8250000029802322,
      "step": 205
    },
    {
      "completion_length": 183.0250015258789,
      "epoch": 0.21358216692586832,
      "grad_norm": 0.6376509666442871,
      "kl": 0.068603515625,
      "learning_rate": 2.131034482758621e-06,
      "loss": 0.082,
      "reward": 1.3750000149011612,
      "reward_std": 0.36067599430680275,
      "rewards/accuracy_reward": 0.5750000104308128,
      "rewards/format_reward": 0.8000000044703484,
      "step": 206
    },
    {
      "completion_length": 186.22500228881836,
      "epoch": 0.21461897356143078,
      "grad_norm": 0.9813095927238464,
      "kl": 0.0640869140625,
      "learning_rate": 2.1413793103448276e-06,
      "loss": 0.0382,
      "reward": 1.3000000417232513,
      "reward_std": 0.45413000881671906,
      "rewards/accuracy_reward": 0.42500000447034836,
      "rewards/format_reward": 0.8750000149011612,
      "step": 207
    },
    {
      "completion_length": 151.05000114440918,
      "epoch": 0.21565578019699327,
      "grad_norm": 0.8648532032966614,
      "kl": 0.0977783203125,
      "learning_rate": 2.1517241379310343e-06,
      "loss": 0.0119,
      "reward": 1.4749999940395355,
      "reward_std": 0.3804604560136795,
      "rewards/accuracy_reward": 0.5500000193715096,
      "rewards/format_reward": 0.925000011920929,
      "step": 208
    },
    {
      "completion_length": 152.5250015258789,
      "epoch": 0.21669258683255574,
      "grad_norm": 0.7379907965660095,
      "kl": 0.09222412109375,
      "learning_rate": 2.1620689655172415e-06,
      "loss": 0.0774,
      "reward": 1.300000011920929,
      "reward_std": 0.44892578572034836,
      "rewards/accuracy_reward": 0.3750000074505806,
      "rewards/format_reward": 0.9250000268220901,
      "step": 209
    },
    {
      "completion_length": 143.6500015258789,
      "epoch": 0.2177293934681182,
      "grad_norm": 0.6392645835876465,
      "kl": 0.07421875,
      "learning_rate": 2.1724137931034482e-06,
      "loss": 0.0565,
      "reward": 1.4249999821186066,
      "reward_std": 0.23617041110992432,
      "rewards/accuracy_reward": 0.42500000447034836,
      "rewards/format_reward": 1.0,
      "step": 210
    },
    {
      "completion_length": 156.05000495910645,
      "epoch": 0.21876620010368067,
      "grad_norm": 0.8323525786399841,
      "kl": 0.0712890625,
      "learning_rate": 2.1827586206896554e-06,
      "loss": -0.0088,
      "reward": 1.5250000357627869,
      "reward_std": 0.5156789347529411,
      "rewards/accuracy_reward": 0.5750000104308128,
      "rewards/format_reward": 0.9500000178813934,
      "step": 211
    },
    {
      "completion_length": 198.5500030517578,
      "epoch": 0.21980300673924313,
      "grad_norm": 0.6546644568443298,
      "kl": 0.07940673828125,
      "learning_rate": 2.193103448275862e-06,
      "loss": 0.0794,
      "reward": 1.5750000178813934,
      "reward_std": 0.42178186774253845,
      "rewards/accuracy_reward": 0.6499999985098839,
      "rewards/format_reward": 0.925000011920929,
      "step": 212
    },
    {
      "completion_length": 146.5000057220459,
      "epoch": 0.2208398133748056,
      "grad_norm": 0.8499487042427063,
      "kl": 0.11083984375,
      "learning_rate": 2.203448275862069e-06,
      "loss": 0.0293,
      "reward": 1.2999999970197678,
      "reward_std": 0.3479738160967827,
      "rewards/accuracy_reward": 0.375,
      "rewards/format_reward": 0.9250000268220901,
      "step": 213
    },
    {
      "completion_length": 145.57500076293945,
      "epoch": 0.22187662001036806,
      "grad_norm": 0.687872588634491,
      "kl": 0.07757568359375,
      "learning_rate": 2.213793103448276e-06,
      "loss": 0.0198,
      "reward": 1.3000000417232513,
      "reward_std": 0.3856646753847599,
      "rewards/accuracy_reward": 0.4500000048428774,
      "rewards/format_reward": 0.8500000089406967,
      "step": 214
    },
    {
      "completion_length": 133.89999961853027,
      "epoch": 0.22291342664593053,
      "grad_norm": 0.5972610116004944,
      "kl": 0.09869384765625,
      "learning_rate": 2.2241379310344828e-06,
      "loss": -0.0411,
      "reward": 1.6250000298023224,
      "reward_std": 0.1928323432803154,
      "rewards/accuracy_reward": 0.6500000059604645,
      "rewards/format_reward": 0.9750000089406967,
      "step": 215
    },
    {
      "completion_length": 121.60000419616699,
      "epoch": 0.223950233281493,
      "grad_norm": 0.7216851711273193,
      "kl": 0.14794921875,
      "learning_rate": 2.23448275862069e-06,
      "loss": -0.0187,
      "reward": 1.5750000178813934,
      "reward_std": 0.2920721285045147,
      "rewards/accuracy_reward": 0.6250000074505806,
      "rewards/format_reward": 0.9500000178813934,
      "step": 216
    },
    {
      "completion_length": 178.8499984741211,
      "epoch": 0.22498703991705546,
      "grad_norm": 0.6720969676971436,
      "kl": 0.113037109375,
      "learning_rate": 2.2448275862068967e-06,
      "loss": -0.0698,
      "reward": 1.2500000447034836,
      "reward_std": 0.40558772161602974,
      "rewards/accuracy_reward": 0.3750000037252903,
      "rewards/format_reward": 0.8750000149011612,
      "step": 217
    },
    {
      "completion_length": 189.72500228881836,
      "epoch": 0.22602384655261792,
      "grad_norm": 0.719994068145752,
      "kl": 0.1602783203125,
      "learning_rate": 2.2551724137931034e-06,
      "loss": 0.0713,
      "reward": 1.4250000417232513,
      "reward_std": 0.45413000136613846,
      "rewards/accuracy_reward": 0.5,
      "rewards/format_reward": 0.925000011920929,
      "step": 218
    },
    {
      "completion_length": 133.8250026702881,
      "epoch": 0.22706065318818042,
      "grad_norm": 0.4400331377983093,
      "kl": 0.1085205078125,
      "learning_rate": 2.26551724137931e-06,
      "loss": 0.0333,
      "reward": 1.5250000208616257,
      "reward_std": 0.12436702474951744,
      "rewards/accuracy_reward": 0.5499999970197678,
      "rewards/format_reward": 0.9750000089406967,
      "step": 219
    },
    {
      "completion_length": 154.80000686645508,
      "epoch": 0.22809745982374288,
      "grad_norm": 0.6450486779212952,
      "kl": 0.131103515625,
      "learning_rate": 2.2758620689655173e-06,
      "loss": 0.0126,
      "reward": 1.3250000327825546,
      "reward_std": 0.31719936430454254,
      "rewards/accuracy_reward": 0.4000000059604645,
      "rewards/format_reward": 0.925000011920929,
      "step": 220
    },
    {
      "completion_length": 145.72500610351562,
      "epoch": 0.22913426645930535,
      "grad_norm": 1.3167037963867188,
      "kl": 0.135986328125,
      "learning_rate": 2.286206896551724e-06,
      "loss": 0.0465,
      "reward": 1.8250000178813934,
      "reward_std": 0.2920721173286438,
      "rewards/accuracy_reward": 0.9750000089406967,
      "rewards/format_reward": 0.8500000238418579,
      "step": 221
    },
    {
      "completion_length": 172.0500030517578,
      "epoch": 0.2301710730948678,
      "grad_norm": 0.7341930866241455,
      "kl": 0.148193359375,
      "learning_rate": 2.2965517241379312e-06,
      "loss": 0.0681,
      "reward": 1.0500000417232513,
      "reward_std": 0.393024068325758,
      "rewards/accuracy_reward": 0.22500000149011612,
      "rewards/format_reward": 0.8250000178813934,
      "step": 222
    },
    {
      "completion_length": 146.42500495910645,
      "epoch": 0.23120787973043028,
      "grad_norm": 0.8762367367744446,
      "kl": 0.123046875,
      "learning_rate": 2.306896551724138e-06,
      "loss": 0.1031,
      "reward": 1.550000011920929,
      "reward_std": 0.5210216194391251,
      "rewards/accuracy_reward": 0.6500000059604645,
      "rewards/format_reward": 0.9000000059604645,
      "step": 223
    },
    {
      "completion_length": 157.7750072479248,
      "epoch": 0.23224468636599274,
      "grad_norm": 0.8583253026008606,
      "kl": 0.13037109375,
      "learning_rate": 2.3172413793103447e-06,
      "loss": 0.1291,
      "reward": 1.6250000298023224,
      "reward_std": 0.41643912717700005,
      "rewards/accuracy_reward": 0.7500000074505806,
      "rewards/format_reward": 0.875,
      "step": 224
    },
    {
      "completion_length": 146.5500030517578,
      "epoch": 0.2332814930015552,
      "grad_norm": 0.8889981508255005,
      "kl": 0.113525390625,
      "learning_rate": 2.327586206896552e-06,
      "loss": -0.024,
      "reward": 1.5999999940395355,
      "reward_std": 0.2795084975659847,
      "rewards/accuracy_reward": 0.6250000223517418,
      "rewards/format_reward": 0.9750000089406967,
      "step": 225
    },
    {
      "completion_length": 137.5500030517578,
      "epoch": 0.23431829963711767,
      "grad_norm": 0.7300592064857483,
      "kl": 0.1185302734375,
      "learning_rate": 2.3379310344827586e-06,
      "loss": 0.0438,
      "reward": 1.3499999940395355,
      "reward_std": 0.46511995419859886,
      "rewards/accuracy_reward": 0.4000000096857548,
      "rewards/format_reward": 0.9500000029802322,
      "step": 226
    },
    {
      "completion_length": 119.70000457763672,
      "epoch": 0.23535510627268014,
      "grad_norm": 0.727929413318634,
      "kl": 0.137451171875,
      "learning_rate": 2.3482758620689658e-06,
      "loss": 0.0458,
      "reward": 1.350000023841858,
      "reward_std": 0.24873404204845428,
      "rewards/accuracy_reward": 0.3999999985098839,
      "rewards/format_reward": 0.9500000178813934,
      "step": 227
    },
    {
      "completion_length": 147.70000076293945,
      "epoch": 0.2363919129082426,
      "grad_norm": 0.9192894101142883,
      "kl": 0.139404296875,
      "learning_rate": 2.3586206896551725e-06,
      "loss": 0.0975,
      "reward": 1.350000023841858,
      "reward_std": 0.39302409067749977,
      "rewards/accuracy_reward": 0.4250000063329935,
      "rewards/format_reward": 0.9250000268220901,
      "step": 228
    },
    {
      "completion_length": 156.4000015258789,
      "epoch": 0.23742871954380507,
      "grad_norm": 0.7950097918510437,
      "kl": 0.1527099609375,
      "learning_rate": 2.3689655172413793e-06,
      "loss": 0.0755,
      "reward": 1.600000023841858,
      "reward_std": 0.3245587833225727,
      "rewards/accuracy_reward": 0.6250000149011612,
      "rewards/format_reward": 0.9750000089406967,
      "step": 229
    },
    {
      "completion_length": 109.77500343322754,
      "epoch": 0.23846552617936756,
      "grad_norm": 0.933161735534668,
      "kl": 0.142333984375,
      "learning_rate": 2.3793103448275864e-06,
      "loss": 0.0125,
      "reward": 1.449999988079071,
      "reward_std": 0.2920721210539341,
      "rewards/accuracy_reward": 0.4750000014901161,
      "rewards/format_reward": 0.9750000089406967,
      "step": 230
    },
    {
      "completion_length": 125.25,
      "epoch": 0.23950233281493002,
      "grad_norm": 0.715398371219635,
      "kl": 0.1328125,
      "learning_rate": 2.389655172413793e-06,
      "loss": -0.0194,
      "reward": 1.5500000417232513,
      "reward_std": 0.3407529182732105,
      "rewards/accuracy_reward": 0.6000000089406967,
      "rewards/format_reward": 0.9500000178813934,
      "step": 231
    },
    {
      "completion_length": 106.65000343322754,
      "epoch": 0.2405391394504925,
      "grad_norm": 1.061570644378662,
      "kl": 0.205810546875,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.0093,
      "reward": 1.5250000059604645,
      "reward_std": 0.3479738160967827,
      "rewards/accuracy_reward": 0.5250000134110451,
      "rewards/format_reward": 1.0,
      "step": 232
    },
    {
      "completion_length": 107.42500305175781,
      "epoch": 0.24157594608605495,
      "grad_norm": 0.8809791207313538,
      "kl": 0.1182861328125,
      "learning_rate": 2.410344827586207e-06,
      "loss": 0.0425,
      "reward": 1.4250000417232513,
      "reward_std": 0.40558769553899765,
      "rewards/accuracy_reward": 0.44999999552965164,
      "rewards/format_reward": 0.9750000089406967,
      "step": 233
    },
    {
      "completion_length": 118.6500015258789,
      "epoch": 0.24261275272161742,
      "grad_norm": 0.6223216652870178,
      "kl": 0.1490478515625,
      "learning_rate": 2.420689655172414e-06,
      "loss": 0.1029,
      "reward": 1.475000023841858,
      "reward_std": 0.2920721173286438,
      "rewards/accuracy_reward": 0.5000000093132257,
      "rewards/format_reward": 0.9750000089406967,
      "step": 234
    },
    {
      "completion_length": 116.7750015258789,
      "epoch": 0.24364955935717988,
      "grad_norm": 1.0359702110290527,
      "kl": 0.21630859375,
      "learning_rate": 2.4310344827586205e-06,
      "loss": 0.1095,
      "reward": 1.4500000178813934,
      "reward_std": 0.5409446731209755,
      "rewards/accuracy_reward": 0.550000011920929,
      "rewards/format_reward": 0.9000000208616257,
      "step": 235
    },
    {
      "completion_length": 101.80000114440918,
      "epoch": 0.24468636599274235,
      "grad_norm": 0.6835160255432129,
      "kl": 0.20654296875,
      "learning_rate": 2.4413793103448277e-06,
      "loss": 0.0014,
      "reward": 1.4500000476837158,
      "reward_std": 0.24873404204845428,
      "rewards/accuracy_reward": 0.450000012293458,
      "rewards/format_reward": 1.0,
      "step": 236
    },
    {
      "completion_length": 110.22500038146973,
      "epoch": 0.24572317262830481,
      "grad_norm": 0.50115966796875,
      "kl": 0.1844482421875,
      "learning_rate": 2.4517241379310344e-06,
      "loss": 0.0505,
      "reward": 1.7249999940395355,
      "reward_std": 0.16770510002970695,
      "rewards/accuracy_reward": 0.7750000059604645,
      "rewards/format_reward": 0.9500000178813934,
      "step": 237
    },
    {
      "completion_length": 113.75000190734863,
      "epoch": 0.24675997926386728,
      "grad_norm": 7.211286544799805,
      "kl": 0.42578125,
      "learning_rate": 2.462068965517241e-06,
      "loss": 0.0999,
      "reward": 1.550000011920929,
      "reward_std": 0.3966546207666397,
      "rewards/accuracy_reward": 0.675000011920929,
      "rewards/format_reward": 0.8750000298023224,
      "step": 238
    },
    {
      "completion_length": 112.39999961853027,
      "epoch": 0.24779678589942974,
      "grad_norm": 0.547843873500824,
      "kl": 0.156494140625,
      "learning_rate": 2.4724137931034483e-06,
      "loss": -0.0177,
      "reward": 1.2750000059604645,
      "reward_std": 0.1928323470056057,
      "rewards/accuracy_reward": 0.27500000037252903,
      "rewards/format_reward": 1.0,
      "step": 239
    },
    {
      "completion_length": 111.02500343322754,
      "epoch": 0.24883359253499224,
      "grad_norm": 0.553968608379364,
      "kl": 0.1614990234375,
      "learning_rate": 2.482758620689655e-06,
      "loss": -0.0008,
      "reward": 1.5,
      "reward_std": 0.20019177719950676,
      "rewards/accuracy_reward": 0.5500000100582838,
      "rewards/format_reward": 0.9500000178813934,
      "step": 240
    },
    {
      "completion_length": 101.9000015258789,
      "epoch": 0.2498703991705547,
      "grad_norm": 0.6699236631393433,
      "kl": 0.17431640625,
      "learning_rate": 2.4931034482758622e-06,
      "loss": 0.0162,
      "reward": 1.3500000089406967,
      "reward_std": 0.16770510748028755,
      "rewards/accuracy_reward": 0.37500000186264515,
      "rewards/format_reward": 0.9750000089406967,
      "step": 241
    },
    {
      "completion_length": 114.30000114440918,
      "epoch": 0.25090720580611714,
      "grad_norm": 0.8109186291694641,
      "kl": 0.145751953125,
      "learning_rate": 2.503448275862069e-06,
      "loss": -0.009,
      "reward": 1.475000023841858,
      "reward_std": 0.3371223919093609,
      "rewards/accuracy_reward": 0.5250000059604645,
      "rewards/format_reward": 0.9500000178813934,
      "step": 242
    },
    {
      "completion_length": 150.85000228881836,
      "epoch": 0.25194401244167963,
      "grad_norm": 0.7055056691169739,
      "kl": 0.14892578125,
      "learning_rate": 2.513793103448276e-06,
      "loss": 0.0376,
      "reward": 1.2500000298023224,
      "reward_std": 0.3930240757763386,
      "rewards/accuracy_reward": 0.32500000670552254,
      "rewards/format_reward": 0.925000011920929,
      "step": 243
    },
    {
      "completion_length": 116.4000015258789,
      "epoch": 0.25298081907724207,
      "grad_norm": 0.8164229393005371,
      "kl": 0.1978759765625,
      "learning_rate": 2.524137931034483e-06,
      "loss": -0.0283,
      "reward": 1.5500000417232513,
      "reward_std": 0.36053745076060295,
      "rewards/accuracy_reward": 0.6000000089406967,
      "rewards/format_reward": 0.9500000178813934,
      "step": 244
    },
    {
      "completion_length": 149.54999923706055,
      "epoch": 0.25401762571280456,
      "grad_norm": 0.702789843082428,
      "kl": 0.1356201171875,
      "learning_rate": 2.5344827586206896e-06,
      "loss": 0.0248,
      "reward": 1.4500000476837158,
      "reward_std": 0.3731010667979717,
      "rewards/accuracy_reward": 0.5000000074505806,
      "rewards/format_reward": 0.9500000178813934,
      "step": 245
    },
    {
      "completion_length": 139.87500381469727,
      "epoch": 0.25505443234836706,
      "grad_norm": 0.8374885320663452,
      "kl": 0.1865234375,
      "learning_rate": 2.5448275862068968e-06,
      "loss": 0.0117,
      "reward": 1.3750000298023224,
      "reward_std": 0.31719936057925224,
      "rewards/accuracy_reward": 0.40000000037252903,
      "rewards/format_reward": 0.9750000089406967,
      "step": 246
    },
    {
      "completion_length": 154.17500686645508,
      "epoch": 0.2560912389839295,
      "grad_norm": 0.5410239696502686,
      "kl": 0.1728515625,
      "learning_rate": 2.5551724137931035e-06,
      "loss": 0.0571,
      "reward": 1.5750000178813934,
      "reward_std": 0.26143617182970047,
      "rewards/accuracy_reward": 0.6249999944120646,
      "rewards/format_reward": 0.9500000178813934,
      "step": 247
    },
    {
      "completion_length": 132.79999923706055,
      "epoch": 0.257128045619492,
      "grad_norm": 0.733527660369873,
      "kl": 0.1473388671875,
      "learning_rate": 2.5655172413793107e-06,
      "loss": 0.0043,
      "reward": 1.5999999940395355,
      "reward_std": 0.3479738123714924,
      "rewards/accuracy_reward": 0.6250000074505806,
      "rewards/format_reward": 0.9750000089406967,
      "step": 248
    },
    {
      "completion_length": 250.8000030517578,
      "epoch": 0.2581648522550544,
      "grad_norm": 0.6939677596092224,
      "kl": 0.1351318359375,
      "learning_rate": 2.5758620689655174e-06,
      "loss": 0.0938,
      "reward": 1.5750000476837158,
      "reward_std": 0.3856646791100502,
      "rewards/accuracy_reward": 0.7000000104308128,
      "rewards/format_reward": 0.8750000149011612,
      "step": 249
    },
    {
      "completion_length": 151.17500495910645,
      "epoch": 0.2592016588906169,
      "grad_norm": 0.3936190605163574,
      "kl": 0.166015625,
      "learning_rate": 2.586206896551724e-06,
      "loss": 0.0012,
      "reward": 1.5999999940395355,
      "reward_std": 0.16770508512854576,
      "rewards/accuracy_reward": 0.6250000093132257,
      "rewards/format_reward": 0.9750000089406967,
      "step": 250
    },
    {
      "completion_length": 235.57499885559082,
      "epoch": 0.26023846552617935,
      "grad_norm": 1.5798455476760864,
      "kl": 0.26806640625,
      "learning_rate": 2.596551724137931e-06,
      "loss": 0.2016,
      "reward": 1.4000000357627869,
      "reward_std": 0.6146142035722733,
      "rewards/accuracy_reward": 0.5749999955296516,
      "rewards/format_reward": 0.8250000029802322,
      "step": 251
    },
    {
      "completion_length": 187.70000457763672,
      "epoch": 0.26127527216174184,
      "grad_norm": 0.5298973917961121,
      "kl": 0.16845703125,
      "learning_rate": 2.606896551724138e-06,
      "loss": 0.0335,
      "reward": 1.3250000029802322,
      "reward_std": 0.2920721098780632,
      "rewards/accuracy_reward": 0.4000000059604645,
      "rewards/format_reward": 0.925000011920929,
      "step": 252
    },
    {
      "completion_length": 160.1750030517578,
      "epoch": 0.2623120787973043,
      "grad_norm": 0.6976402401924133,
      "kl": 0.157958984375,
      "learning_rate": 2.617241379310345e-06,
      "loss": 0.0418,
      "reward": 1.5750000178813934,
      "reward_std": 0.5587124899029732,
      "rewards/accuracy_reward": 0.6500000059604645,
      "rewards/format_reward": 0.9250000268220901,
      "step": 253
    },
    {
      "completion_length": 284.1750144958496,
      "epoch": 0.2633488854328668,
      "grad_norm": 0.6427121758460999,
      "kl": 0.1856689453125,
      "learning_rate": 2.6275862068965515e-06,
      "loss": 0.1826,
      "reward": 1.350000023841858,
      "reward_std": 0.4850429743528366,
      "rewards/accuracy_reward": 0.47500000335276127,
      "rewards/format_reward": 0.8750000298023224,
      "step": 254
    },
    {
      "completion_length": 304.4750061035156,
      "epoch": 0.2643856920684292,
      "grad_norm": 3.0576741695404053,
      "kl": 0.264404296875,
      "learning_rate": 2.6379310344827587e-06,
      "loss": 0.1303,
      "reward": 1.225000038743019,
      "reward_std": 0.6094100177288055,
      "rewards/accuracy_reward": 0.4249999988824129,
      "rewards/format_reward": 0.800000011920929,
      "step": 255
    },
    {
      "completion_length": 373.6000099182129,
      "epoch": 0.2654224987039917,
      "grad_norm": 0.5253204107284546,
      "kl": 0.1571044921875,
      "learning_rate": 2.6482758620689654e-06,
      "loss": 0.1922,
      "reward": 0.9750000089406967,
      "reward_std": 0.47768357396125793,
      "rewards/accuracy_reward": 0.3000000063329935,
      "rewards/format_reward": 0.6750000044703484,
      "step": 256
    },
    {
      "completion_length": 355.32501220703125,
      "epoch": 0.2664593053395542,
      "grad_norm": 0.9178584218025208,
      "kl": 0.2265625,
      "learning_rate": 2.6586206896551726e-06,
      "loss": 0.3166,
      "reward": 1.0000000298023224,
      "reward_std": 0.7397527396678925,
      "rewards/accuracy_reward": 0.375,
      "rewards/format_reward": 0.6250000149011612,
      "step": 257
    },
    {
      "completion_length": 237.27500534057617,
      "epoch": 0.26749611197511663,
      "grad_norm": 0.6554264426231384,
      "kl": 0.17626953125,
      "learning_rate": 2.6689655172413793e-06,
      "loss": 0.1707,
      "reward": 1.0750000327825546,
      "reward_std": 0.6130405068397522,
      "rewards/accuracy_reward": 0.375,
      "rewards/format_reward": 0.7000000178813934,
      "step": 258
    },
    {
      "completion_length": 530.1000061035156,
      "epoch": 0.2685329186106791,
      "grad_norm": 0.6588838696479797,
      "kl": 0.1446533203125,
      "learning_rate": 2.6793103448275865e-06,
      "loss": 0.1994,
      "reward": 1.0000000149011612,
      "reward_std": 0.6033165566623211,
      "rewards/accuracy_reward": 0.42500000447034836,
      "rewards/format_reward": 0.5750000104308128,
      "step": 259
    },
    {
      "completion_length": 372.25000762939453,
      "epoch": 0.26956972524624156,
      "grad_norm": 0.8617604970932007,
      "kl": 0.279052734375,
      "learning_rate": 2.6896551724137932e-06,
      "loss": 0.2631,
      "reward": 1.1500000059604645,
      "reward_std": 0.7571920454502106,
      "rewards/accuracy_reward": 0.5250000022351742,
      "rewards/format_reward": 0.625,
      "step": 260
    },
    {
      "completion_length": 370.0750045776367,
      "epoch": 0.27060653188180406,
      "grad_norm": 0.8590409755706787,
      "kl": 0.257080078125,
      "learning_rate": 2.7e-06,
      "loss": 0.1892,
      "reward": 1.2000000476837158,
      "reward_std": 0.7344100549817085,
      "rewards/accuracy_reward": 0.4000000134110451,
      "rewards/format_reward": 0.800000011920929,
      "step": 261
    },
    {
      "completion_length": 197.8250026702881,
      "epoch": 0.2716433385173665,
      "grad_norm": 0.921504020690918,
      "kl": 0.262939453125,
      "learning_rate": 2.710344827586207e-06,
      "loss": 0.2638,
      "reward": 1.4500000178813934,
      "reward_std": 0.4723408371210098,
      "rewards/accuracy_reward": 0.6000000089406967,
      "rewards/format_reward": 0.8500000089406967,
      "step": 262
    },
    {
      "completion_length": 230.94999885559082,
      "epoch": 0.272680145152929,
      "grad_norm": 0.7630376219749451,
      "kl": 0.238525390625,
      "learning_rate": 2.720689655172414e-06,
      "loss": 0.1966,
      "reward": 1.300000011920929,
      "reward_std": 0.6491576656699181,
      "rewards/accuracy_reward": 0.5250000096857548,
      "rewards/format_reward": 0.7750000059604645,
      "step": 263
    },
    {
      "completion_length": 208.65000343322754,
      "epoch": 0.2737169517884914,
      "grad_norm": 0.9253503680229187,
      "kl": 0.29345703125,
      "learning_rate": 2.731034482758621e-06,
      "loss": 0.2176,
      "reward": 1.1250000447034836,
      "reward_std": 0.5414391383528709,
      "rewards/accuracy_reward": 0.3250000011175871,
      "rewards/format_reward": 0.7999999970197678,
      "step": 264
    },
    {
      "completion_length": 141.70000457763672,
      "epoch": 0.2747537584240539,
      "grad_norm": 0.9654400944709778,
      "kl": 0.34521484375,
      "learning_rate": 2.7413793103448278e-06,
      "loss": 0.1135,
      "reward": 1.1250000298023224,
      "reward_std": 0.4170721210539341,
      "rewards/accuracy_reward": 0.2750000059604645,
      "rewards/format_reward": 0.8500000238418579,
      "step": 265
    },
    {
      "completion_length": 121.32500267028809,
      "epoch": 0.27579056505961635,
      "grad_norm": 1.2874776124954224,
      "kl": 0.447509765625,
      "learning_rate": 2.7517241379310345e-06,
      "loss": 0.1512,
      "reward": 1.3750000298023224,
      "reward_std": 0.41643913462758064,
      "rewards/accuracy_reward": 0.4500000048428774,
      "rewards/format_reward": 0.925000011920929,
      "step": 266
    },
    {
      "completion_length": 124.97500324249268,
      "epoch": 0.27682737169517885,
      "grad_norm": 0.7988603711128235,
      "kl": 0.448486328125,
      "learning_rate": 2.7620689655172413e-06,
      "loss": 0.1464,
      "reward": 1.5249999910593033,
      "reward_std": 0.22360679507255554,
      "rewards/accuracy_reward": 0.5750000104308128,
      "rewards/format_reward": 0.9500000029802322,
      "step": 267
    },
    {
      "completion_length": 43.82500076293945,
      "epoch": 0.27786417833074134,
      "grad_norm": 1.037258505821228,
      "kl": 0.646484375,
      "learning_rate": 2.7724137931034484e-06,
      "loss": 0.0372,
      "reward": 1.4500000178813934,
      "reward_std": 0.2487340308725834,
      "rewards/accuracy_reward": 0.45000001043081284,
      "rewards/format_reward": 1.0,
      "step": 268
    },
    {
      "completion_length": 47.30000019073486,
      "epoch": 0.2789009849663038,
      "grad_norm": 0.7092971205711365,
      "kl": 0.41455078125,
      "learning_rate": 2.782758620689655e-06,
      "loss": 0.0284,
      "reward": 1.6500000059604645,
      "reward_std": 0.24151314795017242,
      "rewards/accuracy_reward": 0.6750000007450581,
      "rewards/format_reward": 0.9750000089406967,
      "step": 269
    },
    {
      "completion_length": 94.62500286102295,
      "epoch": 0.27993779160186627,
      "grad_norm": 0.4653095304965973,
      "kl": 0.7783203125,
      "learning_rate": 2.793103448275862e-06,
      "loss": 0.0589,
      "reward": 1.425000011920929,
      "reward_std": 0.15685367584228516,
      "rewards/accuracy_reward": 0.45000000670552254,
      "rewards/format_reward": 0.9750000089406967,
      "step": 270
    },
    {
      "completion_length": 151.97500228881836,
      "epoch": 0.2809745982374287,
      "grad_norm": 0.9383624792098999,
      "kl": 0.50537109375,
      "learning_rate": 2.803448275862069e-06,
      "loss": 0.0766,
      "reward": 1.5500000417232513,
      "reward_std": 0.32818931341171265,
      "rewards/accuracy_reward": 0.6000000089406967,
      "rewards/format_reward": 0.9500000029802322,
      "step": 271
    },
    {
      "completion_length": 193.1000051498413,
      "epoch": 0.2820114048729912,
      "grad_norm": 0.7510073781013489,
      "kl": 0.46533203125,
      "learning_rate": 2.813793103448276e-06,
      "loss": 0.1247,
      "reward": 1.4500000178813934,
      "reward_std": 0.41657765209674835,
      "rewards/accuracy_reward": 0.5250000059604645,
      "rewards/format_reward": 0.9250000268220901,
      "step": 272
    },
    {
      "completion_length": 219.00000762939453,
      "epoch": 0.28304821150855364,
      "grad_norm": 0.8484097719192505,
      "kl": 0.505859375,
      "learning_rate": 2.824137931034483e-06,
      "loss": 0.2461,
      "reward": 1.475000023841858,
      "reward_std": 0.4783165566623211,
      "rewards/accuracy_reward": 0.5750000141561031,
      "rewards/format_reward": 0.9000000059604645,
      "step": 273
    },
    {
      "completion_length": 54.650001525878906,
      "epoch": 0.28408501814411613,
      "grad_norm": 0.9514493346214294,
      "kl": 0.64794921875,
      "learning_rate": 2.8344827586206897e-06,
      "loss": 0.041,
      "reward": 1.300000011920929,
      "reward_std": 0.11180339008569717,
      "rewards/accuracy_reward": 0.32500000298023224,
      "rewards/format_reward": 0.9750000089406967,
      "step": 274
    },
    {
      "completion_length": 203.30000114440918,
      "epoch": 0.28512182477967857,
      "grad_norm": 0.680706262588501,
      "kl": 0.5048828125,
      "learning_rate": 2.8448275862068964e-06,
      "loss": 0.1976,
      "reward": 1.350000023841858,
      "reward_std": 0.3611704185605049,
      "rewards/accuracy_reward": 0.44999999925494194,
      "rewards/format_reward": 0.9000000059604645,
      "step": 275
    },
    {
      "completion_length": 150.50000381469727,
      "epoch": 0.28615863141524106,
      "grad_norm": 0.5486094355583191,
      "kl": 0.56982421875,
      "learning_rate": 2.8551724137931036e-06,
      "loss": 0.0903,
      "reward": 1.4000000059604645,
      "reward_std": 0.24936703965067863,
      "rewards/accuracy_reward": 0.45000000298023224,
      "rewards/format_reward": 0.9500000029802322,
      "step": 276
    },
    {
      "completion_length": 193.65000534057617,
      "epoch": 0.2871954380508035,
      "grad_norm": 0.9081488847732544,
      "kl": 0.53564453125,
      "learning_rate": 2.8655172413793104e-06,
      "loss": 0.0827,
      "reward": 1.3000000417232513,
      "reward_std": 0.3407529219985008,
      "rewards/accuracy_reward": 0.375,
      "rewards/format_reward": 0.925000011920929,
      "step": 277
    },
    {
      "completion_length": 118.72500324249268,
      "epoch": 0.288232244686366,
      "grad_norm": 0.8595836758613586,
      "kl": 0.46435546875,
      "learning_rate": 2.8758620689655175e-06,
      "loss": 0.096,
      "reward": 1.300000011920929,
      "reward_std": 0.3858031928539276,
      "rewards/accuracy_reward": 0.3750000074505806,
      "rewards/format_reward": 0.9250000268220901,
      "step": 278
    },
    {
      "completion_length": 197.52500247955322,
      "epoch": 0.2892690513219285,
      "grad_norm": 0.6958838105201721,
      "kl": 0.708984375,
      "learning_rate": 2.8862068965517243e-06,
      "loss": 0.1442,
      "reward": 1.2000000029802322,
      "reward_std": 0.26129765436053276,
      "rewards/accuracy_reward": 0.30000000447034836,
      "rewards/format_reward": 0.9000000059604645,
      "step": 279
    },
    {
      "completion_length": 150.2000026702881,
      "epoch": 0.2903058579574909,
      "grad_norm": 0.8232119679450989,
      "kl": 0.640625,
      "learning_rate": 2.8965517241379314e-06,
      "loss": 0.136,
      "reward": 1.350000023841858,
      "reward_std": 0.335410188883543,
      "rewards/accuracy_reward": 0.4000000059604645,
      "rewards/format_reward": 0.9500000178813934,
      "step": 280
    },
    {
      "completion_length": 104.10000324249268,
      "epoch": 0.2913426645930534,
      "grad_norm": 0.7683313488960266,
      "kl": 0.57568359375,
      "learning_rate": 2.906896551724138e-06,
      "loss": 0.084,
      "reward": 1.2500000447034836,
      "reward_std": 0.3046357296407223,
      "rewards/accuracy_reward": 0.2750000059604645,
      "rewards/format_reward": 0.9750000089406967,
      "step": 281
    },
    {
      "completion_length": 179.05000019073486,
      "epoch": 0.29237947122861585,
      "grad_norm": 0.7294011116027832,
      "kl": 0.525390625,
      "learning_rate": 2.917241379310345e-06,
      "loss": 0.2052,
      "reward": 1.4000000357627869,
      "reward_std": 0.4237985461950302,
      "rewards/accuracy_reward": 0.47500000335276127,
      "rewards/format_reward": 0.925000011920929,
      "step": 282
    },
    {
      "completion_length": 99.7750015258789,
      "epoch": 0.29341627786417834,
      "grad_norm": 0.783625602722168,
      "kl": 0.57958984375,
      "learning_rate": 2.9275862068965516e-06,
      "loss": 0.0685,
      "reward": 1.425000011920929,
      "reward_std": 0.23617040738463402,
      "rewards/accuracy_reward": 0.4500000048428774,
      "rewards/format_reward": 0.9750000089406967,
      "step": 283
    },
    {
      "completion_length": 150.60000228881836,
      "epoch": 0.2944530844997408,
      "grad_norm": 0.9992136359214783,
      "kl": 0.68603515625,
      "learning_rate": 2.9379310344827584e-06,
      "loss": 0.1626,
      "reward": 1.4500000029802322,
      "reward_std": 0.2487340345978737,
      "rewards/accuracy_reward": 0.5,
      "rewards/format_reward": 0.9500000029802322,
      "step": 284
    },
    {
      "completion_length": 100.15000057220459,
      "epoch": 0.2954898911353033,
      "grad_norm": 0.5232768654823303,
      "kl": 0.70703125,
      "learning_rate": 2.9482758620689655e-06,
      "loss": 0.0727,
      "reward": 1.2500000149011612,
      "reward_std": 0.11180340498685837,
      "rewards/accuracy_reward": 0.2750000059604645,
      "rewards/format_reward": 0.9750000089406967,
      "step": 285
    },
    {
      "completion_length": 146.7750015258789,
      "epoch": 0.2965266977708657,
      "grad_norm": 1.0567251443862915,
      "kl": 0.83203125,
      "learning_rate": 2.9586206896551723e-06,
      "loss": 0.1205,
      "reward": 1.225000023841858,
      "reward_std": 0.37323957309126854,
      "rewards/accuracy_reward": 0.3000000063329935,
      "rewards/format_reward": 0.925000011920929,
      "step": 286
    },
    {
      "completion_length": 96.50000286102295,
      "epoch": 0.2975635044064282,
      "grad_norm": 0.7808656096458435,
      "kl": 0.728515625,
      "learning_rate": 2.9689655172413794e-06,
      "loss": 0.0931,
      "reward": 1.4000000357627869,
      "reward_std": 0.2361704297363758,
      "rewards/accuracy_reward": 0.4250000100582838,
      "rewards/format_reward": 0.9750000089406967,
      "step": 287
    },
    {
      "completion_length": 196.0250015258789,
      "epoch": 0.2986003110419907,
      "grad_norm": 0.7538319230079651,
      "kl": 0.6689453125,
      "learning_rate": 2.979310344827586e-06,
      "loss": 0.1413,
      "reward": 1.4500000327825546,
      "reward_std": 0.26129764690995216,
      "rewards/accuracy_reward": 0.5250000134110451,
      "rewards/format_reward": 0.925000011920929,
      "step": 288
    },
    {
      "completion_length": 144.70000076293945,
      "epoch": 0.29963711767755313,
      "grad_norm": 1.2029356956481934,
      "kl": 1.0400390625,
      "learning_rate": 2.9896551724137933e-06,
      "loss": 0.1362,
      "reward": 1.175000011920929,
      "reward_std": 0.31199513748288155,
      "rewards/accuracy_reward": 0.22500000707805157,
      "rewards/format_reward": 0.9500000178813934,
      "step": 289
    },
    {
      "completion_length": 354.9250087738037,
      "epoch": 0.3006739243131156,
      "grad_norm": 0.8506849408149719,
      "kl": 0.8056640625,
      "learning_rate": 3e-06,
      "loss": 0.3898,
      "reward": 1.25,
      "reward_std": 0.5210216455161572,
      "rewards/accuracy_reward": 0.45000001043081284,
      "rewards/format_reward": 0.800000011920929,
      "step": 290
    },
    {
      "completion_length": 223.7750062942505,
      "epoch": 0.30171073094867806,
      "grad_norm": 0.479114294052124,
      "kl": 0.705078125,
      "learning_rate": 2.999998906682319e-06,
      "loss": 0.135,
      "reward": 1.2750000357627869,
      "reward_std": 0.22531899064779282,
      "rewards/accuracy_reward": 0.40000000037252903,
      "rewards/format_reward": 0.8750000149011612,
      "step": 291
    },
    {
      "completion_length": 140.07500171661377,
      "epoch": 0.30274753758424056,
      "grad_norm": 0.6931892037391663,
      "kl": 0.734375,
      "learning_rate": 2.9999956267308692e-06,
      "loss": 0.1173,
      "reward": 1.5000000149011612,
      "reward_std": 0.36053743958473206,
      "rewards/accuracy_reward": 0.5500000193715096,
      "rewards/format_reward": 0.9500000178813934,
      "step": 292
    },
    {
      "completion_length": 172.12500286102295,
      "epoch": 0.303784344219803,
      "grad_norm": 0.528679609298706,
      "kl": 0.580078125,
      "learning_rate": 2.9999901601504326e-06,
      "loss": 0.1734,
      "reward": 1.2749999910593033,
      "reward_std": 0.22360679507255554,
      "rewards/accuracy_reward": 0.3500000014901161,
      "rewards/format_reward": 0.925000011920929,
      "step": 293
    },
    {
      "completion_length": 313.8000030517578,
      "epoch": 0.3048211508553655,
      "grad_norm": 0.8700326681137085,
      "kl": 0.62646484375,
      "learning_rate": 2.9999825069489775e-06,
      "loss": 0.2371,
      "reward": 1.0500000268220901,
      "reward_std": 0.47768355160951614,
      "rewards/accuracy_reward": 0.22500000335276127,
      "rewards/format_reward": 0.8250000178813934,
      "step": 294
    },
    {
      "completion_length": 239.125,
      "epoch": 0.3058579574909279,
      "grad_norm": 0.5965785384178162,
      "kl": 0.740234375,
      "learning_rate": 2.999972667137661e-06,
      "loss": 0.2412,
      "reward": 0.9750000387430191,
      "reward_std": 0.2920721136033535,
      "rewards/accuracy_reward": 0.10000000149011612,
      "rewards/format_reward": 0.8750000298023224,
      "step": 295
    },
    {
      "completion_length": 161.44999980926514,
      "epoch": 0.3068947641264904,
      "grad_norm": 0.45877698063850403,
      "kl": 0.638671875,
      "learning_rate": 2.9999606407308272e-06,
      "loss": 0.1932,
      "reward": 1.3750000596046448,
      "reward_std": 0.3913118876516819,
      "rewards/accuracy_reward": 0.45000001043081284,
      "rewards/format_reward": 0.9250000268220901,
      "step": 296
    },
    {
      "completion_length": 230.45000648498535,
      "epoch": 0.30793157076205285,
      "grad_norm": 0.774716854095459,
      "kl": 0.755859375,
      "learning_rate": 2.999946427746007e-06,
      "loss": 0.2691,
      "reward": 1.2750000357627869,
      "reward_std": 0.472340852022171,
      "rewards/accuracy_reward": 0.4000000078231096,
      "rewards/format_reward": 0.8750000149011612,
      "step": 297
    },
    {
      "completion_length": 90.85000038146973,
      "epoch": 0.30896837739761535,
      "grad_norm": 0.41126278042793274,
      "kl": 0.732421875,
      "learning_rate": 2.99993002820392e-06,
      "loss": 0.0062,
      "reward": 1.1500000059604645,
      "reward_std": 0.12436701729893684,
      "rewards/accuracy_reward": 0.17500000447034836,
      "rewards/format_reward": 0.9750000089406967,
      "step": 298
    },
    {
      "completion_length": 37.85000038146973,
      "epoch": 0.31000518403317784,
      "grad_norm": 1.6783168315887451,
      "kl": 0.7119140625,
      "learning_rate": 2.999911442128473e-06,
      "loss": 0.0434,
      "reward": 1.2500000298023224,
      "reward_std": 0.1928323321044445,
      "rewards/accuracy_reward": 0.24999999813735485,
      "rewards/format_reward": 1.0,
      "step": 299
    },
    {
      "completion_length": 91.00000095367432,
      "epoch": 0.3110419906687403,
      "grad_norm": 0.8122076988220215,
      "kl": 0.76318359375,
      "learning_rate": 2.9998906695467587e-06,
      "loss": 0.1001,
      "reward": 1.475000023841858,
      "reward_std": 0.2361704222857952,
      "rewards/accuracy_reward": 0.5000000037252903,
      "rewards/format_reward": 0.9750000089406967,
      "step": 300
    },
    {
      "completion_length": 55.82500076293945,
      "epoch": 0.31207879730430277,
      "grad_norm": 0.7224457859992981,
      "kl": 0.87890625,
      "learning_rate": 2.9998677104890597e-06,
      "loss": 0.1167,
      "reward": 1.5750000476837158,
      "reward_std": 0.2920721098780632,
      "rewards/accuracy_reward": 0.6250000186264515,
      "rewards/format_reward": 0.9500000178813934,
      "step": 301
    },
    {
      "completion_length": 138.60000133514404,
      "epoch": 0.3131156039398652,
      "grad_norm": 0.742752730846405,
      "kl": 0.798828125,
      "learning_rate": 2.9998425649888448e-06,
      "loss": 0.1063,
      "reward": 1.0750000178813934,
      "reward_std": 0.18026872724294662,
      "rewards/accuracy_reward": 0.15000000037252903,
      "rewards/format_reward": 0.925000011920929,
      "step": 302
    },
    {
      "completion_length": 148.55000114440918,
      "epoch": 0.3141524105754277,
      "grad_norm": 1.1690900325775146,
      "kl": 0.955078125,
      "learning_rate": 2.9998152330827693e-06,
      "loss": 0.1856,
      "reward": 1.4000000357627869,
      "reward_std": 0.4723408482968807,
      "rewards/accuracy_reward": 0.5250000134110451,
      "rewards/format_reward": 0.8750000149011612,
      "step": 303
    },
    {
      "completion_length": 225.50000381469727,
      "epoch": 0.31518921721099014,
      "grad_norm": 0.7336009740829468,
      "kl": 0.8759765625,
      "learning_rate": 2.9997857148106767e-06,
      "loss": 0.2877,
      "reward": 1.0750000476837158,
      "reward_std": 0.3479737937450409,
      "rewards/accuracy_reward": 0.22500000149011612,
      "rewards/format_reward": 0.8500000238418579,
      "step": 304
    },
    {
      "completion_length": 199.55000400543213,
      "epoch": 0.31622602384655263,
      "grad_norm": 1.3255078792572021,
      "kl": 1.025390625,
      "learning_rate": 2.9997540102155977e-06,
      "loss": 0.2364,
      "reward": 1.3000000417232513,
      "reward_std": 0.4723408408463001,
      "rewards/accuracy_reward": 0.42500001192092896,
      "rewards/format_reward": 0.8750000149011612,
      "step": 305
    },
    {
      "completion_length": 237.2249984741211,
      "epoch": 0.31726283048211507,
      "grad_norm": 0.7050570845603943,
      "kl": 0.7607421875,
      "learning_rate": 2.9997201193437498e-06,
      "loss": 0.2609,
      "reward": 1.3750000596046448,
      "reward_std": 0.5481655970215797,
      "rewards/accuracy_reward": 0.550000011920929,
      "rewards/format_reward": 0.8250000178813934,
      "step": 306
    },
    {
      "completion_length": 232.12500858306885,
      "epoch": 0.31829963711767756,
      "grad_norm": 0.6234104037284851,
      "kl": 0.64306640625,
      "learning_rate": 2.9996840422445373e-06,
      "loss": 0.2367,
      "reward": 1.0250000208616257,
      "reward_std": 0.3804604709148407,
      "rewards/accuracy_reward": 0.15000000223517418,
      "rewards/format_reward": 0.8750000149011612,
      "step": 307
    },
    {
      "completion_length": 286.7750015258789,
      "epoch": 0.31933644375324,
      "grad_norm": 0.5603132247924805,
      "kl": 0.68310546875,
      "learning_rate": 2.9996457789705527e-06,
      "loss": 0.3039,
      "reward": 1.1500000208616257,
      "reward_std": 0.38409100100398064,
      "rewards/accuracy_reward": 0.2750000022351742,
      "rewards/format_reward": 0.8750000149011612,
      "step": 308
    },
    {
      "completion_length": 97.02500247955322,
      "epoch": 0.3203732503888025,
      "grad_norm": 0.44136732816696167,
      "kl": 0.67578125,
      "learning_rate": 2.9996053295775733e-06,
      "loss": 0.0828,
      "reward": 1.25,
      "reward_std": 0.11180339753627777,
      "rewards/accuracy_reward": 0.27500000037252903,
      "rewards/format_reward": 0.9750000089406967,
      "step": 309
    },
    {
      "completion_length": 253.27499961853027,
      "epoch": 0.321410057024365,
      "grad_norm": 0.6165421009063721,
      "kl": 0.64892578125,
      "learning_rate": 2.999562694124565e-06,
      "loss": 0.2532,
      "reward": 1.350000023841858,
      "reward_std": 0.347973819822073,
      "rewards/accuracy_reward": 0.47500000335276127,
      "rewards/format_reward": 0.8750000298023224,
      "step": 310
    },
    {
      "completion_length": 67.55000019073486,
      "epoch": 0.3224468636599274,
      "grad_norm": 0.5345252752304077,
      "kl": 0.552734375,
      "learning_rate": 2.999517872673681e-06,
      "loss": 0.0778,
      "reward": 1.5250000208616257,
      "reward_std": 0.16770509257912636,
      "rewards/accuracy_reward": 0.5750000029802322,
      "rewards/format_reward": 0.9500000178813934,
      "step": 311
    },
    {
      "completion_length": 140.20000171661377,
      "epoch": 0.3234836702954899,
      "grad_norm": 1.1492671966552734,
      "kl": 0.56787109375,
      "learning_rate": 2.9994708652902586e-06,
      "loss": 0.1224,
      "reward": 1.2000000029802322,
      "reward_std": 0.22360679507255554,
      "rewards/accuracy_reward": 0.25,
      "rewards/format_reward": 0.9500000178813934,
      "step": 312
    },
    {
      "completion_length": 95.85000228881836,
      "epoch": 0.32452047693105235,
      "grad_norm": 0.9709307551383972,
      "kl": 0.71728515625,
      "learning_rate": 2.999421672042824e-06,
      "loss": 0.0839,
      "reward": 1.449999988079071,
      "reward_std": 0.2920721210539341,
      "rewards/accuracy_reward": 0.4750000089406967,
      "rewards/format_reward": 0.9750000089406967,
      "step": 313
    },
    {
      "completion_length": 92.50000190734863,
      "epoch": 0.32555728356661484,
      "grad_norm": 0.989802896976471,
      "kl": 0.6923828125,
      "learning_rate": 2.999370293003089e-06,
      "loss": 0.0873,
      "reward": 1.4250000268220901,
      "reward_std": 0.18026872351765633,
      "rewards/accuracy_reward": 0.45000000298023224,
      "rewards/format_reward": 0.9750000089406967,
      "step": 314
    },
    {
      "completion_length": 140.47500038146973,
      "epoch": 0.3265940902021773,
      "grad_norm": 0.6137426495552063,
      "kl": 0.791015625,
      "learning_rate": 2.9993167282459508e-06,
      "loss": 0.1567,
      "reward": 1.5750000178813934,
      "reward_std": 0.3479738123714924,
      "rewards/accuracy_reward": 0.6250000149011612,
      "rewards/format_reward": 0.9500000178813934,
      "step": 315
    },
    {
      "completion_length": 105.0000057220459,
      "epoch": 0.32763089683773977,
      "grad_norm": 0.6631371974945068,
      "kl": 0.58154296875,
      "learning_rate": 2.9992609778494945e-06,
      "loss": 0.0668,
      "reward": 1.3250000178813934,
      "reward_std": 0.22360679507255554,
      "rewards/accuracy_reward": 0.37500000931322575,
      "rewards/format_reward": 0.9500000178813934,
      "step": 316
    },
    {
      "completion_length": 57.30000114440918,
      "epoch": 0.3286677034733022,
      "grad_norm": 0.542193591594696,
      "kl": 0.53125,
      "learning_rate": 2.999203041894991e-06,
      "loss": 0.0198,
      "reward": 1.475000023841858,
      "reward_std": 0.12436701729893684,
      "rewards/accuracy_reward": 0.4750000089406967,
      "rewards/format_reward": 1.0,
      "step": 317
    },
    {
      "completion_length": 110.09999942779541,
      "epoch": 0.3297045101088647,
      "grad_norm": 0.8033139705657959,
      "kl": 0.7060546875,
      "learning_rate": 2.999142920466896e-06,
      "loss": 0.0931,
      "reward": 1.3750000298023224,
      "reward_std": 0.3354102112352848,
      "rewards/accuracy_reward": 0.4250000026077032,
      "rewards/format_reward": 0.9500000029802322,
      "step": 318
    },
    {
      "completion_length": 155.02500247955322,
      "epoch": 0.33074131674442714,
      "grad_norm": 0.7720692753791809,
      "kl": 0.59521484375,
      "learning_rate": 2.999080613652853e-06,
      "loss": 0.102,
      "reward": 1.600000023841858,
      "reward_std": 0.25609345361590385,
      "rewards/accuracy_reward": 0.6500000208616257,
      "rewards/format_reward": 0.9500000178813934,
      "step": 319
    },
    {
      "completion_length": 125.42500495910645,
      "epoch": 0.33177812337998963,
      "grad_norm": 0.43371641635894775,
      "kl": 0.7421875,
      "learning_rate": 2.9990161215436888e-06,
      "loss": 0.1467,
      "reward": 1.0500000268220901,
      "reward_std": 0.22360678762197495,
      "rewards/accuracy_reward": 0.10000000335276127,
      "rewards/format_reward": 0.9500000178813934,
      "step": 320
    },
    {
      "completion_length": 63.07500076293945,
      "epoch": 0.3328149300155521,
      "grad_norm": 1.1089128255844116,
      "kl": 0.56591796875,
      "learning_rate": 2.9989494442334186e-06,
      "loss": 0.0028,
      "reward": 1.375,
      "reward_std": 0.27228759974241257,
      "rewards/accuracy_reward": 0.4000000134110451,
      "rewards/format_reward": 0.9750000089406967,
      "step": 321
    },
    {
      "completion_length": 69.57500171661377,
      "epoch": 0.33385173665111456,
      "grad_norm": 0.5004400610923767,
      "kl": 0.697265625,
      "learning_rate": 2.998880581819241e-06,
      "loss": 0.0053,
      "reward": 1.5250000357627869,
      "reward_std": 0.13693063706159592,
      "rewards/accuracy_reward": 0.5250000059604645,
      "rewards/format_reward": 1.0,
      "step": 322
    },
    {
      "completion_length": 85.10000228881836,
      "epoch": 0.33488854328667705,
      "grad_norm": 0.7260141968727112,
      "kl": 0.4267578125,
      "learning_rate": 2.9988095344015403e-06,
      "loss": 0.0783,
      "reward": 1.5499999821186066,
      "reward_std": 0.279508501291275,
      "rewards/accuracy_reward": 0.6000000089406967,
      "rewards/format_reward": 0.9500000178813934,
      "step": 323
    },
    {
      "completion_length": 179.37500381469727,
      "epoch": 0.3359253499222395,
      "grad_norm": 0.7410564422607422,
      "kl": 0.70703125,
      "learning_rate": 2.9987363020838867e-06,
      "loss": 0.1431,
      "reward": 1.25,
      "reward_std": 0.3856646940112114,
      "rewards/accuracy_reward": 0.3250000048428774,
      "rewards/format_reward": 0.925000011920929,
      "step": 324
    },
    {
      "completion_length": 128.05000114440918,
      "epoch": 0.336962156557802,
      "grad_norm": 0.2647928297519684,
      "kl": 0.49267578125,
      "learning_rate": 2.9986608849730356e-06,
      "loss": 0.0786,
      "reward": 1.2500000298023224,
      "reward_std": 0.18026870489120483,
      "rewards/accuracy_reward": 0.2750000022351742,
      "rewards/format_reward": 0.9750000089406967,
      "step": 325
    },
    {
      "completion_length": 139.60000228881836,
      "epoch": 0.3379989631933644,
      "grad_norm": 0.6439674496650696,
      "kl": 0.62255859375,
      "learning_rate": 2.998583283178926e-06,
      "loss": 0.113,
      "reward": 1.3750000298023224,
      "reward_std": 0.31733787432312965,
      "rewards/accuracy_reward": 0.4250000100582838,
      "rewards/format_reward": 0.9500000178813934,
      "step": 326
    },
    {
      "completion_length": 122.85000038146973,
      "epoch": 0.3390357698289269,
      "grad_norm": 0.4776754677295685,
      "kl": 0.53173828125,
      "learning_rate": 2.9985034968146832e-06,
      "loss": 0.0487,
      "reward": 1.7000000178813934,
      "reward_std": 0.22360680624842644,
      "rewards/accuracy_reward": 0.7250000089406967,
      "rewards/format_reward": 0.9750000089406967,
      "step": 327
    },
    {
      "completion_length": 324.1000061035156,
      "epoch": 0.34007257646448935,
      "grad_norm": 0.7620232701301575,
      "kl": 0.4736328125,
      "learning_rate": 2.998421525996616e-06,
      "loss": 0.2654,
      "reward": 1.2750000357627869,
      "reward_std": 0.5517961122095585,
      "rewards/accuracy_reward": 0.4000000022351742,
      "rewards/format_reward": 0.8750000298023224,
      "step": 328
    },
    {
      "completion_length": 468.9500198364258,
      "epoch": 0.34110938310005184,
      "grad_norm": 0.35654211044311523,
      "kl": 0.5458984375,
      "learning_rate": 2.9983373708442182e-06,
      "loss": 0.3329,
      "reward": 1.3500000089406967,
      "reward_std": 0.4958944171667099,
      "rewards/accuracy_reward": 0.5750000104308128,
      "rewards/format_reward": 0.7750000059604645,
      "step": 329
    },
    {
      "completion_length": 370.1750030517578,
      "epoch": 0.3421461897356143,
      "grad_norm": 0.5573723316192627,
      "kl": 0.564453125,
      "learning_rate": 2.9982510314801665e-06,
      "loss": 0.2937,
      "reward": 1.2500000149011612,
      "reward_std": 0.6527480855584145,
      "rewards/accuracy_reward": 0.4000000078231096,
      "rewards/format_reward": 0.8500000238418579,
      "step": 330
    },
    {
      "completion_length": 277.975004196167,
      "epoch": 0.3431829963711768,
      "grad_norm": 0.5659462213516235,
      "kl": 0.5029296875,
      "learning_rate": 2.998162508030324e-06,
      "loss": 0.2449,
      "reward": 1.5000000298023224,
      "reward_std": 0.5031153149902821,
      "rewards/accuracy_reward": 0.6000000014901161,
      "rewards/format_reward": 0.9000000208616257,
      "step": 331
    },
    {
      "completion_length": 175.72500610351562,
      "epoch": 0.34421980300673927,
      "grad_norm": 0.402981698513031,
      "kl": 0.49267578125,
      "learning_rate": 2.998071800623736e-06,
      "loss": 0.132,
      "reward": 1.550000011920929,
      "reward_std": 0.15685366839170456,
      "rewards/accuracy_reward": 0.6000000089406967,
      "rewards/format_reward": 0.9500000178813934,
      "step": 332
    },
    {
      "completion_length": 442.42501068115234,
      "epoch": 0.3452566096423017,
      "grad_norm": 0.40613406896591187,
      "kl": 0.59130859375,
      "learning_rate": 2.997978909392631e-06,
      "loss": 0.3856,
      "reward": 1.3750000298023224,
      "reward_std": 0.7138539552688599,
      "rewards/accuracy_reward": 0.6000000089406967,
      "rewards/format_reward": 0.7750000059604645,
      "step": 333
    },
    {
      "completion_length": 437.3250045776367,
      "epoch": 0.3462934162778642,
      "grad_norm": 0.4869440793991089,
      "kl": 0.6865234375,
      "learning_rate": 2.997883834472423e-06,
      "loss": 0.2613,
      "reward": 1.1000000089406967,
      "reward_std": 0.596707858145237,
      "rewards/accuracy_reward": 0.3250000048428774,
      "rewards/format_reward": 0.7750000208616257,
      "step": 334
    },
    {
      "completion_length": 175.32500648498535,
      "epoch": 0.34733022291342663,
      "grad_norm": 0.45390427112579346,
      "kl": 0.51025390625,
      "learning_rate": 2.997786576001708e-06,
      "loss": 0.1233,
      "reward": 1.600000023841858,
      "reward_std": 0.3245587684214115,
      "rewards/accuracy_reward": 0.6500000134110451,
      "rewards/format_reward": 0.9500000178813934,
      "step": 335
    },
    {
      "completion_length": 263.725004196167,
      "epoch": 0.3483670295489891,
      "grad_norm": 0.42588937282562256,
      "kl": 0.72509765625,
      "learning_rate": 2.9976871341222644e-06,
      "loss": 0.2371,
      "reward": 1.3250000178813934,
      "reward_std": 0.3913118802011013,
      "rewards/accuracy_reward": 0.42500001192092896,
      "rewards/format_reward": 0.9000000208616257,
      "step": 336
    },
    {
      "completion_length": 228.55000686645508,
      "epoch": 0.34940383618455156,
      "grad_norm": 0.6435961127281189,
      "kl": 0.6455078125,
      "learning_rate": 2.997585508979055e-06,
      "loss": 0.1453,
      "reward": 1.425000011920929,
      "reward_std": 0.3479738272726536,
      "rewards/accuracy_reward": 0.5250000059604645,
      "rewards/format_reward": 0.9000000059604645,
      "step": 337
    },
    {
      "completion_length": 381.4500026702881,
      "epoch": 0.35044064282011406,
      "grad_norm": 0.48273399472236633,
      "kl": 0.6640625,
      "learning_rate": 2.9974817007202243e-06,
      "loss": 0.2484,
      "reward": 1.350000038743019,
      "reward_std": 0.48553743213415146,
      "rewards/accuracy_reward": 0.5250000096857548,
      "rewards/format_reward": 0.8250000029802322,
      "step": 338
    },
    {
      "completion_length": 181.50000381469727,
      "epoch": 0.3514774494556765,
      "grad_norm": 0.4054751694202423,
      "kl": 0.6533203125,
      "learning_rate": 2.9973757094970992e-06,
      "loss": 0.1321,
      "reward": 1.050000011920929,
      "reward_std": 0.2812207043170929,
      "rewards/accuracy_reward": 0.15000000223517418,
      "rewards/format_reward": 0.9000000059604645,
      "step": 339
    },
    {
      "completion_length": 564.7500076293945,
      "epoch": 0.352514256091239,
      "grad_norm": 0.4397445321083069,
      "kl": 0.755859375,
      "learning_rate": 2.9972675354641895e-06,
      "loss": 0.2461,
      "reward": 1.0500000268220901,
      "reward_std": 0.49746809527277946,
      "rewards/accuracy_reward": 0.3250000048428774,
      "rewards/format_reward": 0.7250000089406967,
      "step": 340
    },
    {
      "completion_length": 295.7500057220459,
      "epoch": 0.3535510627268014,
      "grad_norm": 0.6863256096839905,
      "kl": 0.6005859375,
      "learning_rate": 2.9971571787791866e-06,
      "loss": 0.0904,
      "reward": 1.550000011920929,
      "reward_std": 0.5533697679638863,
      "rewards/accuracy_reward": 0.675000011920929,
      "rewards/format_reward": 0.8750000149011612,
      "step": 341
    },
    {
      "completion_length": 529.0750045776367,
      "epoch": 0.3545878693623639,
      "grad_norm": 0.5725196003913879,
      "kl": 0.5673828125,
      "learning_rate": 2.9970446396029643e-06,
      "loss": 0.3386,
      "reward": 0.9500000178813934,
      "reward_std": 0.5535083040595055,
      "rewards/accuracy_reward": 0.1750000026077032,
      "rewards/format_reward": 0.7750000208616257,
      "step": 342
    },
    {
      "completion_length": 258.2249984741211,
      "epoch": 0.3556246759979264,
      "grad_norm": 0.4096214771270752,
      "kl": 0.51904296875,
      "learning_rate": 2.9969299180995763e-06,
      "loss": 0.2192,
      "reward": 1.2750000059604645,
      "reward_std": 0.3913118839263916,
      "rewards/accuracy_reward": 0.4000000059604645,
      "rewards/format_reward": 0.875,
      "step": 343
    },
    {
      "completion_length": 363.0500030517578,
      "epoch": 0.35666148263348885,
      "grad_norm": 0.6106461882591248,
      "kl": 0.5458984375,
      "learning_rate": 2.996813014436259e-06,
      "loss": 0.2965,
      "reward": 1.4000000357627869,
      "reward_std": 0.6172638833522797,
      "rewards/accuracy_reward": 0.5750000141561031,
      "rewards/format_reward": 0.8250000178813934,
      "step": 344
    },
    {
      "completion_length": 123.2500057220459,
      "epoch": 0.35769828926905134,
      "grad_norm": 0.5532033443450928,
      "kl": 0.46533203125,
      "learning_rate": 2.9966939287834297e-06,
      "loss": -0.0141,
      "reward": 1.5,
      "reward_std": 0.3731010667979717,
      "rewards/accuracy_reward": 0.5250000059604645,
      "rewards/format_reward": 0.9750000089406967,
      "step": 345
    },
    {
      "completion_length": 330.5750045776367,
      "epoch": 0.3587350959046138,
      "grad_norm": 0.5643976330757141,
      "kl": 0.4521484375,
      "learning_rate": 2.9965726613146864e-06,
      "loss": 0.2691,
      "reward": 0.9000000208616257,
      "reward_std": 0.5625799112021923,
      "rewards/accuracy_reward": 0.1250000037252903,
      "rewards/format_reward": 0.7750000059604645,
      "step": 346
    },
    {
      "completion_length": 296.6499996185303,
      "epoch": 0.35977190254017627,
      "grad_norm": 0.5962963104248047,
      "kl": 0.5673828125,
      "learning_rate": 2.9964492122068074e-06,
      "loss": 0.1955,
      "reward": 1.2750000357627869,
      "reward_std": 0.5660719126462936,
      "rewards/accuracy_reward": 0.4000000059604645,
      "rewards/format_reward": 0.875,
      "step": 347
    },
    {
      "completion_length": 210.375,
      "epoch": 0.3608087091757387,
      "grad_norm": 0.4225082993507385,
      "kl": 0.61572265625,
      "learning_rate": 2.9963235816397516e-06,
      "loss": 0.1628,
      "reward": 1.350000023841858,
      "reward_std": 0.29270509257912636,
      "rewards/accuracy_reward": 0.4250000100582838,
      "rewards/format_reward": 0.925000011920929,
      "step": 348
    },
    {
      "completion_length": 552.0000076293945,
      "epoch": 0.3618455158113012,
      "grad_norm": 0.7490342855453491,
      "kl": 0.5478515625,
      "learning_rate": 2.996195769796658e-06,
      "loss": 0.2469,
      "reward": 1.1250000447034836,
      "reward_std": 0.5973408445715904,
      "rewards/accuracy_reward": 0.3500000052154064,
      "rewards/format_reward": 0.7750000208616257,
      "step": 349
    },
    {
      "completion_length": 236.82500839233398,
      "epoch": 0.36288232244686364,
      "grad_norm": 0.4927626848220825,
      "kl": 0.4287109375,
      "learning_rate": 2.996065776863845e-06,
      "loss": 0.0864,
      "reward": 1.475000023841858,
      "reward_std": 0.3966546319425106,
      "rewards/accuracy_reward": 0.5500000156462193,
      "rewards/format_reward": 0.925000011920929,
      "step": 350
    },
    {
      "completion_length": 193.45000457763672,
      "epoch": 0.36391912908242613,
      "grad_norm": 0.5020635724067688,
      "kl": 0.38720703125,
      "learning_rate": 2.9959336030308104e-06,
      "loss": 0.0558,
      "reward": 1.2500000298023224,
      "reward_std": 0.3299014940857887,
      "rewards/accuracy_reward": 0.30000000819563866,
      "rewards/format_reward": 0.9500000178813934,
      "step": 351
    },
    {
      "completion_length": 222.27500534057617,
      "epoch": 0.3649559357179886,
      "grad_norm": 0.4954478442668915,
      "kl": 0.48486328125,
      "learning_rate": 2.995799248490232e-06,
      "loss": 0.1715,
      "reward": 1.2000000178813934,
      "reward_std": 0.36053742095828056,
      "rewards/accuracy_reward": 0.27500000409781933,
      "rewards/format_reward": 0.9250000268220901,
      "step": 352
    },
    {
      "completion_length": 213.42500686645508,
      "epoch": 0.36599274235355106,
      "grad_norm": 0.42243900895118713,
      "kl": 0.34814453125,
      "learning_rate": 2.995662713437966e-06,
      "loss": 0.1177,
      "reward": 1.5500000417232513,
      "reward_std": 0.4290027320384979,
      "rewards/accuracy_reward": 0.6000000089406967,
      "rewards/format_reward": 0.9500000029802322,
      "step": 353
    },
    {
      "completion_length": 118.6500015258789,
      "epoch": 0.36702954898911355,
      "grad_norm": 0.5565142035484314,
      "kl": 0.290283203125,
      "learning_rate": 2.995523998073047e-06,
      "loss": 0.0399,
      "reward": 1.675000011920929,
      "reward_std": 0.31719936057925224,
      "rewards/accuracy_reward": 0.6750000044703484,
      "rewards/format_reward": 1.0,
      "step": 354
    },
    {
      "completion_length": 167.67500495910645,
      "epoch": 0.368066355624676,
      "grad_norm": 0.425595223903656,
      "kl": 0.333984375,
      "learning_rate": 2.9953831025976885e-06,
      "loss": 0.0722,
      "reward": 1.5750000178813934,
      "reward_std": 0.24873404204845428,
      "rewards/accuracy_reward": 0.5999999940395355,
      "rewards/format_reward": 0.9750000089406967,
      "step": 355
    },
    {
      "completion_length": 263.0250053405762,
      "epoch": 0.3691031622602385,
      "grad_norm": 0.34887924790382385,
      "kl": 0.301025390625,
      "learning_rate": 2.9952400272172815e-06,
      "loss": 0.1951,
      "reward": 1.4250000268220901,
      "reward_std": 0.3479738160967827,
      "rewards/accuracy_reward": 0.5000000074505806,
      "rewards/format_reward": 0.925000011920929,
      "step": 356
    },
    {
      "completion_length": 161.350004196167,
      "epoch": 0.3701399688958009,
      "grad_norm": 0.5152186155319214,
      "kl": 0.34130859375,
      "learning_rate": 2.995094772140396e-06,
      "loss": 0.0896,
      "reward": 1.4000000357627869,
      "reward_std": 0.2920721136033535,
      "rewards/accuracy_reward": 0.4249999988824129,
      "rewards/format_reward": 0.9750000089406967,
      "step": 357
    },
    {
      "completion_length": 126.57500076293945,
      "epoch": 0.3711767755313634,
      "grad_norm": 0.5196745991706848,
      "kl": 0.33740234375,
      "learning_rate": 2.9949473375787776e-06,
      "loss": -0.0047,
      "reward": 1.2750000059604645,
      "reward_std": 0.16770508512854576,
      "rewards/accuracy_reward": 0.3000000063329935,
      "rewards/format_reward": 0.9750000089406967,
      "step": 358
    },
    {
      "completion_length": 160.05000686645508,
      "epoch": 0.37221358216692585,
      "grad_norm": 0.6606730222702026,
      "kl": 0.4091796875,
      "learning_rate": 2.994797723747351e-06,
      "loss": 0.1742,
      "reward": 1.5750000178813934,
      "reward_std": 0.4363621734082699,
      "rewards/accuracy_reward": 0.6250000149011612,
      "rewards/format_reward": 0.9500000178813934,
      "step": 359
    },
    {
      "completion_length": 119.82500267028809,
      "epoch": 0.37325038880248834,
      "grad_norm": 0.3371819257736206,
      "kl": 0.364990234375,
      "learning_rate": 2.9946459308642155e-06,
      "loss": -0.0122,
      "reward": 1.6250000298023224,
      "reward_std": 0.13693063706159592,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 360
    },
    {
      "completion_length": 221.07500076293945,
      "epoch": 0.3742871954380508,
      "grad_norm": 0.536543607711792,
      "kl": 0.4248046875,
      "learning_rate": 2.9944919591506495e-06,
      "loss": 0.1191,
      "reward": 1.1500000208616257,
      "reward_std": 0.25609344989061356,
      "rewards/accuracy_reward": 0.20000000670552254,
      "rewards/format_reward": 0.9500000029802322,
      "step": 361
    },
    {
      "completion_length": 203.3250026702881,
      "epoch": 0.37532400207361327,
      "grad_norm": 0.3392835855484009,
      "kl": 0.365234375,
      "learning_rate": 2.994335808831106e-06,
      "loss": 0.0678,
      "reward": 1.5750000178813934,
      "reward_std": 0.19346532225608826,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 0.9500000029802322,
      "step": 362
    },
    {
      "completion_length": 148.77499961853027,
      "epoch": 0.37636080870917576,
      "grad_norm": 0.15861853957176208,
      "kl": 0.36328125,
      "learning_rate": 2.994177480133214e-06,
      "loss": 0.0677,
      "reward": 1.3499999940395355,
      "reward_std": 0.055901702493429184,
      "rewards/accuracy_reward": 0.375,
      "rewards/format_reward": 0.9750000089406967,
      "step": 363
    },
    {
      "completion_length": 403.47501373291016,
      "epoch": 0.3773976153447382,
      "grad_norm": 0.5314847230911255,
      "kl": 0.5068359375,
      "learning_rate": 2.994016973287778e-06,
      "loss": 0.2355,
      "reward": 1.4000000059604645,
      "reward_std": 0.5173911042511463,
      "rewards/accuracy_reward": 0.5500000156462193,
      "rewards/format_reward": 0.8500000238418579,
      "step": 364
    },
    {
      "completion_length": 160.77500534057617,
      "epoch": 0.3784344219803007,
      "grad_norm": 0.3340126574039459,
      "kl": 0.288330078125,
      "learning_rate": 2.9938542885287786e-06,
      "loss": 0.0289,
      "reward": 1.350000023841858,
      "reward_std": 0.22360680624842644,
      "rewards/accuracy_reward": 0.3750000074505806,
      "rewards/format_reward": 0.9750000089406967,
      "step": 365
    },
    {
      "completion_length": 215.65000534057617,
      "epoch": 0.37947122861586313,
      "grad_norm": 0.35049688816070557,
      "kl": 0.376953125,
      "learning_rate": 2.99368942609337e-06,
      "loss": 0.1184,
      "reward": 1.3000000268220901,
      "reward_std": 0.22894952073693275,
      "rewards/accuracy_reward": 0.3499999977648258,
      "rewards/format_reward": 0.9500000178813934,
      "step": 366
    },
    {
      "completion_length": 192.12500381469727,
      "epoch": 0.3805080352514256,
      "grad_norm": 0.4274624288082123,
      "kl": 0.3583984375,
      "learning_rate": 2.993522386221882e-06,
      "loss": -0.0248,
      "reward": 1.5999999940395355,
      "reward_std": 0.24873404949903488,
      "rewards/accuracy_reward": 0.6500000134110451,
      "rewards/format_reward": 0.9500000029802322,
      "step": 367
    },
    {
      "completion_length": 148.375,
      "epoch": 0.38154484188698806,
      "grad_norm": 0.6505801677703857,
      "kl": 0.35107421875,
      "learning_rate": 2.9933531691578178e-06,
      "loss": 0.026,
      "reward": 1.550000011920929,
      "reward_std": 0.26865705102682114,
      "rewards/accuracy_reward": 0.575000012293458,
      "rewards/format_reward": 0.9750000089406967,
      "step": 368
    },
    {
      "completion_length": 293.8000030517578,
      "epoch": 0.38258164852255055,
      "grad_norm": 0.30225127935409546,
      "kl": 0.44970703125,
      "learning_rate": 2.9931817751478547e-06,
      "loss": 0.2183,
      "reward": 1.4250000268220901,
      "reward_std": 0.25609344989061356,
      "rewards/accuracy_reward": 0.525000000372529,
      "rewards/format_reward": 0.9000000059604645,
      "step": 369
    },
    {
      "completion_length": 151.32499885559082,
      "epoch": 0.383618455158113,
      "grad_norm": 0.5463283658027649,
      "kl": 0.296875,
      "learning_rate": 2.9930082044418442e-06,
      "loss": 0.0759,
      "reward": 1.350000023841858,
      "reward_std": 0.24873404577374458,
      "rewards/accuracy_reward": 0.3750000074505806,
      "rewards/format_reward": 0.9750000089406967,
      "step": 370
    },
    {
      "completion_length": 120.22500228881836,
      "epoch": 0.3846552617936755,
      "grad_norm": 0.6592673063278198,
      "kl": 0.37451171875,
      "learning_rate": 2.99283245729281e-06,
      "loss": 0.083,
      "reward": 1.4000000357627869,
      "reward_std": 0.37310105934739113,
      "rewards/accuracy_reward": 0.4000000152736902,
      "rewards/format_reward": 1.0,
      "step": 371
    },
    {
      "completion_length": 150.79999923706055,
      "epoch": 0.3856920684292379,
      "grad_norm": 0.5108554363250732,
      "kl": 0.326171875,
      "learning_rate": 2.9926545339569476e-06,
      "loss": 0.0444,
      "reward": 1.4500000178813934,
      "reward_std": 0.30463575199246407,
      "rewards/accuracy_reward": 0.4750000089406967,
      "rewards/format_reward": 0.9750000089406967,
      "step": 372
    },
    {
      "completion_length": 87.57500267028809,
      "epoch": 0.3867288750648004,
      "grad_norm": 0.5240278840065002,
      "kl": 0.3642578125,
      "learning_rate": 2.992474434693627e-06,
      "loss": -0.0313,
      "reward": 1.600000023841858,
      "reward_std": 0.12436701729893684,
      "rewards/accuracy_reward": 0.6000000033527613,
      "rewards/format_reward": 1.0,
      "step": 373
    },
    {
      "completion_length": 108.4000015258789,
      "epoch": 0.3877656817003629,
      "grad_norm": 0.46822282671928406,
      "kl": 0.33447265625,
      "learning_rate": 2.9922921597653893e-06,
      "loss": -0.0006,
      "reward": 1.5750000178813934,
      "reward_std": 0.1928323470056057,
      "rewards/accuracy_reward": 0.5750000104308128,
      "rewards/format_reward": 1.0,
      "step": 374
    },
    {
      "completion_length": 137.70000457763672,
      "epoch": 0.38880248833592534,
      "grad_norm": 0.554831326007843,
      "kl": 0.4365234375,
      "learning_rate": 2.9921077094379466e-06,
      "loss": 0.0776,
      "reward": 1.375,
      "reward_std": 0.2812207005918026,
      "rewards/accuracy_reward": 0.4000000078231096,
      "rewards/format_reward": 0.9750000089406967,
      "step": 375
    },
    {
      "completion_length": 239.45000839233398,
      "epoch": 0.38983929497148784,
      "grad_norm": 0.5239160060882568,
      "kl": 0.412841796875,
      "learning_rate": 2.9919210839801827e-06,
      "loss": 0.1685,
      "reward": 1.475000023841858,
      "reward_std": 0.452556349337101,
      "rewards/accuracy_reward": 0.5500000044703484,
      "rewards/format_reward": 0.925000011920929,
      "step": 376
    },
    {
      "completion_length": 87.90000343322754,
      "epoch": 0.3908761016070503,
      "grad_norm": 0.6395469307899475,
      "kl": 0.35498046875,
      "learning_rate": 2.991732283664152e-06,
      "loss": 0.0022,
      "reward": 1.5250000357627869,
      "reward_std": 0.3046357184648514,
      "rewards/accuracy_reward": 0.5249999985098839,
      "rewards/format_reward": 1.0,
      "step": 377
    },
    {
      "completion_length": 200.35000038146973,
      "epoch": 0.39191290824261277,
      "grad_norm": 0.6615502834320068,
      "kl": 0.3955078125,
      "learning_rate": 2.99154130876508e-06,
      "loss": 0.1602,
      "reward": 1.425000011920929,
      "reward_std": 0.504966028034687,
      "rewards/accuracy_reward": 0.5250000152736902,
      "rewards/format_reward": 0.9000000357627869,
      "step": 378
    },
    {
      "completion_length": 243.87500190734863,
      "epoch": 0.3929497148781752,
      "grad_norm": 0.588063657283783,
      "kl": 0.41064453125,
      "learning_rate": 2.9913481595613613e-06,
      "loss": 0.1196,
      "reward": 1.2500000149011612,
      "reward_std": 0.4181513413786888,
      "rewards/accuracy_reward": 0.35000000335276127,
      "rewards/format_reward": 0.9000000059604645,
      "step": 379
    },
    {
      "completion_length": 92.82500076293945,
      "epoch": 0.3939865215137377,
      "grad_norm": 0.3841590881347656,
      "kl": 0.41552734375,
      "learning_rate": 2.99115283633456e-06,
      "loss": 0.022,
      "reward": 1.7000000178813934,
      "reward_std": 0.12436702474951744,
      "rewards/accuracy_reward": 0.7000000067055225,
      "rewards/format_reward": 1.0,
      "step": 380
    },
    {
      "completion_length": 167.8250026702881,
      "epoch": 0.39502332814930013,
      "grad_norm": 0.6007952094078064,
      "kl": 0.5205078125,
      "learning_rate": 2.9909553393694107e-06,
      "loss": 0.1088,
      "reward": 1.2999999970197678,
      "reward_std": 0.3245587833225727,
      "rewards/accuracy_reward": 0.40000000037252903,
      "rewards/format_reward": 0.9000000059604645,
      "step": 381
    },
    {
      "completion_length": 150.350004196167,
      "epoch": 0.3960601347848626,
      "grad_norm": 0.4360502064228058,
      "kl": 0.29931640625,
      "learning_rate": 2.9907556689538158e-06,
      "loss": 0.0512,
      "reward": 1.4500000178813934,
      "reward_std": 0.22894952446222305,
      "rewards/accuracy_reward": 0.4749999940395355,
      "rewards/format_reward": 0.9750000089406967,
      "step": 382
    },
    {
      "completion_length": 145.3750057220459,
      "epoch": 0.39709694142042506,
      "grad_norm": 0.7903898358345032,
      "kl": 0.355712890625,
      "learning_rate": 2.990553825378846e-06,
      "loss": 0.127,
      "reward": 1.6250000298023224,
      "reward_std": 0.41643914207816124,
      "rewards/accuracy_reward": 0.6500000134110451,
      "rewards/format_reward": 0.9750000089406967,
      "step": 383
    },
    {
      "completion_length": 194.225004196167,
      "epoch": 0.39813374805598756,
      "grad_norm": 0.7693355083465576,
      "kl": 0.4150390625,
      "learning_rate": 2.99034980893874e-06,
      "loss": 0.0364,
      "reward": 1.7000000476837158,
      "reward_std": 0.3479738086462021,
      "rewards/accuracy_reward": 0.7750000059604645,
      "rewards/format_reward": 0.925000011920929,
      "step": 384
    },
    {
      "completion_length": 145.20000076293945,
      "epoch": 0.39917055469155005,
      "grad_norm": 0.5979889631271362,
      "kl": 0.472900390625,
      "learning_rate": 2.9901436199309044e-06,
      "loss": 0.0716,
      "reward": 1.7000000178813934,
      "reward_std": 0.30463574081659317,
      "rewards/accuracy_reward": 0.7250000089406967,
      "rewards/format_reward": 0.9750000089406967,
      "step": 385
    },
    {
      "completion_length": 244.1250114440918,
      "epoch": 0.4002073613271125,
      "grad_norm": 0.4943735897541046,
      "kl": 0.5654296875,
      "learning_rate": 2.9899352586559133e-06,
      "loss": 0.1302,
      "reward": 1.2000000476837158,
      "reward_std": 0.3856646865606308,
      "rewards/accuracy_reward": 0.2750000059604645,
      "rewards/format_reward": 0.925000011920929,
      "step": 386
    },
    {
      "completion_length": 99.10000228881836,
      "epoch": 0.401244167962675,
      "grad_norm": 0.41970863938331604,
      "kl": 0.36328125,
      "learning_rate": 2.9897247254175052e-06,
      "loss": -0.0189,
      "reward": 1.5750000178813934,
      "reward_std": 0.12436701729893684,
      "rewards/accuracy_reward": 0.5749999973922968,
      "rewards/format_reward": 1.0,
      "step": 387
    },
    {
      "completion_length": 187.52499961853027,
      "epoch": 0.4022809745982374,
      "grad_norm": 0.3286798894405365,
      "kl": 0.505859375,
      "learning_rate": 2.9895120205225883e-06,
      "loss": 0.1248,
      "reward": 1.175000011920929,
      "reward_std": 0.16770510748028755,
      "rewards/accuracy_reward": 0.22500000894069672,
      "rewards/format_reward": 0.9500000178813934,
      "step": 388
    },
    {
      "completion_length": 209.52500534057617,
      "epoch": 0.4033177812337999,
      "grad_norm": 0.5088163018226624,
      "kl": 0.3583984375,
      "learning_rate": 2.9892971442812333e-06,
      "loss": 0.1461,
      "reward": 1.2500000298023224,
      "reward_std": 0.31719937175512314,
      "rewards/accuracy_reward": 0.29999999701976776,
      "rewards/format_reward": 0.9500000178813934,
      "step": 389
    },
    {
      "completion_length": 158.02499961853027,
      "epoch": 0.40435458786936235,
      "grad_norm": 0.3768276274204254,
      "kl": 0.33251953125,
      "learning_rate": 2.989080097006678e-06,
      "loss": 0.0693,
      "reward": 1.2999999970197678,
      "reward_std": 0.16770510748028755,
      "rewards/accuracy_reward": 0.32500000298023224,
      "rewards/format_reward": 0.9750000089406967,
      "step": 390
    },
    {
      "completion_length": 263.57500076293945,
      "epoch": 0.40539139450492484,
      "grad_norm": 12.056117057800293,
      "kl": 1.38525390625,
      "learning_rate": 2.988860879015324e-06,
      "loss": 0.2372,
      "reward": 1.475000023841858,
      "reward_std": 0.4363621547818184,
      "rewards/accuracy_reward": 0.5500000156462193,
      "rewards/format_reward": 0.925000011920929,
      "step": 391
    },
    {
      "completion_length": 165.475004196167,
      "epoch": 0.4064282011404873,
      "grad_norm": 0.36441394686698914,
      "kl": 0.35595703125,
      "learning_rate": 2.9886394906267387e-06,
      "loss": 0.0168,
      "reward": 1.25,
      "reward_std": 0.11180339753627777,
      "rewards/accuracy_reward": 0.2750000022351742,
      "rewards/format_reward": 0.9750000089406967,
      "step": 392
    },
    {
      "completion_length": 254.17500495910645,
      "epoch": 0.40746500777604977,
      "grad_norm": 0.32492274045944214,
      "kl": 0.48095703125,
      "learning_rate": 2.988415932163652e-06,
      "loss": 0.128,
      "reward": 1.125,
      "reward_std": 0.1928323395550251,
      "rewards/accuracy_reward": 0.20000000298023224,
      "rewards/format_reward": 0.925000011920929,
      "step": 393
    },
    {
      "completion_length": 247.7250099182129,
      "epoch": 0.4085018144116122,
      "grad_norm": 425.0500183105469,
      "kl": 15.10888671875,
      "learning_rate": 2.988190203951958e-06,
      "loss": 1.26,
      "reward": 1.4750000536441803,
      "reward_std": 0.5084580183029175,
      "rewards/accuracy_reward": 0.550000011920929,
      "rewards/format_reward": 0.9250000268220901,
      "step": 394
    },
    {
      "completion_length": 204.92500114440918,
      "epoch": 0.4095386210471747,
      "grad_norm": 0.4983512759208679,
      "kl": 0.404052734375,
      "learning_rate": 2.9879623063207136e-06,
      "loss": 0.0576,
      "reward": 1.4250000417232513,
      "reward_std": 0.3354102037847042,
      "rewards/accuracy_reward": 0.47500001080334187,
      "rewards/format_reward": 0.9500000178813934,
      "step": 395
    },
    {
      "completion_length": 252.95000648498535,
      "epoch": 0.4105754276827372,
      "grad_norm": 0.6655735373497009,
      "kl": 0.510986328125,
      "learning_rate": 2.987732239602138e-06,
      "loss": 0.059,
      "reward": 1.2499999850988388,
      "reward_std": 0.26129766926169395,
      "rewards/accuracy_reward": 0.32500001043081284,
      "rewards/format_reward": 0.9249999970197678,
      "step": 396
    },
    {
      "completion_length": 258.30000495910645,
      "epoch": 0.41161223431829963,
      "grad_norm": 17.00373077392578,
      "kl": 0.52880859375,
      "learning_rate": 2.9875000041316126e-06,
      "loss": 0.2363,
      "reward": 1.5500000417232513,
      "reward_std": 0.46511994302272797,
      "rewards/accuracy_reward": 0.6250000037252903,
      "rewards/format_reward": 0.9250000268220901,
      "step": 397
    },
    {
      "completion_length": 305.8000087738037,
      "epoch": 0.4126490409538621,
      "grad_norm": 5.655200004577637,
      "kl": 1.62890625,
      "learning_rate": 2.98726560024768e-06,
      "loss": 0.3134,
      "reward": 1.475000023841858,
      "reward_std": 0.5571388304233551,
      "rewards/accuracy_reward": 0.600000012665987,
      "rewards/format_reward": 0.8750000149011612,
      "step": 398
    },
    {
      "completion_length": 186.90000343322754,
      "epoch": 0.41368584758942456,
      "grad_norm": 67.16045379638672,
      "kl": 10.04833984375,
      "learning_rate": 2.987029028292045e-06,
      "loss": 0.84,
      "reward": 1.3000000268220901,
      "reward_std": 0.3245587907731533,
      "rewards/accuracy_reward": 0.3499999977648258,
      "rewards/format_reward": 0.9500000029802322,
      "step": 399
    },
    {
      "completion_length": 168.5250015258789,
      "epoch": 0.41472265422498705,
      "grad_norm": 17.609403610229492,
      "kl": 3.233154296875,
      "learning_rate": 2.986790288609571e-06,
      "loss": 0.265,
      "reward": 1.6250000298023224,
      "reward_std": 0.3533165529370308,
      "rewards/accuracy_reward": 0.675000011920929,
      "rewards/format_reward": 0.9500000178813934,
      "step": 400
    },
    {
      "completion_length": 184.3000030517578,
      "epoch": 0.4157594608605495,
      "grad_norm": 1.3612682819366455,
      "kl": 0.52490234375,
      "learning_rate": 2.9865493815482827e-06,
      "loss": 0.122,
      "reward": 1.6250000298023224,
      "reward_std": 0.27950848266482353,
      "rewards/accuracy_reward": 0.7000000104308128,
      "rewards/format_reward": 0.9250000268220901,
      "step": 401
    },
    {
      "completion_length": 267.40000343322754,
      "epoch": 0.416796267496112,
      "grad_norm": 31.001413345336914,
      "kl": 4.72412109375,
      "learning_rate": 2.986306307459364e-06,
      "loss": 0.5375,
      "reward": 1.4500000029802322,
      "reward_std": 0.43636219948530197,
      "rewards/accuracy_reward": 0.6000000182539225,
      "rewards/format_reward": 0.8500000089406967,
      "step": 402
    },
    {
      "completion_length": 211.35000038146973,
      "epoch": 0.4178330741316744,
      "grad_norm": 1.4517061710357666,
      "kl": 1.05419921875,
      "learning_rate": 2.986061066697158e-06,
      "loss": 0.0987,
      "reward": 1.2500000149011612,
      "reward_std": 0.24873404949903488,
      "rewards/accuracy_reward": 0.32500000670552254,
      "rewards/format_reward": 0.925000011920929,
      "step": 403
    },
    {
      "completion_length": 142.9250030517578,
      "epoch": 0.4188698807672369,
      "grad_norm": 1.8906280994415283,
      "kl": 1.05908203125,
      "learning_rate": 2.9858136596191662e-06,
      "loss": 0.1521,
      "reward": 1.3250000327825546,
      "reward_std": 0.2920721247792244,
      "rewards/accuracy_reward": 0.3999999985098839,
      "rewards/format_reward": 0.9250000268220901,
      "step": 404
    },
    {
      "completion_length": 141.87500190734863,
      "epoch": 0.4199066874027994,
      "grad_norm": 23.721681594848633,
      "kl": 3.887939453125,
      "learning_rate": 2.985564086586048e-06,
      "loss": 0.3364,
      "reward": 1.475000023841858,
      "reward_std": 0.4740530550479889,
      "rewards/accuracy_reward": 0.5750000029802322,
      "rewards/format_reward": 0.9000000059604645,
      "step": 405
    },
    {
      "completion_length": 162.39999961853027,
      "epoch": 0.42094349403836184,
      "grad_norm": 65.63410949707031,
      "kl": 7.84228515625,
      "learning_rate": 2.9853123479616196e-06,
      "loss": 0.5849,
      "reward": 1.5500000268220901,
      "reward_std": 0.3479738086462021,
      "rewards/accuracy_reward": 0.6500000059604645,
      "rewards/format_reward": 0.9000000208616257,
      "step": 406
    },
    {
      "completion_length": 247.4749984741211,
      "epoch": 0.42198030067392434,
      "grad_norm": 10.55413818359375,
      "kl": 4.9853515625,
      "learning_rate": 2.9850584441128557e-06,
      "loss": 0.4714,
      "reward": 1.475000023841858,
      "reward_std": 0.4472135789692402,
      "rewards/accuracy_reward": 0.6250000149011612,
      "rewards/format_reward": 0.8500000238418579,
      "step": 407
    },
    {
      "completion_length": 220.52500534057617,
      "epoch": 0.4230171073094868,
      "grad_norm": 0.9092906713485718,
      "kl": 0.403076171875,
      "learning_rate": 2.984802375409885e-06,
      "loss": 0.0505,
      "reward": 1.2750000059604645,
      "reward_std": 0.4495588019490242,
      "rewards/accuracy_reward": 0.3750000037252903,
      "rewards/format_reward": 0.9000000208616257,
      "step": 408
    },
    {
      "completion_length": 199.35000038146973,
      "epoch": 0.42405391394504927,
      "grad_norm": 1.2738308906555176,
      "kl": 0.4384765625,
      "learning_rate": 2.984544142225995e-06,
      "loss": 0.1137,
      "reward": 1.4000000059604645,
      "reward_std": 0.3046357296407223,
      "rewards/accuracy_reward": 0.45000001043081284,
      "rewards/format_reward": 0.9500000178813934,
      "step": 409
    },
    {
      "completion_length": 305.950008392334,
      "epoch": 0.4250907205806117,
      "grad_norm": 2.3068294525146484,
      "kl": 0.871826171875,
      "learning_rate": 2.9842837449376264e-06,
      "loss": 0.2054,
      "reward": 1.550000011920929,
      "reward_std": 0.4290027618408203,
      "rewards/accuracy_reward": 0.6749999970197678,
      "rewards/format_reward": 0.8750000298023224,
      "step": 410
    },
    {
      "completion_length": 237.6500015258789,
      "epoch": 0.4261275272161742,
      "grad_norm": 2.3890562057495117,
      "kl": 1.326171875,
      "learning_rate": 2.9840211839243747e-06,
      "loss": 0.2206,
      "reward": 1.5,
      "reward_std": 0.47247934713959694,
      "rewards/accuracy_reward": 0.5999999940395355,
      "rewards/format_reward": 0.9000000357627869,
      "step": 411
    },
    {
      "completion_length": 491.37500953674316,
      "epoch": 0.42716433385173663,
      "grad_norm": 0.7049680948257446,
      "kl": 0.55810546875,
      "learning_rate": 2.9837564595689896e-06,
      "loss": 0.0784,
      "reward": 1.3500000536441803,
      "reward_std": 0.3913119025528431,
      "rewards/accuracy_reward": 0.6000000182539225,
      "rewards/format_reward": 0.7500000149011612,
      "step": 412
    },
    {
      "completion_length": 219.30000114440918,
      "epoch": 0.4282011404872991,
      "grad_norm": 5.027242183685303,
      "kl": 1.90966796875,
      "learning_rate": 2.983489572257376e-06,
      "loss": 0.1836,
      "reward": 1.2000000178813934,
      "reward_std": 0.27228760719299316,
      "rewards/accuracy_reward": 0.4000000096857548,
      "rewards/format_reward": 0.800000011920929,
      "step": 413
    },
    {
      "completion_length": 601.2500057220459,
      "epoch": 0.42923794712286156,
      "grad_norm": 33.8704948425293,
      "kl": 11.8896484375,
      "learning_rate": 2.9832205223785905e-06,
      "loss": 1.1407,
      "reward": 1.1500000059604645,
      "reward_std": 0.5894869565963745,
      "rewards/accuracy_reward": 0.4999999962747097,
      "rewards/format_reward": 0.6499999985098839,
      "step": 414
    },
    {
      "completion_length": 697.1750144958496,
      "epoch": 0.43027475375842406,
      "grad_norm": 0.6441704034805298,
      "kl": 0.45263671875,
      "learning_rate": 2.9829493103248416e-06,
      "loss": 0.169,
      "reward": 1.0000000149011612,
      "reward_std": 0.4237985797226429,
      "rewards/accuracy_reward": 0.3499999977648258,
      "rewards/format_reward": 0.6500000208616257,
      "step": 415
    },
    {
      "completion_length": 626.6500091552734,
      "epoch": 0.43131156039398655,
      "grad_norm": 1.1363885402679443,
      "kl": 1.099609375,
      "learning_rate": 2.9826759364914915e-06,
      "loss": 0.283,
      "reward": 1.0250000059604645,
      "reward_std": 0.504827506840229,
      "rewards/accuracy_reward": 0.3750000074505806,
      "rewards/format_reward": 0.6500000134110451,
      "step": 416
    },
    {
      "completion_length": 217.35000610351562,
      "epoch": 0.432348367029549,
      "grad_norm": 0.9580169916152954,
      "kl": 0.4140625,
      "learning_rate": 2.9824004012770523e-06,
      "loss": 0.1531,
      "reward": 1.2750000059604645,
      "reward_std": 0.3533165343105793,
      "rewards/accuracy_reward": 0.32500000298023224,
      "rewards/format_reward": 0.9500000178813934,
      "step": 417
    },
    {
      "completion_length": 687.4500045776367,
      "epoch": 0.4333851736651115,
      "grad_norm": 0.6423575282096863,
      "kl": 0.49609375,
      "learning_rate": 2.9821227050831874e-06,
      "loss": 0.1532,
      "reward": 0.9749999940395355,
      "reward_std": 0.41643914207816124,
      "rewards/accuracy_reward": 0.35000000335276127,
      "rewards/format_reward": 0.6250000074505806,
      "step": 418
    },
    {
      "completion_length": 339.0999984741211,
      "epoch": 0.4344219803006739,
      "grad_norm": 1.1070829629898071,
      "kl": 1.319580078125,
      "learning_rate": 2.9818428483147104e-06,
      "loss": 0.259,
      "reward": 1.1750000417232513,
      "reward_std": 0.5048274733126163,
      "rewards/accuracy_reward": 0.35000000335276127,
      "rewards/format_reward": 0.8250000029802322,
      "step": 419
    },
    {
      "completion_length": 391.54999923706055,
      "epoch": 0.4354587869362364,
      "grad_norm": 0.9474948048591614,
      "kl": 0.658203125,
      "learning_rate": 2.9815608313795845e-06,
      "loss": 0.1309,
      "reward": 1.2500000447034836,
      "reward_std": 0.44219936802983284,
      "rewards/accuracy_reward": 0.47500000335276127,
      "rewards/format_reward": 0.7750000059604645,
      "step": 420
    },
    {
      "completion_length": 418.125,
      "epoch": 0.43649559357179885,
      "grad_norm": 35.806827545166016,
      "kl": 12.6572265625,
      "learning_rate": 2.981276654688922e-06,
      "loss": 0.7257,
      "reward": 1.0750000029802322,
      "reward_std": 0.4723408445715904,
      "rewards/accuracy_reward": 0.30000000819563866,
      "rewards/format_reward": 0.7750000208616257,
      "step": 421
    },
    {
      "completion_length": 406.25000762939453,
      "epoch": 0.43753240020736134,
      "grad_norm": 4.112382411956787,
      "kl": 2.720703125,
      "learning_rate": 2.9809903186569826e-06,
      "loss": 0.4188,
      "reward": 1.1750000268220901,
      "reward_std": 0.5968463569879532,
      "rewards/accuracy_reward": 0.35000000335276127,
      "rewards/format_reward": 0.8250000178813934,
      "step": 422
    },
    {
      "completion_length": 389.7249984741211,
      "epoch": 0.4385692068429238,
      "grad_norm": 3.500101327896118,
      "kl": 4.51220703125,
      "learning_rate": 2.9807018237011756e-06,
      "loss": 0.4401,
      "reward": 1.2500000149011612,
      "reward_std": 0.3858031928539276,
      "rewards/accuracy_reward": 0.4000000059604645,
      "rewards/format_reward": 0.8500000238418579,
      "step": 423
    },
    {
      "completion_length": 309.550012588501,
      "epoch": 0.43960601347848627,
      "grad_norm": 3.486119031906128,
      "kl": 4.0400390625,
      "learning_rate": 2.980411170242056e-06,
      "loss": 0.4344,
      "reward": 1.3250000178813934,
      "reward_std": 0.5156789012253284,
      "rewards/accuracy_reward": 0.4500000160187483,
      "rewards/format_reward": 0.8750000149011612,
      "step": 424
    },
    {
      "completion_length": 142.0750026702881,
      "epoch": 0.4406428201140487,
      "grad_norm": 0.783508837223053,
      "kl": 1.0380859375,
      "learning_rate": 2.9801183587033266e-06,
      "loss": 0.1069,
      "reward": 1.5250000357627869,
      "reward_std": 0.2920721173286438,
      "rewards/accuracy_reward": 0.5500000193715096,
      "rewards/format_reward": 0.9750000089406967,
      "step": 425
    },
    {
      "completion_length": 118.95000076293945,
      "epoch": 0.4416796267496112,
      "grad_norm": 0.49163949489593506,
      "kl": 0.404296875,
      "learning_rate": 2.9798233895118343e-06,
      "loss": 0.0385,
      "reward": 1.350000023841858,
      "reward_std": 0.23617041483521461,
      "rewards/accuracy_reward": 0.4000000059604645,
      "rewards/format_reward": 0.9500000029802322,
      "step": 426
    },
    {
      "completion_length": 482.90000915527344,
      "epoch": 0.4427164333851737,
      "grad_norm": 1.6972235441207886,
      "kl": 1.5712890625,
      "learning_rate": 2.9795262630975732e-06,
      "loss": 0.3296,
      "reward": 0.9750000387430191,
      "reward_std": 0.5535082966089249,
      "rewards/accuracy_reward": 0.20000000298023224,
      "rewards/format_reward": 0.7750000059604645,
      "step": 427
    },
    {
      "completion_length": 404.5250015258789,
      "epoch": 0.44375324002073613,
      "grad_norm": 1.4435909986495972,
      "kl": 2.01611328125,
      "learning_rate": 2.979226979893681e-06,
      "loss": 0.3348,
      "reward": 1.2500000298023224,
      "reward_std": 0.4349784702062607,
      "rewards/accuracy_reward": 0.4000000134110451,
      "rewards/format_reward": 0.8500000238418579,
      "step": 428
    },
    {
      "completion_length": 241.77500343322754,
      "epoch": 0.4447900466562986,
      "grad_norm": 1.073678970336914,
      "kl": 2.5791015625,
      "learning_rate": 2.978925540336441e-06,
      "loss": 0.2655,
      "reward": 1.3250000327825546,
      "reward_std": 0.40387552604079247,
      "rewards/accuracy_reward": 0.4000000059604645,
      "rewards/format_reward": 0.9250000268220901,
      "step": 429
    },
    {
      "completion_length": 259.87500762939453,
      "epoch": 0.44582685329186106,
      "grad_norm": 3.7204360961914062,
      "kl": 5.47900390625,
      "learning_rate": 2.978621944865277e-06,
      "loss": 0.3859,
      "reward": 1.3250000327825546,
      "reward_std": 0.2920721173286438,
      "rewards/accuracy_reward": 0.42500001192092896,
      "rewards/format_reward": 0.9000000208616257,
      "step": 430
    },
    {
      "completion_length": 210.2000026702881,
      "epoch": 0.44686365992742355,
      "grad_norm": 0.5499123930931091,
      "kl": 0.99951171875,
      "learning_rate": 2.9783161939227587e-06,
      "loss": 0.1771,
      "reward": 1.0999999940395355,
      "reward_std": 0.22360678017139435,
      "rewards/accuracy_reward": 0.15000000596046448,
      "rewards/format_reward": 0.9500000029802322,
      "step": 431
    },
    {
      "completion_length": 254.32501220703125,
      "epoch": 0.447900466562986,
      "grad_norm": 1.4711023569107056,
      "kl": 1.126220703125,
      "learning_rate": 2.9780082879545958e-06,
      "loss": 0.2227,
      "reward": 1.4500000029802322,
      "reward_std": 0.2920721173286438,
      "rewards/accuracy_reward": 0.5250000059604645,
      "rewards/format_reward": 0.9250000268220901,
      "step": 432
    },
    {
      "completion_length": 149.57500076293945,
      "epoch": 0.4489372731985485,
      "grad_norm": 0.3505478799343109,
      "kl": 0.44189453125,
      "learning_rate": 2.9776982274096416e-06,
      "loss": 0.0277,
      "reward": 1.600000023841858,
      "reward_std": 0.16770509257912636,
      "rewards/accuracy_reward": 0.6250000093132257,
      "rewards/format_reward": 0.9750000089406967,
      "step": 433
    },
    {
      "completion_length": 118.62500381469727,
      "epoch": 0.4499740798341109,
      "grad_norm": 1.0018848180770874,
      "kl": 0.70654296875,
      "learning_rate": 2.9773860127398872e-06,
      "loss": 0.0473,
      "reward": 1.550000011920929,
      "reward_std": 0.25609345361590385,
      "rewards/accuracy_reward": 0.6000000163912773,
      "rewards/format_reward": 0.9500000178813934,
      "step": 434
    },
    {
      "completion_length": 149.22500610351562,
      "epoch": 0.4510108864696734,
      "grad_norm": 0.4854688048362732,
      "kl": 1.08154296875,
      "learning_rate": 2.9770716444004673e-06,
      "loss": 0.0993,
      "reward": 1.300000011920929,
      "reward_std": 0.16770510748028755,
      "rewards/accuracy_reward": 0.3500000014901161,
      "rewards/format_reward": 0.9500000178813934,
      "step": 435
    },
    {
      "completion_length": 225.75,
      "epoch": 0.45204769310523585,
      "grad_norm": 1.2092115879058838,
      "kl": 1.08251953125,
      "learning_rate": 2.9767551228496537e-06,
      "loss": 0.0811,
      "reward": 1.300000011920929,
      "reward_std": 0.22894952446222305,
      "rewards/accuracy_reward": 0.3500000014901161,
      "rewards/format_reward": 0.9500000178813934,
      "step": 436
    },
    {
      "completion_length": 191.77499961853027,
      "epoch": 0.45308449974079834,
      "grad_norm": 2.3160505294799805,
      "kl": 1.91552734375,
      "learning_rate": 2.9764364485488584e-06,
      "loss": 0.1791,
      "reward": 1.2000000029802322,
      "reward_std": 0.1604842059314251,
      "rewards/accuracy_reward": 0.27500000037252903,
      "rewards/format_reward": 0.925000011920929,
      "step": 437
    },
    {
      "completion_length": 445.32500648498535,
      "epoch": 0.45412130637636083,
      "grad_norm": 1.1174695491790771,
      "kl": 2.077392578125,
      "learning_rate": 2.9761156219626305e-06,
      "loss": 0.3718,
      "reward": 1.4749999940395355,
      "reward_std": 0.521021630614996,
      "rewards/accuracy_reward": 0.6499999985098839,
      "rewards/format_reward": 0.8250000029802322,
      "step": 438
    },
    {
      "completion_length": 422.75,
      "epoch": 0.45515811301192327,
      "grad_norm": 1.358939528465271,
      "kl": 2.649658203125,
      "learning_rate": 2.9757926435586572e-06,
      "loss": 0.1542,
      "reward": 1.1000000089406967,
      "reward_std": 0.37310105934739113,
      "rewards/accuracy_reward": 0.32500000298023224,
      "rewards/format_reward": 0.7750000059604645,
      "step": 439
    },
    {
      "completion_length": 638.4000091552734,
      "epoch": 0.45619491964748576,
      "grad_norm": 1.3631545305252075,
      "kl": 2.658203125,
      "learning_rate": 2.975467513807763e-06,
      "loss": 0.4623,
      "reward": 1.0000000447034836,
      "reward_std": 0.7521778345108032,
      "rewards/accuracy_reward": 0.37500000186264515,
      "rewards/format_reward": 0.6250000149011612,
      "step": 440
    },
    {
      "completion_length": 549.6250038146973,
      "epoch": 0.4572317262830482,
      "grad_norm": 1.7535611391067505,
      "kl": 1.56591796875,
      "learning_rate": 2.975140233183908e-06,
      "loss": 0.3238,
      "reward": 1.1500000059604645,
      "reward_std": 0.5408061631023884,
      "rewards/accuracy_reward": 0.44999999552965164,
      "rewards/format_reward": 0.7000000029802322,
      "step": 441
    },
    {
      "completion_length": 441.25000762939453,
      "epoch": 0.4582685329186107,
      "grad_norm": 2.6060733795166016,
      "kl": 1.5341796875,
      "learning_rate": 2.9748108021641875e-06,
      "loss": 0.3068,
      "reward": 1.3250000178813934,
      "reward_std": 0.6076978109776974,
      "rewards/accuracy_reward": 0.5000000149011612,
      "rewards/format_reward": 0.8250000029802322,
      "step": 442
    },
    {
      "completion_length": 449.1750068664551,
      "epoch": 0.45930533955417313,
      "grad_norm": 2.323462963104248,
      "kl": 3.5185546875,
      "learning_rate": 2.974479221228831e-06,
      "loss": 0.5005,
      "reward": 1.1499999910593033,
      "reward_std": 0.4981010742485523,
      "rewards/accuracy_reward": 0.3750000074505806,
      "rewards/format_reward": 0.7749999910593033,
      "step": 443
    },
    {
      "completion_length": 369.0999984741211,
      "epoch": 0.4603421461897356,
      "grad_norm": 9.374835968017578,
      "kl": 4.626953125,
      "learning_rate": 2.9741454908612047e-06,
      "loss": 0.4378,
      "reward": 1.1250000149011612,
      "reward_std": 0.4525563307106495,
      "rewards/accuracy_reward": 0.3000000026077032,
      "rewards/format_reward": 0.8250000178813934,
      "step": 444
    },
    {
      "completion_length": 254.1500072479248,
      "epoch": 0.46137895282529806,
      "grad_norm": 1.3832933902740479,
      "kl": 1.93603515625,
      "learning_rate": 2.9738096115478055e-06,
      "loss": 0.2301,
      "reward": 1.3000000268220901,
      "reward_std": 0.3479738235473633,
      "rewards/accuracy_reward": 0.40000000409781933,
      "rewards/format_reward": 0.9000000208616257,
      "step": 445
    },
    {
      "completion_length": 344.5,
      "epoch": 0.46241575946086055,
      "grad_norm": 1.9132006168365479,
      "kl": 2.30419921875,
      "learning_rate": 2.9734715837782635e-06,
      "loss": 0.2175,
      "reward": 1.225000038743019,
      "reward_std": 0.40387552976608276,
      "rewards/accuracy_reward": 0.3500000089406967,
      "rewards/format_reward": 0.8750000149011612,
      "step": 446
    },
    {
      "completion_length": 238.82500648498535,
      "epoch": 0.463452566096423,
      "grad_norm": 1.1751809120178223,
      "kl": 1.783203125,
      "learning_rate": 2.973131408045341e-06,
      "loss": 0.3002,
      "reward": 1.5750000476837158,
      "reward_std": 0.3913118988275528,
      "rewards/accuracy_reward": 0.6500000059604645,
      "rewards/format_reward": 0.9250000268220901,
      "step": 447
    },
    {
      "completion_length": 186.3499984741211,
      "epoch": 0.4644893727319855,
      "grad_norm": 0.9299616813659668,
      "kl": 0.9111328125,
      "learning_rate": 2.972789084844932e-06,
      "loss": 0.1332,
      "reward": 1.5750000178813934,
      "reward_std": 0.2920721247792244,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 0.9500000178813934,
      "step": 448
    },
    {
      "completion_length": 307.1250171661377,
      "epoch": 0.465526179367548,
      "grad_norm": 1.2203192710876465,
      "kl": 2.68505859375,
      "learning_rate": 2.97244461467606e-06,
      "loss": 0.3509,
      "reward": 1.550000011920929,
      "reward_std": 0.36053743958473206,
      "rewards/accuracy_reward": 0.6500000059604645,
      "rewards/format_reward": 0.9000000059604645,
      "step": 449
    },
    {
      "completion_length": 197.77500534057617,
      "epoch": 0.4665629860031104,
      "grad_norm": 0.5328684449195862,
      "kl": 1.17578125,
      "learning_rate": 2.9720979980408795e-06,
      "loss": 0.173,
      "reward": 1.4749999940395355,
      "reward_std": 0.14429005607962608,
      "rewards/accuracy_reward": 0.525000000372529,
      "rewards/format_reward": 0.9500000178813934,
      "step": 450
    },
    {
      "completion_length": 183.67500495910645,
      "epoch": 0.4675997926386729,
      "grad_norm": 2.1329684257507324,
      "kl": 1.76220703125,
      "learning_rate": 2.9717492354446727e-06,
      "loss": 0.1922,
      "reward": 1.2750000059604645,
      "reward_std": 0.2795085087418556,
      "rewards/accuracy_reward": 0.3500000089406967,
      "rewards/format_reward": 0.925000011920929,
      "step": 451
    },
    {
      "completion_length": 97.95000076293945,
      "epoch": 0.46863659927423534,
      "grad_norm": 0.40684643387794495,
      "kl": 0.35595703125,
      "learning_rate": 2.9713983273958507e-06,
      "loss": 0.027,
      "reward": 1.574999988079071,
      "reward_std": 0.18026871606707573,
      "rewards/accuracy_reward": 0.6000000089406967,
      "rewards/format_reward": 0.9750000089406967,
      "step": 452
    },
    {
      "completion_length": 141.92500019073486,
      "epoch": 0.46967340590979784,
      "grad_norm": 3.87530517578125,
      "kl": 2.384521484375,
      "learning_rate": 2.971045274405952e-06,
      "loss": 0.2588,
      "reward": 1.600000023841858,
      "reward_std": 0.2361704297363758,
      "rewards/accuracy_reward": 0.6250000186264515,
      "rewards/format_reward": 0.9750000089406967,
      "step": 453
    },
    {
      "completion_length": 138.90000343322754,
      "epoch": 0.4707102125453603,
      "grad_norm": 4.4843430519104,
      "kl": 2.71875,
      "learning_rate": 2.9706900769896434e-06,
      "loss": 0.1234,
      "reward": 1.5500000417232513,
      "reward_std": 0.36789682134985924,
      "rewards/accuracy_reward": 0.650000000372529,
      "rewards/format_reward": 0.9000000059604645,
      "step": 454
    },
    {
      "completion_length": 337.850004196167,
      "epoch": 0.47174701918092277,
      "grad_norm": 25.936668395996094,
      "kl": 4.15185546875,
      "learning_rate": 2.970332735664714e-06,
      "loss": 0.3841,
      "reward": 1.350000023841858,
      "reward_std": 0.3856646902859211,
      "rewards/accuracy_reward": 0.4750000014901161,
      "rewards/format_reward": 0.8750000149011612,
      "step": 455
    },
    {
      "completion_length": 245.5,
      "epoch": 0.4727838258164852,
      "grad_norm": 1.4629117250442505,
      "kl": 0.405517578125,
      "learning_rate": 2.969973250952083e-06,
      "loss": 0.1739,
      "reward": 1.100000023841858,
      "reward_std": 0.2920721136033535,
      "rewards/accuracy_reward": 0.25,
      "rewards/format_reward": 0.8500000089406967,
      "step": 456
    },
    {
      "completion_length": 551.0750122070312,
      "epoch": 0.4738206324520477,
      "grad_norm": 2.0260560512542725,
      "kl": 0.8857421875,
      "learning_rate": 2.96961162337579e-06,
      "loss": 0.2795,
      "reward": 1.050000011920929,
      "reward_std": 0.4651199281215668,
      "rewards/accuracy_reward": 0.3000000063329935,
      "rewards/format_reward": 0.7500000149011612,
      "step": 457
    },
    {
      "completion_length": 735.4250030517578,
      "epoch": 0.47485743908761013,
      "grad_norm": 5.954936981201172,
      "kl": 0.9501953125,
      "learning_rate": 2.969247853463e-06,
      "loss": 0.424,
      "reward": 0.8750000149011612,
      "reward_std": 0.582404587417841,
      "rewards/accuracy_reward": 0.24999999813735485,
      "rewards/format_reward": 0.6250000186264515,
      "step": 458
    },
    {
      "completion_length": 592.0750122070312,
      "epoch": 0.4758942457231726,
      "grad_norm": 4.934417247772217,
      "kl": 0.63671875,
      "learning_rate": 2.968881941744003e-06,
      "loss": 0.2356,
      "reward": 1.1500000208616257,
      "reward_std": 0.5342182517051697,
      "rewards/accuracy_reward": 0.45000001043081284,
      "rewards/format_reward": 0.7000000029802322,
      "step": 459
    },
    {
      "completion_length": 586.4000091552734,
      "epoch": 0.4769310523587351,
      "grad_norm": 2.2492358684539795,
      "kl": 0.421875,
      "learning_rate": 2.968513888752207e-06,
      "loss": 0.3741,
      "reward": 1.2500000298023224,
      "reward_std": 0.8159334361553192,
      "rewards/accuracy_reward": 0.5750000104308128,
      "rewards/format_reward": 0.6749999970197678,
      "step": 460
    },
    {
      "completion_length": 455.5500030517578,
      "epoch": 0.47796785899429756,
      "grad_norm": 2.0860514640808105,
      "kl": 0.35400390625,
      "learning_rate": 2.9681436950241457e-06,
      "loss": 0.2959,
      "reward": 1.2500000149011612,
      "reward_std": 0.6224680915474892,
      "rewards/accuracy_reward": 0.4750000014901161,
      "rewards/format_reward": 0.7750000208616257,
      "step": 461
    },
    {
      "completion_length": 485.87500762939453,
      "epoch": 0.47900466562986005,
      "grad_norm": 68.13333892822266,
      "kl": 13.9140625,
      "learning_rate": 2.9677713610994704e-06,
      "loss": 1.3759,
      "reward": 1.1500000208616257,
      "reward_std": 0.5533697977662086,
      "rewards/accuracy_reward": 0.4000000134110451,
      "rewards/format_reward": 0.7500000149011612,
      "step": 462
    },
    {
      "completion_length": 181.725004196167,
      "epoch": 0.4800414722654225,
      "grad_norm": 9.417370796203613,
      "kl": 1.84912109375,
      "learning_rate": 2.9673968875209545e-06,
      "loss": 0.1592,
      "reward": 1.4500000178813934,
      "reward_std": 0.5253834910690784,
      "rewards/accuracy_reward": 0.600000012665987,
      "rewards/format_reward": 0.8500000238418579,
      "step": 463
    },
    {
      "completion_length": 575.8250045776367,
      "epoch": 0.481078278900985,
      "grad_norm": 2.923924446105957,
      "kl": 0.75537109375,
      "learning_rate": 2.967020274834488e-06,
      "loss": 0.2154,
      "reward": 1.2000000178813934,
      "reward_std": 0.658585287630558,
      "rewards/accuracy_reward": 0.4750000089406967,
      "rewards/format_reward": 0.7250000238418579,
      "step": 464
    },
    {
      "completion_length": 235.97500228881836,
      "epoch": 0.4821150855365474,
      "grad_norm": 27.21836280822754,
      "kl": 8.6328125,
      "learning_rate": 2.9666415235890823e-06,
      "loss": 0.814,
      "reward": 1.3500000089406967,
      "reward_std": 0.3913119100034237,
      "rewards/accuracy_reward": 0.45000000298023224,
      "rewards/format_reward": 0.9000000208616257,
      "step": 465
    },
    {
      "completion_length": 180.10000038146973,
      "epoch": 0.4831518921721099,
      "grad_norm": 1.1835033893585205,
      "kl": 0.5048828125,
      "learning_rate": 2.966260634336863e-06,
      "loss": 0.0695,
      "reward": 1.350000023841858,
      "reward_std": 0.26129766553640366,
      "rewards/accuracy_reward": 0.4000000059604645,
      "rewards/format_reward": 0.9500000029802322,
      "step": 466
    },
    {
      "completion_length": 141.75,
      "epoch": 0.48418869880767235,
      "grad_norm": 0.5516549348831177,
      "kl": 0.375244140625,
      "learning_rate": 2.965877607633075e-06,
      "loss": 0.0181,
      "reward": 1.5999999940395355,
      "reward_std": 0.33353202417492867,
      "rewards/accuracy_reward": 0.6750000044703484,
      "rewards/format_reward": 0.925000011920929,
      "step": 467
    },
    {
      "completion_length": 151.57499885559082,
      "epoch": 0.48522550544323484,
      "grad_norm": 2.3915843963623047,
      "kl": 0.5625,
      "learning_rate": 2.965492444036078e-06,
      "loss": 0.0569,
      "reward": 1.3499999940395355,
      "reward_std": 0.281220693141222,
      "rewards/accuracy_reward": 0.4000000059604645,
      "rewards/format_reward": 0.9500000178813934,
      "step": 468
    },
    {
      "completion_length": 89.47500228881836,
      "epoch": 0.48626231207879733,
      "grad_norm": 0.3632679879665375,
      "kl": 0.4560546875,
      "learning_rate": 2.965105144107347e-06,
      "loss": 0.0197,
      "reward": 1.2750000059604645,
      "reward_std": 0.055901702493429184,
      "rewards/accuracy_reward": 0.27500000037252903,
      "rewards/format_reward": 1.0,
      "step": 469
    },
    {
      "completion_length": 104.25000381469727,
      "epoch": 0.48729911871435977,
      "grad_norm": 2.3217339515686035,
      "kl": 0.4345703125,
      "learning_rate": 2.9647157084114704e-06,
      "loss": -0.0065,
      "reward": 1.5,
      "reward_std": 0.2920721285045147,
      "rewards/accuracy_reward": 0.5250000078231096,
      "rewards/format_reward": 0.9750000089406967,
      "step": 470
    },
    {
      "completion_length": 157.50000381469727,
      "epoch": 0.48833592534992226,
      "grad_norm": 1.2729434967041016,
      "kl": 0.7998046875,
      "learning_rate": 2.9643241375161517e-06,
      "loss": 0.1192,
      "reward": 1.375,
      "reward_std": 0.5100317001342773,
      "rewards/accuracy_reward": 0.5,
      "rewards/format_reward": 0.875,
      "step": 471
    },
    {
      "completion_length": 656.1500015258789,
      "epoch": 0.4893727319854847,
      "grad_norm": 1.7226147651672363,
      "kl": 0.68115234375,
      "learning_rate": 2.963930431992206e-06,
      "loss": 0.4477,
      "reward": 0.8500000238418579,
      "reward_std": 0.5660719275474548,
      "rewards/accuracy_reward": 0.1750000026077032,
      "rewards/format_reward": 0.6749999970197678,
      "step": 472
    },
    {
      "completion_length": 406.3750057220459,
      "epoch": 0.4904095386210472,
      "grad_norm": 0.951695442199707,
      "kl": 0.376953125,
      "learning_rate": 2.96353459241356e-06,
      "loss": 0.2062,
      "reward": 1.225000023841858,
      "reward_std": 0.49088017642498016,
      "rewards/accuracy_reward": 0.45000000298023224,
      "rewards/format_reward": 0.7750000208616257,
      "step": 473
    },
    {
      "completion_length": 170.22500228881836,
      "epoch": 0.49144634525660963,
      "grad_norm": 0.9786409735679626,
      "kl": 0.43505859375,
      "learning_rate": 2.963136619357251e-06,
      "loss": 0.0848,
      "reward": 1.425000011920929,
      "reward_std": 0.4797002226114273,
      "rewards/accuracy_reward": 0.5500000044703484,
      "rewards/format_reward": 0.8750000149011612,
      "step": 474
    },
    {
      "completion_length": 180.82500076293945,
      "epoch": 0.4924831518921721,
      "grad_norm": 0.526511013507843,
      "kl": 0.50146484375,
      "learning_rate": 2.9627365134034276e-06,
      "loss": 0.0805,
      "reward": 1.2999999970197678,
      "reward_std": 0.06846532225608826,
      "rewards/accuracy_reward": 0.375,
      "rewards/format_reward": 0.9249999970197678,
      "step": 475
    },
    {
      "completion_length": 179.5000057220459,
      "epoch": 0.49351995852773456,
      "grad_norm": 1.3897082805633545,
      "kl": 0.3935546875,
      "learning_rate": 2.9623342751353473e-06,
      "loss": 0.1006,
      "reward": 1.2500000298023224,
      "reward_std": 0.23617039993405342,
      "rewards/accuracy_reward": 0.3500000014901161,
      "rewards/format_reward": 0.9000000208616257,
      "step": 476
    },
    {
      "completion_length": 104.20000267028809,
      "epoch": 0.49455676516329705,
      "grad_norm": 1.2519752979278564,
      "kl": 0.62939453125,
      "learning_rate": 2.961929905139375e-06,
      "loss": 0.0275,
      "reward": 1.5750000178813934,
      "reward_std": 0.3856646902859211,
      "rewards/accuracy_reward": 0.5750000104308128,
      "rewards/format_reward": 1.0,
      "step": 477
    },
    {
      "completion_length": 136.77500534057617,
      "epoch": 0.4955935717988595,
      "grad_norm": 32.357139587402344,
      "kl": 8.801513671875,
      "learning_rate": 2.9615234040049845e-06,
      "loss": 0.5752,
      "reward": 1.1250000149011612,
      "reward_std": 0.18026872724294662,
      "rewards/accuracy_reward": 0.17500000074505806,
      "rewards/format_reward": 0.9500000178813934,
      "step": 478
    },
    {
      "completion_length": 151.99999809265137,
      "epoch": 0.496630378434422,
      "grad_norm": 4.595073699951172,
      "kl": 1.439453125,
      "learning_rate": 2.9611147723247555e-06,
      "loss": 0.154,
      "reward": 1.5250000059604645,
      "reward_std": 0.28485121950507164,
      "rewards/accuracy_reward": 0.5749999992549419,
      "rewards/format_reward": 0.9500000029802322,
      "step": 479
    },
    {
      "completion_length": 102.72500038146973,
      "epoch": 0.4976671850699845,
      "grad_norm": 0.591180682182312,
      "kl": 0.371337890625,
      "learning_rate": 2.9607040106943733e-06,
      "loss": 0.0109,
      "reward": 1.4250000268220901,
      "reward_std": 0.18026872724294662,
      "rewards/accuracy_reward": 0.45000000298023224,
      "rewards/format_reward": 0.9750000089406967,
      "step": 480
    },
    {
      "completion_length": 152.975004196167,
      "epoch": 0.4987039917055469,
      "grad_norm": 1.7282302379608154,
      "kl": 1.240234375,
      "learning_rate": 2.9602911197126286e-06,
      "loss": 0.1355,
      "reward": 1.2750000208616257,
      "reward_std": 0.26129766181111336,
      "rewards/accuracy_reward": 0.30000000074505806,
      "rewards/format_reward": 0.9750000089406967,
      "step": 481
    },
    {
      "completion_length": 119.20000076293945,
      "epoch": 0.4997407983411094,
      "grad_norm": 1.2713792324066162,
      "kl": 1.33203125,
      "learning_rate": 2.9598760999814165e-06,
      "loss": 0.0979,
      "reward": 1.5000000298023224,
      "reward_std": 0.2795084938406944,
      "rewards/accuracy_reward": 0.550000011920929,
      "rewards/format_reward": 0.9500000178813934,
      "step": 482
    },
    {
      "completion_length": 133.9250030517578,
      "epoch": 0.5007776049766719,
      "grad_norm": 0.8651389479637146,
      "kl": 0.416259765625,
      "learning_rate": 2.9594589521057342e-06,
      "loss": 0.0718,
      "reward": 1.4000000208616257,
      "reward_std": 0.22360679507255554,
      "rewards/accuracy_reward": 0.45000001043081284,
      "rewards/format_reward": 0.9500000178813934,
      "step": 483
    },
    {
      "completion_length": 134.850004196167,
      "epoch": 0.5018144116122343,
      "grad_norm": 1.2900584936141968,
      "kl": 1.51318359375,
      "learning_rate": 2.9590396766936826e-06,
      "loss": 0.1183,
      "reward": 1.350000038743019,
      "reward_std": 0.3479738235473633,
      "rewards/accuracy_reward": 0.4000000134110451,
      "rewards/format_reward": 0.9500000178813934,
      "step": 484
    },
    {
      "completion_length": 86.97500133514404,
      "epoch": 0.5028512182477968,
      "grad_norm": 0.4113655388355255,
      "kl": 0.3232421875,
      "learning_rate": 2.9586182743564627e-06,
      "loss": 0.0003,
      "reward": 1.675000011920929,
      "reward_std": 0.12436701729893684,
      "rewards/accuracy_reward": 0.675000011920929,
      "rewards/format_reward": 1.0,
      "step": 485
    },
    {
      "completion_length": 138.35000038146973,
      "epoch": 0.5038880248833593,
      "grad_norm": 3.6755096912384033,
      "kl": 2.095703125,
      "learning_rate": 2.9581947457083773e-06,
      "loss": 0.1498,
      "reward": 1.550000011920929,
      "reward_std": 0.18026871979236603,
      "rewards/accuracy_reward": 0.5750000029802322,
      "rewards/format_reward": 0.9750000089406967,
      "step": 486
    },
    {
      "completion_length": 87.00000381469727,
      "epoch": 0.5049248315189218,
      "grad_norm": 0.35109928250312805,
      "kl": 0.46728515625,
      "learning_rate": 2.957769091366828e-06,
      "loss": 0.0177,
      "reward": 1.550000011920929,
      "reward_std": 0.06846532225608826,
      "rewards/accuracy_reward": 0.5500000007450581,
      "rewards/format_reward": 1.0,
      "step": 487
    },
    {
      "completion_length": 77.22500228881836,
      "epoch": 0.5059616381544841,
      "grad_norm": 1.4628422260284424,
      "kl": 0.9501953125,
      "learning_rate": 2.9573413119523146e-06,
      "loss": 0.0246,
      "reward": 1.5750000178813934,
      "reward_std": 0.12436702474951744,
      "rewards/accuracy_reward": 0.5750000029802322,
      "rewards/format_reward": 1.0,
      "step": 488
    },
    {
      "completion_length": 168.70000457763672,
      "epoch": 0.5069984447900466,
      "grad_norm": 6.089077472686768,
      "kl": 2.49169921875,
      "learning_rate": 2.9569114080884365e-06,
      "loss": 0.2892,
      "reward": 1.7000000476837158,
      "reward_std": 0.3354102000594139,
      "rewards/accuracy_reward": 0.7750000208616257,
      "rewards/format_reward": 0.9250000268220901,
      "step": 489
    },
    {
      "completion_length": 93.82500457763672,
      "epoch": 0.5080352514256091,
      "grad_norm": 1.7852115631103516,
      "kl": 0.6474609375,
      "learning_rate": 2.9564793804018885e-06,
      "loss": 0.0774,
      "reward": 1.5250000059604645,
      "reward_std": 0.2920721247792244,
      "rewards/accuracy_reward": 0.5500000007450581,
      "rewards/format_reward": 0.9750000089406967,
      "step": 490
    },
    {
      "completion_length": 70.42500114440918,
      "epoch": 0.5090720580611716,
      "grad_norm": 0.8128455281257629,
      "kl": 0.35009765625,
      "learning_rate": 2.9560452295224624e-06,
      "loss": 0.0278,
      "reward": 1.5000000298023224,
      "reward_std": 0.31719935312867165,
      "rewards/accuracy_reward": 0.5000000074505806,
      "rewards/format_reward": 1.0,
      "step": 491
    },
    {
      "completion_length": 125.45000076293945,
      "epoch": 0.5101088646967341,
      "grad_norm": 0.7844669222831726,
      "kl": 0.4482421875,
      "learning_rate": 2.955608956083044e-06,
      "loss": 0.05,
      "reward": 1.550000011920929,
      "reward_std": 0.15685366839170456,
      "rewards/accuracy_reward": 0.5750000029802322,
      "rewards/format_reward": 0.9750000089406967,
      "step": 492
    },
    {
      "completion_length": 127.45000457763672,
      "epoch": 0.5111456713322965,
      "grad_norm": 1.1734215021133423,
      "kl": 1.258544921875,
      "learning_rate": 2.9551705607196147e-06,
      "loss": 0.0648,
      "reward": 1.3750000298023224,
      "reward_std": 0.3407529294490814,
      "rewards/accuracy_reward": 0.4500000048428774,
      "rewards/format_reward": 0.925000011920929,
      "step": 493
    },
    {
      "completion_length": 180.07500457763672,
      "epoch": 0.512182477967859,
      "grad_norm": 0.663034975528717,
      "kl": 0.40966796875,
      "learning_rate": 2.9547300440712477e-06,
      "loss": 0.0733,
      "reward": 1.5250000059604645,
      "reward_std": 0.17304783314466476,
      "rewards/accuracy_reward": 0.5750000029802322,
      "rewards/format_reward": 0.9500000029802322,
      "step": 494
    },
    {
      "completion_length": 179.37500667572021,
      "epoch": 0.5132192846034215,
      "grad_norm": 0.9060681462287903,
      "kl": 0.76513671875,
      "learning_rate": 2.9542874067801094e-06,
      "loss": 0.1252,
      "reward": 1.5249999910593033,
      "reward_std": 0.2686570920050144,
      "rewards/accuracy_reward": 0.6250000149011612,
      "rewards/format_reward": 0.9000000059604645,
      "step": 495
    },
    {
      "completion_length": 197.75000667572021,
      "epoch": 0.514256091238984,
      "grad_norm": 1.4791067838668823,
      "kl": 1.224609375,
      "learning_rate": 2.9538426494914574e-06,
      "loss": 0.1744,
      "reward": 1.475000023841858,
      "reward_std": 0.3913119062781334,
      "rewards/accuracy_reward": 0.5500000193715096,
      "rewards/format_reward": 0.925000011920929,
      "step": 496
    },
    {
      "completion_length": 82.92500305175781,
      "epoch": 0.5152928978745464,
      "grad_norm": 22.87507438659668,
      "kl": 4.554931640625,
      "learning_rate": 2.9533957728536397e-06,
      "loss": 0.3108,
      "reward": 1.6250000298023224,
      "reward_std": 0.2920721210539341,
      "rewards/accuracy_reward": 0.6500000208616257,
      "rewards/format_reward": 0.9750000089406967,
      "step": 497
    },
    {
      "completion_length": 97.22500038146973,
      "epoch": 0.5163297045101088,
      "grad_norm": 2.5906031131744385,
      "kl": 0.286376953125,
      "learning_rate": 2.9529467775180935e-06,
      "loss": 0.0659,
      "reward": 1.5000000298023224,
      "reward_std": 0.30463574454188347,
      "rewards/accuracy_reward": 0.5250000096857548,
      "rewards/format_reward": 0.9750000089406967,
      "step": 498
    },
    {
      "completion_length": 160.65000343322754,
      "epoch": 0.5173665111456713,
      "grad_norm": 1.3695307970046997,
      "kl": 1.130859375,
      "learning_rate": 2.952495664139346e-06,
      "loss": 0.1592,
      "reward": 1.475000023841858,
      "reward_std": 0.4723408408463001,
      "rewards/accuracy_reward": 0.5750000141561031,
      "rewards/format_reward": 0.9000000208616257,
      "step": 499
    },
    {
      "completion_length": 145.62500667572021,
      "epoch": 0.5184033177812338,
      "grad_norm": 3.733125925064087,
      "kl": 4.13330078125,
      "learning_rate": 2.952042433375009e-06,
      "loss": 0.1987,
      "reward": 1.425000011920929,
      "reward_std": 0.28485122323036194,
      "rewards/accuracy_reward": 0.5000000074505806,
      "rewards/format_reward": 0.925000011920929,
      "step": 500
    },
    {
      "completion_length": 125.32500457763672,
      "epoch": 0.5194401244167963,
      "grad_norm": 0.9280956983566284,
      "kl": 0.7236328125,
      "learning_rate": 2.9515870858857846e-06,
      "loss": 0.0983,
      "reward": 1.3250000178813934,
      "reward_std": 0.2920721285045147,
      "rewards/accuracy_reward": 0.3750000037252903,
      "rewards/format_reward": 0.9500000178813934,
      "step": 501
    },
    {
      "completion_length": 75.125,
      "epoch": 0.5204769310523587,
      "grad_norm": 0.5787338614463806,
      "kl": 0.39306640625,
      "learning_rate": 2.9511296223354573e-06,
      "loss": 0.0172,
      "reward": 1.300000011920929,
      "reward_std": 0.06846531480550766,
      "rewards/accuracy_reward": 0.30000000074505806,
      "rewards/format_reward": 1.0,
      "step": 502
    },
    {
      "completion_length": 75.7750015258789,
      "epoch": 0.5215137376879212,
      "grad_norm": 0.7337321639060974,
      "kl": 0.386962890625,
      "learning_rate": 2.9506700433908988e-06,
      "loss": 0.0384,
      "reward": 1.375,
      "reward_std": 0.26129766181111336,
      "rewards/accuracy_reward": 0.3750000037252903,
      "rewards/format_reward": 1.0,
      "step": 503
    },
    {
      "completion_length": 67.75000095367432,
      "epoch": 0.5225505443234837,
      "grad_norm": 0.9252765774726868,
      "kl": 0.3251953125,
      "learning_rate": 2.9502083497220632e-06,
      "loss": -0.0029,
      "reward": 1.675000011920929,
      "reward_std": 0.11180339753627777,
      "rewards/accuracy_reward": 0.675000011920929,
      "rewards/format_reward": 1.0,
      "step": 504
    },
    {
      "completion_length": 69.30000114440918,
      "epoch": 0.5235873509590462,
      "grad_norm": 0.8446915745735168,
      "kl": 0.34375,
      "learning_rate": 2.949744542001987e-06,
      "loss": 0.0156,
      "reward": 1.3750000298023224,
      "reward_std": 0.32818931341171265,
      "rewards/accuracy_reward": 0.40000000409781933,
      "rewards/format_reward": 0.9750000089406967,
      "step": 505
    },
    {
      "completion_length": 127.27500343322754,
      "epoch": 0.5246241575946086,
      "grad_norm": 2.3860890865325928,
      "kl": 1.30126953125,
      "learning_rate": 2.94927862090679e-06,
      "loss": 0.1343,
      "reward": 1.4749999940395355,
      "reward_std": 0.30463574454188347,
      "rewards/accuracy_reward": 0.5,
      "rewards/format_reward": 0.9750000089406967,
      "step": 506
    },
    {
      "completion_length": 71.9250020980835,
      "epoch": 0.5256609642301711,
      "grad_norm": 0.4810761511325836,
      "kl": 0.458984375,
      "learning_rate": 2.9488105871156717e-06,
      "loss": 0.063,
      "reward": 1.3750000149011612,
      "reward_std": 0.20019174739718437,
      "rewards/accuracy_reward": 0.42500000074505806,
      "rewards/format_reward": 0.9500000029802322,
      "step": 507
    },
    {
      "completion_length": 117.42500686645508,
      "epoch": 0.5266977708657335,
      "grad_norm": 1.6127690076828003,
      "kl": 0.67724609375,
      "learning_rate": 2.948340441310911e-06,
      "loss": 0.0579,
      "reward": 1.3750000447034836,
      "reward_std": 0.2487340345978737,
      "rewards/accuracy_reward": 0.4000000059604645,
      "rewards/format_reward": 0.9750000089406967,
      "step": 508
    },
    {
      "completion_length": 67.17500305175781,
      "epoch": 0.527734577501296,
      "grad_norm": 1.0923641920089722,
      "kl": 0.5478515625,
      "learning_rate": 2.9478681841778667e-06,
      "loss": 0.0588,
      "reward": 1.5000000298023224,
      "reward_std": 0.292072132229805,
      "rewards/accuracy_reward": 0.5250000134110451,
      "rewards/format_reward": 0.9750000089406967,
      "step": 509
    },
    {
      "completion_length": 91.72500228881836,
      "epoch": 0.5287713841368584,
      "grad_norm": 1.9580719470977783,
      "kl": 0.9287109375,
      "learning_rate": 2.9473938164049744e-06,
      "loss": 0.0741,
      "reward": 1.4250000417232513,
      "reward_std": 0.2795084975659847,
      "rewards/accuracy_reward": 0.47500001080334187,
      "rewards/format_reward": 0.9500000178813934,
      "step": 510
    },
    {
      "completion_length": 74.10000133514404,
      "epoch": 0.5298081907724209,
      "grad_norm": 0.6495768427848816,
      "kl": 0.37744140625,
      "learning_rate": 2.946917338683748e-06,
      "loss": 0.0301,
      "reward": 1.125,
      "reward_std": 0.11180340498685837,
      "rewards/accuracy_reward": 0.15000000037252903,
      "rewards/format_reward": 0.9750000089406967,
      "step": 511
    },
    {
      "completion_length": 121.17500114440918,
      "epoch": 0.5308449974079834,
      "grad_norm": 0.9497795104980469,
      "kl": 0.634765625,
      "learning_rate": 2.946438751708775e-06,
      "loss": 0.0806,
      "reward": 1.4000000059604645,
      "reward_std": 0.37310105189681053,
      "rewards/accuracy_reward": 0.5,
      "rewards/format_reward": 0.9000000208616257,
      "step": 512
    },
    {
      "completion_length": 71.57499980926514,
      "epoch": 0.5318818040435459,
      "grad_norm": 0.5596094131469727,
      "kl": 0.39501953125,
      "learning_rate": 2.94595805617772e-06,
      "loss": 0.0342,
      "reward": 1.2000000029802322,
      "reward_std": 0.11180340498685837,
      "rewards/accuracy_reward": 0.22500000149011612,
      "rewards/format_reward": 0.9750000089406967,
      "step": 513
    },
    {
      "completion_length": 174.45000171661377,
      "epoch": 0.5329186106791084,
      "grad_norm": 5.549030303955078,
      "kl": 0.6337890625,
      "learning_rate": 2.9454752527913194e-06,
      "loss": 0.1269,
      "reward": 1.1750000268220901,
      "reward_std": 0.2920721061527729,
      "rewards/accuracy_reward": 0.22500000335276127,
      "rewards/format_reward": 0.9500000178813934,
      "step": 514
    },
    {
      "completion_length": 148.6500072479248,
      "epoch": 0.5339554173146708,
      "grad_norm": 36.280643463134766,
      "kl": 4.50537109375,
      "learning_rate": 2.9449903422533836e-06,
      "loss": 0.3704,
      "reward": 1.600000023841858,
      "reward_std": 0.347973819822073,
      "rewards/accuracy_reward": 0.675000011920929,
      "rewards/format_reward": 0.925000011920929,
      "step": 515
    },
    {
      "completion_length": 205.25000762939453,
      "epoch": 0.5349922239502333,
      "grad_norm": 97.75532531738281,
      "kl": 7.87744140625,
      "learning_rate": 2.9445033252707943e-06,
      "loss": 0.7113,
      "reward": 1.2249999940395355,
      "reward_std": 0.26143617182970047,
      "rewards/accuracy_reward": 0.30000001192092896,
      "rewards/format_reward": 0.925000011920929,
      "step": 516
    },
    {
      "completion_length": 83.45000267028809,
      "epoch": 0.5360290305857958,
      "grad_norm": 0.8470296263694763,
      "kl": 0.443359375,
      "learning_rate": 2.944014202553503e-06,
      "loss": -0.0235,
      "reward": 1.600000023841858,
      "reward_std": 0.16770509257912636,
      "rewards/accuracy_reward": 0.6000000033527613,
      "rewards/format_reward": 1.0,
      "step": 517
    },
    {
      "completion_length": 80.52500057220459,
      "epoch": 0.5370658372213583,
      "grad_norm": 4.682936191558838,
      "kl": 0.51123046875,
      "learning_rate": 2.943522974814533e-06,
      "loss": 0.0104,
      "reward": 1.7000000178813934,
      "reward_std": 0.18026871979236603,
      "rewards/accuracy_reward": 0.7000000178813934,
      "rewards/format_reward": 1.0,
      "step": 518
    },
    {
      "completion_length": 80.22500228881836,
      "epoch": 0.5381026438569206,
      "grad_norm": 0.6545246243476868,
      "kl": 0.56591796875,
      "learning_rate": 2.9430296427699743e-06,
      "loss": 0.0316,
      "reward": 1.550000011920929,
      "reward_std": 0.21275537461042404,
      "rewards/accuracy_reward": 0.5750000029802322,
      "rewards/format_reward": 0.9750000089406967,
      "step": 519
    },
    {
      "completion_length": 139.82500457763672,
      "epoch": 0.5391394504924831,
      "grad_norm": 0.5691772699356079,
      "kl": 0.54736328125,
      "learning_rate": 2.9425342071389853e-06,
      "loss": 0.0921,
      "reward": 1.2750000357627869,
      "reward_std": 0.1928323432803154,
      "rewards/accuracy_reward": 0.32500000298023224,
      "rewards/format_reward": 0.9500000029802322,
      "step": 520
    },
    {
      "completion_length": 185.52500534057617,
      "epoch": 0.5401762571280456,
      "grad_norm": 1.905286192893982,
      "kl": 0.724609375,
      "learning_rate": 2.94203666864379e-06,
      "loss": 0.1483,
      "reward": 1.475000023841858,
      "reward_std": 0.4290027618408203,
      "rewards/accuracy_reward": 0.5249999947845936,
      "rewards/format_reward": 0.9500000178813934,
      "step": 521
    },
    {
      "completion_length": 80.97500038146973,
      "epoch": 0.5412130637636081,
      "grad_norm": 0.35716575384140015,
      "kl": 0.343994140625,
      "learning_rate": 2.9415370280096797e-06,
      "loss": 0.0305,
      "reward": 1.3499999940395355,
      "reward_std": 0.05590169504284859,
      "rewards/accuracy_reward": 0.375,
      "rewards/format_reward": 0.9750000089406967,
      "step": 522
    },
    {
      "completion_length": 81.00000190734863,
      "epoch": 0.5422498703991706,
      "grad_norm": 0.46804380416870117,
      "kl": 0.41943359375,
      "learning_rate": 2.941035285965008e-06,
      "loss": 0.0485,
      "reward": 1.449999988079071,
      "reward_std": 0.11180340498685837,
      "rewards/accuracy_reward": 0.5,
      "rewards/format_reward": 0.9500000178813934,
      "step": 523
    },
    {
      "completion_length": 241.47500610351562,
      "epoch": 0.543286677034733,
      "grad_norm": 150.73275756835938,
      "kl": 35.86083984375,
      "learning_rate": 2.9405314432411933e-06,
      "loss": 2.8672,
      "reward": 1.350000023841858,
      "reward_std": 0.30477424710989,
      "rewards/accuracy_reward": 0.42500000447034836,
      "rewards/format_reward": 0.925000011920929,
      "step": 524
    },
    {
      "completion_length": 128.45000457763672,
      "epoch": 0.5443234836702955,
      "grad_norm": 1.8508985042572021,
      "kl": 1.2958984375,
      "learning_rate": 2.9400255005727162e-06,
      "loss": 0.1372,
      "reward": 1.550000011920929,
      "reward_std": 0.22360679507255554,
      "rewards/accuracy_reward": 0.5750000178813934,
      "rewards/format_reward": 0.9750000089406967,
      "step": 525
    },
    {
      "completion_length": 245.07500839233398,
      "epoch": 0.545360290305858,
      "grad_norm": 1146.21435546875,
      "kl": 151.87255859375,
      "learning_rate": 2.9395174586971174e-06,
      "loss": 11.6084,
      "reward": 1.4000000059604645,
      "reward_std": 0.3913118802011013,
      "rewards/accuracy_reward": 0.5,
      "rewards/format_reward": 0.9000000208616257,
      "step": 526
    },
    {
      "completion_length": 86.67500114440918,
      "epoch": 0.5463970969414205,
      "grad_norm": 0.6502148509025574,
      "kl": 0.30712890625,
      "learning_rate": 2.939007318354999e-06,
      "loss": -0.0365,
      "reward": 1.6500000357627869,
      "reward_std": 0.1928323395550251,
      "rewards/accuracy_reward": 0.6500000059604645,
      "rewards/format_reward": 1.0,
      "step": 527
    },
    {
      "completion_length": 163.04999923706055,
      "epoch": 0.5474339035769828,
      "grad_norm": 1.801808476448059,
      "kl": 0.300537109375,
      "learning_rate": 2.938495080290021e-06,
      "loss": 0.0618,
      "reward": 1.0250000357627869,
      "reward_std": 0.2361704222857952,
      "rewards/accuracy_reward": 0.07500000111758709,
      "rewards/format_reward": 0.9500000178813934,
      "step": 528
    },
    {
      "completion_length": 288.6750011444092,
      "epoch": 0.5484707102125453,
      "grad_norm": 6.281752109527588,
      "kl": 0.3994140625,
      "learning_rate": 2.937980745248902e-06,
      "loss": 0.1594,
      "reward": 1.7000000476837158,
      "reward_std": 0.3479738309979439,
      "rewards/accuracy_reward": 0.8000000193715096,
      "rewards/format_reward": 0.9000000208616257,
      "step": 529
    },
    {
      "completion_length": 155.25000381469727,
      "epoch": 0.5495075168481078,
      "grad_norm": 0.6555303931236267,
      "kl": 0.35302734375,
      "learning_rate": 2.9374643139814184e-06,
      "loss": 0.0639,
      "reward": 1.300000011920929,
      "reward_std": 0.12436702474951744,
      "rewards/accuracy_reward": 0.32500000298023224,
      "rewards/format_reward": 0.9750000089406967,
      "step": 530
    },
    {
      "completion_length": 214.6250114440918,
      "epoch": 0.5505443234836703,
      "grad_norm": 2.5419232845306396,
      "kl": 0.55859375,
      "learning_rate": 2.936945787240401e-06,
      "loss": 0.1867,
      "reward": 1.3250000476837158,
      "reward_std": 0.44892582297325134,
      "rewards/accuracy_reward": 0.3999999985098839,
      "rewards/format_reward": 0.925000011920929,
      "step": 531
    },
    {
      "completion_length": 100.6500015258789,
      "epoch": 0.5515811301192327,
      "grad_norm": 0.7034846544265747,
      "kl": 0.30908203125,
      "learning_rate": 2.936425165781735e-06,
      "loss": 0.0153,
      "reward": 1.5500000417232513,
      "reward_std": 0.31719936802983284,
      "rewards/accuracy_reward": 0.550000011920929,
      "rewards/format_reward": 1.0,
      "step": 532
    },
    {
      "completion_length": 256.25,
      "epoch": 0.5526179367547952,
      "grad_norm": 4.066845417022705,
      "kl": 0.75,
      "learning_rate": 2.935902450364361e-06,
      "loss": 0.1729,
      "reward": 1.6000000536441803,
      "reward_std": 0.2487340271472931,
      "rewards/accuracy_reward": 0.7000000178813934,
      "rewards/format_reward": 0.9000000059604645,
      "step": 533
    },
    {
      "completion_length": 94.05000305175781,
      "epoch": 0.5536547433903577,
      "grad_norm": 0.6132490634918213,
      "kl": 0.25537109375,
      "learning_rate": 2.9353776417502704e-06,
      "loss": 0.0136,
      "reward": 1.550000011920929,
      "reward_std": 0.24873404949903488,
      "rewards/accuracy_reward": 0.5500000044703484,
      "rewards/format_reward": 1.0,
      "step": 534
    },
    {
      "completion_length": 213.6500015258789,
      "epoch": 0.5546915500259202,
      "grad_norm": 11.384795188903809,
      "kl": 2.087890625,
      "learning_rate": 2.934850740704506e-06,
      "loss": 0.3464,
      "reward": 1.6000000536441803,
      "reward_std": 0.5031152740120888,
      "rewards/accuracy_reward": 0.7000000178813934,
      "rewards/format_reward": 0.9000000357627869,
      "step": 535
    },
    {
      "completion_length": 102.1500015258789,
      "epoch": 0.5557283566614827,
      "grad_norm": 1.437371850013733,
      "kl": 0.63671875,
      "learning_rate": 2.934321747995163e-06,
      "loss": 0.0334,
      "reward": 1.7250000536441803,
      "reward_std": 0.2920721098780632,
      "rewards/accuracy_reward": 0.7500000074505806,
      "rewards/format_reward": 0.9750000089406967,
      "step": 536
    },
    {
      "completion_length": 164.0500030517578,
      "epoch": 0.5567651632970451,
      "grad_norm": 0.8429715037345886,
      "kl": 0.400634765625,
      "learning_rate": 2.933790664393383e-06,
      "loss": 0.093,
      "reward": 1.425000011920929,
      "reward_std": 0.3354102075099945,
      "rewards/accuracy_reward": 0.47500001080334187,
      "rewards/format_reward": 0.9500000178813934,
      "step": 537
    },
    {
      "completion_length": 169.07500076293945,
      "epoch": 0.5578019699326076,
      "grad_norm": 0.981852650642395,
      "kl": 0.619384765625,
      "learning_rate": 2.9332574906733574e-06,
      "loss": 0.1237,
      "reward": 1.7000000476837158,
      "reward_std": 0.3479738309979439,
      "rewards/accuracy_reward": 0.7500000149011612,
      "rewards/format_reward": 0.9500000178813934,
      "step": 538
    },
    {
      "completion_length": 343.6750011444092,
      "epoch": 0.55883877656817,
      "grad_norm": 1.502892255783081,
      "kl": 0.77099609375,
      "learning_rate": 2.9327222276123232e-06,
      "loss": 0.2786,
      "reward": 1.5000000149011612,
      "reward_std": 0.3533165603876114,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 0.8750000149011612,
      "step": 539
    },
    {
      "completion_length": 167.00000190734863,
      "epoch": 0.5598755832037325,
      "grad_norm": 0.9482361674308777,
      "kl": 0.635009765625,
      "learning_rate": 2.9321848759905643e-06,
      "loss": 0.08,
      "reward": 1.725000023841858,
      "reward_std": 0.2361704260110855,
      "rewards/accuracy_reward": 0.7500000149011612,
      "rewards/format_reward": 0.9750000089406967,
      "step": 540
    },
    {
      "completion_length": 113.20000267028809,
      "epoch": 0.5609123898392949,
      "grad_norm": 0.9624785780906677,
      "kl": 0.711669921875,
      "learning_rate": 2.931645436591409e-06,
      "loss": 0.1214,
      "reward": 1.4500000178813934,
      "reward_std": 0.2614361569285393,
      "rewards/accuracy_reward": 0.5000000018626451,
      "rewards/format_reward": 0.9500000178813934,
      "step": 541
    },
    {
      "completion_length": 353.399995803833,
      "epoch": 0.5619491964748574,
      "grad_norm": 4.333626747131348,
      "kl": 2.579345703125,
      "learning_rate": 2.9311039102012277e-06,
      "loss": 0.2335,
      "reward": 1.2000000178813934,
      "reward_std": 0.28485121577978134,
      "rewards/accuracy_reward": 0.3499999977648258,
      "rewards/format_reward": 0.8500000089406967,
      "step": 542
    },
    {
      "completion_length": 177.00000381469727,
      "epoch": 0.5629860031104199,
      "grad_norm": 1.3422383069992065,
      "kl": 0.70458984375,
      "learning_rate": 2.9305602976094354e-06,
      "loss": 0.1408,
      "reward": 1.3750000149011612,
      "reward_std": 0.279508501291275,
      "rewards/accuracy_reward": 0.45000000298023224,
      "rewards/format_reward": 0.9250000268220901,
      "step": 543
    },
    {
      "completion_length": 181.97500610351562,
      "epoch": 0.5640228097459824,
      "grad_norm": 1.8206522464752197,
      "kl": 1.82177734375,
      "learning_rate": 2.9300145996084865e-06,
      "loss": 0.2003,
      "reward": 1.4000000059604645,
      "reward_std": 0.16770510748028755,
      "rewards/accuracy_reward": 0.45000000298023224,
      "rewards/format_reward": 0.9500000178813934,
      "step": 544
    },
    {
      "completion_length": 340.52500915527344,
      "epoch": 0.5650596163815449,
      "grad_norm": 77.96588134765625,
      "kl": 18.46630859375,
      "learning_rate": 2.929466816993877e-06,
      "loss": 1.4838,
      "reward": 1.4250000268220901,
      "reward_std": 0.38109346479177475,
      "rewards/accuracy_reward": 0.5500000063329935,
      "rewards/format_reward": 0.8750000149011612,
      "step": 545
    },
    {
      "completion_length": 107.55000114440918,
      "epoch": 0.5660964230171073,
      "grad_norm": 0.47127431631088257,
      "kl": 0.373779296875,
      "learning_rate": 2.928916950564139e-06,
      "loss": 0.0424,
      "reward": 1.2000000327825546,
      "reward_std": 0.18026871234178543,
      "rewards/accuracy_reward": 0.22500000335276127,
      "rewards/format_reward": 0.9750000089406967,
      "step": 546
    },
    {
      "completion_length": 187.20000076293945,
      "epoch": 0.5671332296526698,
      "grad_norm": 4.727897644042969,
      "kl": 3.77197265625,
      "learning_rate": 2.928365001120846e-06,
      "loss": 0.2137,
      "reward": 1.5000000298023224,
      "reward_std": 0.4723408445715904,
      "rewards/accuracy_reward": 0.6000000014901161,
      "rewards/format_reward": 0.9000000208616257,
      "step": 547
    },
    {
      "completion_length": 212.32500457763672,
      "epoch": 0.5681700362882323,
      "grad_norm": 1.5274919271469116,
      "kl": 2.5712890625,
      "learning_rate": 2.927810969468605e-06,
      "loss": 0.3168,
      "reward": 1.3000000268220901,
      "reward_std": 0.27950848266482353,
      "rewards/accuracy_reward": 0.37500000931322575,
      "rewards/format_reward": 0.9250000268220901,
      "step": 548
    },
    {
      "completion_length": 250.85000038146973,
      "epoch": 0.5692068429237948,
      "grad_norm": 1.4735158681869507,
      "kl": 1.9208984375,
      "learning_rate": 2.9272548564150593e-06,
      "loss": 0.2983,
      "reward": 1.5,
      "reward_std": 0.3913119100034237,
      "rewards/accuracy_reward": 0.5750000029802322,
      "rewards/format_reward": 0.925000011920929,
      "step": 549
    },
    {
      "completion_length": 102.10000228881836,
      "epoch": 0.5702436495593571,
      "grad_norm": 0.5658621191978455,
      "kl": 0.34375,
      "learning_rate": 2.926696662770887e-06,
      "loss": -0.0251,
      "reward": 1.350000023841858,
      "reward_std": 0.12436702474951744,
      "rewards/accuracy_reward": 0.3500000089406967,
      "rewards/format_reward": 1.0,
      "step": 550
    },
    {
      "completion_length": 118.80000495910645,
      "epoch": 0.5712804561949196,
      "grad_norm": 0.3587953448295593,
      "kl": 0.31005859375,
      "learning_rate": 2.9261363893497988e-06,
      "loss": 0.0136,
      "reward": 1.425000011920929,
      "reward_std": 0.11180340498685837,
      "rewards/accuracy_reward": 0.42500000074505806,
      "rewards/format_reward": 1.0,
      "step": 551
    },
    {
      "completion_length": 147.57500076293945,
      "epoch": 0.5723172628304821,
      "grad_norm": 0.8031432032585144,
      "kl": 0.4482421875,
      "learning_rate": 2.9255740369685367e-06,
      "loss": 0.016,
      "reward": 1.3500000089406967,
      "reward_std": 0.30463574454188347,
      "rewards/accuracy_reward": 0.4000000059604645,
      "rewards/format_reward": 0.9500000178813934,
      "step": 552
    },
    {
      "completion_length": 164.05000495910645,
      "epoch": 0.5733540694660446,
      "grad_norm": 1.5201157331466675,
      "kl": 1.3935546875,
      "learning_rate": 2.9250096064468745e-06,
      "loss": 0.1377,
      "reward": 1.3500000536441803,
      "reward_std": 0.37310105562210083,
      "rewards/accuracy_reward": 0.4000000059604645,
      "rewards/format_reward": 0.9500000178813934,
      "step": 553
    },
    {
      "completion_length": 101.75000190734863,
      "epoch": 0.574390876101607,
      "grad_norm": 0.4400118887424469,
      "kl": 0.295166015625,
      "learning_rate": 2.9244430986076146e-06,
      "loss": -0.0034,
      "reward": 1.550000011920929,
      "reward_std": 0.18026872724294662,
      "rewards/accuracy_reward": 0.5500000044703484,
      "rewards/format_reward": 1.0,
      "step": 554
    },
    {
      "completion_length": 202.8499984741211,
      "epoch": 0.5754276827371695,
      "grad_norm": 2.103760004043579,
      "kl": 2.682373046875,
      "learning_rate": 2.923874514276587e-06,
      "loss": 0.2481,
      "reward": 1.300000011920929,
      "reward_std": 0.16770510002970695,
      "rewards/accuracy_reward": 0.375,
      "rewards/format_reward": 0.9250000268220901,
      "step": 555
    },
    {
      "completion_length": 103.17500114440918,
      "epoch": 0.576464489372732,
      "grad_norm": 0.5067854523658752,
      "kl": 0.31201171875,
      "learning_rate": 2.9233038542826496e-06,
      "loss": 0.0438,
      "reward": 1.5250000059604645,
      "reward_std": 0.1928323432803154,
      "rewards/accuracy_reward": 0.5249999985098839,
      "rewards/format_reward": 1.0,
      "step": 556
    },
    {
      "completion_length": 172.92499923706055,
      "epoch": 0.5775012960082945,
      "grad_norm": 1.1114473342895508,
      "kl": 0.310791015625,
      "learning_rate": 2.9227311194576865e-06,
      "loss": 0.0272,
      "reward": 1.4500000178813934,
      "reward_std": 0.1928323395550251,
      "rewards/accuracy_reward": 0.4749999977648258,
      "rewards/format_reward": 0.9750000089406967,
      "step": 557
    },
    {
      "completion_length": 156.7500057220459,
      "epoch": 0.578538102643857,
      "grad_norm": 1.3353294134140015,
      "kl": 1.7294921875,
      "learning_rate": 2.9221563106366057e-06,
      "loss": 0.1717,
      "reward": 1.225000023841858,
      "reward_std": 0.16770510748028755,
      "rewards/accuracy_reward": 0.25000000186264515,
      "rewards/format_reward": 0.9750000089406967,
      "step": 558
    },
    {
      "completion_length": 175.80000686645508,
      "epoch": 0.5795749092794193,
      "grad_norm": 3.629734516143799,
      "kl": 1.093505859375,
      "learning_rate": 2.9215794286573383e-06,
      "loss": 0.1307,
      "reward": 1.275000050663948,
      "reward_std": 0.2920721173286438,
      "rewards/accuracy_reward": 0.3250000048428774,
      "rewards/format_reward": 0.9500000178813934,
      "step": 559
    },
    {
      "completion_length": 111.82500267028809,
      "epoch": 0.5806117159149818,
      "grad_norm": 0.19621193408966064,
      "kl": 0.2568359375,
      "learning_rate": 2.921000474360838e-06,
      "loss": 0.0142,
      "reward": 1.4749999940395355,
      "reward_std": 0.055901702493429184,
      "rewards/accuracy_reward": 0.4750000089406967,
      "rewards/format_reward": 1.0,
      "step": 560
    },
    {
      "completion_length": 121.42500305175781,
      "epoch": 0.5816485225505443,
      "grad_norm": 0.4136292040348053,
      "kl": 0.21484375,
      "learning_rate": 2.9204194485910798e-06,
      "loss": -0.0062,
      "reward": 1.600000023841858,
      "reward_std": 0.1928323358297348,
      "rewards/accuracy_reward": 0.5999999940395355,
      "rewards/format_reward": 1.0,
      "step": 561
    },
    {
      "completion_length": 131.62500190734863,
      "epoch": 0.5826853291861068,
      "grad_norm": 0.49414509534835815,
      "kl": 0.26416015625,
      "learning_rate": 2.9198363521950583e-06,
      "loss": 0.0075,
      "reward": 1.4000000357627869,
      "reward_std": 0.24873404949903488,
      "rewards/accuracy_reward": 0.4000000078231096,
      "rewards/format_reward": 1.0,
      "step": 562
    },
    {
      "completion_length": 173.89999961853027,
      "epoch": 0.5837221358216692,
      "grad_norm": 0.8812211751937866,
      "kl": 0.484375,
      "learning_rate": 2.9192511860227855e-06,
      "loss": 0.0233,
      "reward": 1.3500000089406967,
      "reward_std": 0.16770509257912636,
      "rewards/accuracy_reward": 0.4000000059604645,
      "rewards/format_reward": 0.9500000178813934,
      "step": 563
    },
    {
      "completion_length": 175.225004196167,
      "epoch": 0.5847589424572317,
      "grad_norm": 1.1985092163085938,
      "kl": 1.24365234375,
      "learning_rate": 2.9186639509272923e-06,
      "loss": 0.0881,
      "reward": 1.5000000298023224,
      "reward_std": 0.2795084938406944,
      "rewards/accuracy_reward": 0.5500000044703484,
      "rewards/format_reward": 0.9500000178813934,
      "step": 564
    },
    {
      "completion_length": 134.4250030517578,
      "epoch": 0.5857957490927942,
      "grad_norm": 0.4528398811817169,
      "kl": 0.299072265625,
      "learning_rate": 2.918074647764624e-06,
      "loss": 0.0062,
      "reward": 1.699999988079071,
      "reward_std": 0.18026871606707573,
      "rewards/accuracy_reward": 0.7000000104308128,
      "rewards/format_reward": 1.0,
      "step": 565
    },
    {
      "completion_length": 120.1500015258789,
      "epoch": 0.5868325557283567,
      "grad_norm": 0.4748910069465637,
      "kl": 0.2451171875,
      "learning_rate": 2.9174832773938413e-06,
      "loss": 0.026,
      "reward": 1.725000023841858,
      "reward_std": 0.2361704297363758,
      "rewards/accuracy_reward": 0.725000012665987,
      "rewards/format_reward": 1.0,
      "step": 566
    },
    {
      "completion_length": 180.22500610351562,
      "epoch": 0.5878693623639192,
      "grad_norm": 0.43165019154548645,
      "kl": 0.501708984375,
      "learning_rate": 2.916889840677019e-06,
      "loss": 0.0587,
      "reward": 1.350000023841858,
      "reward_std": 0.248734038323164,
      "rewards/accuracy_reward": 0.3750000037252903,
      "rewards/format_reward": 0.9750000089406967,
      "step": 567
    },
    {
      "completion_length": 176.225004196167,
      "epoch": 0.5889061689994816,
      "grad_norm": 0.5352876782417297,
      "kl": 0.711669921875,
      "learning_rate": 2.9162943384792435e-06,
      "loss": 0.0419,
      "reward": 1.6500000059604645,
      "reward_std": 0.21275537088513374,
      "rewards/accuracy_reward": 0.6750000044703484,
      "rewards/format_reward": 0.9750000089406967,
      "step": 568
    },
    {
      "completion_length": 193.17500495910645,
      "epoch": 0.589942975635044,
      "grad_norm": 0.6368687152862549,
      "kl": 0.36376953125,
      "learning_rate": 2.915696771668612e-06,
      "loss": 0.0535,
      "reward": 1.5750000476837158,
      "reward_std": 0.36053743958473206,
      "rewards/accuracy_reward": 0.6250000074505806,
      "rewards/format_reward": 0.9500000178813934,
      "step": 569
    },
    {
      "completion_length": 132.32500457763672,
      "epoch": 0.5909797822706065,
      "grad_norm": 0.36829519271850586,
      "kl": 0.236328125,
      "learning_rate": 2.9150971411162315e-06,
      "loss": -0.0057,
      "reward": 1.4500000178813934,
      "reward_std": 0.1928323395550251,
      "rewards/accuracy_reward": 0.44999999925494194,
      "rewards/format_reward": 1.0,
      "step": 570
    },
    {
      "completion_length": 152.65000343322754,
      "epoch": 0.592016588906169,
      "grad_norm": 0.4644145965576172,
      "kl": 0.241943359375,
      "learning_rate": 2.914495447696218e-06,
      "loss": -0.0219,
      "reward": 1.625,
      "reward_std": 0.24873404577374458,
      "rewards/accuracy_reward": 0.6250000074505806,
      "rewards/format_reward": 1.0,
      "step": 571
    },
    {
      "completion_length": 190.15000915527344,
      "epoch": 0.5930533955417314,
      "grad_norm": 0.4808287024497986,
      "kl": 0.278564453125,
      "learning_rate": 2.9138916922856946e-06,
      "loss": 0.0605,
      "reward": 1.5250000059604645,
      "reward_std": 0.21275536343455315,
      "rewards/accuracy_reward": 0.5500000044703484,
      "rewards/format_reward": 0.9750000089406967,
      "step": 572
    },
    {
      "completion_length": 203.225004196167,
      "epoch": 0.5940902021772939,
      "grad_norm": 9.010258674621582,
      "kl": 5.313232421875,
      "learning_rate": 2.9132858757647884e-06,
      "loss": 0.4188,
      "reward": 1.6500000357627869,
      "reward_std": 0.30463574454188347,
      "rewards/accuracy_reward": 0.675000011920929,
      "rewards/format_reward": 0.9750000089406967,
      "step": 573
    },
    {
      "completion_length": 142.100004196167,
      "epoch": 0.5951270088128564,
      "grad_norm": 0.4201050400733948,
      "kl": 0.2431640625,
      "learning_rate": 2.912677999016634e-06,
      "loss": 0.0162,
      "reward": 1.350000023841858,
      "reward_std": 0.2487340345978737,
      "rewards/accuracy_reward": 0.3500000089406967,
      "rewards/format_reward": 1.0,
      "step": 574
    },
    {
      "completion_length": 174.1750030517578,
      "epoch": 0.5961638154484189,
      "grad_norm": 0.3380955755710602,
      "kl": 0.2294921875,
      "learning_rate": 2.9120680629273677e-06,
      "loss": -0.0121,
      "reward": 1.4000000357627869,
      "reward_std": 0.18026871234178543,
      "rewards/accuracy_reward": 0.42500000447034836,
      "rewards/format_reward": 0.9750000089406967,
      "step": 575
    },
    {
      "completion_length": 153.12500381469727,
      "epoch": 0.5972006220839814,
      "grad_norm": 0.44647836685180664,
      "kl": 0.2392578125,
      "learning_rate": 2.9114560683861275e-06,
      "loss": 0.0226,
      "reward": 1.5250000357627869,
      "reward_std": 0.24873404577374458,
      "rewards/accuracy_reward": 0.525000000372529,
      "rewards/format_reward": 1.0,
      "step": 576
    },
    {
      "completion_length": 262.6500015258789,
      "epoch": 0.5982374287195438,
      "grad_norm": 7.015067100524902,
      "kl": 0.88427734375,
      "learning_rate": 2.910842016285053e-06,
      "loss": 0.1761,
      "reward": 1.475000023841858,
      "reward_std": 0.3354101851582527,
      "rewards/accuracy_reward": 0.5500000044703484,
      "rewards/format_reward": 0.925000011920929,
      "step": 577
    },
    {
      "completion_length": 132.9000015258789,
      "epoch": 0.5992742353551063,
      "grad_norm": 0.2848128080368042,
      "kl": 0.248046875,
      "learning_rate": 2.910225907519283e-06,
      "loss": -0.002,
      "reward": 1.2750000059604645,
      "reward_std": 0.055901702493429184,
      "rewards/accuracy_reward": 0.27500000037252903,
      "rewards/format_reward": 1.0,
      "step": 578
    },
    {
      "completion_length": 303.50000190734863,
      "epoch": 0.6003110419906688,
      "grad_norm": 96.8685302734375,
      "kl": 25.11279296875,
      "learning_rate": 2.9096077429869543e-06,
      "loss": 1.9498,
      "reward": 1.4500000178813934,
      "reward_std": 0.2920721024274826,
      "rewards/accuracy_reward": 0.5499999970197678,
      "rewards/format_reward": 0.9000000059604645,
      "step": 579
    },
    {
      "completion_length": 245.5250072479248,
      "epoch": 0.6013478486262313,
      "grad_norm": 1.2218270301818848,
      "kl": 0.70263671875,
      "learning_rate": 2.9089875235892005e-06,
      "loss": 0.1386,
      "reward": 1.5250000208616257,
      "reward_std": 0.22360680624842644,
      "rewards/accuracy_reward": 0.5750000029802322,
      "rewards/format_reward": 0.9500000178813934,
      "step": 580
    },
    {
      "completion_length": 188.2000026702881,
      "epoch": 0.6023846552617936,
      "grad_norm": 4.220678806304932,
      "kl": 2.01708984375,
      "learning_rate": 2.9083652502301506e-06,
      "loss": 0.1683,
      "reward": 1.600000023841858,
      "reward_std": 0.18026871234178543,
      "rewards/accuracy_reward": 0.6500000059604645,
      "rewards/format_reward": 0.9500000178813934,
      "step": 581
    },
    {
      "completion_length": 269.4500045776367,
      "epoch": 0.6034214618973561,
      "grad_norm": 5.021411895751953,
      "kl": 4.0146484375,
      "learning_rate": 2.907740923816928e-06,
      "loss": 0.3696,
      "reward": 1.2500000298023224,
      "reward_std": 0.4038754962384701,
      "rewards/accuracy_reward": 0.3250000048428774,
      "rewards/format_reward": 0.9250000268220901,
      "step": 582
    },
    {
      "completion_length": 183.97500038146973,
      "epoch": 0.6044582685329186,
      "grad_norm": 0.7388213872909546,
      "kl": 0.39697265625,
      "learning_rate": 2.907114545259649e-06,
      "loss": 0.1162,
      "reward": 1.350000038743019,
      "reward_std": 0.3354102112352848,
      "rewards/accuracy_reward": 0.45000001043081284,
      "rewards/format_reward": 0.9000000208616257,
      "step": 583
    },
    {
      "completion_length": 198.9749984741211,
      "epoch": 0.6054950751684811,
      "grad_norm": 6.0927934646606445,
      "kl": 1.3525390625,
      "learning_rate": 2.9064861154714206e-06,
      "loss": 0.108,
      "reward": 1.3750000149011612,
      "reward_std": 0.11180340498685837,
      "rewards/accuracy_reward": 0.40000000037252903,
      "rewards/format_reward": 0.9750000089406967,
      "step": 584
    },
    {
      "completion_length": 350.6000099182129,
      "epoch": 0.6065318818040435,
      "grad_norm": 3.432065010070801,
      "kl": 1.06787109375,
      "learning_rate": 2.9058556353683413e-06,
      "loss": 0.1571,
      "reward": 1.6500000059604645,
      "reward_std": 0.5715806148946285,
      "rewards/accuracy_reward": 0.7750000208616257,
      "rewards/format_reward": 0.8750000149011612,
      "step": 585
    },
    {
      "completion_length": 186.05000495910645,
      "epoch": 0.607568688439606,
      "grad_norm": 1.2789217233657837,
      "kl": 1.263916015625,
      "learning_rate": 2.9052231058694975e-06,
      "loss": 0.1736,
      "reward": 1.550000011920929,
      "reward_std": 0.38409099355340004,
      "rewards/accuracy_reward": 0.6500000152736902,
      "rewards/format_reward": 0.9000000059604645,
      "step": 586
    },
    {
      "completion_length": 140.97500228881836,
      "epoch": 0.6086054950751685,
      "grad_norm": 0.31413471698760986,
      "kl": 0.222900390625,
      "learning_rate": 2.9045885278969635e-06,
      "loss": -0.0107,
      "reward": 1.675000011920929,
      "reward_std": 0.12436701729893684,
      "rewards/accuracy_reward": 0.7000000029802322,
      "rewards/format_reward": 0.9750000089406967,
      "step": 587
    },
    {
      "completion_length": 130.9000015258789,
      "epoch": 0.609642301710731,
      "grad_norm": 0.4696264863014221,
      "kl": 0.25244140625,
      "learning_rate": 2.9039519023758004e-06,
      "loss": 0.0824,
      "reward": 1.4000000059604645,
      "reward_std": 0.2487340345978737,
      "rewards/accuracy_reward": 0.4000000022351742,
      "rewards/format_reward": 1.0,
      "step": 588
    },
    {
      "completion_length": 196.32500839233398,
      "epoch": 0.6106791083462935,
      "grad_norm": 4.557334899902344,
      "kl": 0.811767578125,
      "learning_rate": 2.9033132302340523e-06,
      "loss": 0.1282,
      "reward": 1.5250000655651093,
      "reward_std": 0.36053743958473206,
      "rewards/accuracy_reward": 0.5750000029802322,
      "rewards/format_reward": 0.9500000178813934,
      "step": 589
    },
    {
      "completion_length": 292.9749984741211,
      "epoch": 0.6117159149818558,
      "grad_norm": 9.806172370910645,
      "kl": 5.443359375,
      "learning_rate": 2.902672512402749e-06,
      "loss": 0.2563,
      "reward": 1.4000000059604645,
      "reward_std": 0.2974148504436016,
      "rewards/accuracy_reward": 0.5000000037252903,
      "rewards/format_reward": 0.9000000208616257,
      "step": 590
    },
    {
      "completion_length": 274.25,
      "epoch": 0.6127527216174183,
      "grad_norm": 2.256058692932129,
      "kl": 1.713134765625,
      "learning_rate": 2.9020297498159004e-06,
      "loss": 0.2101,
      "reward": 1.5750000476837158,
      "reward_std": 0.36588016152381897,
      "rewards/accuracy_reward": 0.6500000059604645,
      "rewards/format_reward": 0.925000011920929,
      "step": 591
    },
    {
      "completion_length": 241.0500030517578,
      "epoch": 0.6137895282529808,
      "grad_norm": 1.3324028253555298,
      "kl": 0.608154296875,
      "learning_rate": 2.901384943410499e-06,
      "loss": 0.1396,
      "reward": 1.5750000476837158,
      "reward_std": 0.403875507414341,
      "rewards/accuracy_reward": 0.6250000074505806,
      "rewards/format_reward": 0.9500000178813934,
      "step": 592
    },
    {
      "completion_length": 247.00000953674316,
      "epoch": 0.6148263348885433,
      "grad_norm": 6.3438873291015625,
      "kl": 0.499267578125,
      "learning_rate": 2.900738094126515e-06,
      "loss": 0.1196,
      "reward": 1.600000023841858,
      "reward_std": 0.2920721247792244,
      "rewards/accuracy_reward": 0.6500000059604645,
      "rewards/format_reward": 0.9500000178813934,
      "step": 593
    },
    {
      "completion_length": 296.42499923706055,
      "epoch": 0.6158631415241057,
      "grad_norm": 1.7976075410842896,
      "kl": 0.67138671875,
      "learning_rate": 2.9000892029068974e-06,
      "loss": 0.0767,
      "reward": 1.3000000268220901,
      "reward_std": 0.3297629915177822,
      "rewards/accuracy_reward": 0.37500000931322575,
      "rewards/format_reward": 0.9249999970197678,
      "step": 594
    },
    {
      "completion_length": 152.9000015258789,
      "epoch": 0.6168999481596682,
      "grad_norm": 0.41897207498550415,
      "kl": 0.201171875,
      "learning_rate": 2.899438270697573e-06,
      "loss": 0.0164,
      "reward": 1.4000000059604645,
      "reward_std": 0.2361704222857952,
      "rewards/accuracy_reward": 0.4000000115483999,
      "rewards/format_reward": 1.0,
      "step": 595
    },
    {
      "completion_length": 224.95000457763672,
      "epoch": 0.6179367547952307,
      "grad_norm": 1.1412527561187744,
      "kl": 1.325439453125,
      "learning_rate": 2.8987852984474413e-06,
      "loss": 0.1502,
      "reward": 1.4000000357627869,
      "reward_std": 0.23617040738463402,
      "rewards/accuracy_reward": 0.42500000447034836,
      "rewards/format_reward": 0.9750000089406967,
      "step": 596
    },
    {
      "completion_length": 170.4000015258789,
      "epoch": 0.6189735614307932,
      "grad_norm": 0.8881285190582275,
      "kl": 0.442626953125,
      "learning_rate": 2.898130287108378e-06,
      "loss": 0.0808,
      "reward": 1.2500000447034836,
      "reward_std": 0.1928323321044445,
      "rewards/accuracy_reward": 0.2750000059604645,
      "rewards/format_reward": 0.9750000089406967,
      "step": 597
    },
    {
      "completion_length": 282.5500030517578,
      "epoch": 0.6200103680663557,
      "grad_norm": 11.336788177490234,
      "kl": 6.169921875,
      "learning_rate": 2.8974732376352302e-06,
      "loss": 0.6068,
      "reward": 1.5250000357627869,
      "reward_std": 0.347973819822073,
      "rewards/accuracy_reward": 0.6000000014901161,
      "rewards/format_reward": 0.9250000268220901,
      "step": 598
    },
    {
      "completion_length": 203.20000648498535,
      "epoch": 0.6210471747019181,
      "grad_norm": 1.8857403993606567,
      "kl": 1.327392578125,
      "learning_rate": 2.8968141509858157e-06,
      "loss": 0.1394,
      "reward": 1.3250000178813934,
      "reward_std": 0.21275536715984344,
      "rewards/accuracy_reward": 0.35000000335276127,
      "rewards/format_reward": 0.9750000089406967,
      "step": 599
    },
    {
      "completion_length": 165.30000114440918,
      "epoch": 0.6220839813374806,
      "grad_norm": 0.3913152515888214,
      "kl": 0.234619140625,
      "learning_rate": 2.896153028120924e-06,
      "loss": -0.0227,
      "reward": 1.625,
      "reward_std": 0.18026871979236603,
      "rewards/accuracy_reward": 0.6250000186264515,
      "rewards/format_reward": 1.0,
      "step": 600
    },
    {
      "completion_length": 190.225004196167,
      "epoch": 0.623120787973043,
      "grad_norm": 2.7854464054107666,
      "kl": 0.409423828125,
      "learning_rate": 2.89548987000431e-06,
      "loss": 0.0567,
      "reward": 1.2000000178813934,
      "reward_std": 0.28485122323036194,
      "rewards/accuracy_reward": 0.22500000335276127,
      "rewards/format_reward": 0.9750000089406967,
      "step": 601
    },
    {
      "completion_length": 253.82500076293945,
      "epoch": 0.6241575946086055,
      "grad_norm": 5.791003704071045,
      "kl": 0.375244140625,
      "learning_rate": 2.8948246776026985e-06,
      "loss": 0.1521,
      "reward": 1.4500000327825546,
      "reward_std": 0.31733787432312965,
      "rewards/accuracy_reward": 0.5250000059604645,
      "rewards/format_reward": 0.925000011920929,
      "step": 602
    },
    {
      "completion_length": 136.20000076293945,
      "epoch": 0.6251944012441679,
      "grad_norm": 0.45052769780158997,
      "kl": 0.23486328125,
      "learning_rate": 2.8941574518857763e-06,
      "loss": -0.0226,
      "reward": 1.449999988079071,
      "reward_std": 0.18026872351765633,
      "rewards/accuracy_reward": 0.45000001043081284,
      "rewards/format_reward": 1.0,
      "step": 603
    },
    {
      "completion_length": 189.35000610351562,
      "epoch": 0.6262312078797304,
      "grad_norm": 1.993778109550476,
      "kl": 0.494140625,
      "learning_rate": 2.8934881938261987e-06,
      "loss": 0.0845,
      "reward": 1.425000011920929,
      "reward_std": 0.21275537461042404,
      "rewards/accuracy_reward": 0.4499999973922968,
      "rewards/format_reward": 0.9750000089406967,
      "step": 604
    },
    {
      "completion_length": 299.3500099182129,
      "epoch": 0.6272680145152929,
      "grad_norm": 3.556016683578491,
      "kl": 1.59912109375,
      "learning_rate": 2.8928169043995793e-06,
      "loss": 0.2569,
      "reward": 1.2749999910593033,
      "reward_std": 0.22360680252313614,
      "rewards/accuracy_reward": 0.375,
      "rewards/format_reward": 0.9000000357627869,
      "step": 605
    },
    {
      "completion_length": 132.07500076293945,
      "epoch": 0.6283048211508554,
      "grad_norm": 0.5948020219802856,
      "kl": 0.26513671875,
      "learning_rate": 2.8921435845844963e-06,
      "loss": 0.0789,
      "reward": 1.7000000178813934,
      "reward_std": 0.2361704185605049,
      "rewards/accuracy_reward": 0.7000000178813934,
      "rewards/format_reward": 1.0,
      "step": 606
    },
    {
      "completion_length": 239.55000495910645,
      "epoch": 0.6293416277864178,
      "grad_norm": 11.134238243103027,
      "kl": 3.626220703125,
      "learning_rate": 2.8914682353624855e-06,
      "loss": 0.3149,
      "reward": 1.3750000596046448,
      "reward_std": 0.36053745448589325,
      "rewards/accuracy_reward": 0.42500001192092896,
      "rewards/format_reward": 0.9500000178813934,
      "step": 607
    },
    {
      "completion_length": 217.1500015258789,
      "epoch": 0.6303784344219803,
      "grad_norm": 0.6335292458534241,
      "kl": 0.396484375,
      "learning_rate": 2.890790857718042e-06,
      "loss": 0.0686,
      "reward": 1.7000000178813934,
      "reward_std": 0.11180340498685837,
      "rewards/accuracy_reward": 0.7250000089406967,
      "rewards/format_reward": 0.9750000089406967,
      "step": 608
    },
    {
      "completion_length": 252.00000381469727,
      "epoch": 0.6314152410575428,
      "grad_norm": 45.83848190307617,
      "kl": 8.284423828125,
      "learning_rate": 2.8901114526386176e-06,
      "loss": 0.6874,
      "reward": 1.5250000357627869,
      "reward_std": 0.2795084975659847,
      "rewards/accuracy_reward": 0.6000000163912773,
      "rewards/format_reward": 0.925000011920929,
      "step": 609
    },
    {
      "completion_length": 224.375,
      "epoch": 0.6324520476931053,
      "grad_norm": 6.116477012634277,
      "kl": 2.39501953125,
      "learning_rate": 2.8894300211146207e-06,
      "loss": 0.2235,
      "reward": 1.375,
      "reward_std": 0.22360679879784584,
      "rewards/accuracy_reward": 0.40000000037252903,
      "rewards/format_reward": 0.9750000089406967,
      "step": 610
    },
    {
      "completion_length": 194.2000026702881,
      "epoch": 0.6334888543286677,
      "grad_norm": 0.7082158923149109,
      "kl": 0.6552734375,
      "learning_rate": 2.8887465641394114e-06,
      "loss": 0.1211,
      "reward": 1.425000011920929,
      "reward_std": 0.24873404204845428,
      "rewards/accuracy_reward": 0.45000000298023224,
      "rewards/format_reward": 0.9750000089406967,
      "step": 611
    },
    {
      "completion_length": 181.80000686645508,
      "epoch": 0.6345256609642301,
      "grad_norm": 0.7598231434822083,
      "kl": 1.06689453125,
      "learning_rate": 2.8880610827093045e-06,
      "loss": 0.0976,
      "reward": 1.4000000059604645,
      "reward_std": 0.21638592705130577,
      "rewards/accuracy_reward": 0.42500000447034836,
      "rewards/format_reward": 0.9750000089406967,
      "step": 612
    },
    {
      "completion_length": 165.0500030517578,
      "epoch": 0.6355624675997926,
      "grad_norm": 0.45146992802619934,
      "kl": 0.185302734375,
      "learning_rate": 2.8873735778235657e-06,
      "loss": 0.0104,
      "reward": 1.5,
      "reward_std": 0.3354102000594139,
      "rewards/accuracy_reward": 0.5250000134110451,
      "rewards/format_reward": 0.9750000089406967,
      "step": 613
    },
    {
      "completion_length": 252.3750114440918,
      "epoch": 0.6365992742353551,
      "grad_norm": 0.7813171148300171,
      "kl": 0.745849609375,
      "learning_rate": 2.8866840504844094e-06,
      "loss": 0.1231,
      "reward": 1.2500000298023224,
      "reward_std": 0.23617041483521461,
      "rewards/accuracy_reward": 0.32500000298023224,
      "rewards/format_reward": 0.925000011920929,
      "step": 614
    },
    {
      "completion_length": 289.6500015258789,
      "epoch": 0.6376360808709176,
      "grad_norm": 3.395939588546753,
      "kl": 3.01611328125,
      "learning_rate": 2.8859925016969995e-06,
      "loss": 0.2634,
      "reward": 1.4249999821186066,
      "reward_std": 0.3737340532243252,
      "rewards/accuracy_reward": 0.5499999970197678,
      "rewards/format_reward": 0.8750000149011612,
      "step": 615
    },
    {
      "completion_length": 462.9249954223633,
      "epoch": 0.63867288750648,
      "grad_norm": 2.6913440227508545,
      "kl": 3.1015625,
      "learning_rate": 2.885298932469445e-06,
      "loss": 0.4213,
      "reward": 1.3250000476837158,
      "reward_std": 0.7158706709742546,
      "rewards/accuracy_reward": 0.5000000074505806,
      "rewards/format_reward": 0.8250000029802322,
      "step": 616
    },
    {
      "completion_length": 311.7750129699707,
      "epoch": 0.6397096941420425,
      "grad_norm": 1.5979684591293335,
      "kl": 2.26220703125,
      "learning_rate": 2.884603343812802e-06,
      "loss": 0.1652,
      "reward": 1.2500000149011612,
      "reward_std": 0.39728759974241257,
      "rewards/accuracy_reward": 0.3500000014901161,
      "rewards/format_reward": 0.9000000208616257,
      "step": 617
    },
    {
      "completion_length": 327.32501220703125,
      "epoch": 0.640746500777605,
      "grad_norm": 12.20130443572998,
      "kl": 6.74072265625,
      "learning_rate": 2.8839057367410696e-06,
      "loss": 0.6414,
      "reward": 1.600000023841858,
      "reward_std": 0.4237985163927078,
      "rewards/accuracy_reward": 0.7000000178813934,
      "rewards/format_reward": 0.9000000208616257,
      "step": 618
    },
    {
      "completion_length": 207.82500076293945,
      "epoch": 0.6417833074131675,
      "grad_norm": 1.5905780792236328,
      "kl": 0.2890625,
      "learning_rate": 2.883206112271189e-06,
      "loss": 0.0787,
      "reward": 1.375,
      "reward_std": 0.3354102000594139,
      "rewards/accuracy_reward": 0.4000000078231096,
      "rewards/format_reward": 0.9750000089406967,
      "step": 619
    },
    {
      "completion_length": 218.95000076293945,
      "epoch": 0.64282011404873,
      "grad_norm": 3.3236258029937744,
      "kl": 1.61669921875,
      "learning_rate": 2.8825044714230427e-06,
      "loss": 0.1564,
      "reward": 1.5250000208616257,
      "reward_std": 0.16770509257912636,
      "rewards/accuracy_reward": 0.550000011920929,
      "rewards/format_reward": 0.9750000089406967,
      "step": 620
    },
    {
      "completion_length": 233.95000076293945,
      "epoch": 0.6438569206842923,
      "grad_norm": 2.439260721206665,
      "kl": 0.500732421875,
      "learning_rate": 2.881800815219453e-06,
      "loss": 0.1286,
      "reward": 1.3250000178813934,
      "reward_std": 0.22360678762197495,
      "rewards/accuracy_reward": 0.37500000186264515,
      "rewards/format_reward": 0.9500000178813934,
      "step": 621
    },
    {
      "completion_length": 200.4000015258789,
      "epoch": 0.6448937273198548,
      "grad_norm": 0.662738025188446,
      "kl": 0.79296875,
      "learning_rate": 2.881095144686179e-06,
      "loss": 0.0613,
      "reward": 1.4500000178813934,
      "reward_std": 0.3533165529370308,
      "rewards/accuracy_reward": 0.5000000037252903,
      "rewards/format_reward": 0.9500000029802322,
      "step": 622
    },
    {
      "completion_length": 300.60000228881836,
      "epoch": 0.6459305339554173,
      "grad_norm": 1.7969317436218262,
      "kl": 0.51513671875,
      "learning_rate": 2.880387460851917e-06,
      "loss": 0.108,
      "reward": 1.225000023841858,
      "reward_std": 0.6021890863776207,
      "rewards/accuracy_reward": 0.34999999962747097,
      "rewards/format_reward": 0.8750000298023224,
      "step": 623
    },
    {
      "completion_length": 242.57500076293945,
      "epoch": 0.6469673405909798,
      "grad_norm": 0.5022680759429932,
      "kl": 0.31103515625,
      "learning_rate": 2.879677764748298e-06,
      "loss": 0.0101,
      "reward": 1.475000023841858,
      "reward_std": 0.31719935685396194,
      "rewards/accuracy_reward": 0.5249999985098839,
      "rewards/format_reward": 0.9500000029802322,
      "step": 624
    },
    {
      "completion_length": 245.57500076293945,
      "epoch": 0.6480041472265422,
      "grad_norm": 0.5517757534980774,
      "kl": 0.272705078125,
      "learning_rate": 2.8789660574098863e-06,
      "loss": 0.0851,
      "reward": 1.25,
      "reward_std": 0.3696090541779995,
      "rewards/accuracy_reward": 0.30000000819563866,
      "rewards/format_reward": 0.9500000029802322,
      "step": 625
    },
    {
      "completion_length": 160.2750015258789,
      "epoch": 0.6490409538621047,
      "grad_norm": 0.43617773056030273,
      "kl": 0.24365234375,
      "learning_rate": 2.8782523398741783e-06,
      "loss": -0.0277,
      "reward": 1.3250000327825546,
      "reward_std": 0.22360680997371674,
      "rewards/accuracy_reward": 0.3750000074505806,
      "rewards/format_reward": 0.9500000178813934,
      "step": 626
    },
    {
      "completion_length": 194.95000457763672,
      "epoch": 0.6500777604976672,
      "grad_norm": 0.6225988268852234,
      "kl": 0.365234375,
      "learning_rate": 2.8775366131816006e-06,
      "loss": 0.0594,
      "reward": 1.4250000268220901,
      "reward_std": 0.37323956564068794,
      "rewards/accuracy_reward": 0.5250000040978193,
      "rewards/format_reward": 0.9000000208616257,
      "step": 627
    },
    {
      "completion_length": 320.20000076293945,
      "epoch": 0.6511145671332297,
      "grad_norm": 5.313282489776611,
      "kl": 1.0943603515625,
      "learning_rate": 2.876818878375509e-06,
      "loss": 0.2469,
      "reward": 1.2750000208616257,
      "reward_std": 0.4415663853287697,
      "rewards/accuracy_reward": 0.3750000074505806,
      "rewards/format_reward": 0.9000000059604645,
      "step": 628
    },
    {
      "completion_length": 197.725004196167,
      "epoch": 0.6521513737687922,
      "grad_norm": 2.7158896923065186,
      "kl": 1.244873046875,
      "learning_rate": 2.8760991365021856e-06,
      "loss": 0.2859,
      "reward": 1.4250000268220901,
      "reward_std": 0.5048274546861649,
      "rewards/accuracy_reward": 0.5000000093132257,
      "rewards/format_reward": 0.925000011920929,
      "step": 629
    },
    {
      "completion_length": 232.45000457763672,
      "epoch": 0.6531881804043546,
      "grad_norm": 16.022092819213867,
      "kl": 4.732421875,
      "learning_rate": 2.8753773886108405e-06,
      "loss": 0.3514,
      "reward": 1.6500000059604645,
      "reward_std": 0.44533541798591614,
      "rewards/accuracy_reward": 0.7250000089406967,
      "rewards/format_reward": 0.9250000268220901,
      "step": 630
    },
    {
      "completion_length": 307.2250061035156,
      "epoch": 0.654224987039917,
      "grad_norm": 62.19873809814453,
      "kl": 17.984130859375,
      "learning_rate": 2.874653635753605e-06,
      "loss": 1.3583,
      "reward": 1.4250000417232513,
      "reward_std": 0.4525563195347786,
      "rewards/accuracy_reward": 0.550000011920929,
      "rewards/format_reward": 0.8750000149011612,
      "step": 631
    },
    {
      "completion_length": 149.2000026702881,
      "epoch": 0.6552617936754795,
      "grad_norm": 0.5755558013916016,
      "kl": 0.265869140625,
      "learning_rate": 2.8739278789855362e-06,
      "loss": -0.005,
      "reward": 1.3250000327825546,
      "reward_std": 0.40387552231550217,
      "rewards/accuracy_reward": 0.4000000059604645,
      "rewards/format_reward": 0.9250000268220901,
      "step": 632
    },
    {
      "completion_length": 168.62499809265137,
      "epoch": 0.656298600311042,
      "grad_norm": 0.7181000113487244,
      "kl": 0.38720703125,
      "learning_rate": 2.8732001193646104e-06,
      "loss": 0.078,
      "reward": 1.300000011920929,
      "reward_std": 0.16770510002970695,
      "rewards/accuracy_reward": 0.32500001043081284,
      "rewards/format_reward": 0.9750000089406967,
      "step": 633
    },
    {
      "completion_length": 253.22500610351562,
      "epoch": 0.6573354069466044,
      "grad_norm": 77.6446304321289,
      "kl": 20.80859375,
      "learning_rate": 2.872470357951724e-06,
      "loss": 1.654,
      "reward": 1.225000038743019,
      "reward_std": 0.3245587572455406,
      "rewards/accuracy_reward": 0.2999999988824129,
      "rewards/format_reward": 0.925000011920929,
      "step": 634
    },
    {
      "completion_length": 251.20000076293945,
      "epoch": 0.6583722135821669,
      "grad_norm": 1.6625399589538574,
      "kl": 1.81103515625,
      "learning_rate": 2.871738595810692e-06,
      "loss": 0.212,
      "reward": 1.3999999910593033,
      "reward_std": 0.2686570808291435,
      "rewards/accuracy_reward": 0.47500001825392246,
      "rewards/format_reward": 0.925000011920929,
      "step": 635
    },
    {
      "completion_length": 499.15001678466797,
      "epoch": 0.6594090202177294,
      "grad_norm": 8.252129554748535,
      "kl": 2.3154296875,
      "learning_rate": 2.871004834008246e-06,
      "loss": 0.3376,
      "reward": 1.0500000417232513,
      "reward_std": 0.597340852022171,
      "rewards/accuracy_reward": 0.2750000059604645,
      "rewards/format_reward": 0.7750000208616257,
      "step": 636
    },
    {
      "completion_length": 207.90000534057617,
      "epoch": 0.6604458268532919,
      "grad_norm": 2.2362051010131836,
      "kl": 0.253662109375,
      "learning_rate": 2.8702690736140318e-06,
      "loss": 0.0666,
      "reward": 1.550000011920929,
      "reward_std": 0.43636220321059227,
      "rewards/accuracy_reward": 0.5750000029802322,
      "rewards/format_reward": 0.9750000089406967,
      "step": 637
    },
    {
      "completion_length": 230.37500381469727,
      "epoch": 0.6614826334888543,
      "grad_norm": 1.240039587020874,
      "kl": 0.55322265625,
      "learning_rate": 2.8695313157006097e-06,
      "loss": 0.1479,
      "reward": 1.3250000029802322,
      "reward_std": 0.18026872724294662,
      "rewards/accuracy_reward": 0.45000000298023224,
      "rewards/format_reward": 0.8750000149011612,
      "step": 638
    },
    {
      "completion_length": 283.0250053405762,
      "epoch": 0.6625194401244168,
      "grad_norm": 3.555227041244507,
      "kl": 0.6796875,
      "learning_rate": 2.868791561343451e-06,
      "loss": 0.16,
      "reward": 1.475000023841858,
      "reward_std": 0.2920721210539341,
      "rewards/accuracy_reward": 0.5750000178813934,
      "rewards/format_reward": 0.9000000059604645,
      "step": 639
    },
    {
      "completion_length": 114.42500305175781,
      "epoch": 0.6635562467599793,
      "grad_norm": 0.4519474506378174,
      "kl": 0.255126953125,
      "learning_rate": 2.868049811620938e-06,
      "loss": 0.0198,
      "reward": 1.6500000059604645,
      "reward_std": 0.16770509257912636,
      "rewards/accuracy_reward": 0.6500000022351742,
      "rewards/format_reward": 1.0,
      "step": 640
    },
    {
      "completion_length": 236.2750015258789,
      "epoch": 0.6645930533955418,
      "grad_norm": 7.132613182067871,
      "kl": 4.499267578125,
      "learning_rate": 2.8673060676143616e-06,
      "loss": 0.4182,
      "reward": 1.4000000059604645,
      "reward_std": 0.620261438190937,
      "rewards/accuracy_reward": 0.550000011920929,
      "rewards/format_reward": 0.8500000238418579,
      "step": 641
    },
    {
      "completion_length": 224.92499923706055,
      "epoch": 0.6656298600311042,
      "grad_norm": 40.20530319213867,
      "kl": 15.702392578125,
      "learning_rate": 2.8665603304079197e-06,
      "loss": 1.1686,
      "reward": 1.0250000059604645,
      "reward_std": 0.3731010742485523,
      "rewards/accuracy_reward": 0.20000000298023224,
      "rewards/format_reward": 0.8250000029802322,
      "step": 642
    },
    {
      "completion_length": 186.72500038146973,
      "epoch": 0.6666666666666666,
      "grad_norm": 0.7823323011398315,
      "kl": 0.713623046875,
      "learning_rate": 2.865812601088715e-06,
      "loss": 0.154,
      "reward": 1.5500000417232513,
      "reward_std": 0.41643913835287094,
      "rewards/accuracy_reward": 0.6500000059604645,
      "rewards/format_reward": 0.9000000208616257,
      "step": 643
    },
    {
      "completion_length": 192.20000457763672,
      "epoch": 0.6677034733022291,
      "grad_norm": 1.6138575077056885,
      "kl": 1.10498046875,
      "learning_rate": 2.865062880746756e-06,
      "loss": 0.1178,
      "reward": 1.5750000476837158,
      "reward_std": 0.2937843129038811,
      "rewards/accuracy_reward": 0.6000000089406967,
      "rewards/format_reward": 0.9750000089406967,
      "step": 644
    },
    {
      "completion_length": 202.75000381469727,
      "epoch": 0.6687402799377916,
      "grad_norm": 1.0543968677520752,
      "kl": 1.532470703125,
      "learning_rate": 2.864311170474953e-06,
      "loss": 0.1468,
      "reward": 1.350000023841858,
      "reward_std": 0.29270511120557785,
      "rewards/accuracy_reward": 0.42500001192092896,
      "rewards/format_reward": 0.925000011920929,
      "step": 645
    },
    {
      "completion_length": 143.85000038146973,
      "epoch": 0.6697770865733541,
      "grad_norm": 0.39155247807502747,
      "kl": 0.27880859375,
      "learning_rate": 2.8635574713691158e-06,
      "loss": 0.017,
      "reward": 1.350000023841858,
      "reward_std": 0.12436702474951744,
      "rewards/accuracy_reward": 0.37500000186264515,
      "rewards/format_reward": 0.9750000089406967,
      "step": 646
    },
    {
      "completion_length": 149.47500228881836,
      "epoch": 0.6708138932089165,
      "grad_norm": 5.471457481384277,
      "kl": 2.15234375,
      "learning_rate": 2.8628017845279553e-06,
      "loss": 0.1969,
      "reward": 1.4250000268220901,
      "reward_std": 0.4415663853287697,
      "rewards/accuracy_reward": 0.5250000134110451,
      "rewards/format_reward": 0.9000000208616257,
      "step": 647
    },
    {
      "completion_length": 180.02500534057617,
      "epoch": 0.671850699844479,
      "grad_norm": 1.4774538278579712,
      "kl": 1.03564453125,
      "learning_rate": 2.862044111053079e-06,
      "loss": 0.1221,
      "reward": 1.350000038743019,
      "reward_std": 0.4291412830352783,
      "rewards/accuracy_reward": 0.4500000048428774,
      "rewards/format_reward": 0.9000000208616257,
      "step": 648
    },
    {
      "completion_length": 247.97500228881836,
      "epoch": 0.6728875064800415,
      "grad_norm": 0.93613600730896,
      "kl": 0.880126953125,
      "learning_rate": 2.8612844520489902e-06,
      "loss": 0.1469,
      "reward": 1.2000000178813934,
      "reward_std": 0.4129471369087696,
      "rewards/accuracy_reward": 0.30000000447034836,
      "rewards/format_reward": 0.9000000208616257,
      "step": 649
    },
    {
      "completion_length": 251.92500686645508,
      "epoch": 0.673924313115604,
      "grad_norm": 2.6798095703125,
      "kl": 1.1048583984375,
      "learning_rate": 2.8605228086230877e-06,
      "loss": 0.211,
      "reward": 1.475000023841858,
      "reward_std": 0.391311913728714,
      "rewards/accuracy_reward": 0.5500000044703484,
      "rewards/format_reward": 0.9250000268220901,
      "step": 650
    },
    {
      "completion_length": 218.125,
      "epoch": 0.6749611197511665,
      "grad_norm": 2.4933316707611084,
      "kl": 1.405029296875,
      "learning_rate": 2.8597591818856625e-06,
      "loss": 0.18,
      "reward": 1.4500000178813934,
      "reward_std": 0.45977719500660896,
      "rewards/accuracy_reward": 0.5750000104308128,
      "rewards/format_reward": 0.875,
      "step": 651
    },
    {
      "completion_length": 183.3750057220459,
      "epoch": 0.6759979263867288,
      "grad_norm": 0.8898698091506958,
      "kl": 1.068603515625,
      "learning_rate": 2.858993572949896e-06,
      "loss": 0.1626,
      "reward": 1.6250000298023224,
      "reward_std": 0.23617040738463402,
      "rewards/accuracy_reward": 0.7000000029802322,
      "rewards/format_reward": 0.925000011920929,
      "step": 652
    },
    {
      "completion_length": 262.07501220703125,
      "epoch": 0.6770347330222913,
      "grad_norm": 2.555324077606201,
      "kl": 3.16259765625,
      "learning_rate": 2.8582259829318604e-06,
      "loss": 0.3425,
      "reward": 1.5000000149011612,
      "reward_std": 0.36053744331002235,
      "rewards/accuracy_reward": 0.6250000186264515,
      "rewards/format_reward": 0.8750000149011612,
      "step": 653
    },
    {
      "completion_length": 177.27500534057617,
      "epoch": 0.6780715396578538,
      "grad_norm": 1.2724261283874512,
      "kl": 2.198974609375,
      "learning_rate": 2.8574564129505154e-06,
      "loss": 0.2648,
      "reward": 1.3250000178813934,
      "reward_std": 0.452556312084198,
      "rewards/accuracy_reward": 0.4000000022351742,
      "rewards/format_reward": 0.9250000268220901,
      "step": 654
    },
    {
      "completion_length": 144.27500343322754,
      "epoch": 0.6791083462934163,
      "grad_norm": 0.3718305826187134,
      "kl": 0.251220703125,
      "learning_rate": 2.856684864127707e-06,
      "loss": 0.0359,
      "reward": 1.5000000298023224,
      "reward_std": 0.1928323395550251,
      "rewards/accuracy_reward": 0.5000000074505806,
      "rewards/format_reward": 1.0,
      "step": 655
    },
    {
      "completion_length": 239.875,
      "epoch": 0.6801451529289787,
      "grad_norm": 1.6971384286880493,
      "kl": 2.00830078125,
      "learning_rate": 2.8559113375881657e-06,
      "loss": 0.298,
      "reward": 1.0250000357627869,
      "reward_std": 0.31199515238404274,
      "rewards/accuracy_reward": 0.15000000223517418,
      "rewards/format_reward": 0.8750000149011612,
      "step": 656
    },
    {
      "completion_length": 223.1500015258789,
      "epoch": 0.6811819595645412,
      "grad_norm": 1.9796103239059448,
      "kl": 3.091796875,
      "learning_rate": 2.855135834459505e-06,
      "loss": 0.23,
      "reward": 1.5000000298023224,
      "reward_std": 0.546148881316185,
      "rewards/accuracy_reward": 0.5999999940395355,
      "rewards/format_reward": 0.9000000208616257,
      "step": 657
    },
    {
      "completion_length": 201.97500228881836,
      "epoch": 0.6822187662001037,
      "grad_norm": 1.6794363260269165,
      "kl": 1.33544921875,
      "learning_rate": 2.85435835587222e-06,
      "loss": 0.1351,
      "reward": 1.675000011920929,
      "reward_std": 0.12436701729893684,
      "rewards/accuracy_reward": 0.7000000029802322,
      "rewards/format_reward": 0.9750000089406967,
      "step": 658
    },
    {
      "completion_length": 144.45000076293945,
      "epoch": 0.6832555728356662,
      "grad_norm": 0.49781835079193115,
      "kl": 0.26416015625,
      "learning_rate": 2.8535789029596854e-06,
      "loss": -0.0649,
      "reward": 1.324999988079071,
      "reward_std": 0.24873404949903488,
      "rewards/accuracy_reward": 0.32500000298023224,
      "rewards/format_reward": 1.0,
      "step": 659
    },
    {
      "completion_length": 242.22500038146973,
      "epoch": 0.6842923794712286,
      "grad_norm": 0.9583486318588257,
      "kl": 1.5,
      "learning_rate": 2.8527974768581547e-06,
      "loss": 0.1847,
      "reward": 1.4250000417232513,
      "reward_std": 0.2920721173286438,
      "rewards/accuracy_reward": 0.5000000074505806,
      "rewards/format_reward": 0.9250000268220901,
      "step": 660
    },
    {
      "completion_length": 209.17499923706055,
      "epoch": 0.685329186106791,
      "grad_norm": 1.6011143922805786,
      "kl": 0.8896484375,
      "learning_rate": 2.8520140787067567e-06,
      "loss": 0.1899,
      "reward": 1.475000038743019,
      "reward_std": 0.4399927146732807,
      "rewards/accuracy_reward": 0.5750000029802322,
      "rewards/format_reward": 0.9000000357627869,
      "step": 661
    },
    {
      "completion_length": 249.95000076293945,
      "epoch": 0.6863659927423535,
      "grad_norm": 1.6479218006134033,
      "kl": 0.660888671875,
      "learning_rate": 2.8512287096474955e-06,
      "loss": 0.0907,
      "reward": 1.375,
      "reward_std": 0.3731010630726814,
      "rewards/accuracy_reward": 0.42500000819563866,
      "rewards/format_reward": 0.9500000178813934,
      "step": 662
    },
    {
      "completion_length": 138.65000343322754,
      "epoch": 0.687402799377916,
      "grad_norm": 0.9126381278038025,
      "kl": 0.72998046875,
      "learning_rate": 2.8504413708252483e-06,
      "loss": 0.0053,
      "reward": 1.3750000149011612,
      "reward_std": 0.22360680252313614,
      "rewards/accuracy_reward": 0.4000000152736902,
      "rewards/format_reward": 0.9750000089406967,
      "step": 663
    },
    {
      "completion_length": 162.7750015258789,
      "epoch": 0.6884396060134785,
      "grad_norm": 0.6816839575767517,
      "kl": 1.11083984375,
      "learning_rate": 2.8496520633877635e-06,
      "loss": 0.1068,
      "reward": 1.600000023841858,
      "reward_std": 0.16770510748028755,
      "rewards/accuracy_reward": 0.6250000093132257,
      "rewards/format_reward": 0.9750000089406967,
      "step": 664
    },
    {
      "completion_length": 163.40000534057617,
      "epoch": 0.6894764126490409,
      "grad_norm": 0.30915480852127075,
      "kl": 0.21044921875,
      "learning_rate": 2.84886078848566e-06,
      "loss": 0.0071,
      "reward": 1.574999988079071,
      "reward_std": 0.11180339008569717,
      "rewards/accuracy_reward": 0.6000000089406967,
      "rewards/format_reward": 0.9750000089406967,
      "step": 665
    },
    {
      "completion_length": 138.15000534057617,
      "epoch": 0.6905132192846034,
      "grad_norm": 0.2813793420791626,
      "kl": 0.23046875,
      "learning_rate": 2.8480675472724236e-06,
      "loss": 0.0338,
      "reward": 1.6250000298023224,
      "reward_std": 0.1369306445121765,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 666
    },
    {
      "completion_length": 244.97500228881836,
      "epoch": 0.6915500259201659,
      "grad_norm": 8.316036224365234,
      "kl": 6.7216796875,
      "learning_rate": 2.847272340904408e-06,
      "loss": 0.6203,
      "reward": 1.4500000476837158,
      "reward_std": 0.5163118988275528,
      "rewards/accuracy_reward": 0.5750000141561031,
      "rewards/format_reward": 0.8750000298023224,
      "step": 667
    },
    {
      "completion_length": 216.9250030517578,
      "epoch": 0.6925868325557284,
      "grad_norm": 0.797091007232666,
      "kl": 1.13037109375,
      "learning_rate": 2.8464751705408294e-06,
      "loss": 0.1587,
      "reward": 1.2500000149011612,
      "reward_std": 0.2795085124671459,
      "rewards/accuracy_reward": 0.30000000447034836,
      "rewards/format_reward": 0.9500000178813934,
      "step": 668
    },
    {
      "completion_length": 279.1749973297119,
      "epoch": 0.6936236391912908,
      "grad_norm": 4.413926601409912,
      "kl": 4.05224609375,
      "learning_rate": 2.84567603734377e-06,
      "loss": 0.4332,
      "reward": 1.4500000178813934,
      "reward_std": 0.4525563158094883,
      "rewards/accuracy_reward": 0.5250000171363354,
      "rewards/format_reward": 0.9250000268220901,
      "step": 669
    },
    {
      "completion_length": 322.7249984741211,
      "epoch": 0.6946604458268533,
      "grad_norm": 2.120075225830078,
      "kl": 5.30810546875,
      "learning_rate": 2.8448749424781704e-06,
      "loss": 0.3886,
      "reward": 1.2750000208616257,
      "reward_std": 0.4958944171667099,
      "rewards/accuracy_reward": 0.42500000447034836,
      "rewards/format_reward": 0.8500000089406967,
      "step": 670
    },
    {
      "completion_length": 299.50000762939453,
      "epoch": 0.6956972524624158,
      "grad_norm": 0.918604850769043,
      "kl": 0.921630859375,
      "learning_rate": 2.844071887111833e-06,
      "loss": 0.196,
      "reward": 1.725000023841858,
      "reward_std": 0.3354102149605751,
      "rewards/accuracy_reward": 0.8000000193715096,
      "rewards/format_reward": 0.9250000268220901,
      "step": 671
    },
    {
      "completion_length": 267.4250068664551,
      "epoch": 0.6967340590979783,
      "grad_norm": 1.9089648723602295,
      "kl": 1.540283203125,
      "learning_rate": 2.843266872415417e-06,
      "loss": 0.193,
      "reward": 1.4500000178813934,
      "reward_std": 0.3354101926088333,
      "rewards/accuracy_reward": 0.5249999985098839,
      "rewards/format_reward": 0.925000011920929,
      "step": 672
    },
    {
      "completion_length": 206.4250030517578,
      "epoch": 0.6977708657335407,
      "grad_norm": 0.4940345883369446,
      "kl": 0.331787109375,
      "learning_rate": 2.8424598995624386e-06,
      "loss": 0.0692,
      "reward": 1.4250000417232513,
      "reward_std": 0.30463574826717377,
      "rewards/accuracy_reward": 0.4750000014901161,
      "rewards/format_reward": 0.9500000178813934,
      "step": 673
    },
    {
      "completion_length": 187.12500381469727,
      "epoch": 0.6988076723691031,
      "grad_norm": 0.8684625029563904,
      "kl": 0.30908203125,
      "learning_rate": 2.8416509697292676e-06,
      "loss": 0.1091,
      "reward": 1.5000000298023224,
      "reward_std": 0.22360679507255554,
      "rewards/accuracy_reward": 0.5750000029802322,
      "rewards/format_reward": 0.925000011920929,
      "step": 674
    },
    {
      "completion_length": 191.79999923706055,
      "epoch": 0.6998444790046656,
      "grad_norm": 1.0280557870864868,
      "kl": 1.33935546875,
      "learning_rate": 2.8408400840951266e-06,
      "loss": 0.1251,
      "reward": 1.6250000298023224,
      "reward_std": 0.3479738049209118,
      "rewards/accuracy_reward": 0.6750000044703484,
      "rewards/format_reward": 0.9500000178813934,
      "step": 675
    },
    {
      "completion_length": 267.15000915527344,
      "epoch": 0.7008812856402281,
      "grad_norm": 0.3398536741733551,
      "kl": 0.2470703125,
      "learning_rate": 2.8400272438420907e-06,
      "loss": 0.033,
      "reward": 1.2750000208616257,
      "reward_std": 0.2361704260110855,
      "rewards/accuracy_reward": 0.3500000014901161,
      "rewards/format_reward": 0.925000011920929,
      "step": 676
    },
    {
      "completion_length": 391.2000045776367,
      "epoch": 0.7019180922757906,
      "grad_norm": 1.9886372089385986,
      "kl": 1.83837890625,
      "learning_rate": 2.8392124501550828e-06,
      "loss": 0.3499,
      "reward": 1.1500000208616257,
      "reward_std": 0.5283810868859291,
      "rewards/accuracy_reward": 0.2749999985098839,
      "rewards/format_reward": 0.8750000298023224,
      "step": 677
    },
    {
      "completion_length": 174.3000030517578,
      "epoch": 0.702954898911353,
      "grad_norm": 0.7306681275367737,
      "kl": 0.58935546875,
      "learning_rate": 2.838395704221874e-06,
      "loss": 0.0423,
      "reward": 1.7249999940395355,
      "reward_std": 0.3533165641129017,
      "rewards/accuracy_reward": 0.7750000059604645,
      "rewards/format_reward": 0.9500000178813934,
      "step": 678
    },
    {
      "completion_length": 258.9750099182129,
      "epoch": 0.7039917055469155,
      "grad_norm": 10.755302429199219,
      "kl": 6.359130859375,
      "learning_rate": 2.8375770072330817e-06,
      "loss": 0.3311,
      "reward": 1.3250000029802322,
      "reward_std": 0.2722875848412514,
      "rewards/accuracy_reward": 0.4500000011175871,
      "rewards/format_reward": 0.875,
      "step": 679
    },
    {
      "completion_length": 271.7000102996826,
      "epoch": 0.705028512182478,
      "grad_norm": 1.0601376295089722,
      "kl": 1.66357421875,
      "learning_rate": 2.8367563603821675e-06,
      "loss": 0.2495,
      "reward": 1.4750000536441803,
      "reward_std": 0.3354101851582527,
      "rewards/accuracy_reward": 0.5500000193715096,
      "rewards/format_reward": 0.9250000268220901,
      "step": 680
    },
    {
      "completion_length": 313.95000076293945,
      "epoch": 0.7060653188180405,
      "grad_norm": 1.3850581645965576,
      "kl": 1.41650390625,
      "learning_rate": 2.8359337648654334e-06,
      "loss": 0.219,
      "reward": 1.3750000298023224,
      "reward_std": 0.3913118839263916,
      "rewards/accuracy_reward": 0.47500001080334187,
      "rewards/format_reward": 0.9000000208616257,
      "step": 681
    },
    {
      "completion_length": 259.2250061035156,
      "epoch": 0.7071021254536028,
      "grad_norm": 1.035261631011963,
      "kl": 1.794677734375,
      "learning_rate": 2.8351092218820252e-06,
      "loss": 0.2137,
      "reward": 1.625,
      "reward_std": 0.4290027618408203,
      "rewards/accuracy_reward": 0.6750000193715096,
      "rewards/format_reward": 0.9500000029802322,
      "step": 682
    },
    {
      "completion_length": 289.79999923706055,
      "epoch": 0.7081389320891653,
      "grad_norm": 2.4445176124572754,
      "kl": 0.818115234375,
      "learning_rate": 2.8342827326339255e-06,
      "loss": 0.0812,
      "reward": 1.175000011920929,
      "reward_std": 0.31733785569667816,
      "rewards/accuracy_reward": 0.2500000074505806,
      "rewards/format_reward": 0.925000011920929,
      "step": 683
    },
    {
      "completion_length": 278.17499923706055,
      "epoch": 0.7091757387247278,
      "grad_norm": 0.5835633873939514,
      "kl": 0.353759765625,
      "learning_rate": 2.833454298325955e-06,
      "loss": 0.0398,
      "reward": 1.550000011920929,
      "reward_std": 0.2920721285045147,
      "rewards/accuracy_reward": 0.6000000163912773,
      "rewards/format_reward": 0.9500000029802322,
      "step": 684
    },
    {
      "completion_length": 190.80000686645508,
      "epoch": 0.7102125453602903,
      "grad_norm": 1.9967930316925049,
      "kl": 0.5185546875,
      "learning_rate": 2.832623920165769e-06,
      "loss": 0.1104,
      "reward": 1.7750000357627869,
      "reward_std": 0.2361704297363758,
      "rewards/accuracy_reward": 0.800000011920929,
      "rewards/format_reward": 0.9750000089406967,
      "step": 685
    },
    {
      "completion_length": 240.6250114440918,
      "epoch": 0.7112493519958528,
      "grad_norm": 2.839909315109253,
      "kl": 0.76611328125,
      "learning_rate": 2.831791599363858e-06,
      "loss": 0.2053,
      "reward": 1.2750000208616257,
      "reward_std": 0.3245587721467018,
      "rewards/accuracy_reward": 0.32499999925494194,
      "rewards/format_reward": 0.9500000029802322,
      "step": 686
    },
    {
      "completion_length": 175.7750015258789,
      "epoch": 0.7122861586314152,
      "grad_norm": 0.2983464002609253,
      "kl": 0.295166015625,
      "learning_rate": 2.8309573371335426e-06,
      "loss": 0.0193,
      "reward": 1.675000011920929,
      "reward_std": 0.06846532225608826,
      "rewards/accuracy_reward": 0.6750000007450581,
      "rewards/format_reward": 1.0,
      "step": 687
    },
    {
      "completion_length": 150.92499923706055,
      "epoch": 0.7133229652669777,
      "grad_norm": 0.7637765407562256,
      "kl": 0.322998046875,
      "learning_rate": 2.830121134690974e-06,
      "loss": 0.0776,
      "reward": 1.3250000178813934,
      "reward_std": 0.1928323358297348,
      "rewards/accuracy_reward": 0.3499999977648258,
      "rewards/format_reward": 0.9750000089406967,
      "step": 688
    },
    {
      "completion_length": 268.8000011444092,
      "epoch": 0.7143597719025402,
      "grad_norm": 0.7986348271369934,
      "kl": 1.36376953125,
      "learning_rate": 2.8292829932551333e-06,
      "loss": 0.2448,
      "reward": 1.375,
      "reward_std": 0.2812207192182541,
      "rewards/accuracy_reward": 0.45000000298023224,
      "rewards/format_reward": 0.925000011920929,
      "step": 689
    },
    {
      "completion_length": 245.72500228881836,
      "epoch": 0.7153965785381027,
      "grad_norm": 0.7799951434135437,
      "kl": 0.99072265625,
      "learning_rate": 2.8284429140478255e-06,
      "loss": 0.1347,
      "reward": 1.475000023841858,
      "reward_std": 0.47234082594513893,
      "rewards/accuracy_reward": 0.550000011920929,
      "rewards/format_reward": 0.925000011920929,
      "step": 690
    },
    {
      "completion_length": 282.9250068664551,
      "epoch": 0.7164333851736651,
      "grad_norm": 0.9315149784088135,
      "kl": 1.8046875,
      "learning_rate": 2.827600898293683e-06,
      "loss": 0.2766,
      "reward": 1.2500000149011612,
      "reward_std": 0.27950849011540413,
      "rewards/accuracy_reward": 0.3500000014901161,
      "rewards/format_reward": 0.9000000208616257,
      "step": 691
    },
    {
      "completion_length": 182.22500228881836,
      "epoch": 0.7174701918092276,
      "grad_norm": 24.62877655029297,
      "kl": 7.6640625,
      "learning_rate": 2.82675694722016e-06,
      "loss": 0.6286,
      "reward": 1.3250000029802322,
      "reward_std": 0.20019175857305527,
      "rewards/accuracy_reward": 0.37500000931322575,
      "rewards/format_reward": 0.9500000178813934,
      "step": 692
    },
    {
      "completion_length": 183.7250099182129,
      "epoch": 0.71850699844479,
      "grad_norm": 0.7584772109985352,
      "kl": 1.05224609375,
      "learning_rate": 2.8259110620575313e-06,
      "loss": 0.1729,
      "reward": 1.3250000178813934,
      "reward_std": 0.3245587646961212,
      "rewards/accuracy_reward": 0.37499999813735485,
      "rewards/format_reward": 0.9500000178813934,
      "step": 693
    },
    {
      "completion_length": 123.92500305175781,
      "epoch": 0.7195438050803525,
      "grad_norm": 0.2979358434677124,
      "kl": 0.254150390625,
      "learning_rate": 2.8250632440388927e-06,
      "loss": -0.0232,
      "reward": 1.7000000178813934,
      "reward_std": 0.12436701729893684,
      "rewards/accuracy_reward": 0.7000000029802322,
      "rewards/format_reward": 1.0,
      "step": 694
    },
    {
      "completion_length": 223.82501220703125,
      "epoch": 0.720580611715915,
      "grad_norm": 1.2255027294158936,
      "kl": 1.716552734375,
      "learning_rate": 2.8242134944001558e-06,
      "loss": 0.2352,
      "reward": 1.625,
      "reward_std": 0.2795085050165653,
      "rewards/accuracy_reward": 0.6750000193715096,
      "rewards/format_reward": 0.9500000178813934,
      "step": 695
    },
    {
      "completion_length": 152.20000076293945,
      "epoch": 0.7216174183514774,
      "grad_norm": 0.9140526652336121,
      "kl": 0.26806640625,
      "learning_rate": 2.82336181438005e-06,
      "loss": 0.0913,
      "reward": 1.675000011920929,
      "reward_std": 0.16770510748028755,
      "rewards/accuracy_reward": 0.7000000104308128,
      "rewards/format_reward": 0.9750000089406967,
      "step": 696
    },
    {
      "completion_length": 134.87500381469727,
      "epoch": 0.7226542249870399,
      "grad_norm": 0.4066285192966461,
      "kl": 0.310791015625,
      "learning_rate": 2.822508205220117e-06,
      "loss": -0.0062,
      "reward": 1.5750000476837158,
      "reward_std": 0.24873404949903488,
      "rewards/accuracy_reward": 0.5750000067055225,
      "rewards/format_reward": 1.0,
      "step": 697
    },
    {
      "completion_length": 226.60000038146973,
      "epoch": 0.7236910316226024,
      "grad_norm": 0.5627696514129639,
      "kl": 1.79150390625,
      "learning_rate": 2.8216526681647118e-06,
      "loss": 0.0035,
      "reward": 1.8250000178813934,
      "reward_std": 0.2487340308725834,
      "rewards/accuracy_reward": 0.8750000149011612,
      "rewards/format_reward": 0.9500000029802322,
      "step": 698
    },
    {
      "completion_length": 133.60000038146973,
      "epoch": 0.7247278382581649,
      "grad_norm": 0.7156115174293518,
      "kl": 0.302001953125,
      "learning_rate": 2.820795204460999e-06,
      "loss": 0.0222,
      "reward": 1.4749999940395355,
      "reward_std": 0.2361704222857952,
      "rewards/accuracy_reward": 0.5000000074505806,
      "rewards/format_reward": 0.9750000089406967,
      "step": 699
    },
    {
      "completion_length": 123.40000343322754,
      "epoch": 0.7257646448937273,
      "grad_norm": 0.44991451501846313,
      "kl": 0.252685546875,
      "learning_rate": 2.819935815358953e-06,
      "loss": -0.0084,
      "reward": 1.425000011920929,
      "reward_std": 0.18026870489120483,
      "rewards/accuracy_reward": 0.42499999701976776,
      "rewards/format_reward": 1.0,
      "step": 700
    },
    {
      "completion_length": 330.52499771118164,
      "epoch": 0.7268014515292898,
      "grad_norm": 3.5027003288269043,
      "kl": 1.857177734375,
      "learning_rate": 2.819074502111354e-06,
      "loss": 0.2354,
      "reward": 1.5000000149011612,
      "reward_std": 0.41643912717700005,
      "rewards/accuracy_reward": 0.6250000149011612,
      "rewards/format_reward": 0.875,
      "step": 701
    },
    {
      "completion_length": 294.82500076293945,
      "epoch": 0.7278382581648523,
      "grad_norm": 34.1741828918457,
      "kl": 10.48681640625,
      "learning_rate": 2.818211265973787e-06,
      "loss": 0.4339,
      "reward": 1.2000000178813934,
      "reward_std": 0.32818929105997086,
      "rewards/accuracy_reward": 0.3250000048428774,
      "rewards/format_reward": 0.8750000149011612,
      "step": 702
    },
    {
      "completion_length": 178.725004196167,
      "epoch": 0.7288750648004148,
      "grad_norm": 0.9051024913787842,
      "kl": 0.39794921875,
      "learning_rate": 2.8173461082046407e-06,
      "loss": 0.0751,
      "reward": 1.3000000417232513,
      "reward_std": 0.24151314049959183,
      "rewards/accuracy_reward": 0.32500000298023224,
      "rewards/format_reward": 0.9750000089406967,
      "step": 703
    },
    {
      "completion_length": 159.60000610351562,
      "epoch": 0.7299118714359772,
      "grad_norm": 1.2098740339279175,
      "kl": 0.4189453125,
      "learning_rate": 2.8164790300651042e-06,
      "loss": 0.0657,
      "reward": 1.5000000298023224,
      "reward_std": 0.41643914952874184,
      "rewards/accuracy_reward": 0.5250000078231096,
      "rewards/format_reward": 0.9750000089406967,
      "step": 704
    },
    {
      "completion_length": 143.62500190734863,
      "epoch": 0.7309486780715396,
      "grad_norm": 0.858209490776062,
      "kl": 1.26513671875,
      "learning_rate": 2.815610032819168e-06,
      "loss": 0.1172,
      "reward": 1.475000023841858,
      "reward_std": 0.31199515610933304,
      "rewards/accuracy_reward": 0.550000011920929,
      "rewards/format_reward": 0.9250000268220901,
      "step": 705
    },
    {
      "completion_length": 216.0250072479248,
      "epoch": 0.7319854847071021,
      "grad_norm": 0.6318058967590332,
      "kl": 0.768798828125,
      "learning_rate": 2.8147391177336176e-06,
      "loss": 0.0993,
      "reward": 1.7000000029802322,
      "reward_std": 0.1604842059314251,
      "rewards/accuracy_reward": 0.7500000093132257,
      "rewards/format_reward": 0.9500000029802322,
      "step": 706
    },
    {
      "completion_length": 224.87500381469727,
      "epoch": 0.7330222913426646,
      "grad_norm": 518.7442016601562,
      "kl": 119.13671875,
      "learning_rate": 2.8138662860780356e-06,
      "loss": 4.7663,
      "reward": 1.2500000149011612,
      "reward_std": 0.2920721285045147,
      "rewards/accuracy_reward": 0.3250000048428774,
      "rewards/format_reward": 0.925000011920929,
      "step": 707
    },
    {
      "completion_length": 115.35000038146973,
      "epoch": 0.7340590979782271,
      "grad_norm": 0.6044578552246094,
      "kl": 0.365234375,
      "learning_rate": 2.8129915391247988e-06,
      "loss": 0.0126,
      "reward": 1.4749999940395355,
      "reward_std": 0.055901702493429184,
      "rewards/accuracy_reward": 0.4750000014901161,
      "rewards/format_reward": 1.0,
      "step": 708
    },
    {
      "completion_length": 186.9250087738037,
      "epoch": 0.7350959046137895,
      "grad_norm": 2.9357755184173584,
      "kl": 1.806884765625,
      "learning_rate": 2.8121148781490754e-06,
      "loss": 0.1944,
      "reward": 1.4250000268220901,
      "reward_std": 0.22894952073693275,
      "rewards/accuracy_reward": 0.4749999940395355,
      "rewards/format_reward": 0.9500000178813934,
      "step": 709
    },
    {
      "completion_length": 138.32500076293945,
      "epoch": 0.736132711249352,
      "grad_norm": 0.2896471321582794,
      "kl": 0.189453125,
      "learning_rate": 2.8112363044288243e-06,
      "loss": 0.0259,
      "reward": 1.5250000059604645,
      "reward_std": 0.12436702102422714,
      "rewards/accuracy_reward": 0.5500000007450581,
      "rewards/format_reward": 0.9750000089406967,
      "step": 710
    },
    {
      "completion_length": 258.32500648498535,
      "epoch": 0.7371695178849145,
      "grad_norm": 18.005449295043945,
      "kl": 4.0224609375,
      "learning_rate": 2.810355819244792e-06,
      "loss": 0.4517,
      "reward": 1.350000023841858,
      "reward_std": 0.3407529331743717,
      "rewards/accuracy_reward": 0.42500000447034836,
      "rewards/format_reward": 0.925000011920929,
      "step": 711
    },
    {
      "completion_length": 114.47500228881836,
      "epoch": 0.738206324520477,
      "grad_norm": 0.36921098828315735,
      "kl": 0.2666015625,
      "learning_rate": 2.809473423880512e-06,
      "loss": 0.0209,
      "reward": 1.675000011920929,
      "reward_std": 0.12436702102422714,
      "rewards/accuracy_reward": 0.6749999970197678,
      "rewards/format_reward": 1.0,
      "step": 712
    },
    {
      "completion_length": 199.05000686645508,
      "epoch": 0.7392431311560393,
      "grad_norm": 0.9610119462013245,
      "kl": 1.69140625,
      "learning_rate": 2.8085891196223025e-06,
      "loss": 0.1894,
      "reward": 1.1500000208616257,
      "reward_std": 0.30463574454188347,
      "rewards/accuracy_reward": 0.20000000670552254,
      "rewards/format_reward": 0.9500000178813934,
      "step": 713
    },
    {
      "completion_length": 154.62500381469727,
      "epoch": 0.7402799377916018,
      "grad_norm": 1.1751526594161987,
      "kl": 0.3271484375,
      "learning_rate": 2.8077029077592633e-06,
      "loss": 0.0186,
      "reward": 1.225000023841858,
      "reward_std": 0.30463574081659317,
      "rewards/accuracy_reward": 0.27500000409781933,
      "rewards/format_reward": 0.9500000178813934,
      "step": 714
    },
    {
      "completion_length": 209.70000839233398,
      "epoch": 0.7413167444271643,
      "grad_norm": 1.0980820655822754,
      "kl": 0.487548828125,
      "learning_rate": 2.806814789583277e-06,
      "loss": 0.1487,
      "reward": 1.5250000059604645,
      "reward_std": 0.2487340308725834,
      "rewards/accuracy_reward": 0.6000000089406967,
      "rewards/format_reward": 0.925000011920929,
      "step": 715
    },
    {
      "completion_length": 227.0000114440918,
      "epoch": 0.7423535510627268,
      "grad_norm": 0.5780226588249207,
      "kl": 1.57666015625,
      "learning_rate": 2.8059247663890032e-06,
      "loss": 0.2161,
      "reward": 1.5250000059604645,
      "reward_std": 0.18026871606707573,
      "rewards/accuracy_reward": 0.6000000089406967,
      "rewards/format_reward": 0.9249999970197678,
      "step": 716
    },
    {
      "completion_length": 280.20000076293945,
      "epoch": 0.7433903576982893,
      "grad_norm": 1.4871811866760254,
      "kl": 1.12109375,
      "learning_rate": 2.8050328394738803e-06,
      "loss": 0.2866,
      "reward": 1.4250000417232513,
      "reward_std": 0.4729737937450409,
      "rewards/accuracy_reward": 0.5500000081956387,
      "rewards/format_reward": 0.8750000149011612,
      "step": 717
    },
    {
      "completion_length": 310.9500045776367,
      "epoch": 0.7444271643338517,
      "grad_norm": 1.3770198822021484,
      "kl": 0.87255859375,
      "learning_rate": 2.8041390101381195e-06,
      "loss": 0.229,
      "reward": 1.4000000059604645,
      "reward_std": 0.6291945092380047,
      "rewards/accuracy_reward": 0.5250000134110451,
      "rewards/format_reward": 0.8750000149011612,
      "step": 718
    },
    {
      "completion_length": 225.77500343322754,
      "epoch": 0.7454639709694142,
      "grad_norm": 0.8252406120300293,
      "kl": 1.41943359375,
      "learning_rate": 2.8032432796847076e-06,
      "loss": 0.2017,
      "reward": 1.4249999970197678,
      "reward_std": 0.21275536343455315,
      "rewards/accuracy_reward": 0.5000000149011612,
      "rewards/format_reward": 0.925000011920929,
      "step": 719
    },
    {
      "completion_length": 256.90000343322754,
      "epoch": 0.7465007776049767,
      "grad_norm": 0.9165952205657959,
      "kl": 1.5322265625,
      "learning_rate": 2.802345649419402e-06,
      "loss": 0.2268,
      "reward": 1.375,
      "reward_std": 0.329762976616621,
      "rewards/accuracy_reward": 0.5000000037252903,
      "rewards/format_reward": 0.8750000149011612,
      "step": 720
    },
    {
      "completion_length": 112.55000305175781,
      "epoch": 0.7475375842405392,
      "grad_norm": 0.8553647398948669,
      "kl": 0.322265625,
      "learning_rate": 2.8014461206507292e-06,
      "loss": -0.0239,
      "reward": 1.5250000357627869,
      "reward_std": 0.30463573709130287,
      "rewards/accuracy_reward": 0.550000011920929,
      "rewards/format_reward": 0.9750000089406967,
      "step": 721
    },
    {
      "completion_length": 308.075008392334,
      "epoch": 0.7485743908761016,
      "grad_norm": 2.7667524814605713,
      "kl": 3.8203125,
      "learning_rate": 2.800544694689983e-06,
      "loss": 0.3563,
      "reward": 1.2750000208616257,
      "reward_std": 0.4604102000594139,
      "rewards/accuracy_reward": 0.4000000134110451,
      "rewards/format_reward": 0.8750000149011612,
      "step": 722
    },
    {
      "completion_length": 280.6499996185303,
      "epoch": 0.749611197511664,
      "grad_norm": 6.384510517120361,
      "kl": 3.0322265625,
      "learning_rate": 2.7996413728512236e-06,
      "loss": 0.3557,
      "reward": 1.4500000029802322,
      "reward_std": 0.26129764690995216,
      "rewards/accuracy_reward": 0.550000011920929,
      "rewards/format_reward": 0.9000000059604645,
      "step": 723
    },
    {
      "completion_length": 279.8000068664551,
      "epoch": 0.7506480041472265,
      "grad_norm": 7.1993584632873535,
      "kl": 2.51171875,
      "learning_rate": 2.7987361564512757e-06,
      "loss": 0.354,
      "reward": 1.3250000178813934,
      "reward_std": 0.38409097865223885,
      "rewards/accuracy_reward": 0.4249999988824129,
      "rewards/format_reward": 0.9000000357627869,
      "step": 724
    },
    {
      "completion_length": 149.2750015258789,
      "epoch": 0.751684810782789,
      "grad_norm": 3.0475800037384033,
      "kl": 2.4169921875,
      "learning_rate": 2.797829046809723e-06,
      "loss": 0.1504,
      "reward": 1.300000011920929,
      "reward_std": 0.36053744331002235,
      "rewards/accuracy_reward": 0.42500000447034836,
      "rewards/format_reward": 0.8750000149011612,
      "step": 725
    },
    {
      "completion_length": 177.97500228881836,
      "epoch": 0.7527216174183515,
      "grad_norm": 0.7727159857749939,
      "kl": 0.75732421875,
      "learning_rate": 2.7969200452489117e-06,
      "loss": 0.1334,
      "reward": 1.574999988079071,
      "reward_std": 0.22360680997371674,
      "rewards/accuracy_reward": 0.6000000163912773,
      "rewards/format_reward": 0.9750000089406967,
      "step": 726
    },
    {
      "completion_length": 162.05000495910645,
      "epoch": 0.7537584240539139,
      "grad_norm": 1.6836689710617065,
      "kl": 1.5498046875,
      "learning_rate": 2.7960091530939453e-06,
      "loss": 0.1498,
      "reward": 1.375,
      "reward_std": 0.11180340498685837,
      "rewards/accuracy_reward": 0.4000000059604645,
      "rewards/format_reward": 0.9750000089406967,
      "step": 727
    },
    {
      "completion_length": 108.67500305175781,
      "epoch": 0.7547952306894764,
      "grad_norm": 0.8589237332344055,
      "kl": 0.76123046875,
      "learning_rate": 2.7950963716726833e-06,
      "loss": 0.0888,
      "reward": 1.3750000298023224,
      "reward_std": 0.2361704222857952,
      "rewards/accuracy_reward": 0.42500001192092896,
      "rewards/format_reward": 0.9500000178813934,
      "step": 728
    },
    {
      "completion_length": 119.17500114440918,
      "epoch": 0.7558320373250389,
      "grad_norm": 0.9010735750198364,
      "kl": 0.44287109375,
      "learning_rate": 2.7941817023157385e-06,
      "loss": 0.0313,
      "reward": 1.600000023841858,
      "reward_std": 0.1928323470056057,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 0.9750000089406967,
      "step": 729
    },
    {
      "completion_length": 121.82500076293945,
      "epoch": 0.7568688439606014,
      "grad_norm": 2.7615885734558105,
      "kl": 1.18115234375,
      "learning_rate": 2.7932651463564763e-06,
      "loss": 0.1171,
      "reward": 1.300000011920929,
      "reward_std": 0.1604841984808445,
      "rewards/accuracy_reward": 0.3249999973922968,
      "rewards/format_reward": 0.9750000089406967,
      "step": 730
    },
    {
      "completion_length": 102.30000305175781,
      "epoch": 0.7579056505961638,
      "grad_norm": 0.4340980350971222,
      "kl": 0.39697265625,
      "learning_rate": 2.792346705131013e-06,
      "loss": 0.0185,
      "reward": 1.2000000178813934,
      "reward_std": 0.18026871979236603,
      "rewards/accuracy_reward": 0.2000000048428774,
      "rewards/format_reward": 1.0,
      "step": 731
    },
    {
      "completion_length": 118.50000381469727,
      "epoch": 0.7589424572317263,
      "grad_norm": 0.6814145445823669,
      "kl": 0.67236328125,
      "learning_rate": 2.791426379978213e-06,
      "loss": 0.0499,
      "reward": 1.5250000357627869,
      "reward_std": 0.23617041483521461,
      "rewards/accuracy_reward": 0.550000011920929,
      "rewards/format_reward": 0.9750000089406967,
      "step": 732
    },
    {
      "completion_length": 139.77500534057617,
      "epoch": 0.7599792638672888,
      "grad_norm": 3.444451093673706,
      "kl": 2.74609375,
      "learning_rate": 2.7905041722396854e-06,
      "loss": 0.1425,
      "reward": 1.4000000059604645,
      "reward_std": 0.18026872351765633,
      "rewards/accuracy_reward": 0.45000000298023224,
      "rewards/format_reward": 0.9500000178813934,
      "step": 733
    },
    {
      "completion_length": 429.12499809265137,
      "epoch": 0.7610160705028512,
      "grad_norm": 10.602200508117676,
      "kl": 9.31494140625,
      "learning_rate": 2.7895800832597865e-06,
      "loss": 0.7934,
      "reward": 1.3249999955296516,
      "reward_std": 0.3731010667979717,
      "rewards/accuracy_reward": 0.5000000149011612,
      "rewards/format_reward": 0.8250000104308128,
      "step": 734
    },
    {
      "completion_length": 126.12500381469727,
      "epoch": 0.7620528771384136,
      "grad_norm": 0.5543495416641235,
      "kl": 0.70166015625,
      "learning_rate": 2.788654114385612e-06,
      "loss": -0.0408,
      "reward": 1.4750000536441803,
      "reward_std": 0.24873404949903488,
      "rewards/accuracy_reward": 0.5000000074505806,
      "rewards/format_reward": 0.9750000089406967,
      "step": 735
    },
    {
      "completion_length": 106.92499923706055,
      "epoch": 0.7630896837739761,
      "grad_norm": 0.33099156618118286,
      "kl": 0.531982421875,
      "learning_rate": 2.787726266967e-06,
      "loss": -0.0037,
      "reward": 1.675000011920929,
      "reward_std": 0.16770510002970695,
      "rewards/accuracy_reward": 0.7000000178813934,
      "rewards/format_reward": 0.9750000089406967,
      "step": 736
    },
    {
      "completion_length": 266.87500381469727,
      "epoch": 0.7641264904095386,
      "grad_norm": 1.9715381860733032,
      "kl": 1.3359375,
      "learning_rate": 2.7867965423565273e-06,
      "loss": 0.2879,
      "reward": 1.3000000268220901,
      "reward_std": 0.3479738160967827,
      "rewards/accuracy_reward": 0.4000000096857548,
      "rewards/format_reward": 0.9000000357627869,
      "step": 737
    },
    {
      "completion_length": 204.62499809265137,
      "epoch": 0.7651632970451011,
      "grad_norm": 0.3641264736652374,
      "kl": 0.6787109375,
      "learning_rate": 2.785864941909505e-06,
      "loss": 0.0829,
      "reward": 1.4750000089406967,
      "reward_std": 0.05590169504284859,
      "rewards/accuracy_reward": 0.525000000372529,
      "rewards/format_reward": 0.9500000029802322,
      "step": 738
    },
    {
      "completion_length": 233.37500381469727,
      "epoch": 0.7662001036806636,
      "grad_norm": 1.9150782823562622,
      "kl": 1.84033203125,
      "learning_rate": 2.784931466983981e-06,
      "loss": 0.2618,
      "reward": 1.2750000208616257,
      "reward_std": 0.4038755036890507,
      "rewards/accuracy_reward": 0.3750000037252903,
      "rewards/format_reward": 0.9000000208616257,
      "step": 739
    },
    {
      "completion_length": 168.02499961853027,
      "epoch": 0.767236910316226,
      "grad_norm": 23.784427642822266,
      "kl": 9.75,
      "learning_rate": 2.783996118940734e-06,
      "loss": 0.6841,
      "reward": 1.225000038743019,
      "reward_std": 0.3245587609708309,
      "rewards/accuracy_reward": 0.30000001192092896,
      "rewards/format_reward": 0.9250000268220901,
      "step": 740
    },
    {
      "completion_length": 413.52500915527344,
      "epoch": 0.7682737169517885,
      "grad_norm": 28.01406478881836,
      "kl": 10.80078125,
      "learning_rate": 2.7830588991432745e-06,
      "loss": 0.8084,
      "reward": 1.200000062584877,
      "reward_std": 0.30463574454188347,
      "rewards/accuracy_reward": 0.3500000014901161,
      "rewards/format_reward": 0.8500000238418579,
      "step": 741
    },
    {
      "completion_length": 134.600004196167,
      "epoch": 0.769310523587351,
      "grad_norm": 1.1930382251739502,
      "kl": 1.346923828125,
      "learning_rate": 2.7821198089578417e-06,
      "loss": 0.1408,
      "reward": 1.375,
      "reward_std": 0.1604842059314251,
      "rewards/accuracy_reward": 0.42500000074505806,
      "rewards/format_reward": 0.9500000178813934,
      "step": 742
    },
    {
      "completion_length": 269.3500061035156,
      "epoch": 0.7703473302229135,
      "grad_norm": 3.615288496017456,
      "kl": 4.735107421875,
      "learning_rate": 2.7811788497533998e-06,
      "loss": 0.4038,
      "reward": 1.2500000298023224,
      "reward_std": 0.36053742095828056,
      "rewards/accuracy_reward": 0.4000000022351742,
      "rewards/format_reward": 0.8500000089406967,
      "step": 743
    },
    {
      "completion_length": 355.05001068115234,
      "epoch": 0.7713841368584758,
      "grad_norm": 23.248554229736328,
      "kl": 9.390625,
      "learning_rate": 2.780236022901639e-06,
      "loss": 0.8676,
      "reward": 1.225000038743019,
      "reward_std": 0.632825031876564,
      "rewards/accuracy_reward": 0.42500000447034836,
      "rewards/format_reward": 0.800000011920929,
      "step": 744
    },
    {
      "completion_length": 301.225004196167,
      "epoch": 0.7724209434940383,
      "grad_norm": 1.500929594039917,
      "kl": 1.21484375,
      "learning_rate": 2.7792913297769723e-06,
      "loss": 0.1665,
      "reward": 1.2750000208616257,
      "reward_std": 0.4604101926088333,
      "rewards/accuracy_reward": 0.4000000059604645,
      "rewards/format_reward": 0.875,
      "step": 745
    },
    {
      "completion_length": 242.7750015258789,
      "epoch": 0.7734577501296008,
      "grad_norm": 0.9008773565292358,
      "kl": 1.644775390625,
      "learning_rate": 2.7783447717565313e-06,
      "loss": 0.2006,
      "reward": 1.600000023841858,
      "reward_std": 0.2795084938406944,
      "rewards/accuracy_reward": 0.7000000104308128,
      "rewards/format_reward": 0.9000000059604645,
      "step": 746
    },
    {
      "completion_length": 321.52500915527344,
      "epoch": 0.7744945567651633,
      "grad_norm": 4.788297176361084,
      "kl": 4.009765625,
      "learning_rate": 2.777396350220169e-06,
      "loss": 0.436,
      "reward": 1.1500000059604645,
      "reward_std": 0.3534550555050373,
      "rewards/accuracy_reward": 0.25000000186264515,
      "rewards/format_reward": 0.9000000357627869,
      "step": 747
    },
    {
      "completion_length": 274.0750045776367,
      "epoch": 0.7755313634007258,
      "grad_norm": 2.297362804412842,
      "kl": 1.6220703125,
      "learning_rate": 2.7764460665504522e-06,
      "loss": 0.245,
      "reward": 1.4250000268220901,
      "reward_std": 0.3245587684214115,
      "rewards/accuracy_reward": 0.5000000037252903,
      "rewards/format_reward": 0.925000011920929,
      "step": 748
    },
    {
      "completion_length": 185.92500495910645,
      "epoch": 0.7765681700362882,
      "grad_norm": 1.0662373304367065,
      "kl": 1.704345703125,
      "learning_rate": 2.775493922132664e-06,
      "loss": 0.16,
      "reward": 1.3750000298023224,
      "reward_std": 0.2361704260110855,
      "rewards/accuracy_reward": 0.42500000447034836,
      "rewards/format_reward": 0.9500000029802322,
      "step": 749
    },
    {
      "completion_length": 183.27500343322754,
      "epoch": 0.7776049766718507,
      "grad_norm": 0.667378306388855,
      "kl": 0.505615234375,
      "learning_rate": 2.7745399183548e-06,
      "loss": 0.0602,
      "reward": 1.5499999970197678,
      "reward_std": 0.16770510002970695,
      "rewards/accuracy_reward": 0.5750000104308128,
      "rewards/format_reward": 0.9750000089406967,
      "step": 750
    },
    {
      "completion_length": 165.1500015258789,
      "epoch": 0.7786417833074132,
      "grad_norm": 0.5699002146720886,
      "kl": 0.941162109375,
      "learning_rate": 2.7735840566075646e-06,
      "loss": 0.0966,
      "reward": 1.4500000029802322,
      "reward_std": 0.11180340498685837,
      "rewards/accuracy_reward": 0.4750000014901161,
      "rewards/format_reward": 0.9750000089406967,
      "step": 751
    },
    {
      "completion_length": 170.72500228881836,
      "epoch": 0.7796785899429757,
      "grad_norm": 3.4902076721191406,
      "kl": 1.697265625,
      "learning_rate": 2.7726263382843726e-06,
      "loss": 0.1494,
      "reward": 1.5999999940395355,
      "reward_std": 0.25609344989061356,
      "rewards/accuracy_reward": 0.6250000186264515,
      "rewards/format_reward": 0.9750000089406967,
      "step": 752
    },
    {
      "completion_length": 129.47500228881836,
      "epoch": 0.7807153965785381,
      "grad_norm": 0.3129628598690033,
      "kl": 0.272705078125,
      "learning_rate": 2.771666764781345e-06,
      "loss": 0.0141,
      "reward": 1.425000011920929,
      "reward_std": 0.11180339008569717,
      "rewards/accuracy_reward": 0.4250000063329935,
      "rewards/format_reward": 1.0,
      "step": 753
    },
    {
      "completion_length": 171.75000381469727,
      "epoch": 0.7817522032141005,
      "grad_norm": 0.5923978090286255,
      "kl": 0.968505859375,
      "learning_rate": 2.7707053374973055e-06,
      "loss": 0.0773,
      "reward": 1.4000000059604645,
      "reward_std": 0.21638592705130577,
      "rewards/accuracy_reward": 0.4750000089406967,
      "rewards/format_reward": 0.9249999970197678,
      "step": 754
    },
    {
      "completion_length": 132.92500114440918,
      "epoch": 0.782789009849663,
      "grad_norm": 0.7645208835601807,
      "kl": 0.856201171875,
      "learning_rate": 2.7697420578337823e-06,
      "loss": 0.0276,
      "reward": 1.5750000178813934,
      "reward_std": 0.21275537833571434,
      "rewards/accuracy_reward": 0.6000000089406967,
      "rewards/format_reward": 0.9750000089406967,
      "step": 755
    },
    {
      "completion_length": 174.9250030517578,
      "epoch": 0.7838258164852255,
      "grad_norm": 2.4929704666137695,
      "kl": 0.317626953125,
      "learning_rate": 2.768776927195003e-06,
      "loss": 0.0762,
      "reward": 1.600000023841858,
      "reward_std": 0.281220693141222,
      "rewards/accuracy_reward": 0.6500000059604645,
      "rewards/format_reward": 0.9500000178813934,
      "step": 756
    },
    {
      "completion_length": 185.57500076293945,
      "epoch": 0.784862623120788,
      "grad_norm": 1.6370223760604858,
      "kl": 0.39794921875,
      "learning_rate": 2.7678099469878927e-06,
      "loss": 0.0027,
      "reward": 1.5250000655651093,
      "reward_std": 0.36053744703531265,
      "rewards/accuracy_reward": 0.5750000104308128,
      "rewards/format_reward": 0.9500000178813934,
      "step": 757
    },
    {
      "completion_length": 108.42500114440918,
      "epoch": 0.7858994297563504,
      "grad_norm": 0.4571923613548279,
      "kl": 0.2900390625,
      "learning_rate": 2.766841118622074e-06,
      "loss": -0.0458,
      "reward": 1.3750000298023224,
      "reward_std": 0.18026871979236603,
      "rewards/accuracy_reward": 0.3750000037252903,
      "rewards/format_reward": 1.0,
      "step": 758
    },
    {
      "completion_length": 200.82500648498535,
      "epoch": 0.7869362363919129,
      "grad_norm": 2.9244139194488525,
      "kl": 3.072265625,
      "learning_rate": 2.765870443509863e-06,
      "loss": 0.3235,
      "reward": 1.4000000059604645,
      "reward_std": 0.4472135864198208,
      "rewards/accuracy_reward": 0.5,
      "rewards/format_reward": 0.9000000059604645,
      "step": 759
    },
    {
      "completion_length": 134.95000457763672,
      "epoch": 0.7879730430274754,
      "grad_norm": 1.5931257009506226,
      "kl": 0.43212890625,
      "learning_rate": 2.7648979230662682e-06,
      "loss": 0.0302,
      "reward": 1.5,
      "reward_std": 0.31199514865875244,
      "rewards/accuracy_reward": 0.5500000212341547,
      "rewards/format_reward": 0.9500000178813934,
      "step": 760
    },
    {
      "completion_length": 267.575008392334,
      "epoch": 0.7890098496630379,
      "grad_norm": 2.634326934814453,
      "kl": 3.15771484375,
      "learning_rate": 2.763923558708988e-06,
      "loss": 0.3409,
      "reward": 1.2999999970197678,
      "reward_std": 0.2795084938406944,
      "rewards/accuracy_reward": 0.375,
      "rewards/format_reward": 0.9250000268220901,
      "step": 761
    },
    {
      "completion_length": 128.4250030517578,
      "epoch": 0.7900466562986003,
      "grad_norm": 0.6787009835243225,
      "kl": 0.467041015625,
      "learning_rate": 2.7629473518584088e-06,
      "loss": 0.0092,
      "reward": 1.350000023841858,
      "reward_std": 0.2920721285045147,
      "rewards/accuracy_reward": 0.3750000074505806,
      "rewards/format_reward": 0.9750000089406967,
      "step": 762
    },
    {
      "completion_length": 264.8250026702881,
      "epoch": 0.7910834629341628,
      "grad_norm": 0.48455703258514404,
      "kl": 1.8251953125,
      "learning_rate": 2.7619693039376025e-06,
      "loss": 0.2773,
      "reward": 1.2000000029802322,
      "reward_std": 0.15685366839170456,
      "rewards/accuracy_reward": 0.2750000059604645,
      "rewards/format_reward": 0.925000011920929,
      "step": 763
    },
    {
      "completion_length": 204.0750026702881,
      "epoch": 0.7921202695697253,
      "grad_norm": 0.7012991309165955,
      "kl": 0.8583984375,
      "learning_rate": 2.7609894163723257e-06,
      "loss": 0.1481,
      "reward": 1.600000023841858,
      "reward_std": 0.42178187519311905,
      "rewards/accuracy_reward": 0.6749999970197678,
      "rewards/format_reward": 0.925000011920929,
      "step": 764
    },
    {
      "completion_length": 263.72500228881836,
      "epoch": 0.7931570762052877,
      "grad_norm": 1.760319709777832,
      "kl": 1.53173828125,
      "learning_rate": 2.760007690591016e-06,
      "loss": 0.1753,
      "reward": 1.2000000327825546,
      "reward_std": 0.3371223732829094,
      "rewards/accuracy_reward": 0.32500000670552254,
      "rewards/format_reward": 0.8750000149011612,
      "step": 765
    },
    {
      "completion_length": 131.42500495910645,
      "epoch": 0.7941938828408501,
      "grad_norm": 0.4826253056526184,
      "kl": 0.946044921875,
      "learning_rate": 2.7590241280247906e-06,
      "loss": 0.1077,
      "reward": 1.5,
      "reward_std": 0.18026871979236603,
      "rewards/accuracy_reward": 0.5250000022351742,
      "rewards/format_reward": 0.9750000089406967,
      "step": 766
    },
    {
      "completion_length": 117.82500076293945,
      "epoch": 0.7952306894764126,
      "grad_norm": 0.8102556467056274,
      "kl": 0.491455078125,
      "learning_rate": 2.758038730107446e-06,
      "loss": 0.0176,
      "reward": 1.550000011920929,
      "reward_std": 0.21275536715984344,
      "rewards/accuracy_reward": 0.5750000029802322,
      "rewards/format_reward": 0.9750000089406967,
      "step": 767
    },
    {
      "completion_length": 131.2750015258789,
      "epoch": 0.7962674961119751,
      "grad_norm": 0.7947399020195007,
      "kl": 1.2119140625,
      "learning_rate": 2.7570514982754507e-06,
      "loss": 0.061,
      "reward": 1.1250000149011612,
      "reward_std": 0.22360679507255554,
      "rewards/accuracy_reward": 0.17500000074505806,
      "rewards/format_reward": 0.9500000178813934,
      "step": 768
    },
    {
      "completion_length": 215.7250099182129,
      "epoch": 0.7973043027475376,
      "grad_norm": 3.324897527694702,
      "kl": 1.559814453125,
      "learning_rate": 2.7560624339679505e-06,
      "loss": 0.2325,
      "reward": 1.475000023841858,
      "reward_std": 0.3245587795972824,
      "rewards/accuracy_reward": 0.550000011920929,
      "rewards/format_reward": 0.925000011920929,
      "step": 769
    },
    {
      "completion_length": 254.65000915527344,
      "epoch": 0.7983411093831001,
      "grad_norm": 2.051250696182251,
      "kl": 3.601806640625,
      "learning_rate": 2.75507153862676e-06,
      "loss": 0.2329,
      "reward": 1.300000011920929,
      "reward_std": 0.27228758856654167,
      "rewards/accuracy_reward": 0.42499999701976776,
      "rewards/format_reward": 0.8750000149011612,
      "step": 770
    },
    {
      "completion_length": 113.37500381469727,
      "epoch": 0.7993779160186625,
      "grad_norm": 0.8960034847259521,
      "kl": 1.621826171875,
      "learning_rate": 2.7540788136963637e-06,
      "loss": 0.1835,
      "reward": 1.350000023841858,
      "reward_std": 0.40387552231550217,
      "rewards/accuracy_reward": 0.4250000063329935,
      "rewards/format_reward": 0.925000011920929,
      "step": 771
    },
    {
      "completion_length": 134.89999961853027,
      "epoch": 0.800414722654225,
      "grad_norm": 0.7624129056930542,
      "kl": 0.291259765625,
      "learning_rate": 2.7530842606239135e-06,
      "loss": 0.088,
      "reward": 1.2750000059604645,
      "reward_std": 0.3479738309979439,
      "rewards/accuracy_reward": 0.35000000707805157,
      "rewards/format_reward": 0.9250000268220901,
      "step": 772
    },
    {
      "completion_length": 127.10000419616699,
      "epoch": 0.8014515292897875,
      "grad_norm": 0.4995887279510498,
      "kl": 0.360107421875,
      "learning_rate": 2.7520878808592255e-06,
      "loss": 0.0129,
      "reward": 1.6500000357627869,
      "reward_std": 0.3479738347232342,
      "rewards/accuracy_reward": 0.7250000089406967,
      "rewards/format_reward": 0.925000011920929,
      "step": 773
    },
    {
      "completion_length": 192.8000030517578,
      "epoch": 0.80248833592535,
      "grad_norm": 1.0516695976257324,
      "kl": 1.542236328125,
      "learning_rate": 2.7510896758547796e-06,
      "loss": 0.1974,
      "reward": 1.3250000029802322,
      "reward_std": 0.2920721173286438,
      "rewards/accuracy_reward": 0.4499999973922968,
      "rewards/format_reward": 0.8750000149011612,
      "step": 774
    },
    {
      "completion_length": 286.1500053405762,
      "epoch": 0.8035251425609123,
      "grad_norm": 1.4060876369476318,
      "kl": 2.7529296875,
      "learning_rate": 2.7500896470657166e-06,
      "loss": 0.3356,
      "reward": 1.200000062584877,
      "reward_std": 0.5842827521264553,
      "rewards/accuracy_reward": 0.3500000014901161,
      "rewards/format_reward": 0.8500000238418579,
      "step": 775
    },
    {
      "completion_length": 212.77499961853027,
      "epoch": 0.8045619491964748,
      "grad_norm": 1.4797383546829224,
      "kl": 1.840576171875,
      "learning_rate": 2.749087795949834e-06,
      "loss": 0.2744,
      "reward": 1.1000000536441803,
      "reward_std": 0.3913118988275528,
      "rewards/accuracy_reward": 0.20000000298023224,
      "rewards/format_reward": 0.9000000357627869,
      "step": 776
    },
    {
      "completion_length": 171.00000190734863,
      "epoch": 0.8055987558320373,
      "grad_norm": 8.790672302246094,
      "kl": 3.203125,
      "learning_rate": 2.7480841239675883e-06,
      "loss": 0.2483,
      "reward": 1.1250000298023224,
      "reward_std": 0.4814124368131161,
      "rewards/accuracy_reward": 0.25000000186264515,
      "rewards/format_reward": 0.8750000298023224,
      "step": 777
    },
    {
      "completion_length": 208.57500648498535,
      "epoch": 0.8066355624675998,
      "grad_norm": 0.8135401606559753,
      "kl": 1.341064453125,
      "learning_rate": 2.747078632582089e-06,
      "loss": 0.0399,
      "reward": 1.3750000596046448,
      "reward_std": 0.26129765436053276,
      "rewards/accuracy_reward": 0.42500001192092896,
      "rewards/format_reward": 0.9500000029802322,
      "step": 778
    },
    {
      "completion_length": 237.90000343322754,
      "epoch": 0.8076723691031623,
      "grad_norm": 1.9624338150024414,
      "kl": 1.96484375,
      "learning_rate": 2.7460713232590973e-06,
      "loss": 0.3619,
      "reward": 1.4000000357627869,
      "reward_std": 0.45977723225951195,
      "rewards/accuracy_reward": 0.5250000134110451,
      "rewards/format_reward": 0.8750000149011612,
      "step": 779
    },
    {
      "completion_length": 91.25,
      "epoch": 0.8087091757387247,
      "grad_norm": 2.1631221771240234,
      "kl": 5.6884765625,
      "learning_rate": 2.745062197467027e-06,
      "loss": -0.0101,
      "reward": 1.3250000029802322,
      "reward_std": 0.11180339753627777,
      "rewards/accuracy_reward": 0.375,
      "rewards/format_reward": 0.9500000178813934,
      "step": 780
    },
    {
      "completion_length": 204.02500915527344,
      "epoch": 0.8097459823742872,
      "grad_norm": 2.164458990097046,
      "kl": 2.19189453125,
      "learning_rate": 2.7440512566769368e-06,
      "loss": 0.2447,
      "reward": 1.8500000536441803,
      "reward_std": 0.292072094976902,
      "rewards/accuracy_reward": 0.9000000208616257,
      "rewards/format_reward": 0.9500000178813934,
      "step": 781
    },
    {
      "completion_length": 107.25000190734863,
      "epoch": 0.8107827890098497,
      "grad_norm": 0.8715801239013672,
      "kl": 0.63037109375,
      "learning_rate": 2.7430385023625334e-06,
      "loss": 0.073,
      "reward": 1.2500000298023224,
      "reward_std": 0.18026872724294662,
      "rewards/accuracy_reward": 0.2750000022351742,
      "rewards/format_reward": 0.9750000089406967,
      "step": 782
    },
    {
      "completion_length": 149.97500228881836,
      "epoch": 0.8118195956454122,
      "grad_norm": 2.8529815673828125,
      "kl": 2.78369140625,
      "learning_rate": 2.7420239360001654e-06,
      "loss": 0.258,
      "reward": 1.8250000178813934,
      "reward_std": 0.3354101926088333,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 0.9500000178813934,
      "step": 783
    },
    {
      "completion_length": 98.1500015258789,
      "epoch": 0.8128564022809746,
      "grad_norm": 1.0965875387191772,
      "kl": 0.5849609375,
      "learning_rate": 2.741007559068825e-06,
      "loss": 0.0432,
      "reward": 1.375,
      "reward_std": 0.11180339008569717,
      "rewards/accuracy_reward": 0.40000000037252903,
      "rewards/format_reward": 0.9750000089406967,
      "step": 784
    },
    {
      "completion_length": 200.9000072479248,
      "epoch": 0.813893208916537,
      "grad_norm": 0.8102331757545471,
      "kl": 1.67041015625,
      "learning_rate": 2.739989373050142e-06,
      "loss": 0.196,
      "reward": 1.1749999970197678,
      "reward_std": 0.16770510002970695,
      "rewards/accuracy_reward": 0.22500000149011612,
      "rewards/format_reward": 0.9500000178813934,
      "step": 785
    },
    {
      "completion_length": 275.60000228881836,
      "epoch": 0.8149300155520995,
      "grad_norm": 10.27814769744873,
      "kl": 7.51904296875,
      "learning_rate": 2.7389693794283847e-06,
      "loss": 0.7619,
      "reward": 1.3750000298023224,
      "reward_std": 0.45977722853422165,
      "rewards/accuracy_reward": 0.4750000052154064,
      "rewards/format_reward": 0.9000000208616257,
      "step": 786
    },
    {
      "completion_length": 141.5000057220459,
      "epoch": 0.815966822187662,
      "grad_norm": 1.1177572011947632,
      "kl": 1.534423828125,
      "learning_rate": 2.7379475796904555e-06,
      "loss": 0.1921,
      "reward": 1.4500000327825546,
      "reward_std": 0.2920721247792244,
      "rewards/accuracy_reward": 0.4750000089406967,
      "rewards/format_reward": 0.9750000089406967,
      "step": 787
    },
    {
      "completion_length": 159.07500076293945,
      "epoch": 0.8170036288232244,
      "grad_norm": 0.926374614238739,
      "kl": 0.93505859375,
      "learning_rate": 2.73692397532589e-06,
      "loss": 0.1362,
      "reward": 1.449999988079071,
      "reward_std": 0.36053742468357086,
      "rewards/accuracy_reward": 0.4750000014901161,
      "rewards/format_reward": 0.9750000089406967,
      "step": 788
    },
    {
      "completion_length": 151.77500343322754,
      "epoch": 0.8180404354587869,
      "grad_norm": 0.6936078071594238,
      "kl": 0.8388671875,
      "learning_rate": 2.7358985678268544e-06,
      "loss": 0.0432,
      "reward": 1.3499999940395355,
      "reward_std": 0.28485121950507164,
      "rewards/accuracy_reward": 0.3750000037252903,
      "rewards/format_reward": 0.9750000089406967,
      "step": 789
    },
    {
      "completion_length": 166.9000072479248,
      "epoch": 0.8190772420943494,
      "grad_norm": 0.9093707799911499,
      "kl": 0.895263671875,
      "learning_rate": 2.734871358688144e-06,
      "loss": 0.1818,
      "reward": 1.5750000178813934,
      "reward_std": 0.33712238073349,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 0.9500000029802322,
      "step": 790
    },
    {
      "completion_length": 286.17500495910645,
      "epoch": 0.8201140487299119,
      "grad_norm": 11.58954906463623,
      "kl": 5.29541015625,
      "learning_rate": 2.7338423494071795e-06,
      "loss": 0.6152,
      "reward": 1.4249999970197678,
      "reward_std": 0.29270510002970695,
      "rewards/accuracy_reward": 0.5250000059604645,
      "rewards/format_reward": 0.9000000208616257,
      "step": 791
    },
    {
      "completion_length": 293.9500026702881,
      "epoch": 0.8211508553654744,
      "grad_norm": 2.5993452072143555,
      "kl": 2.10888671875,
      "learning_rate": 2.7328115414840066e-06,
      "loss": 0.3068,
      "reward": 1.2249999940395355,
      "reward_std": 0.3047742620110512,
      "rewards/accuracy_reward": 0.32500000298023224,
      "rewards/format_reward": 0.9000000208616257,
      "step": 792
    },
    {
      "completion_length": 179.12500381469727,
      "epoch": 0.8221876620010368,
      "grad_norm": 43.453060150146484,
      "kl": 9.94287109375,
      "learning_rate": 2.7317789364212927e-06,
      "loss": 0.847,
      "reward": 1.300000011920929,
      "reward_std": 0.30114371702075005,
      "rewards/accuracy_reward": 0.3750000037252903,
      "rewards/format_reward": 0.925000011920929,
      "step": 793
    },
    {
      "completion_length": 198.8250026702881,
      "epoch": 0.8232244686365993,
      "grad_norm": 1.3790888786315918,
      "kl": 1.91845703125,
      "learning_rate": 2.730744535724325e-06,
      "loss": 0.1889,
      "reward": 1.3250000178813934,
      "reward_std": 0.4652584567666054,
      "rewards/accuracy_reward": 0.4000000078231096,
      "rewards/format_reward": 0.925000011920929,
      "step": 794
    },
    {
      "completion_length": 166.50000190734863,
      "epoch": 0.8242612752721618,
      "grad_norm": 13.034732818603516,
      "kl": 8.81005859375,
      "learning_rate": 2.729708340901008e-06,
      "loss": 0.7422,
      "reward": 1.550000011920929,
      "reward_std": 0.25609344989061356,
      "rewards/accuracy_reward": 0.6000000014901161,
      "rewards/format_reward": 0.9500000178813934,
      "step": 795
    },
    {
      "completion_length": 134.90000534057617,
      "epoch": 0.8252980819077242,
      "grad_norm": 1.2326252460479736,
      "kl": 0.88623046875,
      "learning_rate": 2.7286703534618622e-06,
      "loss": 0.0926,
      "reward": 1.6000000536441803,
      "reward_std": 0.2487340345978737,
      "rewards/accuracy_reward": 0.6250000149011612,
      "rewards/format_reward": 0.9750000089406967,
      "step": 796
    },
    {
      "completion_length": 133.35000228881836,
      "epoch": 0.8263348885432866,
      "grad_norm": 1.0299975872039795,
      "kl": 1.529296875,
      "learning_rate": 2.7276305749200206e-06,
      "loss": 0.1607,
      "reward": 1.475000023841858,
      "reward_std": 0.3966546133160591,
      "rewards/accuracy_reward": 0.5250000134110451,
      "rewards/format_reward": 0.9500000178813934,
      "step": 797
    },
    {
      "completion_length": 201.5750026702881,
      "epoch": 0.8273716951788491,
      "grad_norm": 1.292431354522705,
      "kl": 0.6396484375,
      "learning_rate": 2.7265890067912275e-06,
      "loss": 0.0736,
      "reward": 1.600000023841858,
      "reward_std": 0.324558787047863,
      "rewards/accuracy_reward": 0.6499999985098839,
      "rewards/format_reward": 0.9500000178813934,
      "step": 798
    },
    {
      "completion_length": 197.82500839233398,
      "epoch": 0.8284085018144116,
      "grad_norm": 1.056061863899231,
      "kl": 0.56640625,
      "learning_rate": 2.725545650593837e-06,
      "loss": 0.0988,
      "reward": 1.4749999940395355,
      "reward_std": 0.25609343126416206,
      "rewards/accuracy_reward": 0.5250000152736902,
      "rewards/format_reward": 0.9500000178813934,
      "step": 799
    },
    {
      "completion_length": 151.5750026702881,
      "epoch": 0.8294453084499741,
      "grad_norm": 2.8053700923919678,
      "kl": 2.60009765625,
      "learning_rate": 2.7245005078488077e-06,
      "loss": 0.2199,
      "reward": 1.324999988079071,
      "reward_std": 0.46511994674801826,
      "rewards/accuracy_reward": 0.3750000037252903,
      "rewards/format_reward": 0.9500000178813934,
      "step": 800
    },
    {
      "completion_length": 137.5250015258789,
      "epoch": 0.8304821150855366,
      "grad_norm": 0.9269716739654541,
      "kl": 1.56103515625,
      "learning_rate": 2.7234535800797037e-06,
      "loss": 0.1335,
      "reward": 1.0999999940395355,
      "reward_std": 0.16770510002970695,
      "rewards/accuracy_reward": 0.12500000186264515,
      "rewards/format_reward": 0.9750000089406967,
      "step": 801
    },
    {
      "completion_length": 195.5750026702881,
      "epoch": 0.831518921721099,
      "grad_norm": 5.310616970062256,
      "kl": 3.5379638671875,
      "learning_rate": 2.7224048688126915e-06,
      "loss": 0.3573,
      "reward": 1.7500000596046448,
      "reward_std": 0.41643913835287094,
      "rewards/accuracy_reward": 0.800000011920929,
      "rewards/format_reward": 0.9500000178813934,
      "step": 802
    },
    {
      "completion_length": 243.20000839233398,
      "epoch": 0.8325557283566615,
      "grad_norm": 11.0709810256958,
      "kl": 6.59619140625,
      "learning_rate": 2.7213543755765377e-06,
      "loss": 0.6267,
      "reward": 1.225000023841858,
      "reward_std": 0.40387551486492157,
      "rewards/accuracy_reward": 0.30000000447034836,
      "rewards/format_reward": 0.9250000268220901,
      "step": 803
    },
    {
      "completion_length": 199.4000072479248,
      "epoch": 0.833592534992224,
      "grad_norm": 1.7671570777893066,
      "kl": 2.40234375,
      "learning_rate": 2.720302101902605e-06,
      "loss": 0.2168,
      "reward": 1.5250000059604645,
      "reward_std": 0.4363621585071087,
      "rewards/accuracy_reward": 0.6000000089406967,
      "rewards/format_reward": 0.925000011920929,
      "step": 804
    },
    {
      "completion_length": 160.1750030517578,
      "epoch": 0.8346293416277865,
      "grad_norm": 0.5831762552261353,
      "kl": 1.02880859375,
      "learning_rate": 2.719248049324853e-06,
      "loss": 0.1246,
      "reward": 1.7750000357627869,
      "reward_std": 0.3407529145479202,
      "rewards/accuracy_reward": 0.7999999970197678,
      "rewards/format_reward": 0.9750000089406967,
      "step": 805
    },
    {
      "completion_length": 110.62500190734863,
      "epoch": 0.8356661482633488,
      "grad_norm": 0.35738223791122437,
      "kl": 0.25,
      "learning_rate": 2.718192219379835e-06,
      "loss": -0.0206,
      "reward": 1.350000023841858,
      "reward_std": 0.12436702474951744,
      "rewards/accuracy_reward": 0.37500000931322575,
      "rewards/format_reward": 0.9750000089406967,
      "step": 806
    },
    {
      "completion_length": 156.70000457763672,
      "epoch": 0.8367029548989113,
      "grad_norm": 1.1867387294769287,
      "kl": 0.779296875,
      "learning_rate": 2.7171346136066936e-06,
      "loss": 0.0683,
      "reward": 1.5750000178813934,
      "reward_std": 0.373101070523262,
      "rewards/accuracy_reward": 0.6000000052154064,
      "rewards/format_reward": 0.9750000089406967,
      "step": 807
    },
    {
      "completion_length": 196.1250057220459,
      "epoch": 0.8377397615344738,
      "grad_norm": 0.2853090763092041,
      "kl": 0.412841796875,
      "learning_rate": 2.716075233547161e-06,
      "loss": 0.0884,
      "reward": 1.2999999970197678,
      "reward_std": 0.12436702474951744,
      "rewards/accuracy_reward": 0.3500000089406967,
      "rewards/format_reward": 0.9500000029802322,
      "step": 808
    },
    {
      "completion_length": 203.225004196167,
      "epoch": 0.8387765681700363,
      "grad_norm": 1.5570887327194214,
      "kl": 1.113525390625,
      "learning_rate": 2.7150140807455555e-06,
      "loss": 0.1719,
      "reward": 1.449999988079071,
      "reward_std": 0.11180339008569717,
      "rewards/accuracy_reward": 0.5,
      "rewards/format_reward": 0.9500000178813934,
      "step": 809
    },
    {
      "completion_length": 269.4750099182129,
      "epoch": 0.8398133748055988,
      "grad_norm": 1.8617844581604004,
      "kl": 2.31640625,
      "learning_rate": 2.7139511567487806e-06,
      "loss": 0.3669,
      "reward": 1.4500000476837158,
      "reward_std": 0.3913119025528431,
      "rewards/accuracy_reward": 0.550000011920929,
      "rewards/format_reward": 0.9000000357627869,
      "step": 810
    },
    {
      "completion_length": 152.3750057220459,
      "epoch": 0.8408501814411612,
      "grad_norm": 0.6547606587409973,
      "kl": 0.7275390625,
      "learning_rate": 2.712886463106321e-06,
      "loss": 0.0751,
      "reward": 1.5250000059604645,
      "reward_std": 0.22360679507255554,
      "rewards/accuracy_reward": 0.550000011920929,
      "rewards/format_reward": 0.9750000089406967,
      "step": 811
    },
    {
      "completion_length": 165.82500648498535,
      "epoch": 0.8418869880767237,
      "grad_norm": 0.41356778144836426,
      "kl": 0.31201171875,
      "learning_rate": 2.7118200013702407e-06,
      "loss": 0.0653,
      "reward": 1.675000011920929,
      "reward_std": 0.30463574826717377,
      "rewards/accuracy_reward": 0.7000000029802322,
      "rewards/format_reward": 0.9750000089406967,
      "step": 812
    },
    {
      "completion_length": 276.02500915527344,
      "epoch": 0.8429237947122862,
      "grad_norm": 0.9744496941566467,
      "kl": 2.72900390625,
      "learning_rate": 2.7107517730951818e-06,
      "loss": 0.3531,
      "reward": 1.400000050663948,
      "reward_std": 0.4723408408463001,
      "rewards/accuracy_reward": 0.4750000014901161,
      "rewards/format_reward": 0.9250000268220901,
      "step": 813
    },
    {
      "completion_length": 187.32500457763672,
      "epoch": 0.8439606013478487,
      "grad_norm": 1.1766014099121094,
      "kl": 0.46630859375,
      "learning_rate": 2.709681779838362e-06,
      "loss": 0.0853,
      "reward": 1.225000023841858,
      "reward_std": 0.3046357333660126,
      "rewards/accuracy_reward": 0.2750000096857548,
      "rewards/format_reward": 0.9500000178813934,
      "step": 814
    },
    {
      "completion_length": 262.5499973297119,
      "epoch": 0.844997407983411,
      "grad_norm": 0.8816485404968262,
      "kl": 1.880126953125,
      "learning_rate": 2.7086100231595707e-06,
      "loss": 0.2727,
      "reward": 1.1250000298023224,
      "reward_std": 0.23617040738463402,
      "rewards/accuracy_reward": 0.20000000298023224,
      "rewards/format_reward": 0.925000011920929,
      "step": 815
    },
    {
      "completion_length": 181.67500114440918,
      "epoch": 0.8460342146189735,
      "grad_norm": 0.4687977731227875,
      "kl": 1.150634765625,
      "learning_rate": 2.7075365046211684e-06,
      "loss": 0.0978,
      "reward": 1.2500000298023224,
      "reward_std": 0.2487340308725834,
      "rewards/accuracy_reward": 0.2750000059604645,
      "rewards/format_reward": 0.9750000089406967,
      "step": 816
    },
    {
      "completion_length": 228.07500839233398,
      "epoch": 0.847071021254536,
      "grad_norm": 2.606320381164551,
      "kl": 3.34521484375,
      "learning_rate": 2.706461225788085e-06,
      "loss": 0.3432,
      "reward": 1.5250000059604645,
      "reward_std": 0.22360680624842644,
      "rewards/accuracy_reward": 0.5750000104308128,
      "rewards/format_reward": 0.9500000029802322,
      "step": 817
    },
    {
      "completion_length": 156.0500030517578,
      "epoch": 0.8481078278900985,
      "grad_norm": 2.9354310035705566,
      "kl": 2.510498046875,
      "learning_rate": 2.7053841882278156e-06,
      "loss": 0.239,
      "reward": 1.1000000089406967,
      "reward_std": 0.16770510002970695,
      "rewards/accuracy_reward": 0.12500000186264515,
      "rewards/format_reward": 0.9750000089406967,
      "step": 818
    },
    {
      "completion_length": 190.42499923706055,
      "epoch": 0.8491446345256609,
      "grad_norm": 0.6598667502403259,
      "kl": 0.934814453125,
      "learning_rate": 2.7043053935104183e-06,
      "loss": 0.0775,
      "reward": 1.375,
      "reward_std": 0.0883883461356163,
      "rewards/accuracy_reward": 0.40000000037252903,
      "rewards/format_reward": 0.9750000089406967,
      "step": 819
    },
    {
      "completion_length": 182.6250057220459,
      "epoch": 0.8501814411612234,
      "grad_norm": 0.46700766682624817,
      "kl": 1.113525390625,
      "learning_rate": 2.7032248432085143e-06,
      "loss": 0.141,
      "reward": 1.3250000327825546,
      "reward_std": 0.18026872724294662,
      "rewards/accuracy_reward": 0.3500000089406967,
      "rewards/format_reward": 0.9750000089406967,
      "step": 820
    },
    {
      "completion_length": 221.8000087738037,
      "epoch": 0.8512182477967859,
      "grad_norm": 3.7838664054870605,
      "kl": 0.30810546875,
      "learning_rate": 2.702142538897283e-06,
      "loss": 0.1173,
      "reward": 1.3250000178813934,
      "reward_std": 0.22360679507255554,
      "rewards/accuracy_reward": 0.3750000074505806,
      "rewards/format_reward": 0.9500000178813934,
      "step": 821
    },
    {
      "completion_length": 353.32501220703125,
      "epoch": 0.8522550544323484,
      "grad_norm": 1.2203960418701172,
      "kl": 2.563232421875,
      "learning_rate": 2.701058482154461e-06,
      "loss": 0.3616,
      "reward": 1.3750000298023224,
      "reward_std": 0.48141248524188995,
      "rewards/accuracy_reward": 0.5000000037252903,
      "rewards/format_reward": 0.8750000149011612,
      "step": 822
    },
    {
      "completion_length": 303.4500045776367,
      "epoch": 0.8532918610679109,
      "grad_norm": 6.787600994110107,
      "kl": 6.1015625,
      "learning_rate": 2.6999726745603396e-06,
      "loss": 0.6308,
      "reward": 1.475000038743019,
      "reward_std": 0.4237985461950302,
      "rewards/accuracy_reward": 0.5750000178813934,
      "rewards/format_reward": 0.9000000208616257,
      "step": 823
    },
    {
      "completion_length": 325.97500801086426,
      "epoch": 0.8543286677034733,
      "grad_norm": 22.804424285888672,
      "kl": 9.36083984375,
      "learning_rate": 2.698885117697762e-06,
      "loss": 0.8731,
      "reward": 1.2750000208616257,
      "reward_std": 0.3840910233557224,
      "rewards/accuracy_reward": 0.3750000074505806,
      "rewards/format_reward": 0.9000000208616257,
      "step": 824
    },
    {
      "completion_length": 269.49999618530273,
      "epoch": 0.8553654743390358,
      "grad_norm": 1.0976574420928955,
      "kl": 1.403564453125,
      "learning_rate": 2.697795813152122e-06,
      "loss": 0.0994,
      "reward": 1.475000023841858,
      "reward_std": 0.31719936430454254,
      "rewards/accuracy_reward": 0.5500000007450581,
      "rewards/format_reward": 0.925000011920929,
      "step": 825
    },
    {
      "completion_length": 226.20000457763672,
      "epoch": 0.8564022809745983,
      "grad_norm": 1.3571267127990723,
      "kl": 1.186279296875,
      "learning_rate": 2.6967047625113606e-06,
      "loss": 0.1751,
      "reward": 1.3250000327825546,
      "reward_std": 0.31199514865875244,
      "rewards/accuracy_reward": 0.37500000931322575,
      "rewards/format_reward": 0.9500000178813934,
      "step": 826
    },
    {
      "completion_length": 199.25000381469727,
      "epoch": 0.8574390876101607,
      "grad_norm": 1.5436522960662842,
      "kl": 0.467529296875,
      "learning_rate": 2.6956119673659652e-06,
      "loss": 0.0601,
      "reward": 1.7249999940395355,
      "reward_std": 0.16770510748028755,
      "rewards/accuracy_reward": 0.7500000149011612,
      "rewards/format_reward": 0.9750000089406967,
      "step": 827
    },
    {
      "completion_length": 180.52500915527344,
      "epoch": 0.8584758942457231,
      "grad_norm": 2.2522006034851074,
      "kl": 0.473388671875,
      "learning_rate": 2.6945174293089644e-06,
      "loss": 0.0962,
      "reward": 1.4000000357627869,
      "reward_std": 0.2361704260110855,
      "rewards/accuracy_reward": 0.42500000447034836,
      "rewards/format_reward": 0.9750000089406967,
      "step": 828
    },
    {
      "completion_length": 210.47500610351562,
      "epoch": 0.8595127008812856,
      "grad_norm": 0.6633756756782532,
      "kl": 1.012451171875,
      "learning_rate": 2.6934211499359293e-06,
      "loss": 0.1798,
      "reward": 1.1500000208616257,
      "reward_std": 0.1928323470056057,
      "rewards/accuracy_reward": 0.20000000670552254,
      "rewards/format_reward": 0.9500000029802322,
      "step": 829
    },
    {
      "completion_length": 273.35000228881836,
      "epoch": 0.8605495075168481,
      "grad_norm": 0.7028055191040039,
      "kl": 0.66015625,
      "learning_rate": 2.6923231308449686e-06,
      "loss": 0.159,
      "reward": 1.425000011920929,
      "reward_std": 0.22360680997371674,
      "rewards/accuracy_reward": 0.5000000018626451,
      "rewards/format_reward": 0.925000011920929,
      "step": 830
    },
    {
      "completion_length": 220.07500839233398,
      "epoch": 0.8615863141524106,
      "grad_norm": 1.8734394311904907,
      "kl": 1.123291015625,
      "learning_rate": 2.6912233736367267e-06,
      "loss": 0.1689,
      "reward": 1.4500000327825546,
      "reward_std": 0.2920721136033535,
      "rewards/accuracy_reward": 0.5,
      "rewards/format_reward": 0.9500000178813934,
      "step": 831
    },
    {
      "completion_length": 316.2000026702881,
      "epoch": 0.8626231207879731,
      "grad_norm": 1.5336312055587769,
      "kl": 1.52294921875,
      "learning_rate": 2.6901218799143837e-06,
      "loss": 0.1906,
      "reward": 1.3250000178813934,
      "reward_std": 0.36053743585944176,
      "rewards/accuracy_reward": 0.42500000447034836,
      "rewards/format_reward": 0.9000000059604645,
      "step": 832
    },
    {
      "completion_length": 132.975004196167,
      "epoch": 0.8636599274235355,
      "grad_norm": 0.27653202414512634,
      "kl": 0.23974609375,
      "learning_rate": 2.689018651283648e-06,
      "loss": 0.0261,
      "reward": 1.6500000059604645,
      "reward_std": 0.12436701729893684,
      "rewards/accuracy_reward": 0.6499999985098839,
      "rewards/format_reward": 1.0,
      "step": 833
    },
    {
      "completion_length": 267.3249988555908,
      "epoch": 0.864696734059098,
      "grad_norm": 1.0966119766235352,
      "kl": 1.613037109375,
      "learning_rate": 2.6879136893527593e-06,
      "loss": 0.2441,
      "reward": 1.4500000476837158,
      "reward_std": 0.3479738309979439,
      "rewards/accuracy_reward": 0.5250000134110451,
      "rewards/format_reward": 0.925000011920929,
      "step": 834
    },
    {
      "completion_length": 174.17500114440918,
      "epoch": 0.8657335406946605,
      "grad_norm": 0.47363966703414917,
      "kl": 0.385986328125,
      "learning_rate": 2.686806995732484e-06,
      "loss": 0.0541,
      "reward": 1.425000011920929,
      "reward_std": 0.26129766926169395,
      "rewards/accuracy_reward": 0.45000000298023224,
      "rewards/format_reward": 0.9750000089406967,
      "step": 835
    },
    {
      "completion_length": 234.4000015258789,
      "epoch": 0.866770347330223,
      "grad_norm": 2.3432672023773193,
      "kl": 3.037841796875,
      "learning_rate": 2.6856985720361114e-06,
      "loss": 0.3162,
      "reward": 1.4000000357627869,
      "reward_std": 0.40387555956840515,
      "rewards/accuracy_reward": 0.4500000048428774,
      "rewards/format_reward": 0.9500000178813934,
      "step": 836
    },
    {
      "completion_length": 188.27500343322754,
      "epoch": 0.8678071539657853,
      "grad_norm": 0.5459396243095398,
      "kl": 0.52294921875,
      "learning_rate": 2.684588419879455e-06,
      "loss": 0.0788,
      "reward": 1.5250000059604645,
      "reward_std": 0.3966546431183815,
      "rewards/accuracy_reward": 0.5500000193715096,
      "rewards/format_reward": 0.9750000089406967,
      "step": 837
    },
    {
      "completion_length": 330.22500801086426,
      "epoch": 0.8688439606013478,
      "grad_norm": 3.8449041843414307,
      "kl": 3.85595703125,
      "learning_rate": 2.683476540880846e-06,
      "loss": 0.4513,
      "reward": 1.4750000536441803,
      "reward_std": 0.46511993557214737,
      "rewards/accuracy_reward": 0.5750000067055225,
      "rewards/format_reward": 0.9000000208616257,
      "step": 838
    },
    {
      "completion_length": 366.2750053405762,
      "epoch": 0.8698807672369103,
      "grad_norm": 6.319846153259277,
      "kl": 7.76025390625,
      "learning_rate": 2.682362936661134e-06,
      "loss": 0.6544,
      "reward": 1.5,
      "reward_std": 0.40450848266482353,
      "rewards/accuracy_reward": 0.6500000059604645,
      "rewards/format_reward": 0.8500000089406967,
      "step": 839
    },
    {
      "completion_length": 122.9000015258789,
      "epoch": 0.8709175738724728,
      "grad_norm": 0.4149312376976013,
      "kl": 0.285400390625,
      "learning_rate": 2.6812476088436827e-06,
      "loss": 0.0377,
      "reward": 1.4000000059604645,
      "reward_std": 0.16770509257912636,
      "rewards/accuracy_reward": 0.4000000059604645,
      "rewards/format_reward": 1.0,
      "step": 840
    },
    {
      "completion_length": 126.32500076293945,
      "epoch": 0.8719543805080352,
      "grad_norm": 0.42162078619003296,
      "kl": 0.322998046875,
      "learning_rate": 2.6801305590543697e-06,
      "loss": 0.0095,
      "reward": 1.3750000298023224,
      "reward_std": 0.1928323395550251,
      "rewards/accuracy_reward": 0.37499999813735485,
      "rewards/format_reward": 1.0,
      "step": 841
    },
    {
      "completion_length": 267.50000381469727,
      "epoch": 0.8729911871435977,
      "grad_norm": 2.6304068565368652,
      "kl": 1.82666015625,
      "learning_rate": 2.6790117889215812e-06,
      "loss": 0.3007,
      "reward": 1.125,
      "reward_std": 0.27950849011540413,
      "rewards/accuracy_reward": 0.22500000149011612,
      "rewards/format_reward": 0.9000000208616257,
      "step": 842
    },
    {
      "completion_length": 169.42500686645508,
      "epoch": 0.8740279937791602,
      "grad_norm": 1.3741490840911865,
      "kl": 0.783203125,
      "learning_rate": 2.677891300076213e-06,
      "loss": 0.0916,
      "reward": 1.375,
      "reward_std": 0.22360680624842644,
      "rewards/accuracy_reward": 0.40000000037252903,
      "rewards/format_reward": 0.9750000089406967,
      "step": 843
    },
    {
      "completion_length": 173.32500457763672,
      "epoch": 0.8750648004147227,
      "grad_norm": 1.253536343574524,
      "kl": 0.6121826171875,
      "learning_rate": 2.6767690941516653e-06,
      "loss": 0.0845,
      "reward": 1.7249999940395355,
      "reward_std": 0.3479738272726536,
      "rewards/accuracy_reward": 0.7500000298023224,
      "rewards/format_reward": 0.9750000089406967,
      "step": 844
    },
    {
      "completion_length": 263.67500495910645,
      "epoch": 0.8761016070502852,
      "grad_norm": 1.1694815158843994,
      "kl": 1.185546875,
      "learning_rate": 2.6756451727838407e-06,
      "loss": 0.1564,
      "reward": 1.3750000149011612,
      "reward_std": 0.3299015015363693,
      "rewards/accuracy_reward": 0.5000000037252903,
      "rewards/format_reward": 0.875,
      "step": 845
    },
    {
      "completion_length": 181.50000190734863,
      "epoch": 0.8771384136858476,
      "grad_norm": 0.7774064540863037,
      "kl": 0.954833984375,
      "learning_rate": 2.674519537611144e-06,
      "loss": 0.0741,
      "reward": 1.5750000476837158,
      "reward_std": 0.36053744703531265,
      "rewards/accuracy_reward": 0.6000000089406967,
      "rewards/format_reward": 0.9750000089406967,
      "step": 846
    },
    {
      "completion_length": 183.3000030517578,
      "epoch": 0.87817522032141,
      "grad_norm": 0.5851902961730957,
      "kl": 1.0263671875,
      "learning_rate": 2.673392190274478e-06,
      "loss": 0.1204,
      "reward": 1.550000011920929,
      "reward_std": 0.21275537833571434,
      "rewards/accuracy_reward": 0.5750000104308128,
      "rewards/format_reward": 0.9750000089406967,
      "step": 847
    },
    {
      "completion_length": 326.75000381469727,
      "epoch": 0.8792120269569725,
      "grad_norm": 6.058239459991455,
      "kl": 1.504150390625,
      "learning_rate": 2.6722631324172407e-06,
      "loss": 0.2304,
      "reward": 1.3250000327825546,
      "reward_std": 0.3479738160967827,
      "rewards/accuracy_reward": 0.45000001043081284,
      "rewards/format_reward": 0.8750000149011612,
      "step": 848
    },
    {
      "completion_length": 246.55000114440918,
      "epoch": 0.880248833592535,
      "grad_norm": 1.6069053411483765,
      "kl": 0.45849609375,
      "learning_rate": 2.6711323656853235e-06,
      "loss": 0.0939,
      "reward": 1.6500000357627869,
      "reward_std": 0.2361704297363758,
      "rewards/accuracy_reward": 0.7250000033527613,
      "rewards/format_reward": 0.925000011920929,
      "step": 849
    },
    {
      "completion_length": 203.32500076293945,
      "epoch": 0.8812856402280974,
      "grad_norm": 0.8683740496635437,
      "kl": 0.555908203125,
      "learning_rate": 2.6699998917271096e-06,
      "loss": 0.0142,
      "reward": 1.4749999940395355,
      "reward_std": 0.3611704334616661,
      "rewards/accuracy_reward": 0.5250000059604645,
      "rewards/format_reward": 0.9500000029802322,
      "step": 850
    },
    {
      "completion_length": 176.20000076293945,
      "epoch": 0.8823224468636599,
      "grad_norm": 2.5231356620788574,
      "kl": 2.1685791015625,
      "learning_rate": 2.6688657121934713e-06,
      "loss": 0.2105,
      "reward": 1.6250000298023224,
      "reward_std": 0.2920721136033535,
      "rewards/accuracy_reward": 0.6500000208616257,
      "rewards/format_reward": 0.9750000089406967,
      "step": 851
    },
    {
      "completion_length": 313.75000381469727,
      "epoch": 0.8833592534992224,
      "grad_norm": 26.584848403930664,
      "kl": 10.794189453125,
      "learning_rate": 2.6677298287377666e-06,
      "loss": 0.9613,
      "reward": 1.350000023841858,
      "reward_std": 0.535601943731308,
      "rewards/accuracy_reward": 0.45000000670552254,
      "rewards/format_reward": 0.9000000208616257,
      "step": 852
    },
    {
      "completion_length": 376.1000118255615,
      "epoch": 0.8843960601347849,
      "grad_norm": 12.684377670288086,
      "kl": 10.703125,
      "learning_rate": 2.666592243015837e-06,
      "loss": 0.9707,
      "reward": 1.0750000327825546,
      "reward_std": 0.542072132229805,
      "rewards/accuracy_reward": 0.2500000037252903,
      "rewards/format_reward": 0.8250000178813934,
      "step": 853
    },
    {
      "completion_length": 372.6500129699707,
      "epoch": 0.8854328667703474,
      "grad_norm": 1.3346270322799683,
      "kl": 3.55712890625,
      "learning_rate": 2.665452956686006e-06,
      "loss": 0.3998,
      "reward": 1.4500000178813934,
      "reward_std": 0.38409099727869034,
      "rewards/accuracy_reward": 0.5750000178813934,
      "rewards/format_reward": 0.8750000149011612,
      "step": 854
    },
    {
      "completion_length": 209.50000762939453,
      "epoch": 0.8864696734059098,
      "grad_norm": 6.27949333190918,
      "kl": 3.934814453125,
      "learning_rate": 2.664311971409076e-06,
      "loss": 0.3364,
      "reward": 1.3500000536441803,
      "reward_std": 0.46511994302272797,
      "rewards/accuracy_reward": 0.42500001192092896,
      "rewards/format_reward": 0.925000011920929,
      "step": 855
    },
    {
      "completion_length": 294.7000026702881,
      "epoch": 0.8875064800414723,
      "grad_norm": 1.2558188438415527,
      "kl": 2.42041015625,
      "learning_rate": 2.663169288848327e-06,
      "loss": 0.2752,
      "reward": 1.375,
      "reward_std": 0.49746809154748917,
      "rewards/accuracy_reward": 0.4750000089406967,
      "rewards/format_reward": 0.9000000059604645,
      "step": 856
    },
    {
      "completion_length": 430.9500026702881,
      "epoch": 0.8885432866770347,
      "grad_norm": 1.8420369625091553,
      "kl": 3.364501953125,
      "learning_rate": 2.662024910669511e-06,
      "loss": 0.3637,
      "reward": 1.4250000268220901,
      "reward_std": 0.582266092300415,
      "rewards/accuracy_reward": 0.5999999977648258,
      "rewards/format_reward": 0.8250000029802322,
      "step": 857
    },
    {
      "completion_length": 131.52500534057617,
      "epoch": 0.8895800933125972,
      "grad_norm": 0.38641226291656494,
      "kl": 0.2255859375,
      "learning_rate": 2.6608788385408546e-06,
      "loss": -0.0141,
      "reward": 1.3499999940395355,
      "reward_std": 0.1928323470056057,
      "rewards/accuracy_reward": 0.3500000014901161,
      "rewards/format_reward": 1.0,
      "step": 858
    },
    {
      "completion_length": 321.15000915527344,
      "epoch": 0.8906168999481596,
      "grad_norm": 1.2833192348480225,
      "kl": 1.921875,
      "learning_rate": 2.6597310741330515e-06,
      "loss": 0.2401,
      "reward": 1.2750000059604645,
      "reward_std": 0.4976065903902054,
      "rewards/accuracy_reward": 0.4250000063329935,
      "rewards/format_reward": 0.8500000238418579,
      "step": 859
    },
    {
      "completion_length": 118.60000419616699,
      "epoch": 0.8916537065837221,
      "grad_norm": 0.39673030376434326,
      "kl": 0.205078125,
      "learning_rate": 2.6585816191192637e-06,
      "loss": 0.0051,
      "reward": 1.5,
      "reward_std": 0.1928323395550251,
      "rewards/accuracy_reward": 0.5000000074505806,
      "rewards/format_reward": 1.0,
      "step": 860
    },
    {
      "completion_length": 176.8750057220459,
      "epoch": 0.8926905132192846,
      "grad_norm": 2.3243377208709717,
      "kl": 0.39306640625,
      "learning_rate": 2.657430475175117e-06,
      "loss": 0.0705,
      "reward": 1.5000000298023224,
      "reward_std": 0.22360679507255554,
      "rewards/accuracy_reward": 0.5500000044703484,
      "rewards/format_reward": 0.9500000178813934,
      "step": 861
    },
    {
      "completion_length": 292.87500381469727,
      "epoch": 0.8937273198548471,
      "grad_norm": 3.260263442993164,
      "kl": 1.212890625,
      "learning_rate": 2.656277643978699e-06,
      "loss": 0.1044,
      "reward": 1.550000011920929,
      "reward_std": 0.34448180347681046,
      "rewards/accuracy_reward": 0.6250000093132257,
      "rewards/format_reward": 0.9250000268220901,
      "step": 862
    },
    {
      "completion_length": 292.2000141143799,
      "epoch": 0.8947641264904095,
      "grad_norm": 1.0654324293136597,
      "kl": 0.982666015625,
      "learning_rate": 2.655123127210558e-06,
      "loss": 0.0851,
      "reward": 1.5500000268220901,
      "reward_std": 0.31719935685396194,
      "rewards/accuracy_reward": 0.675000011920929,
      "rewards/format_reward": 0.8750000149011612,
      "step": 863
    },
    {
      "completion_length": 318.0000114440918,
      "epoch": 0.895800933125972,
      "grad_norm": 146.21029663085938,
      "kl": 1.025390625,
      "learning_rate": 2.6539669265536987e-06,
      "loss": 0.1239,
      "reward": 1.2000000178813934,
      "reward_std": 0.46511993184685707,
      "rewards/accuracy_reward": 0.3000000100582838,
      "rewards/format_reward": 0.9000000208616257,
      "step": 864
    },
    {
      "completion_length": 179.82500076293945,
      "epoch": 0.8968377397615345,
      "grad_norm": 3.667255163192749,
      "kl": 0.69873046875,
      "learning_rate": 2.6528090436935803e-06,
      "loss": 0.0528,
      "reward": 1.425000011920929,
      "reward_std": 0.2361704260110855,
      "rewards/accuracy_reward": 0.4499999973922968,
      "rewards/format_reward": 0.9750000089406967,
      "step": 865
    },
    {
      "completion_length": 241.0500030517578,
      "epoch": 0.897874546397097,
      "grad_norm": 0.824424684047699,
      "kl": 0.658203125,
      "learning_rate": 2.6516494803181147e-06,
      "loss": 0.0801,
      "reward": 1.550000011920929,
      "reward_std": 0.4849044717848301,
      "rewards/accuracy_reward": 0.6000000089406967,
      "rewards/format_reward": 0.9500000178813934,
      "step": 866
    },
    {
      "completion_length": 235.8499984741211,
      "epoch": 0.8989113530326595,
      "grad_norm": 0.9227349162101746,
      "kl": 0.5498046875,
      "learning_rate": 2.650488238117663e-06,
      "loss": 0.1104,
      "reward": 1.5250000059604645,
      "reward_std": 0.24873404949903488,
      "rewards/accuracy_reward": 0.5750000104308128,
      "rewards/format_reward": 0.9500000029802322,
      "step": 867
    },
    {
      "completion_length": 333.700008392334,
      "epoch": 0.8999481596682218,
      "grad_norm": 1.584023356437683,
      "kl": 1.18994140625,
      "learning_rate": 2.6493253187850347e-06,
      "loss": 0.1872,
      "reward": 1.2249999940395355,
      "reward_std": 0.45318927988409996,
      "rewards/accuracy_reward": 0.35000001080334187,
      "rewards/format_reward": 0.8750000149011612,
      "step": 868
    },
    {
      "completion_length": 330.27500343322754,
      "epoch": 0.9009849663037843,
      "grad_norm": 3.394610643386841,
      "kl": 3.2109375,
      "learning_rate": 2.6481607240154826e-06,
      "loss": 0.3783,
      "reward": 1.3750000298023224,
      "reward_std": 0.3533165380358696,
      "rewards/accuracy_reward": 0.4750000052154064,
      "rewards/format_reward": 0.9000000208616257,
      "step": 869
    },
    {
      "completion_length": 196.25,
      "epoch": 0.9020217729393468,
      "grad_norm": 0.48655158281326294,
      "kl": 0.21875,
      "learning_rate": 2.646994455506704e-06,
      "loss": 0.0491,
      "reward": 1.625,
      "reward_std": 0.39302411302924156,
      "rewards/accuracy_reward": 0.6500000134110451,
      "rewards/format_reward": 0.9750000089406967,
      "step": 870
    },
    {
      "completion_length": 240.25000190734863,
      "epoch": 0.9030585795749093,
      "grad_norm": 2.112935781478882,
      "kl": 1.31494140625,
      "learning_rate": 2.6458265149588345e-06,
      "loss": 0.1163,
      "reward": 1.3250000327825546,
      "reward_std": 0.2920721173286438,
      "rewards/accuracy_reward": 0.4000000096857548,
      "rewards/format_reward": 0.9250000268220901,
      "step": 871
    },
    {
      "completion_length": 249.52500915527344,
      "epoch": 0.9040953862104717,
      "grad_norm": 1.491579294204712,
      "kl": 1.40673828125,
      "learning_rate": 2.6446569040744464e-06,
      "loss": 0.1719,
      "reward": 1.5250000357627869,
      "reward_std": 0.3299014940857887,
      "rewards/accuracy_reward": 0.5750000029802322,
      "rewards/format_reward": 0.9500000029802322,
      "step": 872
    },
    {
      "completion_length": 239.32500076293945,
      "epoch": 0.9051321928460342,
      "grad_norm": 0.9075613021850586,
      "kl": 0.900390625,
      "learning_rate": 2.6434856245585493e-06,
      "loss": 0.1707,
      "reward": 1.6500000357627869,
      "reward_std": 0.22360680997371674,
      "rewards/accuracy_reward": 0.7000000178813934,
      "rewards/format_reward": 0.9500000178813934,
      "step": 873
    },
    {
      "completion_length": 213.05000495910645,
      "epoch": 0.9061689994815967,
      "grad_norm": 1.415359616279602,
      "kl": 1.92919921875,
      "learning_rate": 2.642312678118584e-06,
      "loss": 0.217,
      "reward": 1.3750000298023224,
      "reward_std": 0.27228760346770287,
      "rewards/accuracy_reward": 0.42500000819563866,
      "rewards/format_reward": 0.9500000178813934,
      "step": 874
    },
    {
      "completion_length": 283.8000068664551,
      "epoch": 0.9072058061171592,
      "grad_norm": 40.05736541748047,
      "kl": 9.90576171875,
      "learning_rate": 2.6411380664644208e-06,
      "loss": 0.8472,
      "reward": 1.2500000149011612,
      "reward_std": 0.30463574826717377,
      "rewards/accuracy_reward": 0.32500000298023224,
      "rewards/format_reward": 0.925000011920929,
      "step": 875
    },
    {
      "completion_length": 227.15000534057617,
      "epoch": 0.9082426127527217,
      "grad_norm": 1.3082458972930908,
      "kl": 2.181884765625,
      "learning_rate": 2.6399617913083574e-06,
      "loss": 0.0988,
      "reward": 1.225000023841858,
      "reward_std": 0.41643914207816124,
      "rewards/accuracy_reward": 0.3250000048428774,
      "rewards/format_reward": 0.9000000208616257,
      "step": 876
    },
    {
      "completion_length": 118.55000114440918,
      "epoch": 0.909279419388284,
      "grad_norm": 0.44255509972572327,
      "kl": 0.2578125,
      "learning_rate": 2.6387838543651183e-06,
      "loss": 0.0397,
      "reward": 1.5499999821186066,
      "reward_std": 0.16770510002970695,
      "rewards/accuracy_reward": 0.5750000104308128,
      "rewards/format_reward": 0.9750000089406967,
      "step": 877
    },
    {
      "completion_length": 211.2750015258789,
      "epoch": 0.9103162260238465,
      "grad_norm": 3.5066232681274414,
      "kl": 2.357421875,
      "learning_rate": 2.6376042573518482e-06,
      "loss": 0.2314,
      "reward": 1.5000000298023224,
      "reward_std": 0.2253189980983734,
      "rewards/accuracy_reward": 0.550000011920929,
      "rewards/format_reward": 0.9500000178813934,
      "step": 878
    },
    {
      "completion_length": 240.5250015258789,
      "epoch": 0.911353032659409,
      "grad_norm": 2.016002655029297,
      "kl": 2.30078125,
      "learning_rate": 2.6364230019881132e-06,
      "loss": 0.354,
      "reward": 1.4250000417232513,
      "reward_std": 0.4723408557474613,
      "rewards/accuracy_reward": 0.5250000078231096,
      "rewards/format_reward": 0.9000000208616257,
      "step": 879
    },
    {
      "completion_length": 308.575008392334,
      "epoch": 0.9123898392949715,
      "grad_norm": 3.611039876937866,
      "kl": 2.6015625,
      "learning_rate": 2.6352400899958967e-06,
      "loss": 0.3464,
      "reward": 1.4249999970197678,
      "reward_std": 0.36053743585944176,
      "rewards/accuracy_reward": 0.5250000059604645,
      "rewards/format_reward": 0.9000000059604645,
      "step": 880
    },
    {
      "completion_length": 282.22500228881836,
      "epoch": 0.9134266459305339,
      "grad_norm": 2.582071542739868,
      "kl": 2.25634765625,
      "learning_rate": 2.6340555230995963e-06,
      "loss": 0.152,
      "reward": 1.300000011920929,
      "reward_std": 0.4092182442545891,
      "rewards/accuracy_reward": 0.3750000149011612,
      "rewards/format_reward": 0.925000011920929,
      "step": 881
    },
    {
      "completion_length": 237.97501182556152,
      "epoch": 0.9144634525660964,
      "grad_norm": 1.9722750186920166,
      "kl": 1.4404296875,
      "learning_rate": 2.6328693030260233e-06,
      "loss": 0.1863,
      "reward": 1.4249999970197678,
      "reward_std": 0.27950849011540413,
      "rewards/accuracy_reward": 0.4750000089406967,
      "rewards/format_reward": 0.9500000029802322,
      "step": 882
    },
    {
      "completion_length": 262.6999988555908,
      "epoch": 0.9155002592016589,
      "grad_norm": 3.5364909172058105,
      "kl": 1.622314453125,
      "learning_rate": 2.631681431504397e-06,
      "loss": 0.2271,
      "reward": 1.4000000357627869,
      "reward_std": 0.3533165268599987,
      "rewards/accuracy_reward": 0.475000012665987,
      "rewards/format_reward": 0.925000011920929,
      "step": 883
    },
    {
      "completion_length": 308.45000076293945,
      "epoch": 0.9165370658372214,
      "grad_norm": 2.106987237930298,
      "kl": 1.511474609375,
      "learning_rate": 2.6304919102663467e-06,
      "loss": 0.2561,
      "reward": 1.2750000208616257,
      "reward_std": 0.31719936802983284,
      "rewards/accuracy_reward": 0.3750000037252903,
      "rewards/format_reward": 0.9000000208616257,
      "step": 884
    },
    {
      "completion_length": 103.62500190734863,
      "epoch": 0.9175738724727839,
      "grad_norm": 0.7540234923362732,
      "kl": 0.2861328125,
      "learning_rate": 2.629300741045904e-06,
      "loss": 0.0162,
      "reward": 1.5500000417232513,
      "reward_std": 0.31719936057925224,
      "rewards/accuracy_reward": 0.5500000007450581,
      "rewards/format_reward": 1.0,
      "step": 885
    },
    {
      "completion_length": 272.4250011444092,
      "epoch": 0.9186106791083463,
      "grad_norm": 5.264670372009277,
      "kl": 3.08740234375,
      "learning_rate": 2.628107925579505e-06,
      "loss": 0.3337,
      "reward": 1.5750000178813934,
      "reward_std": 0.31199517846107483,
      "rewards/accuracy_reward": 0.6500000022351742,
      "rewards/format_reward": 0.925000011920929,
      "step": 886
    },
    {
      "completion_length": 229.125,
      "epoch": 0.9196474857439088,
      "grad_norm": 1.4002385139465332,
      "kl": 0.61328125,
      "learning_rate": 2.626913465605985e-06,
      "loss": 0.0328,
      "reward": 1.4250000417232513,
      "reward_std": 0.31719935685396194,
      "rewards/accuracy_reward": 0.4750000014901161,
      "rewards/format_reward": 0.9500000029802322,
      "step": 887
    },
    {
      "completion_length": 177.32500457763672,
      "epoch": 0.9206842923794712,
      "grad_norm": 8.91387939453125,
      "kl": 3.0546875,
      "learning_rate": 2.6257173628665746e-06,
      "loss": 0.237,
      "reward": 1.2000000178813934,
      "reward_std": 0.22894951701164246,
      "rewards/accuracy_reward": 0.2500000037252903,
      "rewards/format_reward": 0.9500000029802322,
      "step": 888
    },
    {
      "completion_length": 123.5,
      "epoch": 0.9217210990150337,
      "grad_norm": 0.1785755157470703,
      "kl": 0.228515625,
      "learning_rate": 2.6245196191049022e-06,
      "loss": -0.0007,
      "reward": 1.300000011920929,
      "reward_std": 0.06846532225608826,
      "rewards/accuracy_reward": 0.30000000074505806,
      "rewards/format_reward": 1.0,
      "step": 889
    },
    {
      "completion_length": 254.17500686645508,
      "epoch": 0.9227579056505961,
      "grad_norm": 3.5954160690307617,
      "kl": 2.435546875,
      "learning_rate": 2.6233202360669864e-06,
      "loss": 0.334,
      "reward": 1.275000050663948,
      "reward_std": 0.4472136162221432,
      "rewards/accuracy_reward": 0.375,
      "rewards/format_reward": 0.9000000357627869,
      "step": 890
    },
    {
      "completion_length": 260.72500228881836,
      "epoch": 0.9237947122861586,
      "grad_norm": 14.043997764587402,
      "kl": 6.834228515625,
      "learning_rate": 2.6221192155012366e-06,
      "loss": 0.6215,
      "reward": 1.6250000298023224,
      "reward_std": 0.3245587609708309,
      "rewards/accuracy_reward": 0.7250000089406967,
      "rewards/format_reward": 0.9000000208616257,
      "step": 891
    },
    {
      "completion_length": 350.0750045776367,
      "epoch": 0.9248315189217211,
      "grad_norm": 92.7138442993164,
      "kl": 18.8623046875,
      "learning_rate": 2.6209165591584487e-06,
      "loss": 1.5923,
      "reward": 1.0750000178813934,
      "reward_std": 0.35394952073693275,
      "rewards/accuracy_reward": 0.22500000335276127,
      "rewards/format_reward": 0.8500000089406967,
      "step": 892
    },
    {
      "completion_length": 241.80001068115234,
      "epoch": 0.9258683255572836,
      "grad_norm": 42.686927795410156,
      "kl": 10.860107421875,
      "learning_rate": 2.619712268791803e-06,
      "loss": 0.9162,
      "reward": 1.4000000357627869,
      "reward_std": 0.2920721173286438,
      "rewards/accuracy_reward": 0.450000012293458,
      "rewards/format_reward": 0.9500000178813934,
      "step": 893
    },
    {
      "completion_length": 269.225004196167,
      "epoch": 0.926905132192846,
      "grad_norm": 125.65151977539062,
      "kl": 40.829833984375,
      "learning_rate": 2.6185063461568624e-06,
      "loss": 3.204,
      "reward": 1.3250000476837158,
      "reward_std": 0.3804604783654213,
      "rewards/accuracy_reward": 0.4000000059604645,
      "rewards/format_reward": 0.925000011920929,
      "step": 894
    },
    {
      "completion_length": 165.17500495910645,
      "epoch": 0.9279419388284085,
      "grad_norm": 0.945558488368988,
      "kl": 0.5986328125,
      "learning_rate": 2.617298793011569e-06,
      "loss": 0.0603,
      "reward": 1.5000000298023224,
      "reward_std": 0.2487340345978737,
      "rewards/accuracy_reward": 0.5250000040978193,
      "rewards/format_reward": 0.9750000089406967,
      "step": 895
    },
    {
      "completion_length": 142.74999809265137,
      "epoch": 0.928978745463971,
      "grad_norm": 0.27745455503463745,
      "kl": 0.215576171875,
      "learning_rate": 2.6160896111162412e-06,
      "loss": 0.0277,
      "reward": 1.550000011920929,
      "reward_std": 0.12436702474951744,
      "rewards/accuracy_reward": 0.5500000044703484,
      "rewards/format_reward": 1.0,
      "step": 896
    },
    {
      "completion_length": 269.32501220703125,
      "epoch": 0.9300155520995335,
      "grad_norm": 3.364424705505371,
      "kl": 1.71484375,
      "learning_rate": 2.614878802233573e-06,
      "loss": 0.2486,
      "reward": 1.3750000298023224,
      "reward_std": 0.5173911079764366,
      "rewards/accuracy_reward": 0.45000000298023224,
      "rewards/format_reward": 0.9250000268220901,
      "step": 897
    },
    {
      "completion_length": 307.37500381469727,
      "epoch": 0.931052358735096,
      "grad_norm": 8.091796875,
      "kl": 0.7021484375,
      "learning_rate": 2.613666368128629e-06,
      "loss": 0.1984,
      "reward": 1.5,
      "reward_std": 0.5715806074440479,
      "rewards/accuracy_reward": 0.6000000163912773,
      "rewards/format_reward": 0.9000000208616257,
      "step": 898
    },
    {
      "completion_length": 216.17500114440918,
      "epoch": 0.9320891653706583,
      "grad_norm": 3.7539572715759277,
      "kl": 0.489990234375,
      "learning_rate": 2.612452310568843e-06,
      "loss": 0.166,
      "reward": 1.4500000476837158,
      "reward_std": 0.347973819822073,
      "rewards/accuracy_reward": 0.5000000018626451,
      "rewards/format_reward": 0.9500000178813934,
      "step": 899
    },
    {
      "completion_length": 306.25000381469727,
      "epoch": 0.9331259720062208,
      "grad_norm": 19.283233642578125,
      "kl": 12.60498046875,
      "learning_rate": 2.611236631324017e-06,
      "loss": 0.5753,
      "reward": 1.3000000268220901,
      "reward_std": 0.4038755036890507,
      "rewards/accuracy_reward": 0.4000000134110451,
      "rewards/format_reward": 0.9000000208616257,
      "step": 900
    },
    {
      "completion_length": 301.6750068664551,
      "epoch": 0.9341627786417833,
      "grad_norm": 3.5665500164031982,
      "kl": 3.050048828125,
      "learning_rate": 2.6100193321663147e-06,
      "loss": 0.3779,
      "reward": 1.0750000327825546,
      "reward_std": 0.4019973427057266,
      "rewards/accuracy_reward": 0.17500000447034836,
      "rewards/format_reward": 0.9000000208616257,
      "step": 901
    },
    {
      "completion_length": 171.35000801086426,
      "epoch": 0.9351995852773458,
      "grad_norm": 1.0143321752548218,
      "kl": 0.2734375,
      "learning_rate": 2.608800414870263e-06,
      "loss": 0.0389,
      "reward": 1.5250000357627869,
      "reward_std": 0.30463574826717377,
      "rewards/accuracy_reward": 0.5500000081956387,
      "rewards/format_reward": 0.9750000089406967,
      "step": 902
    },
    {
      "completion_length": 174.27500343322754,
      "epoch": 0.9362363919129082,
      "grad_norm": 1.870166301727295,
      "kl": 0.5362548828125,
      "learning_rate": 2.6075798812127463e-06,
      "loss": 0.0717,
      "reward": 1.3250000327825546,
      "reward_std": 0.2920721210539341,
      "rewards/accuracy_reward": 0.35000000335276127,
      "rewards/format_reward": 0.9750000089406967,
      "step": 903
    },
    {
      "completion_length": 270.29999923706055,
      "epoch": 0.9372731985484707,
      "grad_norm": 1.5089102983474731,
      "kl": 1.107421875,
      "learning_rate": 2.6063577329730072e-06,
      "loss": 0.2227,
      "reward": 1.4000000357627869,
      "reward_std": 0.373101070523262,
      "rewards/accuracy_reward": 0.5000000149011612,
      "rewards/format_reward": 0.9000000059604645,
      "step": 904
    },
    {
      "completion_length": 157.52499771118164,
      "epoch": 0.9383100051840332,
      "grad_norm": 1.0162603855133057,
      "kl": 0.883056640625,
      "learning_rate": 2.605133971932639e-06,
      "loss": 0.1052,
      "reward": 1.8000000417232513,
      "reward_std": 0.2361704222857952,
      "rewards/accuracy_reward": 0.8250000178813934,
      "rewards/format_reward": 0.9750000089406967,
      "step": 905
    },
    {
      "completion_length": 117.125,
      "epoch": 0.9393468118195957,
      "grad_norm": 0.2638833224773407,
      "kl": 0.188232421875,
      "learning_rate": 2.6039085998755895e-06,
      "loss": -0.0455,
      "reward": 1.5,
      "reward_std": 0.11180339753627777,
      "rewards/accuracy_reward": 0.5000000149011612,
      "rewards/format_reward": 1.0,
      "step": 906
    },
    {
      "completion_length": 220.10000228881836,
      "epoch": 0.9403836184551582,
      "grad_norm": 0.5877365469932556,
      "kl": 2.642822265625,
      "learning_rate": 2.602681618588152e-06,
      "loss": 0.2276,
      "reward": 1.3250000327825546,
      "reward_std": 0.31199513375759125,
      "rewards/accuracy_reward": 0.4000000152736902,
      "rewards/format_reward": 0.9250000268220901,
      "step": 907
    },
    {
      "completion_length": 260.37500762939453,
      "epoch": 0.9414204250907205,
      "grad_norm": 1.3724843263626099,
      "kl": 3.5703125,
      "learning_rate": 2.6014530298589674e-06,
      "loss": 0.3882,
      "reward": 1.3000000268220901,
      "reward_std": 0.3479737974703312,
      "rewards/accuracy_reward": 0.375,
      "rewards/format_reward": 0.925000011920929,
      "step": 908
    },
    {
      "completion_length": 233.57500457763672,
      "epoch": 0.942457231726283,
      "grad_norm": 1.3091270923614502,
      "kl": 1.9521484375,
      "learning_rate": 2.60022283547902e-06,
      "loss": 0.1282,
      "reward": 1.375,
      "reward_std": 0.4415663853287697,
      "rewards/accuracy_reward": 0.4750000089406967,
      "rewards/format_reward": 0.9000000208616257,
      "step": 909
    },
    {
      "completion_length": 172.9249973297119,
      "epoch": 0.9434940383618455,
      "grad_norm": 0.9247521758079529,
      "kl": 0.97021484375,
      "learning_rate": 2.5989910372416335e-06,
      "loss": 0.114,
      "reward": 1.350000023841858,
      "reward_std": 0.16770510748028755,
      "rewards/accuracy_reward": 0.3750000074505806,
      "rewards/format_reward": 0.9750000089406967,
      "step": 910
    },
    {
      "completion_length": 195.77500343322754,
      "epoch": 0.944530844997408,
      "grad_norm": 1.2640548944473267,
      "kl": 1.4638671875,
      "learning_rate": 2.59775763694247e-06,
      "loss": 0.1241,
      "reward": 1.225000023841858,
      "reward_std": 0.12436702474951744,
      "rewards/accuracy_reward": 0.27500000037252903,
      "rewards/format_reward": 0.9500000029802322,
      "step": 911
    },
    {
      "completion_length": 269.72500228881836,
      "epoch": 0.9455676516329704,
      "grad_norm": 0.822454035282135,
      "kl": 0.965576171875,
      "learning_rate": 2.596522636379528e-06,
      "loss": 0.2064,
      "reward": 1.5000000298023224,
      "reward_std": 0.30463575199246407,
      "rewards/accuracy_reward": 0.575000012293458,
      "rewards/format_reward": 0.925000011920929,
      "step": 912
    },
    {
      "completion_length": 119.125,
      "epoch": 0.9466044582685329,
      "grad_norm": 0.47956565022468567,
      "kl": 0.22607421875,
      "learning_rate": 2.595286037353138e-06,
      "loss": 0.018,
      "reward": 1.675000011920929,
      "reward_std": 0.18026872724294662,
      "rewards/accuracy_reward": 0.675000011920929,
      "rewards/format_reward": 1.0,
      "step": 913
    },
    {
      "completion_length": 257.4500026702881,
      "epoch": 0.9476412649040954,
      "grad_norm": 1.073453664779663,
      "kl": 2.339599609375,
      "learning_rate": 2.5940478416659605e-06,
      "loss": 0.2984,
      "reward": 1.4000000059604645,
      "reward_std": 0.3407529331743717,
      "rewards/accuracy_reward": 0.4750000163912773,
      "rewards/format_reward": 0.925000011920929,
      "step": 914
    },
    {
      "completion_length": 169.75000190734863,
      "epoch": 0.9486780715396579,
      "grad_norm": 0.3584200441837311,
      "kl": 0.40869140625,
      "learning_rate": 2.5928080511229837e-06,
      "loss": 0.059,
      "reward": 1.699999988079071,
      "reward_std": 0.22360680624842644,
      "rewards/accuracy_reward": 0.7250000089406967,
      "rewards/format_reward": 0.9750000089406967,
      "step": 915
    },
    {
      "completion_length": 268.6500053405762,
      "epoch": 0.9497148781752203,
      "grad_norm": 0.72416752576828,
      "kl": 1.800537109375,
      "learning_rate": 2.591566667531522e-06,
      "loss": 0.2042,
      "reward": 1.5250000059604645,
      "reward_std": 0.34860679507255554,
      "rewards/accuracy_reward": 0.6250000186264515,
      "rewards/format_reward": 0.9000000208616257,
      "step": 916
    },
    {
      "completion_length": 141.25,
      "epoch": 0.9507516848107828,
      "grad_norm": 0.3592819273471832,
      "kl": 0.32470703125,
      "learning_rate": 2.590323692701209e-06,
      "loss": 0.0149,
      "reward": 1.4000000059604645,
      "reward_std": 0.16770510748028755,
      "rewards/accuracy_reward": 0.40000000037252903,
      "rewards/format_reward": 1.0,
      "step": 917
    },
    {
      "completion_length": 224.8500099182129,
      "epoch": 0.9517884914463453,
      "grad_norm": 1.1734187602996826,
      "kl": 0.6982421875,
      "learning_rate": 2.589079128444001e-06,
      "loss": 0.1334,
      "reward": 1.225000023841858,
      "reward_std": 0.27950848266482353,
      "rewards/accuracy_reward": 0.2750000059604645,
      "rewards/format_reward": 0.9500000178813934,
      "step": 918
    },
    {
      "completion_length": 230.95000457763672,
      "epoch": 0.9528252980819077,
      "grad_norm": 1.34982430934906,
      "kl": 0.759033203125,
      "learning_rate": 2.58783297657417e-06,
      "loss": 0.1402,
      "reward": 1.5500000417232513,
      "reward_std": 0.3479738160967827,
      "rewards/accuracy_reward": 0.6000000014901161,
      "rewards/format_reward": 0.9500000178813934,
      "step": 919
    },
    {
      "completion_length": 417.5250015258789,
      "epoch": 0.9538621047174702,
      "grad_norm": 1.6819778680801392,
      "kl": 1.3720703125,
      "learning_rate": 2.586585238908303e-06,
      "loss": 0.2049,
      "reward": 1.4500000476837158,
      "reward_std": 0.5282425507903099,
      "rewards/accuracy_reward": 0.6250000223517418,
      "rewards/format_reward": 0.8250000178813934,
      "step": 920
    },
    {
      "completion_length": 179.52500343322754,
      "epoch": 0.9548989113530326,
      "grad_norm": 0.4821496307849884,
      "kl": 0.600830078125,
      "learning_rate": 2.585335917265297e-06,
      "loss": 0.0838,
      "reward": 1.4000000208616257,
      "reward_std": 0.12436701729893684,
      "rewards/accuracy_reward": 0.42499999701976776,
      "rewards/format_reward": 0.9750000089406967,
      "step": 921
    },
    {
      "completion_length": 266.1250057220459,
      "epoch": 0.9559357179885951,
      "grad_norm": 1.7604442834854126,
      "kl": 1.4638671875,
      "learning_rate": 2.5840850134663604e-06,
      "loss": 0.1657,
      "reward": 1.2500000298023224,
      "reward_std": 0.30463574826717377,
      "rewards/accuracy_reward": 0.325000012293458,
      "rewards/format_reward": 0.925000011920929,
      "step": 922
    },
    {
      "completion_length": 157.10000038146973,
      "epoch": 0.9569725246241576,
      "grad_norm": 0.7505897879600525,
      "kl": 0.798583984375,
      "learning_rate": 2.5828325293350064e-06,
      "loss": 0.1055,
      "reward": 1.600000023841858,
      "reward_std": 0.16770509257912636,
      "rewards/accuracy_reward": 0.6250000074505806,
      "rewards/format_reward": 0.9750000089406967,
      "step": 923
    },
    {
      "completion_length": 172.25000190734863,
      "epoch": 0.9580093312597201,
      "grad_norm": 0.8031712174415588,
      "kl": 1.382080078125,
      "learning_rate": 2.581578466697052e-06,
      "loss": 0.1606,
      "reward": 1.3250000327825546,
      "reward_std": 0.22360680997371674,
      "rewards/accuracy_reward": 0.3750000074505806,
      "rewards/format_reward": 0.9500000178813934,
      "step": 924
    },
    {
      "completion_length": 115.32500267028809,
      "epoch": 0.9590461378952825,
      "grad_norm": 0.28106948733329773,
      "kl": 0.29638671875,
      "learning_rate": 2.580322827380616e-06,
      "loss": 0.0158,
      "reward": 1.6500000357627869,
      "reward_std": 0.1369306445121765,
      "rewards/accuracy_reward": 0.6500000059604645,
      "rewards/format_reward": 1.0,
      "step": 925
    },
    {
      "completion_length": 245.8000030517578,
      "epoch": 0.960082944530845,
      "grad_norm": 1.201001763343811,
      "kl": 1.44873046875,
      "learning_rate": 2.5790656132161155e-06,
      "loss": 0.284,
      "reward": 1.425000011920929,
      "reward_std": 0.3678968548774719,
      "rewards/accuracy_reward": 0.5000000167638063,
      "rewards/format_reward": 0.925000011920929,
      "step": 926
    },
    {
      "completion_length": 117.50000190734863,
      "epoch": 0.9611197511664075,
      "grad_norm": 0.5040531158447266,
      "kl": 0.27978515625,
      "learning_rate": 2.577806826036263e-06,
      "loss": -0.001,
      "reward": 1.7250000536441803,
      "reward_std": 0.20539596676826477,
      "rewards/accuracy_reward": 0.7250000089406967,
      "rewards/format_reward": 1.0,
      "step": 927
    },
    {
      "completion_length": 106.87500381469727,
      "epoch": 0.96215655780197,
      "grad_norm": 0.43804383277893066,
      "kl": 0.2802734375,
      "learning_rate": 2.576546467676064e-06,
      "loss": 0.0252,
      "reward": 1.5999999940395355,
      "reward_std": 0.16770509257912636,
      "rewards/accuracy_reward": 0.6000000163912773,
      "rewards/format_reward": 1.0,
      "step": 928
    },
    {
      "completion_length": 106.35000038146973,
      "epoch": 0.9631933644375325,
      "grad_norm": 0.4537351429462433,
      "kl": 0.33935546875,
      "learning_rate": 2.575284539972815e-06,
      "loss": 0.0106,
      "reward": 1.5750000178813934,
      "reward_std": 0.06846532225608826,
      "rewards/accuracy_reward": 0.5750000029802322,
      "rewards/format_reward": 1.0,
      "step": 929
    },
    {
      "completion_length": 242.62500190734863,
      "epoch": 0.9642301710730948,
      "grad_norm": 47.74652099609375,
      "kl": 13.046875,
      "learning_rate": 2.5740210447660993e-06,
      "loss": 1.1571,
      "reward": 1.5,
      "reward_std": 0.3913119062781334,
      "rewards/accuracy_reward": 0.575000012293458,
      "rewards/format_reward": 0.9250000268220901,
      "step": 930
    },
    {
      "completion_length": 146.2500057220459,
      "epoch": 0.9652669777086573,
      "grad_norm": 24.46285057067871,
      "kl": 5.71484375,
      "learning_rate": 2.572755983897786e-06,
      "loss": 0.4407,
      "reward": 1.625,
      "reward_std": 0.36053745076060295,
      "rewards/accuracy_reward": 0.6500000059604645,
      "rewards/format_reward": 0.9750000089406967,
      "step": 931
    },
    {
      "completion_length": 257.9250144958496,
      "epoch": 0.9663037843442198,
      "grad_norm": 3.5134782791137695,
      "kl": 3.75927734375,
      "learning_rate": 2.5714893592120267e-06,
      "loss": 0.1903,
      "reward": 1.550000011920929,
      "reward_std": 0.17304782569408417,
      "rewards/accuracy_reward": 0.6500000059604645,
      "rewards/format_reward": 0.9000000059604645,
      "step": 932
    },
    {
      "completion_length": 159.45000457763672,
      "epoch": 0.9673405909797823,
      "grad_norm": 2.399360418319702,
      "kl": 2.16796875,
      "learning_rate": 2.570221172555252e-06,
      "loss": 0.1898,
      "reward": 1.3500000089406967,
      "reward_std": 0.055901702493429184,
      "rewards/accuracy_reward": 0.375,
      "rewards/format_reward": 0.9750000089406967,
      "step": 933
    },
    {
      "completion_length": 180.92499923706055,
      "epoch": 0.9683773976153447,
      "grad_norm": 0.9570638537406921,
      "kl": 1.00927734375,
      "learning_rate": 2.5689514257761695e-06,
      "loss": 0.1518,
      "reward": 1.600000023841858,
      "reward_std": 0.23617040738463402,
      "rewards/accuracy_reward": 0.6500000059604645,
      "rewards/format_reward": 0.9500000178813934,
      "step": 934
    },
    {
      "completion_length": 147.29999923706055,
      "epoch": 0.9694142042509072,
      "grad_norm": 10.051190376281738,
      "kl": 3.88720703125,
      "learning_rate": 2.5676801207257614e-06,
      "loss": 0.2523,
      "reward": 1.350000023841858,
      "reward_std": 0.2920721136033535,
      "rewards/accuracy_reward": 0.3750000074505806,
      "rewards/format_reward": 0.9750000089406967,
      "step": 935
    },
    {
      "completion_length": 183.37499809265137,
      "epoch": 0.9704510108864697,
      "grad_norm": 1.349984884262085,
      "kl": 2.6650390625,
      "learning_rate": 2.5664072592572823e-06,
      "loss": 0.2796,
      "reward": 1.550000011920929,
      "reward_std": 0.5247505605220795,
      "rewards/accuracy_reward": 0.6250000149011612,
      "rewards/format_reward": 0.9250000268220901,
      "step": 936
    },
    {
      "completion_length": 158.97500228881836,
      "epoch": 0.9714878175220322,
      "grad_norm": 0.5514269471168518,
      "kl": 0.19921875,
      "learning_rate": 2.565132843226253e-06,
      "loss": 0.0189,
      "reward": 1.4500000178813934,
      "reward_std": 0.3371223993599415,
      "rewards/accuracy_reward": 0.4750000089406967,
      "rewards/format_reward": 0.9750000089406967,
      "step": 937
    },
    {
      "completion_length": 192.82500076293945,
      "epoch": 0.9725246241575947,
      "grad_norm": 22.37244987487793,
      "kl": 6.8203125,
      "learning_rate": 2.563856874490465e-06,
      "loss": 0.634,
      "reward": 1.5000000149011612,
      "reward_std": 0.27950848266482353,
      "rewards/accuracy_reward": 0.550000011920929,
      "rewards/format_reward": 0.9500000029802322,
      "step": 938
    },
    {
      "completion_length": 110.50000190734863,
      "epoch": 0.973561430793157,
      "grad_norm": 0.673575222492218,
      "kl": 0.44140625,
      "learning_rate": 2.5625793549099676e-06,
      "loss": 0.003,
      "reward": 1.5250000059604645,
      "reward_std": 0.49746808037161827,
      "rewards/accuracy_reward": 0.5500000044703484,
      "rewards/format_reward": 0.9750000089406967,
      "step": 939
    },
    {
      "completion_length": 97.17500114440918,
      "epoch": 0.9745982374287195,
      "grad_norm": 0.3349624276161194,
      "kl": 0.352783203125,
      "learning_rate": 2.561300286347075e-06,
      "loss": 0.0131,
      "reward": 1.699999988079071,
      "reward_std": 0.11180339753627777,
      "rewards/accuracy_reward": 0.7000000178813934,
      "rewards/format_reward": 1.0,
      "step": 940
    },
    {
      "completion_length": 245.49999809265137,
      "epoch": 0.975635044064282,
      "grad_norm": 2.73366641998291,
      "kl": 1.84619140625,
      "learning_rate": 2.560019670666359e-06,
      "loss": 0.2749,
      "reward": 1.4500000178813934,
      "reward_std": 0.30463574826717377,
      "rewards/accuracy_reward": 0.5500000044703484,
      "rewards/format_reward": 0.9000000059604645,
      "step": 941
    },
    {
      "completion_length": 138.72500610351562,
      "epoch": 0.9766718506998445,
      "grad_norm": 0.5809561610221863,
      "kl": 0.8857421875,
      "learning_rate": 2.558737509734645e-06,
      "loss": 0.0642,
      "reward": 1.4500000178813934,
      "reward_std": 0.06846532225608826,
      "rewards/accuracy_reward": 0.4750000014901161,
      "rewards/format_reward": 0.9750000089406967,
      "step": 942
    },
    {
      "completion_length": 132.2750015258789,
      "epoch": 0.9777086573354069,
      "grad_norm": 0.9825214147567749,
      "kl": 0.572998046875,
      "learning_rate": 2.5574538054210123e-06,
      "loss": 0.0908,
      "reward": 1.5750000178813934,
      "reward_std": 0.16770510002970695,
      "rewards/accuracy_reward": 0.6000000089406967,
      "rewards/format_reward": 0.9750000089406967,
      "step": 943
    },
    {
      "completion_length": 172.37500381469727,
      "epoch": 0.9787454639709694,
      "grad_norm": 1.4355342388153076,
      "kl": 0.579833984375,
      "learning_rate": 2.5561685595967895e-06,
      "loss": 0.1356,
      "reward": 1.4500000327825546,
      "reward_std": 0.3479738160967827,
      "rewards/accuracy_reward": 0.5250000208616257,
      "rewards/format_reward": 0.9250000268220901,
      "step": 944
    },
    {
      "completion_length": 162.45000076293945,
      "epoch": 0.9797822706065319,
      "grad_norm": 0.6745811104774475,
      "kl": 0.871826171875,
      "learning_rate": 2.5548817741355533e-06,
      "loss": 0.1104,
      "reward": 1.324999988079071,
      "reward_std": 0.20019176974892616,
      "rewards/accuracy_reward": 0.375,
      "rewards/format_reward": 0.9500000178813934,
      "step": 945
    },
    {
      "completion_length": 151.02500534057617,
      "epoch": 0.9808190772420944,
      "grad_norm": 0.9925585985183716,
      "kl": 0.726318359375,
      "learning_rate": 2.5535934509131233e-06,
      "loss": 0.075,
      "reward": 1.5999999940395355,
      "reward_std": 0.3533165454864502,
      "rewards/accuracy_reward": 0.6250000186264515,
      "rewards/format_reward": 0.9750000089406967,
      "step": 946
    },
    {
      "completion_length": 163.75000381469727,
      "epoch": 0.9818558838776568,
      "grad_norm": 0.7139672040939331,
      "kl": 0.64013671875,
      "learning_rate": 2.5523035918075613e-06,
      "loss": 0.064,
      "reward": 1.25,
      "reward_std": 0.20019175857305527,
      "rewards/accuracy_reward": 0.2750000096857548,
      "rewards/format_reward": 0.9750000089406967,
      "step": 947
    },
    {
      "completion_length": 152.00000381469727,
      "epoch": 0.9828926905132193,
      "grad_norm": 2.130598306655884,
      "kl": 0.46142578125,
      "learning_rate": 2.551012198699169e-06,
      "loss": 0.0743,
      "reward": 1.7000000178813934,
      "reward_std": 0.11180339008569717,
      "rewards/accuracy_reward": 0.7250000014901161,
      "rewards/format_reward": 0.9750000089406967,
      "step": 948
    },
    {
      "completion_length": 196.75000190734863,
      "epoch": 0.9839294971487818,
      "grad_norm": 1.8375300168991089,
      "kl": 0.7880859375,
      "learning_rate": 2.549719273470484e-06,
      "loss": 0.1423,
      "reward": 1.725000023841858,
      "reward_std": 0.2920721247792244,
      "rewards/accuracy_reward": 0.7750000059604645,
      "rewards/format_reward": 0.9500000178813934,
      "step": 949
    },
    {
      "completion_length": 222.3250026702881,
      "epoch": 0.9849663037843442,
      "grad_norm": 5.316202640533447,
      "kl": 4.0380859375,
      "learning_rate": 2.548424818006276e-06,
      "loss": 0.4561,
      "reward": 1.675000011920929,
      "reward_std": 0.3479738123714924,
      "rewards/accuracy_reward": 0.7500000149011612,
      "rewards/format_reward": 0.9250000268220901,
      "step": 950
    },
    {
      "completion_length": 212.09999656677246,
      "epoch": 0.9860031104199067,
      "grad_norm": 0.7121568918228149,
      "kl": 0.4951171875,
      "learning_rate": 2.547128834193547e-06,
      "loss": 0.0836,
      "reward": 1.3500000089406967,
      "reward_std": 0.2361704260110855,
      "rewards/accuracy_reward": 0.42499999701976776,
      "rewards/format_reward": 0.9250000268220901,
      "step": 951
    },
    {
      "completion_length": 155.22500038146973,
      "epoch": 0.9870399170554691,
      "grad_norm": 2.3164560794830322,
      "kl": 0.57177734375,
      "learning_rate": 2.5458313239215266e-06,
      "loss": 0.0801,
      "reward": 1.5250000059604645,
      "reward_std": 0.16770510002970695,
      "rewards/accuracy_reward": 0.5750000029802322,
      "rewards/format_reward": 0.9500000178813934,
      "step": 952
    },
    {
      "completion_length": 197.80000495910645,
      "epoch": 0.9880767236910316,
      "grad_norm": 1.507447361946106,
      "kl": 2.1240234375,
      "learning_rate": 2.5445322890816685e-06,
      "loss": 0.2326,
      "reward": 1.6500000357627869,
      "reward_std": 0.4723408557474613,
      "rewards/accuracy_reward": 0.7250000238418579,
      "rewards/format_reward": 0.925000011920929,
      "step": 953
    },
    {
      "completion_length": 174.45000076293945,
      "epoch": 0.9891135303265941,
      "grad_norm": 8.216100692749023,
      "kl": 0.30615234375,
      "learning_rate": 2.54323173156765e-06,
      "loss": 0.0657,
      "reward": 1.5250000059604645,
      "reward_std": 0.2361704185605049,
      "rewards/accuracy_reward": 0.5500000007450581,
      "rewards/format_reward": 0.9750000089406967,
      "step": 954
    },
    {
      "completion_length": 121.99999809265137,
      "epoch": 0.9901503369621566,
      "grad_norm": 0.4198542833328247,
      "kl": 0.197021484375,
      "learning_rate": 2.5419296532753684e-06,
      "loss": 0.0393,
      "reward": 1.5999999940395355,
      "reward_std": 0.16770510748028755,
      "rewards/accuracy_reward": 0.6000000108033419,
      "rewards/format_reward": 1.0,
      "step": 955
    },
    {
      "completion_length": 268.40000915527344,
      "epoch": 0.991187143597719,
      "grad_norm": 14.27199935913086,
      "kl": 7.554931640625,
      "learning_rate": 2.5406260561029365e-06,
      "loss": 0.7576,
      "reward": 1.425000011920929,
      "reward_std": 0.4363621771335602,
      "rewards/accuracy_reward": 0.5000000037252903,
      "rewards/format_reward": 0.925000011920929,
      "step": 956
    },
    {
      "completion_length": 219.4249973297119,
      "epoch": 0.9922239502332815,
      "grad_norm": 8.010781288146973,
      "kl": 5.810546875,
      "learning_rate": 2.539320941950683e-06,
      "loss": 0.423,
      "reward": 1.5000000298023224,
      "reward_std": 0.4472135826945305,
      "rewards/accuracy_reward": 0.575000012293458,
      "rewards/format_reward": 0.925000011920929,
      "step": 957
    },
    {
      "completion_length": 205.37499809265137,
      "epoch": 0.993260756868844,
      "grad_norm": 6.571266174316406,
      "kl": 5.18212890625,
      "learning_rate": 2.5380143127211464e-06,
      "loss": 0.4746,
      "reward": 1.6250000298023224,
      "reward_std": 0.22360679507255554,
      "rewards/accuracy_reward": 0.6750000044703484,
      "rewards/format_reward": 0.9500000178813934,
      "step": 958
    },
    {
      "completion_length": 168.30000686645508,
      "epoch": 0.9942975635044065,
      "grad_norm": 8.582088470458984,
      "kl": 3.159423828125,
      "learning_rate": 2.5367061703190743e-06,
      "loss": 0.239,
      "reward": 1.475000023841858,
      "reward_std": 0.30463573709130287,
      "rewards/accuracy_reward": 0.5000000093132257,
      "rewards/format_reward": 0.9750000089406967,
      "step": 959
    },
    {
      "completion_length": 225.42501068115234,
      "epoch": 0.995334370139969,
      "grad_norm": 1.5330493450164795,
      "kl": 2.22802734375,
      "learning_rate": 2.535396516651421e-06,
      "loss": 0.2924,
      "reward": 1.4500000178813934,
      "reward_std": 0.22360679507255554,
      "rewards/accuracy_reward": 0.5000000018626451,
      "rewards/format_reward": 0.9500000178813934,
      "step": 960
    },
    {
      "completion_length": 221.0999984741211,
      "epoch": 0.9963711767755313,
      "grad_norm": 3.0697624683380127,
      "kl": 2.22119140625,
      "learning_rate": 2.534085353627343e-06,
      "loss": 0.2233,
      "reward": 1.2750000208616257,
      "reward_std": 0.2920721098780632,
      "rewards/accuracy_reward": 0.3500000089406967,
      "rewards/format_reward": 0.925000011920929,
      "step": 961
    },
    {
      "completion_length": 362.57499504089355,
      "epoch": 0.9974079834110938,
      "grad_norm": 3.0965917110443115,
      "kl": 0.933349609375,
      "learning_rate": 2.5327726831581968e-06,
      "loss": 0.2787,
      "reward": 1.6500000059604645,
      "reward_std": 0.41643914580345154,
      "rewards/accuracy_reward": 0.7750000208616257,
      "rewards/format_reward": 0.8750000149011612,
      "step": 962
    },
    {
      "completion_length": 171.12499809265137,
      "epoch": 0.9984447900466563,
      "grad_norm": 1.9162588119506836,
      "kl": 0.46533203125,
      "learning_rate": 2.5314585071575373e-06,
      "loss": 0.031,
      "reward": 1.6500000357627869,
      "reward_std": 0.3731010779738426,
      "rewards/accuracy_reward": 0.675000011920929,
      "rewards/format_reward": 0.9750000089406967,
      "step": 963
    },
    {
      "completion_length": 260.2000102996826,
      "epoch": 0.9994815966822188,
      "grad_norm": 3.7568962574005127,
      "kl": 2.827392578125,
      "learning_rate": 2.530142827541113e-06,
      "loss": 0.3048,
      "reward": 1.4000000059604645,
      "reward_std": 0.25609344989061356,
      "rewards/accuracy_reward": 0.47500000335276127,
      "rewards/format_reward": 0.925000011920929,
      "step": 964
    },
    {
      "completion_length": 416.1000213623047,
      "epoch": 1.0,
      "grad_norm": 3.7568962574005127,
      "kl": 3.8359375,
      "learning_rate": 2.5288256462268662e-06,
      "loss": 0.1403,
      "reward": 1.5000000596046448,
      "reward_std": 0.5590169876813889,
      "rewards/accuracy_reward": 0.6500000208616257,
      "rewards/format_reward": 0.8500000238418579,
      "step": 965
    }
  ],
  "logging_steps": 1,
  "max_steps": 2892,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}