{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06666666666666667,
  "eval_steps": 500,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 485.49220275878906,
      "epoch": 0.0010666666666666667,
      "grad_norm": 0.13112049806907955,
      "kl": 0.0,
      "learning_rate": 7.142857142857142e-08,
      "loss": -0.0,
      "reward": 0.3281250111758709,
      "reward_std": 0.4913413915783167,
      "rewards/equation_reward_func": 0.05729166814126074,
      "rewards/format_reward_func": 0.27083334047347307,
      "step": 2
    },
    {
      "completion_length": 530.2265796661377,
      "epoch": 0.0021333333333333334,
      "grad_norm": 0.12198138838063947,
      "kl": 0.0003826618194580078,
      "learning_rate": 1.4285714285714285e-07,
      "loss": 0.0,
      "reward": 0.299479172565043,
      "reward_std": 0.44007157534360886,
      "rewards/equation_reward_func": 0.03385416744276881,
      "rewards/format_reward_func": 0.26562500977888703,
      "step": 4
    },
    {
      "completion_length": 496.8776264190674,
      "epoch": 0.0032,
      "grad_norm": 0.12162717174644112,
      "kl": 0.0003865957260131836,
      "learning_rate": 2.1428571428571426e-07,
      "loss": 0.0,
      "reward": 0.2916666781529784,
      "reward_std": 0.47719811648130417,
      "rewards/equation_reward_func": 0.05468750116415322,
      "rewards/format_reward_func": 0.23697917303070426,
      "step": 6
    },
    {
      "completion_length": 504.77865982055664,
      "epoch": 0.004266666666666667,
      "grad_norm": 0.13232346241260942,
      "kl": 0.0003762245178222656,
      "learning_rate": 2.857142857142857e-07,
      "loss": 0.0,
      "reward": 0.33593750558793545,
      "reward_std": 0.4751614350825548,
      "rewards/equation_reward_func": 0.04947916720993817,
      "rewards/format_reward_func": 0.28645834140479565,
      "step": 8
    },
    {
      "completion_length": 475.7057456970215,
      "epoch": 0.005333333333333333,
      "grad_norm": 0.13843718324607834,
      "kl": 0.0003968477249145508,
      "learning_rate": 3.5714285714285716e-07,
      "loss": 0.0,
      "reward": 0.3828125102445483,
      "reward_std": 0.5227206833660603,
      "rewards/equation_reward_func": 0.0885416679084301,
      "rewards/format_reward_func": 0.2942708395421505,
      "step": 10
    },
    {
      "completion_length": 475.98699378967285,
      "epoch": 0.0064,
      "grad_norm": 0.14337833822484186,
      "kl": 0.0004818439483642578,
      "learning_rate": 4.285714285714285e-07,
      "loss": 0.0,
      "reward": 0.33333334140479565,
      "reward_std": 0.4693184234201908,
      "rewards/equation_reward_func": 0.05468750139698386,
      "rewards/format_reward_func": 0.2786458395421505,
      "step": 12
    },
    {
      "completion_length": 472.8099060058594,
      "epoch": 0.007466666666666667,
      "grad_norm": 0.129867140491159,
      "kl": 0.0007684230804443359,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 0.45052084885537624,
      "reward_std": 0.5166866518557072,
      "rewards/equation_reward_func": 0.041666667675599456,
      "rewards/format_reward_func": 0.40885418094694614,
      "step": 14
    },
    {
      "completion_length": 464.46875762939453,
      "epoch": 0.008533333333333334,
      "grad_norm": 0.1279190002551803,
      "kl": 0.0013058185577392578,
      "learning_rate": 4.999740409224932e-07,
      "loss": 0.0,
      "reward": 0.5052083488553762,
      "reward_std": 0.5728582534939051,
      "rewards/equation_reward_func": 0.06510416814126074,
      "rewards/format_reward_func": 0.4401041753590107,
      "step": 16
    },
    {
      "completion_length": 480.2291717529297,
      "epoch": 0.0096,
      "grad_norm": 0.10647649710010443,
      "kl": 0.00380706787109375,
      "learning_rate": 4.998961690809627e-07,
      "loss": 0.0,
      "reward": 0.6588541902601719,
      "reward_std": 0.5287479311227798,
      "rewards/equation_reward_func": 0.05468750139698386,
      "rewards/format_reward_func": 0.6041666828095913,
      "step": 18
    },
    {
      "completion_length": 493.8073043823242,
      "epoch": 0.010666666666666666,
      "grad_norm": 0.10522760864642984,
      "kl": 0.004913330078125,
      "learning_rate": 4.997664006472578e-07,
      "loss": 0.0,
      "reward": 0.7734375223517418,
      "reward_std": 0.4910791157744825,
      "rewards/equation_reward_func": 0.07031250116415322,
      "rewards/format_reward_func": 0.7031250186264515,
      "step": 20
    },
    {
      "completion_length": 455.6510524749756,
      "epoch": 0.011733333333333333,
      "grad_norm": 0.09917661844432689,
      "kl": 0.008411407470703125,
      "learning_rate": 4.995847625707292e-07,
      "loss": 0.0,
      "reward": 0.7812500186264515,
      "reward_std": 0.4674575887620449,
      "rewards/equation_reward_func": 0.0651041679084301,
      "rewards/format_reward_func": 0.7161458507180214,
      "step": 22
    },
    {
      "completion_length": 464.50782012939453,
      "epoch": 0.0128,
      "grad_norm": 0.10189992043189328,
      "kl": 0.0059833526611328125,
      "learning_rate": 4.993512925726318e-07,
      "loss": 0.0,
      "reward": 0.8619791865348816,
      "reward_std": 0.49650320410728455,
      "rewards/equation_reward_func": 0.08854166860692203,
      "rewards/format_reward_func": 0.7734375223517418,
      "step": 24
    },
    {
      "completion_length": 447.40626335144043,
      "epoch": 0.013866666666666666,
      "grad_norm": 0.09219816177682034,
      "kl": 0.006900787353515625,
      "learning_rate": 4.990660391382923e-07,
      "loss": 0.0,
      "reward": 0.960937537252903,
      "reward_std": 0.4377214591950178,
      "rewards/equation_reward_func": 0.11718750256113708,
      "rewards/format_reward_func": 0.8437500260770321,
      "step": 26
    },
    {
      "completion_length": 436.3099117279053,
      "epoch": 0.014933333333333333,
      "grad_norm": 0.07907793746945187,
      "kl": 0.009281158447265625,
      "learning_rate": 4.987290615070384e-07,
      "loss": 0.0,
      "reward": 0.9713542014360428,
      "reward_std": 0.3975960807874799,
      "rewards/equation_reward_func": 0.09895833535119891,
      "rewards/format_reward_func": 0.872395858168602,
      "step": 28
    },
    {
      "completion_length": 428.1354293823242,
      "epoch": 0.016,
      "grad_norm": 0.0845150241699145,
      "kl": 0.011430740356445312,
      "learning_rate": 4.983404296598978e-07,
      "loss": 0.0,
      "reward": 0.9531250298023224,
      "reward_std": 0.359499204903841,
      "rewards/equation_reward_func": 0.0703125016298145,
      "rewards/format_reward_func": 0.8828125223517418,
      "step": 30
    },
    {
      "completion_length": 434.62500953674316,
      "epoch": 0.017066666666666667,
      "grad_norm": 0.08196142586101564,
      "kl": 0.010782241821289062,
      "learning_rate": 4.979002243050646e-07,
      "loss": 0.0,
      "reward": 1.0260416977107525,
      "reward_std": 0.30062979739159346,
      "rewards/equation_reward_func": 0.09635416860692203,
      "rewards/format_reward_func": 0.9296875260770321,
      "step": 32
    },
    {
      "completion_length": 438.08595085144043,
      "epoch": 0.018133333333333335,
      "grad_norm": 0.08432790923176402,
      "kl": 0.012115478515625,
      "learning_rate": 4.974085368611381e-07,
      "loss": 0.0,
      "reward": 1.049479205161333,
      "reward_std": 0.3121222285553813,
      "rewards/equation_reward_func": 0.11197917000390589,
      "rewards/format_reward_func": 0.9375000223517418,
      "step": 34
    },
    {
      "completion_length": 421.16407203674316,
      "epoch": 0.0192,
      "grad_norm": 0.080639508238748,
      "kl": 0.01397705078125,
      "learning_rate": 4.968654694381379e-07,
      "loss": 0.0,
      "reward": 1.0598958618938923,
      "reward_std": 0.27779901027679443,
      "rewards/equation_reward_func": 0.10416666907258332,
      "rewards/format_reward_func": 0.9557291865348816,
      "step": 36
    },
    {
      "completion_length": 405.12240982055664,
      "epoch": 0.020266666666666665,
      "grad_norm": 0.07681322754981268,
      "kl": 0.013866424560546875,
      "learning_rate": 4.962711348162987e-07,
      "loss": 0.0,
      "reward": 1.0390625409781933,
      "reward_std": 0.2664716215804219,
      "rewards/equation_reward_func": 0.08593750279396772,
      "rewards/format_reward_func": 0.9531250186264515,
      "step": 38
    },
    {
      "completion_length": 400.0104274749756,
      "epoch": 0.021333333333333333,
      "grad_norm": 0.08198714493646655,
      "kl": 0.015293121337890625,
      "learning_rate": 4.956256564226487e-07,
      "loss": 0.0,
      "reward": 1.1067708730697632,
      "reward_std": 0.28682188084349036,
      "rewards/equation_reward_func": 0.14322917023673654,
      "rewards/format_reward_func": 0.9635416828095913,
      "step": 40
    },
    {
      "completion_length": 400.78386306762695,
      "epoch": 0.0224,
      "grad_norm": 0.0855015587257399,
      "kl": 0.018611907958984375,
      "learning_rate": 4.949291683053768e-07,
      "loss": 0.0,
      "reward": 1.0937500223517418,
      "reward_std": 0.24716421775519848,
      "rewards/equation_reward_func": 0.11197916930541396,
      "rewards/format_reward_func": 0.9817708469927311,
      "step": 42
    },
    {
      "completion_length": 408.34115409851074,
      "epoch": 0.023466666666666667,
      "grad_norm": 0.07249139521720419,
      "kl": 0.017139434814453125,
      "learning_rate": 4.941818151059955e-07,
      "loss": 0.0,
      "reward": 1.0546875298023224,
      "reward_std": 0.24979113461449742,
      "rewards/equation_reward_func": 0.0963541695382446,
      "rewards/format_reward_func": 0.9583333544433117,
      "step": 44
    },
    {
      "completion_length": 388.62761306762695,
      "epoch": 0.024533333333333334,
      "grad_norm": 0.07507762465990464,
      "kl": 0.017795562744140625,
      "learning_rate": 4.933837520293017e-07,
      "loss": 0.0,
      "reward": 1.0781250484287739,
      "reward_std": 0.2523620016872883,
      "rewards/equation_reward_func": 0.11197917046956718,
      "rewards/format_reward_func": 0.9661458507180214,
      "step": 46
    },
    {
      "completion_length": 399.57032585144043,
      "epoch": 0.0256,
      "grad_norm": 0.06604121980517051,
      "kl": 0.017971038818359375,
      "learning_rate": 4.925351448111454e-07,
      "loss": 0.0,
      "reward": 1.0468750335276127,
      "reward_std": 0.21127380011603236,
      "rewards/equation_reward_func": 0.07552083511836827,
      "rewards/format_reward_func": 0.9713541865348816,
      "step": 48
    },
    {
      "completion_length": 392.4687557220459,
      "epoch": 0.02666666666666667,
      "grad_norm": 0.0903310628098169,
      "kl": 0.0193939208984375,
      "learning_rate": 4.91636169684011e-07,
      "loss": 0.0,
      "reward": 1.1093750409781933,
      "reward_std": 0.29062134958803654,
      "rewards/equation_reward_func": 0.13541667209938169,
      "rewards/format_reward_func": 0.9739583432674408,
      "step": 50
    },
    {
      "completion_length": 374.1067810058594,
      "epoch": 0.027733333333333332,
      "grad_norm": 0.07170688038365744,
      "kl": 0.02114105224609375,
      "learning_rate": 4.906870133404186e-07,
      "loss": 0.0,
      "reward": 1.0833333693444729,
      "reward_std": 0.2505181049928069,
      "rewards/equation_reward_func": 0.11458333535119891,
      "rewards/format_reward_func": 0.9687500074505806,
      "step": 52
    },
    {
      "completion_length": 385.36980056762695,
      "epoch": 0.0288,
      "grad_norm": 0.08750349012682264,
      "kl": 0.02417755126953125,
      "learning_rate": 4.896878728941531e-07,
      "loss": 0.0,
      "reward": 1.1432292014360428,
      "reward_std": 0.3026517196558416,
      "rewards/equation_reward_func": 0.16666667186655104,
      "rewards/format_reward_func": 0.9765625186264515,
      "step": 54
    },
    {
      "completion_length": 382.93751335144043,
      "epoch": 0.029866666666666666,
      "grad_norm": 0.08790417727425984,
      "kl": 0.018756866455078125,
      "learning_rate": 4.886389558393284e-07,
      "loss": 0.0,
      "reward": 1.1223958693444729,
      "reward_std": 0.2850013840943575,
      "rewards/equation_reward_func": 0.14322917023673654,
      "rewards/format_reward_func": 0.979166679084301,
      "step": 56
    },
    {
      "completion_length": 403.513032913208,
      "epoch": 0.030933333333333334,
      "grad_norm": 0.07614614875477466,
      "kl": 0.02037811279296875,
      "learning_rate": 4.875404800072976e-07,
      "loss": 0.0,
      "reward": 1.1432292088866234,
      "reward_std": 0.2669796203263104,
      "rewards/equation_reward_func": 0.16145833977498114,
      "rewards/format_reward_func": 0.9817708469927311,
      "step": 58
    },
    {
      "completion_length": 382.6432418823242,
      "epoch": 0.032,
      "grad_norm": 0.0923539372935242,
      "kl": 0.02227783203125,
      "learning_rate": 4.86392673521415e-07,
      "loss": 0.0,
      "reward": 1.1536458693444729,
      "reward_std": 0.31879409588873386,
      "rewards/equation_reward_func": 0.1796875053551048,
      "rewards/format_reward_func": 0.9739583432674408,
      "step": 60
    },
    {
      "completion_length": 358.4349060058594,
      "epoch": 0.03306666666666667,
      "grad_norm": 0.10173008574938576,
      "kl": 0.02350616455078125,
      "learning_rate": 4.851957747496606e-07,
      "loss": 0.0,
      "reward": 1.1562500447034836,
      "reward_std": 0.2772155348211527,
      "rewards/equation_reward_func": 0.16927083814516664,
      "rewards/format_reward_func": 0.9869791753590107,
      "step": 62
    },
    {
      "completion_length": 364.18490409851074,
      "epoch": 0.034133333333333335,
      "grad_norm": 0.08496355305518047,
      "kl": 0.02630615234375,
      "learning_rate": 4.839500322551386e-07,
      "loss": 0.0,
      "reward": 1.1093750447034836,
      "reward_std": 0.24286148557439446,
      "rewards/equation_reward_func": 0.12760417093522847,
      "rewards/format_reward_func": 0.9817708432674408,
      "step": 64
    },
    {
      "completion_length": 373.833345413208,
      "epoch": 0.0352,
      "grad_norm": 0.09458816516251609,
      "kl": 0.02667999267578125,
      "learning_rate": 4.826557047444563e-07,
      "loss": 0.0,
      "reward": 1.1848958656191826,
      "reward_std": 0.3138170298188925,
      "rewards/equation_reward_func": 0.20572917233221233,
      "rewards/format_reward_func": 0.979166679084301,
      "step": 66
    },
    {
      "completion_length": 352.2083435058594,
      "epoch": 0.03626666666666667,
      "grad_norm": 0.08416786947789269,
      "kl": 0.03083038330078125,
      "learning_rate": 4.813130610139993e-07,
      "loss": 0.0,
      "reward": 1.1744792088866234,
      "reward_std": 0.2558550937101245,
      "rewards/equation_reward_func": 0.18489583861082792,
      "rewards/format_reward_func": 0.9895833432674408,
      "step": 68
    },
    {
      "completion_length": 377.62500953674316,
      "epoch": 0.037333333333333336,
      "grad_norm": 0.07539913544982475,
      "kl": 0.03000640869140625,
      "learning_rate": 4.799223798941089e-07,
      "loss": 0.0,
      "reward": 1.070312537252903,
      "reward_std": 0.17193882586434484,
      "rewards/equation_reward_func": 0.08072916814126074,
      "rewards/format_reward_func": 0.9895833432674408,
      "step": 70
    },
    {
      "completion_length": 370.4531364440918,
      "epoch": 0.0384,
      "grad_norm": 0.09187391682605524,
      "kl": 0.03436279296875,
      "learning_rate": 4.78483950191177e-07,
      "loss": 0.0,
      "reward": 1.1562500298023224,
      "reward_std": 0.2756755482405424,
      "rewards/equation_reward_func": 0.1770833362825215,
      "rewards/format_reward_func": 0.979166679084301,
      "step": 72
    },
    {
      "completion_length": 373.04688453674316,
      "epoch": 0.039466666666666664,
      "grad_norm": 0.09537515327502834,
      "kl": 0.03740692138671875,
      "learning_rate": 4.769980706276687e-07,
      "loss": 0.0,
      "reward": 1.1354167088866234,
      "reward_std": 0.25582731096073985,
      "rewards/equation_reward_func": 0.15885417256504297,
      "rewards/format_reward_func": 0.9765625186264515,
      "step": 74
    },
    {
      "completion_length": 387.8567810058594,
      "epoch": 0.04053333333333333,
      "grad_norm": 0.08000596022141122,
      "kl": 0.0389404296875,
      "learning_rate": 4.7546504978008595e-07,
      "loss": 0.0,
      "reward": 1.1328125335276127,
      "reward_std": 0.30721960263326764,
      "rewards/equation_reward_func": 0.1666666700039059,
      "rewards/format_reward_func": 0.9661458507180214,
      "step": 76
    },
    {
      "completion_length": 390.2448024749756,
      "epoch": 0.0416,
      "grad_norm": 0.07863626089779173,
      "kl": 0.0442047119140625,
      "learning_rate": 4.738852060148848e-07,
      "loss": 0.0,
      "reward": 1.127604205161333,
      "reward_std": 0.26901706866919994,
      "rewards/equation_reward_func": 0.15364583814516664,
      "rewards/format_reward_func": 0.9739583507180214,
      "step": 78
    },
    {
      "completion_length": 379.2161521911621,
      "epoch": 0.042666666666666665,
      "grad_norm": 0.08601071973954262,
      "kl": 0.0434417724609375,
      "learning_rate": 4.722588674223593e-07,
      "loss": 0.0,
      "reward": 1.1380208656191826,
      "reward_std": 0.2812240272760391,
      "rewards/equation_reward_func": 0.164062503259629,
      "rewards/format_reward_func": 0.9739583469927311,
      "step": 80
    },
    {
      "completion_length": 371.59115409851074,
      "epoch": 0.04373333333333333,
      "grad_norm": 0.07568126962421509,
      "kl": 0.0497894287109375,
      "learning_rate": 4.70586371748506e-07,
      "loss": 0.0,
      "reward": 1.1380208656191826,
      "reward_std": 0.25603401800617576,
      "rewards/equation_reward_func": 0.15885417070239782,
      "rewards/format_reward_func": 0.9791666828095913,
      "step": 82
    },
    {
      "completion_length": 381.30469703674316,
      "epoch": 0.0448,
      "grad_norm": 0.08065111561901392,
      "kl": 0.0525665283203125,
      "learning_rate": 4.6886806632488363e-07,
      "loss": 0.0001,
      "reward": 1.169270858168602,
      "reward_std": 0.25962691847234964,
      "rewards/equation_reward_func": 0.19531250419095159,
      "rewards/format_reward_func": 0.9739583432674408,
      "step": 84
    },
    {
      "completion_length": 350.8020944595337,
      "epoch": 0.04586666666666667,
      "grad_norm": 0.09857801804683694,
      "kl": 0.0528717041015625,
      "learning_rate": 4.6710430799648143e-07,
      "loss": 0.0001,
      "reward": 1.1796875447034836,
      "reward_std": 0.2887058644555509,
      "rewards/equation_reward_func": 0.1979166748933494,
      "rewards/format_reward_func": 0.9817708507180214,
      "step": 86
    },
    {
      "completion_length": 353.0573024749756,
      "epoch": 0.046933333333333334,
      "grad_norm": 0.09077630030450431,
      "kl": 0.059906005859375,
      "learning_rate": 4.652954630476127e-07,
      "loss": 0.0001,
      "reward": 1.2239583730697632,
      "reward_std": 0.30759388813748956,
      "rewards/equation_reward_func": 0.2500000069849193,
      "rewards/format_reward_func": 0.9739583507180214,
      "step": 88
    },
    {
      "completion_length": 359.1666784286499,
      "epoch": 0.048,
      "grad_norm": 0.09945645690703775,
      "kl": 0.0612030029296875,
      "learning_rate": 4.6344190712584713e-07,
      "loss": 0.0001,
      "reward": 1.2630208805203438,
      "reward_std": 0.27152396691963077,
      "rewards/equation_reward_func": 0.27604167466051877,
      "rewards/format_reward_func": 0.9869791753590107,
      "step": 90
    },
    {
      "completion_length": 349.7083396911621,
      "epoch": 0.04906666666666667,
      "grad_norm": 0.08132855652754273,
      "kl": 0.06951904296875,
      "learning_rate": 4.615440251639995e-07,
      "loss": 0.0001,
      "reward": 1.2395833656191826,
      "reward_std": 0.23549415357410908,
      "rewards/equation_reward_func": 0.25520834024064243,
      "rewards/format_reward_func": 0.9843750074505806,
      "step": 92
    },
    {
      "completion_length": 340.52084159851074,
      "epoch": 0.050133333333333335,
      "grad_norm": 0.08537044318099979,
      "kl": 0.075592041015625,
      "learning_rate": 4.596022113001894e-07,
      "loss": 0.0001,
      "reward": 1.2916667014360428,
      "reward_std": 0.3320260518230498,
      "rewards/equation_reward_func": 0.312500006519258,
      "rewards/format_reward_func": 0.9791666828095913,
      "step": 94
    },
    {
      "completion_length": 327.13282012939453,
      "epoch": 0.0512,
      "grad_norm": 0.09240179037114699,
      "kl": 0.070465087890625,
      "learning_rate": 4.576168687959895e-07,
      "loss": 0.0001,
      "reward": 1.3255208805203438,
      "reward_std": 0.386608456261456,
      "rewards/equation_reward_func": 0.3567708469927311,
      "rewards/format_reward_func": 0.9687500074505806,
      "step": 96
    },
    {
      "completion_length": 364.68751335144043,
      "epoch": 0.05226666666666667,
      "grad_norm": 0.10186126690814491,
      "kl": 0.080108642578125,
      "learning_rate": 4.555884099526793e-07,
      "loss": 0.0001,
      "reward": 1.1770833656191826,
      "reward_std": 0.2261401410214603,
      "rewards/equation_reward_func": 0.19010417093522847,
      "rewards/format_reward_func": 0.986979179084301,
      "step": 98
    },
    {
      "completion_length": 378.69271755218506,
      "epoch": 0.05333333333333334,
      "grad_norm": 0.08283978901098998,
      "kl": 0.070831298828125,
      "learning_rate": 4.5351725602562174e-07,
      "loss": 0.0001,
      "reward": 1.2083333805203438,
      "reward_std": 0.2539973724633455,
      "rewards/equation_reward_func": 0.22656251001171768,
      "rewards/format_reward_func": 0.9817708469927311,
      "step": 100
    },
    {
      "completion_length": 349.2812604904175,
      "epoch": 0.0544,
      "grad_norm": 0.10236681253344297,
      "kl": 0.0821533203125,
      "learning_rate": 4.514038371367791e-07,
      "loss": 0.0001,
      "reward": 1.3098958730697632,
      "reward_std": 0.3604734097607434,
      "rewards/equation_reward_func": 0.3437500107102096,
      "rewards/format_reward_func": 0.9661458432674408,
      "step": 102
    },
    {
      "completion_length": 357.3619899749756,
      "epoch": 0.055466666666666664,
      "grad_norm": 0.09738517323229856,
      "kl": 0.086883544921875,
      "learning_rate": 4.4924859218538936e-07,
      "loss": 0.0001,
      "reward": 1.3046875447034836,
      "reward_std": 0.3255553734488785,
      "rewards/equation_reward_func": 0.33072917233221233,
      "rewards/format_reward_func": 0.9739583469927311,
      "step": 104
    },
    {
      "completion_length": 365.2760524749756,
      "epoch": 0.05653333333333333,
      "grad_norm": 0.08975705250496918,
      "kl": 0.09002685546875,
      "learning_rate": 4.470519687568185e-07,
      "loss": 0.0001,
      "reward": 1.2968750484287739,
      "reward_std": 0.33681244123727083,
      "rewards/equation_reward_func": 0.3203125132713467,
      "rewards/format_reward_func": 0.9765625074505806,
      "step": 106
    },
    {
      "completion_length": 380.40365505218506,
      "epoch": 0.0576,
      "grad_norm": 0.08944591293143872,
      "kl": 0.085113525390625,
      "learning_rate": 4.4481442302960923e-07,
      "loss": 0.0001,
      "reward": 1.2135417126119137,
      "reward_std": 0.2771795648150146,
      "rewards/equation_reward_func": 0.23697917629033327,
      "rewards/format_reward_func": 0.9765625149011612,
      "step": 108
    },
    {
      "completion_length": 389.94271659851074,
      "epoch": 0.058666666666666666,
      "grad_norm": 0.09619766220094576,
      "kl": 0.09130859375,
      "learning_rate": 4.4253641968074505e-07,
      "loss": 0.0001,
      "reward": 1.2500000335276127,
      "reward_std": 0.2892899289727211,
      "rewards/equation_reward_func": 0.28645833977498114,
      "rewards/format_reward_func": 0.963541679084301,
      "step": 110
    },
    {
      "completion_length": 381.99219512939453,
      "epoch": 0.05973333333333333,
      "grad_norm": 0.10498087313979376,
      "kl": 0.09423828125,
      "learning_rate": 4.402184317891501e-07,
      "loss": 0.0001,
      "reward": 1.3229167088866234,
      "reward_std": 0.32423597015440464,
      "rewards/equation_reward_func": 0.35156250768341124,
      "rewards/format_reward_func": 0.9713541865348816,
      "step": 112
    },
    {
      "completion_length": 391.36719608306885,
      "epoch": 0.0608,
      "grad_norm": 0.09626210263887228,
      "kl": 0.097381591796875,
      "learning_rate": 4.37860940737443e-07,
      "loss": 0.0001,
      "reward": 1.2500000298023224,
      "reward_std": 0.3341089729219675,
      "rewards/equation_reward_func": 0.28385417186655104,
      "rewards/format_reward_func": 0.9661458469927311,
      "step": 114
    },
    {
      "completion_length": 379.2812614440918,
      "epoch": 0.06186666666666667,
      "grad_norm": 0.0919023125255689,
      "kl": 0.09576416015625,
      "learning_rate": 4.354644361119671e-07,
      "loss": 0.0001,
      "reward": 1.2968750447034836,
      "reward_std": 0.30213321885094047,
      "rewards/equation_reward_func": 0.3255208437331021,
      "rewards/format_reward_func": 0.9713541865348816,
      "step": 116
    },
    {
      "completion_length": 377.5989694595337,
      "epoch": 0.06293333333333333,
      "grad_norm": 0.1258891080084215,
      "kl": 0.1126708984375,
      "learning_rate": 4.3302941560111716e-07,
      "loss": 0.0001,
      "reward": 1.3880208656191826,
      "reward_std": 0.29082584474235773,
      "rewards/equation_reward_func": 0.4192708428017795,
      "rewards/format_reward_func": 0.9687500149011612,
      "step": 118
    },
    {
      "completion_length": 406.2239742279053,
      "epoch": 0.064,
      "grad_norm": 0.07341804992437591,
      "kl": 0.094940185546875,
      "learning_rate": 4.3055638489198236e-07,
      "loss": 0.0001,
      "reward": 1.3072916977107525,
      "reward_std": 0.3007106310687959,
      "rewards/equation_reward_func": 0.3359375118743628,
      "rewards/format_reward_func": 0.9713541865348816,
      "step": 120
    },
    {
      "completion_length": 440.3489694595337,
      "epoch": 0.06506666666666666,
      "grad_norm": 0.07202980759381214,
      "kl": 0.102081298828125,
      "learning_rate": 4.280458575653296e-07,
      "loss": 0.0001,
      "reward": 1.2942708879709244,
      "reward_std": 0.2781888456083834,
      "rewards/equation_reward_func": 0.34635417629033327,
      "rewards/format_reward_func": 0.9479166828095913,
      "step": 122
    },
    {
      "completion_length": 373.723970413208,
      "epoch": 0.06613333333333334,
      "grad_norm": 0.12005799306967507,
      "kl": 0.109588623046875,
      "learning_rate": 4.2549835498894665e-07,
      "loss": 0.0001,
      "reward": 1.3619792126119137,
      "reward_std": 0.30349841713905334,
      "rewards/equation_reward_func": 0.39583334419876337,
      "rewards/format_reward_func": 0.9661458544433117,
      "step": 124
    }
  ],
  "logging_steps": 2,
  "max_steps": 450,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "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": 1,
  "trial_name": null,
  "trial_params": null
}