{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.6890756302521008,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "clip_ratio": 0.0,
      "completion_length": 523.3984375,
      "epoch": 0.01680672268907563,
      "grad_norm": 0.4084254801273346,
      "kl": 0.0,
      "learning_rate": 3.3333333333333335e-07,
      "loss": 0.0346,
      "num_tokens": 149643.0,
      "reward": 0.05572916800156236,
      "reward_std": 0.1236814484000206,
      "rewards/curriculum_aware_reward_fn": 0.024479168001562357,
      "rewards/format_reward": 0.03125,
      "step": 1
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 446.5390625,
      "epoch": 0.03361344537815126,
      "grad_norm": 0.5236720442771912,
      "kl": 0.0,
      "learning_rate": 6.666666666666667e-07,
      "loss": 0.015,
      "num_tokens": 282184.0,
      "reward": 0.17552083544433117,
      "reward_std": 0.2788553349673748,
      "rewards/curriculum_aware_reward_fn": 0.12864583544433117,
      "rewards/format_reward": 0.046875,
      "step": 2
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 404.5625,
      "epoch": 0.05042016806722689,
      "grad_norm": 0.5860257744789124,
      "kl": 0.00027751922607421875,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.0033,
      "num_tokens": 411536.0,
      "reward": 0.1171875,
      "reward_std": 0.2090039700269699,
      "rewards/curriculum_aware_reward_fn": 0.078125,
      "rewards/format_reward": 0.0390625,
      "step": 3
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 437.8359375,
      "epoch": 0.06722689075630252,
      "grad_norm": 0.5572423338890076,
      "kl": 0.00028705596923828125,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 0.0288,
      "num_tokens": 543811.0,
      "reward": 0.1276041716337204,
      "reward_std": 0.17299909517169,
      "rewards/curriculum_aware_reward_fn": 0.1041666716337204,
      "rewards/format_reward": 0.0234375,
      "step": 4
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 484.453125,
      "epoch": 0.08403361344537816,
      "grad_norm": 0.5424997806549072,
      "kl": 0.0003066062927246094,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 0.0016,
      "num_tokens": 674637.0,
      "reward": 0.15625,
      "reward_std": 0.20851250365376472,
      "rewards/curriculum_aware_reward_fn": 0.109375,
      "rewards/format_reward": 0.046875,
      "step": 5
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 468.078125,
      "epoch": 0.10084033613445378,
      "grad_norm": 0.47155389189720154,
      "kl": 0.0003123283386230469,
      "learning_rate": 2.0000000000000003e-06,
      "loss": -0.0177,
      "num_tokens": 810527.0,
      "reward": 0.1276041716337204,
      "reward_std": 0.18760672956705093,
      "rewards/curriculum_aware_reward_fn": 0.0651041716337204,
      "rewards/format_reward": 0.0625,
      "step": 6
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 500.3125,
      "epoch": 0.11764705882352941,
      "grad_norm": 0.5090876817703247,
      "kl": 0.0004954338073730469,
      "learning_rate": 2.3333333333333336e-06,
      "loss": 0.0566,
      "num_tokens": 947063.0,
      "reward": 0.1354166679084301,
      "reward_std": 0.1753537617623806,
      "rewards/curriculum_aware_reward_fn": 0.07291666697710752,
      "rewards/format_reward": 0.0625,
      "step": 7
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 483.84375,
      "epoch": 0.13445378151260504,
      "grad_norm": 0.6272737979888916,
      "kl": 0.0008707046508789062,
      "learning_rate": 2.666666666666667e-06,
      "loss": 0.0704,
      "num_tokens": 1093987.0,
      "reward": 0.16250000149011612,
      "reward_std": 0.3029462620615959,
      "rewards/curriculum_aware_reward_fn": 0.037500000558793545,
      "rewards/format_reward": 0.125,
      "step": 8
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 423.1484375,
      "epoch": 0.15126050420168066,
      "grad_norm": 0.7402248978614807,
      "kl": 0.00279998779296875,
      "learning_rate": 3e-06,
      "loss": 0.0728,
      "num_tokens": 1218118.0,
      "reward": 0.3968750089406967,
      "reward_std": 0.45669952034950256,
      "rewards/curriculum_aware_reward_fn": 0.10781250474974513,
      "rewards/format_reward": 0.2890625,
      "step": 9
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 496.734375,
      "epoch": 0.16806722689075632,
      "grad_norm": 0.7178624272346497,
      "kl": 0.00432586669921875,
      "learning_rate": 3.3333333333333333e-06,
      "loss": -0.0207,
      "num_tokens": 1362188.0,
      "reward": 0.5677083432674408,
      "reward_std": 0.5023705065250397,
      "rewards/curriculum_aware_reward_fn": 0.013020833721384406,
      "rewards/format_reward": 0.5546875,
      "step": 10
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 500.3984375,
      "epoch": 0.18487394957983194,
      "grad_norm": 0.6241538524627686,
      "kl": 0.0084075927734375,
      "learning_rate": 3.6666666666666666e-06,
      "loss": 0.0165,
      "num_tokens": 1496743.0,
      "reward": 0.714062511920929,
      "reward_std": 0.344537615776062,
      "rewards/curriculum_aware_reward_fn": 0.010937500279396772,
      "rewards/format_reward": 0.703125,
      "step": 11
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 517.5625,
      "epoch": 0.20168067226890757,
      "grad_norm": 0.6269044280052185,
      "kl": 0.00717926025390625,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0195,
      "num_tokens": 1650679.0,
      "reward": 0.7604166716337204,
      "reward_std": 0.2794100269675255,
      "rewards/curriculum_aware_reward_fn": 0.010416666977107525,
      "rewards/format_reward": 0.75,
      "step": 12
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 489.9921875,
      "epoch": 0.2184873949579832,
      "grad_norm": 0.6628085374832153,
      "kl": 0.011993408203125,
      "learning_rate": 4.333333333333334e-06,
      "loss": 0.0178,
      "num_tokens": 1791190.0,
      "reward": 0.9375000298023224,
      "reward_std": 0.23163868859410286,
      "rewards/curriculum_aware_reward_fn": 0.031250000931322575,
      "rewards/format_reward": 0.90625,
      "step": 13
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 418.90625,
      "epoch": 0.23529411764705882,
      "grad_norm": 0.7439326643943787,
      "kl": 0.0212249755859375,
      "learning_rate": 4.666666666666667e-06,
      "loss": -0.0283,
      "num_tokens": 1912322.0,
      "reward": 0.8645833432674408,
      "reward_std": 0.2743529714643955,
      "rewards/curriculum_aware_reward_fn": 0.02864583395421505,
      "rewards/format_reward": 0.8359375,
      "step": 14
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 440.5546875,
      "epoch": 0.25210084033613445,
      "grad_norm": 0.477730393409729,
      "kl": 0.0169830322265625,
      "learning_rate": 5e-06,
      "loss": 0.0314,
      "num_tokens": 2041473.0,
      "reward": 1.0234375298023224,
      "reward_std": 0.159461235627532,
      "rewards/curriculum_aware_reward_fn": 0.05468750325962901,
      "rewards/format_reward": 0.96875,
      "step": 15
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 497.265625,
      "epoch": 0.2689075630252101,
      "grad_norm": 0.3044699728488922,
      "kl": 0.021484375,
      "learning_rate": 4.999952797253148e-06,
      "loss": 0.0386,
      "num_tokens": 2178899.0,
      "reward": 0.9427083432674408,
      "reward_std": 0.10222155228257179,
      "rewards/curriculum_aware_reward_fn": 0.06770833395421505,
      "rewards/format_reward": 0.875,
      "step": 16
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 503.7421875,
      "epoch": 0.2857142857142857,
      "grad_norm": 0.4504559338092804,
      "kl": 0.033233642578125,
      "learning_rate": 4.9998111909931225e-06,
      "loss": 0.0346,
      "num_tokens": 2311042.0,
      "reward": 1.0927083492279053,
      "reward_std": 0.13363875821232796,
      "rewards/curriculum_aware_reward_fn": 0.09270833618938923,
      "rewards/format_reward": 1.0,
      "step": 17
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 582.390625,
      "epoch": 0.3025210084033613,
      "grad_norm": 0.3522663712501526,
      "kl": 0.033416748046875,
      "learning_rate": 4.999575187161439e-06,
      "loss": 0.0049,
      "num_tokens": 2477404.0,
      "reward": 0.997395858168602,
      "reward_std": 0.0840194127522409,
      "rewards/curriculum_aware_reward_fn": 0.05989583651535213,
      "rewards/format_reward": 0.9375,
      "step": 18
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 603.4140625,
      "epoch": 0.31932773109243695,
      "grad_norm": 0.2832561731338501,
      "kl": 0.0328369140625,
      "learning_rate": 4.9992447956603455e-06,
      "loss": 0.0152,
      "num_tokens": 2642801.0,
      "reward": 0.895833358168602,
      "reward_std": 0.05173455877229571,
      "rewards/curriculum_aware_reward_fn": 0.020833333721384406,
      "rewards/format_reward": 0.875,
      "step": 19
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 501.46875,
      "epoch": 0.33613445378151263,
      "grad_norm": 0.4254682660102844,
      "kl": 0.0416259765625,
      "learning_rate": 4.998820030352409e-06,
      "loss": 0.0009,
      "num_tokens": 2784445.0,
      "reward": 1.0010417103767395,
      "reward_std": 0.13327472284436226,
      "rewards/curriculum_aware_reward_fn": 0.07135416753590107,
      "rewards/format_reward": 0.9296875,
      "step": 20
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 598.765625,
      "epoch": 0.35294117647058826,
      "grad_norm": 0.3762480914592743,
      "kl": 0.033721923828125,
      "learning_rate": 4.998300909059929e-06,
      "loss": -0.0163,
      "num_tokens": 2951415.0,
      "reward": 0.9947916865348816,
      "reward_std": 0.11004853993654251,
      "rewards/curriculum_aware_reward_fn": 0.07291666604578495,
      "rewards/format_reward": 0.921875,
      "step": 21
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 489.6484375,
      "epoch": 0.3697478991596639,
      "grad_norm": 0.6521299481391907,
      "kl": 0.04229736328125,
      "learning_rate": 4.997687453564198e-06,
      "loss": 0.0083,
      "num_tokens": 3090354.0,
      "reward": 0.9609375298023224,
      "reward_std": 0.25490327179431915,
      "rewards/curriculum_aware_reward_fn": 0.1562500037252903,
      "rewards/format_reward": 0.8046875,
      "step": 22
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 446.625,
      "epoch": 0.3865546218487395,
      "grad_norm": 0.4581259489059448,
      "kl": 0.02838134765625,
      "learning_rate": 4.9969796896045775e-06,
      "loss": 0.0239,
      "num_tokens": 3234002.0,
      "reward": 1.1093750298023224,
      "reward_std": 0.15402578841894865,
      "rewards/curriculum_aware_reward_fn": 0.17187500139698386,
      "rewards/format_reward": 0.9375,
      "step": 23
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 438.296875,
      "epoch": 0.40336134453781514,
      "grad_norm": 0.469014436006546,
      "kl": 0.02874755859375,
      "learning_rate": 4.996177646877426e-06,
      "loss": 0.0065,
      "num_tokens": 3368280.0,
      "reward": 1.0302083790302277,
      "reward_std": 0.12476669438183308,
      "rewards/curriculum_aware_reward_fn": 0.045833335258066654,
      "rewards/format_reward": 0.984375,
      "step": 24
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 433.9921875,
      "epoch": 0.42016806722689076,
      "grad_norm": 0.5325790643692017,
      "kl": 0.028350830078125,
      "learning_rate": 4.995281359034851e-06,
      "loss": -0.0046,
      "num_tokens": 3495607.0,
      "reward": 1.0026041865348816,
      "reward_std": 0.2044544592499733,
      "rewards/curriculum_aware_reward_fn": 0.08072916977107525,
      "rewards/format_reward": 0.921875,
      "step": 25
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 380.015625,
      "epoch": 0.4369747899159664,
      "grad_norm": 0.5200158357620239,
      "kl": 0.03680419921875,
      "learning_rate": 4.994290863683296e-06,
      "loss": 0.0419,
      "num_tokens": 3609809.0,
      "reward": 1.1458334028720856,
      "reward_std": 0.20207119127735496,
      "rewards/curriculum_aware_reward_fn": 0.15364583837799728,
      "rewards/format_reward": 0.9921875,
      "step": 26
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 413.7265625,
      "epoch": 0.453781512605042,
      "grad_norm": 0.41265320777893066,
      "kl": 0.033966064453125,
      "learning_rate": 4.99320620238196e-06,
      "loss": -0.0204,
      "num_tokens": 3744550.0,
      "reward": 1.0963541865348816,
      "reward_std": 0.11664257757365704,
      "rewards/curriculum_aware_reward_fn": 0.09635416604578495,
      "rewards/format_reward": 1.0,
      "step": 27
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 461.4375,
      "epoch": 0.47058823529411764,
      "grad_norm": 0.3836808502674103,
      "kl": 0.032623291015625,
      "learning_rate": 4.99202742064106e-06,
      "loss": 0.035,
      "num_tokens": 3875238.0,
      "reward": 1.0182291865348816,
      "reward_std": 0.10335793904960155,
      "rewards/curriculum_aware_reward_fn": 0.0807291679084301,
      "rewards/format_reward": 0.9375,
      "step": 28
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 506.953125,
      "epoch": 0.48739495798319327,
      "grad_norm": 0.3787353038787842,
      "kl": 0.029510498046875,
      "learning_rate": 4.990754567919917e-06,
      "loss": 0.0725,
      "num_tokens": 4024312.0,
      "reward": 0.9531250298023224,
      "reward_std": 0.08838835544884205,
      "rewards/curriculum_aware_reward_fn": 0.08593750279396772,
      "rewards/format_reward": 0.8671875,
      "step": 29
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 474.1875,
      "epoch": 0.5042016806722689,
      "grad_norm": 0.37932828068733215,
      "kl": 0.03497314453125,
      "learning_rate": 4.989387697624881e-06,
      "loss": 0.0078,
      "num_tokens": 4161712.0,
      "reward": 1.1328125298023224,
      "reward_std": 0.14552949741482735,
      "rewards/curriculum_aware_reward_fn": 0.1328125037252903,
      "rewards/format_reward": 1.0,
      "step": 30
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 447.6796875,
      "epoch": 0.5210084033613446,
      "grad_norm": 0.396627813577652,
      "kl": 0.0396728515625,
      "learning_rate": 4.987926867107095e-06,
      "loss": 0.004,
      "num_tokens": 4304935.0,
      "reward": 0.9671875089406967,
      "reward_std": 0.12499183788895607,
      "rewards/curriculum_aware_reward_fn": 0.09218750381842256,
      "rewards/format_reward": 0.875,
      "step": 31
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 574.703125,
      "epoch": 0.5378151260504201,
      "grad_norm": 0.39759182929992676,
      "kl": 0.030426025390625,
      "learning_rate": 4.986372137660078e-06,
      "loss": 0.0566,
      "num_tokens": 4464105.0,
      "reward": 0.8953125327825546,
      "reward_std": 0.147516256198287,
      "rewards/curriculum_aware_reward_fn": 0.0906250006519258,
      "rewards/format_reward": 0.8046875,
      "step": 32
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 434.640625,
      "epoch": 0.5546218487394958,
      "grad_norm": 0.3933623433113098,
      "kl": 0.034210205078125,
      "learning_rate": 4.984723574517165e-06,
      "loss": 0.0163,
      "num_tokens": 4602139.0,
      "reward": 1.1234374940395355,
      "reward_std": 0.15428178012371063,
      "rewards/curriculum_aware_reward_fn": 0.18593750335276127,
      "rewards/format_reward": 0.9375,
      "step": 33
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 445.1640625,
      "epoch": 0.5714285714285714,
      "grad_norm": 0.3263511061668396,
      "kl": 0.04083251953125,
      "learning_rate": 4.9829812468487655e-06,
      "loss": 0.0145,
      "num_tokens": 4736544.0,
      "reward": 0.9843750298023224,
      "reward_std": 0.09849035926163197,
      "rewards/curriculum_aware_reward_fn": 0.05468750139698386,
      "rewards/format_reward": 0.9296875,
      "step": 34
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 477.53125,
      "epoch": 0.5882352941176471,
      "grad_norm": 0.336434543132782,
      "kl": 0.0318603515625,
      "learning_rate": 4.981145227759457e-06,
      "loss": 0.0017,
      "num_tokens": 4881308.0,
      "reward": 0.966145858168602,
      "reward_std": 0.07084779627621174,
      "rewards/curriculum_aware_reward_fn": 0.09114583441987634,
      "rewards/format_reward": 0.875,
      "step": 35
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 469.4609375,
      "epoch": 0.6050420168067226,
      "grad_norm": 0.3600573241710663,
      "kl": 0.0386962890625,
      "learning_rate": 4.979215594284924e-06,
      "loss": 0.008,
      "num_tokens": 5017415.0,
      "reward": 1.0843750536441803,
      "reward_std": 0.11371596809476614,
      "rewards/curriculum_aware_reward_fn": 0.08437500288709998,
      "rewards/format_reward": 1.0,
      "step": 36
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 422.7890625,
      "epoch": 0.6218487394957983,
      "grad_norm": 0.38463500142097473,
      "kl": 0.03997802734375,
      "learning_rate": 4.977192427388722e-06,
      "loss": 0.0195,
      "num_tokens": 5141804.0,
      "reward": 1.1130208671092987,
      "reward_std": 0.1456994889304042,
      "rewards/curriculum_aware_reward_fn": 0.12083333730697632,
      "rewards/format_reward": 0.9921875,
      "step": 37
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 415.4765625,
      "epoch": 0.6386554621848739,
      "grad_norm": 0.5343978404998779,
      "kl": 0.04315185546875,
      "learning_rate": 4.9750758119588824e-06,
      "loss": -0.0,
      "num_tokens": 5262529.0,
      "reward": 1.136979192495346,
      "reward_std": 0.29098181426525116,
      "rewards/curriculum_aware_reward_fn": 0.16822916036471725,
      "rewards/format_reward": 0.96875,
      "step": 38
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 442.2421875,
      "epoch": 0.6554621848739496,
      "grad_norm": 0.33322009444236755,
      "kl": 0.047119140625,
      "learning_rate": 4.972865836804349e-06,
      "loss": 0.0088,
      "num_tokens": 5399424.0,
      "reward": 1.03125,
      "reward_std": 0.13204573467373848,
      "rewards/curriculum_aware_reward_fn": 0.109375,
      "rewards/format_reward": 0.921875,
      "step": 39
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 482.59375,
      "epoch": 0.6722689075630253,
      "grad_norm": 0.35028988122940063,
      "kl": 0.0504150390625,
      "learning_rate": 4.970562594651254e-06,
      "loss": 0.0066,
      "num_tokens": 5539492.0,
      "reward": 1.09375,
      "reward_std": 0.1325825173407793,
      "rewards/curriculum_aware_reward_fn": 0.125,
      "rewards/format_reward": 0.96875,
      "step": 40
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 423.125,
      "epoch": 0.6890756302521008,
      "grad_norm": 0.3613918125629425,
      "kl": 0.06549072265625,
      "learning_rate": 4.968166182139026e-06,
      "loss": 0.0516,
      "num_tokens": 5667012.0,
      "reward": 1.122395858168602,
      "reward_std": 0.09522313997149467,
      "rewards/curriculum_aware_reward_fn": 0.13020833837799728,
      "rewards/format_reward": 0.9921875,
      "step": 41
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 391.953125,
      "epoch": 0.7058823529411765,
      "grad_norm": 0.6798313856124878,
      "kl": 0.080322265625,
      "learning_rate": 4.9656766998163306e-06,
      "loss": 0.0429,
      "num_tokens": 5786006.0,
      "reward": 1.1645833551883698,
      "reward_std": 0.23287939466536045,
      "rewards/curriculum_aware_reward_fn": 0.19583334028720856,
      "rewards/format_reward": 0.96875,
      "step": 42
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 406.59375,
      "epoch": 0.7226890756302521,
      "grad_norm": 0.4006165862083435,
      "kl": 0.06298828125,
      "learning_rate": 4.963094252136865e-06,
      "loss": 0.0119,
      "num_tokens": 5910762.0,
      "reward": 1.0989583432674408,
      "reward_std": 0.1059559416025877,
      "rewards/curriculum_aware_reward_fn": 0.16927083767950535,
      "rewards/format_reward": 0.9296875,
      "step": 43
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 411.28125,
      "epoch": 0.7394957983193278,
      "grad_norm": 0.3308926522731781,
      "kl": 0.068359375,
      "learning_rate": 4.960418947454958e-06,
      "loss": 0.0204,
      "num_tokens": 6042942.0,
      "reward": 0.9947916865348816,
      "reward_std": 0.10640286095440388,
      "rewards/curriculum_aware_reward_fn": 0.0572916679084301,
      "rewards/format_reward": 0.9375,
      "step": 44
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 380.9140625,
      "epoch": 0.7563025210084033,
      "grad_norm": 0.478098064661026,
      "kl": 0.0755615234375,
      "learning_rate": 4.957650898021038e-06,
      "loss": 0.0624,
      "num_tokens": 6162299.0,
      "reward": 1.158854216337204,
      "reward_std": 0.20395735278725624,
      "rewards/curriculum_aware_reward_fn": 0.15885416977107525,
      "rewards/format_reward": 1.0,
      "step": 45
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 333.5390625,
      "epoch": 0.773109243697479,
      "grad_norm": 0.47225892543792725,
      "kl": 0.0811767578125,
      "learning_rate": 4.954790219976915e-06,
      "loss": 0.0167,
      "num_tokens": 6272592.0,
      "reward": 1.170312523841858,
      "reward_std": 0.1300742938183248,
      "rewards/curriculum_aware_reward_fn": 0.17031250218860805,
      "rewards/format_reward": 1.0,
      "step": 46
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 366.34375,
      "epoch": 0.7899159663865546,
      "grad_norm": 0.4816167652606964,
      "kl": 0.0848388671875,
      "learning_rate": 4.95183703335091e-06,
      "loss": 0.0103,
      "num_tokens": 6397436.0,
      "reward": 1.1953125298023224,
      "reward_std": 0.12861409783363342,
      "rewards/curriculum_aware_reward_fn": 0.1953125074505806,
      "rewards/format_reward": 1.0,
      "step": 47
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 338.65625,
      "epoch": 0.8067226890756303,
      "grad_norm": 0.47690296173095703,
      "kl": 0.07958984375,
      "learning_rate": 4.948791462052819e-06,
      "loss": -0.0039,
      "num_tokens": 6519896.0,
      "reward": 1.0442708730697632,
      "reward_std": 0.11976211331784725,
      "rewards/curriculum_aware_reward_fn": 0.05208333441987634,
      "rewards/format_reward": 0.9921875,
      "step": 48
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 325.78125,
      "epoch": 0.8235294117647058,
      "grad_norm": 0.46987131237983704,
      "kl": 0.08935546875,
      "learning_rate": 4.945653633868716e-06,
      "loss": 0.023,
      "num_tokens": 6637036.0,
      "reward": 1.1223958730697632,
      "reward_std": 0.18378917127847672,
      "rewards/curriculum_aware_reward_fn": 0.14583333488553762,
      "rewards/format_reward": 0.9765625,
      "step": 49
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 302.6171875,
      "epoch": 0.8403361344537815,
      "grad_norm": 0.5635585784912109,
      "kl": 0.088623046875,
      "learning_rate": 4.942423680455584e-06,
      "loss": 0.0157,
      "num_tokens": 6749411.0,
      "reward": 1.1494792103767395,
      "reward_std": 0.19005249440670013,
      "rewards/curriculum_aware_reward_fn": 0.1494791703298688,
      "rewards/format_reward": 1.0,
      "step": 50
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 366.4140625,
      "epoch": 0.8571428571428571,
      "grad_norm": 0.5150569677352905,
      "kl": 0.0848388671875,
      "learning_rate": 4.939101737335802e-06,
      "loss": -0.0145,
      "num_tokens": 6879104.0,
      "reward": 0.9713541865348816,
      "reward_std": 0.12468592822551727,
      "rewards/curriculum_aware_reward_fn": 0.041666666977107525,
      "rewards/format_reward": 0.9296875,
      "step": 51
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 288.9609375,
      "epoch": 0.8739495798319328,
      "grad_norm": 0.6744732856750488,
      "kl": 0.088134765625,
      "learning_rate": 4.935687943891447e-06,
      "loss": 0.0413,
      "num_tokens": 6981627.0,
      "reward": 1.171354204416275,
      "reward_std": 0.26688926108181477,
      "rewards/curriculum_aware_reward_fn": 0.1791666648350656,
      "rewards/format_reward": 0.9921875,
      "step": 52
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 286.609375,
      "epoch": 0.8907563025210085,
      "grad_norm": 0.6298589706420898,
      "kl": 0.0899658203125,
      "learning_rate": 4.932182443358458e-06,
      "loss": 0.002,
      "num_tokens": 7088449.0,
      "reward": 1.1250000298023224,
      "reward_std": 0.14211241621524096,
      "rewards/curriculum_aware_reward_fn": 0.125000003259629,
      "rewards/format_reward": 1.0,
      "step": 53
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 302.4921875,
      "epoch": 0.907563025210084,
      "grad_norm": 0.6446663737297058,
      "kl": 0.0955810546875,
      "learning_rate": 4.928585382820616e-06,
      "loss": 0.0001,
      "num_tokens": 7197360.0,
      "reward": 1.1005208790302277,
      "reward_std": 0.08887648163363338,
      "rewards/curriculum_aware_reward_fn": 0.10052083828486502,
      "rewards/format_reward": 1.0,
      "step": 54
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 399.0625,
      "epoch": 0.9243697478991597,
      "grad_norm": 0.729965090751648,
      "kl": 0.1077880859375,
      "learning_rate": 4.924896913203376e-06,
      "loss": 0.0496,
      "num_tokens": 7331528.0,
      "reward": 0.9932291805744171,
      "reward_std": 0.15547171607613564,
      "rewards/curriculum_aware_reward_fn": 0.1807291698642075,
      "rewards/format_reward": 0.8125,
      "step": 55
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 494.09375,
      "epoch": 0.9411764705882353,
      "grad_norm": 0.41514354944229126,
      "kl": 0.0888671875,
      "learning_rate": 4.921117189267535e-06,
      "loss": -0.0255,
      "num_tokens": 7482548.0,
      "reward": 0.8671875149011612,
      "reward_std": 0.09729943191632628,
      "rewards/curriculum_aware_reward_fn": 0.05468750069849193,
      "rewards/format_reward": 0.8125,
      "step": 56
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 511.90625,
      "epoch": 0.957983193277311,
      "grad_norm": 0.6172528266906738,
      "kl": 0.1680908203125,
      "learning_rate": 4.917246369602742e-06,
      "loss": 0.0368,
      "num_tokens": 7621256.0,
      "reward": 1.050520896911621,
      "reward_std": 0.1373576819896698,
      "rewards/curriculum_aware_reward_fn": 0.17552083916962147,
      "rewards/format_reward": 0.875,
      "step": 57
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 415.8046875,
      "epoch": 0.9747899159663865,
      "grad_norm": 0.5895751118659973,
      "kl": 0.2454833984375,
      "learning_rate": 4.9132846166208355e-06,
      "loss": 0.0654,
      "num_tokens": 7740207.0,
      "reward": 1.1197916865348816,
      "reward_std": 0.09127403190359473,
      "rewards/curriculum_aware_reward_fn": 0.12760416674427688,
      "rewards/format_reward": 0.9921875,
      "step": 58
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 578.2857208251953,
      "epoch": 0.9915966386554622,
      "grad_norm": 0.4072950482368469,
      "kl": 0.12353515625,
      "learning_rate": 4.9092320965490365e-06,
      "loss": 0.0363,
      "num_tokens": 7885325.0,
      "reward": 1.0598958432674408,
      "reward_std": 0.11012758687138557,
      "rewards/curriculum_aware_reward_fn": 0.0598958358168602,
      "rewards/format_reward": 1.0,
      "step": 59
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 564.78125,
      "epoch": 1.0168067226890756,
      "grad_norm": 0.4054146707057953,
      "kl": 0.1219482421875,
      "learning_rate": 4.905088979422971e-06,
      "loss": 0.0515,
      "num_tokens": 8038297.0,
      "reward": 1.0937500596046448,
      "reward_std": 0.1636663186363876,
      "rewards/curriculum_aware_reward_fn": 0.1015625053551048,
      "rewards/format_reward": 0.9921875,
      "step": 60
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 578.2890625,
      "epoch": 1.0336134453781514,
      "grad_norm": 0.3728667199611664,
      "kl": 0.126708984375,
      "learning_rate": 4.900855439079536e-06,
      "loss": 0.0134,
      "num_tokens": 8185046.0,
      "reward": 1.1265625357627869,
      "reward_std": 0.14053087309002876,
      "rewards/curriculum_aware_reward_fn": 0.12656250409781933,
      "rewards/format_reward": 1.0,
      "step": 61
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 722.3125,
      "epoch": 1.050420168067227,
      "grad_norm": 0.32597795128822327,
      "kl": 0.1097412109375,
      "learning_rate": 4.8965316531496055e-06,
      "loss": 0.0184,
      "num_tokens": 8366894.0,
      "reward": 0.9677083492279053,
      "reward_std": 0.10382660711184144,
      "rewards/curriculum_aware_reward_fn": 0.04583333386108279,
      "rewards/format_reward": 0.921875,
      "step": 62
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 663.3671875,
      "epoch": 1.0672268907563025,
      "grad_norm": 0.4411354064941406,
      "kl": 0.1256103515625,
      "learning_rate": 4.892117803050578e-06,
      "loss": 0.0637,
      "num_tokens": 8514637.0,
      "reward": 1.0671875327825546,
      "reward_std": 0.21371026523411274,
      "rewards/curriculum_aware_reward_fn": 0.09843750204890966,
      "rewards/format_reward": 0.96875,
      "step": 63
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 644.1328125,
      "epoch": 1.084033613445378,
      "grad_norm": 0.36323124170303345,
      "kl": 0.1290283203125,
      "learning_rate": 4.887614073978761e-06,
      "loss": -0.0258,
      "num_tokens": 8683182.0,
      "reward": 0.9921875,
      "reward_std": 0.12415501847863197,
      "rewards/curriculum_aware_reward_fn": 0.0859375,
      "rewards/format_reward": 0.90625,
      "step": 64
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 659.5703125,
      "epoch": 1.1008403361344539,
      "grad_norm": 0.5263646245002747,
      "kl": 0.1494140625,
      "learning_rate": 4.883020654901609e-06,
      "loss": -0.03,
      "num_tokens": 8846031.0,
      "reward": 0.9375000149011612,
      "reward_std": 0.29325952008366585,
      "rewards/curriculum_aware_reward_fn": 0.08593750093132257,
      "rewards/format_reward": 0.8515625,
      "step": 65
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 542.421875,
      "epoch": 1.1176470588235294,
      "grad_norm": 0.5841398239135742,
      "kl": 0.1328125,
      "learning_rate": 4.878337738549785e-06,
      "loss": 0.0185,
      "num_tokens": 8994685.0,
      "reward": 0.9244791865348816,
      "reward_std": 0.350746251642704,
      "rewards/curriculum_aware_reward_fn": 0.0651041679084301,
      "rewards/format_reward": 0.859375,
      "step": 66
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 582.9453125,
      "epoch": 1.134453781512605,
      "grad_norm": 0.5570164322853088,
      "kl": 0.122314453125,
      "learning_rate": 4.873565521409082e-06,
      "loss": 0.0521,
      "num_tokens": 9155622.0,
      "reward": 0.9843750298023224,
      "reward_std": 0.3105625621974468,
      "rewards/curriculum_aware_reward_fn": 0.140625,
      "rewards/format_reward": 0.84375,
      "step": 67
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 485.3359375,
      "epoch": 1.1512605042016806,
      "grad_norm": 0.5985521078109741,
      "kl": 0.1263427734375,
      "learning_rate": 4.868704203712173e-06,
      "loss": 0.0059,
      "num_tokens": 9288609.0,
      "reward": 1.052083358168602,
      "reward_std": 0.3865399658679962,
      "rewards/curriculum_aware_reward_fn": 0.18489583488553762,
      "rewards/format_reward": 0.8671875,
      "step": 68
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 535.578125,
      "epoch": 1.1680672268907564,
      "grad_norm": 0.564681887626648,
      "kl": 0.1126708984375,
      "learning_rate": 4.86375398943021e-06,
      "loss": -0.0485,
      "num_tokens": 9437915.0,
      "reward": 0.9140625298023224,
      "reward_std": 0.28478266298770905,
      "rewards/curriculum_aware_reward_fn": 0.07031250256113708,
      "rewards/format_reward": 0.84375,
      "step": 69
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 496.0703125,
      "epoch": 1.184873949579832,
      "grad_norm": 0.5399004220962524,
      "kl": 0.099853515625,
      "learning_rate": 4.858715086264274e-06,
      "loss": 0.0,
      "num_tokens": 9580828.0,
      "reward": 0.934895858168602,
      "reward_std": 0.19700524397194386,
      "rewards/curriculum_aware_reward_fn": 0.04427083441987634,
      "rewards/format_reward": 0.890625,
      "step": 70
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 469.078125,
      "epoch": 1.2016806722689075,
      "grad_norm": 0.552808940410614,
      "kl": 0.104736328125,
      "learning_rate": 4.853587705636646e-06,
      "loss": -0.0129,
      "num_tokens": 9710926.0,
      "reward": 1.0234375447034836,
      "reward_std": 0.2662259414792061,
      "rewards/curriculum_aware_reward_fn": 0.07031250186264515,
      "rewards/format_reward": 0.953125,
      "step": 71
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 539.765625,
      "epoch": 1.2184873949579833,
      "grad_norm": 0.4241795837879181,
      "kl": 0.093505859375,
      "learning_rate": 4.84837206268195e-06,
      "loss": -0.0161,
      "num_tokens": 9867328.0,
      "reward": 0.796875,
      "reward_std": 0.12126770988106728,
      "rewards/curriculum_aware_reward_fn": 0.015625,
      "rewards/format_reward": 0.78125,
      "step": 72
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 502.6328125,
      "epoch": 1.2352941176470589,
      "grad_norm": 0.4336708188056946,
      "kl": 0.0975341796875,
      "learning_rate": 4.8430683762381195e-06,
      "loss": 0.0086,
      "num_tokens": 10007809.0,
      "reward": 1.0416666865348816,
      "reward_std": 0.1647402998059988,
      "rewards/curriculum_aware_reward_fn": 0.07291666697710752,
      "rewards/format_reward": 0.96875,
      "step": 73
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 523.640625,
      "epoch": 1.2521008403361344,
      "grad_norm": 0.46911758184432983,
      "kl": 0.1041259765625,
      "learning_rate": 4.837676868837213e-06,
      "loss": 0.0313,
      "num_tokens": 10147291.0,
      "reward": 1.0302083790302277,
      "reward_std": 0.18167300708591938,
      "rewards/curriculum_aware_reward_fn": 0.06145833572372794,
      "rewards/format_reward": 0.96875,
      "step": 74
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 628.6171875,
      "epoch": 1.26890756302521,
      "grad_norm": 0.5553966760635376,
      "kl": 0.091552734375,
      "learning_rate": 4.832197766696085e-06,
      "loss": 0.0771,
      "num_tokens": 10304234.0,
      "reward": 1.0401041805744171,
      "reward_std": 0.2994466572999954,
      "rewards/curriculum_aware_reward_fn": 0.14166666939854622,
      "rewards/format_reward": 0.8984375,
      "step": 75
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 541.03125,
      "epoch": 1.2857142857142856,
      "grad_norm": 0.4850277602672577,
      "kl": 0.092529296875,
      "learning_rate": 4.826631299706887e-06,
      "loss": -0.0076,
      "num_tokens": 10455718.0,
      "reward": 1.043229192495346,
      "reward_std": 0.18734892271459103,
      "rewards/curriculum_aware_reward_fn": 0.12135417200624943,
      "rewards/format_reward": 0.921875,
      "step": 76
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 513.34375,
      "epoch": 1.3025210084033614,
      "grad_norm": 0.5054645538330078,
      "kl": 0.098876953125,
      "learning_rate": 4.820977701427424e-06,
      "loss": 0.0342,
      "num_tokens": 10586514.0,
      "reward": 1.0703125149011612,
      "reward_std": 0.18218252062797546,
      "rewards/curriculum_aware_reward_fn": 0.10156250256113708,
      "rewards/format_reward": 0.96875,
      "step": 77
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 554.0390625,
      "epoch": 1.319327731092437,
      "grad_norm": 0.5157454013824463,
      "kl": 0.0882568359375,
      "learning_rate": 4.81523720907136e-06,
      "loss": 0.05,
      "num_tokens": 10726735.0,
      "reward": 1.1385416984558105,
      "reward_std": 0.23471001349389553,
      "rewards/curriculum_aware_reward_fn": 0.17760416865348816,
      "rewards/format_reward": 0.9609375,
      "step": 78
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 580.015625,
      "epoch": 1.3361344537815127,
      "grad_norm": 0.41959676146507263,
      "kl": 0.0958251953125,
      "learning_rate": 4.809410063498254e-06,
      "loss": 0.0059,
      "num_tokens": 10884185.0,
      "reward": 0.8411458283662796,
      "reward_std": 0.22234245762228966,
      "rewards/curriculum_aware_reward_fn": 0.06770833395421505,
      "rewards/format_reward": 0.7734375,
      "step": 79
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 534.84375,
      "epoch": 1.3529411764705883,
      "grad_norm": 0.6390196681022644,
      "kl": 0.093017578125,
      "learning_rate": 4.8034965092034656e-06,
      "loss": 0.0963,
      "num_tokens": 11024149.0,
      "reward": 1.0494791865348816,
      "reward_std": 0.2942212373018265,
      "rewards/curriculum_aware_reward_fn": 0.1432291679084301,
      "rewards/format_reward": 0.90625,
      "step": 80
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 525.671875,
      "epoch": 1.3697478991596639,
      "grad_norm": 0.4957650303840637,
      "kl": 0.105224609375,
      "learning_rate": 4.797496794307889e-06,
      "loss": -0.0236,
      "num_tokens": 11167547.0,
      "reward": 0.9828125238418579,
      "reward_std": 0.14313106751069427,
      "rewards/curriculum_aware_reward_fn": 0.06093750288709998,
      "rewards/format_reward": 0.921875,
      "step": 81
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 488.7890625,
      "epoch": 1.3865546218487395,
      "grad_norm": 0.5502341389656067,
      "kl": 0.104248046875,
      "learning_rate": 4.791411170547545e-06,
      "loss": 0.072,
      "num_tokens": 11300104.0,
      "reward": 1.143229216337204,
      "reward_std": 0.2514217048883438,
      "rewards/curriculum_aware_reward_fn": 0.1822916679084301,
      "rewards/format_reward": 0.9609375,
      "step": 82
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 508.1015625,
      "epoch": 1.403361344537815,
      "grad_norm": 0.489242285490036,
      "kl": 0.0986328125,
      "learning_rate": 4.785239893263017e-06,
      "loss": 0.1064,
      "num_tokens": 11446565.0,
      "reward": 0.9505208730697632,
      "reward_std": 0.18909456953406334,
      "rewards/curriculum_aware_reward_fn": 0.1145833358168602,
      "rewards/format_reward": 0.8359375,
      "step": 83
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 448.359375,
      "epoch": 1.4201680672268908,
      "grad_norm": 0.46208083629608154,
      "kl": 0.11083984375,
      "learning_rate": 4.778983221388742e-06,
      "loss": 0.0139,
      "num_tokens": 11580547.0,
      "reward": 1.0276041626930237,
      "reward_std": 0.12672015465795994,
      "rewards/curriculum_aware_reward_fn": 0.09791666641831398,
      "rewards/format_reward": 0.9296875,
      "step": 84
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 457.3515625,
      "epoch": 1.4369747899159664,
      "grad_norm": 0.44321703910827637,
      "kl": 0.1085205078125,
      "learning_rate": 4.77264141744214e-06,
      "loss": 0.0184,
      "num_tokens": 11712984.0,
      "reward": 1.160416692495346,
      "reward_std": 0.15310384705662727,
      "rewards/curriculum_aware_reward_fn": 0.16041666828095913,
      "rewards/format_reward": 1.0,
      "step": 85
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 384.3984375,
      "epoch": 1.453781512605042,
      "grad_norm": 0.4427275061607361,
      "kl": 0.123779296875,
      "learning_rate": 4.766214747512603e-06,
      "loss": 0.0233,
      "num_tokens": 11829315.0,
      "reward": 1.1666666865348816,
      "reward_std": 0.14362479094415903,
      "rewards/curriculum_aware_reward_fn": 0.1744791674427688,
      "rewards/format_reward": 0.9921875,
      "step": 86
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 389.265625,
      "epoch": 1.4705882352941178,
      "grad_norm": 0.5121983885765076,
      "kl": 0.12841796875,
      "learning_rate": 4.759703481250331e-06,
      "loss": 0.0229,
      "num_tokens": 11949533.0,
      "reward": 1.1343750357627869,
      "reward_std": 0.16322745941579342,
      "rewards/curriculum_aware_reward_fn": 0.1500000013038516,
      "rewards/format_reward": 0.984375,
      "step": 87
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 459.921875,
      "epoch": 1.4873949579831933,
      "grad_norm": 0.6308655738830566,
      "kl": 0.11328125,
      "learning_rate": 4.753107891855015e-06,
      "loss": 0.02,
      "num_tokens": 12092563.0,
      "reward": 0.8854166716337204,
      "reward_std": 0.22940894588828087,
      "rewards/curriculum_aware_reward_fn": 0.11197916697710752,
      "rewards/format_reward": 0.7734375,
      "step": 88
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 325.625,
      "epoch": 1.504201680672269,
      "grad_norm": 0.6008861660957336,
      "kl": 0.14013671875,
      "learning_rate": 4.746428256064375e-06,
      "loss": 0.0021,
      "num_tokens": 12195803.0,
      "reward": 1.261979192495346,
      "reward_std": 0.17762075550854206,
      "rewards/curriculum_aware_reward_fn": 0.2697916701436043,
      "rewards/format_reward": 0.9921875,
      "step": 89
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 348.2421875,
      "epoch": 1.5210084033613445,
      "grad_norm": 0.5485793948173523,
      "kl": 0.13720703125,
      "learning_rate": 4.7396648541425534e-06,
      "loss": 0.0053,
      "num_tokens": 12314866.0,
      "reward": 1.2442708611488342,
      "reward_std": 0.21353545226156712,
      "rewards/curriculum_aware_reward_fn": 0.24427084252238274,
      "rewards/format_reward": 1.0,
      "step": 90
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 519.265625,
      "epoch": 1.53781512605042,
      "grad_norm": 0.4276430010795593,
      "kl": 0.11962890625,
      "learning_rate": 4.732817969868348e-06,
      "loss": 0.0315,
      "num_tokens": 12463604.0,
      "reward": 0.895833358168602,
      "reward_std": 0.09582467563450336,
      "rewards/curriculum_aware_reward_fn": 0.0833333358168602,
      "rewards/format_reward": 0.8125,
      "step": 91
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 334.859375,
      "epoch": 1.5546218487394958,
      "grad_norm": 0.5961228013038635,
      "kl": 0.1279296875,
      "learning_rate": 4.7258878905233095e-06,
      "loss": 0.0697,
      "num_tokens": 12583698.0,
      "reward": 1.2239583432674408,
      "reward_std": 0.18167817778885365,
      "rewards/curriculum_aware_reward_fn": 0.2317708358168602,
      "rewards/format_reward": 0.9921875,
      "step": 92
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 363.859375,
      "epoch": 1.5714285714285714,
      "grad_norm": 0.7697988152503967,
      "kl": 0.1495361328125,
      "learning_rate": 4.718874906879688e-06,
      "loss": 0.1313,
      "num_tokens": 12705640.0,
      "reward": 1.123437523841858,
      "reward_std": 0.29410218447446823,
      "rewards/curriculum_aware_reward_fn": 0.17812500521540642,
      "rewards/format_reward": 0.9453125,
      "step": 93
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 297.1328125,
      "epoch": 1.5882352941176472,
      "grad_norm": 0.5211566686630249,
      "kl": 0.133056640625,
      "learning_rate": 4.711779313188231e-06,
      "loss": 0.04,
      "num_tokens": 12824305.0,
      "reward": 1.1119791865348816,
      "reward_std": 0.18469560518860817,
      "rewards/curriculum_aware_reward_fn": 0.1119791679084301,
      "rewards/format_reward": 1.0,
      "step": 94
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 253.859375,
      "epoch": 1.6050420168067228,
      "grad_norm": 0.6686471104621887,
      "kl": 0.1435546875,
      "learning_rate": 4.70460140716584e-06,
      "loss": -0.0138,
      "num_tokens": 12918559.0,
      "reward": 1.1968750357627869,
      "reward_std": 0.1724256370216608,
      "rewards/curriculum_aware_reward_fn": 0.20468750596046448,
      "rewards/format_reward": 0.9921875,
      "step": 95
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 575.90625,
      "epoch": 1.6218487394957983,
      "grad_norm": 0.3436340093612671,
      "kl": 0.160888671875,
      "learning_rate": 4.697341489983076e-06,
      "loss": 0.0223,
      "num_tokens": 13076699.0,
      "reward": 0.8567708432674408,
      "reward_std": 0.08664888702332973,
      "rewards/curriculum_aware_reward_fn": 0.10677083395421505,
      "rewards/format_reward": 0.75,
      "step": 96
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 301.9140625,
      "epoch": 1.638655462184874,
      "grad_norm": 1.0377366542816162,
      "kl": 0.162353515625,
      "learning_rate": 4.6899998662515215e-06,
      "loss": 0.0906,
      "num_tokens": 13192776.0,
      "reward": 1.1197916716337204,
      "reward_std": 0.12685893662273884,
      "rewards/curriculum_aware_reward_fn": 0.13541666674427688,
      "rewards/format_reward": 0.984375,
      "step": 97
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 331.28125,
      "epoch": 1.6554621848739495,
      "grad_norm": 0.477889746427536,
      "kl": 0.151123046875,
      "learning_rate": 4.682576844011007e-06,
      "loss": 0.0147,
      "num_tokens": 13309884.0,
      "reward": 1.2942708730697632,
      "reward_std": 0.10486710164695978,
      "rewards/curriculum_aware_reward_fn": 0.3567708432674408,
      "rewards/format_reward": 0.9375,
      "step": 98
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 418.96875,
      "epoch": 1.6722689075630253,
      "grad_norm": 1.2051795721054077,
      "kl": 0.1630859375,
      "learning_rate": 4.675072734716678e-06,
      "loss": 0.0986,
      "num_tokens": 13443272.0,
      "reward": 1.0937500298023224,
      "reward_std": 0.1639669369906187,
      "rewards/curriculum_aware_reward_fn": 0.1796875111758709,
      "rewards/format_reward": 0.9140625,
      "step": 99
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 257.484375,
      "epoch": 1.6890756302521008,
      "grad_norm": 0.6367622017860413,
      "kl": 0.157958984375,
      "learning_rate": 4.667487853225931e-06,
      "loss": 0.0274,
      "num_tokens": 13546814.0,
      "reward": 1.3072916865348816,
      "reward_std": 0.1563644390553236,
      "rewards/curriculum_aware_reward_fn": 0.3307291641831398,
      "rewards/format_reward": 0.9765625,
      "step": 100
    },
    {
      "epoch": 1.6890756302521008,
      "step": 100,
      "total_flos": 0.0,
      "train_loss": 0.0,
      "train_runtime": 1.1082,
      "train_samples_per_second": 1712.724,
      "train_steps_per_second": 52.338
    }
  ],
  "logging_steps": 1,
  "max_steps": 58,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "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": 8,
  "trial_name": null,
  "trial_params": null
}