{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "clip_ratio": 0.0,
      "completion_length": 497.53125,
      "epoch": 0.02,
      "grad_norm": 0.3983331024646759,
      "kl": 0.0,
      "learning_rate": 2e-07,
      "loss": 0.0772,
      "num_tokens": 228808.0,
      "reward": 1.737890601158142,
      "reward_std": 0.7095816880464554,
      "rewards/warning_cot_reward": 1.737890601158142,
      "step": 1
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 613.80078125,
      "epoch": 0.04,
      "grad_norm": 0.3328753113746643,
      "kl": 0.0,
      "learning_rate": 4e-07,
      "loss": -0.0489,
      "num_tokens": 482421.0,
      "reward": 1.605859398841858,
      "reward_std": 0.93210569024086,
      "rewards/warning_cot_reward": 1.605859398841858,
      "step": 2
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 579.875,
      "epoch": 0.06,
      "grad_norm": 0.3494884967803955,
      "kl": 0.0007886886596679688,
      "learning_rate": 6e-07,
      "loss": 0.0492,
      "num_tokens": 719573.0,
      "reward": 1.3273437321186066,
      "reward_std": 1.1463946402072906,
      "rewards/warning_cot_reward": 1.3273437321186066,
      "step": 3
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 579.0625,
      "epoch": 0.08,
      "grad_norm": 0.39709338545799255,
      "kl": 0.0008220672607421875,
      "learning_rate": 8e-07,
      "loss": -0.0238,
      "num_tokens": 966549.0,
      "reward": 1.1554687172174454,
      "reward_std": 1.3593965470790863,
      "rewards/warning_cot_reward": 1.1554687172174454,
      "step": 4
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 635.0078125,
      "epoch": 0.1,
      "grad_norm": 0.3334640860557556,
      "kl": 0.0007543563842773438,
      "learning_rate": 1e-06,
      "loss": 0.0674,
      "num_tokens": 1224887.0,
      "reward": 1.3519530892372131,
      "reward_std": 1.1553629487752914,
      "rewards/warning_cot_reward": 1.3519530892372131,
      "step": 5
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 532.6875,
      "epoch": 0.12,
      "grad_norm": 0.3795444667339325,
      "kl": 0.0008840560913085938,
      "learning_rate": 9.989038226169207e-07,
      "loss": -0.0175,
      "num_tokens": 1459143.0,
      "reward": 1.3195312470197678,
      "reward_std": 1.2002772986888885,
      "rewards/warning_cot_reward": 1.3195312470197678,
      "step": 6
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 524.8359375,
      "epoch": 0.14,
      "grad_norm": 0.39956167340278625,
      "kl": 0.000896453857421875,
      "learning_rate": 9.956206309337066e-07,
      "loss": 0.0483,
      "num_tokens": 1690813.0,
      "reward": 0.9855468720197678,
      "reward_std": 1.2580644488334656,
      "rewards/warning_cot_reward": 0.9855468720197678,
      "step": 7
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 544.5390625,
      "epoch": 0.16,
      "grad_norm": 0.3839609622955322,
      "kl": 0.0008993148803710938,
      "learning_rate": 9.901664203302124e-07,
      "loss": -0.0353,
      "num_tokens": 1932679.0,
      "reward": 1.0003906339406967,
      "reward_std": 1.3724247217178345,
      "rewards/warning_cot_reward": 1.0003906339406967,
      "step": 8
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 645.4453125,
      "epoch": 0.18,
      "grad_norm": 0.3397459089756012,
      "kl": 0.0007791519165039062,
      "learning_rate": 9.825677631722435e-07,
      "loss": -0.1073,
      "num_tokens": 2193049.0,
      "reward": 1.3714843690395355,
      "reward_std": 0.9502582252025604,
      "rewards/warning_cot_reward": 1.3714843690395355,
      "step": 9
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 547.05859375,
      "epoch": 0.2,
      "grad_norm": 0.4041031002998352,
      "kl": 0.001007080078125,
      "learning_rate": 9.728616793536587e-07,
      "loss": -0.0211,
      "num_tokens": 2444840.0,
      "reward": 1.3960936814546585,
      "reward_std": 1.0811447501182556,
      "rewards/warning_cot_reward": 1.3960936814546585,
      "step": 10
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 632.29296875,
      "epoch": 0.22,
      "grad_norm": 0.3459642827510834,
      "kl": 0.0008764266967773438,
      "learning_rate": 9.610954559391704e-07,
      "loss": -0.0344,
      "num_tokens": 2699107.0,
      "reward": 1.5503905415534973,
      "reward_std": 1.1313166320323944,
      "rewards/warning_cot_reward": 1.5503905415534973,
      "step": 11
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 569.53515625,
      "epoch": 0.24,
      "grad_norm": 0.36894500255584717,
      "kl": 0.00095367431640625,
      "learning_rate": 9.473264167865171e-07,
      "loss": 0.0816,
      "num_tokens": 2951516.0,
      "reward": 1.454687476158142,
      "reward_std": 0.9914004057645798,
      "rewards/warning_cot_reward": 1.454687476158142,
      "step": 12
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 557.0859375,
      "epoch": 0.26,
      "grad_norm": 0.38127055764198303,
      "kl": 0.00091552734375,
      "learning_rate": 9.316216432703916e-07,
      "loss": -0.043,
      "num_tokens": 3186146.0,
      "reward": 1.4449218809604645,
      "reward_std": 1.0739844143390656,
      "rewards/warning_cot_reward": 1.4449218809604645,
      "step": 13
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 555.015625,
      "epoch": 0.28,
      "grad_norm": 0.4119281768798828,
      "kl": 0.0010194778442382812,
      "learning_rate": 9.140576474687263e-07,
      "loss": 0.0125,
      "num_tokens": 3427702.0,
      "reward": 1.466796875,
      "reward_std": 1.0849339067935944,
      "rewards/warning_cot_reward": 1.466796875,
      "step": 14
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 560.5390625,
      "epoch": 0.3,
      "grad_norm": 0.36460286378860474,
      "kl": 0.0010156631469726562,
      "learning_rate": 8.9471999940354e-07,
      "loss": -0.0946,
      "num_tokens": 3669552.0,
      "reward": 1.4507812559604645,
      "reward_std": 1.213493824005127,
      "rewards/warning_cot_reward": 1.4507812559604645,
      "step": 15
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 552.671875,
      "epoch": 0.32,
      "grad_norm": 0.39756470918655396,
      "kl": 0.0012159347534179688,
      "learning_rate": 8.737029101523929e-07,
      "loss": 0.1041,
      "num_tokens": 3906716.0,
      "reward": 1.6800780892372131,
      "reward_std": 0.9159540981054306,
      "rewards/warning_cot_reward": 1.6800780892372131,
      "step": 16
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 565.70703125,
      "epoch": 0.34,
      "grad_norm": 0.3725472092628479,
      "kl": 0.001255035400390625,
      "learning_rate": 8.511087728614862e-07,
      "loss": 0.0308,
      "num_tokens": 4151057.0,
      "reward": 1.5542968809604645,
      "reward_std": 1.088392198085785,
      "rewards/warning_cot_reward": 1.5542968809604645,
      "step": 17
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 581.0234375,
      "epoch": 0.36,
      "grad_norm": 0.36802971363067627,
      "kl": 0.0012559890747070312,
      "learning_rate": 8.270476638965461e-07,
      "loss": -0.0196,
      "num_tokens": 4396711.0,
      "reward": 1.507031261920929,
      "reward_std": 1.076774537563324,
      "rewards/warning_cot_reward": 1.507031261920929,
      "step": 18
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 576.203125,
      "epoch": 0.38,
      "grad_norm": 0.3900078535079956,
      "kl": 0.0012340545654296875,
      "learning_rate": 8.01636806561836e-07,
      "loss": 0.0322,
      "num_tokens": 4641115.0,
      "reward": 1.468359351158142,
      "reward_std": 0.9576149135828018,
      "rewards/warning_cot_reward": 1.468359351158142,
      "step": 19
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 509.41015625,
      "epoch": 0.4,
      "grad_norm": 0.40923792123794556,
      "kl": 0.0012531280517578125,
      "learning_rate": 7.75e-07,
      "loss": 0.0172,
      "num_tokens": 4872788.0,
      "reward": 1.548046886920929,
      "reward_std": 1.1000525951385498,
      "rewards/warning_cot_reward": 1.548046886920929,
      "step": 20
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 584.56640625,
      "epoch": 0.42,
      "grad_norm": 0.35544759035110474,
      "kl": 0.00128936767578125,
      "learning_rate": 7.472670160550848e-07,
      "loss": 0.0714,
      "num_tokens": 5117237.0,
      "reward": 1.1402343213558197,
      "reward_std": 1.1906223744153976,
      "rewards/warning_cot_reward": 1.1402343213558197,
      "step": 21
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 532.4375,
      "epoch": 0.44,
      "grad_norm": 0.3666287958621979,
      "kl": 0.00128936767578125,
      "learning_rate": 7.185729670371604e-07,
      "loss": -0.001,
      "num_tokens": 5346645.0,
      "reward": 1.501171886920929,
      "reward_std": 1.0229820162057877,
      "rewards/warning_cot_reward": 1.501171886920929,
      "step": 22
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 515.3828125,
      "epoch": 0.46,
      "grad_norm": 0.3824121057987213,
      "kl": 0.001613616943359375,
      "learning_rate": 6.890576474687263e-07,
      "loss": 0.0309,
      "num_tokens": 5577335.0,
      "reward": 1.1945312023162842,
      "reward_std": 1.1885981112718582,
      "rewards/warning_cot_reward": 1.1945312023162842,
      "step": 23
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 587.578125,
      "epoch": 0.48,
      "grad_norm": 0.37454530596733093,
      "kl": 0.001590728759765625,
      "learning_rate": 6.588648530198504e-07,
      "loss": -0.0059,
      "num_tokens": 5826923.0,
      "reward": 1.4167968332767487,
      "reward_std": 1.0897981077432632,
      "rewards/warning_cot_reward": 1.4167968332767487,
      "step": 24
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 501.8203125,
      "epoch": 0.5,
      "grad_norm": 0.4218956232070923,
      "kl": 0.0016937255859375,
      "learning_rate": 6.281416799501187e-07,
      "loss": -0.0434,
      "num_tokens": 6060285.0,
      "reward": 1.393750011920929,
      "reward_std": 1.1672577857971191,
      "rewards/warning_cot_reward": 1.393750011920929,
      "step": 25
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 548.58203125,
      "epoch": 0.52,
      "grad_norm": 0.36240002512931824,
      "kl": 0.0015087127685546875,
      "learning_rate": 5.97037808470444e-07,
      "loss": -0.0644,
      "num_tokens": 6289490.0,
      "reward": 1.391406238079071,
      "reward_std": 1.312122255563736,
      "rewards/warning_cot_reward": 1.391406238079071,
      "step": 26
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 518.28515625,
      "epoch": 0.54,
      "grad_norm": 0.3815212845802307,
      "kl": 0.0014057159423828125,
      "learning_rate": 5.657047735161255e-07,
      "loss": -0.0122,
      "num_tokens": 6524891.0,
      "reward": 1.2050780951976776,
      "reward_std": 1.2014616578817368,
      "rewards/warning_cot_reward": 1.2050780951976776,
      "step": 27
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 635.2578125,
      "epoch": 0.56,
      "grad_norm": 0.31691455841064453,
      "kl": 0.00139617919921875,
      "learning_rate": 5.342952264838747e-07,
      "loss": -0.1015,
      "num_tokens": 6776045.0,
      "reward": 1.519140601158142,
      "reward_std": 1.0139589607715607,
      "rewards/warning_cot_reward": 1.519140601158142,
      "step": 28
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 619.26953125,
      "epoch": 0.58,
      "grad_norm": 0.3376880884170532,
      "kl": 0.0014934539794921875,
      "learning_rate": 5.02962191529556e-07,
      "loss": -0.0553,
      "num_tokens": 7028770.0,
      "reward": 1.3453125059604645,
      "reward_std": 1.2301103472709656,
      "rewards/warning_cot_reward": 1.3453125059604645,
      "step": 29
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 665.69140625,
      "epoch": 0.6,
      "grad_norm": 0.3069409430027008,
      "kl": 0.0014553070068359375,
      "learning_rate": 4.7185832004988133e-07,
      "loss": 0.1318,
      "num_tokens": 7293779.0,
      "reward": 1.3515624701976776,
      "reward_std": 1.2059955894947052,
      "rewards/warning_cot_reward": 1.3515624701976776,
      "step": 30
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 530.3828125,
      "epoch": 0.62,
      "grad_norm": 0.37838348746299744,
      "kl": 0.0017681121826171875,
      "learning_rate": 4.4113514698014953e-07,
      "loss": 0.0002,
      "num_tokens": 7521813.0,
      "reward": 1.4878906309604645,
      "reward_std": 0.9572159051895142,
      "rewards/warning_cot_reward": 1.4878906309604645,
      "step": 31
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 573.53515625,
      "epoch": 0.64,
      "grad_norm": 0.33926212787628174,
      "kl": 0.0018672943115234375,
      "learning_rate": 4.1094235253127374e-07,
      "loss": -0.0254,
      "num_tokens": 7774382.0,
      "reward": 1.5277343541383743,
      "reward_std": 0.7851940989494324,
      "rewards/warning_cot_reward": 1.5277343541383743,
      "step": 32
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 547.49609375,
      "epoch": 0.66,
      "grad_norm": 0.38276809453964233,
      "kl": 0.001667022705078125,
      "learning_rate": 3.8142703296283953e-07,
      "loss": -0.0008,
      "num_tokens": 8006125.0,
      "reward": 1.448046863079071,
      "reward_std": 1.0810334235429764,
      "rewards/warning_cot_reward": 1.448046863079071,
      "step": 33
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 621.3828125,
      "epoch": 0.68,
      "grad_norm": 0.3453586995601654,
      "kl": 0.0017833709716796875,
      "learning_rate": 3.5273298394491515e-07,
      "loss": -0.0065,
      "num_tokens": 8256127.0,
      "reward": 1.607421875,
      "reward_std": 1.0255936235189438,
      "rewards/warning_cot_reward": 1.607421875,
      "step": 34
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 583.40234375,
      "epoch": 0.7,
      "grad_norm": 0.3764957785606384,
      "kl": 0.00176239013671875,
      "learning_rate": 3.250000000000001e-07,
      "loss": 0.0254,
      "num_tokens": 8499270.0,
      "reward": 1.3753906041383743,
      "reward_std": 1.0650920569896698,
      "rewards/warning_cot_reward": 1.3753906041383743,
      "step": 35
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 545.67578125,
      "epoch": 0.72,
      "grad_norm": 0.37808629870414734,
      "kl": 0.001529693603515625,
      "learning_rate": 2.9836319343816397e-07,
      "loss": -0.1193,
      "num_tokens": 8720291.0,
      "reward": 1.5816406607627869,
      "reward_std": 0.9250695407390594,
      "rewards/warning_cot_reward": 1.5816406607627869,
      "step": 36
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 523.50390625,
      "epoch": 0.74,
      "grad_norm": 0.3750839829444885,
      "kl": 0.0019397735595703125,
      "learning_rate": 2.729523361034538e-07,
      "loss": 0.0956,
      "num_tokens": 8956036.0,
      "reward": 1.4640625417232513,
      "reward_std": 1.0201859176158905,
      "rewards/warning_cot_reward": 1.4640625417232513,
      "step": 37
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 577.0234375,
      "epoch": 0.76,
      "grad_norm": 0.3557916283607483,
      "kl": 0.0016345977783203125,
      "learning_rate": 2.488912271385139e-07,
      "loss": 0.0539,
      "num_tokens": 9194538.0,
      "reward": 1.5382812917232513,
      "reward_std": 0.9682637453079224,
      "rewards/warning_cot_reward": 1.5382812917232513,
      "step": 38
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 561.96484375,
      "epoch": 0.78,
      "grad_norm": 0.3804481625556946,
      "kl": 0.0017147064208984375,
      "learning_rate": 2.2629708984760706e-07,
      "loss": 0.0415,
      "num_tokens": 9435153.0,
      "reward": 1.300390586256981,
      "reward_std": 1.2824777960777283,
      "rewards/warning_cot_reward": 1.300390586256981,
      "step": 39
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 493.734375,
      "epoch": 0.8,
      "grad_norm": 0.4389341175556183,
      "kl": 0.0018177032470703125,
      "learning_rate": 2.0528000059645995e-07,
      "loss": 0.0064,
      "num_tokens": 9677949.0,
      "reward": 1.3738280832767487,
      "reward_std": 1.304576188325882,
      "rewards/warning_cot_reward": 1.3738280832767487,
      "step": 40
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 564.50390625,
      "epoch": 0.82,
      "grad_norm": 0.33817851543426514,
      "kl": 0.0019779205322265625,
      "learning_rate": 1.8594235253127372e-07,
      "loss": -0.0186,
      "num_tokens": 9931214.0,
      "reward": 1.306249976158142,
      "reward_std": 1.1715005040168762,
      "rewards/warning_cot_reward": 1.306249976158142,
      "step": 41
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 619.93359375,
      "epoch": 0.84,
      "grad_norm": 0.40954455733299255,
      "kl": 0.0017337799072265625,
      "learning_rate": 1.6837835672960831e-07,
      "loss": 0.0427,
      "num_tokens": 10187485.0,
      "reward": 1.4433593600988388,
      "reward_std": 1.0932807922363281,
      "rewards/warning_cot_reward": 1.4433593600988388,
      "step": 42
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 595.421875,
      "epoch": 0.86,
      "grad_norm": 0.3559175729751587,
      "kl": 0.0014438629150390625,
      "learning_rate": 1.5267358321348285e-07,
      "loss": 0.0327,
      "num_tokens": 10435529.0,
      "reward": 1.0273437201976776,
      "reward_std": 1.2055754661560059,
      "rewards/warning_cot_reward": 1.0273437201976776,
      "step": 43
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 540.23046875,
      "epoch": 0.88,
      "grad_norm": 0.4031689167022705,
      "kl": 0.001720428466796875,
      "learning_rate": 1.3890454406082956e-07,
      "loss": -0.0089,
      "num_tokens": 10679172.0,
      "reward": 1.3703124225139618,
      "reward_std": 1.09530109167099,
      "rewards/warning_cot_reward": 1.3703124225139618,
      "step": 44
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 534.99609375,
      "epoch": 0.9,
      "grad_norm": 0.3752831518650055,
      "kl": 0.001987457275390625,
      "learning_rate": 1.2713832064634125e-07,
      "loss": -0.0754,
      "num_tokens": 10912243.0,
      "reward": 1.3703124821186066,
      "reward_std": 0.9851697236299515,
      "rewards/warning_cot_reward": 1.3703124821186066,
      "step": 45
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 608.8984375,
      "epoch": 0.92,
      "grad_norm": 0.32730016112327576,
      "kl": 0.0017032623291015625,
      "learning_rate": 1.1743223682775649e-07,
      "loss": -0.0539,
      "num_tokens": 11155417.0,
      "reward": 1.4210937321186066,
      "reward_std": 1.0002857744693756,
      "rewards/warning_cot_reward": 1.4210937321186066,
      "step": 46
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 570.6484375,
      "epoch": 0.94,
      "grad_norm": 0.36017531156539917,
      "kl": 0.001678466796875,
      "learning_rate": 1.0983357966978745e-07,
      "loss": -0.0264,
      "num_tokens": 11399151.0,
      "reward": 1.1734374910593033,
      "reward_std": 1.2424213588237762,
      "rewards/warning_cot_reward": 1.1734374910593033,
      "step": 47
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 585.82421875,
      "epoch": 0.96,
      "grad_norm": 0.37404605746269226,
      "kl": 0.001621246337890625,
      "learning_rate": 1.0437936906629334e-07,
      "loss": 0.0319,
      "num_tokens": 11643970.0,
      "reward": 1.5425781309604645,
      "reward_std": 1.0051147043704987,
      "rewards/warning_cot_reward": 1.5425781309604645,
      "step": 48
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 540.48046875,
      "epoch": 0.98,
      "grad_norm": 0.42852458357810974,
      "kl": 0.001628875732421875,
      "learning_rate": 1.0109617738307911e-07,
      "loss": 0.0334,
      "num_tokens": 11891341.0,
      "reward": 1.5019530951976776,
      "reward_std": 1.0244712382555008,
      "rewards/warning_cot_reward": 1.5019530951976776,
      "step": 49
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 526.125,
      "epoch": 1.0,
      "grad_norm": 0.3930824100971222,
      "kl": 0.00223541259765625,
      "learning_rate": 1e-07,
      "loss": 0.095,
      "num_tokens": 12129961.0,
      "reward": 1.430468738079071,
      "reward_std": 0.8986857831478119,
      "rewards/warning_cot_reward": 1.430468738079071,
      "step": 50
    },
    {
      "epoch": 1.0,
      "step": 50,
      "total_flos": 0.0,
      "train_loss": 0.002978094220161438,
      "train_runtime": 17358.3669,
      "train_samples_per_second": 0.046,
      "train_steps_per_second": 0.003
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}