{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9485384932070811,
  "eval_steps": 500,
  "global_step": 72,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013174145738987238,
      "grad_norm": 0.48070791363716125,
      "learning_rate": 6.25e-08,
      "logits/chosen": 10.32492733001709,
      "logits/rejected": 10.282785415649414,
      "logps/chosen": -176.09544372558594,
      "logps/ref_chosen": -176.09544372558594,
      "logps/ref_rejected": -181.75552368164062,
      "logps/rejected": -181.75552368164062,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.026348291477974475,
      "grad_norm": 0.4185059070587158,
      "learning_rate": 1.25e-07,
      "logits/chosen": 10.530074119567871,
      "logits/rejected": 10.672085762023926,
      "logps/chosen": -173.2084503173828,
      "logps/ref_chosen": -173.2084503173828,
      "logps/ref_rejected": -187.02206420898438,
      "logps/rejected": -187.02206420898438,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 2
    },
    {
      "epoch": 0.03952243721696171,
      "grad_norm": 0.3848375082015991,
      "learning_rate": 1.875e-07,
      "logits/chosen": 10.340475082397461,
      "logits/rejected": 10.486526489257812,
      "logps/chosen": -169.6623992919922,
      "logps/ref_chosen": -169.080810546875,
      "logps/ref_rejected": -182.52792358398438,
      "logps/rejected": -182.80642700195312,
      "loss": 0.6947,
      "rewards/accuracies": 0.3828125,
      "rewards/chosen": -0.005815833806991577,
      "rewards/margins": -0.0030306153930723667,
      "rewards/rejected": -0.002785218646749854,
      "step": 3
    },
    {
      "epoch": 0.05269658295594895,
      "grad_norm": 0.7261964678764343,
      "learning_rate": 2.5e-07,
      "logits/chosen": 10.3652925491333,
      "logits/rejected": 10.412069320678711,
      "logps/chosen": -177.03428649902344,
      "logps/ref_chosen": -176.78369140625,
      "logps/ref_rejected": -180.0931396484375,
      "logps/rejected": -180.21463012695312,
      "loss": 0.6938,
      "rewards/accuracies": 0.4765625,
      "rewards/chosen": -0.0025058696046471596,
      "rewards/margins": -0.0012909012148156762,
      "rewards/rejected": -0.0012149682734161615,
      "step": 4
    },
    {
      "epoch": 0.06587072869493618,
      "grad_norm": 0.3572319746017456,
      "learning_rate": 3.1249999999999997e-07,
      "logits/chosen": 10.757452011108398,
      "logits/rejected": 10.791389465332031,
      "logps/chosen": -169.12631225585938,
      "logps/ref_chosen": -168.522216796875,
      "logps/ref_rejected": -176.08982849121094,
      "logps/rejected": -176.59901428222656,
      "loss": 0.6936,
      "rewards/accuracies": 0.4609375,
      "rewards/chosen": -0.0060411859303712845,
      "rewards/margins": -0.0009493756806477904,
      "rewards/rejected": -0.0050918105989694595,
      "step": 5
    },
    {
      "epoch": 0.07904487443392343,
      "grad_norm": 0.4071093201637268,
      "learning_rate": 3.75e-07,
      "logits/chosen": 11.003137588500977,
      "logits/rejected": 11.056475639343262,
      "logps/chosen": -174.662353515625,
      "logps/ref_chosen": -174.5843048095703,
      "logps/ref_rejected": -181.65040588378906,
      "logps/rejected": -181.72401428222656,
      "loss": 0.6932,
      "rewards/accuracies": 0.5078125,
      "rewards/chosen": -0.0007804610067978501,
      "rewards/margins": -4.43047538283281e-05,
      "rewards/rejected": -0.0007361561874859035,
      "step": 6
    },
    {
      "epoch": 0.09221902017291066,
      "grad_norm": 0.7951124906539917,
      "learning_rate": 4.375e-07,
      "logits/chosen": 10.003807067871094,
      "logits/rejected": 10.067156791687012,
      "logps/chosen": -171.4049530029297,
      "logps/ref_chosen": -170.4031219482422,
      "logps/ref_rejected": -181.00917053222656,
      "logps/rejected": -181.8280792236328,
      "loss": 0.6941,
      "rewards/accuracies": 0.4453125,
      "rewards/chosen": -0.010018287226557732,
      "rewards/margins": -0.0018291514134034514,
      "rewards/rejected": -0.008189136162400246,
      "step": 7
    },
    {
      "epoch": 0.1053931659118979,
      "grad_norm": 0.5591660737991333,
      "learning_rate": 5e-07,
      "logits/chosen": 10.874868392944336,
      "logits/rejected": 10.79828929901123,
      "logps/chosen": -179.36700439453125,
      "logps/ref_chosen": -178.47369384765625,
      "logps/ref_rejected": -184.52243041992188,
      "logps/rejected": -185.44284057617188,
      "loss": 0.693,
      "rewards/accuracies": 0.5078125,
      "rewards/chosen": -0.008933190256357193,
      "rewards/margins": 0.0002710025873966515,
      "rewards/rejected": -0.009204192087054253,
      "step": 8
    },
    {
      "epoch": 0.11856731165088513,
      "grad_norm": 0.45744186639785767,
      "learning_rate": 4.997252228714278e-07,
      "logits/chosen": 10.472944259643555,
      "logits/rejected": 10.640350341796875,
      "logps/chosen": -175.36553955078125,
      "logps/ref_chosen": -174.38418579101562,
      "logps/ref_rejected": -182.0985565185547,
      "logps/rejected": -183.1609649658203,
      "loss": 0.6928,
      "rewards/accuracies": 0.5234375,
      "rewards/chosen": -0.009813489392399788,
      "rewards/margins": 0.0008107352769002318,
      "rewards/rejected": -0.010624224320054054,
      "step": 9
    },
    {
      "epoch": 0.13174145738987236,
      "grad_norm": 0.3784727156162262,
      "learning_rate": 4.989014955054745e-07,
      "logits/chosen": 10.471797943115234,
      "logits/rejected": 10.57437515258789,
      "logps/chosen": -173.78768920898438,
      "logps/ref_chosen": -172.48837280273438,
      "logps/ref_rejected": -179.625,
      "logps/rejected": -180.91595458984375,
      "loss": 0.6932,
      "rewards/accuracies": 0.4765625,
      "rewards/chosen": -0.012993087992072105,
      "rewards/margins": -8.335959864780307e-05,
      "rewards/rejected": -0.012909728102385998,
      "step": 10
    },
    {
      "epoch": 0.14491560312885962,
      "grad_norm": 0.4041476547718048,
      "learning_rate": 4.975306286336627e-07,
      "logits/chosen": 10.539186477661133,
      "logits/rejected": 10.477883338928223,
      "logps/chosen": -172.62416076660156,
      "logps/ref_chosen": -169.97216796875,
      "logps/ref_rejected": -180.00955200195312,
      "logps/rejected": -182.72525024414062,
      "loss": 0.6929,
      "rewards/accuracies": 0.546875,
      "rewards/chosen": -0.026519589126110077,
      "rewards/margins": 0.0006374535150825977,
      "rewards/rejected": -0.027157040312886238,
      "step": 11
    },
    {
      "epoch": 0.15808974886784685,
      "grad_norm": 0.5964677333831787,
      "learning_rate": 4.956156357188939e-07,
      "logits/chosen": 10.28010082244873,
      "logits/rejected": 10.401304244995117,
      "logps/chosen": -178.43714904785156,
      "logps/ref_chosen": -175.83639526367188,
      "logps/ref_rejected": -181.73045349121094,
      "logps/rejected": -184.20223999023438,
      "loss": 0.6938,
      "rewards/accuracies": 0.4375,
      "rewards/chosen": -0.026007818058133125,
      "rewards/margins": -0.0012897354317829013,
      "rewards/rejected": -0.024718083441257477,
      "step": 12
    },
    {
      "epoch": 0.17126389460683408,
      "grad_norm": 0.488361120223999,
      "learning_rate": 4.931607263312032e-07,
      "logits/chosen": 10.292243957519531,
      "logits/rejected": 10.386707305908203,
      "logps/chosen": -173.99058532714844,
      "logps/ref_chosen": -170.8806610107422,
      "logps/ref_rejected": -180.6468963623047,
      "logps/rejected": -184.01853942871094,
      "loss": 0.6919,
      "rewards/accuracies": 0.5234375,
      "rewards/chosen": -0.03109920769929886,
      "rewards/margins": 0.002617327030748129,
      "rewards/rejected": -0.033716537058353424,
      "step": 13
    },
    {
      "epoch": 0.1844380403458213,
      "grad_norm": 0.45636966824531555,
      "learning_rate": 4.9017129689421e-07,
      "logits/chosen": 10.729025840759277,
      "logits/rejected": 10.921786308288574,
      "logps/chosen": -174.65345764160156,
      "logps/ref_chosen": -171.15963745117188,
      "logps/ref_rejected": -180.73471069335938,
      "logps/rejected": -184.30807495117188,
      "loss": 0.6928,
      "rewards/accuracies": 0.515625,
      "rewards/chosen": -0.03493800014257431,
      "rewards/margins": 0.0007955244509503245,
      "rewards/rejected": -0.03573352098464966,
      "step": 14
    },
    {
      "epoch": 0.19761218608480857,
      "grad_norm": 0.3838670551776886,
      "learning_rate": 4.866539188226085e-07,
      "logits/chosen": 10.265353202819824,
      "logits/rejected": 10.378411293029785,
      "logps/chosen": -177.72991943359375,
      "logps/ref_chosen": -173.84222412109375,
      "logps/ref_rejected": -182.6996612548828,
      "logps/rejected": -186.89825439453125,
      "loss": 0.6916,
      "rewards/accuracies": 0.515625,
      "rewards/chosen": -0.03887684643268585,
      "rewards/margins": 0.003108714707195759,
      "rewards/rejected": -0.04198555648326874,
      "step": 15
    },
    {
      "epoch": 0.2107863318237958,
      "grad_norm": 0.3698700964450836,
      "learning_rate": 4.826163240767716e-07,
      "logits/chosen": 10.751184463500977,
      "logits/rejected": 10.945128440856934,
      "logps/chosen": -181.60301208496094,
      "logps/ref_chosen": -178.638671875,
      "logps/ref_rejected": -185.8243408203125,
      "logps/rejected": -188.93057250976562,
      "loss": 0.6925,
      "rewards/accuracies": 0.5234375,
      "rewards/chosen": -0.029643364250659943,
      "rewards/margins": 0.0014189946232363582,
      "rewards/rejected": -0.03106236271560192,
      "step": 16
    },
    {
      "epoch": 0.22396047756278303,
      "grad_norm": 0.5419145822525024,
      "learning_rate": 4.780673881662242e-07,
      "logits/chosen": 10.279337882995605,
      "logits/rejected": 10.265542984008789,
      "logps/chosen": -176.72821044921875,
      "logps/ref_chosen": -172.87332153320312,
      "logps/ref_rejected": -177.30355834960938,
      "logps/rejected": -181.23831176757812,
      "loss": 0.6928,
      "rewards/accuracies": 0.484375,
      "rewards/chosen": -0.038549020886421204,
      "rewards/margins": 0.0007985997945070267,
      "rewards/rejected": -0.03934762626886368,
      "step": 17
    },
    {
      "epoch": 0.23713462330177026,
      "grad_norm": 0.5288915038108826,
      "learning_rate": 4.730171106393466e-07,
      "logits/chosen": 10.508716583251953,
      "logits/rejected": 10.601346969604492,
      "logps/chosen": -176.69735717773438,
      "logps/ref_chosen": -172.82644653320312,
      "logps/ref_rejected": -180.93768310546875,
      "logps/rejected": -184.82861328125,
      "loss": 0.6931,
      "rewards/accuracies": 0.5234375,
      "rewards/chosen": -0.038708824664354324,
      "rewards/margins": 0.00020039017545059323,
      "rewards/rejected": -0.03890921175479889,
      "step": 18
    },
    {
      "epoch": 0.2503087690407575,
      "grad_norm": 0.45863935351371765,
      "learning_rate": 4.6747659310219757e-07,
      "logits/chosen": 10.509140014648438,
      "logits/rejected": 10.403264999389648,
      "logps/chosen": -183.62411499023438,
      "logps/ref_chosen": -179.5069122314453,
      "logps/ref_rejected": -185.01487731933594,
      "logps/rejected": -189.2952880859375,
      "loss": 0.6924,
      "rewards/accuracies": 0.5078125,
      "rewards/chosen": -0.041171781718730927,
      "rewards/margins": 0.0016320659779012203,
      "rewards/rejected": -0.04280385002493858,
      "step": 19
    },
    {
      "epoch": 0.2634829147797447,
      "grad_norm": 0.6024115085601807,
      "learning_rate": 4.6145801481477433e-07,
      "logits/chosen": 10.452649116516113,
      "logits/rejected": 10.525249481201172,
      "logps/chosen": -174.3675994873047,
      "logps/ref_chosen": -170.23623657226562,
      "logps/ref_rejected": -177.55618286132812,
      "logps/rejected": -181.85946655273438,
      "loss": 0.6923,
      "rewards/accuracies": 0.5078125,
      "rewards/chosen": -0.04131368175148964,
      "rewards/margins": 0.0017191548831760883,
      "rewards/rejected": -0.04303283616900444,
      "step": 20
    },
    {
      "epoch": 0.276657060518732,
      "grad_norm": 0.4595341384410858,
      "learning_rate": 4.549746059183561e-07,
      "logits/chosen": 10.422194480895996,
      "logits/rejected": 10.483356475830078,
      "logps/chosen": -180.44906616210938,
      "logps/ref_chosen": -176.3700408935547,
      "logps/ref_rejected": -182.80032348632812,
      "logps/rejected": -187.17276000976562,
      "loss": 0.6917,
      "rewards/accuracies": 0.5703125,
      "rewards/chosen": -0.04079030081629753,
      "rewards/margins": 0.0029342519119381905,
      "rewards/rejected": -0.04372455179691315,
      "step": 21
    },
    {
      "epoch": 0.28983120625771924,
      "grad_norm": 0.3111652731895447,
      "learning_rate": 4.480406183527823e-07,
      "logits/chosen": 10.481276512145996,
      "logits/rejected": 10.559721946716309,
      "logps/chosen": -177.63865661621094,
      "logps/ref_chosen": -173.29742431640625,
      "logps/ref_rejected": -177.54916381835938,
      "logps/rejected": -182.2364044189453,
      "loss": 0.6915,
      "rewards/accuracies": 0.6015625,
      "rewards/chosen": -0.043412309139966965,
      "rewards/margins": 0.003460067557170987,
      "rewards/rejected": -0.04687237739562988,
      "step": 22
    },
    {
      "epoch": 0.3030053519967065,
      "grad_norm": 0.520114541053772,
      "learning_rate": 4.4067129452759546e-07,
      "logits/chosen": 10.153634071350098,
      "logits/rejected": 10.433453559875488,
      "logps/chosen": -174.9644012451172,
      "logps/ref_chosen": -170.41177368164062,
      "logps/ref_rejected": -182.7073974609375,
      "logps/rejected": -187.5763397216797,
      "loss": 0.6916,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": -0.04552610218524933,
      "rewards/margins": 0.0031630881130695343,
      "rewards/rejected": -0.04868919029831886,
      "step": 23
    },
    {
      "epoch": 0.3161794977356937,
      "grad_norm": 0.38157743215560913,
      "learning_rate": 4.3288283381591725e-07,
      "logits/chosen": 10.212328910827637,
      "logits/rejected": 10.149028778076172,
      "logps/chosen": -178.75759887695312,
      "logps/ref_chosen": -174.15003967285156,
      "logps/ref_rejected": -181.65594482421875,
      "logps/rejected": -186.58934020996094,
      "loss": 0.6916,
      "rewards/accuracies": 0.5703125,
      "rewards/chosen": -0.046075694262981415,
      "rewards/margins": 0.003258442971855402,
      "rewards/rejected": -0.04933413863182068,
      "step": 24
    },
    {
      "epoch": 0.32935364347468093,
      "grad_norm": 0.5030648112297058,
      "learning_rate": 4.246923569447104e-07,
      "logits/chosen": 10.425580978393555,
      "logits/rejected": 10.567748069763184,
      "logps/chosen": -181.23281860351562,
      "logps/ref_chosen": -177.0232391357422,
      "logps/ref_rejected": -184.0133056640625,
      "logps/rejected": -188.3357696533203,
      "loss": 0.6926,
      "rewards/accuracies": 0.5234375,
      "rewards/chosen": -0.04209586977958679,
      "rewards/margins": 0.0011287340894341469,
      "rewards/rejected": -0.04322460666298866,
      "step": 25
    },
    {
      "epoch": 0.34252778921366817,
      "grad_norm": 0.3347052335739136,
      "learning_rate": 4.161178683597054e-07,
      "logits/chosen": 10.395452499389648,
      "logits/rejected": 10.5776948928833,
      "logps/chosen": -177.6590576171875,
      "logps/ref_chosen": -172.2715606689453,
      "logps/ref_rejected": -180.46673583984375,
      "logps/rejected": -186.09349060058594,
      "loss": 0.692,
      "rewards/accuracies": 0.5703125,
      "rewards/chosen": -0.05387478694319725,
      "rewards/margins": 0.002392976311966777,
      "rewards/rejected": -0.056267764419317245,
      "step": 26
    },
    {
      "epoch": 0.3557019349526554,
      "grad_norm": 0.40187934041023254,
      "learning_rate": 4.0717821664772124e-07,
      "logits/chosen": 10.416847229003906,
      "logits/rejected": 10.693917274475098,
      "logps/chosen": -180.66729736328125,
      "logps/ref_chosen": -174.87091064453125,
      "logps/ref_rejected": -183.6770477294922,
      "logps/rejected": -189.53399658203125,
      "loss": 0.6929,
      "rewards/accuracies": 0.4921875,
      "rewards/chosen": -0.057963769882917404,
      "rewards/margins": 0.0006057576974853873,
      "rewards/rejected": -0.0585695244371891,
      "step": 27
    },
    {
      "epoch": 0.3688760806916426,
      "grad_norm": 0.537835419178009,
      "learning_rate": 3.978930531033806e-07,
      "logits/chosen": 10.315240859985352,
      "logits/rejected": 10.52540111541748,
      "logps/chosen": -178.289794921875,
      "logps/ref_chosen": -172.75225830078125,
      "logps/ref_rejected": -180.3443145751953,
      "logps/rejected": -186.29811096191406,
      "loss": 0.6911,
      "rewards/accuracies": 0.578125,
      "rewards/chosen": -0.05537542328238487,
      "rewards/margins": 0.004162484314292669,
      "rewards/rejected": -0.05953790992498398,
      "step": 28
    },
    {
      "epoch": 0.3820502264306299,
      "grad_norm": 0.9168035984039307,
      "learning_rate": 3.882827885312998e-07,
      "logits/chosen": 10.197809219360352,
      "logits/rejected": 10.199935913085938,
      "logps/chosen": -181.69606018066406,
      "logps/ref_chosen": -176.17613220214844,
      "logps/ref_rejected": -180.6341552734375,
      "logps/rejected": -186.46124267578125,
      "loss": 0.6917,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": -0.05519918352365494,
      "rewards/margins": 0.0030717107001692057,
      "rewards/rejected": -0.0582708939909935,
      "step": 29
    },
    {
      "epoch": 0.39522437216961714,
      "grad_norm": 0.3577282428741455,
      "learning_rate": 3.7836854837871044e-07,
      "logits/chosen": 10.497368812561035,
      "logits/rejected": 10.725122451782227,
      "logps/chosen": -184.75241088867188,
      "logps/ref_chosen": -178.8612060546875,
      "logps/ref_rejected": -187.1546173095703,
      "logps/rejected": -193.5741424560547,
      "loss": 0.6906,
      "rewards/accuracies": 0.5859375,
      "rewards/chosen": -0.058911994099617004,
      "rewards/margins": 0.0052833897061645985,
      "rewards/rejected": -0.06419539451599121,
      "step": 30
    },
    {
      "epoch": 0.4083985179086044,
      "grad_norm": 0.46136385202407837,
      "learning_rate": 3.681721262971413e-07,
      "logits/chosen": 10.34453010559082,
      "logits/rejected": 10.35668659210205,
      "logps/chosen": -178.43930053710938,
      "logps/ref_chosen": -172.60848999023438,
      "logps/ref_rejected": -179.45013427734375,
      "logps/rejected": -185.967529296875,
      "loss": 0.6898,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": -0.0583079531788826,
      "rewards/margins": 0.006865999195724726,
      "rewards/rejected": -0.06517395377159119,
      "step": 31
    },
    {
      "epoch": 0.4215726636475916,
      "grad_norm": 0.3592880368232727,
      "learning_rate": 3.577159362352426e-07,
      "logits/chosen": 10.357152938842773,
      "logits/rejected": 10.40371322631836,
      "logps/chosen": -181.8780975341797,
      "logps/ref_chosen": -175.29119873046875,
      "logps/ref_rejected": -182.2250213623047,
      "logps/rejected": -189.01063537597656,
      "loss": 0.6923,
      "rewards/accuracies": 0.5390625,
      "rewards/chosen": -0.06586895883083344,
      "rewards/margins": 0.001987436320632696,
      "rewards/rejected": -0.06785639375448227,
      "step": 32
    },
    {
      "epoch": 0.43474680938657884,
      "grad_norm": 0.4338357746601105,
      "learning_rate": 3.470229631680624e-07,
      "logits/chosen": 10.255874633789062,
      "logits/rejected": 10.296948432922363,
      "logps/chosen": -183.95484924316406,
      "logps/ref_chosen": -177.42674255371094,
      "logps/ref_rejected": -181.18801879882812,
      "logps/rejected": -188.07952880859375,
      "loss": 0.6914,
      "rewards/accuracies": 0.5859375,
      "rewards/chosen": -0.065280981361866,
      "rewards/margins": 0.003634275868535042,
      "rewards/rejected": -0.06891525536775589,
      "step": 33
    },
    {
      "epoch": 0.44792095512556607,
      "grad_norm": 0.4542549252510071,
      "learning_rate": 3.361167125710832e-07,
      "logits/chosen": 10.056829452514648,
      "logits/rejected": 10.121377944946289,
      "logps/chosen": -181.4767303466797,
      "logps/ref_chosen": -173.72467041015625,
      "logps/ref_rejected": -180.5912322998047,
      "logps/rejected": -188.53164672851562,
      "loss": 0.6923,
      "rewards/accuracies": 0.4921875,
      "rewards/chosen": -0.07752064615488052,
      "rewards/margins": 0.0018832057248800993,
      "rewards/rejected": -0.0794038400053978,
      "step": 34
    },
    {
      "epoch": 0.4610951008645533,
      "grad_norm": 0.4729287028312683,
      "learning_rate": 3.2502115875008516e-07,
      "logits/chosen": 10.46947193145752,
      "logits/rejected": 10.667445182800293,
      "logps/chosen": -182.939208984375,
      "logps/ref_chosen": -175.0980987548828,
      "logps/ref_rejected": -181.65821838378906,
      "logps/rejected": -189.89309692382812,
      "loss": 0.6913,
      "rewards/accuracies": 0.578125,
      "rewards/chosen": -0.07841099798679352,
      "rewards/margins": 0.00393773103132844,
      "rewards/rejected": -0.08234872668981552,
      "step": 35
    },
    {
      "epoch": 0.47426924660354053,
      "grad_norm": 0.8570416569709778,
      "learning_rate": 3.137606921404191e-07,
      "logits/chosen": 10.280503273010254,
      "logits/rejected": 10.623340606689453,
      "logps/chosen": -182.2921142578125,
      "logps/ref_chosen": -174.0312042236328,
      "logps/ref_rejected": -181.84324645996094,
      "logps/rejected": -190.1889190673828,
      "loss": 0.6928,
      "rewards/accuracies": 0.484375,
      "rewards/chosen": -0.08260920643806458,
      "rewards/margins": 0.0008472882909700274,
      "rewards/rejected": -0.08345648646354675,
      "step": 36
    },
    {
      "epoch": 0.4874433923425278,
      "grad_norm": 0.9711470007896423,
      "learning_rate": 3.0236006569153616e-07,
      "logits/chosen": 10.310943603515625,
      "logits/rejected": 10.279195785522461,
      "logps/chosen": -183.245361328125,
      "logps/ref_chosen": -175.3839569091797,
      "logps/ref_rejected": -182.51773071289062,
      "logps/rejected": -190.82374572753906,
      "loss": 0.691,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": -0.07861402630805969,
      "rewards/margins": 0.004445935599505901,
      "rewards/rejected": -0.08305995911359787,
      "step": 37
    },
    {
      "epoch": 0.500617538081515,
      "grad_norm": 0.680104672908783,
      "learning_rate": 2.9084434045463254e-07,
      "logits/chosen": 10.41287612915039,
      "logits/rejected": 10.449625968933105,
      "logps/chosen": -182.55191040039062,
      "logps/ref_chosen": -174.5338134765625,
      "logps/ref_rejected": -179.96829223632812,
      "logps/rejected": -188.60166931152344,
      "loss": 0.6902,
      "rewards/accuracies": 0.6171875,
      "rewards/chosen": -0.08018088340759277,
      "rewards/margins": 0.00615295534953475,
      "rewards/rejected": -0.08633382618427277,
      "step": 38
    },
    {
      "epoch": 0.5137916838205022,
      "grad_norm": 0.41836705803871155,
      "learning_rate": 2.7923883049302066e-07,
      "logits/chosen": 10.237342834472656,
      "logits/rejected": 10.221612930297852,
      "logps/chosen": -190.19024658203125,
      "logps/ref_chosen": -181.61000061035156,
      "logps/ref_rejected": -187.48886108398438,
      "logps/rejected": -196.35353088378906,
      "loss": 0.6919,
      "rewards/accuracies": 0.53125,
      "rewards/chosen": -0.08580265194177628,
      "rewards/margins": 0.0028439394664019346,
      "rewards/rejected": -0.08864659070968628,
      "step": 39
    },
    {
      "epoch": 0.5269658295594895,
      "grad_norm": 0.4576071798801422,
      "learning_rate": 2.6756904723632324e-07,
      "logits/chosen": 10.366464614868164,
      "logits/rejected": 10.504589080810547,
      "logps/chosen": -181.5367431640625,
      "logps/ref_chosen": -172.43283081054688,
      "logps/ref_rejected": -186.99594116210938,
      "logps/rejected": -196.2064971923828,
      "loss": 0.6927,
      "rewards/accuracies": 0.53125,
      "rewards/chosen": -0.0910390242934227,
      "rewards/margins": 0.001066619879566133,
      "rewards/rejected": -0.09210564941167831,
      "step": 40
    },
    {
      "epoch": 0.5401399752984768,
      "grad_norm": 0.5803886651992798,
      "learning_rate": 2.5586064340081516e-07,
      "logits/chosen": 10.624752044677734,
      "logits/rejected": 10.738086700439453,
      "logps/chosen": -183.4002685546875,
      "logps/ref_chosen": -175.37374877929688,
      "logps/ref_rejected": -181.78671264648438,
      "logps/rejected": -190.14678955078125,
      "loss": 0.6916,
      "rewards/accuracies": 0.5703125,
      "rewards/chosen": -0.08026508241891861,
      "rewards/margins": 0.003335628192871809,
      "rewards/rejected": -0.083600714802742,
      "step": 41
    },
    {
      "epoch": 0.553314121037464,
      "grad_norm": 0.48118287324905396,
      "learning_rate": 2.4413935659918487e-07,
      "logits/chosen": 10.010458946228027,
      "logits/rejected": 10.1697359085083,
      "logps/chosen": -182.1250457763672,
      "logps/ref_chosen": -173.79501342773438,
      "logps/ref_rejected": -179.49351501464844,
      "logps/rejected": -188.2036895751953,
      "loss": 0.6914,
      "rewards/accuracies": 0.4921875,
      "rewards/chosen": -0.08330036699771881,
      "rewards/margins": 0.003801207058131695,
      "rewards/rejected": -0.08710157871246338,
      "step": 42
    },
    {
      "epoch": 0.5664882667764513,
      "grad_norm": 0.7869899868965149,
      "learning_rate": 2.3243095276367684e-07,
      "logits/chosen": 9.809760093688965,
      "logits/rejected": 10.002002716064453,
      "logps/chosen": -171.12933349609375,
      "logps/ref_chosen": -162.35044860839844,
      "logps/ref_rejected": -177.5733642578125,
      "logps/rejected": -187.271240234375,
      "loss": 0.6887,
      "rewards/accuracies": 0.640625,
      "rewards/chosen": -0.08778898417949677,
      "rewards/margins": 0.009189910255372524,
      "rewards/rejected": -0.09697890281677246,
      "step": 43
    },
    {
      "epoch": 0.5796624125154385,
      "grad_norm": 0.46572622656822205,
      "learning_rate": 2.2076116950697937e-07,
      "logits/chosen": 10.310693740844727,
      "logits/rejected": 10.41200065612793,
      "logps/chosen": -177.54794311523438,
      "logps/ref_chosen": -168.2965545654297,
      "logps/ref_rejected": -176.21559143066406,
      "logps/rejected": -185.90658569335938,
      "loss": 0.6911,
      "rewards/accuracies": 0.609375,
      "rewards/chosen": -0.09251392632722855,
      "rewards/margins": 0.004395842086523771,
      "rewards/rejected": -0.0969097688794136,
      "step": 44
    },
    {
      "epoch": 0.5928365582544257,
      "grad_norm": 0.4241108298301697,
      "learning_rate": 2.091556595453674e-07,
      "logits/chosen": 10.16834831237793,
      "logits/rejected": 10.282001495361328,
      "logps/chosen": -186.37091064453125,
      "logps/ref_chosen": -177.40481567382812,
      "logps/ref_rejected": -184.82774353027344,
      "logps/rejected": -194.56387329101562,
      "loss": 0.6894,
      "rewards/accuracies": 0.5703125,
      "rewards/chosen": -0.08966079354286194,
      "rewards/margins": 0.007700393907725811,
      "rewards/rejected": -0.09736119955778122,
      "step": 45
    },
    {
      "epoch": 0.606010703993413,
      "grad_norm": 0.5031992197036743,
      "learning_rate": 1.9763993430846392e-07,
      "logits/chosen": 10.157776832580566,
      "logits/rejected": 10.314593315124512,
      "logps/chosen": -184.5338134765625,
      "logps/ref_chosen": -176.05081176757812,
      "logps/ref_rejected": -183.15682983398438,
      "logps/rejected": -192.16787719726562,
      "loss": 0.6906,
      "rewards/accuracies": 0.53125,
      "rewards/chosen": -0.08483003079891205,
      "rewards/margins": 0.0052804588340222836,
      "rewards/rejected": -0.09011048823595047,
      "step": 46
    },
    {
      "epoch": 0.6191848497324002,
      "grad_norm": 0.5240408778190613,
      "learning_rate": 1.862393078595809e-07,
      "logits/chosen": 10.676742553710938,
      "logits/rejected": 10.760393142700195,
      "logps/chosen": -182.15650939941406,
      "logps/ref_chosen": -172.76321411132812,
      "logps/ref_rejected": -181.09564208984375,
      "logps/rejected": -190.9324493408203,
      "loss": 0.691,
      "rewards/accuracies": 0.578125,
      "rewards/chosen": -0.0939328670501709,
      "rewards/margins": 0.004435211420059204,
      "rewards/rejected": -0.0983680710196495,
      "step": 47
    },
    {
      "epoch": 0.6323589954713874,
      "grad_norm": 0.7354983687400818,
      "learning_rate": 1.7497884124991485e-07,
      "logits/chosen": 10.81379508972168,
      "logits/rejected": 10.839184761047363,
      "logps/chosen": -183.8255157470703,
      "logps/ref_chosen": -174.04627990722656,
      "logps/ref_rejected": -178.9498748779297,
      "logps/rejected": -188.9517059326172,
      "loss": 0.6921,
      "rewards/accuracies": 0.5078125,
      "rewards/chosen": -0.09779238700866699,
      "rewards/margins": 0.0022260185796767473,
      "rewards/rejected": -0.10001839697360992,
      "step": 48
    },
    {
      "epoch": 0.6455331412103746,
      "grad_norm": 0.46142828464508057,
      "learning_rate": 1.6388328742891678e-07,
      "logits/chosen": 10.411097526550293,
      "logits/rejected": 10.650638580322266,
      "logps/chosen": -182.78021240234375,
      "logps/ref_chosen": -173.49203491210938,
      "logps/ref_rejected": -184.48907470703125,
      "logps/rejected": -194.2916717529297,
      "loss": 0.6907,
      "rewards/accuracies": 0.5234375,
      "rewards/chosen": -0.09288190305233002,
      "rewards/margins": 0.005143978167325258,
      "rewards/rejected": -0.09802587330341339,
      "step": 49
    },
    {
      "epoch": 0.6587072869493619,
      "grad_norm": 0.46846839785575867,
      "learning_rate": 1.5297703683193753e-07,
      "logits/chosen": 10.26883316040039,
      "logits/rejected": 10.302979469299316,
      "logps/chosen": -182.86697387695312,
      "logps/ref_chosen": -174.3692626953125,
      "logps/ref_rejected": -179.42811584472656,
      "logps/rejected": -188.55862426757812,
      "loss": 0.6901,
      "rewards/accuracies": 0.5390625,
      "rewards/chosen": -0.0849771574139595,
      "rewards/margins": 0.006327708251774311,
      "rewards/rejected": -0.09130486845970154,
      "step": 50
    },
    {
      "epoch": 0.6718814326883491,
      "grad_norm": 0.4509861469268799,
      "learning_rate": 1.422840637647574e-07,
      "logits/chosen": 9.835365295410156,
      "logits/rejected": 10.054549217224121,
      "logps/chosen": -180.4107666015625,
      "logps/ref_chosen": -170.41490173339844,
      "logps/ref_rejected": -178.72731018066406,
      "logps/rejected": -188.8809356689453,
      "loss": 0.6925,
      "rewards/accuracies": 0.5078125,
      "rewards/chosen": -0.0999586284160614,
      "rewards/margins": 0.001577734830789268,
      "rewards/rejected": -0.10153636336326599,
      "step": 51
    },
    {
      "epoch": 0.6850555784273363,
      "grad_norm": 0.47539010643959045,
      "learning_rate": 1.3182787370285865e-07,
      "logits/chosen": 10.200839042663574,
      "logits/rejected": 10.327034950256348,
      "logps/chosen": -182.788330078125,
      "logps/ref_chosen": -173.27346801757812,
      "logps/ref_rejected": -181.28955078125,
      "logps/rejected": -190.73574829101562,
      "loss": 0.6936,
      "rewards/accuracies": 0.53125,
      "rewards/chosen": -0.09514841437339783,
      "rewards/margins": -0.0006866034236736596,
      "rewards/rejected": -0.09446181356906891,
      "step": 52
    },
    {
      "epoch": 0.6982297241663236,
      "grad_norm": 0.4662962555885315,
      "learning_rate": 1.2163145162128946e-07,
      "logits/chosen": 10.18519115447998,
      "logits/rejected": 10.273019790649414,
      "logps/chosen": -178.12774658203125,
      "logps/ref_chosen": -169.4412841796875,
      "logps/ref_rejected": -177.9136962890625,
      "logps/rejected": -186.86569213867188,
      "loss": 0.6919,
      "rewards/accuracies": 0.5703125,
      "rewards/chosen": -0.08686451613903046,
      "rewards/margins": 0.002655319171026349,
      "rewards/rejected": -0.08951984345912933,
      "step": 53
    },
    {
      "epoch": 0.7114038699053108,
      "grad_norm": 0.8465985655784607,
      "learning_rate": 1.1171721146870014e-07,
      "logits/chosen": 10.456581115722656,
      "logits/rejected": 10.613874435424805,
      "logps/chosen": -178.52198791503906,
      "logps/ref_chosen": -169.522705078125,
      "logps/ref_rejected": -178.76429748535156,
      "logps/rejected": -188.03038024902344,
      "loss": 0.6919,
      "rewards/accuracies": 0.5546875,
      "rewards/chosen": -0.08999277651309967,
      "rewards/margins": 0.002668112050741911,
      "rewards/rejected": -0.09266088157892227,
      "step": 54
    },
    {
      "epoch": 0.724578015644298,
      "grad_norm": 0.6576270461082458,
      "learning_rate": 1.0210694689661939e-07,
      "logits/chosen": 10.151554107666016,
      "logits/rejected": 10.437423706054688,
      "logps/chosen": -180.3101806640625,
      "logps/ref_chosen": -170.54901123046875,
      "logps/ref_rejected": -182.5826416015625,
      "logps/rejected": -192.5031280517578,
      "loss": 0.6925,
      "rewards/accuracies": 0.5,
      "rewards/chosen": -0.09761152416467667,
      "rewards/margins": 0.001593249849975109,
      "rewards/rejected": -0.09920478612184525,
      "step": 55
    },
    {
      "epoch": 0.7377521613832853,
      "grad_norm": 0.41899698972702026,
      "learning_rate": 9.282178335227883e-08,
      "logits/chosen": 10.053117752075195,
      "logits/rejected": 10.20742416381836,
      "logps/chosen": -176.72296142578125,
      "logps/ref_chosen": -167.25425720214844,
      "logps/ref_rejected": -179.09097290039062,
      "logps/rejected": -189.30906677246094,
      "loss": 0.6895,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -0.09468717873096466,
      "rewards/margins": 0.007493786513805389,
      "rewards/rejected": -0.10218098014593124,
      "step": 56
    },
    {
      "epoch": 0.7509263071222725,
      "grad_norm": 0.9100576639175415,
      "learning_rate": 8.388213164029459e-08,
      "logits/chosen": 10.378426551818848,
      "logits/rejected": 10.488100051879883,
      "logps/chosen": -178.44271850585938,
      "logps/ref_chosen": -168.67286682128906,
      "logps/ref_rejected": -175.382080078125,
      "logps/rejected": -185.38555908203125,
      "loss": 0.6921,
      "rewards/accuracies": 0.5390625,
      "rewards/chosen": -0.09769845008850098,
      "rewards/margins": 0.0023363539949059486,
      "rewards/rejected": -0.10003480315208435,
      "step": 57
    },
    {
      "epoch": 0.7641004528612598,
      "grad_norm": 0.5843770503997803,
      "learning_rate": 7.530764305528958e-08,
      "logits/chosen": 10.184845924377441,
      "logits/rejected": 10.465659141540527,
      "logps/chosen": -182.78147888183594,
      "logps/ref_chosen": -173.50100708007812,
      "logps/ref_rejected": -185.66575622558594,
      "logps/rejected": -195.41639709472656,
      "loss": 0.6909,
      "rewards/accuracies": 0.5703125,
      "rewards/chosen": -0.09280481189489365,
      "rewards/margins": 0.004701639991253614,
      "rewards/rejected": -0.09750644117593765,
      "step": 58
    },
    {
      "epoch": 0.7772745986002471,
      "grad_norm": 0.7781294584274292,
      "learning_rate": 6.711716618408281e-08,
      "logits/chosen": 10.412872314453125,
      "logits/rejected": 10.303376197814941,
      "logps/chosen": -186.38430786132812,
      "logps/ref_chosen": -176.9933624267578,
      "logps/ref_rejected": -179.3916015625,
      "logps/rejected": -189.677001953125,
      "loss": 0.6888,
      "rewards/accuracies": 0.6328125,
      "rewards/chosen": -0.09390951693058014,
      "rewards/margins": 0.00894430186599493,
      "rewards/rejected": -0.10285381972789764,
      "step": 59
    },
    {
      "epoch": 0.7904487443392343,
      "grad_norm": 0.7131383419036865,
      "learning_rate": 5.932870547240454e-08,
      "logits/chosen": 10.266400337219238,
      "logits/rejected": 10.431807518005371,
      "logps/chosen": -182.096435546875,
      "logps/ref_chosen": -172.4757080078125,
      "logps/ref_rejected": -181.6919403076172,
      "logps/rejected": -191.6405029296875,
      "loss": 0.6917,
      "rewards/accuracies": 0.53125,
      "rewards/chosen": -0.09620757400989532,
      "rewards/margins": 0.0032782030757516623,
      "rewards/rejected": -0.09948578476905823,
      "step": 60
    },
    {
      "epoch": 0.8036228900782215,
      "grad_norm": 0.8971508741378784,
      "learning_rate": 5.1959381647217665e-08,
      "logits/chosen": 10.6429443359375,
      "logits/rejected": 10.80582332611084,
      "logps/chosen": -185.9635467529297,
      "logps/ref_chosen": -176.46063232421875,
      "logps/ref_rejected": -181.6070556640625,
      "logps/rejected": -191.1348419189453,
      "loss": 0.6931,
      "rewards/accuracies": 0.546875,
      "rewards/chosen": -0.09502905607223511,
      "rewards/margins": 0.0002487818128429353,
      "rewards/rejected": -0.0952778309583664,
      "step": 61
    },
    {
      "epoch": 0.8167970358172087,
      "grad_norm": 0.49599340558052063,
      "learning_rate": 4.502539408164385e-08,
      "logits/chosen": 10.2130126953125,
      "logits/rejected": 10.290302276611328,
      "logps/chosen": -182.39906311035156,
      "logps/ref_chosen": -173.50965881347656,
      "logps/ref_rejected": -181.95948791503906,
      "logps/rejected": -191.3000030517578,
      "loss": 0.691,
      "rewards/accuracies": 0.546875,
      "rewards/chosen": -0.08889415860176086,
      "rewards/margins": 0.004511075094342232,
      "rewards/rejected": -0.09340524673461914,
      "step": 62
    },
    {
      "epoch": 0.829971181556196,
      "grad_norm": 0.9597389101982117,
      "learning_rate": 3.854198518522564e-08,
      "logits/chosen": 10.418037414550781,
      "logits/rejected": 10.477688789367676,
      "logps/chosen": -186.2067413330078,
      "logps/ref_chosen": -176.99668884277344,
      "logps/ref_rejected": -179.9959259033203,
      "logps/rejected": -189.2750701904297,
      "loss": 0.6929,
      "rewards/accuracies": 0.4921875,
      "rewards/chosen": -0.09210053086280823,
      "rewards/margins": 0.0006907913484610617,
      "rewards/rejected": -0.09279131889343262,
      "step": 63
    },
    {
      "epoch": 0.8431453272951832,
      "grad_norm": 0.5417306423187256,
      "learning_rate": 3.2523406897802444e-08,
      "logits/chosen": 10.14089298248291,
      "logits/rejected": 10.332672119140625,
      "logps/chosen": -180.74453735351562,
      "logps/ref_chosen": -171.4447784423828,
      "logps/ref_rejected": -179.7430877685547,
      "logps/rejected": -189.95082092285156,
      "loss": 0.6888,
      "rewards/accuracies": 0.6171875,
      "rewards/chosen": -0.09299754351377487,
      "rewards/margins": 0.009079902432858944,
      "rewards/rejected": -0.1020774394273758,
      "step": 64
    },
    {
      "epoch": 0.8563194730341704,
      "grad_norm": 0.43316248059272766,
      "learning_rate": 2.6982889360653376e-08,
      "logits/chosen": 9.99162483215332,
      "logits/rejected": 10.228858947753906,
      "logps/chosen": -180.99267578125,
      "logps/ref_chosen": -172.0072021484375,
      "logps/ref_rejected": -185.04971313476562,
      "logps/rejected": -194.4329071044922,
      "loss": 0.6913,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": -0.08985472470521927,
      "rewards/margins": 0.003977032843977213,
      "rewards/rejected": -0.09383176267147064,
      "step": 65
    },
    {
      "epoch": 0.8694936187731577,
      "grad_norm": 0.36356666684150696,
      "learning_rate": 2.1932611833775843e-08,
      "logits/chosen": 10.639575958251953,
      "logits/rejected": 10.7981595993042,
      "logps/chosen": -181.5137939453125,
      "logps/ref_chosen": -172.55426025390625,
      "logps/ref_rejected": -179.38259887695312,
      "logps/rejected": -188.9515380859375,
      "loss": 0.6902,
      "rewards/accuracies": 0.578125,
      "rewards/chosen": -0.08959527313709259,
      "rewards/margins": 0.006094326265156269,
      "rewards/rejected": -0.09568959474563599,
      "step": 66
    },
    {
      "epoch": 0.8826677645121449,
      "grad_norm": 0.5667024254798889,
      "learning_rate": 1.738367592322837e-08,
      "logits/chosen": 9.989572525024414,
      "logits/rejected": 10.212047576904297,
      "logps/chosen": -182.31504821777344,
      "logps/ref_chosen": -172.5652313232422,
      "logps/ref_rejected": -181.12344360351562,
      "logps/rejected": -190.916015625,
      "loss": 0.6931,
      "rewards/accuracies": 0.4921875,
      "rewards/chosen": -0.09749818593263626,
      "rewards/margins": 0.0004273450467735529,
      "rewards/rejected": -0.09792553633451462,
      "step": 67
    },
    {
      "epoch": 0.8958419102511321,
      "grad_norm": 0.5381993055343628,
      "learning_rate": 1.3346081177391472e-08,
      "logits/chosen": 10.527931213378906,
      "logits/rejected": 10.72231674194336,
      "logps/chosen": -184.08009338378906,
      "logps/ref_chosen": -174.92095947265625,
      "logps/ref_rejected": -184.9745330810547,
      "logps/rejected": -194.40374755859375,
      "loss": 0.6919,
      "rewards/accuracies": 0.5703125,
      "rewards/chosen": -0.09159158170223236,
      "rewards/margins": 0.0027003707364201546,
      "rewards/rejected": -0.09429195523262024,
      "step": 68
    },
    {
      "epoch": 0.9090160559901194,
      "grad_norm": 0.3892871141433716,
      "learning_rate": 9.828703105789981e-09,
      "logits/chosen": 10.44791316986084,
      "logits/rejected": 10.606199264526367,
      "logps/chosen": -179.3982696533203,
      "logps/ref_chosen": -170.1553497314453,
      "logps/ref_rejected": -177.0266571044922,
      "logps/rejected": -186.47589111328125,
      "loss": 0.6923,
      "rewards/accuracies": 0.546875,
      "rewards/chosen": -0.09242918342351913,
      "rewards/margins": 0.0020632066298276186,
      "rewards/rejected": -0.09449239820241928,
      "step": 69
    },
    {
      "epoch": 0.9221902017291066,
      "grad_norm": 0.36983534693717957,
      "learning_rate": 6.839273668796747e-09,
      "logits/chosen": 9.935354232788086,
      "logits/rejected": 10.000804901123047,
      "logps/chosen": -186.02670288085938,
      "logps/ref_chosen": -176.646728515625,
      "logps/ref_rejected": -181.71400451660156,
      "logps/rejected": -191.41668701171875,
      "loss": 0.6916,
      "rewards/accuracies": 0.5234375,
      "rewards/chosen": -0.09379980713129044,
      "rewards/margins": 0.003227120265364647,
      "rewards/rejected": -0.09702693670988083,
      "step": 70
    },
    {
      "epoch": 0.9353643474680938,
      "grad_norm": 0.5925127267837524,
      "learning_rate": 4.384364281105973e-09,
      "logits/chosen": 10.40229606628418,
      "logits/rejected": 10.555439949035645,
      "logps/chosen": -180.85951232910156,
      "logps/ref_chosen": -171.08848571777344,
      "logps/ref_rejected": -180.61367797851562,
      "logps/rejected": -190.57582092285156,
      "loss": 0.6923,
      "rewards/accuracies": 0.546875,
      "rewards/chosen": -0.09771019965410233,
      "rewards/margins": 0.0019110110588371754,
      "rewards/rejected": -0.09962122142314911,
      "step": 71
    },
    {
      "epoch": 0.9485384932070811,
      "grad_norm": 0.4126102924346924,
      "learning_rate": 2.469371366337264e-09,
      "logits/chosen": 10.298188209533691,
      "logits/rejected": 10.579760551452637,
      "logps/chosen": -183.428955078125,
      "logps/ref_chosen": -174.154296875,
      "logps/ref_rejected": -185.73587036132812,
      "logps/rejected": -195.6343536376953,
      "loss": 0.6902,
      "rewards/accuracies": 0.6328125,
      "rewards/chosen": -0.092746801674366,
      "rewards/margins": 0.0062379841692745686,
      "rewards/rejected": -0.09898478537797928,
      "step": 72
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 12,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}