{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 124,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016260162601626018,
      "grad_norm": 18.177886962890625,
      "learning_rate": 2e-05,
      "logits/chosen": -0.3472236394882202,
      "logits/rejected": -0.13716036081314087,
      "logps/chosen": -780.8181762695312,
      "logps/rejected": -909.20263671875,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.032520325203252036,
      "grad_norm": 23.274246215820312,
      "learning_rate": 4e-05,
      "logits/chosen": -0.2127760350704193,
      "logits/rejected": -0.08323362469673157,
      "logps/chosen": -583.0169067382812,
      "logps/rejected": -715.5615234375,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 2
    },
    {
      "epoch": 0.04878048780487805,
      "grad_norm": 20.149507522583008,
      "learning_rate": 6e-05,
      "logits/chosen": -0.18167662620544434,
      "logits/rejected": -0.04478086531162262,
      "logps/chosen": -941.0387573242188,
      "logps/rejected": -825.662841796875,
      "loss": 0.6976,
      "rewards/accuracies": 0.5,
      "rewards/chosen": 0.025517277419567108,
      "rewards/margins": 0.022285467013716698,
      "rewards/rejected": 0.0032318076118826866,
      "step": 3
    },
    {
      "epoch": 0.06504065040650407,
      "grad_norm": 16.67251205444336,
      "learning_rate": 8e-05,
      "logits/chosen": 0.6866837739944458,
      "logits/rejected": 0.971089243888855,
      "logps/chosen": -999.306640625,
      "logps/rejected": -386.5375671386719,
      "loss": 0.563,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.2688583433628082,
      "rewards/margins": 0.3312031030654907,
      "rewards/rejected": -0.062344741076231,
      "step": 4
    },
    {
      "epoch": 0.08130081300813008,
      "grad_norm": 15.646084785461426,
      "learning_rate": 0.0001,
      "logits/chosen": 0.5107800364494324,
      "logits/rejected": 0.5942208766937256,
      "logps/chosen": -1051.1270751953125,
      "logps/rejected": -745.8003540039062,
      "loss": 0.647,
      "rewards/accuracies": 0.5,
      "rewards/chosen": 0.3622299134731293,
      "rewards/margins": 0.34313660860061646,
      "rewards/rejected": 0.01909332349896431,
      "step": 5
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 38.70280456542969,
      "learning_rate": 0.00012,
      "logits/chosen": -0.31406939029693604,
      "logits/rejected": -0.24293695390224457,
      "logps/chosen": -845.9321899414062,
      "logps/rejected": -932.499755859375,
      "loss": 0.5175,
      "rewards/accuracies": 0.75,
      "rewards/chosen": 0.5435073971748352,
      "rewards/margins": 0.47774890065193176,
      "rewards/rejected": 0.06575851887464523,
      "step": 6
    },
    {
      "epoch": 0.11382113821138211,
      "grad_norm": 23.665071487426758,
      "learning_rate": 0.00014,
      "logits/chosen": -0.2646118402481079,
      "logits/rejected": -0.11520399153232574,
      "logps/chosen": -866.503173828125,
      "logps/rejected": -975.55126953125,
      "loss": 0.5487,
      "rewards/accuracies": 0.5,
      "rewards/chosen": 0.6112838387489319,
      "rewards/margins": 0.4790405333042145,
      "rewards/rejected": 0.1322433352470398,
      "step": 7
    },
    {
      "epoch": 0.13008130081300814,
      "grad_norm": 15.794047355651855,
      "learning_rate": 0.00016,
      "logits/chosen": -0.8256000876426697,
      "logits/rejected": -0.8912097811698914,
      "logps/chosen": -523.3858032226562,
      "logps/rejected": -1084.9468994140625,
      "loss": 0.4442,
      "rewards/accuracies": 0.5,
      "rewards/chosen": 0.5804435610771179,
      "rewards/margins": 0.24081651866436005,
      "rewards/rejected": 0.33962705731391907,
      "step": 8
    },
    {
      "epoch": 0.14634146341463414,
      "grad_norm": 13.538564682006836,
      "learning_rate": 0.00018,
      "logits/chosen": -0.11683523654937744,
      "logits/rejected": -0.0632472038269043,
      "logps/chosen": -652.114501953125,
      "logps/rejected": -551.6069946289062,
      "loss": 0.1564,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.6716469526290894,
      "rewards/margins": 2.151698350906372,
      "rewards/rejected": -0.4800514578819275,
      "step": 9
    },
    {
      "epoch": 0.16260162601626016,
      "grad_norm": 3.9652626514434814,
      "learning_rate": 0.0002,
      "logits/chosen": 0.4062778949737549,
      "logits/rejected": 0.5438919067382812,
      "logps/chosen": -771.1934814453125,
      "logps/rejected": -616.55908203125,
      "loss": 0.0792,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.8721909523010254,
      "rewards/margins": 5.208758354187012,
      "rewards/rejected": -1.3365669250488281,
      "step": 10
    },
    {
      "epoch": 0.17886178861788618,
      "grad_norm": 0.18261243402957916,
      "learning_rate": 0.0001999911398855782,
      "logits/chosen": -0.7774271965026855,
      "logits/rejected": -0.8629493117332458,
      "logps/chosen": -601.1015014648438,
      "logps/rejected": -1039.275146484375,
      "loss": 0.0019,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.0800025463104248,
      "rewards/margins": 6.853862762451172,
      "rewards/rejected": -5.773860454559326,
      "step": 11
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 0.1421748697757721,
      "learning_rate": 0.00019996456111234527,
      "logits/chosen": 0.7899215817451477,
      "logits/rejected": 1.119359016418457,
      "logps/chosen": -1416.412353515625,
      "logps/rejected": -827.2066650390625,
      "loss": 0.0008,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.7505874633789062,
      "rewards/margins": 15.09115982055664,
      "rewards/rejected": -11.340574264526367,
      "step": 12
    },
    {
      "epoch": 0.21138211382113822,
      "grad_norm": 3.4406840801239014,
      "learning_rate": 0.00019992026839012067,
      "logits/chosen": -0.8033453226089478,
      "logits/rejected": -0.877557098865509,
      "logps/chosen": -514.6026611328125,
      "logps/rejected": -1206.25537109375,
      "loss": 0.0102,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.7983558177947998,
      "rewards/margins": 23.49526596069336,
      "rewards/rejected": -21.696908950805664,
      "step": 13
    },
    {
      "epoch": 0.22764227642276422,
      "grad_norm": 0.19398577511310577,
      "learning_rate": 0.0001998582695676762,
      "logits/chosen": 0.9254277944564819,
      "logits/rejected": 1.1634798049926758,
      "logps/chosen": -1028.993408203125,
      "logps/rejected": -955.4432983398438,
      "loss": 0.001,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -0.5009795427322388,
      "rewards/margins": 17.867931365966797,
      "rewards/rejected": -18.368911743164062,
      "step": 14
    },
    {
      "epoch": 0.24390243902439024,
      "grad_norm": 0.00010074722376884893,
      "learning_rate": 0.000199778575631345,
      "logits/chosen": 0.3904605507850647,
      "logits/rejected": 0.3719422519207001,
      "logps/chosen": -884.9620361328125,
      "logps/rejected": -1075.615966796875,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.482113838195801,
      "rewards/margins": 21.95424461364746,
      "rewards/rejected": -24.436357498168945,
      "step": 15
    },
    {
      "epoch": 0.2601626016260163,
      "grad_norm": 3.7136353057576343e-05,
      "learning_rate": 0.000199681200703075,
      "logits/chosen": 0.2578551769256592,
      "logits/rejected": 0.5335351824760437,
      "logps/chosen": -1073.548828125,
      "logps/rejected": -992.4033813476562,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.9434356689453125,
      "rewards/margins": 20.854663848876953,
      "rewards/rejected": -23.798099517822266,
      "step": 16
    },
    {
      "epoch": 0.2764227642276423,
      "grad_norm": 8.596338147981442e-07,
      "learning_rate": 0.00019956616203792635,
      "logits/chosen": 0.5267460346221924,
      "logits/rejected": 0.4893237352371216,
      "logps/chosen": -987.3567504882812,
      "logps/rejected": -1127.171875,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -1.0684036016464233,
      "rewards/margins": 32.558319091796875,
      "rewards/rejected": -33.62671661376953,
      "step": 17
    },
    {
      "epoch": 0.2926829268292683,
      "grad_norm": 0.004051027819514275,
      "learning_rate": 0.00019943348002101371,
      "logits/chosen": 1.0484071969985962,
      "logits/rejected": 1.1081664562225342,
      "logps/chosen": -1105.1634521484375,
      "logps/rejected": -898.9759521484375,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -3.1622314453125,
      "rewards/margins": 23.434669494628906,
      "rewards/rejected": -26.596900939941406,
      "step": 18
    },
    {
      "epoch": 0.3089430894308943,
      "grad_norm": 0.003306547412648797,
      "learning_rate": 0.00019928317816389417,
      "logits/chosen": 0.5566614866256714,
      "logits/rejected": 0.6963181495666504,
      "logps/chosen": -932.650390625,
      "logps/rejected": -1061.4989013671875,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -4.36033821105957,
      "rewards/margins": 30.25779914855957,
      "rewards/rejected": -34.61813735961914,
      "step": 19
    },
    {
      "epoch": 0.3252032520325203,
      "grad_norm": 1.3893560968369911e-08,
      "learning_rate": 0.00019911528310040074,
      "logits/chosen": 1.239579200744629,
      "logits/rejected": 1.046311855316162,
      "logps/chosen": -1079.0159912109375,
      "logps/rejected": -1033.2017822265625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.044548749923706,
      "rewards/margins": 41.88936233520508,
      "rewards/rejected": -40.844810485839844,
      "step": 20
    },
    {
      "epoch": 0.34146341463414637,
      "grad_norm": 4.666223851756968e-09,
      "learning_rate": 0.00019892982458192288,
      "logits/chosen": 0.2726232409477234,
      "logits/rejected": 0.14665402472019196,
      "logps/chosen": -978.7222900390625,
      "logps/rejected": -1133.2047119140625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 11.054238319396973,
      "rewards/margins": 54.86410140991211,
      "rewards/rejected": -43.80986404418945,
      "step": 21
    },
    {
      "epoch": 0.35772357723577236,
      "grad_norm": 4.876813477494579e-07,
      "learning_rate": 0.00019872683547213446,
      "logits/chosen": -0.16925190389156342,
      "logits/rejected": -0.19759103655815125,
      "logps/chosen": -965.187255859375,
      "logps/rejected": -1239.143798828125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -14.977485656738281,
      "rewards/margins": 29.40732765197754,
      "rewards/rejected": -44.38481140136719,
      "step": 22
    },
    {
      "epoch": 0.37398373983739835,
      "grad_norm": 37.638973236083984,
      "learning_rate": 0.00019850635174117033,
      "logits/chosen": 0.437714159488678,
      "logits/rejected": 0.4761970639228821,
      "logps/chosen": -1137.6966552734375,
      "logps/rejected": -1166.5640869140625,
      "loss": 0.4393,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -11.159793853759766,
      "rewards/margins": 32.14189529418945,
      "rewards/rejected": -43.301692962646484,
      "step": 23
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 1.8173747229344173e-11,
      "learning_rate": 0.00019826841245925212,
      "logits/chosen": -0.7153763175010681,
      "logits/rejected": -0.6940470933914185,
      "logps/chosen": -938.263916015625,
      "logps/rejected": -1608.4205322265625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -24.817350387573242,
      "rewards/margins": 34.095001220703125,
      "rewards/rejected": -58.912349700927734,
      "step": 24
    },
    {
      "epoch": 0.4065040650406504,
      "grad_norm": 83.79772186279297,
      "learning_rate": 0.0001980130597897651,
      "logits/chosen": 1.1592888832092285,
      "logits/rejected": 1.1738824844360352,
      "logps/chosen": -948.4622802734375,
      "logps/rejected": -865.396728515625,
      "loss": 0.3825,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -3.343675374984741,
      "rewards/margins": 26.49417495727539,
      "rewards/rejected": -29.837852478027344,
      "step": 25
    },
    {
      "epoch": 0.42276422764227645,
      "grad_norm": 2.6143006834900007e-06,
      "learning_rate": 0.00019774033898178667,
      "logits/chosen": 0.5444796085357666,
      "logits/rejected": 0.47586876153945923,
      "logps/chosen": -932.6605834960938,
      "logps/rejected": -1091.639892578125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -4.2753777503967285,
      "rewards/margins": 34.133514404296875,
      "rewards/rejected": -38.40888977050781,
      "step": 26
    },
    {
      "epoch": 0.43902439024390244,
      "grad_norm": 0.0003061926399823278,
      "learning_rate": 0.00019745029836206813,
      "logits/chosen": -0.6794779896736145,
      "logits/rejected": -0.8602011203765869,
      "logps/chosen": -894.3270263671875,
      "logps/rejected": -1067.5921630859375,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -13.433198928833008,
      "rewards/margins": 17.333955764770508,
      "rewards/rejected": -30.767154693603516,
      "step": 27
    },
    {
      "epoch": 0.45528455284552843,
      "grad_norm": 3.805017101399244e-08,
      "learning_rate": 0.00019714298932647098,
      "logits/chosen": 0.4980026185512543,
      "logits/rejected": 0.6999194025993347,
      "logps/chosen": -911.8473510742188,
      "logps/rejected": -1126.07421875,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -0.5412168502807617,
      "rewards/margins": 29.520708084106445,
      "rewards/rejected": -30.06192398071289,
      "step": 28
    },
    {
      "epoch": 0.4715447154471545,
      "grad_norm": 5.17633900187775e-08,
      "learning_rate": 0.00019681846633085967,
      "logits/chosen": -0.5973828434944153,
      "logits/rejected": -0.8376109600067139,
      "logps/chosen": -711.66259765625,
      "logps/rejected": -1186.1884765625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.467390537261963,
      "rewards/margins": 25.050704956054688,
      "rewards/rejected": -27.518096923828125,
      "step": 29
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 0.00011633769463514909,
      "learning_rate": 0.0001964767868814516,
      "logits/chosen": 1.3797093629837036,
      "logits/rejected": 1.5397391319274902,
      "logps/chosen": -877.42333984375,
      "logps/rejected": -1003.4732666015625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 4.624107360839844,
      "rewards/margins": 29.784557342529297,
      "rewards/rejected": -25.160449981689453,
      "step": 30
    },
    {
      "epoch": 0.5040650406504065,
      "grad_norm": 6.257723228486611e-09,
      "learning_rate": 0.00019611801152462715,
      "logits/chosen": 1.2731826305389404,
      "logits/rejected": 1.6379995346069336,
      "logps/chosen": -1053.573486328125,
      "logps/rejected": -1010.915283203125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 11.018058776855469,
      "rewards/margins": 32.15219497680664,
      "rewards/rejected": -21.13413429260254,
      "step": 31
    },
    {
      "epoch": 0.5203252032520326,
      "grad_norm": 0.00035472630406729877,
      "learning_rate": 0.00019574220383620055,
      "logits/chosen": 0.6649560928344727,
      "logits/rejected": 0.983564019203186,
      "logps/chosen": -872.1873168945312,
      "logps/rejected": -965.9480590820312,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 5.504961967468262,
      "rewards/margins": 23.669071197509766,
      "rewards/rejected": -18.164108276367188,
      "step": 32
    },
    {
      "epoch": 0.5365853658536586,
      "grad_norm": 3.0934195820009336e-05,
      "learning_rate": 0.00019534943041015423,
      "logits/chosen": 0.49574941396713257,
      "logits/rejected": 0.5190873742103577,
      "logps/chosen": -708.9269409179688,
      "logps/rejected": -842.974365234375,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 7.209194660186768,
      "rewards/margins": 20.690357208251953,
      "rewards/rejected": -13.48116397857666,
      "step": 33
    },
    {
      "epoch": 0.5528455284552846,
      "grad_norm": 0.0006856573163531721,
      "learning_rate": 0.00019493976084683813,
      "logits/chosen": 0.992796778678894,
      "logits/rejected": 1.1291236877441406,
      "logps/chosen": -673.6188354492188,
      "logps/rejected": -723.4482421875,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 5.3715057373046875,
      "rewards/margins": 19.963485717773438,
      "rewards/rejected": -14.591980934143066,
      "step": 34
    },
    {
      "epoch": 0.5691056910569106,
      "grad_norm": 5.983891969663091e-05,
      "learning_rate": 0.00019451326774063636,
      "logits/chosen": 0.7630600929260254,
      "logits/rejected": 0.910960853099823,
      "logps/chosen": -993.23828125,
      "logps/rejected": -1011.3184204101562,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 7.109509468078613,
      "rewards/margins": 24.603878021240234,
      "rewards/rejected": -17.494367599487305,
      "step": 35
    },
    {
      "epoch": 0.5853658536585366,
      "grad_norm": 1.9749455532291904e-05,
      "learning_rate": 0.00019407002666710336,
      "logits/chosen": 1.8401339054107666,
      "logits/rejected": 1.9955703020095825,
      "logps/chosen": -1152.950927734375,
      "logps/rejected": -827.0269775390625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 15.768245697021484,
      "rewards/margins": 38.1776123046875,
      "rewards/rejected": -22.40936851501465,
      "step": 36
    },
    {
      "epoch": 0.6016260162601627,
      "grad_norm": 0.0017285533249378204,
      "learning_rate": 0.00019361011616957164,
      "logits/chosen": 2.153351306915283,
      "logits/rejected": 2.235447883605957,
      "logps/chosen": -1090.1943359375,
      "logps/rejected": -682.7992553710938,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 11.726329803466797,
      "rewards/margins": 24.018630981445312,
      "rewards/rejected": -12.292303085327148,
      "step": 37
    },
    {
      "epoch": 0.6178861788617886,
      "grad_norm": 0.00919501855969429,
      "learning_rate": 0.00019313361774523385,
      "logits/chosen": 0.47314736247062683,
      "logits/rejected": 0.557833731174469,
      "logps/chosen": -691.4217529296875,
      "logps/rejected": -673.1847534179688,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 6.087795257568359,
      "rewards/margins": 12.628225326538086,
      "rewards/rejected": -6.540430068969727,
      "step": 38
    },
    {
      "epoch": 0.6341463414634146,
      "grad_norm": 0.002680833451449871,
      "learning_rate": 0.00019264061583070127,
      "logits/chosen": 0.20066705346107483,
      "logits/rejected": 0.2085224837064743,
      "logps/chosen": -693.7376098632812,
      "logps/rejected": -982.19091796875,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 7.779763221740723,
      "rewards/margins": 22.904094696044922,
      "rewards/rejected": -15.124334335327148,
      "step": 39
    },
    {
      "epoch": 0.6504065040650406,
      "grad_norm": 8.798202907200903e-05,
      "learning_rate": 0.00019213119778704128,
      "logits/chosen": 1.3898746967315674,
      "logits/rejected": 1.5520107746124268,
      "logps/chosen": -1247.770263671875,
      "logps/rejected": -916.4830322265625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 15.276836395263672,
      "rewards/margins": 34.69191360473633,
      "rewards/rejected": -19.415077209472656,
      "step": 40
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.0009758697124198079,
      "learning_rate": 0.00019160545388429708,
      "logits/chosen": 2.345059633255005,
      "logits/rejected": 2.5746054649353027,
      "logps/chosen": -1102.5548095703125,
      "logps/rejected": -722.4332885742188,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 13.800348281860352,
      "rewards/margins": 32.747169494628906,
      "rewards/rejected": -18.946823120117188,
      "step": 41
    },
    {
      "epoch": 0.6829268292682927,
      "grad_norm": 0.0016077810432761908,
      "learning_rate": 0.00019106347728549135,
      "logits/chosen": 0.9104095697402954,
      "logits/rejected": 0.9921329021453857,
      "logps/chosen": -753.8040771484375,
      "logps/rejected": -886.5813598632812,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 11.367500305175781,
      "rewards/margins": 27.856563568115234,
      "rewards/rejected": -16.489063262939453,
      "step": 42
    },
    {
      "epoch": 0.6991869918699187,
      "grad_norm": 0.0004074655589647591,
      "learning_rate": 0.0001905053640301176,
      "logits/chosen": 0.5256392955780029,
      "logits/rejected": 0.4733426570892334,
      "logps/chosen": -715.4669189453125,
      "logps/rejected": -565.0441284179688,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 6.25009822845459,
      "rewards/margins": 21.391075134277344,
      "rewards/rejected": -15.14097785949707,
      "step": 43
    },
    {
      "epoch": 0.7154471544715447,
      "grad_norm": 0.013145952485501766,
      "learning_rate": 0.00018993121301712193,
      "logits/chosen": 0.9358551502227783,
      "logits/rejected": 0.8306156992912292,
      "logps/chosen": -867.1063232421875,
      "logps/rejected": -973.7214965820312,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 7.3925018310546875,
      "rewards/margins": 21.35105323791504,
      "rewards/rejected": -13.958552360534668,
      "step": 44
    },
    {
      "epoch": 0.7317073170731707,
      "grad_norm": 8.829876605886966e-05,
      "learning_rate": 0.00018934112598737777,
      "logits/chosen": 2.2844998836517334,
      "logits/rejected": 2.831254482269287,
      "logps/chosen": -1142.8726806640625,
      "logps/rejected": -776.1110229492188,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 17.17538833618164,
      "rewards/margins": 33.72625732421875,
      "rewards/rejected": -16.550867080688477,
      "step": 45
    },
    {
      "epoch": 0.7479674796747967,
      "grad_norm": 0.02624354511499405,
      "learning_rate": 0.00018873520750565718,
      "logits/chosen": 0.1806122362613678,
      "logits/rejected": 0.31054702401161194,
      "logps/chosen": -692.7060546875,
      "logps/rejected": -1032.708740234375,
      "loss": 0.0001,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 6.434965133666992,
      "rewards/margins": 16.74932098388672,
      "rewards/rejected": -10.314356803894043,
      "step": 46
    },
    {
      "epoch": 0.7642276422764228,
      "grad_norm": 4.268178963684477e-05,
      "learning_rate": 0.00018811356494210165,
      "logits/chosen": 1.1679103374481201,
      "logits/rejected": 1.0418663024902344,
      "logps/chosen": -720.220703125,
      "logps/rejected": -911.58837890625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 7.991888523101807,
      "rewards/margins": 21.064565658569336,
      "rewards/rejected": -13.072675704956055,
      "step": 47
    },
    {
      "epoch": 0.7804878048780488,
      "grad_norm": 0.0009461237932555377,
      "learning_rate": 0.00018747630845319612,
      "logits/chosen": 0.13339552283287048,
      "logits/rejected": 0.3655449151992798,
      "logps/chosen": -420.11431884765625,
      "logps/rejected": -786.4783325195312,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 11.16606330871582,
      "rewards/margins": 30.41803741455078,
      "rewards/rejected": -19.251976013183594,
      "step": 48
    },
    {
      "epoch": 0.7967479674796748,
      "grad_norm": 0.0033115639816969633,
      "learning_rate": 0.00018682355096224872,
      "logits/chosen": 0.4472777247428894,
      "logits/rejected": 0.3390260934829712,
      "logps/chosen": -536.7960205078125,
      "logps/rejected": -901.3749389648438,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 10.887458801269531,
      "rewards/margins": 27.701595306396484,
      "rewards/rejected": -16.814136505126953,
      "step": 49
    },
    {
      "epoch": 0.8130081300813008,
      "grad_norm": 0.01153454091399908,
      "learning_rate": 0.0001861554081393806,
      "logits/chosen": 0.6489148139953613,
      "logits/rejected": 0.689254105091095,
      "logps/chosen": -738.5593872070312,
      "logps/rejected": -755.362060546875,
      "loss": 0.0001,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 10.205413818359375,
      "rewards/margins": 16.344358444213867,
      "rewards/rejected": -6.138944625854492,
      "step": 50
    },
    {
      "epoch": 0.8292682926829268,
      "grad_norm": 0.001985176932066679,
      "learning_rate": 0.00018547199838102904,
      "logits/chosen": 0.144524484872818,
      "logits/rejected": 0.26266002655029297,
      "logps/chosen": -893.19482421875,
      "logps/rejected": -1031.27294921875,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 9.087849617004395,
      "rewards/margins": 23.393884658813477,
      "rewards/rejected": -14.306035041809082,
      "step": 51
    },
    {
      "epoch": 0.8455284552845529,
      "grad_norm": 0.00042794409091584384,
      "learning_rate": 0.0001847734427889671,
      "logits/chosen": 0.5121033191680908,
      "logits/rejected": 1.0676312446594238,
      "logps/chosen": -987.8340454101562,
      "logps/rejected": -830.7366943359375,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 11.409669876098633,
      "rewards/margins": 19.569660186767578,
      "rewards/rejected": -8.159988403320312,
      "step": 52
    },
    {
      "epoch": 0.8617886178861789,
      "grad_norm": 0.0011688657104969025,
      "learning_rate": 0.00018405986514884434,
      "logits/chosen": 1.793473243713379,
      "logits/rejected": 1.9872632026672363,
      "logps/chosen": -926.424560546875,
      "logps/rejected": -618.4228515625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 11.011417388916016,
      "rewards/margins": 22.01776123046875,
      "rewards/rejected": -11.006343841552734,
      "step": 53
    },
    {
      "epoch": 0.8780487804878049,
      "grad_norm": 0.005157554987818003,
      "learning_rate": 0.0001833313919082515,
      "logits/chosen": -0.02910199761390686,
      "logits/rejected": 0.14243453741073608,
      "logps/chosen": -725.36376953125,
      "logps/rejected": -997.5311279296875,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 5.557222366333008,
      "rewards/margins": 15.359309196472168,
      "rewards/rejected": -9.802087783813477,
      "step": 54
    },
    {
      "epoch": 0.8943089430894309,
      "grad_norm": 0.005044507794082165,
      "learning_rate": 0.00018258815215431396,
      "logits/chosen": 0.17898443341255188,
      "logits/rejected": 0.09989897906780243,
      "logps/chosen": -803.9798583984375,
      "logps/rejected": -925.3179321289062,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 6.798739433288574,
      "rewards/margins": 17.492319107055664,
      "rewards/rejected": -10.69357967376709,
      "step": 55
    },
    {
      "epoch": 0.9105691056910569,
      "grad_norm": 0.0031374047975987196,
      "learning_rate": 0.0001818302775908169,
      "logits/chosen": 1.017639398574829,
      "logits/rejected": 1.2823631763458252,
      "logps/chosen": -824.6445922851562,
      "logps/rejected": -860.8942260742188,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 6.019498825073242,
      "rewards/margins": 16.16924285888672,
      "rewards/rejected": -10.149742126464844,
      "step": 56
    },
    {
      "epoch": 0.926829268292683,
      "grad_norm": 0.00014241511235013604,
      "learning_rate": 0.0001810579025148674,
      "logits/chosen": 1.0959478616714478,
      "logits/rejected": 0.9008815288543701,
      "logps/chosen": -782.0526123046875,
      "logps/rejected": -916.8338623046875,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 8.443077087402344,
      "rewards/margins": 24.263744354248047,
      "rewards/rejected": -15.820667266845703,
      "step": 57
    },
    {
      "epoch": 0.943089430894309,
      "grad_norm": 5.913816494285129e-05,
      "learning_rate": 0.00018027116379309638,
      "logits/chosen": 0.2709883153438568,
      "logits/rejected": 0.29769933223724365,
      "logps/chosen": -735.5257568359375,
      "logps/rejected": -1044.0601806640625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 8.65300178527832,
      "rewards/margins": 18.755083084106445,
      "rewards/rejected": -10.102080345153809,
      "step": 58
    },
    {
      "epoch": 0.959349593495935,
      "grad_norm": 0.01578771322965622,
      "learning_rate": 0.00017947020083740575,
      "logits/chosen": 1.5522100925445557,
      "logits/rejected": 1.7518442869186401,
      "logps/chosen": -1019.1099853515625,
      "logps/rejected": -624.6131591796875,
      "loss": 0.0001,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 10.32003402709961,
      "rewards/margins": 23.75770378112793,
      "rewards/rejected": -13.43766975402832,
      "step": 59
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 0.0010152229806408286,
      "learning_rate": 0.00017865515558026428,
      "logits/chosen": 0.8601479530334473,
      "logits/rejected": 0.819040060043335,
      "logps/chosen": -763.342041015625,
      "logps/rejected": -817.870849609375,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 8.2501859664917,
      "rewards/margins": 16.491539001464844,
      "rewards/rejected": -8.241353034973145,
      "step": 60
    },
    {
      "epoch": 0.991869918699187,
      "grad_norm": 0.008696873672306538,
      "learning_rate": 0.0001778261724495566,
      "logits/chosen": 0.7409014701843262,
      "logits/rejected": 0.9245580434799194,
      "logps/chosen": -888.8350830078125,
      "logps/rejected": -796.002685546875,
      "loss": 0.0001,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 11.07230281829834,
      "rewards/margins": 22.53582000732422,
      "rewards/rejected": -11.463518142700195,
      "step": 61
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.3132517526391894e-05,
      "learning_rate": 0.00017698339834299061,
      "logits/chosen": 0.962340772151947,
      "logits/rejected": 1.369040608406067,
      "logps/chosen": -843.8861083984375,
      "logps/rejected": -833.0137329101562,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 7.60971736907959,
      "rewards/margins": 22.649456024169922,
      "rewards/rejected": -15.039739608764648,
      "step": 62
    },
    {
      "epoch": 1.016260162601626,
      "grad_norm": 3.0814584306426696e-07,
      "learning_rate": 0.00017612698260206666,
      "logits/chosen": 1.7351003885269165,
      "logits/rejected": 2.39410400390625,
      "logps/chosen": -1081.0841064453125,
      "logps/rejected": -664.132080078125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 12.010480880737305,
      "rewards/margins": 23.851722717285156,
      "rewards/rejected": -11.841242790222168,
      "step": 63
    },
    {
      "epoch": 1.032520325203252,
      "grad_norm": 0.0014821357326582074,
      "learning_rate": 0.00017525707698561385,
      "logits/chosen": 0.8669869899749756,
      "logits/rejected": 1.2894644737243652,
      "logps/chosen": -794.047607421875,
      "logps/rejected": -812.5697631835938,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 11.141783714294434,
      "rewards/margins": 23.891061782836914,
      "rewards/rejected": -12.749277114868164,
      "step": 64
    },
    {
      "epoch": 1.048780487804878,
      "grad_norm": 0.002492019208148122,
      "learning_rate": 0.00017437383564289816,
      "logits/chosen": 1.1617192029953003,
      "logits/rejected": 1.0443211793899536,
      "logps/chosen": -706.7365112304688,
      "logps/rejected": -834.9153442382812,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 10.32893180847168,
      "rewards/margins": 23.380508422851562,
      "rewards/rejected": -13.0515775680542,
      "step": 65
    },
    {
      "epoch": 1.065040650406504,
      "grad_norm": 0.10320430248975754,
      "learning_rate": 0.00017347741508630672,
      "logits/chosen": 1.5734750032424927,
      "logits/rejected": 2.108652114868164,
      "logps/chosen": -919.78125,
      "logps/rejected": -843.049560546875,
      "loss": 0.0005,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 14.794572830200195,
      "rewards/margins": 27.74661636352539,
      "rewards/rejected": -12.952045440673828,
      "step": 66
    },
    {
      "epoch": 1.08130081300813,
      "grad_norm": 0.00033748566056601703,
      "learning_rate": 0.00017256797416361362,
      "logits/chosen": 0.10465478897094727,
      "logits/rejected": 0.11954197287559509,
      "logps/chosen": -770.0354614257812,
      "logps/rejected": -705.5811767578125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 8.188321113586426,
      "rewards/margins": 18.007652282714844,
      "rewards/rejected": -9.819330215454102,
      "step": 67
    },
    {
      "epoch": 1.0975609756097562,
      "grad_norm": 0.4934139549732208,
      "learning_rate": 0.00017164567402983152,
      "logits/chosen": 0.7908147573471069,
      "logits/rejected": 1.0772439241409302,
      "logps/chosen": -869.843017578125,
      "logps/rejected": -729.0626831054688,
      "loss": 0.0024,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 8.537101745605469,
      "rewards/margins": 12.491724014282227,
      "rewards/rejected": -3.9546217918395996,
      "step": 68
    },
    {
      "epoch": 1.113821138211382,
      "grad_norm": 2.1183014098369313e-07,
      "learning_rate": 0.00017071067811865476,
      "logits/chosen": 0.6217237710952759,
      "logits/rejected": 0.5386490225791931,
      "logps/chosen": -799.1664428710938,
      "logps/rejected": -820.0735473632812,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 12.295455932617188,
      "rewards/margins": 30.9702091217041,
      "rewards/rejected": -18.674753189086914,
      "step": 69
    },
    {
      "epoch": 1.1300813008130082,
      "grad_norm": 7.591093162773177e-05,
      "learning_rate": 0.0001697631521134985,
      "logits/chosen": 1.664866328239441,
      "logits/rejected": 1.980355978012085,
      "logps/chosen": -1113.451416015625,
      "logps/rejected": -825.9473876953125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 11.451591491699219,
      "rewards/margins": 29.68605613708496,
      "rewards/rejected": -18.23446273803711,
      "step": 70
    },
    {
      "epoch": 1.146341463414634,
      "grad_norm": 4.4439241264626617e-07,
      "learning_rate": 0.00016880326391813916,
      "logits/chosen": -0.02196294069290161,
      "logits/rejected": 0.18253503739833832,
      "logps/chosen": -661.0505981445312,
      "logps/rejected": -834.158203125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 9.791834831237793,
      "rewards/margins": 28.233205795288086,
      "rewards/rejected": -18.441370010375977,
      "step": 71
    },
    {
      "epoch": 1.1626016260162602,
      "grad_norm": 8.045230060815811e-05,
      "learning_rate": 0.00016783118362696163,
      "logits/chosen": 0.24465110898017883,
      "logits/rejected": 0.2313007265329361,
      "logps/chosen": -715.2831420898438,
      "logps/rejected": -1050.01171875,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 4.176504611968994,
      "rewards/margins": 19.875812530517578,
      "rewards/rejected": -15.699307441711426,
      "step": 72
    },
    {
      "epoch": 1.1788617886178863,
      "grad_norm": 5.927664005866973e-06,
      "learning_rate": 0.00016684708349481804,
      "logits/chosen": 1.5342342853546143,
      "logits/rejected": 2.0414443016052246,
      "logps/chosen": -1195.0989990234375,
      "logps/rejected": -652.9114990234375,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 8.883450508117676,
      "rewards/margins": 19.403560638427734,
      "rewards/rejected": -10.520109176635742,
      "step": 73
    },
    {
      "epoch": 1.1951219512195121,
      "grad_norm": 1.7679340089671314e-05,
      "learning_rate": 0.00016585113790650388,
      "logits/chosen": 0.13918209075927734,
      "logits/rejected": 0.21283580362796783,
      "logps/chosen": -937.8267211914062,
      "logps/rejected": -958.693115234375,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 9.578910827636719,
      "rewards/margins": 31.493125915527344,
      "rewards/rejected": -21.914215087890625,
      "step": 74
    },
    {
      "epoch": 1.2113821138211383,
      "grad_norm": 9.838218102231622e-05,
      "learning_rate": 0.00016484352334585653,
      "logits/chosen": 1.7902581691741943,
      "logits/rejected": 1.8008999824523926,
      "logps/chosen": -898.8333740234375,
      "logps/rejected": -869.8264770507812,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 8.36214828491211,
      "rewards/margins": 23.546051025390625,
      "rewards/rejected": -15.183902740478516,
      "step": 75
    },
    {
      "epoch": 1.2276422764227641,
      "grad_norm": 0.00042859543464146554,
      "learning_rate": 0.00016382441836448202,
      "logits/chosen": 0.40593788027763367,
      "logits/rejected": 0.24162518978118896,
      "logps/chosen": -713.95263671875,
      "logps/rejected": -873.909423828125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.870103359222412,
      "rewards/margins": 17.166872024536133,
      "rewards/rejected": -13.296768188476562,
      "step": 76
    },
    {
      "epoch": 1.2439024390243902,
      "grad_norm": 0.0007489994168281555,
      "learning_rate": 0.0001627940035501152,
      "logits/chosen": 1.2316575050354004,
      "logits/rejected": 1.2072526216506958,
      "logps/chosen": -961.4344482421875,
      "logps/rejected": -1073.3685302734375,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 6.6541852951049805,
      "rewards/margins": 27.57451057434082,
      "rewards/rejected": -20.920326232910156,
      "step": 77
    },
    {
      "epoch": 1.2601626016260163,
      "grad_norm": 3.269678200013004e-05,
      "learning_rate": 0.0001617524614946192,
      "logits/chosen": 0.06140974164009094,
      "logits/rejected": 0.11881747841835022,
      "logps/chosen": -900.48876953125,
      "logps/rejected": -1085.7061767578125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.6411392688751221,
      "rewards/margins": 19.955745697021484,
      "rewards/rejected": -19.314605712890625,
      "step": 78
    },
    {
      "epoch": 1.2764227642276422,
      "grad_norm": 3.813441480815527e-06,
      "learning_rate": 0.0001606999767616298,
      "logits/chosen": 1.1457127332687378,
      "logits/rejected": 0.8977339267730713,
      "logps/chosen": -757.8355712890625,
      "logps/rejected": -838.0936279296875,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 8.651698112487793,
      "rewards/margins": 31.715707778930664,
      "rewards/rejected": -23.064010620117188,
      "step": 79
    },
    {
      "epoch": 1.2926829268292683,
      "grad_norm": 2.5300651032011956e-05,
      "learning_rate": 0.00015963673585385016,
      "logits/chosen": -0.5050560235977173,
      "logits/rejected": -0.5818659067153931,
      "logps/chosen": -833.4871826171875,
      "logps/rejected": -1177.144287109375,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.1878601312637329,
      "rewards/margins": 28.51848602294922,
      "rewards/rejected": -28.330625534057617,
      "step": 80
    },
    {
      "epoch": 1.3089430894308944,
      "grad_norm": 6.81912133586593e-05,
      "learning_rate": 0.00015856292718000235,
      "logits/chosen": 1.6245973110198975,
      "logits/rejected": 1.942758560180664,
      "logps/chosen": -925.15966796875,
      "logps/rejected": -746.8193969726562,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 9.29654598236084,
      "rewards/margins": 26.77484893798828,
      "rewards/rejected": -17.478303909301758,
      "step": 81
    },
    {
      "epoch": 1.3252032520325203,
      "grad_norm": 1.1350484783179127e-06,
      "learning_rate": 0.0001574787410214407,
      "logits/chosen": 0.8831353187561035,
      "logits/rejected": 1.1747808456420898,
      "logps/chosen": -812.7021484375,
      "logps/rejected": -1058.893310546875,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.832669258117676,
      "rewards/margins": 33.81871795654297,
      "rewards/rejected": -29.986047744750977,
      "step": 82
    },
    {
      "epoch": 1.3414634146341464,
      "grad_norm": 7.43222301480273e-07,
      "learning_rate": 0.0001563843694984336,
      "logits/chosen": 1.199593424797058,
      "logits/rejected": 1.2259372472763062,
      "logps/chosen": -846.8779296875,
      "logps/rejected": -1035.00244140625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 4.645470142364502,
      "rewards/margins": 35.18595886230469,
      "rewards/rejected": -30.540489196777344,
      "step": 83
    },
    {
      "epoch": 1.3577235772357723,
      "grad_norm": 4.4819596951128915e-05,
      "learning_rate": 0.00015528000653611935,
      "logits/chosen": 1.7928721904754639,
      "logits/rejected": 2.1661128997802734,
      "logps/chosen": -932.3726806640625,
      "logps/rejected": -844.2169189453125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 4.103044509887695,
      "rewards/margins": 21.569711685180664,
      "rewards/rejected": -17.4666690826416,
      "step": 84
    },
    {
      "epoch": 1.3739837398373984,
      "grad_norm": 7.042069594120903e-09,
      "learning_rate": 0.0001541658478301421,
      "logits/chosen": 0.2531038522720337,
      "logits/rejected": 0.2639998197555542,
      "logps/chosen": -1010.8427734375,
      "logps/rejected": -1247.974609375,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.7464678287506104,
      "rewards/margins": 30.038406372070312,
      "rewards/rejected": -29.291942596435547,
      "step": 85
    },
    {
      "epoch": 1.3902439024390243,
      "grad_norm": 2.4762075057083166e-08,
      "learning_rate": 0.00015304209081197425,
      "logits/chosen": 2.228158473968506,
      "logits/rejected": 2.7146129608154297,
      "logps/chosen": -1221.494384765625,
      "logps/rejected": -882.4944458007812,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 13.98241901397705,
      "rewards/margins": 33.62451171875,
      "rewards/rejected": -19.642091751098633,
      "step": 86
    },
    {
      "epoch": 1.4065040650406504,
      "grad_norm": 3.7480401715583866e-06,
      "learning_rate": 0.00015190893461393108,
      "logits/chosen": 1.5811924934387207,
      "logits/rejected": 2.0754153728485107,
      "logps/chosen": -958.1056518554688,
      "logps/rejected": -741.9910278320312,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 14.536327362060547,
      "rewards/margins": 32.516456604003906,
      "rewards/rejected": -17.980131149291992,
      "step": 87
    },
    {
      "epoch": 1.4227642276422765,
      "grad_norm": 1.9098067696177168e-06,
      "learning_rate": 0.000150766580033884,
      "logits/chosen": 1.6907765865325928,
      "logits/rejected": 1.9654494524002075,
      "logps/chosen": -1132.77978515625,
      "logps/rejected": -908.571044921875,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 5.22573709487915,
      "rewards/margins": 34.5124626159668,
      "rewards/rejected": -29.286724090576172,
      "step": 88
    },
    {
      "epoch": 1.4390243902439024,
      "grad_norm": 1.1447126780694816e-05,
      "learning_rate": 0.00014961522949967886,
      "logits/chosen": 0.9937865734100342,
      "logits/rejected": 1.2049672603607178,
      "logps/chosen": -739.3209838867188,
      "logps/rejected": -1007.2611083984375,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 10.235821723937988,
      "rewards/margins": 34.75508499145508,
      "rewards/rejected": -24.51926040649414,
      "step": 89
    },
    {
      "epoch": 1.4552845528455285,
      "grad_norm": 1.5996234026260936e-07,
      "learning_rate": 0.00014845508703326504,
      "logits/chosen": 1.005773663520813,
      "logits/rejected": 0.9975143671035767,
      "logps/chosen": -912.9910278320312,
      "logps/rejected": -1205.926513671875,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.948190212249756,
      "rewards/margins": 31.25839614868164,
      "rewards/rejected": -28.310203552246094,
      "step": 90
    },
    {
      "epoch": 1.4715447154471546,
      "grad_norm": 1.9003784473170526e-05,
      "learning_rate": 0.00014728635821454255,
      "logits/chosen": 2.574889659881592,
      "logits/rejected": 2.5759711265563965,
      "logps/chosen": -915.0121459960938,
      "logps/rejected": -623.8654174804688,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 15.099142074584961,
      "rewards/margins": 31.881959915161133,
      "rewards/rejected": -16.782817840576172,
      "step": 91
    },
    {
      "epoch": 1.4878048780487805,
      "grad_norm": 4.1650441318097364e-08,
      "learning_rate": 0.0001461092501449326,
      "logits/chosen": 1.0031987428665161,
      "logits/rejected": 1.2941582202911377,
      "logps/chosen": -823.1492309570312,
      "logps/rejected": -1055.567626953125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.4376673698425293,
      "rewards/margins": 26.05483055114746,
      "rewards/rejected": -23.617162704467773,
      "step": 92
    },
    {
      "epoch": 1.5040650406504064,
      "grad_norm": 4.165614697626552e-08,
      "learning_rate": 0.00014492397141067887,
      "logits/chosen": 0.8133536577224731,
      "logits/rejected": 1.0407506227493286,
      "logps/chosen": -961.2422485351562,
      "logps/rejected": -1156.6856689453125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.8701601028442383,
      "rewards/margins": 33.655277252197266,
      "rewards/rejected": -31.785114288330078,
      "step": 93
    },
    {
      "epoch": 1.5203252032520327,
      "grad_norm": 3.824939540209016e-06,
      "learning_rate": 0.00014373073204588556,
      "logits/chosen": 2.6779818534851074,
      "logits/rejected": 2.7686123847961426,
      "logps/chosen": -1121.3564453125,
      "logps/rejected": -698.586669921875,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 10.171032905578613,
      "rewards/margins": 27.788890838623047,
      "rewards/rejected": -17.617855072021484,
      "step": 94
    },
    {
      "epoch": 1.5365853658536586,
      "grad_norm": 3.954168641939759e-05,
      "learning_rate": 0.0001425297434952987,
      "logits/chosen": 0.22321929037570953,
      "logits/rejected": 0.2271191030740738,
      "logps/chosen": -671.6175537109375,
      "logps/rejected": -1141.6953125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.185655355453491,
      "rewards/margins": 26.3375301361084,
      "rewards/rejected": -28.52318572998047,
      "step": 95
    },
    {
      "epoch": 1.5528455284552845,
      "grad_norm": 6.408844566152538e-10,
      "learning_rate": 0.00014132121857683783,
      "logits/chosen": 1.1100516319274902,
      "logits/rejected": 1.0310027599334717,
      "logps/chosen": -995.9828491210938,
      "logps/rejected": -1024.00244140625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 8.543378829956055,
      "rewards/margins": 33.411643981933594,
      "rewards/rejected": -24.868263244628906,
      "step": 96
    },
    {
      "epoch": 1.5691056910569106,
      "grad_norm": 6.710484399263805e-07,
      "learning_rate": 0.00014010537144388416,
      "logits/chosen": 0.19941049814224243,
      "logits/rejected": 0.2904074490070343,
      "logps/chosen": -580.1328125,
      "logps/rejected": -1122.187744140625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -0.563772439956665,
      "rewards/margins": 23.33687400817871,
      "rewards/rejected": -23.900646209716797,
      "step": 97
    },
    {
      "epoch": 1.5853658536585367,
      "grad_norm": 2.6136473252336145e-07,
      "learning_rate": 0.00013888241754733208,
      "logits/chosen": 0.8143081665039062,
      "logits/rejected": 1.183271050453186,
      "logps/chosen": -973.23583984375,
      "logps/rejected": -904.20556640625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.3894622325897217,
      "rewards/margins": 23.915855407714844,
      "rewards/rejected": -20.526391983032227,
      "step": 98
    },
    {
      "epoch": 1.6016260162601625,
      "grad_norm": 1.735031582938973e-05,
      "learning_rate": 0.00013765257359741063,
      "logits/chosen": 0.8897725343704224,
      "logits/rejected": 0.8052040338516235,
      "logps/chosen": -771.9832763671875,
      "logps/rejected": -874.3773193359375,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 6.943796157836914,
      "rewards/margins": 29.497058868408203,
      "rewards/rejected": -22.55326271057129,
      "step": 99
    },
    {
      "epoch": 1.6178861788617886,
      "grad_norm": 1.2570103535836097e-07,
      "learning_rate": 0.00013641605752528224,
      "logits/chosen": 1.0415421724319458,
      "logits/rejected": 1.3014307022094727,
      "logps/chosen": -918.8525390625,
      "logps/rejected": -955.0538330078125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 7.44915771484375,
      "rewards/margins": 33.4973258972168,
      "rewards/rejected": -26.04817008972168,
      "step": 100
    },
    {
      "epoch": 1.6341463414634148,
      "grad_norm": 3.719053154327412e-07,
      "learning_rate": 0.0001351730884444245,
      "logits/chosen": 0.4167521595954895,
      "logits/rejected": 0.3483416438102722,
      "logps/chosen": -604.3650512695312,
      "logps/rejected": -1362.02587890625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.4617691040039062,
      "rewards/margins": 44.77275466918945,
      "rewards/rejected": -47.23452377319336,
      "step": 101
    },
    {
      "epoch": 1.6504065040650406,
      "grad_norm": 1.487089633656069e-07,
      "learning_rate": 0.00013392388661180303,
      "logits/chosen": 0.9698238968849182,
      "logits/rejected": 1.1324440240859985,
      "logps/chosen": -742.9386596679688,
      "logps/rejected": -905.581298828125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 5.503021717071533,
      "rewards/margins": 32.864501953125,
      "rewards/rejected": -27.361482620239258,
      "step": 102
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.00015168750542216003,
      "learning_rate": 0.0001326686733888413,
      "logits/chosen": 2.734503746032715,
      "logits/rejected": 2.7868616580963135,
      "logps/chosen": -845.9635009765625,
      "logps/rejected": -674.9261474609375,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 6.455021858215332,
      "rewards/margins": 21.768619537353516,
      "rewards/rejected": -15.3135986328125,
      "step": 103
    },
    {
      "epoch": 1.6829268292682928,
      "grad_norm": 5.236762717686361e-06,
      "learning_rate": 0.0001314076712021949,
      "logits/chosen": 0.8474237322807312,
      "logits/rejected": 1.0795999765396118,
      "logps/chosen": -844.8881225585938,
      "logps/rejected": -1026.413818359375,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 9.01052474975586,
      "rewards/margins": 34.12953186035156,
      "rewards/rejected": -25.119007110595703,
      "step": 104
    },
    {
      "epoch": 1.6991869918699187,
      "grad_norm": 4.3044991571150604e-08,
      "learning_rate": 0.000130141103504337,
      "logits/chosen": 1.0104427337646484,
      "logits/rejected": 0.809540867805481,
      "logps/chosen": -806.0650634765625,
      "logps/rejected": -1019.7612915039062,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 7.093156814575195,
      "rewards/margins": 29.144248962402344,
      "rewards/rejected": -22.051090240478516,
      "step": 105
    },
    {
      "epoch": 1.7154471544715446,
      "grad_norm": 6.236035243745164e-09,
      "learning_rate": 0.0001288691947339621,
      "logits/chosen": 0.26283663511276245,
      "logits/rejected": 0.21620601415634155,
      "logps/chosen": -764.7117919921875,
      "logps/rejected": -1384.037353515625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -0.5661294460296631,
      "rewards/margins": 35.904212951660156,
      "rewards/rejected": -36.470340728759766,
      "step": 106
    },
    {
      "epoch": 1.7317073170731707,
      "grad_norm": 0.0002312189608346671,
      "learning_rate": 0.00012759217027621505,
      "logits/chosen": 0.8271576166152954,
      "logits/rejected": 0.8352835178375244,
      "logps/chosen": -639.9276123046875,
      "logps/rejected": -721.3944702148438,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.1902108192443848,
      "rewards/margins": 19.32707977294922,
      "rewards/rejected": -16.13686752319336,
      "step": 107
    },
    {
      "epoch": 1.7479674796747968,
      "grad_norm": 5.53435963723814e-09,
      "learning_rate": 0.00012631025642275212,
      "logits/chosen": 0.9540997743606567,
      "logits/rejected": 1.0216646194458008,
      "logps/chosen": -920.1544189453125,
      "logps/rejected": -919.189453125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 8.917628288269043,
      "rewards/margins": 31.62308692932129,
      "rewards/rejected": -22.705459594726562,
      "step": 108
    },
    {
      "epoch": 1.7642276422764227,
      "grad_norm": 5.7604488290508016e-08,
      "learning_rate": 0.00012502368033164176,
      "logits/chosen": 1.9378834962844849,
      "logits/rejected": 2.0527262687683105,
      "logps/chosen": -616.1436767578125,
      "logps/rejected": -781.5704956054688,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 4.269429683685303,
      "rewards/margins": 27.761857986450195,
      "rewards/rejected": -23.492429733276367,
      "step": 109
    },
    {
      "epoch": 1.7804878048780488,
      "grad_norm": 3.0333463740817024e-08,
      "learning_rate": 0.0001237326699871115,
      "logits/chosen": 0.784665584564209,
      "logits/rejected": 1.0081039667129517,
      "logps/chosen": -864.7948608398438,
      "logps/rejected": -946.906982421875,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 6.097116470336914,
      "rewards/margins": 30.87978172302246,
      "rewards/rejected": -24.78266716003418,
      "step": 110
    },
    {
      "epoch": 1.796747967479675,
      "grad_norm": 3.1582476367475465e-07,
      "learning_rate": 0.00012243745415914883,
      "logits/chosen": -0.5353690385818481,
      "logits/rejected": -0.6592149138450623,
      "logps/chosen": -722.5419921875,
      "logps/rejected": -1070.7403564453125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -1.3367981910705566,
      "rewards/margins": 27.85375213623047,
      "rewards/rejected": -29.190549850463867,
      "step": 111
    },
    {
      "epoch": 1.8130081300813008,
      "grad_norm": 2.334864745989762e-07,
      "learning_rate": 0.00012113826236296244,
      "logits/chosen": 1.986028790473938,
      "logits/rejected": 2.0000312328338623,
      "logps/chosen": -1034.116455078125,
      "logps/rejected": -924.2823486328125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 9.337306022644043,
      "rewards/margins": 34.88032531738281,
      "rewards/rejected": -25.54302215576172,
      "step": 112
    },
    {
      "epoch": 1.8292682926829267,
      "grad_norm": 1.956110463652294e-05,
      "learning_rate": 0.0001198353248183118,
      "logits/chosen": 1.1676946878433228,
      "logits/rejected": 1.3392938375473022,
      "logps/chosen": -839.8267211914062,
      "logps/rejected": -966.1685180664062,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 4.940967082977295,
      "rewards/margins": 33.268653869628906,
      "rewards/rejected": -28.327686309814453,
      "step": 113
    },
    {
      "epoch": 1.845528455284553,
      "grad_norm": 1.2582788144754886e-07,
      "learning_rate": 0.00011852887240871145,
      "logits/chosen": 1.7121946811676025,
      "logits/rejected": 1.834307074546814,
      "logps/chosen": -825.6591796875,
      "logps/rejected": -910.5638427734375,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 5.057826519012451,
      "rewards/margins": 26.722637176513672,
      "rewards/rejected": -21.664812088012695,
      "step": 114
    },
    {
      "epoch": 1.8617886178861789,
      "grad_norm": 3.8171506275830325e-06,
      "learning_rate": 0.00011721913664051813,
      "logits/chosen": 0.09213051199913025,
      "logits/rejected": 0.2805327773094177,
      "logps/chosen": -785.7156982421875,
      "logps/rejected": -1021.4864501953125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.823834240436554,
      "rewards/margins": 25.152664184570312,
      "rewards/rejected": -24.32883071899414,
      "step": 115
    },
    {
      "epoch": 1.8780487804878048,
      "grad_norm": 2.6529932029006886e-08,
      "learning_rate": 0.00011590634960190721,
      "logits/chosen": -0.5069230198860168,
      "logits/rejected": -0.5888826847076416,
      "logps/chosen": -707.7698974609375,
      "logps/rejected": -1266.01904296875,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.027275919914245605,
      "rewards/margins": 27.478078842163086,
      "rewards/rejected": -27.450803756713867,
      "step": 116
    },
    {
      "epoch": 1.8943089430894309,
      "grad_norm": 9.935014304573997e-07,
      "learning_rate": 0.00011459074392174618,
      "logits/chosen": 1.5636107921600342,
      "logits/rejected": 1.8575186729431152,
      "logps/chosen": -1191.93359375,
      "logps/rejected": -990.843505859375,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 12.92037582397461,
      "rewards/margins": 39.89407730102539,
      "rewards/rejected": -26.973697662353516,
      "step": 117
    },
    {
      "epoch": 1.910569105691057,
      "grad_norm": 1.2037819942634087e-05,
      "learning_rate": 0.00011327255272837221,
      "logits/chosen": 1.0499224662780762,
      "logits/rejected": 0.9787989854812622,
      "logps/chosen": -971.0214233398438,
      "logps/rejected": -877.3848876953125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.003582715988159,
      "rewards/margins": 20.236526489257812,
      "rewards/rejected": -18.23294448852539,
      "step": 118
    },
    {
      "epoch": 1.9268292682926829,
      "grad_norm": 1.8166872450819938e-06,
      "learning_rate": 0.00011195200960828139,
      "logits/chosen": 1.6961169242858887,
      "logits/rejected": 2.2738733291625977,
      "logps/chosen": -1074.953369140625,
      "logps/rejected": -778.5762939453125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 8.411404609680176,
      "rewards/margins": 25.984111785888672,
      "rewards/rejected": -17.57270622253418,
      "step": 119
    },
    {
      "epoch": 1.943089430894309,
      "grad_norm": 0.002434302121400833,
      "learning_rate": 0.00011062934856473655,
      "logits/chosen": 0.24992449581623077,
      "logits/rejected": 0.18503600358963013,
      "logps/chosen": -811.4505615234375,
      "logps/rejected": -1088.271240234375,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.826874017715454,
      "rewards/margins": 32.1160888671875,
      "rewards/rejected": -29.289215087890625,
      "step": 120
    },
    {
      "epoch": 1.959349593495935,
      "grad_norm": 3.818647797970698e-08,
      "learning_rate": 0.00010930480397630145,
      "logits/chosen": 1.889555811882019,
      "logits/rejected": 2.055070400238037,
      "logps/chosen": -1008.6806640625,
      "logps/rejected": -997.8306884765625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 4.727387428283691,
      "rewards/margins": 32.15311813354492,
      "rewards/rejected": -27.42573356628418,
      "step": 121
    },
    {
      "epoch": 1.975609756097561,
      "grad_norm": 4.203374359690315e-08,
      "learning_rate": 0.00010797861055530831,
      "logits/chosen": 0.33176711201667786,
      "logits/rejected": 0.2883341312408447,
      "logps/chosen": -764.9257202148438,
      "logps/rejected": -1157.33642578125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -0.931965708732605,
      "rewards/margins": 29.445417404174805,
      "rewards/rejected": -30.377384185791016,
      "step": 122
    },
    {
      "epoch": 1.9918699186991868,
      "grad_norm": 0.0003661888767965138,
      "learning_rate": 0.00010665100330626625,
      "logits/chosen": 2.023690700531006,
      "logits/rejected": 2.543468475341797,
      "logps/chosen": -1341.046875,
      "logps/rejected": -852.0292358398438,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 13.60735034942627,
      "rewards/margins": 33.2912483215332,
      "rewards/rejected": -19.68389892578125,
      "step": 123
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.4813576854066923e-07,
      "learning_rate": 0.00010532221748421787,
      "logits/chosen": 2.4457969665527344,
      "logits/rejected": 2.6656110286712646,
      "logps/chosen": -1094.49560546875,
      "logps/rejected": -546.4738159179688,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 12.480463027954102,
      "rewards/margins": 21.069480895996094,
      "rewards/rejected": -8.589018821716309,
      "step": 124
    }
  ],
  "logging_steps": 1,
  "max_steps": 246,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 62,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}