checkpoint-450/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3867640739149119,
  "eval_steps": 50,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008594757198109154,
      "grad_norm": 0.06708361208438873,
      "learning_rate": 4.999451708687114e-06,
      "logits/chosen": 14.524938583374023,
      "logits/rejected": 14.82593822479248,
      "logps/chosen": -0.31433865427970886,
      "logps/rejected": -0.32406437397003174,
      "loss": 0.9442,
      "rewards/accuracies": 0.4124999940395355,
      "rewards/chosen": -0.4715079367160797,
      "rewards/margins": 0.014588532969355583,
      "rewards/rejected": -0.48609647154808044,
      "step": 10
    },
    {
      "epoch": 0.017189514396218308,
      "grad_norm": 0.056814808398485184,
      "learning_rate": 4.997807075247147e-06,
      "logits/chosen": 14.309213638305664,
      "logits/rejected": 14.978128433227539,
      "logps/chosen": -0.31283506751060486,
      "logps/rejected": -0.3911947011947632,
      "loss": 0.928,
      "rewards/accuracies": 0.550000011920929,
      "rewards/chosen": -0.46925264596939087,
      "rewards/margins": 0.1175394207239151,
      "rewards/rejected": -0.5867919921875,
      "step": 20
    },
    {
      "epoch": 0.02578427159432746,
      "grad_norm": 0.061199307441711426,
      "learning_rate": 4.9950668210706795e-06,
      "logits/chosen": 14.68384075164795,
      "logits/rejected": 15.338122367858887,
      "logps/chosen": -0.3007296621799469,
      "logps/rejected": -0.3204456865787506,
      "loss": 0.9439,
      "rewards/accuracies": 0.4375,
      "rewards/chosen": -0.45109447836875916,
      "rewards/margins": 0.029573997482657433,
      "rewards/rejected": -0.48066848516464233,
      "step": 30
    },
    {
      "epoch": 0.034379028792436615,
      "grad_norm": 0.08423774689435959,
      "learning_rate": 4.9912321481237616e-06,
      "logits/chosen": 14.39265251159668,
      "logits/rejected": 15.059102058410645,
      "logps/chosen": -0.28216058015823364,
      "logps/rejected": -0.33495840430259705,
      "loss": 0.9184,
      "rewards/accuracies": 0.4124999940395355,
      "rewards/chosen": -0.42324090003967285,
      "rewards/margins": 0.07919676601886749,
      "rewards/rejected": -0.5024376511573792,
      "step": 40
    },
    {
      "epoch": 0.042973785990545764,
      "grad_norm": 0.06052614375948906,
      "learning_rate": 4.986304738420684e-06,
      "logits/chosen": 14.383735656738281,
      "logits/rejected": 15.029413223266602,
      "logps/chosen": -0.27970507740974426,
      "logps/rejected": -0.33213528990745544,
      "loss": 0.9317,
      "rewards/accuracies": 0.5249999761581421,
      "rewards/chosen": -0.4195576310157776,
      "rewards/margins": 0.07864536345005035,
      "rewards/rejected": -0.49820294976234436,
      "step": 50
    },
    {
      "epoch": 0.042973785990545764,
      "eval_logits/chosen": 14.424538612365723,
      "eval_logits/rejected": 15.006633758544922,
      "eval_logps/chosen": -0.2923925220966339,
      "eval_logps/rejected": -0.3531996011734009,
      "eval_loss": 0.9324354529380798,
      "eval_rewards/accuracies": 0.5052631497383118,
      "eval_rewards/chosen": -0.43858882784843445,
      "eval_rewards/margins": 0.09121060371398926,
      "eval_rewards/rejected": -0.5297994017601013,
      "eval_runtime": 26.3759,
      "eval_samples_per_second": 28.549,
      "eval_steps_per_second": 3.602,
      "step": 50
    },
    {
      "epoch": 0.05156854318865492,
      "grad_norm": 0.06899414211511612,
      "learning_rate": 4.980286753286196e-06,
      "logits/chosen": 14.888933181762695,
      "logits/rejected": 15.33955192565918,
      "logps/chosen": -0.2886829972267151,
      "logps/rejected": -0.34016504883766174,
      "loss": 0.9323,
      "rewards/accuracies": 0.5,
      "rewards/chosen": -0.43302449584007263,
      "rewards/margins": 0.07722309231758118,
      "rewards/rejected": -0.5102475881576538,
      "step": 60
    },
    {
      "epoch": 0.060163300386764075,
      "grad_norm": 0.06679105013608932,
      "learning_rate": 4.973180832407471e-06,
      "logits/chosen": 14.721624374389648,
      "logits/rejected": 15.614666938781738,
      "logps/chosen": -0.29435139894485474,
      "logps/rejected": -0.38699784874916077,
      "loss": 0.9172,
      "rewards/accuracies": 0.48750001192092896,
      "rewards/chosen": -0.4415270686149597,
      "rewards/margins": 0.13896968960762024,
      "rewards/rejected": -0.5804967880249023,
      "step": 70
    },
    {
      "epoch": 0.06875805758487323,
      "grad_norm": 0.07169903814792633,
      "learning_rate": 4.964990092676263e-06,
      "logits/chosen": 13.848808288574219,
      "logits/rejected": 14.609800338745117,
      "logps/chosen": -0.26156893372535706,
      "logps/rejected": -0.33030644059181213,
      "loss": 0.9245,
      "rewards/accuracies": 0.48750001192092896,
      "rewards/chosen": -0.3923533856868744,
      "rewards/margins": 0.10310628265142441,
      "rewards/rejected": -0.495459645986557,
      "step": 80
    },
    {
      "epoch": 0.07735281478298238,
      "grad_norm": 0.06593246012926102,
      "learning_rate": 4.9557181268217225e-06,
      "logits/chosen": 14.603567123413086,
      "logits/rejected": 14.994171142578125,
      "logps/chosen": -0.3191321790218353,
      "logps/rejected": -0.3477073311805725,
      "loss": 0.9359,
      "rewards/accuracies": 0.5,
      "rewards/chosen": -0.4786983132362366,
      "rewards/margins": 0.042862698435783386,
      "rewards/rejected": -0.5215609669685364,
      "step": 90
    },
    {
      "epoch": 0.08594757198109153,
      "grad_norm": 0.0718066617846489,
      "learning_rate": 4.9453690018345144e-06,
      "logits/chosen": 13.928094863891602,
      "logits/rejected": 14.792709350585938,
      "logps/chosen": -0.24115696549415588,
      "logps/rejected": -0.3537539839744568,
      "loss": 0.9066,
      "rewards/accuracies": 0.5874999761581421,
      "rewards/chosen": -0.3617354929447174,
      "rewards/margins": 0.16889554262161255,
      "rewards/rejected": -0.5306310653686523,
      "step": 100
    },
    {
      "epoch": 0.08594757198109153,
      "eval_logits/chosen": 14.40036392211914,
      "eval_logits/rejected": 14.97786808013916,
      "eval_logps/chosen": -0.2777771055698395,
      "eval_logps/rejected": -0.3516874611377716,
      "eval_loss": 0.9236211180686951,
      "eval_rewards/accuracies": 0.5052631497383118,
      "eval_rewards/chosen": -0.4166657328605652,
      "eval_rewards/margins": 0.11086549609899521,
      "eval_rewards/rejected": -0.5275312066078186,
      "eval_runtime": 25.8056,
      "eval_samples_per_second": 29.18,
      "eval_steps_per_second": 3.681,
      "step": 100
    },
    {
      "epoch": 0.09454232917920069,
      "grad_norm": 0.06681054830551147,
      "learning_rate": 4.933947257182901e-06,
      "logits/chosen": 14.76116943359375,
      "logits/rejected": 15.001077651977539,
      "logps/chosen": -0.297056645154953,
      "logps/rejected": -0.3221590518951416,
      "loss": 0.929,
      "rewards/accuracies": 0.44999998807907104,
      "rewards/chosen": -0.4455850124359131,
      "rewards/margins": 0.03765357658267021,
      "rewards/rejected": -0.4832385182380676,
      "step": 110
    },
    {
      "epoch": 0.10313708637730984,
      "grad_norm": 0.10024584829807281,
      "learning_rate": 4.921457902821578e-06,
      "logits/chosen": 14.405306816101074,
      "logits/rejected": 15.084524154663086,
      "logps/chosen": -0.2726767361164093,
      "logps/rejected": -0.3543504774570465,
      "loss": 0.9299,
      "rewards/accuracies": 0.5874999761581421,
      "rewards/chosen": -0.40901508927345276,
      "rewards/margins": 0.12251058965921402,
      "rewards/rejected": -0.531525731086731,
      "step": 120
    },
    {
      "epoch": 0.11173184357541899,
      "grad_norm": 0.08629737794399261,
      "learning_rate": 4.907906416994146e-06,
      "logits/chosen": 14.073992729187012,
      "logits/rejected": 14.882128715515137,
      "logps/chosen": -0.2827032506465912,
      "logps/rejected": -0.369393527507782,
      "loss": 0.9109,
      "rewards/accuracies": 0.5375000238418579,
      "rewards/chosen": -0.42405492067337036,
      "rewards/margins": 0.13003548979759216,
      "rewards/rejected": -0.5540903806686401,
      "step": 130
    },
    {
      "epoch": 0.12032660077352815,
      "grad_norm": 0.07973086833953857,
      "learning_rate": 4.893298743830168e-06,
      "logits/chosen": 13.96656322479248,
      "logits/rejected": 14.639463424682617,
      "logps/chosen": -0.28426361083984375,
      "logps/rejected": -0.3899250030517578,
      "loss": 0.9138,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": -0.4263954162597656,
      "rewards/margins": 0.1584920585155487,
      "rewards/rejected": -0.5848874449729919,
      "step": 140
    },
    {
      "epoch": 0.1289213579716373,
      "grad_norm": 0.08767445385456085,
      "learning_rate": 4.8776412907378845e-06,
      "logits/chosen": 13.705177307128906,
      "logits/rejected": 14.19865608215332,
      "logps/chosen": -0.26735779643058777,
      "logps/rejected": -0.34726911783218384,
      "loss": 0.9157,
      "rewards/accuracies": 0.574999988079071,
      "rewards/chosen": -0.40103667974472046,
      "rewards/margins": 0.1198669821023941,
      "rewards/rejected": -0.5209037065505981,
      "step": 150
    },
    {
      "epoch": 0.1289213579716373,
      "eval_logits/chosen": 13.20260238647461,
      "eval_logits/rejected": 13.959339141845703,
      "eval_logps/chosen": -0.27623170614242554,
      "eval_logps/rejected": -0.3724917769432068,
      "eval_loss": 0.909102737903595,
      "eval_rewards/accuracies": 0.557894766330719,
      "eval_rewards/chosen": -0.4143475592136383,
      "eval_rewards/margins": 0.14439010620117188,
      "eval_rewards/rejected": -0.5587376356124878,
      "eval_runtime": 25.7839,
      "eval_samples_per_second": 29.204,
      "eval_steps_per_second": 3.684,
      "step": 150
    },
    {
      "epoch": 0.13751611516974646,
      "grad_norm": 0.09749539196491241,
      "learning_rate": 4.860940925593703e-06,
      "logits/chosen": 13.301411628723145,
      "logits/rejected": 14.054819107055664,
      "logps/chosen": -0.2808162569999695,
      "logps/rejected": -0.39500662684440613,
      "loss": 0.9,
      "rewards/accuracies": 0.512499988079071,
      "rewards/chosen": -0.4212244153022766,
      "rewards/margins": 0.17128555476665497,
      "rewards/rejected": -0.592509925365448,
      "step": 160
    },
    {
      "epoch": 0.1461108723678556,
      "grad_norm": 0.14965052902698517,
      "learning_rate": 4.84320497372973e-06,
      "logits/chosen": 12.261284828186035,
      "logits/rejected": 13.0617036819458,
      "logps/chosen": -0.29266461730003357,
      "logps/rejected": -0.4265298843383789,
      "loss": 0.896,
      "rewards/accuracies": 0.637499988079071,
      "rewards/chosen": -0.43899694085121155,
      "rewards/margins": 0.20079784095287323,
      "rewards/rejected": -0.6397948265075684,
      "step": 170
    },
    {
      "epoch": 0.15470562956596476,
      "grad_norm": 0.13044072687625885,
      "learning_rate": 4.824441214720629e-06,
      "logits/chosen": 11.509119033813477,
      "logits/rejected": 12.31033706665039,
      "logps/chosen": -0.27384257316589355,
      "logps/rejected": -0.3920982778072357,
      "loss": 0.8911,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": -0.4107638895511627,
      "rewards/margins": 0.17738358676433563,
      "rewards/rejected": -0.5881474018096924,
      "step": 180
    },
    {
      "epoch": 0.1633003867640739,
      "grad_norm": 0.16182811558246613,
      "learning_rate": 4.804657878971252e-06,
      "logits/chosen": 10.68933391571045,
      "logits/rejected": 11.632065773010254,
      "logps/chosen": -0.292975515127182,
      "logps/rejected": -0.42257896065711975,
      "loss": 0.9002,
      "rewards/accuracies": 0.6000000238418579,
      "rewards/chosen": -0.4394632875919342,
      "rewards/margins": 0.19440510869026184,
      "rewards/rejected": -0.633868396282196,
      "step": 190
    },
    {
      "epoch": 0.17189514396218306,
      "grad_norm": 0.181160107254982,
      "learning_rate": 4.783863644106502e-06,
      "logits/chosen": 10.593437194824219,
      "logits/rejected": 11.435877799987793,
      "logps/chosen": -0.32495418190956116,
      "logps/rejected": -0.4480825364589691,
      "loss": 0.8773,
      "rewards/accuracies": 0.574999988079071,
      "rewards/chosen": -0.48743128776550293,
      "rewards/margins": 0.18469250202178955,
      "rewards/rejected": -0.6721237897872925,
      "step": 200
    },
    {
      "epoch": 0.17189514396218306,
      "eval_logits/chosen": 9.299257278442383,
      "eval_logits/rejected": 10.055145263671875,
      "eval_logps/chosen": -0.31059205532073975,
      "eval_logps/rejected": -0.47102925181388855,
      "eval_loss": 0.8721462488174438,
      "eval_rewards/accuracies": 0.6105263233184814,
      "eval_rewards/chosen": -0.4658880829811096,
      "eval_rewards/margins": 0.24065588414669037,
      "eval_rewards/rejected": -0.7065439224243164,
      "eval_runtime": 25.78,
      "eval_samples_per_second": 29.209,
      "eval_steps_per_second": 3.685,
      "step": 200
    },
    {
      "epoch": 0.18048990116029223,
      "grad_norm": 0.24912959337234497,
      "learning_rate": 4.762067631165049e-06,
      "logits/chosen": 8.803088188171387,
      "logits/rejected": 9.326388359069824,
      "logps/chosen": -0.3249451816082001,
      "logps/rejected": -0.44993042945861816,
      "loss": 0.8484,
      "rewards/accuracies": 0.5375000238418579,
      "rewards/chosen": -0.4874177575111389,
      "rewards/margins": 0.18747788667678833,
      "rewards/rejected": -0.6748956441879272,
      "step": 210
    },
    {
      "epoch": 0.18908465835840138,
      "grad_norm": 0.319579541683197,
      "learning_rate": 4.7392794005985324e-06,
      "logits/chosen": 6.257112979888916,
      "logits/rejected": 7.168400764465332,
      "logps/chosen": -0.335318386554718,
      "logps/rejected": -0.5439311265945435,
      "loss": 0.8499,
      "rewards/accuracies": 0.637499988079071,
      "rewards/chosen": -0.5029775500297546,
      "rewards/margins": 0.31291908025741577,
      "rewards/rejected": -0.8158966302871704,
      "step": 220
    },
    {
      "epoch": 0.19767941555651053,
      "grad_norm": 0.31494757533073425,
      "learning_rate": 4.715508948078037e-06,
      "logits/chosen": 5.725883960723877,
      "logits/rejected": 5.9254865646362305,
      "logps/chosen": -0.3735908567905426,
      "logps/rejected": -0.5729750394821167,
      "loss": 0.826,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": -0.5603862404823303,
      "rewards/margins": 0.2990763187408447,
      "rewards/rejected": -0.859462559223175,
      "step": 230
    },
    {
      "epoch": 0.20627417275461968,
      "grad_norm": 0.46439653635025024,
      "learning_rate": 4.690766700109659e-06,
      "logits/chosen": 5.059751033782959,
      "logits/rejected": 5.128623008728027,
      "logps/chosen": -0.4083784222602844,
      "logps/rejected": -0.6792675852775574,
      "loss": 0.7992,
      "rewards/accuracies": 0.637499988079071,
      "rewards/chosen": -0.612567663192749,
      "rewards/margins": 0.40633392333984375,
      "rewards/rejected": -1.0189014673233032,
      "step": 240
    },
    {
      "epoch": 0.21486892995272883,
      "grad_norm": 0.42406076192855835,
      "learning_rate": 4.665063509461098e-06,
      "logits/chosen": 4.128974437713623,
      "logits/rejected": 4.141166687011719,
      "logps/chosen": -0.4256651997566223,
      "logps/rejected": -0.7279168367385864,
      "loss": 0.7848,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -0.6384977102279663,
      "rewards/margins": 0.4533773958683014,
      "rewards/rejected": -1.0918750762939453,
      "step": 250
    },
    {
      "epoch": 0.21486892995272883,
      "eval_logits/chosen": 3.800307512283325,
      "eval_logits/rejected": 3.1472771167755127,
      "eval_logps/chosen": -0.4563433527946472,
      "eval_logps/rejected": -0.8247694373130798,
      "eval_loss": 0.7728626728057861,
      "eval_rewards/accuracies": 0.6526315808296204,
      "eval_rewards/chosen": -0.6845150589942932,
      "eval_rewards/margins": 0.5526391267776489,
      "eval_rewards/rejected": -1.237154245376587,
      "eval_runtime": 25.7836,
      "eval_samples_per_second": 29.205,
      "eval_steps_per_second": 3.685,
      "step": 250
    },
    {
      "epoch": 0.22346368715083798,
      "grad_norm": 0.4071955680847168,
      "learning_rate": 4.638410650401267e-06,
      "logits/chosen": 3.169527530670166,
      "logits/rejected": 2.603461503982544,
      "logps/chosen": -0.5029922723770142,
      "logps/rejected": -0.9469219446182251,
      "loss": 0.7273,
      "rewards/accuracies": 0.7124999761581421,
      "rewards/chosen": -0.7544883489608765,
      "rewards/margins": 0.6658946871757507,
      "rewards/rejected": -1.4203828573226929,
      "step": 260
    },
    {
      "epoch": 0.23205844434894715,
      "grad_norm": 0.6253886222839355,
      "learning_rate": 4.610819813755038e-06,
      "logits/chosen": 3.8718018531799316,
      "logits/rejected": 2.569753646850586,
      "logps/chosen": -0.4955294132232666,
      "logps/rejected": -0.8811863660812378,
      "loss": 0.7483,
      "rewards/accuracies": 0.6875,
      "rewards/chosen": -0.7432941198348999,
      "rewards/margins": 0.5784854888916016,
      "rewards/rejected": -1.321779489517212,
      "step": 270
    },
    {
      "epoch": 0.2406532015470563,
      "grad_norm": 0.5592113733291626,
      "learning_rate": 4.582303101775249e-06,
      "logits/chosen": 3.4818286895751953,
      "logits/rejected": 2.428328275680542,
      "logps/chosen": -0.5700691342353821,
      "logps/rejected": -1.010145664215088,
      "loss": 0.7165,
      "rewards/accuracies": 0.612500011920929,
      "rewards/chosen": -0.8551036715507507,
      "rewards/margins": 0.6601148843765259,
      "rewards/rejected": -1.5152184963226318,
      "step": 280
    },
    {
      "epoch": 0.24924795874516545,
      "grad_norm": 0.8438608050346375,
      "learning_rate": 4.55287302283426e-06,
      "logits/chosen": 2.5937914848327637,
      "logits/rejected": 1.8570162057876587,
      "logps/chosen": -0.592321515083313,
      "logps/rejected": -1.1775600910186768,
      "loss": 0.6685,
      "rewards/accuracies": 0.6000000238418579,
      "rewards/chosen": -0.8884822130203247,
      "rewards/margins": 0.8778578042984009,
      "rewards/rejected": -1.7663400173187256,
      "step": 290
    },
    {
      "epoch": 0.2578427159432746,
      "grad_norm": 2.9559757709503174,
      "learning_rate": 4.522542485937369e-06,
      "logits/chosen": 3.2419090270996094,
      "logits/rejected": 1.9082870483398438,
      "logps/chosen": -0.6832663416862488,
      "logps/rejected": -1.5631868839263916,
      "loss": 0.6009,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -1.0248994827270508,
      "rewards/margins": 1.3198809623718262,
      "rewards/rejected": -2.344780445098877,
      "step": 300
    },
    {
      "epoch": 0.2578427159432746,
      "eval_logits/chosen": 2.5470504760742188,
      "eval_logits/rejected": 1.492888331413269,
      "eval_logps/chosen": -0.7285813689231873,
      "eval_logps/rejected": -1.8318607807159424,
      "eval_loss": 0.5855891704559326,
      "eval_rewards/accuracies": 0.7052631378173828,
      "eval_rewards/chosen": -1.092872142791748,
      "eval_rewards/margins": 1.6549187898635864,
      "eval_rewards/rejected": -2.747790813446045,
      "eval_runtime": 25.8105,
      "eval_samples_per_second": 29.174,
      "eval_steps_per_second": 3.681,
      "step": 300
    },
    {
      "epoch": 0.2664374731413838,
      "grad_norm": 1.4503060579299927,
      "learning_rate": 4.491324795060491e-06,
      "logits/chosen": 1.6672757863998413,
      "logits/rejected": 0.7888604402542114,
      "logps/chosen": -0.769140899181366,
      "logps/rejected": -2.0822532176971436,
      "loss": 0.512,
      "rewards/accuracies": 0.75,
      "rewards/chosen": -1.1537113189697266,
      "rewards/margins": 1.9696683883666992,
      "rewards/rejected": -3.123379945755005,
      "step": 310
    },
    {
      "epoch": 0.2750322303394929,
      "grad_norm": 0.36741188168525696,
      "learning_rate": 4.4592336433146e-06,
      "logits/chosen": 2.6584715843200684,
      "logits/rejected": 1.835911750793457,
      "logps/chosen": -0.8400143384933472,
      "logps/rejected": -1.9262489080429077,
      "loss": 0.5405,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": -1.2600215673446655,
      "rewards/margins": 1.6293519735336304,
      "rewards/rejected": -2.889373302459717,
      "step": 320
    },
    {
      "epoch": 0.28362698753760207,
      "grad_norm": 0.6233783960342407,
      "learning_rate": 4.426283106939474e-06,
      "logits/chosen": 3.2203617095947266,
      "logits/rejected": 2.3215420246124268,
      "logps/chosen": -0.7985933423042297,
      "logps/rejected": -2.4170174598693848,
      "loss": 0.5335,
      "rewards/accuracies": 0.637499988079071,
      "rewards/chosen": -1.197890043258667,
      "rewards/margins": 2.427635669708252,
      "rewards/rejected": -3.625525712966919,
      "step": 330
    },
    {
      "epoch": 0.2922217447357112,
      "grad_norm": 1.0881849527359009,
      "learning_rate": 4.3924876391293915e-06,
      "logits/chosen": 2.229017734527588,
      "logits/rejected": 1.2251309156417847,
      "logps/chosen": -0.8058193325996399,
      "logps/rejected": -2.810622215270996,
      "loss": 0.4903,
      "rewards/accuracies": 0.7124999761581421,
      "rewards/chosen": -1.2087291479110718,
      "rewards/margins": 3.007204294204712,
      "rewards/rejected": -4.215933799743652,
      "step": 340
    },
    {
      "epoch": 0.30081650193382037,
      "grad_norm": 4.168415069580078,
      "learning_rate": 4.357862063693486e-06,
      "logits/chosen": 2.4198296070098877,
      "logits/rejected": 1.5391919612884521,
      "logps/chosen": -1.010558843612671,
      "logps/rejected": -2.2362923622131348,
      "loss": 0.5249,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": -1.515838384628296,
      "rewards/margins": 1.8385999202728271,
      "rewards/rejected": -3.3544387817382812,
      "step": 350
    },
    {
      "epoch": 0.30081650193382037,
      "eval_logits/chosen": 2.996535539627075,
      "eval_logits/rejected": 2.064058303833008,
      "eval_logps/chosen": -0.8687878847122192,
      "eval_logps/rejected": -2.9790267944335938,
      "eval_loss": 0.5171241760253906,
      "eval_rewards/accuracies": 0.7263157963752747,
      "eval_rewards/chosen": -1.3031818866729736,
      "eval_rewards/margins": 3.165358781814575,
      "eval_rewards/rejected": -4.468540668487549,
      "eval_runtime": 25.8152,
      "eval_samples_per_second": 29.169,
      "eval_steps_per_second": 3.68,
      "step": 350
    },
    {
      "epoch": 0.3094112591319295,
      "grad_norm": 0.5646592378616333,
      "learning_rate": 4.322421568553529e-06,
      "logits/chosen": 3.050445556640625,
      "logits/rejected": 2.0960793495178223,
      "logps/chosen": -0.7702202796936035,
      "logps/rejected": -2.5967533588409424,
      "loss": 0.5067,
      "rewards/accuracies": 0.675000011920929,
      "rewards/chosen": -1.1553303003311157,
      "rewards/margins": 2.739799737930298,
      "rewards/rejected": -3.895130157470703,
      "step": 360
    },
    {
      "epoch": 0.31800601633003867,
      "grad_norm": 0.5547713041305542,
      "learning_rate": 4.286181699082008e-06,
      "logits/chosen": 2.7148895263671875,
      "logits/rejected": 1.9958852529525757,
      "logps/chosen": -0.9548311233520508,
      "logps/rejected": -3.1348252296447754,
      "loss": 0.4726,
      "rewards/accuracies": 0.800000011920929,
      "rewards/chosen": -1.4322465658187866,
      "rewards/margins": 3.269991397857666,
      "rewards/rejected": -4.702237606048584,
      "step": 370
    },
    {
      "epoch": 0.3266007735281478,
      "grad_norm": 3.4396660327911377,
      "learning_rate": 4.249158351283414e-06,
      "logits/chosen": 2.586766004562378,
      "logits/rejected": 2.070089340209961,
      "logps/chosen": -0.9903923273086548,
      "logps/rejected": -3.0135743618011475,
      "loss": 0.4801,
      "rewards/accuracies": 0.6625000238418579,
      "rewards/chosen": -1.485588550567627,
      "rewards/margins": 3.034773349761963,
      "rewards/rejected": -4.52036190032959,
      "step": 380
    },
    {
      "epoch": 0.33519553072625696,
      "grad_norm": 0.9405317306518555,
      "learning_rate": 4.211367764821722e-06,
      "logits/chosen": 4.370789527893066,
      "logits/rejected": 3.165931224822998,
      "logps/chosen": -0.7785463929176331,
      "logps/rejected": -2.456723928451538,
      "loss": 0.4585,
      "rewards/accuracies": 0.5874999761581421,
      "rewards/chosen": -1.1678194999694824,
      "rewards/margins": 2.5172665119171143,
      "rewards/rejected": -3.6850857734680176,
      "step": 390
    },
    {
      "epoch": 0.3437902879243661,
      "grad_norm": 0.7120731472969055,
      "learning_rate": 4.172826515897146e-06,
      "logits/chosen": 3.3425400257110596,
      "logits/rejected": 2.6448545455932617,
      "logps/chosen": -0.9174768328666687,
      "logps/rejected": -3.047037124633789,
      "loss": 0.4771,
      "rewards/accuracies": 0.675000011920929,
      "rewards/chosen": -1.3762153387069702,
      "rewards/margins": 3.194340229034424,
      "rewards/rejected": -4.570555686950684,
      "step": 400
    },
    {
      "epoch": 0.3437902879243661,
      "eval_logits/chosen": 3.548964262008667,
      "eval_logits/rejected": 2.7726428508758545,
      "eval_logps/chosen": -1.0053316354751587,
      "eval_logps/rejected": -3.487654447555542,
      "eval_loss": 0.47841358184814453,
      "eval_rewards/accuracies": 0.7368420958518982,
      "eval_rewards/chosen": -1.5079973936080933,
      "eval_rewards/margins": 3.723484992980957,
      "eval_rewards/rejected": -5.231482028961182,
      "eval_runtime": 25.8148,
      "eval_samples_per_second": 29.169,
      "eval_steps_per_second": 3.68,
      "step": 400
    },
    {
      "epoch": 0.3523850451224753,
      "grad_norm": 2.403956651687622,
      "learning_rate": 4.133551509975264e-06,
      "logits/chosen": 3.2028489112854004,
      "logits/rejected": 2.2486982345581055,
      "logps/chosen": -0.9957242012023926,
      "logps/rejected": -3.243959426879883,
      "loss": 0.4449,
      "rewards/accuracies": 0.637499988079071,
      "rewards/chosen": -1.4935863018035889,
      "rewards/margins": 3.3723526000976562,
      "rewards/rejected": -4.865939140319824,
      "step": 410
    },
    {
      "epoch": 0.36097980232058446,
      "grad_norm": 0.39530256390571594,
      "learning_rate": 4.093559974371725e-06,
      "logits/chosen": 3.8590214252471924,
      "logits/rejected": 3.1420931816101074,
      "logps/chosen": -0.9541120529174805,
      "logps/rejected": -3.0112829208374023,
      "loss": 0.4598,
      "rewards/accuracies": 0.699999988079071,
      "rewards/chosen": -1.4311680793762207,
      "rewards/margins": 3.085756301879883,
      "rewards/rejected": -4.5169243812561035,
      "step": 420
    },
    {
      "epoch": 0.3695745595186936,
      "grad_norm": 0.29451707005500793,
      "learning_rate": 4.052869450695776e-06,
      "logits/chosen": 4.697268486022949,
      "logits/rejected": 3.7647697925567627,
      "logps/chosen": -1.1037578582763672,
      "logps/rejected": -3.8626160621643066,
      "loss": 0.4275,
      "rewards/accuracies": 0.75,
      "rewards/chosen": -1.6556367874145508,
      "rewards/margins": 4.138287544250488,
      "rewards/rejected": -5.793923854827881,
      "step": 430
    },
    {
      "epoch": 0.37816931671680276,
      "grad_norm": 0.5065125823020935,
      "learning_rate": 4.011497787155938e-06,
      "logits/chosen": 3.5233864784240723,
      "logits/rejected": 2.798567533493042,
      "logps/chosen": -1.1753087043762207,
      "logps/rejected": -4.171238899230957,
      "loss": 0.4132,
      "rewards/accuracies": 0.75,
      "rewards/chosen": -1.7629629373550415,
      "rewards/margins": 4.493895053863525,
      "rewards/rejected": -6.256857872009277,
      "step": 440
    },
    {
      "epoch": 0.3867640739149119,
      "grad_norm": 1.414167881011963,
      "learning_rate": 3.969463130731183e-06,
      "logits/chosen": 4.733740329742432,
      "logits/rejected": 4.114102363586426,
      "logps/chosen": -1.1846634149551392,
      "logps/rejected": -4.04649543762207,
      "loss": 0.4266,
      "rewards/accuracies": 0.7749999761581421,
      "rewards/chosen": -1.776995301246643,
      "rewards/margins": 4.292747974395752,
      "rewards/rejected": -6.0697431564331055,
      "step": 450
    },
    {
      "epoch": 0.3867640739149119,
      "eval_logits/chosen": 4.25229549407959,
      "eval_logits/rejected": 3.900564193725586,
      "eval_logps/chosen": -1.410205602645874,
      "eval_logps/rejected": -4.276910781860352,
      "eval_loss": 0.4397798478603363,
      "eval_rewards/accuracies": 0.800000011920929,
      "eval_rewards/chosen": -2.1153085231781006,
      "eval_rewards/margins": 4.3000569343566895,
      "eval_rewards/rejected": -6.415364742279053,
      "eval_runtime": 25.7968,
      "eval_samples_per_second": 29.19,
      "eval_steps_per_second": 3.683,
      "step": 450
    }
  ],
  "logging_steps": 10,
  "max_steps": 1500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0263737055817236e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}