checkpoint-600/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5156854318865493,
  "eval_steps": 50,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008594757198109154,
      "grad_norm": 0.05934199318289757,
      "learning_rate": 4.999451708687114e-06,
      "logits/chosen": 14.762972831726074,
      "logits/rejected": 15.199728012084961,
      "logps/chosen": -0.3259914815425873,
      "logps/rejected": -0.34297481179237366,
      "loss": 0.9377,
      "rewards/accuracies": 0.4000000059604645,
      "rewards/chosen": -0.4889872074127197,
      "rewards/margins": 0.02547495998442173,
      "rewards/rejected": -0.5144621729850769,
      "step": 10
    },
    {
      "epoch": 0.017189514396218308,
      "grad_norm": 0.06342790275812149,
      "learning_rate": 4.997807075247147e-06,
      "logits/chosen": 14.351249694824219,
      "logits/rejected": 15.068448066711426,
      "logps/chosen": -0.2809392511844635,
      "logps/rejected": -0.3711296617984772,
      "loss": 0.9352,
      "rewards/accuracies": 0.574999988079071,
      "rewards/chosen": -0.42140883207321167,
      "rewards/margins": 0.1352856159210205,
      "rewards/rejected": -0.5566944479942322,
      "step": 20
    },
    {
      "epoch": 0.02578427159432746,
      "grad_norm": 0.053961098194122314,
      "learning_rate": 4.9950668210706795e-06,
      "logits/chosen": 14.636960983276367,
      "logits/rejected": 15.265243530273438,
      "logps/chosen": -0.2820780873298645,
      "logps/rejected": -0.34024301171302795,
      "loss": 0.9351,
      "rewards/accuracies": 0.4749999940395355,
      "rewards/chosen": -0.42311716079711914,
      "rewards/margins": 0.08724743127822876,
      "rewards/rejected": -0.5103646516799927,
      "step": 30
    },
    {
      "epoch": 0.034379028792436615,
      "grad_norm": 0.13506193459033966,
      "learning_rate": 4.9912321481237616e-06,
      "logits/chosen": 14.4556884765625,
      "logits/rejected": 15.048967361450195,
      "logps/chosen": -0.2897028625011444,
      "logps/rejected": -0.34129124879837036,
      "loss": 0.922,
      "rewards/accuracies": 0.44999998807907104,
      "rewards/chosen": -0.43455424904823303,
      "rewards/margins": 0.07738252729177475,
      "rewards/rejected": -0.5119368433952332,
      "step": 40
    },
    {
      "epoch": 0.042973785990545764,
      "grad_norm": 0.05230574309825897,
      "learning_rate": 4.986304738420684e-06,
      "logits/chosen": 14.628789901733398,
      "logits/rejected": 15.307828903198242,
      "logps/chosen": -0.28786614537239075,
      "logps/rejected": -0.3513876795768738,
      "loss": 0.9201,
      "rewards/accuracies": 0.5375000238418579,
      "rewards/chosen": -0.4317992329597473,
      "rewards/margins": 0.09528233855962753,
      "rewards/rejected": -0.5270815491676331,
      "step": 50
    },
    {
      "epoch": 0.042973785990545764,
      "eval_logits/chosen": 14.234943389892578,
      "eval_logits/rejected": 15.258601188659668,
      "eval_logps/chosen": -0.2844341993331909,
      "eval_logps/rejected": -0.3695394694805145,
      "eval_loss": 0.9226060509681702,
      "eval_rewards/accuracies": 0.5157894492149353,
      "eval_rewards/chosen": -0.42665132880210876,
      "eval_rewards/margins": 0.1276579648256302,
      "eval_rewards/rejected": -0.5543092489242554,
      "eval_runtime": 25.9356,
      "eval_samples_per_second": 29.033,
      "eval_steps_per_second": 3.663,
      "step": 50
    },
    {
      "epoch": 0.05156854318865492,
      "grad_norm": 0.09328428655862808,
      "learning_rate": 4.980286753286196e-06,
      "logits/chosen": 14.35963249206543,
      "logits/rejected": 15.055354118347168,
      "logps/chosen": -0.27534741163253784,
      "logps/rejected": -0.33098170161247253,
      "loss": 0.9356,
      "rewards/accuracies": 0.512499988079071,
      "rewards/chosen": -0.4130210876464844,
      "rewards/margins": 0.08345144242048264,
      "rewards/rejected": -0.4964725375175476,
      "step": 60
    },
    {
      "epoch": 0.060163300386764075,
      "grad_norm": 0.06518550217151642,
      "learning_rate": 4.973180832407471e-06,
      "logits/chosen": 14.599525451660156,
      "logits/rejected": 14.825297355651855,
      "logps/chosen": -0.2708163857460022,
      "logps/rejected": -0.3305850923061371,
      "loss": 0.9257,
      "rewards/accuracies": 0.550000011920929,
      "rewards/chosen": -0.4062245786190033,
      "rewards/margins": 0.08965305984020233,
      "rewards/rejected": -0.4958776533603668,
      "step": 70
    },
    {
      "epoch": 0.06875805758487323,
      "grad_norm": 0.07543154805898666,
      "learning_rate": 4.964990092676263e-06,
      "logits/chosen": 14.947430610656738,
      "logits/rejected": 15.093690872192383,
      "logps/chosen": -0.2602943778038025,
      "logps/rejected": -0.31820863485336304,
      "loss": 0.9168,
      "rewards/accuracies": 0.5,
      "rewards/chosen": -0.39044153690338135,
      "rewards/margins": 0.08687138557434082,
      "rewards/rejected": -0.47731298208236694,
      "step": 80
    },
    {
      "epoch": 0.07735281478298238,
      "grad_norm": 0.06628195196390152,
      "learning_rate": 4.9557181268217225e-06,
      "logits/chosen": 14.43529987335205,
      "logits/rejected": 14.750699043273926,
      "logps/chosen": -0.2884291708469391,
      "logps/rejected": -0.34193652868270874,
      "loss": 0.9273,
      "rewards/accuracies": 0.5249999761581421,
      "rewards/chosen": -0.43264374136924744,
      "rewards/margins": 0.08026103675365448,
      "rewards/rejected": -0.5129047632217407,
      "step": 90
    },
    {
      "epoch": 0.08594757198109153,
      "grad_norm": 0.08684897422790527,
      "learning_rate": 4.9453690018345144e-06,
      "logits/chosen": 13.573002815246582,
      "logits/rejected": 14.441877365112305,
      "logps/chosen": -0.2569890320301056,
      "logps/rejected": -0.37049269676208496,
      "loss": 0.9009,
      "rewards/accuracies": 0.574999988079071,
      "rewards/chosen": -0.3854835629463196,
      "rewards/margins": 0.17025551199913025,
      "rewards/rejected": -0.5557390451431274,
      "step": 100
    },
    {
      "epoch": 0.08594757198109153,
      "eval_logits/chosen": 14.026633262634277,
      "eval_logits/rejected": 15.08835220336914,
      "eval_logps/chosen": -0.2761566936969757,
      "eval_logps/rejected": -0.3717801570892334,
      "eval_loss": 0.9138591885566711,
      "eval_rewards/accuracies": 0.5368421077728271,
      "eval_rewards/chosen": -0.41423505544662476,
      "eval_rewards/margins": 0.1434352546930313,
      "eval_rewards/rejected": -0.5576702952384949,
      "eval_runtime": 25.3996,
      "eval_samples_per_second": 29.646,
      "eval_steps_per_second": 3.74,
      "step": 100
    },
    {
      "epoch": 0.09454232917920069,
      "grad_norm": 0.08046824485063553,
      "learning_rate": 4.933947257182901e-06,
      "logits/chosen": 14.500630378723145,
      "logits/rejected": 14.831761360168457,
      "logps/chosen": -0.30049553513526917,
      "logps/rejected": -0.3315966725349426,
      "loss": 0.916,
      "rewards/accuracies": 0.4625000059604645,
      "rewards/chosen": -0.45074325799942017,
      "rewards/margins": 0.04665176197886467,
      "rewards/rejected": -0.49739497900009155,
      "step": 110
    },
    {
      "epoch": 0.10313708637730984,
      "grad_norm": 0.12244562804698944,
      "learning_rate": 4.921457902821578e-06,
      "logits/chosen": 14.26713752746582,
      "logits/rejected": 14.495455741882324,
      "logps/chosen": -0.2670941650867462,
      "logps/rejected": -0.32481229305267334,
      "loss": 0.9167,
      "rewards/accuracies": 0.550000011920929,
      "rewards/chosen": -0.4006412625312805,
      "rewards/margins": 0.08657723665237427,
      "rewards/rejected": -0.4872184693813324,
      "step": 120
    },
    {
      "epoch": 0.11173184357541899,
      "grad_norm": 0.1828213334083557,
      "learning_rate": 4.907906416994146e-06,
      "logits/chosen": 14.009546279907227,
      "logits/rejected": 14.297094345092773,
      "logps/chosen": -0.27995598316192627,
      "logps/rejected": -0.3530685007572174,
      "loss": 0.9087,
      "rewards/accuracies": 0.5249999761581421,
      "rewards/chosen": -0.419933944940567,
      "rewards/margins": 0.10966875404119492,
      "rewards/rejected": -0.5296027660369873,
      "step": 130
    },
    {
      "epoch": 0.12032660077352815,
      "grad_norm": 0.10407563298940659,
      "learning_rate": 4.893298743830168e-06,
      "logits/chosen": 13.689155578613281,
      "logits/rejected": 14.1933012008667,
      "logps/chosen": -0.25955715775489807,
      "logps/rejected": -0.3815004229545593,
      "loss": 0.9053,
      "rewards/accuracies": 0.612500011920929,
      "rewards/chosen": -0.3893357217311859,
      "rewards/margins": 0.18291489779949188,
      "rewards/rejected": -0.5722506046295166,
      "step": 140
    },
    {
      "epoch": 0.1289213579716373,
      "grad_norm": 0.10028588026762009,
      "learning_rate": 4.8776412907378845e-06,
      "logits/chosen": 12.851397514343262,
      "logits/rejected": 13.509778022766113,
      "logps/chosen": -0.23652991652488708,
      "logps/rejected": -0.3720462918281555,
      "loss": 0.8999,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -0.3547949194908142,
      "rewards/margins": 0.2032744586467743,
      "rewards/rejected": -0.5580693483352661,
      "step": 150
    },
    {
      "epoch": 0.1289213579716373,
      "eval_logits/chosen": 12.384929656982422,
      "eval_logits/rejected": 13.672826766967773,
      "eval_logps/chosen": -0.27857670187950134,
      "eval_logps/rejected": -0.4014737904071808,
      "eval_loss": 0.8956203460693359,
      "eval_rewards/accuracies": 0.5684210658073425,
      "eval_rewards/chosen": -0.4178650677204132,
      "eval_rewards/margins": 0.18434564769268036,
      "eval_rewards/rejected": -0.6022107601165771,
      "eval_runtime": 25.4176,
      "eval_samples_per_second": 29.625,
      "eval_steps_per_second": 3.738,
      "step": 150
    },
    {
      "epoch": 0.13751611516974646,
      "grad_norm": 0.12453093379735947,
      "learning_rate": 4.860940925593703e-06,
      "logits/chosen": 12.110003471374512,
      "logits/rejected": 13.076980590820312,
      "logps/chosen": -0.27192068099975586,
      "logps/rejected": -0.3863692879676819,
      "loss": 0.8907,
      "rewards/accuracies": 0.5874999761581421,
      "rewards/chosen": -0.4078810214996338,
      "rewards/margins": 0.1716729700565338,
      "rewards/rejected": -0.5795539617538452,
      "step": 160
    },
    {
      "epoch": 0.1461108723678556,
      "grad_norm": 0.17137788236141205,
      "learning_rate": 4.84320497372973e-06,
      "logits/chosen": 11.92918586730957,
      "logits/rejected": 12.573629379272461,
      "logps/chosen": -0.27472984790802,
      "logps/rejected": -0.41249385476112366,
      "loss": 0.8831,
      "rewards/accuracies": 0.612500011920929,
      "rewards/chosen": -0.41209474205970764,
      "rewards/margins": 0.20664596557617188,
      "rewards/rejected": -0.6187406778335571,
      "step": 170
    },
    {
      "epoch": 0.15470562956596476,
      "grad_norm": 0.3904883861541748,
      "learning_rate": 4.824441214720629e-06,
      "logits/chosen": 11.182531356811523,
      "logits/rejected": 12.176573753356934,
      "logps/chosen": -0.2953718304634094,
      "logps/rejected": -0.4208717942237854,
      "loss": 0.8736,
      "rewards/accuracies": 0.5375000238418579,
      "rewards/chosen": -0.4430577754974365,
      "rewards/margins": 0.18824996054172516,
      "rewards/rejected": -0.6313077211380005,
      "step": 180
    },
    {
      "epoch": 0.1633003867640739,
      "grad_norm": 0.17574089765548706,
      "learning_rate": 4.804657878971252e-06,
      "logits/chosen": 10.119890213012695,
      "logits/rejected": 11.05900764465332,
      "logps/chosen": -0.29340866208076477,
      "logps/rejected": -0.4555762708187103,
      "loss": 0.884,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -0.44011297821998596,
      "rewards/margins": 0.24325144290924072,
      "rewards/rejected": -0.6833644509315491,
      "step": 190
    },
    {
      "epoch": 0.17189514396218306,
      "grad_norm": 0.2242884337902069,
      "learning_rate": 4.783863644106502e-06,
      "logits/chosen": 9.674784660339355,
      "logits/rejected": 10.418611526489258,
      "logps/chosen": -0.3504490852355957,
      "logps/rejected": -0.5431731939315796,
      "loss": 0.8419,
      "rewards/accuracies": 0.612500011920929,
      "rewards/chosen": -0.5256736278533936,
      "rewards/margins": 0.2890861928462982,
      "rewards/rejected": -0.8147598505020142,
      "step": 200
    },
    {
      "epoch": 0.17189514396218306,
      "eval_logits/chosen": 7.944870471954346,
      "eval_logits/rejected": 8.979729652404785,
      "eval_logps/chosen": -0.33341673016548157,
      "eval_logps/rejected": -0.5431775450706482,
      "eval_loss": 0.8462886810302734,
      "eval_rewards/accuracies": 0.6000000238418579,
      "eval_rewards/chosen": -0.5001251101493835,
      "eval_rewards/margins": 0.3146411180496216,
      "eval_rewards/rejected": -0.8147663474082947,
      "eval_runtime": 25.419,
      "eval_samples_per_second": 29.623,
      "eval_steps_per_second": 3.737,
      "step": 200
    },
    {
      "epoch": 0.18048990116029223,
      "grad_norm": 0.32119837403297424,
      "learning_rate": 4.762067631165049e-06,
      "logits/chosen": 7.16138219833374,
      "logits/rejected": 8.43680477142334,
      "logps/chosen": -0.36649250984191895,
      "logps/rejected": -0.5420924425125122,
      "loss": 0.8187,
      "rewards/accuracies": 0.612500011920929,
      "rewards/chosen": -0.5497387647628784,
      "rewards/margins": 0.2633998692035675,
      "rewards/rejected": -0.8131386041641235,
      "step": 210
    },
    {
      "epoch": 0.18908465835840138,
      "grad_norm": 0.48516562581062317,
      "learning_rate": 4.7392794005985324e-06,
      "logits/chosen": 4.770083427429199,
      "logits/rejected": 5.710458278656006,
      "logps/chosen": -0.34041497111320496,
      "logps/rejected": -0.6309320330619812,
      "loss": 0.8448,
      "rewards/accuracies": 0.675000011920929,
      "rewards/chosen": -0.510622501373291,
      "rewards/margins": 0.4357755780220032,
      "rewards/rejected": -0.9463980793952942,
      "step": 220
    },
    {
      "epoch": 0.19767941555651053,
      "grad_norm": 0.29154208302497864,
      "learning_rate": 4.715508948078037e-06,
      "logits/chosen": 5.168765068054199,
      "logits/rejected": 5.421420574188232,
      "logps/chosen": -0.3792352080345154,
      "logps/rejected": -0.65748131275177,
      "loss": 0.8066,
      "rewards/accuracies": 0.6625000238418579,
      "rewards/chosen": -0.5688528418540955,
      "rewards/margins": 0.41736921668052673,
      "rewards/rejected": -0.986221969127655,
      "step": 230
    },
    {
      "epoch": 0.20627417275461968,
      "grad_norm": 0.42973750829696655,
      "learning_rate": 4.690766700109659e-06,
      "logits/chosen": 4.204717636108398,
      "logits/rejected": 3.706291913986206,
      "logps/chosen": -0.39414530992507935,
      "logps/rejected": -0.7194588780403137,
      "loss": 0.7787,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": -0.5912179350852966,
      "rewards/margins": 0.4879704415798187,
      "rewards/rejected": -1.079188346862793,
      "step": 240
    },
    {
      "epoch": 0.21486892995272883,
      "grad_norm": 0.5244571566581726,
      "learning_rate": 4.665063509461098e-06,
      "logits/chosen": 3.335484743118286,
      "logits/rejected": 3.3176345825195312,
      "logps/chosen": -0.4493131637573242,
      "logps/rejected": -0.8293434381484985,
      "loss": 0.7776,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -0.6739697456359863,
      "rewards/margins": 0.5700454115867615,
      "rewards/rejected": -1.244015097618103,
      "step": 250
    },
    {
      "epoch": 0.21486892995272883,
      "eval_logits/chosen": 2.590949058532715,
      "eval_logits/rejected": 2.2929749488830566,
      "eval_logps/chosen": -0.48714593052864075,
      "eval_logps/rejected": -0.9267774224281311,
      "eval_loss": 0.7469337582588196,
      "eval_rewards/accuracies": 0.6526315808296204,
      "eval_rewards/chosen": -0.7307189106941223,
      "eval_rewards/margins": 0.659447193145752,
      "eval_rewards/rejected": -1.390166163444519,
      "eval_runtime": 25.3944,
      "eval_samples_per_second": 29.652,
      "eval_steps_per_second": 3.741,
      "step": 250
    },
    {
      "epoch": 0.22346368715083798,
      "grad_norm": 0.39347293972969055,
      "learning_rate": 4.638410650401267e-06,
      "logits/chosen": 2.2975668907165527,
      "logits/rejected": 1.2855035066604614,
      "logps/chosen": -0.5228341817855835,
      "logps/rejected": -1.00227952003479,
      "loss": 0.6981,
      "rewards/accuracies": 0.7124999761581421,
      "rewards/chosen": -0.78425133228302,
      "rewards/margins": 0.7191681265830994,
      "rewards/rejected": -1.5034195184707642,
      "step": 260
    },
    {
      "epoch": 0.23205844434894715,
      "grad_norm": 0.69575434923172,
      "learning_rate": 4.610819813755038e-06,
      "logits/chosen": 2.8782780170440674,
      "logits/rejected": 1.9394336938858032,
      "logps/chosen": -0.4982885718345642,
      "logps/rejected": -1.035541296005249,
      "loss": 0.7174,
      "rewards/accuracies": 0.7250000238418579,
      "rewards/chosen": -0.7474328875541687,
      "rewards/margins": 0.8058789372444153,
      "rewards/rejected": -1.5533119440078735,
      "step": 270
    },
    {
      "epoch": 0.2406532015470563,
      "grad_norm": 0.7858326435089111,
      "learning_rate": 4.582303101775249e-06,
      "logits/chosen": 2.710908889770508,
      "logits/rejected": 1.6444288492202759,
      "logps/chosen": -0.600068211555481,
      "logps/rejected": -1.1271780729293823,
      "loss": 0.6972,
      "rewards/accuracies": 0.6625000238418579,
      "rewards/chosen": -0.9001023173332214,
      "rewards/margins": 0.7906648516654968,
      "rewards/rejected": -1.6907672882080078,
      "step": 280
    },
    {
      "epoch": 0.24924795874516545,
      "grad_norm": 0.7384620904922485,
      "learning_rate": 4.55287302283426e-06,
      "logits/chosen": 1.5841500759124756,
      "logits/rejected": 0.640514612197876,
      "logps/chosen": -0.6465060710906982,
      "logps/rejected": -1.4245095252990723,
      "loss": 0.6192,
      "rewards/accuracies": 0.612500011920929,
      "rewards/chosen": -0.9697591066360474,
      "rewards/margins": 1.1670053005218506,
      "rewards/rejected": -2.1367642879486084,
      "step": 290
    },
    {
      "epoch": 0.2578427159432746,
      "grad_norm": 0.8262321352958679,
      "learning_rate": 4.522542485937369e-06,
      "logits/chosen": 1.7300422191619873,
      "logits/rejected": 0.7782856225967407,
      "logps/chosen": -0.7083590626716614,
      "logps/rejected": -1.6742557287216187,
      "loss": 0.5721,
      "rewards/accuracies": 0.612500011920929,
      "rewards/chosen": -1.062538504600525,
      "rewards/margins": 1.4488452672958374,
      "rewards/rejected": -2.511383533477783,
      "step": 300
    },
    {
      "epoch": 0.2578427159432746,
      "eval_logits/chosen": 1.3559931516647339,
      "eval_logits/rejected": 0.6592276096343994,
      "eval_logps/chosen": -0.7815767526626587,
      "eval_logps/rejected": -2.1176154613494873,
      "eval_loss": 0.5730626583099365,
      "eval_rewards/accuracies": 0.7052631378173828,
      "eval_rewards/chosen": -1.1723653078079224,
      "eval_rewards/margins": 2.0040581226348877,
      "eval_rewards/rejected": -3.1764233112335205,
      "eval_runtime": 25.539,
      "eval_samples_per_second": 29.484,
      "eval_steps_per_second": 3.72,
      "step": 300
    },
    {
      "epoch": 0.2664374731413838,
      "grad_norm": 0.8472572565078735,
      "learning_rate": 4.491324795060491e-06,
      "logits/chosen": 1.4461088180541992,
      "logits/rejected": 0.49669915437698364,
      "logps/chosen": -0.7694377899169922,
      "logps/rejected": -2.362783432006836,
      "loss": 0.5091,
      "rewards/accuracies": 0.762499988079071,
      "rewards/chosen": -1.1541565656661987,
      "rewards/margins": 2.390018939971924,
      "rewards/rejected": -3.544174909591675,
      "step": 310
    },
    {
      "epoch": 0.2750322303394929,
      "grad_norm": 0.41847530007362366,
      "learning_rate": 4.4592336433146e-06,
      "logits/chosen": 2.172646999359131,
      "logits/rejected": 1.0526962280273438,
      "logps/chosen": -0.7410945296287537,
      "logps/rejected": -1.9158353805541992,
      "loss": 0.5352,
      "rewards/accuracies": 0.675000011920929,
      "rewards/chosen": -1.1116416454315186,
      "rewards/margins": 1.7621114253997803,
      "rewards/rejected": -2.873753070831299,
      "step": 320
    },
    {
      "epoch": 0.28362698753760207,
      "grad_norm": 1.7422096729278564,
      "learning_rate": 4.426283106939474e-06,
      "logits/chosen": 2.611234188079834,
      "logits/rejected": 1.7068111896514893,
      "logps/chosen": -0.8319486379623413,
      "logps/rejected": -2.32024884223938,
      "loss": 0.5397,
      "rewards/accuracies": 0.6000000238418579,
      "rewards/chosen": -1.2479230165481567,
      "rewards/margins": 2.232450008392334,
      "rewards/rejected": -3.480372905731201,
      "step": 330
    },
    {
      "epoch": 0.2922217447357112,
      "grad_norm": 0.8699240684509277,
      "learning_rate": 4.3924876391293915e-06,
      "logits/chosen": 1.996747612953186,
      "logits/rejected": 1.1473515033721924,
      "logps/chosen": -0.8445833921432495,
      "logps/rejected": -2.675687551498413,
      "loss": 0.4817,
      "rewards/accuracies": 0.699999988079071,
      "rewards/chosen": -1.2668750286102295,
      "rewards/margins": 2.7466559410095215,
      "rewards/rejected": -4.01353120803833,
      "step": 340
    },
    {
      "epoch": 0.30081650193382037,
      "grad_norm": 2.089289426803589,
      "learning_rate": 4.357862063693486e-06,
      "logits/chosen": 1.7134803533554077,
      "logits/rejected": 1.3000510931015015,
      "logps/chosen": -0.8976927995681763,
      "logps/rejected": -2.1593873500823975,
      "loss": 0.5098,
      "rewards/accuracies": 0.574999988079071,
      "rewards/chosen": -1.3465392589569092,
      "rewards/margins": 1.8925418853759766,
      "rewards/rejected": -3.2390809059143066,
      "step": 350
    },
    {
      "epoch": 0.30081650193382037,
      "eval_logits/chosen": 1.6772903203964233,
      "eval_logits/rejected": 1.2370609045028687,
      "eval_logps/chosen": -0.9737761616706848,
      "eval_logps/rejected": -3.1528680324554443,
      "eval_loss": 0.5162621736526489,
      "eval_rewards/accuracies": 0.7263157963752747,
      "eval_rewards/chosen": -1.46066415309906,
      "eval_rewards/margins": 3.2686376571655273,
      "eval_rewards/rejected": -4.729301929473877,
      "eval_runtime": 25.4163,
      "eval_samples_per_second": 29.627,
      "eval_steps_per_second": 3.738,
      "step": 350
    },
    {
      "epoch": 0.3094112591319295,
      "grad_norm": 0.47079572081565857,
      "learning_rate": 4.322421568553529e-06,
      "logits/chosen": 1.9561872482299805,
      "logits/rejected": 0.8960329294204712,
      "logps/chosen": -0.9378088712692261,
      "logps/rejected": -2.8065876960754395,
      "loss": 0.5046,
      "rewards/accuracies": 0.675000011920929,
      "rewards/chosen": -1.4067132472991943,
      "rewards/margins": 2.8031680583953857,
      "rewards/rejected": -4.209881782531738,
      "step": 360
    },
    {
      "epoch": 0.31800601633003867,
      "grad_norm": 0.6202365159988403,
      "learning_rate": 4.286181699082008e-06,
      "logits/chosen": 2.152726411819458,
      "logits/rejected": 1.4309433698654175,
      "logps/chosen": -1.007157564163208,
      "logps/rejected": -3.3813462257385254,
      "loss": 0.4526,
      "rewards/accuracies": 0.800000011920929,
      "rewards/chosen": -1.5107364654541016,
      "rewards/margins": 3.561283588409424,
      "rewards/rejected": -5.072019577026367,
      "step": 370
    },
    {
      "epoch": 0.3266007735281478,
      "grad_norm": 1.080393671989441,
      "learning_rate": 4.249158351283414e-06,
      "logits/chosen": 1.7528371810913086,
      "logits/rejected": 1.3293968439102173,
      "logps/chosen": -1.0258004665374756,
      "logps/rejected": -2.984057903289795,
      "loss": 0.4879,
      "rewards/accuracies": 0.675000011920929,
      "rewards/chosen": -1.5387006998062134,
      "rewards/margins": 2.9373860359191895,
      "rewards/rejected": -4.476086616516113,
      "step": 380
    },
    {
      "epoch": 0.33519553072625696,
      "grad_norm": 1.4520032405853271,
      "learning_rate": 4.211367764821722e-06,
      "logits/chosen": 3.061373233795166,
      "logits/rejected": 2.0103466510772705,
      "logps/chosen": -1.0191391706466675,
      "logps/rejected": -2.9054081439971924,
      "loss": 0.4776,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -1.5287089347839355,
      "rewards/margins": 2.8294031620025635,
      "rewards/rejected": -4.358112335205078,
      "step": 390
    },
    {
      "epoch": 0.3437902879243661,
      "grad_norm": 0.5479139089584351,
      "learning_rate": 4.172826515897146e-06,
      "logits/chosen": 2.8395092487335205,
      "logits/rejected": 2.0935282707214355,
      "logps/chosen": -1.0769506692886353,
      "logps/rejected": -3.11635160446167,
      "loss": 0.4686,
      "rewards/accuracies": 0.6875,
      "rewards/chosen": -1.6154258251190186,
      "rewards/margins": 3.0591015815734863,
      "rewards/rejected": -4.674527168273926,
      "step": 400
    },
    {
      "epoch": 0.3437902879243661,
      "eval_logits/chosen": 2.5064592361450195,
      "eval_logits/rejected": 2.108433485031128,
      "eval_logps/chosen": -1.1957285404205322,
      "eval_logps/rejected": -3.7678382396698,
      "eval_loss": 0.46578800678253174,
      "eval_rewards/accuracies": 0.7368420958518982,
      "eval_rewards/chosen": -1.793592929840088,
      "eval_rewards/margins": 3.8581647872924805,
      "eval_rewards/rejected": -5.651757717132568,
      "eval_runtime": 25.415,
      "eval_samples_per_second": 29.628,
      "eval_steps_per_second": 3.738,
      "step": 400
    },
    {
      "epoch": 0.3523850451224753,
      "grad_norm": 0.9966821670532227,
      "learning_rate": 4.133551509975264e-06,
      "logits/chosen": 2.6411917209625244,
      "logits/rejected": 1.8634885549545288,
      "logps/chosen": -1.0934125185012817,
      "logps/rejected": -3.2207794189453125,
      "loss": 0.4335,
      "rewards/accuracies": 0.6625000238418579,
      "rewards/chosen": -1.6401188373565674,
      "rewards/margins": 3.1910502910614014,
      "rewards/rejected": -4.831169128417969,
      "step": 410
    },
    {
      "epoch": 0.36097980232058446,
      "grad_norm": 0.6384722590446472,
      "learning_rate": 4.093559974371725e-06,
      "logits/chosen": 3.1368844509124756,
      "logits/rejected": 2.3800251483917236,
      "logps/chosen": -1.2108217477798462,
      "logps/rejected": -3.484806537628174,
      "loss": 0.4543,
      "rewards/accuracies": 0.7124999761581421,
      "rewards/chosen": -1.816232681274414,
      "rewards/margins": 3.4109771251678467,
      "rewards/rejected": -5.227209568023682,
      "step": 420
    },
    {
      "epoch": 0.3695745595186936,
      "grad_norm": 0.856741726398468,
      "learning_rate": 4.052869450695776e-06,
      "logits/chosen": 3.155728816986084,
      "logits/rejected": 2.257838726043701,
      "logps/chosen": -1.4214586019515991,
      "logps/rejected": -4.186622619628906,
      "loss": 0.4091,
      "rewards/accuracies": 0.7749999761581421,
      "rewards/chosen": -2.132187604904175,
      "rewards/margins": 4.1477460861206055,
      "rewards/rejected": -6.279933929443359,
      "step": 430
    },
    {
      "epoch": 0.37816931671680276,
      "grad_norm": 1.3310774564743042,
      "learning_rate": 4.011497787155938e-06,
      "logits/chosen": 1.9942185878753662,
      "logits/rejected": 1.6246827840805054,
      "logps/chosen": -1.8575637340545654,
      "logps/rejected": -4.5355329513549805,
      "loss": 0.3995,
      "rewards/accuracies": 0.862500011920929,
      "rewards/chosen": -2.7863457202911377,
      "rewards/margins": 4.016953945159912,
      "rewards/rejected": -6.8032989501953125,
      "step": 440
    },
    {
      "epoch": 0.3867640739149119,
      "grad_norm": 2.0849101543426514,
      "learning_rate": 3.969463130731183e-06,
      "logits/chosen": 2.406555652618408,
      "logits/rejected": 2.0490009784698486,
      "logps/chosen": -2.392570972442627,
      "logps/rejected": -5.055584907531738,
      "loss": 0.3671,
      "rewards/accuracies": 0.887499988079071,
      "rewards/chosen": -3.588855743408203,
      "rewards/margins": 3.994520902633667,
      "rewards/rejected": -7.583376884460449,
      "step": 450
    },
    {
      "epoch": 0.3867640739149119,
      "eval_logits/chosen": 2.2324020862579346,
      "eval_logits/rejected": 2.365755319595337,
      "eval_logps/chosen": -2.736898422241211,
      "eval_logps/rejected": -5.73967170715332,
      "eval_loss": 0.3965117633342743,
      "eval_rewards/accuracies": 0.8736842274665833,
      "eval_rewards/chosen": -4.105347633361816,
      "eval_rewards/margins": 4.504159927368164,
      "eval_rewards/rejected": -8.60950756072998,
      "eval_runtime": 25.428,
      "eval_samples_per_second": 29.613,
      "eval_steps_per_second": 3.736,
      "step": 450
    },
    {
      "epoch": 0.39535883111302106,
      "grad_norm": 2.223949432373047,
      "learning_rate": 3.92678391921108e-06,
      "logits/chosen": 2.651564598083496,
      "logits/rejected": 2.383842945098877,
      "logps/chosen": -2.591308355331421,
      "logps/rejected": -5.308972358703613,
      "loss": 0.3412,
      "rewards/accuracies": 0.762499988079071,
      "rewards/chosen": -3.886962413787842,
      "rewards/margins": 4.07649564743042,
      "rewards/rejected": -7.963458061218262,
      "step": 460
    },
    {
      "epoch": 0.4039535883111302,
      "grad_norm": 3.110624074935913,
      "learning_rate": 3.88347887310836e-06,
      "logits/chosen": 2.5435309410095215,
      "logits/rejected": 2.46763277053833,
      "logps/chosen": -2.413583993911743,
      "logps/rejected": -5.543262481689453,
      "loss": 0.3832,
      "rewards/accuracies": 0.824999988079071,
      "rewards/chosen": -3.620375871658325,
      "rewards/margins": 4.694517135620117,
      "rewards/rejected": -8.314892768859863,
      "step": 470
    },
    {
      "epoch": 0.41254834550923936,
      "grad_norm": 1.6255794763565063,
      "learning_rate": 3.839566987447492e-06,
      "logits/chosen": 3.842928409576416,
      "logits/rejected": 3.5797982215881348,
      "logps/chosen": -2.6448044776916504,
      "logps/rejected": -4.98160982131958,
      "loss": 0.3547,
      "rewards/accuracies": 0.8125,
      "rewards/chosen": -3.9672069549560547,
      "rewards/margins": 3.5052082538604736,
      "rewards/rejected": -7.472414493560791,
      "step": 480
    },
    {
      "epoch": 0.4211431027073485,
      "grad_norm": 2.9274284839630127,
      "learning_rate": 3.795067523432826e-06,
      "logits/chosen": 3.3297150135040283,
      "logits/rejected": 3.0205535888671875,
      "logps/chosen": -2.811923027038574,
      "logps/rejected": -6.040881156921387,
      "loss": 0.3097,
      "rewards/accuracies": 0.887499988079071,
      "rewards/chosen": -4.217884063720703,
      "rewards/margins": 4.843437194824219,
      "rewards/rejected": -9.061322212219238,
      "step": 490
    },
    {
      "epoch": 0.42973785990545765,
      "grad_norm": 2.9143636226654053,
      "learning_rate": 3.7500000000000005e-06,
      "logits/chosen": 2.760014772415161,
      "logits/rejected": 2.535520315170288,
      "logps/chosen": -3.068406820297241,
      "logps/rejected": -5.877435684204102,
      "loss": 0.3031,
      "rewards/accuracies": 0.875,
      "rewards/chosen": -4.602609634399414,
      "rewards/margins": 4.21354341506958,
      "rewards/rejected": -8.816153526306152,
      "step": 500
    },
    {
      "epoch": 0.42973785990545765,
      "eval_logits/chosen": 2.0952131748199463,
      "eval_logits/rejected": 2.1864659786224365,
      "eval_logps/chosen": -3.392296075820923,
      "eval_logps/rejected": -6.948195457458496,
      "eval_loss": 0.33660775423049927,
      "eval_rewards/accuracies": 0.9263157844543457,
      "eval_rewards/chosen": -5.088444232940674,
      "eval_rewards/margins": 5.3338494300842285,
      "eval_rewards/rejected": -10.422293663024902,
      "eval_runtime": 25.4226,
      "eval_samples_per_second": 29.619,
      "eval_steps_per_second": 3.737,
      "step": 500
    },
    {
      "epoch": 0.4383326171035668,
      "grad_norm": 2.563810348510742,
      "learning_rate": 3.7043841852542884e-06,
      "logits/chosen": 2.950286388397217,
      "logits/rejected": 2.619025945663452,
      "logps/chosen": -3.237391710281372,
      "logps/rejected": -5.953216552734375,
      "loss": 0.318,
      "rewards/accuracies": 0.9125000238418579,
      "rewards/chosen": -4.856087684631348,
      "rewards/margins": 4.073737144470215,
      "rewards/rejected": -8.929824829101562,
      "step": 510
    },
    {
      "epoch": 0.44692737430167595,
      "grad_norm": 2.0339434146881104,
      "learning_rate": 3.658240087799655e-06,
      "logits/chosen": 2.987595558166504,
      "logits/rejected": 2.6243975162506104,
      "logps/chosen": -3.5633530616760254,
      "logps/rejected": -7.0458879470825195,
      "loss": 0.3053,
      "rewards/accuracies": 0.8999999761581421,
      "rewards/chosen": -5.345029354095459,
      "rewards/margins": 5.223802089691162,
      "rewards/rejected": -10.568831443786621,
      "step": 520
    },
    {
      "epoch": 0.45552213149978515,
      "grad_norm": 4.091029644012451,
      "learning_rate": 3.611587947962319e-06,
      "logits/chosen": 2.297576904296875,
      "logits/rejected": 2.0218777656555176,
      "logps/chosen": -3.297245502471924,
      "logps/rejected": -6.101919651031494,
      "loss": 0.3255,
      "rewards/accuracies": 0.887499988079071,
      "rewards/chosen": -4.945868015289307,
      "rewards/margins": 4.207010746002197,
      "rewards/rejected": -9.152878761291504,
      "step": 530
    },
    {
      "epoch": 0.4641168886978943,
      "grad_norm": 2.7896900177001953,
      "learning_rate": 3.564448228912682e-06,
      "logits/chosen": 2.103950023651123,
      "logits/rejected": 1.9478647708892822,
      "logps/chosen": -2.9360263347625732,
      "logps/rejected": -6.406435489654541,
      "loss": 0.3361,
      "rewards/accuracies": 0.8999999761581421,
      "rewards/chosen": -4.40403938293457,
      "rewards/margins": 5.20561408996582,
      "rewards/rejected": -9.60965347290039,
      "step": 540
    },
    {
      "epoch": 0.47271164589600345,
      "grad_norm": 2.657970905303955,
      "learning_rate": 3.516841607689501e-06,
      "logits/chosen": 2.1658639907836914,
      "logits/rejected": 2.214900493621826,
      "logps/chosen": -3.084073066711426,
      "logps/rejected": -6.935500144958496,
      "loss": 0.2928,
      "rewards/accuracies": 0.862500011920929,
      "rewards/chosen": -4.626110076904297,
      "rewards/margins": 5.7771406173706055,
      "rewards/rejected": -10.403249740600586,
      "step": 550
    },
    {
      "epoch": 0.47271164589600345,
      "eval_logits/chosen": 2.285294771194458,
      "eval_logits/rejected": 2.3312103748321533,
      "eval_logps/chosen": -3.35794997215271,
      "eval_logps/rejected": -7.37537145614624,
      "eval_loss": 0.3121817409992218,
      "eval_rewards/accuracies": 0.9263157844543457,
      "eval_rewards/chosen": -5.036925792694092,
      "eval_rewards/margins": 6.026132106781006,
      "eval_rewards/rejected": -11.063057899475098,
      "eval_runtime": 25.4015,
      "eval_samples_per_second": 29.644,
      "eval_steps_per_second": 3.74,
      "step": 550
    },
    {
      "epoch": 0.4813064030941126,
      "grad_norm": 2.940019369125366,
      "learning_rate": 3.4687889661302577e-06,
      "logits/chosen": 1.9122416973114014,
      "logits/rejected": 1.9943454265594482,
      "logps/chosen": -3.27177095413208,
      "logps/rejected": -7.023342132568359,
      "loss": 0.3105,
      "rewards/accuracies": 0.925000011920929,
      "rewards/chosen": -4.907656669616699,
      "rewards/margins": 5.6273579597473145,
      "rewards/rejected": -10.535014152526855,
      "step": 560
    },
    {
      "epoch": 0.48990116029222175,
      "grad_norm": 1.8887412548065186,
      "learning_rate": 3.4203113817116955e-06,
      "logits/chosen": 2.274843692779541,
      "logits/rejected": 2.392199993133545,
      "logps/chosen": -3.383749008178711,
      "logps/rejected": -7.265415191650391,
      "loss": 0.3003,
      "rewards/accuracies": 0.9750000238418579,
      "rewards/chosen": -5.075623512268066,
      "rewards/margins": 5.8224992752075195,
      "rewards/rejected": -10.898123741149902,
      "step": 570
    },
    {
      "epoch": 0.4984959174903309,
      "grad_norm": 1.6364414691925049,
      "learning_rate": 3.3714301183045382e-06,
      "logits/chosen": 2.423910617828369,
      "logits/rejected": 2.244985818862915,
      "logps/chosen": -3.0959205627441406,
      "logps/rejected": -6.822405815124512,
      "loss": 0.2471,
      "rewards/accuracies": 0.9624999761581421,
      "rewards/chosen": -4.643880844116211,
      "rewards/margins": 5.58972692489624,
      "rewards/rejected": -10.233609199523926,
      "step": 580
    },
    {
      "epoch": 0.50709067468844,
      "grad_norm": 2.6540188789367676,
      "learning_rate": 3.3221666168464584e-06,
      "logits/chosen": 2.8146812915802,
      "logits/rejected": 2.5971922874450684,
      "logps/chosen": -4.139407157897949,
      "logps/rejected": -7.71649694442749,
      "loss": 0.2809,
      "rewards/accuracies": 0.9624999761581421,
      "rewards/chosen": -6.209111213684082,
      "rewards/margins": 5.365634441375732,
      "rewards/rejected": -11.574746131896973,
      "step": 590
    },
    {
      "epoch": 0.5156854318865493,
      "grad_norm": 4.229885578155518,
      "learning_rate": 3.272542485937369e-06,
      "logits/chosen": 2.2735249996185303,
      "logits/rejected": 1.8577899932861328,
      "logps/chosen": -3.731342315673828,
      "logps/rejected": -7.2900390625,
      "loss": 0.2956,
      "rewards/accuracies": 0.887499988079071,
      "rewards/chosen": -5.5970139503479,
      "rewards/margins": 5.338044166564941,
      "rewards/rejected": -10.93505859375,
      "step": 600
    },
    {
      "epoch": 0.5156854318865493,
      "eval_logits/chosen": 2.3333992958068848,
      "eval_logits/rejected": 2.529745578765869,
      "eval_logps/chosen": -3.679597854614258,
      "eval_logps/rejected": -7.917842864990234,
      "eval_loss": 0.3030374050140381,
      "eval_rewards/accuracies": 0.9263157844543457,
      "eval_rewards/chosen": -5.519396781921387,
      "eval_rewards/margins": 6.357367992401123,
      "eval_rewards/rejected": -11.876765251159668,
      "eval_runtime": 25.5622,
      "eval_samples_per_second": 29.458,
      "eval_steps_per_second": 3.716,
      "step": 600
    }
  ],
  "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": 1.3837243562275635e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}