{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.21486892995272883,
  "eval_steps": 50,
  "global_step": 250,
  "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
    }
  ],
  "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": 5.770513103066235e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}