{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.17189514396218306,
  "eval_steps": 50,
  "global_step": 200,
  "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
    }
  ],
  "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": 4.569984252510208e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}