{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.17761989342806395,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008880994671403197,
      "grad_norm": 0.045356735587120056,
      "learning_rate": 4.999451708687114e-06,
      "logits/chosen": 14.352750778198242,
      "logits/rejected": 14.82281494140625,
      "logps/chosen": -0.2592294216156006,
      "logps/rejected": -0.32852867245674133,
      "loss": 0.9315,
      "rewards/accuracies": 0.574999988079071,
      "rewards/chosen": -0.38884416222572327,
      "rewards/margins": 0.10394889116287231,
      "rewards/rejected": -0.4927930235862732,
      "step": 10
    },
    {
      "epoch": 0.017761989342806393,
      "grad_norm": 0.05255189165472984,
      "learning_rate": 4.997807075247147e-06,
      "logits/chosen": 14.80792236328125,
      "logits/rejected": 15.017183303833008,
      "logps/chosen": -0.2825874388217926,
      "logps/rejected": -0.36373966932296753,
      "loss": 0.9318,
      "rewards/accuracies": 0.5249999761581421,
      "rewards/chosen": -0.4238811433315277,
      "rewards/margins": 0.12172831594944,
      "rewards/rejected": -0.5456094741821289,
      "step": 20
    },
    {
      "epoch": 0.02664298401420959,
      "grad_norm": 0.056027185171842575,
      "learning_rate": 4.9950668210706795e-06,
      "logits/chosen": 14.45336627960205,
      "logits/rejected": 15.261484146118164,
      "logps/chosen": -0.2638034522533417,
      "logps/rejected": -0.37216562032699585,
      "loss": 0.9211,
      "rewards/accuracies": 0.6625000238418579,
      "rewards/chosen": -0.3957051932811737,
      "rewards/margins": 0.1625431776046753,
      "rewards/rejected": -0.5582484006881714,
      "step": 30
    },
    {
      "epoch": 0.035523978685612786,
      "grad_norm": 0.06511653959751129,
      "learning_rate": 4.9912321481237616e-06,
      "logits/chosen": 14.59851360321045,
      "logits/rejected": 15.112770080566406,
      "logps/chosen": -0.28972768783569336,
      "logps/rejected": -0.36043626070022583,
      "loss": 0.941,
      "rewards/accuracies": 0.5375000238418579,
      "rewards/chosen": -0.43459147214889526,
      "rewards/margins": 0.10606291145086288,
      "rewards/rejected": -0.5406544208526611,
      "step": 40
    },
    {
      "epoch": 0.04440497335701599,
      "grad_norm": 0.0637577474117279,
      "learning_rate": 4.986304738420684e-06,
      "logits/chosen": 14.678179740905762,
      "logits/rejected": 15.114399909973145,
      "logps/chosen": -0.3033604919910431,
      "logps/rejected": -0.3262741267681122,
      "loss": 0.929,
      "rewards/accuracies": 0.44999998807907104,
      "rewards/chosen": -0.45504075288772583,
      "rewards/margins": 0.03437047079205513,
      "rewards/rejected": -0.4894111752510071,
      "step": 50
    },
    {
      "epoch": 0.04440497335701599,
      "eval_logits/chosen": 14.936029434204102,
      "eval_logits/rejected": 14.780267715454102,
      "eval_logps/chosen": -0.29386037588119507,
      "eval_logps/rejected": -0.3304942548274994,
      "eval_loss": 0.9458721876144409,
      "eval_rewards/accuracies": 0.49450549483299255,
      "eval_rewards/chosen": -0.4407905340194702,
      "eval_rewards/margins": 0.05495081841945648,
      "eval_rewards/rejected": -0.49574142694473267,
      "eval_runtime": 27.7436,
      "eval_samples_per_second": 26.24,
      "eval_steps_per_second": 3.28,
      "step": 50
    },
    {
      "epoch": 0.05328596802841918,
      "grad_norm": 0.06470987200737,
      "learning_rate": 4.980286753286196e-06,
      "logits/chosen": 14.19079303741455,
      "logits/rejected": 14.986845016479492,
      "logps/chosen": -0.26126712560653687,
      "logps/rejected": -0.31976616382598877,
      "loss": 0.9335,
      "rewards/accuracies": 0.5,
      "rewards/chosen": -0.3919006288051605,
      "rewards/margins": 0.08774860948324203,
      "rewards/rejected": -0.47964924573898315,
      "step": 60
    },
    {
      "epoch": 0.06216696269982238,
      "grad_norm": 0.06163545697927475,
      "learning_rate": 4.973180832407471e-06,
      "logits/chosen": 14.062408447265625,
      "logits/rejected": 15.050743103027344,
      "logps/chosen": -0.2698076367378235,
      "logps/rejected": -0.37131980061531067,
      "loss": 0.9234,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": -0.4047114849090576,
      "rewards/margins": 0.1522682160139084,
      "rewards/rejected": -0.556979775428772,
      "step": 70
    },
    {
      "epoch": 0.07104795737122557,
      "grad_norm": 0.05943402647972107,
      "learning_rate": 4.964990092676263e-06,
      "logits/chosen": 14.523780822753906,
      "logits/rejected": 15.173608779907227,
      "logps/chosen": -0.2835150957107544,
      "logps/rejected": -0.35379332304000854,
      "loss": 0.9317,
      "rewards/accuracies": 0.550000011920929,
      "rewards/chosen": -0.4252726137638092,
      "rewards/margins": 0.10541732609272003,
      "rewards/rejected": -0.5306899547576904,
      "step": 80
    },
    {
      "epoch": 0.07992895204262877,
      "grad_norm": 0.05566830188035965,
      "learning_rate": 4.9557181268217225e-06,
      "logits/chosen": 14.752237319946289,
      "logits/rejected": 15.213434219360352,
      "logps/chosen": -0.25490278005599976,
      "logps/rejected": -0.31673288345336914,
      "loss": 0.9276,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": -0.38235417008399963,
      "rewards/margins": 0.09274514764547348,
      "rewards/rejected": -0.4750993847846985,
      "step": 90
    },
    {
      "epoch": 0.08880994671403197,
      "grad_norm": 0.07879115641117096,
      "learning_rate": 4.9453690018345144e-06,
      "logits/chosen": 14.362078666687012,
      "logits/rejected": 14.708786010742188,
      "logps/chosen": -0.27969443798065186,
      "logps/rejected": -0.3294224143028259,
      "loss": 0.9448,
      "rewards/accuracies": 0.5249999761581421,
      "rewards/chosen": -0.41954168677330017,
      "rewards/margins": 0.0745919868350029,
      "rewards/rejected": -0.4941336512565613,
      "step": 100
    },
    {
      "epoch": 0.08880994671403197,
      "eval_logits/chosen": 14.668691635131836,
      "eval_logits/rejected": 14.53217601776123,
      "eval_logps/chosen": -0.2837528884410858,
      "eval_logps/rejected": -0.33105531334877014,
      "eval_loss": 0.9382757544517517,
      "eval_rewards/accuracies": 0.5164835453033447,
      "eval_rewards/chosen": -0.4256293475627899,
      "eval_rewards/margins": 0.07095365226268768,
      "eval_rewards/rejected": -0.4965830445289612,
      "eval_runtime": 26.9204,
      "eval_samples_per_second": 27.043,
      "eval_steps_per_second": 3.38,
      "step": 100
    },
    {
      "epoch": 0.09769094138543517,
      "grad_norm": 0.0677201971411705,
      "learning_rate": 4.933947257182901e-06,
      "logits/chosen": 14.2677640914917,
      "logits/rejected": 14.437828063964844,
      "logps/chosen": -0.26914283633232117,
      "logps/rejected": -0.3498677909374237,
      "loss": 0.9307,
      "rewards/accuracies": 0.5874999761581421,
      "rewards/chosen": -0.40371423959732056,
      "rewards/margins": 0.12108743190765381,
      "rewards/rejected": -0.5248016715049744,
      "step": 110
    },
    {
      "epoch": 0.10657193605683836,
      "grad_norm": 0.08429163694381714,
      "learning_rate": 4.921457902821578e-06,
      "logits/chosen": 13.978253364562988,
      "logits/rejected": 14.673884391784668,
      "logps/chosen": -0.2842218279838562,
      "logps/rejected": -0.35421326756477356,
      "loss": 0.9046,
      "rewards/accuracies": 0.574999988079071,
      "rewards/chosen": -0.4263327121734619,
      "rewards/margins": 0.10498716682195663,
      "rewards/rejected": -0.5313198566436768,
      "step": 120
    },
    {
      "epoch": 0.11545293072824156,
      "grad_norm": 0.08969741314649582,
      "learning_rate": 4.907906416994146e-06,
      "logits/chosen": 13.98906135559082,
      "logits/rejected": 14.70555305480957,
      "logps/chosen": -0.26557397842407227,
      "logps/rejected": -0.3823702037334442,
      "loss": 0.9151,
      "rewards/accuracies": 0.6000000238418579,
      "rewards/chosen": -0.3983609974384308,
      "rewards/margins": 0.1751943826675415,
      "rewards/rejected": -0.5735553503036499,
      "step": 130
    },
    {
      "epoch": 0.12433392539964476,
      "grad_norm": 0.10470724105834961,
      "learning_rate": 4.893298743830168e-06,
      "logits/chosen": 13.948530197143555,
      "logits/rejected": 14.77311897277832,
      "logps/chosen": -0.2675064504146576,
      "logps/rejected": -0.3631269335746765,
      "loss": 0.9053,
      "rewards/accuracies": 0.6000000238418579,
      "rewards/chosen": -0.4012596607208252,
      "rewards/margins": 0.14343078434467316,
      "rewards/rejected": -0.5446904301643372,
      "step": 140
    },
    {
      "epoch": 0.13321492007104796,
      "grad_norm": 0.09238290041685104,
      "learning_rate": 4.8776412907378845e-06,
      "logits/chosen": 12.939355850219727,
      "logits/rejected": 13.387840270996094,
      "logps/chosen": -0.27794820070266724,
      "logps/rejected": -0.3520648777484894,
      "loss": 0.9097,
      "rewards/accuracies": 0.5375000238418579,
      "rewards/chosen": -0.41692233085632324,
      "rewards/margins": 0.11117497831583023,
      "rewards/rejected": -0.5280972719192505,
      "step": 150
    },
    {
      "epoch": 0.13321492007104796,
      "eval_logits/chosen": 13.123927116394043,
      "eval_logits/rejected": 13.085403442382812,
      "eval_logps/chosen": -0.28104570508003235,
      "eval_logps/rejected": -0.3562033474445343,
      "eval_loss": 0.9194123148918152,
      "eval_rewards/accuracies": 0.5824176073074341,
      "eval_rewards/chosen": -0.42156851291656494,
      "eval_rewards/margins": 0.11273646354675293,
      "eval_rewards/rejected": -0.5343050360679626,
      "eval_runtime": 26.928,
      "eval_samples_per_second": 27.035,
      "eval_steps_per_second": 3.379,
      "step": 150
    },
    {
      "epoch": 0.14209591474245115,
      "grad_norm": 0.14459910988807678,
      "learning_rate": 4.860940925593703e-06,
      "logits/chosen": 11.937938690185547,
      "logits/rejected": 13.300163269042969,
      "logps/chosen": -0.24840429425239563,
      "logps/rejected": -0.4205872118473053,
      "loss": 0.8929,
      "rewards/accuracies": 0.6000000238418579,
      "rewards/chosen": -0.37260642647743225,
      "rewards/margins": 0.2582743763923645,
      "rewards/rejected": -0.6308808326721191,
      "step": 160
    },
    {
      "epoch": 0.15097690941385436,
      "grad_norm": 0.13749755918979645,
      "learning_rate": 4.84320497372973e-06,
      "logits/chosen": 12.549962997436523,
      "logits/rejected": 12.858027458190918,
      "logps/chosen": -0.2944340109825134,
      "logps/rejected": -0.38480544090270996,
      "loss": 0.895,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -0.44165101647377014,
      "rewards/margins": 0.1355571448802948,
      "rewards/rejected": -0.5772081613540649,
      "step": 170
    },
    {
      "epoch": 0.15985790408525755,
      "grad_norm": 0.14530803263187408,
      "learning_rate": 4.824441214720629e-06,
      "logits/chosen": 10.892537117004395,
      "logits/rejected": 11.756756782531738,
      "logps/chosen": -0.2693363130092621,
      "logps/rejected": -0.3874126374721527,
      "loss": 0.8801,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": -0.4040044844150543,
      "rewards/margins": 0.17711447179317474,
      "rewards/rejected": -0.5811189413070679,
      "step": 180
    },
    {
      "epoch": 0.16873889875666073,
      "grad_norm": 0.20053793489933014,
      "learning_rate": 4.804657878971252e-06,
      "logits/chosen": 9.238119125366211,
      "logits/rejected": 10.233763694763184,
      "logps/chosen": -0.269479900598526,
      "logps/rejected": -0.4149019122123718,
      "loss": 0.8776,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": -0.4042198657989502,
      "rewards/margins": 0.21813304722309113,
      "rewards/rejected": -0.6223528385162354,
      "step": 190
    },
    {
      "epoch": 0.17761989342806395,
      "grad_norm": 0.20254959166049957,
      "learning_rate": 4.783863644106502e-06,
      "logits/chosen": 9.261235237121582,
      "logits/rejected": 9.7451753616333,
      "logps/chosen": -0.29611462354660034,
      "logps/rejected": -0.44530659914016724,
      "loss": 0.8596,
      "rewards/accuracies": 0.5874999761581421,
      "rewards/chosen": -0.4441719651222229,
      "rewards/margins": 0.22378793358802795,
      "rewards/rejected": -0.6679598689079285,
      "step": 200
    },
    {
      "epoch": 0.17761989342806395,
      "eval_logits/chosen": 8.231317520141602,
      "eval_logits/rejected": 8.285564422607422,
      "eval_logps/chosen": -0.3201982080936432,
      "eval_logps/rejected": -0.4862101078033447,
      "eval_loss": 0.8602121472358704,
      "eval_rewards/accuracies": 0.6153846383094788,
      "eval_rewards/chosen": -0.480297327041626,
      "eval_rewards/margins": 0.2490178644657135,
      "eval_rewards/rejected": -0.7293152213096619,
      "eval_runtime": 26.9054,
      "eval_samples_per_second": 27.058,
      "eval_steps_per_second": 3.382,
      "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": 4.869276493026427e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}