{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 100,
  "global_step": 314,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1.5625e-08,
      "logits/generated": -3.0857884883880615,
      "logits/real": -2.988919258117676,
      "logps/generated": -105.47663879394531,
      "logps/real": -159.43017578125,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/generated": 0.0,
      "rewards/margins": 0.0,
      "rewards/real": 0.0,
      "step": 1
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.5624999999999999e-07,
      "logits/generated": -3.0524420738220215,
      "logits/real": -2.888369560241699,
      "logps/generated": -98.16116333007812,
      "logps/real": -124.24053192138672,
      "loss": 0.4499,
      "rewards/accuracies": 0.7916666865348816,
      "rewards/generated": -0.5709724426269531,
      "rewards/margins": 0.7495355606079102,
      "rewards/real": 0.17856311798095703,
      "step": 10
    },
    {
      "epoch": 0.13,
      "learning_rate": 3.1249999999999997e-07,
      "logits/generated": -3.0165483951568604,
      "logits/real": -2.757232189178467,
      "logps/generated": -125.3254165649414,
      "logps/real": -120.93900299072266,
      "loss": 0.0982,
      "rewards/accuracies": 1.0,
      "rewards/generated": -2.5599706172943115,
      "rewards/margins": 3.3923709392547607,
      "rewards/real": 0.8324005007743835,
      "step": 20
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.6874999999999996e-07,
      "logits/generated": -2.9717984199523926,
      "logits/real": -2.703868865966797,
      "logps/generated": -137.14996337890625,
      "logps/real": -138.37025451660156,
      "loss": 0.0423,
      "rewards/accuracies": 1.0,
      "rewards/generated": -3.964935302734375,
      "rewards/margins": 4.9714460372924805,
      "rewards/real": 1.0065107345581055,
      "step": 30
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.858156028368794e-07,
      "logits/generated": -2.896350145339966,
      "logits/real": -2.632850408554077,
      "logps/generated": -149.0387420654297,
      "logps/real": -131.4845733642578,
      "loss": 0.0209,
      "rewards/accuracies": 0.987500011920929,
      "rewards/generated": -5.3386735916137695,
      "rewards/margins": 6.378259658813477,
      "rewards/real": 1.0395863056182861,
      "step": 40
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.6808510638297873e-07,
      "logits/generated": -2.864506244659424,
      "logits/real": -2.635793685913086,
      "logps/generated": -161.58311462402344,
      "logps/real": -133.5462646484375,
      "loss": 0.0157,
      "rewards/accuracies": 1.0,
      "rewards/generated": -6.72866678237915,
      "rewards/margins": 7.655924320220947,
      "rewards/real": 0.9272577166557312,
      "step": 50
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.50354609929078e-07,
      "logits/generated": -2.8477931022644043,
      "logits/real": -2.5890610218048096,
      "logps/generated": -163.30792236328125,
      "logps/real": -120.96208190917969,
      "loss": 0.016,
      "rewards/accuracies": 1.0,
      "rewards/generated": -7.271246433258057,
      "rewards/margins": 7.847572326660156,
      "rewards/real": 0.5763252973556519,
      "step": 60
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.326241134751773e-07,
      "logits/generated": -2.817225694656372,
      "logits/real": -2.618878126144409,
      "logps/generated": -178.3530731201172,
      "logps/real": -133.58116149902344,
      "loss": 0.0134,
      "rewards/accuracies": 1.0,
      "rewards/generated": -8.513948440551758,
      "rewards/margins": 9.06941032409668,
      "rewards/real": 0.5554608702659607,
      "step": 70
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.148936170212766e-07,
      "logits/generated": -2.743182420730591,
      "logits/real": -2.5085911750793457,
      "logps/generated": -182.21102905273438,
      "logps/real": -141.52438354492188,
      "loss": 0.0132,
      "rewards/accuracies": 1.0,
      "rewards/generated": -9.143477439880371,
      "rewards/margins": 8.894549369812012,
      "rewards/real": -0.24892878532409668,
      "step": 80
    },
    {
      "epoch": 0.57,
      "learning_rate": 3.971631205673759e-07,
      "logits/generated": -2.667142152786255,
      "logits/real": -2.3680872917175293,
      "logps/generated": -221.4196014404297,
      "logps/real": -156.9970703125,
      "loss": 0.0073,
      "rewards/accuracies": 1.0,
      "rewards/generated": -11.756684303283691,
      "rewards/margins": 11.24407958984375,
      "rewards/real": -0.5126041769981384,
      "step": 90
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.7943262411347514e-07,
      "logits/generated": -2.716907024383545,
      "logits/real": -2.384260654449463,
      "logps/generated": -195.7281951904297,
      "logps/real": -141.03294372558594,
      "loss": 0.0106,
      "rewards/accuracies": 1.0,
      "rewards/generated": -10.495864868164062,
      "rewards/margins": 10.102469444274902,
      "rewards/real": -0.39339518547058105,
      "step": 100
    },
    {
      "epoch": 0.64,
      "eval_logits/generated": -2.708615779876709,
      "eval_logits/real": -2.4488255977630615,
      "eval_logps/generated": -208.8447265625,
      "eval_logps/real": -143.2593536376953,
      "eval_loss": 0.008355233818292618,
      "eval_rewards/accuracies": 0.9992038011550903,
      "eval_rewards/generated": -11.555154800415039,
      "eval_rewards/margins": 10.695781707763672,
      "eval_rewards/real": -0.8593728542327881,
      "eval_runtime": 338.0923,
      "eval_samples_per_second": 14.789,
      "eval_steps_per_second": 0.464,
      "step": 100
    },
    {
      "epoch": 0.7,
      "learning_rate": 3.617021276595745e-07,
      "logits/generated": -2.6799185276031494,
      "logits/real": -2.4362854957580566,
      "logps/generated": -229.9918975830078,
      "logps/real": -144.79042053222656,
      "loss": 0.0055,
      "rewards/accuracies": 1.0,
      "rewards/generated": -13.137945175170898,
      "rewards/margins": 11.87834358215332,
      "rewards/real": -1.259602427482605,
      "step": 110
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.4397163120567375e-07,
      "logits/generated": -2.70621919631958,
      "logits/real": -2.4253954887390137,
      "logps/generated": -228.62405395507812,
      "logps/real": -158.47494506835938,
      "loss": 0.0066,
      "rewards/accuracies": 1.0,
      "rewards/generated": -13.207649230957031,
      "rewards/margins": 12.149269104003906,
      "rewards/real": -1.0583809614181519,
      "step": 120
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.2624113475177305e-07,
      "logits/generated": -2.662909746170044,
      "logits/real": -2.3800911903381348,
      "logps/generated": -227.56619262695312,
      "logps/real": -156.76431274414062,
      "loss": 0.0066,
      "rewards/accuracies": 1.0,
      "rewards/generated": -13.599740982055664,
      "rewards/margins": 12.402183532714844,
      "rewards/real": -1.1975574493408203,
      "step": 130
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.085106382978723e-07,
      "logits/generated": -2.69126033782959,
      "logits/real": -2.4004807472229004,
      "logps/generated": -229.597900390625,
      "logps/real": -146.2201385498047,
      "loss": 0.0055,
      "rewards/accuracies": 1.0,
      "rewards/generated": -13.650607109069824,
      "rewards/margins": 12.299604415893555,
      "rewards/real": -1.3510032892227173,
      "step": 140
    },
    {
      "epoch": 0.96,
      "learning_rate": 2.907801418439716e-07,
      "logits/generated": -2.6775763034820557,
      "logits/real": -2.324918508529663,
      "logps/generated": -218.3529510498047,
      "logps/real": -140.95547485351562,
      "loss": 0.0138,
      "rewards/accuracies": 1.0,
      "rewards/generated": -12.812429428100586,
      "rewards/margins": 12.05975341796875,
      "rewards/real": -0.752677321434021,
      "step": 150
    },
    {
      "epoch": 1.02,
      "learning_rate": 2.730496453900709e-07,
      "logits/generated": -2.6712429523468018,
      "logits/real": -2.2760770320892334,
      "logps/generated": -196.49375915527344,
      "logps/real": -121.7732925415039,
      "loss": 0.0069,
      "rewards/accuracies": 1.0,
      "rewards/generated": -10.348185539245605,
      "rewards/margins": 9.94708251953125,
      "rewards/real": -0.40110310912132263,
      "step": 160
    },
    {
      "epoch": 1.08,
      "learning_rate": 2.5531914893617016e-07,
      "logits/generated": -2.6528658866882324,
      "logits/real": -2.1584651470184326,
      "logps/generated": -213.1004638671875,
      "logps/real": -121.10084533691406,
      "loss": 0.003,
      "rewards/accuracies": 1.0,
      "rewards/generated": -11.93848991394043,
      "rewards/margins": 11.793214797973633,
      "rewards/real": -0.14527548849582672,
      "step": 170
    },
    {
      "epoch": 1.15,
      "learning_rate": 2.375886524822695e-07,
      "logits/generated": -2.6257143020629883,
      "logits/real": -2.2728638648986816,
      "logps/generated": -228.39248657226562,
      "logps/real": -152.61045837402344,
      "loss": 0.0032,
      "rewards/accuracies": 1.0,
      "rewards/generated": -13.100919723510742,
      "rewards/margins": 12.766759872436523,
      "rewards/real": -0.3341600298881531,
      "step": 180
    },
    {
      "epoch": 1.21,
      "learning_rate": 2.198581560283688e-07,
      "logits/generated": -2.609994411468506,
      "logits/real": -2.2576498985290527,
      "logps/generated": -222.8015594482422,
      "logps/real": -145.87921142578125,
      "loss": 0.0036,
      "rewards/accuracies": 0.987500011920929,
      "rewards/generated": -13.061747550964355,
      "rewards/margins": 12.396347999572754,
      "rewards/real": -0.6654000282287598,
      "step": 190
    },
    {
      "epoch": 1.27,
      "learning_rate": 2.0212765957446807e-07,
      "logits/generated": -2.600148916244507,
      "logits/real": -2.1764094829559326,
      "logps/generated": -236.9789581298828,
      "logps/real": -137.09503173828125,
      "loss": 0.002,
      "rewards/accuracies": 1.0,
      "rewards/generated": -14.19157886505127,
      "rewards/margins": 13.38233470916748,
      "rewards/real": -0.8092441558837891,
      "step": 200
    },
    {
      "epoch": 1.27,
      "eval_logits/generated": -2.600484609603882,
      "eval_logits/real": -2.2709195613861084,
      "eval_logps/generated": -234.47348022460938,
      "eval_logps/real": -144.0410919189453,
      "eval_loss": 0.0056638033129274845,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/generated": -14.118030548095703,
      "eval_rewards/margins": 13.180484771728516,
      "eval_rewards/real": -0.9375430345535278,
      "eval_runtime": 334.9223,
      "eval_samples_per_second": 14.929,
      "eval_steps_per_second": 0.469,
      "step": 200
    },
    {
      "epoch": 1.34,
      "learning_rate": 1.8439716312056735e-07,
      "logits/generated": -2.617143154144287,
      "logits/real": -2.263977289199829,
      "logps/generated": -242.97866821289062,
      "logps/real": -152.24502563476562,
      "loss": 0.0025,
      "rewards/accuracies": 1.0,
      "rewards/generated": -14.723902702331543,
      "rewards/margins": 13.91853141784668,
      "rewards/real": -0.8053719401359558,
      "step": 210
    },
    {
      "epoch": 1.4,
      "learning_rate": 1.6666666666666665e-07,
      "logits/generated": -2.5576019287109375,
      "logits/real": -2.3169806003570557,
      "logps/generated": -233.3745880126953,
      "logps/real": -145.44570922851562,
      "loss": 0.0023,
      "rewards/accuracies": 1.0,
      "rewards/generated": -14.311078071594238,
      "rewards/margins": 13.486970901489258,
      "rewards/real": -0.8241075277328491,
      "step": 220
    },
    {
      "epoch": 1.46,
      "learning_rate": 1.4893617021276595e-07,
      "logits/generated": -2.553480386734009,
      "logits/real": -2.315396785736084,
      "logps/generated": -243.16702270507812,
      "logps/real": -168.13119506835938,
      "loss": 0.0013,
      "rewards/accuracies": 1.0,
      "rewards/generated": -14.701271057128906,
      "rewards/margins": 13.865699768066406,
      "rewards/real": -0.8355696797370911,
      "step": 230
    },
    {
      "epoch": 1.53,
      "learning_rate": 1.3120567375886523e-07,
      "logits/generated": -2.6132516860961914,
      "logits/real": -2.2840161323547363,
      "logps/generated": -246.56961059570312,
      "logps/real": -152.701171875,
      "loss": 0.0008,
      "rewards/accuracies": 1.0,
      "rewards/generated": -14.995321273803711,
      "rewards/margins": 14.276300430297852,
      "rewards/real": -0.7190229892730713,
      "step": 240
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.1347517730496453e-07,
      "logits/generated": -2.591722249984741,
      "logits/real": -2.277804374694824,
      "logps/generated": -263.14129638671875,
      "logps/real": -158.726806640625,
      "loss": 0.0038,
      "rewards/accuracies": 1.0,
      "rewards/generated": -16.25307273864746,
      "rewards/margins": 15.087217330932617,
      "rewards/real": -1.1658554077148438,
      "step": 250
    },
    {
      "epoch": 1.66,
      "learning_rate": 9.574468085106382e-08,
      "logits/generated": -2.569918155670166,
      "logits/real": -2.1422371864318848,
      "logps/generated": -244.6776123046875,
      "logps/real": -145.0582733154297,
      "loss": 0.0019,
      "rewards/accuracies": 1.0,
      "rewards/generated": -15.619791984558105,
      "rewards/margins": 14.159820556640625,
      "rewards/real": -1.4599710702896118,
      "step": 260
    },
    {
      "epoch": 1.72,
      "learning_rate": 7.801418439716311e-08,
      "logits/generated": -2.539750099182129,
      "logits/real": -2.137476682662964,
      "logps/generated": -265.46429443359375,
      "logps/real": -163.37588500976562,
      "loss": 0.0013,
      "rewards/accuracies": 1.0,
      "rewards/generated": -16.41511344909668,
      "rewards/margins": 14.795074462890625,
      "rewards/real": -1.6200393438339233,
      "step": 270
    },
    {
      "epoch": 1.78,
      "learning_rate": 6.02836879432624e-08,
      "logits/generated": -2.574856996536255,
      "logits/real": -2.0835378170013428,
      "logps/generated": -262.6173095703125,
      "logps/real": -142.27984619140625,
      "loss": 0.0005,
      "rewards/accuracies": 1.0,
      "rewards/generated": -16.557262420654297,
      "rewards/margins": 15.236516952514648,
      "rewards/real": -1.3207473754882812,
      "step": 280
    },
    {
      "epoch": 1.85,
      "learning_rate": 4.25531914893617e-08,
      "logits/generated": -2.5489261150360107,
      "logits/real": -2.2142765522003174,
      "logps/generated": -268.306396484375,
      "logps/real": -147.05963134765625,
      "loss": 0.0016,
      "rewards/accuracies": 1.0,
      "rewards/generated": -17.089282989501953,
      "rewards/margins": 15.543319702148438,
      "rewards/real": -1.5459634065628052,
      "step": 290
    },
    {
      "epoch": 1.91,
      "learning_rate": 2.4822695035460993e-08,
      "logits/generated": -2.556087017059326,
      "logits/real": -2.1201999187469482,
      "logps/generated": -249.31875610351562,
      "logps/real": -138.080322265625,
      "loss": 0.0007,
      "rewards/accuracies": 1.0,
      "rewards/generated": -15.890460014343262,
      "rewards/margins": 14.16200065612793,
      "rewards/real": -1.728456735610962,
      "step": 300
    },
    {
      "epoch": 1.91,
      "eval_logits/generated": -2.5437142848968506,
      "eval_logits/real": -2.19522762298584,
      "eval_logps/generated": -257.48858642578125,
      "eval_logps/real": -151.0966796875,
      "eval_loss": 0.005383754149079323,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/generated": -16.419538497924805,
      "eval_rewards/margins": 14.776435852050781,
      "eval_rewards/real": -1.6431050300598145,
      "eval_runtime": 335.2989,
      "eval_samples_per_second": 14.912,
      "eval_steps_per_second": 0.468,
      "step": 300
    },
    {
      "epoch": 1.97,
      "learning_rate": 7.092198581560283e-09,
      "logits/generated": -2.5656914710998535,
      "logits/real": -2.300166368484497,
      "logps/generated": -260.5529479980469,
      "logps/real": -153.91053771972656,
      "loss": 0.0008,
      "rewards/accuracies": 1.0,
      "rewards/generated": -16.434940338134766,
      "rewards/margins": 14.854705810546875,
      "rewards/real": -1.5802339315414429,
      "step": 310
    },
    {
      "epoch": 2.0,
      "step": 314,
      "total_flos": 0.0,
      "train_loss": 0.025043586236395084,
      "train_runtime": 2649.1704,
      "train_samples_per_second": 3.775,
      "train_steps_per_second": 0.119
    }
  ],
  "logging_steps": 10,
  "max_steps": 314,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}