{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14496692941922623,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007248346470961312,
      "grad_norm": 0.07201674580574036,
      "learning_rate": 4.999451708687114e-06,
      "logits/chosen": -1.9793262481689453,
      "logits/rejected": -2.5381760597229004,
      "logps/chosen": -0.28126341104507446,
      "logps/rejected": -0.3779803514480591,
      "loss": 7.3904,
      "rewards/accuracies": 0.550000011920929,
      "rewards/chosen": -0.4218950867652893,
      "rewards/margins": 0.14507544040679932,
      "rewards/rejected": -0.5669704675674438,
      "step": 10
    },
    {
      "epoch": 0.014496692941922623,
      "grad_norm": 0.07562297582626343,
      "learning_rate": 4.997807075247147e-06,
      "logits/chosen": -2.0567643642425537,
      "logits/rejected": -2.4989147186279297,
      "logps/chosen": -0.27690139412879944,
      "logps/rejected": -0.33544114232063293,
      "loss": 7.3756,
      "rewards/accuracies": 0.574999988079071,
      "rewards/chosen": -0.41535210609436035,
      "rewards/margins": 0.08780960738658905,
      "rewards/rejected": -0.5031617283821106,
      "step": 20
    },
    {
      "epoch": 0.021745039412883936,
      "grad_norm": 0.09685570746660233,
      "learning_rate": 4.9950668210706795e-06,
      "logits/chosen": -2.10174298286438,
      "logits/rejected": -2.378197431564331,
      "logps/chosen": -0.26717427372932434,
      "logps/rejected": -0.30565372109413147,
      "loss": 7.451,
      "rewards/accuracies": 0.4375,
      "rewards/chosen": -0.4007614254951477,
      "rewards/margins": 0.05771917849779129,
      "rewards/rejected": -0.4584805369377136,
      "step": 30
    },
    {
      "epoch": 0.028993385883845247,
      "grad_norm": 0.08213861286640167,
      "learning_rate": 4.9912321481237616e-06,
      "logits/chosen": -2.1633317470550537,
      "logits/rejected": -2.387866497039795,
      "logps/chosen": -0.27634260058403015,
      "logps/rejected": -0.37035584449768066,
      "loss": 7.3892,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": -0.4145139157772064,
      "rewards/margins": 0.14101983606815338,
      "rewards/rejected": -0.555533766746521,
      "step": 40
    },
    {
      "epoch": 0.03624173235480656,
      "grad_norm": 0.08846044540405273,
      "learning_rate": 4.986304738420684e-06,
      "logits/chosen": -2.1402599811553955,
      "logits/rejected": -2.4459526538848877,
      "logps/chosen": -0.2535383999347687,
      "logps/rejected": -0.3090876042842865,
      "loss": 7.5171,
      "rewards/accuracies": 0.512499988079071,
      "rewards/chosen": -0.3803076148033142,
      "rewards/margins": 0.08332376182079315,
      "rewards/rejected": -0.4636313319206238,
      "step": 50
    },
    {
      "epoch": 0.03624173235480656,
      "eval_logits/chosen": -2.1165692806243896,
      "eval_logits/rejected": -2.476428747177124,
      "eval_logps/chosen": -0.2828062176704407,
      "eval_logps/rejected": -0.3432886600494385,
      "eval_loss": 0.9120001792907715,
      "eval_rewards/accuracies": 0.5089285969734192,
      "eval_rewards/chosen": -0.4242093861103058,
      "eval_rewards/margins": 0.09072363376617432,
      "eval_rewards/rejected": -0.5149329900741577,
      "eval_runtime": 30.971,
      "eval_samples_per_second": 28.801,
      "eval_steps_per_second": 3.616,
      "step": 50
    },
    {
      "epoch": 0.04349007882576787,
      "grad_norm": 0.11753705143928528,
      "learning_rate": 4.980286753286196e-06,
      "logits/chosen": -2.0575368404388428,
      "logits/rejected": -2.5456700325012207,
      "logps/chosen": -0.24622221291065216,
      "logps/rejected": -0.32402220368385315,
      "loss": 7.3926,
      "rewards/accuracies": 0.5874999761581421,
      "rewards/chosen": -0.36933332681655884,
      "rewards/margins": 0.11669999361038208,
      "rewards/rejected": -0.48603329062461853,
      "step": 60
    },
    {
      "epoch": 0.05073842529672919,
      "grad_norm": 0.09996571391820908,
      "learning_rate": 4.973180832407471e-06,
      "logits/chosen": -1.9278606176376343,
      "logits/rejected": -2.4620182514190674,
      "logps/chosen": -0.2596542239189148,
      "logps/rejected": -0.3665880560874939,
      "loss": 7.185,
      "rewards/accuracies": 0.5874999761581421,
      "rewards/chosen": -0.3894812762737274,
      "rewards/margins": 0.160400852560997,
      "rewards/rejected": -0.5498821139335632,
      "step": 70
    },
    {
      "epoch": 0.057986771767690494,
      "grad_norm": 0.07287321239709854,
      "learning_rate": 4.964990092676263e-06,
      "logits/chosen": -2.078031063079834,
      "logits/rejected": -2.461479663848877,
      "logps/chosen": -0.24513795971870422,
      "logps/rejected": -0.3448730707168579,
      "loss": 7.365,
      "rewards/accuracies": 0.5874999761581421,
      "rewards/chosen": -0.36770695447921753,
      "rewards/margins": 0.14960262179374695,
      "rewards/rejected": -0.5173095464706421,
      "step": 80
    },
    {
      "epoch": 0.0652351182386518,
      "grad_norm": 0.09656044095754623,
      "learning_rate": 4.9557181268217225e-06,
      "logits/chosen": -1.9979238510131836,
      "logits/rejected": -2.4381277561187744,
      "logps/chosen": -0.24047240614891052,
      "logps/rejected": -0.3277527987957001,
      "loss": 7.2664,
      "rewards/accuracies": 0.6000000238418579,
      "rewards/chosen": -0.36070865392684937,
      "rewards/margins": 0.13092057406902313,
      "rewards/rejected": -0.4916292130947113,
      "step": 90
    },
    {
      "epoch": 0.07248346470961312,
      "grad_norm": 0.08125138282775879,
      "learning_rate": 4.9453690018345144e-06,
      "logits/chosen": -1.8948112726211548,
      "logits/rejected": -2.4755520820617676,
      "logps/chosen": -0.20189261436462402,
      "logps/rejected": -0.29732149839401245,
      "loss": 7.2542,
      "rewards/accuracies": 0.5874999761581421,
      "rewards/chosen": -0.30283889174461365,
      "rewards/margins": 0.14314329624176025,
      "rewards/rejected": -0.44598227739334106,
      "step": 100
    },
    {
      "epoch": 0.07248346470961312,
      "eval_logits/chosen": -2.12322735786438,
      "eval_logits/rejected": -2.481174945831299,
      "eval_logps/chosen": -0.2438412606716156,
      "eval_logps/rejected": -0.3260033428668976,
      "eval_loss": 0.891861081123352,
      "eval_rewards/accuracies": 0.5625,
      "eval_rewards/chosen": -0.3657619059085846,
      "eval_rewards/margins": 0.12324309349060059,
      "eval_rewards/rejected": -0.48900502920150757,
      "eval_runtime": 30.3299,
      "eval_samples_per_second": 29.41,
      "eval_steps_per_second": 3.693,
      "step": 100
    },
    {
      "epoch": 0.07973181118057443,
      "grad_norm": 0.05962231010198593,
      "learning_rate": 4.933947257182901e-06,
      "logits/chosen": -2.1134355068206787,
      "logits/rejected": -2.516538381576538,
      "logps/chosen": -0.237023264169693,
      "logps/rejected": -0.31476154923439026,
      "loss": 7.1749,
      "rewards/accuracies": 0.550000011920929,
      "rewards/chosen": -0.3555349111557007,
      "rewards/margins": 0.11660744249820709,
      "rewards/rejected": -0.4721423089504242,
      "step": 110
    },
    {
      "epoch": 0.08698015765153574,
      "grad_norm": 0.06015922501683235,
      "learning_rate": 4.921457902821578e-06,
      "logits/chosen": -2.0215041637420654,
      "logits/rejected": -2.4902031421661377,
      "logps/chosen": -0.1890055537223816,
      "logps/rejected": -0.3192065358161926,
      "loss": 7.142,
      "rewards/accuracies": 0.637499988079071,
      "rewards/chosen": -0.2835083603858948,
      "rewards/margins": 0.19530144333839417,
      "rewards/rejected": -0.47880974411964417,
      "step": 120
    },
    {
      "epoch": 0.09422850412249706,
      "grad_norm": 0.06430571526288986,
      "learning_rate": 4.907906416994146e-06,
      "logits/chosen": -2.0684752464294434,
      "logits/rejected": -2.510018825531006,
      "logps/chosen": -0.2073744535446167,
      "logps/rejected": -0.3121300935745239,
      "loss": 7.1438,
      "rewards/accuracies": 0.612500011920929,
      "rewards/chosen": -0.31106168031692505,
      "rewards/margins": 0.15713343024253845,
      "rewards/rejected": -0.4681951403617859,
      "step": 130
    },
    {
      "epoch": 0.10147685059345837,
      "grad_norm": 0.08829955011606216,
      "learning_rate": 4.893298743830168e-06,
      "logits/chosen": -2.026458263397217,
      "logits/rejected": -2.496157646179199,
      "logps/chosen": -0.19946983456611633,
      "logps/rejected": -0.32050156593322754,
      "loss": 7.1196,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -0.2992047667503357,
      "rewards/margins": 0.18154758214950562,
      "rewards/rejected": -0.4807523787021637,
      "step": 140
    },
    {
      "epoch": 0.10872519706441967,
      "grad_norm": 0.09773921221494675,
      "learning_rate": 4.8776412907378845e-06,
      "logits/chosen": -2.101029872894287,
      "logits/rejected": -2.5849032402038574,
      "logps/chosen": -0.18889756500720978,
      "logps/rejected": -0.36427801847457886,
      "loss": 7.1227,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": -0.28334635496139526,
      "rewards/margins": 0.26307064294815063,
      "rewards/rejected": -0.5464169979095459,
      "step": 150
    },
    {
      "epoch": 0.10872519706441967,
      "eval_logits/chosen": -2.1945455074310303,
      "eval_logits/rejected": -2.559415578842163,
      "eval_logps/chosen": -0.22209034860134125,
      "eval_logps/rejected": -0.32476040720939636,
      "eval_loss": 0.8760393261909485,
      "eval_rewards/accuracies": 0.5803571343421936,
      "eval_rewards/chosen": -0.33313554525375366,
      "eval_rewards/margins": 0.15400508046150208,
      "eval_rewards/rejected": -0.48714062571525574,
      "eval_runtime": 30.3484,
      "eval_samples_per_second": 29.392,
      "eval_steps_per_second": 3.69,
      "step": 150
    },
    {
      "epoch": 0.11597354353538099,
      "grad_norm": 0.09142427891492844,
      "learning_rate": 4.860940925593703e-06,
      "logits/chosen": -2.235069751739502,
      "logits/rejected": -2.5513346195220947,
      "logps/chosen": -0.19598741829395294,
      "logps/rejected": -0.2772120535373688,
      "loss": 7.0272,
      "rewards/accuracies": 0.5375000238418579,
      "rewards/chosen": -0.2939811050891876,
      "rewards/margins": 0.12183700501918793,
      "rewards/rejected": -0.41581812500953674,
      "step": 160
    },
    {
      "epoch": 0.1232218900063423,
      "grad_norm": 0.11735275387763977,
      "learning_rate": 4.84320497372973e-06,
      "logits/chosen": -2.154263496398926,
      "logits/rejected": -2.512010335922241,
      "logps/chosen": -0.1798369437456131,
      "logps/rejected": -0.30910637974739075,
      "loss": 7.1603,
      "rewards/accuracies": 0.637499988079071,
      "rewards/chosen": -0.26975542306900024,
      "rewards/margins": 0.19390416145324707,
      "rewards/rejected": -0.4636595845222473,
      "step": 170
    },
    {
      "epoch": 0.1304702364773036,
      "grad_norm": 0.09398588538169861,
      "learning_rate": 4.824441214720629e-06,
      "logits/chosen": -2.292147159576416,
      "logits/rejected": -2.581425189971924,
      "logps/chosen": -0.18498703837394714,
      "logps/rejected": -0.31237050890922546,
      "loss": 6.995,
      "rewards/accuracies": 0.637499988079071,
      "rewards/chosen": -0.2774805426597595,
      "rewards/margins": 0.19107523560523987,
      "rewards/rejected": -0.4685557782649994,
      "step": 180
    },
    {
      "epoch": 0.13771858294826492,
      "grad_norm": 0.13551996648311615,
      "learning_rate": 4.804657878971252e-06,
      "logits/chosen": -2.274120330810547,
      "logits/rejected": -2.5797386169433594,
      "logps/chosen": -0.21168990433216095,
      "logps/rejected": -0.34927254915237427,
      "loss": 6.9941,
      "rewards/accuracies": 0.5874999761581421,
      "rewards/chosen": -0.317534863948822,
      "rewards/margins": 0.20637397468090057,
      "rewards/rejected": -0.5239088535308838,
      "step": 190
    },
    {
      "epoch": 0.14496692941922623,
      "grad_norm": 0.15515944361686707,
      "learning_rate": 4.783863644106502e-06,
      "logits/chosen": -2.2116379737854004,
      "logits/rejected": -2.6693203449249268,
      "logps/chosen": -0.1971816122531891,
      "logps/rejected": -0.3498842120170593,
      "loss": 7.0413,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": -0.2957724332809448,
      "rewards/margins": 0.22905388474464417,
      "rewards/rejected": -0.5248263478279114,
      "step": 200
    },
    {
      "epoch": 0.14496692941922623,
      "eval_logits/chosen": -2.3369696140289307,
      "eval_logits/rejected": -2.7298672199249268,
      "eval_logps/chosen": -0.22749511897563934,
      "eval_logps/rejected": -0.3613782525062561,
      "eval_loss": 0.8543878793716431,
      "eval_rewards/accuracies": 0.5714285969734192,
      "eval_rewards/chosen": -0.34124264121055603,
      "eval_rewards/margins": 0.2008247673511505,
      "eval_rewards/rejected": -0.5420674681663513,
      "eval_runtime": 30.3397,
      "eval_samples_per_second": 29.4,
      "eval_steps_per_second": 3.692,
      "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": 7.387465726191206e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}