{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.16145307769929365,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008072653884964682,
      "grad_norm": 0.04381619393825531,
      "learning_rate": 4.999451708687114e-06,
      "logits/chosen": 14.719314575195312,
      "logits/rejected": 15.156938552856445,
      "logps/chosen": -0.2856016755104065,
      "logps/rejected": -0.31895095109939575,
      "loss": 0.9242,
      "rewards/accuracies": 0.4375,
      "rewards/chosen": -0.42840251326560974,
      "rewards/margins": 0.050023891031742096,
      "rewards/rejected": -0.47842639684677124,
      "step": 10
    },
    {
      "epoch": 0.016145307769929364,
      "grad_norm": 0.05155143886804581,
      "learning_rate": 4.997807075247147e-06,
      "logits/chosen": 14.559402465820312,
      "logits/rejected": 15.32939338684082,
      "logps/chosen": -0.2736968398094177,
      "logps/rejected": -0.3458033502101898,
      "loss": 0.9127,
      "rewards/accuracies": 0.5375000238418579,
      "rewards/chosen": -0.4105452597141266,
      "rewards/margins": 0.10815979540348053,
      "rewards/rejected": -0.5187050104141235,
      "step": 20
    },
    {
      "epoch": 0.024217961654894045,
      "grad_norm": 0.05071854218840599,
      "learning_rate": 4.9950668210706795e-06,
      "logits/chosen": 14.653738021850586,
      "logits/rejected": 15.168347358703613,
      "logps/chosen": -0.2985997200012207,
      "logps/rejected": -0.34624338150024414,
      "loss": 0.9141,
      "rewards/accuracies": 0.4625000059604645,
      "rewards/chosen": -0.44789963960647583,
      "rewards/margins": 0.07146544009447098,
      "rewards/rejected": -0.5193650722503662,
      "step": 30
    },
    {
      "epoch": 0.03229061553985873,
      "grad_norm": 0.052318744361400604,
      "learning_rate": 4.9912321481237616e-06,
      "logits/chosen": 14.621539115905762,
      "logits/rejected": 15.138806343078613,
      "logps/chosen": -0.27971988916397095,
      "logps/rejected": -0.360626757144928,
      "loss": 0.9313,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": -0.4195798337459564,
      "rewards/margins": 0.12136033922433853,
      "rewards/rejected": -0.5409401655197144,
      "step": 40
    },
    {
      "epoch": 0.04036326942482341,
      "grad_norm": 0.06900553405284882,
      "learning_rate": 4.986304738420684e-06,
      "logits/chosen": 14.308789253234863,
      "logits/rejected": 14.605737686157227,
      "logps/chosen": -0.2685723304748535,
      "logps/rejected": -0.323064386844635,
      "loss": 0.9076,
      "rewards/accuracies": 0.4749999940395355,
      "rewards/chosen": -0.40285855531692505,
      "rewards/margins": 0.08173803985118866,
      "rewards/rejected": -0.4845965802669525,
      "step": 50
    },
    {
      "epoch": 0.04036326942482341,
      "eval_logits/chosen": 14.528907775878906,
      "eval_logits/rejected": 15.016877174377441,
      "eval_logps/chosen": -0.2801212966442108,
      "eval_logps/rejected": -0.34862396121025085,
      "eval_loss": 0.9108895063400269,
      "eval_rewards/accuracies": 0.5544554591178894,
      "eval_rewards/chosen": -0.4201819598674774,
      "eval_rewards/margins": 0.10275395959615707,
      "eval_rewards/rejected": -0.5229359865188599,
      "eval_runtime": 30.01,
      "eval_samples_per_second": 26.691,
      "eval_steps_per_second": 3.366,
      "step": 50
    },
    {
      "epoch": 0.04843592330978809,
      "grad_norm": 0.32321593165397644,
      "learning_rate": 4.980286753286196e-06,
      "logits/chosen": 14.644981384277344,
      "logits/rejected": 15.177103996276855,
      "logps/chosen": -0.26382654905319214,
      "logps/rejected": -0.33932510018348694,
      "loss": 0.9204,
      "rewards/accuracies": 0.5249999761581421,
      "rewards/chosen": -0.3957397937774658,
      "rewards/margins": 0.1132478266954422,
      "rewards/rejected": -0.5089876055717468,
      "step": 60
    },
    {
      "epoch": 0.056508577194752774,
      "grad_norm": 0.07268164306879044,
      "learning_rate": 4.973180832407471e-06,
      "logits/chosen": 14.562113761901855,
      "logits/rejected": 15.092450141906738,
      "logps/chosen": -0.2856511175632477,
      "logps/rejected": -0.34295767545700073,
      "loss": 0.915,
      "rewards/accuracies": 0.5375000238418579,
      "rewards/chosen": -0.42847663164138794,
      "rewards/margins": 0.08595988899469376,
      "rewards/rejected": -0.5144366025924683,
      "step": 70
    },
    {
      "epoch": 0.06458123107971746,
      "grad_norm": 0.06727313250303268,
      "learning_rate": 4.964990092676263e-06,
      "logits/chosen": 13.979713439941406,
      "logits/rejected": 14.924532890319824,
      "logps/chosen": -0.27184560894966125,
      "logps/rejected": -0.3679867386817932,
      "loss": 0.9223,
      "rewards/accuracies": 0.637499988079071,
      "rewards/chosen": -0.4077683985233307,
      "rewards/margins": 0.14421164989471436,
      "rewards/rejected": -0.5519800186157227,
      "step": 80
    },
    {
      "epoch": 0.07265388496468214,
      "grad_norm": 0.06138753890991211,
      "learning_rate": 4.9557181268217225e-06,
      "logits/chosen": 14.366241455078125,
      "logits/rejected": 14.924840927124023,
      "logps/chosen": -0.2656143009662628,
      "logps/rejected": -0.3583180606365204,
      "loss": 0.9117,
      "rewards/accuracies": 0.6000000238418579,
      "rewards/chosen": -0.39842137694358826,
      "rewards/margins": 0.13905569911003113,
      "rewards/rejected": -0.5374771356582642,
      "step": 90
    },
    {
      "epoch": 0.08072653884964683,
      "grad_norm": 0.14299456775188446,
      "learning_rate": 4.9453690018345144e-06,
      "logits/chosen": 14.401769638061523,
      "logits/rejected": 14.532609939575195,
      "logps/chosen": -0.2966740131378174,
      "logps/rejected": -0.3347373604774475,
      "loss": 0.9162,
      "rewards/accuracies": 0.5249999761581421,
      "rewards/chosen": -0.4450109899044037,
      "rewards/margins": 0.05709508806467056,
      "rewards/rejected": -0.5021060705184937,
      "step": 100
    },
    {
      "epoch": 0.08072653884964683,
      "eval_logits/chosen": 14.096770286560059,
      "eval_logits/rejected": 14.638699531555176,
      "eval_logps/chosen": -0.2713560461997986,
      "eval_logps/rejected": -0.35128629207611084,
      "eval_loss": 0.900999128818512,
      "eval_rewards/accuracies": 0.5643564462661743,
      "eval_rewards/chosen": -0.4070340394973755,
      "eval_rewards/margins": 0.11989541351795197,
      "eval_rewards/rejected": -0.5269294381141663,
      "eval_runtime": 29.986,
      "eval_samples_per_second": 26.712,
      "eval_steps_per_second": 3.368,
      "step": 100
    },
    {
      "epoch": 0.08879919273461151,
      "grad_norm": 0.0759090781211853,
      "learning_rate": 4.933947257182901e-06,
      "logits/chosen": 13.392621994018555,
      "logits/rejected": 14.395462036132812,
      "logps/chosen": -0.22954440116882324,
      "logps/rejected": -0.36977845430374146,
      "loss": 0.8951,
      "rewards/accuracies": 0.699999988079071,
      "rewards/chosen": -0.3443165421485901,
      "rewards/margins": 0.21035107970237732,
      "rewards/rejected": -0.5546677112579346,
      "step": 110
    },
    {
      "epoch": 0.09687184661957618,
      "grad_norm": 0.155408576130867,
      "learning_rate": 4.921457902821578e-06,
      "logits/chosen": 13.7767915725708,
      "logits/rejected": 14.654029846191406,
      "logps/chosen": -0.2693817615509033,
      "logps/rejected": -0.38339418172836304,
      "loss": 0.9012,
      "rewards/accuracies": 0.637499988079071,
      "rewards/chosen": -0.40407267212867737,
      "rewards/margins": 0.17101867496967316,
      "rewards/rejected": -0.5750913619995117,
      "step": 120
    },
    {
      "epoch": 0.10494450050454086,
      "grad_norm": 0.31760165095329285,
      "learning_rate": 4.907906416994146e-06,
      "logits/chosen": 13.619878768920898,
      "logits/rejected": 14.147298812866211,
      "logps/chosen": -0.2787878215312958,
      "logps/rejected": -0.35886240005493164,
      "loss": 0.8911,
      "rewards/accuracies": 0.5249999761581421,
      "rewards/chosen": -0.41818171739578247,
      "rewards/margins": 0.12011190503835678,
      "rewards/rejected": -0.5382936000823975,
      "step": 130
    },
    {
      "epoch": 0.11301715438950555,
      "grad_norm": 0.10735614597797394,
      "learning_rate": 4.893298743830168e-06,
      "logits/chosen": 13.27166748046875,
      "logits/rejected": 13.826273918151855,
      "logps/chosen": -0.25437131524086,
      "logps/rejected": -0.3877837061882019,
      "loss": 0.8915,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": -0.3815569281578064,
      "rewards/margins": 0.20011858642101288,
      "rewards/rejected": -0.5816755890846252,
      "step": 140
    },
    {
      "epoch": 0.12108980827447023,
      "grad_norm": 0.12984605133533478,
      "learning_rate": 4.8776412907378845e-06,
      "logits/chosen": 12.981040954589844,
      "logits/rejected": 13.055997848510742,
      "logps/chosen": -0.27253809571266174,
      "logps/rejected": -0.32365134358406067,
      "loss": 0.8954,
      "rewards/accuracies": 0.4375,
      "rewards/chosen": -0.4088071286678314,
      "rewards/margins": 0.07666991651058197,
      "rewards/rejected": -0.4854770302772522,
      "step": 150
    },
    {
      "epoch": 0.12108980827447023,
      "eval_logits/chosen": 12.205692291259766,
      "eval_logits/rejected": 12.830544471740723,
      "eval_logps/chosen": -0.2716449201107025,
      "eval_logps/rejected": -0.37988847494125366,
      "eval_loss": 0.8780961036682129,
      "eval_rewards/accuracies": 0.5841584205627441,
      "eval_rewards/chosen": -0.40746742486953735,
      "eval_rewards/margins": 0.16236530244350433,
      "eval_rewards/rejected": -0.5698326826095581,
      "eval_runtime": 30.0006,
      "eval_samples_per_second": 26.699,
      "eval_steps_per_second": 3.367,
      "step": 150
    },
    {
      "epoch": 0.12916246215943492,
      "grad_norm": 0.1466989368200302,
      "learning_rate": 4.860940925593703e-06,
      "logits/chosen": 12.592086791992188,
      "logits/rejected": 12.590131759643555,
      "logps/chosen": -0.2901991307735443,
      "logps/rejected": -0.37141314148902893,
      "loss": 0.8814,
      "rewards/accuracies": 0.5874999761581421,
      "rewards/chosen": -0.4352986812591553,
      "rewards/margins": 0.12182100117206573,
      "rewards/rejected": -0.5571196675300598,
      "step": 160
    },
    {
      "epoch": 0.13723511604439959,
      "grad_norm": 0.15794874727725983,
      "learning_rate": 4.84320497372973e-06,
      "logits/chosen": 10.324287414550781,
      "logits/rejected": 11.248865127563477,
      "logps/chosen": -0.24505829811096191,
      "logps/rejected": -0.4437941610813141,
      "loss": 0.8739,
      "rewards/accuracies": 0.7124999761581421,
      "rewards/chosen": -0.3675874173641205,
      "rewards/margins": 0.29810377955436707,
      "rewards/rejected": -0.6656912565231323,
      "step": 170
    },
    {
      "epoch": 0.14530776992936428,
      "grad_norm": 0.34027722477912903,
      "learning_rate": 4.824441214720629e-06,
      "logits/chosen": 9.277830123901367,
      "logits/rejected": 10.56584644317627,
      "logps/chosen": -0.29055729508399963,
      "logps/rejected": -0.4694874882698059,
      "loss": 0.8732,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": -0.43583592772483826,
      "rewards/margins": 0.2683953046798706,
      "rewards/rejected": -0.7042312026023865,
      "step": 180
    },
    {
      "epoch": 0.15338042381432895,
      "grad_norm": 0.21653155982494354,
      "learning_rate": 4.804657878971252e-06,
      "logits/chosen": 6.692442417144775,
      "logits/rejected": 8.371492385864258,
      "logps/chosen": -0.2739722728729248,
      "logps/rejected": -0.5168331265449524,
      "loss": 0.8425,
      "rewards/accuracies": 0.6875,
      "rewards/chosen": -0.4109583795070648,
      "rewards/margins": 0.36429136991500854,
      "rewards/rejected": -0.7752498388290405,
      "step": 190
    },
    {
      "epoch": 0.16145307769929365,
      "grad_norm": 0.27401649951934814,
      "learning_rate": 4.783863644106502e-06,
      "logits/chosen": 7.028637886047363,
      "logits/rejected": 7.22598123550415,
      "logps/chosen": -0.32309776544570923,
      "logps/rejected": -0.5094671249389648,
      "loss": 0.8327,
      "rewards/accuracies": 0.612500011920929,
      "rewards/chosen": -0.48464661836624146,
      "rewards/margins": 0.2795540988445282,
      "rewards/rejected": -0.7642006874084473,
      "step": 200
    },
    {
      "epoch": 0.16145307769929365,
      "eval_logits/chosen": 6.369185924530029,
      "eval_logits/rejected": 6.641132831573486,
      "eval_logps/chosen": -0.32840561866760254,
      "eval_logps/rejected": -0.5301258563995361,
      "eval_loss": 0.8103437423706055,
      "eval_rewards/accuracies": 0.6237623691558838,
      "eval_rewards/chosen": -0.4926084876060486,
      "eval_rewards/margins": 0.30258041620254517,
      "eval_rewards/rejected": -0.795188844203949,
      "eval_runtime": 29.9886,
      "eval_samples_per_second": 26.71,
      "eval_steps_per_second": 3.368,
      "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": 4.850494343342981e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}