{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13321492007104796,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008880994671403197,
      "grad_norm": 0.04571289196610451,
      "learning_rate": 4.999451708687114e-06,
      "logits/chosen": 14.56671142578125,
      "logits/rejected": 15.112574577331543,
      "logps/chosen": -0.26506316661834717,
      "logps/rejected": -0.3439488410949707,
      "loss": 0.9267,
      "rewards/accuracies": 0.574999988079071,
      "rewards/chosen": -0.39759472012519836,
      "rewards/margins": 0.11832849681377411,
      "rewards/rejected": -0.5159232020378113,
      "step": 10
    },
    {
      "epoch": 0.017761989342806393,
      "grad_norm": 0.0512714721262455,
      "learning_rate": 4.997807075247147e-06,
      "logits/chosen": 14.376543045043945,
      "logits/rejected": 14.862703323364258,
      "logps/chosen": -0.2708089351654053,
      "logps/rejected": -0.32412824034690857,
      "loss": 0.936,
      "rewards/accuracies": 0.5,
      "rewards/chosen": -0.4062133729457855,
      "rewards/margins": 0.07997899502515793,
      "rewards/rejected": -0.4861923158168793,
      "step": 20
    },
    {
      "epoch": 0.02664298401420959,
      "grad_norm": 0.058383647352457047,
      "learning_rate": 4.9950668210706795e-06,
      "logits/chosen": 14.208717346191406,
      "logits/rejected": 15.370651245117188,
      "logps/chosen": -0.28206294775009155,
      "logps/rejected": -0.38387423753738403,
      "loss": 0.9215,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -0.42309442162513733,
      "rewards/margins": 0.15271687507629395,
      "rewards/rejected": -0.5758112668991089,
      "step": 30
    },
    {
      "epoch": 0.035523978685612786,
      "grad_norm": 0.06262075155973434,
      "learning_rate": 4.9912321481237616e-06,
      "logits/chosen": 14.768765449523926,
      "logits/rejected": 15.169331550598145,
      "logps/chosen": -0.27857059240341187,
      "logps/rejected": -0.3388269543647766,
      "loss": 0.9386,
      "rewards/accuracies": 0.5,
      "rewards/chosen": -0.4178559184074402,
      "rewards/margins": 0.09038447588682175,
      "rewards/rejected": -0.5082404017448425,
      "step": 40
    },
    {
      "epoch": 0.04440497335701599,
      "grad_norm": 0.06259036809206009,
      "learning_rate": 4.986304738420684e-06,
      "logits/chosen": 14.950456619262695,
      "logits/rejected": 15.232122421264648,
      "logps/chosen": -0.2961367070674896,
      "logps/rejected": -0.3322262465953827,
      "loss": 0.9317,
      "rewards/accuracies": 0.44999998807907104,
      "rewards/chosen": -0.44420504570007324,
      "rewards/margins": 0.054134320467710495,
      "rewards/rejected": -0.4983394145965576,
      "step": 50
    },
    {
      "epoch": 0.04440497335701599,
      "eval_logits/chosen": 14.56529426574707,
      "eval_logits/rejected": 14.895020484924316,
      "eval_logps/chosen": -0.2806546986103058,
      "eval_logps/rejected": -0.3486972451210022,
      "eval_loss": 0.9381324052810669,
      "eval_rewards/accuracies": 0.5274725556373596,
      "eval_rewards/chosen": -0.4209820330142975,
      "eval_rewards/margins": 0.10206379741430283,
      "eval_rewards/rejected": -0.5230458974838257,
      "eval_runtime": 25.2574,
      "eval_samples_per_second": 28.823,
      "eval_steps_per_second": 3.603,
      "step": 50
    },
    {
      "epoch": 0.05328596802841918,
      "grad_norm": 0.07301533967256546,
      "learning_rate": 4.980286753286196e-06,
      "logits/chosen": 14.195574760437012,
      "logits/rejected": 15.173194885253906,
      "logps/chosen": -0.2693648636341095,
      "logps/rejected": -0.33997970819473267,
      "loss": 0.9319,
      "rewards/accuracies": 0.512499988079071,
      "rewards/chosen": -0.40404725074768066,
      "rewards/margins": 0.10592226684093475,
      "rewards/rejected": -0.5099694728851318,
      "step": 60
    },
    {
      "epoch": 0.06216696269982238,
      "grad_norm": 0.0659889206290245,
      "learning_rate": 4.973180832407471e-06,
      "logits/chosen": 14.910173416137695,
      "logits/rejected": 15.361429214477539,
      "logps/chosen": -0.28456225991249084,
      "logps/rejected": -0.3702812194824219,
      "loss": 0.9185,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -0.42684346437454224,
      "rewards/margins": 0.12857840955257416,
      "rewards/rejected": -0.5554218292236328,
      "step": 70
    },
    {
      "epoch": 0.07104795737122557,
      "grad_norm": 0.05815625935792923,
      "learning_rate": 4.964990092676263e-06,
      "logits/chosen": 14.407182693481445,
      "logits/rejected": 14.948204040527344,
      "logps/chosen": -0.292889267206192,
      "logps/rejected": -0.3381648063659668,
      "loss": 0.9388,
      "rewards/accuracies": 0.5375000238418579,
      "rewards/chosen": -0.43933385610580444,
      "rewards/margins": 0.06791339069604874,
      "rewards/rejected": -0.5072472095489502,
      "step": 80
    },
    {
      "epoch": 0.07992895204262877,
      "grad_norm": 0.06627190113067627,
      "learning_rate": 4.9557181268217225e-06,
      "logits/chosen": 14.622471809387207,
      "logits/rejected": 15.167770385742188,
      "logps/chosen": -0.28155821561813354,
      "logps/rejected": -0.33633899688720703,
      "loss": 0.9256,
      "rewards/accuracies": 0.5375000238418579,
      "rewards/chosen": -0.4223373532295227,
      "rewards/margins": 0.08217118680477142,
      "rewards/rejected": -0.5045084953308105,
      "step": 90
    },
    {
      "epoch": 0.08880994671403197,
      "grad_norm": 0.0724545568227768,
      "learning_rate": 4.9453690018345144e-06,
      "logits/chosen": 14.289724349975586,
      "logits/rejected": 14.882037162780762,
      "logps/chosen": -0.2791440486907959,
      "logps/rejected": -0.35329627990722656,
      "loss": 0.9374,
      "rewards/accuracies": 0.5375000238418579,
      "rewards/chosen": -0.41871610283851624,
      "rewards/margins": 0.11122839152812958,
      "rewards/rejected": -0.5299445390701294,
      "step": 100
    },
    {
      "epoch": 0.08880994671403197,
      "eval_logits/chosen": 14.337930679321289,
      "eval_logits/rejected": 14.689269065856934,
      "eval_logps/chosen": -0.2726942300796509,
      "eval_logps/rejected": -0.34668418765068054,
      "eval_loss": 0.9302808046340942,
      "eval_rewards/accuracies": 0.5384615659713745,
      "eval_rewards/chosen": -0.40904131531715393,
      "eval_rewards/margins": 0.11098497360944748,
      "eval_rewards/rejected": -0.5200263261795044,
      "eval_runtime": 25.2585,
      "eval_samples_per_second": 28.822,
      "eval_steps_per_second": 3.603,
      "step": 100
    },
    {
      "epoch": 0.09769094138543517,
      "grad_norm": 0.08156246691942215,
      "learning_rate": 4.933947257182901e-06,
      "logits/chosen": 14.499124526977539,
      "logits/rejected": 14.916313171386719,
      "logps/chosen": -0.2798352837562561,
      "logps/rejected": -0.3477734327316284,
      "loss": 0.9243,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": -0.4197530150413513,
      "rewards/margins": 0.10190720856189728,
      "rewards/rejected": -0.5216602087020874,
      "step": 110
    },
    {
      "epoch": 0.10657193605683836,
      "grad_norm": 0.08161844313144684,
      "learning_rate": 4.921457902821578e-06,
      "logits/chosen": 13.595013618469238,
      "logits/rejected": 14.390353202819824,
      "logps/chosen": -0.26682502031326294,
      "logps/rejected": -0.3336995542049408,
      "loss": 0.9123,
      "rewards/accuracies": 0.5874999761581421,
      "rewards/chosen": -0.400237500667572,
      "rewards/margins": 0.10031183809041977,
      "rewards/rejected": -0.5005493760108948,
      "step": 120
    },
    {
      "epoch": 0.11545293072824156,
      "grad_norm": 0.28624778985977173,
      "learning_rate": 4.907906416994146e-06,
      "logits/chosen": 13.711044311523438,
      "logits/rejected": 14.558542251586914,
      "logps/chosen": -0.27874043583869934,
      "logps/rejected": -0.3582325279712677,
      "loss": 0.9163,
      "rewards/accuracies": 0.5375000238418579,
      "rewards/chosen": -0.41811060905456543,
      "rewards/margins": 0.11923813819885254,
      "rewards/rejected": -0.537348747253418,
      "step": 130
    },
    {
      "epoch": 0.12433392539964476,
      "grad_norm": 0.10971464216709137,
      "learning_rate": 4.893298743830168e-06,
      "logits/chosen": 14.18798828125,
      "logits/rejected": 14.993026733398438,
      "logps/chosen": -0.2750400900840759,
      "logps/rejected": -0.39451608061790466,
      "loss": 0.9098,
      "rewards/accuracies": 0.574999988079071,
      "rewards/chosen": -0.4125601351261139,
      "rewards/margins": 0.17921395599842072,
      "rewards/rejected": -0.5917741060256958,
      "step": 140
    },
    {
      "epoch": 0.13321492007104796,
      "grad_norm": 0.09321591258049011,
      "learning_rate": 4.8776412907378845e-06,
      "logits/chosen": 12.775139808654785,
      "logits/rejected": 13.751996994018555,
      "logps/chosen": -0.28446996212005615,
      "logps/rejected": -0.36404967308044434,
      "loss": 0.9104,
      "rewards/accuracies": 0.5249999761581421,
      "rewards/chosen": -0.42670494318008423,
      "rewards/margins": 0.11936960369348526,
      "rewards/rejected": -0.5460745096206665,
      "step": 150
    },
    {
      "epoch": 0.13321492007104796,
      "eval_logits/chosen": 12.97266960144043,
      "eval_logits/rejected": 13.47339916229248,
      "eval_logps/chosen": -0.27297571301460266,
      "eval_logps/rejected": -0.36854612827301025,
      "eval_loss": 0.9143257737159729,
      "eval_rewards/accuracies": 0.5824176073074341,
      "eval_rewards/chosen": -0.4094635546207428,
      "eval_rewards/margins": 0.14335563778877258,
      "eval_rewards/rejected": -0.5528191924095154,
      "eval_runtime": 25.2406,
      "eval_samples_per_second": 28.842,
      "eval_steps_per_second": 3.605,
      "step": 150
    }
  ],
  "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": 3.560389740760924e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}