{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 162,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 2.9411764705882356e-07,
      "logits/chosen": -2.7916789054870605,
      "logits/rejected": -2.7116382122039795,
      "logps/chosen": -323.9847717285156,
      "logps/rejected": -313.6904296875,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.9411764705882355e-06,
      "logits/chosen": -2.673537492752075,
      "logits/rejected": -2.636620044708252,
      "logps/chosen": -280.41143798828125,
      "logps/rejected": -293.9028625488281,
      "loss": 0.6926,
      "rewards/accuracies": 0.4305555522441864,
      "rewards/chosen": 0.0071474602445960045,
      "rewards/margins": 0.0006154652219265699,
      "rewards/rejected": 0.006531994789838791,
      "step": 10
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.994720857837211e-06,
      "logits/chosen": -2.6557788848876953,
      "logits/rejected": -2.6616427898406982,
      "logps/chosen": -242.90036010742188,
      "logps/rejected": -262.7171630859375,
      "loss": 0.6876,
      "rewards/accuracies": 0.5687500238418579,
      "rewards/chosen": 0.17924346029758453,
      "rewards/margins": 0.011152910068631172,
      "rewards/rejected": 0.1680905520915985,
      "step": 20
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.901488388458247e-06,
      "logits/chosen": -2.6518654823303223,
      "logits/rejected": -2.661100387573242,
      "logps/chosen": -248.0233612060547,
      "logps/rejected": -281.92254638671875,
      "loss": 0.6776,
      "rewards/accuracies": 0.640625,
      "rewards/chosen": 0.21578983962535858,
      "rewards/margins": 0.03539184108376503,
      "rewards/rejected": 0.18039801716804504,
      "step": 30
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.6959649910976165e-06,
      "logits/chosen": -2.6537535190582275,
      "logits/rejected": -2.5938658714294434,
      "logps/chosen": -256.3780212402344,
      "logps/rejected": -289.9882507324219,
      "loss": 0.6675,
      "rewards/accuracies": 0.625,
      "rewards/chosen": 0.15942983329296112,
      "rewards/margins": 0.06988275796175003,
      "rewards/rejected": 0.08954708278179169,
      "step": 40
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.387760711393052e-06,
      "logits/chosen": -2.5633559226989746,
      "logits/rejected": -2.5739550590515137,
      "logps/chosen": -240.4188232421875,
      "logps/rejected": -295.7885437011719,
      "loss": 0.6634,
      "rewards/accuracies": 0.6156250238418579,
      "rewards/chosen": 0.020841460675001144,
      "rewards/margins": 0.06278014928102493,
      "rewards/rejected": -0.04193869233131409,
      "step": 50
    },
    {
      "epoch": 0.37,
      "learning_rate": 3.991286838919086e-06,
      "logits/chosen": -2.5727829933166504,
      "logits/rejected": -2.5552239418029785,
      "logps/chosen": -271.25531005859375,
      "logps/rejected": -284.837646484375,
      "loss": 0.6597,
      "rewards/accuracies": 0.596875011920929,
      "rewards/chosen": 0.10798764228820801,
      "rewards/margins": 0.07805077731609344,
      "rewards/rejected": 0.029936855658888817,
      "step": 60
    },
    {
      "epoch": 0.43,
      "learning_rate": 3.5250820513035403e-06,
      "logits/chosen": -2.5731635093688965,
      "logits/rejected": -2.561147451400757,
      "logps/chosen": -277.0789794921875,
      "logps/rejected": -301.56134033203125,
      "loss": 0.6577,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -0.024448225274682045,
      "rewards/margins": 0.09842626750469208,
      "rewards/rejected": -0.12287448346614838,
      "step": 70
    },
    {
      "epoch": 0.49,
      "learning_rate": 3.0109455662659126e-06,
      "logits/chosen": -2.563314914703369,
      "logits/rejected": -2.529156446456909,
      "logps/chosen": -258.3672790527344,
      "logps/rejected": -269.1060791015625,
      "loss": 0.6578,
      "rewards/accuracies": 0.625,
      "rewards/chosen": 0.09700657427310944,
      "rewards/margins": 0.09656216204166412,
      "rewards/rejected": 0.0004444071964826435,
      "step": 80
    },
    {
      "epoch": 0.56,
      "learning_rate": 2.4729178344249007e-06,
      "logits/chosen": -2.61881422996521,
      "logits/rejected": -2.595266580581665,
      "logps/chosen": -295.1117858886719,
      "logps/rejected": -314.3699035644531,
      "loss": 0.6503,
      "rewards/accuracies": 0.6187499761581421,
      "rewards/chosen": -0.054836757481098175,
      "rewards/margins": 0.10771781206130981,
      "rewards/rejected": -0.1625545769929886,
      "step": 90
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.936156434546515e-06,
      "logits/chosen": -2.587148904800415,
      "logits/rejected": -2.5676586627960205,
      "logps/chosen": -283.98406982421875,
      "logps/rejected": -304.22027587890625,
      "loss": 0.6561,
      "rewards/accuracies": 0.59375,
      "rewards/chosen": -0.020496565848588943,
      "rewards/margins": 0.08849820494651794,
      "rewards/rejected": -0.10899476706981659,
      "step": 100
    },
    {
      "epoch": 0.62,
      "eval_logits/chosen": -2.6306071281433105,
      "eval_logits/rejected": -2.5270211696624756,
      "eval_logps/chosen": -305.47430419921875,
      "eval_logps/rejected": -292.46490478515625,
      "eval_loss": 0.6558266878128052,
      "eval_rewards/accuracies": 0.5979999899864197,
      "eval_rewards/chosen": 0.048699021339416504,
      "eval_rewards/margins": 0.10221949964761734,
      "eval_rewards/rejected": -0.053520478308200836,
      "eval_runtime": 384.3017,
      "eval_samples_per_second": 5.204,
      "eval_steps_per_second": 0.651,
      "step": 100
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.4257597331216211e-06,
      "logits/chosen": -2.5318920612335205,
      "logits/rejected": -2.544257879257202,
      "logps/chosen": -247.9283447265625,
      "logps/rejected": -287.6404724121094,
      "loss": 0.6463,
      "rewards/accuracies": 0.6187499761581421,
      "rewards/chosen": 0.021015625447034836,
      "rewards/margins": 0.11108793318271637,
      "rewards/rejected": -0.09007229655981064,
      "step": 110
    },
    {
      "epoch": 0.74,
      "learning_rate": 9.655933126436565e-07,
      "logits/chosen": -2.5357818603515625,
      "logits/rejected": -2.534702777862549,
      "logps/chosen": -273.9105224609375,
      "logps/rejected": -312.25885009765625,
      "loss": 0.6432,
      "rewards/accuracies": 0.59375,
      "rewards/chosen": -0.0325644388794899,
      "rewards/margins": 0.10732172429561615,
      "rewards/rejected": -0.13988614082336426,
      "step": 120
    },
    {
      "epoch": 0.8,
      "learning_rate": 5.771740434959278e-07,
      "logits/chosen": -2.556398630142212,
      "logits/rejected": -2.560457229614258,
      "logps/chosen": -263.99798583984375,
      "logps/rejected": -307.7806701660156,
      "loss": 0.6483,
      "rewards/accuracies": 0.6468750238418579,
      "rewards/chosen": -0.007414107210934162,
      "rewards/margins": 0.11074688285589218,
      "rewards/rejected": -0.11816100031137466,
      "step": 130
    },
    {
      "epoch": 0.86,
      "learning_rate": 2.786639790067719e-07,
      "logits/chosen": -2.563178539276123,
      "logits/rejected": -2.5608487129211426,
      "logps/chosen": -264.00750732421875,
      "logps/rejected": -310.0502014160156,
      "loss": 0.6492,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": -0.03133418411016464,
      "rewards/margins": 0.12591516971588135,
      "rewards/rejected": -0.1572493612766266,
      "step": 140
    },
    {
      "epoch": 0.93,
      "learning_rate": 8.402111802159413e-08,
      "logits/chosen": -2.5827817916870117,
      "logits/rejected": -2.5521092414855957,
      "logps/chosen": -257.99468994140625,
      "logps/rejected": -305.74700927734375,
      "loss": 0.6457,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": 0.012706765905022621,
      "rewards/margins": 0.15555641055107117,
      "rewards/rejected": -0.1428496539592743,
      "step": 150
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.34674439005822e-09,
      "logits/chosen": -2.63196063041687,
      "logits/rejected": -2.579667568206787,
      "logps/chosen": -291.2770080566406,
      "logps/rejected": -327.9423828125,
      "loss": 0.6383,
      "rewards/accuracies": 0.6625000238418579,
      "rewards/chosen": -0.003916625864803791,
      "rewards/margins": 0.17247094213962555,
      "rewards/rejected": -0.17638754844665527,
      "step": 160
    },
    {
      "epoch": 1.0,
      "step": 162,
      "total_flos": 0.0,
      "train_loss": 0.6587186426292231,
      "train_runtime": 6701.6263,
      "train_samples_per_second": 3.094,
      "train_steps_per_second": 0.024
    }
  ],
  "logging_steps": 10,
  "max_steps": 162,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}