{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9991836734693877,
  "eval_steps": 100,
  "global_step": 153,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 3.125e-07,
      "logits/chosen": -2.8246347904205322,
      "logits/rejected": -2.7856249809265137,
      "logps/chosen": -238.8000030517578,
      "logps/rejected": -252.79095458984375,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.125e-06,
      "logits/chosen": -2.786410331726074,
      "logits/rejected": -2.722076177597046,
      "logps/chosen": -234.3753204345703,
      "logps/rejected": -252.82334899902344,
      "loss": 0.6931,
      "rewards/accuracies": 0.4340277910232544,
      "rewards/chosen": 0.00016520876670256257,
      "rewards/margins": 0.00022823104518465698,
      "rewards/rejected": -6.302232213784009e-05,
      "step": 10
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.989490450759331e-06,
      "logits/chosen": -2.761898994445801,
      "logits/rejected": -2.750577926635742,
      "logps/chosen": -254.90945434570312,
      "logps/rejected": -267.8478088378906,
      "loss": 0.6927,
      "rewards/accuracies": 0.581250011920929,
      "rewards/chosen": 0.008927298709750175,
      "rewards/margins": 0.0008864253759384155,
      "rewards/rejected": 0.00804087333381176,
      "step": 20
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.872270441827174e-06,
      "logits/chosen": -2.714113235473633,
      "logits/rejected": -2.7077224254608154,
      "logps/chosen": -241.08413696289062,
      "logps/rejected": -277.0527038574219,
      "loss": 0.6915,
      "rewards/accuracies": 0.550000011920929,
      "rewards/chosen": 0.03635140508413315,
      "rewards/margins": 0.0032049957662820816,
      "rewards/rejected": 0.03314640372991562,
      "step": 30
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.630851211353007e-06,
      "logits/chosen": -2.719871997833252,
      "logits/rejected": -2.692225694656372,
      "logps/chosen": -238.7860870361328,
      "logps/rejected": -257.0961608886719,
      "loss": 0.6899,
      "rewards/accuracies": 0.640625,
      "rewards/chosen": 0.05657622963190079,
      "rewards/margins": 0.00868198275566101,
      "rewards/rejected": 0.04789424687623978,
      "step": 40
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.277872161641682e-06,
      "logits/chosen": -2.706775665283203,
      "logits/rejected": -2.682394504547119,
      "logps/chosen": -214.5376434326172,
      "logps/rejected": -231.01980590820312,
      "loss": 0.6874,
      "rewards/accuracies": 0.578125,
      "rewards/chosen": 0.04568081349134445,
      "rewards/margins": 0.007289577275514603,
      "rewards/rejected": 0.03839123994112015,
      "step": 50
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.831813362428005e-06,
      "logits/chosen": -2.743227481842041,
      "logits/rejected": -2.7235677242279053,
      "logps/chosen": -239.521728515625,
      "logps/rejected": -274.9012451171875,
      "loss": 0.6861,
      "rewards/accuracies": 0.65625,
      "rewards/chosen": 0.010201004333794117,
      "rewards/margins": 0.016733800992369652,
      "rewards/rejected": -0.006532798055559397,
      "step": 60
    },
    {
      "epoch": 0.46,
      "learning_rate": 3.3160280345958614e-06,
      "logits/chosen": -2.720754623413086,
      "logits/rejected": -2.7016873359680176,
      "logps/chosen": -247.5521697998047,
      "logps/rejected": -262.7969665527344,
      "loss": 0.6839,
      "rewards/accuracies": 0.6000000238418579,
      "rewards/chosen": 0.01951005309820175,
      "rewards/margins": 0.02022537961602211,
      "rewards/rejected": -0.0007153252372518182,
      "step": 70
    },
    {
      "epoch": 0.52,
      "learning_rate": 2.757519902117886e-06,
      "logits/chosen": -2.649031162261963,
      "logits/rejected": -2.644374132156372,
      "logps/chosen": -229.58657836914062,
      "logps/rejected": -238.00997924804688,
      "loss": 0.6811,
      "rewards/accuracies": 0.609375,
      "rewards/chosen": -0.00663757836446166,
      "rewards/margins": 0.023349270224571228,
      "rewards/rejected": -0.029986849054694176,
      "step": 80
    },
    {
      "epoch": 0.59,
      "learning_rate": 2.185529423440807e-06,
      "logits/chosen": -2.718346357345581,
      "logits/rejected": -2.676443576812744,
      "logps/chosen": -231.41738891601562,
      "logps/rejected": -247.0604248046875,
      "loss": 0.6793,
      "rewards/accuracies": 0.612500011920929,
      "rewards/chosen": -0.029531260952353477,
      "rewards/margins": 0.027696972712874413,
      "rewards/rejected": -0.05722822993993759,
      "step": 90
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.6300029195778454e-06,
      "logits/chosen": -2.6499805450439453,
      "logits/rejected": -2.648062229156494,
      "logps/chosen": -232.34140014648438,
      "logps/rejected": -263.8648986816406,
      "loss": 0.6794,
      "rewards/accuracies": 0.609375,
      "rewards/chosen": -0.014353279955685139,
      "rewards/margins": 0.034331899136304855,
      "rewards/rejected": -0.04868517816066742,
      "step": 100
    },
    {
      "epoch": 0.65,
      "eval_logits/chosen": -2.744441270828247,
      "eval_logits/rejected": -2.664565324783325,
      "eval_logps/chosen": -288.15252685546875,
      "eval_logps/rejected": -266.5563049316406,
      "eval_loss": 0.6748670935630798,
      "eval_rewards/accuracies": 0.6100000143051147,
      "eval_rewards/chosen": -0.04112808406352997,
      "eval_rewards/margins": 0.049276191741228104,
      "eval_rewards/rejected": -0.09040427207946777,
      "eval_runtime": 397.1405,
      "eval_samples_per_second": 5.036,
      "eval_steps_per_second": 0.63,
      "step": 100
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.1200247470632394e-06,
      "logits/chosen": -2.6374545097351074,
      "logits/rejected": -2.621342897415161,
      "logps/chosen": -241.2566680908203,
      "logps/rejected": -255.6346435546875,
      "loss": 0.677,
      "rewards/accuracies": 0.5687500238418579,
      "rewards/chosen": -0.05732475966215134,
      "rewards/margins": 0.021493583917617798,
      "rewards/rejected": -0.07881833612918854,
      "step": 110
    },
    {
      "epoch": 0.78,
      "learning_rate": 6.822945986946386e-07,
      "logits/chosen": -2.725903272628784,
      "logits/rejected": -2.6800780296325684,
      "logps/chosen": -255.1395721435547,
      "logps/rejected": -279.15704345703125,
      "loss": 0.6751,
      "rewards/accuracies": 0.606249988079071,
      "rewards/chosen": -0.055112093687057495,
      "rewards/margins": 0.03783201053738594,
      "rewards/rejected": -0.09294410794973373,
      "step": 120
    },
    {
      "epoch": 0.85,
      "learning_rate": 3.397296523427807e-07,
      "logits/chosen": -2.6524956226348877,
      "logits/rejected": -2.644578695297241,
      "logps/chosen": -262.2508850097656,
      "logps/rejected": -293.28948974609375,
      "loss": 0.67,
      "rewards/accuracies": 0.659375011920929,
      "rewards/chosen": -0.057227589190006256,
      "rewards/margins": 0.054884664714336395,
      "rewards/rejected": -0.11211224645376205,
      "step": 130
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.102647517397798e-07,
      "logits/chosen": -2.7097370624542236,
      "logits/rejected": -2.6917481422424316,
      "logps/chosen": -232.8185272216797,
      "logps/rejected": -257.655029296875,
      "loss": 0.6737,
      "rewards/accuracies": 0.6031249761581421,
      "rewards/chosen": -0.06133182719349861,
      "rewards/margins": 0.038163263350725174,
      "rewards/rejected": -0.09949509054422379,
      "step": 140
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.9134352763748345e-09,
      "logits/chosen": -2.65732479095459,
      "logits/rejected": -2.6523807048797607,
      "logps/chosen": -237.37509155273438,
      "logps/rejected": -260.47747802734375,
      "loss": 0.6725,
      "rewards/accuracies": 0.59375,
      "rewards/chosen": -0.04952359199523926,
      "rewards/margins": 0.044595662504434586,
      "rewards/rejected": -0.09411924332380295,
      "step": 150
    },
    {
      "epoch": 1.0,
      "step": 153,
      "total_flos": 0.0,
      "train_loss": 0.0,
      "train_runtime": 0.012,
      "train_samples_per_second": 1639445.565,
      "train_steps_per_second": 12797.713
    }
  ],
  "logging_steps": 10,
  "max_steps": 153,
  "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
}