{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9997382884061764,
  "eval_steps": 100,
  "global_step": 955,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 5.208333333333333e-09,
      "logits/chosen": -2.676934003829956,
      "logits/rejected": -2.509021043777466,
      "logps/chosen": -304.709228515625,
      "logps/rejected": -229.49505615234375,
      "loss": 0.6931,
      "pred_label": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1,
      "use_label": 10.0
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.976717112922002e-07,
      "logits/chosen": -2.4758388996124268,
      "logits/rejected": -2.4836206436157227,
      "logps/chosen": -273.62322998046875,
      "logps/rejected": -258.89813232421875,
      "loss": 0.6823,
      "pred_label": 156.05050659179688,
      "rewards/accuracies": 0.4886363744735718,
      "rewards/chosen": -0.002133187372237444,
      "rewards/margins": -0.0010164172854274511,
      "rewards/rejected": -0.0011167696211487055,
      "step": 100,
      "use_label": 653.9495239257812
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.3946449359720607e-07,
      "logits/chosen": -2.4878945350646973,
      "logits/rejected": -2.4750781059265137,
      "logps/chosen": -267.72540283203125,
      "logps/rejected": -250.30291748046875,
      "loss": 0.6801,
      "pred_label": 512.7750244140625,
      "rewards/accuracies": 0.5575000047683716,
      "rewards/chosen": 0.003957623615860939,
      "rewards/margins": 0.008218127302825451,
      "rewards/rejected": -0.0042605032213032246,
      "step": 200,
      "use_label": 1889.2249755859375
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.812572759022118e-07,
      "logits/chosen": -2.47322940826416,
      "logits/rejected": -2.4768893718719482,
      "logps/chosen": -272.0399169921875,
      "logps/rejected": -244.90228271484375,
      "loss": 0.6733,
      "pred_label": 943.1199951171875,
      "rewards/accuracies": 0.6075000166893005,
      "rewards/chosen": 0.010850328952074051,
      "rewards/margins": 0.01955023780465126,
      "rewards/rejected": -0.008699909783899784,
      "step": 300,
      "use_label": 3058.8798828125
    },
    {
      "epoch": 0.42,
      "learning_rate": 3.230500582072177e-07,
      "logits/chosen": -2.486250400543213,
      "logits/rejected": -2.466102361679077,
      "logps/chosen": -270.7090759277344,
      "logps/rejected": -252.9911346435547,
      "loss": 0.6635,
      "pred_label": 1496.31005859375,
      "rewards/accuracies": 0.628125011920929,
      "rewards/chosen": 0.01578013226389885,
      "rewards/margins": 0.0331539586186409,
      "rewards/rejected": -0.01737382635474205,
      "step": 400,
      "use_label": 4105.68994140625
    },
    {
      "epoch": 0.52,
      "learning_rate": 2.648428405122235e-07,
      "logits/chosen": -2.46098256111145,
      "logits/rejected": -2.446549654006958,
      "logps/chosen": -259.1031799316406,
      "logps/rejected": -241.98345947265625,
      "loss": 0.6543,
      "pred_label": 2180.89990234375,
      "rewards/accuracies": 0.6175000071525574,
      "rewards/chosen": 0.019046209752559662,
      "rewards/margins": 0.03530467674136162,
      "rewards/rejected": -0.016258466988801956,
      "step": 500,
      "use_label": 5021.10009765625
    },
    {
      "epoch": 0.63,
      "learning_rate": 2.0663562281722933e-07,
      "logits/chosen": -2.4896275997161865,
      "logits/rejected": -2.4663710594177246,
      "logps/chosen": -271.8394470214844,
      "logps/rejected": -252.83351135253906,
      "loss": 0.646,
      "pred_label": 2942.87255859375,
      "rewards/accuracies": 0.6600000262260437,
      "rewards/chosen": 0.02863229252398014,
      "rewards/margins": 0.05473264306783676,
      "rewards/rejected": -0.02610035613179207,
      "step": 600,
      "use_label": 5859.12744140625
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.4842840512223514e-07,
      "logits/chosen": -2.485153913497925,
      "logits/rejected": -2.472170352935791,
      "logps/chosen": -269.14117431640625,
      "logps/rejected": -238.4977569580078,
      "loss": 0.6421,
      "pred_label": 3756.925048828125,
      "rewards/accuracies": 0.6418750286102295,
      "rewards/chosen": 0.03320219740271568,
      "rewards/margins": 0.05917687341570854,
      "rewards/rejected": -0.02597467601299286,
      "step": 700,
      "use_label": 6645.0751953125
    },
    {
      "epoch": 0.84,
      "learning_rate": 9.022118742724097e-08,
      "logits/chosen": -2.4880199432373047,
      "logits/rejected": -2.5014524459838867,
      "logps/chosen": -276.52313232421875,
      "logps/rejected": -252.34681701660156,
      "loss": 0.6386,
      "pred_label": 4625.42236328125,
      "rewards/accuracies": 0.640625,
      "rewards/chosen": 0.03754829242825508,
      "rewards/margins": 0.06682833284139633,
      "rewards/rejected": -0.02928004413843155,
      "step": 800,
      "use_label": 7376.57763671875
    },
    {
      "epoch": 0.94,
      "learning_rate": 3.20139697322468e-08,
      "logits/chosen": -2.4699513912200928,
      "logits/rejected": -2.485213279724121,
      "logps/chosen": -266.04229736328125,
      "logps/rejected": -247.93341064453125,
      "loss": 0.6393,
      "pred_label": 5488.7001953125,
      "rewards/accuracies": 0.6587499976158142,
      "rewards/chosen": 0.03272656351327896,
      "rewards/margins": 0.06201673671603203,
      "rewards/rejected": -0.02929016388952732,
      "step": 900,
      "use_label": 8113.2998046875
    },
    {
      "epoch": 1.0,
      "eval_logits/chosen": -2.5063796043395996,
      "eval_logits/rejected": -2.5199685096740723,
      "eval_logps/chosen": -272.9034729003906,
      "eval_logps/rejected": -250.30796813964844,
      "eval_loss": 0.6366299986839294,
      "eval_pred_label": 6565.14404296875,
      "eval_rewards/accuracies": 0.6320000290870667,
      "eval_rewards/chosen": 0.03307868540287018,
      "eval_rewards/margins": 0.06870328634977341,
      "eval_rewards/rejected": -0.03562460467219353,
      "eval_runtime": 443.034,
      "eval_samples_per_second": 4.514,
      "eval_steps_per_second": 0.282,
      "eval_use_label": 8966.8564453125,
      "step": 955
    },
    {
      "epoch": 1.0,
      "step": 955,
      "total_flos": 0.0,
      "train_loss": 0.6567496789063458,
      "train_runtime": 24439.922,
      "train_samples_per_second": 2.501,
      "train_steps_per_second": 0.039
    }
  ],
  "logging_steps": 100,
  "max_steps": 955,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}