{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.99581589958159,
  "eval_steps": 500,
  "global_step": 119,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 4.166666666666666e-08,
      "logits/chosen": -2.4389588832855225,
      "logits/rejected": -2.3863701820373535,
      "logps/chosen": -220.68759155273438,
      "logps/rejected": -373.33087158203125,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.1666666666666667e-07,
      "logits/chosen": -2.3459177017211914,
      "logits/rejected": -2.334230422973633,
      "logps/chosen": -247.85926818847656,
      "logps/rejected": -363.747802734375,
      "loss": 0.6811,
      "rewards/accuracies": 0.5555555820465088,
      "rewards/chosen": -0.021831953898072243,
      "rewards/margins": 0.03538733720779419,
      "rewards/rejected": -0.05721929296851158,
      "step": 10
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.931352528237397e-07,
      "logits/chosen": -2.238157272338867,
      "logits/rejected": -2.2056198120117188,
      "logps/chosen": -283.0589294433594,
      "logps/rejected": -371.25146484375,
      "loss": 0.6646,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -0.3717283308506012,
      "rewards/margins": 0.2823185622692108,
      "rewards/rejected": -0.654046893119812,
      "step": 20
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.658920803689553e-07,
      "logits/chosen": -2.2126076221466064,
      "logits/rejected": -2.165159225463867,
      "logps/chosen": -284.18988037109375,
      "logps/rejected": -394.07562255859375,
      "loss": 0.6218,
      "rewards/accuracies": 0.612500011920929,
      "rewards/chosen": -0.2739036977291107,
      "rewards/margins": 0.25531530380249023,
      "rewards/rejected": -0.5292190313339233,
      "step": 30
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.201712553872657e-07,
      "logits/chosen": -2.2903313636779785,
      "logits/rejected": -2.253678798675537,
      "logps/chosen": -268.6778259277344,
      "logps/rejected": -406.4809875488281,
      "loss": 0.6207,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": -0.3238675594329834,
      "rewards/margins": 0.3434136211872101,
      "rewards/rejected": -0.6672812104225159,
      "step": 40
    },
    {
      "epoch": 0.42,
      "learning_rate": 3.598859066780754e-07,
      "logits/chosen": -2.216749668121338,
      "logits/rejected": -2.1586577892303467,
      "logps/chosen": -270.4320373535156,
      "logps/rejected": -431.34161376953125,
      "loss": 0.6423,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": -0.3394399583339691,
      "rewards/margins": 0.34264153242111206,
      "rewards/rejected": -0.6820814609527588,
      "step": 50
    },
    {
      "epoch": 0.5,
      "learning_rate": 2.9019570347986706e-07,
      "logits/chosen": -2.3308839797973633,
      "logits/rejected": -2.299959659576416,
      "logps/chosen": -260.9419860839844,
      "logps/rejected": -367.1455383300781,
      "loss": 0.6307,
      "rewards/accuracies": 0.59375,
      "rewards/chosen": -0.20153513550758362,
      "rewards/margins": 0.20082291960716248,
      "rewards/rejected": -0.4023580551147461,
      "step": 60
    },
    {
      "epoch": 0.59,
      "learning_rate": 2.1706525253979534e-07,
      "logits/chosen": -2.3276865482330322,
      "logits/rejected": -2.293214797973633,
      "logps/chosen": -288.04248046875,
      "logps/rejected": -417.49383544921875,
      "loss": 0.6296,
      "rewards/accuracies": 0.6312500238418579,
      "rewards/chosen": -0.24966976046562195,
      "rewards/margins": 0.32144370675086975,
      "rewards/rejected": -0.5711134076118469,
      "step": 70
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.4675360263490295e-07,
      "logits/chosen": -2.3125128746032715,
      "logits/rejected": -2.2743871212005615,
      "logps/chosen": -275.89019775390625,
      "logps/rejected": -385.26055908203125,
      "loss": 0.6214,
      "rewards/accuracies": 0.643750011920929,
      "rewards/chosen": -0.2819868326187134,
      "rewards/margins": 0.24118752777576447,
      "rewards/rejected": -0.5231744050979614,
      "step": 80
    },
    {
      "epoch": 0.75,
      "learning_rate": 8.527854855097224e-08,
      "logits/chosen": -2.294402837753296,
      "logits/rejected": -2.2615461349487305,
      "logps/chosen": -298.8416748046875,
      "logps/rejected": -409.93212890625,
      "loss": 0.6106,
      "rewards/accuracies": 0.612500011920929,
      "rewards/chosen": -0.285415917634964,
      "rewards/margins": 0.26987579464912415,
      "rewards/rejected": -0.5552917718887329,
      "step": 90
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.790158337517127e-08,
      "logits/chosen": -2.341721534729004,
      "logits/rejected": -2.3034510612487793,
      "logps/chosen": -271.6078186035156,
      "logps/rejected": -407.69989013671875,
      "loss": 0.606,
      "rewards/accuracies": 0.6937500238418579,
      "rewards/chosen": -0.26334214210510254,
      "rewards/margins": 0.33658233284950256,
      "rewards/rejected": -0.5999244451522827,
      "step": 100
    },
    {
      "epoch": 0.92,
      "learning_rate": 8.677580722139671e-09,
      "logits/chosen": -2.2649519443511963,
      "logits/rejected": -2.2306463718414307,
      "logps/chosen": -257.1134338378906,
      "logps/rejected": -387.23760986328125,
      "loss": 0.6153,
      "rewards/accuracies": 0.6937500238418579,
      "rewards/chosen": -0.28197985887527466,
      "rewards/margins": 0.3022700846195221,
      "rewards/rejected": -0.5842499732971191,
      "step": 110
    },
    {
      "epoch": 1.0,
      "step": 119,
      "total_flos": 0.0,
      "train_loss": 0.6313913529660521,
      "train_runtime": 1987.426,
      "train_samples_per_second": 7.69,
      "train_steps_per_second": 0.06
    }
  ],
  "logging_steps": 10,
  "max_steps": 119,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}