{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9984,
  "eval_steps": 100,
  "global_step": 78,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 6.25e-07,
      "logits/chosen": -2.882505416870117,
      "logits/rejected": -2.8317012786865234,
      "logps/chosen": -292.0869140625,
      "logps/rejected": -281.9166259765625,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.989935734988098e-06,
      "logits/chosen": -2.760279893875122,
      "logits/rejected": -2.7416226863861084,
      "logps/chosen": -269.30419921875,
      "logps/rejected": -258.9988098144531,
      "loss": 0.692,
      "rewards/accuracies": 0.5208333134651184,
      "rewards/chosen": -0.0003755867655854672,
      "rewards/margins": 0.0020193441305309534,
      "rewards/rejected": -0.0023949304595589638,
      "step": 10
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.646121984004666e-06,
      "logits/chosen": -2.7458298206329346,
      "logits/rejected": -2.6916747093200684,
      "logps/chosen": -292.1165771484375,
      "logps/rejected": -262.5185546875,
      "loss": 0.6832,
      "rewards/accuracies": 0.667187511920929,
      "rewards/chosen": 0.0018152827396988869,
      "rewards/margins": 0.019987957552075386,
      "rewards/rejected": -0.018172672018408775,
      "step": 20
    },
    {
      "epoch": 0.38,
      "learning_rate": 3.8772424536302565e-06,
      "logits/chosen": -2.7215728759765625,
      "logits/rejected": -2.6702420711517334,
      "logps/chosen": -277.44805908203125,
      "logps/rejected": -274.95843505859375,
      "loss": 0.6721,
      "rewards/accuracies": 0.676562488079071,
      "rewards/chosen": 0.019489800557494164,
      "rewards/margins": 0.04290051385760307,
      "rewards/rejected": -0.02341071143746376,
      "step": 30
    },
    {
      "epoch": 0.51,
      "learning_rate": 2.835583164544139e-06,
      "logits/chosen": -2.7158000469207764,
      "logits/rejected": -2.6738948822021484,
      "logps/chosen": -264.43963623046875,
      "logps/rejected": -257.14398193359375,
      "loss": 0.6625,
      "rewards/accuracies": 0.6343749761581421,
      "rewards/chosen": 0.0011910212924703956,
      "rewards/margins": 0.05646045133471489,
      "rewards/rejected": -0.055269431322813034,
      "step": 40
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.7274575140626318e-06,
      "logits/chosen": -2.67500638961792,
      "logits/rejected": -2.6178138256073,
      "logps/chosen": -276.2191467285156,
      "logps/rejected": -270.31317138671875,
      "loss": 0.6502,
      "rewards/accuracies": 0.6875,
      "rewards/chosen": -0.02652786299586296,
      "rewards/margins": 0.08806131035089493,
      "rewards/rejected": -0.11458916962146759,
      "step": 50
    },
    {
      "epoch": 0.77,
      "learning_rate": 7.723433775328385e-07,
      "logits/chosen": -2.65384840965271,
      "logits/rejected": -2.599376916885376,
      "logps/chosen": -279.11370849609375,
      "logps/rejected": -260.7146911621094,
      "loss": 0.6465,
      "rewards/accuracies": 0.699999988079071,
      "rewards/chosen": -0.02440836653113365,
      "rewards/margins": 0.11430301517248154,
      "rewards/rejected": -0.1387113779783249,
      "step": 60
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.59412823400657e-07,
      "logits/chosen": -2.668872833251953,
      "logits/rejected": -2.5930261611938477,
      "logps/chosen": -283.5231628417969,
      "logps/rejected": -279.5673828125,
      "loss": 0.6429,
      "rewards/accuracies": 0.692187488079071,
      "rewards/chosen": -0.021219942718744278,
      "rewards/margins": 0.12081662565469742,
      "rewards/rejected": -0.1420365869998932,
      "step": 70
    },
    {
      "epoch": 1.0,
      "step": 78,
      "total_flos": 0.0,
      "train_loss": 0.6621483755417359,
      "train_runtime": 6542.6499,
      "train_samples_per_second": 3.057,
      "train_steps_per_second": 0.012
    }
  ],
  "logging_steps": 10,
  "max_steps": 78,
  "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
}