{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9984,
  "eval_steps": 100,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 1.25e-06,
      "logits/chosen": -2.264090061187744,
      "logits/rejected": -2.2814104557037354,
      "logps/chosen": -378.7221984863281,
      "logps/rejected": -349.12091064453125,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.646121984004666e-06,
      "logits/chosen": -2.1407036781311035,
      "logits/rejected": -2.0471224784851074,
      "logps/chosen": -311.7917785644531,
      "logps/rejected": -308.5755920410156,
      "loss": 0.6844,
      "rewards/accuracies": 0.5381944179534912,
      "rewards/chosen": -0.03722098469734192,
      "rewards/margins": 0.02491396851837635,
      "rewards/rejected": -0.06213495507836342,
      "step": 10
    },
    {
      "epoch": 0.51,
      "learning_rate": 2.835583164544139e-06,
      "logits/chosen": -1.7066662311553955,
      "logits/rejected": -1.6785262823104858,
      "logps/chosen": -368.2060546875,
      "logps/rejected": -405.3633117675781,
      "loss": 0.6718,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -0.5245077013969421,
      "rewards/margins": 0.0827646404504776,
      "rewards/rejected": -0.6072723269462585,
      "step": 20
    },
    {
      "epoch": 0.77,
      "learning_rate": 7.723433775328385e-07,
      "logits/chosen": -1.618902564048767,
      "logits/rejected": -1.5914952754974365,
      "logps/chosen": -365.43450927734375,
      "logps/rejected": -394.15802001953125,
      "loss": 0.6538,
      "rewards/accuracies": 0.621874988079071,
      "rewards/chosen": -0.3924678862094879,
      "rewards/margins": 0.11069536209106445,
      "rewards/rejected": -0.50316321849823,
      "step": 30
    },
    {
      "epoch": 1.0,
      "step": 39,
      "total_flos": 0.0,
      "train_loss": 0.665724610671019,
      "train_runtime": 1696.1298,
      "train_samples_per_second": 2.948,
      "train_steps_per_second": 0.023
    }
  ],
  "logging_steps": 10,
  "max_steps": 39,
  "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
}