{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9874476987447699,
  "eval_steps": 500,
  "global_step": 59,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 8.333333333333333e-08,
      "logits/chosen": -2.940945625305176,
      "logits/rejected": -2.8081953525543213,
      "logps/chosen": -373.83038330078125,
      "logps/pi_response": -367.2508544921875,
      "logps/ref_response": -367.2508544921875,
      "logps/rejected": -354.8029479980469,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.930057285201027e-07,
      "logits/chosen": -2.8032095432281494,
      "logits/rejected": -2.7498764991760254,
      "logps/chosen": -334.4217529296875,
      "logps/pi_response": -352.21014404296875,
      "logps/ref_response": -351.01263427734375,
      "logps/rejected": -357.6781311035156,
      "loss": 0.6883,
      "rewards/accuracies": 0.5763888955116272,
      "rewards/chosen": -0.020477451384067535,
      "rewards/margins": 0.022380363196134567,
      "rewards/rejected": -0.0428578145802021,
      "step": 10
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.187457503795526e-07,
      "logits/chosen": -2.7823891639709473,
      "logits/rejected": -2.7310681343078613,
      "logps/chosen": -357.344482421875,
      "logps/pi_response": -359.2858581542969,
      "logps/ref_response": -349.52899169921875,
      "logps/rejected": -366.3606872558594,
      "loss": 0.6344,
      "rewards/accuracies": 0.690625011920929,
      "rewards/chosen": -0.1733517050743103,
      "rewards/margins": 0.18930229544639587,
      "rewards/rejected": -0.3626540005207062,
      "step": 20
    },
    {
      "epoch": 0.5,
      "learning_rate": 2.8691164100062034e-07,
      "logits/chosen": -2.6963818073272705,
      "logits/rejected": -2.6740260124206543,
      "logps/chosen": -387.28399658203125,
      "logps/pi_response": -385.0074157714844,
      "logps/ref_response": -349.4725341796875,
      "logps/rejected": -426.54205322265625,
      "loss": 0.588,
      "rewards/accuracies": 0.671875,
      "rewards/chosen": -0.5384770035743713,
      "rewards/margins": 0.38316935300827026,
      "rewards/rejected": -0.9216462969779968,
      "step": 30
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.4248369943086995e-07,
      "logits/chosen": -2.576090097427368,
      "logits/rejected": -2.5352632999420166,
      "logps/chosen": -388.36114501953125,
      "logps/pi_response": -392.815185546875,
      "logps/ref_response": -334.27154541015625,
      "logps/rejected": -480.95147705078125,
      "loss": 0.5299,
      "rewards/accuracies": 0.6968749761581421,
      "rewards/chosen": -0.759750485420227,
      "rewards/margins": 0.683925211429596,
      "rewards/rejected": -1.4436757564544678,
      "step": 40
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.473909705816111e-08,
      "logits/chosen": -2.5585336685180664,
      "logits/rejected": -2.5140857696533203,
      "logps/chosen": -400.4565734863281,
      "logps/pi_response": -407.38433837890625,
      "logps/ref_response": -343.3310546875,
      "logps/rejected": -472.02996826171875,
      "loss": 0.5298,
      "rewards/accuracies": 0.731249988079071,
      "rewards/chosen": -0.7769991159439087,
      "rewards/margins": 0.6114187240600586,
      "rewards/rejected": -1.3884178400039673,
      "step": 50
    },
    {
      "epoch": 0.99,
      "step": 59,
      "total_flos": 0.0,
      "train_loss": 0.5893503851809744,
      "train_runtime": 3552.0479,
      "train_samples_per_second": 4.303,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 10,
  "max_steps": 59,
  "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
}