{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.646090534979424,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3292181069958848,
      "grad_norm": 0.5561477541923523,
      "learning_rate": 8.333333333333333e-07,
      "logits/chosen": 1.7485754489898682,
      "logits/rejected": 1.8832639455795288,
      "logps/chosen": -70.18267059326172,
      "logps/rejected": -77.9986343383789,
      "loss": 0.6938,
      "rewards/accuracies": 0.4749999940395355,
      "rewards/chosen": 0.005453853867948055,
      "rewards/margins": 0.013218576088547707,
      "rewards/rejected": -0.007764720823615789,
      "step": 10
    },
    {
      "epoch": 0.6584362139917695,
      "grad_norm": 0.48141908645629883,
      "learning_rate": 1.6666666666666667e-06,
      "logits/chosen": 1.9016907215118408,
      "logits/rejected": 1.9251121282577515,
      "logps/chosen": -96.5027847290039,
      "logps/rejected": -87.00735473632812,
      "loss": 0.6937,
      "rewards/accuracies": 0.5249999761581421,
      "rewards/chosen": -0.005797500256448984,
      "rewards/margins": -0.0004409264656715095,
      "rewards/rejected": -0.005356573965400457,
      "step": 20
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.4639015197753906,
      "learning_rate": 2.5e-06,
      "logits/chosen": 1.7938541173934937,
      "logits/rejected": 1.6962993144989014,
      "logps/chosen": -71.47590637207031,
      "logps/rejected": -66.45989227294922,
      "loss": 0.6942,
      "rewards/accuracies": 0.4124999940395355,
      "rewards/chosen": -0.004830303601920605,
      "rewards/margins": -0.00935445912182331,
      "rewards/rejected": 0.004524155054241419,
      "step": 30
    },
    {
      "epoch": 1.316872427983539,
      "grad_norm": 0.44931092858314514,
      "learning_rate": 3.3333333333333333e-06,
      "logits/chosen": 1.8256213665008545,
      "logits/rejected": 1.8677200078964233,
      "logps/chosen": -75.90711975097656,
      "logps/rejected": -76.26548767089844,
      "loss": 0.6935,
      "rewards/accuracies": 0.5375000238418579,
      "rewards/chosen": -0.004859285429120064,
      "rewards/margins": -0.007447429001331329,
      "rewards/rejected": 0.0025881435722112656,
      "step": 40
    },
    {
      "epoch": 1.646090534979424,
      "grad_norm": 0.512350857257843,
      "learning_rate": 4.166666666666667e-06,
      "logits/chosen": 1.7572576999664307,
      "logits/rejected": 1.7408854961395264,
      "logps/chosen": -80.90664672851562,
      "logps/rejected": -85.82096862792969,
      "loss": 0.6937,
      "rewards/accuracies": 0.4749999940395355,
      "rewards/chosen": -0.00120059447363019,
      "rewards/margins": -0.0018891148502007127,
      "rewards/rejected": 0.0006885197362862527,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7075005624732877e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}