{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 78,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1282051282051282,
      "grad_norm": 35.16144561767578,
      "learning_rate": 4.997482666353286e-07,
      "logits/chosen": -4.892792224884033,
      "logits/rejected": -4.889645099639893,
      "logps/chosen": -109.9691162109375,
      "logps/rejected": -118.3992919921875,
      "loss": 0.6925,
      "rewards/accuracies": 0.4124999940395355,
      "rewards/chosen": 0.005595622584223747,
      "rewards/margins": 0.0018954325933009386,
      "rewards/rejected": 0.0037001892924308777,
      "step": 10
    },
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 33.09076690673828,
      "learning_rate": 4.7014888296418447e-07,
      "logits/chosen": -4.896066665649414,
      "logits/rejected": -4.894492149353027,
      "logps/chosen": -109.54179382324219,
      "logps/rejected": -114.97733306884766,
      "loss": 0.6925,
      "rewards/accuracies": 0.53125,
      "rewards/chosen": -0.010609785094857216,
      "rewards/margins": 0.0020811271388083696,
      "rewards/rejected": -0.012690911069512367,
      "step": 20
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 30.685495376586914,
      "learning_rate": 3.9694631307311825e-07,
      "logits/chosen": -4.896415710449219,
      "logits/rejected": -4.894046306610107,
      "logps/chosen": -107.42914581298828,
      "logps/rejected": -115.08940887451172,
      "loss": 0.6812,
      "rewards/accuracies": 0.675000011920929,
      "rewards/chosen": -0.007030453532934189,
      "rewards/margins": 0.02506021037697792,
      "rewards/rejected": -0.03209066763520241,
      "step": 30
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 32.84953308105469,
      "learning_rate": 2.9463922369965915e-07,
      "logits/chosen": -4.89896297454834,
      "logits/rejected": -4.89543342590332,
      "logps/chosen": -110.29290771484375,
      "logps/rejected": -118.01644897460938,
      "loss": 0.6726,
      "rewards/accuracies": 0.6624999642372131,
      "rewards/chosen": -0.025739433243870735,
      "rewards/margins": 0.04335205629467964,
      "rewards/rejected": -0.06909148395061493,
      "step": 40
    },
    {
      "epoch": 0.6410256410256411,
      "grad_norm": 30.98584747314453,
      "learning_rate": 1.8349078860833124e-07,
      "logits/chosen": -4.878735542297363,
      "logits/rejected": -4.874364852905273,
      "logps/chosen": -111.37123107910156,
      "logps/rejected": -120.30442810058594,
      "loss": 0.6678,
      "rewards/accuracies": 0.6937500834465027,
      "rewards/chosen": -0.05289134010672569,
      "rewards/margins": 0.05404452234506607,
      "rewards/rejected": -0.10693586617708206,
      "step": 50
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 28.358613967895508,
      "learning_rate": 8.551531851507185e-08,
      "logits/chosen": -4.883856773376465,
      "logits/rejected": -4.879419326782227,
      "logps/chosen": -109.68328094482422,
      "logps/rejected": -116.46817779541016,
      "loss": 0.6593,
      "rewards/accuracies": 0.731249988079071,
      "rewards/chosen": -0.046140156686306,
      "rewards/margins": 0.07184445112943649,
      "rewards/rejected": -0.11798460781574249,
      "step": 60
    },
    {
      "epoch": 0.8974358974358975,
      "grad_norm": 28.672161102294922,
      "learning_rate": 2.0118056862137354e-08,
      "logits/chosen": -4.915767669677734,
      "logits/rejected": -4.912926197052002,
      "logps/chosen": -107.08367919921875,
      "logps/rejected": -116.36421966552734,
      "loss": 0.6584,
      "rewards/accuracies": 0.762499988079071,
      "rewards/chosen": -0.06524230539798737,
      "rewards/margins": 0.07396502792835236,
      "rewards/rejected": -0.13920733332633972,
      "step": 70
    },
    {
      "epoch": 1.0,
      "step": 78,
      "total_flos": 31921202790400.0,
      "train_loss": 0.6738651104462452,
      "train_runtime": 50989.9065,
      "train_samples_per_second": 0.024,
      "train_steps_per_second": 0.002
    }
  ],
  "logging_steps": 10,
  "max_steps": 78,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 31921202790400.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}