{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.992,
  "eval_steps": 50,
  "global_step": 62,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016,
      "grad_norm": 98.16447669559693,
      "learning_rate": 7.142857142857142e-08,
      "logits/generated": -1.7165532112121582,
      "logits/real": -1.9473252296447754,
      "logps/generated": -275.8633728027344,
      "logps/real": -119.67874145507812,
      "loss": 0.8563,
      "rewards/accuracies": 0.0,
      "rewards/generated": 0.0,
      "rewards/margins": 0.0,
      "rewards/real": 0.0,
      "step": 1
    },
    {
      "epoch": 0.16,
      "grad_norm": 8.433954312310394,
      "learning_rate": 4.727272727272727e-07,
      "logits/generated": -1.7268381118774414,
      "logits/real": -1.6472580432891846,
      "logps/generated": -287.07708740234375,
      "logps/real": -172.39788818359375,
      "loss": 0.5272,
      "rewards/accuracies": 0.8472222089767456,
      "rewards/generated": -0.3371984362602234,
      "rewards/margins": 1.6153303384780884,
      "rewards/real": 1.2781319618225098,
      "step": 10
    },
    {
      "epoch": 0.32,
      "grad_norm": 2.0626183508441827,
      "learning_rate": 3.818181818181818e-07,
      "logits/generated": -1.3058226108551025,
      "logits/real": -1.6506996154785156,
      "logps/generated": -306.6280212402344,
      "logps/real": -114.25825500488281,
      "loss": 0.1169,
      "rewards/accuracies": 1.0,
      "rewards/generated": -2.2147715091705322,
      "rewards/margins": 8.338987350463867,
      "rewards/real": 6.124215602874756,
      "step": 20
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.5086367809412861,
      "learning_rate": 2.909090909090909e-07,
      "logits/generated": -1.0788180828094482,
      "logits/real": -1.9709659814834595,
      "logps/generated": -329.04046630859375,
      "logps/real": -102.8577880859375,
      "loss": 0.1079,
      "rewards/accuracies": 1.0,
      "rewards/generated": -4.102789878845215,
      "rewards/margins": 10.5944242477417,
      "rewards/real": 6.491633415222168,
      "step": 30
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.5442495957101562,
      "learning_rate": 2e-07,
      "logits/generated": -0.9625035524368286,
      "logits/real": -1.762656807899475,
      "logps/generated": -316.8744201660156,
      "logps/real": -105.2821044921875,
      "loss": 0.1084,
      "rewards/accuracies": 1.0,
      "rewards/generated": -4.126258373260498,
      "rewards/margins": 10.838096618652344,
      "rewards/real": 6.711838722229004,
      "step": 40
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.466220159360493,
      "learning_rate": 1.0909090909090908e-07,
      "logits/generated": -1.0104159116744995,
      "logits/real": -1.8771381378173828,
      "logps/generated": -325.93133544921875,
      "logps/real": -100.94727325439453,
      "loss": 0.1108,
      "rewards/accuracies": 1.0,
      "rewards/generated": -4.898512840270996,
      "rewards/margins": 11.485854148864746,
      "rewards/real": 6.58734130859375,
      "step": 50
    },
    {
      "epoch": 0.8,
      "eval_logits/generated": -0.9536736011505127,
      "eval_logits/real": -1.6165881156921387,
      "eval_logps/generated": -348.4621887207031,
      "eval_logps/real": -123.68927764892578,
      "eval_loss": 0.11147800087928772,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/generated": -5.697763442993164,
      "eval_rewards/margins": 12.328431129455566,
      "eval_rewards/real": 6.630667686462402,
      "eval_runtime": 31.5183,
      "eval_samples_per_second": 6.346,
      "eval_steps_per_second": 0.412,
      "step": 50
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.403885105692105,
      "learning_rate": 1.818181818181818e-08,
      "logits/generated": -1.0189651250839233,
      "logits/real": -1.817792296409607,
      "logps/generated": -332.2081298828125,
      "logps/real": -104.88079833984375,
      "loss": 0.1131,
      "rewards/accuracies": 1.0,
      "rewards/generated": -5.417947769165039,
      "rewards/margins": 11.97882080078125,
      "rewards/real": 6.560873985290527,
      "step": 60
    },
    {
      "epoch": 0.992,
      "step": 62,
      "total_flos": 0.0,
      "train_loss": 0.18373099305937368,
      "train_runtime": 1010.4406,
      "train_samples_per_second": 1.974,
      "train_steps_per_second": 0.061
    }
  ],
  "logging_steps": 10,
  "max_steps": 62,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}