{
  "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": 172.64869693559058,
      "learning_rate": 7.142857142857142e-08,
      "logits/generated": -1.2273778915405273,
      "logits/real": -1.2039141654968262,
      "logps/generated": -206.67124938964844,
      "logps/real": -205.5660400390625,
      "loss": 0.8641,
      "rewards/accuracies": 0.0,
      "rewards/generated": 0.0,
      "rewards/margins": 0.0,
      "rewards/real": 0.0,
      "step": 1
    },
    {
      "epoch": 0.16,
      "grad_norm": 17.9963728436732,
      "learning_rate": 4.727272727272727e-07,
      "logits/generated": -0.9921329021453857,
      "logits/real": -1.4087518453598022,
      "logps/generated": -269.45074462890625,
      "logps/real": -176.27444458007812,
      "loss": 0.5717,
      "rewards/accuracies": 0.7916666865348816,
      "rewards/generated": -0.5155463218688965,
      "rewards/margins": 1.0976147651672363,
      "rewards/real": 0.5820685625076294,
      "step": 10
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.3167505323680695,
      "learning_rate": 3.818181818181818e-07,
      "logits/generated": -0.9158234596252441,
      "logits/real": -1.23444402217865,
      "logps/generated": -290.01763916015625,
      "logps/real": -133.15634155273438,
      "loss": 0.1401,
      "rewards/accuracies": 1.0,
      "rewards/generated": -1.8766648769378662,
      "rewards/margins": 6.993840217590332,
      "rewards/real": 5.117175579071045,
      "step": 20
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.143979248605827,
      "learning_rate": 2.909090909090909e-07,
      "logits/generated": -0.8833307027816772,
      "logits/real": -1.2017673254013062,
      "logps/generated": -291.2628173828125,
      "logps/real": -108.21414947509766,
      "loss": 0.1051,
      "rewards/accuracies": 1.0,
      "rewards/generated": -2.4183554649353027,
      "rewards/margins": 9.443326950073242,
      "rewards/real": 7.024971961975098,
      "step": 30
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.1521481495621884,
      "learning_rate": 2e-07,
      "logits/generated": -0.8197547793388367,
      "logits/real": -1.3791146278381348,
      "logps/generated": -300.85272216796875,
      "logps/real": -103.9669418334961,
      "loss": 0.109,
      "rewards/accuracies": 1.0,
      "rewards/generated": -2.676192283630371,
      "rewards/margins": 10.094086647033691,
      "rewards/real": 7.417893409729004,
      "step": 40
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.9444812615274184,
      "learning_rate": 1.0909090909090908e-07,
      "logits/generated": -0.7446190714836121,
      "logits/real": -1.2031835317611694,
      "logps/generated": -291.2001037597656,
      "logps/real": -112.4259033203125,
      "loss": 0.1077,
      "rewards/accuracies": 1.0,
      "rewards/generated": -3.0988755226135254,
      "rewards/margins": 10.734658241271973,
      "rewards/real": 7.6357831954956055,
      "step": 50
    },
    {
      "epoch": 0.8,
      "eval_logits/generated": -0.7102611064910889,
      "eval_logits/real": -1.2791945934295654,
      "eval_logps/generated": -309.5072021484375,
      "eval_logps/real": -106.08367156982422,
      "eval_loss": 0.11177420616149902,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/generated": -3.027305841445923,
      "eval_rewards/margins": 10.505950927734375,
      "eval_rewards/real": 7.478644847869873,
      "eval_runtime": 43.646,
      "eval_samples_per_second": 4.582,
      "eval_steps_per_second": 0.298,
      "step": 50
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.9396063017984428,
      "learning_rate": 1.818181818181818e-08,
      "logits/generated": -0.8561418652534485,
      "logits/real": -1.2593237161636353,
      "logps/generated": -298.5728454589844,
      "logps/real": -117.7249526977539,
      "loss": 0.105,
      "rewards/accuracies": 1.0,
      "rewards/generated": -3.1451587677001953,
      "rewards/margins": 11.042920112609863,
      "rewards/real": 7.897761344909668,
      "step": 60
    },
    {
      "epoch": 0.992,
      "step": 62,
      "total_flos": 0.0,
      "train_loss": 0.19183721777892881,
      "train_runtime": 1154.8655,
      "train_samples_per_second": 1.728,
      "train_steps_per_second": 0.054
    }
  ],
  "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
}