{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 14,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 3.1672253608703613,
      "learning_rate": 1.9714285714285718e-05,
      "logps/anchor": 0.4348521828651428,
      "logps/policy": -69.89246368408203,
      "loss": 0.3538,
      "step": 1
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 12.092653274536133,
      "learning_rate": 1.942857142857143e-05,
      "logps/anchor": 0.6565061807632446,
      "logps/policy": -72.86190032958984,
      "loss": 0.4353,
      "step": 2
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 4.009256839752197,
      "learning_rate": 1.9142857142857146e-05,
      "logps/anchor": 0.24830026924610138,
      "logps/policy": -72.61256408691406,
      "loss": 0.3256,
      "step": 3
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 2.732830286026001,
      "learning_rate": 1.885714285714286e-05,
      "logps/anchor": 0.28446492552757263,
      "logps/policy": -60.2266731262207,
      "loss": 0.3314,
      "step": 4
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 1.894191026687622,
      "learning_rate": 1.8571428571428575e-05,
      "logps/anchor": 0.4391743540763855,
      "logps/policy": -66.86183166503906,
      "loss": 0.3081,
      "step": 5
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 1.734279751777649,
      "learning_rate": 1.8285714285714288e-05,
      "logps/anchor": 0.29031452536582947,
      "logps/policy": -59.80109786987305,
      "loss": 0.2218,
      "step": 6
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.2599438428878784,
      "learning_rate": 1.8e-05,
      "logps/anchor": 0.062131937593221664,
      "logps/policy": -66.06212615966797,
      "loss": 0.1533,
      "step": 7
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 1.0272470712661743,
      "learning_rate": 1.7714285714285717e-05,
      "logps/anchor": 0.08727352321147919,
      "logps/policy": -31.806640625,
      "loss": 0.127,
      "step": 8
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 1.0852797031402588,
      "learning_rate": 1.742857142857143e-05,
      "logps/anchor": 0.16654472053050995,
      "logps/policy": -37.08126449584961,
      "loss": 0.1622,
      "step": 9
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 1.2848658561706543,
      "learning_rate": 1.7142857142857142e-05,
      "logps/anchor": 0.2580033540725708,
      "logps/policy": -34.01033401489258,
      "loss": 0.1272,
      "step": 10
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 1.1476317644119263,
      "learning_rate": 1.6857142857142858e-05,
      "logps/anchor": 0.1905135065317154,
      "logps/policy": -29.186994552612305,
      "loss": 0.1409,
      "step": 11
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 1.1124459505081177,
      "learning_rate": 1.6571428571428574e-05,
      "logps/anchor": 0.08628815412521362,
      "logps/policy": -32.86701202392578,
      "loss": 0.091,
      "step": 12
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 1.09062922000885,
      "learning_rate": 1.6285714285714287e-05,
      "logps/anchor": 0.06508912891149521,
      "logps/policy": -31.805673599243164,
      "loss": 0.093,
      "step": 13
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.8760924935340881,
      "learning_rate": 1.6000000000000003e-05,
      "logps/anchor": 0.022830532863736153,
      "logps/policy": -36.078948974609375,
      "loss": 0.0725,
      "step": 14
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 70,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}