{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 253.0375,
      "epoch": 0.08,
      "grad_norm": 0.34916529059410095,
      "kl": 0.00048295065280399283,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.0,
      "reward": 0.6274130865931511,
      "reward_std": 0.03938147491426207,
      "rewards/<lambda>": 0.6274130865931511,
      "step": 10
    },
    {
      "completion_length": 253.225,
      "epoch": 0.16,
      "grad_norm": 0.41210684180259705,
      "kl": 0.000624238243472064,
      "learning_rate": 7.600000000000001e-06,
      "loss": 0.0,
      "reward": 0.6234804779291153,
      "reward_std": 0.039024536509532484,
      "rewards/<lambda>": 0.6234804779291153,
      "step": 20
    },
    {
      "completion_length": 254.025,
      "epoch": 0.24,
      "grad_norm": 0.24894775450229645,
      "kl": 0.000612898166582454,
      "learning_rate": 1.16e-05,
      "loss": 0.0,
      "reward": 0.6120496317744255,
      "reward_std": 0.03366693327843677,
      "rewards/<lambda>": 0.6120496317744255,
      "step": 30
    },
    {
      "completion_length": 252.25,
      "epoch": 0.32,
      "grad_norm": 0.38096368312835693,
      "kl": 0.0006592169374926016,
      "learning_rate": 1.5600000000000003e-05,
      "loss": 0.0,
      "reward": 0.6164205402135849,
      "reward_std": 0.042428855784237385,
      "rewards/<lambda>": 0.6164205402135849,
      "step": 40
    },
    {
      "completion_length": 251.275,
      "epoch": 0.4,
      "grad_norm": 0.33936625719070435,
      "kl": 0.0006831091290223412,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 0.0,
      "reward": 0.6328483298420906,
      "reward_std": 0.035810240707360205,
      "rewards/<lambda>": 0.6328483298420906,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}