{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 67,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 354.5310432434082,
      "epoch": 0.14925373134328357,
      "grad_norm": 26.582666397094727,
      "kl": 0.02456921637058258,
      "learning_rate": 2.981532510892707e-06,
      "loss": 0.001,
      "reward": 0.38080358956940474,
      "reward_std": 0.3429007441736758,
      "rewards/accuracy_reward": 0.12935268479632214,
      "rewards/format_reward": 0.2514509041327983,
      "step": 10
    },
    {
      "completion_length": 82.56049494743347,
      "epoch": 0.29850746268656714,
      "grad_norm": 6.207046031951904,
      "kl": 0.192266845703125,
      "learning_rate": 2.6657189421854562e-06,
      "loss": 0.0077,
      "reward": 1.1937500540167094,
      "reward_std": 0.2890436253976077,
      "rewards/accuracy_reward": 0.2324776900582947,
      "rewards/format_reward": 0.9612723555415869,
      "step": 20
    },
    {
      "completion_length": 163.46440453529357,
      "epoch": 0.44776119402985076,
      "grad_norm": 0.9332170486450195,
      "kl": 0.28681182861328125,
      "learning_rate": 2.03755192431795e-06,
      "loss": 0.0115,
      "reward": 1.377120592445135,
      "reward_std": 0.35549838868901135,
      "rewards/accuracy_reward": 0.4252232332248241,
      "rewards/format_reward": 0.9518973540514708,
      "step": 30
    },
    {
      "completion_length": 289.2572672843933,
      "epoch": 0.5970149253731343,
      "grad_norm": 0.30436766147613525,
      "kl": 0.11348419189453125,
      "learning_rate": 1.2653483024396534e-06,
      "loss": 0.0045,
      "reward": 1.5142857864499093,
      "reward_std": 0.3293194776400924,
      "rewards/accuracy_reward": 0.5575893112458289,
      "rewards/format_reward": 0.9566964589059352,
      "step": 40
    },
    {
      "completion_length": 328.3682068824768,
      "epoch": 0.746268656716418,
      "grad_norm": 0.4712439179420471,
      "kl": 0.0519775390625,
      "learning_rate": 5.560194134252441e-07,
      "loss": 0.0021,
      "reward": 1.4938616767525672,
      "reward_std": 0.352480823546648,
      "rewards/accuracy_reward": 0.5599330620840192,
      "rewards/format_reward": 0.9339286085218191,
      "step": 50
    },
    {
      "completion_length": 326.48863105773927,
      "epoch": 0.8955223880597015,
      "grad_norm": 1.6945326328277588,
      "kl": 0.05061798095703125,
      "learning_rate": 9.962936025419756e-08,
      "loss": 0.002,
      "reward": 1.528236673772335,
      "reward_std": 0.33247090512886646,
      "rewards/accuracy_reward": 0.574107170663774,
      "rewards/format_reward": 0.9541294977068902,
      "step": 60
    },
    {
      "completion_length": 317.54422964368547,
      "epoch": 1.0,
      "kl": 0.05271693638392857,
      "reward": 1.535608057464872,
      "reward_std": 0.3223346844315529,
      "rewards/accuracy_reward": 0.5788690721882241,
      "rewards/format_reward": 0.9567389748990536,
      "step": 67,
      "total_flos": 0.0,
      "train_loss": 0.004519763499943178,
      "train_runtime": 8988.1744,
      "train_samples_per_second": 0.834,
      "train_steps_per_second": 0.007
    }
  ],
  "logging_steps": 10,
  "max_steps": 67,
  "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": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}