{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.995334370139969,
  "eval_steps": 100,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 60.11629695892334,
      "epoch": 0.12441679626749612,
      "grad_norm": 16.40437889099121,
      "kl": 63.01280255060992,
      "learning_rate": 1.9961946980917457e-05,
      "loss": 2.5205,
      "reward": 0.38191965967416763,
      "reward_std": 0.2867388492450118,
      "rewards/accuracy_reward": 0.2412946522468701,
      "rewards/format_reward": 0.140625008684583,
      "step": 10
    },
    {
      "completion_length": 16.49442042708397,
      "epoch": 0.24883359253499224,
      "grad_norm": 23.840904235839844,
      "kl": 3.4006959587335586,
      "learning_rate": 1.866025403784439e-05,
      "loss": 0.136,
      "reward": 0.6703125294297934,
      "reward_std": 0.0943066231906414,
      "rewards/accuracy_reward": 0.6703125294297934,
      "rewards/format_reward": 0.0,
      "step": 20
    },
    {
      "completion_length": 6.576339554786682,
      "epoch": 0.37325038880248834,
      "grad_norm": 98.27102661132812,
      "kl": 3.4875148802995684,
      "learning_rate": 1.573576436351046e-05,
      "loss": 0.1395,
      "reward": 0.6897321730852127,
      "reward_std": 0.05730184903368354,
      "rewards/accuracy_reward": 0.6897321730852127,
      "rewards/format_reward": 0.0,
      "step": 30
    },
    {
      "completion_length": 5.630803817510605,
      "epoch": 0.4976671850699845,
      "grad_norm": 13.046979904174805,
      "kl": 6.134880331158638,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 0.2454,
      "reward": 0.675892886146903,
      "reward_std": 0.06669598994776607,
      "rewards/accuracy_reward": 0.675892886146903,
      "rewards/format_reward": 0.0,
      "step": 40
    },
    {
      "completion_length": 4.387500202655792,
      "epoch": 0.6220839813374806,
      "grad_norm": 9.880926132202148,
      "kl": 4.37996047437191,
      "learning_rate": 7.411809548974792e-06,
      "loss": 0.1752,
      "reward": 0.722098245844245,
      "reward_std": 0.053018782567232844,
      "rewards/accuracy_reward": 0.722098245844245,
      "rewards/format_reward": 0.0,
      "step": 50
    },
    {
      "completion_length": 4.102901968359947,
      "epoch": 0.7465007776049767,
      "grad_norm": 44.39680099487305,
      "kl": 4.635663989186287,
      "learning_rate": 3.5721239031346067e-06,
      "loss": 0.1854,
      "reward": 0.806026816368103,
      "reward_std": 0.03498344626277685,
      "rewards/accuracy_reward": 0.806026816368103,
      "rewards/format_reward": 0.0,
      "step": 60
    },
    {
      "completion_length": 4.064062669873238,
      "epoch": 0.8709175738724728,
      "grad_norm": 11.00207805633545,
      "kl": 4.604912614822387,
      "learning_rate": 9.369221296335007e-07,
      "loss": 0.1842,
      "reward": 0.8270089641213417,
      "reward_std": 0.038598133344203235,
      "rewards/accuracy_reward": 0.8270089641213417,
      "rewards/format_reward": 0.0,
      "step": 70
    },
    {
      "completion_length": 4.110714480280876,
      "epoch": 0.995334370139969,
      "grad_norm": 81.93522644042969,
      "kl": 4.7607938081026075,
      "learning_rate": 0.0,
      "loss": 0.1904,
      "reward": 0.8185268178582191,
      "reward_std": 0.0355328387580812,
      "rewards/accuracy_reward": 0.8185268178582191,
      "rewards/format_reward": 0.0,
      "step": 80
    },
    {
      "epoch": 0.995334370139969,
      "step": 80,
      "total_flos": 0.0,
      "train_loss": 0.47208611369132997,
      "train_runtime": 1802.3417,
      "train_samples_per_second": 2.497,
      "train_steps_per_second": 0.044
    }
  ],
  "logging_steps": 10,
  "max_steps": 80,
  "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
}