{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013333333333333334,
  "eval_steps": 500,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 485.49220275878906,
      "epoch": 0.0010666666666666667,
      "grad_norm": 0.13112049806907955,
      "kl": 0.0,
      "learning_rate": 7.142857142857142e-08,
      "loss": -0.0,
      "reward": 0.3281250111758709,
      "reward_std": 0.4913413915783167,
      "rewards/equation_reward_func": 0.05729166814126074,
      "rewards/format_reward_func": 0.27083334047347307,
      "step": 2
    },
    {
      "completion_length": 530.2265796661377,
      "epoch": 0.0021333333333333334,
      "grad_norm": 0.12198138838063947,
      "kl": 0.0003826618194580078,
      "learning_rate": 1.4285714285714285e-07,
      "loss": 0.0,
      "reward": 0.299479172565043,
      "reward_std": 0.44007157534360886,
      "rewards/equation_reward_func": 0.03385416744276881,
      "rewards/format_reward_func": 0.26562500977888703,
      "step": 4
    },
    {
      "completion_length": 496.8776264190674,
      "epoch": 0.0032,
      "grad_norm": 0.12162717174644112,
      "kl": 0.0003865957260131836,
      "learning_rate": 2.1428571428571426e-07,
      "loss": 0.0,
      "reward": 0.2916666781529784,
      "reward_std": 0.47719811648130417,
      "rewards/equation_reward_func": 0.05468750116415322,
      "rewards/format_reward_func": 0.23697917303070426,
      "step": 6
    },
    {
      "completion_length": 504.77865982055664,
      "epoch": 0.004266666666666667,
      "grad_norm": 0.13232346241260942,
      "kl": 0.0003762245178222656,
      "learning_rate": 2.857142857142857e-07,
      "loss": 0.0,
      "reward": 0.33593750558793545,
      "reward_std": 0.4751614350825548,
      "rewards/equation_reward_func": 0.04947916720993817,
      "rewards/format_reward_func": 0.28645834140479565,
      "step": 8
    },
    {
      "completion_length": 475.7057456970215,
      "epoch": 0.005333333333333333,
      "grad_norm": 0.13843718324607834,
      "kl": 0.0003968477249145508,
      "learning_rate": 3.5714285714285716e-07,
      "loss": 0.0,
      "reward": 0.3828125102445483,
      "reward_std": 0.5227206833660603,
      "rewards/equation_reward_func": 0.0885416679084301,
      "rewards/format_reward_func": 0.2942708395421505,
      "step": 10
    },
    {
      "completion_length": 475.98699378967285,
      "epoch": 0.0064,
      "grad_norm": 0.14337833822484186,
      "kl": 0.0004818439483642578,
      "learning_rate": 4.285714285714285e-07,
      "loss": 0.0,
      "reward": 0.33333334140479565,
      "reward_std": 0.4693184234201908,
      "rewards/equation_reward_func": 0.05468750139698386,
      "rewards/format_reward_func": 0.2786458395421505,
      "step": 12
    },
    {
      "completion_length": 472.8099060058594,
      "epoch": 0.007466666666666667,
      "grad_norm": 0.129867140491159,
      "kl": 0.0007684230804443359,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 0.45052084885537624,
      "reward_std": 0.5166866518557072,
      "rewards/equation_reward_func": 0.041666667675599456,
      "rewards/format_reward_func": 0.40885418094694614,
      "step": 14
    },
    {
      "completion_length": 464.46875762939453,
      "epoch": 0.008533333333333334,
      "grad_norm": 0.1279190002551803,
      "kl": 0.0013058185577392578,
      "learning_rate": 4.999740409224932e-07,
      "loss": 0.0,
      "reward": 0.5052083488553762,
      "reward_std": 0.5728582534939051,
      "rewards/equation_reward_func": 0.06510416814126074,
      "rewards/format_reward_func": 0.4401041753590107,
      "step": 16
    },
    {
      "completion_length": 480.2291717529297,
      "epoch": 0.0096,
      "grad_norm": 0.10647649710010443,
      "kl": 0.00380706787109375,
      "learning_rate": 4.998961690809627e-07,
      "loss": 0.0,
      "reward": 0.6588541902601719,
      "reward_std": 0.5287479311227798,
      "rewards/equation_reward_func": 0.05468750139698386,
      "rewards/format_reward_func": 0.6041666828095913,
      "step": 18
    },
    {
      "completion_length": 493.8073043823242,
      "epoch": 0.010666666666666666,
      "grad_norm": 0.10522760864642984,
      "kl": 0.004913330078125,
      "learning_rate": 4.997664006472578e-07,
      "loss": 0.0,
      "reward": 0.7734375223517418,
      "reward_std": 0.4910791157744825,
      "rewards/equation_reward_func": 0.07031250116415322,
      "rewards/format_reward_func": 0.7031250186264515,
      "step": 20
    },
    {
      "completion_length": 455.6510524749756,
      "epoch": 0.011733333333333333,
      "grad_norm": 0.09917661844432689,
      "kl": 0.008411407470703125,
      "learning_rate": 4.995847625707292e-07,
      "loss": 0.0,
      "reward": 0.7812500186264515,
      "reward_std": 0.4674575887620449,
      "rewards/equation_reward_func": 0.0651041679084301,
      "rewards/format_reward_func": 0.7161458507180214,
      "step": 22
    },
    {
      "completion_length": 464.50782012939453,
      "epoch": 0.0128,
      "grad_norm": 0.10189992043189328,
      "kl": 0.0059833526611328125,
      "learning_rate": 4.993512925726318e-07,
      "loss": 0.0,
      "reward": 0.8619791865348816,
      "reward_std": 0.49650320410728455,
      "rewards/equation_reward_func": 0.08854166860692203,
      "rewards/format_reward_func": 0.7734375223517418,
      "step": 24
    }
  ],
  "logging_steps": 2,
  "max_steps": 450,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "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": 1,
  "trial_name": null,
  "trial_params": null
}