{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005333333333333333,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 495.080379486084,
      "epoch": 0.00035555555555555557,
      "grad_norm": 0.2174892404258369,
      "kl": 0.0,
      "learning_rate": 4.985344892885899e-07,
      "loss": 0.0,
      "reward": 0.2857143022119999,
      "reward_std": 0.43269163370132446,
      "rewards/equation_reward_func": 0.0357142873108387,
      "rewards/format_reward_func": 0.2500000149011612,
      "step": 2
    },
    {
      "completion_length": 497.4018096923828,
      "epoch": 0.0007111111111111111,
      "grad_norm": 0.22154184238668786,
      "kl": 0.0003987550735473633,
      "learning_rate": 4.869132927957006e-07,
      "loss": 0.0,
      "reward": 0.35714287776499987,
      "reward_std": 0.4787949416786432,
      "rewards/equation_reward_func": 0.05357143096625805,
      "rewards/format_reward_func": 0.30357144866138697,
      "step": 4
    },
    {
      "completion_length": 502.78573989868164,
      "epoch": 0.0010666666666666667,
      "grad_norm": 0.18277559355029982,
      "kl": 0.0004475116729736328,
      "learning_rate": 4.642142940418973e-07,
      "loss": 0.0,
      "reward": 0.28571430314332247,
      "reward_std": 0.4405473303049803,
      "rewards/equation_reward_func": 0.0357142873108387,
      "rewards/format_reward_func": 0.2500000139698386,
      "step": 6
    },
    {
      "completion_length": 475.142879486084,
      "epoch": 0.0014222222222222223,
      "grad_norm": 0.19482331072759956,
      "kl": 0.0005053281784057617,
      "learning_rate": 4.314988729807827e-07,
      "loss": 0.0,
      "reward": 0.3660714477300644,
      "reward_std": 0.48892509937286377,
      "rewards/equation_reward_func": 0.04464286006987095,
      "rewards/format_reward_func": 0.32142858672887087,
      "step": 8
    },
    {
      "completion_length": 484.68752098083496,
      "epoch": 0.0017777777777777779,
      "grad_norm": 0.18758626438214032,
      "kl": 0.0006405115127563477,
      "learning_rate": 3.902967663405956e-07,
      "loss": 0.0,
      "reward": 0.4107143012806773,
      "reward_std": 0.5162536893039942,
      "rewards/equation_reward_func": 0.05357143096625805,
      "rewards/format_reward_func": 0.3571428721770644,
      "step": 10
    },
    {
      "completion_length": 476.7410888671875,
      "epoch": 0.0021333333333333334,
      "grad_norm": 0.19195993642334963,
      "kl": 0.0009016990661621094,
      "learning_rate": 3.4253453883497864e-07,
      "loss": 0.0,
      "reward": 0.4375000251457095,
      "reward_std": 0.5308322850614786,
      "rewards/equation_reward_func": 0.05357143096625805,
      "rewards/format_reward_func": 0.38392859138548374,
      "step": 12
    },
    {
      "completion_length": 513.0893096923828,
      "epoch": 0.002488888888888889,
      "grad_norm": 0.1780296803915782,
      "kl": 0.0014204978942871094,
      "learning_rate": 2.9044549913819124e-07,
      "loss": 0.0,
      "reward": 0.5803571734577417,
      "reward_std": 0.5420807637274265,
      "rewards/equation_reward_func": 0.08035714738070965,
      "rewards/format_reward_func": 0.5000000242143869,
      "step": 14
    },
    {
      "completion_length": 475.6964473724365,
      "epoch": 0.0028444444444444446,
      "grad_norm": 0.18578955531425126,
      "kl": 0.0019216537475585938,
      "learning_rate": 2.3646527285364563e-07,
      "loss": 0.0,
      "reward": 0.6339286062866449,
      "reward_std": 0.5776853580027819,
      "rewards/equation_reward_func": 0.08928571827709675,
      "rewards/format_reward_func": 0.5446428842842579,
      "step": 16
    },
    {
      "completion_length": 472.723237991333,
      "epoch": 0.0032,
      "grad_norm": 0.17761745784153318,
      "kl": 0.002444744110107422,
      "learning_rate": 1.8311791536769483e-07,
      "loss": 0.0,
      "reward": 0.5625000214204192,
      "reward_std": 0.5268590040504932,
      "rewards/equation_reward_func": 0.044642859138548374,
      "rewards/format_reward_func": 0.517857170663774,
      "step": 18
    },
    {
      "completion_length": 443.6964530944824,
      "epoch": 0.0035555555555555557,
      "grad_norm": 0.21019280132551116,
      "kl": 0.0029592514038085938,
      "learning_rate": 1.328978898250525e-07,
      "loss": 0.0,
      "reward": 0.5982143143191934,
      "reward_std": 0.5197608303278685,
      "rewards/equation_reward_func": 0.05357143096625805,
      "rewards/format_reward_func": 0.5446428870782256,
      "step": 20
    },
    {
      "completion_length": 448.9821662902832,
      "epoch": 0.003911111111111111,
      "grad_norm": 0.21013630596816346,
      "kl": 0.0033364295959472656,
      "learning_rate": 8.81534288045431e-08,
      "loss": 0.0,
      "reward": 0.6517857424914837,
      "reward_std": 0.5414303578436375,
      "rewards/equation_reward_func": 0.044642859138548374,
      "rewards/format_reward_func": 0.6071428805589676,
      "step": 22
    },
    {
      "completion_length": 495.6785888671875,
      "epoch": 0.004266666666666667,
      "grad_norm": 0.18425036339737497,
      "kl": 0.0029821395874023438,
      "learning_rate": 5.097673357358906e-08,
      "loss": 0.0,
      "reward": 0.6607143096625805,
      "reward_std": 0.5480529572814703,
      "rewards/equation_reward_func": 0.06250000279396772,
      "rewards/format_reward_func": 0.5982143189758062,
      "step": 24
    },
    {
      "completion_length": 429.2589511871338,
      "epoch": 0.004622222222222222,
      "grad_norm": 0.21101924326333663,
      "kl": 0.004176139831542969,
      "learning_rate": 2.3106145082260774e-08,
      "loss": 0.0,
      "reward": 0.6339285988360643,
      "reward_std": 0.6071197390556335,
      "rewards/equation_reward_func": 0.08035714738070965,
      "rewards/format_reward_func": 0.5535714533179998,
      "step": 26
    },
    {
      "completion_length": 461.3214530944824,
      "epoch": 0.004977777777777778,
      "grad_norm": 0.18232336491131187,
      "kl": 0.0030603408813476562,
      "learning_rate": 5.844861072478335e-09,
      "loss": 0.0,
      "reward": 0.7500000353902578,
      "reward_std": 0.5386870224028826,
      "rewards/equation_reward_func": 0.08928571827709675,
      "rewards/format_reward_func": 0.6607143077999353,
      "step": 28
    },
    {
      "completion_length": 432.61609077453613,
      "epoch": 0.005333333333333333,
      "grad_norm": 0.1956194297501798,
      "kl": 0.0031890869140625,
      "learning_rate": 0.0,
      "loss": 0.0,
      "reward": 0.7321428880095482,
      "reward_std": 0.505688888952136,
      "rewards/equation_reward_func": 0.026785715483129025,
      "rewards/format_reward_func": 0.7053571790456772,
      "step": 30
    },
    {
      "epoch": 0.005333333333333333,
      "step": 30,
      "total_flos": 0.0,
      "train_loss": 1.9422600227395983e-06,
      "train_runtime": 1359.2142,
      "train_samples_per_second": 1.236,
      "train_steps_per_second": 0.022
    }
  ],
  "logging_steps": 2,
  "max_steps": 30,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}