{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8403361344537815,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "clip_ratio": 0.0,
      "completion_length": 1599.671875,
      "epoch": 0.01680672268907563,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "num_tokens": 266094.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 1
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1544.015625,
      "epoch": 0.03361344537815126,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 523136.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 2
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1510.03125,
      "epoch": 0.05042016806722689,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 9.990365154573716e-07,
      "loss": 0.0,
      "num_tokens": 778148.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 3
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1525.9296875,
      "epoch": 0.06722689075630252,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 9.961501876182148e-07,
      "loss": 0.0,
      "num_tokens": 1032547.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 4
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1469.1953125,
      "epoch": 0.08403361344537816,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 9.913533761814537e-07,
      "loss": 0.0,
      "num_tokens": 1278956.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 5
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1516.4375,
      "epoch": 0.10084033613445378,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 9.846666218300807e-07,
      "loss": 0.0,
      "num_tokens": 1532156.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 6
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1353.75,
      "epoch": 0.11764705882352941,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 9.761185582727976e-07,
      "loss": 0.0,
      "num_tokens": 1760652.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 7
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1524.59375,
      "epoch": 0.13445378151260504,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 9.657457896300791e-07,
      "loss": 0.0,
      "num_tokens": 2017904.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 8
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1266.0703125,
      "epoch": 0.15126050420168066,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 9.535927336897097e-07,
      "loss": 0.0,
      "num_tokens": 2233457.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 9
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1721.0390625,
      "epoch": 0.16806722689075632,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 9.397114317029974e-07,
      "loss": 0.0,
      "num_tokens": 2516198.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 10
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1270.0546875,
      "epoch": 0.18487394957983194,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 9.241613255361454e-07,
      "loss": 0.0,
      "num_tokens": 2734181.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 11
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1756.8515625,
      "epoch": 0.20168067226890757,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 9.070090031310558e-07,
      "loss": 0.0,
      "num_tokens": 3022002.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 12
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1439.25,
      "epoch": 0.2184873949579832,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 8.883279133655398e-07,
      "loss": 0.0,
      "num_tokens": 3265898.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 13
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1287.7109375,
      "epoch": 0.23529411764705882,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 8.681980515339463e-07,
      "loss": 0.0,
      "num_tokens": 3485349.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 14
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1291.4765625,
      "epoch": 0.25210084033613445,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 8.46705616795031e-07,
      "loss": 0.0,
      "num_tokens": 3709706.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 15
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1431.7890625,
      "epoch": 0.2689075630252101,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 8.239426430539243e-07,
      "loss": 0.0,
      "num_tokens": 3949471.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 16
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1147.71875,
      "epoch": 0.2857142857142857,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 8.00006604858821e-07,
      "loss": 0.0,
      "num_tokens": 4152771.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 17
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1743.6484375,
      "epoch": 0.3025210084033613,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 7.75e-07,
      "loss": 0.0,
      "num_tokens": 4439918.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 18
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1624.828125,
      "epoch": 0.31932773109243695,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 7.490299105985506e-07,
      "loss": 0.0,
      "num_tokens": 4708000.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 19
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1281.0859375,
      "epoch": 0.33613445378151263,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 7.222075445642904e-07,
      "loss": 0.0,
      "num_tokens": 4930731.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 20
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1734.984375,
      "epoch": 0.35294117647058826,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 6.946477593864227e-07,
      "loss": 0.0,
      "num_tokens": 5215121.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 21
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1469.5625,
      "epoch": 0.3697478991596639,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 6.664685702961344e-07,
      "loss": 0.0,
      "num_tokens": 5459289.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 22
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1616.2734375,
      "epoch": 0.3865546218487395,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 6.377906449072577e-07,
      "loss": 0.0,
      "num_tokens": 5727860.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 23
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1414.109375,
      "epoch": 0.40336134453781514,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 6.087367864990232e-07,
      "loss": 0.0,
      "num_tokens": 5971898.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 24
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1353.9296875,
      "epoch": 0.42016806722689076,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 5.794314081535644e-07,
      "loss": 0.0,
      "num_tokens": 6203001.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 25
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1247.484375,
      "epoch": 0.4369747899159664,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 5.5e-07,
      "loss": 0.0,
      "num_tokens": 6419583.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 26
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1523.859375,
      "epoch": 0.453781512605042,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 5.205685918464355e-07,
      "loss": 0.0,
      "num_tokens": 6674853.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 27
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1352.765625,
      "epoch": 0.47058823529411764,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 4.912632135009769e-07,
      "loss": 0.0,
      "num_tokens": 6904127.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 28
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1583.96875,
      "epoch": 0.48739495798319327,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 4.6220935509274227e-07,
      "loss": 0.0,
      "num_tokens": 7167227.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 29
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1578.2421875,
      "epoch": 0.5042016806722689,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 4.3353142970386557e-07,
      "loss": 0.0,
      "num_tokens": 7432202.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 30
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1786.71875,
      "epoch": 0.5210084033613446,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 4.053522406135774e-07,
      "loss": 0.0,
      "num_tokens": 7721798.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 31
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1568.609375,
      "epoch": 0.5378151260504201,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 3.777924554357096e-07,
      "loss": 0.0,
      "num_tokens": 7986012.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 32
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1542.75,
      "epoch": 0.5546218487394958,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 3.5097008940144955e-07,
      "loss": 0.0,
      "num_tokens": 8244964.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 33
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1326.6875,
      "epoch": 0.5714285714285714,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 3.250000000000001e-07,
      "loss": 0.0,
      "num_tokens": 8476132.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 34
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1582.921875,
      "epoch": 0.5882352941176471,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 2.999933951411791e-07,
      "loss": 0.0,
      "num_tokens": 8739482.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 35
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1426.2890625,
      "epoch": 0.6050420168067226,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 2.760573569460757e-07,
      "loss": 0.0,
      "num_tokens": 8981671.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 36
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1474.1796875,
      "epoch": 0.6218487394957983,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 2.53294383204969e-07,
      "loss": 0.0,
      "num_tokens": 9227398.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 37
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1203.25,
      "epoch": 0.6386554621848739,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 2.3180194846605364e-07,
      "loss": 0.0,
      "num_tokens": 9436654.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 38
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1524.3671875,
      "epoch": 0.6554621848739496,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 2.1167208663446022e-07,
      "loss": 0.0,
      "num_tokens": 9690789.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 39
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1663.359375,
      "epoch": 0.6722689075630253,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1.929909968689442e-07,
      "loss": 0.0,
      "num_tokens": 9964307.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 40
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1360.765625,
      "epoch": 0.6890756302521008,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1.758386744638546e-07,
      "loss": 0.0,
      "num_tokens": 10195365.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 41
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1217.7421875,
      "epoch": 0.7058823529411765,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1.6028856829700258e-07,
      "loss": 0.0,
      "num_tokens": 10409540.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 42
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1373.4375,
      "epoch": 0.7226890756302521,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1.464072663102903e-07,
      "loss": 0.0,
      "num_tokens": 10643324.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 43
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1329.703125,
      "epoch": 0.7394957983193278,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1.3425421036992097e-07,
      "loss": 0.0,
      "num_tokens": 10876006.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 44
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1481.7890625,
      "epoch": 0.7563025210084033,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1.238814417272025e-07,
      "loss": 0.0,
      "num_tokens": 11124203.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 45
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1337.3515625,
      "epoch": 0.773109243697479,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1.1533337816991931e-07,
      "loss": 0.0,
      "num_tokens": 11350872.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 46
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1556.4453125,
      "epoch": 0.7899159663865546,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1.086466238185463e-07,
      "loss": 0.0,
      "num_tokens": 11611593.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 47
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1598.1484375,
      "epoch": 0.8067226890756303,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1.0384981238178533e-07,
      "loss": 0.0,
      "num_tokens": 11876876.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 48
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1476.125,
      "epoch": 0.8235294117647058,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1.0096348454262843e-07,
      "loss": 0.0,
      "num_tokens": 12127164.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 49
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1574.3984375,
      "epoch": 0.8403361344537815,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1e-07,
      "loss": 0.0,
      "num_tokens": 12387831.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "step": 50
    },
    {
      "epoch": 0.8403361344537815,
      "step": 50,
      "total_flos": 0.0,
      "train_loss": 0.0,
      "train_runtime": 13359.4688,
      "train_samples_per_second": 0.479,
      "train_steps_per_second": 0.004
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": 8,
  "trial_name": null,
  "trial_params": null
}