{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0380499405469679,
  "eval_steps": 500,
  "global_step": 110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 303.736328125,
      "epoch": 0.009512485136741973,
      "grad_norm": 6.413900149410157,
      "kl": 1.2040138244628906e-05,
      "learning_rate": 0.0,
      "loss": 0.0,
      "reward": 2.494140625,
      "reward_std": 0.48784760665148497,
      "rewards/accuracy_reward": 0.5234375,
      "rewards/format_reward": 0.966796875,
      "rewards/influence_reward": 0.439453125,
      "rewards/len_reward": 0.564453125,
      "step": 1
    },
    {
      "completion_length": 301.1767578125,
      "epoch": 0.04756242568370987,
      "grad_norm": 4.538431755996993,
      "kl": 0.0020136237144470215,
      "learning_rate": 1.818181818181818e-07,
      "loss": 0.0001,
      "reward": 2.59033203125,
      "reward_std": 0.43952864897437394,
      "rewards/accuracy_reward": 0.55126953125,
      "rewards/format_reward": 0.9775390625,
      "rewards/influence_reward": 0.4755859375,
      "rewards/len_reward": 0.5859375,
      "step": 5
    },
    {
      "completion_length": 301.173828125,
      "epoch": 0.09512485136741974,
      "grad_norm": 4.540110582735695,
      "kl": 0.009919834136962891,
      "learning_rate": 4.090909090909091e-07,
      "loss": 0.0004,
      "reward": 2.617578125,
      "reward_std": 0.4504364486783743,
      "rewards/accuracy_reward": 0.567578125,
      "rewards/format_reward": 0.98125,
      "rewards/influence_reward": 0.490625,
      "rewards/len_reward": 0.578125,
      "step": 10
    },
    {
      "completion_length": 309.38203125,
      "epoch": 0.1426872770511296,
      "grad_norm": 9.38796433749952,
      "kl": 0.31930999755859374,
      "learning_rate": 6.363636363636363e-07,
      "loss": 0.0128,
      "reward": 2.521875,
      "reward_std": 0.4318226620554924,
      "rewards/accuracy_reward": 0.54609375,
      "rewards/format_reward": 0.98515625,
      "rewards/influence_reward": 0.46171875,
      "rewards/len_reward": 0.52890625,
      "step": 15
    },
    {
      "completion_length": 304.08203125,
      "epoch": 0.1902497027348395,
      "grad_norm": 5.807979490306425,
      "kl": 1.21444091796875,
      "learning_rate": 8.636363636363636e-07,
      "loss": 0.0486,
      "reward": 2.5875,
      "reward_std": 0.4287548726424575,
      "rewards/accuracy_reward": 0.5609375,
      "rewards/format_reward": 0.988671875,
      "rewards/influence_reward": 0.492578125,
      "rewards/len_reward": 0.5453125,
      "step": 20
    },
    {
      "completion_length": 290.6125,
      "epoch": 0.23781212841854935,
      "grad_norm": 3.8640143749200977,
      "kl": 0.981396484375,
      "learning_rate": 9.99726628670463e-07,
      "loss": 0.0393,
      "reward": 2.65078125,
      "reward_std": 0.4463936248794198,
      "rewards/accuracy_reward": 0.587890625,
      "rewards/format_reward": 0.991796875,
      "rewards/influence_reward": 0.5046875,
      "rewards/len_reward": 0.56640625,
      "step": 25
    },
    {
      "completion_length": 277.168359375,
      "epoch": 0.2853745541022592,
      "grad_norm": 5.9327975012771335,
      "kl": 0.938134765625,
      "learning_rate": 9.966546331768192e-07,
      "loss": 0.0375,
      "reward": 2.69765625,
      "reward_std": 0.44224537797272206,
      "rewards/accuracy_reward": 0.6,
      "rewards/format_reward": 0.9953125,
      "rewards/influence_reward": 0.52421875,
      "rewards/len_reward": 0.578125,
      "step": 30
    },
    {
      "completion_length": 276.28984375,
      "epoch": 0.3329369797859691,
      "grad_norm": 2.7489316254164975,
      "kl": 0.70294189453125,
      "learning_rate": 9.901899829374047e-07,
      "loss": 0.0281,
      "reward": 2.692578125,
      "reward_std": 0.4814893426373601,
      "rewards/accuracy_reward": 0.56875,
      "rewards/format_reward": 0.991015625,
      "rewards/influence_reward": 0.490234375,
      "rewards/len_reward": 0.642578125,
      "step": 35
    },
    {
      "completion_length": 268.661328125,
      "epoch": 0.380499405469679,
      "grad_norm": 2.682655071546903,
      "kl": 0.676513671875,
      "learning_rate": 9.803768380684242e-07,
      "loss": 0.0271,
      "reward": 2.63125,
      "reward_std": 0.4533083649352193,
      "rewards/accuracy_reward": 0.546875,
      "rewards/format_reward": 0.98515625,
      "rewards/influence_reward": 0.471875,
      "rewards/len_reward": 0.62734375,
      "step": 40
    },
    {
      "completion_length": 268.608203125,
      "epoch": 0.4280618311533888,
      "grad_norm": 2.1083125911924,
      "kl": 0.7,
      "learning_rate": 9.672822322997304e-07,
      "loss": 0.028,
      "reward": 2.59765625,
      "reward_std": 0.45362772420048714,
      "rewards/accuracy_reward": 0.5359375,
      "rewards/format_reward": 0.9828125,
      "rewards/influence_reward": 0.462109375,
      "rewards/len_reward": 0.616796875,
      "step": 45
    },
    {
      "completion_length": 274.96875,
      "epoch": 0.4756242568370987,
      "grad_norm": 3.73008866914067,
      "kl": 0.75595703125,
      "learning_rate": 9.509956150664795e-07,
      "loss": 0.0302,
      "reward": 2.702734375,
      "reward_std": 0.45859763100743295,
      "rewards/accuracy_reward": 0.56640625,
      "rewards/format_reward": 0.98125,
      "rewards/influence_reward": 0.496484375,
      "rewards/len_reward": 0.65859375,
      "step": 50
    },
    {
      "completion_length": 265.771484375,
      "epoch": 0.5231866825208086,
      "grad_norm": 3.802630610023971,
      "kl": 0.813330078125,
      "learning_rate": 9.316282404787869e-07,
      "loss": 0.0325,
      "reward": 2.643359375,
      "reward_std": 0.4470154155045748,
      "rewards/accuracy_reward": 0.552734375,
      "rewards/format_reward": 0.972265625,
      "rewards/influence_reward": 0.471484375,
      "rewards/len_reward": 0.646875,
      "step": 55
    },
    {
      "completion_length": 266.3578125,
      "epoch": 0.5707491082045184,
      "grad_norm": 4.83224856477163,
      "kl": 0.7421142578125,
      "learning_rate": 9.093124073433462e-07,
      "loss": 0.0297,
      "reward": 2.6046875,
      "reward_std": 0.4854748765006661,
      "rewards/accuracy_reward": 0.5296875,
      "rewards/format_reward": 0.976953125,
      "rewards/influence_reward": 0.4609375,
      "rewards/len_reward": 0.637109375,
      "step": 60
    },
    {
      "completion_length": 275.097265625,
      "epoch": 0.6183115338882283,
      "grad_norm": 2.621315662268698,
      "kl": 3.4989013671875,
      "learning_rate": 8.842005554284295e-07,
      "loss": 0.1394,
      "reward": 2.628515625,
      "reward_std": 0.446920876391232,
      "rewards/accuracy_reward": 0.5578125,
      "rewards/format_reward": 0.9828125,
      "rewards/influence_reward": 0.478125,
      "rewards/len_reward": 0.609765625,
      "step": 65
    },
    {
      "completion_length": 277.68515625,
      "epoch": 0.6658739595719382,
      "grad_norm": 8.38339899136128,
      "kl": 1.1263671875,
      "learning_rate": 8.564642241456986e-07,
      "loss": 0.0451,
      "reward": 2.6890625,
      "reward_std": 0.4215613199397922,
      "rewards/accuracy_reward": 0.574609375,
      "rewards/format_reward": 0.988671875,
      "rewards/influence_reward": 0.511328125,
      "rewards/len_reward": 0.614453125,
      "step": 70
    },
    {
      "completion_length": 280.144140625,
      "epoch": 0.713436385255648,
      "grad_norm": 2.409653168135675,
      "kl": 1.0015869140625,
      "learning_rate": 8.262928807620843e-07,
      "loss": 0.0401,
      "reward": 2.652734375,
      "reward_std": 0.4218899512663484,
      "rewards/accuracy_reward": 0.571875,
      "rewards/format_reward": 0.993359375,
      "rewards/influence_reward": 0.5046875,
      "rewards/len_reward": 0.5828125,
      "step": 75
    },
    {
      "completion_length": 277.308203125,
      "epoch": 0.760998810939358,
      "grad_norm": 2.590566498907629,
      "kl": 0.793359375,
      "learning_rate": 7.938926261462365e-07,
      "loss": 0.0317,
      "reward": 2.6328125,
      "reward_std": 0.4484955586493015,
      "rewards/accuracy_reward": 0.557421875,
      "rewards/format_reward": 0.986328125,
      "rewards/influence_reward": 0.501953125,
      "rewards/len_reward": 0.587109375,
      "step": 80
    },
    {
      "completion_length": 291.658984375,
      "epoch": 0.8085612366230678,
      "grad_norm": 3.971963408922625,
      "kl": 1.0347900390625,
      "learning_rate": 7.594847868906076e-07,
      "loss": 0.0414,
      "reward": 2.640234375,
      "reward_std": 0.4194062201306224,
      "rewards/accuracy_reward": 0.54609375,
      "rewards/format_reward": 0.993359375,
      "rewards/influence_reward": 0.487890625,
      "rewards/len_reward": 0.612890625,
      "step": 85
    },
    {
      "completion_length": 291.239453125,
      "epoch": 0.8561236623067776,
      "grad_norm": 34.65140376012252,
      "kl": 0.8489990234375,
      "learning_rate": 7.233044034264033e-07,
      "loss": 0.034,
      "reward": 2.628125,
      "reward_std": 0.4221027422696352,
      "rewards/accuracy_reward": 0.563671875,
      "rewards/format_reward": 0.98671875,
      "rewards/influence_reward": 0.505078125,
      "rewards/len_reward": 0.57265625,
      "step": 90
    },
    {
      "completion_length": 299.859765625,
      "epoch": 0.9036860879904876,
      "grad_norm": 8.66190613014165,
      "kl": 2.2581787109375,
      "learning_rate": 6.855986244591103e-07,
      "loss": 0.0906,
      "reward": 2.66484375,
      "reward_std": 0.40759068857878444,
      "rewards/accuracy_reward": 0.580078125,
      "rewards/format_reward": 0.991015625,
      "rewards/influence_reward": 0.520703125,
      "rewards/len_reward": 0.573046875,
      "step": 95
    },
    {
      "completion_length": 292.805859375,
      "epoch": 0.9512485136741974,
      "grad_norm": 2.2808791606709584,
      "kl": 1.0470458984375,
      "learning_rate": 6.466250186922324e-07,
      "loss": 0.0419,
      "reward": 2.6,
      "reward_std": 0.4078312264755368,
      "rewards/accuracy_reward": 0.5515625,
      "rewards/format_reward": 0.992578125,
      "rewards/influence_reward": 0.493359375,
      "rewards/len_reward": 0.5625,
      "step": 100
    },
    {
      "completion_length": 292.933203125,
      "epoch": 0.9988109393579072,
      "grad_norm": 6.450288248580225,
      "kl": 0.9684326171875,
      "learning_rate": 6.066498153718734e-07,
      "loss": 0.0387,
      "reward": 2.588671875,
      "reward_std": 0.4406403709203005,
      "rewards/accuracy_reward": 0.538671875,
      "rewards/format_reward": 0.989453125,
      "rewards/influence_reward": 0.473828125,
      "rewards/len_reward": 0.58671875,
      "step": 105
    },
    {
      "completion_length": 285.20596590909093,
      "epoch": 1.0380499405469679,
      "grad_norm": 2.320328222243095,
      "kl": 0.9564393939393939,
      "learning_rate": 5.659460856710345e-07,
      "loss": 0.0377,
      "reward": 2.694128787878788,
      "reward_std": 0.41189532523805444,
      "rewards/accuracy_reward": 0.5814393939393939,
      "rewards/format_reward": 0.9947916666666666,
      "rewards/influence_reward": 0.5236742424242424,
      "rewards/len_reward": 0.5942234848484849,
      "step": 110
    }
  ],
  "logging_steps": 5,
  "max_steps": 212,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 10,
  "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
}