{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 3301.4214477539062,
      "epoch": 0.02564102564102564,
      "grad_norm": 2.992680549621582,
      "kl": 0.0,
      "learning_rate": 0.0,
      "loss": 0.0,
      "reward": 0.1030658227391541,
      "reward_std": 0.20713394414633512,
      "rewards/code_reward": 0.1030658227391541,
      "rewards/format_reward": 0.0,
      "step": 1
    },
    {
      "completion_length": 3303.0679321289062,
      "epoch": 0.05128205128205128,
      "grad_norm": 1.2384196519851685,
      "kl": 0.0,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "reward": 0.09688444854691625,
      "reward_std": 0.16041716001927853,
      "rewards/code_reward": 0.0968844504095614,
      "rewards/format_reward": 0.0,
      "step": 2
    },
    {
      "completion_length": 3189.9893188476562,
      "epoch": 0.07692307692307693,
      "grad_norm": 10.27621841430664,
      "kl": 0.004179954528808594,
      "learning_rate": 1e-05,
      "loss": 0.0002,
      "reward": 0.10514286020770669,
      "reward_std": 0.2078455975279212,
      "rewards/code_reward": 0.10514286020770669,
      "rewards/format_reward": 0.0,
      "step": 3
    },
    {
      "completion_length": 3000.7999267578125,
      "epoch": 0.10256410256410256,
      "grad_norm": 2.5482373237609863,
      "kl": 0.0092010498046875,
      "learning_rate": 9.98378869844137e-06,
      "loss": 0.0004,
      "reward": 0.1636996939778328,
      "reward_std": 0.28437332436442375,
      "rewards/code_reward": 0.1636996977031231,
      "rewards/format_reward": 0.0,
      "step": 4
    },
    {
      "completion_length": 3725.6929321289062,
      "epoch": 0.1282051282051282,
      "grad_norm": 3.836555004119873,
      "kl": 0.0565185546875,
      "learning_rate": 9.935271596564688e-06,
      "loss": 0.0023,
      "reward": 0.1552258525043726,
      "reward_std": 0.20690688118338585,
      "rewards/code_reward": 0.1552258525043726,
      "rewards/format_reward": 0.0,
      "step": 5
    },
    {
      "completion_length": 3449.982177734375,
      "epoch": 0.15384615384615385,
      "grad_norm": 0.9245039224624634,
      "kl": 0.153564453125,
      "learning_rate": 9.854798261200746e-06,
      "loss": 0.0061,
      "reward": 0.20291369408369064,
      "reward_std": 0.2591838911175728,
      "rewards/code_reward": 0.20291369780898094,
      "rewards/format_reward": 0.0,
      "step": 6
    },
    {
      "completion_length": 2533.5928955078125,
      "epoch": 0.1794871794871795,
      "grad_norm": 4.267428874969482,
      "kl": 0.276611328125,
      "learning_rate": 9.74294850457488e-06,
      "loss": 0.0111,
      "reward": 0.09451580978929996,
      "reward_std": 0.19575391709804535,
      "rewards/code_reward": 0.09451580978929996,
      "rewards/format_reward": 0.0,
      "step": 7
    },
    {
      "completion_length": 3610.7678833007812,
      "epoch": 0.20512820512820512,
      "grad_norm": 0.9869590997695923,
      "kl": 0.216552734375,
      "learning_rate": 9.600528206746613e-06,
      "loss": 0.0087,
      "reward": 0.1328175999224186,
      "reward_std": 0.24701963737607002,
      "rewards/code_reward": 0.13246045634150505,
      "rewards/format_reward": 0.0035714285913854837,
      "step": 8
    },
    {
      "completion_length": 3664.2072143554688,
      "epoch": 0.23076923076923078,
      "grad_norm": 0.6975364685058594,
      "kl": 0.23388671875,
      "learning_rate": 9.428563509225348e-06,
      "loss": 0.0093,
      "reward": 0.123524846509099,
      "reward_std": 0.20174134522676468,
      "rewards/code_reward": 0.123524846509099,
      "rewards/format_reward": 0.0,
      "step": 9
    },
    {
      "completion_length": 3931.4750366210938,
      "epoch": 0.2564102564102564,
      "grad_norm": 0.7551573514938354,
      "kl": 0.20751953125,
      "learning_rate": 9.22829342159729e-06,
      "loss": 0.0083,
      "reward": 0.08102564234286547,
      "reward_std": 0.13897551037371159,
      "rewards/code_reward": 0.08102564420551062,
      "rewards/format_reward": 0.0,
      "step": 10
    },
    {
      "completion_length": 4086.3500366210938,
      "epoch": 0.28205128205128205,
      "grad_norm": 0.3929460942745209,
      "kl": 0.201171875,
      "learning_rate": 9.001160894432979e-06,
      "loss": 0.008,
      "reward": 0.06611721590161324,
      "reward_std": 0.1253935508430004,
      "rewards/code_reward": 0.06611721590161324,
      "rewards/format_reward": 0.0,
      "step": 11
    },
    {
      "completion_length": 4031.3786010742188,
      "epoch": 0.3076923076923077,
      "grad_norm": 0.3564222455024719,
      "kl": 0.208984375,
      "learning_rate": 8.748802422795361e-06,
      "loss": 0.0084,
      "reward": 0.09780338406562805,
      "reward_std": 0.15440805070102215,
      "rewards/code_reward": 0.09780338034033775,
      "rewards/format_reward": 0.0,
      "step": 12
    },
    {
      "completion_length": 4077.70361328125,
      "epoch": 0.3333333333333333,
      "grad_norm": 0.26154839992523193,
      "kl": 0.215576171875,
      "learning_rate": 8.473036255255368e-06,
      "loss": 0.0086,
      "reward": 0.07981190085411072,
      "reward_std": 0.1499769315123558,
      "rewards/code_reward": 0.07981190085411072,
      "rewards/format_reward": 0.0,
      "step": 13
    },
    {
      "completion_length": 3955.335693359375,
      "epoch": 0.358974358974359,
      "grad_norm": 0.2279486507177353,
      "kl": 0.22412109375,
      "learning_rate": 8.175849293369292e-06,
      "loss": 0.009,
      "reward": 0.08388392464257777,
      "reward_std": 0.12758804112672806,
      "rewards/code_reward": 0.08388392464257777,
      "rewards/format_reward": 0.0,
      "step": 14
    },
    {
      "completion_length": 3789.925048828125,
      "epoch": 0.38461538461538464,
      "grad_norm": 0.24723802506923676,
      "kl": 0.227294921875,
      "learning_rate": 7.859382776007544e-06,
      "loss": 0.0091,
      "reward": 0.11268522241152823,
      "reward_std": 0.18607539124786854,
      "rewards/code_reward": 0.11268522613681853,
      "rewards/format_reward": 0.0,
      "step": 15
    },
    {
      "completion_length": 3539.6714477539062,
      "epoch": 0.41025641025641024,
      "grad_norm": 0.2956843376159668,
      "kl": 0.248779296875,
      "learning_rate": 7.52591685167953e-06,
      "loss": 0.01,
      "reward": 0.2600744627416134,
      "reward_std": 0.21227671578526497,
      "rewards/code_reward": 0.2600744664669037,
      "rewards/format_reward": 0.0,
      "step": 16
    },
    {
      "completion_length": 3560.6357421875,
      "epoch": 0.4358974358974359,
      "grad_norm": 0.3600841164588928,
      "kl": 0.24560546875,
      "learning_rate": 7.1778541500113895e-06,
      "loss": 0.0098,
      "reward": 0.1853646468371153,
      "reward_std": 0.23910802975296974,
      "rewards/code_reward": 0.1853646282106638,
      "rewards/format_reward": 0.0,
      "step": 17
    },
    {
      "completion_length": 3478.9179077148438,
      "epoch": 0.46153846153846156,
      "grad_norm": 0.33355042338371277,
      "kl": 0.243896484375,
      "learning_rate": 6.817702470744477e-06,
      "loss": 0.0098,
      "reward": 0.1517396867275238,
      "reward_std": 0.1984270103275776,
      "rewards/code_reward": 0.15173968486487865,
      "rewards/format_reward": 0.0,
      "step": 18
    },
    {
      "completion_length": 3242.70361328125,
      "epoch": 0.48717948717948717,
      "grad_norm": 0.4373861849308014,
      "kl": 0.2568359375,
      "learning_rate": 6.448056714980768e-06,
      "loss": 0.0103,
      "reward": 0.25208037719130516,
      "reward_std": 0.2785281799733639,
      "rewards/code_reward": 0.25208036229014397,
      "rewards/format_reward": 0.0,
      "step": 19
    },
    {
      "completion_length": 3169.1214599609375,
      "epoch": 0.5128205128205128,
      "grad_norm": 0.44415220618247986,
      "kl": 0.2646484375,
      "learning_rate": 6.071580188860955e-06,
      "loss": 0.0106,
      "reward": 0.2603498362004757,
      "reward_std": 0.27874595671892166,
      "rewards/code_reward": 0.2603498287498951,
      "rewards/format_reward": 0.0,
      "step": 20
    },
    {
      "completion_length": 2705.0072021484375,
      "epoch": 0.5384615384615384,
      "grad_norm": 0.4169292151927948,
      "kl": 0.283203125,
      "learning_rate": 5.690985414382668e-06,
      "loss": 0.0113,
      "reward": 0.29475487023591995,
      "reward_std": 0.29297249019145966,
      "rewards/code_reward": 0.29475487396121025,
      "rewards/format_reward": 0.0,
      "step": 21
    },
    {
      "completion_length": 2707.617919921875,
      "epoch": 0.5641025641025641,
      "grad_norm": 3693.0712890625,
      "kl": 29.77001953125,
      "learning_rate": 5.309014585617335e-06,
      "loss": 1.1875,
      "reward": 0.2492063995450735,
      "reward_std": 0.25761475786566734,
      "rewards/code_reward": 0.2492063995450735,
      "rewards/format_reward": 0.0,
      "step": 22
    },
    {
      "completion_length": 2344.096466064453,
      "epoch": 0.5897435897435898,
      "grad_norm": 0.38532546162605286,
      "kl": 0.29150390625,
      "learning_rate": 4.928419811139046e-06,
      "loss": 0.0117,
      "reward": 0.35850388184189796,
      "reward_std": 0.2855670154094696,
      "rewards/code_reward": 0.35850388184189796,
      "rewards/format_reward": 0.0,
      "step": 23
    },
    {
      "completion_length": 2637.9856567382812,
      "epoch": 0.6153846153846154,
      "grad_norm": 0.5114049315452576,
      "kl": 0.326171875,
      "learning_rate": 4.551943285019233e-06,
      "loss": 0.013,
      "reward": 0.28699367493391037,
      "reward_std": 0.2507447600364685,
      "rewards/code_reward": 0.28699367120862007,
      "rewards/format_reward": 0.0,
      "step": 24
    },
    {
      "completion_length": 2756.8214721679688,
      "epoch": 0.6410256410256411,
      "grad_norm": 0.483265221118927,
      "kl": 0.357421875,
      "learning_rate": 4.182297529255525e-06,
      "loss": 0.0143,
      "reward": 0.22337647899985313,
      "reward_std": 0.2525235004723072,
      "rewards/code_reward": 0.22337647527456284,
      "rewards/format_reward": 0.0,
      "step": 25
    },
    {
      "completion_length": 2624.0642700195312,
      "epoch": 0.6666666666666666,
      "grad_norm": 0.44989556074142456,
      "kl": 0.36669921875,
      "learning_rate": 3.822145849988612e-06,
      "loss": 0.0147,
      "reward": 0.2586754858493805,
      "reward_std": 0.24251952394843102,
      "rewards/code_reward": 0.2586754783987999,
      "rewards/format_reward": 0.0,
      "step": 26
    },
    {
      "completion_length": 2454.8429260253906,
      "epoch": 0.6923076923076923,
      "grad_norm": 0.3866746425628662,
      "kl": 0.37109375,
      "learning_rate": 3.4740831483204696e-06,
      "loss": 0.0148,
      "reward": 0.2748478166759014,
      "reward_std": 0.21565091237425804,
      "rewards/code_reward": 0.2748478055000305,
      "rewards/format_reward": 0.0,
      "step": 27
    },
    {
      "completion_length": 2283.039306640625,
      "epoch": 0.717948717948718,
      "grad_norm": 0.34683477878570557,
      "kl": 0.36376953125,
      "learning_rate": 3.1406172239924583e-06,
      "loss": 0.0145,
      "reward": 0.40325161814689636,
      "reward_std": 0.29274996370077133,
      "rewards/code_reward": 0.40325161069631577,
      "rewards/format_reward": 0.0,
      "step": 28
    },
    {
      "completion_length": 2789.1107788085938,
      "epoch": 0.7435897435897436,
      "grad_norm": 0.6074942350387573,
      "kl": 0.45703125,
      "learning_rate": 2.8241507066307106e-06,
      "loss": 0.0183,
      "reward": 0.23605629801750183,
      "reward_std": 0.22556601464748383,
      "rewards/code_reward": 0.23605630174279213,
      "rewards/format_reward": 0.0,
      "step": 29
    },
    {
      "completion_length": 2618.4750366210938,
      "epoch": 0.7692307692307693,
      "grad_norm": 0.47094276547431946,
      "kl": 0.4296875,
      "learning_rate": 2.526963744744635e-06,
      "loss": 0.0172,
      "reward": 0.24552644789218903,
      "reward_std": 0.22016411647200584,
      "rewards/code_reward": 0.24552644416689873,
      "rewards/format_reward": 0.0,
      "step": 30
    },
    {
      "completion_length": 2504.3535766601562,
      "epoch": 0.7948717948717948,
      "grad_norm": 0.460906058549881,
      "kl": 0.390625,
      "learning_rate": 2.2511975772046403e-06,
      "loss": 0.0156,
      "reward": 0.2590152435004711,
      "reward_std": 0.24991632625460625,
      "rewards/code_reward": 0.2590152509510517,
      "rewards/format_reward": 0.0,
      "step": 31
    },
    {
      "completion_length": 2634.0321655273438,
      "epoch": 0.8205128205128205,
      "grad_norm": 0.3826371729373932,
      "kl": 0.4052734375,
      "learning_rate": 1.9988391055670234e-06,
      "loss": 0.0162,
      "reward": 0.2098755855113268,
      "reward_std": 0.16958633810281754,
      "rewards/code_reward": 0.2098755929619074,
      "rewards/format_reward": 0.0,
      "step": 32
    },
    {
      "completion_length": 2563.767822265625,
      "epoch": 0.8461538461538461,
      "grad_norm": 0.40869322419166565,
      "kl": 0.39990234375,
      "learning_rate": 1.771706578402711e-06,
      "loss": 0.016,
      "reward": 0.298298716545105,
      "reward_std": 0.29596007615327835,
      "rewards/code_reward": 0.29829873889684677,
      "rewards/format_reward": 0.0,
      "step": 33
    },
    {
      "completion_length": 2526.94287109375,
      "epoch": 0.8717948717948718,
      "grad_norm": 0.45944005250930786,
      "kl": 0.43359375,
      "learning_rate": 1.5714364907746535e-06,
      "loss": 0.0173,
      "reward": 0.2921798676252365,
      "reward_std": 0.18791194818913937,
      "rewards/code_reward": 0.2921798825263977,
      "rewards/format_reward": 0.0,
      "step": 34
    },
    {
      "completion_length": 2652.6107177734375,
      "epoch": 0.8974358974358975,
      "grad_norm": 0.42779994010925293,
      "kl": 0.44091796875,
      "learning_rate": 1.399471793253389e-06,
      "loss": 0.0176,
      "reward": 0.20903684198856354,
      "reward_std": 0.23266056552529335,
      "rewards/code_reward": 0.20903684571385384,
      "rewards/format_reward": 0.0,
      "step": 35
    },
    {
      "completion_length": 2777.0642700195312,
      "epoch": 0.9230769230769231,
      "grad_norm": 0.48290908336639404,
      "kl": 0.44189453125,
      "learning_rate": 1.257051495425121e-06,
      "loss": 0.0177,
      "reward": 0.07366262283176184,
      "reward_std": 0.12753414548933506,
      "rewards/code_reward": 0.07366262283176184,
      "rewards/format_reward": 0.0,
      "step": 36
    },
    {
      "completion_length": 2577.3999633789062,
      "epoch": 0.9487179487179487,
      "grad_norm": 0.41417568922042847,
      "kl": 0.43896484375,
      "learning_rate": 1.1452017387992552e-06,
      "loss": 0.0176,
      "reward": 0.12102217739447951,
      "reward_std": 0.10151251405477524,
      "rewards/code_reward": 0.12102217366918921,
      "rewards/format_reward": 0.0,
      "step": 37
    },
    {
      "completion_length": 2499.4678649902344,
      "epoch": 0.9743589743589743,
      "grad_norm": 0.3276176452636719,
      "kl": 0.4169921875,
      "learning_rate": 1.0647284034353122e-06,
      "loss": 0.0167,
      "reward": 0.16568297561025247,
      "reward_std": 0.10975269501795992,
      "rewards/code_reward": 0.16568297561025247,
      "rewards/format_reward": 0.0,
      "step": 38
    },
    {
      "completion_length": 2488.5069580078125,
      "epoch": 1.0,
      "grad_norm": 0.42517927289009094,
      "kl": 0.40771484375,
      "learning_rate": 1.0162113015586309e-06,
      "loss": 0.0163,
      "reward": 0.18103422969579697,
      "reward_std": 0.11617903341539204,
      "rewards/code_reward": 0.18103424459695816,
      "rewards/format_reward": 0.0,
      "step": 39
    },
    {
      "epoch": 1.0,
      "step": 39,
      "total_flos": 0.0,
      "train_loss": 0.04123398642398541,
      "train_runtime": 18693.2835,
      "train_samples_per_second": 0.058,
      "train_steps_per_second": 0.002
    }
  ],
  "logging_steps": 1,
  "max_steps": 39,
  "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": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}