{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 231,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 6.057079066807802,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.3733,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.12278221547603607,
      "step": 5,
      "valid_targets_mean": 3397.3,
      "valid_targets_min": 1727
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 1.9357682815309185,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.312,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.1016702950000763,
      "step": 10,
      "valid_targets_mean": 3230.0,
      "valid_targets_min": 1680
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.8312941460348809,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 0.2681,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.09491170942783356,
      "step": 15,
      "valid_targets_mean": 2857.5,
      "valid_targets_min": 1839
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.4158059347121491,
      "learning_rate": 3.1666666666666666e-05,
      "loss": 0.2136,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05754208192229271,
      "step": 20,
      "valid_targets_mean": 3214.3,
      "valid_targets_min": 1884
    },
    {
      "epoch": 0.7575757575757576,
      "grad_norm": 0.31278109144655264,
      "learning_rate": 4e-05,
      "loss": 0.1873,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06500861793756485,
      "step": 25,
      "valid_targets_mean": 4166.3,
      "valid_targets_min": 1993
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.2571670345543004,
      "learning_rate": 3.994244399375679e-05,
      "loss": 0.1678,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05598926544189453,
      "step": 30,
      "valid_targets_mean": 3023.3,
      "valid_targets_min": 1964
    },
    {
      "epoch": 1.0606060606060606,
      "grad_norm": 0.18211562027887052,
      "learning_rate": 3.977010724441261e-05,
      "loss": 0.154,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.04845510050654411,
      "step": 35,
      "valid_targets_mean": 4795.8,
      "valid_targets_min": 1751
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 0.1847599593737035,
      "learning_rate": 3.9483981653469586e-05,
      "loss": 0.1478,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.044909439980983734,
      "step": 40,
      "valid_targets_mean": 3843.7,
      "valid_targets_min": 1952
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.2095868038344813,
      "learning_rate": 3.908571404555758e-05,
      "loss": 0.1413,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05491482838988304,
      "step": 45,
      "valid_targets_mean": 4408.9,
      "valid_targets_min": 1981
    },
    {
      "epoch": 1.5151515151515151,
      "grad_norm": 0.1638929758946134,
      "learning_rate": 3.8577596689969346e-05,
      "loss": 0.1279,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.04170622676610947,
      "step": 50,
      "valid_targets_mean": 3393.7,
      "valid_targets_min": 1884
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.17488311510988763,
      "learning_rate": 3.7962554107273926e-05,
      "loss": 0.1353,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.04213090240955353,
      "step": 55,
      "valid_targets_mean": 4166.2,
      "valid_targets_min": 1919
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.16614643886860392,
      "learning_rate": 3.724412623694427e-05,
      "loss": 0.1222,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.04267009347677231,
      "step": 60,
      "valid_targets_mean": 3267.3,
      "valid_targets_min": 1836
    },
    {
      "epoch": 1.9696969696969697,
      "grad_norm": 0.18257612037274068,
      "learning_rate": 3.642644806287938e-05,
      "loss": 0.1232,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.04186457395553589,
      "step": 65,
      "valid_targets_mean": 3968.7,
      "valid_targets_min": 2080
    },
    {
      "epoch": 2.121212121212121,
      "grad_norm": 0.19648836279548257,
      "learning_rate": 3.55142258140884e-05,
      "loss": 0.1158,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.04170043393969536,
      "step": 70,
      "valid_targets_mean": 3565.9,
      "valid_targets_min": 1709
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 0.161248915765299,
      "learning_rate": 3.451270987751598e-05,
      "loss": 0.1118,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.033035580068826675,
      "step": 75,
      "valid_targets_mean": 4527.8,
      "valid_targets_min": 1786
    },
    {
      "epoch": 2.4242424242424243,
      "grad_norm": 0.17273322419326265,
      "learning_rate": 3.342766457891194e-05,
      "loss": 0.1109,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.04147561639547348,
      "step": 80,
      "valid_targets_mean": 4303.3,
      "valid_targets_min": 1802
    },
    {
      "epoch": 2.5757575757575757,
      "grad_norm": 0.21495077559714412,
      "learning_rate": 3.226533500567433e-05,
      "loss": 0.107,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.03459729626774788,
      "step": 85,
      "valid_targets_mean": 5005.4,
      "valid_targets_min": 1959
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.17330277599242455,
      "learning_rate": 3.1032411062620544e-05,
      "loss": 0.1065,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.03450329601764679,
      "step": 90,
      "valid_targets_mean": 3855.8,
      "valid_targets_min": 2000
    },
    {
      "epoch": 2.878787878787879,
      "grad_norm": 0.2058052432782279,
      "learning_rate": 2.973598896756697e-05,
      "loss": 0.1002,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.034510307013988495,
      "step": 95,
      "valid_targets_mean": 2783.3,
      "valid_targets_min": 1517
    },
    {
      "epoch": 3.0303030303030303,
      "grad_norm": 0.1831716887148403,
      "learning_rate": 2.8383530408333285e-05,
      "loss": 0.1045,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.034129731357097626,
      "step": 100,
      "valid_targets_mean": 4927.6,
      "valid_targets_min": 1839
    },
    {
      "epoch": 3.1818181818181817,
      "grad_norm": 0.2213504054767785,
      "learning_rate": 2.6982819596247373e-05,
      "loss": 0.0913,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.03140562027692795,
      "step": 105,
      "valid_targets_mean": 4125.8,
      "valid_targets_min": 1952
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.2357403108609295,
      "learning_rate": 2.554191846333378e-05,
      "loss": 0.0977,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.04095553234219551,
      "step": 110,
      "valid_targets_mean": 3955.2,
      "valid_targets_min": 1884
    },
    {
      "epoch": 3.484848484848485,
      "grad_norm": 0.21189842608787948,
      "learning_rate": 2.4069120261052682e-05,
      "loss": 0.0944,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.03247535228729248,
      "step": 115,
      "valid_targets_mean": 4148.2,
      "valid_targets_min": 1833
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.17986746292389105,
      "learning_rate": 2.2572901827656626e-05,
      "loss": 0.0941,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.028431307524442673,
      "step": 120,
      "valid_targets_mean": 3585.2,
      "valid_targets_min": 1838
    },
    {
      "epoch": 3.787878787878788,
      "grad_norm": 0.16969823562432254,
      "learning_rate": 2.1061874798894992e-05,
      "loss": 0.0887,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.029099609702825546,
      "step": 125,
      "valid_targets_mean": 4505.8,
      "valid_targets_min": 1839
    },
    {
      "epoch": 3.9393939393939394,
      "grad_norm": 0.1984359751489041,
      "learning_rate": 1.9544736042877886e-05,
      "loss": 0.0949,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.0295043233782053,
      "step": 130,
      "valid_targets_mean": 3523.4,
      "valid_targets_min": 1771
    },
    {
      "epoch": 4.090909090909091,
      "grad_norm": 0.20675052605469652,
      "learning_rate": 1.8030217604376628e-05,
      "loss": 0.0865,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.02581365406513214,
      "step": 135,
      "valid_targets_mean": 3747.0,
      "valid_targets_min": 1891
    },
    {
      "epoch": 4.242424242424242,
      "grad_norm": 0.20602993352135518,
      "learning_rate": 1.6527036446661396e-05,
      "loss": 0.0831,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.026312127709388733,
      "step": 140,
      "valid_targets_mean": 3792.3,
      "valid_targets_min": 1601
    },
    {
      "epoch": 4.393939393939394,
      "grad_norm": 0.35322379499269224,
      "learning_rate": 1.5043844280142005e-05,
      "loss": 0.0811,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.022907646372914314,
      "step": 145,
      "valid_targets_mean": 3479.7,
      "valid_targets_min": 1764
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 0.20717971378191377,
      "learning_rate": 1.358917776657806e-05,
      "loss": 0.0825,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.02863912098109722,
      "step": 150,
      "valid_targets_mean": 4172.6,
      "valid_targets_min": 1907
    },
    {
      "epoch": 4.696969696969697,
      "grad_norm": 0.21192392671392013,
      "learning_rate": 1.2171409385463218e-05,
      "loss": 0.0834,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.027893800288438797,
      "step": 155,
      "valid_targets_mean": 5243.5,
      "valid_targets_min": 2145
    },
    {
      "epoch": 4.848484848484849,
      "grad_norm": 0.183311922132141,
      "learning_rate": 1.0798699245376959e-05,
      "loss": 0.0802,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.02220100164413452,
      "step": 160,
      "valid_targets_mean": 4365.3,
      "valid_targets_min": 1802
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.2352242705791683,
      "learning_rate": 9.478948117658577e-06,
      "loss": 0.0866,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.0274435393512249,
      "step": 165,
      "valid_targets_mean": 2765.8,
      "valid_targets_min": 1918
    },
    {
      "epoch": 5.151515151515151,
      "grad_norm": 0.22402682073481225,
      "learning_rate": 8.219751962722726e-06,
      "loss": 0.0809,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.025124292820692062,
      "step": 170,
      "valid_targets_mean": 2667.7,
      "valid_targets_min": 1680
    },
    {
      "epoch": 5.303030303030303,
      "grad_norm": 0.2253066902214136,
      "learning_rate": 7.028358210744881e-06,
      "loss": 0.0749,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.02643812820315361,
      "step": 175,
      "valid_targets_mean": 3633.1,
      "valid_targets_min": 2001
    },
    {
      "epoch": 5.454545454545454,
      "grad_norm": 0.2122452461863688,
      "learning_rate": 5.911624048347757e-06,
      "loss": 0.077,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.025532612577080727,
      "step": 180,
      "valid_targets_mean": 3961.9,
      "valid_targets_min": 1904
    },
    {
      "epoch": 5.606060606060606,
      "grad_norm": 0.21672480103767722,
      "learning_rate": 4.875976951373633e-06,
      "loss": 0.0761,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.02824552357196808,
      "step": 185,
      "valid_targets_mean": 3794.2,
      "valid_targets_min": 1709
    },
    {
      "epoch": 5.757575757575758,
      "grad_norm": 0.21336791110807513,
      "learning_rate": 3.927377690900436e-06,
      "loss": 0.0786,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.023748915642499924,
      "step": 190,
      "valid_targets_mean": 2816.2,
      "valid_targets_min": 1931
    },
    {
      "epoch": 5.909090909090909,
      "grad_norm": 0.19971132204134792,
      "learning_rate": 3.071286025423983e-06,
      "loss": 0.0754,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.021909723058342934,
      "step": 195,
      "valid_targets_mean": 3034.3,
      "valid_targets_min": 1709
    },
    {
      "epoch": 6.0606060606060606,
      "grad_norm": 0.19967467647532736,
      "learning_rate": 2.312629276668554e-06,
      "loss": 0.0761,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.02368747815489769,
      "step": 200,
      "valid_targets_mean": 3495.7,
      "valid_targets_min": 1891
    },
    {
      "epoch": 6.212121212121212,
      "grad_norm": 0.21684418439150877,
      "learning_rate": 1.6557739698909436e-06,
      "loss": 0.0757,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.025541555136442184,
      "step": 205,
      "valid_targets_mean": 4154.6,
      "valid_targets_min": 1868
    },
    {
      "epoch": 6.363636363636363,
      "grad_norm": 0.24983119975734241,
      "learning_rate": 1.1045007019049182e-06,
      "loss": 0.0749,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.02706868201494217,
      "step": 210,
      "valid_targets_mean": 3688.0,
      "valid_targets_min": 2086
    },
    {
      "epoch": 6.515151515151516,
      "grad_norm": 0.21233551956379038,
      "learning_rate": 6.619823814758786e-07,
      "loss": 0.0746,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.023870835080742836,
      "step": 215,
      "valid_targets_mean": 4682.3,
      "valid_targets_min": 1914
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 0.19011857432739673,
      "learning_rate": 3.307659673251595e-07,
      "loss": 0.0733,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.027834340929985046,
      "step": 220,
      "valid_targets_mean": 4573.5,
      "valid_targets_min": 2055
    },
    {
      "epoch": 6.818181818181818,
      "grad_norm": 0.2113606209898585,
      "learning_rate": 1.1275780885282806e-07,
      "loss": 0.0763,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.021668311208486557,
      "step": 225,
      "valid_targets_mean": 3098.8,
      "valid_targets_min": 1838
    },
    {
      "epoch": 6.96969696969697,
      "grad_norm": 0.23339033147330146,
      "learning_rate": 9.212673951897177e-09,
      "loss": 0.0708,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.023356806486845016,
      "step": 230,
      "valid_targets_mean": 3134.9,
      "valid_targets_min": 1601
    },
    {
      "epoch": 7.0,
      "step": 231,
      "total_flos": 2.9757843152725606e+17,
      "train_loss": 0.0,
      "train_runtime": 1.1973,
      "train_samples_per_second": 18474.619,
      "train_steps_per_second": 192.931
    }
  ],
  "logging_steps": 5,
  "max_steps": 231,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 300,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.9757843152725606e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}