{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.315955766192733,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00105318588730911,
      "grad_norm": 1.3147555589675903,
      "learning_rate": 0.0,
      "loss": 13.5907,
      "num_input_tokens_seen": 2363056,
      "step": 1
    },
    {
      "epoch": 0.00210637177461822,
      "grad_norm": 1.1668343544006348,
      "learning_rate": 5e-06,
      "loss": 15.1869,
      "num_input_tokens_seen": 4914924,
      "step": 2
    },
    {
      "epoch": 0.00315955766192733,
      "grad_norm": 1.078931212425232,
      "learning_rate": 1e-05,
      "loss": 14.1278,
      "num_input_tokens_seen": 7350666,
      "step": 3
    },
    {
      "epoch": 0.00421274354923644,
      "grad_norm": 0.9630680084228516,
      "learning_rate": 1.5e-05,
      "loss": 14.4448,
      "num_input_tokens_seen": 9911760,
      "step": 4
    },
    {
      "epoch": 0.0052659294365455505,
      "grad_norm": 1.2464635372161865,
      "learning_rate": 2e-05,
      "loss": 14.539,
      "num_input_tokens_seen": 12460110,
      "step": 5
    },
    {
      "epoch": 0.00631911532385466,
      "grad_norm": 1.4388000965118408,
      "learning_rate": 2.5e-05,
      "loss": 14.9989,
      "num_input_tokens_seen": 14941884,
      "step": 6
    },
    {
      "epoch": 0.00737230121116377,
      "grad_norm": 0.9652966856956482,
      "learning_rate": 3e-05,
      "loss": 14.4027,
      "num_input_tokens_seen": 17514914,
      "step": 7
    },
    {
      "epoch": 0.00842548709847288,
      "grad_norm": 1.1013789176940918,
      "learning_rate": 3.5000000000000004e-05,
      "loss": 12.0805,
      "num_input_tokens_seen": 20142298,
      "step": 8
    },
    {
      "epoch": 0.009478672985781991,
      "grad_norm": 1.1957684755325317,
      "learning_rate": 4e-05,
      "loss": 13.4646,
      "num_input_tokens_seen": 22656144,
      "step": 9
    },
    {
      "epoch": 0.010531858873091101,
      "grad_norm": 1.1999417543411255,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 14.9708,
      "num_input_tokens_seen": 25175402,
      "step": 10
    },
    {
      "epoch": 0.01158504476040021,
      "grad_norm": 1.2181422710418701,
      "learning_rate": 5e-05,
      "loss": 12.8572,
      "num_input_tokens_seen": 27603302,
      "step": 11
    },
    {
      "epoch": 0.01263823064770932,
      "grad_norm": 1.1232861280441284,
      "learning_rate": 5.5e-05,
      "loss": 13.4139,
      "num_input_tokens_seen": 30063438,
      "step": 12
    },
    {
      "epoch": 0.01369141653501843,
      "grad_norm": 1.4094243049621582,
      "learning_rate": 6e-05,
      "loss": 13.6033,
      "num_input_tokens_seen": 32496926,
      "step": 13
    },
    {
      "epoch": 0.01474460242232754,
      "grad_norm": 1.1449795961380005,
      "learning_rate": 6.500000000000001e-05,
      "loss": 13.7514,
      "num_input_tokens_seen": 34824490,
      "step": 14
    },
    {
      "epoch": 0.01579778830963665,
      "grad_norm": 1.305707335472107,
      "learning_rate": 7.000000000000001e-05,
      "loss": 12.9037,
      "num_input_tokens_seen": 37474392,
      "step": 15
    },
    {
      "epoch": 0.01685097419694576,
      "grad_norm": 0.8636656403541565,
      "learning_rate": 7.5e-05,
      "loss": 14.264,
      "num_input_tokens_seen": 40079890,
      "step": 16
    },
    {
      "epoch": 0.01790416008425487,
      "grad_norm": 1.3949730396270752,
      "learning_rate": 8e-05,
      "loss": 14.129,
      "num_input_tokens_seen": 42483202,
      "step": 17
    },
    {
      "epoch": 0.018957345971563982,
      "grad_norm": 1.0275214910507202,
      "learning_rate": 8.5e-05,
      "loss": 14.9399,
      "num_input_tokens_seen": 44983536,
      "step": 18
    },
    {
      "epoch": 0.020010531858873092,
      "grad_norm": 1.1338497400283813,
      "learning_rate": 8.999999999999999e-05,
      "loss": 14.9256,
      "num_input_tokens_seen": 47556326,
      "step": 19
    },
    {
      "epoch": 0.021063717746182202,
      "grad_norm": 1.1364272832870483,
      "learning_rate": 9.5e-05,
      "loss": 14.2354,
      "num_input_tokens_seen": 49984930,
      "step": 20
    },
    {
      "epoch": 0.022116903633491312,
      "grad_norm": 1.0504145622253418,
      "learning_rate": 0.0001,
      "loss": 13.1098,
      "num_input_tokens_seen": 52475706,
      "step": 21
    },
    {
      "epoch": 0.02317008952080042,
      "grad_norm": 1.0692085027694702,
      "learning_rate": 0.000105,
      "loss": 13.6485,
      "num_input_tokens_seen": 54931676,
      "step": 22
    },
    {
      "epoch": 0.02422327540810953,
      "grad_norm": 1.125333309173584,
      "learning_rate": 0.00011,
      "loss": 12.9832,
      "num_input_tokens_seen": 57311266,
      "step": 23
    },
    {
      "epoch": 0.02527646129541864,
      "grad_norm": 1.2768787145614624,
      "learning_rate": 0.000115,
      "loss": 13.8192,
      "num_input_tokens_seen": 59782354,
      "step": 24
    },
    {
      "epoch": 0.02632964718272775,
      "grad_norm": 1.0284156799316406,
      "learning_rate": 0.00012,
      "loss": 14.8322,
      "num_input_tokens_seen": 62186446,
      "step": 25
    },
    {
      "epoch": 0.02738283307003686,
      "grad_norm": 1.0253136157989502,
      "learning_rate": 0.000125,
      "loss": 13.353,
      "num_input_tokens_seen": 64698904,
      "step": 26
    },
    {
      "epoch": 0.02843601895734597,
      "grad_norm": 1.2211846113204956,
      "learning_rate": 0.00013000000000000002,
      "loss": 13.8297,
      "num_input_tokens_seen": 67157778,
      "step": 27
    },
    {
      "epoch": 0.02948920484465508,
      "grad_norm": 1.8428621292114258,
      "learning_rate": 0.000135,
      "loss": 14.5567,
      "num_input_tokens_seen": 69536532,
      "step": 28
    },
    {
      "epoch": 0.030542390731964193,
      "grad_norm": 1.5557100772857666,
      "learning_rate": 0.00014000000000000001,
      "loss": 12.739,
      "num_input_tokens_seen": 72073830,
      "step": 29
    },
    {
      "epoch": 0.0315955766192733,
      "grad_norm": 1.0637712478637695,
      "learning_rate": 0.000145,
      "loss": 14.8383,
      "num_input_tokens_seen": 74649418,
      "step": 30
    },
    {
      "epoch": 0.03264876250658241,
      "grad_norm": 0.9268069863319397,
      "learning_rate": 0.00015,
      "loss": 14.7157,
      "num_input_tokens_seen": 77194468,
      "step": 31
    },
    {
      "epoch": 0.03370194839389152,
      "grad_norm": 1.081074595451355,
      "learning_rate": 0.000155,
      "loss": 14.3469,
      "num_input_tokens_seen": 79567360,
      "step": 32
    },
    {
      "epoch": 0.03475513428120063,
      "grad_norm": 1.1562591791152954,
      "learning_rate": 0.00016,
      "loss": 13.2922,
      "num_input_tokens_seen": 81976622,
      "step": 33
    },
    {
      "epoch": 0.03580832016850974,
      "grad_norm": 1.40042245388031,
      "learning_rate": 0.000165,
      "loss": 12.6052,
      "num_input_tokens_seen": 84456254,
      "step": 34
    },
    {
      "epoch": 0.03686150605581885,
      "grad_norm": 1.1846578121185303,
      "learning_rate": 0.00017,
      "loss": 14.8395,
      "num_input_tokens_seen": 86912082,
      "step": 35
    },
    {
      "epoch": 0.037914691943127965,
      "grad_norm": 1.1414552927017212,
      "learning_rate": 0.000175,
      "loss": 13.8918,
      "num_input_tokens_seen": 89296692,
      "step": 36
    },
    {
      "epoch": 0.03896787783043707,
      "grad_norm": 1.0319195985794067,
      "learning_rate": 0.00017999999999999998,
      "loss": 14.3268,
      "num_input_tokens_seen": 91786022,
      "step": 37
    },
    {
      "epoch": 0.040021063717746184,
      "grad_norm": 1.2396275997161865,
      "learning_rate": 0.000185,
      "loss": 13.6008,
      "num_input_tokens_seen": 94451030,
      "step": 38
    },
    {
      "epoch": 0.04107424960505529,
      "grad_norm": 0.9682689309120178,
      "learning_rate": 0.00019,
      "loss": 14.997,
      "num_input_tokens_seen": 96817518,
      "step": 39
    },
    {
      "epoch": 0.042127435492364404,
      "grad_norm": 0.8734373450279236,
      "learning_rate": 0.00019500000000000002,
      "loss": 13.0396,
      "num_input_tokens_seen": 99234416,
      "step": 40
    },
    {
      "epoch": 0.04318062137967351,
      "grad_norm": 1.5965349674224854,
      "learning_rate": 0.0002,
      "loss": 14.213,
      "num_input_tokens_seen": 101710538,
      "step": 41
    },
    {
      "epoch": 0.044233807266982623,
      "grad_norm": 1.6115487813949585,
      "learning_rate": 0.000205,
      "loss": 15.0594,
      "num_input_tokens_seen": 104066772,
      "step": 42
    },
    {
      "epoch": 0.04528699315429173,
      "grad_norm": 1.5525461435317993,
      "learning_rate": 0.00021,
      "loss": 14.3995,
      "num_input_tokens_seen": 106478524,
      "step": 43
    },
    {
      "epoch": 0.04634017904160084,
      "grad_norm": 1.5180985927581787,
      "learning_rate": 0.000215,
      "loss": 13.0277,
      "num_input_tokens_seen": 108918022,
      "step": 44
    },
    {
      "epoch": 0.04739336492890995,
      "grad_norm": 1.388283371925354,
      "learning_rate": 0.00022,
      "loss": 15.5197,
      "num_input_tokens_seen": 111331584,
      "step": 45
    },
    {
      "epoch": 0.04844655081621906,
      "grad_norm": 0.7749722003936768,
      "learning_rate": 0.00022500000000000002,
      "loss": 14.1346,
      "num_input_tokens_seen": 113804550,
      "step": 46
    },
    {
      "epoch": 0.049499736703528176,
      "grad_norm": 1.8673762083053589,
      "learning_rate": 0.00023,
      "loss": 15.5638,
      "num_input_tokens_seen": 116406598,
      "step": 47
    },
    {
      "epoch": 0.05055292259083728,
      "grad_norm": 1.6054580211639404,
      "learning_rate": 0.000235,
      "loss": 12.8775,
      "num_input_tokens_seen": 118834762,
      "step": 48
    },
    {
      "epoch": 0.051606108478146395,
      "grad_norm": 1.256948709487915,
      "learning_rate": 0.00024,
      "loss": 13.8707,
      "num_input_tokens_seen": 121241054,
      "step": 49
    },
    {
      "epoch": 0.0526592943654555,
      "grad_norm": 1.5192618370056152,
      "learning_rate": 0.000245,
      "loss": 12.771,
      "num_input_tokens_seen": 123714340,
      "step": 50
    },
    {
      "epoch": 0.053712480252764615,
      "grad_norm": 1.45964515209198,
      "learning_rate": 0.00025,
      "loss": 12.7207,
      "num_input_tokens_seen": 126399394,
      "step": 51
    },
    {
      "epoch": 0.05476566614007372,
      "grad_norm": 1.0744571685791016,
      "learning_rate": 0.000255,
      "loss": 14.2132,
      "num_input_tokens_seen": 128815712,
      "step": 52
    },
    {
      "epoch": 0.055818852027382834,
      "grad_norm": 0.9800078868865967,
      "learning_rate": 0.00026000000000000003,
      "loss": 12.3437,
      "num_input_tokens_seen": 131243982,
      "step": 53
    },
    {
      "epoch": 0.05687203791469194,
      "grad_norm": 1.7293643951416016,
      "learning_rate": 0.00026500000000000004,
      "loss": 15.0475,
      "num_input_tokens_seen": 133695752,
      "step": 54
    },
    {
      "epoch": 0.057925223802001054,
      "grad_norm": 1.134101152420044,
      "learning_rate": 0.00027,
      "loss": 15.3197,
      "num_input_tokens_seen": 136206586,
      "step": 55
    },
    {
      "epoch": 0.05897840968931016,
      "grad_norm": 1.7910157442092896,
      "learning_rate": 0.000275,
      "loss": 15.8412,
      "num_input_tokens_seen": 138588134,
      "step": 56
    },
    {
      "epoch": 0.06003159557661927,
      "grad_norm": 1.3835411071777344,
      "learning_rate": 0.00028000000000000003,
      "loss": 12.9363,
      "num_input_tokens_seen": 141117190,
      "step": 57
    },
    {
      "epoch": 0.061084781463928386,
      "grad_norm": 1.0232059955596924,
      "learning_rate": 0.000285,
      "loss": 15.1391,
      "num_input_tokens_seen": 143491738,
      "step": 58
    },
    {
      "epoch": 0.06213796735123749,
      "grad_norm": 1.1751936674118042,
      "learning_rate": 0.00029,
      "loss": 14.5678,
      "num_input_tokens_seen": 145991144,
      "step": 59
    },
    {
      "epoch": 0.0631911532385466,
      "grad_norm": 1.3430085182189941,
      "learning_rate": 0.000295,
      "loss": 13.1367,
      "num_input_tokens_seen": 148486356,
      "step": 60
    },
    {
      "epoch": 0.06424433912585571,
      "grad_norm": 1.3005839586257935,
      "learning_rate": 0.0003,
      "loss": 13.769,
      "num_input_tokens_seen": 150891696,
      "step": 61
    },
    {
      "epoch": 0.06529752501316483,
      "grad_norm": 2.0061893463134766,
      "learning_rate": 0.000305,
      "loss": 14.7883,
      "num_input_tokens_seen": 153414658,
      "step": 62
    },
    {
      "epoch": 0.06635071090047394,
      "grad_norm": 1.4493314027786255,
      "learning_rate": 0.00031,
      "loss": 12.5738,
      "num_input_tokens_seen": 155793700,
      "step": 63
    },
    {
      "epoch": 0.06740389678778304,
      "grad_norm": 1.2789517641067505,
      "learning_rate": 0.000315,
      "loss": 13.7151,
      "num_input_tokens_seen": 158248338,
      "step": 64
    },
    {
      "epoch": 0.06845708267509215,
      "grad_norm": 1.1854947805404663,
      "learning_rate": 0.00032,
      "loss": 13.5257,
      "num_input_tokens_seen": 160737224,
      "step": 65
    },
    {
      "epoch": 0.06951026856240126,
      "grad_norm": 0.983009934425354,
      "learning_rate": 0.00032500000000000004,
      "loss": 13.5613,
      "num_input_tokens_seen": 163317772,
      "step": 66
    },
    {
      "epoch": 0.07056345444971038,
      "grad_norm": 1.1745814085006714,
      "learning_rate": 0.00033,
      "loss": 14.2875,
      "num_input_tokens_seen": 165797524,
      "step": 67
    },
    {
      "epoch": 0.07161664033701948,
      "grad_norm": 1.0742534399032593,
      "learning_rate": 0.000335,
      "loss": 13.1399,
      "num_input_tokens_seen": 168202674,
      "step": 68
    },
    {
      "epoch": 0.07266982622432859,
      "grad_norm": 1.2481011152267456,
      "learning_rate": 0.00034,
      "loss": 12.9279,
      "num_input_tokens_seen": 170618878,
      "step": 69
    },
    {
      "epoch": 0.0737230121116377,
      "grad_norm": 1.4287097454071045,
      "learning_rate": 0.000345,
      "loss": 12.6019,
      "num_input_tokens_seen": 173023976,
      "step": 70
    },
    {
      "epoch": 0.07477619799894682,
      "grad_norm": 0.9344131350517273,
      "learning_rate": 0.00035,
      "loss": 14.5578,
      "num_input_tokens_seen": 175423500,
      "step": 71
    },
    {
      "epoch": 0.07582938388625593,
      "grad_norm": 1.383571982383728,
      "learning_rate": 0.000355,
      "loss": 12.3683,
      "num_input_tokens_seen": 177865696,
      "step": 72
    },
    {
      "epoch": 0.07688256977356503,
      "grad_norm": 1.5278881788253784,
      "learning_rate": 0.00035999999999999997,
      "loss": 13.7148,
      "num_input_tokens_seen": 180215372,
      "step": 73
    },
    {
      "epoch": 0.07793575566087414,
      "grad_norm": 0.9833160042762756,
      "learning_rate": 0.000365,
      "loss": 13.9058,
      "num_input_tokens_seen": 182660290,
      "step": 74
    },
    {
      "epoch": 0.07898894154818326,
      "grad_norm": 1.1421438455581665,
      "learning_rate": 0.00037,
      "loss": 14.5135,
      "num_input_tokens_seen": 185180996,
      "step": 75
    },
    {
      "epoch": 0.08004212743549237,
      "grad_norm": 1.5786970853805542,
      "learning_rate": 0.000375,
      "loss": 12.5171,
      "num_input_tokens_seen": 187704644,
      "step": 76
    },
    {
      "epoch": 0.08109531332280147,
      "grad_norm": 1.9583278894424438,
      "learning_rate": 0.00038,
      "loss": 13.6645,
      "num_input_tokens_seen": 190082764,
      "step": 77
    },
    {
      "epoch": 0.08214849921011058,
      "grad_norm": 2.4497997760772705,
      "learning_rate": 0.00038500000000000003,
      "loss": 14.2632,
      "num_input_tokens_seen": 192368804,
      "step": 78
    },
    {
      "epoch": 0.0832016850974197,
      "grad_norm": 1.5003597736358643,
      "learning_rate": 0.00039000000000000005,
      "loss": 13.2001,
      "num_input_tokens_seen": 194857438,
      "step": 79
    },
    {
      "epoch": 0.08425487098472881,
      "grad_norm": 1.39485502243042,
      "learning_rate": 0.000395,
      "loss": 13.5808,
      "num_input_tokens_seen": 197152948,
      "step": 80
    },
    {
      "epoch": 0.08530805687203792,
      "grad_norm": 1.288568139076233,
      "learning_rate": 0.0004,
      "loss": 13.7794,
      "num_input_tokens_seen": 199500708,
      "step": 81
    },
    {
      "epoch": 0.08636124275934702,
      "grad_norm": 1.300167202949524,
      "learning_rate": 0.00040500000000000003,
      "loss": 12.8507,
      "num_input_tokens_seen": 201991874,
      "step": 82
    },
    {
      "epoch": 0.08741442864665613,
      "grad_norm": 0.8545141816139221,
      "learning_rate": 0.00041,
      "loss": 14.328,
      "num_input_tokens_seen": 204251674,
      "step": 83
    },
    {
      "epoch": 0.08846761453396525,
      "grad_norm": 1.0194705724716187,
      "learning_rate": 0.000415,
      "loss": 13.6767,
      "num_input_tokens_seen": 206656880,
      "step": 84
    },
    {
      "epoch": 0.08952080042127436,
      "grad_norm": 0.9372128844261169,
      "learning_rate": 0.00042,
      "loss": 14.5693,
      "num_input_tokens_seen": 208918254,
      "step": 85
    },
    {
      "epoch": 0.09057398630858346,
      "grad_norm": 1.2995604276657104,
      "learning_rate": 0.000425,
      "loss": 13.5958,
      "num_input_tokens_seen": 211434142,
      "step": 86
    },
    {
      "epoch": 0.09162717219589257,
      "grad_norm": 1.2741903066635132,
      "learning_rate": 0.00043,
      "loss": 13.8848,
      "num_input_tokens_seen": 214000898,
      "step": 87
    },
    {
      "epoch": 0.09268035808320169,
      "grad_norm": 2.0325863361358643,
      "learning_rate": 0.000435,
      "loss": 13.8518,
      "num_input_tokens_seen": 216309292,
      "step": 88
    },
    {
      "epoch": 0.0937335439705108,
      "grad_norm": 1.449713110923767,
      "learning_rate": 0.00044,
      "loss": 13.7997,
      "num_input_tokens_seen": 218756170,
      "step": 89
    },
    {
      "epoch": 0.0947867298578199,
      "grad_norm": 1.5175477266311646,
      "learning_rate": 0.00044500000000000003,
      "loss": 13.5718,
      "num_input_tokens_seen": 221193636,
      "step": 90
    },
    {
      "epoch": 0.09583991574512901,
      "grad_norm": 1.2801398038864136,
      "learning_rate": 0.00045000000000000004,
      "loss": 14.4654,
      "num_input_tokens_seen": 223524870,
      "step": 91
    },
    {
      "epoch": 0.09689310163243813,
      "grad_norm": 1.0959213972091675,
      "learning_rate": 0.000455,
      "loss": 11.545,
      "num_input_tokens_seen": 226066666,
      "step": 92
    },
    {
      "epoch": 0.09794628751974724,
      "grad_norm": 1.1696399450302124,
      "learning_rate": 0.00046,
      "loss": 13.3462,
      "num_input_tokens_seen": 228525260,
      "step": 93
    },
    {
      "epoch": 0.09899947340705635,
      "grad_norm": 1.1905299425125122,
      "learning_rate": 0.000465,
      "loss": 13.4698,
      "num_input_tokens_seen": 231156516,
      "step": 94
    },
    {
      "epoch": 0.10005265929436545,
      "grad_norm": 0.9483806490898132,
      "learning_rate": 0.00047,
      "loss": 14.8114,
      "num_input_tokens_seen": 233846560,
      "step": 95
    },
    {
      "epoch": 0.10110584518167456,
      "grad_norm": 1.5830718278884888,
      "learning_rate": 0.000475,
      "loss": 12.9401,
      "num_input_tokens_seen": 236170696,
      "step": 96
    },
    {
      "epoch": 0.10215903106898368,
      "grad_norm": 1.66010582447052,
      "learning_rate": 0.00048,
      "loss": 13.3604,
      "num_input_tokens_seen": 238549390,
      "step": 97
    },
    {
      "epoch": 0.10321221695629279,
      "grad_norm": 1.1955476999282837,
      "learning_rate": 0.00048499999999999997,
      "loss": 14.7142,
      "num_input_tokens_seen": 240990068,
      "step": 98
    },
    {
      "epoch": 0.10426540284360189,
      "grad_norm": 1.2605278491973877,
      "learning_rate": 0.00049,
      "loss": 13.8786,
      "num_input_tokens_seen": 243394892,
      "step": 99
    },
    {
      "epoch": 0.105318588730911,
      "grad_norm": 1.1509404182434082,
      "learning_rate": 0.000495,
      "loss": 12.2201,
      "num_input_tokens_seen": 245927990,
      "step": 100
    },
    {
      "epoch": 0.10637177461822012,
      "grad_norm": 1.566206693649292,
      "learning_rate": 0.0005,
      "loss": 10.9783,
      "num_input_tokens_seen": 248369144,
      "step": 101
    },
    {
      "epoch": 0.10742496050552923,
      "grad_norm": 1.2243906259536743,
      "learning_rate": 0.0004999922894119685,
      "loss": 13.9885,
      "num_input_tokens_seen": 250819650,
      "step": 102
    },
    {
      "epoch": 0.10847814639283834,
      "grad_norm": 0.7832080125808716,
      "learning_rate": 0.0004999691581234994,
      "loss": 15.5307,
      "num_input_tokens_seen": 253219186,
      "step": 103
    },
    {
      "epoch": 0.10953133228014744,
      "grad_norm": 0.8975496888160706,
      "learning_rate": 0.0004999306075614394,
      "loss": 15.138,
      "num_input_tokens_seen": 255671766,
      "step": 104
    },
    {
      "epoch": 0.11058451816745656,
      "grad_norm": 0.9028383493423462,
      "learning_rate": 0.0004998766401037688,
      "loss": 14.13,
      "num_input_tokens_seen": 258276528,
      "step": 105
    },
    {
      "epoch": 0.11163770405476567,
      "grad_norm": 1.4537795782089233,
      "learning_rate": 0.0004998072590794548,
      "loss": 13.9269,
      "num_input_tokens_seen": 260625306,
      "step": 106
    },
    {
      "epoch": 0.11269088994207478,
      "grad_norm": 0.916918158531189,
      "learning_rate": 0.0004997224687682457,
      "loss": 13.1447,
      "num_input_tokens_seen": 263021648,
      "step": 107
    },
    {
      "epoch": 0.11374407582938388,
      "grad_norm": 1.0510584115982056,
      "learning_rate": 0.000499622274400407,
      "loss": 14.1054,
      "num_input_tokens_seen": 265467338,
      "step": 108
    },
    {
      "epoch": 0.114797261716693,
      "grad_norm": 0.8123775720596313,
      "learning_rate": 0.0004995066821563998,
      "loss": 14.0404,
      "num_input_tokens_seen": 267981590,
      "step": 109
    },
    {
      "epoch": 0.11585044760400211,
      "grad_norm": 1.1095675230026245,
      "learning_rate": 0.0004993756991664976,
      "loss": 12.6619,
      "num_input_tokens_seen": 270308658,
      "step": 110
    },
    {
      "epoch": 0.11690363349131122,
      "grad_norm": 0.9915770888328552,
      "learning_rate": 0.0004992293335103487,
      "loss": 13.9319,
      "num_input_tokens_seen": 272795368,
      "step": 111
    },
    {
      "epoch": 0.11795681937862032,
      "grad_norm": 1.075748324394226,
      "learning_rate": 0.0004990675942164759,
      "loss": 14.3729,
      "num_input_tokens_seen": 275169288,
      "step": 112
    },
    {
      "epoch": 0.11901000526592943,
      "grad_norm": 0.8833720684051514,
      "learning_rate": 0.0004988904912617209,
      "loss": 15.3386,
      "num_input_tokens_seen": 277598550,
      "step": 113
    },
    {
      "epoch": 0.12006319115323855,
      "grad_norm": 0.6812732815742493,
      "learning_rate": 0.000498698035570628,
      "loss": 14.4552,
      "num_input_tokens_seen": 280073876,
      "step": 114
    },
    {
      "epoch": 0.12111637704054766,
      "grad_norm": 1.2348415851593018,
      "learning_rate": 0.0004984902390147711,
      "loss": 13.8133,
      "num_input_tokens_seen": 282587368,
      "step": 115
    },
    {
      "epoch": 0.12216956292785677,
      "grad_norm": 1.1452962160110474,
      "learning_rate": 0.0004982671144120202,
      "loss": 13.8322,
      "num_input_tokens_seen": 285113802,
      "step": 116
    },
    {
      "epoch": 0.12322274881516587,
      "grad_norm": 1.5170722007751465,
      "learning_rate": 0.000498028675525752,
      "loss": 11.1536,
      "num_input_tokens_seen": 287411358,
      "step": 117
    },
    {
      "epoch": 0.12427593470247499,
      "grad_norm": 1.1934428215026855,
      "learning_rate": 0.000497774937064,
      "loss": 12.9464,
      "num_input_tokens_seen": 289841892,
      "step": 118
    },
    {
      "epoch": 0.1253291205897841,
      "grad_norm": 1.2093623876571655,
      "learning_rate": 0.0004975059146785479,
      "loss": 12.8343,
      "num_input_tokens_seen": 292269164,
      "step": 119
    },
    {
      "epoch": 0.1263823064770932,
      "grad_norm": 0.9261972308158875,
      "learning_rate": 0.0004972216249639638,
      "loss": 14.9848,
      "num_input_tokens_seen": 294553234,
      "step": 120
    },
    {
      "epoch": 0.12743549236440233,
      "grad_norm": 0.9841050505638123,
      "learning_rate": 0.000496922085456576,
      "loss": 13.9842,
      "num_input_tokens_seen": 297047120,
      "step": 121
    },
    {
      "epoch": 0.12848867825171142,
      "grad_norm": 1.0842055082321167,
      "learning_rate": 0.0004966073146333924,
      "loss": 12.092,
      "num_input_tokens_seen": 299619262,
      "step": 122
    },
    {
      "epoch": 0.12954186413902052,
      "grad_norm": 0.7394796013832092,
      "learning_rate": 0.0004962773319109604,
      "loss": 13.4262,
      "num_input_tokens_seen": 302193484,
      "step": 123
    },
    {
      "epoch": 0.13059505002632965,
      "grad_norm": 0.9171662330627441,
      "learning_rate": 0.0004959321576441683,
      "loss": 14.5414,
      "num_input_tokens_seen": 304771644,
      "step": 124
    },
    {
      "epoch": 0.13164823591363875,
      "grad_norm": 0.8625826239585876,
      "learning_rate": 0.0004955718131249909,
      "loss": 14.7163,
      "num_input_tokens_seen": 307154770,
      "step": 125
    },
    {
      "epoch": 0.13270142180094788,
      "grad_norm": 1.2097444534301758,
      "learning_rate": 0.0004951963205811756,
      "loss": 13.6051,
      "num_input_tokens_seen": 309623990,
      "step": 126
    },
    {
      "epoch": 0.13375460768825698,
      "grad_norm": 0.9684086441993713,
      "learning_rate": 0.0004948057031748712,
      "loss": 12.3401,
      "num_input_tokens_seen": 312189822,
      "step": 127
    },
    {
      "epoch": 0.13480779357556608,
      "grad_norm": 0.7330049872398376,
      "learning_rate": 0.0004943999850011993,
      "loss": 13.428,
      "num_input_tokens_seen": 314481274,
      "step": 128
    },
    {
      "epoch": 0.1358609794628752,
      "grad_norm": 0.8198027014732361,
      "learning_rate": 0.0004939791910867678,
      "loss": 13.366,
      "num_input_tokens_seen": 316975100,
      "step": 129
    },
    {
      "epoch": 0.1369141653501843,
      "grad_norm": 0.7812517285346985,
      "learning_rate": 0.0004935433473881276,
      "loss": 14.3236,
      "num_input_tokens_seen": 319629918,
      "step": 130
    },
    {
      "epoch": 0.13796735123749343,
      "grad_norm": 0.9930380582809448,
      "learning_rate": 0.0004930924807901711,
      "loss": 11.7665,
      "num_input_tokens_seen": 322045726,
      "step": 131
    },
    {
      "epoch": 0.13902053712480253,
      "grad_norm": 1.002437949180603,
      "learning_rate": 0.0004926266191044738,
      "loss": 13.4716,
      "num_input_tokens_seen": 324422858,
      "step": 132
    },
    {
      "epoch": 0.14007372301211163,
      "grad_norm": 0.9191110134124756,
      "learning_rate": 0.0004921457910675788,
      "loss": 13.1584,
      "num_input_tokens_seen": 326675990,
      "step": 133
    },
    {
      "epoch": 0.14112690889942076,
      "grad_norm": 0.9338858723640442,
      "learning_rate": 0.0004916500263392243,
      "loss": 13.192,
      "num_input_tokens_seen": 329185696,
      "step": 134
    },
    {
      "epoch": 0.14218009478672985,
      "grad_norm": 0.7161638140678406,
      "learning_rate": 0.000491139355500514,
      "loss": 13.9349,
      "num_input_tokens_seen": 331756854,
      "step": 135
    },
    {
      "epoch": 0.14323328067403895,
      "grad_norm": 0.8185762166976929,
      "learning_rate": 0.0004906138100520309,
      "loss": 12.6261,
      "num_input_tokens_seen": 334321854,
      "step": 136
    },
    {
      "epoch": 0.14428646656134808,
      "grad_norm": 0.6805868744850159,
      "learning_rate": 0.0004900734224118936,
      "loss": 14.4888,
      "num_input_tokens_seen": 336876626,
      "step": 137
    },
    {
      "epoch": 0.14533965244865718,
      "grad_norm": 0.9425003528594971,
      "learning_rate": 0.0004895182259137573,
      "loss": 12.113,
      "num_input_tokens_seen": 339348464,
      "step": 138
    },
    {
      "epoch": 0.1463928383359663,
      "grad_norm": 0.8056529760360718,
      "learning_rate": 0.0004889482548047572,
      "loss": 14.649,
      "num_input_tokens_seen": 341823736,
      "step": 139
    },
    {
      "epoch": 0.1474460242232754,
      "grad_norm": 0.7355366945266724,
      "learning_rate": 0.0004883635442433959,
      "loss": 12.0118,
      "num_input_tokens_seen": 344380626,
      "step": 140
    },
    {
      "epoch": 0.1484992101105845,
      "grad_norm": 0.8561354279518127,
      "learning_rate": 0.0004877641302973755,
      "loss": 15.144,
      "num_input_tokens_seen": 346692052,
      "step": 141
    },
    {
      "epoch": 0.14955239599789363,
      "grad_norm": 0.9879862666130066,
      "learning_rate": 0.00048715004994137124,
      "loss": 14.6901,
      "num_input_tokens_seen": 349112532,
      "step": 142
    },
    {
      "epoch": 0.15060558188520273,
      "grad_norm": 0.9572948217391968,
      "learning_rate": 0.0004865213410547524,
      "loss": 14.3239,
      "num_input_tokens_seen": 351452022,
      "step": 143
    },
    {
      "epoch": 0.15165876777251186,
      "grad_norm": 0.8329271078109741,
      "learning_rate": 0.0004858780424192443,
      "loss": 12.3414,
      "num_input_tokens_seen": 353797086,
      "step": 144
    },
    {
      "epoch": 0.15271195365982096,
      "grad_norm": 0.7736046314239502,
      "learning_rate": 0.0004852201937165372,
      "loss": 13.5231,
      "num_input_tokens_seen": 356162002,
      "step": 145
    },
    {
      "epoch": 0.15376513954713006,
      "grad_norm": 0.7838310599327087,
      "learning_rate": 0.0004845478355258377,
      "loss": 14.2139,
      "num_input_tokens_seen": 358794470,
      "step": 146
    },
    {
      "epoch": 0.15481832543443919,
      "grad_norm": 0.6623799204826355,
      "learning_rate": 0.00048386100932136614,
      "loss": 14.1852,
      "num_input_tokens_seen": 361060330,
      "step": 147
    },
    {
      "epoch": 0.15587151132174829,
      "grad_norm": 0.8017021417617798,
      "learning_rate": 0.00048315975746979797,
      "loss": 12.8818,
      "num_input_tokens_seen": 363503210,
      "step": 148
    },
    {
      "epoch": 0.1569246972090574,
      "grad_norm": 0.6893861889839172,
      "learning_rate": 0.0004824441232276507,
      "loss": 13.4499,
      "num_input_tokens_seen": 365979336,
      "step": 149
    },
    {
      "epoch": 0.1579778830963665,
      "grad_norm": 0.9454759955406189,
      "learning_rate": 0.0004817141507386153,
      "loss": 13.5658,
      "num_input_tokens_seen": 368459936,
      "step": 150
    },
    {
      "epoch": 0.1590310689836756,
      "grad_norm": 0.6542503237724304,
      "learning_rate": 0.0004809698850308334,
      "loss": 12.5393,
      "num_input_tokens_seen": 370972514,
      "step": 151
    },
    {
      "epoch": 0.16008425487098474,
      "grad_norm": 0.7843099236488342,
      "learning_rate": 0.0004802113720141196,
      "loss": 13.8876,
      "num_input_tokens_seen": 373538886,
      "step": 152
    },
    {
      "epoch": 0.16113744075829384,
      "grad_norm": 0.681400716304779,
      "learning_rate": 0.00047943865847712965,
      "loss": 12.6614,
      "num_input_tokens_seen": 375997348,
      "step": 153
    },
    {
      "epoch": 0.16219062664560294,
      "grad_norm": 0.6228338479995728,
      "learning_rate": 0.0004786517920844744,
      "loss": 14.8045,
      "num_input_tokens_seen": 378368452,
      "step": 154
    },
    {
      "epoch": 0.16324381253291206,
      "grad_norm": 0.696509599685669,
      "learning_rate": 0.00047785082137377936,
      "loss": 14.3078,
      "num_input_tokens_seen": 380908798,
      "step": 155
    },
    {
      "epoch": 0.16429699842022116,
      "grad_norm": 0.746185839176178,
      "learning_rate": 0.000477035795752691,
      "loss": 14.4622,
      "num_input_tokens_seen": 383363952,
      "step": 156
    },
    {
      "epoch": 0.1653501843075303,
      "grad_norm": 0.8552024364471436,
      "learning_rate": 0.0004762067654958286,
      "loss": 13.1467,
      "num_input_tokens_seen": 385820504,
      "step": 157
    },
    {
      "epoch": 0.1664033701948394,
      "grad_norm": 0.7352308034896851,
      "learning_rate": 0.0004753637817416835,
      "loss": 14.5263,
      "num_input_tokens_seen": 388280752,
      "step": 158
    },
    {
      "epoch": 0.1674565560821485,
      "grad_norm": 0.624199628829956,
      "learning_rate": 0.0004745068964894645,
      "loss": 14.1771,
      "num_input_tokens_seen": 390877896,
      "step": 159
    },
    {
      "epoch": 0.16850974196945762,
      "grad_norm": 0.7346677184104919,
      "learning_rate": 0.00047363616259589025,
      "loss": 14.1435,
      "num_input_tokens_seen": 393477216,
      "step": 160
    },
    {
      "epoch": 0.16956292785676672,
      "grad_norm": 0.500455915927887,
      "learning_rate": 0.00047275163377192886,
      "loss": 11.8482,
      "num_input_tokens_seen": 396021712,
      "step": 161
    },
    {
      "epoch": 0.17061611374407584,
      "grad_norm": 0.7637024521827698,
      "learning_rate": 0.0004718533645794847,
      "loss": 12.7018,
      "num_input_tokens_seen": 398528988,
      "step": 162
    },
    {
      "epoch": 0.17166929963138494,
      "grad_norm": 0.6212698221206665,
      "learning_rate": 0.0004709414104280326,
      "loss": 14.0043,
      "num_input_tokens_seen": 401033514,
      "step": 163
    },
    {
      "epoch": 0.17272248551869404,
      "grad_norm": 0.7096490859985352,
      "learning_rate": 0.00047001582757120054,
      "loss": 13.5022,
      "num_input_tokens_seen": 403501710,
      "step": 164
    },
    {
      "epoch": 0.17377567140600317,
      "grad_norm": 0.5144787430763245,
      "learning_rate": 0.00046907667310329887,
      "loss": 13.0917,
      "num_input_tokens_seen": 405903642,
      "step": 165
    },
    {
      "epoch": 0.17482885729331227,
      "grad_norm": 0.5807265043258667,
      "learning_rate": 0.0004681240049557991,
      "loss": 14.2594,
      "num_input_tokens_seen": 408463312,
      "step": 166
    },
    {
      "epoch": 0.17588204318062137,
      "grad_norm": 0.6672924160957336,
      "learning_rate": 0.00046715788189375995,
      "loss": 14.18,
      "num_input_tokens_seen": 410857116,
      "step": 167
    },
    {
      "epoch": 0.1769352290679305,
      "grad_norm": 0.5318564176559448,
      "learning_rate": 0.0004661783635122028,
      "loss": 12.7704,
      "num_input_tokens_seen": 413293324,
      "step": 168
    },
    {
      "epoch": 0.1779884149552396,
      "grad_norm": 0.794619083404541,
      "learning_rate": 0.0004651855102324352,
      "loss": 14.1618,
      "num_input_tokens_seen": 415708708,
      "step": 169
    },
    {
      "epoch": 0.17904160084254872,
      "grad_norm": 0.45533284544944763,
      "learning_rate": 0.0004641793832983245,
      "loss": 14.5507,
      "num_input_tokens_seen": 418090970,
      "step": 170
    },
    {
      "epoch": 0.18009478672985782,
      "grad_norm": 0.8352651000022888,
      "learning_rate": 0.0004631600447725189,
      "loss": 12.2149,
      "num_input_tokens_seen": 420536658,
      "step": 171
    },
    {
      "epoch": 0.18114797261716692,
      "grad_norm": 0.720396876335144,
      "learning_rate": 0.0004621275575326206,
      "loss": 14.3939,
      "num_input_tokens_seen": 423068800,
      "step": 172
    },
    {
      "epoch": 0.18220115850447605,
      "grad_norm": 0.6031028032302856,
      "learning_rate": 0.00046108198526730563,
      "loss": 14.285,
      "num_input_tokens_seen": 425683216,
      "step": 173
    },
    {
      "epoch": 0.18325434439178515,
      "grad_norm": 0.7864506840705872,
      "learning_rate": 0.0004600233924723966,
      "loss": 14.9537,
      "num_input_tokens_seen": 428019392,
      "step": 174
    },
    {
      "epoch": 0.18430753027909427,
      "grad_norm": 0.6037179827690125,
      "learning_rate": 0.0004589518444468836,
      "loss": 14.3359,
      "num_input_tokens_seen": 430450162,
      "step": 175
    },
    {
      "epoch": 0.18536071616640337,
      "grad_norm": 0.5774262547492981,
      "learning_rate": 0.000457867407288896,
      "loss": 14.7474,
      "num_input_tokens_seen": 432988892,
      "step": 176
    },
    {
      "epoch": 0.18641390205371247,
      "grad_norm": 0.5661394000053406,
      "learning_rate": 0.0004567701478916261,
      "loss": 12.7355,
      "num_input_tokens_seen": 435403104,
      "step": 177
    },
    {
      "epoch": 0.1874670879410216,
      "grad_norm": 0.48973754048347473,
      "learning_rate": 0.00045566013393920205,
      "loss": 14.4007,
      "num_input_tokens_seen": 437894208,
      "step": 178
    },
    {
      "epoch": 0.1885202738283307,
      "grad_norm": 0.6543258428573608,
      "learning_rate": 0.0004545374339025129,
      "loss": 13.388,
      "num_input_tokens_seen": 440361302,
      "step": 179
    },
    {
      "epoch": 0.1895734597156398,
      "grad_norm": 0.6435189247131348,
      "learning_rate": 0.0004534021170349856,
      "loss": 12.7891,
      "num_input_tokens_seen": 442772076,
      "step": 180
    },
    {
      "epoch": 0.19062664560294892,
      "grad_norm": 0.5193156599998474,
      "learning_rate": 0.000452254253368312,
      "loss": 13.4092,
      "num_input_tokens_seen": 445142352,
      "step": 181
    },
    {
      "epoch": 0.19167983149025802,
      "grad_norm": 0.6403075456619263,
      "learning_rate": 0.0004510939137081302,
      "loss": 12.8269,
      "num_input_tokens_seen": 447635106,
      "step": 182
    },
    {
      "epoch": 0.19273301737756715,
      "grad_norm": 0.5330055356025696,
      "learning_rate": 0.00044992116962965623,
      "loss": 13.845,
      "num_input_tokens_seen": 449969556,
      "step": 183
    },
    {
      "epoch": 0.19378620326487625,
      "grad_norm": 0.7812511920928955,
      "learning_rate": 0.00044873609347326866,
      "loss": 12.8747,
      "num_input_tokens_seen": 452367082,
      "step": 184
    },
    {
      "epoch": 0.19483938915218535,
      "grad_norm": 0.734370231628418,
      "learning_rate": 0.0004475387583400473,
      "loss": 13.4237,
      "num_input_tokens_seen": 454829434,
      "step": 185
    },
    {
      "epoch": 0.19589257503949448,
      "grad_norm": 0.4542326331138611,
      "learning_rate": 0.00044632923808726293,
      "loss": 13.5973,
      "num_input_tokens_seen": 457344632,
      "step": 186
    },
    {
      "epoch": 0.19694576092680358,
      "grad_norm": 0.630257248878479,
      "learning_rate": 0.0004451076073238223,
      "loss": 14.2557,
      "num_input_tokens_seen": 459728304,
      "step": 187
    },
    {
      "epoch": 0.1979989468141127,
      "grad_norm": 0.5169203281402588,
      "learning_rate": 0.0004438739414056651,
      "loss": 14.2164,
      "num_input_tokens_seen": 462371360,
      "step": 188
    },
    {
      "epoch": 0.1990521327014218,
      "grad_norm": 0.8144217729568481,
      "learning_rate": 0.0004426283164311162,
      "loss": 13.2628,
      "num_input_tokens_seen": 464826406,
      "step": 189
    },
    {
      "epoch": 0.2001053185887309,
      "grad_norm": 0.643693745136261,
      "learning_rate": 0.00044137080923619174,
      "loss": 12.6582,
      "num_input_tokens_seen": 467463708,
      "step": 190
    },
    {
      "epoch": 0.20115850447604003,
      "grad_norm": 0.7169672250747681,
      "learning_rate": 0.0004401014973898586,
      "loss": 13.8927,
      "num_input_tokens_seen": 469992746,
      "step": 191
    },
    {
      "epoch": 0.20221169036334913,
      "grad_norm": 0.5725452303886414,
      "learning_rate": 0.0004388204591892506,
      "loss": 12.8936,
      "num_input_tokens_seen": 472498546,
      "step": 192
    },
    {
      "epoch": 0.20326487625065823,
      "grad_norm": 0.885722279548645,
      "learning_rate": 0.00043752777365483816,
      "loss": 13.1909,
      "num_input_tokens_seen": 474859284,
      "step": 193
    },
    {
      "epoch": 0.20431806213796735,
      "grad_norm": 0.5468750596046448,
      "learning_rate": 0.0004362235205255541,
      "loss": 13.3254,
      "num_input_tokens_seen": 477239588,
      "step": 194
    },
    {
      "epoch": 0.20537124802527645,
      "grad_norm": 0.5252361297607422,
      "learning_rate": 0.0004349077802538751,
      "loss": 14.707,
      "num_input_tokens_seen": 479559702,
      "step": 195
    },
    {
      "epoch": 0.20642443391258558,
      "grad_norm": 0.5459883213043213,
      "learning_rate": 0.0004335806340008587,
      "loss": 12.9516,
      "num_input_tokens_seen": 482139806,
      "step": 196
    },
    {
      "epoch": 0.20747761979989468,
      "grad_norm": 0.6774821877479553,
      "learning_rate": 0.00043224216363113723,
      "loss": 13.8214,
      "num_input_tokens_seen": 484606370,
      "step": 197
    },
    {
      "epoch": 0.20853080568720378,
      "grad_norm": 0.6609899997711182,
      "learning_rate": 0.0004308924517078678,
      "loss": 13.5105,
      "num_input_tokens_seen": 487088894,
      "step": 198
    },
    {
      "epoch": 0.2095839915745129,
      "grad_norm": 0.6434972286224365,
      "learning_rate": 0.00042953158148763975,
      "loss": 14.704,
      "num_input_tokens_seen": 489502024,
      "step": 199
    },
    {
      "epoch": 0.210637177461822,
      "grad_norm": 0.530325710773468,
      "learning_rate": 0.0004281596369153384,
      "loss": 13.314,
      "num_input_tokens_seen": 491847958,
      "step": 200
    },
    {
      "epoch": 0.21169036334913113,
      "grad_norm": 0.5580898523330688,
      "learning_rate": 0.0004267767026189673,
      "loss": 13.3497,
      "num_input_tokens_seen": 494483540,
      "step": 201
    },
    {
      "epoch": 0.21274354923644023,
      "grad_norm": 0.7523868083953857,
      "learning_rate": 0.00042538286390442833,
      "loss": 13.4598,
      "num_input_tokens_seen": 496784334,
      "step": 202
    },
    {
      "epoch": 0.21379673512374933,
      "grad_norm": 0.6943124532699585,
      "learning_rate": 0.00042397820675025866,
      "loss": 14.4622,
      "num_input_tokens_seen": 499122570,
      "step": 203
    },
    {
      "epoch": 0.21484992101105846,
      "grad_norm": 0.703617513179779,
      "learning_rate": 0.0004225628178023283,
      "loss": 14.4754,
      "num_input_tokens_seen": 501601060,
      "step": 204
    },
    {
      "epoch": 0.21590310689836756,
      "grad_norm": 0.6258761286735535,
      "learning_rate": 0.00042113678436849454,
      "loss": 12.8945,
      "num_input_tokens_seen": 504016506,
      "step": 205
    },
    {
      "epoch": 0.21695629278567669,
      "grad_norm": 0.7714695334434509,
      "learning_rate": 0.0004197001944132168,
      "loss": 13.6326,
      "num_input_tokens_seen": 506604150,
      "step": 206
    },
    {
      "epoch": 0.21800947867298578,
      "grad_norm": 0.6725168228149414,
      "learning_rate": 0.0004182531365521305,
      "loss": 14.247,
      "num_input_tokens_seen": 509053728,
      "step": 207
    },
    {
      "epoch": 0.21906266456029488,
      "grad_norm": 0.767383337020874,
      "learning_rate": 0.0004167957000465808,
      "loss": 14.331,
      "num_input_tokens_seen": 511567478,
      "step": 208
    },
    {
      "epoch": 0.220115850447604,
      "grad_norm": 0.505607545375824,
      "learning_rate": 0.00041532797479811636,
      "loss": 12.4713,
      "num_input_tokens_seen": 514136400,
      "step": 209
    },
    {
      "epoch": 0.2211690363349131,
      "grad_norm": 0.5330973863601685,
      "learning_rate": 0.00041385005134294417,
      "loss": 13.1837,
      "num_input_tokens_seen": 516530356,
      "step": 210
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.9914455413818359,
      "learning_rate": 0.00041236202084634466,
      "loss": 14.6703,
      "num_input_tokens_seen": 519028524,
      "step": 211
    },
    {
      "epoch": 0.22327540810953134,
      "grad_norm": 0.6133384108543396,
      "learning_rate": 0.0004108639750970481,
      "loss": 14.6338,
      "num_input_tokens_seen": 521436334,
      "step": 212
    },
    {
      "epoch": 0.22432859399684044,
      "grad_norm": 0.5959540009498596,
      "learning_rate": 0.00040935600650157265,
      "loss": 12.1111,
      "num_input_tokens_seen": 524024802,
      "step": 213
    },
    {
      "epoch": 0.22538177988414956,
      "grad_norm": 0.45092490315437317,
      "learning_rate": 0.00040783820807852457,
      "loss": 13.4522,
      "num_input_tokens_seen": 526580534,
      "step": 214
    },
    {
      "epoch": 0.22643496577145866,
      "grad_norm": 0.5904210805892944,
      "learning_rate": 0.00040631067345285994,
      "loss": 13.2396,
      "num_input_tokens_seen": 529062886,
      "step": 215
    },
    {
      "epoch": 0.22748815165876776,
      "grad_norm": 0.46232736110687256,
      "learning_rate": 0.0004047734968501098,
      "loss": 13.8601,
      "num_input_tokens_seen": 531535650,
      "step": 216
    },
    {
      "epoch": 0.2285413375460769,
      "grad_norm": 0.617415189743042,
      "learning_rate": 0.0004032267730905678,
      "loss": 12.8285,
      "num_input_tokens_seen": 534061814,
      "step": 217
    },
    {
      "epoch": 0.229594523433386,
      "grad_norm": 0.7234218120574951,
      "learning_rate": 0.00040167059758344114,
      "loss": 15.3652,
      "num_input_tokens_seen": 536687100,
      "step": 218
    },
    {
      "epoch": 0.23064770932069512,
      "grad_norm": 0.8561363220214844,
      "learning_rate": 0.00040010506632096537,
      "loss": 12.8718,
      "num_input_tokens_seen": 539150044,
      "step": 219
    },
    {
      "epoch": 0.23170089520800422,
      "grad_norm": 0.7568314671516418,
      "learning_rate": 0.0003985302758724831,
      "loss": 12.4404,
      "num_input_tokens_seen": 541648322,
      "step": 220
    },
    {
      "epoch": 0.23275408109531331,
      "grad_norm": 0.6514911651611328,
      "learning_rate": 0.000396946323378487,
      "loss": 13.7264,
      "num_input_tokens_seen": 544168352,
      "step": 221
    },
    {
      "epoch": 0.23380726698262244,
      "grad_norm": 0.6163381338119507,
      "learning_rate": 0.0003953533065446281,
      "loss": 13.1166,
      "num_input_tokens_seen": 546741482,
      "step": 222
    },
    {
      "epoch": 0.23486045286993154,
      "grad_norm": 0.696421205997467,
      "learning_rate": 0.00039375132363568836,
      "loss": 13.3474,
      "num_input_tokens_seen": 549104356,
      "step": 223
    },
    {
      "epoch": 0.23591363875724064,
      "grad_norm": 0.6050801873207092,
      "learning_rate": 0.00039214047346951974,
      "loss": 14.6743,
      "num_input_tokens_seen": 551429474,
      "step": 224
    },
    {
      "epoch": 0.23696682464454977,
      "grad_norm": 0.6175264120101929,
      "learning_rate": 0.00039052085541094823,
      "loss": 13.7552,
      "num_input_tokens_seen": 553859868,
      "step": 225
    },
    {
      "epoch": 0.23802001053185887,
      "grad_norm": 0.5892110466957092,
      "learning_rate": 0.0003888925693656447,
      "loss": 11.5144,
      "num_input_tokens_seen": 556346556,
      "step": 226
    },
    {
      "epoch": 0.239073196419168,
      "grad_norm": 0.4362712502479553,
      "learning_rate": 0.00038725571577396254,
      "loss": 14.626,
      "num_input_tokens_seen": 558924540,
      "step": 227
    },
    {
      "epoch": 0.2401263823064771,
      "grad_norm": 0.6579407453536987,
      "learning_rate": 0.0003856103956047413,
      "loss": 13.2753,
      "num_input_tokens_seen": 561327442,
      "step": 228
    },
    {
      "epoch": 0.2411795681937862,
      "grad_norm": 0.7273943424224854,
      "learning_rate": 0.0003839567103490793,
      "loss": 13.0622,
      "num_input_tokens_seen": 563837514,
      "step": 229
    },
    {
      "epoch": 0.24223275408109532,
      "grad_norm": 0.4669589698314667,
      "learning_rate": 0.0003822947620140726,
      "loss": 13.8885,
      "num_input_tokens_seen": 566302658,
      "step": 230
    },
    {
      "epoch": 0.24328593996840442,
      "grad_norm": 0.5003737211227417,
      "learning_rate": 0.0003806246531165231,
      "loss": 12.9119,
      "num_input_tokens_seen": 568934814,
      "step": 231
    },
    {
      "epoch": 0.24433912585571355,
      "grad_norm": 0.6652275323867798,
      "learning_rate": 0.0003789464866766144,
      "loss": 12.8361,
      "num_input_tokens_seen": 571237934,
      "step": 232
    },
    {
      "epoch": 0.24539231174302265,
      "grad_norm": 0.6242262125015259,
      "learning_rate": 0.0003772603662115575,
      "loss": 15.0241,
      "num_input_tokens_seen": 573556058,
      "step": 233
    },
    {
      "epoch": 0.24644549763033174,
      "grad_norm": 0.48296427726745605,
      "learning_rate": 0.0003755663957292048,
      "loss": 13.4312,
      "num_input_tokens_seen": 575930124,
      "step": 234
    },
    {
      "epoch": 0.24749868351764087,
      "grad_norm": 0.6832424998283386,
      "learning_rate": 0.00037386467972163516,
      "loss": 14.7431,
      "num_input_tokens_seen": 578430022,
      "step": 235
    },
    {
      "epoch": 0.24855186940494997,
      "grad_norm": 0.5334222912788391,
      "learning_rate": 0.00037215532315870774,
      "loss": 14.7028,
      "num_input_tokens_seen": 580816748,
      "step": 236
    },
    {
      "epoch": 0.24960505529225907,
      "grad_norm": 0.7042843699455261,
      "learning_rate": 0.00037043843148158696,
      "loss": 12.5905,
      "num_input_tokens_seen": 583366398,
      "step": 237
    },
    {
      "epoch": 0.2506582411795682,
      "grad_norm": 0.7521989941596985,
      "learning_rate": 0.0003687141105962389,
      "loss": 12.383,
      "num_input_tokens_seen": 585825914,
      "step": 238
    },
    {
      "epoch": 0.2517114270668773,
      "grad_norm": 0.5999695658683777,
      "learning_rate": 0.000366982466866898,
      "loss": 12.7159,
      "num_input_tokens_seen": 588320922,
      "step": 239
    },
    {
      "epoch": 0.2527646129541864,
      "grad_norm": 0.5892810225486755,
      "learning_rate": 0.00036524360710950624,
      "loss": 15.1348,
      "num_input_tokens_seen": 590762520,
      "step": 240
    },
    {
      "epoch": 0.2538177988414955,
      "grad_norm": 0.5765227675437927,
      "learning_rate": 0.0003634976385851242,
      "loss": 12.3584,
      "num_input_tokens_seen": 593119346,
      "step": 241
    },
    {
      "epoch": 0.25487098472880465,
      "grad_norm": 0.4210558533668518,
      "learning_rate": 0.00036174466899331484,
      "loss": 13.7542,
      "num_input_tokens_seen": 595480902,
      "step": 242
    },
    {
      "epoch": 0.2559241706161137,
      "grad_norm": 0.6763030290603638,
      "learning_rate": 0.0003599848064654995,
      "loss": 13.2929,
      "num_input_tokens_seen": 597986692,
      "step": 243
    },
    {
      "epoch": 0.25697735650342285,
      "grad_norm": 0.7130559086799622,
      "learning_rate": 0.000358218159558289,
      "loss": 13.3078,
      "num_input_tokens_seen": 600640014,
      "step": 244
    },
    {
      "epoch": 0.258030542390732,
      "grad_norm": 0.4660380184650421,
      "learning_rate": 0.0003564448372467859,
      "loss": 14.6048,
      "num_input_tokens_seen": 602922284,
      "step": 245
    },
    {
      "epoch": 0.25908372827804105,
      "grad_norm": 0.44570890069007874,
      "learning_rate": 0.0003546649489178636,
      "loss": 14.8523,
      "num_input_tokens_seen": 605350038,
      "step": 246
    },
    {
      "epoch": 0.2601369141653502,
      "grad_norm": 0.6495239734649658,
      "learning_rate": 0.00035287860436341824,
      "loss": 15.1324,
      "num_input_tokens_seen": 607725012,
      "step": 247
    },
    {
      "epoch": 0.2611901000526593,
      "grad_norm": 0.5707351565361023,
      "learning_rate": 0.0003510859137735964,
      "loss": 15.3348,
      "num_input_tokens_seen": 610117954,
      "step": 248
    },
    {
      "epoch": 0.26224328593996843,
      "grad_norm": 0.4367353618144989,
      "learning_rate": 0.00034928698772999787,
      "loss": 13.6328,
      "num_input_tokens_seen": 612557846,
      "step": 249
    },
    {
      "epoch": 0.2632964718272775,
      "grad_norm": 0.6344426274299622,
      "learning_rate": 0.0003474819371988549,
      "loss": 12.4955,
      "num_input_tokens_seen": 614861376,
      "step": 250
    },
    {
      "epoch": 0.2643496577145866,
      "grad_norm": 0.6118125319480896,
      "learning_rate": 0.00034567087352418665,
      "loss": 14.4303,
      "num_input_tokens_seen": 617294518,
      "step": 251
    },
    {
      "epoch": 0.26540284360189575,
      "grad_norm": 0.7218714356422424,
      "learning_rate": 0.0003438539084209315,
      "loss": 14.22,
      "num_input_tokens_seen": 619635220,
      "step": 252
    },
    {
      "epoch": 0.2664560294892048,
      "grad_norm": 0.6843687891960144,
      "learning_rate": 0.0003420311539680557,
      "loss": 12.9144,
      "num_input_tokens_seen": 622075956,
      "step": 253
    },
    {
      "epoch": 0.26750921537651395,
      "grad_norm": 0.7561080455780029,
      "learning_rate": 0.00034020272260163977,
      "loss": 13.2422,
      "num_input_tokens_seen": 624607758,
      "step": 254
    },
    {
      "epoch": 0.2685624012638231,
      "grad_norm": 0.7663512229919434,
      "learning_rate": 0.0003383687271079432,
      "loss": 14.6787,
      "num_input_tokens_seen": 627172634,
      "step": 255
    },
    {
      "epoch": 0.26961558715113215,
      "grad_norm": 0.4203454554080963,
      "learning_rate": 0.0003365292806164468,
      "loss": 14.2549,
      "num_input_tokens_seen": 629690912,
      "step": 256
    },
    {
      "epoch": 0.2706687730384413,
      "grad_norm": 0.546712338924408,
      "learning_rate": 0.00033468449659287486,
      "loss": 14.3124,
      "num_input_tokens_seen": 632255410,
      "step": 257
    },
    {
      "epoch": 0.2717219589257504,
      "grad_norm": 0.7108402252197266,
      "learning_rate": 0.0003328344888321955,
      "loss": 13.3583,
      "num_input_tokens_seen": 634582544,
      "step": 258
    },
    {
      "epoch": 0.2727751448130595,
      "grad_norm": 0.6388810276985168,
      "learning_rate": 0.0003309793714516019,
      "loss": 13.9617,
      "num_input_tokens_seen": 637108470,
      "step": 259
    },
    {
      "epoch": 0.2738283307003686,
      "grad_norm": 0.5022799372673035,
      "learning_rate": 0.00032911925888347234,
      "loss": 13.8352,
      "num_input_tokens_seen": 639426634,
      "step": 260
    },
    {
      "epoch": 0.27488151658767773,
      "grad_norm": 0.5447593927383423,
      "learning_rate": 0.00032725426586831203,
      "loss": 15.0631,
      "num_input_tokens_seen": 641900154,
      "step": 261
    },
    {
      "epoch": 0.27593470247498686,
      "grad_norm": 0.5760501027107239,
      "learning_rate": 0.0003253845074476749,
      "loss": 13.7699,
      "num_input_tokens_seen": 644205144,
      "step": 262
    },
    {
      "epoch": 0.27698788836229593,
      "grad_norm": 0.5831496715545654,
      "learning_rate": 0.00032351009895706785,
      "loss": 14.5406,
      "num_input_tokens_seen": 646496932,
      "step": 263
    },
    {
      "epoch": 0.27804107424960506,
      "grad_norm": 0.5406723618507385,
      "learning_rate": 0.00032163115601883583,
      "loss": 12.7346,
      "num_input_tokens_seen": 649096904,
      "step": 264
    },
    {
      "epoch": 0.2790942601369142,
      "grad_norm": 0.49079757928848267,
      "learning_rate": 0.0003197477945350297,
      "loss": 14.2354,
      "num_input_tokens_seen": 651600900,
      "step": 265
    },
    {
      "epoch": 0.28014744602422326,
      "grad_norm": 0.6124666929244995,
      "learning_rate": 0.0003178601306802573,
      "loss": 14.5682,
      "num_input_tokens_seen": 654189842,
      "step": 266
    },
    {
      "epoch": 0.2812006319115324,
      "grad_norm": 0.5420570969581604,
      "learning_rate": 0.00031596828089451703,
      "loss": 14.2276,
      "num_input_tokens_seen": 656636650,
      "step": 267
    },
    {
      "epoch": 0.2822538177988415,
      "grad_norm": 0.8127923011779785,
      "learning_rate": 0.00031407236187601487,
      "loss": 11.0238,
      "num_input_tokens_seen": 659070838,
      "step": 268
    },
    {
      "epoch": 0.2833070036861506,
      "grad_norm": 0.6101799011230469,
      "learning_rate": 0.0003121724905739666,
      "loss": 12.8694,
      "num_input_tokens_seen": 661668122,
      "step": 269
    },
    {
      "epoch": 0.2843601895734597,
      "grad_norm": 0.5585333108901978,
      "learning_rate": 0.0003102687841813832,
      "loss": 12.3072,
      "num_input_tokens_seen": 664055676,
      "step": 270
    },
    {
      "epoch": 0.28541337546076884,
      "grad_norm": 0.5515812635421753,
      "learning_rate": 0.00030836136012784226,
      "loss": 14.4035,
      "num_input_tokens_seen": 666712162,
      "step": 271
    },
    {
      "epoch": 0.2864665613480779,
      "grad_norm": 0.873502254486084,
      "learning_rate": 0.00030645033607224425,
      "loss": 11.5386,
      "num_input_tokens_seen": 669145358,
      "step": 272
    },
    {
      "epoch": 0.28751974723538704,
      "grad_norm": 0.7929896712303162,
      "learning_rate": 0.0003045358298955546,
      "loss": 13.7234,
      "num_input_tokens_seen": 671496934,
      "step": 273
    },
    {
      "epoch": 0.28857293312269616,
      "grad_norm": 0.6259802579879761,
      "learning_rate": 0.0003026179596935324,
      "loss": 12.9467,
      "num_input_tokens_seen": 673956840,
      "step": 274
    },
    {
      "epoch": 0.2896261190100053,
      "grad_norm": 0.5827144980430603,
      "learning_rate": 0.00030069684376944573,
      "loss": 13.7525,
      "num_input_tokens_seen": 676522688,
      "step": 275
    },
    {
      "epoch": 0.29067930489731436,
      "grad_norm": 0.438773512840271,
      "learning_rate": 0.000298772600626774,
      "loss": 14.4876,
      "num_input_tokens_seen": 678987128,
      "step": 276
    },
    {
      "epoch": 0.2917324907846235,
      "grad_norm": 0.461264431476593,
      "learning_rate": 0.00029684534896189834,
      "loss": 13.9557,
      "num_input_tokens_seen": 681376426,
      "step": 277
    },
    {
      "epoch": 0.2927856766719326,
      "grad_norm": 0.6426395177841187,
      "learning_rate": 0.0002949152076567795,
      "loss": 13.2047,
      "num_input_tokens_seen": 683908570,
      "step": 278
    },
    {
      "epoch": 0.2938388625592417,
      "grad_norm": 0.6306378245353699,
      "learning_rate": 0.0002929822957716248,
      "loss": 14.3553,
      "num_input_tokens_seen": 686435460,
      "step": 279
    },
    {
      "epoch": 0.2948920484465508,
      "grad_norm": 0.7777087092399597,
      "learning_rate": 0.00029104673253754456,
      "loss": 14.459,
      "num_input_tokens_seen": 689001010,
      "step": 280
    },
    {
      "epoch": 0.29594523433385994,
      "grad_norm": 0.6122662425041199,
      "learning_rate": 0.00028910863734919615,
      "loss": 11.8841,
      "num_input_tokens_seen": 691555714,
      "step": 281
    },
    {
      "epoch": 0.296998420221169,
      "grad_norm": 0.5533509850502014,
      "learning_rate": 0.00028716812975741995,
      "loss": 13.8105,
      "num_input_tokens_seen": 694038390,
      "step": 282
    },
    {
      "epoch": 0.29805160610847814,
      "grad_norm": 0.4330850839614868,
      "learning_rate": 0.00028522532946186486,
      "loss": 15.3927,
      "num_input_tokens_seen": 696690606,
      "step": 283
    },
    {
      "epoch": 0.29910479199578727,
      "grad_norm": 0.42759576439857483,
      "learning_rate": 0.0002832803563036046,
      "loss": 14.1626,
      "num_input_tokens_seen": 698974368,
      "step": 284
    },
    {
      "epoch": 0.3001579778830964,
      "grad_norm": 0.603848934173584,
      "learning_rate": 0.00028133333025774524,
      "loss": 14.7466,
      "num_input_tokens_seen": 701514324,
      "step": 285
    },
    {
      "epoch": 0.30121116377040547,
      "grad_norm": 0.7019180655479431,
      "learning_rate": 0.0002793843714260245,
      "loss": 15.9288,
      "num_input_tokens_seen": 703856054,
      "step": 286
    },
    {
      "epoch": 0.3022643496577146,
      "grad_norm": 0.5272998213768005,
      "learning_rate": 0.0002774336000294035,
      "loss": 14.2158,
      "num_input_tokens_seen": 706380374,
      "step": 287
    },
    {
      "epoch": 0.3033175355450237,
      "grad_norm": 0.6808348298072815,
      "learning_rate": 0.0002754811364006511,
      "loss": 14.3927,
      "num_input_tokens_seen": 708733546,
      "step": 288
    },
    {
      "epoch": 0.3043707214323328,
      "grad_norm": 0.5963918566703796,
      "learning_rate": 0.0002735271009769208,
      "loss": 15.4471,
      "num_input_tokens_seen": 711304704,
      "step": 289
    },
    {
      "epoch": 0.3054239073196419,
      "grad_norm": 0.5460891127586365,
      "learning_rate": 0.00027157161429232173,
      "loss": 15.3405,
      "num_input_tokens_seen": 713915084,
      "step": 290
    },
    {
      "epoch": 0.30647709320695105,
      "grad_norm": 0.4156426787376404,
      "learning_rate": 0.00026961479697048385,
      "loss": 14.4655,
      "num_input_tokens_seen": 716304858,
      "step": 291
    },
    {
      "epoch": 0.3075302790942601,
      "grad_norm": 0.6879798173904419,
      "learning_rate": 0.00026765676971711704,
      "loss": 13.2176,
      "num_input_tokens_seen": 718782282,
      "step": 292
    },
    {
      "epoch": 0.30858346498156924,
      "grad_norm": 0.41598352789878845,
      "learning_rate": 0.00026569765331256536,
      "loss": 14.1726,
      "num_input_tokens_seen": 721256712,
      "step": 293
    },
    {
      "epoch": 0.30963665086887837,
      "grad_norm": 0.5724912285804749,
      "learning_rate": 0.000263737568604357,
      "loss": 13.6108,
      "num_input_tokens_seen": 723712914,
      "step": 294
    },
    {
      "epoch": 0.31068983675618744,
      "grad_norm": 0.6704716682434082,
      "learning_rate": 0.00026177663649974936,
      "loss": 13.6995,
      "num_input_tokens_seen": 726014718,
      "step": 295
    },
    {
      "epoch": 0.31174302264349657,
      "grad_norm": 0.6606157422065735,
      "learning_rate": 0.00025981497795827174,
      "loss": 13.7077,
      "num_input_tokens_seen": 728471242,
      "step": 296
    },
    {
      "epoch": 0.3127962085308057,
      "grad_norm": 0.5907959342002869,
      "learning_rate": 0.0002578527139842631,
      "loss": 13.3751,
      "num_input_tokens_seen": 730842942,
      "step": 297
    },
    {
      "epoch": 0.3138493944181148,
      "grad_norm": 0.710864782333374,
      "learning_rate": 0.00025588996561940846,
      "loss": 13.9066,
      "num_input_tokens_seen": 733445910,
      "step": 298
    },
    {
      "epoch": 0.3149025803054239,
      "grad_norm": 0.44538646936416626,
      "learning_rate": 0.0002539268539352723,
      "loss": 14.0321,
      "num_input_tokens_seen": 735908532,
      "step": 299
    },
    {
      "epoch": 0.315955766192733,
      "grad_norm": 0.5508079528808594,
      "learning_rate": 0.00025196350002583027,
      "loss": 13.4983,
      "num_input_tokens_seen": 738472692,
      "step": 300
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 500,
  "num_input_tokens_seen": 738472692,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.0242409621374894e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}