{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.998,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008008008008008008,
      "grad_norm": 1.6445057392120361,
      "learning_rate": 2e-05,
      "loss": 2.3547,
      "step": 1
    },
    {
      "epoch": 0.016016016016016016,
      "grad_norm": 1.63363778591156,
      "learning_rate": 4e-05,
      "loss": 2.3812,
      "step": 2
    },
    {
      "epoch": 0.024024024024024024,
      "grad_norm": 1.6492197513580322,
      "learning_rate": 6e-05,
      "loss": 2.3399,
      "step": 3
    },
    {
      "epoch": 0.03203203203203203,
      "grad_norm": 1.6518611907958984,
      "learning_rate": 8e-05,
      "loss": 2.3172,
      "step": 4
    },
    {
      "epoch": 0.04004004004004004,
      "grad_norm": 1.7173571586608887,
      "learning_rate": 0.0001,
      "loss": 2.2563,
      "step": 5
    },
    {
      "epoch": 0.04804804804804805,
      "grad_norm": 1.563859224319458,
      "learning_rate": 0.00012,
      "loss": 2.0256,
      "step": 6
    },
    {
      "epoch": 0.056056056056056056,
      "grad_norm": 1.5590581893920898,
      "learning_rate": 0.00014,
      "loss": 1.8324,
      "step": 7
    },
    {
      "epoch": 0.06406406406406406,
      "grad_norm": 1.5127277374267578,
      "learning_rate": 0.00016,
      "loss": 1.5787,
      "step": 8
    },
    {
      "epoch": 0.07207207207207207,
      "grad_norm": 1.5447226762771606,
      "learning_rate": 0.00018,
      "loss": 1.3826,
      "step": 9
    },
    {
      "epoch": 0.08008008008008008,
      "grad_norm": 4.600811004638672,
      "learning_rate": 0.0002,
      "loss": 1.2388,
      "step": 10
    },
    {
      "epoch": 0.08808808808808809,
      "grad_norm": 1.6333264112472534,
      "learning_rate": 0.00019999629591162656,
      "loss": 1.0977,
      "step": 11
    },
    {
      "epoch": 0.0960960960960961,
      "grad_norm": 1.5325253009796143,
      "learning_rate": 0.00019998518392091164,
      "loss": 1.0178,
      "step": 12
    },
    {
      "epoch": 0.1041041041041041,
      "grad_norm": 1.866473913192749,
      "learning_rate": 0.00019996666485105113,
      "loss": 0.9454,
      "step": 13
    },
    {
      "epoch": 0.11211211211211211,
      "grad_norm": 1.450692892074585,
      "learning_rate": 0.0001999407400739705,
      "loss": 0.8514,
      "step": 14
    },
    {
      "epoch": 0.12012012012012012,
      "grad_norm": 5.149086952209473,
      "learning_rate": 0.00019990741151022301,
      "loss": 0.9136,
      "step": 15
    },
    {
      "epoch": 0.12812812812812813,
      "grad_norm": 0.7399551272392273,
      "learning_rate": 0.00019986668162884762,
      "loss": 0.8742,
      "step": 16
    },
    {
      "epoch": 0.13613613613613615,
      "grad_norm": 0.6142033934593201,
      "learning_rate": 0.00019981855344718588,
      "loss": 0.8082,
      "step": 17
    },
    {
      "epoch": 0.14414414414414414,
      "grad_norm": 0.47605425119400024,
      "learning_rate": 0.00019976303053065859,
      "loss": 0.8019,
      "step": 18
    },
    {
      "epoch": 0.15215215215215216,
      "grad_norm": 0.3993614614009857,
      "learning_rate": 0.00019970011699250152,
      "loss": 0.7625,
      "step": 19
    },
    {
      "epoch": 0.16016016016016016,
      "grad_norm": 0.4947199821472168,
      "learning_rate": 0.00019962981749346078,
      "loss": 0.7419,
      "step": 20
    },
    {
      "epoch": 0.16816816816816818,
      "grad_norm": 0.549526572227478,
      "learning_rate": 0.00019955213724144754,
      "loss": 0.7468,
      "step": 21
    },
    {
      "epoch": 0.17617617617617617,
      "grad_norm": 0.34314435720443726,
      "learning_rate": 0.00019946708199115211,
      "loss": 0.7482,
      "step": 22
    },
    {
      "epoch": 0.1841841841841842,
      "grad_norm": 0.38283613324165344,
      "learning_rate": 0.00019937465804361783,
      "loss": 0.7304,
      "step": 23
    },
    {
      "epoch": 0.1921921921921922,
      "grad_norm": 0.28871795535087585,
      "learning_rate": 0.00019927487224577402,
      "loss": 0.746,
      "step": 24
    },
    {
      "epoch": 0.2002002002002002,
      "grad_norm": 0.321494996547699,
      "learning_rate": 0.000199167731989929,
      "loss": 0.7461,
      "step": 25
    },
    {
      "epoch": 0.2082082082082082,
      "grad_norm": 0.315449982881546,
      "learning_rate": 0.0001990532452132223,
      "loss": 0.7286,
      "step": 26
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 0.2904318571090698,
      "learning_rate": 0.00019893142039703664,
      "loss": 0.7119,
      "step": 27
    },
    {
      "epoch": 0.22422422422422422,
      "grad_norm": 0.27874529361724854,
      "learning_rate": 0.00019880226656636977,
      "loss": 0.7105,
      "step": 28
    },
    {
      "epoch": 0.23223223223223224,
      "grad_norm": 0.2948579490184784,
      "learning_rate": 0.0001986657932891657,
      "loss": 0.6976,
      "step": 29
    },
    {
      "epoch": 0.24024024024024024,
      "grad_norm": 0.2542964220046997,
      "learning_rate": 0.00019852201067560606,
      "loss": 0.7351,
      "step": 30
    },
    {
      "epoch": 0.24824824824824826,
      "grad_norm": 0.2960706353187561,
      "learning_rate": 0.000198370929377361,
      "loss": 0.7179,
      "step": 31
    },
    {
      "epoch": 0.25625625625625625,
      "grad_norm": 0.24776384234428406,
      "learning_rate": 0.00019821256058680006,
      "loss": 0.7134,
      "step": 32
    },
    {
      "epoch": 0.26426426426426425,
      "grad_norm": 0.33054184913635254,
      "learning_rate": 0.00019804691603616324,
      "loss": 0.6995,
      "step": 33
    },
    {
      "epoch": 0.2722722722722723,
      "grad_norm": 0.2543237805366516,
      "learning_rate": 0.00019787400799669154,
      "loss": 0.7081,
      "step": 34
    },
    {
      "epoch": 0.2802802802802803,
      "grad_norm": 0.25240710377693176,
      "learning_rate": 0.0001976938492777182,
      "loss": 0.6928,
      "step": 35
    },
    {
      "epoch": 0.2882882882882883,
      "grad_norm": 0.35880276560783386,
      "learning_rate": 0.0001975064532257195,
      "loss": 0.7177,
      "step": 36
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.3675362467765808,
      "learning_rate": 0.0001973118337233262,
      "loss": 0.6865,
      "step": 37
    },
    {
      "epoch": 0.30430430430430433,
      "grad_norm": 0.3688451051712036,
      "learning_rate": 0.00019711000518829507,
      "loss": 0.6724,
      "step": 38
    },
    {
      "epoch": 0.3123123123123123,
      "grad_norm": 0.2982208728790283,
      "learning_rate": 0.00019690098257244064,
      "loss": 0.671,
      "step": 39
    },
    {
      "epoch": 0.3203203203203203,
      "grad_norm": 0.24197936058044434,
      "learning_rate": 0.00019668478136052774,
      "loss": 0.6777,
      "step": 40
    },
    {
      "epoch": 0.3283283283283283,
      "grad_norm": 0.748349130153656,
      "learning_rate": 0.00019646141756912434,
      "loss": 0.6641,
      "step": 41
    },
    {
      "epoch": 0.33633633633633636,
      "grad_norm": 0.5585939288139343,
      "learning_rate": 0.00019623090774541487,
      "loss": 0.6988,
      "step": 42
    },
    {
      "epoch": 0.34434434434434436,
      "grad_norm": 0.40285471081733704,
      "learning_rate": 0.00019599326896597448,
      "loss": 0.6811,
      "step": 43
    },
    {
      "epoch": 0.35235235235235235,
      "grad_norm": 0.25714346766471863,
      "learning_rate": 0.00019574851883550395,
      "loss": 0.6913,
      "step": 44
    },
    {
      "epoch": 0.36036036036036034,
      "grad_norm": 0.4926215708255768,
      "learning_rate": 0.00019549667548552556,
      "loss": 0.6707,
      "step": 45
    },
    {
      "epoch": 0.3683683683683684,
      "grad_norm": 0.3760850429534912,
      "learning_rate": 0.00019523775757303974,
      "loss": 0.6809,
      "step": 46
    },
    {
      "epoch": 0.3763763763763764,
      "grad_norm": 0.3734811842441559,
      "learning_rate": 0.0001949717842791432,
      "loss": 0.6386,
      "step": 47
    },
    {
      "epoch": 0.3843843843843844,
      "grad_norm": 0.3447561264038086,
      "learning_rate": 0.00019469877530760754,
      "loss": 0.6955,
      "step": 48
    },
    {
      "epoch": 0.3923923923923924,
      "grad_norm": 0.2680707573890686,
      "learning_rate": 0.00019441875088341997,
      "loss": 0.6625,
      "step": 49
    },
    {
      "epoch": 0.4004004004004004,
      "grad_norm": 0.2692941725254059,
      "learning_rate": 0.00019413173175128473,
      "loss": 0.66,
      "step": 50
    },
    {
      "epoch": 0.4084084084084084,
      "grad_norm": 0.32329630851745605,
      "learning_rate": 0.00019383773917408642,
      "loss": 0.6612,
      "step": 51
    },
    {
      "epoch": 0.4164164164164164,
      "grad_norm": 0.281435489654541,
      "learning_rate": 0.00019353679493131485,
      "loss": 0.6621,
      "step": 52
    },
    {
      "epoch": 0.4244244244244244,
      "grad_norm": 0.22186556458473206,
      "learning_rate": 0.00019322892131745135,
      "loss": 0.6465,
      "step": 53
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 0.2902645468711853,
      "learning_rate": 0.00019291414114031743,
      "loss": 0.6693,
      "step": 54
    },
    {
      "epoch": 0.44044044044044045,
      "grad_norm": 0.2899124324321747,
      "learning_rate": 0.000192592477719385,
      "loss": 0.6568,
      "step": 55
    },
    {
      "epoch": 0.44844844844844844,
      "grad_norm": 0.2124062478542328,
      "learning_rate": 0.00019226395488404876,
      "loss": 0.6724,
      "step": 56
    },
    {
      "epoch": 0.45645645645645644,
      "grad_norm": 0.23896393179893494,
      "learning_rate": 0.00019192859697186106,
      "loss": 0.6459,
      "step": 57
    },
    {
      "epoch": 0.4644644644644645,
      "grad_norm": 0.2762405574321747,
      "learning_rate": 0.00019158642882672873,
      "loss": 0.6498,
      "step": 58
    },
    {
      "epoch": 0.4724724724724725,
      "grad_norm": 0.2079935222864151,
      "learning_rate": 0.00019123747579707275,
      "loss": 0.6604,
      "step": 59
    },
    {
      "epoch": 0.4804804804804805,
      "grad_norm": 0.23864208161830902,
      "learning_rate": 0.0001908817637339503,
      "loss": 0.6378,
      "step": 60
    },
    {
      "epoch": 0.48848848848848847,
      "grad_norm": 0.21718506515026093,
      "learning_rate": 0.00019051931898913976,
      "loss": 0.6424,
      "step": 61
    },
    {
      "epoch": 0.4964964964964965,
      "grad_norm": 0.2773915231227875,
      "learning_rate": 0.0001901501684131884,
      "loss": 0.6474,
      "step": 62
    },
    {
      "epoch": 0.5045045045045045,
      "grad_norm": 0.23982493579387665,
      "learning_rate": 0.0001897743393534234,
      "loss": 0.6256,
      "step": 63
    },
    {
      "epoch": 0.5125125125125125,
      "grad_norm": 0.23621873557567596,
      "learning_rate": 0.0001893918596519257,
      "loss": 0.6403,
      "step": 64
    },
    {
      "epoch": 0.5205205205205206,
      "grad_norm": 0.22759953141212463,
      "learning_rate": 0.00018900275764346768,
      "loss": 0.6484,
      "step": 65
    },
    {
      "epoch": 0.5285285285285285,
      "grad_norm": 0.26695549488067627,
      "learning_rate": 0.00018860706215341382,
      "loss": 0.609,
      "step": 66
    },
    {
      "epoch": 0.5365365365365365,
      "grad_norm": 0.24594709277153015,
      "learning_rate": 0.00018820480249558537,
      "loss": 0.6338,
      "step": 67
    },
    {
      "epoch": 0.5445445445445446,
      "grad_norm": 0.22960062325000763,
      "learning_rate": 0.00018779600847008884,
      "loss": 0.6166,
      "step": 68
    },
    {
      "epoch": 0.5525525525525525,
      "grad_norm": 0.25302109122276306,
      "learning_rate": 0.00018738071036110808,
      "loss": 0.6422,
      "step": 69
    },
    {
      "epoch": 0.5605605605605606,
      "grad_norm": 0.3339892327785492,
      "learning_rate": 0.0001869589389346611,
      "loss": 0.6558,
      "step": 70
    },
    {
      "epoch": 0.5685685685685685,
      "grad_norm": 0.21397258341312408,
      "learning_rate": 0.00018653072543632062,
      "loss": 0.6323,
      "step": 71
    },
    {
      "epoch": 0.5765765765765766,
      "grad_norm": 0.2514493465423584,
      "learning_rate": 0.00018609610158889942,
      "loss": 0.657,
      "step": 72
    },
    {
      "epoch": 0.5845845845845846,
      "grad_norm": 0.25317835807800293,
      "learning_rate": 0.00018565509959010036,
      "loss": 0.641,
      "step": 73
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.22669494152069092,
      "learning_rate": 0.00018520775211013093,
      "loss": 0.6369,
      "step": 74
    },
    {
      "epoch": 0.6006006006006006,
      "grad_norm": 0.2214743047952652,
      "learning_rate": 0.00018475409228928312,
      "loss": 0.6307,
      "step": 75
    },
    {
      "epoch": 0.6086086086086087,
      "grad_norm": 0.24376747012138367,
      "learning_rate": 0.00018429415373547828,
      "loss": 0.6557,
      "step": 76
    },
    {
      "epoch": 0.6166166166166166,
      "grad_norm": 0.2158333659172058,
      "learning_rate": 0.00018382797052177746,
      "loss": 0.655,
      "step": 77
    },
    {
      "epoch": 0.6246246246246246,
      "grad_norm": 0.25565382838249207,
      "learning_rate": 0.000183355577183857,
      "loss": 0.6299,
      "step": 78
    },
    {
      "epoch": 0.6326326326326326,
      "grad_norm": 0.20636747777462006,
      "learning_rate": 0.00018287700871745036,
      "loss": 0.6283,
      "step": 79
    },
    {
      "epoch": 0.6406406406406406,
      "grad_norm": 0.21258121728897095,
      "learning_rate": 0.00018239230057575542,
      "loss": 0.6174,
      "step": 80
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 0.2861458957195282,
      "learning_rate": 0.00018190148866680802,
      "loss": 0.6547,
      "step": 81
    },
    {
      "epoch": 0.6566566566566566,
      "grad_norm": 0.23667441308498383,
      "learning_rate": 0.0001814046093508218,
      "loss": 0.6416,
      "step": 82
    },
    {
      "epoch": 0.6646646646646647,
      "grad_norm": 0.23191799223423004,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.642,
      "step": 83
    },
    {
      "epoch": 0.6726726726726727,
      "grad_norm": 0.2622171938419342,
      "learning_rate": 0.00018039279618328212,
      "loss": 0.6241,
      "step": 84
    },
    {
      "epoch": 0.6806806806806807,
      "grad_norm": 0.2891266345977783,
      "learning_rate": 0.00017987793728863651,
      "loss": 0.6284,
      "step": 85
    },
    {
      "epoch": 0.6886886886886887,
      "grad_norm": 0.26767420768737793,
      "learning_rate": 0.00017935716089521474,
      "loss": 0.627,
      "step": 86
    },
    {
      "epoch": 0.6966966966966966,
      "grad_norm": 0.2828672230243683,
      "learning_rate": 0.00017883050558305255,
      "loss": 0.6418,
      "step": 87
    },
    {
      "epoch": 0.7047047047047047,
      "grad_norm": 0.32730573415756226,
      "learning_rate": 0.00017829801036770628,
      "loss": 0.6629,
      "step": 88
    },
    {
      "epoch": 0.7127127127127127,
      "grad_norm": 0.24029900133609772,
      "learning_rate": 0.0001777597146973627,
      "loss": 0.614,
      "step": 89
    },
    {
      "epoch": 0.7207207207207207,
      "grad_norm": 0.2929212152957916,
      "learning_rate": 0.00017721565844991643,
      "loss": 0.632,
      "step": 90
    },
    {
      "epoch": 0.7287287287287287,
      "grad_norm": 0.2860666513442993,
      "learning_rate": 0.00017666588193001595,
      "loss": 0.6289,
      "step": 91
    },
    {
      "epoch": 0.7367367367367368,
      "grad_norm": 0.23325330018997192,
      "learning_rate": 0.00017611042586607748,
      "loss": 0.6392,
      "step": 92
    },
    {
      "epoch": 0.7447447447447447,
      "grad_norm": 0.3126169443130493,
      "learning_rate": 0.00017554933140726802,
      "loss": 0.6422,
      "step": 93
    },
    {
      "epoch": 0.7527527527527528,
      "grad_norm": 0.26704883575439453,
      "learning_rate": 0.00017498264012045687,
      "loss": 0.6166,
      "step": 94
    },
    {
      "epoch": 0.7607607607607607,
      "grad_norm": 0.2184283286333084,
      "learning_rate": 0.00017441039398713608,
      "loss": 0.6235,
      "step": 95
    },
    {
      "epoch": 0.7687687687687688,
      "grad_norm": 0.23906390368938446,
      "learning_rate": 0.00017383263540031067,
      "loss": 0.6643,
      "step": 96
    },
    {
      "epoch": 0.7767767767767768,
      "grad_norm": 0.26839691400527954,
      "learning_rate": 0.0001732494071613579,
      "loss": 0.6514,
      "step": 97
    },
    {
      "epoch": 0.7847847847847848,
      "grad_norm": 0.2805701494216919,
      "learning_rate": 0.00017266075247685656,
      "loss": 0.6168,
      "step": 98
    },
    {
      "epoch": 0.7927927927927928,
      "grad_norm": 0.21650992333889008,
      "learning_rate": 0.00017206671495538612,
      "loss": 0.5983,
      "step": 99
    },
    {
      "epoch": 0.8008008008008008,
      "grad_norm": 0.2302800416946411,
      "learning_rate": 0.00017146733860429612,
      "loss": 0.6301,
      "step": 100
    },
    {
      "epoch": 0.8088088088088088,
      "grad_norm": 0.29078415036201477,
      "learning_rate": 0.000170862667826446,
      "loss": 0.616,
      "step": 101
    },
    {
      "epoch": 0.8168168168168168,
      "grad_norm": 0.24860034883022308,
      "learning_rate": 0.0001702527474169157,
      "loss": 0.6352,
      "step": 102
    },
    {
      "epoch": 0.8248248248248248,
      "grad_norm": 0.26281973719596863,
      "learning_rate": 0.00016963762255968722,
      "loss": 0.6218,
      "step": 103
    },
    {
      "epoch": 0.8328328328328328,
      "grad_norm": 0.29051998257637024,
      "learning_rate": 0.0001690173388242972,
      "loss": 0.6233,
      "step": 104
    },
    {
      "epoch": 0.8408408408408409,
      "grad_norm": 0.2471507042646408,
      "learning_rate": 0.00016839194216246108,
      "loss": 0.6147,
      "step": 105
    },
    {
      "epoch": 0.8488488488488488,
      "grad_norm": 0.2574704587459564,
      "learning_rate": 0.0001677614789046689,
      "loss": 0.6174,
      "step": 106
    },
    {
      "epoch": 0.8568568568568569,
      "grad_norm": 0.2551233172416687,
      "learning_rate": 0.00016712599575675316,
      "loss": 0.5989,
      "step": 107
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 0.2901318371295929,
      "learning_rate": 0.00016648553979642868,
      "loss": 0.6241,
      "step": 108
    },
    {
      "epoch": 0.8728728728728729,
      "grad_norm": 0.23769080638885498,
      "learning_rate": 0.0001658401584698049,
      "loss": 0.6044,
      "step": 109
    },
    {
      "epoch": 0.8808808808808809,
      "grad_norm": 0.2580976188182831,
      "learning_rate": 0.00016518989958787126,
      "loss": 0.622,
      "step": 110
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.24077744781970978,
      "learning_rate": 0.00016453481132295506,
      "loss": 0.6047,
      "step": 111
    },
    {
      "epoch": 0.8968968968968969,
      "grad_norm": 0.228902667760849,
      "learning_rate": 0.00016387494220515274,
      "loss": 0.6138,
      "step": 112
    },
    {
      "epoch": 0.9049049049049049,
      "grad_norm": 0.2607581317424774,
      "learning_rate": 0.00016321034111873488,
      "loss": 0.6307,
      "step": 113
    },
    {
      "epoch": 0.9129129129129129,
      "grad_norm": 0.2575569450855255,
      "learning_rate": 0.00016254105729852464,
      "loss": 0.6008,
      "step": 114
    },
    {
      "epoch": 0.9209209209209209,
      "grad_norm": 0.231553852558136,
      "learning_rate": 0.00016186714032625035,
      "loss": 0.617,
      "step": 115
    },
    {
      "epoch": 0.928928928928929,
      "grad_norm": 0.24820354580879211,
      "learning_rate": 0.00016118864012687245,
      "loss": 0.5991,
      "step": 116
    },
    {
      "epoch": 0.9369369369369369,
      "grad_norm": 0.2364109754562378,
      "learning_rate": 0.00016050560696488492,
      "loss": 0.6094,
      "step": 117
    },
    {
      "epoch": 0.944944944944945,
      "grad_norm": 0.2492029368877411,
      "learning_rate": 0.00015981809144059166,
      "loss": 0.6143,
      "step": 118
    },
    {
      "epoch": 0.9529529529529529,
      "grad_norm": 0.27745717763900757,
      "learning_rate": 0.00015912614448635782,
      "loss": 0.6203,
      "step": 119
    },
    {
      "epoch": 0.960960960960961,
      "grad_norm": 0.2555610239505768,
      "learning_rate": 0.00015842981736283686,
      "loss": 0.6314,
      "step": 120
    },
    {
      "epoch": 0.968968968968969,
      "grad_norm": 0.2268420308828354,
      "learning_rate": 0.00015772916165517273,
      "loss": 0.6155,
      "step": 121
    },
    {
      "epoch": 0.9769769769769769,
      "grad_norm": 0.250041127204895,
      "learning_rate": 0.00015702422926917872,
      "loss": 0.6226,
      "step": 122
    },
    {
      "epoch": 0.984984984984985,
      "grad_norm": 0.2596072554588318,
      "learning_rate": 0.00015631507242749187,
      "loss": 0.6086,
      "step": 123
    },
    {
      "epoch": 0.992992992992993,
      "grad_norm": 0.2280743271112442,
      "learning_rate": 0.00015560174366570446,
      "loss": 0.5994,
      "step": 124
    },
    {
      "epoch": 1.001001001001001,
      "grad_norm": 0.23362237215042114,
      "learning_rate": 0.00015488429582847192,
      "loss": 0.616,
      "step": 125
    },
    {
      "epoch": 1.006,
      "grad_norm": 0.2956937849521637,
      "learning_rate": 0.00015416278206559816,
      "loss": 0.6038,
      "step": 126
    },
    {
      "epoch": 1.014,
      "grad_norm": 0.250629723072052,
      "learning_rate": 0.0001534372558280979,
      "loss": 0.5991,
      "step": 127
    },
    {
      "epoch": 1.022,
      "grad_norm": 0.231906458735466,
      "learning_rate": 0.00015270777086423722,
      "loss": 0.6088,
      "step": 128
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.2888093590736389,
      "learning_rate": 0.0001519743812155516,
      "loss": 0.5892,
      "step": 129
    },
    {
      "epoch": 1.038,
      "grad_norm": 0.24940524995326996,
      "learning_rate": 0.0001512371412128424,
      "loss": 0.5982,
      "step": 130
    },
    {
      "epoch": 1.046,
      "grad_norm": 0.24017778038978577,
      "learning_rate": 0.00015049610547215205,
      "loss": 0.5608,
      "step": 131
    },
    {
      "epoch": 1.054,
      "grad_norm": 0.2334035485982895,
      "learning_rate": 0.00014975132889071807,
      "loss": 0.6034,
      "step": 132
    },
    {
      "epoch": 1.062,
      "grad_norm": 0.2773897349834442,
      "learning_rate": 0.00014900286664290592,
      "loss": 0.6387,
      "step": 133
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.24266445636749268,
      "learning_rate": 0.00014825077417612186,
      "loss": 0.5612,
      "step": 134
    },
    {
      "epoch": 1.078,
      "grad_norm": 0.22919470071792603,
      "learning_rate": 0.00014749510720670506,
      "loss": 0.599,
      "step": 135
    },
    {
      "epoch": 1.086,
      "grad_norm": 0.23829148709774017,
      "learning_rate": 0.00014673592171580025,
      "loss": 0.6066,
      "step": 136
    },
    {
      "epoch": 1.094,
      "grad_norm": 0.31981223821640015,
      "learning_rate": 0.00014597327394521044,
      "loss": 0.5692,
      "step": 137
    },
    {
      "epoch": 1.102,
      "grad_norm": 0.2747564911842346,
      "learning_rate": 0.00014520722039323045,
      "loss": 0.62,
      "step": 138
    },
    {
      "epoch": 1.11,
      "grad_norm": 0.2592499852180481,
      "learning_rate": 0.00014443781781046136,
      "loss": 0.5937,
      "step": 139
    },
    {
      "epoch": 1.1179999999999999,
      "grad_norm": 0.31891530752182007,
      "learning_rate": 0.0001436651231956064,
      "loss": 0.5973,
      "step": 140
    },
    {
      "epoch": 1.126,
      "grad_norm": 0.2743702232837677,
      "learning_rate": 0.00014288919379124837,
      "loss": 0.6045,
      "step": 141
    },
    {
      "epoch": 1.134,
      "grad_norm": 0.2665708661079407,
      "learning_rate": 0.00014211008707960897,
      "loss": 0.5898,
      "step": 142
    },
    {
      "epoch": 1.142,
      "grad_norm": 0.33267003297805786,
      "learning_rate": 0.00014132786077829043,
      "loss": 0.5945,
      "step": 143
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.28636589646339417,
      "learning_rate": 0.00014054257283599973,
      "loss": 0.5914,
      "step": 144
    },
    {
      "epoch": 1.158,
      "grad_norm": 0.27305400371551514,
      "learning_rate": 0.0001397542814282556,
      "loss": 0.6093,
      "step": 145
    },
    {
      "epoch": 1.166,
      "grad_norm": 0.2839919924736023,
      "learning_rate": 0.0001389630449530788,
      "loss": 0.6074,
      "step": 146
    },
    {
      "epoch": 1.174,
      "grad_norm": 0.25652188062667847,
      "learning_rate": 0.0001381689220266659,
      "loss": 0.6059,
      "step": 147
    },
    {
      "epoch": 1.182,
      "grad_norm": 0.2549704909324646,
      "learning_rate": 0.0001373719714790469,
      "loss": 0.5568,
      "step": 148
    },
    {
      "epoch": 1.19,
      "grad_norm": 0.2509196400642395,
      "learning_rate": 0.00013657225234972695,
      "loss": 0.5968,
      "step": 149
    },
    {
      "epoch": 1.198,
      "grad_norm": 0.25909289717674255,
      "learning_rate": 0.0001357698238833126,
      "loss": 0.5902,
      "step": 150
    },
    {
      "epoch": 1.206,
      "grad_norm": 0.26162394881248474,
      "learning_rate": 0.00013496474552512287,
      "loss": 0.5763,
      "step": 151
    },
    {
      "epoch": 1.214,
      "grad_norm": 0.2721655070781708,
      "learning_rate": 0.00013415707691678556,
      "loss": 0.6037,
      "step": 152
    },
    {
      "epoch": 1.222,
      "grad_norm": 0.28691592812538147,
      "learning_rate": 0.0001333468778918187,
      "loss": 0.625,
      "step": 153
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.25801119208335876,
      "learning_rate": 0.00013253420847119803,
      "loss": 0.5994,
      "step": 154
    },
    {
      "epoch": 1.238,
      "grad_norm": 0.2609824538230896,
      "learning_rate": 0.00013171912885891063,
      "loss": 0.5999,
      "step": 155
    },
    {
      "epoch": 1.246,
      "grad_norm": 0.2631840407848358,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.5844,
      "step": 156
    },
    {
      "epoch": 1.254,
      "grad_norm": 0.2862647473812103,
      "learning_rate": 0.00013008198076356676,
      "loss": 0.5653,
      "step": 157
    },
    {
      "epoch": 1.262,
      "grad_norm": 0.27327024936676025,
      "learning_rate": 0.00012926003356333488,
      "loss": 0.5933,
      "step": 158
    },
    {
      "epoch": 1.27,
      "grad_norm": 0.2684379518032074,
      "learning_rate": 0.0001284359187281004,
      "loss": 0.5842,
      "step": 159
    },
    {
      "epoch": 1.278,
      "grad_norm": 0.2620231807231903,
      "learning_rate": 0.00012760969730974694,
      "loss": 0.6079,
      "step": 160
    },
    {
      "epoch": 1.286,
      "grad_norm": 0.2584543526172638,
      "learning_rate": 0.00012678143051621742,
      "loss": 0.5941,
      "step": 161
    },
    {
      "epoch": 1.294,
      "grad_norm": 0.26279789209365845,
      "learning_rate": 0.00012595117970697997,
      "loss": 0.6086,
      "step": 162
    },
    {
      "epoch": 1.302,
      "grad_norm": 0.2541520893573761,
      "learning_rate": 0.00012511900638848195,
      "loss": 0.5907,
      "step": 163
    },
    {
      "epoch": 1.31,
      "grad_norm": 0.27384746074676514,
      "learning_rate": 0.0001242849722095936,
      "loss": 0.6055,
      "step": 164
    },
    {
      "epoch": 1.318,
      "grad_norm": 0.25682300329208374,
      "learning_rate": 0.00012344913895704097,
      "loss": 0.609,
      "step": 165
    },
    {
      "epoch": 1.326,
      "grad_norm": 0.25404492020606995,
      "learning_rate": 0.00012261156855082882,
      "loss": 0.6121,
      "step": 166
    },
    {
      "epoch": 1.334,
      "grad_norm": 0.2649850845336914,
      "learning_rate": 0.0001217723230396532,
      "loss": 0.5695,
      "step": 167
    },
    {
      "epoch": 1.342,
      "grad_norm": 0.28349268436431885,
      "learning_rate": 0.00012093146459630487,
      "loss": 0.5883,
      "step": 168
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.27068182826042175,
      "learning_rate": 0.00012008905551306356,
      "loss": 0.6147,
      "step": 169
    },
    {
      "epoch": 1.358,
      "grad_norm": 0.29566338658332825,
      "learning_rate": 0.000119245158197083,
      "loss": 0.5901,
      "step": 170
    },
    {
      "epoch": 1.366,
      "grad_norm": 0.27946797013282776,
      "learning_rate": 0.00011839983516576802,
      "loss": 0.5831,
      "step": 171
    },
    {
      "epoch": 1.374,
      "grad_norm": 0.25005409121513367,
      "learning_rate": 0.00011755314904214284,
      "loss": 0.5656,
      "step": 172
    },
    {
      "epoch": 1.3820000000000001,
      "grad_norm": 0.2621053159236908,
      "learning_rate": 0.00011670516255021193,
      "loss": 0.5769,
      "step": 173
    },
    {
      "epoch": 1.3900000000000001,
      "grad_norm": 0.2531629502773285,
      "learning_rate": 0.00011585593851031347,
      "loss": 0.5641,
      "step": 174
    },
    {
      "epoch": 1.3980000000000001,
      "grad_norm": 0.3026553690433502,
      "learning_rate": 0.00011500553983446527,
      "loss": 0.6038,
      "step": 175
    },
    {
      "epoch": 1.4060000000000001,
      "grad_norm": 0.2748616337776184,
      "learning_rate": 0.00011415402952170433,
      "loss": 0.5808,
      "step": 176
    },
    {
      "epoch": 1.414,
      "grad_norm": 0.27345311641693115,
      "learning_rate": 0.0001133014706534196,
      "loss": 0.5848,
      "step": 177
    },
    {
      "epoch": 1.422,
      "grad_norm": 0.273357629776001,
      "learning_rate": 0.00011244792638867893,
      "loss": 0.5906,
      "step": 178
    },
    {
      "epoch": 1.43,
      "grad_norm": 0.26230183243751526,
      "learning_rate": 0.00011159345995955006,
      "loss": 0.5886,
      "step": 179
    },
    {
      "epoch": 1.438,
      "grad_norm": 0.2515832483768463,
      "learning_rate": 0.00011073813466641632,
      "loss": 0.5876,
      "step": 180
    },
    {
      "epoch": 1.446,
      "grad_norm": 0.27451092004776,
      "learning_rate": 0.00010988201387328717,
      "loss": 0.5841,
      "step": 181
    },
    {
      "epoch": 1.454,
      "grad_norm": 0.2588571012020111,
      "learning_rate": 0.00010902516100310411,
      "loss": 0.5674,
      "step": 182
    },
    {
      "epoch": 1.462,
      "grad_norm": 0.2440604865550995,
      "learning_rate": 0.00010816763953304227,
      "loss": 0.5646,
      "step": 183
    },
    {
      "epoch": 1.47,
      "grad_norm": 0.2681560516357422,
      "learning_rate": 0.00010730951298980776,
      "loss": 0.5671,
      "step": 184
    },
    {
      "epoch": 1.478,
      "grad_norm": 0.297048419713974,
      "learning_rate": 0.00010645084494493165,
      "loss": 0.583,
      "step": 185
    },
    {
      "epoch": 1.486,
      "grad_norm": 0.29275089502334595,
      "learning_rate": 0.00010559169901006034,
      "loss": 0.6007,
      "step": 186
    },
    {
      "epoch": 1.494,
      "grad_norm": 0.2599998414516449,
      "learning_rate": 0.0001047321388322432,
      "loss": 0.5692,
      "step": 187
    },
    {
      "epoch": 1.502,
      "grad_norm": 0.2714841663837433,
      "learning_rate": 0.00010387222808921746,
      "loss": 0.5996,
      "step": 188
    },
    {
      "epoch": 1.51,
      "grad_norm": 0.2618089020252228,
      "learning_rate": 0.00010301203048469083,
      "loss": 0.5861,
      "step": 189
    },
    {
      "epoch": 1.518,
      "grad_norm": 0.27270275354385376,
      "learning_rate": 0.00010215160974362223,
      "loss": 0.5771,
      "step": 190
    },
    {
      "epoch": 1.526,
      "grad_norm": 0.2583703398704529,
      "learning_rate": 0.00010129102960750092,
      "loss": 0.5897,
      "step": 191
    },
    {
      "epoch": 1.534,
      "grad_norm": 0.25854265689849854,
      "learning_rate": 0.00010043035382962443,
      "loss": 0.5778,
      "step": 192
    },
    {
      "epoch": 1.542,
      "grad_norm": 0.27234703302383423,
      "learning_rate": 9.956964617037558e-05,
      "loss": 0.5659,
      "step": 193
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.2672337293624878,
      "learning_rate": 9.870897039249911e-05,
      "loss": 0.5792,
      "step": 194
    },
    {
      "epoch": 1.558,
      "grad_norm": 0.2644350528717041,
      "learning_rate": 9.784839025637778e-05,
      "loss": 0.5798,
      "step": 195
    },
    {
      "epoch": 1.5659999999999998,
      "grad_norm": 0.2572389543056488,
      "learning_rate": 9.698796951530919e-05,
      "loss": 0.6008,
      "step": 196
    },
    {
      "epoch": 1.5739999999999998,
      "grad_norm": 0.2693156898021698,
      "learning_rate": 9.612777191078258e-05,
      "loss": 0.5903,
      "step": 197
    },
    {
      "epoch": 1.5819999999999999,
      "grad_norm": 0.26244068145751953,
      "learning_rate": 9.526786116775682e-05,
      "loss": 0.569,
      "step": 198
    },
    {
      "epoch": 1.5899999999999999,
      "grad_norm": 0.25875815749168396,
      "learning_rate": 9.440830098993969e-05,
      "loss": 0.6042,
      "step": 199
    },
    {
      "epoch": 1.5979999999999999,
      "grad_norm": 0.27209436893463135,
      "learning_rate": 9.354915505506839e-05,
      "loss": 0.5846,
      "step": 200
    },
    {
      "epoch": 1.6059999999999999,
      "grad_norm": 0.270780473947525,
      "learning_rate": 9.269048701019226e-05,
      "loss": 0.5957,
      "step": 201
    },
    {
      "epoch": 1.6139999999999999,
      "grad_norm": 0.25013670325279236,
      "learning_rate": 9.183236046695777e-05,
      "loss": 0.5845,
      "step": 202
    },
    {
      "epoch": 1.6219999999999999,
      "grad_norm": 0.2716957628726959,
      "learning_rate": 9.09748389968959e-05,
      "loss": 0.5584,
      "step": 203
    },
    {
      "epoch": 1.63,
      "grad_norm": 0.2737436890602112,
      "learning_rate": 9.011798612671286e-05,
      "loss": 0.5836,
      "step": 204
    },
    {
      "epoch": 1.638,
      "grad_norm": 0.2748481333255768,
      "learning_rate": 8.92618653335837e-05,
      "loss": 0.5927,
      "step": 205
    },
    {
      "epoch": 1.646,
      "grad_norm": 0.2642996609210968,
      "learning_rate": 8.840654004044996e-05,
      "loss": 0.6088,
      "step": 206
    },
    {
      "epoch": 1.654,
      "grad_norm": 0.26341068744659424,
      "learning_rate": 8.755207361132108e-05,
      "loss": 0.5841,
      "step": 207
    },
    {
      "epoch": 1.662,
      "grad_norm": 0.30515289306640625,
      "learning_rate": 8.669852934658042e-05,
      "loss": 0.5525,
      "step": 208
    },
    {
      "epoch": 1.67,
      "grad_norm": 0.2801468074321747,
      "learning_rate": 8.58459704782957e-05,
      "loss": 0.5547,
      "step": 209
    },
    {
      "epoch": 1.678,
      "grad_norm": 0.27618443965911865,
      "learning_rate": 8.499446016553474e-05,
      "loss": 0.5613,
      "step": 210
    },
    {
      "epoch": 1.686,
      "grad_norm": 0.26961931586265564,
      "learning_rate": 8.414406148968657e-05,
      "loss": 0.5639,
      "step": 211
    },
    {
      "epoch": 1.694,
      "grad_norm": 0.29023805260658264,
      "learning_rate": 8.32948374497881e-05,
      "loss": 0.5878,
      "step": 212
    },
    {
      "epoch": 1.702,
      "grad_norm": 0.2671249508857727,
      "learning_rate": 8.244685095785719e-05,
      "loss": 0.5743,
      "step": 213
    },
    {
      "epoch": 1.71,
      "grad_norm": 0.26124948263168335,
      "learning_rate": 8.160016483423199e-05,
      "loss": 0.5801,
      "step": 214
    },
    {
      "epoch": 1.718,
      "grad_norm": 0.2721916437149048,
      "learning_rate": 8.075484180291701e-05,
      "loss": 0.5975,
      "step": 215
    },
    {
      "epoch": 1.726,
      "grad_norm": 0.2630290687084198,
      "learning_rate": 7.991094448693648e-05,
      "loss": 0.5714,
      "step": 216
    },
    {
      "epoch": 1.734,
      "grad_norm": 0.25962400436401367,
      "learning_rate": 7.906853540369514e-05,
      "loss": 0.5912,
      "step": 217
    },
    {
      "epoch": 1.742,
      "grad_norm": 0.26142629981040955,
      "learning_rate": 7.822767696034682e-05,
      "loss": 0.577,
      "step": 218
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.26839005947113037,
      "learning_rate": 7.738843144917119e-05,
      "loss": 0.5747,
      "step": 219
    },
    {
      "epoch": 1.758,
      "grad_norm": 0.28053659200668335,
      "learning_rate": 7.655086104295904e-05,
      "loss": 0.612,
      "step": 220
    },
    {
      "epoch": 1.766,
      "grad_norm": 0.2728564143180847,
      "learning_rate": 7.571502779040645e-05,
      "loss": 0.5895,
      "step": 221
    },
    {
      "epoch": 1.774,
      "grad_norm": 0.26337721943855286,
      "learning_rate": 7.48809936115181e-05,
      "loss": 0.5666,
      "step": 222
    },
    {
      "epoch": 1.782,
      "grad_norm": 0.2544887661933899,
      "learning_rate": 7.404882029302003e-05,
      "loss": 0.5552,
      "step": 223
    },
    {
      "epoch": 1.79,
      "grad_norm": 0.2690827250480652,
      "learning_rate": 7.321856948378259e-05,
      "loss": 0.5559,
      "step": 224
    },
    {
      "epoch": 1.798,
      "grad_norm": 0.27959364652633667,
      "learning_rate": 7.239030269025311e-05,
      "loss": 0.5738,
      "step": 225
    },
    {
      "epoch": 1.806,
      "grad_norm": 0.29118430614471436,
      "learning_rate": 7.156408127189965e-05,
      "loss": 0.5753,
      "step": 226
    },
    {
      "epoch": 1.814,
      "grad_norm": 0.2585116922855377,
      "learning_rate": 7.073996643666517e-05,
      "loss": 0.5499,
      "step": 227
    },
    {
      "epoch": 1.822,
      "grad_norm": 0.24918395280838013,
      "learning_rate": 6.991801923643324e-05,
      "loss": 0.5792,
      "step": 228
    },
    {
      "epoch": 1.83,
      "grad_norm": 0.2664697766304016,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.582,
      "step": 229
    },
    {
      "epoch": 1.838,
      "grad_norm": 0.2679463326931,
      "learning_rate": 6.82808711410894e-05,
      "loss": 0.5919,
      "step": 230
    },
    {
      "epoch": 1.846,
      "grad_norm": 0.26800620555877686,
      "learning_rate": 6.746579152880201e-05,
      "loss": 0.5774,
      "step": 231
    },
    {
      "epoch": 1.854,
      "grad_norm": 0.25649094581604004,
      "learning_rate": 6.665312210818131e-05,
      "loss": 0.5569,
      "step": 232
    },
    {
      "epoch": 1.862,
      "grad_norm": 0.2661426067352295,
      "learning_rate": 6.584292308321445e-05,
      "loss": 0.5759,
      "step": 233
    },
    {
      "epoch": 1.87,
      "grad_norm": 0.27011772990226746,
      "learning_rate": 6.503525447487715e-05,
      "loss": 0.5752,
      "step": 234
    },
    {
      "epoch": 1.8780000000000001,
      "grad_norm": 0.28006768226623535,
      "learning_rate": 6.423017611668745e-05,
      "loss": 0.5873,
      "step": 235
    },
    {
      "epoch": 1.8860000000000001,
      "grad_norm": 0.281974196434021,
      "learning_rate": 6.342774765027309e-05,
      "loss": 0.5868,
      "step": 236
    },
    {
      "epoch": 1.8940000000000001,
      "grad_norm": 0.28022536635398865,
      "learning_rate": 6.262802852095311e-05,
      "loss": 0.5505,
      "step": 237
    },
    {
      "epoch": 1.9020000000000001,
      "grad_norm": 0.2971389889717102,
      "learning_rate": 6.18310779733341e-05,
      "loss": 0.5879,
      "step": 238
    },
    {
      "epoch": 1.9100000000000001,
      "grad_norm": 0.2779372036457062,
      "learning_rate": 6.103695504692122e-05,
      "loss": 0.5648,
      "step": 239
    },
    {
      "epoch": 1.9180000000000001,
      "grad_norm": 0.3032248616218567,
      "learning_rate": 6.024571857174443e-05,
      "loss": 0.5884,
      "step": 240
    },
    {
      "epoch": 1.9260000000000002,
      "grad_norm": 0.26035642623901367,
      "learning_rate": 5.94574271640003e-05,
      "loss": 0.5837,
      "step": 241
    },
    {
      "epoch": 1.9340000000000002,
      "grad_norm": 0.2789236009120941,
      "learning_rate": 5.8672139221709577e-05,
      "loss": 0.5745,
      "step": 242
    },
    {
      "epoch": 1.942,
      "grad_norm": 0.27459922432899475,
      "learning_rate": 5.788991292039103e-05,
      "loss": 0.568,
      "step": 243
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.2857699394226074,
      "learning_rate": 5.7110806208751655e-05,
      "loss": 0.5619,
      "step": 244
    },
    {
      "epoch": 1.958,
      "grad_norm": 0.2715800106525421,
      "learning_rate": 5.633487680439361e-05,
      "loss": 0.5763,
      "step": 245
    },
    {
      "epoch": 1.966,
      "grad_norm": 0.27073079347610474,
      "learning_rate": 5.556218218953868e-05,
      "loss": 0.5815,
      "step": 246
    },
    {
      "epoch": 1.974,
      "grad_norm": 0.2630924880504608,
      "learning_rate": 5.479277960676958e-05,
      "loss": 0.5735,
      "step": 247
    },
    {
      "epoch": 1.982,
      "grad_norm": 0.2807694971561432,
      "learning_rate": 5.40267260547896e-05,
      "loss": 0.5611,
      "step": 248
    },
    {
      "epoch": 1.99,
      "grad_norm": 0.28481224179267883,
      "learning_rate": 5.326407828419979e-05,
      "loss": 0.5671,
      "step": 249
    },
    {
      "epoch": 1.998,
      "grad_norm": 0.27675607800483704,
      "learning_rate": 5.2504892793295e-05,
      "loss": 0.5825,
      "step": 250
    }
  ],
  "logging_steps": 1,
  "max_steps": 375,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 125,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.479651398516736e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}