{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09780548933308882,
  "eval_steps": 34,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004890274466654441,
      "grad_norm": 1.4216102361679077,
      "learning_rate": 6.666666666666667e-06,
      "loss": 3.258,
      "step": 1
    },
    {
      "epoch": 0.0004890274466654441,
      "eval_loss": 3.5600969791412354,
      "eval_runtime": 1313.2977,
      "eval_samples_per_second": 1.967,
      "eval_steps_per_second": 0.656,
      "step": 1
    },
    {
      "epoch": 0.0009780548933308881,
      "grad_norm": 1.504632830619812,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 3.8029,
      "step": 2
    },
    {
      "epoch": 0.0014670823399963323,
      "grad_norm": 1.6489232778549194,
      "learning_rate": 2e-05,
      "loss": 3.6594,
      "step": 3
    },
    {
      "epoch": 0.0019561097866617762,
      "grad_norm": 1.274643063545227,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 3.1495,
      "step": 4
    },
    {
      "epoch": 0.0024451372333272204,
      "grad_norm": 1.4067387580871582,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 3.6677,
      "step": 5
    },
    {
      "epoch": 0.0029341646799926646,
      "grad_norm": 1.7147626876831055,
      "learning_rate": 4e-05,
      "loss": 3.8075,
      "step": 6
    },
    {
      "epoch": 0.0034231921266581087,
      "grad_norm": 1.672584891319275,
      "learning_rate": 4.666666666666667e-05,
      "loss": 3.3499,
      "step": 7
    },
    {
      "epoch": 0.0039122195733235525,
      "grad_norm": 2.0120997428894043,
      "learning_rate": 5.333333333333333e-05,
      "loss": 4.2653,
      "step": 8
    },
    {
      "epoch": 0.004401247019988997,
      "grad_norm": 2.0601062774658203,
      "learning_rate": 6e-05,
      "loss": 3.3055,
      "step": 9
    },
    {
      "epoch": 0.004890274466654441,
      "grad_norm": 2.0153276920318604,
      "learning_rate": 6.666666666666667e-05,
      "loss": 3.1547,
      "step": 10
    },
    {
      "epoch": 0.005379301913319885,
      "grad_norm": 2.443328857421875,
      "learning_rate": 7.333333333333333e-05,
      "loss": 3.4654,
      "step": 11
    },
    {
      "epoch": 0.005868329359985329,
      "grad_norm": 2.801769971847534,
      "learning_rate": 8e-05,
      "loss": 2.8224,
      "step": 12
    },
    {
      "epoch": 0.006357356806650773,
      "grad_norm": 2.6738572120666504,
      "learning_rate": 8.666666666666667e-05,
      "loss": 2.8465,
      "step": 13
    },
    {
      "epoch": 0.0068463842533162175,
      "grad_norm": 2.8812367916107178,
      "learning_rate": 9.333333333333334e-05,
      "loss": 2.622,
      "step": 14
    },
    {
      "epoch": 0.007335411699981661,
      "grad_norm": 2.9697248935699463,
      "learning_rate": 0.0001,
      "loss": 2.9623,
      "step": 15
    },
    {
      "epoch": 0.007824439146647105,
      "grad_norm": 2.5231637954711914,
      "learning_rate": 0.00010666666666666667,
      "loss": 2.2665,
      "step": 16
    },
    {
      "epoch": 0.00831346659331255,
      "grad_norm": 2.341275691986084,
      "learning_rate": 0.00011333333333333334,
      "loss": 2.2247,
      "step": 17
    },
    {
      "epoch": 0.008802494039977994,
      "grad_norm": 2.683793306350708,
      "learning_rate": 0.00012,
      "loss": 1.9371,
      "step": 18
    },
    {
      "epoch": 0.009291521486643438,
      "grad_norm": 2.972334384918213,
      "learning_rate": 0.00012666666666666666,
      "loss": 1.8682,
      "step": 19
    },
    {
      "epoch": 0.009780548933308882,
      "grad_norm": 3.541074275970459,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.912,
      "step": 20
    },
    {
      "epoch": 0.010269576379974325,
      "grad_norm": 2.9546866416931152,
      "learning_rate": 0.00014,
      "loss": 1.6904,
      "step": 21
    },
    {
      "epoch": 0.01075860382663977,
      "grad_norm": 2.5912656784057617,
      "learning_rate": 0.00014666666666666666,
      "loss": 1.5096,
      "step": 22
    },
    {
      "epoch": 0.011247631273305215,
      "grad_norm": 2.258963108062744,
      "learning_rate": 0.00015333333333333334,
      "loss": 1.3978,
      "step": 23
    },
    {
      "epoch": 0.011736658719970658,
      "grad_norm": 2.275815725326538,
      "learning_rate": 0.00016,
      "loss": 1.1538,
      "step": 24
    },
    {
      "epoch": 0.012225686166636102,
      "grad_norm": 2.224825382232666,
      "learning_rate": 0.0001666666666666667,
      "loss": 1.471,
      "step": 25
    },
    {
      "epoch": 0.012714713613301546,
      "grad_norm": 1.876035451889038,
      "learning_rate": 0.00017333333333333334,
      "loss": 1.4368,
      "step": 26
    },
    {
      "epoch": 0.013203741059966991,
      "grad_norm": 1.6051979064941406,
      "learning_rate": 0.00018,
      "loss": 1.3951,
      "step": 27
    },
    {
      "epoch": 0.013692768506632435,
      "grad_norm": 1.7268619537353516,
      "learning_rate": 0.0001866666666666667,
      "loss": 1.1915,
      "step": 28
    },
    {
      "epoch": 0.014181795953297879,
      "grad_norm": 1.888218879699707,
      "learning_rate": 0.00019333333333333333,
      "loss": 1.1358,
      "step": 29
    },
    {
      "epoch": 0.014670823399963322,
      "grad_norm": 1.7404896020889282,
      "learning_rate": 0.0002,
      "loss": 1.2051,
      "step": 30
    },
    {
      "epoch": 0.015159850846628768,
      "grad_norm": 1.560935139656067,
      "learning_rate": 0.00019998292504580528,
      "loss": 1.1611,
      "step": 31
    },
    {
      "epoch": 0.01564887829329421,
      "grad_norm": 2.000502824783325,
      "learning_rate": 0.0001999317060143023,
      "loss": 1.4315,
      "step": 32
    },
    {
      "epoch": 0.016137905739959654,
      "grad_norm": 1.7972925901412964,
      "learning_rate": 0.0001998463603967434,
      "loss": 1.1507,
      "step": 33
    },
    {
      "epoch": 0.0166269331866251,
      "grad_norm": 1.4039409160614014,
      "learning_rate": 0.00019972691733857883,
      "loss": 1.1626,
      "step": 34
    },
    {
      "epoch": 0.0166269331866251,
      "eval_loss": 1.1705251932144165,
      "eval_runtime": 1316.0492,
      "eval_samples_per_second": 1.963,
      "eval_steps_per_second": 0.654,
      "step": 34
    },
    {
      "epoch": 0.017115960633290545,
      "grad_norm": 1.5077097415924072,
      "learning_rate": 0.00019957341762950344,
      "loss": 1.0223,
      "step": 35
    },
    {
      "epoch": 0.017604988079955988,
      "grad_norm": 1.4470211267471313,
      "learning_rate": 0.0001993859136895274,
      "loss": 1.0228,
      "step": 36
    },
    {
      "epoch": 0.018094015526621432,
      "grad_norm": 1.7781013250350952,
      "learning_rate": 0.00019916446955107428,
      "loss": 1.0388,
      "step": 37
    },
    {
      "epoch": 0.018583042973286876,
      "grad_norm": 1.8719812631607056,
      "learning_rate": 0.0001989091608371146,
      "loss": 1.0568,
      "step": 38
    },
    {
      "epoch": 0.01907207041995232,
      "grad_norm": 1.389418363571167,
      "learning_rate": 0.00019862007473534025,
      "loss": 1.2011,
      "step": 39
    },
    {
      "epoch": 0.019561097866617763,
      "grad_norm": 1.561482310295105,
      "learning_rate": 0.0001982973099683902,
      "loss": 1.2364,
      "step": 40
    },
    {
      "epoch": 0.020050125313283207,
      "grad_norm": 1.3894869089126587,
      "learning_rate": 0.0001979409767601366,
      "loss": 1.0156,
      "step": 41
    },
    {
      "epoch": 0.02053915275994865,
      "grad_norm": 1.2144147157669067,
      "learning_rate": 0.00019755119679804367,
      "loss": 0.9838,
      "step": 42
    },
    {
      "epoch": 0.021028180206614098,
      "grad_norm": 1.2613141536712646,
      "learning_rate": 0.0001971281031916114,
      "loss": 0.9763,
      "step": 43
    },
    {
      "epoch": 0.02151720765327954,
      "grad_norm": 1.316279649734497,
      "learning_rate": 0.00019667184042691875,
      "loss": 1.0909,
      "step": 44
    },
    {
      "epoch": 0.022006235099944985,
      "grad_norm": 1.4056583642959595,
      "learning_rate": 0.00019618256431728194,
      "loss": 1.2575,
      "step": 45
    },
    {
      "epoch": 0.02249526254661043,
      "grad_norm": 1.4552671909332275,
      "learning_rate": 0.0001956604419500441,
      "loss": 1.1668,
      "step": 46
    },
    {
      "epoch": 0.022984289993275873,
      "grad_norm": 1.2041035890579224,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.0945,
      "step": 47
    },
    {
      "epoch": 0.023473317439941317,
      "grad_norm": 1.2852847576141357,
      "learning_rate": 0.00019451838281608197,
      "loss": 1.1085,
      "step": 48
    },
    {
      "epoch": 0.02396234488660676,
      "grad_norm": 1.4202251434326172,
      "learning_rate": 0.00019389883606150566,
      "loss": 1.1757,
      "step": 49
    },
    {
      "epoch": 0.024451372333272204,
      "grad_norm": 1.2115014791488647,
      "learning_rate": 0.00019324722294043558,
      "loss": 1.0677,
      "step": 50
    },
    {
      "epoch": 0.024940399779937648,
      "grad_norm": 1.692592740058899,
      "learning_rate": 0.00019256376597815564,
      "loss": 0.9642,
      "step": 51
    },
    {
      "epoch": 0.02542942722660309,
      "grad_norm": 1.4862620830535889,
      "learning_rate": 0.00019184869857459232,
      "loss": 1.2206,
      "step": 52
    },
    {
      "epoch": 0.02591845467326854,
      "grad_norm": 1.3480483293533325,
      "learning_rate": 0.00019110226492460885,
      "loss": 1.0028,
      "step": 53
    },
    {
      "epoch": 0.026407482119933982,
      "grad_norm": 1.2847557067871094,
      "learning_rate": 0.0001903247199346129,
      "loss": 1.1267,
      "step": 54
    },
    {
      "epoch": 0.026896509566599426,
      "grad_norm": 1.1814807653427124,
      "learning_rate": 0.00018951632913550626,
      "loss": 0.963,
      "step": 55
    },
    {
      "epoch": 0.02738553701326487,
      "grad_norm": 1.348286747932434,
      "learning_rate": 0.0001886773685920062,
      "loss": 1.0553,
      "step": 56
    },
    {
      "epoch": 0.027874564459930314,
      "grad_norm": 1.2073681354522705,
      "learning_rate": 0.0001878081248083698,
      "loss": 1.0966,
      "step": 57
    },
    {
      "epoch": 0.028363591906595757,
      "grad_norm": 1.29014253616333,
      "learning_rate": 0.00018690889463055283,
      "loss": 1.2225,
      "step": 58
    },
    {
      "epoch": 0.0288526193532612,
      "grad_norm": 1.265650987625122,
      "learning_rate": 0.00018597998514483725,
      "loss": 0.9056,
      "step": 59
    },
    {
      "epoch": 0.029341646799926645,
      "grad_norm": 1.264709711074829,
      "learning_rate": 0.00018502171357296144,
      "loss": 1.1566,
      "step": 60
    },
    {
      "epoch": 0.02983067424659209,
      "grad_norm": 1.1395761966705322,
      "learning_rate": 0.00018403440716378928,
      "loss": 0.9825,
      "step": 61
    },
    {
      "epoch": 0.030319701693257536,
      "grad_norm": 1.1984392404556274,
      "learning_rate": 0.00018301840308155507,
      "loss": 1.1295,
      "step": 62
    },
    {
      "epoch": 0.03080872913992298,
      "grad_norm": 1.3706929683685303,
      "learning_rate": 0.00018197404829072215,
      "loss": 1.3507,
      "step": 63
    },
    {
      "epoch": 0.03129775658658842,
      "grad_norm": 1.0434547662734985,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.9119,
      "step": 64
    },
    {
      "epoch": 0.03178678403325386,
      "grad_norm": 1.2470561265945435,
      "learning_rate": 0.000179801722728024,
      "loss": 1.1485,
      "step": 65
    },
    {
      "epoch": 0.03227581147991931,
      "grad_norm": 1.2176910638809204,
      "learning_rate": 0.00017867449380334834,
      "loss": 1.0743,
      "step": 66
    },
    {
      "epoch": 0.03276483892658476,
      "grad_norm": 1.239547848701477,
      "learning_rate": 0.00017752039761111297,
      "loss": 1.0839,
      "step": 67
    },
    {
      "epoch": 0.0332538663732502,
      "grad_norm": 1.4201483726501465,
      "learning_rate": 0.00017633982827411032,
      "loss": 1.1837,
      "step": 68
    },
    {
      "epoch": 0.0332538663732502,
      "eval_loss": 1.062552571296692,
      "eval_runtime": 1315.0047,
      "eval_samples_per_second": 1.964,
      "eval_steps_per_second": 0.655,
      "step": 68
    },
    {
      "epoch": 0.033742893819915645,
      "grad_norm": 1.2789006233215332,
      "learning_rate": 0.00017513318895568737,
      "loss": 1.0102,
      "step": 69
    },
    {
      "epoch": 0.03423192126658109,
      "grad_norm": 1.3672975301742554,
      "learning_rate": 0.00017390089172206592,
      "loss": 1.3682,
      "step": 70
    },
    {
      "epoch": 0.03472094871324653,
      "grad_norm": 1.5209168195724487,
      "learning_rate": 0.00017264335740162242,
      "loss": 1.2258,
      "step": 71
    },
    {
      "epoch": 0.035209976159911976,
      "grad_norm": 1.3500794172286987,
      "learning_rate": 0.00017136101544117525,
      "loss": 1.2796,
      "step": 72
    },
    {
      "epoch": 0.03569900360657742,
      "grad_norm": 1.3323686122894287,
      "learning_rate": 0.0001700543037593291,
      "loss": 0.9231,
      "step": 73
    },
    {
      "epoch": 0.036188031053242864,
      "grad_norm": 1.4972914457321167,
      "learning_rate": 0.00016872366859692627,
      "loss": 1.2526,
      "step": 74
    },
    {
      "epoch": 0.03667705849990831,
      "grad_norm": 1.2735319137573242,
      "learning_rate": 0.00016736956436465573,
      "loss": 1.368,
      "step": 75
    },
    {
      "epoch": 0.03716608594657375,
      "grad_norm": 1.0858744382858276,
      "learning_rate": 0.0001659924534878723,
      "loss": 0.7402,
      "step": 76
    },
    {
      "epoch": 0.037655113393239195,
      "grad_norm": 1.3259844779968262,
      "learning_rate": 0.00016459280624867874,
      "loss": 0.9388,
      "step": 77
    },
    {
      "epoch": 0.03814414083990464,
      "grad_norm": 1.348748803138733,
      "learning_rate": 0.0001631711006253251,
      "loss": 1.2139,
      "step": 78
    },
    {
      "epoch": 0.03863316828657008,
      "grad_norm": 3.0502963066101074,
      "learning_rate": 0.0001617278221289793,
      "loss": 0.9326,
      "step": 79
    },
    {
      "epoch": 0.039122195733235526,
      "grad_norm": 1.213534951210022,
      "learning_rate": 0.00016026346363792567,
      "loss": 1.042,
      "step": 80
    },
    {
      "epoch": 0.03961122317990097,
      "grad_norm": 1.3361854553222656,
      "learning_rate": 0.00015877852522924732,
      "loss": 1.1104,
      "step": 81
    },
    {
      "epoch": 0.040100250626566414,
      "grad_norm": 1.0672283172607422,
      "learning_rate": 0.00015727351400805052,
      "loss": 0.7879,
      "step": 82
    },
    {
      "epoch": 0.04058927807323186,
      "grad_norm": 1.6033365726470947,
      "learning_rate": 0.00015574894393428855,
      "loss": 1.0356,
      "step": 83
    },
    {
      "epoch": 0.0410783055198973,
      "grad_norm": 1.579293131828308,
      "learning_rate": 0.00015420533564724495,
      "loss": 1.3671,
      "step": 84
    },
    {
      "epoch": 0.041567332966562745,
      "grad_norm": 3.389050006866455,
      "learning_rate": 0.0001526432162877356,
      "loss": 1.0248,
      "step": 85
    },
    {
      "epoch": 0.042056360413228196,
      "grad_norm": 1.3093312978744507,
      "learning_rate": 0.0001510631193180907,
      "loss": 1.017,
      "step": 86
    },
    {
      "epoch": 0.04254538785989364,
      "grad_norm": 2.124237537384033,
      "learning_rate": 0.0001494655843399779,
      "loss": 0.9459,
      "step": 87
    },
    {
      "epoch": 0.04303441530655908,
      "grad_norm": 1.416883111000061,
      "learning_rate": 0.00014785115691012864,
      "loss": 1.0393,
      "step": 88
    },
    {
      "epoch": 0.04352344275322453,
      "grad_norm": 1.1954100131988525,
      "learning_rate": 0.00014622038835403133,
      "loss": 1.4326,
      "step": 89
    },
    {
      "epoch": 0.04401247019988997,
      "grad_norm": 1.1562423706054688,
      "learning_rate": 0.00014457383557765386,
      "loss": 0.9829,
      "step": 90
    },
    {
      "epoch": 0.044501497646555414,
      "grad_norm": 1.9508070945739746,
      "learning_rate": 0.0001429120608772609,
      "loss": 1.1847,
      "step": 91
    },
    {
      "epoch": 0.04499052509322086,
      "grad_norm": 1.0829613208770752,
      "learning_rate": 0.00014123563174739037,
      "loss": 1.0758,
      "step": 92
    },
    {
      "epoch": 0.0454795525398863,
      "grad_norm": 1.0986757278442383,
      "learning_rate": 0.00013954512068705424,
      "loss": 0.9567,
      "step": 93
    },
    {
      "epoch": 0.045968579986551746,
      "grad_norm": 1.0479655265808105,
      "learning_rate": 0.00013784110500423104,
      "loss": 0.8693,
      "step": 94
    },
    {
      "epoch": 0.04645760743321719,
      "grad_norm": 1.2674229145050049,
      "learning_rate": 0.00013612416661871533,
      "loss": 1.0495,
      "step": 95
    },
    {
      "epoch": 0.04694663487988263,
      "grad_norm": 1.1395543813705444,
      "learning_rate": 0.00013439489186339282,
      "loss": 0.9213,
      "step": 96
    },
    {
      "epoch": 0.04743566232654808,
      "grad_norm": 1.1885366439819336,
      "learning_rate": 0.0001326538712840083,
      "loss": 0.9957,
      "step": 97
    },
    {
      "epoch": 0.04792468977321352,
      "grad_norm": 1.3940829038619995,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.056,
      "step": 98
    },
    {
      "epoch": 0.048413717219878964,
      "grad_norm": 1.4555394649505615,
      "learning_rate": 0.00012913897468893248,
      "loss": 1.1525,
      "step": 99
    },
    {
      "epoch": 0.04890274466654441,
      "grad_norm": 1.1065882444381714,
      "learning_rate": 0.0001273662990072083,
      "loss": 0.8194,
      "step": 100
    },
    {
      "epoch": 0.04939177211320985,
      "grad_norm": 1.2166293859481812,
      "learning_rate": 0.00012558427775944357,
      "loss": 1.198,
      "step": 101
    },
    {
      "epoch": 0.049880799559875295,
      "grad_norm": 1.2149029970169067,
      "learning_rate": 0.00012379351950426187,
      "loss": 0.9292,
      "step": 102
    },
    {
      "epoch": 0.049880799559875295,
      "eval_loss": 1.0268832445144653,
      "eval_runtime": 1315.1963,
      "eval_samples_per_second": 1.964,
      "eval_steps_per_second": 0.655,
      "step": 102
    },
    {
      "epoch": 0.05036982700654074,
      "grad_norm": 1.1670883893966675,
      "learning_rate": 0.00012199463578396688,
      "loss": 0.8447,
      "step": 103
    },
    {
      "epoch": 0.05085885445320618,
      "grad_norm": 1.4905412197113037,
      "learning_rate": 0.00012018824091570103,
      "loss": 1.2532,
      "step": 104
    },
    {
      "epoch": 0.051347881899871634,
      "grad_norm": 1.334544062614441,
      "learning_rate": 0.00011837495178165706,
      "loss": 0.7804,
      "step": 105
    },
    {
      "epoch": 0.05183690934653708,
      "grad_norm": 1.6085052490234375,
      "learning_rate": 0.000116555387618413,
      "loss": 1.093,
      "step": 106
    },
    {
      "epoch": 0.05232593679320252,
      "grad_norm": 1.4606610536575317,
      "learning_rate": 0.00011473016980546377,
      "loss": 1.0967,
      "step": 107
    },
    {
      "epoch": 0.052814964239867965,
      "grad_norm": 1.591978669166565,
      "learning_rate": 0.00011289992165302035,
      "loss": 1.1526,
      "step": 108
    },
    {
      "epoch": 0.05330399168653341,
      "grad_norm": 1.4087272882461548,
      "learning_rate": 0.00011106526818915008,
      "loss": 1.1814,
      "step": 109
    },
    {
      "epoch": 0.05379301913319885,
      "grad_norm": 1.3588765859603882,
      "learning_rate": 0.00010922683594633021,
      "loss": 1.11,
      "step": 110
    },
    {
      "epoch": 0.054282046579864296,
      "grad_norm": 1.154991865158081,
      "learning_rate": 0.00010738525274748741,
      "loss": 0.9469,
      "step": 111
    },
    {
      "epoch": 0.05477107402652974,
      "grad_norm": 1.1687790155410767,
      "learning_rate": 0.000105541147491597,
      "loss": 1.1575,
      "step": 112
    },
    {
      "epoch": 0.05526010147319518,
      "grad_norm": 1.1781808137893677,
      "learning_rate": 0.00010369514993891452,
      "loss": 1.0453,
      "step": 113
    },
    {
      "epoch": 0.05574912891986063,
      "grad_norm": 1.1359920501708984,
      "learning_rate": 0.00010184789049591299,
      "loss": 1.072,
      "step": 114
    },
    {
      "epoch": 0.05623815636652607,
      "grad_norm": 1.2046093940734863,
      "learning_rate": 0.0001,
      "loss": 0.921,
      "step": 115
    },
    {
      "epoch": 0.056727183813191515,
      "grad_norm": 1.1520406007766724,
      "learning_rate": 9.815210950408704e-05,
      "loss": 0.9206,
      "step": 116
    },
    {
      "epoch": 0.05721621125985696,
      "grad_norm": 1.240869402885437,
      "learning_rate": 9.630485006108553e-05,
      "loss": 1.0142,
      "step": 117
    },
    {
      "epoch": 0.0577052387065224,
      "grad_norm": 1.4092172384262085,
      "learning_rate": 9.4458852508403e-05,
      "loss": 1.2377,
      "step": 118
    },
    {
      "epoch": 0.058194266153187846,
      "grad_norm": 1.3101301193237305,
      "learning_rate": 9.261474725251261e-05,
      "loss": 1.1154,
      "step": 119
    },
    {
      "epoch": 0.05868329359985329,
      "grad_norm": 1.2811529636383057,
      "learning_rate": 9.077316405366981e-05,
      "loss": 0.9481,
      "step": 120
    },
    {
      "epoch": 0.05917232104651873,
      "grad_norm": 1.3437144756317139,
      "learning_rate": 8.893473181084994e-05,
      "loss": 1.1713,
      "step": 121
    },
    {
      "epoch": 0.05966134849318418,
      "grad_norm": 1.3384225368499756,
      "learning_rate": 8.710007834697969e-05,
      "loss": 1.0073,
      "step": 122
    },
    {
      "epoch": 0.06015037593984962,
      "grad_norm": 1.2030497789382935,
      "learning_rate": 8.526983019453623e-05,
      "loss": 1.2027,
      "step": 123
    },
    {
      "epoch": 0.06063940338651507,
      "grad_norm": 1.4308159351348877,
      "learning_rate": 8.344461238158699e-05,
      "loss": 1.0608,
      "step": 124
    },
    {
      "epoch": 0.061128430833180515,
      "grad_norm": 1.2718294858932495,
      "learning_rate": 8.162504821834295e-05,
      "loss": 1.0317,
      "step": 125
    },
    {
      "epoch": 0.06161745827984596,
      "grad_norm": 1.2479735612869263,
      "learning_rate": 7.9811759084299e-05,
      "loss": 0.995,
      "step": 126
    },
    {
      "epoch": 0.0621064857265114,
      "grad_norm": 1.208580732345581,
      "learning_rate": 7.800536421603317e-05,
      "loss": 1.0329,
      "step": 127
    },
    {
      "epoch": 0.06259551317317684,
      "grad_norm": 1.1326062679290771,
      "learning_rate": 7.620648049573815e-05,
      "loss": 0.9994,
      "step": 128
    },
    {
      "epoch": 0.06308454061984228,
      "grad_norm": 1.2653576135635376,
      "learning_rate": 7.441572224055644e-05,
      "loss": 0.9734,
      "step": 129
    },
    {
      "epoch": 0.06357356806650773,
      "grad_norm": 1.065186858177185,
      "learning_rate": 7.263370099279172e-05,
      "loss": 1.0234,
      "step": 130
    },
    {
      "epoch": 0.06406259551317317,
      "grad_norm": 1.2168216705322266,
      "learning_rate": 7.086102531106754e-05,
      "loss": 0.9007,
      "step": 131
    },
    {
      "epoch": 0.06455162295983861,
      "grad_norm": 1.2329150438308716,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.9663,
      "step": 132
    },
    {
      "epoch": 0.06504065040650407,
      "grad_norm": 0.9967830777168274,
      "learning_rate": 6.734612871599168e-05,
      "loss": 0.7774,
      "step": 133
    },
    {
      "epoch": 0.06552967785316952,
      "grad_norm": 0.8475475311279297,
      "learning_rate": 6.560510813660719e-05,
      "loss": 0.757,
      "step": 134
    },
    {
      "epoch": 0.06601870529983496,
      "grad_norm": 1.1470617055892944,
      "learning_rate": 6.387583338128471e-05,
      "loss": 1.074,
      "step": 135
    },
    {
      "epoch": 0.0665077327465004,
      "grad_norm": 1.2866921424865723,
      "learning_rate": 6.215889499576898e-05,
      "loss": 1.1369,
      "step": 136
    },
    {
      "epoch": 0.0665077327465004,
      "eval_loss": 1.008103847503662,
      "eval_runtime": 1314.805,
      "eval_samples_per_second": 1.965,
      "eval_steps_per_second": 0.655,
      "step": 136
    },
    {
      "epoch": 0.06699676019316585,
      "grad_norm": 1.012360692024231,
      "learning_rate": 6.0454879312945754e-05,
      "loss": 0.923,
      "step": 137
    },
    {
      "epoch": 0.06748578763983129,
      "grad_norm": 1.1338571310043335,
      "learning_rate": 5.876436825260967e-05,
      "loss": 0.8111,
      "step": 138
    },
    {
      "epoch": 0.06797481508649673,
      "grad_norm": 1.3135179281234741,
      "learning_rate": 5.708793912273911e-05,
      "loss": 1.0341,
      "step": 139
    },
    {
      "epoch": 0.06846384253316218,
      "grad_norm": 1.311312198638916,
      "learning_rate": 5.542616442234618e-05,
      "loss": 1.0275,
      "step": 140
    },
    {
      "epoch": 0.06895286997982762,
      "grad_norm": 1.3476301431655884,
      "learning_rate": 5.37796116459687e-05,
      "loss": 1.1978,
      "step": 141
    },
    {
      "epoch": 0.06944189742649307,
      "grad_norm": 0.9491245150566101,
      "learning_rate": 5.214884308987136e-05,
      "loss": 0.8215,
      "step": 142
    },
    {
      "epoch": 0.06993092487315851,
      "grad_norm": 1.420305848121643,
      "learning_rate": 5.0534415660022136e-05,
      "loss": 1.0719,
      "step": 143
    },
    {
      "epoch": 0.07041995231982395,
      "grad_norm": 1.1467198133468628,
      "learning_rate": 4.893688068190932e-05,
      "loss": 0.8647,
      "step": 144
    },
    {
      "epoch": 0.0709089797664894,
      "grad_norm": 1.2014856338500977,
      "learning_rate": 4.735678371226441e-05,
      "loss": 1.0392,
      "step": 145
    },
    {
      "epoch": 0.07139800721315484,
      "grad_norm": 1.0036952495574951,
      "learning_rate": 4.5794664352755055e-05,
      "loss": 0.8395,
      "step": 146
    },
    {
      "epoch": 0.07188703465982028,
      "grad_norm": 1.3835173845291138,
      "learning_rate": 4.425105606571145e-05,
      "loss": 1.1466,
      "step": 147
    },
    {
      "epoch": 0.07237606210648573,
      "grad_norm": 1.0508882999420166,
      "learning_rate": 4.272648599194948e-05,
      "loss": 0.9299,
      "step": 148
    },
    {
      "epoch": 0.07286508955315117,
      "grad_norm": 1.1250102519989014,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.071,
      "step": 149
    },
    {
      "epoch": 0.07335411699981662,
      "grad_norm": 1.1226435899734497,
      "learning_rate": 3.973653636207437e-05,
      "loss": 1.0422,
      "step": 150
    },
    {
      "epoch": 0.07384314444648206,
      "grad_norm": 1.3410860300064087,
      "learning_rate": 3.8272177871020723e-05,
      "loss": 1.0522,
      "step": 151
    },
    {
      "epoch": 0.0743321718931475,
      "grad_norm": 1.0031688213348389,
      "learning_rate": 3.682889937467493e-05,
      "loss": 0.9383,
      "step": 152
    },
    {
      "epoch": 0.07482119933981295,
      "grad_norm": 1.1532304286956787,
      "learning_rate": 3.540719375132129e-05,
      "loss": 1.0742,
      "step": 153
    },
    {
      "epoch": 0.07531022678647839,
      "grad_norm": 1.2422029972076416,
      "learning_rate": 3.400754651212776e-05,
      "loss": 1.0617,
      "step": 154
    },
    {
      "epoch": 0.07579925423314383,
      "grad_norm": 1.1498128175735474,
      "learning_rate": 3.263043563534428e-05,
      "loss": 1.1001,
      "step": 155
    },
    {
      "epoch": 0.07628828167980928,
      "grad_norm": 1.2348723411560059,
      "learning_rate": 3.1276331403073735e-05,
      "loss": 1.2324,
      "step": 156
    },
    {
      "epoch": 0.07677730912647472,
      "grad_norm": 1.0501295328140259,
      "learning_rate": 2.9945696240670906e-05,
      "loss": 1.0257,
      "step": 157
    },
    {
      "epoch": 0.07726633657314017,
      "grad_norm": 1.0802302360534668,
      "learning_rate": 2.8638984558824777e-05,
      "loss": 0.9022,
      "step": 158
    },
    {
      "epoch": 0.07775536401980561,
      "grad_norm": 1.1807763576507568,
      "learning_rate": 2.7356642598377603e-05,
      "loss": 0.8648,
      "step": 159
    },
    {
      "epoch": 0.07824439146647105,
      "grad_norm": 1.0485153198242188,
      "learning_rate": 2.6099108277934103e-05,
      "loss": 0.8645,
      "step": 160
    },
    {
      "epoch": 0.0787334189131365,
      "grad_norm": 1.2471535205841064,
      "learning_rate": 2.4866811044312665e-05,
      "loss": 1.0674,
      "step": 161
    },
    {
      "epoch": 0.07922244635980194,
      "grad_norm": 1.1193430423736572,
      "learning_rate": 2.36601717258897e-05,
      "loss": 1.1859,
      "step": 162
    },
    {
      "epoch": 0.07971147380646738,
      "grad_norm": 0.9289650917053223,
      "learning_rate": 2.2479602388887012e-05,
      "loss": 0.9537,
      "step": 163
    },
    {
      "epoch": 0.08020050125313283,
      "grad_norm": 1.0112844705581665,
      "learning_rate": 2.132550619665168e-05,
      "loss": 0.8756,
      "step": 164
    },
    {
      "epoch": 0.08068952869979827,
      "grad_norm": 1.5007420778274536,
      "learning_rate": 2.0198277271976052e-05,
      "loss": 1.0459,
      "step": 165
    },
    {
      "epoch": 0.08117855614646372,
      "grad_norm": 1.1469403505325317,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.9885,
      "step": 166
    },
    {
      "epoch": 0.08166758359312916,
      "grad_norm": 1.1436965465545654,
      "learning_rate": 1.8025951709277898e-05,
      "loss": 0.9769,
      "step": 167
    },
    {
      "epoch": 0.0821566110397946,
      "grad_norm": 1.0451879501342773,
      "learning_rate": 1.6981596918444953e-05,
      "loss": 1.0134,
      "step": 168
    },
    {
      "epoch": 0.08264563848646005,
      "grad_norm": 1.125041127204895,
      "learning_rate": 1.5965592836210743e-05,
      "loss": 0.9923,
      "step": 169
    },
    {
      "epoch": 0.08313466593312549,
      "grad_norm": 0.8700924515724182,
      "learning_rate": 1.4978286427038601e-05,
      "loss": 0.7571,
      "step": 170
    },
    {
      "epoch": 0.08313466593312549,
      "eval_loss": 0.9938088655471802,
      "eval_runtime": 1314.6112,
      "eval_samples_per_second": 1.965,
      "eval_steps_per_second": 0.655,
      "step": 170
    },
    {
      "epoch": 0.08362369337979095,
      "grad_norm": 1.2007029056549072,
      "learning_rate": 1.4020014855162755e-05,
      "loss": 0.9449,
      "step": 171
    },
    {
      "epoch": 0.08411272082645639,
      "grad_norm": 1.0278856754302979,
      "learning_rate": 1.3091105369447165e-05,
      "loss": 0.9973,
      "step": 172
    },
    {
      "epoch": 0.08460174827312184,
      "grad_norm": 1.101802945137024,
      "learning_rate": 1.2191875191630209e-05,
      "loss": 1.2075,
      "step": 173
    },
    {
      "epoch": 0.08509077571978728,
      "grad_norm": 0.9632481336593628,
      "learning_rate": 1.1322631407993811e-05,
      "loss": 0.7475,
      "step": 174
    },
    {
      "epoch": 0.08557980316645272,
      "grad_norm": 1.0847288370132446,
      "learning_rate": 1.0483670864493778e-05,
      "loss": 0.8914,
      "step": 175
    },
    {
      "epoch": 0.08606883061311817,
      "grad_norm": 1.2630629539489746,
      "learning_rate": 9.675280065387116e-06,
      "loss": 1.0159,
      "step": 176
    },
    {
      "epoch": 0.08655785805978361,
      "grad_norm": 1.059738278388977,
      "learning_rate": 8.897735075391155e-06,
      "loss": 0.897,
      "step": 177
    },
    {
      "epoch": 0.08704688550644905,
      "grad_norm": 1.183966875076294,
      "learning_rate": 8.151301425407699e-06,
      "loss": 0.9258,
      "step": 178
    },
    {
      "epoch": 0.0875359129531145,
      "grad_norm": 1.2419488430023193,
      "learning_rate": 7.43623402184438e-06,
      "loss": 0.9676,
      "step": 179
    },
    {
      "epoch": 0.08802494039977994,
      "grad_norm": 1.0326918363571167,
      "learning_rate": 6.75277705956443e-06,
      "loss": 0.8304,
      "step": 180
    },
    {
      "epoch": 0.08851396784644538,
      "grad_norm": 1.0449199676513672,
      "learning_rate": 6.1011639384943585e-06,
      "loss": 1.0186,
      "step": 181
    },
    {
      "epoch": 0.08900299529311083,
      "grad_norm": 1.2107876539230347,
      "learning_rate": 5.481617183918053e-06,
      "loss": 1.1832,
      "step": 182
    },
    {
      "epoch": 0.08949202273977627,
      "grad_norm": 1.49854576587677,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 1.2453,
      "step": 183
    },
    {
      "epoch": 0.08998105018644172,
      "grad_norm": 1.2521921396255493,
      "learning_rate": 4.339558049955927e-06,
      "loss": 0.9645,
      "step": 184
    },
    {
      "epoch": 0.09047007763310716,
      "grad_norm": 1.0324766635894775,
      "learning_rate": 3.817435682718096e-06,
      "loss": 0.9331,
      "step": 185
    },
    {
      "epoch": 0.0909591050797726,
      "grad_norm": 1.7339527606964111,
      "learning_rate": 3.3281595730812575e-06,
      "loss": 1.0684,
      "step": 186
    },
    {
      "epoch": 0.09144813252643805,
      "grad_norm": 0.9455498456954956,
      "learning_rate": 2.8718968083886075e-06,
      "loss": 0.91,
      "step": 187
    },
    {
      "epoch": 0.09193715997310349,
      "grad_norm": 1.0833247900009155,
      "learning_rate": 2.4488032019563402e-06,
      "loss": 0.9828,
      "step": 188
    },
    {
      "epoch": 0.09242618741976893,
      "grad_norm": 1.0382250547409058,
      "learning_rate": 2.0590232398634114e-06,
      "loss": 1.0874,
      "step": 189
    },
    {
      "epoch": 0.09291521486643438,
      "grad_norm": 1.0121673345565796,
      "learning_rate": 1.7026900316098215e-06,
      "loss": 0.8295,
      "step": 190
    },
    {
      "epoch": 0.09340424231309982,
      "grad_norm": 1.2903939485549927,
      "learning_rate": 1.3799252646597426e-06,
      "loss": 1.0516,
      "step": 191
    },
    {
      "epoch": 0.09389326975976527,
      "grad_norm": 1.140723705291748,
      "learning_rate": 1.0908391628854041e-06,
      "loss": 0.9476,
      "step": 192
    },
    {
      "epoch": 0.09438229720643071,
      "grad_norm": 1.051087737083435,
      "learning_rate": 8.355304489257254e-07,
      "loss": 0.9245,
      "step": 193
    },
    {
      "epoch": 0.09487132465309615,
      "grad_norm": 1.2365599870681763,
      "learning_rate": 6.140863104726391e-07,
      "loss": 0.9907,
      "step": 194
    },
    {
      "epoch": 0.0953603520997616,
      "grad_norm": 1.1254229545593262,
      "learning_rate": 4.2658237049655323e-07,
      "loss": 0.8159,
      "step": 195
    },
    {
      "epoch": 0.09584937954642704,
      "grad_norm": 1.173430323600769,
      "learning_rate": 2.7308266142119785e-07,
      "loss": 1.1951,
      "step": 196
    },
    {
      "epoch": 0.09633840699309248,
      "grad_norm": 1.0540282726287842,
      "learning_rate": 1.5363960325660565e-07,
      "loss": 1.0794,
      "step": 197
    },
    {
      "epoch": 0.09682743443975793,
      "grad_norm": 1.3299025297164917,
      "learning_rate": 6.829398569770939e-08,
      "loss": 1.2289,
      "step": 198
    },
    {
      "epoch": 0.09731646188642337,
      "grad_norm": 1.0798887014389038,
      "learning_rate": 1.7074954194729044e-08,
      "loss": 0.994,
      "step": 199
    },
    {
      "epoch": 0.09780548933308882,
      "grad_norm": 1.3523894548416138,
      "learning_rate": 0.0,
      "loss": 1.2413,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.877908391100416e+17,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}