{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05379301913319885,
  "eval_steps": 34,
  "global_step": 110,
  "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
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.882849615105229e+17,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}