{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 35,
  "global_step": 176,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022727272727272728,
      "grad_norm": 1.1206783056259155,
      "learning_rate": 0.0,
      "loss": 1.4756,
      "step": 1
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 0.9496277570724487,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 1.3696,
      "step": 2
    },
    {
      "epoch": 0.06818181818181818,
      "grad_norm": 1.1058847904205322,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 1.5078,
      "step": 3
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 0.8029769062995911,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.2568,
      "step": 4
    },
    {
      "epoch": 0.11363636363636363,
      "grad_norm": 0.38214796781539917,
      "learning_rate": 8.888888888888889e-05,
      "loss": 1.2388,
      "step": 5
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 0.2158196121454239,
      "learning_rate": 0.00011111111111111112,
      "loss": 1.1294,
      "step": 6
    },
    {
      "epoch": 0.1590909090909091,
      "grad_norm": 0.16952140629291534,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.1768,
      "step": 7
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.1662416160106659,
      "learning_rate": 0.00015555555555555556,
      "loss": 1.1709,
      "step": 8
    },
    {
      "epoch": 0.20454545454545456,
      "grad_norm": 0.13825193047523499,
      "learning_rate": 0.00017777777777777779,
      "loss": 1.1504,
      "step": 9
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 0.07861247658729553,
      "learning_rate": 0.0002,
      "loss": 1.124,
      "step": 10
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.07430972158908844,
      "learning_rate": 0.0001999831907783077,
      "loss": 1.168,
      "step": 11
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.11529561132192612,
      "learning_rate": 0.0001999327690616505,
      "loss": 1.0981,
      "step": 12
    },
    {
      "epoch": 0.29545454545454547,
      "grad_norm": 0.09737521409988403,
      "learning_rate": 0.00019984875269318233,
      "loss": 1.1455,
      "step": 13
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 0.06155918911099434,
      "learning_rate": 0.00019973117140447712,
      "loss": 0.9917,
      "step": 14
    },
    {
      "epoch": 0.3409090909090909,
      "grad_norm": 0.05671455338597298,
      "learning_rate": 0.00019958006680500753,
      "loss": 1.0488,
      "step": 15
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.05696249008178711,
      "learning_rate": 0.00019939549236742013,
      "loss": 1.1436,
      "step": 16
    },
    {
      "epoch": 0.38636363636363635,
      "grad_norm": 0.04749668389558792,
      "learning_rate": 0.00019917751340861256,
      "loss": 1.0332,
      "step": 17
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 0.05082089081406593,
      "learning_rate": 0.0001989262070666194,
      "loss": 1.1011,
      "step": 18
    },
    {
      "epoch": 0.4318181818181818,
      "grad_norm": 0.047943856567144394,
      "learning_rate": 0.00019864166227331472,
      "loss": 1.0796,
      "step": 19
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.03905141353607178,
      "learning_rate": 0.0001983239797229408,
      "loss": 1.0347,
      "step": 20
    },
    {
      "epoch": 0.4772727272727273,
      "grad_norm": 0.03786393627524376,
      "learning_rate": 0.0001979732718364749,
      "loss": 1.0708,
      "step": 21
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.04183785989880562,
      "learning_rate": 0.00019758966272184566,
      "loss": 0.9497,
      "step": 22
    },
    {
      "epoch": 0.5227272727272727,
      "grad_norm": 0.040070075541734695,
      "learning_rate": 0.00019717328813001424,
      "loss": 0.918,
      "step": 23
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.0371328629553318,
      "learning_rate": 0.00019672429540693465,
      "loss": 0.9961,
      "step": 24
    },
    {
      "epoch": 0.5681818181818182,
      "grad_norm": 0.04202131927013397,
      "learning_rate": 0.0001962428434414116,
      "loss": 1.0327,
      "step": 25
    },
    {
      "epoch": 0.5909090909090909,
      "grad_norm": 0.03759108856320381,
      "learning_rate": 0.00019572910260887299,
      "loss": 1.0576,
      "step": 26
    },
    {
      "epoch": 0.6136363636363636,
      "grad_norm": 0.03564843535423279,
      "learning_rate": 0.00019518325471107754,
      "loss": 0.9098,
      "step": 27
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 0.03715354576706886,
      "learning_rate": 0.0001946054929117796,
      "loss": 0.9473,
      "step": 28
    },
    {
      "epoch": 0.6590909090909091,
      "grad_norm": 0.036995336413383484,
      "learning_rate": 0.00019399602166837214,
      "loss": 1.0566,
      "step": 29
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 0.03732811287045479,
      "learning_rate": 0.000193355056659534,
      "loss": 1.0688,
      "step": 30
    },
    {
      "epoch": 0.7045454545454546,
      "grad_norm": 0.03539854660630226,
      "learning_rate": 0.0001926828247089059,
      "loss": 1.0107,
      "step": 31
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.038864873349666595,
      "learning_rate": 0.00019197956370482221,
      "loss": 1.1074,
      "step": 32
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.03247080743312836,
      "learning_rate": 0.00019124552251612774,
      "loss": 0.8381,
      "step": 33
    },
    {
      "epoch": 0.7727272727272727,
      "grad_norm": 0.03792323172092438,
      "learning_rate": 0.0001904809609041082,
      "loss": 1.0229,
      "step": 34
    },
    {
      "epoch": 0.7954545454545454,
      "grad_norm": 0.03529801964759827,
      "learning_rate": 0.00018968614943056636,
      "loss": 1.0142,
      "step": 35
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.04061409831047058,
      "learning_rate": 0.0001888613693620762,
      "loss": 1.0557,
      "step": 36
    },
    {
      "epoch": 0.8181818181818182,
      "eval_loss": 1.02685546875,
      "eval_runtime": 2.1867,
      "eval_samples_per_second": 3.201,
      "eval_steps_per_second": 0.457,
      "step": 36
    },
    {
      "epoch": 0.8409090909090909,
      "grad_norm": 0.03531581535935402,
      "learning_rate": 0.00018800691257044868,
      "loss": 0.9868,
      "step": 37
    },
    {
      "epoch": 0.8636363636363636,
      "grad_norm": 0.03277561813592911,
      "learning_rate": 0.0001871230814294445,
      "loss": 0.9712,
      "step": 38
    },
    {
      "epoch": 0.8863636363636364,
      "grad_norm": 0.03188008442521095,
      "learning_rate": 0.0001862101887077708,
      "loss": 0.9849,
      "step": 39
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.029968153685331345,
      "learning_rate": 0.00018526855745839898,
      "loss": 0.8632,
      "step": 40
    },
    {
      "epoch": 0.9318181818181818,
      "grad_norm": 0.034472040832042694,
      "learning_rate": 0.00018429852090424316,
      "loss": 1.001,
      "step": 41
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 0.029998162761330605,
      "learning_rate": 0.00018330042232023993,
      "loss": 0.7714,
      "step": 42
    },
    {
      "epoch": 0.9772727272727273,
      "grad_norm": 0.0348285436630249,
      "learning_rate": 0.00018227461491187084,
      "loss": 0.9824,
      "step": 43
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.0326283760368824,
      "learning_rate": 0.00018122146169017035,
      "loss": 0.9897,
      "step": 44
    },
    {
      "epoch": 1.0227272727272727,
      "grad_norm": 0.032206494361162186,
      "learning_rate": 0.00018014133534326437,
      "loss": 0.9756,
      "step": 45
    },
    {
      "epoch": 1.0454545454545454,
      "grad_norm": 0.03450873866677284,
      "learning_rate": 0.00017903461810448386,
      "loss": 0.9287,
      "step": 46
    },
    {
      "epoch": 1.0681818181818181,
      "grad_norm": 0.030909940600395203,
      "learning_rate": 0.00017790170161710077,
      "loss": 1.0044,
      "step": 47
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.029604636132717133,
      "learning_rate": 0.00017674298679573394,
      "loss": 0.8599,
      "step": 48
    },
    {
      "epoch": 1.1136363636363635,
      "grad_norm": 0.03281280770897865,
      "learning_rate": 0.00017555888368447412,
      "loss": 0.9678,
      "step": 49
    },
    {
      "epoch": 1.1363636363636362,
      "grad_norm": 0.0340212918817997,
      "learning_rate": 0.00017434981131177825,
      "loss": 0.918,
      "step": 50
    },
    {
      "epoch": 1.1590909090909092,
      "grad_norm": 0.03562180697917938,
      "learning_rate": 0.00017311619754218428,
      "loss": 0.9702,
      "step": 51
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 0.034595854580402374,
      "learning_rate": 0.00017185847892489935,
      "loss": 0.9849,
      "step": 52
    },
    {
      "epoch": 1.2045454545454546,
      "grad_norm": 0.037027474492788315,
      "learning_rate": 0.00017057710053931422,
      "loss": 0.9727,
      "step": 53
    },
    {
      "epoch": 1.2272727272727273,
      "grad_norm": 0.03537385165691376,
      "learning_rate": 0.00016927251583749955,
      "loss": 0.9824,
      "step": 54
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.039779458194971085,
      "learning_rate": 0.0001679451864837389,
      "loss": 1.0161,
      "step": 55
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 0.03505770117044449,
      "learning_rate": 0.00016659558219115576,
      "loss": 0.9609,
      "step": 56
    },
    {
      "epoch": 1.2954545454545454,
      "grad_norm": 0.03853118419647217,
      "learning_rate": 0.00016522418055549224,
      "loss": 1.0093,
      "step": 57
    },
    {
      "epoch": 1.3181818181818181,
      "grad_norm": 0.03246483951807022,
      "learning_rate": 0.00016383146688609836,
      "loss": 0.8838,
      "step": 58
    },
    {
      "epoch": 1.3409090909090908,
      "grad_norm": 0.03590584918856621,
      "learning_rate": 0.00016241793403419134,
      "loss": 0.9307,
      "step": 59
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.04366080462932587,
      "learning_rate": 0.0001609840822184466,
      "loss": 1.0205,
      "step": 60
    },
    {
      "epoch": 1.3863636363636362,
      "grad_norm": 0.03435956686735153,
      "learning_rate": 0.0001595304188479808,
      "loss": 0.9258,
      "step": 61
    },
    {
      "epoch": 1.4090909090909092,
      "grad_norm": 0.03861411660909653,
      "learning_rate": 0.00015805745834279102,
      "loss": 0.9902,
      "step": 62
    },
    {
      "epoch": 1.4318181818181819,
      "grad_norm": 0.03771635890007019,
      "learning_rate": 0.0001565657219517125,
      "loss": 0.979,
      "step": 63
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.03524011746048927,
      "learning_rate": 0.00015505573756796016,
      "loss": 0.9355,
      "step": 64
    },
    {
      "epoch": 1.4772727272727273,
      "grad_norm": 0.03491239622235298,
      "learning_rate": 0.00015352803954231826,
      "loss": 0.9741,
      "step": 65
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.037287212908267975,
      "learning_rate": 0.00015198316849404566,
      "loss": 0.8633,
      "step": 66
    },
    {
      "epoch": 1.5227272727272727,
      "grad_norm": 0.03426371514797211,
      "learning_rate": 0.00015042167111956203,
      "loss": 0.8389,
      "step": 67
    },
    {
      "epoch": 1.5454545454545454,
      "grad_norm": 0.03486687317490578,
      "learning_rate": 0.00014884409999898406,
      "loss": 0.9102,
      "step": 68
    },
    {
      "epoch": 1.5681818181818183,
      "grad_norm": 0.03577412664890289,
      "learning_rate": 0.00014725101340057906,
      "loss": 0.9453,
      "step": 69
    },
    {
      "epoch": 1.5909090909090908,
      "grad_norm": 0.03450024127960205,
      "learning_rate": 0.00014564297508320618,
      "loss": 0.9741,
      "step": 70
    },
    {
      "epoch": 1.6136363636363638,
      "grad_norm": 0.03229016810655594,
      "learning_rate": 0.00014402055409681421,
      "loss": 0.835,
      "step": 71
    },
    {
      "epoch": 1.6136363636363638,
      "eval_loss": 0.98358154296875,
      "eval_runtime": 2.1903,
      "eval_samples_per_second": 3.196,
      "eval_steps_per_second": 0.457,
      "step": 71
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 0.03623503819108009,
      "learning_rate": 0.00014238432458106709,
      "loss": 0.8713,
      "step": 72
    },
    {
      "epoch": 1.6590909090909092,
      "grad_norm": 0.03640628978610039,
      "learning_rate": 0.00014073486556216838,
      "loss": 0.9727,
      "step": 73
    },
    {
      "epoch": 1.6818181818181817,
      "grad_norm": 0.036052148789167404,
      "learning_rate": 0.00013907276074795642,
      "loss": 0.9858,
      "step": 74
    },
    {
      "epoch": 1.7045454545454546,
      "grad_norm": 0.03817129135131836,
      "learning_rate": 0.00013739859832134278,
      "loss": 0.9351,
      "step": 75
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 0.03991701826453209,
      "learning_rate": 0.00013571297073216695,
      "loss": 1.0283,
      "step": 76
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.03450099006295204,
      "learning_rate": 0.0001340164744875413,
      "loss": 0.7749,
      "step": 77
    },
    {
      "epoch": 1.7727272727272727,
      "grad_norm": 0.03970921412110329,
      "learning_rate": 0.00013230970994076012,
      "loss": 0.9487,
      "step": 78
    },
    {
      "epoch": 1.7954545454545454,
      "grad_norm": 0.04119304567575455,
      "learning_rate": 0.0001305932810788474,
      "loss": 0.9399,
      "step": 79
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.038538262248039246,
      "learning_rate": 0.00012886779530881917,
      "loss": 0.981,
      "step": 80
    },
    {
      "epoch": 1.8409090909090908,
      "grad_norm": 0.035877276211977005,
      "learning_rate": 0.00012713386324273506,
      "loss": 0.9189,
      "step": 81
    },
    {
      "epoch": 1.8636363636363638,
      "grad_norm": 0.036334339529275894,
      "learning_rate": 0.00012539209848161617,
      "loss": 0.897,
      "step": 82
    },
    {
      "epoch": 1.8863636363636362,
      "grad_norm": 0.033809829503297806,
      "learning_rate": 0.00012364311739830467,
      "loss": 0.9204,
      "step": 83
    },
    {
      "epoch": 1.9090909090909092,
      "grad_norm": 0.03626739978790283,
      "learning_rate": 0.00012188753891934297,
      "loss": 0.8051,
      "step": 84
    },
    {
      "epoch": 1.9318181818181817,
      "grad_norm": 0.03722269460558891,
      "learning_rate": 0.00012012598430594906,
      "loss": 0.9341,
      "step": 85
    },
    {
      "epoch": 1.9545454545454546,
      "grad_norm": 0.03311004862189293,
      "learning_rate": 0.00011835907693416537,
      "loss": 0.7198,
      "step": 86
    },
    {
      "epoch": 1.9772727272727273,
      "grad_norm": 0.04086141288280487,
      "learning_rate": 0.00011658744207425975,
      "loss": 0.9111,
      "step": 87
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.03870685026049614,
      "learning_rate": 0.00011481170666945578,
      "loss": 0.917,
      "step": 88
    },
    {
      "epoch": 2.022727272727273,
      "grad_norm": 0.03754683583974838,
      "learning_rate": 0.00011303249911407101,
      "loss": 0.9033,
      "step": 89
    },
    {
      "epoch": 2.0454545454545454,
      "grad_norm": 0.03624191880226135,
      "learning_rate": 0.00011125044903114203,
      "loss": 0.8677,
      "step": 90
    },
    {
      "epoch": 2.0681818181818183,
      "grad_norm": 0.03998927026987076,
      "learning_rate": 0.00010946618704961427,
      "loss": 0.9443,
      "step": 91
    },
    {
      "epoch": 2.090909090909091,
      "grad_norm": 0.03589046373963356,
      "learning_rate": 0.00010768034458117628,
      "loss": 0.8089,
      "step": 92
    },
    {
      "epoch": 2.1136363636363638,
      "grad_norm": 0.03793152794241905,
      "learning_rate": 0.0001058935535968167,
      "loss": 0.9058,
      "step": 93
    },
    {
      "epoch": 2.1363636363636362,
      "grad_norm": 0.03866463154554367,
      "learning_rate": 0.00010410644640318335,
      "loss": 0.8564,
      "step": 94
    },
    {
      "epoch": 2.159090909090909,
      "grad_norm": 0.03865712508559227,
      "learning_rate": 0.00010231965541882374,
      "loss": 0.9131,
      "step": 95
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 0.04023934528231621,
      "learning_rate": 0.00010053381295038576,
      "loss": 0.9302,
      "step": 96
    },
    {
      "epoch": 2.2045454545454546,
      "grad_norm": 0.04135757312178612,
      "learning_rate": 9.8749550968858e-05,
      "loss": 0.9146,
      "step": 97
    },
    {
      "epoch": 2.227272727272727,
      "grad_norm": 0.04282484948635101,
      "learning_rate": 9.696750088592899e-05,
      "loss": 0.9341,
      "step": 98
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.04101482778787613,
      "learning_rate": 9.518829333054425e-05,
      "loss": 0.959,
      "step": 99
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 0.03919293358922005,
      "learning_rate": 9.341255792574027e-05,
      "loss": 0.9048,
      "step": 100
    },
    {
      "epoch": 2.2954545454545454,
      "grad_norm": 0.046711232513189316,
      "learning_rate": 9.164092306583469e-05,
      "loss": 0.9575,
      "step": 101
    },
    {
      "epoch": 2.3181818181818183,
      "grad_norm": 0.038469649851322174,
      "learning_rate": 8.987401569405097e-05,
      "loss": 0.835,
      "step": 102
    },
    {
      "epoch": 2.340909090909091,
      "grad_norm": 0.04006647318601608,
      "learning_rate": 8.811246108065704e-05,
      "loss": 0.876,
      "step": 103
    },
    {
      "epoch": 2.3636363636363638,
      "grad_norm": 0.04686180129647255,
      "learning_rate": 8.635688260169533e-05,
      "loss": 0.9585,
      "step": 104
    },
    {
      "epoch": 2.3863636363636362,
      "grad_norm": 0.03884272649884224,
      "learning_rate": 8.460790151838383e-05,
      "loss": 0.8755,
      "step": 105
    },
    {
      "epoch": 2.409090909090909,
      "grad_norm": 0.044794514775276184,
      "learning_rate": 8.286613675726495e-05,
      "loss": 0.938,
      "step": 106
    },
    {
      "epoch": 2.409090909090909,
      "eval_loss": 0.96563720703125,
      "eval_runtime": 2.1948,
      "eval_samples_per_second": 3.189,
      "eval_steps_per_second": 0.456,
      "step": 106
    },
    {
      "epoch": 2.4318181818181817,
      "grad_norm": 0.04436111822724342,
      "learning_rate": 8.113220469118087e-05,
      "loss": 0.9292,
      "step": 107
    },
    {
      "epoch": 2.4545454545454546,
      "grad_norm": 0.041413839906454086,
      "learning_rate": 7.940671892115264e-05,
      "loss": 0.8887,
      "step": 108
    },
    {
      "epoch": 2.4772727272727275,
      "grad_norm": 0.040317073464393616,
      "learning_rate": 7.76902900592399e-05,
      "loss": 0.9268,
      "step": 109
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.040230900049209595,
      "learning_rate": 7.598352551245871e-05,
      "loss": 0.8169,
      "step": 110
    },
    {
      "epoch": 2.5227272727272725,
      "grad_norm": 0.03752891346812248,
      "learning_rate": 7.428702926783306e-05,
      "loss": 0.7996,
      "step": 111
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 0.043321698904037476,
      "learning_rate": 7.260140167865722e-05,
      "loss": 0.8638,
      "step": 112
    },
    {
      "epoch": 2.5681818181818183,
      "grad_norm": 0.0414450466632843,
      "learning_rate": 7.092723925204361e-05,
      "loss": 0.8994,
      "step": 113
    },
    {
      "epoch": 2.590909090909091,
      "grad_norm": 0.039529651403427124,
      "learning_rate": 6.926513443783163e-05,
      "loss": 0.9292,
      "step": 114
    },
    {
      "epoch": 2.6136363636363638,
      "grad_norm": 0.03540017455816269,
      "learning_rate": 6.761567541893294e-05,
      "loss": 0.798,
      "step": 115
    },
    {
      "epoch": 2.6363636363636362,
      "grad_norm": 0.0417497493326664,
      "learning_rate": 6.59794459031858e-05,
      "loss": 0.8298,
      "step": 116
    },
    {
      "epoch": 2.659090909090909,
      "grad_norm": 0.04431189224123955,
      "learning_rate": 6.43570249167938e-05,
      "loss": 0.9287,
      "step": 117
    },
    {
      "epoch": 2.6818181818181817,
      "grad_norm": 0.040859613567590714,
      "learning_rate": 6.274898659942096e-05,
      "loss": 0.9419,
      "step": 118
    },
    {
      "epoch": 2.7045454545454546,
      "grad_norm": 0.04349968209862709,
      "learning_rate": 6.115590000101597e-05,
      "loss": 0.8926,
      "step": 119
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.04619387164711952,
      "learning_rate": 5.957832888043796e-05,
      "loss": 0.9829,
      "step": 120
    },
    {
      "epoch": 2.75,
      "grad_norm": 0.03812430426478386,
      "learning_rate": 5.801683150595435e-05,
      "loss": 0.7394,
      "step": 121
    },
    {
      "epoch": 2.7727272727272725,
      "grad_norm": 0.04161018133163452,
      "learning_rate": 5.647196045768177e-05,
      "loss": 0.9072,
      "step": 122
    },
    {
      "epoch": 2.7954545454545454,
      "grad_norm": 0.0428486131131649,
      "learning_rate": 5.4944262432039886e-05,
      "loss": 0.8994,
      "step": 123
    },
    {
      "epoch": 2.8181818181818183,
      "grad_norm": 0.04286428168416023,
      "learning_rate": 5.3434278048287476e-05,
      "loss": 0.9404,
      "step": 124
    },
    {
      "epoch": 2.840909090909091,
      "grad_norm": 0.040211714804172516,
      "learning_rate": 5.1942541657209006e-05,
      "loss": 0.8813,
      "step": 125
    },
    {
      "epoch": 2.8636363636363638,
      "grad_norm": 0.042145051062107086,
      "learning_rate": 5.046958115201921e-05,
      "loss": 0.8574,
      "step": 126
    },
    {
      "epoch": 2.8863636363636362,
      "grad_norm": 0.04282425343990326,
      "learning_rate": 4.901591778155343e-05,
      "loss": 0.8828,
      "step": 127
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 0.0363474078476429,
      "learning_rate": 4.758206596580864e-05,
      "loss": 0.7745,
      "step": 128
    },
    {
      "epoch": 2.9318181818181817,
      "grad_norm": 0.041176341474056244,
      "learning_rate": 4.616853311390168e-05,
      "loss": 0.8994,
      "step": 129
    },
    {
      "epoch": 2.9545454545454546,
      "grad_norm": 0.03660375624895096,
      "learning_rate": 4.477581944450777e-05,
      "loss": 0.6917,
      "step": 130
    },
    {
      "epoch": 2.9772727272727275,
      "grad_norm": 0.040555551648139954,
      "learning_rate": 4.3404417808844264e-05,
      "loss": 0.8735,
      "step": 131
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.04534464702010155,
      "learning_rate": 4.205481351626114e-05,
      "loss": 0.873,
      "step": 132
    },
    {
      "epoch": 3.022727272727273,
      "grad_norm": 0.04196697846055031,
      "learning_rate": 4.0727484162500475e-05,
      "loss": 0.8594,
      "step": 133
    },
    {
      "epoch": 3.0454545454545454,
      "grad_norm": 0.04108813777565956,
      "learning_rate": 3.9422899460685827e-05,
      "loss": 0.8354,
      "step": 134
    },
    {
      "epoch": 3.0681818181818183,
      "grad_norm": 0.04293624684214592,
      "learning_rate": 3.8141521075100684e-05,
      "loss": 0.9131,
      "step": 135
    },
    {
      "epoch": 3.090909090909091,
      "grad_norm": 0.03855728730559349,
      "learning_rate": 3.688380245781572e-05,
      "loss": 0.7843,
      "step": 136
    },
    {
      "epoch": 3.1136363636363638,
      "grad_norm": 0.042156051844358444,
      "learning_rate": 3.565018868822175e-05,
      "loss": 0.8745,
      "step": 137
    },
    {
      "epoch": 3.1363636363636362,
      "grad_norm": 0.046880971640348434,
      "learning_rate": 3.444111631552587e-05,
      "loss": 0.8271,
      "step": 138
    },
    {
      "epoch": 3.159090909090909,
      "grad_norm": 0.0405617319047451,
      "learning_rate": 3.3257013204266074e-05,
      "loss": 0.8823,
      "step": 139
    },
    {
      "epoch": 3.1818181818181817,
      "grad_norm": 0.039144791662693024,
      "learning_rate": 3.2098298382899237e-05,
      "loss": 0.9019,
      "step": 140
    },
    {
      "epoch": 3.2045454545454546,
      "grad_norm": 0.04265075922012329,
      "learning_rate": 3.0965381895516166e-05,
      "loss": 0.8848,
      "step": 141
    },
    {
      "epoch": 3.2045454545454546,
      "eval_loss": 0.958740234375,
      "eval_runtime": 2.1697,
      "eval_samples_per_second": 3.226,
      "eval_steps_per_second": 0.461,
      "step": 141
    },
    {
      "epoch": 3.227272727272727,
      "grad_norm": 0.03980688750743866,
      "learning_rate": 2.9858664656735656e-05,
      "loss": 0.9048,
      "step": 142
    },
    {
      "epoch": 3.25,
      "grad_norm": 0.04210719093680382,
      "learning_rate": 2.8778538309829663e-05,
      "loss": 0.9302,
      "step": 143
    },
    {
      "epoch": 3.2727272727272725,
      "grad_norm": 0.03925318270921707,
      "learning_rate": 2.772538508812917e-05,
      "loss": 0.877,
      "step": 144
    },
    {
      "epoch": 3.2954545454545454,
      "grad_norm": 0.0381309874355793,
      "learning_rate": 2.6699577679760045e-05,
      "loss": 0.9302,
      "step": 145
    },
    {
      "epoch": 3.3181818181818183,
      "grad_norm": 0.03723252937197685,
      "learning_rate": 2.5701479095756865e-05,
      "loss": 0.8105,
      "step": 146
    },
    {
      "epoch": 3.340909090909091,
      "grad_norm": 0.03968927636742592,
      "learning_rate": 2.4731442541601045e-05,
      "loss": 0.8506,
      "step": 147
    },
    {
      "epoch": 3.3636363636363638,
      "grad_norm": 0.05284200608730316,
      "learning_rate": 2.3789811292229234e-05,
      "loss": 0.9268,
      "step": 148
    },
    {
      "epoch": 3.3863636363636362,
      "grad_norm": 0.040034014731645584,
      "learning_rate": 2.2876918570555536e-05,
      "loss": 0.8516,
      "step": 149
    },
    {
      "epoch": 3.409090909090909,
      "grad_norm": 0.041558850556612015,
      "learning_rate": 2.1993087429551352e-05,
      "loss": 0.9126,
      "step": 150
    },
    {
      "epoch": 3.4318181818181817,
      "grad_norm": 0.039900146424770355,
      "learning_rate": 2.1138630637923796e-05,
      "loss": 0.9043,
      "step": 151
    },
    {
      "epoch": 3.4545454545454546,
      "grad_norm": 0.03813033923506737,
      "learning_rate": 2.0313850569433645e-05,
      "loss": 0.8643,
      "step": 152
    },
    {
      "epoch": 3.4772727272727275,
      "grad_norm": 0.039038874208927155,
      "learning_rate": 1.951903909589183e-05,
      "loss": 0.9053,
      "step": 153
    },
    {
      "epoch": 3.5,
      "grad_norm": 0.039629869163036346,
      "learning_rate": 1.8754477483872255e-05,
      "loss": 0.7964,
      "step": 154
    },
    {
      "epoch": 3.5227272727272725,
      "grad_norm": 0.037337273359298706,
      "learning_rate": 1.8020436295177795e-05,
      "loss": 0.7791,
      "step": 155
    },
    {
      "epoch": 3.5454545454545454,
      "grad_norm": 0.038527488708496094,
      "learning_rate": 1.7317175291094117e-05,
      "loss": 0.8413,
      "step": 156
    },
    {
      "epoch": 3.5681818181818183,
      "grad_norm": 0.04014235734939575,
      "learning_rate": 1.6644943340465982e-05,
      "loss": 0.8779,
      "step": 157
    },
    {
      "epoch": 3.590909090909091,
      "grad_norm": 0.03881339728832245,
      "learning_rate": 1.6003978331627874e-05,
      "loss": 0.9097,
      "step": 158
    },
    {
      "epoch": 3.6136363636363638,
      "grad_norm": 0.03548410162329674,
      "learning_rate": 1.53945070882204e-05,
      "loss": 0.7811,
      "step": 159
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.03763340041041374,
      "learning_rate": 1.4816745288922454e-05,
      "loss": 0.8103,
      "step": 160
    },
    {
      "epoch": 3.659090909090909,
      "grad_norm": 0.03936903923749924,
      "learning_rate": 1.4270897391127048e-05,
      "loss": 0.9082,
      "step": 161
    },
    {
      "epoch": 3.6818181818181817,
      "grad_norm": 0.0402388721704483,
      "learning_rate": 1.3757156558588402e-05,
      "loss": 0.9214,
      "step": 162
    },
    {
      "epoch": 3.7045454545454546,
      "grad_norm": 0.03981705754995346,
      "learning_rate": 1.3275704593065354e-05,
      "loss": 0.873,
      "step": 163
    },
    {
      "epoch": 3.7272727272727275,
      "grad_norm": 0.04118829965591431,
      "learning_rate": 1.2826711869985789e-05,
      "loss": 0.9639,
      "step": 164
    },
    {
      "epoch": 3.75,
      "grad_norm": 0.03788629546761513,
      "learning_rate": 1.241033727815433e-05,
      "loss": 0.7242,
      "step": 165
    },
    {
      "epoch": 3.7727272727272725,
      "grad_norm": 0.03944149613380432,
      "learning_rate": 1.2026728163525116e-05,
      "loss": 0.8921,
      "step": 166
    },
    {
      "epoch": 3.7954545454545454,
      "grad_norm": 0.039055123925209045,
      "learning_rate": 1.1676020277059198e-05,
      "loss": 0.8823,
      "step": 167
    },
    {
      "epoch": 3.8181818181818183,
      "grad_norm": 0.041722510010004044,
      "learning_rate": 1.1358337726685295e-05,
      "loss": 0.9233,
      "step": 168
    },
    {
      "epoch": 3.840909090909091,
      "grad_norm": 0.03798840194940567,
      "learning_rate": 1.10737929333806e-05,
      "loss": 0.8643,
      "step": 169
    },
    {
      "epoch": 3.8636363636363638,
      "grad_norm": 0.03837035968899727,
      "learning_rate": 1.0822486591387454e-05,
      "loss": 0.8428,
      "step": 170
    },
    {
      "epoch": 3.8863636363636362,
      "grad_norm": 0.03759411722421646,
      "learning_rate": 1.060450763257989e-05,
      "loss": 0.8672,
      "step": 171
    },
    {
      "epoch": 3.909090909090909,
      "grad_norm": 0.03673923388123512,
      "learning_rate": 1.041993319499247e-05,
      "loss": 0.7627,
      "step": 172
    },
    {
      "epoch": 3.9318181818181817,
      "grad_norm": 0.0386042557656765,
      "learning_rate": 1.0268828595522896e-05,
      "loss": 0.8857,
      "step": 173
    },
    {
      "epoch": 3.9545454545454546,
      "grad_norm": 0.0360184982419014,
      "learning_rate": 1.0151247306817713e-05,
      "loss": 0.6814,
      "step": 174
    },
    {
      "epoch": 3.9772727272727275,
      "grad_norm": 0.0401356965303421,
      "learning_rate": 1.0067230938349514e-05,
      "loss": 0.8589,
      "step": 175
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.0426001101732254,
      "learning_rate": 1.0016809221692297e-05,
      "loss": 0.8545,
      "step": 176
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.9586181640625,
      "eval_runtime": 2.1886,
      "eval_samples_per_second": 3.198,
      "eval_steps_per_second": 0.457,
      "step": 176
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 176,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2903686563124216e+19,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}