VLZip-3B / trainer_state.json
SII-BIU's picture
Upload folder using huggingface_hub
e464a61 verified
Raw
History Blame Contribute Delete
135 kB
{
"best_global_step": 500,
"best_metric": 1.6160000562667847,
"best_model_checkpoint": "/path/to/vlzip-stage4/checkpoint-500",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 772,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0012953367875647669,
"grad_norm": 3.961988687515259,
"learning_rate": 0.0,
"loss": 3.5942,
"step": 1
},
{
"epoch": 0.0025906735751295338,
"grad_norm": 4.237163543701172,
"learning_rate": 4.1666666666666667e-07,
"loss": 3.4457,
"step": 2
},
{
"epoch": 0.0038860103626943004,
"grad_norm": 3.947713851928711,
"learning_rate": 8.333333333333333e-07,
"loss": 3.4934,
"step": 3
},
{
"epoch": 0.0051813471502590676,
"grad_norm": 4.103781700134277,
"learning_rate": 1.25e-06,
"loss": 3.5077,
"step": 4
},
{
"epoch": 0.006476683937823834,
"grad_norm": 4.139891624450684,
"learning_rate": 1.6666666666666667e-06,
"loss": 3.3517,
"step": 5
},
{
"epoch": 0.007772020725388601,
"grad_norm": 4.1965508460998535,
"learning_rate": 2.0833333333333334e-06,
"loss": 3.2401,
"step": 6
},
{
"epoch": 0.009067357512953367,
"grad_norm": 3.610322952270508,
"learning_rate": 2.5e-06,
"loss": 3.4581,
"step": 7
},
{
"epoch": 0.010362694300518135,
"grad_norm": 2.114593744277954,
"learning_rate": 2.916666666666667e-06,
"loss": 2.9238,
"step": 8
},
{
"epoch": 0.011658031088082901,
"grad_norm": 2.2600114345550537,
"learning_rate": 3.3333333333333333e-06,
"loss": 2.9519,
"step": 9
},
{
"epoch": 0.012953367875647668,
"grad_norm": 1.712815284729004,
"learning_rate": 3.7500000000000005e-06,
"loss": 2.9783,
"step": 10
},
{
"epoch": 0.014248704663212436,
"grad_norm": 1.186911702156067,
"learning_rate": 4.166666666666667e-06,
"loss": 2.5526,
"step": 11
},
{
"epoch": 0.015544041450777202,
"grad_norm": 1.2582861185073853,
"learning_rate": 4.583333333333333e-06,
"loss": 2.485,
"step": 12
},
{
"epoch": 0.01683937823834197,
"grad_norm": 1.2093693017959595,
"learning_rate": 5e-06,
"loss": 2.4841,
"step": 13
},
{
"epoch": 0.018134715025906734,
"grad_norm": 1.1385802030563354,
"learning_rate": 5.416666666666667e-06,
"loss": 2.6597,
"step": 14
},
{
"epoch": 0.019430051813471502,
"grad_norm": 0.7675687074661255,
"learning_rate": 5.833333333333334e-06,
"loss": 2.7972,
"step": 15
},
{
"epoch": 0.02072538860103627,
"grad_norm": 0.7423077821731567,
"learning_rate": 6.25e-06,
"loss": 2.326,
"step": 16
},
{
"epoch": 0.022020725388601035,
"grad_norm": 0.7392103672027588,
"learning_rate": 6.666666666666667e-06,
"loss": 2.555,
"step": 17
},
{
"epoch": 0.023316062176165803,
"grad_norm": 0.7092238664627075,
"learning_rate": 7.083333333333335e-06,
"loss": 2.4831,
"step": 18
},
{
"epoch": 0.02461139896373057,
"grad_norm": 0.6350530385971069,
"learning_rate": 7.500000000000001e-06,
"loss": 2.4156,
"step": 19
},
{
"epoch": 0.025906735751295335,
"grad_norm": 1.1924011707305908,
"learning_rate": 7.916666666666667e-06,
"loss": 2.0769,
"step": 20
},
{
"epoch": 0.027202072538860103,
"grad_norm": 1.100220799446106,
"learning_rate": 8.333333333333334e-06,
"loss": 2.3253,
"step": 21
},
{
"epoch": 0.02849740932642487,
"grad_norm": 1.2065426111221313,
"learning_rate": 8.750000000000001e-06,
"loss": 2.1464,
"step": 22
},
{
"epoch": 0.029792746113989636,
"grad_norm": 0.805694043636322,
"learning_rate": 9.166666666666666e-06,
"loss": 2.3394,
"step": 23
},
{
"epoch": 0.031088082901554404,
"grad_norm": 1.0455610752105713,
"learning_rate": 9.583333333333335e-06,
"loss": 2.4677,
"step": 24
},
{
"epoch": 0.03238341968911917,
"grad_norm": 1.7390717267990112,
"learning_rate": 1e-05,
"loss": 2.3276,
"step": 25
},
{
"epoch": 0.03367875647668394,
"grad_norm": 3.5062222480773926,
"learning_rate": 9.999955900271076e-06,
"loss": 2.1411,
"step": 26
},
{
"epoch": 0.034974093264248704,
"grad_norm": 1.047017216682434,
"learning_rate": 9.999823601862217e-06,
"loss": 2.2771,
"step": 27
},
{
"epoch": 0.03626943005181347,
"grad_norm": 1.6287448406219482,
"learning_rate": 9.999603107107153e-06,
"loss": 2.1028,
"step": 28
},
{
"epoch": 0.03756476683937824,
"grad_norm": 1.4858123064041138,
"learning_rate": 9.999294419895389e-06,
"loss": 2.3778,
"step": 29
},
{
"epoch": 0.038860103626943004,
"grad_norm": 0.6668227314949036,
"learning_rate": 9.998897545672133e-06,
"loss": 2.3638,
"step": 30
},
{
"epoch": 0.04015544041450777,
"grad_norm": 1.0612903833389282,
"learning_rate": 9.998412491438201e-06,
"loss": 2.462,
"step": 31
},
{
"epoch": 0.04145077720207254,
"grad_norm": 0.6636863946914673,
"learning_rate": 9.9978392657499e-06,
"loss": 2.3579,
"step": 32
},
{
"epoch": 0.042746113989637305,
"grad_norm": 0.781121551990509,
"learning_rate": 9.99717787871887e-06,
"loss": 2.0975,
"step": 33
},
{
"epoch": 0.04404145077720207,
"grad_norm": 0.9479854702949524,
"learning_rate": 9.996428342011902e-06,
"loss": 2.2859,
"step": 34
},
{
"epoch": 0.04533678756476684,
"grad_norm": 0.8649857044219971,
"learning_rate": 9.995590668850745e-06,
"loss": 2.1732,
"step": 35
},
{
"epoch": 0.046632124352331605,
"grad_norm": 0.591148853302002,
"learning_rate": 9.994664874011864e-06,
"loss": 2.2894,
"step": 36
},
{
"epoch": 0.04792746113989637,
"grad_norm": 0.7663190960884094,
"learning_rate": 9.993650973826177e-06,
"loss": 2.2415,
"step": 37
},
{
"epoch": 0.04922279792746114,
"grad_norm": 0.6417776346206665,
"learning_rate": 9.992548986178774e-06,
"loss": 2.2576,
"step": 38
},
{
"epoch": 0.050518134715025906,
"grad_norm": 0.7108107805252075,
"learning_rate": 9.991358930508599e-06,
"loss": 2.2915,
"step": 39
},
{
"epoch": 0.05181347150259067,
"grad_norm": 0.7626336812973022,
"learning_rate": 9.990080827808104e-06,
"loss": 2.2403,
"step": 40
},
{
"epoch": 0.05310880829015544,
"grad_norm": 0.6871465444564819,
"learning_rate": 9.988714700622882e-06,
"loss": 2.2173,
"step": 41
},
{
"epoch": 0.054404145077720206,
"grad_norm": 0.6497645974159241,
"learning_rate": 9.987260573051268e-06,
"loss": 2.1961,
"step": 42
},
{
"epoch": 0.05569948186528497,
"grad_norm": 0.5896015763282776,
"learning_rate": 9.985718470743916e-06,
"loss": 2.1507,
"step": 43
},
{
"epoch": 0.05699481865284974,
"grad_norm": 0.9964750409126282,
"learning_rate": 9.984088420903343e-06,
"loss": 2.4303,
"step": 44
},
{
"epoch": 0.05829015544041451,
"grad_norm": 0.7197266221046448,
"learning_rate": 9.982370452283451e-06,
"loss": 2.518,
"step": 45
},
{
"epoch": 0.05958549222797927,
"grad_norm": 0.7837846279144287,
"learning_rate": 9.980564595189019e-06,
"loss": 2.3789,
"step": 46
},
{
"epoch": 0.06088082901554404,
"grad_norm": 1.0444233417510986,
"learning_rate": 9.978670881475173e-06,
"loss": 2.2147,
"step": 47
},
{
"epoch": 0.06217616580310881,
"grad_norm": 0.654209315776825,
"learning_rate": 9.976689344546817e-06,
"loss": 2.3509,
"step": 48
},
{
"epoch": 0.06347150259067358,
"grad_norm": 0.8203169703483582,
"learning_rate": 9.974620019358046e-06,
"loss": 2.1634,
"step": 49
},
{
"epoch": 0.06476683937823834,
"grad_norm": 1.495806336402893,
"learning_rate": 9.972462942411531e-06,
"loss": 2.3835,
"step": 50
},
{
"epoch": 0.06606217616580311,
"grad_norm": 0.6987830400466919,
"learning_rate": 9.97021815175788e-06,
"loss": 2.0951,
"step": 51
},
{
"epoch": 0.06735751295336788,
"grad_norm": 0.9444453716278076,
"learning_rate": 9.967885686994953e-06,
"loss": 2.2561,
"step": 52
},
{
"epoch": 0.06865284974093264,
"grad_norm": 1.0102063417434692,
"learning_rate": 9.965465589267176e-06,
"loss": 2.1208,
"step": 53
},
{
"epoch": 0.06994818652849741,
"grad_norm": 1.6975420713424683,
"learning_rate": 9.962957901264811e-06,
"loss": 2.3005,
"step": 54
},
{
"epoch": 0.07124352331606218,
"grad_norm": 0.9733851552009583,
"learning_rate": 9.960362667223202e-06,
"loss": 2.3454,
"step": 55
},
{
"epoch": 0.07253886010362694,
"grad_norm": 1.0678082704544067,
"learning_rate": 9.957679932921997e-06,
"loss": 2.3193,
"step": 56
},
{
"epoch": 0.07383419689119171,
"grad_norm": 0.6987249255180359,
"learning_rate": 9.954909745684339e-06,
"loss": 2.2726,
"step": 57
},
{
"epoch": 0.07512953367875648,
"grad_norm": 0.82325679063797,
"learning_rate": 9.952052154376027e-06,
"loss": 2.216,
"step": 58
},
{
"epoch": 0.07642487046632124,
"grad_norm": 0.6493696570396423,
"learning_rate": 9.949107209404664e-06,
"loss": 2.1224,
"step": 59
},
{
"epoch": 0.07772020725388601,
"grad_norm": 0.7731466889381409,
"learning_rate": 9.94607496271876e-06,
"loss": 2.2307,
"step": 60
},
{
"epoch": 0.07901554404145078,
"grad_norm": 0.78420090675354,
"learning_rate": 9.94295546780682e-06,
"loss": 2.0552,
"step": 61
},
{
"epoch": 0.08031088082901554,
"grad_norm": 0.7467367649078369,
"learning_rate": 9.939748779696391e-06,
"loss": 2.2447,
"step": 62
},
{
"epoch": 0.08160621761658031,
"grad_norm": 0.765451967716217,
"learning_rate": 9.936454954953108e-06,
"loss": 2.0992,
"step": 63
},
{
"epoch": 0.08290155440414508,
"grad_norm": 0.755013644695282,
"learning_rate": 9.933074051679681e-06,
"loss": 2.1052,
"step": 64
},
{
"epoch": 0.08419689119170984,
"grad_norm": 0.8792553544044495,
"learning_rate": 9.929606129514875e-06,
"loss": 2.2379,
"step": 65
},
{
"epoch": 0.08549222797927461,
"grad_norm": 0.8433871865272522,
"learning_rate": 9.926051249632465e-06,
"loss": 2.1096,
"step": 66
},
{
"epoch": 0.08678756476683938,
"grad_norm": 0.8772946000099182,
"learning_rate": 9.922409474740142e-06,
"loss": 2.0573,
"step": 67
},
{
"epoch": 0.08808290155440414,
"grad_norm": 0.7098591923713684,
"learning_rate": 9.918680869078425e-06,
"loss": 2.1351,
"step": 68
},
{
"epoch": 0.08937823834196891,
"grad_norm": 0.8203537464141846,
"learning_rate": 9.91486549841951e-06,
"loss": 2.101,
"step": 69
},
{
"epoch": 0.09067357512953368,
"grad_norm": 0.752184271812439,
"learning_rate": 9.910963430066123e-06,
"loss": 1.9835,
"step": 70
},
{
"epoch": 0.09196891191709844,
"grad_norm": 0.8483728170394897,
"learning_rate": 9.906974732850327e-06,
"loss": 2.0507,
"step": 71
},
{
"epoch": 0.09326424870466321,
"grad_norm": 0.7311016321182251,
"learning_rate": 9.902899477132306e-06,
"loss": 2.2265,
"step": 72
},
{
"epoch": 0.09455958549222798,
"grad_norm": 0.746991753578186,
"learning_rate": 9.898737734799134e-06,
"loss": 2.1962,
"step": 73
},
{
"epoch": 0.09585492227979274,
"grad_norm": 0.840429961681366,
"learning_rate": 9.89448957926349e-06,
"loss": 2.049,
"step": 74
},
{
"epoch": 0.09715025906735751,
"grad_norm": 0.732631504535675,
"learning_rate": 9.890155085462376e-06,
"loss": 2.0014,
"step": 75
},
{
"epoch": 0.09844559585492228,
"grad_norm": 0.9324226379394531,
"learning_rate": 9.885734329855798e-06,
"loss": 2.1824,
"step": 76
},
{
"epoch": 0.09974093264248704,
"grad_norm": 0.8776330351829529,
"learning_rate": 9.881227390425404e-06,
"loss": 2.0997,
"step": 77
},
{
"epoch": 0.10103626943005181,
"grad_norm": 0.7887237668037415,
"learning_rate": 9.876634346673114e-06,
"loss": 1.9468,
"step": 78
},
{
"epoch": 0.10233160621761658,
"grad_norm": 0.7851561307907104,
"learning_rate": 9.871955279619721e-06,
"loss": 2.1354,
"step": 79
},
{
"epoch": 0.10362694300518134,
"grad_norm": 1.1628029346466064,
"learning_rate": 9.867190271803466e-06,
"loss": 2.2231,
"step": 80
},
{
"epoch": 0.10492227979274611,
"grad_norm": 0.7979488372802734,
"learning_rate": 9.862339407278564e-06,
"loss": 2.0726,
"step": 81
},
{
"epoch": 0.10621761658031088,
"grad_norm": 0.7587772011756897,
"learning_rate": 9.857402771613744e-06,
"loss": 2.0956,
"step": 82
},
{
"epoch": 0.10751295336787564,
"grad_norm": 0.816105306148529,
"learning_rate": 9.852380451890723e-06,
"loss": 2.1771,
"step": 83
},
{
"epoch": 0.10880829015544041,
"grad_norm": 0.6705862283706665,
"learning_rate": 9.847272536702674e-06,
"loss": 2.0122,
"step": 84
},
{
"epoch": 0.11010362694300518,
"grad_norm": 0.7731279134750366,
"learning_rate": 9.84207911615267e-06,
"loss": 2.1042,
"step": 85
},
{
"epoch": 0.11139896373056994,
"grad_norm": 0.9606695175170898,
"learning_rate": 9.836800281852084e-06,
"loss": 2.0314,
"step": 86
},
{
"epoch": 0.11269430051813471,
"grad_norm": 0.8623000383377075,
"learning_rate": 9.83143612691898e-06,
"loss": 2.126,
"step": 87
},
{
"epoch": 0.11398963730569948,
"grad_norm": 0.955909013748169,
"learning_rate": 9.825986745976472e-06,
"loss": 2.1247,
"step": 88
},
{
"epoch": 0.11528497409326424,
"grad_norm": 1.1289267539978027,
"learning_rate": 9.82045223515105e-06,
"loss": 2.1497,
"step": 89
},
{
"epoch": 0.11658031088082901,
"grad_norm": 0.955631673336029,
"learning_rate": 9.814832692070879e-06,
"loss": 2.2668,
"step": 90
},
{
"epoch": 0.11787564766839378,
"grad_norm": 1.339616298675537,
"learning_rate": 9.809128215864096e-06,
"loss": 1.913,
"step": 91
},
{
"epoch": 0.11917098445595854,
"grad_norm": 1.027266502380371,
"learning_rate": 9.80333890715704e-06,
"loss": 2.1082,
"step": 92
},
{
"epoch": 0.12046632124352331,
"grad_norm": 0.8723363876342773,
"learning_rate": 9.797464868072489e-06,
"loss": 2.0449,
"step": 93
},
{
"epoch": 0.12176165803108809,
"grad_norm": 0.9281970262527466,
"learning_rate": 9.791506202227853e-06,
"loss": 2.0743,
"step": 94
},
{
"epoch": 0.12305699481865284,
"grad_norm": 0.980986475944519,
"learning_rate": 9.785463014733356e-06,
"loss": 2.1245,
"step": 95
},
{
"epoch": 0.12435233160621761,
"grad_norm": 0.8615231513977051,
"learning_rate": 9.779335412190168e-06,
"loss": 1.9081,
"step": 96
},
{
"epoch": 0.12564766839378239,
"grad_norm": 0.852705180644989,
"learning_rate": 9.773123502688532e-06,
"loss": 2.1476,
"step": 97
},
{
"epoch": 0.12694300518134716,
"grad_norm": 0.8371450304985046,
"learning_rate": 9.766827395805862e-06,
"loss": 2.0162,
"step": 98
},
{
"epoch": 0.12823834196891193,
"grad_norm": 0.8834793567657471,
"learning_rate": 9.760447202604796e-06,
"loss": 1.8537,
"step": 99
},
{
"epoch": 0.12953367875647667,
"grad_norm": 0.9118489623069763,
"learning_rate": 9.753983035631254e-06,
"loss": 2.108,
"step": 100
},
{
"epoch": 0.13082901554404144,
"grad_norm": 0.9087600708007812,
"learning_rate": 9.747435008912438e-06,
"loss": 2.0516,
"step": 101
},
{
"epoch": 0.13212435233160622,
"grad_norm": 2.1685822010040283,
"learning_rate": 9.74080323795483e-06,
"loss": 2.1669,
"step": 102
},
{
"epoch": 0.133419689119171,
"grad_norm": 0.9142223596572876,
"learning_rate": 9.734087839742152e-06,
"loss": 2.0137,
"step": 103
},
{
"epoch": 0.13471502590673576,
"grad_norm": 0.9200546145439148,
"learning_rate": 9.7272889327333e-06,
"loss": 2.0868,
"step": 104
},
{
"epoch": 0.13601036269430053,
"grad_norm": 0.8486931324005127,
"learning_rate": 9.720406636860252e-06,
"loss": 1.9464,
"step": 105
},
{
"epoch": 0.13730569948186527,
"grad_norm": 1.0030617713928223,
"learning_rate": 9.713441073525968e-06,
"loss": 2.0824,
"step": 106
},
{
"epoch": 0.13860103626943004,
"grad_norm": 1.1330851316452026,
"learning_rate": 9.706392365602224e-06,
"loss": 1.9878,
"step": 107
},
{
"epoch": 0.13989637305699482,
"grad_norm": 0.9762888550758362,
"learning_rate": 9.699260637427468e-06,
"loss": 2.0657,
"step": 108
},
{
"epoch": 0.1411917098445596,
"grad_norm": 1.104365348815918,
"learning_rate": 9.69204601480461e-06,
"loss": 1.8497,
"step": 109
},
{
"epoch": 0.14248704663212436,
"grad_norm": 1.0455023050308228,
"learning_rate": 9.68474862499881e-06,
"loss": 1.9817,
"step": 110
},
{
"epoch": 0.14378238341968913,
"grad_norm": 1.0105725526809692,
"learning_rate": 9.677368596735232e-06,
"loss": 1.9604,
"step": 111
},
{
"epoch": 0.14507772020725387,
"grad_norm": 1.4316058158874512,
"learning_rate": 9.669906060196778e-06,
"loss": 1.8574,
"step": 112
},
{
"epoch": 0.14637305699481865,
"grad_norm": 1.1934871673583984,
"learning_rate": 9.66236114702178e-06,
"loss": 1.8443,
"step": 113
},
{
"epoch": 0.14766839378238342,
"grad_norm": 1.037026286125183,
"learning_rate": 9.65473399030169e-06,
"loss": 2.1034,
"step": 114
},
{
"epoch": 0.1489637305699482,
"grad_norm": 1.0123029947280884,
"learning_rate": 9.647024724578724e-06,
"loss": 1.9682,
"step": 115
},
{
"epoch": 0.15025906735751296,
"grad_norm": 1.0621418952941895,
"learning_rate": 9.639233485843495e-06,
"loss": 1.9351,
"step": 116
},
{
"epoch": 0.15155440414507773,
"grad_norm": 1.1957042217254639,
"learning_rate": 9.631360411532609e-06,
"loss": 2.0339,
"step": 117
},
{
"epoch": 0.15284974093264247,
"grad_norm": 0.8379104733467102,
"learning_rate": 9.623405640526244e-06,
"loss": 2.0601,
"step": 118
},
{
"epoch": 0.15414507772020725,
"grad_norm": 0.9850704669952393,
"learning_rate": 9.615369313145695e-06,
"loss": 2.0911,
"step": 119
},
{
"epoch": 0.15544041450777202,
"grad_norm": 0.8857843279838562,
"learning_rate": 9.60725157115091e-06,
"loss": 1.8598,
"step": 120
},
{
"epoch": 0.1567357512953368,
"grad_norm": 1.175421118736267,
"learning_rate": 9.599052557737973e-06,
"loss": 2.178,
"step": 121
},
{
"epoch": 0.15803108808290156,
"grad_norm": 1.030266284942627,
"learning_rate": 9.590772417536595e-06,
"loss": 1.9296,
"step": 122
},
{
"epoch": 0.15932642487046633,
"grad_norm": 1.0185019969940186,
"learning_rate": 9.58241129660755e-06,
"loss": 1.8519,
"step": 123
},
{
"epoch": 0.16062176165803108,
"grad_norm": 0.9762274622917175,
"learning_rate": 9.573969342440107e-06,
"loss": 1.9746,
"step": 124
},
{
"epoch": 0.16191709844559585,
"grad_norm": 0.8578293919563293,
"learning_rate": 9.565446703949417e-06,
"loss": 1.7968,
"step": 125
},
{
"epoch": 0.16321243523316062,
"grad_norm": 0.8589891195297241,
"learning_rate": 9.556843531473903e-06,
"loss": 2.0645,
"step": 126
},
{
"epoch": 0.1645077720207254,
"grad_norm": 1.1950880289077759,
"learning_rate": 9.548159976772593e-06,
"loss": 1.8846,
"step": 127
},
{
"epoch": 0.16580310880829016,
"grad_norm": 0.9333671927452087,
"learning_rate": 9.53939619302245e-06,
"loss": 1.9932,
"step": 128
},
{
"epoch": 0.16709844559585493,
"grad_norm": 1.0318408012390137,
"learning_rate": 9.530552334815672e-06,
"loss": 2.0922,
"step": 129
},
{
"epoch": 0.16839378238341968,
"grad_norm": 1.160930871963501,
"learning_rate": 9.521628558156955e-06,
"loss": 1.7745,
"step": 130
},
{
"epoch": 0.16968911917098445,
"grad_norm": 1.0356159210205078,
"learning_rate": 9.512625020460754e-06,
"loss": 1.8838,
"step": 131
},
{
"epoch": 0.17098445595854922,
"grad_norm": 0.9528965950012207,
"learning_rate": 9.503541880548496e-06,
"loss": 1.8735,
"step": 132
},
{
"epoch": 0.172279792746114,
"grad_norm": 0.8905000686645508,
"learning_rate": 9.494379298645788e-06,
"loss": 1.9654,
"step": 133
},
{
"epoch": 0.17357512953367876,
"grad_norm": 1.0470200777053833,
"learning_rate": 9.485137436379577e-06,
"loss": 2.0082,
"step": 134
},
{
"epoch": 0.17487046632124353,
"grad_norm": 1.0726947784423828,
"learning_rate": 9.475816456775313e-06,
"loss": 2.0453,
"step": 135
},
{
"epoch": 0.17616580310880828,
"grad_norm": 1.0658563375473022,
"learning_rate": 9.466416524254065e-06,
"loss": 1.9271,
"step": 136
},
{
"epoch": 0.17746113989637305,
"grad_norm": 1.0881139039993286,
"learning_rate": 9.456937804629623e-06,
"loss": 1.9145,
"step": 137
},
{
"epoch": 0.17875647668393782,
"grad_norm": 1.1098933219909668,
"learning_rate": 9.447380465105575e-06,
"loss": 1.9094,
"step": 138
},
{
"epoch": 0.1800518134715026,
"grad_norm": 1.0471988916397095,
"learning_rate": 9.437744674272353e-06,
"loss": 2.0622,
"step": 139
},
{
"epoch": 0.18134715025906736,
"grad_norm": 0.9718754291534424,
"learning_rate": 9.428030602104264e-06,
"loss": 2.0524,
"step": 140
},
{
"epoch": 0.18264248704663213,
"grad_norm": 1.09941828250885,
"learning_rate": 9.418238419956484e-06,
"loss": 2.126,
"step": 141
},
{
"epoch": 0.18393782383419688,
"grad_norm": 1.6236449480056763,
"learning_rate": 9.408368300562047e-06,
"loss": 1.9437,
"step": 142
},
{
"epoch": 0.18523316062176165,
"grad_norm": 0.9504075050354004,
"learning_rate": 9.398420418028789e-06,
"loss": 1.8707,
"step": 143
},
{
"epoch": 0.18652849740932642,
"grad_norm": 1.9062823057174683,
"learning_rate": 9.388394947836278e-06,
"loss": 1.8351,
"step": 144
},
{
"epoch": 0.1878238341968912,
"grad_norm": 1.2809261083602905,
"learning_rate": 9.378292066832723e-06,
"loss": 2.0364,
"step": 145
},
{
"epoch": 0.18911917098445596,
"grad_norm": 0.9997020363807678,
"learning_rate": 9.368111953231849e-06,
"loss": 1.8263,
"step": 146
},
{
"epoch": 0.19041450777202074,
"grad_norm": 0.9715490937232971,
"learning_rate": 9.357854786609754e-06,
"loss": 1.9957,
"step": 147
},
{
"epoch": 0.19170984455958548,
"grad_norm": 1.8801630735397339,
"learning_rate": 9.347520747901745e-06,
"loss": 1.8042,
"step": 148
},
{
"epoch": 0.19300518134715025,
"grad_norm": 0.9815563559532166,
"learning_rate": 9.33711001939915e-06,
"loss": 2.0121,
"step": 149
},
{
"epoch": 0.19430051813471502,
"grad_norm": 0.9765826463699341,
"learning_rate": 9.326622784746083e-06,
"loss": 1.9974,
"step": 150
},
{
"epoch": 0.1955958549222798,
"grad_norm": 1.181368112564087,
"learning_rate": 9.316059228936231e-06,
"loss": 1.861,
"step": 151
},
{
"epoch": 0.19689119170984457,
"grad_norm": 1.0723419189453125,
"learning_rate": 9.305419538309573e-06,
"loss": 1.8014,
"step": 152
},
{
"epoch": 0.19818652849740934,
"grad_norm": 3.325817823410034,
"learning_rate": 9.294703900549096e-06,
"loss": 1.9829,
"step": 153
},
{
"epoch": 0.19948186528497408,
"grad_norm": 1.0286307334899902,
"learning_rate": 9.283912504677487e-06,
"loss": 1.8462,
"step": 154
},
{
"epoch": 0.20077720207253885,
"grad_norm": 2.030907154083252,
"learning_rate": 9.273045541053805e-06,
"loss": 1.782,
"step": 155
},
{
"epoch": 0.20207253886010362,
"grad_norm": 1.1784623861312866,
"learning_rate": 9.262103201370103e-06,
"loss": 1.9296,
"step": 156
},
{
"epoch": 0.2033678756476684,
"grad_norm": 1.3142341375350952,
"learning_rate": 9.251085678648072e-06,
"loss": 1.9228,
"step": 157
},
{
"epoch": 0.20466321243523317,
"grad_norm": 1.1284396648406982,
"learning_rate": 9.239993167235614e-06,
"loss": 2.0876,
"step": 158
},
{
"epoch": 0.20595854922279794,
"grad_norm": 1.1834419965744019,
"learning_rate": 9.22882586280343e-06,
"loss": 1.8292,
"step": 159
},
{
"epoch": 0.20725388601036268,
"grad_norm": 0.9924725890159607,
"learning_rate": 9.21758396234156e-06,
"loss": 1.8513,
"step": 160
},
{
"epoch": 0.20854922279792745,
"grad_norm": 3.2172844409942627,
"learning_rate": 9.206267664155906e-06,
"loss": 1.9895,
"step": 161
},
{
"epoch": 0.20984455958549222,
"grad_norm": 1.2252551317214966,
"learning_rate": 9.194877167864745e-06,
"loss": 1.9236,
"step": 162
},
{
"epoch": 0.211139896373057,
"grad_norm": 0.9770820736885071,
"learning_rate": 9.183412674395193e-06,
"loss": 1.9062,
"step": 163
},
{
"epoch": 0.21243523316062177,
"grad_norm": 1.036807894706726,
"learning_rate": 9.171874385979673e-06,
"loss": 2.0328,
"step": 164
},
{
"epoch": 0.21373056994818654,
"grad_norm": 1.2175438404083252,
"learning_rate": 9.160262506152343e-06,
"loss": 1.766,
"step": 165
},
{
"epoch": 0.21502590673575128,
"grad_norm": 1.2329623699188232,
"learning_rate": 9.148577239745501e-06,
"loss": 1.8496,
"step": 166
},
{
"epoch": 0.21632124352331605,
"grad_norm": 1.1274627447128296,
"learning_rate": 9.136818792885981e-06,
"loss": 1.915,
"step": 167
},
{
"epoch": 0.21761658031088082,
"grad_norm": 1.1261439323425293,
"learning_rate": 9.124987372991512e-06,
"loss": 1.7809,
"step": 168
},
{
"epoch": 0.2189119170984456,
"grad_norm": 1.107468605041504,
"learning_rate": 9.113083188767057e-06,
"loss": 1.8009,
"step": 169
},
{
"epoch": 0.22020725388601037,
"grad_norm": 1.3558907508850098,
"learning_rate": 9.101106450201133e-06,
"loss": 1.8587,
"step": 170
},
{
"epoch": 0.22150259067357514,
"grad_norm": 1.2380905151367188,
"learning_rate": 9.089057368562113e-06,
"loss": 1.7511,
"step": 171
},
{
"epoch": 0.22279792746113988,
"grad_norm": 1.2809183597564697,
"learning_rate": 9.07693615639449e-06,
"loss": 1.9445,
"step": 172
},
{
"epoch": 0.22409326424870465,
"grad_norm": 1.1314321756362915,
"learning_rate": 9.064743027515127e-06,
"loss": 2.0023,
"step": 173
},
{
"epoch": 0.22538860103626943,
"grad_norm": 1.0015232563018799,
"learning_rate": 9.052478197009504e-06,
"loss": 1.8165,
"step": 174
},
{
"epoch": 0.2266839378238342,
"grad_norm": 1.163474678993225,
"learning_rate": 9.040141881227897e-06,
"loss": 2.009,
"step": 175
},
{
"epoch": 0.22797927461139897,
"grad_norm": 1.0280187129974365,
"learning_rate": 9.027734297781576e-06,
"loss": 1.9904,
"step": 176
},
{
"epoch": 0.22927461139896374,
"grad_norm": 1.3255523443222046,
"learning_rate": 9.015255665538972e-06,
"loss": 1.7671,
"step": 177
},
{
"epoch": 0.23056994818652848,
"grad_norm": 1.0369282960891724,
"learning_rate": 9.002706204621802e-06,
"loss": 1.7188,
"step": 178
},
{
"epoch": 0.23186528497409326,
"grad_norm": 1.0396777391433716,
"learning_rate": 8.990086136401199e-06,
"loss": 1.6908,
"step": 179
},
{
"epoch": 0.23316062176165803,
"grad_norm": 1.2296425104141235,
"learning_rate": 8.977395683493793e-06,
"loss": 1.821,
"step": 180
},
{
"epoch": 0.2344559585492228,
"grad_norm": 1.0347245931625366,
"learning_rate": 8.964635069757803e-06,
"loss": 1.8169,
"step": 181
},
{
"epoch": 0.23575129533678757,
"grad_norm": 1.122043251991272,
"learning_rate": 8.951804520289067e-06,
"loss": 1.8777,
"step": 182
},
{
"epoch": 0.23704663212435234,
"grad_norm": 0.9733263254165649,
"learning_rate": 8.938904261417088e-06,
"loss": 1.8081,
"step": 183
},
{
"epoch": 0.23834196891191708,
"grad_norm": 1.0532820224761963,
"learning_rate": 8.925934520701034e-06,
"loss": 1.9201,
"step": 184
},
{
"epoch": 0.23963730569948186,
"grad_norm": 1.0515098571777344,
"learning_rate": 8.912895526925726e-06,
"loss": 1.9071,
"step": 185
},
{
"epoch": 0.24093264248704663,
"grad_norm": 1.121208906173706,
"learning_rate": 8.899787510097598e-06,
"loss": 1.8093,
"step": 186
},
{
"epoch": 0.2422279792746114,
"grad_norm": 1.170974850654602,
"learning_rate": 8.886610701440648e-06,
"loss": 1.8721,
"step": 187
},
{
"epoch": 0.24352331606217617,
"grad_norm": 0.9363534450531006,
"learning_rate": 8.873365333392349e-06,
"loss": 1.73,
"step": 188
},
{
"epoch": 0.24481865284974094,
"grad_norm": 0.9910795092582703,
"learning_rate": 8.86005163959956e-06,
"loss": 1.8079,
"step": 189
},
{
"epoch": 0.24611398963730569,
"grad_norm": 1.0895111560821533,
"learning_rate": 8.846669854914395e-06,
"loss": 1.8131,
"step": 190
},
{
"epoch": 0.24740932642487046,
"grad_norm": 1.3464375734329224,
"learning_rate": 8.833220215390085e-06,
"loss": 1.6697,
"step": 191
},
{
"epoch": 0.24870466321243523,
"grad_norm": 1.6414902210235596,
"learning_rate": 8.819702958276812e-06,
"loss": 1.739,
"step": 192
},
{
"epoch": 0.25,
"grad_norm": 1.2388039827346802,
"learning_rate": 8.806118322017525e-06,
"loss": 1.8006,
"step": 193
},
{
"epoch": 0.25129533678756477,
"grad_norm": 1.2335573434829712,
"learning_rate": 8.79246654624374e-06,
"loss": 1.6888,
"step": 194
},
{
"epoch": 0.25259067357512954,
"grad_norm": 1.41487717628479,
"learning_rate": 8.778747871771293e-06,
"loss": 1.7543,
"step": 195
},
{
"epoch": 0.2538860103626943,
"grad_norm": 2.6147382259368896,
"learning_rate": 8.76496254059612e-06,
"loss": 1.9427,
"step": 196
},
{
"epoch": 0.2551813471502591,
"grad_norm": 1.1078357696533203,
"learning_rate": 8.751110795889966e-06,
"loss": 1.7878,
"step": 197
},
{
"epoch": 0.25647668393782386,
"grad_norm": 1.0752217769622803,
"learning_rate": 8.737192881996106e-06,
"loss": 1.7959,
"step": 198
},
{
"epoch": 0.25777202072538863,
"grad_norm": 1.1847490072250366,
"learning_rate": 8.723209044425034e-06,
"loss": 1.8002,
"step": 199
},
{
"epoch": 0.25906735751295334,
"grad_norm": 1.1260130405426025,
"learning_rate": 8.709159529850126e-06,
"loss": 1.7823,
"step": 200
},
{
"epoch": 0.2603626943005181,
"grad_norm": 1.1287868022918701,
"learning_rate": 8.695044586103297e-06,
"loss": 1.9234,
"step": 201
},
{
"epoch": 0.2616580310880829,
"grad_norm": 1.1062188148498535,
"learning_rate": 8.680864462170622e-06,
"loss": 1.9002,
"step": 202
},
{
"epoch": 0.26295336787564766,
"grad_norm": 1.5891491174697876,
"learning_rate": 8.666619408187953e-06,
"loss": 1.7853,
"step": 203
},
{
"epoch": 0.26424870466321243,
"grad_norm": 1.2890671491622925,
"learning_rate": 8.652309675436496e-06,
"loss": 1.8849,
"step": 204
},
{
"epoch": 0.2655440414507772,
"grad_norm": 1.1872892379760742,
"learning_rate": 8.637935516338384e-06,
"loss": 1.9165,
"step": 205
},
{
"epoch": 0.266839378238342,
"grad_norm": 1.1047430038452148,
"learning_rate": 8.623497184452227e-06,
"loss": 1.8993,
"step": 206
},
{
"epoch": 0.26813471502590674,
"grad_norm": 0.8833361268043518,
"learning_rate": 8.608994934468633e-06,
"loss": 1.8237,
"step": 207
},
{
"epoch": 0.2694300518134715,
"grad_norm": 2.3226280212402344,
"learning_rate": 8.594429022205719e-06,
"loss": 1.7962,
"step": 208
},
{
"epoch": 0.2707253886010363,
"grad_norm": 1.1140997409820557,
"learning_rate": 8.579799704604597e-06,
"loss": 1.8456,
"step": 209
},
{
"epoch": 0.27202072538860106,
"grad_norm": 1.1130684614181519,
"learning_rate": 8.565107239724845e-06,
"loss": 1.968,
"step": 210
},
{
"epoch": 0.27331606217616583,
"grad_norm": 1.15550696849823,
"learning_rate": 8.550351886739949e-06,
"loss": 1.8073,
"step": 211
},
{
"epoch": 0.27461139896373055,
"grad_norm": 1.2736618518829346,
"learning_rate": 8.535533905932739e-06,
"loss": 1.741,
"step": 212
},
{
"epoch": 0.2759067357512953,
"grad_norm": 1.0873605012893677,
"learning_rate": 8.520653558690785e-06,
"loss": 1.8537,
"step": 213
},
{
"epoch": 0.2772020725388601,
"grad_norm": 1.1784409284591675,
"learning_rate": 8.505711107501802e-06,
"loss": 1.8454,
"step": 214
},
{
"epoch": 0.27849740932642486,
"grad_norm": 1.124671459197998,
"learning_rate": 8.490706815949006e-06,
"loss": 1.9044,
"step": 215
},
{
"epoch": 0.27979274611398963,
"grad_norm": 1.2479369640350342,
"learning_rate": 8.475640948706476e-06,
"loss": 1.8752,
"step": 216
},
{
"epoch": 0.2810880829015544,
"grad_norm": 0.9774690866470337,
"learning_rate": 8.460513771534475e-06,
"loss": 1.81,
"step": 217
},
{
"epoch": 0.2823834196891192,
"grad_norm": 0.8613808751106262,
"learning_rate": 8.44532555127477e-06,
"loss": 1.7319,
"step": 218
},
{
"epoch": 0.28367875647668395,
"grad_norm": 1.05380117893219,
"learning_rate": 8.430076555845917e-06,
"loss": 1.633,
"step": 219
},
{
"epoch": 0.2849740932642487,
"grad_norm": 1.3016676902770996,
"learning_rate": 8.414767054238541e-06,
"loss": 1.8628,
"step": 220
},
{
"epoch": 0.2862694300518135,
"grad_norm": 1.00297212600708,
"learning_rate": 8.399397316510596e-06,
"loss": 1.7533,
"step": 221
},
{
"epoch": 0.28756476683937826,
"grad_norm": 1.1722593307495117,
"learning_rate": 8.383967613782582e-06,
"loss": 1.7736,
"step": 222
},
{
"epoch": 0.28886010362694303,
"grad_norm": 1.0967048406600952,
"learning_rate": 8.368478218232787e-06,
"loss": 1.8093,
"step": 223
},
{
"epoch": 0.29015544041450775,
"grad_norm": 1.1382930278778076,
"learning_rate": 8.352929403092466e-06,
"loss": 1.7477,
"step": 224
},
{
"epoch": 0.2914507772020725,
"grad_norm": 1.0129637718200684,
"learning_rate": 8.337321442641036e-06,
"loss": 1.8,
"step": 225
},
{
"epoch": 0.2927461139896373,
"grad_norm": 0.9240421056747437,
"learning_rate": 8.321654612201222e-06,
"loss": 1.8488,
"step": 226
},
{
"epoch": 0.29404145077720206,
"grad_norm": 0.9596297740936279,
"learning_rate": 8.305929188134216e-06,
"loss": 1.8923,
"step": 227
},
{
"epoch": 0.29533678756476683,
"grad_norm": 0.9442227482795715,
"learning_rate": 8.290145447834797e-06,
"loss": 1.6718,
"step": 228
},
{
"epoch": 0.2966321243523316,
"grad_norm": 0.879130482673645,
"learning_rate": 8.274303669726427e-06,
"loss": 1.7457,
"step": 229
},
{
"epoch": 0.2979274611398964,
"grad_norm": 2.1004528999328613,
"learning_rate": 8.258404133256356e-06,
"loss": 1.8799,
"step": 230
},
{
"epoch": 0.29922279792746115,
"grad_norm": 1.181241750717163,
"learning_rate": 8.242447118890686e-06,
"loss": 1.8044,
"step": 231
},
{
"epoch": 0.3005181347150259,
"grad_norm": 0.95156329870224,
"learning_rate": 8.226432908109416e-06,
"loss": 1.9068,
"step": 232
},
{
"epoch": 0.3018134715025907,
"grad_norm": 1.1262156963348389,
"learning_rate": 8.210361783401491e-06,
"loss": 1.7666,
"step": 233
},
{
"epoch": 0.30310880829015546,
"grad_norm": 1.143411636352539,
"learning_rate": 8.194234028259806e-06,
"loss": 1.9038,
"step": 234
},
{
"epoch": 0.30440414507772023,
"grad_norm": 1.1027392148971558,
"learning_rate": 8.178049927176217e-06,
"loss": 1.8737,
"step": 235
},
{
"epoch": 0.30569948186528495,
"grad_norm": 1.9728175401687622,
"learning_rate": 8.161809765636506e-06,
"loss": 1.8091,
"step": 236
},
{
"epoch": 0.3069948186528497,
"grad_norm": 0.9247788190841675,
"learning_rate": 8.145513830115367e-06,
"loss": 1.6863,
"step": 237
},
{
"epoch": 0.3082901554404145,
"grad_norm": 1.0272600650787354,
"learning_rate": 8.129162408071334e-06,
"loss": 1.8442,
"step": 238
},
{
"epoch": 0.30958549222797926,
"grad_norm": 0.9048571586608887,
"learning_rate": 8.112755787941718e-06,
"loss": 2.0023,
"step": 239
},
{
"epoch": 0.31088082901554404,
"grad_norm": 0.9695209264755249,
"learning_rate": 8.096294259137519e-06,
"loss": 1.837,
"step": 240
},
{
"epoch": 0.3121761658031088,
"grad_norm": 1.2371660470962524,
"learning_rate": 8.079778112038318e-06,
"loss": 1.8026,
"step": 241
},
{
"epoch": 0.3134715025906736,
"grad_norm": 1.0513858795166016,
"learning_rate": 8.063207637987166e-06,
"loss": 1.9963,
"step": 242
},
{
"epoch": 0.31476683937823835,
"grad_norm": 0.885572075843811,
"learning_rate": 8.046583129285422e-06,
"loss": 1.9847,
"step": 243
},
{
"epoch": 0.3160621761658031,
"grad_norm": 0.9771511554718018,
"learning_rate": 8.02990487918762e-06,
"loss": 1.765,
"step": 244
},
{
"epoch": 0.3173575129533679,
"grad_norm": 0.9950928092002869,
"learning_rate": 8.013173181896283e-06,
"loss": 1.7532,
"step": 245
},
{
"epoch": 0.31865284974093266,
"grad_norm": 0.9537307024002075,
"learning_rate": 7.996388332556735e-06,
"loss": 1.6613,
"step": 246
},
{
"epoch": 0.31994818652849744,
"grad_norm": 0.9764825701713562,
"learning_rate": 7.979550627251901e-06,
"loss": 1.6735,
"step": 247
},
{
"epoch": 0.32124352331606215,
"grad_norm": 0.9874715805053711,
"learning_rate": 7.962660362997074e-06,
"loss": 1.7708,
"step": 248
},
{
"epoch": 0.3225388601036269,
"grad_norm": 1.1472409963607788,
"learning_rate": 7.945717837734688e-06,
"loss": 1.6714,
"step": 249
},
{
"epoch": 0.3238341968911917,
"grad_norm": 1.0249556303024292,
"learning_rate": 7.928723350329048e-06,
"loss": 1.7346,
"step": 250
},
{
"epoch": 0.32512953367875647,
"grad_norm": 0.8988825678825378,
"learning_rate": 7.91167720056107e-06,
"loss": 1.6264,
"step": 251
},
{
"epoch": 0.32642487046632124,
"grad_norm": 1.1042741537094116,
"learning_rate": 7.89457968912299e-06,
"loss": 1.8723,
"step": 252
},
{
"epoch": 0.327720207253886,
"grad_norm": 0.8447934985160828,
"learning_rate": 7.87743111761305e-06,
"loss": 1.7967,
"step": 253
},
{
"epoch": 0.3290155440414508,
"grad_norm": 0.9557591080665588,
"learning_rate": 7.860231788530199e-06,
"loss": 1.7971,
"step": 254
},
{
"epoch": 0.33031088082901555,
"grad_norm": 0.9893816113471985,
"learning_rate": 7.842982005268733e-06,
"loss": 1.8599,
"step": 255
},
{
"epoch": 0.3316062176165803,
"grad_norm": 0.9495405554771423,
"learning_rate": 7.82568207211296e-06,
"loss": 1.6566,
"step": 256
},
{
"epoch": 0.3329015544041451,
"grad_norm": 0.8749702572822571,
"learning_rate": 7.808332294231824e-06,
"loss": 1.8063,
"step": 257
},
{
"epoch": 0.33419689119170987,
"grad_norm": 1.2533146142959595,
"learning_rate": 7.790932977673525e-06,
"loss": 1.7195,
"step": 258
},
{
"epoch": 0.33549222797927464,
"grad_norm": 0.9891936779022217,
"learning_rate": 7.773484429360122e-06,
"loss": 1.7417,
"step": 259
},
{
"epoch": 0.33678756476683935,
"grad_norm": 0.9500993490219116,
"learning_rate": 7.755986957082116e-06,
"loss": 1.5809,
"step": 260
},
{
"epoch": 0.3380829015544041,
"grad_norm": 1.0449806451797485,
"learning_rate": 7.738440869493018e-06,
"loss": 1.8223,
"step": 261
},
{
"epoch": 0.3393782383419689,
"grad_norm": 0.9454615116119385,
"learning_rate": 7.720846476103911e-06,
"loss": 1.8198,
"step": 262
},
{
"epoch": 0.34067357512953367,
"grad_norm": 1.0545799732208252,
"learning_rate": 7.703204087277989e-06,
"loss": 1.8983,
"step": 263
},
{
"epoch": 0.34196891191709844,
"grad_norm": 1.026430368423462,
"learning_rate": 7.685514014225076e-06,
"loss": 1.8356,
"step": 264
},
{
"epoch": 0.3432642487046632,
"grad_norm": 1.0940204858779907,
"learning_rate": 7.667776568996143e-06,
"loss": 1.6725,
"step": 265
},
{
"epoch": 0.344559585492228,
"grad_norm": 1.041306972503662,
"learning_rate": 7.6499920644778e-06,
"loss": 1.6349,
"step": 266
},
{
"epoch": 0.34585492227979275,
"grad_norm": 1.1469593048095703,
"learning_rate": 7.63216081438678e-06,
"loss": 1.7095,
"step": 267
},
{
"epoch": 0.3471502590673575,
"grad_norm": 1.0388603210449219,
"learning_rate": 7.6142831332643994e-06,
"loss": 1.8134,
"step": 268
},
{
"epoch": 0.3484455958549223,
"grad_norm": 0.8775234818458557,
"learning_rate": 7.596359336471015e-06,
"loss": 1.7744,
"step": 269
},
{
"epoch": 0.34974093264248707,
"grad_norm": 1.0327327251434326,
"learning_rate": 7.578389740180461e-06,
"loss": 1.6926,
"step": 270
},
{
"epoch": 0.35103626943005184,
"grad_norm": 1.2564126253128052,
"learning_rate": 7.560374661374463e-06,
"loss": 1.7779,
"step": 271
},
{
"epoch": 0.35233160621761656,
"grad_norm": 1.0119752883911133,
"learning_rate": 7.542314417837062e-06,
"loss": 1.7482,
"step": 272
},
{
"epoch": 0.3536269430051813,
"grad_norm": 1.0766204595565796,
"learning_rate": 7.524209328148995e-06,
"loss": 1.9719,
"step": 273
},
{
"epoch": 0.3549222797927461,
"grad_norm": 1.1861612796783447,
"learning_rate": 7.506059711682078e-06,
"loss": 1.9527,
"step": 274
},
{
"epoch": 0.35621761658031087,
"grad_norm": 1.015496015548706,
"learning_rate": 7.487865888593579e-06,
"loss": 1.6868,
"step": 275
},
{
"epoch": 0.35751295336787564,
"grad_norm": 1.0318480730056763,
"learning_rate": 7.469628179820567e-06,
"loss": 1.6657,
"step": 276
},
{
"epoch": 0.3588082901554404,
"grad_norm": 1.084868311882019,
"learning_rate": 7.451346907074245e-06,
"loss": 1.7777,
"step": 277
},
{
"epoch": 0.3601036269430052,
"grad_norm": 1.0875519514083862,
"learning_rate": 7.4330223928342814e-06,
"loss": 1.6756,
"step": 278
},
{
"epoch": 0.36139896373056996,
"grad_norm": 1.1082035303115845,
"learning_rate": 7.4146549603431225e-06,
"loss": 1.7694,
"step": 279
},
{
"epoch": 0.3626943005181347,
"grad_norm": 1.2754228115081787,
"learning_rate": 7.396244933600285e-06,
"loss": 1.7314,
"step": 280
},
{
"epoch": 0.3639896373056995,
"grad_norm": 0.9865210056304932,
"learning_rate": 7.377792637356644e-06,
"loss": 1.8106,
"step": 281
},
{
"epoch": 0.36528497409326427,
"grad_norm": 1.0488427877426147,
"learning_rate": 7.359298397108704e-06,
"loss": 1.6691,
"step": 282
},
{
"epoch": 0.36658031088082904,
"grad_norm": 0.8308634757995605,
"learning_rate": 7.340762539092858e-06,
"loss": 1.7633,
"step": 283
},
{
"epoch": 0.36787564766839376,
"grad_norm": 1.0312767028808594,
"learning_rate": 7.322185390279632e-06,
"loss": 1.9481,
"step": 284
},
{
"epoch": 0.36917098445595853,
"grad_norm": 2.3829352855682373,
"learning_rate": 7.303567278367918e-06,
"loss": 1.5043,
"step": 285
},
{
"epoch": 0.3704663212435233,
"grad_norm": 1.0807713270187378,
"learning_rate": 7.284908531779189e-06,
"loss": 1.7574,
"step": 286
},
{
"epoch": 0.37176165803108807,
"grad_norm": 0.9812313914299011,
"learning_rate": 7.266209479651712e-06,
"loss": 1.5752,
"step": 287
},
{
"epoch": 0.37305699481865284,
"grad_norm": 1.042359709739685,
"learning_rate": 7.247470451834741e-06,
"loss": 1.7806,
"step": 288
},
{
"epoch": 0.3743523316062176,
"grad_norm": 0.9092085361480713,
"learning_rate": 7.2286917788826926e-06,
"loss": 1.6291,
"step": 289
},
{
"epoch": 0.3756476683937824,
"grad_norm": 1.1348210573196411,
"learning_rate": 7.209873792049322e-06,
"loss": 1.9856,
"step": 290
},
{
"epoch": 0.37694300518134716,
"grad_norm": 1.0171518325805664,
"learning_rate": 7.1910168232818765e-06,
"loss": 1.6933,
"step": 291
},
{
"epoch": 0.37823834196891193,
"grad_norm": 1.0894110202789307,
"learning_rate": 7.172121205215241e-06,
"loss": 1.6217,
"step": 292
},
{
"epoch": 0.3795336787564767,
"grad_norm": 1.1747410297393799,
"learning_rate": 7.153187271166071e-06,
"loss": 1.6353,
"step": 293
},
{
"epoch": 0.38082901554404147,
"grad_norm": 0.9109553098678589,
"learning_rate": 7.134215355126905e-06,
"loss": 1.7126,
"step": 294
},
{
"epoch": 0.38212435233160624,
"grad_norm": 0.8959193825721741,
"learning_rate": 7.1152057917602904e-06,
"loss": 1.6252,
"step": 295
},
{
"epoch": 0.38341968911917096,
"grad_norm": 0.9879838228225708,
"learning_rate": 7.096158916392861e-06,
"loss": 1.793,
"step": 296
},
{
"epoch": 0.38471502590673573,
"grad_norm": 1.1411892175674438,
"learning_rate": 7.0770750650094335e-06,
"loss": 1.6636,
"step": 297
},
{
"epoch": 0.3860103626943005,
"grad_norm": 1.0462467670440674,
"learning_rate": 7.057954574247076e-06,
"loss": 1.7945,
"step": 298
},
{
"epoch": 0.3873056994818653,
"grad_norm": 1.1615983247756958,
"learning_rate": 7.038797781389174e-06,
"loss": 1.6988,
"step": 299
},
{
"epoch": 0.38860103626943004,
"grad_norm": 1.0192328691482544,
"learning_rate": 7.019605024359475e-06,
"loss": 1.6852,
"step": 300
},
{
"epoch": 0.3898963730569948,
"grad_norm": 1.082013726234436,
"learning_rate": 7.0003766417161335e-06,
"loss": 1.6827,
"step": 301
},
{
"epoch": 0.3911917098445596,
"grad_norm": 1.0153688192367554,
"learning_rate": 6.981112972645734e-06,
"loss": 1.6573,
"step": 302
},
{
"epoch": 0.39248704663212436,
"grad_norm": 0.9773356914520264,
"learning_rate": 6.961814356957308e-06,
"loss": 1.6384,
"step": 303
},
{
"epoch": 0.39378238341968913,
"grad_norm": 1.1218401193618774,
"learning_rate": 6.942481135076346e-06,
"loss": 1.902,
"step": 304
},
{
"epoch": 0.3950777202072539,
"grad_norm": 0.9850178956985474,
"learning_rate": 6.923113648038784e-06,
"loss": 1.6767,
"step": 305
},
{
"epoch": 0.3963730569948187,
"grad_norm": 1.0459367036819458,
"learning_rate": 6.9037122374849966e-06,
"loss": 1.5925,
"step": 306
},
{
"epoch": 0.39766839378238344,
"grad_norm": 1.0688074827194214,
"learning_rate": 6.884277245653758e-06,
"loss": 1.5956,
"step": 307
},
{
"epoch": 0.39896373056994816,
"grad_norm": 1.026476502418518,
"learning_rate": 6.864809015376218e-06,
"loss": 1.6139,
"step": 308
},
{
"epoch": 0.40025906735751293,
"grad_norm": 0.9798409938812256,
"learning_rate": 6.845307890069851e-06,
"loss": 1.5926,
"step": 309
},
{
"epoch": 0.4015544041450777,
"grad_norm": 0.8492075204849243,
"learning_rate": 6.825774213732388e-06,
"loss": 1.6014,
"step": 310
},
{
"epoch": 0.4028497409326425,
"grad_norm": 1.1730836629867554,
"learning_rate": 6.806208330935766e-06,
"loss": 1.6712,
"step": 311
},
{
"epoch": 0.40414507772020725,
"grad_norm": 1.06760573387146,
"learning_rate": 6.7866105868200325e-06,
"loss": 1.7203,
"step": 312
},
{
"epoch": 0.405440414507772,
"grad_norm": 2.8247268199920654,
"learning_rate": 6.766981327087271e-06,
"loss": 1.7615,
"step": 313
},
{
"epoch": 0.4067357512953368,
"grad_norm": 0.9581862688064575,
"learning_rate": 6.747320897995493e-06,
"loss": 1.6228,
"step": 314
},
{
"epoch": 0.40803108808290156,
"grad_norm": 1.0653893947601318,
"learning_rate": 6.727629646352536e-06,
"loss": 1.5399,
"step": 315
},
{
"epoch": 0.40932642487046633,
"grad_norm": 0.9498708844184875,
"learning_rate": 6.707907919509946e-06,
"loss": 1.5992,
"step": 316
},
{
"epoch": 0.4106217616580311,
"grad_norm": 1.0044955015182495,
"learning_rate": 6.688156065356845e-06,
"loss": 1.6313,
"step": 317
},
{
"epoch": 0.4119170984455959,
"grad_norm": 1.09602952003479,
"learning_rate": 6.668374432313797e-06,
"loss": 1.5978,
"step": 318
},
{
"epoch": 0.41321243523316065,
"grad_norm": 1.0281319618225098,
"learning_rate": 6.648563369326666e-06,
"loss": 1.6621,
"step": 319
},
{
"epoch": 0.41450777202072536,
"grad_norm": 0.9845161437988281,
"learning_rate": 6.628723225860454e-06,
"loss": 1.5473,
"step": 320
},
{
"epoch": 0.41580310880829013,
"grad_norm": 1.1111558675765991,
"learning_rate": 6.60885435189314e-06,
"loss": 1.7279,
"step": 321
},
{
"epoch": 0.4170984455958549,
"grad_norm": 0.9977635741233826,
"learning_rate": 6.588957097909509e-06,
"loss": 1.5733,
"step": 322
},
{
"epoch": 0.4183937823834197,
"grad_norm": 0.9844448566436768,
"learning_rate": 6.569031814894962e-06,
"loss": 1.591,
"step": 323
},
{
"epoch": 0.41968911917098445,
"grad_norm": 1.0853886604309082,
"learning_rate": 6.549078854329328e-06,
"loss": 1.579,
"step": 324
},
{
"epoch": 0.4209844559585492,
"grad_norm": 0.9131169319152832,
"learning_rate": 6.529098568180672e-06,
"loss": 1.6398,
"step": 325
},
{
"epoch": 0.422279792746114,
"grad_norm": 0.9565425515174866,
"learning_rate": 6.509091308899074e-06,
"loss": 1.5868,
"step": 326
},
{
"epoch": 0.42357512953367876,
"grad_norm": 1.0737073421478271,
"learning_rate": 6.489057429410418e-06,
"loss": 1.5986,
"step": 327
},
{
"epoch": 0.42487046632124353,
"grad_norm": 0.8935278058052063,
"learning_rate": 6.468997283110166e-06,
"loss": 1.6069,
"step": 328
},
{
"epoch": 0.4261658031088083,
"grad_norm": 1.210968017578125,
"learning_rate": 6.448911223857124e-06,
"loss": 1.7825,
"step": 329
},
{
"epoch": 0.4274611398963731,
"grad_norm": 0.9139443039894104,
"learning_rate": 6.4287996059671985e-06,
"loss": 1.6052,
"step": 330
},
{
"epoch": 0.42875647668393785,
"grad_norm": 1.0823360681533813,
"learning_rate": 6.408662784207149e-06,
"loss": 1.6982,
"step": 331
},
{
"epoch": 0.43005181347150256,
"grad_norm": 0.997048556804657,
"learning_rate": 6.388501113788328e-06,
"loss": 1.6636,
"step": 332
},
{
"epoch": 0.43134715025906734,
"grad_norm": 4.892472267150879,
"learning_rate": 6.368314950360416e-06,
"loss": 1.6278,
"step": 333
},
{
"epoch": 0.4326424870466321,
"grad_norm": 1.1357526779174805,
"learning_rate": 6.348104650005145e-06,
"loss": 1.6224,
"step": 334
},
{
"epoch": 0.4339378238341969,
"grad_norm": 0.9890827536582947,
"learning_rate": 6.327870569230022e-06,
"loss": 1.7661,
"step": 335
},
{
"epoch": 0.43523316062176165,
"grad_norm": 0.9172429442405701,
"learning_rate": 6.307613064962042e-06,
"loss": 1.666,
"step": 336
},
{
"epoch": 0.4365284974093264,
"grad_norm": 1.2755533456802368,
"learning_rate": 6.28733249454138e-06,
"loss": 1.8189,
"step": 337
},
{
"epoch": 0.4378238341968912,
"grad_norm": 1.1116775274276733,
"learning_rate": 6.267029215715099e-06,
"loss": 1.6772,
"step": 338
},
{
"epoch": 0.43911917098445596,
"grad_norm": 1.0353986024856567,
"learning_rate": 6.246703586630838e-06,
"loss": 1.7197,
"step": 339
},
{
"epoch": 0.44041450777202074,
"grad_norm": 1.169368863105774,
"learning_rate": 6.226355965830488e-06,
"loss": 1.7546,
"step": 340
},
{
"epoch": 0.4417098445595855,
"grad_norm": 1.421899437904358,
"learning_rate": 6.205986712243876e-06,
"loss": 1.7473,
"step": 341
},
{
"epoch": 0.4430051813471503,
"grad_norm": 1.2078102827072144,
"learning_rate": 6.185596185182426e-06,
"loss": 1.52,
"step": 342
},
{
"epoch": 0.44430051813471505,
"grad_norm": 1.0147042274475098,
"learning_rate": 6.165184744332824e-06,
"loss": 1.658,
"step": 343
},
{
"epoch": 0.44559585492227977,
"grad_norm": 2.307651996612549,
"learning_rate": 6.144752749750671e-06,
"loss": 1.6091,
"step": 344
},
{
"epoch": 0.44689119170984454,
"grad_norm": 0.8909070491790771,
"learning_rate": 6.124300561854139e-06,
"loss": 1.5986,
"step": 345
},
{
"epoch": 0.4481865284974093,
"grad_norm": 1.4015833139419556,
"learning_rate": 6.103828541417606e-06,
"loss": 1.929,
"step": 346
},
{
"epoch": 0.4494818652849741,
"grad_norm": 1.2431873083114624,
"learning_rate": 6.0833370495652885e-06,
"loss": 1.8011,
"step": 347
},
{
"epoch": 0.45077720207253885,
"grad_norm": 1.2874951362609863,
"learning_rate": 6.062826447764883e-06,
"loss": 1.6861,
"step": 348
},
{
"epoch": 0.4520725388601036,
"grad_norm": 7.429315567016602,
"learning_rate": 6.042297097821184e-06,
"loss": 1.5128,
"step": 349
},
{
"epoch": 0.4533678756476684,
"grad_norm": 1.1864122152328491,
"learning_rate": 6.021749361869693e-06,
"loss": 1.7035,
"step": 350
},
{
"epoch": 0.45466321243523317,
"grad_norm": 1.115491271018982,
"learning_rate": 6.001183602370249e-06,
"loss": 1.5819,
"step": 351
},
{
"epoch": 0.45595854922279794,
"grad_norm": 1.4851834774017334,
"learning_rate": 5.980600182100617e-06,
"loss": 1.6518,
"step": 352
},
{
"epoch": 0.4572538860103627,
"grad_norm": 1.0581804513931274,
"learning_rate": 5.959999464150101e-06,
"loss": 1.6243,
"step": 353
},
{
"epoch": 0.4585492227979275,
"grad_norm": 1.6220453977584839,
"learning_rate": 5.939381811913128e-06,
"loss": 1.7538,
"step": 354
},
{
"epoch": 0.45984455958549225,
"grad_norm": 1.1932604312896729,
"learning_rate": 5.918747589082853e-06,
"loss": 1.5363,
"step": 355
},
{
"epoch": 0.46113989637305697,
"grad_norm": 1.4205118417739868,
"learning_rate": 5.898097159644725e-06,
"loss": 1.7182,
"step": 356
},
{
"epoch": 0.46243523316062174,
"grad_norm": 1.1873120069503784,
"learning_rate": 5.877430887870081e-06,
"loss": 1.6459,
"step": 357
},
{
"epoch": 0.4637305699481865,
"grad_norm": 1.6799578666687012,
"learning_rate": 5.856749138309716e-06,
"loss": 1.6532,
"step": 358
},
{
"epoch": 0.4650259067357513,
"grad_norm": 1.1090807914733887,
"learning_rate": 5.836052275787448e-06,
"loss": 1.5684,
"step": 359
},
{
"epoch": 0.46632124352331605,
"grad_norm": 1.193097472190857,
"learning_rate": 5.8153406653936895e-06,
"loss": 1.652,
"step": 360
},
{
"epoch": 0.4676165803108808,
"grad_norm": 1.2036798000335693,
"learning_rate": 5.794614672479e-06,
"loss": 1.7192,
"step": 361
},
{
"epoch": 0.4689119170984456,
"grad_norm": 1.5199964046478271,
"learning_rate": 5.7738746626476495e-06,
"loss": 1.6227,
"step": 362
},
{
"epoch": 0.47020725388601037,
"grad_norm": 1.3393440246582031,
"learning_rate": 5.753121001751161e-06,
"loss": 1.7378,
"step": 363
},
{
"epoch": 0.47150259067357514,
"grad_norm": 1.3441263437271118,
"learning_rate": 5.7323540558818615e-06,
"loss": 1.7988,
"step": 364
},
{
"epoch": 0.4727979274611399,
"grad_norm": 1.7060637474060059,
"learning_rate": 5.711574191366427e-06,
"loss": 1.5902,
"step": 365
},
{
"epoch": 0.4740932642487047,
"grad_norm": 1.7133537530899048,
"learning_rate": 5.690781774759412e-06,
"loss": 1.7443,
"step": 366
},
{
"epoch": 0.47538860103626945,
"grad_norm": 1.383394479751587,
"learning_rate": 5.669977172836791e-06,
"loss": 1.6801,
"step": 367
},
{
"epoch": 0.47668393782383417,
"grad_norm": 1.609458565711975,
"learning_rate": 5.64916075258949e-06,
"loss": 1.6125,
"step": 368
},
{
"epoch": 0.47797927461139894,
"grad_norm": 1.224892020225525,
"learning_rate": 5.628332881216899e-06,
"loss": 1.6805,
"step": 369
},
{
"epoch": 0.4792746113989637,
"grad_norm": 1.2945423126220703,
"learning_rate": 5.6074939261204145e-06,
"loss": 1.6782,
"step": 370
},
{
"epoch": 0.4805699481865285,
"grad_norm": 1.320286512374878,
"learning_rate": 5.586644254896945e-06,
"loss": 1.6714,
"step": 371
},
{
"epoch": 0.48186528497409326,
"grad_norm": 1.4307211637496948,
"learning_rate": 5.565784235332427e-06,
"loss": 1.6666,
"step": 372
},
{
"epoch": 0.483160621761658,
"grad_norm": 1.0741175413131714,
"learning_rate": 5.544914235395347e-06,
"loss": 1.5124,
"step": 373
},
{
"epoch": 0.4844559585492228,
"grad_norm": 1.430330753326416,
"learning_rate": 5.524034623230241e-06,
"loss": 1.566,
"step": 374
},
{
"epoch": 0.48575129533678757,
"grad_norm": 1.4610899686813354,
"learning_rate": 5.503145767151201e-06,
"loss": 1.697,
"step": 375
},
{
"epoch": 0.48704663212435234,
"grad_norm": 1.0354617834091187,
"learning_rate": 5.482248035635386e-06,
"loss": 1.6581,
"step": 376
},
{
"epoch": 0.4883419689119171,
"grad_norm": 1.0924460887908936,
"learning_rate": 5.46134179731651e-06,
"loss": 1.6695,
"step": 377
},
{
"epoch": 0.4896373056994819,
"grad_norm": 1.2419058084487915,
"learning_rate": 5.440427420978356e-06,
"loss": 1.5944,
"step": 378
},
{
"epoch": 0.49093264248704666,
"grad_norm": 1.578084945678711,
"learning_rate": 5.419505275548249e-06,
"loss": 1.6733,
"step": 379
},
{
"epoch": 0.49222797927461137,
"grad_norm": 1.2596430778503418,
"learning_rate": 5.398575730090569e-06,
"loss": 1.7591,
"step": 380
},
{
"epoch": 0.49352331606217614,
"grad_norm": 1.3724911212921143,
"learning_rate": 5.377639153800229e-06,
"loss": 1.7693,
"step": 381
},
{
"epoch": 0.4948186528497409,
"grad_norm": 0.9356993436813354,
"learning_rate": 5.356695915996162e-06,
"loss": 1.5514,
"step": 382
},
{
"epoch": 0.4961139896373057,
"grad_norm": 1.0379865169525146,
"learning_rate": 5.335746386114814e-06,
"loss": 1.5637,
"step": 383
},
{
"epoch": 0.49740932642487046,
"grad_norm": 1.2603338956832886,
"learning_rate": 5.3147909337036205e-06,
"loss": 1.5882,
"step": 384
},
{
"epoch": 0.49870466321243523,
"grad_norm": 1.176857352256775,
"learning_rate": 5.29382992841449e-06,
"loss": 1.5807,
"step": 385
},
{
"epoch": 0.5,
"grad_norm": 1.5517312288284302,
"learning_rate": 5.27286373999728e-06,
"loss": 1.6554,
"step": 386
},
{
"epoch": 0.5012953367875648,
"grad_norm": 1.2538155317306519,
"learning_rate": 5.251892738293285e-06,
"loss": 1.7086,
"step": 387
},
{
"epoch": 0.5025906735751295,
"grad_norm": 1.224009394645691,
"learning_rate": 5.230917293228699e-06,
"loss": 1.6491,
"step": 388
},
{
"epoch": 0.5038860103626943,
"grad_norm": 1.1826633214950562,
"learning_rate": 5.209937774808098e-06,
"loss": 1.4343,
"step": 389
},
{
"epoch": 0.5051813471502591,
"grad_norm": 1.0940345525741577,
"learning_rate": 5.188954553107913e-06,
"loss": 1.5727,
"step": 390
},
{
"epoch": 0.5064766839378239,
"grad_norm": 1.5314024686813354,
"learning_rate": 5.167967998269902e-06,
"loss": 1.7214,
"step": 391
},
{
"epoch": 0.5077720207253886,
"grad_norm": 1.0600006580352783,
"learning_rate": 5.146978480494611e-06,
"loss": 1.5912,
"step": 392
},
{
"epoch": 0.5090673575129534,
"grad_norm": 0.9453856348991394,
"learning_rate": 5.125986370034862e-06,
"loss": 1.7152,
"step": 393
},
{
"epoch": 0.5103626943005182,
"grad_norm": 1.116500973701477,
"learning_rate": 5.104992037189208e-06,
"loss": 1.6561,
"step": 394
},
{
"epoch": 0.5116580310880829,
"grad_norm": 0.9965620040893555,
"learning_rate": 5.083995852295402e-06,
"loss": 1.6923,
"step": 395
},
{
"epoch": 0.5129533678756477,
"grad_norm": 1.0267661809921265,
"learning_rate": 5.062998185723868e-06,
"loss": 1.5762,
"step": 396
},
{
"epoch": 0.5142487046632125,
"grad_norm": 1.1577237844467163,
"learning_rate": 5.041999407871168e-06,
"loss": 1.5136,
"step": 397
},
{
"epoch": 0.5155440414507773,
"grad_norm": 1.2488936185836792,
"learning_rate": 5.020999889153469e-06,
"loss": 1.5415,
"step": 398
},
{
"epoch": 0.5168393782383419,
"grad_norm": 1.2881699800491333,
"learning_rate": 5e-06,
"loss": 1.7089,
"step": 399
},
{
"epoch": 0.5181347150259067,
"grad_norm": 1.234460711479187,
"learning_rate": 4.979000110846533e-06,
"loss": 1.7478,
"step": 400
},
{
"epoch": 0.5194300518134715,
"grad_norm": 1.1152491569519043,
"learning_rate": 4.958000592128834e-06,
"loss": 1.5783,
"step": 401
},
{
"epoch": 0.5207253886010362,
"grad_norm": 1.104040503501892,
"learning_rate": 4.937001814276135e-06,
"loss": 1.719,
"step": 402
},
{
"epoch": 0.522020725388601,
"grad_norm": 2.0457229614257812,
"learning_rate": 4.9160041477046e-06,
"loss": 1.6806,
"step": 403
},
{
"epoch": 0.5233160621761658,
"grad_norm": 1.250631332397461,
"learning_rate": 4.895007962810794e-06,
"loss": 1.3879,
"step": 404
},
{
"epoch": 0.5246113989637305,
"grad_norm": 1.5960781574249268,
"learning_rate": 4.874013629965138e-06,
"loss": 1.4102,
"step": 405
},
{
"epoch": 0.5259067357512953,
"grad_norm": 0.9493226408958435,
"learning_rate": 4.85302151950539e-06,
"loss": 1.477,
"step": 406
},
{
"epoch": 0.5272020725388601,
"grad_norm": 1.1279934644699097,
"learning_rate": 4.8320320017301e-06,
"loss": 1.4733,
"step": 407
},
{
"epoch": 0.5284974093264249,
"grad_norm": 1.3732160329818726,
"learning_rate": 4.811045446892087e-06,
"loss": 1.6295,
"step": 408
},
{
"epoch": 0.5297927461139896,
"grad_norm": 1.0034644603729248,
"learning_rate": 4.790062225191902e-06,
"loss": 1.4118,
"step": 409
},
{
"epoch": 0.5310880829015544,
"grad_norm": 1.6584422588348389,
"learning_rate": 4.7690827067713035e-06,
"loss": 1.5566,
"step": 410
},
{
"epoch": 0.5323834196891192,
"grad_norm": 0.9733951091766357,
"learning_rate": 4.748107261706716e-06,
"loss": 1.5223,
"step": 411
},
{
"epoch": 0.533678756476684,
"grad_norm": 0.9838838577270508,
"learning_rate": 4.727136260002721e-06,
"loss": 1.5925,
"step": 412
},
{
"epoch": 0.5349740932642487,
"grad_norm": 1.6726466417312622,
"learning_rate": 4.706170071585513e-06,
"loss": 1.6752,
"step": 413
},
{
"epoch": 0.5362694300518135,
"grad_norm": 1.116659164428711,
"learning_rate": 4.68520906629638e-06,
"loss": 1.6404,
"step": 414
},
{
"epoch": 0.5375647668393783,
"grad_norm": 1.0223548412322998,
"learning_rate": 4.664253613885187e-06,
"loss": 1.7367,
"step": 415
},
{
"epoch": 0.538860103626943,
"grad_norm": 1.0119036436080933,
"learning_rate": 4.643304084003839e-06,
"loss": 1.5952,
"step": 416
},
{
"epoch": 0.5401554404145078,
"grad_norm": 1.2546696662902832,
"learning_rate": 4.622360846199772e-06,
"loss": 1.4798,
"step": 417
},
{
"epoch": 0.5414507772020726,
"grad_norm": 1.0571644306182861,
"learning_rate": 4.6014242699094325e-06,
"loss": 1.6201,
"step": 418
},
{
"epoch": 0.5427461139896373,
"grad_norm": 1.355104923248291,
"learning_rate": 4.580494724451752e-06,
"loss": 1.5711,
"step": 419
},
{
"epoch": 0.5440414507772021,
"grad_norm": 1.3718758821487427,
"learning_rate": 4.559572579021646e-06,
"loss": 1.5926,
"step": 420
},
{
"epoch": 0.5453367875647669,
"grad_norm": 1.108573317527771,
"learning_rate": 4.53865820268349e-06,
"loss": 1.6342,
"step": 421
},
{
"epoch": 0.5466321243523317,
"grad_norm": 1.0821819305419922,
"learning_rate": 4.517751964364616e-06,
"loss": 1.444,
"step": 422
},
{
"epoch": 0.5479274611398963,
"grad_norm": 0.8122926354408264,
"learning_rate": 4.4968542328488e-06,
"loss": 1.4668,
"step": 423
},
{
"epoch": 0.5492227979274611,
"grad_norm": 0.9012024998664856,
"learning_rate": 4.4759653767697604e-06,
"loss": 1.5672,
"step": 424
},
{
"epoch": 0.5505181347150259,
"grad_norm": 0.9969602823257446,
"learning_rate": 4.455085764604653e-06,
"loss": 1.6746,
"step": 425
},
{
"epoch": 0.5518134715025906,
"grad_norm": 0.935289204120636,
"learning_rate": 4.434215764667573e-06,
"loss": 1.5376,
"step": 426
},
{
"epoch": 0.5531088082901554,
"grad_norm": 0.9820874333381653,
"learning_rate": 4.413355745103057e-06,
"loss": 1.4695,
"step": 427
},
{
"epoch": 0.5544041450777202,
"grad_norm": 0.8623206615447998,
"learning_rate": 4.392506073879586e-06,
"loss": 1.8803,
"step": 428
},
{
"epoch": 0.555699481865285,
"grad_norm": 0.9572321176528931,
"learning_rate": 4.371667118783101e-06,
"loss": 1.6612,
"step": 429
},
{
"epoch": 0.5569948186528497,
"grad_norm": 0.9998318552970886,
"learning_rate": 4.3508392474105125e-06,
"loss": 1.7152,
"step": 430
},
{
"epoch": 0.5582901554404145,
"grad_norm": 1.0092027187347412,
"learning_rate": 4.3300228271632105e-06,
"loss": 1.4818,
"step": 431
},
{
"epoch": 0.5595854922279793,
"grad_norm": 0.9644368886947632,
"learning_rate": 4.309218225240591e-06,
"loss": 1.5026,
"step": 432
},
{
"epoch": 0.560880829015544,
"grad_norm": 1.040366291999817,
"learning_rate": 4.2884258086335755e-06,
"loss": 1.4348,
"step": 433
},
{
"epoch": 0.5621761658031088,
"grad_norm": 0.8842604160308838,
"learning_rate": 4.267645944118141e-06,
"loss": 1.6283,
"step": 434
},
{
"epoch": 0.5634715025906736,
"grad_norm": 1.082820177078247,
"learning_rate": 4.2468789982488415e-06,
"loss": 1.5415,
"step": 435
},
{
"epoch": 0.5647668393782384,
"grad_norm": 1.0361484289169312,
"learning_rate": 4.226125337352352e-06,
"loss": 1.6463,
"step": 436
},
{
"epoch": 0.5660621761658031,
"grad_norm": 1.1396458148956299,
"learning_rate": 4.205385327521002e-06,
"loss": 1.5432,
"step": 437
},
{
"epoch": 0.5673575129533679,
"grad_norm": 0.9382902979850769,
"learning_rate": 4.184659334606312e-06,
"loss": 1.5663,
"step": 438
},
{
"epoch": 0.5686528497409327,
"grad_norm": 1.1375499963760376,
"learning_rate": 4.163947724212553e-06,
"loss": 1.6349,
"step": 439
},
{
"epoch": 0.5699481865284974,
"grad_norm": 0.9998140335083008,
"learning_rate": 4.143250861690285e-06,
"loss": 1.5026,
"step": 440
},
{
"epoch": 0.5712435233160622,
"grad_norm": 0.9888291954994202,
"learning_rate": 4.12256911212992e-06,
"loss": 1.6247,
"step": 441
},
{
"epoch": 0.572538860103627,
"grad_norm": 0.8778893351554871,
"learning_rate": 4.101902840355277e-06,
"loss": 1.509,
"step": 442
},
{
"epoch": 0.5738341968911918,
"grad_norm": 0.9216470122337341,
"learning_rate": 4.081252410917148e-06,
"loss": 1.6658,
"step": 443
},
{
"epoch": 0.5751295336787565,
"grad_norm": 1.1155840158462524,
"learning_rate": 4.060618188086873e-06,
"loss": 1.5044,
"step": 444
},
{
"epoch": 0.5764248704663213,
"grad_norm": 1.1149576902389526,
"learning_rate": 4.0400005358499e-06,
"loss": 1.6852,
"step": 445
},
{
"epoch": 0.5777202072538861,
"grad_norm": 1.0324351787567139,
"learning_rate": 4.019399817899383e-06,
"loss": 1.4633,
"step": 446
},
{
"epoch": 0.5790155440414507,
"grad_norm": 1.2651646137237549,
"learning_rate": 3.998816397629752e-06,
"loss": 1.6137,
"step": 447
},
{
"epoch": 0.5803108808290155,
"grad_norm": 1.1591652631759644,
"learning_rate": 3.978250638130306e-06,
"loss": 1.4481,
"step": 448
},
{
"epoch": 0.5816062176165803,
"grad_norm": 1.0747854709625244,
"learning_rate": 3.957702902178816e-06,
"loss": 1.5043,
"step": 449
},
{
"epoch": 0.582901554404145,
"grad_norm": 1.2648824453353882,
"learning_rate": 3.937173552235117e-06,
"loss": 1.6337,
"step": 450
},
{
"epoch": 0.5841968911917098,
"grad_norm": 1.089403748512268,
"learning_rate": 3.916662950434714e-06,
"loss": 1.6302,
"step": 451
},
{
"epoch": 0.5854922279792746,
"grad_norm": 1.0358097553253174,
"learning_rate": 3.8961714585823975e-06,
"loss": 1.5623,
"step": 452
},
{
"epoch": 0.5867875647668394,
"grad_norm": 0.8972602486610413,
"learning_rate": 3.875699438145862e-06,
"loss": 1.4872,
"step": 453
},
{
"epoch": 0.5880829015544041,
"grad_norm": 1.003226637840271,
"learning_rate": 3.855247250249331e-06,
"loss": 1.6823,
"step": 454
},
{
"epoch": 0.5893782383419689,
"grad_norm": 0.9723194241523743,
"learning_rate": 3.834815255667179e-06,
"loss": 1.6676,
"step": 455
},
{
"epoch": 0.5906735751295337,
"grad_norm": 1.1487172842025757,
"learning_rate": 3.8144038148175756e-06,
"loss": 1.5668,
"step": 456
},
{
"epoch": 0.5919689119170984,
"grad_norm": 0.963367223739624,
"learning_rate": 3.794013287756125e-06,
"loss": 1.4729,
"step": 457
},
{
"epoch": 0.5932642487046632,
"grad_norm": 1.21097731590271,
"learning_rate": 3.773644034169513e-06,
"loss": 1.5769,
"step": 458
},
{
"epoch": 0.594559585492228,
"grad_norm": 1.1029012203216553,
"learning_rate": 3.7532964133691634e-06,
"loss": 1.655,
"step": 459
},
{
"epoch": 0.5958549222797928,
"grad_norm": 1.105193018913269,
"learning_rate": 3.732970784284903e-06,
"loss": 1.5472,
"step": 460
},
{
"epoch": 0.5971502590673575,
"grad_norm": 0.9611952900886536,
"learning_rate": 3.712667505458622e-06,
"loss": 1.5649,
"step": 461
},
{
"epoch": 0.5984455958549223,
"grad_norm": 0.9506083130836487,
"learning_rate": 3.6923869350379595e-06,
"loss": 1.4536,
"step": 462
},
{
"epoch": 0.5997409326424871,
"grad_norm": 1.0346324443817139,
"learning_rate": 3.6721294307699786e-06,
"loss": 1.5303,
"step": 463
},
{
"epoch": 0.6010362694300518,
"grad_norm": 0.9203392267227173,
"learning_rate": 3.651895349994857e-06,
"loss": 1.6319,
"step": 464
},
{
"epoch": 0.6023316062176166,
"grad_norm": 1.121604323387146,
"learning_rate": 3.6316850496395863e-06,
"loss": 1.5527,
"step": 465
},
{
"epoch": 0.6036269430051814,
"grad_norm": 1.0689448118209839,
"learning_rate": 3.6114988862116736e-06,
"loss": 1.6516,
"step": 466
},
{
"epoch": 0.6049222797927462,
"grad_norm": 1.163565993309021,
"learning_rate": 3.5913372157928515e-06,
"loss": 1.5561,
"step": 467
},
{
"epoch": 0.6062176165803109,
"grad_norm": 1.1336215734481812,
"learning_rate": 3.5712003940328024e-06,
"loss": 1.7935,
"step": 468
},
{
"epoch": 0.6075129533678757,
"grad_norm": 1.0477566719055176,
"learning_rate": 3.5510887761428764e-06,
"loss": 1.4886,
"step": 469
},
{
"epoch": 0.6088082901554405,
"grad_norm": 0.9331677556037903,
"learning_rate": 3.5310027168898346e-06,
"loss": 1.5742,
"step": 470
},
{
"epoch": 0.6101036269430051,
"grad_norm": 1.1255176067352295,
"learning_rate": 3.510942570589583e-06,
"loss": 1.5736,
"step": 471
},
{
"epoch": 0.6113989637305699,
"grad_norm": 0.9851495027542114,
"learning_rate": 3.4909086911009284e-06,
"loss": 1.6295,
"step": 472
},
{
"epoch": 0.6126943005181347,
"grad_norm": 1.101414442062378,
"learning_rate": 3.4709014318193298e-06,
"loss": 1.4968,
"step": 473
},
{
"epoch": 0.6139896373056994,
"grad_norm": 1.1658620834350586,
"learning_rate": 3.450921145670674e-06,
"loss": 1.5622,
"step": 474
},
{
"epoch": 0.6152849740932642,
"grad_norm": 1.6204978227615356,
"learning_rate": 3.4309681851050414e-06,
"loss": 1.6013,
"step": 475
},
{
"epoch": 0.616580310880829,
"grad_norm": 1.067237138748169,
"learning_rate": 3.4110429020904924e-06,
"loss": 1.5437,
"step": 476
},
{
"epoch": 0.6178756476683938,
"grad_norm": 1.2805628776550293,
"learning_rate": 3.3911456481068613e-06,
"loss": 1.4822,
"step": 477
},
{
"epoch": 0.6191709844559585,
"grad_norm": 1.1127654314041138,
"learning_rate": 3.3712767741395475e-06,
"loss": 1.5126,
"step": 478
},
{
"epoch": 0.6204663212435233,
"grad_norm": 1.1410140991210938,
"learning_rate": 3.3514366306733348e-06,
"loss": 1.5273,
"step": 479
},
{
"epoch": 0.6217616580310881,
"grad_norm": 1.0110243558883667,
"learning_rate": 3.3316255676862048e-06,
"loss": 1.4573,
"step": 480
},
{
"epoch": 0.6230569948186528,
"grad_norm": 1.1052619218826294,
"learning_rate": 3.311843934643157e-06,
"loss": 1.6726,
"step": 481
},
{
"epoch": 0.6243523316062176,
"grad_norm": 1.104994535446167,
"learning_rate": 3.2920920804900546e-06,
"loss": 1.5638,
"step": 482
},
{
"epoch": 0.6256476683937824,
"grad_norm": 1.474835753440857,
"learning_rate": 3.272370353647465e-06,
"loss": 1.6106,
"step": 483
},
{
"epoch": 0.6269430051813472,
"grad_norm": 1.1585274934768677,
"learning_rate": 3.252679102004509e-06,
"loss": 1.6305,
"step": 484
},
{
"epoch": 0.6282383419689119,
"grad_norm": 1.1967158317565918,
"learning_rate": 3.233018672912731e-06,
"loss": 1.5684,
"step": 485
},
{
"epoch": 0.6295336787564767,
"grad_norm": 1.050734043121338,
"learning_rate": 3.213389413179969e-06,
"loss": 1.6936,
"step": 486
},
{
"epoch": 0.6308290155440415,
"grad_norm": 1.0748276710510254,
"learning_rate": 3.1937916690642356e-06,
"loss": 1.5009,
"step": 487
},
{
"epoch": 0.6321243523316062,
"grad_norm": 1.71390700340271,
"learning_rate": 3.1742257862676118e-06,
"loss": 1.4632,
"step": 488
},
{
"epoch": 0.633419689119171,
"grad_norm": 1.0704139471054077,
"learning_rate": 3.1546921099301507e-06,
"loss": 1.5499,
"step": 489
},
{
"epoch": 0.6347150259067358,
"grad_norm": 1.167057752609253,
"learning_rate": 3.1351909846237817e-06,
"loss": 1.5004,
"step": 490
},
{
"epoch": 0.6360103626943006,
"grad_norm": 1.131659984588623,
"learning_rate": 3.1157227543462428e-06,
"loss": 1.4833,
"step": 491
},
{
"epoch": 0.6373056994818653,
"grad_norm": 1.113950490951538,
"learning_rate": 3.096287762515005e-06,
"loss": 1.492,
"step": 492
},
{
"epoch": 0.6386010362694301,
"grad_norm": 1.0356504917144775,
"learning_rate": 3.076886351961217e-06,
"loss": 1.4545,
"step": 493
},
{
"epoch": 0.6398963730569949,
"grad_norm": 1.108083724975586,
"learning_rate": 3.0575188649236566e-06,
"loss": 1.5549,
"step": 494
},
{
"epoch": 0.6411917098445595,
"grad_norm": 0.9786263704299927,
"learning_rate": 3.0381856430426935e-06,
"loss": 1.6381,
"step": 495
},
{
"epoch": 0.6424870466321243,
"grad_norm": 1.0314662456512451,
"learning_rate": 3.0188870273542682e-06,
"loss": 1.6056,
"step": 496
},
{
"epoch": 0.6437823834196891,
"grad_norm": 1.3183842897415161,
"learning_rate": 2.9996233582838686e-06,
"loss": 1.5303,
"step": 497
},
{
"epoch": 0.6450777202072538,
"grad_norm": 1.3431285619735718,
"learning_rate": 2.980394975640526e-06,
"loss": 1.4197,
"step": 498
},
{
"epoch": 0.6463730569948186,
"grad_norm": 0.9174752831459045,
"learning_rate": 2.9612022186108267e-06,
"loss": 1.4469,
"step": 499
},
{
"epoch": 0.6476683937823834,
"grad_norm": 1.3870748281478882,
"learning_rate": 2.9420454257529258e-06,
"loss": 1.5492,
"step": 500
},
{
"epoch": 0.6476683937823834,
"eval_loss": 1.6160000562667847,
"eval_runtime": 277.8404,
"eval_samples_per_second": 18.719,
"eval_steps_per_second": 0.295,
"step": 500
},
{
"epoch": 0.6489637305699482,
"grad_norm": 1.276574969291687,
"learning_rate": 2.9229249349905686e-06,
"loss": 1.653,
"step": 501
},
{
"epoch": 0.6502590673575129,
"grad_norm": 1.0013084411621094,
"learning_rate": 2.9038410836071406e-06,
"loss": 1.465,
"step": 502
},
{
"epoch": 0.6515544041450777,
"grad_norm": 1.042726755142212,
"learning_rate": 2.8847942082397112e-06,
"loss": 1.5701,
"step": 503
},
{
"epoch": 0.6528497409326425,
"grad_norm": 1.0435270071029663,
"learning_rate": 2.8657846448730965e-06,
"loss": 1.4272,
"step": 504
},
{
"epoch": 0.6541450777202072,
"grad_norm": 1.0832363367080688,
"learning_rate": 2.846812728833931e-06,
"loss": 1.5845,
"step": 505
},
{
"epoch": 0.655440414507772,
"grad_norm": 1.2031161785125732,
"learning_rate": 2.8278787947847595e-06,
"loss": 1.5273,
"step": 506
},
{
"epoch": 0.6567357512953368,
"grad_norm": 1.143031358718872,
"learning_rate": 2.808983176718125e-06,
"loss": 1.6102,
"step": 507
},
{
"epoch": 0.6580310880829016,
"grad_norm": 1.031115174293518,
"learning_rate": 2.7901262079506785e-06,
"loss": 1.4989,
"step": 508
},
{
"epoch": 0.6593264248704663,
"grad_norm": 1.117822289466858,
"learning_rate": 2.771308221117309e-06,
"loss": 1.5646,
"step": 509
},
{
"epoch": 0.6606217616580311,
"grad_norm": 1.2189844846725464,
"learning_rate": 2.752529548165259e-06,
"loss": 1.4254,
"step": 510
},
{
"epoch": 0.6619170984455959,
"grad_norm": 1.257439136505127,
"learning_rate": 2.7337905203482884e-06,
"loss": 1.3703,
"step": 511
},
{
"epoch": 0.6632124352331606,
"grad_norm": 1.341373324394226,
"learning_rate": 2.7150914682208118e-06,
"loss": 1.527,
"step": 512
},
{
"epoch": 0.6645077720207254,
"grad_norm": 1.1142569780349731,
"learning_rate": 2.696432721632082e-06,
"loss": 1.7398,
"step": 513
},
{
"epoch": 0.6658031088082902,
"grad_norm": 1.0872329473495483,
"learning_rate": 2.6778146097203693e-06,
"loss": 1.4836,
"step": 514
},
{
"epoch": 0.667098445595855,
"grad_norm": 0.9008902907371521,
"learning_rate": 2.6592374609071446e-06,
"loss": 1.5111,
"step": 515
},
{
"epoch": 0.6683937823834197,
"grad_norm": 1.2986565828323364,
"learning_rate": 2.640701602891298e-06,
"loss": 1.4221,
"step": 516
},
{
"epoch": 0.6696891191709845,
"grad_norm": 0.9051121473312378,
"learning_rate": 2.6222073626433587e-06,
"loss": 1.6283,
"step": 517
},
{
"epoch": 0.6709844559585493,
"grad_norm": 1.0537306070327759,
"learning_rate": 2.603755066399718e-06,
"loss": 1.4292,
"step": 518
},
{
"epoch": 0.6722797927461139,
"grad_norm": 1.146615743637085,
"learning_rate": 2.585345039656878e-06,
"loss": 1.5965,
"step": 519
},
{
"epoch": 0.6735751295336787,
"grad_norm": 1.0994024276733398,
"learning_rate": 2.5669776071657194e-06,
"loss": 1.5731,
"step": 520
},
{
"epoch": 0.6748704663212435,
"grad_norm": 1.1996729373931885,
"learning_rate": 2.5486530929257574e-06,
"loss": 1.5688,
"step": 521
},
{
"epoch": 0.6761658031088082,
"grad_norm": 1.2363718748092651,
"learning_rate": 2.5303718201794336e-06,
"loss": 1.553,
"step": 522
},
{
"epoch": 0.677461139896373,
"grad_norm": 1.2366348505020142,
"learning_rate": 2.512134111406422e-06,
"loss": 1.5713,
"step": 523
},
{
"epoch": 0.6787564766839378,
"grad_norm": 1.1853890419006348,
"learning_rate": 2.493940288317925e-06,
"loss": 1.6119,
"step": 524
},
{
"epoch": 0.6800518134715026,
"grad_norm": 1.0547943115234375,
"learning_rate": 2.475790671851007e-06,
"loss": 1.5044,
"step": 525
},
{
"epoch": 0.6813471502590673,
"grad_norm": 0.995441734790802,
"learning_rate": 2.4576855821629397e-06,
"loss": 1.5633,
"step": 526
},
{
"epoch": 0.6826424870466321,
"grad_norm": 1.2481443881988525,
"learning_rate": 2.4396253386255386e-06,
"loss": 1.6463,
"step": 527
},
{
"epoch": 0.6839378238341969,
"grad_norm": 1.2301651239395142,
"learning_rate": 2.4216102598195407e-06,
"loss": 1.5592,
"step": 528
},
{
"epoch": 0.6852331606217616,
"grad_norm": 1.0866541862487793,
"learning_rate": 2.403640663528986e-06,
"loss": 1.4683,
"step": 529
},
{
"epoch": 0.6865284974093264,
"grad_norm": 0.8681275248527527,
"learning_rate": 2.3857168667356022e-06,
"loss": 1.4146,
"step": 530
},
{
"epoch": 0.6878238341968912,
"grad_norm": 1.3087412118911743,
"learning_rate": 2.3678391856132203e-06,
"loss": 1.6037,
"step": 531
},
{
"epoch": 0.689119170984456,
"grad_norm": 1.0823169946670532,
"learning_rate": 2.3500079355222005e-06,
"loss": 1.5972,
"step": 532
},
{
"epoch": 0.6904145077720207,
"grad_norm": 1.0805624723434448,
"learning_rate": 2.332223431003859e-06,
"loss": 1.4776,
"step": 533
},
{
"epoch": 0.6917098445595855,
"grad_norm": 1.1508588790893555,
"learning_rate": 2.3144859857749245e-06,
"loss": 1.5446,
"step": 534
},
{
"epoch": 0.6930051813471503,
"grad_norm": 1.0843334197998047,
"learning_rate": 2.296795912722014e-06,
"loss": 1.5923,
"step": 535
},
{
"epoch": 0.694300518134715,
"grad_norm": 1.4934511184692383,
"learning_rate": 2.2791535238960903e-06,
"loss": 1.4969,
"step": 536
},
{
"epoch": 0.6955958549222798,
"grad_norm": 1.0955530405044556,
"learning_rate": 2.2615591305069846e-06,
"loss": 1.5942,
"step": 537
},
{
"epoch": 0.6968911917098446,
"grad_norm": 1.28902006149292,
"learning_rate": 2.2440130429178874e-06,
"loss": 1.6066,
"step": 538
},
{
"epoch": 0.6981865284974094,
"grad_norm": 1.1328999996185303,
"learning_rate": 2.226515570639879e-06,
"loss": 1.5089,
"step": 539
},
{
"epoch": 0.6994818652849741,
"grad_norm": 1.2266199588775635,
"learning_rate": 2.209067022326476e-06,
"loss": 1.6595,
"step": 540
},
{
"epoch": 0.7007772020725389,
"grad_norm": 1.104842185974121,
"learning_rate": 2.1916677057681786e-06,
"loss": 1.5564,
"step": 541
},
{
"epoch": 0.7020725388601037,
"grad_norm": 0.9999545812606812,
"learning_rate": 2.174317927887041e-06,
"loss": 1.5504,
"step": 542
},
{
"epoch": 0.7033678756476683,
"grad_norm": 1.0765515565872192,
"learning_rate": 2.1570179947312674e-06,
"loss": 1.4155,
"step": 543
},
{
"epoch": 0.7046632124352331,
"grad_norm": 1.035628080368042,
"learning_rate": 2.139768211469803e-06,
"loss": 1.4189,
"step": 544
},
{
"epoch": 0.7059585492227979,
"grad_norm": 1.1408976316452026,
"learning_rate": 2.1225688823869494e-06,
"loss": 1.3906,
"step": 545
},
{
"epoch": 0.7072538860103627,
"grad_norm": 1.3467857837677002,
"learning_rate": 2.105420310877012e-06,
"loss": 1.4841,
"step": 546
},
{
"epoch": 0.7085492227979274,
"grad_norm": 1.10527765750885,
"learning_rate": 2.088322799438931e-06,
"loss": 1.6632,
"step": 547
},
{
"epoch": 0.7098445595854922,
"grad_norm": 1.4465583562850952,
"learning_rate": 2.0712766496709524e-06,
"loss": 1.4955,
"step": 548
},
{
"epoch": 0.711139896373057,
"grad_norm": 0.9860876798629761,
"learning_rate": 2.054282162265313e-06,
"loss": 1.4963,
"step": 549
},
{
"epoch": 0.7124352331606217,
"grad_norm": 1.2740287780761719,
"learning_rate": 2.0373396370029266e-06,
"loss": 1.625,
"step": 550
},
{
"epoch": 0.7137305699481865,
"grad_norm": 1.0191733837127686,
"learning_rate": 2.0204493727480996e-06,
"loss": 1.4699,
"step": 551
},
{
"epoch": 0.7150259067357513,
"grad_norm": 1.0626295804977417,
"learning_rate": 2.0036116674432653e-06,
"loss": 1.5369,
"step": 552
},
{
"epoch": 0.716321243523316,
"grad_norm": 1.200140118598938,
"learning_rate": 1.9868268181037186e-06,
"loss": 1.5947,
"step": 553
},
{
"epoch": 0.7176165803108808,
"grad_norm": 1.2359869480133057,
"learning_rate": 1.9700951208123796e-06,
"loss": 1.7231,
"step": 554
},
{
"epoch": 0.7189119170984456,
"grad_norm": 1.2748795747756958,
"learning_rate": 1.95341687071458e-06,
"loss": 1.6175,
"step": 555
},
{
"epoch": 0.7202072538860104,
"grad_norm": 1.128735899925232,
"learning_rate": 1.9367923620128354e-06,
"loss": 1.5427,
"step": 556
},
{
"epoch": 0.7215025906735751,
"grad_norm": 0.9714717864990234,
"learning_rate": 1.9202218879616824e-06,
"loss": 1.6575,
"step": 557
},
{
"epoch": 0.7227979274611399,
"grad_norm": 1.1940597295761108,
"learning_rate": 1.9037057408624849e-06,
"loss": 1.661,
"step": 558
},
{
"epoch": 0.7240932642487047,
"grad_norm": 1.0992833375930786,
"learning_rate": 1.8872442120582845e-06,
"loss": 1.3107,
"step": 559
},
{
"epoch": 0.7253886010362695,
"grad_norm": 1.0003715753555298,
"learning_rate": 1.8708375919286681e-06,
"loss": 1.5674,
"step": 560
},
{
"epoch": 0.7266839378238342,
"grad_norm": 0.9289507865905762,
"learning_rate": 1.854486169884635e-06,
"loss": 1.5403,
"step": 561
},
{
"epoch": 0.727979274611399,
"grad_norm": 1.1293492317199707,
"learning_rate": 1.8381902343634938e-06,
"loss": 1.4391,
"step": 562
},
{
"epoch": 0.7292746113989638,
"grad_norm": 1.0137596130371094,
"learning_rate": 1.8219500728237849e-06,
"loss": 1.6329,
"step": 563
},
{
"epoch": 0.7305699481865285,
"grad_norm": 1.5705465078353882,
"learning_rate": 1.8057659717401948e-06,
"loss": 1.583,
"step": 564
},
{
"epoch": 0.7318652849740933,
"grad_norm": 1.2883741855621338,
"learning_rate": 1.7896382165985094e-06,
"loss": 1.5483,
"step": 565
},
{
"epoch": 0.7331606217616581,
"grad_norm": 0.981034517288208,
"learning_rate": 1.773567091890585e-06,
"loss": 1.4047,
"step": 566
},
{
"epoch": 0.7344559585492227,
"grad_norm": 1.0456409454345703,
"learning_rate": 1.7575528811093168e-06,
"loss": 1.4473,
"step": 567
},
{
"epoch": 0.7357512953367875,
"grad_norm": 1.0574207305908203,
"learning_rate": 1.7415958667436445e-06,
"loss": 1.5636,
"step": 568
},
{
"epoch": 0.7370466321243523,
"grad_norm": 1.5023987293243408,
"learning_rate": 1.7256963302735752e-06,
"loss": 1.48,
"step": 569
},
{
"epoch": 0.7383419689119171,
"grad_norm": 0.9984103441238403,
"learning_rate": 1.709854552165206e-06,
"loss": 1.6165,
"step": 570
},
{
"epoch": 0.7396373056994818,
"grad_norm": 0.9938836097717285,
"learning_rate": 1.6940708118657838e-06,
"loss": 1.5157,
"step": 571
},
{
"epoch": 0.7409326424870466,
"grad_norm": 1.81129789352417,
"learning_rate": 1.67834538779878e-06,
"loss": 1.4584,
"step": 572
},
{
"epoch": 0.7422279792746114,
"grad_norm": 1.189976453781128,
"learning_rate": 1.6626785573589667e-06,
"loss": 1.5368,
"step": 573
},
{
"epoch": 0.7435233160621761,
"grad_norm": 1.0208349227905273,
"learning_rate": 1.6470705969075335e-06,
"loss": 1.6937,
"step": 574
},
{
"epoch": 0.7448186528497409,
"grad_norm": 1.2884913682937622,
"learning_rate": 1.6315217817672142e-06,
"loss": 1.5275,
"step": 575
},
{
"epoch": 0.7461139896373057,
"grad_norm": 1.036279320716858,
"learning_rate": 1.6160323862174188e-06,
"loss": 1.3944,
"step": 576
},
{
"epoch": 0.7474093264248705,
"grad_norm": 1.1106023788452148,
"learning_rate": 1.6006026834894068e-06,
"loss": 1.5507,
"step": 577
},
{
"epoch": 0.7487046632124352,
"grad_norm": 1.2403995990753174,
"learning_rate": 1.5852329457614602e-06,
"loss": 1.5353,
"step": 578
},
{
"epoch": 0.75,
"grad_norm": 1.0434019565582275,
"learning_rate": 1.5699234441540845e-06,
"loss": 1.3099,
"step": 579
},
{
"epoch": 0.7512953367875648,
"grad_norm": 1.2283532619476318,
"learning_rate": 1.554674448725232e-06,
"loss": 1.4023,
"step": 580
},
{
"epoch": 0.7525906735751295,
"grad_norm": 0.9876958131790161,
"learning_rate": 1.5394862284655266e-06,
"loss": 1.4635,
"step": 581
},
{
"epoch": 0.7538860103626943,
"grad_norm": 1.6783874034881592,
"learning_rate": 1.5243590512935246e-06,
"loss": 1.7265,
"step": 582
},
{
"epoch": 0.7551813471502591,
"grad_norm": 1.021437168121338,
"learning_rate": 1.509293184050995e-06,
"loss": 1.2684,
"step": 583
},
{
"epoch": 0.7564766839378239,
"grad_norm": 1.098883867263794,
"learning_rate": 1.4942888924982008e-06,
"loss": 1.4472,
"step": 584
},
{
"epoch": 0.7577720207253886,
"grad_norm": 1.1636520624160767,
"learning_rate": 1.4793464413092161e-06,
"loss": 1.4747,
"step": 585
},
{
"epoch": 0.7590673575129534,
"grad_norm": 1.0701802968978882,
"learning_rate": 1.4644660940672628e-06,
"loss": 1.5903,
"step": 586
},
{
"epoch": 0.7603626943005182,
"grad_norm": 1.0113797187805176,
"learning_rate": 1.4496481132600516e-06,
"loss": 1.486,
"step": 587
},
{
"epoch": 0.7616580310880829,
"grad_norm": 1.1597944498062134,
"learning_rate": 1.4348927602751555e-06,
"loss": 1.402,
"step": 588
},
{
"epoch": 0.7629533678756477,
"grad_norm": 0.996114194393158,
"learning_rate": 1.4202002953954042e-06,
"loss": 1.4693,
"step": 589
},
{
"epoch": 0.7642487046632125,
"grad_norm": 1.1687228679656982,
"learning_rate": 1.4055709777942833e-06,
"loss": 1.3874,
"step": 590
},
{
"epoch": 0.7655440414507773,
"grad_norm": 0.9727877378463745,
"learning_rate": 1.3910050655313679e-06,
"loss": 1.5345,
"step": 591
},
{
"epoch": 0.7668393782383419,
"grad_norm": 1.0391204357147217,
"learning_rate": 1.376502815547774e-06,
"loss": 1.5989,
"step": 592
},
{
"epoch": 0.7681347150259067,
"grad_norm": 1.0674517154693604,
"learning_rate": 1.362064483661617e-06,
"loss": 1.4254,
"step": 593
},
{
"epoch": 0.7694300518134715,
"grad_norm": 1.392815113067627,
"learning_rate": 1.3476903245635048e-06,
"loss": 1.5638,
"step": 594
},
{
"epoch": 0.7707253886010362,
"grad_norm": 1.4136853218078613,
"learning_rate": 1.3333805918120473e-06,
"loss": 1.4939,
"step": 595
},
{
"epoch": 0.772020725388601,
"grad_norm": 0.9590978026390076,
"learning_rate": 1.3191355378293785e-06,
"loss": 1.521,
"step": 596
},
{
"epoch": 0.7733160621761658,
"grad_norm": 1.1052613258361816,
"learning_rate": 1.3049554138967052e-06,
"loss": 1.535,
"step": 597
},
{
"epoch": 0.7746113989637305,
"grad_norm": 1.246604323387146,
"learning_rate": 1.2908404701498762e-06,
"loss": 1.548,
"step": 598
},
{
"epoch": 0.7759067357512953,
"grad_norm": 1.6142481565475464,
"learning_rate": 1.2767909555749676e-06,
"loss": 1.5366,
"step": 599
},
{
"epoch": 0.7772020725388601,
"grad_norm": 1.3247530460357666,
"learning_rate": 1.2628071180038949e-06,
"loss": 1.6351,
"step": 600
},
{
"epoch": 0.7784974093264249,
"grad_norm": 1.8179649114608765,
"learning_rate": 1.2488892041100364e-06,
"loss": 1.4831,
"step": 601
},
{
"epoch": 0.7797927461139896,
"grad_norm": 1.045743465423584,
"learning_rate": 1.2350374594038817e-06,
"loss": 1.6823,
"step": 602
},
{
"epoch": 0.7810880829015544,
"grad_norm": 1.3222979307174683,
"learning_rate": 1.2212521282287093e-06,
"loss": 1.3961,
"step": 603
},
{
"epoch": 0.7823834196891192,
"grad_norm": 1.320797324180603,
"learning_rate": 1.2075334537562638e-06,
"loss": 1.6146,
"step": 604
},
{
"epoch": 0.783678756476684,
"grad_norm": 1.0100151300430298,
"learning_rate": 1.1938816779824753e-06,
"loss": 1.5368,
"step": 605
},
{
"epoch": 0.7849740932642487,
"grad_norm": 1.3419349193572998,
"learning_rate": 1.1802970417231897e-06,
"loss": 1.5065,
"step": 606
},
{
"epoch": 0.7862694300518135,
"grad_norm": 1.0231964588165283,
"learning_rate": 1.1667797846099172e-06,
"loss": 1.6798,
"step": 607
},
{
"epoch": 0.7875647668393783,
"grad_norm": 1.1260253190994263,
"learning_rate": 1.1533301450856054e-06,
"loss": 1.518,
"step": 608
},
{
"epoch": 0.788860103626943,
"grad_norm": 1.2313636541366577,
"learning_rate": 1.1399483604004403e-06,
"loss": 1.507,
"step": 609
},
{
"epoch": 0.7901554404145078,
"grad_norm": 1.043979525566101,
"learning_rate": 1.1266346666076516e-06,
"loss": 1.4741,
"step": 610
},
{
"epoch": 0.7914507772020726,
"grad_norm": 1.038160800933838,
"learning_rate": 1.1133892985593532e-06,
"loss": 1.576,
"step": 611
},
{
"epoch": 0.7927461139896373,
"grad_norm": 1.0800235271453857,
"learning_rate": 1.1002124899024024e-06,
"loss": 1.4181,
"step": 612
},
{
"epoch": 0.7940414507772021,
"grad_norm": 1.0968854427337646,
"learning_rate": 1.0871044730742752e-06,
"loss": 1.5242,
"step": 613
},
{
"epoch": 0.7953367875647669,
"grad_norm": 1.0271400213241577,
"learning_rate": 1.0740654792989658e-06,
"loss": 1.4949,
"step": 614
},
{
"epoch": 0.7966321243523317,
"grad_norm": 2.4453909397125244,
"learning_rate": 1.061095738582913e-06,
"loss": 1.4534,
"step": 615
},
{
"epoch": 0.7979274611398963,
"grad_norm": 1.303238034248352,
"learning_rate": 1.0481954797109344e-06,
"loss": 1.5555,
"step": 616
},
{
"epoch": 0.7992227979274611,
"grad_norm": 0.9862561225891113,
"learning_rate": 1.0353649302421982e-06,
"loss": 1.4974,
"step": 617
},
{
"epoch": 0.8005181347150259,
"grad_norm": 1.011978268623352,
"learning_rate": 1.0226043165062082e-06,
"loss": 1.3898,
"step": 618
},
{
"epoch": 0.8018134715025906,
"grad_norm": 1.3432072401046753,
"learning_rate": 1.0099138635988026e-06,
"loss": 1.5856,
"step": 619
},
{
"epoch": 0.8031088082901554,
"grad_norm": 1.4225488901138306,
"learning_rate": 9.972937953781985e-07,
"loss": 1.5499,
"step": 620
},
{
"epoch": 0.8044041450777202,
"grad_norm": 1.9342267513275146,
"learning_rate": 9.847443344610296e-07,
"loss": 1.4327,
"step": 621
},
{
"epoch": 0.805699481865285,
"grad_norm": 1.0823417901992798,
"learning_rate": 9.722657022184245e-07,
"loss": 1.4037,
"step": 622
},
{
"epoch": 0.8069948186528497,
"grad_norm": 1.3602349758148193,
"learning_rate": 9.59858118772105e-07,
"loss": 1.563,
"step": 623
},
{
"epoch": 0.8082901554404145,
"grad_norm": 1.2760757207870483,
"learning_rate": 9.47521802990497e-07,
"loss": 1.7271,
"step": 624
},
{
"epoch": 0.8095854922279793,
"grad_norm": 1.1673961877822876,
"learning_rate": 9.352569724848715e-07,
"loss": 1.7494,
"step": 625
},
{
"epoch": 0.810880829015544,
"grad_norm": 1.0064778327941895,
"learning_rate": 9.230638436055122e-07,
"loss": 1.3722,
"step": 626
},
{
"epoch": 0.8121761658031088,
"grad_norm": 2.09700608253479,
"learning_rate": 9.109426314378878e-07,
"loss": 1.3962,
"step": 627
},
{
"epoch": 0.8134715025906736,
"grad_norm": 1.417157769203186,
"learning_rate": 8.988935497988666e-07,
"loss": 1.5885,
"step": 628
},
{
"epoch": 0.8147668393782384,
"grad_norm": 1.1651970148086548,
"learning_rate": 8.86916811232944e-07,
"loss": 1.4713,
"step": 629
},
{
"epoch": 0.8160621761658031,
"grad_norm": 1.0425779819488525,
"learning_rate": 8.750126270084891e-07,
"loss": 1.4059,
"step": 630
},
{
"epoch": 0.8173575129533679,
"grad_norm": 1.2462821006774902,
"learning_rate": 8.631812071140189e-07,
"loss": 1.4826,
"step": 631
},
{
"epoch": 0.8186528497409327,
"grad_norm": 0.9702634811401367,
"learning_rate": 8.514227602545e-07,
"loss": 1.5013,
"step": 632
},
{
"epoch": 0.8199481865284974,
"grad_norm": 1.1513921022415161,
"learning_rate": 8.397374938476594e-07,
"loss": 1.6157,
"step": 633
},
{
"epoch": 0.8212435233160622,
"grad_norm": 1.1683169603347778,
"learning_rate": 8.28125614020327e-07,
"loss": 1.4692,
"step": 634
},
{
"epoch": 0.822538860103627,
"grad_norm": 1.1551121473312378,
"learning_rate": 8.165873256048079e-07,
"loss": 1.5019,
"step": 635
},
{
"epoch": 0.8238341968911918,
"grad_norm": 1.3063536882400513,
"learning_rate": 8.051228321352567e-07,
"loss": 1.4964,
"step": 636
},
{
"epoch": 0.8251295336787565,
"grad_norm": 1.1921881437301636,
"learning_rate": 7.937323358440935e-07,
"loss": 1.4022,
"step": 637
},
{
"epoch": 0.8264248704663213,
"grad_norm": 1.0258533954620361,
"learning_rate": 7.824160376584422e-07,
"loss": 1.5113,
"step": 638
},
{
"epoch": 0.8277202072538861,
"grad_norm": 1.6122270822525024,
"learning_rate": 7.711741371965703e-07,
"loss": 1.4753,
"step": 639
},
{
"epoch": 0.8290155440414507,
"grad_norm": 1.2944881916046143,
"learning_rate": 7.600068327643867e-07,
"loss": 1.7111,
"step": 640
},
{
"epoch": 0.8303108808290155,
"grad_norm": 1.1729899644851685,
"learning_rate": 7.489143213519301e-07,
"loss": 1.3627,
"step": 641
},
{
"epoch": 0.8316062176165803,
"grad_norm": 1.096620798110962,
"learning_rate": 7.378967986298974e-07,
"loss": 1.5417,
"step": 642
},
{
"epoch": 0.832901554404145,
"grad_norm": 1.161104679107666,
"learning_rate": 7.269544589461968e-07,
"loss": 1.5107,
"step": 643
},
{
"epoch": 0.8341968911917098,
"grad_norm": 1.1583714485168457,
"learning_rate": 7.160874953225133e-07,
"loss": 1.3914,
"step": 644
},
{
"epoch": 0.8354922279792746,
"grad_norm": 1.3577739000320435,
"learning_rate": 7.052960994509056e-07,
"loss": 1.4662,
"step": 645
},
{
"epoch": 0.8367875647668394,
"grad_norm": 1.3174091577529907,
"learning_rate": 6.945804616904284e-07,
"loss": 1.6151,
"step": 646
},
{
"epoch": 0.8380829015544041,
"grad_norm": 1.4153250455856323,
"learning_rate": 6.839407710637696e-07,
"loss": 1.596,
"step": 647
},
{
"epoch": 0.8393782383419689,
"grad_norm": 1.5289397239685059,
"learning_rate": 6.73377215253917e-07,
"loss": 1.4646,
"step": 648
},
{
"epoch": 0.8406735751295337,
"grad_norm": 1.250548005104065,
"learning_rate": 6.628899806008515e-07,
"loss": 1.5456,
"step": 649
},
{
"epoch": 0.8419689119170984,
"grad_norm": 1.1685513257980347,
"learning_rate": 6.524792520982548e-07,
"loss": 1.5779,
"step": 650
},
{
"epoch": 0.8432642487046632,
"grad_norm": 1.0056496858596802,
"learning_rate": 6.421452133902467e-07,
"loss": 1.5776,
"step": 651
},
{
"epoch": 0.844559585492228,
"grad_norm": 1.121643304824829,
"learning_rate": 6.318880467681527e-07,
"loss": 1.4929,
"step": 652
},
{
"epoch": 0.8458549222797928,
"grad_norm": 0.9304026365280151,
"learning_rate": 6.217079331672777e-07,
"loss": 1.4239,
"step": 653
},
{
"epoch": 0.8471502590673575,
"grad_norm": 1.0143840312957764,
"learning_rate": 6.116050521637218e-07,
"loss": 1.4688,
"step": 654
},
{
"epoch": 0.8484455958549223,
"grad_norm": 1.0243223905563354,
"learning_rate": 6.015795819712117e-07,
"loss": 1.5488,
"step": 655
},
{
"epoch": 0.8497409326424871,
"grad_norm": 1.1203079223632812,
"learning_rate": 5.916316994379539e-07,
"loss": 1.5494,
"step": 656
},
{
"epoch": 0.8510362694300518,
"grad_norm": 1.1410661935806274,
"learning_rate": 5.817615800435167e-07,
"loss": 1.4268,
"step": 657
},
{
"epoch": 0.8523316062176166,
"grad_norm": 1.0074669122695923,
"learning_rate": 5.71969397895738e-07,
"loss": 1.5056,
"step": 658
},
{
"epoch": 0.8536269430051814,
"grad_norm": 2.5608999729156494,
"learning_rate": 5.622553257276487e-07,
"loss": 1.3922,
"step": 659
},
{
"epoch": 0.8549222797927462,
"grad_norm": 1.035542607307434,
"learning_rate": 5.526195348944263e-07,
"loss": 1.5839,
"step": 660
},
{
"epoch": 0.8562176165803109,
"grad_norm": 1.0975297689437866,
"learning_rate": 5.430621953703785e-07,
"loss": 1.4795,
"step": 661
},
{
"epoch": 0.8575129533678757,
"grad_norm": 1.055418848991394,
"learning_rate": 5.335834757459374e-07,
"loss": 1.3781,
"step": 662
},
{
"epoch": 0.8588082901554405,
"grad_norm": 1.0941356420516968,
"learning_rate": 5.241835432246888e-07,
"loss": 1.4547,
"step": 663
},
{
"epoch": 0.8601036269430051,
"grad_norm": 1.3171483278274536,
"learning_rate": 5.148625636204246e-07,
"loss": 1.4029,
"step": 664
},
{
"epoch": 0.8613989637305699,
"grad_norm": 1.208213448524475,
"learning_rate": 5.056207013542131e-07,
"loss": 1.504,
"step": 665
},
{
"epoch": 0.8626943005181347,
"grad_norm": 1.5083415508270264,
"learning_rate": 4.964581194515033e-07,
"loss": 1.563,
"step": 666
},
{
"epoch": 0.8639896373056994,
"grad_norm": 1.1956511735916138,
"learning_rate": 4.873749795392469e-07,
"loss": 1.6327,
"step": 667
},
{
"epoch": 0.8652849740932642,
"grad_norm": 1.0977568626403809,
"learning_rate": 4.783714418430452e-07,
"loss": 1.7057,
"step": 668
},
{
"epoch": 0.866580310880829,
"grad_norm": 1.0108611583709717,
"learning_rate": 4.6944766518432936e-07,
"loss": 1.366,
"step": 669
},
{
"epoch": 0.8678756476683938,
"grad_norm": 1.1947669982910156,
"learning_rate": 4.6060380697755037e-07,
"loss": 1.5102,
"step": 670
},
{
"epoch": 0.8691709844559585,
"grad_norm": 1.0838466882705688,
"learning_rate": 4.5184002322740784e-07,
"loss": 1.6398,
"step": 671
},
{
"epoch": 0.8704663212435233,
"grad_norm": 1.454020619392395,
"learning_rate": 4.4315646852609863e-07,
"loss": 1.3655,
"step": 672
},
{
"epoch": 0.8717616580310881,
"grad_norm": 1.3168362379074097,
"learning_rate": 4.3455329605058436e-07,
"loss": 1.4982,
"step": 673
},
{
"epoch": 0.8730569948186528,
"grad_norm": 1.051073670387268,
"learning_rate": 4.2603065755989493e-07,
"loss": 1.3786,
"step": 674
},
{
"epoch": 0.8743523316062176,
"grad_norm": 1.2360527515411377,
"learning_rate": 4.175887033924503e-07,
"loss": 1.5025,
"step": 675
},
{
"epoch": 0.8756476683937824,
"grad_norm": 1.0617810487747192,
"learning_rate": 4.0922758246340567e-07,
"loss": 1.5329,
"step": 676
},
{
"epoch": 0.8769430051813472,
"grad_norm": 0.9416881799697876,
"learning_rate": 4.009474422620269e-07,
"loss": 1.4376,
"step": 677
},
{
"epoch": 0.8782383419689119,
"grad_norm": 1.3161721229553223,
"learning_rate": 3.9274842884909127e-07,
"loss": 1.5307,
"step": 678
},
{
"epoch": 0.8795336787564767,
"grad_norm": 1.0494760274887085,
"learning_rate": 3.846306868543054e-07,
"loss": 1.5753,
"step": 679
},
{
"epoch": 0.8808290155440415,
"grad_norm": 1.216455340385437,
"learning_rate": 3.765943594737581e-07,
"loss": 1.5939,
"step": 680
},
{
"epoch": 0.8821243523316062,
"grad_norm": 1.8970232009887695,
"learning_rate": 3.6863958846739213e-07,
"loss": 1.4686,
"step": 681
},
{
"epoch": 0.883419689119171,
"grad_norm": 1.0949366092681885,
"learning_rate": 3.607665141565064e-07,
"loss": 1.5858,
"step": 682
},
{
"epoch": 0.8847150259067358,
"grad_norm": 1.0741788148880005,
"learning_rate": 3.5297527542127675e-07,
"loss": 1.679,
"step": 683
},
{
"epoch": 0.8860103626943006,
"grad_norm": 0.9756839871406555,
"learning_rate": 3.452660096983118e-07,
"loss": 1.4888,
"step": 684
},
{
"epoch": 0.8873056994818653,
"grad_norm": 1.0563324689865112,
"learning_rate": 3.3763885297822153e-07,
"loss": 1.3987,
"step": 685
},
{
"epoch": 0.8886010362694301,
"grad_norm": 0.9850306510925293,
"learning_rate": 3.3009393980322325e-07,
"loss": 1.5413,
"step": 686
},
{
"epoch": 0.8898963730569949,
"grad_norm": 1.3995580673217773,
"learning_rate": 3.226314032647687e-07,
"loss": 1.6805,
"step": 687
},
{
"epoch": 0.8911917098445595,
"grad_norm": 1.0318669080734253,
"learning_rate": 3.1525137500119207e-07,
"loss": 1.5607,
"step": 688
},
{
"epoch": 0.8924870466321243,
"grad_norm": 1.2014789581298828,
"learning_rate": 3.0795398519539113e-07,
"loss": 1.5258,
"step": 689
},
{
"epoch": 0.8937823834196891,
"grad_norm": 1.2160273790359497,
"learning_rate": 3.0073936257253243e-07,
"loss": 1.4627,
"step": 690
},
{
"epoch": 0.8950777202072538,
"grad_norm": 1.0839946269989014,
"learning_rate": 2.936076343977762e-07,
"loss": 1.4173,
"step": 691
},
{
"epoch": 0.8963730569948186,
"grad_norm": 1.1021478176116943,
"learning_rate": 2.8655892647403316e-07,
"loss": 1.6038,
"step": 692
},
{
"epoch": 0.8976683937823834,
"grad_norm": 1.130834937095642,
"learning_rate": 2.7959336313974847e-07,
"loss": 1.4834,
"step": 693
},
{
"epoch": 0.8989637305699482,
"grad_norm": 1.414772868156433,
"learning_rate": 2.7271106726670327e-07,
"loss": 1.32,
"step": 694
},
{
"epoch": 0.9002590673575129,
"grad_norm": 1.4941953420639038,
"learning_rate": 2.6591216025784904e-07,
"loss": 1.5023,
"step": 695
},
{
"epoch": 0.9015544041450777,
"grad_norm": 1.0596383810043335,
"learning_rate": 2.5919676204517073e-07,
"loss": 1.5257,
"step": 696
},
{
"epoch": 0.9028497409326425,
"grad_norm": 1.493388295173645,
"learning_rate": 2.525649910875627e-07,
"loss": 1.651,
"step": 697
},
{
"epoch": 0.9041450777202072,
"grad_norm": 1.2009479999542236,
"learning_rate": 2.4601696436874714e-07,
"loss": 1.6201,
"step": 698
},
{
"epoch": 0.905440414507772,
"grad_norm": 1.7740060091018677,
"learning_rate": 2.3955279739520496e-07,
"loss": 1.4531,
"step": 699
},
{
"epoch": 0.9067357512953368,
"grad_norm": 1.3489179611206055,
"learning_rate": 2.33172604194139e-07,
"loss": 1.3992,
"step": 700
},
{
"epoch": 0.9080310880829016,
"grad_norm": 0.9706228375434875,
"learning_rate": 2.2687649731146844e-07,
"loss": 1.3963,
"step": 701
},
{
"epoch": 0.9093264248704663,
"grad_norm": 1.2245378494262695,
"learning_rate": 2.2066458780983402e-07,
"loss": 1.4028,
"step": 702
},
{
"epoch": 0.9106217616580311,
"grad_norm": 1.0631040334701538,
"learning_rate": 2.1453698526664513e-07,
"loss": 1.5179,
"step": 703
},
{
"epoch": 0.9119170984455959,
"grad_norm": 1.1595566272735596,
"learning_rate": 2.0849379777214795e-07,
"loss": 1.4707,
"step": 704
},
{
"epoch": 0.9132124352331606,
"grad_norm": 1.0438196659088135,
"learning_rate": 2.0253513192751374e-07,
"loss": 1.2734,
"step": 705
},
{
"epoch": 0.9145077720207254,
"grad_norm": 0.9485345482826233,
"learning_rate": 1.9666109284296132e-07,
"loss": 1.2829,
"step": 706
},
{
"epoch": 0.9158031088082902,
"grad_norm": 1.0819053649902344,
"learning_rate": 1.908717841359048e-07,
"loss": 1.4419,
"step": 707
},
{
"epoch": 0.917098445595855,
"grad_norm": 1.095530390739441,
"learning_rate": 1.8516730792912162e-07,
"loss": 1.3958,
"step": 708
},
{
"epoch": 0.9183937823834197,
"grad_norm": 1.1274775266647339,
"learning_rate": 1.7954776484895188e-07,
"loss": 1.5041,
"step": 709
},
{
"epoch": 0.9196891191709845,
"grad_norm": 0.9921205639839172,
"learning_rate": 1.740132540235284e-07,
"loss": 1.4632,
"step": 710
},
{
"epoch": 0.9209844559585493,
"grad_norm": 1.066158413887024,
"learning_rate": 1.6856387308102073e-07,
"loss": 1.4718,
"step": 711
},
{
"epoch": 0.9222797927461139,
"grad_norm": 1.3315412998199463,
"learning_rate": 1.631997181479178e-07,
"loss": 1.5242,
"step": 712
},
{
"epoch": 0.9235751295336787,
"grad_norm": 1.34335196018219,
"learning_rate": 1.5792088384733174e-07,
"loss": 1.5353,
"step": 713
},
{
"epoch": 0.9248704663212435,
"grad_norm": 1.4508405923843384,
"learning_rate": 1.527274632973269e-07,
"loss": 1.5095,
"step": 714
},
{
"epoch": 0.9261658031088082,
"grad_norm": 1.0910401344299316,
"learning_rate": 1.4761954810927791e-07,
"loss": 1.3197,
"step": 715
},
{
"epoch": 0.927461139896373,
"grad_norm": 1.2772433757781982,
"learning_rate": 1.4259722838625644e-07,
"loss": 1.5011,
"step": 716
},
{
"epoch": 0.9287564766839378,
"grad_norm": 1.0307416915893555,
"learning_rate": 1.376605927214364e-07,
"loss": 1.5205,
"step": 717
},
{
"epoch": 0.9300518134715026,
"grad_norm": 1.1507757902145386,
"learning_rate": 1.328097281965357e-07,
"loss": 1.4095,
"step": 718
},
{
"epoch": 0.9313471502590673,
"grad_norm": 1.028639793395996,
"learning_rate": 1.2804472038027983e-07,
"loss": 1.3675,
"step": 719
},
{
"epoch": 0.9326424870466321,
"grad_norm": 1.1907833814620972,
"learning_rate": 1.23365653326889e-07,
"loss": 1.599,
"step": 720
},
{
"epoch": 0.9339378238341969,
"grad_norm": 1.2436916828155518,
"learning_rate": 1.1877260957459835e-07,
"loss": 1.5927,
"step": 721
},
{
"epoch": 0.9352331606217616,
"grad_norm": 1.514359712600708,
"learning_rate": 1.1426567014420297e-07,
"loss": 1.5129,
"step": 722
},
{
"epoch": 0.9365284974093264,
"grad_norm": 0.9220609664916992,
"learning_rate": 1.0984491453762402e-07,
"loss": 1.4133,
"step": 723
},
{
"epoch": 0.9378238341968912,
"grad_norm": 1.2586432695388794,
"learning_rate": 1.0551042073651263e-07,
"loss": 1.4889,
"step": 724
},
{
"epoch": 0.939119170984456,
"grad_norm": 1.1107631921768188,
"learning_rate": 1.0126226520086823e-07,
"loss": 1.3768,
"step": 725
},
{
"epoch": 0.9404145077720207,
"grad_norm": 0.9724913835525513,
"learning_rate": 9.710052286769467e-08,
"loss": 1.4573,
"step": 726
},
{
"epoch": 0.9417098445595855,
"grad_norm": 1.2193260192871094,
"learning_rate": 9.302526714967508e-08,
"loss": 1.5472,
"step": 727
},
{
"epoch": 0.9430051813471503,
"grad_norm": 1.103522539138794,
"learning_rate": 8.903656993387855e-08,
"loss": 1.428,
"step": 728
},
{
"epoch": 0.944300518134715,
"grad_norm": 1.2310312986373901,
"learning_rate": 8.513450158049109e-08,
"loss": 1.4826,
"step": 729
},
{
"epoch": 0.9455958549222798,
"grad_norm": 1.2056171894073486,
"learning_rate": 8.131913092157607e-08,
"loss": 1.6688,
"step": 730
},
{
"epoch": 0.9468911917098446,
"grad_norm": 1.054947853088379,
"learning_rate": 7.7590525259858e-08,
"loss": 1.6276,
"step": 731
},
{
"epoch": 0.9481865284974094,
"grad_norm": 1.3186241388320923,
"learning_rate": 7.394875036753624e-08,
"loss": 1.6413,
"step": 732
},
{
"epoch": 0.9494818652849741,
"grad_norm": 1.2025482654571533,
"learning_rate": 7.03938704851248e-08,
"loss": 1.438,
"step": 733
},
{
"epoch": 0.9507772020725389,
"grad_norm": 1.414857268333435,
"learning_rate": 6.692594832031996e-08,
"loss": 1.4823,
"step": 734
},
{
"epoch": 0.9520725388601037,
"grad_norm": 0.9129720330238342,
"learning_rate": 6.354504504689219e-08,
"loss": 1.4277,
"step": 735
},
{
"epoch": 0.9533678756476683,
"grad_norm": 1.019188404083252,
"learning_rate": 6.025122030360875e-08,
"loss": 1.5039,
"step": 736
},
{
"epoch": 0.9546632124352331,
"grad_norm": 0.9425042867660522,
"learning_rate": 5.704453219318118e-08,
"loss": 1.4127,
"step": 737
},
{
"epoch": 0.9559585492227979,
"grad_norm": 1.0015157461166382,
"learning_rate": 5.392503728123943e-08,
"loss": 1.5229,
"step": 738
},
{
"epoch": 0.9572538860103627,
"grad_norm": 1.1523234844207764,
"learning_rate": 5.089279059533658e-08,
"loss": 1.4312,
"step": 739
},
{
"epoch": 0.9585492227979274,
"grad_norm": 0.9955514073371887,
"learning_rate": 4.794784562397459e-08,
"loss": 1.5079,
"step": 740
},
{
"epoch": 0.9598445595854922,
"grad_norm": 1.2135977745056152,
"learning_rate": 4.509025431566283e-08,
"loss": 1.3699,
"step": 741
},
{
"epoch": 0.961139896373057,
"grad_norm": 1.2525806427001953,
"learning_rate": 4.232006707800385e-08,
"loss": 1.4568,
"step": 742
},
{
"epoch": 0.9624352331606217,
"grad_norm": 1.6499637365341187,
"learning_rate": 3.963733277679904e-08,
"loss": 1.6413,
"step": 743
},
{
"epoch": 0.9637305699481865,
"grad_norm": 1.0440094470977783,
"learning_rate": 3.704209873519049e-08,
"loss": 1.549,
"step": 744
},
{
"epoch": 0.9650259067357513,
"grad_norm": 1.091898798942566,
"learning_rate": 3.4534410732825485e-08,
"loss": 1.4922,
"step": 745
},
{
"epoch": 0.966321243523316,
"grad_norm": 1.240093469619751,
"learning_rate": 3.2114313005048306e-08,
"loss": 1.4725,
"step": 746
},
{
"epoch": 0.9676165803108808,
"grad_norm": 1.2280330657958984,
"learning_rate": 2.978184824212138e-08,
"loss": 1.493,
"step": 747
},
{
"epoch": 0.9689119170984456,
"grad_norm": 1.147080898284912,
"learning_rate": 2.753705758846925e-08,
"loss": 1.4519,
"step": 748
},
{
"epoch": 0.9702072538860104,
"grad_norm": 1.269758939743042,
"learning_rate": 2.5379980641955792e-08,
"loss": 1.4197,
"step": 749
},
{
"epoch": 0.9715025906735751,
"grad_norm": 1.1858763694763184,
"learning_rate": 2.3310655453184228e-08,
"loss": 1.4899,
"step": 750
},
{
"epoch": 0.9727979274611399,
"grad_norm": 1.1615616083145142,
"learning_rate": 2.1329118524827662e-08,
"loss": 1.423,
"step": 751
},
{
"epoch": 0.9740932642487047,
"grad_norm": 1.3260447978973389,
"learning_rate": 1.9435404810981274e-08,
"loss": 1.5746,
"step": 752
},
{
"epoch": 0.9753886010362695,
"grad_norm": 1.1854459047317505,
"learning_rate": 1.762954771655001e-08,
"loss": 1.5478,
"step": 753
},
{
"epoch": 0.9766839378238342,
"grad_norm": 1.1647753715515137,
"learning_rate": 1.591157909665797e-08,
"loss": 1.3276,
"step": 754
},
{
"epoch": 0.977979274611399,
"grad_norm": 1.194664716720581,
"learning_rate": 1.4281529256084393e-08,
"loss": 1.3428,
"step": 755
},
{
"epoch": 0.9792746113989638,
"grad_norm": 1.1397722959518433,
"learning_rate": 1.2739426948732426e-08,
"loss": 1.5889,
"step": 756
},
{
"epoch": 0.9805699481865285,
"grad_norm": 1.1827527284622192,
"learning_rate": 1.1285299377118974e-08,
"loss": 1.5029,
"step": 757
},
{
"epoch": 0.9818652849740933,
"grad_norm": 1.8461915254592896,
"learning_rate": 9.919172191896753e-09,
"loss": 1.6082,
"step": 758
},
{
"epoch": 0.9831606217616581,
"grad_norm": 1.200221061706543,
"learning_rate": 8.641069491401866e-09,
"loss": 1.4912,
"step": 759
},
{
"epoch": 0.9844559585492227,
"grad_norm": 1.479081153869629,
"learning_rate": 7.451013821226926e-09,
"loss": 1.672,
"step": 760
},
{
"epoch": 0.9857512953367875,
"grad_norm": 1.0301047563552856,
"learning_rate": 6.349026173824713e-09,
"loss": 1.3822,
"step": 761
},
{
"epoch": 0.9870466321243523,
"grad_norm": 1.1225385665893555,
"learning_rate": 5.3351259881379016e-09,
"loss": 1.4322,
"step": 762
},
{
"epoch": 0.9883419689119171,
"grad_norm": 1.059754729270935,
"learning_rate": 4.409331149256013e-09,
"loss": 1.5162,
"step": 763
},
{
"epoch": 0.9896373056994818,
"grad_norm": 0.9742915630340576,
"learning_rate": 3.571657988099553e-09,
"loss": 1.3936,
"step": 764
},
{
"epoch": 0.9909326424870466,
"grad_norm": 1.053778886795044,
"learning_rate": 2.8221212811324616e-09,
"loss": 1.5584,
"step": 765
},
{
"epoch": 0.9922279792746114,
"grad_norm": 1.1606477499008179,
"learning_rate": 2.16073425010066e-09,
"loss": 1.6356,
"step": 766
},
{
"epoch": 0.9935233160621761,
"grad_norm": 0.9651188254356384,
"learning_rate": 1.5875085617994558e-09,
"loss": 1.462,
"step": 767
},
{
"epoch": 0.9948186528497409,
"grad_norm": 1.2689077854156494,
"learning_rate": 1.1024543278687072e-09,
"loss": 1.6316,
"step": 768
},
{
"epoch": 0.9961139896373057,
"grad_norm": 1.1141794919967651,
"learning_rate": 7.055801046113031e-10,
"loss": 1.4444,
"step": 769
},
{
"epoch": 0.9974093264248705,
"grad_norm": 1.2026137113571167,
"learning_rate": 3.96892892846612e-10,
"loss": 1.5424,
"step": 770
},
{
"epoch": 0.9987046632124352,
"grad_norm": 1.5451464653015137,
"learning_rate": 1.7639813778336233e-10,
"loss": 1.5545,
"step": 771
},
{
"epoch": 1.0,
"grad_norm": 1.247829794883728,
"learning_rate": 4.409972892416292e-11,
"loss": 1.6096,
"step": 772
},
{
"epoch": 1.0,
"step": 772,
"total_flos": 4.500722646748496e+18,
"train_loss": 1.728162583909504,
"train_runtime": 33108.0128,
"train_samples_per_second": 2.984,
"train_steps_per_second": 0.023
}
],
"logging_steps": 1.0,
"max_steps": 772,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 3,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4.500722646748496e+18,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}