Files
orpheus-3b-0.1-ft/trainer_state.json
ModelHub XC 9c8ac88724 初始化项目,由ModelHub XC社区提供模型
Model: baseten/orpheus-3b-0.1-ft
Source: Original Platform
2026-08-23 21:23:12 +08:00

5256 lines
127 KiB
JSON

{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 746,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0013404825737265416,
"grad_norm": 3.3526411056518555,
"learning_rate": 4.9999778317473914e-05,
"loss": 4.9952,
"step": 1
},
{
"epoch": 0.002680965147453083,
"grad_norm": 3.2630183696746826,
"learning_rate": 4.999911327382711e-05,
"loss": 4.971,
"step": 2
},
{
"epoch": 0.004021447721179625,
"grad_norm": 3.3700828552246094,
"learning_rate": 4.999800488085388e-05,
"loss": 4.4211,
"step": 3
},
{
"epoch": 0.005361930294906166,
"grad_norm": 5.005458354949951,
"learning_rate": 4.999645315821111e-05,
"loss": 4.4647,
"step": 4
},
{
"epoch": 0.006702412868632708,
"grad_norm": 2.819751024246216,
"learning_rate": 4.9994458133418e-05,
"loss": 4.616,
"step": 5
},
{
"epoch": 0.00804289544235925,
"grad_norm": 2.5557587146759033,
"learning_rate": 4.999201984185552e-05,
"loss": 4.5558,
"step": 6
},
{
"epoch": 0.00938337801608579,
"grad_norm": 2.4157004356384277,
"learning_rate": 4.998913832676579e-05,
"loss": 4.6775,
"step": 7
},
{
"epoch": 0.010723860589812333,
"grad_norm": 4.6227898597717285,
"learning_rate": 4.9985813639251355e-05,
"loss": 4.2805,
"step": 8
},
{
"epoch": 0.012064343163538873,
"grad_norm": 3.3465769290924072,
"learning_rate": 4.998204583827421e-05,
"loss": 4.6374,
"step": 9
},
{
"epoch": 0.013404825737265416,
"grad_norm": 2.7642695903778076,
"learning_rate": 4.9977834990654804e-05,
"loss": 4.6426,
"step": 10
},
{
"epoch": 0.014745308310991957,
"grad_norm": 2.5907504558563232,
"learning_rate": 4.997318117107085e-05,
"loss": 4.6113,
"step": 11
},
{
"epoch": 0.0160857908847185,
"grad_norm": 3.1902687549591064,
"learning_rate": 4.996808446205599e-05,
"loss": 4.6342,
"step": 12
},
{
"epoch": 0.01742627345844504,
"grad_norm": 2.263828992843628,
"learning_rate": 4.9962544953998316e-05,
"loss": 4.6859,
"step": 13
},
{
"epoch": 0.01876675603217158,
"grad_norm": 4.422379493713379,
"learning_rate": 4.995656274513881e-05,
"loss": 4.6602,
"step": 14
},
{
"epoch": 0.020107238605898123,
"grad_norm": 2.6276822090148926,
"learning_rate": 4.995013794156957e-05,
"loss": 4.602,
"step": 15
},
{
"epoch": 0.021447721179624665,
"grad_norm": 2.7755320072174072,
"learning_rate": 4.994327065723192e-05,
"loss": 4.7146,
"step": 16
},
{
"epoch": 0.022788203753351208,
"grad_norm": 3.358004570007324,
"learning_rate": 4.993596101391443e-05,
"loss": 4.743,
"step": 17
},
{
"epoch": 0.024128686327077747,
"grad_norm": 3.4165093898773193,
"learning_rate": 4.992820914125069e-05,
"loss": 4.5962,
"step": 18
},
{
"epoch": 0.02546916890080429,
"grad_norm": 2.9194705486297607,
"learning_rate": 4.9920015176717105e-05,
"loss": 4.589,
"step": 19
},
{
"epoch": 0.02680965147453083,
"grad_norm": 3.347116708755493,
"learning_rate": 4.991137926563036e-05,
"loss": 4.4779,
"step": 20
},
{
"epoch": 0.028150134048257374,
"grad_norm": 2.8503966331481934,
"learning_rate": 4.99023015611449e-05,
"loss": 4.507,
"step": 21
},
{
"epoch": 0.029490616621983913,
"grad_norm": 3.68805193901062,
"learning_rate": 4.989278222425021e-05,
"loss": 4.3752,
"step": 22
},
{
"epoch": 0.030831099195710455,
"grad_norm": 2.815739393234253,
"learning_rate": 4.988282142376795e-05,
"loss": 4.557,
"step": 23
},
{
"epoch": 0.032171581769437,
"grad_norm": 2.82580304145813,
"learning_rate": 4.987241933634893e-05,
"loss": 4.3446,
"step": 24
},
{
"epoch": 0.03351206434316354,
"grad_norm": 2.799983501434326,
"learning_rate": 4.986157614647005e-05,
"loss": 4.5178,
"step": 25
},
{
"epoch": 0.03485254691689008,
"grad_norm": 2.573227882385254,
"learning_rate": 4.985029204643095e-05,
"loss": 4.5714,
"step": 26
},
{
"epoch": 0.036193029490616625,
"grad_norm": 4.1363725662231445,
"learning_rate": 4.983856723635067e-05,
"loss": 4.5211,
"step": 27
},
{
"epoch": 0.03753351206434316,
"grad_norm": 2.340411901473999,
"learning_rate": 4.982640192416404e-05,
"loss": 4.4884,
"step": 28
},
{
"epoch": 0.0388739946380697,
"grad_norm": 2.98046612739563,
"learning_rate": 4.9813796325618055e-05,
"loss": 4.4493,
"step": 29
},
{
"epoch": 0.040214477211796246,
"grad_norm": 3.8894741535186768,
"learning_rate": 4.980075066426796e-05,
"loss": 4.444,
"step": 30
},
{
"epoch": 0.04155495978552279,
"grad_norm": 1.941263198852539,
"learning_rate": 4.9787265171473385e-05,
"loss": 4.4268,
"step": 31
},
{
"epoch": 0.04289544235924933,
"grad_norm": 3.7895383834838867,
"learning_rate": 4.977334008639417e-05,
"loss": 4.5663,
"step": 32
},
{
"epoch": 0.04423592493297587,
"grad_norm": 2.8732171058654785,
"learning_rate": 4.9758975655986164e-05,
"loss": 4.3439,
"step": 33
},
{
"epoch": 0.045576407506702415,
"grad_norm": 2.5092976093292236,
"learning_rate": 4.974417213499681e-05,
"loss": 4.5183,
"step": 34
},
{
"epoch": 0.04691689008042895,
"grad_norm": 2.5558083057403564,
"learning_rate": 4.972892978596069e-05,
"loss": 4.5031,
"step": 35
},
{
"epoch": 0.04825737265415549,
"grad_norm": 2.3673853874206543,
"learning_rate": 4.9713248879194776e-05,
"loss": 4.4335,
"step": 36
},
{
"epoch": 0.049597855227882036,
"grad_norm": 3.106703758239746,
"learning_rate": 4.969712969279372e-05,
"loss": 4.2437,
"step": 37
},
{
"epoch": 0.05093833780160858,
"grad_norm": 3.259270191192627,
"learning_rate": 4.9680572512624865e-05,
"loss": 4.1792,
"step": 38
},
{
"epoch": 0.05227882037533512,
"grad_norm": 2.3385283946990967,
"learning_rate": 4.9663577632323235e-05,
"loss": 4.4908,
"step": 39
},
{
"epoch": 0.05361930294906166,
"grad_norm": 1.8254426717758179,
"learning_rate": 4.964614535328626e-05,
"loss": 4.3529,
"step": 40
},
{
"epoch": 0.054959785522788206,
"grad_norm": 2.6058223247528076,
"learning_rate": 4.962827598466846e-05,
"loss": 4.4056,
"step": 41
},
{
"epoch": 0.05630026809651475,
"grad_norm": 2.2239863872528076,
"learning_rate": 4.960996984337599e-05,
"loss": 4.3295,
"step": 42
},
{
"epoch": 0.057640750670241284,
"grad_norm": 2.376335620880127,
"learning_rate": 4.959122725406098e-05,
"loss": 4.5717,
"step": 43
},
{
"epoch": 0.058981233243967826,
"grad_norm": 1.7582008838653564,
"learning_rate": 4.957204854911579e-05,
"loss": 4.1705,
"step": 44
},
{
"epoch": 0.06032171581769437,
"grad_norm": 3.278836250305176,
"learning_rate": 4.955243406866713e-05,
"loss": 4.5934,
"step": 45
},
{
"epoch": 0.06166219839142091,
"grad_norm": 3.2046706676483154,
"learning_rate": 4.953238416057e-05,
"loss": 4.3644,
"step": 46
},
{
"epoch": 0.06300268096514745,
"grad_norm": 2.464764356613159,
"learning_rate": 4.951189918040153e-05,
"loss": 4.4133,
"step": 47
},
{
"epoch": 0.064343163538874,
"grad_norm": 2.0737338066101074,
"learning_rate": 4.9490979491454716e-05,
"loss": 4.399,
"step": 48
},
{
"epoch": 0.06568364611260054,
"grad_norm": 1.9400380849838257,
"learning_rate": 4.94696254647319e-05,
"loss": 4.1675,
"step": 49
},
{
"epoch": 0.06702412868632708,
"grad_norm": 2.4042038917541504,
"learning_rate": 4.944783747893825e-05,
"loss": 4.4438,
"step": 50
},
{
"epoch": 0.06836461126005362,
"grad_norm": 2.0460598468780518,
"learning_rate": 4.942561592047503e-05,
"loss": 4.3132,
"step": 51
},
{
"epoch": 0.06970509383378017,
"grad_norm": 2.495248317718506,
"learning_rate": 4.940296118343274e-05,
"loss": 4.4234,
"step": 52
},
{
"epoch": 0.07104557640750671,
"grad_norm": 2.2051336765289307,
"learning_rate": 4.937987366958411e-05,
"loss": 4.1376,
"step": 53
},
{
"epoch": 0.07238605898123325,
"grad_norm": 2.5037894248962402,
"learning_rate": 4.935635378837703e-05,
"loss": 4.3765,
"step": 54
},
{
"epoch": 0.07372654155495978,
"grad_norm": 2.715787172317505,
"learning_rate": 4.9332401956927224e-05,
"loss": 4.7173,
"step": 55
},
{
"epoch": 0.07506702412868632,
"grad_norm": 1.9515987634658813,
"learning_rate": 4.9308018600010905e-05,
"loss": 4.3838,
"step": 56
},
{
"epoch": 0.07640750670241286,
"grad_norm": 3.664212703704834,
"learning_rate": 4.9283204150057186e-05,
"loss": 4.0593,
"step": 57
},
{
"epoch": 0.0777479892761394,
"grad_norm": 2.650737762451172,
"learning_rate": 4.9257959047140476e-05,
"loss": 4.2866,
"step": 58
},
{
"epoch": 0.07908847184986595,
"grad_norm": 1.847379446029663,
"learning_rate": 4.923228373897263e-05,
"loss": 4.4003,
"step": 59
},
{
"epoch": 0.08042895442359249,
"grad_norm": 2.86777925491333,
"learning_rate": 4.920617868089501e-05,
"loss": 4.0874,
"step": 60
},
{
"epoch": 0.08176943699731903,
"grad_norm": 1.791843295097351,
"learning_rate": 4.9179644335870444e-05,
"loss": 4.1438,
"step": 61
},
{
"epoch": 0.08310991957104558,
"grad_norm": 4.354154109954834,
"learning_rate": 4.915268117447498e-05,
"loss": 4.4184,
"step": 62
},
{
"epoch": 0.08445040214477212,
"grad_norm": 1.8598178625106812,
"learning_rate": 4.9125289674889566e-05,
"loss": 4.3217,
"step": 63
},
{
"epoch": 0.08579088471849866,
"grad_norm": 2.750469923019409,
"learning_rate": 4.909747032289153e-05,
"loss": 4.3744,
"step": 64
},
{
"epoch": 0.0871313672922252,
"grad_norm": 2.4330313205718994,
"learning_rate": 4.9069223611846014e-05,
"loss": 4.3427,
"step": 65
},
{
"epoch": 0.08847184986595175,
"grad_norm": 1.9383248090744019,
"learning_rate": 4.9040550042697206e-05,
"loss": 4.3464,
"step": 66
},
{
"epoch": 0.08981233243967829,
"grad_norm": 3.577594041824341,
"learning_rate": 4.901145012395945e-05,
"loss": 4.3135,
"step": 67
},
{
"epoch": 0.09115281501340483,
"grad_norm": 1.7440192699432373,
"learning_rate": 4.898192437170822e-05,
"loss": 4.5179,
"step": 68
},
{
"epoch": 0.09249329758713137,
"grad_norm": 2.0847866535186768,
"learning_rate": 4.895197330957097e-05,
"loss": 4.3644,
"step": 69
},
{
"epoch": 0.0938337801608579,
"grad_norm": 2.44808292388916,
"learning_rate": 4.8921597468717887e-05,
"loss": 4.0271,
"step": 70
},
{
"epoch": 0.09517426273458444,
"grad_norm": 1.4615987539291382,
"learning_rate": 4.889079738785242e-05,
"loss": 4.5157,
"step": 71
},
{
"epoch": 0.09651474530831099,
"grad_norm": 2.008985757827759,
"learning_rate": 4.8859573613201725e-05,
"loss": 4.1515,
"step": 72
},
{
"epoch": 0.09785522788203753,
"grad_norm": 2.1875059604644775,
"learning_rate": 4.882792669850705e-05,
"loss": 4.3656,
"step": 73
},
{
"epoch": 0.09919571045576407,
"grad_norm": 1.706811785697937,
"learning_rate": 4.879585720501383e-05,
"loss": 4.2608,
"step": 74
},
{
"epoch": 0.10053619302949061,
"grad_norm": 1.9756377935409546,
"learning_rate": 4.876336570146175e-05,
"loss": 4.3485,
"step": 75
},
{
"epoch": 0.10187667560321716,
"grad_norm": 2.3771932125091553,
"learning_rate": 4.8730452764074716e-05,
"loss": 4.7132,
"step": 76
},
{
"epoch": 0.1032171581769437,
"grad_norm": 1.7962132692337036,
"learning_rate": 4.8697118976550574e-05,
"loss": 4.371,
"step": 77
},
{
"epoch": 0.10455764075067024,
"grad_norm": 1.597954511642456,
"learning_rate": 4.866336493005078e-05,
"loss": 4.1567,
"step": 78
},
{
"epoch": 0.10589812332439678,
"grad_norm": 1.3557466268539429,
"learning_rate": 4.8629191223189916e-05,
"loss": 4.1133,
"step": 79
},
{
"epoch": 0.10723860589812333,
"grad_norm": 1.7042794227600098,
"learning_rate": 4.859459846202507e-05,
"loss": 4.5002,
"step": 80
},
{
"epoch": 0.10857908847184987,
"grad_norm": 1.6977810859680176,
"learning_rate": 4.8559587260045105e-05,
"loss": 4.3682,
"step": 81
},
{
"epoch": 0.10991957104557641,
"grad_norm": 1.827391505241394,
"learning_rate": 4.8524158238159756e-05,
"loss": 4.2495,
"step": 82
},
{
"epoch": 0.11126005361930295,
"grad_norm": 1.9541435241699219,
"learning_rate": 4.848831202468862e-05,
"loss": 4.4091,
"step": 83
},
{
"epoch": 0.1126005361930295,
"grad_norm": 2.02805233001709,
"learning_rate": 4.845204925535004e-05,
"loss": 4.4052,
"step": 84
},
{
"epoch": 0.11394101876675604,
"grad_norm": 1.873839259147644,
"learning_rate": 4.841537057324979e-05,
"loss": 4.3652,
"step": 85
},
{
"epoch": 0.11528150134048257,
"grad_norm": 1.5007935762405396,
"learning_rate": 4.837827662886971e-05,
"loss": 4.3055,
"step": 86
},
{
"epoch": 0.11662198391420911,
"grad_norm": 1.8006932735443115,
"learning_rate": 4.834076808005614e-05,
"loss": 4.2383,
"step": 87
},
{
"epoch": 0.11796246648793565,
"grad_norm": 1.4325038194656372,
"learning_rate": 4.830284559200828e-05,
"loss": 4.3694,
"step": 88
},
{
"epoch": 0.1193029490616622,
"grad_norm": 1.5972894430160522,
"learning_rate": 4.826450983726635e-05,
"loss": 4.4479,
"step": 89
},
{
"epoch": 0.12064343163538874,
"grad_norm": 1.7590267658233643,
"learning_rate": 4.82257614956997e-05,
"loss": 4.302,
"step": 90
},
{
"epoch": 0.12198391420911528,
"grad_norm": 1.8001571893692017,
"learning_rate": 4.818660125449477e-05,
"loss": 4.2703,
"step": 91
},
{
"epoch": 0.12332439678284182,
"grad_norm": 1.6677050590515137,
"learning_rate": 4.814702980814284e-05,
"loss": 4.351,
"step": 92
},
{
"epoch": 0.12466487935656836,
"grad_norm": 1.6096783876419067,
"learning_rate": 4.810704785842778e-05,
"loss": 4.2497,
"step": 93
},
{
"epoch": 0.1260053619302949,
"grad_norm": 2.0199062824249268,
"learning_rate": 4.806665611441354e-05,
"loss": 4.4206,
"step": 94
},
{
"epoch": 0.12734584450402145,
"grad_norm": 2.203843116760254,
"learning_rate": 4.802585529243164e-05,
"loss": 4.3003,
"step": 95
},
{
"epoch": 0.128686327077748,
"grad_norm": 2.0496983528137207,
"learning_rate": 4.7984646116068424e-05,
"loss": 4.4975,
"step": 96
},
{
"epoch": 0.13002680965147453,
"grad_norm": 1.7279603481292725,
"learning_rate": 4.794302931615223e-05,
"loss": 4.1659,
"step": 97
},
{
"epoch": 0.13136729222520108,
"grad_norm": 1.6434085369110107,
"learning_rate": 4.790100563074045e-05,
"loss": 4.3738,
"step": 98
},
{
"epoch": 0.13270777479892762,
"grad_norm": 2.495715856552124,
"learning_rate": 4.7858575805106423e-05,
"loss": 4.133,
"step": 99
},
{
"epoch": 0.13404825737265416,
"grad_norm": 1.7205560207366943,
"learning_rate": 4.781574059172621e-05,
"loss": 4.2405,
"step": 100
},
{
"epoch": 0.1353887399463807,
"grad_norm": 1.8256422281265259,
"learning_rate": 4.77725007502653e-05,
"loss": 4.4148,
"step": 101
},
{
"epoch": 0.13672922252010725,
"grad_norm": 1.5527430772781372,
"learning_rate": 4.772885704756506e-05,
"loss": 4.1488,
"step": 102
},
{
"epoch": 0.1380697050938338,
"grad_norm": 1.8024431467056274,
"learning_rate": 4.768481025762918e-05,
"loss": 4.3247,
"step": 103
},
{
"epoch": 0.13941018766756033,
"grad_norm": 1.5963706970214844,
"learning_rate": 4.7640361161609975e-05,
"loss": 4.3261,
"step": 104
},
{
"epoch": 0.14075067024128687,
"grad_norm": 1.5833405256271362,
"learning_rate": 4.7595510547794465e-05,
"loss": 4.2407,
"step": 105
},
{
"epoch": 0.14209115281501342,
"grad_norm": 1.635737419128418,
"learning_rate": 4.755025921159044e-05,
"loss": 4.2942,
"step": 106
},
{
"epoch": 0.14343163538873996,
"grad_norm": 2.2439887523651123,
"learning_rate": 4.750460795551235e-05,
"loss": 4.329,
"step": 107
},
{
"epoch": 0.1447721179624665,
"grad_norm": 1.521741271018982,
"learning_rate": 4.7458557589167044e-05,
"loss": 4.2611,
"step": 108
},
{
"epoch": 0.14611260053619302,
"grad_norm": 1.5195074081420898,
"learning_rate": 4.7412108929239455e-05,
"loss": 4.1535,
"step": 109
},
{
"epoch": 0.14745308310991956,
"grad_norm": 1.7524590492248535,
"learning_rate": 4.736526279947807e-05,
"loss": 4.1324,
"step": 110
},
{
"epoch": 0.1487935656836461,
"grad_norm": 1.5709757804870605,
"learning_rate": 4.731802003068038e-05,
"loss": 4.3759,
"step": 111
},
{
"epoch": 0.15013404825737264,
"grad_norm": 2.3734326362609863,
"learning_rate": 4.727038146067807e-05,
"loss": 4.0612,
"step": 112
},
{
"epoch": 0.15147453083109919,
"grad_norm": 1.7686563730239868,
"learning_rate": 4.722234793432224e-05,
"loss": 4.2815,
"step": 113
},
{
"epoch": 0.15281501340482573,
"grad_norm": 2.2321314811706543,
"learning_rate": 4.717392030346836e-05,
"loss": 4.2936,
"step": 114
},
{
"epoch": 0.15415549597855227,
"grad_norm": 1.6879431009292603,
"learning_rate": 4.7125099426961185e-05,
"loss": 4.3934,
"step": 115
},
{
"epoch": 0.1554959785522788,
"grad_norm": 1.6961618661880493,
"learning_rate": 4.7075886170619543e-05,
"loss": 4.322,
"step": 116
},
{
"epoch": 0.15683646112600536,
"grad_norm": 1.763327717781067,
"learning_rate": 4.702628140722096e-05,
"loss": 4.1915,
"step": 117
},
{
"epoch": 0.1581769436997319,
"grad_norm": 9.971641540527344,
"learning_rate": 4.697628601648616e-05,
"loss": 4.408,
"step": 118
},
{
"epoch": 0.15951742627345844,
"grad_norm": 1.5898083448410034,
"learning_rate": 4.692590088506351e-05,
"loss": 4.3775,
"step": 119
},
{
"epoch": 0.16085790884718498,
"grad_norm": 1.706078290939331,
"learning_rate": 4.687512690651328e-05,
"loss": 4.3802,
"step": 120
},
{
"epoch": 0.16219839142091153,
"grad_norm": 2.41762113571167,
"learning_rate": 4.6823964981291755e-05,
"loss": 4.2379,
"step": 121
},
{
"epoch": 0.16353887399463807,
"grad_norm": 1.5153508186340332,
"learning_rate": 4.677241601673533e-05,
"loss": 4.4031,
"step": 122
},
{
"epoch": 0.1648793565683646,
"grad_norm": 1.601252555847168,
"learning_rate": 4.672048092704438e-05,
"loss": 4.5279,
"step": 123
},
{
"epoch": 0.16621983914209115,
"grad_norm": 3.5004804134368896,
"learning_rate": 4.666816063326706e-05,
"loss": 4.3672,
"step": 124
},
{
"epoch": 0.1675603217158177,
"grad_norm": 1.838731050491333,
"learning_rate": 4.6615456063282944e-05,
"loss": 4.4294,
"step": 125
},
{
"epoch": 0.16890080428954424,
"grad_norm": 1.8564834594726562,
"learning_rate": 4.656236815178663e-05,
"loss": 4.1836,
"step": 126
},
{
"epoch": 0.17024128686327078,
"grad_norm": 1.6874207258224487,
"learning_rate": 4.6508897840271086e-05,
"loss": 4.2818,
"step": 127
},
{
"epoch": 0.17158176943699732,
"grad_norm": 2.0717060565948486,
"learning_rate": 4.645504607701102e-05,
"loss": 4.4053,
"step": 128
},
{
"epoch": 0.17292225201072386,
"grad_norm": 1.5888526439666748,
"learning_rate": 4.640081381704603e-05,
"loss": 4.0819,
"step": 129
},
{
"epoch": 0.1742627345844504,
"grad_norm": 1.6559789180755615,
"learning_rate": 4.634620202216366e-05,
"loss": 4.2886,
"step": 130
},
{
"epoch": 0.17560321715817695,
"grad_norm": 1.318756341934204,
"learning_rate": 4.629121166088236e-05,
"loss": 4.4066,
"step": 131
},
{
"epoch": 0.1769436997319035,
"grad_norm": 1.5231109857559204,
"learning_rate": 4.6235843708434315e-05,
"loss": 4.1626,
"step": 132
},
{
"epoch": 0.17828418230563003,
"grad_norm": 2.5188205242156982,
"learning_rate": 4.618009914674811e-05,
"loss": 4.0126,
"step": 133
},
{
"epoch": 0.17962466487935658,
"grad_norm": 1.5713856220245361,
"learning_rate": 4.612397896443138e-05,
"loss": 4.4837,
"step": 134
},
{
"epoch": 0.18096514745308312,
"grad_norm": 1.650790810585022,
"learning_rate": 4.6067484156753234e-05,
"loss": 4.6447,
"step": 135
},
{
"epoch": 0.18230563002680966,
"grad_norm": 1.526718258857727,
"learning_rate": 4.6010615725626594e-05,
"loss": 4.3942,
"step": 136
},
{
"epoch": 0.1836461126005362,
"grad_norm": 1.750684380531311,
"learning_rate": 4.595337467959045e-05,
"loss": 4.2953,
"step": 137
},
{
"epoch": 0.18498659517426275,
"grad_norm": 1.5442519187927246,
"learning_rate": 4.5895762033792e-05,
"loss": 4.2861,
"step": 138
},
{
"epoch": 0.1863270777479893,
"grad_norm": 2.508603096008301,
"learning_rate": 4.583777880996858e-05,
"loss": 4.0075,
"step": 139
},
{
"epoch": 0.1876675603217158,
"grad_norm": 2.661263942718506,
"learning_rate": 4.577942603642959e-05,
"loss": 4.1049,
"step": 140
},
{
"epoch": 0.18900804289544235,
"grad_norm": 1.8339372873306274,
"learning_rate": 4.572070474803825e-05,
"loss": 4.3574,
"step": 141
},
{
"epoch": 0.1903485254691689,
"grad_norm": 1.620552659034729,
"learning_rate": 4.566161598619325e-05,
"loss": 4.3972,
"step": 142
},
{
"epoch": 0.19168900804289543,
"grad_norm": 1.8532575368881226,
"learning_rate": 4.5602160798810256e-05,
"loss": 4.2641,
"step": 143
},
{
"epoch": 0.19302949061662197,
"grad_norm": 1.7382028102874756,
"learning_rate": 4.554234024030337e-05,
"loss": 4.5016,
"step": 144
},
{
"epoch": 0.19436997319034852,
"grad_norm": 2.024874448776245,
"learning_rate": 4.5482155371566384e-05,
"loss": 4.3223,
"step": 145
},
{
"epoch": 0.19571045576407506,
"grad_norm": 1.7250862121582031,
"learning_rate": 4.5421607259954017e-05,
"loss": 4.3304,
"step": 146
},
{
"epoch": 0.1970509383378016,
"grad_norm": 2.2707390785217285,
"learning_rate": 4.5360696979262905e-05,
"loss": 4.2743,
"step": 147
},
{
"epoch": 0.19839142091152814,
"grad_norm": 1.3240299224853516,
"learning_rate": 4.529942560971266e-05,
"loss": 4.1492,
"step": 148
},
{
"epoch": 0.19973190348525469,
"grad_norm": 1.6945743560791016,
"learning_rate": 4.523779423792665e-05,
"loss": 4.347,
"step": 149
},
{
"epoch": 0.20107238605898123,
"grad_norm": 1.5952167510986328,
"learning_rate": 4.51758039569127e-05,
"loss": 4.1712,
"step": 150
},
{
"epoch": 0.20241286863270777,
"grad_norm": 1.9782387018203735,
"learning_rate": 4.51134558660438e-05,
"loss": 4.2414,
"step": 151
},
{
"epoch": 0.2037533512064343,
"grad_norm": 1.838925838470459,
"learning_rate": 4.505075107103852e-05,
"loss": 4.2947,
"step": 152
},
{
"epoch": 0.20509383378016086,
"grad_norm": 1.7607638835906982,
"learning_rate": 4.498769068394145e-05,
"loss": 4.0831,
"step": 153
},
{
"epoch": 0.2064343163538874,
"grad_norm": 1.8876625299453735,
"learning_rate": 4.4924275823103465e-05,
"loss": 4.2192,
"step": 154
},
{
"epoch": 0.20777479892761394,
"grad_norm": 1.637762188911438,
"learning_rate": 4.48605076131619e-05,
"loss": 4.4715,
"step": 155
},
{
"epoch": 0.20911528150134048,
"grad_norm": 2.7469165325164795,
"learning_rate": 4.4796387185020566e-05,
"loss": 4.1303,
"step": 156
},
{
"epoch": 0.21045576407506703,
"grad_norm": 1.4918110370635986,
"learning_rate": 4.473191567582975e-05,
"loss": 4.4115,
"step": 157
},
{
"epoch": 0.21179624664879357,
"grad_norm": 1.77053964138031,
"learning_rate": 4.466709422896601e-05,
"loss": 4.2949,
"step": 158
},
{
"epoch": 0.2131367292225201,
"grad_norm": 1.3985557556152344,
"learning_rate": 4.460192399401192e-05,
"loss": 4.4337,
"step": 159
},
{
"epoch": 0.21447721179624665,
"grad_norm": 1.6528301239013672,
"learning_rate": 4.4536406126735664e-05,
"loss": 3.9079,
"step": 160
},
{
"epoch": 0.2158176943699732,
"grad_norm": 2.1471214294433594,
"learning_rate": 4.4470541789070536e-05,
"loss": 4.3985,
"step": 161
},
{
"epoch": 0.21715817694369974,
"grad_norm": 1.532997727394104,
"learning_rate": 4.4404332149094365e-05,
"loss": 4.4077,
"step": 162
},
{
"epoch": 0.21849865951742628,
"grad_norm": 1.709489345550537,
"learning_rate": 4.433777838100876e-05,
"loss": 4.1316,
"step": 163
},
{
"epoch": 0.21983914209115282,
"grad_norm": 1.771577000617981,
"learning_rate": 4.427088166511835e-05,
"loss": 4.2523,
"step": 164
},
{
"epoch": 0.22117962466487937,
"grad_norm": 1.3879780769348145,
"learning_rate": 4.420364318780973e-05,
"loss": 4.3171,
"step": 165
},
{
"epoch": 0.2225201072386059,
"grad_norm": 1.483606219291687,
"learning_rate": 4.413606414153055e-05,
"loss": 4.2561,
"step": 166
},
{
"epoch": 0.22386058981233245,
"grad_norm": 1.595353364944458,
"learning_rate": 4.4068145724768324e-05,
"loss": 4.3484,
"step": 167
},
{
"epoch": 0.225201072386059,
"grad_norm": 1.7268496751785278,
"learning_rate": 4.399988914202913e-05,
"loss": 4.5508,
"step": 168
},
{
"epoch": 0.22654155495978553,
"grad_norm": 2.074028253555298,
"learning_rate": 4.393129560381632e-05,
"loss": 4.3195,
"step": 169
},
{
"epoch": 0.22788203753351208,
"grad_norm": 1.8451873064041138,
"learning_rate": 4.3862366326608975e-05,
"loss": 4.2486,
"step": 170
},
{
"epoch": 0.2292225201072386,
"grad_norm": 1.6457356214523315,
"learning_rate": 4.379310253284041e-05,
"loss": 3.967,
"step": 171
},
{
"epoch": 0.23056300268096513,
"grad_norm": 2.2118191719055176,
"learning_rate": 4.3723505450876454e-05,
"loss": 4.2569,
"step": 172
},
{
"epoch": 0.23190348525469168,
"grad_norm": 1.9560130834579468,
"learning_rate": 4.365357631499366e-05,
"loss": 4.2011,
"step": 173
},
{
"epoch": 0.23324396782841822,
"grad_norm": 1.492055892944336,
"learning_rate": 4.358331636535742e-05,
"loss": 4.2366,
"step": 174
},
{
"epoch": 0.23458445040214476,
"grad_norm": 1.7142921686172485,
"learning_rate": 4.3512726847999987e-05,
"loss": 4.0431,
"step": 175
},
{
"epoch": 0.2359249329758713,
"grad_norm": 1.3217313289642334,
"learning_rate": 4.344180901479836e-05,
"loss": 4.347,
"step": 176
},
{
"epoch": 0.23726541554959785,
"grad_norm": 1.899259328842163,
"learning_rate": 4.3370564123452094e-05,
"loss": 4.0226,
"step": 177
},
{
"epoch": 0.2386058981233244,
"grad_norm": 1.5178223848342896,
"learning_rate": 4.329899343746099e-05,
"loss": 4.0522,
"step": 178
},
{
"epoch": 0.23994638069705093,
"grad_norm": 1.474506139755249,
"learning_rate": 4.3227098226102685e-05,
"loss": 4.3556,
"step": 179
},
{
"epoch": 0.24128686327077747,
"grad_norm": 1.5425620079040527,
"learning_rate": 4.315487976441014e-05,
"loss": 4.3349,
"step": 180
},
{
"epoch": 0.24262734584450402,
"grad_norm": 1.785186529159546,
"learning_rate": 4.308233933314904e-05,
"loss": 4.3767,
"step": 181
},
{
"epoch": 0.24396782841823056,
"grad_norm": 1.6833457946777344,
"learning_rate": 4.300947821879507e-05,
"loss": 4.3415,
"step": 182
},
{
"epoch": 0.2453083109919571,
"grad_norm": 1.6081000566482544,
"learning_rate": 4.29362977135111e-05,
"loss": 4.3398,
"step": 183
},
{
"epoch": 0.24664879356568364,
"grad_norm": 1.5955443382263184,
"learning_rate": 4.286279911512426e-05,
"loss": 4.1918,
"step": 184
},
{
"epoch": 0.2479892761394102,
"grad_norm": 2.135406970977783,
"learning_rate": 4.278898372710296e-05,
"loss": 3.9686,
"step": 185
},
{
"epoch": 0.24932975871313673,
"grad_norm": 1.5492300987243652,
"learning_rate": 4.271485285853374e-05,
"loss": 4.1644,
"step": 186
},
{
"epoch": 0.25067024128686327,
"grad_norm": 1.4507619142532349,
"learning_rate": 4.264040782409804e-05,
"loss": 4.5032,
"step": 187
},
{
"epoch": 0.2520107238605898,
"grad_norm": 1.7045412063598633,
"learning_rate": 4.256564994404893e-05,
"loss": 4.3946,
"step": 188
},
{
"epoch": 0.25335120643431636,
"grad_norm": 1.4163429737091064,
"learning_rate": 4.249058054418766e-05,
"loss": 4.1216,
"step": 189
},
{
"epoch": 0.2546916890080429,
"grad_norm": 1.946765661239624,
"learning_rate": 4.2415200955840184e-05,
"loss": 4.1634,
"step": 190
},
{
"epoch": 0.25603217158176944,
"grad_norm": 1.6845455169677734,
"learning_rate": 4.233951251583349e-05,
"loss": 4.1091,
"step": 191
},
{
"epoch": 0.257372654155496,
"grad_norm": 1.8467648029327393,
"learning_rate": 4.226351656647194e-05,
"loss": 4.5806,
"step": 192
},
{
"epoch": 0.2587131367292225,
"grad_norm": 1.9924100637435913,
"learning_rate": 4.218721445551348e-05,
"loss": 4.0176,
"step": 193
},
{
"epoch": 0.26005361930294907,
"grad_norm": 1.6211397647857666,
"learning_rate": 4.2110607536145654e-05,
"loss": 4.2865,
"step": 194
},
{
"epoch": 0.2613941018766756,
"grad_norm": 1.843051791191101,
"learning_rate": 4.2033697166961716e-05,
"loss": 4.2915,
"step": 195
},
{
"epoch": 0.26273458445040215,
"grad_norm": 1.7140624523162842,
"learning_rate": 4.1956484711936464e-05,
"loss": 4.0178,
"step": 196
},
{
"epoch": 0.2640750670241287,
"grad_norm": 1.618522047996521,
"learning_rate": 4.1878971540402044e-05,
"loss": 4.2507,
"step": 197
},
{
"epoch": 0.26541554959785524,
"grad_norm": 1.6312532424926758,
"learning_rate": 4.180115902702372e-05,
"loss": 4.5598,
"step": 198
},
{
"epoch": 0.2667560321715818,
"grad_norm": 1.7146576642990112,
"learning_rate": 4.1723048551775454e-05,
"loss": 4.3715,
"step": 199
},
{
"epoch": 0.2680965147453083,
"grad_norm": 1.303650975227356,
"learning_rate": 4.1644641499915454e-05,
"loss": 4.1698,
"step": 200
},
{
"epoch": 0.26943699731903487,
"grad_norm": 2.1732089519500732,
"learning_rate": 4.156593926196157e-05,
"loss": 4.0639,
"step": 201
},
{
"epoch": 0.2707774798927614,
"grad_norm": 1.6341739892959595,
"learning_rate": 4.148694323366668e-05,
"loss": 4.3151,
"step": 202
},
{
"epoch": 0.27211796246648795,
"grad_norm": 1.5698548555374146,
"learning_rate": 4.140765481599391e-05,
"loss": 4.2357,
"step": 203
},
{
"epoch": 0.2734584450402145,
"grad_norm": 1.790808081626892,
"learning_rate": 4.13280754150918e-05,
"loss": 4.1957,
"step": 204
},
{
"epoch": 0.27479892761394104,
"grad_norm": 1.5973646640777588,
"learning_rate": 4.124820644226936e-05,
"loss": 4.2999,
"step": 205
},
{
"epoch": 0.2761394101876676,
"grad_norm": 1.9699524641036987,
"learning_rate": 4.116804931397105e-05,
"loss": 4.3858,
"step": 206
},
{
"epoch": 0.2774798927613941,
"grad_norm": 1.3920892477035522,
"learning_rate": 4.108760545175163e-05,
"loss": 4.3195,
"step": 207
},
{
"epoch": 0.27882037533512066,
"grad_norm": 1.7220263481140137,
"learning_rate": 4.100687628225099e-05,
"loss": 4.038,
"step": 208
},
{
"epoch": 0.2801608579088472,
"grad_norm": 1.54973304271698,
"learning_rate": 4.092586323716883e-05,
"loss": 4.2801,
"step": 209
},
{
"epoch": 0.28150134048257375,
"grad_norm": 1.623826026916504,
"learning_rate": 4.0844567753239276e-05,
"loss": 4.2336,
"step": 210
},
{
"epoch": 0.2828418230563003,
"grad_norm": 1.3568044900894165,
"learning_rate": 4.076299127220538e-05,
"loss": 4.4482,
"step": 211
},
{
"epoch": 0.28418230563002683,
"grad_norm": 1.5761674642562866,
"learning_rate": 4.068113524079358e-05,
"loss": 4.5305,
"step": 212
},
{
"epoch": 0.2855227882037534,
"grad_norm": 1.4738843441009521,
"learning_rate": 4.0599001110688e-05,
"loss": 3.9993,
"step": 213
},
{
"epoch": 0.2868632707774799,
"grad_norm": 2.239969253540039,
"learning_rate": 4.051659033850478e-05,
"loss": 4.0927,
"step": 214
},
{
"epoch": 0.28820375335120646,
"grad_norm": 1.611913800239563,
"learning_rate": 4.043390438576616e-05,
"loss": 4.5465,
"step": 215
},
{
"epoch": 0.289544235924933,
"grad_norm": 1.6325899362564087,
"learning_rate": 4.0350944718874606e-05,
"loss": 4.4422,
"step": 216
},
{
"epoch": 0.29088471849865954,
"grad_norm": 1.7556217908859253,
"learning_rate": 4.026771280908681e-05,
"loss": 3.9823,
"step": 217
},
{
"epoch": 0.29222520107238603,
"grad_norm": 1.6510450839996338,
"learning_rate": 4.0184210132487576e-05,
"loss": 3.9193,
"step": 218
},
{
"epoch": 0.2935656836461126,
"grad_norm": 2.267282009124756,
"learning_rate": 4.0100438169963636e-05,
"loss": 4.0549,
"step": 219
},
{
"epoch": 0.2949061662198391,
"grad_norm": 1.6804044246673584,
"learning_rate": 4.001639840717741e-05,
"loss": 4.3879,
"step": 220
},
{
"epoch": 0.29624664879356566,
"grad_norm": 1.3055918216705322,
"learning_rate": 3.993209233454066e-05,
"loss": 4.3085,
"step": 221
},
{
"epoch": 0.2975871313672922,
"grad_norm": 1.4905943870544434,
"learning_rate": 3.9847521447188034e-05,
"loss": 4.4018,
"step": 222
},
{
"epoch": 0.29892761394101874,
"grad_norm": 1.7155883312225342,
"learning_rate": 3.976268724495057e-05,
"loss": 4.2343,
"step": 223
},
{
"epoch": 0.3002680965147453,
"grad_norm": 2.746023416519165,
"learning_rate": 3.967759123232908e-05,
"loss": 4.2406,
"step": 224
},
{
"epoch": 0.30160857908847183,
"grad_norm": 1.6308192014694214,
"learning_rate": 3.959223491846749e-05,
"loss": 4.2082,
"step": 225
},
{
"epoch": 0.30294906166219837,
"grad_norm": 2.0225327014923096,
"learning_rate": 3.950661981712606e-05,
"loss": 4.2411,
"step": 226
},
{
"epoch": 0.3042895442359249,
"grad_norm": 1.790639877319336,
"learning_rate": 3.9420747446654556e-05,
"loss": 4.1923,
"step": 227
},
{
"epoch": 0.30563002680965146,
"grad_norm": 1.459539532661438,
"learning_rate": 3.933461932996528e-05,
"loss": 4.2988,
"step": 228
},
{
"epoch": 0.306970509383378,
"grad_norm": 1.9452991485595703,
"learning_rate": 3.924823699450614e-05,
"loss": 4.1299,
"step": 229
},
{
"epoch": 0.30831099195710454,
"grad_norm": 1.9040483236312866,
"learning_rate": 3.916160197223344e-05,
"loss": 4.1229,
"step": 230
},
{
"epoch": 0.3096514745308311,
"grad_norm": 2.81461763381958,
"learning_rate": 3.9074715799584874e-05,
"loss": 4.1425,
"step": 231
},
{
"epoch": 0.3109919571045576,
"grad_norm": 1.4306813478469849,
"learning_rate": 3.89875800174521e-05,
"loss": 4.1418,
"step": 232
},
{
"epoch": 0.31233243967828417,
"grad_norm": 1.4787055253982544,
"learning_rate": 3.890019617115357e-05,
"loss": 4.2288,
"step": 233
},
{
"epoch": 0.3136729222520107,
"grad_norm": 2.2095518112182617,
"learning_rate": 3.881256581040701e-05,
"loss": 4.4499,
"step": 234
},
{
"epoch": 0.31501340482573725,
"grad_norm": 1.8035799264907837,
"learning_rate": 3.8724690489302004e-05,
"loss": 4.3237,
"step": 235
},
{
"epoch": 0.3163538873994638,
"grad_norm": 1.730271816253662,
"learning_rate": 3.8636571766272404e-05,
"loss": 4.3262,
"step": 236
},
{
"epoch": 0.31769436997319034,
"grad_norm": 1.5243645906448364,
"learning_rate": 3.8548211204068704e-05,
"loss": 4.2728,
"step": 237
},
{
"epoch": 0.3190348525469169,
"grad_norm": 1.7042049169540405,
"learning_rate": 3.8459610369730316e-05,
"loss": 4.1133,
"step": 238
},
{
"epoch": 0.3203753351206434,
"grad_norm": 1.6111284494400024,
"learning_rate": 3.8370770834557765e-05,
"loss": 4.1065,
"step": 239
},
{
"epoch": 0.32171581769436997,
"grad_norm": 1.9032849073410034,
"learning_rate": 3.828169417408488e-05,
"loss": 4.5417,
"step": 240
},
{
"epoch": 0.3230563002680965,
"grad_norm": 1.5171478986740112,
"learning_rate": 3.819238196805077e-05,
"loss": 4.1116,
"step": 241
},
{
"epoch": 0.32439678284182305,
"grad_norm": 2.0508604049682617,
"learning_rate": 3.810283580037188e-05,
"loss": 4.4837,
"step": 242
},
{
"epoch": 0.3257372654155496,
"grad_norm": 1.5974640846252441,
"learning_rate": 3.801305725911387e-05,
"loss": 4.1371,
"step": 243
},
{
"epoch": 0.32707774798927614,
"grad_norm": 1.529778242111206,
"learning_rate": 3.792304793646343e-05,
"loss": 4.3942,
"step": 244
},
{
"epoch": 0.3284182305630027,
"grad_norm": 1.8285270929336548,
"learning_rate": 3.78328094287001e-05,
"loss": 4.0091,
"step": 245
},
{
"epoch": 0.3297587131367292,
"grad_norm": 2.31738543510437,
"learning_rate": 3.774234333616788e-05,
"loss": 4.0133,
"step": 246
},
{
"epoch": 0.33109919571045576,
"grad_norm": 1.7283586263656616,
"learning_rate": 3.765165126324695e-05,
"loss": 4.483,
"step": 247
},
{
"epoch": 0.3324396782841823,
"grad_norm": 2.2344255447387695,
"learning_rate": 3.756073481832512e-05,
"loss": 4.253,
"step": 248
},
{
"epoch": 0.33378016085790885,
"grad_norm": 2.0832972526550293,
"learning_rate": 3.746959561376937e-05,
"loss": 4.0796,
"step": 249
},
{
"epoch": 0.3351206434316354,
"grad_norm": 1.4113162755966187,
"learning_rate": 3.737823526589722e-05,
"loss": 4.3089,
"step": 250
},
{
"epoch": 0.33646112600536193,
"grad_norm": 1.932127594947815,
"learning_rate": 3.728665539494809e-05,
"loss": 4.0903,
"step": 251
},
{
"epoch": 0.3378016085790885,
"grad_norm": 1.6619492769241333,
"learning_rate": 3.719485762505457e-05,
"loss": 4.2508,
"step": 252
},
{
"epoch": 0.339142091152815,
"grad_norm": 2.39372181892395,
"learning_rate": 3.7102843584213556e-05,
"loss": 4.4867,
"step": 253
},
{
"epoch": 0.34048257372654156,
"grad_norm": 1.6463251113891602,
"learning_rate": 3.701061490425745e-05,
"loss": 4.1576,
"step": 254
},
{
"epoch": 0.3418230563002681,
"grad_norm": 1.641948938369751,
"learning_rate": 3.6918173220825204e-05,
"loss": 4.2981,
"step": 255
},
{
"epoch": 0.34316353887399464,
"grad_norm": 1.940873384475708,
"learning_rate": 3.682552017333328e-05,
"loss": 4.0453,
"step": 256
},
{
"epoch": 0.3445040214477212,
"grad_norm": 1.4857423305511475,
"learning_rate": 3.673265740494662e-05,
"loss": 4.3173,
"step": 257
},
{
"epoch": 0.34584450402144773,
"grad_norm": 1.6838629245758057,
"learning_rate": 3.663958656254947e-05,
"loss": 4.2694,
"step": 258
},
{
"epoch": 0.34718498659517427,
"grad_norm": 1.514359712600708,
"learning_rate": 3.654630929671616e-05,
"loss": 4.1445,
"step": 259
},
{
"epoch": 0.3485254691689008,
"grad_norm": 1.842326283454895,
"learning_rate": 3.645282726168191e-05,
"loss": 4.2037,
"step": 260
},
{
"epoch": 0.34986595174262736,
"grad_norm": 2.151712656021118,
"learning_rate": 3.63591421153134e-05,
"loss": 4.131,
"step": 261
},
{
"epoch": 0.3512064343163539,
"grad_norm": 1.5983384847640991,
"learning_rate": 3.626525551907943e-05,
"loss": 4.1629,
"step": 262
},
{
"epoch": 0.35254691689008044,
"grad_norm": 1.7316803932189941,
"learning_rate": 3.617116913802143e-05,
"loss": 4.368,
"step": 263
},
{
"epoch": 0.353887399463807,
"grad_norm": 1.8699780702590942,
"learning_rate": 3.6076884640723914e-05,
"loss": 4.1434,
"step": 264
},
{
"epoch": 0.3552278820375335,
"grad_norm": 1.6108945608139038,
"learning_rate": 3.598240369928494e-05,
"loss": 4.3329,
"step": 265
},
{
"epoch": 0.35656836461126007,
"grad_norm": 1.8125485181808472,
"learning_rate": 3.58877279892864e-05,
"loss": 4.2709,
"step": 266
},
{
"epoch": 0.3579088471849866,
"grad_norm": 1.8078837394714355,
"learning_rate": 3.579285918976433e-05,
"loss": 4.1348,
"step": 267
},
{
"epoch": 0.35924932975871315,
"grad_norm": 1.5984883308410645,
"learning_rate": 3.5697798983179165e-05,
"loss": 4.2623,
"step": 268
},
{
"epoch": 0.3605898123324397,
"grad_norm": 1.7439504861831665,
"learning_rate": 3.560254905538582e-05,
"loss": 4.014,
"step": 269
},
{
"epoch": 0.36193029490616624,
"grad_norm": 1.5043836832046509,
"learning_rate": 3.5507111095603864e-05,
"loss": 4.4548,
"step": 270
},
{
"epoch": 0.3632707774798928,
"grad_norm": 1.7845739126205444,
"learning_rate": 3.541148679638756e-05,
"loss": 4.0811,
"step": 271
},
{
"epoch": 0.3646112600536193,
"grad_norm": 1.594000220298767,
"learning_rate": 3.531567785359579e-05,
"loss": 4.0656,
"step": 272
},
{
"epoch": 0.36595174262734587,
"grad_norm": 1.3641453981399536,
"learning_rate": 3.5219685966362024e-05,
"loss": 4.1347,
"step": 273
},
{
"epoch": 0.3672922252010724,
"grad_norm": 2.123870372772217,
"learning_rate": 3.512351283706419e-05,
"loss": 4.0572,
"step": 274
},
{
"epoch": 0.36863270777479895,
"grad_norm": 1.5682214498519897,
"learning_rate": 3.5027160171294476e-05,
"loss": 3.9792,
"step": 275
},
{
"epoch": 0.3699731903485255,
"grad_norm": 1.7921156883239746,
"learning_rate": 3.493062967782906e-05,
"loss": 4.2667,
"step": 276
},
{
"epoch": 0.37131367292225204,
"grad_norm": 1.289312720298767,
"learning_rate": 3.483392306859784e-05,
"loss": 4.2908,
"step": 277
},
{
"epoch": 0.3726541554959786,
"grad_norm": 1.6255465745925903,
"learning_rate": 3.473704205865405e-05,
"loss": 4.3037,
"step": 278
},
{
"epoch": 0.3739946380697051,
"grad_norm": 5.407750606536865,
"learning_rate": 3.463998836614383e-05,
"loss": 3.9892,
"step": 279
},
{
"epoch": 0.3753351206434316,
"grad_norm": 1.6176046133041382,
"learning_rate": 3.4542763712275836e-05,
"loss": 4.1985,
"step": 280
},
{
"epoch": 0.37667560321715815,
"grad_norm": 1.957220196723938,
"learning_rate": 3.444536982129058e-05,
"loss": 4.2234,
"step": 281
},
{
"epoch": 0.3780160857908847,
"grad_norm": 1.6883248090744019,
"learning_rate": 3.4347808420429986e-05,
"loss": 4.3222,
"step": 282
},
{
"epoch": 0.37935656836461124,
"grad_norm": 2.0616700649261475,
"learning_rate": 3.4250081239906674e-05,
"loss": 4.186,
"step": 283
},
{
"epoch": 0.3806970509383378,
"grad_norm": 1.6081446409225464,
"learning_rate": 3.4152190012873296e-05,
"loss": 3.941,
"step": 284
},
{
"epoch": 0.3820375335120643,
"grad_norm": 2.2144858837127686,
"learning_rate": 3.405413647539182e-05,
"loss": 3.8544,
"step": 285
},
{
"epoch": 0.38337801608579086,
"grad_norm": 2.4649174213409424,
"learning_rate": 3.395592236640271e-05,
"loss": 4.2041,
"step": 286
},
{
"epoch": 0.3847184986595174,
"grad_norm": 2.011274814605713,
"learning_rate": 3.3857549427694114e-05,
"loss": 4.1236,
"step": 287
},
{
"epoch": 0.38605898123324395,
"grad_norm": 1.6481976509094238,
"learning_rate": 3.375901940387096e-05,
"loss": 4.2079,
"step": 288
},
{
"epoch": 0.3873994638069705,
"grad_norm": 2.9300923347473145,
"learning_rate": 3.3660334042324e-05,
"loss": 4.1188,
"step": 289
},
{
"epoch": 0.38873994638069703,
"grad_norm": 1.484844446182251,
"learning_rate": 3.356149509319886e-05,
"loss": 4.1278,
"step": 290
},
{
"epoch": 0.3900804289544236,
"grad_norm": 2.7519867420196533,
"learning_rate": 3.346250430936498e-05,
"loss": 4.0015,
"step": 291
},
{
"epoch": 0.3914209115281501,
"grad_norm": 1.782799243927002,
"learning_rate": 3.336336344638451e-05,
"loss": 4.092,
"step": 292
},
{
"epoch": 0.39276139410187666,
"grad_norm": 1.6486201286315918,
"learning_rate": 3.326407426248121e-05,
"loss": 4.144,
"step": 293
},
{
"epoch": 0.3941018766756032,
"grad_norm": 1.4300029277801514,
"learning_rate": 3.316463851850925e-05,
"loss": 4.3014,
"step": 294
},
{
"epoch": 0.39544235924932974,
"grad_norm": 1.3786250352859497,
"learning_rate": 3.3065057977921986e-05,
"loss": 4.0207,
"step": 295
},
{
"epoch": 0.3967828418230563,
"grad_norm": 2.008800745010376,
"learning_rate": 3.296533440674067e-05,
"loss": 4.0964,
"step": 296
},
{
"epoch": 0.39812332439678283,
"grad_norm": 1.933161735534668,
"learning_rate": 3.2865469573523163e-05,
"loss": 4.0538,
"step": 297
},
{
"epoch": 0.39946380697050937,
"grad_norm": 1.932469367980957,
"learning_rate": 3.2765465249332545e-05,
"loss": 4.4318,
"step": 298
},
{
"epoch": 0.4008042895442359,
"grad_norm": 1.565575122833252,
"learning_rate": 3.266532320770571e-05,
"loss": 3.9859,
"step": 299
},
{
"epoch": 0.40214477211796246,
"grad_norm": 1.6429823637008667,
"learning_rate": 3.2565045224621923e-05,
"loss": 4.0066,
"step": 300
},
{
"epoch": 0.403485254691689,
"grad_norm": 1.5932061672210693,
"learning_rate": 3.2464633078471305e-05,
"loss": 4.1402,
"step": 301
},
{
"epoch": 0.40482573726541554,
"grad_norm": 1.3744337558746338,
"learning_rate": 3.236408855002332e-05,
"loss": 4.119,
"step": 302
},
{
"epoch": 0.4061662198391421,
"grad_norm": 1.62874174118042,
"learning_rate": 3.226341342239516e-05,
"loss": 4.0802,
"step": 303
},
{
"epoch": 0.4075067024128686,
"grad_norm": 1.5629057884216309,
"learning_rate": 3.216260948102017e-05,
"loss": 4.2826,
"step": 304
},
{
"epoch": 0.40884718498659517,
"grad_norm": 1.5869566202163696,
"learning_rate": 3.2061678513616125e-05,
"loss": 4.2169,
"step": 305
},
{
"epoch": 0.4101876675603217,
"grad_norm": 1.4807497262954712,
"learning_rate": 3.1960622310153576e-05,
"loss": 4.5131,
"step": 306
},
{
"epoch": 0.41152815013404825,
"grad_norm": 1.5955722332000732,
"learning_rate": 3.185944266282409e-05,
"loss": 3.9613,
"step": 307
},
{
"epoch": 0.4128686327077748,
"grad_norm": 2.003096103668213,
"learning_rate": 3.1758141366008434e-05,
"loss": 4.1859,
"step": 308
},
{
"epoch": 0.41420911528150134,
"grad_norm": 1.6839512586593628,
"learning_rate": 3.165672021624481e-05,
"loss": 4.208,
"step": 309
},
{
"epoch": 0.4155495978552279,
"grad_norm": 1.5364892482757568,
"learning_rate": 3.1555181012196936e-05,
"loss": 4.2504,
"step": 310
},
{
"epoch": 0.4168900804289544,
"grad_norm": 1.7070716619491577,
"learning_rate": 3.1453525554622206e-05,
"loss": 4.2403,
"step": 311
},
{
"epoch": 0.41823056300268097,
"grad_norm": 1.6160207986831665,
"learning_rate": 3.135175564633972e-05,
"loss": 4.055,
"step": 312
},
{
"epoch": 0.4195710455764075,
"grad_norm": 1.8000752925872803,
"learning_rate": 3.124987309219828e-05,
"loss": 4.4229,
"step": 313
},
{
"epoch": 0.42091152815013405,
"grad_norm": 1.8859308958053589,
"learning_rate": 3.114787969904446e-05,
"loss": 4.0175,
"step": 314
},
{
"epoch": 0.4222520107238606,
"grad_norm": 1.5302249193191528,
"learning_rate": 3.1045777275690505e-05,
"loss": 4.2045,
"step": 315
},
{
"epoch": 0.42359249329758714,
"grad_norm": 1.6178743839263916,
"learning_rate": 3.094356763288226e-05,
"loss": 4.0892,
"step": 316
},
{
"epoch": 0.4249329758713137,
"grad_norm": 1.6156505346298218,
"learning_rate": 3.0841252583267065e-05,
"loss": 4.2745,
"step": 317
},
{
"epoch": 0.4262734584450402,
"grad_norm": 1.4816884994506836,
"learning_rate": 3.073883394136162e-05,
"loss": 4.0643,
"step": 318
},
{
"epoch": 0.42761394101876676,
"grad_norm": 1.9754472970962524,
"learning_rate": 3.0636313523519784e-05,
"loss": 3.9154,
"step": 319
},
{
"epoch": 0.4289544235924933,
"grad_norm": 1.4505501985549927,
"learning_rate": 3.0533693147900365e-05,
"loss": 4.1663,
"step": 320
},
{
"epoch": 0.43029490616621985,
"grad_norm": 1.533445119857788,
"learning_rate": 3.0430974634434907e-05,
"loss": 4.1609,
"step": 321
},
{
"epoch": 0.4316353887399464,
"grad_norm": 2.11559796333313,
"learning_rate": 3.0328159804795358e-05,
"loss": 4.0373,
"step": 322
},
{
"epoch": 0.43297587131367293,
"grad_norm": 1.5644017457962036,
"learning_rate": 3.0225250482361818e-05,
"loss": 4.1189,
"step": 323
},
{
"epoch": 0.4343163538873995,
"grad_norm": 1.9247467517852783,
"learning_rate": 3.0122248492190163e-05,
"loss": 4.1166,
"step": 324
},
{
"epoch": 0.435656836461126,
"grad_norm": 1.447979211807251,
"learning_rate": 3.0019155660979713e-05,
"loss": 4.2561,
"step": 325
},
{
"epoch": 0.43699731903485256,
"grad_norm": 1.1518259048461914,
"learning_rate": 2.9915973817040804e-05,
"loss": 4.2113,
"step": 326
},
{
"epoch": 0.4383378016085791,
"grad_norm": 1.999643325805664,
"learning_rate": 2.9812704790262384e-05,
"loss": 3.9495,
"step": 327
},
{
"epoch": 0.43967828418230565,
"grad_norm": 1.5407859086990356,
"learning_rate": 2.9709350412079544e-05,
"loss": 3.9462,
"step": 328
},
{
"epoch": 0.4410187667560322,
"grad_norm": 1.5092459917068481,
"learning_rate": 2.960591251544106e-05,
"loss": 4.093,
"step": 329
},
{
"epoch": 0.44235924932975873,
"grad_norm": 2.3044111728668213,
"learning_rate": 2.950239293477687e-05,
"loss": 3.9705,
"step": 330
},
{
"epoch": 0.4436997319034853,
"grad_norm": 1.4893378019332886,
"learning_rate": 2.9398793505965537e-05,
"loss": 4.0784,
"step": 331
},
{
"epoch": 0.4450402144772118,
"grad_norm": 2.1338768005371094,
"learning_rate": 2.929511606630172e-05,
"loss": 4.0829,
"step": 332
},
{
"epoch": 0.44638069705093836,
"grad_norm": 1.5938509702682495,
"learning_rate": 2.919136245446354e-05,
"loss": 4.092,
"step": 333
},
{
"epoch": 0.4477211796246649,
"grad_norm": 2.1453089714050293,
"learning_rate": 2.9087534510480037e-05,
"loss": 4.0956,
"step": 334
},
{
"epoch": 0.44906166219839144,
"grad_norm": 1.3650685548782349,
"learning_rate": 2.8983634075698475e-05,
"loss": 4.28,
"step": 335
},
{
"epoch": 0.450402144772118,
"grad_norm": 1.623462200164795,
"learning_rate": 2.8879662992751715e-05,
"loss": 4.0597,
"step": 336
},
{
"epoch": 0.4517426273458445,
"grad_norm": 2.046614646911621,
"learning_rate": 2.8775623105525556e-05,
"loss": 4.2283,
"step": 337
},
{
"epoch": 0.45308310991957107,
"grad_norm": 1.830880880355835,
"learning_rate": 2.8671516259125985e-05,
"loss": 4.1797,
"step": 338
},
{
"epoch": 0.4544235924932976,
"grad_norm": 2.3801305294036865,
"learning_rate": 2.8567344299846506e-05,
"loss": 4.2286,
"step": 339
},
{
"epoch": 0.45576407506702415,
"grad_norm": 1.6630080938339233,
"learning_rate": 2.846310907513536e-05,
"loss": 3.9841,
"step": 340
},
{
"epoch": 0.4571045576407507,
"grad_norm": 2.3895809650421143,
"learning_rate": 2.8358812433562786e-05,
"loss": 4.0095,
"step": 341
},
{
"epoch": 0.4584450402144772,
"grad_norm": 1.6159062385559082,
"learning_rate": 2.8254456224788217e-05,
"loss": 4.4268,
"step": 342
},
{
"epoch": 0.4597855227882037,
"grad_norm": 2.209702730178833,
"learning_rate": 2.815004229952749e-05,
"loss": 3.8829,
"step": 343
},
{
"epoch": 0.46112600536193027,
"grad_norm": 1.8387476205825806,
"learning_rate": 2.804557250952003e-05,
"loss": 4.2603,
"step": 344
},
{
"epoch": 0.4624664879356568,
"grad_norm": 1.9558207988739014,
"learning_rate": 2.7941048707495982e-05,
"loss": 4.1728,
"step": 345
},
{
"epoch": 0.46380697050938335,
"grad_norm": 1.757020354270935,
"learning_rate": 2.783647274714339e-05,
"loss": 3.9945,
"step": 346
},
{
"epoch": 0.4651474530831099,
"grad_norm": 1.8099054098129272,
"learning_rate": 2.7731846483075297e-05,
"loss": 4.0947,
"step": 347
},
{
"epoch": 0.46648793565683644,
"grad_norm": 2.22983980178833,
"learning_rate": 2.7627171770796868e-05,
"loss": 4.0306,
"step": 348
},
{
"epoch": 0.467828418230563,
"grad_norm": 2.307410955429077,
"learning_rate": 2.7522450466672466e-05,
"loss": 3.941,
"step": 349
},
{
"epoch": 0.4691689008042895,
"grad_norm": 1.9241867065429688,
"learning_rate": 2.7417684427892747e-05,
"loss": 4.0862,
"step": 350
},
{
"epoch": 0.47050938337801607,
"grad_norm": 1.8793531656265259,
"learning_rate": 2.731287551244174e-05,
"loss": 4.1502,
"step": 351
},
{
"epoch": 0.4718498659517426,
"grad_norm": 1.5548282861709595,
"learning_rate": 2.7208025579063835e-05,
"loss": 4.064,
"step": 352
},
{
"epoch": 0.47319034852546915,
"grad_norm": 1.5908820629119873,
"learning_rate": 2.7103136487230895e-05,
"loss": 4.2391,
"step": 353
},
{
"epoch": 0.4745308310991957,
"grad_norm": 1.8269513845443726,
"learning_rate": 2.6998210097109216e-05,
"loss": 4.1805,
"step": 354
},
{
"epoch": 0.47587131367292224,
"grad_norm": 2.038243293762207,
"learning_rate": 2.6893248269526578e-05,
"loss": 4.0751,
"step": 355
},
{
"epoch": 0.4772117962466488,
"grad_norm": 1.7675917148590088,
"learning_rate": 2.6788252865939235e-05,
"loss": 4.2343,
"step": 356
},
{
"epoch": 0.4785522788203753,
"grad_norm": 2.9496965408325195,
"learning_rate": 2.668322574839888e-05,
"loss": 4.0658,
"step": 357
},
{
"epoch": 0.47989276139410186,
"grad_norm": 1.8500744104385376,
"learning_rate": 2.6578168779519652e-05,
"loss": 4.0354,
"step": 358
},
{
"epoch": 0.4812332439678284,
"grad_norm": 1.6212828159332275,
"learning_rate": 2.6473083822445088e-05,
"loss": 4.2147,
"step": 359
},
{
"epoch": 0.48257372654155495,
"grad_norm": 1.7091350555419922,
"learning_rate": 2.63679727408151e-05,
"loss": 4.0787,
"step": 360
},
{
"epoch": 0.4839142091152815,
"grad_norm": 2.0279293060302734,
"learning_rate": 2.6262837398732886e-05,
"loss": 4.3703,
"step": 361
},
{
"epoch": 0.48525469168900803,
"grad_norm": 1.6604502201080322,
"learning_rate": 2.615767966073191e-05,
"loss": 3.9092,
"step": 362
},
{
"epoch": 0.4865951742627346,
"grad_norm": 1.5565494298934937,
"learning_rate": 2.6052501391742802e-05,
"loss": 4.238,
"step": 363
},
{
"epoch": 0.4879356568364611,
"grad_norm": 1.6518850326538086,
"learning_rate": 2.594730445706032e-05,
"loss": 4.0058,
"step": 364
},
{
"epoch": 0.48927613941018766,
"grad_norm": 1.786001205444336,
"learning_rate": 2.584209072231023e-05,
"loss": 4.5111,
"step": 365
},
{
"epoch": 0.4906166219839142,
"grad_norm": 1.9006179571151733,
"learning_rate": 2.573686205341626e-05,
"loss": 4.3652,
"step": 366
},
{
"epoch": 0.49195710455764075,
"grad_norm": 1.466137170791626,
"learning_rate": 2.5631620316566985e-05,
"loss": 3.9843,
"step": 367
},
{
"epoch": 0.4932975871313673,
"grad_norm": 1.9523398876190186,
"learning_rate": 2.5526367378182725e-05,
"loss": 4.2517,
"step": 368
},
{
"epoch": 0.49463806970509383,
"grad_norm": 1.8389662504196167,
"learning_rate": 2.5421105104882452e-05,
"loss": 4.1378,
"step": 369
},
{
"epoch": 0.4959785522788204,
"grad_norm": 2.1850528717041016,
"learning_rate": 2.531583536345072e-05,
"loss": 4.0543,
"step": 370
},
{
"epoch": 0.4973190348525469,
"grad_norm": 1.5716923475265503,
"learning_rate": 2.5210560020804487e-05,
"loss": 4.3041,
"step": 371
},
{
"epoch": 0.49865951742627346,
"grad_norm": 1.5218499898910522,
"learning_rate": 2.510528094396007e-05,
"loss": 3.9674,
"step": 372
},
{
"epoch": 0.5,
"grad_norm": 2.0628247261047363,
"learning_rate": 2.5e-05,
"loss": 3.6712,
"step": 373
},
{
"epoch": 0.5013404825737265,
"grad_norm": 1.67324960231781,
"learning_rate": 2.4894719056039936e-05,
"loss": 4.6679,
"step": 374
},
{
"epoch": 0.5026809651474531,
"grad_norm": 1.8018375635147095,
"learning_rate": 2.478943997919552e-05,
"loss": 4.0665,
"step": 375
},
{
"epoch": 0.5040214477211796,
"grad_norm": 1.6567829847335815,
"learning_rate": 2.4684164636549286e-05,
"loss": 4.1501,
"step": 376
},
{
"epoch": 0.5053619302949062,
"grad_norm": 1.7089920043945312,
"learning_rate": 2.457889489511755e-05,
"loss": 4.1043,
"step": 377
},
{
"epoch": 0.5067024128686327,
"grad_norm": 1.5544612407684326,
"learning_rate": 2.447363262181728e-05,
"loss": 4.0276,
"step": 378
},
{
"epoch": 0.5080428954423593,
"grad_norm": 1.2641175985336304,
"learning_rate": 2.4368379683433017e-05,
"loss": 4.4423,
"step": 379
},
{
"epoch": 0.5093833780160858,
"grad_norm": 2.165229320526123,
"learning_rate": 2.4263137946583743e-05,
"loss": 4.0363,
"step": 380
},
{
"epoch": 0.5107238605898123,
"grad_norm": 1.398396372795105,
"learning_rate": 2.4157909277689776e-05,
"loss": 4.0501,
"step": 381
},
{
"epoch": 0.5120643431635389,
"grad_norm": 2.626469135284424,
"learning_rate": 2.405269554293969e-05,
"loss": 4.2245,
"step": 382
},
{
"epoch": 0.5134048257372654,
"grad_norm": 1.6333599090576172,
"learning_rate": 2.3947498608257204e-05,
"loss": 4.1822,
"step": 383
},
{
"epoch": 0.514745308310992,
"grad_norm": 1.9292958974838257,
"learning_rate": 2.38423203392681e-05,
"loss": 3.9859,
"step": 384
},
{
"epoch": 0.5160857908847185,
"grad_norm": 1.9943302869796753,
"learning_rate": 2.373716260126712e-05,
"loss": 4.0657,
"step": 385
},
{
"epoch": 0.517426273458445,
"grad_norm": 1.8861877918243408,
"learning_rate": 2.3632027259184906e-05,
"loss": 4.0267,
"step": 386
},
{
"epoch": 0.5187667560321716,
"grad_norm": 1.7671360969543457,
"learning_rate": 2.3526916177554918e-05,
"loss": 4.1377,
"step": 387
},
{
"epoch": 0.5201072386058981,
"grad_norm": 1.4360904693603516,
"learning_rate": 2.3421831220480357e-05,
"loss": 4.1517,
"step": 388
},
{
"epoch": 0.5214477211796247,
"grad_norm": 1.7188514471054077,
"learning_rate": 2.331677425160113e-05,
"loss": 4.2611,
"step": 389
},
{
"epoch": 0.5227882037533512,
"grad_norm": 2.168728828430176,
"learning_rate": 2.3211747134060774e-05,
"loss": 3.8085,
"step": 390
},
{
"epoch": 0.5241286863270778,
"grad_norm": 1.2896836996078491,
"learning_rate": 2.3106751730473424e-05,
"loss": 4.2546,
"step": 391
},
{
"epoch": 0.5254691689008043,
"grad_norm": 1.6042603254318237,
"learning_rate": 2.3001789902890793e-05,
"loss": 4.1296,
"step": 392
},
{
"epoch": 0.5268096514745308,
"grad_norm": 1.416872501373291,
"learning_rate": 2.289686351276911e-05,
"loss": 4.3228,
"step": 393
},
{
"epoch": 0.5281501340482574,
"grad_norm": 1.7337288856506348,
"learning_rate": 2.2791974420936168e-05,
"loss": 4.3559,
"step": 394
},
{
"epoch": 0.5294906166219839,
"grad_norm": 1.6385115385055542,
"learning_rate": 2.2687124487558267e-05,
"loss": 4.3017,
"step": 395
},
{
"epoch": 0.5308310991957105,
"grad_norm": 1.6782629489898682,
"learning_rate": 2.2582315572107255e-05,
"loss": 4.052,
"step": 396
},
{
"epoch": 0.532171581769437,
"grad_norm": 1.493320345878601,
"learning_rate": 2.247754953332754e-05,
"loss": 3.87,
"step": 397
},
{
"epoch": 0.5335120643431636,
"grad_norm": 3.0621447563171387,
"learning_rate": 2.237282822920314e-05,
"loss": 4.0244,
"step": 398
},
{
"epoch": 0.5348525469168901,
"grad_norm": 1.372417688369751,
"learning_rate": 2.226815351692471e-05,
"loss": 4.1853,
"step": 399
},
{
"epoch": 0.5361930294906166,
"grad_norm": 1.5652010440826416,
"learning_rate": 2.2163527252856614e-05,
"loss": 4.1655,
"step": 400
},
{
"epoch": 0.5375335120643432,
"grad_norm": 1.9100714921951294,
"learning_rate": 2.2058951292504024e-05,
"loss": 4.2346,
"step": 401
},
{
"epoch": 0.5388739946380697,
"grad_norm": 1.4861701726913452,
"learning_rate": 2.195442749047998e-05,
"loss": 4.1875,
"step": 402
},
{
"epoch": 0.5402144772117963,
"grad_norm": 1.5334513187408447,
"learning_rate": 2.1849957700472515e-05,
"loss": 4.2791,
"step": 403
},
{
"epoch": 0.5415549597855228,
"grad_norm": 1.784036636352539,
"learning_rate": 2.1745543775211792e-05,
"loss": 3.9542,
"step": 404
},
{
"epoch": 0.5428954423592494,
"grad_norm": 1.2979745864868164,
"learning_rate": 2.164118756643722e-05,
"loss": 4.0638,
"step": 405
},
{
"epoch": 0.5442359249329759,
"grad_norm": 1.5068295001983643,
"learning_rate": 2.153689092486464e-05,
"loss": 4.462,
"step": 406
},
{
"epoch": 0.5455764075067024,
"grad_norm": 2.4616341590881348,
"learning_rate": 2.1432655700153496e-05,
"loss": 3.982,
"step": 407
},
{
"epoch": 0.546916890080429,
"grad_norm": 1.5166085958480835,
"learning_rate": 2.1328483740874014e-05,
"loss": 4.0979,
"step": 408
},
{
"epoch": 0.5482573726541555,
"grad_norm": 1.7746466398239136,
"learning_rate": 2.1224376894474447e-05,
"loss": 4.1738,
"step": 409
},
{
"epoch": 0.5495978552278821,
"grad_norm": 1.845697283744812,
"learning_rate": 2.1120337007248284e-05,
"loss": 4.2767,
"step": 410
},
{
"epoch": 0.5509383378016086,
"grad_norm": 1.6201977729797363,
"learning_rate": 2.1016365924301527e-05,
"loss": 4.1614,
"step": 411
},
{
"epoch": 0.5522788203753352,
"grad_norm": 1.8354599475860596,
"learning_rate": 2.0912465489519965e-05,
"loss": 4.1648,
"step": 412
},
{
"epoch": 0.5536193029490617,
"grad_norm": 1.29779851436615,
"learning_rate": 2.080863754553646e-05,
"loss": 4.2336,
"step": 413
},
{
"epoch": 0.5549597855227882,
"grad_norm": 1.2807518243789673,
"learning_rate": 2.0704883933698288e-05,
"loss": 4.3824,
"step": 414
},
{
"epoch": 0.5563002680965148,
"grad_norm": 1.7258468866348267,
"learning_rate": 2.0601206494034465e-05,
"loss": 3.8289,
"step": 415
},
{
"epoch": 0.5576407506702413,
"grad_norm": 1.8805090188980103,
"learning_rate": 2.049760706522313e-05,
"loss": 3.9097,
"step": 416
},
{
"epoch": 0.5589812332439679,
"grad_norm": 1.453730821609497,
"learning_rate": 2.039408748455894e-05,
"loss": 4.339,
"step": 417
},
{
"epoch": 0.5603217158176944,
"grad_norm": 2.244704008102417,
"learning_rate": 2.029064958792046e-05,
"loss": 4.2103,
"step": 418
},
{
"epoch": 0.561662198391421,
"grad_norm": 1.9460493326187134,
"learning_rate": 2.0187295209737618e-05,
"loss": 4.0649,
"step": 419
},
{
"epoch": 0.5630026809651475,
"grad_norm": 2.0036537647247314,
"learning_rate": 2.0084026182959195e-05,
"loss": 4.0956,
"step": 420
},
{
"epoch": 0.564343163538874,
"grad_norm": 1.766777515411377,
"learning_rate": 1.998084433902029e-05,
"loss": 4.2547,
"step": 421
},
{
"epoch": 0.5656836461126006,
"grad_norm": 1.8891938924789429,
"learning_rate": 1.987775150780984e-05,
"loss": 3.8096,
"step": 422
},
{
"epoch": 0.5670241286863271,
"grad_norm": 1.5875290632247925,
"learning_rate": 1.9774749517638188e-05,
"loss": 4.037,
"step": 423
},
{
"epoch": 0.5683646112600537,
"grad_norm": 1.3783862590789795,
"learning_rate": 1.9671840195204648e-05,
"loss": 4.102,
"step": 424
},
{
"epoch": 0.5697050938337802,
"grad_norm": 1.4722927808761597,
"learning_rate": 1.9569025365565095e-05,
"loss": 4.1249,
"step": 425
},
{
"epoch": 0.5710455764075067,
"grad_norm": 1.4961539506912231,
"learning_rate": 1.946630685209963e-05,
"loss": 4.0784,
"step": 426
},
{
"epoch": 0.5723860589812333,
"grad_norm": 1.4038958549499512,
"learning_rate": 1.9363686476480218e-05,
"loss": 4.1614,
"step": 427
},
{
"epoch": 0.5737265415549598,
"grad_norm": 1.734254240989685,
"learning_rate": 1.926116605863838e-05,
"loss": 3.9904,
"step": 428
},
{
"epoch": 0.5750670241286864,
"grad_norm": 1.8497049808502197,
"learning_rate": 1.9158747416732934e-05,
"loss": 4.2653,
"step": 429
},
{
"epoch": 0.5764075067024129,
"grad_norm": 2.33406925201416,
"learning_rate": 1.9056432367117744e-05,
"loss": 4.1001,
"step": 430
},
{
"epoch": 0.5777479892761395,
"grad_norm": 1.7938520908355713,
"learning_rate": 1.8954222724309494e-05,
"loss": 4.1204,
"step": 431
},
{
"epoch": 0.579088471849866,
"grad_norm": 1.6719881296157837,
"learning_rate": 1.8852120300955536e-05,
"loss": 4.0443,
"step": 432
},
{
"epoch": 0.5804289544235925,
"grad_norm": 1.1521655321121216,
"learning_rate": 1.875012690780172e-05,
"loss": 4.3216,
"step": 433
},
{
"epoch": 0.5817694369973191,
"grad_norm": 1.8876456022262573,
"learning_rate": 1.8648244353660287e-05,
"loss": 4.0171,
"step": 434
},
{
"epoch": 0.5831099195710456,
"grad_norm": 1.6012482643127441,
"learning_rate": 1.8546474445377786e-05,
"loss": 4.1606,
"step": 435
},
{
"epoch": 0.5844504021447721,
"grad_norm": 1.6673461198806763,
"learning_rate": 1.8444818987803077e-05,
"loss": 3.9613,
"step": 436
},
{
"epoch": 0.5857908847184986,
"grad_norm": 1.9050394296646118,
"learning_rate": 1.834327978375521e-05,
"loss": 4.1962,
"step": 437
},
{
"epoch": 0.5871313672922251,
"grad_norm": 2.8008038997650146,
"learning_rate": 1.8241858633991578e-05,
"loss": 4.1348,
"step": 438
},
{
"epoch": 0.5884718498659517,
"grad_norm": 1.8459497690200806,
"learning_rate": 1.8140557337175925e-05,
"loss": 4.0426,
"step": 439
},
{
"epoch": 0.5898123324396782,
"grad_norm": 1.9654160737991333,
"learning_rate": 1.8039377689846427e-05,
"loss": 4.2719,
"step": 440
},
{
"epoch": 0.5911528150134048,
"grad_norm": 1.234697699546814,
"learning_rate": 1.793832148638388e-05,
"loss": 4.1523,
"step": 441
},
{
"epoch": 0.5924932975871313,
"grad_norm": 2.1580123901367188,
"learning_rate": 1.783739051897984e-05,
"loss": 3.9168,
"step": 442
},
{
"epoch": 0.5938337801608579,
"grad_norm": 1.6117770671844482,
"learning_rate": 1.7736586577604846e-05,
"loss": 4.1645,
"step": 443
},
{
"epoch": 0.5951742627345844,
"grad_norm": 1.648154377937317,
"learning_rate": 1.7635911449976694e-05,
"loss": 4.1189,
"step": 444
},
{
"epoch": 0.596514745308311,
"grad_norm": 2.4047629833221436,
"learning_rate": 1.7535366921528707e-05,
"loss": 4.2343,
"step": 445
},
{
"epoch": 0.5978552278820375,
"grad_norm": 1.445083737373352,
"learning_rate": 1.7434954775378086e-05,
"loss": 4.1891,
"step": 446
},
{
"epoch": 0.599195710455764,
"grad_norm": 2.135385274887085,
"learning_rate": 1.7334676792294303e-05,
"loss": 4.3261,
"step": 447
},
{
"epoch": 0.6005361930294906,
"grad_norm": 1.8604485988616943,
"learning_rate": 1.7234534750667468e-05,
"loss": 3.9987,
"step": 448
},
{
"epoch": 0.6018766756032171,
"grad_norm": 1.5339124202728271,
"learning_rate": 1.7134530426476846e-05,
"loss": 4.191,
"step": 449
},
{
"epoch": 0.6032171581769437,
"grad_norm": 1.743237018585205,
"learning_rate": 1.7034665593259338e-05,
"loss": 3.989,
"step": 450
},
{
"epoch": 0.6045576407506702,
"grad_norm": 1.4767019748687744,
"learning_rate": 1.6934942022078027e-05,
"loss": 4.2716,
"step": 451
},
{
"epoch": 0.6058981233243967,
"grad_norm": 1.3678908348083496,
"learning_rate": 1.6835361481490757e-05,
"loss": 4.396,
"step": 452
},
{
"epoch": 0.6072386058981233,
"grad_norm": 1.6478397846221924,
"learning_rate": 1.67359257375188e-05,
"loss": 3.983,
"step": 453
},
{
"epoch": 0.6085790884718498,
"grad_norm": 1.7605869770050049,
"learning_rate": 1.6636636553615504e-05,
"loss": 4.1603,
"step": 454
},
{
"epoch": 0.6099195710455764,
"grad_norm": 1.7511756420135498,
"learning_rate": 1.6537495690635034e-05,
"loss": 4.1582,
"step": 455
},
{
"epoch": 0.6112600536193029,
"grad_norm": 1.309372067451477,
"learning_rate": 1.643850490680115e-05,
"loss": 4.0716,
"step": 456
},
{
"epoch": 0.6126005361930295,
"grad_norm": 1.6176837682724,
"learning_rate": 1.6339665957676012e-05,
"loss": 4.3069,
"step": 457
},
{
"epoch": 0.613941018766756,
"grad_norm": 1.6048171520233154,
"learning_rate": 1.6240980596129053e-05,
"loss": 3.8597,
"step": 458
},
{
"epoch": 0.6152815013404825,
"grad_norm": 1.5734343528747559,
"learning_rate": 1.6142450572305888e-05,
"loss": 4.1895,
"step": 459
},
{
"epoch": 0.6166219839142091,
"grad_norm": 2.189875602722168,
"learning_rate": 1.6044077633597292e-05,
"loss": 3.9668,
"step": 460
},
{
"epoch": 0.6179624664879356,
"grad_norm": 1.540818691253662,
"learning_rate": 1.5945863524608187e-05,
"loss": 4.1322,
"step": 461
},
{
"epoch": 0.6193029490616622,
"grad_norm": 1.704729676246643,
"learning_rate": 1.584780998712671e-05,
"loss": 4.0237,
"step": 462
},
{
"epoch": 0.6206434316353887,
"grad_norm": 1.5379844903945923,
"learning_rate": 1.574991876009334e-05,
"loss": 4.2837,
"step": 463
},
{
"epoch": 0.6219839142091153,
"grad_norm": 1.3772886991500854,
"learning_rate": 1.5652191579570023e-05,
"loss": 4.0742,
"step": 464
},
{
"epoch": 0.6233243967828418,
"grad_norm": 1.3018437623977661,
"learning_rate": 1.5554630178709427e-05,
"loss": 4.0137,
"step": 465
},
{
"epoch": 0.6246648793565683,
"grad_norm": 1.476588249206543,
"learning_rate": 1.545723628772418e-05,
"loss": 4.2714,
"step": 466
},
{
"epoch": 0.6260053619302949,
"grad_norm": 1.8913376331329346,
"learning_rate": 1.5360011633856176e-05,
"loss": 3.9787,
"step": 467
},
{
"epoch": 0.6273458445040214,
"grad_norm": 1.6905183792114258,
"learning_rate": 1.526295794134596e-05,
"loss": 4.0426,
"step": 468
},
{
"epoch": 0.628686327077748,
"grad_norm": 1.3571633100509644,
"learning_rate": 1.5166076931402162e-05,
"loss": 3.9984,
"step": 469
},
{
"epoch": 0.6300268096514745,
"grad_norm": 1.3958309888839722,
"learning_rate": 1.5069370322170941e-05,
"loss": 4.3721,
"step": 470
},
{
"epoch": 0.631367292225201,
"grad_norm": 2.798372507095337,
"learning_rate": 1.4972839828705526e-05,
"loss": 3.9628,
"step": 471
},
{
"epoch": 0.6327077747989276,
"grad_norm": 1.5644121170043945,
"learning_rate": 1.4876487162935812e-05,
"loss": 4.1202,
"step": 472
},
{
"epoch": 0.6340482573726541,
"grad_norm": 1.6360480785369873,
"learning_rate": 1.4780314033637982e-05,
"loss": 4.0697,
"step": 473
},
{
"epoch": 0.6353887399463807,
"grad_norm": 1.815441608428955,
"learning_rate": 1.4684322146404217e-05,
"loss": 3.968,
"step": 474
},
{
"epoch": 0.6367292225201072,
"grad_norm": 1.5409667491912842,
"learning_rate": 1.458851320361244e-05,
"loss": 4.031,
"step": 475
},
{
"epoch": 0.6380697050938338,
"grad_norm": 1.2886230945587158,
"learning_rate": 1.4492888904396135e-05,
"loss": 4.2815,
"step": 476
},
{
"epoch": 0.6394101876675603,
"grad_norm": 1.7692686319351196,
"learning_rate": 1.4397450944614186e-05,
"loss": 4.2953,
"step": 477
},
{
"epoch": 0.6407506702412868,
"grad_norm": 1.5783576965332031,
"learning_rate": 1.4302201016820849e-05,
"loss": 4.084,
"step": 478
},
{
"epoch": 0.6420911528150134,
"grad_norm": 1.467386245727539,
"learning_rate": 1.4207140810235672e-05,
"loss": 4.1305,
"step": 479
},
{
"epoch": 0.6434316353887399,
"grad_norm": 1.6338868141174316,
"learning_rate": 1.4112272010713617e-05,
"loss": 3.8298,
"step": 480
},
{
"epoch": 0.6447721179624665,
"grad_norm": 1.6367789506912231,
"learning_rate": 1.4017596300715069e-05,
"loss": 4.2634,
"step": 481
},
{
"epoch": 0.646112600536193,
"grad_norm": 1.390328049659729,
"learning_rate": 1.3923115359276084e-05,
"loss": 4.1546,
"step": 482
},
{
"epoch": 0.6474530831099196,
"grad_norm": 1.5065929889678955,
"learning_rate": 1.3828830861978579e-05,
"loss": 4.142,
"step": 483
},
{
"epoch": 0.6487935656836461,
"grad_norm": 1.524415135383606,
"learning_rate": 1.373474448092057e-05,
"loss": 4.4572,
"step": 484
},
{
"epoch": 0.6501340482573726,
"grad_norm": 1.5448362827301025,
"learning_rate": 1.3640857884686603e-05,
"loss": 3.9685,
"step": 485
},
{
"epoch": 0.6514745308310992,
"grad_norm": 1.897816777229309,
"learning_rate": 1.3547172738318093e-05,
"loss": 3.9411,
"step": 486
},
{
"epoch": 0.6528150134048257,
"grad_norm": 1.5400289297103882,
"learning_rate": 1.3453690703283847e-05,
"loss": 3.9751,
"step": 487
},
{
"epoch": 0.6541554959785523,
"grad_norm": 1.643668293952942,
"learning_rate": 1.3360413437450542e-05,
"loss": 4.0027,
"step": 488
},
{
"epoch": 0.6554959785522788,
"grad_norm": 1.4362705945968628,
"learning_rate": 1.3267342595053386e-05,
"loss": 3.9511,
"step": 489
},
{
"epoch": 0.6568364611260054,
"grad_norm": 1.5446350574493408,
"learning_rate": 1.317447982666672e-05,
"loss": 4.1382,
"step": 490
},
{
"epoch": 0.6581769436997319,
"grad_norm": 1.4813910722732544,
"learning_rate": 1.3081826779174805e-05,
"loss": 4.1631,
"step": 491
},
{
"epoch": 0.6595174262734584,
"grad_norm": 1.6765987873077393,
"learning_rate": 1.2989385095742557e-05,
"loss": 4.149,
"step": 492
},
{
"epoch": 0.660857908847185,
"grad_norm": 1.8691000938415527,
"learning_rate": 1.289715641578645e-05,
"loss": 4.1047,
"step": 493
},
{
"epoch": 0.6621983914209115,
"grad_norm": 1.5709315538406372,
"learning_rate": 1.280514237494544e-05,
"loss": 4.1226,
"step": 494
},
{
"epoch": 0.6635388739946381,
"grad_norm": 2.259974956512451,
"learning_rate": 1.2713344605051905e-05,
"loss": 4.1064,
"step": 495
},
{
"epoch": 0.6648793565683646,
"grad_norm": 1.8946611881256104,
"learning_rate": 1.2621764734102786e-05,
"loss": 4.2389,
"step": 496
},
{
"epoch": 0.6662198391420912,
"grad_norm": 1.4251221418380737,
"learning_rate": 1.2530404386230638e-05,
"loss": 4.0866,
"step": 497
},
{
"epoch": 0.6675603217158177,
"grad_norm": 1.6305046081542969,
"learning_rate": 1.2439265181674895e-05,
"loss": 4.3335,
"step": 498
},
{
"epoch": 0.6689008042895442,
"grad_norm": 1.532456874847412,
"learning_rate": 1.234834873675306e-05,
"loss": 3.9201,
"step": 499
},
{
"epoch": 0.6702412868632708,
"grad_norm": 2.4865877628326416,
"learning_rate": 1.2257656663832129e-05,
"loss": 4.2511,
"step": 500
},
{
"epoch": 0.6715817694369973,
"grad_norm": 1.3506802320480347,
"learning_rate": 1.2167190571299911e-05,
"loss": 3.9312,
"step": 501
},
{
"epoch": 0.6729222520107239,
"grad_norm": 1.504542350769043,
"learning_rate": 1.2076952063536567e-05,
"loss": 4.1099,
"step": 502
},
{
"epoch": 0.6742627345844504,
"grad_norm": 1.6404659748077393,
"learning_rate": 1.1986942740886135e-05,
"loss": 4.1739,
"step": 503
},
{
"epoch": 0.675603217158177,
"grad_norm": 2.0798070430755615,
"learning_rate": 1.1897164199628117e-05,
"loss": 3.9686,
"step": 504
},
{
"epoch": 0.6769436997319035,
"grad_norm": 1.451737880706787,
"learning_rate": 1.1807618031949235e-05,
"loss": 4.2728,
"step": 505
},
{
"epoch": 0.67828418230563,
"grad_norm": 1.5113872289657593,
"learning_rate": 1.1718305825915125e-05,
"loss": 4.1488,
"step": 506
},
{
"epoch": 0.6796246648793566,
"grad_norm": 1.7265151739120483,
"learning_rate": 1.162922916544224e-05,
"loss": 4.3999,
"step": 507
},
{
"epoch": 0.6809651474530831,
"grad_norm": 1.6517037153244019,
"learning_rate": 1.1540389630269693e-05,
"loss": 3.9868,
"step": 508
},
{
"epoch": 0.6823056300268097,
"grad_norm": 2.1054139137268066,
"learning_rate": 1.1451788795931307e-05,
"loss": 4.0988,
"step": 509
},
{
"epoch": 0.6836461126005362,
"grad_norm": 1.4923871755599976,
"learning_rate": 1.13634282337276e-05,
"loss": 3.8554,
"step": 510
},
{
"epoch": 0.6849865951742627,
"grad_norm": 2.8622472286224365,
"learning_rate": 1.1275309510697999e-05,
"loss": 3.99,
"step": 511
},
{
"epoch": 0.6863270777479893,
"grad_norm": 1.826074242591858,
"learning_rate": 1.1187434189593e-05,
"loss": 4.0461,
"step": 512
},
{
"epoch": 0.6876675603217158,
"grad_norm": 2.4107580184936523,
"learning_rate": 1.1099803828846437e-05,
"loss": 3.8922,
"step": 513
},
{
"epoch": 0.6890080428954424,
"grad_norm": 2.0733463764190674,
"learning_rate": 1.1012419982547905e-05,
"loss": 4.1695,
"step": 514
},
{
"epoch": 0.6903485254691689,
"grad_norm": 1.6084847450256348,
"learning_rate": 1.0925284200415134e-05,
"loss": 4.2329,
"step": 515
},
{
"epoch": 0.6916890080428955,
"grad_norm": 1.6451109647750854,
"learning_rate": 1.083839802776656e-05,
"loss": 4.1565,
"step": 516
},
{
"epoch": 0.693029490616622,
"grad_norm": 1.3165000677108765,
"learning_rate": 1.075176300549387e-05,
"loss": 4.2409,
"step": 517
},
{
"epoch": 0.6943699731903485,
"grad_norm": 1.7777302265167236,
"learning_rate": 1.0665380670034725e-05,
"loss": 4.1882,
"step": 518
},
{
"epoch": 0.6957104557640751,
"grad_norm": 1.3372153043746948,
"learning_rate": 1.0579252553345451e-05,
"loss": 3.9595,
"step": 519
},
{
"epoch": 0.6970509383378016,
"grad_norm": 1.2749888896942139,
"learning_rate": 1.0493380182873941e-05,
"loss": 4.0133,
"step": 520
},
{
"epoch": 0.6983914209115282,
"grad_norm": 1.6833118200302124,
"learning_rate": 1.040776508153252e-05,
"loss": 4.2144,
"step": 521
},
{
"epoch": 0.6997319034852547,
"grad_norm": 1.8305304050445557,
"learning_rate": 1.0322408767670927e-05,
"loss": 4.0447,
"step": 522
},
{
"epoch": 0.7010723860589813,
"grad_norm": 1.5214430093765259,
"learning_rate": 1.023731275504944e-05,
"loss": 4.1392,
"step": 523
},
{
"epoch": 0.7024128686327078,
"grad_norm": 1.817636251449585,
"learning_rate": 1.0152478552811967e-05,
"loss": 4.1138,
"step": 524
},
{
"epoch": 0.7037533512064343,
"grad_norm": 1.561204433441162,
"learning_rate": 1.0067907665459344e-05,
"loss": 4.337,
"step": 525
},
{
"epoch": 0.7050938337801609,
"grad_norm": 1.4202795028686523,
"learning_rate": 9.98360159282259e-06,
"loss": 4.1084,
"step": 526
},
{
"epoch": 0.7064343163538874,
"grad_norm": 1.6342689990997314,
"learning_rate": 9.899561830036371e-06,
"loss": 4.2733,
"step": 527
},
{
"epoch": 0.707774798927614,
"grad_norm": 1.620021104812622,
"learning_rate": 9.815789867512427e-06,
"loss": 4.098,
"step": 528
},
{
"epoch": 0.7091152815013405,
"grad_norm": 1.5363893508911133,
"learning_rate": 9.732287190913184e-06,
"loss": 3.9743,
"step": 529
},
{
"epoch": 0.710455764075067,
"grad_norm": 1.8716835975646973,
"learning_rate": 9.649055281125394e-06,
"loss": 4.0672,
"step": 530
},
{
"epoch": 0.7117962466487936,
"grad_norm": 1.7030665874481201,
"learning_rate": 9.566095614233842e-06,
"loss": 4.3018,
"step": 531
},
{
"epoch": 0.7131367292225201,
"grad_norm": 2.1955244541168213,
"learning_rate": 9.483409661495226e-06,
"loss": 4.09,
"step": 532
},
{
"epoch": 0.7144772117962467,
"grad_norm": 2.0487895011901855,
"learning_rate": 9.400998889311999e-06,
"loss": 4.1931,
"step": 533
},
{
"epoch": 0.7158176943699732,
"grad_norm": 2.382164239883423,
"learning_rate": 9.31886475920643e-06,
"loss": 3.74,
"step": 534
},
{
"epoch": 0.7171581769436998,
"grad_norm": 1.835524559020996,
"learning_rate": 9.237008727794618e-06,
"loss": 4.1571,
"step": 535
},
{
"epoch": 0.7184986595174263,
"grad_norm": 1.6688836812973022,
"learning_rate": 9.155432246760726e-06,
"loss": 3.9046,
"step": 536
},
{
"epoch": 0.7198391420911529,
"grad_norm": 2.1579833030700684,
"learning_rate": 9.074136762831167e-06,
"loss": 4.0313,
"step": 537
},
{
"epoch": 0.7211796246648794,
"grad_norm": 1.5827877521514893,
"learning_rate": 8.993123717749016e-06,
"loss": 4.283,
"step": 538
},
{
"epoch": 0.7225201072386059,
"grad_norm": 1.3723039627075195,
"learning_rate": 8.912394548248377e-06,
"loss": 3.8828,
"step": 539
},
{
"epoch": 0.7238605898123325,
"grad_norm": 2.1818349361419678,
"learning_rate": 8.831950686028953e-06,
"loss": 3.7389,
"step": 540
},
{
"epoch": 0.725201072386059,
"grad_norm": 1.4615998268127441,
"learning_rate": 8.751793557730642e-06,
"loss": 4.2028,
"step": 541
},
{
"epoch": 0.7265415549597856,
"grad_norm": 1.7461323738098145,
"learning_rate": 8.671924584908198e-06,
"loss": 4.0668,
"step": 542
},
{
"epoch": 0.7278820375335121,
"grad_norm": 1.5973039865493774,
"learning_rate": 8.592345184006096e-06,
"loss": 4.1812,
"step": 543
},
{
"epoch": 0.7292225201072386,
"grad_norm": 1.6790518760681152,
"learning_rate": 8.513056766333324e-06,
"loss": 4.2097,
"step": 544
},
{
"epoch": 0.7305630026809652,
"grad_norm": 1.5632734298706055,
"learning_rate": 8.434060738038438e-06,
"loss": 4.1809,
"step": 545
},
{
"epoch": 0.7319034852546917,
"grad_norm": 2.273946523666382,
"learning_rate": 8.355358500084549e-06,
"loss": 3.95,
"step": 546
},
{
"epoch": 0.7332439678284183,
"grad_norm": 2.0586934089660645,
"learning_rate": 8.276951448224546e-06,
"loss": 4.1303,
"step": 547
},
{
"epoch": 0.7345844504021448,
"grad_norm": 2.111582040786743,
"learning_rate": 8.19884097297628e-06,
"loss": 4.1593,
"step": 548
},
{
"epoch": 0.7359249329758714,
"grad_norm": 1.8287386894226074,
"learning_rate": 8.121028459597953e-06,
"loss": 4.1659,
"step": 549
},
{
"epoch": 0.7372654155495979,
"grad_norm": 1.3675771951675415,
"learning_rate": 8.043515288063542e-06,
"loss": 4.0701,
"step": 550
},
{
"epoch": 0.7386058981233244,
"grad_norm": 1.6444734334945679,
"learning_rate": 7.966302833038278e-06,
"loss": 4.174,
"step": 551
},
{
"epoch": 0.739946380697051,
"grad_norm": 1.4653570652008057,
"learning_rate": 7.889392463854348e-06,
"loss": 4.1164,
"step": 552
},
{
"epoch": 0.7412868632707775,
"grad_norm": 3.4404611587524414,
"learning_rate": 7.812785544486526e-06,
"loss": 3.823,
"step": 553
},
{
"epoch": 0.7426273458445041,
"grad_norm": 1.891850233078003,
"learning_rate": 7.73648343352806e-06,
"loss": 4.119,
"step": 554
},
{
"epoch": 0.7439678284182306,
"grad_norm": 2.303138017654419,
"learning_rate": 7.660487484166513e-06,
"loss": 4.1603,
"step": 555
},
{
"epoch": 0.7453083109919572,
"grad_norm": 1.4972648620605469,
"learning_rate": 7.584799044159821e-06,
"loss": 4.06,
"step": 556
},
{
"epoch": 0.7466487935656837,
"grad_norm": 1.5143014192581177,
"learning_rate": 7.509419455812336e-06,
"loss": 4.0462,
"step": 557
},
{
"epoch": 0.7479892761394102,
"grad_norm": 2.32197642326355,
"learning_rate": 7.43435005595107e-06,
"loss": 3.8975,
"step": 558
},
{
"epoch": 0.7493297587131368,
"grad_norm": 1.409792184829712,
"learning_rate": 7.359592175901964e-06,
"loss": 4.4135,
"step": 559
},
{
"epoch": 0.7506702412868632,
"grad_norm": 1.722603678703308,
"learning_rate": 7.285147141466269e-06,
"loss": 4.0134,
"step": 560
},
{
"epoch": 0.7520107238605898,
"grad_norm": 1.627700924873352,
"learning_rate": 7.2110162728970475e-06,
"loss": 4.1396,
"step": 561
},
{
"epoch": 0.7533512064343163,
"grad_norm": 2.29186749458313,
"learning_rate": 7.137200884875747e-06,
"loss": 3.9754,
"step": 562
},
{
"epoch": 0.7546916890080428,
"grad_norm": 1.4593878984451294,
"learning_rate": 7.06370228648891e-06,
"loss": 4.0244,
"step": 563
},
{
"epoch": 0.7560321715817694,
"grad_norm": 1.6213958263397217,
"learning_rate": 6.990521781204939e-06,
"loss": 4.2598,
"step": 564
},
{
"epoch": 0.7573726541554959,
"grad_norm": 1.5174040794372559,
"learning_rate": 6.917660666850964e-06,
"loss": 4.2098,
"step": 565
},
{
"epoch": 0.7587131367292225,
"grad_norm": 1.761343002319336,
"learning_rate": 6.845120235589869e-06,
"loss": 4.2062,
"step": 566
},
{
"epoch": 0.760053619302949,
"grad_norm": 1.5893421173095703,
"learning_rate": 6.772901773897319e-06,
"loss": 4.2258,
"step": 567
},
{
"epoch": 0.7613941018766756,
"grad_norm": 2.2588400840759277,
"learning_rate": 6.701006562539019e-06,
"loss": 3.8174,
"step": 568
},
{
"epoch": 0.7627345844504021,
"grad_norm": 1.8464969396591187,
"learning_rate": 6.62943587654791e-06,
"loss": 4.1097,
"step": 569
},
{
"epoch": 0.7640750670241286,
"grad_norm": 1.8879106044769287,
"learning_rate": 6.558190985201651e-06,
"loss": 4.1451,
"step": 570
},
{
"epoch": 0.7654155495978552,
"grad_norm": 1.3377039432525635,
"learning_rate": 6.487273152000023e-06,
"loss": 4.2291,
"step": 571
},
{
"epoch": 0.7667560321715817,
"grad_norm": 2.1687779426574707,
"learning_rate": 6.416683634642584e-06,
"loss": 4.1151,
"step": 572
},
{
"epoch": 0.7680965147453083,
"grad_norm": 1.888623833656311,
"learning_rate": 6.346423685006348e-06,
"loss": 3.683,
"step": 573
},
{
"epoch": 0.7694369973190348,
"grad_norm": 1.3975709676742554,
"learning_rate": 6.276494549123546e-06,
"loss": 4.0913,
"step": 574
},
{
"epoch": 0.7707774798927614,
"grad_norm": 1.4594451189041138,
"learning_rate": 6.206897467159595e-06,
"loss": 4.2179,
"step": 575
},
{
"epoch": 0.7721179624664879,
"grad_norm": 1.4480808973312378,
"learning_rate": 6.137633673391033e-06,
"loss": 3.9305,
"step": 576
},
{
"epoch": 0.7734584450402144,
"grad_norm": 1.895422101020813,
"learning_rate": 6.068704396183695e-06,
"loss": 4.0433,
"step": 577
},
{
"epoch": 0.774798927613941,
"grad_norm": 1.5772151947021484,
"learning_rate": 6.000110857970873e-06,
"loss": 4.1734,
"step": 578
},
{
"epoch": 0.7761394101876675,
"grad_norm": 2.339197874069214,
"learning_rate": 5.931854275231685e-06,
"loss": 3.9478,
"step": 579
},
{
"epoch": 0.7774798927613941,
"grad_norm": 1.7511122226715088,
"learning_rate": 5.863935858469452e-06,
"loss": 4.0084,
"step": 580
},
{
"epoch": 0.7788203753351206,
"grad_norm": 1.8038029670715332,
"learning_rate": 5.796356812190276e-06,
"loss": 3.9554,
"step": 581
},
{
"epoch": 0.7801608579088471,
"grad_norm": 1.323141098022461,
"learning_rate": 5.729118334881661e-06,
"loss": 4.3301,
"step": 582
},
{
"epoch": 0.7815013404825737,
"grad_norm": 1.350898027420044,
"learning_rate": 5.662221618991234e-06,
"loss": 3.8981,
"step": 583
},
{
"epoch": 0.7828418230563002,
"grad_norm": 1.4751012325286865,
"learning_rate": 5.595667850905642e-06,
"loss": 4.131,
"step": 584
},
{
"epoch": 0.7841823056300268,
"grad_norm": 1.9315931797027588,
"learning_rate": 5.5294582109294696e-06,
"loss": 4.0313,
"step": 585
},
{
"epoch": 0.7855227882037533,
"grad_norm": 1.4609266519546509,
"learning_rate": 5.463593873264347e-06,
"loss": 4.0325,
"step": 586
},
{
"epoch": 0.7868632707774799,
"grad_norm": 1.9292317628860474,
"learning_rate": 5.398076005988081e-06,
"loss": 4.0818,
"step": 587
},
{
"epoch": 0.7882037533512064,
"grad_norm": 1.9036489725112915,
"learning_rate": 5.332905771033994e-06,
"loss": 3.731,
"step": 588
},
{
"epoch": 0.789544235924933,
"grad_norm": 2.0196640491485596,
"learning_rate": 5.268084324170253e-06,
"loss": 3.9546,
"step": 589
},
{
"epoch": 0.7908847184986595,
"grad_norm": 1.6353363990783691,
"learning_rate": 5.203612814979442e-06,
"loss": 4.0226,
"step": 590
},
{
"epoch": 0.792225201072386,
"grad_norm": 1.7163848876953125,
"learning_rate": 5.1394923868381075e-06,
"loss": 4.0016,
"step": 591
},
{
"epoch": 0.7935656836461126,
"grad_norm": 2.6417622566223145,
"learning_rate": 5.075724176896532e-06,
"loss": 4.1135,
"step": 592
},
{
"epoch": 0.7949061662198391,
"grad_norm": 2.6591272354125977,
"learning_rate": 5.012309316058555e-06,
"loss": 4.306,
"step": 593
},
{
"epoch": 0.7962466487935657,
"grad_norm": 1.7307076454162598,
"learning_rate": 4.949248928961489e-06,
"loss": 4.0088,
"step": 594
},
{
"epoch": 0.7975871313672922,
"grad_norm": 1.313391923904419,
"learning_rate": 4.886544133956211e-06,
"loss": 4.0909,
"step": 595
},
{
"epoch": 0.7989276139410187,
"grad_norm": 1.6195955276489258,
"learning_rate": 4.824196043087306e-06,
"loss": 4.2288,
"step": 596
},
{
"epoch": 0.8002680965147453,
"grad_norm": 2.218224287033081,
"learning_rate": 4.762205762073363e-06,
"loss": 3.7363,
"step": 597
},
{
"epoch": 0.8016085790884718,
"grad_norm": 1.5383011102676392,
"learning_rate": 4.700574390287341e-06,
"loss": 4.0846,
"step": 598
},
{
"epoch": 0.8029490616621984,
"grad_norm": 1.5616196393966675,
"learning_rate": 4.639303020737101e-06,
"loss": 3.947,
"step": 599
},
{
"epoch": 0.8042895442359249,
"grad_norm": 1.7160272598266602,
"learning_rate": 4.578392740045994e-06,
"loss": 4.1478,
"step": 600
},
{
"epoch": 0.8056300268096515,
"grad_norm": 1.7334322929382324,
"learning_rate": 4.5178446284336155e-06,
"loss": 4.1115,
"step": 601
},
{
"epoch": 0.806970509383378,
"grad_norm": 1.4539278745651245,
"learning_rate": 4.457659759696639e-06,
"loss": 4.007,
"step": 602
},
{
"epoch": 0.8083109919571045,
"grad_norm": 1.7417395114898682,
"learning_rate": 4.397839201189749e-06,
"loss": 4.2025,
"step": 603
},
{
"epoch": 0.8096514745308311,
"grad_norm": 1.6823294162750244,
"learning_rate": 4.338384013806762e-06,
"loss": 4.1711,
"step": 604
},
{
"epoch": 0.8109919571045576,
"grad_norm": 1.6005618572235107,
"learning_rate": 4.279295251961754e-06,
"loss": 4.0891,
"step": 605
},
{
"epoch": 0.8123324396782842,
"grad_norm": 1.7852652072906494,
"learning_rate": 4.220573963570418e-06,
"loss": 4.2479,
"step": 606
},
{
"epoch": 0.8136729222520107,
"grad_norm": 1.916030764579773,
"learning_rate": 4.162221190031424e-06,
"loss": 4.0771,
"step": 607
},
{
"epoch": 0.8150134048257373,
"grad_norm": 1.7884804010391235,
"learning_rate": 4.104237966208002e-06,
"loss": 4.0865,
"step": 608
},
{
"epoch": 0.8163538873994638,
"grad_norm": 1.854982852935791,
"learning_rate": 4.046625320409547e-06,
"loss": 4.0798,
"step": 609
},
{
"epoch": 0.8176943699731903,
"grad_norm": 1.502204418182373,
"learning_rate": 3.989384274373409e-06,
"loss": 4.1344,
"step": 610
},
{
"epoch": 0.8190348525469169,
"grad_norm": 1.4239370822906494,
"learning_rate": 3.932515843246773e-06,
"loss": 4.1115,
"step": 611
},
{
"epoch": 0.8203753351206434,
"grad_norm": 1.4142134189605713,
"learning_rate": 3.876021035568619e-06,
"loss": 4.1107,
"step": 612
},
{
"epoch": 0.82171581769437,
"grad_norm": 1.9802576303482056,
"learning_rate": 3.819900853251896e-06,
"loss": 4.4778,
"step": 613
},
{
"epoch": 0.8230563002680965,
"grad_norm": 1.581973910331726,
"learning_rate": 3.764156291565693e-06,
"loss": 4.0747,
"step": 614
},
{
"epoch": 0.824396782841823,
"grad_norm": 2.4213356971740723,
"learning_rate": 3.708788339117644e-06,
"loss": 3.9894,
"step": 615
},
{
"epoch": 0.8257372654155496,
"grad_norm": 2.2809488773345947,
"learning_rate": 3.653797977836343e-06,
"loss": 4.2533,
"step": 616
},
{
"epoch": 0.8270777479892761,
"grad_norm": 1.6151589155197144,
"learning_rate": 3.5991861829539732e-06,
"loss": 4.0398,
"step": 617
},
{
"epoch": 0.8284182305630027,
"grad_norm": 1.6391048431396484,
"learning_rate": 3.5449539229889807e-06,
"loss": 4.1706,
"step": 618
},
{
"epoch": 0.8297587131367292,
"grad_norm": 1.5368852615356445,
"learning_rate": 3.4911021597289153e-06,
"loss": 4.0299,
"step": 619
},
{
"epoch": 0.8310991957104558,
"grad_norm": 1.8355164527893066,
"learning_rate": 3.4376318482133797e-06,
"loss": 4.3147,
"step": 620
},
{
"epoch": 0.8324396782841823,
"grad_norm": 1.5161722898483276,
"learning_rate": 3.3845439367170605e-06,
"loss": 3.9595,
"step": 621
},
{
"epoch": 0.8337801608579088,
"grad_norm": 2.366042375564575,
"learning_rate": 3.3318393667329527e-06,
"loss": 4.1286,
"step": 622
},
{
"epoch": 0.8351206434316354,
"grad_norm": 1.7051384449005127,
"learning_rate": 3.2795190729556254e-06,
"loss": 3.9755,
"step": 623
},
{
"epoch": 0.8364611260053619,
"grad_norm": 1.3396157026290894,
"learning_rate": 3.2275839832646786e-06,
"loss": 4.0855,
"step": 624
},
{
"epoch": 0.8378016085790885,
"grad_norm": 1.4888492822647095,
"learning_rate": 3.176035018708251e-06,
"loss": 4.1917,
"step": 625
},
{
"epoch": 0.839142091152815,
"grad_norm": 1.8398135900497437,
"learning_rate": 3.1248730934867297e-06,
"loss": 4.002,
"step": 626
},
{
"epoch": 0.8404825737265416,
"grad_norm": 1.6706128120422363,
"learning_rate": 3.0740991149364905e-06,
"loss": 4.3033,
"step": 627
},
{
"epoch": 0.8418230563002681,
"grad_norm": 1.629183292388916,
"learning_rate": 3.0237139835138402e-06,
"loss": 4.1518,
"step": 628
},
{
"epoch": 0.8431635388739946,
"grad_norm": 1.707590937614441,
"learning_rate": 2.9737185927790455e-06,
"loss": 3.9776,
"step": 629
},
{
"epoch": 0.8445040214477212,
"grad_norm": 3.17254376411438,
"learning_rate": 2.9241138293804565e-06,
"loss": 4.069,
"step": 630
},
{
"epoch": 0.8458445040214477,
"grad_norm": 1.5430855751037598,
"learning_rate": 2.874900573038819e-06,
"loss": 4.2447,
"step": 631
},
{
"epoch": 0.8471849865951743,
"grad_norm": 1.6813849210739136,
"learning_rate": 2.826079696531647e-06,
"loss": 3.9423,
"step": 632
},
{
"epoch": 0.8485254691689008,
"grad_norm": 1.6792819499969482,
"learning_rate": 2.777652065677766e-06,
"loss": 4.3446,
"step": 633
},
{
"epoch": 0.8498659517426274,
"grad_norm": 1.510520577430725,
"learning_rate": 2.729618539321932e-06,
"loss": 4.1472,
"step": 634
},
{
"epoch": 0.8512064343163539,
"grad_norm": 1.7376744747161865,
"learning_rate": 2.6819799693196283e-06,
"loss": 3.9529,
"step": 635
},
{
"epoch": 0.8525469168900804,
"grad_norm": 1.5206412076950073,
"learning_rate": 2.6347372005219305e-06,
"loss": 4.154,
"step": 636
},
{
"epoch": 0.853887399463807,
"grad_norm": 1.4670528173446655,
"learning_rate": 2.5878910707605537e-06,
"loss": 4.1295,
"step": 637
},
{
"epoch": 0.8552278820375335,
"grad_norm": 1.8389042615890503,
"learning_rate": 2.541442410832959e-06,
"loss": 3.999,
"step": 638
},
{
"epoch": 0.8565683646112601,
"grad_norm": 2.0346367359161377,
"learning_rate": 2.495392044487649e-06,
"loss": 3.9343,
"step": 639
},
{
"epoch": 0.8579088471849866,
"grad_norm": 1.5337841510772705,
"learning_rate": 2.4497407884095575e-06,
"loss": 4.3079,
"step": 640
},
{
"epoch": 0.8592493297587132,
"grad_norm": 1.6186468601226807,
"learning_rate": 2.404489452205533e-06,
"loss": 4.3633,
"step": 641
},
{
"epoch": 0.8605898123324397,
"grad_norm": 1.3302162885665894,
"learning_rate": 2.359638838390027e-06,
"loss": 4.0979,
"step": 642
},
{
"epoch": 0.8619302949061662,
"grad_norm": 1.7183328866958618,
"learning_rate": 2.3151897423708214e-06,
"loss": 4.0574,
"step": 643
},
{
"epoch": 0.8632707774798928,
"grad_norm": 1.6089767217636108,
"learning_rate": 2.2711429524349515e-06,
"loss": 4.0084,
"step": 644
},
{
"epoch": 0.8646112600536193,
"grad_norm": 1.973074197769165,
"learning_rate": 2.2274992497347045e-06,
"loss": 4.1426,
"step": 645
},
{
"epoch": 0.8659517426273459,
"grad_norm": 1.370041847229004,
"learning_rate": 2.184259408273792e-06,
"loss": 4.1338,
"step": 646
},
{
"epoch": 0.8672922252010724,
"grad_norm": 1.6897451877593994,
"learning_rate": 2.141424194893582e-06,
"loss": 4.4458,
"step": 647
},
{
"epoch": 0.868632707774799,
"grad_norm": 1.3583239316940308,
"learning_rate": 2.0989943692595495e-06,
"loss": 4.174,
"step": 648
},
{
"epoch": 0.8699731903485255,
"grad_norm": 1.6080747842788696,
"learning_rate": 2.05697068384777e-06,
"loss": 4.1498,
"step": 649
},
{
"epoch": 0.871313672922252,
"grad_norm": 1.6234769821166992,
"learning_rate": 2.0153538839315756e-06,
"loss": 3.9852,
"step": 650
},
{
"epoch": 0.8726541554959786,
"grad_norm": 1.5308585166931152,
"learning_rate": 1.9741447075683595e-06,
"loss": 4.0212,
"step": 651
},
{
"epoch": 0.8739946380697051,
"grad_norm": 1.3633662462234497,
"learning_rate": 1.933343885586458e-06,
"loss": 4.0292,
"step": 652
},
{
"epoch": 0.8753351206434317,
"grad_norm": 1.6495016813278198,
"learning_rate": 1.8929521415722267e-06,
"loss": 4.1943,
"step": 653
},
{
"epoch": 0.8766756032171582,
"grad_norm": 1.7188185453414917,
"learning_rate": 1.852970191857159e-06,
"loss": 4.1658,
"step": 654
},
{
"epoch": 0.8780160857908847,
"grad_norm": 2.570451021194458,
"learning_rate": 1.813398745505235e-06,
"loss": 3.7912,
"step": 655
},
{
"epoch": 0.8793565683646113,
"grad_norm": 1.6092784404754639,
"learning_rate": 1.7742385043003018e-06,
"loss": 4.1793,
"step": 656
},
{
"epoch": 0.8806970509383378,
"grad_norm": 1.6216198205947876,
"learning_rate": 1.7354901627336578e-06,
"loss": 4.0577,
"step": 657
},
{
"epoch": 0.8820375335120644,
"grad_norm": 1.4914729595184326,
"learning_rate": 1.6971544079917273e-06,
"loss": 3.8955,
"step": 658
},
{
"epoch": 0.8833780160857909,
"grad_norm": 3.0483927726745605,
"learning_rate": 1.6592319199438573e-06,
"loss": 3.8942,
"step": 659
},
{
"epoch": 0.8847184986595175,
"grad_norm": 1.6463979482650757,
"learning_rate": 1.6217233711302904e-06,
"loss": 4.1147,
"step": 660
},
{
"epoch": 0.886058981233244,
"grad_norm": 1.4989440441131592,
"learning_rate": 1.5846294267502116e-06,
"loss": 4.0875,
"step": 661
},
{
"epoch": 0.8873994638069705,
"grad_norm": 1.5697479248046875,
"learning_rate": 1.5479507446499674e-06,
"loss": 3.8637,
"step": 662
},
{
"epoch": 0.8887399463806971,
"grad_norm": 1.796716570854187,
"learning_rate": 1.5116879753113822e-06,
"loss": 4.0613,
"step": 663
},
{
"epoch": 0.8900804289544236,
"grad_norm": 1.7171390056610107,
"learning_rate": 1.4758417618402521e-06,
"loss": 4.1748,
"step": 664
},
{
"epoch": 0.8914209115281502,
"grad_norm": 2.2504525184631348,
"learning_rate": 1.4404127399548966e-06,
"loss": 4.2548,
"step": 665
},
{
"epoch": 0.8927613941018767,
"grad_norm": 1.8576676845550537,
"learning_rate": 1.405401537974929e-06,
"loss": 4.3631,
"step": 666
},
{
"epoch": 0.8941018766756033,
"grad_norm": 1.5815280675888062,
"learning_rate": 1.3708087768100897e-06,
"loss": 4.0721,
"step": 667
},
{
"epoch": 0.8954423592493298,
"grad_norm": 1.3464423418045044,
"learning_rate": 1.3366350699492214e-06,
"loss": 4.1092,
"step": 668
},
{
"epoch": 0.8967828418230563,
"grad_norm": 2.2372212409973145,
"learning_rate": 1.3028810234494259e-06,
"loss": 3.7378,
"step": 669
},
{
"epoch": 0.8981233243967829,
"grad_norm": 1.5314258337020874,
"learning_rate": 1.2695472359252808e-06,
"loss": 4.1706,
"step": 670
},
{
"epoch": 0.8994638069705094,
"grad_norm": 1.3317408561706543,
"learning_rate": 1.2366342985382501e-06,
"loss": 4.1836,
"step": 671
},
{
"epoch": 0.900804289544236,
"grad_norm": 2.3380496501922607,
"learning_rate": 1.2041427949861766e-06,
"loss": 4.0531,
"step": 672
},
{
"epoch": 0.9021447721179625,
"grad_norm": 1.5681943893432617,
"learning_rate": 1.1720733014929514e-06,
"loss": 4.2023,
"step": 673
},
{
"epoch": 0.903485254691689,
"grad_norm": 1.7159653902053833,
"learning_rate": 1.140426386798274e-06,
"loss": 4.259,
"step": 674
},
{
"epoch": 0.9048257372654156,
"grad_norm": 2.031643867492676,
"learning_rate": 1.109202612147589e-06,
"loss": 4.2252,
"step": 675
},
{
"epoch": 0.9061662198391421,
"grad_norm": 1.9987703561782837,
"learning_rate": 1.078402531282116e-06,
"loss": 3.9663,
"step": 676
},
{
"epoch": 0.9075067024128687,
"grad_norm": 1.4590847492218018,
"learning_rate": 1.0480266904290298e-06,
"loss": 3.8881,
"step": 677
},
{
"epoch": 0.9088471849865952,
"grad_norm": 1.8944475650787354,
"learning_rate": 1.018075628291787e-06,
"loss": 3.9444,
"step": 678
},
{
"epoch": 0.9101876675603218,
"grad_norm": 1.3491789102554321,
"learning_rate": 9.885498760405481e-07,
"loss": 4.0536,
"step": 679
},
{
"epoch": 0.9115281501340483,
"grad_norm": 1.6329096555709839,
"learning_rate": 9.59449957302791e-07,
"loss": 4.1612,
"step": 680
},
{
"epoch": 0.9128686327077749,
"grad_norm": 1.457969069480896,
"learning_rate": 9.307763881539839e-07,
"loss": 4.1119,
"step": 681
},
{
"epoch": 0.9142091152815014,
"grad_norm": 1.6089447736740112,
"learning_rate": 9.025296771084768e-07,
"loss": 4.1044,
"step": 682
},
{
"epoch": 0.9155495978552279,
"grad_norm": 1.8320618867874146,
"learning_rate": 8.747103251104394e-07,
"loss": 4.1481,
"step": 683
},
{
"epoch": 0.9168900804289544,
"grad_norm": 1.648786187171936,
"learning_rate": 8.473188255250203e-07,
"loss": 3.9891,
"step": 684
},
{
"epoch": 0.9182305630026809,
"grad_norm": 1.6430078744888306,
"learning_rate": 8.203556641295601e-07,
"loss": 4.4098,
"step": 685
},
{
"epoch": 0.9195710455764075,
"grad_norm": 1.3675403594970703,
"learning_rate": 7.938213191049953e-07,
"loss": 4.0304,
"step": 686
},
{
"epoch": 0.920911528150134,
"grad_norm": 1.7190208435058594,
"learning_rate": 7.677162610273819e-07,
"loss": 3.788,
"step": 687
},
{
"epoch": 0.9222520107238605,
"grad_norm": 1.8116778135299683,
"learning_rate": 7.420409528595296e-07,
"loss": 4.1156,
"step": 688
},
{
"epoch": 0.9235924932975871,
"grad_norm": 1.9070864915847778,
"learning_rate": 7.167958499428196e-07,
"loss": 4.1029,
"step": 689
},
{
"epoch": 0.9249329758713136,
"grad_norm": 1.6403416395187378,
"learning_rate": 6.919813999891028e-07,
"loss": 4.1598,
"step": 690
},
{
"epoch": 0.9262734584450402,
"grad_norm": 1.574585199356079,
"learning_rate": 6.675980430727758e-07,
"loss": 4.3613,
"step": 691
},
{
"epoch": 0.9276139410187667,
"grad_norm": 1.9115116596221924,
"learning_rate": 6.436462116229725e-07,
"loss": 4.2608,
"step": 692
},
{
"epoch": 0.9289544235924933,
"grad_norm": 1.822980523109436,
"learning_rate": 6.201263304158905e-07,
"loss": 4.1126,
"step": 693
},
{
"epoch": 0.9302949061662198,
"grad_norm": 1.3983780145645142,
"learning_rate": 5.970388165672691e-07,
"loss": 3.9964,
"step": 694
},
{
"epoch": 0.9316353887399463,
"grad_norm": 1.9300884008407593,
"learning_rate": 5.743840795249727e-07,
"loss": 3.8454,
"step": 695
},
{
"epoch": 0.9329758713136729,
"grad_norm": 1.8419654369354248,
"learning_rate": 5.521625210617553e-07,
"loss": 4.0762,
"step": 696
},
{
"epoch": 0.9343163538873994,
"grad_norm": 1.751046061515808,
"learning_rate": 5.30374535268105e-07,
"loss": 4.1852,
"step": 697
},
{
"epoch": 0.935656836461126,
"grad_norm": 2.3287787437438965,
"learning_rate": 5.090205085452909e-07,
"loss": 3.8736,
"step": 698
},
{
"epoch": 0.9369973190348525,
"grad_norm": 1.5687111616134644,
"learning_rate": 4.881008195984693e-07,
"loss": 3.9057,
"step": 699
},
{
"epoch": 0.938337801608579,
"grad_norm": 1.934680461883545,
"learning_rate": 4.676158394300051e-07,
"loss": 3.8041,
"step": 700
},
{
"epoch": 0.9396782841823056,
"grad_norm": 1.6318399906158447,
"learning_rate": 4.475659313328745e-07,
"loss": 3.8188,
"step": 701
},
{
"epoch": 0.9410187667560321,
"grad_norm": 1.4505863189697266,
"learning_rate": 4.279514508842092e-07,
"loss": 3.9981,
"step": 702
},
{
"epoch": 0.9423592493297587,
"grad_norm": 1.3285362720489502,
"learning_rate": 4.0877274593902335e-07,
"loss": 4.3346,
"step": 703
},
{
"epoch": 0.9436997319034852,
"grad_norm": 2.0423738956451416,
"learning_rate": 3.900301566240161e-07,
"loss": 4.1022,
"step": 704
},
{
"epoch": 0.9450402144772118,
"grad_norm": 1.565425992012024,
"learning_rate": 3.7172401533154823e-07,
"loss": 4.3183,
"step": 705
},
{
"epoch": 0.9463806970509383,
"grad_norm": 1.874189853668213,
"learning_rate": 3.5385464671375266e-07,
"loss": 4.0596,
"step": 706
},
{
"epoch": 0.9477211796246648,
"grad_norm": 1.5646862983703613,
"learning_rate": 3.364223676767725e-07,
"loss": 3.9984,
"step": 707
},
{
"epoch": 0.9490616621983914,
"grad_norm": 1.845935583114624,
"learning_rate": 3.194274873751374e-07,
"loss": 4.2646,
"step": 708
},
{
"epoch": 0.9504021447721179,
"grad_norm": 2.1210970878601074,
"learning_rate": 3.0287030720628774e-07,
"loss": 3.8583,
"step": 709
},
{
"epoch": 0.9517426273458445,
"grad_norm": 1.6326839923858643,
"learning_rate": 2.867511208052315e-07,
"loss": 4.2113,
"step": 710
},
{
"epoch": 0.953083109919571,
"grad_norm": 1.8023695945739746,
"learning_rate": 2.710702140393151e-07,
"loss": 3.935,
"step": 711
},
{
"epoch": 0.9544235924932976,
"grad_norm": 1.5123698711395264,
"learning_rate": 2.558278650031887e-07,
"loss": 4.007,
"step": 712
},
{
"epoch": 0.9557640750670241,
"grad_norm": 2.063042163848877,
"learning_rate": 2.410243440138432e-07,
"loss": 3.9025,
"step": 713
},
{
"epoch": 0.9571045576407506,
"grad_norm": 1.3973208665847778,
"learning_rate": 2.266599136058367e-07,
"loss": 3.9194,
"step": 714
},
{
"epoch": 0.9584450402144772,
"grad_norm": 2.1018564701080322,
"learning_rate": 2.1273482852662007e-07,
"loss": 3.8329,
"step": 715
},
{
"epoch": 0.9597855227882037,
"grad_norm": 1.4930899143218994,
"learning_rate": 1.9924933573204352e-07,
"loss": 4.3282,
"step": 716
},
{
"epoch": 0.9611260053619303,
"grad_norm": 1.8336726427078247,
"learning_rate": 1.8620367438194897e-07,
"loss": 4.0716,
"step": 717
},
{
"epoch": 0.9624664879356568,
"grad_norm": 1.7525848150253296,
"learning_rate": 1.73598075835954e-07,
"loss": 4.3068,
"step": 718
},
{
"epoch": 0.9638069705093834,
"grad_norm": 2.3989834785461426,
"learning_rate": 1.6143276364933292e-07,
"loss": 4.1048,
"step": 719
},
{
"epoch": 0.9651474530831099,
"grad_norm": 1.8317017555236816,
"learning_rate": 1.497079535690532e-07,
"loss": 4.1938,
"step": 720
},
{
"epoch": 0.9664879356568364,
"grad_norm": 1.3087552785873413,
"learning_rate": 1.3842385352995923e-07,
"loss": 4.2681,
"step": 721
},
{
"epoch": 0.967828418230563,
"grad_norm": 1.7893511056900024,
"learning_rate": 1.2758066365107514e-07,
"loss": 4.1186,
"step": 722
},
{
"epoch": 0.9691689008042895,
"grad_norm": 1.495792031288147,
"learning_rate": 1.1717857623205764e-07,
"loss": 3.9886,
"step": 723
},
{
"epoch": 0.9705093833780161,
"grad_norm": 1.5346589088439941,
"learning_rate": 1.0721777574978775e-07,
"loss": 4.0355,
"step": 724
},
{
"epoch": 0.9718498659517426,
"grad_norm": 1.4128694534301758,
"learning_rate": 9.769843885509834e-08,
"loss": 4.3073,
"step": 725
},
{
"epoch": 0.9731903485254692,
"grad_norm": 1.714119553565979,
"learning_rate": 8.862073436964324e-08,
"loss": 4.0481,
"step": 726
},
{
"epoch": 0.9745308310991957,
"grad_norm": 1.435090184211731,
"learning_rate": 7.998482328289703e-08,
"loss": 3.8309,
"step": 727
},
{
"epoch": 0.9758713136729222,
"grad_norm": 1.8121684789657593,
"learning_rate": 7.179085874930713e-08,
"loss": 3.9464,
"step": 728
},
{
"epoch": 0.9772117962466488,
"grad_norm": 2.054342269897461,
"learning_rate": 6.403898608557391e-08,
"loss": 3.8396,
"step": 729
},
{
"epoch": 0.9785522788203753,
"grad_norm": 2.2567222118377686,
"learning_rate": 5.672934276807762e-08,
"loss": 3.9102,
"step": 730
},
{
"epoch": 0.9798927613941019,
"grad_norm": 1.64995539188385,
"learning_rate": 4.9862058430427685e-08,
"loss": 3.7965,
"step": 731
},
{
"epoch": 0.9812332439678284,
"grad_norm": 1.4625040292739868,
"learning_rate": 4.343725486118666e-08,
"loss": 4.0566,
"step": 732
},
{
"epoch": 0.982573726541555,
"grad_norm": 1.3524330854415894,
"learning_rate": 3.745504600168315e-08,
"loss": 4.098,
"step": 733
},
{
"epoch": 0.9839142091152815,
"grad_norm": 1.7329251766204834,
"learning_rate": 3.191553794401336e-08,
"loss": 4.1363,
"step": 734
},
{
"epoch": 0.985254691689008,
"grad_norm": 1.5572080612182617,
"learning_rate": 2.681882892914822e-08,
"loss": 4.2099,
"step": 735
},
{
"epoch": 0.9865951742627346,
"grad_norm": 1.7131426334381104,
"learning_rate": 2.216500934519583e-08,
"loss": 4.3434,
"step": 736
},
{
"epoch": 0.9879356568364611,
"grad_norm": 1.6540027856826782,
"learning_rate": 1.7954161725791674e-08,
"loss": 4.1726,
"step": 737
},
{
"epoch": 0.9892761394101877,
"grad_norm": 2.0801782608032227,
"learning_rate": 1.4186360748644212e-08,
"loss": 4.1129,
"step": 738
},
{
"epoch": 0.9906166219839142,
"grad_norm": 1.5830508470535278,
"learning_rate": 1.0861673234205394e-08,
"loss": 4.0883,
"step": 739
},
{
"epoch": 0.9919571045576407,
"grad_norm": 1.6722745895385742,
"learning_rate": 7.98015814448272e-09,
"loss": 4.1126,
"step": 740
},
{
"epoch": 0.9932975871313673,
"grad_norm": 1.443785309791565,
"learning_rate": 5.541866582003952e-09,
"loss": 4.2395,
"step": 741
},
{
"epoch": 0.9946380697050938,
"grad_norm": 1.4968252182006836,
"learning_rate": 3.5468417888956386e-09,
"loss": 4.2435,
"step": 742
},
{
"epoch": 0.9959785522788204,
"grad_norm": 1.835752248764038,
"learning_rate": 1.9951191461281547e-09,
"loss": 4.1708,
"step": 743
},
{
"epoch": 0.9973190348525469,
"grad_norm": 1.7169502973556519,
"learning_rate": 8.867261728912057e-10,
"loss": 4.2061,
"step": 744
},
{
"epoch": 0.9986595174262735,
"grad_norm": 1.7341909408569336,
"learning_rate": 2.216825260858979e-10,
"loss": 4.1109,
"step": 745
},
{
"epoch": 1.0,
"grad_norm": 1.789974331855774,
"learning_rate": 0.0,
"loss": 3.9941,
"step": 746
}
],
"logging_steps": 1,
"max_steps": 746,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 12000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 9240588194414592.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}